From 8d00a6c8f6b08e7167bc03bf955cdc7e47c5132e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 22 Jul 2008 08:39:57 +0200
Subject: genirq: remove last NO_IDLE_HZ leftovers

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 8ccb462ea42c..f3047df2d23c 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -197,10 +197,6 @@ extern int setup_irq(unsigned int irq, struct irqaction *new);
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 
-#ifndef handle_dynamic_tick
-# define handle_dynamic_tick(a)		do { } while (0)
-#endif
-
 #ifdef CONFIG_SMP
 
 #if defined(CONFIG_GENERIC_PENDING_IRQ) || defined(CONFIG_IRQBALANCE)
-- 
cgit v1.2.3


From feb2f55db45919aa80731f8877b60cab454b7b94 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <ext-adrian.hunter@nokia.com>
Date: Fri, 1 Aug 2008 11:53:29 +0300
Subject: [MTD] [OneNAND] Add defines for HF and sync write

Signed-off-by: Adrian Hunter <ext-adrian.hunter@nokia.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 include/linux/mtd/onenand_regs.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/mtd/onenand_regs.h b/include/linux/mtd/onenand_regs.h
index d1b310c92eb4..0c6bbe28f38c 100644
--- a/include/linux/mtd/onenand_regs.h
+++ b/include/linux/mtd/onenand_regs.h
@@ -152,6 +152,8 @@
 #define ONENAND_SYS_CFG1_INT		(1 << 6)
 #define ONENAND_SYS_CFG1_IOBE		(1 << 5)
 #define ONENAND_SYS_CFG1_RDY_CONF	(1 << 4)
+#define ONENAND_SYS_CFG1_HF		(1 << 2)
+#define ONENAND_SYS_CFG1_SYNC_WRITE	(1 << 1)
 
 /*
  * Controller Status Register F240h (R)
-- 
cgit v1.2.3


From 2e489e077a6ad118c4f247faedf330117b107cce Mon Sep 17 00:00:00 2001
From: Alexey Korolev <akorolev@infradead.org>
Date: Tue, 5 Aug 2008 16:39:42 +0100
Subject: [MTD] [NOR] Add qry_mode_on()/qry_omde_off() to deal with odd chips

There are some CFI chips which require non standard procedures to get
into QRY mode. The possible way to support them would be trying
different modes till QRY will be read. This patch introduce two new
functions qry_mode_on qry_mode_off. qry_mode_on tries different commands
in order switch chip into QRY mode.

So if we have one more "odd" chip - we just could add several lines to
qry_mode_on. Also using these functions remove unnecessary code
duplicaton in porbe procedure.

Currently there are two "odd" cases
1. Some old intel chips which require 0xFF before 0x98
2. ST M29DW chip which requires 0x98 to be sent at 0x555 (according to
CFI should be 0x55)

This patch is partialy based on the patch from Uwe
(see "[PATCH 2/4] [RFC][MTD] cfi_probe: remove Intel chip workaround"
thread )

Signed-off-by: Alexey Korolev <akorolev@infradead.org>
Signed-off-by: Alexander Belyakov <abelyako@gmail.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/mtd/chips/cfi_probe.c | 52 +++++-------------------------------
 drivers/mtd/chips/cfi_util.c  | 62 ++++++++++++++++++++++++++++++++++++++++---
 include/linux/mtd/cfi.h       |  9 ++++++-
 3 files changed, 73 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/chips/cfi_probe.c b/drivers/mtd/chips/cfi_probe.c
index c418e92e1d92..e706be2ad0cb 100644
--- a/drivers/mtd/chips/cfi_probe.c
+++ b/drivers/mtd/chips/cfi_probe.c
@@ -44,17 +44,14 @@ do { \
 
 #define xip_enable(base, map, cfi) \
 do { \
-	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); \
-	cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL); \
+	qry_mode_off(base, map, cfi); \
 	xip_allowed(base, map); \
 } while (0)
 
 #define xip_disable_qry(base, map, cfi) \
 do { \
 	xip_disable(); \
-	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL); \
-	cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL); \
-	cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL); \
+	qry_mode_on(base, map, cfi); \
 } while (0)
 
 #else
@@ -70,32 +67,6 @@ do { \
    in: interleave,type,mode
    ret: table index, <0 for error
  */
-static int __xipram qry_present(struct map_info *map, __u32 base,
-				struct cfi_private *cfi)
-{
-	int osf = cfi->interleave * cfi->device_type;	// scale factor
-	map_word val[3];
-	map_word qry[3];
-
-	qry[0] = cfi_build_cmd('Q', map, cfi);
-	qry[1] = cfi_build_cmd('R', map, cfi);
-	qry[2] = cfi_build_cmd('Y', map, cfi);
-
-	val[0] = map_read(map, base + osf*0x10);
-	val[1] = map_read(map, base + osf*0x11);
-	val[2] = map_read(map, base + osf*0x12);
-
-	if (!map_word_equal(map, qry[0], val[0]))
-		return 0;
-
-	if (!map_word_equal(map, qry[1], val[1]))
-		return 0;
-
-	if (!map_word_equal(map, qry[2], val[2]))
-		return 0;
-
-	return 1; 	// "QRY" found
-}
 
 static int __xipram cfi_probe_chip(struct map_info *map, __u32 base,
 				   unsigned long *chip_map, struct cfi_private *cfi)
@@ -116,11 +87,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base,
 	}
 
 	xip_disable();
-	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
-	cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL);
-	cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL);
-
-	if (!qry_present(map,base,cfi)) {
+	if (!qry_mode_on(base, map, cfi)) {
 		xip_enable(base, map, cfi);
 		return 0;
 	}
@@ -144,8 +111,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base,
 		if (qry_present(map, start, cfi)) {
 			/* Eep. This chip also had the QRY marker.
 			 * Is it an alias for the new one? */
-			cfi_send_gen_cmd(0xF0, 0, start, map, cfi, cfi->device_type, NULL);
-			cfi_send_gen_cmd(0xFF, 0, start, map, cfi, cfi->device_type, NULL);
+			qry_mode_off(start, map, cfi);
 
 			/* If the QRY marker goes away, it's an alias */
 			if (!qry_present(map, start, cfi)) {
@@ -158,8 +124,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base,
 			 * unfortunate. Stick the new chip in read mode
 			 * too and if it's the same, assume it's an alias. */
 			/* FIXME: Use other modes to do a proper check */
-			cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
-			cfi_send_gen_cmd(0xFF, 0, start, map, cfi, cfi->device_type, NULL);
+			qry_mode_off(base, map, cfi);
 
 			if (qry_present(map, base, cfi)) {
 				xip_allowed(base, map);
@@ -176,8 +141,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base,
 	cfi->numchips++;
 
 	/* Put it back into Read Mode */
-	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
-	cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL);
+	qry_mode_off(base, map, cfi);
 	xip_allowed(base, map);
 
 	printk(KERN_INFO "%s: Found %d x%d devices at 0x%x in %d-bit bank\n",
@@ -237,9 +201,7 @@ static int __xipram cfi_chip_setup(struct map_info *map,
 			  cfi_read_query(map, base + 0xf * ofs_factor);
 
 	/* Put it back into Read Mode */
-	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
-	/* ... even if it's an Intel chip */
-	cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL);
+	qry_mode_off(base, map, cfi);
 	xip_allowed(base, map);
 
 	/* Do any necessary byteswapping */
diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c
index 0ee457018016..8d7553670526 100644
--- a/drivers/mtd/chips/cfi_util.c
+++ b/drivers/mtd/chips/cfi_util.c
@@ -24,6 +24,62 @@
 #include <linux/mtd/cfi.h>
 #include <linux/mtd/compatmac.h>
 
+int __xipram qry_present(struct map_info *map, __u32 base,
+				struct cfi_private *cfi)
+{
+	int osf = cfi->interleave * cfi->device_type;	/* scale factor */
+	map_word val[3];
+	map_word qry[3];
+
+	qry[0] = cfi_build_cmd('Q', map, cfi);
+	qry[1] = cfi_build_cmd('R', map, cfi);
+	qry[2] = cfi_build_cmd('Y', map, cfi);
+
+	val[0] = map_read(map, base + osf*0x10);
+	val[1] = map_read(map, base + osf*0x11);
+	val[2] = map_read(map, base + osf*0x12);
+
+	if (!map_word_equal(map, qry[0], val[0]))
+		return 0;
+
+	if (!map_word_equal(map, qry[1], val[1]))
+		return 0;
+
+	if (!map_word_equal(map, qry[2], val[2]))
+		return 0;
+
+	return 1; 	/* "QRY" found */
+}
+
+int __xipram qry_mode_on(uint32_t base, struct map_info *map,
+				struct cfi_private *cfi)
+{
+	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
+	cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL);
+	if (qry_present(map, base, cfi))
+		return 1;
+	/* QRY not found probably we deal with some odd CFI chips */
+	/* Some revisions of some old Intel chips? */
+	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
+	cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL);
+	cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL);
+	if (qry_present(map, base, cfi))
+		return 1;
+	/* ST M29DW chips */
+	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
+	cfi_send_gen_cmd(0x98, 0x555, base, map, cfi, cfi->device_type, NULL);
+	if (qry_present(map, base, cfi))
+		return 1;
+	/* QRY not found */
+	return 0;
+}
+void __xipram qry_mode_off(uint32_t base, struct map_info *map,
+				struct cfi_private *cfi)
+{
+	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
+	cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL);
+}
+
 struct cfi_extquery *
 __xipram cfi_read_pri(struct map_info *map, __u16 adr, __u16 size, const char* name)
 {
@@ -48,8 +104,7 @@ __xipram cfi_read_pri(struct map_info *map, __u16 adr, __u16 size, const char* n
 #endif
 
 	/* Switch it into Query Mode */
-	cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL);
-
+	qry_mode_on(base, map, cfi);
 	/* Read in the Extended Query Table */
 	for (i=0; i<size; i++) {
 		((unsigned char *)extp)[i] =
@@ -57,8 +112,7 @@ __xipram cfi_read_pri(struct map_info *map, __u16 adr, __u16 size, const char* n
 	}
 
 	/* Make sure it returns to read mode */
-	cfi_send_gen_cmd(0xf0, 0, base, map, cfi, cfi->device_type, NULL);
-	cfi_send_gen_cmd(0xff, 0, base, map, cfi, cfi->device_type, NULL);
+	qry_mode_off(base, map, cfi);
 
 #ifdef CONFIG_MTD_XIP
 	(void) map_read(map, base);
diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h
index d6fb115f5a07..3058917d7b92 100644
--- a/include/linux/mtd/cfi.h
+++ b/include/linux/mtd/cfi.h
@@ -12,6 +12,7 @@
 #include <linux/mtd/flashchip.h>
 #include <linux/mtd/map.h>
 #include <linux/mtd/cfi_endian.h>
+#include <linux/mtd/xip.h>
 
 #ifdef CONFIG_MTD_CFI_I1
 #define cfi_interleave(cfi) 1
@@ -430,7 +431,6 @@ static inline uint32_t cfi_send_gen_cmd(u_char cmd, uint32_t cmd_addr, uint32_t
 {
 	map_word val;
 	uint32_t addr = base + cfi_build_cmd_addr(cmd_addr, cfi_interleave(cfi), type);
-
 	val = cfi_build_cmd(cmd, map, cfi);
 
 	if (prev_val)
@@ -483,6 +483,13 @@ static inline void cfi_udelay(int us)
 	}
 }
 
+int __xipram qry_present(struct map_info *map, __u32 base,
+				struct cfi_private *cfi);
+int __xipram qry_mode_on(uint32_t base, struct map_info *map,
+				struct cfi_private *cfi);
+void __xipram qry_mode_off(uint32_t base, struct map_info *map,
+				struct cfi_private *cfi);
+
 struct cfi_extquery *cfi_read_pri(struct map_info *map, uint16_t adr, uint16_t size,
 			     const char* name);
 struct cfi_fixup {
-- 
cgit v1.2.3


From e93cafe45fd74935e0aca2b79e533f0e3ed9640f Mon Sep 17 00:00:00 2001
From: Anders Grafström <grfstrm@users.sourceforge.net>
Date: Tue, 5 Aug 2008 18:37:41 +0200
Subject: [MTD] [NOR] cfi_cmdset_0001: Timeouts for erase, write and unlock
 operations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Timeouts are currently given by the typical operation time times 8.
It works in the general well-behaved case but not when an erase block is
failing. For erase operations, it seems that a failing erase block will
keep the device state machine in erasing state until the vendor
specified maximum timeout period has passed. By this time the driver
would have long since timed out, left erasing state and attempted
further operations which all fail. This patch implements timeouts using
values from the CFI Query structure when available.
The patch also sets a longer timeout for locking operations. The current
value used for locking/unlocking given by 1000000/HZ microseconds is too
short for devices like J3 and J5 Strataflash which have a typical clear
lock-bits time of 0.5 seconds.

Signed-off-by: Anders Grafström <grfstrm@users.sourceforge.net>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/mtd/chips/cfi_cmdset_0001.c | 52 +++++++++++++++++++++++++++----------
 include/linux/mtd/flashchip.h       |  4 +++
 2 files changed, 42 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/chips/cfi_cmdset_0001.c b/drivers/mtd/chips/cfi_cmdset_0001.c
index d49cbe2738a8..5157e3cb4b9e 100644
--- a/drivers/mtd/chips/cfi_cmdset_0001.c
+++ b/drivers/mtd/chips/cfi_cmdset_0001.c
@@ -478,6 +478,28 @@ struct mtd_info *cfi_cmdset_0001(struct map_info *map, int primary)
 		else
 			cfi->chips[i].erase_time = 2000000;
 
+		if (cfi->cfiq->WordWriteTimeoutTyp &&
+		    cfi->cfiq->WordWriteTimeoutMax)
+			cfi->chips[i].word_write_time_max =
+				1<<(cfi->cfiq->WordWriteTimeoutTyp +
+				    cfi->cfiq->WordWriteTimeoutMax);
+		else
+			cfi->chips[i].word_write_time_max = 50000 * 8;
+
+		if (cfi->cfiq->BufWriteTimeoutTyp &&
+		    cfi->cfiq->BufWriteTimeoutMax)
+			cfi->chips[i].buffer_write_time_max =
+				1<<(cfi->cfiq->BufWriteTimeoutTyp +
+				    cfi->cfiq->BufWriteTimeoutMax);
+
+		if (cfi->cfiq->BlockEraseTimeoutTyp &&
+		    cfi->cfiq->BlockEraseTimeoutMax)
+			cfi->chips[i].erase_time_max =
+				1000<<(cfi->cfiq->BlockEraseTimeoutTyp +
+				       cfi->cfiq->BlockEraseTimeoutMax);
+		else
+			cfi->chips[i].erase_time_max = 2000000 * 8;
+
 		cfi->chips[i].ref_point_counter = 0;
 		init_waitqueue_head(&(cfi->chips[i].wq));
 	}
@@ -1012,7 +1034,7 @@ static void __xipram xip_enable(struct map_info *map, struct flchip *chip,
 
 static int __xipram xip_wait_for_operation(
 		struct map_info *map, struct flchip *chip,
-		unsigned long adr, unsigned int chip_op_time )
+		unsigned long adr, unsigned int chip_op_time_max)
 {
 	struct cfi_private *cfi = map->fldrv_priv;
 	struct cfi_pri_intelext *cfip = cfi->cmdset_priv;
@@ -1021,7 +1043,7 @@ static int __xipram xip_wait_for_operation(
 	flstate_t oldstate, newstate;
 
        	start = xip_currtime();
-	usec = chip_op_time * 8;
+	usec = chip_op_time_max;
 	if (usec == 0)
 		usec = 500000;
 	done = 0;
@@ -1131,8 +1153,8 @@ static int __xipram xip_wait_for_operation(
 #define XIP_INVAL_CACHED_RANGE(map, from, size)  \
 	INVALIDATE_CACHED_RANGE(map, from, size)
 
-#define INVAL_CACHE_AND_WAIT(map, chip, cmd_adr, inval_adr, inval_len, usec) \
-	xip_wait_for_operation(map, chip, cmd_adr, usec)
+#define INVAL_CACHE_AND_WAIT(map, chip, cmd_adr, inval_adr, inval_len, usec, usec_max) \
+	xip_wait_for_operation(map, chip, cmd_adr, usec_max)
 
 #else
 
@@ -1144,7 +1166,7 @@ static int __xipram xip_wait_for_operation(
 static int inval_cache_and_wait_for_operation(
 		struct map_info *map, struct flchip *chip,
 		unsigned long cmd_adr, unsigned long inval_adr, int inval_len,
-		unsigned int chip_op_time)
+		unsigned int chip_op_time, unsigned int chip_op_time_max)
 {
 	struct cfi_private *cfi = map->fldrv_priv;
 	map_word status, status_OK = CMD(0x80);
@@ -1156,8 +1178,7 @@ static int inval_cache_and_wait_for_operation(
 		INVALIDATE_CACHED_RANGE(map, inval_adr, inval_len);
 	spin_lock(chip->mutex);
 
-	/* set our timeout to 8 times the expected delay */
-	timeo = chip_op_time * 8;
+	timeo = chip_op_time_max;
 	if (!timeo)
 		timeo = 500000;
 	reset_timeo = timeo;
@@ -1217,8 +1238,8 @@ static int inval_cache_and_wait_for_operation(
 
 #endif
 
-#define WAIT_TIMEOUT(map, chip, adr, udelay) \
-	INVAL_CACHE_AND_WAIT(map, chip, adr, 0, 0, udelay);
+#define WAIT_TIMEOUT(map, chip, adr, udelay, udelay_max) \
+	INVAL_CACHE_AND_WAIT(map, chip, adr, 0, 0, udelay, udelay_max);
 
 
 static int do_point_onechip (struct map_info *map, struct flchip *chip, loff_t adr, size_t len)
@@ -1452,7 +1473,8 @@ static int __xipram do_write_oneword(struct map_info *map, struct flchip *chip,
 
 	ret = INVAL_CACHE_AND_WAIT(map, chip, adr,
 				   adr, map_bankwidth(map),
-				   chip->word_write_time);
+				   chip->word_write_time,
+				   chip->word_write_time_max);
 	if (ret) {
 		xip_enable(map, chip, adr);
 		printk(KERN_ERR "%s: word write error (status timeout)\n", map->name);
@@ -1623,7 +1645,7 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip,
 
 	chip->state = FL_WRITING_TO_BUFFER;
 	map_write(map, write_cmd, cmd_adr);
-	ret = WAIT_TIMEOUT(map, chip, cmd_adr, 0);
+	ret = WAIT_TIMEOUT(map, chip, cmd_adr, 0, 0);
 	if (ret) {
 		/* Argh. Not ready for write to buffer */
 		map_word Xstatus = map_read(map, cmd_adr);
@@ -1692,7 +1714,8 @@ static int __xipram do_write_buffer(struct map_info *map, struct flchip *chip,
 
 	ret = INVAL_CACHE_AND_WAIT(map, chip, cmd_adr,
 				   initial_adr, initial_len,
-				   chip->buffer_write_time);
+				   chip->buffer_write_time,
+				   chip->buffer_write_time_max);
 	if (ret) {
 		map_write(map, CMD(0x70), cmd_adr);
 		chip->state = FL_STATUS;
@@ -1827,7 +1850,8 @@ static int __xipram do_erase_oneblock(struct map_info *map, struct flchip *chip,
 
 	ret = INVAL_CACHE_AND_WAIT(map, chip, adr,
 				   adr, len,
-				   chip->erase_time);
+				   chip->erase_time,
+				   chip->erase_time_max);
 	if (ret) {
 		map_write(map, CMD(0x70), adr);
 		chip->state = FL_STATUS;
@@ -2006,7 +2030,7 @@ static int __xipram do_xxlock_oneblock(struct map_info *map, struct flchip *chip
 	 */
 	udelay = (!extp || !(extp->FeatureSupport & (1 << 5))) ? 1000000/HZ : 0;
 
-	ret = WAIT_TIMEOUT(map, chip, adr, udelay);
+	ret = WAIT_TIMEOUT(map, chip, adr, udelay, udelay * 100);
 	if (ret) {
 		map_write(map, CMD(0x70), adr);
 		chip->state = FL_STATUS;
diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h
index 08dd131301c1..d4f38c5fd44e 100644
--- a/include/linux/mtd/flashchip.h
+++ b/include/linux/mtd/flashchip.h
@@ -73,6 +73,10 @@ struct flchip {
 	int buffer_write_time;
 	int erase_time;
 
+	int word_write_time_max;
+	int buffer_write_time_max;
+	int erase_time_max;
+
 	void *priv;
 };
 
-- 
cgit v1.2.3


From c314dfdc358847eef0fc07ec8682e1acc8cadd00 Mon Sep 17 00:00:00 2001
From: David Woodhouse <David.Woodhouse@intel.com>
Date: Thu, 7 Aug 2008 11:55:07 +0100
Subject: [MTD] [NOR] Rename and export new cfi_qry_*() functions

They need to be exported, so let's give them less generic-sounding names
while we're at it.

Original export patch, along with the suggestion about the nomenclature,
from Stephen Rothwell.

Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/mtd/chips/cfi_probe.c | 20 ++++++++++----------
 drivers/mtd/chips/cfi_util.c  | 26 +++++++++++++++-----------
 include/linux/mtd/cfi.h       | 12 ++++++------
 3 files changed, 31 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/chips/cfi_probe.c b/drivers/mtd/chips/cfi_probe.c
index e706be2ad0cb..e63e6749429a 100644
--- a/drivers/mtd/chips/cfi_probe.c
+++ b/drivers/mtd/chips/cfi_probe.c
@@ -44,14 +44,14 @@ do { \
 
 #define xip_enable(base, map, cfi) \
 do { \
-	qry_mode_off(base, map, cfi); \
+	cfi_qry_mode_off(base, map, cfi);		\
 	xip_allowed(base, map); \
 } while (0)
 
 #define xip_disable_qry(base, map, cfi) \
 do { \
 	xip_disable(); \
-	qry_mode_on(base, map, cfi); \
+	cfi_qry_mode_on(base, map, cfi); \
 } while (0)
 
 #else
@@ -87,7 +87,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base,
 	}
 
 	xip_disable();
-	if (!qry_mode_on(base, map, cfi)) {
+	if (!cfi_qry_mode_on(base, map, cfi)) {
 		xip_enable(base, map, cfi);
 		return 0;
 	}
@@ -108,13 +108,13 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base,
  		start = i << cfi->chipshift;
 		/* This chip should be in read mode if it's one
 		   we've already touched. */
-		if (qry_present(map, start, cfi)) {
+		if (cfi_qry_present(map, start, cfi)) {
 			/* Eep. This chip also had the QRY marker.
 			 * Is it an alias for the new one? */
-			qry_mode_off(start, map, cfi);
+			cfi_qry_mode_off(start, map, cfi);
 
 			/* If the QRY marker goes away, it's an alias */
-			if (!qry_present(map, start, cfi)) {
+			if (!cfi_qry_present(map, start, cfi)) {
 				xip_allowed(base, map);
 				printk(KERN_DEBUG "%s: Found an alias at 0x%x for the chip at 0x%lx\n",
 				       map->name, base, start);
@@ -124,9 +124,9 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base,
 			 * unfortunate. Stick the new chip in read mode
 			 * too and if it's the same, assume it's an alias. */
 			/* FIXME: Use other modes to do a proper check */
-			qry_mode_off(base, map, cfi);
+			cfi_qry_mode_off(base, map, cfi);
 
-			if (qry_present(map, base, cfi)) {
+			if (cfi_qry_present(map, base, cfi)) {
 				xip_allowed(base, map);
 				printk(KERN_DEBUG "%s: Found an alias at 0x%x for the chip at 0x%lx\n",
 				       map->name, base, start);
@@ -141,7 +141,7 @@ static int __xipram cfi_probe_chip(struct map_info *map, __u32 base,
 	cfi->numchips++;
 
 	/* Put it back into Read Mode */
-	qry_mode_off(base, map, cfi);
+	cfi_qry_mode_off(base, map, cfi);
 	xip_allowed(base, map);
 
 	printk(KERN_INFO "%s: Found %d x%d devices at 0x%x in %d-bit bank\n",
@@ -201,7 +201,7 @@ static int __xipram cfi_chip_setup(struct map_info *map,
 			  cfi_read_query(map, base + 0xf * ofs_factor);
 
 	/* Put it back into Read Mode */
-	qry_mode_off(base, map, cfi);
+	cfi_qry_mode_off(base, map, cfi);
 	xip_allowed(base, map);
 
 	/* Do any necessary byteswapping */
diff --git a/drivers/mtd/chips/cfi_util.c b/drivers/mtd/chips/cfi_util.c
index 8d7553670526..34d40e25d312 100644
--- a/drivers/mtd/chips/cfi_util.c
+++ b/drivers/mtd/chips/cfi_util.c
@@ -24,8 +24,8 @@
 #include <linux/mtd/cfi.h>
 #include <linux/mtd/compatmac.h>
 
-int __xipram qry_present(struct map_info *map, __u32 base,
-				struct cfi_private *cfi)
+int __xipram cfi_qry_present(struct map_info *map, __u32 base,
+			     struct cfi_private *cfi)
 {
 	int osf = cfi->interleave * cfi->device_type;	/* scale factor */
 	map_word val[3];
@@ -50,35 +50,39 @@ int __xipram qry_present(struct map_info *map, __u32 base,
 
 	return 1; 	/* "QRY" found */
 }
+EXPORT_SYMBOL_GPL(cfi_qry_present);
 
-int __xipram qry_mode_on(uint32_t base, struct map_info *map,
-				struct cfi_private *cfi)
+int __xipram cfi_qry_mode_on(uint32_t base, struct map_info *map,
+			     struct cfi_private *cfi)
 {
 	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
 	cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL);
-	if (qry_present(map, base, cfi))
+	if (cfi_qry_present(map, base, cfi))
 		return 1;
 	/* QRY not found probably we deal with some odd CFI chips */
 	/* Some revisions of some old Intel chips? */
 	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
 	cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL);
 	cfi_send_gen_cmd(0x98, 0x55, base, map, cfi, cfi->device_type, NULL);
-	if (qry_present(map, base, cfi))
+	if (cfi_qry_present(map, base, cfi))
 		return 1;
 	/* ST M29DW chips */
 	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
 	cfi_send_gen_cmd(0x98, 0x555, base, map, cfi, cfi->device_type, NULL);
-	if (qry_present(map, base, cfi))
+	if (cfi_qry_present(map, base, cfi))
 		return 1;
 	/* QRY not found */
 	return 0;
 }
-void __xipram qry_mode_off(uint32_t base, struct map_info *map,
-				struct cfi_private *cfi)
+EXPORT_SYMBOL_GPL(cfi_qry_mode_on);
+
+void __xipram cfi_qry_mode_off(uint32_t base, struct map_info *map,
+			       struct cfi_private *cfi)
 {
 	cfi_send_gen_cmd(0xF0, 0, base, map, cfi, cfi->device_type, NULL);
 	cfi_send_gen_cmd(0xFF, 0, base, map, cfi, cfi->device_type, NULL);
 }
+EXPORT_SYMBOL_GPL(cfi_qry_mode_off);
 
 struct cfi_extquery *
 __xipram cfi_read_pri(struct map_info *map, __u16 adr, __u16 size, const char* name)
@@ -104,7 +108,7 @@ __xipram cfi_read_pri(struct map_info *map, __u16 adr, __u16 size, const char* n
 #endif
 
 	/* Switch it into Query Mode */
-	qry_mode_on(base, map, cfi);
+	cfi_qry_mode_on(base, map, cfi);
 	/* Read in the Extended Query Table */
 	for (i=0; i<size; i++) {
 		((unsigned char *)extp)[i] =
@@ -112,7 +116,7 @@ __xipram cfi_read_pri(struct map_info *map, __u16 adr, __u16 size, const char* n
 	}
 
 	/* Make sure it returns to read mode */
-	qry_mode_off(base, map, cfi);
+	cfi_qry_mode_off(base, map, cfi);
 
 #ifdef CONFIG_MTD_XIP
 	(void) map_read(map, base);
diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h
index 3058917d7b92..ee5124ec319e 100644
--- a/include/linux/mtd/cfi.h
+++ b/include/linux/mtd/cfi.h
@@ -483,12 +483,12 @@ static inline void cfi_udelay(int us)
 	}
 }
 
-int __xipram qry_present(struct map_info *map, __u32 base,
-				struct cfi_private *cfi);
-int __xipram qry_mode_on(uint32_t base, struct map_info *map,
-				struct cfi_private *cfi);
-void __xipram qry_mode_off(uint32_t base, struct map_info *map,
-				struct cfi_private *cfi);
+int __xipram cfi_qry_present(struct map_info *map, __u32 base,
+			     struct cfi_private *cfi);
+int __xipram cfi_qry_mode_on(uint32_t base, struct map_info *map,
+			     struct cfi_private *cfi);
+void __xipram cfi_qry_mode_off(uint32_t base, struct map_info *map,
+			       struct cfi_private *cfi);
 
 struct cfi_extquery *cfi_read_pri(struct map_info *map, uint16_t adr, uint16_t size,
 			     const char* name);
-- 
cgit v1.2.3


From bb0eb217c980d50c45f3e793b4dcc70ab9ee820d Mon Sep 17 00:00:00 2001
From: Adrian Hunter <ext-adrian.hunter@nokia.com>
Date: Tue, 12 Aug 2008 12:40:50 +0300
Subject: [MTD] Define and use MTD_FAIL_ADDR_UNKNOWN instead of 0xffffffff

Signed-off-by: Adrian Hunter <ext-adrian.hunter@nokia.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/mtd/mtdconcat.c            | 4 ++--
 drivers/mtd/mtdpart.c              | 4 ++--
 drivers/mtd/nand/nand_base.c       | 2 +-
 drivers/mtd/onenand/onenand_base.c | 2 +-
 fs/jffs2/erase.c                   | 4 ++--
 include/linux/mtd/mtd.h            | 4 +++-
 6 files changed, 11 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/mtdconcat.c b/drivers/mtd/mtdconcat.c
index 2972a5edb73d..789842d0e6f2 100644
--- a/drivers/mtd/mtdconcat.c
+++ b/drivers/mtd/mtdconcat.c
@@ -444,7 +444,7 @@ static int concat_erase(struct mtd_info *mtd, struct erase_info *instr)
 			return -EINVAL;
 	}
 
-	instr->fail_addr = 0xffffffff;
+	instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
 
 	/* make a local copy of instr to avoid modifying the caller's struct */
 	erase = kmalloc(sizeof (struct erase_info), GFP_KERNEL);
@@ -493,7 +493,7 @@ static int concat_erase(struct mtd_info *mtd, struct erase_info *instr)
 			/* sanity check: should never happen since
 			 * block alignment has been checked above */
 			BUG_ON(err == -EINVAL);
-			if (erase->fail_addr != 0xffffffff)
+			if (erase->fail_addr != MTD_FAIL_ADDR_UNKNOWN)
 				instr->fail_addr = erase->fail_addr + offset;
 			break;
 		}
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index edb90b58a9b1..8e77e36e75ee 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -214,7 +214,7 @@ static int part_erase(struct mtd_info *mtd, struct erase_info *instr)
 	instr->addr += part->offset;
 	ret = part->master->erase(part->master, instr);
 	if (ret) {
-		if (instr->fail_addr != 0xffffffff)
+		if (instr->fail_addr != MTD_FAIL_ADDR_UNKNOWN)
 			instr->fail_addr -= part->offset;
 		instr->addr -= part->offset;
 	}
@@ -226,7 +226,7 @@ void mtd_erase_callback(struct erase_info *instr)
 	if (instr->mtd->erase == part_erase) {
 		struct mtd_part *part = PART(instr->mtd);
 
-		if (instr->fail_addr != 0xffffffff)
+		if (instr->fail_addr != MTD_FAIL_ADDR_UNKNOWN)
 			instr->fail_addr -= part->offset;
 		instr->addr -= part->offset;
 	}
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index d1129bae6c27..582280560c89 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2042,7 +2042,7 @@ int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 		return -EINVAL;
 	}
 
-	instr->fail_addr = 0xffffffff;
+	instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
 
 	/* Grab the lock and see if the device is available */
 	nand_get_device(chip, mtd, FL_ERASING);
diff --git a/drivers/mtd/onenand/onenand_base.c b/drivers/mtd/onenand/onenand_base.c
index 926cf3a4135d..90ed319f26e6 100644
--- a/drivers/mtd/onenand/onenand_base.c
+++ b/drivers/mtd/onenand/onenand_base.c
@@ -1794,7 +1794,7 @@ static int onenand_erase(struct mtd_info *mtd, struct erase_info *instr)
 		return -EINVAL;
 	}
 
-	instr->fail_addr = 0xffffffff;
+	instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
 
 	/* Grab the lock and see if the device is available */
 	onenand_get_device(mtd, FL_ERASING);
diff --git a/fs/jffs2/erase.c b/fs/jffs2/erase.c
index dddb2a6c9e2c..259461b910af 100644
--- a/fs/jffs2/erase.c
+++ b/fs/jffs2/erase.c
@@ -68,7 +68,7 @@ static void jffs2_erase_block(struct jffs2_sb_info *c,
 	instr->len = c->sector_size;
 	instr->callback = jffs2_erase_callback;
 	instr->priv = (unsigned long)(&instr[1]);
-	instr->fail_addr = 0xffffffff;
+	instr->fail_addr = MTD_FAIL_ADDR_UNKNOWN;
 
 	((struct erase_priv_struct *)instr->priv)->jeb = jeb;
 	((struct erase_priv_struct *)instr->priv)->c = c;
@@ -175,7 +175,7 @@ static void jffs2_erase_failed(struct jffs2_sb_info *c, struct jffs2_eraseblock
 {
 	/* For NAND, if the failure did not occur at the device level for a
 	   specific physical page, don't bother updating the bad block table. */
-	if (jffs2_cleanmarker_oob(c) && (bad_offset != 0xffffffff)) {
+	if (jffs2_cleanmarker_oob(c) && (bad_offset != MTD_FAIL_ADDR_UNKNOWN)) {
 		/* We had a device-level failure to erase.  Let's see if we've
 		   failed too many times. */
 		if (!jffs2_write_nand_badblock(c, jeb, bad_offset)) {
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 922636548558..eae26bb6430a 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -25,8 +25,10 @@
 #define MTD_ERASE_DONE          0x08
 #define MTD_ERASE_FAILED        0x10
 
+#define MTD_FAIL_ADDR_UNKNOWN 0xffffffff
+
 /* If the erase fails, fail_addr might indicate exactly which block failed.  If
-   fail_addr = 0xffffffff, the failure was not at the device level or was not
+   fail_addr = MTD_FAIL_ADDR_UNKNOWN, the failure was not at the device level or was not
    specific to any particular block. */
 struct erase_info {
 	struct mtd_info *mtd;
-- 
cgit v1.2.3


From 36cd4fb5d277f34fe9e4db0deac2d4efd7dff735 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <ext-adrian.hunter@nokia.com>
Date: Wed, 6 Aug 2008 10:08:46 +0300
Subject: [MTD] [OneNAND] Add OMAP2 / OMAP3 OneNAND driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This driver had resided in the OMAP tree but is now to be in MTD.

Original authors were:
	Jarkko Lavinen <jarkko.lavinen@nokia.com> and Juha Yrjölä
	IRQ and DMA support written by Timo Teras

Signed-off-by: Adrian Hunter <ext-adrian.hunter@nokia.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/mtd/onenand/Kconfig         |   7 +
 drivers/mtd/onenand/Makefile        |   1 +
 drivers/mtd/onenand/omap2.c         | 777 ++++++++++++++++++++++++++++++++++++
 include/asm-arm/arch-omap/onenand.h |   7 +-
 4 files changed, 791 insertions(+), 1 deletion(-)
 create mode 100644 drivers/mtd/onenand/omap2.c

(limited to 'include')

diff --git a/drivers/mtd/onenand/Kconfig b/drivers/mtd/onenand/Kconfig
index b94a61b670d1..79fa79e8f8de 100644
--- a/drivers/mtd/onenand/Kconfig
+++ b/drivers/mtd/onenand/Kconfig
@@ -27,6 +27,13 @@ config MTD_ONENAND_GENERIC
 	help
 	  Support for OneNAND flash via platform device driver.
 
+config MTD_ONENAND_OMAP2
+	tristate "OneNAND on OMAP2/OMAP3 support"
+	depends on MTD_ONENAND && (ARCH_OMAP2 || ARCH_OMAP3)
+	help
+	  Support for a OneNAND flash device connected to an OMAP2/OMAP3 CPU
+	  via the GPMC memory controller.
+
 config MTD_ONENAND_OTP
 	bool "OneNAND OTP Support"
 	select HAVE_MTD_OTP
diff --git a/drivers/mtd/onenand/Makefile b/drivers/mtd/onenand/Makefile
index 4d2eacfd7e11..64b6cc61a520 100644
--- a/drivers/mtd/onenand/Makefile
+++ b/drivers/mtd/onenand/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_MTD_ONENAND)		+= onenand.o
 
 # Board specific.
 obj-$(CONFIG_MTD_ONENAND_GENERIC)	+= generic.o
+obj-$(CONFIG_MTD_ONENAND_OMAP2)		+= omap2.o
 
 # Simulator
 obj-$(CONFIG_MTD_ONENAND_SIM)		+= onenand_sim.o
diff --git a/drivers/mtd/onenand/omap2.c b/drivers/mtd/onenand/omap2.c
new file mode 100644
index 000000000000..40153ace5df6
--- /dev/null
+++ b/drivers/mtd/onenand/omap2.c
@@ -0,0 +1,777 @@
+/*
+ *  linux/drivers/mtd/onenand/omap2.c
+ *
+ *  OneNAND driver for OMAP2 / OMAP3
+ *
+ *  Copyright © 2005-2006 Nokia Corporation
+ *
+ *  Author: Jarkko Lavinen <jarkko.lavinen@nokia.com> and Juha Yrjölä
+ *  IRQ and DMA support written by Timo Teras
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program; see the file COPYING. If not, write to the Free Software
+ * Foundation, 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ */
+
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/onenand.h>
+#include <linux/mtd/partitions.h>
+#include <linux/platform_device.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+
+#include <asm/io.h>
+#include <asm/mach/flash.h>
+#include <asm/arch/gpmc.h>
+#include <asm/arch/onenand.h>
+#include <asm/arch/gpio.h>
+#include <asm/arch/gpmc.h>
+#include <asm/arch/pm.h>
+
+#include <linux/dma-mapping.h>
+#include <asm/dma-mapping.h>
+#include <asm/arch/dma.h>
+
+#include <asm/arch/board.h>
+
+#define DRIVER_NAME "omap2-onenand"
+
+#define ONENAND_IO_SIZE		SZ_128K
+#define ONENAND_BUFRAM_SIZE	(1024 * 5)
+
+struct omap2_onenand {
+	struct platform_device *pdev;
+	int gpmc_cs;
+	unsigned long phys_base;
+	int gpio_irq;
+	struct mtd_info mtd;
+	struct mtd_partition *parts;
+	struct onenand_chip onenand;
+	struct completion irq_done;
+	struct completion dma_done;
+	int dma_channel;
+	int freq;
+	int (*setup)(void __iomem *base, int freq);
+};
+
+static void omap2_onenand_dma_cb(int lch, u16 ch_status, void *data)
+{
+	struct omap2_onenand *c = data;
+
+	complete(&c->dma_done);
+}
+
+static irqreturn_t omap2_onenand_interrupt(int irq, void *dev_id)
+{
+	struct omap2_onenand *c = dev_id;
+
+	complete(&c->irq_done);
+
+	return IRQ_HANDLED;
+}
+
+static inline unsigned short read_reg(struct omap2_onenand *c, int reg)
+{
+	return readw(c->onenand.base + reg);
+}
+
+static inline void write_reg(struct omap2_onenand *c, unsigned short value,
+			     int reg)
+{
+	writew(value, c->onenand.base + reg);
+}
+
+static void wait_err(char *msg, int state, unsigned int ctrl, unsigned int intr)
+{
+	printk(KERN_ERR "onenand_wait: %s! state %d ctrl 0x%04x intr 0x%04x\n",
+	       msg, state, ctrl, intr);
+}
+
+static void wait_warn(char *msg, int state, unsigned int ctrl,
+		      unsigned int intr)
+{
+	printk(KERN_WARNING "onenand_wait: %s! state %d ctrl 0x%04x "
+	       "intr 0x%04x\n", msg, state, ctrl, intr);
+}
+
+static int omap2_onenand_wait(struct mtd_info *mtd, int state)
+{
+	struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd);
+	unsigned int intr = 0;
+	unsigned int ctrl;
+	unsigned long timeout;
+	u32 syscfg;
+
+	if (state == FL_RESETING) {
+		int i;
+
+		for (i = 0; i < 20; i++) {
+			udelay(1);
+			intr = read_reg(c, ONENAND_REG_INTERRUPT);
+			if (intr & ONENAND_INT_MASTER)
+				break;
+		}
+		ctrl = read_reg(c, ONENAND_REG_CTRL_STATUS);
+		if (ctrl & ONENAND_CTRL_ERROR) {
+			wait_err("controller error", state, ctrl, intr);
+			return -EIO;
+		}
+		if (!(intr & ONENAND_INT_RESET)) {
+			wait_err("timeout", state, ctrl, intr);
+			return -EIO;
+		}
+		return 0;
+	}
+
+	if (state != FL_READING) {
+		int result;
+
+		/* Turn interrupts on */
+		syscfg = read_reg(c, ONENAND_REG_SYS_CFG1);
+		syscfg |= ONENAND_SYS_CFG1_IOBE;
+		write_reg(c, syscfg, ONENAND_REG_SYS_CFG1);
+
+		INIT_COMPLETION(c->irq_done);
+		if (c->gpio_irq) {
+			result = omap_get_gpio_datain(c->gpio_irq);
+			if (result == -1) {
+				ctrl = read_reg(c, ONENAND_REG_CTRL_STATUS);
+				intr = read_reg(c, ONENAND_REG_INTERRUPT);
+				wait_err("gpio error", state, ctrl, intr);
+				return -EIO;
+			}
+		} else
+			result = 0;
+		if (result == 0) {
+			int retry_cnt = 0;
+retry:
+			result = wait_for_completion_timeout(&c->irq_done,
+						    msecs_to_jiffies(20));
+			if (result == 0) {
+				/* Timeout after 20ms */
+				ctrl = read_reg(c, ONENAND_REG_CTRL_STATUS);
+				if (ctrl & ONENAND_CTRL_ONGO) {
+					/*
+					 * The operation seems to be still going
+					 * so give it some more time.
+					 */
+					retry_cnt += 1;
+					if (retry_cnt < 3)
+						goto retry;
+					intr = read_reg(c,
+							ONENAND_REG_INTERRUPT);
+					wait_err("timeout", state, ctrl, intr);
+					return -EIO;
+				}
+				intr = read_reg(c, ONENAND_REG_INTERRUPT);
+				if ((intr & ONENAND_INT_MASTER) == 0)
+					wait_warn("timeout", state, ctrl, intr);
+			}
+		}
+	} else {
+		/* Turn interrupts off */
+		syscfg = read_reg(c, ONENAND_REG_SYS_CFG1);
+		syscfg &= ~ONENAND_SYS_CFG1_IOBE;
+		write_reg(c, syscfg, ONENAND_REG_SYS_CFG1);
+
+		timeout = jiffies + msecs_to_jiffies(20);
+		while (time_before(jiffies, timeout)) {
+			intr = read_reg(c, ONENAND_REG_INTERRUPT);
+			if (intr & ONENAND_INT_MASTER)
+				break;
+		}
+	}
+
+	intr = read_reg(c, ONENAND_REG_INTERRUPT);
+	ctrl = read_reg(c, ONENAND_REG_CTRL_STATUS);
+
+	if (intr & ONENAND_INT_READ) {
+		int ecc = read_reg(c, ONENAND_REG_ECC_STATUS);
+
+		if (ecc) {
+			unsigned int addr1, addr8;
+
+			addr1 = read_reg(c, ONENAND_REG_START_ADDRESS1);
+			addr8 = read_reg(c, ONENAND_REG_START_ADDRESS8);
+			if (ecc & ONENAND_ECC_2BIT_ALL) {
+				printk(KERN_ERR "onenand_wait: ECC error = "
+				       "0x%04x, addr1 %#x, addr8 %#x\n",
+				       ecc, addr1, addr8);
+				mtd->ecc_stats.failed++;
+				return -EBADMSG;
+			} else if (ecc & ONENAND_ECC_1BIT_ALL) {
+				printk(KERN_NOTICE "onenand_wait: correctable "
+				       "ECC error = 0x%04x, addr1 %#x, "
+				       "addr8 %#x\n", ecc, addr1, addr8);
+				mtd->ecc_stats.corrected++;
+			}
+		}
+	} else if (state == FL_READING) {
+		wait_err("timeout", state, ctrl, intr);
+		return -EIO;
+	}
+
+	if (ctrl & ONENAND_CTRL_ERROR) {
+		wait_err("controller error", state, ctrl, intr);
+		if (ctrl & ONENAND_CTRL_LOCK)
+			printk(KERN_ERR "onenand_wait: "
+					"Device is write protected!!!\n");
+		return -EIO;
+	}
+
+	if (ctrl & 0xFE9F)
+		wait_warn("unexpected controller status", state, ctrl, intr);
+
+	return 0;
+}
+
+static inline int omap2_onenand_bufferram_offset(struct mtd_info *mtd, int area)
+{
+	struct onenand_chip *this = mtd->priv;
+
+	if (ONENAND_CURRENT_BUFFERRAM(this)) {
+		if (area == ONENAND_DATARAM)
+			return mtd->writesize;
+		if (area == ONENAND_SPARERAM)
+			return mtd->oobsize;
+	}
+
+	return 0;
+}
+
+#if defined(CONFIG_ARCH_OMAP3) || defined(MULTI_OMAP2)
+
+static int omap3_onenand_read_bufferram(struct mtd_info *mtd, int area,
+					unsigned char *buffer, int offset,
+					size_t count)
+{
+	struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd);
+	struct onenand_chip *this = mtd->priv;
+	dma_addr_t dma_src, dma_dst;
+	int bram_offset;
+	unsigned long timeout;
+	void *buf = (void *)buffer;
+	size_t xtra;
+	volatile unsigned *done;
+
+	bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset;
+	if (bram_offset & 3 || (size_t)buf & 3 || count < 384)
+		goto out_copy;
+
+	if (buf >= high_memory) {
+		struct page *p1;
+
+		if (((size_t)buf & PAGE_MASK) !=
+		    ((size_t)(buf + count - 1) & PAGE_MASK))
+			goto out_copy;
+		p1 = vmalloc_to_page(buf);
+		if (!p1)
+			goto out_copy;
+		buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK);
+	}
+
+	xtra = count & 3;
+	if (xtra) {
+		count -= xtra;
+		memcpy(buf + count, this->base + bram_offset + count, xtra);
+	}
+
+	dma_src = c->phys_base + bram_offset;
+	dma_dst = dma_map_single(&c->pdev->dev, buf, count, DMA_FROM_DEVICE);
+	if (dma_mapping_error(&c->pdev->dev, dma_dst)) {
+		dev_err(&c->pdev->dev,
+			"Couldn't DMA map a %d byte buffer\n",
+			count);
+		goto out_copy;
+	}
+
+	omap_set_dma_transfer_params(c->dma_channel, OMAP_DMA_DATA_TYPE_S32,
+				     count >> 2, 1, 0, 0, 0);
+	omap_set_dma_src_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC,
+				dma_src, 0, 0);
+	omap_set_dma_dest_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC,
+				 dma_dst, 0, 0);
+
+	INIT_COMPLETION(c->dma_done);
+	omap_start_dma(c->dma_channel);
+
+	timeout = jiffies + msecs_to_jiffies(20);
+	done = &c->dma_done.done;
+	while (time_before(jiffies, timeout))
+		if (*done)
+			break;
+
+	dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_FROM_DEVICE);
+
+	if (!*done) {
+		dev_err(&c->pdev->dev, "timeout waiting for DMA\n");
+		goto out_copy;
+	}
+
+	return 0;
+
+out_copy:
+	memcpy(buf, this->base + bram_offset, count);
+	return 0;
+}
+
+static int omap3_onenand_write_bufferram(struct mtd_info *mtd, int area,
+					 const unsigned char *buffer,
+					 int offset, size_t count)
+{
+	struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd);
+	struct onenand_chip *this = mtd->priv;
+	dma_addr_t dma_src, dma_dst;
+	int bram_offset;
+	unsigned long timeout;
+	void *buf = (void *)buffer;
+	volatile unsigned *done;
+
+	bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset;
+	if (bram_offset & 3 || (size_t)buf & 3 || count < 384)
+		goto out_copy;
+
+	/* panic_write() may be in an interrupt context */
+	if (in_interrupt())
+		goto out_copy;
+
+	if (buf >= high_memory) {
+		struct page *p1;
+
+		if (((size_t)buf & PAGE_MASK) !=
+		    ((size_t)(buf + count - 1) & PAGE_MASK))
+			goto out_copy;
+		p1 = vmalloc_to_page(buf);
+		if (!p1)
+			goto out_copy;
+		buf = page_address(p1) + ((size_t)buf & ~PAGE_MASK);
+	}
+
+	dma_src = dma_map_single(&c->pdev->dev, buf, count, DMA_TO_DEVICE);
+	dma_dst = c->phys_base + bram_offset;
+	if (dma_mapping_error(&c->pdev->dev, dma_dst)) {
+		dev_err(&c->pdev->dev,
+			"Couldn't DMA map a %d byte buffer\n",
+			count);
+		return -1;
+	}
+
+	omap_set_dma_transfer_params(c->dma_channel, OMAP_DMA_DATA_TYPE_S32,
+				     count >> 2, 1, 0, 0, 0);
+	omap_set_dma_src_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC,
+				dma_src, 0, 0);
+	omap_set_dma_dest_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC,
+				 dma_dst, 0, 0);
+
+	INIT_COMPLETION(c->dma_done);
+	omap_start_dma(c->dma_channel);
+
+	timeout = jiffies + msecs_to_jiffies(20);
+	done = &c->dma_done.done;
+	while (time_before(jiffies, timeout))
+		if (*done)
+			break;
+
+	dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_TO_DEVICE);
+
+	if (!*done) {
+		dev_err(&c->pdev->dev, "timeout waiting for DMA\n");
+		goto out_copy;
+	}
+
+	return 0;
+
+out_copy:
+	memcpy(this->base + bram_offset, buf, count);
+	return 0;
+}
+
+#else
+
+int omap3_onenand_read_bufferram(struct mtd_info *mtd, int area,
+				 unsigned char *buffer, int offset,
+				 size_t count);
+
+int omap3_onenand_write_bufferram(struct mtd_info *mtd, int area,
+				  const unsigned char *buffer,
+				  int offset, size_t count);
+
+#endif
+
+#if defined(CONFIG_ARCH_OMAP2) || defined(MULTI_OMAP2)
+
+static int omap2_onenand_read_bufferram(struct mtd_info *mtd, int area,
+					unsigned char *buffer, int offset,
+					size_t count)
+{
+	struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd);
+	struct onenand_chip *this = mtd->priv;
+	dma_addr_t dma_src, dma_dst;
+	int bram_offset;
+
+	bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset;
+	/* DMA is not used.  Revisit PM requirements before enabling it. */
+	if (1 || (c->dma_channel < 0) ||
+	    ((void *) buffer >= (void *) high_memory) || (bram_offset & 3) ||
+	    (((unsigned int) buffer) & 3) || (count < 1024) || (count & 3)) {
+		memcpy(buffer, (__force void *)(this->base + bram_offset),
+		       count);
+		return 0;
+	}
+
+	dma_src = c->phys_base + bram_offset;
+	dma_dst = dma_map_single(&c->pdev->dev, buffer, count,
+				 DMA_FROM_DEVICE);
+	if (dma_mapping_error(&c->pdev->dev, dma_dst)) {
+		dev_err(&c->pdev->dev,
+			"Couldn't DMA map a %d byte buffer\n",
+			count);
+		return -1;
+	}
+
+	omap_set_dma_transfer_params(c->dma_channel, OMAP_DMA_DATA_TYPE_S32,
+				     count / 4, 1, 0, 0, 0);
+	omap_set_dma_src_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC,
+				dma_src, 0, 0);
+	omap_set_dma_dest_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC,
+				 dma_dst, 0, 0);
+
+	INIT_COMPLETION(c->dma_done);
+	omap_start_dma(c->dma_channel);
+	wait_for_completion(&c->dma_done);
+
+	dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_FROM_DEVICE);
+
+	return 0;
+}
+
+static int omap2_onenand_write_bufferram(struct mtd_info *mtd, int area,
+					 const unsigned char *buffer,
+					 int offset, size_t count)
+{
+	struct omap2_onenand *c = container_of(mtd, struct omap2_onenand, mtd);
+	struct onenand_chip *this = mtd->priv;
+	dma_addr_t dma_src, dma_dst;
+	int bram_offset;
+
+	bram_offset = omap2_onenand_bufferram_offset(mtd, area) + area + offset;
+	/* DMA is not used.  Revisit PM requirements before enabling it. */
+	if (1 || (c->dma_channel < 0) ||
+	    ((void *) buffer >= (void *) high_memory) || (bram_offset & 3) ||
+	    (((unsigned int) buffer) & 3) || (count < 1024) || (count & 3)) {
+		memcpy((__force void *)(this->base + bram_offset), buffer,
+		       count);
+		return 0;
+	}
+
+	dma_src = dma_map_single(&c->pdev->dev, (void *) buffer, count,
+				 DMA_TO_DEVICE);
+	dma_dst = c->phys_base + bram_offset;
+	if (dma_mapping_error(&c->pdev->dev, dma_dst)) {
+		dev_err(&c->pdev->dev,
+			"Couldn't DMA map a %d byte buffer\n",
+			count);
+		return -1;
+	}
+
+	omap_set_dma_transfer_params(c->dma_channel, OMAP_DMA_DATA_TYPE_S16,
+				     count / 2, 1, 0, 0, 0);
+	omap_set_dma_src_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC,
+				dma_src, 0, 0);
+	omap_set_dma_dest_params(c->dma_channel, 0, OMAP_DMA_AMODE_POST_INC,
+				 dma_dst, 0, 0);
+
+	INIT_COMPLETION(c->dma_done);
+	omap_start_dma(c->dma_channel);
+	wait_for_completion(&c->dma_done);
+
+	dma_unmap_single(&c->pdev->dev, dma_dst, count, DMA_TO_DEVICE);
+
+	return 0;
+}
+
+#else
+
+int omap2_onenand_read_bufferram(struct mtd_info *mtd, int area,
+				 unsigned char *buffer, int offset,
+				 size_t count);
+
+int omap2_onenand_write_bufferram(struct mtd_info *mtd, int area,
+				  const unsigned char *buffer,
+				  int offset, size_t count);
+
+#endif
+
+static struct platform_driver omap2_onenand_driver;
+
+static int __adjust_timing(struct device *dev, void *data)
+{
+	int ret = 0;
+	struct omap2_onenand *c;
+
+	c = dev_get_drvdata(dev);
+
+	BUG_ON(c->setup == NULL);
+
+	/* DMA is not in use so this is all that is needed */
+	/* Revisit for OMAP3! */
+	ret = c->setup(c->onenand.base, c->freq);
+
+	return ret;
+}
+
+int omap2_onenand_rephase(void)
+{
+	return driver_for_each_device(&omap2_onenand_driver.driver, NULL,
+				      NULL, __adjust_timing);
+}
+
+static void __devexit omap2_onenand_shutdown(struct platform_device *pdev)
+{
+	struct omap2_onenand *c = dev_get_drvdata(&pdev->dev);
+
+	/* With certain content in the buffer RAM, the OMAP boot ROM code
+	 * can recognize the flash chip incorrectly. Zero it out before
+	 * soft reset.
+	 */
+	memset((__force void *)c->onenand.base, 0, ONENAND_BUFRAM_SIZE);
+}
+
+static int __devinit omap2_onenand_probe(struct platform_device *pdev)
+{
+	struct omap_onenand_platform_data *pdata;
+	struct omap2_onenand *c;
+	int r;
+
+	pdata = pdev->dev.platform_data;
+	if (pdata == NULL) {
+		dev_err(&pdev->dev, "platform data missing\n");
+		return -ENODEV;
+	}
+
+	c = kzalloc(sizeof(struct omap2_onenand), GFP_KERNEL);
+	if (!c)
+		return -ENOMEM;
+
+	init_completion(&c->irq_done);
+	init_completion(&c->dma_done);
+	c->gpmc_cs = pdata->cs;
+	c->gpio_irq = pdata->gpio_irq;
+	c->dma_channel = pdata->dma_channel;
+	if (c->dma_channel < 0) {
+		/* if -1, don't use DMA */
+		c->gpio_irq = 0;
+	}
+
+	r = gpmc_cs_request(c->gpmc_cs, ONENAND_IO_SIZE, &c->phys_base);
+	if (r < 0) {
+		dev_err(&pdev->dev, "Cannot request GPMC CS\n");
+		goto err_kfree;
+	}
+
+	if (request_mem_region(c->phys_base, ONENAND_IO_SIZE,
+			       pdev->dev.driver->name) == NULL) {
+		dev_err(&pdev->dev, "Cannot reserve memory region at 0x%08lx, "
+			"size: 0x%x\n",	c->phys_base, ONENAND_IO_SIZE);
+		r = -EBUSY;
+		goto err_free_cs;
+	}
+	c->onenand.base = ioremap(c->phys_base, ONENAND_IO_SIZE);
+	if (c->onenand.base == NULL) {
+		r = -ENOMEM;
+		goto err_release_mem_region;
+	}
+
+	if (pdata->onenand_setup != NULL) {
+		r = pdata->onenand_setup(c->onenand.base, c->freq);
+		if (r < 0) {
+			dev_err(&pdev->dev, "Onenand platform setup failed: "
+				"%d\n", r);
+			goto err_iounmap;
+		}
+		c->setup = pdata->onenand_setup;
+	}
+
+	if (c->gpio_irq) {
+		if ((r = omap_request_gpio(c->gpio_irq)) < 0) {
+			dev_err(&pdev->dev,  "Failed to request GPIO%d for "
+				"OneNAND\n", c->gpio_irq);
+			goto err_iounmap;
+	}
+	omap_set_gpio_direction(c->gpio_irq, 1);
+
+	if ((r = request_irq(OMAP_GPIO_IRQ(c->gpio_irq),
+			     omap2_onenand_interrupt, IRQF_TRIGGER_RISING,
+			     pdev->dev.driver->name, c)) < 0)
+		goto err_release_gpio;
+	}
+
+	if (c->dma_channel >= 0) {
+		r = omap_request_dma(0, pdev->dev.driver->name,
+				     omap2_onenand_dma_cb, (void *) c,
+				     &c->dma_channel);
+		if (r == 0) {
+			omap_set_dma_write_mode(c->dma_channel,
+						OMAP_DMA_WRITE_NON_POSTED);
+			omap_set_dma_src_data_pack(c->dma_channel, 1);
+			omap_set_dma_src_burst_mode(c->dma_channel,
+						    OMAP_DMA_DATA_BURST_8);
+			omap_set_dma_dest_data_pack(c->dma_channel, 1);
+			omap_set_dma_dest_burst_mode(c->dma_channel,
+						     OMAP_DMA_DATA_BURST_8);
+		} else {
+			dev_info(&pdev->dev,
+				 "failed to allocate DMA for OneNAND, "
+				 "using PIO instead\n");
+			c->dma_channel = -1;
+		}
+	}
+
+	dev_info(&pdev->dev, "initializing on CS%d, phys base 0x%08lx, virtual "
+		 "base %p\n", c->gpmc_cs, c->phys_base,
+		 c->onenand.base);
+
+	c->pdev = pdev;
+	c->mtd.name = pdev->dev.bus_id;
+	c->mtd.priv = &c->onenand;
+	c->mtd.owner = THIS_MODULE;
+
+	if (c->dma_channel >= 0) {
+		struct onenand_chip *this = &c->onenand;
+
+		this->wait = omap2_onenand_wait;
+		if (cpu_is_omap34xx()) {
+			this->read_bufferram = omap3_onenand_read_bufferram;
+			this->write_bufferram = omap3_onenand_write_bufferram;
+		} else {
+			this->read_bufferram = omap2_onenand_read_bufferram;
+			this->write_bufferram = omap2_onenand_write_bufferram;
+		}
+	}
+
+	if ((r = onenand_scan(&c->mtd, 1)) < 0)
+		goto err_release_dma;
+
+	switch ((c->onenand.version_id >> 4) & 0xf) {
+	case 0:
+		c->freq = 40;
+		break;
+	case 1:
+		c->freq = 54;
+		break;
+	case 2:
+		c->freq = 66;
+		break;
+	case 3:
+		c->freq = 83;
+		break;
+	}
+
+#ifdef CONFIG_MTD_PARTITIONS
+	if (pdata->parts != NULL)
+		r = add_mtd_partitions(&c->mtd, pdata->parts,
+				       pdata->nr_parts);
+	else
+#endif
+		r = add_mtd_device(&c->mtd);
+	if (r < 0)
+		goto err_release_onenand;
+
+	platform_set_drvdata(pdev, c);
+
+	return 0;
+
+err_release_onenand:
+	onenand_release(&c->mtd);
+err_release_dma:
+	if (c->dma_channel != -1)
+		omap_free_dma(c->dma_channel);
+	if (c->gpio_irq)
+		free_irq(OMAP_GPIO_IRQ(c->gpio_irq), c);
+err_release_gpio:
+	if (c->gpio_irq)
+		omap_free_gpio(c->gpio_irq);
+err_iounmap:
+	iounmap(c->onenand.base);
+err_release_mem_region:
+	release_mem_region(c->phys_base, ONENAND_IO_SIZE);
+err_free_cs:
+	gpmc_cs_free(c->gpmc_cs);
+err_kfree:
+	kfree(c);
+
+	return r;
+}
+
+static int __devexit omap2_onenand_remove(struct platform_device *pdev)
+{
+	struct omap2_onenand *c = dev_get_drvdata(&pdev->dev);
+
+	BUG_ON(c == NULL);
+
+#ifdef CONFIG_MTD_PARTITIONS
+	if (c->parts)
+		del_mtd_partitions(&c->mtd);
+	else
+		del_mtd_device(&c->mtd);
+#else
+	del_mtd_device(&c->mtd);
+#endif
+
+	onenand_release(&c->mtd);
+	if (c->dma_channel != -1)
+		omap_free_dma(c->dma_channel);
+	omap2_onenand_shutdown(pdev);
+	platform_set_drvdata(pdev, NULL);
+	if (c->gpio_irq) {
+		free_irq(OMAP_GPIO_IRQ(c->gpio_irq), c);
+		omap_free_gpio(c->gpio_irq);
+	}
+	iounmap(c->onenand.base);
+	release_mem_region(c->phys_base, ONENAND_IO_SIZE);
+	kfree(c);
+
+	return 0;
+}
+
+static struct platform_driver omap2_onenand_driver = {
+	.probe		= omap2_onenand_probe,
+	.remove		= omap2_onenand_remove,
+	.shutdown	= omap2_onenand_shutdown,
+	.driver		= {
+		.name	= DRIVER_NAME,
+		.owner  = THIS_MODULE,
+	},
+};
+
+static int __init omap2_onenand_init(void)
+{
+	printk(KERN_INFO "OneNAND driver initializing\n");
+	return platform_driver_register(&omap2_onenand_driver);
+}
+
+static void __exit omap2_onenand_exit(void)
+{
+	platform_driver_unregister(&omap2_onenand_driver);
+}
+
+module_init(omap2_onenand_init);
+module_exit(omap2_onenand_exit);
+
+MODULE_ALIAS(DRIVER_NAME);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jarkko Lavinen <jarkko.lavinen@nokia.com>");
+MODULE_DESCRIPTION("Glue layer for OneNAND flash on OMAP2 / OMAP3");
diff --git a/include/asm-arm/arch-omap/onenand.h b/include/asm-arm/arch-omap/onenand.h
index 6c959d0ce470..e30237117b69 100644
--- a/include/asm-arm/arch-omap/onenand.h
+++ b/include/asm-arm/arch-omap/onenand.h
@@ -16,6 +16,11 @@ struct omap_onenand_platform_data {
 	int			gpio_irq;
 	struct mtd_partition	*parts;
 	int			nr_parts;
-	int                     (*onenand_setup)(void __iomem *);
+	int                     (*onenand_setup)(void __iomem *, int freq);
 	int			dma_channel;
 };
+
+int omap2_onenand_rephase(void);
+
+#define ONENAND_MAX_PARTITIONS 8
+
-- 
cgit v1.2.3


From 17c1d2be28e485c0c8b09661db39d5bf2605069d Mon Sep 17 00:00:00 2001
From: Alexey Korolev <akorolev@infradead.org>
Date: Wed, 20 Aug 2008 22:32:08 +0100
Subject: [MTD] [NAND] Fix missing kernel-doc

[Reported by Randy Dunlap]

Signed-off-by: Alexey Korolev <akorolev@infradead.org>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/mtd/nand/nand_base.c | 6 +++---
 drivers/mtd/nand/nand_ecc.c  | 6 +++---
 include/linux/mtd/nand.h     | 1 +
 3 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 582280560c89..d303db39c48d 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -801,9 +801,9 @@ static int nand_read_page_swecc(struct mtd_info *mtd, struct nand_chip *chip,
  * nand_read_subpage - [REPLACABLE] software ecc based sub-page read function
  * @mtd:	mtd info structure
  * @chip:	nand chip info structure
- * @dataofs	offset of requested data within the page
- * @readlen	data length
- * @buf:	buffer to store read data
+ * @data_offs:	offset of requested data within the page
+ * @readlen:	data length
+ * @bufpoi:	buffer to store read data
  */
 static int nand_read_subpage(struct mtd_info *mtd, struct nand_chip *chip, uint32_t data_offs, uint32_t readlen, uint8_t *bufpoi)
 {
diff --git a/drivers/mtd/nand/nand_ecc.c b/drivers/mtd/nand/nand_ecc.c
index d99e569e999f..fd19787c9ce7 100644
--- a/drivers/mtd/nand/nand_ecc.c
+++ b/drivers/mtd/nand/nand_ecc.c
@@ -150,8 +150,8 @@ static const char addressbits[256] = {
 /**
  * nand_calculate_ecc - [NAND Interface] Calculate 3-byte ECC for 256-byte block
  * @mtd:	MTD block structure (unused)
- * @dat:	raw data
- * @ecc_code:	buffer for ECC
+ * @buf:	input buffer with raw data
+ * @code:	output buffer with ECC
  */
 int nand_calculate_ecc(struct mtd_info *mtd, const unsigned char *buf,
 		       unsigned char *code)
@@ -390,7 +390,7 @@ EXPORT_SYMBOL(nand_calculate_ecc);
 /**
  * nand_correct_data - [NAND Interface] Detect and correct bit error(s)
  * @mtd:	MTD block structure (unused)
- * @dat:	raw data read from the chip
+ * @buf:	raw data read from the chip
  * @read_ecc:	ECC from the chip
  * @calc_ecc:	the ECC calculated from raw data
  *
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index 81774e5facf4..733d3f3b4eb8 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -248,6 +248,7 @@ struct nand_hw_control {
  * @read_page_raw:	function to read a raw page without ECC
  * @write_page_raw:	function to write a raw page without ECC
  * @read_page:	function to read a page according to the ecc generator requirements
+ * @read_subpage:	function to read parts of the page covered by ECC.
  * @write_page:	function to write a page according to the ecc generator requirements
  * @read_oob:	function to read chip OOB data
  * @write_oob:	function to write chip OOB data
-- 
cgit v1.2.3


From 1aa5dfb751d275ae7117d3b73ac423b4a46f2a73 Mon Sep 17 00:00:00 2001
From: John Stultz <johnstul@us.ibm.com>
Date: Wed, 20 Aug 2008 16:37:28 -0700
Subject: clocksource: keep track of original clocksource frequency

The clocksource frequency is represented by
clocksource->mult/2^(clocksource->shift).  Currently, when NTP makes
adjustments to the clock frequency, they are made directly to the mult
value.

This has the drawback that once changed, we cannot know what the orignal
mult value was, or how much adjustment has been applied.

This property causes problems in calculating proper ntp intervals when
switching back and forth between clocksources.

This patch separates the current mult value into a mult and mult_orig
pair.  The mult_orig value stays constant, while the ntp clocksource
adjustments are done only to the mult value.

This allows for correct ntp interval calculation and additionally lays the
groundwork for a new notion of time, what I'm calling the monotonic-raw
time, which is introduced in a following patch.

Signed-off-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/clocksource.h | 11 +++++++----
 kernel/time/clocksource.c   |  3 +++
 kernel/time/jiffies.c       |  1 +
 3 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 55e434feec99..f0a7fb984413 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -45,7 +45,8 @@ struct clocksource;
  * @read:		returns a cycle value
  * @mask:		bitmask for two's complement
  *			subtraction of non 64 bit counters
- * @mult:		cycle to nanosecond multiplier
+ * @mult:		cycle to nanosecond multiplier (adjusted by NTP)
+ * @mult_orig:		cycle to nanosecond multiplier (unadjusted by NTP)
  * @shift:		cycle to nanosecond divisor (power of two)
  * @flags:		flags describing special properties
  * @vread:		vsyscall based read
@@ -63,6 +64,7 @@ struct clocksource {
 	cycle_t (*read)(void);
 	cycle_t mask;
 	u32 mult;
+	u32 mult_orig;
 	u32 shift;
 	unsigned long flags;
 	cycle_t (*vread)(void);
@@ -201,16 +203,17 @@ static inline void clocksource_calculate_interval(struct clocksource *c,
 {
 	u64 tmp;
 
-	/* XXX - All of this could use a whole lot of optimization */
+	/* Do the ns -> cycle conversion first, using original mult */
 	tmp = length_nsec;
 	tmp <<= c->shift;
-	tmp += c->mult/2;
-	do_div(tmp, c->mult);
+	tmp += c->mult_orig/2;
+	do_div(tmp, c->mult_orig);
 
 	c->cycle_interval = (cycle_t)tmp;
 	if (c->cycle_interval == 0)
 		c->cycle_interval = 1;
 
+	/* Go back from cycles -> shifted ns, this time use ntp adjused mult */
 	c->xtime_interval = (u64)c->cycle_interval * c->mult;
 }
 
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 093d4acf993b..9ed2eec97526 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -325,6 +325,9 @@ int clocksource_register(struct clocksource *c)
 	unsigned long flags;
 	int ret;
 
+	/* save mult_orig on registration */
+	c->mult_orig = c->mult;
+
 	spin_lock_irqsave(&clocksource_lock, flags);
 	ret = clocksource_enqueue(c);
 	if (!ret)
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 4c256fdb8875..1ca99557e929 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -61,6 +61,7 @@ struct clocksource clocksource_jiffies = {
 	.read		= jiffies_read,
 	.mask		= 0xffffffff, /*32bits*/
 	.mult		= NSEC_PER_JIFFY << JIFFIES_SHIFT, /* details above */
+	.mult_orig	= NSEC_PER_JIFFY << JIFFIES_SHIFT,
 	.shift		= JIFFIES_SHIFT,
 };
 
-- 
cgit v1.2.3


From 2d42244ae71d6c7b0884b5664cf2eda30fb2ae68 Mon Sep 17 00:00:00 2001
From: John Stultz <johnstul@us.ibm.com>
Date: Wed, 20 Aug 2008 16:37:30 -0700
Subject: clocksource: introduce CLOCK_MONOTONIC_RAW

In talking with Josip Loncaric, and his work on clock synchronization (see
btime.sf.net), he mentioned that for really close synchronization, it is
useful to have access to "hardware time", that is a notion of time that is
not in any way adjusted by the clock slewing done to keep close time sync.

Part of the issue is if we are using the kernel's ntp adjusted
representation of time in order to measure how we should correct time, we
can run into what Paul McKenney aptly described as "Painting a road using
the lines we're painting as the guide".

I had been thinking of a similar problem, and was trying to come up with a
way to give users access to a purely hardware based time representation
that avoided users having to know the underlying frequency and mask values
needed to deal with the wide variety of possible underlying hardware
counters.

My solution is to introduce CLOCK_MONOTONIC_RAW.  This exposes a
nanosecond based time value, that increments starting at bootup and has no
frequency adjustments made to it what so ever.

The time is accessed from userspace via the posix_clock_gettime() syscall,
passing CLOCK_MONOTONIC_RAW as the clock_id.

Signed-off-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/clocksource.h |  3 +++
 include/linux/time.h        |  2 ++
 kernel/posix-timers.c       | 15 +++++++++++++++
 kernel/time/timekeeping.c   | 44 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 64 insertions(+)

(limited to 'include')

diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index f0a7fb984413..f88d32f8ff7c 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -79,6 +79,7 @@ struct clocksource {
 	/* timekeeping specific data, ignore */
 	cycle_t cycle_interval;
 	u64	xtime_interval;
+	u32	raw_interval;
 	/*
 	 * Second part is written at each timer interrupt
 	 * Keep it in a different cache line to dirty no
@@ -87,6 +88,7 @@ struct clocksource {
 	cycle_t cycle_last ____cacheline_aligned_in_smp;
 	u64 xtime_nsec;
 	s64 error;
+	struct timespec raw_time;
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 	/* Watchdog related data, used by the framework */
@@ -215,6 +217,7 @@ static inline void clocksource_calculate_interval(struct clocksource *c,
 
 	/* Go back from cycles -> shifted ns, this time use ntp adjused mult */
 	c->xtime_interval = (u64)c->cycle_interval * c->mult;
+	c->raw_interval = ((u64)c->cycle_interval * c->mult_orig) >> c->shift;
 }
 
 
diff --git a/include/linux/time.h b/include/linux/time.h
index e15206a7e82e..205f974b9ebf 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -117,6 +117,7 @@ extern int do_setitimer(int which, struct itimerval *value,
 extern unsigned int alarm_setitimer(unsigned int seconds);
 extern int do_getitimer(int which, struct itimerval *value);
 extern void getnstimeofday(struct timespec *tv);
+extern void getrawmonotonic(struct timespec *ts);
 extern void getboottime(struct timespec *ts);
 extern void monotonic_to_bootbased(struct timespec *ts);
 
@@ -214,6 +215,7 @@ struct itimerval {
 #define CLOCK_MONOTONIC			1
 #define CLOCK_PROCESS_CPUTIME_ID	2
 #define CLOCK_THREAD_CPUTIME_ID		3
+#define CLOCK_MONOTONIC_RAW		4
 
 /*
  * The IDs of various hardware clocks:
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index e36d5798cbff..d3c66b53dff6 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -222,6 +222,15 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec *tp)
 	return 0;
 }
 
+/*
+ * Get monotonic time for posix timers
+ */
+static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec *tp)
+{
+	getrawmonotonic(tp);
+	return 0;
+}
+
 /*
  * Initialize everything, well, just everything in Posix clocks/timers ;)
  */
@@ -235,9 +244,15 @@ static __init int init_posix_timers(void)
 		.clock_get = posix_ktime_get_ts,
 		.clock_set = do_posix_clock_nosettime,
 	};
+	struct k_clock clock_monotonic_raw = {
+		.clock_getres = hrtimer_get_res,
+		.clock_get = posix_get_monotonic_raw,
+		.clock_set = do_posix_clock_nosettime,
+	};
 
 	register_posix_clock(CLOCK_REALTIME, &clock_realtime);
 	register_posix_clock(CLOCK_MONOTONIC, &clock_monotonic);
+	register_posix_clock(CLOCK_MONOTONIC_RAW, &clock_monotonic_raw);
 
 	posix_timers_cache = kmem_cache_create("posix_timers_cache",
 					sizeof (struct k_itimer), 0, SLAB_PANIC,
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 83d3555a6998..5099c95b8aa2 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -75,6 +75,9 @@ static void clocksource_forward_now(void)
 
 	nsec = cyc2ns(clock, cycle_delta);
 	timespec_add_ns(&xtime, nsec);
+
+	nsec = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
+	clock->raw_time.tv_nsec += nsec;
 }
 
 /**
@@ -183,6 +186,8 @@ static void change_clocksource(void)
 
 	clocksource_forward_now();
 
+	new->raw_time = clock->raw_time;
+
 	clock = new;
 	clock->cycle_last = 0;
 	clock->cycle_last = clocksource_read(new);
@@ -204,6 +209,39 @@ static inline void clocksource_forward_now(void) { }
 static inline void change_clocksource(void) { }
 #endif
 
+/**
+ * getrawmonotonic - Returns the raw monotonic time in a timespec
+ * @ts:		pointer to the timespec to be set
+ *
+ * Returns the raw monotonic time (completely un-modified by ntp)
+ */
+void getrawmonotonic(struct timespec *ts)
+{
+	unsigned long seq;
+	s64 nsecs;
+	cycle_t cycle_now, cycle_delta;
+
+	do {
+		seq = read_seqbegin(&xtime_lock);
+
+		/* read clocksource: */
+		cycle_now = clocksource_read(clock);
+
+		/* calculate the delta since the last update_wall_time: */
+		cycle_delta = (cycle_now - clock->cycle_last) & clock->mask;
+
+		/* convert to nanoseconds: */
+		nsecs = ((s64)cycle_delta * clock->mult_orig) >> clock->shift;
+
+		*ts = clock->raw_time;
+
+	} while (read_seqretry(&xtime_lock, seq));
+
+	timespec_add_ns(ts, nsecs);
+}
+EXPORT_SYMBOL(getrawmonotonic);
+
+
 /**
  * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
  */
@@ -466,6 +504,12 @@ void update_wall_time(void)
 			second_overflow();
 		}
 
+		clock->raw_time.tv_nsec += clock->raw_interval;
+		if (clock->raw_time.tv_nsec >= NSEC_PER_SEC) {
+			clock->raw_time.tv_nsec -= NSEC_PER_SEC;
+			clock->raw_time.tv_sec++;
+		}
+
 		/* accumulate error between NTP and clock interval */
 		clock->error += tick_length;
 		clock->error -= clock->xtime_interval << (NTP_SCALE_SHIFT - clock->shift);
-- 
cgit v1.2.3


From 916c7a855174e3b53d182b97a26b2e27a29726a1 Mon Sep 17 00:00:00 2001
From: Roman Zippel <zippel@linux-m68k.org>
Date: Wed, 20 Aug 2008 16:46:08 -0700
Subject: ntp: fix ADJ_OFFSET_SS_READ bug and do_adjtimex() cleanup

Thanks to the review by Michael Kerrisk a bug in the recent
ADJ_OFFSET_SS_READ option was discovered, where the ntp time_offset was
inadvertently set by it.  This fixes this by making the adjtime code
more separate from the ntp_adjtime code (both of which really want to
be separate syscalls).

Signed-off-by: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/timex.h |  9 +++++-
 kernel/time/ntp.c     | 76 +++++++++++++++++++++++++++------------------------
 2 files changed, 48 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/linux/timex.h b/include/linux/timex.h
index fc6035d29d56..c00bcdd3ae42 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -141,8 +141,15 @@ struct timex {
 #define ADJ_MICRO		0x1000	/* select microsecond resolution */
 #define ADJ_NANO		0x2000	/* select nanosecond resolution */
 #define ADJ_TICK		0x4000	/* tick value */
+
+#ifdef __KERNEL__
+#define ADJ_ADJTIME		0x8000	/* switch between adjtime/adjtimex modes */
+#define ADJ_OFFSET_SINGLESHOT	0x0001	/* old-fashioned adjtime */
+#define ADJ_OFFSET_READONLY	0x2000	/* read-only adjtime */
+#else
 #define ADJ_OFFSET_SINGLESHOT	0x8001	/* old-fashioned adjtime */
-#define ADJ_OFFSET_SS_READ	0xa001  /* read-only adjtime */
+#define ADJ_OFFSET_SS_READ	0xa001	/* read-only adjtime */
+#endif
 
 /* xntp 3.4 compatibility names */
 #define MOD_OFFSET	ADJ_OFFSET
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 5125ddd8196b..c6921aa1a42a 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -277,38 +277,50 @@ static inline void notify_cmos_timer(void) { }
 int do_adjtimex(struct timex *txc)
 {
 	struct timespec ts;
-	long save_adjust, sec;
 	int result;
 
-	/* In order to modify anything, you gotta be super-user! */
-	if (txc->modes && !capable(CAP_SYS_TIME))
-		return -EPERM;
-
-	/* Now we validate the data before disabling interrupts */
-
-	if ((txc->modes & ADJ_OFFSET_SINGLESHOT) == ADJ_OFFSET_SINGLESHOT) {
+	/* Validate the data before disabling interrupts */
+	if (txc->modes & ADJ_ADJTIME) {
 		/* singleshot must not be used with any other mode bits */
-		if (txc->modes & ~ADJ_OFFSET_SS_READ)
+		if (!(txc->modes & ADJ_OFFSET_SINGLESHOT))
 			return -EINVAL;
+		if (!(txc->modes & ADJ_OFFSET_READONLY) &&
+		    !capable(CAP_SYS_TIME))
+			return -EPERM;
+	} else {
+		/* In order to modify anything, you gotta be super-user! */
+		 if (txc->modes && !capable(CAP_SYS_TIME))
+			return -EPERM;
+
+		/* if the quartz is off by more than 10% something is VERY wrong! */
+		if (txc->modes & ADJ_TICK &&
+		    (txc->tick <  900000/USER_HZ ||
+		     txc->tick > 1100000/USER_HZ))
+				return -EINVAL;
+
+		if (txc->modes & ADJ_STATUS && time_state != TIME_OK)
+			hrtimer_cancel(&leap_timer);
 	}
 
-	/* if the quartz is off by more than 10% something is VERY wrong ! */
-	if (txc->modes & ADJ_TICK)
-		if (txc->tick <  900000/USER_HZ ||
-		    txc->tick > 1100000/USER_HZ)
-			return -EINVAL;
-
-	if (time_state != TIME_OK && txc->modes & ADJ_STATUS)
-		hrtimer_cancel(&leap_timer);
 	getnstimeofday(&ts);
 
 	write_seqlock_irq(&xtime_lock);
 
-	/* Save for later - semantics of adjtime is to return old value */
-	save_adjust = time_adjust;
-
 	/* If there are input parameters, then process them */
+	if (txc->modes & ADJ_ADJTIME) {
+		long save_adjust = time_adjust;
+
+		if (!(txc->modes & ADJ_OFFSET_READONLY)) {
+			/* adjtime() is independent from ntp_adjtime() */
+			time_adjust = txc->offset;
+			ntp_update_frequency();
+		}
+		txc->offset = save_adjust;
+		goto adj_done;
+	}
 	if (txc->modes) {
+		long sec;
+
 		if (txc->modes & ADJ_STATUS) {
 			if ((time_status & STA_PLL) &&
 			    !(txc->status & STA_PLL)) {
@@ -375,13 +387,8 @@ int do_adjtimex(struct timex *txc)
 		if (txc->modes & ADJ_TAI && txc->constant > 0)
 			time_tai = txc->constant;
 
-		if (txc->modes & ADJ_OFFSET) {
-			if (txc->modes == ADJ_OFFSET_SINGLESHOT)
-				/* adjtime() is independent from ntp_adjtime() */
-				time_adjust = txc->offset;
-			else
-				ntp_update_offset(txc->offset);
-		}
+		if (txc->modes & ADJ_OFFSET)
+			ntp_update_offset(txc->offset);
 		if (txc->modes & ADJ_TICK)
 			tick_usec = txc->tick;
 
@@ -389,19 +396,16 @@ int do_adjtimex(struct timex *txc)
 			ntp_update_frequency();
 	}
 
+	txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
+				  NTP_SCALE_SHIFT);
+	if (!(time_status & STA_NANO))
+		txc->offset /= NSEC_PER_USEC;
+
+adj_done:
 	result = time_state;	/* mostly `TIME_OK' */
 	if (time_status & (STA_UNSYNC|STA_CLOCKERR))
 		result = TIME_ERROR;
 
-	if ((txc->modes == ADJ_OFFSET_SINGLESHOT) ||
-	    (txc->modes == ADJ_OFFSET_SS_READ))
-		txc->offset = save_adjust;
-	else {
-		txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
-					  NTP_SCALE_SHIFT);
-		if (!(time_status & STA_NANO))
-			txc->offset /= NSEC_PER_USEC;
-	}
 	txc->freq	   = shift_right((s32)(time_freq >> PPM_SCALE_INV_SHIFT) *
 					 (s64)PPM_SCALE_INV,
 					 NTP_SCALE_SHIFT);
-- 
cgit v1.2.3


From 942ed161944b3476639916cf544e6975b29c985a Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg59@srcf.ucam.org>
Date: Tue, 26 Aug 2008 21:09:59 +0100
Subject: power_supply: Add function to return system-wide power state

Certain drivers benefit from knowing whether the system is on ac or
battery, for instance when determining which backlight registers to
read. This adds a simple call to determine whether there's an online
power supply other than any batteries.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
Signed-off-by: Anton Vorontsov <cbouatmailru@gmail.com>
---
 drivers/power/power_supply_core.c | 25 +++++++++++++++++++++++++
 include/linux/power_supply.h      |  6 ++++++
 2 files changed, 31 insertions(+)

(limited to 'include')

diff --git a/drivers/power/power_supply_core.c b/drivers/power/power_supply_core.c
index cb1ccb472921..f44f5b608f6a 100644
--- a/drivers/power/power_supply_core.c
+++ b/drivers/power/power_supply_core.c
@@ -87,6 +87,30 @@ int power_supply_am_i_supplied(struct power_supply *psy)
 	return error;
 }
 
+static int __power_supply_is_system_supplied(struct device *dev, void *data)
+{
+	union power_supply_propval ret = {0,};
+	struct power_supply *psy = dev_get_drvdata(dev);
+
+	if (psy->type != POWER_SUPPLY_TYPE_BATTERY) {
+		if (psy->get_property(psy, POWER_SUPPLY_PROP_ONLINE, &ret))
+			return 0;
+		if (ret.intval)
+			return ret.intval;
+	}
+	return 0;
+}
+
+int power_supply_is_system_supplied(void)
+{
+	int error;
+
+	error = class_for_each_device(power_supply_class, NULL, NULL,
+				      __power_supply_is_system_supplied);
+
+	return error;
+}
+
 int power_supply_register(struct device *parent, struct power_supply *psy)
 {
 	int rc = 0;
@@ -148,6 +172,7 @@ static void __exit power_supply_class_exit(void)
 
 EXPORT_SYMBOL_GPL(power_supply_changed);
 EXPORT_SYMBOL_GPL(power_supply_am_i_supplied);
+EXPORT_SYMBOL_GPL(power_supply_is_system_supplied);
 EXPORT_SYMBOL_GPL(power_supply_register);
 EXPORT_SYMBOL_GPL(power_supply_unregister);
 
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index ea96ead1d39d..f9348cba6dc1 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -165,6 +165,12 @@ struct power_supply_info {
 extern void power_supply_changed(struct power_supply *psy);
 extern int power_supply_am_i_supplied(struct power_supply *psy);
 
+#if defined(CONFIG_POWER_SUPPLY) || defined(CONFIG_POWER_SUPPLY_MODULE)
+extern int power_supply_is_system_supplied(void);
+#else
+static inline int power_supply_is_system_supplied(void) { return -ENOSYS; }
+#endif
+
 extern int power_supply_register(struct device *parent,
 				 struct power_supply *psy);
 extern void power_supply_unregister(struct power_supply *psy);
-- 
cgit v1.2.3


From 7bb67439bf6bd3782f07f1d7be1e63406453d5de Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Sun, 31 Aug 2008 08:05:58 -0700
Subject: select: Introduce a hrtimeout function

This patch adds a schedule_hrtimeout() function, to be used by select() and
poll() in a later patch. This function works similar to schedule_timeout()
in most ways, but takes a timespec rather than jiffies.

With a lot of contributions/fixes from Thomas

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/hrtimer.h |  2 ++
 kernel/hrtimer.c        | 65 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 67 insertions(+)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 6d93dce61cbb..becd17db1a1a 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -346,6 +346,8 @@ extern long hrtimer_nanosleep_restart(struct restart_block *restart_block);
 extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
 				 struct task_struct *tsk);
 
+extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
+
 /* Soft interrupt function to run the hrtimer queues: */
 extern void hrtimer_run_queues(void);
 extern void hrtimer_run_pending(void);
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index b8e4dce80a74..782137dc755f 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1678,3 +1678,68 @@ void __init hrtimers_init(void)
 #endif
 }
 
+/**
+ * schedule_hrtimeout - sleep until timeout
+ * @expires:	timeout value (ktime_t)
+ * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout(ktime_t *expires,
+			       const enum hrtimer_mode mode)
+{
+	struct hrtimer_sleeper t;
+
+	/*
+	 * Optimize when a zero timeout value is given. It does not
+	 * matter whether this is an absolute or a relative time.
+	 */
+	if (expires && !expires->tv64) {
+		__set_current_state(TASK_RUNNING);
+		return 0;
+	}
+
+	/*
+	 * A NULL parameter means "inifinte"
+	 */
+	if (!expires) {
+		schedule();
+		__set_current_state(TASK_RUNNING);
+		return -EINTR;
+	}
+
+	hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
+	t.timer.expires = *expires;
+
+	hrtimer_init_sleeper(&t, current);
+
+	hrtimer_start(&t.timer, t.timer.expires, mode);
+	if (!hrtimer_active(&t.timer))
+		t.task = NULL;
+
+	if (likely(t.task))
+		schedule();
+
+	hrtimer_cancel(&t.timer);
+	destroy_hrtimer_on_stack(&t.timer);
+
+	__set_current_state(TASK_RUNNING);
+
+	return !t.task ? 0 : -EINTR;
+}
+EXPORT_SYMBOL_GPL(schedule_hrtimeout);
-- 
cgit v1.2.3


From df0cc0539b4127bd02f64de2c335b4af1fdb3845 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 31 Aug 2008 08:09:53 -0700
Subject: select: add a timespec_add_safe() function

For the select() rework, it's important to be able to add timespec
structures in an overflow-safe manner.

This patch adds a timespec_add_safe() function for this which is similar in
operation to ktime_add_safe(), but works on a struct timespec.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 include/linux/time.h |  4 ++++
 kernel/time.c        | 18 ++++++++++++++++++
 2 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/linux/time.h b/include/linux/time.h
index e15206a7e82e..726976478480 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -38,6 +38,8 @@ struct timezone {
 #define NSEC_PER_SEC	1000000000L
 #define FSEC_PER_SEC	1000000000000000L
 
+#define TIME_T_MAX	(time_t)((1UL << ((sizeof(time_t) << 3) - 1)) - 1)
+
 static inline int timespec_equal(const struct timespec *a,
                                  const struct timespec *b)
 {
@@ -72,6 +74,8 @@ extern unsigned long mktime(const unsigned int year, const unsigned int mon,
 			    const unsigned int min, const unsigned int sec);
 
 extern void set_normalized_timespec(struct timespec *ts, time_t sec, long nsec);
+extern struct timespec timespec_add_safe(const struct timespec lhs,
+					 const struct timespec rhs);
 
 /*
  * sub = lhs - rhs, in normalized form
diff --git a/kernel/time.c b/kernel/time.c
index 6a08660b4fac..d63a4336fad6 100644
--- a/kernel/time.c
+++ b/kernel/time.c
@@ -669,3 +669,21 @@ EXPORT_SYMBOL(get_jiffies_64);
 #endif
 
 EXPORT_SYMBOL(jiffies);
+
+/*
+ * Add two timespec values and do a safety check for overflow.
+ * It's assumed that both values are valid (>= 0)
+ */
+struct timespec timespec_add_safe(const struct timespec lhs,
+				  const struct timespec rhs)
+{
+	struct timespec res;
+
+	set_normalized_timespec(&res, lhs.tv_sec + rhs.tv_sec,
+				lhs.tv_nsec + rhs.tv_nsec);
+
+	if (res.tv_sec < lhs.tv_sec || res.tv_sec < rhs.tv_sec)
+		res.tv_sec = TIME_T_MAX;
+
+	return res;
+}
-- 
cgit v1.2.3


From b773ad40aca5bd755ba886620842f16e8fef6d75 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 31 Aug 2008 08:16:57 -0700
Subject: select: add poll_select_set_timeout() and
 poll_select_copy_remaining() helpers

This patch adds 2 helpers that will be used for the hrtimer based select/poll:

poll_select_set_timeout() is a helper that takes a timeout (as a second, nanosecond
pair) and turns that into a "struct timespec" that represents the absolute end time.
This is a common operation in the many select() and poll() variants and needs various,
common, sanity checks.

poll_select_copy_remaining() is a helper that takes care of copying the remaining
time to userspace, as select(), pselect() and ppoll() do. This function comes in
both a natural and a compat implementation (due to datastructure differences).

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 fs/compat.c          | 51 +++++++++++++++++++++++++++++++++++
 fs/select.c          | 75 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/poll.h |  2 ++
 3 files changed, 128 insertions(+)

(limited to 'include')

diff --git a/fs/compat.c b/fs/compat.c
index 075d0509970d..424767c954a0 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1436,6 +1436,57 @@ out_ret:
 
 #define __COMPAT_NFDBITS       (8 * sizeof(compat_ulong_t))
 
+static int poll_select_copy_remaining(struct timespec *end_time, void __user *p,
+				      int timeval, int ret)
+{
+	struct timespec ts;
+
+	if (!p)
+		return ret;
+
+	if (current->personality & STICKY_TIMEOUTS)
+		goto sticky;
+
+	/* No update for zero timeout */
+	if (!end_time->tv_sec && !end_time->tv_nsec)
+		return ret;
+
+	ktime_get_ts(&ts);
+	ts = timespec_sub(*end_time, ts);
+	if (ts.tv_sec < 0)
+		ts.tv_sec = ts.tv_nsec = 0;
+
+	if (timeval) {
+		struct compat_timeval rtv;
+
+		rtv.tv_sec = ts.tv_sec;
+		rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+
+		if (!copy_to_user(p, &rtv, sizeof(rtv)))
+			return ret;
+	} else {
+		struct compat_timespec rts;
+
+		rts.tv_sec = ts.tv_sec;
+		rts.tv_nsec = ts.tv_nsec;
+
+		if (!copy_to_user(p, &rts, sizeof(rts)))
+			return ret;
+	}
+	/*
+	 * If an application puts its timeval in read-only memory, we
+	 * don't want the Linux-specific update to the timeval to
+	 * cause a fault after the select has completed
+	 * successfully. However, because we're not updating the
+	 * timeval, we can't restart the system call.
+	 */
+
+sticky:
+	if (ret == -ERESTARTNOHAND)
+		ret = -EINTR;
+	return ret;
+}
+
 /*
  * Ooo, nasty.  We need here to frob 32-bit unsigned longs to
  * 64-bit unsigned longs.
diff --git a/fs/select.c b/fs/select.c
index da0e88201c3a..1180a6207789 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -130,6 +130,81 @@ static void __pollwait(struct file *filp, wait_queue_head_t *wait_address,
 	add_wait_queue(wait_address, &entry->wait);
 }
 
+/**
+ * poll_select_set_timeout - helper function to setup the timeout value
+ * @to:		pointer to timespec variable for the final timeout
+ * @sec:	seconds (from user space)
+ * @nsec:	nanoseconds (from user space)
+ *
+ * Note, we do not use a timespec for the user space value here, That
+ * way we can use the function for timeval and compat interfaces as well.
+ *
+ * Returns -EINVAL if sec/nsec are not normalized. Otherwise 0.
+ */
+int poll_select_set_timeout(struct timespec *to, long sec, long nsec)
+{
+	struct timespec ts = {.tv_sec = sec, .tv_nsec = nsec};
+
+	if (!timespec_valid(&ts))
+		return -EINVAL;
+
+	/* Optimize for the zero timeout value here */
+	if (!sec && !nsec) {
+		to->tv_sec = to->tv_nsec = 0;
+	} else {
+		ktime_get_ts(to);
+		*to = timespec_add_safe(*to, ts);
+	}
+	return 0;
+}
+
+static int poll_select_copy_remaining(struct timespec *end_time, void __user *p,
+				      int timeval, int ret)
+{
+	struct timespec rts;
+	struct timeval rtv;
+
+	if (!p)
+		return ret;
+
+	if (current->personality & STICKY_TIMEOUTS)
+		goto sticky;
+
+	/* No update for zero timeout */
+	if (!end_time->tv_sec && !end_time->tv_nsec)
+		return ret;
+
+	ktime_get_ts(&rts);
+	rts = timespec_sub(*end_time, rts);
+	if (rts.tv_sec < 0)
+		rts.tv_sec = rts.tv_nsec = 0;
+
+	if (timeval) {
+		rtv.tv_sec = rts.tv_sec;
+		rtv.tv_usec = rts.tv_nsec / NSEC_PER_USEC;
+
+		if (!copy_to_user(p, &rtv, sizeof(rtv)))
+			return ret;
+
+	} else if (!copy_to_user(p, &rts, sizeof(rts)))
+		return ret;
+
+	/*
+	 * If an application puts its timeval in read-only memory, we
+	 * don't want the Linux-specific update to the timeval to
+	 * cause a fault after the select has completed
+	 * successfully. However, because we're not updating the
+	 * timeval, we can't restart the system call.
+	 */
+
+sticky:
+	if (ret == -ERESTARTNOHAND)
+		ret = -EINTR;
+	return ret;
+}
+
+
+
 #define FDS_IN(fds, n)		(fds->in + n)
 #define FDS_OUT(fds, n)		(fds->out + n)
 #define FDS_EX(fds, n)		(fds->ex + n)
diff --git a/include/linux/poll.h b/include/linux/poll.h
index ef453828877a..f65de5128a9e 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -120,6 +120,8 @@ extern int do_sys_poll(struct pollfd __user * ufds, unsigned int nfds,
 extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
 			   fd_set __user *exp, s64 *timeout);
 
+extern int poll_select_set_timeout(struct timespec *to, long sec, long nsec);
+
 #endif /* KERNEL */
 
 #endif /* _LINUX_POLL_H */
-- 
cgit v1.2.3


From be5dad20a55e054a35dac7f6f5f184dc72b379b4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 31 Aug 2008 08:19:15 -0700
Subject: select: add a poll specific struct to the restart_block union

with hrtimer poll/select, the signal restart data no longer is a single
long representing a jiffies count, but it becomes a second/nanosecond pair
that also needs to encode if there was a timeout at all or not.

This patch adds a struct to the restart_block union for this purpose

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 include/linux/thread_info.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include')

diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index 38a56477f27a..e6b820f8b56b 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -38,6 +38,14 @@ struct restart_block {
 #endif
 			u64 expires;
 		} nanosleep;
+		/* For poll */
+		struct {
+			struct pollfd __user *ufds;
+			int nfds;
+			int has_timeout;
+			unsigned long tv_sec;
+			unsigned long tv_nsec;
+		} poll;
 	};
 };
 
-- 
cgit v1.2.3


From 8ff3e8e85fa6c312051134b3953e397feb639f51 Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Sun, 31 Aug 2008 08:26:40 -0700
Subject: select: switch select() and poll() over to hrtimers

With lots of help, input and cleanups from Thomas Gleixner

This patch switches select() and poll() over to hrtimers.

The core of the patch is replacing the "s64 timeout" with a
"struct timespec end_time" in all the plumbing.

But most of the diffstat comes from using the just introduced helpers:
	poll_select_set_timeout
	poll_select_copy_remaining
	timespec_add_safe
which make manipulating the timespec easier and less error-prone.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 fs/compat.c          | 136 ++++----------------------
 fs/select.c          | 263 +++++++++++++++++----------------------------------
 include/linux/poll.h |   6 +-
 3 files changed, 111 insertions(+), 294 deletions(-)

(limited to 'include')

diff --git a/fs/compat.c b/fs/compat.c
index 424767c954a0..133ed7f5d681 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1568,7 +1568,8 @@ int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
 	((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1)
 
 int compat_core_sys_select(int n, compat_ulong_t __user *inp,
-	compat_ulong_t __user *outp, compat_ulong_t __user *exp, s64 *timeout)
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+	struct timespec *end_time)
 {
 	fd_set_bits fds;
 	void *bits;
@@ -1615,7 +1616,7 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp,
 	zero_fd_set(n, fds.res_out);
 	zero_fd_set(n, fds.res_ex);
 
-	ret = do_select(n, &fds, timeout);
+	ret = do_select(n, &fds, end_time);
 
 	if (ret < 0)
 		goto out;
@@ -1641,7 +1642,7 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
 	struct compat_timeval __user *tvp)
 {
-	s64 timeout = -1;
+	struct timespec end_time, *to = NULL;
 	struct compat_timeval tv;
 	int ret;
 
@@ -1649,43 +1650,14 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp,
 		if (copy_from_user(&tv, tvp, sizeof(tv)))
 			return -EFAULT;
 
-		if (tv.tv_sec < 0 || tv.tv_usec < 0)
+		to = &end_time;
+		if (poll_select_set_timeout(to, tv.tv_sec,
+					    tv.tv_usec * NSEC_PER_USEC))
 			return -EINVAL;
-
-		/* Cast to u64 to make GCC stop complaining */
-		if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS)
-			timeout = -1;	/* infinite */
-		else {
-			timeout = DIV_ROUND_UP(tv.tv_usec, 1000000/HZ);
-			timeout += tv.tv_sec * HZ;
-		}
 	}
 
-	ret = compat_core_sys_select(n, inp, outp, exp, &timeout);
-
-	if (tvp) {
-		struct compat_timeval rtv;
-
-		if (current->personality & STICKY_TIMEOUTS)
-			goto sticky;
-		rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
-		rtv.tv_sec = timeout;
-		if (compat_timeval_compare(&rtv, &tv) >= 0)
-			rtv = tv;
-		if (copy_to_user(tvp, &rtv, sizeof(rtv))) {
-sticky:
-			/*
-			 * If an application puts its timeval in read-only
-			 * memory, we don't want the Linux-specific update to
-			 * the timeval to cause a fault after the select has
-			 * completed successfully. However, because we're not
-			 * updating the timeval, we can't restart the system
-			 * call.
-			 */
-			if (ret == -ERESTARTNOHAND)
-				ret = -EINTR;
-		}
-	}
+	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	ret = poll_select_copy_remaining(&end_time, tvp, 1, ret);
 
 	return ret;
 }
@@ -1698,15 +1670,16 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp,
 {
 	compat_sigset_t ss32;
 	sigset_t ksigmask, sigsaved;
-	s64 timeout = MAX_SCHEDULE_TIMEOUT;
 	struct compat_timespec ts;
+	struct timespec end_time, *to = NULL;
 	int ret;
 
 	if (tsp) {
 		if (copy_from_user(&ts, tsp, sizeof(ts)))
 			return -EFAULT;
 
-		if (ts.tv_sec < 0 || ts.tv_nsec < 0)
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
 			return -EINVAL;
 	}
 
@@ -1721,51 +1694,8 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp,
 		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
 	}
 
-	do {
-		if (tsp) {
-			if ((unsigned long)ts.tv_sec < MAX_SELECT_SECONDS) {
-				timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ);
-				timeout += ts.tv_sec * (unsigned long)HZ;
-				ts.tv_sec = 0;
-				ts.tv_nsec = 0;
-			} else {
-				ts.tv_sec -= MAX_SELECT_SECONDS;
-				timeout = MAX_SELECT_SECONDS * HZ;
-			}
-		}
-
-		ret = compat_core_sys_select(n, inp, outp, exp, &timeout);
-
-	} while (!ret && !timeout && tsp && (ts.tv_sec || ts.tv_nsec));
-
-	if (tsp) {
-		struct compat_timespec rts;
-
-		if (current->personality & STICKY_TIMEOUTS)
-			goto sticky;
-
-		rts.tv_sec = timeout / HZ;
-		rts.tv_nsec = (timeout % HZ) * (NSEC_PER_SEC/HZ);
-		if (rts.tv_nsec >= NSEC_PER_SEC) {
-			rts.tv_sec++;
-			rts.tv_nsec -= NSEC_PER_SEC;
-		}
-		if (compat_timespec_compare(&rts, &ts) >= 0)
-			rts = ts;
-		if (copy_to_user(tsp, &rts, sizeof(rts))) {
-sticky:
-			/*
-			 * If an application puts its timeval in read-only
-			 * memory, we don't want the Linux-specific update to
-			 * the timeval to cause a fault after the select has
-			 * completed successfully. However, because we're not
-			 * updating the timeval, we can't restart the system
-			 * call.
-			 */
-			if (ret == -ERESTARTNOHAND)
-				ret = -EINTR;
-		}
-	}
+	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
 
 	if (ret == -ERESTARTNOHAND) {
 		/*
@@ -1810,18 +1740,16 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
 	compat_sigset_t ss32;
 	sigset_t ksigmask, sigsaved;
 	struct compat_timespec ts;
-	s64 timeout = -1;
+	struct timespec end_time, *to = NULL;
 	int ret;
 
 	if (tsp) {
 		if (copy_from_user(&ts, tsp, sizeof(ts)))
 			return -EFAULT;
 
-		/* We assume that ts.tv_sec is always lower than
-		   the number of seconds that can be expressed in
-		   an s64. Otherwise the compiler bitches at us */
-		timeout = DIV_ROUND_UP(ts.tv_nsec, 1000000000/HZ);
-		timeout += ts.tv_sec * HZ;
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
+			return -EINVAL;
 	}
 
 	if (sigmask) {
@@ -1835,7 +1763,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
 		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
 	}
 
-	ret = do_sys_poll(ufds, nfds, &timeout);
+	ret = do_sys_poll(ufds, nfds, to);
 
 	/* We can restart this syscall, usually */
 	if (ret == -EINTR) {
@@ -1853,31 +1781,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
 	} else if (sigmask)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 
-	if (tsp && timeout >= 0) {
-		struct compat_timespec rts;
-
-		if (current->personality & STICKY_TIMEOUTS)
-			goto sticky;
-		/* Yes, we know it's actually an s64, but it's also positive. */
-		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
-					1000;
-		rts.tv_sec = timeout;
-		if (compat_timespec_compare(&rts, &ts) >= 0)
-			rts = ts;
-		if (copy_to_user(tsp, &rts, sizeof(rts))) {
-sticky:
-			/*
-			 * If an application puts its timeval in read-only
-			 * memory, we don't want the Linux-specific update to
-			 * the timeval to cause a fault after the select has
-			 * completed successfully. However, because we're not
-			 * updating the timeval, we can't restart the system
-			 * call.
-			 */
-			if (ret == -ERESTARTNOHAND && timeout >= 0)
-				ret = -EINTR;
-		}
-	}
+	ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
 
 	return ret;
 }
diff --git a/fs/select.c b/fs/select.c
index 1180a6207789..f6dceb56793f 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -24,6 +24,7 @@
 #include <linux/fdtable.h>
 #include <linux/fs.h>
 #include <linux/rcupdate.h>
+#include <linux/hrtimer.h>
 
 #include <asm/uaccess.h>
 
@@ -203,8 +204,6 @@ sticky:
 	return ret;
 }
 
-
-
 #define FDS_IN(fds, n)		(fds->in + n)
 #define FDS_OUT(fds, n)		(fds->out + n)
 #define FDS_EX(fds, n)		(fds->ex + n)
@@ -257,11 +256,12 @@ get_max:
 #define POLLOUT_SET (POLLWRBAND | POLLWRNORM | POLLOUT | POLLERR)
 #define POLLEX_SET (POLLPRI)
 
-int do_select(int n, fd_set_bits *fds, s64 *timeout)
+int do_select(int n, fd_set_bits *fds, struct timespec *end_time)
 {
+	ktime_t expire, *to = NULL;
 	struct poll_wqueues table;
 	poll_table *wait;
-	int retval, i;
+	int retval, i, timed_out = 0;
 
 	rcu_read_lock();
 	retval = max_select_fd(n, fds);
@@ -273,12 +273,14 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout)
 
 	poll_initwait(&table);
 	wait = &table.pt;
-	if (!*timeout)
+	if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
 		wait = NULL;
+		timed_out = 1;
+	}
+
 	retval = 0;
 	for (;;) {
 		unsigned long *rinp, *routp, *rexp, *inp, *outp, *exp;
-		long __timeout;
 
 		set_current_state(TASK_INTERRUPTIBLE);
 
@@ -334,27 +336,25 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout)
 			cond_resched();
 		}
 		wait = NULL;
-		if (retval || !*timeout || signal_pending(current))
+		if (retval || timed_out || signal_pending(current))
 			break;
 		if (table.error) {
 			retval = table.error;
 			break;
 		}
 
-		if (*timeout < 0) {
-			/* Wait indefinitely */
-			__timeout = MAX_SCHEDULE_TIMEOUT;
-		} else if (unlikely(*timeout >= (s64)MAX_SCHEDULE_TIMEOUT - 1)) {
-			/* Wait for longer than MAX_SCHEDULE_TIMEOUT. Do it in a loop */
-			__timeout = MAX_SCHEDULE_TIMEOUT - 1;
-			*timeout -= __timeout;
-		} else {
-			__timeout = *timeout;
-			*timeout = 0;
+		/*
+		 * If this is the first loop and we have a timeout
+		 * given, then we convert to ktime_t and set the to
+		 * pointer to the expiry value.
+		 */
+		if (end_time && !to) {
+			expire = timespec_to_ktime(*end_time);
+			to = &expire;
 		}
-		__timeout = schedule_timeout(__timeout);
-		if (*timeout >= 0)
-			*timeout += __timeout;
+
+		if (!schedule_hrtimeout(to, HRTIMER_MODE_ABS))
+			timed_out = 1;
 	}
 	__set_current_state(TASK_RUNNING);
 
@@ -375,7 +375,7 @@ int do_select(int n, fd_set_bits *fds, s64 *timeout)
 	((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1)
 
 int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
-			   fd_set __user *exp, s64 *timeout)
+			   fd_set __user *exp, struct timespec *end_time)
 {
 	fd_set_bits fds;
 	void *bits;
@@ -426,7 +426,7 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
 	zero_fd_set(n, fds.res_out);
 	zero_fd_set(n, fds.res_ex);
 
-	ret = do_select(n, &fds, timeout);
+	ret = do_select(n, &fds, end_time);
 
 	if (ret < 0)
 		goto out;
@@ -452,7 +452,7 @@ out_nofds:
 asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp,
 			fd_set __user *exp, struct timeval __user *tvp)
 {
-	s64 timeout = -1;
+	struct timespec end_time, *to = NULL;
 	struct timeval tv;
 	int ret;
 
@@ -460,43 +460,14 @@ asmlinkage long sys_select(int n, fd_set __user *inp, fd_set __user *outp,
 		if (copy_from_user(&tv, tvp, sizeof(tv)))
 			return -EFAULT;
 
-		if (tv.tv_sec < 0 || tv.tv_usec < 0)
+		to = &end_time;
+		if (poll_select_set_timeout(to, tv.tv_sec,
+					    tv.tv_usec * NSEC_PER_USEC))
 			return -EINVAL;
-
-		/* Cast to u64 to make GCC stop complaining */
-		if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS)
-			timeout = -1;	/* infinite */
-		else {
-			timeout = DIV_ROUND_UP(tv.tv_usec, USEC_PER_SEC/HZ);
-			timeout += tv.tv_sec * HZ;
-		}
 	}
 
-	ret = core_sys_select(n, inp, outp, exp, &timeout);
-
-	if (tvp) {
-		struct timeval rtv;
-
-		if (current->personality & STICKY_TIMEOUTS)
-			goto sticky;
-		rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ));
-		rtv.tv_sec = timeout;
-		if (timeval_compare(&rtv, &tv) >= 0)
-			rtv = tv;
-		if (copy_to_user(tvp, &rtv, sizeof(rtv))) {
-sticky:
-			/*
-			 * If an application puts its timeval in read-only
-			 * memory, we don't want the Linux-specific update to
-			 * the timeval to cause a fault after the select has
-			 * completed successfully. However, because we're not
-			 * updating the timeval, we can't restart the system
-			 * call.
-			 */
-			if (ret == -ERESTARTNOHAND)
-				ret = -EINTR;
-		}
-	}
+	ret = core_sys_select(n, inp, outp, exp, to);
+	ret = poll_select_copy_remaining(&end_time, tvp, 1, ret);
 
 	return ret;
 }
@@ -506,25 +477,17 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp,
 		fd_set __user *exp, struct timespec __user *tsp,
 		const sigset_t __user *sigmask, size_t sigsetsize)
 {
-	s64 timeout = MAX_SCHEDULE_TIMEOUT;
 	sigset_t ksigmask, sigsaved;
-	struct timespec ts;
+	struct timespec ts, end_time, *to = NULL;
 	int ret;
 
 	if (tsp) {
 		if (copy_from_user(&ts, tsp, sizeof(ts)))
 			return -EFAULT;
 
-		if (ts.tv_sec < 0 || ts.tv_nsec < 0)
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
 			return -EINVAL;
-
-		/* Cast to u64 to make GCC stop complaining */
-		if ((u64)ts.tv_sec >= (u64)MAX_INT64_SECONDS)
-			timeout = -1;	/* infinite */
-		else {
-			timeout = DIV_ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ);
-			timeout += ts.tv_sec * HZ;
-		}
 	}
 
 	if (sigmask) {
@@ -538,32 +501,8 @@ asmlinkage long sys_pselect7(int n, fd_set __user *inp, fd_set __user *outp,
 		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
 	}
 
-	ret = core_sys_select(n, inp, outp, exp, &timeout);
-
-	if (tsp) {
-		struct timespec rts;
-
-		if (current->personality & STICKY_TIMEOUTS)
-			goto sticky;
-		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
-						1000;
-		rts.tv_sec = timeout;
-		if (timespec_compare(&rts, &ts) >= 0)
-			rts = ts;
-		if (copy_to_user(tsp, &rts, sizeof(rts))) {
-sticky:
-			/*
-			 * If an application puts its timeval in read-only
-			 * memory, we don't want the Linux-specific update to
-			 * the timeval to cause a fault after the select has
-			 * completed successfully. However, because we're not
-			 * updating the timeval, we can't restart the system
-			 * call.
-			 */
-			if (ret == -ERESTARTNOHAND)
-				ret = -EINTR;
-		}
-	}
+	ret = core_sys_select(n, inp, outp, exp, &end_time);
+	ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
 
 	if (ret == -ERESTARTNOHAND) {
 		/*
@@ -649,18 +588,20 @@ static inline unsigned int do_pollfd(struct pollfd *pollfd, poll_table *pwait)
 }
 
 static int do_poll(unsigned int nfds,  struct poll_list *list,
-		   struct poll_wqueues *wait, s64 *timeout)
+		   struct poll_wqueues *wait, struct timespec *end_time)
 {
-	int count = 0;
 	poll_table* pt = &wait->pt;
+	ktime_t expire, *to = NULL;
+	int timed_out = 0, count = 0;
 
 	/* Optimise the no-wait case */
-	if (!(*timeout))
+	if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
 		pt = NULL;
+		timed_out = 1;
+	}
 
 	for (;;) {
 		struct poll_list *walk;
-		long __timeout;
 
 		set_current_state(TASK_INTERRUPTIBLE);
 		for (walk = list; walk != NULL; walk = walk->next) {
@@ -692,27 +633,21 @@ static int do_poll(unsigned int nfds,  struct poll_list *list,
 			if (signal_pending(current))
 				count = -EINTR;
 		}
-		if (count || !*timeout)
+		if (count || timed_out)
 			break;
 
-		if (*timeout < 0) {
-			/* Wait indefinitely */
-			__timeout = MAX_SCHEDULE_TIMEOUT;
-		} else if (unlikely(*timeout >= (s64)MAX_SCHEDULE_TIMEOUT-1)) {
-			/*
-			 * Wait for longer than MAX_SCHEDULE_TIMEOUT. Do it in
-			 * a loop
-			 */
-			__timeout = MAX_SCHEDULE_TIMEOUT - 1;
-			*timeout -= __timeout;
-		} else {
-			__timeout = *timeout;
-			*timeout = 0;
+		/*
+		 * If this is the first loop and we have a timeout
+		 * given, then we convert to ktime_t and set the to
+		 * pointer to the expiry value.
+		 */
+		if (end_time && !to) {
+			expire = timespec_to_ktime(*end_time);
+			to = &expire;
 		}
 
-		__timeout = schedule_timeout(__timeout);
-		if (*timeout >= 0)
-			*timeout += __timeout;
+		if (!schedule_hrtimeout(to, HRTIMER_MODE_ABS))
+			timed_out = 1;
 	}
 	__set_current_state(TASK_RUNNING);
 	return count;
@@ -721,7 +656,8 @@ static int do_poll(unsigned int nfds,  struct poll_list *list,
 #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list))  / \
 			sizeof(struct pollfd))
 
-int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, s64 *timeout)
+int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
+		struct timespec *end_time)
 {
 	struct poll_wqueues table;
  	int err = -EFAULT, fdcount, len, size;
@@ -761,7 +697,7 @@ int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds, s64 *timeout)
 	}
 
 	poll_initwait(&table);
-	fdcount = do_poll(nfds, head, &table, timeout);
+	fdcount = do_poll(nfds, head, &table, end_time);
 	poll_freewait(&table);
 
 	for (walk = head; walk; walk = walk->next) {
@@ -787,16 +723,21 @@ out_fds:
 
 static long do_restart_poll(struct restart_block *restart_block)
 {
-	struct pollfd __user *ufds = (struct pollfd __user*)restart_block->arg0;
-	int nfds = restart_block->arg1;
-	s64 timeout = ((s64)restart_block->arg3<<32) | (s64)restart_block->arg2;
+	struct pollfd __user *ufds = restart_block->poll.ufds;
+	int nfds = restart_block->poll.nfds;
+	struct timespec *to = NULL, end_time;
 	int ret;
 
-	ret = do_sys_poll(ufds, nfds, &timeout);
+	if (restart_block->poll.has_timeout) {
+		end_time.tv_sec = restart_block->poll.tv_sec;
+		end_time.tv_nsec = restart_block->poll.tv_nsec;
+		to = &end_time;
+	}
+
+	ret = do_sys_poll(ufds, nfds, to);
+
 	if (ret == -EINTR) {
 		restart_block->fn = do_restart_poll;
-		restart_block->arg2 = timeout & 0xFFFFFFFF;
-		restart_block->arg3 = (u64)timeout >> 32;
 		ret = -ERESTART_RESTARTBLOCK;
 	}
 	return ret;
@@ -805,31 +746,32 @@ static long do_restart_poll(struct restart_block *restart_block)
 asmlinkage long sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 			long timeout_msecs)
 {
-	s64 timeout_jiffies;
+	struct timespec end_time, *to = NULL;
 	int ret;
 
-	if (timeout_msecs > 0) {
-#if HZ > 1000
-		/* We can only overflow if HZ > 1000 */
-		if (timeout_msecs / 1000 > (s64)0x7fffffffffffffffULL / (s64)HZ)
-			timeout_jiffies = -1;
-		else
-#endif
-			timeout_jiffies = msecs_to_jiffies(timeout_msecs) + 1;
-	} else {
-		/* Infinite (< 0) or no (0) timeout */
-		timeout_jiffies = timeout_msecs;
+	if (timeout_msecs >= 0) {
+		to = &end_time;
+		poll_select_set_timeout(to, timeout_msecs / MSEC_PER_SEC,
+			NSEC_PER_MSEC * (timeout_msecs % MSEC_PER_SEC));
 	}
 
-	ret = do_sys_poll(ufds, nfds, &timeout_jiffies);
+	ret = do_sys_poll(ufds, nfds, to);
+
 	if (ret == -EINTR) {
 		struct restart_block *restart_block;
+
 		restart_block = &current_thread_info()->restart_block;
 		restart_block->fn = do_restart_poll;
-		restart_block->arg0 = (unsigned long)ufds;
-		restart_block->arg1 = nfds;
-		restart_block->arg2 = timeout_jiffies & 0xFFFFFFFF;
-		restart_block->arg3 = (u64)timeout_jiffies >> 32;
+		restart_block->poll.ufds = ufds;
+		restart_block->poll.nfds = nfds;
+
+		if (timeout_msecs >= 0) {
+			restart_block->poll.tv_sec = end_time.tv_sec;
+			restart_block->poll.tv_nsec = end_time.tv_nsec;
+			restart_block->poll.has_timeout = 1;
+		} else
+			restart_block->poll.has_timeout = 0;
+
 		ret = -ERESTART_RESTARTBLOCK;
 	}
 	return ret;
@@ -841,21 +783,16 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
 	size_t sigsetsize)
 {
 	sigset_t ksigmask, sigsaved;
-	struct timespec ts;
-	s64 timeout = -1;
+	struct timespec ts, end_time, *to = NULL;
 	int ret;
 
 	if (tsp) {
 		if (copy_from_user(&ts, tsp, sizeof(ts)))
 			return -EFAULT;
 
-		/* Cast to u64 to make GCC stop complaining */
-		if ((u64)ts.tv_sec >= (u64)MAX_INT64_SECONDS)
-			timeout = -1;	/* infinite */
-		else {
-			timeout = DIV_ROUND_UP(ts.tv_nsec, NSEC_PER_SEC/HZ);
-			timeout += ts.tv_sec * HZ;
-		}
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
+			return -EINVAL;
 	}
 
 	if (sigmask) {
@@ -869,7 +806,7 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
 		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
 	}
 
-	ret = do_sys_poll(ufds, nfds, &timeout);
+	ret = do_sys_poll(ufds, nfds, to);
 
 	/* We can restart this syscall, usually */
 	if (ret == -EINTR) {
@@ -887,31 +824,7 @@ asmlinkage long sys_ppoll(struct pollfd __user *ufds, unsigned int nfds,
 	} else if (sigmask)
 		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
 
-	if (tsp && timeout >= 0) {
-		struct timespec rts;
-
-		if (current->personality & STICKY_TIMEOUTS)
-			goto sticky;
-		/* Yes, we know it's actually an s64, but it's also positive. */
-		rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) *
-						1000;
-		rts.tv_sec = timeout;
-		if (timespec_compare(&rts, &ts) >= 0)
-			rts = ts;
-		if (copy_to_user(tsp, &rts, sizeof(rts))) {
-		sticky:
-			/*
-			 * If an application puts its timeval in read-only
-			 * memory, we don't want the Linux-specific update to
-			 * the timeval to cause a fault after the select has
-			 * completed successfully. However, because we're not
-			 * updating the timeval, we can't restart the system
-			 * call.
-			 */
-			if (ret == -ERESTARTNOHAND && timeout >= 0)
-				ret = -EINTR;
-		}
-	}
+	ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
 
 	return ret;
 }
diff --git a/include/linux/poll.h b/include/linux/poll.h
index f65de5128a9e..badd98ab06f6 100644
--- a/include/linux/poll.h
+++ b/include/linux/poll.h
@@ -114,11 +114,11 @@ void zero_fd_set(unsigned long nr, unsigned long *fdset)
 
 #define MAX_INT64_SECONDS (((s64)(~((u64)0)>>1)/HZ)-1)
 
-extern int do_select(int n, fd_set_bits *fds, s64 *timeout);
+extern int do_select(int n, fd_set_bits *fds, struct timespec *end_time);
 extern int do_sys_poll(struct pollfd __user * ufds, unsigned int nfds,
-		       s64 *timeout);
+		       struct timespec *end_time);
 extern int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
-			   fd_set __user *exp, s64 *timeout);
+			   fd_set __user *exp, struct timespec *end_time);
 
 extern int poll_select_set_timeout(struct timespec *to, long sec, long nsec);
 
-- 
cgit v1.2.3


From 63ca243b271f5b44e0b1057003cf498b6d0fadf7 Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Mon, 1 Sep 2008 14:35:02 -0700
Subject: hrtimer: add abstraction functions for accessing the "expires" member

In order to be able to turn hrtimers into range based, we need to provide
accessor functions for getting to the "expires" ktime_t member of the
struct hrtimer.

This patch adds a set of accessors for this purpose:
* hrtimer_set_expires
* hrtimer_set_expires_tv64
* hrtimer_add_expires
* hrtimer_add_expires_ns
* hrtimer_get_expires
* hrtimer_get_expires_tv64
* hrtimer_get_expires_ns
* hrtimer_expires_remaining
* hrtimer_start_expires

No users of these new accessors are added yet; these follow in later patches.
Hopefully this patch can even go into 2.6.27-rc so that the conversions will
not have a bottleneck in -next

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 include/linux/hrtimer.h | 45 +++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index becd17db1a1a..9900e998ea8f 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -217,6 +217,45 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 	return timer->base->cpu_base->hres_active;
 }
 
+static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
+{
+	timer->expires = time;
+}
+static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64)
+{
+	timer->expires.tv64 = tv64;
+}
+
+static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time)
+{
+	timer->expires = ktime_add_safe(timer->expires, time);
+}
+
+static inline void hrtimer_add_expires_ns(struct hrtimer *timer, unsigned long ns)
+{
+	timer->expires = ktime_add_ns(timer->expires, ns);
+}
+
+static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer)
+{
+	return timer->expires;
+}
+
+static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer)
+{
+	return timer->expires.tv64;
+}
+
+static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer)
+{
+	return ktime_to_ns(timer->expires);
+}
+
+static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
+{
+    return ktime_sub(timer->expires, timer->base->get_time());
+}
+
 /*
  * The resolution of the clocks. The resolution value is returned in
  * the clock_getres() system call to give application programmers an
@@ -287,6 +326,12 @@ extern int hrtimer_start(struct hrtimer *timer, ktime_t tim,
 extern int hrtimer_cancel(struct hrtimer *timer);
 extern int hrtimer_try_to_cancel(struct hrtimer *timer);
 
+static inline int hrtimer_start_expires(struct hrtimer *timer,
+						enum hrtimer_mode mode)
+{
+	return hrtimer_start(timer, hrtimer_get_expires(timer), mode);
+}
+
 static inline int hrtimer_restart(struct hrtimer *timer)
 {
 	return hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS);
-- 
cgit v1.2.3


From 799b64de256ea68fbb5db63bb55f61c305870643 Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Mon, 1 Sep 2008 15:27:58 -0700
Subject: hrtimer: rename the "expires" struct member to avoid accidental usage

To catch code that still touches the "expires" memory directly, rename it
to have the compiler complain rather than get nasty, hard to explain,
runtime behavior

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 include/linux/hrtimer.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 9900e998ea8f..485a634fd6e2 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -111,7 +111,7 @@ enum hrtimer_cb_mode {
  */
 struct hrtimer {
 	struct rb_node			node;
-	ktime_t				expires;
+	ktime_t				_expires;
 	enum hrtimer_restart		(*function)(struct hrtimer *);
 	struct hrtimer_clock_base	*base;
 	unsigned long			state;
@@ -219,41 +219,41 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 
 static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
 {
-	timer->expires = time;
+	timer->_expires = time;
 }
 static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64)
 {
-	timer->expires.tv64 = tv64;
+	timer->_expires.tv64 = tv64;
 }
 
 static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time)
 {
-	timer->expires = ktime_add_safe(timer->expires, time);
+	timer->_expires = ktime_add_safe(timer->_expires, time);
 }
 
 static inline void hrtimer_add_expires_ns(struct hrtimer *timer, unsigned long ns)
 {
-	timer->expires = ktime_add_ns(timer->expires, ns);
+	timer->_expires = ktime_add_ns(timer->_expires, ns);
 }
 
 static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer)
 {
-	return timer->expires;
+	return timer->_expires;
 }
 
 static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer)
 {
-	return timer->expires.tv64;
+	return timer->_expires.tv64;
 }
 
 static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer)
 {
-	return ktime_to_ns(timer->expires);
+	return ktime_to_ns(timer->_expires);
 }
 
 static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
 {
-    return ktime_sub(timer->expires, timer->base->get_time());
+    return ktime_sub(timer->_expires, timer->base->get_time());
 }
 
 /*
@@ -334,7 +334,7 @@ static inline int hrtimer_start_expires(struct hrtimer *timer,
 
 static inline int hrtimer_restart(struct hrtimer *timer)
 {
-	return hrtimer_start(timer, timer->expires, HRTIMER_MODE_ABS);
+	return hrtimer_start(timer, timer->_expires, HRTIMER_MODE_ABS);
 }
 
 /* Query timers: */
-- 
cgit v1.2.3


From 654c8e0b1c623b156c5b92f28d914ab38c9c2c90 Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Mon, 1 Sep 2008 15:47:08 -0700
Subject: hrtimer: turn hrtimers into range timers

this patch turns hrtimers into range timers; they have 2 expire points
1) the soft expire point
2) the hard expire point

the kernel will do it's regular best effort attempt to get the timer run
at the hard expire point. However, if some other time fires after the soft
expire point, the kernel now has the freedom to fire this timer at this point,
and thus grouping the events and preventing a power-expensive wakeup in the
future.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 include/linux/hrtimer.h | 31 ++++++++++++++++++++++++++-
 kernel/hrtimer.c        | 56 +++++++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 82 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 485a634fd6e2..28259c336679 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -112,6 +112,7 @@ enum hrtimer_cb_mode {
 struct hrtimer {
 	struct rb_node			node;
 	ktime_t				_expires;
+	ktime_t				_softexpires;
 	enum hrtimer_restart		(*function)(struct hrtimer *);
 	struct hrtimer_clock_base	*base;
 	unsigned long			state;
@@ -220,20 +221,37 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
 {
 	timer->_expires = time;
+	timer->_softexpires = time;
 }
+
+static inline void hrtimer_set_expires_range(struct hrtimer *timer, ktime_t time, ktime_t delta)
+{
+	timer->_softexpires = time;
+	timer->_expires = ktime_add_safe(time, delta);
+}
+
+static inline void hrtimer_set_expires_range_ns(struct hrtimer *timer, ktime_t time, unsigned long delta)
+{
+	timer->_softexpires = time;
+	timer->_expires = ktime_add_safe(time, ns_to_ktime(delta));
+}
+
 static inline void hrtimer_set_expires_tv64(struct hrtimer *timer, s64 tv64)
 {
 	timer->_expires.tv64 = tv64;
+	timer->_softexpires.tv64 = tv64;
 }
 
 static inline void hrtimer_add_expires(struct hrtimer *timer, ktime_t time)
 {
 	timer->_expires = ktime_add_safe(timer->_expires, time);
+	timer->_softexpires = ktime_add_safe(timer->_softexpires, time);
 }
 
 static inline void hrtimer_add_expires_ns(struct hrtimer *timer, unsigned long ns)
 {
 	timer->_expires = ktime_add_ns(timer->_expires, ns);
+	timer->_softexpires = ktime_add_ns(timer->_softexpires, ns);
 }
 
 static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer)
@@ -241,10 +259,19 @@ static inline ktime_t hrtimer_get_expires(const struct hrtimer *timer)
 	return timer->_expires;
 }
 
+static inline ktime_t hrtimer_get_softexpires(const struct hrtimer *timer)
+{
+	return timer->_softexpires;
+}
+
 static inline s64 hrtimer_get_expires_tv64(const struct hrtimer *timer)
 {
 	return timer->_expires.tv64;
 }
+static inline s64 hrtimer_get_softexpires_tv64(const struct hrtimer *timer)
+{
+	return timer->_softexpires.tv64;
+}
 
 static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer)
 {
@@ -334,7 +361,7 @@ static inline int hrtimer_start_expires(struct hrtimer *timer,
 
 static inline int hrtimer_restart(struct hrtimer *timer)
 {
-	return hrtimer_start(timer, timer->_expires, HRTIMER_MODE_ABS);
+	return hrtimer_start_expires(timer, HRTIMER_MODE_ABS);
 }
 
 /* Query timers: */
@@ -391,6 +418,8 @@ extern long hrtimer_nanosleep_restart(struct restart_block *restart_block);
 extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl,
 				 struct task_struct *tsk);
 
+extern int schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
+						const enum hrtimer_mode mode);
 extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
 
 /* Soft interrupt function to run the hrtimer queues: */
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index ae307feec74c..01483004183d 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1309,7 +1309,20 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 
 			timer = rb_entry(node, struct hrtimer, node);
 
-			if (basenow.tv64 < hrtimer_get_expires_tv64(timer)) {
+			/*
+			 * The immediate goal for using the softexpires is
+			 * minimizing wakeups, not running timers at the
+			 * earliest interrupt after their soft expiration.
+			 * This allows us to avoid using a Priority Search
+			 * Tree, which can answer a stabbing querry for
+			 * overlapping intervals and instead use the simple
+			 * BST we already have.
+			 * We don't add extra wakeups by delaying timers that
+			 * are right-of a not yet expired timer, because that
+			 * timer will have to trigger a wakeup anyway.
+			 */
+
+			if (basenow.tv64 < hrtimer_get_softexpires_tv64(timer)) {
 				ktime_t expires;
 
 				expires = ktime_sub(hrtimer_get_expires(timer),
@@ -1681,14 +1694,20 @@ void __init hrtimers_init(void)
 }
 
 /**
- * schedule_hrtimeout - sleep until timeout
+ * schedule_hrtimeout_range - sleep until timeout
  * @expires:	timeout value (ktime_t)
+ * @delta:	slack in expires timeout (ktime_t)
  * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
  *
  * Make the current task sleep until the given expiry time has
  * elapsed. The routine will return immediately unless
  * the current task state has been set (see set_current_state()).
  *
+ * The @delta argument gives the kernel the freedom to schedule the
+ * actual wakeup to a time that is both power and performance friendly.
+ * The kernel give the normal best effort behavior for "@expires+@delta",
+ * but may decide to fire the timer earlier, but no earlier than @expires.
+ *
  * You can set the task state as follows -
  *
  * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
@@ -1702,7 +1721,7 @@ void __init hrtimers_init(void)
  *
  * Returns 0 when the timer has expired otherwise -EINTR
  */
-int __sched schedule_hrtimeout(ktime_t *expires,
+int __sched schedule_hrtimeout_range(ktime_t *expires, unsigned long delta,
 			       const enum hrtimer_mode mode)
 {
 	struct hrtimer_sleeper t;
@@ -1726,7 +1745,7 @@ int __sched schedule_hrtimeout(ktime_t *expires,
 	}
 
 	hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, mode);
-	hrtimer_set_expires(&t.timer, *expires);
+	hrtimer_set_expires_range_ns(&t.timer, *expires, delta);
 
 	hrtimer_init_sleeper(&t, current);
 
@@ -1744,4 +1763,33 @@ int __sched schedule_hrtimeout(ktime_t *expires,
 
 	return !t.task ? 0 : -EINTR;
 }
+EXPORT_SYMBOL_GPL(schedule_hrtimeout_range);
+
+/**
+ * schedule_hrtimeout - sleep until timeout
+ * @expires:	timeout value (ktime_t)
+ * @mode:	timer mode, HRTIMER_MODE_ABS or HRTIMER_MODE_REL
+ *
+ * Make the current task sleep until the given expiry time has
+ * elapsed. The routine will return immediately unless
+ * the current task state has been set (see set_current_state()).
+ *
+ * You can set the task state as follows -
+ *
+ * %TASK_UNINTERRUPTIBLE - at least @timeout time is guaranteed to
+ * pass before the routine returns.
+ *
+ * %TASK_INTERRUPTIBLE - the routine may return early if a signal is
+ * delivered to the current task.
+ *
+ * The current task state is guaranteed to be TASK_RUNNING when this
+ * routine returns.
+ *
+ * Returns 0 when the timer has expired otherwise -EINTR
+ */
+int __sched schedule_hrtimeout(ktime_t *expires,
+			       const enum hrtimer_mode mode)
+{
+	return schedule_hrtimeout_range(expires, 0, mode);
+}
 EXPORT_SYMBOL_GPL(schedule_hrtimeout);
-- 
cgit v1.2.3


From 6976675d94042fbd446231d1bd8b7de71a980ada Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Mon, 1 Sep 2008 15:52:40 -0700
Subject: hrtimer: create a "timer_slack" field in the task struct

We want to be able to control the default "rounding" that is used by
select() and poll() and friends. This is a per process property
(so that we can have a "nice" like program to start certain programs with
a looser or stricter rounding) that can be set/get via a prctl().

For this purpose, a field called "timer_slack_ns" is added to the task
struct. In addition, a field called "default_timer_slack"ns" is added
so that tasks easily can temporarily to a more/less accurate slack and then
back to the default.

The default value of the slack is set to 50 usec; this is significantly less
than 2.6.27's average select() and poll() timing error but still allows
the kernel to group timers somewhat to preserve power behavior. Applications
and admins can override this via the prctl()

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 include/linux/init_task.h |  1 +
 include/linux/prctl.h     |  7 +++++++
 include/linux/sched.h     |  6 ++++++
 kernel/fork.c             |  2 ++
 kernel/sys.c              | 10 ++++++++++
 5 files changed, 26 insertions(+)

(limited to 'include')

diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 021d8e720c79..23fd8909b9e5 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -170,6 +170,7 @@ extern struct group_info init_groups;
 	.cpu_timers	= INIT_CPU_TIMERS(tsk.cpu_timers),		\
 	.fs_excl	= ATOMIC_INIT(0),				\
 	.pi_lock	= __SPIN_LOCK_UNLOCKED(tsk.pi_lock),		\
+	.timer_slack_ns = 50000, /* 50 usec default slack */		\
 	.pids = {							\
 		[PIDTYPE_PID]  = INIT_PID_LINK(PIDTYPE_PID),		\
 		[PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID),		\
diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index 5ad79198d6f9..48d887e3c6e7 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -78,4 +78,11 @@
 #define PR_GET_SECUREBITS 27
 #define PR_SET_SECUREBITS 28
 
+/*
+ * Get/set the timerslack as used by poll/select/nanosleep
+ * A value of 0 means "use default"
+ */
+#define PR_SET_TIMERSLACK 29
+#define PR_GET_TIMERSLACK 30
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3d9120c5ad15..dcc03fd5a7f3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1301,6 +1301,12 @@ struct task_struct {
 	int latency_record_count;
 	struct latency_record latency_record[LT_SAVECOUNT];
 #endif
+	/*
+	 * time slack values; these are used to round up poll() and
+	 * select() etc timeout values. These are in nanoseconds.
+	 */
+	unsigned long timer_slack_ns;
+	unsigned long default_timer_slack_ns;
 };
 
 /*
diff --git a/kernel/fork.c b/kernel/fork.c
index 7ce2ebe84796..4308d75f0fa5 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -987,6 +987,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	p->prev_utime = cputime_zero;
 	p->prev_stime = cputime_zero;
 
+	p->default_timer_slack_ns = current->timer_slack_ns;
+
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 	p->last_switch_count = 0;
 	p->last_switch_timestamp = 0;
diff --git a/kernel/sys.c b/kernel/sys.c
index 038a7bc0901d..1b96401a0576 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -1727,6 +1727,16 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 		case PR_SET_TSC:
 			error = SET_TSC_CTL(arg2);
 			break;
+		case PR_GET_TIMERSLACK:
+			error = current->timer_slack_ns;
+			break;
+		case PR_SET_TIMERSLACK:
+			if (arg2 <= 0)
+				current->timer_slack_ns =
+					current->default_timer_slack_ns;
+			else
+				current->timer_slack_ns = arg2;
+			break;
 		default:
 			error = -EINVAL;
 			break;
-- 
cgit v1.2.3


From 584fb4a76413ec9215741e075e0dfb69173b213f Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Sat, 6 Sep 2008 08:32:57 -0700
Subject: hrtimer: fix build bug found by Ingo

in some randconfig configurations, hrtimers are used even though
the hrtimer config if off; and it broke the build due to some of
the new functions being on the wrong side of the ifdef.

This patch moves the functions to the other side of the ifdef, fixing
the build bug.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 include/linux/hrtimer.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 28259c336679..c407b33ef844 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -198,13 +198,6 @@ struct hrtimer_cpu_base {
 #endif
 };
 
-#ifdef CONFIG_HIGH_RES_TIMERS
-struct clock_event_device;
-
-extern void clock_was_set(void);
-extern void hres_timers_resume(void);
-extern void hrtimer_interrupt(struct clock_event_device *dev);
-
 /*
  * In high resolution mode the time reference must be read accurate
  */
@@ -283,6 +276,13 @@ static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
     return ktime_sub(timer->_expires, timer->base->get_time());
 }
 
+#ifdef CONFIG_HIGH_RES_TIMERS
+struct clock_event_device;
+
+extern void clock_was_set(void);
+extern void hres_timers_resume(void);
+extern void hrtimer_interrupt(struct clock_event_device *dev);
+
 /*
  * The resolution of the clocks. The resolution value is returned in
  * the clock_getres() system call to give application programmers an
-- 
cgit v1.2.3


From 2ec02270c00f94b08fddfb68c37510a9fb47ac7c Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Sat, 6 Sep 2008 09:36:56 -0700
Subject: hrtimer: another build fix

More randconfig testing

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 include/linux/hrtimer.h | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index c407b33ef844..4c1a834b9849 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -198,19 +198,6 @@ struct hrtimer_cpu_base {
 #endif
 };
 
-/*
- * In high resolution mode the time reference must be read accurate
- */
-static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
-{
-	return timer->base->get_time();
-}
-
-static inline int hrtimer_is_hres_active(struct hrtimer *timer)
-{
-	return timer->base->cpu_base->hres_active;
-}
-
 static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
 {
 	timer->_expires = time;
@@ -283,6 +270,19 @@ extern void clock_was_set(void);
 extern void hres_timers_resume(void);
 extern void hrtimer_interrupt(struct clock_event_device *dev);
 
+/*
+ * In high resolution mode the time reference must be read accurate
+ */
+static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
+{
+	return timer->base->get_time();
+}
+
+static inline int hrtimer_is_hres_active(struct hrtimer *timer)
+{
+	return timer->base->cpu_base->hres_active;
+}
+
 /*
  * The resolution of the clocks. The resolution value is returned in
  * the clock_getres() system call to give application programmers an
-- 
cgit v1.2.3


From da8f2e170ea94cc20f8ebbc8ee8d127edb8f12f1 Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Sun, 7 Sep 2008 10:47:46 -0700
Subject: hrtimer: add a hrtimer_start_range() function

this patch adds a _range version of hrtimer_start() so that range timers
can be created; the hrtimer_start() function is just a wrapper around this.

In addition, hrtimer_start_expires() will now preserve existing ranges.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 include/linux/hrtimer.h |  9 ++++++++-
 kernel/hrtimer.c        | 26 +++++++++++++++++++++++---
 2 files changed, 31 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 4c1a834b9849..1c0473e8ecb4 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -350,13 +350,20 @@ static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
 /* Basic timer operations: */
 extern int hrtimer_start(struct hrtimer *timer, ktime_t tim,
 			 const enum hrtimer_mode mode);
+extern int hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
+			unsigned long range_ns, const enum hrtimer_mode mode);
 extern int hrtimer_cancel(struct hrtimer *timer);
 extern int hrtimer_try_to_cancel(struct hrtimer *timer);
 
 static inline int hrtimer_start_expires(struct hrtimer *timer,
 						enum hrtimer_mode mode)
 {
-	return hrtimer_start(timer, hrtimer_get_expires(timer), mode);
+	unsigned long delta;
+	ktime_t soft, hard;
+	soft = hrtimer_get_softexpires(timer);
+	hard = hrtimer_get_expires(timer);
+	delta = ktime_to_ns(ktime_sub(hard, soft));
+	return hrtimer_start_range_ns(timer, hrtimer_get_expires(timer), delta, mode);
 }
 
 static inline int hrtimer_restart(struct hrtimer *timer)
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 01483004183d..a0222097c57e 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -945,9 +945,10 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
 }
 
 /**
- * hrtimer_start - (re)start an relative timer on the current CPU
+ * hrtimer_start_range_ns - (re)start an relative timer on the current CPU
  * @timer:	the timer to be added
  * @tim:	expiry time
+ * @delta_ns:	"slack" range for the timer
  * @mode:	expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
  *
  * Returns:
@@ -955,7 +956,8 @@ remove_hrtimer(struct hrtimer *timer, struct hrtimer_clock_base *base)
  *  1 when the timer was active
  */
 int
-hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
+hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, unsigned long delta_ns,
+			const enum hrtimer_mode mode)
 {
 	struct hrtimer_clock_base *base, *new_base;
 	unsigned long flags;
@@ -983,7 +985,7 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 #endif
 	}
 
-	hrtimer_set_expires(timer, tim);
+	hrtimer_set_expires_range_ns(timer, tim, delta_ns);
 
 	timer_stats_hrtimer_set_start_info(timer);
 
@@ -1016,8 +1018,26 @@ hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(hrtimer_start_range_ns);
+
+/**
+ * hrtimer_start - (re)start an relative timer on the current CPU
+ * @timer:	the timer to be added
+ * @tim:	expiry time
+ * @mode:	expiry mode: absolute (HRTIMER_ABS) or relative (HRTIMER_REL)
+ *
+ * Returns:
+ *  0 on success
+ *  1 when the timer was active
+ */
+int
+hrtimer_start(struct hrtimer *timer, ktime_t tim, const enum hrtimer_mode mode)
+{
+	return hrtimer_start_range_ns(timer, tim, 0, mode);
+}
 EXPORT_SYMBOL_GPL(hrtimer_start);
 
+
 /**
  * hrtimer_try_to_cancel - try to deactivate a timer
  * @timer:	hrtimer to stop
-- 
cgit v1.2.3


From 4ce105d30e08fb8a1783c55a0e48aa3fa200c455 Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Sun, 7 Sep 2008 15:31:39 -0700
Subject: hrtimer: incorporate feedback from Peter Zijlstra

(based on  lkml review)
* use rt_task()
* task_nice() has a sign

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 fs/select.c             | 5 ++---
 include/linux/hrtimer.h | 2 +-
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/select.c b/fs/select.c
index 5e61b43d0766..fdd8584e536d 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -46,7 +46,7 @@ static unsigned long __estimate_accuracy(struct timespec *tv)
 	unsigned long slack;
 	int divfactor = 1000;
 
-	if (task_nice(current))
+	if (task_nice(current) > 0)
 		divfactor = divfactor / 5;
 
 	slack = tv->tv_nsec / divfactor;
@@ -66,8 +66,7 @@ static unsigned long estimate_accuracy(struct timespec *tv)
 	 * Realtime tasks get a slack of 0 for obvious reasons.
 	 */
 
-	if (current->policy == SCHED_FIFO ||
-		current->policy == SCHED_RR)
+	if (rt_task(current))
 		return 0;
 
 	ktime_get_ts(&now);
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 1c0473e8ecb4..95db11f62ff2 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -363,7 +363,7 @@ static inline int hrtimer_start_expires(struct hrtimer *timer,
 	soft = hrtimer_get_softexpires(timer);
 	hard = hrtimer_get_expires(timer);
 	delta = ktime_to_ns(ktime_sub(hard, soft));
-	return hrtimer_start_range_ns(timer, hrtimer_get_expires(timer), delta, mode);
+	return hrtimer_start_range_ns(timer, soft, delta, mode);
 }
 
 static inline int hrtimer_restart(struct hrtimer *timer)
-- 
cgit v1.2.3


From 2e94d1f71f7e4404d997e6fb4f1618aa147d76f9 Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Wed, 10 Sep 2008 16:06:00 -0700
Subject: hrtimer: peek at the timer queue just before going idle

As part of going idle, we already look at the time of the next timer event to determine
which C-state to select etc.

This patch adds functionality that causes the timers that are past their
soft expire time, to fire at this time, before we calculate the next wakeup
time. This functionality will thus avoid wakeups by running timers before
going idle rather than specially waking up for it.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 drivers/cpuidle/cpuidle.c |  7 +++++++
 include/linux/hrtimer.h   |  5 +++++
 kernel/hrtimer.c          | 30 ++++++++++++++++++++++++++++++
 3 files changed, 42 insertions(+)

(limited to 'include')

diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index 5ce07b517c58..2e3148499368 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -16,6 +16,7 @@
 #include <linux/cpu.h>
 #include <linux/cpuidle.h>
 #include <linux/ktime.h>
+#include <linux/hrtimer.h>
 
 #include "cpuidle.h"
 
@@ -60,6 +61,12 @@ static void cpuidle_idle_call(void)
 		return;
 	}
 
+	/*
+	 * run any timers that can be run now, at this point
+	 * before calculating the idle duration etc.
+	 */
+	hrtimer_peek_ahead_timers();
+
 	/* ask the governor for the next state */
 	next_state = cpuidle_curr_governor->select(dev);
 	if (need_resched())
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 95db11f62ff2..d93b1e1dc169 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -326,6 +326,11 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 extern ktime_t ktime_get(void);
 extern ktime_t ktime_get_real(void);
 
+
+DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
+extern void hrtimer_peek_ahead_timers(void);
+
+
 /* Exported timer functions: */
 
 /* Initialize timers: */
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 9a4c90185566..eb2cf984959f 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1381,6 +1381,36 @@ void hrtimer_interrupt(struct clock_event_device *dev)
 		raise_softirq(HRTIMER_SOFTIRQ);
 }
 
+/**
+ * hrtimer_peek_ahead_timers -- run soft-expired timers now
+ *
+ * hrtimer_peek_ahead_timers will peek at the timer queue of
+ * the current cpu and check if there are any timers for which
+ * the soft expires time has passed. If any such timers exist,
+ * they are run immediately and then removed from the timer queue.
+ *
+ */
+void hrtimer_peek_ahead_timers(void)
+{
+	unsigned long flags;
+	struct tick_device *td;
+	struct clock_event_device *dev;
+
+	if (hrtimer_hres_active())
+		return;
+
+	local_irq_save(flags);
+	td = &__get_cpu_var(tick_cpu_device);
+	if (!td)
+		goto out;
+	dev = td->evtdev;
+	if (!dev)
+		goto out;
+	hrtimer_interrupt(dev);
+out:
+	local_irq_restore(flags);
+}
+
 static void run_hrtimer_softirq(struct softirq_action *h)
 {
 	run_hrtimer_pending(&__get_cpu_var(hrtimer_bases));
-- 
cgit v1.2.3


From f06febc96ba8e0af80bcc3eaec0a109e88275fac Mon Sep 17 00:00:00 2001
From: Frank Mayhar <fmayhar@google.com>
Date: Fri, 12 Sep 2008 09:54:39 -0700
Subject: timers: fix itimer/many thread hang

Overview

This patch reworks the handling of POSIX CPU timers, including the
ITIMER_PROF, ITIMER_VIRT timers and rlimit handling.  It was put together
with the help of Roland McGrath, the owner and original writer of this code.

The problem we ran into, and the reason for this rework, has to do with using
a profiling timer in a process with a large number of threads.  It appears
that the performance of the old implementation of run_posix_cpu_timers() was
at least O(n*3) (where "n" is the number of threads in a process) or worse.
Everything is fine with an increasing number of threads until the time taken
for that routine to run becomes the same as or greater than the tick time, at
which point things degrade rather quickly.

This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF."

Code Changes

This rework corrects the implementation of run_posix_cpu_timers() to make it
run in constant time for a particular machine.  (Performance may vary between
one machine and another depending upon whether the kernel is built as single-
or multiprocessor and, in the latter case, depending upon the number of
running processors.)  To do this, at each tick we now update fields in
signal_struct as well as task_struct.  The run_posix_cpu_timers() function
uses those fields to make its decisions.

We define a new structure, "task_cputime," to contain user, system and
scheduler times and use these in appropriate places:

struct task_cputime {
	cputime_t utime;
	cputime_t stime;
	unsigned long long sum_exec_runtime;
};

This is included in the structure "thread_group_cputime," which is a new
substructure of signal_struct and which varies for uniprocessor versus
multiprocessor kernels.  For uniprocessor kernels, it uses "task_cputime" as
a simple substructure, while for multiprocessor kernels it is a pointer:

struct thread_group_cputime {
	struct task_cputime totals;
};

struct thread_group_cputime {
	struct task_cputime *totals;
};

We also add a new task_cputime substructure directly to signal_struct, to
cache the earliest expiration of process-wide timers, and task_cputime also
replaces the it_*_expires fields of task_struct (used for earliest expiration
of thread timers).  The "thread_group_cputime" structure contains process-wide
timers that are updated via account_user_time() and friends.  In the non-SMP
case the structure is a simple aggregator; unfortunately in the SMP case that
simplicity was not achievable due to cache-line contention between CPUs (in
one measured case performance was actually _worse_ on a 16-cpu system than
the same test on a 4-cpu system, due to this contention).  For SMP, the
thread_group_cputime counters are maintained as a per-cpu structure allocated
using alloc_percpu().  The timer functions update only the timer field in
the structure corresponding to the running CPU, obtained using per_cpu_ptr().

We define a set of inline functions in sched.h that we use to maintain the
thread_group_cputime structure and hide the differences between UP and SMP
implementations from the rest of the kernel.  The thread_group_cputime_init()
function initializes the thread_group_cputime structure for the given task.
The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the
out-of-line function thread_group_cputime_alloc_smp() to allocate and fill
in the per-cpu structures and fields.  The thread_group_cputime_free()
function, also a no-op for UP, in SMP frees the per-cpu structures.  The
thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls
thread_group_cputime_alloc() if the per-cpu structures haven't yet been
allocated.  The thread_group_cputime() function fills the task_cputime
structure it is passed with the contents of the thread_group_cputime fields;
in UP it's that simple but in SMP it must also safely check that tsk->signal
is non-NULL (if it is it just uses the appropriate fields of task_struct) and,
if so, sums the per-cpu values for each online CPU.  Finally, the three
functions account_group_user_time(), account_group_system_time() and
account_group_exec_runtime() are used by timer functions to update the
respective fields of the thread_group_cputime structure.

Non-SMP operation is trivial and will not be mentioned further.

The per-cpu structure is always allocated when a task creates its first new
thread, via a call to thread_group_cputime_clone_thread() from copy_signal().
It is freed at process exit via a call to thread_group_cputime_free() from
cleanup_signal().

All functions that formerly summed utime/stime/sum_sched_runtime values from
from all threads in the thread group now use thread_group_cputime() to
snapshot the values in the thread_group_cputime structure or the values in
the task structure itself if the per-cpu structure hasn't been allocated.

Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit.
The run_posix_cpu_timers() function has been split into a fast path and a
slow path; the former safely checks whether there are any expired thread
timers and, if not, just returns, while the slow path does the heavy lifting.
With the dedicated thread group fields, timers are no longer "rebalanced" and
the process_timer_rebalance() function and related code has gone away.  All
summing loops are gone and all code that used them now uses the
thread_group_cputime() inline.  When process-wide timers are set, the new
task_cputime structure in signal_struct is used to cache the earliest
expiration; this is checked in the fast path.

Performance

The fix appears not to add significant overhead to existing operations.  It
generally performs the same as the current code except in two cases, one in
which it performs slightly worse (Case 5 below) and one in which it performs
very significantly better (Case 2 below).  Overall it's a wash except in those
two cases.

I've since done somewhat more involved testing on a dual-core Opteron system.

Case 1: With no itimer running, for a test with 100,000 threads, the fixed
	kernel took 1428.5 seconds, 513 seconds more than the unfixed system,
	all of which was spent in the system.  There were twice as many
	voluntary context switches with the fix as without it.

Case 2: With an itimer running at .01 second ticks and 4000 threads (the most
	an unmodified kernel can handle), the fixed kernel ran the test in
	eight percent of the time (5.8 seconds as opposed to 70 seconds) and
	had better tick accuracy (.012 seconds per tick as opposed to .023
	seconds per tick).

Case 3: A 4000-thread test with an initial timer tick of .01 second and an
	interval of 10,000 seconds (i.e. a timer that ticks only once) had
	very nearly the same performance in both cases:  6.3 seconds elapsed
	for the fixed kernel versus 5.5 seconds for the unfixed kernel.

With fewer threads (eight in these tests), the Case 1 test ran in essentially
the same time on both the modified and unmodified kernels (5.2 seconds versus
5.8 seconds).  The Case 2 test ran in about the same time as well, 5.9 seconds
versus 5.4 seconds but again with much better tick accuracy, .013 seconds per
tick versus .025 seconds per tick for the unmodified kernel.

Since the fix affected the rlimit code, I also tested soft and hard CPU limits.

Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer
	running), the modified kernel was very slightly favored in that while
	it killed the process in 19.997 seconds of CPU time (5.002 seconds of
	wall time), only .003 seconds of that was system time, the rest was
	user time.  The unmodified kernel killed the process in 20.001 seconds
	of CPU (5.014 seconds of wall time) of which .016 seconds was system
	time.  Really, though, the results were too close to call.  The results
	were essentially the same with no itimer running.

Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds
	(where the hard limit would never be reached) and an itimer running,
	the modified kernel exhibited worse tick accuracy than the unmodified
	kernel: .050 seconds/tick versus .028 seconds/tick.  Otherwise,
	performance was almost indistinguishable.  With no itimer running this
	test exhibited virtually identical behavior and times in both cases.

In times past I did some limited performance testing.  those results are below.

On a four-cpu Opteron system without this fix, a sixteen-thread test executed
in 3569.991 seconds, of which user was 3568.435s and system was 1.556s.  On
the same system with the fix, user and elapsed time were about the same, but
system time dropped to 0.007 seconds.  Performance with eight, four and one
thread were comparable.  Interestingly, the timer ticks with the fix seemed
more accurate:  The sixteen-thread test with the fix received 149543 ticks
for 0.024 seconds per tick, while the same test without the fix received 58720
for 0.061 seconds per tick.  Both cases were configured for an interval of
0.01 seconds.  Again, the other tests were comparable.  Each thread in this
test computed the primes up to 25,000,000.

I also did a test with a large number of threads, 100,000 threads, which is
impossible without the fix.  In this case each thread computed the primes only
up to 10,000 (to make the runtime manageable).  System time dominated, at
1546.968 seconds out of a total 2176.906 seconds (giving a user time of
629.938s).  It received 147651 ticks for 0.015 seconds per tick, still quite
accurate.  There is obviously no comparable test without the fix.

Signed-off-by: Frank Mayhar <fmayhar@google.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 fs/binfmt_elf.c              |  19 +-
 fs/proc/array.c              |   8 +-
 include/linux/posix-timers.h |   2 +
 include/linux/sched.h        | 257 +++++++++++++++++++++--
 include/linux/time.h         |   3 +
 kernel/compat.c              |  53 ++---
 kernel/exit.c                |  19 +-
 kernel/fork.c                |  88 ++++----
 kernel/itimer.c              |  33 +--
 kernel/posix-cpu-timers.c    | 471 +++++++++++++++++++++++--------------------
 kernel/sched.c               |  53 ++++-
 kernel/sched_fair.c          |   1 +
 kernel/sched_rt.c            |   4 +-
 kernel/signal.c              |   8 +-
 kernel/sys.c                 |  75 +++----
 security/selinux/hooks.c     |   9 +-
 16 files changed, 677 insertions(+), 426 deletions(-)

(limited to 'include')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 655ed8d30a86..a8635f637038 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1333,20 +1333,15 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
 	prstatus->pr_pgrp = task_pgrp_vnr(p);
 	prstatus->pr_sid = task_session_vnr(p);
 	if (thread_group_leader(p)) {
+		struct task_cputime cputime;
+
 		/*
-		 * This is the record for the group leader.  Add in the
-		 * cumulative times of previous dead threads.  This total
-		 * won't include the time of each live thread whose state
-		 * is included in the core dump.  The final total reported
-		 * to our parent process when it calls wait4 will include
-		 * those sums as well as the little bit more time it takes
-		 * this and each other thread to finish dying after the
-		 * core dump synchronization phase.
+		 * This is the record for the group leader.  It shows the
+		 * group-wide total, not its individual thread total.
 		 */
-		cputime_to_timeval(cputime_add(p->utime, p->signal->utime),
-				   &prstatus->pr_utime);
-		cputime_to_timeval(cputime_add(p->stime, p->signal->stime),
-				   &prstatus->pr_stime);
+		thread_group_cputime(p, &cputime);
+		cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
+		cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
 	} else {
 		cputime_to_timeval(p->utime, &prstatus->pr_utime);
 		cputime_to_timeval(p->stime, &prstatus->pr_stime);
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 71c9be59c9c2..933953c4e407 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -395,20 +395,20 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
 		/* add up live thread stats at the group level */
 		if (whole) {
+			struct task_cputime cputime;
 			struct task_struct *t = task;
 			do {
 				min_flt += t->min_flt;
 				maj_flt += t->maj_flt;
-				utime = cputime_add(utime, task_utime(t));
-				stime = cputime_add(stime, task_stime(t));
 				gtime = cputime_add(gtime, task_gtime(t));
 				t = next_thread(t);
 			} while (t != task);
 
 			min_flt += sig->min_flt;
 			maj_flt += sig->maj_flt;
-			utime = cputime_add(utime, sig->utime);
-			stime = cputime_add(stime, sig->stime);
+			thread_group_cputime(task, &cputime);
+			utime = cputime.utime;
+			stime = cputime.stime;
 			gtime = cputime_add(gtime, sig->gtime);
 		}
 
diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index a7dd38f30ade..f9d8e9e94e9b 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -115,4 +115,6 @@ void set_process_cpu_timer(struct task_struct *task, unsigned int clock_idx,
 
 long clock_nanosleep_restart(struct restart_block *restart_block);
 
+void update_rlimit_cpu(unsigned long rlim_new);
+
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 3d9120c5ad15..26d7a5f2d0ba 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -425,6 +425,45 @@ struct pacct_struct {
 	unsigned long		ac_minflt, ac_majflt;
 };
 
+/**
+ * struct task_cputime - collected CPU time counts
+ * @utime:		time spent in user mode, in &cputime_t units
+ * @stime:		time spent in kernel mode, in &cputime_t units
+ * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
+ * 
+ * This structure groups together three kinds of CPU time that are
+ * tracked for threads and thread groups.  Most things considering
+ * CPU time want to group these counts together and treat all three
+ * of them in parallel.
+ */
+struct task_cputime {
+	cputime_t utime;
+	cputime_t stime;
+	unsigned long long sum_exec_runtime;
+};
+/* Alternate field names when used to cache expirations. */
+#define prof_exp	stime
+#define virt_exp	utime
+#define sched_exp	sum_exec_runtime
+
+/**
+ * struct thread_group_cputime - thread group interval timer counts
+ * @totals:		thread group interval timers; substructure for
+ *			uniprocessor kernel, per-cpu for SMP kernel.
+ *
+ * This structure contains the version of task_cputime, above, that is
+ * used for thread group CPU clock calculations.
+ */
+#ifdef CONFIG_SMP
+struct thread_group_cputime {
+	struct task_cputime *totals;
+};
+#else
+struct thread_group_cputime {
+	struct task_cputime totals;
+};
+#endif
+
 /*
  * NOTE! "signal_struct" does not have it's own
  * locking, because a shared signal_struct always
@@ -470,6 +509,17 @@ struct signal_struct {
 	cputime_t it_prof_expires, it_virt_expires;
 	cputime_t it_prof_incr, it_virt_incr;
 
+	/*
+	 * Thread group totals for process CPU clocks.
+	 * See thread_group_cputime(), et al, for details.
+	 */
+	struct thread_group_cputime cputime;
+
+	/* Earliest-expiration cache. */
+	struct task_cputime cputime_expires;
+
+	struct list_head cpu_timers[3];
+
 	/* job control IDs */
 
 	/*
@@ -500,7 +550,7 @@ struct signal_struct {
 	 * Live threads maintain their own counters and add to these
 	 * in __exit_signal, except for the group leader.
 	 */
-	cputime_t utime, stime, cutime, cstime;
+	cputime_t cutime, cstime;
 	cputime_t gtime;
 	cputime_t cgtime;
 	unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
@@ -508,14 +558,6 @@ struct signal_struct {
 	unsigned long inblock, oublock, cinblock, coublock;
 	struct task_io_accounting ioac;
 
-	/*
-	 * Cumulative ns of scheduled CPU time for dead threads in the
-	 * group, not including a zombie group leader.  (This only differs
-	 * from jiffies_to_ns(utime + stime) if sched_clock uses something
-	 * other than jiffies.)
-	 */
-	unsigned long long sum_sched_runtime;
-
 	/*
 	 * We don't bother to synchronize most readers of this at all,
 	 * because there is no reader checking a limit that actually needs
@@ -527,8 +569,6 @@ struct signal_struct {
 	 */
 	struct rlimit rlim[RLIM_NLIMITS];
 
-	struct list_head cpu_timers[3];
-
 	/* keep the process-shared keyrings here so that they do the right
 	 * thing in threads created with CLONE_THREAD */
 #ifdef CONFIG_KEYS
@@ -1134,8 +1174,7 @@ struct task_struct {
 /* mm fault and swap info: this can arguably be seen as either mm-specific or thread-specific */
 	unsigned long min_flt, maj_flt;
 
-  	cputime_t it_prof_expires, it_virt_expires;
-	unsigned long long it_sched_expires;
+	struct task_cputime cputime_expires;
 	struct list_head cpu_timers[3];
 
 /* process credentials */
@@ -1585,6 +1624,7 @@ extern unsigned long long cpu_clock(int cpu);
 
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
+extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
 
 /* sched_exec is called by processes performing an exec */
 #ifdef CONFIG_SMP
@@ -2081,6 +2121,197 @@ static inline int spin_needbreak(spinlock_t *lock)
 #endif
 }
 
+/*
+ * Thread group CPU time accounting.
+ */
+#ifdef CONFIG_SMP
+
+extern int thread_group_cputime_alloc_smp(struct task_struct *);
+extern void thread_group_cputime_smp(struct task_struct *, struct task_cputime *);
+
+static inline void thread_group_cputime_init(struct signal_struct *sig)
+{
+	sig->cputime.totals = NULL;
+}
+
+static inline int thread_group_cputime_clone_thread(struct task_struct *curr,
+						    struct task_struct *new)
+{
+	if (curr->signal->cputime.totals)
+		return 0;
+	return thread_group_cputime_alloc_smp(curr);
+}
+
+static inline void thread_group_cputime_free(struct signal_struct *sig)
+{
+	free_percpu(sig->cputime.totals);
+}
+
+/**
+ * thread_group_cputime - Sum the thread group time fields across all CPUs.
+ *
+ * This is a wrapper for the real routine, thread_group_cputime_smp().  See
+ * that routine for details.
+ */
+static inline void thread_group_cputime(
+	struct task_struct *tsk,
+	struct task_cputime *times)
+{
+	thread_group_cputime_smp(tsk, times);
+}
+
+/**
+ * thread_group_cputime_account_user - Maintain utime for a thread group.
+ *
+ * @tgtimes:	Pointer to thread_group_cputime structure.
+ * @cputime:	Time value by which to increment the utime field of that
+ *		structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the utime field there.
+ */
+static inline void thread_group_cputime_account_user(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	if (tgtimes->totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times->utime = cputime_add(times->utime, cputime);
+		put_cpu_no_resched();
+	}
+}
+
+/**
+ * thread_group_cputime_account_system - Maintain stime for a thread group.
+ *
+ * @tgtimes:	Pointer to thread_group_cputime structure.
+ * @cputime:	Time value by which to increment the stime field of that
+ *		structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the stime field there.
+ */
+static inline void thread_group_cputime_account_system(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	if (tgtimes->totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times->stime = cputime_add(times->stime, cputime);
+		put_cpu_no_resched();
+	}
+}
+
+/**
+ * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a
+ *						thread group.
+ *
+ * @tgtimes:	Pointer to thread_group_cputime structure.
+ * @ns:		Time value by which to increment the sum_exec_runtime field
+ *		of that structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the sum_exec_runtime field there.
+ */
+static inline void thread_group_cputime_account_exec_runtime(
+	struct thread_group_cputime *tgtimes,
+	unsigned long long ns)
+{
+	if (tgtimes->totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times->sum_exec_runtime += ns;
+		put_cpu_no_resched();
+	}
+}
+
+#else /* CONFIG_SMP */
+
+static inline void thread_group_cputime_init(struct signal_struct *sig)
+{
+	sig->cputime.totals.utime = cputime_zero;
+	sig->cputime.totals.stime = cputime_zero;
+	sig->cputime.totals.sum_exec_runtime = 0;
+}
+
+static inline int thread_group_cputime_alloc(struct task_struct *tsk)
+{
+	return 0;
+}
+
+static inline void thread_group_cputime_free(struct signal_struct *sig)
+{
+}
+
+static inline int thread_group_cputime_clone_thread(struct task_struct *curr,
+						     struct task_struct *tsk)
+{
+}
+
+static inline void thread_group_cputime(struct task_struct *tsk,
+					 struct task_cputime *cputime)
+{
+	*cputime = tsk->signal->cputime.totals;
+}
+
+static inline void thread_group_cputime_account_user(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime);
+}
+
+static inline void thread_group_cputime_account_system(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime);
+}
+
+static inline void thread_group_cputime_account_exec_runtime(
+	struct thread_group_cputime *tgtimes,
+	unsigned long long ns)
+{
+	tgtimes->totals->sum_exec_runtime += ns;
+}
+
+#endif /* CONFIG_SMP */
+
+static inline void account_group_user_time(struct task_struct *tsk,
+					    cputime_t cputime)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (likely(sig))
+		thread_group_cputime_account_user(&sig->cputime, cputime);
+}
+
+static inline void account_group_system_time(struct task_struct *tsk,
+					      cputime_t cputime)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (likely(sig))
+		thread_group_cputime_account_system(&sig->cputime, cputime);
+}
+
+static inline void account_group_exec_runtime(struct task_struct *tsk,
+					       unsigned long long ns)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (likely(sig))
+		thread_group_cputime_account_exec_runtime(&sig->cputime, ns);
+}
+
 /*
  * Reevaluate whether the task has signals pending delivery.
  * Wake the task if so.
diff --git a/include/linux/time.h b/include/linux/time.h
index e15206a7e82e..1b70b3c293e9 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -125,6 +125,9 @@ extern int timekeeping_valid_for_hres(void);
 extern void update_wall_time(void);
 extern void update_xtime_cache(u64 nsec);
 
+struct tms;
+extern void do_sys_times(struct tms *);
+
 /**
  * timespec_to_ns - Convert timespec to nanoseconds
  * @ts:		pointer to the timespec variable to be converted
diff --git a/kernel/compat.c b/kernel/compat.c
index 32c254a8ab9a..72650e39b3e6 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -23,6 +23,7 @@
 #include <linux/timex.h>
 #include <linux/migrate.h>
 #include <linux/posix-timers.h>
+#include <linux/times.h>
 
 #include <asm/uaccess.h>
 
@@ -150,49 +151,23 @@ asmlinkage long compat_sys_setitimer(int which,
 	return 0;
 }
 
+static compat_clock_t clock_t_to_compat_clock_t(clock_t x)
+{
+	return compat_jiffies_to_clock_t(clock_t_to_jiffies(x));
+}
+
 asmlinkage long compat_sys_times(struct compat_tms __user *tbuf)
 {
-	/*
-	 *	In the SMP world we might just be unlucky and have one of
-	 *	the times increment as we use it. Since the value is an
-	 *	atomically safe type this is just fine. Conceptually its
-	 *	as if the syscall took an instant longer to occur.
-	 */
 	if (tbuf) {
+		struct tms tms;
 		struct compat_tms tmp;
-		struct task_struct *tsk = current;
-		struct task_struct *t;
-		cputime_t utime, stime, cutime, cstime;
-
-		read_lock(&tasklist_lock);
-		utime = tsk->signal->utime;
-		stime = tsk->signal->stime;
-		t = tsk;
-		do {
-			utime = cputime_add(utime, t->utime);
-			stime = cputime_add(stime, t->stime);
-			t = next_thread(t);
-		} while (t != tsk);
-
-		/*
-		 * While we have tasklist_lock read-locked, no dying thread
-		 * can be updating current->signal->[us]time.  Instead,
-		 * we got their counts included in the live thread loop.
-		 * However, another thread can come in right now and
-		 * do a wait call that updates current->signal->c[us]time.
-		 * To make sure we always see that pair updated atomically,
-		 * we take the siglock around fetching them.
-		 */
-		spin_lock_irq(&tsk->sighand->siglock);
-		cutime = tsk->signal->cutime;
-		cstime = tsk->signal->cstime;
-		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
-
-		tmp.tms_utime = compat_jiffies_to_clock_t(cputime_to_jiffies(utime));
-		tmp.tms_stime = compat_jiffies_to_clock_t(cputime_to_jiffies(stime));
-		tmp.tms_cutime = compat_jiffies_to_clock_t(cputime_to_jiffies(cutime));
-		tmp.tms_cstime = compat_jiffies_to_clock_t(cputime_to_jiffies(cstime));
+
+		do_sys_times(&tms);
+		/* Convert our struct tms to the compat version. */
+		tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime);
+		tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime);
+		tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime);
+		tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime);
 		if (copy_to_user(tbuf, &tmp, sizeof(tmp)))
 			return -EFAULT;
 	}
diff --git a/kernel/exit.c b/kernel/exit.c
index 16395644a98f..40036ac04271 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -112,8 +112,6 @@ static void __exit_signal(struct task_struct *tsk)
 		 * We won't ever get here for the group leader, since it
 		 * will have been the last reference on the signal_struct.
 		 */
-		sig->utime = cputime_add(sig->utime, task_utime(tsk));
-		sig->stime = cputime_add(sig->stime, task_stime(tsk));
 		sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
 		sig->min_flt += tsk->min_flt;
 		sig->maj_flt += tsk->maj_flt;
@@ -122,7 +120,6 @@ static void __exit_signal(struct task_struct *tsk)
 		sig->inblock += task_io_get_inblock(tsk);
 		sig->oublock += task_io_get_oublock(tsk);
 		task_io_accounting_add(&sig->ioac, &tsk->ioac);
-		sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
 		sig = NULL; /* Marker for below. */
 	}
 
@@ -1294,6 +1291,7 @@ static int wait_task_zombie(struct task_struct *p, int options,
 	if (likely(!traced)) {
 		struct signal_struct *psig;
 		struct signal_struct *sig;
+		struct task_cputime cputime;
 
 		/*
 		 * The resource counters for the group leader are in its
@@ -1309,20 +1307,23 @@ static int wait_task_zombie(struct task_struct *p, int options,
 		 * need to protect the access to p->parent->signal fields,
 		 * as other threads in the parent group can be right
 		 * here reaping other children at the same time.
+		 *
+		 * We use thread_group_cputime() to get times for the thread
+		 * group, which consolidates times for all threads in the
+		 * group including the group leader.
 		 */
 		spin_lock_irq(&p->parent->sighand->siglock);
 		psig = p->parent->signal;
 		sig = p->signal;
+		thread_group_cputime(p, &cputime);
 		psig->cutime =
 			cputime_add(psig->cutime,
-			cputime_add(p->utime,
-			cputime_add(sig->utime,
-				    sig->cutime)));
+			cputime_add(cputime.utime,
+				    sig->cutime));
 		psig->cstime =
 			cputime_add(psig->cstime,
-			cputime_add(p->stime,
-			cputime_add(sig->stime,
-				    sig->cstime)));
+			cputime_add(cputime.stime,
+				    sig->cstime));
 		psig->cgtime =
 			cputime_add(psig->cgtime,
 			cputime_add(p->gtime,
diff --git a/kernel/fork.c b/kernel/fork.c
index 7ce2ebe84796..a8ac2efb8e30 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -759,15 +759,44 @@ void __cleanup_sighand(struct sighand_struct *sighand)
 		kmem_cache_free(sighand_cachep, sighand);
 }
 
+
+/*
+ * Initialize POSIX timer handling for a thread group.
+ */
+static void posix_cpu_timers_init_group(struct signal_struct *sig)
+{
+	/* Thread group counters. */
+	thread_group_cputime_init(sig);
+
+	/* Expiration times and increments. */
+	sig->it_virt_expires = cputime_zero;
+	sig->it_virt_incr = cputime_zero;
+	sig->it_prof_expires = cputime_zero;
+	sig->it_prof_incr = cputime_zero;
+
+	/* Cached expiration times. */
+	sig->cputime_expires.prof_exp = cputime_zero;
+	sig->cputime_expires.virt_exp = cputime_zero;
+	sig->cputime_expires.sched_exp = 0;
+
+	/* The timer lists. */
+	INIT_LIST_HEAD(&sig->cpu_timers[0]);
+	INIT_LIST_HEAD(&sig->cpu_timers[1]);
+	INIT_LIST_HEAD(&sig->cpu_timers[2]);
+}
+
 static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 {
 	struct signal_struct *sig;
 	int ret;
 
 	if (clone_flags & CLONE_THREAD) {
-		atomic_inc(&current->signal->count);
-		atomic_inc(&current->signal->live);
-		return 0;
+		ret = thread_group_cputime_clone_thread(current, tsk);
+		if (likely(!ret)) {
+			atomic_inc(&current->signal->count);
+			atomic_inc(&current->signal->live);
+		}
+		return ret;
 	}
 	sig = kmem_cache_alloc(signal_cachep, GFP_KERNEL);
 	tsk->signal = sig;
@@ -795,15 +824,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->it_real_incr.tv64 = 0;
 	sig->real_timer.function = it_real_fn;
 
-	sig->it_virt_expires = cputime_zero;
-	sig->it_virt_incr = cputime_zero;
-	sig->it_prof_expires = cputime_zero;
-	sig->it_prof_incr = cputime_zero;
-
 	sig->leader = 0;	/* session leadership doesn't inherit */
 	sig->tty_old_pgrp = NULL;
 
-	sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
+	sig->cutime = sig->cstime = cputime_zero;
 	sig->gtime = cputime_zero;
 	sig->cgtime = cputime_zero;
 	sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
@@ -820,14 +844,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	memcpy(sig->rlim, current->signal->rlim, sizeof sig->rlim);
 	task_unlock(current->group_leader);
 
-	if (sig->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
-		/*
-		 * New sole thread in the process gets an expiry time
-		 * of the whole CPU time limit.
-		 */
-		tsk->it_prof_expires =
-			secs_to_cputime(sig->rlim[RLIMIT_CPU].rlim_cur);
-	}
+	posix_cpu_timers_init_group(sig);
+
 	acct_init_pacct(&sig->pacct);
 
 	tty_audit_fork(sig);
@@ -837,6 +855,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 
 void __cleanup_signal(struct signal_struct *sig)
 {
+	thread_group_cputime_free(sig);
 	exit_thread_group_keys(sig);
 	kmem_cache_free(signal_cachep, sig);
 }
@@ -885,6 +904,19 @@ void mm_init_owner(struct mm_struct *mm, struct task_struct *p)
 }
 #endif /* CONFIG_MM_OWNER */
 
+/*
+ * Initialize POSIX timer handling for a single task.
+ */
+static void posix_cpu_timers_init(struct task_struct *tsk)
+{
+	tsk->cputime_expires.prof_exp = cputime_zero;
+	tsk->cputime_expires.virt_exp = cputime_zero;
+	tsk->cputime_expires.sched_exp = 0;
+	INIT_LIST_HEAD(&tsk->cpu_timers[0]);
+	INIT_LIST_HEAD(&tsk->cpu_timers[1]);
+	INIT_LIST_HEAD(&tsk->cpu_timers[2]);
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -995,12 +1027,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	task_io_accounting_init(&p->ioac);
 	acct_clear_integrals(p);
 
-	p->it_virt_expires = cputime_zero;
-	p->it_prof_expires = cputime_zero;
-	p->it_sched_expires = 0;
-	INIT_LIST_HEAD(&p->cpu_timers[0]);
-	INIT_LIST_HEAD(&p->cpu_timers[1]);
-	INIT_LIST_HEAD(&p->cpu_timers[2]);
+	posix_cpu_timers_init(p);
 
 	p->lock_depth = -1;		/* -1 = no lock */
 	do_posix_clock_monotonic_gettime(&p->start_time);
@@ -1201,21 +1228,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	if (clone_flags & CLONE_THREAD) {
 		p->group_leader = current->group_leader;
 		list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group);
-
-		if (!cputime_eq(current->signal->it_virt_expires,
-				cputime_zero) ||
-		    !cputime_eq(current->signal->it_prof_expires,
-				cputime_zero) ||
-		    current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY ||
-		    !list_empty(&current->signal->cpu_timers[0]) ||
-		    !list_empty(&current->signal->cpu_timers[1]) ||
-		    !list_empty(&current->signal->cpu_timers[2])) {
-			/*
-			 * Have child wake up on its first tick to check
-			 * for process CPU timers.
-			 */
-			p->it_prof_expires = jiffies_to_cputime(1);
-		}
 	}
 
 	if (likely(p->pid)) {
diff --git a/kernel/itimer.c b/kernel/itimer.c
index ab982747d9bd..db7c358b9a02 100644
--- a/kernel/itimer.c
+++ b/kernel/itimer.c
@@ -55,17 +55,15 @@ int do_getitimer(int which, struct itimerval *value)
 		spin_unlock_irq(&tsk->sighand->siglock);
 		break;
 	case ITIMER_VIRTUAL:
-		read_lock(&tasklist_lock);
 		spin_lock_irq(&tsk->sighand->siglock);
 		cval = tsk->signal->it_virt_expires;
 		cinterval = tsk->signal->it_virt_incr;
 		if (!cputime_eq(cval, cputime_zero)) {
-			struct task_struct *t = tsk;
-			cputime_t utime = tsk->signal->utime;
-			do {
-				utime = cputime_add(utime, t->utime);
-				t = next_thread(t);
-			} while (t != tsk);
+			struct task_cputime cputime;
+			cputime_t utime;
+
+			thread_group_cputime(tsk, &cputime);
+			utime = cputime.utime;
 			if (cputime_le(cval, utime)) { /* about to fire */
 				cval = jiffies_to_cputime(1);
 			} else {
@@ -73,25 +71,19 @@ int do_getitimer(int which, struct itimerval *value)
 			}
 		}
 		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
 		cputime_to_timeval(cval, &value->it_value);
 		cputime_to_timeval(cinterval, &value->it_interval);
 		break;
 	case ITIMER_PROF:
-		read_lock(&tasklist_lock);
 		spin_lock_irq(&tsk->sighand->siglock);
 		cval = tsk->signal->it_prof_expires;
 		cinterval = tsk->signal->it_prof_incr;
 		if (!cputime_eq(cval, cputime_zero)) {
-			struct task_struct *t = tsk;
-			cputime_t ptime = cputime_add(tsk->signal->utime,
-						      tsk->signal->stime);
-			do {
-				ptime = cputime_add(ptime,
-						    cputime_add(t->utime,
-								t->stime));
-				t = next_thread(t);
-			} while (t != tsk);
+			struct task_cputime times;
+			cputime_t ptime;
+
+			thread_group_cputime(tsk, &times);
+			ptime = cputime_add(times.utime, times.stime);
 			if (cputime_le(cval, ptime)) { /* about to fire */
 				cval = jiffies_to_cputime(1);
 			} else {
@@ -99,7 +91,6 @@ int do_getitimer(int which, struct itimerval *value)
 			}
 		}
 		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
 		cputime_to_timeval(cval, &value->it_value);
 		cputime_to_timeval(cinterval, &value->it_interval);
 		break;
@@ -185,7 +176,6 @@ again:
 	case ITIMER_VIRTUAL:
 		nval = timeval_to_cputime(&value->it_value);
 		ninterval = timeval_to_cputime(&value->it_interval);
-		read_lock(&tasklist_lock);
 		spin_lock_irq(&tsk->sighand->siglock);
 		cval = tsk->signal->it_virt_expires;
 		cinterval = tsk->signal->it_virt_incr;
@@ -200,7 +190,6 @@ again:
 		tsk->signal->it_virt_expires = nval;
 		tsk->signal->it_virt_incr = ninterval;
 		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
 		if (ovalue) {
 			cputime_to_timeval(cval, &ovalue->it_value);
 			cputime_to_timeval(cinterval, &ovalue->it_interval);
@@ -209,7 +198,6 @@ again:
 	case ITIMER_PROF:
 		nval = timeval_to_cputime(&value->it_value);
 		ninterval = timeval_to_cputime(&value->it_interval);
-		read_lock(&tasklist_lock);
 		spin_lock_irq(&tsk->sighand->siglock);
 		cval = tsk->signal->it_prof_expires;
 		cinterval = tsk->signal->it_prof_incr;
@@ -224,7 +212,6 @@ again:
 		tsk->signal->it_prof_expires = nval;
 		tsk->signal->it_prof_incr = ninterval;
 		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
 		if (ovalue) {
 			cputime_to_timeval(cval, &ovalue->it_value);
 			cputime_to_timeval(cinterval, &ovalue->it_interval);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index c42a03aef36f..dba1c334c3e8 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -8,6 +8,99 @@
 #include <linux/math64.h>
 #include <asm/uaccess.h>
 
+#ifdef CONFIG_SMP
+/*
+ * Allocate the thread_group_cputime structure appropriately for SMP kernels
+ * and fill in the current values of the fields.  Called from copy_signal()
+ * via thread_group_cputime_clone_thread() when adding a second or subsequent
+ * thread to a thread group.  Assumes interrupts are enabled when called.
+ */
+int thread_group_cputime_alloc_smp(struct task_struct *tsk)
+{
+	struct signal_struct *sig = tsk->signal;
+	struct task_cputime *cputime;
+
+	/*
+	 * If we have multiple threads and we don't already have a
+	 * per-CPU task_cputime struct, allocate one and fill it in with
+	 * the times accumulated so far.
+	 */
+	if (sig->cputime.totals)
+		return 0;
+	cputime = alloc_percpu(struct task_cputime);
+	if (cputime == NULL)
+		return -ENOMEM;
+	read_lock(&tasklist_lock);
+	spin_lock_irq(&tsk->sighand->siglock);
+	if (sig->cputime.totals) {
+		spin_unlock_irq(&tsk->sighand->siglock);
+		read_unlock(&tasklist_lock);
+		free_percpu(cputime);
+		return 0;
+	}
+	sig->cputime.totals = cputime;
+	cputime = per_cpu_ptr(sig->cputime.totals, get_cpu());
+	cputime->utime = tsk->utime;
+	cputime->stime = tsk->stime;
+	cputime->sum_exec_runtime = tsk->se.sum_exec_runtime;
+	put_cpu_no_resched();
+	spin_unlock_irq(&tsk->sighand->siglock);
+	read_unlock(&tasklist_lock);
+	return 0;
+}
+
+/**
+ * thread_group_cputime_smp - Sum the thread group time fields across all CPUs.
+ *
+ * @tsk:	The task we use to identify the thread group.
+ * @times:	task_cputime structure in which we return the summed fields.
+ *
+ * Walk the list of CPUs to sum the per-CPU time fields in the thread group
+ * time structure.
+ */
+void thread_group_cputime_smp(
+	struct task_struct *tsk,
+	struct task_cputime *times)
+{
+	struct signal_struct *sig;
+	int i;
+	struct task_cputime *tot;
+
+	sig = tsk->signal;
+	if (unlikely(!sig) || !sig->cputime.totals) {
+		times->utime = tsk->utime;
+		times->stime = tsk->stime;
+		times->sum_exec_runtime = tsk->se.sum_exec_runtime;
+		return;
+	}
+	times->stime = times->utime = cputime_zero;
+	times->sum_exec_runtime = 0;
+	for_each_possible_cpu(i) {
+		tot = per_cpu_ptr(tsk->signal->cputime.totals, i);
+		times->utime = cputime_add(times->utime, tot->utime);
+		times->stime = cputime_add(times->stime, tot->stime);
+		times->sum_exec_runtime += tot->sum_exec_runtime;
+	}
+}
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Called after updating RLIMIT_CPU to set timer expiration if necessary.
+ */
+void update_rlimit_cpu(unsigned long rlim_new)
+{
+	cputime_t cputime;
+
+	cputime = secs_to_cputime(rlim_new);
+	if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
+            cputime_lt(current->signal->it_prof_expires, cputime)) {
+		spin_lock_irq(&current->sighand->siglock);
+		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
+		spin_unlock_irq(&current->sighand->siglock);
+	}
+}
+
 static int check_clock(const clockid_t which_clock)
 {
 	int error = 0;
@@ -158,10 +251,6 @@ static inline cputime_t virt_ticks(struct task_struct *p)
 {
 	return p->utime;
 }
-static inline unsigned long long sched_ns(struct task_struct *p)
-{
-	return task_sched_runtime(p);
-}
 
 int posix_cpu_clock_getres(const clockid_t which_clock, struct timespec *tp)
 {
@@ -211,7 +300,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 		cpu->cpu = virt_ticks(p);
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = sched_ns(p);
+		cpu->sched = task_sched_runtime(p);
 		break;
 	}
 	return 0;
@@ -226,31 +315,20 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx,
 					 struct task_struct *p,
 					 union cpu_time_count *cpu)
 {
-	struct task_struct *t = p;
- 	switch (clock_idx) {
+	struct task_cputime cputime;
+
+	thread_group_cputime(p, &cputime);
+	switch (clock_idx) {
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
-		cpu->cpu = cputime_add(p->signal->utime, p->signal->stime);
-		do {
-			cpu->cpu = cputime_add(cpu->cpu, prof_ticks(t));
-			t = next_thread(t);
-		} while (t != p);
+		cpu->cpu = cputime_add(cputime.utime, cputime.stime);
 		break;
 	case CPUCLOCK_VIRT:
-		cpu->cpu = p->signal->utime;
-		do {
-			cpu->cpu = cputime_add(cpu->cpu, virt_ticks(t));
-			t = next_thread(t);
-		} while (t != p);
+		cpu->cpu = cputime.utime;
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = p->signal->sum_sched_runtime;
-		/* Add in each other live thread.  */
-		while ((t = next_thread(t)) != p) {
-			cpu->sched += t->se.sum_exec_runtime;
-		}
-		cpu->sched += sched_ns(p);
+		cpu->sched = thread_group_sched_runtime(p);
 		break;
 	}
 	return 0;
@@ -471,80 +549,11 @@ void posix_cpu_timers_exit(struct task_struct *tsk)
 }
 void posix_cpu_timers_exit_group(struct task_struct *tsk)
 {
-	cleanup_timers(tsk->signal->cpu_timers,
-		       cputime_add(tsk->utime, tsk->signal->utime),
-		       cputime_add(tsk->stime, tsk->signal->stime),
-		     tsk->se.sum_exec_runtime + tsk->signal->sum_sched_runtime);
-}
-
-
-/*
- * Set the expiry times of all the threads in the process so one of them
- * will go off before the process cumulative expiry total is reached.
- */
-static void process_timer_rebalance(struct task_struct *p,
-				    unsigned int clock_idx,
-				    union cpu_time_count expires,
-				    union cpu_time_count val)
-{
-	cputime_t ticks, left;
-	unsigned long long ns, nsleft;
- 	struct task_struct *t = p;
-	unsigned int nthreads = atomic_read(&p->signal->live);
-
-	if (!nthreads)
-		return;
+	struct task_cputime cputime;
 
-	switch (clock_idx) {
-	default:
-		BUG();
-		break;
-	case CPUCLOCK_PROF:
-		left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu),
-				       nthreads);
-		do {
-			if (likely(!(t->flags & PF_EXITING))) {
-				ticks = cputime_add(prof_ticks(t), left);
-				if (cputime_eq(t->it_prof_expires,
-					       cputime_zero) ||
-				    cputime_gt(t->it_prof_expires, ticks)) {
-					t->it_prof_expires = ticks;
-				}
-			}
-			t = next_thread(t);
-		} while (t != p);
-		break;
-	case CPUCLOCK_VIRT:
-		left = cputime_div_non_zero(cputime_sub(expires.cpu, val.cpu),
-				       nthreads);
-		do {
-			if (likely(!(t->flags & PF_EXITING))) {
-				ticks = cputime_add(virt_ticks(t), left);
-				if (cputime_eq(t->it_virt_expires,
-					       cputime_zero) ||
-				    cputime_gt(t->it_virt_expires, ticks)) {
-					t->it_virt_expires = ticks;
-				}
-			}
-			t = next_thread(t);
-		} while (t != p);
-		break;
-	case CPUCLOCK_SCHED:
-		nsleft = expires.sched - val.sched;
-		do_div(nsleft, nthreads);
-		nsleft = max_t(unsigned long long, nsleft, 1);
-		do {
-			if (likely(!(t->flags & PF_EXITING))) {
-				ns = t->se.sum_exec_runtime + nsleft;
-				if (t->it_sched_expires == 0 ||
-				    t->it_sched_expires > ns) {
-					t->it_sched_expires = ns;
-				}
-			}
-			t = next_thread(t);
-		} while (t != p);
-		break;
-	}
+	thread_group_cputime(tsk, &cputime);
+	cleanup_timers(tsk->signal->cpu_timers,
+		       cputime.utime, cputime.stime, cputime.sum_exec_runtime);
 }
 
 static void clear_dead_task(struct k_itimer *timer, union cpu_time_count now)
@@ -608,29 +617,32 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
 			default:
 				BUG();
 			case CPUCLOCK_PROF:
-				if (cputime_eq(p->it_prof_expires,
+				if (cputime_eq(p->cputime_expires.prof_exp,
 					       cputime_zero) ||
-				    cputime_gt(p->it_prof_expires,
+				    cputime_gt(p->cputime_expires.prof_exp,
 					       nt->expires.cpu))
-					p->it_prof_expires = nt->expires.cpu;
+					p->cputime_expires.prof_exp =
+						nt->expires.cpu;
 				break;
 			case CPUCLOCK_VIRT:
-				if (cputime_eq(p->it_virt_expires,
+				if (cputime_eq(p->cputime_expires.virt_exp,
 					       cputime_zero) ||
-				    cputime_gt(p->it_virt_expires,
+				    cputime_gt(p->cputime_expires.virt_exp,
 					       nt->expires.cpu))
-					p->it_virt_expires = nt->expires.cpu;
+					p->cputime_expires.virt_exp =
+						nt->expires.cpu;
 				break;
 			case CPUCLOCK_SCHED:
-				if (p->it_sched_expires == 0 ||
-				    p->it_sched_expires > nt->expires.sched)
-					p->it_sched_expires = nt->expires.sched;
+				if (p->cputime_expires.sched_exp == 0 ||
+				    p->cputime_expires.sched_exp >
+							nt->expires.sched)
+					p->cputime_expires.sched_exp =
+						nt->expires.sched;
 				break;
 			}
 		} else {
 			/*
-			 * For a process timer, we must balance
-			 * all the live threads' expirations.
+			 * For a process timer, set the cached expiration time.
 			 */
 			switch (CPUCLOCK_WHICH(timer->it_clock)) {
 			default:
@@ -641,7 +653,9 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
 				    cputime_lt(p->signal->it_virt_expires,
 					       timer->it.cpu.expires.cpu))
 					break;
-				goto rebalance;
+				p->signal->cputime_expires.virt_exp =
+					timer->it.cpu.expires.cpu;
+				break;
 			case CPUCLOCK_PROF:
 				if (!cputime_eq(p->signal->it_prof_expires,
 						cputime_zero) &&
@@ -652,13 +666,12 @@ static void arm_timer(struct k_itimer *timer, union cpu_time_count now)
 				if (i != RLIM_INFINITY &&
 				    i <= cputime_to_secs(timer->it.cpu.expires.cpu))
 					break;
-				goto rebalance;
+				p->signal->cputime_expires.prof_exp =
+					timer->it.cpu.expires.cpu;
+				break;
 			case CPUCLOCK_SCHED:
-			rebalance:
-				process_timer_rebalance(
-					timer->it.cpu.task,
-					CPUCLOCK_WHICH(timer->it_clock),
-					timer->it.cpu.expires, now);
+				p->signal->cputime_expires.sched_exp =
+					timer->it.cpu.expires.sched;
 				break;
 			}
 		}
@@ -969,13 +982,13 @@ static void check_thread_timers(struct task_struct *tsk,
 	struct signal_struct *const sig = tsk->signal;
 
 	maxfire = 20;
-	tsk->it_prof_expires = cputime_zero;
+	tsk->cputime_expires.prof_exp = cputime_zero;
 	while (!list_empty(timers)) {
 		struct cpu_timer_list *t = list_first_entry(timers,
 						      struct cpu_timer_list,
 						      entry);
 		if (!--maxfire || cputime_lt(prof_ticks(tsk), t->expires.cpu)) {
-			tsk->it_prof_expires = t->expires.cpu;
+			tsk->cputime_expires.prof_exp = t->expires.cpu;
 			break;
 		}
 		t->firing = 1;
@@ -984,13 +997,13 @@ static void check_thread_timers(struct task_struct *tsk,
 
 	++timers;
 	maxfire = 20;
-	tsk->it_virt_expires = cputime_zero;
+	tsk->cputime_expires.virt_exp = cputime_zero;
 	while (!list_empty(timers)) {
 		struct cpu_timer_list *t = list_first_entry(timers,
 						      struct cpu_timer_list,
 						      entry);
 		if (!--maxfire || cputime_lt(virt_ticks(tsk), t->expires.cpu)) {
-			tsk->it_virt_expires = t->expires.cpu;
+			tsk->cputime_expires.virt_exp = t->expires.cpu;
 			break;
 		}
 		t->firing = 1;
@@ -999,13 +1012,13 @@ static void check_thread_timers(struct task_struct *tsk,
 
 	++timers;
 	maxfire = 20;
-	tsk->it_sched_expires = 0;
+	tsk->cputime_expires.sched_exp = 0;
 	while (!list_empty(timers)) {
 		struct cpu_timer_list *t = list_first_entry(timers,
 						      struct cpu_timer_list,
 						      entry);
 		if (!--maxfire || tsk->se.sum_exec_runtime < t->expires.sched) {
-			tsk->it_sched_expires = t->expires.sched;
+			tsk->cputime_expires.sched_exp = t->expires.sched;
 			break;
 		}
 		t->firing = 1;
@@ -1055,10 +1068,10 @@ static void check_process_timers(struct task_struct *tsk,
 {
 	int maxfire;
 	struct signal_struct *const sig = tsk->signal;
-	cputime_t utime, stime, ptime, virt_expires, prof_expires;
+	cputime_t utime, ptime, virt_expires, prof_expires;
 	unsigned long long sum_sched_runtime, sched_expires;
-	struct task_struct *t;
 	struct list_head *timers = sig->cpu_timers;
+	struct task_cputime cputime;
 
 	/*
 	 * Don't sample the current process CPU clocks if there are no timers.
@@ -1074,18 +1087,10 @@ static void check_process_timers(struct task_struct *tsk,
 	/*
 	 * Collect the current process totals.
 	 */
-	utime = sig->utime;
-	stime = sig->stime;
-	sum_sched_runtime = sig->sum_sched_runtime;
-	t = tsk;
-	do {
-		utime = cputime_add(utime, t->utime);
-		stime = cputime_add(stime, t->stime);
-		sum_sched_runtime += t->se.sum_exec_runtime;
-		t = next_thread(t);
-	} while (t != tsk);
-	ptime = cputime_add(utime, stime);
-
+	thread_group_cputime(tsk, &cputime);
+	utime = cputime.utime;
+	ptime = cputime_add(utime, cputime.stime);
+	sum_sched_runtime = cputime.sum_exec_runtime;
 	maxfire = 20;
 	prof_expires = cputime_zero;
 	while (!list_empty(timers)) {
@@ -1193,60 +1198,18 @@ static void check_process_timers(struct task_struct *tsk,
 		}
 	}
 
-	if (!cputime_eq(prof_expires, cputime_zero) ||
-	    !cputime_eq(virt_expires, cputime_zero) ||
-	    sched_expires != 0) {
-		/*
-		 * Rebalance the threads' expiry times for the remaining
-		 * process CPU timers.
-		 */
-
-		cputime_t prof_left, virt_left, ticks;
-		unsigned long long sched_left, sched;
-		const unsigned int nthreads = atomic_read(&sig->live);
-
-		if (!nthreads)
-			return;
-
-		prof_left = cputime_sub(prof_expires, utime);
-		prof_left = cputime_sub(prof_left, stime);
-		prof_left = cputime_div_non_zero(prof_left, nthreads);
-		virt_left = cputime_sub(virt_expires, utime);
-		virt_left = cputime_div_non_zero(virt_left, nthreads);
-		if (sched_expires) {
-			sched_left = sched_expires - sum_sched_runtime;
-			do_div(sched_left, nthreads);
-			sched_left = max_t(unsigned long long, sched_left, 1);
-		} else {
-			sched_left = 0;
-		}
-		t = tsk;
-		do {
-			if (unlikely(t->flags & PF_EXITING))
-				continue;
-
-			ticks = cputime_add(cputime_add(t->utime, t->stime),
-					    prof_left);
-			if (!cputime_eq(prof_expires, cputime_zero) &&
-			    (cputime_eq(t->it_prof_expires, cputime_zero) ||
-			     cputime_gt(t->it_prof_expires, ticks))) {
-				t->it_prof_expires = ticks;
-			}
-
-			ticks = cputime_add(t->utime, virt_left);
-			if (!cputime_eq(virt_expires, cputime_zero) &&
-			    (cputime_eq(t->it_virt_expires, cputime_zero) ||
-			     cputime_gt(t->it_virt_expires, ticks))) {
-				t->it_virt_expires = ticks;
-			}
-
-			sched = t->se.sum_exec_runtime + sched_left;
-			if (sched_expires && (t->it_sched_expires == 0 ||
-					      t->it_sched_expires > sched)) {
-				t->it_sched_expires = sched;
-			}
-		} while ((t = next_thread(t)) != tsk);
-	}
+	if (!cputime_eq(prof_expires, cputime_zero) &&
+	    (cputime_eq(sig->cputime_expires.prof_exp, cputime_zero) ||
+	     cputime_gt(sig->cputime_expires.prof_exp, prof_expires)))
+		sig->cputime_expires.prof_exp = prof_expires;
+	if (!cputime_eq(virt_expires, cputime_zero) &&
+	    (cputime_eq(sig->cputime_expires.virt_exp, cputime_zero) ||
+	     cputime_gt(sig->cputime_expires.virt_exp, virt_expires)))
+		sig->cputime_expires.virt_exp = virt_expires;
+	if (sched_expires != 0 &&
+	    (sig->cputime_expires.sched_exp == 0 ||
+	     sig->cputime_expires.sched_exp > sched_expires))
+		sig->cputime_expires.sched_exp = sched_expires;
 }
 
 /*
@@ -1314,6 +1277,78 @@ out:
 	++timer->it_requeue_pending;
 }
 
+/**
+ * task_cputime_zero - Check a task_cputime struct for all zero fields.
+ *
+ * @cputime:	The struct to compare.
+ *
+ * Checks @cputime to see if all fields are zero.  Returns true if all fields
+ * are zero, false if any field is nonzero.
+ */
+static inline int task_cputime_zero(const struct task_cputime *cputime)
+{
+	if (cputime_eq(cputime->utime, cputime_zero) &&
+	    cputime_eq(cputime->stime, cputime_zero) &&
+	    cputime->sum_exec_runtime == 0)
+		return 1;
+	return 0;
+}
+
+/**
+ * task_cputime_expired - Compare two task_cputime entities.
+ *
+ * @sample:	The task_cputime structure to be checked for expiration.
+ * @expires:	Expiration times, against which @sample will be checked.
+ *
+ * Checks @sample against @expires to see if any field of @sample has expired.
+ * Returns true if any field of the former is greater than the corresponding
+ * field of the latter if the latter field is set.  Otherwise returns false.
+ */
+static inline int task_cputime_expired(const struct task_cputime *sample,
+					const struct task_cputime *expires)
+{
+	if (!cputime_eq(expires->utime, cputime_zero) &&
+	    cputime_ge(sample->utime, expires->utime))
+		return 1;
+	if (!cputime_eq(expires->stime, cputime_zero) &&
+	    cputime_ge(cputime_add(sample->utime, sample->stime),
+		       expires->stime))
+		return 1;
+	if (expires->sum_exec_runtime != 0 &&
+	    sample->sum_exec_runtime >= expires->sum_exec_runtime)
+		return 1;
+	return 0;
+}
+
+/**
+ * fastpath_timer_check - POSIX CPU timers fast path.
+ *
+ * @tsk:	The task (thread) being checked.
+ * @sig:	The signal pointer for that task.
+ *
+ * If there are no timers set return false.  Otherwise snapshot the task and
+ * thread group timers, then compare them with the corresponding expiration
+ # times.  Returns true if a timer has expired, else returns false.
+ */
+static inline int fastpath_timer_check(struct task_struct *tsk,
+					struct signal_struct *sig)
+{
+	struct task_cputime task_sample = {
+		.utime = tsk->utime,
+		.stime = tsk->stime,
+		.sum_exec_runtime = tsk->se.sum_exec_runtime
+	};
+	struct task_cputime group_sample;
+
+	if (task_cputime_zero(&tsk->cputime_expires) &&
+	    task_cputime_zero(&sig->cputime_expires))
+		return 0;
+	if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
+		return 1;
+	thread_group_cputime(tsk, &group_sample);
+	return task_cputime_expired(&group_sample, &sig->cputime_expires);
+}
+
 /*
  * This is called from the timer interrupt handler.  The irq handler has
  * already updated our counts.  We need to check if any timers fire now.
@@ -1323,30 +1358,29 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 {
 	LIST_HEAD(firing);
 	struct k_itimer *timer, *next;
+	struct signal_struct *sig;
+	struct sighand_struct *sighand;
+	unsigned long flags;
 
 	BUG_ON(!irqs_disabled());
 
-#define UNEXPIRED(clock) \
-		(cputime_eq(tsk->it_##clock##_expires, cputime_zero) || \
-		 cputime_lt(clock##_ticks(tsk), tsk->it_##clock##_expires))
-
-	if (UNEXPIRED(prof) && UNEXPIRED(virt) &&
-	    (tsk->it_sched_expires == 0 ||
-	     tsk->se.sum_exec_runtime < tsk->it_sched_expires))
-		return;
-
-#undef	UNEXPIRED
-
+	/* Pick up tsk->signal and make sure it's valid. */
+	sig = tsk->signal;
 	/*
-	 * Double-check with locks held.
+	 * The fast path checks that there are no expired thread or thread
+	 * group timers.  If that's so, just return.  Also check that
+	 * tsk->signal is non-NULL; this probably can't happen but cover the
+	 * possibility anyway.
 	 */
-	read_lock(&tasklist_lock);
-	if (likely(tsk->signal != NULL)) {
-		spin_lock(&tsk->sighand->siglock);
-
+	if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) {
+		return;
+	}
+	sighand = lock_task_sighand(tsk, &flags);
+	if (likely(sighand)) {
 		/*
-		 * Here we take off tsk->cpu_timers[N] and tsk->signal->cpu_timers[N]
-		 * all the timers that are firing, and put them on the firing list.
+		 * Here we take off tsk->signal->cpu_timers[N] and
+		 * tsk->cpu_timers[N] all the timers that are firing, and
+		 * put them on the firing list.
 		 */
 		check_thread_timers(tsk, &firing);
 		check_process_timers(tsk, &firing);
@@ -1359,9 +1393,8 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 		 * that gets the timer lock before we do will give it up and
 		 * spin until we've taken care of that timer below.
 		 */
-		spin_unlock(&tsk->sighand->siglock);
 	}
-	read_unlock(&tasklist_lock);
+	unlock_task_sighand(tsk, &flags);
 
 	/*
 	 * Now that all the timers on our list have the firing flag,
@@ -1389,10 +1422,9 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 
 /*
  * Set one of the process-wide special case CPU timers.
- * The tasklist_lock and tsk->sighand->siglock must be held by the caller.
- * The oldval argument is null for the RLIMIT_CPU timer, where *newval is
- * absolute; non-null for ITIMER_*, where *newval is relative and we update
- * it to be absolute, *oldval is absolute and we update it to be relative.
+ * The tsk->sighand->siglock must be held by the caller.
+ * The *newval argument is relative and we update it to be absolute, *oldval
+ * is absolute and we update it to be relative.
  */
 void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 			   cputime_t *newval, cputime_t *oldval)
@@ -1435,13 +1467,14 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 	    cputime_ge(list_first_entry(head,
 				  struct cpu_timer_list, entry)->expires.cpu,
 		       *newval)) {
-		/*
-		 * Rejigger each thread's expiry time so that one will
-		 * notice before we hit the process-cumulative expiry time.
-		 */
-		union cpu_time_count expires = { .sched = 0 };
-		expires.cpu = *newval;
-		process_timer_rebalance(tsk, clock_idx, expires, now);
+		switch (clock_idx) {
+		case CPUCLOCK_PROF:
+			tsk->signal->cputime_expires.prof_exp = *newval;
+			break;
+		case CPUCLOCK_VIRT:
+			tsk->signal->cputime_expires.virt_exp = *newval;
+			break;
+		}
 	}
 }
 
diff --git a/kernel/sched.c b/kernel/sched.c
index cc1f81b50b82..c51b5d276665 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4036,6 +4036,25 @@ DEFINE_PER_CPU(struct kernel_stat, kstat);
 
 EXPORT_PER_CPU_SYMBOL(kstat);
 
+/*
+ * Return any ns on the sched_clock that have not yet been banked in
+ * @p in case that task is currently running.
+ *
+ * Called with task_rq_lock() held on @rq.
+ */
+static unsigned long long task_delta_exec(struct task_struct *p, struct rq *rq)
+{
+	if (task_current(rq, p)) {
+		u64 delta_exec;
+
+		update_rq_clock(rq);
+		delta_exec = rq->clock - p->se.exec_start;
+		if ((s64)delta_exec > 0)
+			return delta_exec;
+	}
+	return 0;
+}
+
 /*
  * Return p->sum_exec_runtime plus any more ns on the sched_clock
  * that have not yet been banked in case the task is currently running.
@@ -4043,17 +4062,31 @@ EXPORT_PER_CPU_SYMBOL(kstat);
 unsigned long long task_sched_runtime(struct task_struct *p)
 {
 	unsigned long flags;
-	u64 ns, delta_exec;
+	u64 ns;
 	struct rq *rq;
 
 	rq = task_rq_lock(p, &flags);
-	ns = p->se.sum_exec_runtime;
-	if (task_current(rq, p)) {
-		update_rq_clock(rq);
-		delta_exec = rq->clock - p->se.exec_start;
-		if ((s64)delta_exec > 0)
-			ns += delta_exec;
-	}
+	ns = p->se.sum_exec_runtime + task_delta_exec(p, rq);
+	task_rq_unlock(rq, &flags);
+
+	return ns;
+}
+
+/*
+ * Return sum_exec_runtime for the thread group plus any more ns on the
+ * sched_clock that have not yet been banked in case the task is currently
+ * running.
+ */
+unsigned long long thread_group_sched_runtime(struct task_struct *p)
+{
+	unsigned long flags;
+	u64 ns;
+	struct rq *rq;
+	struct task_cputime totals;
+
+	rq = task_rq_lock(p, &flags);
+	thread_group_cputime(p, &totals);
+	ns = totals.sum_exec_runtime + task_delta_exec(p, rq);
 	task_rq_unlock(rq, &flags);
 
 	return ns;
@@ -4070,6 +4103,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime)
 	cputime64_t tmp;
 
 	p->utime = cputime_add(p->utime, cputime);
+	account_group_user_time(p, cputime);
 
 	/* Add user time to cpustat. */
 	tmp = cputime_to_cputime64(cputime);
@@ -4094,6 +4128,7 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime)
 	tmp = cputime_to_cputime64(cputime);
 
 	p->utime = cputime_add(p->utime, cputime);
+	account_group_user_time(p, cputime);
 	p->gtime = cputime_add(p->gtime, cputime);
 
 	cpustat->user = cputime64_add(cpustat->user, tmp);
@@ -4129,6 +4164,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
 	}
 
 	p->stime = cputime_add(p->stime, cputime);
+	account_group_system_time(p, cputime);
 
 	/* Add system time to cpustat. */
 	tmp = cputime_to_cputime64(cputime);
@@ -4170,6 +4206,7 @@ void account_steal_time(struct task_struct *p, cputime_t steal)
 
 	if (p == rq->idle) {
 		p->stime = cputime_add(p->stime, steal);
+		account_group_system_time(p, steal);
 		if (atomic_read(&rq->nr_iowait) > 0)
 			cpustat->iowait = cputime64_add(cpustat->iowait, tmp);
 		else
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index fb8994c6d4bb..99aa31acc544 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -507,6 +507,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 		struct task_struct *curtask = task_of(curr);
 
 		cpuacct_charge(curtask, delta_exec);
+		account_group_exec_runtime(curtask, delta_exec);
 	}
 }
 
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 552310798dad..8375e69af36a 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -483,6 +483,8 @@ static void update_curr_rt(struct rq *rq)
 	schedstat_set(curr->se.exec_max, max(curr->se.exec_max, delta_exec));
 
 	curr->se.sum_exec_runtime += delta_exec;
+	account_group_exec_runtime(curr, delta_exec);
+
 	curr->se.exec_start = rq->clock;
 	cpuacct_charge(curr, delta_exec);
 
@@ -1412,7 +1414,7 @@ static void watchdog(struct rq *rq, struct task_struct *p)
 		p->rt.timeout++;
 		next = DIV_ROUND_UP(min(soft, hard), USEC_PER_SEC/HZ);
 		if (p->rt.timeout > next)
-			p->it_sched_expires = p->se.sum_exec_runtime;
+			p->cputime_expires.sched_exp = p->se.sum_exec_runtime;
 	}
 }
 
diff --git a/kernel/signal.c b/kernel/signal.c
index e661b01d340f..6eea5826d618 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1338,6 +1338,7 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 	struct siginfo info;
 	unsigned long flags;
 	struct sighand_struct *psig;
+	struct task_cputime cputime;
 	int ret = sig;
 
 	BUG_ON(sig == -1);
@@ -1368,10 +1369,9 @@ int do_notify_parent(struct task_struct *tsk, int sig)
 
 	info.si_uid = tsk->uid;
 
-	info.si_utime = cputime_to_clock_t(cputime_add(tsk->utime,
-						       tsk->signal->utime));
-	info.si_stime = cputime_to_clock_t(cputime_add(tsk->stime,
-						       tsk->signal->stime));
+	thread_group_cputime(tsk, &cputime);
+	info.si_utime = cputime_to_jiffies(cputime.utime);
+	info.si_stime = cputime_to_jiffies(cputime.stime);
 
 	info.si_status = tsk->exit_code & 0x7f;
 	if (tsk->exit_code & 0x80)
diff --git a/kernel/sys.c b/kernel/sys.c
index 038a7bc0901d..d046a7a055c2 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -853,38 +853,28 @@ asmlinkage long sys_setfsgid(gid_t gid)
 	return old_fsgid;
 }
 
+void do_sys_times(struct tms *tms)
+{
+	struct task_cputime cputime;
+	cputime_t cutime, cstime;
+
+	spin_lock_irq(&current->sighand->siglock);
+	thread_group_cputime(current, &cputime);
+	cutime = current->signal->cutime;
+	cstime = current->signal->cstime;
+	spin_unlock_irq(&current->sighand->siglock);
+	tms->tms_utime = cputime_to_clock_t(cputime.utime);
+	tms->tms_stime = cputime_to_clock_t(cputime.stime);
+	tms->tms_cutime = cputime_to_clock_t(cutime);
+	tms->tms_cstime = cputime_to_clock_t(cstime);
+}
+
 asmlinkage long sys_times(struct tms __user * tbuf)
 {
-	/*
-	 *	In the SMP world we might just be unlucky and have one of
-	 *	the times increment as we use it. Since the value is an
-	 *	atomically safe type this is just fine. Conceptually its
-	 *	as if the syscall took an instant longer to occur.
-	 */
 	if (tbuf) {
 		struct tms tmp;
-		struct task_struct *tsk = current;
-		struct task_struct *t;
-		cputime_t utime, stime, cutime, cstime;
-
-		spin_lock_irq(&tsk->sighand->siglock);
-		utime = tsk->signal->utime;
-		stime = tsk->signal->stime;
-		t = tsk;
-		do {
-			utime = cputime_add(utime, t->utime);
-			stime = cputime_add(stime, t->stime);
-			t = next_thread(t);
-		} while (t != tsk);
-
-		cutime = tsk->signal->cutime;
-		cstime = tsk->signal->cstime;
-		spin_unlock_irq(&tsk->sighand->siglock);
-
-		tmp.tms_utime = cputime_to_clock_t(utime);
-		tmp.tms_stime = cputime_to_clock_t(stime);
-		tmp.tms_cutime = cputime_to_clock_t(cutime);
-		tmp.tms_cstime = cputime_to_clock_t(cstime);
+
+		do_sys_times(&tmp);
 		if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
 			return -EFAULT;
 	}
@@ -1445,7 +1435,6 @@ asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *r
 asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
 {
 	struct rlimit new_rlim, *old_rlim;
-	unsigned long it_prof_secs;
 	int retval;
 
 	if (resource >= RLIM_NLIMITS)
@@ -1491,18 +1480,7 @@ asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
 	if (new_rlim.rlim_cur == RLIM_INFINITY)
 		goto out;
 
-	it_prof_secs = cputime_to_secs(current->signal->it_prof_expires);
-	if (it_prof_secs == 0 || new_rlim.rlim_cur <= it_prof_secs) {
-		unsigned long rlim_cur = new_rlim.rlim_cur;
-		cputime_t cputime;
-
-		cputime = secs_to_cputime(rlim_cur);
-		read_lock(&tasklist_lock);
-		spin_lock_irq(&current->sighand->siglock);
-		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
-		spin_unlock_irq(&current->sighand->siglock);
-		read_unlock(&tasklist_lock);
-	}
+	update_rlimit_cpu(new_rlim.rlim_cur);
 out:
 	return 0;
 }
@@ -1540,11 +1518,8 @@ out:
  *
  */
 
-static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r,
-				     cputime_t *utimep, cputime_t *stimep)
+static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r)
 {
-	*utimep = cputime_add(*utimep, t->utime);
-	*stimep = cputime_add(*stimep, t->stime);
 	r->ru_nvcsw += t->nvcsw;
 	r->ru_nivcsw += t->nivcsw;
 	r->ru_minflt += t->min_flt;
@@ -1558,12 +1533,13 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 	struct task_struct *t;
 	unsigned long flags;
 	cputime_t utime, stime;
+	struct task_cputime cputime;
 
 	memset((char *) r, 0, sizeof *r);
 	utime = stime = cputime_zero;
 
 	if (who == RUSAGE_THREAD) {
-		accumulate_thread_rusage(p, r, &utime, &stime);
+		accumulate_thread_rusage(p, r);
 		goto out;
 	}
 
@@ -1586,8 +1562,9 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 				break;
 
 		case RUSAGE_SELF:
-			utime = cputime_add(utime, p->signal->utime);
-			stime = cputime_add(stime, p->signal->stime);
+			thread_group_cputime(p, &cputime);
+			utime = cputime_add(utime, cputime.utime);
+			stime = cputime_add(stime, cputime.stime);
 			r->ru_nvcsw += p->signal->nvcsw;
 			r->ru_nivcsw += p->signal->nivcsw;
 			r->ru_minflt += p->signal->min_flt;
@@ -1596,7 +1573,7 @@ static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
 			r->ru_oublock += p->signal->oublock;
 			t = p;
 			do {
-				accumulate_thread_rusage(t, r, &utime, &stime);
+				accumulate_thread_rusage(t, r);
 				t = next_thread(t);
 			} while (t != p);
 			break;
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 03fc6a81ae32..69649783c266 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -75,6 +75,7 @@
 #include <linux/string.h>
 #include <linux/selinux.h>
 #include <linux/mutex.h>
+#include <linux/posix-timers.h>
 
 #include "avc.h"
 #include "objsec.h"
@@ -2321,13 +2322,7 @@ static void selinux_bprm_post_apply_creds(struct linux_binprm *bprm)
 			initrlim = init_task.signal->rlim+i;
 			rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur);
 		}
-		if (current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY) {
-			/*
-			 * This will cause RLIMIT_CPU calculations
-			 * to be refigured.
-			 */
-			current->it_prof_expires = jiffies_to_cputime(1);
-		}
+		update_rlimit_cpu(rlim->rlim_cur);
 	}
 
 	/* Wake up the parent if it is waiting so that it can
-- 
cgit v1.2.3


From 0a8eaa4f9b58759595a1bfe13a1295fdc25ba026 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Sun, 14 Sep 2008 17:03:52 +0200
Subject: timers: fix itimer/many thread hang, fix #2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

fix the UP build:

In file included from arch/x86/kernel/asm-offsets_32.c:9,
                 from arch/x86/kernel/asm-offsets.c:3:
include/linux/sched.h: In function ‘thread_group_cputime_clone_thread’:
include/linux/sched.h:2272: warning: no return statement in function returning non-void
include/linux/sched.h: In function ‘thread_group_cputime_account_user’:
include/linux/sched.h:2284: error: invalid type argument of ‘->’ (have ‘struct task_cputime’)
include/linux/sched.h:2284: error: invalid type argument of ‘->’ (have ‘struct task_cputime’)
include/linux/sched.h: In function ‘thread_group_cputime_account_system’:
include/linux/sched.h:2291: error: invalid type argument of ‘->’ (have ‘struct task_cputime’)
include/linux/sched.h:2291: error: invalid type argument of ‘->’ (have ‘struct task_cputime’)
include/linux/sched.h: In function ‘thread_group_cputime_account_exec_runtime’:
include/linux/sched.h:2298: error: invalid type argument of ‘->’ (have ‘struct task_cputime’)
distcc[14501] ERROR: compile arch/x86/kernel/asm-offsets.c on a/30 failed
make[1]: *** [arch/x86/kernel/asm-offsets.s] Error 1

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/sched.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 26d7a5f2d0ba..ed355f02d329 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2251,6 +2251,7 @@ static inline void thread_group_cputime_free(struct signal_struct *sig)
 static inline int thread_group_cputime_clone_thread(struct task_struct *curr,
 						     struct task_struct *tsk)
 {
+	return 0;
 }
 
 static inline void thread_group_cputime(struct task_struct *tsk,
@@ -2263,21 +2264,21 @@ static inline void thread_group_cputime_account_user(
 	struct thread_group_cputime *tgtimes,
 	cputime_t cputime)
 {
-	tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime);
+	tgtimes->totals.utime = cputime_add(tgtimes->totals.utime, cputime);
 }
 
 static inline void thread_group_cputime_account_system(
 	struct thread_group_cputime *tgtimes,
 	cputime_t cputime)
 {
-	tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime);
+	tgtimes->totals.stime = cputime_add(tgtimes->totals.stime, cputime);
 }
 
 static inline void thread_group_cputime_account_exec_runtime(
 	struct thread_group_cputime *tgtimes,
 	unsigned long long ns)
 {
-	tgtimes->totals->sum_exec_runtime += ns;
+	tgtimes->totals.sum_exec_runtime += ns;
 }
 
 #endif /* CONFIG_SMP */
-- 
cgit v1.2.3


From 5ce73a4a5a4893a1aa4cdeed1b1a5a6de42c43b6 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Sun, 14 Sep 2008 17:11:46 +0200
Subject: timers: fix itimer/many thread hang, cleanups

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/sched.h     | 2 +-
 kernel/posix-cpu-timers.c | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index ed355f02d329..7ce8d4e53565 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -430,7 +430,7 @@ struct pacct_struct {
  * @utime:		time spent in user mode, in &cputime_t units
  * @stime:		time spent in kernel mode, in &cputime_t units
  * @sum_exec_runtime:	total time spent on the CPU, in nanoseconds
- * 
+ *
  * This structure groups together three kinds of CPU time that are
  * tracked for threads and thread groups.  Most things considering
  * CPU time want to group these counts together and treat all three
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index dba1c334c3e8..9a7ea049fcdc 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -94,7 +94,7 @@ void update_rlimit_cpu(unsigned long rlim_new)
 
 	cputime = secs_to_cputime(rlim_new);
 	if (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
-            cputime_lt(current->signal->it_prof_expires, cputime)) {
+	    cputime_lt(current->signal->it_prof_expires, cputime)) {
 		spin_lock_irq(&current->sighand->siglock);
 		set_process_cpu_timer(current, CPUCLOCK_PROF, &cputime, NULL);
 		spin_unlock_irq(&current->sighand->siglock);
@@ -1372,9 +1372,9 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 	 * tsk->signal is non-NULL; this probably can't happen but cover the
 	 * possibility anyway.
 	 */
-	if (unlikely(!sig) || !fastpath_timer_check(tsk, sig)) {
+	if (unlikely(!sig) || !fastpath_timer_check(tsk, sig))
 		return;
-	}
+
 	sighand = lock_task_sighand(tsk, &flags);
 	if (likely(sighand)) {
 		/*
-- 
cgit v1.2.3


From ccbe329bcd87924baed96474ec0a6725e3957897 Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@csr.com>
Date: Wed, 17 Sep 2008 16:34:03 +0100
Subject: bitmap: add bitmap_copy_le()

bitmap_copy_le() copies a bitmap, putting the bits into little-endian
order (i.e., each unsigned long word in the bitmap is put into
little-endian order).

The UWB stack used bitmaps to manage Medium Access Slot availability,
and these bitmaps need to be written to the hardware in LE order.

Signed-off-by: David Vrabel <david.vrabel@csr.com>
---
 include/linux/bitmap.h |  1 +
 lib/bitmap.c           | 22 ++++++++++++++++++++++
 2 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 89781fd48859..5379913aca52 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -130,6 +130,7 @@ extern void bitmap_fold(unsigned long *dst, const unsigned long *orig,
 extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order);
 extern void bitmap_release_region(unsigned long *bitmap, int pos, int order);
 extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order);
+extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits);
 
 #define BITMAP_LAST_WORD_MASK(nbits)					\
 (									\
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 06fb57c86de0..c2006bfeea41 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -1007,3 +1007,25 @@ int bitmap_allocate_region(unsigned long *bitmap, int pos, int order)
 	return 0;
 }
 EXPORT_SYMBOL(bitmap_allocate_region);
+
+/**
+ * bitmap_copy_le - copy a bitmap, putting the bits into little-endian order.
+ * @dst:   destination buffer
+ * @src:   bitmap to copy
+ * @nbits: number of bits in the bitmap
+ *
+ * Require nbits % BITS_PER_LONG == 0.
+ */
+void bitmap_copy_le(void *dst, const unsigned long *src, int nbits)
+{
+	unsigned long *d = dst;
+	int i;
+
+	for (i = 0; i < nbits/BITS_PER_LONG; i++) {
+		if (BITS_PER_LONG == 64)
+			d[i] = cpu_to_le64(src[i]);
+		else
+			d[i] = cpu_to_le32(src[i]);
+	}
+}
+EXPORT_SYMBOL(bitmap_copy_le);
-- 
cgit v1.2.3


From 34e95e41f1fd751e33a7eb3fa66594903b81f13d Mon Sep 17 00:00:00 2001
From: Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
Date: Wed, 17 Sep 2008 16:34:05 +0100
Subject: uwb: add the uwb include files

Signed-off-by: David Vrabel <david.vrabel@csr.com>
---
 include/linux/uwb.h           | 761 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/uwb/debug-cmd.h |  57 ++++
 include/linux/uwb/debug.h     |  82 +++++
 include/linux/uwb/spec.h      | 727 ++++++++++++++++++++++++++++++++++++++++
 include/linux/wlp.h           | 735 ++++++++++++++++++++++++++++++++++++++++
 5 files changed, 2362 insertions(+)
 create mode 100644 include/linux/uwb.h
 create mode 100644 include/linux/uwb/debug-cmd.h
 create mode 100644 include/linux/uwb/debug.h
 create mode 100644 include/linux/uwb/spec.h
 create mode 100644 include/linux/wlp.h

(limited to 'include')

diff --git a/include/linux/uwb.h b/include/linux/uwb.h
new file mode 100644
index 000000000000..0cd35937e120
--- /dev/null
+++ b/include/linux/uwb.h
@@ -0,0 +1,761 @@
+/*
+ * Ultra Wide Band
+ * UWB API
+ *
+ * Copyright (C) 2005-2006 Intel Corporation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
+ *
+ * FIXME: doc: overview of the API, different parts and pointers
+ */
+
+#ifndef __LINUX__UWB_H__
+#define __LINUX__UWB_H__
+
+#include <linux/limits.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/timer.h>
+#include <linux/workqueue.h>
+#include <linux/uwb/spec.h>
+
+struct uwb_dev;
+struct uwb_beca_e;
+struct uwb_rc;
+struct uwb_rsv;
+struct uwb_dbg;
+
+/**
+ * struct uwb_dev - a UWB Device
+ * @rc: UWB Radio Controller that discovered the device (kind of its
+ *     parent).
+ * @bce: a beacon cache entry for this device; or NULL if the device
+ *     is a local radio controller.
+ * @mac_addr: the EUI-48 address of this device.
+ * @dev_addr: the current DevAddr used by this device.
+ * @beacon_slot: the slot number the beacon is using.
+ * @streams: bitmap of streams allocated to reservations targeted at
+ *     this device.  For an RC, this is the streams allocated for
+ *     reservations targeted at DevAddrs.
+ *
+ * A UWB device may either by a neighbor or part of a local radio
+ * controller.
+ */
+struct uwb_dev {
+	struct mutex mutex;
+	struct list_head list_node;
+	struct device dev;
+	struct uwb_rc *rc;		/* radio controller */
+	struct uwb_beca_e *bce;		/* Beacon Cache Entry */
+
+	struct uwb_mac_addr mac_addr;
+	struct uwb_dev_addr dev_addr;
+	int beacon_slot;
+	DECLARE_BITMAP(streams, UWB_NUM_STREAMS);
+};
+#define to_uwb_dev(d) container_of(d, struct uwb_dev, dev)
+
+/**
+ * UWB HWA/WHCI Radio Control {Command|Event} Block context IDs
+ *
+ * RC[CE]Bs have a 'context ID' field that matches the command with
+ * the event received to confirm it.
+ *
+ * Maximum number of context IDs
+ */
+enum { UWB_RC_CTX_MAX = 256 };
+
+
+/** Notification chain head for UWB generated events to listeners */
+struct uwb_notifs_chain {
+	struct list_head list;
+	struct mutex mutex;
+};
+
+/**
+ * struct uwb_mas_bm - a bitmap of all MAS in a superframe
+ * @bm: a bitmap of length #UWB_NUM_MAS
+ */
+struct uwb_mas_bm {
+	DECLARE_BITMAP(bm, UWB_NUM_MAS);
+};
+
+/**
+ * uwb_rsv_state - UWB Reservation state.
+ *
+ * NONE - reservation is not active (no DRP IE being transmitted).
+ *
+ * Owner reservation states:
+ *
+ * INITIATED - owner has sent an initial DRP request.
+ * PENDING - target responded with pending Reason Code.
+ * MODIFIED - reservation manager is modifying an established
+ * reservation with a different MAS allocation.
+ * ESTABLISHED - the reservation has been successfully negotiated.
+ *
+ * Target reservation states:
+ *
+ * DENIED - request is denied.
+ * ACCEPTED - request is accepted.
+ * PENDING - PAL has yet to make a decision to whether to accept or
+ * deny.
+ *
+ * FIXME: further target states TBD.
+ */
+enum uwb_rsv_state {
+	UWB_RSV_STATE_NONE,
+	UWB_RSV_STATE_O_INITIATED,
+	UWB_RSV_STATE_O_PENDING,
+	UWB_RSV_STATE_O_MODIFIED,
+	UWB_RSV_STATE_O_ESTABLISHED,
+	UWB_RSV_STATE_T_ACCEPTED,
+	UWB_RSV_STATE_T_DENIED,
+	UWB_RSV_STATE_T_PENDING,
+
+	UWB_RSV_STATE_LAST,
+};
+
+enum uwb_rsv_target_type {
+	UWB_RSV_TARGET_DEV,
+	UWB_RSV_TARGET_DEVADDR,
+};
+
+/**
+ * struct uwb_rsv_target - the target of a reservation.
+ *
+ * Reservations unicast and targeted at a single device
+ * (UWB_RSV_TARGET_DEV); or (e.g., in the case of WUSB) targeted at a
+ * specific (private) DevAddr (UWB_RSV_TARGET_DEVADDR).
+ */
+struct uwb_rsv_target {
+	enum uwb_rsv_target_type type;
+	union {
+		struct uwb_dev *dev;
+		struct uwb_dev_addr devaddr;
+	};
+};
+
+/*
+ * Number of streams reserved for reservations targeted at DevAddrs.
+ */
+#define UWB_NUM_GLOBAL_STREAMS 1
+
+typedef void (*uwb_rsv_cb_f)(struct uwb_rsv *rsv);
+
+/**
+ * struct uwb_rsv - a DRP reservation
+ *
+ * Data structure management:
+ *
+ * @rc:             the radio controller this reservation is for
+ *                  (as target or owner)
+ * @rc_node:        a list node for the RC
+ * @pal_node:       a list node for the PAL
+ *
+ * Owner and target parameters:
+ *
+ * @owner:          the UWB device owning this reservation
+ * @target:         the target UWB device
+ * @type:           reservation type
+ *
+ * Owner parameters:
+ *
+ * @max_mas:        maxiumum number of MAS
+ * @min_mas:        minimum number of MAS
+ * @sparsity:       owner selected sparsity
+ * @is_multicast:   true iff multicast
+ *
+ * @callback:       callback function when the reservation completes
+ * @pal_priv:       private data for the PAL making the reservation
+ *
+ * Reservation status:
+ *
+ * @status:         negotiation status
+ * @stream:         stream index allocated for this reservation
+ * @mas:            reserved MAS
+ * @drp_ie:         the DRP IE
+ * @ie_valid:       true iff the DRP IE matches the reservation parameters
+ *
+ * DRP reservations are uniquely identified by the owner, target and
+ * stream index.  However, when using a DevAddr as a target (e.g., for
+ * a WUSB cluster reservation) the responses may be received from
+ * devices with different DevAddrs.  In this case, reservations are
+ * uniquely identified by just the stream index.  A number of stream
+ * indexes (UWB_NUM_GLOBAL_STREAMS) are reserved for this.
+ */
+struct uwb_rsv {
+	struct uwb_rc *rc;
+	struct list_head rc_node;
+	struct list_head pal_node;
+
+	struct uwb_dev *owner;
+	struct uwb_rsv_target target;
+	enum uwb_drp_type type;
+	int max_mas;
+	int min_mas;
+	int sparsity;
+	bool is_multicast;
+
+	uwb_rsv_cb_f callback;
+	void *pal_priv;
+
+	enum uwb_rsv_state state;
+	u8 stream;
+	struct uwb_mas_bm mas;
+	struct uwb_ie_drp *drp_ie;
+	bool ie_valid;
+	struct timer_list timer;
+	bool expired;
+};
+
+static const
+struct uwb_mas_bm uwb_mas_bm_zero = { .bm = { 0 } };
+
+static inline void uwb_mas_bm_copy_le(void *dst, const struct uwb_mas_bm *mas)
+{
+	bitmap_copy_le(dst, mas->bm, UWB_NUM_MAS);
+}
+
+/**
+ * struct uwb_drp_avail - a radio controller's view of MAS usage
+ * @global:   MAS unused by neighbors (excluding reservations targetted
+ *            or owned by the local radio controller) or the beaon period
+ * @local:    MAS unused by local established reservations
+ * @pending:  MAS unused by local pending reservations
+ * @ie:       DRP Availability IE to be included in the beacon
+ * @ie_valid: true iff @ie is valid and does not need to regenerated from
+ *            @global and @local
+ *
+ * Each radio controller maintains a view of MAS usage or
+ * availability. MAS available for a new reservation are determined
+ * from the intersection of @global, @local, and @pending.
+ *
+ * The radio controller must transmit a DRP Availability IE that's the
+ * intersection of @global and @local.
+ *
+ * A set bit indicates the MAS is unused and available.
+ *
+ * rc->rsvs_mutex should be held before accessing this data structure.
+ *
+ * [ECMA-368] section 17.4.3.
+ */
+struct uwb_drp_avail {
+	DECLARE_BITMAP(global, UWB_NUM_MAS);
+	DECLARE_BITMAP(local, UWB_NUM_MAS);
+	DECLARE_BITMAP(pending, UWB_NUM_MAS);
+	struct uwb_ie_drp_avail ie;
+	bool ie_valid;
+};
+
+
+const char *uwb_rsv_state_str(enum uwb_rsv_state state);
+const char *uwb_rsv_type_str(enum uwb_drp_type type);
+
+struct uwb_rsv *uwb_rsv_create(struct uwb_rc *rc, uwb_rsv_cb_f cb,
+			       void *pal_priv);
+void uwb_rsv_destroy(struct uwb_rsv *rsv);
+
+int uwb_rsv_establish(struct uwb_rsv *rsv);
+int uwb_rsv_modify(struct uwb_rsv *rsv,
+		   int max_mas, int min_mas, int sparsity);
+void uwb_rsv_terminate(struct uwb_rsv *rsv);
+
+void uwb_rsv_accept(struct uwb_rsv *rsv, uwb_rsv_cb_f cb, void *pal_priv);
+
+/**
+ * Radio Control Interface instance
+ *
+ *
+ * Life cycle rules: those of the UWB Device.
+ *
+ * @index:    an index number for this radio controller, as used in the
+ *            device name.
+ * @version:  version of protocol supported by this device
+ * @priv:     Backend implementation; rw with uwb_dev.dev.sem taken.
+ * @cmd:      Backend implementation to execute commands; rw and call
+ *            only  with uwb_dev.dev.sem taken.
+ * @reset:    Hardware reset of radio controller and any PAL controllers.
+ * @filter:   Backend implementation to manipulate data to and from device
+ *            to be compliant to specification assumed by driver (WHCI
+ *            0.95).
+ *
+ *            uwb_dev.dev.mutex is used to execute commands and update
+ *            the corresponding structures; can't use a spinlock
+ *            because rc->cmd() can sleep.
+ * @ies:         This is a dynamically allocated array cacheing the
+ *               IEs (settable by the host) that the beacon of this
+ *               radio controller is currently sending.
+ *
+ *               In reality, we store here the full command we set to
+ *               the radio controller (which is basically a command
+ *               prefix followed by all the IEs the beacon currently
+ *               contains). This way we don't have to realloc and
+ *               memcpy when setting it.
+ *
+ *               We set this up in uwb_rc_ie_setup(), where we alloc
+ *               this struct, call get_ie() [so we know which IEs are
+ *               currently being sent, if any].
+ *
+ * @ies_capacity:Amount of space (in bytes) allocated in @ies. The
+ *               amount used is given by sizeof(*ies) plus ies->wIELength
+ *               (which is a little endian quantity all the time).
+ * @ies_mutex:   protect the IE cache
+ * @dbg:         information for the debug interface
+ */
+struct uwb_rc {
+	struct uwb_dev uwb_dev;
+	int index;
+	u16 version;
+
+	struct module *owner;
+	void *priv;
+	int (*start)(struct uwb_rc *rc);
+	void (*stop)(struct uwb_rc *rc);
+	int (*cmd)(struct uwb_rc *, const struct uwb_rccb *, size_t);
+	int (*reset)(struct uwb_rc *rc);
+	int (*filter_cmd)(struct uwb_rc *, struct uwb_rccb **, size_t *);
+	int (*filter_event)(struct uwb_rc *, struct uwb_rceb **, const size_t,
+			    size_t *, size_t *);
+
+	spinlock_t neh_lock;		/* protects neh_* and ctx_* */
+	struct list_head neh_list;	/* Open NE handles */
+	unsigned long ctx_bm[UWB_RC_CTX_MAX / 8 / sizeof(unsigned long)];
+	u8 ctx_roll;
+
+	int beaconing;			/* Beaconing state [channel number] */
+	int scanning;
+	enum uwb_scan_type scan_type:3;
+	unsigned ready:1;
+	struct uwb_notifs_chain notifs_chain;
+
+	struct uwb_drp_avail drp_avail;
+	struct list_head reservations;
+	struct mutex rsvs_mutex;
+	struct workqueue_struct *rsv_workq;
+	struct work_struct rsv_update_work;
+
+	struct mutex ies_mutex;
+	struct uwb_rc_cmd_set_ie *ies;
+	size_t ies_capacity;
+
+	spinlock_t pal_lock;
+	struct list_head pals;
+
+	struct uwb_dbg *dbg;
+};
+
+
+/**
+ * struct uwb_pal - a UWB PAL
+ * @new_rsv: called when a peer requests a reservation (may be NULL if
+ *           the PAL cannot accept reservation requests).
+ *
+ * A Protocol Adaptation Layer (PAL) is a user of the WiMedia UWB
+ * radio platform (e.g., WUSB, WLP or Bluetooth UWB AMP).
+ *
+ * The PALs using a radio controller must register themselves to
+ * permit the UWB stack to coordinate usage of the radio between the
+ * various PALs or to allow PALs to response to certain requests from
+ * peers.
+ *
+ * A struct uwb_pal should be embedded in a containing structure
+ * belonging to the PAL and initialized with uwb_pal_init()).  Fields
+ * should be set appropriately by the PAL before registering the PAL
+ * with uwb_pal_register().
+ */
+struct uwb_pal {
+	struct list_head node;
+
+	void (*new_rsv)(struct uwb_rsv *rsv);
+};
+
+void uwb_pal_init(struct uwb_pal *pal);
+int uwb_pal_register(struct uwb_rc *rc, struct uwb_pal *pal);
+void uwb_pal_unregister(struct uwb_rc *rc, struct uwb_pal *pal);
+
+/*
+ * General public API
+ *
+ * This API can be used by UWB device drivers or by those implementing
+ * UWB Radio Controllers
+ */
+struct uwb_dev *uwb_dev_get_by_devaddr(struct uwb_rc *rc,
+				       const struct uwb_dev_addr *devaddr);
+struct uwb_dev *uwb_dev_get_by_rc(struct uwb_dev *, struct uwb_rc *);
+static inline void uwb_dev_get(struct uwb_dev *uwb_dev)
+{
+	get_device(&uwb_dev->dev);
+}
+static inline void uwb_dev_put(struct uwb_dev *uwb_dev)
+{
+	put_device(&uwb_dev->dev);
+}
+struct uwb_dev *uwb_dev_try_get(struct uwb_rc *rc, struct uwb_dev *uwb_dev);
+
+/**
+ * Callback function for 'uwb_{dev,rc}_foreach()'.
+ *
+ * @dev:  Linux device instance
+ *        'uwb_dev = container_of(dev, struct uwb_dev, dev)'
+ * @priv: Data passed by the caller to 'uwb_{dev,rc}_foreach()'.
+ *
+ * @returns: 0 to continue the iterations, any other val to stop
+ *           iterating and return the value to the caller of
+ *           _foreach().
+ */
+typedef int (*uwb_dev_for_each_f)(struct device *dev, void *priv);
+int uwb_dev_for_each(struct uwb_rc *rc, uwb_dev_for_each_f func, void *priv);
+
+struct uwb_rc *uwb_rc_alloc(void);
+struct uwb_rc *uwb_rc_get_by_dev(const struct uwb_dev_addr *);
+struct uwb_rc *uwb_rc_get_by_grandpa(const struct device *);
+void uwb_rc_put(struct uwb_rc *rc);
+
+typedef void (*uwb_rc_cmd_cb_f)(struct uwb_rc *rc, void *arg,
+                                struct uwb_rceb *reply, ssize_t reply_size);
+
+int uwb_rc_cmd_async(struct uwb_rc *rc, const char *cmd_name,
+		     struct uwb_rccb *cmd, size_t cmd_size,
+		     u8 expected_type, u16 expected_event,
+		     uwb_rc_cmd_cb_f cb, void *arg);
+ssize_t uwb_rc_cmd(struct uwb_rc *rc, const char *cmd_name,
+		   struct uwb_rccb *cmd, size_t cmd_size,
+		   struct uwb_rceb *reply, size_t reply_size);
+ssize_t uwb_rc_vcmd(struct uwb_rc *rc, const char *cmd_name,
+		    struct uwb_rccb *cmd, size_t cmd_size,
+		    u8 expected_type, u16 expected_event,
+		    struct uwb_rceb **preply);
+ssize_t uwb_rc_get_ie(struct uwb_rc *, struct uwb_rc_evt_get_ie **);
+int uwb_bg_joined(struct uwb_rc *rc);
+
+size_t __uwb_addr_print(char *, size_t, const unsigned char *, int);
+
+int uwb_rc_dev_addr_set(struct uwb_rc *, const struct uwb_dev_addr *);
+int uwb_rc_dev_addr_get(struct uwb_rc *, struct uwb_dev_addr *);
+int uwb_rc_mac_addr_set(struct uwb_rc *, const struct uwb_mac_addr *);
+int uwb_rc_mac_addr_get(struct uwb_rc *, struct uwb_mac_addr *);
+int __uwb_mac_addr_assigned_check(struct device *, void *);
+int __uwb_dev_addr_assigned_check(struct device *, void *);
+
+/* Print in @buf a pretty repr of @addr */
+static inline size_t uwb_dev_addr_print(char *buf, size_t buf_size,
+					const struct uwb_dev_addr *addr)
+{
+	return __uwb_addr_print(buf, buf_size, addr->data, 0);
+}
+
+/* Print in @buf a pretty repr of @addr */
+static inline size_t uwb_mac_addr_print(char *buf, size_t buf_size,
+					const struct uwb_mac_addr *addr)
+{
+	return __uwb_addr_print(buf, buf_size, addr->data, 1);
+}
+
+/* @returns 0 if device addresses @addr2 and @addr1 are equal */
+static inline int uwb_dev_addr_cmp(const struct uwb_dev_addr *addr1,
+				   const struct uwb_dev_addr *addr2)
+{
+	return memcmp(addr1, addr2, sizeof(*addr1));
+}
+
+/* @returns 0 if MAC addresses @addr2 and @addr1 are equal */
+static inline int uwb_mac_addr_cmp(const struct uwb_mac_addr *addr1,
+				   const struct uwb_mac_addr *addr2)
+{
+	return memcmp(addr1, addr2, sizeof(*addr1));
+}
+
+/* @returns !0 if a MAC @addr is a broadcast address */
+static inline int uwb_mac_addr_bcast(const struct uwb_mac_addr *addr)
+{
+	struct uwb_mac_addr bcast = {
+		.data = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff }
+	};
+	return !uwb_mac_addr_cmp(addr, &bcast);
+}
+
+/* @returns !0 if a MAC @addr is all zeroes*/
+static inline int uwb_mac_addr_unset(const struct uwb_mac_addr *addr)
+{
+	struct uwb_mac_addr unset = {
+		.data = { 0x00, 0x00, 0x00, 0x00, 0x00, 0x00 }
+	};
+	return !uwb_mac_addr_cmp(addr, &unset);
+}
+
+/* @returns !0 if the address is in use. */
+static inline unsigned __uwb_dev_addr_assigned(struct uwb_rc *rc,
+					       struct uwb_dev_addr *addr)
+{
+	return uwb_dev_for_each(rc, __uwb_dev_addr_assigned_check, addr);
+}
+
+/*
+ * UWB Radio Controller API
+ *
+ * This API is used (in addition to the general API) to implement UWB
+ * Radio Controllers.
+ */
+void uwb_rc_init(struct uwb_rc *);
+int uwb_rc_add(struct uwb_rc *, struct device *dev, void *rc_priv);
+void uwb_rc_rm(struct uwb_rc *);
+void uwb_rc_neh_grok(struct uwb_rc *, void *, size_t);
+void uwb_rc_neh_error(struct uwb_rc *, int);
+void uwb_rc_reset_all(struct uwb_rc *rc);
+
+/**
+ * uwb_rsv_is_owner - is the owner of this reservation the RC?
+ * @rsv: the reservation
+ */
+static inline bool uwb_rsv_is_owner(struct uwb_rsv *rsv)
+{
+	return rsv->owner == &rsv->rc->uwb_dev;
+}
+
+/**
+ * Events generated by UWB that can be passed to any listeners
+ *
+ * Higher layers can register callback functions with the radio
+ * controller using uwb_notifs_register(). The radio controller
+ * maintains a list of all registered handlers and will notify all
+ * nodes when an event occurs.
+ */
+enum uwb_notifs {
+	UWB_NOTIF_BG_JOIN = 0,	/* radio controller joined a beacon group */
+	UWB_NOTIF_BG_LEAVE = 1,	/* radio controller left a beacon group */
+	UWB_NOTIF_ONAIR,
+	UWB_NOTIF_OFFAIR,
+};
+
+/* Callback function registered with UWB */
+struct uwb_notifs_handler {
+	struct list_head list_node;
+	void (*cb)(void *, struct uwb_dev *, enum uwb_notifs);
+	void *data;
+};
+
+int uwb_notifs_register(struct uwb_rc *, struct uwb_notifs_handler *);
+int uwb_notifs_deregister(struct uwb_rc *, struct uwb_notifs_handler *);
+
+
+/**
+ * UWB radio controller Event Size Entry (for creating entry tables)
+ *
+ * WUSB and WHCI define events and notifications, and they might have
+ * fixed or variable size.
+ *
+ * Each event/notification has a size which is not necessarily known
+ * in advance based on the event code. As well, vendor specific
+ * events/notifications will have a size impossible to determine
+ * unless we know about the device's specific details.
+ *
+ * It was way too smart of the spec writers not to think that it would
+ * be impossible for a generic driver to skip over vendor specific
+ * events/notifications if there are no LENGTH fields in the HEADER of
+ * each message...the transaction size cannot be counted on as the
+ * spec does not forbid to pack more than one event in a single
+ * transaction.
+ *
+ * Thus, we guess sizes with tables (or for events, when you know the
+ * size ahead of time you can use uwb_rc_neh_extra_size*()). We
+ * register tables with the known events and their sizes, and then we
+ * traverse those tables. For those with variable length, we provide a
+ * way to lookup the size inside the event/notification's
+ * payload. This allows device-specific event size tables to be
+ * registered.
+ *
+ * @size:   Size of the payload
+ *
+ * @offset: if != 0, at offset @offset-1 starts a field with a length
+ *          that has to be added to @size. The format of the field is
+ *          given by @type.
+ *
+ * @type:   Type and length of the offset field. Most common is LE 16
+ *          bits (that's why that is zero); others are there mostly to
+ *          cover for bugs and weirdos.
+ */
+struct uwb_est_entry {
+	size_t size;
+	unsigned offset;
+	enum { UWB_EST_16 = 0, UWB_EST_8 = 1 } type;
+};
+
+int uwb_est_register(u8 type, u8 code_high, u16 vendor, u16 product,
+		     const struct uwb_est_entry *, size_t entries);
+int uwb_est_unregister(u8 type, u8 code_high, u16 vendor, u16 product,
+		       const struct uwb_est_entry *, size_t entries);
+ssize_t uwb_est_find_size(struct uwb_rc *rc, const struct uwb_rceb *rceb,
+			  size_t len);
+
+/* -- Misc */
+
+enum {
+	EDC_MAX_ERRORS = 10,
+	EDC_ERROR_TIMEFRAME = HZ,
+};
+
+/* error density counter */
+struct edc {
+	unsigned long timestart;
+	u16 errorcount;
+};
+
+static inline
+void edc_init(struct edc *edc)
+{
+	edc->timestart = jiffies;
+}
+
+/* Called when an error occured.
+ * This is way to determine if the number of acceptable errors per time
+ * period has been exceeded. It is not accurate as there are cases in which
+ * this scheme will not work, for example if there are periodic occurences
+ * of errors that straddle updates to the start time. This scheme is
+ * sufficient for our usage.
+ *
+ * @returns 1 if maximum acceptable errors per timeframe has been exceeded.
+ */
+static inline int edc_inc(struct edc *err_hist, u16 max_err, u16 timeframe)
+{
+	unsigned long now;
+
+	now = jiffies;
+	if (now - err_hist->timestart > timeframe) {
+		err_hist->errorcount = 1;
+		err_hist->timestart = now;
+	} else if (++err_hist->errorcount > max_err) {
+			err_hist->errorcount = 0;
+			err_hist->timestart = now;
+			return 1;
+	}
+	return 0;
+}
+
+
+/* Information Element handling */
+
+/* For representing the state of writing to a buffer when iterating */
+struct uwb_buf_ctx {
+	char *buf;
+	size_t bytes, size;
+};
+
+typedef int (*uwb_ie_f)(struct uwb_dev *, const struct uwb_ie_hdr *,
+			size_t, void *);
+struct uwb_ie_hdr *uwb_ie_next(void **ptr, size_t *len);
+ssize_t uwb_ie_for_each(struct uwb_dev *uwb_dev, uwb_ie_f fn, void *data,
+			const void *buf, size_t size);
+int uwb_ie_dump_hex(struct uwb_dev *, const struct uwb_ie_hdr *,
+		    size_t, void *);
+int uwb_rc_set_ie(struct uwb_rc *, struct uwb_rc_cmd_set_ie *);
+struct uwb_ie_hdr *uwb_ie_next(void **ptr, size_t *len);
+
+
+/*
+ * Transmission statistics
+ *
+ * UWB uses LQI and RSSI (one byte values) for reporting radio signal
+ * strength and line quality indication. We do quick and dirty
+ * averages of those. They are signed values, btw.
+ *
+ * For 8 bit quantities, we keep the min, the max, an accumulator
+ * (@sigma) and a # of samples. When @samples gets to 255, we compute
+ * the average (@sigma / @samples), place it in @sigma and reset
+ * @samples to 1 (so we use it as the first sample).
+ *
+ * Now, statistically speaking, probably I am kicking the kidneys of
+ * some books I have in my shelves collecting dust, but I just want to
+ * get an approx, not the Nobel.
+ *
+ * LOCKING: there is no locking per se, but we try to keep a lockless
+ * schema. Only _add_samples() modifies the values--as long as you
+ * have other locking on top that makes sure that no two calls of
+ * _add_sample() happen at the same time, then we are fine. Now, for
+ * resetting the values we just set @samples to 0 and that makes the
+ * next _add_sample() to start with defaults. Reading the values in
+ * _show() currently can race, so you need to make sure the calls are
+ * under the same lock that protects calls to _add_sample(). FIXME:
+ * currently unlocked (It is not ultraprecise but does the trick. Bite
+ * me).
+ */
+struct stats {
+	s8 min, max;
+	s16 sigma;
+	atomic_t samples;
+};
+
+static inline
+void stats_init(struct stats *stats)
+{
+	atomic_set(&stats->samples, 0);
+	wmb();
+}
+
+static inline
+void stats_add_sample(struct stats *stats, s8 sample)
+{
+	s8 min, max;
+	s16 sigma;
+	unsigned samples = atomic_read(&stats->samples);
+	if (samples == 0) {	/* it was zero before, so we initialize */
+		min = 127;
+		max = -128;
+		sigma = 0;
+	} else {
+		min = stats->min;
+		max = stats->max;
+		sigma = stats->sigma;
+	}
+
+	if (sample < min)	/* compute new values */
+		min = sample;
+	else if (sample > max)
+		max = sample;
+	sigma += sample;
+
+	stats->min = min;	/* commit */
+	stats->max = max;
+	stats->sigma = sigma;
+	if (atomic_add_return(1, &stats->samples) > 255) {
+		/* wrapped around! reset */
+		stats->sigma = sigma / 256;
+		atomic_set(&stats->samples, 1);
+	}
+}
+
+static inline ssize_t stats_show(struct stats *stats, char *buf)
+{
+	int min, max, avg;
+	int samples = atomic_read(&stats->samples);
+	if (samples == 0)
+		min = max = avg = 0;
+	else {
+		min = stats->min;
+		max = stats->max;
+		avg = stats->sigma / samples;
+	}
+	return scnprintf(buf, PAGE_SIZE, "%d %d %d\n", min, max, avg);
+}
+
+static inline ssize_t stats_store(struct stats *stats, const char *buf,
+				  size_t size)
+{
+	stats_init(stats);
+	return size;
+}
+
+#endif /* #ifndef __LINUX__UWB_H__ */
diff --git a/include/linux/uwb/debug-cmd.h b/include/linux/uwb/debug-cmd.h
new file mode 100644
index 000000000000..1141f41bab5c
--- /dev/null
+++ b/include/linux/uwb/debug-cmd.h
@@ -0,0 +1,57 @@
+/*
+ * Ultra Wide Band
+ * Debug interface commands
+ *
+ * Copyright (C) 2008 Cambridge Silicon Radio Ltd.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __LINUX__UWB__DEBUG_CMD_H__
+#define __LINUX__UWB__DEBUG_CMD_H__
+
+#include <linux/types.h>
+
+/*
+ * Debug interface commands
+ *
+ * UWB_DBG_CMD_RSV_ESTABLISH: Establish a new unicast reservation.
+ *
+ * UWB_DBG_CMD_RSV_TERMINATE: Terminate the Nth reservation.
+ */
+
+enum uwb_dbg_cmd_type {
+	UWB_DBG_CMD_RSV_ESTABLISH = 1,
+	UWB_DBG_CMD_RSV_TERMINATE = 2,
+};
+
+struct uwb_dbg_cmd_rsv_establish {
+	__u8  target[6];
+	__u8  type;
+	__u16 max_mas;
+	__u16 min_mas;
+	__u8  sparsity;
+};
+
+struct uwb_dbg_cmd_rsv_terminate {
+	int index;
+};
+
+struct uwb_dbg_cmd {
+	__u32 type;
+	union {
+		struct uwb_dbg_cmd_rsv_establish rsv_establish;
+		struct uwb_dbg_cmd_rsv_terminate rsv_terminate;
+	};
+};
+
+#endif /* #ifndef __LINUX__UWB__DEBUG_CMD_H__ */
diff --git a/include/linux/uwb/debug.h b/include/linux/uwb/debug.h
new file mode 100644
index 000000000000..a86a73fe303f
--- /dev/null
+++ b/include/linux/uwb/debug.h
@@ -0,0 +1,82 @@
+/*
+ * Ultra Wide Band
+ * Debug Support
+ *
+ * Copyright (C) 2005-2006 Intel Corporation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
+ *
+ * FIXME: doc
+ * Invoke like:
+ *
+ * #define D_LOCAL 4
+ * #include <linux/uwb/debug.h>
+ *
+ * At the end of your include files.
+ */
+#include <linux/types.h>
+
+struct device;
+extern void dump_bytes(struct device *dev, const void *_buf, size_t rsize);
+
+/* Master debug switch; !0 enables, 0 disables */
+#define D_MASTER (!0)
+
+/* Local (per-file) debug switch; #define before #including */
+#ifndef D_LOCAL
+#define D_LOCAL 0
+#endif
+
+#undef __d_printf
+#undef d_fnstart
+#undef d_fnend
+#undef d_printf
+#undef d_dump
+
+#define __d_printf(l, _tag, _dev, f, a...)				\
+do {									\
+	struct device *__dev = (_dev);					\
+	if (D_MASTER && D_LOCAL >= (l)) {				\
+		char __head[64] = "";					\
+		if (_dev != NULL) {					\
+			if ((unsigned long)__dev < 4096)		\
+				printk(KERN_ERR "E: Corrupt dev %p\n",	\
+					__dev);				\
+			else						\
+				snprintf(__head, sizeof(__head),	\
+					 "%s %s: ",			\
+					 dev_driver_string(__dev),	\
+					 __dev->bus_id);		\
+		}							\
+		printk(KERN_ERR "%s%s" _tag ": " f, __head,		\
+			__func__, ## a);				\
+	}								\
+} while (0 && _dev)
+
+#define d_fnstart(l, _dev, f, a...)	\
+	__d_printf(l, " FNSTART", _dev, f, ## a)
+#define d_fnend(l, _dev, f, a...)	\
+	__d_printf(l, " FNEND", _dev, f, ## a)
+#define d_printf(l, _dev, f, a...)	\
+	__d_printf(l, "", _dev, f, ## a)
+#define d_dump(l, _dev, ptr, size)		\
+do {						\
+	struct device *__dev = _dev;		\
+	if (D_MASTER && D_LOCAL >= (l))		\
+		dump_bytes(__dev, ptr, size);	\
+} while (0 && _dev)
+#define d_test(l) (D_MASTER && D_LOCAL >= (l))
diff --git a/include/linux/uwb/spec.h b/include/linux/uwb/spec.h
new file mode 100644
index 000000000000..198c15f8e251
--- /dev/null
+++ b/include/linux/uwb/spec.h
@@ -0,0 +1,727 @@
+/*
+ * Ultra Wide Band
+ * UWB Standard definitions
+ *
+ * Copyright (C) 2005-2006 Intel Corporation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
+ *
+ * All these definitions are based on the ECMA-368 standard.
+ *
+ * Note all definitions are Little Endian in the wire, and we will
+ * convert them to host order before operating on the bitfields (that
+ * yes, we use extensively).
+ */
+
+#ifndef __LINUX__UWB_SPEC_H__
+#define __LINUX__UWB_SPEC_H__
+
+#include <linux/types.h>
+#include <linux/bitmap.h>
+
+#define i1480_FW 0x00000303
+/* #define i1480_FW 0x00000302 */
+
+/**
+ * Number of Medium Access Slots in a superframe.
+ *
+ * UWB divides time in SuperFrames, each one divided in 256 pieces, or
+ * Medium Access Slots. See MBOA MAC[5.4.5] for details. The MAS is the
+ * basic bandwidth allocation unit in UWB.
+ */
+enum { UWB_NUM_MAS = 256 };
+
+/**
+ * Number of Zones in superframe.
+ *
+ * UWB divides the superframe into zones with numbering starting from BPST.
+ * See MBOA MAC[16.8.6]
+ */
+enum { UWB_NUM_ZONES = 16 };
+
+/*
+ * Number of MAS in a zone.
+ */
+#define UWB_MAS_PER_ZONE (UWB_NUM_MAS / UWB_NUM_ZONES)
+
+/*
+ * Number of streams per DRP reservation between a pair of devices.
+ *
+ * [ECMA-368] section 16.8.6.
+ */
+enum { UWB_NUM_STREAMS = 8 };
+
+/*
+ * mMasLength
+ *
+ * The length of a MAS in microseconds.
+ *
+ * [ECMA-368] section 17.16.
+ */
+enum { UWB_MAS_LENGTH_US = 256 };
+
+/*
+ * mBeaconSlotLength
+ *
+ * The length of the beacon slot in microseconds.
+ *
+ * [ECMA-368] section 17.16
+ */
+enum { UWB_BEACON_SLOT_LENGTH_US = 85 };
+
+/*
+ * mMaxLostBeacons
+ *
+ * The number beacons missing in consecutive superframes before a
+ * device can be considered as unreachable.
+ *
+ * [ECMA-368] section 17.16
+ */
+enum { UWB_MAX_LOST_BEACONS = 3 };
+
+/*
+ * Length of a superframe in microseconds.
+ */
+#define UWB_SUPERFRAME_LENGTH_US (UWB_MAS_LENGTH_US * UWB_NUM_MAS)
+
+/**
+ * UWB MAC address
+ *
+ * It is *imperative* that this struct is exactly 6 packed bytes (as
+ * it is also used to define headers sent down and up the wire/radio).
+ */
+struct uwb_mac_addr {
+	u8 data[6];
+} __attribute__((packed));
+
+
+/**
+ * UWB device address
+ *
+ * It is *imperative* that this struct is exactly 6 packed bytes (as
+ * it is also used to define headers sent down and up the wire/radio).
+ */
+struct uwb_dev_addr {
+	u8 data[2];
+} __attribute__((packed));
+
+
+/**
+ * Types of UWB addresses
+ *
+ * Order matters (by size).
+ */
+enum uwb_addr_type {
+	UWB_ADDR_DEV = 0,
+	UWB_ADDR_MAC = 1,
+};
+
+
+/** Size of a char buffer for printing a MAC/device address */
+enum { UWB_ADDR_STRSIZE = 32 };
+
+
+/** UWB WiMedia protocol IDs. */
+enum uwb_prid {
+	UWB_PRID_WLP_RESERVED   = 0x0000,
+	UWB_PRID_WLP		= 0x0001,
+	UWB_PRID_WUSB_BOT	= 0x0010,
+	UWB_PRID_WUSB		= 0x0010,
+	UWB_PRID_WUSB_TOP	= 0x001F,
+};
+
+
+/** PHY Rate (MBOA MAC[7.8.12, Table 61]) */
+enum uwb_phy_rate {
+	UWB_PHY_RATE_53 = 0,
+	UWB_PHY_RATE_80,
+	UWB_PHY_RATE_106,
+	UWB_PHY_RATE_160,
+	UWB_PHY_RATE_200,
+	UWB_PHY_RATE_320,
+	UWB_PHY_RATE_400,
+	UWB_PHY_RATE_480,
+	UWB_PHY_RATE_INVALID
+};
+
+
+/**
+ * Different ways to scan (MBOA MAC[6.2.2, Table 8], WUSB[Table 8-78])
+ */
+enum uwb_scan_type {
+	UWB_SCAN_ONLY = 0,
+	UWB_SCAN_OUTSIDE_BP,
+	UWB_SCAN_WHILE_INACTIVE,
+	UWB_SCAN_DISABLED,
+	UWB_SCAN_ONLY_STARTTIME,
+	UWB_SCAN_TOP
+};
+
+
+/** ACK Policy types (MBOA MAC[7.2.1.3]) */
+enum uwb_ack_pol {
+	UWB_ACK_NO = 0,
+	UWB_ACK_INM = 1,
+	UWB_ACK_B = 2,
+	UWB_ACK_B_REQ = 3,
+};
+
+
+/** DRP reservation types ([ECMA-368 table 106) */
+enum uwb_drp_type {
+	UWB_DRP_TYPE_ALIEN_BP = 0,
+	UWB_DRP_TYPE_HARD,
+	UWB_DRP_TYPE_SOFT,
+	UWB_DRP_TYPE_PRIVATE,
+	UWB_DRP_TYPE_PCA,
+};
+
+
+/** DRP Reason Codes ([ECMA-368] table 107) */
+enum uwb_drp_reason {
+	UWB_DRP_REASON_ACCEPTED = 0,
+	UWB_DRP_REASON_CONFLICT,
+	UWB_DRP_REASON_PENDING,
+	UWB_DRP_REASON_DENIED,
+	UWB_DRP_REASON_MODIFIED,
+};
+
+/**
+ *  DRP Notification Reason Codes (WHCI 0.95 [3.1.4.9])
+ */
+enum uwb_drp_notif_reason {
+	UWB_DRP_NOTIF_DRP_IE_RCVD = 0,
+	UWB_DRP_NOTIF_CONFLICT,
+	UWB_DRP_NOTIF_TERMINATE,
+};
+
+
+/** Allocation of MAS slots in a DRP request MBOA MAC[7.8.7] */
+struct uwb_drp_alloc {
+	__le16 zone_bm;
+	__le16 mas_bm;
+} __attribute__((packed));
+
+
+/** General MAC Header format (ECMA-368[16.2]) */
+struct uwb_mac_frame_hdr {
+	__le16 Frame_Control;
+	struct uwb_dev_addr DestAddr;
+	struct uwb_dev_addr SrcAddr;
+	__le16 Sequence_Control;
+	__le16 Access_Information;
+} __attribute__((packed));
+
+
+/**
+ * uwb_beacon_frame - a beacon frame including MAC headers
+ *
+ * [ECMA] section 16.3.
+ */
+struct uwb_beacon_frame {
+	struct uwb_mac_frame_hdr hdr;
+	struct uwb_mac_addr Device_Identifier;	/* may be a NULL EUI-48 */
+	u8 Beacon_Slot_Number;
+	u8 Device_Control;
+	u8 IEData[];
+} __attribute__((packed));
+
+
+/** Information Element codes (MBOA MAC[T54]) */
+enum uwb_ie {
+	UWB_PCA_AVAILABILITY = 2,
+	UWB_IE_DRP_AVAILABILITY = 8,
+	UWB_IE_DRP = 9,
+	UWB_BP_SWITCH_IE = 11,
+	UWB_MAC_CAPABILITIES_IE = 12,
+	UWB_PHY_CAPABILITIES_IE = 13,
+	UWB_APP_SPEC_PROBE_IE = 15,
+	UWB_IDENTIFICATION_IE = 19,
+	UWB_MASTER_KEY_ID_IE = 20,
+	UWB_IE_WLP = 250, /* WiMedia Logical Link Control Protocol WLP 0.99 */
+	UWB_APP_SPEC_IE = 255,
+};
+
+
+/**
+ * Header common to all Information Elements (IEs)
+ */
+struct uwb_ie_hdr {
+	u8 element_id;	/* enum uwb_ie */
+	u8 length;
+} __attribute__((packed));
+
+
+/** Dynamic Reservation Protocol IE (MBOA MAC[7.8.6]) */
+struct uwb_ie_drp {
+	struct uwb_ie_hdr	hdr;
+	__le16                  drp_control;
+	struct uwb_dev_addr	dev_addr;
+	struct uwb_drp_alloc	allocs[];
+} __attribute__((packed));
+
+static inline int uwb_ie_drp_type(struct uwb_ie_drp *ie)
+{
+	return (le16_to_cpu(ie->drp_control) >> 0) & 0x7;
+}
+
+static inline int uwb_ie_drp_stream_index(struct uwb_ie_drp *ie)
+{
+	return (le16_to_cpu(ie->drp_control) >> 3) & 0x7;
+}
+
+static inline int uwb_ie_drp_reason_code(struct uwb_ie_drp *ie)
+{
+	return (le16_to_cpu(ie->drp_control) >> 6) & 0x7;
+}
+
+static inline int uwb_ie_drp_status(struct uwb_ie_drp *ie)
+{
+	return (le16_to_cpu(ie->drp_control) >> 9) & 0x1;
+}
+
+static inline int uwb_ie_drp_owner(struct uwb_ie_drp *ie)
+{
+	return (le16_to_cpu(ie->drp_control) >> 10) & 0x1;
+}
+
+static inline int uwb_ie_drp_tiebreaker(struct uwb_ie_drp *ie)
+{
+	return (le16_to_cpu(ie->drp_control) >> 11) & 0x1;
+}
+
+static inline int uwb_ie_drp_unsafe(struct uwb_ie_drp *ie)
+{
+	return (le16_to_cpu(ie->drp_control) >> 12) & 0x1;
+}
+
+static inline void uwb_ie_drp_set_type(struct uwb_ie_drp *ie, enum uwb_drp_type type)
+{
+	u16 drp_control = le16_to_cpu(ie->drp_control);
+	drp_control = (drp_control & ~(0x7 << 0)) | (type << 0);
+	ie->drp_control = cpu_to_le16(drp_control);
+}
+
+static inline void uwb_ie_drp_set_stream_index(struct uwb_ie_drp *ie, int stream_index)
+{
+	u16 drp_control = le16_to_cpu(ie->drp_control);
+	drp_control = (drp_control & ~(0x7 << 3)) | (stream_index << 3);
+	ie->drp_control = cpu_to_le16(drp_control);
+}
+
+static inline void uwb_ie_drp_set_reason_code(struct uwb_ie_drp *ie,
+				       enum uwb_drp_reason reason_code)
+{
+	u16 drp_control = le16_to_cpu(ie->drp_control);
+	drp_control = (ie->drp_control & ~(0x7 << 6)) | (reason_code << 6);
+	ie->drp_control = cpu_to_le16(drp_control);
+}
+
+static inline void uwb_ie_drp_set_status(struct uwb_ie_drp *ie, int status)
+{
+	u16 drp_control = le16_to_cpu(ie->drp_control);
+	drp_control = (drp_control & ~(0x1 << 9)) | (status << 9);
+	ie->drp_control = cpu_to_le16(drp_control);
+}
+
+static inline void uwb_ie_drp_set_owner(struct uwb_ie_drp *ie, int owner)
+{
+	u16 drp_control = le16_to_cpu(ie->drp_control);
+	drp_control = (drp_control & ~(0x1 << 10)) | (owner << 10);
+	ie->drp_control = cpu_to_le16(drp_control);
+}
+
+static inline void uwb_ie_drp_set_tiebreaker(struct uwb_ie_drp *ie, int tiebreaker)
+{
+	u16 drp_control = le16_to_cpu(ie->drp_control);
+	drp_control = (drp_control & ~(0x1 << 11)) | (tiebreaker << 11);
+	ie->drp_control = cpu_to_le16(drp_control);
+}
+
+static inline void uwb_ie_drp_set_unsafe(struct uwb_ie_drp *ie, int unsafe)
+{
+	u16 drp_control = le16_to_cpu(ie->drp_control);
+	drp_control = (drp_control & ~(0x1 << 12)) | (unsafe << 12);
+	ie->drp_control = cpu_to_le16(drp_control);
+}
+
+/** Dynamic Reservation Protocol IE (MBOA MAC[7.8.7]) */
+struct uwb_ie_drp_avail {
+	struct uwb_ie_hdr	hdr;
+	DECLARE_BITMAP(bmp, UWB_NUM_MAS);
+} __attribute__((packed));
+
+/**
+ * The Vendor ID is set to an OUI that indicates the vendor of the device.
+ * ECMA-368 [16.8.10]
+ */
+struct uwb_vendor_id {
+	u8 data[3];
+} __attribute__((packed));
+
+/**
+ * The device type ID
+ * FIXME: clarify what this means
+ * ECMA-368 [16.8.10]
+ */
+struct uwb_device_type_id {
+	u8 data[3];
+} __attribute__((packed));
+
+
+/**
+ * UWB device information types
+ * ECMA-368 [16.8.10]
+ */
+enum uwb_dev_info_type {
+	UWB_DEV_INFO_VENDOR_ID = 0,
+	UWB_DEV_INFO_VENDOR_TYPE,
+	UWB_DEV_INFO_NAME,
+};
+
+/**
+ * UWB device information found in Identification IE
+ * ECMA-368 [16.8.10]
+ */
+struct uwb_dev_info {
+	u8 type;	/* enum uwb_dev_info_type */
+	u8 length;
+	u8 data[];
+} __attribute__((packed));
+
+/**
+ * UWB Identification IE
+ * ECMA-368 [16.8.10]
+ */
+struct uwb_identification_ie {
+	struct uwb_ie_hdr hdr;
+	struct uwb_dev_info info[];
+} __attribute__((packed));
+
+/*
+ * UWB Radio Controller
+ *
+ * These definitions are common to the Radio Control layers as
+ * exported by the WUSB1.0 HWA and WHCI interfaces.
+ */
+
+/** Radio Control Command Block (WUSB1.0[Table 8-65] and WHCI 0.95) */
+struct uwb_rccb {
+	u8 bCommandType;		/* enum hwa_cet */
+	__le16 wCommand;		/* Command code */
+	u8 bCommandContext;		/* Context ID */
+} __attribute__((packed));
+
+
+/** Radio Control Event Block (WUSB[table 8-66], WHCI 0.95) */
+struct uwb_rceb {
+	u8 bEventType;			/* enum hwa_cet */
+	__le16 wEvent;			/* Event code */
+	u8 bEventContext;		/* Context ID */
+} __attribute__((packed));
+
+
+enum {
+	UWB_RC_CET_GENERAL = 0,		/* General Command/Event type */
+	UWB_RC_CET_EX_TYPE_1 = 1,	/* Extended Type 1 Command/Event type */
+};
+
+/* Commands to the radio controller */
+enum uwb_rc_cmd {
+	UWB_RC_CMD_CHANNEL_CHANGE = 16,
+	UWB_RC_CMD_DEV_ADDR_MGMT = 17,	/* Device Address Management */
+	UWB_RC_CMD_GET_IE = 18,		/* GET Information Elements */
+	UWB_RC_CMD_RESET = 19,
+	UWB_RC_CMD_SCAN = 20,		/* Scan management  */
+	UWB_RC_CMD_SET_BEACON_FILTER = 21,
+	UWB_RC_CMD_SET_DRP_IE = 22,	/* Dynamic Reservation Protocol IEs */
+	UWB_RC_CMD_SET_IE = 23,		/* Information Element management */
+	UWB_RC_CMD_SET_NOTIFICATION_FILTER = 24,
+	UWB_RC_CMD_SET_TX_POWER = 25,
+	UWB_RC_CMD_SLEEP = 26,
+	UWB_RC_CMD_START_BEACON = 27,
+	UWB_RC_CMD_STOP_BEACON = 28,
+	UWB_RC_CMD_BP_MERGE = 29,
+	UWB_RC_CMD_SEND_COMMAND_FRAME = 30,
+	UWB_RC_CMD_SET_ASIE_NOTIF = 31,
+};
+
+/* Notifications from the radio controller */
+enum uwb_rc_evt {
+	UWB_RC_EVT_IE_RCV = 0,
+	UWB_RC_EVT_BEACON = 1,
+	UWB_RC_EVT_BEACON_SIZE = 2,
+	UWB_RC_EVT_BPOIE_CHANGE = 3,
+	UWB_RC_EVT_BP_SLOT_CHANGE = 4,
+	UWB_RC_EVT_BP_SWITCH_IE_RCV = 5,
+	UWB_RC_EVT_DEV_ADDR_CONFLICT = 6,
+	UWB_RC_EVT_DRP_AVAIL = 7,
+	UWB_RC_EVT_DRP = 8,
+	UWB_RC_EVT_BP_SWITCH_STATUS = 9,
+	UWB_RC_EVT_CMD_FRAME_RCV = 10,
+	UWB_RC_EVT_CHANNEL_CHANGE_IE_RCV = 11,
+	/* Events (command responses) use the same code as the command */
+	UWB_RC_EVT_UNKNOWN_CMD_RCV = 65535,
+};
+
+enum uwb_rc_extended_type_1_cmd {
+	UWB_RC_SET_DAA_ENERGY_MASK = 32,
+	UWB_RC_SET_NOTIFICATION_FILTER_EX = 33,
+};
+
+enum uwb_rc_extended_type_1_evt {
+	UWB_RC_DAA_ENERGY_DETECTED = 0,
+};
+
+/* Radio Control Result Code. [WHCI] table 3-3. */
+enum {
+	UWB_RC_RES_SUCCESS = 0,
+	UWB_RC_RES_FAIL,
+	UWB_RC_RES_FAIL_HARDWARE,
+	UWB_RC_RES_FAIL_NO_SLOTS,
+	UWB_RC_RES_FAIL_BEACON_TOO_LARGE,
+	UWB_RC_RES_FAIL_INVALID_PARAMETER,
+	UWB_RC_RES_FAIL_UNSUPPORTED_PWR_LEVEL,
+	UWB_RC_RES_FAIL_INVALID_IE_DATA,
+	UWB_RC_RES_FAIL_BEACON_SIZE_EXCEEDED,
+	UWB_RC_RES_FAIL_CANCELLED,
+	UWB_RC_RES_FAIL_INVALID_STATE,
+	UWB_RC_RES_FAIL_INVALID_SIZE,
+	UWB_RC_RES_FAIL_ACK_NOT_RECEIVED,
+	UWB_RC_RES_FAIL_NO_MORE_ASIE_NOTIF,
+	UWB_RC_RES_FAIL_TIME_OUT = 255,
+};
+
+/* Confirm event. [WHCI] section 3.1.3.1 etc. */
+struct uwb_rc_evt_confirm {
+	struct uwb_rceb rceb;
+	u8 bResultCode;
+} __attribute__((packed));
+
+/* Device Address Management event. [WHCI] section 3.1.3.2. */
+struct uwb_rc_evt_dev_addr_mgmt {
+	struct uwb_rceb rceb;
+	u8 baAddr[6];
+	u8 bResultCode;
+} __attribute__((packed));
+
+
+/* Get IE Event. [WHCI] section 3.1.3.3. */
+struct uwb_rc_evt_get_ie {
+	struct uwb_rceb rceb;
+	__le16 wIELength;
+	u8 IEData[];
+} __attribute__((packed));
+
+/* Set DRP IE Event. [WHCI] section 3.1.3.7. */
+struct uwb_rc_evt_set_drp_ie {
+	struct uwb_rceb rceb;
+	__le16 wRemainingSpace;
+	u8 bResultCode;
+} __attribute__((packed));
+
+/* Set IE Event. [WHCI] section 3.1.3.8. */
+struct uwb_rc_evt_set_ie {
+	struct uwb_rceb rceb;
+	__le16 RemainingSpace;
+	u8 bResultCode;
+} __attribute__((packed));
+
+/* Scan command. [WHCI] 3.1.3.5. */
+struct uwb_rc_cmd_scan {
+	struct uwb_rccb rccb;
+	u8 bChannelNumber;
+	u8 bScanState;
+	__le16 wStartTime;
+} __attribute__((packed));
+
+/* Set DRP IE command. [WHCI] section 3.1.3.7. */
+struct uwb_rc_cmd_set_drp_ie {
+	struct uwb_rccb rccb;
+	__le16 wIELength;
+	struct uwb_ie_drp IEData[];
+} __attribute__((packed));
+
+/* Set IE command. [WHCI] section 3.1.3.8. */
+struct uwb_rc_cmd_set_ie {
+	struct uwb_rccb rccb;
+	__le16 wIELength;
+	u8 IEData[];
+} __attribute__((packed));
+
+/* Set DAA Energy Mask event. [WHCI 0.96] section 3.1.3.17. */
+struct uwb_rc_evt_set_daa_energy_mask {
+	struct uwb_rceb rceb;
+	__le16 wLength;
+	u8 result;
+} __attribute__((packed));
+
+/* Set Notification Filter Extended event. [WHCI 0.96] section 3.1.3.18. */
+struct uwb_rc_evt_set_notification_filter_ex {
+	struct uwb_rceb rceb;
+	__le16 wLength;
+	u8 result;
+} __attribute__((packed));
+
+/* IE Received notification. [WHCI] section 3.1.4.1. */
+struct uwb_rc_evt_ie_rcv {
+	struct uwb_rceb rceb;
+	struct uwb_dev_addr SrcAddr;
+	__le16 wIELength;
+	u8 IEData[];
+} __attribute__((packed));
+
+/* Type of the received beacon. [WHCI] section 3.1.4.2. */
+enum uwb_rc_beacon_type {
+	UWB_RC_BEACON_TYPE_SCAN = 0,
+	UWB_RC_BEACON_TYPE_NEIGHBOR,
+	UWB_RC_BEACON_TYPE_OL_ALIEN,
+	UWB_RC_BEACON_TYPE_NOL_ALIEN,
+};
+
+/* Beacon received notification. [WHCI] 3.1.4.2. */
+struct uwb_rc_evt_beacon {
+	struct uwb_rceb rceb;
+	u8	bChannelNumber;
+	u8	bBeaconType;
+	__le16	wBPSTOffset;
+	u8	bLQI;
+	u8	bRSSI;
+	__le16	wBeaconInfoLength;
+	u8	BeaconInfo[];
+} __attribute__((packed));
+
+
+/* Beacon Size Change notification. [WHCI] section 3.1.4.3 */
+struct uwb_rc_evt_beacon_size {
+	struct uwb_rceb rceb;
+	__le16 wNewBeaconSize;
+} __attribute__((packed));
+
+
+/* BPOIE Change notification. [WHCI] section 3.1.4.4. */
+struct uwb_rc_evt_bpoie_change {
+	struct uwb_rceb rceb;
+	__le16 wBPOIELength;
+	u8 BPOIE[];
+} __attribute__((packed));
+
+
+/* Beacon Slot Change notification. [WHCI] section 3.1.4.5. */
+struct uwb_rc_evt_bp_slot_change {
+	struct uwb_rceb rceb;
+	u8 slot_info;
+} __attribute__((packed));
+
+static inline int uwb_rc_evt_bp_slot_change_slot_num(
+	const struct uwb_rc_evt_bp_slot_change *evt)
+{
+	return evt->slot_info & 0x7f;
+}
+
+static inline int uwb_rc_evt_bp_slot_change_no_slot(
+	const struct uwb_rc_evt_bp_slot_change *evt)
+{
+	return (evt->slot_info & 0x80) >> 7;
+}
+
+/* BP Switch IE Received notification. [WHCI] section 3.1.4.6. */
+struct uwb_rc_evt_bp_switch_ie_rcv {
+	struct uwb_rceb rceb;
+	struct uwb_dev_addr wSrcAddr;
+	__le16 wIELength;
+	u8 IEData[];
+} __attribute__((packed));
+
+/* DevAddr Conflict notification. [WHCI] section 3.1.4.7. */
+struct uwb_rc_evt_dev_addr_conflict {
+	struct uwb_rceb rceb;
+} __attribute__((packed));
+
+/* DRP notification. [WHCI] section 3.1.4.9. */
+struct uwb_rc_evt_drp {
+	struct uwb_rceb           rceb;
+	struct uwb_dev_addr       src_addr;
+	u8                        reason;
+	u8                        beacon_slot_number;
+	__le16                    ie_length;
+	u8                        ie_data[];
+} __attribute__((packed));
+
+static inline enum uwb_drp_notif_reason uwb_rc_evt_drp_reason(struct uwb_rc_evt_drp *evt)
+{
+	return evt->reason & 0x0f;
+}
+
+
+/* DRP Availability Change notification. [WHCI] section 3.1.4.8. */
+struct uwb_rc_evt_drp_avail {
+	struct uwb_rceb rceb;
+	DECLARE_BITMAP(bmp, UWB_NUM_MAS);
+} __attribute__((packed));
+
+/* BP switch status notification. [WHCI] section 3.1.4.10. */
+struct uwb_rc_evt_bp_switch_status {
+	struct uwb_rceb rceb;
+	u8 status;
+	u8 slot_offset;
+	__le16 bpst_offset;
+	u8 move_countdown;
+} __attribute__((packed));
+
+/* Command Frame Received notification. [WHCI] section 3.1.4.11. */
+struct uwb_rc_evt_cmd_frame_rcv {
+	struct uwb_rceb rceb;
+	__le16 receive_time;
+	struct uwb_dev_addr wSrcAddr;
+	struct uwb_dev_addr wDstAddr;
+	__le16 control;
+	__le16 reserved;
+	__le16 dataLength;
+	u8 data[];
+} __attribute__((packed));
+
+/* Channel Change IE Received notification. [WHCI] section 3.1.4.12. */
+struct uwb_rc_evt_channel_change_ie_rcv {
+	struct uwb_rceb rceb;
+	struct uwb_dev_addr wSrcAddr;
+	__le16 wIELength;
+	u8 IEData[];
+} __attribute__((packed));
+
+/* DAA Energy Detected notification. [WHCI 0.96] section 3.1.4.14. */
+struct uwb_rc_evt_daa_energy_detected {
+	struct uwb_rceb rceb;
+	__le16 wLength;
+	u8 bandID;
+	u8 reserved;
+	u8 toneBmp[16];
+} __attribute__((packed));
+
+
+/**
+ * Radio Control Interface Class Descriptor
+ *
+ *  WUSB 1.0 [8.6.1.2]
+ */
+struct uwb_rc_control_intf_class_desc {
+	u8 bLength;
+	u8 bDescriptorType;
+	__le16 bcdRCIVersion;
+} __attribute__((packed));
+
+#endif /* #ifndef __LINUX__UWB_SPEC_H__ */
diff --git a/include/linux/wlp.h b/include/linux/wlp.h
new file mode 100644
index 000000000000..033545e145c7
--- /dev/null
+++ b/include/linux/wlp.h
@@ -0,0 +1,735 @@
+/*
+ * WiMedia Logical Link Control Protocol (WLP)
+ *
+ * Copyright (C) 2005-2006 Intel Corporation
+ * Reinette Chatre <reinette.chatre@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
+ *
+ * FIXME: docs
+ *
+ * - Does not (yet) include support for WLP control frames
+ *   WLP Draft 0.99 [6.5].
+ *
+ *   A visual representation of the data structures.
+ *
+ *                              wssidB      wssidB
+ *                               ^           ^
+ *                               |           |
+ *                              wssidA      wssidA
+ *   wlp interface {             ^           ^
+ *       ...                     |           |
+ *       ...               ...  wssid      wssid ...
+ *       wlp --- ...             |           |
+ *   };          neighbors --> neighbA --> neighbB
+ *               ...
+ *               wss
+ *               ...
+ *               eda cache  --> neighborA --> neighborB --> neighborC ...
+ */
+
+#ifndef __LINUX__WLP_H_
+#define __LINUX__WLP_H_
+
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/list.h>
+#include <linux/uwb.h>
+
+/**
+ * WLP Protocol ID
+ * WLP Draft 0.99 [6.2]
+ *
+ * The MUX header for all WLP frames
+ */
+#define WLP_PROTOCOL_ID 0x0100
+
+/**
+ * WLP Version
+ * WLP version placed in the association frames (WLP 0.99 [6.6])
+ */
+#define WLP_VERSION 0x10
+
+/**
+ * Bytes needed to print UUID as string
+ */
+#define WLP_WSS_UUID_STRSIZE 48
+
+/**
+ * Bytes needed to print nonce as string
+ */
+#define WLP_WSS_NONCE_STRSIZE 48
+
+
+/**
+ * Size used for WLP name size
+ *
+ * The WSS name is set to 65 bytes, 1 byte larger than the maximum
+ * allowed by the WLP spec. This is to have a null terminated string
+ * for display to the user. A maximum of 64 bytes will still be used
+ * when placing the WSS name field in association frames.
+ */
+#define WLP_WSS_NAME_SIZE 65
+
+/**
+ * Number of bytes added by WLP to data frame
+ *
+ * A data frame transmitted from a host will be placed in a Standard or
+ * Abbreviated WLP frame. These have an extra 4 bytes of header (struct
+ * wlp_frame_std_abbrv_hdr).
+ * When the stack sends this data frame for transmission it needs to ensure
+ * there is enough headroom for this header.
+ */
+#define WLP_DATA_HLEN 4
+
+/**
+ * State of device regarding WLP Service Set
+ *
+ * WLP_WSS_STATE_NONE: the host does not participate in any WSS
+ * WLP_WSS_STATE_PART_ENROLLED: used as part of the enrollment sequence
+ *                            ("Partial Enroll"). This state is used to
+ *                            indicate the first part of enrollment that is
+ *                            unsecure. If the WSS is unsecure then the
+ *                            state will promptly go to WLP_WSS_STATE_ENROLLED,
+ *                            if the WSS is not secure then the enrollment
+ *                            procedure is a few more steps before we are
+ *                            enrolled.
+ * WLP_WSS_STATE_ENROLLED: the host is enrolled in a WSS
+ * WLP_WSS_STATE_ACTIVE: WSS is activated
+ * WLP_WSS_STATE_CONNECTED: host is connected to neighbor in WSS
+ *
+ */
+enum wlp_wss_state {
+	WLP_WSS_STATE_NONE = 0,
+	WLP_WSS_STATE_PART_ENROLLED,
+	WLP_WSS_STATE_ENROLLED,
+	WLP_WSS_STATE_ACTIVE,
+	WLP_WSS_STATE_CONNECTED,
+};
+
+/**
+ * WSS Secure status
+ * WLP 0.99 Table 6
+ *
+ * Set to one if the WSS is secure, zero if it is not secure
+ */
+enum wlp_wss_sec_status {
+	WLP_WSS_UNSECURE = 0,
+	WLP_WSS_SECURE,
+};
+
+/**
+ * WLP frame type
+ * WLP Draft 0.99 [6.2 Table 1]
+ */
+enum wlp_frame_type {
+	WLP_FRAME_STANDARD = 0,
+	WLP_FRAME_ABBREVIATED,
+	WLP_FRAME_CONTROL,
+	WLP_FRAME_ASSOCIATION,
+};
+
+/**
+ * WLP Association Message Type
+ * WLP Draft 0.99 [6.6.1.2 Table 8]
+ */
+enum wlp_assoc_type {
+	WLP_ASSOC_D1 = 2,
+	WLP_ASSOC_D2 = 3,
+	WLP_ASSOC_M1 = 4,
+	WLP_ASSOC_M2 = 5,
+	WLP_ASSOC_M3 = 7,
+	WLP_ASSOC_M4 = 8,
+	WLP_ASSOC_M5 = 9,
+	WLP_ASSOC_M6 = 10,
+	WLP_ASSOC_M7 = 11,
+	WLP_ASSOC_M8 = 12,
+	WLP_ASSOC_F0 = 14,
+	WLP_ASSOC_E1 = 32,
+	WLP_ASSOC_E2 = 33,
+	WLP_ASSOC_C1 = 34,
+	WLP_ASSOC_C2 = 35,
+	WLP_ASSOC_C3 = 36,
+	WLP_ASSOC_C4 = 37,
+};
+
+/**
+ * WLP Attribute Type
+ * WLP Draft 0.99 [6.6.1 Table 6]
+ */
+enum wlp_attr_type {
+	WLP_ATTR_AUTH		= 0x1005, /* Authenticator */
+	WLP_ATTR_DEV_NAME 	= 0x1011, /* Device Name */
+	WLP_ATTR_DEV_PWD_ID 	= 0x1012, /* Device Password ID */
+	WLP_ATTR_E_HASH1	= 0x1014, /* E-Hash1 */
+	WLP_ATTR_E_HASH2	= 0x1015, /* E-Hash2 */
+	WLP_ATTR_E_SNONCE1	= 0x1016, /* E-SNonce1 */
+	WLP_ATTR_E_SNONCE2	= 0x1017, /* E-SNonce2 */
+	WLP_ATTR_ENCR_SET	= 0x1018, /* Encrypted Settings */
+	WLP_ATTR_ENRL_NONCE	= 0x101A, /* Enrollee Nonce */
+	WLP_ATTR_KEYWRAP_AUTH	= 0x101E, /* Key Wrap Authenticator */
+	WLP_ATTR_MANUF		= 0x1021, /* Manufacturer */
+	WLP_ATTR_MSG_TYPE	= 0x1022, /* Message Type */
+	WLP_ATTR_MODEL_NAME	= 0x1023, /* Model Name */
+	WLP_ATTR_MODEL_NR	= 0x1024, /* Model Number */
+	WLP_ATTR_PUB_KEY	= 0x1032, /* Public Key */
+	WLP_ATTR_REG_NONCE	= 0x1039, /* Registrar Nonce */
+	WLP_ATTR_R_HASH1	= 0x103D, /* R-Hash1 */
+	WLP_ATTR_R_HASH2	= 0x103E, /* R-Hash2 */
+	WLP_ATTR_R_SNONCE1	= 0x103F, /* R-SNonce1 */
+	WLP_ATTR_R_SNONCE2	= 0x1040, /* R-SNonce2 */
+	WLP_ATTR_SERIAL		= 0x1042, /* Serial number */
+	WLP_ATTR_UUID_E		= 0x1047, /* UUID-E */
+	WLP_ATTR_UUID_R		= 0x1048, /* UUID-R */
+	WLP_ATTR_PRI_DEV_TYPE	= 0x1054, /* Primary Device Type */
+	WLP_ATTR_SEC_DEV_TYPE	= 0x1055, /* Secondary Device Type */
+	WLP_ATTR_PORT_DEV	= 0x1056, /* Portable Device */
+	WLP_ATTR_APP_EXT	= 0x1058, /* Application Extension */
+	WLP_ATTR_WLP_VER	= 0x2000, /* WLP Version */
+	WLP_ATTR_WSSID		= 0x2001, /* WSSID */
+	WLP_ATTR_WSS_NAME	= 0x2002, /* WSS Name */
+	WLP_ATTR_WSS_SEC_STAT	= 0x2003, /* WSS Secure Status */
+	WLP_ATTR_WSS_BCAST	= 0x2004, /* WSS Broadcast Address */
+	WLP_ATTR_WSS_M_KEY	= 0x2005, /* WSS Master Key */
+	WLP_ATTR_ACC_ENRL	= 0x2006, /* Accepting Enrollment */
+	WLP_ATTR_WSS_INFO	= 0x2007, /* WSS Information */
+	WLP_ATTR_WSS_SEL_MTHD	= 0x2008, /* WSS Selection Method */
+	WLP_ATTR_ASSC_MTHD_LIST	= 0x2009, /* Association Methods List */
+	WLP_ATTR_SEL_ASSC_MTHD	= 0x200A, /* Selected Association Method */
+	WLP_ATTR_ENRL_HASH_COMM	= 0x200B, /* Enrollee Hash Commitment */
+	WLP_ATTR_WSS_TAG	= 0x200C, /* WSS Tag */
+	WLP_ATTR_WSS_VIRT	= 0x200D, /* WSS Virtual EUI-48 */
+	WLP_ATTR_WLP_ASSC_ERR	= 0x200E, /* WLP Association Error */
+	WLP_ATTR_VNDR_EXT	= 0x200F, /* Vendor Extension */
+};
+
+/**
+ * WLP Category ID of primary/secondary device
+ * WLP Draft 0.99 [6.6.1.8 Table 12]
+ */
+enum wlp_dev_category_id {
+	WLP_DEV_CAT_COMPUTER = 1,
+	WLP_DEV_CAT_INPUT,
+	WLP_DEV_CAT_PRINT_SCAN_FAX_COPIER,
+	WLP_DEV_CAT_CAMERA,
+	WLP_DEV_CAT_STORAGE,
+	WLP_DEV_CAT_INFRASTRUCTURE,
+	WLP_DEV_CAT_DISPLAY,
+	WLP_DEV_CAT_MULTIM,
+	WLP_DEV_CAT_GAMING,
+	WLP_DEV_CAT_TELEPHONE,
+	WLP_DEV_CAT_OTHER = 65535,
+};
+
+/**
+ * WLP WSS selection method
+ * WLP Draft 0.99 [6.6.1.6 Table 10]
+ */
+enum wlp_wss_sel_mthd {
+	WLP_WSS_ENRL_SELECT = 1,	/* Enrollee selects */
+	WLP_WSS_REG_SELECT,		/* Registrar selects */
+};
+
+/**
+ * WLP association error values
+ * WLP Draft 0.99 [6.6.1.5 Table 9]
+ */
+enum wlp_assc_error {
+	WLP_ASSOC_ERROR_NONE,
+	WLP_ASSOC_ERROR_AUTH,		/* Authenticator Failure */
+	WLP_ASSOC_ERROR_ROGUE,		/* Rogue activity suspected */
+	WLP_ASSOC_ERROR_BUSY,		/* Device busy */
+	WLP_ASSOC_ERROR_LOCK,		/* Setup Locked */
+	WLP_ASSOC_ERROR_NOT_READY,	/* Registrar not ready */
+	WLP_ASSOC_ERROR_INV,		/* Invalid WSS selection */
+	WLP_ASSOC_ERROR_MSG_TIME,	/* Message timeout */
+	WLP_ASSOC_ERROR_ENR_TIME,	/* Enrollment session timeout */
+	WLP_ASSOC_ERROR_PW,		/* Device password invalid */
+	WLP_ASSOC_ERROR_VER,		/* Unsupported version */
+	WLP_ASSOC_ERROR_INT,		/* Internal error */
+	WLP_ASSOC_ERROR_UNDEF,		/* Undefined error */
+	WLP_ASSOC_ERROR_NUM,		/* Numeric comparison failure */
+	WLP_ASSOC_ERROR_WAIT,		/* Waiting for user input */
+};
+
+/**
+ * WLP Parameters
+ * WLP 0.99 [7.7]
+ */
+enum wlp_parameters {
+	WLP_PER_MSG_TIMEOUT = 15,	/* Seconds to wait for response to
+					   association message. */
+};
+
+/**
+ * WLP IE
+ *
+ * The WLP IE should be included in beacons by all devices.
+ *
+ * The driver can set only a few of the fields in this information element,
+ * most fields are managed by the device self. When the driver needs to set
+ * a field it will only provide values for the fields of interest, the rest
+ * will be filled with zeroes. The fields of interest are:
+ *
+ * Element ID
+ * Length
+ * Capabilities (only to include WSSID Hash list length)
+ * WSSID Hash List fields
+ *
+ * WLP 0.99 [6.7]
+ *
+ * Only the fields that will be used are detailed in this structure, rest
+ * are not detailed or marked as "notused".
+ */
+struct wlp_ie {
+	struct uwb_ie_hdr hdr;
+	__le16 capabilities;
+	__le16 cycle_param;
+	__le16 acw_anchor_addr;
+	u8 wssid_hash_list[];
+} __attribute__((packed));
+
+static inline int wlp_ie_hash_length(struct wlp_ie *ie)
+{
+	return (le16_to_cpu(ie->capabilities) >> 12) & 0xf;
+}
+
+static inline void wlp_ie_set_hash_length(struct wlp_ie *ie, int hash_length)
+{
+	u16 caps = le16_to_cpu(ie->capabilities);
+	caps = (caps & ~(0xf << 12)) | (hash_length << 12);
+	ie->capabilities = cpu_to_le16(caps);
+}
+
+/**
+ * WLP nonce
+ * WLP Draft 0.99 [6.6.1 Table 6]
+ *
+ * A 128-bit random number often used (E-SNonce1, E-SNonce2, Enrollee
+ * Nonce, Registrar Nonce, R-SNonce1, R-SNonce2). It is passed to HW so
+ * it is packed.
+ */
+struct wlp_nonce {
+	u8 data[16];
+} __attribute__((packed));
+
+/**
+ * WLP UUID
+ * WLP Draft 0.99 [6.6.1 Table 6]
+ *
+ * Universally Unique Identifier (UUID) encoded as an octet string in the
+ * order the octets are shown in string representation in RFC4122. A UUID
+ * is often used (UUID-E, UUID-R, WSSID). It is passed to HW so it is packed.
+ */
+struct wlp_uuid {
+	u8 data[16];
+} __attribute__((packed));
+
+
+/**
+ * Primary and secondary device type attributes
+ * WLP Draft 0.99 [6.6.1.8]
+ */
+struct wlp_dev_type {
+	enum wlp_dev_category_id category:16;
+	u8 OUI[3];
+	u8 OUIsubdiv;
+	__le16 subID;
+} __attribute__((packed));
+
+/**
+ * WLP frame header
+ * WLP Draft 0.99 [6.2]
+ */
+struct wlp_frame_hdr {
+	__le16 mux_hdr;			/* WLP_PROTOCOL_ID */
+	enum wlp_frame_type type:8;
+} __attribute__((packed));
+
+/**
+ * WLP attribute field header
+ * WLP Draft 0.99 [6.6.1]
+ *
+ * Header of each attribute found in an association frame
+ */
+struct wlp_attr_hdr {
+	__le16 type;
+	__le16 length;
+} __attribute__((packed));
+
+/**
+ * Device information commonly used together
+ *
+ * Each of these device information elements has a specified range in which it
+ * should fit (WLP 0.99 [Table 6]). This range provided in the spec does not
+ * include the termination null '\0' character (when used in the
+ * association protocol the attribute fields are accompanied
+ * with a "length" field so the full range from the spec can be used for
+ * the value). We thus allocate an extra byte to be able to store a string
+ * of max length with a terminating '\0'.
+ */
+struct wlp_device_info {
+	char name[33];
+	char model_name[33];
+	char manufacturer[65];
+	char model_nr[33];
+	char serial[33];
+	struct wlp_dev_type prim_dev_type;
+};
+
+/**
+ * Macros for the WLP attributes
+ *
+ * There are quite a few attributes (total is 43). The attribute layout can be
+ * in one of three categories: one value, an array, an enum forced to 8 bits.
+ * These macros help with their definitions.
+ */
+#define wlp_attr(type, name)						\
+struct wlp_attr_##name {						\
+	struct wlp_attr_hdr hdr;					\
+	type name;							\
+} __attribute__((packed));
+
+#define wlp_attr_array(type, name)					\
+struct wlp_attr_##name {						\
+	struct wlp_attr_hdr hdr;					\
+	type name[];							\
+} __attribute__((packed));
+
+/**
+ * WLP association attribute fields
+ * WLP Draft 0.99 [6.6.1 Table 6]
+ *
+ * Attributes appear in same order as the Table in the spec
+ * FIXME Does not define all attributes yet
+ */
+
+/* Device name: Friendly name of sending device */
+wlp_attr_array(u8, dev_name)
+
+/* Enrollee Nonce: Random number generated by enrollee for an enrollment
+ * session */
+wlp_attr(struct wlp_nonce, enonce)
+
+/* Manufacturer name: Name of manufacturer of the sending device */
+wlp_attr_array(u8, manufacturer)
+
+/* WLP Message Type */
+wlp_attr(u8, msg_type)
+
+/* WLP Model name: Model name of sending device */
+wlp_attr_array(u8, model_name)
+
+/* WLP Model number: Model number of sending device */
+wlp_attr_array(u8, model_nr)
+
+/* Registrar Nonce: Random number generated by registrar for an enrollment
+ * session */
+wlp_attr(struct wlp_nonce, rnonce)
+
+/* Serial number of device */
+wlp_attr_array(u8, serial)
+
+/* UUID of enrollee */
+wlp_attr(struct wlp_uuid, uuid_e)
+
+/* UUID of registrar */
+wlp_attr(struct wlp_uuid, uuid_r)
+
+/* WLP Primary device type */
+wlp_attr(struct wlp_dev_type, prim_dev_type)
+
+/* WLP Secondary device type */
+wlp_attr(struct wlp_dev_type, sec_dev_type)
+
+/* WLP protocol version */
+wlp_attr(u8, version)
+
+/* WLP service set identifier */
+wlp_attr(struct wlp_uuid, wssid)
+
+/* WLP WSS name */
+wlp_attr_array(u8, wss_name)
+
+/* WLP WSS Secure Status */
+wlp_attr(u8, wss_sec_status)
+
+/* WSS Broadcast Address */
+wlp_attr(struct uwb_mac_addr, wss_bcast)
+
+/* WLP Accepting Enrollment */
+wlp_attr(u8, accept_enrl)
+
+/**
+ * WSS information attributes
+ * WLP Draft 0.99 [6.6.3 Table 15]
+ */
+struct wlp_wss_info {
+	struct wlp_attr_wssid wssid;
+	struct wlp_attr_wss_name name;
+	struct wlp_attr_accept_enrl accept;
+	struct wlp_attr_wss_sec_status sec_stat;
+	struct wlp_attr_wss_bcast bcast;
+} __attribute__((packed));
+
+/* WLP WSS Information */
+wlp_attr_array(struct wlp_wss_info, wss_info)
+
+/* WLP WSS Selection method */
+wlp_attr(u8, wss_sel_mthd)
+
+/* WLP WSS tag */
+wlp_attr(u8, wss_tag)
+
+/* WSS Virtual Address */
+wlp_attr(struct uwb_mac_addr, wss_virt)
+
+/* WLP association error */
+wlp_attr(u8, wlp_assc_err)
+
+/**
+ * WLP standard and abbreviated frames
+ *
+ * WLP Draft 0.99 [6.3] and [6.4]
+ *
+ * The difference between the WLP standard frame and the WLP
+ * abbreviated frame is that the standard frame includes the src
+ * and dest addresses from the Ethernet header, the abbreviated frame does
+ * not.
+ * The src/dest (as well as the type/length and client data) are already
+ * defined as part of the Ethernet header, we do not do this here.
+ * From this perspective the standard and abbreviated frames appear the
+ * same - they will be treated differently though.
+ *
+ * The size of this header is also captured in WLP_DATA_HLEN to enable
+ * interfaces to prepare their headroom.
+ */
+struct wlp_frame_std_abbrv_hdr {
+	struct wlp_frame_hdr hdr;
+	u8 tag;
+} __attribute__((packed));
+
+/**
+ * WLP association frames
+ *
+ * WLP Draft 0.99 [6.6]
+ */
+struct wlp_frame_assoc {
+	struct wlp_frame_hdr hdr;
+	enum wlp_assoc_type type:8;
+	struct wlp_attr_version version;
+	struct wlp_attr_msg_type msg_type;
+	u8 attr[];
+} __attribute__((packed));
+
+/* Ethernet to dev address mapping */
+struct wlp_eda {
+	spinlock_t lock;
+	struct list_head cache;	/* Eth<->Dev Addr cache */
+};
+
+/**
+ * WSS information temporary storage
+ *
+ * This information is only stored temporarily during discovery. It should
+ * not be stored unless the device is enrolled in the advertised WSS. This
+ * is done mainly because we follow the letter of the spec in this regard.
+ * See WLP 0.99 [7.2.3].
+ * When the device does become enrolled in a WSS the WSS information will
+ * be stored as part of the more comprehensive struct wlp_wss.
+ */
+struct wlp_wss_tmp_info {
+	char name[WLP_WSS_NAME_SIZE];
+	u8 accept_enroll;
+	u8 sec_status;
+	struct uwb_mac_addr bcast;
+};
+
+struct wlp_wssid_e {
+	struct list_head node;
+	struct wlp_uuid wssid;
+	struct wlp_wss_tmp_info *info;
+};
+
+/**
+ * A cache entry of WLP neighborhood
+ *
+ * @node: head of list is wlp->neighbors
+ * @wssid: list of wssids of this neighbor, element is wlp_wssid_e
+ * @info:  temporary storage for information learned during discovery. This
+ *         storage is used together with the wssid_e temporary storage
+ *         during discovery.
+ */
+struct wlp_neighbor_e {
+	struct list_head node;
+	struct wlp_uuid uuid;
+	struct uwb_dev *uwb_dev;
+	struct list_head wssid; /* Elements are wlp_wssid_e */
+	struct wlp_device_info *info;
+};
+
+struct wlp;
+/**
+ * Information for an association session in progress.
+ *
+ * @exp_message: The type of the expected message. Both this message and a
+ *               F0 message (which can be sent in response to any
+ *               association frame) will be accepted as a valid message for
+ *               this session.
+ * @cb:          The function that will be called upon receipt of this
+ *               message.
+ * @cb_priv:     Private data of callback
+ * @data:        Data used in association process (always a sk_buff?)
+ * @neighbor:    Address of neighbor with which association session is in
+ *               progress.
+ */
+struct wlp_session {
+	enum wlp_assoc_type exp_message;
+	void (*cb)(struct wlp *);
+	void *cb_priv;
+	void *data;
+	struct uwb_dev_addr neighbor_addr;
+};
+
+/**
+ * WLP Service Set
+ *
+ * @mutex: used to protect entire WSS structure.
+ *
+ * @name: The WSS name is set to 65 bytes, 1 byte larger than the maximum
+ *        allowed by the WLP spec. This is to have a null terminated string
+ *        for display to the user. A maximum of 64 bytes will still be used
+ *        when placing the WSS name field in association frames.
+ *
+ * @accept_enroll: Accepting enrollment: Set to one if registrar is
+ *                 accepting enrollment in WSS, or zero otherwise.
+ *
+ * Global and local information for each WSS in which we are enrolled.
+ * WLP 0.99 Section 7.2.1 and Section 7.2.2
+ */
+struct wlp_wss {
+	struct mutex mutex;
+	struct kobject kobj;
+	/* Global properties. */
+	struct wlp_uuid wssid;
+	u8 hash;
+	char name[WLP_WSS_NAME_SIZE];
+	struct uwb_mac_addr bcast;
+	u8 secure_status:1;
+	u8 master_key[16];
+	/* Local properties. */
+	u8 tag;
+	struct uwb_mac_addr virtual_addr;
+	/* Extra */
+	u8 accept_enroll:1;
+	enum wlp_wss_state state;
+};
+
+/**
+ * WLP main structure
+ * @mutex: protect changes to WLP structure. We only allow changes to the
+ *         uuid, so currently this mutex only protects this field.
+ */
+struct wlp {
+	struct mutex mutex;
+	struct uwb_rc *rc;		/* UWB radio controller */
+	struct uwb_pal pal;
+	struct wlp_eda eda;
+	struct wlp_uuid uuid;
+	struct wlp_session *session;
+	struct wlp_wss wss;
+	struct mutex nbmutex; /* Neighbor mutex protects neighbors list */
+	struct list_head neighbors; /* Elements are wlp_neighbor_e */
+	struct uwb_notifs_handler uwb_notifs_handler;
+	struct wlp_device_info *dev_info;
+	void (*fill_device_info)(struct wlp *wlp, struct wlp_device_info *info);
+	int (*xmit_frame)(struct wlp *, struct sk_buff *,
+			  struct uwb_dev_addr *);
+	void (*stop_queue)(struct wlp *);
+	void (*start_queue)(struct wlp *);
+};
+
+/* sysfs */
+
+
+struct wlp_wss_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct wlp_wss *wss, char *buf);
+	ssize_t (*store)(struct wlp_wss *wss, const char *buf, size_t count);
+};
+
+#define WSS_ATTR(_name, _mode, _show, _store) \
+static struct wlp_wss_attribute wss_attr_##_name = __ATTR(_name, _mode,	\
+							  _show, _store)
+
+extern int wlp_setup(struct wlp *, struct uwb_rc *);
+extern void wlp_remove(struct wlp *);
+extern ssize_t wlp_neighborhood_show(struct wlp *, char *);
+extern int wlp_wss_setup(struct net_device *, struct wlp_wss *);
+extern void wlp_wss_remove(struct wlp_wss *);
+extern ssize_t wlp_wss_activate_show(struct wlp_wss *, char *);
+extern ssize_t wlp_wss_activate_store(struct wlp_wss *, const char *, size_t);
+extern ssize_t wlp_eda_show(struct wlp *, char *);
+extern ssize_t wlp_eda_store(struct wlp *, const char *, size_t);
+extern ssize_t wlp_uuid_show(struct wlp *, char *);
+extern ssize_t wlp_uuid_store(struct wlp *, const char *, size_t);
+extern ssize_t wlp_dev_name_show(struct wlp *, char *);
+extern ssize_t wlp_dev_name_store(struct wlp *, const char *, size_t);
+extern ssize_t wlp_dev_manufacturer_show(struct wlp *, char *);
+extern ssize_t wlp_dev_manufacturer_store(struct wlp *, const char *, size_t);
+extern ssize_t wlp_dev_model_name_show(struct wlp *, char *);
+extern ssize_t wlp_dev_model_name_store(struct wlp *, const char *, size_t);
+extern ssize_t wlp_dev_model_nr_show(struct wlp *, char *);
+extern ssize_t wlp_dev_model_nr_store(struct wlp *, const char *, size_t);
+extern ssize_t wlp_dev_serial_show(struct wlp *, char *);
+extern ssize_t wlp_dev_serial_store(struct wlp *, const char *, size_t);
+extern ssize_t wlp_dev_prim_category_show(struct wlp *, char *);
+extern ssize_t wlp_dev_prim_category_store(struct wlp *, const char *,
+					   size_t);
+extern ssize_t wlp_dev_prim_OUI_show(struct wlp *, char *);
+extern ssize_t wlp_dev_prim_OUI_store(struct wlp *, const char *, size_t);
+extern ssize_t wlp_dev_prim_OUI_sub_show(struct wlp *, char *);
+extern ssize_t wlp_dev_prim_OUI_sub_store(struct wlp *, const char *,
+					  size_t);
+extern ssize_t wlp_dev_prim_subcat_show(struct wlp *, char *);
+extern ssize_t wlp_dev_prim_subcat_store(struct wlp *, const char *,
+					 size_t);
+extern int wlp_receive_frame(struct device *, struct wlp *, struct sk_buff *,
+			     struct uwb_dev_addr *);
+extern int wlp_prepare_tx_frame(struct device *, struct wlp *,
+			       struct sk_buff *, struct uwb_dev_addr *);
+void wlp_reset_all(struct wlp *wlp);
+
+/**
+ * Initialize WSS
+ */
+static inline
+void wlp_wss_init(struct wlp_wss *wss)
+{
+	mutex_init(&wss->mutex);
+}
+
+static inline
+void wlp_init(struct wlp *wlp)
+{
+	INIT_LIST_HEAD(&wlp->neighbors);
+	mutex_init(&wlp->mutex);
+	mutex_init(&wlp->nbmutex);
+	wlp_wss_init(&wlp->wss);
+}
+
+
+#endif /* #ifndef __LINUX__WLP_H_ */
-- 
cgit v1.2.3


From da389eac31be24556a71dd59ea6539ae4cba5c15 Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@csr.com>
Date: Wed, 17 Sep 2008 16:34:12 +0100
Subject: uwb: add the umc bus

The UMC bus is used for the capabilities exposed by a UWB Multi-interface
Controller as described in the WHCI specification.

Signed-off-by: David Vrabel <david.vrabel@csr.com>
---
 drivers/uwb/Makefile    |   6 ++
 drivers/uwb/umc-bus.c   | 218 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/uwb/umc-dev.c   | 104 +++++++++++++++++++++++
 drivers/uwb/umc-drv.c   |  31 +++++++
 include/linux/uwb/umc.h | 194 ++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 553 insertions(+)
 create mode 100644 drivers/uwb/umc-bus.c
 create mode 100644 drivers/uwb/umc-dev.c
 create mode 100644 drivers/uwb/umc-drv.c
 create mode 100644 include/linux/uwb/umc.h

(limited to 'include')

diff --git a/drivers/uwb/Makefile b/drivers/uwb/Makefile
index 9a67be5ac5c1..41c9fca5f875 100644
--- a/drivers/uwb/Makefile
+++ b/drivers/uwb/Makefile
@@ -1,4 +1,5 @@
 obj-$(CONFIG_UWB)		+= uwb.o
+obj-$(CONFIG_UWB_WHCI)		+= umc.o
 
 uwb-objs :=		\
 	address.o	\
@@ -18,3 +19,8 @@ uwb-objs :=		\
 	scan.o		\
 	uwb-debug.o	\
 	uwbd.o
+
+umc-objs :=		\
+	umc-bus.o	\
+	umc-dev.o	\
+	umc-drv.o
diff --git a/drivers/uwb/umc-bus.c b/drivers/uwb/umc-bus.c
new file mode 100644
index 000000000000..2d8d62d9f53e
--- /dev/null
+++ b/drivers/uwb/umc-bus.c
@@ -0,0 +1,218 @@
+/*
+ * Bus for UWB Multi-interface Controller capabilities.
+ *
+ * Copyright (C) 2007 Cambridge Silicon Radio Ltd.
+ *
+ * This file is released under the GNU GPL v2.
+ */
+#include <linux/kernel.h>
+#include <linux/sysfs.h>
+#include <linux/workqueue.h>
+#include <linux/uwb/umc.h>
+#include <linux/pci.h>
+
+static int umc_bus_unbind_helper(struct device *dev, void *data)
+{
+	struct device *parent = data;
+
+	if (dev->parent == parent && dev->driver)
+		device_release_driver(dev);
+	return 0;
+}
+
+/**
+ * umc_controller_reset - reset the whole UMC controller
+ * @umc: the UMC device for the radio controller.
+ *
+ * Drivers will be unbound from all UMC devices belonging to the
+ * controller and then the radio controller will be rebound.  The
+ * radio controller is expected to do a full hardware reset when it is
+ * probed.
+ *
+ * If this is called while a probe() or remove() is in progress it
+ * will return -EAGAIN and not perform the reset.
+ */
+int umc_controller_reset(struct umc_dev *umc)
+{
+	struct device *parent = umc->dev.parent;
+	int ret;
+
+	if (down_trylock(&parent->sem))
+		return -EAGAIN;
+	bus_for_each_dev(&umc_bus_type, NULL, parent, umc_bus_unbind_helper);
+	ret = device_attach(&umc->dev);
+	if (ret == 1)
+		ret = 0;
+	up(&parent->sem);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(umc_controller_reset);
+
+/**
+ * umc_match_pci_id - match a UMC driver to a UMC device's parent PCI device.
+ * @umc_drv: umc driver with match_data pointing to a zero-terminated
+ * table of pci_device_id's.
+ * @umc: umc device whose parent is to be matched.
+ */
+int umc_match_pci_id(struct umc_driver *umc_drv, struct umc_dev *umc)
+{
+	const struct pci_device_id *id_table = umc_drv->match_data;
+	struct pci_dev *pci;
+
+	if (umc->dev.parent->bus != &pci_bus_type)
+		return 0;
+
+	pci = to_pci_dev(umc->dev.parent);
+	return pci_match_id(id_table, pci) != NULL;
+}
+EXPORT_SYMBOL_GPL(umc_match_pci_id);
+
+static int umc_bus_rescan_helper(struct device *dev, void *data)
+{
+	int ret = 0;
+
+	if (!dev->driver)
+		ret = device_attach(dev);
+
+	return ret < 0 ? ret : 0;
+}
+
+static void umc_bus_rescan(void)
+{
+	int err;
+
+	/*
+	 * We can't use bus_rescan_devices() here as it deadlocks when
+	 * it tries to retake the dev->parent semaphore.
+	 */
+	err = bus_for_each_dev(&umc_bus_type, NULL, NULL, umc_bus_rescan_helper);
+	if (err < 0)
+		printk(KERN_WARNING "%s: rescan of bus failed: %d\n",
+		       KBUILD_MODNAME, err);
+}
+
+static int umc_bus_match(struct device *dev, struct device_driver *drv)
+{
+	struct umc_dev *umc = to_umc_dev(dev);
+	struct umc_driver *umc_driver = to_umc_driver(drv);
+
+	if (umc->cap_id == umc_driver->cap_id) {
+		if (umc_driver->match)
+			return umc_driver->match(umc_driver, umc);
+		else
+			return 1;
+	}
+	return 0;
+}
+
+static int umc_device_probe(struct device *dev)
+{
+	struct umc_dev *umc;
+	struct umc_driver *umc_driver;
+	int err;
+
+	umc_driver = to_umc_driver(dev->driver);
+	umc = to_umc_dev(dev);
+
+	get_device(dev);
+	err = umc_driver->probe(umc);
+	if (err)
+		put_device(dev);
+	else
+		umc_bus_rescan();
+
+	return err;
+}
+
+static int umc_device_remove(struct device *dev)
+{
+	struct umc_dev *umc;
+	struct umc_driver *umc_driver;
+
+	umc_driver = to_umc_driver(dev->driver);
+	umc = to_umc_dev(dev);
+
+	umc_driver->remove(umc);
+	put_device(dev);
+	return 0;
+}
+
+static int umc_device_suspend(struct device *dev, pm_message_t state)
+{
+	struct umc_dev *umc;
+	struct umc_driver *umc_driver;
+	int err = 0;
+
+	umc = to_umc_dev(dev);
+
+	if (dev->driver) {
+		umc_driver = to_umc_driver(dev->driver);
+		if (umc_driver->suspend)
+			err = umc_driver->suspend(umc, state);
+	}
+	return err;
+}
+
+static int umc_device_resume(struct device *dev)
+{
+	struct umc_dev *umc;
+	struct umc_driver *umc_driver;
+	int err = 0;
+
+	umc = to_umc_dev(dev);
+
+	if (dev->driver) {
+		umc_driver = to_umc_driver(dev->driver);
+		if (umc_driver->resume)
+			err = umc_driver->resume(umc);
+	}
+	return err;
+}
+
+static ssize_t capability_id_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct umc_dev *umc = to_umc_dev(dev);
+
+	return sprintf(buf, "0x%02x\n", umc->cap_id);
+}
+
+static ssize_t version_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	struct umc_dev *umc = to_umc_dev(dev);
+
+	return sprintf(buf, "0x%04x\n", umc->version);
+}
+
+static struct device_attribute umc_dev_attrs[] = {
+	__ATTR_RO(capability_id),
+	__ATTR_RO(version),
+	__ATTR_NULL,
+};
+
+struct bus_type umc_bus_type = {
+	.name		= "umc",
+	.match		= umc_bus_match,
+	.probe		= umc_device_probe,
+	.remove		= umc_device_remove,
+	.suspend        = umc_device_suspend,
+	.resume         = umc_device_resume,
+	.dev_attrs	= umc_dev_attrs,
+};
+EXPORT_SYMBOL_GPL(umc_bus_type);
+
+static int __init umc_bus_init(void)
+{
+	return bus_register(&umc_bus_type);
+}
+module_init(umc_bus_init);
+
+static void __exit umc_bus_exit(void)
+{
+	bus_unregister(&umc_bus_type);
+}
+module_exit(umc_bus_exit);
+
+MODULE_DESCRIPTION("UWB Multi-interface Controller capability bus");
+MODULE_AUTHOR("Cambridge Silicon Radio Ltd.");
+MODULE_LICENSE("GPL");
diff --git a/drivers/uwb/umc-dev.c b/drivers/uwb/umc-dev.c
new file mode 100644
index 000000000000..aa44e1c1a102
--- /dev/null
+++ b/drivers/uwb/umc-dev.c
@@ -0,0 +1,104 @@
+/*
+ * UWB Multi-interface Controller device management.
+ *
+ * Copyright (C) 2007 Cambridge Silicon Radio Ltd.
+ *
+ * This file is released under the GNU GPL v2.
+ */
+#include <linux/kernel.h>
+#include <linux/uwb/umc.h>
+#define D_LOCAL 0
+#include <linux/uwb/debug.h>
+
+static void umc_device_release(struct device *dev)
+{
+	struct umc_dev *umc = to_umc_dev(dev);
+
+	kfree(umc);
+}
+
+/**
+ * umc_device_create - allocate a child UMC device
+ * @parent: parent of the new UMC device.
+ * @n:      index of the new device.
+ *
+ * The new UMC device will have a bus ID of the parent with '-n'
+ * appended.
+ */
+struct umc_dev *umc_device_create(struct device *parent, int n)
+{
+	struct umc_dev *umc;
+
+	umc = kzalloc(sizeof(struct umc_dev), GFP_KERNEL);
+	if (umc) {
+		snprintf(umc->dev.bus_id, sizeof(umc->dev.bus_id), "%s-%d",
+			 parent->bus_id, n);
+		umc->dev.parent  = parent;
+		umc->dev.bus     = &umc_bus_type;
+		umc->dev.release = umc_device_release;
+
+		umc->dev.dma_mask = parent->dma_mask;
+	}
+	return umc;
+}
+EXPORT_SYMBOL_GPL(umc_device_create);
+
+/**
+ * umc_device_register - register a UMC device
+ * @umc: pointer to the UMC device
+ *
+ * The memory resource for the UMC device is acquired and the device
+ * registered with the system.
+ */
+int umc_device_register(struct umc_dev *umc)
+{
+	int err;
+
+	d_fnstart(3, &umc->dev, "(umc_dev %p)\n", umc);
+
+	err = request_resource(umc->resource.parent, &umc->resource);
+	if (err < 0) {
+		dev_err(&umc->dev, "can't allocate resource range "
+			"%016Lx to %016Lx: %d\n",
+			(unsigned long long)umc->resource.start,
+			(unsigned long long)umc->resource.end,
+			err);
+		goto error_request_resource;
+	}
+
+	err = device_register(&umc->dev);
+	if (err < 0)
+		goto error_device_register;
+	d_fnend(3, &umc->dev, "(umc_dev %p) = 0\n", umc);
+	return 0;
+
+error_device_register:
+	release_resource(&umc->resource);
+error_request_resource:
+	d_fnend(3, &umc->dev, "(umc_dev %p) = %d\n", umc, err);
+	return err;
+}
+EXPORT_SYMBOL_GPL(umc_device_register);
+
+/**
+ * umc_device_unregister - unregister a UMC device
+ * @umc: pointer to the UMC device
+ *
+ * First we unregister the device, make sure the driver can do it's
+ * resource release thing and then we try to release any left over
+ * resources. We take a ref to the device, to make sure it doesn't
+ * dissapear under our feet.
+ */
+void umc_device_unregister(struct umc_dev *umc)
+{
+	struct device *dev;
+	if (!umc)
+		return;
+	dev = get_device(&umc->dev);
+	d_fnstart(3, dev, "(umc_dev %p)\n", umc);
+	device_unregister(&umc->dev);
+	release_resource(&umc->resource);
+	d_fnend(3, dev, "(umc_dev %p) = void\n", umc);
+	put_device(dev);
+}
+EXPORT_SYMBOL_GPL(umc_device_unregister);
diff --git a/drivers/uwb/umc-drv.c b/drivers/uwb/umc-drv.c
new file mode 100644
index 000000000000..367b5eb85d60
--- /dev/null
+++ b/drivers/uwb/umc-drv.c
@@ -0,0 +1,31 @@
+/*
+ * UWB Multi-interface Controller driver management.
+ *
+ * Copyright (C) 2007 Cambridge Silicon Radio Ltd.
+ *
+ * This file is released under the GNU GPL v2.
+ */
+#include <linux/kernel.h>
+#include <linux/uwb/umc.h>
+
+int __umc_driver_register(struct umc_driver *umc_drv, struct module *module,
+			  const char *mod_name)
+{
+	umc_drv->driver.name     = umc_drv->name;
+	umc_drv->driver.owner    = module;
+	umc_drv->driver.mod_name = mod_name;
+	umc_drv->driver.bus      = &umc_bus_type;
+
+	return driver_register(&umc_drv->driver);
+}
+EXPORT_SYMBOL_GPL(__umc_driver_register);
+
+/**
+ * umc_driver_register - unregister a UMC capabiltity driver.
+ * @umc_drv:  pointer to the driver.
+ */
+void umc_driver_unregister(struct umc_driver *umc_drv)
+{
+	driver_unregister(&umc_drv->driver);
+}
+EXPORT_SYMBOL_GPL(umc_driver_unregister);
diff --git a/include/linux/uwb/umc.h b/include/linux/uwb/umc.h
new file mode 100644
index 000000000000..36a39e34f8d7
--- /dev/null
+++ b/include/linux/uwb/umc.h
@@ -0,0 +1,194 @@
+/*
+ * UWB Multi-interface Controller support.
+ *
+ * Copyright (C) 2007 Cambridge Silicon Radio Ltd.
+ *
+ * This file is released under the GPLv2
+ *
+ * UMC (UWB Multi-interface Controller) capabilities (e.g., radio
+ * controller, host controller) are presented as devices on the "umc"
+ * bus.
+ *
+ * The radio controller is not strictly a UMC capability but it's
+ * useful to present it as such.
+ *
+ * References:
+ *
+ *   [WHCI] Wireless Host Controller Interface Specification for
+ *          Certified Wireless Universal Serial Bus, revision 0.95.
+ *
+ * How this works is kind of convoluted but simple. The whci.ko driver
+ * loads when WHCI devices are detected. These WHCI devices expose
+ * many devices in the same PCI function (they couldn't have reused
+ * functions, no), so for each PCI function that exposes these many
+ * devices, whci ceates a umc_dev [whci_probe() -> whci_add_cap()]
+ * with umc_device_create() and adds it to the bus with
+ * umc_device_register().
+ *
+ * umc_device_register() calls device_register() which will push the
+ * bus management code to load your UMC driver's somehting_probe()
+ * that you have registered for that capability code.
+ *
+ * Now when the WHCI device is removed, whci_remove() will go over
+ * each umc_dev assigned to each of the PCI function's capabilities
+ * and through whci_del_cap() call umc_device_unregister() each
+ * created umc_dev. Of course, if you are bound to the device, your
+ * driver's something_remove() will be called.
+ */
+
+#ifndef _LINUX_UWB_UMC_H_
+#define _LINUX_UWB_UMC_H_
+
+#include <linux/device.h>
+#include <linux/pci.h>
+
+/*
+ * UMC capability IDs.
+ *
+ * 0x00 is reserved so use it for the radio controller device.
+ *
+ * [WHCI] table 2-8
+ */
+#define UMC_CAP_ID_WHCI_RC      0x00 /* radio controller */
+#define UMC_CAP_ID_WHCI_WUSB_HC 0x01 /* WUSB host controller */
+
+/**
+ * struct umc_dev - UMC capability device
+ *
+ * @version:  version of the specification this capability conforms to.
+ * @cap_id:   capability ID.
+ * @bar:      PCI Bar (64 bit) where the resource lies
+ * @resource: register space resource.
+ * @irq:      interrupt line.
+ */
+struct umc_dev {
+	u16		version;
+	u8		cap_id;
+	u8		bar;
+	struct resource resource;
+	unsigned	irq;
+	struct device	dev;
+};
+
+#define to_umc_dev(d) container_of(d, struct umc_dev, dev)
+
+/**
+ * struct umc_driver - UMC capability driver
+ * @cap_id: supported capability ID.
+ * @match: driver specific capability matching function.
+ * @match_data: driver specific data for match() (e.g., a
+ * table of pci_device_id's if umc_match_pci_id() is used).
+ */
+struct umc_driver {
+	char *name;
+	u8 cap_id;
+	int (*match)(struct umc_driver *, struct umc_dev *);
+	const void *match_data;
+
+	int  (*probe)(struct umc_dev *);
+	void (*remove)(struct umc_dev *);
+	int  (*suspend)(struct umc_dev *, pm_message_t state);
+	int  (*resume)(struct umc_dev *);
+
+	struct device_driver driver;
+};
+
+#define to_umc_driver(d) container_of(d, struct umc_driver, driver)
+
+extern struct bus_type umc_bus_type;
+
+struct umc_dev *umc_device_create(struct device *parent, int n);
+int __must_check umc_device_register(struct umc_dev *umc);
+void umc_device_unregister(struct umc_dev *umc);
+
+int __must_check __umc_driver_register(struct umc_driver *umc_drv,
+				       struct module *mod,
+				       const char *mod_name);
+
+/**
+ * umc_driver_register - register a UMC capabiltity driver.
+ * @umc_drv:  pointer to the driver.
+ */
+static inline int __must_check umc_driver_register(struct umc_driver *umc_drv)
+{
+	return __umc_driver_register(umc_drv, THIS_MODULE, KBUILD_MODNAME);
+}
+void umc_driver_unregister(struct umc_driver *umc_drv);
+
+/*
+ * Utility function you can use to match (umc_driver->match) against a
+ * null-terminated array of 'struct pci_device_id' in
+ * umc_driver->match_data.
+ */
+int umc_match_pci_id(struct umc_driver *umc_drv, struct umc_dev *umc);
+
+/**
+ * umc_parent_pci_dev - return the UMC's parent PCI device or NULL if none
+ * @umc_dev: UMC device whose parent PCI device we are looking for
+ *
+ * DIRTY!!! DON'T RELY ON THIS
+ *
+ * FIXME: This is as dirty as it gets, but we need some way to check
+ * the correct type of umc_dev->parent (so that for example, we can
+ * cast to pci_dev). Casting to pci_dev is necesary because at some
+ * point we need to request resources from the device. Mapping is
+ * easily over come (ioremap and stuff are bus agnostic), but hooking
+ * up to some error handlers (such as pci error handlers) might need
+ * this.
+ *
+ * THIS might (probably will) be removed in the future, so don't count
+ * on it.
+ */
+static inline struct pci_dev *umc_parent_pci_dev(struct umc_dev *umc_dev)
+{
+	struct pci_dev *pci_dev = NULL;
+	if (umc_dev->dev.parent->bus == &pci_bus_type)
+		pci_dev = to_pci_dev(umc_dev->dev.parent);
+	return pci_dev;
+}
+
+/**
+ * umc_dev_get() - reference a UMC device.
+ * @umc_dev: Pointer to UMC device.
+ *
+ * NOTE: we are assuming in this whole scheme that the parent device
+ *       is referenced at _probe() time and unreferenced at _remove()
+ *       time by the parent's subsystem.
+ */
+static inline struct umc_dev *umc_dev_get(struct umc_dev *umc_dev)
+{
+	get_device(&umc_dev->dev);
+	return umc_dev;
+}
+
+/**
+ * umc_dev_put() - unreference a UMC device.
+ * @umc_dev: Pointer to UMC device.
+ */
+static inline void umc_dev_put(struct umc_dev *umc_dev)
+{
+	put_device(&umc_dev->dev);
+}
+
+/**
+ * umc_set_drvdata - set UMC device's driver data.
+ * @umc_dev: Pointer to UMC device.
+ * @data:    Data to set.
+ */
+static inline void umc_set_drvdata(struct umc_dev *umc_dev, void *data)
+{
+	dev_set_drvdata(&umc_dev->dev, data);
+}
+
+/**
+ * umc_get_drvdata - recover UMC device's driver data.
+ * @umc_dev: Pointer to UMC device.
+ */
+static inline void *umc_get_drvdata(struct umc_dev *umc_dev)
+{
+	return dev_get_drvdata(&umc_dev->dev);
+}
+
+int umc_controller_reset(struct umc_dev *umc);
+
+#endif /* #ifndef _LINUX_UWB_UMC_H_ */
-- 
cgit v1.2.3


From 8f1b678ab900c2bda1620dfb6e1f1f02604fc3a2 Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@csr.com>
Date: Wed, 17 Sep 2008 16:34:13 +0100
Subject: uwb: add the driver to enumerate WHCI capabilities

This enumerates the capabilties of a WHCI device, adding a umc device for
each one.

Signed-off-by: David Vrabel <david.vrabel@csr.com>
---
 drivers/uwb/Makefile     |   2 +-
 drivers/uwb/whci.c       | 269 +++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/uwb/whci.h | 117 +++++++++++++++++++++
 3 files changed, 387 insertions(+), 1 deletion(-)
 create mode 100644 drivers/uwb/whci.c
 create mode 100644 include/linux/uwb/whci.h

(limited to 'include')

diff --git a/drivers/uwb/Makefile b/drivers/uwb/Makefile
index 41c9fca5f875..b054471af28d 100644
--- a/drivers/uwb/Makefile
+++ b/drivers/uwb/Makefile
@@ -1,5 +1,5 @@
 obj-$(CONFIG_UWB)		+= uwb.o
-obj-$(CONFIG_UWB_WHCI)		+= umc.o
+obj-$(CONFIG_UWB_WHCI)		+= umc.o whci.o
 
 uwb-objs :=		\
 	address.o	\
diff --git a/drivers/uwb/whci.c b/drivers/uwb/whci.c
new file mode 100644
index 000000000000..3df2388f908f
--- /dev/null
+++ b/drivers/uwb/whci.c
@@ -0,0 +1,269 @@
+/*
+ * WHCI UWB Multi-interface Controller enumerator.
+ *
+ * Copyright (C) 2007 Cambridge Silicon Radio Ltd.
+ *
+ * This file is released under the GNU GPL v2.
+ */
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/dma-mapping.h>
+#include <linux/uwb/whci.h>
+#include <linux/uwb/umc.h>
+
+struct whci_card {
+	struct pci_dev *pci;
+	void __iomem *uwbbase;
+	u8 n_caps;
+	struct umc_dev *devs[0];
+};
+
+
+/* Fix faulty HW :( */
+static
+u64 whci_capdata_quirks(struct whci_card *card, u64 capdata)
+{
+	u64 capdata_orig = capdata;
+	struct pci_dev *pci_dev = card->pci;
+	if (pci_dev->vendor == PCI_VENDOR_ID_INTEL
+	    && (pci_dev->device == 0x0c3b || pci_dev->device == 0004)
+	    && pci_dev->class == 0x0d1010) {
+		switch (UWBCAPDATA_TO_CAP_ID(capdata)) {
+			/* WLP capability has 0x100 bytes of aperture */
+		case 0x80:
+			capdata |= 0x40 << 8; break;
+			/* WUSB capability has 0x80 bytes of aperture
+			 * and ID is 1 */
+		case 0x02:
+			capdata &= ~0xffff;
+			capdata |= 0x2001;
+			break;
+		}
+	}
+	if (capdata_orig != capdata)
+		dev_warn(&pci_dev->dev,
+			 "PCI v%04x d%04x c%06x#%02x: "
+			 "corrected capdata from %016Lx to %016Lx\n",
+			 pci_dev->vendor, pci_dev->device, pci_dev->class,
+			 (unsigned)UWBCAPDATA_TO_CAP_ID(capdata),
+			 (unsigned long long)capdata_orig,
+			 (unsigned long long)capdata);
+	return capdata;
+}
+
+
+/**
+ * whci_wait_for - wait for a WHCI register to be set
+ *
+ * Polls (for at most @max_ms ms) until '*@reg & @mask == @result'.
+ */
+int whci_wait_for(struct device *dev, u32 __iomem *reg, u32 mask, u32 result,
+	unsigned long max_ms, const char *tag)
+{
+	unsigned t = 0;
+	u32 val;
+	for (;;) {
+		val = le_readl(reg);
+		if ((val & mask) == result)
+			break;
+		msleep(10);
+		if (t >= max_ms) {
+			dev_err(dev, "timed out waiting for %s ", tag);
+			return -ETIMEDOUT;
+		}
+		t += 10;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(whci_wait_for);
+
+
+/*
+ * NOTE: the capinfo and capdata registers are slightly different
+ *       (size and cap-id fields). So for cap #0, we need to fill
+ *       in. Size comes from the size of the register block
+ *       (statically calculated); cap_id comes from nowhere, we use
+ *       zero, that is reserved, for the radio controller, because
+ *       none was defined at the spec level.
+ */
+static int whci_add_cap(struct whci_card *card, int n)
+{
+	struct umc_dev *umc;
+	u64 capdata;
+	int bar, err;
+
+	umc = umc_device_create(&card->pci->dev, n);
+	if (umc == NULL)
+		return -ENOMEM;
+
+	capdata = le_readq(card->uwbbase + UWBCAPDATA(n));
+
+	bar = UWBCAPDATA_TO_BAR(capdata) << 1;
+
+	capdata = whci_capdata_quirks(card, capdata);
+	/* Capability 0 is the radio controller. It's size is 32
+	 * bytes (WHCI0.95[2.3, T2-9]). */
+	umc->version         = UWBCAPDATA_TO_VERSION(capdata);
+	umc->cap_id          = n == 0 ? 0 : UWBCAPDATA_TO_CAP_ID(capdata);
+	umc->bar	     = bar;
+	umc->resource.start  = pci_resource_start(card->pci, bar)
+		+ UWBCAPDATA_TO_OFFSET(capdata);
+	umc->resource.end    = umc->resource.start
+		+ (n == 0 ? 0x20 : UWBCAPDATA_TO_SIZE(capdata)) - 1;
+	umc->resource.name   = umc->dev.bus_id;
+	umc->resource.flags  = card->pci->resource[bar].flags;
+	umc->resource.parent = &card->pci->resource[bar];
+	umc->irq             = card->pci->irq;
+
+	err = umc_device_register(umc);
+	if (err < 0)
+		goto error;
+	card->devs[n] = umc;
+	return 0;
+
+error:
+	kfree(umc);
+	return err;
+}
+
+static void whci_del_cap(struct whci_card *card, int n)
+{
+	struct umc_dev *umc = card->devs[n];
+
+	if (umc != NULL)
+		umc_device_unregister(umc);
+}
+
+static int whci_n_caps(struct pci_dev *pci)
+{
+	void __iomem *uwbbase;
+	u64 capinfo;
+
+	uwbbase = pci_iomap(pci, 0, 8);
+	if (!uwbbase)
+		return -ENOMEM;
+	capinfo = le_readq(uwbbase + UWBCAPINFO);
+	pci_iounmap(pci, uwbbase);
+
+	return UWBCAPINFO_TO_N_CAPS(capinfo);
+}
+
+static int whci_probe(struct pci_dev *pci, const struct pci_device_id *id)
+{
+	struct whci_card *card;
+	int err, n_caps, n;
+
+	err = pci_enable_device(pci);
+	if (err < 0)
+		goto error;
+	pci_enable_msi(pci);
+	pci_set_master(pci);
+	err = -ENXIO;
+	if (!pci_set_dma_mask(pci, DMA_64BIT_MASK))
+		pci_set_consistent_dma_mask(pci, DMA_64BIT_MASK);
+	else if (!pci_set_dma_mask(pci, DMA_32BIT_MASK))
+		pci_set_consistent_dma_mask(pci, DMA_32BIT_MASK);
+	else
+		goto error_dma;
+
+	err = n_caps = whci_n_caps(pci);
+	if (n_caps < 0)
+		goto error_ncaps;
+
+	err = -ENOMEM;
+	card = kzalloc(sizeof(struct whci_card)
+		       + sizeof(struct whci_dev *) * (n_caps + 1),
+		       GFP_KERNEL);
+	if (card == NULL)
+		goto error_kzalloc;
+	card->pci = pci;
+	card->n_caps = n_caps;
+
+	err = -EBUSY;
+	if (!request_mem_region(pci_resource_start(pci, 0),
+				UWBCAPDATA_SIZE(card->n_caps),
+				"whci (capability data)"))
+		goto error_request_memregion;
+	err = -ENOMEM;
+	card->uwbbase = pci_iomap(pci, 0, UWBCAPDATA_SIZE(card->n_caps));
+	if (!card->uwbbase)
+		goto error_iomap;
+
+	/* Add each capability. */
+	for (n = 0; n <= card->n_caps; n++) {
+		err = whci_add_cap(card, n);
+		if (err < 0 && n == 0) {
+			dev_err(&pci->dev, "cannot bind UWB radio controller:"
+				" %d\n", err);
+			goto error_bind;
+		}
+		if (err < 0)
+			dev_warn(&pci->dev, "warning: cannot bind capability "
+				 "#%u: %d\n", n, err);
+	}
+	pci_set_drvdata(pci, card);
+	return 0;
+
+error_bind:
+	pci_iounmap(pci, card->uwbbase);
+error_iomap:
+	release_mem_region(pci_resource_start(pci, 0), UWBCAPDATA_SIZE(card->n_caps));
+error_request_memregion:
+	kfree(card);
+error_kzalloc:
+error_ncaps:
+error_dma:
+	pci_disable_msi(pci);
+	pci_disable_device(pci);
+error:
+	return err;
+}
+
+static void whci_remove(struct pci_dev *pci)
+{
+	struct whci_card *card = pci_get_drvdata(pci);
+	int n;
+
+	pci_set_drvdata(pci, NULL);
+	/* Unregister each capability in reverse (so the master device
+	 * is unregistered last). */
+	for (n = card->n_caps; n >= 0 ; n--)
+		whci_del_cap(card, n);
+	pci_iounmap(pci, card->uwbbase);
+	release_mem_region(pci_resource_start(pci, 0), UWBCAPDATA_SIZE(card->n_caps));
+	kfree(card);
+	pci_disable_msi(pci);
+	pci_disable_device(pci);
+}
+
+static struct pci_device_id whci_id_table[] = {
+	{ PCI_DEVICE_CLASS(PCI_CLASS_WIRELESS_WHCI, ~0) },
+	{ 0 },
+};
+MODULE_DEVICE_TABLE(pci, whci_id_table);
+
+
+static struct pci_driver whci_driver = {
+	.name     = "whci",
+	.id_table = whci_id_table,
+	.probe    = whci_probe,
+	.remove   = whci_remove,
+};
+
+static int __init whci_init(void)
+{
+	return pci_register_driver(&whci_driver);
+}
+
+static void __exit whci_exit(void)
+{
+	pci_unregister_driver(&whci_driver);
+}
+
+module_init(whci_init);
+module_exit(whci_exit);
+
+MODULE_DESCRIPTION("WHCI UWB Multi-interface Controller enumerator");
+MODULE_AUTHOR("Cambridge Silicon Radio Ltd.");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/uwb/whci.h b/include/linux/uwb/whci.h
new file mode 100644
index 000000000000..915ec23042d4
--- /dev/null
+++ b/include/linux/uwb/whci.h
@@ -0,0 +1,117 @@
+/*
+ * Wireless Host Controller Interface for Ultra-Wide-Band and Wireless USB
+ *
+ * Copyright (C) 2005-2006 Intel Corporation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
+ *
+ *
+ * References:
+ *   [WHCI] Wireless Host Controller Interface Specification for
+ *          Certified Wireless Universal Serial Bus, revision 0.95.
+ */
+#ifndef _LINUX_UWB_WHCI_H_
+#define _LINUX_UWB_WHCI_H_
+
+#include <linux/pci.h>
+
+/*
+ * UWB interface capability registers (offsets from UWBBASE)
+ *
+ * [WHCI] section 2.2
+ */
+#define UWBCAPINFO	0x00 /* == UWBCAPDATA(0) */
+#  define UWBCAPINFO_TO_N_CAPS(c)	(((c) >> 0)  & 0xFull)
+#define UWBCAPDATA(n)	(8*(n))
+#  define UWBCAPDATA_TO_VERSION(c)	(((c) >> 32) & 0xFFFFull)
+#  define UWBCAPDATA_TO_OFFSET(c)	(((c) >> 18) & 0x3FFFull)
+#  define UWBCAPDATA_TO_BAR(c)		(((c) >> 16) & 0x3ull)
+#  define UWBCAPDATA_TO_SIZE(c)		((((c) >> 8) & 0xFFull) * sizeof(u32))
+#  define UWBCAPDATA_TO_CAP_ID(c)	(((c) >> 0)  & 0xFFull)
+
+/* Size of the WHCI capability data (including the RC capability) for
+   a device with n capabilities. */
+#define UWBCAPDATA_SIZE(n) (8 + 8*(n))
+
+
+/*
+ * URC registers (offsets from URCBASE)
+ *
+ * [WHCI] section 2.3
+ */
+#define URCCMD		0x00
+#  define URCCMD_RESET		(1 << 31)  /* UMC Hardware reset */
+#  define URCCMD_RS		(1 << 30)  /* Run/Stop */
+#  define URCCMD_EARV		(1 << 29)  /* Event Address Register Valid */
+#  define URCCMD_ACTIVE		(1 << 15)  /* Command is active */
+#  define URCCMD_IWR		(1 << 14)  /* Interrupt When Ready */
+#  define URCCMD_SIZE_MASK	0x00000fff /* Command size mask */
+#define URCSTS		0x04
+#  define URCSTS_EPS		(1 << 17)  /* Event Processing Status */
+#  define URCSTS_HALTED		(1 << 16)  /* RC halted */
+#  define URCSTS_HSE		(1 << 10)  /* Host System Error...fried */
+#  define URCSTS_ER		(1 <<  9)  /* Event Ready */
+#  define URCSTS_RCI		(1 <<  8)  /* Ready for Command Interrupt */
+#  define URCSTS_INT_MASK	0x00000700 /* URC interrupt sources */
+#  define URCSTS_ISI		0x000000ff /* Interrupt Source Identification */
+#define URCINTR		0x08
+#  define URCINTR_EN_ALL	0x000007ff /* Enable all interrupt sources */
+#define URCCMDADDR	0x10
+#define URCEVTADDR	0x18
+#  define URCEVTADDR_OFFSET_MASK 0xfff    /* Event pointer offset mask */
+
+
+/** Write 32 bit @value to little endian register at @addr */
+static inline
+void le_writel(u32 value, void __iomem *addr)
+{
+	iowrite32(value, addr);
+}
+
+
+/** Read from 32 bit little endian register at @addr */
+static inline
+u32 le_readl(void __iomem *addr)
+{
+	return ioread32(addr);
+}
+
+
+/** Write 64 bit @value to little endian register at @addr */
+static inline
+void le_writeq(u64 value, void __iomem *addr)
+{
+	iowrite32(value, addr);
+	iowrite32(value >> 32, addr + 4);
+}
+
+
+/** Read from 64 bit little endian register at @addr */
+static inline
+u64 le_readq(void __iomem *addr)
+{
+	u64 value;
+	value  = ioread32(addr);
+	value |= (u64)ioread32(addr + 4) << 32;
+	return value;
+}
+
+extern int whci_wait_for(struct device *dev, u32 __iomem *reg,
+			 u32 mask, u32 result,
+			 unsigned long max_ms,  const char *tag);
+
+#endif /* #ifndef _LINUX_UWB_WHCI_H_ */
-- 
cgit v1.2.3


From c7f736484f8ecde4dc1bc8459179c4d65f2ccbe4 Mon Sep 17 00:00:00 2001
From: Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
Date: Wed, 17 Sep 2008 16:34:22 +0100
Subject: wusb: add the Wireless USB include files.

Common header files derived from the WUSB 1.0 specification.

Signed-off-by: David Vrabel <david.vrabel@csr.com>
---
 include/linux/usb/wusb-wa.h | 271 +++++++++++++++++++++++++++++++
 include/linux/usb/wusb.h    | 376 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 647 insertions(+)
 create mode 100644 include/linux/usb/wusb-wa.h
 create mode 100644 include/linux/usb/wusb.h

(limited to 'include')

diff --git a/include/linux/usb/wusb-wa.h b/include/linux/usb/wusb-wa.h
new file mode 100644
index 000000000000..a102561e7026
--- /dev/null
+++ b/include/linux/usb/wusb-wa.h
@@ -0,0 +1,271 @@
+/*
+ * Wireless USB Wire Adapter constants and structures.
+ *
+ * Copyright (C) 2005-2006 Intel Corporation.
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
+ *
+ * FIXME: docs
+ * FIXME: organize properly, group logically
+ *
+ * All the event structures are defined in uwb/spec.h, as they are
+ * common to the WHCI and WUSB radio control interfaces.
+ *
+ * References:
+ *   [WUSB] Wireless Universal Serial Bus Specification, revision 1.0, ch8
+ */
+#ifndef __LINUX_USB_WUSB_WA_H
+#define __LINUX_USB_WUSB_WA_H
+
+/**
+ * Radio Command Request for the Radio Control Interface
+ *
+ * Radio Control Interface command and event codes are the same as
+ * WHCI, and listed in include/linux/uwb.h:UWB_RC_{CMD,EVT}_*
+ */
+enum {
+	WA_EXEC_RC_CMD = 40,	/* Radio Control command Request */
+};
+
+/* Wireless Adapter Requests ([WUSB] table 8-51) */
+enum {
+	WUSB_REQ_ADD_MMC_IE     = 20,
+	WUSB_REQ_REMOVE_MMC_IE  = 21,
+	WUSB_REQ_SET_NUM_DNTS   = 22,
+	WUSB_REQ_SET_CLUSTER_ID = 23,
+	WUSB_REQ_SET_DEV_INFO   = 24,
+	WUSB_REQ_GET_TIME       = 25,
+	WUSB_REQ_SET_STREAM_IDX = 26,
+	WUSB_REQ_SET_WUSB_MAS   = 27,
+};
+
+
+/* Wireless Adapter WUSB Channel Time types ([WUSB] table 8-52) */
+enum {
+	WUSB_TIME_ADJ   = 0,
+	WUSB_TIME_BPST  = 1,
+	WUSB_TIME_WUSB  = 2,
+};
+
+enum {
+	WA_ENABLE = 0x01,
+	WA_RESET = 0x02,
+	RPIPE_PAUSE = 0x1,
+};
+
+/* Responses from Get Status request ([WUSB] section 8.3.1.6) */
+enum {
+	WA_STATUS_ENABLED = 0x01,
+	WA_STATUS_RESETTING = 0x02
+};
+
+enum rpipe_crs {
+	RPIPE_CRS_CTL = 0x01,
+	RPIPE_CRS_ISO = 0x02,
+	RPIPE_CRS_BULK = 0x04,
+	RPIPE_CRS_INTR = 0x08
+};
+
+/**
+ * RPipe descriptor ([WUSB] section 8.5.2.11)
+ *
+ * FIXME: explain rpipes
+ */
+struct usb_rpipe_descriptor {
+	u8 	bLength;
+	u8	bDescriptorType;
+	__le16  wRPipeIndex;
+	__le16	wRequests;
+	__le16	wBlocks;		/* rw if 0 */
+	__le16	wMaxPacketSize;		/* rw? */
+	u8	bHSHubAddress;		/* reserved: 0 */
+	u8	bHSHubPort;		/* ??? FIXME ??? */
+	u8	bSpeed;			/* rw: xfer rate 'enum uwb_phy_rate' */
+	u8	bDeviceAddress;		/* rw: Target device address */
+	u8	bEndpointAddress;	/* rw: Target EP address */
+	u8	bDataSequence;		/* ro: Current Data sequence */
+	__le32	dwCurrentWindow;	/* ro */
+	u8	bMaxDataSequence;	/* ro?: max supported seq */
+	u8	bInterval;		/* rw:  */
+	u8	bOverTheAirInterval;	/* rw:  */
+	u8	bmAttribute;		/* ro?  */
+	u8	bmCharacteristics;	/* ro? enum rpipe_attr, supported xsactions */
+	u8	bmRetryOptions;		/* rw? */
+	__le16	wNumTransactionErrors;	/* rw */
+} __attribute__ ((packed));
+
+/**
+ * Wire Adapter Notification types ([WUSB] sections 8.4.5 & 8.5.4)
+ *
+ * These are the notifications coming on the notification endpoint of
+ * an HWA and a DWA.
+ */
+enum wa_notif_type {
+	DWA_NOTIF_RWAKE = 0x91,
+	DWA_NOTIF_PORTSTATUS = 0x92,
+	WA_NOTIF_TRANSFER = 0x93,
+	HWA_NOTIF_BPST_ADJ = 0x94,
+	HWA_NOTIF_DN = 0x95,
+};
+
+/**
+ * Wire Adapter notification header
+ *
+ * Notifications coming from a wire adapter use a common header
+ * defined in [WUSB] sections 8.4.5 & 8.5.4.
+ */
+struct wa_notif_hdr {
+	u8 bLength;
+	u8 bNotifyType;			/* enum wa_notif_type */
+} __attribute__((packed));
+
+/**
+ * HWA DN Received notification [(WUSB] section 8.5.4.2)
+ *
+ * The DNData is specified in WUSB1.0[7.6]. For each device
+ * notification we received, we just need to dispatch it.
+ *
+ * @dndata:  this is really an array of notifications, but all start
+ *           with the same header.
+ */
+struct hwa_notif_dn {
+	struct wa_notif_hdr hdr;
+	u8 bSourceDeviceAddr;		/* from errata 2005/07 */
+	u8 bmAttributes;
+	struct wusb_dn_hdr dndata[];
+} __attribute__((packed));
+
+/* [WUSB] section 8.3.3 */
+enum wa_xfer_type {
+	WA_XFER_TYPE_CTL = 0x80,
+	WA_XFER_TYPE_BI = 0x81,		/* bulk/interrupt */
+	WA_XFER_TYPE_ISO = 0x82,
+	WA_XFER_RESULT = 0x83,
+	WA_XFER_ABORT = 0x84,
+};
+
+/* [WUSB] section 8.3.3 */
+struct wa_xfer_hdr {
+	u8 bLength;			/* 0x18 */
+	u8 bRequestType;		/* 0x80 WA_REQUEST_TYPE_CTL */
+	__le16 wRPipe;			/* RPipe index */
+	__le32 dwTransferID;		/* Host-assigned ID */
+	__le32 dwTransferLength;	/* Length of data to xfer */
+	u8 bTransferSegment;
+} __attribute__((packed));
+
+struct wa_xfer_ctl {
+	struct wa_xfer_hdr hdr;
+	u8 bmAttribute;
+	__le16 wReserved;
+	struct usb_ctrlrequest baSetupData;
+} __attribute__((packed));
+
+struct wa_xfer_bi {
+	struct wa_xfer_hdr hdr;
+	u8 bReserved;
+	__le16 wReserved;
+} __attribute__((packed));
+
+struct wa_xfer_hwaiso {
+	struct wa_xfer_hdr hdr;
+	u8 bReserved;
+	__le16 wPresentationTime;
+	__le32 dwNumOfPackets;
+	/* FIXME: u8 pktdata[]? */
+} __attribute__((packed));
+
+/* [WUSB] section 8.3.3.5 */
+struct wa_xfer_abort {
+	u8 bLength;
+	u8 bRequestType;
+	__le16 wRPipe;			/* RPipe index */
+	__le32 dwTransferID;		/* Host-assigned ID */
+} __attribute__((packed));
+
+/**
+ * WA Transfer Complete notification ([WUSB] section 8.3.3.3)
+ *
+ */
+struct wa_notif_xfer {
+	struct wa_notif_hdr hdr;
+	u8 bEndpoint;
+	u8 Reserved;
+} __attribute__((packed));
+
+/** Transfer result basic codes [WUSB] table 8-15 */
+enum {
+	WA_XFER_STATUS_SUCCESS,
+	WA_XFER_STATUS_HALTED,
+	WA_XFER_STATUS_DATA_BUFFER_ERROR,
+	WA_XFER_STATUS_BABBLE,
+	WA_XFER_RESERVED,
+	WA_XFER_STATUS_NOT_FOUND,
+	WA_XFER_STATUS_INSUFFICIENT_RESOURCE,
+	WA_XFER_STATUS_TRANSACTION_ERROR,
+	WA_XFER_STATUS_ABORTED,
+	WA_XFER_STATUS_RPIPE_NOT_READY,
+	WA_XFER_INVALID_FORMAT,
+	WA_XFER_UNEXPECTED_SEGMENT_NUMBER,
+	WA_XFER_STATUS_RPIPE_TYPE_MISMATCH,
+};
+
+/** [WUSB] section 8.3.3.4 */
+struct wa_xfer_result {
+	struct wa_notif_hdr hdr;
+	__le32 dwTransferID;
+	__le32 dwTransferLength;
+	u8     bTransferSegment;
+	u8     bTransferStatus;
+	__le32 dwNumOfPackets;
+} __attribute__((packed));
+
+/**
+ * Wire Adapter Class Descriptor ([WUSB] section 8.5.2.7).
+ *
+ * NOTE: u16 fields are read Little Endian from the hardware.
+ *
+ * @bNumPorts is the original max number of devices that the host can
+ *            connect; we might chop this so the stack can handle
+ *            it. In case you need to access it, use wusbhc->ports_max
+ *            if it is a Wireless USB WA.
+ */
+struct usb_wa_descriptor {
+	u8	bLength;
+	u8	bDescriptorType;
+	u16	bcdWAVersion;
+	u8	bNumPorts;		/* don't use!! */
+	u8	bmAttributes;		/* Reserved == 0 */
+	u16	wNumRPipes;
+	u16	wRPipeMaxBlock;
+	u8	bRPipeBlockSize;
+	u8	bPwrOn2PwrGood;
+	u8	bNumMMCIEs;
+	u8	DeviceRemovable;	/* FIXME: in DWA this is up to 16 bytes */
+} __attribute__((packed));
+
+/**
+ * HWA Device Information Buffer (WUSB1.0[T8.54])
+ */
+struct hwa_dev_info {
+	u8	bmDeviceAvailability[32];       /* FIXME: ignored for now */
+	u8	bDeviceAddress;
+	__le16	wPHYRates;
+	u8	bmDeviceAttribute;
+} __attribute__((packed));
+
+#endif /* #ifndef __LINUX_USB_WUSB_WA_H */
diff --git a/include/linux/usb/wusb.h b/include/linux/usb/wusb.h
new file mode 100644
index 000000000000..5f401b644ed5
--- /dev/null
+++ b/include/linux/usb/wusb.h
@@ -0,0 +1,376 @@
+/*
+ * Wireless USB Standard Definitions
+ * Event Size Tables
+ *
+ * Copyright (C) 2005-2006 Intel Corporation
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301, USA.
+ *
+ *
+ * FIXME: docs
+ * FIXME: organize properly, group logically
+ *
+ * All the event structures are defined in uwb/spec.h, as they are
+ * common to the WHCI and WUSB radio control interfaces.
+ */
+
+#ifndef __WUSB_H__
+#define __WUSB_H__
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/uwb/spec.h>
+#include <linux/usb/ch9.h>
+#include <linux/param.h>
+
+/**
+ * WUSB Information Element header
+ *
+ * I don't know why, they decided to make it different to the MBOA MAC
+ * IE Header; beats me.
+ */
+struct wuie_hdr {
+	u8 bLength;
+	u8 bIEIdentifier;
+} __attribute__((packed));
+
+enum {
+	WUIE_ID_WCTA = 0x80,
+	WUIE_ID_CONNECTACK,
+	WUIE_ID_HOST_INFO,
+	WUIE_ID_CHANGE_ANNOUNCE,
+	WUIE_ID_DEVICE_DISCONNECT,
+	WUIE_ID_HOST_DISCONNECT,
+	WUIE_ID_KEEP_ALIVE = 0x89,
+	WUIE_ID_ISOCH_DISCARD,
+	WUIE_ID_RESET_DEVICE,
+};
+
+/**
+ * Maximum number of array elements in a WUSB IE.
+ *
+ * WUSB1.0[7.5 before table 7-38] says that in WUSB IEs that
+ * are "arrays" have to limited to 4 elements. So we define it
+ * like that to ease up and submit only the neeed size.
+ */
+#define WUIE_ELT_MAX 4
+
+/**
+ * Wrapper for the data that defines a CHID, a CDID or a CK
+ *
+ * WUSB defines that CHIDs, CDIDs and CKs are a 16 byte string of
+ * data. In order to avoid confusion and enforce types, we wrap it.
+ *
+ * Make it packed, as we use it in some hw defintions.
+ */
+struct wusb_ckhdid {
+	u8 data[16];
+} __attribute__((packed));
+
+const static
+struct wusb_ckhdid wusb_ckhdid_zero = { .data = { 0 } };
+
+#define WUSB_CKHDID_STRSIZE (3 * sizeof(struct wusb_ckhdid) + 1)
+
+/**
+ * WUSB IE: Host Information (WUSB1.0[7.5.2])
+ *
+ * Used to provide information about the host to the Wireless USB
+ * devices in range (CHID can be used as an ASCII string).
+ */
+struct wuie_host_info {
+	struct wuie_hdr hdr;
+	__le16 attributes;
+	struct wusb_ckhdid CHID;
+} __attribute__((packed));
+
+/**
+ * WUSB IE: Connect Ack (WUSB1.0[7.5.1])
+ *
+ * Used to acknowledge device connect requests. See note for
+ * WUIE_ELT_MAX.
+ */
+struct wuie_connect_ack {
+	struct wuie_hdr hdr;
+	struct {
+		struct wusb_ckhdid CDID;
+		u8 bDeviceAddress;	/* 0 means unused */
+		u8 bReserved;
+	} blk[WUIE_ELT_MAX];
+} __attribute__((packed));
+
+/**
+ * WUSB IE Host Information Element, Connect Availability
+ *
+ * WUSB1.0[7.5.2], bmAttributes description
+ */
+enum {
+	WUIE_HI_CAP_RECONNECT = 0,
+	WUIE_HI_CAP_LIMITED,
+	WUIE_HI_CAP_RESERVED,
+	WUIE_HI_CAP_ALL,
+};
+
+/**
+ * WUSB IE: Channel Stop (WUSB1.0[7.5.8])
+ *
+ * Tells devices the host is going to stop sending MMCs and will dissapear.
+ */
+struct wuie_channel_stop {
+	struct wuie_hdr hdr;
+	u8 attributes;
+	u8 timestamp[3];
+} __attribute__((packed));
+
+/**
+ * WUSB IE: Keepalive (WUSB1.0[7.5.9])
+ *
+ * Ask device(s) to send keepalives.
+ */
+struct wuie_keep_alive {
+	struct wuie_hdr hdr;
+	u8 bDeviceAddress[WUIE_ELT_MAX];
+} __attribute__((packed));
+
+/**
+ * WUSB IE: Reset device (WUSB1.0[7.5.11])
+ *
+ * Tell device to reset; in all truth, we can fit 4 CDIDs, but we only
+ * use it for one at the time...
+ *
+ * In any case, this request is a wee bit silly: why don't they target
+ * by address??
+ */
+struct wuie_reset {
+	struct wuie_hdr hdr;
+	struct wusb_ckhdid CDID;
+} __attribute__((packed));
+
+/**
+ * WUSB IE: Disconnect device (WUSB1.0[7.5.11])
+ *
+ * Tell device to disconnect; we can fit 4 addresses, but we only use
+ * it for one at the time...
+ */
+struct wuie_disconnect {
+	struct wuie_hdr hdr;
+	u8 bDeviceAddress;
+	u8 padding;
+} __attribute__((packed));
+
+/**
+ * WUSB IE: Host disconnect ([WUSB] section 7.5.5)
+ *
+ * Tells all connected devices to disconnect.
+ */
+struct wuie_host_disconnect {
+	struct wuie_hdr hdr;
+} __attribute__((packed));
+
+/**
+ * WUSB Device Notification header (WUSB1.0[7.6])
+ */
+struct wusb_dn_hdr {
+	u8 bType;
+	u8 notifdata[];
+} __attribute__((packed));
+
+/** Device Notification codes (WUSB1.0[Table 7-54]) */
+enum WUSB_DN {
+	WUSB_DN_CONNECT = 0x01,
+	WUSB_DN_DISCONNECT = 0x02,
+	WUSB_DN_EPRDY = 0x03,
+	WUSB_DN_MASAVAILCHANGED = 0x04,
+	WUSB_DN_RWAKE = 0x05,
+	WUSB_DN_SLEEP = 0x06,
+	WUSB_DN_ALIVE = 0x07,
+};
+
+/** WUSB Device Notification Connect */
+struct wusb_dn_connect {
+	struct wusb_dn_hdr hdr;
+	__le16 attributes;
+	struct wusb_ckhdid CDID;
+} __attribute__((packed));
+
+static inline int wusb_dn_connect_prev_dev_addr(const struct wusb_dn_connect *dn)
+{
+	return le16_to_cpu(dn->attributes) & 0xff;
+}
+
+static inline int wusb_dn_connect_new_connection(const struct wusb_dn_connect *dn)
+{
+	return (le16_to_cpu(dn->attributes) >> 8) & 0x1;
+}
+
+static inline int wusb_dn_connect_beacon_behavior(const struct wusb_dn_connect *dn)
+{
+	return (le16_to_cpu(dn->attributes) >> 9) & 0x03;
+}
+
+/** Device is alive (aka: pong) (WUSB1.0[7.6.7]) */
+struct wusb_dn_alive {
+	struct wusb_dn_hdr hdr;
+} __attribute__((packed));
+
+/** Device is disconnecting (WUSB1.0[7.6.2]) */
+struct wusb_dn_disconnect {
+	struct wusb_dn_hdr hdr;
+} __attribute__((packed));
+
+/* General constants */
+enum {
+	WUSB_TRUST_TIMEOUT_MS = 4000,	/* [WUSB] section 4.15.1 */
+};
+
+static inline size_t ckhdid_printf(char *pr_ckhdid, size_t size,
+				   const struct wusb_ckhdid *ckhdid)
+{
+	return scnprintf(pr_ckhdid, size,
+			 "%02hx %02hx %02hx %02hx %02hx %02hx %02hx %02hx "
+			 "%02hx %02hx %02hx %02hx %02hx %02hx %02hx %02hx",
+			 ckhdid->data[0],  ckhdid->data[1],
+			 ckhdid->data[2],  ckhdid->data[3],
+			 ckhdid->data[4],  ckhdid->data[5],
+			 ckhdid->data[6],  ckhdid->data[7],
+			 ckhdid->data[8],  ckhdid->data[9],
+			 ckhdid->data[10], ckhdid->data[11],
+			 ckhdid->data[12], ckhdid->data[13],
+			 ckhdid->data[14], ckhdid->data[15]);
+}
+
+/*
+ * WUSB Crypto stuff (WUSB1.0[6])
+ */
+
+extern const char *wusb_et_name(u8);
+
+/**
+ * WUSB key index WUSB1.0[7.3.2.4], for usage when setting keys for
+ * the host or the device.
+ */
+static inline u8 wusb_key_index(int index, int type, int originator)
+{
+	return (originator << 6) | (type << 4) | index;
+}
+
+#define WUSB_KEY_INDEX_TYPE_PTK			0 /* for HWA only */
+#define WUSB_KEY_INDEX_TYPE_ASSOC		1
+#define WUSB_KEY_INDEX_TYPE_GTK			2
+#define WUSB_KEY_INDEX_ORIGINATOR_HOST		0
+#define WUSB_KEY_INDEX_ORIGINATOR_DEVICE	1
+
+/* A CCM Nonce, defined in WUSB1.0[6.4.1] */
+struct aes_ccm_nonce {
+	u8 sfn[6];              /* Little Endian */
+	u8 tkid[3];             /* LE */
+	struct uwb_dev_addr dest_addr;
+	struct uwb_dev_addr src_addr;
+} __attribute__((packed));
+
+/* A CCM operation label, defined on WUSB1.0[6.5.x] */
+struct aes_ccm_label {
+	u8 data[14];
+} __attribute__((packed));
+
+/*
+ * Input to the key derivation sequence defined in
+ * WUSB1.0[6.5.1]. Rest of the data is in the CCM Nonce passed to the
+ * PRF function.
+ */
+struct wusb_keydvt_in {
+	u8 hnonce[16];
+	u8 dnonce[16];
+} __attribute__((packed));
+
+/*
+ * Output from the key derivation sequence defined in
+ * WUSB1.0[6.5.1].
+ */
+struct wusb_keydvt_out {
+	u8 kck[16];
+	u8 ptk[16];
+} __attribute__((packed));
+
+/* Pseudo Random Function WUSB1.0[6.5] */
+extern int wusb_crypto_init(void);
+extern void wusb_crypto_exit(void);
+extern ssize_t wusb_prf(void *out, size_t out_size,
+			const u8 key[16], const struct aes_ccm_nonce *_n,
+			const struct aes_ccm_label *a,
+			const void *b, size_t blen, size_t len);
+
+static inline int wusb_prf_64(void *out, size_t out_size, const u8 key[16],
+			      const struct aes_ccm_nonce *n,
+			      const struct aes_ccm_label *a,
+			      const void *b, size_t blen)
+{
+	return wusb_prf(out, out_size, key, n, a, b, blen, 64);
+}
+
+static inline int wusb_prf_128(void *out, size_t out_size, const u8 key[16],
+			       const struct aes_ccm_nonce *n,
+			       const struct aes_ccm_label *a,
+			       const void *b, size_t blen)
+{
+	return wusb_prf(out, out_size, key, n, a, b, blen, 128);
+}
+
+static inline int wusb_prf_256(void *out, size_t out_size, const u8 key[16],
+			       const struct aes_ccm_nonce *n,
+			       const struct aes_ccm_label *a,
+			       const void *b, size_t blen)
+{
+	return wusb_prf(out, out_size, key, n, a, b, blen, 256);
+}
+
+/* Key derivation WUSB1.0[6.5.1] */
+static inline int wusb_key_derive(struct wusb_keydvt_out *keydvt_out,
+				  const u8 key[16],
+				  const struct aes_ccm_nonce *n,
+				  const struct wusb_keydvt_in *keydvt_in)
+{
+	const struct aes_ccm_label a = { .data = "Pair-wise keys" };
+	return wusb_prf_256(keydvt_out, sizeof(*keydvt_out), key, n, &a,
+			    keydvt_in, sizeof(*keydvt_in));
+}
+
+/*
+ * Out-of-band MIC Generation WUSB1.0[6.5.2]
+ *
+ * Compute the MIC over @key, @n and @hs and place it in @mic_out.
+ *
+ * @mic_out:  Where to place the 8 byte MIC tag
+ * @key:      KCK from the derivation process
+ * @n:        CCM nonce, n->sfn == 0, TKID as established in the
+ *            process.
+ * @hs:       Handshake struct for phase 2 of the 4-way.
+ *            hs->bStatus and hs->bReserved are zero.
+ *            hs->bMessageNumber is 2 (WUSB1.0[7.3.2.5.2]
+ *            hs->dest_addr is the device's USB address padded with 0
+ *            hs->src_addr is the hosts's UWB device address
+ *            hs->mic is ignored (as we compute that value).
+ */
+static inline int wusb_oob_mic(u8 mic_out[8], const u8 key[16],
+			       const struct aes_ccm_nonce *n,
+			       const struct usb_handshake *hs)
+{
+	const struct aes_ccm_label a = { .data = "out-of-bandMIC" };
+	return wusb_prf_64(mic_out, 8, key, n, &a,
+			   hs, sizeof(*hs) - sizeof(hs->MIC));
+}
+
+#endif /* #ifndef __WUSB_H__ */
-- 
cgit v1.2.3


From b60066c141997ac2e4ef08459b75638ae86ae781 Mon Sep 17 00:00:00 2001
From: David Vrabel <david.vrabel@csr.com>
Date: Wed, 17 Sep 2008 16:34:40 +0100
Subject: uwb: add symlinks in sysfs between radio controllers and PALs

Add a facility for PALs to have symlinks to their radio controller
(and vice-versa) and make WUSB host controllers use this.

Signed-off-by: David Vrabel <david.vrabel@csr.com>
---
 drivers/usb/wusbcore/pal.c    |  3 +++
 drivers/usb/wusbcore/wusbhc.c | 16 +++++++++-------
 drivers/uwb/pal.c             | 20 ++++++++++++++++++++
 include/linux/uwb.h           |  6 +++++-
 4 files changed, 37 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/wusbcore/pal.c b/drivers/usb/wusbcore/pal.c
index cc126b444734..7cc51e9905cf 100644
--- a/drivers/usb/wusbcore/pal.c
+++ b/drivers/usb/wusbcore/pal.c
@@ -26,6 +26,9 @@ int wusbhc_pal_register(struct wusbhc *wusbhc)
 {
 	uwb_pal_init(&wusbhc->pal);
 
+	wusbhc->pal.name   = "wusbhc";
+	wusbhc->pal.device = wusbhc->usb_hcd.self.controller;
+
 	return uwb_pal_register(wusbhc->uwb_rc, &wusbhc->pal);
 }
 
diff --git a/drivers/usb/wusbcore/wusbhc.c b/drivers/usb/wusbcore/wusbhc.c
index 1149b1e59c86..07c63a31c799 100644
--- a/drivers/usb/wusbcore/wusbhc.c
+++ b/drivers/usb/wusbcore/wusbhc.c
@@ -192,13 +192,8 @@ int wusbhc_create(struct wusbhc *wusbhc)
 	result = wusbhc_sec_create(wusbhc);
 	if (result < 0)
 		goto error_sec_create;
-	result = wusbhc_pal_register(wusbhc);
-	if (result < 0)
-		goto error_pal_register;
 	return 0;
 
-error_pal_register:
-	wusbhc_sec_destroy(wusbhc);
 error_sec_create:
 	wusbhc_rh_destroy(wusbhc);
 error_rh_create:
@@ -235,7 +230,14 @@ int wusbhc_b_create(struct wusbhc *wusbhc)
 		dev_err(dev, "Cannot register WUSBHC attributes: %d\n", result);
 		goto error_create_attr_group;
 	}
-	/* Yep, I plan to add stuff here... */
+
+	result = wusbhc_pal_register(wusbhc);
+	if (result < 0)
+		goto error_pal_register;
+	return 0;
+
+error_pal_register:
+	sysfs_remove_group(wusbhc_kobj(wusbhc), &wusbhc_attr_group);
 error_create_attr_group:
 	return result;
 }
@@ -243,13 +245,13 @@ EXPORT_SYMBOL_GPL(wusbhc_b_create);
 
 void wusbhc_b_destroy(struct wusbhc *wusbhc)
 {
+	wusbhc_pal_unregister(wusbhc);
 	sysfs_remove_group(wusbhc_kobj(wusbhc), &wusbhc_attr_group);
 }
 EXPORT_SYMBOL_GPL(wusbhc_b_destroy);
 
 void wusbhc_destroy(struct wusbhc *wusbhc)
 {
-	wusbhc_pal_unregister(wusbhc);
 	wusbhc_sec_destroy(wusbhc);
 	wusbhc_rh_destroy(wusbhc);
 	wusbhc_devconnect_destroy(wusbhc);
diff --git a/drivers/uwb/pal.c b/drivers/uwb/pal.c
index 5508993a820e..1afb38eacb9a 100644
--- a/drivers/uwb/pal.c
+++ b/drivers/uwb/pal.c
@@ -39,6 +39,21 @@ EXPORT_SYMBOL_GPL(uwb_pal_init);
  */
 int uwb_pal_register(struct uwb_rc *rc, struct uwb_pal *pal)
 {
+	int ret;
+
+	if (pal->device) {
+		ret = sysfs_create_link(&pal->device->kobj,
+					&rc->uwb_dev.dev.kobj, "uwb_rc");
+		if (ret < 0)
+			return ret;
+		ret = sysfs_create_link(&rc->uwb_dev.dev.kobj,
+					&pal->device->kobj, pal->name);
+		if (ret < 0) {
+			sysfs_remove_link(&pal->device->kobj, "uwb_rc");
+			return ret;
+		}
+	}
+
 	spin_lock(&rc->pal_lock);
 	list_add(&pal->node, &rc->pals);
 	spin_unlock(&rc->pal_lock);
@@ -57,6 +72,11 @@ void uwb_pal_unregister(struct uwb_rc *rc, struct uwb_pal *pal)
 	spin_lock(&rc->pal_lock);
 	list_del(&pal->node);
 	spin_unlock(&rc->pal_lock);
+
+	if (pal->device) {
+		sysfs_remove_link(&rc->uwb_dev.dev.kobj, pal->name);
+		sysfs_remove_link(&pal->device->kobj, "uwb_rc");
+	}
 }
 EXPORT_SYMBOL_GPL(uwb_pal_unregister);
 
diff --git a/include/linux/uwb.h b/include/linux/uwb.h
index 0cd35937e120..f9ccbd9a2ced 100644
--- a/include/linux/uwb.h
+++ b/include/linux/uwb.h
@@ -361,6 +361,9 @@ struct uwb_rc {
 
 /**
  * struct uwb_pal - a UWB PAL
+ * @name:    descriptive name for this PAL (wushc, wlp, etc.).
+ * @device:  a device for the PAL.  Used to link the PAL and the radio
+ *           controller in sysfs.
  * @new_rsv: called when a peer requests a reservation (may be NULL if
  *           the PAL cannot accept reservation requests).
  *
@@ -379,7 +382,8 @@ struct uwb_rc {
  */
 struct uwb_pal {
 	struct list_head node;
-
+	const char *name;
+	struct device *device;
 	void (*new_rsv)(struct uwb_rsv *rsv);
 };
 
-- 
cgit v1.2.3


From d7cfb60c5cf904ecf1e0ae23ec178175b86f0d4a Mon Sep 17 00:00:00 2001
From: Mark McLoughlin <markmc@redhat.com>
Date: Fri, 19 Sep 2008 13:13:44 +0100
Subject: hrtimer: remove hrtimer_clock_base::get_softirq_time()

Peter Zijlstra noticed this 8 months ago and I just noticed
it again.

hrtimer_clock_base::get_softirq_time() is currently unused
in the entire tree. In fact, looking at the logs, it appears
as if it was never used. Remove it.

Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/hrtimer.h | 2 --
 kernel/hrtimer.c        | 4 +---
 2 files changed, 1 insertion(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 6d93dce61cbb..1b079bd29c35 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -145,7 +145,6 @@ struct hrtimer_sleeper {
  * @first:		pointer to the timer node which expires first
  * @resolution:		the resolution of the clock, in nanoseconds
  * @get_time:		function to retrieve the current time of the clock
- * @get_softirq_time:	function to retrieve the current time from the softirq
  * @softirq_time:	the time when running the hrtimer queue in the softirq
  * @offset:		offset of this clock to the monotonic base
  * @reprogram:		function to reprogram the timer event
@@ -157,7 +156,6 @@ struct hrtimer_clock_base {
 	struct rb_node		*first;
 	ktime_t			resolution;
 	ktime_t			(*get_time)(void);
-	ktime_t			(*get_softirq_time)(void);
 	ktime_t			softirq_time;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	ktime_t			offset;
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index 03ea1378c43b..4d761d50c529 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -1401,9 +1401,7 @@ void hrtimer_run_queues(void)
 		if (!base->first)
 			continue;
 
-		if (base->get_softirq_time)
-			base->softirq_time = base->get_softirq_time();
-		else if (gettime) {
+		if (gettime) {
 			hrtimer_get_softirq_time(cpu_base);
 			gettime = 0;
 		}
-- 
cgit v1.2.3


From b91c4996df56fcd201f85c392a1de7bc3f6641f5 Mon Sep 17 00:00:00 2001
From: Mark McLoughlin <markmc@redhat.com>
Date: Fri, 19 Sep 2008 13:13:48 +0100
Subject: hrtimer: remove hrtimer_clock_base::reprogram()

hrtimer_clock_base::reprogram() also appears to never
have been used, so remove it.

Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/hrtimer.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 1b079bd29c35..68b0196d8696 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -147,7 +147,6 @@ struct hrtimer_sleeper {
  * @get_time:		function to retrieve the current time of the clock
  * @softirq_time:	the time when running the hrtimer queue in the softirq
  * @offset:		offset of this clock to the monotonic base
- * @reprogram:		function to reprogram the timer event
  */
 struct hrtimer_clock_base {
 	struct hrtimer_cpu_base	*cpu_base;
@@ -159,9 +158,6 @@ struct hrtimer_clock_base {
 	ktime_t			softirq_time;
 #ifdef CONFIG_HIGH_RES_TIMERS
 	ktime_t			offset;
-	int			(*reprogram)(struct hrtimer *t,
-					     struct hrtimer_clock_base *b,
-					     ktime_t n);
 #endif
 };
 
-- 
cgit v1.2.3


From a0ad05c75aa362c91f4d9cd91ff375a739574dd8 Mon Sep 17 00:00:00 2001
From: Thomas Renninger <trenn@suse.de>
Date: Mon, 1 Sep 2008 14:27:02 +0200
Subject: Introduce FW_BUG, FW_WARN and FW_INFO to consistenly tell users about
 BIOS bugs

The idea is to add this to printk after the severity:
printk(KERN_ERR FW_BUG "This is not our fault, BIOS developer: fix it by
simply add ...\n");

If a Firmware issue should be hidden, because it is
work-arounded, but you still want to see something popping up e.g.
for info only:
printk(KERN_INFO FW_INFO "This is done stupid, we can handle it,
but it should better be avoided in future\n");

or on the Linuxfirmwarekit to tell vendors that they did something
stupid or wrong without bothering the user:
printk(KERN_INFO FW_BUG "This is done stupid, we can handle it,
but it should better be avoided in future\n");

Some use cases:
  - If a user sees a [Firmware Bug] message in the kernel
    he should first update the BIOS before wasting time with
    debugging and submiting on old firmware code to mailing
    lists.

  - The linuxfirmwarekit (http://www.linuxfirmwarekit.org)
    tries to detect firmware bugs. It currently is doing that
    in userspace which results in:
        - Huge test scripts that could be a one liner in the kernel
        - A lot of BIOS bugs are already absorbed by the kernel

What do we need such a stupid linuxfirmwarekit for?

  - Vendors: Can test their BIOSes for Linux compatibility.
    There will be the time when vendors realize that the test utils
    on Linux are more strict and using them increases the qualitity
    and stability of their products.

  - Vendors: Can easily fix up their BIOSes and be more Linux
    compatible by:
    dmesg |grep "Firmware Bug"
    and send the result to their BIOS developer colleagues who should
    know what the messages are about and how to fix them, without
    the need of studying kernel code.

  - Distributions: can do a first automated HW/BIOS checks.
    This can then be done without the need of asking kernel developers
    who need to dig down the code and explain the details.
    Certification can/will just be rejected until
    dmesg |grep "Firmware Bug" is empty.

  - Thus this can be used as an instrument to enforce cleaner BIOS
    code. Currently every stupid Windows ACPI bug is
    re-implemented in Linux which is a rather unfortunate situation.
    We already have the power to avoid this in e.g. memory
    or cpu hot-plug ACPI implementations, because Linux certification
    is a must for most vendors in the server area.
    Working towards being able to do that in the laptop area
    (vendors are starting to look at Linux here also and will use this tool)
    is the goal. At least provide them a tool to make it as easy
    for this guys (e.g. not needing to browse kernel code) as possible.

  - The ordinary Linux user: can go into the next shop, boots the
    firmwarekit on his most preferred machines. He chooses one without
    BIOS bugs. Unsupported HW is ok, he likes to try out latest projects
    which might support them or likes to dig on it on his own, but he
    hates to workaround broken BIOSes like hell.

I double checked with the firmwarekit.
There they have:
So the mapping generally is (also depending on how likely the BIOS is
to blame, this could sometimes be difficult):
FW_INFO  = INFO
FW_WARN  = WARN
FW_BUG   = FAIL

For more info about the linuxfirmwarekit and why this is needed
can be found here:
http://www.linuxfirmwarekit.org

While severity matches with the firmwarekit, it might be tricky
to hide messages from the user.
E.g. we recently found out that on HP BIOSes negative temperatures
are returned, which seem to indicate that the thermal zone is
invalid.
We can work around that gracefully by ignoring the thermal zone
and we do not want to bother the ordinary user with a frightening
message: Firmware Bug: thermal management absolutely broken
but want to hide it from the user.

But in the linuxfirmwarekit this should be shown as a real
show stopper (the temperatures could really be wrong,
broken thermal management is one of the worst things
that can happen and the BIOS guys of the machine must
implement this properly).

It is intended to do that (hide it from the user with
KERN_INFO msg, but still print it as a BIOS bug) by:
printk(KERN_INFO FW_BUG "Negativ temperature values detected.
Try to workarounded, BIOS must get fixed\n");
Hope that works out..., no idea how to better hide it
as printk is the only way to easily provide this functionality.

Signed-off-by: Thomas Renninger <trenn@suse.de>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 include/linux/kernel.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 2651f805ba6d..0b19848e380e 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -190,6 +190,30 @@ extern int kernel_text_address(unsigned long addr);
 struct pid;
 extern struct pid *session_of_pgrp(struct pid *pgrp);
 
+/*
+ * FW_BUG
+ * Add this to a message where you are sure the firmware is buggy or behaves
+ * really stupid or out of spec. Be aware that the responsible BIOS developer
+ * should be able to fix this issue or at least get a concrete idea of the
+ * problem by reading your message without the need of looking at the kernel
+ * code.
+ * 
+ * Use it for definite and high priority BIOS bugs.
+ *
+ * FW_WARN
+ * Use it for not that clear (e.g. could the kernel messed up things already?)
+ * and medium priority BIOS bugs.
+ *
+ * FW_INFO
+ * Use this one if you want to tell the user or vendor about something
+ * suspicious, but generally harmless related to the firmware.
+ *
+ * Use it for information or very low priority BIOS bugs.
+ */
+#define FW_BUG		"[Firmware Bug]: "
+#define FW_WARN		"[Firmware Warn]: "
+#define FW_INFO		"[Firmware Info]: "
+
 #ifdef CONFIG_PRINTK
 asmlinkage int vprintk(const char *fmt, va_list args)
 	__attribute__ ((format (printf, 1, 0)));
-- 
cgit v1.2.3


From bb34d92f643086d546b49cef680f6f305ed84414 Mon Sep 17 00:00:00 2001
From: Frank Mayhar <fmayhar@google.com>
Date: Fri, 12 Sep 2008 09:54:39 -0700
Subject: timers: fix itimer/many thread hang, v2

This is the second resubmission of the posix timer rework patch, posted
a few days ago.

This includes the changes from the previous resubmittion, which addressed
Oleg Nesterov's comments, removing the RCU stuff from the patch and
un-inlining the thread_group_cputime() function for SMP.

In addition, per Ingo Molnar it simplifies the UP code, consolidating much
of it with the SMP version and depending on lower-level SMP/UP handling to
take care of the differences.

It also cleans up some UP compile errors, moves the scheduler stats-related
macros into kernel/sched_stats.h, cleans up a merge error in
kernel/fork.c and has a few other minor fixes and cleanups as suggested
by Oleg and Ingo. Thanks for the review, guys.

Signed-off-by: Frank Mayhar <fmayhar@google.com>
Cc: Roland McGrath <roland@redhat.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/kernel_stat.h |   1 +
 include/linux/sched.h       | 183 ++------------------------------------------
 kernel/fork.c               |   5 +-
 kernel/posix-cpu-timers.c   | 153 ++++++++++++++++--------------------
 kernel/sched.c              |  47 ++----------
 kernel/sched_stats.h        | 136 ++++++++++++++++++++++++++++++++
 6 files changed, 214 insertions(+), 311 deletions(-)

(limited to 'include')

diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index cf9f40a91c9c..cac3750cd65e 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -52,6 +52,7 @@ static inline int kstat_irqs(int irq)
 	return sum;
 }
 
+extern unsigned long long task_delta_exec(struct task_struct *);
 extern void account_user_time(struct task_struct *, cputime_t);
 extern void account_user_time_scaled(struct task_struct *, cputime_t);
 extern void account_system_time(struct task_struct *, int, cputime_t);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7ce8d4e53565..b982fb48c8f0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -454,15 +454,9 @@ struct task_cputime {
  * This structure contains the version of task_cputime, above, that is
  * used for thread group CPU clock calculations.
  */
-#ifdef CONFIG_SMP
 struct thread_group_cputime {
 	struct task_cputime *totals;
 };
-#else
-struct thread_group_cputime {
-	struct task_cputime totals;
-};
-#endif
 
 /*
  * NOTE! "signal_struct" does not have it's own
@@ -2124,193 +2118,26 @@ static inline int spin_needbreak(spinlock_t *lock)
 /*
  * Thread group CPU time accounting.
  */
-#ifdef CONFIG_SMP
 
-extern int thread_group_cputime_alloc_smp(struct task_struct *);
-extern void thread_group_cputime_smp(struct task_struct *, struct task_cputime *);
+extern int thread_group_cputime_alloc(struct task_struct *);
+extern void thread_group_cputime(struct task_struct *, struct task_cputime *);
 
 static inline void thread_group_cputime_init(struct signal_struct *sig)
 {
 	sig->cputime.totals = NULL;
 }
 
-static inline int thread_group_cputime_clone_thread(struct task_struct *curr,
-						    struct task_struct *new)
+static inline int thread_group_cputime_clone_thread(struct task_struct *curr)
 {
 	if (curr->signal->cputime.totals)
 		return 0;
-	return thread_group_cputime_alloc_smp(curr);
+	return thread_group_cputime_alloc(curr);
 }
 
-static inline void thread_group_cputime_free(struct signal_struct *sig)
-{
-	free_percpu(sig->cputime.totals);
-}
-
-/**
- * thread_group_cputime - Sum the thread group time fields across all CPUs.
- *
- * This is a wrapper for the real routine, thread_group_cputime_smp().  See
- * that routine for details.
- */
-static inline void thread_group_cputime(
-	struct task_struct *tsk,
-	struct task_cputime *times)
-{
-	thread_group_cputime_smp(tsk, times);
-}
-
-/**
- * thread_group_cputime_account_user - Maintain utime for a thread group.
- *
- * @tgtimes:	Pointer to thread_group_cputime structure.
- * @cputime:	Time value by which to increment the utime field of that
- *		structure.
- *
- * If thread group time is being maintained, get the structure for the
- * running CPU and update the utime field there.
- */
-static inline void thread_group_cputime_account_user(
-	struct thread_group_cputime *tgtimes,
-	cputime_t cputime)
-{
-	if (tgtimes->totals) {
-		struct task_cputime *times;
-
-		times = per_cpu_ptr(tgtimes->totals, get_cpu());
-		times->utime = cputime_add(times->utime, cputime);
-		put_cpu_no_resched();
-	}
-}
-
-/**
- * thread_group_cputime_account_system - Maintain stime for a thread group.
- *
- * @tgtimes:	Pointer to thread_group_cputime structure.
- * @cputime:	Time value by which to increment the stime field of that
- *		structure.
- *
- * If thread group time is being maintained, get the structure for the
- * running CPU and update the stime field there.
- */
-static inline void thread_group_cputime_account_system(
-	struct thread_group_cputime *tgtimes,
-	cputime_t cputime)
-{
-	if (tgtimes->totals) {
-		struct task_cputime *times;
-
-		times = per_cpu_ptr(tgtimes->totals, get_cpu());
-		times->stime = cputime_add(times->stime, cputime);
-		put_cpu_no_resched();
-	}
-}
-
-/**
- * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a
- *						thread group.
- *
- * @tgtimes:	Pointer to thread_group_cputime structure.
- * @ns:		Time value by which to increment the sum_exec_runtime field
- *		of that structure.
- *
- * If thread group time is being maintained, get the structure for the
- * running CPU and update the sum_exec_runtime field there.
- */
-static inline void thread_group_cputime_account_exec_runtime(
-	struct thread_group_cputime *tgtimes,
-	unsigned long long ns)
-{
-	if (tgtimes->totals) {
-		struct task_cputime *times;
-
-		times = per_cpu_ptr(tgtimes->totals, get_cpu());
-		times->sum_exec_runtime += ns;
-		put_cpu_no_resched();
-	}
-}
-
-#else /* CONFIG_SMP */
-
-static inline void thread_group_cputime_init(struct signal_struct *sig)
-{
-	sig->cputime.totals.utime = cputime_zero;
-	sig->cputime.totals.stime = cputime_zero;
-	sig->cputime.totals.sum_exec_runtime = 0;
-}
-
-static inline int thread_group_cputime_alloc(struct task_struct *tsk)
-{
-	return 0;
-}
 
 static inline void thread_group_cputime_free(struct signal_struct *sig)
 {
-}
-
-static inline int thread_group_cputime_clone_thread(struct task_struct *curr,
-						     struct task_struct *tsk)
-{
-	return 0;
-}
-
-static inline void thread_group_cputime(struct task_struct *tsk,
-					 struct task_cputime *cputime)
-{
-	*cputime = tsk->signal->cputime.totals;
-}
-
-static inline void thread_group_cputime_account_user(
-	struct thread_group_cputime *tgtimes,
-	cputime_t cputime)
-{
-	tgtimes->totals.utime = cputime_add(tgtimes->totals.utime, cputime);
-}
-
-static inline void thread_group_cputime_account_system(
-	struct thread_group_cputime *tgtimes,
-	cputime_t cputime)
-{
-	tgtimes->totals.stime = cputime_add(tgtimes->totals.stime, cputime);
-}
-
-static inline void thread_group_cputime_account_exec_runtime(
-	struct thread_group_cputime *tgtimes,
-	unsigned long long ns)
-{
-	tgtimes->totals.sum_exec_runtime += ns;
-}
-
-#endif /* CONFIG_SMP */
-
-static inline void account_group_user_time(struct task_struct *tsk,
-					    cputime_t cputime)
-{
-	struct signal_struct *sig;
-
-	sig = tsk->signal;
-	if (likely(sig))
-		thread_group_cputime_account_user(&sig->cputime, cputime);
-}
-
-static inline void account_group_system_time(struct task_struct *tsk,
-					      cputime_t cputime)
-{
-	struct signal_struct *sig;
-
-	sig = tsk->signal;
-	if (likely(sig))
-		thread_group_cputime_account_system(&sig->cputime, cputime);
-}
-
-static inline void account_group_exec_runtime(struct task_struct *tsk,
-					       unsigned long long ns)
-{
-	struct signal_struct *sig;
-
-	sig = tsk->signal;
-	if (likely(sig))
-		thread_group_cputime_account_exec_runtime(&sig->cputime, ns);
+	free_percpu(sig->cputime.totals);
 }
 
 /*
diff --git a/kernel/fork.c b/kernel/fork.c
index 1181b9aac48e..021ae012cc75 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -791,7 +791,7 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	int ret;
 
 	if (clone_flags & CLONE_THREAD) {
-		ret = thread_group_cputime_clone_thread(current, tsk);
+		ret = thread_group_cputime_clone_thread(current);
 		if (likely(!ret)) {
 			atomic_inc(&current->signal->count);
 			atomic_inc(&current->signal->live);
@@ -834,9 +834,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
 	sig->inblock = sig->oublock = sig->cinblock = sig->coublock = 0;
 	task_io_accounting_init(&sig->ioac);
-	INIT_LIST_HEAD(&sig->cpu_timers[0]);
-	INIT_LIST_HEAD(&sig->cpu_timers[1]);
-	INIT_LIST_HEAD(&sig->cpu_timers[2]);
 	taskstats_tgid_init(sig);
 
 	task_lock(current->group_leader);
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 9a7ea049fcdc..153dcb2639c3 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -7,50 +7,46 @@
 #include <linux/errno.h>
 #include <linux/math64.h>
 #include <asm/uaccess.h>
+#include <linux/kernel_stat.h>
 
-#ifdef CONFIG_SMP
 /*
- * Allocate the thread_group_cputime structure appropriately for SMP kernels
- * and fill in the current values of the fields.  Called from copy_signal()
- * via thread_group_cputime_clone_thread() when adding a second or subsequent
+ * Allocate the thread_group_cputime structure appropriately and fill in the
+ * current values of the fields.  Called from copy_signal() via
+ * thread_group_cputime_clone_thread() when adding a second or subsequent
  * thread to a thread group.  Assumes interrupts are enabled when called.
  */
-int thread_group_cputime_alloc_smp(struct task_struct *tsk)
+int thread_group_cputime_alloc(struct task_struct *tsk)
 {
 	struct signal_struct *sig = tsk->signal;
 	struct task_cputime *cputime;
 
 	/*
 	 * If we have multiple threads and we don't already have a
-	 * per-CPU task_cputime struct, allocate one and fill it in with
-	 * the times accumulated so far.
+	 * per-CPU task_cputime struct (checked in the caller), allocate
+	 * one and fill it in with the times accumulated so far.  We may
+	 * race with another thread so recheck after we pick up the sighand
+	 * lock.
 	 */
-	if (sig->cputime.totals)
-		return 0;
 	cputime = alloc_percpu(struct task_cputime);
 	if (cputime == NULL)
 		return -ENOMEM;
-	read_lock(&tasklist_lock);
 	spin_lock_irq(&tsk->sighand->siglock);
 	if (sig->cputime.totals) {
 		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
 		free_percpu(cputime);
 		return 0;
 	}
 	sig->cputime.totals = cputime;
-	cputime = per_cpu_ptr(sig->cputime.totals, get_cpu());
+	cputime = per_cpu_ptr(sig->cputime.totals, smp_processor_id());
 	cputime->utime = tsk->utime;
 	cputime->stime = tsk->stime;
 	cputime->sum_exec_runtime = tsk->se.sum_exec_runtime;
-	put_cpu_no_resched();
 	spin_unlock_irq(&tsk->sighand->siglock);
-	read_unlock(&tasklist_lock);
 	return 0;
 }
 
 /**
- * thread_group_cputime_smp - Sum the thread group time fields across all CPUs.
+ * thread_group_cputime - Sum the thread group time fields across all CPUs.
  *
  * @tsk:	The task we use to identify the thread group.
  * @times:	task_cputime structure in which we return the summed fields.
@@ -58,7 +54,7 @@ int thread_group_cputime_alloc_smp(struct task_struct *tsk)
  * Walk the list of CPUs to sum the per-CPU time fields in the thread group
  * time structure.
  */
-void thread_group_cputime_smp(
+void thread_group_cputime(
 	struct task_struct *tsk,
 	struct task_cputime *times)
 {
@@ -83,8 +79,6 @@ void thread_group_cputime_smp(
 	}
 }
 
-#endif /* CONFIG_SMP */
-
 /*
  * Called after updating RLIMIT_CPU to set timer expiration if necessary.
  */
@@ -300,7 +294,7 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 		cpu->cpu = virt_ticks(p);
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = task_sched_runtime(p);
+		cpu->sched = p->se.sum_exec_runtime + task_delta_exec(p);
 		break;
 	}
 	return 0;
@@ -309,16 +303,15 @@ static int cpu_clock_sample(const clockid_t which_clock, struct task_struct *p,
 /*
  * Sample a process (thread group) clock for the given group_leader task.
  * Must be called with tasklist_lock held for reading.
- * Must be called with tasklist_lock held for reading, and p->sighand->siglock.
  */
-static int cpu_clock_sample_group_locked(unsigned int clock_idx,
-					 struct task_struct *p,
-					 union cpu_time_count *cpu)
+static int cpu_clock_sample_group(const clockid_t which_clock,
+				  struct task_struct *p,
+				  union cpu_time_count *cpu)
 {
 	struct task_cputime cputime;
 
 	thread_group_cputime(p, &cputime);
-	switch (clock_idx) {
+	switch (which_clock) {
 	default:
 		return -EINVAL;
 	case CPUCLOCK_PROF:
@@ -328,29 +321,12 @@ static int cpu_clock_sample_group_locked(unsigned int clock_idx,
 		cpu->cpu = cputime.utime;
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = thread_group_sched_runtime(p);
+		cpu->sched = cputime.sum_exec_runtime + task_delta_exec(p);
 		break;
 	}
 	return 0;
 }
 
-/*
- * Sample a process (thread group) clock for the given group_leader task.
- * Must be called with tasklist_lock held for reading.
- */
-static int cpu_clock_sample_group(const clockid_t which_clock,
-				  struct task_struct *p,
-				  union cpu_time_count *cpu)
-{
-	int ret;
-	unsigned long flags;
-	spin_lock_irqsave(&p->sighand->siglock, flags);
-	ret = cpu_clock_sample_group_locked(CPUCLOCK_WHICH(which_clock), p,
-					    cpu);
-	spin_unlock_irqrestore(&p->sighand->siglock, flags);
-	return ret;
-}
-
 
 int posix_cpu_clock_get(const clockid_t which_clock, struct timespec *tp)
 {
@@ -1324,29 +1300,37 @@ static inline int task_cputime_expired(const struct task_cputime *sample,
  * fastpath_timer_check - POSIX CPU timers fast path.
  *
  * @tsk:	The task (thread) being checked.
- * @sig:	The signal pointer for that task.
  *
- * If there are no timers set return false.  Otherwise snapshot the task and
- * thread group timers, then compare them with the corresponding expiration
- # times.  Returns true if a timer has expired, else returns false.
+ * Check the task and thread group timers.  If both are zero (there are no
+ * timers set) return false.  Otherwise snapshot the task and thread group
+ * timers and compare them with the corresponding expiration times.  Return
+ * true if a timer has expired, else return false.
  */
-static inline int fastpath_timer_check(struct task_struct *tsk,
-					struct signal_struct *sig)
+static inline int fastpath_timer_check(struct task_struct *tsk)
 {
-	struct task_cputime task_sample = {
-		.utime = tsk->utime,
-		.stime = tsk->stime,
-		.sum_exec_runtime = tsk->se.sum_exec_runtime
-	};
-	struct task_cputime group_sample;
+	struct signal_struct *sig = tsk->signal;
 
-	if (task_cputime_zero(&tsk->cputime_expires) &&
-	    task_cputime_zero(&sig->cputime_expires))
+	if (unlikely(!sig))
 		return 0;
-	if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
-		return 1;
-	thread_group_cputime(tsk, &group_sample);
-	return task_cputime_expired(&group_sample, &sig->cputime_expires);
+
+	if (!task_cputime_zero(&tsk->cputime_expires)) {
+		struct task_cputime task_sample = {
+			.utime = tsk->utime,
+			.stime = tsk->stime,
+			.sum_exec_runtime = tsk->se.sum_exec_runtime
+		};
+
+		if (task_cputime_expired(&task_sample, &tsk->cputime_expires))
+			return 1;
+	}
+	if (!task_cputime_zero(&sig->cputime_expires)) {
+		struct task_cputime group_sample;
+
+		thread_group_cputime(tsk, &group_sample);
+		if (task_cputime_expired(&group_sample, &sig->cputime_expires))
+			return 1;
+	}
+	return 0;
 }
 
 /*
@@ -1358,43 +1342,34 @@ void run_posix_cpu_timers(struct task_struct *tsk)
 {
 	LIST_HEAD(firing);
 	struct k_itimer *timer, *next;
-	struct signal_struct *sig;
-	struct sighand_struct *sighand;
-	unsigned long flags;
 
 	BUG_ON(!irqs_disabled());
 
-	/* Pick up tsk->signal and make sure it's valid. */
-	sig = tsk->signal;
 	/*
 	 * The fast path checks that there are no expired thread or thread
-	 * group timers.  If that's so, just return.  Also check that
-	 * tsk->signal is non-NULL; this probably can't happen but cover the
-	 * possibility anyway.
+	 * group timers.  If that's so, just return.
 	 */
-	if (unlikely(!sig) || !fastpath_timer_check(tsk, sig))
+	if (!fastpath_timer_check(tsk))
 		return;
 
-	sighand = lock_task_sighand(tsk, &flags);
-	if (likely(sighand)) {
-		/*
-		 * Here we take off tsk->signal->cpu_timers[N] and
-		 * tsk->cpu_timers[N] all the timers that are firing, and
-		 * put them on the firing list.
-		 */
-		check_thread_timers(tsk, &firing);
-		check_process_timers(tsk, &firing);
+	spin_lock(&tsk->sighand->siglock);
+	/*
+	 * Here we take off tsk->signal->cpu_timers[N] and
+	 * tsk->cpu_timers[N] all the timers that are firing, and
+	 * put them on the firing list.
+	 */
+	check_thread_timers(tsk, &firing);
+	check_process_timers(tsk, &firing);
 
-		/*
-		 * We must release these locks before taking any timer's lock.
-		 * There is a potential race with timer deletion here, as the
-		 * siglock now protects our private firing list.  We have set
-		 * the firing flag in each timer, so that a deletion attempt
-		 * that gets the timer lock before we do will give it up and
-		 * spin until we've taken care of that timer below.
-		 */
-	}
-	unlock_task_sighand(tsk, &flags);
+	/*
+	 * We must release these locks before taking any timer's lock.
+	 * There is a potential race with timer deletion here, as the
+	 * siglock now protects our private firing list.  We have set
+	 * the firing flag in each timer, so that a deletion attempt
+	 * that gets the timer lock before we do will give it up and
+	 * spin until we've taken care of that timer below.
+	 */
+	spin_unlock(&tsk->sighand->siglock);
 
 	/*
 	 * Now that all the timers on our list have the firing flag,
@@ -1433,7 +1408,7 @@ void set_process_cpu_timer(struct task_struct *tsk, unsigned int clock_idx,
 	struct list_head *head;
 
 	BUG_ON(clock_idx == CPUCLOCK_SCHED);
-	cpu_clock_sample_group_locked(clock_idx, tsk, &now);
+	cpu_clock_sample_group(clock_idx, tsk, &now);
 
 	if (oldval) {
 		if (!cputime_eq(*oldval, cputime_zero)) {
diff --git a/kernel/sched.c b/kernel/sched.c
index c51b5d276665..260c22cc530a 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4039,55 +4039,22 @@ EXPORT_PER_CPU_SYMBOL(kstat);
 /*
  * Return any ns on the sched_clock that have not yet been banked in
  * @p in case that task is currently running.
- *
- * Called with task_rq_lock() held on @rq.
  */
-static unsigned long long task_delta_exec(struct task_struct *p, struct rq *rq)
+unsigned long long task_delta_exec(struct task_struct *p)
 {
+	struct rq *rq;
+	unsigned long flags;
+	u64 ns = 0;
+
+	rq = task_rq_lock(p, &flags);
 	if (task_current(rq, p)) {
 		u64 delta_exec;
 
 		update_rq_clock(rq);
 		delta_exec = rq->clock - p->se.exec_start;
 		if ((s64)delta_exec > 0)
-			return delta_exec;
+			ns = delta_exec;
 	}
-	return 0;
-}
-
-/*
- * Return p->sum_exec_runtime plus any more ns on the sched_clock
- * that have not yet been banked in case the task is currently running.
- */
-unsigned long long task_sched_runtime(struct task_struct *p)
-{
-	unsigned long flags;
-	u64 ns;
-	struct rq *rq;
-
-	rq = task_rq_lock(p, &flags);
-	ns = p->se.sum_exec_runtime + task_delta_exec(p, rq);
-	task_rq_unlock(rq, &flags);
-
-	return ns;
-}
-
-/*
- * Return sum_exec_runtime for the thread group plus any more ns on the
- * sched_clock that have not yet been banked in case the task is currently
- * running.
- */
-unsigned long long thread_group_sched_runtime(struct task_struct *p)
-{
-	unsigned long flags;
-	u64 ns;
-	struct rq *rq;
-	struct task_cputime totals;
-
-	rq = task_rq_lock(p, &flags);
-	thread_group_cputime(p, &totals);
-	ns = totals.sum_exec_runtime + task_delta_exec(p, rq);
-	task_rq_unlock(rq, &flags);
 
 	return ns;
 }
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index 8385d43987e2..d6903bd0c7a8 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -270,3 +270,139 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
 #define sched_info_switch(t, next)		do { } while (0)
 #endif /* CONFIG_SCHEDSTATS || CONFIG_TASK_DELAY_ACCT */
 
+/*
+ * The following are functions that support scheduler-internal time accounting.
+ * These functions are generally called at the timer tick.  None of this depends
+ * on CONFIG_SCHEDSTATS.
+ */
+
+#ifdef CONFIG_SMP
+
+/**
+ * thread_group_cputime_account_user - Maintain utime for a thread group.
+ *
+ * @tgtimes:	Pointer to thread_group_cputime structure.
+ * @cputime:	Time value by which to increment the utime field of that
+ *		structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the utime field there.
+ */
+static inline void thread_group_cputime_account_user(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	if (tgtimes->totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times->utime = cputime_add(times->utime, cputime);
+		put_cpu_no_resched();
+	}
+}
+
+/**
+ * thread_group_cputime_account_system - Maintain stime for a thread group.
+ *
+ * @tgtimes:	Pointer to thread_group_cputime structure.
+ * @cputime:	Time value by which to increment the stime field of that
+ *		structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the stime field there.
+ */
+static inline void thread_group_cputime_account_system(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	if (tgtimes->totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times->stime = cputime_add(times->stime, cputime);
+		put_cpu_no_resched();
+	}
+}
+
+/**
+ * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a
+ *						thread group.
+ *
+ * @tgtimes:	Pointer to thread_group_cputime structure.
+ * @ns:		Time value by which to increment the sum_exec_runtime field
+ *		of that structure.
+ *
+ * If thread group time is being maintained, get the structure for the
+ * running CPU and update the sum_exec_runtime field there.
+ */
+static inline void thread_group_cputime_account_exec_runtime(
+	struct thread_group_cputime *tgtimes,
+	unsigned long long ns)
+{
+	if (tgtimes->totals) {
+		struct task_cputime *times;
+
+		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times->sum_exec_runtime += ns;
+		put_cpu_no_resched();
+	}
+}
+
+#else /* CONFIG_SMP */
+
+static inline void thread_group_cputime_account_user(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime);
+}
+
+static inline void thread_group_cputime_account_system(
+	struct thread_group_cputime *tgtimes,
+	cputime_t cputime)
+{
+	tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime);
+}
+
+static inline void thread_group_cputime_account_exec_runtime(
+	struct thread_group_cputime *tgtimes,
+	unsigned long long ns)
+{
+	tgtimes->totals->sum_exec_runtime += ns;
+}
+
+#endif /* CONFIG_SMP */
+
+/*
+ * These are the generic time-accounting routines that use the above
+ * functions.  They are the functions actually called by the scheduler.
+ */
+static inline void account_group_user_time(struct task_struct *tsk,
+					    cputime_t cputime)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (likely(sig))
+		thread_group_cputime_account_user(&sig->cputime, cputime);
+}
+
+static inline void account_group_system_time(struct task_struct *tsk,
+					      cputime_t cputime)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (likely(sig))
+		thread_group_cputime_account_system(&sig->cputime, cputime);
+}
+
+static inline void account_group_exec_runtime(struct task_struct *tsk,
+					       unsigned long long ns)
+{
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (likely(sig))
+		thread_group_cputime_account_exec_runtime(&sig->cputime, ns);
+}
-- 
cgit v1.2.3


From 6bd00a61ab63d4ceb635ae0316353c11c900b8d8 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shaohua.li@intel.com>
Date: Thu, 28 Aug 2008 10:04:29 +0800
Subject: ACPI: introduce notifier change to avoid duplicates

The battery driver already registers notification handler.
To avoid registering notification handler again,
introduce a notifier chain in global system notifier handler
and use it in dock driver.

Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/bus.c      | 15 +++++++++++++++
 drivers/acpi/dock.c     | 46 ++++++++++++++++++++++++----------------------
 include/acpi/acpi_bus.h |  3 +++
 3 files changed, 42 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index ccae305ee55d..0dc44945725e 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -496,6 +496,19 @@ static int acpi_bus_check_scope(struct acpi_device *device)
 	return 0;
 }
 
+static BLOCKING_NOTIFIER_HEAD(acpi_bus_notify_list);
+int register_acpi_bus_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&acpi_bus_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(register_acpi_bus_notifier);
+
+void unregister_acpi_bus_notifier(struct notifier_block *nb)
+{
+	blocking_notifier_chain_unregister(&acpi_bus_notify_list, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_acpi_bus_notifier);
+
 /**
  * acpi_bus_notify
  * ---------------
@@ -506,6 +519,8 @@ static void acpi_bus_notify(acpi_handle handle, u32 type, void *data)
 	int result = 0;
 	struct acpi_device *device = NULL;
 
+	blocking_notifier_call_chain(&acpi_bus_notify_list,
+		type, (void *)handle);
 
 	if (acpi_bus_get_device(handle, &device))
 		return;
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index 799a0fdbb62d..2563bc62987d 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -748,6 +748,28 @@ static void dock_notify(acpi_handle handle, u32 event, void *data)
 	}
 }
 
+static int acpi_dock_notifier_call(struct notifier_block *this,
+	unsigned long event, void *data)
+{
+	struct dock_station *dock_station;
+	acpi_handle handle = (acpi_handle)data;
+
+	if (event != ACPI_NOTIFY_BUS_CHECK && event != ACPI_NOTIFY_DEVICE_CHECK
+	   && event != ACPI_NOTIFY_EJECT_REQUEST)
+		return 0;
+	list_for_each_entry(dock_station, &dock_stations, sibiling) {
+		if (dock_station->handle == handle) {
+			dock_notify(handle, event, dock_station);
+			return 0 ;
+		}
+	}
+	return 0;
+}
+
+static struct notifier_block dock_acpi_notifier = {
+	.notifier_call = acpi_dock_notifier_call,
+};
+
 /**
  * find_dock_devices - find devices on the dock station
  * @handle: the handle of the device we are examining
@@ -861,7 +883,6 @@ static DEVICE_ATTR(uid, S_IRUGO, show_dock_uid, NULL);
 static int dock_add(acpi_handle handle)
 {
 	int ret;
-	acpi_status status;
 	struct dock_dependent_device *dd;
 	struct dock_station *dock_station;
 	struct platform_device *dock_device;
@@ -956,23 +977,10 @@ static int dock_add(acpi_handle handle)
 	}
 	add_dock_dependent_device(dock_station, dd);
 
-	/* register for dock events */
-	status = acpi_install_notify_handler(dock_station->handle,
-					     ACPI_SYSTEM_NOTIFY,
-					     dock_notify, dock_station);
-
-	if (ACPI_FAILURE(status)) {
-		printk(KERN_ERR PREFIX "Error installing notify handler\n");
-		ret = -ENODEV;
-		goto dock_add_err;
-	}
-
 	dock_station_count++;
 	list_add(&dock_station->sibiling, &dock_stations);
 	return 0;
 
-dock_add_err:
-	kfree(dd);
 dock_add_err_unregister:
 	device_remove_file(&dock_device->dev, &dev_attr_docked);
 	device_remove_file(&dock_device->dev, &dev_attr_undock);
@@ -990,7 +998,6 @@ dock_add_err_unregister:
 static int dock_remove(struct dock_station *dock_station)
 {
 	struct dock_dependent_device *dd, *tmp;
-	acpi_status status;
 	struct platform_device *dock_device = dock_station->dock_device;
 
 	if (!dock_station_count)
@@ -1001,13 +1008,6 @@ static int dock_remove(struct dock_station *dock_station)
 				 list)
 	    kfree(dd);
 
-	/* remove dock notify handler */
-	status = acpi_remove_notify_handler(dock_station->handle,
-					    ACPI_SYSTEM_NOTIFY,
-					    dock_notify);
-	if (ACPI_FAILURE(status))
-		printk(KERN_ERR "Error removing notify handler\n");
-
 	/* cleanup sysfs */
 	device_remove_file(&dock_device->dev, &dev_attr_docked);
 	device_remove_file(&dock_device->dev, &dev_attr_undock);
@@ -1069,6 +1069,7 @@ static int __init dock_init(void)
 		return 0;
 	}
 
+	register_acpi_bus_notifier(&dock_acpi_notifier);
 	printk(KERN_INFO PREFIX "%s: %d docks/bays found\n",
 		ACPI_DOCK_DRIVER_DESCRIPTION, dock_station_count);
 	return 0;
@@ -1078,6 +1079,7 @@ static void __exit dock_exit(void)
 {
 	struct dock_station *dock_station;
 
+	unregister_acpi_bus_notifier(&dock_acpi_notifier);
 	list_for_each_entry(dock_station, &dock_stations, sibiling)
 		dock_remove(dock_station);
 }
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index a5ac0bc7f52e..f74f882609f8 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -327,6 +327,9 @@ int acpi_bus_get_private_data(acpi_handle, void **);
 extern int acpi_notifier_call_chain(struct acpi_device *, u32, u32);
 extern int register_acpi_notifier(struct notifier_block *);
 extern int unregister_acpi_notifier(struct notifier_block *);
+
+extern int register_acpi_bus_notifier(struct notifier_block *nb);
+extern void unregister_acpi_bus_notifier(struct notifier_block *nb);
 /*
  * External Functions
  */
-- 
cgit v1.2.3


From 19cd847ab24fefe9e50101ec94479e0400a08650 Mon Sep 17 00:00:00 2001
From: Zhang Rui <rui.zhang@intel.com>
Date: Thu, 28 Aug 2008 10:05:06 +0800
Subject: ACPI: fix hotplug race

The hotplug notification handler and drivers' notification handler all
run in one workqueue.  Before hotplug removes an acpi device, the
device driver's notification handler is already be recorded to run just
after global notification handler.  After hotplug notification handler
runs, acpica will notice a NULL notification handler and crash.

So now we run run hotplug in another workqueue and wait
for all acpi notication handlers finish.
This was found in battery hotplug, but actually all
hotplug can be affected.

Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/dock.c     | 25 ++++++++++++++++++++++++-
 drivers/acpi/osl.c      | 46 +++++++++++++++++++++++++++++++++++++++++-----
 include/acpi/acpiosxf.h |  3 +++
 3 files changed, 68 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index 2563bc62987d..4b395b1e61b2 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -748,6 +748,20 @@ static void dock_notify(acpi_handle handle, u32 event, void *data)
 	}
 }
 
+struct dock_data {
+	acpi_handle handle;
+	unsigned long event;
+	struct dock_station *ds;
+};
+
+static void acpi_dock_deferred_cb(void *context)
+{
+	struct dock_data *data = (struct dock_data *)context;
+
+	dock_notify(data->handle, data->event, data->ds);
+	kfree(data);
+}
+
 static int acpi_dock_notifier_call(struct notifier_block *this,
 	unsigned long event, void *data)
 {
@@ -759,7 +773,16 @@ static int acpi_dock_notifier_call(struct notifier_block *this,
 		return 0;
 	list_for_each_entry(dock_station, &dock_stations, sibiling) {
 		if (dock_station->handle == handle) {
-			dock_notify(handle, event, dock_station);
+			struct dock_data *dock_data;
+
+			dock_data = kmalloc(sizeof(*dock_data), GFP_KERNEL);
+			if (!dock_data)
+				return 0;
+			dock_data->handle = handle;
+			dock_data->event = event;
+			dock_data->ds = dock_station;
+			acpi_os_hotplug_execute(acpi_dock_deferred_cb,
+				dock_data);
 			return 0 ;
 		}
 	}
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 235a1386888a..750e0df15604 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -682,6 +682,22 @@ static void acpi_os_execute_deferred(struct work_struct *work)
 	return;
 }
 
+static void acpi_os_execute_hp_deferred(struct work_struct *work)
+{
+	struct acpi_os_dpc *dpc = container_of(work, struct acpi_os_dpc, work);
+	if (!dpc) {
+		printk(KERN_ERR PREFIX "Invalid (NULL) context\n");
+		return;
+	}
+
+	acpi_os_wait_events_complete(NULL);
+
+	dpc->function(dpc->context);
+	kfree(dpc);
+
+	return;
+}
+
 /*******************************************************************************
  *
  * FUNCTION:    acpi_os_execute
@@ -697,12 +713,13 @@ static void acpi_os_execute_deferred(struct work_struct *work)
  *
  ******************************************************************************/
 
-acpi_status acpi_os_execute(acpi_execute_type type,
-			    acpi_osd_exec_callback function, void *context)
+static acpi_status __acpi_os_execute(acpi_execute_type type,
+	acpi_osd_exec_callback function, void *context, int hp)
 {
 	acpi_status status = AE_OK;
 	struct acpi_os_dpc *dpc;
 	struct workqueue_struct *queue;
+	int ret;
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
 			  "Scheduling function [%p(%p)] for deferred execution.\n",
 			  function, context));
@@ -726,9 +743,17 @@ acpi_status acpi_os_execute(acpi_execute_type type,
 	dpc->function = function;
 	dpc->context = context;
 
-	INIT_WORK(&dpc->work, acpi_os_execute_deferred);
-	queue = (type == OSL_NOTIFY_HANDLER) ? kacpi_notify_wq : kacpid_wq;
-	if (!queue_work(queue, &dpc->work)) {
+	if (!hp) {
+		INIT_WORK(&dpc->work, acpi_os_execute_deferred);
+		queue = (type == OSL_NOTIFY_HANDLER) ?
+			kacpi_notify_wq : kacpid_wq;
+		ret = queue_work(queue, &dpc->work);
+	} else {
+		INIT_WORK(&dpc->work, acpi_os_execute_hp_deferred);
+		ret = schedule_work(&dpc->work);
+	}
+
+	if (!ret) {
 		ACPI_DEBUG_PRINT((ACPI_DB_ERROR,
 			  "Call to queue_work() failed.\n"));
 		status = AE_ERROR;
@@ -737,8 +762,19 @@ acpi_status acpi_os_execute(acpi_execute_type type,
 	return_ACPI_STATUS(status);
 }
 
+acpi_status acpi_os_execute(acpi_execute_type type,
+			    acpi_osd_exec_callback function, void *context)
+{
+	return __acpi_os_execute(type, function, context, 0);
+}
 EXPORT_SYMBOL(acpi_os_execute);
 
+acpi_status acpi_os_hotplug_execute(acpi_osd_exec_callback function,
+	void *context)
+{
+	return __acpi_os_execute(0, function, context, 1);
+}
+
 void acpi_os_wait_events_complete(void *context)
 {
 	flush_workqueue(kacpid_wq);
diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 3f93a6b4e17f..b91440ac0d16 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -193,6 +193,9 @@ acpi_status
 acpi_os_execute(acpi_execute_type type,
 		acpi_osd_exec_callback function, void *context);
 
+acpi_status
+acpi_os_hotplug_execute(acpi_osd_exec_callback function, void *context);
+
 void acpi_os_wait_events_complete(void *context);
 
 void acpi_os_sleep(acpi_integer milliseconds);
-- 
cgit v1.2.3


From 1253f7aabfebc51446dbec5c8895c5c8846dfe06 Mon Sep 17 00:00:00 2001
From: Shaohua Li <shaohua.li@intel.com>
Date: Thu, 28 Aug 2008 10:06:16 +0800
Subject: dock: introduce .uevent for devices in dock, eg libata

dock's uevent reported itself, not ata. It might be difficult to find an
ata device just according to a dock. This patch introduces docking ops
for each device in a dock. when docking, dock driver can send device
specific uevent. This should help dock station too (not just bay)

Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Acked-by: Tejun Heo <htejun@gmail.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/dock.c                | 22 +++++++++++++------
 drivers/ata/libata-acpi.c          | 44 ++++++++++++++++++++++++++++++++++++--
 drivers/pci/hotplug/acpiphp_glue.c |  6 ++++--
 include/acpi/acpi_drivers.h        |  9 ++++++--
 4 files changed, 68 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index f19f643fb362..ac7dfefcb50b 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -75,7 +75,7 @@ struct dock_dependent_device {
 	struct list_head list;
 	struct list_head hotplug_list;
 	acpi_handle handle;
-	acpi_notify_handler handler;
+	struct acpi_dock_ops *ops;
 	void *context;
 };
 
@@ -385,8 +385,8 @@ static void hotplug_dock_devices(struct dock_station *ds, u32 event)
 	 * First call driver specific hotplug functions
 	 */
 	list_for_each_entry(dd, &ds->hotplug_devices, hotplug_list) {
-		if (dd->handler)
-			dd->handler(dd->handle, event, dd->context);
+		if (dd->ops && dd->ops->handler)
+			dd->ops->handler(dd->handle, event, dd->context);
 	}
 
 	/*
@@ -409,6 +409,7 @@ static void dock_event(struct dock_station *ds, u32 event, int num)
 	struct device *dev = &ds->dock_device->dev;
 	char event_string[13];
 	char *envp[] = { event_string, NULL };
+	struct dock_dependent_device *dd;
 
 	if (num == UNDOCK_EVENT)
 		sprintf(event_string, "EVENT=undock");
@@ -419,7 +420,14 @@ static void dock_event(struct dock_station *ds, u32 event, int num)
 	 * Indicate that the status of the dock station has
 	 * changed.
 	 */
-	kobject_uevent_env(&dev->kobj, KOBJ_CHANGE, envp);
+	if (num == DOCK_EVENT)
+		kobject_uevent_env(&dev->kobj, KOBJ_CHANGE, envp);
+
+	list_for_each_entry(dd, &ds->hotplug_devices, hotplug_list)
+		if (dd->ops && dd->ops->uevent)
+			dd->ops->uevent(dd->handle, event, dd->context);
+	if (num != DOCK_EVENT)
+		kobject_uevent_env(&dev->kobj, KOBJ_CHANGE, envp);
 }
 
 /**
@@ -588,7 +596,7 @@ EXPORT_SYMBOL_GPL(unregister_dock_notifier);
 /**
  * register_hotplug_dock_device - register a hotplug function
  * @handle: the handle of the device
- * @handler: the acpi_notifier_handler to call after docking
+ * @ops: handlers to call after docking
  * @context: device specific data
  *
  * If a driver would like to perform a hotplug operation after a dock
@@ -596,7 +604,7 @@ EXPORT_SYMBOL_GPL(unregister_dock_notifier);
  * the dock driver after _DCK is executed.
  */
 int
-register_hotplug_dock_device(acpi_handle handle, acpi_notify_handler handler,
+register_hotplug_dock_device(acpi_handle handle, struct acpi_dock_ops *ops,
 			     void *context)
 {
 	struct dock_dependent_device *dd;
@@ -612,7 +620,7 @@ register_hotplug_dock_device(acpi_handle handle, acpi_notify_handler handler,
 	list_for_each_entry(dock_station, &dock_stations, sibiling) {
 		dd = find_dock_dependent_device(dock_station, handle);
 		if (dd) {
-			dd->handler = handler;
+			dd->ops = ops;
 			dd->context = context;
 			dock_add_hotplug_device(dock_station, dd);
 			return 0;
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index 97727be7e158..c012307d0ba6 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -209,6 +209,46 @@ static void ata_acpi_ap_notify_dock(acpi_handle handle, u32 event, void *data)
 	ata_acpi_handle_hotplug(ap, NULL, event);
 }
 
+static void ata_acpi_uevent(struct ata_port *ap, struct ata_device *dev,
+	u32 event)
+{
+	struct kobject *kobj = NULL;
+	char event_string[20];
+	char *envp[] = { event_string, NULL };
+
+	if (dev) {
+		if (dev->sdev)
+			kobj = &dev->sdev->sdev_gendev.kobj;
+	} else
+		kobj = &ap->dev->kobj;
+
+	if (kobj) {
+		snprintf(event_string, 20, "BAY_EVENT=%d", event);
+		kobject_uevent_env(kobj, KOBJ_CHANGE, envp);
+	}
+}
+
+static void ata_acpi_ap_uevent(acpi_handle handle, u32 event, void *data)
+{
+	ata_acpi_uevent(data, NULL, event);
+}
+
+static void ata_acpi_dev_uevent(acpi_handle handle, u32 event, void *data)
+{
+	struct ata_device *dev = data;
+	ata_acpi_uevent(dev->link->ap, dev, event);
+}
+
+static struct acpi_dock_ops ata_acpi_dev_dock_ops = {
+	.handler = ata_acpi_dev_notify_dock,
+	.uevent = ata_acpi_dev_uevent,
+};
+
+static struct acpi_dock_ops ata_acpi_ap_dock_ops = {
+	.handler = ata_acpi_ap_notify_dock,
+	.uevent = ata_acpi_ap_uevent,
+};
+
 /**
  * ata_acpi_associate - associate ATA host with ACPI objects
  * @host: target ATA host
@@ -244,7 +284,7 @@ void ata_acpi_associate(struct ata_host *host)
 		if (ap->acpi_handle) {
 			/* we might be on a docking station */
 			register_hotplug_dock_device(ap->acpi_handle,
-					     ata_acpi_ap_notify_dock, ap);
+					     &ata_acpi_ap_dock_ops, ap);
 		}
 
 		for (j = 0; j < ata_link_max_devices(&ap->link); j++) {
@@ -253,7 +293,7 @@ void ata_acpi_associate(struct ata_host *host)
 			if (dev->acpi_handle) {
 				/* we might be on a docking station */
 				register_hotplug_dock_device(dev->acpi_handle,
-					     ata_acpi_dev_notify_dock, dev);
+					     &ata_acpi_dev_dock_ops, dev);
 			}
 		}
 	}
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index a3e4705dd8f0..db54c5ef2aa5 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -169,7 +169,9 @@ static int post_dock_fixups(struct notifier_block *nb, unsigned long val,
 }
 
 
-
+static struct acpi_dock_ops acpiphp_dock_ops = {
+	.handler = handle_hotplug_event_func,
+};
 
 /* callback routine to register each ACPI PCI slot object */
 static acpi_status
@@ -285,7 +287,7 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
 		 */
 		newfunc->flags &= ~FUNC_HAS_EJ0;
 		if (register_hotplug_dock_device(handle,
-			handle_hotplug_event_func, newfunc))
+			&acpiphp_dock_ops, newfunc))
 			dbg("failed to register dock device\n");
 
 		/* we need to be notified when dock events happen
diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h
index e5f38e5ce86f..4f5042a0ef80 100644
--- a/include/acpi/acpi_drivers.h
+++ b/include/acpi/acpi_drivers.h
@@ -115,12 +115,17 @@ int acpi_processor_set_thermal_limit(acpi_handle handle, int type);
 /*--------------------------------------------------------------------------
                                   Dock Station
   -------------------------------------------------------------------------- */
+struct acpi_dock_ops {
+	acpi_notify_handler handler;
+	acpi_notify_handler uevent;
+};
+
 #if defined(CONFIG_ACPI_DOCK) || defined(CONFIG_ACPI_DOCK_MODULE)
 extern int is_dock_device(acpi_handle handle);
 extern int register_dock_notifier(struct notifier_block *nb);
 extern void unregister_dock_notifier(struct notifier_block *nb);
 extern int register_hotplug_dock_device(acpi_handle handle,
-					acpi_notify_handler handler,
+					struct acpi_dock_ops *ops,
 					void *context);
 extern void unregister_hotplug_dock_device(acpi_handle handle);
 #else
@@ -136,7 +141,7 @@ static inline void unregister_dock_notifier(struct notifier_block *nb)
 {
 }
 static inline int register_hotplug_dock_device(acpi_handle handle,
-					       acpi_notify_handler handler,
+					       struct acpi_dock_ops *ops,
 					       void *context)
 {
 	return -ENODEV;
-- 
cgit v1.2.3


From 5a9fa73072854981a5c05eb7ba18a96d49c2804f Mon Sep 17 00:00:00 2001
From: Oleg Nesterov <oleg@tv-sign.ru>
Date: Mon, 22 Sep 2008 14:42:50 -0700
Subject: posix-timers: kill ->it_sigev_signo and ->it_sigev_value

With the recent changes ->it_sigev_signo and ->it_sigev_value are only
used in sys_timer_create(), kill them.

Signed-off-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: mingo@elte.hu
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/posix-timers.h |  2 --
 kernel/posix-timers.c        | 17 +++++++----------
 2 files changed, 7 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index f9d8e9e94e9b..a7c721355549 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -45,8 +45,6 @@ struct k_itimer {
 	int it_requeue_pending;		/* waiting to requeue this timer */
 #define REQUEUE_PENDING 1
 	int it_sigev_notify;		/* notify word of sigevent struct */
-	int it_sigev_signo;		/* signo word of sigevent struct */
-	sigval_t it_sigev_value;	/* value word of sigevent struct */
 	struct task_struct *it_process;	/* process to send signal to */
 	struct sigqueue *sigq;		/* signal queue entry. */
 	union {
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index 7be385fe4eca..3eff47b0d8d5 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -510,10 +510,6 @@ sys_timer_create(const clockid_t which_clock,
 			error = -EFAULT;
 			goto out;
 		}
-		new_timer->it_sigev_notify = event.sigev_notify;
-		new_timer->it_sigev_signo = event.sigev_signo;
-		new_timer->it_sigev_value = event.sigev_value;
-
 		rcu_read_lock();
 		process = good_sigevent(&event);
 		if (process)
@@ -524,17 +520,18 @@ sys_timer_create(const clockid_t which_clock,
 			goto out;
 		}
 	} else {
-		new_timer->it_sigev_notify = SIGEV_SIGNAL;
-		new_timer->it_sigev_signo = SIGALRM;
-		new_timer->it_sigev_value.sival_int = new_timer->it_id;
+		event.sigev_notify = SIGEV_SIGNAL;
+		event.sigev_signo = SIGALRM;
+		event.sigev_value.sival_int = new_timer->it_id;
 		process = current->group_leader;
 		get_task_struct(process);
 	}
 
-	new_timer->sigq->info.si_code  = SI_TIMER;
+	new_timer->it_sigev_notify     = event.sigev_notify;
+	new_timer->sigq->info.si_signo = event.sigev_signo;
+	new_timer->sigq->info.si_value = event.sigev_value;
 	new_timer->sigq->info.si_tid   = new_timer->it_id;
-	new_timer->sigq->info.si_signo = new_timer->it_sigev_signo;
-	new_timer->sigq->info.si_value = new_timer->it_sigev_value;
+	new_timer->sigq->info.si_code  = SI_TIMER;
 
 	spin_lock_irq(&current->sighand->siglock);
 	new_timer->it_process = process;
-- 
cgit v1.2.3


From 1b02469088ac7a13d7e622b618b7410d0f1ce5ec Mon Sep 17 00:00:00 2001
From: Richard Kennedy <richard@rsk.demon.co.uk>
Date: Mon, 22 Sep 2008 14:42:43 -0700
Subject: hrtimer: reorder struct hrtimer to save 8 bytes on 64bit builds

reorder struct hrtimer to save 8 bytes on 64 bit builds when
CONFIG_TIMER_STATS selected.  (also removes 8 bytes from signal_struct)

Signed-off-by: Richard Kennedy <richard@rsk.demon.co.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/hrtimer.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 68b0196d8696..8730b60c9432 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -115,12 +115,12 @@ struct hrtimer {
 	enum hrtimer_restart		(*function)(struct hrtimer *);
 	struct hrtimer_clock_base	*base;
 	unsigned long			state;
-	enum hrtimer_cb_mode		cb_mode;
 	struct list_head		cb_entry;
+	enum hrtimer_cb_mode		cb_mode;
 #ifdef CONFIG_TIMER_STATS
+	int				start_pid;
 	void				*start_site;
 	char				start_comm[16];
-	int				start_pid;
 #endif
 };
 
-- 
cgit v1.2.3


From d40e944c25fb4642adb2a4c580a48218a9f3f824 Mon Sep 17 00:00:00 2001
From: Roman Zippel <zippel@linux-m68k.org>
Date: Mon, 22 Sep 2008 14:42:44 -0700
Subject: ntp: improve adjtimex frequency rounding

Change PPM_SCALE_INV_SHIFT so that it doesn't throw away any input bits
(19 is the amount of the factor 2 in PPM_SCALE), the output frequency
can then be calculated back to its input value, as the inverse divide
produce a slightly larger value, which is then correctly rounded by the
final shift.

Reported-by: Martin Ziegler <ziegler@uni-freiburg.de>
Signed-off-by: Roman Zippel <zippel@linux-m68k.org>
Cc: John Stultz <johnstul@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/timex.h | 2 +-
 kernel/time/ntp.c     | 5 ++---
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/timex.h b/include/linux/timex.h
index c00bcdd3ae42..9007313b5b71 100644
--- a/include/linux/timex.h
+++ b/include/linux/timex.h
@@ -82,7 +82,7 @@
  */
 #define SHIFT_USEC 16		/* frequency offset scale (shift) */
 #define PPM_SCALE (NSEC_PER_USEC << (NTP_SCALE_SHIFT - SHIFT_USEC))
-#define PPM_SCALE_INV_SHIFT 20
+#define PPM_SCALE_INV_SHIFT 19
 #define PPM_SCALE_INV ((1ll << (PPM_SCALE_INV_SHIFT + NTP_SCALE_SHIFT)) / \
 		       PPM_SCALE + 1)
 
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 450a45cb01c1..ddb0465a6baa 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -406,9 +406,8 @@ adj_done:
 	if (time_status & (STA_UNSYNC|STA_CLOCKERR))
 		result = TIME_ERROR;
 
-	txc->freq	   = shift_right((s32)(time_freq >> PPM_SCALE_INV_SHIFT) *
-					 (s64)PPM_SCALE_INV,
-					 NTP_SCALE_SHIFT);
+	txc->freq	   = shift_right((time_freq >> PPM_SCALE_INV_SHIFT) *
+					 (s64)PPM_SCALE_INV, NTP_SCALE_SHIFT);
 	txc->maxerror	   = time_maxerror;
 	txc->esterror	   = time_esterror;
 	txc->status	   = time_status;
-- 
cgit v1.2.3


From e416de5e61e1a9b7f987804cbb67230b5f5293c6 Mon Sep 17 00:00:00 2001
From: Alan Cox <alan@lxorguk.ukuu.org.uk>
Date: Tue, 23 Sep 2008 17:25:10 +0100
Subject: Export the ROM enable/disable helpers

.... so that they can be used by MTD map drivers. Lets us close #9420

Signed-off-by: Alan Cox <alan@redhat.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/pci/rom.c   | 6 ++++--
 include/linux/pci.h | 2 ++
 2 files changed, 6 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index bd5c0e031398..1f5f6143f35c 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -21,7 +21,7 @@
  * between the ROM and other resources, so enabling it may disable access
  * to MMIO registers or other card memory.
  */
-static int pci_enable_rom(struct pci_dev *pdev)
+int pci_enable_rom(struct pci_dev *pdev)
 {
 	struct resource *res = pdev->resource + PCI_ROM_RESOURCE;
 	struct pci_bus_region region;
@@ -45,7 +45,7 @@ static int pci_enable_rom(struct pci_dev *pdev)
  * Disable ROM decoding on a PCI device by turning off the last bit in the
  * ROM BAR.
  */
-static void pci_disable_rom(struct pci_dev *pdev)
+void pci_disable_rom(struct pci_dev *pdev)
 {
 	u32 rom_addr;
 	pci_read_config_dword(pdev, pdev->rom_base_reg, &rom_addr);
@@ -260,3 +260,5 @@ void pci_cleanup_rom(struct pci_dev *pdev)
 
 EXPORT_SYMBOL(pci_map_rom);
 EXPORT_SYMBOL(pci_unmap_rom);
+EXPORT_SYMBOL_GPL(pci_enable_rom);
+EXPORT_SYMBOL_GPL(pci_disable_rom);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c0e14008a3c2..7a4cee00c1d6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -631,6 +631,8 @@ int __must_check pci_assign_resource(struct pci_dev *dev, int i);
 int pci_select_bars(struct pci_dev *dev, unsigned long flags);
 
 /* ROM control related routines */
+int pci_enable_rom(struct pci_dev *pdev);
+void pci_disable_rom(struct pci_dev *pdev);
 void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size);
 void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom);
 size_t pci_get_rom_size(void __iomem *rom, size_t size);
-- 
cgit v1.2.3


From 7086efe1c1536f6bc160e7d60a9bfd645b91f279 Mon Sep 17 00:00:00 2001
From: Frank Mayhar <fmayhar@google.com>
Date: Fri, 12 Sep 2008 09:54:39 -0700
Subject: timers: fix itimer/many thread hang, v3

- fix UP lockup
- another set of UP/SMP cleanups and simplifications

Signed-off-by: Frank Mayhar <fmayhar@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/sched.h |   1 -
 kernel/sched.c        |   1 -
 kernel/sched_stats.h  | 126 +++++++++++++++-----------------------------------
 3 files changed, 38 insertions(+), 90 deletions(-)

(limited to 'include')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b982fb48c8f0..23d9d5464544 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2134,7 +2134,6 @@ static inline int thread_group_cputime_clone_thread(struct task_struct *curr)
 	return thread_group_cputime_alloc(curr);
 }
 
-
 static inline void thread_group_cputime_free(struct signal_struct *sig)
 {
 	free_percpu(sig->cputime.totals);
diff --git a/kernel/sched.c b/kernel/sched.c
index 260c22cc530a..29a3152c45db 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4046,7 +4046,6 @@ unsigned long long task_delta_exec(struct task_struct *p)
 	unsigned long flags;
 	u64 ns = 0;
 
-	rq = task_rq_lock(p, &flags);
 	if (task_current(rq, p)) {
 		u64 delta_exec;
 
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index d6903bd0c7a8..b8c156979cf2 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -276,133 +276,83 @@ sched_info_switch(struct task_struct *prev, struct task_struct *next)
  * on CONFIG_SCHEDSTATS.
  */
 
-#ifdef CONFIG_SMP
-
 /**
- * thread_group_cputime_account_user - Maintain utime for a thread group.
+ * account_group_user_time - Maintain utime for a thread group.
  *
- * @tgtimes:	Pointer to thread_group_cputime structure.
- * @cputime:	Time value by which to increment the utime field of that
- *		structure.
+ * @tsk:	Pointer to task structure.
+ * @cputime:	Time value by which to increment the utime field of the
+ *		thread_group_cputime structure.
  *
  * If thread group time is being maintained, get the structure for the
  * running CPU and update the utime field there.
  */
-static inline void thread_group_cputime_account_user(
-	struct thread_group_cputime *tgtimes,
-	cputime_t cputime)
+static inline void account_group_user_time(struct task_struct *tsk,
+					   cputime_t cputime)
 {
-	if (tgtimes->totals) {
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (unlikely(!sig))
+		return;
+	if (sig->cputime.totals) {
 		struct task_cputime *times;
 
-		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
 		times->utime = cputime_add(times->utime, cputime);
 		put_cpu_no_resched();
 	}
 }
 
 /**
- * thread_group_cputime_account_system - Maintain stime for a thread group.
+ * account_group_system_time - Maintain stime for a thread group.
  *
- * @tgtimes:	Pointer to thread_group_cputime structure.
- * @cputime:	Time value by which to increment the stime field of that
- *		structure.
+ * @tsk:	Pointer to task structure.
+ * @cputime:	Time value by which to increment the stime field of the
+ *		thread_group_cputime structure.
  *
  * If thread group time is being maintained, get the structure for the
  * running CPU and update the stime field there.
  */
-static inline void thread_group_cputime_account_system(
-	struct thread_group_cputime *tgtimes,
-	cputime_t cputime)
+static inline void account_group_system_time(struct task_struct *tsk,
+					     cputime_t cputime)
 {
-	if (tgtimes->totals) {
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (unlikely(!sig))
+		return;
+	if (sig->cputime.totals) {
 		struct task_cputime *times;
 
-		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
 		times->stime = cputime_add(times->stime, cputime);
 		put_cpu_no_resched();
 	}
 }
 
 /**
- * thread_group_cputime_account_exec_runtime - Maintain exec runtime for a
- *						thread group.
+ * account_group_exec_runtime - Maintain exec runtime for a thread group.
  *
- * @tgtimes:	Pointer to thread_group_cputime structure.
+ * @tsk:	Pointer to task structure.
  * @ns:		Time value by which to increment the sum_exec_runtime field
- *		of that structure.
+ *		of the thread_group_cputime structure.
  *
  * If thread group time is being maintained, get the structure for the
  * running CPU and update the sum_exec_runtime field there.
  */
-static inline void thread_group_cputime_account_exec_runtime(
-	struct thread_group_cputime *tgtimes,
-	unsigned long long ns)
+static inline void account_group_exec_runtime(struct task_struct *tsk,
+					      unsigned long long ns)
 {
-	if (tgtimes->totals) {
+	struct signal_struct *sig;
+
+	sig = tsk->signal;
+	if (unlikely(!sig))
+		return;
+	if (sig->cputime.totals) {
 		struct task_cputime *times;
 
-		times = per_cpu_ptr(tgtimes->totals, get_cpu());
+		times = per_cpu_ptr(sig->cputime.totals, get_cpu());
 		times->sum_exec_runtime += ns;
 		put_cpu_no_resched();
 	}
 }
-
-#else /* CONFIG_SMP */
-
-static inline void thread_group_cputime_account_user(
-	struct thread_group_cputime *tgtimes,
-	cputime_t cputime)
-{
-	tgtimes->totals->utime = cputime_add(tgtimes->totals->utime, cputime);
-}
-
-static inline void thread_group_cputime_account_system(
-	struct thread_group_cputime *tgtimes,
-	cputime_t cputime)
-{
-	tgtimes->totals->stime = cputime_add(tgtimes->totals->stime, cputime);
-}
-
-static inline void thread_group_cputime_account_exec_runtime(
-	struct thread_group_cputime *tgtimes,
-	unsigned long long ns)
-{
-	tgtimes->totals->sum_exec_runtime += ns;
-}
-
-#endif /* CONFIG_SMP */
-
-/*
- * These are the generic time-accounting routines that use the above
- * functions.  They are the functions actually called by the scheduler.
- */
-static inline void account_group_user_time(struct task_struct *tsk,
-					    cputime_t cputime)
-{
-	struct signal_struct *sig;
-
-	sig = tsk->signal;
-	if (likely(sig))
-		thread_group_cputime_account_user(&sig->cputime, cputime);
-}
-
-static inline void account_group_system_time(struct task_struct *tsk,
-					      cputime_t cputime)
-{
-	struct signal_struct *sig;
-
-	sig = tsk->signal;
-	if (likely(sig))
-		thread_group_cputime_account_system(&sig->cputime, cputime);
-}
-
-static inline void account_group_exec_runtime(struct task_struct *tsk,
-					       unsigned long long ns)
-{
-	struct signal_struct *sig;
-
-	sig = tsk->signal;
-	if (likely(sig))
-		thread_group_cputime_account_exec_runtime(&sig->cputime, ns);
-}
-- 
cgit v1.2.3


From bbfbd8b151fe35c9a1180a7f5254c5d6b8387cc0 Mon Sep 17 00:00:00 2001
From: Paul Mundt <lethal@linux-sh.org>
Date: Wed, 1 Oct 2008 16:13:54 +0900
Subject: sh: Move the shared INTC code out to drivers/sh/

The INTC code will be re-used across different architectures, so move
this out to drivers/sh/ and include/linux/sh_intc.h respectively.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
---
 arch/sh/include/asm/hw_irq.h    |  92 +-----
 arch/sh/kernel/cpu/irq/Makefile |   2 -
 arch/sh/kernel/cpu/irq/intc.c   | 712 ---------------------------------------
 drivers/sh/Makefile             |   2 +-
 drivers/sh/intc.c               | 713 ++++++++++++++++++++++++++++++++++++++++
 include/linux/sh_intc.h         |  91 +++++
 6 files changed, 807 insertions(+), 805 deletions(-)
 delete mode 100644 arch/sh/kernel/cpu/irq/intc.c
 create mode 100644 drivers/sh/intc.c
 create mode 100644 include/linux/sh_intc.h

(limited to 'include')

diff --git a/arch/sh/include/asm/hw_irq.h b/arch/sh/include/asm/hw_irq.h
index d557b00111bf..603cdde813d1 100644
--- a/arch/sh/include/asm/hw_irq.h
+++ b/arch/sh/include/asm/hw_irq.h
@@ -2,6 +2,7 @@
 #define __ASM_SH_HW_IRQ_H
 
 #include <linux/init.h>
+#include <linux/sh_intc.h>
 #include <asm/atomic.h>
 
 extern atomic_t irq_err_count;
@@ -23,101 +24,12 @@ struct ipr_desc {
 
 void register_ipr_controller(struct ipr_desc *);
 
-typedef unsigned char intc_enum;
-
-struct intc_vect {
-	intc_enum enum_id;
-	unsigned short vect;
-};
-
-#define INTC_VECT(enum_id, vect) { enum_id, vect }
-#define INTC_IRQ(enum_id, irq) INTC_VECT(enum_id, irq2evt(irq))
-
-struct intc_group {
-	intc_enum enum_id;
-	intc_enum enum_ids[32];
-};
-
-#define INTC_GROUP(enum_id, ids...) { enum_id, { ids } }
-
-struct intc_mask_reg {
-	unsigned long set_reg, clr_reg, reg_width;
-	intc_enum enum_ids[32];
-#ifdef CONFIG_SMP
-	unsigned long smp;
-#endif
-};
-
-struct intc_prio_reg {
-	unsigned long set_reg, clr_reg, reg_width, field_width;
-	intc_enum enum_ids[16];
-#ifdef CONFIG_SMP
-	unsigned long smp;
-#endif
-};
-
-struct intc_sense_reg {
-	unsigned long reg, reg_width, field_width;
-	intc_enum enum_ids[16];
-};
-
-#ifdef CONFIG_SMP
-#define INTC_SMP(stride, nr) .smp = (stride) | ((nr) << 8)
-#else
-#define INTC_SMP(stride, nr)
-#endif
-
-struct intc_desc {
-	struct intc_vect *vectors;
-	unsigned int nr_vectors;
-	struct intc_group *groups;
-	unsigned int nr_groups;
-	struct intc_mask_reg *mask_regs;
-	unsigned int nr_mask_regs;
-	struct intc_prio_reg *prio_regs;
-	unsigned int nr_prio_regs;
-	struct intc_sense_reg *sense_regs;
-	unsigned int nr_sense_regs;
-	char *name;
-#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
-	struct intc_mask_reg *ack_regs;
-	unsigned int nr_ack_regs;
-#endif
-};
-
-#define _INTC_ARRAY(a) a, sizeof(a)/sizeof(*a)
-#define DECLARE_INTC_DESC(symbol, chipname, vectors, groups,		\
-	mask_regs, prio_regs, sense_regs)				\
-struct intc_desc symbol __initdata = {					\
-	_INTC_ARRAY(vectors), _INTC_ARRAY(groups),			\
-	_INTC_ARRAY(mask_regs), _INTC_ARRAY(prio_regs),			\
-	_INTC_ARRAY(sense_regs),					\
-	chipname,							\
-}
-
-#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
-#define DECLARE_INTC_DESC_ACK(symbol, chipname, vectors, groups,	\
-	mask_regs, prio_regs, sense_regs, ack_regs)			\
-struct intc_desc symbol __initdata = {					\
-	_INTC_ARRAY(vectors), _INTC_ARRAY(groups),			\
-	_INTC_ARRAY(mask_regs), _INTC_ARRAY(prio_regs),			\
-	_INTC_ARRAY(sense_regs),					\
-	chipname,							\
-	_INTC_ARRAY(ack_regs),						\
-}
-#endif
-
-void __init register_intc_controller(struct intc_desc *desc);
-int intc_set_priority(unsigned int irq, unsigned int prio);
-
 void __init plat_irq_setup(void);
-#ifdef CONFIG_CPU_SH3
 void __init plat_irq_setup_sh3(void);
-#endif
+void __init plat_irq_setup_pins(int mode);
 
 enum { IRQ_MODE_IRQ, IRQ_MODE_IRQ7654, IRQ_MODE_IRQ3210,
        IRQ_MODE_IRL7654_MASK, IRQ_MODE_IRL3210_MASK,
        IRQ_MODE_IRL7654, IRQ_MODE_IRL3210 };
-void __init plat_irq_setup_pins(int mode);
 
 #endif /* __ASM_SH_HW_IRQ_H */
diff --git a/arch/sh/kernel/cpu/irq/Makefile b/arch/sh/kernel/cpu/irq/Makefile
index 462a8f6dfee2..f0c7025a67d1 100644
--- a/arch/sh/kernel/cpu/irq/Makefile
+++ b/arch/sh/kernel/cpu/irq/Makefile
@@ -1,8 +1,6 @@
 #
 # Makefile for the Linux/SuperH CPU-specifc IRQ handlers.
 #
-obj-y	+= intc.o
-
 obj-$(CONFIG_SUPERH32)			+= imask.o
 obj-$(CONFIG_CPU_SH5)			+= intc-sh5.o
 obj-$(CONFIG_CPU_HAS_IPR_IRQ)		+= ipr.o
diff --git a/arch/sh/kernel/cpu/irq/intc.c b/arch/sh/kernel/cpu/irq/intc.c
deleted file mode 100644
index 138efa4e95db..000000000000
--- a/arch/sh/kernel/cpu/irq/intc.c
+++ /dev/null
@@ -1,712 +0,0 @@
-/*
- * Shared interrupt handling code for IPR and INTC2 types of IRQs.
- *
- * Copyright (C) 2007, 2008 Magnus Damm
- *
- * Based on intc2.c and ipr.c
- *
- * Copyright (C) 1999  Niibe Yutaka & Takeshi Yaegashi
- * Copyright (C) 2000  Kazumoto Kojima
- * Copyright (C) 2001  David J. Mckay (david.mckay@st.com)
- * Copyright (C) 2003  Takashi Kusuda <kusuda-takashi@hitachi-ul.co.jp>
- * Copyright (C) 2005, 2006  Paul Mundt
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/init.h>
-#include <linux/irq.h>
-#include <linux/module.h>
-#include <linux/io.h>
-#include <linux/interrupt.h>
-#include <linux/bootmem.h>
-
-#define _INTC_MK(fn, mode, addr_e, addr_d, width, shift) \
-	((shift) | ((width) << 5) | ((fn) << 9) | ((mode) << 13) | \
-	 ((addr_e) << 16) | ((addr_d << 24)))
-
-#define _INTC_SHIFT(h) (h & 0x1f)
-#define _INTC_WIDTH(h) ((h >> 5) & 0xf)
-#define _INTC_FN(h) ((h >> 9) & 0xf)
-#define _INTC_MODE(h) ((h >> 13) & 0x7)
-#define _INTC_ADDR_E(h) ((h >> 16) & 0xff)
-#define _INTC_ADDR_D(h) ((h >> 24) & 0xff)
-
-struct intc_handle_int {
-	unsigned int irq;
-	unsigned long handle;
-};
-
-struct intc_desc_int {
-	unsigned long *reg;
-#ifdef CONFIG_SMP
-	unsigned long *smp;
-#endif
-	unsigned int nr_reg;
-	struct intc_handle_int *prio;
-	unsigned int nr_prio;
-	struct intc_handle_int *sense;
-	unsigned int nr_sense;
-	struct irq_chip chip;
-};
-
-#ifdef CONFIG_SMP
-#define IS_SMP(x) x.smp
-#define INTC_REG(d, x, c) (d->reg[(x)] + ((d->smp[(x)] & 0xff) * c))
-#define SMP_NR(d, x) ((d->smp[(x)] >> 8) ? (d->smp[(x)] >> 8) : 1)
-#else
-#define IS_SMP(x) 0
-#define INTC_REG(d, x, c) (d->reg[(x)])
-#define SMP_NR(d, x) 1
-#endif
-
-static unsigned int intc_prio_level[NR_IRQS]; /* for now */
-#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
-static unsigned long ack_handle[NR_IRQS];
-#endif
-
-static inline struct intc_desc_int *get_intc_desc(unsigned int irq)
-{
-	struct irq_chip *chip = get_irq_chip(irq);
-	return (void *)((char *)chip - offsetof(struct intc_desc_int, chip));
-}
-
-static inline unsigned int set_field(unsigned int value,
-				     unsigned int field_value,
-				     unsigned int handle)
-{
-	unsigned int width = _INTC_WIDTH(handle);
-	unsigned int shift = _INTC_SHIFT(handle);
-
-	value &= ~(((1 << width) - 1) << shift);
-	value |= field_value << shift;
-	return value;
-}
-
-static void write_8(unsigned long addr, unsigned long h, unsigned long data)
-{
-	__raw_writeb(set_field(0, data, h), addr);
-}
-
-static void write_16(unsigned long addr, unsigned long h, unsigned long data)
-{
-	__raw_writew(set_field(0, data, h), addr);
-}
-
-static void write_32(unsigned long addr, unsigned long h, unsigned long data)
-{
-	__raw_writel(set_field(0, data, h), addr);
-}
-
-static void modify_8(unsigned long addr, unsigned long h, unsigned long data)
-{
-	unsigned long flags;
-	local_irq_save(flags);
-	__raw_writeb(set_field(__raw_readb(addr), data, h), addr);
-	local_irq_restore(flags);
-}
-
-static void modify_16(unsigned long addr, unsigned long h, unsigned long data)
-{
-	unsigned long flags;
-	local_irq_save(flags);
-	__raw_writew(set_field(__raw_readw(addr), data, h), addr);
-	local_irq_restore(flags);
-}
-
-static void modify_32(unsigned long addr, unsigned long h, unsigned long data)
-{
-	unsigned long flags;
-	local_irq_save(flags);
-	__raw_writel(set_field(__raw_readl(addr), data, h), addr);
-	local_irq_restore(flags);
-}
-
-enum {	REG_FN_ERR = 0, REG_FN_WRITE_BASE = 1, REG_FN_MODIFY_BASE = 5 };
-
-static void (*intc_reg_fns[])(unsigned long addr,
-			      unsigned long h,
-			      unsigned long data) = {
-	[REG_FN_WRITE_BASE + 0] = write_8,
-	[REG_FN_WRITE_BASE + 1] = write_16,
-	[REG_FN_WRITE_BASE + 3] = write_32,
-	[REG_FN_MODIFY_BASE + 0] = modify_8,
-	[REG_FN_MODIFY_BASE + 1] = modify_16,
-	[REG_FN_MODIFY_BASE + 3] = modify_32,
-};
-
-enum {	MODE_ENABLE_REG = 0, /* Bit(s) set -> interrupt enabled */
-	MODE_MASK_REG,       /* Bit(s) set -> interrupt disabled */
-	MODE_DUAL_REG,       /* Two registers, set bit to enable / disable */
-	MODE_PRIO_REG,       /* Priority value written to enable interrupt */
-	MODE_PCLR_REG,       /* Above plus all bits set to disable interrupt */
-};
-
-static void intc_mode_field(unsigned long addr,
-			    unsigned long handle,
-			    void (*fn)(unsigned long,
-				       unsigned long,
-				       unsigned long),
-			    unsigned int irq)
-{
-	fn(addr, handle, ((1 << _INTC_WIDTH(handle)) - 1));
-}
-
-static void intc_mode_zero(unsigned long addr,
-			   unsigned long handle,
-			   void (*fn)(unsigned long,
-				       unsigned long,
-				       unsigned long),
-			   unsigned int irq)
-{
-	fn(addr, handle, 0);
-}
-
-static void intc_mode_prio(unsigned long addr,
-			   unsigned long handle,
-			   void (*fn)(unsigned long,
-				       unsigned long,
-				       unsigned long),
-			   unsigned int irq)
-{
-	fn(addr, handle, intc_prio_level[irq]);
-}
-
-static void (*intc_enable_fns[])(unsigned long addr,
-				 unsigned long handle,
-				 void (*fn)(unsigned long,
-					    unsigned long,
-					    unsigned long),
-				 unsigned int irq) = {
-	[MODE_ENABLE_REG] = intc_mode_field,
-	[MODE_MASK_REG] = intc_mode_zero,
-	[MODE_DUAL_REG] = intc_mode_field,
-	[MODE_PRIO_REG] = intc_mode_prio,
-	[MODE_PCLR_REG] = intc_mode_prio,
-};
-
-static void (*intc_disable_fns[])(unsigned long addr,
-				  unsigned long handle,
-				  void (*fn)(unsigned long,
-					     unsigned long,
-					     unsigned long),
-				  unsigned int irq) = {
-	[MODE_ENABLE_REG] = intc_mode_zero,
-	[MODE_MASK_REG] = intc_mode_field,
-	[MODE_DUAL_REG] = intc_mode_field,
-	[MODE_PRIO_REG] = intc_mode_zero,
-	[MODE_PCLR_REG] = intc_mode_field,
-};
-
-static inline void _intc_enable(unsigned int irq, unsigned long handle)
-{
-	struct intc_desc_int *d = get_intc_desc(irq);
-	unsigned long addr;
-	unsigned int cpu;
-
-	for (cpu = 0; cpu < SMP_NR(d, _INTC_ADDR_E(handle)); cpu++) {
-		addr = INTC_REG(d, _INTC_ADDR_E(handle), cpu);
-		intc_enable_fns[_INTC_MODE(handle)](addr, handle, intc_reg_fns\
-						    [_INTC_FN(handle)], irq);
-	}
-}
-
-static void intc_enable(unsigned int irq)
-{
-	_intc_enable(irq, (unsigned long)get_irq_chip_data(irq));
-}
-
-static void intc_disable(unsigned int irq)
-{
-	struct intc_desc_int *d = get_intc_desc(irq);
-	unsigned long handle = (unsigned long) get_irq_chip_data(irq);
-	unsigned long addr;
-	unsigned int cpu;
-
-	for (cpu = 0; cpu < SMP_NR(d, _INTC_ADDR_D(handle)); cpu++) {
-		addr = INTC_REG(d, _INTC_ADDR_D(handle), cpu);
-		intc_disable_fns[_INTC_MODE(handle)](addr, handle,intc_reg_fns\
-						     [_INTC_FN(handle)], irq);
-	}
-}
-
-#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
-static void intc_mask_ack(unsigned int irq)
-{
-	struct intc_desc_int *d = get_intc_desc(irq);
-	unsigned long handle = ack_handle[irq];
-	unsigned long addr;
-
-	intc_disable(irq);
-
-	/* read register and write zero only to the assocaited bit */
-
-	if (handle) {
-		addr = INTC_REG(d, _INTC_ADDR_D(handle), 0);
-		switch (_INTC_FN(handle)) {
-		case REG_FN_MODIFY_BASE + 0:	/* 8bit */
-			__raw_readb(addr);
-			__raw_writeb(0xff ^ set_field(0, 1, handle), addr);
-			break;
-		case REG_FN_MODIFY_BASE + 1:	/* 16bit */
-			__raw_readw(addr);
-			__raw_writew(0xffff ^ set_field(0, 1, handle), addr);
-			break;
-		case REG_FN_MODIFY_BASE + 3:	/* 32bit */
-			__raw_readl(addr);
-			__raw_writel(0xffffffff ^ set_field(0, 1, handle), addr);
-			break;
-		default:
-			BUG();
-			break;
-		}
-	}
-}
-#endif
-
-static struct intc_handle_int *intc_find_irq(struct intc_handle_int *hp,
-					     unsigned int nr_hp,
-					     unsigned int irq)
-{
-	int i;
-
-	/* this doesn't scale well, but...
-	 *
-	 * this function should only be used for cerain uncommon
-	 * operations such as intc_set_priority() and intc_set_sense()
-	 * and in those rare cases performance doesn't matter that much.
-	 * keeping the memory footprint low is more important.
-	 *
-	 * one rather simple way to speed this up and still keep the
-	 * memory footprint down is to make sure the array is sorted
-	 * and then perform a bisect to lookup the irq.
-	 */
-
-	for (i = 0; i < nr_hp; i++) {
-		if ((hp + i)->irq != irq)
-			continue;
-
-		return hp + i;
-	}
-
-	return NULL;
-}
-
-int intc_set_priority(unsigned int irq, unsigned int prio)
-{
-	struct intc_desc_int *d = get_intc_desc(irq);
-	struct intc_handle_int *ihp;
-
-	if (!intc_prio_level[irq] || prio <= 1)
-		return -EINVAL;
-
-	ihp = intc_find_irq(d->prio, d->nr_prio, irq);
-	if (ihp) {
-		if (prio >= (1 << _INTC_WIDTH(ihp->handle)))
-			return -EINVAL;
-
-		intc_prio_level[irq] = prio;
-
-		/*
-		 * only set secondary masking method directly
-		 * primary masking method is using intc_prio_level[irq]
-		 * priority level will be set during next enable()
-		 */
-
-		if (_INTC_FN(ihp->handle) != REG_FN_ERR)
-			_intc_enable(irq, ihp->handle);
-	}
-	return 0;
-}
-
-#define VALID(x) (x | 0x80)
-
-static unsigned char intc_irq_sense_table[IRQ_TYPE_SENSE_MASK + 1] = {
-	[IRQ_TYPE_EDGE_FALLING] = VALID(0),
-	[IRQ_TYPE_EDGE_RISING] = VALID(1),
-	[IRQ_TYPE_LEVEL_LOW] = VALID(2),
-	/* SH7706, SH7707 and SH7709 do not support high level triggered */
-#if !defined(CONFIG_CPU_SUBTYPE_SH7706) && \
-    !defined(CONFIG_CPU_SUBTYPE_SH7707) && \
-    !defined(CONFIG_CPU_SUBTYPE_SH7709)
-	[IRQ_TYPE_LEVEL_HIGH] = VALID(3),
-#endif
-};
-
-static int intc_set_sense(unsigned int irq, unsigned int type)
-{
-	struct intc_desc_int *d = get_intc_desc(irq);
-	unsigned char value = intc_irq_sense_table[type & IRQ_TYPE_SENSE_MASK];
-	struct intc_handle_int *ihp;
-	unsigned long addr;
-
-	if (!value)
-		return -EINVAL;
-
-	ihp = intc_find_irq(d->sense, d->nr_sense, irq);
-	if (ihp) {
-		addr = INTC_REG(d, _INTC_ADDR_E(ihp->handle), 0);
-		intc_reg_fns[_INTC_FN(ihp->handle)](addr, ihp->handle, value);
-	}
-	return 0;
-}
-
-static unsigned int __init intc_get_reg(struct intc_desc_int *d,
-				 unsigned long address)
-{
-	unsigned int k;
-
-	for (k = 0; k < d->nr_reg; k++) {
-		if (d->reg[k] == address)
-			return k;
-	}
-
-	BUG();
-	return 0;
-}
-
-static intc_enum __init intc_grp_id(struct intc_desc *desc,
-				    intc_enum enum_id)
-{
-	struct intc_group *g = desc->groups;
-	unsigned int i, j;
-
-	for (i = 0; g && enum_id && i < desc->nr_groups; i++) {
-		g = desc->groups + i;
-
-		for (j = 0; g->enum_ids[j]; j++) {
-			if (g->enum_ids[j] != enum_id)
-				continue;
-
-			return g->enum_id;
-		}
-	}
-
-	return 0;
-}
-
-static unsigned int __init intc_mask_data(struct intc_desc *desc,
-					  struct intc_desc_int *d,
-					  intc_enum enum_id, int do_grps)
-{
-	struct intc_mask_reg *mr = desc->mask_regs;
-	unsigned int i, j, fn, mode;
-	unsigned long reg_e, reg_d;
-
-	for (i = 0; mr && enum_id && i < desc->nr_mask_regs; i++) {
-		mr = desc->mask_regs + i;
-
-		for (j = 0; j < ARRAY_SIZE(mr->enum_ids); j++) {
-			if (mr->enum_ids[j] != enum_id)
-				continue;
-
-			if (mr->set_reg && mr->clr_reg) {
-				fn = REG_FN_WRITE_BASE;
-				mode = MODE_DUAL_REG;
-				reg_e = mr->clr_reg;
-				reg_d = mr->set_reg;
-			} else {
-				fn = REG_FN_MODIFY_BASE;
-				if (mr->set_reg) {
-					mode = MODE_ENABLE_REG;
-					reg_e = mr->set_reg;
-					reg_d = mr->set_reg;
-				} else {
-					mode = MODE_MASK_REG;
-					reg_e = mr->clr_reg;
-					reg_d = mr->clr_reg;
-				}
-			}
-
-			fn += (mr->reg_width >> 3) - 1;
-			return _INTC_MK(fn, mode,
-					intc_get_reg(d, reg_e),
-					intc_get_reg(d, reg_d),
-					1,
-					(mr->reg_width - 1) - j);
-		}
-	}
-
-	if (do_grps)
-		return intc_mask_data(desc, d, intc_grp_id(desc, enum_id), 0);
-
-	return 0;
-}
-
-static unsigned int __init intc_prio_data(struct intc_desc *desc,
-					  struct intc_desc_int *d,
-					  intc_enum enum_id, int do_grps)
-{
-	struct intc_prio_reg *pr = desc->prio_regs;
-	unsigned int i, j, fn, mode, bit;
-	unsigned long reg_e, reg_d;
-
-	for (i = 0; pr && enum_id && i < desc->nr_prio_regs; i++) {
-		pr = desc->prio_regs + i;
-
-		for (j = 0; j < ARRAY_SIZE(pr->enum_ids); j++) {
-			if (pr->enum_ids[j] != enum_id)
-				continue;
-
-			if (pr->set_reg && pr->clr_reg) {
-				fn = REG_FN_WRITE_BASE;
-				mode = MODE_PCLR_REG;
-				reg_e = pr->set_reg;
-				reg_d = pr->clr_reg;
-			} else {
-				fn = REG_FN_MODIFY_BASE;
-				mode = MODE_PRIO_REG;
-				if (!pr->set_reg)
-					BUG();
-				reg_e = pr->set_reg;
-				reg_d = pr->set_reg;
-			}
-
-			fn += (pr->reg_width >> 3) - 1;
-
-			BUG_ON((j + 1) * pr->field_width > pr->reg_width);
-
-			bit = pr->reg_width - ((j + 1) * pr->field_width);
-
-			return _INTC_MK(fn, mode,
-					intc_get_reg(d, reg_e),
-					intc_get_reg(d, reg_d),
-					pr->field_width, bit);
-		}
-	}
-
-	if (do_grps)
-		return intc_prio_data(desc, d, intc_grp_id(desc, enum_id), 0);
-
-	return 0;
-}
-
-#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
-static unsigned int __init intc_ack_data(struct intc_desc *desc,
-					  struct intc_desc_int *d,
-					  intc_enum enum_id)
-{
-	struct intc_mask_reg *mr = desc->ack_regs;
-	unsigned int i, j, fn, mode;
-	unsigned long reg_e, reg_d;
-
-	for (i = 0; mr && enum_id && i < desc->nr_ack_regs; i++) {
-		mr = desc->ack_regs + i;
-
-		for (j = 0; j < ARRAY_SIZE(mr->enum_ids); j++) {
-			if (mr->enum_ids[j] != enum_id)
-				continue;
-
-			fn = REG_FN_MODIFY_BASE;
-			mode = MODE_ENABLE_REG;
-			reg_e = mr->set_reg;
-			reg_d = mr->set_reg;
-
-			fn += (mr->reg_width >> 3) - 1;
-			return _INTC_MK(fn, mode,
-					intc_get_reg(d, reg_e),
-					intc_get_reg(d, reg_d),
-					1,
-					(mr->reg_width - 1) - j);
-		}
-	}
-
-	return 0;
-}
-#endif
-
-static unsigned int __init intc_sense_data(struct intc_desc *desc,
-					   struct intc_desc_int *d,
-					   intc_enum enum_id)
-{
-	struct intc_sense_reg *sr = desc->sense_regs;
-	unsigned int i, j, fn, bit;
-
-	for (i = 0; sr && enum_id && i < desc->nr_sense_regs; i++) {
-		sr = desc->sense_regs + i;
-
-		for (j = 0; j < ARRAY_SIZE(sr->enum_ids); j++) {
-			if (sr->enum_ids[j] != enum_id)
-				continue;
-
-			fn = REG_FN_MODIFY_BASE;
-			fn += (sr->reg_width >> 3) - 1;
-
-			BUG_ON((j + 1) * sr->field_width > sr->reg_width);
-
-			bit = sr->reg_width - ((j + 1) * sr->field_width);
-
-			return _INTC_MK(fn, 0, intc_get_reg(d, sr->reg),
-					0, sr->field_width, bit);
-		}
-	}
-
-	return 0;
-}
-
-static void __init intc_register_irq(struct intc_desc *desc,
-				     struct intc_desc_int *d,
-				     intc_enum enum_id,
-				     unsigned int irq)
-{
-	struct intc_handle_int *hp;
-	unsigned int data[2], primary;
-
-	/* Prefer single interrupt source bitmap over other combinations:
-	 * 1. bitmap, single interrupt source
-	 * 2. priority, single interrupt source
-	 * 3. bitmap, multiple interrupt sources (groups)
-	 * 4. priority, multiple interrupt sources (groups)
-	 */
-
-	data[0] = intc_mask_data(desc, d, enum_id, 0);
-	data[1] = intc_prio_data(desc, d, enum_id, 0);
-
-	primary = 0;
-	if (!data[0] && data[1])
-		primary = 1;
-
-	data[0] = data[0] ? data[0] : intc_mask_data(desc, d, enum_id, 1);
-	data[1] = data[1] ? data[1] : intc_prio_data(desc, d, enum_id, 1);
-
-	if (!data[primary])
-		primary ^= 1;
-
-	BUG_ON(!data[primary]); /* must have primary masking method */
-
-	disable_irq_nosync(irq);
-	set_irq_chip_and_handler_name(irq, &d->chip,
-				      handle_level_irq, "level");
-	set_irq_chip_data(irq, (void *)data[primary]);
-
-	/* set priority level
-	 * - this needs to be at least 2 for 5-bit priorities on 7780
-	 */
-	intc_prio_level[irq] = 2;
-
-	/* enable secondary masking method if present */
-	if (data[!primary])
-		_intc_enable(irq, data[!primary]);
-
-	/* add irq to d->prio list if priority is available */
-	if (data[1]) {
-		hp = d->prio + d->nr_prio;
-		hp->irq = irq;
-		hp->handle = data[1];
-
-		if (primary) {
-			/*
-			 * only secondary priority should access registers, so
-			 * set _INTC_FN(h) = REG_FN_ERR for intc_set_priority()
-			 */
-
-			hp->handle &= ~_INTC_MK(0x0f, 0, 0, 0, 0, 0);
-			hp->handle |= _INTC_MK(REG_FN_ERR, 0, 0, 0, 0, 0);
-		}
-		d->nr_prio++;
-	}
-
-	/* add irq to d->sense list if sense is available */
-	data[0] = intc_sense_data(desc, d, enum_id);
-	if (data[0]) {
-		(d->sense + d->nr_sense)->irq = irq;
-		(d->sense + d->nr_sense)->handle = data[0];
-		d->nr_sense++;
-	}
-
-	/* irq should be disabled by default */
-	d->chip.mask(irq);
-
-#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
-	if (desc->ack_regs)
-		ack_handle[irq] = intc_ack_data(desc, d, enum_id);
-#endif
-}
-
-static unsigned int __init save_reg(struct intc_desc_int *d,
-				    unsigned int cnt,
-				    unsigned long value,
-				    unsigned int smp)
-{
-	if (value) {
-		d->reg[cnt] = value;
-#ifdef CONFIG_SMP
-		d->smp[cnt] = smp;
-#endif
-		return 1;
-	}
-
-	return 0;
-}
-
-
-void __init register_intc_controller(struct intc_desc *desc)
-{
-	unsigned int i, k, smp;
-	struct intc_desc_int *d;
-
-	d = alloc_bootmem(sizeof(*d));
-
-	d->nr_reg = desc->mask_regs ? desc->nr_mask_regs * 2 : 0;
-	d->nr_reg += desc->prio_regs ? desc->nr_prio_regs * 2 : 0;
-	d->nr_reg += desc->sense_regs ? desc->nr_sense_regs : 0;
-
-#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
-	d->nr_reg += desc->ack_regs ? desc->nr_ack_regs : 0;
-#endif
-	d->reg = alloc_bootmem(d->nr_reg * sizeof(*d->reg));
-#ifdef CONFIG_SMP
-	d->smp = alloc_bootmem(d->nr_reg * sizeof(*d->smp));
-#endif
-	k = 0;
-
-	if (desc->mask_regs) {
-		for (i = 0; i < desc->nr_mask_regs; i++) {
-			smp = IS_SMP(desc->mask_regs[i]);
-			k += save_reg(d, k, desc->mask_regs[i].set_reg, smp);
-			k += save_reg(d, k, desc->mask_regs[i].clr_reg, smp);
-		}
-	}
-
-	if (desc->prio_regs) {
-		d->prio = alloc_bootmem(desc->nr_vectors * sizeof(*d->prio));
-
-		for (i = 0; i < desc->nr_prio_regs; i++) {
-			smp = IS_SMP(desc->prio_regs[i]);
-			k += save_reg(d, k, desc->prio_regs[i].set_reg, smp);
-			k += save_reg(d, k, desc->prio_regs[i].clr_reg, smp);
-		}
-	}
-
-	if (desc->sense_regs) {
-		d->sense = alloc_bootmem(desc->nr_vectors * sizeof(*d->sense));
-
-		for (i = 0; i < desc->nr_sense_regs; i++) {
-			k += save_reg(d, k, desc->sense_regs[i].reg, 0);
-		}
-	}
-
-	d->chip.name = desc->name;
-	d->chip.mask = intc_disable;
-	d->chip.unmask = intc_enable;
-	d->chip.mask_ack = intc_disable;
-	d->chip.set_type = intc_set_sense;
-
-#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
-	if (desc->ack_regs) {
-		for (i = 0; i < desc->nr_ack_regs; i++)
-			k += save_reg(d, k, desc->ack_regs[i].set_reg, 0);
-
-		d->chip.mask_ack = intc_mask_ack;
-	}
-#endif
-
-	BUG_ON(k > 256); /* _INTC_ADDR_E() and _INTC_ADDR_D() are 8 bits */
-
-	for (i = 0; i < desc->nr_vectors; i++) {
-		struct intc_vect *vect = desc->vectors + i;
-
-		intc_register_irq(desc, d, vect->enum_id, evt2irq(vect->vect));
-	}
-}
diff --git a/drivers/sh/Makefile b/drivers/sh/Makefile
index a96f4a8cfeb8..6a025cefe6dc 100644
--- a/drivers/sh/Makefile
+++ b/drivers/sh/Makefile
@@ -1,6 +1,6 @@
 #
 # Makefile for the SuperH specific drivers.
 #
-
 obj-$(CONFIG_SUPERHYWAY)	+= superhyway/
 obj-$(CONFIG_MAPLE)		+= maple/
+obj-y				+= intc.o
diff --git a/drivers/sh/intc.c b/drivers/sh/intc.c
new file mode 100644
index 000000000000..58d24c5a76ce
--- /dev/null
+++ b/drivers/sh/intc.c
@@ -0,0 +1,713 @@
+/*
+ * Shared interrupt handling code for IPR and INTC2 types of IRQs.
+ *
+ * Copyright (C) 2007, 2008 Magnus Damm
+ *
+ * Based on intc2.c and ipr.c
+ *
+ * Copyright (C) 1999  Niibe Yutaka & Takeshi Yaegashi
+ * Copyright (C) 2000  Kazumoto Kojima
+ * Copyright (C) 2001  David J. Mckay (david.mckay@st.com)
+ * Copyright (C) 2003  Takashi Kusuda <kusuda-takashi@hitachi-ul.co.jp>
+ * Copyright (C) 2005, 2006  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/bootmem.h>
+#include <linux/sh_intc.h>
+
+#define _INTC_MK(fn, mode, addr_e, addr_d, width, shift) \
+	((shift) | ((width) << 5) | ((fn) << 9) | ((mode) << 13) | \
+	 ((addr_e) << 16) | ((addr_d << 24)))
+
+#define _INTC_SHIFT(h) (h & 0x1f)
+#define _INTC_WIDTH(h) ((h >> 5) & 0xf)
+#define _INTC_FN(h) ((h >> 9) & 0xf)
+#define _INTC_MODE(h) ((h >> 13) & 0x7)
+#define _INTC_ADDR_E(h) ((h >> 16) & 0xff)
+#define _INTC_ADDR_D(h) ((h >> 24) & 0xff)
+
+struct intc_handle_int {
+	unsigned int irq;
+	unsigned long handle;
+};
+
+struct intc_desc_int {
+	unsigned long *reg;
+#ifdef CONFIG_SMP
+	unsigned long *smp;
+#endif
+	unsigned int nr_reg;
+	struct intc_handle_int *prio;
+	unsigned int nr_prio;
+	struct intc_handle_int *sense;
+	unsigned int nr_sense;
+	struct irq_chip chip;
+};
+
+#ifdef CONFIG_SMP
+#define IS_SMP(x) x.smp
+#define INTC_REG(d, x, c) (d->reg[(x)] + ((d->smp[(x)] & 0xff) * c))
+#define SMP_NR(d, x) ((d->smp[(x)] >> 8) ? (d->smp[(x)] >> 8) : 1)
+#else
+#define IS_SMP(x) 0
+#define INTC_REG(d, x, c) (d->reg[(x)])
+#define SMP_NR(d, x) 1
+#endif
+
+static unsigned int intc_prio_level[NR_IRQS]; /* for now */
+#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
+static unsigned long ack_handle[NR_IRQS];
+#endif
+
+static inline struct intc_desc_int *get_intc_desc(unsigned int irq)
+{
+	struct irq_chip *chip = get_irq_chip(irq);
+	return (void *)((char *)chip - offsetof(struct intc_desc_int, chip));
+}
+
+static inline unsigned int set_field(unsigned int value,
+				     unsigned int field_value,
+				     unsigned int handle)
+{
+	unsigned int width = _INTC_WIDTH(handle);
+	unsigned int shift = _INTC_SHIFT(handle);
+
+	value &= ~(((1 << width) - 1) << shift);
+	value |= field_value << shift;
+	return value;
+}
+
+static void write_8(unsigned long addr, unsigned long h, unsigned long data)
+{
+	__raw_writeb(set_field(0, data, h), addr);
+}
+
+static void write_16(unsigned long addr, unsigned long h, unsigned long data)
+{
+	__raw_writew(set_field(0, data, h), addr);
+}
+
+static void write_32(unsigned long addr, unsigned long h, unsigned long data)
+{
+	__raw_writel(set_field(0, data, h), addr);
+}
+
+static void modify_8(unsigned long addr, unsigned long h, unsigned long data)
+{
+	unsigned long flags;
+	local_irq_save(flags);
+	__raw_writeb(set_field(__raw_readb(addr), data, h), addr);
+	local_irq_restore(flags);
+}
+
+static void modify_16(unsigned long addr, unsigned long h, unsigned long data)
+{
+	unsigned long flags;
+	local_irq_save(flags);
+	__raw_writew(set_field(__raw_readw(addr), data, h), addr);
+	local_irq_restore(flags);
+}
+
+static void modify_32(unsigned long addr, unsigned long h, unsigned long data)
+{
+	unsigned long flags;
+	local_irq_save(flags);
+	__raw_writel(set_field(__raw_readl(addr), data, h), addr);
+	local_irq_restore(flags);
+}
+
+enum {	REG_FN_ERR = 0, REG_FN_WRITE_BASE = 1, REG_FN_MODIFY_BASE = 5 };
+
+static void (*intc_reg_fns[])(unsigned long addr,
+			      unsigned long h,
+			      unsigned long data) = {
+	[REG_FN_WRITE_BASE + 0] = write_8,
+	[REG_FN_WRITE_BASE + 1] = write_16,
+	[REG_FN_WRITE_BASE + 3] = write_32,
+	[REG_FN_MODIFY_BASE + 0] = modify_8,
+	[REG_FN_MODIFY_BASE + 1] = modify_16,
+	[REG_FN_MODIFY_BASE + 3] = modify_32,
+};
+
+enum {	MODE_ENABLE_REG = 0, /* Bit(s) set -> interrupt enabled */
+	MODE_MASK_REG,       /* Bit(s) set -> interrupt disabled */
+	MODE_DUAL_REG,       /* Two registers, set bit to enable / disable */
+	MODE_PRIO_REG,       /* Priority value written to enable interrupt */
+	MODE_PCLR_REG,       /* Above plus all bits set to disable interrupt */
+};
+
+static void intc_mode_field(unsigned long addr,
+			    unsigned long handle,
+			    void (*fn)(unsigned long,
+				       unsigned long,
+				       unsigned long),
+			    unsigned int irq)
+{
+	fn(addr, handle, ((1 << _INTC_WIDTH(handle)) - 1));
+}
+
+static void intc_mode_zero(unsigned long addr,
+			   unsigned long handle,
+			   void (*fn)(unsigned long,
+				       unsigned long,
+				       unsigned long),
+			   unsigned int irq)
+{
+	fn(addr, handle, 0);
+}
+
+static void intc_mode_prio(unsigned long addr,
+			   unsigned long handle,
+			   void (*fn)(unsigned long,
+				       unsigned long,
+				       unsigned long),
+			   unsigned int irq)
+{
+	fn(addr, handle, intc_prio_level[irq]);
+}
+
+static void (*intc_enable_fns[])(unsigned long addr,
+				 unsigned long handle,
+				 void (*fn)(unsigned long,
+					    unsigned long,
+					    unsigned long),
+				 unsigned int irq) = {
+	[MODE_ENABLE_REG] = intc_mode_field,
+	[MODE_MASK_REG] = intc_mode_zero,
+	[MODE_DUAL_REG] = intc_mode_field,
+	[MODE_PRIO_REG] = intc_mode_prio,
+	[MODE_PCLR_REG] = intc_mode_prio,
+};
+
+static void (*intc_disable_fns[])(unsigned long addr,
+				  unsigned long handle,
+				  void (*fn)(unsigned long,
+					     unsigned long,
+					     unsigned long),
+				  unsigned int irq) = {
+	[MODE_ENABLE_REG] = intc_mode_zero,
+	[MODE_MASK_REG] = intc_mode_field,
+	[MODE_DUAL_REG] = intc_mode_field,
+	[MODE_PRIO_REG] = intc_mode_zero,
+	[MODE_PCLR_REG] = intc_mode_field,
+};
+
+static inline void _intc_enable(unsigned int irq, unsigned long handle)
+{
+	struct intc_desc_int *d = get_intc_desc(irq);
+	unsigned long addr;
+	unsigned int cpu;
+
+	for (cpu = 0; cpu < SMP_NR(d, _INTC_ADDR_E(handle)); cpu++) {
+		addr = INTC_REG(d, _INTC_ADDR_E(handle), cpu);
+		intc_enable_fns[_INTC_MODE(handle)](addr, handle, intc_reg_fns\
+						    [_INTC_FN(handle)], irq);
+	}
+}
+
+static void intc_enable(unsigned int irq)
+{
+	_intc_enable(irq, (unsigned long)get_irq_chip_data(irq));
+}
+
+static void intc_disable(unsigned int irq)
+{
+	struct intc_desc_int *d = get_intc_desc(irq);
+	unsigned long handle = (unsigned long) get_irq_chip_data(irq);
+	unsigned long addr;
+	unsigned int cpu;
+
+	for (cpu = 0; cpu < SMP_NR(d, _INTC_ADDR_D(handle)); cpu++) {
+		addr = INTC_REG(d, _INTC_ADDR_D(handle), cpu);
+		intc_disable_fns[_INTC_MODE(handle)](addr, handle,intc_reg_fns\
+						     [_INTC_FN(handle)], irq);
+	}
+}
+
+#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
+static void intc_mask_ack(unsigned int irq)
+{
+	struct intc_desc_int *d = get_intc_desc(irq);
+	unsigned long handle = ack_handle[irq];
+	unsigned long addr;
+
+	intc_disable(irq);
+
+	/* read register and write zero only to the assocaited bit */
+
+	if (handle) {
+		addr = INTC_REG(d, _INTC_ADDR_D(handle), 0);
+		switch (_INTC_FN(handle)) {
+		case REG_FN_MODIFY_BASE + 0:	/* 8bit */
+			__raw_readb(addr);
+			__raw_writeb(0xff ^ set_field(0, 1, handle), addr);
+			break;
+		case REG_FN_MODIFY_BASE + 1:	/* 16bit */
+			__raw_readw(addr);
+			__raw_writew(0xffff ^ set_field(0, 1, handle), addr);
+			break;
+		case REG_FN_MODIFY_BASE + 3:	/* 32bit */
+			__raw_readl(addr);
+			__raw_writel(0xffffffff ^ set_field(0, 1, handle), addr);
+			break;
+		default:
+			BUG();
+			break;
+		}
+	}
+}
+#endif
+
+static struct intc_handle_int *intc_find_irq(struct intc_handle_int *hp,
+					     unsigned int nr_hp,
+					     unsigned int irq)
+{
+	int i;
+
+	/* this doesn't scale well, but...
+	 *
+	 * this function should only be used for cerain uncommon
+	 * operations such as intc_set_priority() and intc_set_sense()
+	 * and in those rare cases performance doesn't matter that much.
+	 * keeping the memory footprint low is more important.
+	 *
+	 * one rather simple way to speed this up and still keep the
+	 * memory footprint down is to make sure the array is sorted
+	 * and then perform a bisect to lookup the irq.
+	 */
+
+	for (i = 0; i < nr_hp; i++) {
+		if ((hp + i)->irq != irq)
+			continue;
+
+		return hp + i;
+	}
+
+	return NULL;
+}
+
+int intc_set_priority(unsigned int irq, unsigned int prio)
+{
+	struct intc_desc_int *d = get_intc_desc(irq);
+	struct intc_handle_int *ihp;
+
+	if (!intc_prio_level[irq] || prio <= 1)
+		return -EINVAL;
+
+	ihp = intc_find_irq(d->prio, d->nr_prio, irq);
+	if (ihp) {
+		if (prio >= (1 << _INTC_WIDTH(ihp->handle)))
+			return -EINVAL;
+
+		intc_prio_level[irq] = prio;
+
+		/*
+		 * only set secondary masking method directly
+		 * primary masking method is using intc_prio_level[irq]
+		 * priority level will be set during next enable()
+		 */
+
+		if (_INTC_FN(ihp->handle) != REG_FN_ERR)
+			_intc_enable(irq, ihp->handle);
+	}
+	return 0;
+}
+
+#define VALID(x) (x | 0x80)
+
+static unsigned char intc_irq_sense_table[IRQ_TYPE_SENSE_MASK + 1] = {
+	[IRQ_TYPE_EDGE_FALLING] = VALID(0),
+	[IRQ_TYPE_EDGE_RISING] = VALID(1),
+	[IRQ_TYPE_LEVEL_LOW] = VALID(2),
+	/* SH7706, SH7707 and SH7709 do not support high level triggered */
+#if !defined(CONFIG_CPU_SUBTYPE_SH7706) && \
+    !defined(CONFIG_CPU_SUBTYPE_SH7707) && \
+    !defined(CONFIG_CPU_SUBTYPE_SH7709)
+	[IRQ_TYPE_LEVEL_HIGH] = VALID(3),
+#endif
+};
+
+static int intc_set_sense(unsigned int irq, unsigned int type)
+{
+	struct intc_desc_int *d = get_intc_desc(irq);
+	unsigned char value = intc_irq_sense_table[type & IRQ_TYPE_SENSE_MASK];
+	struct intc_handle_int *ihp;
+	unsigned long addr;
+
+	if (!value)
+		return -EINVAL;
+
+	ihp = intc_find_irq(d->sense, d->nr_sense, irq);
+	if (ihp) {
+		addr = INTC_REG(d, _INTC_ADDR_E(ihp->handle), 0);
+		intc_reg_fns[_INTC_FN(ihp->handle)](addr, ihp->handle, value);
+	}
+	return 0;
+}
+
+static unsigned int __init intc_get_reg(struct intc_desc_int *d,
+				 unsigned long address)
+{
+	unsigned int k;
+
+	for (k = 0; k < d->nr_reg; k++) {
+		if (d->reg[k] == address)
+			return k;
+	}
+
+	BUG();
+	return 0;
+}
+
+static intc_enum __init intc_grp_id(struct intc_desc *desc,
+				    intc_enum enum_id)
+{
+	struct intc_group *g = desc->groups;
+	unsigned int i, j;
+
+	for (i = 0; g && enum_id && i < desc->nr_groups; i++) {
+		g = desc->groups + i;
+
+		for (j = 0; g->enum_ids[j]; j++) {
+			if (g->enum_ids[j] != enum_id)
+				continue;
+
+			return g->enum_id;
+		}
+	}
+
+	return 0;
+}
+
+static unsigned int __init intc_mask_data(struct intc_desc *desc,
+					  struct intc_desc_int *d,
+					  intc_enum enum_id, int do_grps)
+{
+	struct intc_mask_reg *mr = desc->mask_regs;
+	unsigned int i, j, fn, mode;
+	unsigned long reg_e, reg_d;
+
+	for (i = 0; mr && enum_id && i < desc->nr_mask_regs; i++) {
+		mr = desc->mask_regs + i;
+
+		for (j = 0; j < ARRAY_SIZE(mr->enum_ids); j++) {
+			if (mr->enum_ids[j] != enum_id)
+				continue;
+
+			if (mr->set_reg && mr->clr_reg) {
+				fn = REG_FN_WRITE_BASE;
+				mode = MODE_DUAL_REG;
+				reg_e = mr->clr_reg;
+				reg_d = mr->set_reg;
+			} else {
+				fn = REG_FN_MODIFY_BASE;
+				if (mr->set_reg) {
+					mode = MODE_ENABLE_REG;
+					reg_e = mr->set_reg;
+					reg_d = mr->set_reg;
+				} else {
+					mode = MODE_MASK_REG;
+					reg_e = mr->clr_reg;
+					reg_d = mr->clr_reg;
+				}
+			}
+
+			fn += (mr->reg_width >> 3) - 1;
+			return _INTC_MK(fn, mode,
+					intc_get_reg(d, reg_e),
+					intc_get_reg(d, reg_d),
+					1,
+					(mr->reg_width - 1) - j);
+		}
+	}
+
+	if (do_grps)
+		return intc_mask_data(desc, d, intc_grp_id(desc, enum_id), 0);
+
+	return 0;
+}
+
+static unsigned int __init intc_prio_data(struct intc_desc *desc,
+					  struct intc_desc_int *d,
+					  intc_enum enum_id, int do_grps)
+{
+	struct intc_prio_reg *pr = desc->prio_regs;
+	unsigned int i, j, fn, mode, bit;
+	unsigned long reg_e, reg_d;
+
+	for (i = 0; pr && enum_id && i < desc->nr_prio_regs; i++) {
+		pr = desc->prio_regs + i;
+
+		for (j = 0; j < ARRAY_SIZE(pr->enum_ids); j++) {
+			if (pr->enum_ids[j] != enum_id)
+				continue;
+
+			if (pr->set_reg && pr->clr_reg) {
+				fn = REG_FN_WRITE_BASE;
+				mode = MODE_PCLR_REG;
+				reg_e = pr->set_reg;
+				reg_d = pr->clr_reg;
+			} else {
+				fn = REG_FN_MODIFY_BASE;
+				mode = MODE_PRIO_REG;
+				if (!pr->set_reg)
+					BUG();
+				reg_e = pr->set_reg;
+				reg_d = pr->set_reg;
+			}
+
+			fn += (pr->reg_width >> 3) - 1;
+
+			BUG_ON((j + 1) * pr->field_width > pr->reg_width);
+
+			bit = pr->reg_width - ((j + 1) * pr->field_width);
+
+			return _INTC_MK(fn, mode,
+					intc_get_reg(d, reg_e),
+					intc_get_reg(d, reg_d),
+					pr->field_width, bit);
+		}
+	}
+
+	if (do_grps)
+		return intc_prio_data(desc, d, intc_grp_id(desc, enum_id), 0);
+
+	return 0;
+}
+
+#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
+static unsigned int __init intc_ack_data(struct intc_desc *desc,
+					  struct intc_desc_int *d,
+					  intc_enum enum_id)
+{
+	struct intc_mask_reg *mr = desc->ack_regs;
+	unsigned int i, j, fn, mode;
+	unsigned long reg_e, reg_d;
+
+	for (i = 0; mr && enum_id && i < desc->nr_ack_regs; i++) {
+		mr = desc->ack_regs + i;
+
+		for (j = 0; j < ARRAY_SIZE(mr->enum_ids); j++) {
+			if (mr->enum_ids[j] != enum_id)
+				continue;
+
+			fn = REG_FN_MODIFY_BASE;
+			mode = MODE_ENABLE_REG;
+			reg_e = mr->set_reg;
+			reg_d = mr->set_reg;
+
+			fn += (mr->reg_width >> 3) - 1;
+			return _INTC_MK(fn, mode,
+					intc_get_reg(d, reg_e),
+					intc_get_reg(d, reg_d),
+					1,
+					(mr->reg_width - 1) - j);
+		}
+	}
+
+	return 0;
+}
+#endif
+
+static unsigned int __init intc_sense_data(struct intc_desc *desc,
+					   struct intc_desc_int *d,
+					   intc_enum enum_id)
+{
+	struct intc_sense_reg *sr = desc->sense_regs;
+	unsigned int i, j, fn, bit;
+
+	for (i = 0; sr && enum_id && i < desc->nr_sense_regs; i++) {
+		sr = desc->sense_regs + i;
+
+		for (j = 0; j < ARRAY_SIZE(sr->enum_ids); j++) {
+			if (sr->enum_ids[j] != enum_id)
+				continue;
+
+			fn = REG_FN_MODIFY_BASE;
+			fn += (sr->reg_width >> 3) - 1;
+
+			BUG_ON((j + 1) * sr->field_width > sr->reg_width);
+
+			bit = sr->reg_width - ((j + 1) * sr->field_width);
+
+			return _INTC_MK(fn, 0, intc_get_reg(d, sr->reg),
+					0, sr->field_width, bit);
+		}
+	}
+
+	return 0;
+}
+
+static void __init intc_register_irq(struct intc_desc *desc,
+				     struct intc_desc_int *d,
+				     intc_enum enum_id,
+				     unsigned int irq)
+{
+	struct intc_handle_int *hp;
+	unsigned int data[2], primary;
+
+	/* Prefer single interrupt source bitmap over other combinations:
+	 * 1. bitmap, single interrupt source
+	 * 2. priority, single interrupt source
+	 * 3. bitmap, multiple interrupt sources (groups)
+	 * 4. priority, multiple interrupt sources (groups)
+	 */
+
+	data[0] = intc_mask_data(desc, d, enum_id, 0);
+	data[1] = intc_prio_data(desc, d, enum_id, 0);
+
+	primary = 0;
+	if (!data[0] && data[1])
+		primary = 1;
+
+	data[0] = data[0] ? data[0] : intc_mask_data(desc, d, enum_id, 1);
+	data[1] = data[1] ? data[1] : intc_prio_data(desc, d, enum_id, 1);
+
+	if (!data[primary])
+		primary ^= 1;
+
+	BUG_ON(!data[primary]); /* must have primary masking method */
+
+	disable_irq_nosync(irq);
+	set_irq_chip_and_handler_name(irq, &d->chip,
+				      handle_level_irq, "level");
+	set_irq_chip_data(irq, (void *)data[primary]);
+
+	/* set priority level
+	 * - this needs to be at least 2 for 5-bit priorities on 7780
+	 */
+	intc_prio_level[irq] = 2;
+
+	/* enable secondary masking method if present */
+	if (data[!primary])
+		_intc_enable(irq, data[!primary]);
+
+	/* add irq to d->prio list if priority is available */
+	if (data[1]) {
+		hp = d->prio + d->nr_prio;
+		hp->irq = irq;
+		hp->handle = data[1];
+
+		if (primary) {
+			/*
+			 * only secondary priority should access registers, so
+			 * set _INTC_FN(h) = REG_FN_ERR for intc_set_priority()
+			 */
+
+			hp->handle &= ~_INTC_MK(0x0f, 0, 0, 0, 0, 0);
+			hp->handle |= _INTC_MK(REG_FN_ERR, 0, 0, 0, 0, 0);
+		}
+		d->nr_prio++;
+	}
+
+	/* add irq to d->sense list if sense is available */
+	data[0] = intc_sense_data(desc, d, enum_id);
+	if (data[0]) {
+		(d->sense + d->nr_sense)->irq = irq;
+		(d->sense + d->nr_sense)->handle = data[0];
+		d->nr_sense++;
+	}
+
+	/* irq should be disabled by default */
+	d->chip.mask(irq);
+
+#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
+	if (desc->ack_regs)
+		ack_handle[irq] = intc_ack_data(desc, d, enum_id);
+#endif
+}
+
+static unsigned int __init save_reg(struct intc_desc_int *d,
+				    unsigned int cnt,
+				    unsigned long value,
+				    unsigned int smp)
+{
+	if (value) {
+		d->reg[cnt] = value;
+#ifdef CONFIG_SMP
+		d->smp[cnt] = smp;
+#endif
+		return 1;
+	}
+
+	return 0;
+}
+
+
+void __init register_intc_controller(struct intc_desc *desc)
+{
+	unsigned int i, k, smp;
+	struct intc_desc_int *d;
+
+	d = alloc_bootmem(sizeof(*d));
+
+	d->nr_reg = desc->mask_regs ? desc->nr_mask_regs * 2 : 0;
+	d->nr_reg += desc->prio_regs ? desc->nr_prio_regs * 2 : 0;
+	d->nr_reg += desc->sense_regs ? desc->nr_sense_regs : 0;
+
+#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
+	d->nr_reg += desc->ack_regs ? desc->nr_ack_regs : 0;
+#endif
+	d->reg = alloc_bootmem(d->nr_reg * sizeof(*d->reg));
+#ifdef CONFIG_SMP
+	d->smp = alloc_bootmem(d->nr_reg * sizeof(*d->smp));
+#endif
+	k = 0;
+
+	if (desc->mask_regs) {
+		for (i = 0; i < desc->nr_mask_regs; i++) {
+			smp = IS_SMP(desc->mask_regs[i]);
+			k += save_reg(d, k, desc->mask_regs[i].set_reg, smp);
+			k += save_reg(d, k, desc->mask_regs[i].clr_reg, smp);
+		}
+	}
+
+	if (desc->prio_regs) {
+		d->prio = alloc_bootmem(desc->nr_vectors * sizeof(*d->prio));
+
+		for (i = 0; i < desc->nr_prio_regs; i++) {
+			smp = IS_SMP(desc->prio_regs[i]);
+			k += save_reg(d, k, desc->prio_regs[i].set_reg, smp);
+			k += save_reg(d, k, desc->prio_regs[i].clr_reg, smp);
+		}
+	}
+
+	if (desc->sense_regs) {
+		d->sense = alloc_bootmem(desc->nr_vectors * sizeof(*d->sense));
+
+		for (i = 0; i < desc->nr_sense_regs; i++) {
+			k += save_reg(d, k, desc->sense_regs[i].reg, 0);
+		}
+	}
+
+	d->chip.name = desc->name;
+	d->chip.mask = intc_disable;
+	d->chip.unmask = intc_enable;
+	d->chip.mask_ack = intc_disable;
+	d->chip.set_type = intc_set_sense;
+
+#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
+	if (desc->ack_regs) {
+		for (i = 0; i < desc->nr_ack_regs; i++)
+			k += save_reg(d, k, desc->ack_regs[i].set_reg, 0);
+
+		d->chip.mask_ack = intc_mask_ack;
+	}
+#endif
+
+	BUG_ON(k > 256); /* _INTC_ADDR_E() and _INTC_ADDR_D() are 8 bits */
+
+	for (i = 0; i < desc->nr_vectors; i++) {
+		struct intc_vect *vect = desc->vectors + i;
+
+		intc_register_irq(desc, d, vect->enum_id, evt2irq(vect->vect));
+	}
+}
diff --git a/include/linux/sh_intc.h b/include/linux/sh_intc.h
new file mode 100644
index 000000000000..68e212ff9dde
--- /dev/null
+++ b/include/linux/sh_intc.h
@@ -0,0 +1,91 @@
+#ifndef __SH_INTC_H
+#define __SH_INTC_H
+
+typedef unsigned char intc_enum;
+
+struct intc_vect {
+	intc_enum enum_id;
+	unsigned short vect;
+};
+
+#define INTC_VECT(enum_id, vect) { enum_id, vect }
+#define INTC_IRQ(enum_id, irq) INTC_VECT(enum_id, irq2evt(irq))
+
+struct intc_group {
+	intc_enum enum_id;
+	intc_enum enum_ids[32];
+};
+
+#define INTC_GROUP(enum_id, ids...) { enum_id, { ids } }
+
+struct intc_mask_reg {
+	unsigned long set_reg, clr_reg, reg_width;
+	intc_enum enum_ids[32];
+#ifdef CONFIG_SMP
+	unsigned long smp;
+#endif
+};
+
+struct intc_prio_reg {
+	unsigned long set_reg, clr_reg, reg_width, field_width;
+	intc_enum enum_ids[16];
+#ifdef CONFIG_SMP
+	unsigned long smp;
+#endif
+};
+
+struct intc_sense_reg {
+	unsigned long reg, reg_width, field_width;
+	intc_enum enum_ids[16];
+};
+
+#ifdef CONFIG_SMP
+#define INTC_SMP(stride, nr) .smp = (stride) | ((nr) << 8)
+#else
+#define INTC_SMP(stride, nr)
+#endif
+
+struct intc_desc {
+	struct intc_vect *vectors;
+	unsigned int nr_vectors;
+	struct intc_group *groups;
+	unsigned int nr_groups;
+	struct intc_mask_reg *mask_regs;
+	unsigned int nr_mask_regs;
+	struct intc_prio_reg *prio_regs;
+	unsigned int nr_prio_regs;
+	struct intc_sense_reg *sense_regs;
+	unsigned int nr_sense_regs;
+	char *name;
+#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
+	struct intc_mask_reg *ack_regs;
+	unsigned int nr_ack_regs;
+#endif
+};
+
+#define _INTC_ARRAY(a) a, sizeof(a)/sizeof(*a)
+#define DECLARE_INTC_DESC(symbol, chipname, vectors, groups,		\
+	mask_regs, prio_regs, sense_regs)				\
+struct intc_desc symbol __initdata = {					\
+	_INTC_ARRAY(vectors), _INTC_ARRAY(groups),			\
+	_INTC_ARRAY(mask_regs), _INTC_ARRAY(prio_regs),			\
+	_INTC_ARRAY(sense_regs),					\
+	chipname,							\
+}
+
+#if defined(CONFIG_CPU_SH3) || defined(CONFIG_CPU_SH4A)
+#define DECLARE_INTC_DESC_ACK(symbol, chipname, vectors, groups,	\
+	mask_regs, prio_regs, sense_regs, ack_regs)			\
+struct intc_desc symbol __initdata = {					\
+	_INTC_ARRAY(vectors), _INTC_ARRAY(groups),			\
+	_INTC_ARRAY(mask_regs), _INTC_ARRAY(prio_regs),			\
+	_INTC_ARRAY(sense_regs),					\
+	chipname,							\
+	_INTC_ARRAY(ack_regs),						\
+}
+#endif
+
+void __init register_intc_controller(struct intc_desc *desc);
+int intc_set_priority(unsigned int irq, unsigned int prio);
+
+#endif /* __SH_INTC_H */
-- 
cgit v1.2.3


From 225c9a8d1da274bf23efec43ec28b1c9e45e12f8 Mon Sep 17 00:00:00 2001
From: Paul Mundt <lethal@linux-sh.org>
Date: Wed, 1 Oct 2008 16:24:32 +0900
Subject: video: sh_mobile_lcdcfb: Support HAVE_CLK=n configurations.

This provides a workaround for users of sh_mobile_lcdcfb that don't
define HAVE_CLK and have otherwise sane clock initialization.

At the same time, move the sh_mobile_lcdc.h header to include/video/.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
---
 arch/sh/boards/board-ap325rxa.c      |  2 +-
 arch/sh/boards/mach-migor/lcd_qvga.c |  2 +-
 arch/sh/boards/mach-migor/setup.c    |  2 +-
 arch/sh/include/asm/migor.h          |  2 +-
 arch/sh/include/asm/sh_mobile_lcdc.h | 72 ------------------------------------
 drivers/video/sh_mobile_lcdcfb.c     |  8 +++-
 include/video/sh_mobile_lcdc.h       | 72 ++++++++++++++++++++++++++++++++++++
 7 files changed, 83 insertions(+), 77 deletions(-)
 delete mode 100644 arch/sh/include/asm/sh_mobile_lcdc.h
 create mode 100644 include/video/sh_mobile_lcdc.h

(limited to 'include')

diff --git a/arch/sh/boards/board-ap325rxa.c b/arch/sh/boards/board-ap325rxa.c
index 00e632fc0688..7ae8dcddfeb4 100644
--- a/arch/sh/boards/board-ap325rxa.c
+++ b/arch/sh/boards/board-ap325rxa.c
@@ -20,7 +20,7 @@
 #include <linux/smc911x.h>
 #include <media/soc_camera_platform.h>
 #include <media/sh_mobile_ceu.h>
-#include <asm/sh_mobile_lcdc.h>
+#include <video/sh_mobile_lcdc.h>
 #include <asm/io.h>
 #include <asm/clock.h>
 
diff --git a/arch/sh/boards/mach-migor/lcd_qvga.c b/arch/sh/boards/mach-migor/lcd_qvga.c
index 6e9609596448..735326c04497 100644
--- a/arch/sh/boards/mach-migor/lcd_qvga.c
+++ b/arch/sh/boards/mach-migor/lcd_qvga.c
@@ -17,7 +17,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <asm/sh_mobile_lcdc.h>
+#include <video/sh_mobile_lcdc.h>
 #include <asm/migor.h>
 
 /* LCD Module is a PH240320T according to board schematics. This module
diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index 714dce91cc9b..f27475d2fa0c 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -19,11 +19,11 @@
 #include <linux/clk.h>
 #include <media/soc_camera_platform.h>
 #include <media/sh_mobile_ceu.h>
+#include <video/sh_mobile_lcdc.h>
 #include <asm/clock.h>
 #include <asm/machvec.h>
 #include <asm/io.h>
 #include <asm/sh_keysc.h>
-#include <asm/sh_mobile_lcdc.h>
 #include <asm/migor.h>
 
 /* Address     IRQ  Size  Bus  Description
diff --git a/arch/sh/include/asm/migor.h b/arch/sh/include/asm/migor.h
index c12b632c540b..70596d38fd67 100644
--- a/arch/sh/include/asm/migor.h
+++ b/arch/sh/include/asm/migor.h
@@ -54,7 +54,7 @@
 
 #define BSC_CS6ABCR 0xfec1001c
 
-#include <asm/sh_mobile_lcdc.h>
+#include <video/sh_mobile_lcdc.h>
 
 int migor_lcd_qvga_setup(void *board_data, void *sys_ops_handle,
 			 struct sh_mobile_lcdc_sys_bus_ops *sys_ops);
diff --git a/arch/sh/include/asm/sh_mobile_lcdc.h b/arch/sh/include/asm/sh_mobile_lcdc.h
deleted file mode 100644
index 130102f663f5..000000000000
--- a/arch/sh/include/asm/sh_mobile_lcdc.h
+++ /dev/null
@@ -1,72 +0,0 @@
-#ifndef __ASM_SH_MOBILE_LCDC_H__
-#define __ASM_SH_MOBILE_LCDC_H__
-
-#include <linux/fb.h>
-
-enum { RGB8,   /* 24bpp, 8:8:8 */
-       RGB9,   /* 18bpp, 9:9 */
-       RGB12A, /* 24bpp, 12:12 */
-       RGB12B, /* 12bpp */
-       RGB16,  /* 16bpp */
-       RGB18,  /* 18bpp */
-       RGB24,  /* 24bpp */
-       SYS8A,  /* 24bpp, 8:8:8 */
-       SYS8B,  /* 18bpp, 8:8:2 */
-       SYS8C,  /* 18bpp, 2:8:8 */
-       SYS8D,  /* 16bpp, 8:8 */
-       SYS9,   /* 18bpp, 9:9 */
-       SYS12,  /* 24bpp, 12:12 */
-       SYS16A, /* 16bpp */
-       SYS16B, /* 18bpp, 16:2 */
-       SYS16C, /* 18bpp, 2:16 */
-       SYS18,  /* 18bpp */
-       SYS24 };/* 24bpp */
-
-enum { LCDC_CHAN_DISABLED = 0,
-       LCDC_CHAN_MAINLCD,
-       LCDC_CHAN_SUBLCD };
-
-enum { LCDC_CLK_BUS, LCDC_CLK_PERIPHERAL, LCDC_CLK_EXTERNAL };
-
-struct sh_mobile_lcdc_sys_bus_cfg {
-	unsigned long ldmt2r;
-	unsigned long ldmt3r;
-};
-
-struct sh_mobile_lcdc_sys_bus_ops {
-	void (*write_index)(void *handle, unsigned long data);
-	void (*write_data)(void *handle, unsigned long data);
-	unsigned long (*read_data)(void *handle);
-};
-
-struct sh_mobile_lcdc_board_cfg {
-	void *board_data;
-	int (*setup_sys)(void *board_data, void *sys_ops_handle,
-			 struct sh_mobile_lcdc_sys_bus_ops *sys_ops);
-	void (*display_on)(void *board_data);
-	void (*display_off)(void *board_data);
-};
-
-struct sh_mobile_lcdc_lcd_size_cfg { /* width and height of panel in mm */
-	unsigned long width;
-	unsigned long height;
-};
-
-struct sh_mobile_lcdc_chan_cfg {
-	int chan;
-	int bpp;
-	int interface_type; /* selects RGBn or SYSn I/F, see above */
-	int clock_divider;
-	struct fb_videomode lcd_cfg;
-	struct sh_mobile_lcdc_lcd_size_cfg lcd_size_cfg;
-	struct sh_mobile_lcdc_board_cfg board_cfg;
-	struct sh_mobile_lcdc_sys_bus_cfg sys_bus_cfg; /* only for SYSn I/F */
-};
-
-struct sh_mobile_lcdc_info {
-	unsigned long lddckr;
-	int clock_source;
-	struct sh_mobile_lcdc_chan_cfg ch[2];
-};
-
-#endif /* __ASM_SH_MOBILE_LCDC_H__ */
diff --git a/drivers/video/sh_mobile_lcdcfb.c b/drivers/video/sh_mobile_lcdcfb.c
index 4c32c06579a0..b7468bacce80 100644
--- a/drivers/video/sh_mobile_lcdcfb.c
+++ b/drivers/video/sh_mobile_lcdcfb.c
@@ -16,7 +16,7 @@
 #include <linux/clk.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
-#include <asm/sh_mobile_lcdc.h>
+#include <video/sh_mobile_lcdc.h>
 
 #define PALETTE_NR 16
 
@@ -34,7 +34,9 @@ struct sh_mobile_lcdc_chan {
 
 struct sh_mobile_lcdc_priv {
 	void __iomem *base;
+#ifdef CONFIG_HAVE_CLK
 	struct clk *clk;
+#endif
 	unsigned long lddckr;
 	struct sh_mobile_lcdc_chan ch[2];
 };
@@ -422,6 +424,7 @@ static int sh_mobile_lcdc_setup_clocks(struct device *dev, int clock_source,
 
 	priv->lddckr = icksel << 16;
 
+#ifdef CONFIG_HAVE_CLK
 	if (str) {
 		priv->clk = clk_get(dev, str);
 		if (IS_ERR(priv->clk)) {
@@ -431,6 +434,7 @@ static int sh_mobile_lcdc_setup_clocks(struct device *dev, int clock_source,
 
 		clk_enable(priv->clk);
 	}
+#endif
 
 	return 0;
 }
@@ -688,10 +692,12 @@ static int sh_mobile_lcdc_remove(struct platform_device *pdev)
 		fb_dealloc_cmap(&info->cmap);
 	}
 
+#ifdef CONFIG_HAVE_CLK
 	if (priv->clk) {
 		clk_disable(priv->clk);
 		clk_put(priv->clk);
 	}
+#endif
 
 	if (priv->base)
 		iounmap(priv->base);
diff --git a/include/video/sh_mobile_lcdc.h b/include/video/sh_mobile_lcdc.h
new file mode 100644
index 000000000000..130102f663f5
--- /dev/null
+++ b/include/video/sh_mobile_lcdc.h
@@ -0,0 +1,72 @@
+#ifndef __ASM_SH_MOBILE_LCDC_H__
+#define __ASM_SH_MOBILE_LCDC_H__
+
+#include <linux/fb.h>
+
+enum { RGB8,   /* 24bpp, 8:8:8 */
+       RGB9,   /* 18bpp, 9:9 */
+       RGB12A, /* 24bpp, 12:12 */
+       RGB12B, /* 12bpp */
+       RGB16,  /* 16bpp */
+       RGB18,  /* 18bpp */
+       RGB24,  /* 24bpp */
+       SYS8A,  /* 24bpp, 8:8:8 */
+       SYS8B,  /* 18bpp, 8:8:2 */
+       SYS8C,  /* 18bpp, 2:8:8 */
+       SYS8D,  /* 16bpp, 8:8 */
+       SYS9,   /* 18bpp, 9:9 */
+       SYS12,  /* 24bpp, 12:12 */
+       SYS16A, /* 16bpp */
+       SYS16B, /* 18bpp, 16:2 */
+       SYS16C, /* 18bpp, 2:16 */
+       SYS18,  /* 18bpp */
+       SYS24 };/* 24bpp */
+
+enum { LCDC_CHAN_DISABLED = 0,
+       LCDC_CHAN_MAINLCD,
+       LCDC_CHAN_SUBLCD };
+
+enum { LCDC_CLK_BUS, LCDC_CLK_PERIPHERAL, LCDC_CLK_EXTERNAL };
+
+struct sh_mobile_lcdc_sys_bus_cfg {
+	unsigned long ldmt2r;
+	unsigned long ldmt3r;
+};
+
+struct sh_mobile_lcdc_sys_bus_ops {
+	void (*write_index)(void *handle, unsigned long data);
+	void (*write_data)(void *handle, unsigned long data);
+	unsigned long (*read_data)(void *handle);
+};
+
+struct sh_mobile_lcdc_board_cfg {
+	void *board_data;
+	int (*setup_sys)(void *board_data, void *sys_ops_handle,
+			 struct sh_mobile_lcdc_sys_bus_ops *sys_ops);
+	void (*display_on)(void *board_data);
+	void (*display_off)(void *board_data);
+};
+
+struct sh_mobile_lcdc_lcd_size_cfg { /* width and height of panel in mm */
+	unsigned long width;
+	unsigned long height;
+};
+
+struct sh_mobile_lcdc_chan_cfg {
+	int chan;
+	int bpp;
+	int interface_type; /* selects RGBn or SYSn I/F, see above */
+	int clock_divider;
+	struct fb_videomode lcd_cfg;
+	struct sh_mobile_lcdc_lcd_size_cfg lcd_size_cfg;
+	struct sh_mobile_lcdc_board_cfg board_cfg;
+	struct sh_mobile_lcdc_sys_bus_cfg sys_bus_cfg; /* only for SYSn I/F */
+};
+
+struct sh_mobile_lcdc_info {
+	unsigned long lddckr;
+	int clock_source;
+	struct sh_mobile_lcdc_chan_cfg ch[2];
+};
+
+#endif /* __ASM_SH_MOBILE_LCDC_H__ */
-- 
cgit v1.2.3


From 2075eb8d95612cadde91ef5be82691d97a2ea6c5 Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Tue, 7 Oct 2008 10:57:54 -0700
Subject: rangetimer: fix x86 build failure for the !HRTIMERS case

the timer peek function was on the wrong side of an ifdef,
breaking for the !HRTIMERs case. Just provide an empty inline
for that case since it doesn't make sense in that scenario.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
---
 include/linux/hrtimer.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index d93b1e1dc169..508ce20b8f9c 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -283,6 +283,8 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
 	return timer->base->cpu_base->hres_active;
 }
 
+extern void hrtimer_peek_ahead_timers(void);
+
 /*
  * The resolution of the clocks. The resolution value is returned in
  * the clock_getres() system call to give application programmers an
@@ -305,6 +307,7 @@ static inline int hrtimer_is_hres_active(struct hrtimer *timer)
  * is expired in the next softirq when the clock was advanced.
  */
 static inline void clock_was_set(void) { }
+static inline void hrtimer_peek_ahead_timers(void) { }
 
 static inline void hres_timers_resume(void) { }
 
@@ -328,7 +331,6 @@ extern ktime_t ktime_get_real(void);
 
 
 DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
-extern void hrtimer_peek_ahead_timers(void);
 
 
 /* Exported timer functions: */
-- 
cgit v1.2.3


From 40b10fc58a62a9698f4fa1916e61b0953139928a Mon Sep 17 00:00:00 2001
From: Kyle McMartin <kyle@mcmartin.ca>
Date: Mon, 28 Jul 2008 16:22:34 -0400
Subject: parisc: ropes.h - fix <asm-parisc/*> -> <asm/*>

---
 include/asm-parisc/ropes.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-parisc/ropes.h b/include/asm-parisc/ropes.h
index 007a880615eb..09f51d5ab57c 100644
--- a/include/asm-parisc/ropes.h
+++ b/include/asm-parisc/ropes.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_PARISC_ROPES_H_
 #define _ASM_PARISC_ROPES_H_
 
-#include <asm-parisc/parisc-device.h>
+#include <asm/parisc-device.h>
 
 #ifdef CONFIG_64BIT
 /* "low end" PA8800 machines use ZX1 chipset: PAT PDC and only run 64-bit */
-- 
cgit v1.2.3


From 6c86cb8237bf08443806089130dc108051569a93 Mon Sep 17 00:00:00 2001
From: Kyle McMartin <kyle@mcmartin.ca>
Date: Mon, 28 Jul 2008 22:52:18 -0400
Subject: parisc: move pdc_result to real2.S

---
 arch/parisc/kernel/asm-offsets.c |  3 +++
 arch/parisc/kernel/firmware.c    |  4 ++--
 arch/parisc/kernel/real2.S       | 12 ++++++++++++
 include/asm-parisc/pdc.h         |  3 +++
 4 files changed, 20 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/parisc/kernel/asm-offsets.c b/arch/parisc/kernel/asm-offsets.c
index 3efc0b73e4ff..699cf8ef2118 100644
--- a/arch/parisc/kernel/asm-offsets.c
+++ b/arch/parisc/kernel/asm-offsets.c
@@ -290,5 +290,8 @@ int main(void)
 	DEFINE(EXCDATA_IP, offsetof(struct exception_data, fault_ip));
 	DEFINE(EXCDATA_SPACE, offsetof(struct exception_data, fault_space));
 	DEFINE(EXCDATA_ADDR, offsetof(struct exception_data, fault_addr));
+	BLANK();
+	DEFINE(ASM_PDC_RESULT_SIZE, NUM_PDC_RESULT * sizeof(unsigned long));
+	BLANK();
 	return 0;
 }
diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index 7177a6cd1b7f..99a9e505edf9 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -71,8 +71,8 @@
 #include <asm/processor.h>	/* for boot_cpu_data */
 
 static DEFINE_SPINLOCK(pdc_lock);
-static unsigned long pdc_result[32] __attribute__ ((aligned (8)));
-static unsigned long pdc_result2[32] __attribute__ ((aligned (8)));
+extern unsigned long pdc_result[NUM_PDC_RESULT];
+extern unsigned long pdc_result2[NUM_PDC_RESULT];
 
 #ifdef CONFIG_64BIT
 #define WIDE_FIRMWARE 0x1
diff --git a/arch/parisc/kernel/real2.S b/arch/parisc/kernel/real2.S
index 7a92695d95a6..5f3d3a1f9037 100644
--- a/arch/parisc/kernel/real2.S
+++ b/arch/parisc/kernel/real2.S
@@ -8,12 +8,24 @@
  *
  */
 
+#include <asm/pdc.h>
 #include <asm/psw.h>
 #include <asm/assembly.h>
+#include <asm/asm-offsets.h>
 
 #include <linux/linkage.h>
 
+
 	.section	.bss
+
+	.export pdc_result
+	.export pdc_result2
+	.align 8
+pdc_result:
+	.block	ASM_PDC_RESULT_SIZE
+pdc_result2:
+	.block	ASM_PDC_RESULT_SIZE
+
 	.export real_stack
 	.export real32_stack
 	.export real64_stack
diff --git a/include/asm-parisc/pdc.h b/include/asm-parisc/pdc.h
index 9eaa794c3e4a..46b75f9cce51 100644
--- a/include/asm-parisc/pdc.h
+++ b/include/asm-parisc/pdc.h
@@ -332,6 +332,9 @@
 #define BOOT_CONSOLE_SPA_OFFSET  0x3c4
 #define BOOT_CONSOLE_PATH_OFFSET 0x3a8
 
+/* size of the pdc_result buffer for firmware.c */
+#define NUM_PDC_RESULT	32
+
 #if !defined(__ASSEMBLY__)
 #ifdef __KERNEL__
 
-- 
cgit v1.2.3


From deae26bf6a10e47983606f5df080b91e97650ead Mon Sep 17 00:00:00 2001
From: Kyle McMartin <kyle@mcmartin.ca>
Date: Mon, 28 Jul 2008 23:02:13 -0400
Subject: parisc: move include/asm-parisc to arch/parisc/include/asm

---
 arch/parisc/include/asm/Kbuild               |   3 +
 arch/parisc/include/asm/a.out.h              |  20 +
 arch/parisc/include/asm/agp.h                |  24 +
 arch/parisc/include/asm/asmregs.h            | 183 +++++
 arch/parisc/include/asm/assembly.h           | 519 ++++++++++++++
 arch/parisc/include/asm/atomic.h             | 348 ++++++++++
 arch/parisc/include/asm/auxvec.h             |   4 +
 arch/parisc/include/asm/bitops.h             | 239 +++++++
 arch/parisc/include/asm/bug.h                |  92 +++
 arch/parisc/include/asm/bugs.h               |  19 +
 arch/parisc/include/asm/byteorder.h          |  82 +++
 arch/parisc/include/asm/cache.h              |  60 ++
 arch/parisc/include/asm/cacheflush.h         | 121 ++++
 arch/parisc/include/asm/checksum.h           | 210 ++++++
 arch/parisc/include/asm/compat.h             | 165 +++++
 arch/parisc/include/asm/compat_rt_sigframe.h |  50 ++
 arch/parisc/include/asm/compat_signal.h      |   2 +
 arch/parisc/include/asm/compat_ucontext.h    |  17 +
 arch/parisc/include/asm/cputime.h            |   6 +
 arch/parisc/include/asm/current.h            |  15 +
 arch/parisc/include/asm/delay.h              |  43 ++
 arch/parisc/include/asm/device.h             |   7 +
 arch/parisc/include/asm/div64.h              |   1 +
 arch/parisc/include/asm/dma-mapping.h        | 253 +++++++
 arch/parisc/include/asm/dma.h                | 186 +++++
 arch/parisc/include/asm/eisa_bus.h           |  23 +
 arch/parisc/include/asm/eisa_eeprom.h        | 153 +++++
 arch/parisc/include/asm/elf.h                | 342 +++++++++
 arch/parisc/include/asm/emergency-restart.h  |   6 +
 arch/parisc/include/asm/errno.h              | 124 ++++
 arch/parisc/include/asm/fb.h                 |  19 +
 arch/parisc/include/asm/fcntl.h              |  39 ++
 arch/parisc/include/asm/fixmap.h             |  30 +
 arch/parisc/include/asm/floppy.h             | 271 ++++++++
 arch/parisc/include/asm/futex.h              |  77 +++
 arch/parisc/include/asm/grfioctl.h           | 113 +++
 arch/parisc/include/asm/hardirq.h            |  29 +
 arch/parisc/include/asm/hardware.h           | 127 ++++
 arch/parisc/include/asm/hw_irq.h             |   8 +
 arch/parisc/include/asm/ide.h                |  61 ++
 arch/parisc/include/asm/io.h                 | 293 ++++++++
 arch/parisc/include/asm/ioctl.h              |  44 ++
 arch/parisc/include/asm/ioctls.h             |  90 +++
 arch/parisc/include/asm/ipcbuf.h             |  27 +
 arch/parisc/include/asm/irq.h                |  57 ++
 arch/parisc/include/asm/irq_regs.h           |   1 +
 arch/parisc/include/asm/kdebug.h             |   1 +
 arch/parisc/include/asm/kmap_types.h         |  30 +
 arch/parisc/include/asm/led.h                |  42 ++
 arch/parisc/include/asm/linkage.h            |  31 +
 arch/parisc/include/asm/local.h              |   1 +
 arch/parisc/include/asm/machdep.h            |  16 +
 arch/parisc/include/asm/mc146818rtc.h        |   9 +
 arch/parisc/include/asm/mckinley.h           |   9 +
 arch/parisc/include/asm/mman.h               |  61 ++
 arch/parisc/include/asm/mmu.h                |   7 +
 arch/parisc/include/asm/mmu_context.h        |  75 ++
 arch/parisc/include/asm/mmzone.h             |  73 ++
 arch/parisc/include/asm/module.h             |  32 +
 arch/parisc/include/asm/msgbuf.h             |  37 +
 arch/parisc/include/asm/mutex.h              |   9 +
 arch/parisc/include/asm/page.h               | 173 +++++
 arch/parisc/include/asm/param.h              |  22 +
 arch/parisc/include/asm/parisc-device.h      |  64 ++
 arch/parisc/include/asm/parport.h            |  18 +
 arch/parisc/include/asm/pci.h                | 294 ++++++++
 arch/parisc/include/asm/pdc.h                | 760 ++++++++++++++++++++
 arch/parisc/include/asm/pdc_chassis.h        | 381 ++++++++++
 arch/parisc/include/asm/pdcpat.h             | 308 +++++++++
 arch/parisc/include/asm/percpu.h             |   7 +
 arch/parisc/include/asm/perf.h               |  74 ++
 arch/parisc/include/asm/pgalloc.h            | 149 ++++
 arch/parisc/include/asm/pgtable.h            | 508 ++++++++++++++
 arch/parisc/include/asm/poll.h               |   1 +
 arch/parisc/include/asm/posix_types.h        | 129 ++++
 arch/parisc/include/asm/prefetch.h           |  39 ++
 arch/parisc/include/asm/processor.h          | 357 ++++++++++
 arch/parisc/include/asm/psw.h                |  62 ++
 arch/parisc/include/asm/ptrace.h             |  58 ++
 arch/parisc/include/asm/real.h               |   5 +
 arch/parisc/include/asm/resource.h           |   7 +
 arch/parisc/include/asm/ropes.h              | 322 +++++++++
 arch/parisc/include/asm/rt_sigframe.h        |  23 +
 arch/parisc/include/asm/rtc.h                | 131 ++++
 arch/parisc/include/asm/runway.h             |  12 +
 arch/parisc/include/asm/scatterlist.h        |  27 +
 arch/parisc/include/asm/sections.h           |  12 +
 arch/parisc/include/asm/segment.h            |   6 +
 arch/parisc/include/asm/sembuf.h             |  29 +
 arch/parisc/include/asm/serial.h             |  10 +
 arch/parisc/include/asm/setup.h              |   6 +
 arch/parisc/include/asm/shmbuf.h             |  58 ++
 arch/parisc/include/asm/shmparam.h           |   8 +
 arch/parisc/include/asm/sigcontext.h         |  20 +
 arch/parisc/include/asm/siginfo.h            |  14 +
 arch/parisc/include/asm/signal.h             | 153 +++++
 arch/parisc/include/asm/smp.h                |  68 ++
 arch/parisc/include/asm/socket.h             |  62 ++
 arch/parisc/include/asm/sockios.h            |  13 +
 arch/parisc/include/asm/spinlock.h           | 194 ++++++
 arch/parisc/include/asm/spinlock_types.h     |  21 +
 arch/parisc/include/asm/stat.h               | 100 +++
 arch/parisc/include/asm/statfs.h             |  58 ++
 arch/parisc/include/asm/string.h             |  10 +
 arch/parisc/include/asm/superio.h            |  85 +++
 arch/parisc/include/asm/system.h             | 182 +++++
 arch/parisc/include/asm/termbits.h           | 200 ++++++
 arch/parisc/include/asm/termios.h            |  90 +++
 arch/parisc/include/asm/thread_info.h        |  74 ++
 arch/parisc/include/asm/timex.h              |  20 +
 arch/parisc/include/asm/tlb.h                |  27 +
 arch/parisc/include/asm/tlbflush.h           |  80 +++
 arch/parisc/include/asm/topology.h           |   6 +
 arch/parisc/include/asm/traps.h              |  16 +
 arch/parisc/include/asm/types.h              |  36 +
 arch/parisc/include/asm/uaccess.h            | 244 +++++++
 arch/parisc/include/asm/ucontext.h           |  12 +
 arch/parisc/include/asm/unaligned.h          |  16 +
 arch/parisc/include/asm/unistd.h             | 991 +++++++++++++++++++++++++++
 arch/parisc/include/asm/unwind.h             |  77 +++
 arch/parisc/include/asm/user.h               |   5 +
 arch/parisc/include/asm/vga.h                |   6 +
 arch/parisc/include/asm/xor.h                |   1 +
 include/asm-parisc/Kbuild                    |   3 -
 include/asm-parisc/a.out.h                   |  20 -
 include/asm-parisc/agp.h                     |  24 -
 include/asm-parisc/asmregs.h                 | 183 -----
 include/asm-parisc/assembly.h                | 519 --------------
 include/asm-parisc/atomic.h                  | 348 ----------
 include/asm-parisc/auxvec.h                  |   4 -
 include/asm-parisc/bitops.h                  | 239 -------
 include/asm-parisc/bug.h                     |  92 ---
 include/asm-parisc/bugs.h                    |  19 -
 include/asm-parisc/byteorder.h               |  82 ---
 include/asm-parisc/cache.h                   |  60 --
 include/asm-parisc/cacheflush.h              | 121 ----
 include/asm-parisc/checksum.h                | 210 ------
 include/asm-parisc/compat.h                  | 165 -----
 include/asm-parisc/compat_rt_sigframe.h      |  50 --
 include/asm-parisc/compat_signal.h           |   2 -
 include/asm-parisc/compat_ucontext.h         |  17 -
 include/asm-parisc/cputime.h                 |   6 -
 include/asm-parisc/current.h                 |  15 -
 include/asm-parisc/delay.h                   |  43 --
 include/asm-parisc/device.h                  |   7 -
 include/asm-parisc/div64.h                   |   1 -
 include/asm-parisc/dma-mapping.h             | 253 -------
 include/asm-parisc/dma.h                     | 186 -----
 include/asm-parisc/eisa_bus.h                |  23 -
 include/asm-parisc/eisa_eeprom.h             | 153 -----
 include/asm-parisc/elf.h                     | 342 ---------
 include/asm-parisc/emergency-restart.h       |   6 -
 include/asm-parisc/errno.h                   | 124 ----
 include/asm-parisc/fb.h                      |  19 -
 include/asm-parisc/fcntl.h                   |  39 --
 include/asm-parisc/fixmap.h                  |  30 -
 include/asm-parisc/floppy.h                  | 271 --------
 include/asm-parisc/futex.h                   |  77 ---
 include/asm-parisc/grfioctl.h                | 113 ---
 include/asm-parisc/hardirq.h                 |  29 -
 include/asm-parisc/hardware.h                | 127 ----
 include/asm-parisc/hw_irq.h                  |   8 -
 include/asm-parisc/ide.h                     |  61 --
 include/asm-parisc/io.h                      | 293 --------
 include/asm-parisc/ioctl.h                   |  44 --
 include/asm-parisc/ioctls.h                  |  90 ---
 include/asm-parisc/ipcbuf.h                  |  27 -
 include/asm-parisc/irq.h                     |  57 --
 include/asm-parisc/irq_regs.h                |   1 -
 include/asm-parisc/kdebug.h                  |   1 -
 include/asm-parisc/kmap_types.h              |  30 -
 include/asm-parisc/led.h                     |  42 --
 include/asm-parisc/linkage.h                 |  31 -
 include/asm-parisc/local.h                   |   1 -
 include/asm-parisc/machdep.h                 |  16 -
 include/asm-parisc/mc146818rtc.h             |   9 -
 include/asm-parisc/mckinley.h                |   9 -
 include/asm-parisc/mman.h                    |  61 --
 include/asm-parisc/mmu.h                     |   7 -
 include/asm-parisc/mmu_context.h             |  75 --
 include/asm-parisc/mmzone.h                  |  73 --
 include/asm-parisc/module.h                  |  32 -
 include/asm-parisc/msgbuf.h                  |  37 -
 include/asm-parisc/mutex.h                   |   9 -
 include/asm-parisc/page.h                    | 173 -----
 include/asm-parisc/param.h                   |  22 -
 include/asm-parisc/parisc-device.h           |  64 --
 include/asm-parisc/parport.h                 |  18 -
 include/asm-parisc/pci.h                     | 294 --------
 include/asm-parisc/pdc.h                     | 760 --------------------
 include/asm-parisc/pdc_chassis.h             | 381 ----------
 include/asm-parisc/pdcpat.h                  | 308 ---------
 include/asm-parisc/percpu.h                  |   7 -
 include/asm-parisc/perf.h                    |  74 --
 include/asm-parisc/pgalloc.h                 | 149 ----
 include/asm-parisc/pgtable.h                 | 508 --------------
 include/asm-parisc/poll.h                    |   1 -
 include/asm-parisc/posix_types.h             | 129 ----
 include/asm-parisc/prefetch.h                |  39 --
 include/asm-parisc/processor.h               | 357 ----------
 include/asm-parisc/psw.h                     |  62 --
 include/asm-parisc/ptrace.h                  |  58 --
 include/asm-parisc/real.h                    |   5 -
 include/asm-parisc/resource.h                |   7 -
 include/asm-parisc/ropes.h                   | 322 ---------
 include/asm-parisc/rt_sigframe.h             |  23 -
 include/asm-parisc/rtc.h                     | 131 ----
 include/asm-parisc/runway.h                  |  12 -
 include/asm-parisc/scatterlist.h             |  27 -
 include/asm-parisc/sections.h                |  12 -
 include/asm-parisc/segment.h                 |   6 -
 include/asm-parisc/sembuf.h                  |  29 -
 include/asm-parisc/serial.h                  |  10 -
 include/asm-parisc/setup.h                   |   6 -
 include/asm-parisc/shmbuf.h                  |  58 --
 include/asm-parisc/shmparam.h                |   8 -
 include/asm-parisc/sigcontext.h              |  20 -
 include/asm-parisc/siginfo.h                 |  14 -
 include/asm-parisc/signal.h                  | 153 -----
 include/asm-parisc/smp.h                     |  68 --
 include/asm-parisc/socket.h                  |  62 --
 include/asm-parisc/sockios.h                 |  13 -
 include/asm-parisc/spinlock.h                | 194 ------
 include/asm-parisc/spinlock_types.h          |  21 -
 include/asm-parisc/stat.h                    | 100 ---
 include/asm-parisc/statfs.h                  |  58 --
 include/asm-parisc/string.h                  |  10 -
 include/asm-parisc/superio.h                 |  85 ---
 include/asm-parisc/system.h                  | 182 -----
 include/asm-parisc/termbits.h                | 200 ------
 include/asm-parisc/termios.h                 |  90 ---
 include/asm-parisc/thread_info.h             |  74 --
 include/asm-parisc/timex.h                   |  20 -
 include/asm-parisc/tlb.h                     |  27 -
 include/asm-parisc/tlbflush.h                |  80 ---
 include/asm-parisc/topology.h                |   6 -
 include/asm-parisc/traps.h                   |  16 -
 include/asm-parisc/types.h                   |  36 -
 include/asm-parisc/uaccess.h                 | 244 -------
 include/asm-parisc/ucontext.h                |  12 -
 include/asm-parisc/unaligned.h               |  16 -
 include/asm-parisc/unistd.h                  | 991 ---------------------------
 include/asm-parisc/unwind.h                  |  77 ---
 include/asm-parisc/user.h                    |   5 -
 include/asm-parisc/vga.h                     |   6 -
 include/asm-parisc/xor.h                     |   1 -
 246 files changed, 11977 insertions(+), 11977 deletions(-)
 create mode 100644 arch/parisc/include/asm/Kbuild
 create mode 100644 arch/parisc/include/asm/a.out.h
 create mode 100644 arch/parisc/include/asm/agp.h
 create mode 100644 arch/parisc/include/asm/asmregs.h
 create mode 100644 arch/parisc/include/asm/assembly.h
 create mode 100644 arch/parisc/include/asm/atomic.h
 create mode 100644 arch/parisc/include/asm/auxvec.h
 create mode 100644 arch/parisc/include/asm/bitops.h
 create mode 100644 arch/parisc/include/asm/bug.h
 create mode 100644 arch/parisc/include/asm/bugs.h
 create mode 100644 arch/parisc/include/asm/byteorder.h
 create mode 100644 arch/parisc/include/asm/cache.h
 create mode 100644 arch/parisc/include/asm/cacheflush.h
 create mode 100644 arch/parisc/include/asm/checksum.h
 create mode 100644 arch/parisc/include/asm/compat.h
 create mode 100644 arch/parisc/include/asm/compat_rt_sigframe.h
 create mode 100644 arch/parisc/include/asm/compat_signal.h
 create mode 100644 arch/parisc/include/asm/compat_ucontext.h
 create mode 100644 arch/parisc/include/asm/cputime.h
 create mode 100644 arch/parisc/include/asm/current.h
 create mode 100644 arch/parisc/include/asm/delay.h
 create mode 100644 arch/parisc/include/asm/device.h
 create mode 100644 arch/parisc/include/asm/div64.h
 create mode 100644 arch/parisc/include/asm/dma-mapping.h
 create mode 100644 arch/parisc/include/asm/dma.h
 create mode 100644 arch/parisc/include/asm/eisa_bus.h
 create mode 100644 arch/parisc/include/asm/eisa_eeprom.h
 create mode 100644 arch/parisc/include/asm/elf.h
 create mode 100644 arch/parisc/include/asm/emergency-restart.h
 create mode 100644 arch/parisc/include/asm/errno.h
 create mode 100644 arch/parisc/include/asm/fb.h
 create mode 100644 arch/parisc/include/asm/fcntl.h
 create mode 100644 arch/parisc/include/asm/fixmap.h
 create mode 100644 arch/parisc/include/asm/floppy.h
 create mode 100644 arch/parisc/include/asm/futex.h
 create mode 100644 arch/parisc/include/asm/grfioctl.h
 create mode 100644 arch/parisc/include/asm/hardirq.h
 create mode 100644 arch/parisc/include/asm/hardware.h
 create mode 100644 arch/parisc/include/asm/hw_irq.h
 create mode 100644 arch/parisc/include/asm/ide.h
 create mode 100644 arch/parisc/include/asm/io.h
 create mode 100644 arch/parisc/include/asm/ioctl.h
 create mode 100644 arch/parisc/include/asm/ioctls.h
 create mode 100644 arch/parisc/include/asm/ipcbuf.h
 create mode 100644 arch/parisc/include/asm/irq.h
 create mode 100644 arch/parisc/include/asm/irq_regs.h
 create mode 100644 arch/parisc/include/asm/kdebug.h
 create mode 100644 arch/parisc/include/asm/kmap_types.h
 create mode 100644 arch/parisc/include/asm/led.h
 create mode 100644 arch/parisc/include/asm/linkage.h
 create mode 100644 arch/parisc/include/asm/local.h
 create mode 100644 arch/parisc/include/asm/machdep.h
 create mode 100644 arch/parisc/include/asm/mc146818rtc.h
 create mode 100644 arch/parisc/include/asm/mckinley.h
 create mode 100644 arch/parisc/include/asm/mman.h
 create mode 100644 arch/parisc/include/asm/mmu.h
 create mode 100644 arch/parisc/include/asm/mmu_context.h
 create mode 100644 arch/parisc/include/asm/mmzone.h
 create mode 100644 arch/parisc/include/asm/module.h
 create mode 100644 arch/parisc/include/asm/msgbuf.h
 create mode 100644 arch/parisc/include/asm/mutex.h
 create mode 100644 arch/parisc/include/asm/page.h
 create mode 100644 arch/parisc/include/asm/param.h
 create mode 100644 arch/parisc/include/asm/parisc-device.h
 create mode 100644 arch/parisc/include/asm/parport.h
 create mode 100644 arch/parisc/include/asm/pci.h
 create mode 100644 arch/parisc/include/asm/pdc.h
 create mode 100644 arch/parisc/include/asm/pdc_chassis.h
 create mode 100644 arch/parisc/include/asm/pdcpat.h
 create mode 100644 arch/parisc/include/asm/percpu.h
 create mode 100644 arch/parisc/include/asm/perf.h
 create mode 100644 arch/parisc/include/asm/pgalloc.h
 create mode 100644 arch/parisc/include/asm/pgtable.h
 create mode 100644 arch/parisc/include/asm/poll.h
 create mode 100644 arch/parisc/include/asm/posix_types.h
 create mode 100644 arch/parisc/include/asm/prefetch.h
 create mode 100644 arch/parisc/include/asm/processor.h
 create mode 100644 arch/parisc/include/asm/psw.h
 create mode 100644 arch/parisc/include/asm/ptrace.h
 create mode 100644 arch/parisc/include/asm/real.h
 create mode 100644 arch/parisc/include/asm/resource.h
 create mode 100644 arch/parisc/include/asm/ropes.h
 create mode 100644 arch/parisc/include/asm/rt_sigframe.h
 create mode 100644 arch/parisc/include/asm/rtc.h
 create mode 100644 arch/parisc/include/asm/runway.h
 create mode 100644 arch/parisc/include/asm/scatterlist.h
 create mode 100644 arch/parisc/include/asm/sections.h
 create mode 100644 arch/parisc/include/asm/segment.h
 create mode 100644 arch/parisc/include/asm/sembuf.h
 create mode 100644 arch/parisc/include/asm/serial.h
 create mode 100644 arch/parisc/include/asm/setup.h
 create mode 100644 arch/parisc/include/asm/shmbuf.h
 create mode 100644 arch/parisc/include/asm/shmparam.h
 create mode 100644 arch/parisc/include/asm/sigcontext.h
 create mode 100644 arch/parisc/include/asm/siginfo.h
 create mode 100644 arch/parisc/include/asm/signal.h
 create mode 100644 arch/parisc/include/asm/smp.h
 create mode 100644 arch/parisc/include/asm/socket.h
 create mode 100644 arch/parisc/include/asm/sockios.h
 create mode 100644 arch/parisc/include/asm/spinlock.h
 create mode 100644 arch/parisc/include/asm/spinlock_types.h
 create mode 100644 arch/parisc/include/asm/stat.h
 create mode 100644 arch/parisc/include/asm/statfs.h
 create mode 100644 arch/parisc/include/asm/string.h
 create mode 100644 arch/parisc/include/asm/superio.h
 create mode 100644 arch/parisc/include/asm/system.h
 create mode 100644 arch/parisc/include/asm/termbits.h
 create mode 100644 arch/parisc/include/asm/termios.h
 create mode 100644 arch/parisc/include/asm/thread_info.h
 create mode 100644 arch/parisc/include/asm/timex.h
 create mode 100644 arch/parisc/include/asm/tlb.h
 create mode 100644 arch/parisc/include/asm/tlbflush.h
 create mode 100644 arch/parisc/include/asm/topology.h
 create mode 100644 arch/parisc/include/asm/traps.h
 create mode 100644 arch/parisc/include/asm/types.h
 create mode 100644 arch/parisc/include/asm/uaccess.h
 create mode 100644 arch/parisc/include/asm/ucontext.h
 create mode 100644 arch/parisc/include/asm/unaligned.h
 create mode 100644 arch/parisc/include/asm/unistd.h
 create mode 100644 arch/parisc/include/asm/unwind.h
 create mode 100644 arch/parisc/include/asm/user.h
 create mode 100644 arch/parisc/include/asm/vga.h
 create mode 100644 arch/parisc/include/asm/xor.h
 delete mode 100644 include/asm-parisc/Kbuild
 delete mode 100644 include/asm-parisc/a.out.h
 delete mode 100644 include/asm-parisc/agp.h
 delete mode 100644 include/asm-parisc/asmregs.h
 delete mode 100644 include/asm-parisc/assembly.h
 delete mode 100644 include/asm-parisc/atomic.h
 delete mode 100644 include/asm-parisc/auxvec.h
 delete mode 100644 include/asm-parisc/bitops.h
 delete mode 100644 include/asm-parisc/bug.h
 delete mode 100644 include/asm-parisc/bugs.h
 delete mode 100644 include/asm-parisc/byteorder.h
 delete mode 100644 include/asm-parisc/cache.h
 delete mode 100644 include/asm-parisc/cacheflush.h
 delete mode 100644 include/asm-parisc/checksum.h
 delete mode 100644 include/asm-parisc/compat.h
 delete mode 100644 include/asm-parisc/compat_rt_sigframe.h
 delete mode 100644 include/asm-parisc/compat_signal.h
 delete mode 100644 include/asm-parisc/compat_ucontext.h
 delete mode 100644 include/asm-parisc/cputime.h
 delete mode 100644 include/asm-parisc/current.h
 delete mode 100644 include/asm-parisc/delay.h
 delete mode 100644 include/asm-parisc/device.h
 delete mode 100644 include/asm-parisc/div64.h
 delete mode 100644 include/asm-parisc/dma-mapping.h
 delete mode 100644 include/asm-parisc/dma.h
 delete mode 100644 include/asm-parisc/eisa_bus.h
 delete mode 100644 include/asm-parisc/eisa_eeprom.h
 delete mode 100644 include/asm-parisc/elf.h
 delete mode 100644 include/asm-parisc/emergency-restart.h
 delete mode 100644 include/asm-parisc/errno.h
 delete mode 100644 include/asm-parisc/fb.h
 delete mode 100644 include/asm-parisc/fcntl.h
 delete mode 100644 include/asm-parisc/fixmap.h
 delete mode 100644 include/asm-parisc/floppy.h
 delete mode 100644 include/asm-parisc/futex.h
 delete mode 100644 include/asm-parisc/grfioctl.h
 delete mode 100644 include/asm-parisc/hardirq.h
 delete mode 100644 include/asm-parisc/hardware.h
 delete mode 100644 include/asm-parisc/hw_irq.h
 delete mode 100644 include/asm-parisc/ide.h
 delete mode 100644 include/asm-parisc/io.h
 delete mode 100644 include/asm-parisc/ioctl.h
 delete mode 100644 include/asm-parisc/ioctls.h
 delete mode 100644 include/asm-parisc/ipcbuf.h
 delete mode 100644 include/asm-parisc/irq.h
 delete mode 100644 include/asm-parisc/irq_regs.h
 delete mode 100644 include/asm-parisc/kdebug.h
 delete mode 100644 include/asm-parisc/kmap_types.h
 delete mode 100644 include/asm-parisc/led.h
 delete mode 100644 include/asm-parisc/linkage.h
 delete mode 100644 include/asm-parisc/local.h
 delete mode 100644 include/asm-parisc/machdep.h
 delete mode 100644 include/asm-parisc/mc146818rtc.h
 delete mode 100644 include/asm-parisc/mckinley.h
 delete mode 100644 include/asm-parisc/mman.h
 delete mode 100644 include/asm-parisc/mmu.h
 delete mode 100644 include/asm-parisc/mmu_context.h
 delete mode 100644 include/asm-parisc/mmzone.h
 delete mode 100644 include/asm-parisc/module.h
 delete mode 100644 include/asm-parisc/msgbuf.h
 delete mode 100644 include/asm-parisc/mutex.h
 delete mode 100644 include/asm-parisc/page.h
 delete mode 100644 include/asm-parisc/param.h
 delete mode 100644 include/asm-parisc/parisc-device.h
 delete mode 100644 include/asm-parisc/parport.h
 delete mode 100644 include/asm-parisc/pci.h
 delete mode 100644 include/asm-parisc/pdc.h
 delete mode 100644 include/asm-parisc/pdc_chassis.h
 delete mode 100644 include/asm-parisc/pdcpat.h
 delete mode 100644 include/asm-parisc/percpu.h
 delete mode 100644 include/asm-parisc/perf.h
 delete mode 100644 include/asm-parisc/pgalloc.h
 delete mode 100644 include/asm-parisc/pgtable.h
 delete mode 100644 include/asm-parisc/poll.h
 delete mode 100644 include/asm-parisc/posix_types.h
 delete mode 100644 include/asm-parisc/prefetch.h
 delete mode 100644 include/asm-parisc/processor.h
 delete mode 100644 include/asm-parisc/psw.h
 delete mode 100644 include/asm-parisc/ptrace.h
 delete mode 100644 include/asm-parisc/real.h
 delete mode 100644 include/asm-parisc/resource.h
 delete mode 100644 include/asm-parisc/ropes.h
 delete mode 100644 include/asm-parisc/rt_sigframe.h
 delete mode 100644 include/asm-parisc/rtc.h
 delete mode 100644 include/asm-parisc/runway.h
 delete mode 100644 include/asm-parisc/scatterlist.h
 delete mode 100644 include/asm-parisc/sections.h
 delete mode 100644 include/asm-parisc/segment.h
 delete mode 100644 include/asm-parisc/sembuf.h
 delete mode 100644 include/asm-parisc/serial.h
 delete mode 100644 include/asm-parisc/setup.h
 delete mode 100644 include/asm-parisc/shmbuf.h
 delete mode 100644 include/asm-parisc/shmparam.h
 delete mode 100644 include/asm-parisc/sigcontext.h
 delete mode 100644 include/asm-parisc/siginfo.h
 delete mode 100644 include/asm-parisc/signal.h
 delete mode 100644 include/asm-parisc/smp.h
 delete mode 100644 include/asm-parisc/socket.h
 delete mode 100644 include/asm-parisc/sockios.h
 delete mode 100644 include/asm-parisc/spinlock.h
 delete mode 100644 include/asm-parisc/spinlock_types.h
 delete mode 100644 include/asm-parisc/stat.h
 delete mode 100644 include/asm-parisc/statfs.h
 delete mode 100644 include/asm-parisc/string.h
 delete mode 100644 include/asm-parisc/superio.h
 delete mode 100644 include/asm-parisc/system.h
 delete mode 100644 include/asm-parisc/termbits.h
 delete mode 100644 include/asm-parisc/termios.h
 delete mode 100644 include/asm-parisc/thread_info.h
 delete mode 100644 include/asm-parisc/timex.h
 delete mode 100644 include/asm-parisc/tlb.h
 delete mode 100644 include/asm-parisc/tlbflush.h
 delete mode 100644 include/asm-parisc/topology.h
 delete mode 100644 include/asm-parisc/traps.h
 delete mode 100644 include/asm-parisc/types.h
 delete mode 100644 include/asm-parisc/uaccess.h
 delete mode 100644 include/asm-parisc/ucontext.h
 delete mode 100644 include/asm-parisc/unaligned.h
 delete mode 100644 include/asm-parisc/unistd.h
 delete mode 100644 include/asm-parisc/unwind.h
 delete mode 100644 include/asm-parisc/user.h
 delete mode 100644 include/asm-parisc/vga.h
 delete mode 100644 include/asm-parisc/xor.h

(limited to 'include')

diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
new file mode 100644
index 000000000000..f88b252e419c
--- /dev/null
+++ b/arch/parisc/include/asm/Kbuild
@@ -0,0 +1,3 @@
+include include/asm-generic/Kbuild.asm
+
+unifdef-y += pdc.h
diff --git a/arch/parisc/include/asm/a.out.h b/arch/parisc/include/asm/a.out.h
new file mode 100644
index 000000000000..eb04e34c5bb1
--- /dev/null
+++ b/arch/parisc/include/asm/a.out.h
@@ -0,0 +1,20 @@
+#ifndef __PARISC_A_OUT_H__
+#define __PARISC_A_OUT_H__
+
+struct exec
+{
+  unsigned int a_info;		/* Use macros N_MAGIC, etc for access */
+  unsigned a_text;		/* length of text, in bytes */
+  unsigned a_data;		/* length of data, in bytes */
+  unsigned a_bss;		/* length of uninitialized data area for file, in bytes */
+  unsigned a_syms;		/* length of symbol table data in file, in bytes */
+  unsigned a_entry;		/* start address */
+  unsigned a_trsize;		/* length of relocation info for text, in bytes */
+  unsigned a_drsize;		/* length of relocation info for data, in bytes */
+};
+
+#define N_TRSIZE(a)	((a).a_trsize)
+#define N_DRSIZE(a)	((a).a_drsize)
+#define N_SYMSIZE(a)	((a).a_syms)
+
+#endif /* __A_OUT_GNU_H__ */
diff --git a/arch/parisc/include/asm/agp.h b/arch/parisc/include/asm/agp.h
new file mode 100644
index 000000000000..9651660da639
--- /dev/null
+++ b/arch/parisc/include/asm/agp.h
@@ -0,0 +1,24 @@
+#ifndef _ASM_PARISC_AGP_H
+#define _ASM_PARISC_AGP_H
+
+/*
+ * PARISC specific AGP definitions.
+ * Copyright (c) 2006 Kyle McMartin <kyle@parisc-linux.org>
+ *
+ */
+
+#define map_page_into_agp(page)		/* nothing */
+#define unmap_page_from_agp(page)	/* nothing */
+#define flush_agp_cache()		mb()
+
+/* Convert a physical address to an address suitable for the GART. */
+#define phys_to_gart(x) (x)
+#define gart_to_phys(x) (x)
+
+/* GATT allocation. Returns/accepts GATT kernel virtual address. */
+#define alloc_gatt_pages(order)		\
+	((char *)__get_free_pages(GFP_KERNEL, (order)))
+#define free_gatt_pages(table, order)	\
+	free_pages((unsigned long)(table), (order))
+
+#endif /* _ASM_PARISC_AGP_H */
diff --git a/arch/parisc/include/asm/asmregs.h b/arch/parisc/include/asm/asmregs.h
new file mode 100644
index 000000000000..d93c646e1887
--- /dev/null
+++ b/arch/parisc/include/asm/asmregs.h
@@ -0,0 +1,183 @@
+/*
+ * Copyright (C) 1999 Hewlett-Packard (Frank Rowand)
+ *
+ *	This program is free software; you can redistribute it and/or modify
+ *	it under the terms of the GNU General Public License as published by
+ *	the Free Software Foundation; either version 2, or (at your option)
+ *	any later version.
+ *
+ *	This program is distributed in the hope that it will be useful,
+ *	but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *	GNU General Public License for more details.
+ *
+ *	You should have received a copy of the GNU General Public License
+ *	along with this program; if not, write to the Free Software
+ *	Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef _PARISC_ASMREGS_H
+#define _PARISC_ASMREGS_H
+
+;! General Registers
+
+rp:	.reg	%r2
+arg3:	.reg	%r23
+arg2:	.reg	%r24
+arg1:	.reg	%r25
+arg0:	.reg	%r26
+dp:	.reg	%r27
+ret0:	.reg	%r28
+ret1:	.reg	%r29
+sl:	.reg	%r29
+sp:	.reg	%r30
+
+#if 0
+/* PA20_REVISIT */
+arg7:	.reg	r19
+arg6:	.reg	r20
+arg5:	.reg	r21
+arg4:	.reg	r22
+gp:	.reg	r27
+ap:	.reg	r29
+#endif
+
+
+r0:	.reg	%r0
+r1:	.reg	%r1
+r2:	.reg	%r2
+r3:	.reg	%r3
+r4:	.reg	%r4
+r5:	.reg	%r5
+r6:	.reg	%r6
+r7:	.reg	%r7
+r8:	.reg	%r8
+r9:	.reg	%r9
+r10:	.reg	%r10
+r11:	.reg	%r11
+r12:	.reg	%r12
+r13:	.reg	%r13
+r14:	.reg	%r14
+r15:	.reg	%r15
+r16:	.reg	%r16
+r17:	.reg	%r17
+r18:	.reg	%r18
+r19:	.reg	%r19
+r20:	.reg	%r20
+r21:	.reg	%r21
+r22:	.reg	%r22
+r23:	.reg	%r23
+r24:	.reg	%r24
+r25:	.reg	%r25
+r26:	.reg	%r26
+r27:	.reg	%r27
+r28:	.reg	%r28
+r29:	.reg	%r29
+r30:	.reg	%r30
+r31:	.reg	%r31
+
+
+;! Space Registers
+
+sr0:	.reg	%sr0
+sr1:	.reg	%sr1
+sr2:	.reg	%sr2
+sr3:	.reg	%sr3
+sr4:	.reg	%sr4
+sr5:	.reg	%sr5
+sr6:	.reg	%sr6
+sr7:	.reg	%sr7
+
+
+;! Floating Point Registers
+
+fr0:	.reg	%fr0
+fr1:	.reg	%fr1
+fr2:	.reg	%fr2
+fr3:	.reg	%fr3
+fr4:	.reg	%fr4
+fr5:	.reg	%fr5
+fr6:	.reg	%fr6
+fr7:	.reg	%fr7
+fr8:	.reg	%fr8
+fr9:	.reg	%fr9
+fr10:	.reg	%fr10
+fr11:	.reg	%fr11
+fr12:	.reg	%fr12
+fr13:	.reg	%fr13
+fr14:	.reg	%fr14
+fr15:	.reg	%fr15
+fr16:	.reg	%fr16
+fr17:	.reg	%fr17
+fr18:	.reg	%fr18
+fr19:	.reg	%fr19
+fr20:	.reg	%fr20
+fr21:	.reg	%fr21
+fr22:	.reg	%fr22
+fr23:	.reg	%fr23
+fr24:	.reg	%fr24
+fr25:	.reg	%fr25
+fr26:	.reg	%fr26
+fr27:	.reg	%fr27
+fr28:	.reg	%fr28
+fr29:	.reg	%fr29
+fr30:	.reg	%fr30
+fr31:	.reg	%fr31
+
+
+;! Control Registers
+
+rctr:	.reg	%cr0
+pidr1:	.reg	%cr8
+pidr2:	.reg	%cr9
+ccr:	.reg	%cr10
+sar:	.reg	%cr11
+pidr3:	.reg	%cr12
+pidr4:	.reg	%cr13
+iva:	.reg	%cr14
+eiem:	.reg	%cr15
+itmr:	.reg	%cr16
+pcsq:	.reg	%cr17
+pcoq:	.reg	%cr18
+iir:	.reg	%cr19
+isr:	.reg	%cr20
+ior:	.reg	%cr21
+ipsw:	.reg	%cr22
+eirr:	.reg	%cr23
+tr0:	.reg	%cr24
+tr1:	.reg	%cr25
+tr2:	.reg	%cr26
+tr3:	.reg	%cr27
+tr4:	.reg	%cr28
+tr5:	.reg	%cr29
+tr6:	.reg	%cr30
+tr7:	.reg	%cr31
+
+
+cr0:	.reg	%cr0
+cr8:	.reg	%cr8
+cr9:	.reg	%cr9
+cr10:	.reg	%cr10
+cr11:	.reg	%cr11
+cr12:	.reg	%cr12
+cr13:	.reg	%cr13
+cr14:	.reg	%cr14
+cr15:	.reg	%cr15
+cr16:	.reg	%cr16
+cr17:	.reg	%cr17
+cr18:	.reg	%cr18
+cr19:	.reg	%cr19
+cr20:	.reg	%cr20
+cr21:	.reg	%cr21
+cr22:	.reg	%cr22
+cr23:	.reg	%cr23
+cr24:	.reg	%cr24
+cr25:	.reg	%cr25
+cr26:	.reg	%cr26
+cr27:	.reg	%cr27
+cr28:	.reg	%cr28
+cr29:	.reg	%cr29
+cr30:	.reg	%cr30
+cr31:	.reg	%cr31
+
+#endif
diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
new file mode 100644
index 000000000000..ffb208840ecc
--- /dev/null
+++ b/arch/parisc/include/asm/assembly.h
@@ -0,0 +1,519 @@
+/*
+ * Copyright (C) 1999 Hewlett-Packard (Frank Rowand)
+ * Copyright (C) 1999 Philipp Rumpf <prumpf@tux.org>
+ * Copyright (C) 1999 SuSE GmbH
+ *
+ *    This program is free software; you can redistribute it and/or modify
+ *    it under the terms of the GNU General Public License as published by
+ *    the Free Software Foundation; either version 2, or (at your option)
+ *    any later version.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU General Public License for more details.
+ *
+ *    You should have received a copy of the GNU General Public License
+ *    along with this program; if not, write to the Free Software
+ *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+#ifndef _PARISC_ASSEMBLY_H
+#define _PARISC_ASSEMBLY_H
+
+#define CALLEE_FLOAT_FRAME_SIZE	80
+
+#ifdef CONFIG_64BIT
+#define LDREG	ldd
+#define STREG	std
+#define LDREGX  ldd,s
+#define LDREGM	ldd,mb
+#define STREGM	std,ma
+#define SHRREG	shrd
+#define SHLREG	shld
+#define ANDCM   andcm,*
+#define	COND(x)	* ## x
+#define RP_OFFSET	16
+#define FRAME_SIZE	128
+#define CALLEE_REG_FRAME_SIZE	144
+#define ASM_ULONG_INSN	.dword
+#else	/* CONFIG_64BIT */
+#define LDREG	ldw
+#define STREG	stw
+#define LDREGX  ldwx,s
+#define LDREGM	ldwm
+#define STREGM	stwm
+#define SHRREG	shr
+#define SHLREG	shlw
+#define ANDCM   andcm
+#define COND(x)	x
+#define RP_OFFSET	20
+#define FRAME_SIZE	64
+#define CALLEE_REG_FRAME_SIZE	128
+#define ASM_ULONG_INSN	.word
+#endif
+
+#define CALLEE_SAVE_FRAME_SIZE (CALLEE_REG_FRAME_SIZE + CALLEE_FLOAT_FRAME_SIZE)
+
+#ifdef CONFIG_PA20
+#define LDCW		ldcw,co
+#define BL		b,l
+# ifdef CONFIG_64BIT
+#  define LEVEL		2.0w
+# else
+#  define LEVEL		2.0
+# endif
+#else
+#define LDCW		ldcw
+#define BL		bl
+#define LEVEL		1.1
+#endif
+
+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_64BIT
+/* the 64-bit pa gnu assembler unfortunately defaults to .level 1.1 or 2.0 so
+ * work around that for now... */
+	.level 2.0w
+#endif
+
+#include <asm/asm-offsets.h>
+#include <asm/page.h>
+
+#include <asm/asmregs.h>
+
+	sp	=	30
+	gp	=	27
+	ipsw	=	22
+
+	/*
+	 * We provide two versions of each macro to convert from physical
+	 * to virtual and vice versa. The "_r1" versions take one argument
+	 * register, but trashes r1 to do the conversion. The other
+	 * version takes two arguments: a src and destination register.
+	 * However, the source and destination registers can not be
+	 * the same register.
+	 */
+
+	.macro  tophys  grvirt, grphys
+	ldil    L%(__PAGE_OFFSET), \grphys
+	sub     \grvirt, \grphys, \grphys
+	.endm
+	
+	.macro  tovirt  grphys, grvirt
+	ldil    L%(__PAGE_OFFSET), \grvirt
+	add     \grphys, \grvirt, \grvirt
+	.endm
+
+	.macro  tophys_r1  gr
+	ldil    L%(__PAGE_OFFSET), %r1
+	sub     \gr, %r1, \gr
+	.endm
+	
+	.macro  tovirt_r1  gr
+	ldil    L%(__PAGE_OFFSET), %r1
+	add     \gr, %r1, \gr
+	.endm
+
+	.macro delay value
+	ldil	L%\value, 1
+	ldo	R%\value(1), 1
+	addib,UV,n -1,1,.
+	addib,NUV,n -1,1,.+8
+	nop
+	.endm
+
+	.macro	debug value
+	.endm
+
+
+	/* Shift Left - note the r and t can NOT be the same! */
+	.macro shl r, sa, t
+	dep,z	\r, 31-\sa, 32-\sa, \t
+	.endm
+
+	/* The PA 2.0 shift left */
+	.macro shlw r, sa, t
+	depw,z	\r, 31-\sa, 32-\sa, \t
+	.endm
+
+	/* And the PA 2.0W shift left */
+	.macro shld r, sa, t
+	depd,z	\r, 63-\sa, 64-\sa, \t
+	.endm
+
+	/* Shift Right - note the r and t can NOT be the same! */
+	.macro shr r, sa, t
+	extru \r, 31-\sa, 32-\sa, \t
+	.endm
+
+	/* pa20w version of shift right */
+	.macro shrd r, sa, t
+	extrd,u \r, 63-\sa, 64-\sa, \t
+	.endm
+
+	/* load 32-bit 'value' into 'reg' compensating for the ldil
+	 * sign-extension when running in wide mode.
+	 * WARNING!! neither 'value' nor 'reg' can be expressions
+	 * containing '.'!!!! */
+	.macro	load32 value, reg
+	ldil	L%\value, \reg
+	ldo	R%\value(\reg), \reg
+	.endm
+
+	.macro loadgp
+#ifdef CONFIG_64BIT
+	ldil		L%__gp, %r27
+	ldo		R%__gp(%r27), %r27
+#else
+	ldil		L%$global$, %r27
+	ldo		R%$global$(%r27), %r27
+#endif
+	.endm
+
+#define SAVE_SP(r, where) mfsp r, %r1 ! STREG %r1, where
+#define REST_SP(r, where) LDREG where, %r1 ! mtsp %r1, r
+#define SAVE_CR(r, where) mfctl r, %r1 ! STREG %r1, where
+#define REST_CR(r, where) LDREG where, %r1 ! mtctl %r1, r
+
+	.macro	save_general	regs
+	STREG %r1, PT_GR1 (\regs)
+	STREG %r2, PT_GR2 (\regs)
+	STREG %r3, PT_GR3 (\regs)
+	STREG %r4, PT_GR4 (\regs)
+	STREG %r5, PT_GR5 (\regs)
+	STREG %r6, PT_GR6 (\regs)
+	STREG %r7, PT_GR7 (\regs)
+	STREG %r8, PT_GR8 (\regs)
+	STREG %r9, PT_GR9 (\regs)
+	STREG %r10, PT_GR10(\regs)
+	STREG %r11, PT_GR11(\regs)
+	STREG %r12, PT_GR12(\regs)
+	STREG %r13, PT_GR13(\regs)
+	STREG %r14, PT_GR14(\regs)
+	STREG %r15, PT_GR15(\regs)
+	STREG %r16, PT_GR16(\regs)
+	STREG %r17, PT_GR17(\regs)
+	STREG %r18, PT_GR18(\regs)
+	STREG %r19, PT_GR19(\regs)
+	STREG %r20, PT_GR20(\regs)
+	STREG %r21, PT_GR21(\regs)
+	STREG %r22, PT_GR22(\regs)
+	STREG %r23, PT_GR23(\regs)
+	STREG %r24, PT_GR24(\regs)
+	STREG %r25, PT_GR25(\regs)
+	/* r26 is saved in get_stack and used to preserve a value across virt_map */
+	STREG %r27, PT_GR27(\regs)
+	STREG %r28, PT_GR28(\regs)
+	/* r29 is saved in get_stack and used to point to saved registers */
+	/* r30 stack pointer saved in get_stack */
+	STREG %r31, PT_GR31(\regs)
+	.endm
+
+	.macro	rest_general	regs
+	/* r1 used as a temp in rest_stack and is restored there */
+	LDREG PT_GR2 (\regs), %r2
+	LDREG PT_GR3 (\regs), %r3
+	LDREG PT_GR4 (\regs), %r4
+	LDREG PT_GR5 (\regs), %r5
+	LDREG PT_GR6 (\regs), %r6
+	LDREG PT_GR7 (\regs), %r7
+	LDREG PT_GR8 (\regs), %r8
+	LDREG PT_GR9 (\regs), %r9
+	LDREG PT_GR10(\regs), %r10
+	LDREG PT_GR11(\regs), %r11
+	LDREG PT_GR12(\regs), %r12
+	LDREG PT_GR13(\regs), %r13
+	LDREG PT_GR14(\regs), %r14
+	LDREG PT_GR15(\regs), %r15
+	LDREG PT_GR16(\regs), %r16
+	LDREG PT_GR17(\regs), %r17
+	LDREG PT_GR18(\regs), %r18
+	LDREG PT_GR19(\regs), %r19
+	LDREG PT_GR20(\regs), %r20
+	LDREG PT_GR21(\regs), %r21
+	LDREG PT_GR22(\regs), %r22
+	LDREG PT_GR23(\regs), %r23
+	LDREG PT_GR24(\regs), %r24
+	LDREG PT_GR25(\regs), %r25
+	LDREG PT_GR26(\regs), %r26
+	LDREG PT_GR27(\regs), %r27
+	LDREG PT_GR28(\regs), %r28
+	/* r29 points to register save area, and is restored in rest_stack */
+	/* r30 stack pointer restored in rest_stack */
+	LDREG PT_GR31(\regs), %r31
+	.endm
+
+	.macro	save_fp 	regs
+	fstd,ma  %fr0, 8(\regs)
+	fstd,ma	 %fr1, 8(\regs)
+	fstd,ma	 %fr2, 8(\regs)
+	fstd,ma	 %fr3, 8(\regs)
+	fstd,ma	 %fr4, 8(\regs)
+	fstd,ma	 %fr5, 8(\regs)
+	fstd,ma	 %fr6, 8(\regs)
+	fstd,ma	 %fr7, 8(\regs)
+	fstd,ma	 %fr8, 8(\regs)
+	fstd,ma	 %fr9, 8(\regs)
+	fstd,ma	%fr10, 8(\regs)
+	fstd,ma	%fr11, 8(\regs)
+	fstd,ma	%fr12, 8(\regs)
+	fstd,ma	%fr13, 8(\regs)
+	fstd,ma	%fr14, 8(\regs)
+	fstd,ma	%fr15, 8(\regs)
+	fstd,ma	%fr16, 8(\regs)
+	fstd,ma	%fr17, 8(\regs)
+	fstd,ma	%fr18, 8(\regs)
+	fstd,ma	%fr19, 8(\regs)
+	fstd,ma	%fr20, 8(\regs)
+	fstd,ma	%fr21, 8(\regs)
+	fstd,ma	%fr22, 8(\regs)
+	fstd,ma	%fr23, 8(\regs)
+	fstd,ma	%fr24, 8(\regs)
+	fstd,ma	%fr25, 8(\regs)
+	fstd,ma	%fr26, 8(\regs)
+	fstd,ma	%fr27, 8(\regs)
+	fstd,ma	%fr28, 8(\regs)
+	fstd,ma	%fr29, 8(\regs)
+	fstd,ma	%fr30, 8(\regs)
+	fstd	%fr31, 0(\regs)
+	.endm
+
+	.macro	rest_fp 	regs
+	fldd	0(\regs),	 %fr31
+	fldd,mb	-8(\regs),       %fr30
+	fldd,mb	-8(\regs),       %fr29
+	fldd,mb	-8(\regs),       %fr28
+	fldd,mb	-8(\regs),       %fr27
+	fldd,mb	-8(\regs),       %fr26
+	fldd,mb	-8(\regs),       %fr25
+	fldd,mb	-8(\regs),       %fr24
+	fldd,mb	-8(\regs),       %fr23
+	fldd,mb	-8(\regs),       %fr22
+	fldd,mb	-8(\regs),       %fr21
+	fldd,mb	-8(\regs),       %fr20
+	fldd,mb	-8(\regs),       %fr19
+	fldd,mb	-8(\regs),       %fr18
+	fldd,mb	-8(\regs),       %fr17
+	fldd,mb	-8(\regs),       %fr16
+	fldd,mb	-8(\regs),       %fr15
+	fldd,mb	-8(\regs),       %fr14
+	fldd,mb	-8(\regs),       %fr13
+	fldd,mb	-8(\regs),       %fr12
+	fldd,mb	-8(\regs),       %fr11
+	fldd,mb	-8(\regs),       %fr10
+	fldd,mb	-8(\regs),       %fr9
+	fldd,mb	-8(\regs),       %fr8
+	fldd,mb	-8(\regs),       %fr7
+	fldd,mb	-8(\regs),       %fr6
+	fldd,mb	-8(\regs),       %fr5
+	fldd,mb	-8(\regs),       %fr4
+	fldd,mb	-8(\regs),       %fr3
+	fldd,mb	-8(\regs),       %fr2
+	fldd,mb	-8(\regs),       %fr1
+	fldd,mb	-8(\regs),       %fr0
+	.endm
+
+	.macro	callee_save_float
+	fstd,ma	 %fr12,	8(%r30)
+	fstd,ma	 %fr13,	8(%r30)
+	fstd,ma	 %fr14,	8(%r30)
+	fstd,ma	 %fr15,	8(%r30)
+	fstd,ma	 %fr16,	8(%r30)
+	fstd,ma	 %fr17,	8(%r30)
+	fstd,ma	 %fr18,	8(%r30)
+	fstd,ma	 %fr19,	8(%r30)
+	fstd,ma	 %fr20,	8(%r30)
+	fstd,ma	 %fr21,	8(%r30)
+	.endm
+
+	.macro	callee_rest_float
+	fldd,mb	-8(%r30),   %fr21
+	fldd,mb	-8(%r30),   %fr20
+	fldd,mb	-8(%r30),   %fr19
+	fldd,mb	-8(%r30),   %fr18
+	fldd,mb	-8(%r30),   %fr17
+	fldd,mb	-8(%r30),   %fr16
+	fldd,mb	-8(%r30),   %fr15
+	fldd,mb	-8(%r30),   %fr14
+	fldd,mb	-8(%r30),   %fr13
+	fldd,mb	-8(%r30),   %fr12
+	.endm
+
+#ifdef CONFIG_64BIT
+	.macro	callee_save
+	std,ma	  %r3,	 CALLEE_REG_FRAME_SIZE(%r30)
+	mfctl	  %cr27, %r3
+	std	  %r4,	-136(%r30)
+	std	  %r5,	-128(%r30)
+	std	  %r6,	-120(%r30)
+	std	  %r7,	-112(%r30)
+	std	  %r8,	-104(%r30)
+	std	  %r9,	 -96(%r30)
+	std	 %r10,	 -88(%r30)
+	std	 %r11,	 -80(%r30)
+	std	 %r12,	 -72(%r30)
+	std	 %r13,	 -64(%r30)
+	std	 %r14,	 -56(%r30)
+	std	 %r15,	 -48(%r30)
+	std	 %r16,	 -40(%r30)
+	std	 %r17,	 -32(%r30)
+	std	 %r18,	 -24(%r30)
+	std	  %r3,	 -16(%r30)
+	.endm
+
+	.macro	callee_rest
+	ldd	 -16(%r30),    %r3
+	ldd	 -24(%r30),   %r18
+	ldd	 -32(%r30),   %r17
+	ldd	 -40(%r30),   %r16
+	ldd	 -48(%r30),   %r15
+	ldd	 -56(%r30),   %r14
+	ldd	 -64(%r30),   %r13
+	ldd	 -72(%r30),   %r12
+	ldd	 -80(%r30),   %r11
+	ldd	 -88(%r30),   %r10
+	ldd	 -96(%r30),    %r9
+	ldd	-104(%r30),    %r8
+	ldd	-112(%r30),    %r7
+	ldd	-120(%r30),    %r6
+	ldd	-128(%r30),    %r5
+	ldd	-136(%r30),    %r4
+	mtctl	%r3, %cr27
+	ldd,mb	-CALLEE_REG_FRAME_SIZE(%r30),    %r3
+	.endm
+
+#else /* ! CONFIG_64BIT */
+
+	.macro	callee_save
+	stw,ma	 %r3,	CALLEE_REG_FRAME_SIZE(%r30)
+	mfctl	 %cr27, %r3
+	stw	 %r4,	-124(%r30)
+	stw	 %r5,	-120(%r30)
+	stw	 %r6,	-116(%r30)
+	stw	 %r7,	-112(%r30)
+	stw	 %r8,	-108(%r30)
+	stw	 %r9,	-104(%r30)
+	stw	 %r10,	-100(%r30)
+	stw	 %r11,	 -96(%r30)
+	stw	 %r12,	 -92(%r30)
+	stw	 %r13,	 -88(%r30)
+	stw	 %r14,	 -84(%r30)
+	stw	 %r15,	 -80(%r30)
+	stw	 %r16,	 -76(%r30)
+	stw	 %r17,	 -72(%r30)
+	stw	 %r18,	 -68(%r30)
+	stw	  %r3,	 -64(%r30)
+	.endm
+
+	.macro	callee_rest
+	ldw	 -64(%r30),    %r3
+	ldw	 -68(%r30),   %r18
+	ldw	 -72(%r30),   %r17
+	ldw	 -76(%r30),   %r16
+	ldw	 -80(%r30),   %r15
+	ldw	 -84(%r30),   %r14
+	ldw	 -88(%r30),   %r13
+	ldw	 -92(%r30),   %r12
+	ldw	 -96(%r30),   %r11
+	ldw	-100(%r30),   %r10
+	ldw	-104(%r30),   %r9
+	ldw	-108(%r30),   %r8
+	ldw	-112(%r30),   %r7
+	ldw	-116(%r30),   %r6
+	ldw	-120(%r30),   %r5
+	ldw	-124(%r30),   %r4
+	mtctl	%r3, %cr27
+	ldw,mb	-CALLEE_REG_FRAME_SIZE(%r30),   %r3
+	.endm
+#endif /* ! CONFIG_64BIT */
+
+	.macro	save_specials	regs
+
+	SAVE_SP  (%sr0, PT_SR0 (\regs))
+	SAVE_SP  (%sr1, PT_SR1 (\regs))
+	SAVE_SP  (%sr2, PT_SR2 (\regs))
+	SAVE_SP  (%sr3, PT_SR3 (\regs))
+	SAVE_SP  (%sr4, PT_SR4 (\regs))
+	SAVE_SP  (%sr5, PT_SR5 (\regs))
+	SAVE_SP  (%sr6, PT_SR6 (\regs))
+	SAVE_SP  (%sr7, PT_SR7 (\regs))
+
+	SAVE_CR  (%cr17, PT_IASQ0(\regs))
+	mtctl	 %r0,	%cr17
+	SAVE_CR  (%cr17, PT_IASQ1(\regs))
+
+	SAVE_CR  (%cr18, PT_IAOQ0(\regs))
+	mtctl	 %r0,	%cr18
+	SAVE_CR  (%cr18, PT_IAOQ1(\regs))
+
+#ifdef CONFIG_64BIT
+	/* cr11 (sar) is a funny one.  5 bits on PA1.1 and 6 bit on PA2.0
+	 * For PA2.0 mtsar or mtctl always write 6 bits, but mfctl only
+	 * reads 5 bits.  Use mfctl,w to read all six bits.  Otherwise
+	 * we lose the 6th bit on a save/restore over interrupt.
+	 */
+	mfctl,w  %cr11, %r1
+	STREG    %r1, PT_SAR (\regs)
+#else
+	SAVE_CR  (%cr11, PT_SAR  (\regs))
+#endif
+	SAVE_CR  (%cr19, PT_IIR  (\regs))
+
+	/*
+	 * Code immediately following this macro (in intr_save) relies
+	 * on r8 containing ipsw.
+	 */
+	mfctl    %cr22, %r8
+	STREG    %r8,   PT_PSW(\regs)
+	.endm
+
+	.macro	rest_specials	regs
+
+	REST_SP  (%sr0, PT_SR0 (\regs))
+	REST_SP  (%sr1, PT_SR1 (\regs))
+	REST_SP  (%sr2, PT_SR2 (\regs))
+	REST_SP  (%sr3, PT_SR3 (\regs))
+	REST_SP  (%sr4, PT_SR4 (\regs))
+	REST_SP  (%sr5, PT_SR5 (\regs))
+	REST_SP  (%sr6, PT_SR6 (\regs))
+	REST_SP  (%sr7, PT_SR7 (\regs))
+
+	REST_CR	(%cr17, PT_IASQ0(\regs))
+	REST_CR	(%cr17, PT_IASQ1(\regs))
+
+	REST_CR	(%cr18, PT_IAOQ0(\regs))
+	REST_CR	(%cr18, PT_IAOQ1(\regs))
+
+	REST_CR (%cr11, PT_SAR	(\regs))
+
+	REST_CR	(%cr22, PT_PSW	(\regs))
+	.endm
+
+
+	/* First step to create a "relied upon translation"
+	 * See PA 2.0 Arch. page F-4 and F-5.
+	 *
+	 * The ssm was originally necessary due to a "PCxT bug".
+	 * But someone decided it needed to be added to the architecture
+	 * and this "feature" went into rev3 of PA-RISC 1.1 Arch Manual.
+	 * It's been carried forward into PA 2.0 Arch as well. :^(
+	 *
+	 * "ssm 0,%r0" is a NOP with side effects (prefetch barrier).
+	 * rsm/ssm prevents the ifetch unit from speculatively fetching
+	 * instructions past this line in the code stream.
+	 * PA 2.0 processor will single step all insn in the same QUAD (4 insn).
+	 */
+	.macro	pcxt_ssm_bug
+	rsm	PSW_SM_I,%r0
+	nop	/* 1 */
+	nop	/* 2 */
+	nop	/* 3 */
+	nop	/* 4 */
+	nop	/* 5 */
+	nop	/* 6 */
+	nop	/* 7 */
+	.endm
+
+#endif /* __ASSEMBLY__ */
+#endif
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
new file mode 100644
index 000000000000..57fcc4a5ebb4
--- /dev/null
+++ b/arch/parisc/include/asm/atomic.h
@@ -0,0 +1,348 @@
+/* Copyright (C) 2000 Philipp Rumpf <prumpf@tux.org>
+ * Copyright (C) 2006 Kyle McMartin <kyle@parisc-linux.org>
+ */
+
+#ifndef _ASM_PARISC_ATOMIC_H_
+#define _ASM_PARISC_ATOMIC_H_
+
+#include <linux/types.h>
+#include <asm/system.h>
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ *
+ * And probably incredibly slow on parisc.  OTOH, we don't
+ * have to write any serious assembly.   prumpf
+ */
+
+#ifdef CONFIG_SMP
+#include <asm/spinlock.h>
+#include <asm/cache.h>		/* we use L1_CACHE_BYTES */
+
+/* Use an array of spinlocks for our atomic_ts.
+ * Hash function to index into a different SPINLOCK.
+ * Since "a" is usually an address, use one spinlock per cacheline.
+ */
+#  define ATOMIC_HASH_SIZE 4
+#  define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
+
+extern raw_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
+
+/* Can't use raw_spin_lock_irq because of #include problems, so
+ * this is the substitute */
+#define _atomic_spin_lock_irqsave(l,f) do {	\
+	raw_spinlock_t *s = ATOMIC_HASH(l);		\
+	local_irq_save(f);			\
+	__raw_spin_lock(s);			\
+} while(0)
+
+#define _atomic_spin_unlock_irqrestore(l,f) do {	\
+	raw_spinlock_t *s = ATOMIC_HASH(l);			\
+	__raw_spin_unlock(s);				\
+	local_irq_restore(f);				\
+} while(0)
+
+
+#else
+#  define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0)
+#  define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
+#endif
+
+/* This should get optimized out since it's never called.
+** Or get a link error if xchg is used "wrong".
+*/
+extern void __xchg_called_with_bad_pointer(void);
+
+
+/* __xchg32/64 defined in arch/parisc/lib/bitops.c */
+extern unsigned long __xchg8(char, char *);
+extern unsigned long __xchg32(int, int *);
+#ifdef CONFIG_64BIT
+extern unsigned long __xchg64(unsigned long, unsigned long *);
+#endif
+
+/* optimizer better get rid of switch since size is a constant */
+static __inline__ unsigned long
+__xchg(unsigned long x, __volatile__ void * ptr, int size)
+{
+	switch(size) {
+#ifdef CONFIG_64BIT
+	case 8: return __xchg64(x,(unsigned long *) ptr);
+#endif
+	case 4: return __xchg32((int) x, (int *) ptr);
+	case 1: return __xchg8((char) x, (char *) ptr);
+	}
+	__xchg_called_with_bad_pointer();
+	return x;
+}
+
+
+/*
+** REVISIT - Abandoned use of LDCW in xchg() for now:
+** o need to test sizeof(*ptr) to avoid clearing adjacent bytes
+** o and while we are at it, could CONFIG_64BIT code use LDCD too?
+**
+**	if (__builtin_constant_p(x) && (x == NULL))
+**		if (((unsigned long)p & 0xf) == 0)
+**			return __ldcw(p);
+*/
+#define xchg(ptr,x) \
+	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
+
+
+#define __HAVE_ARCH_CMPXCHG	1
+
+/* bug catcher for when unsupported size is used - won't link */
+extern void __cmpxchg_called_with_bad_pointer(void);
+
+/* __cmpxchg_u32/u64 defined in arch/parisc/lib/bitops.c */
+extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old, unsigned int new_);
+extern unsigned long __cmpxchg_u64(volatile unsigned long *ptr, unsigned long old, unsigned long new_);
+
+/* don't worry...optimizer will get rid of most of this */
+static __inline__ unsigned long
+__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
+{
+	switch(size) {
+#ifdef CONFIG_64BIT
+	case 8: return __cmpxchg_u64((unsigned long *)ptr, old, new_);
+#endif
+	case 4: return __cmpxchg_u32((unsigned int *)ptr, (unsigned int) old, (unsigned int) new_);
+	}
+	__cmpxchg_called_with_bad_pointer();
+	return old;
+}
+
+#define cmpxchg(ptr,o,n)						 \
+  ({									 \
+     __typeof__(*(ptr)) _o_ = (o);					 \
+     __typeof__(*(ptr)) _n_ = (n);					 \
+     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
+				    (unsigned long)_n_, sizeof(*(ptr))); \
+  })
+
+#include <asm-generic/cmpxchg-local.h>
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+				      unsigned long old,
+				      unsigned long new_, int size)
+{
+	switch (size) {
+#ifdef CONFIG_64BIT
+	case 8:	return __cmpxchg_u64((unsigned long *)ptr, old, new_);
+#endif
+	case 4:	return __cmpxchg_u32(ptr, old, new_);
+	default:
+		return __cmpxchg_local_generic(ptr, old, new_, size);
+	}
+}
+
+/*
+ * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
+ * them available.
+ */
+#define cmpxchg_local(ptr, o, n)				  	\
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
+			(unsigned long)(n), sizeof(*(ptr))))
+#ifdef CONFIG_64BIT
+#define cmpxchg64_local(ptr, o, n)					\
+  ({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_local((ptr), (o), (n));					\
+  })
+#else
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+#endif
+
+/* Note that we need not lock read accesses - aligned word writes/reads
+ * are atomic, so a reader never sees unconsistent values.
+ *
+ * Cache-line alignment would conflict with, for example, linux/module.h
+ */
+
+typedef struct { volatile int counter; } atomic_t;
+
+/* It's possible to reduce all atomic operations to either
+ * __atomic_add_return, atomic_set and atomic_read (the latter
+ * is there only for consistency).
+ */
+
+static __inline__ int __atomic_add_return(int i, atomic_t *v)
+{
+	int ret;
+	unsigned long flags;
+	_atomic_spin_lock_irqsave(v, flags);
+
+	ret = (v->counter += i);
+
+	_atomic_spin_unlock_irqrestore(v, flags);
+	return ret;
+}
+
+static __inline__ void atomic_set(atomic_t *v, int i) 
+{
+	unsigned long flags;
+	_atomic_spin_lock_irqsave(v, flags);
+
+	v->counter = i;
+
+	_atomic_spin_unlock_irqrestore(v, flags);
+}
+
+static __inline__ int atomic_read(const atomic_t *v)
+{
+	return v->counter;
+}
+
+/* exported interface */
+#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+
+/**
+ * atomic_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int c, old;
+	c = atomic_read(v);
+	for (;;) {
+		if (unlikely(c == (u)))
+			break;
+		old = atomic_cmpxchg((v), c, c + (a));
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+	return c != (u);
+}
+
+#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+
+#define atomic_add(i,v)	((void)(__atomic_add_return( ((int)i),(v))))
+#define atomic_sub(i,v)	((void)(__atomic_add_return(-((int)i),(v))))
+#define atomic_inc(v)	((void)(__atomic_add_return(   1,(v))))
+#define atomic_dec(v)	((void)(__atomic_add_return(  -1,(v))))
+
+#define atomic_add_return(i,v)	(__atomic_add_return( ((int)i),(v)))
+#define atomic_sub_return(i,v)	(__atomic_add_return(-((int)i),(v)))
+#define atomic_inc_return(v)	(__atomic_add_return(   1,(v)))
+#define atomic_dec_return(v)	(__atomic_add_return(  -1,(v)))
+
+#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
+
+/*
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
+
+#define atomic_dec_and_test(v)	(atomic_dec_return(v) == 0)
+
+#define atomic_sub_and_test(i,v)	(atomic_sub_return((i),(v)) == 0)
+
+#define ATOMIC_INIT(i)	((atomic_t) { (i) })
+
+#define smp_mb__before_atomic_dec()	smp_mb()
+#define smp_mb__after_atomic_dec()	smp_mb()
+#define smp_mb__before_atomic_inc()	smp_mb()
+#define smp_mb__after_atomic_inc()	smp_mb()
+
+#ifdef CONFIG_64BIT
+
+typedef struct { volatile s64 counter; } atomic64_t;
+
+#define ATOMIC64_INIT(i) ((atomic64_t) { (i) })
+
+static __inline__ int
+__atomic64_add_return(s64 i, atomic64_t *v)
+{
+	int ret;
+	unsigned long flags;
+	_atomic_spin_lock_irqsave(v, flags);
+
+	ret = (v->counter += i);
+
+	_atomic_spin_unlock_irqrestore(v, flags);
+	return ret;
+}
+
+static __inline__ void
+atomic64_set(atomic64_t *v, s64 i)
+{
+	unsigned long flags;
+	_atomic_spin_lock_irqsave(v, flags);
+
+	v->counter = i;
+
+	_atomic_spin_unlock_irqrestore(v, flags);
+}
+
+static __inline__ s64
+atomic64_read(const atomic64_t *v)
+{
+	return v->counter;
+}
+
+#define atomic64_add(i,v)	((void)(__atomic64_add_return( ((s64)i),(v))))
+#define atomic64_sub(i,v)	((void)(__atomic64_add_return(-((s64)i),(v))))
+#define atomic64_inc(v)		((void)(__atomic64_add_return(   1,(v))))
+#define atomic64_dec(v)		((void)(__atomic64_add_return(  -1,(v))))
+
+#define atomic64_add_return(i,v)	(__atomic64_add_return( ((s64)i),(v)))
+#define atomic64_sub_return(i,v)	(__atomic64_add_return(-((s64)i),(v)))
+#define atomic64_inc_return(v)		(__atomic64_add_return(   1,(v)))
+#define atomic64_dec_return(v)		(__atomic64_add_return(  -1,(v)))
+
+#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
+
+#define atomic64_inc_and_test(v) 	(atomic64_inc_return(v) == 0)
+#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
+#define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i),(v)) == 0)
+
+/* exported interface */
+#define atomic64_cmpxchg(v, o, n) \
+	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
+#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
+
+/**
+ * atomic64_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+{
+	long c, old;
+	c = atomic64_read(v);
+	for (;;) {
+		if (unlikely(c == (u)))
+			break;
+		old = atomic64_cmpxchg((v), c, c + (a));
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+	return c != (u);
+}
+
+#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+
+#endif /* CONFIG_64BIT */
+
+#include <asm-generic/atomic.h>
+
+#endif /* _ASM_PARISC_ATOMIC_H_ */
diff --git a/arch/parisc/include/asm/auxvec.h b/arch/parisc/include/asm/auxvec.h
new file mode 100644
index 000000000000..9c3ac4b89dc9
--- /dev/null
+++ b/arch/parisc/include/asm/auxvec.h
@@ -0,0 +1,4 @@
+#ifndef __ASMPARISC_AUXVEC_H
+#define __ASMPARISC_AUXVEC_H
+
+#endif
diff --git a/arch/parisc/include/asm/bitops.h b/arch/parisc/include/asm/bitops.h
new file mode 100644
index 000000000000..7a6ea10bd231
--- /dev/null
+++ b/arch/parisc/include/asm/bitops.h
@@ -0,0 +1,239 @@
+#ifndef _PARISC_BITOPS_H
+#define _PARISC_BITOPS_H
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <linux/compiler.h>
+#include <asm/types.h>		/* for BITS_PER_LONG/SHIFT_PER_LONG */
+#include <asm/byteorder.h>
+#include <asm/atomic.h>
+
+/*
+ * HP-PARISC specific bit operations
+ * for a detailed description of the functions please refer
+ * to include/asm-i386/bitops.h or kerneldoc
+ */
+
+#define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1))
+
+
+#define smp_mb__before_clear_bit()      smp_mb()
+#define smp_mb__after_clear_bit()       smp_mb()
+
+/* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion
+ * on use of volatile and __*_bit() (set/clear/change):
+ *	*_bit() want use of volatile.
+ *	__*_bit() are "relaxed" and don't use spinlock or volatile.
+ */
+
+static __inline__ void set_bit(int nr, volatile unsigned long * addr)
+{
+	unsigned long mask = 1UL << CHOP_SHIFTCOUNT(nr);
+	unsigned long flags;
+
+	addr += (nr >> SHIFT_PER_LONG);
+	_atomic_spin_lock_irqsave(addr, flags);
+	*addr |= mask;
+	_atomic_spin_unlock_irqrestore(addr, flags);
+}
+
+static __inline__ void clear_bit(int nr, volatile unsigned long * addr)
+{
+	unsigned long mask = ~(1UL << CHOP_SHIFTCOUNT(nr));
+	unsigned long flags;
+
+	addr += (nr >> SHIFT_PER_LONG);
+	_atomic_spin_lock_irqsave(addr, flags);
+	*addr &= mask;
+	_atomic_spin_unlock_irqrestore(addr, flags);
+}
+
+static __inline__ void change_bit(int nr, volatile unsigned long * addr)
+{
+	unsigned long mask = 1UL << CHOP_SHIFTCOUNT(nr);
+	unsigned long flags;
+
+	addr += (nr >> SHIFT_PER_LONG);
+	_atomic_spin_lock_irqsave(addr, flags);
+	*addr ^= mask;
+	_atomic_spin_unlock_irqrestore(addr, flags);
+}
+
+static __inline__ int test_and_set_bit(int nr, volatile unsigned long * addr)
+{
+	unsigned long mask = 1UL << CHOP_SHIFTCOUNT(nr);
+	unsigned long old;
+	unsigned long flags;
+	int set;
+
+	addr += (nr >> SHIFT_PER_LONG);
+	_atomic_spin_lock_irqsave(addr, flags);
+	old = *addr;
+	set = (old & mask) ? 1 : 0;
+	if (!set)
+		*addr = old | mask;
+	_atomic_spin_unlock_irqrestore(addr, flags);
+
+	return set;
+}
+
+static __inline__ int test_and_clear_bit(int nr, volatile unsigned long * addr)
+{
+	unsigned long mask = 1UL << CHOP_SHIFTCOUNT(nr);
+	unsigned long old;
+	unsigned long flags;
+	int set;
+
+	addr += (nr >> SHIFT_PER_LONG);
+	_atomic_spin_lock_irqsave(addr, flags);
+	old = *addr;
+	set = (old & mask) ? 1 : 0;
+	if (set)
+		*addr = old & ~mask;
+	_atomic_spin_unlock_irqrestore(addr, flags);
+
+	return set;
+}
+
+static __inline__ int test_and_change_bit(int nr, volatile unsigned long * addr)
+{
+	unsigned long mask = 1UL << CHOP_SHIFTCOUNT(nr);
+	unsigned long oldbit;
+	unsigned long flags;
+
+	addr += (nr >> SHIFT_PER_LONG);
+	_atomic_spin_lock_irqsave(addr, flags);
+	oldbit = *addr;
+	*addr = oldbit ^ mask;
+	_atomic_spin_unlock_irqrestore(addr, flags);
+
+	return (oldbit & mask) ? 1 : 0;
+}
+
+#include <asm-generic/bitops/non-atomic.h>
+
+#ifdef __KERNEL__
+
+/**
+ * __ffs - find first bit in word. returns 0 to "BITS_PER_LONG-1".
+ * @word: The word to search
+ *
+ * __ffs() return is undefined if no bit is set.
+ *
+ * 32-bit fast __ffs by LaMont Jones "lamont At hp com".
+ * 64-bit enhancement by Grant Grundler "grundler At parisc-linux org".
+ * (with help from willy/jejb to get the semantics right)
+ *
+ * This algorithm avoids branches by making use of nullification.
+ * One side effect of "extr" instructions is it sets PSW[N] bit.
+ * How PSW[N] (nullify next insn) gets set is determined by the 
+ * "condition" field (eg "<>" or "TR" below) in the extr* insn.
+ * Only the 1st and one of either the 2cd or 3rd insn will get executed.
+ * Each set of 3 insn will get executed in 2 cycles on PA8x00 vs 16 or so
+ * cycles for each mispredicted branch.
+ */
+
+static __inline__ unsigned long __ffs(unsigned long x)
+{
+	unsigned long ret;
+
+	__asm__(
+#ifdef CONFIG_64BIT
+		" ldi       63,%1\n"
+		" extrd,u,*<>  %0,63,32,%%r0\n"
+		" extrd,u,*TR  %0,31,32,%0\n"	/* move top 32-bits down */
+		" addi    -32,%1,%1\n"
+#else
+		" ldi       31,%1\n"
+#endif
+		" extru,<>  %0,31,16,%%r0\n"
+		" extru,TR  %0,15,16,%0\n"	/* xxxx0000 -> 0000xxxx */
+		" addi    -16,%1,%1\n"
+		" extru,<>  %0,31,8,%%r0\n"
+		" extru,TR  %0,23,8,%0\n"	/* 0000xx00 -> 000000xx */
+		" addi    -8,%1,%1\n"
+		" extru,<>  %0,31,4,%%r0\n"
+		" extru,TR  %0,27,4,%0\n"	/* 000000x0 -> 0000000x */
+		" addi    -4,%1,%1\n"
+		" extru,<>  %0,31,2,%%r0\n"
+		" extru,TR  %0,29,2,%0\n"	/* 0000000y, 1100b -> 0011b */
+		" addi    -2,%1,%1\n"
+		" extru,=  %0,31,1,%%r0\n"	/* check last bit */
+		" addi    -1,%1,%1\n"
+			: "+r" (x), "=r" (ret) );
+	return ret;
+}
+
+#include <asm-generic/bitops/ffz.h>
+
+/*
+ * ffs: find first bit set. returns 1 to BITS_PER_LONG or 0 (if none set)
+ * This is defined the same way as the libc and compiler builtin
+ * ffs routines, therefore differs in spirit from the above ffz (man ffs).
+ */
+static __inline__ int ffs(int x)
+{
+	return x ? (__ffs((unsigned long)x) + 1) : 0;
+}
+
+/*
+ * fls: find last (most significant) bit set.
+ * fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
+ */
+
+static __inline__ int fls(int x)
+{
+	int ret;
+	if (!x)
+		return 0;
+
+	__asm__(
+	"	ldi		1,%1\n"
+	"	extru,<>	%0,15,16,%%r0\n"
+	"	zdep,TR		%0,15,16,%0\n"		/* xxxx0000 */
+	"	addi		16,%1,%1\n"
+	"	extru,<>	%0,7,8,%%r0\n"
+	"	zdep,TR		%0,23,24,%0\n"		/* xx000000 */
+	"	addi		8,%1,%1\n"
+	"	extru,<>	%0,3,4,%%r0\n"
+	"	zdep,TR		%0,27,28,%0\n"		/* x0000000 */
+	"	addi		4,%1,%1\n"
+	"	extru,<>	%0,1,2,%%r0\n"
+	"	zdep,TR		%0,29,30,%0\n"		/* y0000000 (y&3 = 0) */
+	"	addi		2,%1,%1\n"
+	"	extru,=		%0,0,1,%%r0\n"
+	"	addi		1,%1,%1\n"		/* if y & 8, add 1 */
+		: "+r" (x), "=r" (ret) );
+
+	return ret;
+}
+
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/lock.h>
+#include <asm-generic/bitops/sched.h>
+
+#endif /* __KERNEL__ */
+
+#include <asm-generic/bitops/find.h>
+
+#ifdef __KERNEL__
+
+#include <asm-generic/bitops/ext2-non-atomic.h>
+
+/* '3' is bits per byte */
+#define LE_BYTE_ADDR ((sizeof(unsigned long) - 1) << 3)
+
+#define ext2_set_bit_atomic(l,nr,addr) \
+		test_and_set_bit((nr)   ^ LE_BYTE_ADDR, (unsigned long *)addr)
+#define ext2_clear_bit_atomic(l,nr,addr) \
+		test_and_clear_bit( (nr) ^ LE_BYTE_ADDR, (unsigned long *)addr)
+
+#endif	/* __KERNEL__ */
+
+#include <asm-generic/bitops/minix-le.h>
+
+#endif /* _PARISC_BITOPS_H */
diff --git a/arch/parisc/include/asm/bug.h b/arch/parisc/include/asm/bug.h
new file mode 100644
index 000000000000..8cfc553fc837
--- /dev/null
+++ b/arch/parisc/include/asm/bug.h
@@ -0,0 +1,92 @@
+#ifndef _PARISC_BUG_H
+#define _PARISC_BUG_H
+
+/*
+ * Tell the user there is some problem.
+ * The offending file and line are encoded in the __bug_table section.
+ */
+
+#ifdef CONFIG_BUG
+#define HAVE_ARCH_BUG
+#define HAVE_ARCH_WARN_ON
+
+/* the break instruction is used as BUG() marker.  */
+#define	PARISC_BUG_BREAK_ASM	"break 0x1f, 0x1fff"
+#define	PARISC_BUG_BREAK_INSN	0x03ffe01f  /* PARISC_BUG_BREAK_ASM */
+
+#if defined(CONFIG_64BIT)
+#define ASM_WORD_INSN		".dword\t"
+#else
+#define ASM_WORD_INSN		".word\t"
+#endif
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define BUG()								\
+	do {								\
+		asm volatile("\n"					\
+			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
+			     "\t.pushsection __bug_table,\"a\"\n"	\
+			     "2:\t" ASM_WORD_INSN "1b, %c0\n"		\
+			     "\t.short %c1, %c2\n"			\
+			     "\t.org 2b+%c3\n"				\
+			     "\t.popsection"				\
+			     : : "i" (__FILE__), "i" (__LINE__),	\
+			     "i" (0), "i" (sizeof(struct bug_entry)) ); \
+		for(;;) ;						\
+	} while(0)
+
+#else
+#define BUG()								\
+	do {								\
+		asm volatile(PARISC_BUG_BREAK_ASM : : );		\
+		for(;;) ;						\
+	} while(0)
+#endif
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define __WARN()							\
+	do {								\
+		asm volatile("\n"					\
+			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
+			     "\t.pushsection __bug_table,\"a\"\n"	\
+			     "2:\t" ASM_WORD_INSN "1b, %c0\n"		\
+			     "\t.short %c1, %c2\n"			\
+			     "\t.org 2b+%c3\n"				\
+			     "\t.popsection"				\
+			     : : "i" (__FILE__), "i" (__LINE__),	\
+			     "i" (BUGFLAG_WARNING),			\
+			     "i" (sizeof(struct bug_entry)) );		\
+	} while(0)
+#else
+#define __WARN()							\
+	do {								\
+		asm volatile("\n"					\
+			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
+			     "\t.pushsection __bug_table,\"a\"\n"	\
+			     "2:\t" ASM_WORD_INSN "1b\n"		\
+			     "\t.short %c0\n"				\
+			     "\t.org 2b+%c1\n"				\
+			     "\t.popsection"				\
+			     : : "i" (BUGFLAG_WARNING),			\
+			     "i" (sizeof(struct bug_entry)) );		\
+	} while(0)
+#endif
+
+
+#define WARN_ON(x) ({						\
+	int __ret_warn_on = !!(x);				\
+	if (__builtin_constant_p(__ret_warn_on)) {		\
+		if (__ret_warn_on)				\
+			__WARN();				\
+	} else {						\
+		if (unlikely(__ret_warn_on))			\
+			__WARN();				\
+	}							\
+	unlikely(__ret_warn_on);				\
+})
+
+#endif
+
+#include <asm-generic/bug.h>
+#endif
+
diff --git a/arch/parisc/include/asm/bugs.h b/arch/parisc/include/asm/bugs.h
new file mode 100644
index 000000000000..9e6284342a5f
--- /dev/null
+++ b/arch/parisc/include/asm/bugs.h
@@ -0,0 +1,19 @@
+/*
+ *  include/asm-parisc/bugs.h
+ *
+ *  Copyright (C) 1999	Mike Shaver
+ */
+
+/*
+ * This is included by init/main.c to check for architecture-dependent bugs.
+ *
+ * Needs:
+ *	void check_bugs(void);
+ */
+
+#include <asm/processor.h>
+
+static inline void check_bugs(void)
+{
+//	identify_cpu(&boot_cpu_data);
+}
diff --git a/arch/parisc/include/asm/byteorder.h b/arch/parisc/include/asm/byteorder.h
new file mode 100644
index 000000000000..db148313de5d
--- /dev/null
+++ b/arch/parisc/include/asm/byteorder.h
@@ -0,0 +1,82 @@
+#ifndef _PARISC_BYTEORDER_H
+#define _PARISC_BYTEORDER_H
+
+#include <asm/types.h>
+#include <linux/compiler.h>
+
+#ifdef __GNUC__
+
+static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 x)
+{
+	__asm__("dep %0, 15, 8, %0\n\t"		/* deposit 00ab -> 0bab */
+		"shd %%r0, %0, 8, %0"		/* shift 000000ab -> 00ba */
+		: "=r" (x)
+		: "0" (x));
+	return x;
+}
+
+static __inline__ __attribute_const__ __u32 ___arch__swab24(__u32 x)
+{
+	__asm__("shd %0, %0, 8, %0\n\t"		/* shift xabcxabc -> cxab */
+		"dep %0, 15, 8, %0\n\t"		/* deposit cxab -> cbab */
+		"shd %%r0, %0, 8, %0"		/* shift 0000cbab -> 0cba */
+		: "=r" (x)
+		: "0" (x));
+	return x;
+}
+
+static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 x)
+{
+	unsigned int temp;
+	__asm__("shd %0, %0, 16, %1\n\t"	/* shift abcdabcd -> cdab */
+		"dep %1, 15, 8, %1\n\t"		/* deposit cdab -> cbab */
+		"shd %0, %1, 8, %0"		/* shift abcdcbab -> dcba */
+		: "=r" (x), "=&r" (temp)
+		: "0" (x));
+	return x;
+}
+
+
+#if BITS_PER_LONG > 32
+/*
+** From "PA-RISC 2.0 Architecture", HP Professional Books.
+** See Appendix I page 8 , "Endian Byte Swapping".
+**
+** Pretty cool algorithm: (* == zero'd bits)
+**      PERMH   01234567 -> 67452301 into %0
+**      HSHL    67452301 -> 7*5*3*1* into %1
+**      HSHR    67452301 -> *6*4*2*0 into %0
+**      OR      %0 | %1  -> 76543210 into %0 (all done!)
+*/
+static __inline__ __attribute_const__ __u64 ___arch__swab64(__u64 x) {
+	__u64 temp;
+	__asm__("permh,3210 %0, %0\n\t"
+		"hshl %0, 8, %1\n\t"
+		"hshr,u %0, 8, %0\n\t"
+		"or %1, %0, %0"
+		: "=r" (x), "=&r" (temp)
+		: "0" (x));
+	return x;
+}
+#define __arch__swab64(x) ___arch__swab64(x)
+#define __BYTEORDER_HAS_U64__
+#elif !defined(__STRICT_ANSI__)
+static __inline__ __attribute_const__ __u64 ___arch__swab64(__u64 x)
+{
+	__u32 t1 = ___arch__swab32((__u32) x);
+	__u32 t2 = ___arch__swab32((__u32) (x >> 32));
+	return (((__u64) t1 << 32) | t2);
+}
+#define __arch__swab64(x) ___arch__swab64(x)
+#define __BYTEORDER_HAS_U64__
+#endif
+
+#define __arch__swab16(x) ___arch__swab16(x)
+#define __arch__swab24(x) ___arch__swab24(x)
+#define __arch__swab32(x) ___arch__swab32(x)
+
+#endif /* __GNUC__ */
+
+#include <linux/byteorder/big_endian.h>
+
+#endif /* _PARISC_BYTEORDER_H */
diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h
new file mode 100644
index 000000000000..32c2cca74345
--- /dev/null
+++ b/arch/parisc/include/asm/cache.h
@@ -0,0 +1,60 @@
+/*
+ * include/asm-parisc/cache.h
+ */
+
+#ifndef __ARCH_PARISC_CACHE_H
+#define __ARCH_PARISC_CACHE_H
+
+
+/*
+ * PA 2.0 processors have 64-byte cachelines; PA 1.1 processors have
+ * 32-byte cachelines.  The default configuration is not for SMP anyway,
+ * so if you're building for SMP, you should select the appropriate
+ * processor type.  There is a potential livelock danger when running
+ * a machine with this value set too small, but it's more probable you'll
+ * just ruin performance.
+ */
+#ifdef CONFIG_PA20
+#define L1_CACHE_BYTES 64
+#define L1_CACHE_SHIFT 6
+#else
+#define L1_CACHE_BYTES 32
+#define L1_CACHE_SHIFT 5
+#endif
+
+#ifndef __ASSEMBLY__
+
+#define L1_CACHE_ALIGN(x)       (((x)+(L1_CACHE_BYTES-1))&~(L1_CACHE_BYTES-1))
+
+#define SMP_CACHE_BYTES L1_CACHE_BYTES
+
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
+void parisc_cache_init(void);	/* initializes cache-flushing */
+void disable_sr_hashing_asm(int); /* low level support for above */
+void disable_sr_hashing(void);   /* turns off space register hashing */
+void free_sid(unsigned long);
+unsigned long alloc_sid(void);
+
+struct seq_file;
+extern void show_cache_info(struct seq_file *m);
+
+extern int split_tlb;
+extern int dcache_stride;
+extern int icache_stride;
+extern struct pdc_cache_info cache_info;
+void parisc_setup_cache_timing(void);
+
+#define pdtlb(addr)         asm volatile("pdtlb 0(%%sr1,%0)" : : "r" (addr));
+#define pitlb(addr)         asm volatile("pitlb 0(%%sr1,%0)" : : "r" (addr));
+#define pdtlb_kernel(addr)  asm volatile("pdtlb 0(%0)" : : "r" (addr));
+
+#endif /* ! __ASSEMBLY__ */
+
+/* Classes of processor wrt: disabling space register hashing */
+
+#define SRHASH_PCXST    0   /* pcxs, pcxt, pcxt_ */
+#define SRHASH_PCXL     1   /* pcxl */
+#define SRHASH_PA20     2   /* pcxu, pcxu_, pcxw, pcxw_ */
+
+#endif
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
new file mode 100644
index 000000000000..b7ca6dc7fddc
--- /dev/null
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -0,0 +1,121 @@
+#ifndef _PARISC_CACHEFLUSH_H
+#define _PARISC_CACHEFLUSH_H
+
+#include <linux/mm.h>
+
+/* The usual comment is "Caches aren't brain-dead on the <architecture>".
+ * Unfortunately, that doesn't apply to PA-RISC. */
+
+/* Internal implementation */
+void flush_data_cache_local(void *);  /* flushes local data-cache only */
+void flush_instruction_cache_local(void *); /* flushes local code-cache only */
+#ifdef CONFIG_SMP
+void flush_data_cache(void); /* flushes data-cache only (all processors) */
+void flush_instruction_cache(void); /* flushes i-cache only (all processors) */
+#else
+#define flush_data_cache() flush_data_cache_local(NULL)
+#define flush_instruction_cache() flush_instruction_cache_local(NULL)
+#endif
+
+#define flush_cache_dup_mm(mm) flush_cache_mm(mm)
+
+void flush_user_icache_range_asm(unsigned long, unsigned long);
+void flush_kernel_icache_range_asm(unsigned long, unsigned long);
+void flush_user_dcache_range_asm(unsigned long, unsigned long);
+void flush_kernel_dcache_range_asm(unsigned long, unsigned long);
+void flush_kernel_dcache_page_asm(void *);
+void flush_kernel_icache_page(void *);
+void flush_user_dcache_page(unsigned long);
+void flush_user_icache_page(unsigned long);
+void flush_user_dcache_range(unsigned long, unsigned long);
+void flush_user_icache_range(unsigned long, unsigned long);
+
+/* Cache flush operations */
+
+void flush_cache_all_local(void);
+void flush_cache_all(void);
+void flush_cache_mm(struct mm_struct *mm);
+
+#define flush_kernel_dcache_range(start,size) \
+	flush_kernel_dcache_range_asm((start), (start)+(size));
+
+#define flush_cache_vmap(start, end)		flush_cache_all()
+#define flush_cache_vunmap(start, end)		flush_cache_all()
+
+extern void flush_dcache_page(struct page *page);
+
+#define flush_dcache_mmap_lock(mapping) \
+	spin_lock_irq(&(mapping)->tree_lock)
+#define flush_dcache_mmap_unlock(mapping) \
+	spin_unlock_irq(&(mapping)->tree_lock)
+
+#define flush_icache_page(vma,page)	do { 		\
+	flush_kernel_dcache_page(page);			\
+	flush_kernel_icache_page(page_address(page)); 	\
+} while (0)
+
+#define flush_icache_range(s,e)		do { 		\
+	flush_kernel_dcache_range_asm(s,e); 		\
+	flush_kernel_icache_range_asm(s,e); 		\
+} while (0)
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
+do { \
+	flush_cache_page(vma, vaddr, page_to_pfn(page)); \
+	memcpy(dst, src, len); \
+	flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); \
+} while (0)
+
+#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
+do { \
+	flush_cache_page(vma, vaddr, page_to_pfn(page)); \
+	memcpy(dst, src, len); \
+} while (0)
+
+void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn);
+void flush_cache_range(struct vm_area_struct *vma,
+		unsigned long start, unsigned long end);
+
+#define ARCH_HAS_FLUSH_ANON_PAGE
+static inline void
+flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
+{
+	if (PageAnon(page))
+		flush_user_dcache_page(vmaddr);
+}
+
+#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
+void flush_kernel_dcache_page_addr(void *addr);
+static inline void flush_kernel_dcache_page(struct page *page)
+{
+	flush_kernel_dcache_page_addr(page_address(page));
+}
+
+#ifdef CONFIG_DEBUG_RODATA
+void mark_rodata_ro(void);
+#endif
+
+#ifdef CONFIG_PA8X00
+/* Only pa8800, pa8900 needs this */
+#define ARCH_HAS_KMAP
+
+void kunmap_parisc(void *addr);
+
+static inline void *kmap(struct page *page)
+{
+	might_sleep();
+	return page_address(page);
+}
+
+#define kunmap(page)			kunmap_parisc(page_address(page))
+
+#define kmap_atomic(page, idx)		page_address(page)
+
+#define kunmap_atomic(addr, idx)	kunmap_parisc(addr)
+
+#define kmap_atomic_pfn(pfn, idx)	page_address(pfn_to_page(pfn))
+#define kmap_atomic_to_page(ptr)	virt_to_page(ptr)
+#endif
+
+#endif /* _PARISC_CACHEFLUSH_H */
+
diff --git a/arch/parisc/include/asm/checksum.h b/arch/parisc/include/asm/checksum.h
new file mode 100644
index 000000000000..e9639ccc3fce
--- /dev/null
+++ b/arch/parisc/include/asm/checksum.h
@@ -0,0 +1,210 @@
+#ifndef _PARISC_CHECKSUM_H
+#define _PARISC_CHECKSUM_H
+
+#include <linux/in6.h>
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+extern __wsum csum_partial(const void *, int, __wsum);
+
+/*
+ * The same as csum_partial, but copies from src while it checksums.
+ *
+ * Here even more important to align src and dst on a 32-bit (or even
+ * better 64-bit) boundary
+ */
+extern __wsum csum_partial_copy_nocheck(const void *, void *, int, __wsum);
+
+/*
+ * this is a new version of the above that records errors it finds in *errp,
+ * but continues and zeros the rest of the buffer.
+ */
+extern __wsum csum_partial_copy_from_user(const void __user *src,
+		void *dst, int len, __wsum sum, int *errp);
+
+/*
+ *	Optimized for IP headers, which always checksum on 4 octet boundaries.
+ *
+ *	Written by Randolph Chung <tausq@debian.org>, and then mucked with by
+ *	LaMont Jones <lamont@debian.org>
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	unsigned int sum;
+
+	__asm__ __volatile__ (
+"	ldws,ma		4(%1), %0\n"
+"	addib,<=	-4, %2, 2f\n"
+"\n"
+"	ldws		4(%1), %%r20\n"
+"	ldws		8(%1), %%r21\n"
+"	add		%0, %%r20, %0\n"
+"	ldws,ma		12(%1), %%r19\n"
+"	addc		%0, %%r21, %0\n"
+"	addc		%0, %%r19, %0\n"
+"1:	ldws,ma		4(%1), %%r19\n"
+"	addib,<		0, %2, 1b\n"
+"	addc		%0, %%r19, %0\n"
+"\n"
+"	extru		%0, 31, 16, %%r20\n"
+"	extru		%0, 15, 16, %%r21\n"
+"	addc		%%r20, %%r21, %0\n"
+"	extru		%0, 15, 16, %%r21\n"
+"	add		%0, %%r21, %0\n"
+"	subi		-1, %0, %0\n"
+"2:\n"
+	: "=r" (sum), "=r" (iph), "=r" (ihl)
+	: "1" (iph), "2" (ihl)
+	: "r19", "r20", "r21", "memory");
+
+	return (__force __sum16)sum;
+}
+
+/*
+ *	Fold a partial checksum
+ */
+static inline __sum16 csum_fold(__wsum csum)
+{
+	u32 sum = (__force u32)csum;
+	/* add the swapped two 16-bit halves of sum,
+	   a possible carry from adding the two 16-bit halves,
+	   will carry from the lower half into the upper half,
+	   giving us the correct sum in the upper half. */
+	sum += (sum << 16) + (sum >> 16);
+	return (__force __sum16)(~sum >> 16);
+}
+ 
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+					       unsigned short len,
+					       unsigned short proto,
+					       __wsum sum)
+{
+	__asm__(
+	"	add  %1, %0, %0\n"
+	"	addc %2, %0, %0\n"
+	"	addc %3, %0, %0\n"
+	"	addc %%r0, %0, %0\n"
+		: "=r" (sum)
+		: "r" (daddr), "r"(saddr), "r"(proto+len), "0"(sum));
+	return sum;
+}
+
+/*
+ * computes the checksum of the TCP/UDP pseudo-header
+ * returns a 16-bit checksum, already complemented
+ */
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+						   unsigned short len,
+						   unsigned short proto,
+						   __wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
+}
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+static inline __sum16 ip_compute_csum(const void *buf, int len)
+{
+	 return csum_fold (csum_partial(buf, len, 0));
+}
+
+
+#define _HAVE_ARCH_IPV6_CSUM
+static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+					  const struct in6_addr *daddr,
+					  __u32 len, unsigned short proto,
+					  __wsum sum)
+{
+	__asm__ __volatile__ (
+
+#if BITS_PER_LONG > 32
+
+	/*
+	** We can execute two loads and two adds per cycle on PA 8000.
+	** But add insn's get serialized waiting for the carry bit.
+	** Try to keep 4 registers with "live" values ahead of the ALU.
+	*/
+
+"	ldd,ma		8(%1), %%r19\n"	/* get 1st saddr word */
+"	ldd,ma		8(%2), %%r20\n"	/* get 1st daddr word */
+"	add		%8, %3, %3\n"/* add 16-bit proto + len */
+"	add		%%r19, %0, %0\n"
+"	ldd,ma		8(%1), %%r21\n"	/* 2cd saddr */
+"	ldd,ma		8(%2), %%r22\n"	/* 2cd daddr */
+"	add,dc		%%r20, %0, %0\n"
+"	add,dc		%%r21, %0, %0\n"
+"	add,dc		%%r22, %0, %0\n"
+"	add,dc		%3, %0, %0\n"  /* fold in proto+len | carry bit */
+"	extrd,u		%0, 31, 32, %%r19\n"	/* copy upper half down */
+"	depdi		0, 31, 32, %0\n"	/* clear upper half */
+"	add		%%r19, %0, %0\n"	/* fold into 32-bits */
+"	addc		0, %0, %0\n"		/* add carry */
+
+#else
+
+	/*
+	** For PA 1.x, the insn order doesn't matter as much.
+	** Insn stream is serialized on the carry bit here too.
+	** result from the previous operation (eg r0 + x)
+	*/
+
+"	ldw,ma		4(%1), %%r19\n"	/* get 1st saddr word */
+"	ldw,ma		4(%2), %%r20\n"	/* get 1st daddr word */
+"	add		%8, %3, %3\n"	/* add 16-bit proto + len */
+"	add		%%r19, %0, %0\n"
+"	ldw,ma		4(%1), %%r21\n"	/* 2cd saddr */
+"	addc		%%r20, %0, %0\n"
+"	ldw,ma		4(%2), %%r22\n"	/* 2cd daddr */
+"	addc		%%r21, %0, %0\n"
+"	ldw,ma		4(%1), %%r19\n"	/* 3rd saddr */
+"	addc		%%r22, %0, %0\n"
+"	ldw,ma		4(%2), %%r20\n"	/* 3rd daddr */
+"	addc		%%r19, %0, %0\n"
+"	ldw,ma		4(%1), %%r21\n"	/* 4th saddr */
+"	addc		%%r20, %0, %0\n"
+"	ldw,ma		4(%2), %%r22\n"	/* 4th daddr */
+"	addc		%%r21, %0, %0\n"
+"	addc		%%r22, %0, %0\n"
+"	addc		%3, %0, %0\n"	/* fold in proto+len, catch carry */
+
+#endif
+	: "=r" (sum), "=r" (saddr), "=r" (daddr), "=r" (len)
+	: "0" (sum), "1" (saddr), "2" (daddr), "3" (len), "r" (proto)
+	: "r19", "r20", "r21", "r22");
+	return csum_fold(sum);
+}
+
+/* 
+ *	Copy and checksum to user
+ */
+#define HAVE_CSUM_COPY_USER
+static __inline__ __wsum csum_and_copy_to_user(const void *src,
+						      void __user *dst,
+						      int len, __wsum sum,
+						      int *err_ptr)
+{
+	/* code stolen from include/asm-mips64 */
+	sum = csum_partial(src, len, sum);
+	 
+	if (copy_to_user(dst, src, len)) {
+		*err_ptr = -EFAULT;
+		return (__force __wsum)-1;
+	}
+
+	return sum;
+}
+
+#endif
+
diff --git a/arch/parisc/include/asm/compat.h b/arch/parisc/include/asm/compat.h
new file mode 100644
index 000000000000..7f32611a7a5e
--- /dev/null
+++ b/arch/parisc/include/asm/compat.h
@@ -0,0 +1,165 @@
+#ifndef _ASM_PARISC_COMPAT_H
+#define _ASM_PARISC_COMPAT_H
+/*
+ * Architecture specific compatibility types
+ */
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/thread_info.h>
+
+#define COMPAT_USER_HZ 100
+
+typedef u32	compat_size_t;
+typedef s32	compat_ssize_t;
+typedef s32	compat_time_t;
+typedef s32	compat_clock_t;
+typedef s32	compat_pid_t;
+typedef u32	__compat_uid_t;
+typedef u32	__compat_gid_t;
+typedef u32	__compat_uid32_t;
+typedef u32	__compat_gid32_t;
+typedef u16	compat_mode_t;
+typedef u32	compat_ino_t;
+typedef u32	compat_dev_t;
+typedef s32	compat_off_t;
+typedef s64	compat_loff_t;
+typedef u16	compat_nlink_t;
+typedef u16	compat_ipc_pid_t;
+typedef s32	compat_daddr_t;
+typedef u32	compat_caddr_t;
+typedef s32	compat_timer_t;
+
+typedef s32	compat_int_t;
+typedef s32	compat_long_t;
+typedef s64	compat_s64;
+typedef u32	compat_uint_t;
+typedef u32	compat_ulong_t;
+typedef u64	compat_u64;
+
+struct compat_timespec {
+	compat_time_t		tv_sec;
+	s32			tv_nsec;
+};
+
+struct compat_timeval {
+	compat_time_t		tv_sec;
+	s32			tv_usec;
+};
+
+struct compat_stat {
+	compat_dev_t		st_dev;	/* dev_t is 32 bits on parisc */
+	compat_ino_t		st_ino;	/* 32 bits */
+	compat_mode_t		st_mode;	/* 16 bits */
+	compat_nlink_t  	st_nlink;	/* 16 bits */
+	u16			st_reserved1;	/* old st_uid */
+	u16			st_reserved2;	/* old st_gid */
+	compat_dev_t		st_rdev;
+	compat_off_t		st_size;
+	compat_time_t		st_atime;
+	u32			st_atime_nsec;
+	compat_time_t		st_mtime;
+	u32			st_mtime_nsec;
+	compat_time_t		st_ctime;
+	u32			st_ctime_nsec;
+	s32			st_blksize;
+	s32			st_blocks;
+	u32			__unused1;	/* ACL stuff */
+	compat_dev_t		__unused2;	/* network */
+	compat_ino_t		__unused3;	/* network */
+	u32			__unused4;	/* cnodes */
+	u16			__unused5;	/* netsite */
+	short			st_fstype;
+	compat_dev_t		st_realdev;
+	u16			st_basemode;
+	u16			st_spareshort;
+	__compat_uid32_t	st_uid;
+	__compat_gid32_t	st_gid;
+	u32			st_spare4[3];
+};
+
+struct compat_flock {
+	short			l_type;
+	short			l_whence;
+	compat_off_t		l_start;
+	compat_off_t		l_len;
+	compat_pid_t		l_pid;
+};
+
+struct compat_flock64 {
+	short			l_type;
+	short			l_whence;
+	compat_loff_t		l_start;
+	compat_loff_t		l_len;
+	compat_pid_t		l_pid;
+};
+
+struct compat_statfs {
+	s32		f_type;
+	s32		f_bsize;
+	s32		f_blocks;
+	s32		f_bfree;
+	s32		f_bavail;
+	s32		f_files;
+	s32		f_ffree;
+	__kernel_fsid_t	f_fsid;
+	s32		f_namelen;
+	s32		f_frsize;
+	s32		f_spare[5];
+};
+
+struct compat_sigcontext {
+	compat_int_t sc_flags;
+	compat_int_t sc_gr[32]; /* PSW in sc_gr[0] */
+	u64 sc_fr[32];
+	compat_int_t sc_iasq[2];
+	compat_int_t sc_iaoq[2];
+	compat_int_t sc_sar; /* cr11 */
+};
+
+#define COMPAT_RLIM_INFINITY 0xffffffff
+
+typedef u32		compat_old_sigset_t;	/* at least 32 bits */
+
+#define _COMPAT_NSIG		64
+#define _COMPAT_NSIG_BPW	32
+
+typedef u32		compat_sigset_word;
+
+#define COMPAT_OFF_T_MAX	0x7fffffff
+#define COMPAT_LOFF_T_MAX	0x7fffffffffffffffL
+
+/*
+ * A pointer passed in from user mode. This should not
+ * be used for syscall parameters, just declare them
+ * as pointers because the syscall entry code will have
+ * appropriately converted them already.
+ */
+typedef	u32		compat_uptr_t;
+
+static inline void __user *compat_ptr(compat_uptr_t uptr)
+{
+	return (void __user *)(unsigned long)uptr;
+}
+
+static inline compat_uptr_t ptr_to_compat(void __user *uptr)
+{
+	return (u32)(unsigned long)uptr;
+}
+
+static __inline__ void __user *compat_alloc_user_space(long len)
+{
+	struct pt_regs *regs = &current->thread.regs;
+	return (void __user *)regs->gr[30];
+}
+
+static inline int __is_compat_task(struct task_struct *t)
+{
+	return test_ti_thread_flag(task_thread_info(t), TIF_32BIT);
+}
+
+static inline int is_compat_task(void)
+{
+	return __is_compat_task(current);
+}
+
+#endif /* _ASM_PARISC_COMPAT_H */
diff --git a/arch/parisc/include/asm/compat_rt_sigframe.h b/arch/parisc/include/asm/compat_rt_sigframe.h
new file mode 100644
index 000000000000..81bec28bdc48
--- /dev/null
+++ b/arch/parisc/include/asm/compat_rt_sigframe.h
@@ -0,0 +1,50 @@
+#include<linux/compat.h>
+#include<linux/compat_siginfo.h>
+#include<asm/compat_ucontext.h>
+
+#ifndef _ASM_PARISC_COMPAT_RT_SIGFRAME_H
+#define _ASM_PARISC_COMPAT_RT_SIGFRAME_H
+
+/* In a deft move of uber-hackery, we decide to carry the top half of all
+ * 64-bit registers in a non-portable, non-ABI, hidden structure.
+ * Userspace can read the hidden structure if it *wants* but is never
+ * guaranteed to be in the same place. Infact the uc_sigmask from the 
+ * ucontext_t structure may push the hidden register file downards
+ */
+struct compat_regfile {
+	/* Upper half of all the 64-bit registers that were truncated
+	   on a copy to a 32-bit userspace */
+	compat_int_t rf_gr[32];
+	compat_int_t rf_iasq[2];
+	compat_int_t rf_iaoq[2];
+	compat_int_t rf_sar;
+};
+
+#define COMPAT_SIGRETURN_TRAMP 4
+#define COMPAT_SIGRESTARTBLOCK_TRAMP 5 
+#define COMPAT_TRAMP_SIZE (COMPAT_SIGRETURN_TRAMP + COMPAT_SIGRESTARTBLOCK_TRAMP)
+
+struct compat_rt_sigframe {
+	/* XXX: Must match trampoline size in arch/parisc/kernel/signal.c 
+	        Secondary to that it must protect the ERESTART_RESTARTBLOCK
+		trampoline we left on the stack (we were bad and didn't 
+		change sp so we could run really fast.) */
+	compat_uint_t tramp[COMPAT_TRAMP_SIZE];
+	compat_siginfo_t info;
+	struct compat_ucontext uc;
+	/* Hidden location of truncated registers, *must* be last. */
+	struct compat_regfile regs; 
+};
+
+/*
+ * The 32-bit ABI wants at least 48 bytes for a function call frame:
+ * 16 bytes for arg0-arg3, and 32 bytes for magic (the only part of
+ * which Linux/parisc uses is sp-20 for the saved return pointer...)
+ * Then, the stack pointer must be rounded to a cache line (64 bytes).
+ */
+#define SIGFRAME32		64
+#define FUNCTIONCALLFRAME32	48
+#define PARISC_RT_SIGFRAME_SIZE32					\
+	(((sizeof(struct compat_rt_sigframe) + FUNCTIONCALLFRAME32) + SIGFRAME32) & -SIGFRAME32)
+
+#endif
diff --git a/arch/parisc/include/asm/compat_signal.h b/arch/parisc/include/asm/compat_signal.h
new file mode 100644
index 000000000000..6ad02c360b21
--- /dev/null
+++ b/arch/parisc/include/asm/compat_signal.h
@@ -0,0 +1,2 @@
+/* Use generic */
+#include <asm-generic/compat_signal.h>
diff --git a/arch/parisc/include/asm/compat_ucontext.h b/arch/parisc/include/asm/compat_ucontext.h
new file mode 100644
index 000000000000..2f7292afde3c
--- /dev/null
+++ b/arch/parisc/include/asm/compat_ucontext.h
@@ -0,0 +1,17 @@
+#ifndef _ASM_PARISC_COMPAT_UCONTEXT_H
+#define _ASM_PARISC_COMPAT_UCONTEXT_H
+
+#include <linux/compat.h>
+
+/* 32-bit ucontext as seen from an 64-bit kernel */
+struct compat_ucontext {
+	compat_uint_t uc_flags;
+	compat_uptr_t uc_link;
+	compat_stack_t uc_stack;	/* struct compat_sigaltstack (12 bytes)*/	
+	/* FIXME: Pad out to get uc_mcontext to start at an 8-byte aligned boundary */
+	compat_uint_t pad[1];
+	struct compat_sigcontext uc_mcontext;
+	compat_sigset_t uc_sigmask;	/* mask last for extensibility */
+};
+
+#endif /* !_ASM_PARISC_COMPAT_UCONTEXT_H */
diff --git a/arch/parisc/include/asm/cputime.h b/arch/parisc/include/asm/cputime.h
new file mode 100644
index 000000000000..dcdf2fbd7e72
--- /dev/null
+++ b/arch/parisc/include/asm/cputime.h
@@ -0,0 +1,6 @@
+#ifndef __PARISC_CPUTIME_H
+#define __PARISC_CPUTIME_H
+
+#include <asm-generic/cputime.h>
+
+#endif /* __PARISC_CPUTIME_H */
diff --git a/arch/parisc/include/asm/current.h b/arch/parisc/include/asm/current.h
new file mode 100644
index 000000000000..0fb9338e3bf2
--- /dev/null
+++ b/arch/parisc/include/asm/current.h
@@ -0,0 +1,15 @@
+#ifndef _PARISC_CURRENT_H
+#define _PARISC_CURRENT_H
+
+#include <linux/thread_info.h>
+
+struct task_struct;
+
+static inline struct task_struct * get_current(void)
+{
+	return current_thread_info()->task;
+}
+ 
+#define current get_current()
+
+#endif /* !(_PARISC_CURRENT_H) */
diff --git a/arch/parisc/include/asm/delay.h b/arch/parisc/include/asm/delay.h
new file mode 100644
index 000000000000..7a75e984674b
--- /dev/null
+++ b/arch/parisc/include/asm/delay.h
@@ -0,0 +1,43 @@
+#ifndef _PARISC_DELAY_H
+#define _PARISC_DELAY_H
+
+#include <asm/system.h>    /* for mfctl() */
+#include <asm/processor.h> /* for boot_cpu_data */
+
+
+/*
+ * Copyright (C) 1993 Linus Torvalds
+ *
+ * Delay routines
+ */
+
+static __inline__ void __delay(unsigned long loops) {
+	asm volatile(
+	"	.balignl	64,0x34000034\n"
+	"	addib,UV -1,%0,.\n"
+	"	nop\n"
+		: "=r" (loops) : "0" (loops));
+}
+
+static __inline__ void __cr16_delay(unsigned long clocks) {
+	unsigned long start;
+
+	/*
+	 * Note: Due to unsigned math, cr16 rollovers shouldn't be
+	 * a problem here. However, on 32 bit, we need to make sure
+	 * we don't pass in too big a value. The current default
+	 * value of MAX_UDELAY_MS should help prevent this.
+	 */
+
+	start = mfctl(16);
+	while ((mfctl(16) - start) < clocks)
+	    ;
+}
+
+static __inline__ void __udelay(unsigned long usecs) {
+	__cr16_delay(usecs * ((unsigned long)boot_cpu_data.cpu_hz / 1000000UL));
+}
+
+#define udelay(n) __udelay(n)
+
+#endif /* defined(_PARISC_DELAY_H) */
diff --git a/arch/parisc/include/asm/device.h b/arch/parisc/include/asm/device.h
new file mode 100644
index 000000000000..d8f9872b0e2d
--- /dev/null
+++ b/arch/parisc/include/asm/device.h
@@ -0,0 +1,7 @@
+/*
+ * Arch specific extensions to struct device
+ *
+ * This file is released under the GPLv2
+ */
+#include <asm-generic/device.h>
+
diff --git a/arch/parisc/include/asm/div64.h b/arch/parisc/include/asm/div64.h
new file mode 100644
index 000000000000..6cd978cefb28
--- /dev/null
+++ b/arch/parisc/include/asm/div64.h
@@ -0,0 +1 @@
+#include <asm-generic/div64.h>
diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h
new file mode 100644
index 000000000000..53af696f23d2
--- /dev/null
+++ b/arch/parisc/include/asm/dma-mapping.h
@@ -0,0 +1,253 @@
+#ifndef _PARISC_DMA_MAPPING_H
+#define _PARISC_DMA_MAPPING_H
+
+#include <linux/mm.h>
+#include <asm/cacheflush.h>
+#include <asm/scatterlist.h>
+
+/* See Documentation/DMA-mapping.txt */
+struct hppa_dma_ops {
+	int  (*dma_supported)(struct device *dev, u64 mask);
+	void *(*alloc_consistent)(struct device *dev, size_t size, dma_addr_t *iova, gfp_t flag);
+	void *(*alloc_noncoherent)(struct device *dev, size_t size, dma_addr_t *iova, gfp_t flag);
+	void (*free_consistent)(struct device *dev, size_t size, void *vaddr, dma_addr_t iova);
+	dma_addr_t (*map_single)(struct device *dev, void *addr, size_t size, enum dma_data_direction direction);
+	void (*unmap_single)(struct device *dev, dma_addr_t iova, size_t size, enum dma_data_direction direction);
+	int  (*map_sg)(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction);
+	void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nhwents, enum dma_data_direction direction);
+	void (*dma_sync_single_for_cpu)(struct device *dev, dma_addr_t iova, unsigned long offset, size_t size, enum dma_data_direction direction);
+	void (*dma_sync_single_for_device)(struct device *dev, dma_addr_t iova, unsigned long offset, size_t size, enum dma_data_direction direction);
+	void (*dma_sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction direction);
+	void (*dma_sync_sg_for_device)(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction direction);
+};
+
+/*
+** We could live without the hppa_dma_ops indirection if we didn't want
+** to support 4 different coherent dma models with one binary (they will
+** someday be loadable modules):
+**     I/O MMU        consistent method           dma_sync behavior
+**  =============   ======================       =======================
+**  a) PA-7x00LC    uncachable host memory          flush/purge
+**  b) U2/Uturn      cachable host memory              NOP
+**  c) Ike/Astro     cachable host memory              NOP
+**  d) EPIC/SAGA     memory on EPIC/SAGA         flush/reset DMA channel
+**
+** PA-7[13]00LC processors have a GSC bus interface and no I/O MMU.
+**
+** Systems (eg PCX-T workstations) that don't fall into the above
+** categories will need to modify the needed drivers to perform
+** flush/purge and allocate "regular" cacheable pages for everything.
+*/
+
+#ifdef CONFIG_PA11
+extern struct hppa_dma_ops pcxl_dma_ops;
+extern struct hppa_dma_ops pcx_dma_ops;
+#endif
+
+extern struct hppa_dma_ops *hppa_dma_ops;
+
+static inline void *
+dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		   gfp_t flag)
+{
+	return hppa_dma_ops->alloc_consistent(dev, size, dma_handle, flag);
+}
+
+static inline void *
+dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		      gfp_t flag)
+{
+	return hppa_dma_ops->alloc_noncoherent(dev, size, dma_handle, flag);
+}
+
+static inline void
+dma_free_coherent(struct device *dev, size_t size, 
+		    void *vaddr, dma_addr_t dma_handle)
+{
+	hppa_dma_ops->free_consistent(dev, size, vaddr, dma_handle);
+}
+
+static inline void
+dma_free_noncoherent(struct device *dev, size_t size, 
+		    void *vaddr, dma_addr_t dma_handle)
+{
+	hppa_dma_ops->free_consistent(dev, size, vaddr, dma_handle);
+}
+
+static inline dma_addr_t
+dma_map_single(struct device *dev, void *ptr, size_t size,
+	       enum dma_data_direction direction)
+{
+	return hppa_dma_ops->map_single(dev, ptr, size, direction);
+}
+
+static inline void
+dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
+		 enum dma_data_direction direction)
+{
+	hppa_dma_ops->unmap_single(dev, dma_addr, size, direction);
+}
+
+static inline int
+dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+	   enum dma_data_direction direction)
+{
+	return hppa_dma_ops->map_sg(dev, sg, nents, direction);
+}
+
+static inline void
+dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
+	     enum dma_data_direction direction)
+{
+	hppa_dma_ops->unmap_sg(dev, sg, nhwentries, direction);
+}
+
+static inline dma_addr_t
+dma_map_page(struct device *dev, struct page *page, unsigned long offset,
+	     size_t size, enum dma_data_direction direction)
+{
+	return dma_map_single(dev, (page_address(page) + (offset)), size, direction);
+}
+
+static inline void
+dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
+	       enum dma_data_direction direction)
+{
+	dma_unmap_single(dev, dma_address, size, direction);
+}
+
+
+static inline void
+dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
+{
+	if(hppa_dma_ops->dma_sync_single_for_cpu)
+		hppa_dma_ops->dma_sync_single_for_cpu(dev, dma_handle, 0, size, direction);
+}
+
+static inline void
+dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
+{
+	if(hppa_dma_ops->dma_sync_single_for_device)
+		hppa_dma_ops->dma_sync_single_for_device(dev, dma_handle, 0, size, direction);
+}
+
+static inline void
+dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
+		      unsigned long offset, size_t size,
+		      enum dma_data_direction direction)
+{
+	if(hppa_dma_ops->dma_sync_single_for_cpu)
+		hppa_dma_ops->dma_sync_single_for_cpu(dev, dma_handle, offset, size, direction);
+}
+
+static inline void
+dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
+		      unsigned long offset, size_t size,
+		      enum dma_data_direction direction)
+{
+	if(hppa_dma_ops->dma_sync_single_for_device)
+		hppa_dma_ops->dma_sync_single_for_device(dev, dma_handle, offset, size, direction);
+}
+
+static inline void
+dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
+		 enum dma_data_direction direction)
+{
+	if(hppa_dma_ops->dma_sync_sg_for_cpu)
+		hppa_dma_ops->dma_sync_sg_for_cpu(dev, sg, nelems, direction);
+}
+
+static inline void
+dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
+		 enum dma_data_direction direction)
+{
+	if(hppa_dma_ops->dma_sync_sg_for_device)
+		hppa_dma_ops->dma_sync_sg_for_device(dev, sg, nelems, direction);
+}
+
+static inline int
+dma_supported(struct device *dev, u64 mask)
+{
+	return hppa_dma_ops->dma_supported(dev, mask);
+}
+
+static inline int
+dma_set_mask(struct device *dev, u64 mask)
+{
+	if(!dev->dma_mask || !dma_supported(dev, mask))
+		return -EIO;
+
+	*dev->dma_mask = mask;
+
+	return 0;
+}
+
+static inline int
+dma_get_cache_alignment(void)
+{
+	return dcache_stride;
+}
+
+static inline int
+dma_is_consistent(struct device *dev, dma_addr_t dma_addr)
+{
+	return (hppa_dma_ops->dma_sync_single_for_cpu == NULL);
+}
+
+static inline void
+dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+	       enum dma_data_direction direction)
+{
+	if(hppa_dma_ops->dma_sync_single_for_cpu)
+		flush_kernel_dcache_range((unsigned long)vaddr, size);
+}
+
+static inline void *
+parisc_walk_tree(struct device *dev)
+{
+	struct device *otherdev;
+	if(likely(dev->platform_data != NULL))
+		return dev->platform_data;
+	/* OK, just traverse the bus to find it */
+	for(otherdev = dev->parent; otherdev;
+	    otherdev = otherdev->parent) {
+		if(otherdev->platform_data) {
+			dev->platform_data = otherdev->platform_data;
+			break;
+		}
+	}
+	BUG_ON(!dev->platform_data);
+	return dev->platform_data;
+}
+		
+#define GET_IOC(dev) (HBA_DATA(parisc_walk_tree(dev))->iommu);	
+	
+
+#ifdef CONFIG_IOMMU_CCIO
+struct parisc_device;
+struct ioc;
+void * ccio_get_iommu(const struct parisc_device *dev);
+int ccio_request_resource(const struct parisc_device *dev,
+		struct resource *res);
+int ccio_allocate_resource(const struct parisc_device *dev,
+		struct resource *res, unsigned long size,
+		unsigned long min, unsigned long max, unsigned long align);
+#else /* !CONFIG_IOMMU_CCIO */
+#define ccio_get_iommu(dev) NULL
+#define ccio_request_resource(dev, res) insert_resource(&iomem_resource, res)
+#define ccio_allocate_resource(dev, res, size, min, max, align) \
+		allocate_resource(&iomem_resource, res, size, min, max, \
+				align, NULL, NULL)
+#endif /* !CONFIG_IOMMU_CCIO */
+
+#ifdef CONFIG_IOMMU_SBA
+struct parisc_device;
+void * sba_get_iommu(struct parisc_device *dev);
+#endif
+
+/* At the moment, we panic on error for IOMMU resource exaustion */
+#define dma_mapping_error(dev, x)	0
+
+#endif
diff --git a/arch/parisc/include/asm/dma.h b/arch/parisc/include/asm/dma.h
new file mode 100644
index 000000000000..31ad0f05af3d
--- /dev/null
+++ b/arch/parisc/include/asm/dma.h
@@ -0,0 +1,186 @@
+/* $Id: dma.h,v 1.2 1999/04/27 00:46:18 deller Exp $
+ * linux/include/asm/dma.h: Defines for using and allocating dma channels.
+ * Written by Hennus Bergman, 1992.
+ * High DMA channel support & info by Hannu Savolainen
+ * and John Boyd, Nov. 1992.
+ * (c) Copyright 2000, Grant Grundler
+ */
+
+#ifndef _ASM_DMA_H
+#define _ASM_DMA_H
+
+#include <asm/io.h>		/* need byte IO */
+#include <asm/system.h>	
+
+#define dma_outb	outb
+#define dma_inb		inb
+
+/*
+** DMA_CHUNK_SIZE is used by the SCSI mid-layer to break up
+** (or rather not merge) DMAs into manageable chunks.
+** On parisc, this is more of the software/tuning constraint
+** rather than the HW. I/O MMU allocation algorithms can be
+** faster with smaller sizes (to some degree).
+*/
+#define DMA_CHUNK_SIZE	(BITS_PER_LONG*PAGE_SIZE)
+
+/* The maximum address that we can perform a DMA transfer to on this platform
+** New dynamic DMA interfaces should obsolete this....
+*/
+#define MAX_DMA_ADDRESS (~0UL)
+
+/*
+** We don't have DMA channels... well V-class does but the
+** Dynamic DMA Mapping interface will support them... right? :^)
+** Note: this is not relevant right now for PA-RISC, but we cannot 
+** leave this as undefined because some things (e.g. sound)
+** won't compile :-(
+*/
+#define MAX_DMA_CHANNELS 8
+#define DMA_MODE_READ	0x44	/* I/O to memory, no autoinit, increment, single mode */
+#define DMA_MODE_WRITE	0x48	/* memory to I/O, no autoinit, increment, single mode */
+#define DMA_MODE_CASCADE 0xC0	/* pass thru DREQ->HRQ, DACK<-HLDA only */
+
+#define DMA_AUTOINIT	0x10
+
+/* 8237 DMA controllers */
+#define IO_DMA1_BASE	0x00	/* 8 bit slave DMA, channels 0..3 */
+#define IO_DMA2_BASE	0xC0	/* 16 bit master DMA, ch 4(=slave input)..7 */
+
+/* DMA controller registers */
+#define DMA1_CMD_REG		0x08	/* command register (w) */
+#define DMA1_STAT_REG		0x08	/* status register (r) */
+#define DMA1_REQ_REG            0x09    /* request register (w) */
+#define DMA1_MASK_REG		0x0A	/* single-channel mask (w) */
+#define DMA1_MODE_REG		0x0B	/* mode register (w) */
+#define DMA1_CLEAR_FF_REG	0x0C	/* clear pointer flip-flop (w) */
+#define DMA1_TEMP_REG           0x0D    /* Temporary Register (r) */
+#define DMA1_RESET_REG		0x0D	/* Master Clear (w) */
+#define DMA1_CLR_MASK_REG       0x0E    /* Clear Mask */
+#define DMA1_MASK_ALL_REG       0x0F    /* all-channels mask (w) */
+#define DMA1_EXT_MODE_REG	(0x400 | DMA1_MODE_REG)
+
+#define DMA2_CMD_REG		0xD0	/* command register (w) */
+#define DMA2_STAT_REG		0xD0	/* status register (r) */
+#define DMA2_REQ_REG            0xD2    /* request register (w) */
+#define DMA2_MASK_REG		0xD4	/* single-channel mask (w) */
+#define DMA2_MODE_REG		0xD6	/* mode register (w) */
+#define DMA2_CLEAR_FF_REG	0xD8	/* clear pointer flip-flop (w) */
+#define DMA2_TEMP_REG           0xDA    /* Temporary Register (r) */
+#define DMA2_RESET_REG		0xDA	/* Master Clear (w) */
+#define DMA2_CLR_MASK_REG       0xDC    /* Clear Mask */
+#define DMA2_MASK_ALL_REG       0xDE    /* all-channels mask (w) */
+#define DMA2_EXT_MODE_REG	(0x400 | DMA2_MODE_REG)
+
+static __inline__ unsigned long claim_dma_lock(void)
+{
+	return 0;
+}
+
+static __inline__ void release_dma_lock(unsigned long flags)
+{
+}
+
+
+/* Get DMA residue count. After a DMA transfer, this
+ * should return zero. Reading this while a DMA transfer is
+ * still in progress will return unpredictable results.
+ * If called before the channel has been used, it may return 1.
+ * Otherwise, it returns the number of _bytes_ left to transfer.
+ *
+ * Assumes DMA flip-flop is clear.
+ */
+static __inline__ int get_dma_residue(unsigned int dmanr)
+{
+	unsigned int io_port = (dmanr<=3)? ((dmanr&3)<<1) + 1 + IO_DMA1_BASE
+					 : ((dmanr&3)<<2) + 2 + IO_DMA2_BASE;
+
+	/* using short to get 16-bit wrap around */
+	unsigned short count;
+
+	count = 1 + dma_inb(io_port);
+	count += dma_inb(io_port) << 8;
+	
+	return (dmanr<=3)? count : (count<<1);
+}
+
+/* enable/disable a specific DMA channel */
+static __inline__ void enable_dma(unsigned int dmanr)
+{
+#ifdef CONFIG_SUPERIO
+	if (dmanr<=3)
+		dma_outb(dmanr,  DMA1_MASK_REG);
+	else
+		dma_outb(dmanr & 3,  DMA2_MASK_REG);
+#endif
+}
+
+static __inline__ void disable_dma(unsigned int dmanr)
+{
+#ifdef CONFIG_SUPERIO
+	if (dmanr<=3)
+		dma_outb(dmanr | 4,  DMA1_MASK_REG);
+	else
+		dma_outb((dmanr & 3) | 4,  DMA2_MASK_REG);
+#endif
+}
+
+/* reserve a DMA channel */
+#define request_dma(dmanr, device_id)	(0)
+
+/* Clear the 'DMA Pointer Flip Flop'.
+ * Write 0 for LSB/MSB, 1 for MSB/LSB access.
+ * Use this once to initialize the FF to a known state.
+ * After that, keep track of it. :-)
+ * --- In order to do that, the DMA routines below should ---
+ * --- only be used while holding the DMA lock ! ---
+ */
+static __inline__ void clear_dma_ff(unsigned int dmanr)
+{
+}
+
+/* set mode (above) for a specific DMA channel */
+static __inline__ void set_dma_mode(unsigned int dmanr, char mode)
+{
+}
+
+/* Set only the page register bits of the transfer address.
+ * This is used for successive transfers when we know the contents of
+ * the lower 16 bits of the DMA current address register, but a 64k boundary
+ * may have been crossed.
+ */
+static __inline__ void set_dma_page(unsigned int dmanr, char pagenr)
+{
+}
+
+
+/* Set transfer address & page bits for specific DMA channel.
+ * Assumes dma flipflop is clear.
+ */
+static __inline__ void set_dma_addr(unsigned int dmanr, unsigned int a)
+{
+}
+
+
+/* Set transfer size (max 64k for DMA1..3, 128k for DMA5..7) for
+ * a specific DMA channel.
+ * You must ensure the parameters are valid.
+ * NOTE: from a manual: "the number of transfers is one more
+ * than the initial word count"! This is taken into account.
+ * Assumes dma flip-flop is clear.
+ * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7.
+ */
+static __inline__ void set_dma_count(unsigned int dmanr, unsigned int count)
+{
+}
+
+
+#define free_dma(dmanr)
+
+#ifdef CONFIG_PCI
+extern int isa_dma_bridge_buggy;
+#else
+#define isa_dma_bridge_buggy 	(0)
+#endif
+
+#endif /* _ASM_DMA_H */
diff --git a/arch/parisc/include/asm/eisa_bus.h b/arch/parisc/include/asm/eisa_bus.h
new file mode 100644
index 000000000000..201085f83dd5
--- /dev/null
+++ b/arch/parisc/include/asm/eisa_bus.h
@@ -0,0 +1,23 @@
+/*
+ * eisa_bus.h interface between the eisa BA driver and the bus enumerator
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Copyright (c) 2002 Daniel Engstrom <5116@telia.com>
+ *
+ */
+
+#ifndef ASM_EISA_H
+#define ASM_EISA_H
+
+extern void eisa_make_irq_level(int num);
+extern void eisa_make_irq_edge(int num);
+extern int eisa_enumerator(unsigned long eeprom_addr,
+			   struct resource *io_parent, 
+			   struct resource *mem_parent);
+extern int eisa_eeprom_init(unsigned long addr);
+
+#endif
diff --git a/arch/parisc/include/asm/eisa_eeprom.h b/arch/parisc/include/asm/eisa_eeprom.h
new file mode 100644
index 000000000000..9c9da980402a
--- /dev/null
+++ b/arch/parisc/include/asm/eisa_eeprom.h
@@ -0,0 +1,153 @@
+/*
+ * eisa_eeprom.h - provide support for EISA adapters in PA-RISC machines
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * Copyright (c) 2001, 2002 Daniel Engstrom <5116@telia.com>
+ *
+ */
+
+#ifndef ASM_EISA_EEPROM_H
+#define ASM_EISA_EEPROM_H
+
+extern void __iomem *eisa_eeprom_addr;
+
+#define HPEE_MAX_LENGTH       0x2000	/* maximum eeprom length */
+
+#define HPEE_SLOT_INFO(slot) (20+(48*slot))
+
+struct eeprom_header 
+{
+   
+	u_int32_t num_writes;       /* number of writes */
+ 	u_int8_t  flags;            /* flags, usage? */
+	u_int8_t  ver_maj;
+	u_int8_t  ver_min;
+	u_int8_t  num_slots;        /* number of EISA slots in system */
+	u_int16_t csum;             /* checksum, I don't know how to calulate this */
+	u_int8_t  pad[10];
+} __attribute__ ((packed));
+
+
+struct eeprom_eisa_slot_info
+{
+	u_int32_t eisa_slot_id;
+	u_int32_t config_data_offset;
+	u_int32_t num_writes;
+	u_int16_t csum;
+	u_int16_t num_functions;
+	u_int16_t config_data_length;
+	
+	/* bits 0..3 are the duplicate slot id */ 
+#define HPEE_SLOT_INFO_EMBEDDED  0x10
+#define HPEE_SLOT_INFO_VIRTUAL   0x20
+#define HPEE_SLOT_INFO_NO_READID 0x40
+#define HPEE_SLOT_INFO_DUPLICATE 0x80
+	u_int8_t slot_info;
+	
+#define HPEE_SLOT_FEATURES_ENABLE         0x01
+#define HPEE_SLOT_FEATURES_IOCHK          0x02
+#define HPEE_SLOT_FEATURES_CFG_INCOMPLETE 0x80
+	u_int8_t slot_features;
+	
+	u_int8_t  ver_min;
+	u_int8_t  ver_maj;
+	
+#define HPEE_FUNCTION_INFO_HAVE_TYPE      0x01
+#define HPEE_FUNCTION_INFO_HAVE_MEMORY    0x02
+#define HPEE_FUNCTION_INFO_HAVE_IRQ       0x04
+#define HPEE_FUNCTION_INFO_HAVE_DMA       0x08
+#define HPEE_FUNCTION_INFO_HAVE_PORT      0x10
+#define HPEE_FUNCTION_INFO_HAVE_PORT_INIT 0x20
+/* I think there are two slighty different 
+ * versions of the function_info field 
+ * one int the fixed header and one optional 
+ * in the parsed slot data area */
+#define HPEE_FUNCTION_INFO_HAVE_FUNCTION  0x01
+#define HPEE_FUNCTION_INFO_F_DISABLED     0x80
+#define HPEE_FUNCTION_INFO_CFG_FREE_FORM  0x40
+	u_int8_t  function_info;
+
+#define HPEE_FLAG_BOARD_IS_ISA		  0x01 /* flag and minor version for isa board */
+	u_int8_t  flags;
+	u_int8_t  pad[24];
+} __attribute__ ((packed));
+
+
+#define HPEE_MEMORY_MAX_ENT   9
+/* memory descriptor: byte 0 */
+#define HPEE_MEMORY_WRITABLE  0x01
+#define HPEE_MEMORY_CACHABLE  0x02
+#define HPEE_MEMORY_TYPE_MASK 0x18
+#define HPEE_MEMORY_TYPE_SYS  0x00
+#define HPEE_MEMORY_TYPE_EXP  0x08
+#define HPEE_MEMORY_TYPE_VIR  0x10
+#define HPEE_MEMORY_TYPE_OTH  0x18
+#define HPEE_MEMORY_SHARED    0x20
+#define HPEE_MEMORY_MORE      0x80
+
+/* memory descriptor: byte 1 */
+#define HPEE_MEMORY_WIDTH_MASK 0x03
+#define HPEE_MEMORY_WIDTH_BYTE 0x00
+#define HPEE_MEMORY_WIDTH_WORD 0x01
+#define HPEE_MEMORY_WIDTH_DWORD 0x02
+#define HPEE_MEMORY_DECODE_MASK 0x0c
+#define HPEE_MEMORY_DECODE_20BITS 0x00
+#define HPEE_MEMORY_DECODE_24BITS 0x04
+#define HPEE_MEMORY_DECODE_32BITS 0x08
+/* byte 2 and 3 are a 16bit LE value
+ * containging the memory size in kilobytes */
+/* byte 4,5,6 are a 24bit LE value
+ * containing the memory base address */
+
+
+#define HPEE_IRQ_MAX_ENT      7
+/* Interrupt entry: byte 0 */
+#define HPEE_IRQ_CHANNEL_MASK 0xf
+#define HPEE_IRQ_TRIG_LEVEL   0x20
+#define HPEE_IRQ_MORE         0x80
+/* byte 1 seems to be unused */
+
+#define HPEE_DMA_MAX_ENT     4
+
+/* dma entry: byte 0 */
+#define HPEE_DMA_CHANNEL_MASK 7
+#define HPEE_DMA_SIZE_MASK	0xc
+#define HPEE_DMA_SIZE_BYTE	0x0
+#define HPEE_DMA_SIZE_WORD	0x4
+#define HPEE_DMA_SIZE_DWORD	0x8
+#define HPEE_DMA_SHARED      0x40
+#define HPEE_DMA_MORE        0x80
+
+/* dma entry: byte 1 */
+#define HPEE_DMA_TIMING_MASK 0x30
+#define HPEE_DMA_TIMING_ISA	0x0
+#define HPEE_DMA_TIMING_TYPEA 0x10
+#define HPEE_DMA_TIMING_TYPEB 0x20
+#define HPEE_DMA_TIMING_TYPEC 0x30
+
+#define HPEE_PORT_MAX_ENT 20
+/* port entry byte 0 */
+#define HPEE_PORT_SIZE_MASK 0x1f
+#define HPEE_PORT_SHARED    0x40
+#define HPEE_PORT_MORE      0x80
+/* byte 1 and 2 is a 16bit LE value
+ * conating the start port number */
+
+#define HPEE_PORT_INIT_MAX_LEN     60 /* in bytes here */
+/* port init entry byte 0 */
+#define HPEE_PORT_INIT_WIDTH_MASK  0x3
+#define HPEE_PORT_INIT_WIDTH_BYTE  0x0
+#define HPEE_PORT_INIT_WIDTH_WORD  0x1
+#define HPEE_PORT_INIT_WIDTH_DWORD 0x2
+#define HPEE_PORT_INIT_MASK        0x4
+#define HPEE_PORT_INIT_MORE        0x80
+
+#define HPEE_SELECTION_MAX_ENT 26
+
+#define HPEE_TYPE_MAX_LEN    80
+
+#endif
diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h
new file mode 100644
index 000000000000..d0a4a8262818
--- /dev/null
+++ b/arch/parisc/include/asm/elf.h
@@ -0,0 +1,342 @@
+#ifndef __ASMPARISC_ELF_H
+#define __ASMPARISC_ELF_H
+
+/*
+ * ELF register definitions..
+ */
+
+#include <asm/ptrace.h>
+
+#define EM_PARISC 15
+
+/* HPPA specific definitions.  */
+
+/* Legal values for e_flags field of Elf32_Ehdr.  */
+
+#define EF_PARISC_TRAPNIL	0x00010000 /* Trap nil pointer dereference.  */
+#define EF_PARISC_EXT		0x00020000 /* Program uses arch. extensions. */
+#define EF_PARISC_LSB		0x00040000 /* Program expects little endian. */
+#define EF_PARISC_WIDE		0x00080000 /* Program expects wide mode.  */
+#define EF_PARISC_NO_KABP	0x00100000 /* No kernel assisted branch
+					      prediction.  */
+#define EF_PARISC_LAZYSWAP	0x00400000 /* Allow lazy swapping.  */
+#define EF_PARISC_ARCH		0x0000ffff /* Architecture version.  */
+
+/* Defined values for `e_flags & EF_PARISC_ARCH' are:  */
+
+#define EFA_PARISC_1_0		    0x020b /* PA-RISC 1.0 big-endian.  */
+#define EFA_PARISC_1_1		    0x0210 /* PA-RISC 1.1 big-endian.  */
+#define EFA_PARISC_2_0		    0x0214 /* PA-RISC 2.0 big-endian.  */
+
+/* Additional section indices.  */
+
+#define SHN_PARISC_ANSI_COMMON	0xff00	   /* Section for tenatively declared
+					      symbols in ANSI C.  */
+#define SHN_PARISC_HUGE_COMMON	0xff01	   /* Common blocks in huge model.  */
+
+/* Legal values for sh_type field of Elf32_Shdr.  */
+
+#define SHT_PARISC_EXT		0x70000000 /* Contains product specific ext. */
+#define SHT_PARISC_UNWIND	0x70000001 /* Unwind information.  */
+#define SHT_PARISC_DOC		0x70000002 /* Debug info for optimized code. */
+
+/* Legal values for sh_flags field of Elf32_Shdr.  */
+
+#define SHF_PARISC_SHORT	0x20000000 /* Section with short addressing. */
+#define SHF_PARISC_HUGE		0x40000000 /* Section far from gp.  */
+#define SHF_PARISC_SBP		0x80000000 /* Static branch prediction code. */
+
+/* Legal values for ST_TYPE subfield of st_info (symbol type).  */
+
+#define STT_PARISC_MILLICODE	13	/* Millicode function entry point.  */
+
+#define STT_HP_OPAQUE		(STT_LOOS + 0x1)
+#define STT_HP_STUB		(STT_LOOS + 0x2)
+
+/* HPPA relocs.  */
+
+#define R_PARISC_NONE		0	/* No reloc.  */
+#define R_PARISC_DIR32		1	/* Direct 32-bit reference.  */
+#define R_PARISC_DIR21L		2	/* Left 21 bits of eff. address.  */
+#define R_PARISC_DIR17R		3	/* Right 17 bits of eff. address.  */
+#define R_PARISC_DIR17F		4	/* 17 bits of eff. address.  */
+#define R_PARISC_DIR14R		6	/* Right 14 bits of eff. address.  */
+#define R_PARISC_PCREL32	9	/* 32-bit rel. address.  */
+#define R_PARISC_PCREL21L	10	/* Left 21 bits of rel. address.  */
+#define R_PARISC_PCREL17R	11	/* Right 17 bits of rel. address.  */
+#define R_PARISC_PCREL17F	12	/* 17 bits of rel. address.  */
+#define R_PARISC_PCREL14R	14	/* Right 14 bits of rel. address.  */
+#define R_PARISC_DPREL21L	18	/* Left 21 bits of rel. address.  */
+#define R_PARISC_DPREL14R	22	/* Right 14 bits of rel. address.  */
+#define R_PARISC_GPREL21L	26	/* GP-relative, left 21 bits.  */
+#define R_PARISC_GPREL14R	30	/* GP-relative, right 14 bits.  */
+#define R_PARISC_LTOFF21L	34	/* LT-relative, left 21 bits.  */
+#define R_PARISC_LTOFF14R	38	/* LT-relative, right 14 bits.  */
+#define R_PARISC_SECREL32	41	/* 32 bits section rel. address.  */
+#define R_PARISC_SEGBASE	48	/* No relocation, set segment base.  */
+#define R_PARISC_SEGREL32	49	/* 32 bits segment rel. address.  */
+#define R_PARISC_PLTOFF21L	50	/* PLT rel. address, left 21 bits.  */
+#define R_PARISC_PLTOFF14R	54	/* PLT rel. address, right 14 bits.  */
+#define R_PARISC_LTOFF_FPTR32	57	/* 32 bits LT-rel. function pointer. */
+#define R_PARISC_LTOFF_FPTR21L	58	/* LT-rel. fct ptr, left 21 bits. */
+#define R_PARISC_LTOFF_FPTR14R	62	/* LT-rel. fct ptr, right 14 bits. */
+#define R_PARISC_FPTR64		64	/* 64 bits function address.  */
+#define R_PARISC_PLABEL32	65	/* 32 bits function address.  */
+#define R_PARISC_PCREL64	72	/* 64 bits PC-rel. address.  */
+#define R_PARISC_PCREL22F	74	/* 22 bits PC-rel. address.  */
+#define R_PARISC_PCREL14WR	75	/* PC-rel. address, right 14 bits.  */
+#define R_PARISC_PCREL14DR	76	/* PC rel. address, right 14 bits.  */
+#define R_PARISC_PCREL16F	77	/* 16 bits PC-rel. address.  */
+#define R_PARISC_PCREL16WF	78	/* 16 bits PC-rel. address.  */
+#define R_PARISC_PCREL16DF	79	/* 16 bits PC-rel. address.  */
+#define R_PARISC_DIR64		80	/* 64 bits of eff. address.  */
+#define R_PARISC_DIR14WR	83	/* 14 bits of eff. address.  */
+#define R_PARISC_DIR14DR	84	/* 14 bits of eff. address.  */
+#define R_PARISC_DIR16F		85	/* 16 bits of eff. address.  */
+#define R_PARISC_DIR16WF	86	/* 16 bits of eff. address.  */
+#define R_PARISC_DIR16DF	87	/* 16 bits of eff. address.  */
+#define R_PARISC_GPREL64	88	/* 64 bits of GP-rel. address.  */
+#define R_PARISC_GPREL14WR	91	/* GP-rel. address, right 14 bits.  */
+#define R_PARISC_GPREL14DR	92	/* GP-rel. address, right 14 bits.  */
+#define R_PARISC_GPREL16F	93	/* 16 bits GP-rel. address.  */
+#define R_PARISC_GPREL16WF	94	/* 16 bits GP-rel. address.  */
+#define R_PARISC_GPREL16DF	95	/* 16 bits GP-rel. address.  */
+#define R_PARISC_LTOFF64	96	/* 64 bits LT-rel. address.  */
+#define R_PARISC_LTOFF14WR	99	/* LT-rel. address, right 14 bits.  */
+#define R_PARISC_LTOFF14DR	100	/* LT-rel. address, right 14 bits.  */
+#define R_PARISC_LTOFF16F	101	/* 16 bits LT-rel. address.  */
+#define R_PARISC_LTOFF16WF	102	/* 16 bits LT-rel. address.  */
+#define R_PARISC_LTOFF16DF	103	/* 16 bits LT-rel. address.  */
+#define R_PARISC_SECREL64	104	/* 64 bits section rel. address.  */
+#define R_PARISC_SEGREL64	112	/* 64 bits segment rel. address.  */
+#define R_PARISC_PLTOFF14WR	115	/* PLT-rel. address, right 14 bits.  */
+#define R_PARISC_PLTOFF14DR	116	/* PLT-rel. address, right 14 bits.  */
+#define R_PARISC_PLTOFF16F	117	/* 16 bits LT-rel. address.  */
+#define R_PARISC_PLTOFF16WF	118	/* 16 bits PLT-rel. address.  */
+#define R_PARISC_PLTOFF16DF	119	/* 16 bits PLT-rel. address.  */
+#define R_PARISC_LTOFF_FPTR64	120	/* 64 bits LT-rel. function ptr.  */
+#define R_PARISC_LTOFF_FPTR14WR	123	/* LT-rel. fct. ptr., right 14 bits. */
+#define R_PARISC_LTOFF_FPTR14DR	124	/* LT-rel. fct. ptr., right 14 bits. */
+#define R_PARISC_LTOFF_FPTR16F	125	/* 16 bits LT-rel. function ptr.  */
+#define R_PARISC_LTOFF_FPTR16WF	126	/* 16 bits LT-rel. function ptr.  */
+#define R_PARISC_LTOFF_FPTR16DF	127	/* 16 bits LT-rel. function ptr.  */
+#define R_PARISC_LORESERVE	128
+#define R_PARISC_COPY		128	/* Copy relocation.  */
+#define R_PARISC_IPLT		129	/* Dynamic reloc, imported PLT */
+#define R_PARISC_EPLT		130	/* Dynamic reloc, exported PLT */
+#define R_PARISC_TPREL32	153	/* 32 bits TP-rel. address.  */
+#define R_PARISC_TPREL21L	154	/* TP-rel. address, left 21 bits.  */
+#define R_PARISC_TPREL14R	158	/* TP-rel. address, right 14 bits.  */
+#define R_PARISC_LTOFF_TP21L	162	/* LT-TP-rel. address, left 21 bits. */
+#define R_PARISC_LTOFF_TP14R	166	/* LT-TP-rel. address, right 14 bits.*/
+#define R_PARISC_LTOFF_TP14F	167	/* 14 bits LT-TP-rel. address.  */
+#define R_PARISC_TPREL64	216	/* 64 bits TP-rel. address.  */
+#define R_PARISC_TPREL14WR	219	/* TP-rel. address, right 14 bits.  */
+#define R_PARISC_TPREL14DR	220	/* TP-rel. address, right 14 bits.  */
+#define R_PARISC_TPREL16F	221	/* 16 bits TP-rel. address.  */
+#define R_PARISC_TPREL16WF	222	/* 16 bits TP-rel. address.  */
+#define R_PARISC_TPREL16DF	223	/* 16 bits TP-rel. address.  */
+#define R_PARISC_LTOFF_TP64	224	/* 64 bits LT-TP-rel. address.  */
+#define R_PARISC_LTOFF_TP14WR	227	/* LT-TP-rel. address, right 14 bits.*/
+#define R_PARISC_LTOFF_TP14DR	228	/* LT-TP-rel. address, right 14 bits.*/
+#define R_PARISC_LTOFF_TP16F	229	/* 16 bits LT-TP-rel. address.  */
+#define R_PARISC_LTOFF_TP16WF	230	/* 16 bits LT-TP-rel. address.  */
+#define R_PARISC_LTOFF_TP16DF	231	/* 16 bits LT-TP-rel. address.  */
+#define R_PARISC_HIRESERVE	255
+
+#define PA_PLABEL_FDESC		0x02	/* bit set if PLABEL points to
+					 * a function descriptor, not
+					 * an address */
+
+/* The following are PA function descriptors 
+ *
+ * addr:	the absolute address of the function
+ * gp:		either the data pointer (r27) for non-PIC code or the
+ *		the PLT pointer (r19) for PIC code */
+
+/* Format for the Elf32 Function descriptor */
+typedef struct elf32_fdesc {
+	__u32	addr;
+	__u32	gp;
+} Elf32_Fdesc;
+
+/* Format for the Elf64 Function descriptor */
+typedef struct elf64_fdesc {
+	__u64	dummy[2]; /* FIXME: nothing uses these, why waste
+			   * the space */
+	__u64	addr;
+	__u64	gp;
+} Elf64_Fdesc;
+
+/* Legal values for p_type field of Elf32_Phdr/Elf64_Phdr.  */
+
+#define PT_HP_TLS		(PT_LOOS + 0x0)
+#define PT_HP_CORE_NONE		(PT_LOOS + 0x1)
+#define PT_HP_CORE_VERSION	(PT_LOOS + 0x2)
+#define PT_HP_CORE_KERNEL	(PT_LOOS + 0x3)
+#define PT_HP_CORE_COMM		(PT_LOOS + 0x4)
+#define PT_HP_CORE_PROC		(PT_LOOS + 0x5)
+#define PT_HP_CORE_LOADABLE	(PT_LOOS + 0x6)
+#define PT_HP_CORE_STACK	(PT_LOOS + 0x7)
+#define PT_HP_CORE_SHM		(PT_LOOS + 0x8)
+#define PT_HP_CORE_MMF		(PT_LOOS + 0x9)
+#define PT_HP_PARALLEL		(PT_LOOS + 0x10)
+#define PT_HP_FASTBIND		(PT_LOOS + 0x11)
+#define PT_HP_OPT_ANNOT		(PT_LOOS + 0x12)
+#define PT_HP_HSL_ANNOT		(PT_LOOS + 0x13)
+#define PT_HP_STACK		(PT_LOOS + 0x14)
+
+#define PT_PARISC_ARCHEXT	0x70000000
+#define PT_PARISC_UNWIND	0x70000001
+
+/* Legal values for p_flags field of Elf32_Phdr/Elf64_Phdr.  */
+
+#define PF_PARISC_SBP		0x08000000
+
+#define PF_HP_PAGE_SIZE		0x00100000
+#define PF_HP_FAR_SHARED	0x00200000
+#define PF_HP_NEAR_SHARED	0x00400000
+#define PF_HP_CODE		0x01000000
+#define PF_HP_MODIFY		0x02000000
+#define PF_HP_LAZYSWAP		0x04000000
+#define PF_HP_SBP		0x08000000
+
+/*
+ * The following definitions are those for 32-bit ELF binaries on a 32-bit
+ * kernel and for 64-bit binaries on a 64-bit kernel.  To run 32-bit binaries
+ * on a 64-bit kernel, arch/parisc/kernel/binfmt_elf32.c defines these
+ * macros appropriately and then #includes binfmt_elf.c, which then includes
+ * this file.
+ */
+#ifndef ELF_CLASS
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ *
+ * Note that this header file is used by default in fs/binfmt_elf.c. So
+ * the following macros are for the default case. However, for the 64
+ * bit kernel we also support 32 bit parisc binaries. To do that
+ * arch/parisc/kernel/binfmt_elf32.c defines its own set of these
+ * macros, and then it includes fs/binfmt_elf.c to provide an alternate
+ * elf binary handler for 32 bit binaries (on the 64 bit kernel).
+ */
+#ifdef CONFIG_64BIT
+#define ELF_CLASS   ELFCLASS64
+#else
+#define ELF_CLASS	ELFCLASS32
+#endif
+
+typedef unsigned long elf_greg_t;
+
+/*
+ * This yields a string that ld.so will use to load implementation
+ * specific libraries for optimization.  This is more specific in
+ * intent than poking at uname or /proc/cpuinfo.
+ */
+
+#define ELF_PLATFORM  ("PARISC\0")
+
+#define SET_PERSONALITY(ex, ibcs2) \
+	current->personality = PER_LINUX; \
+	current->thread.map_base = DEFAULT_MAP_BASE; \
+	current->thread.task_size = DEFAULT_TASK_SIZE \
+
+/*
+ * Fill in general registers in a core dump.  This saves pretty
+ * much the same registers as hp-ux, although in a different order.
+ * Registers marked # below are not currently saved in pt_regs, so
+ * we use their current values here.
+ *
+ * 	gr0..gr31
+ * 	sr0..sr7
+ * 	iaoq0..iaoq1
+ * 	iasq0..iasq1
+ * 	cr11 (sar)
+ * 	cr19 (iir)
+ * 	cr20 (isr)
+ * 	cr21 (ior)
+ *  #	cr22 (ipsw)
+ *  #	cr0 (recovery counter)
+ *  #	cr24..cr31 (temporary registers)
+ *  #	cr8,9,12,13 (protection IDs)
+ *  #	cr10 (scr/ccr)
+ *  #	cr15 (ext int enable mask)
+ *
+ */
+
+#define ELF_CORE_COPY_REGS(dst, pt)	\
+	memset(dst, 0, sizeof(dst));	/* don't leak any "random" bits */ \
+	memcpy(dst + 0, pt->gr, 32 * sizeof(elf_greg_t)); \
+	memcpy(dst + 32, pt->sr, 8 * sizeof(elf_greg_t)); \
+	memcpy(dst + 40, pt->iaoq, 2 * sizeof(elf_greg_t)); \
+	memcpy(dst + 42, pt->iasq, 2 * sizeof(elf_greg_t)); \
+	dst[44] = pt->sar;   dst[45] = pt->iir; \
+	dst[46] = pt->isr;   dst[47] = pt->ior; \
+	dst[48] = mfctl(22); dst[49] = mfctl(0); \
+	dst[50] = mfctl(24); dst[51] = mfctl(25); \
+	dst[52] = mfctl(26); dst[53] = mfctl(27); \
+	dst[54] = mfctl(28); dst[55] = mfctl(29); \
+	dst[56] = mfctl(30); dst[57] = mfctl(31); \
+	dst[58] = mfctl( 8); dst[59] = mfctl( 9); \
+	dst[60] = mfctl(12); dst[61] = mfctl(13); \
+	dst[62] = mfctl(10); dst[63] = mfctl(15);
+
+#endif /* ! ELF_CLASS */
+
+#define ELF_NGREG 80	/* We only need 64 at present, but leave space
+			   for expansion. */
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+#define ELF_NFPREG 32
+typedef double elf_fpreg_t;
+typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
+
+struct task_struct;
+
+extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
+#define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
+
+struct pt_regs;	/* forward declaration... */
+
+
+#define elf_check_arch(x) ((x)->e_machine == EM_PARISC && (x)->e_ident[EI_CLASS] == ELF_CLASS)
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_DATA	ELFDATA2MSB
+#define ELF_ARCH	EM_PARISC
+#define ELF_OSABI 	ELFOSABI_LINUX
+
+/* %r23 is set by ld.so to a pointer to a function which might be 
+   registered using atexit.  This provides a means for the dynamic
+   linker to call DT_FINI functions for shared libraries that have
+   been loaded before the code runs.
+
+   So that we can use the same startup file with static executables,
+   we start programs with a value of 0 to indicate that there is no
+   such function.  */
+#define ELF_PLAT_INIT(_r, load_addr)       _r->gr[23] = 0
+
+#define USE_ELF_CORE_DUMP
+#define ELF_EXEC_PAGESIZE	4096
+
+/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
+   use of this is to invoke "./ld.so someprog" to test out a new version of
+   the loader.  We need to make sure that it is out of the way of the program
+   that it will "exec", and that there is sufficient room for the brk.
+
+   (2 * TASK_SIZE / 3) turns into something undefined when run through a
+   32 bit preprocessor and in some cases results in the kernel trying to map
+   ld.so to the kernel virtual base. Use a sane value instead. /Jes 
+  */
+
+#define ELF_ET_DYN_BASE         (TASK_UNMAPPED_BASE + 0x01000000)
+
+/* This yields a mask that user programs can use to figure out what
+   instruction set this CPU supports.  This could be done in user space,
+   but it's not easy, and we've already done it here.  */
+
+#define ELF_HWCAP	0
+
+#endif
diff --git a/arch/parisc/include/asm/emergency-restart.h b/arch/parisc/include/asm/emergency-restart.h
new file mode 100644
index 000000000000..108d8c48e42e
--- /dev/null
+++ b/arch/parisc/include/asm/emergency-restart.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_EMERGENCY_RESTART_H
+#define _ASM_EMERGENCY_RESTART_H
+
+#include <asm-generic/emergency-restart.h>
+
+#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/arch/parisc/include/asm/errno.h b/arch/parisc/include/asm/errno.h
new file mode 100644
index 000000000000..e2f3ddc796be
--- /dev/null
+++ b/arch/parisc/include/asm/errno.h
@@ -0,0 +1,124 @@
+#ifndef _PARISC_ERRNO_H
+#define _PARISC_ERRNO_H
+
+#include <asm-generic/errno-base.h>
+
+#define	ENOMSG		35	/* No message of desired type */
+#define	EIDRM		36	/* Identifier removed */
+#define	ECHRNG		37	/* Channel number out of range */
+#define	EL2NSYNC	38	/* Level 2 not synchronized */
+#define	EL3HLT		39	/* Level 3 halted */
+#define	EL3RST		40	/* Level 3 reset */
+#define	ELNRNG		41	/* Link number out of range */
+#define	EUNATCH		42	/* Protocol driver not attached */
+#define	ENOCSI		43	/* No CSI structure available */
+#define	EL2HLT		44	/* Level 2 halted */
+#define	EDEADLK		45	/* Resource deadlock would occur */
+#define	EDEADLOCK	EDEADLK
+#define	ENOLCK		46	/* No record locks available */
+#define	EILSEQ		47	/* Illegal byte sequence */
+
+#define	ENONET		50	/* Machine is not on the network */
+#define	ENODATA		51	/* No data available */
+#define	ETIME		52	/* Timer expired */
+#define	ENOSR		53	/* Out of streams resources */
+#define	ENOSTR		54	/* Device not a stream */
+#define	ENOPKG		55	/* Package not installed */
+
+#define	ENOLINK		57	/* Link has been severed */
+#define	EADV		58	/* Advertise error */
+#define	ESRMNT		59	/* Srmount error */
+#define	ECOMM		60	/* Communication error on send */
+#define	EPROTO		61	/* Protocol error */
+
+#define	EMULTIHOP	64	/* Multihop attempted */
+
+#define	EDOTDOT		66	/* RFS specific error */
+#define	EBADMSG		67	/* Not a data message */
+#define	EUSERS		68	/* Too many users */
+#define	EDQUOT		69	/* Quota exceeded */
+#define	ESTALE		70	/* Stale NFS file handle */
+#define	EREMOTE		71	/* Object is remote */
+#define	EOVERFLOW	72	/* Value too large for defined data type */
+
+/* these errnos are defined by Linux but not HPUX. */
+
+#define	EBADE		160	/* Invalid exchange */
+#define	EBADR		161	/* Invalid request descriptor */
+#define	EXFULL		162	/* Exchange full */
+#define	ENOANO		163	/* No anode */
+#define	EBADRQC		164	/* Invalid request code */
+#define	EBADSLT		165	/* Invalid slot */
+#define	EBFONT		166	/* Bad font file format */
+#define	ENOTUNIQ	167	/* Name not unique on network */
+#define	EBADFD		168	/* File descriptor in bad state */
+#define	EREMCHG		169	/* Remote address changed */
+#define	ELIBACC		170	/* Can not access a needed shared library */
+#define	ELIBBAD		171	/* Accessing a corrupted shared library */
+#define	ELIBSCN		172	/* .lib section in a.out corrupted */
+#define	ELIBMAX		173	/* Attempting to link in too many shared libraries */
+#define	ELIBEXEC	174	/* Cannot exec a shared library directly */
+#define	ERESTART	175	/* Interrupted system call should be restarted */
+#define	ESTRPIPE	176	/* Streams pipe error */
+#define	EUCLEAN		177	/* Structure needs cleaning */
+#define	ENOTNAM		178	/* Not a XENIX named type file */
+#define	ENAVAIL		179	/* No XENIX semaphores available */
+#define	EISNAM		180	/* Is a named type file */
+#define	EREMOTEIO	181	/* Remote I/O error */
+#define	ENOMEDIUM	182	/* No medium found */
+#define	EMEDIUMTYPE	183	/* Wrong medium type */
+#define	ENOKEY		184	/* Required key not available */
+#define	EKEYEXPIRED	185	/* Key has expired */
+#define	EKEYREVOKED	186	/* Key has been revoked */
+#define	EKEYREJECTED	187	/* Key was rejected by service */
+
+/* We now return you to your regularly scheduled HPUX. */
+
+#define ENOSYM		215	/* symbol does not exist in executable */
+#define	ENOTSOCK	216	/* Socket operation on non-socket */
+#define	EDESTADDRREQ	217	/* Destination address required */
+#define	EMSGSIZE	218	/* Message too long */
+#define	EPROTOTYPE	219	/* Protocol wrong type for socket */
+#define	ENOPROTOOPT	220	/* Protocol not available */
+#define	EPROTONOSUPPORT	221	/* Protocol not supported */
+#define	ESOCKTNOSUPPORT	222	/* Socket type not supported */
+#define	EOPNOTSUPP	223	/* Operation not supported on transport endpoint */
+#define	EPFNOSUPPORT	224	/* Protocol family not supported */
+#define	EAFNOSUPPORT	225	/* Address family not supported by protocol */
+#define	EADDRINUSE	226	/* Address already in use */
+#define	EADDRNOTAVAIL	227	/* Cannot assign requested address */
+#define	ENETDOWN	228	/* Network is down */
+#define	ENETUNREACH	229	/* Network is unreachable */
+#define	ENETRESET	230	/* Network dropped connection because of reset */
+#define	ECONNABORTED	231	/* Software caused connection abort */
+#define	ECONNRESET	232	/* Connection reset by peer */
+#define	ENOBUFS		233	/* No buffer space available */
+#define	EISCONN		234	/* Transport endpoint is already connected */
+#define	ENOTCONN	235	/* Transport endpoint is not connected */
+#define	ESHUTDOWN	236	/* Cannot send after transport endpoint shutdown */
+#define	ETOOMANYREFS	237	/* Too many references: cannot splice */
+#define EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
+#define	ETIMEDOUT	238	/* Connection timed out */
+#define	ECONNREFUSED	239	/* Connection refused */
+#define EREMOTERELEASE	240	/* Remote peer released connection */
+#define	EHOSTDOWN	241	/* Host is down */
+#define	EHOSTUNREACH	242	/* No route to host */
+
+#define	EALREADY	244	/* Operation already in progress */
+#define	EINPROGRESS	245	/* Operation now in progress */
+#define	EWOULDBLOCK	246	/* Operation would block (Linux returns EAGAIN) */
+#define	ENOTEMPTY	247	/* Directory not empty */
+#define	ENAMETOOLONG	248	/* File name too long */
+#define	ELOOP		249	/* Too many symbolic links encountered */
+#define	ENOSYS		251	/* Function not implemented */
+
+#define ENOTSUP		252	/* Function not implemented (POSIX.4 / HPUX) */
+#define ECANCELLED	253	/* aio request was canceled before complete (POSIX.4 / HPUX) */
+#define ECANCELED	ECANCELLED	/* SuSv3 and Solaris wants one 'L' */
+
+/* for robust mutexes */
+#define EOWNERDEAD	254	/* Owner died */
+#define ENOTRECOVERABLE	255	/* State not recoverable */
+
+
+#endif
diff --git a/arch/parisc/include/asm/fb.h b/arch/parisc/include/asm/fb.h
new file mode 100644
index 000000000000..4d503a023ab2
--- /dev/null
+++ b/arch/parisc/include/asm/fb.h
@@ -0,0 +1,19 @@
+#ifndef _ASM_FB_H_
+#define _ASM_FB_H_
+
+#include <linux/fb.h>
+#include <linux/fs.h>
+#include <asm/page.h>
+
+static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
+				unsigned long off)
+{
+	pgprot_val(vma->vm_page_prot) |= _PAGE_NO_CACHE;
+}
+
+static inline int fb_is_primary_device(struct fb_info *info)
+{
+	return 0;
+}
+
+#endif /* _ASM_FB_H_ */
diff --git a/arch/parisc/include/asm/fcntl.h b/arch/parisc/include/asm/fcntl.h
new file mode 100644
index 000000000000..1e1c824764ee
--- /dev/null
+++ b/arch/parisc/include/asm/fcntl.h
@@ -0,0 +1,39 @@
+#ifndef _PARISC_FCNTL_H
+#define _PARISC_FCNTL_H
+
+/* open/fcntl - O_SYNC is only implemented on blocks devices and on files
+   located on an ext2 file system */
+#define O_APPEND	000000010
+#define O_BLKSEEK	000000100 /* HPUX only */
+#define O_CREAT		000000400 /* not fcntl */
+#define O_EXCL		000002000 /* not fcntl */
+#define O_LARGEFILE	000004000
+#define O_SYNC		000100000
+#define O_NONBLOCK	000200004 /* HPUX has separate NDELAY & NONBLOCK */
+#define O_NOCTTY	000400000 /* not fcntl */
+#define O_DSYNC		001000000 /* HPUX only */
+#define O_RSYNC		002000000 /* HPUX only */
+#define O_NOATIME	004000000
+#define O_CLOEXEC	010000000 /* set close_on_exec */
+
+#define O_DIRECTORY	000010000 /* must be a directory */
+#define O_NOFOLLOW	000000200 /* don't follow links */
+#define O_INVISIBLE	004000000 /* invisible I/O, for DMAPI/XDSM */
+
+#define F_GETLK64	8
+#define F_SETLK64	9
+#define F_SETLKW64	10
+
+#define F_GETOWN	11	/*  for sockets. */
+#define F_SETOWN	12	/*  for sockets. */
+#define F_SETSIG	13	/*  for sockets. */
+#define F_GETSIG	14	/*  for sockets. */
+
+/* for posix fcntl() and lockf() */
+#define F_RDLCK		01
+#define F_WRLCK		02
+#define F_UNLCK		03
+
+#include <asm-generic/fcntl.h>
+
+#endif
diff --git a/arch/parisc/include/asm/fixmap.h b/arch/parisc/include/asm/fixmap.h
new file mode 100644
index 000000000000..de3fe3a18229
--- /dev/null
+++ b/arch/parisc/include/asm/fixmap.h
@@ -0,0 +1,30 @@
+#ifndef _ASM_FIXMAP_H
+#define _ASM_FIXMAP_H
+
+/*
+ * This file defines the locations of the fixed mappings on parisc.
+ *
+ * All of the values in this file are machine virtual addresses.
+ *
+ * All of the values in this file must be <4GB (because of assembly
+ * loading restrictions).  If you place this region anywhere above
+ * __PAGE_OFFSET, you must adjust the memory map accordingly */
+
+/* The alias region is used in kernel space to do copy/clear to or
+ * from areas congruently mapped with user space.  It is 8MB large
+ * and must be 16MB aligned */
+#define TMPALIAS_MAP_START	((__PAGE_OFFSET) - 16*1024*1024)
+/* This is the kernel area for all maps (vmalloc, dma etc.)  most
+ * usually, it extends up to TMPALIAS_MAP_START.  Virtual addresses
+ * 0..GATEWAY_PAGE_SIZE are reserved for the gateway page */
+#define KERNEL_MAP_START	(GATEWAY_PAGE_SIZE)
+#define KERNEL_MAP_END		(TMPALIAS_MAP_START)
+
+#ifndef __ASSEMBLY__
+extern void *vmalloc_start;
+#define PCXL_DMA_MAP_SIZE	(8*1024*1024)
+#define VMALLOC_START		((unsigned long)vmalloc_start)
+#define VMALLOC_END		(KERNEL_MAP_END)
+#endif /*__ASSEMBLY__*/
+
+#endif /*_ASM_FIXMAP_H*/
diff --git a/arch/parisc/include/asm/floppy.h b/arch/parisc/include/asm/floppy.h
new file mode 100644
index 000000000000..4ca69f558fae
--- /dev/null
+++ b/arch/parisc/include/asm/floppy.h
@@ -0,0 +1,271 @@
+/*    Architecture specific parts of the Floppy driver
+ *
+ *    Linux/PA-RISC Project (http://www.parisc-linux.org/)
+ *    Copyright (C) 2000 Matthew Wilcox (willy a debian . org)
+ *    Copyright (C) 2000 Dave Kennedy
+ *
+ *    This program is free software; you can redistribute it and/or modify
+ *    it under the terms of the GNU General Public License as published by
+ *    the Free Software Foundation; either version 2 of the License, or
+ *    (at your option) any later version.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU General Public License for more details.
+ *
+ *    You should have received a copy of the GNU General Public License
+ *    along with this program; if not, write to the Free Software
+ *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+#ifndef __ASM_PARISC_FLOPPY_H
+#define __ASM_PARISC_FLOPPY_H
+
+#include <linux/vmalloc.h>
+
+
+/*
+ * The DMA channel used by the floppy controller cannot access data at
+ * addresses >= 16MB
+ *
+ * Went back to the 1MB limit, as some people had problems with the floppy
+ * driver otherwise. It doesn't matter much for performance anyway, as most
+ * floppy accesses go through the track buffer.
+ */
+#define _CROSS_64KB(a,s,vdma) \
+(!vdma && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
+
+#define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
+
+
+#define SW fd_routine[use_virtual_dma&1]
+#define CSW fd_routine[can_use_virtual_dma & 1]
+
+
+#define fd_inb(port)			readb(port)
+#define fd_outb(value, port)		writeb(value, port)
+
+#define fd_request_dma()        CSW._request_dma(FLOPPY_DMA,"floppy")
+#define fd_free_dma()           CSW._free_dma(FLOPPY_DMA)
+#define fd_enable_irq()         enable_irq(FLOPPY_IRQ)
+#define fd_disable_irq()        disable_irq(FLOPPY_IRQ)
+#define fd_free_irq()		free_irq(FLOPPY_IRQ, NULL)
+#define fd_get_dma_residue()    SW._get_dma_residue(FLOPPY_DMA)
+#define fd_dma_mem_alloc(size)	SW._dma_mem_alloc(size)
+#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
+
+#define FLOPPY_CAN_FALLBACK_ON_NODMA
+
+static int virtual_dma_count=0;
+static int virtual_dma_residue=0;
+static char *virtual_dma_addr=0;
+static int virtual_dma_mode=0;
+static int doing_pdma=0;
+
+static void floppy_hardint(int irq, void *dev_id, struct pt_regs * regs)
+{
+	register unsigned char st;
+
+#undef TRACE_FLPY_INT
+
+#ifdef TRACE_FLPY_INT
+	static int calls=0;
+	static int bytes=0;
+	static int dma_wait=0;
+#endif
+	if (!doing_pdma) {
+		floppy_interrupt(irq, dev_id, regs);
+		return;
+	}
+
+#ifdef TRACE_FLPY_INT
+	if(!calls)
+		bytes = virtual_dma_count;
+#endif
+
+	{
+		register int lcount;
+		register char *lptr = virtual_dma_addr;
+
+		for (lcount = virtual_dma_count; lcount; lcount--) {
+			st = fd_inb(virtual_dma_port+4) & 0xa0 ;
+			if (st != 0xa0) 
+				break;
+			if (virtual_dma_mode) {
+				fd_outb(*lptr, virtual_dma_port+5);
+			} else {
+				*lptr = fd_inb(virtual_dma_port+5);
+			}
+			lptr++;
+		}
+		virtual_dma_count = lcount;
+		virtual_dma_addr = lptr;
+		st = fd_inb(virtual_dma_port+4);
+	}
+
+#ifdef TRACE_FLPY_INT
+	calls++;
+#endif
+	if (st == 0x20)
+		return;
+	if (!(st & 0x20)) {
+		virtual_dma_residue += virtual_dma_count;
+		virtual_dma_count = 0;
+#ifdef TRACE_FLPY_INT
+		printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", 
+		       virtual_dma_count, virtual_dma_residue, calls, bytes,
+		       dma_wait);
+		calls = 0;
+		dma_wait=0;
+#endif
+		doing_pdma = 0;
+		floppy_interrupt(irq, dev_id, regs);
+		return;
+	}
+#ifdef TRACE_FLPY_INT
+	if (!virtual_dma_count)
+		dma_wait++;
+#endif
+}
+
+static void fd_disable_dma(void)
+{
+	if(! (can_use_virtual_dma & 1))
+		disable_dma(FLOPPY_DMA);
+	doing_pdma = 0;
+	virtual_dma_residue += virtual_dma_count;
+	virtual_dma_count=0;
+}
+
+static int vdma_request_dma(unsigned int dmanr, const char * device_id)
+{
+	return 0;
+}
+
+static void vdma_nop(unsigned int dummy)
+{
+}
+
+
+static int vdma_get_dma_residue(unsigned int dummy)
+{
+	return virtual_dma_count + virtual_dma_residue;
+}
+
+
+static int fd_request_irq(void)
+{
+	if(can_use_virtual_dma)
+		return request_irq(FLOPPY_IRQ, floppy_hardint,
+				   IRQF_DISABLED, "floppy", NULL);
+	else
+		return request_irq(FLOPPY_IRQ, floppy_interrupt,
+				   IRQF_DISABLED, "floppy", NULL);
+}
+
+static unsigned long dma_mem_alloc(unsigned long size)
+{
+	return __get_dma_pages(GFP_KERNEL, get_order(size));
+}
+
+
+static unsigned long vdma_mem_alloc(unsigned long size)
+{
+	return (unsigned long) vmalloc(size);
+
+}
+
+#define nodma_mem_alloc(size) vdma_mem_alloc(size)
+
+static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
+{
+	if((unsigned int) addr >= (unsigned int) high_memory)
+		return vfree((void *)addr);
+	else
+		free_pages(addr, get_order(size));		
+}
+
+#define fd_dma_mem_free(addr, size)  _fd_dma_mem_free(addr, size) 
+
+static void _fd_chose_dma_mode(char *addr, unsigned long size)
+{
+	if(can_use_virtual_dma == 2) {
+		if((unsigned int) addr >= (unsigned int) high_memory ||
+		   virt_to_bus(addr) >= 0x1000000 ||
+		   _CROSS_64KB(addr, size, 0))
+			use_virtual_dma = 1;
+		else
+			use_virtual_dma = 0;
+	} else {
+		use_virtual_dma = can_use_virtual_dma & 1;
+	}
+}
+
+#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
+
+
+static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+	doing_pdma = 1;
+	virtual_dma_port = io;
+	virtual_dma_mode = (mode  == DMA_MODE_WRITE);
+	virtual_dma_addr = addr;
+	virtual_dma_count = size;
+	virtual_dma_residue = 0;
+	return 0;
+}
+
+static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+#ifdef FLOPPY_SANITY_CHECK
+	if (CROSS_64KB(addr, size)) {
+		printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
+		return -1;
+	}
+#endif
+	/* actual, physical DMA */
+	doing_pdma = 0;
+	clear_dma_ff(FLOPPY_DMA);
+	set_dma_mode(FLOPPY_DMA,mode);
+	set_dma_addr(FLOPPY_DMA,virt_to_bus(addr));
+	set_dma_count(FLOPPY_DMA,size);
+	enable_dma(FLOPPY_DMA);
+	return 0;
+}
+
+static struct fd_routine_l {
+	int (*_request_dma)(unsigned int dmanr, const char * device_id);
+	void (*_free_dma)(unsigned int dmanr);
+	int (*_get_dma_residue)(unsigned int dummy);
+	unsigned long (*_dma_mem_alloc) (unsigned long size);
+	int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
+} fd_routine[] = {
+	{
+		request_dma,
+		free_dma,
+		get_dma_residue,
+		dma_mem_alloc,
+		hard_dma_setup
+	},
+	{
+		vdma_request_dma,
+		vdma_nop,
+		vdma_get_dma_residue,
+		vdma_mem_alloc,
+		vdma_dma_setup
+	}
+};
+
+
+static int FDC1 = 0x3f0; /* Lies.  Floppy controller is memory mapped, not io mapped */
+static int FDC2 = -1;
+
+#define FLOPPY0_TYPE	0
+#define FLOPPY1_TYPE	0
+
+#define N_FDC 1
+#define N_DRIVE 8
+
+#define EXTRA_FLOPPY_PARAMS
+
+#endif /* __ASM_PARISC_FLOPPY_H */
diff --git a/arch/parisc/include/asm/futex.h b/arch/parisc/include/asm/futex.h
new file mode 100644
index 000000000000..0c705c3a55ef
--- /dev/null
+++ b/arch/parisc/include/asm/futex.h
@@ -0,0 +1,77 @@
+#ifndef _ASM_PARISC_FUTEX_H
+#define _ASM_PARISC_FUTEX_H
+
+#ifdef __KERNEL__
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+#include <asm/errno.h>
+
+static inline int
+futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+{
+	int op = (encoded_op >> 28) & 7;
+	int cmp = (encoded_op >> 24) & 15;
+	int oparg = (encoded_op << 8) >> 20;
+	int cmparg = (encoded_op << 20) >> 20;
+	int oldval = 0, ret;
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
+		return -EFAULT;
+
+	pagefault_disable();
+
+	switch (op) {
+	case FUTEX_OP_SET:
+	case FUTEX_OP_ADD:
+	case FUTEX_OP_OR:
+	case FUTEX_OP_ANDN:
+	case FUTEX_OP_XOR:
+	default:
+		ret = -ENOSYS;
+	}
+
+	pagefault_enable();
+
+	if (!ret) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
+		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
+		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
+		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
+		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
+		default: ret = -ENOSYS;
+		}
+	}
+	return ret;
+}
+
+/* Non-atomic version */
+static inline int
+futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+{
+	int err = 0;
+	int uval;
+
+	/* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is
+	 * our gateway page, and causes no end of trouble...
+	 */
+	if (segment_eq(KERNEL_DS, get_fs()) && !uaddr)
+		return -EFAULT;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+		return -EFAULT;
+
+	err = get_user(uval, uaddr);
+	if (err) return -EFAULT;
+	if (uval == oldval)
+		err = put_user(newval, uaddr);
+	if (err) return -EFAULT;
+	return uval;
+}
+
+#endif /*__KERNEL__*/
+#endif /*_ASM_PARISC_FUTEX_H*/
diff --git a/arch/parisc/include/asm/grfioctl.h b/arch/parisc/include/asm/grfioctl.h
new file mode 100644
index 000000000000..671e06042b40
--- /dev/null
+++ b/arch/parisc/include/asm/grfioctl.h
@@ -0,0 +1,113 @@
+/*  Architecture specific parts of HP's STI (framebuffer) driver.
+ *  Structures are HP-UX compatible for XFree86 usage.
+ * 
+ *    Linux/PA-RISC Project (http://www.parisc-linux.org/)
+ *    Copyright (C) 2001 Helge Deller (deller a parisc-linux org)
+ *
+ *    This program is free software; you can redistribute it and/or modify
+ *    it under the terms of the GNU General Public License as published by
+ *    the Free Software Foundation; either version 2 of the License, or
+ *    (at your option) any later version.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU General Public License for more details.
+ *
+ *    You should have received a copy of the GNU General Public License
+ *    along with this program; if not, write to the Free Software
+ *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+#ifndef __ASM_PARISC_GRFIOCTL_H
+#define __ASM_PARISC_GRFIOCTL_H
+
+/* upper 32 bits of graphics id (HP/UX identifier) */
+
+#define GRFGATOR		8
+#define S9000_ID_S300		9
+#define GRFBOBCAT		9
+#define	GRFCATSEYE		9
+#define S9000_ID_98720		10
+#define GRFRBOX			10
+#define S9000_ID_98550		11
+#define GRFFIREEYE		11
+#define S9000_ID_A1096A		12
+#define GRFHYPERION		12
+#define S9000_ID_FRI		13
+#define S9000_ID_98730		14
+#define GRFDAVINCI		14
+#define S9000_ID_98705		0x26C08070	/* Tigershark */
+#define S9000_ID_98736		0x26D148AB
+#define S9000_ID_A1659A		0x26D1482A	/* CRX 8 plane color (=ELK) */
+#define S9000_ID_ELK		S9000_ID_A1659A
+#define S9000_ID_A1439A		0x26D148EE	/* CRX24 = CRX+ (24-plane color) */
+#define S9000_ID_A1924A		0x26D1488C	/* GRX gray-scale */
+#define S9000_ID_ELM		S9000_ID_A1924A
+#define S9000_ID_98765		0x27480DEF
+#define S9000_ID_ELK_768	0x27482101
+#define S9000_ID_STINGER	0x27A4A402
+#define S9000_ID_TIMBER		0x27F12392	/* Bushmaster (710) Graphics */
+#define S9000_ID_TOMCAT		0x27FCCB6D	/* dual-headed ELK (Dual CRX) */
+#define S9000_ID_ARTIST		0x2B4DED6D	/* Artist (Gecko/712 & 715) onboard Graphics */
+#define S9000_ID_HCRX		0x2BCB015A	/* Hyperdrive/Hyperbowl (A4071A) Graphics */
+#define CRX24_OVERLAY_PLANES	0x920825AA	/* Overlay planes on CRX24 */
+
+#define CRT_ID_ELK_1024		S9000_ID_ELK_768 /* Elk 1024x768  CRX */
+#define CRT_ID_ELK_1280		S9000_ID_A1659A	/* Elk 1280x1024 CRX */
+#define CRT_ID_ELK_1024DB	0x27849CA5      /* Elk 1024x768 double buffer */
+#define CRT_ID_ELK_GS		S9000_ID_A1924A	/* Elk 1280x1024 GreyScale    */
+#define CRT_ID_CRX24		S9000_ID_A1439A	/* Piranha */
+#define CRT_ID_VISUALIZE_EG	0x2D08C0A7      /* Graffiti, A4450A (built-in B132+/B160L) */
+#define CRT_ID_THUNDER		0x2F23E5FC      /* Thunder 1 VISUALIZE 48*/
+#define CRT_ID_THUNDER2		0x2F8D570E      /* Thunder 2 VISUALIZE 48 XP*/
+#define CRT_ID_HCRX		S9000_ID_HCRX	/* Hyperdrive HCRX */
+#define CRT_ID_CRX48Z		S9000_ID_STINGER /* Stinger */
+#define CRT_ID_DUAL_CRX		S9000_ID_TOMCAT	/* Tomcat */
+#define CRT_ID_PVRX		S9000_ID_98705	/* Tigershark */
+#define CRT_ID_TIMBER		S9000_ID_TIMBER	/* Timber (710 builtin) */
+#define CRT_ID_TVRX		S9000_ID_98765	/* TVRX (gto/falcon) */
+#define CRT_ID_ARTIST		S9000_ID_ARTIST	/* Artist */
+#define CRT_ID_SUMMIT		0x2FC1066B      /* Summit FX2, FX4, FX6 ... */
+#define CRT_ID_LEGO		0x35ACDA30	/* Lego FX5, FX10 ... */
+#define CRT_ID_PINNACLE		0x35ACDA16	/* Pinnacle FXe */ 
+
+/* structure for ioctl(GCDESCRIBE) */
+
+#define gaddr_t unsigned long	/* FIXME: PA2.0 (64bit) portable ? */
+
+struct	grf_fbinfo {
+	unsigned int	id;		/* upper 32 bits of graphics id */
+	unsigned int	mapsize;	/* mapped size of framebuffer */
+	unsigned int	dwidth, dlength;/* x and y sizes */
+	unsigned int	width, length;	/* total x and total y size */
+	unsigned int	xlen;		/* x pitch size */
+	unsigned int	bpp, bppu;	/* bits per pixel and used bpp */
+	unsigned int	npl, nplbytes;	/* # of planes and bytes per plane */
+	char		name[32];	/* name of the device (from ROM) */
+	unsigned int	attr;		/* attributes */
+	gaddr_t 	fbbase, regbase;/* framebuffer and register base addr */
+	gaddr_t		regions[6];	/* region bases */
+};
+
+#define	GCID		_IOR('G', 0, int)
+#define	GCON		_IO('G', 1)
+#define	GCOFF		_IO('G', 2)
+#define	GCAON		_IO('G', 3)
+#define	GCAOFF		_IO('G', 4)
+#define	GCMAP		_IOWR('G', 5, int)
+#define	GCUNMAP		_IOWR('G', 6, int)
+#define	GCMAP_HPUX	_IO('G', 5)
+#define	GCUNMAP_HPUX	_IO('G', 6)
+#define	GCLOCK		_IO('G', 7)
+#define	GCUNLOCK	_IO('G', 8)
+#define	GCLOCK_MINIMUM	_IO('G', 9)
+#define	GCUNLOCK_MINIMUM _IO('G', 10)
+#define	GCSTATIC_CMAP	_IO('G', 11)
+#define	GCVARIABLE_CMAP _IO('G', 12)
+#define GCTERM		_IOWR('G',20,int)	/* multi-headed Tomcat */ 
+#define GCDESCRIBE	_IOR('G', 21, struct grf_fbinfo)
+#define GCFASTLOCK	_IO('G', 26)
+
+#endif /* __ASM_PARISC_GRFIOCTL_H */
+
diff --git a/arch/parisc/include/asm/hardirq.h b/arch/parisc/include/asm/hardirq.h
new file mode 100644
index 000000000000..ce93133d5112
--- /dev/null
+++ b/arch/parisc/include/asm/hardirq.h
@@ -0,0 +1,29 @@
+/* hardirq.h: PA-RISC hard IRQ support.
+ *
+ * Copyright (C) 2001 Matthew Wilcox <matthew@wil.cx>
+ *
+ * The locking is really quite interesting.  There's a cpu-local
+ * count of how many interrupts are being handled, and a global
+ * lock.  An interrupt can only be serviced if the global lock
+ * is free.  You can't be sure no more interrupts are being
+ * serviced until you've acquired the lock and then checked
+ * all the per-cpu interrupt counts are all zero.  It's a specialised
+ * br_lock, and that's exactly how Sparc does it.  We don't because
+ * it's more locking for us.  This way is lock-free in the interrupt path.
+ */
+
+#ifndef _PARISC_HARDIRQ_H
+#define _PARISC_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+typedef struct {
+	unsigned long __softirq_pending; /* set_bit is used on this */
+} ____cacheline_aligned irq_cpustat_t;
+
+#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+
+void ack_bad_irq(unsigned int irq);
+
+#endif /* _PARISC_HARDIRQ_H */
diff --git a/arch/parisc/include/asm/hardware.h b/arch/parisc/include/asm/hardware.h
new file mode 100644
index 000000000000..4e9626836bab
--- /dev/null
+++ b/arch/parisc/include/asm/hardware.h
@@ -0,0 +1,127 @@
+#ifndef _PARISC_HARDWARE_H
+#define _PARISC_HARDWARE_H
+
+#include <linux/mod_devicetable.h>
+#include <asm/pdc.h>
+
+#define HWTYPE_ANY_ID		PA_HWTYPE_ANY_ID
+#define HVERSION_ANY_ID		PA_HVERSION_ANY_ID
+#define HVERSION_REV_ANY_ID	PA_HVERSION_REV_ANY_ID
+#define SVERSION_ANY_ID		PA_SVERSION_ANY_ID
+
+struct hp_hardware {
+	unsigned short	hw_type:5;	/* HPHW_xxx */
+	unsigned short	hversion;
+	unsigned long	sversion:28;
+	unsigned short	opt;
+	const char	name[80];	/* The hardware description */
+};
+
+struct parisc_device;
+
+enum cpu_type {
+	pcx	= 0, /* pa7000		pa 1.0  */
+	pcxs	= 1, /* pa7000		pa 1.1a */
+	pcxt	= 2, /* pa7100		pa 1.1b */
+	pcxt_	= 3, /* pa7200	(t')	pa 1.1c */
+	pcxl	= 4, /* pa7100lc	pa 1.1d */
+	pcxl2	= 5, /* pa7300lc	pa 1.1e */
+	pcxu	= 6, /* pa8000		pa 2.0  */
+	pcxu_	= 7, /* pa8200	(u+)	pa 2.0  */
+	pcxw	= 8, /* pa8500		pa 2.0  */
+	pcxw_	= 9, /* pa8600	(w+)	pa 2.0  */
+	pcxw2	= 10, /* pa8700		pa 2.0  */
+	mako	= 11, /* pa8800		pa 2.0  */
+	mako2	= 12  /* pa8900		pa 2.0  */
+};
+
+extern const char * const cpu_name_version[][2]; /* mapping from enum cpu_type to strings */
+
+struct parisc_driver;
+
+struct io_module {
+        volatile uint32_t nothing;		/* reg 0 */
+        volatile uint32_t io_eim;
+        volatile uint32_t io_dc_adata;
+        volatile uint32_t io_ii_cdata;
+        volatile uint32_t io_dma_link;		/* reg 4 */
+        volatile uint32_t io_dma_command;
+        volatile uint32_t io_dma_address;
+        volatile uint32_t io_dma_count;
+        volatile uint32_t io_flex;		/* reg 8 */
+        volatile uint32_t io_spa_address;
+        volatile uint32_t reserved1[2];
+        volatile uint32_t io_command;		/* reg 12 */
+        volatile uint32_t io_status;
+        volatile uint32_t io_control;
+        volatile uint32_t io_data;
+        volatile uint32_t reserved2;		/* reg 16 */
+        volatile uint32_t chain_addr;
+        volatile uint32_t sub_mask_clr;
+        volatile uint32_t reserved3[13];
+        volatile uint32_t undefined[480];
+        volatile uint32_t unpriv[512];
+};
+
+struct bc_module {
+        volatile uint32_t unused1[12];
+        volatile uint32_t io_command;
+        volatile uint32_t io_status;
+        volatile uint32_t io_control;
+        volatile uint32_t unused2[1];
+        volatile uint32_t io_err_resp;
+        volatile uint32_t io_err_info;
+        volatile uint32_t io_err_req;
+        volatile uint32_t unused3[11];
+        volatile uint32_t io_io_low;
+        volatile uint32_t io_io_high;
+};
+
+#define HPHW_NPROC     0 
+#define HPHW_MEMORY    1       
+#define HPHW_B_DMA     2
+#define HPHW_OBSOLETE  3
+#define HPHW_A_DMA     4
+#define HPHW_A_DIRECT  5
+#define HPHW_OTHER     6
+#define HPHW_BCPORT    7
+#define HPHW_CIO       8
+#define HPHW_CONSOLE   9
+#define HPHW_FIO       10
+#define HPHW_BA        11
+#define HPHW_IOA       12
+#define HPHW_BRIDGE    13
+#define HPHW_FABRIC    14
+#define HPHW_MC	       15
+#define HPHW_FAULTY    31
+
+
+/* hardware.c: */
+extern const char *parisc_hardware_description(struct parisc_device_id *id);
+extern enum cpu_type parisc_get_cpu_type(unsigned long hversion);
+
+struct pci_dev;
+
+/* drivers.c: */
+extern struct parisc_device *alloc_pa_dev(unsigned long hpa,
+		struct hardware_path *path);
+extern int register_parisc_device(struct parisc_device *dev);
+extern int register_parisc_driver(struct parisc_driver *driver);
+extern int count_parisc_driver(struct parisc_driver *driver);
+extern int unregister_parisc_driver(struct parisc_driver *driver);
+extern void walk_central_bus(void);
+extern const struct parisc_device *find_pa_parent_type(const struct parisc_device *, int);
+extern void print_parisc_devices(void);
+extern char *print_pa_hwpath(struct parisc_device *dev, char *path);
+extern char *print_pci_hwpath(struct pci_dev *dev, char *path);
+extern void get_pci_node_path(struct pci_dev *dev, struct hardware_path *path);
+extern void init_parisc_bus(void);
+extern struct device *hwpath_to_device(struct hardware_path *modpath);
+extern void device_to_hwpath(struct device *dev, struct hardware_path *path);
+
+
+/* inventory.c: */
+extern void do_memory_inventory(void);
+extern void do_device_inventory(void);
+
+#endif /* _PARISC_HARDWARE_H */
diff --git a/arch/parisc/include/asm/hw_irq.h b/arch/parisc/include/asm/hw_irq.h
new file mode 100644
index 000000000000..6707f7df3921
--- /dev/null
+++ b/arch/parisc/include/asm/hw_irq.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_HW_IRQ_H
+#define _ASM_HW_IRQ_H
+
+/*
+ *	linux/include/asm/hw_irq.h
+ */
+
+#endif
diff --git a/arch/parisc/include/asm/ide.h b/arch/parisc/include/asm/ide.h
new file mode 100644
index 000000000000..c246ef75017d
--- /dev/null
+++ b/arch/parisc/include/asm/ide.h
@@ -0,0 +1,61 @@
+/*
+ *  linux/include/asm-parisc/ide.h
+ *
+ *  Copyright (C) 1994-1996  Linus Torvalds & authors
+ */
+
+/*
+ *  This file contains the PARISC architecture specific IDE code.
+ */
+
+#ifndef __ASM_PARISC_IDE_H
+#define __ASM_PARISC_IDE_H
+
+#ifdef __KERNEL__
+
+#define ide_request_irq(irq,hand,flg,dev,id)	request_irq((irq),(hand),(flg),(dev),(id))
+#define ide_free_irq(irq,dev_id)		free_irq((irq), (dev_id))
+#define ide_request_region(from,extent,name)	request_region((from), (extent), (name))
+#define ide_release_region(from,extent)		release_region((from), (extent))
+/* Generic I/O and MEMIO string operations.  */
+
+#define __ide_insw	insw
+#define __ide_insl	insl
+#define __ide_outsw	outsw
+#define __ide_outsl	outsl
+
+static __inline__ void __ide_mm_insw(void __iomem *port, void *addr, u32 count)
+{
+	while (count--) {
+		*(u16 *)addr = __raw_readw(port);
+		addr += 2;
+	}
+}
+
+static __inline__ void __ide_mm_insl(void __iomem *port, void *addr, u32 count)
+{
+	while (count--) {
+		*(u32 *)addr = __raw_readl(port);
+		addr += 4;
+	}
+}
+
+static __inline__ void __ide_mm_outsw(void __iomem *port, void *addr, u32 count)
+{
+	while (count--) {
+		__raw_writew(*(u16 *)addr, port);
+		addr += 2;
+	}
+}
+
+static __inline__ void __ide_mm_outsl(void __iomem *port, void *addr, u32 count)
+{
+	while (count--) {
+		__raw_writel(*(u32 *)addr, port);
+		addr += 4;
+	}
+}
+
+#endif /* __KERNEL__ */
+
+#endif /* __ASM_PARISC_IDE_H */
diff --git a/arch/parisc/include/asm/io.h b/arch/parisc/include/asm/io.h
new file mode 100644
index 000000000000..55ddb1842107
--- /dev/null
+++ b/arch/parisc/include/asm/io.h
@@ -0,0 +1,293 @@
+#ifndef _ASM_IO_H
+#define _ASM_IO_H
+
+#include <linux/types.h>
+#include <asm/pgtable.h>
+
+extern unsigned long parisc_vmerge_boundary;
+extern unsigned long parisc_vmerge_max_size;
+
+#define BIO_VMERGE_BOUNDARY	parisc_vmerge_boundary
+#define BIO_VMERGE_MAX_SIZE	parisc_vmerge_max_size
+
+#define virt_to_phys(a) ((unsigned long)__pa(a))
+#define phys_to_virt(a) __va(a)
+#define virt_to_bus virt_to_phys
+#define bus_to_virt phys_to_virt
+
+static inline unsigned long isa_bus_to_virt(unsigned long addr) {
+	BUG();
+	return 0;
+}
+
+static inline unsigned long isa_virt_to_bus(void *addr) {
+	BUG();
+	return 0;
+}
+
+/*
+ * Memory mapped I/O
+ *
+ * readX()/writeX() do byteswapping and take an ioremapped address
+ * __raw_readX()/__raw_writeX() don't byteswap and take an ioremapped address.
+ * gsc_*() don't byteswap and operate on physical addresses;
+ *   eg dev->hpa or 0xfee00000.
+ */
+
+static inline unsigned char gsc_readb(unsigned long addr)
+{
+	long flags;
+	unsigned char ret;
+
+	__asm__ __volatile__(
+	"	rsm	2,%0\n"
+	"	ldbx	0(%2),%1\n"
+	"	mtsm	%0\n"
+	: "=&r" (flags), "=r" (ret) : "r" (addr) );
+
+	return ret;
+}
+
+static inline unsigned short gsc_readw(unsigned long addr)
+{
+	long flags;
+	unsigned short ret;
+
+	__asm__ __volatile__(
+	"	rsm	2,%0\n"
+	"	ldhx	0(%2),%1\n"
+	"	mtsm	%0\n"
+	: "=&r" (flags), "=r" (ret) : "r" (addr) );
+
+	return ret;
+}
+
+static inline unsigned int gsc_readl(unsigned long addr)
+{
+	u32 ret;
+
+	__asm__ __volatile__(
+	"	ldwax	0(%1),%0\n"
+	: "=r" (ret) : "r" (addr) );
+
+	return ret;
+}
+
+static inline unsigned long long gsc_readq(unsigned long addr)
+{
+	unsigned long long ret;
+
+#ifdef CONFIG_64BIT
+	__asm__ __volatile__(
+	"	ldda	0(%1),%0\n"
+	:  "=r" (ret) : "r" (addr) );
+#else
+	/* two reads may have side effects.. */
+	ret = ((u64) gsc_readl(addr)) << 32;
+	ret |= gsc_readl(addr+4);
+#endif
+	return ret;
+}
+
+static inline void gsc_writeb(unsigned char val, unsigned long addr)
+{
+	long flags;
+	__asm__ __volatile__(
+	"	rsm	2,%0\n"
+	"	stbs	%1,0(%2)\n"
+	"	mtsm	%0\n"
+	: "=&r" (flags) :  "r" (val), "r" (addr) );
+}
+
+static inline void gsc_writew(unsigned short val, unsigned long addr)
+{
+	long flags;
+	__asm__ __volatile__(
+	"	rsm	2,%0\n"
+	"	sths	%1,0(%2)\n"
+	"	mtsm	%0\n"
+	: "=&r" (flags) :  "r" (val), "r" (addr) );
+}
+
+static inline void gsc_writel(unsigned int val, unsigned long addr)
+{
+	__asm__ __volatile__(
+	"	stwas	%0,0(%1)\n"
+	: :  "r" (val), "r" (addr) );
+}
+
+static inline void gsc_writeq(unsigned long long val, unsigned long addr)
+{
+#ifdef CONFIG_64BIT
+	__asm__ __volatile__(
+	"	stda	%0,0(%1)\n"
+	: :  "r" (val), "r" (addr) );
+#else
+	/* two writes may have side effects.. */
+	gsc_writel(val >> 32, addr);
+	gsc_writel(val, addr+4);
+#endif
+}
+
+/*
+ * The standard PCI ioremap interfaces
+ */
+
+extern void __iomem * __ioremap(unsigned long offset, unsigned long size, unsigned long flags);
+
+/* Most machines react poorly to I/O-space being cacheable... Instead let's
+ * define ioremap() in terms of ioremap_nocache().
+ */
+static inline void __iomem * ioremap(unsigned long offset, unsigned long size)
+{
+	return __ioremap(offset, size, _PAGE_NO_CACHE);
+}
+#define ioremap_nocache(off, sz)	ioremap((off), (sz))
+
+extern void iounmap(const volatile void __iomem *addr);
+
+static inline unsigned char __raw_readb(const volatile void __iomem *addr)
+{
+	return (*(volatile unsigned char __force *) (addr));
+}
+static inline unsigned short __raw_readw(const volatile void __iomem *addr)
+{
+	return *(volatile unsigned short __force *) addr;
+}
+static inline unsigned int __raw_readl(const volatile void __iomem *addr)
+{
+	return *(volatile unsigned int __force *) addr;
+}
+static inline unsigned long long __raw_readq(const volatile void __iomem *addr)
+{
+	return *(volatile unsigned long long __force *) addr;
+}
+
+static inline void __raw_writeb(unsigned char b, volatile void __iomem *addr)
+{
+	*(volatile unsigned char __force *) addr = b;
+}
+static inline void __raw_writew(unsigned short b, volatile void __iomem *addr)
+{
+	*(volatile unsigned short __force *) addr = b;
+}
+static inline void __raw_writel(unsigned int b, volatile void __iomem *addr)
+{
+	*(volatile unsigned int __force *) addr = b;
+}
+static inline void __raw_writeq(unsigned long long b, volatile void __iomem *addr)
+{
+	*(volatile unsigned long long __force *) addr = b;
+}
+
+/* readb can never be const, so use __fswab instead of le*_to_cpu */
+#define readb(addr) __raw_readb(addr)
+#define readw(addr) __fswab16(__raw_readw(addr))
+#define readl(addr) __fswab32(__raw_readl(addr))
+#define readq(addr) __fswab64(__raw_readq(addr))
+#define writeb(b, addr) __raw_writeb(b, addr)
+#define writew(b, addr) __raw_writew(cpu_to_le16(b), addr)
+#define writel(b, addr) __raw_writel(cpu_to_le32(b), addr)
+#define writeq(b, addr) __raw_writeq(cpu_to_le64(b), addr)
+
+#define readb_relaxed(addr) readb(addr)
+#define readw_relaxed(addr) readw(addr)
+#define readl_relaxed(addr) readl(addr)
+#define readq_relaxed(addr) readq(addr)
+
+#define mmiowb() do { } while (0)
+
+void memset_io(volatile void __iomem *addr, unsigned char val, int count);
+void memcpy_fromio(void *dst, const volatile void __iomem *src, int count);
+void memcpy_toio(volatile void __iomem *dst, const void *src, int count);
+
+/* Port-space IO */
+
+#define inb_p inb
+#define inw_p inw
+#define inl_p inl
+#define outb_p outb
+#define outw_p outw
+#define outl_p outl
+
+extern unsigned char eisa_in8(unsigned short port);
+extern unsigned short eisa_in16(unsigned short port);
+extern unsigned int eisa_in32(unsigned short port);
+extern void eisa_out8(unsigned char data, unsigned short port);
+extern void eisa_out16(unsigned short data, unsigned short port);
+extern void eisa_out32(unsigned int data, unsigned short port);
+
+#if defined(CONFIG_PCI)
+extern unsigned char inb(int addr);
+extern unsigned short inw(int addr);
+extern unsigned int inl(int addr);
+
+extern void outb(unsigned char b, int addr);
+extern void outw(unsigned short b, int addr);
+extern void outl(unsigned int b, int addr);
+#elif defined(CONFIG_EISA)
+#define inb eisa_in8
+#define inw eisa_in16
+#define inl eisa_in32
+#define outb eisa_out8
+#define outw eisa_out16
+#define outl eisa_out32
+#else
+static inline char inb(unsigned long addr)
+{
+	BUG();
+	return -1;
+}
+
+static inline short inw(unsigned long addr)
+{
+	BUG();
+	return -1;
+}
+
+static inline int inl(unsigned long addr)
+{
+	BUG();
+	return -1;
+}
+
+#define outb(x, y)	BUG()
+#define outw(x, y)	BUG()
+#define outl(x, y)	BUG()
+#endif
+
+/*
+ * String versions of in/out ops:
+ */
+extern void insb (unsigned long port, void *dst, unsigned long count);
+extern void insw (unsigned long port, void *dst, unsigned long count);
+extern void insl (unsigned long port, void *dst, unsigned long count);
+extern void outsb (unsigned long port, const void *src, unsigned long count);
+extern void outsw (unsigned long port, const void *src, unsigned long count);
+extern void outsl (unsigned long port, const void *src, unsigned long count);
+
+
+/* IO Port space is :      BBiiii   where BB is HBA number. */
+#define IO_SPACE_LIMIT 0x00ffffff
+
+/* PA machines have an MM I/O space from 0xf0000000-0xffffffff in 32
+ * bit mode and from 0xfffffffff0000000-0xfffffffffffffff in 64 bit
+ * mode (essentially just sign extending.  This macro takes in a 32
+ * bit I/O address (still with the leading f) and outputs the correct
+ * value for either 32 or 64 bit mode */
+#define F_EXTEND(x) ((unsigned long)((x) | (0xffffffff00000000ULL)))
+
+#include <asm-generic/iomap.h>
+
+/*
+ * Convert a physical pointer to a virtual kernel pointer for /dev/mem
+ * access
+ */
+#define xlate_dev_mem_ptr(p)	__va(p)
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p)	p
+
+#endif
diff --git a/arch/parisc/include/asm/ioctl.h b/arch/parisc/include/asm/ioctl.h
new file mode 100644
index 000000000000..ec8efa02beda
--- /dev/null
+++ b/arch/parisc/include/asm/ioctl.h
@@ -0,0 +1,44 @@
+/*
+ *    Linux/PA-RISC Project (http://www.parisc-linux.org/)
+ *    Copyright (C) 1999,2003 Matthew Wilcox < willy at debian . org >
+ *    portions from "linux/ioctl.h for Linux" by H.H. Bergman.
+ *
+ *    This program is free software; you can redistribute it and/or modify
+ *    it under the terms of the GNU General Public License as published by
+ *    the Free Software Foundation; either version 2 of the License, or
+ *    (at your option) any later version.
+ *
+ *    This program is distributed in the hope that it will be useful,
+ *    but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *    GNU General Public License for more details.
+ *
+ *    You should have received a copy of the GNU General Public License
+ *    along with this program; if not, write to the Free Software
+ *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ */
+
+
+#ifndef _ASM_PARISC_IOCTL_H
+#define _ASM_PARISC_IOCTL_H
+
+/* ioctl command encoding: 32 bits total, command in lower 16 bits,
+ * size of the parameter structure in the lower 14 bits of the
+ * upper 16 bits.
+ * Encoding the size of the parameter structure in the ioctl request
+ * is useful for catching programs compiled with old versions
+ * and to avoid overwriting user space outside the user buffer area.
+ * The highest 2 bits are reserved for indicating the ``access mode''.
+ * NOTE: This limits the max parameter size to 16kB -1 !
+ */
+
+/*
+ * Direction bits.
+ */
+#define _IOC_NONE	0U
+#define _IOC_WRITE	2U
+#define _IOC_READ	1U
+
+#include <asm-generic/ioctl.h>
+
+#endif /* _ASM_PARISC_IOCTL_H */
diff --git a/arch/parisc/include/asm/ioctls.h b/arch/parisc/include/asm/ioctls.h
new file mode 100644
index 000000000000..6747fad07a3e
--- /dev/null
+++ b/arch/parisc/include/asm/ioctls.h
@@ -0,0 +1,90 @@
+#ifndef __ARCH_PARISC_IOCTLS_H__
+#define __ARCH_PARISC_IOCTLS_H__
+
+#include <asm/ioctl.h>
+
+/* 0x54 is just a magic number to make these relatively unique ('T') */
+
+#define TCGETS		_IOR('T', 16, struct termios) /* TCGETATTR */
+#define TCSETS		_IOW('T', 17, struct termios) /* TCSETATTR */
+#define TCSETSW		_IOW('T', 18, struct termios) /* TCSETATTRD */
+#define TCSETSF		_IOW('T', 19, struct termios) /* TCSETATTRF */
+#define TCGETA		_IOR('T', 1, struct termio)
+#define TCSETA		_IOW('T', 2, struct termio)
+#define TCSETAW		_IOW('T', 3, struct termio)
+#define TCSETAF		_IOW('T', 4, struct termio)
+#define TCSBRK		_IO('T', 5)
+#define TCXONC		_IO('T', 6)
+#define TCFLSH		_IO('T', 7)
+#define TIOCEXCL	0x540C
+#define TIOCNXCL	0x540D
+#define TIOCSCTTY	0x540E
+#define TIOCGPGRP	_IOR('T', 30, int)
+#define TIOCSPGRP	_IOW('T', 29, int)
+#define TIOCOUTQ	0x5411
+#define TIOCSTI		0x5412
+#define TIOCGWINSZ	0x5413
+#define TIOCSWINSZ	0x5414
+#define TIOCMGET	0x5415
+#define TIOCMBIS	0x5416
+#define TIOCMBIC	0x5417
+#define TIOCMSET	0x5418
+#define TIOCGSOFTCAR	0x5419
+#define TIOCSSOFTCAR	0x541A
+#define FIONREAD	0x541B
+#define TIOCINQ		FIONREAD
+#define TIOCLINUX	0x541C
+#define TIOCCONS	0x541D
+#define TIOCGSERIAL	0x541E
+#define TIOCSSERIAL	0x541F
+#define TIOCPKT		0x5420
+#define FIONBIO		0x5421
+#define TIOCNOTTY	0x5422
+#define TIOCSETD	0x5423
+#define TIOCGETD	0x5424
+#define TCSBRKP		0x5425	/* Needed for POSIX tcsendbreak() */
+#define TIOCSBRK	0x5427  /* BSD compatibility */
+#define TIOCCBRK	0x5428  /* BSD compatibility */
+#define TIOCGSID	_IOR('T', 20, int) /* Return the session ID of FD */
+#define TCGETS2		_IOR('T',0x2A, struct termios2)
+#define TCSETS2		_IOW('T',0x2B, struct termios2)
+#define TCSETSW2	_IOW('T',0x2C, struct termios2)
+#define TCSETSF2	_IOW('T',0x2D, struct termios2)
+#define TIOCGPTN	_IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
+#define TIOCSPTLCK	_IOW('T',0x31, int)  /* Lock/unlock Pty */
+
+#define FIONCLEX	0x5450  /* these numbers need to be adjusted. */
+#define FIOCLEX		0x5451
+#define FIOASYNC	0x5452
+#define TIOCSERCONFIG	0x5453
+#define TIOCSERGWILD	0x5454
+#define TIOCSERSWILD	0x5455
+#define TIOCGLCKTRMIOS	0x5456
+#define TIOCSLCKTRMIOS	0x5457
+#define TIOCSERGSTRUCT	0x5458 /* For debugging only */
+#define TIOCSERGETLSR   0x5459 /* Get line status register */
+#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
+#define TIOCSERSETMULTI 0x545B /* Set multiport config */
+
+#define TIOCMIWAIT	0x545C	/* wait for a change on serial input line(s) */
+#define TIOCGICOUNT	0x545D	/* read serial port inline interrupt counts */
+#define TIOCGHAYESESP   0x545E  /* Get Hayes ESP configuration */
+#define TIOCSHAYESESP   0x545F  /* Set Hayes ESP configuration */
+#define FIOQSIZE	0x5460	/* Get exact space used by quota */
+
+#define TIOCSTART	0x5461
+#define TIOCSTOP	0x5462
+#define TIOCSLTC	0x5462
+
+/* Used for packet mode */
+#define TIOCPKT_DATA		 0
+#define TIOCPKT_FLUSHREAD	 1
+#define TIOCPKT_FLUSHWRITE	 2
+#define TIOCPKT_STOP		 4
+#define TIOCPKT_START		 8
+#define TIOCPKT_NOSTOP		16
+#define TIOCPKT_DOSTOP		32
+
+#define TIOCSER_TEMT    0x01	/* Transmitter physically empty */
+
+#endif /* _ASM_PARISC_IOCTLS_H */
diff --git a/arch/parisc/include/asm/ipcbuf.h b/arch/parisc/include/asm/ipcbuf.h
new file mode 100644
index 000000000000..bd956c425785
--- /dev/null
+++ b/arch/parisc/include/asm/ipcbuf.h
@@ -0,0 +1,27 @@
+#ifndef __PARISC_IPCBUF_H__
+#define __PARISC_IPCBUF_H__
+
+/*
+ * The ipc64_perm structure for PA-RISC is almost identical to
+ * kern_ipc_perm as we have always had 32-bit UIDs and GIDs in the kernel.
+ * 'seq' has been changed from long to int so that it's the same size
+ * on 64-bit kernels as on 32-bit ones.
+ */
+
+struct ipc64_perm
+{
+	key_t           key;
+	uid_t           uid;
+	gid_t           gid;
+	uid_t           cuid;
+	gid_t           cgid;
+	unsigned short int	__pad1;
+	mode_t          mode;
+	unsigned short int	__pad2;
+	unsigned short int	seq;
+	unsigned int	__pad3;
+	unsigned long long int __unused1;
+	unsigned long long int __unused2;
+};
+
+#endif /* __PARISC_IPCBUF_H__ */
diff --git a/arch/parisc/include/asm/irq.h b/arch/parisc/include/asm/irq.h
new file mode 100644
index 000000000000..399c81981ed5
--- /dev/null
+++ b/arch/parisc/include/asm/irq.h
@@ -0,0 +1,57 @@
+/*
+ * include/asm-parisc/irq.h
+ *
+ * Copyright 2005 Matthew Wilcox <matthew@wil.cx>
+ */
+
+#ifndef _ASM_PARISC_IRQ_H
+#define _ASM_PARISC_IRQ_H
+
+#include <linux/cpumask.h>
+#include <asm/types.h>
+
+#define NO_IRQ		(-1)
+
+#ifdef CONFIG_GSC
+#define GSC_IRQ_BASE	16
+#define GSC_IRQ_MAX	63
+#define CPU_IRQ_BASE	64
+#else
+#define CPU_IRQ_BASE	16
+#endif
+
+#define TIMER_IRQ	(CPU_IRQ_BASE + 0)
+#define	IPI_IRQ		(CPU_IRQ_BASE + 1)
+#define CPU_IRQ_MAX	(CPU_IRQ_BASE + (BITS_PER_LONG - 1))
+
+#define NR_IRQS		(CPU_IRQ_MAX + 1)
+
+static __inline__ int irq_canonicalize(int irq)
+{
+	return (irq == 2) ? 9 : irq;
+}
+
+struct irq_chip;
+
+/*
+ * Some useful "we don't have to do anything here" handlers.  Should
+ * probably be provided by the generic code.
+ */
+void no_ack_irq(unsigned int irq);
+void no_end_irq(unsigned int irq);
+void cpu_ack_irq(unsigned int irq);
+void cpu_end_irq(unsigned int irq);
+
+extern int txn_alloc_irq(unsigned int nbits);
+extern int txn_claim_irq(int);
+extern unsigned int txn_alloc_data(unsigned int);
+extern unsigned long txn_alloc_addr(unsigned int);
+extern unsigned long txn_affinity_addr(unsigned int irq, int cpu);
+
+extern int cpu_claim_irq(unsigned int irq, struct irq_chip *, void *);
+extern int cpu_check_affinity(unsigned int irq, cpumask_t *dest);
+
+/* soft power switch support (power.c) */
+extern struct tasklet_struct power_tasklet;
+
+#endif	/* _ASM_PARISC_IRQ_H */
diff --git a/arch/parisc/include/asm/irq_regs.h b/arch/parisc/include/asm/irq_regs.h
new file mode 100644
index 000000000000..3dd9c0b70270
--- /dev/null
+++ b/arch/parisc/include/asm/irq_regs.h
@@ -0,0 +1 @@
+#include <asm-generic/irq_regs.h>
diff --git a/arch/parisc/include/asm/kdebug.h b/arch/parisc/include/asm/kdebug.h
new file mode 100644
index 000000000000..6ece1b037665
--- /dev/null
+++ b/arch/parisc/include/asm/kdebug.h
@@ -0,0 +1 @@
+#include <asm-generic/kdebug.h>
diff --git a/arch/parisc/include/asm/kmap_types.h b/arch/parisc/include/asm/kmap_types.h
new file mode 100644
index 000000000000..806aae3c5338
--- /dev/null
+++ b/arch/parisc/include/asm/kmap_types.h
@@ -0,0 +1,30 @@
+#ifndef _ASM_KMAP_TYPES_H
+#define _ASM_KMAP_TYPES_H
+
+
+#ifdef CONFIG_DEBUG_HIGHMEM
+# define D(n) __KM_FENCE_##n ,
+#else
+# define D(n)
+#endif
+
+enum km_type {
+D(0)	KM_BOUNCE_READ,
+D(1)	KM_SKB_SUNRPC_DATA,
+D(2)	KM_SKB_DATA_SOFTIRQ,
+D(3)	KM_USER0,
+D(4)	KM_USER1,
+D(5)	KM_BIO_SRC_IRQ,
+D(6)	KM_BIO_DST_IRQ,
+D(7)	KM_PTE0,
+D(8)	KM_PTE1,
+D(9)	KM_IRQ0,
+D(10)	KM_IRQ1,
+D(11)	KM_SOFTIRQ0,
+D(12)	KM_SOFTIRQ1,
+D(13)	KM_TYPE_NR
+};
+
+#undef D
+
+#endif
diff --git a/arch/parisc/include/asm/led.h b/arch/parisc/include/asm/led.h
new file mode 100644
index 000000000000..c3405ab9d60a
--- /dev/null
+++ b/arch/parisc/include/asm/led.h
@@ -0,0 +1,42 @@
+#ifndef LED_H
+#define LED_H
+
+#define	LED7		0x80		/* top (or furthest right) LED */
+#define	LED6		0x40
+#define	LED5		0x20
+#define	LED4		0x10
+#define	LED3		0x08
+#define	LED2		0x04
+#define	LED1		0x02
+#define	LED0		0x01		/* bottom (or furthest left) LED */
+
+#define	LED_LAN_TX	LED0		/* for LAN transmit activity */
+#define	LED_LAN_RCV	LED1		/* for LAN receive activity */
+#define	LED_DISK_IO	LED2		/* for disk activity */
+#define	LED_HEARTBEAT	LED3		/* heartbeat */
+
+/* values for pdc_chassis_lcd_info_ret_block.model: */
+#define DISPLAY_MODEL_LCD  0		/* KittyHawk LED or LCD */
+#define DISPLAY_MODEL_NONE 1		/* no LED or LCD */
+#define DISPLAY_MODEL_LASI 2		/* LASI style 8 bit LED */
+#define DISPLAY_MODEL_OLD_ASP 0x7F	/* faked: ASP style 8 x 1 bit LED (only very old ASP versions) */
+
+#define LED_CMD_REG_NONE 0		/* NULL == no addr for the cmd register */
+
+/* register_led_driver() */
+int __init register_led_driver(int model, unsigned long cmd_reg, unsigned long data_reg);
+
+/* registers the LED regions for procfs */
+void __init register_led_regions(void);
+
+#ifdef CONFIG_CHASSIS_LCD_LED
+/* writes a string to the LCD display (if possible on this h/w) */
+int lcd_print(const char *str);
+#else
+#define lcd_print(str)
+#endif
+
+/* main LED initialization function (uses PDC) */ 
+int __init led_init(void);
+
+#endif /* LED_H */
diff --git a/arch/parisc/include/asm/linkage.h b/arch/parisc/include/asm/linkage.h
new file mode 100644
index 000000000000..0b19a7242d0c
--- /dev/null
+++ b/arch/parisc/include/asm/linkage.h
@@ -0,0 +1,31 @@
+#ifndef __ASM_PARISC_LINKAGE_H
+#define __ASM_PARISC_LINKAGE_H
+
+#ifndef __ALIGN
+#define __ALIGN         .align 4
+#define __ALIGN_STR     ".align 4"
+#endif
+
+/*
+ * In parisc assembly a semicolon marks a comment while a
+ * exclamation mark is used to separate independent lines.
+ */
+#ifdef __ASSEMBLY__
+
+#define ENTRY(name) \
+	.export name !\
+	ALIGN !\
+name:
+
+#ifdef CONFIG_64BIT
+#define ENDPROC(name) \
+	END(name)
+#else
+#define ENDPROC(name) \
+	.type name, @function !\
+	END(name)
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif  /* __ASM_PARISC_LINKAGE_H */
diff --git a/arch/parisc/include/asm/local.h b/arch/parisc/include/asm/local.h
new file mode 100644
index 000000000000..c11c530f74d0
--- /dev/null
+++ b/arch/parisc/include/asm/local.h
@@ -0,0 +1 @@
+#include <asm-generic/local.h>
diff --git a/arch/parisc/include/asm/machdep.h b/arch/parisc/include/asm/machdep.h
new file mode 100644
index 000000000000..a231c97d703e
--- /dev/null
+++ b/arch/parisc/include/asm/machdep.h
@@ -0,0 +1,16 @@
+#ifndef _PARISC_MACHDEP_H
+#define _PARISC_MACHDEP_H
+
+#include <linux/notifier.h>
+
+#define	MACH_RESTART	1
+#define	MACH_HALT	2
+#define MACH_POWER_ON	3
+#define	MACH_POWER_OFF	4
+
+extern struct notifier_block *mach_notifier;
+extern void pa7300lc_init(void);
+
+extern void (*cpu_lpmc)(int, struct pt_regs *);
+
+#endif
diff --git a/arch/parisc/include/asm/mc146818rtc.h b/arch/parisc/include/asm/mc146818rtc.h
new file mode 100644
index 000000000000..adf41631449f
--- /dev/null
+++ b/arch/parisc/include/asm/mc146818rtc.h
@@ -0,0 +1,9 @@
+/*
+ * Machine dependent access functions for RTC registers.
+ */
+#ifndef _ASM_MC146818RTC_H
+#define _ASM_MC146818RTC_H
+
+/* empty include file to satisfy the include in genrtc.c */
+
+#endif /* _ASM_MC146818RTC_H */
diff --git a/arch/parisc/include/asm/mckinley.h b/arch/parisc/include/asm/mckinley.h
new file mode 100644
index 000000000000..d1ea6f12915e
--- /dev/null
+++ b/arch/parisc/include/asm/mckinley.h
@@ -0,0 +1,9 @@
+#ifndef ASM_PARISC_MCKINLEY_H
+#define ASM_PARISC_MCKINLEY_H
+#ifdef __KERNEL__
+
+/* declared in arch/parisc/kernel/setup.c */
+extern struct proc_dir_entry * proc_mckinley_root;
+
+#endif /*__KERNEL__*/
+#endif /*ASM_PARISC_MCKINLEY_H*/
diff --git a/arch/parisc/include/asm/mman.h b/arch/parisc/include/asm/mman.h
new file mode 100644
index 000000000000..defe752cc996
--- /dev/null
+++ b/arch/parisc/include/asm/mman.h
@@ -0,0 +1,61 @@
+#ifndef __PARISC_MMAN_H__
+#define __PARISC_MMAN_H__
+
+#define PROT_READ	0x1		/* page can be read */
+#define PROT_WRITE	0x2		/* page can be written */
+#define PROT_EXEC	0x4		/* page can be executed */
+#define PROT_SEM	0x8		/* page may be used for atomic ops */
+#define PROT_NONE	0x0		/* page can not be accessed */
+#define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
+#define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
+
+#define MAP_SHARED	0x01		/* Share changes */
+#define MAP_PRIVATE	0x02		/* Changes are private */
+#define MAP_TYPE	0x03		/* Mask for type of mapping */
+#define MAP_FIXED	0x04		/* Interpret addr exactly */
+#define MAP_ANONYMOUS	0x10		/* don't use a file */
+
+#define MAP_DENYWRITE	0x0800		/* ETXTBSY */
+#define MAP_EXECUTABLE	0x1000		/* mark it as an executable */
+#define MAP_LOCKED	0x2000		/* pages are locked */
+#define MAP_NORESERVE	0x4000		/* don't check for reservations */
+#define MAP_GROWSDOWN	0x8000		/* stack-like segment */
+#define MAP_POPULATE	0x10000		/* populate (prefault) pagetables */
+#define MAP_NONBLOCK	0x20000		/* do not block on IO */
+
+#define MS_SYNC		1		/* synchronous memory sync */
+#define MS_ASYNC	2		/* sync memory asynchronously */
+#define MS_INVALIDATE	4		/* invalidate the caches */
+
+#define MCL_CURRENT	1		/* lock all current mappings */
+#define MCL_FUTURE	2		/* lock all future mappings */
+
+#define MADV_NORMAL     0               /* no further special treatment */
+#define MADV_RANDOM     1               /* expect random page references */
+#define MADV_SEQUENTIAL 2               /* expect sequential page references */
+#define MADV_WILLNEED   3               /* will need these pages */
+#define MADV_DONTNEED   4               /* don't need these pages */
+#define MADV_SPACEAVAIL 5               /* insure that resources are reserved */
+#define MADV_VPS_PURGE  6               /* Purge pages from VM page cache */
+#define MADV_VPS_INHERIT 7              /* Inherit parents page size */
+
+/* common/generic parameters */
+#define MADV_REMOVE	9		/* remove these pages & resources */
+#define MADV_DONTFORK	10		/* don't inherit across fork */
+#define MADV_DOFORK	11		/* do inherit across fork */
+
+/* The range 12-64 is reserved for page size specification. */
+#define MADV_4K_PAGES   12              /* Use 4K pages  */
+#define MADV_16K_PAGES  14              /* Use 16K pages */
+#define MADV_64K_PAGES  16              /* Use 64K pages */
+#define MADV_256K_PAGES 18              /* Use 256K pages */
+#define MADV_1M_PAGES   20              /* Use 1 Megabyte pages */
+#define MADV_4M_PAGES   22              /* Use 4 Megabyte pages */
+#define MADV_16M_PAGES  24              /* Use 16 Megabyte pages */
+#define MADV_64M_PAGES  26              /* Use 64 Megabyte pages */
+
+/* compatibility flags */
+#define MAP_FILE	0
+#define MAP_VARIABLE	0
+
+#endif /* __PARISC_MMAN_H__ */
diff --git a/arch/parisc/include/asm/mmu.h b/arch/parisc/include/asm/mmu.h
new file mode 100644
index 000000000000..6a310cf8b734
--- /dev/null
+++ b/arch/parisc/include/asm/mmu.h
@@ -0,0 +1,7 @@
+#ifndef _PARISC_MMU_H_
+#define _PARISC_MMU_H_
+
+/* On parisc, we store the space id here */
+typedef unsigned long mm_context_t;
+
+#endif /* _PARISC_MMU_H_ */
diff --git a/arch/parisc/include/asm/mmu_context.h b/arch/parisc/include/asm/mmu_context.h
new file mode 100644
index 000000000000..85856c74ad1d
--- /dev/null
+++ b/arch/parisc/include/asm/mmu_context.h
@@ -0,0 +1,75 @@
+#ifndef __PARISC_MMU_CONTEXT_H
+#define __PARISC_MMU_CONTEXT_H
+
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <asm/atomic.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
+#include <asm-generic/mm_hooks.h>
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+}
+
+/* on PA-RISC, we actually have enough contexts to justify an allocator
+ * for them.  prumpf */
+
+extern unsigned long alloc_sid(void);
+extern void free_sid(unsigned long);
+
+static inline int
+init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+	BUG_ON(atomic_read(&mm->mm_users) != 1);
+
+	mm->context = alloc_sid();
+	return 0;
+}
+
+static inline void
+destroy_context(struct mm_struct *mm)
+{
+	free_sid(mm->context);
+	mm->context = 0;
+}
+
+static inline void load_context(mm_context_t context)
+{
+	mtsp(context, 3);
+#if SPACEID_SHIFT == 0
+	mtctl(context << 1,8);
+#else
+	mtctl(context >> (SPACEID_SHIFT - 1),8);
+#endif
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
+{
+
+	if (prev != next) {
+		mtctl(__pa(next->pgd), 25);
+		load_context(next->context);
+	}
+}
+
+#define deactivate_mm(tsk,mm)	do { } while (0)
+
+static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
+{
+	/*
+	 * Activate_mm is our one chance to allocate a space id
+	 * for a new mm created in the exec path. There's also
+	 * some lazy tlb stuff, which is currently dead code, but
+	 * we only allocate a space id if one hasn't been allocated
+	 * already, so we should be OK.
+	 */
+
+	BUG_ON(next == &init_mm); /* Should never happen */
+
+	if (next->context == 0)
+	    next->context = alloc_sid();
+
+	switch_mm(prev,next,current);
+}
+#endif
diff --git a/arch/parisc/include/asm/mmzone.h b/arch/parisc/include/asm/mmzone.h
new file mode 100644
index 000000000000..9608d2cf214a
--- /dev/null
+++ b/arch/parisc/include/asm/mmzone.h
@@ -0,0 +1,73 @@
+#ifndef _PARISC_MMZONE_H
+#define _PARISC_MMZONE_H
+
+#ifdef CONFIG_DISCONTIGMEM
+
+#define MAX_PHYSMEM_RANGES 8 /* Fix the size for now (current known max is 3) */
+extern int npmem_ranges;
+
+struct node_map_data {
+    pg_data_t pg_data;
+};
+
+extern struct node_map_data node_data[];
+
+#define NODE_DATA(nid)          (&node_data[nid].pg_data)
+
+#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
+#define node_end_pfn(nid)						\
+({									\
+	pg_data_t *__pgdat = NODE_DATA(nid);				\
+	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
+})
+
+/* We have these possible memory map layouts:
+ * Astro: 0-3.75, 67.75-68, 4-64
+ * zx1: 0-1, 257-260, 4-256
+ * Stretch (N-class): 0-2, 4-32, 34-xxx
+ */
+
+/* Since each 1GB can only belong to one region (node), we can create
+ * an index table for pfn to nid lookup; each entry in pfnnid_map 
+ * represents 1GB, and contains the node that the memory belongs to. */
+
+#define PFNNID_SHIFT (30 - PAGE_SHIFT)
+#define PFNNID_MAP_MAX  512     /* support 512GB */
+extern unsigned char pfnnid_map[PFNNID_MAP_MAX];
+
+#ifndef CONFIG_64BIT
+#define pfn_is_io(pfn) ((pfn & (0xf0000000UL >> PAGE_SHIFT)) == (0xf0000000UL >> PAGE_SHIFT))
+#else
+/* io can be 0xf0f0f0f0f0xxxxxx or 0xfffffffff0000000 */
+#define pfn_is_io(pfn) ((pfn & (0xf000000000000000UL >> PAGE_SHIFT)) == (0xf000000000000000UL >> PAGE_SHIFT))
+#endif
+
+static inline int pfn_to_nid(unsigned long pfn)
+{
+	unsigned int i;
+	unsigned char r;
+
+	if (unlikely(pfn_is_io(pfn)))
+		return 0;
+
+	i = pfn >> PFNNID_SHIFT;
+	BUG_ON(i >= sizeof(pfnnid_map) / sizeof(pfnnid_map[0]));
+	r = pfnnid_map[i];
+	BUG_ON(r == 0xff);
+
+	return (int)r;
+}
+
+static inline int pfn_valid(int pfn)
+{
+	int nid = pfn_to_nid(pfn);
+
+	if (nid >= 0)
+		return (pfn < node_end_pfn(nid));
+	return 0;
+}
+
+#else /* !CONFIG_DISCONTIGMEM */
+#define MAX_PHYSMEM_RANGES 	1 
+#endif
+#endif /* _PARISC_MMZONE_H */
diff --git a/arch/parisc/include/asm/module.h b/arch/parisc/include/asm/module.h
new file mode 100644
index 000000000000..c2cb49e934c1
--- /dev/null
+++ b/arch/parisc/include/asm/module.h
@@ -0,0 +1,32 @@
+#ifndef _ASM_PARISC_MODULE_H
+#define _ASM_PARISC_MODULE_H
+/*
+ * This file contains the parisc architecture specific module code.
+ */
+#ifdef CONFIG_64BIT
+#define Elf_Shdr Elf64_Shdr
+#define Elf_Sym Elf64_Sym
+#define Elf_Ehdr Elf64_Ehdr
+#define Elf_Addr Elf64_Addr
+#define Elf_Rela Elf64_Rela
+#else
+#define Elf_Shdr Elf32_Shdr
+#define Elf_Sym Elf32_Sym
+#define Elf_Ehdr Elf32_Ehdr
+#define Elf_Addr Elf32_Addr
+#define Elf_Rela Elf32_Rela
+#endif
+
+struct unwind_table;
+
+struct mod_arch_specific
+{
+	unsigned long got_offset, got_count, got_max;
+	unsigned long fdesc_offset, fdesc_count, fdesc_max;
+	unsigned long stub_offset, stub_count, stub_max;
+	unsigned long init_stub_offset, init_stub_count, init_stub_max;
+	int unwind_section;
+	struct unwind_table *unwind;
+};
+
+#endif /* _ASM_PARISC_MODULE_H */
diff --git a/arch/parisc/include/asm/msgbuf.h b/arch/parisc/include/asm/msgbuf.h
new file mode 100644
index 000000000000..fe88f2649418
--- /dev/null
+++ b/arch/parisc/include/asm/msgbuf.h
@@ -0,0 +1,37 @@
+#ifndef _PARISC_MSGBUF_H
+#define _PARISC_MSGBUF_H
+
+/* 
+ * The msqid64_ds structure for parisc architecture, copied from sparc.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct msqid64_ds {
+	struct ipc64_perm msg_perm;
+#ifndef CONFIG_64BIT
+	unsigned int   __pad1;
+#endif
+	__kernel_time_t msg_stime;	/* last msgsnd time */
+#ifndef CONFIG_64BIT
+	unsigned int   __pad2;
+#endif
+	__kernel_time_t msg_rtime;	/* last msgrcv time */
+#ifndef CONFIG_64BIT
+	unsigned int   __pad3;
+#endif
+	__kernel_time_t msg_ctime;	/* last change time */
+	unsigned int  msg_cbytes;	/* current number of bytes on queue */
+	unsigned int  msg_qnum;	/* number of messages in queue */
+	unsigned int  msg_qbytes;	/* max number of bytes on queue */
+	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
+	__kernel_pid_t msg_lrpid;	/* last receive pid */
+	unsigned int  __unused1;
+	unsigned int  __unused2;
+};
+
+#endif /* _PARISC_MSGBUF_H */
diff --git a/arch/parisc/include/asm/mutex.h b/arch/parisc/include/asm/mutex.h
new file mode 100644
index 000000000000..458c1f7fbc18
--- /dev/null
+++ b/arch/parisc/include/asm/mutex.h
@@ -0,0 +1,9 @@
+/*
+ * Pull in the generic implementation for the mutex fastpath.
+ *
+ * TODO: implement optimized primitives instead, or leave the generic
+ * implementation in place, or pick the atomic_xchg() based generic
+ * implementation. (see asm-generic/mutex-xchg.h for details)
+ */
+
+#include <asm-generic/mutex-dec.h>
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
new file mode 100644
index 000000000000..c3941f09a878
--- /dev/null
+++ b/arch/parisc/include/asm/page.h
@@ -0,0 +1,173 @@
+#ifndef _PARISC_PAGE_H
+#define _PARISC_PAGE_H
+
+#include <linux/const.h>
+
+#if defined(CONFIG_PARISC_PAGE_SIZE_4KB)
+# define PAGE_SHIFT	12
+#elif defined(CONFIG_PARISC_PAGE_SIZE_16KB)
+# define PAGE_SHIFT	14
+#elif defined(CONFIG_PARISC_PAGE_SIZE_64KB)
+# define PAGE_SHIFT	16
+#else
+# error "unknown default kernel page size"
+#endif
+#define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
+#define PAGE_MASK	(~(PAGE_SIZE-1))
+
+
+#ifndef __ASSEMBLY__
+
+#include <asm/types.h>
+#include <asm/cache.h>
+
+#define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
+#define copy_page(to,from)      copy_user_page_asm((void *)(to), (void *)(from))
+
+struct page;
+
+void copy_user_page_asm(void *to, void *from);
+void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
+			   struct page *pg);
+void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
+
+/*
+ * These are used to make use of C type-checking..
+ */
+#define STRICT_MM_TYPECHECKS
+#ifdef STRICT_MM_TYPECHECKS
+typedef struct { unsigned long pte;
+#if !defined(CONFIG_64BIT)
+                 unsigned long future_flags;
+ /* XXX: it's possible to remove future_flags and change BITS_PER_PTE_ENTRY
+	 to 2, but then strangely the identical 32bit kernel boots on a
+	 c3000(pa20), but not any longer on a 715(pa11).
+	 Still investigating... HelgeD.
+  */
+#endif
+} pte_t; /* either 32 or 64bit */
+
+/* NOTE: even on 64 bits, these entries are __u32 because we allocate
+ * the pmd and pgd in ZONE_DMA (i.e. under 4GB) */
+typedef struct { __u32 pmd; } pmd_t;
+typedef struct { __u32 pgd; } pgd_t;
+typedef struct { unsigned long pgprot; } pgprot_t;
+
+#define pte_val(x)	((x).pte)
+/* These do not work lvalues, so make sure we don't use them as such. */
+#define pmd_val(x)	((x).pmd + 0)
+#define pgd_val(x)	((x).pgd + 0)
+#define pgprot_val(x)	((x).pgprot)
+
+#define __pte(x)	((pte_t) { (x) } )
+#define __pmd(x)	((pmd_t) { (x) } )
+#define __pgd(x)	((pgd_t) { (x) } )
+#define __pgprot(x)	((pgprot_t) { (x) } )
+
+#define __pmd_val_set(x,n) (x).pmd = (n)
+#define __pgd_val_set(x,n) (x).pgd = (n)
+
+#else
+/*
+ * .. while these make it easier on the compiler
+ */
+typedef unsigned long pte_t;
+typedef         __u32 pmd_t;
+typedef         __u32 pgd_t;
+typedef unsigned long pgprot_t;
+
+#define pte_val(x)      (x)
+#define pmd_val(x)      (x)
+#define pgd_val(x)      (x)
+#define pgprot_val(x)   (x)
+
+#define __pte(x)        (x)
+#define __pmd(x)	(x)
+#define __pgd(x)        (x)
+#define __pgprot(x)     (x)
+
+#define __pmd_val_set(x,n) (x) = (n)
+#define __pgd_val_set(x,n) (x) = (n)
+
+#endif /* STRICT_MM_TYPECHECKS */
+
+typedef struct page *pgtable_t;
+
+typedef struct __physmem_range {
+	unsigned long start_pfn;
+	unsigned long pages;       /* PAGE_SIZE pages */
+} physmem_range_t;
+
+extern physmem_range_t pmem_ranges[];
+extern int npmem_ranges;
+
+#endif /* !__ASSEMBLY__ */
+
+/* WARNING: The definitions below must match exactly to sizeof(pte_t)
+ * etc
+ */
+#ifdef CONFIG_64BIT
+#define BITS_PER_PTE_ENTRY	3
+#define BITS_PER_PMD_ENTRY	2
+#define BITS_PER_PGD_ENTRY	2
+#else
+#define BITS_PER_PTE_ENTRY	3
+#define BITS_PER_PMD_ENTRY	2
+#define BITS_PER_PGD_ENTRY	BITS_PER_PMD_ENTRY
+#endif
+#define PGD_ENTRY_SIZE	(1UL << BITS_PER_PGD_ENTRY)
+#define PMD_ENTRY_SIZE	(1UL << BITS_PER_PMD_ENTRY)
+#define PTE_ENTRY_SIZE	(1UL << BITS_PER_PTE_ENTRY)
+
+#define LINUX_GATEWAY_SPACE     0
+
+/* This governs the relationship between virtual and physical addresses.
+ * If you alter it, make sure to take care of our various fixed mapping
+ * segments in fixmap.h */
+#ifdef CONFIG_64BIT
+#define __PAGE_OFFSET	(0x40000000)	/* 1GB */
+#else
+#define __PAGE_OFFSET	(0x10000000)	/* 256MB */
+#endif
+
+#define PAGE_OFFSET		((unsigned long)__PAGE_OFFSET)
+
+/* The size of the gateway page (we leave lots of room for expansion) */
+#define GATEWAY_PAGE_SIZE	0x4000
+
+/* The start of the actual kernel binary---used in vmlinux.lds.S
+ * Leave some space after __PAGE_OFFSET for detecting kernel null
+ * ptr derefs */
+#define KERNEL_BINARY_TEXT_START	(__PAGE_OFFSET + 0x100000)
+
+/* These macros don't work for 64-bit C code -- don't allow in C at all */
+#ifdef __ASSEMBLY__
+#   define PA(x)	((x)-__PAGE_OFFSET)
+#   define VA(x)	((x)+__PAGE_OFFSET)
+#endif
+#define __pa(x)			((unsigned long)(x)-PAGE_OFFSET)
+#define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
+
+#ifndef CONFIG_DISCONTIGMEM
+#define pfn_valid(pfn)		((pfn) < max_mapnr)
+#endif /* CONFIG_DISCONTIGMEM */
+
+#ifdef CONFIG_HUGETLB_PAGE
+#define HPAGE_SHIFT		22	/* 4MB (is this fixed?) */
+#define HPAGE_SIZE      	((1UL) << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+#endif
+
+#define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+
+#define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
+#define virt_to_page(kaddr)     pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+
+#define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
+				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/page.h>
+
+#endif /* _PARISC_PAGE_H */
diff --git a/arch/parisc/include/asm/param.h b/arch/parisc/include/asm/param.h
new file mode 100644
index 000000000000..32e03d877858
--- /dev/null
+++ b/arch/parisc/include/asm/param.h
@@ -0,0 +1,22 @@
+#ifndef _ASMPARISC_PARAM_H
+#define _ASMPARISC_PARAM_H
+
+#ifdef __KERNEL__
+#define HZ		CONFIG_HZ
+#define USER_HZ		100		/* some user API use "ticks" */
+#define CLOCKS_PER_SEC	(USER_HZ)	/* like times() */
+#endif
+
+#ifndef HZ
+#define HZ 100
+#endif
+
+#define EXEC_PAGESIZE	4096
+
+#ifndef NOGROUP
+#define NOGROUP		(-1)
+#endif
+
+#define MAXHOSTNAMELEN	64	/* max length of hostname */
+
+#endif
diff --git a/arch/parisc/include/asm/parisc-device.h b/arch/parisc/include/asm/parisc-device.h
new file mode 100644
index 000000000000..7aa13f2add7a
--- /dev/null
+++ b/arch/parisc/include/asm/parisc-device.h
@@ -0,0 +1,64 @@
+#ifndef _ASM_PARISC_PARISC_DEVICE_H_
+#define _ASM_PARISC_PARISC_DEVICE_H_
+
+#include <linux/device.h>
+
+struct parisc_device {
+	struct resource hpa;		/* Hard Physical Address */
+	struct parisc_device_id id;
+	struct parisc_driver *driver;	/* Driver for this device */
+	char		name[80];	/* The hardware description */
+	int		irq;
+	int		aux_irq;	/* Some devices have a second IRQ */
+
+	char		hw_path;        /* The module number on this bus */
+	unsigned int	num_addrs;	/* some devices have additional address ranges. */
+	unsigned long	*addr;          /* which will be stored here */
+ 
+#ifdef CONFIG_64BIT
+	/* parms for pdc_pat_cell_module() call */
+	unsigned long	pcell_loc;	/* Physical Cell location */
+	unsigned long	mod_index;	/* PAT specific - Misc Module info */
+
+	/* generic info returned from pdc_pat_cell_module() */
+	unsigned long	mod_info;	/* PAT specific - Misc Module info */
+	unsigned long	pmod_loc;	/* physical Module location */
+#endif
+	u64		dma_mask;	/* DMA mask for I/O */
+	struct device 	dev;
+};
+
+struct parisc_driver {
+	struct parisc_driver *next;
+	char *name; 
+	const struct parisc_device_id *id_table;
+	int (*probe) (struct parisc_device *dev); /* New device discovered */
+	int (*remove) (struct parisc_device *dev);
+	struct device_driver drv;
+};
+
+
+#define to_parisc_device(d)	container_of(d, struct parisc_device, dev)
+#define to_parisc_driver(d)	container_of(d, struct parisc_driver, drv)
+#define parisc_parent(d)	to_parisc_device(d->dev.parent)
+
+static inline char *parisc_pathname(struct parisc_device *d)
+{
+	return d->dev.bus_id;
+}
+
+static inline void
+parisc_set_drvdata(struct parisc_device *d, void *p)
+{
+	dev_set_drvdata(&d->dev, p);
+}
+
+static inline void *
+parisc_get_drvdata(struct parisc_device *d)
+{
+	return dev_get_drvdata(&d->dev);
+}
+
+extern struct bus_type parisc_bus_type;
+
+#endif /*_ASM_PARISC_PARISC_DEVICE_H_*/
diff --git a/arch/parisc/include/asm/parport.h b/arch/parisc/include/asm/parport.h
new file mode 100644
index 000000000000..00d9cc3e7b97
--- /dev/null
+++ b/arch/parisc/include/asm/parport.h
@@ -0,0 +1,18 @@
+/* 
+ *
+ * parport.h: ia32-compatible parport initialisation
+ *
+ * This file should only be included by drivers/parport/parport_pc.c.
+ */
+#ifndef _ASM_PARPORT_H
+#define _ASM_PARPORT_H 1
+
+
+static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
+{
+	/* nothing ! */
+	return 0;
+}
+
+
+#endif /* !(_ASM_PARPORT_H) */
diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h
new file mode 100644
index 000000000000..4ba868f44a5e
--- /dev/null
+++ b/arch/parisc/include/asm/pci.h
@@ -0,0 +1,294 @@
+#ifndef __ASM_PARISC_PCI_H
+#define __ASM_PARISC_PCI_H
+
+#include <asm/scatterlist.h>
+
+
+
+/*
+** HP PCI platforms generally support multiple bus adapters.
+**    (workstations 1-~4, servers 2-~32)
+**
+** Newer platforms number the busses across PCI bus adapters *sparsely*.
+** E.g. 0, 8, 16, ...
+**
+** Under a PCI bus, most HP platforms support PPBs up to two or three
+** levels deep. See "Bit3" product line. 
+*/
+#define PCI_MAX_BUSSES	256
+
+
+/* To be used as: mdelay(pci_post_reset_delay);
+ *
+ * post_reset is the time the kernel should stall to prevent anyone from
+ * accessing the PCI bus once #RESET is de-asserted. 
+ * PCI spec somewhere says 1 second but with multi-PCI bus systems,
+ * this makes the boot time much longer than necessary.
+ * 20ms seems to work for all the HP PCI implementations to date.
+ */
+#define pci_post_reset_delay 50
+
+
+/*
+** pci_hba_data (aka H2P_OBJECT in HP/UX)
+**
+** This is the "common" or "base" data structure which HBA drivers
+** (eg Dino or LBA) are required to place at the top of their own
+** platform_data structure.  I've heard this called "C inheritance" too.
+**
+** Data needed by pcibios layer belongs here.
+*/
+struct pci_hba_data {
+	void __iomem   *base_addr;	/* aka Host Physical Address */
+	const struct parisc_device *dev; /* device from PA bus walk */
+	struct pci_bus *hba_bus;	/* primary PCI bus below HBA */
+	int		hba_num;	/* I/O port space access "key" */
+	struct resource bus_num;	/* PCI bus numbers */
+	struct resource io_space;	/* PIOP */
+	struct resource lmmio_space;	/* bus addresses < 4Gb */
+	struct resource elmmio_space;	/* additional bus addresses < 4Gb */
+	struct resource gmmio_space;	/* bus addresses > 4Gb */
+
+	/* NOTE: Dino code assumes it can use *all* of the lmmio_space,
+	 * elmmio_space and gmmio_space as a contiguous array of
+	 * resources.  This #define represents the array size */
+	#define DINO_MAX_LMMIO_RESOURCES	3
+
+	unsigned long   lmmio_space_offset;  /* CPU view - PCI view */
+	void *          iommu;          /* IOMMU this device is under */
+	/* REVISIT - spinlock to protect resources? */
+
+	#define HBA_NAME_SIZE 16
+	char io_name[HBA_NAME_SIZE];
+	char lmmio_name[HBA_NAME_SIZE];
+	char elmmio_name[HBA_NAME_SIZE];
+	char gmmio_name[HBA_NAME_SIZE];
+};
+
+#define HBA_DATA(d)		((struct pci_hba_data *) (d))
+
+/* 
+** We support 2^16 I/O ports per HBA.  These are set up in the form
+** 0xbbxxxx, where bb is the bus number and xxxx is the I/O port
+** space address.
+*/
+#define HBA_PORT_SPACE_BITS	16
+
+#define HBA_PORT_BASE(h)	((h) << HBA_PORT_SPACE_BITS)
+#define HBA_PORT_SPACE_SIZE	(1UL << HBA_PORT_SPACE_BITS)
+
+#define PCI_PORT_HBA(a)		((a) >> HBA_PORT_SPACE_BITS)
+#define PCI_PORT_ADDR(a)	((a) & (HBA_PORT_SPACE_SIZE - 1))
+
+#ifdef CONFIG_64BIT
+#define PCI_F_EXTEND		0xffffffff00000000UL
+#define PCI_IS_LMMIO(hba,a)	pci_is_lmmio(hba,a)
+
+/* We need to know if an address is LMMMIO or GMMIO.
+ * LMMIO requires mangling and GMMIO we must use as-is.
+ */
+static __inline__  int pci_is_lmmio(struct pci_hba_data *hba, unsigned long a)
+{
+	return(((a) & PCI_F_EXTEND) == PCI_F_EXTEND);
+}
+
+/*
+** Convert between PCI (IO_VIEW) addresses and processor (PA_VIEW) addresses.
+** See pci.c for more conversions used by Generic PCI code.
+**
+** Platform characteristics/firmware guarantee that
+**	(1) PA_VIEW - IO_VIEW = lmmio_offset for both LMMIO and ELMMIO
+**	(2) PA_VIEW == IO_VIEW for GMMIO
+*/
+#define PCI_BUS_ADDR(hba,a)	(PCI_IS_LMMIO(hba,a)	\
+		?  ((a) - hba->lmmio_space_offset)	/* mangle LMMIO */ \
+		: (a))					/* GMMIO */
+#define PCI_HOST_ADDR(hba,a)	(((a) & PCI_F_EXTEND) == 0 \
+		? (a) + hba->lmmio_space_offset \
+		: (a))
+
+#else	/* !CONFIG_64BIT */
+
+#define PCI_BUS_ADDR(hba,a)	(a)
+#define PCI_HOST_ADDR(hba,a)	(a)
+#define PCI_F_EXTEND		0UL
+#define PCI_IS_LMMIO(hba,a)	(1)	/* 32-bit doesn't support GMMIO */
+
+#endif /* !CONFIG_64BIT */
+
+/*
+** KLUGE: linux/pci.h include asm/pci.h BEFORE declaring struct pci_bus
+** (This eliminates some of the warnings).
+*/
+struct pci_bus;
+struct pci_dev;
+
+/*
+ * If the PCI device's view of memory is the same as the CPU's view of memory,
+ * PCI_DMA_BUS_IS_PHYS is true.  The networking and block device layers use
+ * this boolean for bounce buffer decisions.
+ */
+#ifdef CONFIG_PA20
+/* All PA-2.0 machines have an IOMMU. */
+#define PCI_DMA_BUS_IS_PHYS	0
+#define parisc_has_iommu()	do { } while (0)
+#else
+
+#if defined(CONFIG_IOMMU_CCIO) || defined(CONFIG_IOMMU_SBA)
+extern int parisc_bus_is_phys; 	/* in arch/parisc/kernel/setup.c */
+#define PCI_DMA_BUS_IS_PHYS	parisc_bus_is_phys
+#define parisc_has_iommu()	do { parisc_bus_is_phys = 0; } while (0)
+#else
+#define PCI_DMA_BUS_IS_PHYS	1
+#define parisc_has_iommu()	do { } while (0)
+#endif
+
+#endif	/* !CONFIG_PA20 */
+
+
+/*
+** Most PCI devices (eg Tulip, NCR720) also export the same registers
+** to both MMIO and I/O port space.  Due to poor performance of I/O Port
+** access under HP PCI bus adapters, strongly recommend the use of MMIO
+** address space.
+**
+** While I'm at it more PA programming notes:
+**
+** 1) MMIO stores (writes) are posted operations. This means the processor
+**    gets an "ACK" before the write actually gets to the device. A read
+**    to the same device (or typically the bus adapter above it) will
+**    force in-flight write transaction(s) out to the targeted device
+**    before the read can complete.
+**
+** 2) The Programmed I/O (PIO) data may not always be strongly ordered with
+**    respect to DMA on all platforms. Ie PIO data can reach the processor
+**    before in-flight DMA reaches memory. Since most SMP PA platforms
+**    are I/O coherent, it generally doesn't matter...but sometimes
+**    it does.
+**
+** I've helped device driver writers debug both types of problems.
+*/
+struct pci_port_ops {
+	  u8 (*inb)  (struct pci_hba_data *hba, u16 port);
+	 u16 (*inw)  (struct pci_hba_data *hba, u16 port);
+	 u32 (*inl)  (struct pci_hba_data *hba, u16 port);
+	void (*outb) (struct pci_hba_data *hba, u16 port,  u8 data);
+	void (*outw) (struct pci_hba_data *hba, u16 port, u16 data);
+	void (*outl) (struct pci_hba_data *hba, u16 port, u32 data);
+};
+
+
+struct pci_bios_ops {
+	void (*init)(void);
+	void (*fixup_bus)(struct pci_bus *bus);
+};
+
+/* pci_unmap_{single,page} is not a nop, thus... */
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	\
+	dma_addr_t ADDR_NAME;
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)		\
+	__u32 LEN_NAME;
+#define pci_unmap_addr(PTR, ADDR_NAME)			\
+	((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)		\
+	(((PTR)->ADDR_NAME) = (VAL))
+#define pci_unmap_len(PTR, LEN_NAME)			\
+	((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL)		\
+	(((PTR)->LEN_NAME) = (VAL))
+
+/*
+** Stuff declared in arch/parisc/kernel/pci.c
+*/
+extern struct pci_port_ops *pci_port;
+extern struct pci_bios_ops *pci_bios;
+
+#ifdef CONFIG_PCI
+extern void pcibios_register_hba(struct pci_hba_data *);
+extern void pcibios_set_master(struct pci_dev *);
+#else
+static inline void pcibios_register_hba(struct pci_hba_data *x)
+{
+}
+#endif
+
+/*
+ * pcibios_assign_all_busses() is used in drivers/pci/pci.c:pci_do_scan_bus()
+ *   0 == check if bridge is numbered before re-numbering.
+ *   1 == pci_do_scan_bus() should automatically number all PCI-PCI bridges.
+ *
+ *   We *should* set this to zero for "legacy" platforms and one
+ *   for PAT platforms.
+ *
+ *   But legacy platforms also need to renumber the busses below a Host
+ *   Bus controller.  Adding a 4-port Tulip card on the first PCI root
+ *   bus of a C200 resulted in the secondary bus being numbered as 1.
+ *   The second PCI host bus controller's root bus had already been
+ *   assigned bus number 1 by firmware and sysfs complained.
+ *
+ *   Firmware isn't doing anything wrong here since each controller
+ *   is its own PCI domain.  It's simpler and easier for us to renumber
+ *   the busses rather than treat each Dino as a separate PCI domain.
+ *   Eventually, we may want to introduce PCI domains for Superdome or
+ *   rp7420/8420 boxes and then revisit this issue.
+ */
+#define pcibios_assign_all_busses()     (1)
+#define pcibios_scan_all_fns(a, b)	(0)
+
+#define PCIBIOS_MIN_IO          0x10
+#define PCIBIOS_MIN_MEM         0x1000 /* NBPG - but pci/setup-res.c dies */
+
+/* export the pci_ DMA API in terms of the dma_ one */
+#include <asm-generic/pci-dma-compat.h>
+
+#ifdef CONFIG_PCI
+static inline void pci_dma_burst_advice(struct pci_dev *pdev,
+					enum pci_dma_burst_strategy *strat,
+					unsigned long *strategy_parameter)
+{
+	unsigned long cacheline_size;
+	u8 byte;
+
+	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
+	if (byte == 0)
+		cacheline_size = 1024;
+	else
+		cacheline_size = (int) byte * 4;
+
+	*strat = PCI_DMA_BURST_MULTIPLE;
+	*strategy_parameter = cacheline_size;
+}
+#endif
+
+extern void
+pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
+			 struct resource *res);
+
+extern void
+pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
+			struct pci_bus_region *region);
+
+static inline struct resource *
+pcibios_select_root(struct pci_dev *pdev, struct resource *res)
+{
+	struct resource *root = NULL;
+
+	if (res->flags & IORESOURCE_IO)
+		root = &ioport_resource;
+	if (res->flags & IORESOURCE_MEM)
+		root = &iomem_resource;
+
+	return root;
+}
+
+static inline void pcibios_penalize_isa_irq(int irq, int active)
+{
+	/* We don't need to penalize isa irq's */
+}
+
+static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
+{
+	return channel ? 15 : 14;
+}
+
+#endif /* __ASM_PARISC_PCI_H */
diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h
new file mode 100644
index 000000000000..46b75f9cce51
--- /dev/null
+++ b/arch/parisc/include/asm/pdc.h
@@ -0,0 +1,760 @@
+#ifndef _PARISC_PDC_H
+#define _PARISC_PDC_H
+
+/*
+ *	PDC return values ...
+ *	All PDC calls return a subset of these errors. 
+ */
+
+#define PDC_WARN		  3	/* Call completed with a warning */
+#define PDC_REQ_ERR_1		  2	/* See above			 */
+#define PDC_REQ_ERR_0		  1	/* Call would generate a requestor error */
+#define PDC_OK			  0	/* Call completed successfully	*/
+#define PDC_BAD_PROC		 -1	/* Called non-existent procedure*/
+#define PDC_BAD_OPTION		 -2	/* Called with non-existent option */
+#define PDC_ERROR		 -3	/* Call could not complete without an error */
+#define PDC_NE_MOD		 -5	/* Module not found		*/
+#define PDC_NE_CELL_MOD		 -7	/* Cell module not found	*/
+#define PDC_INVALID_ARG		-10	/* Called with an invalid argument */
+#define PDC_BUS_POW_WARN	-12	/* Call could not complete in allowed power budget */
+#define PDC_NOT_NARROW		-17	/* Narrow mode not supported	*/
+
+/*
+ *	PDC entry points...
+ */
+
+#define PDC_POW_FAIL	1		/* perform a power-fail		*/
+#define PDC_POW_FAIL_PREPARE	0	/* prepare for powerfail	*/
+
+#define PDC_CHASSIS	2		/* PDC-chassis functions	*/
+#define PDC_CHASSIS_DISP	0	/* update chassis display	*/
+#define PDC_CHASSIS_WARN	1	/* return chassis warnings	*/
+#define PDC_CHASSIS_DISPWARN	2	/* update&return chassis status */
+#define PDC_RETURN_CHASSIS_INFO 128	/* HVERSION dependent: return chassis LED/LCD info  */
+
+#define PDC_PIM         3               /* Get PIM data                 */
+#define PDC_PIM_HPMC            0       /* Transfer HPMC data           */
+#define PDC_PIM_RETURN_SIZE     1       /* Get Max buffer needed for PIM*/
+#define PDC_PIM_LPMC            2       /* Transfer HPMC data           */
+#define PDC_PIM_SOFT_BOOT       3       /* Transfer Soft Boot data      */
+#define PDC_PIM_TOC             4       /* Transfer TOC data            */
+
+#define PDC_MODEL	4		/* PDC model information call	*/
+#define PDC_MODEL_INFO		0	/* returns information 		*/
+#define PDC_MODEL_BOOTID	1	/* set the BOOT_ID		*/
+#define PDC_MODEL_VERSIONS	2	/* returns cpu-internal versions*/
+#define PDC_MODEL_SYSMODEL	3	/* return system model info	*/
+#define PDC_MODEL_ENSPEC	4	/* enable specific option	*/
+#define PDC_MODEL_DISPEC	5	/* disable specific option	*/
+#define PDC_MODEL_CPU_ID	6	/* returns cpu-id (only newer machines!) */
+#define PDC_MODEL_CAPABILITIES	7	/* returns OS32/OS64-flags	*/
+/* Values for PDC_MODEL_CAPABILITIES non-equivalent virtual aliasing support */
+#define  PDC_MODEL_IOPDIR_FDC		(1 << 2)
+#define  PDC_MODEL_NVA_MASK		(3 << 4)
+#define  PDC_MODEL_NVA_SUPPORTED	(0 << 4)
+#define  PDC_MODEL_NVA_SLOW		(1 << 4)
+#define  PDC_MODEL_NVA_UNSUPPORTED	(3 << 4)
+#define PDC_MODEL_GET_BOOT__OP	8	/* returns boot test options	*/
+#define PDC_MODEL_SET_BOOT__OP	9	/* set boot test options	*/
+
+#define PA89_INSTRUCTION_SET	0x4	/* capatibilies returned	*/
+#define PA90_INSTRUCTION_SET	0x8
+
+#define PDC_CACHE	5		/* return/set cache (& TLB) info*/
+#define PDC_CACHE_INFO		0	/* returns information 		*/
+#define PDC_CACHE_SET_COH	1	/* set coherence state		*/
+#define PDC_CACHE_RET_SPID	2	/* returns space-ID bits	*/
+
+#define PDC_HPA		6		/* return HPA of processor	*/
+#define PDC_HPA_PROCESSOR	0
+#define PDC_HPA_MODULES		1
+
+#define PDC_COPROC	7		/* Co-Processor (usually FP unit(s)) */
+#define PDC_COPROC_CFG		0	/* Co-Processor Cfg (FP unit(s) enabled?) */
+
+#define PDC_IODC	8		/* talk to IODC			*/
+#define PDC_IODC_READ		0	/* read IODC entry point	*/
+/*      PDC_IODC_RI_			 * INDEX parameter of PDC_IODC_READ */
+#define PDC_IODC_RI_DATA_BYTES	0	/* IODC Data Bytes		*/
+/*				1, 2	   obsolete - HVERSION dependent*/
+#define PDC_IODC_RI_INIT	3	/* Initialize module		*/
+#define PDC_IODC_RI_IO		4	/* Module input/output		*/
+#define PDC_IODC_RI_SPA		5	/* Module input/output		*/
+#define PDC_IODC_RI_CONFIG	6	/* Module input/output		*/
+/*				7	  obsolete - HVERSION dependent */
+#define PDC_IODC_RI_TEST	8	/* Module input/output		*/
+#define PDC_IODC_RI_TLB		9	/* Module input/output		*/
+#define PDC_IODC_NINIT		2	/* non-destructive init		*/
+#define PDC_IODC_DINIT		3	/* destructive init		*/
+#define PDC_IODC_MEMERR		4	/* check for memory errors	*/
+#define PDC_IODC_INDEX_DATA	0	/* get first 16 bytes from mod IODC */
+#define PDC_IODC_BUS_ERROR	-4	/* bus error return value	*/
+#define PDC_IODC_INVALID_INDEX	-5	/* invalid index return value	*/
+#define PDC_IODC_COUNT		-6	/* count is too small		*/
+
+#define PDC_TOD		9		/* time-of-day clock (TOD)	*/
+#define PDC_TOD_READ		0	/* read TOD			*/
+#define PDC_TOD_WRITE		1	/* write TOD			*/
+
+
+#define PDC_STABLE	10		/* stable storage (sprockets)	*/
+#define PDC_STABLE_READ		0
+#define PDC_STABLE_WRITE	1
+#define PDC_STABLE_RETURN_SIZE	2
+#define PDC_STABLE_VERIFY_CONTENTS 3
+#define PDC_STABLE_INITIALIZE	4
+
+#define PDC_NVOLATILE	11		/* often not implemented	*/
+
+#define PDC_ADD_VALID	12		/* Memory validation PDC call	*/
+#define PDC_ADD_VALID_VERIFY	0	/* Make PDC_ADD_VALID verify region */
+
+#define PDC_INSTR	15		/* get instr to invoke PDCE_CHECK() */
+
+#define PDC_PROC	16		/* (sprockets)			*/
+
+#define PDC_CONFIG	16		/* (sprockets)			*/
+#define PDC_CONFIG_DECONFIG	0
+#define PDC_CONFIG_DRECONFIG	1
+#define PDC_CONFIG_DRETURN_CONFIG 2
+
+#define PDC_BLOCK_TLB	18		/* manage hardware block-TLB	*/
+#define PDC_BTLB_INFO		0	/* returns parameter 		*/
+#define PDC_BTLB_INSERT		1	/* insert BTLB entry		*/
+#define PDC_BTLB_PURGE		2	/* purge BTLB entries 		*/
+#define PDC_BTLB_PURGE_ALL	3	/* purge all BTLB entries 	*/
+
+#define PDC_TLB		19		/* manage hardware TLB miss handling */
+#define PDC_TLB_INFO		0	/* returns parameter 		*/
+#define PDC_TLB_SETUP		1	/* set up miss handling 	*/
+
+#define PDC_MEM		20		/* Manage memory		*/
+#define PDC_MEM_MEMINFO		0
+#define PDC_MEM_ADD_PAGE	1
+#define PDC_MEM_CLEAR_PDT	2
+#define PDC_MEM_READ_PDT	3
+#define PDC_MEM_RESET_CLEAR	4
+#define PDC_MEM_GOODMEM		5
+#define PDC_MEM_TABLE		128	/* Non contig mem map (sprockets) */
+#define PDC_MEM_RETURN_ADDRESS_TABLE	PDC_MEM_TABLE
+#define PDC_MEM_GET_MEMORY_SYSTEM_TABLES_SIZE	131
+#define PDC_MEM_GET_MEMORY_SYSTEM_TABLES	132
+#define PDC_MEM_GET_PHYSICAL_LOCATION_FROM_MEMORY_ADDRESS 133
+
+#define PDC_MEM_RET_SBE_REPLACED	5	/* PDC_MEM return values */
+#define PDC_MEM_RET_DUPLICATE_ENTRY	4
+#define PDC_MEM_RET_BUF_SIZE_SMALL	1
+#define PDC_MEM_RET_PDT_FULL		-11
+#define PDC_MEM_RET_INVALID_PHYSICAL_LOCATION ~0ULL
+
+#define PDC_PSW		21		/* Get/Set default System Mask  */
+#define PDC_PSW_MASK		0	/* Return mask                  */
+#define PDC_PSW_GET_DEFAULTS	1	/* Return defaults              */
+#define PDC_PSW_SET_DEFAULTS	2	/* Set default                  */
+#define PDC_PSW_ENDIAN_BIT	1	/* set for big endian           */
+#define PDC_PSW_WIDE_BIT	2	/* set for wide mode            */ 
+
+#define PDC_SYSTEM_MAP	22		/* find system modules		*/
+#define PDC_FIND_MODULE 	0
+#define PDC_FIND_ADDRESS	1
+#define PDC_TRANSLATE_PATH	2
+
+#define PDC_SOFT_POWER	23		/* soft power switch		*/
+#define PDC_SOFT_POWER_INFO	0	/* return info about the soft power switch */
+#define PDC_SOFT_POWER_ENABLE	1	/* enable/disable soft power switch */
+
+
+/* HVERSION dependent */
+
+/* The PDC_MEM_MAP calls */
+#define PDC_MEM_MAP	128		/* on s700: return page info	*/
+#define PDC_MEM_MAP_HPA		0	/* returns hpa of a module	*/
+
+#define PDC_EEPROM	129		/* EEPROM access		*/
+#define PDC_EEPROM_READ_WORD	0
+#define PDC_EEPROM_WRITE_WORD	1
+#define PDC_EEPROM_READ_BYTE	2
+#define PDC_EEPROM_WRITE_BYTE	3
+#define PDC_EEPROM_EEPROM_PASSWORD -1000
+
+#define PDC_NVM		130		/* NVM (non-volatile memory) access */
+#define PDC_NVM_READ_WORD	0
+#define PDC_NVM_WRITE_WORD	1
+#define PDC_NVM_READ_BYTE	2
+#define PDC_NVM_WRITE_BYTE	3
+
+#define PDC_SEED_ERROR	132		/* (sprockets)			*/
+
+#define PDC_IO		135		/* log error info, reset IO system */
+#define PDC_IO_READ_AND_CLEAR_ERRORS	0
+#define PDC_IO_RESET			1
+#define PDC_IO_RESET_DEVICES		2
+/* sets bits 6&7 (little endian) of the HcControl Register */
+#define PDC_IO_USB_SUSPEND	0xC000000000000000
+#define PDC_IO_EEPROM_IO_ERR_TABLE_FULL	-5	/* return value */
+#define PDC_IO_NO_SUSPEND		-6	/* return value */
+
+#define PDC_BROADCAST_RESET 136		/* reset all processors		*/
+#define PDC_DO_RESET		0	/* option: perform a broadcast reset */
+#define PDC_DO_FIRM_TEST_RESET	1	/* Do broadcast reset with bitmap */
+#define PDC_BR_RECONFIGURATION	2	/* reset w/reconfiguration	*/
+#define PDC_FIRM_TEST_MAGIC	0xab9ec36fUL    /* for this reboot only	*/
+
+#define PDC_LAN_STATION_ID 138		/* Hversion dependent mechanism for */
+#define PDC_LAN_STATION_ID_READ	0	/* getting the lan station address  */
+
+#define	PDC_LAN_STATION_ID_SIZE	6
+
+#define PDC_CHECK_RANGES 139		/* (sprockets)			*/
+
+#define PDC_NV_SECTIONS	141		/* (sprockets)			*/
+
+#define PDC_PERFORMANCE	142		/* performance monitoring	*/
+
+#define PDC_SYSTEM_INFO	143		/* system information		*/
+#define PDC_SYSINFO_RETURN_INFO_SIZE	0
+#define PDC_SYSINFO_RRETURN_SYS_INFO	1
+#define PDC_SYSINFO_RRETURN_ERRORS	2
+#define PDC_SYSINFO_RRETURN_WARNINGS	3
+#define PDC_SYSINFO_RETURN_REVISIONS	4
+#define PDC_SYSINFO_RRETURN_DIAGNOSE	5
+#define PDC_SYSINFO_RRETURN_HV_DIAGNOSE	1005
+
+#define PDC_RDR		144		/* (sprockets)			*/
+#define PDC_RDR_READ_BUFFER	0
+#define PDC_RDR_READ_SINGLE	1
+#define PDC_RDR_WRITE_SINGLE	2
+
+#define PDC_INTRIGUE	145 		/* (sprockets)			*/
+#define PDC_INTRIGUE_WRITE_BUFFER 	 0
+#define PDC_INTRIGUE_GET_SCRATCH_BUFSIZE 1
+#define PDC_INTRIGUE_START_CPU_COUNTERS	 2
+#define PDC_INTRIGUE_STOP_CPU_COUNTERS	 3
+
+#define PDC_STI		146 		/* STI access			*/
+/* same as PDC_PCI_XXX values (see below) */
+
+/* Legacy PDC definitions for same stuff */
+#define PDC_PCI_INDEX	147
+#define PDC_PCI_INTERFACE_INFO		0
+#define PDC_PCI_SLOT_INFO		1
+#define PDC_PCI_INFLIGHT_BYTES		2
+#define PDC_PCI_READ_CONFIG		3
+#define PDC_PCI_WRITE_CONFIG		4
+#define PDC_PCI_READ_PCI_IO		5
+#define PDC_PCI_WRITE_PCI_IO		6
+#define PDC_PCI_READ_CONFIG_DELAY	7
+#define PDC_PCI_UPDATE_CONFIG_DELAY	8
+#define PDC_PCI_PCI_PATH_TO_PCI_HPA	9
+#define PDC_PCI_PCI_HPA_TO_PCI_PATH	10
+#define PDC_PCI_PCI_PATH_TO_PCI_BUS	11
+#define PDC_PCI_PCI_RESERVED		12
+#define PDC_PCI_PCI_INT_ROUTE_SIZE	13
+#define PDC_PCI_GET_INT_TBL_SIZE	PDC_PCI_PCI_INT_ROUTE_SIZE
+#define PDC_PCI_PCI_INT_ROUTE		14
+#define PDC_PCI_GET_INT_TBL		PDC_PCI_PCI_INT_ROUTE 
+#define PDC_PCI_READ_MON_TYPE		15
+#define PDC_PCI_WRITE_MON_TYPE		16
+
+
+/* Get SCSI Interface Card info:  SDTR, SCSI ID, mode (SE vs LVD) */
+#define PDC_INITIATOR	163
+#define PDC_GET_INITIATOR	0
+#define PDC_SET_INITIATOR	1
+#define PDC_DELETE_INITIATOR	2
+#define PDC_RETURN_TABLE_SIZE	3
+#define PDC_RETURN_TABLE	4
+
+#define PDC_LINK	165 		/* (sprockets)			*/
+#define PDC_LINK_PCI_ENTRY_POINTS	0  /* list (Arg1) = 0 */
+#define PDC_LINK_USB_ENTRY_POINTS	1  /* list (Arg1) = 1 */
+
+/* cl_class
+ * page 3-33 of IO-Firmware ARS
+ * IODC ENTRY_INIT(Search first) RET[1]
+ */
+#define	CL_NULL		0	/* invalid */
+#define	CL_RANDOM	1	/* random access (as disk) */
+#define	CL_SEQU		2	/* sequential access (as tape) */
+#define	CL_DUPLEX	7	/* full-duplex point-to-point (RS-232, Net) */
+#define	CL_KEYBD	8	/* half-duplex console (HIL Keyboard) */
+#define	CL_DISPL	9	/* half-duplex console (display) */
+#define	CL_FC		10	/* FiberChannel access media */
+
+/* IODC ENTRY_INIT() */
+#define ENTRY_INIT_SRCH_FRST	2
+#define ENTRY_INIT_SRCH_NEXT	3
+#define ENTRY_INIT_MOD_DEV	4
+#define ENTRY_INIT_DEV		5
+#define ENTRY_INIT_MOD		6
+#define ENTRY_INIT_MSG		9
+
+/* IODC ENTRY_IO() */
+#define ENTRY_IO_BOOTIN		0
+#define ENTRY_IO_BOOTOUT	1
+#define ENTRY_IO_CIN		2
+#define ENTRY_IO_COUT		3
+#define ENTRY_IO_CLOSE		4
+#define ENTRY_IO_GETMSG		9
+#define ENTRY_IO_BBLOCK_IN	16
+#define ENTRY_IO_BBLOCK_OUT	17
+
+/* IODC ENTRY_SPA() */
+
+/* IODC ENTRY_CONFIG() */
+
+/* IODC ENTRY_TEST() */
+
+/* IODC ENTRY_TLB() */
+
+/* constants for OS (NVM...) */
+#define OS_ID_NONE		0	/* Undefined OS ID	*/
+#define OS_ID_HPUX		1	/* HP-UX OS		*/
+#define OS_ID_MPEXL		2	/* MPE XL OS		*/
+#define OS_ID_OSF		3	/* OSF OS		*/
+#define OS_ID_HPRT		4	/* HP-RT OS		*/
+#define OS_ID_NOVEL		5	/* NOVELL OS		*/
+#define OS_ID_LINUX		6	/* Linux		*/
+
+
+/* constants for PDC_CHASSIS */
+#define OSTAT_OFF		0
+#define OSTAT_FLT		1 
+#define OSTAT_TEST		2
+#define OSTAT_INIT		3
+#define OSTAT_SHUT		4
+#define OSTAT_WARN		5
+#define OSTAT_RUN		6
+#define OSTAT_ON		7
+
+/* Page Zero constant offsets used by the HPMC handler */
+#define BOOT_CONSOLE_HPA_OFFSET  0x3c0
+#define BOOT_CONSOLE_SPA_OFFSET  0x3c4
+#define BOOT_CONSOLE_PATH_OFFSET 0x3a8
+
+/* size of the pdc_result buffer for firmware.c */
+#define NUM_PDC_RESULT	32
+
+#if !defined(__ASSEMBLY__)
+#ifdef __KERNEL__
+
+#include <linux/types.h>
+
+extern int pdc_type;
+
+/* Values for pdc_type */
+#define PDC_TYPE_ILLEGAL	-1
+#define PDC_TYPE_PAT		 0 /* 64-bit PAT-PDC */
+#define PDC_TYPE_SYSTEM_MAP	 1 /* 32-bit, but supports PDC_SYSTEM_MAP */
+#define PDC_TYPE_SNAKE		 2 /* Doesn't support SYSTEM_MAP */
+
+struct pdc_chassis_info {       /* for PDC_CHASSIS_INFO */
+	unsigned long actcnt;   /* actual number of bytes returned */
+	unsigned long maxcnt;   /* maximum number of bytes that could be returned */
+};
+
+struct pdc_coproc_cfg {         /* for PDC_COPROC_CFG */
+        unsigned long ccr_functional;
+        unsigned long ccr_present;
+        unsigned long revision;
+        unsigned long model;
+};
+
+struct pdc_model {		/* for PDC_MODEL */
+	unsigned long hversion;
+	unsigned long sversion;
+	unsigned long hw_id;
+	unsigned long boot_id;
+	unsigned long sw_id;
+	unsigned long sw_cap;
+	unsigned long arch_rev;
+	unsigned long pot_key;
+	unsigned long curr_key;
+};
+
+struct pdc_cache_cf {		/* for PDC_CACHE  (I/D-caches) */
+    unsigned long
+#ifdef CONFIG_64BIT
+		cc_padW:32,
+#endif
+		cc_alias: 4,	/* alias boundaries for virtual addresses   */
+		cc_block: 4,	/* to determine most efficient stride */
+		cc_line	: 3,	/* maximum amount written back as a result of store (multiple of 16 bytes) */
+		cc_shift: 2,	/* how much to shift cc_block left */
+		cc_wt	: 1,	/* 0 = WT-Dcache, 1 = WB-Dcache */
+		cc_sh	: 2,	/* 0 = separate I/D-cache, else shared I/D-cache */
+		cc_cst  : 3,	/* 0 = incoherent D-cache, 1=coherent D-cache */
+		cc_pad1 : 10,	/* reserved */
+		cc_hv   : 3;	/* hversion dependent */
+};
+
+struct pdc_tlb_cf {		/* for PDC_CACHE (I/D-TLB's) */
+    unsigned long tc_pad0:12,	/* reserved */
+#ifdef CONFIG_64BIT
+		tc_padW:32,
+#endif
+		tc_sh	: 2,	/* 0 = separate I/D-TLB, else shared I/D-TLB */
+		tc_hv   : 1,	/* HV */
+		tc_page : 1,	/* 0 = 2K page-size-machine, 1 = 4k page size */
+		tc_cst  : 3,	/* 0 = incoherent operations, else coherent operations */
+		tc_aid  : 5,	/* ITLB: width of access ids of processor (encoded!) */
+		tc_pad1 : 8;	/* ITLB: width of space-registers (encoded) */
+};
+
+struct pdc_cache_info {		/* main-PDC_CACHE-structure (caches & TLB's) */
+	/* I-cache */
+	unsigned long	ic_size;	/* size in bytes */
+	struct pdc_cache_cf ic_conf;	/* configuration */
+	unsigned long	ic_base;	/* base-addr */
+	unsigned long	ic_stride;
+	unsigned long	ic_count;
+	unsigned long	ic_loop;
+	/* D-cache */
+	unsigned long	dc_size;	/* size in bytes */
+	struct pdc_cache_cf dc_conf;	/* configuration */
+	unsigned long	dc_base;	/* base-addr */
+	unsigned long	dc_stride;
+	unsigned long	dc_count;
+	unsigned long	dc_loop;
+	/* Instruction-TLB */
+	unsigned long	it_size;	/* number of entries in I-TLB */
+	struct pdc_tlb_cf it_conf;	/* I-TLB-configuration */
+	unsigned long	it_sp_base;
+	unsigned long	it_sp_stride;
+	unsigned long	it_sp_count;
+	unsigned long	it_off_base;
+	unsigned long	it_off_stride;
+	unsigned long	it_off_count;
+	unsigned long	it_loop;
+	/* data-TLB */
+	unsigned long	dt_size;	/* number of entries in D-TLB */
+	struct pdc_tlb_cf dt_conf;	/* D-TLB-configuration */
+	unsigned long	dt_sp_base;
+	unsigned long	dt_sp_stride;
+	unsigned long	dt_sp_count;
+	unsigned long	dt_off_base;
+	unsigned long	dt_off_stride;
+	unsigned long	dt_off_count;
+	unsigned long	dt_loop;
+};
+
+#if 0
+/* If you start using the next struct, you'll have to adjust it to
+ * work with 64-bit firmware I think -PB
+ */
+struct pdc_iodc {     /* PDC_IODC */
+	unsigned char   hversion_model;
+	unsigned char 	hversion;
+	unsigned char 	spa;
+	unsigned char 	type;
+	unsigned int	sversion_rev:4;
+	unsigned int	sversion_model:19;
+	unsigned int	sversion_opt:8;
+	unsigned char	rev;
+	unsigned char	dep;
+	unsigned char	features;
+	unsigned char	pad1;
+	unsigned int	checksum:16;
+	unsigned int	length:16;
+	unsigned int    pad[15];
+} __attribute__((aligned(8))) ;
+#endif
+
+#ifndef CONFIG_PA20
+/* no BLTBs in pa2.0 processors */
+struct pdc_btlb_info_range {
+	__u8 res00;
+	__u8 num_i;
+	__u8 num_d;
+	__u8 num_comb;
+};
+
+struct pdc_btlb_info {	/* PDC_BLOCK_TLB, return of PDC_BTLB_INFO */
+	unsigned int min_size;	/* minimum size of BTLB in pages */
+	unsigned int max_size;	/* maximum size of BTLB in pages */
+	struct pdc_btlb_info_range fixed_range_info;
+	struct pdc_btlb_info_range variable_range_info;
+};
+
+#endif /* !CONFIG_PA20 */
+
+#ifdef CONFIG_64BIT
+struct pdc_memory_table_raddr { /* PDC_MEM/PDC_MEM_TABLE (return info) */
+	unsigned long entries_returned;
+	unsigned long entries_total;
+};
+
+struct pdc_memory_table {       /* PDC_MEM/PDC_MEM_TABLE (arguments) */
+	unsigned long paddr;
+	unsigned int  pages;
+	unsigned int  reserved;
+};
+#endif /* CONFIG_64BIT */
+
+struct pdc_system_map_mod_info { /* PDC_SYSTEM_MAP/FIND_MODULE */
+	unsigned long mod_addr;
+	unsigned long mod_pgs;
+	unsigned long add_addrs;
+};
+
+struct pdc_system_map_addr_info { /* PDC_SYSTEM_MAP/FIND_ADDRESS */
+	unsigned long mod_addr;
+	unsigned long mod_pgs;
+};
+
+struct pdc_initiator { /* PDC_INITIATOR */
+	int host_id;
+	int factor;
+	int width;
+	int mode;
+};
+
+struct hardware_path {
+	char  flags;	/* see bit definitions below */
+	char  bc[6];	/* Bus Converter routing info to a specific */
+			/* I/O adaptor (< 0 means none, > 63 resvd) */
+	char  mod;	/* fixed field of specified module */
+};
+
+/*
+ * Device path specifications used by PDC.
+ */
+struct pdc_module_path {
+	struct hardware_path path;
+	unsigned int layers[6]; /* device-specific info (ctlr #, unit # ...) */
+};
+
+#ifndef CONFIG_PA20
+/* Only used on some pre-PA2.0 boxes */
+struct pdc_memory_map {		/* PDC_MEMORY_MAP */
+	unsigned long hpa;	/* mod's register set address */
+	unsigned long more_pgs;	/* number of additional I/O pgs */
+};
+#endif
+
+struct pdc_tod {
+	unsigned long tod_sec; 
+	unsigned long tod_usec;
+};
+
+/* architected results from PDC_PIM/transfer hpmc on a PA1.1 machine */
+
+struct pdc_hpmc_pim_11 { /* PDC_PIM */
+	__u32 gr[32];
+	__u32 cr[32];
+	__u32 sr[8];
+	__u32 iasq_back;
+	__u32 iaoq_back;
+	__u32 check_type;
+	__u32 cpu_state;
+	__u32 rsvd1;
+	__u32 cache_check;
+	__u32 tlb_check;
+	__u32 bus_check;
+	__u32 assists_check;
+	__u32 rsvd2;
+	__u32 assist_state;
+	__u32 responder_addr;
+	__u32 requestor_addr;
+	__u32 path_info;
+	__u64 fr[32];
+};
+
+/*
+ * architected results from PDC_PIM/transfer hpmc on a PA2.0 machine
+ *
+ * Note that PDC_PIM doesn't care whether or not wide mode was enabled
+ * so the results are different on  PA1.1 vs. PA2.0 when in narrow mode.
+ *
+ * Note also that there are unarchitected results available, which
+ * are hversion dependent. Do a "ser pim 0 hpmc" after rebooting, since
+ * the firmware is probably the best way of printing hversion dependent
+ * data.
+ */
+
+struct pdc_hpmc_pim_20 { /* PDC_PIM */
+	__u64 gr[32];
+	__u64 cr[32];
+	__u64 sr[8];
+	__u64 iasq_back;
+	__u64 iaoq_back;
+	__u32 check_type;
+	__u32 cpu_state;
+	__u32 cache_check;
+	__u32 tlb_check;
+	__u32 bus_check;
+	__u32 assists_check;
+	__u32 assist_state;
+	__u32 path_info;
+	__u64 responder_addr;
+	__u64 requestor_addr;
+	__u64 fr[32];
+};
+
+void pdc_console_init(void);	/* in pdc_console.c */
+void pdc_console_restart(void);
+
+void setup_pdc(void);		/* in inventory.c */
+
+/* wrapper-functions from pdc.c */
+
+int pdc_add_valid(unsigned long address);
+int pdc_chassis_info(struct pdc_chassis_info *chassis_info, void *led_info, unsigned long len);
+int pdc_chassis_disp(unsigned long disp);
+int pdc_chassis_warn(unsigned long *warn);
+int pdc_coproc_cfg(struct pdc_coproc_cfg *pdc_coproc_info);
+int pdc_iodc_read(unsigned long *actcnt, unsigned long hpa, unsigned int index,
+		  void *iodc_data, unsigned int iodc_data_size);
+int pdc_system_map_find_mods(struct pdc_system_map_mod_info *pdc_mod_info,
+			     struct pdc_module_path *mod_path, long mod_index);
+int pdc_system_map_find_addrs(struct pdc_system_map_addr_info *pdc_addr_info,
+			      long mod_index, long addr_index);
+int pdc_model_info(struct pdc_model *model);
+int pdc_model_sysmodel(char *name);
+int pdc_model_cpuid(unsigned long *cpu_id);
+int pdc_model_versions(unsigned long *versions, int id);
+int pdc_model_capabilities(unsigned long *capabilities);
+int pdc_cache_info(struct pdc_cache_info *cache);
+int pdc_spaceid_bits(unsigned long *space_bits);
+#ifndef CONFIG_PA20
+int pdc_btlb_info(struct pdc_btlb_info *btlb);
+int pdc_mem_map_hpa(struct pdc_memory_map *r_addr, struct pdc_module_path *mod_path);
+#endif /* !CONFIG_PA20 */
+int pdc_lan_station_id(char *lan_addr, unsigned long net_hpa);
+
+int pdc_stable_read(unsigned long staddr, void *memaddr, unsigned long count);
+int pdc_stable_write(unsigned long staddr, void *memaddr, unsigned long count);
+int pdc_stable_get_size(unsigned long *size);
+int pdc_stable_verify_contents(void);
+int pdc_stable_initialize(void);
+
+int pdc_pci_irt_size(unsigned long *num_entries, unsigned long hpa);
+int pdc_pci_irt(unsigned long num_entries, unsigned long hpa, void *tbl);
+
+int pdc_get_initiator(struct hardware_path *, struct pdc_initiator *);
+int pdc_tod_read(struct pdc_tod *tod);
+int pdc_tod_set(unsigned long sec, unsigned long usec);
+
+#ifdef CONFIG_64BIT
+int pdc_mem_mem_table(struct pdc_memory_table_raddr *r_addr,
+		struct pdc_memory_table *tbl, unsigned long entries);
+#endif
+
+void set_firmware_width(void);
+int pdc_do_firm_test_reset(unsigned long ftc_bitmap);
+int pdc_do_reset(void);
+int pdc_soft_power_info(unsigned long *power_reg);
+int pdc_soft_power_button(int sw_control);
+void pdc_io_reset(void);
+void pdc_io_reset_devices(void);
+int pdc_iodc_getc(void);
+int pdc_iodc_print(const unsigned char *str, unsigned count);
+
+void pdc_emergency_unlock(void);
+int pdc_sti_call(unsigned long func, unsigned long flags,
+                 unsigned long inptr, unsigned long outputr,
+                 unsigned long glob_cfg);
+
+static inline char * os_id_to_string(u16 os_id) {
+	switch(os_id) {
+	case OS_ID_NONE:	return "No OS";
+	case OS_ID_HPUX:	return "HP-UX";
+	case OS_ID_MPEXL:	return "MPE-iX";
+	case OS_ID_OSF:		return "OSF";
+	case OS_ID_HPRT:	return "HP-RT";
+	case OS_ID_NOVEL:	return "Novell Netware";
+	case OS_ID_LINUX:	return "Linux";
+	default:	return "Unknown";
+	}
+}
+
+#endif /* __KERNEL__ */
+
+#define PAGE0   ((struct zeropage *)__PAGE_OFFSET)
+
+/* DEFINITION OF THE ZERO-PAGE (PAG0) */
+/* based on work by Jason Eckhardt (jason@equator.com) */
+
+/* flags of the device_path */
+#define	PF_AUTOBOOT	0x80
+#define	PF_AUTOSEARCH	0x40
+#define	PF_TIMER	0x0F
+
+struct device_path {		/* page 1-69 */
+	unsigned char flags;	/* flags see above! */
+	unsigned char bc[6];	/* bus converter routing info */
+	unsigned char mod;
+	unsigned int  layers[6];/* device-specific layer-info */
+} __attribute__((aligned(8))) ;
+
+struct pz_device {
+	struct	device_path dp;	/* see above */
+	/* struct	iomod *hpa; */
+	unsigned int hpa;	/* HPA base address */
+	/* char	*spa; */
+	unsigned int spa;	/* SPA base address */
+	/* int	(*iodc_io)(struct iomod*, ...); */
+	unsigned int iodc_io;	/* device entry point */
+	short	pad;		/* reserved */
+	unsigned short cl_class;/* see below */
+} __attribute__((aligned(8))) ;
+
+struct zeropage {
+	/* [0x000] initialize vectors (VEC) */
+	unsigned int	vec_special;		/* must be zero */
+	/* int	(*vec_pow_fail)(void);*/
+	unsigned int	vec_pow_fail; /* power failure handler */
+	/* int	(*vec_toc)(void); */
+	unsigned int	vec_toc;
+	unsigned int	vec_toclen;
+	/* int	(*vec_rendz)(void); */
+	unsigned int vec_rendz;
+	int	vec_pow_fail_flen;
+	int	vec_pad[10];		
+	
+	/* [0x040] reserved processor dependent */
+	int	pad0[112];
+
+	/* [0x200] reserved */
+	int	pad1[84];
+
+	/* [0x350] memory configuration (MC) */
+	int	memc_cont;		/* contiguous mem size (bytes) */
+	int	memc_phsize;		/* physical memory size */
+	int	memc_adsize;		/* additional mem size, bytes of SPA space used by PDC */
+	unsigned int mem_pdc_hi;	/* used for 64-bit */
+
+	/* [0x360] various parameters for the boot-CPU */
+	/* unsigned int *mem_booterr[8]; */
+	unsigned int mem_booterr[8];	/* ptr to boot errors */
+	unsigned int mem_free;		/* first location, where OS can be loaded */
+	/* struct iomod *mem_hpa; */
+	unsigned int mem_hpa;		/* HPA of the boot-CPU */
+	/* int (*mem_pdc)(int, ...); */
+	unsigned int mem_pdc;		/* PDC entry point */
+	unsigned int mem_10msec;	/* number of clock ticks in 10msec */
+
+	/* [0x390] initial memory module (IMM) */
+	/* struct iomod *imm_hpa; */
+	unsigned int imm_hpa;		/* HPA of the IMM */
+	int	imm_soft_boot;		/* 0 = was hard boot, 1 = was soft boot */
+	unsigned int	imm_spa_size;		/* SPA size of the IMM in bytes */
+	unsigned int	imm_max_mem;		/* bytes of mem in IMM */
+
+	/* [0x3A0] boot console, display device and keyboard */
+	struct pz_device mem_cons;	/* description of console device */
+	struct pz_device mem_boot;	/* description of boot device */
+	struct pz_device mem_kbd;	/* description of keyboard device */
+
+	/* [0x430] reserved */
+	int	pad430[116];
+
+	/* [0x600] processor dependent */
+	__u32	pad600[1];
+	__u32	proc_sti;		/* pointer to STI ROM */
+	__u32	pad608[126];
+};
+
+#endif /* !defined(__ASSEMBLY__) */
+
+#endif /* _PARISC_PDC_H */
diff --git a/arch/parisc/include/asm/pdc_chassis.h b/arch/parisc/include/asm/pdc_chassis.h
new file mode 100644
index 000000000000..a609273dc6bf
--- /dev/null
+++ b/arch/parisc/include/asm/pdc_chassis.h
@@ -0,0 +1,381 @@
+/*
+ *	include/asm-parisc/pdc_chassis.h
+ *
+ *	Copyright (C) 2002 Laurent Canet <canetl@esiee.fr>
+ *	Copyright (C) 2002 Thibaut Varene <varenet@parisc-linux.org>
+ *
+ *
+ *      This program is free software; you can redistribute it and/or modify
+ *      it under the terms of the GNU General Public License, version 2, as
+ *      published by the Free Software Foundation.
+ *      
+ *      This program is distributed in the hope that it will be useful,
+ *      but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *      MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *      GNU General Public License for more details.
+ *      
+ *      You should have received a copy of the GNU General Public License
+ *      along with this program; if not, write to the Free Software
+ *      Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ *      TODO:	- handle processor number on SMP systems (Reporting Entity ID)
+ *      	- handle message ID
+ *      	- handle timestamps
+ */
+ 
+
+#ifndef _PARISC_PDC_CHASSIS_H
+#define _PARISC_PDC_CHASSIS_H
+
+/*
+ * ----------
+ * Prototypes
+ * ----------
+ */
+
+int pdc_chassis_send_status(int message);
+void parisc_pdc_chassis_init(void);
+
+
+/*
+ * -----------------
+ * Direct call names
+ * -----------------
+ * They setup everything for you, the Log message and the corresponding LED state
+ */
+
+#define PDC_CHASSIS_DIRECT_BSTART	0
+#define PDC_CHASSIS_DIRECT_BCOMPLETE	1
+#define PDC_CHASSIS_DIRECT_SHUTDOWN	2
+#define PDC_CHASSIS_DIRECT_PANIC	3
+#define PDC_CHASSIS_DIRECT_HPMC		4
+#define PDC_CHASSIS_DIRECT_LPMC		5
+#define PDC_CHASSIS_DIRECT_DUMP		6	/* not yet implemented */
+#define PDC_CHASSIS_DIRECT_OOPS		7	/* not yet implemented */
+
+
+/*
+ * ------------
+ * LEDs control
+ * ------------
+ * Set the three LEDs -- Run, Attn, and Fault.
+ */
+
+/* Old PDC LED control */
+#define PDC_CHASSIS_DISP_DATA(v)	((unsigned long)(v) << 17)
+
+/* 
+ * Available PDC PAT LED states
+ */
+
+#define PDC_CHASSIS_LED_RUN_OFF		(0ULL << 4)
+#define PDC_CHASSIS_LED_RUN_FLASH	(1ULL << 4)
+#define PDC_CHASSIS_LED_RUN_ON		(2ULL << 4)
+#define PDC_CHASSIS_LED_RUN_NC		(3ULL << 4)
+#define PDC_CHASSIS_LED_ATTN_OFF	(0ULL << 6)
+#define PDC_CHASSIS_LED_ATTN_FLASH	(1ULL << 6)
+#define PDC_CHASSIS_LED_ATTN_NC		(3ULL << 6)	/* ATTN ON is invalid */
+#define PDC_CHASSIS_LED_FAULT_OFF	(0ULL << 8)
+#define PDC_CHASSIS_LED_FAULT_FLASH	(1ULL << 8)
+#define PDC_CHASSIS_LED_FAULT_ON	(2ULL << 8)
+#define PDC_CHASSIS_LED_FAULT_NC	(3ULL << 8)
+#define PDC_CHASSIS_LED_VALID		(1ULL << 10)
+
+/* 
+ * Valid PDC PAT LED states combinations
+ */
+
+/* System running normally */
+#define PDC_CHASSIS_LSTATE_RUN_NORMAL	(PDC_CHASSIS_LED_RUN_ON		| \
+					 PDC_CHASSIS_LED_ATTN_OFF	| \
+					 PDC_CHASSIS_LED_FAULT_OFF	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* System crashed and rebooted itself successfully */
+#define PDC_CHASSIS_LSTATE_RUN_CRASHREC	(PDC_CHASSIS_LED_RUN_ON		| \
+					 PDC_CHASSIS_LED_ATTN_OFF	| \
+					 PDC_CHASSIS_LED_FAULT_FLASH	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* There was a system interruption that did not take the system down */
+#define PDC_CHASSIS_LSTATE_RUN_SYSINT	(PDC_CHASSIS_LED_RUN_ON		| \
+					 PDC_CHASSIS_LED_ATTN_FLASH	| \
+					 PDC_CHASSIS_LED_FAULT_OFF	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* System running and unexpected reboot or non-critical error detected */
+#define PDC_CHASSIS_LSTATE_RUN_NCRIT	(PDC_CHASSIS_LED_RUN_ON		| \
+					 PDC_CHASSIS_LED_ATTN_FLASH	| \
+					 PDC_CHASSIS_LED_FAULT_FLASH	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* Executing non-OS code */
+#define PDC_CHASSIS_LSTATE_NONOS	(PDC_CHASSIS_LED_RUN_FLASH	| \
+					 PDC_CHASSIS_LED_ATTN_OFF	| \
+					 PDC_CHASSIS_LED_FAULT_OFF	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* Boot failed - Executing non-OS code */
+#define PDC_CHASSIS_LSTATE_NONOS_BFAIL	(PDC_CHASSIS_LED_RUN_FLASH	| \
+					 PDC_CHASSIS_LED_ATTN_OFF	| \
+					 PDC_CHASSIS_LED_FAULT_ON	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* Unexpected reboot occurred - Executing non-OS code */
+#define PDC_CHASSIS_LSTATE_NONOS_UNEXP	(PDC_CHASSIS_LED_RUN_FLASH	| \
+					 PDC_CHASSIS_LED_ATTN_OFF	| \
+					 PDC_CHASSIS_LED_FAULT_FLASH	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* Executing non-OS code - Non-critical error detected */
+#define PDC_CHASSIS_LSTATE_NONOS_NCRIT	(PDC_CHASSIS_LED_RUN_FLASH	| \
+					 PDC_CHASSIS_LED_ATTN_FLASH	| \
+					 PDC_CHASSIS_LED_FAULT_OFF	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* Boot failed - Executing non-OS code - Non-critical error detected */
+#define PDC_CHASSIS_LSTATE_BFAIL_NCRIT	(PDC_CHASSIS_LED_RUN_FLASH	| \
+					 PDC_CHASSIS_LED_ATTN_FLASH	| \
+					 PDC_CHASSIS_LED_FAULT_ON	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* Unexpected reboot/recovering - Executing non-OS code - Non-critical error detected */
+#define PDC_CHASSIS_LSTATE_UNEXP_NCRIT	(PDC_CHASSIS_LED_RUN_FLASH	| \
+					 PDC_CHASSIS_LED_ATTN_FLASH	| \
+					 PDC_CHASSIS_LED_FAULT_FLASH	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* Cannot execute PDC */
+#define PDC_CHASSIS_LSTATE_CANNOT_PDC	(PDC_CHASSIS_LED_RUN_OFF	| \
+					 PDC_CHASSIS_LED_ATTN_OFF	| \
+					 PDC_CHASSIS_LED_FAULT_OFF	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* Boot failed - OS not up - PDC has detected a failure that prevents boot */
+#define PDC_CHASSIS_LSTATE_FATAL_BFAIL	(PDC_CHASSIS_LED_RUN_OFF	| \
+					 PDC_CHASSIS_LED_ATTN_OFF	| \
+					 PDC_CHASSIS_LED_FAULT_ON	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* No code running - Non-critical error detected (double fault situation) */
+#define PDC_CHASSIS_LSTATE_NOCODE_NCRIT	(PDC_CHASSIS_LED_RUN_OFF	| \
+					 PDC_CHASSIS_LED_ATTN_FLASH	| \
+					 PDC_CHASSIS_LED_FAULT_OFF	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* Boot failed - OS not up - Fatal failure detected - Non-critical error detected */
+#define PDC_CHASSIS_LSTATE_FATAL_NCRIT	(PDC_CHASSIS_LED_RUN_OFF	| \
+					 PDC_CHASSIS_LED_ATTN_FLASH	| \
+					 PDC_CHASSIS_LED_FAULT_ON	| \
+					 PDC_CHASSIS_LED_VALID		)
+/* All other states are invalid */
+
+
+/*
+ * --------------
+ * PDC Log events
+ * --------------
+ * Here follows bits needed to fill up the log event sent to PDC_CHASSIS
+ * The log message contains: Alert level, Source, Source detail,
+ * Source ID, Problem detail, Caller activity, Activity status, 
+ * Caller subactivity, Reporting entity type, Reporting entity ID,
+ * Data type, Unique message ID and EOM. 
+ */
+
+/* Alert level */
+#define PDC_CHASSIS_ALERT_FORWARD	(0ULL << 36)	/* no failure detected */
+#define PDC_CHASSIS_ALERT_SERPROC	(1ULL << 36)	/* service proc - no failure */
+#define PDC_CHASSIS_ALERT_NURGENT	(2ULL << 36)	/* non-urgent operator attn */
+#define PDC_CHASSIS_ALERT_BLOCKED	(3ULL << 36)	/* system blocked */
+#define PDC_CHASSIS_ALERT_CONF_CHG	(4ULL << 36)	/* unexpected configuration change */
+#define PDC_CHASSIS_ALERT_ENV_PB	(5ULL << 36)	/* boot possible, environmental pb */
+#define PDC_CHASSIS_ALERT_PENDING	(6ULL << 36)	/* boot possible, pending failure */
+#define PDC_CHASSIS_ALERT_PERF_IMP	(8ULL << 36)	/* boot possible, performance impaired */
+#define PDC_CHASSIS_ALERT_FUNC_IMP	(10ULL << 36)	/* boot possible, functionality impaired */
+#define PDC_CHASSIS_ALERT_SOFT_FAIL	(12ULL << 36)	/* software failure */
+#define PDC_CHASSIS_ALERT_HANG		(13ULL << 36)	/* system hang */
+#define PDC_CHASSIS_ALERT_ENV_FATAL	(14ULL << 36)	/* fatal power or environmental pb */
+#define PDC_CHASSIS_ALERT_HW_FATAL	(15ULL << 36)	/* fatal hardware problem */
+
+/* Source */
+#define PDC_CHASSIS_SRC_NONE		(0ULL << 28)	/* unknown, no source stated */
+#define PDC_CHASSIS_SRC_PROC		(1ULL << 28)	/* processor */
+/* For later use ? */
+#define PDC_CHASSIS_SRC_PROC_CACHE	(2ULL << 28)	/* processor cache*/
+#define PDC_CHASSIS_SRC_PDH		(3ULL << 28)	/* processor dependent hardware */
+#define PDC_CHASSIS_SRC_PWR		(4ULL << 28)	/* power */
+#define PDC_CHASSIS_SRC_FAB		(5ULL << 28)	/* fabric connector */
+#define PDC_CHASSIS_SRC_PLATi		(6ULL << 28)	/* platform */
+#define PDC_CHASSIS_SRC_MEM		(7ULL << 28)	/* memory */
+#define PDC_CHASSIS_SRC_IO		(8ULL << 28)	/* I/O */
+#define PDC_CHASSIS_SRC_CELL		(9ULL << 28)	/* cell */
+#define PDC_CHASSIS_SRC_PD		(10ULL << 28)	/* protected domain */
+
+/* Source detail field */
+#define PDC_CHASSIS_SRC_D_PROC		(1ULL << 24)	/* processor general */
+
+/* Source ID - platform dependent */
+#define PDC_CHASSIS_SRC_ID_UNSPEC	(0ULL << 16)
+
+/* Problem detail - problem source dependent */
+#define PDC_CHASSIS_PB_D_PROC_NONE	(0ULL << 32)	/* no problem detail */
+#define PDC_CHASSIS_PB_D_PROC_TIMEOUT	(4ULL << 32)	/* timeout */
+
+/* Caller activity */
+#define PDC_CHASSIS_CALL_ACT_HPUX_BL	(7ULL << 12)	/* Boot Loader */
+#define PDC_CHASSIS_CALL_ACT_HPUX_PD	(8ULL << 12)	/* SAL_PD activities */
+#define PDC_CHASSIS_CALL_ACT_HPUX_EVENT	(9ULL << 12)	/* SAL_EVENTS activities */
+#define PDC_CHASSIS_CALL_ACT_HPUX_IO	(10ULL << 12)	/* SAL_IO activities */
+#define PDC_CHASSIS_CALL_ACT_HPUX_PANIC	(11ULL << 12)	/* System panic */
+#define PDC_CHASSIS_CALL_ACT_HPUX_INIT	(12ULL << 12)	/* System initialization */
+#define PDC_CHASSIS_CALL_ACT_HPUX_SHUT	(13ULL << 12)	/* System shutdown */
+#define PDC_CHASSIS_CALL_ACT_HPUX_WARN	(14ULL << 12)	/* System warning */
+#define PDC_CHASSIS_CALL_ACT_HPUX_DU	(15ULL << 12)	/* Display_Activity() update */
+
+/* Activity status - implementation dependent */
+#define PDC_CHASSIS_ACT_STATUS_UNSPEC	(0ULL << 0)
+
+/* Caller subactivity - implementation dependent */
+/* FIXME: other subactivities ? */
+#define PDC_CHASSIS_CALL_SACT_UNSPEC	(0ULL << 4)	/* implementation dependent */
+
+/* Reporting entity type */
+#define PDC_CHASSIS_RET_GENERICOS	(12ULL << 52)	/* generic OSes */
+#define PDC_CHASSIS_RET_IA64_NT		(13ULL << 52)	/* IA-64 NT */
+#define PDC_CHASSIS_RET_HPUX		(14ULL << 52)	/* HP-UX */
+#define PDC_CHASSIS_RET_DIAG		(15ULL << 52)	/* offline diagnostics & utilities */
+
+/* Reporting entity ID */
+#define PDC_CHASSIS_REID_UNSPEC		(0ULL << 44)
+
+/* Data type */
+#define PDC_CHASSIS_DT_NONE		(0ULL << 59)	/* data field unused */
+/* For later use ? Do we need these ? */
+#define PDC_CHASSIS_DT_PHYS_ADDR	(1ULL << 59)	/* physical address */
+#define PDC_CHASSIS_DT_DATA_EXPECT	(2ULL << 59)	/* expected data */
+#define PDC_CHASSIS_DT_ACTUAL		(3ULL << 59)	/* actual data */
+#define PDC_CHASSIS_DT_PHYS_LOC		(4ULL << 59)	/* physical location */
+#define PDC_CHASSIS_DT_PHYS_LOC_EXT	(5ULL << 59)	/* physical location extension */
+#define PDC_CHASSIS_DT_TAG		(6ULL << 59)	/* tag */
+#define PDC_CHASSIS_DT_SYNDROME		(7ULL << 59)	/* syndrome */
+#define PDC_CHASSIS_DT_CODE_ADDR	(8ULL << 59)	/* code address */
+#define PDC_CHASSIS_DT_ASCII_MSG	(9ULL << 59)	/* ascii message */
+#define PDC_CHASSIS_DT_POST		(10ULL << 59)	/* POST code */
+#define PDC_CHASSIS_DT_TIMESTAMP	(11ULL << 59)	/* timestamp */
+#define PDC_CHASSIS_DT_DEV_STAT		(12ULL << 59)	/* device status */
+#define PDC_CHASSIS_DT_DEV_TYPE		(13ULL << 59)	/* device type */
+#define PDC_CHASSIS_DT_PB_DET		(14ULL << 59)	/* problem detail */
+#define PDC_CHASSIS_DT_ACT_LEV		(15ULL << 59)	/* activity level/timeout */
+#define PDC_CHASSIS_DT_SER_NUM		(16ULL << 59)	/* serial number */
+#define PDC_CHASSIS_DT_REV_NUM		(17ULL << 59)	/* revision number */
+#define PDC_CHASSIS_DT_INTERRUPT	(18ULL << 59)	/* interruption information */
+#define PDC_CHASSIS_DT_TEST_NUM		(19ULL << 59)	/* test number */
+#define PDC_CHASSIS_DT_STATE_CHG	(20ULL << 59)	/* major changes in system state */
+#define PDC_CHASSIS_DT_PROC_DEALLOC	(21ULL << 59)	/* processor deallocate */
+#define PDC_CHASSIS_DT_RESET		(30ULL << 59)	/* reset type and cause */
+#define PDC_CHASSIS_DT_PA_LEGACY	(31ULL << 59)	/* legacy PA hex chassis code */
+
+/* System states - part of major changes in system state data field */
+#define PDC_CHASSIS_SYSTATE_BSTART	(0ULL << 0)	/* boot start */
+#define PDC_CHASSIS_SYSTATE_BCOMP	(1ULL << 0)	/* boot complete */
+#define PDC_CHASSIS_SYSTATE_CHANGE	(2ULL << 0)	/* major change */
+#define PDC_CHASSIS_SYSTATE_LED		(3ULL << 0)	/* LED change */
+#define PDC_CHASSIS_SYSTATE_PANIC	(9ULL << 0)	/* OS Panic */
+#define PDC_CHASSIS_SYSTATE_DUMP	(10ULL << 0)	/* memory dump */
+#define PDC_CHASSIS_SYSTATE_HPMC	(11ULL << 0)	/* processing HPMC */
+#define PDC_CHASSIS_SYSTATE_HALT	(15ULL << 0)	/* system halted */
+
+/* Message ID */
+#define PDC_CHASSIS_MSG_ID		(0ULL << 40)	/* we do not handle msg IDs atm */
+
+/* EOM - separates log entries */
+#define PDC_CHASSIS_EOM_CLEAR		(0ULL << 43)
+#define PDC_CHASSIS_EOM_SET		(1ULL << 43)
+
+/*
+ * Preformated well known messages
+ */
+
+/* Boot started */
+#define PDC_CHASSIS_PMSG_BSTART		(PDC_CHASSIS_ALERT_SERPROC	| \
+					 PDC_CHASSIS_SRC_PROC		| \
+					 PDC_CHASSIS_SRC_D_PROC		| \
+					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
+					 PDC_CHASSIS_PB_D_PROC_NONE	| \
+					 PDC_CHASSIS_CALL_ACT_HPUX_INIT	| \
+					 PDC_CHASSIS_ACT_STATUS_UNSPEC	| \
+					 PDC_CHASSIS_CALL_SACT_UNSPEC	| \
+					 PDC_CHASSIS_RET_HPUX		| \
+					 PDC_CHASSIS_REID_UNSPEC	| \
+					 PDC_CHASSIS_DT_STATE_CHG	| \
+					 PDC_CHASSIS_SYSTATE_BSTART	| \
+					 PDC_CHASSIS_MSG_ID		| \
+					 PDC_CHASSIS_EOM_SET		)
+
+/* Boot complete */
+#define PDC_CHASSIS_PMSG_BCOMPLETE	(PDC_CHASSIS_ALERT_SERPROC	| \
+					 PDC_CHASSIS_SRC_PROC		| \
+					 PDC_CHASSIS_SRC_D_PROC		| \
+					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
+					 PDC_CHASSIS_PB_D_PROC_NONE	| \
+					 PDC_CHASSIS_CALL_ACT_HPUX_INIT	| \
+					 PDC_CHASSIS_ACT_STATUS_UNSPEC	| \
+					 PDC_CHASSIS_CALL_SACT_UNSPEC	| \
+					 PDC_CHASSIS_RET_HPUX		| \
+					 PDC_CHASSIS_REID_UNSPEC	| \
+					 PDC_CHASSIS_DT_STATE_CHG	| \
+					 PDC_CHASSIS_SYSTATE_BCOMP	| \
+					 PDC_CHASSIS_MSG_ID		| \
+					 PDC_CHASSIS_EOM_SET		)
+
+/* Shutdown */
+#define PDC_CHASSIS_PMSG_SHUTDOWN	(PDC_CHASSIS_ALERT_SERPROC	| \
+					 PDC_CHASSIS_SRC_PROC		| \
+					 PDC_CHASSIS_SRC_D_PROC		| \
+					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
+					 PDC_CHASSIS_PB_D_PROC_NONE	| \
+					 PDC_CHASSIS_CALL_ACT_HPUX_SHUT	| \
+					 PDC_CHASSIS_ACT_STATUS_UNSPEC	| \
+					 PDC_CHASSIS_CALL_SACT_UNSPEC	| \
+					 PDC_CHASSIS_RET_HPUX		| \
+					 PDC_CHASSIS_REID_UNSPEC	| \
+					 PDC_CHASSIS_DT_STATE_CHG	| \
+					 PDC_CHASSIS_SYSTATE_HALT	| \
+					 PDC_CHASSIS_MSG_ID		| \
+					 PDC_CHASSIS_EOM_SET		)
+
+/* Panic */
+#define PDC_CHASSIS_PMSG_PANIC		(PDC_CHASSIS_ALERT_SOFT_FAIL	| \
+					 PDC_CHASSIS_SRC_PROC		| \
+					 PDC_CHASSIS_SRC_D_PROC		| \
+					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
+					 PDC_CHASSIS_PB_D_PROC_NONE	| \
+					 PDC_CHASSIS_CALL_ACT_HPUX_PANIC| \
+					 PDC_CHASSIS_ACT_STATUS_UNSPEC	| \
+					 PDC_CHASSIS_CALL_SACT_UNSPEC	| \
+					 PDC_CHASSIS_RET_HPUX		| \
+					 PDC_CHASSIS_REID_UNSPEC	| \
+					 PDC_CHASSIS_DT_STATE_CHG	| \
+					 PDC_CHASSIS_SYSTATE_PANIC	| \
+					 PDC_CHASSIS_MSG_ID		| \
+					 PDC_CHASSIS_EOM_SET		)
+
+// FIXME: extrapolated data
+/* HPMC */
+#define PDC_CHASSIS_PMSG_HPMC		(PDC_CHASSIS_ALERT_CONF_CHG /*?*/	| \
+					 PDC_CHASSIS_SRC_PROC		| \
+					 PDC_CHASSIS_SRC_D_PROC		| \
+					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
+					 PDC_CHASSIS_PB_D_PROC_NONE	| \
+					 PDC_CHASSIS_CALL_ACT_HPUX_WARN	| \
+					 PDC_CHASSIS_RET_HPUX		| \
+					 PDC_CHASSIS_DT_STATE_CHG	| \
+					 PDC_CHASSIS_SYSTATE_HPMC	| \
+					 PDC_CHASSIS_MSG_ID		| \
+					 PDC_CHASSIS_EOM_SET		)
+
+/* LPMC */
+#define PDC_CHASSIS_PMSG_LPMC		(PDC_CHASSIS_ALERT_BLOCKED /*?*/| \
+					 PDC_CHASSIS_SRC_PROC		| \
+					 PDC_CHASSIS_SRC_D_PROC		| \
+					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
+					 PDC_CHASSIS_PB_D_PROC_NONE	| \
+					 PDC_CHASSIS_CALL_ACT_HPUX_WARN	| \
+					 PDC_CHASSIS_ACT_STATUS_UNSPEC	| \
+					 PDC_CHASSIS_CALL_SACT_UNSPEC	| \
+					 PDC_CHASSIS_RET_HPUX		| \
+					 PDC_CHASSIS_REID_UNSPEC	| \
+					 PDC_CHASSIS_DT_STATE_CHG	| \
+					 PDC_CHASSIS_SYSTATE_CHANGE	| \
+					 PDC_CHASSIS_MSG_ID		| \
+					 PDC_CHASSIS_EOM_SET		)
+
+#endif /* _PARISC_PDC_CHASSIS_H */
+/* vim: set ts=8 */
diff --git a/arch/parisc/include/asm/pdcpat.h b/arch/parisc/include/asm/pdcpat.h
new file mode 100644
index 000000000000..47539f117958
--- /dev/null
+++ b/arch/parisc/include/asm/pdcpat.h
@@ -0,0 +1,308 @@
+#ifndef __PARISC_PATPDC_H
+#define __PARISC_PATPDC_H
+
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright 2000 (c) Hewlett Packard (Paul Bame <bame()spam.parisc-linux.org>)
+ * Copyright 2000,2004 (c) Grant Grundler <grundler()nahspam.parisc-linux.org>
+ */
+
+
+#define PDC_PAT_CELL           	64L   /* Interface for gaining and 
+                                         * manipulatin g cell state within PD */
+#define PDC_PAT_CELL_GET_NUMBER    0L   /* Return Cell number */
+#define PDC_PAT_CELL_GET_INFO      1L   /* Returns info about Cell */
+#define PDC_PAT_CELL_MODULE        2L   /* Returns info about Module */
+#define PDC_PAT_CELL_SET_ATTENTION 9L   /* Set Cell Attention indicator */
+#define PDC_PAT_CELL_NUMBER_TO_LOC 10L   /* Cell Number -> Location */
+#define PDC_PAT_CELL_WALK_FABRIC   11L   /* Walk the Fabric */
+#define PDC_PAT_CELL_GET_RDT_SIZE  12L   /* Return Route Distance Table Sizes */
+#define PDC_PAT_CELL_GET_RDT       13L   /* Return Route Distance Tables */
+#define PDC_PAT_CELL_GET_LOCAL_PDH_SZ 14L /* Read Local PDH Buffer Size */
+#define PDC_PAT_CELL_SET_LOCAL_PDH    15L  /* Write Local PDH Buffer */
+#define PDC_PAT_CELL_GET_REMOTE_PDH_SZ 16L /* Return Remote PDH Buffer Size */
+#define PDC_PAT_CELL_GET_REMOTE_PDH 17L /* Read Remote PDH Buffer */
+#define PDC_PAT_CELL_GET_DBG_INFO   128L  /* Return DBG Buffer Info */
+#define PDC_PAT_CELL_CHANGE_ALIAS   129L  /* Change Non-Equivalent Alias Chacking */
+
+
+/*
+** Arg to PDC_PAT_CELL_MODULE memaddr[4]
+**
+** Addresses on the Merced Bus != all Runway Bus addresses.
+** This is intended for programming SBA/LBA chips range registers.
+*/
+#define IO_VIEW      0UL
+#define PA_VIEW      1UL
+
+/* PDC_PAT_CELL_MODULE entity type values */
+#define	PAT_ENTITY_CA	0	/* central agent */
+#define	PAT_ENTITY_PROC	1	/* processor */
+#define	PAT_ENTITY_MEM	2	/* memory controller */
+#define	PAT_ENTITY_SBA	3	/* system bus adapter */
+#define	PAT_ENTITY_LBA	4	/* local bus adapter */
+#define	PAT_ENTITY_PBC	5	/* processor bus converter */
+#define	PAT_ENTITY_XBC	6	/* crossbar fabric connect */
+#define	PAT_ENTITY_RC	7	/* fabric interconnect */
+
+/* PDC_PAT_CELL_MODULE address range type values */
+#define PAT_PBNUM           0         /* PCI Bus Number */
+#define PAT_LMMIO           1         /* < 4G MMIO Space */
+#define PAT_GMMIO           2         /* > 4G MMIO Space */
+#define PAT_NPIOP           3         /* Non Postable I/O Port Space */
+#define PAT_PIOP            4         /* Postable I/O Port Space */
+#define PAT_AHPA            5         /* Addional HPA Space */
+#define PAT_UFO             6         /* HPA Space (UFO for Mariposa) */
+#define PAT_GNIP            7         /* GNI Reserved Space */
+
+
+
+/* PDC PAT CHASSIS LOG -- Platform logging & forward progress functions */
+
+#define PDC_PAT_CHASSIS_LOG		65L
+#define PDC_PAT_CHASSIS_WRITE_LOG    	0L /* Write Log Entry */
+#define PDC_PAT_CHASSIS_READ_LOG     	1L /* Read  Log Entry */
+
+
+/* PDC PAT CPU  -- CPU configuration within the protection domain */
+
+#define PDC_PAT_CPU                	67L
+#define PDC_PAT_CPU_INFO            	0L /* Return CPU config info */
+#define PDC_PAT_CPU_DELETE          	1L /* Delete CPU */
+#define PDC_PAT_CPU_ADD             	2L /* Add    CPU */
+#define PDC_PAT_CPU_GET_NUMBER      	3L /* Return CPU Number */
+#define PDC_PAT_CPU_GET_HPA         	4L /* Return CPU HPA */
+#define PDC_PAT_CPU_STOP            	5L /* Stop   CPU */
+#define PDC_PAT_CPU_RENDEZVOUS      	6L /* Rendezvous CPU */
+#define PDC_PAT_CPU_GET_CLOCK_INFO  	7L /* Return CPU Clock info */
+#define PDC_PAT_CPU_GET_RENDEZVOUS_STATE 8L /* Return Rendezvous State */
+#define PDC_PAT_CPU_PLUNGE_FABRIC 	128L /* Plunge Fabric */
+#define PDC_PAT_CPU_UPDATE_CACHE_CLEANSING 129L /* Manipulate Cache 
+                                                 * Cleansing Mode */
+/*  PDC PAT EVENT -- Platform Events */
+
+#define PDC_PAT_EVENT              	68L
+#define PDC_PAT_EVENT_GET_CAPS     	0L /* Get Capabilities */
+#define PDC_PAT_EVENT_SET_MODE     	1L /* Set Notification Mode */
+#define PDC_PAT_EVENT_SCAN         	2L /* Scan Event */
+#define PDC_PAT_EVENT_HANDLE       	3L /* Handle Event */
+#define PDC_PAT_EVENT_GET_NB_CALL  	4L /* Get Non-Blocking call Args */
+
+/*  PDC PAT HPMC -- Cause processor to go into spin loop, and wait
+ *  			for wake up from Monarch Processor.
+ */
+
+#define PDC_PAT_HPMC               70L
+#define PDC_PAT_HPMC_RENDEZ_CPU     0L /* go into spin loop */
+#define PDC_PAT_HPMC_SET_PARAMS     1L /* Allows OS to specify intr which PDC 
+                                        * will use to interrupt OS during
+                                        * machine check rendezvous */
+
+/* parameters for PDC_PAT_HPMC_SET_PARAMS: */
+#define HPMC_SET_PARAMS_INTR 	    1L /* Rendezvous Interrupt */
+#define HPMC_SET_PARAMS_WAKE 	    2L /* Wake up processor */
+
+
+/*  PDC PAT IO  -- On-line services for I/O modules */
+
+#define PDC_PAT_IO                  71L
+#define PDC_PAT_IO_GET_SLOT_STATUS   	5L /* Get Slot Status Info*/
+#define PDC_PAT_IO_GET_LOC_FROM_HARDWARE 6L /* Get Physical Location from */
+                                            /* Hardware Path */
+#define PDC_PAT_IO_GET_HARDWARE_FROM_LOC 7L /* Get Hardware Path from 
+                                             * Physical Location */
+#define PDC_PAT_IO_GET_PCI_CONFIG_FROM_HW 11L /* Get PCI Configuration
+                                               * Address from Hardware Path */
+#define PDC_PAT_IO_GET_HW_FROM_PCI_CONFIG 12L /* Get Hardware Path 
+                                               * from PCI Configuration Address */
+#define PDC_PAT_IO_READ_HOST_BRIDGE_INFO 13L  /* Read Host Bridge State Info */
+#define PDC_PAT_IO_CLEAR_HOST_BRIDGE_INFO 14L /* Clear Host Bridge State Info*/
+#define PDC_PAT_IO_GET_PCI_ROUTING_TABLE_SIZE 15L /* Get PCI INT Routing Table 
+                                                   * Size */
+#define PDC_PAT_IO_GET_PCI_ROUTING_TABLE  16L /* Get PCI INT Routing Table */
+#define PDC_PAT_IO_GET_HINT_TABLE_SIZE 	17L /* Get Hint Table Size */
+#define PDC_PAT_IO_GET_HINT_TABLE   	18L /* Get Hint Table */
+#define PDC_PAT_IO_PCI_CONFIG_READ  	19L /* PCI Config Read */
+#define PDC_PAT_IO_PCI_CONFIG_WRITE 	20L /* PCI Config Write */
+#define PDC_PAT_IO_GET_NUM_IO_SLOTS 	21L /* Get Number of I/O Bay Slots in 
+                                       		  * Cabinet */
+#define PDC_PAT_IO_GET_LOC_IO_SLOTS 	22L /* Get Physical Location of I/O */
+                                   		     /* Bay Slots in Cabinet */
+#define PDC_PAT_IO_BAY_STATUS_INFO  	28L /* Get I/O Bay Slot Status Info */
+#define PDC_PAT_IO_GET_PROC_VIEW        29L /* Get Processor view of IO address */
+#define PDC_PAT_IO_PROG_SBA_DIR_RANGE   30L /* Program directed range */
+
+
+/* PDC PAT MEM  -- Manage memory page deallocation */
+
+#define PDC_PAT_MEM            72L
+#define PDC_PAT_MEM_PD_INFO     	0L /* Return PDT info for PD       */
+#define PDC_PAT_MEM_PD_CLEAR    	1L /* Clear PDT for PD             */
+#define PDC_PAT_MEM_PD_READ     	2L /* Read PDT entries for PD      */
+#define PDC_PAT_MEM_PD_RESET    	3L /* Reset clear bit for PD       */
+#define PDC_PAT_MEM_CELL_INFO   	5L /* Return PDT info For Cell     */
+#define PDC_PAT_MEM_CELL_CLEAR  	6L /* Clear PDT For Cell           */
+#define PDC_PAT_MEM_CELL_READ   	7L /* Read PDT entries For Cell    */
+#define PDC_PAT_MEM_CELL_RESET  	8L /* Reset clear bit For Cell     */
+#define PDC_PAT_MEM_SETGM	  	9L /* Set Golden Memory value      */
+#define PDC_PAT_MEM_ADD_PAGE    	10L /* ADDs a page to the cell      */
+#define PDC_PAT_MEM_ADDRESS     	11L /* Get Physical Location From   */
+                                    		 /* Memory Address               */
+#define PDC_PAT_MEM_GET_TXT_SIZE   	12L /* Get Formatted Text Size   */
+#define PDC_PAT_MEM_GET_PD_TXT     	13L /* Get PD Formatted Text     */
+#define PDC_PAT_MEM_GET_CELL_TXT   	14L /* Get Cell Formatted Text   */
+#define PDC_PAT_MEM_RD_STATE_INFO  	15L /* Read Mem Module State Info*/
+#define PDC_PAT_MEM_CLR_STATE_INFO 	16L /*Clear Mem Module State Info*/
+#define PDC_PAT_MEM_CLEAN_RANGE    	128L /*Clean Mem in specific range*/
+#define PDC_PAT_MEM_GET_TBL_SIZE   	131L /* Get Memory Table Size     */
+#define PDC_PAT_MEM_GET_TBL        	132L /* Get Memory Table          */
+
+
+/* PDC PAT NVOLATILE  --  Access Non-Volatile Memory */
+
+#define PDC_PAT_NVOLATILE	73L
+#define PDC_PAT_NVOLATILE_READ		0L /* Read Non-Volatile Memory   */
+#define PDC_PAT_NVOLATILE_WRITE		1L /* Write Non-Volatile Memory  */
+#define PDC_PAT_NVOLATILE_GET_SIZE	2L /* Return size of NVM         */
+#define PDC_PAT_NVOLATILE_VERIFY	3L /* Verify contents of NVM     */
+#define PDC_PAT_NVOLATILE_INIT		4L /* Initialize NVM             */
+
+/* PDC PAT PD */
+#define PDC_PAT_PD		74L         /* Protection Domain Info   */
+#define PDC_PAT_PD_GET_ADDR_MAP		0L  /* Get Address Map          */
+
+/* PDC_PAT_PD_GET_ADDR_MAP entry types */
+#define PAT_MEMORY_DESCRIPTOR		1   
+
+/* PDC_PAT_PD_GET_ADDR_MAP memory types */
+#define PAT_MEMTYPE_MEMORY		0
+#define PAT_MEMTYPE_FIRMWARE		4
+
+/* PDC_PAT_PD_GET_ADDR_MAP memory usage */
+#define PAT_MEMUSE_GENERAL		0
+#define PAT_MEMUSE_GI			128
+#define PAT_MEMUSE_GNI			129
+
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+
+#ifdef CONFIG_64BIT
+#define is_pdc_pat()	(PDC_TYPE_PAT == pdc_type)
+extern int pdc_pat_get_irt_size(unsigned long *num_entries, unsigned long cell_num);
+extern int pdc_pat_get_irt(void *r_addr, unsigned long cell_num);
+#else	/* ! CONFIG_64BIT */
+/* No PAT support for 32-bit kernels...sorry */
+#define is_pdc_pat()	(0)
+#define pdc_pat_get_irt_size(num_entries, cell_numn)	PDC_BAD_PROC
+#define pdc_pat_get_irt(r_addr, cell_num)		PDC_BAD_PROC
+#endif	/* ! CONFIG_64BIT */
+
+
+struct pdc_pat_cell_num {
+	unsigned long cell_num;
+	unsigned long cell_loc;
+};
+
+struct pdc_pat_cpu_num {
+	unsigned long cpu_num;
+	unsigned long cpu_loc;
+};
+
+struct pdc_pat_pd_addr_map_entry {
+	unsigned char entry_type;       /* 1 = Memory Descriptor Entry Type */
+	unsigned char reserve1[5];
+	unsigned char memory_type;
+	unsigned char memory_usage;
+	unsigned long paddr;
+	unsigned int  pages;            /* Length in 4K pages */
+	unsigned int  reserve2;
+	unsigned long cell_map;
+};
+
+/********************************************************************
+* PDC_PAT_CELL[Return Cell Module] memaddr[0] conf_base_addr
+* ----------------------------------------------------------
+* Bit  0 to 51 - conf_base_addr
+* Bit 52 to 62 - reserved
+* Bit       63 - endianess bit
+********************************************************************/
+#define PAT_GET_CBA(value) ((value) & 0xfffffffffffff000UL)
+
+/********************************************************************
+* PDC_PAT_CELL[Return Cell Module] memaddr[1] mod_info
+* ----------------------------------------------------
+* Bit  0 to  7 - entity type
+*    0 = central agent,            1 = processor,
+*    2 = memory controller,        3 = system bus adapter,
+*    4 = local bus adapter,        5 = processor bus converter,
+*    6 = crossbar fabric connect,  7 = fabric interconnect,
+*    8 to 254 reserved,            255 = unknown.
+* Bit  8 to 15 - DVI
+* Bit 16 to 23 - IOC functions
+* Bit 24 to 39 - reserved
+* Bit 40 to 63 - mod_pages
+*    number of 4K pages a module occupies starting at conf_base_addr
+********************************************************************/
+#define PAT_GET_ENTITY(value)	(((value) >> 56) & 0xffUL)
+#define PAT_GET_DVI(value)	(((value) >> 48) & 0xffUL)
+#define PAT_GET_IOC(value)	(((value) >> 40) & 0xffUL)
+#define PAT_GET_MOD_PAGES(value) ((value) & 0xffffffUL)
+
+
+/*
+** PDC_PAT_CELL_GET_INFO return block
+*/
+typedef struct pdc_pat_cell_info_rtn_block {
+	unsigned long cpu_info;
+	unsigned long cell_info;
+	unsigned long cell_location;
+	unsigned long reo_location;
+	unsigned long mem_size;
+	unsigned long dimm_status;
+	unsigned long pdc_rev;
+	unsigned long fabric_info0;
+	unsigned long fabric_info1;
+	unsigned long fabric_info2;
+	unsigned long fabric_info3;
+	unsigned long reserved[21];
+} pdc_pat_cell_info_rtn_block_t;
+
+
+/* FIXME: mod[508] should really be a union of the various mod components */
+struct pdc_pat_cell_mod_maddr_block {	/* PDC_PAT_CELL_MODULE */
+	unsigned long cba;		/* func 0 cfg space address */
+	unsigned long mod_info;		/* module information */
+	unsigned long mod_location;	/* physical location of the module */
+	struct hardware_path mod_path;	/* module path (device path - layers) */
+	unsigned long mod[508];		/* PAT cell module components */
+} __attribute__((aligned(8))) ;
+
+typedef struct pdc_pat_cell_mod_maddr_block pdc_pat_cell_mod_maddr_block_t;
+
+
+extern int pdc_pat_chassis_send_log(unsigned long status, unsigned long data);
+extern int pdc_pat_cell_get_number(struct pdc_pat_cell_num *cell_info);
+extern int pdc_pat_cell_module(unsigned long *actcnt, unsigned long ploc, unsigned long mod, unsigned long view_type, void *mem_addr);
+extern int pdc_pat_cell_num_to_loc(void *, unsigned long);
+
+extern int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, void *hpa);
+
+extern int pdc_pat_pd_get_addr_map(unsigned long *actual_len, void *mem_addr, unsigned long count, unsigned long offset);
+
+
+extern int pdc_pat_io_pci_cfg_read(unsigned long pci_addr, int pci_size, u32 *val); 
+extern int pdc_pat_io_pci_cfg_write(unsigned long pci_addr, int pci_size, u32 val); 
+
+
+/* Flag to indicate this is a PAT box...don't use this unless you
+** really have to...it might go away some day.
+*/
+extern int pdc_pat;     /* arch/parisc/kernel/inventory.c */
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* ! __PARISC_PATPDC_H */
diff --git a/arch/parisc/include/asm/percpu.h b/arch/parisc/include/asm/percpu.h
new file mode 100644
index 000000000000..a0dcd1970128
--- /dev/null
+++ b/arch/parisc/include/asm/percpu.h
@@ -0,0 +1,7 @@
+#ifndef _PARISC_PERCPU_H
+#define _PARISC_PERCPU_H
+
+#include <asm-generic/percpu.h>
+
+#endif 
+
diff --git a/arch/parisc/include/asm/perf.h b/arch/parisc/include/asm/perf.h
new file mode 100644
index 000000000000..a18e11972c09
--- /dev/null
+++ b/arch/parisc/include/asm/perf.h
@@ -0,0 +1,74 @@
+#ifndef _ASM_PERF_H_
+#define _ASM_PERF_H_
+
+/* ioctls */
+#define PA_PERF_ON	_IO('p', 1)
+#define PA_PERF_OFF	_IOR('p', 2, unsigned int)
+#define PA_PERF_VERSION	_IOR('p', 3, int)
+
+#define PA_PERF_DEV	"perf"
+#define PA_PERF_MINOR	146
+
+/* Interface types */
+#define UNKNOWN_INTF    255
+#define ONYX_INTF         0
+#define CUDA_INTF         1
+
+/* Common Onyx and Cuda images */
+#define CPI                 0
+#define BUSUTIL             1
+#define TLBMISS             2
+#define TLBHANDMISS         3
+#define PTKN                4
+#define PNTKN               5
+#define IMISS               6
+#define DMISS               7
+#define DMISS_ACCESS        8 
+#define BIG_CPI 	    9
+#define BIG_LS		   10  
+#define BR_ABORT	   11
+#define ISNT		   12 
+#define QUADRANT           13
+#define RW_PDFET           14
+#define RW_WDFET           15
+#define SHLIB_CPI          16
+
+/* Cuda only Images */
+#define FLOPS              17
+#define CACHEMISS          18 
+#define BRANCHES           19             
+#define CRSTACK            20 
+#define I_CACHE_SPEC       21 
+#define MAX_CUDA_IMAGES    22 
+
+/* Onyx only Images */
+#define ADDR_INV_ABORT_ALU 17
+#define BRAD_STALL	   18 
+#define CNTL_IN_PIPEL	   19 
+#define DSNT_XFH	   20 
+#define FET_SIG1	   21 
+#define FET_SIG2	   22 
+#define G7_1		   23 
+#define G7_2		   24 
+#define G7_3 		   25
+#define G7_4		   26
+#define MPB_LABORT         27
+#define PANIC              28
+#define RARE_INST          29 
+#define RW_DFET            30 
+#define RW_IFET            31 
+#define RW_SDFET           32 
+#define SPEC_IFET          33 
+#define ST_COND0           34 
+#define ST_COND1           35 
+#define ST_COND2           36
+#define ST_COND3           37
+#define ST_COND4           38
+#define ST_UNPRED0         39 
+#define ST_UNPRED1         40 
+#define UNPRED             41 
+#define GO_STORE           42
+#define SHLIB_CALL         43
+#define MAX_ONYX_IMAGES    44
+
+#endif
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
new file mode 100644
index 000000000000..fc987a1c12a8
--- /dev/null
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -0,0 +1,149 @@
+#ifndef _ASM_PGALLOC_H
+#define _ASM_PGALLOC_H
+
+#include <linux/gfp.h>
+#include <linux/mm.h>
+#include <linux/threads.h>
+#include <asm/processor.h>
+#include <asm/fixmap.h>
+
+#include <asm/cache.h>
+
+/* Allocate the top level pgd (page directory)
+ *
+ * Here (for 64 bit kernels) we implement a Hybrid L2/L3 scheme: we
+ * allocate the first pmd adjacent to the pgd.  This means that we can
+ * subtract a constant offset to get to it.  The pmd and pgd sizes are
+ * arranged so that a single pmd covers 4GB (giving a full 64-bit
+ * process access to 8TB) so our lookups are effectively L2 for the
+ * first 4GB of the kernel (i.e. for all ILP32 processes and all the
+ * kernel for machines with under 4GB of memory) */
+static inline pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *pgd = (pgd_t *)__get_free_pages(GFP_KERNEL,
+					       PGD_ALLOC_ORDER);
+	pgd_t *actual_pgd = pgd;
+
+	if (likely(pgd != NULL)) {
+		memset(pgd, 0, PAGE_SIZE<<PGD_ALLOC_ORDER);
+#ifdef CONFIG_64BIT
+		actual_pgd += PTRS_PER_PGD;
+		/* Populate first pmd with allocated memory.  We mark it
+		 * with PxD_FLAG_ATTACHED as a signal to the system that this
+		 * pmd entry may not be cleared. */
+		__pgd_val_set(*actual_pgd, (PxD_FLAG_PRESENT | 
+				        PxD_FLAG_VALID | 
+					PxD_FLAG_ATTACHED) 
+			+ (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT));
+		/* The first pmd entry also is marked with _PAGE_GATEWAY as
+		 * a signal that this pmd may not be freed */
+		__pgd_val_set(*pgd, PxD_FLAG_ATTACHED);
+#endif
+	}
+	return actual_pgd;
+}
+
+static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+#ifdef CONFIG_64BIT
+	pgd -= PTRS_PER_PGD;
+#endif
+	free_pages((unsigned long)pgd, PGD_ALLOC_ORDER);
+}
+
+#if PT_NLEVELS == 3
+
+/* Three Level Page Table Support for pmd's */
+
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
+{
+	__pgd_val_set(*pgd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID) +
+		        (__u32)(__pa((unsigned long)pmd) >> PxD_VALUE_SHIFT));
+}
+
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+	pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT,
+					       PMD_ORDER);
+	if (pmd)
+		memset(pmd, 0, PAGE_SIZE<<PMD_ORDER);
+	return pmd;
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+#ifdef CONFIG_64BIT
+	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
+		/* This is the permanent pmd attached to the pgd;
+		 * cannot free it */
+		return;
+#endif
+	free_pages((unsigned long)pmd, PMD_ORDER);
+}
+
+#else
+
+/* Two Level Page Table Support for pmd's */
+
+/*
+ * allocating and freeing a pmd is trivial: the 1-entry pmd is
+ * inside the pgd, so has no extra memory associated with it.
+ */
+
+#define pmd_alloc_one(mm, addr)		({ BUG(); ((pmd_t *)2); })
+#define pmd_free(mm, x)			do { } while (0)
+#define pgd_populate(mm, pmd, pte)	BUG()
+
+#endif
+
+static inline void
+pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
+{
+#ifdef CONFIG_64BIT
+	/* preserve the gateway marker if this is the beginning of
+	 * the permanent pmd */
+	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
+		__pmd_val_set(*pmd, (PxD_FLAG_PRESENT |
+				 PxD_FLAG_VALID |
+				 PxD_FLAG_ATTACHED) 
+			+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
+	else
+#endif
+		__pmd_val_set(*pmd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID) 
+			+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
+}
+
+#define pmd_populate(mm, pmd, pte_page) \
+	pmd_populate_kernel(mm, pmd, page_address(pte_page))
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
+static inline pgtable_t
+pte_alloc_one(struct mm_struct *mm, unsigned long address)
+{
+	struct page *page = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	if (page)
+		pgtable_page_ctor(page);
+	return page;
+}
+
+static inline pte_t *
+pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
+{
+	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
+	return pte;
+}
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, struct page *pte)
+{
+	pgtable_page_dtor(pte);
+	pte_free_kernel(mm, page_address(pte));
+}
+
+#define check_pgt_cache()	do { } while (0)
+
+#endif
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
new file mode 100644
index 000000000000..470a4b88124d
--- /dev/null
+++ b/arch/parisc/include/asm/pgtable.h
@@ -0,0 +1,508 @@
+#ifndef _PARISC_PGTABLE_H
+#define _PARISC_PGTABLE_H
+
+#include <asm-generic/4level-fixup.h>
+
+#include <asm/fixmap.h>
+
+#ifndef __ASSEMBLY__
+/*
+ * we simulate an x86-style page table for the linux mm code
+ */
+
+#include <linux/mm.h>		/* for vm_area_struct */
+#include <linux/bitops.h>
+#include <asm/processor.h>
+#include <asm/cache.h>
+
+/*
+ * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
+ * memory.  For the return value to be meaningful, ADDR must be >=
+ * PAGE_OFFSET.  This operation can be relatively expensive (e.g.,
+ * require a hash-, or multi-level tree-lookup or something of that
+ * sort) but it guarantees to return TRUE only if accessing the page
+ * at that address does not cause an error.  Note that there may be
+ * addresses for which kern_addr_valid() returns FALSE even though an
+ * access would not cause an error (e.g., this is typically true for
+ * memory mapped I/O regions.
+ *
+ * XXX Need to implement this for parisc.
+ */
+#define kern_addr_valid(addr)	(1)
+
+/* Certain architectures need to do special things when PTEs
+ * within a page table are directly modified.  Thus, the following
+ * hook is made available.
+ */
+#define set_pte(pteptr, pteval)                                 \
+        do{                                                     \
+                *(pteptr) = (pteval);                           \
+        } while(0)
+#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
+
+#endif /* !__ASSEMBLY__ */
+
+#define pte_ERROR(e) \
+	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
+#define pmd_ERROR(e) \
+	printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, (unsigned long)pmd_val(e))
+#define pgd_ERROR(e) \
+	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e))
+
+/* This is the size of the initially mapped kernel memory */
+#ifdef CONFIG_64BIT
+#define KERNEL_INITIAL_ORDER	24	/* 0 to 1<<24 = 16MB */
+#else
+#define KERNEL_INITIAL_ORDER	23	/* 0 to 1<<23 = 8MB */
+#endif
+#define KERNEL_INITIAL_SIZE	(1 << KERNEL_INITIAL_ORDER)
+
+#if defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB)
+#define PT_NLEVELS	3
+#define PGD_ORDER	1 /* Number of pages per pgd */
+#define PMD_ORDER	1 /* Number of pages per pmd */
+#define PGD_ALLOC_ORDER	2 /* first pgd contains pmd */
+#else
+#define PT_NLEVELS	2
+#define PGD_ORDER	1 /* Number of pages per pgd */
+#define PGD_ALLOC_ORDER	PGD_ORDER
+#endif
+
+/* Definitions for 3rd level (we use PLD here for Page Lower directory
+ * because PTE_SHIFT is used lower down to mean shift that has to be
+ * done to get usable bits out of the PTE) */
+#define PLD_SHIFT	PAGE_SHIFT
+#define PLD_SIZE	PAGE_SIZE
+#define BITS_PER_PTE	(PAGE_SHIFT - BITS_PER_PTE_ENTRY)
+#define PTRS_PER_PTE    (1UL << BITS_PER_PTE)
+
+/* Definitions for 2nd level */
+#define pgtable_cache_init()	do { } while (0)
+
+#define PMD_SHIFT       (PLD_SHIFT + BITS_PER_PTE)
+#define PMD_SIZE	(1UL << PMD_SHIFT)
+#define PMD_MASK	(~(PMD_SIZE-1))
+#if PT_NLEVELS == 3
+#define BITS_PER_PMD	(PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY)
+#else
+#define BITS_PER_PMD	0
+#endif
+#define PTRS_PER_PMD    (1UL << BITS_PER_PMD)
+
+/* Definitions for 1st level */
+#define PGDIR_SHIFT	(PMD_SHIFT + BITS_PER_PMD)
+#define BITS_PER_PGD	(PAGE_SHIFT + PGD_ORDER - BITS_PER_PGD_ENTRY)
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+#define PTRS_PER_PGD    (1UL << BITS_PER_PGD)
+#define USER_PTRS_PER_PGD       PTRS_PER_PGD
+
+#define MAX_ADDRBITS	(PGDIR_SHIFT + BITS_PER_PGD)
+#define MAX_ADDRESS	(1UL << MAX_ADDRBITS)
+
+#define SPACEID_SHIFT	(MAX_ADDRBITS - 32)
+
+/* This calculates the number of initial pages we need for the initial
+ * page tables */
+#if (KERNEL_INITIAL_ORDER) >= (PMD_SHIFT)
+# define PT_INITIAL	(1 << (KERNEL_INITIAL_ORDER - PMD_SHIFT))
+#else
+# define PT_INITIAL	(1)  /* all initial PTEs fit into one page */
+#endif
+
+/*
+ * pgd entries used up by user/kernel:
+ */
+
+#define FIRST_USER_ADDRESS	0
+
+/* NB: The tlb miss handlers make certain assumptions about the order */
+/*     of the following bits, so be careful (One example, bits 25-31  */
+/*     are moved together in one instruction).                        */
+
+#define _PAGE_READ_BIT     31   /* (0x001) read access allowed */
+#define _PAGE_WRITE_BIT    30   /* (0x002) write access allowed */
+#define _PAGE_EXEC_BIT     29   /* (0x004) execute access allowed */
+#define _PAGE_GATEWAY_BIT  28   /* (0x008) privilege promotion allowed */
+#define _PAGE_DMB_BIT      27   /* (0x010) Data Memory Break enable (B bit) */
+#define _PAGE_DIRTY_BIT    26   /* (0x020) Page Dirty (D bit) */
+#define _PAGE_FILE_BIT	_PAGE_DIRTY_BIT	/* overload this bit */
+#define _PAGE_REFTRAP_BIT  25   /* (0x040) Page Ref. Trap enable (T bit) */
+#define _PAGE_NO_CACHE_BIT 24   /* (0x080) Uncached Page (U bit) */
+#define _PAGE_ACCESSED_BIT 23   /* (0x100) Software: Page Accessed */
+#define _PAGE_PRESENT_BIT  22   /* (0x200) Software: translation valid */
+#define _PAGE_FLUSH_BIT    21   /* (0x400) Software: translation valid */
+				/*             for cache flushing only */
+#define _PAGE_USER_BIT     20   /* (0x800) Software: User accessible page */
+
+/* N.B. The bits are defined in terms of a 32 bit word above, so the */
+/*      following macro is ok for both 32 and 64 bit.                */
+
+#define xlate_pabit(x) (31 - x)
+
+/* this defines the shift to the usable bits in the PTE it is set so
+ * that the valid bits _PAGE_PRESENT_BIT and _PAGE_USER_BIT are set
+ * to zero */
+#define PTE_SHIFT	   	xlate_pabit(_PAGE_USER_BIT)
+
+/* PFN_PTE_SHIFT defines the shift of a PTE value to access the PFN field */
+#define PFN_PTE_SHIFT		12
+
+
+/* this is how many bits may be used by the file functions */
+#define PTE_FILE_MAX_BITS	(BITS_PER_LONG - PTE_SHIFT)
+
+#define pte_to_pgoff(pte) (pte_val(pte) >> PTE_SHIFT)
+#define pgoff_to_pte(off) ((pte_t) { ((off) << PTE_SHIFT) | _PAGE_FILE })
+
+#define _PAGE_READ     (1 << xlate_pabit(_PAGE_READ_BIT))
+#define _PAGE_WRITE    (1 << xlate_pabit(_PAGE_WRITE_BIT))
+#define _PAGE_RW       (_PAGE_READ | _PAGE_WRITE)
+#define _PAGE_EXEC     (1 << xlate_pabit(_PAGE_EXEC_BIT))
+#define _PAGE_GATEWAY  (1 << xlate_pabit(_PAGE_GATEWAY_BIT))
+#define _PAGE_DMB      (1 << xlate_pabit(_PAGE_DMB_BIT))
+#define _PAGE_DIRTY    (1 << xlate_pabit(_PAGE_DIRTY_BIT))
+#define _PAGE_REFTRAP  (1 << xlate_pabit(_PAGE_REFTRAP_BIT))
+#define _PAGE_NO_CACHE (1 << xlate_pabit(_PAGE_NO_CACHE_BIT))
+#define _PAGE_ACCESSED (1 << xlate_pabit(_PAGE_ACCESSED_BIT))
+#define _PAGE_PRESENT  (1 << xlate_pabit(_PAGE_PRESENT_BIT))
+#define _PAGE_FLUSH    (1 << xlate_pabit(_PAGE_FLUSH_BIT))
+#define _PAGE_USER     (1 << xlate_pabit(_PAGE_USER_BIT))
+#define _PAGE_FILE     (1 << xlate_pabit(_PAGE_FILE_BIT))
+
+#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE |  _PAGE_DIRTY | _PAGE_ACCESSED)
+#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_KERNEL	(_PAGE_PRESENT | _PAGE_EXEC | _PAGE_READ | _PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED)
+
+/* The pgd/pmd contains a ptr (in phys addr space); since all pgds/pmds
+ * are page-aligned, we don't care about the PAGE_OFFSET bits, except
+ * for a few meta-information bits, so we shift the address to be
+ * able to effectively address 40/42/44-bits of physical address space
+ * depending on 4k/16k/64k PAGE_SIZE */
+#define _PxD_PRESENT_BIT   31
+#define _PxD_ATTACHED_BIT  30
+#define _PxD_VALID_BIT     29
+
+#define PxD_FLAG_PRESENT  (1 << xlate_pabit(_PxD_PRESENT_BIT))
+#define PxD_FLAG_ATTACHED (1 << xlate_pabit(_PxD_ATTACHED_BIT))
+#define PxD_FLAG_VALID    (1 << xlate_pabit(_PxD_VALID_BIT))
+#define PxD_FLAG_MASK     (0xf)
+#define PxD_FLAG_SHIFT    (4)
+#define PxD_VALUE_SHIFT   (8) /* (PAGE_SHIFT-PxD_FLAG_SHIFT) */
+
+#ifndef __ASSEMBLY__
+
+#define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_WRITE | _PAGE_ACCESSED)
+/* Others seem to make this executable, I don't know if that's correct
+   or not.  The stack is mapped this way though so this is necessary
+   in the short term - dhd@linuxcare.com, 2000-08-08 */
+#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_ACCESSED)
+#define PAGE_WRITEONLY  __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_WRITE | _PAGE_ACCESSED)
+#define PAGE_EXECREAD   __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_EXEC |_PAGE_ACCESSED)
+#define PAGE_COPY       PAGE_EXECREAD
+#define PAGE_RWX        __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_WRITE | _PAGE_EXEC |_PAGE_ACCESSED)
+#define PAGE_KERNEL	__pgprot(_PAGE_KERNEL)
+#define PAGE_KERNEL_RO	__pgprot(_PAGE_KERNEL & ~_PAGE_WRITE)
+#define PAGE_KERNEL_UNC	__pgprot(_PAGE_KERNEL | _PAGE_NO_CACHE)
+#define PAGE_GATEWAY    __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_GATEWAY| _PAGE_READ)
+#define PAGE_FLUSH      __pgprot(_PAGE_FLUSH)
+
+
+/*
+ * We could have an execute only page using "gateway - promote to priv
+ * level 3", but that is kind of silly. So, the way things are defined
+ * now, we must always have read permission for pages with execute
+ * permission. For the fun of it we'll go ahead and support write only
+ * pages.
+ */
+
+	 /*xwr*/
+#define __P000  PAGE_NONE
+#define __P001  PAGE_READONLY
+#define __P010  __P000 /* copy on write */
+#define __P011  __P001 /* copy on write */
+#define __P100  PAGE_EXECREAD
+#define __P101  PAGE_EXECREAD
+#define __P110  __P100 /* copy on write */
+#define __P111  __P101 /* copy on write */
+
+#define __S000  PAGE_NONE
+#define __S001  PAGE_READONLY
+#define __S010  PAGE_WRITEONLY
+#define __S011  PAGE_SHARED
+#define __S100  PAGE_EXECREAD
+#define __S101  PAGE_EXECREAD
+#define __S110  PAGE_RWX
+#define __S111  PAGE_RWX
+
+
+extern pgd_t swapper_pg_dir[]; /* declared in init_task.c */
+
+/* initial page tables for 0-8MB for kernel */
+
+extern pte_t pg0[];
+
+/* zero page used for uninitialized stuff */
+
+extern unsigned long *empty_zero_page;
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+#define pte_none(x)     ((pte_val(x) == 0) || (pte_val(x) & _PAGE_FLUSH))
+#define pte_present(x)	(pte_val(x) & _PAGE_PRESENT)
+#define pte_clear(mm,addr,xp)	do { pte_val(*(xp)) = 0; } while (0)
+
+#define pmd_flag(x)	(pmd_val(x) & PxD_FLAG_MASK)
+#define pmd_address(x)	((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
+#define pgd_flag(x)	(pgd_val(x) & PxD_FLAG_MASK)
+#define pgd_address(x)	((unsigned long)(pgd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
+
+#if PT_NLEVELS == 3
+/* The first entry of the permanent pmd is not there if it contains
+ * the gateway marker */
+#define pmd_none(x)	(!pmd_val(x) || pmd_flag(x) == PxD_FLAG_ATTACHED)
+#else
+#define pmd_none(x)	(!pmd_val(x))
+#endif
+#define pmd_bad(x)	(!(pmd_flag(x) & PxD_FLAG_VALID))
+#define pmd_present(x)	(pmd_flag(x) & PxD_FLAG_PRESENT)
+static inline void pmd_clear(pmd_t *pmd) {
+#if PT_NLEVELS == 3
+	if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
+		/* This is the entry pointing to the permanent pmd
+		 * attached to the pgd; cannot clear it */
+		__pmd_val_set(*pmd, PxD_FLAG_ATTACHED);
+	else
+#endif
+		__pmd_val_set(*pmd,  0);
+}
+
+
+
+#if PT_NLEVELS == 3
+#define pgd_page_vaddr(pgd) ((unsigned long) __va(pgd_address(pgd)))
+#define pgd_page(pgd)	virt_to_page((void *)pgd_page_vaddr(pgd))
+
+/* For 64 bit we have three level tables */
+
+#define pgd_none(x)     (!pgd_val(x))
+#define pgd_bad(x)      (!(pgd_flag(x) & PxD_FLAG_VALID))
+#define pgd_present(x)  (pgd_flag(x) & PxD_FLAG_PRESENT)
+static inline void pgd_clear(pgd_t *pgd) {
+#if PT_NLEVELS == 3
+	if(pgd_flag(*pgd) & PxD_FLAG_ATTACHED)
+		/* This is the permanent pmd attached to the pgd; cannot
+		 * free it */
+		return;
+#endif
+	__pgd_val_set(*pgd, 0);
+}
+#else
+/*
+ * The "pgd_xxx()" functions here are trivial for a folded two-level
+ * setup: the pgd is never bad, and a pmd always exists (as it's folded
+ * into the pgd entry)
+ */
+static inline int pgd_none(pgd_t pgd)		{ return 0; }
+static inline int pgd_bad(pgd_t pgd)		{ return 0; }
+static inline int pgd_present(pgd_t pgd)	{ return 1; }
+static inline void pgd_clear(pgd_t * pgdp)	{ }
+#endif
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
+static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
+static inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_WRITE; }
+static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
+static inline int pte_special(pte_t pte)	{ return 0; }
+
+static inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~_PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkold(pte_t pte)	{ pte_val(pte) &= ~_PAGE_ACCESSED; return pte; }
+static inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) &= ~_PAGE_WRITE; return pte; }
+static inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= _PAGE_DIRTY; return pte; }
+static inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= _PAGE_ACCESSED; return pte; }
+static inline pte_t pte_mkwrite(pte_t pte)	{ pte_val(pte) |= _PAGE_WRITE; return pte; }
+static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+#define __mk_pte(addr,pgprot) \
+({									\
+	pte_t __pte;							\
+									\
+	pte_val(__pte) = ((((addr)>>PAGE_SHIFT)<<PFN_PTE_SHIFT) + pgprot_val(pgprot));	\
+									\
+	__pte;								\
+})
+
+#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
+
+static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
+{
+	pte_t pte;
+	pte_val(pte) = (pfn << PFN_PTE_SHIFT) | pgprot_val(pgprot);
+	return pte;
+}
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{ pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot); return pte; }
+
+/* Permanent address of a page.  On parisc we don't have highmem. */
+
+#define pte_pfn(x)		(pte_val(x) >> PFN_PTE_SHIFT)
+
+#define pte_page(pte)		(pfn_to_page(pte_pfn(pte)))
+
+#define pmd_page_vaddr(pmd)	((unsigned long) __va(pmd_address(pmd)))
+
+#define __pmd_page(pmd) ((unsigned long) __va(pmd_address(pmd)))
+#define pmd_page(pmd)	virt_to_page((void *)__pmd_page(pmd))
+
+#define pgd_index(address) ((address) >> PGDIR_SHIFT)
+
+/* to find an entry in a page-table-directory */
+#define pgd_offset(mm, address) \
+((mm)->pgd + ((address) >> PGDIR_SHIFT))
+
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+/* Find an entry in the second-level page table.. */
+
+#if PT_NLEVELS == 3
+#define pmd_offset(dir,address) \
+((pmd_t *) pgd_page_vaddr(*(dir)) + (((address)>>PMD_SHIFT) & (PTRS_PER_PMD-1)))
+#else
+#define pmd_offset(dir,addr) ((pmd_t *) dir)
+#endif
+
+/* Find an entry in the third-level page table.. */ 
+#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE-1))
+#define pte_offset_kernel(pmd, address) \
+	((pte_t *) pmd_page_vaddr(*(pmd)) + pte_index(address))
+#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
+#define pte_offset_map_nested(pmd, address) pte_offset_kernel(pmd, address)
+#define pte_unmap(pte) do { } while (0)
+#define pte_unmap_nested(pte) do { } while (0)
+
+#define pte_unmap(pte)			do { } while (0)
+#define pte_unmap_nested(pte)		do { } while (0)
+
+extern void paging_init (void);
+
+/* Used for deferring calls to flush_dcache_page() */
+
+#define PG_dcache_dirty         PG_arch_1
+
+extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t);
+
+/* Encode and de-code a swap entry */
+
+#define __swp_type(x)                     ((x).val & 0x1f)
+#define __swp_offset(x)                   ( (((x).val >> 6) &  0x7) | \
+					  (((x).val >> 8) & ~0x7) )
+#define __swp_entry(type, offset)         ((swp_entry_t) { (type) | \
+					    ((offset &  0x7) << 6) | \
+					    ((offset & ~0x7) << 8) })
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val })
+
+static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
+{
+#ifdef CONFIG_SMP
+	if (!pte_young(*ptep))
+		return 0;
+	return test_and_clear_bit(xlate_pabit(_PAGE_ACCESSED_BIT), &pte_val(*ptep));
+#else
+	pte_t pte = *ptep;
+	if (!pte_young(pte))
+		return 0;
+	set_pte_at(vma->vm_mm, addr, ptep, pte_mkold(pte));
+	return 1;
+#endif
+}
+
+extern spinlock_t pa_dbit_lock;
+
+struct mm_struct;
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	pte_t old_pte;
+	pte_t pte;
+
+	spin_lock(&pa_dbit_lock);
+	pte = old_pte = *ptep;
+	pte_val(pte) &= ~_PAGE_PRESENT;
+	pte_val(pte) |= _PAGE_FLUSH;
+	set_pte_at(mm,addr,ptep,pte);
+	spin_unlock(&pa_dbit_lock);
+
+	return old_pte;
+}
+
+static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+#ifdef CONFIG_SMP
+	unsigned long new, old;
+
+	do {
+		old = pte_val(*ptep);
+		new = pte_val(pte_wrprotect(__pte (old)));
+	} while (cmpxchg((unsigned long *) ptep, old, new) != old);
+#else
+	pte_t old_pte = *ptep;
+	set_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
+#endif
+}
+
+#define pte_same(A,B)	(pte_val(A) == pte_val(B))
+
+#endif /* !__ASSEMBLY__ */
+
+
+/* TLB page size encoding - see table 3-1 in parisc20.pdf */
+#define _PAGE_SIZE_ENCODING_4K		0
+#define _PAGE_SIZE_ENCODING_16K		1
+#define _PAGE_SIZE_ENCODING_64K		2
+#define _PAGE_SIZE_ENCODING_256K	3
+#define _PAGE_SIZE_ENCODING_1M		4
+#define _PAGE_SIZE_ENCODING_4M		5
+#define _PAGE_SIZE_ENCODING_16M		6
+#define _PAGE_SIZE_ENCODING_64M		7
+
+#if defined(CONFIG_PARISC_PAGE_SIZE_4KB)
+# define _PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_4K
+#elif defined(CONFIG_PARISC_PAGE_SIZE_16KB)
+# define _PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_16K
+#elif defined(CONFIG_PARISC_PAGE_SIZE_64KB)
+# define _PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_64K
+#endif
+
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)		\
+		remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+#define pgprot_noncached(prot) __pgprot(pgprot_val(prot) | _PAGE_NO_CACHE)
+
+/* We provide our own get_unmapped_area to provide cache coherency */
+
+#define HAVE_ARCH_UNMAPPED_AREA
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+#define __HAVE_ARCH_PTE_SAME
+#include <asm-generic/pgtable.h>
+
+#endif /* _PARISC_PGTABLE_H */
diff --git a/arch/parisc/include/asm/poll.h b/arch/parisc/include/asm/poll.h
new file mode 100644
index 000000000000..c98509d3149e
--- /dev/null
+++ b/arch/parisc/include/asm/poll.h
@@ -0,0 +1 @@
+#include <asm-generic/poll.h>
diff --git a/arch/parisc/include/asm/posix_types.h b/arch/parisc/include/asm/posix_types.h
new file mode 100644
index 000000000000..bb725a6630bb
--- /dev/null
+++ b/arch/parisc/include/asm/posix_types.h
@@ -0,0 +1,129 @@
+#ifndef __ARCH_PARISC_POSIX_TYPES_H
+#define __ARCH_PARISC_POSIX_TYPES_H
+
+/*
+ * This file is generally used by user-level software, so you need to
+ * be a little careful about namespace pollution etc.  Also, we cannot
+ * assume GCC is being used.
+ */
+typedef unsigned long		__kernel_ino_t;
+typedef unsigned short		__kernel_mode_t;
+typedef unsigned short		__kernel_nlink_t;
+typedef long			__kernel_off_t;
+typedef int			__kernel_pid_t;
+typedef unsigned short		__kernel_ipc_pid_t;
+typedef unsigned int		__kernel_uid_t;
+typedef unsigned int		__kernel_gid_t;
+typedef int			__kernel_suseconds_t;
+typedef long			__kernel_clock_t;
+typedef int			__kernel_timer_t;
+typedef int			__kernel_clockid_t;
+typedef int			__kernel_daddr_t;
+/* Note these change from narrow to wide kernels */
+#ifdef CONFIG_64BIT
+typedef unsigned long		__kernel_size_t;
+typedef long			__kernel_ssize_t;
+typedef long			__kernel_ptrdiff_t;
+typedef long			__kernel_time_t;
+#else
+typedef unsigned int		__kernel_size_t;
+typedef int			__kernel_ssize_t;
+typedef int			__kernel_ptrdiff_t;
+typedef long			__kernel_time_t;
+#endif
+typedef char *			__kernel_caddr_t;
+
+typedef unsigned short		__kernel_uid16_t;
+typedef unsigned short		__kernel_gid16_t;
+typedef unsigned int		__kernel_uid32_t;
+typedef unsigned int		__kernel_gid32_t;
+
+#ifdef __GNUC__
+typedef long long		__kernel_loff_t;
+typedef long long		__kernel_off64_t;
+typedef unsigned long long	__kernel_ino64_t;
+#endif
+
+typedef unsigned int		__kernel_old_dev_t;
+
+typedef struct {
+	int	val[2];
+} __kernel_fsid_t;
+
+/* compatibility stuff */
+typedef __kernel_uid_t __kernel_old_uid_t;
+typedef __kernel_gid_t __kernel_old_gid_t;
+
+#if defined(__KERNEL__)
+
+#undef __FD_SET
+static __inline__ void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
+{
+	unsigned long __tmp = __fd / __NFDBITS;
+	unsigned long __rem = __fd % __NFDBITS;
+	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
+}
+
+#undef __FD_CLR
+static __inline__ void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
+{
+	unsigned long __tmp = __fd / __NFDBITS;
+	unsigned long __rem = __fd % __NFDBITS;
+	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
+}
+
+#undef __FD_ISSET
+static __inline__ int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
+{ 
+	unsigned long __tmp = __fd / __NFDBITS;
+	unsigned long __rem = __fd % __NFDBITS;
+	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
+}
+
+/*
+ * This will unroll the loop for the normal constant case (8 ints,
+ * for a 256-bit fd_set)
+ */
+#undef __FD_ZERO
+static __inline__ void __FD_ZERO(__kernel_fd_set *__p)
+{
+	unsigned long *__tmp = __p->fds_bits;
+	int __i;
+
+	if (__builtin_constant_p(__FDSET_LONGS)) {
+		switch (__FDSET_LONGS) {
+		case 16:
+			__tmp[ 0] = 0; __tmp[ 1] = 0;
+			__tmp[ 2] = 0; __tmp[ 3] = 0;
+			__tmp[ 4] = 0; __tmp[ 5] = 0;
+			__tmp[ 6] = 0; __tmp[ 7] = 0;
+			__tmp[ 8] = 0; __tmp[ 9] = 0;
+			__tmp[10] = 0; __tmp[11] = 0;
+			__tmp[12] = 0; __tmp[13] = 0;
+			__tmp[14] = 0; __tmp[15] = 0;
+			return;
+
+		case 8:
+			__tmp[ 0] = 0; __tmp[ 1] = 0;
+			__tmp[ 2] = 0; __tmp[ 3] = 0;
+			__tmp[ 4] = 0; __tmp[ 5] = 0;
+			__tmp[ 6] = 0; __tmp[ 7] = 0;
+			return;
+
+		case 4:
+			__tmp[ 0] = 0; __tmp[ 1] = 0;
+			__tmp[ 2] = 0; __tmp[ 3] = 0;
+			return;
+		}
+	}
+	__i = __FDSET_LONGS;
+	while (__i) {
+		__i--;
+		*__tmp = 0;
+		__tmp++;
+	}
+}
+
+#endif /* defined(__KERNEL__) */
+
+#endif
diff --git a/arch/parisc/include/asm/prefetch.h b/arch/parisc/include/asm/prefetch.h
new file mode 100644
index 000000000000..c5edc60c059f
--- /dev/null
+++ b/arch/parisc/include/asm/prefetch.h
@@ -0,0 +1,39 @@
+/*
+ * include/asm-parisc/prefetch.h
+ *
+ * PA 2.0 defines data prefetch instructions on page 6-11 of the Kane book.
+ * In addition, many implementations do hardware prefetching of both
+ * instructions and data.
+ *
+ * PA7300LC (page 14-4 of the ERS) also implements prefetching by a load
+ * to gr0 but not in a way that Linux can use.  If the load would cause an
+ * interruption (eg due to prefetching 0), it is suppressed on PA2.0
+ * processors, but not on 7300LC.
+ *
+ */
+
+#ifndef __ASM_PARISC_PREFETCH_H
+#define __ASM_PARISC_PREFETCH_H
+
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_PREFETCH
+
+#define ARCH_HAS_PREFETCH
+static inline void prefetch(const void *addr)
+{
+	__asm__("ldw 0(%0), %%r0" : : "r" (addr));
+}
+
+/* LDD is a PA2.0 addition. */
+#ifdef CONFIG_PA20
+#define ARCH_HAS_PREFETCHW
+static inline void prefetchw(const void *addr)
+{
+	__asm__("ldd 0(%0), %%r0" : : "r" (addr));
+}
+#endif /* CONFIG_PA20 */
+
+#endif /* CONFIG_PREFETCH */
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_PARISC_PROCESSOR_H */
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
new file mode 100644
index 000000000000..3c9d34844c83
--- /dev/null
+++ b/arch/parisc/include/asm/processor.h
@@ -0,0 +1,357 @@
+/*
+ * include/asm-parisc/processor.h
+ *
+ * Copyright (C) 1994 Linus Torvalds
+ * Copyright (C) 2001 Grant Grundler
+ */
+
+#ifndef __ASM_PARISC_PROCESSOR_H
+#define __ASM_PARISC_PROCESSOR_H
+
+#ifndef __ASSEMBLY__
+#include <linux/threads.h>
+
+#include <asm/prefetch.h>
+#include <asm/hardware.h>
+#include <asm/pdc.h>
+#include <asm/ptrace.h>
+#include <asm/types.h>
+#include <asm/system.h>
+#endif /* __ASSEMBLY__ */
+
+#define KERNEL_STACK_SIZE 	(4*PAGE_SIZE)
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+#ifdef CONFIG_PA20
+#define current_ia(x)	__asm__("mfia %0" : "=r"(x))
+#else /* mfia added in pa2.0 */
+#define current_ia(x)	__asm__("blr 0,%0\n\tnop" : "=r"(x))
+#endif
+#define current_text_addr() ({ void *pc; current_ia(pc); pc; })
+
+#define TASK_SIZE_OF(tsk)       ((tsk)->thread.task_size)
+#define TASK_SIZE	        TASK_SIZE_OF(current)
+#define TASK_UNMAPPED_BASE      (current->thread.map_base)
+
+#define DEFAULT_TASK_SIZE32	(0xFFF00000UL)
+#define DEFAULT_MAP_BASE32	(0x40000000UL)
+
+#ifdef CONFIG_64BIT
+#define DEFAULT_TASK_SIZE       (MAX_ADDRESS-0xf000000)
+#define DEFAULT_MAP_BASE        (0x200000000UL)
+#else
+#define DEFAULT_TASK_SIZE	DEFAULT_TASK_SIZE32
+#define DEFAULT_MAP_BASE	DEFAULT_MAP_BASE32
+#endif
+
+#ifdef __KERNEL__
+
+/* XXX: STACK_TOP actually should be STACK_BOTTOM for parisc.
+ * prumpf */
+
+#define STACK_TOP	TASK_SIZE
+#define STACK_TOP_MAX	DEFAULT_TASK_SIZE
+
+#endif
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Data detected about CPUs at boot time which is the same for all CPU's.
+ * HP boxes are SMP - ie identical processors.
+ *
+ * FIXME: some CPU rev info may be processor specific...
+ */
+struct system_cpuinfo_parisc {
+	unsigned int	cpu_count;
+	unsigned int	cpu_hz;
+	unsigned int	hversion;
+	unsigned int	sversion;
+	enum cpu_type	cpu_type;
+
+	struct {
+		struct pdc_model model;
+		unsigned long versions;
+		unsigned long cpuid;
+		unsigned long capabilities;
+		char   sys_model_name[81]; /* PDC-ROM returnes this model name */
+	} pdc;
+
+	const char	*cpu_name;	/* e.g. "PA7300LC (PCX-L2)" */
+	const char	*family_name;	/* e.g. "1.1e" */
+};
+
+
+/* Per CPU data structure - ie varies per CPU.  */
+struct cpuinfo_parisc {
+	unsigned long it_value;     /* Interval Timer at last timer Intr */
+	unsigned long it_delta;     /* Interval delta (tic_10ms / HZ * 100) */
+	unsigned long irq_count;    /* number of IRQ's since boot */
+	unsigned long irq_max_cr16; /* longest time to handle a single IRQ */
+	unsigned long cpuid;        /* aka slot_number or set to NO_PROC_ID */
+	unsigned long hpa;          /* Host Physical address */
+	unsigned long txn_addr;     /* MMIO addr of EIR or id_eid */
+#ifdef CONFIG_SMP
+	unsigned long pending_ipi;  /* bitmap of type ipi_message_type */
+	unsigned long ipi_count;    /* number ipi Interrupts */
+#endif
+	unsigned long bh_count;     /* number of times bh was invoked */
+	unsigned long prof_counter; /* per CPU profiling support */
+	unsigned long prof_multiplier;	/* per CPU profiling support */
+	unsigned long fp_rev;
+	unsigned long fp_model;
+	unsigned int state;
+	struct parisc_device *dev;
+	unsigned long loops_per_jiffy;
+};
+
+extern struct system_cpuinfo_parisc boot_cpu_data;
+extern struct cpuinfo_parisc cpu_data[NR_CPUS];
+#define current_cpu_data cpu_data[smp_processor_id()]
+
+#define CPU_HVERSION ((boot_cpu_data.hversion >> 4) & 0x0FFF)
+
+typedef struct {
+	int seg;  
+} mm_segment_t;
+
+#define ARCH_MIN_TASKALIGN	8
+
+struct thread_struct {
+	struct pt_regs regs;
+	unsigned long  task_size;
+	unsigned long  map_base;
+	unsigned long  flags;
+}; 
+
+/* Thread struct flags. */
+#define PARISC_UAC_NOPRINT	(1UL << 0)	/* see prctl and unaligned.c */
+#define PARISC_UAC_SIGBUS	(1UL << 1)
+#define PARISC_KERNEL_DEATH	(1UL << 31)	/* see die_if_kernel()... */
+
+#define PARISC_UAC_SHIFT	0
+#define PARISC_UAC_MASK		(PARISC_UAC_NOPRINT|PARISC_UAC_SIGBUS)
+
+#define SET_UNALIGN_CTL(task,value)                                       \
+        ({                                                                \
+        (task)->thread.flags = (((task)->thread.flags & ~PARISC_UAC_MASK) \
+                                | (((value) << PARISC_UAC_SHIFT) &        \
+                                   PARISC_UAC_MASK));                     \
+        0;                                                                \
+        })
+
+#define GET_UNALIGN_CTL(task,addr)                                        \
+        ({                                                                \
+        put_user(((task)->thread.flags & PARISC_UAC_MASK)                 \
+                 >> PARISC_UAC_SHIFT, (int __user *) (addr));             \
+        })
+
+#define INIT_THREAD { \
+	.regs = {	.gr	= { 0, }, \
+			.fr	= { 0, }, \
+			.sr	= { 0, }, \
+			.iasq	= { 0, }, \
+			.iaoq	= { 0, }, \
+			.cr27	= 0, \
+		}, \
+	.task_size	= DEFAULT_TASK_SIZE, \
+	.map_base	= DEFAULT_MAP_BASE, \
+	.flags		= 0 \
+	}
+
+/*
+ * Return saved PC of a blocked thread.  This is used by ps mostly.
+ */
+
+unsigned long thread_saved_pc(struct task_struct *t);
+void show_trace(struct task_struct *task, unsigned long *stack);
+
+/*
+ * Start user thread in another space.
+ *
+ * Note that we set both the iaoq and r31 to the new pc. When
+ * the kernel initially calls execve it will return through an
+ * rfi path that will use the values in the iaoq. The execve
+ * syscall path will return through the gateway page, and
+ * that uses r31 to branch to.
+ *
+ * For ELF we clear r23, because the dynamic linker uses it to pass
+ * the address of the finalizer function.
+ *
+ * We also initialize sr3 to an illegal value (illegal for our
+ * implementation, not for the architecture).
+ */
+typedef unsigned int elf_caddr_t;
+
+#define start_thread_som(regs, new_pc, new_sp) do {	\
+	unsigned long *sp = (unsigned long *)new_sp;	\
+	__u32 spaceid = (__u32)current->mm->context;	\
+	unsigned long pc = (unsigned long)new_pc;	\
+	/* offset pc for priv. level */			\
+	pc |= 3;					\
+							\
+	set_fs(USER_DS);				\
+	regs->iasq[0] = spaceid;			\
+	regs->iasq[1] = spaceid;			\
+	regs->iaoq[0] = pc;				\
+	regs->iaoq[1] = pc + 4;                         \
+	regs->sr[2] = LINUX_GATEWAY_SPACE;              \
+	regs->sr[3] = 0xffff;				\
+	regs->sr[4] = spaceid;				\
+	regs->sr[5] = spaceid;				\
+	regs->sr[6] = spaceid;				\
+	regs->sr[7] = spaceid;				\
+	regs->gr[ 0] = USER_PSW;                        \
+	regs->gr[30] = ((new_sp)+63)&~63;		\
+	regs->gr[31] = pc;				\
+							\
+	get_user(regs->gr[26],&sp[0]);			\
+	get_user(regs->gr[25],&sp[-1]); 		\
+	get_user(regs->gr[24],&sp[-2]); 		\
+	get_user(regs->gr[23],&sp[-3]); 		\
+} while(0)
+
+/* The ELF abi wants things done a "wee bit" differently than
+ * som does.  Supporting this behavior here avoids
+ * having our own version of create_elf_tables.
+ *
+ * Oh, and yes, that is not a typo, we are really passing argc in r25
+ * and argv in r24 (rather than r26 and r25).  This is because that's
+ * where __libc_start_main wants them.
+ *
+ * Duplicated from dl-machine.h for the benefit of readers:
+ *
+ *  Our initial stack layout is rather different from everyone else's
+ *  due to the unique PA-RISC ABI.  As far as I know it looks like
+ *  this:
+
+   -----------------------------------  (user startup code creates this frame)
+   |         32 bytes of magic       |
+   |---------------------------------|
+   | 32 bytes argument/sp save area  |
+   |---------------------------------| (bprm->p)
+   |	    ELF auxiliary info	     |
+   |         (up to 28 words)        |
+   |---------------------------------|
+   |		   NULL		     |
+   |---------------------------------|
+   |	   Environment pointers	     |
+   |---------------------------------|
+   |		   NULL		     |
+   |---------------------------------|
+   |        Argument pointers        |
+   |---------------------------------| <- argv
+   |          argc (1 word)          |
+   |---------------------------------| <- bprm->exec (HACK!)
+   |         N bytes of slack        |
+   |---------------------------------|
+   |	filename passed to execve    |
+   |---------------------------------| (mm->env_end)
+   |           env strings           |
+   |---------------------------------| (mm->env_start, mm->arg_end)
+   |           arg strings           |
+   |---------------------------------|
+   | additional faked arg strings if |
+   | we're invoked via binfmt_script |
+   |---------------------------------| (mm->arg_start)
+   stack base is at TASK_SIZE - rlim_max.
+
+on downward growing arches, it looks like this:
+   stack base at TASK_SIZE
+   | filename passed to execve
+   | env strings
+   | arg strings
+   | faked arg strings
+   | slack
+   | ELF
+   | envps
+   | argvs
+   | argc
+
+ *  The pleasant part of this is that if we need to skip arguments we
+ *  can just decrement argc and move argv, because the stack pointer
+ *  is utterly unrelated to the location of the environment and
+ *  argument vectors.
+ *
+ * Note that the S/390 people took the easy way out and hacked their
+ * GCC to make the stack grow downwards.
+ *
+ * Final Note: For entry from syscall, the W (wide) bit of the PSW
+ * is stuffed into the lowest bit of the user sp (%r30), so we fill
+ * it in here from the current->personality
+ */
+
+#ifdef CONFIG_64BIT
+#define USER_WIDE_MODE	(!test_thread_flag(TIF_32BIT))
+#else
+#define USER_WIDE_MODE	0
+#endif
+
+#define start_thread(regs, new_pc, new_sp) do {		\
+	elf_addr_t *sp = (elf_addr_t *)new_sp;		\
+	__u32 spaceid = (__u32)current->mm->context;	\
+	elf_addr_t pc = (elf_addr_t)new_pc | 3;		\
+	elf_caddr_t *argv = (elf_caddr_t *)bprm->exec + 1;	\
+							\
+	set_fs(USER_DS);				\
+	regs->iasq[0] = spaceid;			\
+	regs->iasq[1] = spaceid;			\
+	regs->iaoq[0] = pc;				\
+	regs->iaoq[1] = pc + 4;                         \
+	regs->sr[2] = LINUX_GATEWAY_SPACE;              \
+	regs->sr[3] = 0xffff;				\
+	regs->sr[4] = spaceid;				\
+	regs->sr[5] = spaceid;				\
+	regs->sr[6] = spaceid;				\
+	regs->sr[7] = spaceid;				\
+	regs->gr[ 0] = USER_PSW | (USER_WIDE_MODE ? PSW_W : 0); \
+	regs->fr[ 0] = 0LL;                            	\
+	regs->fr[ 1] = 0LL;                            	\
+	regs->fr[ 2] = 0LL;                            	\
+	regs->fr[ 3] = 0LL;                            	\
+	regs->gr[30] = (((unsigned long)sp + 63) &~ 63) | (USER_WIDE_MODE ? 1 : 0); \
+	regs->gr[31] = pc;				\
+							\
+	get_user(regs->gr[25], (argv - 1));		\
+	regs->gr[24] = (long) argv;			\
+	regs->gr[23] = 0;				\
+} while(0)
+
+struct task_struct;
+struct mm_struct;
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
+
+/* Prepare to copy thread state - unlazy all lazy status */
+#define prepare_to_copy(tsk)	do { } while (0)
+
+extern void map_hpux_gateway_page(struct task_struct *tsk, struct mm_struct *mm);
+
+extern unsigned long get_wchan(struct task_struct *p);
+
+#define KSTK_EIP(tsk)	((tsk)->thread.regs.iaoq[0])
+#define KSTK_ESP(tsk)	((tsk)->thread.regs.gr[30])
+
+#define cpu_relax()	barrier()
+
+/* Used as a macro to identify the combined VIPT/PIPT cached
+ * CPUs which require a guarantee of coherency (no inequivalent
+ * aliases with different data, whether clean or not) to operate */
+static inline int parisc_requires_coherency(void)
+{
+#ifdef CONFIG_PA8X00
+	return (boot_cpu_data.cpu_type == mako) ||
+		(boot_cpu_data.cpu_type == mako2);
+#else
+	return 0;
+#endif
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_PARISC_PROCESSOR_H */
diff --git a/arch/parisc/include/asm/psw.h b/arch/parisc/include/asm/psw.h
new file mode 100644
index 000000000000..5a3e23c9ce63
--- /dev/null
+++ b/arch/parisc/include/asm/psw.h
@@ -0,0 +1,62 @@
+#ifndef _PARISC_PSW_H
+
+
+#define	PSW_I	0x00000001
+#define	PSW_D	0x00000002
+#define	PSW_P	0x00000004
+#define	PSW_Q	0x00000008
+
+#define	PSW_R	0x00000010
+#define	PSW_F	0x00000020
+#define	PSW_G	0x00000040	/* PA1.x only */
+#define PSW_O	0x00000080	/* PA2.0 only */
+
+/* ssm/rsm instructions number PSW_W and PSW_E differently */
+#define PSW_SM_I	PSW_I	/* Enable External Interrupts */
+#define PSW_SM_D	PSW_D
+#define PSW_SM_P	PSW_P
+#define PSW_SM_Q	PSW_Q	/* Enable Interrupt State Collection */
+#define PSW_SM_R	PSW_R	/* Enable Recover Counter Trap */
+#define PSW_SM_W	0x200	/* PA2.0 only : Enable Wide Mode */
+
+#define PSW_SM_QUIET	PSW_SM_R+PSW_SM_Q+PSW_SM_P+PSW_SM_D+PSW_SM_I
+
+#define PSW_CB	0x0000ff00
+
+#define	PSW_M	0x00010000
+#define	PSW_V	0x00020000
+#define	PSW_C	0x00040000
+#define	PSW_B	0x00080000
+
+#define	PSW_X	0x00100000
+#define	PSW_N	0x00200000
+#define	PSW_L	0x00400000
+#define	PSW_H	0x00800000
+
+#define	PSW_T	0x01000000
+#define	PSW_S	0x02000000
+#define	PSW_E	0x04000000
+#define PSW_W	0x08000000	/* PA2.0 only */
+#define PSW_W_BIT       36      /* PA2.0 only */
+
+#define	PSW_Z	0x40000000	/* PA1.x only */
+#define	PSW_Y	0x80000000	/* PA1.x only */
+
+#ifdef CONFIG_64BIT
+#  define PSW_HI_CB 0x000000ff    /* PA2.0 only */
+#endif
+
+#ifdef CONFIG_64BIT
+#  define USER_PSW_HI_MASK	PSW_HI_CB
+#  define WIDE_PSW		PSW_W
+#else 
+#  define WIDE_PSW		0
+#endif
+
+/* Used when setting up for rfi */
+#define KERNEL_PSW    (WIDE_PSW | PSW_C | PSW_Q | PSW_P | PSW_D)
+#define REAL_MODE_PSW (WIDE_PSW | PSW_Q)
+#define USER_PSW_MASK (WIDE_PSW | PSW_T | PSW_N | PSW_X | PSW_B | PSW_V | PSW_CB)
+#define USER_PSW      (PSW_C | PSW_Q | PSW_P | PSW_D | PSW_I)
+
+#endif
diff --git a/arch/parisc/include/asm/ptrace.h b/arch/parisc/include/asm/ptrace.h
new file mode 100644
index 000000000000..3e94c5d85ff5
--- /dev/null
+++ b/arch/parisc/include/asm/ptrace.h
@@ -0,0 +1,58 @@
+#ifndef _PARISC_PTRACE_H
+#define _PARISC_PTRACE_H
+
+/* written by Philipp Rumpf, Copyright (C) 1999 SuSE GmbH Nuernberg
+** Copyright (C) 2000 Grant Grundler, Hewlett-Packard
+*/
+
+#include <linux/types.h>
+
+/* This struct defines the way the registers are stored on the 
+ * stack during a system call.
+ *
+ * N.B. gdb/strace care about the size and offsets within this
+ * structure. If you change things, you may break object compatibility
+ * for those applications.
+ */
+
+struct pt_regs {
+	unsigned long gr[32];	/* PSW is in gr[0] */
+	__u64 fr[32];
+	unsigned long sr[ 8];
+	unsigned long iasq[2];
+	unsigned long iaoq[2];
+	unsigned long cr27;
+	unsigned long pad0;     /* available for other uses */
+	unsigned long orig_r28;
+	unsigned long ksp;
+	unsigned long kpc;
+	unsigned long sar;	/* CR11 */
+	unsigned long iir;	/* CR19 */
+	unsigned long isr;	/* CR20 */
+	unsigned long ior;	/* CR21 */
+	unsigned long ipsw;	/* CR22 */
+};
+
+/*
+ * The numbers chosen here are somewhat arbitrary but absolutely MUST
+ * not overlap with any of the number assigned in <linux/ptrace.h>.
+ *
+ * These ones are taken from IA-64 on the assumption that theirs are
+ * the most correct (and we also want to support PTRACE_SINGLEBLOCK
+ * since we have taken branch traps too)
+ */
+#define PTRACE_SINGLEBLOCK	12	/* resume execution until next branch */
+
+#ifdef __KERNEL__
+
+#define task_regs(task) ((struct pt_regs *) ((char *)(task) + TASK_REGS))
+
+/* XXX should we use iaoq[1] or iaoq[0] ? */
+#define user_mode(regs)			(((regs)->iaoq[0] & 3) ? 1 : 0)
+#define user_space(regs)		(((regs)->iasq[1] != 0) ? 1 : 0)
+#define instruction_pointer(regs)	((regs)->iaoq[0] & ~3)
+unsigned long profile_pc(struct pt_regs *);
+extern void show_regs(struct pt_regs *);
+#endif
+
+#endif
diff --git a/arch/parisc/include/asm/real.h b/arch/parisc/include/asm/real.h
new file mode 100644
index 000000000000..82acb25db395
--- /dev/null
+++ b/arch/parisc/include/asm/real.h
@@ -0,0 +1,5 @@
+#ifndef _PARISC_REAL_H
+#define _PARISC_REAL_H
+
+
+#endif
diff --git a/arch/parisc/include/asm/resource.h b/arch/parisc/include/asm/resource.h
new file mode 100644
index 000000000000..8b06343b62ed
--- /dev/null
+++ b/arch/parisc/include/asm/resource.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_PARISC_RESOURCE_H
+#define _ASM_PARISC_RESOURCE_H
+
+#define _STK_LIM_MAX	10 * _STK_LIM
+#include <asm-generic/resource.h>
+
+#endif
diff --git a/arch/parisc/include/asm/ropes.h b/arch/parisc/include/asm/ropes.h
new file mode 100644
index 000000000000..09f51d5ab57c
--- /dev/null
+++ b/arch/parisc/include/asm/ropes.h
@@ -0,0 +1,322 @@
+#ifndef _ASM_PARISC_ROPES_H_
+#define _ASM_PARISC_ROPES_H_
+
+#include <asm/parisc-device.h>
+
+#ifdef CONFIG_64BIT
+/* "low end" PA8800 machines use ZX1 chipset: PAT PDC and only run 64-bit */
+#define ZX1_SUPPORT
+#endif
+
+#ifdef CONFIG_PROC_FS
+/* depends on proc fs support. But costs CPU performance */
+#undef SBA_COLLECT_STATS
+#endif
+
+/*
+** The number of pdir entries to "free" before issuing
+** a read to PCOM register to flush out PCOM writes.
+** Interacts with allocation granularity (ie 4 or 8 entries
+** allocated and free'd/purged at a time might make this
+** less interesting).
+*/
+#define DELAYED_RESOURCE_CNT	16
+
+#define MAX_IOC		2	/* per Ike. Pluto/Astro only have 1. */
+#define ROPES_PER_IOC	8	/* per Ike half or Pluto/Astro */
+
+struct ioc {
+	void __iomem	*ioc_hpa;	/* I/O MMU base address */
+	char		*res_map;	/* resource map, bit == pdir entry */
+	u64		*pdir_base;	/* physical base address */
+	unsigned long	ibase;		/* pdir IOV Space base - shared w/lba_pci */
+	unsigned long	imask;		/* pdir IOV Space mask - shared w/lba_pci */
+#ifdef ZX1_SUPPORT
+	unsigned long	iovp_mask;	/* help convert IOVA to IOVP */
+#endif
+	unsigned long	*res_hint;	/* next avail IOVP - circular search */
+	spinlock_t	res_lock;
+	unsigned int	res_bitshift;	/* from the LEFT! */
+	unsigned int	res_size;	/* size of resource map in bytes */
+#ifdef SBA_HINT_SUPPORT
+/* FIXME : DMA HINTs not used */
+	unsigned long	hint_mask_pdir; /* bits used for DMA hints */
+	unsigned int	hint_shift_pdir;
+#endif
+#if DELAYED_RESOURCE_CNT > 0
+	int		saved_cnt;
+	struct sba_dma_pair {
+			dma_addr_t	iova;
+			size_t		size;
+        } saved[DELAYED_RESOURCE_CNT];
+#endif
+
+#ifdef SBA_COLLECT_STATS
+#define SBA_SEARCH_SAMPLE	0x100
+	unsigned long	avg_search[SBA_SEARCH_SAMPLE];
+	unsigned long	avg_idx;	/* current index into avg_search */
+	unsigned long	used_pages;
+	unsigned long	msingle_calls;
+	unsigned long	msingle_pages;
+	unsigned long	msg_calls;
+	unsigned long	msg_pages;
+	unsigned long	usingle_calls;
+	unsigned long	usingle_pages;
+	unsigned long	usg_calls;
+	unsigned long	usg_pages;
+#endif
+        /* STUFF We don't need in performance path */
+	unsigned int	pdir_size;	/* in bytes, determined by IOV Space size */
+};
+
+struct sba_device {
+	struct sba_device	*next;  /* list of SBA's in system */
+	struct parisc_device	*dev;   /* dev found in bus walk */
+	const char		*name;
+	void __iomem		*sba_hpa; /* base address */
+	spinlock_t		sba_lock;
+	unsigned int		flags;  /* state/functionality enabled */
+	unsigned int		hw_rev;  /* HW revision of chip */
+
+	struct resource		chip_resv; /* MMIO reserved for chip */
+	struct resource		iommu_resv; /* MMIO reserved for iommu */
+
+	unsigned int		num_ioc;  /* number of on-board IOC's */
+	struct ioc		ioc[MAX_IOC];
+};
+
+#define ASTRO_RUNWAY_PORT	0x582
+#define IKE_MERCED_PORT		0x803
+#define REO_MERCED_PORT		0x804
+#define REOG_MERCED_PORT	0x805
+#define PLUTO_MCKINLEY_PORT	0x880
+
+static inline int IS_ASTRO(struct parisc_device *d) {
+	return d->id.hversion == ASTRO_RUNWAY_PORT;
+}
+
+static inline int IS_IKE(struct parisc_device *d) {
+	return d->id.hversion == IKE_MERCED_PORT;
+}
+
+static inline int IS_PLUTO(struct parisc_device *d) {
+	return d->id.hversion == PLUTO_MCKINLEY_PORT;
+}
+
+#define PLUTO_IOVA_BASE	(1UL*1024*1024*1024)	/* 1GB */
+#define PLUTO_IOVA_SIZE	(1UL*1024*1024*1024)	/* 1GB */
+#define PLUTO_GART_SIZE	(PLUTO_IOVA_SIZE / 2)
+
+#define SBA_PDIR_VALID_BIT	0x8000000000000000ULL
+
+#define SBA_AGPGART_COOKIE	0x0000badbadc0ffeeULL
+
+#define SBA_FUNC_ID	0x0000	/* function id */
+#define SBA_FCLASS	0x0008	/* function class, bist, header, rev... */
+
+#define SBA_FUNC_SIZE 4096   /* SBA configuration function reg set */
+
+#define ASTRO_IOC_OFFSET	(32 * SBA_FUNC_SIZE)
+#define PLUTO_IOC_OFFSET	(1 * SBA_FUNC_SIZE)
+/* Ike's IOC's occupy functions 2 and 3 */
+#define IKE_IOC_OFFSET(p)	((p+2) * SBA_FUNC_SIZE)
+
+#define IOC_CTRL          0x8	/* IOC_CTRL offset */
+#define IOC_CTRL_TC       (1 << 0) /* TOC Enable */
+#define IOC_CTRL_CE       (1 << 1) /* Coalesce Enable */
+#define IOC_CTRL_DE       (1 << 2) /* Dillon Enable */
+#define IOC_CTRL_RM       (1 << 8) /* Real Mode */
+#define IOC_CTRL_NC       (1 << 9) /* Non Coherent Mode */
+#define IOC_CTRL_D4       (1 << 11) /* Disable 4-byte coalescing */
+#define IOC_CTRL_DD       (1 << 13) /* Disable distr. LMMIO range coalescing */
+
+/*
+** Offsets into MBIB (Function 0 on Ike and hopefully Astro)
+** Firmware programs this stuff. Don't touch it.
+*/
+#define LMMIO_DIRECT0_BASE  0x300
+#define LMMIO_DIRECT0_MASK  0x308
+#define LMMIO_DIRECT0_ROUTE 0x310
+
+#define LMMIO_DIST_BASE  0x360
+#define LMMIO_DIST_MASK  0x368
+#define LMMIO_DIST_ROUTE 0x370
+
+#define IOS_DIST_BASE	0x390
+#define IOS_DIST_MASK	0x398
+#define IOS_DIST_ROUTE	0x3A0
+
+#define IOS_DIRECT_BASE	0x3C0
+#define IOS_DIRECT_MASK	0x3C8
+#define IOS_DIRECT_ROUTE 0x3D0
+
+/*
+** Offsets into I/O TLB (Function 2 and 3 on Ike)
+*/
+#define ROPE0_CTL	0x200  /* "regbus pci0" */
+#define ROPE1_CTL	0x208
+#define ROPE2_CTL	0x210
+#define ROPE3_CTL	0x218
+#define ROPE4_CTL	0x220
+#define ROPE5_CTL	0x228
+#define ROPE6_CTL	0x230
+#define ROPE7_CTL	0x238
+
+#define IOC_ROPE0_CFG	0x500	/* pluto only */
+#define   IOC_ROPE_AO	  0x10	/* Allow "Relaxed Ordering" */
+
+#define HF_ENABLE	0x40
+
+#define IOC_IBASE	0x300	/* IO TLB */
+#define IOC_IMASK	0x308
+#define IOC_PCOM	0x310
+#define IOC_TCNFG	0x318
+#define IOC_PDIR_BASE	0x320
+
+/*
+** IOC supports 4/8/16/64KB page sizes (see TCNFG register)
+** It's safer (avoid memory corruption) to keep DMA page mappings
+** equivalently sized to VM PAGE_SIZE.
+**
+** We really can't avoid generating a new mapping for each
+** page since the Virtual Coherence Index has to be generated
+** and updated for each page.
+**
+** PAGE_SIZE could be greater than IOVP_SIZE. But not the inverse.
+*/
+#define IOVP_SIZE	PAGE_SIZE
+#define IOVP_SHIFT	PAGE_SHIFT
+#define IOVP_MASK	PAGE_MASK
+
+#define SBA_PERF_CFG	0x708	/* Performance Counter stuff */
+#define SBA_PERF_MASK1	0x718
+#define SBA_PERF_MASK2	0x730
+
+/*
+** Offsets into PCI Performance Counters (functions 12 and 13)
+** Controlled by PERF registers in function 2 & 3 respectively.
+*/
+#define SBA_PERF_CNT1	0x200
+#define SBA_PERF_CNT2	0x208
+#define SBA_PERF_CNT3	0x210
+
+/*
+** lba_device: Per instance Elroy data structure
+*/
+struct lba_device {
+	struct pci_hba_data	hba;
+
+	spinlock_t		lba_lock;
+	void			*iosapic_obj;
+
+#ifdef CONFIG_64BIT
+	void __iomem		*iop_base;	/* PA_VIEW - for IO port accessor funcs */
+#endif
+
+	int			flags;		/* state/functionality enabled */
+	int			hw_rev;		/* HW revision of chip */
+};
+
+#define ELROY_HVERS		0x782
+#define MERCURY_HVERS		0x783
+#define QUICKSILVER_HVERS	0x784
+
+static inline int IS_ELROY(struct parisc_device *d) {
+	return (d->id.hversion == ELROY_HVERS);
+}
+
+static inline int IS_MERCURY(struct parisc_device *d) {
+	return (d->id.hversion == MERCURY_HVERS);
+}
+
+static inline int IS_QUICKSILVER(struct parisc_device *d) {
+	return (d->id.hversion == QUICKSILVER_HVERS);
+}
+
+static inline int agp_mode_mercury(void __iomem *hpa) {
+	u64 bus_mode;
+
+	bus_mode = readl(hpa + 0x0620);
+	if (bus_mode & 1)
+		return 1;
+
+	return 0;
+}
+
+/*
+** I/O SAPIC init function
+** Caller knows where an I/O SAPIC is. LBA has an integrated I/O SAPIC.
+** Call setup as part of per instance initialization.
+** (ie *not* init_module() function unless only one is present.)
+** fixup_irq is to initialize PCI IRQ line support and
+** virtualize pcidev->irq value. To be called by pci_fixup_bus().
+*/
+extern void *iosapic_register(unsigned long hpa);
+extern int iosapic_fixup_irq(void *obj, struct pci_dev *pcidev);
+
+#define LBA_FUNC_ID	0x0000	/* function id */
+#define LBA_FCLASS	0x0008	/* function class, bist, header, rev... */
+#define LBA_CAPABLE	0x0030	/* capabilities register */
+
+#define LBA_PCI_CFG_ADDR	0x0040	/* poke CFG address here */
+#define LBA_PCI_CFG_DATA	0x0048	/* read or write data here */
+
+#define LBA_PMC_MTLT	0x0050	/* Firmware sets this - read only. */
+#define LBA_FW_SCRATCH	0x0058	/* Firmware writes the PCI bus number here. */
+#define LBA_ERROR_ADDR	0x0070	/* On error, address gets logged here */
+
+#define LBA_ARB_MASK	0x0080	/* bit 0 enable arbitration. PAT/PDC enables */
+#define LBA_ARB_PRI	0x0088	/* firmware sets this. */
+#define LBA_ARB_MODE	0x0090	/* firmware sets this. */
+#define LBA_ARB_MTLT	0x0098	/* firmware sets this. */
+
+#define LBA_MOD_ID	0x0100	/* Module ID. PDC_PAT_CELL reports 4 */
+
+#define LBA_STAT_CTL	0x0108	/* Status & Control */
+#define   LBA_BUS_RESET		0x01	/*  Deassert PCI Bus Reset Signal */
+#define   CLEAR_ERRLOG		0x10	/*  "Clear Error Log" cmd */
+#define   CLEAR_ERRLOG_ENABLE	0x20	/*  "Clear Error Log" Enable */
+#define   HF_ENABLE	0x40	/*    enable HF mode (default is -1 mode) */
+
+#define LBA_LMMIO_BASE	0x0200	/* < 4GB I/O address range */
+#define LBA_LMMIO_MASK	0x0208
+
+#define LBA_GMMIO_BASE	0x0210	/* > 4GB I/O address range */
+#define LBA_GMMIO_MASK	0x0218
+
+#define LBA_WLMMIO_BASE	0x0220	/* All < 4GB ranges under the same *SBA* */
+#define LBA_WLMMIO_MASK	0x0228
+
+#define LBA_WGMMIO_BASE	0x0230	/* All > 4GB ranges under the same *SBA* */
+#define LBA_WGMMIO_MASK	0x0238
+
+#define LBA_IOS_BASE	0x0240	/* I/O port space for this LBA */
+#define LBA_IOS_MASK	0x0248
+
+#define LBA_ELMMIO_BASE	0x0250	/* Extra LMMIO range */
+#define LBA_ELMMIO_MASK	0x0258
+
+#define LBA_EIOS_BASE	0x0260	/* Extra I/O port space */
+#define LBA_EIOS_MASK	0x0268
+
+#define LBA_GLOBAL_MASK	0x0270	/* Mercury only: Global Address Mask */
+#define LBA_DMA_CTL	0x0278	/* firmware sets this */
+
+#define LBA_IBASE	0x0300	/* SBA DMA support */
+#define LBA_IMASK	0x0308
+
+/* FIXME: ignore DMA Hint stuff until we can measure performance */
+#define LBA_HINT_CFG	0x0310
+#define LBA_HINT_BASE	0x0380	/* 14 registers at every 8 bytes. */
+
+#define LBA_BUS_MODE	0x0620
+
+/* ERROR regs are needed for config cycle kluges */
+#define LBA_ERROR_CONFIG 0x0680
+#define     LBA_SMART_MODE 0x20
+#define LBA_ERROR_STATUS 0x0688
+#define LBA_ROPE_CTL     0x06A0
+
+#define LBA_IOSAPIC_BASE	0x800 /* Offset of IRQ logic */
+
+#endif /*_ASM_PARISC_ROPES_H_*/
diff --git a/arch/parisc/include/asm/rt_sigframe.h b/arch/parisc/include/asm/rt_sigframe.h
new file mode 100644
index 000000000000..f0dd3b30f6c4
--- /dev/null
+++ b/arch/parisc/include/asm/rt_sigframe.h
@@ -0,0 +1,23 @@
+#ifndef _ASM_PARISC_RT_SIGFRAME_H
+#define _ASM_PARISC_RT_SIGFRAME_H
+
+#define SIGRETURN_TRAMP 4
+#define SIGRESTARTBLOCK_TRAMP 5 
+#define TRAMP_SIZE (SIGRETURN_TRAMP + SIGRESTARTBLOCK_TRAMP)
+
+struct rt_sigframe {
+	/* XXX: Must match trampoline size in arch/parisc/kernel/signal.c 
+	        Secondary to that it must protect the ERESTART_RESTARTBLOCK
+		trampoline we left on the stack (we were bad and didn't 
+		change sp so we could run really fast.) */
+	unsigned int tramp[TRAMP_SIZE];
+	struct siginfo info;
+	struct ucontext uc;
+};
+
+#define	SIGFRAME		128
+#define FUNCTIONCALLFRAME	96
+#define PARISC_RT_SIGFRAME_SIZE					\
+	(((sizeof(struct rt_sigframe) + FUNCTIONCALLFRAME) + SIGFRAME) & -SIGFRAME)
+
+#endif
diff --git a/arch/parisc/include/asm/rtc.h b/arch/parisc/include/asm/rtc.h
new file mode 100644
index 000000000000..099d641a42c2
--- /dev/null
+++ b/arch/parisc/include/asm/rtc.h
@@ -0,0 +1,131 @@
+/* 
+ * include/asm-parisc/rtc.h
+ *
+ * Copyright 2002 Randolph CHung <tausq@debian.org>
+ *
+ * Based on: include/asm-ppc/rtc.h and the genrtc driver in the
+ * 2.4 parisc linux tree
+ */
+
+#ifndef __ASM_RTC_H__
+#define __ASM_RTC_H__
+
+#ifdef __KERNEL__
+
+#include <linux/rtc.h>
+
+#include <asm/pdc.h>
+
+#define SECS_PER_HOUR   (60 * 60)
+#define SECS_PER_DAY    (SECS_PER_HOUR * 24)
+
+
+#define RTC_PIE 0x40		/* periodic interrupt enable */
+#define RTC_AIE 0x20		/* alarm interrupt enable */
+#define RTC_UIE 0x10		/* update-finished interrupt enable */
+
+#define RTC_BATT_BAD 0x100	/* battery bad */
+
+/* some dummy definitions */
+#define RTC_SQWE 0x08		/* enable square-wave output */
+#define RTC_DM_BINARY 0x04	/* all time/date values are BCD if clear */
+#define RTC_24H 0x02		/* 24 hour mode - else hours bit 7 means pm */
+#define RTC_DST_EN 0x01	        /* auto switch DST - works f. USA only */
+
+# define __isleap(year) \
+  ((year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0))
+
+/* How many days come before each month (0-12).  */
+static const unsigned short int __mon_yday[2][13] =
+{
+	/* Normal years.  */
+	{ 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365 },
+	/* Leap years.  */
+	{ 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366 }
+};
+
+static inline unsigned int get_rtc_time(struct rtc_time *wtime)
+{
+	struct pdc_tod tod_data;
+	long int days, rem, y;
+	const unsigned short int *ip;
+
+	memset(wtime, 0, sizeof(*wtime));
+	if (pdc_tod_read(&tod_data) < 0)
+		return RTC_24H | RTC_BATT_BAD;
+
+	// most of the remainder of this function is:
+//	Copyright (C) 1991, 1993, 1997, 1998 Free Software Foundation, Inc.
+//	This was originally a part of the GNU C Library.
+//      It is distributed under the GPL, and was swiped from offtime.c
+
+
+	days = tod_data.tod_sec / SECS_PER_DAY;
+	rem = tod_data.tod_sec % SECS_PER_DAY;
+
+	wtime->tm_hour = rem / SECS_PER_HOUR;
+	rem %= SECS_PER_HOUR;
+	wtime->tm_min = rem / 60;
+	wtime->tm_sec = rem % 60;
+
+	y = 1970;
+
+#define DIV(a, b) ((a) / (b) - ((a) % (b) < 0))
+#define LEAPS_THRU_END_OF(y) (DIV (y, 4) - DIV (y, 100) + DIV (y, 400))
+
+	while (days < 0 || days >= (__isleap (y) ? 366 : 365))
+	{
+		/* Guess a corrected year, assuming 365 days per year.  */
+		long int yg = y + days / 365 - (days % 365 < 0);
+
+		/* Adjust DAYS and Y to match the guessed year.  */
+		days -= ((yg - y) * 365
+			 + LEAPS_THRU_END_OF (yg - 1)
+			 - LEAPS_THRU_END_OF (y - 1));
+		y = yg;
+	}
+	wtime->tm_year = y - 1900;
+
+	ip = __mon_yday[__isleap(y)];
+	for (y = 11; days < (long int) ip[y]; --y)
+		continue;
+	days -= ip[y];
+	wtime->tm_mon = y;
+	wtime->tm_mday = days + 1;
+
+	return RTC_24H;
+}
+
+static int set_rtc_time(struct rtc_time *wtime)
+{
+	u_int32_t secs;
+
+	secs = mktime(wtime->tm_year + 1900, wtime->tm_mon + 1, wtime->tm_mday, 
+		      wtime->tm_hour, wtime->tm_min, wtime->tm_sec);
+
+	if(pdc_tod_set(secs, 0) < 0)
+		return -1;
+	else
+		return 0;
+
+}
+
+static inline unsigned int get_rtc_ss(void)
+{
+	struct rtc_time h;
+
+	get_rtc_time(&h);
+	return h.tm_sec;
+}
+
+static inline int get_rtc_pll(struct rtc_pll_info *pll)
+{
+	return -EINVAL;
+}
+static inline int set_rtc_pll(struct rtc_pll_info *pll)
+{
+	return -EINVAL;
+}
+
+#endif /* __KERNEL__ */
+#endif /* __ASM_RTC_H__ */
diff --git a/arch/parisc/include/asm/runway.h b/arch/parisc/include/asm/runway.h
new file mode 100644
index 000000000000..5bea02da7e22
--- /dev/null
+++ b/arch/parisc/include/asm/runway.h
@@ -0,0 +1,12 @@
+#ifndef ASM_PARISC_RUNWAY_H
+#define ASM_PARISC_RUNWAY_H
+#ifdef __KERNEL__
+
+/* declared in arch/parisc/kernel/setup.c */
+extern struct proc_dir_entry * proc_runway_root;
+
+#define RUNWAY_STATUS	0x10
+#define RUNWAY_DEBUG	0x40
+
+#endif /* __KERNEL__ */
+#endif /* ASM_PARISC_RUNWAY_H */
diff --git a/arch/parisc/include/asm/scatterlist.h b/arch/parisc/include/asm/scatterlist.h
new file mode 100644
index 000000000000..62269b31ebf4
--- /dev/null
+++ b/arch/parisc/include/asm/scatterlist.h
@@ -0,0 +1,27 @@
+#ifndef _ASM_PARISC_SCATTERLIST_H
+#define _ASM_PARISC_SCATTERLIST_H
+
+#include <asm/page.h>
+#include <asm/types.h>
+
+struct scatterlist {
+#ifdef CONFIG_DEBUG_SG
+	unsigned long sg_magic;
+#endif
+	unsigned long page_link;
+	unsigned int offset;
+
+	unsigned int length;
+
+	/* an IOVA can be 64-bits on some PA-Risc platforms. */
+	dma_addr_t iova;	/* I/O Virtual Address */
+	__u32      iova_length; /* bytes mapped */
+};
+
+#define sg_virt_addr(sg) ((unsigned long)sg_virt(sg))
+#define sg_dma_address(sg) ((sg)->iova)
+#define sg_dma_len(sg)     ((sg)->iova_length)
+
+#define ISA_DMA_THRESHOLD (~0UL)
+
+#endif /* _ASM_PARISC_SCATTERLIST_H */
diff --git a/arch/parisc/include/asm/sections.h b/arch/parisc/include/asm/sections.h
new file mode 100644
index 000000000000..9d13c3507ad6
--- /dev/null
+++ b/arch/parisc/include/asm/sections.h
@@ -0,0 +1,12 @@
+#ifndef _PARISC_SECTIONS_H
+#define _PARISC_SECTIONS_H
+
+/* nothing to see, move along */
+#include <asm-generic/sections.h>
+
+#ifdef CONFIG_64BIT
+#undef dereference_function_descriptor
+void *dereference_function_descriptor(void *);
+#endif
+
+#endif
diff --git a/arch/parisc/include/asm/segment.h b/arch/parisc/include/asm/segment.h
new file mode 100644
index 000000000000..26794ddb6524
--- /dev/null
+++ b/arch/parisc/include/asm/segment.h
@@ -0,0 +1,6 @@
+#ifndef __PARISC_SEGMENT_H
+#define __PARISC_SEGMENT_H
+
+/* Only here because we have some old header files that expect it.. */
+
+#endif
diff --git a/arch/parisc/include/asm/sembuf.h b/arch/parisc/include/asm/sembuf.h
new file mode 100644
index 000000000000..1e59ffd3bd1e
--- /dev/null
+++ b/arch/parisc/include/asm/sembuf.h
@@ -0,0 +1,29 @@
+#ifndef _PARISC_SEMBUF_H
+#define _PARISC_SEMBUF_H
+
+/* 
+ * The semid64_ds structure for parisc architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct semid64_ds {
+	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
+#ifndef CONFIG_64BIT
+	unsigned int	__pad1;
+#endif
+	__kernel_time_t	sem_otime;		/* last semop time */
+#ifndef CONFIG_64BIT
+	unsigned int	__pad2;
+#endif
+	__kernel_time_t	sem_ctime;		/* last change time */
+	unsigned int	sem_nsems;		/* no. of semaphores in array */
+	unsigned int	__unused1;
+	unsigned int	__unused2;
+};
+
+#endif /* _PARISC_SEMBUF_H */
diff --git a/arch/parisc/include/asm/serial.h b/arch/parisc/include/asm/serial.h
new file mode 100644
index 000000000000..d7e3cc60dbc3
--- /dev/null
+++ b/arch/parisc/include/asm/serial.h
@@ -0,0 +1,10 @@
+/*
+ * include/asm-parisc/serial.h
+ */
+
+/*
+ * This is used for 16550-compatible UARTs
+ */
+#define BASE_BAUD ( 1843200 / 16 )
+
+#define SERIAL_PORT_DFNS
diff --git a/arch/parisc/include/asm/setup.h b/arch/parisc/include/asm/setup.h
new file mode 100644
index 000000000000..7da2e5b8747e
--- /dev/null
+++ b/arch/parisc/include/asm/setup.h
@@ -0,0 +1,6 @@
+#ifndef _PARISC_SETUP_H
+#define _PARISC_SETUP_H
+
+#define COMMAND_LINE_SIZE	1024
+
+#endif /* _PARISC_SETUP_H */
diff --git a/arch/parisc/include/asm/shmbuf.h b/arch/parisc/include/asm/shmbuf.h
new file mode 100644
index 000000000000..0a3eada1863b
--- /dev/null
+++ b/arch/parisc/include/asm/shmbuf.h
@@ -0,0 +1,58 @@
+#ifndef _PARISC_SHMBUF_H
+#define _PARISC_SHMBUF_H
+
+/* 
+ * The shmid64_ds structure for parisc architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct shmid64_ds {
+	struct ipc64_perm	shm_perm;	/* operation perms */
+#ifndef CONFIG_64BIT
+	unsigned int		__pad1;
+#endif
+	__kernel_time_t		shm_atime;	/* last attach time */
+#ifndef CONFIG_64BIT
+	unsigned int		__pad2;
+#endif
+	__kernel_time_t		shm_dtime;	/* last detach time */
+#ifndef CONFIG_64BIT
+	unsigned int		__pad3;
+#endif
+	__kernel_time_t		shm_ctime;	/* last change time */
+#ifndef CONFIG_64BIT
+	unsigned int		__pad4;
+#endif
+	size_t			shm_segsz;	/* size of segment (bytes) */
+	__kernel_pid_t		shm_cpid;	/* pid of creator */
+	__kernel_pid_t		shm_lpid;	/* pid of last operator */
+	unsigned int		shm_nattch;	/* no. of current attaches */
+	unsigned int		__unused1;
+	unsigned int		__unused2;
+};
+
+#ifdef CONFIG_64BIT
+/* The 'unsigned int' (formerly 'unsigned long') data types below will
+ * ensure that a 32-bit app calling shmctl(*,IPC_INFO,*) will work on
+ * a wide kernel, but if some of these values are meant to contain pointers
+ * they may need to be 'long long' instead. -PB XXX FIXME
+ */
+#endif
+struct shminfo64 {
+	unsigned int	shmmax;
+	unsigned int	shmmin;
+	unsigned int	shmmni;
+	unsigned int	shmseg;
+	unsigned int	shmall;
+	unsigned int	__unused1;
+	unsigned int	__unused2;
+	unsigned int	__unused3;
+	unsigned int	__unused4;
+};
+
+#endif /* _PARISC_SHMBUF_H */
diff --git a/arch/parisc/include/asm/shmparam.h b/arch/parisc/include/asm/shmparam.h
new file mode 100644
index 000000000000..628ddc22faa8
--- /dev/null
+++ b/arch/parisc/include/asm/shmparam.h
@@ -0,0 +1,8 @@
+#ifndef _ASMPARISC_SHMPARAM_H
+#define _ASMPARISC_SHMPARAM_H
+
+#define __ARCH_FORCE_SHMLBA 	1
+
+#define SHMLBA 0x00400000   /* attach addr needs to be 4 Mb aligned */
+
+#endif /* _ASMPARISC_SHMPARAM_H */
diff --git a/arch/parisc/include/asm/sigcontext.h b/arch/parisc/include/asm/sigcontext.h
new file mode 100644
index 000000000000..27ef31bb3b6e
--- /dev/null
+++ b/arch/parisc/include/asm/sigcontext.h
@@ -0,0 +1,20 @@
+#ifndef _ASMPARISC_SIGCONTEXT_H
+#define _ASMPARISC_SIGCONTEXT_H
+
+#define PARISC_SC_FLAG_ONSTACK 1<<0
+#define PARISC_SC_FLAG_IN_SYSCALL 1<<1
+
+/* We will add more stuff here as it becomes necessary, until we know
+   it works. */
+struct sigcontext {
+	unsigned long sc_flags;
+
+	unsigned long sc_gr[32]; /* PSW in sc_gr[0] */
+	unsigned long long sc_fr[32]; /* FIXME, do we need other state info? */
+	unsigned long sc_iasq[2];
+	unsigned long sc_iaoq[2];
+	unsigned long sc_sar; /* cr11 */
+};
+
+
+#endif
diff --git a/arch/parisc/include/asm/siginfo.h b/arch/parisc/include/asm/siginfo.h
new file mode 100644
index 000000000000..d4909f55fe35
--- /dev/null
+++ b/arch/parisc/include/asm/siginfo.h
@@ -0,0 +1,14 @@
+#ifndef _PARISC_SIGINFO_H
+#define _PARISC_SIGINFO_H
+
+#include <asm-generic/siginfo.h>
+
+/*
+ * SIGTRAP si_codes
+ */
+#define TRAP_BRANCH	(__SI_FAULT|3)	/* process taken branch trap */
+#define TRAP_HWBKPT	(__SI_FAULT|4)	/* hardware breakpoint or watchpoint */
+#undef NSIGTRAP
+#define NSIGTRAP	4
+
+#endif
diff --git a/arch/parisc/include/asm/signal.h b/arch/parisc/include/asm/signal.h
new file mode 100644
index 000000000000..c20356375d1d
--- /dev/null
+++ b/arch/parisc/include/asm/signal.h
@@ -0,0 +1,153 @@
+#ifndef _ASM_PARISC_SIGNAL_H
+#define _ASM_PARISC_SIGNAL_H
+
+#define SIGHUP		 1
+#define SIGINT		 2
+#define SIGQUIT		 3
+#define SIGILL		 4
+#define SIGTRAP		 5
+#define SIGABRT		 6
+#define SIGIOT		 6
+#define SIGEMT		 7
+#define SIGFPE		 8
+#define SIGKILL		 9
+#define SIGBUS		10
+#define SIGSEGV		11
+#define SIGSYS		12 /* Linux doesn't use this */
+#define SIGPIPE		13
+#define SIGALRM		14
+#define SIGTERM		15
+#define SIGUSR1		16
+#define SIGUSR2		17
+#define SIGCHLD		18
+#define SIGPWR		19
+#define SIGVTALRM	20
+#define SIGPROF		21
+#define SIGIO		22
+#define SIGPOLL		SIGIO
+#define SIGWINCH	23
+#define SIGSTOP		24
+#define SIGTSTP		25
+#define SIGCONT		26
+#define SIGTTIN		27
+#define SIGTTOU		28
+#define SIGURG		29
+#define SIGLOST		30 /* Linux doesn't use this either */
+#define	SIGUNUSED	31
+#define SIGRESERVE	SIGUNUSED
+
+#define SIGXCPU		33
+#define SIGXFSZ		34
+#define SIGSTKFLT	36
+
+/* These should not be considered constants from userland.  */
+#define SIGRTMIN	37
+#define SIGRTMAX	_NSIG /* it's 44 under HP/UX */
+
+/*
+ * SA_FLAGS values:
+ *
+ * SA_ONSTACK indicates that a registered stack_t will be used.
+ * SA_RESTART flag to get restarting signals (which were the default long ago)
+ * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
+ * SA_RESETHAND clears the handler when the signal is delivered.
+ * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
+ * SA_NODEFER prevents the current signal from being masked in the handler.
+ *
+ * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
+ * Unix names RESETHAND and NODEFER respectively.
+ */
+#define SA_ONSTACK	0x00000001
+#define SA_RESETHAND	0x00000004
+#define SA_NOCLDSTOP	0x00000008
+#define SA_SIGINFO	0x00000010
+#define SA_NODEFER	0x00000020
+#define SA_RESTART	0x00000040
+#define SA_NOCLDWAIT	0x00000080
+#define _SA_SIGGFAULT	0x00000100 /* HPUX */
+
+#define SA_NOMASK	SA_NODEFER
+#define SA_ONESHOT	SA_RESETHAND
+
+#define SA_RESTORER	0x04000000 /* obsolete -- ignored */
+
+/* 
+ * sigaltstack controls
+ */
+#define SS_ONSTACK	1
+#define SS_DISABLE	2
+
+#define MINSIGSTKSZ	2048
+#define SIGSTKSZ	8192
+
+#ifdef __KERNEL__
+
+#define _NSIG		64
+/* bits-per-word, where word apparently means 'long' not 'int' */
+#define _NSIG_BPW	BITS_PER_LONG
+#define _NSIG_WORDS	(_NSIG / _NSIG_BPW)
+
+#endif /* __KERNEL__ */
+
+#define SIG_BLOCK          0	/* for blocking signals */
+#define SIG_UNBLOCK        1	/* for unblocking signals */
+#define SIG_SETMASK        2	/* for setting the signal mask */
+
+#define SIG_DFL	((__sighandler_t)0)	/* default signal handling */
+#define SIG_IGN	((__sighandler_t)1)	/* ignore signal */
+#define SIG_ERR	((__sighandler_t)-1)	/* error return from signal */
+
+# ifndef __ASSEMBLY__
+
+#  include <linux/types.h>
+
+/* Avoid too many header ordering problems.  */
+struct siginfo;
+
+/* Type of a signal handler.  */
+#ifdef CONFIG_64BIT
+/* function pointers on 64-bit parisc are pointers to little structs and the
+ * compiler doesn't support code which changes or tests the address of
+ * the function in the little struct.  This is really ugly -PB
+ */
+typedef char __user *__sighandler_t;
+#else
+typedef void __signalfn_t(int);
+typedef __signalfn_t __user *__sighandler_t;
+#endif
+
+typedef struct sigaltstack {
+	void __user *ss_sp;
+	int ss_flags;
+	size_t ss_size;
+} stack_t;
+
+#ifdef __KERNEL__
+
+/* Most things should be clean enough to redefine this at will, if care
+   is taken to make libc match.  */
+
+typedef unsigned long old_sigset_t;		/* at least 32 bits */
+
+typedef struct {
+	/* next_signal() assumes this is a long - no choice */
+	unsigned long sig[_NSIG_WORDS];
+} sigset_t;
+
+struct sigaction {
+	__sighandler_t sa_handler;
+	unsigned long sa_flags;
+	sigset_t sa_mask;		/* mask last for extensibility */
+};
+
+struct k_sigaction {
+	struct sigaction sa;
+};
+
+#define ptrace_signal_deliver(regs, cookie) do { } while (0)
+
+#include <asm/sigcontext.h>
+
+#endif /* __KERNEL__ */
+#endif /* !__ASSEMBLY */
+#endif /* _ASM_PARISC_SIGNAL_H */
diff --git a/arch/parisc/include/asm/smp.h b/arch/parisc/include/asm/smp.h
new file mode 100644
index 000000000000..398cdbaf4e54
--- /dev/null
+++ b/arch/parisc/include/asm/smp.h
@@ -0,0 +1,68 @@
+#ifndef __ASM_SMP_H
+#define __ASM_SMP_H
+
+
+#if defined(CONFIG_SMP)
+
+/* Page Zero Location PDC will look for the address to branch to when we poke
+** slave CPUs still in "Icache loop".
+*/
+#define PDC_OS_BOOT_RENDEZVOUS     0x10
+#define PDC_OS_BOOT_RENDEZVOUS_HI  0x28
+
+#ifndef ASSEMBLY
+#include <linux/bitops.h>
+#include <linux/threads.h>	/* for NR_CPUS */
+#include <linux/cpumask.h>
+typedef unsigned long address_t;
+
+extern cpumask_t cpu_online_map;
+
+
+/*
+ *	Private routines/data
+ *
+ *	physical and logical are equivalent until we support CPU hotplug.
+ */
+#define cpu_number_map(cpu)	(cpu)
+#define cpu_logical_map(cpu)	(cpu)
+
+extern void smp_send_reschedule(int cpu);
+extern void smp_send_all_nop(void);
+
+extern void arch_send_call_function_single_ipi(int cpu);
+extern void arch_send_call_function_ipi(cpumask_t mask);
+
+#endif /* !ASSEMBLY */
+
+/*
+ *	This magic constant controls our willingness to transfer
+ *      a process across CPUs. Such a transfer incurs cache and tlb
+ *      misses. The current value is inherited from i386. Still needs
+ *      to be tuned for parisc.
+ */
+ 
+#define PROC_CHANGE_PENALTY	15		/* Schedule penalty */
+
+extern unsigned long cpu_present_mask;
+
+#define raw_smp_processor_id()	(current_thread_info()->cpu)
+
+#else /* CONFIG_SMP */
+
+static inline void smp_send_all_nop(void) { return; }
+
+#endif
+
+#define NO_PROC_ID		0xFF		/* No processor magic marker */
+#define ANY_PROC_ID		0xFF		/* Any processor magic marker */
+static inline int __cpu_disable (void) {
+  return 0;
+}
+static inline void __cpu_die (unsigned int cpu) {
+  while(1)
+    ;
+}
+extern int __cpu_up (unsigned int cpu);
+
+#endif /*  __ASM_SMP_H */
diff --git a/arch/parisc/include/asm/socket.h b/arch/parisc/include/asm/socket.h
new file mode 100644
index 000000000000..fba402c95ac2
--- /dev/null
+++ b/arch/parisc/include/asm/socket.h
@@ -0,0 +1,62 @@
+#ifndef _ASM_SOCKET_H
+#define _ASM_SOCKET_H
+
+#include <asm/sockios.h>
+
+/* For setsockopt(2) */
+#define SOL_SOCKET	0xffff
+
+#define SO_DEBUG	0x0001
+#define SO_REUSEADDR	0x0004
+#define SO_KEEPALIVE	0x0008
+#define SO_DONTROUTE	0x0010
+#define SO_BROADCAST	0x0020
+#define SO_LINGER	0x0080
+#define SO_OOBINLINE	0x0100
+/* To add :#define SO_REUSEPORT 0x0200 */
+#define SO_SNDBUF	0x1001
+#define SO_RCVBUF	0x1002
+#define SO_SNDBUFFORCE	0x100a
+#define SO_RCVBUFFORCE	0x100b
+#define SO_SNDLOWAT	0x1003
+#define SO_RCVLOWAT	0x1004
+#define SO_SNDTIMEO	0x1005
+#define SO_RCVTIMEO	0x1006
+#define SO_ERROR	0x1007
+#define SO_TYPE		0x1008
+#define SO_PEERNAME	0x2000
+
+#define SO_NO_CHECK	0x400b
+#define SO_PRIORITY	0x400c
+#define SO_BSDCOMPAT	0x400e
+#define SO_PASSCRED	0x4010
+#define SO_PEERCRED	0x4011
+#define SO_TIMESTAMP	0x4012
+#define SCM_TIMESTAMP	SO_TIMESTAMP
+#define SO_TIMESTAMPNS	0x4013
+#define SCM_TIMESTAMPNS	SO_TIMESTAMPNS
+
+/* Security levels - as per NRL IPv6 - don't actually do anything */
+#define SO_SECURITY_AUTHENTICATION		0x4016
+#define SO_SECURITY_ENCRYPTION_TRANSPORT	0x4017
+#define SO_SECURITY_ENCRYPTION_NETWORK		0x4018
+
+#define SO_BINDTODEVICE	0x4019
+
+/* Socket filtering */
+#define SO_ATTACH_FILTER        0x401a
+#define SO_DETACH_FILTER        0x401b
+
+#define SO_ACCEPTCONN		0x401c
+
+#define SO_PEERSEC		0x401d
+#define SO_PASSSEC		0x401e
+
+#define SO_MARK			0x401f
+
+/* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
+ * have to define SOCK_NONBLOCK to a different value here.
+ */
+#define SOCK_NONBLOCK   0x40000000
+
+#endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/asm/sockios.h b/arch/parisc/include/asm/sockios.h
new file mode 100644
index 000000000000..dabfbc7483f6
--- /dev/null
+++ b/arch/parisc/include/asm/sockios.h
@@ -0,0 +1,13 @@
+#ifndef __ARCH_PARISC_SOCKIOS__
+#define __ARCH_PARISC_SOCKIOS__
+
+/* Socket-level I/O control calls. */
+#define FIOSETOWN 	0x8901
+#define SIOCSPGRP	0x8902
+#define FIOGETOWN	0x8903
+#define SIOCGPGRP	0x8904
+#define SIOCATMARK	0x8905
+#define SIOCGSTAMP	0x8906		/* Get stamp (timeval) */
+#define SIOCGSTAMPNS	0x8907		/* Get stamp (timespec) */
+
+#endif
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
new file mode 100644
index 000000000000..f3d2090a18dc
--- /dev/null
+++ b/arch/parisc/include/asm/spinlock.h
@@ -0,0 +1,194 @@
+#ifndef __ASM_SPINLOCK_H
+#define __ASM_SPINLOCK_H
+
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <asm/spinlock_types.h>
+
+static inline int __raw_spin_is_locked(raw_spinlock_t *x)
+{
+	volatile unsigned int *a = __ldcw_align(x);
+	return *a == 0;
+}
+
+#define __raw_spin_lock(lock) __raw_spin_lock_flags(lock, 0)
+#define __raw_spin_unlock_wait(x) \
+		do { cpu_relax(); } while (__raw_spin_is_locked(x))
+
+static inline void __raw_spin_lock_flags(raw_spinlock_t *x,
+					 unsigned long flags)
+{
+	volatile unsigned int *a;
+
+	mb();
+	a = __ldcw_align(x);
+	while (__ldcw(a) == 0)
+		while (*a == 0)
+			if (flags & PSW_SM_I) {
+				local_irq_enable();
+				cpu_relax();
+				local_irq_disable();
+			} else
+				cpu_relax();
+	mb();
+}
+
+static inline void __raw_spin_unlock(raw_spinlock_t *x)
+{
+	volatile unsigned int *a;
+	mb();
+	a = __ldcw_align(x);
+	*a = 1;
+	mb();
+}
+
+static inline int __raw_spin_trylock(raw_spinlock_t *x)
+{
+	volatile unsigned int *a;
+	int ret;
+
+	mb();
+	a = __ldcw_align(x);
+        ret = __ldcw(a) != 0;
+	mb();
+
+	return ret;
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Linux rwlocks are unfair to writers; they can be starved for an indefinite
+ * time by readers.  With care, they can also be taken in interrupt context.
+ *
+ * In the PA-RISC implementation, we have a spinlock and a counter.
+ * Readers use the lock to serialise their access to the counter (which
+ * records how many readers currently hold the lock).
+ * Writers hold the spinlock, preventing any readers or other writers from
+ * grabbing the rwlock.
+ */
+
+/* Note that we have to ensure interrupts are disabled in case we're
+ * interrupted by some other code that wants to grab the same read lock */
+static  __inline__ void __raw_read_lock(raw_rwlock_t *rw)
+{
+	unsigned long flags;
+	local_irq_save(flags);
+	__raw_spin_lock_flags(&rw->lock, flags);
+	rw->counter++;
+	__raw_spin_unlock(&rw->lock);
+	local_irq_restore(flags);
+}
+
+/* Note that we have to ensure interrupts are disabled in case we're
+ * interrupted by some other code that wants to grab the same read lock */
+static  __inline__ void __raw_read_unlock(raw_rwlock_t *rw)
+{
+	unsigned long flags;
+	local_irq_save(flags);
+	__raw_spin_lock_flags(&rw->lock, flags);
+	rw->counter--;
+	__raw_spin_unlock(&rw->lock);
+	local_irq_restore(flags);
+}
+
+/* Note that we have to ensure interrupts are disabled in case we're
+ * interrupted by some other code that wants to grab the same read lock */
+static __inline__ int __raw_read_trylock(raw_rwlock_t *rw)
+{
+	unsigned long flags;
+ retry:
+	local_irq_save(flags);
+	if (__raw_spin_trylock(&rw->lock)) {
+		rw->counter++;
+		__raw_spin_unlock(&rw->lock);
+		local_irq_restore(flags);
+		return 1;
+	}
+
+	local_irq_restore(flags);
+	/* If write-locked, we fail to acquire the lock */
+	if (rw->counter < 0)
+		return 0;
+
+	/* Wait until we have a realistic chance at the lock */
+	while (__raw_spin_is_locked(&rw->lock) && rw->counter >= 0)
+		cpu_relax();
+
+	goto retry;
+}
+
+/* Note that we have to ensure interrupts are disabled in case we're
+ * interrupted by some other code that wants to read_trylock() this lock */
+static __inline__ void __raw_write_lock(raw_rwlock_t *rw)
+{
+	unsigned long flags;
+retry:
+	local_irq_save(flags);
+	__raw_spin_lock_flags(&rw->lock, flags);
+
+	if (rw->counter != 0) {
+		__raw_spin_unlock(&rw->lock);
+		local_irq_restore(flags);
+
+		while (rw->counter != 0)
+			cpu_relax();
+
+		goto retry;
+	}
+
+	rw->counter = -1; /* mark as write-locked */
+	mb();
+	local_irq_restore(flags);
+}
+
+static __inline__ void __raw_write_unlock(raw_rwlock_t *rw)
+{
+	rw->counter = 0;
+	__raw_spin_unlock(&rw->lock);
+}
+
+/* Note that we have to ensure interrupts are disabled in case we're
+ * interrupted by some other code that wants to read_trylock() this lock */
+static __inline__ int __raw_write_trylock(raw_rwlock_t *rw)
+{
+	unsigned long flags;
+	int result = 0;
+
+	local_irq_save(flags);
+	if (__raw_spin_trylock(&rw->lock)) {
+		if (rw->counter == 0) {
+			rw->counter = -1;
+			result = 1;
+		} else {
+			/* Read-locked.  Oh well. */
+			__raw_spin_unlock(&rw->lock);
+		}
+	}
+	local_irq_restore(flags);
+
+	return result;
+}
+
+/*
+ * read_can_lock - would read_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+static __inline__ int __raw_read_can_lock(raw_rwlock_t *rw)
+{
+	return rw->counter >= 0;
+}
+
+/*
+ * write_can_lock - would write_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+static __inline__ int __raw_write_can_lock(raw_rwlock_t *rw)
+{
+	return !rw->counter;
+}
+
+#define _raw_spin_relax(lock)	cpu_relax()
+#define _raw_read_relax(lock)	cpu_relax()
+#define _raw_write_relax(lock)	cpu_relax()
+
+#endif /* __ASM_SPINLOCK_H */
diff --git a/arch/parisc/include/asm/spinlock_types.h b/arch/parisc/include/asm/spinlock_types.h
new file mode 100644
index 000000000000..3f72f47cf4b2
--- /dev/null
+++ b/arch/parisc/include/asm/spinlock_types.h
@@ -0,0 +1,21 @@
+#ifndef __ASM_SPINLOCK_TYPES_H
+#define __ASM_SPINLOCK_TYPES_H
+
+typedef struct {
+#ifdef CONFIG_PA20
+	volatile unsigned int slock;
+# define __RAW_SPIN_LOCK_UNLOCKED { 1 }
+#else
+	volatile unsigned int lock[4];
+# define __RAW_SPIN_LOCK_UNLOCKED	{ { 1, 1, 1, 1 } }
+#endif
+} raw_spinlock_t;
+
+typedef struct {
+	raw_spinlock_t lock;
+	volatile int counter;
+} raw_rwlock_t;
+
+#define __RAW_RW_LOCK_UNLOCKED		{ __RAW_SPIN_LOCK_UNLOCKED, 0 }
+
+#endif
diff --git a/arch/parisc/include/asm/stat.h b/arch/parisc/include/asm/stat.h
new file mode 100644
index 000000000000..9d5fbbc5c31f
--- /dev/null
+++ b/arch/parisc/include/asm/stat.h
@@ -0,0 +1,100 @@
+#ifndef _PARISC_STAT_H
+#define _PARISC_STAT_H
+
+#include <linux/types.h>
+
+struct stat {
+	unsigned int	st_dev;		/* dev_t is 32 bits on parisc */
+	ino_t		st_ino;		/* 32 bits */
+	mode_t		st_mode;	/* 16 bits */
+	nlink_t		st_nlink;	/* 16 bits */
+	unsigned short	st_reserved1;	/* old st_uid */
+	unsigned short	st_reserved2;	/* old st_gid */
+	unsigned int	st_rdev;
+	off_t		st_size;
+	time_t		st_atime;
+	unsigned int	st_atime_nsec;
+	time_t		st_mtime;
+	unsigned int	st_mtime_nsec;
+	time_t		st_ctime;
+	unsigned int	st_ctime_nsec;
+	int		st_blksize;
+	int		st_blocks;
+	unsigned int	__unused1;	/* ACL stuff */
+	unsigned int	__unused2;	/* network */
+	ino_t		__unused3;	/* network */
+	unsigned int	__unused4;	/* cnodes */
+	unsigned short	__unused5;	/* netsite */
+	short		st_fstype;
+	unsigned int	st_realdev;
+	unsigned short	st_basemode;
+	unsigned short	st_spareshort;
+	uid_t		st_uid;
+	gid_t		st_gid;
+	unsigned int	st_spare4[3];
+};
+
+#define STAT_HAVE_NSEC
+
+typedef __kernel_off64_t	off64_t;
+
+struct hpux_stat64 {
+	unsigned int	st_dev;		/* dev_t is 32 bits on parisc */
+	ino_t           st_ino;         /* 32 bits */
+	mode_t		st_mode;	/* 16 bits */
+	nlink_t		st_nlink;	/* 16 bits */
+	unsigned short	st_reserved1;	/* old st_uid */
+	unsigned short	st_reserved2;	/* old st_gid */
+	unsigned int	st_rdev;
+	off64_t		st_size;
+	time_t		st_atime;
+	unsigned int	st_spare1;
+	time_t		st_mtime;
+	unsigned int	st_spare2;
+	time_t		st_ctime;
+	unsigned int	st_spare3;
+	int		st_blksize;
+	__u64		st_blocks;
+	unsigned int	__unused1;	/* ACL stuff */
+	unsigned int	__unused2;	/* network */
+	ino_t           __unused3;      /* network */
+	unsigned int	__unused4;	/* cnodes */
+	unsigned short	__unused5;	/* netsite */
+	short		st_fstype;
+	unsigned int	st_realdev;
+	unsigned short	st_basemode;
+	unsigned short	st_spareshort;
+	uid_t		st_uid;
+	gid_t		st_gid;
+	unsigned int	st_spare4[3];
+};
+
+/* This is the struct that 32-bit userspace applications are expecting.
+ * How 64-bit apps are going to be compiled, I have no idea.  But at least
+ * this way, we don't have a wrapper in the kernel.
+ */
+struct stat64 {
+	unsigned long long	st_dev;
+	unsigned int		__pad1;
+
+	unsigned int		__st_ino;	/* Not actually filled in */
+	unsigned int		st_mode;
+	unsigned int		st_nlink;
+	unsigned int		st_uid;
+	unsigned int		st_gid;
+	unsigned long long	st_rdev;
+	unsigned int		__pad2;
+	signed long long	st_size;
+	signed int		st_blksize;
+
+	signed long long	st_blocks;
+	signed int		st_atime;
+	unsigned int		st_atime_nsec;
+	signed int		st_mtime;
+	unsigned int		st_mtime_nsec;
+	signed int		st_ctime;
+	unsigned int		st_ctime_nsec;
+	unsigned long long	st_ino;
+};
+
+#endif
diff --git a/arch/parisc/include/asm/statfs.h b/arch/parisc/include/asm/statfs.h
new file mode 100644
index 000000000000..1d2b8130b23d
--- /dev/null
+++ b/arch/parisc/include/asm/statfs.h
@@ -0,0 +1,58 @@
+#ifndef _PARISC_STATFS_H
+#define _PARISC_STATFS_H
+
+#ifndef __KERNEL_STRICT_NAMES
+
+#include <linux/types.h>
+
+typedef __kernel_fsid_t	fsid_t;
+
+#endif
+
+/*
+ * It appears that PARISC could be 64 _or_ 32 bit.
+ * 64-bit fields must be explicitly 64-bit in statfs64.
+ */
+struct statfs {
+	long f_type;
+	long f_bsize;
+	long f_blocks;
+	long f_bfree;
+	long f_bavail;
+	long f_files;
+	long f_ffree;
+	__kernel_fsid_t f_fsid;
+	long f_namelen;
+	long f_frsize;
+	long f_spare[5];
+};
+
+struct statfs64 {
+	long f_type;
+	long f_bsize;
+	__u64 f_blocks;
+	__u64 f_bfree;
+	__u64 f_bavail;
+	__u64 f_files;
+	__u64 f_ffree;
+	__kernel_fsid_t f_fsid;
+	long f_namelen;
+	long f_frsize;
+	long f_spare[5];
+};
+
+struct compat_statfs64 {
+	__u32 f_type;
+	__u32 f_bsize;
+	__u64 f_blocks;
+	__u64 f_bfree;
+	__u64 f_bavail;
+	__u64 f_files;
+	__u64 f_ffree;
+	__kernel_fsid_t f_fsid;
+	__u32 f_namelen;
+	__u32 f_frsize;
+	__u32 f_spare[5];
+};
+
+#endif
diff --git a/arch/parisc/include/asm/string.h b/arch/parisc/include/asm/string.h
new file mode 100644
index 000000000000..eda01be65e35
--- /dev/null
+++ b/arch/parisc/include/asm/string.h
@@ -0,0 +1,10 @@
+#ifndef _PA_STRING_H_
+#define _PA_STRING_H_
+
+#define __HAVE_ARCH_MEMSET
+extern void * memset(void *, int, size_t);
+
+#define __HAVE_ARCH_MEMCPY
+void * memcpy(void * dest,const void *src,size_t count);
+
+#endif
diff --git a/arch/parisc/include/asm/superio.h b/arch/parisc/include/asm/superio.h
new file mode 100644
index 000000000000..6598acb4d46d
--- /dev/null
+++ b/arch/parisc/include/asm/superio.h
@@ -0,0 +1,85 @@
+#ifndef _PARISC_SUPERIO_H
+#define _PARISC_SUPERIO_H
+
+#define IC_PIC1    0x20		/* PCI I/O address of master 8259 */
+#define IC_PIC2    0xA0		/* PCI I/O address of slave */
+
+/* Config Space Offsets to configuration and base address registers */
+#define SIO_CR     0x5A		/* Configuration Register */
+#define SIO_ACPIBAR 0x88	/* ACPI BAR */
+#define SIO_FDCBAR 0x90		/* Floppy Disk Controller BAR */
+#define SIO_SP1BAR 0x94		/* Serial 1 BAR */
+#define SIO_SP2BAR 0x98		/* Serial 2 BAR */
+#define SIO_PPBAR  0x9C		/* Parallel BAR */
+
+#define TRIGGER_1  0x67		/* Edge/level trigger register 1 */
+#define TRIGGER_2  0x68		/* Edge/level trigger register 2 */
+
+/* Interrupt Routing Control registers */
+#define CFG_IR_SER    0x69	/* Serial 1 [0:3] and Serial 2 [4:7] */
+#define CFG_IR_PFD    0x6a	/* Parallel [0:3] and Floppy [4:7] */
+#define CFG_IR_IDE    0x6b	/* IDE1     [0:3] and IDE2 [4:7] */
+#define CFG_IR_INTAB  0x6c	/* PCI INTA [0:3] and INT B [4:7] */
+#define CFG_IR_INTCD  0x6d	/* PCI INTC [0:3] and INT D [4:7] */
+#define CFG_IR_PS2    0x6e	/* PS/2 KBINT [0:3] and Mouse [4:7] */
+#define CFG_IR_FXBUS  0x6f	/* FXIRQ[0] [0:3] and FXIRQ[1] [4:7] */
+#define CFG_IR_USB    0x70	/* FXIRQ[2] [0:3] and USB [4:7] */
+#define CFG_IR_ACPI   0x71	/* ACPI SCI [0:3] and reserved [4:7] */
+
+#define CFG_IR_LOW     CFG_IR_SER	/* Lowest interrupt routing reg */
+#define CFG_IR_HIGH    CFG_IR_ACPI	/* Highest interrupt routing reg */
+
+/* 8259 operational control words */
+#define OCW2_EOI   0x20		/* Non-specific EOI */
+#define OCW2_SEOI  0x60		/* Specific EOI */
+#define OCW3_IIR   0x0A		/* Read request register */
+#define OCW3_ISR   0x0B		/* Read service register */
+#define OCW3_POLL  0x0C		/* Poll the PIC for an interrupt vector */
+
+/* Interrupt lines. Only PIC1 is used */
+#define USB_IRQ    1		/* USB */
+#define SP1_IRQ    3		/* Serial port 1 */
+#define SP2_IRQ    4		/* Serial port 2 */
+#define PAR_IRQ    5		/* Parallel port */
+#define FDC_IRQ    6		/* Floppy controller */
+#define IDE_IRQ    7		/* IDE (pri+sec) */
+
+/* ACPI registers */
+#define USB_REG_CR	0x1f	/* USB Regulator Control Register */
+
+#define SUPERIO_NIRQS   8
+
+struct superio_device {
+	u32 fdc_base;
+	u32 sp1_base;
+	u32 sp2_base;
+	u32 pp_base;
+	u32 acpi_base;
+	int suckyio_irq_enabled;
+	struct pci_dev *lio_pdev;       /* pci device for legacy IO (fn 1) */
+	struct pci_dev *usb_pdev;       /* pci device for USB (fn 2) */
+};
+
+/*
+ * Does NS make a 87415 based plug in PCI card? If so, because of this
+ * macro we currently don't support it being plugged into a machine
+ * that contains a SuperIO chip AND has CONFIG_SUPERIO enabled.
+ *
+ * This could be fixed by checking to see if function 1 exists, and
+ * if it is SuperIO Legacy IO; but really now, is this combination
+ * going to EVER happen?
+ */
+
+#define SUPERIO_IDE_FN 0 /* Function number of IDE controller */
+#define SUPERIO_LIO_FN 1 /* Function number of Legacy IO controller */
+#define SUPERIO_USB_FN 2 /* Function number of USB controller */
+
+#define is_superio_device(x) \
+	(((x)->vendor == PCI_VENDOR_ID_NS) && \
+	(  ((x)->device == PCI_DEVICE_ID_NS_87415) \
+	|| ((x)->device == PCI_DEVICE_ID_NS_87560_LIO) \
+	|| ((x)->device == PCI_DEVICE_ID_NS_87560_USB) ) )
+
+extern int superio_fixup_irq(struct pci_dev *pcidev); /* called by iosapic */
+
+#endif /* _PARISC_SUPERIO_H */
diff --git a/arch/parisc/include/asm/system.h b/arch/parisc/include/asm/system.h
new file mode 100644
index 000000000000..ee80c920b464
--- /dev/null
+++ b/arch/parisc/include/asm/system.h
@@ -0,0 +1,182 @@
+#ifndef __PARISC_SYSTEM_H
+#define __PARISC_SYSTEM_H
+
+#include <asm/psw.h>
+
+/* The program status word as bitfields.  */
+struct pa_psw {
+	unsigned int y:1;
+	unsigned int z:1;
+	unsigned int rv:2;
+	unsigned int w:1;
+	unsigned int e:1;
+	unsigned int s:1;
+	unsigned int t:1;
+
+	unsigned int h:1;
+	unsigned int l:1;
+	unsigned int n:1;
+	unsigned int x:1;
+	unsigned int b:1;
+	unsigned int c:1;
+	unsigned int v:1;
+	unsigned int m:1;
+
+	unsigned int cb:8;
+
+	unsigned int o:1;
+	unsigned int g:1;
+	unsigned int f:1;
+	unsigned int r:1;
+	unsigned int q:1;
+	unsigned int p:1;
+	unsigned int d:1;
+	unsigned int i:1;
+};
+
+#ifdef CONFIG_64BIT
+#define pa_psw(task) ((struct pa_psw *) ((char *) (task) + TASK_PT_PSW + 4))
+#else
+#define pa_psw(task) ((struct pa_psw *) ((char *) (task) + TASK_PT_PSW))
+#endif
+
+struct task_struct;
+
+extern struct task_struct *_switch_to(struct task_struct *, struct task_struct *);
+
+#define switch_to(prev, next, last) do {			\
+	(last) = _switch_to(prev, next);			\
+} while(0)
+
+/* interrupt control */
+#define local_save_flags(x)	__asm__ __volatile__("ssm 0, %0" : "=r" (x) : : "memory")
+#define local_irq_disable()	__asm__ __volatile__("rsm %0,%%r0\n" : : "i" (PSW_I) : "memory" )
+#define local_irq_enable()	__asm__ __volatile__("ssm %0,%%r0\n" : : "i" (PSW_I) : "memory" )
+
+#define local_irq_save(x) \
+	__asm__ __volatile__("rsm %1,%0" : "=r" (x) :"i" (PSW_I) : "memory" )
+#define local_irq_restore(x) \
+	__asm__ __volatile__("mtsm %0" : : "r" (x) : "memory" )
+
+#define irqs_disabled()			\
+({					\
+	unsigned long flags;		\
+	local_save_flags(flags);	\
+	(flags & PSW_I) == 0;		\
+})
+
+#define mfctl(reg)	({		\
+	unsigned long cr;		\
+	__asm__ __volatile__(		\
+		"mfctl " #reg ",%0" :	\
+		 "=r" (cr)		\
+	);				\
+	cr;				\
+})
+
+#define mtctl(gr, cr) \
+	__asm__ __volatile__("mtctl %0,%1" \
+		: /* no outputs */ \
+		: "r" (gr), "i" (cr) : "memory")
+
+/* these are here to de-mystefy the calling code, and to provide hooks */
+/* which I needed for debugging EIEM problems -PB */
+#define get_eiem() mfctl(15)
+static inline void set_eiem(unsigned long val)
+{
+	mtctl(val, 15);
+}
+
+#define mfsp(reg)	({		\
+	unsigned long cr;		\
+	__asm__ __volatile__(		\
+		"mfsp " #reg ",%0" :	\
+		 "=r" (cr)		\
+	);				\
+	cr;				\
+})
+
+#define mtsp(gr, cr) \
+	__asm__ __volatile__("mtsp %0,%1" \
+		: /* no outputs */ \
+		: "r" (gr), "i" (cr) : "memory")
+
+
+/*
+** This is simply the barrier() macro from linux/kernel.h but when serial.c
+** uses tqueue.h uses smp_mb() defined using barrier(), linux/kernel.h
+** hasn't yet been included yet so it fails, thus repeating the macro here.
+**
+** PA-RISC architecture allows for weakly ordered memory accesses although
+** none of the processors use it. There is a strong ordered bit that is
+** set in the O-bit of the page directory entry. Operating systems that
+** can not tolerate out of order accesses should set this bit when mapping
+** pages. The O-bit of the PSW should also be set to 1 (I don't believe any
+** of the processor implemented the PSW O-bit). The PCX-W ERS states that
+** the TLB O-bit is not implemented so the page directory does not need to
+** have the O-bit set when mapping pages (section 3.1). This section also
+** states that the PSW Y, Z, G, and O bits are not implemented.
+** So it looks like nothing needs to be done for parisc-linux (yet).
+** (thanks to chada for the above comment -ggg)
+**
+** The __asm__ op below simple prevents gcc/ld from reordering
+** instructions across the mb() "call".
+*/
+#define mb()		__asm__ __volatile__("":::"memory")	/* barrier() */
+#define rmb()		mb()
+#define wmb()		mb()
+#define smp_mb()	mb()
+#define smp_rmb()	mb()
+#define smp_wmb()	mb()
+#define smp_read_barrier_depends()	do { } while(0)
+#define read_barrier_depends()		do { } while(0)
+
+#define set_mb(var, value)		do { var = value; mb(); } while (0)
+
+#ifndef CONFIG_PA20
+/* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data,
+   and GCC only guarantees 8-byte alignment for stack locals, we can't
+   be assured of 16-byte alignment for atomic lock data even if we
+   specify "__attribute ((aligned(16)))" in the type declaration.  So,
+   we use a struct containing an array of four ints for the atomic lock
+   type and dynamically select the 16-byte aligned int from the array
+   for the semaphore.  */
+
+#define __PA_LDCW_ALIGNMENT	16
+#define __ldcw_align(a) ({					\
+	unsigned long __ret = (unsigned long) &(a)->lock[0];	\
+	__ret = (__ret + __PA_LDCW_ALIGNMENT - 1)		\
+		& ~(__PA_LDCW_ALIGNMENT - 1);			\
+	(volatile unsigned int *) __ret;			\
+})
+#define __LDCW	"ldcw"
+
+#else /*CONFIG_PA20*/
+/* From: "Jim Hull" <jim.hull of hp.com>
+   I've attached a summary of the change, but basically, for PA 2.0, as
+   long as the ",CO" (coherent operation) completer is specified, then the
+   16-byte alignment requirement for ldcw and ldcd is relaxed, and instead
+   they only require "natural" alignment (4-byte for ldcw, 8-byte for
+   ldcd). */
+
+#define __PA_LDCW_ALIGNMENT	4
+#define __ldcw_align(a) ((volatile unsigned int *)a)
+#define __LDCW	"ldcw,co"
+
+#endif /*!CONFIG_PA20*/
+
+/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*.  */
+#define __ldcw(a) ({						\
+	unsigned __ret;						\
+	__asm__ __volatile__(__LDCW " 0(%1),%0"			\
+		: "=r" (__ret) : "r" (a));			\
+	__ret;							\
+})
+
+#ifdef CONFIG_SMP
+# define __lock_aligned __attribute__((__section__(".data.lock_aligned")))
+#endif
+
+#define arch_align_stack(x) (x)
+
+#endif
diff --git a/arch/parisc/include/asm/termbits.h b/arch/parisc/include/asm/termbits.h
new file mode 100644
index 000000000000..d8bbc73b16b7
--- /dev/null
+++ b/arch/parisc/include/asm/termbits.h
@@ -0,0 +1,200 @@
+#ifndef __ARCH_PARISC_TERMBITS_H__
+#define __ARCH_PARISC_TERMBITS_H__
+
+#include <linux/posix_types.h>
+
+typedef unsigned char	cc_t;
+typedef unsigned int	speed_t;
+typedef unsigned int	tcflag_t;
+
+#define NCCS 19
+struct termios {
+	tcflag_t c_iflag;		/* input mode flags */
+	tcflag_t c_oflag;		/* output mode flags */
+	tcflag_t c_cflag;		/* control mode flags */
+	tcflag_t c_lflag;		/* local mode flags */
+	cc_t c_line;			/* line discipline */
+	cc_t c_cc[NCCS];		/* control characters */
+};
+
+struct termios2 {
+	tcflag_t c_iflag;		/* input mode flags */
+	tcflag_t c_oflag;		/* output mode flags */
+	tcflag_t c_cflag;		/* control mode flags */
+	tcflag_t c_lflag;		/* local mode flags */
+	cc_t c_line;			/* line discipline */
+	cc_t c_cc[NCCS];		/* control characters */
+	speed_t c_ispeed;		/* input speed */
+	speed_t c_ospeed;		/* output speed */
+};
+
+struct ktermios {
+	tcflag_t c_iflag;		/* input mode flags */
+	tcflag_t c_oflag;		/* output mode flags */
+	tcflag_t c_cflag;		/* control mode flags */
+	tcflag_t c_lflag;		/* local mode flags */
+	cc_t c_line;			/* line discipline */
+	cc_t c_cc[NCCS];		/* control characters */
+	speed_t c_ispeed;		/* input speed */
+	speed_t c_ospeed;		/* output speed */
+};
+
+/* c_cc characters */
+#define VINTR 0
+#define VQUIT 1
+#define VERASE 2
+#define VKILL 3
+#define VEOF 4
+#define VTIME 5
+#define VMIN 6
+#define VSWTC 7
+#define VSTART 8
+#define VSTOP 9
+#define VSUSP 10
+#define VEOL 11
+#define VREPRINT 12
+#define VDISCARD 13
+#define VWERASE 14
+#define VLNEXT 15
+#define VEOL2 16
+
+
+/* c_iflag bits */
+#define IGNBRK	0000001
+#define BRKINT	0000002
+#define IGNPAR	0000004
+#define PARMRK	0000010
+#define INPCK	0000020
+#define ISTRIP	0000040
+#define INLCR	0000100
+#define IGNCR	0000200
+#define ICRNL	0000400
+#define IUCLC	0001000
+#define IXON	0002000
+#define IXANY	0004000
+#define IXOFF	0010000
+#define IMAXBEL	0040000
+#define IUTF8	0100000
+
+/* c_oflag bits */
+#define OPOST	0000001
+#define OLCUC	0000002
+#define ONLCR	0000004
+#define OCRNL	0000010
+#define ONOCR	0000020
+#define ONLRET	0000040
+#define OFILL	0000100
+#define OFDEL	0000200
+#define NLDLY	0000400
+#define   NL0	0000000
+#define   NL1	0000400
+#define CRDLY	0003000
+#define   CR0	0000000
+#define   CR1	0001000
+#define   CR2	0002000
+#define   CR3	0003000
+#define TABDLY	0014000
+#define   TAB0	0000000
+#define   TAB1	0004000
+#define   TAB2	0010000
+#define   TAB3	0014000
+#define   XTABS	0014000
+#define BSDLY	0020000
+#define   BS0	0000000
+#define   BS1	0020000
+#define VTDLY	0040000
+#define   VT0	0000000
+#define   VT1	0040000
+#define FFDLY	0100000
+#define   FF0	0000000
+#define   FF1	0100000
+
+/* c_cflag bit meaning */
+#define CBAUD   0010017
+#define  B0     0000000         /* hang up */
+#define  B50    0000001
+#define  B75    0000002
+#define  B110   0000003
+#define  B134   0000004
+#define  B150   0000005
+#define  B200   0000006
+#define  B300   0000007
+#define  B600   0000010
+#define  B1200  0000011
+#define  B1800  0000012
+#define  B2400  0000013
+#define  B4800  0000014
+#define  B9600  0000015
+#define  B19200 0000016
+#define  B38400 0000017
+#define EXTA B19200
+#define EXTB B38400
+#define CSIZE   0000060
+#define   CS5   0000000
+#define   CS6   0000020
+#define   CS7   0000040
+#define   CS8   0000060
+#define CSTOPB  0000100
+#define CREAD   0000200
+#define PARENB  0000400
+#define PARODD  0001000
+#define HUPCL   0002000
+#define CLOCAL  0004000
+#define CBAUDEX 0010000
+#define    BOTHER 0010000
+#define    B57600 0010001
+#define   B115200 0010002
+#define   B230400 0010003
+#define   B460800 0010004
+#define   B500000 0010005
+#define   B576000 0010006
+#define   B921600 0010007
+#define  B1000000 0010010
+#define  B1152000 0010011
+#define  B1500000 0010012
+#define  B2000000 0010013
+#define  B2500000 0010014
+#define  B3000000 0010015
+#define  B3500000 0010016
+#define  B4000000 0010017
+#define CIBAUD    002003600000		/* input baud rate */
+#define CMSPAR    010000000000          /* mark or space (stick) parity */
+#define CRTSCTS   020000000000          /* flow control */
+
+#define IBSHIFT	16		/* Shift from CBAUD to CIBAUD */
+
+
+/* c_lflag bits */
+#define ISIG    0000001
+#define ICANON  0000002
+#define XCASE   0000004
+#define ECHO    0000010
+#define ECHOE   0000020
+#define ECHOK   0000040
+#define ECHONL  0000100
+#define NOFLSH  0000200
+#define TOSTOP  0000400
+#define ECHOCTL 0001000
+#define ECHOPRT 0002000
+#define ECHOKE  0004000
+#define FLUSHO  0010000
+#define PENDIN  0040000
+#define IEXTEN  0100000
+
+/* tcflow() and TCXONC use these */
+#define	TCOOFF		0
+#define	TCOON		1
+#define	TCIOFF		2
+#define	TCION		3
+
+/* tcflush() and TCFLSH use these */
+#define	TCIFLUSH	0
+#define	TCOFLUSH	1
+#define	TCIOFLUSH	2
+
+/* tcsetattr uses these */
+#define	TCSANOW		0
+#define	TCSADRAIN	1
+#define	TCSAFLUSH	2
+
+#endif
diff --git a/arch/parisc/include/asm/termios.h b/arch/parisc/include/asm/termios.h
new file mode 100644
index 000000000000..a2a57a4548af
--- /dev/null
+++ b/arch/parisc/include/asm/termios.h
@@ -0,0 +1,90 @@
+#ifndef _PARISC_TERMIOS_H
+#define _PARISC_TERMIOS_H
+
+#include <asm/termbits.h>
+#include <asm/ioctls.h>
+
+struct winsize {
+	unsigned short ws_row;
+	unsigned short ws_col;
+	unsigned short ws_xpixel;
+	unsigned short ws_ypixel;
+};
+
+#define NCC 8
+struct termio {
+	unsigned short c_iflag;		/* input mode flags */
+	unsigned short c_oflag;		/* output mode flags */
+	unsigned short c_cflag;		/* control mode flags */
+	unsigned short c_lflag;		/* local mode flags */
+	unsigned char c_line;		/* line discipline */
+	unsigned char c_cc[NCC];	/* control characters */
+};
+
+/* modem lines */
+#define TIOCM_LE	0x001
+#define TIOCM_DTR	0x002
+#define TIOCM_RTS	0x004
+#define TIOCM_ST	0x008
+#define TIOCM_SR	0x010
+#define TIOCM_CTS	0x020
+#define TIOCM_CAR	0x040
+#define TIOCM_RNG	0x080
+#define TIOCM_DSR	0x100
+#define TIOCM_CD	TIOCM_CAR
+#define TIOCM_RI	TIOCM_RNG
+#define TIOCM_OUT1	0x2000
+#define TIOCM_OUT2	0x4000
+#define TIOCM_LOOP	0x8000
+
+/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
+
+#ifdef __KERNEL__
+
+/*	intr=^C		quit=^\		erase=del	kill=^U
+	eof=^D		vtime=\0	vmin=\1		sxtc=\0
+	start=^Q	stop=^S		susp=^Z		eol=\0
+	reprint=^R	discard=^U	werase=^W	lnext=^V
+	eol2=\0
+*/
+#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
+
+/*
+ * Translate a "termio" structure into a "termios". Ugh.
+ */
+#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
+	unsigned short __tmp; \
+	get_user(__tmp,&(termio)->x); \
+	*(unsigned short *) &(termios)->x = __tmp; \
+}
+
+#define user_termio_to_kernel_termios(termios, termio) \
+({ \
+	SET_LOW_TERMIOS_BITS(termios, termio, c_iflag); \
+	SET_LOW_TERMIOS_BITS(termios, termio, c_oflag); \
+	SET_LOW_TERMIOS_BITS(termios, termio, c_cflag); \
+	SET_LOW_TERMIOS_BITS(termios, termio, c_lflag); \
+	copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
+})
+
+/*
+ * Translate a "termios" structure into a "termio". Ugh.
+ */
+#define kernel_termios_to_user_termio(termio, termios) \
+({ \
+	put_user((termios)->c_iflag, &(termio)->c_iflag); \
+	put_user((termios)->c_oflag, &(termio)->c_oflag); \
+	put_user((termios)->c_cflag, &(termio)->c_cflag); \
+	put_user((termios)->c_lflag, &(termio)->c_lflag); \
+	put_user((termios)->c_line,  &(termio)->c_line); \
+	copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
+})
+
+#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios2))
+#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios2))
+#define user_termios_to_kernel_termios_1(k, u) copy_from_user(k, u, sizeof(struct termios))
+#define kernel_termios_to_user_termios_1(u, k) copy_to_user(u, k, sizeof(struct termios))
+
+#endif	/* __KERNEL__ */
+
+#endif	/* _PARISC_TERMIOS_H */
diff --git a/arch/parisc/include/asm/thread_info.h b/arch/parisc/include/asm/thread_info.h
new file mode 100644
index 000000000000..9f812741c355
--- /dev/null
+++ b/arch/parisc/include/asm/thread_info.h
@@ -0,0 +1,74 @@
+#ifndef _ASM_PARISC_THREAD_INFO_H
+#define _ASM_PARISC_THREAD_INFO_H
+
+#ifdef __KERNEL__
+
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+
+struct thread_info {
+	struct task_struct *task;	/* main task structure */
+	struct exec_domain *exec_domain;/* execution domain */
+	unsigned long flags;		/* thread_info flags (see TIF_*) */
+	mm_segment_t addr_limit;	/* user-level address space limit */
+	__u32 cpu;			/* current CPU */
+	int preempt_count;		/* 0=premptable, <0=BUG; will also serve as bh-counter */
+	struct restart_block restart_block;
+};
+
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.task		= &tsk,			\
+	.exec_domain	= &default_exec_domain,	\
+	.flags		= 0,			\
+	.cpu		= 0,			\
+	.addr_limit	= KERNEL_DS,		\
+	.preempt_count	= 1,			\
+  	.restart_block	= {			\
+		.fn = do_no_restart_syscall	\
+	}					\
+}
+
+#define init_thread_info        (init_thread_union.thread_info)
+#define init_stack              (init_thread_union.stack)
+
+/* thread information allocation */
+
+#define THREAD_SIZE_ORDER            2
+/* Be sure to hunt all references to this down when you change the size of
+ * the kernel stack */
+#define THREAD_SIZE             (PAGE_SIZE << THREAD_SIZE_ORDER)
+#define THREAD_SHIFT            (PAGE_SHIFT + THREAD_SIZE_ORDER)
+
+/* how to get the thread information struct from C */
+#define current_thread_info()	((struct thread_info *)mfctl(30))
+
+#endif /* !__ASSEMBLY */
+
+#define PREEMPT_ACTIVE_BIT	28
+#define PREEMPT_ACTIVE		(1 << PREEMPT_ACTIVE_BIT)
+
+/*
+ * thread information flags
+ */
+#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
+#define TIF_SIGPENDING		1	/* signal pending */
+#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
+#define TIF_POLLING_NRFLAG	3	/* true if poll_idle() is polling TIF_NEED_RESCHED */
+#define TIF_32BIT               4       /* 32 bit binary */
+#define TIF_MEMDIE		5
+#define TIF_RESTORE_SIGMASK	6	/* restore saved signal mask */
+
+#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
+#define _TIF_32BIT		(1 << TIF_32BIT)
+#define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
+
+#define _TIF_USER_WORK_MASK     (_TIF_SIGPENDING | \
+                                 _TIF_NEED_RESCHED | _TIF_RESTORE_SIGMASK)
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_PARISC_THREAD_INFO_H */
diff --git a/arch/parisc/include/asm/timex.h b/arch/parisc/include/asm/timex.h
new file mode 100644
index 000000000000..3b68d77273d9
--- /dev/null
+++ b/arch/parisc/include/asm/timex.h
@@ -0,0 +1,20 @@
+/*
+ * linux/include/asm-parisc/timex.h
+ *
+ * PARISC architecture timex specifications
+ */
+#ifndef _ASMPARISC_TIMEX_H
+#define _ASMPARISC_TIMEX_H
+
+#include <asm/system.h>
+
+#define CLOCK_TICK_RATE	1193180 /* Underlying HZ */
+
+typedef unsigned long cycles_t;
+
+static inline cycles_t get_cycles (void)
+{
+	return mfctl(16);
+}
+
+#endif
diff --git a/arch/parisc/include/asm/tlb.h b/arch/parisc/include/asm/tlb.h
new file mode 100644
index 000000000000..383b1db310ee
--- /dev/null
+++ b/arch/parisc/include/asm/tlb.h
@@ -0,0 +1,27 @@
+#ifndef _PARISC_TLB_H
+#define _PARISC_TLB_H
+
+#define tlb_flush(tlb)			\
+do {	if ((tlb)->fullmm)		\
+		flush_tlb_mm((tlb)->mm);\
+} while (0)
+
+#define tlb_start_vma(tlb, vma) \
+do {	if (!(tlb)->fullmm)	\
+		flush_cache_range(vma, vma->vm_start, vma->vm_end); \
+} while (0)
+
+#define tlb_end_vma(tlb, vma)	\
+do {	if (!(tlb)->fullmm)	\
+		flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
+} while (0)
+
+#define __tlb_remove_tlb_entry(tlb, pte, address) \
+	do { } while (0)
+
+#include <asm-generic/tlb.h>
+
+#define __pmd_free_tlb(tlb, pmd)	pmd_free((tlb)->mm, pmd)
+#define __pte_free_tlb(tlb, pte)	pte_free((tlb)->mm, pte)
+
+#endif
diff --git a/arch/parisc/include/asm/tlbflush.h b/arch/parisc/include/asm/tlbflush.h
new file mode 100644
index 000000000000..b72ec66db699
--- /dev/null
+++ b/arch/parisc/include/asm/tlbflush.h
@@ -0,0 +1,80 @@
+#ifndef _PARISC_TLBFLUSH_H
+#define _PARISC_TLBFLUSH_H
+
+/* TLB flushing routines.... */
+
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <asm/mmu_context.h>
+
+
+/* This is for the serialisation of PxTLB broadcasts.  At least on the
+ * N class systems, only one PxTLB inter processor broadcast can be
+ * active at any one time on the Merced bus.  This tlb purge
+ * synchronisation is fairly lightweight and harmless so we activate
+ * it on all SMP systems not just the N class.  We also need to have
+ * preemption disabled on uniprocessor machines, and spin_lock does that
+ * nicely.
+ */
+extern spinlock_t pa_tlb_lock;
+
+#define purge_tlb_start(x) spin_lock(&pa_tlb_lock)
+#define purge_tlb_end(x) spin_unlock(&pa_tlb_lock)
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_all_local(void *);
+
+/*
+ * flush_tlb_mm()
+ *
+ * XXX This code is NOT valid for HP-UX compatibility processes,
+ * (although it will probably work 99% of the time). HP-UX
+ * processes are free to play with the space id's and save them
+ * over long periods of time, etc. so we have to preserve the
+ * space and just flush the entire tlb. We need to check the
+ * personality in order to do that, but the personality is not
+ * currently being set correctly.
+ *
+ * Of course, Linux processes could do the same thing, but
+ * we don't support that (and the compilers, dynamic linker,
+ * etc. do not do that).
+ */
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+	BUG_ON(mm == &init_mm); /* Should never happen */
+
+#ifdef CONFIG_SMP
+	flush_tlb_all();
+#else
+	if (mm) {
+		if (mm->context != 0)
+			free_sid(mm->context);
+		mm->context = alloc_sid();
+		if (mm == current->active_mm)
+			load_context(mm->context);
+	}
+#endif
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+	unsigned long addr)
+{
+	/* For one page, it's not worth testing the split_tlb variable */
+
+	mb();
+	mtsp(vma->vm_mm->context,1);
+	purge_tlb_start();
+	pdtlb(addr);
+	pitlb(addr);
+	purge_tlb_end();
+}
+
+void __flush_tlb_range(unsigned long sid,
+	unsigned long start, unsigned long end);
+
+#define flush_tlb_range(vma,start,end) __flush_tlb_range((vma)->vm_mm->context,start,end)
+
+#define flush_tlb_kernel_range(start, end) __flush_tlb_range(0,start,end)
+
+#endif
diff --git a/arch/parisc/include/asm/topology.h b/arch/parisc/include/asm/topology.h
new file mode 100644
index 000000000000..d8133eb0b1e7
--- /dev/null
+++ b/arch/parisc/include/asm/topology.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_PARISC_TOPOLOGY_H
+#define _ASM_PARISC_TOPOLOGY_H
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_PARISC_TOPOLOGY_H */
diff --git a/arch/parisc/include/asm/traps.h b/arch/parisc/include/asm/traps.h
new file mode 100644
index 000000000000..1945f995f2df
--- /dev/null
+++ b/arch/parisc/include/asm/traps.h
@@ -0,0 +1,16 @@
+#ifndef __ASM_TRAPS_H
+#define __ASM_TRAPS_H
+
+#ifdef __KERNEL__
+struct pt_regs;
+
+/* traps.c */
+void parisc_terminate(char *msg, struct pt_regs *regs,
+		int code, unsigned long offset);
+
+/* mm/fault.c */
+void do_page_fault(struct pt_regs *regs, unsigned long code,
+		unsigned long address);
+#endif
+
+#endif
diff --git a/arch/parisc/include/asm/types.h b/arch/parisc/include/asm/types.h
new file mode 100644
index 000000000000..7f5a39bfb4ce
--- /dev/null
+++ b/arch/parisc/include/asm/types.h
@@ -0,0 +1,36 @@
+#ifndef _PARISC_TYPES_H
+#define _PARISC_TYPES_H
+
+#include <asm-generic/int-ll64.h>
+
+#ifndef __ASSEMBLY__
+
+typedef unsigned short umode_t;
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * These aren't exported outside the kernel to avoid name space clashes
+ */
+#ifdef __KERNEL__
+
+#ifdef CONFIG_64BIT
+#define BITS_PER_LONG 64
+#define SHIFT_PER_LONG 6
+#else
+#define BITS_PER_LONG 32
+#define SHIFT_PER_LONG 5
+#endif
+
+#ifndef __ASSEMBLY__
+
+/* Dma addresses are 32-bits wide.  */
+
+typedef u32 dma_addr_t;
+typedef u64 dma64_addr_t;
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __KERNEL__ */
+
+#endif
diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h
new file mode 100644
index 000000000000..4878b9501f24
--- /dev/null
+++ b/arch/parisc/include/asm/uaccess.h
@@ -0,0 +1,244 @@
+#ifndef __PARISC_UACCESS_H
+#define __PARISC_UACCESS_H
+
+/*
+ * User space memory access functions
+ */
+#include <asm/page.h>
+#include <asm/system.h>
+#include <asm/cache.h>
+#include <asm-generic/uaccess.h>
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+#define KERNEL_DS	((mm_segment_t){0})
+#define USER_DS 	((mm_segment_t){1})
+
+#define segment_eq(a,b)	((a).seg == (b).seg)
+
+#define get_ds()	(KERNEL_DS)
+#define get_fs()	(current_thread_info()->addr_limit)
+#define set_fs(x)	(current_thread_info()->addr_limit = (x))
+
+/*
+ * Note that since kernel addresses are in a separate address space on
+ * parisc, we don't need to do anything for access_ok().
+ * We just let the page fault handler do the right thing. This also means
+ * that put_user is the same as __put_user, etc.
+ */
+
+extern int __get_kernel_bad(void);
+extern int __get_user_bad(void);
+extern int __put_kernel_bad(void);
+extern int __put_user_bad(void);
+
+static inline long access_ok(int type, const void __user * addr,
+		unsigned long size)
+{
+	return 1;
+}
+
+#define put_user __put_user
+#define get_user __get_user
+
+#if !defined(CONFIG_64BIT)
+#define LDD_KERNEL(ptr)		__get_kernel_bad();
+#define LDD_USER(ptr)		__get_user_bad();
+#define STD_KERNEL(x, ptr)	__put_kernel_asm64(x,ptr)
+#define STD_USER(x, ptr)	__put_user_asm64(x,ptr)
+#define ASM_WORD_INSN		".word\t"
+#else
+#define LDD_KERNEL(ptr)		__get_kernel_asm("ldd",ptr)
+#define LDD_USER(ptr)		__get_user_asm("ldd",ptr)
+#define STD_KERNEL(x, ptr)	__put_kernel_asm("std",x,ptr)
+#define STD_USER(x, ptr)	__put_user_asm("std",x,ptr)
+#define ASM_WORD_INSN		".dword\t"
+#endif
+
+/*
+ * The exception table contains two values: the first is an address
+ * for an instruction that is allowed to fault, and the second is
+ * the address to the fixup routine. 
+ */
+
+struct exception_table_entry {
+	unsigned long insn;  /* address of insn that is allowed to fault.   */
+	long fixup;          /* fixup routine */
+};
+
+#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\
+	".section __ex_table,\"aw\"\n"			   \
+	ASM_WORD_INSN #fault_addr ", " #except_addr "\n\t" \
+	".previous\n"
+
+/*
+ * The page fault handler stores, in a per-cpu area, the following information
+ * if a fixup routine is available.
+ */
+struct exception_data {
+	unsigned long fault_ip;
+	unsigned long fault_space;
+	unsigned long fault_addr;
+};
+
+#define __get_user(x,ptr)                               \
+({                                                      \
+	register long __gu_err __asm__ ("r8") = 0;      \
+	register long __gu_val __asm__ ("r9") = 0;      \
+							\
+	if (segment_eq(get_fs(),KERNEL_DS)) {           \
+	    switch (sizeof(*(ptr))) {                   \
+	    case 1: __get_kernel_asm("ldb",ptr); break; \
+	    case 2: __get_kernel_asm("ldh",ptr); break; \
+	    case 4: __get_kernel_asm("ldw",ptr); break; \
+	    case 8: LDD_KERNEL(ptr); break;		\
+	    default: __get_kernel_bad(); break;         \
+	    }                                           \
+	}                                               \
+	else {                                          \
+	    switch (sizeof(*(ptr))) {                   \
+	    case 1: __get_user_asm("ldb",ptr); break;   \
+	    case 2: __get_user_asm("ldh",ptr); break;   \
+	    case 4: __get_user_asm("ldw",ptr); break;   \
+	    case 8: LDD_USER(ptr);  break;		\
+	    default: __get_user_bad(); break;           \
+	    }                                           \
+	}                                               \
+							\
+	(x) = (__typeof__(*(ptr))) __gu_val;            \
+	__gu_err;                                       \
+})
+
+#define __get_kernel_asm(ldx,ptr)                       \
+	__asm__("\n1:\t" ldx "\t0(%2),%0\n\t"		\
+		ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_get_user_skip_1)\
+		: "=r"(__gu_val), "=r"(__gu_err)        \
+		: "r"(ptr), "1"(__gu_err)		\
+		: "r1");
+
+#define __get_user_asm(ldx,ptr)                         \
+	__asm__("\n1:\t" ldx "\t0(%%sr3,%2),%0\n\t"	\
+		ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_get_user_skip_1)\
+		: "=r"(__gu_val), "=r"(__gu_err)        \
+		: "r"(ptr), "1"(__gu_err)		\
+		: "r1");
+
+#define __put_user(x,ptr)                                       \
+({								\
+	register long __pu_err __asm__ ("r8") = 0;      	\
+        __typeof__(*(ptr)) __x = (__typeof__(*(ptr)))(x);	\
+								\
+	if (segment_eq(get_fs(),KERNEL_DS)) {                   \
+	    switch (sizeof(*(ptr))) {                           \
+	    case 1: __put_kernel_asm("stb",__x,ptr); break;     \
+	    case 2: __put_kernel_asm("sth",__x,ptr); break;     \
+	    case 4: __put_kernel_asm("stw",__x,ptr); break;     \
+	    case 8: STD_KERNEL(__x,ptr); break;			\
+	    default: __put_kernel_bad(); break;			\
+	    }                                                   \
+	}                                                       \
+	else {                                                  \
+	    switch (sizeof(*(ptr))) {                           \
+	    case 1: __put_user_asm("stb",__x,ptr); break;       \
+	    case 2: __put_user_asm("sth",__x,ptr); break;       \
+	    case 4: __put_user_asm("stw",__x,ptr); break;       \
+	    case 8: STD_USER(__x,ptr); break;			\
+	    default: __put_user_bad(); break;			\
+	    }                                                   \
+	}                                                       \
+								\
+	__pu_err;						\
+})
+
+/*
+ * The "__put_user/kernel_asm()" macros tell gcc they read from memory
+ * instead of writing. This is because they do not write to any memory
+ * gcc knows about, so there are no aliasing issues. These macros must
+ * also be aware that "fixup_put_user_skip_[12]" are executed in the
+ * context of the fault, and any registers used there must be listed
+ * as clobbers. In this case only "r1" is used by the current routines.
+ * r8/r9 are already listed as err/val.
+ */
+
+#define __put_kernel_asm(stx,x,ptr)                         \
+	__asm__ __volatile__ (                              \
+		"\n1:\t" stx "\t%2,0(%1)\n\t"		    \
+		ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_1)\
+		: "=r"(__pu_err)                            \
+		: "r"(ptr), "r"(x), "0"(__pu_err)	    \
+	    	: "r1")
+
+#define __put_user_asm(stx,x,ptr)                           \
+	__asm__ __volatile__ (                              \
+		"\n1:\t" stx "\t%2,0(%%sr3,%1)\n\t"	    \
+		ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_1)\
+		: "=r"(__pu_err)                            \
+		: "r"(ptr), "r"(x), "0"(__pu_err)	    \
+		: "r1")
+
+
+#if !defined(CONFIG_64BIT)
+
+#define __put_kernel_asm64(__val,ptr) do {		    \
+	u64 __val64 = (u64)(__val);			    \
+	u32 hi = (__val64) >> 32;			    \
+	u32 lo = (__val64) & 0xffffffff;		    \
+	__asm__ __volatile__ (				    \
+		"\n1:\tstw %2,0(%1)"			    \
+		"\n2:\tstw %3,4(%1)\n\t"		    \
+		ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\
+		ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\
+		: "=r"(__pu_err)                            \
+		: "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \
+		: "r1");				    \
+} while (0)
+
+#define __put_user_asm64(__val,ptr) do {	    	    \
+	u64 __val64 = (u64)(__val);			    \
+	u32 hi = (__val64) >> 32;			    \
+	u32 lo = (__val64) & 0xffffffff;		    \
+	__asm__ __volatile__ (				    \
+		"\n1:\tstw %2,0(%%sr3,%1)"		    \
+		"\n2:\tstw %3,4(%%sr3,%1)\n\t"		    \
+		ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\
+		ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\
+		: "=r"(__pu_err)                            \
+		: "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \
+		: "r1");				    \
+} while (0)
+
+#endif /* !defined(CONFIG_64BIT) */
+
+
+/*
+ * Complex access routines -- external declarations
+ */
+
+extern unsigned long lcopy_to_user(void __user *, const void *, unsigned long);
+extern unsigned long lcopy_from_user(void *, const void __user *, unsigned long);
+extern unsigned long lcopy_in_user(void __user *, const void __user *, unsigned long);
+extern long lstrncpy_from_user(char *, const char __user *, long);
+extern unsigned lclear_user(void __user *,unsigned long);
+extern long lstrnlen_user(const char __user *,long);
+
+/*
+ * Complex access routines -- macros
+ */
+
+#define strncpy_from_user lstrncpy_from_user
+#define strnlen_user lstrnlen_user
+#define strlen_user(str) lstrnlen_user(str, 0x7fffffffL)
+#define clear_user lclear_user
+#define __clear_user lclear_user
+
+unsigned long copy_to_user(void __user *dst, const void *src, unsigned long len);
+#define __copy_to_user copy_to_user
+unsigned long copy_from_user(void *dst, const void __user *src, unsigned long len);
+#define __copy_from_user copy_from_user
+unsigned long copy_in_user(void __user *dst, const void __user *src, unsigned long len);
+#define __copy_in_user copy_in_user
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
+
+#endif /* __PARISC_UACCESS_H */
diff --git a/arch/parisc/include/asm/ucontext.h b/arch/parisc/include/asm/ucontext.h
new file mode 100644
index 000000000000..6c8883e4b0bd
--- /dev/null
+++ b/arch/parisc/include/asm/ucontext.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_PARISC_UCONTEXT_H
+#define _ASM_PARISC_UCONTEXT_H
+
+struct ucontext {
+	unsigned int	  uc_flags;
+	struct ucontext  *uc_link;
+	stack_t		  uc_stack;
+	struct sigcontext uc_mcontext;
+	sigset_t	  uc_sigmask;	/* mask last for extensibility */
+};
+
+#endif /* !_ASM_PARISC_UCONTEXT_H */
diff --git a/arch/parisc/include/asm/unaligned.h b/arch/parisc/include/asm/unaligned.h
new file mode 100644
index 000000000000..dfc5d3321a54
--- /dev/null
+++ b/arch/parisc/include/asm/unaligned.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_PARISC_UNALIGNED_H
+#define _ASM_PARISC_UNALIGNED_H
+
+#include <linux/unaligned/be_struct.h>
+#include <linux/unaligned/le_byteshift.h>
+#include <linux/unaligned/generic.h>
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
+
+#ifdef __KERNEL__
+struct pt_regs;
+void handle_unaligned(struct pt_regs *regs);
+int check_unaligned(struct pt_regs *regs);
+#endif
+
+#endif /* _ASM_PARISC_UNALIGNED_H */
diff --git a/arch/parisc/include/asm/unistd.h b/arch/parisc/include/asm/unistd.h
new file mode 100644
index 000000000000..a7d857f0e4f4
--- /dev/null
+++ b/arch/parisc/include/asm/unistd.h
@@ -0,0 +1,991 @@
+#ifndef _ASM_PARISC_UNISTD_H_
+#define _ASM_PARISC_UNISTD_H_
+
+/*
+ * This file contains the system call numbers.
+ */
+
+/*
+ *   HP-UX system calls get their native numbers for binary compatibility.
+ */
+
+#define __NR_HPUX_exit                    1
+#define __NR_HPUX_fork                    2
+#define __NR_HPUX_read                    3
+#define __NR_HPUX_write                   4
+#define __NR_HPUX_open                    5
+#define __NR_HPUX_close                   6
+#define __NR_HPUX_wait                    7
+#define __NR_HPUX_creat                   8
+#define __NR_HPUX_link                    9
+#define __NR_HPUX_unlink                 10
+#define __NR_HPUX_execv                  11
+#define __NR_HPUX_chdir                  12
+#define __NR_HPUX_time                   13
+#define __NR_HPUX_mknod                  14
+#define __NR_HPUX_chmod                  15
+#define __NR_HPUX_chown                  16
+#define __NR_HPUX_break                  17
+#define __NR_HPUX_lchmod                 18
+#define __NR_HPUX_lseek                  19
+#define __NR_HPUX_getpid                 20
+#define __NR_HPUX_mount                  21
+#define __NR_HPUX_umount                 22
+#define __NR_HPUX_setuid                 23
+#define __NR_HPUX_getuid                 24
+#define __NR_HPUX_stime                  25
+#define __NR_HPUX_ptrace                 26
+#define __NR_HPUX_alarm                  27
+#define __NR_HPUX_oldfstat               28
+#define __NR_HPUX_pause                  29
+#define __NR_HPUX_utime                  30
+#define __NR_HPUX_stty                   31
+#define __NR_HPUX_gtty                   32
+#define __NR_HPUX_access                 33
+#define __NR_HPUX_nice                   34
+#define __NR_HPUX_ftime                  35
+#define __NR_HPUX_sync                   36
+#define __NR_HPUX_kill                   37
+#define __NR_HPUX_stat                   38
+#define __NR_HPUX_setpgrp3               39
+#define __NR_HPUX_lstat                  40
+#define __NR_HPUX_dup                    41
+#define __NR_HPUX_pipe                   42
+#define __NR_HPUX_times                  43
+#define __NR_HPUX_profil                 44
+#define __NR_HPUX_ki_call                45
+#define __NR_HPUX_setgid                 46
+#define __NR_HPUX_getgid                 47
+#define __NR_HPUX_sigsys                 48
+#define __NR_HPUX_reserved1              49
+#define __NR_HPUX_reserved2              50
+#define __NR_HPUX_acct                   51
+#define __NR_HPUX_set_userthreadid       52
+#define __NR_HPUX_oldlock                53
+#define __NR_HPUX_ioctl                  54
+#define __NR_HPUX_reboot                 55
+#define __NR_HPUX_symlink                56
+#define __NR_HPUX_utssys                 57
+#define __NR_HPUX_readlink               58
+#define __NR_HPUX_execve                 59
+#define __NR_HPUX_umask                  60
+#define __NR_HPUX_chroot                 61
+#define __NR_HPUX_fcntl                  62
+#define __NR_HPUX_ulimit                 63
+#define __NR_HPUX_getpagesize            64
+#define __NR_HPUX_mremap                 65
+#define __NR_HPUX_vfork                  66
+#define __NR_HPUX_vread                  67
+#define __NR_HPUX_vwrite                 68
+#define __NR_HPUX_sbrk                   69
+#define __NR_HPUX_sstk                   70
+#define __NR_HPUX_mmap                   71
+#define __NR_HPUX_vadvise                72
+#define __NR_HPUX_munmap                 73
+#define __NR_HPUX_mprotect               74
+#define __NR_HPUX_madvise                75
+#define __NR_HPUX_vhangup                76
+#define __NR_HPUX_swapoff                77
+#define __NR_HPUX_mincore                78
+#define __NR_HPUX_getgroups              79
+#define __NR_HPUX_setgroups              80
+#define __NR_HPUX_getpgrp2               81
+#define __NR_HPUX_setpgrp2               82
+#define __NR_HPUX_setitimer              83
+#define __NR_HPUX_wait3                  84
+#define __NR_HPUX_swapon                 85
+#define __NR_HPUX_getitimer              86
+#define __NR_HPUX_gethostname42          87
+#define __NR_HPUX_sethostname42          88
+#define __NR_HPUX_getdtablesize          89
+#define __NR_HPUX_dup2                   90
+#define __NR_HPUX_getdopt                91
+#define __NR_HPUX_fstat                  92
+#define __NR_HPUX_select                 93
+#define __NR_HPUX_setdopt                94
+#define __NR_HPUX_fsync                  95
+#define __NR_HPUX_setpriority            96
+#define __NR_HPUX_socket_old             97
+#define __NR_HPUX_connect_old            98
+#define __NR_HPUX_accept_old             99
+#define __NR_HPUX_getpriority           100
+#define __NR_HPUX_send_old              101
+#define __NR_HPUX_recv_old              102
+#define __NR_HPUX_socketaddr_old        103
+#define __NR_HPUX_bind_old              104
+#define __NR_HPUX_setsockopt_old        105
+#define __NR_HPUX_listen_old            106
+#define __NR_HPUX_vtimes_old            107
+#define __NR_HPUX_sigvector             108
+#define __NR_HPUX_sigblock              109
+#define __NR_HPUX_siggetmask            110
+#define __NR_HPUX_sigpause              111
+#define __NR_HPUX_sigstack              112
+#define __NR_HPUX_recvmsg_old           113
+#define __NR_HPUX_sendmsg_old           114
+#define __NR_HPUX_vtrace_old            115
+#define __NR_HPUX_gettimeofday          116
+#define __NR_HPUX_getrusage             117
+#define __NR_HPUX_getsockopt_old        118
+#define __NR_HPUX_resuba_old            119
+#define __NR_HPUX_readv                 120
+#define __NR_HPUX_writev                121
+#define __NR_HPUX_settimeofday          122
+#define __NR_HPUX_fchown                123
+#define __NR_HPUX_fchmod                124
+#define __NR_HPUX_recvfrom_old          125
+#define __NR_HPUX_setresuid             126
+#define __NR_HPUX_setresgid             127
+#define __NR_HPUX_rename                128
+#define __NR_HPUX_truncate              129
+#define __NR_HPUX_ftruncate             130
+#define __NR_HPUX_flock_old             131
+#define __NR_HPUX_sysconf               132
+#define __NR_HPUX_sendto_old            133
+#define __NR_HPUX_shutdown_old          134
+#define __NR_HPUX_socketpair_old        135
+#define __NR_HPUX_mkdir                 136
+#define __NR_HPUX_rmdir                 137
+#define __NR_HPUX_utimes_old            138
+#define __NR_HPUX_sigcleanup_old        139
+#define __NR_HPUX_setcore               140
+#define __NR_HPUX_getpeername_old       141
+#define __NR_HPUX_gethostid             142
+#define __NR_HPUX_sethostid             143
+#define __NR_HPUX_getrlimit             144
+#define __NR_HPUX_setrlimit             145
+#define __NR_HPUX_killpg_old            146
+#define __NR_HPUX_cachectl              147
+#define __NR_HPUX_quotactl              148
+#define __NR_HPUX_get_sysinfo           149
+#define __NR_HPUX_getsockname_old       150
+#define __NR_HPUX_privgrp               151
+#define __NR_HPUX_rtprio                152
+#define __NR_HPUX_plock                 153
+#define __NR_HPUX_reserved3             154
+#define __NR_HPUX_lockf                 155
+#define __NR_HPUX_semget                156
+#define __NR_HPUX_osemctl               157
+#define __NR_HPUX_semop                 158
+#define __NR_HPUX_msgget                159
+#define __NR_HPUX_omsgctl               160
+#define __NR_HPUX_msgsnd                161
+#define __NR_HPUX_msgrecv               162
+#define __NR_HPUX_shmget                163
+#define __NR_HPUX_oshmctl               164
+#define __NR_HPUX_shmat                 165
+#define __NR_HPUX_shmdt                 166
+#define __NR_HPUX_m68020_advise         167
+/* [168,189] are for Discless/DUX */
+#define __NR_HPUX_csp                   168
+#define __NR_HPUX_cluster               169
+#define __NR_HPUX_mkrnod                170
+#define __NR_HPUX_test                  171
+#define __NR_HPUX_unsp_open             172
+#define __NR_HPUX_reserved4             173
+#define __NR_HPUX_getcontext_old        174
+#define __NR_HPUX_osetcontext           175
+#define __NR_HPUX_bigio                 176
+#define __NR_HPUX_pipenode              177
+#define __NR_HPUX_lsync                 178
+#define __NR_HPUX_getmachineid          179
+#define __NR_HPUX_cnodeid               180
+#define __NR_HPUX_cnodes                181
+#define __NR_HPUX_swapclients           182
+#define __NR_HPUX_rmt_process           183
+#define __NR_HPUX_dskless_stats         184
+#define __NR_HPUX_sigprocmask           185
+#define __NR_HPUX_sigpending            186
+#define __NR_HPUX_sigsuspend            187
+#define __NR_HPUX_sigaction             188
+#define __NR_HPUX_reserved5             189
+#define __NR_HPUX_nfssvc                190
+#define __NR_HPUX_getfh                 191
+#define __NR_HPUX_getdomainname         192
+#define __NR_HPUX_setdomainname         193
+#define __NR_HPUX_async_daemon          194
+#define __NR_HPUX_getdirentries         195
+#define __NR_HPUX_statfs                196
+#define __NR_HPUX_fstatfs               197
+#define __NR_HPUX_vfsmount              198
+#define __NR_HPUX_reserved6             199
+#define __NR_HPUX_waitpid               200
+/* 201 - 223 missing */
+#define __NR_HPUX_sigsetreturn          224
+#define __NR_HPUX_sigsetstatemask       225
+/* 226 missing */
+#define __NR_HPUX_cs                    227
+#define __NR_HPUX_cds                   228
+#define __NR_HPUX_set_no_trunc          229
+#define __NR_HPUX_pathconf              230
+#define __NR_HPUX_fpathconf             231
+/* 232, 233 missing */
+#define __NR_HPUX_nfs_fcntl             234
+#define __NR_HPUX_ogetacl               235
+#define __NR_HPUX_ofgetacl              236
+#define __NR_HPUX_osetacl               237
+#define __NR_HPUX_ofsetacl              238
+#define __NR_HPUX_pstat                 239
+#define __NR_HPUX_getaudid              240
+#define __NR_HPUX_setaudid              241
+#define __NR_HPUX_getaudproc            242
+#define __NR_HPUX_setaudproc            243
+#define __NR_HPUX_getevent              244
+#define __NR_HPUX_setevent              245
+#define __NR_HPUX_audwrite              246
+#define __NR_HPUX_audswitch             247
+#define __NR_HPUX_audctl                248
+#define __NR_HPUX_ogetaccess            249
+#define __NR_HPUX_fsctl                 250
+/* 251 - 258 missing */
+#define __NR_HPUX_swapfs                259
+#define __NR_HPUX_fss                   260
+/* 261 - 266 missing */
+#define __NR_HPUX_tsync                 267
+#define __NR_HPUX_getnumfds             268
+#define __NR_HPUX_poll                  269
+#define __NR_HPUX_getmsg                270
+#define __NR_HPUX_putmsg                271
+#define __NR_HPUX_fchdir                272
+#define __NR_HPUX_getmount_cnt          273
+#define __NR_HPUX_getmount_entry        274
+#define __NR_HPUX_accept                275
+#define __NR_HPUX_bind                  276
+#define __NR_HPUX_connect               277
+#define __NR_HPUX_getpeername           278
+#define __NR_HPUX_getsockname           279
+#define __NR_HPUX_getsockopt            280
+#define __NR_HPUX_listen                281
+#define __NR_HPUX_recv                  282
+#define __NR_HPUX_recvfrom              283
+#define __NR_HPUX_recvmsg               284
+#define __NR_HPUX_send                  285
+#define __NR_HPUX_sendmsg               286
+#define __NR_HPUX_sendto                287
+#define __NR_HPUX_setsockopt            288
+#define __NR_HPUX_shutdown              289
+#define __NR_HPUX_socket                290
+#define __NR_HPUX_socketpair            291
+#define __NR_HPUX_proc_open             292
+#define __NR_HPUX_proc_close            293
+#define __NR_HPUX_proc_send             294
+#define __NR_HPUX_proc_recv             295
+#define __NR_HPUX_proc_sendrecv         296
+#define __NR_HPUX_proc_syscall          297
+/* 298 - 311 missing */
+#define __NR_HPUX_semctl                312
+#define __NR_HPUX_msgctl                313
+#define __NR_HPUX_shmctl                314
+#define __NR_HPUX_mpctl                 315
+#define __NR_HPUX_exportfs              316
+#define __NR_HPUX_getpmsg               317
+#define __NR_HPUX_putpmsg               318
+/* 319 missing */
+#define __NR_HPUX_msync                 320
+#define __NR_HPUX_msleep                321
+#define __NR_HPUX_mwakeup               322
+#define __NR_HPUX_msem_init             323
+#define __NR_HPUX_msem_remove           324
+#define __NR_HPUX_adjtime               325
+#define __NR_HPUX_kload                 326
+#define __NR_HPUX_fattach               327
+#define __NR_HPUX_fdetach               328
+#define __NR_HPUX_serialize             329
+#define __NR_HPUX_statvfs               330
+#define __NR_HPUX_fstatvfs              331
+#define __NR_HPUX_lchown                332
+#define __NR_HPUX_getsid                333
+#define __NR_HPUX_sysfs                 334
+/* 335, 336 missing */
+#define __NR_HPUX_sched_setparam        337
+#define __NR_HPUX_sched_getparam        338
+#define __NR_HPUX_sched_setscheduler    339
+#define __NR_HPUX_sched_getscheduler    340
+#define __NR_HPUX_sched_yield           341
+#define __NR_HPUX_sched_get_priority_max 342
+#define __NR_HPUX_sched_get_priority_min 343
+#define __NR_HPUX_sched_rr_get_interval 344
+#define __NR_HPUX_clock_settime         345
+#define __NR_HPUX_clock_gettime         346
+#define __NR_HPUX_clock_getres          347
+#define __NR_HPUX_timer_create          348
+#define __NR_HPUX_timer_delete          349
+#define __NR_HPUX_timer_settime         350
+#define __NR_HPUX_timer_gettime         351
+#define __NR_HPUX_timer_getoverrun      352
+#define __NR_HPUX_nanosleep             353
+#define __NR_HPUX_toolbox               354
+/* 355 missing */
+#define __NR_HPUX_getdents              356
+#define __NR_HPUX_getcontext            357
+#define __NR_HPUX_sysinfo               358
+#define __NR_HPUX_fcntl64               359
+#define __NR_HPUX_ftruncate64           360
+#define __NR_HPUX_fstat64               361
+#define __NR_HPUX_getdirentries64       362
+#define __NR_HPUX_getrlimit64           363
+#define __NR_HPUX_lockf64               364
+#define __NR_HPUX_lseek64               365
+#define __NR_HPUX_lstat64               366
+#define __NR_HPUX_mmap64                367
+#define __NR_HPUX_setrlimit64           368
+#define __NR_HPUX_stat64                369
+#define __NR_HPUX_truncate64            370
+#define __NR_HPUX_ulimit64              371
+#define __NR_HPUX_pread                 372
+#define __NR_HPUX_preadv                373
+#define __NR_HPUX_pwrite                374
+#define __NR_HPUX_pwritev               375
+#define __NR_HPUX_pread64               376
+#define __NR_HPUX_preadv64              377
+#define __NR_HPUX_pwrite64              378
+#define __NR_HPUX_pwritev64             379
+#define __NR_HPUX_setcontext            380
+#define __NR_HPUX_sigaltstack           381
+#define __NR_HPUX_waitid                382
+#define __NR_HPUX_setpgrp               383
+#define __NR_HPUX_recvmsg2              384
+#define __NR_HPUX_sendmsg2              385
+#define __NR_HPUX_socket2               386
+#define __NR_HPUX_socketpair2           387
+#define __NR_HPUX_setregid              388
+#define __NR_HPUX_lwp_create            389
+#define __NR_HPUX_lwp_terminate         390
+#define __NR_HPUX_lwp_wait              391
+#define __NR_HPUX_lwp_suspend           392
+#define __NR_HPUX_lwp_resume            393
+/* 394 missing */
+#define __NR_HPUX_lwp_abort_syscall     395
+#define __NR_HPUX_lwp_info              396
+#define __NR_HPUX_lwp_kill              397
+#define __NR_HPUX_ksleep                398
+#define __NR_HPUX_kwakeup               399
+/* 400 missing */
+#define __NR_HPUX_pstat_getlwp          401
+#define __NR_HPUX_lwp_exit              402
+#define __NR_HPUX_lwp_continue          403
+#define __NR_HPUX_getacl                404
+#define __NR_HPUX_fgetacl               405
+#define __NR_HPUX_setacl                406
+#define __NR_HPUX_fsetacl               407
+#define __NR_HPUX_getaccess             408
+#define __NR_HPUX_lwp_mutex_init        409
+#define __NR_HPUX_lwp_mutex_lock_sys    410
+#define __NR_HPUX_lwp_mutex_unlock      411
+#define __NR_HPUX_lwp_cond_init         412
+#define __NR_HPUX_lwp_cond_signal       413
+#define __NR_HPUX_lwp_cond_broadcast    414
+#define __NR_HPUX_lwp_cond_wait_sys     415
+#define __NR_HPUX_lwp_getscheduler      416
+#define __NR_HPUX_lwp_setscheduler      417
+#define __NR_HPUX_lwp_getstate          418
+#define __NR_HPUX_lwp_setstate          419
+#define __NR_HPUX_lwp_detach            420
+#define __NR_HPUX_mlock                 421
+#define __NR_HPUX_munlock               422
+#define __NR_HPUX_mlockall              423
+#define __NR_HPUX_munlockall            424
+#define __NR_HPUX_shm_open              425
+#define __NR_HPUX_shm_unlink            426
+#define __NR_HPUX_sigqueue              427
+#define __NR_HPUX_sigwaitinfo           428
+#define __NR_HPUX_sigtimedwait          429
+#define __NR_HPUX_sigwait               430
+#define __NR_HPUX_aio_read              431
+#define __NR_HPUX_aio_write             432
+#define __NR_HPUX_lio_listio            433
+#define __NR_HPUX_aio_error             434
+#define __NR_HPUX_aio_return            435
+#define __NR_HPUX_aio_cancel            436
+#define __NR_HPUX_aio_suspend           437
+#define __NR_HPUX_aio_fsync             438
+#define __NR_HPUX_mq_open               439
+#define __NR_HPUX_mq_close              440
+#define __NR_HPUX_mq_unlink             441
+#define __NR_HPUX_mq_send               442
+#define __NR_HPUX_mq_receive            443
+#define __NR_HPUX_mq_notify             444
+#define __NR_HPUX_mq_setattr            445
+#define __NR_HPUX_mq_getattr            446
+#define __NR_HPUX_ksem_open             447
+#define __NR_HPUX_ksem_unlink           448
+#define __NR_HPUX_ksem_close            449
+#define __NR_HPUX_ksem_post             450
+#define __NR_HPUX_ksem_wait             451
+#define __NR_HPUX_ksem_read             452
+#define __NR_HPUX_ksem_trywait          453
+#define __NR_HPUX_lwp_rwlock_init       454
+#define __NR_HPUX_lwp_rwlock_destroy    455
+#define __NR_HPUX_lwp_rwlock_rdlock_sys 456
+#define __NR_HPUX_lwp_rwlock_wrlock_sys 457
+#define __NR_HPUX_lwp_rwlock_tryrdlock  458
+#define __NR_HPUX_lwp_rwlock_trywrlock  459
+#define __NR_HPUX_lwp_rwlock_unlock     460
+#define __NR_HPUX_ttrace                461
+#define __NR_HPUX_ttrace_wait           462
+#define __NR_HPUX_lf_wire_mem           463
+#define __NR_HPUX_lf_unwire_mem         464
+#define __NR_HPUX_lf_send_pin_map       465
+#define __NR_HPUX_lf_free_buf           466
+#define __NR_HPUX_lf_wait_nq            467
+#define __NR_HPUX_lf_wakeup_conn_q      468
+#define __NR_HPUX_lf_unused             469
+#define __NR_HPUX_lwp_sema_init         470
+#define __NR_HPUX_lwp_sema_post         471
+#define __NR_HPUX_lwp_sema_wait         472
+#define __NR_HPUX_lwp_sema_trywait      473
+#define __NR_HPUX_lwp_sema_destroy      474
+#define __NR_HPUX_statvfs64             475
+#define __NR_HPUX_fstatvfs64            476
+#define __NR_HPUX_msh_register          477
+#define __NR_HPUX_ptrace64              478
+#define __NR_HPUX_sendfile              479
+#define __NR_HPUX_sendpath              480
+#define __NR_HPUX_sendfile64            481
+#define __NR_HPUX_sendpath64            482
+#define __NR_HPUX_modload               483
+#define __NR_HPUX_moduload              484
+#define __NR_HPUX_modpath               485
+#define __NR_HPUX_getksym               486
+#define __NR_HPUX_modadm                487
+#define __NR_HPUX_modstat               488
+#define __NR_HPUX_lwp_detached_exit     489
+#define __NR_HPUX_crashconf             490
+#define __NR_HPUX_siginhibit            491
+#define __NR_HPUX_sigenable             492
+#define __NR_HPUX_spuctl                493
+#define __NR_HPUX_zerokernelsum         494
+#define __NR_HPUX_nfs_kstat             495
+#define __NR_HPUX_aio_read64            496
+#define __NR_HPUX_aio_write64           497
+#define __NR_HPUX_aio_error64           498
+#define __NR_HPUX_aio_return64          499
+#define __NR_HPUX_aio_cancel64          500
+#define __NR_HPUX_aio_suspend64         501
+#define __NR_HPUX_aio_fsync64           502
+#define __NR_HPUX_lio_listio64          503
+#define __NR_HPUX_recv2                 504
+#define __NR_HPUX_recvfrom2             505
+#define __NR_HPUX_send2                 506
+#define __NR_HPUX_sendto2               507
+#define __NR_HPUX_acl                   508
+#define __NR_HPUX___cnx_p2p_ctl         509
+#define __NR_HPUX___cnx_gsched_ctl      510
+#define __NR_HPUX___cnx_pmon_ctl        511
+
+#define __NR_HPUX_syscalls		512
+
+/*
+ * Linux system call numbers.
+ *
+ * Cary Coutant says that we should just use another syscall gateway
+ * page to avoid clashing with the HPUX space, and I think he's right:
+ * it will would keep a branch out of our syscall entry path, at the
+ * very least.  If we decide to change it later, we can ``just'' tweak
+ * the LINUX_GATEWAY_ADDR define at the bottom and make __NR_Linux be
+ * 1024 or something.  Oh, and recompile libc. =)
+ *
+ * 64-bit HPUX binaries get the syscall gateway address passed in a register
+ * from the kernel at startup, which seems a sane strategy.
+ */
+
+#define __NR_Linux                0
+#define __NR_restart_syscall      (__NR_Linux + 0)
+#define __NR_exit                 (__NR_Linux + 1)
+#define __NR_fork                 (__NR_Linux + 2)
+#define __NR_read                 (__NR_Linux + 3)
+#define __NR_write                (__NR_Linux + 4)
+#define __NR_open                 (__NR_Linux + 5)
+#define __NR_close                (__NR_Linux + 6)
+#define __NR_waitpid              (__NR_Linux + 7)
+#define __NR_creat                (__NR_Linux + 8)
+#define __NR_link                 (__NR_Linux + 9)
+#define __NR_unlink              (__NR_Linux + 10)
+#define __NR_execve              (__NR_Linux + 11)
+#define __NR_chdir               (__NR_Linux + 12)
+#define __NR_time                (__NR_Linux + 13)
+#define __NR_mknod               (__NR_Linux + 14)
+#define __NR_chmod               (__NR_Linux + 15)
+#define __NR_lchown              (__NR_Linux + 16)
+#define __NR_socket              (__NR_Linux + 17)
+#define __NR_stat                (__NR_Linux + 18)
+#define __NR_lseek               (__NR_Linux + 19)
+#define __NR_getpid              (__NR_Linux + 20)
+#define __NR_mount               (__NR_Linux + 21)
+#define __NR_bind                (__NR_Linux + 22)
+#define __NR_setuid              (__NR_Linux + 23)
+#define __NR_getuid              (__NR_Linux + 24)
+#define __NR_stime               (__NR_Linux + 25)
+#define __NR_ptrace              (__NR_Linux + 26)
+#define __NR_alarm               (__NR_Linux + 27)
+#define __NR_fstat               (__NR_Linux + 28)
+#define __NR_pause               (__NR_Linux + 29)
+#define __NR_utime               (__NR_Linux + 30)
+#define __NR_connect             (__NR_Linux + 31)
+#define __NR_listen              (__NR_Linux + 32)
+#define __NR_access              (__NR_Linux + 33)
+#define __NR_nice                (__NR_Linux + 34)
+#define __NR_accept              (__NR_Linux + 35)
+#define __NR_sync                (__NR_Linux + 36)
+#define __NR_kill                (__NR_Linux + 37)
+#define __NR_rename              (__NR_Linux + 38)
+#define __NR_mkdir               (__NR_Linux + 39)
+#define __NR_rmdir               (__NR_Linux + 40)
+#define __NR_dup                 (__NR_Linux + 41)
+#define __NR_pipe                (__NR_Linux + 42)
+#define __NR_times               (__NR_Linux + 43)
+#define __NR_getsockname         (__NR_Linux + 44)
+#define __NR_brk                 (__NR_Linux + 45)
+#define __NR_setgid              (__NR_Linux + 46)
+#define __NR_getgid              (__NR_Linux + 47)
+#define __NR_signal              (__NR_Linux + 48)
+#define __NR_geteuid             (__NR_Linux + 49)
+#define __NR_getegid             (__NR_Linux + 50)
+#define __NR_acct                (__NR_Linux + 51)
+#define __NR_umount2             (__NR_Linux + 52)
+#define __NR_getpeername         (__NR_Linux + 53)
+#define __NR_ioctl               (__NR_Linux + 54)
+#define __NR_fcntl               (__NR_Linux + 55)
+#define __NR_socketpair          (__NR_Linux + 56)
+#define __NR_setpgid             (__NR_Linux + 57)
+#define __NR_send                (__NR_Linux + 58)
+#define __NR_uname               (__NR_Linux + 59)
+#define __NR_umask               (__NR_Linux + 60)
+#define __NR_chroot              (__NR_Linux + 61)
+#define __NR_ustat               (__NR_Linux + 62)
+#define __NR_dup2                (__NR_Linux + 63)
+#define __NR_getppid             (__NR_Linux + 64)
+#define __NR_getpgrp             (__NR_Linux + 65)
+#define __NR_setsid              (__NR_Linux + 66)
+#define __NR_pivot_root          (__NR_Linux + 67)
+#define __NR_sgetmask            (__NR_Linux + 68)
+#define __NR_ssetmask            (__NR_Linux + 69)
+#define __NR_setreuid            (__NR_Linux + 70)
+#define __NR_setregid            (__NR_Linux + 71)
+#define __NR_mincore             (__NR_Linux + 72)
+#define __NR_sigpending          (__NR_Linux + 73)
+#define __NR_sethostname         (__NR_Linux + 74)
+#define __NR_setrlimit           (__NR_Linux + 75)
+#define __NR_getrlimit           (__NR_Linux + 76)
+#define __NR_getrusage           (__NR_Linux + 77)
+#define __NR_gettimeofday        (__NR_Linux + 78)
+#define __NR_settimeofday        (__NR_Linux + 79)
+#define __NR_getgroups           (__NR_Linux + 80)
+#define __NR_setgroups           (__NR_Linux + 81)
+#define __NR_sendto              (__NR_Linux + 82)
+#define __NR_symlink             (__NR_Linux + 83)
+#define __NR_lstat               (__NR_Linux + 84)
+#define __NR_readlink            (__NR_Linux + 85)
+#define __NR_uselib              (__NR_Linux + 86)
+#define __NR_swapon              (__NR_Linux + 87)
+#define __NR_reboot              (__NR_Linux + 88)
+#define __NR_mmap2             (__NR_Linux + 89)
+#define __NR_mmap                (__NR_Linux + 90)
+#define __NR_munmap              (__NR_Linux + 91)
+#define __NR_truncate            (__NR_Linux + 92)
+#define __NR_ftruncate           (__NR_Linux + 93)
+#define __NR_fchmod              (__NR_Linux + 94)
+#define __NR_fchown              (__NR_Linux + 95)
+#define __NR_getpriority         (__NR_Linux + 96)
+#define __NR_setpriority         (__NR_Linux + 97)
+#define __NR_recv                (__NR_Linux + 98)
+#define __NR_statfs              (__NR_Linux + 99)
+#define __NR_fstatfs            (__NR_Linux + 100)
+#define __NR_stat64           (__NR_Linux + 101)
+/* #define __NR_socketcall         (__NR_Linux + 102) */
+#define __NR_syslog             (__NR_Linux + 103)
+#define __NR_setitimer          (__NR_Linux + 104)
+#define __NR_getitimer          (__NR_Linux + 105)
+#define __NR_capget             (__NR_Linux + 106)
+#define __NR_capset             (__NR_Linux + 107)
+#define __NR_pread64            (__NR_Linux + 108)
+#define __NR_pwrite64           (__NR_Linux + 109)
+#define __NR_getcwd             (__NR_Linux + 110)
+#define __NR_vhangup            (__NR_Linux + 111)
+#define __NR_fstat64            (__NR_Linux + 112)
+#define __NR_vfork              (__NR_Linux + 113)
+#define __NR_wait4              (__NR_Linux + 114)
+#define __NR_swapoff            (__NR_Linux + 115)
+#define __NR_sysinfo            (__NR_Linux + 116)
+#define __NR_shutdown           (__NR_Linux + 117)
+#define __NR_fsync              (__NR_Linux + 118)
+#define __NR_madvise            (__NR_Linux + 119)
+#define __NR_clone              (__NR_Linux + 120)
+#define __NR_setdomainname      (__NR_Linux + 121)
+#define __NR_sendfile           (__NR_Linux + 122)
+#define __NR_recvfrom           (__NR_Linux + 123)
+#define __NR_adjtimex           (__NR_Linux + 124)
+#define __NR_mprotect           (__NR_Linux + 125)
+#define __NR_sigprocmask        (__NR_Linux + 126)
+#define __NR_create_module      (__NR_Linux + 127)
+#define __NR_init_module        (__NR_Linux + 128)
+#define __NR_delete_module      (__NR_Linux + 129)
+#define __NR_get_kernel_syms    (__NR_Linux + 130)
+#define __NR_quotactl           (__NR_Linux + 131)
+#define __NR_getpgid            (__NR_Linux + 132)
+#define __NR_fchdir             (__NR_Linux + 133)
+#define __NR_bdflush            (__NR_Linux + 134)
+#define __NR_sysfs              (__NR_Linux + 135)
+#define __NR_personality        (__NR_Linux + 136)
+#define __NR_afs_syscall        (__NR_Linux + 137) /* Syscall for Andrew File System */
+#define __NR_setfsuid           (__NR_Linux + 138)
+#define __NR_setfsgid           (__NR_Linux + 139)
+#define __NR__llseek            (__NR_Linux + 140)
+#define __NR_getdents           (__NR_Linux + 141)
+#define __NR__newselect         (__NR_Linux + 142)
+#define __NR_flock              (__NR_Linux + 143)
+#define __NR_msync              (__NR_Linux + 144)
+#define __NR_readv              (__NR_Linux + 145)
+#define __NR_writev             (__NR_Linux + 146)
+#define __NR_getsid             (__NR_Linux + 147)
+#define __NR_fdatasync          (__NR_Linux + 148)
+#define __NR__sysctl            (__NR_Linux + 149)
+#define __NR_mlock              (__NR_Linux + 150)
+#define __NR_munlock            (__NR_Linux + 151)
+#define __NR_mlockall           (__NR_Linux + 152)
+#define __NR_munlockall         (__NR_Linux + 153)
+#define __NR_sched_setparam             (__NR_Linux + 154)
+#define __NR_sched_getparam             (__NR_Linux + 155)
+#define __NR_sched_setscheduler         (__NR_Linux + 156)
+#define __NR_sched_getscheduler         (__NR_Linux + 157)
+#define __NR_sched_yield                (__NR_Linux + 158)
+#define __NR_sched_get_priority_max     (__NR_Linux + 159)
+#define __NR_sched_get_priority_min     (__NR_Linux + 160)
+#define __NR_sched_rr_get_interval      (__NR_Linux + 161)
+#define __NR_nanosleep          (__NR_Linux + 162)
+#define __NR_mremap             (__NR_Linux + 163)
+#define __NR_setresuid          (__NR_Linux + 164)
+#define __NR_getresuid          (__NR_Linux + 165)
+#define __NR_sigaltstack        (__NR_Linux + 166)
+#define __NR_query_module       (__NR_Linux + 167)
+#define __NR_poll               (__NR_Linux + 168)
+#define __NR_nfsservctl         (__NR_Linux + 169)
+#define __NR_setresgid          (__NR_Linux + 170)
+#define __NR_getresgid          (__NR_Linux + 171)
+#define __NR_prctl              (__NR_Linux + 172)
+#define __NR_rt_sigreturn       (__NR_Linux + 173)
+#define __NR_rt_sigaction       (__NR_Linux + 174)
+#define __NR_rt_sigprocmask     (__NR_Linux + 175)
+#define __NR_rt_sigpending      (__NR_Linux + 176)
+#define __NR_rt_sigtimedwait    (__NR_Linux + 177)
+#define __NR_rt_sigqueueinfo    (__NR_Linux + 178)
+#define __NR_rt_sigsuspend      (__NR_Linux + 179)
+#define __NR_chown              (__NR_Linux + 180)
+#define __NR_setsockopt         (__NR_Linux + 181)
+#define __NR_getsockopt         (__NR_Linux + 182)
+#define __NR_sendmsg            (__NR_Linux + 183)
+#define __NR_recvmsg            (__NR_Linux + 184)
+#define __NR_semop              (__NR_Linux + 185)
+#define __NR_semget             (__NR_Linux + 186)
+#define __NR_semctl             (__NR_Linux + 187)
+#define __NR_msgsnd             (__NR_Linux + 188)
+#define __NR_msgrcv             (__NR_Linux + 189)
+#define __NR_msgget             (__NR_Linux + 190)
+#define __NR_msgctl             (__NR_Linux + 191)
+#define __NR_shmat              (__NR_Linux + 192)
+#define __NR_shmdt              (__NR_Linux + 193)
+#define __NR_shmget             (__NR_Linux + 194)
+#define __NR_shmctl             (__NR_Linux + 195)
+
+#define __NR_getpmsg		(__NR_Linux + 196) /* Somebody *wants* streams? */
+#define __NR_putpmsg		(__NR_Linux + 197)
+
+#define __NR_lstat64            (__NR_Linux + 198)
+#define __NR_truncate64         (__NR_Linux + 199)
+#define __NR_ftruncate64        (__NR_Linux + 200)
+#define __NR_getdents64         (__NR_Linux + 201)
+#define __NR_fcntl64            (__NR_Linux + 202)
+#define __NR_attrctl            (__NR_Linux + 203)
+#define __NR_acl_get            (__NR_Linux + 204)
+#define __NR_acl_set            (__NR_Linux + 205)
+#define __NR_gettid             (__NR_Linux + 206)
+#define __NR_readahead          (__NR_Linux + 207)
+#define __NR_tkill              (__NR_Linux + 208)
+#define __NR_sendfile64         (__NR_Linux + 209)
+#define __NR_futex              (__NR_Linux + 210)
+#define __NR_sched_setaffinity  (__NR_Linux + 211)
+#define __NR_sched_getaffinity  (__NR_Linux + 212)
+#define __NR_set_thread_area    (__NR_Linux + 213)
+#define __NR_get_thread_area    (__NR_Linux + 214)
+#define __NR_io_setup           (__NR_Linux + 215)
+#define __NR_io_destroy         (__NR_Linux + 216)
+#define __NR_io_getevents       (__NR_Linux + 217)
+#define __NR_io_submit          (__NR_Linux + 218)
+#define __NR_io_cancel          (__NR_Linux + 219)
+#define __NR_alloc_hugepages    (__NR_Linux + 220)
+#define __NR_free_hugepages     (__NR_Linux + 221)
+#define __NR_exit_group         (__NR_Linux + 222)
+#define __NR_lookup_dcookie     (__NR_Linux + 223)
+#define __NR_epoll_create       (__NR_Linux + 224)
+#define __NR_epoll_ctl          (__NR_Linux + 225)
+#define __NR_epoll_wait         (__NR_Linux + 226)
+#define __NR_remap_file_pages   (__NR_Linux + 227)
+#define __NR_semtimedop         (__NR_Linux + 228)
+#define __NR_mq_open            (__NR_Linux + 229)
+#define __NR_mq_unlink          (__NR_Linux + 230)
+#define __NR_mq_timedsend       (__NR_Linux + 231)
+#define __NR_mq_timedreceive    (__NR_Linux + 232)
+#define __NR_mq_notify          (__NR_Linux + 233)
+#define __NR_mq_getsetattr      (__NR_Linux + 234)
+#define __NR_waitid		(__NR_Linux + 235)
+#define __NR_fadvise64_64	(__NR_Linux + 236)
+#define __NR_set_tid_address	(__NR_Linux + 237)
+#define __NR_setxattr		(__NR_Linux + 238)
+#define __NR_lsetxattr		(__NR_Linux + 239)
+#define __NR_fsetxattr		(__NR_Linux + 240)
+#define __NR_getxattr		(__NR_Linux + 241)
+#define __NR_lgetxattr		(__NR_Linux + 242)
+#define __NR_fgetxattr		(__NR_Linux + 243)
+#define __NR_listxattr		(__NR_Linux + 244)
+#define __NR_llistxattr		(__NR_Linux + 245)
+#define __NR_flistxattr		(__NR_Linux + 246)
+#define __NR_removexattr	(__NR_Linux + 247)
+#define __NR_lremovexattr	(__NR_Linux + 248)
+#define __NR_fremovexattr	(__NR_Linux + 249)
+#define __NR_timer_create	(__NR_Linux + 250)
+#define __NR_timer_settime	(__NR_Linux + 251)
+#define __NR_timer_gettime	(__NR_Linux + 252)
+#define __NR_timer_getoverrun	(__NR_Linux + 253)
+#define __NR_timer_delete	(__NR_Linux + 254)
+#define __NR_clock_settime	(__NR_Linux + 255)
+#define __NR_clock_gettime	(__NR_Linux + 256)
+#define __NR_clock_getres	(__NR_Linux + 257)
+#define __NR_clock_nanosleep	(__NR_Linux + 258)
+#define __NR_tgkill		(__NR_Linux + 259)
+#define __NR_mbind		(__NR_Linux + 260)
+#define __NR_get_mempolicy	(__NR_Linux + 261)
+#define __NR_set_mempolicy	(__NR_Linux + 262)
+#define __NR_vserver		(__NR_Linux + 263)
+#define __NR_add_key		(__NR_Linux + 264)
+#define __NR_request_key	(__NR_Linux + 265)
+#define __NR_keyctl		(__NR_Linux + 266)
+#define __NR_ioprio_set		(__NR_Linux + 267)
+#define __NR_ioprio_get		(__NR_Linux + 268)
+#define __NR_inotify_init	(__NR_Linux + 269)
+#define __NR_inotify_add_watch	(__NR_Linux + 270)
+#define __NR_inotify_rm_watch	(__NR_Linux + 271)
+#define __NR_migrate_pages	(__NR_Linux + 272)
+#define __NR_pselect6		(__NR_Linux + 273)
+#define __NR_ppoll		(__NR_Linux + 274)
+#define __NR_openat		(__NR_Linux + 275)
+#define __NR_mkdirat		(__NR_Linux + 276)
+#define __NR_mknodat		(__NR_Linux + 277)
+#define __NR_fchownat		(__NR_Linux + 278)
+#define __NR_futimesat		(__NR_Linux + 279)
+#define __NR_fstatat64		(__NR_Linux + 280)
+#define __NR_unlinkat		(__NR_Linux + 281)
+#define __NR_renameat		(__NR_Linux + 282)
+#define __NR_linkat		(__NR_Linux + 283)
+#define __NR_symlinkat		(__NR_Linux + 284)
+#define __NR_readlinkat		(__NR_Linux + 285)
+#define __NR_fchmodat		(__NR_Linux + 286)
+#define __NR_faccessat		(__NR_Linux + 287)
+#define __NR_unshare		(__NR_Linux + 288)
+#define __NR_set_robust_list	(__NR_Linux + 289)
+#define __NR_get_robust_list	(__NR_Linux + 290)
+#define __NR_splice		(__NR_Linux + 291)
+#define __NR_sync_file_range	(__NR_Linux + 292)
+#define __NR_tee		(__NR_Linux + 293)
+#define __NR_vmsplice		(__NR_Linux + 294)
+#define __NR_move_pages		(__NR_Linux + 295)
+#define __NR_getcpu		(__NR_Linux + 296)
+#define __NR_epoll_pwait	(__NR_Linux + 297)
+#define __NR_statfs64		(__NR_Linux + 298)
+#define __NR_fstatfs64		(__NR_Linux + 299)
+#define __NR_kexec_load		(__NR_Linux + 300)
+#define __NR_utimensat		(__NR_Linux + 301)
+#define __NR_signalfd		(__NR_Linux + 302)
+#define __NR_timerfd		(__NR_Linux + 303)
+#define __NR_eventfd		(__NR_Linux + 304)
+#define __NR_fallocate		(__NR_Linux + 305)
+#define __NR_timerfd_create	(__NR_Linux + 306)
+#define __NR_timerfd_settime	(__NR_Linux + 307)
+#define __NR_timerfd_gettime	(__NR_Linux + 308)
+
+#define __NR_Linux_syscalls	(__NR_timerfd_gettime + 1)
+
+
+#define __IGNORE_select		/* newselect */
+#define __IGNORE_fadvise64	/* fadvise64_64 */
+#define __IGNORE_utimes		/* utime */
+
+
+#define HPUX_GATEWAY_ADDR       0xC0000004
+#define LINUX_GATEWAY_ADDR      0x100
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+#define SYS_ify(syscall_name)   __NR_##syscall_name
+
+#ifndef ASM_LINE_SEP
+# define ASM_LINE_SEP ;
+#endif
+
+/* Definition taken from glibc 2.3.3
+ * sysdeps/unix/sysv/linux/hppa/sysdep.h
+ */
+
+#ifdef PIC
+/* WARNING: CANNOT BE USED IN A NOP! */
+# define K_STW_ASM_PIC	"       copy %%r19, %%r4\n"
+# define K_LDW_ASM_PIC	"       copy %%r4, %%r19\n"
+# define K_USING_GR4	"%r4",
+#else
+# define K_STW_ASM_PIC	" \n"
+# define K_LDW_ASM_PIC	" \n"
+# define K_USING_GR4
+#endif
+
+/* GCC has to be warned that a syscall may clobber all the ABI
+   registers listed as "caller-saves", see page 8, Table 2
+   in section 2.2.6 of the PA-RISC RUN-TIME architecture
+   document. However! r28 is the result and will conflict with
+   the clobber list so it is left out. Also the input arguments
+   registers r20 -> r26 will conflict with the list so they
+   are treated specially. Although r19 is clobbered by the syscall
+   we cannot say this because it would violate ABI, thus we say
+   r4 is clobbered and use that register to save/restore r19
+   across the syscall. */
+
+#define K_CALL_CLOB_REGS "%r1", "%r2", K_USING_GR4 \
+	        	 "%r20", "%r29", "%r31"
+
+#undef K_INLINE_SYSCALL
+#define K_INLINE_SYSCALL(name, nr, args...)	({			\
+	long __sys_res;							\
+	{								\
+		register unsigned long __res __asm__("r28");		\
+		K_LOAD_ARGS_##nr(args)					\
+		/* FIXME: HACK stw/ldw r19 around syscall */		\
+		__asm__ volatile(					\
+			K_STW_ASM_PIC					\
+			"	ble  0x100(%%sr2, %%r0)\n"		\
+			"	ldi %1, %%r20\n"			\
+			K_LDW_ASM_PIC					\
+			: "=r" (__res)					\
+			: "i" (SYS_ify(name)) K_ASM_ARGS_##nr   	\
+			: "memory", K_CALL_CLOB_REGS K_CLOB_ARGS_##nr	\
+		);							\
+		__sys_res = (long)__res;				\
+	}								\
+	if ( (unsigned long)__sys_res >= (unsigned long)-4095 ){	\
+		errno = -__sys_res;		        		\
+		__sys_res = -1;						\
+	}								\
+	__sys_res;							\
+})
+
+#define K_LOAD_ARGS_0()
+#define K_LOAD_ARGS_1(r26)					\
+	register unsigned long __r26 __asm__("r26") = (unsigned long)(r26);   \
+	K_LOAD_ARGS_0()
+#define K_LOAD_ARGS_2(r26,r25)					\
+	register unsigned long __r25 __asm__("r25") = (unsigned long)(r25);   \
+	K_LOAD_ARGS_1(r26)
+#define K_LOAD_ARGS_3(r26,r25,r24)				\
+	register unsigned long __r24 __asm__("r24") = (unsigned long)(r24);   \
+	K_LOAD_ARGS_2(r26,r25)
+#define K_LOAD_ARGS_4(r26,r25,r24,r23)				\
+	register unsigned long __r23 __asm__("r23") = (unsigned long)(r23);   \
+	K_LOAD_ARGS_3(r26,r25,r24)
+#define K_LOAD_ARGS_5(r26,r25,r24,r23,r22)			\
+	register unsigned long __r22 __asm__("r22") = (unsigned long)(r22);   \
+	K_LOAD_ARGS_4(r26,r25,r24,r23)
+#define K_LOAD_ARGS_6(r26,r25,r24,r23,r22,r21)			\
+	register unsigned long __r21 __asm__("r21") = (unsigned long)(r21);   \
+	K_LOAD_ARGS_5(r26,r25,r24,r23,r22)
+
+/* Even with zero args we use r20 for the syscall number */
+#define K_ASM_ARGS_0
+#define K_ASM_ARGS_1 K_ASM_ARGS_0, "r" (__r26)
+#define K_ASM_ARGS_2 K_ASM_ARGS_1, "r" (__r25)
+#define K_ASM_ARGS_3 K_ASM_ARGS_2, "r" (__r24)
+#define K_ASM_ARGS_4 K_ASM_ARGS_3, "r" (__r23)
+#define K_ASM_ARGS_5 K_ASM_ARGS_4, "r" (__r22)
+#define K_ASM_ARGS_6 K_ASM_ARGS_5, "r" (__r21)
+
+/* The registers not listed as inputs but clobbered */
+#define K_CLOB_ARGS_6
+#define K_CLOB_ARGS_5 K_CLOB_ARGS_6, "%r21"
+#define K_CLOB_ARGS_4 K_CLOB_ARGS_5, "%r22"
+#define K_CLOB_ARGS_3 K_CLOB_ARGS_4, "%r23"
+#define K_CLOB_ARGS_2 K_CLOB_ARGS_3, "%r24"
+#define K_CLOB_ARGS_1 K_CLOB_ARGS_2, "%r25"
+#define K_CLOB_ARGS_0 K_CLOB_ARGS_1, "%r26"
+
+#define _syscall0(type,name)						\
+type name(void)								\
+{									\
+    return K_INLINE_SYSCALL(name, 0);	                                \
+}
+
+#define _syscall1(type,name,type1,arg1)					\
+type name(type1 arg1)							\
+{									\
+    return K_INLINE_SYSCALL(name, 1, arg1);	                        \
+}
+
+#define _syscall2(type,name,type1,arg1,type2,arg2)			\
+type name(type1 arg1, type2 arg2)					\
+{									\
+    return K_INLINE_SYSCALL(name, 2, arg1, arg2);	                \
+}
+
+#define _syscall3(type,name,type1,arg1,type2,arg2,type3,arg3)		\
+type name(type1 arg1, type2 arg2, type3 arg3)				\
+{									\
+    return K_INLINE_SYSCALL(name, 3, arg1, arg2, arg3);	                \
+}
+
+#define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \
+type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4)		\
+{									\
+    return K_INLINE_SYSCALL(name, 4, arg1, arg2, arg3, arg4);	        \
+}
+
+/* select takes 5 arguments */
+#define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4,type5,arg5) \
+type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5)	\
+{									\
+    return K_INLINE_SYSCALL(name, 5, arg1, arg2, arg3, arg4, arg5);	\
+}
+
+#define __ARCH_WANT_OLD_READDIR
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SYS_ALARM
+#define __ARCH_WANT_SYS_GETHOSTNAME
+#define __ARCH_WANT_SYS_PAUSE
+#define __ARCH_WANT_SYS_SGETMASK
+#define __ARCH_WANT_SYS_SIGNAL
+#define __ARCH_WANT_SYS_TIME
+#define __ARCH_WANT_COMPAT_SYS_TIME
+#define __ARCH_WANT_SYS_UTIME
+#define __ARCH_WANT_SYS_WAITPID
+#define __ARCH_WANT_SYS_SOCKETCALL
+#define __ARCH_WANT_SYS_FADVISE64
+#define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
+#define __ARCH_WANT_SYS_NICE
+#define __ARCH_WANT_SYS_OLD_GETRLIMIT
+#define __ARCH_WANT_SYS_OLDUMOUNT
+#define __ARCH_WANT_SYS_SIGPENDING
+#define __ARCH_WANT_SYS_SIGPROCMASK
+#define __ARCH_WANT_SYS_RT_SIGACTION
+#define __ARCH_WANT_SYS_RT_SIGSUSPEND
+#define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
+
+#endif /* __ASSEMBLY__ */
+
+#undef STR
+
+/*
+ * "Conditional" syscalls
+ *
+ * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
+ * but it doesn't work on all toolchains, so we just do it by hand
+ */
+#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_PARISC_UNISTD_H_ */
diff --git a/arch/parisc/include/asm/unwind.h b/arch/parisc/include/asm/unwind.h
new file mode 100644
index 000000000000..2f7e6e50a158
--- /dev/null
+++ b/arch/parisc/include/asm/unwind.h
@@ -0,0 +1,77 @@
+#ifndef _UNWIND_H_
+#define _UNWIND_H_
+
+#include <linux/list.h>
+
+/* From ABI specifications */
+struct unwind_table_entry {
+	unsigned int region_start;
+	unsigned int region_end;
+	unsigned int Cannot_unwind:1; /* 0 */
+	unsigned int Millicode:1;	/* 1 */
+	unsigned int Millicode_save_sr0:1;	/* 2 */
+	unsigned int Region_description:2;	/* 3..4 */
+	unsigned int reserved1:1;	/* 5 */
+	unsigned int Entry_SR:1;	/* 6 */
+	unsigned int Entry_FR:4;	/* number saved *//* 7..10 */
+	unsigned int Entry_GR:5;	/* number saved *//* 11..15 */
+	unsigned int Args_stored:1;	/* 16 */
+	unsigned int Variable_Frame:1;	/* 17 */
+	unsigned int Separate_Package_Body:1;	/* 18 */
+	unsigned int Frame_Extension_Millicode:1;	/* 19 */
+	unsigned int Stack_Overflow_Check:1;	/* 20 */
+	unsigned int Two_Instruction_SP_Increment:1;	/* 21 */
+	unsigned int Ada_Region:1;	/* 22 */
+	unsigned int cxx_info:1;	/* 23 */
+	unsigned int cxx_try_catch:1;	/* 24 */
+	unsigned int sched_entry_seq:1;	/* 25 */
+	unsigned int reserved2:1;	/* 26 */
+	unsigned int Save_SP:1;	/* 27 */
+	unsigned int Save_RP:1;	/* 28 */
+	unsigned int Save_MRP_in_frame:1;	/* 29 */
+	unsigned int extn_ptr_defined:1;	/* 30 */
+	unsigned int Cleanup_defined:1;	/* 31 */
+	
+	unsigned int MPE_XL_interrupt_marker:1;	/* 0 */
+	unsigned int HP_UX_interrupt_marker:1;	/* 1 */
+	unsigned int Large_frame:1;	/* 2 */
+	unsigned int Pseudo_SP_Set:1;	/* 3 */
+	unsigned int reserved4:1;	/* 4 */
+	unsigned int Total_frame_size:27;	/* 5..31 */
+};
+
+struct unwind_table {
+	struct list_head list;
+	const char *name;
+	unsigned long gp;
+	unsigned long base_addr;
+	unsigned long start;
+	unsigned long end;
+	const struct unwind_table_entry *table;
+	unsigned long length;
+};
+
+struct unwind_frame_info {
+	struct task_struct *t;
+	/* Eventually we would like to be able to get at any of the registers
+	   available; but for now we only try to get the sp and ip for each
+	   frame */
+	/* struct pt_regs regs; */
+	unsigned long sp, ip, rp, r31;
+	unsigned long prev_sp, prev_ip;
+};
+
+struct unwind_table *
+unwind_table_add(const char *name, unsigned long base_addr, 
+		 unsigned long gp, void *start, void *end);
+void
+unwind_table_remove(struct unwind_table *table);
+
+void unwind_frame_init(struct unwind_frame_info *info, struct task_struct *t, 
+		       struct pt_regs *regs);
+void unwind_frame_init_from_blocked_task(struct unwind_frame_info *info, struct task_struct *t);
+void unwind_frame_init_running(struct unwind_frame_info *info, struct pt_regs *regs);
+int unwind_once(struct unwind_frame_info *info);
+int unwind_to_user(struct unwind_frame_info *info);
+
+#endif
diff --git a/arch/parisc/include/asm/user.h b/arch/parisc/include/asm/user.h
new file mode 100644
index 000000000000..80224753e508
--- /dev/null
+++ b/arch/parisc/include/asm/user.h
@@ -0,0 +1,5 @@
+/* This file should not exist, but lots of generic code still includes
+   it. It's a hangover from old a.out days and the traditional core
+   dump format.  We are ELF-only, and so are our core dumps.  If we
+   need to support HP/UX core format then we'll do it here
+   eventually. */
diff --git a/arch/parisc/include/asm/vga.h b/arch/parisc/include/asm/vga.h
new file mode 100644
index 000000000000..171399a88ca6
--- /dev/null
+++ b/arch/parisc/include/asm/vga.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_PARISC_VGA_H__
+#define __ASM_PARISC_VGA_H__
+
+/* nothing */
+
+#endif /* __ASM_PARISC_VGA_H__ */
diff --git a/arch/parisc/include/asm/xor.h b/arch/parisc/include/asm/xor.h
new file mode 100644
index 000000000000..c82eb12a5b18
--- /dev/null
+++ b/arch/parisc/include/asm/xor.h
@@ -0,0 +1 @@
+#include <asm-generic/xor.h>
diff --git a/include/asm-parisc/Kbuild b/include/asm-parisc/Kbuild
deleted file mode 100644
index f88b252e419c..000000000000
--- a/include/asm-parisc/Kbuild
+++ /dev/null
@@ -1,3 +0,0 @@
-include include/asm-generic/Kbuild.asm
-
-unifdef-y += pdc.h
diff --git a/include/asm-parisc/a.out.h b/include/asm-parisc/a.out.h
deleted file mode 100644
index eb04e34c5bb1..000000000000
--- a/include/asm-parisc/a.out.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef __PARISC_A_OUT_H__
-#define __PARISC_A_OUT_H__
-
-struct exec
-{
-  unsigned int a_info;		/* Use macros N_MAGIC, etc for access */
-  unsigned a_text;		/* length of text, in bytes */
-  unsigned a_data;		/* length of data, in bytes */
-  unsigned a_bss;		/* length of uninitialized data area for file, in bytes */
-  unsigned a_syms;		/* length of symbol table data in file, in bytes */
-  unsigned a_entry;		/* start address */
-  unsigned a_trsize;		/* length of relocation info for text, in bytes */
-  unsigned a_drsize;		/* length of relocation info for data, in bytes */
-};
-
-#define N_TRSIZE(a)	((a).a_trsize)
-#define N_DRSIZE(a)	((a).a_drsize)
-#define N_SYMSIZE(a)	((a).a_syms)
-
-#endif /* __A_OUT_GNU_H__ */
diff --git a/include/asm-parisc/agp.h b/include/asm-parisc/agp.h
deleted file mode 100644
index 9651660da639..000000000000
--- a/include/asm-parisc/agp.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef _ASM_PARISC_AGP_H
-#define _ASM_PARISC_AGP_H
-
-/*
- * PARISC specific AGP definitions.
- * Copyright (c) 2006 Kyle McMartin <kyle@parisc-linux.org>
- *
- */
-
-#define map_page_into_agp(page)		/* nothing */
-#define unmap_page_from_agp(page)	/* nothing */
-#define flush_agp_cache()		mb()
-
-/* Convert a physical address to an address suitable for the GART. */
-#define phys_to_gart(x) (x)
-#define gart_to_phys(x) (x)
-
-/* GATT allocation. Returns/accepts GATT kernel virtual address. */
-#define alloc_gatt_pages(order)		\
-	((char *)__get_free_pages(GFP_KERNEL, (order)))
-#define free_gatt_pages(table, order)	\
-	free_pages((unsigned long)(table), (order))
-
-#endif /* _ASM_PARISC_AGP_H */
diff --git a/include/asm-parisc/asmregs.h b/include/asm-parisc/asmregs.h
deleted file mode 100644
index d93c646e1887..000000000000
--- a/include/asm-parisc/asmregs.h
+++ /dev/null
@@ -1,183 +0,0 @@
-/*
- * Copyright (C) 1999 Hewlett-Packard (Frank Rowand)
- *
- *	This program is free software; you can redistribute it and/or modify
- *	it under the terms of the GNU General Public License as published by
- *	the Free Software Foundation; either version 2, or (at your option)
- *	any later version.
- *
- *	This program is distributed in the hope that it will be useful,
- *	but WITHOUT ANY WARRANTY; without even the implied warranty of
- *	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *	GNU General Public License for more details.
- *
- *	You should have received a copy of the GNU General Public License
- *	along with this program; if not, write to the Free Software
- *	Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#ifndef _PARISC_ASMREGS_H
-#define _PARISC_ASMREGS_H
-
-;! General Registers
-
-rp:	.reg	%r2
-arg3:	.reg	%r23
-arg2:	.reg	%r24
-arg1:	.reg	%r25
-arg0:	.reg	%r26
-dp:	.reg	%r27
-ret0:	.reg	%r28
-ret1:	.reg	%r29
-sl:	.reg	%r29
-sp:	.reg	%r30
-
-#if 0
-/* PA20_REVISIT */
-arg7:	.reg	r19
-arg6:	.reg	r20
-arg5:	.reg	r21
-arg4:	.reg	r22
-gp:	.reg	r27
-ap:	.reg	r29
-#endif
-
-
-r0:	.reg	%r0
-r1:	.reg	%r1
-r2:	.reg	%r2
-r3:	.reg	%r3
-r4:	.reg	%r4
-r5:	.reg	%r5
-r6:	.reg	%r6
-r7:	.reg	%r7
-r8:	.reg	%r8
-r9:	.reg	%r9
-r10:	.reg	%r10
-r11:	.reg	%r11
-r12:	.reg	%r12
-r13:	.reg	%r13
-r14:	.reg	%r14
-r15:	.reg	%r15
-r16:	.reg	%r16
-r17:	.reg	%r17
-r18:	.reg	%r18
-r19:	.reg	%r19
-r20:	.reg	%r20
-r21:	.reg	%r21
-r22:	.reg	%r22
-r23:	.reg	%r23
-r24:	.reg	%r24
-r25:	.reg	%r25
-r26:	.reg	%r26
-r27:	.reg	%r27
-r28:	.reg	%r28
-r29:	.reg	%r29
-r30:	.reg	%r30
-r31:	.reg	%r31
-
-
-;! Space Registers
-
-sr0:	.reg	%sr0
-sr1:	.reg	%sr1
-sr2:	.reg	%sr2
-sr3:	.reg	%sr3
-sr4:	.reg	%sr4
-sr5:	.reg	%sr5
-sr6:	.reg	%sr6
-sr7:	.reg	%sr7
-
-
-;! Floating Point Registers
-
-fr0:	.reg	%fr0
-fr1:	.reg	%fr1
-fr2:	.reg	%fr2
-fr3:	.reg	%fr3
-fr4:	.reg	%fr4
-fr5:	.reg	%fr5
-fr6:	.reg	%fr6
-fr7:	.reg	%fr7
-fr8:	.reg	%fr8
-fr9:	.reg	%fr9
-fr10:	.reg	%fr10
-fr11:	.reg	%fr11
-fr12:	.reg	%fr12
-fr13:	.reg	%fr13
-fr14:	.reg	%fr14
-fr15:	.reg	%fr15
-fr16:	.reg	%fr16
-fr17:	.reg	%fr17
-fr18:	.reg	%fr18
-fr19:	.reg	%fr19
-fr20:	.reg	%fr20
-fr21:	.reg	%fr21
-fr22:	.reg	%fr22
-fr23:	.reg	%fr23
-fr24:	.reg	%fr24
-fr25:	.reg	%fr25
-fr26:	.reg	%fr26
-fr27:	.reg	%fr27
-fr28:	.reg	%fr28
-fr29:	.reg	%fr29
-fr30:	.reg	%fr30
-fr31:	.reg	%fr31
-
-
-;! Control Registers
-
-rctr:	.reg	%cr0
-pidr1:	.reg	%cr8
-pidr2:	.reg	%cr9
-ccr:	.reg	%cr10
-sar:	.reg	%cr11
-pidr3:	.reg	%cr12
-pidr4:	.reg	%cr13
-iva:	.reg	%cr14
-eiem:	.reg	%cr15
-itmr:	.reg	%cr16
-pcsq:	.reg	%cr17
-pcoq:	.reg	%cr18
-iir:	.reg	%cr19
-isr:	.reg	%cr20
-ior:	.reg	%cr21
-ipsw:	.reg	%cr22
-eirr:	.reg	%cr23
-tr0:	.reg	%cr24
-tr1:	.reg	%cr25
-tr2:	.reg	%cr26
-tr3:	.reg	%cr27
-tr4:	.reg	%cr28
-tr5:	.reg	%cr29
-tr6:	.reg	%cr30
-tr7:	.reg	%cr31
-
-
-cr0:	.reg	%cr0
-cr8:	.reg	%cr8
-cr9:	.reg	%cr9
-cr10:	.reg	%cr10
-cr11:	.reg	%cr11
-cr12:	.reg	%cr12
-cr13:	.reg	%cr13
-cr14:	.reg	%cr14
-cr15:	.reg	%cr15
-cr16:	.reg	%cr16
-cr17:	.reg	%cr17
-cr18:	.reg	%cr18
-cr19:	.reg	%cr19
-cr20:	.reg	%cr20
-cr21:	.reg	%cr21
-cr22:	.reg	%cr22
-cr23:	.reg	%cr23
-cr24:	.reg	%cr24
-cr25:	.reg	%cr25
-cr26:	.reg	%cr26
-cr27:	.reg	%cr27
-cr28:	.reg	%cr28
-cr29:	.reg	%cr29
-cr30:	.reg	%cr30
-cr31:	.reg	%cr31
-
-#endif
diff --git a/include/asm-parisc/assembly.h b/include/asm-parisc/assembly.h
deleted file mode 100644
index ffb208840ecc..000000000000
--- a/include/asm-parisc/assembly.h
+++ /dev/null
@@ -1,519 +0,0 @@
-/*
- * Copyright (C) 1999 Hewlett-Packard (Frank Rowand)
- * Copyright (C) 1999 Philipp Rumpf <prumpf@tux.org>
- * Copyright (C) 1999 SuSE GmbH
- *
- *    This program is free software; you can redistribute it and/or modify
- *    it under the terms of the GNU General Public License as published by
- *    the Free Software Foundation; either version 2, or (at your option)
- *    any later version.
- *
- *    This program is distributed in the hope that it will be useful,
- *    but WITHOUT ANY WARRANTY; without even the implied warranty of
- *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *    GNU General Public License for more details.
- *
- *    You should have received a copy of the GNU General Public License
- *    along with this program; if not, write to the Free Software
- *    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#ifndef _PARISC_ASSEMBLY_H
-#define _PARISC_ASSEMBLY_H
-
-#define CALLEE_FLOAT_FRAME_SIZE	80
-
-#ifdef CONFIG_64BIT
-#define LDREG	ldd
-#define STREG	std
-#define LDREGX  ldd,s
-#define LDREGM	ldd,mb
-#define STREGM	std,ma
-#define SHRREG	shrd
-#define SHLREG	shld
-#define ANDCM   andcm,*
-#define	COND(x)	* ## x
-#define RP_OFFSET	16
-#define FRAME_SIZE	128
-#define CALLEE_REG_FRAME_SIZE	144
-#define ASM_ULONG_INSN	.dword
-#else	/* CONFIG_64BIT */
-#define LDREG	ldw
-#define STREG	stw
-#define LDREGX  ldwx,s
-#define LDREGM	ldwm
-#define STREGM	stwm
-#define SHRREG	shr
-#define SHLREG	shlw
-#define ANDCM   andcm
-#define COND(x)	x
-#define RP_OFFSET	20
-#define FRAME_SIZE	64
-#define CALLEE_REG_FRAME_SIZE	128
-#define ASM_ULONG_INSN	.word
-#endif
-
-#define CALLEE_SAVE_FRAME_SIZE (CALLEE_REG_FRAME_SIZE + CALLEE_FLOAT_FRAME_SIZE)
-
-#ifdef CONFIG_PA20
-#define LDCW		ldcw,co
-#define BL		b,l
-# ifdef CONFIG_64BIT
-#  define LEVEL		2.0w
-# else
-#  define LEVEL		2.0
-# endif
-#else
-#define LDCW		ldcw
-#define BL		bl
-#define LEVEL		1.1
-#endif
-
-#ifdef __ASSEMBLY__
-
-#ifdef CONFIG_64BIT
-/* the 64-bit pa gnu assembler unfortunately defaults to .level 1.1 or 2.0 so
- * work around that for now... */
-	.level 2.0w
-#endif
-
-#include <asm/asm-offsets.h>
-#include <asm/page.h>
-
-#include <asm/asmregs.h>
-
-	sp	=	30
-	gp	=	27
-	ipsw	=	22
-
-	/*
-	 * We provide two versions of each macro to convert from physical
-	 * to virtual and vice versa. The "_r1" versions take one argument
-	 * register, but trashes r1 to do the conversion. The other
-	 * version takes two arguments: a src and destination register.
-	 * However, the source and destination registers can not be
-	 * the same register.
-	 */
-
-	.macro  tophys  grvirt, grphys
-	ldil    L%(__PAGE_OFFSET), \grphys
-	sub     \grvirt, \grphys, \grphys
-	.endm
-	
-	.macro  tovirt  grphys, grvirt
-	ldil    L%(__PAGE_OFFSET), \grvirt
-	add     \grphys, \grvirt, \grvirt
-	.endm
-
-	.macro  tophys_r1  gr
-	ldil    L%(__PAGE_OFFSET), %r1
-	sub     \gr, %r1, \gr
-	.endm
-	
-	.macro  tovirt_r1  gr
-	ldil    L%(__PAGE_OFFSET), %r1
-	add     \gr, %r1, \gr
-	.endm
-
-	.macro delay value
-	ldil	L%\value, 1
-	ldo	R%\value(1), 1
-	addib,UV,n -1,1,.
-	addib,NUV,n -1,1,.+8
-	nop
-	.endm
-
-	.macro	debug value
-	.endm
-
-
-	/* Shift Left - note the r and t can NOT be the same! */
-	.macro shl r, sa, t
-	dep,z	\r, 31-\sa, 32-\sa, \t
-	.endm
-
-	/* The PA 2.0 shift left */
-	.macro shlw r, sa, t
-	depw,z	\r, 31-\sa, 32-\sa, \t
-	.endm
-
-	/* And the PA 2.0W shift left */
-	.macro shld r, sa, t
-	depd,z	\r, 63-\sa, 64-\sa, \t
-	.endm
-
-	/* Shift Right - note the r and t can NOT be the same! */
-	.macro shr r, sa, t
-	extru \r, 31-\sa, 32-\sa, \t
-	.endm
-
-	/* pa20w version of shift right */
-	.macro shrd r, sa, t
-	extrd,u \r, 63-\sa, 64-\sa, \t
-	.endm
-
-	/* load 32-bit 'value' into 'reg' compensating for the ldil
-	 * sign-extension when running in wide mode.
-	 * WARNING!! neither 'value' nor 'reg' can be expressions
-	 * containing '.'!!!! */
-	.macro	load32 value, reg
-	ldil	L%\value, \reg
-	ldo	R%\value(\reg), \reg
-	.endm
-
-	.macro loadgp
-#ifdef CONFIG_64BIT
-	ldil		L%__gp, %r27
-	ldo		R%__gp(%r27), %r27
-#else
-	ldil		L%$global$, %r27
-	ldo		R%$global$(%r27), %r27
-#endif
-	.endm
-
-#define SAVE_SP(r, where) mfsp r, %r1 ! STREG %r1, where
-#define REST_SP(r, where) LDREG where, %r1 ! mtsp %r1, r
-#define SAVE_CR(r, where) mfctl r, %r1 ! STREG %r1, where
-#define REST_CR(r, where) LDREG where, %r1 ! mtctl %r1, r
-
-	.macro	save_general	regs
-	STREG %r1, PT_GR1 (\regs)
-	STREG %r2, PT_GR2 (\regs)
-	STREG %r3, PT_GR3 (\regs)
-	STREG %r4, PT_GR4 (\regs)
-	STREG %r5, PT_GR5 (\regs)
-	STREG %r6, PT_GR6 (\regs)
-	STREG %r7, PT_GR7 (\regs)
-	STREG %r8, PT_GR8 (\regs)
-	STREG %r9, PT_GR9 (\regs)
-	STREG %r10, PT_GR10(\regs)
-	STREG %r11, PT_GR11(\regs)
-	STREG %r12, PT_GR12(\regs)
-	STREG %r13, PT_GR13(\regs)
-	STREG %r14, PT_GR14(\regs)
-	STREG %r15, PT_GR15(\regs)
-	STREG %r16, PT_GR16(\regs)
-	STREG %r17, PT_GR17(\regs)
-	STREG %r18, PT_GR18(\regs)
-	STREG %r19, PT_GR19(\regs)
-	STREG %r20, PT_GR20(\regs)
-	STREG %r21, PT_GR21(\regs)
-	STREG %r22, PT_GR22(\regs)
-	STREG %r23, PT_GR23(\regs)
-	STREG %r24, PT_GR24(\regs)
-	STREG %r25, PT_GR25(\regs)
-	/* r26 is saved in get_stack and used to preserve a value across virt_map */
-	STREG %r27, PT_GR27(\regs)
-	STREG %r28, PT_GR28(\regs)
-	/* r29 is saved in get_stack and used to point to saved registers */
-	/* r30 stack pointer saved in get_stack */
-	STREG %r31, PT_GR31(\regs)
-	.endm
-
-	.macro	rest_general	regs
-	/* r1 used as a temp in rest_stack and is restored there */
-	LDREG PT_GR2 (\regs), %r2
-	LDREG PT_GR3 (\regs), %r3
-	LDREG PT_GR4 (\regs), %r4
-	LDREG PT_GR5 (\regs), %r5
-	LDREG PT_GR6 (\regs), %r6
-	LDREG PT_GR7 (\regs), %r7
-	LDREG PT_GR8 (\regs), %r8
-	LDREG PT_GR9 (\regs), %r9
-	LDREG PT_GR10(\regs), %r10
-	LDREG PT_GR11(\regs), %r11
-	LDREG PT_GR12(\regs), %r12
-	LDREG PT_GR13(\regs), %r13
-	LDREG PT_GR14(\regs), %r14
-	LDREG PT_GR15(\regs), %r15
-	LDREG PT_GR16(\regs), %r16
-	LDREG PT_GR17(\regs), %r17
-	LDREG PT_GR18(\regs), %r18
-	LDREG PT_GR19(\regs), %r19
-	LDREG PT_GR20(\regs), %r20
-	LDREG PT_GR21(\regs), %r21
-	LDREG PT_GR22(\regs), %r22
-	LDREG PT_GR23(\regs), %r23
-	LDREG PT_GR24(\regs), %r24
-	LDREG PT_GR25(\regs), %r25
-	LDREG PT_GR26(\regs), %r26
-	LDREG PT_GR27(\regs), %r27
-	LDREG PT_GR28(\regs), %r28
-	/* r29 points to register save area, and is restored in rest_stack */
-	/* r30 stack pointer restored in rest_stack */
-	LDREG PT_GR31(\regs), %r31
-	.endm
-
-	.macro	save_fp 	regs
-	fstd,ma  %fr0, 8(\regs)
-	fstd,ma	 %fr1, 8(\regs)
-	fstd,ma	 %fr2, 8(\regs)
-	fstd,ma	 %fr3, 8(\regs)
-	fstd,ma	 %fr4, 8(\regs)
-	fstd,ma	 %fr5, 8(\regs)
-	fstd,ma	 %fr6, 8(\regs)
-	fstd,ma	 %fr7, 8(\regs)
-	fstd,ma	 %fr8, 8(\regs)
-	fstd,ma	 %fr9, 8(\regs)
-	fstd,ma	%fr10, 8(\regs)
-	fstd,ma	%fr11, 8(\regs)
-	fstd,ma	%fr12, 8(\regs)
-	fstd,ma	%fr13, 8(\regs)
-	fstd,ma	%fr14, 8(\regs)
-	fstd,ma	%fr15, 8(\regs)
-	fstd,ma	%fr16, 8(\regs)
-	fstd,ma	%fr17, 8(\regs)
-	fstd,ma	%fr18, 8(\regs)
-	fstd,ma	%fr19, 8(\regs)
-	fstd,ma	%fr20, 8(\regs)
-	fstd,ma	%fr21, 8(\regs)
-	fstd,ma	%fr22, 8(\regs)
-	fstd,ma	%fr23, 8(\regs)
-	fstd,ma	%fr24, 8(\regs)
-	fstd,ma	%fr25, 8(\regs)
-	fstd,ma	%fr26, 8(\regs)
-	fstd,ma	%fr27, 8(\regs)
-	fstd,ma	%fr28, 8(\regs)
-	fstd,ma	%fr29, 8(\regs)
-	fstd,ma	%fr30, 8(\regs)
-	fstd	%fr31, 0(\regs)
-	.endm
-
-	.macro	rest_fp 	regs
-	fldd	0(\regs),	 %fr31
-	fldd,mb	-8(\regs),       %fr30
-	fldd,mb	-8(\regs),       %fr29
-	fldd,mb	-8(\regs),       %fr28
-	fldd,mb	-8(\regs),       %fr27
-	fldd,mb	-8(\regs),       %fr26
-	fldd,mb	-8(\regs),       %fr25
-	fldd,mb	-8(\regs),       %fr24
-	fldd,mb	-8(\regs),       %fr23
-	fldd,mb	-8(\regs),       %fr22
-	fldd,mb	-8(\regs),       %fr21
-	fldd,mb	-8(\regs),       %fr20
-	fldd,mb	-8(\regs),       %fr19
-	fldd,mb	-8(\regs),       %fr18
-	fldd,mb	-8(\regs),       %fr17
-	fldd,mb	-8(\regs),       %fr16
-	fldd,mb	-8(\regs),       %fr15
-	fldd,mb	-8(\regs),       %fr14
-	fldd,mb	-8(\regs),       %fr13
-	fldd,mb	-8(\regs),       %fr12
-	fldd,mb	-8(\regs),       %fr11
-	fldd,mb	-8(\regs),       %fr10
-	fldd,mb	-8(\regs),       %fr9
-	fldd,mb	-8(\regs),       %fr8
-	fldd,mb	-8(\regs),       %fr7
-	fldd,mb	-8(\regs),       %fr6
-	fldd,mb	-8(\regs),       %fr5
-	fldd,mb	-8(\regs),       %fr4
-	fldd,mb	-8(\regs),       %fr3
-	fldd,mb	-8(\regs),       %fr2
-	fldd,mb	-8(\regs),       %fr1
-	fldd,mb	-8(\regs),       %fr0
-	.endm
-
-	.macro	callee_save_float
-	fstd,ma	 %fr12,	8(%r30)
-	fstd,ma	 %fr13,	8(%r30)
-	fstd,ma	 %fr14,	8(%r30)
-	fstd,ma	 %fr15,	8(%r30)
-	fstd,ma	 %fr16,	8(%r30)
-	fstd,ma	 %fr17,	8(%r30)
-	fstd,ma	 %fr18,	8(%r30)
-	fstd,ma	 %fr19,	8(%r30)
-	fstd,ma	 %fr20,	8(%r30)
-	fstd,ma	 %fr21,	8(%r30)
-	.endm
-
-	.macro	callee_rest_float
-	fldd,mb	-8(%r30),   %fr21
-	fldd,mb	-8(%r30),   %fr20
-	fldd,mb	-8(%r30),   %fr19
-	fldd,mb	-8(%r30),   %fr18
-	fldd,mb	-8(%r30),   %fr17
-	fldd,mb	-8(%r30),   %fr16
-	fldd,mb	-8(%r30),   %fr15
-	fldd,mb	-8(%r30),   %fr14
-	fldd,mb	-8(%r30),   %fr13
-	fldd,mb	-8(%r30),   %fr12
-	.endm
-
-#ifdef CONFIG_64BIT
-	.macro	callee_save
-	std,ma	  %r3,	 CALLEE_REG_FRAME_SIZE(%r30)
-	mfctl	  %cr27, %r3
-	std	  %r4,	-136(%r30)
-	std	  %r5,	-128(%r30)
-	std	  %r6,	-120(%r30)
-	std	  %r7,	-112(%r30)
-	std	  %r8,	-104(%r30)
-	std	  %r9,	 -96(%r30)
-	std	 %r10,	 -88(%r30)
-	std	 %r11,	 -80(%r30)
-	std	 %r12,	 -72(%r30)
-	std	 %r13,	 -64(%r30)
-	std	 %r14,	 -56(%r30)
-	std	 %r15,	 -48(%r30)
-	std	 %r16,	 -40(%r30)
-	std	 %r17,	 -32(%r30)
-	std	 %r18,	 -24(%r30)
-	std	  %r3,	 -16(%r30)
-	.endm
-
-	.macro	callee_rest
-	ldd	 -16(%r30),    %r3
-	ldd	 -24(%r30),   %r18
-	ldd	 -32(%r30),   %r17
-	ldd	 -40(%r30),   %r16
-	ldd	 -48(%r30),   %r15
-	ldd	 -56(%r30),   %r14
-	ldd	 -64(%r30),   %r13
-	ldd	 -72(%r30),   %r12
-	ldd	 -80(%r30),   %r11
-	ldd	 -88(%r30),   %r10
-	ldd	 -96(%r30),    %r9
-	ldd	-104(%r30),    %r8
-	ldd	-112(%r30),    %r7
-	ldd	-120(%r30),    %r6
-	ldd	-128(%r30),    %r5
-	ldd	-136(%r30),    %r4
-	mtctl	%r3, %cr27
-	ldd,mb	-CALLEE_REG_FRAME_SIZE(%r30),    %r3
-	.endm
-
-#else /* ! CONFIG_64BIT */
-
-	.macro	callee_save
-	stw,ma	 %r3,	CALLEE_REG_FRAME_SIZE(%r30)
-	mfctl	 %cr27, %r3
-	stw	 %r4,	-124(%r30)
-	stw	 %r5,	-120(%r30)
-	stw	 %r6,	-116(%r30)
-	stw	 %r7,	-112(%r30)
-	stw	 %r8,	-108(%r30)
-	stw	 %r9,	-104(%r30)
-	stw	 %r10,	-100(%r30)
-	stw	 %r11,	 -96(%r30)
-	stw	 %r12,	 -92(%r30)
-	stw	 %r13,	 -88(%r30)
-	stw	 %r14,	 -84(%r30)
-	stw	 %r15,	 -80(%r30)
-	stw	 %r16,	 -76(%r30)
-	stw	 %r17,	 -72(%r30)
-	stw	 %r18,	 -68(%r30)
-	stw	  %r3,	 -64(%r30)
-	.endm
-
-	.macro	callee_rest
-	ldw	 -64(%r30),    %r3
-	ldw	 -68(%r30),   %r18
-	ldw	 -72(%r30),   %r17
-	ldw	 -76(%r30),   %r16
-	ldw	 -80(%r30),   %r15
-	ldw	 -84(%r30),   %r14
-	ldw	 -88(%r30),   %r13
-	ldw	 -92(%r30),   %r12
-	ldw	 -96(%r30),   %r11
-	ldw	-100(%r30),   %r10
-	ldw	-104(%r30),   %r9
-	ldw	-108(%r30),   %r8
-	ldw	-112(%r30),   %r7
-	ldw	-116(%r30),   %r6
-	ldw	-120(%r30),   %r5
-	ldw	-124(%r30),   %r4
-	mtctl	%r3, %cr27
-	ldw,mb	-CALLEE_REG_FRAME_SIZE(%r30),   %r3
-	.endm
-#endif /* ! CONFIG_64BIT */
-
-	.macro	save_specials	regs
-
-	SAVE_SP  (%sr0, PT_SR0 (\regs))
-	SAVE_SP  (%sr1, PT_SR1 (\regs))
-	SAVE_SP  (%sr2, PT_SR2 (\regs))
-	SAVE_SP  (%sr3, PT_SR3 (\regs))
-	SAVE_SP  (%sr4, PT_SR4 (\regs))
-	SAVE_SP  (%sr5, PT_SR5 (\regs))
-	SAVE_SP  (%sr6, PT_SR6 (\regs))
-	SAVE_SP  (%sr7, PT_SR7 (\regs))
-
-	SAVE_CR  (%cr17, PT_IASQ0(\regs))
-	mtctl	 %r0,	%cr17
-	SAVE_CR  (%cr17, PT_IASQ1(\regs))
-
-	SAVE_CR  (%cr18, PT_IAOQ0(\regs))
-	mtctl	 %r0,	%cr18
-	SAVE_CR  (%cr18, PT_IAOQ1(\regs))
-
-#ifdef CONFIG_64BIT
-	/* cr11 (sar) is a funny one.  5 bits on PA1.1 and 6 bit on PA2.0
-	 * For PA2.0 mtsar or mtctl always write 6 bits, but mfctl only
-	 * reads 5 bits.  Use mfctl,w to read all six bits.  Otherwise
-	 * we lose the 6th bit on a save/restore over interrupt.
-	 */
-	mfctl,w  %cr11, %r1
-	STREG    %r1, PT_SAR (\regs)
-#else
-	SAVE_CR  (%cr11, PT_SAR  (\regs))
-#endif
-	SAVE_CR  (%cr19, PT_IIR  (\regs))
-
-	/*
-	 * Code immediately following this macro (in intr_save) relies
-	 * on r8 containing ipsw.
-	 */
-	mfctl    %cr22, %r8
-	STREG    %r8,   PT_PSW(\regs)
-	.endm
-
-	.macro	rest_specials	regs
-
-	REST_SP  (%sr0, PT_SR0 (\regs))
-	REST_SP  (%sr1, PT_SR1 (\regs))
-	REST_SP  (%sr2, PT_SR2 (\regs))
-	REST_SP  (%sr3, PT_SR3 (\regs))
-	REST_SP  (%sr4, PT_SR4 (\regs))
-	REST_SP  (%sr5, PT_SR5 (\regs))
-	REST_SP  (%sr6, PT_SR6 (\regs))
-	REST_SP  (%sr7, PT_SR7 (\regs))
-
-	REST_CR	(%cr17, PT_IASQ0(\regs))
-	REST_CR	(%cr17, PT_IASQ1(\regs))
-
-	REST_CR	(%cr18, PT_IAOQ0(\regs))
-	REST_CR	(%cr18, PT_IAOQ1(\regs))
-
-	REST_CR (%cr11, PT_SAR	(\regs))
-
-	REST_CR	(%cr22, PT_PSW	(\regs))
-	.endm
-
-
-	/* First step to create a "relied upon translation"
-	 * See PA 2.0 Arch. page F-4 and F-5.
-	 *
-	 * The ssm was originally necessary due to a "PCxT bug".
-	 * But someone decided it needed to be added to the architecture
-	 * and this "feature" went into rev3 of PA-RISC 1.1 Arch Manual.
-	 * It's been carried forward into PA 2.0 Arch as well. :^(
-	 *
-	 * "ssm 0,%r0" is a NOP with side effects (prefetch barrier).
-	 * rsm/ssm prevents the ifetch unit from speculatively fetching
-	 * instructions past this line in the code stream.
-	 * PA 2.0 processor will single step all insn in the same QUAD (4 insn).
-	 */
-	.macro	pcxt_ssm_bug
-	rsm	PSW_SM_I,%r0
-	nop	/* 1 */
-	nop	/* 2 */
-	nop	/* 3 */
-	nop	/* 4 */
-	nop	/* 5 */
-	nop	/* 6 */
-	nop	/* 7 */
-	.endm
-
-#endif /* __ASSEMBLY__ */
-#endif
diff --git a/include/asm-parisc/atomic.h b/include/asm-parisc/atomic.h
deleted file mode 100644
index 57fcc4a5ebb4..000000000000
--- a/include/asm-parisc/atomic.h
+++ /dev/null
@@ -1,348 +0,0 @@
-/* Copyright (C) 2000 Philipp Rumpf <prumpf@tux.org>
- * Copyright (C) 2006 Kyle McMartin <kyle@parisc-linux.org>
- */
-
-#ifndef _ASM_PARISC_ATOMIC_H_
-#define _ASM_PARISC_ATOMIC_H_
-
-#include <linux/types.h>
-#include <asm/system.h>
-
-/*
- * Atomic operations that C can't guarantee us.  Useful for
- * resource counting etc..
- *
- * And probably incredibly slow on parisc.  OTOH, we don't
- * have to write any serious assembly.   prumpf
- */
-
-#ifdef CONFIG_SMP
-#include <asm/spinlock.h>
-#include <asm/cache.h>		/* we use L1_CACHE_BYTES */
-
-/* Use an array of spinlocks for our atomic_ts.
- * Hash function to index into a different SPINLOCK.
- * Since "a" is usually an address, use one spinlock per cacheline.
- */
-#  define ATOMIC_HASH_SIZE 4
-#  define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
-
-extern raw_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
-
-/* Can't use raw_spin_lock_irq because of #include problems, so
- * this is the substitute */
-#define _atomic_spin_lock_irqsave(l,f) do {	\
-	raw_spinlock_t *s = ATOMIC_HASH(l);		\
-	local_irq_save(f);			\
-	__raw_spin_lock(s);			\
-} while(0)
-
-#define _atomic_spin_unlock_irqrestore(l,f) do {	\
-	raw_spinlock_t *s = ATOMIC_HASH(l);			\
-	__raw_spin_unlock(s);				\
-	local_irq_restore(f);				\
-} while(0)
-
-
-#else
-#  define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0)
-#  define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
-#endif
-
-/* This should get optimized out since it's never called.
-** Or get a link error if xchg is used "wrong".
-*/
-extern void __xchg_called_with_bad_pointer(void);
-
-
-/* __xchg32/64 defined in arch/parisc/lib/bitops.c */
-extern unsigned long __xchg8(char, char *);
-extern unsigned long __xchg32(int, int *);
-#ifdef CONFIG_64BIT
-extern unsigned long __xchg64(unsigned long, unsigned long *);
-#endif
-
-/* optimizer better get rid of switch since size is a constant */
-static __inline__ unsigned long
-__xchg(unsigned long x, __volatile__ void * ptr, int size)
-{
-	switch(size) {
-#ifdef CONFIG_64BIT
-	case 8: return __xchg64(x,(unsigned long *) ptr);
-#endif
-	case 4: return __xchg32((int) x, (int *) ptr);
-	case 1: return __xchg8((char) x, (char *) ptr);
-	}
-	__xchg_called_with_bad_pointer();
-	return x;
-}
-
-
-/*
-** REVISIT - Abandoned use of LDCW in xchg() for now:
-** o need to test sizeof(*ptr) to avoid clearing adjacent bytes
-** o and while we are at it, could CONFIG_64BIT code use LDCD too?
-**
-**	if (__builtin_constant_p(x) && (x == NULL))
-**		if (((unsigned long)p & 0xf) == 0)
-**			return __ldcw(p);
-*/
-#define xchg(ptr,x) \
-	((__typeof__(*(ptr)))__xchg((unsigned long)(x),(ptr),sizeof(*(ptr))))
-
-
-#define __HAVE_ARCH_CMPXCHG	1
-
-/* bug catcher for when unsupported size is used - won't link */
-extern void __cmpxchg_called_with_bad_pointer(void);
-
-/* __cmpxchg_u32/u64 defined in arch/parisc/lib/bitops.c */
-extern unsigned long __cmpxchg_u32(volatile unsigned int *m, unsigned int old, unsigned int new_);
-extern unsigned long __cmpxchg_u64(volatile unsigned long *ptr, unsigned long old, unsigned long new_);
-
-/* don't worry...optimizer will get rid of most of this */
-static __inline__ unsigned long
-__cmpxchg(volatile void *ptr, unsigned long old, unsigned long new_, int size)
-{
-	switch(size) {
-#ifdef CONFIG_64BIT
-	case 8: return __cmpxchg_u64((unsigned long *)ptr, old, new_);
-#endif
-	case 4: return __cmpxchg_u32((unsigned int *)ptr, (unsigned int) old, (unsigned int) new_);
-	}
-	__cmpxchg_called_with_bad_pointer();
-	return old;
-}
-
-#define cmpxchg(ptr,o,n)						 \
-  ({									 \
-     __typeof__(*(ptr)) _o_ = (o);					 \
-     __typeof__(*(ptr)) _n_ = (n);					 \
-     (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_,		 \
-				    (unsigned long)_n_, sizeof(*(ptr))); \
-  })
-
-#include <asm-generic/cmpxchg-local.h>
-
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
-				      unsigned long old,
-				      unsigned long new_, int size)
-{
-	switch (size) {
-#ifdef CONFIG_64BIT
-	case 8:	return __cmpxchg_u64((unsigned long *)ptr, old, new_);
-#endif
-	case 4:	return __cmpxchg_u32(ptr, old, new_);
-	default:
-		return __cmpxchg_local_generic(ptr, old, new_, size);
-	}
-}
-
-/*
- * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
- * them available.
- */
-#define cmpxchg_local(ptr, o, n)				  	\
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
-			(unsigned long)(n), sizeof(*(ptr))))
-#ifdef CONFIG_64BIT
-#define cmpxchg64_local(ptr, o, n)					\
-  ({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
-  })
-#else
-#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
-#endif
-
-/* Note that we need not lock read accesses - aligned word writes/reads
- * are atomic, so a reader never sees unconsistent values.
- *
- * Cache-line alignment would conflict with, for example, linux/module.h
- */
-
-typedef struct { volatile int counter; } atomic_t;
-
-/* It's possible to reduce all atomic operations to either
- * __atomic_add_return, atomic_set and atomic_read (the latter
- * is there only for consistency).
- */
-
-static __inline__ int __atomic_add_return(int i, atomic_t *v)
-{
-	int ret;
-	unsigned long flags;
-	_atomic_spin_lock_irqsave(v, flags);
-
-	ret = (v->counter += i);
-
-	_atomic_spin_unlock_irqrestore(v, flags);
-	return ret;
-}
-
-static __inline__ void atomic_set(atomic_t *v, int i) 
-{
-	unsigned long flags;
-	_atomic_spin_lock_irqsave(v, flags);
-
-	v->counter = i;
-
-	_atomic_spin_unlock_irqrestore(v, flags);
-}
-
-static __inline__ int atomic_read(const atomic_t *v)
-{
-	return v->counter;
-}
-
-/* exported interface */
-#define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-
-/**
- * atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-#define atomic_add(i,v)	((void)(__atomic_add_return( ((int)i),(v))))
-#define atomic_sub(i,v)	((void)(__atomic_add_return(-((int)i),(v))))
-#define atomic_inc(v)	((void)(__atomic_add_return(   1,(v))))
-#define atomic_dec(v)	((void)(__atomic_add_return(  -1,(v))))
-
-#define atomic_add_return(i,v)	(__atomic_add_return( ((int)i),(v)))
-#define atomic_sub_return(i,v)	(__atomic_add_return(-((int)i),(v)))
-#define atomic_inc_return(v)	(__atomic_add_return(   1,(v)))
-#define atomic_dec_return(v)	(__atomic_add_return(  -1,(v)))
-
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec_and_test(v)	(atomic_dec_return(v) == 0)
-
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i),(v)) == 0)
-
-#define ATOMIC_INIT(i)	((atomic_t) { (i) })
-
-#define smp_mb__before_atomic_dec()	smp_mb()
-#define smp_mb__after_atomic_dec()	smp_mb()
-#define smp_mb__before_atomic_inc()	smp_mb()
-#define smp_mb__after_atomic_inc()	smp_mb()
-
-#ifdef CONFIG_64BIT
-
-typedef struct { volatile s64 counter; } atomic64_t;
-
-#define ATOMIC64_INIT(i) ((atomic64_t) { (i) })
-
-static __inline__ int
-__atomic64_add_return(s64 i, atomic64_t *v)
-{
-	int ret;
-	unsigned long flags;
-	_atomic_spin_lock_irqsave(v, flags);
-
-	ret = (v->counter += i);
-
-	_atomic_spin_unlock_irqrestore(v, flags);
-	return ret;
-}
-
-static __inline__ void
-atomic64_set(atomic64_t *v, s64 i)
-{
-	unsigned long flags;
-	_atomic_spin_lock_irqsave(v, flags);
-
-	v->counter = i;
-
-	_atomic_spin_unlock_irqrestore(v, flags);
-}
-
-static __inline__ s64
-atomic64_read(const atomic64_t *v)
-{
-	return v->counter;
-}
-
-#define atomic64_add(i,v)	((void)(__atomic64_add_return( ((s64)i),(v))))
-#define atomic64_sub(i,v)	((void)(__atomic64_add_return(-((s64)i),(v))))
-#define atomic64_inc(v)		((void)(__atomic64_add_return(   1,(v))))
-#define atomic64_dec(v)		((void)(__atomic64_add_return(  -1,(v))))
-
-#define atomic64_add_return(i,v)	(__atomic64_add_return( ((s64)i),(v)))
-#define atomic64_sub_return(i,v)	(__atomic64_add_return(-((s64)i),(v)))
-#define atomic64_inc_return(v)		(__atomic64_add_return(   1,(v)))
-#define atomic64_dec_return(v)		(__atomic64_add_return(  -1,(v)))
-
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-
-#define atomic64_inc_and_test(v) 	(atomic64_inc_return(v) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
-#define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i),(v)) == 0)
-
-/* exported interface */
-#define atomic64_cmpxchg(v, o, n) \
-	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
-#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
-
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-#endif /* CONFIG_64BIT */
-
-#include <asm-generic/atomic.h>
-
-#endif /* _ASM_PARISC_ATOMIC_H_ */
diff --git a/include/asm-parisc/auxvec.h b/include/asm-parisc/auxvec.h
deleted file mode 100644
index 9c3ac4b89dc9..000000000000
--- a/include/asm-parisc/auxvec.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef __ASMPARISC_AUXVEC_H
-#define __ASMPARISC_AUXVEC_H
-
-#endif
diff --git a/include/asm-parisc/bitops.h b/include/asm-parisc/bitops.h
deleted file mode 100644
index 7a6ea10bd231..000000000000
--- a/include/asm-parisc/bitops.h
+++ /dev/null
@@ -1,239 +0,0 @@
-#ifndef _PARISC_BITOPS_H
-#define _PARISC_BITOPS_H
-
-#ifndef _LINUX_BITOPS_H
-#error only <linux/bitops.h> can be included directly
-#endif
-
-#include <linux/compiler.h>
-#include <asm/types.h>		/* for BITS_PER_LONG/SHIFT_PER_LONG */
-#include <asm/byteorder.h>
-#include <asm/atomic.h>
-
-/*
- * HP-PARISC specific bit operations
- * for a detailed description of the functions please refer
- * to include/asm-i386/bitops.h or kerneldoc
- */
-
-#define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1))
-
-
-#define smp_mb__before_clear_bit()      smp_mb()
-#define smp_mb__after_clear_bit()       smp_mb()
-
-/* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion
- * on use of volatile and __*_bit() (set/clear/change):
- *	*_bit() want use of volatile.
- *	__*_bit() are "relaxed" and don't use spinlock or volatile.
- */
-
-static __inline__ void set_bit(int nr, volatile unsigned long * addr)
-{
-	unsigned long mask = 1UL << CHOP_SHIFTCOUNT(nr);
-	unsigned long flags;
-
-	addr += (nr >> SHIFT_PER_LONG);
-	_atomic_spin_lock_irqsave(addr, flags);
-	*addr |= mask;
-	_atomic_spin_unlock_irqrestore(addr, flags);
-}
-
-static __inline__ void clear_bit(int nr, volatile unsigned long * addr)
-{
-	unsigned long mask = ~(1UL << CHOP_SHIFTCOUNT(nr));
-	unsigned long flags;
-
-	addr += (nr >> SHIFT_PER_LONG);
-	_atomic_spin_lock_irqsave(addr, flags);
-	*addr &= mask;
-	_atomic_spin_unlock_irqrestore(addr, flags);
-}
-
-static __inline__ void change_bit(int nr, volatile unsigned long * addr)
-{
-	unsigned long mask = 1UL << CHOP_SHIFTCOUNT(nr);
-	unsigned long flags;
-
-	addr += (nr >> SHIFT_PER_LONG);
-	_atomic_spin_lock_irqsave(addr, flags);
-	*addr ^= mask;
-	_atomic_spin_unlock_irqrestore(addr, flags);
-}
-
-static __inline__ int test_and_set_bit(int nr, volatile unsigned long * addr)
-{
-	unsigned long mask = 1UL << CHOP_SHIFTCOUNT(nr);
-	unsigned long old;
-	unsigned long flags;
-	int set;
-
-	addr += (nr >> SHIFT_PER_LONG);
-	_atomic_spin_lock_irqsave(addr, flags);
-	old = *addr;
-	set = (old & mask) ? 1 : 0;
-	if (!set)
-		*addr = old | mask;
-	_atomic_spin_unlock_irqrestore(addr, flags);
-
-	return set;
-}
-
-static __inline__ int test_and_clear_bit(int nr, volatile unsigned long * addr)
-{
-	unsigned long mask = 1UL << CHOP_SHIFTCOUNT(nr);
-	unsigned long old;
-	unsigned long flags;
-	int set;
-
-	addr += (nr >> SHIFT_PER_LONG);
-	_atomic_spin_lock_irqsave(addr, flags);
-	old = *addr;
-	set = (old & mask) ? 1 : 0;
-	if (set)
-		*addr = old & ~mask;
-	_atomic_spin_unlock_irqrestore(addr, flags);
-
-	return set;
-}
-
-static __inline__ int test_and_change_bit(int nr, volatile unsigned long * addr)
-{
-	unsigned long mask = 1UL << CHOP_SHIFTCOUNT(nr);
-	unsigned long oldbit;
-	unsigned long flags;
-
-	addr += (nr >> SHIFT_PER_LONG);
-	_atomic_spin_lock_irqsave(addr, flags);
-	oldbit = *addr;
-	*addr = oldbit ^ mask;
-	_atomic_spin_unlock_irqrestore(addr, flags);
-
-	return (oldbit & mask) ? 1 : 0;
-}
-
-#include <asm-generic/bitops/non-atomic.h>
-
-#ifdef __KERNEL__
-
-/**
- * __ffs - find first bit in word. returns 0 to "BITS_PER_LONG-1".
- * @word: The word to search
- *
- * __ffs() return is undefined if no bit is set.
- *
- * 32-bit fast __ffs by LaMont Jones "lamont At hp com".
- * 64-bit enhancement by Grant Grundler "grundler At parisc-linux org".
- * (with help from willy/jejb to get the semantics right)
- *
- * This algorithm avoids branches by making use of nullification.
- * One side effect of "extr" instructions is it sets PSW[N] bit.
- * How PSW[N] (nullify next insn) gets set is determined by the 
- * "condition" field (eg "<>" or "TR" below) in the extr* insn.
- * Only the 1st and one of either the 2cd or 3rd insn will get executed.
- * Each set of 3 insn will get executed in 2 cycles on PA8x00 vs 16 or so
- * cycles for each mispredicted branch.
- */
-
-static __inline__ unsigned long __ffs(unsigned long x)
-{
-	unsigned long ret;
-
-	__asm__(
-#ifdef CONFIG_64BIT
-		" ldi       63,%1\n"
-		" extrd,u,*<>  %0,63,32,%%r0\n"
-		" extrd,u,*TR  %0,31,32,%0\n"	/* move top 32-bits down */
-		" addi    -32,%1,%1\n"
-#else
-		" ldi       31,%1\n"
-#endif
-		" extru,<>  %0,31,16,%%r0\n"
-		" extru,TR  %0,15,16,%0\n"	/* xxxx0000 -> 0000xxxx */
-		" addi    -16,%1,%1\n"
-		" extru,<>  %0,31,8,%%r0\n"
-		" extru,TR  %0,23,8,%0\n"	/* 0000xx00 -> 000000xx */
-		" addi    -8,%1,%1\n"
-		" extru,<>  %0,31,4,%%r0\n"
-		" extru,TR  %0,27,4,%0\n"	/* 000000x0 -> 0000000x */
-		" addi    -4,%1,%1\n"
-		" extru,<>  %0,31,2,%%r0\n"
-		" extru,TR  %0,29,2,%0\n"	/* 0000000y, 1100b -> 0011b */
-		" addi    -2,%1,%1\n"
-		" extru,=  %0,31,1,%%r0\n"	/* check last bit */
-		" addi    -1,%1,%1\n"
-			: "+r" (x), "=r" (ret) );
-	return ret;
-}
-
-#include <asm-generic/bitops/ffz.h>
-
-/*
- * ffs: find first bit set. returns 1 to BITS_PER_LONG or 0 (if none set)
- * This is defined the same way as the libc and compiler builtin
- * ffs routines, therefore differs in spirit from the above ffz (man ffs).
- */
-static __inline__ int ffs(int x)
-{
-	return x ? (__ffs((unsigned long)x) + 1) : 0;
-}
-
-/*
- * fls: find last (most significant) bit set.
- * fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
- */
-
-static __inline__ int fls(int x)
-{
-	int ret;
-	if (!x)
-		return 0;
-
-	__asm__(
-	"	ldi		1,%1\n"
-	"	extru,<>	%0,15,16,%%r0\n"
-	"	zdep,TR		%0,15,16,%0\n"		/* xxxx0000 */
-	"	addi		16,%1,%1\n"
-	"	extru,<>	%0,7,8,%%r0\n"
-	"	zdep,TR		%0,23,24,%0\n"		/* xx000000 */
-	"	addi		8,%1,%1\n"
-	"	extru,<>	%0,3,4,%%r0\n"
-	"	zdep,TR		%0,27,28,%0\n"		/* x0000000 */
-	"	addi		4,%1,%1\n"
-	"	extru,<>	%0,1,2,%%r0\n"
-	"	zdep,TR		%0,29,30,%0\n"		/* y0000000 (y&3 = 0) */
-	"	addi		2,%1,%1\n"
-	"	extru,=		%0,0,1,%%r0\n"
-	"	addi		1,%1,%1\n"		/* if y & 8, add 1 */
-		: "+r" (x), "=r" (ret) );
-
-	return ret;
-}
-
-#include <asm-generic/bitops/__fls.h>
-#include <asm-generic/bitops/fls64.h>
-#include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
-#include <asm-generic/bitops/sched.h>
-
-#endif /* __KERNEL__ */
-
-#include <asm-generic/bitops/find.h>
-
-#ifdef __KERNEL__
-
-#include <asm-generic/bitops/ext2-non-atomic.h>
-
-/* '3' is bits per byte */
-#define LE_BYTE_ADDR ((sizeof(unsigned long) - 1) << 3)
-
-#define ext2_set_bit_atomic(l,nr,addr) \
-		test_and_set_bit((nr)   ^ LE_BYTE_ADDR, (unsigned long *)addr)
-#define ext2_clear_bit_atomic(l,nr,addr) \
-		test_and_clear_bit( (nr) ^ LE_BYTE_ADDR, (unsigned long *)addr)
-
-#endif	/* __KERNEL__ */
-
-#include <asm-generic/bitops/minix-le.h>
-
-#endif /* _PARISC_BITOPS_H */
diff --git a/include/asm-parisc/bug.h b/include/asm-parisc/bug.h
deleted file mode 100644
index 8cfc553fc837..000000000000
--- a/include/asm-parisc/bug.h
+++ /dev/null
@@ -1,92 +0,0 @@
-#ifndef _PARISC_BUG_H
-#define _PARISC_BUG_H
-
-/*
- * Tell the user there is some problem.
- * The offending file and line are encoded in the __bug_table section.
- */
-
-#ifdef CONFIG_BUG
-#define HAVE_ARCH_BUG
-#define HAVE_ARCH_WARN_ON
-
-/* the break instruction is used as BUG() marker.  */
-#define	PARISC_BUG_BREAK_ASM	"break 0x1f, 0x1fff"
-#define	PARISC_BUG_BREAK_INSN	0x03ffe01f  /* PARISC_BUG_BREAK_ASM */
-
-#if defined(CONFIG_64BIT)
-#define ASM_WORD_INSN		".dword\t"
-#else
-#define ASM_WORD_INSN		".word\t"
-#endif
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-#define BUG()								\
-	do {								\
-		asm volatile("\n"					\
-			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
-			     "\t.pushsection __bug_table,\"a\"\n"	\
-			     "2:\t" ASM_WORD_INSN "1b, %c0\n"		\
-			     "\t.short %c1, %c2\n"			\
-			     "\t.org 2b+%c3\n"				\
-			     "\t.popsection"				\
-			     : : "i" (__FILE__), "i" (__LINE__),	\
-			     "i" (0), "i" (sizeof(struct bug_entry)) ); \
-		for(;;) ;						\
-	} while(0)
-
-#else
-#define BUG()								\
-	do {								\
-		asm volatile(PARISC_BUG_BREAK_ASM : : );		\
-		for(;;) ;						\
-	} while(0)
-#endif
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-#define __WARN()							\
-	do {								\
-		asm volatile("\n"					\
-			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
-			     "\t.pushsection __bug_table,\"a\"\n"	\
-			     "2:\t" ASM_WORD_INSN "1b, %c0\n"		\
-			     "\t.short %c1, %c2\n"			\
-			     "\t.org 2b+%c3\n"				\
-			     "\t.popsection"				\
-			     : : "i" (__FILE__), "i" (__LINE__),	\
-			     "i" (BUGFLAG_WARNING),			\
-			     "i" (sizeof(struct bug_entry)) );		\
-	} while(0)
-#else
-#define __WARN()							\
-	do {								\
-		asm volatile("\n"					\
-			     "1:\t" PARISC_BUG_BREAK_ASM "\n"		\
-			     "\t.pushsection __bug_table,\"a\"\n"	\
-			     "2:\t" ASM_WORD_INSN "1b\n"		\
-			     "\t.short %c0\n"				\
-			     "\t.org 2b+%c1\n"				\
-			     "\t.popsection"				\
-			     : : "i" (BUGFLAG_WARNING),			\
-			     "i" (sizeof(struct bug_entry)) );		\
-	} while(0)
-#endif
-
-
-#define WARN_ON(x) ({						\
-	int __ret_warn_on = !!(x);				\
-	if (__builtin_constant_p(__ret_warn_on)) {		\
-		if (__ret_warn_on)				\
-			__WARN();				\
-	} else {						\
-		if (unlikely(__ret_warn_on))			\
-			__WARN();				\
-	}							\
-	unlikely(__ret_warn_on);				\
-})
-
-#endif
-
-#include <asm-generic/bug.h>
-#endif
-
diff --git a/include/asm-parisc/bugs.h b/include/asm-parisc/bugs.h
deleted file mode 100644
index 9e6284342a5f..000000000000
--- a/include/asm-parisc/bugs.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- *  include/asm-parisc/bugs.h
- *
- *  Copyright (C) 1999	Mike Shaver
- */
-
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- *	void check_bugs(void);
- */
-
-#include <asm/processor.h>
-
-static inline void check_bugs(void)
-{
-//	identify_cpu(&boot_cpu_data);
-}
diff --git a/include/asm-parisc/byteorder.h b/include/asm-parisc/byteorder.h
deleted file mode 100644
index db148313de5d..000000000000
--- a/include/asm-parisc/byteorder.h
+++ /dev/null
@@ -1,82 +0,0 @@
-#ifndef _PARISC_BYTEORDER_H
-#define _PARISC_BYTEORDER_H
-
-#include <asm/types.h>
-#include <linux/compiler.h>
-
-#ifdef __GNUC__
-
-static __inline__ __attribute_const__ __u16 ___arch__swab16(__u16 x)
-{
-	__asm__("dep %0, 15, 8, %0\n\t"		/* deposit 00ab -> 0bab */
-		"shd %%r0, %0, 8, %0"		/* shift 000000ab -> 00ba */
-		: "=r" (x)
-		: "0" (x));
-	return x;
-}
-
-static __inline__ __attribute_const__ __u32 ___arch__swab24(__u32 x)
-{
-	__asm__("shd %0, %0, 8, %0\n\t"		/* shift xabcxabc -> cxab */
-		"dep %0, 15, 8, %0\n\t"		/* deposit cxab -> cbab */
-		"shd %%r0, %0, 8, %0"		/* shift 0000cbab -> 0cba */
-		: "=r" (x)
-		: "0" (x));
-	return x;
-}
-
-static __inline__ __attribute_const__ __u32 ___arch__swab32(__u32 x)
-{
-	unsigned int temp;
-	__asm__("shd %0, %0, 16, %1\n\t"	/* shift abcdabcd -> cdab */
-		"dep %1, 15, 8, %1\n\t"		/* deposit cdab -> cbab */
-		"shd %0, %1, 8, %0"		/* shift abcdcbab -> dcba */
-		: "=r" (x), "=&r" (temp)
-		: "0" (x));
-	return x;
-}
-
-
-#if BITS_PER_LONG > 32
-/*
-** From "PA-RISC 2.0 Architecture", HP Professional Books.
-** See Appendix I page 8 , "Endian Byte Swapping".
-**
-** Pretty cool algorithm: (* == zero'd bits)
-**      PERMH   01234567 -> 67452301 into %0
-**      HSHL    67452301 -> 7*5*3*1* into %1
-**      HSHR    67452301 -> *6*4*2*0 into %0
-**      OR      %0 | %1  -> 76543210 into %0 (all done!)
-*/
-static __inline__ __attribute_const__ __u64 ___arch__swab64(__u64 x) {
-	__u64 temp;
-	__asm__("permh,3210 %0, %0\n\t"
-		"hshl %0, 8, %1\n\t"
-		"hshr,u %0, 8, %0\n\t"
-		"or %1, %0, %0"
-		: "=r" (x), "=&r" (temp)
-		: "0" (x));
-	return x;
-}
-#define __arch__swab64(x) ___arch__swab64(x)
-#define __BYTEORDER_HAS_U64__
-#elif !defined(__STRICT_ANSI__)
-static __inline__ __attribute_const__ __u64 ___arch__swab64(__u64 x)
-{
-	__u32 t1 = ___arch__swab32((__u32) x);
-	__u32 t2 = ___arch__swab32((__u32) (x >> 32));
-	return (((__u64) t1 << 32) | t2);
-}
-#define __arch__swab64(x) ___arch__swab64(x)
-#define __BYTEORDER_HAS_U64__
-#endif
-
-#define __arch__swab16(x) ___arch__swab16(x)
-#define __arch__swab24(x) ___arch__swab24(x)
-#define __arch__swab32(x) ___arch__swab32(x)
-
-#endif /* __GNUC__ */
-
-#include <linux/byteorder/big_endian.h>
-
-#endif /* _PARISC_BYTEORDER_H */
diff --git a/include/asm-parisc/cache.h b/include/asm-parisc/cache.h
deleted file mode 100644
index 32c2cca74345..000000000000
--- a/include/asm-parisc/cache.h
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * include/asm-parisc/cache.h
- */
-
-#ifndef __ARCH_PARISC_CACHE_H
-#define __ARCH_PARISC_CACHE_H
-
-
-/*
- * PA 2.0 processors have 64-byte cachelines; PA 1.1 processors have
- * 32-byte cachelines.  The default configuration is not for SMP anyway,
- * so if you're building for SMP, you should select the appropriate
- * processor type.  There is a potential livelock danger when running
- * a machine with this value set too small, but it's more probable you'll
- * just ruin performance.
- */
-#ifdef CONFIG_PA20
-#define L1_CACHE_BYTES 64
-#define L1_CACHE_SHIFT 6
-#else
-#define L1_CACHE_BYTES 32
-#define L1_CACHE_SHIFT 5
-#endif
-
-#ifndef __ASSEMBLY__
-
-#define L1_CACHE_ALIGN(x)       (((x)+(L1_CACHE_BYTES-1))&~(L1_CACHE_BYTES-1))
-
-#define SMP_CACHE_BYTES L1_CACHE_BYTES
-
-#define __read_mostly __attribute__((__section__(".data.read_mostly")))
-
-void parisc_cache_init(void);	/* initializes cache-flushing */
-void disable_sr_hashing_asm(int); /* low level support for above */
-void disable_sr_hashing(void);   /* turns off space register hashing */
-void free_sid(unsigned long);
-unsigned long alloc_sid(void);
-
-struct seq_file;
-extern void show_cache_info(struct seq_file *m);
-
-extern int split_tlb;
-extern int dcache_stride;
-extern int icache_stride;
-extern struct pdc_cache_info cache_info;
-void parisc_setup_cache_timing(void);
-
-#define pdtlb(addr)         asm volatile("pdtlb 0(%%sr1,%0)" : : "r" (addr));
-#define pitlb(addr)         asm volatile("pitlb 0(%%sr1,%0)" : : "r" (addr));
-#define pdtlb_kernel(addr)  asm volatile("pdtlb 0(%0)" : : "r" (addr));
-
-#endif /* ! __ASSEMBLY__ */
-
-/* Classes of processor wrt: disabling space register hashing */
-
-#define SRHASH_PCXST    0   /* pcxs, pcxt, pcxt_ */
-#define SRHASH_PCXL     1   /* pcxl */
-#define SRHASH_PA20     2   /* pcxu, pcxu_, pcxw, pcxw_ */
-
-#endif
diff --git a/include/asm-parisc/cacheflush.h b/include/asm-parisc/cacheflush.h
deleted file mode 100644
index b7ca6dc7fddc..000000000000
--- a/include/asm-parisc/cacheflush.h
+++ /dev/null
@@ -1,121 +0,0 @@
-#ifndef _PARISC_CACHEFLUSH_H
-#define _PARISC_CACHEFLUSH_H
-
-#include <linux/mm.h>
-
-/* The usual comment is "Caches aren't brain-dead on the <architecture>".
- * Unfortunately, that doesn't apply to PA-RISC. */
-
-/* Internal implementation */
-void flush_data_cache_local(void *);  /* flushes local data-cache only */
-void flush_instruction_cache_local(void *); /* flushes local code-cache only */
-#ifdef CONFIG_SMP
-void flush_data_cache(void); /* flushes data-cache only (all processors) */
-void flush_instruction_cache(void); /* flushes i-cache only (all processors) */
-#else
-#define flush_data_cache() flush_data_cache_local(NULL)
-#define flush_instruction_cache() flush_instruction_cache_local(NULL)
-#endif
-
-#define flush_cache_dup_mm(mm) flush_cache_mm(mm)
-
-void flush_user_icache_range_asm(unsigned long, unsigned long);
-void flush_kernel_icache_range_asm(unsigned long, unsigned long);
-void flush_user_dcache_range_asm(unsigned long, unsigned long);
-void flush_kernel_dcache_range_asm(unsigned long, unsigned long);
-void flush_kernel_dcache_page_asm(void *);
-void flush_kernel_icache_page(void *);
-void flush_user_dcache_page(unsigned long);
-void flush_user_icache_page(unsigned long);
-void flush_user_dcache_range(unsigned long, unsigned long);
-void flush_user_icache_range(unsigned long, unsigned long);
-
-/* Cache flush operations */
-
-void flush_cache_all_local(void);
-void flush_cache_all(void);
-void flush_cache_mm(struct mm_struct *mm);
-
-#define flush_kernel_dcache_range(start,size) \
-	flush_kernel_dcache_range_asm((start), (start)+(size));
-
-#define flush_cache_vmap(start, end)		flush_cache_all()
-#define flush_cache_vunmap(start, end)		flush_cache_all()
-
-extern void flush_dcache_page(struct page *page);
-
-#define flush_dcache_mmap_lock(mapping) \
-	spin_lock_irq(&(mapping)->tree_lock)
-#define flush_dcache_mmap_unlock(mapping) \
-	spin_unlock_irq(&(mapping)->tree_lock)
-
-#define flush_icache_page(vma,page)	do { 		\
-	flush_kernel_dcache_page(page);			\
-	flush_kernel_icache_page(page_address(page)); 	\
-} while (0)
-
-#define flush_icache_range(s,e)		do { 		\
-	flush_kernel_dcache_range_asm(s,e); 		\
-	flush_kernel_icache_range_asm(s,e); 		\
-} while (0)
-
-#define copy_to_user_page(vma, page, vaddr, dst, src, len) \
-do { \
-	flush_cache_page(vma, vaddr, page_to_pfn(page)); \
-	memcpy(dst, src, len); \
-	flush_kernel_dcache_range_asm((unsigned long)dst, (unsigned long)dst + len); \
-} while (0)
-
-#define copy_from_user_page(vma, page, vaddr, dst, src, len) \
-do { \
-	flush_cache_page(vma, vaddr, page_to_pfn(page)); \
-	memcpy(dst, src, len); \
-} while (0)
-
-void flush_cache_page(struct vm_area_struct *vma, unsigned long vmaddr, unsigned long pfn);
-void flush_cache_range(struct vm_area_struct *vma,
-		unsigned long start, unsigned long end);
-
-#define ARCH_HAS_FLUSH_ANON_PAGE
-static inline void
-flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vmaddr)
-{
-	if (PageAnon(page))
-		flush_user_dcache_page(vmaddr);
-}
-
-#define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
-void flush_kernel_dcache_page_addr(void *addr);
-static inline void flush_kernel_dcache_page(struct page *page)
-{
-	flush_kernel_dcache_page_addr(page_address(page));
-}
-
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
-#endif
-
-#ifdef CONFIG_PA8X00
-/* Only pa8800, pa8900 needs this */
-#define ARCH_HAS_KMAP
-
-void kunmap_parisc(void *addr);
-
-static inline void *kmap(struct page *page)
-{
-	might_sleep();
-	return page_address(page);
-}
-
-#define kunmap(page)			kunmap_parisc(page_address(page))
-
-#define kmap_atomic(page, idx)		page_address(page)
-
-#define kunmap_atomic(addr, idx)	kunmap_parisc(addr)
-
-#define kmap_atomic_pfn(pfn, idx)	page_address(pfn_to_page(pfn))
-#define kmap_atomic_to_page(ptr)	virt_to_page(ptr)
-#endif
-
-#endif /* _PARISC_CACHEFLUSH_H */
-
diff --git a/include/asm-parisc/checksum.h b/include/asm-parisc/checksum.h
deleted file mode 100644
index e9639ccc3fce..000000000000
--- a/include/asm-parisc/checksum.h
+++ /dev/null
@@ -1,210 +0,0 @@
-#ifndef _PARISC_CHECKSUM_H
-#define _PARISC_CHECKSUM_H
-
-#include <linux/in6.h>
-
-/*
- * computes the checksum of a memory block at buff, length len,
- * and adds in "sum" (32-bit)
- *
- * returns a 32-bit number suitable for feeding into itself
- * or csum_tcpudp_magic
- *
- * this function must be called with even lengths, except
- * for the last fragment, which may be odd
- *
- * it's best to have buff aligned on a 32-bit boundary
- */
-extern __wsum csum_partial(const void *, int, __wsum);
-
-/*
- * The same as csum_partial, but copies from src while it checksums.
- *
- * Here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-extern __wsum csum_partial_copy_nocheck(const void *, void *, int, __wsum);
-
-/*
- * this is a new version of the above that records errors it finds in *errp,
- * but continues and zeros the rest of the buffer.
- */
-extern __wsum csum_partial_copy_from_user(const void __user *src,
-		void *dst, int len, __wsum sum, int *errp);
-
-/*
- *	Optimized for IP headers, which always checksum on 4 octet boundaries.
- *
- *	Written by Randolph Chung <tausq@debian.org>, and then mucked with by
- *	LaMont Jones <lamont@debian.org>
- */
-static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
-{
-	unsigned int sum;
-
-	__asm__ __volatile__ (
-"	ldws,ma		4(%1), %0\n"
-"	addib,<=	-4, %2, 2f\n"
-"\n"
-"	ldws		4(%1), %%r20\n"
-"	ldws		8(%1), %%r21\n"
-"	add		%0, %%r20, %0\n"
-"	ldws,ma		12(%1), %%r19\n"
-"	addc		%0, %%r21, %0\n"
-"	addc		%0, %%r19, %0\n"
-"1:	ldws,ma		4(%1), %%r19\n"
-"	addib,<		0, %2, 1b\n"
-"	addc		%0, %%r19, %0\n"
-"\n"
-"	extru		%0, 31, 16, %%r20\n"
-"	extru		%0, 15, 16, %%r21\n"
-"	addc		%%r20, %%r21, %0\n"
-"	extru		%0, 15, 16, %%r21\n"
-"	add		%0, %%r21, %0\n"
-"	subi		-1, %0, %0\n"
-"2:\n"
-	: "=r" (sum), "=r" (iph), "=r" (ihl)
-	: "1" (iph), "2" (ihl)
-	: "r19", "r20", "r21", "memory");
-
-	return (__force __sum16)sum;
-}
-
-/*
- *	Fold a partial checksum
- */
-static inline __sum16 csum_fold(__wsum csum)
-{
-	u32 sum = (__force u32)csum;
-	/* add the swapped two 16-bit halves of sum,
-	   a possible carry from adding the two 16-bit halves,
-	   will carry from the lower half into the upper half,
-	   giving us the correct sum in the upper half. */
-	sum += (sum << 16) + (sum >> 16);
-	return (__force __sum16)(~sum >> 16);
-}
- 
-static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					       unsigned short len,
-					       unsigned short proto,
-					       __wsum sum)
-{
-	__asm__(
-	"	add  %1, %0, %0\n"
-	"	addc %2, %0, %0\n"
-	"	addc %3, %0, %0\n"
-	"	addc %%r0, %0, %0\n"
-		: "=r" (sum)
-		: "r" (daddr), "r"(saddr), "r"(proto+len), "0"(sum));
-	return sum;
-}
-
-/*
- * computes the checksum of the TCP/UDP pseudo-header
- * returns a 16-bit checksum, already complemented
- */
-static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-						   unsigned short len,
-						   unsigned short proto,
-						   __wsum sum)
-{
-	return csum_fold(csum_tcpudp_nofold(saddr,daddr,len,proto,sum));
-}
-
-/*
- * this routine is used for miscellaneous IP-like checksums, mainly
- * in icmp.c
- */
-static inline __sum16 ip_compute_csum(const void *buf, int len)
-{
-	 return csum_fold (csum_partial(buf, len, 0));
-}
-
-
-#define _HAVE_ARCH_IPV6_CSUM
-static __inline__ __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
-					  const struct in6_addr *daddr,
-					  __u32 len, unsigned short proto,
-					  __wsum sum)
-{
-	__asm__ __volatile__ (
-
-#if BITS_PER_LONG > 32
-
-	/*
-	** We can execute two loads and two adds per cycle on PA 8000.
-	** But add insn's get serialized waiting for the carry bit.
-	** Try to keep 4 registers with "live" values ahead of the ALU.
-	*/
-
-"	ldd,ma		8(%1), %%r19\n"	/* get 1st saddr word */
-"	ldd,ma		8(%2), %%r20\n"	/* get 1st daddr word */
-"	add		%8, %3, %3\n"/* add 16-bit proto + len */
-"	add		%%r19, %0, %0\n"
-"	ldd,ma		8(%1), %%r21\n"	/* 2cd saddr */
-"	ldd,ma		8(%2), %%r22\n"	/* 2cd daddr */
-"	add,dc		%%r20, %0, %0\n"
-"	add,dc		%%r21, %0, %0\n"
-"	add,dc		%%r22, %0, %0\n"
-"	add,dc		%3, %0, %0\n"  /* fold in proto+len | carry bit */
-"	extrd,u		%0, 31, 32, %%r19\n"	/* copy upper half down */
-"	depdi		0, 31, 32, %0\n"	/* clear upper half */
-"	add		%%r19, %0, %0\n"	/* fold into 32-bits */
-"	addc		0, %0, %0\n"		/* add carry */
-
-#else
-
-	/*
-	** For PA 1.x, the insn order doesn't matter as much.
-	** Insn stream is serialized on the carry bit here too.
-	** result from the previous operation (eg r0 + x)
-	*/
-
-"	ldw,ma		4(%1), %%r19\n"	/* get 1st saddr word */
-"	ldw,ma		4(%2), %%r20\n"	/* get 1st daddr word */
-"	add		%8, %3, %3\n"	/* add 16-bit proto + len */
-"	add		%%r19, %0, %0\n"
-"	ldw,ma		4(%1), %%r21\n"	/* 2cd saddr */
-"	addc		%%r20, %0, %0\n"
-"	ldw,ma		4(%2), %%r22\n"	/* 2cd daddr */
-"	addc		%%r21, %0, %0\n"
-"	ldw,ma		4(%1), %%r19\n"	/* 3rd saddr */
-"	addc		%%r22, %0, %0\n"
-"	ldw,ma		4(%2), %%r20\n"	/* 3rd daddr */
-"	addc		%%r19, %0, %0\n"
-"	ldw,ma		4(%1), %%r21\n"	/* 4th saddr */
-"	addc		%%r20, %0, %0\n"
-"	ldw,ma		4(%2), %%r22\n"	/* 4th daddr */
-"	addc		%%r21, %0, %0\n"
-"	addc		%%r22, %0, %0\n"
-"	addc		%3, %0, %0\n"	/* fold in proto+len, catch carry */
-
-#endif
-	: "=r" (sum), "=r" (saddr), "=r" (daddr), "=r" (len)
-	: "0" (sum), "1" (saddr), "2" (daddr), "3" (len), "r" (proto)
-	: "r19", "r20", "r21", "r22");
-	return csum_fold(sum);
-}
-
-/* 
- *	Copy and checksum to user
- */
-#define HAVE_CSUM_COPY_USER
-static __inline__ __wsum csum_and_copy_to_user(const void *src,
-						      void __user *dst,
-						      int len, __wsum sum,
-						      int *err_ptr)
-{
-	/* code stolen from include/asm-mips64 */
-	sum = csum_partial(src, len, sum);
-	 
-	if (copy_to_user(dst, src, len)) {
-		*err_ptr = -EFAULT;
-		return (__force __wsum)-1;
-	}
-
-	return sum;
-}
-
-#endif
-
diff --git a/include/asm-parisc/compat.h b/include/asm-parisc/compat.h
deleted file mode 100644
index 7f32611a7a5e..000000000000
--- a/include/asm-parisc/compat.h
+++ /dev/null
@@ -1,165 +0,0 @@
-#ifndef _ASM_PARISC_COMPAT_H
-#define _ASM_PARISC_COMPAT_H
-/*
- * Architecture specific compatibility types
- */
-#include <linux/types.h>
-#include <linux/sched.h>
-#include <linux/thread_info.h>
-
-#define COMPAT_USER_HZ 100
-
-typedef u32	compat_size_t;
-typedef s32	compat_ssize_t;
-typedef s32	compat_time_t;
-typedef s32	compat_clock_t;
-typedef s32	compat_pid_t;
-typedef u32	__compat_uid_t;
-typedef u32	__compat_gid_t;
-typedef u32	__compat_uid32_t;
-typedef u32	__compat_gid32_t;
-typedef u16	compat_mode_t;
-typedef u32	compat_ino_t;
-typedef u32	compat_dev_t;
-typedef s32	compat_off_t;
-typedef s64	compat_loff_t;
-typedef u16	compat_nlink_t;
-typedef u16	compat_ipc_pid_t;
-typedef s32	compat_daddr_t;
-typedef u32	compat_caddr_t;
-typedef s32	compat_timer_t;
-
-typedef s32	compat_int_t;
-typedef s32	compat_long_t;
-typedef s64	compat_s64;
-typedef u32	compat_uint_t;
-typedef u32	compat_ulong_t;
-typedef u64	compat_u64;
-
-struct compat_timespec {
-	compat_time_t		tv_sec;
-	s32			tv_nsec;
-};
-
-struct compat_timeval {
-	compat_time_t		tv_sec;
-	s32			tv_usec;
-};
-
-struct compat_stat {
-	compat_dev_t		st_dev;	/* dev_t is 32 bits on parisc */
-	compat_ino_t		st_ino;	/* 32 bits */
-	compat_mode_t		st_mode;	/* 16 bits */
-	compat_nlink_t  	st_nlink;	/* 16 bits */
-	u16			st_reserved1;	/* old st_uid */
-	u16			st_reserved2;	/* old st_gid */
-	compat_dev_t		st_rdev;
-	compat_off_t		st_size;
-	compat_time_t		st_atime;
-	u32			st_atime_nsec;
-	compat_time_t		st_mtime;
-	u32			st_mtime_nsec;
-	compat_time_t		st_ctime;
-	u32			st_ctime_nsec;
-	s32			st_blksize;
-	s32			st_blocks;
-	u32			__unused1;	/* ACL stuff */
-	compat_dev_t		__unused2;	/* network */
-	compat_ino_t		__unused3;	/* network */
-	u32			__unused4;	/* cnodes */
-	u16			__unused5;	/* netsite */
-	short			st_fstype;
-	compat_dev_t		st_realdev;
-	u16			st_basemode;
-	u16			st_spareshort;
-	__compat_uid32_t	st_uid;
-	__compat_gid32_t	st_gid;
-	u32			st_spare4[3];
-};
-
-struct compat_flock {
-	short			l_type;
-	short			l_whence;
-	compat_off_t		l_start;
-	compat_off_t		l_len;
-	compat_pid_t		l_pid;
-};
-
-struct compat_flock64 {
-	short			l_type;
-	short			l_whence;
-	compat_loff_t		l_start;
-	compat_loff_t		l_len;
-	compat_pid_t		l_pid;
-};
-
-struct compat_statfs {
-	s32		f_type;
-	s32		f_bsize;
-	s32		f_blocks;
-	s32		f_bfree;
-	s32		f_bavail;
-	s32		f_files;
-	s32		f_ffree;
-	__kernel_fsid_t	f_fsid;
-	s32		f_namelen;
-	s32		f_frsize;
-	s32		f_spare[5];
-};
-
-struct compat_sigcontext {
-	compat_int_t sc_flags;
-	compat_int_t sc_gr[32]; /* PSW in sc_gr[0] */
-	u64 sc_fr[32];
-	compat_int_t sc_iasq[2];
-	compat_int_t sc_iaoq[2];
-	compat_int_t sc_sar; /* cr11 */
-};
-
-#define COMPAT_RLIM_INFINITY 0xffffffff
-
-typedef u32		compat_old_sigset_t;	/* at least 32 bits */
-
-#define _COMPAT_NSIG		64
-#define _COMPAT_NSIG_BPW	32
-
-typedef u32		compat_sigset_word;
-
-#define COMPAT_OFF_T_MAX	0x7fffffff
-#define COMPAT_LOFF_T_MAX	0x7fffffffffffffffL
-
-/*
- * A pointer passed in from user mode. This should not
- * be used for syscall parameters, just declare them
- * as pointers because the syscall entry code will have
- * appropriately converted them already.
- */
-typedef	u32		compat_uptr_t;
-
-static inline void __user *compat_ptr(compat_uptr_t uptr)
-{
-	return (void __user *)(unsigned long)uptr;
-}
-
-static inline compat_uptr_t ptr_to_compat(void __user *uptr)
-{
-	return (u32)(unsigned long)uptr;
-}
-
-static __inline__ void __user *compat_alloc_user_space(long len)
-{
-	struct pt_regs *regs = &current->thread.regs;
-	return (void __user *)regs->gr[30];
-}
-
-static inline int __is_compat_task(struct task_struct *t)
-{
-	return test_ti_thread_flag(task_thread_info(t), TIF_32BIT);
-}
-
-static inline int is_compat_task(void)
-{
-	return __is_compat_task(current);
-}
-
-#endif /* _ASM_PARISC_COMPAT_H */
diff --git a/include/asm-parisc/compat_rt_sigframe.h b/include/asm-parisc/compat_rt_sigframe.h
deleted file mode 100644
index 81bec28bdc48..000000000000
--- a/include/asm-parisc/compat_rt_sigframe.h
+++ /dev/null
@@ -1,50 +0,0 @@
-#include<linux/compat.h>
-#include<linux/compat_siginfo.h>
-#include<asm/compat_ucontext.h>
-
-#ifndef _ASM_PARISC_COMPAT_RT_SIGFRAME_H
-#define _ASM_PARISC_COMPAT_RT_SIGFRAME_H
-
-/* In a deft move of uber-hackery, we decide to carry the top half of all
- * 64-bit registers in a non-portable, non-ABI, hidden structure.
- * Userspace can read the hidden structure if it *wants* but is never
- * guaranteed to be in the same place. Infact the uc_sigmask from the 
- * ucontext_t structure may push the hidden register file downards
- */
-struct compat_regfile {
-	/* Upper half of all the 64-bit registers that were truncated
-	   on a copy to a 32-bit userspace */
-	compat_int_t rf_gr[32];
-	compat_int_t rf_iasq[2];
-	compat_int_t rf_iaoq[2];
-	compat_int_t rf_sar;
-};
-
-#define COMPAT_SIGRETURN_TRAMP 4
-#define COMPAT_SIGRESTARTBLOCK_TRAMP 5 
-#define COMPAT_TRAMP_SIZE (COMPAT_SIGRETURN_TRAMP + COMPAT_SIGRESTARTBLOCK_TRAMP)
-
-struct compat_rt_sigframe {
-	/* XXX: Must match trampoline size in arch/parisc/kernel/signal.c 
-	        Secondary to that it must protect the ERESTART_RESTARTBLOCK
-		trampoline we left on the stack (we were bad and didn't 
-		change sp so we could run really fast.) */
-	compat_uint_t tramp[COMPAT_TRAMP_SIZE];
-	compat_siginfo_t info;
-	struct compat_ucontext uc;
-	/* Hidden location of truncated registers, *must* be last. */
-	struct compat_regfile regs; 
-};
-
-/*
- * The 32-bit ABI wants at least 48 bytes for a function call frame:
- * 16 bytes for arg0-arg3, and 32 bytes for magic (the only part of
- * which Linux/parisc uses is sp-20 for the saved return pointer...)
- * Then, the stack pointer must be rounded to a cache line (64 bytes).
- */
-#define SIGFRAME32		64
-#define FUNCTIONCALLFRAME32	48
-#define PARISC_RT_SIGFRAME_SIZE32					\
-	(((sizeof(struct compat_rt_sigframe) + FUNCTIONCALLFRAME32) + SIGFRAME32) & -SIGFRAME32)
-
-#endif
diff --git a/include/asm-parisc/compat_signal.h b/include/asm-parisc/compat_signal.h
deleted file mode 100644
index 6ad02c360b21..000000000000
--- a/include/asm-parisc/compat_signal.h
+++ /dev/null
@@ -1,2 +0,0 @@
-/* Use generic */
-#include <asm-generic/compat_signal.h>
diff --git a/include/asm-parisc/compat_ucontext.h b/include/asm-parisc/compat_ucontext.h
deleted file mode 100644
index 2f7292afde3c..000000000000
--- a/include/asm-parisc/compat_ucontext.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef _ASM_PARISC_COMPAT_UCONTEXT_H
-#define _ASM_PARISC_COMPAT_UCONTEXT_H
-
-#include <linux/compat.h>
-
-/* 32-bit ucontext as seen from an 64-bit kernel */
-struct compat_ucontext {
-	compat_uint_t uc_flags;
-	compat_uptr_t uc_link;
-	compat_stack_t uc_stack;	/* struct compat_sigaltstack (12 bytes)*/	
-	/* FIXME: Pad out to get uc_mcontext to start at an 8-byte aligned boundary */
-	compat_uint_t pad[1];
-	struct compat_sigcontext uc_mcontext;
-	compat_sigset_t uc_sigmask;	/* mask last for extensibility */
-};
-
-#endif /* !_ASM_PARISC_COMPAT_UCONTEXT_H */
diff --git a/include/asm-parisc/cputime.h b/include/asm-parisc/cputime.h
deleted file mode 100644
index dcdf2fbd7e72..000000000000
--- a/include/asm-parisc/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __PARISC_CPUTIME_H
-#define __PARISC_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __PARISC_CPUTIME_H */
diff --git a/include/asm-parisc/current.h b/include/asm-parisc/current.h
deleted file mode 100644
index 0fb9338e3bf2..000000000000
--- a/include/asm-parisc/current.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef _PARISC_CURRENT_H
-#define _PARISC_CURRENT_H
-
-#include <linux/thread_info.h>
-
-struct task_struct;
-
-static inline struct task_struct * get_current(void)
-{
-	return current_thread_info()->task;
-}
- 
-#define current get_current()
-
-#endif /* !(_PARISC_CURRENT_H) */
diff --git a/include/asm-parisc/delay.h b/include/asm-parisc/delay.h
deleted file mode 100644
index 7a75e984674b..000000000000
--- a/include/asm-parisc/delay.h
+++ /dev/null
@@ -1,43 +0,0 @@
-#ifndef _PARISC_DELAY_H
-#define _PARISC_DELAY_H
-
-#include <asm/system.h>    /* for mfctl() */
-#include <asm/processor.h> /* for boot_cpu_data */
-
-
-/*
- * Copyright (C) 1993 Linus Torvalds
- *
- * Delay routines
- */
-
-static __inline__ void __delay(unsigned long loops) {
-	asm volatile(
-	"	.balignl	64,0x34000034\n"
-	"	addib,UV -1,%0,.\n"
-	"	nop\n"
-		: "=r" (loops) : "0" (loops));
-}
-
-static __inline__ void __cr16_delay(unsigned long clocks) {
-	unsigned long start;
-
-	/*
-	 * Note: Due to unsigned math, cr16 rollovers shouldn't be
-	 * a problem here. However, on 32 bit, we need to make sure
-	 * we don't pass in too big a value. The current default
-	 * value of MAX_UDELAY_MS should help prevent this.
-	 */
-
-	start = mfctl(16);
-	while ((mfctl(16) - start) < clocks)
-	    ;
-}
-
-static __inline__ void __udelay(unsigned long usecs) {
-	__cr16_delay(usecs * ((unsigned long)boot_cpu_data.cpu_hz / 1000000UL));
-}
-
-#define udelay(n) __udelay(n)
-
-#endif /* defined(_PARISC_DELAY_H) */
diff --git a/include/asm-parisc/device.h b/include/asm-parisc/device.h
deleted file mode 100644
index d8f9872b0e2d..000000000000
--- a/include/asm-parisc/device.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/*
- * Arch specific extensions to struct device
- *
- * This file is released under the GPLv2
- */
-#include <asm-generic/device.h>
-
diff --git a/include/asm-parisc/div64.h b/include/asm-parisc/div64.h
deleted file mode 100644
index 6cd978cefb28..000000000000
--- a/include/asm-parisc/div64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/div64.h>
diff --git a/include/asm-parisc/dma-mapping.h b/include/asm-parisc/dma-mapping.h
deleted file mode 100644
index 53af696f23d2..000000000000
--- a/include/asm-parisc/dma-mapping.h
+++ /dev/null
@@ -1,253 +0,0 @@
-#ifndef _PARISC_DMA_MAPPING_H
-#define _PARISC_DMA_MAPPING_H
-
-#include <linux/mm.h>
-#include <asm/cacheflush.h>
-#include <asm/scatterlist.h>
-
-/* See Documentation/DMA-mapping.txt */
-struct hppa_dma_ops {
-	int  (*dma_supported)(struct device *dev, u64 mask);
-	void *(*alloc_consistent)(struct device *dev, size_t size, dma_addr_t *iova, gfp_t flag);
-	void *(*alloc_noncoherent)(struct device *dev, size_t size, dma_addr_t *iova, gfp_t flag);
-	void (*free_consistent)(struct device *dev, size_t size, void *vaddr, dma_addr_t iova);
-	dma_addr_t (*map_single)(struct device *dev, void *addr, size_t size, enum dma_data_direction direction);
-	void (*unmap_single)(struct device *dev, dma_addr_t iova, size_t size, enum dma_data_direction direction);
-	int  (*map_sg)(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction);
-	void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nhwents, enum dma_data_direction direction);
-	void (*dma_sync_single_for_cpu)(struct device *dev, dma_addr_t iova, unsigned long offset, size_t size, enum dma_data_direction direction);
-	void (*dma_sync_single_for_device)(struct device *dev, dma_addr_t iova, unsigned long offset, size_t size, enum dma_data_direction direction);
-	void (*dma_sync_sg_for_cpu)(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction direction);
-	void (*dma_sync_sg_for_device)(struct device *dev, struct scatterlist *sg, int nelems, enum dma_data_direction direction);
-};
-
-/*
-** We could live without the hppa_dma_ops indirection if we didn't want
-** to support 4 different coherent dma models with one binary (they will
-** someday be loadable modules):
-**     I/O MMU        consistent method           dma_sync behavior
-**  =============   ======================       =======================
-**  a) PA-7x00LC    uncachable host memory          flush/purge
-**  b) U2/Uturn      cachable host memory              NOP
-**  c) Ike/Astro     cachable host memory              NOP
-**  d) EPIC/SAGA     memory on EPIC/SAGA         flush/reset DMA channel
-**
-** PA-7[13]00LC processors have a GSC bus interface and no I/O MMU.
-**
-** Systems (eg PCX-T workstations) that don't fall into the above
-** categories will need to modify the needed drivers to perform
-** flush/purge and allocate "regular" cacheable pages for everything.
-*/
-
-#ifdef CONFIG_PA11
-extern struct hppa_dma_ops pcxl_dma_ops;
-extern struct hppa_dma_ops pcx_dma_ops;
-#endif
-
-extern struct hppa_dma_ops *hppa_dma_ops;
-
-static inline void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		   gfp_t flag)
-{
-	return hppa_dma_ops->alloc_consistent(dev, size, dma_handle, flag);
-}
-
-static inline void *
-dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		      gfp_t flag)
-{
-	return hppa_dma_ops->alloc_noncoherent(dev, size, dma_handle, flag);
-}
-
-static inline void
-dma_free_coherent(struct device *dev, size_t size, 
-		    void *vaddr, dma_addr_t dma_handle)
-{
-	hppa_dma_ops->free_consistent(dev, size, vaddr, dma_handle);
-}
-
-static inline void
-dma_free_noncoherent(struct device *dev, size_t size, 
-		    void *vaddr, dma_addr_t dma_handle)
-{
-	hppa_dma_ops->free_consistent(dev, size, vaddr, dma_handle);
-}
-
-static inline dma_addr_t
-dma_map_single(struct device *dev, void *ptr, size_t size,
-	       enum dma_data_direction direction)
-{
-	return hppa_dma_ops->map_single(dev, ptr, size, direction);
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction direction)
-{
-	hppa_dma_ops->unmap_single(dev, dma_addr, size, direction);
-}
-
-static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-	   enum dma_data_direction direction)
-{
-	return hppa_dma_ops->map_sg(dev, sg, nents, direction);
-}
-
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-	     enum dma_data_direction direction)
-{
-	hppa_dma_ops->unmap_sg(dev, sg, nhwentries, direction);
-}
-
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page, unsigned long offset,
-	     size_t size, enum dma_data_direction direction)
-{
-	return dma_map_single(dev, (page_address(page) + (offset)), size, direction);
-}
-
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-	       enum dma_data_direction direction)
-{
-	dma_unmap_single(dev, dma_address, size, direction);
-}
-
-
-static inline void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_single_for_cpu)
-		hppa_dma_ops->dma_sync_single_for_cpu(dev, dma_handle, 0, size, direction);
-}
-
-static inline void
-dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_single_for_device)
-		hppa_dma_ops->dma_sync_single_for_device(dev, dma_handle, 0, size, direction);
-}
-
-static inline void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_handle,
-		      unsigned long offset, size_t size,
-		      enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_single_for_cpu)
-		hppa_dma_ops->dma_sync_single_for_cpu(dev, dma_handle, offset, size, direction);
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_handle,
-		      unsigned long offset, size_t size,
-		      enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_single_for_device)
-		hppa_dma_ops->dma_sync_single_for_device(dev, dma_handle, offset, size, direction);
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nelems,
-		 enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_sg_for_cpu)
-		hppa_dma_ops->dma_sync_sg_for_cpu(dev, sg, nelems, direction);
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nelems,
-		 enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_sg_for_device)
-		hppa_dma_ops->dma_sync_sg_for_device(dev, sg, nelems, direction);
-}
-
-static inline int
-dma_supported(struct device *dev, u64 mask)
-{
-	return hppa_dma_ops->dma_supported(dev, mask);
-}
-
-static inline int
-dma_set_mask(struct device *dev, u64 mask)
-{
-	if(!dev->dma_mask || !dma_supported(dev, mask))
-		return -EIO;
-
-	*dev->dma_mask = mask;
-
-	return 0;
-}
-
-static inline int
-dma_get_cache_alignment(void)
-{
-	return dcache_stride;
-}
-
-static inline int
-dma_is_consistent(struct device *dev, dma_addr_t dma_addr)
-{
-	return (hppa_dma_ops->dma_sync_single_for_cpu == NULL);
-}
-
-static inline void
-dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	       enum dma_data_direction direction)
-{
-	if(hppa_dma_ops->dma_sync_single_for_cpu)
-		flush_kernel_dcache_range((unsigned long)vaddr, size);
-}
-
-static inline void *
-parisc_walk_tree(struct device *dev)
-{
-	struct device *otherdev;
-	if(likely(dev->platform_data != NULL))
-		return dev->platform_data;
-	/* OK, just traverse the bus to find it */
-	for(otherdev = dev->parent; otherdev;
-	    otherdev = otherdev->parent) {
-		if(otherdev->platform_data) {
-			dev->platform_data = otherdev->platform_data;
-			break;
-		}
-	}
-	BUG_ON(!dev->platform_data);
-	return dev->platform_data;
-}
-		
-#define GET_IOC(dev) (HBA_DATA(parisc_walk_tree(dev))->iommu);	
-	
-
-#ifdef CONFIG_IOMMU_CCIO
-struct parisc_device;
-struct ioc;
-void * ccio_get_iommu(const struct parisc_device *dev);
-int ccio_request_resource(const struct parisc_device *dev,
-		struct resource *res);
-int ccio_allocate_resource(const struct parisc_device *dev,
-		struct resource *res, unsigned long size,
-		unsigned long min, unsigned long max, unsigned long align);
-#else /* !CONFIG_IOMMU_CCIO */
-#define ccio_get_iommu(dev) NULL
-#define ccio_request_resource(dev, res) insert_resource(&iomem_resource, res)
-#define ccio_allocate_resource(dev, res, size, min, max, align) \
-		allocate_resource(&iomem_resource, res, size, min, max, \
-				align, NULL, NULL)
-#endif /* !CONFIG_IOMMU_CCIO */
-
-#ifdef CONFIG_IOMMU_SBA
-struct parisc_device;
-void * sba_get_iommu(struct parisc_device *dev);
-#endif
-
-/* At the moment, we panic on error for IOMMU resource exaustion */
-#define dma_mapping_error(dev, x)	0
-
-#endif
diff --git a/include/asm-parisc/dma.h b/include/asm-parisc/dma.h
deleted file mode 100644
index 31ad0f05af3d..000000000000
--- a/include/asm-parisc/dma.h
+++ /dev/null
@@ -1,186 +0,0 @@
-/* $Id: dma.h,v 1.2 1999/04/27 00:46:18 deller Exp $
- * linux/include/asm/dma.h: Defines for using and allocating dma channels.
- * Written by Hennus Bergman, 1992.
- * High DMA channel support & info by Hannu Savolainen
- * and John Boyd, Nov. 1992.
- * (c) Copyright 2000, Grant Grundler
- */
-
-#ifndef _ASM_DMA_H
-#define _ASM_DMA_H
-
-#include <asm/io.h>		/* need byte IO */
-#include <asm/system.h>	
-
-#define dma_outb	outb
-#define dma_inb		inb
-
-/*
-** DMA_CHUNK_SIZE is used by the SCSI mid-layer to break up
-** (or rather not merge) DMAs into manageable chunks.
-** On parisc, this is more of the software/tuning constraint
-** rather than the HW. I/O MMU allocation algorithms can be
-** faster with smaller sizes (to some degree).
-*/
-#define DMA_CHUNK_SIZE	(BITS_PER_LONG*PAGE_SIZE)
-
-/* The maximum address that we can perform a DMA transfer to on this platform
-** New dynamic DMA interfaces should obsolete this....
-*/
-#define MAX_DMA_ADDRESS (~0UL)
-
-/*
-** We don't have DMA channels... well V-class does but the
-** Dynamic DMA Mapping interface will support them... right? :^)
-** Note: this is not relevant right now for PA-RISC, but we cannot 
-** leave this as undefined because some things (e.g. sound)
-** won't compile :-(
-*/
-#define MAX_DMA_CHANNELS 8
-#define DMA_MODE_READ	0x44	/* I/O to memory, no autoinit, increment, single mode */
-#define DMA_MODE_WRITE	0x48	/* memory to I/O, no autoinit, increment, single mode */
-#define DMA_MODE_CASCADE 0xC0	/* pass thru DREQ->HRQ, DACK<-HLDA only */
-
-#define DMA_AUTOINIT	0x10
-
-/* 8237 DMA controllers */
-#define IO_DMA1_BASE	0x00	/* 8 bit slave DMA, channels 0..3 */
-#define IO_DMA2_BASE	0xC0	/* 16 bit master DMA, ch 4(=slave input)..7 */
-
-/* DMA controller registers */
-#define DMA1_CMD_REG		0x08	/* command register (w) */
-#define DMA1_STAT_REG		0x08	/* status register (r) */
-#define DMA1_REQ_REG            0x09    /* request register (w) */
-#define DMA1_MASK_REG		0x0A	/* single-channel mask (w) */
-#define DMA1_MODE_REG		0x0B	/* mode register (w) */
-#define DMA1_CLEAR_FF_REG	0x0C	/* clear pointer flip-flop (w) */
-#define DMA1_TEMP_REG           0x0D    /* Temporary Register (r) */
-#define DMA1_RESET_REG		0x0D	/* Master Clear (w) */
-#define DMA1_CLR_MASK_REG       0x0E    /* Clear Mask */
-#define DMA1_MASK_ALL_REG       0x0F    /* all-channels mask (w) */
-#define DMA1_EXT_MODE_REG	(0x400 | DMA1_MODE_REG)
-
-#define DMA2_CMD_REG		0xD0	/* command register (w) */
-#define DMA2_STAT_REG		0xD0	/* status register (r) */
-#define DMA2_REQ_REG            0xD2    /* request register (w) */
-#define DMA2_MASK_REG		0xD4	/* single-channel mask (w) */
-#define DMA2_MODE_REG		0xD6	/* mode register (w) */
-#define DMA2_CLEAR_FF_REG	0xD8	/* clear pointer flip-flop (w) */
-#define DMA2_TEMP_REG           0xDA    /* Temporary Register (r) */
-#define DMA2_RESET_REG		0xDA	/* Master Clear (w) */
-#define DMA2_CLR_MASK_REG       0xDC    /* Clear Mask */
-#define DMA2_MASK_ALL_REG       0xDE    /* all-channels mask (w) */
-#define DMA2_EXT_MODE_REG	(0x400 | DMA2_MODE_REG)
-
-static __inline__ unsigned long claim_dma_lock(void)
-{
-	return 0;
-}
-
-static __inline__ void release_dma_lock(unsigned long flags)
-{
-}
-
-
-/* Get DMA residue count. After a DMA transfer, this
- * should return zero. Reading this while a DMA transfer is
- * still in progress will return unpredictable results.
- * If called before the channel has been used, it may return 1.
- * Otherwise, it returns the number of _bytes_ left to transfer.
- *
- * Assumes DMA flip-flop is clear.
- */
-static __inline__ int get_dma_residue(unsigned int dmanr)
-{
-	unsigned int io_port = (dmanr<=3)? ((dmanr&3)<<1) + 1 + IO_DMA1_BASE
-					 : ((dmanr&3)<<2) + 2 + IO_DMA2_BASE;
-
-	/* using short to get 16-bit wrap around */
-	unsigned short count;
-
-	count = 1 + dma_inb(io_port);
-	count += dma_inb(io_port) << 8;
-	
-	return (dmanr<=3)? count : (count<<1);
-}
-
-/* enable/disable a specific DMA channel */
-static __inline__ void enable_dma(unsigned int dmanr)
-{
-#ifdef CONFIG_SUPERIO
-	if (dmanr<=3)
-		dma_outb(dmanr,  DMA1_MASK_REG);
-	else
-		dma_outb(dmanr & 3,  DMA2_MASK_REG);
-#endif
-}
-
-static __inline__ void disable_dma(unsigned int dmanr)
-{
-#ifdef CONFIG_SUPERIO
-	if (dmanr<=3)
-		dma_outb(dmanr | 4,  DMA1_MASK_REG);
-	else
-		dma_outb((dmanr & 3) | 4,  DMA2_MASK_REG);
-#endif
-}
-
-/* reserve a DMA channel */
-#define request_dma(dmanr, device_id)	(0)
-
-/* Clear the 'DMA Pointer Flip Flop'.
- * Write 0 for LSB/MSB, 1 for MSB/LSB access.
- * Use this once to initialize the FF to a known state.
- * After that, keep track of it. :-)
- * --- In order to do that, the DMA routines below should ---
- * --- only be used while holding the DMA lock ! ---
- */
-static __inline__ void clear_dma_ff(unsigned int dmanr)
-{
-}
-
-/* set mode (above) for a specific DMA channel */
-static __inline__ void set_dma_mode(unsigned int dmanr, char mode)
-{
-}
-
-/* Set only the page register bits of the transfer address.
- * This is used for successive transfers when we know the contents of
- * the lower 16 bits of the DMA current address register, but a 64k boundary
- * may have been crossed.
- */
-static __inline__ void set_dma_page(unsigned int dmanr, char pagenr)
-{
-}
-
-
-/* Set transfer address & page bits for specific DMA channel.
- * Assumes dma flipflop is clear.
- */
-static __inline__ void set_dma_addr(unsigned int dmanr, unsigned int a)
-{
-}
-
-
-/* Set transfer size (max 64k for DMA1..3, 128k for DMA5..7) for
- * a specific DMA channel.
- * You must ensure the parameters are valid.
- * NOTE: from a manual: "the number of transfers is one more
- * than the initial word count"! This is taken into account.
- * Assumes dma flip-flop is clear.
- * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7.
- */
-static __inline__ void set_dma_count(unsigned int dmanr, unsigned int count)
-{
-}
-
-
-#define free_dma(dmanr)
-
-#ifdef CONFIG_PCI
-extern int isa_dma_bridge_buggy;
-#else
-#define isa_dma_bridge_buggy 	(0)
-#endif
-
-#endif /* _ASM_DMA_H */
diff --git a/include/asm-parisc/eisa_bus.h b/include/asm-parisc/eisa_bus.h
deleted file mode 100644
index 201085f83dd5..000000000000
--- a/include/asm-parisc/eisa_bus.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * eisa_bus.h interface between the eisa BA driver and the bus enumerator
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- * Copyright (c) 2002 Daniel Engstrom <5116@telia.com>
- *
- */
-
-#ifndef ASM_EISA_H
-#define ASM_EISA_H
-
-extern void eisa_make_irq_level(int num);
-extern void eisa_make_irq_edge(int num);
-extern int eisa_enumerator(unsigned long eeprom_addr,
-			   struct resource *io_parent, 
-			   struct resource *mem_parent);
-extern int eisa_eeprom_init(unsigned long addr);
-
-#endif
diff --git a/include/asm-parisc/eisa_eeprom.h b/include/asm-parisc/eisa_eeprom.h
deleted file mode 100644
index 9c9da980402a..000000000000
--- a/include/asm-parisc/eisa_eeprom.h
+++ /dev/null
@@ -1,153 +0,0 @@
-/*
- * eisa_eeprom.h - provide support for EISA adapters in PA-RISC machines
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
- * Copyright (c) 2001, 2002 Daniel Engstrom <5116@telia.com>
- *
- */
-
-#ifndef ASM_EISA_EEPROM_H
-#define ASM_EISA_EEPROM_H
-
-extern void __iomem *eisa_eeprom_addr;
-
-#define HPEE_MAX_LENGTH       0x2000	/* maximum eeprom length */
-
-#define HPEE_SLOT_INFO(slot) (20+(48*slot))
-
-struct eeprom_header 
-{
-   
-	u_int32_t num_writes;       /* number of writes */
- 	u_int8_t  flags;            /* flags, usage? */
-	u_int8_t  ver_maj;
-	u_int8_t  ver_min;
-	u_int8_t  num_slots;        /* number of EISA slots in system */
-	u_int16_t csum;             /* checksum, I don't know how to calulate this */
-	u_int8_t  pad[10];
-} __attribute__ ((packed));
-
-
-struct eeprom_eisa_slot_info
-{
-	u_int32_t eisa_slot_id;
-	u_int32_t config_data_offset;
-	u_int32_t num_writes;
-	u_int16_t csum;
-	u_int16_t num_functions;
-	u_int16_t config_data_length;
-	
-	/* bits 0..3 are the duplicate slot id */ 
-#define HPEE_SLOT_INFO_EMBEDDED  0x10
-#define HPEE_SLOT_INFO_VIRTUAL   0x20
-#define HPEE_SLOT_INFO_NO_READID 0x40
-#define HPEE_SLOT_INFO_DUPLICATE 0x80
-	u_int8_t slot_info;
-	
-#define HPEE_SLOT_FEATURES_ENABLE         0x01
-#define HPEE_SLOT_FEATURES_IOCHK          0x02
-#define HPEE_SLOT_FEATURES_CFG_INCOMPLETE 0x80
-	u_int8_t slot_features;
-	
-	u_int8_t  ver_min;
-	u_int8_t  ver_maj;
-	
-#define HPEE_FUNCTION_INFO_HAVE_TYPE      0x01
-#define HPEE_FUNCTION_INFO_HAVE_MEMORY    0x02
-#define HPEE_FUNCTION_INFO_HAVE_IRQ       0x04
-#define HPEE_FUNCTION_INFO_HAVE_DMA       0x08
-#define HPEE_FUNCTION_INFO_HAVE_PORT      0x10
-#define HPEE_FUNCTION_INFO_HAVE_PORT_INIT 0x20
-/* I think there are two slighty different 
- * versions of the function_info field 
- * one int the fixed header and one optional 
- * in the parsed slot data area */
-#define HPEE_FUNCTION_INFO_HAVE_FUNCTION  0x01
-#define HPEE_FUNCTION_INFO_F_DISABLED     0x80
-#define HPEE_FUNCTION_INFO_CFG_FREE_FORM  0x40
-	u_int8_t  function_info;
-
-#define HPEE_FLAG_BOARD_IS_ISA		  0x01 /* flag and minor version for isa board */
-	u_int8_t  flags;
-	u_int8_t  pad[24];
-} __attribute__ ((packed));
-
-
-#define HPEE_MEMORY_MAX_ENT   9
-/* memory descriptor: byte 0 */
-#define HPEE_MEMORY_WRITABLE  0x01
-#define HPEE_MEMORY_CACHABLE  0x02
-#define HPEE_MEMORY_TYPE_MASK 0x18
-#define HPEE_MEMORY_TYPE_SYS  0x00
-#define HPEE_MEMORY_TYPE_EXP  0x08
-#define HPEE_MEMORY_TYPE_VIR  0x10
-#define HPEE_MEMORY_TYPE_OTH  0x18
-#define HPEE_MEMORY_SHARED    0x20
-#define HPEE_MEMORY_MORE      0x80
-
-/* memory descriptor: byte 1 */
-#define HPEE_MEMORY_WIDTH_MASK 0x03
-#define HPEE_MEMORY_WIDTH_BYTE 0x00
-#define HPEE_MEMORY_WIDTH_WORD 0x01
-#define HPEE_MEMORY_WIDTH_DWORD 0x02
-#define HPEE_MEMORY_DECODE_MASK 0x0c
-#define HPEE_MEMORY_DECODE_20BITS 0x00
-#define HPEE_MEMORY_DECODE_24BITS 0x04
-#define HPEE_MEMORY_DECODE_32BITS 0x08
-/* byte 2 and 3 are a 16bit LE value
- * containging the memory size in kilobytes */
-/* byte 4,5,6 are a 24bit LE value
- * containing the memory base address */
-
-
-#define HPEE_IRQ_MAX_ENT      7
-/* Interrupt entry: byte 0 */
-#define HPEE_IRQ_CHANNEL_MASK 0xf
-#define HPEE_IRQ_TRIG_LEVEL   0x20
-#define HPEE_IRQ_MORE         0x80
-/* byte 1 seems to be unused */
-
-#define HPEE_DMA_MAX_ENT     4
-
-/* dma entry: byte 0 */
-#define HPEE_DMA_CHANNEL_MASK 7
-#define HPEE_DMA_SIZE_MASK	0xc
-#define HPEE_DMA_SIZE_BYTE	0x0
-#define HPEE_DMA_SIZE_WORD	0x4
-#define HPEE_DMA_SIZE_DWORD	0x8
-#define HPEE_DMA_SHARED      0x40
-#define HPEE_DMA_MORE        0x80
-
-/* dma entry: byte 1 */
-#define HPEE_DMA_TIMING_MASK 0x30
-#define HPEE_DMA_TIMING_ISA	0x0
-#define HPEE_DMA_TIMING_TYPEA 0x10
-#define HPEE_DMA_TIMING_TYPEB 0x20
-#define HPEE_DMA_TIMING_TYPEC 0x30
-
-#define HPEE_PORT_MAX_ENT 20
-/* port entry byte 0 */
-#define HPEE_PORT_SIZE_MASK 0x1f
-#define HPEE_PORT_SHARED    0x40
-#define HPEE_PORT_MORE      0x80
-/* byte 1 and 2 is a 16bit LE value
- * conating the start port number */
-
-#define HPEE_PORT_INIT_MAX_LEN     60 /* in bytes here */
-/* port init entry byte 0 */
-#define HPEE_PORT_INIT_WIDTH_MASK  0x3
-#define HPEE_PORT_INIT_WIDTH_BYTE  0x0
-#define HPEE_PORT_INIT_WIDTH_WORD  0x1
-#define HPEE_PORT_INIT_WIDTH_DWORD 0x2
-#define HPEE_PORT_INIT_MASK        0x4
-#define HPEE_PORT_INIT_MORE        0x80
-
-#define HPEE_SELECTION_MAX_ENT 26
-
-#define HPEE_TYPE_MAX_LEN    80
-
-#endif
diff --git a/include/asm-parisc/elf.h b/include/asm-parisc/elf.h
deleted file mode 100644
index d0a4a8262818..000000000000
--- a/include/asm-parisc/elf.h
+++ /dev/null
@@ -1,342 +0,0 @@
-#ifndef __ASMPARISC_ELF_H
-#define __ASMPARISC_ELF_H
-
-/*
- * ELF register definitions..
- */
-
-#include <asm/ptrace.h>
-
-#define EM_PARISC 15
-
-/* HPPA specific definitions.  */
-
-/* Legal values for e_flags field of Elf32_Ehdr.  */
-
-#define EF_PARISC_TRAPNIL	0x00010000 /* Trap nil pointer dereference.  */
-#define EF_PARISC_EXT		0x00020000 /* Program uses arch. extensions. */
-#define EF_PARISC_LSB		0x00040000 /* Program expects little endian. */
-#define EF_PARISC_WIDE		0x00080000 /* Program expects wide mode.  */
-#define EF_PARISC_NO_KABP	0x00100000 /* No kernel assisted branch
-					      prediction.  */
-#define EF_PARISC_LAZYSWAP	0x00400000 /* Allow lazy swapping.  */
-#define EF_PARISC_ARCH		0x0000ffff /* Architecture version.  */
-
-/* Defined values for `e_flags & EF_PARISC_ARCH' are:  */
-
-#define EFA_PARISC_1_0		    0x020b /* PA-RISC 1.0 big-endian.  */
-#define EFA_PARISC_1_1		    0x0210 /* PA-RISC 1.1 big-endian.  */
-#define EFA_PARISC_2_0		    0x0214 /* PA-RISC 2.0 big-endian.  */
-
-/* Additional section indices.  */
-
-#define SHN_PARISC_ANSI_COMMON	0xff00	   /* Section for tenatively declared
-					      symbols in ANSI C.  */
-#define SHN_PARISC_HUGE_COMMON	0xff01	   /* Common blocks in huge model.  */
-
-/* Legal values for sh_type field of Elf32_Shdr.  */
-
-#define SHT_PARISC_EXT		0x70000000 /* Contains product specific ext. */
-#define SHT_PARISC_UNWIND	0x70000001 /* Unwind information.  */
-#define SHT_PARISC_DOC		0x70000002 /* Debug info for optimized code. */
-
-/* Legal values for sh_flags field of Elf32_Shdr.  */
-
-#define SHF_PARISC_SHORT	0x20000000 /* Section with short addressing. */
-#define SHF_PARISC_HUGE		0x40000000 /* Section far from gp.  */
-#define SHF_PARISC_SBP		0x80000000 /* Static branch prediction code. */
-
-/* Legal values for ST_TYPE subfield of st_info (symbol type).  */
-
-#define STT_PARISC_MILLICODE	13	/* Millicode function entry point.  */
-
-#define STT_HP_OPAQUE		(STT_LOOS + 0x1)
-#define STT_HP_STUB		(STT_LOOS + 0x2)
-
-/* HPPA relocs.  */
-
-#define R_PARISC_NONE		0	/* No reloc.  */
-#define R_PARISC_DIR32		1	/* Direct 32-bit reference.  */
-#define R_PARISC_DIR21L		2	/* Left 21 bits of eff. address.  */
-#define R_PARISC_DIR17R		3	/* Right 17 bits of eff. address.  */
-#define R_PARISC_DIR17F		4	/* 17 bits of eff. address.  */
-#define R_PARISC_DIR14R		6	/* Right 14 bits of eff. address.  */
-#define R_PARISC_PCREL32	9	/* 32-bit rel. address.  */
-#define R_PARISC_PCREL21L	10	/* Left 21 bits of rel. address.  */
-#define R_PARISC_PCREL17R	11	/* Right 17 bits of rel. address.  */
-#define R_PARISC_PCREL17F	12	/* 17 bits of rel. address.  */
-#define R_PARISC_PCREL14R	14	/* Right 14 bits of rel. address.  */
-#define R_PARISC_DPREL21L	18	/* Left 21 bits of rel. address.  */
-#define R_PARISC_DPREL14R	22	/* Right 14 bits of rel. address.  */
-#define R_PARISC_GPREL21L	26	/* GP-relative, left 21 bits.  */
-#define R_PARISC_GPREL14R	30	/* GP-relative, right 14 bits.  */
-#define R_PARISC_LTOFF21L	34	/* LT-relative, left 21 bits.  */
-#define R_PARISC_LTOFF14R	38	/* LT-relative, right 14 bits.  */
-#define R_PARISC_SECREL32	41	/* 32 bits section rel. address.  */
-#define R_PARISC_SEGBASE	48	/* No relocation, set segment base.  */
-#define R_PARISC_SEGREL32	49	/* 32 bits segment rel. address.  */
-#define R_PARISC_PLTOFF21L	50	/* PLT rel. address, left 21 bits.  */
-#define R_PARISC_PLTOFF14R	54	/* PLT rel. address, right 14 bits.  */
-#define R_PARISC_LTOFF_FPTR32	57	/* 32 bits LT-rel. function pointer. */
-#define R_PARISC_LTOFF_FPTR21L	58	/* LT-rel. fct ptr, left 21 bits. */
-#define R_PARISC_LTOFF_FPTR14R	62	/* LT-rel. fct ptr, right 14 bits. */
-#define R_PARISC_FPTR64		64	/* 64 bits function address.  */
-#define R_PARISC_PLABEL32	65	/* 32 bits function address.  */
-#define R_PARISC_PCREL64	72	/* 64 bits PC-rel. address.  */
-#define R_PARISC_PCREL22F	74	/* 22 bits PC-rel. address.  */
-#define R_PARISC_PCREL14WR	75	/* PC-rel. address, right 14 bits.  */
-#define R_PARISC_PCREL14DR	76	/* PC rel. address, right 14 bits.  */
-#define R_PARISC_PCREL16F	77	/* 16 bits PC-rel. address.  */
-#define R_PARISC_PCREL16WF	78	/* 16 bits PC-rel. address.  */
-#define R_PARISC_PCREL16DF	79	/* 16 bits PC-rel. address.  */
-#define R_PARISC_DIR64		80	/* 64 bits of eff. address.  */
-#define R_PARISC_DIR14WR	83	/* 14 bits of eff. address.  */
-#define R_PARISC_DIR14DR	84	/* 14 bits of eff. address.  */
-#define R_PARISC_DIR16F		85	/* 16 bits of eff. address.  */
-#define R_PARISC_DIR16WF	86	/* 16 bits of eff. address.  */
-#define R_PARISC_DIR16DF	87	/* 16 bits of eff. address.  */
-#define R_PARISC_GPREL64	88	/* 64 bits of GP-rel. address.  */
-#define R_PARISC_GPREL14WR	91	/* GP-rel. address, right 14 bits.  */
-#define R_PARISC_GPREL14DR	92	/* GP-rel. address, right 14 bits.  */
-#define R_PARISC_GPREL16F	93	/* 16 bits GP-rel. address.  */
-#define R_PARISC_GPREL16WF	94	/* 16 bits GP-rel. address.  */
-#define R_PARISC_GPREL16DF	95	/* 16 bits GP-rel. address.  */
-#define R_PARISC_LTOFF64	96	/* 64 bits LT-rel. address.  */
-#define R_PARISC_LTOFF14WR	99	/* LT-rel. address, right 14 bits.  */
-#define R_PARISC_LTOFF14DR	100	/* LT-rel. address, right 14 bits.  */
-#define R_PARISC_LTOFF16F	101	/* 16 bits LT-rel. address.  */
-#define R_PARISC_LTOFF16WF	102	/* 16 bits LT-rel. address.  */
-#define R_PARISC_LTOFF16DF	103	/* 16 bits LT-rel. address.  */
-#define R_PARISC_SECREL64	104	/* 64 bits section rel. address.  */
-#define R_PARISC_SEGREL64	112	/* 64 bits segment rel. address.  */
-#define R_PARISC_PLTOFF14WR	115	/* PLT-rel. address, right 14 bits.  */
-#define R_PARISC_PLTOFF14DR	116	/* PLT-rel. address, right 14 bits.  */
-#define R_PARISC_PLTOFF16F	117	/* 16 bits LT-rel. address.  */
-#define R_PARISC_PLTOFF16WF	118	/* 16 bits PLT-rel. address.  */
-#define R_PARISC_PLTOFF16DF	119	/* 16 bits PLT-rel. address.  */
-#define R_PARISC_LTOFF_FPTR64	120	/* 64 bits LT-rel. function ptr.  */
-#define R_PARISC_LTOFF_FPTR14WR	123	/* LT-rel. fct. ptr., right 14 bits. */
-#define R_PARISC_LTOFF_FPTR14DR	124	/* LT-rel. fct. ptr., right 14 bits. */
-#define R_PARISC_LTOFF_FPTR16F	125	/* 16 bits LT-rel. function ptr.  */
-#define R_PARISC_LTOFF_FPTR16WF	126	/* 16 bits LT-rel. function ptr.  */
-#define R_PARISC_LTOFF_FPTR16DF	127	/* 16 bits LT-rel. function ptr.  */
-#define R_PARISC_LORESERVE	128
-#define R_PARISC_COPY		128	/* Copy relocation.  */
-#define R_PARISC_IPLT		129	/* Dynamic reloc, imported PLT */
-#define R_PARISC_EPLT		130	/* Dynamic reloc, exported PLT */
-#define R_PARISC_TPREL32	153	/* 32 bits TP-rel. address.  */
-#define R_PARISC_TPREL21L	154	/* TP-rel. address, left 21 bits.  */
-#define R_PARISC_TPREL14R	158	/* TP-rel. address, right 14 bits.  */
-#define R_PARISC_LTOFF_TP21L	162	/* LT-TP-rel. address, left 21 bits. */
-#define R_PARISC_LTOFF_TP14R	166	/* LT-TP-rel. address, right 14 bits.*/
-#define R_PARISC_LTOFF_TP14F	167	/* 14 bits LT-TP-rel. address.  */
-#define R_PARISC_TPREL64	216	/* 64 bits TP-rel. address.  */
-#define R_PARISC_TPREL14WR	219	/* TP-rel. address, right 14 bits.  */
-#define R_PARISC_TPREL14DR	220	/* TP-rel. address, right 14 bits.  */
-#define R_PARISC_TPREL16F	221	/* 16 bits TP-rel. address.  */
-#define R_PARISC_TPREL16WF	222	/* 16 bits TP-rel. address.  */
-#define R_PARISC_TPREL16DF	223	/* 16 bits TP-rel. address.  */
-#define R_PARISC_LTOFF_TP64	224	/* 64 bits LT-TP-rel. address.  */
-#define R_PARISC_LTOFF_TP14WR	227	/* LT-TP-rel. address, right 14 bits.*/
-#define R_PARISC_LTOFF_TP14DR	228	/* LT-TP-rel. address, right 14 bits.*/
-#define R_PARISC_LTOFF_TP16F	229	/* 16 bits LT-TP-rel. address.  */
-#define R_PARISC_LTOFF_TP16WF	230	/* 16 bits LT-TP-rel. address.  */
-#define R_PARISC_LTOFF_TP16DF	231	/* 16 bits LT-TP-rel. address.  */
-#define R_PARISC_HIRESERVE	255
-
-#define PA_PLABEL_FDESC		0x02	/* bit set if PLABEL points to
-					 * a function descriptor, not
-					 * an address */
-
-/* The following are PA function descriptors 
- *
- * addr:	the absolute address of the function
- * gp:		either the data pointer (r27) for non-PIC code or the
- *		the PLT pointer (r19) for PIC code */
-
-/* Format for the Elf32 Function descriptor */
-typedef struct elf32_fdesc {
-	__u32	addr;
-	__u32	gp;
-} Elf32_Fdesc;
-
-/* Format for the Elf64 Function descriptor */
-typedef struct elf64_fdesc {
-	__u64	dummy[2]; /* FIXME: nothing uses these, why waste
-			   * the space */
-	__u64	addr;
-	__u64	gp;
-} Elf64_Fdesc;
-
-/* Legal values for p_type field of Elf32_Phdr/Elf64_Phdr.  */
-
-#define PT_HP_TLS		(PT_LOOS + 0x0)
-#define PT_HP_CORE_NONE		(PT_LOOS + 0x1)
-#define PT_HP_CORE_VERSION	(PT_LOOS + 0x2)
-#define PT_HP_CORE_KERNEL	(PT_LOOS + 0x3)
-#define PT_HP_CORE_COMM		(PT_LOOS + 0x4)
-#define PT_HP_CORE_PROC		(PT_LOOS + 0x5)
-#define PT_HP_CORE_LOADABLE	(PT_LOOS + 0x6)
-#define PT_HP_CORE_STACK	(PT_LOOS + 0x7)
-#define PT_HP_CORE_SHM		(PT_LOOS + 0x8)
-#define PT_HP_CORE_MMF		(PT_LOOS + 0x9)
-#define PT_HP_PARALLEL		(PT_LOOS + 0x10)
-#define PT_HP_FASTBIND		(PT_LOOS + 0x11)
-#define PT_HP_OPT_ANNOT		(PT_LOOS + 0x12)
-#define PT_HP_HSL_ANNOT		(PT_LOOS + 0x13)
-#define PT_HP_STACK		(PT_LOOS + 0x14)
-
-#define PT_PARISC_ARCHEXT	0x70000000
-#define PT_PARISC_UNWIND	0x70000001
-
-/* Legal values for p_flags field of Elf32_Phdr/Elf64_Phdr.  */
-
-#define PF_PARISC_SBP		0x08000000
-
-#define PF_HP_PAGE_SIZE		0x00100000
-#define PF_HP_FAR_SHARED	0x00200000
-#define PF_HP_NEAR_SHARED	0x00400000
-#define PF_HP_CODE		0x01000000
-#define PF_HP_MODIFY		0x02000000
-#define PF_HP_LAZYSWAP		0x04000000
-#define PF_HP_SBP		0x08000000
-
-/*
- * The following definitions are those for 32-bit ELF binaries on a 32-bit
- * kernel and for 64-bit binaries on a 64-bit kernel.  To run 32-bit binaries
- * on a 64-bit kernel, arch/parisc/kernel/binfmt_elf32.c defines these
- * macros appropriately and then #includes binfmt_elf.c, which then includes
- * this file.
- */
-#ifndef ELF_CLASS
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- *
- * Note that this header file is used by default in fs/binfmt_elf.c. So
- * the following macros are for the default case. However, for the 64
- * bit kernel we also support 32 bit parisc binaries. To do that
- * arch/parisc/kernel/binfmt_elf32.c defines its own set of these
- * macros, and then it includes fs/binfmt_elf.c to provide an alternate
- * elf binary handler for 32 bit binaries (on the 64 bit kernel).
- */
-#ifdef CONFIG_64BIT
-#define ELF_CLASS   ELFCLASS64
-#else
-#define ELF_CLASS	ELFCLASS32
-#endif
-
-typedef unsigned long elf_greg_t;
-
-/*
- * This yields a string that ld.so will use to load implementation
- * specific libraries for optimization.  This is more specific in
- * intent than poking at uname or /proc/cpuinfo.
- */
-
-#define ELF_PLATFORM  ("PARISC\0")
-
-#define SET_PERSONALITY(ex, ibcs2) \
-	current->personality = PER_LINUX; \
-	current->thread.map_base = DEFAULT_MAP_BASE; \
-	current->thread.task_size = DEFAULT_TASK_SIZE \
-
-/*
- * Fill in general registers in a core dump.  This saves pretty
- * much the same registers as hp-ux, although in a different order.
- * Registers marked # below are not currently saved in pt_regs, so
- * we use their current values here.
- *
- * 	gr0..gr31
- * 	sr0..sr7
- * 	iaoq0..iaoq1
- * 	iasq0..iasq1
- * 	cr11 (sar)
- * 	cr19 (iir)
- * 	cr20 (isr)
- * 	cr21 (ior)
- *  #	cr22 (ipsw)
- *  #	cr0 (recovery counter)
- *  #	cr24..cr31 (temporary registers)
- *  #	cr8,9,12,13 (protection IDs)
- *  #	cr10 (scr/ccr)
- *  #	cr15 (ext int enable mask)
- *
- */
-
-#define ELF_CORE_COPY_REGS(dst, pt)	\
-	memset(dst, 0, sizeof(dst));	/* don't leak any "random" bits */ \
-	memcpy(dst + 0, pt->gr, 32 * sizeof(elf_greg_t)); \
-	memcpy(dst + 32, pt->sr, 8 * sizeof(elf_greg_t)); \
-	memcpy(dst + 40, pt->iaoq, 2 * sizeof(elf_greg_t)); \
-	memcpy(dst + 42, pt->iasq, 2 * sizeof(elf_greg_t)); \
-	dst[44] = pt->sar;   dst[45] = pt->iir; \
-	dst[46] = pt->isr;   dst[47] = pt->ior; \
-	dst[48] = mfctl(22); dst[49] = mfctl(0); \
-	dst[50] = mfctl(24); dst[51] = mfctl(25); \
-	dst[52] = mfctl(26); dst[53] = mfctl(27); \
-	dst[54] = mfctl(28); dst[55] = mfctl(29); \
-	dst[56] = mfctl(30); dst[57] = mfctl(31); \
-	dst[58] = mfctl( 8); dst[59] = mfctl( 9); \
-	dst[60] = mfctl(12); dst[61] = mfctl(13); \
-	dst[62] = mfctl(10); dst[63] = mfctl(15);
-
-#endif /* ! ELF_CLASS */
-
-#define ELF_NGREG 80	/* We only need 64 at present, but leave space
-			   for expansion. */
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-#define ELF_NFPREG 32
-typedef double elf_fpreg_t;
-typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
-
-struct task_struct;
-
-extern int dump_task_fpu (struct task_struct *, elf_fpregset_t *);
-#define ELF_CORE_COPY_FPREGS(tsk, elf_fpregs) dump_task_fpu(tsk, elf_fpregs)
-
-struct pt_regs;	/* forward declaration... */
-
-
-#define elf_check_arch(x) ((x)->e_machine == EM_PARISC && (x)->e_ident[EI_CLASS] == ELF_CLASS)
-
-/*
- * These are used to set parameters in the core dumps.
- */
-#define ELF_DATA	ELFDATA2MSB
-#define ELF_ARCH	EM_PARISC
-#define ELF_OSABI 	ELFOSABI_LINUX
-
-/* %r23 is set by ld.so to a pointer to a function which might be 
-   registered using atexit.  This provides a means for the dynamic
-   linker to call DT_FINI functions for shared libraries that have
-   been loaded before the code runs.
-
-   So that we can use the same startup file with static executables,
-   we start programs with a value of 0 to indicate that there is no
-   such function.  */
-#define ELF_PLAT_INIT(_r, load_addr)       _r->gr[23] = 0
-
-#define USE_ELF_CORE_DUMP
-#define ELF_EXEC_PAGESIZE	4096
-
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.
-
-   (2 * TASK_SIZE / 3) turns into something undefined when run through a
-   32 bit preprocessor and in some cases results in the kernel trying to map
-   ld.so to the kernel virtual base. Use a sane value instead. /Jes 
-  */
-
-#define ELF_ET_DYN_BASE         (TASK_UNMAPPED_BASE + 0x01000000)
-
-/* This yields a mask that user programs can use to figure out what
-   instruction set this CPU supports.  This could be done in user space,
-   but it's not easy, and we've already done it here.  */
-
-#define ELF_HWCAP	0
-
-#endif
diff --git a/include/asm-parisc/emergency-restart.h b/include/asm-parisc/emergency-restart.h
deleted file mode 100644
index 108d8c48e42e..000000000000
--- a/include/asm-parisc/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/include/asm-parisc/errno.h b/include/asm-parisc/errno.h
deleted file mode 100644
index e2f3ddc796be..000000000000
--- a/include/asm-parisc/errno.h
+++ /dev/null
@@ -1,124 +0,0 @@
-#ifndef _PARISC_ERRNO_H
-#define _PARISC_ERRNO_H
-
-#include <asm-generic/errno-base.h>
-
-#define	ENOMSG		35	/* No message of desired type */
-#define	EIDRM		36	/* Identifier removed */
-#define	ECHRNG		37	/* Channel number out of range */
-#define	EL2NSYNC	38	/* Level 2 not synchronized */
-#define	EL3HLT		39	/* Level 3 halted */
-#define	EL3RST		40	/* Level 3 reset */
-#define	ELNRNG		41	/* Link number out of range */
-#define	EUNATCH		42	/* Protocol driver not attached */
-#define	ENOCSI		43	/* No CSI structure available */
-#define	EL2HLT		44	/* Level 2 halted */
-#define	EDEADLK		45	/* Resource deadlock would occur */
-#define	EDEADLOCK	EDEADLK
-#define	ENOLCK		46	/* No record locks available */
-#define	EILSEQ		47	/* Illegal byte sequence */
-
-#define	ENONET		50	/* Machine is not on the network */
-#define	ENODATA		51	/* No data available */
-#define	ETIME		52	/* Timer expired */
-#define	ENOSR		53	/* Out of streams resources */
-#define	ENOSTR		54	/* Device not a stream */
-#define	ENOPKG		55	/* Package not installed */
-
-#define	ENOLINK		57	/* Link has been severed */
-#define	EADV		58	/* Advertise error */
-#define	ESRMNT		59	/* Srmount error */
-#define	ECOMM		60	/* Communication error on send */
-#define	EPROTO		61	/* Protocol error */
-
-#define	EMULTIHOP	64	/* Multihop attempted */
-
-#define	EDOTDOT		66	/* RFS specific error */
-#define	EBADMSG		67	/* Not a data message */
-#define	EUSERS		68	/* Too many users */
-#define	EDQUOT		69	/* Quota exceeded */
-#define	ESTALE		70	/* Stale NFS file handle */
-#define	EREMOTE		71	/* Object is remote */
-#define	EOVERFLOW	72	/* Value too large for defined data type */
-
-/* these errnos are defined by Linux but not HPUX. */
-
-#define	EBADE		160	/* Invalid exchange */
-#define	EBADR		161	/* Invalid request descriptor */
-#define	EXFULL		162	/* Exchange full */
-#define	ENOANO		163	/* No anode */
-#define	EBADRQC		164	/* Invalid request code */
-#define	EBADSLT		165	/* Invalid slot */
-#define	EBFONT		166	/* Bad font file format */
-#define	ENOTUNIQ	167	/* Name not unique on network */
-#define	EBADFD		168	/* File descriptor in bad state */
-#define	EREMCHG		169	/* Remote address changed */
-#define	ELIBACC		170	/* Can not access a needed shared library */
-#define	ELIBBAD		171	/* Accessing a corrupted shared library */
-#define	ELIBSCN		172	/* .lib section in a.out corrupted */
-#define	ELIBMAX		173	/* Attempting to link in too many shared libraries */
-#define	ELIBEXEC	174	/* Cannot exec a shared library directly */
-#define	ERESTART	175	/* Interrupted system call should be restarted */
-#define	ESTRPIPE	176	/* Streams pipe error */
-#define	EUCLEAN		177	/* Structure needs cleaning */
-#define	ENOTNAM		178	/* Not a XENIX named type file */
-#define	ENAVAIL		179	/* No XENIX semaphores available */
-#define	EISNAM		180	/* Is a named type file */
-#define	EREMOTEIO	181	/* Remote I/O error */
-#define	ENOMEDIUM	182	/* No medium found */
-#define	EMEDIUMTYPE	183	/* Wrong medium type */
-#define	ENOKEY		184	/* Required key not available */
-#define	EKEYEXPIRED	185	/* Key has expired */
-#define	EKEYREVOKED	186	/* Key has been revoked */
-#define	EKEYREJECTED	187	/* Key was rejected by service */
-
-/* We now return you to your regularly scheduled HPUX. */
-
-#define ENOSYM		215	/* symbol does not exist in executable */
-#define	ENOTSOCK	216	/* Socket operation on non-socket */
-#define	EDESTADDRREQ	217	/* Destination address required */
-#define	EMSGSIZE	218	/* Message too long */
-#define	EPROTOTYPE	219	/* Protocol wrong type for socket */
-#define	ENOPROTOOPT	220	/* Protocol not available */
-#define	EPROTONOSUPPORT	221	/* Protocol not supported */
-#define	ESOCKTNOSUPPORT	222	/* Socket type not supported */
-#define	EOPNOTSUPP	223	/* Operation not supported on transport endpoint */
-#define	EPFNOSUPPORT	224	/* Protocol family not supported */
-#define	EAFNOSUPPORT	225	/* Address family not supported by protocol */
-#define	EADDRINUSE	226	/* Address already in use */
-#define	EADDRNOTAVAIL	227	/* Cannot assign requested address */
-#define	ENETDOWN	228	/* Network is down */
-#define	ENETUNREACH	229	/* Network is unreachable */
-#define	ENETRESET	230	/* Network dropped connection because of reset */
-#define	ECONNABORTED	231	/* Software caused connection abort */
-#define	ECONNRESET	232	/* Connection reset by peer */
-#define	ENOBUFS		233	/* No buffer space available */
-#define	EISCONN		234	/* Transport endpoint is already connected */
-#define	ENOTCONN	235	/* Transport endpoint is not connected */
-#define	ESHUTDOWN	236	/* Cannot send after transport endpoint shutdown */
-#define	ETOOMANYREFS	237	/* Too many references: cannot splice */
-#define EREFUSED	ECONNREFUSED	/* for HP's NFS apparently */
-#define	ETIMEDOUT	238	/* Connection timed out */
-#define	ECONNREFUSED	239	/* Connection refused */
-#define EREMOTERELEASE	240	/* Remote peer released connection */
-#define	EHOSTDOWN	241	/* Host is down */
-#define	EHOSTUNREACH	242	/* No route to host */
-
-#define	EALREADY	244	/* Operation already in progress */
-#define	EINPROGRESS	245	/* Operation now in progress */
-#define	EWOULDBLOCK	246	/* Operation would block (Linux returns EAGAIN) */
-#define	ENOTEMPTY	247	/* Directory not empty */
-#define	ENAMETOOLONG	248	/* File name too long */
-#define	ELOOP		249	/* Too many symbolic links encountered */
-#define	ENOSYS		251	/* Function not implemented */
-
-#define ENOTSUP		252	/* Function not implemented (POSIX.4 / HPUX) */
-#define ECANCELLED	253	/* aio request was canceled before complete (POSIX.4 / HPUX) */
-#define ECANCELED	ECANCELLED	/* SuSv3 and Solaris wants one 'L' */
-
-/* for robust mutexes */
-#define EOWNERDEAD	254	/* Owner died */
-#define ENOTRECOVERABLE	255	/* State not recoverable */
-
-
-#endif
diff --git a/include/asm-parisc/fb.h b/include/asm-parisc/fb.h
deleted file mode 100644
index 4d503a023ab2..000000000000
--- a/include/asm-parisc/fb.h
+++ /dev/null
@@ -1,19 +0,0 @@
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
-
-#include <linux/fb.h>
-#include <linux/fs.h>
-#include <asm/page.h>
-
-static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
-				unsigned long off)
-{
-	pgprot_val(vma->vm_page_prot) |= _PAGE_NO_CACHE;
-}
-
-static inline int fb_is_primary_device(struct fb_info *info)
-{
-	return 0;
-}
-
-#endif /* _ASM_FB_H_ */
diff --git a/include/asm-parisc/fcntl.h b/include/asm-parisc/fcntl.h
deleted file mode 100644
index 1e1c824764ee..000000000000
--- a/include/asm-parisc/fcntl.h
+++ /dev/null
@@ -1,39 +0,0 @@
-#ifndef _PARISC_FCNTL_H
-#define _PARISC_FCNTL_H
-
-/* open/fcntl - O_SYNC is only implemented on blocks devices and on files
-   located on an ext2 file system */
-#define O_APPEND	000000010
-#define O_BLKSEEK	000000100 /* HPUX only */
-#define O_CREAT		000000400 /* not fcntl */
-#define O_EXCL		000002000 /* not fcntl */
-#define O_LARGEFILE	000004000
-#define O_SYNC		000100000
-#define O_NONBLOCK	000200004 /* HPUX has separate NDELAY & NONBLOCK */
-#define O_NOCTTY	000400000 /* not fcntl */
-#define O_DSYNC		001000000 /* HPUX only */
-#define O_RSYNC		002000000 /* HPUX only */
-#define O_NOATIME	004000000
-#define O_CLOEXEC	010000000 /* set close_on_exec */
-
-#define O_DIRECTORY	000010000 /* must be a directory */
-#define O_NOFOLLOW	000000200 /* don't follow links */
-#define O_INVISIBLE	004000000 /* invisible I/O, for DMAPI/XDSM */
-
-#define F_GETLK64	8
-#define F_SETLK64	9
-#define F_SETLKW64	10
-
-#define F_GETOWN	11	/*  for sockets. */
-#define F_SETOWN	12	/*  for sockets. */
-#define F_SETSIG	13	/*  for sockets. */
-#define F_GETSIG	14	/*  for sockets. */
-
-/* for posix fcntl() and lockf() */
-#define F_RDLCK		01
-#define F_WRLCK		02
-#define F_UNLCK		03
-
-#include <asm-generic/fcntl.h>
-
-#endif
diff --git a/include/asm-parisc/fixmap.h b/include/asm-parisc/fixmap.h
deleted file mode 100644
index de3fe3a18229..000000000000
--- a/include/asm-parisc/fixmap.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _ASM_FIXMAP_H
-#define _ASM_FIXMAP_H
-
-/*
- * This file defines the locations of the fixed mappings on parisc.
- *
- * All of the values in this file are machine virtual addresses.
- *
- * All of the values in this file must be <4GB (because of assembly
- * loading restrictions).  If you place this region anywhere above
- * __PAGE_OFFSET, you must adjust the memory map accordingly */
-
-/* The alias region is used in kernel space to do copy/clear to or
- * from areas congruently mapped with user space.  It is 8MB large
- * and must be 16MB aligned */
-#define TMPALIAS_MAP_START	((__PAGE_OFFSET) - 16*1024*1024)
-/* This is the kernel area for all maps (vmalloc, dma etc.)  most
- * usually, it extends up to TMPALIAS_MAP_START.  Virtual addresses
- * 0..GATEWAY_PAGE_SIZE are reserved for the gateway page */
-#define KERNEL_MAP_START	(GATEWAY_PAGE_SIZE)
-#define KERNEL_MAP_END		(TMPALIAS_MAP_START)
-
-#ifndef __ASSEMBLY__
-extern void *vmalloc_start;
-#define PCXL_DMA_MAP_SIZE	(8*1024*1024)
-#define VMALLOC_START		((unsigned long)vmalloc_start)
-#define VMALLOC_END		(KERNEL_MAP_END)
-#endif /*__ASSEMBLY__*/
-
-#endif /*_ASM_FIXMAP_H*/
diff --git a/include/asm-parisc/floppy.h b/include/asm-parisc/floppy.h
deleted file mode 100644
index 4ca69f558fae..000000000000
--- a/include/asm-parisc/floppy.h
+++ /dev/null
@@ -1,271 +0,0 @@
-/*    Architecture specific parts of the Floppy driver
- *
- *    Linux/PA-RISC Project (http://www.parisc-linux.org/)
- *    Copyright (C) 2000 Matthew Wilcox (willy a debian . org)
- *    Copyright (C) 2000 Dave Kennedy
- *
- *    This program is free software; you can redistribute it and/or modify
- *    it under the terms of the GNU General Public License as published by
- *    the Free Software Foundation; either version 2 of the License, or
- *    (at your option) any later version.
- *
- *    This program is distributed in the hope that it will be useful,
- *    but WITHOUT ANY WARRANTY; without even the implied warranty of
- *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *    GNU General Public License for more details.
- *
- *    You should have received a copy of the GNU General Public License
- *    along with this program; if not, write to the Free Software
- *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-#ifndef __ASM_PARISC_FLOPPY_H
-#define __ASM_PARISC_FLOPPY_H
-
-#include <linux/vmalloc.h>
-
-
-/*
- * The DMA channel used by the floppy controller cannot access data at
- * addresses >= 16MB
- *
- * Went back to the 1MB limit, as some people had problems with the floppy
- * driver otherwise. It doesn't matter much for performance anyway, as most
- * floppy accesses go through the track buffer.
- */
-#define _CROSS_64KB(a,s,vdma) \
-(!vdma && ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
-
-#define CROSS_64KB(a,s) _CROSS_64KB(a,s,use_virtual_dma & 1)
-
-
-#define SW fd_routine[use_virtual_dma&1]
-#define CSW fd_routine[can_use_virtual_dma & 1]
-
-
-#define fd_inb(port)			readb(port)
-#define fd_outb(value, port)		writeb(value, port)
-
-#define fd_request_dma()        CSW._request_dma(FLOPPY_DMA,"floppy")
-#define fd_free_dma()           CSW._free_dma(FLOPPY_DMA)
-#define fd_enable_irq()         enable_irq(FLOPPY_IRQ)
-#define fd_disable_irq()        disable_irq(FLOPPY_IRQ)
-#define fd_free_irq()		free_irq(FLOPPY_IRQ, NULL)
-#define fd_get_dma_residue()    SW._get_dma_residue(FLOPPY_DMA)
-#define fd_dma_mem_alloc(size)	SW._dma_mem_alloc(size)
-#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
-
-#define FLOPPY_CAN_FALLBACK_ON_NODMA
-
-static int virtual_dma_count=0;
-static int virtual_dma_residue=0;
-static char *virtual_dma_addr=0;
-static int virtual_dma_mode=0;
-static int doing_pdma=0;
-
-static void floppy_hardint(int irq, void *dev_id, struct pt_regs * regs)
-{
-	register unsigned char st;
-
-#undef TRACE_FLPY_INT
-
-#ifdef TRACE_FLPY_INT
-	static int calls=0;
-	static int bytes=0;
-	static int dma_wait=0;
-#endif
-	if (!doing_pdma) {
-		floppy_interrupt(irq, dev_id, regs);
-		return;
-	}
-
-#ifdef TRACE_FLPY_INT
-	if(!calls)
-		bytes = virtual_dma_count;
-#endif
-
-	{
-		register int lcount;
-		register char *lptr = virtual_dma_addr;
-
-		for (lcount = virtual_dma_count; lcount; lcount--) {
-			st = fd_inb(virtual_dma_port+4) & 0xa0 ;
-			if (st != 0xa0) 
-				break;
-			if (virtual_dma_mode) {
-				fd_outb(*lptr, virtual_dma_port+5);
-			} else {
-				*lptr = fd_inb(virtual_dma_port+5);
-			}
-			lptr++;
-		}
-		virtual_dma_count = lcount;
-		virtual_dma_addr = lptr;
-		st = fd_inb(virtual_dma_port+4);
-	}
-
-#ifdef TRACE_FLPY_INT
-	calls++;
-#endif
-	if (st == 0x20)
-		return;
-	if (!(st & 0x20)) {
-		virtual_dma_residue += virtual_dma_count;
-		virtual_dma_count = 0;
-#ifdef TRACE_FLPY_INT
-		printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n", 
-		       virtual_dma_count, virtual_dma_residue, calls, bytes,
-		       dma_wait);
-		calls = 0;
-		dma_wait=0;
-#endif
-		doing_pdma = 0;
-		floppy_interrupt(irq, dev_id, regs);
-		return;
-	}
-#ifdef TRACE_FLPY_INT
-	if (!virtual_dma_count)
-		dma_wait++;
-#endif
-}
-
-static void fd_disable_dma(void)
-{
-	if(! (can_use_virtual_dma & 1))
-		disable_dma(FLOPPY_DMA);
-	doing_pdma = 0;
-	virtual_dma_residue += virtual_dma_count;
-	virtual_dma_count=0;
-}
-
-static int vdma_request_dma(unsigned int dmanr, const char * device_id)
-{
-	return 0;
-}
-
-static void vdma_nop(unsigned int dummy)
-{
-}
-
-
-static int vdma_get_dma_residue(unsigned int dummy)
-{
-	return virtual_dma_count + virtual_dma_residue;
-}
-
-
-static int fd_request_irq(void)
-{
-	if(can_use_virtual_dma)
-		return request_irq(FLOPPY_IRQ, floppy_hardint,
-				   IRQF_DISABLED, "floppy", NULL);
-	else
-		return request_irq(FLOPPY_IRQ, floppy_interrupt,
-				   IRQF_DISABLED, "floppy", NULL);
-}
-
-static unsigned long dma_mem_alloc(unsigned long size)
-{
-	return __get_dma_pages(GFP_KERNEL, get_order(size));
-}
-
-
-static unsigned long vdma_mem_alloc(unsigned long size)
-{
-	return (unsigned long) vmalloc(size);
-
-}
-
-#define nodma_mem_alloc(size) vdma_mem_alloc(size)
-
-static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
-{
-	if((unsigned int) addr >= (unsigned int) high_memory)
-		return vfree((void *)addr);
-	else
-		free_pages(addr, get_order(size));		
-}
-
-#define fd_dma_mem_free(addr, size)  _fd_dma_mem_free(addr, size) 
-
-static void _fd_chose_dma_mode(char *addr, unsigned long size)
-{
-	if(can_use_virtual_dma == 2) {
-		if((unsigned int) addr >= (unsigned int) high_memory ||
-		   virt_to_bus(addr) >= 0x1000000 ||
-		   _CROSS_64KB(addr, size, 0))
-			use_virtual_dma = 1;
-		else
-			use_virtual_dma = 0;
-	} else {
-		use_virtual_dma = can_use_virtual_dma & 1;
-	}
-}
-
-#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
-
-
-static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
-{
-	doing_pdma = 1;
-	virtual_dma_port = io;
-	virtual_dma_mode = (mode  == DMA_MODE_WRITE);
-	virtual_dma_addr = addr;
-	virtual_dma_count = size;
-	virtual_dma_residue = 0;
-	return 0;
-}
-
-static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
-{
-#ifdef FLOPPY_SANITY_CHECK
-	if (CROSS_64KB(addr, size)) {
-		printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
-		return -1;
-	}
-#endif
-	/* actual, physical DMA */
-	doing_pdma = 0;
-	clear_dma_ff(FLOPPY_DMA);
-	set_dma_mode(FLOPPY_DMA,mode);
-	set_dma_addr(FLOPPY_DMA,virt_to_bus(addr));
-	set_dma_count(FLOPPY_DMA,size);
-	enable_dma(FLOPPY_DMA);
-	return 0;
-}
-
-static struct fd_routine_l {
-	int (*_request_dma)(unsigned int dmanr, const char * device_id);
-	void (*_free_dma)(unsigned int dmanr);
-	int (*_get_dma_residue)(unsigned int dummy);
-	unsigned long (*_dma_mem_alloc) (unsigned long size);
-	int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
-} fd_routine[] = {
-	{
-		request_dma,
-		free_dma,
-		get_dma_residue,
-		dma_mem_alloc,
-		hard_dma_setup
-	},
-	{
-		vdma_request_dma,
-		vdma_nop,
-		vdma_get_dma_residue,
-		vdma_mem_alloc,
-		vdma_dma_setup
-	}
-};
-
-
-static int FDC1 = 0x3f0; /* Lies.  Floppy controller is memory mapped, not io mapped */
-static int FDC2 = -1;
-
-#define FLOPPY0_TYPE	0
-#define FLOPPY1_TYPE	0
-
-#define N_FDC 1
-#define N_DRIVE 8
-
-#define EXTRA_FLOPPY_PARAMS
-
-#endif /* __ASM_PARISC_FLOPPY_H */
diff --git a/include/asm-parisc/futex.h b/include/asm-parisc/futex.h
deleted file mode 100644
index 0c705c3a55ef..000000000000
--- a/include/asm-parisc/futex.h
+++ /dev/null
@@ -1,77 +0,0 @@
-#ifndef _ASM_PARISC_FUTEX_H
-#define _ASM_PARISC_FUTEX_H
-
-#ifdef __KERNEL__
-
-#include <linux/futex.h>
-#include <linux/uaccess.h>
-#include <asm/errno.h>
-
-static inline int
-futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
-{
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
-	int oldval = 0, ret;
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
-
-	pagefault_disable();
-
-	switch (op) {
-	case FUTEX_OP_SET:
-	case FUTEX_OP_ADD:
-	case FUTEX_OP_OR:
-	case FUTEX_OP_ANDN:
-	case FUTEX_OP_XOR:
-	default:
-		ret = -ENOSYS;
-	}
-
-	pagefault_enable();
-
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
-	return ret;
-}
-
-/* Non-atomic version */
-static inline int
-futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
-{
-	int err = 0;
-	int uval;
-
-	/* futex.c wants to do a cmpxchg_inatomic on kernel NULL, which is
-	 * our gateway page, and causes no end of trouble...
-	 */
-	if (segment_eq(KERNEL_DS, get_fs()) && !uaddr)
-		return -EFAULT;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
-
-	err = get_user(uval, uaddr);
-	if (err) return -EFAULT;
-	if (uval == oldval)
-		err = put_user(newval, uaddr);
-	if (err) return -EFAULT;
-	return uval;
-}
-
-#endif /*__KERNEL__*/
-#endif /*_ASM_PARISC_FUTEX_H*/
diff --git a/include/asm-parisc/grfioctl.h b/include/asm-parisc/grfioctl.h
deleted file mode 100644
index 671e06042b40..000000000000
--- a/include/asm-parisc/grfioctl.h
+++ /dev/null
@@ -1,113 +0,0 @@
-/*  Architecture specific parts of HP's STI (framebuffer) driver.
- *  Structures are HP-UX compatible for XFree86 usage.
- * 
- *    Linux/PA-RISC Project (http://www.parisc-linux.org/)
- *    Copyright (C) 2001 Helge Deller (deller a parisc-linux org)
- *
- *    This program is free software; you can redistribute it and/or modify
- *    it under the terms of the GNU General Public License as published by
- *    the Free Software Foundation; either version 2 of the License, or
- *    (at your option) any later version.
- *
- *    This program is distributed in the hope that it will be useful,
- *    but WITHOUT ANY WARRANTY; without even the implied warranty of
- *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *    GNU General Public License for more details.
- *
- *    You should have received a copy of the GNU General Public License
- *    along with this program; if not, write to the Free Software
- *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-#ifndef __ASM_PARISC_GRFIOCTL_H
-#define __ASM_PARISC_GRFIOCTL_H
-
-/* upper 32 bits of graphics id (HP/UX identifier) */
-
-#define GRFGATOR		8
-#define S9000_ID_S300		9
-#define GRFBOBCAT		9
-#define	GRFCATSEYE		9
-#define S9000_ID_98720		10
-#define GRFRBOX			10
-#define S9000_ID_98550		11
-#define GRFFIREEYE		11
-#define S9000_ID_A1096A		12
-#define GRFHYPERION		12
-#define S9000_ID_FRI		13
-#define S9000_ID_98730		14
-#define GRFDAVINCI		14
-#define S9000_ID_98705		0x26C08070	/* Tigershark */
-#define S9000_ID_98736		0x26D148AB
-#define S9000_ID_A1659A		0x26D1482A	/* CRX 8 plane color (=ELK) */
-#define S9000_ID_ELK		S9000_ID_A1659A
-#define S9000_ID_A1439A		0x26D148EE	/* CRX24 = CRX+ (24-plane color) */
-#define S9000_ID_A1924A		0x26D1488C	/* GRX gray-scale */
-#define S9000_ID_ELM		S9000_ID_A1924A
-#define S9000_ID_98765		0x27480DEF
-#define S9000_ID_ELK_768	0x27482101
-#define S9000_ID_STINGER	0x27A4A402
-#define S9000_ID_TIMBER		0x27F12392	/* Bushmaster (710) Graphics */
-#define S9000_ID_TOMCAT		0x27FCCB6D	/* dual-headed ELK (Dual CRX) */
-#define S9000_ID_ARTIST		0x2B4DED6D	/* Artist (Gecko/712 & 715) onboard Graphics */
-#define S9000_ID_HCRX		0x2BCB015A	/* Hyperdrive/Hyperbowl (A4071A) Graphics */
-#define CRX24_OVERLAY_PLANES	0x920825AA	/* Overlay planes on CRX24 */
-
-#define CRT_ID_ELK_1024		S9000_ID_ELK_768 /* Elk 1024x768  CRX */
-#define CRT_ID_ELK_1280		S9000_ID_A1659A	/* Elk 1280x1024 CRX */
-#define CRT_ID_ELK_1024DB	0x27849CA5      /* Elk 1024x768 double buffer */
-#define CRT_ID_ELK_GS		S9000_ID_A1924A	/* Elk 1280x1024 GreyScale    */
-#define CRT_ID_CRX24		S9000_ID_A1439A	/* Piranha */
-#define CRT_ID_VISUALIZE_EG	0x2D08C0A7      /* Graffiti, A4450A (built-in B132+/B160L) */
-#define CRT_ID_THUNDER		0x2F23E5FC      /* Thunder 1 VISUALIZE 48*/
-#define CRT_ID_THUNDER2		0x2F8D570E      /* Thunder 2 VISUALIZE 48 XP*/
-#define CRT_ID_HCRX		S9000_ID_HCRX	/* Hyperdrive HCRX */
-#define CRT_ID_CRX48Z		S9000_ID_STINGER /* Stinger */
-#define CRT_ID_DUAL_CRX		S9000_ID_TOMCAT	/* Tomcat */
-#define CRT_ID_PVRX		S9000_ID_98705	/* Tigershark */
-#define CRT_ID_TIMBER		S9000_ID_TIMBER	/* Timber (710 builtin) */
-#define CRT_ID_TVRX		S9000_ID_98765	/* TVRX (gto/falcon) */
-#define CRT_ID_ARTIST		S9000_ID_ARTIST	/* Artist */
-#define CRT_ID_SUMMIT		0x2FC1066B      /* Summit FX2, FX4, FX6 ... */
-#define CRT_ID_LEGO		0x35ACDA30	/* Lego FX5, FX10 ... */
-#define CRT_ID_PINNACLE		0x35ACDA16	/* Pinnacle FXe */ 
-
-/* structure for ioctl(GCDESCRIBE) */
-
-#define gaddr_t unsigned long	/* FIXME: PA2.0 (64bit) portable ? */
-
-struct	grf_fbinfo {
-	unsigned int	id;		/* upper 32 bits of graphics id */
-	unsigned int	mapsize;	/* mapped size of framebuffer */
-	unsigned int	dwidth, dlength;/* x and y sizes */
-	unsigned int	width, length;	/* total x and total y size */
-	unsigned int	xlen;		/* x pitch size */
-	unsigned int	bpp, bppu;	/* bits per pixel and used bpp */
-	unsigned int	npl, nplbytes;	/* # of planes and bytes per plane */
-	char		name[32];	/* name of the device (from ROM) */
-	unsigned int	attr;		/* attributes */
-	gaddr_t 	fbbase, regbase;/* framebuffer and register base addr */
-	gaddr_t		regions[6];	/* region bases */
-};
-
-#define	GCID		_IOR('G', 0, int)
-#define	GCON		_IO('G', 1)
-#define	GCOFF		_IO('G', 2)
-#define	GCAON		_IO('G', 3)
-#define	GCAOFF		_IO('G', 4)
-#define	GCMAP		_IOWR('G', 5, int)
-#define	GCUNMAP		_IOWR('G', 6, int)
-#define	GCMAP_HPUX	_IO('G', 5)
-#define	GCUNMAP_HPUX	_IO('G', 6)
-#define	GCLOCK		_IO('G', 7)
-#define	GCUNLOCK	_IO('G', 8)
-#define	GCLOCK_MINIMUM	_IO('G', 9)
-#define	GCUNLOCK_MINIMUM _IO('G', 10)
-#define	GCSTATIC_CMAP	_IO('G', 11)
-#define	GCVARIABLE_CMAP _IO('G', 12)
-#define GCTERM		_IOWR('G',20,int)	/* multi-headed Tomcat */ 
-#define GCDESCRIBE	_IOR('G', 21, struct grf_fbinfo)
-#define GCFASTLOCK	_IO('G', 26)
-
-#endif /* __ASM_PARISC_GRFIOCTL_H */
-
diff --git a/include/asm-parisc/hardirq.h b/include/asm-parisc/hardirq.h
deleted file mode 100644
index ce93133d5112..000000000000
--- a/include/asm-parisc/hardirq.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* hardirq.h: PA-RISC hard IRQ support.
- *
- * Copyright (C) 2001 Matthew Wilcox <matthew@wil.cx>
- *
- * The locking is really quite interesting.  There's a cpu-local
- * count of how many interrupts are being handled, and a global
- * lock.  An interrupt can only be serviced if the global lock
- * is free.  You can't be sure no more interrupts are being
- * serviced until you've acquired the lock and then checked
- * all the per-cpu interrupt counts are all zero.  It's a specialised
- * br_lock, and that's exactly how Sparc does it.  We don't because
- * it's more locking for us.  This way is lock-free in the interrupt path.
- */
-
-#ifndef _PARISC_HARDIRQ_H
-#define _PARISC_HARDIRQ_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-typedef struct {
-	unsigned long __softirq_pending; /* set_bit is used on this */
-} ____cacheline_aligned irq_cpustat_t;
-
-#include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
-
-void ack_bad_irq(unsigned int irq);
-
-#endif /* _PARISC_HARDIRQ_H */
diff --git a/include/asm-parisc/hardware.h b/include/asm-parisc/hardware.h
deleted file mode 100644
index 4e9626836bab..000000000000
--- a/include/asm-parisc/hardware.h
+++ /dev/null
@@ -1,127 +0,0 @@
-#ifndef _PARISC_HARDWARE_H
-#define _PARISC_HARDWARE_H
-
-#include <linux/mod_devicetable.h>
-#include <asm/pdc.h>
-
-#define HWTYPE_ANY_ID		PA_HWTYPE_ANY_ID
-#define HVERSION_ANY_ID		PA_HVERSION_ANY_ID
-#define HVERSION_REV_ANY_ID	PA_HVERSION_REV_ANY_ID
-#define SVERSION_ANY_ID		PA_SVERSION_ANY_ID
-
-struct hp_hardware {
-	unsigned short	hw_type:5;	/* HPHW_xxx */
-	unsigned short	hversion;
-	unsigned long	sversion:28;
-	unsigned short	opt;
-	const char	name[80];	/* The hardware description */
-};
-
-struct parisc_device;
-
-enum cpu_type {
-	pcx	= 0, /* pa7000		pa 1.0  */
-	pcxs	= 1, /* pa7000		pa 1.1a */
-	pcxt	= 2, /* pa7100		pa 1.1b */
-	pcxt_	= 3, /* pa7200	(t')	pa 1.1c */
-	pcxl	= 4, /* pa7100lc	pa 1.1d */
-	pcxl2	= 5, /* pa7300lc	pa 1.1e */
-	pcxu	= 6, /* pa8000		pa 2.0  */
-	pcxu_	= 7, /* pa8200	(u+)	pa 2.0  */
-	pcxw	= 8, /* pa8500		pa 2.0  */
-	pcxw_	= 9, /* pa8600	(w+)	pa 2.0  */
-	pcxw2	= 10, /* pa8700		pa 2.0  */
-	mako	= 11, /* pa8800		pa 2.0  */
-	mako2	= 12  /* pa8900		pa 2.0  */
-};
-
-extern const char * const cpu_name_version[][2]; /* mapping from enum cpu_type to strings */
-
-struct parisc_driver;
-
-struct io_module {
-        volatile uint32_t nothing;		/* reg 0 */
-        volatile uint32_t io_eim;
-        volatile uint32_t io_dc_adata;
-        volatile uint32_t io_ii_cdata;
-        volatile uint32_t io_dma_link;		/* reg 4 */
-        volatile uint32_t io_dma_command;
-        volatile uint32_t io_dma_address;
-        volatile uint32_t io_dma_count;
-        volatile uint32_t io_flex;		/* reg 8 */
-        volatile uint32_t io_spa_address;
-        volatile uint32_t reserved1[2];
-        volatile uint32_t io_command;		/* reg 12 */
-        volatile uint32_t io_status;
-        volatile uint32_t io_control;
-        volatile uint32_t io_data;
-        volatile uint32_t reserved2;		/* reg 16 */
-        volatile uint32_t chain_addr;
-        volatile uint32_t sub_mask_clr;
-        volatile uint32_t reserved3[13];
-        volatile uint32_t undefined[480];
-        volatile uint32_t unpriv[512];
-};
-
-struct bc_module {
-        volatile uint32_t unused1[12];
-        volatile uint32_t io_command;
-        volatile uint32_t io_status;
-        volatile uint32_t io_control;
-        volatile uint32_t unused2[1];
-        volatile uint32_t io_err_resp;
-        volatile uint32_t io_err_info;
-        volatile uint32_t io_err_req;
-        volatile uint32_t unused3[11];
-        volatile uint32_t io_io_low;
-        volatile uint32_t io_io_high;
-};
-
-#define HPHW_NPROC     0 
-#define HPHW_MEMORY    1       
-#define HPHW_B_DMA     2
-#define HPHW_OBSOLETE  3
-#define HPHW_A_DMA     4
-#define HPHW_A_DIRECT  5
-#define HPHW_OTHER     6
-#define HPHW_BCPORT    7
-#define HPHW_CIO       8
-#define HPHW_CONSOLE   9
-#define HPHW_FIO       10
-#define HPHW_BA        11
-#define HPHW_IOA       12
-#define HPHW_BRIDGE    13
-#define HPHW_FABRIC    14
-#define HPHW_MC	       15
-#define HPHW_FAULTY    31
-
-
-/* hardware.c: */
-extern const char *parisc_hardware_description(struct parisc_device_id *id);
-extern enum cpu_type parisc_get_cpu_type(unsigned long hversion);
-
-struct pci_dev;
-
-/* drivers.c: */
-extern struct parisc_device *alloc_pa_dev(unsigned long hpa,
-		struct hardware_path *path);
-extern int register_parisc_device(struct parisc_device *dev);
-extern int register_parisc_driver(struct parisc_driver *driver);
-extern int count_parisc_driver(struct parisc_driver *driver);
-extern int unregister_parisc_driver(struct parisc_driver *driver);
-extern void walk_central_bus(void);
-extern const struct parisc_device *find_pa_parent_type(const struct parisc_device *, int);
-extern void print_parisc_devices(void);
-extern char *print_pa_hwpath(struct parisc_device *dev, char *path);
-extern char *print_pci_hwpath(struct pci_dev *dev, char *path);
-extern void get_pci_node_path(struct pci_dev *dev, struct hardware_path *path);
-extern void init_parisc_bus(void);
-extern struct device *hwpath_to_device(struct hardware_path *modpath);
-extern void device_to_hwpath(struct device *dev, struct hardware_path *path);
-
-
-/* inventory.c: */
-extern void do_memory_inventory(void);
-extern void do_device_inventory(void);
-
-#endif /* _PARISC_HARDWARE_H */
diff --git a/include/asm-parisc/hw_irq.h b/include/asm-parisc/hw_irq.h
deleted file mode 100644
index 6707f7df3921..000000000000
--- a/include/asm-parisc/hw_irq.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _ASM_HW_IRQ_H
-#define _ASM_HW_IRQ_H
-
-/*
- *	linux/include/asm/hw_irq.h
- */
-
-#endif
diff --git a/include/asm-parisc/ide.h b/include/asm-parisc/ide.h
deleted file mode 100644
index c246ef75017d..000000000000
--- a/include/asm-parisc/ide.h
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- *  linux/include/asm-parisc/ide.h
- *
- *  Copyright (C) 1994-1996  Linus Torvalds & authors
- */
-
-/*
- *  This file contains the PARISC architecture specific IDE code.
- */
-
-#ifndef __ASM_PARISC_IDE_H
-#define __ASM_PARISC_IDE_H
-
-#ifdef __KERNEL__
-
-#define ide_request_irq(irq,hand,flg,dev,id)	request_irq((irq),(hand),(flg),(dev),(id))
-#define ide_free_irq(irq,dev_id)		free_irq((irq), (dev_id))
-#define ide_request_region(from,extent,name)	request_region((from), (extent), (name))
-#define ide_release_region(from,extent)		release_region((from), (extent))
-/* Generic I/O and MEMIO string operations.  */
-
-#define __ide_insw	insw
-#define __ide_insl	insl
-#define __ide_outsw	outsw
-#define __ide_outsl	outsl
-
-static __inline__ void __ide_mm_insw(void __iomem *port, void *addr, u32 count)
-{
-	while (count--) {
-		*(u16 *)addr = __raw_readw(port);
-		addr += 2;
-	}
-}
-
-static __inline__ void __ide_mm_insl(void __iomem *port, void *addr, u32 count)
-{
-	while (count--) {
-		*(u32 *)addr = __raw_readl(port);
-		addr += 4;
-	}
-}
-
-static __inline__ void __ide_mm_outsw(void __iomem *port, void *addr, u32 count)
-{
-	while (count--) {
-		__raw_writew(*(u16 *)addr, port);
-		addr += 2;
-	}
-}
-
-static __inline__ void __ide_mm_outsl(void __iomem *port, void *addr, u32 count)
-{
-	while (count--) {
-		__raw_writel(*(u32 *)addr, port);
-		addr += 4;
-	}
-}
-
-#endif /* __KERNEL__ */
-
-#endif /* __ASM_PARISC_IDE_H */
diff --git a/include/asm-parisc/io.h b/include/asm-parisc/io.h
deleted file mode 100644
index 55ddb1842107..000000000000
--- a/include/asm-parisc/io.h
+++ /dev/null
@@ -1,293 +0,0 @@
-#ifndef _ASM_IO_H
-#define _ASM_IO_H
-
-#include <linux/types.h>
-#include <asm/pgtable.h>
-
-extern unsigned long parisc_vmerge_boundary;
-extern unsigned long parisc_vmerge_max_size;
-
-#define BIO_VMERGE_BOUNDARY	parisc_vmerge_boundary
-#define BIO_VMERGE_MAX_SIZE	parisc_vmerge_max_size
-
-#define virt_to_phys(a) ((unsigned long)__pa(a))
-#define phys_to_virt(a) __va(a)
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-
-static inline unsigned long isa_bus_to_virt(unsigned long addr) {
-	BUG();
-	return 0;
-}
-
-static inline unsigned long isa_virt_to_bus(void *addr) {
-	BUG();
-	return 0;
-}
-
-/*
- * Memory mapped I/O
- *
- * readX()/writeX() do byteswapping and take an ioremapped address
- * __raw_readX()/__raw_writeX() don't byteswap and take an ioremapped address.
- * gsc_*() don't byteswap and operate on physical addresses;
- *   eg dev->hpa or 0xfee00000.
- */
-
-static inline unsigned char gsc_readb(unsigned long addr)
-{
-	long flags;
-	unsigned char ret;
-
-	__asm__ __volatile__(
-	"	rsm	2,%0\n"
-	"	ldbx	0(%2),%1\n"
-	"	mtsm	%0\n"
-	: "=&r" (flags), "=r" (ret) : "r" (addr) );
-
-	return ret;
-}
-
-static inline unsigned short gsc_readw(unsigned long addr)
-{
-	long flags;
-	unsigned short ret;
-
-	__asm__ __volatile__(
-	"	rsm	2,%0\n"
-	"	ldhx	0(%2),%1\n"
-	"	mtsm	%0\n"
-	: "=&r" (flags), "=r" (ret) : "r" (addr) );
-
-	return ret;
-}
-
-static inline unsigned int gsc_readl(unsigned long addr)
-{
-	u32 ret;
-
-	__asm__ __volatile__(
-	"	ldwax	0(%1),%0\n"
-	: "=r" (ret) : "r" (addr) );
-
-	return ret;
-}
-
-static inline unsigned long long gsc_readq(unsigned long addr)
-{
-	unsigned long long ret;
-
-#ifdef CONFIG_64BIT
-	__asm__ __volatile__(
-	"	ldda	0(%1),%0\n"
-	:  "=r" (ret) : "r" (addr) );
-#else
-	/* two reads may have side effects.. */
-	ret = ((u64) gsc_readl(addr)) << 32;
-	ret |= gsc_readl(addr+4);
-#endif
-	return ret;
-}
-
-static inline void gsc_writeb(unsigned char val, unsigned long addr)
-{
-	long flags;
-	__asm__ __volatile__(
-	"	rsm	2,%0\n"
-	"	stbs	%1,0(%2)\n"
-	"	mtsm	%0\n"
-	: "=&r" (flags) :  "r" (val), "r" (addr) );
-}
-
-static inline void gsc_writew(unsigned short val, unsigned long addr)
-{
-	long flags;
-	__asm__ __volatile__(
-	"	rsm	2,%0\n"
-	"	sths	%1,0(%2)\n"
-	"	mtsm	%0\n"
-	: "=&r" (flags) :  "r" (val), "r" (addr) );
-}
-
-static inline void gsc_writel(unsigned int val, unsigned long addr)
-{
-	__asm__ __volatile__(
-	"	stwas	%0,0(%1)\n"
-	: :  "r" (val), "r" (addr) );
-}
-
-static inline void gsc_writeq(unsigned long long val, unsigned long addr)
-{
-#ifdef CONFIG_64BIT
-	__asm__ __volatile__(
-	"	stda	%0,0(%1)\n"
-	: :  "r" (val), "r" (addr) );
-#else
-	/* two writes may have side effects.. */
-	gsc_writel(val >> 32, addr);
-	gsc_writel(val, addr+4);
-#endif
-}
-
-/*
- * The standard PCI ioremap interfaces
- */
-
-extern void __iomem * __ioremap(unsigned long offset, unsigned long size, unsigned long flags);
-
-/* Most machines react poorly to I/O-space being cacheable... Instead let's
- * define ioremap() in terms of ioremap_nocache().
- */
-static inline void __iomem * ioremap(unsigned long offset, unsigned long size)
-{
-	return __ioremap(offset, size, _PAGE_NO_CACHE);
-}
-#define ioremap_nocache(off, sz)	ioremap((off), (sz))
-
-extern void iounmap(const volatile void __iomem *addr);
-
-static inline unsigned char __raw_readb(const volatile void __iomem *addr)
-{
-	return (*(volatile unsigned char __force *) (addr));
-}
-static inline unsigned short __raw_readw(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned short __force *) addr;
-}
-static inline unsigned int __raw_readl(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned int __force *) addr;
-}
-static inline unsigned long long __raw_readq(const volatile void __iomem *addr)
-{
-	return *(volatile unsigned long long __force *) addr;
-}
-
-static inline void __raw_writeb(unsigned char b, volatile void __iomem *addr)
-{
-	*(volatile unsigned char __force *) addr = b;
-}
-static inline void __raw_writew(unsigned short b, volatile void __iomem *addr)
-{
-	*(volatile unsigned short __force *) addr = b;
-}
-static inline void __raw_writel(unsigned int b, volatile void __iomem *addr)
-{
-	*(volatile unsigned int __force *) addr = b;
-}
-static inline void __raw_writeq(unsigned long long b, volatile void __iomem *addr)
-{
-	*(volatile unsigned long long __force *) addr = b;
-}
-
-/* readb can never be const, so use __fswab instead of le*_to_cpu */
-#define readb(addr) __raw_readb(addr)
-#define readw(addr) __fswab16(__raw_readw(addr))
-#define readl(addr) __fswab32(__raw_readl(addr))
-#define readq(addr) __fswab64(__raw_readq(addr))
-#define writeb(b, addr) __raw_writeb(b, addr)
-#define writew(b, addr) __raw_writew(cpu_to_le16(b), addr)
-#define writel(b, addr) __raw_writel(cpu_to_le32(b), addr)
-#define writeq(b, addr) __raw_writeq(cpu_to_le64(b), addr)
-
-#define readb_relaxed(addr) readb(addr)
-#define readw_relaxed(addr) readw(addr)
-#define readl_relaxed(addr) readl(addr)
-#define readq_relaxed(addr) readq(addr)
-
-#define mmiowb() do { } while (0)
-
-void memset_io(volatile void __iomem *addr, unsigned char val, int count);
-void memcpy_fromio(void *dst, const volatile void __iomem *src, int count);
-void memcpy_toio(volatile void __iomem *dst, const void *src, int count);
-
-/* Port-space IO */
-
-#define inb_p inb
-#define inw_p inw
-#define inl_p inl
-#define outb_p outb
-#define outw_p outw
-#define outl_p outl
-
-extern unsigned char eisa_in8(unsigned short port);
-extern unsigned short eisa_in16(unsigned short port);
-extern unsigned int eisa_in32(unsigned short port);
-extern void eisa_out8(unsigned char data, unsigned short port);
-extern void eisa_out16(unsigned short data, unsigned short port);
-extern void eisa_out32(unsigned int data, unsigned short port);
-
-#if defined(CONFIG_PCI)
-extern unsigned char inb(int addr);
-extern unsigned short inw(int addr);
-extern unsigned int inl(int addr);
-
-extern void outb(unsigned char b, int addr);
-extern void outw(unsigned short b, int addr);
-extern void outl(unsigned int b, int addr);
-#elif defined(CONFIG_EISA)
-#define inb eisa_in8
-#define inw eisa_in16
-#define inl eisa_in32
-#define outb eisa_out8
-#define outw eisa_out16
-#define outl eisa_out32
-#else
-static inline char inb(unsigned long addr)
-{
-	BUG();
-	return -1;
-}
-
-static inline short inw(unsigned long addr)
-{
-	BUG();
-	return -1;
-}
-
-static inline int inl(unsigned long addr)
-{
-	BUG();
-	return -1;
-}
-
-#define outb(x, y)	BUG()
-#define outw(x, y)	BUG()
-#define outl(x, y)	BUG()
-#endif
-
-/*
- * String versions of in/out ops:
- */
-extern void insb (unsigned long port, void *dst, unsigned long count);
-extern void insw (unsigned long port, void *dst, unsigned long count);
-extern void insl (unsigned long port, void *dst, unsigned long count);
-extern void outsb (unsigned long port, const void *src, unsigned long count);
-extern void outsw (unsigned long port, const void *src, unsigned long count);
-extern void outsl (unsigned long port, const void *src, unsigned long count);
-
-
-/* IO Port space is :      BBiiii   where BB is HBA number. */
-#define IO_SPACE_LIMIT 0x00ffffff
-
-/* PA machines have an MM I/O space from 0xf0000000-0xffffffff in 32
- * bit mode and from 0xfffffffff0000000-0xfffffffffffffff in 64 bit
- * mode (essentially just sign extending.  This macro takes in a 32
- * bit I/O address (still with the leading f) and outputs the correct
- * value for either 32 or 64 bit mode */
-#define F_EXTEND(x) ((unsigned long)((x) | (0xffffffff00000000ULL)))
-
-#include <asm-generic/iomap.h>
-
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
-
-#endif
diff --git a/include/asm-parisc/ioctl.h b/include/asm-parisc/ioctl.h
deleted file mode 100644
index ec8efa02beda..000000000000
--- a/include/asm-parisc/ioctl.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/*
- *    Linux/PA-RISC Project (http://www.parisc-linux.org/)
- *    Copyright (C) 1999,2003 Matthew Wilcox < willy at debian . org >
- *    portions from "linux/ioctl.h for Linux" by H.H. Bergman.
- *
- *    This program is free software; you can redistribute it and/or modify
- *    it under the terms of the GNU General Public License as published by
- *    the Free Software Foundation; either version 2 of the License, or
- *    (at your option) any later version.
- *
- *    This program is distributed in the hope that it will be useful,
- *    but WITHOUT ANY WARRANTY; without even the implied warranty of
- *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *    GNU General Public License for more details.
- *
- *    You should have received a copy of the GNU General Public License
- *    along with this program; if not, write to the Free Software
- *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-
-#ifndef _ASM_PARISC_IOCTL_H
-#define _ASM_PARISC_IOCTL_H
-
-/* ioctl command encoding: 32 bits total, command in lower 16 bits,
- * size of the parameter structure in the lower 14 bits of the
- * upper 16 bits.
- * Encoding the size of the parameter structure in the ioctl request
- * is useful for catching programs compiled with old versions
- * and to avoid overwriting user space outside the user buffer area.
- * The highest 2 bits are reserved for indicating the ``access mode''.
- * NOTE: This limits the max parameter size to 16kB -1 !
- */
-
-/*
- * Direction bits.
- */
-#define _IOC_NONE	0U
-#define _IOC_WRITE	2U
-#define _IOC_READ	1U
-
-#include <asm-generic/ioctl.h>
-
-#endif /* _ASM_PARISC_IOCTL_H */
diff --git a/include/asm-parisc/ioctls.h b/include/asm-parisc/ioctls.h
deleted file mode 100644
index 6747fad07a3e..000000000000
--- a/include/asm-parisc/ioctls.h
+++ /dev/null
@@ -1,90 +0,0 @@
-#ifndef __ARCH_PARISC_IOCTLS_H__
-#define __ARCH_PARISC_IOCTLS_H__
-
-#include <asm/ioctl.h>
-
-/* 0x54 is just a magic number to make these relatively unique ('T') */
-
-#define TCGETS		_IOR('T', 16, struct termios) /* TCGETATTR */
-#define TCSETS		_IOW('T', 17, struct termios) /* TCSETATTR */
-#define TCSETSW		_IOW('T', 18, struct termios) /* TCSETATTRD */
-#define TCSETSF		_IOW('T', 19, struct termios) /* TCSETATTRF */
-#define TCGETA		_IOR('T', 1, struct termio)
-#define TCSETA		_IOW('T', 2, struct termio)
-#define TCSETAW		_IOW('T', 3, struct termio)
-#define TCSETAF		_IOW('T', 4, struct termio)
-#define TCSBRK		_IO('T', 5)
-#define TCXONC		_IO('T', 6)
-#define TCFLSH		_IO('T', 7)
-#define TIOCEXCL	0x540C
-#define TIOCNXCL	0x540D
-#define TIOCSCTTY	0x540E
-#define TIOCGPGRP	_IOR('T', 30, int)
-#define TIOCSPGRP	_IOW('T', 29, int)
-#define TIOCOUTQ	0x5411
-#define TIOCSTI		0x5412
-#define TIOCGWINSZ	0x5413
-#define TIOCSWINSZ	0x5414
-#define TIOCMGET	0x5415
-#define TIOCMBIS	0x5416
-#define TIOCMBIC	0x5417
-#define TIOCMSET	0x5418
-#define TIOCGSOFTCAR	0x5419
-#define TIOCSSOFTCAR	0x541A
-#define FIONREAD	0x541B
-#define TIOCINQ		FIONREAD
-#define TIOCLINUX	0x541C
-#define TIOCCONS	0x541D
-#define TIOCGSERIAL	0x541E
-#define TIOCSSERIAL	0x541F
-#define TIOCPKT		0x5420
-#define FIONBIO		0x5421
-#define TIOCNOTTY	0x5422
-#define TIOCSETD	0x5423
-#define TIOCGETD	0x5424
-#define TCSBRKP		0x5425	/* Needed for POSIX tcsendbreak() */
-#define TIOCSBRK	0x5427  /* BSD compatibility */
-#define TIOCCBRK	0x5428  /* BSD compatibility */
-#define TIOCGSID	_IOR('T', 20, int) /* Return the session ID of FD */
-#define TCGETS2		_IOR('T',0x2A, struct termios2)
-#define TCSETS2		_IOW('T',0x2B, struct termios2)
-#define TCSETSW2	_IOW('T',0x2C, struct termios2)
-#define TCSETSF2	_IOW('T',0x2D, struct termios2)
-#define TIOCGPTN	_IOR('T',0x30, unsigned int) /* Get Pty Number (of pty-mux device) */
-#define TIOCSPTLCK	_IOW('T',0x31, int)  /* Lock/unlock Pty */
-
-#define FIONCLEX	0x5450  /* these numbers need to be adjusted. */
-#define FIOCLEX		0x5451
-#define FIOASYNC	0x5452
-#define TIOCSERCONFIG	0x5453
-#define TIOCSERGWILD	0x5454
-#define TIOCSERSWILD	0x5455
-#define TIOCGLCKTRMIOS	0x5456
-#define TIOCSLCKTRMIOS	0x5457
-#define TIOCSERGSTRUCT	0x5458 /* For debugging only */
-#define TIOCSERGETLSR   0x5459 /* Get line status register */
-#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
-#define TIOCSERSETMULTI 0x545B /* Set multiport config */
-
-#define TIOCMIWAIT	0x545C	/* wait for a change on serial input line(s) */
-#define TIOCGICOUNT	0x545D	/* read serial port inline interrupt counts */
-#define TIOCGHAYESESP   0x545E  /* Get Hayes ESP configuration */
-#define TIOCSHAYESESP   0x545F  /* Set Hayes ESP configuration */
-#define FIOQSIZE	0x5460	/* Get exact space used by quota */
-
-#define TIOCSTART	0x5461
-#define TIOCSTOP	0x5462
-#define TIOCSLTC	0x5462
-
-/* Used for packet mode */
-#define TIOCPKT_DATA		 0
-#define TIOCPKT_FLUSHREAD	 1
-#define TIOCPKT_FLUSHWRITE	 2
-#define TIOCPKT_STOP		 4
-#define TIOCPKT_START		 8
-#define TIOCPKT_NOSTOP		16
-#define TIOCPKT_DOSTOP		32
-
-#define TIOCSER_TEMT    0x01	/* Transmitter physically empty */
-
-#endif /* _ASM_PARISC_IOCTLS_H */
diff --git a/include/asm-parisc/ipcbuf.h b/include/asm-parisc/ipcbuf.h
deleted file mode 100644
index bd956c425785..000000000000
--- a/include/asm-parisc/ipcbuf.h
+++ /dev/null
@@ -1,27 +0,0 @@
-#ifndef __PARISC_IPCBUF_H__
-#define __PARISC_IPCBUF_H__
-
-/*
- * The ipc64_perm structure for PA-RISC is almost identical to
- * kern_ipc_perm as we have always had 32-bit UIDs and GIDs in the kernel.
- * 'seq' has been changed from long to int so that it's the same size
- * on 64-bit kernels as on 32-bit ones.
- */
-
-struct ipc64_perm
-{
-	key_t           key;
-	uid_t           uid;
-	gid_t           gid;
-	uid_t           cuid;
-	gid_t           cgid;
-	unsigned short int	__pad1;
-	mode_t          mode;
-	unsigned short int	__pad2;
-	unsigned short int	seq;
-	unsigned int	__pad3;
-	unsigned long long int __unused1;
-	unsigned long long int __unused2;
-};
-
-#endif /* __PARISC_IPCBUF_H__ */
diff --git a/include/asm-parisc/irq.h b/include/asm-parisc/irq.h
deleted file mode 100644
index 399c81981ed5..000000000000
--- a/include/asm-parisc/irq.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/*
- * include/asm-parisc/irq.h
- *
- * Copyright 2005 Matthew Wilcox <matthew@wil.cx>
- */
-
-#ifndef _ASM_PARISC_IRQ_H
-#define _ASM_PARISC_IRQ_H
-
-#include <linux/cpumask.h>
-#include <asm/types.h>
-
-#define NO_IRQ		(-1)
-
-#ifdef CONFIG_GSC
-#define GSC_IRQ_BASE	16
-#define GSC_IRQ_MAX	63
-#define CPU_IRQ_BASE	64
-#else
-#define CPU_IRQ_BASE	16
-#endif
-
-#define TIMER_IRQ	(CPU_IRQ_BASE + 0)
-#define	IPI_IRQ		(CPU_IRQ_BASE + 1)
-#define CPU_IRQ_MAX	(CPU_IRQ_BASE + (BITS_PER_LONG - 1))
-
-#define NR_IRQS		(CPU_IRQ_MAX + 1)
-
-static __inline__ int irq_canonicalize(int irq)
-{
-	return (irq == 2) ? 9 : irq;
-}
-
-struct irq_chip;
-
-/*
- * Some useful "we don't have to do anything here" handlers.  Should
- * probably be provided by the generic code.
- */
-void no_ack_irq(unsigned int irq);
-void no_end_irq(unsigned int irq);
-void cpu_ack_irq(unsigned int irq);
-void cpu_end_irq(unsigned int irq);
-
-extern int txn_alloc_irq(unsigned int nbits);
-extern int txn_claim_irq(int);
-extern unsigned int txn_alloc_data(unsigned int);
-extern unsigned long txn_alloc_addr(unsigned int);
-extern unsigned long txn_affinity_addr(unsigned int irq, int cpu);
-
-extern int cpu_claim_irq(unsigned int irq, struct irq_chip *, void *);
-extern int cpu_check_affinity(unsigned int irq, cpumask_t *dest);
-
-/* soft power switch support (power.c) */
-extern struct tasklet_struct power_tasklet;
-
-#endif	/* _ASM_PARISC_IRQ_H */
diff --git a/include/asm-parisc/irq_regs.h b/include/asm-parisc/irq_regs.h
deleted file mode 100644
index 3dd9c0b70270..000000000000
--- a/include/asm-parisc/irq_regs.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/include/asm-parisc/kdebug.h b/include/asm-parisc/kdebug.h
deleted file mode 100644
index 6ece1b037665..000000000000
--- a/include/asm-parisc/kdebug.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/kdebug.h>
diff --git a/include/asm-parisc/kmap_types.h b/include/asm-parisc/kmap_types.h
deleted file mode 100644
index 806aae3c5338..000000000000
--- a/include/asm-parisc/kmap_types.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _ASM_KMAP_TYPES_H
-#define _ASM_KMAP_TYPES_H
-
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-# define D(n) __KM_FENCE_##n ,
-#else
-# define D(n)
-#endif
-
-enum km_type {
-D(0)	KM_BOUNCE_READ,
-D(1)	KM_SKB_SUNRPC_DATA,
-D(2)	KM_SKB_DATA_SOFTIRQ,
-D(3)	KM_USER0,
-D(4)	KM_USER1,
-D(5)	KM_BIO_SRC_IRQ,
-D(6)	KM_BIO_DST_IRQ,
-D(7)	KM_PTE0,
-D(8)	KM_PTE1,
-D(9)	KM_IRQ0,
-D(10)	KM_IRQ1,
-D(11)	KM_SOFTIRQ0,
-D(12)	KM_SOFTIRQ1,
-D(13)	KM_TYPE_NR
-};
-
-#undef D
-
-#endif
diff --git a/include/asm-parisc/led.h b/include/asm-parisc/led.h
deleted file mode 100644
index c3405ab9d60a..000000000000
--- a/include/asm-parisc/led.h
+++ /dev/null
@@ -1,42 +0,0 @@
-#ifndef LED_H
-#define LED_H
-
-#define	LED7		0x80		/* top (or furthest right) LED */
-#define	LED6		0x40
-#define	LED5		0x20
-#define	LED4		0x10
-#define	LED3		0x08
-#define	LED2		0x04
-#define	LED1		0x02
-#define	LED0		0x01		/* bottom (or furthest left) LED */
-
-#define	LED_LAN_TX	LED0		/* for LAN transmit activity */
-#define	LED_LAN_RCV	LED1		/* for LAN receive activity */
-#define	LED_DISK_IO	LED2		/* for disk activity */
-#define	LED_HEARTBEAT	LED3		/* heartbeat */
-
-/* values for pdc_chassis_lcd_info_ret_block.model: */
-#define DISPLAY_MODEL_LCD  0		/* KittyHawk LED or LCD */
-#define DISPLAY_MODEL_NONE 1		/* no LED or LCD */
-#define DISPLAY_MODEL_LASI 2		/* LASI style 8 bit LED */
-#define DISPLAY_MODEL_OLD_ASP 0x7F	/* faked: ASP style 8 x 1 bit LED (only very old ASP versions) */
-
-#define LED_CMD_REG_NONE 0		/* NULL == no addr for the cmd register */
-
-/* register_led_driver() */
-int __init register_led_driver(int model, unsigned long cmd_reg, unsigned long data_reg);
-
-/* registers the LED regions for procfs */
-void __init register_led_regions(void);
-
-#ifdef CONFIG_CHASSIS_LCD_LED
-/* writes a string to the LCD display (if possible on this h/w) */
-int lcd_print(const char *str);
-#else
-#define lcd_print(str)
-#endif
-
-/* main LED initialization function (uses PDC) */ 
-int __init led_init(void);
-
-#endif /* LED_H */
diff --git a/include/asm-parisc/linkage.h b/include/asm-parisc/linkage.h
deleted file mode 100644
index 0b19a7242d0c..000000000000
--- a/include/asm-parisc/linkage.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef __ASM_PARISC_LINKAGE_H
-#define __ASM_PARISC_LINKAGE_H
-
-#ifndef __ALIGN
-#define __ALIGN         .align 4
-#define __ALIGN_STR     ".align 4"
-#endif
-
-/*
- * In parisc assembly a semicolon marks a comment while a
- * exclamation mark is used to separate independent lines.
- */
-#ifdef __ASSEMBLY__
-
-#define ENTRY(name) \
-	.export name !\
-	ALIGN !\
-name:
-
-#ifdef CONFIG_64BIT
-#define ENDPROC(name) \
-	END(name)
-#else
-#define ENDPROC(name) \
-	.type name, @function !\
-	END(name)
-#endif
-
-#endif /* __ASSEMBLY__ */
-
-#endif  /* __ASM_PARISC_LINKAGE_H */
diff --git a/include/asm-parisc/local.h b/include/asm-parisc/local.h
deleted file mode 100644
index c11c530f74d0..000000000000
--- a/include/asm-parisc/local.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/local.h>
diff --git a/include/asm-parisc/machdep.h b/include/asm-parisc/machdep.h
deleted file mode 100644
index a231c97d703e..000000000000
--- a/include/asm-parisc/machdep.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef _PARISC_MACHDEP_H
-#define _PARISC_MACHDEP_H
-
-#include <linux/notifier.h>
-
-#define	MACH_RESTART	1
-#define	MACH_HALT	2
-#define MACH_POWER_ON	3
-#define	MACH_POWER_OFF	4
-
-extern struct notifier_block *mach_notifier;
-extern void pa7300lc_init(void);
-
-extern void (*cpu_lpmc)(int, struct pt_regs *);
-
-#endif
diff --git a/include/asm-parisc/mc146818rtc.h b/include/asm-parisc/mc146818rtc.h
deleted file mode 100644
index adf41631449f..000000000000
--- a/include/asm-parisc/mc146818rtc.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Machine dependent access functions for RTC registers.
- */
-#ifndef _ASM_MC146818RTC_H
-#define _ASM_MC146818RTC_H
-
-/* empty include file to satisfy the include in genrtc.c */
-
-#endif /* _ASM_MC146818RTC_H */
diff --git a/include/asm-parisc/mckinley.h b/include/asm-parisc/mckinley.h
deleted file mode 100644
index d1ea6f12915e..000000000000
--- a/include/asm-parisc/mckinley.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef ASM_PARISC_MCKINLEY_H
-#define ASM_PARISC_MCKINLEY_H
-#ifdef __KERNEL__
-
-/* declared in arch/parisc/kernel/setup.c */
-extern struct proc_dir_entry * proc_mckinley_root;
-
-#endif /*__KERNEL__*/
-#endif /*ASM_PARISC_MCKINLEY_H*/
diff --git a/include/asm-parisc/mman.h b/include/asm-parisc/mman.h
deleted file mode 100644
index defe752cc996..000000000000
--- a/include/asm-parisc/mman.h
+++ /dev/null
@@ -1,61 +0,0 @@
-#ifndef __PARISC_MMAN_H__
-#define __PARISC_MMAN_H__
-
-#define PROT_READ	0x1		/* page can be read */
-#define PROT_WRITE	0x2		/* page can be written */
-#define PROT_EXEC	0x4		/* page can be executed */
-#define PROT_SEM	0x8		/* page may be used for atomic ops */
-#define PROT_NONE	0x0		/* page can not be accessed */
-#define PROT_GROWSDOWN	0x01000000	/* mprotect flag: extend change to start of growsdown vma */
-#define PROT_GROWSUP	0x02000000	/* mprotect flag: extend change to end of growsup vma */
-
-#define MAP_SHARED	0x01		/* Share changes */
-#define MAP_PRIVATE	0x02		/* Changes are private */
-#define MAP_TYPE	0x03		/* Mask for type of mapping */
-#define MAP_FIXED	0x04		/* Interpret addr exactly */
-#define MAP_ANONYMOUS	0x10		/* don't use a file */
-
-#define MAP_DENYWRITE	0x0800		/* ETXTBSY */
-#define MAP_EXECUTABLE	0x1000		/* mark it as an executable */
-#define MAP_LOCKED	0x2000		/* pages are locked */
-#define MAP_NORESERVE	0x4000		/* don't check for reservations */
-#define MAP_GROWSDOWN	0x8000		/* stack-like segment */
-#define MAP_POPULATE	0x10000		/* populate (prefault) pagetables */
-#define MAP_NONBLOCK	0x20000		/* do not block on IO */
-
-#define MS_SYNC		1		/* synchronous memory sync */
-#define MS_ASYNC	2		/* sync memory asynchronously */
-#define MS_INVALIDATE	4		/* invalidate the caches */
-
-#define MCL_CURRENT	1		/* lock all current mappings */
-#define MCL_FUTURE	2		/* lock all future mappings */
-
-#define MADV_NORMAL     0               /* no further special treatment */
-#define MADV_RANDOM     1               /* expect random page references */
-#define MADV_SEQUENTIAL 2               /* expect sequential page references */
-#define MADV_WILLNEED   3               /* will need these pages */
-#define MADV_DONTNEED   4               /* don't need these pages */
-#define MADV_SPACEAVAIL 5               /* insure that resources are reserved */
-#define MADV_VPS_PURGE  6               /* Purge pages from VM page cache */
-#define MADV_VPS_INHERIT 7              /* Inherit parents page size */
-
-/* common/generic parameters */
-#define MADV_REMOVE	9		/* remove these pages & resources */
-#define MADV_DONTFORK	10		/* don't inherit across fork */
-#define MADV_DOFORK	11		/* do inherit across fork */
-
-/* The range 12-64 is reserved for page size specification. */
-#define MADV_4K_PAGES   12              /* Use 4K pages  */
-#define MADV_16K_PAGES  14              /* Use 16K pages */
-#define MADV_64K_PAGES  16              /* Use 64K pages */
-#define MADV_256K_PAGES 18              /* Use 256K pages */
-#define MADV_1M_PAGES   20              /* Use 1 Megabyte pages */
-#define MADV_4M_PAGES   22              /* Use 4 Megabyte pages */
-#define MADV_16M_PAGES  24              /* Use 16 Megabyte pages */
-#define MADV_64M_PAGES  26              /* Use 64 Megabyte pages */
-
-/* compatibility flags */
-#define MAP_FILE	0
-#define MAP_VARIABLE	0
-
-#endif /* __PARISC_MMAN_H__ */
diff --git a/include/asm-parisc/mmu.h b/include/asm-parisc/mmu.h
deleted file mode 100644
index 6a310cf8b734..000000000000
--- a/include/asm-parisc/mmu.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _PARISC_MMU_H_
-#define _PARISC_MMU_H_
-
-/* On parisc, we store the space id here */
-typedef unsigned long mm_context_t;
-
-#endif /* _PARISC_MMU_H_ */
diff --git a/include/asm-parisc/mmu_context.h b/include/asm-parisc/mmu_context.h
deleted file mode 100644
index 85856c74ad1d..000000000000
--- a/include/asm-parisc/mmu_context.h
+++ /dev/null
@@ -1,75 +0,0 @@
-#ifndef __PARISC_MMU_CONTEXT_H
-#define __PARISC_MMU_CONTEXT_H
-
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <asm/atomic.h>
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-#include <asm-generic/mm_hooks.h>
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
-
-/* on PA-RISC, we actually have enough contexts to justify an allocator
- * for them.  prumpf */
-
-extern unsigned long alloc_sid(void);
-extern void free_sid(unsigned long);
-
-static inline int
-init_new_context(struct task_struct *tsk, struct mm_struct *mm)
-{
-	BUG_ON(atomic_read(&mm->mm_users) != 1);
-
-	mm->context = alloc_sid();
-	return 0;
-}
-
-static inline void
-destroy_context(struct mm_struct *mm)
-{
-	free_sid(mm->context);
-	mm->context = 0;
-}
-
-static inline void load_context(mm_context_t context)
-{
-	mtsp(context, 3);
-#if SPACEID_SHIFT == 0
-	mtctl(context << 1,8);
-#else
-	mtctl(context >> (SPACEID_SHIFT - 1),8);
-#endif
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
-{
-
-	if (prev != next) {
-		mtctl(__pa(next->pgd), 25);
-		load_context(next->context);
-	}
-}
-
-#define deactivate_mm(tsk,mm)	do { } while (0)
-
-static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
-{
-	/*
-	 * Activate_mm is our one chance to allocate a space id
-	 * for a new mm created in the exec path. There's also
-	 * some lazy tlb stuff, which is currently dead code, but
-	 * we only allocate a space id if one hasn't been allocated
-	 * already, so we should be OK.
-	 */
-
-	BUG_ON(next == &init_mm); /* Should never happen */
-
-	if (next->context == 0)
-	    next->context = alloc_sid();
-
-	switch_mm(prev,next,current);
-}
-#endif
diff --git a/include/asm-parisc/mmzone.h b/include/asm-parisc/mmzone.h
deleted file mode 100644
index 9608d2cf214a..000000000000
--- a/include/asm-parisc/mmzone.h
+++ /dev/null
@@ -1,73 +0,0 @@
-#ifndef _PARISC_MMZONE_H
-#define _PARISC_MMZONE_H
-
-#ifdef CONFIG_DISCONTIGMEM
-
-#define MAX_PHYSMEM_RANGES 8 /* Fix the size for now (current known max is 3) */
-extern int npmem_ranges;
-
-struct node_map_data {
-    pg_data_t pg_data;
-};
-
-extern struct node_map_data node_data[];
-
-#define NODE_DATA(nid)          (&node_data[nid].pg_data)
-
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)						\
-({									\
-	pg_data_t *__pgdat = NODE_DATA(nid);				\
-	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
-})
-
-/* We have these possible memory map layouts:
- * Astro: 0-3.75, 67.75-68, 4-64
- * zx1: 0-1, 257-260, 4-256
- * Stretch (N-class): 0-2, 4-32, 34-xxx
- */
-
-/* Since each 1GB can only belong to one region (node), we can create
- * an index table for pfn to nid lookup; each entry in pfnnid_map 
- * represents 1GB, and contains the node that the memory belongs to. */
-
-#define PFNNID_SHIFT (30 - PAGE_SHIFT)
-#define PFNNID_MAP_MAX  512     /* support 512GB */
-extern unsigned char pfnnid_map[PFNNID_MAP_MAX];
-
-#ifndef CONFIG_64BIT
-#define pfn_is_io(pfn) ((pfn & (0xf0000000UL >> PAGE_SHIFT)) == (0xf0000000UL >> PAGE_SHIFT))
-#else
-/* io can be 0xf0f0f0f0f0xxxxxx or 0xfffffffff0000000 */
-#define pfn_is_io(pfn) ((pfn & (0xf000000000000000UL >> PAGE_SHIFT)) == (0xf000000000000000UL >> PAGE_SHIFT))
-#endif
-
-static inline int pfn_to_nid(unsigned long pfn)
-{
-	unsigned int i;
-	unsigned char r;
-
-	if (unlikely(pfn_is_io(pfn)))
-		return 0;
-
-	i = pfn >> PFNNID_SHIFT;
-	BUG_ON(i >= sizeof(pfnnid_map) / sizeof(pfnnid_map[0]));
-	r = pfnnid_map[i];
-	BUG_ON(r == 0xff);
-
-	return (int)r;
-}
-
-static inline int pfn_valid(int pfn)
-{
-	int nid = pfn_to_nid(pfn);
-
-	if (nid >= 0)
-		return (pfn < node_end_pfn(nid));
-	return 0;
-}
-
-#else /* !CONFIG_DISCONTIGMEM */
-#define MAX_PHYSMEM_RANGES 	1 
-#endif
-#endif /* _PARISC_MMZONE_H */
diff --git a/include/asm-parisc/module.h b/include/asm-parisc/module.h
deleted file mode 100644
index c2cb49e934c1..000000000000
--- a/include/asm-parisc/module.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef _ASM_PARISC_MODULE_H
-#define _ASM_PARISC_MODULE_H
-/*
- * This file contains the parisc architecture specific module code.
- */
-#ifdef CONFIG_64BIT
-#define Elf_Shdr Elf64_Shdr
-#define Elf_Sym Elf64_Sym
-#define Elf_Ehdr Elf64_Ehdr
-#define Elf_Addr Elf64_Addr
-#define Elf_Rela Elf64_Rela
-#else
-#define Elf_Shdr Elf32_Shdr
-#define Elf_Sym Elf32_Sym
-#define Elf_Ehdr Elf32_Ehdr
-#define Elf_Addr Elf32_Addr
-#define Elf_Rela Elf32_Rela
-#endif
-
-struct unwind_table;
-
-struct mod_arch_specific
-{
-	unsigned long got_offset, got_count, got_max;
-	unsigned long fdesc_offset, fdesc_count, fdesc_max;
-	unsigned long stub_offset, stub_count, stub_max;
-	unsigned long init_stub_offset, init_stub_count, init_stub_max;
-	int unwind_section;
-	struct unwind_table *unwind;
-};
-
-#endif /* _ASM_PARISC_MODULE_H */
diff --git a/include/asm-parisc/msgbuf.h b/include/asm-parisc/msgbuf.h
deleted file mode 100644
index fe88f2649418..000000000000
--- a/include/asm-parisc/msgbuf.h
+++ /dev/null
@@ -1,37 +0,0 @@
-#ifndef _PARISC_MSGBUF_H
-#define _PARISC_MSGBUF_H
-
-/* 
- * The msqid64_ds structure for parisc architecture, copied from sparc.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct msqid64_ds {
-	struct ipc64_perm msg_perm;
-#ifndef CONFIG_64BIT
-	unsigned int   __pad1;
-#endif
-	__kernel_time_t msg_stime;	/* last msgsnd time */
-#ifndef CONFIG_64BIT
-	unsigned int   __pad2;
-#endif
-	__kernel_time_t msg_rtime;	/* last msgrcv time */
-#ifndef CONFIG_64BIT
-	unsigned int   __pad3;
-#endif
-	__kernel_time_t msg_ctime;	/* last change time */
-	unsigned int  msg_cbytes;	/* current number of bytes on queue */
-	unsigned int  msg_qnum;	/* number of messages in queue */
-	unsigned int  msg_qbytes;	/* max number of bytes on queue */
-	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
-	__kernel_pid_t msg_lrpid;	/* last receive pid */
-	unsigned int  __unused1;
-	unsigned int  __unused2;
-};
-
-#endif /* _PARISC_MSGBUF_H */
diff --git a/include/asm-parisc/mutex.h b/include/asm-parisc/mutex.h
deleted file mode 100644
index 458c1f7fbc18..000000000000
--- a/include/asm-parisc/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
diff --git a/include/asm-parisc/page.h b/include/asm-parisc/page.h
deleted file mode 100644
index c3941f09a878..000000000000
--- a/include/asm-parisc/page.h
+++ /dev/null
@@ -1,173 +0,0 @@
-#ifndef _PARISC_PAGE_H
-#define _PARISC_PAGE_H
-
-#include <linux/const.h>
-
-#if defined(CONFIG_PARISC_PAGE_SIZE_4KB)
-# define PAGE_SHIFT	12
-#elif defined(CONFIG_PARISC_PAGE_SIZE_16KB)
-# define PAGE_SHIFT	14
-#elif defined(CONFIG_PARISC_PAGE_SIZE_64KB)
-# define PAGE_SHIFT	16
-#else
-# error "unknown default kernel page size"
-#endif
-#define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
-#define PAGE_MASK	(~(PAGE_SIZE-1))
-
-
-#ifndef __ASSEMBLY__
-
-#include <asm/types.h>
-#include <asm/cache.h>
-
-#define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
-#define copy_page(to,from)      copy_user_page_asm((void *)(to), (void *)(from))
-
-struct page;
-
-void copy_user_page_asm(void *to, void *from);
-void copy_user_page(void *vto, void *vfrom, unsigned long vaddr,
-			   struct page *pg);
-void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
-
-/*
- * These are used to make use of C type-checking..
- */
-#define STRICT_MM_TYPECHECKS
-#ifdef STRICT_MM_TYPECHECKS
-typedef struct { unsigned long pte;
-#if !defined(CONFIG_64BIT)
-                 unsigned long future_flags;
- /* XXX: it's possible to remove future_flags and change BITS_PER_PTE_ENTRY
-	 to 2, but then strangely the identical 32bit kernel boots on a
-	 c3000(pa20), but not any longer on a 715(pa11).
-	 Still investigating... HelgeD.
-  */
-#endif
-} pte_t; /* either 32 or 64bit */
-
-/* NOTE: even on 64 bits, these entries are __u32 because we allocate
- * the pmd and pgd in ZONE_DMA (i.e. under 4GB) */
-typedef struct { __u32 pmd; } pmd_t;
-typedef struct { __u32 pgd; } pgd_t;
-typedef struct { unsigned long pgprot; } pgprot_t;
-
-#define pte_val(x)	((x).pte)
-/* These do not work lvalues, so make sure we don't use them as such. */
-#define pmd_val(x)	((x).pmd + 0)
-#define pgd_val(x)	((x).pgd + 0)
-#define pgprot_val(x)	((x).pgprot)
-
-#define __pte(x)	((pte_t) { (x) } )
-#define __pmd(x)	((pmd_t) { (x) } )
-#define __pgd(x)	((pgd_t) { (x) } )
-#define __pgprot(x)	((pgprot_t) { (x) } )
-
-#define __pmd_val_set(x,n) (x).pmd = (n)
-#define __pgd_val_set(x,n) (x).pgd = (n)
-
-#else
-/*
- * .. while these make it easier on the compiler
- */
-typedef unsigned long pte_t;
-typedef         __u32 pmd_t;
-typedef         __u32 pgd_t;
-typedef unsigned long pgprot_t;
-
-#define pte_val(x)      (x)
-#define pmd_val(x)      (x)
-#define pgd_val(x)      (x)
-#define pgprot_val(x)   (x)
-
-#define __pte(x)        (x)
-#define __pmd(x)	(x)
-#define __pgd(x)        (x)
-#define __pgprot(x)     (x)
-
-#define __pmd_val_set(x,n) (x) = (n)
-#define __pgd_val_set(x,n) (x) = (n)
-
-#endif /* STRICT_MM_TYPECHECKS */
-
-typedef struct page *pgtable_t;
-
-typedef struct __physmem_range {
-	unsigned long start_pfn;
-	unsigned long pages;       /* PAGE_SIZE pages */
-} physmem_range_t;
-
-extern physmem_range_t pmem_ranges[];
-extern int npmem_ranges;
-
-#endif /* !__ASSEMBLY__ */
-
-/* WARNING: The definitions below must match exactly to sizeof(pte_t)
- * etc
- */
-#ifdef CONFIG_64BIT
-#define BITS_PER_PTE_ENTRY	3
-#define BITS_PER_PMD_ENTRY	2
-#define BITS_PER_PGD_ENTRY	2
-#else
-#define BITS_PER_PTE_ENTRY	3
-#define BITS_PER_PMD_ENTRY	2
-#define BITS_PER_PGD_ENTRY	BITS_PER_PMD_ENTRY
-#endif
-#define PGD_ENTRY_SIZE	(1UL << BITS_PER_PGD_ENTRY)
-#define PMD_ENTRY_SIZE	(1UL << BITS_PER_PMD_ENTRY)
-#define PTE_ENTRY_SIZE	(1UL << BITS_PER_PTE_ENTRY)
-
-#define LINUX_GATEWAY_SPACE     0
-
-/* This governs the relationship between virtual and physical addresses.
- * If you alter it, make sure to take care of our various fixed mapping
- * segments in fixmap.h */
-#ifdef CONFIG_64BIT
-#define __PAGE_OFFSET	(0x40000000)	/* 1GB */
-#else
-#define __PAGE_OFFSET	(0x10000000)	/* 256MB */
-#endif
-
-#define PAGE_OFFSET		((unsigned long)__PAGE_OFFSET)
-
-/* The size of the gateway page (we leave lots of room for expansion) */
-#define GATEWAY_PAGE_SIZE	0x4000
-
-/* The start of the actual kernel binary---used in vmlinux.lds.S
- * Leave some space after __PAGE_OFFSET for detecting kernel null
- * ptr derefs */
-#define KERNEL_BINARY_TEXT_START	(__PAGE_OFFSET + 0x100000)
-
-/* These macros don't work for 64-bit C code -- don't allow in C at all */
-#ifdef __ASSEMBLY__
-#   define PA(x)	((x)-__PAGE_OFFSET)
-#   define VA(x)	((x)+__PAGE_OFFSET)
-#endif
-#define __pa(x)			((unsigned long)(x)-PAGE_OFFSET)
-#define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
-
-#ifndef CONFIG_DISCONTIGMEM
-#define pfn_valid(pfn)		((pfn) < max_mapnr)
-#endif /* CONFIG_DISCONTIGMEM */
-
-#ifdef CONFIG_HUGETLB_PAGE
-#define HPAGE_SHIFT		22	/* 4MB (is this fixed?) */
-#define HPAGE_SIZE      	((1UL) << HPAGE_SHIFT)
-#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
-#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
-#endif
-
-#define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
-
-#define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
-#define virt_to_page(kaddr)     pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-
-#define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
-				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
-#include <asm-generic/memory_model.h>
-#include <asm-generic/page.h>
-
-#endif /* _PARISC_PAGE_H */
diff --git a/include/asm-parisc/param.h b/include/asm-parisc/param.h
deleted file mode 100644
index 32e03d877858..000000000000
--- a/include/asm-parisc/param.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _ASMPARISC_PARAM_H
-#define _ASMPARISC_PARAM_H
-
-#ifdef __KERNEL__
-#define HZ		CONFIG_HZ
-#define USER_HZ		100		/* some user API use "ticks" */
-#define CLOCKS_PER_SEC	(USER_HZ)	/* like times() */
-#endif
-
-#ifndef HZ
-#define HZ 100
-#endif
-
-#define EXEC_PAGESIZE	4096
-
-#ifndef NOGROUP
-#define NOGROUP		(-1)
-#endif
-
-#define MAXHOSTNAMELEN	64	/* max length of hostname */
-
-#endif
diff --git a/include/asm-parisc/parisc-device.h b/include/asm-parisc/parisc-device.h
deleted file mode 100644
index 7aa13f2add7a..000000000000
--- a/include/asm-parisc/parisc-device.h
+++ /dev/null
@@ -1,64 +0,0 @@
-#ifndef _ASM_PARISC_PARISC_DEVICE_H_
-#define _ASM_PARISC_PARISC_DEVICE_H_
-
-#include <linux/device.h>
-
-struct parisc_device {
-	struct resource hpa;		/* Hard Physical Address */
-	struct parisc_device_id id;
-	struct parisc_driver *driver;	/* Driver for this device */
-	char		name[80];	/* The hardware description */
-	int		irq;
-	int		aux_irq;	/* Some devices have a second IRQ */
-
-	char		hw_path;        /* The module number on this bus */
-	unsigned int	num_addrs;	/* some devices have additional address ranges. */
-	unsigned long	*addr;          /* which will be stored here */
- 
-#ifdef CONFIG_64BIT
-	/* parms for pdc_pat_cell_module() call */
-	unsigned long	pcell_loc;	/* Physical Cell location */
-	unsigned long	mod_index;	/* PAT specific - Misc Module info */
-
-	/* generic info returned from pdc_pat_cell_module() */
-	unsigned long	mod_info;	/* PAT specific - Misc Module info */
-	unsigned long	pmod_loc;	/* physical Module location */
-#endif
-	u64		dma_mask;	/* DMA mask for I/O */
-	struct device 	dev;
-};
-
-struct parisc_driver {
-	struct parisc_driver *next;
-	char *name; 
-	const struct parisc_device_id *id_table;
-	int (*probe) (struct parisc_device *dev); /* New device discovered */
-	int (*remove) (struct parisc_device *dev);
-	struct device_driver drv;
-};
-
-
-#define to_parisc_device(d)	container_of(d, struct parisc_device, dev)
-#define to_parisc_driver(d)	container_of(d, struct parisc_driver, drv)
-#define parisc_parent(d)	to_parisc_device(d->dev.parent)
-
-static inline char *parisc_pathname(struct parisc_device *d)
-{
-	return d->dev.bus_id;
-}
-
-static inline void
-parisc_set_drvdata(struct parisc_device *d, void *p)
-{
-	dev_set_drvdata(&d->dev, p);
-}
-
-static inline void *
-parisc_get_drvdata(struct parisc_device *d)
-{
-	return dev_get_drvdata(&d->dev);
-}
-
-extern struct bus_type parisc_bus_type;
-
-#endif /*_ASM_PARISC_PARISC_DEVICE_H_*/
diff --git a/include/asm-parisc/parport.h b/include/asm-parisc/parport.h
deleted file mode 100644
index 00d9cc3e7b97..000000000000
--- a/include/asm-parisc/parport.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* 
- *
- * parport.h: ia32-compatible parport initialisation
- *
- * This file should only be included by drivers/parport/parport_pc.c.
- */
-#ifndef _ASM_PARPORT_H
-#define _ASM_PARPORT_H 1
-
-
-static int __devinit parport_pc_find_nonpci_ports (int autoirq, int autodma)
-{
-	/* nothing ! */
-	return 0;
-}
-
-
-#endif /* !(_ASM_PARPORT_H) */
diff --git a/include/asm-parisc/pci.h b/include/asm-parisc/pci.h
deleted file mode 100644
index 4ba868f44a5e..000000000000
--- a/include/asm-parisc/pci.h
+++ /dev/null
@@ -1,294 +0,0 @@
-#ifndef __ASM_PARISC_PCI_H
-#define __ASM_PARISC_PCI_H
-
-#include <asm/scatterlist.h>
-
-
-
-/*
-** HP PCI platforms generally support multiple bus adapters.
-**    (workstations 1-~4, servers 2-~32)
-**
-** Newer platforms number the busses across PCI bus adapters *sparsely*.
-** E.g. 0, 8, 16, ...
-**
-** Under a PCI bus, most HP platforms support PPBs up to two or three
-** levels deep. See "Bit3" product line. 
-*/
-#define PCI_MAX_BUSSES	256
-
-
-/* To be used as: mdelay(pci_post_reset_delay);
- *
- * post_reset is the time the kernel should stall to prevent anyone from
- * accessing the PCI bus once #RESET is de-asserted. 
- * PCI spec somewhere says 1 second but with multi-PCI bus systems,
- * this makes the boot time much longer than necessary.
- * 20ms seems to work for all the HP PCI implementations to date.
- */
-#define pci_post_reset_delay 50
-
-
-/*
-** pci_hba_data (aka H2P_OBJECT in HP/UX)
-**
-** This is the "common" or "base" data structure which HBA drivers
-** (eg Dino or LBA) are required to place at the top of their own
-** platform_data structure.  I've heard this called "C inheritance" too.
-**
-** Data needed by pcibios layer belongs here.
-*/
-struct pci_hba_data {
-	void __iomem   *base_addr;	/* aka Host Physical Address */
-	const struct parisc_device *dev; /* device from PA bus walk */
-	struct pci_bus *hba_bus;	/* primary PCI bus below HBA */
-	int		hba_num;	/* I/O port space access "key" */
-	struct resource bus_num;	/* PCI bus numbers */
-	struct resource io_space;	/* PIOP */
-	struct resource lmmio_space;	/* bus addresses < 4Gb */
-	struct resource elmmio_space;	/* additional bus addresses < 4Gb */
-	struct resource gmmio_space;	/* bus addresses > 4Gb */
-
-	/* NOTE: Dino code assumes it can use *all* of the lmmio_space,
-	 * elmmio_space and gmmio_space as a contiguous array of
-	 * resources.  This #define represents the array size */
-	#define DINO_MAX_LMMIO_RESOURCES	3
-
-	unsigned long   lmmio_space_offset;  /* CPU view - PCI view */
-	void *          iommu;          /* IOMMU this device is under */
-	/* REVISIT - spinlock to protect resources? */
-
-	#define HBA_NAME_SIZE 16
-	char io_name[HBA_NAME_SIZE];
-	char lmmio_name[HBA_NAME_SIZE];
-	char elmmio_name[HBA_NAME_SIZE];
-	char gmmio_name[HBA_NAME_SIZE];
-};
-
-#define HBA_DATA(d)		((struct pci_hba_data *) (d))
-
-/* 
-** We support 2^16 I/O ports per HBA.  These are set up in the form
-** 0xbbxxxx, where bb is the bus number and xxxx is the I/O port
-** space address.
-*/
-#define HBA_PORT_SPACE_BITS	16
-
-#define HBA_PORT_BASE(h)	((h) << HBA_PORT_SPACE_BITS)
-#define HBA_PORT_SPACE_SIZE	(1UL << HBA_PORT_SPACE_BITS)
-
-#define PCI_PORT_HBA(a)		((a) >> HBA_PORT_SPACE_BITS)
-#define PCI_PORT_ADDR(a)	((a) & (HBA_PORT_SPACE_SIZE - 1))
-
-#ifdef CONFIG_64BIT
-#define PCI_F_EXTEND		0xffffffff00000000UL
-#define PCI_IS_LMMIO(hba,a)	pci_is_lmmio(hba,a)
-
-/* We need to know if an address is LMMMIO or GMMIO.
- * LMMIO requires mangling and GMMIO we must use as-is.
- */
-static __inline__  int pci_is_lmmio(struct pci_hba_data *hba, unsigned long a)
-{
-	return(((a) & PCI_F_EXTEND) == PCI_F_EXTEND);
-}
-
-/*
-** Convert between PCI (IO_VIEW) addresses and processor (PA_VIEW) addresses.
-** See pci.c for more conversions used by Generic PCI code.
-**
-** Platform characteristics/firmware guarantee that
-**	(1) PA_VIEW - IO_VIEW = lmmio_offset for both LMMIO and ELMMIO
-**	(2) PA_VIEW == IO_VIEW for GMMIO
-*/
-#define PCI_BUS_ADDR(hba,a)	(PCI_IS_LMMIO(hba,a)	\
-		?  ((a) - hba->lmmio_space_offset)	/* mangle LMMIO */ \
-		: (a))					/* GMMIO */
-#define PCI_HOST_ADDR(hba,a)	(((a) & PCI_F_EXTEND) == 0 \
-		? (a) + hba->lmmio_space_offset \
-		: (a))
-
-#else	/* !CONFIG_64BIT */
-
-#define PCI_BUS_ADDR(hba,a)	(a)
-#define PCI_HOST_ADDR(hba,a)	(a)
-#define PCI_F_EXTEND		0UL
-#define PCI_IS_LMMIO(hba,a)	(1)	/* 32-bit doesn't support GMMIO */
-
-#endif /* !CONFIG_64BIT */
-
-/*
-** KLUGE: linux/pci.h include asm/pci.h BEFORE declaring struct pci_bus
-** (This eliminates some of the warnings).
-*/
-struct pci_bus;
-struct pci_dev;
-
-/*
- * If the PCI device's view of memory is the same as the CPU's view of memory,
- * PCI_DMA_BUS_IS_PHYS is true.  The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#ifdef CONFIG_PA20
-/* All PA-2.0 machines have an IOMMU. */
-#define PCI_DMA_BUS_IS_PHYS	0
-#define parisc_has_iommu()	do { } while (0)
-#else
-
-#if defined(CONFIG_IOMMU_CCIO) || defined(CONFIG_IOMMU_SBA)
-extern int parisc_bus_is_phys; 	/* in arch/parisc/kernel/setup.c */
-#define PCI_DMA_BUS_IS_PHYS	parisc_bus_is_phys
-#define parisc_has_iommu()	do { parisc_bus_is_phys = 0; } while (0)
-#else
-#define PCI_DMA_BUS_IS_PHYS	1
-#define parisc_has_iommu()	do { } while (0)
-#endif
-
-#endif	/* !CONFIG_PA20 */
-
-
-/*
-** Most PCI devices (eg Tulip, NCR720) also export the same registers
-** to both MMIO and I/O port space.  Due to poor performance of I/O Port
-** access under HP PCI bus adapters, strongly recommend the use of MMIO
-** address space.
-**
-** While I'm at it more PA programming notes:
-**
-** 1) MMIO stores (writes) are posted operations. This means the processor
-**    gets an "ACK" before the write actually gets to the device. A read
-**    to the same device (or typically the bus adapter above it) will
-**    force in-flight write transaction(s) out to the targeted device
-**    before the read can complete.
-**
-** 2) The Programmed I/O (PIO) data may not always be strongly ordered with
-**    respect to DMA on all platforms. Ie PIO data can reach the processor
-**    before in-flight DMA reaches memory. Since most SMP PA platforms
-**    are I/O coherent, it generally doesn't matter...but sometimes
-**    it does.
-**
-** I've helped device driver writers debug both types of problems.
-*/
-struct pci_port_ops {
-	  u8 (*inb)  (struct pci_hba_data *hba, u16 port);
-	 u16 (*inw)  (struct pci_hba_data *hba, u16 port);
-	 u32 (*inl)  (struct pci_hba_data *hba, u16 port);
-	void (*outb) (struct pci_hba_data *hba, u16 port,  u8 data);
-	void (*outw) (struct pci_hba_data *hba, u16 port, u16 data);
-	void (*outl) (struct pci_hba_data *hba, u16 port, u32 data);
-};
-
-
-struct pci_bios_ops {
-	void (*init)(void);
-	void (*fixup_bus)(struct pci_bus *bus);
-};
-
-/* pci_unmap_{single,page} is not a nop, thus... */
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	\
-	dma_addr_t ADDR_NAME;
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)		\
-	__u32 LEN_NAME;
-#define pci_unmap_addr(PTR, ADDR_NAME)			\
-	((PTR)->ADDR_NAME)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)		\
-	(((PTR)->ADDR_NAME) = (VAL))
-#define pci_unmap_len(PTR, LEN_NAME)			\
-	((PTR)->LEN_NAME)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)		\
-	(((PTR)->LEN_NAME) = (VAL))
-
-/*
-** Stuff declared in arch/parisc/kernel/pci.c
-*/
-extern struct pci_port_ops *pci_port;
-extern struct pci_bios_ops *pci_bios;
-
-#ifdef CONFIG_PCI
-extern void pcibios_register_hba(struct pci_hba_data *);
-extern void pcibios_set_master(struct pci_dev *);
-#else
-static inline void pcibios_register_hba(struct pci_hba_data *x)
-{
-}
-#endif
-
-/*
- * pcibios_assign_all_busses() is used in drivers/pci/pci.c:pci_do_scan_bus()
- *   0 == check if bridge is numbered before re-numbering.
- *   1 == pci_do_scan_bus() should automatically number all PCI-PCI bridges.
- *
- *   We *should* set this to zero for "legacy" platforms and one
- *   for PAT platforms.
- *
- *   But legacy platforms also need to renumber the busses below a Host
- *   Bus controller.  Adding a 4-port Tulip card on the first PCI root
- *   bus of a C200 resulted in the secondary bus being numbered as 1.
- *   The second PCI host bus controller's root bus had already been
- *   assigned bus number 1 by firmware and sysfs complained.
- *
- *   Firmware isn't doing anything wrong here since each controller
- *   is its own PCI domain.  It's simpler and easier for us to renumber
- *   the busses rather than treat each Dino as a separate PCI domain.
- *   Eventually, we may want to introduce PCI domains for Superdome or
- *   rp7420/8420 boxes and then revisit this issue.
- */
-#define pcibios_assign_all_busses()     (1)
-#define pcibios_scan_all_fns(a, b)	(0)
-
-#define PCIBIOS_MIN_IO          0x10
-#define PCIBIOS_MIN_MEM         0x1000 /* NBPG - but pci/setup-res.c dies */
-
-/* export the pci_ DMA API in terms of the dma_ one */
-#include <asm-generic/pci-dma-compat.h>
-
-#ifdef CONFIG_PCI
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	unsigned long cacheline_size;
-	u8 byte;
-
-	pci_read_config_byte(pdev, PCI_CACHE_LINE_SIZE, &byte);
-	if (byte == 0)
-		cacheline_size = 1024;
-	else
-		cacheline_size = (int) byte * 4;
-
-	*strat = PCI_DMA_BURST_MULTIPLE;
-	*strategy_parameter = cacheline_size;
-}
-#endif
-
-extern void
-pcibios_resource_to_bus(struct pci_dev *dev, struct pci_bus_region *region,
-			 struct resource *res);
-
-extern void
-pcibios_bus_to_resource(struct pci_dev *dev, struct resource *res,
-			struct pci_bus_region *region);
-
-static inline struct resource *
-pcibios_select_root(struct pci_dev *pdev, struct resource *res)
-{
-	struct resource *root = NULL;
-
-	if (res->flags & IORESOURCE_IO)
-		root = &ioport_resource;
-	if (res->flags & IORESOURCE_MEM)
-		root = &iomem_resource;
-
-	return root;
-}
-
-static inline void pcibios_penalize_isa_irq(int irq, int active)
-{
-	/* We don't need to penalize isa irq's */
-}
-
-static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
-{
-	return channel ? 15 : 14;
-}
-
-#endif /* __ASM_PARISC_PCI_H */
diff --git a/include/asm-parisc/pdc.h b/include/asm-parisc/pdc.h
deleted file mode 100644
index 46b75f9cce51..000000000000
--- a/include/asm-parisc/pdc.h
+++ /dev/null
@@ -1,760 +0,0 @@
-#ifndef _PARISC_PDC_H
-#define _PARISC_PDC_H
-
-/*
- *	PDC return values ...
- *	All PDC calls return a subset of these errors. 
- */
-
-#define PDC_WARN		  3	/* Call completed with a warning */
-#define PDC_REQ_ERR_1		  2	/* See above			 */
-#define PDC_REQ_ERR_0		  1	/* Call would generate a requestor error */
-#define PDC_OK			  0	/* Call completed successfully	*/
-#define PDC_BAD_PROC		 -1	/* Called non-existent procedure*/
-#define PDC_BAD_OPTION		 -2	/* Called with non-existent option */
-#define PDC_ERROR		 -3	/* Call could not complete without an error */
-#define PDC_NE_MOD		 -5	/* Module not found		*/
-#define PDC_NE_CELL_MOD		 -7	/* Cell module not found	*/
-#define PDC_INVALID_ARG		-10	/* Called with an invalid argument */
-#define PDC_BUS_POW_WARN	-12	/* Call could not complete in allowed power budget */
-#define PDC_NOT_NARROW		-17	/* Narrow mode not supported	*/
-
-/*
- *	PDC entry points...
- */
-
-#define PDC_POW_FAIL	1		/* perform a power-fail		*/
-#define PDC_POW_FAIL_PREPARE	0	/* prepare for powerfail	*/
-
-#define PDC_CHASSIS	2		/* PDC-chassis functions	*/
-#define PDC_CHASSIS_DISP	0	/* update chassis display	*/
-#define PDC_CHASSIS_WARN	1	/* return chassis warnings	*/
-#define PDC_CHASSIS_DISPWARN	2	/* update&return chassis status */
-#define PDC_RETURN_CHASSIS_INFO 128	/* HVERSION dependent: return chassis LED/LCD info  */
-
-#define PDC_PIM         3               /* Get PIM data                 */
-#define PDC_PIM_HPMC            0       /* Transfer HPMC data           */
-#define PDC_PIM_RETURN_SIZE     1       /* Get Max buffer needed for PIM*/
-#define PDC_PIM_LPMC            2       /* Transfer HPMC data           */
-#define PDC_PIM_SOFT_BOOT       3       /* Transfer Soft Boot data      */
-#define PDC_PIM_TOC             4       /* Transfer TOC data            */
-
-#define PDC_MODEL	4		/* PDC model information call	*/
-#define PDC_MODEL_INFO		0	/* returns information 		*/
-#define PDC_MODEL_BOOTID	1	/* set the BOOT_ID		*/
-#define PDC_MODEL_VERSIONS	2	/* returns cpu-internal versions*/
-#define PDC_MODEL_SYSMODEL	3	/* return system model info	*/
-#define PDC_MODEL_ENSPEC	4	/* enable specific option	*/
-#define PDC_MODEL_DISPEC	5	/* disable specific option	*/
-#define PDC_MODEL_CPU_ID	6	/* returns cpu-id (only newer machines!) */
-#define PDC_MODEL_CAPABILITIES	7	/* returns OS32/OS64-flags	*/
-/* Values for PDC_MODEL_CAPABILITIES non-equivalent virtual aliasing support */
-#define  PDC_MODEL_IOPDIR_FDC		(1 << 2)
-#define  PDC_MODEL_NVA_MASK		(3 << 4)
-#define  PDC_MODEL_NVA_SUPPORTED	(0 << 4)
-#define  PDC_MODEL_NVA_SLOW		(1 << 4)
-#define  PDC_MODEL_NVA_UNSUPPORTED	(3 << 4)
-#define PDC_MODEL_GET_BOOT__OP	8	/* returns boot test options	*/
-#define PDC_MODEL_SET_BOOT__OP	9	/* set boot test options	*/
-
-#define PA89_INSTRUCTION_SET	0x4	/* capatibilies returned	*/
-#define PA90_INSTRUCTION_SET	0x8
-
-#define PDC_CACHE	5		/* return/set cache (& TLB) info*/
-#define PDC_CACHE_INFO		0	/* returns information 		*/
-#define PDC_CACHE_SET_COH	1	/* set coherence state		*/
-#define PDC_CACHE_RET_SPID	2	/* returns space-ID bits	*/
-
-#define PDC_HPA		6		/* return HPA of processor	*/
-#define PDC_HPA_PROCESSOR	0
-#define PDC_HPA_MODULES		1
-
-#define PDC_COPROC	7		/* Co-Processor (usually FP unit(s)) */
-#define PDC_COPROC_CFG		0	/* Co-Processor Cfg (FP unit(s) enabled?) */
-
-#define PDC_IODC	8		/* talk to IODC			*/
-#define PDC_IODC_READ		0	/* read IODC entry point	*/
-/*      PDC_IODC_RI_			 * INDEX parameter of PDC_IODC_READ */
-#define PDC_IODC_RI_DATA_BYTES	0	/* IODC Data Bytes		*/
-/*				1, 2	   obsolete - HVERSION dependent*/
-#define PDC_IODC_RI_INIT	3	/* Initialize module		*/
-#define PDC_IODC_RI_IO		4	/* Module input/output		*/
-#define PDC_IODC_RI_SPA		5	/* Module input/output		*/
-#define PDC_IODC_RI_CONFIG	6	/* Module input/output		*/
-/*				7	  obsolete - HVERSION dependent */
-#define PDC_IODC_RI_TEST	8	/* Module input/output		*/
-#define PDC_IODC_RI_TLB		9	/* Module input/output		*/
-#define PDC_IODC_NINIT		2	/* non-destructive init		*/
-#define PDC_IODC_DINIT		3	/* destructive init		*/
-#define PDC_IODC_MEMERR		4	/* check for memory errors	*/
-#define PDC_IODC_INDEX_DATA	0	/* get first 16 bytes from mod IODC */
-#define PDC_IODC_BUS_ERROR	-4	/* bus error return value	*/
-#define PDC_IODC_INVALID_INDEX	-5	/* invalid index return value	*/
-#define PDC_IODC_COUNT		-6	/* count is too small		*/
-
-#define PDC_TOD		9		/* time-of-day clock (TOD)	*/
-#define PDC_TOD_READ		0	/* read TOD			*/
-#define PDC_TOD_WRITE		1	/* write TOD			*/
-
-
-#define PDC_STABLE	10		/* stable storage (sprockets)	*/
-#define PDC_STABLE_READ		0
-#define PDC_STABLE_WRITE	1
-#define PDC_STABLE_RETURN_SIZE	2
-#define PDC_STABLE_VERIFY_CONTENTS 3
-#define PDC_STABLE_INITIALIZE	4
-
-#define PDC_NVOLATILE	11		/* often not implemented	*/
-
-#define PDC_ADD_VALID	12		/* Memory validation PDC call	*/
-#define PDC_ADD_VALID_VERIFY	0	/* Make PDC_ADD_VALID verify region */
-
-#define PDC_INSTR	15		/* get instr to invoke PDCE_CHECK() */
-
-#define PDC_PROC	16		/* (sprockets)			*/
-
-#define PDC_CONFIG	16		/* (sprockets)			*/
-#define PDC_CONFIG_DECONFIG	0
-#define PDC_CONFIG_DRECONFIG	1
-#define PDC_CONFIG_DRETURN_CONFIG 2
-
-#define PDC_BLOCK_TLB	18		/* manage hardware block-TLB	*/
-#define PDC_BTLB_INFO		0	/* returns parameter 		*/
-#define PDC_BTLB_INSERT		1	/* insert BTLB entry		*/
-#define PDC_BTLB_PURGE		2	/* purge BTLB entries 		*/
-#define PDC_BTLB_PURGE_ALL	3	/* purge all BTLB entries 	*/
-
-#define PDC_TLB		19		/* manage hardware TLB miss handling */
-#define PDC_TLB_INFO		0	/* returns parameter 		*/
-#define PDC_TLB_SETUP		1	/* set up miss handling 	*/
-
-#define PDC_MEM		20		/* Manage memory		*/
-#define PDC_MEM_MEMINFO		0
-#define PDC_MEM_ADD_PAGE	1
-#define PDC_MEM_CLEAR_PDT	2
-#define PDC_MEM_READ_PDT	3
-#define PDC_MEM_RESET_CLEAR	4
-#define PDC_MEM_GOODMEM		5
-#define PDC_MEM_TABLE		128	/* Non contig mem map (sprockets) */
-#define PDC_MEM_RETURN_ADDRESS_TABLE	PDC_MEM_TABLE
-#define PDC_MEM_GET_MEMORY_SYSTEM_TABLES_SIZE	131
-#define PDC_MEM_GET_MEMORY_SYSTEM_TABLES	132
-#define PDC_MEM_GET_PHYSICAL_LOCATION_FROM_MEMORY_ADDRESS 133
-
-#define PDC_MEM_RET_SBE_REPLACED	5	/* PDC_MEM return values */
-#define PDC_MEM_RET_DUPLICATE_ENTRY	4
-#define PDC_MEM_RET_BUF_SIZE_SMALL	1
-#define PDC_MEM_RET_PDT_FULL		-11
-#define PDC_MEM_RET_INVALID_PHYSICAL_LOCATION ~0ULL
-
-#define PDC_PSW		21		/* Get/Set default System Mask  */
-#define PDC_PSW_MASK		0	/* Return mask                  */
-#define PDC_PSW_GET_DEFAULTS	1	/* Return defaults              */
-#define PDC_PSW_SET_DEFAULTS	2	/* Set default                  */
-#define PDC_PSW_ENDIAN_BIT	1	/* set for big endian           */
-#define PDC_PSW_WIDE_BIT	2	/* set for wide mode            */ 
-
-#define PDC_SYSTEM_MAP	22		/* find system modules		*/
-#define PDC_FIND_MODULE 	0
-#define PDC_FIND_ADDRESS	1
-#define PDC_TRANSLATE_PATH	2
-
-#define PDC_SOFT_POWER	23		/* soft power switch		*/
-#define PDC_SOFT_POWER_INFO	0	/* return info about the soft power switch */
-#define PDC_SOFT_POWER_ENABLE	1	/* enable/disable soft power switch */
-
-
-/* HVERSION dependent */
-
-/* The PDC_MEM_MAP calls */
-#define PDC_MEM_MAP	128		/* on s700: return page info	*/
-#define PDC_MEM_MAP_HPA		0	/* returns hpa of a module	*/
-
-#define PDC_EEPROM	129		/* EEPROM access		*/
-#define PDC_EEPROM_READ_WORD	0
-#define PDC_EEPROM_WRITE_WORD	1
-#define PDC_EEPROM_READ_BYTE	2
-#define PDC_EEPROM_WRITE_BYTE	3
-#define PDC_EEPROM_EEPROM_PASSWORD -1000
-
-#define PDC_NVM		130		/* NVM (non-volatile memory) access */
-#define PDC_NVM_READ_WORD	0
-#define PDC_NVM_WRITE_WORD	1
-#define PDC_NVM_READ_BYTE	2
-#define PDC_NVM_WRITE_BYTE	3
-
-#define PDC_SEED_ERROR	132		/* (sprockets)			*/
-
-#define PDC_IO		135		/* log error info, reset IO system */
-#define PDC_IO_READ_AND_CLEAR_ERRORS	0
-#define PDC_IO_RESET			1
-#define PDC_IO_RESET_DEVICES		2
-/* sets bits 6&7 (little endian) of the HcControl Register */
-#define PDC_IO_USB_SUSPEND	0xC000000000000000
-#define PDC_IO_EEPROM_IO_ERR_TABLE_FULL	-5	/* return value */
-#define PDC_IO_NO_SUSPEND		-6	/* return value */
-
-#define PDC_BROADCAST_RESET 136		/* reset all processors		*/
-#define PDC_DO_RESET		0	/* option: perform a broadcast reset */
-#define PDC_DO_FIRM_TEST_RESET	1	/* Do broadcast reset with bitmap */
-#define PDC_BR_RECONFIGURATION	2	/* reset w/reconfiguration	*/
-#define PDC_FIRM_TEST_MAGIC	0xab9ec36fUL    /* for this reboot only	*/
-
-#define PDC_LAN_STATION_ID 138		/* Hversion dependent mechanism for */
-#define PDC_LAN_STATION_ID_READ	0	/* getting the lan station address  */
-
-#define	PDC_LAN_STATION_ID_SIZE	6
-
-#define PDC_CHECK_RANGES 139		/* (sprockets)			*/
-
-#define PDC_NV_SECTIONS	141		/* (sprockets)			*/
-
-#define PDC_PERFORMANCE	142		/* performance monitoring	*/
-
-#define PDC_SYSTEM_INFO	143		/* system information		*/
-#define PDC_SYSINFO_RETURN_INFO_SIZE	0
-#define PDC_SYSINFO_RRETURN_SYS_INFO	1
-#define PDC_SYSINFO_RRETURN_ERRORS	2
-#define PDC_SYSINFO_RRETURN_WARNINGS	3
-#define PDC_SYSINFO_RETURN_REVISIONS	4
-#define PDC_SYSINFO_RRETURN_DIAGNOSE	5
-#define PDC_SYSINFO_RRETURN_HV_DIAGNOSE	1005
-
-#define PDC_RDR		144		/* (sprockets)			*/
-#define PDC_RDR_READ_BUFFER	0
-#define PDC_RDR_READ_SINGLE	1
-#define PDC_RDR_WRITE_SINGLE	2
-
-#define PDC_INTRIGUE	145 		/* (sprockets)			*/
-#define PDC_INTRIGUE_WRITE_BUFFER 	 0
-#define PDC_INTRIGUE_GET_SCRATCH_BUFSIZE 1
-#define PDC_INTRIGUE_START_CPU_COUNTERS	 2
-#define PDC_INTRIGUE_STOP_CPU_COUNTERS	 3
-
-#define PDC_STI		146 		/* STI access			*/
-/* same as PDC_PCI_XXX values (see below) */
-
-/* Legacy PDC definitions for same stuff */
-#define PDC_PCI_INDEX	147
-#define PDC_PCI_INTERFACE_INFO		0
-#define PDC_PCI_SLOT_INFO		1
-#define PDC_PCI_INFLIGHT_BYTES		2
-#define PDC_PCI_READ_CONFIG		3
-#define PDC_PCI_WRITE_CONFIG		4
-#define PDC_PCI_READ_PCI_IO		5
-#define PDC_PCI_WRITE_PCI_IO		6
-#define PDC_PCI_READ_CONFIG_DELAY	7
-#define PDC_PCI_UPDATE_CONFIG_DELAY	8
-#define PDC_PCI_PCI_PATH_TO_PCI_HPA	9
-#define PDC_PCI_PCI_HPA_TO_PCI_PATH	10
-#define PDC_PCI_PCI_PATH_TO_PCI_BUS	11
-#define PDC_PCI_PCI_RESERVED		12
-#define PDC_PCI_PCI_INT_ROUTE_SIZE	13
-#define PDC_PCI_GET_INT_TBL_SIZE	PDC_PCI_PCI_INT_ROUTE_SIZE
-#define PDC_PCI_PCI_INT_ROUTE		14
-#define PDC_PCI_GET_INT_TBL		PDC_PCI_PCI_INT_ROUTE 
-#define PDC_PCI_READ_MON_TYPE		15
-#define PDC_PCI_WRITE_MON_TYPE		16
-
-
-/* Get SCSI Interface Card info:  SDTR, SCSI ID, mode (SE vs LVD) */
-#define PDC_INITIATOR	163
-#define PDC_GET_INITIATOR	0
-#define PDC_SET_INITIATOR	1
-#define PDC_DELETE_INITIATOR	2
-#define PDC_RETURN_TABLE_SIZE	3
-#define PDC_RETURN_TABLE	4
-
-#define PDC_LINK	165 		/* (sprockets)			*/
-#define PDC_LINK_PCI_ENTRY_POINTS	0  /* list (Arg1) = 0 */
-#define PDC_LINK_USB_ENTRY_POINTS	1  /* list (Arg1) = 1 */
-
-/* cl_class
- * page 3-33 of IO-Firmware ARS
- * IODC ENTRY_INIT(Search first) RET[1]
- */
-#define	CL_NULL		0	/* invalid */
-#define	CL_RANDOM	1	/* random access (as disk) */
-#define	CL_SEQU		2	/* sequential access (as tape) */
-#define	CL_DUPLEX	7	/* full-duplex point-to-point (RS-232, Net) */
-#define	CL_KEYBD	8	/* half-duplex console (HIL Keyboard) */
-#define	CL_DISPL	9	/* half-duplex console (display) */
-#define	CL_FC		10	/* FiberChannel access media */
-
-/* IODC ENTRY_INIT() */
-#define ENTRY_INIT_SRCH_FRST	2
-#define ENTRY_INIT_SRCH_NEXT	3
-#define ENTRY_INIT_MOD_DEV	4
-#define ENTRY_INIT_DEV		5
-#define ENTRY_INIT_MOD		6
-#define ENTRY_INIT_MSG		9
-
-/* IODC ENTRY_IO() */
-#define ENTRY_IO_BOOTIN		0
-#define ENTRY_IO_BOOTOUT	1
-#define ENTRY_IO_CIN		2
-#define ENTRY_IO_COUT		3
-#define ENTRY_IO_CLOSE		4
-#define ENTRY_IO_GETMSG		9
-#define ENTRY_IO_BBLOCK_IN	16
-#define ENTRY_IO_BBLOCK_OUT	17
-
-/* IODC ENTRY_SPA() */
-
-/* IODC ENTRY_CONFIG() */
-
-/* IODC ENTRY_TEST() */
-
-/* IODC ENTRY_TLB() */
-
-/* constants for OS (NVM...) */
-#define OS_ID_NONE		0	/* Undefined OS ID	*/
-#define OS_ID_HPUX		1	/* HP-UX OS		*/
-#define OS_ID_MPEXL		2	/* MPE XL OS		*/
-#define OS_ID_OSF		3	/* OSF OS		*/
-#define OS_ID_HPRT		4	/* HP-RT OS		*/
-#define OS_ID_NOVEL		5	/* NOVELL OS		*/
-#define OS_ID_LINUX		6	/* Linux		*/
-
-
-/* constants for PDC_CHASSIS */
-#define OSTAT_OFF		0
-#define OSTAT_FLT		1 
-#define OSTAT_TEST		2
-#define OSTAT_INIT		3
-#define OSTAT_SHUT		4
-#define OSTAT_WARN		5
-#define OSTAT_RUN		6
-#define OSTAT_ON		7
-
-/* Page Zero constant offsets used by the HPMC handler */
-#define BOOT_CONSOLE_HPA_OFFSET  0x3c0
-#define BOOT_CONSOLE_SPA_OFFSET  0x3c4
-#define BOOT_CONSOLE_PATH_OFFSET 0x3a8
-
-/* size of the pdc_result buffer for firmware.c */
-#define NUM_PDC_RESULT	32
-
-#if !defined(__ASSEMBLY__)
-#ifdef __KERNEL__
-
-#include <linux/types.h>
-
-extern int pdc_type;
-
-/* Values for pdc_type */
-#define PDC_TYPE_ILLEGAL	-1
-#define PDC_TYPE_PAT		 0 /* 64-bit PAT-PDC */
-#define PDC_TYPE_SYSTEM_MAP	 1 /* 32-bit, but supports PDC_SYSTEM_MAP */
-#define PDC_TYPE_SNAKE		 2 /* Doesn't support SYSTEM_MAP */
-
-struct pdc_chassis_info {       /* for PDC_CHASSIS_INFO */
-	unsigned long actcnt;   /* actual number of bytes returned */
-	unsigned long maxcnt;   /* maximum number of bytes that could be returned */
-};
-
-struct pdc_coproc_cfg {         /* for PDC_COPROC_CFG */
-        unsigned long ccr_functional;
-        unsigned long ccr_present;
-        unsigned long revision;
-        unsigned long model;
-};
-
-struct pdc_model {		/* for PDC_MODEL */
-	unsigned long hversion;
-	unsigned long sversion;
-	unsigned long hw_id;
-	unsigned long boot_id;
-	unsigned long sw_id;
-	unsigned long sw_cap;
-	unsigned long arch_rev;
-	unsigned long pot_key;
-	unsigned long curr_key;
-};
-
-struct pdc_cache_cf {		/* for PDC_CACHE  (I/D-caches) */
-    unsigned long
-#ifdef CONFIG_64BIT
-		cc_padW:32,
-#endif
-		cc_alias: 4,	/* alias boundaries for virtual addresses   */
-		cc_block: 4,	/* to determine most efficient stride */
-		cc_line	: 3,	/* maximum amount written back as a result of store (multiple of 16 bytes) */
-		cc_shift: 2,	/* how much to shift cc_block left */
-		cc_wt	: 1,	/* 0 = WT-Dcache, 1 = WB-Dcache */
-		cc_sh	: 2,	/* 0 = separate I/D-cache, else shared I/D-cache */
-		cc_cst  : 3,	/* 0 = incoherent D-cache, 1=coherent D-cache */
-		cc_pad1 : 10,	/* reserved */
-		cc_hv   : 3;	/* hversion dependent */
-};
-
-struct pdc_tlb_cf {		/* for PDC_CACHE (I/D-TLB's) */
-    unsigned long tc_pad0:12,	/* reserved */
-#ifdef CONFIG_64BIT
-		tc_padW:32,
-#endif
-		tc_sh	: 2,	/* 0 = separate I/D-TLB, else shared I/D-TLB */
-		tc_hv   : 1,	/* HV */
-		tc_page : 1,	/* 0 = 2K page-size-machine, 1 = 4k page size */
-		tc_cst  : 3,	/* 0 = incoherent operations, else coherent operations */
-		tc_aid  : 5,	/* ITLB: width of access ids of processor (encoded!) */
-		tc_pad1 : 8;	/* ITLB: width of space-registers (encoded) */
-};
-
-struct pdc_cache_info {		/* main-PDC_CACHE-structure (caches & TLB's) */
-	/* I-cache */
-	unsigned long	ic_size;	/* size in bytes */
-	struct pdc_cache_cf ic_conf;	/* configuration */
-	unsigned long	ic_base;	/* base-addr */
-	unsigned long	ic_stride;
-	unsigned long	ic_count;
-	unsigned long	ic_loop;
-	/* D-cache */
-	unsigned long	dc_size;	/* size in bytes */
-	struct pdc_cache_cf dc_conf;	/* configuration */
-	unsigned long	dc_base;	/* base-addr */
-	unsigned long	dc_stride;
-	unsigned long	dc_count;
-	unsigned long	dc_loop;
-	/* Instruction-TLB */
-	unsigned long	it_size;	/* number of entries in I-TLB */
-	struct pdc_tlb_cf it_conf;	/* I-TLB-configuration */
-	unsigned long	it_sp_base;
-	unsigned long	it_sp_stride;
-	unsigned long	it_sp_count;
-	unsigned long	it_off_base;
-	unsigned long	it_off_stride;
-	unsigned long	it_off_count;
-	unsigned long	it_loop;
-	/* data-TLB */
-	unsigned long	dt_size;	/* number of entries in D-TLB */
-	struct pdc_tlb_cf dt_conf;	/* D-TLB-configuration */
-	unsigned long	dt_sp_base;
-	unsigned long	dt_sp_stride;
-	unsigned long	dt_sp_count;
-	unsigned long	dt_off_base;
-	unsigned long	dt_off_stride;
-	unsigned long	dt_off_count;
-	unsigned long	dt_loop;
-};
-
-#if 0
-/* If you start using the next struct, you'll have to adjust it to
- * work with 64-bit firmware I think -PB
- */
-struct pdc_iodc {     /* PDC_IODC */
-	unsigned char   hversion_model;
-	unsigned char 	hversion;
-	unsigned char 	spa;
-	unsigned char 	type;
-	unsigned int	sversion_rev:4;
-	unsigned int	sversion_model:19;
-	unsigned int	sversion_opt:8;
-	unsigned char	rev;
-	unsigned char	dep;
-	unsigned char	features;
-	unsigned char	pad1;
-	unsigned int	checksum:16;
-	unsigned int	length:16;
-	unsigned int    pad[15];
-} __attribute__((aligned(8))) ;
-#endif
-
-#ifndef CONFIG_PA20
-/* no BLTBs in pa2.0 processors */
-struct pdc_btlb_info_range {
-	__u8 res00;
-	__u8 num_i;
-	__u8 num_d;
-	__u8 num_comb;
-};
-
-struct pdc_btlb_info {	/* PDC_BLOCK_TLB, return of PDC_BTLB_INFO */
-	unsigned int min_size;	/* minimum size of BTLB in pages */
-	unsigned int max_size;	/* maximum size of BTLB in pages */
-	struct pdc_btlb_info_range fixed_range_info;
-	struct pdc_btlb_info_range variable_range_info;
-};
-
-#endif /* !CONFIG_PA20 */
-
-#ifdef CONFIG_64BIT
-struct pdc_memory_table_raddr { /* PDC_MEM/PDC_MEM_TABLE (return info) */
-	unsigned long entries_returned;
-	unsigned long entries_total;
-};
-
-struct pdc_memory_table {       /* PDC_MEM/PDC_MEM_TABLE (arguments) */
-	unsigned long paddr;
-	unsigned int  pages;
-	unsigned int  reserved;
-};
-#endif /* CONFIG_64BIT */
-
-struct pdc_system_map_mod_info { /* PDC_SYSTEM_MAP/FIND_MODULE */
-	unsigned long mod_addr;
-	unsigned long mod_pgs;
-	unsigned long add_addrs;
-};
-
-struct pdc_system_map_addr_info { /* PDC_SYSTEM_MAP/FIND_ADDRESS */
-	unsigned long mod_addr;
-	unsigned long mod_pgs;
-};
-
-struct pdc_initiator { /* PDC_INITIATOR */
-	int host_id;
-	int factor;
-	int width;
-	int mode;
-};
-
-struct hardware_path {
-	char  flags;	/* see bit definitions below */
-	char  bc[6];	/* Bus Converter routing info to a specific */
-			/* I/O adaptor (< 0 means none, > 63 resvd) */
-	char  mod;	/* fixed field of specified module */
-};
-
-/*
- * Device path specifications used by PDC.
- */
-struct pdc_module_path {
-	struct hardware_path path;
-	unsigned int layers[6]; /* device-specific info (ctlr #, unit # ...) */
-};
-
-#ifndef CONFIG_PA20
-/* Only used on some pre-PA2.0 boxes */
-struct pdc_memory_map {		/* PDC_MEMORY_MAP */
-	unsigned long hpa;	/* mod's register set address */
-	unsigned long more_pgs;	/* number of additional I/O pgs */
-};
-#endif
-
-struct pdc_tod {
-	unsigned long tod_sec; 
-	unsigned long tod_usec;
-};
-
-/* architected results from PDC_PIM/transfer hpmc on a PA1.1 machine */
-
-struct pdc_hpmc_pim_11 { /* PDC_PIM */
-	__u32 gr[32];
-	__u32 cr[32];
-	__u32 sr[8];
-	__u32 iasq_back;
-	__u32 iaoq_back;
-	__u32 check_type;
-	__u32 cpu_state;
-	__u32 rsvd1;
-	__u32 cache_check;
-	__u32 tlb_check;
-	__u32 bus_check;
-	__u32 assists_check;
-	__u32 rsvd2;
-	__u32 assist_state;
-	__u32 responder_addr;
-	__u32 requestor_addr;
-	__u32 path_info;
-	__u64 fr[32];
-};
-
-/*
- * architected results from PDC_PIM/transfer hpmc on a PA2.0 machine
- *
- * Note that PDC_PIM doesn't care whether or not wide mode was enabled
- * so the results are different on  PA1.1 vs. PA2.0 when in narrow mode.
- *
- * Note also that there are unarchitected results available, which
- * are hversion dependent. Do a "ser pim 0 hpmc" after rebooting, since
- * the firmware is probably the best way of printing hversion dependent
- * data.
- */
-
-struct pdc_hpmc_pim_20 { /* PDC_PIM */
-	__u64 gr[32];
-	__u64 cr[32];
-	__u64 sr[8];
-	__u64 iasq_back;
-	__u64 iaoq_back;
-	__u32 check_type;
-	__u32 cpu_state;
-	__u32 cache_check;
-	__u32 tlb_check;
-	__u32 bus_check;
-	__u32 assists_check;
-	__u32 assist_state;
-	__u32 path_info;
-	__u64 responder_addr;
-	__u64 requestor_addr;
-	__u64 fr[32];
-};
-
-void pdc_console_init(void);	/* in pdc_console.c */
-void pdc_console_restart(void);
-
-void setup_pdc(void);		/* in inventory.c */
-
-/* wrapper-functions from pdc.c */
-
-int pdc_add_valid(unsigned long address);
-int pdc_chassis_info(struct pdc_chassis_info *chassis_info, void *led_info, unsigned long len);
-int pdc_chassis_disp(unsigned long disp);
-int pdc_chassis_warn(unsigned long *warn);
-int pdc_coproc_cfg(struct pdc_coproc_cfg *pdc_coproc_info);
-int pdc_iodc_read(unsigned long *actcnt, unsigned long hpa, unsigned int index,
-		  void *iodc_data, unsigned int iodc_data_size);
-int pdc_system_map_find_mods(struct pdc_system_map_mod_info *pdc_mod_info,
-			     struct pdc_module_path *mod_path, long mod_index);
-int pdc_system_map_find_addrs(struct pdc_system_map_addr_info *pdc_addr_info,
-			      long mod_index, long addr_index);
-int pdc_model_info(struct pdc_model *model);
-int pdc_model_sysmodel(char *name);
-int pdc_model_cpuid(unsigned long *cpu_id);
-int pdc_model_versions(unsigned long *versions, int id);
-int pdc_model_capabilities(unsigned long *capabilities);
-int pdc_cache_info(struct pdc_cache_info *cache);
-int pdc_spaceid_bits(unsigned long *space_bits);
-#ifndef CONFIG_PA20
-int pdc_btlb_info(struct pdc_btlb_info *btlb);
-int pdc_mem_map_hpa(struct pdc_memory_map *r_addr, struct pdc_module_path *mod_path);
-#endif /* !CONFIG_PA20 */
-int pdc_lan_station_id(char *lan_addr, unsigned long net_hpa);
-
-int pdc_stable_read(unsigned long staddr, void *memaddr, unsigned long count);
-int pdc_stable_write(unsigned long staddr, void *memaddr, unsigned long count);
-int pdc_stable_get_size(unsigned long *size);
-int pdc_stable_verify_contents(void);
-int pdc_stable_initialize(void);
-
-int pdc_pci_irt_size(unsigned long *num_entries, unsigned long hpa);
-int pdc_pci_irt(unsigned long num_entries, unsigned long hpa, void *tbl);
-
-int pdc_get_initiator(struct hardware_path *, struct pdc_initiator *);
-int pdc_tod_read(struct pdc_tod *tod);
-int pdc_tod_set(unsigned long sec, unsigned long usec);
-
-#ifdef CONFIG_64BIT
-int pdc_mem_mem_table(struct pdc_memory_table_raddr *r_addr,
-		struct pdc_memory_table *tbl, unsigned long entries);
-#endif
-
-void set_firmware_width(void);
-int pdc_do_firm_test_reset(unsigned long ftc_bitmap);
-int pdc_do_reset(void);
-int pdc_soft_power_info(unsigned long *power_reg);
-int pdc_soft_power_button(int sw_control);
-void pdc_io_reset(void);
-void pdc_io_reset_devices(void);
-int pdc_iodc_getc(void);
-int pdc_iodc_print(const unsigned char *str, unsigned count);
-
-void pdc_emergency_unlock(void);
-int pdc_sti_call(unsigned long func, unsigned long flags,
-                 unsigned long inptr, unsigned long outputr,
-                 unsigned long glob_cfg);
-
-static inline char * os_id_to_string(u16 os_id) {
-	switch(os_id) {
-	case OS_ID_NONE:	return "No OS";
-	case OS_ID_HPUX:	return "HP-UX";
-	case OS_ID_MPEXL:	return "MPE-iX";
-	case OS_ID_OSF:		return "OSF";
-	case OS_ID_HPRT:	return "HP-RT";
-	case OS_ID_NOVEL:	return "Novell Netware";
-	case OS_ID_LINUX:	return "Linux";
-	default:	return "Unknown";
-	}
-}
-
-#endif /* __KERNEL__ */
-
-#define PAGE0   ((struct zeropage *)__PAGE_OFFSET)
-
-/* DEFINITION OF THE ZERO-PAGE (PAG0) */
-/* based on work by Jason Eckhardt (jason@equator.com) */
-
-/* flags of the device_path */
-#define	PF_AUTOBOOT	0x80
-#define	PF_AUTOSEARCH	0x40
-#define	PF_TIMER	0x0F
-
-struct device_path {		/* page 1-69 */
-	unsigned char flags;	/* flags see above! */
-	unsigned char bc[6];	/* bus converter routing info */
-	unsigned char mod;
-	unsigned int  layers[6];/* device-specific layer-info */
-} __attribute__((aligned(8))) ;
-
-struct pz_device {
-	struct	device_path dp;	/* see above */
-	/* struct	iomod *hpa; */
-	unsigned int hpa;	/* HPA base address */
-	/* char	*spa; */
-	unsigned int spa;	/* SPA base address */
-	/* int	(*iodc_io)(struct iomod*, ...); */
-	unsigned int iodc_io;	/* device entry point */
-	short	pad;		/* reserved */
-	unsigned short cl_class;/* see below */
-} __attribute__((aligned(8))) ;
-
-struct zeropage {
-	/* [0x000] initialize vectors (VEC) */
-	unsigned int	vec_special;		/* must be zero */
-	/* int	(*vec_pow_fail)(void);*/
-	unsigned int	vec_pow_fail; /* power failure handler */
-	/* int	(*vec_toc)(void); */
-	unsigned int	vec_toc;
-	unsigned int	vec_toclen;
-	/* int	(*vec_rendz)(void); */
-	unsigned int vec_rendz;
-	int	vec_pow_fail_flen;
-	int	vec_pad[10];		
-	
-	/* [0x040] reserved processor dependent */
-	int	pad0[112];
-
-	/* [0x200] reserved */
-	int	pad1[84];
-
-	/* [0x350] memory configuration (MC) */
-	int	memc_cont;		/* contiguous mem size (bytes) */
-	int	memc_phsize;		/* physical memory size */
-	int	memc_adsize;		/* additional mem size, bytes of SPA space used by PDC */
-	unsigned int mem_pdc_hi;	/* used for 64-bit */
-
-	/* [0x360] various parameters for the boot-CPU */
-	/* unsigned int *mem_booterr[8]; */
-	unsigned int mem_booterr[8];	/* ptr to boot errors */
-	unsigned int mem_free;		/* first location, where OS can be loaded */
-	/* struct iomod *mem_hpa; */
-	unsigned int mem_hpa;		/* HPA of the boot-CPU */
-	/* int (*mem_pdc)(int, ...); */
-	unsigned int mem_pdc;		/* PDC entry point */
-	unsigned int mem_10msec;	/* number of clock ticks in 10msec */
-
-	/* [0x390] initial memory module (IMM) */
-	/* struct iomod *imm_hpa; */
-	unsigned int imm_hpa;		/* HPA of the IMM */
-	int	imm_soft_boot;		/* 0 = was hard boot, 1 = was soft boot */
-	unsigned int	imm_spa_size;		/* SPA size of the IMM in bytes */
-	unsigned int	imm_max_mem;		/* bytes of mem in IMM */
-
-	/* [0x3A0] boot console, display device and keyboard */
-	struct pz_device mem_cons;	/* description of console device */
-	struct pz_device mem_boot;	/* description of boot device */
-	struct pz_device mem_kbd;	/* description of keyboard device */
-
-	/* [0x430] reserved */
-	int	pad430[116];
-
-	/* [0x600] processor dependent */
-	__u32	pad600[1];
-	__u32	proc_sti;		/* pointer to STI ROM */
-	__u32	pad608[126];
-};
-
-#endif /* !defined(__ASSEMBLY__) */
-
-#endif /* _PARISC_PDC_H */
diff --git a/include/asm-parisc/pdc_chassis.h b/include/asm-parisc/pdc_chassis.h
deleted file mode 100644
index a609273dc6bf..000000000000
--- a/include/asm-parisc/pdc_chassis.h
+++ /dev/null
@@ -1,381 +0,0 @@
-/*
- *	include/asm-parisc/pdc_chassis.h
- *
- *	Copyright (C) 2002 Laurent Canet <canetl@esiee.fr>
- *	Copyright (C) 2002 Thibaut Varene <varenet@parisc-linux.org>
- *
- *
- *      This program is free software; you can redistribute it and/or modify
- *      it under the terms of the GNU General Public License, version 2, as
- *      published by the Free Software Foundation.
- *      
- *      This program is distributed in the hope that it will be useful,
- *      but WITHOUT ANY WARRANTY; without even the implied warranty of
- *      MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *      GNU General Public License for more details.
- *      
- *      You should have received a copy of the GNU General Public License
- *      along with this program; if not, write to the Free Software
- *      Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- *      TODO:	- handle processor number on SMP systems (Reporting Entity ID)
- *      	- handle message ID
- *      	- handle timestamps
- */
- 
-
-#ifndef _PARISC_PDC_CHASSIS_H
-#define _PARISC_PDC_CHASSIS_H
-
-/*
- * ----------
- * Prototypes
- * ----------
- */
-
-int pdc_chassis_send_status(int message);
-void parisc_pdc_chassis_init(void);
-
-
-/*
- * -----------------
- * Direct call names
- * -----------------
- * They setup everything for you, the Log message and the corresponding LED state
- */
-
-#define PDC_CHASSIS_DIRECT_BSTART	0
-#define PDC_CHASSIS_DIRECT_BCOMPLETE	1
-#define PDC_CHASSIS_DIRECT_SHUTDOWN	2
-#define PDC_CHASSIS_DIRECT_PANIC	3
-#define PDC_CHASSIS_DIRECT_HPMC		4
-#define PDC_CHASSIS_DIRECT_LPMC		5
-#define PDC_CHASSIS_DIRECT_DUMP		6	/* not yet implemented */
-#define PDC_CHASSIS_DIRECT_OOPS		7	/* not yet implemented */
-
-
-/*
- * ------------
- * LEDs control
- * ------------
- * Set the three LEDs -- Run, Attn, and Fault.
- */
-
-/* Old PDC LED control */
-#define PDC_CHASSIS_DISP_DATA(v)	((unsigned long)(v) << 17)
-
-/* 
- * Available PDC PAT LED states
- */
-
-#define PDC_CHASSIS_LED_RUN_OFF		(0ULL << 4)
-#define PDC_CHASSIS_LED_RUN_FLASH	(1ULL << 4)
-#define PDC_CHASSIS_LED_RUN_ON		(2ULL << 4)
-#define PDC_CHASSIS_LED_RUN_NC		(3ULL << 4)
-#define PDC_CHASSIS_LED_ATTN_OFF	(0ULL << 6)
-#define PDC_CHASSIS_LED_ATTN_FLASH	(1ULL << 6)
-#define PDC_CHASSIS_LED_ATTN_NC		(3ULL << 6)	/* ATTN ON is invalid */
-#define PDC_CHASSIS_LED_FAULT_OFF	(0ULL << 8)
-#define PDC_CHASSIS_LED_FAULT_FLASH	(1ULL << 8)
-#define PDC_CHASSIS_LED_FAULT_ON	(2ULL << 8)
-#define PDC_CHASSIS_LED_FAULT_NC	(3ULL << 8)
-#define PDC_CHASSIS_LED_VALID		(1ULL << 10)
-
-/* 
- * Valid PDC PAT LED states combinations
- */
-
-/* System running normally */
-#define PDC_CHASSIS_LSTATE_RUN_NORMAL	(PDC_CHASSIS_LED_RUN_ON		| \
-					 PDC_CHASSIS_LED_ATTN_OFF	| \
-					 PDC_CHASSIS_LED_FAULT_OFF	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* System crashed and rebooted itself successfully */
-#define PDC_CHASSIS_LSTATE_RUN_CRASHREC	(PDC_CHASSIS_LED_RUN_ON		| \
-					 PDC_CHASSIS_LED_ATTN_OFF	| \
-					 PDC_CHASSIS_LED_FAULT_FLASH	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* There was a system interruption that did not take the system down */
-#define PDC_CHASSIS_LSTATE_RUN_SYSINT	(PDC_CHASSIS_LED_RUN_ON		| \
-					 PDC_CHASSIS_LED_ATTN_FLASH	| \
-					 PDC_CHASSIS_LED_FAULT_OFF	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* System running and unexpected reboot or non-critical error detected */
-#define PDC_CHASSIS_LSTATE_RUN_NCRIT	(PDC_CHASSIS_LED_RUN_ON		| \
-					 PDC_CHASSIS_LED_ATTN_FLASH	| \
-					 PDC_CHASSIS_LED_FAULT_FLASH	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* Executing non-OS code */
-#define PDC_CHASSIS_LSTATE_NONOS	(PDC_CHASSIS_LED_RUN_FLASH	| \
-					 PDC_CHASSIS_LED_ATTN_OFF	| \
-					 PDC_CHASSIS_LED_FAULT_OFF	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* Boot failed - Executing non-OS code */
-#define PDC_CHASSIS_LSTATE_NONOS_BFAIL	(PDC_CHASSIS_LED_RUN_FLASH	| \
-					 PDC_CHASSIS_LED_ATTN_OFF	| \
-					 PDC_CHASSIS_LED_FAULT_ON	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* Unexpected reboot occurred - Executing non-OS code */
-#define PDC_CHASSIS_LSTATE_NONOS_UNEXP	(PDC_CHASSIS_LED_RUN_FLASH	| \
-					 PDC_CHASSIS_LED_ATTN_OFF	| \
-					 PDC_CHASSIS_LED_FAULT_FLASH	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* Executing non-OS code - Non-critical error detected */
-#define PDC_CHASSIS_LSTATE_NONOS_NCRIT	(PDC_CHASSIS_LED_RUN_FLASH	| \
-					 PDC_CHASSIS_LED_ATTN_FLASH	| \
-					 PDC_CHASSIS_LED_FAULT_OFF	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* Boot failed - Executing non-OS code - Non-critical error detected */
-#define PDC_CHASSIS_LSTATE_BFAIL_NCRIT	(PDC_CHASSIS_LED_RUN_FLASH	| \
-					 PDC_CHASSIS_LED_ATTN_FLASH	| \
-					 PDC_CHASSIS_LED_FAULT_ON	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* Unexpected reboot/recovering - Executing non-OS code - Non-critical error detected */
-#define PDC_CHASSIS_LSTATE_UNEXP_NCRIT	(PDC_CHASSIS_LED_RUN_FLASH	| \
-					 PDC_CHASSIS_LED_ATTN_FLASH	| \
-					 PDC_CHASSIS_LED_FAULT_FLASH	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* Cannot execute PDC */
-#define PDC_CHASSIS_LSTATE_CANNOT_PDC	(PDC_CHASSIS_LED_RUN_OFF	| \
-					 PDC_CHASSIS_LED_ATTN_OFF	| \
-					 PDC_CHASSIS_LED_FAULT_OFF	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* Boot failed - OS not up - PDC has detected a failure that prevents boot */
-#define PDC_CHASSIS_LSTATE_FATAL_BFAIL	(PDC_CHASSIS_LED_RUN_OFF	| \
-					 PDC_CHASSIS_LED_ATTN_OFF	| \
-					 PDC_CHASSIS_LED_FAULT_ON	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* No code running - Non-critical error detected (double fault situation) */
-#define PDC_CHASSIS_LSTATE_NOCODE_NCRIT	(PDC_CHASSIS_LED_RUN_OFF	| \
-					 PDC_CHASSIS_LED_ATTN_FLASH	| \
-					 PDC_CHASSIS_LED_FAULT_OFF	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* Boot failed - OS not up - Fatal failure detected - Non-critical error detected */
-#define PDC_CHASSIS_LSTATE_FATAL_NCRIT	(PDC_CHASSIS_LED_RUN_OFF	| \
-					 PDC_CHASSIS_LED_ATTN_FLASH	| \
-					 PDC_CHASSIS_LED_FAULT_ON	| \
-					 PDC_CHASSIS_LED_VALID		)
-/* All other states are invalid */
-
-
-/*
- * --------------
- * PDC Log events
- * --------------
- * Here follows bits needed to fill up the log event sent to PDC_CHASSIS
- * The log message contains: Alert level, Source, Source detail,
- * Source ID, Problem detail, Caller activity, Activity status, 
- * Caller subactivity, Reporting entity type, Reporting entity ID,
- * Data type, Unique message ID and EOM. 
- */
-
-/* Alert level */
-#define PDC_CHASSIS_ALERT_FORWARD	(0ULL << 36)	/* no failure detected */
-#define PDC_CHASSIS_ALERT_SERPROC	(1ULL << 36)	/* service proc - no failure */
-#define PDC_CHASSIS_ALERT_NURGENT	(2ULL << 36)	/* non-urgent operator attn */
-#define PDC_CHASSIS_ALERT_BLOCKED	(3ULL << 36)	/* system blocked */
-#define PDC_CHASSIS_ALERT_CONF_CHG	(4ULL << 36)	/* unexpected configuration change */
-#define PDC_CHASSIS_ALERT_ENV_PB	(5ULL << 36)	/* boot possible, environmental pb */
-#define PDC_CHASSIS_ALERT_PENDING	(6ULL << 36)	/* boot possible, pending failure */
-#define PDC_CHASSIS_ALERT_PERF_IMP	(8ULL << 36)	/* boot possible, performance impaired */
-#define PDC_CHASSIS_ALERT_FUNC_IMP	(10ULL << 36)	/* boot possible, functionality impaired */
-#define PDC_CHASSIS_ALERT_SOFT_FAIL	(12ULL << 36)	/* software failure */
-#define PDC_CHASSIS_ALERT_HANG		(13ULL << 36)	/* system hang */
-#define PDC_CHASSIS_ALERT_ENV_FATAL	(14ULL << 36)	/* fatal power or environmental pb */
-#define PDC_CHASSIS_ALERT_HW_FATAL	(15ULL << 36)	/* fatal hardware problem */
-
-/* Source */
-#define PDC_CHASSIS_SRC_NONE		(0ULL << 28)	/* unknown, no source stated */
-#define PDC_CHASSIS_SRC_PROC		(1ULL << 28)	/* processor */
-/* For later use ? */
-#define PDC_CHASSIS_SRC_PROC_CACHE	(2ULL << 28)	/* processor cache*/
-#define PDC_CHASSIS_SRC_PDH		(3ULL << 28)	/* processor dependent hardware */
-#define PDC_CHASSIS_SRC_PWR		(4ULL << 28)	/* power */
-#define PDC_CHASSIS_SRC_FAB		(5ULL << 28)	/* fabric connector */
-#define PDC_CHASSIS_SRC_PLATi		(6ULL << 28)	/* platform */
-#define PDC_CHASSIS_SRC_MEM		(7ULL << 28)	/* memory */
-#define PDC_CHASSIS_SRC_IO		(8ULL << 28)	/* I/O */
-#define PDC_CHASSIS_SRC_CELL		(9ULL << 28)	/* cell */
-#define PDC_CHASSIS_SRC_PD		(10ULL << 28)	/* protected domain */
-
-/* Source detail field */
-#define PDC_CHASSIS_SRC_D_PROC		(1ULL << 24)	/* processor general */
-
-/* Source ID - platform dependent */
-#define PDC_CHASSIS_SRC_ID_UNSPEC	(0ULL << 16)
-
-/* Problem detail - problem source dependent */
-#define PDC_CHASSIS_PB_D_PROC_NONE	(0ULL << 32)	/* no problem detail */
-#define PDC_CHASSIS_PB_D_PROC_TIMEOUT	(4ULL << 32)	/* timeout */
-
-/* Caller activity */
-#define PDC_CHASSIS_CALL_ACT_HPUX_BL	(7ULL << 12)	/* Boot Loader */
-#define PDC_CHASSIS_CALL_ACT_HPUX_PD	(8ULL << 12)	/* SAL_PD activities */
-#define PDC_CHASSIS_CALL_ACT_HPUX_EVENT	(9ULL << 12)	/* SAL_EVENTS activities */
-#define PDC_CHASSIS_CALL_ACT_HPUX_IO	(10ULL << 12)	/* SAL_IO activities */
-#define PDC_CHASSIS_CALL_ACT_HPUX_PANIC	(11ULL << 12)	/* System panic */
-#define PDC_CHASSIS_CALL_ACT_HPUX_INIT	(12ULL << 12)	/* System initialization */
-#define PDC_CHASSIS_CALL_ACT_HPUX_SHUT	(13ULL << 12)	/* System shutdown */
-#define PDC_CHASSIS_CALL_ACT_HPUX_WARN	(14ULL << 12)	/* System warning */
-#define PDC_CHASSIS_CALL_ACT_HPUX_DU	(15ULL << 12)	/* Display_Activity() update */
-
-/* Activity status - implementation dependent */
-#define PDC_CHASSIS_ACT_STATUS_UNSPEC	(0ULL << 0)
-
-/* Caller subactivity - implementation dependent */
-/* FIXME: other subactivities ? */
-#define PDC_CHASSIS_CALL_SACT_UNSPEC	(0ULL << 4)	/* implementation dependent */
-
-/* Reporting entity type */
-#define PDC_CHASSIS_RET_GENERICOS	(12ULL << 52)	/* generic OSes */
-#define PDC_CHASSIS_RET_IA64_NT		(13ULL << 52)	/* IA-64 NT */
-#define PDC_CHASSIS_RET_HPUX		(14ULL << 52)	/* HP-UX */
-#define PDC_CHASSIS_RET_DIAG		(15ULL << 52)	/* offline diagnostics & utilities */
-
-/* Reporting entity ID */
-#define PDC_CHASSIS_REID_UNSPEC		(0ULL << 44)
-
-/* Data type */
-#define PDC_CHASSIS_DT_NONE		(0ULL << 59)	/* data field unused */
-/* For later use ? Do we need these ? */
-#define PDC_CHASSIS_DT_PHYS_ADDR	(1ULL << 59)	/* physical address */
-#define PDC_CHASSIS_DT_DATA_EXPECT	(2ULL << 59)	/* expected data */
-#define PDC_CHASSIS_DT_ACTUAL		(3ULL << 59)	/* actual data */
-#define PDC_CHASSIS_DT_PHYS_LOC		(4ULL << 59)	/* physical location */
-#define PDC_CHASSIS_DT_PHYS_LOC_EXT	(5ULL << 59)	/* physical location extension */
-#define PDC_CHASSIS_DT_TAG		(6ULL << 59)	/* tag */
-#define PDC_CHASSIS_DT_SYNDROME		(7ULL << 59)	/* syndrome */
-#define PDC_CHASSIS_DT_CODE_ADDR	(8ULL << 59)	/* code address */
-#define PDC_CHASSIS_DT_ASCII_MSG	(9ULL << 59)	/* ascii message */
-#define PDC_CHASSIS_DT_POST		(10ULL << 59)	/* POST code */
-#define PDC_CHASSIS_DT_TIMESTAMP	(11ULL << 59)	/* timestamp */
-#define PDC_CHASSIS_DT_DEV_STAT		(12ULL << 59)	/* device status */
-#define PDC_CHASSIS_DT_DEV_TYPE		(13ULL << 59)	/* device type */
-#define PDC_CHASSIS_DT_PB_DET		(14ULL << 59)	/* problem detail */
-#define PDC_CHASSIS_DT_ACT_LEV		(15ULL << 59)	/* activity level/timeout */
-#define PDC_CHASSIS_DT_SER_NUM		(16ULL << 59)	/* serial number */
-#define PDC_CHASSIS_DT_REV_NUM		(17ULL << 59)	/* revision number */
-#define PDC_CHASSIS_DT_INTERRUPT	(18ULL << 59)	/* interruption information */
-#define PDC_CHASSIS_DT_TEST_NUM		(19ULL << 59)	/* test number */
-#define PDC_CHASSIS_DT_STATE_CHG	(20ULL << 59)	/* major changes in system state */
-#define PDC_CHASSIS_DT_PROC_DEALLOC	(21ULL << 59)	/* processor deallocate */
-#define PDC_CHASSIS_DT_RESET		(30ULL << 59)	/* reset type and cause */
-#define PDC_CHASSIS_DT_PA_LEGACY	(31ULL << 59)	/* legacy PA hex chassis code */
-
-/* System states - part of major changes in system state data field */
-#define PDC_CHASSIS_SYSTATE_BSTART	(0ULL << 0)	/* boot start */
-#define PDC_CHASSIS_SYSTATE_BCOMP	(1ULL << 0)	/* boot complete */
-#define PDC_CHASSIS_SYSTATE_CHANGE	(2ULL << 0)	/* major change */
-#define PDC_CHASSIS_SYSTATE_LED		(3ULL << 0)	/* LED change */
-#define PDC_CHASSIS_SYSTATE_PANIC	(9ULL << 0)	/* OS Panic */
-#define PDC_CHASSIS_SYSTATE_DUMP	(10ULL << 0)	/* memory dump */
-#define PDC_CHASSIS_SYSTATE_HPMC	(11ULL << 0)	/* processing HPMC */
-#define PDC_CHASSIS_SYSTATE_HALT	(15ULL << 0)	/* system halted */
-
-/* Message ID */
-#define PDC_CHASSIS_MSG_ID		(0ULL << 40)	/* we do not handle msg IDs atm */
-
-/* EOM - separates log entries */
-#define PDC_CHASSIS_EOM_CLEAR		(0ULL << 43)
-#define PDC_CHASSIS_EOM_SET		(1ULL << 43)
-
-/*
- * Preformated well known messages
- */
-
-/* Boot started */
-#define PDC_CHASSIS_PMSG_BSTART		(PDC_CHASSIS_ALERT_SERPROC	| \
-					 PDC_CHASSIS_SRC_PROC		| \
-					 PDC_CHASSIS_SRC_D_PROC		| \
-					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
-					 PDC_CHASSIS_PB_D_PROC_NONE	| \
-					 PDC_CHASSIS_CALL_ACT_HPUX_INIT	| \
-					 PDC_CHASSIS_ACT_STATUS_UNSPEC	| \
-					 PDC_CHASSIS_CALL_SACT_UNSPEC	| \
-					 PDC_CHASSIS_RET_HPUX		| \
-					 PDC_CHASSIS_REID_UNSPEC	| \
-					 PDC_CHASSIS_DT_STATE_CHG	| \
-					 PDC_CHASSIS_SYSTATE_BSTART	| \
-					 PDC_CHASSIS_MSG_ID		| \
-					 PDC_CHASSIS_EOM_SET		)
-
-/* Boot complete */
-#define PDC_CHASSIS_PMSG_BCOMPLETE	(PDC_CHASSIS_ALERT_SERPROC	| \
-					 PDC_CHASSIS_SRC_PROC		| \
-					 PDC_CHASSIS_SRC_D_PROC		| \
-					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
-					 PDC_CHASSIS_PB_D_PROC_NONE	| \
-					 PDC_CHASSIS_CALL_ACT_HPUX_INIT	| \
-					 PDC_CHASSIS_ACT_STATUS_UNSPEC	| \
-					 PDC_CHASSIS_CALL_SACT_UNSPEC	| \
-					 PDC_CHASSIS_RET_HPUX		| \
-					 PDC_CHASSIS_REID_UNSPEC	| \
-					 PDC_CHASSIS_DT_STATE_CHG	| \
-					 PDC_CHASSIS_SYSTATE_BCOMP	| \
-					 PDC_CHASSIS_MSG_ID		| \
-					 PDC_CHASSIS_EOM_SET		)
-
-/* Shutdown */
-#define PDC_CHASSIS_PMSG_SHUTDOWN	(PDC_CHASSIS_ALERT_SERPROC	| \
-					 PDC_CHASSIS_SRC_PROC		| \
-					 PDC_CHASSIS_SRC_D_PROC		| \
-					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
-					 PDC_CHASSIS_PB_D_PROC_NONE	| \
-					 PDC_CHASSIS_CALL_ACT_HPUX_SHUT	| \
-					 PDC_CHASSIS_ACT_STATUS_UNSPEC	| \
-					 PDC_CHASSIS_CALL_SACT_UNSPEC	| \
-					 PDC_CHASSIS_RET_HPUX		| \
-					 PDC_CHASSIS_REID_UNSPEC	| \
-					 PDC_CHASSIS_DT_STATE_CHG	| \
-					 PDC_CHASSIS_SYSTATE_HALT	| \
-					 PDC_CHASSIS_MSG_ID		| \
-					 PDC_CHASSIS_EOM_SET		)
-
-/* Panic */
-#define PDC_CHASSIS_PMSG_PANIC		(PDC_CHASSIS_ALERT_SOFT_FAIL	| \
-					 PDC_CHASSIS_SRC_PROC		| \
-					 PDC_CHASSIS_SRC_D_PROC		| \
-					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
-					 PDC_CHASSIS_PB_D_PROC_NONE	| \
-					 PDC_CHASSIS_CALL_ACT_HPUX_PANIC| \
-					 PDC_CHASSIS_ACT_STATUS_UNSPEC	| \
-					 PDC_CHASSIS_CALL_SACT_UNSPEC	| \
-					 PDC_CHASSIS_RET_HPUX		| \
-					 PDC_CHASSIS_REID_UNSPEC	| \
-					 PDC_CHASSIS_DT_STATE_CHG	| \
-					 PDC_CHASSIS_SYSTATE_PANIC	| \
-					 PDC_CHASSIS_MSG_ID		| \
-					 PDC_CHASSIS_EOM_SET		)
-
-// FIXME: extrapolated data
-/* HPMC */
-#define PDC_CHASSIS_PMSG_HPMC		(PDC_CHASSIS_ALERT_CONF_CHG /*?*/	| \
-					 PDC_CHASSIS_SRC_PROC		| \
-					 PDC_CHASSIS_SRC_D_PROC		| \
-					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
-					 PDC_CHASSIS_PB_D_PROC_NONE	| \
-					 PDC_CHASSIS_CALL_ACT_HPUX_WARN	| \
-					 PDC_CHASSIS_RET_HPUX		| \
-					 PDC_CHASSIS_DT_STATE_CHG	| \
-					 PDC_CHASSIS_SYSTATE_HPMC	| \
-					 PDC_CHASSIS_MSG_ID		| \
-					 PDC_CHASSIS_EOM_SET		)
-
-/* LPMC */
-#define PDC_CHASSIS_PMSG_LPMC		(PDC_CHASSIS_ALERT_BLOCKED /*?*/| \
-					 PDC_CHASSIS_SRC_PROC		| \
-					 PDC_CHASSIS_SRC_D_PROC		| \
-					 PDC_CHASSIS_SRC_ID_UNSPEC	| \
-					 PDC_CHASSIS_PB_D_PROC_NONE	| \
-					 PDC_CHASSIS_CALL_ACT_HPUX_WARN	| \
-					 PDC_CHASSIS_ACT_STATUS_UNSPEC	| \
-					 PDC_CHASSIS_CALL_SACT_UNSPEC	| \
-					 PDC_CHASSIS_RET_HPUX		| \
-					 PDC_CHASSIS_REID_UNSPEC	| \
-					 PDC_CHASSIS_DT_STATE_CHG	| \
-					 PDC_CHASSIS_SYSTATE_CHANGE	| \
-					 PDC_CHASSIS_MSG_ID		| \
-					 PDC_CHASSIS_EOM_SET		)
-
-#endif /* _PARISC_PDC_CHASSIS_H */
-/* vim: set ts=8 */
diff --git a/include/asm-parisc/pdcpat.h b/include/asm-parisc/pdcpat.h
deleted file mode 100644
index 47539f117958..000000000000
--- a/include/asm-parisc/pdcpat.h
+++ /dev/null
@@ -1,308 +0,0 @@
-#ifndef __PARISC_PATPDC_H
-#define __PARISC_PATPDC_H
-
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright 2000 (c) Hewlett Packard (Paul Bame <bame()spam.parisc-linux.org>)
- * Copyright 2000,2004 (c) Grant Grundler <grundler()nahspam.parisc-linux.org>
- */
-
-
-#define PDC_PAT_CELL           	64L   /* Interface for gaining and 
-                                         * manipulatin g cell state within PD */
-#define PDC_PAT_CELL_GET_NUMBER    0L   /* Return Cell number */
-#define PDC_PAT_CELL_GET_INFO      1L   /* Returns info about Cell */
-#define PDC_PAT_CELL_MODULE        2L   /* Returns info about Module */
-#define PDC_PAT_CELL_SET_ATTENTION 9L   /* Set Cell Attention indicator */
-#define PDC_PAT_CELL_NUMBER_TO_LOC 10L   /* Cell Number -> Location */
-#define PDC_PAT_CELL_WALK_FABRIC   11L   /* Walk the Fabric */
-#define PDC_PAT_CELL_GET_RDT_SIZE  12L   /* Return Route Distance Table Sizes */
-#define PDC_PAT_CELL_GET_RDT       13L   /* Return Route Distance Tables */
-#define PDC_PAT_CELL_GET_LOCAL_PDH_SZ 14L /* Read Local PDH Buffer Size */
-#define PDC_PAT_CELL_SET_LOCAL_PDH    15L  /* Write Local PDH Buffer */
-#define PDC_PAT_CELL_GET_REMOTE_PDH_SZ 16L /* Return Remote PDH Buffer Size */
-#define PDC_PAT_CELL_GET_REMOTE_PDH 17L /* Read Remote PDH Buffer */
-#define PDC_PAT_CELL_GET_DBG_INFO   128L  /* Return DBG Buffer Info */
-#define PDC_PAT_CELL_CHANGE_ALIAS   129L  /* Change Non-Equivalent Alias Chacking */
-
-
-/*
-** Arg to PDC_PAT_CELL_MODULE memaddr[4]
-**
-** Addresses on the Merced Bus != all Runway Bus addresses.
-** This is intended for programming SBA/LBA chips range registers.
-*/
-#define IO_VIEW      0UL
-#define PA_VIEW      1UL
-
-/* PDC_PAT_CELL_MODULE entity type values */
-#define	PAT_ENTITY_CA	0	/* central agent */
-#define	PAT_ENTITY_PROC	1	/* processor */
-#define	PAT_ENTITY_MEM	2	/* memory controller */
-#define	PAT_ENTITY_SBA	3	/* system bus adapter */
-#define	PAT_ENTITY_LBA	4	/* local bus adapter */
-#define	PAT_ENTITY_PBC	5	/* processor bus converter */
-#define	PAT_ENTITY_XBC	6	/* crossbar fabric connect */
-#define	PAT_ENTITY_RC	7	/* fabric interconnect */
-
-/* PDC_PAT_CELL_MODULE address range type values */
-#define PAT_PBNUM           0         /* PCI Bus Number */
-#define PAT_LMMIO           1         /* < 4G MMIO Space */
-#define PAT_GMMIO           2         /* > 4G MMIO Space */
-#define PAT_NPIOP           3         /* Non Postable I/O Port Space */
-#define PAT_PIOP            4         /* Postable I/O Port Space */
-#define PAT_AHPA            5         /* Addional HPA Space */
-#define PAT_UFO             6         /* HPA Space (UFO for Mariposa) */
-#define PAT_GNIP            7         /* GNI Reserved Space */
-
-
-
-/* PDC PAT CHASSIS LOG -- Platform logging & forward progress functions */
-
-#define PDC_PAT_CHASSIS_LOG		65L
-#define PDC_PAT_CHASSIS_WRITE_LOG    	0L /* Write Log Entry */
-#define PDC_PAT_CHASSIS_READ_LOG     	1L /* Read  Log Entry */
-
-
-/* PDC PAT CPU  -- CPU configuration within the protection domain */
-
-#define PDC_PAT_CPU                	67L
-#define PDC_PAT_CPU_INFO            	0L /* Return CPU config info */
-#define PDC_PAT_CPU_DELETE          	1L /* Delete CPU */
-#define PDC_PAT_CPU_ADD             	2L /* Add    CPU */
-#define PDC_PAT_CPU_GET_NUMBER      	3L /* Return CPU Number */
-#define PDC_PAT_CPU_GET_HPA         	4L /* Return CPU HPA */
-#define PDC_PAT_CPU_STOP            	5L /* Stop   CPU */
-#define PDC_PAT_CPU_RENDEZVOUS      	6L /* Rendezvous CPU */
-#define PDC_PAT_CPU_GET_CLOCK_INFO  	7L /* Return CPU Clock info */
-#define PDC_PAT_CPU_GET_RENDEZVOUS_STATE 8L /* Return Rendezvous State */
-#define PDC_PAT_CPU_PLUNGE_FABRIC 	128L /* Plunge Fabric */
-#define PDC_PAT_CPU_UPDATE_CACHE_CLEANSING 129L /* Manipulate Cache 
-                                                 * Cleansing Mode */
-/*  PDC PAT EVENT -- Platform Events */
-
-#define PDC_PAT_EVENT              	68L
-#define PDC_PAT_EVENT_GET_CAPS     	0L /* Get Capabilities */
-#define PDC_PAT_EVENT_SET_MODE     	1L /* Set Notification Mode */
-#define PDC_PAT_EVENT_SCAN         	2L /* Scan Event */
-#define PDC_PAT_EVENT_HANDLE       	3L /* Handle Event */
-#define PDC_PAT_EVENT_GET_NB_CALL  	4L /* Get Non-Blocking call Args */
-
-/*  PDC PAT HPMC -- Cause processor to go into spin loop, and wait
- *  			for wake up from Monarch Processor.
- */
-
-#define PDC_PAT_HPMC               70L
-#define PDC_PAT_HPMC_RENDEZ_CPU     0L /* go into spin loop */
-#define PDC_PAT_HPMC_SET_PARAMS     1L /* Allows OS to specify intr which PDC 
-                                        * will use to interrupt OS during
-                                        * machine check rendezvous */
-
-/* parameters for PDC_PAT_HPMC_SET_PARAMS: */
-#define HPMC_SET_PARAMS_INTR 	    1L /* Rendezvous Interrupt */
-#define HPMC_SET_PARAMS_WAKE 	    2L /* Wake up processor */
-
-
-/*  PDC PAT IO  -- On-line services for I/O modules */
-
-#define PDC_PAT_IO                  71L
-#define PDC_PAT_IO_GET_SLOT_STATUS   	5L /* Get Slot Status Info*/
-#define PDC_PAT_IO_GET_LOC_FROM_HARDWARE 6L /* Get Physical Location from */
-                                            /* Hardware Path */
-#define PDC_PAT_IO_GET_HARDWARE_FROM_LOC 7L /* Get Hardware Path from 
-                                             * Physical Location */
-#define PDC_PAT_IO_GET_PCI_CONFIG_FROM_HW 11L /* Get PCI Configuration
-                                               * Address from Hardware Path */
-#define PDC_PAT_IO_GET_HW_FROM_PCI_CONFIG 12L /* Get Hardware Path 
-                                               * from PCI Configuration Address */
-#define PDC_PAT_IO_READ_HOST_BRIDGE_INFO 13L  /* Read Host Bridge State Info */
-#define PDC_PAT_IO_CLEAR_HOST_BRIDGE_INFO 14L /* Clear Host Bridge State Info*/
-#define PDC_PAT_IO_GET_PCI_ROUTING_TABLE_SIZE 15L /* Get PCI INT Routing Table 
-                                                   * Size */
-#define PDC_PAT_IO_GET_PCI_ROUTING_TABLE  16L /* Get PCI INT Routing Table */
-#define PDC_PAT_IO_GET_HINT_TABLE_SIZE 	17L /* Get Hint Table Size */
-#define PDC_PAT_IO_GET_HINT_TABLE   	18L /* Get Hint Table */
-#define PDC_PAT_IO_PCI_CONFIG_READ  	19L /* PCI Config Read */
-#define PDC_PAT_IO_PCI_CONFIG_WRITE 	20L /* PCI Config Write */
-#define PDC_PAT_IO_GET_NUM_IO_SLOTS 	21L /* Get Number of I/O Bay Slots in 
-                                       		  * Cabinet */
-#define PDC_PAT_IO_GET_LOC_IO_SLOTS 	22L /* Get Physical Location of I/O */
-                                   		     /* Bay Slots in Cabinet */
-#define PDC_PAT_IO_BAY_STATUS_INFO  	28L /* Get I/O Bay Slot Status Info */
-#define PDC_PAT_IO_GET_PROC_VIEW        29L /* Get Processor view of IO address */
-#define PDC_PAT_IO_PROG_SBA_DIR_RANGE   30L /* Program directed range */
-
-
-/* PDC PAT MEM  -- Manage memory page deallocation */
-
-#define PDC_PAT_MEM            72L
-#define PDC_PAT_MEM_PD_INFO     	0L /* Return PDT info for PD       */
-#define PDC_PAT_MEM_PD_CLEAR    	1L /* Clear PDT for PD             */
-#define PDC_PAT_MEM_PD_READ     	2L /* Read PDT entries for PD      */
-#define PDC_PAT_MEM_PD_RESET    	3L /* Reset clear bit for PD       */
-#define PDC_PAT_MEM_CELL_INFO   	5L /* Return PDT info For Cell     */
-#define PDC_PAT_MEM_CELL_CLEAR  	6L /* Clear PDT For Cell           */
-#define PDC_PAT_MEM_CELL_READ   	7L /* Read PDT entries For Cell    */
-#define PDC_PAT_MEM_CELL_RESET  	8L /* Reset clear bit For Cell     */
-#define PDC_PAT_MEM_SETGM	  	9L /* Set Golden Memory value      */
-#define PDC_PAT_MEM_ADD_PAGE    	10L /* ADDs a page to the cell      */
-#define PDC_PAT_MEM_ADDRESS     	11L /* Get Physical Location From   */
-                                    		 /* Memory Address               */
-#define PDC_PAT_MEM_GET_TXT_SIZE   	12L /* Get Formatted Text Size   */
-#define PDC_PAT_MEM_GET_PD_TXT     	13L /* Get PD Formatted Text     */
-#define PDC_PAT_MEM_GET_CELL_TXT   	14L /* Get Cell Formatted Text   */
-#define PDC_PAT_MEM_RD_STATE_INFO  	15L /* Read Mem Module State Info*/
-#define PDC_PAT_MEM_CLR_STATE_INFO 	16L /*Clear Mem Module State Info*/
-#define PDC_PAT_MEM_CLEAN_RANGE    	128L /*Clean Mem in specific range*/
-#define PDC_PAT_MEM_GET_TBL_SIZE   	131L /* Get Memory Table Size     */
-#define PDC_PAT_MEM_GET_TBL        	132L /* Get Memory Table          */
-
-
-/* PDC PAT NVOLATILE  --  Access Non-Volatile Memory */
-
-#define PDC_PAT_NVOLATILE	73L
-#define PDC_PAT_NVOLATILE_READ		0L /* Read Non-Volatile Memory   */
-#define PDC_PAT_NVOLATILE_WRITE		1L /* Write Non-Volatile Memory  */
-#define PDC_PAT_NVOLATILE_GET_SIZE	2L /* Return size of NVM         */
-#define PDC_PAT_NVOLATILE_VERIFY	3L /* Verify contents of NVM     */
-#define PDC_PAT_NVOLATILE_INIT		4L /* Initialize NVM             */
-
-/* PDC PAT PD */
-#define PDC_PAT_PD		74L         /* Protection Domain Info   */
-#define PDC_PAT_PD_GET_ADDR_MAP		0L  /* Get Address Map          */
-
-/* PDC_PAT_PD_GET_ADDR_MAP entry types */
-#define PAT_MEMORY_DESCRIPTOR		1   
-
-/* PDC_PAT_PD_GET_ADDR_MAP memory types */
-#define PAT_MEMTYPE_MEMORY		0
-#define PAT_MEMTYPE_FIRMWARE		4
-
-/* PDC_PAT_PD_GET_ADDR_MAP memory usage */
-#define PAT_MEMUSE_GENERAL		0
-#define PAT_MEMUSE_GI			128
-#define PAT_MEMUSE_GNI			129
-
-
-#ifndef __ASSEMBLY__
-#include <linux/types.h>
-
-#ifdef CONFIG_64BIT
-#define is_pdc_pat()	(PDC_TYPE_PAT == pdc_type)
-extern int pdc_pat_get_irt_size(unsigned long *num_entries, unsigned long cell_num);
-extern int pdc_pat_get_irt(void *r_addr, unsigned long cell_num);
-#else	/* ! CONFIG_64BIT */
-/* No PAT support for 32-bit kernels...sorry */
-#define is_pdc_pat()	(0)
-#define pdc_pat_get_irt_size(num_entries, cell_numn)	PDC_BAD_PROC
-#define pdc_pat_get_irt(r_addr, cell_num)		PDC_BAD_PROC
-#endif	/* ! CONFIG_64BIT */
-
-
-struct pdc_pat_cell_num {
-	unsigned long cell_num;
-	unsigned long cell_loc;
-};
-
-struct pdc_pat_cpu_num {
-	unsigned long cpu_num;
-	unsigned long cpu_loc;
-};
-
-struct pdc_pat_pd_addr_map_entry {
-	unsigned char entry_type;       /* 1 = Memory Descriptor Entry Type */
-	unsigned char reserve1[5];
-	unsigned char memory_type;
-	unsigned char memory_usage;
-	unsigned long paddr;
-	unsigned int  pages;            /* Length in 4K pages */
-	unsigned int  reserve2;
-	unsigned long cell_map;
-};
-
-/********************************************************************
-* PDC_PAT_CELL[Return Cell Module] memaddr[0] conf_base_addr
-* ----------------------------------------------------------
-* Bit  0 to 51 - conf_base_addr
-* Bit 52 to 62 - reserved
-* Bit       63 - endianess bit
-********************************************************************/
-#define PAT_GET_CBA(value) ((value) & 0xfffffffffffff000UL)
-
-/********************************************************************
-* PDC_PAT_CELL[Return Cell Module] memaddr[1] mod_info
-* ----------------------------------------------------
-* Bit  0 to  7 - entity type
-*    0 = central agent,            1 = processor,
-*    2 = memory controller,        3 = system bus adapter,
-*    4 = local bus adapter,        5 = processor bus converter,
-*    6 = crossbar fabric connect,  7 = fabric interconnect,
-*    8 to 254 reserved,            255 = unknown.
-* Bit  8 to 15 - DVI
-* Bit 16 to 23 - IOC functions
-* Bit 24 to 39 - reserved
-* Bit 40 to 63 - mod_pages
-*    number of 4K pages a module occupies starting at conf_base_addr
-********************************************************************/
-#define PAT_GET_ENTITY(value)	(((value) >> 56) & 0xffUL)
-#define PAT_GET_DVI(value)	(((value) >> 48) & 0xffUL)
-#define PAT_GET_IOC(value)	(((value) >> 40) & 0xffUL)
-#define PAT_GET_MOD_PAGES(value) ((value) & 0xffffffUL)
-
-
-/*
-** PDC_PAT_CELL_GET_INFO return block
-*/
-typedef struct pdc_pat_cell_info_rtn_block {
-	unsigned long cpu_info;
-	unsigned long cell_info;
-	unsigned long cell_location;
-	unsigned long reo_location;
-	unsigned long mem_size;
-	unsigned long dimm_status;
-	unsigned long pdc_rev;
-	unsigned long fabric_info0;
-	unsigned long fabric_info1;
-	unsigned long fabric_info2;
-	unsigned long fabric_info3;
-	unsigned long reserved[21];
-} pdc_pat_cell_info_rtn_block_t;
-
-
-/* FIXME: mod[508] should really be a union of the various mod components */
-struct pdc_pat_cell_mod_maddr_block {	/* PDC_PAT_CELL_MODULE */
-	unsigned long cba;		/* func 0 cfg space address */
-	unsigned long mod_info;		/* module information */
-	unsigned long mod_location;	/* physical location of the module */
-	struct hardware_path mod_path;	/* module path (device path - layers) */
-	unsigned long mod[508];		/* PAT cell module components */
-} __attribute__((aligned(8))) ;
-
-typedef struct pdc_pat_cell_mod_maddr_block pdc_pat_cell_mod_maddr_block_t;
-
-
-extern int pdc_pat_chassis_send_log(unsigned long status, unsigned long data);
-extern int pdc_pat_cell_get_number(struct pdc_pat_cell_num *cell_info);
-extern int pdc_pat_cell_module(unsigned long *actcnt, unsigned long ploc, unsigned long mod, unsigned long view_type, void *mem_addr);
-extern int pdc_pat_cell_num_to_loc(void *, unsigned long);
-
-extern int pdc_pat_cpu_get_number(struct pdc_pat_cpu_num *cpu_info, void *hpa);
-
-extern int pdc_pat_pd_get_addr_map(unsigned long *actual_len, void *mem_addr, unsigned long count, unsigned long offset);
-
-
-extern int pdc_pat_io_pci_cfg_read(unsigned long pci_addr, int pci_size, u32 *val); 
-extern int pdc_pat_io_pci_cfg_write(unsigned long pci_addr, int pci_size, u32 val); 
-
-
-/* Flag to indicate this is a PAT box...don't use this unless you
-** really have to...it might go away some day.
-*/
-extern int pdc_pat;     /* arch/parisc/kernel/inventory.c */
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* ! __PARISC_PATPDC_H */
diff --git a/include/asm-parisc/percpu.h b/include/asm-parisc/percpu.h
deleted file mode 100644
index a0dcd1970128..000000000000
--- a/include/asm-parisc/percpu.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _PARISC_PERCPU_H
-#define _PARISC_PERCPU_H
-
-#include <asm-generic/percpu.h>
-
-#endif 
-
diff --git a/include/asm-parisc/perf.h b/include/asm-parisc/perf.h
deleted file mode 100644
index a18e11972c09..000000000000
--- a/include/asm-parisc/perf.h
+++ /dev/null
@@ -1,74 +0,0 @@
-#ifndef _ASM_PERF_H_
-#define _ASM_PERF_H_
-
-/* ioctls */
-#define PA_PERF_ON	_IO('p', 1)
-#define PA_PERF_OFF	_IOR('p', 2, unsigned int)
-#define PA_PERF_VERSION	_IOR('p', 3, int)
-
-#define PA_PERF_DEV	"perf"
-#define PA_PERF_MINOR	146
-
-/* Interface types */
-#define UNKNOWN_INTF    255
-#define ONYX_INTF         0
-#define CUDA_INTF         1
-
-/* Common Onyx and Cuda images */
-#define CPI                 0
-#define BUSUTIL             1
-#define TLBMISS             2
-#define TLBHANDMISS         3
-#define PTKN                4
-#define PNTKN               5
-#define IMISS               6
-#define DMISS               7
-#define DMISS_ACCESS        8 
-#define BIG_CPI 	    9
-#define BIG_LS		   10  
-#define BR_ABORT	   11
-#define ISNT		   12 
-#define QUADRANT           13
-#define RW_PDFET           14
-#define RW_WDFET           15
-#define SHLIB_CPI          16
-
-/* Cuda only Images */
-#define FLOPS              17
-#define CACHEMISS          18 
-#define BRANCHES           19             
-#define CRSTACK            20 
-#define I_CACHE_SPEC       21 
-#define MAX_CUDA_IMAGES    22 
-
-/* Onyx only Images */
-#define ADDR_INV_ABORT_ALU 17
-#define BRAD_STALL	   18 
-#define CNTL_IN_PIPEL	   19 
-#define DSNT_XFH	   20 
-#define FET_SIG1	   21 
-#define FET_SIG2	   22 
-#define G7_1		   23 
-#define G7_2		   24 
-#define G7_3 		   25
-#define G7_4		   26
-#define MPB_LABORT         27
-#define PANIC              28
-#define RARE_INST          29 
-#define RW_DFET            30 
-#define RW_IFET            31 
-#define RW_SDFET           32 
-#define SPEC_IFET          33 
-#define ST_COND0           34 
-#define ST_COND1           35 
-#define ST_COND2           36
-#define ST_COND3           37
-#define ST_COND4           38
-#define ST_UNPRED0         39 
-#define ST_UNPRED1         40 
-#define UNPRED             41 
-#define GO_STORE           42
-#define SHLIB_CALL         43
-#define MAX_ONYX_IMAGES    44
-
-#endif
diff --git a/include/asm-parisc/pgalloc.h b/include/asm-parisc/pgalloc.h
deleted file mode 100644
index fc987a1c12a8..000000000000
--- a/include/asm-parisc/pgalloc.h
+++ /dev/null
@@ -1,149 +0,0 @@
-#ifndef _ASM_PGALLOC_H
-#define _ASM_PGALLOC_H
-
-#include <linux/gfp.h>
-#include <linux/mm.h>
-#include <linux/threads.h>
-#include <asm/processor.h>
-#include <asm/fixmap.h>
-
-#include <asm/cache.h>
-
-/* Allocate the top level pgd (page directory)
- *
- * Here (for 64 bit kernels) we implement a Hybrid L2/L3 scheme: we
- * allocate the first pmd adjacent to the pgd.  This means that we can
- * subtract a constant offset to get to it.  The pmd and pgd sizes are
- * arranged so that a single pmd covers 4GB (giving a full 64-bit
- * process access to 8TB) so our lookups are effectively L2 for the
- * first 4GB of the kernel (i.e. for all ILP32 processes and all the
- * kernel for machines with under 4GB of memory) */
-static inline pgd_t *pgd_alloc(struct mm_struct *mm)
-{
-	pgd_t *pgd = (pgd_t *)__get_free_pages(GFP_KERNEL,
-					       PGD_ALLOC_ORDER);
-	pgd_t *actual_pgd = pgd;
-
-	if (likely(pgd != NULL)) {
-		memset(pgd, 0, PAGE_SIZE<<PGD_ALLOC_ORDER);
-#ifdef CONFIG_64BIT
-		actual_pgd += PTRS_PER_PGD;
-		/* Populate first pmd with allocated memory.  We mark it
-		 * with PxD_FLAG_ATTACHED as a signal to the system that this
-		 * pmd entry may not be cleared. */
-		__pgd_val_set(*actual_pgd, (PxD_FLAG_PRESENT | 
-				        PxD_FLAG_VALID | 
-					PxD_FLAG_ATTACHED) 
-			+ (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT));
-		/* The first pmd entry also is marked with _PAGE_GATEWAY as
-		 * a signal that this pmd may not be freed */
-		__pgd_val_set(*pgd, PxD_FLAG_ATTACHED);
-#endif
-	}
-	return actual_pgd;
-}
-
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-#ifdef CONFIG_64BIT
-	pgd -= PTRS_PER_PGD;
-#endif
-	free_pages((unsigned long)pgd, PGD_ALLOC_ORDER);
-}
-
-#if PT_NLEVELS == 3
-
-/* Three Level Page Table Support for pmd's */
-
-static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
-{
-	__pgd_val_set(*pgd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID) +
-		        (__u32)(__pa((unsigned long)pmd) >> PxD_VALUE_SHIFT));
-}
-
-static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
-{
-	pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT,
-					       PMD_ORDER);
-	if (pmd)
-		memset(pmd, 0, PAGE_SIZE<<PMD_ORDER);
-	return pmd;
-}
-
-static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
-{
-#ifdef CONFIG_64BIT
-	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
-		/* This is the permanent pmd attached to the pgd;
-		 * cannot free it */
-		return;
-#endif
-	free_pages((unsigned long)pmd, PMD_ORDER);
-}
-
-#else
-
-/* Two Level Page Table Support for pmd's */
-
-/*
- * allocating and freeing a pmd is trivial: the 1-entry pmd is
- * inside the pgd, so has no extra memory associated with it.
- */
-
-#define pmd_alloc_one(mm, addr)		({ BUG(); ((pmd_t *)2); })
-#define pmd_free(mm, x)			do { } while (0)
-#define pgd_populate(mm, pmd, pte)	BUG()
-
-#endif
-
-static inline void
-pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
-{
-#ifdef CONFIG_64BIT
-	/* preserve the gateway marker if this is the beginning of
-	 * the permanent pmd */
-	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
-		__pmd_val_set(*pmd, (PxD_FLAG_PRESENT |
-				 PxD_FLAG_VALID |
-				 PxD_FLAG_ATTACHED) 
-			+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
-	else
-#endif
-		__pmd_val_set(*pmd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID) 
-			+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
-}
-
-#define pmd_populate(mm, pmd, pte_page) \
-	pmd_populate_kernel(mm, pmd, page_address(pte_page))
-#define pmd_pgtable(pmd) pmd_page(pmd)
-
-static inline pgtable_t
-pte_alloc_one(struct mm_struct *mm, unsigned long address)
-{
-	struct page *page = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
-	if (page)
-		pgtable_page_ctor(page);
-	return page;
-}
-
-static inline pte_t *
-pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
-{
-	pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
-	return pte;
-}
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
-{
-	pgtable_page_dtor(pte);
-	pte_free_kernel(mm, page_address(pte));
-}
-
-#define check_pgt_cache()	do { } while (0)
-
-#endif
diff --git a/include/asm-parisc/pgtable.h b/include/asm-parisc/pgtable.h
deleted file mode 100644
index 470a4b88124d..000000000000
--- a/include/asm-parisc/pgtable.h
+++ /dev/null
@@ -1,508 +0,0 @@
-#ifndef _PARISC_PGTABLE_H
-#define _PARISC_PGTABLE_H
-
-#include <asm-generic/4level-fixup.h>
-
-#include <asm/fixmap.h>
-
-#ifndef __ASSEMBLY__
-/*
- * we simulate an x86-style page table for the linux mm code
- */
-
-#include <linux/mm.h>		/* for vm_area_struct */
-#include <linux/bitops.h>
-#include <asm/processor.h>
-#include <asm/cache.h>
-
-/*
- * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
- * memory.  For the return value to be meaningful, ADDR must be >=
- * PAGE_OFFSET.  This operation can be relatively expensive (e.g.,
- * require a hash-, or multi-level tree-lookup or something of that
- * sort) but it guarantees to return TRUE only if accessing the page
- * at that address does not cause an error.  Note that there may be
- * addresses for which kern_addr_valid() returns FALSE even though an
- * access would not cause an error (e.g., this is typically true for
- * memory mapped I/O regions.
- *
- * XXX Need to implement this for parisc.
- */
-#define kern_addr_valid(addr)	(1)
-
-/* Certain architectures need to do special things when PTEs
- * within a page table are directly modified.  Thus, the following
- * hook is made available.
- */
-#define set_pte(pteptr, pteval)                                 \
-        do{                                                     \
-                *(pteptr) = (pteval);                           \
-        } while(0)
-#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
-
-#endif /* !__ASSEMBLY__ */
-
-#define pte_ERROR(e) \
-	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, pte_val(e))
-#define pmd_ERROR(e) \
-	printk("%s:%d: bad pmd %08lx.\n", __FILE__, __LINE__, (unsigned long)pmd_val(e))
-#define pgd_ERROR(e) \
-	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e))
-
-/* This is the size of the initially mapped kernel memory */
-#ifdef CONFIG_64BIT
-#define KERNEL_INITIAL_ORDER	24	/* 0 to 1<<24 = 16MB */
-#else
-#define KERNEL_INITIAL_ORDER	23	/* 0 to 1<<23 = 8MB */
-#endif
-#define KERNEL_INITIAL_SIZE	(1 << KERNEL_INITIAL_ORDER)
-
-#if defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB)
-#define PT_NLEVELS	3
-#define PGD_ORDER	1 /* Number of pages per pgd */
-#define PMD_ORDER	1 /* Number of pages per pmd */
-#define PGD_ALLOC_ORDER	2 /* first pgd contains pmd */
-#else
-#define PT_NLEVELS	2
-#define PGD_ORDER	1 /* Number of pages per pgd */
-#define PGD_ALLOC_ORDER	PGD_ORDER
-#endif
-
-/* Definitions for 3rd level (we use PLD here for Page Lower directory
- * because PTE_SHIFT is used lower down to mean shift that has to be
- * done to get usable bits out of the PTE) */
-#define PLD_SHIFT	PAGE_SHIFT
-#define PLD_SIZE	PAGE_SIZE
-#define BITS_PER_PTE	(PAGE_SHIFT - BITS_PER_PTE_ENTRY)
-#define PTRS_PER_PTE    (1UL << BITS_PER_PTE)
-
-/* Definitions for 2nd level */
-#define pgtable_cache_init()	do { } while (0)
-
-#define PMD_SHIFT       (PLD_SHIFT + BITS_PER_PTE)
-#define PMD_SIZE	(1UL << PMD_SHIFT)
-#define PMD_MASK	(~(PMD_SIZE-1))
-#if PT_NLEVELS == 3
-#define BITS_PER_PMD	(PAGE_SHIFT + PMD_ORDER - BITS_PER_PMD_ENTRY)
-#else
-#define BITS_PER_PMD	0
-#endif
-#define PTRS_PER_PMD    (1UL << BITS_PER_PMD)
-
-/* Definitions for 1st level */
-#define PGDIR_SHIFT	(PMD_SHIFT + BITS_PER_PMD)
-#define BITS_PER_PGD	(PAGE_SHIFT + PGD_ORDER - BITS_PER_PGD_ENTRY)
-#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
-#define PGDIR_MASK	(~(PGDIR_SIZE-1))
-#define PTRS_PER_PGD    (1UL << BITS_PER_PGD)
-#define USER_PTRS_PER_PGD       PTRS_PER_PGD
-
-#define MAX_ADDRBITS	(PGDIR_SHIFT + BITS_PER_PGD)
-#define MAX_ADDRESS	(1UL << MAX_ADDRBITS)
-
-#define SPACEID_SHIFT	(MAX_ADDRBITS - 32)
-
-/* This calculates the number of initial pages we need for the initial
- * page tables */
-#if (KERNEL_INITIAL_ORDER) >= (PMD_SHIFT)
-# define PT_INITIAL	(1 << (KERNEL_INITIAL_ORDER - PMD_SHIFT))
-#else
-# define PT_INITIAL	(1)  /* all initial PTEs fit into one page */
-#endif
-
-/*
- * pgd entries used up by user/kernel:
- */
-
-#define FIRST_USER_ADDRESS	0
-
-/* NB: The tlb miss handlers make certain assumptions about the order */
-/*     of the following bits, so be careful (One example, bits 25-31  */
-/*     are moved together in one instruction).                        */
-
-#define _PAGE_READ_BIT     31   /* (0x001) read access allowed */
-#define _PAGE_WRITE_BIT    30   /* (0x002) write access allowed */
-#define _PAGE_EXEC_BIT     29   /* (0x004) execute access allowed */
-#define _PAGE_GATEWAY_BIT  28   /* (0x008) privilege promotion allowed */
-#define _PAGE_DMB_BIT      27   /* (0x010) Data Memory Break enable (B bit) */
-#define _PAGE_DIRTY_BIT    26   /* (0x020) Page Dirty (D bit) */
-#define _PAGE_FILE_BIT	_PAGE_DIRTY_BIT	/* overload this bit */
-#define _PAGE_REFTRAP_BIT  25   /* (0x040) Page Ref. Trap enable (T bit) */
-#define _PAGE_NO_CACHE_BIT 24   /* (0x080) Uncached Page (U bit) */
-#define _PAGE_ACCESSED_BIT 23   /* (0x100) Software: Page Accessed */
-#define _PAGE_PRESENT_BIT  22   /* (0x200) Software: translation valid */
-#define _PAGE_FLUSH_BIT    21   /* (0x400) Software: translation valid */
-				/*             for cache flushing only */
-#define _PAGE_USER_BIT     20   /* (0x800) Software: User accessible page */
-
-/* N.B. The bits are defined in terms of a 32 bit word above, so the */
-/*      following macro is ok for both 32 and 64 bit.                */
-
-#define xlate_pabit(x) (31 - x)
-
-/* this defines the shift to the usable bits in the PTE it is set so
- * that the valid bits _PAGE_PRESENT_BIT and _PAGE_USER_BIT are set
- * to zero */
-#define PTE_SHIFT	   	xlate_pabit(_PAGE_USER_BIT)
-
-/* PFN_PTE_SHIFT defines the shift of a PTE value to access the PFN field */
-#define PFN_PTE_SHIFT		12
-
-
-/* this is how many bits may be used by the file functions */
-#define PTE_FILE_MAX_BITS	(BITS_PER_LONG - PTE_SHIFT)
-
-#define pte_to_pgoff(pte) (pte_val(pte) >> PTE_SHIFT)
-#define pgoff_to_pte(off) ((pte_t) { ((off) << PTE_SHIFT) | _PAGE_FILE })
-
-#define _PAGE_READ     (1 << xlate_pabit(_PAGE_READ_BIT))
-#define _PAGE_WRITE    (1 << xlate_pabit(_PAGE_WRITE_BIT))
-#define _PAGE_RW       (_PAGE_READ | _PAGE_WRITE)
-#define _PAGE_EXEC     (1 << xlate_pabit(_PAGE_EXEC_BIT))
-#define _PAGE_GATEWAY  (1 << xlate_pabit(_PAGE_GATEWAY_BIT))
-#define _PAGE_DMB      (1 << xlate_pabit(_PAGE_DMB_BIT))
-#define _PAGE_DIRTY    (1 << xlate_pabit(_PAGE_DIRTY_BIT))
-#define _PAGE_REFTRAP  (1 << xlate_pabit(_PAGE_REFTRAP_BIT))
-#define _PAGE_NO_CACHE (1 << xlate_pabit(_PAGE_NO_CACHE_BIT))
-#define _PAGE_ACCESSED (1 << xlate_pabit(_PAGE_ACCESSED_BIT))
-#define _PAGE_PRESENT  (1 << xlate_pabit(_PAGE_PRESENT_BIT))
-#define _PAGE_FLUSH    (1 << xlate_pabit(_PAGE_FLUSH_BIT))
-#define _PAGE_USER     (1 << xlate_pabit(_PAGE_USER_BIT))
-#define _PAGE_FILE     (1 << xlate_pabit(_PAGE_FILE_BIT))
-
-#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_READ | _PAGE_WRITE |  _PAGE_DIRTY | _PAGE_ACCESSED)
-#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _PAGE_KERNEL	(_PAGE_PRESENT | _PAGE_EXEC | _PAGE_READ | _PAGE_WRITE | _PAGE_DIRTY | _PAGE_ACCESSED)
-
-/* The pgd/pmd contains a ptr (in phys addr space); since all pgds/pmds
- * are page-aligned, we don't care about the PAGE_OFFSET bits, except
- * for a few meta-information bits, so we shift the address to be
- * able to effectively address 40/42/44-bits of physical address space
- * depending on 4k/16k/64k PAGE_SIZE */
-#define _PxD_PRESENT_BIT   31
-#define _PxD_ATTACHED_BIT  30
-#define _PxD_VALID_BIT     29
-
-#define PxD_FLAG_PRESENT  (1 << xlate_pabit(_PxD_PRESENT_BIT))
-#define PxD_FLAG_ATTACHED (1 << xlate_pabit(_PxD_ATTACHED_BIT))
-#define PxD_FLAG_VALID    (1 << xlate_pabit(_PxD_VALID_BIT))
-#define PxD_FLAG_MASK     (0xf)
-#define PxD_FLAG_SHIFT    (4)
-#define PxD_VALUE_SHIFT   (8) /* (PAGE_SHIFT-PxD_FLAG_SHIFT) */
-
-#ifndef __ASSEMBLY__
-
-#define PAGE_NONE	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_WRITE | _PAGE_ACCESSED)
-/* Others seem to make this executable, I don't know if that's correct
-   or not.  The stack is mapped this way though so this is necessary
-   in the short term - dhd@linuxcare.com, 2000-08-08 */
-#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_ACCESSED)
-#define PAGE_WRITEONLY  __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_WRITE | _PAGE_ACCESSED)
-#define PAGE_EXECREAD   __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_EXEC |_PAGE_ACCESSED)
-#define PAGE_COPY       PAGE_EXECREAD
-#define PAGE_RWX        __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_READ | _PAGE_WRITE | _PAGE_EXEC |_PAGE_ACCESSED)
-#define PAGE_KERNEL	__pgprot(_PAGE_KERNEL)
-#define PAGE_KERNEL_RO	__pgprot(_PAGE_KERNEL & ~_PAGE_WRITE)
-#define PAGE_KERNEL_UNC	__pgprot(_PAGE_KERNEL | _PAGE_NO_CACHE)
-#define PAGE_GATEWAY    __pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED | _PAGE_GATEWAY| _PAGE_READ)
-#define PAGE_FLUSH      __pgprot(_PAGE_FLUSH)
-
-
-/*
- * We could have an execute only page using "gateway - promote to priv
- * level 3", but that is kind of silly. So, the way things are defined
- * now, we must always have read permission for pages with execute
- * permission. For the fun of it we'll go ahead and support write only
- * pages.
- */
-
-	 /*xwr*/
-#define __P000  PAGE_NONE
-#define __P001  PAGE_READONLY
-#define __P010  __P000 /* copy on write */
-#define __P011  __P001 /* copy on write */
-#define __P100  PAGE_EXECREAD
-#define __P101  PAGE_EXECREAD
-#define __P110  __P100 /* copy on write */
-#define __P111  __P101 /* copy on write */
-
-#define __S000  PAGE_NONE
-#define __S001  PAGE_READONLY
-#define __S010  PAGE_WRITEONLY
-#define __S011  PAGE_SHARED
-#define __S100  PAGE_EXECREAD
-#define __S101  PAGE_EXECREAD
-#define __S110  PAGE_RWX
-#define __S111  PAGE_RWX
-
-
-extern pgd_t swapper_pg_dir[]; /* declared in init_task.c */
-
-/* initial page tables for 0-8MB for kernel */
-
-extern pte_t pg0[];
-
-/* zero page used for uninitialized stuff */
-
-extern unsigned long *empty_zero_page;
-
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
-
-#define pte_none(x)     ((pte_val(x) == 0) || (pte_val(x) & _PAGE_FLUSH))
-#define pte_present(x)	(pte_val(x) & _PAGE_PRESENT)
-#define pte_clear(mm,addr,xp)	do { pte_val(*(xp)) = 0; } while (0)
-
-#define pmd_flag(x)	(pmd_val(x) & PxD_FLAG_MASK)
-#define pmd_address(x)	((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
-#define pgd_flag(x)	(pgd_val(x) & PxD_FLAG_MASK)
-#define pgd_address(x)	((unsigned long)(pgd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
-
-#if PT_NLEVELS == 3
-/* The first entry of the permanent pmd is not there if it contains
- * the gateway marker */
-#define pmd_none(x)	(!pmd_val(x) || pmd_flag(x) == PxD_FLAG_ATTACHED)
-#else
-#define pmd_none(x)	(!pmd_val(x))
-#endif
-#define pmd_bad(x)	(!(pmd_flag(x) & PxD_FLAG_VALID))
-#define pmd_present(x)	(pmd_flag(x) & PxD_FLAG_PRESENT)
-static inline void pmd_clear(pmd_t *pmd) {
-#if PT_NLEVELS == 3
-	if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
-		/* This is the entry pointing to the permanent pmd
-		 * attached to the pgd; cannot clear it */
-		__pmd_val_set(*pmd, PxD_FLAG_ATTACHED);
-	else
-#endif
-		__pmd_val_set(*pmd,  0);
-}
-
-
-
-#if PT_NLEVELS == 3
-#define pgd_page_vaddr(pgd) ((unsigned long) __va(pgd_address(pgd)))
-#define pgd_page(pgd)	virt_to_page((void *)pgd_page_vaddr(pgd))
-
-/* For 64 bit we have three level tables */
-
-#define pgd_none(x)     (!pgd_val(x))
-#define pgd_bad(x)      (!(pgd_flag(x) & PxD_FLAG_VALID))
-#define pgd_present(x)  (pgd_flag(x) & PxD_FLAG_PRESENT)
-static inline void pgd_clear(pgd_t *pgd) {
-#if PT_NLEVELS == 3
-	if(pgd_flag(*pgd) & PxD_FLAG_ATTACHED)
-		/* This is the permanent pmd attached to the pgd; cannot
-		 * free it */
-		return;
-#endif
-	__pgd_val_set(*pgd, 0);
-}
-#else
-/*
- * The "pgd_xxx()" functions here are trivial for a folded two-level
- * setup: the pgd is never bad, and a pmd always exists (as it's folded
- * into the pgd entry)
- */
-static inline int pgd_none(pgd_t pgd)		{ return 0; }
-static inline int pgd_bad(pgd_t pgd)		{ return 0; }
-static inline int pgd_present(pgd_t pgd)	{ return 1; }
-static inline void pgd_clear(pgd_t * pgdp)	{ }
-#endif
-
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
-static inline int pte_dirty(pte_t pte)		{ return pte_val(pte) & _PAGE_DIRTY; }
-static inline int pte_young(pte_t pte)		{ return pte_val(pte) & _PAGE_ACCESSED; }
-static inline int pte_write(pte_t pte)		{ return pte_val(pte) & _PAGE_WRITE; }
-static inline int pte_file(pte_t pte)		{ return pte_val(pte) & _PAGE_FILE; }
-static inline int pte_special(pte_t pte)	{ return 0; }
-
-static inline pte_t pte_mkclean(pte_t pte)	{ pte_val(pte) &= ~_PAGE_DIRTY; return pte; }
-static inline pte_t pte_mkold(pte_t pte)	{ pte_val(pte) &= ~_PAGE_ACCESSED; return pte; }
-static inline pte_t pte_wrprotect(pte_t pte)	{ pte_val(pte) &= ~_PAGE_WRITE; return pte; }
-static inline pte_t pte_mkdirty(pte_t pte)	{ pte_val(pte) |= _PAGE_DIRTY; return pte; }
-static inline pte_t pte_mkyoung(pte_t pte)	{ pte_val(pte) |= _PAGE_ACCESSED; return pte; }
-static inline pte_t pte_mkwrite(pte_t pte)	{ pte_val(pte) |= _PAGE_WRITE; return pte; }
-static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
-
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define __mk_pte(addr,pgprot) \
-({									\
-	pte_t __pte;							\
-									\
-	pte_val(__pte) = ((((addr)>>PAGE_SHIFT)<<PFN_PTE_SHIFT) + pgprot_val(pgprot));	\
-									\
-	__pte;								\
-})
-
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
-
-static inline pte_t pfn_pte(unsigned long pfn, pgprot_t pgprot)
-{
-	pte_t pte;
-	pte_val(pte) = (pfn << PFN_PTE_SHIFT) | pgprot_val(pgprot);
-	return pte;
-}
-
-static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
-{ pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot); return pte; }
-
-/* Permanent address of a page.  On parisc we don't have highmem. */
-
-#define pte_pfn(x)		(pte_val(x) >> PFN_PTE_SHIFT)
-
-#define pte_page(pte)		(pfn_to_page(pte_pfn(pte)))
-
-#define pmd_page_vaddr(pmd)	((unsigned long) __va(pmd_address(pmd)))
-
-#define __pmd_page(pmd) ((unsigned long) __va(pmd_address(pmd)))
-#define pmd_page(pmd)	virt_to_page((void *)__pmd_page(pmd))
-
-#define pgd_index(address) ((address) >> PGDIR_SHIFT)
-
-/* to find an entry in a page-table-directory */
-#define pgd_offset(mm, address) \
-((mm)->pgd + ((address) >> PGDIR_SHIFT))
-
-/* to find an entry in a kernel page-table-directory */
-#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-
-/* Find an entry in the second-level page table.. */
-
-#if PT_NLEVELS == 3
-#define pmd_offset(dir,address) \
-((pmd_t *) pgd_page_vaddr(*(dir)) + (((address)>>PMD_SHIFT) & (PTRS_PER_PMD-1)))
-#else
-#define pmd_offset(dir,addr) ((pmd_t *) dir)
-#endif
-
-/* Find an entry in the third-level page table.. */ 
-#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE-1))
-#define pte_offset_kernel(pmd, address) \
-	((pte_t *) pmd_page_vaddr(*(pmd)) + pte_index(address))
-#define pte_offset_map(pmd, address) pte_offset_kernel(pmd, address)
-#define pte_offset_map_nested(pmd, address) pte_offset_kernel(pmd, address)
-#define pte_unmap(pte) do { } while (0)
-#define pte_unmap_nested(pte) do { } while (0)
-
-#define pte_unmap(pte)			do { } while (0)
-#define pte_unmap_nested(pte)		do { } while (0)
-
-extern void paging_init (void);
-
-/* Used for deferring calls to flush_dcache_page() */
-
-#define PG_dcache_dirty         PG_arch_1
-
-extern void update_mmu_cache(struct vm_area_struct *, unsigned long, pte_t);
-
-/* Encode and de-code a swap entry */
-
-#define __swp_type(x)                     ((x).val & 0x1f)
-#define __swp_offset(x)                   ( (((x).val >> 6) &  0x7) | \
-					  (((x).val >> 8) & ~0x7) )
-#define __swp_entry(type, offset)         ((swp_entry_t) { (type) | \
-					    ((offset &  0x7) << 6) | \
-					    ((offset & ~0x7) << 8) })
-#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) })
-#define __swp_entry_to_pte(x)		((pte_t) { (x).val })
-
-static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
-{
-#ifdef CONFIG_SMP
-	if (!pte_young(*ptep))
-		return 0;
-	return test_and_clear_bit(xlate_pabit(_PAGE_ACCESSED_BIT), &pte_val(*ptep));
-#else
-	pte_t pte = *ptep;
-	if (!pte_young(pte))
-		return 0;
-	set_pte_at(vma->vm_mm, addr, ptep, pte_mkold(pte));
-	return 1;
-#endif
-}
-
-extern spinlock_t pa_dbit_lock;
-
-struct mm_struct;
-static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-	pte_t old_pte;
-	pte_t pte;
-
-	spin_lock(&pa_dbit_lock);
-	pte = old_pte = *ptep;
-	pte_val(pte) &= ~_PAGE_PRESENT;
-	pte_val(pte) |= _PAGE_FLUSH;
-	set_pte_at(mm,addr,ptep,pte);
-	spin_unlock(&pa_dbit_lock);
-
-	return old_pte;
-}
-
-static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
-{
-#ifdef CONFIG_SMP
-	unsigned long new, old;
-
-	do {
-		old = pte_val(*ptep);
-		new = pte_val(pte_wrprotect(__pte (old)));
-	} while (cmpxchg((unsigned long *) ptep, old, new) != old);
-#else
-	pte_t old_pte = *ptep;
-	set_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
-#endif
-}
-
-#define pte_same(A,B)	(pte_val(A) == pte_val(B))
-
-#endif /* !__ASSEMBLY__ */
-
-
-/* TLB page size encoding - see table 3-1 in parisc20.pdf */
-#define _PAGE_SIZE_ENCODING_4K		0
-#define _PAGE_SIZE_ENCODING_16K		1
-#define _PAGE_SIZE_ENCODING_64K		2
-#define _PAGE_SIZE_ENCODING_256K	3
-#define _PAGE_SIZE_ENCODING_1M		4
-#define _PAGE_SIZE_ENCODING_4M		5
-#define _PAGE_SIZE_ENCODING_16M		6
-#define _PAGE_SIZE_ENCODING_64M		7
-
-#if defined(CONFIG_PARISC_PAGE_SIZE_4KB)
-# define _PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_4K
-#elif defined(CONFIG_PARISC_PAGE_SIZE_16KB)
-# define _PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_16K
-#elif defined(CONFIG_PARISC_PAGE_SIZE_64KB)
-# define _PAGE_SIZE_ENCODING_DEFAULT _PAGE_SIZE_ENCODING_64K
-#endif
-
-
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)		\
-		remap_pfn_range(vma, vaddr, pfn, size, prot)
-
-#define pgprot_noncached(prot) __pgprot(pgprot_val(prot) | _PAGE_NO_CACHE)
-
-/* We provide our own get_unmapped_area to provide cache coherency */
-
-#define HAVE_ARCH_UNMAPPED_AREA
-
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
-#define __HAVE_ARCH_PTEP_SET_WRPROTECT
-#define __HAVE_ARCH_PTE_SAME
-#include <asm-generic/pgtable.h>
-
-#endif /* _PARISC_PGTABLE_H */
diff --git a/include/asm-parisc/poll.h b/include/asm-parisc/poll.h
deleted file mode 100644
index c98509d3149e..000000000000
--- a/include/asm-parisc/poll.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/poll.h>
diff --git a/include/asm-parisc/posix_types.h b/include/asm-parisc/posix_types.h
deleted file mode 100644
index bb725a6630bb..000000000000
--- a/include/asm-parisc/posix_types.h
+++ /dev/null
@@ -1,129 +0,0 @@
-#ifndef __ARCH_PARISC_POSIX_TYPES_H
-#define __ARCH_PARISC_POSIX_TYPES_H
-
-/*
- * This file is generally used by user-level software, so you need to
- * be a little careful about namespace pollution etc.  Also, we cannot
- * assume GCC is being used.
- */
-typedef unsigned long		__kernel_ino_t;
-typedef unsigned short		__kernel_mode_t;
-typedef unsigned short		__kernel_nlink_t;
-typedef long			__kernel_off_t;
-typedef int			__kernel_pid_t;
-typedef unsigned short		__kernel_ipc_pid_t;
-typedef unsigned int		__kernel_uid_t;
-typedef unsigned int		__kernel_gid_t;
-typedef int			__kernel_suseconds_t;
-typedef long			__kernel_clock_t;
-typedef int			__kernel_timer_t;
-typedef int			__kernel_clockid_t;
-typedef int			__kernel_daddr_t;
-/* Note these change from narrow to wide kernels */
-#ifdef CONFIG_64BIT
-typedef unsigned long		__kernel_size_t;
-typedef long			__kernel_ssize_t;
-typedef long			__kernel_ptrdiff_t;
-typedef long			__kernel_time_t;
-#else
-typedef unsigned int		__kernel_size_t;
-typedef int			__kernel_ssize_t;
-typedef int			__kernel_ptrdiff_t;
-typedef long			__kernel_time_t;
-#endif
-typedef char *			__kernel_caddr_t;
-
-typedef unsigned short		__kernel_uid16_t;
-typedef unsigned short		__kernel_gid16_t;
-typedef unsigned int		__kernel_uid32_t;
-typedef unsigned int		__kernel_gid32_t;
-
-#ifdef __GNUC__
-typedef long long		__kernel_loff_t;
-typedef long long		__kernel_off64_t;
-typedef unsigned long long	__kernel_ino64_t;
-#endif
-
-typedef unsigned int		__kernel_old_dev_t;
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-/* compatibility stuff */
-typedef __kernel_uid_t __kernel_old_uid_t;
-typedef __kernel_gid_t __kernel_old_gid_t;
-
-#if defined(__KERNEL__)
-
-#undef __FD_SET
-static __inline__ void __FD_SET(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] |= (1UL<<__rem);
-}
-
-#undef __FD_CLR
-static __inline__ void __FD_CLR(unsigned long __fd, __kernel_fd_set *__fdsetp)
-{
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	__fdsetp->fds_bits[__tmp] &= ~(1UL<<__rem);
-}
-
-#undef __FD_ISSET
-static __inline__ int __FD_ISSET(unsigned long __fd, const __kernel_fd_set *__p)
-{ 
-	unsigned long __tmp = __fd / __NFDBITS;
-	unsigned long __rem = __fd % __NFDBITS;
-	return (__p->fds_bits[__tmp] & (1UL<<__rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant case (8 ints,
- * for a 256-bit fd_set)
- */
-#undef __FD_ZERO
-static __inline__ void __FD_ZERO(__kernel_fd_set *__p)
-{
-	unsigned long *__tmp = __p->fds_bits;
-	int __i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 16:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			__tmp[ 8] = 0; __tmp[ 9] = 0;
-			__tmp[10] = 0; __tmp[11] = 0;
-			__tmp[12] = 0; __tmp[13] = 0;
-			__tmp[14] = 0; __tmp[15] = 0;
-			return;
-
-		case 8:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			__tmp[ 4] = 0; __tmp[ 5] = 0;
-			__tmp[ 6] = 0; __tmp[ 7] = 0;
-			return;
-
-		case 4:
-			__tmp[ 0] = 0; __tmp[ 1] = 0;
-			__tmp[ 2] = 0; __tmp[ 3] = 0;
-			return;
-		}
-	}
-	__i = __FDSET_LONGS;
-	while (__i) {
-		__i--;
-		*__tmp = 0;
-		__tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
-
-#endif
diff --git a/include/asm-parisc/prefetch.h b/include/asm-parisc/prefetch.h
deleted file mode 100644
index c5edc60c059f..000000000000
--- a/include/asm-parisc/prefetch.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * include/asm-parisc/prefetch.h
- *
- * PA 2.0 defines data prefetch instructions on page 6-11 of the Kane book.
- * In addition, many implementations do hardware prefetching of both
- * instructions and data.
- *
- * PA7300LC (page 14-4 of the ERS) also implements prefetching by a load
- * to gr0 but not in a way that Linux can use.  If the load would cause an
- * interruption (eg due to prefetching 0), it is suppressed on PA2.0
- * processors, but not on 7300LC.
- *
- */
-
-#ifndef __ASM_PARISC_PREFETCH_H
-#define __ASM_PARISC_PREFETCH_H
-
-#ifndef __ASSEMBLY__
-#ifdef CONFIG_PREFETCH
-
-#define ARCH_HAS_PREFETCH
-static inline void prefetch(const void *addr)
-{
-	__asm__("ldw 0(%0), %%r0" : : "r" (addr));
-}
-
-/* LDD is a PA2.0 addition. */
-#ifdef CONFIG_PA20
-#define ARCH_HAS_PREFETCHW
-static inline void prefetchw(const void *addr)
-{
-	__asm__("ldd 0(%0), %%r0" : : "r" (addr));
-}
-#endif /* CONFIG_PA20 */
-
-#endif /* CONFIG_PREFETCH */
-#endif /* __ASSEMBLY__ */
-
-#endif /* __ASM_PARISC_PROCESSOR_H */
diff --git a/include/asm-parisc/processor.h b/include/asm-parisc/processor.h
deleted file mode 100644
index 3c9d34844c83..000000000000
--- a/include/asm-parisc/processor.h
+++ /dev/null
@@ -1,357 +0,0 @@
-/*
- * include/asm-parisc/processor.h
- *
- * Copyright (C) 1994 Linus Torvalds
- * Copyright (C) 2001 Grant Grundler
- */
-
-#ifndef __ASM_PARISC_PROCESSOR_H
-#define __ASM_PARISC_PROCESSOR_H
-
-#ifndef __ASSEMBLY__
-#include <linux/threads.h>
-
-#include <asm/prefetch.h>
-#include <asm/hardware.h>
-#include <asm/pdc.h>
-#include <asm/ptrace.h>
-#include <asm/types.h>
-#include <asm/system.h>
-#endif /* __ASSEMBLY__ */
-
-#define KERNEL_STACK_SIZE 	(4*PAGE_SIZE)
-
-/*
- * Default implementation of macro that returns current
- * instruction pointer ("program counter").
- */
-#ifdef CONFIG_PA20
-#define current_ia(x)	__asm__("mfia %0" : "=r"(x))
-#else /* mfia added in pa2.0 */
-#define current_ia(x)	__asm__("blr 0,%0\n\tnop" : "=r"(x))
-#endif
-#define current_text_addr() ({ void *pc; current_ia(pc); pc; })
-
-#define TASK_SIZE_OF(tsk)       ((tsk)->thread.task_size)
-#define TASK_SIZE	        TASK_SIZE_OF(current)
-#define TASK_UNMAPPED_BASE      (current->thread.map_base)
-
-#define DEFAULT_TASK_SIZE32	(0xFFF00000UL)
-#define DEFAULT_MAP_BASE32	(0x40000000UL)
-
-#ifdef CONFIG_64BIT
-#define DEFAULT_TASK_SIZE       (MAX_ADDRESS-0xf000000)
-#define DEFAULT_MAP_BASE        (0x200000000UL)
-#else
-#define DEFAULT_TASK_SIZE	DEFAULT_TASK_SIZE32
-#define DEFAULT_MAP_BASE	DEFAULT_MAP_BASE32
-#endif
-
-#ifdef __KERNEL__
-
-/* XXX: STACK_TOP actually should be STACK_BOTTOM for parisc.
- * prumpf */
-
-#define STACK_TOP	TASK_SIZE
-#define STACK_TOP_MAX	DEFAULT_TASK_SIZE
-
-#endif
-
-#ifndef __ASSEMBLY__
-
-/*
- * Data detected about CPUs at boot time which is the same for all CPU's.
- * HP boxes are SMP - ie identical processors.
- *
- * FIXME: some CPU rev info may be processor specific...
- */
-struct system_cpuinfo_parisc {
-	unsigned int	cpu_count;
-	unsigned int	cpu_hz;
-	unsigned int	hversion;
-	unsigned int	sversion;
-	enum cpu_type	cpu_type;
-
-	struct {
-		struct pdc_model model;
-		unsigned long versions;
-		unsigned long cpuid;
-		unsigned long capabilities;
-		char   sys_model_name[81]; /* PDC-ROM returnes this model name */
-	} pdc;
-
-	const char	*cpu_name;	/* e.g. "PA7300LC (PCX-L2)" */
-	const char	*family_name;	/* e.g. "1.1e" */
-};
-
-
-/* Per CPU data structure - ie varies per CPU.  */
-struct cpuinfo_parisc {
-	unsigned long it_value;     /* Interval Timer at last timer Intr */
-	unsigned long it_delta;     /* Interval delta (tic_10ms / HZ * 100) */
-	unsigned long irq_count;    /* number of IRQ's since boot */
-	unsigned long irq_max_cr16; /* longest time to handle a single IRQ */
-	unsigned long cpuid;        /* aka slot_number or set to NO_PROC_ID */
-	unsigned long hpa;          /* Host Physical address */
-	unsigned long txn_addr;     /* MMIO addr of EIR or id_eid */
-#ifdef CONFIG_SMP
-	unsigned long pending_ipi;  /* bitmap of type ipi_message_type */
-	unsigned long ipi_count;    /* number ipi Interrupts */
-#endif
-	unsigned long bh_count;     /* number of times bh was invoked */
-	unsigned long prof_counter; /* per CPU profiling support */
-	unsigned long prof_multiplier;	/* per CPU profiling support */
-	unsigned long fp_rev;
-	unsigned long fp_model;
-	unsigned int state;
-	struct parisc_device *dev;
-	unsigned long loops_per_jiffy;
-};
-
-extern struct system_cpuinfo_parisc boot_cpu_data;
-extern struct cpuinfo_parisc cpu_data[NR_CPUS];
-#define current_cpu_data cpu_data[smp_processor_id()]
-
-#define CPU_HVERSION ((boot_cpu_data.hversion >> 4) & 0x0FFF)
-
-typedef struct {
-	int seg;  
-} mm_segment_t;
-
-#define ARCH_MIN_TASKALIGN	8
-
-struct thread_struct {
-	struct pt_regs regs;
-	unsigned long  task_size;
-	unsigned long  map_base;
-	unsigned long  flags;
-}; 
-
-/* Thread struct flags. */
-#define PARISC_UAC_NOPRINT	(1UL << 0)	/* see prctl and unaligned.c */
-#define PARISC_UAC_SIGBUS	(1UL << 1)
-#define PARISC_KERNEL_DEATH	(1UL << 31)	/* see die_if_kernel()... */
-
-#define PARISC_UAC_SHIFT	0
-#define PARISC_UAC_MASK		(PARISC_UAC_NOPRINT|PARISC_UAC_SIGBUS)
-
-#define SET_UNALIGN_CTL(task,value)                                       \
-        ({                                                                \
-        (task)->thread.flags = (((task)->thread.flags & ~PARISC_UAC_MASK) \
-                                | (((value) << PARISC_UAC_SHIFT) &        \
-                                   PARISC_UAC_MASK));                     \
-        0;                                                                \
-        })
-
-#define GET_UNALIGN_CTL(task,addr)                                        \
-        ({                                                                \
-        put_user(((task)->thread.flags & PARISC_UAC_MASK)                 \
-                 >> PARISC_UAC_SHIFT, (int __user *) (addr));             \
-        })
-
-#define INIT_THREAD { \
-	.regs = {	.gr	= { 0, }, \
-			.fr	= { 0, }, \
-			.sr	= { 0, }, \
-			.iasq	= { 0, }, \
-			.iaoq	= { 0, }, \
-			.cr27	= 0, \
-		}, \
-	.task_size	= DEFAULT_TASK_SIZE, \
-	.map_base	= DEFAULT_MAP_BASE, \
-	.flags		= 0 \
-	}
-
-/*
- * Return saved PC of a blocked thread.  This is used by ps mostly.
- */
-
-unsigned long thread_saved_pc(struct task_struct *t);
-void show_trace(struct task_struct *task, unsigned long *stack);
-
-/*
- * Start user thread in another space.
- *
- * Note that we set both the iaoq and r31 to the new pc. When
- * the kernel initially calls execve it will return through an
- * rfi path that will use the values in the iaoq. The execve
- * syscall path will return through the gateway page, and
- * that uses r31 to branch to.
- *
- * For ELF we clear r23, because the dynamic linker uses it to pass
- * the address of the finalizer function.
- *
- * We also initialize sr3 to an illegal value (illegal for our
- * implementation, not for the architecture).
- */
-typedef unsigned int elf_caddr_t;
-
-#define start_thread_som(regs, new_pc, new_sp) do {	\
-	unsigned long *sp = (unsigned long *)new_sp;	\
-	__u32 spaceid = (__u32)current->mm->context;	\
-	unsigned long pc = (unsigned long)new_pc;	\
-	/* offset pc for priv. level */			\
-	pc |= 3;					\
-							\
-	set_fs(USER_DS);				\
-	regs->iasq[0] = spaceid;			\
-	regs->iasq[1] = spaceid;			\
-	regs->iaoq[0] = pc;				\
-	regs->iaoq[1] = pc + 4;                         \
-	regs->sr[2] = LINUX_GATEWAY_SPACE;              \
-	regs->sr[3] = 0xffff;				\
-	regs->sr[4] = spaceid;				\
-	regs->sr[5] = spaceid;				\
-	regs->sr[6] = spaceid;				\
-	regs->sr[7] = spaceid;				\
-	regs->gr[ 0] = USER_PSW;                        \
-	regs->gr[30] = ((new_sp)+63)&~63;		\
-	regs->gr[31] = pc;				\
-							\
-	get_user(regs->gr[26],&sp[0]);			\
-	get_user(regs->gr[25],&sp[-1]); 		\
-	get_user(regs->gr[24],&sp[-2]); 		\
-	get_user(regs->gr[23],&sp[-3]); 		\
-} while(0)
-
-/* The ELF abi wants things done a "wee bit" differently than
- * som does.  Supporting this behavior here avoids
- * having our own version of create_elf_tables.
- *
- * Oh, and yes, that is not a typo, we are really passing argc in r25
- * and argv in r24 (rather than r26 and r25).  This is because that's
- * where __libc_start_main wants them.
- *
- * Duplicated from dl-machine.h for the benefit of readers:
- *
- *  Our initial stack layout is rather different from everyone else's
- *  due to the unique PA-RISC ABI.  As far as I know it looks like
- *  this:
-
-   -----------------------------------  (user startup code creates this frame)
-   |         32 bytes of magic       |
-   |---------------------------------|
-   | 32 bytes argument/sp save area  |
-   |---------------------------------| (bprm->p)
-   |	    ELF auxiliary info	     |
-   |         (up to 28 words)        |
-   |---------------------------------|
-   |		   NULL		     |
-   |---------------------------------|
-   |	   Environment pointers	     |
-   |---------------------------------|
-   |		   NULL		     |
-   |---------------------------------|
-   |        Argument pointers        |
-   |---------------------------------| <- argv
-   |          argc (1 word)          |
-   |---------------------------------| <- bprm->exec (HACK!)
-   |         N bytes of slack        |
-   |---------------------------------|
-   |	filename passed to execve    |
-   |---------------------------------| (mm->env_end)
-   |           env strings           |
-   |---------------------------------| (mm->env_start, mm->arg_end)
-   |           arg strings           |
-   |---------------------------------|
-   | additional faked arg strings if |
-   | we're invoked via binfmt_script |
-   |---------------------------------| (mm->arg_start)
-   stack base is at TASK_SIZE - rlim_max.
-
-on downward growing arches, it looks like this:
-   stack base at TASK_SIZE
-   | filename passed to execve
-   | env strings
-   | arg strings
-   | faked arg strings
-   | slack
-   | ELF
-   | envps
-   | argvs
-   | argc
-
- *  The pleasant part of this is that if we need to skip arguments we
- *  can just decrement argc and move argv, because the stack pointer
- *  is utterly unrelated to the location of the environment and
- *  argument vectors.
- *
- * Note that the S/390 people took the easy way out and hacked their
- * GCC to make the stack grow downwards.
- *
- * Final Note: For entry from syscall, the W (wide) bit of the PSW
- * is stuffed into the lowest bit of the user sp (%r30), so we fill
- * it in here from the current->personality
- */
-
-#ifdef CONFIG_64BIT
-#define USER_WIDE_MODE	(!test_thread_flag(TIF_32BIT))
-#else
-#define USER_WIDE_MODE	0
-#endif
-
-#define start_thread(regs, new_pc, new_sp) do {		\
-	elf_addr_t *sp = (elf_addr_t *)new_sp;		\
-	__u32 spaceid = (__u32)current->mm->context;	\
-	elf_addr_t pc = (elf_addr_t)new_pc | 3;		\
-	elf_caddr_t *argv = (elf_caddr_t *)bprm->exec + 1;	\
-							\
-	set_fs(USER_DS);				\
-	regs->iasq[0] = spaceid;			\
-	regs->iasq[1] = spaceid;			\
-	regs->iaoq[0] = pc;				\
-	regs->iaoq[1] = pc + 4;                         \
-	regs->sr[2] = LINUX_GATEWAY_SPACE;              \
-	regs->sr[3] = 0xffff;				\
-	regs->sr[4] = spaceid;				\
-	regs->sr[5] = spaceid;				\
-	regs->sr[6] = spaceid;				\
-	regs->sr[7] = spaceid;				\
-	regs->gr[ 0] = USER_PSW | (USER_WIDE_MODE ? PSW_W : 0); \
-	regs->fr[ 0] = 0LL;                            	\
-	regs->fr[ 1] = 0LL;                            	\
-	regs->fr[ 2] = 0LL;                            	\
-	regs->fr[ 3] = 0LL;                            	\
-	regs->gr[30] = (((unsigned long)sp + 63) &~ 63) | (USER_WIDE_MODE ? 1 : 0); \
-	regs->gr[31] = pc;				\
-							\
-	get_user(regs->gr[25], (argv - 1));		\
-	regs->gr[24] = (long) argv;			\
-	regs->gr[23] = 0;				\
-} while(0)
-
-struct task_struct;
-struct mm_struct;
-
-/* Free all resources held by a thread. */
-extern void release_thread(struct task_struct *);
-extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
-
-/* Prepare to copy thread state - unlazy all lazy status */
-#define prepare_to_copy(tsk)	do { } while (0)
-
-extern void map_hpux_gateway_page(struct task_struct *tsk, struct mm_struct *mm);
-
-extern unsigned long get_wchan(struct task_struct *p);
-
-#define KSTK_EIP(tsk)	((tsk)->thread.regs.iaoq[0])
-#define KSTK_ESP(tsk)	((tsk)->thread.regs.gr[30])
-
-#define cpu_relax()	barrier()
-
-/* Used as a macro to identify the combined VIPT/PIPT cached
- * CPUs which require a guarantee of coherency (no inequivalent
- * aliases with different data, whether clean or not) to operate */
-static inline int parisc_requires_coherency(void)
-{
-#ifdef CONFIG_PA8X00
-	return (boot_cpu_data.cpu_type == mako) ||
-		(boot_cpu_data.cpu_type == mako2);
-#else
-	return 0;
-#endif
-}
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* __ASM_PARISC_PROCESSOR_H */
diff --git a/include/asm-parisc/psw.h b/include/asm-parisc/psw.h
deleted file mode 100644
index 5a3e23c9ce63..000000000000
--- a/include/asm-parisc/psw.h
+++ /dev/null
@@ -1,62 +0,0 @@
-#ifndef _PARISC_PSW_H
-
-
-#define	PSW_I	0x00000001
-#define	PSW_D	0x00000002
-#define	PSW_P	0x00000004
-#define	PSW_Q	0x00000008
-
-#define	PSW_R	0x00000010
-#define	PSW_F	0x00000020
-#define	PSW_G	0x00000040	/* PA1.x only */
-#define PSW_O	0x00000080	/* PA2.0 only */
-
-/* ssm/rsm instructions number PSW_W and PSW_E differently */
-#define PSW_SM_I	PSW_I	/* Enable External Interrupts */
-#define PSW_SM_D	PSW_D
-#define PSW_SM_P	PSW_P
-#define PSW_SM_Q	PSW_Q	/* Enable Interrupt State Collection */
-#define PSW_SM_R	PSW_R	/* Enable Recover Counter Trap */
-#define PSW_SM_W	0x200	/* PA2.0 only : Enable Wide Mode */
-
-#define PSW_SM_QUIET	PSW_SM_R+PSW_SM_Q+PSW_SM_P+PSW_SM_D+PSW_SM_I
-
-#define PSW_CB	0x0000ff00
-
-#define	PSW_M	0x00010000
-#define	PSW_V	0x00020000
-#define	PSW_C	0x00040000
-#define	PSW_B	0x00080000
-
-#define	PSW_X	0x00100000
-#define	PSW_N	0x00200000
-#define	PSW_L	0x00400000
-#define	PSW_H	0x00800000
-
-#define	PSW_T	0x01000000
-#define	PSW_S	0x02000000
-#define	PSW_E	0x04000000
-#define PSW_W	0x08000000	/* PA2.0 only */
-#define PSW_W_BIT       36      /* PA2.0 only */
-
-#define	PSW_Z	0x40000000	/* PA1.x only */
-#define	PSW_Y	0x80000000	/* PA1.x only */
-
-#ifdef CONFIG_64BIT
-#  define PSW_HI_CB 0x000000ff    /* PA2.0 only */
-#endif
-
-#ifdef CONFIG_64BIT
-#  define USER_PSW_HI_MASK	PSW_HI_CB
-#  define WIDE_PSW		PSW_W
-#else 
-#  define WIDE_PSW		0
-#endif
-
-/* Used when setting up for rfi */
-#define KERNEL_PSW    (WIDE_PSW | PSW_C | PSW_Q | PSW_P | PSW_D)
-#define REAL_MODE_PSW (WIDE_PSW | PSW_Q)
-#define USER_PSW_MASK (WIDE_PSW | PSW_T | PSW_N | PSW_X | PSW_B | PSW_V | PSW_CB)
-#define USER_PSW      (PSW_C | PSW_Q | PSW_P | PSW_D | PSW_I)
-
-#endif
diff --git a/include/asm-parisc/ptrace.h b/include/asm-parisc/ptrace.h
deleted file mode 100644
index 3e94c5d85ff5..000000000000
--- a/include/asm-parisc/ptrace.h
+++ /dev/null
@@ -1,58 +0,0 @@
-#ifndef _PARISC_PTRACE_H
-#define _PARISC_PTRACE_H
-
-/* written by Philipp Rumpf, Copyright (C) 1999 SuSE GmbH Nuernberg
-** Copyright (C) 2000 Grant Grundler, Hewlett-Packard
-*/
-
-#include <linux/types.h>
-
-/* This struct defines the way the registers are stored on the 
- * stack during a system call.
- *
- * N.B. gdb/strace care about the size and offsets within this
- * structure. If you change things, you may break object compatibility
- * for those applications.
- */
-
-struct pt_regs {
-	unsigned long gr[32];	/* PSW is in gr[0] */
-	__u64 fr[32];
-	unsigned long sr[ 8];
-	unsigned long iasq[2];
-	unsigned long iaoq[2];
-	unsigned long cr27;
-	unsigned long pad0;     /* available for other uses */
-	unsigned long orig_r28;
-	unsigned long ksp;
-	unsigned long kpc;
-	unsigned long sar;	/* CR11 */
-	unsigned long iir;	/* CR19 */
-	unsigned long isr;	/* CR20 */
-	unsigned long ior;	/* CR21 */
-	unsigned long ipsw;	/* CR22 */
-};
-
-/*
- * The numbers chosen here are somewhat arbitrary but absolutely MUST
- * not overlap with any of the number assigned in <linux/ptrace.h>.
- *
- * These ones are taken from IA-64 on the assumption that theirs are
- * the most correct (and we also want to support PTRACE_SINGLEBLOCK
- * since we have taken branch traps too)
- */
-#define PTRACE_SINGLEBLOCK	12	/* resume execution until next branch */
-
-#ifdef __KERNEL__
-
-#define task_regs(task) ((struct pt_regs *) ((char *)(task) + TASK_REGS))
-
-/* XXX should we use iaoq[1] or iaoq[0] ? */
-#define user_mode(regs)			(((regs)->iaoq[0] & 3) ? 1 : 0)
-#define user_space(regs)		(((regs)->iasq[1] != 0) ? 1 : 0)
-#define instruction_pointer(regs)	((regs)->iaoq[0] & ~3)
-unsigned long profile_pc(struct pt_regs *);
-extern void show_regs(struct pt_regs *);
-#endif
-
-#endif
diff --git a/include/asm-parisc/real.h b/include/asm-parisc/real.h
deleted file mode 100644
index 82acb25db395..000000000000
--- a/include/asm-parisc/real.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifndef _PARISC_REAL_H
-#define _PARISC_REAL_H
-
-
-#endif
diff --git a/include/asm-parisc/resource.h b/include/asm-parisc/resource.h
deleted file mode 100644
index 8b06343b62ed..000000000000
--- a/include/asm-parisc/resource.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _ASM_PARISC_RESOURCE_H
-#define _ASM_PARISC_RESOURCE_H
-
-#define _STK_LIM_MAX	10 * _STK_LIM
-#include <asm-generic/resource.h>
-
-#endif
diff --git a/include/asm-parisc/ropes.h b/include/asm-parisc/ropes.h
deleted file mode 100644
index 09f51d5ab57c..000000000000
--- a/include/asm-parisc/ropes.h
+++ /dev/null
@@ -1,322 +0,0 @@
-#ifndef _ASM_PARISC_ROPES_H_
-#define _ASM_PARISC_ROPES_H_
-
-#include <asm/parisc-device.h>
-
-#ifdef CONFIG_64BIT
-/* "low end" PA8800 machines use ZX1 chipset: PAT PDC and only run 64-bit */
-#define ZX1_SUPPORT
-#endif
-
-#ifdef CONFIG_PROC_FS
-/* depends on proc fs support. But costs CPU performance */
-#undef SBA_COLLECT_STATS
-#endif
-
-/*
-** The number of pdir entries to "free" before issuing
-** a read to PCOM register to flush out PCOM writes.
-** Interacts with allocation granularity (ie 4 or 8 entries
-** allocated and free'd/purged at a time might make this
-** less interesting).
-*/
-#define DELAYED_RESOURCE_CNT	16
-
-#define MAX_IOC		2	/* per Ike. Pluto/Astro only have 1. */
-#define ROPES_PER_IOC	8	/* per Ike half or Pluto/Astro */
-
-struct ioc {
-	void __iomem	*ioc_hpa;	/* I/O MMU base address */
-	char		*res_map;	/* resource map, bit == pdir entry */
-	u64		*pdir_base;	/* physical base address */
-	unsigned long	ibase;		/* pdir IOV Space base - shared w/lba_pci */
-	unsigned long	imask;		/* pdir IOV Space mask - shared w/lba_pci */
-#ifdef ZX1_SUPPORT
-	unsigned long	iovp_mask;	/* help convert IOVA to IOVP */
-#endif
-	unsigned long	*res_hint;	/* next avail IOVP - circular search */
-	spinlock_t	res_lock;
-	unsigned int	res_bitshift;	/* from the LEFT! */
-	unsigned int	res_size;	/* size of resource map in bytes */
-#ifdef SBA_HINT_SUPPORT
-/* FIXME : DMA HINTs not used */
-	unsigned long	hint_mask_pdir; /* bits used for DMA hints */
-	unsigned int	hint_shift_pdir;
-#endif
-#if DELAYED_RESOURCE_CNT > 0
-	int		saved_cnt;
-	struct sba_dma_pair {
-			dma_addr_t	iova;
-			size_t		size;
-        } saved[DELAYED_RESOURCE_CNT];
-#endif
-
-#ifdef SBA_COLLECT_STATS
-#define SBA_SEARCH_SAMPLE	0x100
-	unsigned long	avg_search[SBA_SEARCH_SAMPLE];
-	unsigned long	avg_idx;	/* current index into avg_search */
-	unsigned long	used_pages;
-	unsigned long	msingle_calls;
-	unsigned long	msingle_pages;
-	unsigned long	msg_calls;
-	unsigned long	msg_pages;
-	unsigned long	usingle_calls;
-	unsigned long	usingle_pages;
-	unsigned long	usg_calls;
-	unsigned long	usg_pages;
-#endif
-        /* STUFF We don't need in performance path */
-	unsigned int	pdir_size;	/* in bytes, determined by IOV Space size */
-};
-
-struct sba_device {
-	struct sba_device	*next;  /* list of SBA's in system */
-	struct parisc_device	*dev;   /* dev found in bus walk */
-	const char		*name;
-	void __iomem		*sba_hpa; /* base address */
-	spinlock_t		sba_lock;
-	unsigned int		flags;  /* state/functionality enabled */
-	unsigned int		hw_rev;  /* HW revision of chip */
-
-	struct resource		chip_resv; /* MMIO reserved for chip */
-	struct resource		iommu_resv; /* MMIO reserved for iommu */
-
-	unsigned int		num_ioc;  /* number of on-board IOC's */
-	struct ioc		ioc[MAX_IOC];
-};
-
-#define ASTRO_RUNWAY_PORT	0x582
-#define IKE_MERCED_PORT		0x803
-#define REO_MERCED_PORT		0x804
-#define REOG_MERCED_PORT	0x805
-#define PLUTO_MCKINLEY_PORT	0x880
-
-static inline int IS_ASTRO(struct parisc_device *d) {
-	return d->id.hversion == ASTRO_RUNWAY_PORT;
-}
-
-static inline int IS_IKE(struct parisc_device *d) {
-	return d->id.hversion == IKE_MERCED_PORT;
-}
-
-static inline int IS_PLUTO(struct parisc_device *d) {
-	return d->id.hversion == PLUTO_MCKINLEY_PORT;
-}
-
-#define PLUTO_IOVA_BASE	(1UL*1024*1024*1024)	/* 1GB */
-#define PLUTO_IOVA_SIZE	(1UL*1024*1024*1024)	/* 1GB */
-#define PLUTO_GART_SIZE	(PLUTO_IOVA_SIZE / 2)
-
-#define SBA_PDIR_VALID_BIT	0x8000000000000000ULL
-
-#define SBA_AGPGART_COOKIE	0x0000badbadc0ffeeULL
-
-#define SBA_FUNC_ID	0x0000	/* function id */
-#define SBA_FCLASS	0x0008	/* function class, bist, header, rev... */
-
-#define SBA_FUNC_SIZE 4096   /* SBA configuration function reg set */
-
-#define ASTRO_IOC_OFFSET	(32 * SBA_FUNC_SIZE)
-#define PLUTO_IOC_OFFSET	(1 * SBA_FUNC_SIZE)
-/* Ike's IOC's occupy functions 2 and 3 */
-#define IKE_IOC_OFFSET(p)	((p+2) * SBA_FUNC_SIZE)
-
-#define IOC_CTRL          0x8	/* IOC_CTRL offset */
-#define IOC_CTRL_TC       (1 << 0) /* TOC Enable */
-#define IOC_CTRL_CE       (1 << 1) /* Coalesce Enable */
-#define IOC_CTRL_DE       (1 << 2) /* Dillon Enable */
-#define IOC_CTRL_RM       (1 << 8) /* Real Mode */
-#define IOC_CTRL_NC       (1 << 9) /* Non Coherent Mode */
-#define IOC_CTRL_D4       (1 << 11) /* Disable 4-byte coalescing */
-#define IOC_CTRL_DD       (1 << 13) /* Disable distr. LMMIO range coalescing */
-
-/*
-** Offsets into MBIB (Function 0 on Ike and hopefully Astro)
-** Firmware programs this stuff. Don't touch it.
-*/
-#define LMMIO_DIRECT0_BASE  0x300
-#define LMMIO_DIRECT0_MASK  0x308
-#define LMMIO_DIRECT0_ROUTE 0x310
-
-#define LMMIO_DIST_BASE  0x360
-#define LMMIO_DIST_MASK  0x368
-#define LMMIO_DIST_ROUTE 0x370
-
-#define IOS_DIST_BASE	0x390
-#define IOS_DIST_MASK	0x398
-#define IOS_DIST_ROUTE	0x3A0
-
-#define IOS_DIRECT_BASE	0x3C0
-#define IOS_DIRECT_MASK	0x3C8
-#define IOS_DIRECT_ROUTE 0x3D0
-
-/*
-** Offsets into I/O TLB (Function 2 and 3 on Ike)
-*/
-#define ROPE0_CTL	0x200  /* "regbus pci0" */
-#define ROPE1_CTL	0x208
-#define ROPE2_CTL	0x210
-#define ROPE3_CTL	0x218
-#define ROPE4_CTL	0x220
-#define ROPE5_CTL	0x228
-#define ROPE6_CTL	0x230
-#define ROPE7_CTL	0x238
-
-#define IOC_ROPE0_CFG	0x500	/* pluto only */
-#define   IOC_ROPE_AO	  0x10	/* Allow "Relaxed Ordering" */
-
-#define HF_ENABLE	0x40
-
-#define IOC_IBASE	0x300	/* IO TLB */
-#define IOC_IMASK	0x308
-#define IOC_PCOM	0x310
-#define IOC_TCNFG	0x318
-#define IOC_PDIR_BASE	0x320
-
-/*
-** IOC supports 4/8/16/64KB page sizes (see TCNFG register)
-** It's safer (avoid memory corruption) to keep DMA page mappings
-** equivalently sized to VM PAGE_SIZE.
-**
-** We really can't avoid generating a new mapping for each
-** page since the Virtual Coherence Index has to be generated
-** and updated for each page.
-**
-** PAGE_SIZE could be greater than IOVP_SIZE. But not the inverse.
-*/
-#define IOVP_SIZE	PAGE_SIZE
-#define IOVP_SHIFT	PAGE_SHIFT
-#define IOVP_MASK	PAGE_MASK
-
-#define SBA_PERF_CFG	0x708	/* Performance Counter stuff */
-#define SBA_PERF_MASK1	0x718
-#define SBA_PERF_MASK2	0x730
-
-/*
-** Offsets into PCI Performance Counters (functions 12 and 13)
-** Controlled by PERF registers in function 2 & 3 respectively.
-*/
-#define SBA_PERF_CNT1	0x200
-#define SBA_PERF_CNT2	0x208
-#define SBA_PERF_CNT3	0x210
-
-/*
-** lba_device: Per instance Elroy data structure
-*/
-struct lba_device {
-	struct pci_hba_data	hba;
-
-	spinlock_t		lba_lock;
-	void			*iosapic_obj;
-
-#ifdef CONFIG_64BIT
-	void __iomem		*iop_base;	/* PA_VIEW - for IO port accessor funcs */
-#endif
-
-	int			flags;		/* state/functionality enabled */
-	int			hw_rev;		/* HW revision of chip */
-};
-
-#define ELROY_HVERS		0x782
-#define MERCURY_HVERS		0x783
-#define QUICKSILVER_HVERS	0x784
-
-static inline int IS_ELROY(struct parisc_device *d) {
-	return (d->id.hversion == ELROY_HVERS);
-}
-
-static inline int IS_MERCURY(struct parisc_device *d) {
-	return (d->id.hversion == MERCURY_HVERS);
-}
-
-static inline int IS_QUICKSILVER(struct parisc_device *d) {
-	return (d->id.hversion == QUICKSILVER_HVERS);
-}
-
-static inline int agp_mode_mercury(void __iomem *hpa) {
-	u64 bus_mode;
-
-	bus_mode = readl(hpa + 0x0620);
-	if (bus_mode & 1)
-		return 1;
-
-	return 0;
-}
-
-/*
-** I/O SAPIC init function
-** Caller knows where an I/O SAPIC is. LBA has an integrated I/O SAPIC.
-** Call setup as part of per instance initialization.
-** (ie *not* init_module() function unless only one is present.)
-** fixup_irq is to initialize PCI IRQ line support and
-** virtualize pcidev->irq value. To be called by pci_fixup_bus().
-*/
-extern void *iosapic_register(unsigned long hpa);
-extern int iosapic_fixup_irq(void *obj, struct pci_dev *pcidev);
-
-#define LBA_FUNC_ID	0x0000	/* function id */
-#define LBA_FCLASS	0x0008	/* function class, bist, header, rev... */
-#define LBA_CAPABLE	0x0030	/* capabilities register */
-
-#define LBA_PCI_CFG_ADDR	0x0040	/* poke CFG address here */
-#define LBA_PCI_CFG_DATA	0x0048	/* read or write data here */
-
-#define LBA_PMC_MTLT	0x0050	/* Firmware sets this - read only. */
-#define LBA_FW_SCRATCH	0x0058	/* Firmware writes the PCI bus number here. */
-#define LBA_ERROR_ADDR	0x0070	/* On error, address gets logged here */
-
-#define LBA_ARB_MASK	0x0080	/* bit 0 enable arbitration. PAT/PDC enables */
-#define LBA_ARB_PRI	0x0088	/* firmware sets this. */
-#define LBA_ARB_MODE	0x0090	/* firmware sets this. */
-#define LBA_ARB_MTLT	0x0098	/* firmware sets this. */
-
-#define LBA_MOD_ID	0x0100	/* Module ID. PDC_PAT_CELL reports 4 */
-
-#define LBA_STAT_CTL	0x0108	/* Status & Control */
-#define   LBA_BUS_RESET		0x01	/*  Deassert PCI Bus Reset Signal */
-#define   CLEAR_ERRLOG		0x10	/*  "Clear Error Log" cmd */
-#define   CLEAR_ERRLOG_ENABLE	0x20	/*  "Clear Error Log" Enable */
-#define   HF_ENABLE	0x40	/*    enable HF mode (default is -1 mode) */
-
-#define LBA_LMMIO_BASE	0x0200	/* < 4GB I/O address range */
-#define LBA_LMMIO_MASK	0x0208
-
-#define LBA_GMMIO_BASE	0x0210	/* > 4GB I/O address range */
-#define LBA_GMMIO_MASK	0x0218
-
-#define LBA_WLMMIO_BASE	0x0220	/* All < 4GB ranges under the same *SBA* */
-#define LBA_WLMMIO_MASK	0x0228
-
-#define LBA_WGMMIO_BASE	0x0230	/* All > 4GB ranges under the same *SBA* */
-#define LBA_WGMMIO_MASK	0x0238
-
-#define LBA_IOS_BASE	0x0240	/* I/O port space for this LBA */
-#define LBA_IOS_MASK	0x0248
-
-#define LBA_ELMMIO_BASE	0x0250	/* Extra LMMIO range */
-#define LBA_ELMMIO_MASK	0x0258
-
-#define LBA_EIOS_BASE	0x0260	/* Extra I/O port space */
-#define LBA_EIOS_MASK	0x0268
-
-#define LBA_GLOBAL_MASK	0x0270	/* Mercury only: Global Address Mask */
-#define LBA_DMA_CTL	0x0278	/* firmware sets this */
-
-#define LBA_IBASE	0x0300	/* SBA DMA support */
-#define LBA_IMASK	0x0308
-
-/* FIXME: ignore DMA Hint stuff until we can measure performance */
-#define LBA_HINT_CFG	0x0310
-#define LBA_HINT_BASE	0x0380	/* 14 registers at every 8 bytes. */
-
-#define LBA_BUS_MODE	0x0620
-
-/* ERROR regs are needed for config cycle kluges */
-#define LBA_ERROR_CONFIG 0x0680
-#define     LBA_SMART_MODE 0x20
-#define LBA_ERROR_STATUS 0x0688
-#define LBA_ROPE_CTL     0x06A0
-
-#define LBA_IOSAPIC_BASE	0x800 /* Offset of IRQ logic */
-
-#endif /*_ASM_PARISC_ROPES_H_*/
diff --git a/include/asm-parisc/rt_sigframe.h b/include/asm-parisc/rt_sigframe.h
deleted file mode 100644
index f0dd3b30f6c4..000000000000
--- a/include/asm-parisc/rt_sigframe.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef _ASM_PARISC_RT_SIGFRAME_H
-#define _ASM_PARISC_RT_SIGFRAME_H
-
-#define SIGRETURN_TRAMP 4
-#define SIGRESTARTBLOCK_TRAMP 5 
-#define TRAMP_SIZE (SIGRETURN_TRAMP + SIGRESTARTBLOCK_TRAMP)
-
-struct rt_sigframe {
-	/* XXX: Must match trampoline size in arch/parisc/kernel/signal.c 
-	        Secondary to that it must protect the ERESTART_RESTARTBLOCK
-		trampoline we left on the stack (we were bad and didn't 
-		change sp so we could run really fast.) */
-	unsigned int tramp[TRAMP_SIZE];
-	struct siginfo info;
-	struct ucontext uc;
-};
-
-#define	SIGFRAME		128
-#define FUNCTIONCALLFRAME	96
-#define PARISC_RT_SIGFRAME_SIZE					\
-	(((sizeof(struct rt_sigframe) + FUNCTIONCALLFRAME) + SIGFRAME) & -SIGFRAME)
-
-#endif
diff --git a/include/asm-parisc/rtc.h b/include/asm-parisc/rtc.h
deleted file mode 100644
index 099d641a42c2..000000000000
--- a/include/asm-parisc/rtc.h
+++ /dev/null
@@ -1,131 +0,0 @@
-/* 
- * include/asm-parisc/rtc.h
- *
- * Copyright 2002 Randolph CHung <tausq@debian.org>
- *
- * Based on: include/asm-ppc/rtc.h and the genrtc driver in the
- * 2.4 parisc linux tree
- */
-
-#ifndef __ASM_RTC_H__
-#define __ASM_RTC_H__
-
-#ifdef __KERNEL__
-
-#include <linux/rtc.h>
-
-#include <asm/pdc.h>
-
-#define SECS_PER_HOUR   (60 * 60)
-#define SECS_PER_DAY    (SECS_PER_HOUR * 24)
-
-
-#define RTC_PIE 0x40		/* periodic interrupt enable */
-#define RTC_AIE 0x20		/* alarm interrupt enable */
-#define RTC_UIE 0x10		/* update-finished interrupt enable */
-
-#define RTC_BATT_BAD 0x100	/* battery bad */
-
-/* some dummy definitions */
-#define RTC_SQWE 0x08		/* enable square-wave output */
-#define RTC_DM_BINARY 0x04	/* all time/date values are BCD if clear */
-#define RTC_24H 0x02		/* 24 hour mode - else hours bit 7 means pm */
-#define RTC_DST_EN 0x01	        /* auto switch DST - works f. USA only */
-
-# define __isleap(year) \
-  ((year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0))
-
-/* How many days come before each month (0-12).  */
-static const unsigned short int __mon_yday[2][13] =
-{
-	/* Normal years.  */
-	{ 0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365 },
-	/* Leap years.  */
-	{ 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366 }
-};
-
-static inline unsigned int get_rtc_time(struct rtc_time *wtime)
-{
-	struct pdc_tod tod_data;
-	long int days, rem, y;
-	const unsigned short int *ip;
-
-	memset(wtime, 0, sizeof(*wtime));
-	if (pdc_tod_read(&tod_data) < 0)
-		return RTC_24H | RTC_BATT_BAD;
-
-	// most of the remainder of this function is:
-//	Copyright (C) 1991, 1993, 1997, 1998 Free Software Foundation, Inc.
-//	This was originally a part of the GNU C Library.
-//      It is distributed under the GPL, and was swiped from offtime.c
-
-
-	days = tod_data.tod_sec / SECS_PER_DAY;
-	rem = tod_data.tod_sec % SECS_PER_DAY;
-
-	wtime->tm_hour = rem / SECS_PER_HOUR;
-	rem %= SECS_PER_HOUR;
-	wtime->tm_min = rem / 60;
-	wtime->tm_sec = rem % 60;
-
-	y = 1970;
-
-#define DIV(a, b) ((a) / (b) - ((a) % (b) < 0))
-#define LEAPS_THRU_END_OF(y) (DIV (y, 4) - DIV (y, 100) + DIV (y, 400))
-
-	while (days < 0 || days >= (__isleap (y) ? 366 : 365))
-	{
-		/* Guess a corrected year, assuming 365 days per year.  */
-		long int yg = y + days / 365 - (days % 365 < 0);
-
-		/* Adjust DAYS and Y to match the guessed year.  */
-		days -= ((yg - y) * 365
-			 + LEAPS_THRU_END_OF (yg - 1)
-			 - LEAPS_THRU_END_OF (y - 1));
-		y = yg;
-	}
-	wtime->tm_year = y - 1900;
-
-	ip = __mon_yday[__isleap(y)];
-	for (y = 11; days < (long int) ip[y]; --y)
-		continue;
-	days -= ip[y];
-	wtime->tm_mon = y;
-	wtime->tm_mday = days + 1;
-
-	return RTC_24H;
-}
-
-static int set_rtc_time(struct rtc_time *wtime)
-{
-	u_int32_t secs;
-
-	secs = mktime(wtime->tm_year + 1900, wtime->tm_mon + 1, wtime->tm_mday, 
-		      wtime->tm_hour, wtime->tm_min, wtime->tm_sec);
-
-	if(pdc_tod_set(secs, 0) < 0)
-		return -1;
-	else
-		return 0;
-
-}
-
-static inline unsigned int get_rtc_ss(void)
-{
-	struct rtc_time h;
-
-	get_rtc_time(&h);
-	return h.tm_sec;
-}
-
-static inline int get_rtc_pll(struct rtc_pll_info *pll)
-{
-	return -EINVAL;
-}
-static inline int set_rtc_pll(struct rtc_pll_info *pll)
-{
-	return -EINVAL;
-}
-
-#endif /* __KERNEL__ */
-#endif /* __ASM_RTC_H__ */
diff --git a/include/asm-parisc/runway.h b/include/asm-parisc/runway.h
deleted file mode 100644
index 5bea02da7e22..000000000000
--- a/include/asm-parisc/runway.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef ASM_PARISC_RUNWAY_H
-#define ASM_PARISC_RUNWAY_H
-#ifdef __KERNEL__
-
-/* declared in arch/parisc/kernel/setup.c */
-extern struct proc_dir_entry * proc_runway_root;
-
-#define RUNWAY_STATUS	0x10
-#define RUNWAY_DEBUG	0x40
-
-#endif /* __KERNEL__ */
-#endif /* ASM_PARISC_RUNWAY_H */
diff --git a/include/asm-parisc/scatterlist.h b/include/asm-parisc/scatterlist.h
deleted file mode 100644
index 62269b31ebf4..000000000000
--- a/include/asm-parisc/scatterlist.h
+++ /dev/null
@@ -1,27 +0,0 @@
-#ifndef _ASM_PARISC_SCATTERLIST_H
-#define _ASM_PARISC_SCATTERLIST_H
-
-#include <asm/page.h>
-#include <asm/types.h>
-
-struct scatterlist {
-#ifdef CONFIG_DEBUG_SG
-	unsigned long sg_magic;
-#endif
-	unsigned long page_link;
-	unsigned int offset;
-
-	unsigned int length;
-
-	/* an IOVA can be 64-bits on some PA-Risc platforms. */
-	dma_addr_t iova;	/* I/O Virtual Address */
-	__u32      iova_length; /* bytes mapped */
-};
-
-#define sg_virt_addr(sg) ((unsigned long)sg_virt(sg))
-#define sg_dma_address(sg) ((sg)->iova)
-#define sg_dma_len(sg)     ((sg)->iova_length)
-
-#define ISA_DMA_THRESHOLD (~0UL)
-
-#endif /* _ASM_PARISC_SCATTERLIST_H */
diff --git a/include/asm-parisc/sections.h b/include/asm-parisc/sections.h
deleted file mode 100644
index 9d13c3507ad6..000000000000
--- a/include/asm-parisc/sections.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _PARISC_SECTIONS_H
-#define _PARISC_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#ifdef CONFIG_64BIT
-#undef dereference_function_descriptor
-void *dereference_function_descriptor(void *);
-#endif
-
-#endif
diff --git a/include/asm-parisc/segment.h b/include/asm-parisc/segment.h
deleted file mode 100644
index 26794ddb6524..000000000000
--- a/include/asm-parisc/segment.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __PARISC_SEGMENT_H
-#define __PARISC_SEGMENT_H
-
-/* Only here because we have some old header files that expect it.. */
-
-#endif
diff --git a/include/asm-parisc/sembuf.h b/include/asm-parisc/sembuf.h
deleted file mode 100644
index 1e59ffd3bd1e..000000000000
--- a/include/asm-parisc/sembuf.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef _PARISC_SEMBUF_H
-#define _PARISC_SEMBUF_H
-
-/* 
- * The semid64_ds structure for parisc architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct semid64_ds {
-	struct ipc64_perm sem_perm;		/* permissions .. see ipc.h */
-#ifndef CONFIG_64BIT
-	unsigned int	__pad1;
-#endif
-	__kernel_time_t	sem_otime;		/* last semop time */
-#ifndef CONFIG_64BIT
-	unsigned int	__pad2;
-#endif
-	__kernel_time_t	sem_ctime;		/* last change time */
-	unsigned int	sem_nsems;		/* no. of semaphores in array */
-	unsigned int	__unused1;
-	unsigned int	__unused2;
-};
-
-#endif /* _PARISC_SEMBUF_H */
diff --git a/include/asm-parisc/serial.h b/include/asm-parisc/serial.h
deleted file mode 100644
index d7e3cc60dbc3..000000000000
--- a/include/asm-parisc/serial.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/*
- * include/asm-parisc/serial.h
- */
-
-/*
- * This is used for 16550-compatible UARTs
- */
-#define BASE_BAUD ( 1843200 / 16 )
-
-#define SERIAL_PORT_DFNS
diff --git a/include/asm-parisc/setup.h b/include/asm-parisc/setup.h
deleted file mode 100644
index 7da2e5b8747e..000000000000
--- a/include/asm-parisc/setup.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _PARISC_SETUP_H
-#define _PARISC_SETUP_H
-
-#define COMMAND_LINE_SIZE	1024
-
-#endif /* _PARISC_SETUP_H */
diff --git a/include/asm-parisc/shmbuf.h b/include/asm-parisc/shmbuf.h
deleted file mode 100644
index 0a3eada1863b..000000000000
--- a/include/asm-parisc/shmbuf.h
+++ /dev/null
@@ -1,58 +0,0 @@
-#ifndef _PARISC_SHMBUF_H
-#define _PARISC_SHMBUF_H
-
-/* 
- * The shmid64_ds structure for parisc architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-
-struct shmid64_ds {
-	struct ipc64_perm	shm_perm;	/* operation perms */
-#ifndef CONFIG_64BIT
-	unsigned int		__pad1;
-#endif
-	__kernel_time_t		shm_atime;	/* last attach time */
-#ifndef CONFIG_64BIT
-	unsigned int		__pad2;
-#endif
-	__kernel_time_t		shm_dtime;	/* last detach time */
-#ifndef CONFIG_64BIT
-	unsigned int		__pad3;
-#endif
-	__kernel_time_t		shm_ctime;	/* last change time */
-#ifndef CONFIG_64BIT
-	unsigned int		__pad4;
-#endif
-	size_t			shm_segsz;	/* size of segment (bytes) */
-	__kernel_pid_t		shm_cpid;	/* pid of creator */
-	__kernel_pid_t		shm_lpid;	/* pid of last operator */
-	unsigned int		shm_nattch;	/* no. of current attaches */
-	unsigned int		__unused1;
-	unsigned int		__unused2;
-};
-
-#ifdef CONFIG_64BIT
-/* The 'unsigned int' (formerly 'unsigned long') data types below will
- * ensure that a 32-bit app calling shmctl(*,IPC_INFO,*) will work on
- * a wide kernel, but if some of these values are meant to contain pointers
- * they may need to be 'long long' instead. -PB XXX FIXME
- */
-#endif
-struct shminfo64 {
-	unsigned int	shmmax;
-	unsigned int	shmmin;
-	unsigned int	shmmni;
-	unsigned int	shmseg;
-	unsigned int	shmall;
-	unsigned int	__unused1;
-	unsigned int	__unused2;
-	unsigned int	__unused3;
-	unsigned int	__unused4;
-};
-
-#endif /* _PARISC_SHMBUF_H */
diff --git a/include/asm-parisc/shmparam.h b/include/asm-parisc/shmparam.h
deleted file mode 100644
index 628ddc22faa8..000000000000
--- a/include/asm-parisc/shmparam.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _ASMPARISC_SHMPARAM_H
-#define _ASMPARISC_SHMPARAM_H
-
-#define __ARCH_FORCE_SHMLBA 	1
-
-#define SHMLBA 0x00400000   /* attach addr needs to be 4 Mb aligned */
-
-#endif /* _ASMPARISC_SHMPARAM_H */
diff --git a/include/asm-parisc/sigcontext.h b/include/asm-parisc/sigcontext.h
deleted file mode 100644
index 27ef31bb3b6e..000000000000
--- a/include/asm-parisc/sigcontext.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef _ASMPARISC_SIGCONTEXT_H
-#define _ASMPARISC_SIGCONTEXT_H
-
-#define PARISC_SC_FLAG_ONSTACK 1<<0
-#define PARISC_SC_FLAG_IN_SYSCALL 1<<1
-
-/* We will add more stuff here as it becomes necessary, until we know
-   it works. */
-struct sigcontext {
-	unsigned long sc_flags;
-
-	unsigned long sc_gr[32]; /* PSW in sc_gr[0] */
-	unsigned long long sc_fr[32]; /* FIXME, do we need other state info? */
-	unsigned long sc_iasq[2];
-	unsigned long sc_iaoq[2];
-	unsigned long sc_sar; /* cr11 */
-};
-
-
-#endif
diff --git a/include/asm-parisc/siginfo.h b/include/asm-parisc/siginfo.h
deleted file mode 100644
index d4909f55fe35..000000000000
--- a/include/asm-parisc/siginfo.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef _PARISC_SIGINFO_H
-#define _PARISC_SIGINFO_H
-
-#include <asm-generic/siginfo.h>
-
-/*
- * SIGTRAP si_codes
- */
-#define TRAP_BRANCH	(__SI_FAULT|3)	/* process taken branch trap */
-#define TRAP_HWBKPT	(__SI_FAULT|4)	/* hardware breakpoint or watchpoint */
-#undef NSIGTRAP
-#define NSIGTRAP	4
-
-#endif
diff --git a/include/asm-parisc/signal.h b/include/asm-parisc/signal.h
deleted file mode 100644
index c20356375d1d..000000000000
--- a/include/asm-parisc/signal.h
+++ /dev/null
@@ -1,153 +0,0 @@
-#ifndef _ASM_PARISC_SIGNAL_H
-#define _ASM_PARISC_SIGNAL_H
-
-#define SIGHUP		 1
-#define SIGINT		 2
-#define SIGQUIT		 3
-#define SIGILL		 4
-#define SIGTRAP		 5
-#define SIGABRT		 6
-#define SIGIOT		 6
-#define SIGEMT		 7
-#define SIGFPE		 8
-#define SIGKILL		 9
-#define SIGBUS		10
-#define SIGSEGV		11
-#define SIGSYS		12 /* Linux doesn't use this */
-#define SIGPIPE		13
-#define SIGALRM		14
-#define SIGTERM		15
-#define SIGUSR1		16
-#define SIGUSR2		17
-#define SIGCHLD		18
-#define SIGPWR		19
-#define SIGVTALRM	20
-#define SIGPROF		21
-#define SIGIO		22
-#define SIGPOLL		SIGIO
-#define SIGWINCH	23
-#define SIGSTOP		24
-#define SIGTSTP		25
-#define SIGCONT		26
-#define SIGTTIN		27
-#define SIGTTOU		28
-#define SIGURG		29
-#define SIGLOST		30 /* Linux doesn't use this either */
-#define	SIGUNUSED	31
-#define SIGRESERVE	SIGUNUSED
-
-#define SIGXCPU		33
-#define SIGXFSZ		34
-#define SIGSTKFLT	36
-
-/* These should not be considered constants from userland.  */
-#define SIGRTMIN	37
-#define SIGRTMAX	_NSIG /* it's 44 under HP/UX */
-
-/*
- * SA_FLAGS values:
- *
- * SA_ONSTACK indicates that a registered stack_t will be used.
- * SA_RESTART flag to get restarting signals (which were the default long ago)
- * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
- * SA_RESETHAND clears the handler when the signal is delivered.
- * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
- * SA_NODEFER prevents the current signal from being masked in the handler.
- *
- * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
- * Unix names RESETHAND and NODEFER respectively.
- */
-#define SA_ONSTACK	0x00000001
-#define SA_RESETHAND	0x00000004
-#define SA_NOCLDSTOP	0x00000008
-#define SA_SIGINFO	0x00000010
-#define SA_NODEFER	0x00000020
-#define SA_RESTART	0x00000040
-#define SA_NOCLDWAIT	0x00000080
-#define _SA_SIGGFAULT	0x00000100 /* HPUX */
-
-#define SA_NOMASK	SA_NODEFER
-#define SA_ONESHOT	SA_RESETHAND
-
-#define SA_RESTORER	0x04000000 /* obsolete -- ignored */
-
-/* 
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
-#define MINSIGSTKSZ	2048
-#define SIGSTKSZ	8192
-
-#ifdef __KERNEL__
-
-#define _NSIG		64
-/* bits-per-word, where word apparently means 'long' not 'int' */
-#define _NSIG_BPW	BITS_PER_LONG
-#define _NSIG_WORDS	(_NSIG / _NSIG_BPW)
-
-#endif /* __KERNEL__ */
-
-#define SIG_BLOCK          0	/* for blocking signals */
-#define SIG_UNBLOCK        1	/* for unblocking signals */
-#define SIG_SETMASK        2	/* for setting the signal mask */
-
-#define SIG_DFL	((__sighandler_t)0)	/* default signal handling */
-#define SIG_IGN	((__sighandler_t)1)	/* ignore signal */
-#define SIG_ERR	((__sighandler_t)-1)	/* error return from signal */
-
-# ifndef __ASSEMBLY__
-
-#  include <linux/types.h>
-
-/* Avoid too many header ordering problems.  */
-struct siginfo;
-
-/* Type of a signal handler.  */
-#ifdef CONFIG_64BIT
-/* function pointers on 64-bit parisc are pointers to little structs and the
- * compiler doesn't support code which changes or tests the address of
- * the function in the little struct.  This is really ugly -PB
- */
-typedef char __user *__sighandler_t;
-#else
-typedef void __signalfn_t(int);
-typedef __signalfn_t __user *__sighandler_t;
-#endif
-
-typedef struct sigaltstack {
-	void __user *ss_sp;
-	int ss_flags;
-	size_t ss_size;
-} stack_t;
-
-#ifdef __KERNEL__
-
-/* Most things should be clean enough to redefine this at will, if care
-   is taken to make libc match.  */
-
-typedef unsigned long old_sigset_t;		/* at least 32 bits */
-
-typedef struct {
-	/* next_signal() assumes this is a long - no choice */
-	unsigned long sig[_NSIG_WORDS];
-} sigset_t;
-
-struct sigaction {
-	__sighandler_t sa_handler;
-	unsigned long sa_flags;
-	sigset_t sa_mask;		/* mask last for extensibility */
-};
-
-struct k_sigaction {
-	struct sigaction sa;
-};
-
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
-#include <asm/sigcontext.h>
-
-#endif /* __KERNEL__ */
-#endif /* !__ASSEMBLY */
-#endif /* _ASM_PARISC_SIGNAL_H */
diff --git a/include/asm-parisc/smp.h b/include/asm-parisc/smp.h
deleted file mode 100644
index 398cdbaf4e54..000000000000
--- a/include/asm-parisc/smp.h
+++ /dev/null
@@ -1,68 +0,0 @@
-#ifndef __ASM_SMP_H
-#define __ASM_SMP_H
-
-
-#if defined(CONFIG_SMP)
-
-/* Page Zero Location PDC will look for the address to branch to when we poke
-** slave CPUs still in "Icache loop".
-*/
-#define PDC_OS_BOOT_RENDEZVOUS     0x10
-#define PDC_OS_BOOT_RENDEZVOUS_HI  0x28
-
-#ifndef ASSEMBLY
-#include <linux/bitops.h>
-#include <linux/threads.h>	/* for NR_CPUS */
-#include <linux/cpumask.h>
-typedef unsigned long address_t;
-
-extern cpumask_t cpu_online_map;
-
-
-/*
- *	Private routines/data
- *
- *	physical and logical are equivalent until we support CPU hotplug.
- */
-#define cpu_number_map(cpu)	(cpu)
-#define cpu_logical_map(cpu)	(cpu)
-
-extern void smp_send_reschedule(int cpu);
-extern void smp_send_all_nop(void);
-
-extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
-
-#endif /* !ASSEMBLY */
-
-/*
- *	This magic constant controls our willingness to transfer
- *      a process across CPUs. Such a transfer incurs cache and tlb
- *      misses. The current value is inherited from i386. Still needs
- *      to be tuned for parisc.
- */
- 
-#define PROC_CHANGE_PENALTY	15		/* Schedule penalty */
-
-extern unsigned long cpu_present_mask;
-
-#define raw_smp_processor_id()	(current_thread_info()->cpu)
-
-#else /* CONFIG_SMP */
-
-static inline void smp_send_all_nop(void) { return; }
-
-#endif
-
-#define NO_PROC_ID		0xFF		/* No processor magic marker */
-#define ANY_PROC_ID		0xFF		/* Any processor magic marker */
-static inline int __cpu_disable (void) {
-  return 0;
-}
-static inline void __cpu_die (unsigned int cpu) {
-  while(1)
-    ;
-}
-extern int __cpu_up (unsigned int cpu);
-
-#endif /*  __ASM_SMP_H */
diff --git a/include/asm-parisc/socket.h b/include/asm-parisc/socket.h
deleted file mode 100644
index fba402c95ac2..000000000000
--- a/include/asm-parisc/socket.h
+++ /dev/null
@@ -1,62 +0,0 @@
-#ifndef _ASM_SOCKET_H
-#define _ASM_SOCKET_H
-
-#include <asm/sockios.h>
-
-/* For setsockopt(2) */
-#define SOL_SOCKET	0xffff
-
-#define SO_DEBUG	0x0001
-#define SO_REUSEADDR	0x0004
-#define SO_KEEPALIVE	0x0008
-#define SO_DONTROUTE	0x0010
-#define SO_BROADCAST	0x0020
-#define SO_LINGER	0x0080
-#define SO_OOBINLINE	0x0100
-/* To add :#define SO_REUSEPORT 0x0200 */
-#define SO_SNDBUF	0x1001
-#define SO_RCVBUF	0x1002
-#define SO_SNDBUFFORCE	0x100a
-#define SO_RCVBUFFORCE	0x100b
-#define SO_SNDLOWAT	0x1003
-#define SO_RCVLOWAT	0x1004
-#define SO_SNDTIMEO	0x1005
-#define SO_RCVTIMEO	0x1006
-#define SO_ERROR	0x1007
-#define SO_TYPE		0x1008
-#define SO_PEERNAME	0x2000
-
-#define SO_NO_CHECK	0x400b
-#define SO_PRIORITY	0x400c
-#define SO_BSDCOMPAT	0x400e
-#define SO_PASSCRED	0x4010
-#define SO_PEERCRED	0x4011
-#define SO_TIMESTAMP	0x4012
-#define SCM_TIMESTAMP	SO_TIMESTAMP
-#define SO_TIMESTAMPNS	0x4013
-#define SCM_TIMESTAMPNS	SO_TIMESTAMPNS
-
-/* Security levels - as per NRL IPv6 - don't actually do anything */
-#define SO_SECURITY_AUTHENTICATION		0x4016
-#define SO_SECURITY_ENCRYPTION_TRANSPORT	0x4017
-#define SO_SECURITY_ENCRYPTION_NETWORK		0x4018
-
-#define SO_BINDTODEVICE	0x4019
-
-/* Socket filtering */
-#define SO_ATTACH_FILTER        0x401a
-#define SO_DETACH_FILTER        0x401b
-
-#define SO_ACCEPTCONN		0x401c
-
-#define SO_PEERSEC		0x401d
-#define SO_PASSSEC		0x401e
-
-#define SO_MARK			0x401f
-
-/* O_NONBLOCK clashes with the bits used for socket types.  Therefore we
- * have to define SOCK_NONBLOCK to a different value here.
- */
-#define SOCK_NONBLOCK   0x40000000
-
-#endif /* _ASM_SOCKET_H */
diff --git a/include/asm-parisc/sockios.h b/include/asm-parisc/sockios.h
deleted file mode 100644
index dabfbc7483f6..000000000000
--- a/include/asm-parisc/sockios.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ARCH_PARISC_SOCKIOS__
-#define __ARCH_PARISC_SOCKIOS__
-
-/* Socket-level I/O control calls. */
-#define FIOSETOWN 	0x8901
-#define SIOCSPGRP	0x8902
-#define FIOGETOWN	0x8903
-#define SIOCGPGRP	0x8904
-#define SIOCATMARK	0x8905
-#define SIOCGSTAMP	0x8906		/* Get stamp (timeval) */
-#define SIOCGSTAMPNS	0x8907		/* Get stamp (timespec) */
-
-#endif
diff --git a/include/asm-parisc/spinlock.h b/include/asm-parisc/spinlock.h
deleted file mode 100644
index f3d2090a18dc..000000000000
--- a/include/asm-parisc/spinlock.h
+++ /dev/null
@@ -1,194 +0,0 @@
-#ifndef __ASM_SPINLOCK_H
-#define __ASM_SPINLOCK_H
-
-#include <asm/system.h>
-#include <asm/processor.h>
-#include <asm/spinlock_types.h>
-
-static inline int __raw_spin_is_locked(raw_spinlock_t *x)
-{
-	volatile unsigned int *a = __ldcw_align(x);
-	return *a == 0;
-}
-
-#define __raw_spin_lock(lock) __raw_spin_lock_flags(lock, 0)
-#define __raw_spin_unlock_wait(x) \
-		do { cpu_relax(); } while (__raw_spin_is_locked(x))
-
-static inline void __raw_spin_lock_flags(raw_spinlock_t *x,
-					 unsigned long flags)
-{
-	volatile unsigned int *a;
-
-	mb();
-	a = __ldcw_align(x);
-	while (__ldcw(a) == 0)
-		while (*a == 0)
-			if (flags & PSW_SM_I) {
-				local_irq_enable();
-				cpu_relax();
-				local_irq_disable();
-			} else
-				cpu_relax();
-	mb();
-}
-
-static inline void __raw_spin_unlock(raw_spinlock_t *x)
-{
-	volatile unsigned int *a;
-	mb();
-	a = __ldcw_align(x);
-	*a = 1;
-	mb();
-}
-
-static inline int __raw_spin_trylock(raw_spinlock_t *x)
-{
-	volatile unsigned int *a;
-	int ret;
-
-	mb();
-	a = __ldcw_align(x);
-        ret = __ldcw(a) != 0;
-	mb();
-
-	return ret;
-}
-
-/*
- * Read-write spinlocks, allowing multiple readers but only one writer.
- * Linux rwlocks are unfair to writers; they can be starved for an indefinite
- * time by readers.  With care, they can also be taken in interrupt context.
- *
- * In the PA-RISC implementation, we have a spinlock and a counter.
- * Readers use the lock to serialise their access to the counter (which
- * records how many readers currently hold the lock).
- * Writers hold the spinlock, preventing any readers or other writers from
- * grabbing the rwlock.
- */
-
-/* Note that we have to ensure interrupts are disabled in case we're
- * interrupted by some other code that wants to grab the same read lock */
-static  __inline__ void __raw_read_lock(raw_rwlock_t *rw)
-{
-	unsigned long flags;
-	local_irq_save(flags);
-	__raw_spin_lock_flags(&rw->lock, flags);
-	rw->counter++;
-	__raw_spin_unlock(&rw->lock);
-	local_irq_restore(flags);
-}
-
-/* Note that we have to ensure interrupts are disabled in case we're
- * interrupted by some other code that wants to grab the same read lock */
-static  __inline__ void __raw_read_unlock(raw_rwlock_t *rw)
-{
-	unsigned long flags;
-	local_irq_save(flags);
-	__raw_spin_lock_flags(&rw->lock, flags);
-	rw->counter--;
-	__raw_spin_unlock(&rw->lock);
-	local_irq_restore(flags);
-}
-
-/* Note that we have to ensure interrupts are disabled in case we're
- * interrupted by some other code that wants to grab the same read lock */
-static __inline__ int __raw_read_trylock(raw_rwlock_t *rw)
-{
-	unsigned long flags;
- retry:
-	local_irq_save(flags);
-	if (__raw_spin_trylock(&rw->lock)) {
-		rw->counter++;
-		__raw_spin_unlock(&rw->lock);
-		local_irq_restore(flags);
-		return 1;
-	}
-
-	local_irq_restore(flags);
-	/* If write-locked, we fail to acquire the lock */
-	if (rw->counter < 0)
-		return 0;
-
-	/* Wait until we have a realistic chance at the lock */
-	while (__raw_spin_is_locked(&rw->lock) && rw->counter >= 0)
-		cpu_relax();
-
-	goto retry;
-}
-
-/* Note that we have to ensure interrupts are disabled in case we're
- * interrupted by some other code that wants to read_trylock() this lock */
-static __inline__ void __raw_write_lock(raw_rwlock_t *rw)
-{
-	unsigned long flags;
-retry:
-	local_irq_save(flags);
-	__raw_spin_lock_flags(&rw->lock, flags);
-
-	if (rw->counter != 0) {
-		__raw_spin_unlock(&rw->lock);
-		local_irq_restore(flags);
-
-		while (rw->counter != 0)
-			cpu_relax();
-
-		goto retry;
-	}
-
-	rw->counter = -1; /* mark as write-locked */
-	mb();
-	local_irq_restore(flags);
-}
-
-static __inline__ void __raw_write_unlock(raw_rwlock_t *rw)
-{
-	rw->counter = 0;
-	__raw_spin_unlock(&rw->lock);
-}
-
-/* Note that we have to ensure interrupts are disabled in case we're
- * interrupted by some other code that wants to read_trylock() this lock */
-static __inline__ int __raw_write_trylock(raw_rwlock_t *rw)
-{
-	unsigned long flags;
-	int result = 0;
-
-	local_irq_save(flags);
-	if (__raw_spin_trylock(&rw->lock)) {
-		if (rw->counter == 0) {
-			rw->counter = -1;
-			result = 1;
-		} else {
-			/* Read-locked.  Oh well. */
-			__raw_spin_unlock(&rw->lock);
-		}
-	}
-	local_irq_restore(flags);
-
-	return result;
-}
-
-/*
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static __inline__ int __raw_read_can_lock(raw_rwlock_t *rw)
-{
-	return rw->counter >= 0;
-}
-
-/*
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static __inline__ int __raw_write_can_lock(raw_rwlock_t *rw)
-{
-	return !rw->counter;
-}
-
-#define _raw_spin_relax(lock)	cpu_relax()
-#define _raw_read_relax(lock)	cpu_relax()
-#define _raw_write_relax(lock)	cpu_relax()
-
-#endif /* __ASM_SPINLOCK_H */
diff --git a/include/asm-parisc/spinlock_types.h b/include/asm-parisc/spinlock_types.h
deleted file mode 100644
index 3f72f47cf4b2..000000000000
--- a/include/asm-parisc/spinlock_types.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef __ASM_SPINLOCK_TYPES_H
-#define __ASM_SPINLOCK_TYPES_H
-
-typedef struct {
-#ifdef CONFIG_PA20
-	volatile unsigned int slock;
-# define __RAW_SPIN_LOCK_UNLOCKED { 1 }
-#else
-	volatile unsigned int lock[4];
-# define __RAW_SPIN_LOCK_UNLOCKED	{ { 1, 1, 1, 1 } }
-#endif
-} raw_spinlock_t;
-
-typedef struct {
-	raw_spinlock_t lock;
-	volatile int counter;
-} raw_rwlock_t;
-
-#define __RAW_RW_LOCK_UNLOCKED		{ __RAW_SPIN_LOCK_UNLOCKED, 0 }
-
-#endif
diff --git a/include/asm-parisc/stat.h b/include/asm-parisc/stat.h
deleted file mode 100644
index 9d5fbbc5c31f..000000000000
--- a/include/asm-parisc/stat.h
+++ /dev/null
@@ -1,100 +0,0 @@
-#ifndef _PARISC_STAT_H
-#define _PARISC_STAT_H
-
-#include <linux/types.h>
-
-struct stat {
-	unsigned int	st_dev;		/* dev_t is 32 bits on parisc */
-	ino_t		st_ino;		/* 32 bits */
-	mode_t		st_mode;	/* 16 bits */
-	nlink_t		st_nlink;	/* 16 bits */
-	unsigned short	st_reserved1;	/* old st_uid */
-	unsigned short	st_reserved2;	/* old st_gid */
-	unsigned int	st_rdev;
-	off_t		st_size;
-	time_t		st_atime;
-	unsigned int	st_atime_nsec;
-	time_t		st_mtime;
-	unsigned int	st_mtime_nsec;
-	time_t		st_ctime;
-	unsigned int	st_ctime_nsec;
-	int		st_blksize;
-	int		st_blocks;
-	unsigned int	__unused1;	/* ACL stuff */
-	unsigned int	__unused2;	/* network */
-	ino_t		__unused3;	/* network */
-	unsigned int	__unused4;	/* cnodes */
-	unsigned short	__unused5;	/* netsite */
-	short		st_fstype;
-	unsigned int	st_realdev;
-	unsigned short	st_basemode;
-	unsigned short	st_spareshort;
-	uid_t		st_uid;
-	gid_t		st_gid;
-	unsigned int	st_spare4[3];
-};
-
-#define STAT_HAVE_NSEC
-
-typedef __kernel_off64_t	off64_t;
-
-struct hpux_stat64 {
-	unsigned int	st_dev;		/* dev_t is 32 bits on parisc */
-	ino_t           st_ino;         /* 32 bits */
-	mode_t		st_mode;	/* 16 bits */
-	nlink_t		st_nlink;	/* 16 bits */
-	unsigned short	st_reserved1;	/* old st_uid */
-	unsigned short	st_reserved2;	/* old st_gid */
-	unsigned int	st_rdev;
-	off64_t		st_size;
-	time_t		st_atime;
-	unsigned int	st_spare1;
-	time_t		st_mtime;
-	unsigned int	st_spare2;
-	time_t		st_ctime;
-	unsigned int	st_spare3;
-	int		st_blksize;
-	__u64		st_blocks;
-	unsigned int	__unused1;	/* ACL stuff */
-	unsigned int	__unused2;	/* network */
-	ino_t           __unused3;      /* network */
-	unsigned int	__unused4;	/* cnodes */
-	unsigned short	__unused5;	/* netsite */
-	short		st_fstype;
-	unsigned int	st_realdev;
-	unsigned short	st_basemode;
-	unsigned short	st_spareshort;
-	uid_t		st_uid;
-	gid_t		st_gid;
-	unsigned int	st_spare4[3];
-};
-
-/* This is the struct that 32-bit userspace applications are expecting.
- * How 64-bit apps are going to be compiled, I have no idea.  But at least
- * this way, we don't have a wrapper in the kernel.
- */
-struct stat64 {
-	unsigned long long	st_dev;
-	unsigned int		__pad1;
-
-	unsigned int		__st_ino;	/* Not actually filled in */
-	unsigned int		st_mode;
-	unsigned int		st_nlink;
-	unsigned int		st_uid;
-	unsigned int		st_gid;
-	unsigned long long	st_rdev;
-	unsigned int		__pad2;
-	signed long long	st_size;
-	signed int		st_blksize;
-
-	signed long long	st_blocks;
-	signed int		st_atime;
-	unsigned int		st_atime_nsec;
-	signed int		st_mtime;
-	unsigned int		st_mtime_nsec;
-	signed int		st_ctime;
-	unsigned int		st_ctime_nsec;
-	unsigned long long	st_ino;
-};
-
-#endif
diff --git a/include/asm-parisc/statfs.h b/include/asm-parisc/statfs.h
deleted file mode 100644
index 1d2b8130b23d..000000000000
--- a/include/asm-parisc/statfs.h
+++ /dev/null
@@ -1,58 +0,0 @@
-#ifndef _PARISC_STATFS_H
-#define _PARISC_STATFS_H
-
-#ifndef __KERNEL_STRICT_NAMES
-
-#include <linux/types.h>
-
-typedef __kernel_fsid_t	fsid_t;
-
-#endif
-
-/*
- * It appears that PARISC could be 64 _or_ 32 bit.
- * 64-bit fields must be explicitly 64-bit in statfs64.
- */
-struct statfs {
-	long f_type;
-	long f_bsize;
-	long f_blocks;
-	long f_bfree;
-	long f_bavail;
-	long f_files;
-	long f_ffree;
-	__kernel_fsid_t f_fsid;
-	long f_namelen;
-	long f_frsize;
-	long f_spare[5];
-};
-
-struct statfs64 {
-	long f_type;
-	long f_bsize;
-	__u64 f_blocks;
-	__u64 f_bfree;
-	__u64 f_bavail;
-	__u64 f_files;
-	__u64 f_ffree;
-	__kernel_fsid_t f_fsid;
-	long f_namelen;
-	long f_frsize;
-	long f_spare[5];
-};
-
-struct compat_statfs64 {
-	__u32 f_type;
-	__u32 f_bsize;
-	__u64 f_blocks;
-	__u64 f_bfree;
-	__u64 f_bavail;
-	__u64 f_files;
-	__u64 f_ffree;
-	__kernel_fsid_t f_fsid;
-	__u32 f_namelen;
-	__u32 f_frsize;
-	__u32 f_spare[5];
-};
-
-#endif
diff --git a/include/asm-parisc/string.h b/include/asm-parisc/string.h
deleted file mode 100644
index eda01be65e35..000000000000
--- a/include/asm-parisc/string.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _PA_STRING_H_
-#define _PA_STRING_H_
-
-#define __HAVE_ARCH_MEMSET
-extern void * memset(void *, int, size_t);
-
-#define __HAVE_ARCH_MEMCPY
-void * memcpy(void * dest,const void *src,size_t count);
-
-#endif
diff --git a/include/asm-parisc/superio.h b/include/asm-parisc/superio.h
deleted file mode 100644
index 6598acb4d46d..000000000000
--- a/include/asm-parisc/superio.h
+++ /dev/null
@@ -1,85 +0,0 @@
-#ifndef _PARISC_SUPERIO_H
-#define _PARISC_SUPERIO_H
-
-#define IC_PIC1    0x20		/* PCI I/O address of master 8259 */
-#define IC_PIC2    0xA0		/* PCI I/O address of slave */
-
-/* Config Space Offsets to configuration and base address registers */
-#define SIO_CR     0x5A		/* Configuration Register */
-#define SIO_ACPIBAR 0x88	/* ACPI BAR */
-#define SIO_FDCBAR 0x90		/* Floppy Disk Controller BAR */
-#define SIO_SP1BAR 0x94		/* Serial 1 BAR */
-#define SIO_SP2BAR 0x98		/* Serial 2 BAR */
-#define SIO_PPBAR  0x9C		/* Parallel BAR */
-
-#define TRIGGER_1  0x67		/* Edge/level trigger register 1 */
-#define TRIGGER_2  0x68		/* Edge/level trigger register 2 */
-
-/* Interrupt Routing Control registers */
-#define CFG_IR_SER    0x69	/* Serial 1 [0:3] and Serial 2 [4:7] */
-#define CFG_IR_PFD    0x6a	/* Parallel [0:3] and Floppy [4:7] */
-#define CFG_IR_IDE    0x6b	/* IDE1     [0:3] and IDE2 [4:7] */
-#define CFG_IR_INTAB  0x6c	/* PCI INTA [0:3] and INT B [4:7] */
-#define CFG_IR_INTCD  0x6d	/* PCI INTC [0:3] and INT D [4:7] */
-#define CFG_IR_PS2    0x6e	/* PS/2 KBINT [0:3] and Mouse [4:7] */
-#define CFG_IR_FXBUS  0x6f	/* FXIRQ[0] [0:3] and FXIRQ[1] [4:7] */
-#define CFG_IR_USB    0x70	/* FXIRQ[2] [0:3] and USB [4:7] */
-#define CFG_IR_ACPI   0x71	/* ACPI SCI [0:3] and reserved [4:7] */
-
-#define CFG_IR_LOW     CFG_IR_SER	/* Lowest interrupt routing reg */
-#define CFG_IR_HIGH    CFG_IR_ACPI	/* Highest interrupt routing reg */
-
-/* 8259 operational control words */
-#define OCW2_EOI   0x20		/* Non-specific EOI */
-#define OCW2_SEOI  0x60		/* Specific EOI */
-#define OCW3_IIR   0x0A		/* Read request register */
-#define OCW3_ISR   0x0B		/* Read service register */
-#define OCW3_POLL  0x0C		/* Poll the PIC for an interrupt vector */
-
-/* Interrupt lines. Only PIC1 is used */
-#define USB_IRQ    1		/* USB */
-#define SP1_IRQ    3		/* Serial port 1 */
-#define SP2_IRQ    4		/* Serial port 2 */
-#define PAR_IRQ    5		/* Parallel port */
-#define FDC_IRQ    6		/* Floppy controller */
-#define IDE_IRQ    7		/* IDE (pri+sec) */
-
-/* ACPI registers */
-#define USB_REG_CR	0x1f	/* USB Regulator Control Register */
-
-#define SUPERIO_NIRQS   8
-
-struct superio_device {
-	u32 fdc_base;
-	u32 sp1_base;
-	u32 sp2_base;
-	u32 pp_base;
-	u32 acpi_base;
-	int suckyio_irq_enabled;
-	struct pci_dev *lio_pdev;       /* pci device for legacy IO (fn 1) */
-	struct pci_dev *usb_pdev;       /* pci device for USB (fn 2) */
-};
-
-/*
- * Does NS make a 87415 based plug in PCI card? If so, because of this
- * macro we currently don't support it being plugged into a machine
- * that contains a SuperIO chip AND has CONFIG_SUPERIO enabled.
- *
- * This could be fixed by checking to see if function 1 exists, and
- * if it is SuperIO Legacy IO; but really now, is this combination
- * going to EVER happen?
- */
-
-#define SUPERIO_IDE_FN 0 /* Function number of IDE controller */
-#define SUPERIO_LIO_FN 1 /* Function number of Legacy IO controller */
-#define SUPERIO_USB_FN 2 /* Function number of USB controller */
-
-#define is_superio_device(x) \
-	(((x)->vendor == PCI_VENDOR_ID_NS) && \
-	(  ((x)->device == PCI_DEVICE_ID_NS_87415) \
-	|| ((x)->device == PCI_DEVICE_ID_NS_87560_LIO) \
-	|| ((x)->device == PCI_DEVICE_ID_NS_87560_USB) ) )
-
-extern int superio_fixup_irq(struct pci_dev *pcidev); /* called by iosapic */
-
-#endif /* _PARISC_SUPERIO_H */
diff --git a/include/asm-parisc/system.h b/include/asm-parisc/system.h
deleted file mode 100644
index ee80c920b464..000000000000
--- a/include/asm-parisc/system.h
+++ /dev/null
@@ -1,182 +0,0 @@
-#ifndef __PARISC_SYSTEM_H
-#define __PARISC_SYSTEM_H
-
-#include <asm/psw.h>
-
-/* The program status word as bitfields.  */
-struct pa_psw {
-	unsigned int y:1;
-	unsigned int z:1;
-	unsigned int rv:2;
-	unsigned int w:1;
-	unsigned int e:1;
-	unsigned int s:1;
-	unsigned int t:1;
-
-	unsigned int h:1;
-	unsigned int l:1;
-	unsigned int n:1;
-	unsigned int x:1;
-	unsigned int b:1;
-	unsigned int c:1;
-	unsigned int v:1;
-	unsigned int m:1;
-
-	unsigned int cb:8;
-
-	unsigned int o:1;
-	unsigned int g:1;
-	unsigned int f:1;
-	unsigned int r:1;
-	unsigned int q:1;
-	unsigned int p:1;
-	unsigned int d:1;
-	unsigned int i:1;
-};
-
-#ifdef CONFIG_64BIT
-#define pa_psw(task) ((struct pa_psw *) ((char *) (task) + TASK_PT_PSW + 4))
-#else
-#define pa_psw(task) ((struct pa_psw *) ((char *) (task) + TASK_PT_PSW))
-#endif
-
-struct task_struct;
-
-extern struct task_struct *_switch_to(struct task_struct *, struct task_struct *);
-
-#define switch_to(prev, next, last) do {			\
-	(last) = _switch_to(prev, next);			\
-} while(0)
-
-/* interrupt control */
-#define local_save_flags(x)	__asm__ __volatile__("ssm 0, %0" : "=r" (x) : : "memory")
-#define local_irq_disable()	__asm__ __volatile__("rsm %0,%%r0\n" : : "i" (PSW_I) : "memory" )
-#define local_irq_enable()	__asm__ __volatile__("ssm %0,%%r0\n" : : "i" (PSW_I) : "memory" )
-
-#define local_irq_save(x) \
-	__asm__ __volatile__("rsm %1,%0" : "=r" (x) :"i" (PSW_I) : "memory" )
-#define local_irq_restore(x) \
-	__asm__ __volatile__("mtsm %0" : : "r" (x) : "memory" )
-
-#define irqs_disabled()			\
-({					\
-	unsigned long flags;		\
-	local_save_flags(flags);	\
-	(flags & PSW_I) == 0;		\
-})
-
-#define mfctl(reg)	({		\
-	unsigned long cr;		\
-	__asm__ __volatile__(		\
-		"mfctl " #reg ",%0" :	\
-		 "=r" (cr)		\
-	);				\
-	cr;				\
-})
-
-#define mtctl(gr, cr) \
-	__asm__ __volatile__("mtctl %0,%1" \
-		: /* no outputs */ \
-		: "r" (gr), "i" (cr) : "memory")
-
-/* these are here to de-mystefy the calling code, and to provide hooks */
-/* which I needed for debugging EIEM problems -PB */
-#define get_eiem() mfctl(15)
-static inline void set_eiem(unsigned long val)
-{
-	mtctl(val, 15);
-}
-
-#define mfsp(reg)	({		\
-	unsigned long cr;		\
-	__asm__ __volatile__(		\
-		"mfsp " #reg ",%0" :	\
-		 "=r" (cr)		\
-	);				\
-	cr;				\
-})
-
-#define mtsp(gr, cr) \
-	__asm__ __volatile__("mtsp %0,%1" \
-		: /* no outputs */ \
-		: "r" (gr), "i" (cr) : "memory")
-
-
-/*
-** This is simply the barrier() macro from linux/kernel.h but when serial.c
-** uses tqueue.h uses smp_mb() defined using barrier(), linux/kernel.h
-** hasn't yet been included yet so it fails, thus repeating the macro here.
-**
-** PA-RISC architecture allows for weakly ordered memory accesses although
-** none of the processors use it. There is a strong ordered bit that is
-** set in the O-bit of the page directory entry. Operating systems that
-** can not tolerate out of order accesses should set this bit when mapping
-** pages. The O-bit of the PSW should also be set to 1 (I don't believe any
-** of the processor implemented the PSW O-bit). The PCX-W ERS states that
-** the TLB O-bit is not implemented so the page directory does not need to
-** have the O-bit set when mapping pages (section 3.1). This section also
-** states that the PSW Y, Z, G, and O bits are not implemented.
-** So it looks like nothing needs to be done for parisc-linux (yet).
-** (thanks to chada for the above comment -ggg)
-**
-** The __asm__ op below simple prevents gcc/ld from reordering
-** instructions across the mb() "call".
-*/
-#define mb()		__asm__ __volatile__("":::"memory")	/* barrier() */
-#define rmb()		mb()
-#define wmb()		mb()
-#define smp_mb()	mb()
-#define smp_rmb()	mb()
-#define smp_wmb()	mb()
-#define smp_read_barrier_depends()	do { } while(0)
-#define read_barrier_depends()		do { } while(0)
-
-#define set_mb(var, value)		do { var = value; mb(); } while (0)
-
-#ifndef CONFIG_PA20
-/* Because kmalloc only guarantees 8-byte alignment for kmalloc'd data,
-   and GCC only guarantees 8-byte alignment for stack locals, we can't
-   be assured of 16-byte alignment for atomic lock data even if we
-   specify "__attribute ((aligned(16)))" in the type declaration.  So,
-   we use a struct containing an array of four ints for the atomic lock
-   type and dynamically select the 16-byte aligned int from the array
-   for the semaphore.  */
-
-#define __PA_LDCW_ALIGNMENT	16
-#define __ldcw_align(a) ({					\
-	unsigned long __ret = (unsigned long) &(a)->lock[0];	\
-	__ret = (__ret + __PA_LDCW_ALIGNMENT - 1)		\
-		& ~(__PA_LDCW_ALIGNMENT - 1);			\
-	(volatile unsigned int *) __ret;			\
-})
-#define __LDCW	"ldcw"
-
-#else /*CONFIG_PA20*/
-/* From: "Jim Hull" <jim.hull of hp.com>
-   I've attached a summary of the change, but basically, for PA 2.0, as
-   long as the ",CO" (coherent operation) completer is specified, then the
-   16-byte alignment requirement for ldcw and ldcd is relaxed, and instead
-   they only require "natural" alignment (4-byte for ldcw, 8-byte for
-   ldcd). */
-
-#define __PA_LDCW_ALIGNMENT	4
-#define __ldcw_align(a) ((volatile unsigned int *)a)
-#define __LDCW	"ldcw,co"
-
-#endif /*!CONFIG_PA20*/
-
-/* LDCW, the only atomic read-write operation PA-RISC has. *sigh*.  */
-#define __ldcw(a) ({						\
-	unsigned __ret;						\
-	__asm__ __volatile__(__LDCW " 0(%1),%0"			\
-		: "=r" (__ret) : "r" (a));			\
-	__ret;							\
-})
-
-#ifdef CONFIG_SMP
-# define __lock_aligned __attribute__((__section__(".data.lock_aligned")))
-#endif
-
-#define arch_align_stack(x) (x)
-
-#endif
diff --git a/include/asm-parisc/termbits.h b/include/asm-parisc/termbits.h
deleted file mode 100644
index d8bbc73b16b7..000000000000
--- a/include/asm-parisc/termbits.h
+++ /dev/null
@@ -1,200 +0,0 @@
-#ifndef __ARCH_PARISC_TERMBITS_H__
-#define __ARCH_PARISC_TERMBITS_H__
-
-#include <linux/posix_types.h>
-
-typedef unsigned char	cc_t;
-typedef unsigned int	speed_t;
-typedef unsigned int	tcflag_t;
-
-#define NCCS 19
-struct termios {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-};
-
-struct termios2 {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-	speed_t c_ispeed;		/* input speed */
-	speed_t c_ospeed;		/* output speed */
-};
-
-struct ktermios {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-	speed_t c_ispeed;		/* input speed */
-	speed_t c_ospeed;		/* output speed */
-};
-
-/* c_cc characters */
-#define VINTR 0
-#define VQUIT 1
-#define VERASE 2
-#define VKILL 3
-#define VEOF 4
-#define VTIME 5
-#define VMIN 6
-#define VSWTC 7
-#define VSTART 8
-#define VSTOP 9
-#define VSUSP 10
-#define VEOL 11
-#define VREPRINT 12
-#define VDISCARD 13
-#define VWERASE 14
-#define VLNEXT 15
-#define VEOL2 16
-
-
-/* c_iflag bits */
-#define IGNBRK	0000001
-#define BRKINT	0000002
-#define IGNPAR	0000004
-#define PARMRK	0000010
-#define INPCK	0000020
-#define ISTRIP	0000040
-#define INLCR	0000100
-#define IGNCR	0000200
-#define ICRNL	0000400
-#define IUCLC	0001000
-#define IXON	0002000
-#define IXANY	0004000
-#define IXOFF	0010000
-#define IMAXBEL	0040000
-#define IUTF8	0100000
-
-/* c_oflag bits */
-#define OPOST	0000001
-#define OLCUC	0000002
-#define ONLCR	0000004
-#define OCRNL	0000010
-#define ONOCR	0000020
-#define ONLRET	0000040
-#define OFILL	0000100
-#define OFDEL	0000200
-#define NLDLY	0000400
-#define   NL0	0000000
-#define   NL1	0000400
-#define CRDLY	0003000
-#define   CR0	0000000
-#define   CR1	0001000
-#define   CR2	0002000
-#define   CR3	0003000
-#define TABDLY	0014000
-#define   TAB0	0000000
-#define   TAB1	0004000
-#define   TAB2	0010000
-#define   TAB3	0014000
-#define   XTABS	0014000
-#define BSDLY	0020000
-#define   BS0	0000000
-#define   BS1	0020000
-#define VTDLY	0040000
-#define   VT0	0000000
-#define   VT1	0040000
-#define FFDLY	0100000
-#define   FF0	0000000
-#define   FF1	0100000
-
-/* c_cflag bit meaning */
-#define CBAUD   0010017
-#define  B0     0000000         /* hang up */
-#define  B50    0000001
-#define  B75    0000002
-#define  B110   0000003
-#define  B134   0000004
-#define  B150   0000005
-#define  B200   0000006
-#define  B300   0000007
-#define  B600   0000010
-#define  B1200  0000011
-#define  B1800  0000012
-#define  B2400  0000013
-#define  B4800  0000014
-#define  B9600  0000015
-#define  B19200 0000016
-#define  B38400 0000017
-#define EXTA B19200
-#define EXTB B38400
-#define CSIZE   0000060
-#define   CS5   0000000
-#define   CS6   0000020
-#define   CS7   0000040
-#define   CS8   0000060
-#define CSTOPB  0000100
-#define CREAD   0000200
-#define PARENB  0000400
-#define PARODD  0001000
-#define HUPCL   0002000
-#define CLOCAL  0004000
-#define CBAUDEX 0010000
-#define    BOTHER 0010000
-#define    B57600 0010001
-#define   B115200 0010002
-#define   B230400 0010003
-#define   B460800 0010004
-#define   B500000 0010005
-#define   B576000 0010006
-#define   B921600 0010007
-#define  B1000000 0010010
-#define  B1152000 0010011
-#define  B1500000 0010012
-#define  B2000000 0010013
-#define  B2500000 0010014
-#define  B3000000 0010015
-#define  B3500000 0010016
-#define  B4000000 0010017
-#define CIBAUD    002003600000		/* input baud rate */
-#define CMSPAR    010000000000          /* mark or space (stick) parity */
-#define CRTSCTS   020000000000          /* flow control */
-
-#define IBSHIFT	16		/* Shift from CBAUD to CIBAUD */
-
-
-/* c_lflag bits */
-#define ISIG    0000001
-#define ICANON  0000002
-#define XCASE   0000004
-#define ECHO    0000010
-#define ECHOE   0000020
-#define ECHOK   0000040
-#define ECHONL  0000100
-#define NOFLSH  0000200
-#define TOSTOP  0000400
-#define ECHOCTL 0001000
-#define ECHOPRT 0002000
-#define ECHOKE  0004000
-#define FLUSHO  0010000
-#define PENDIN  0040000
-#define IEXTEN  0100000
-
-/* tcflow() and TCXONC use these */
-#define	TCOOFF		0
-#define	TCOON		1
-#define	TCIOFF		2
-#define	TCION		3
-
-/* tcflush() and TCFLSH use these */
-#define	TCIFLUSH	0
-#define	TCOFLUSH	1
-#define	TCIOFLUSH	2
-
-/* tcsetattr uses these */
-#define	TCSANOW		0
-#define	TCSADRAIN	1
-#define	TCSAFLUSH	2
-
-#endif
diff --git a/include/asm-parisc/termios.h b/include/asm-parisc/termios.h
deleted file mode 100644
index a2a57a4548af..000000000000
--- a/include/asm-parisc/termios.h
+++ /dev/null
@@ -1,90 +0,0 @@
-#ifndef _PARISC_TERMIOS_H
-#define _PARISC_TERMIOS_H
-
-#include <asm/termbits.h>
-#include <asm/ioctls.h>
-
-struct winsize {
-	unsigned short ws_row;
-	unsigned short ws_col;
-	unsigned short ws_xpixel;
-	unsigned short ws_ypixel;
-};
-
-#define NCC 8
-struct termio {
-	unsigned short c_iflag;		/* input mode flags */
-	unsigned short c_oflag;		/* output mode flags */
-	unsigned short c_cflag;		/* control mode flags */
-	unsigned short c_lflag;		/* local mode flags */
-	unsigned char c_line;		/* line discipline */
-	unsigned char c_cc[NCC];	/* control characters */
-};
-
-/* modem lines */
-#define TIOCM_LE	0x001
-#define TIOCM_DTR	0x002
-#define TIOCM_RTS	0x004
-#define TIOCM_ST	0x008
-#define TIOCM_SR	0x010
-#define TIOCM_CTS	0x020
-#define TIOCM_CAR	0x040
-#define TIOCM_RNG	0x080
-#define TIOCM_DSR	0x100
-#define TIOCM_CD	TIOCM_CAR
-#define TIOCM_RI	TIOCM_RNG
-#define TIOCM_OUT1	0x2000
-#define TIOCM_OUT2	0x4000
-#define TIOCM_LOOP	0x8000
-
-/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
-
-#ifdef __KERNEL__
-
-/*	intr=^C		quit=^\		erase=del	kill=^U
-	eof=^D		vtime=\0	vmin=\1		sxtc=\0
-	start=^Q	stop=^S		susp=^Z		eol=\0
-	reprint=^R	discard=^U	werase=^W	lnext=^V
-	eol2=\0
-*/
-#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
-
-/*
- * Translate a "termio" structure into a "termios". Ugh.
- */
-#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
-	unsigned short __tmp; \
-	get_user(__tmp,&(termio)->x); \
-	*(unsigned short *) &(termios)->x = __tmp; \
-}
-
-#define user_termio_to_kernel_termios(termios, termio) \
-({ \
-	SET_LOW_TERMIOS_BITS(termios, termio, c_iflag); \
-	SET_LOW_TERMIOS_BITS(termios, termio, c_oflag); \
-	SET_LOW_TERMIOS_BITS(termios, termio, c_cflag); \
-	SET_LOW_TERMIOS_BITS(termios, termio, c_lflag); \
-	copy_from_user((termios)->c_cc, (termio)->c_cc, NCC); \
-})
-
-/*
- * Translate a "termios" structure into a "termio". Ugh.
- */
-#define kernel_termios_to_user_termio(termio, termios) \
-({ \
-	put_user((termios)->c_iflag, &(termio)->c_iflag); \
-	put_user((termios)->c_oflag, &(termio)->c_oflag); \
-	put_user((termios)->c_cflag, &(termio)->c_cflag); \
-	put_user((termios)->c_lflag, &(termio)->c_lflag); \
-	put_user((termios)->c_line,  &(termio)->c_line); \
-	copy_to_user((termio)->c_cc, (termios)->c_cc, NCC); \
-})
-
-#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios2))
-#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios2))
-#define user_termios_to_kernel_termios_1(k, u) copy_from_user(k, u, sizeof(struct termios))
-#define kernel_termios_to_user_termios_1(u, k) copy_to_user(u, k, sizeof(struct termios))
-
-#endif	/* __KERNEL__ */
-
-#endif	/* _PARISC_TERMIOS_H */
diff --git a/include/asm-parisc/thread_info.h b/include/asm-parisc/thread_info.h
deleted file mode 100644
index 9f812741c355..000000000000
--- a/include/asm-parisc/thread_info.h
+++ /dev/null
@@ -1,74 +0,0 @@
-#ifndef _ASM_PARISC_THREAD_INFO_H
-#define _ASM_PARISC_THREAD_INFO_H
-
-#ifdef __KERNEL__
-
-#ifndef __ASSEMBLY__
-#include <asm/processor.h>
-
-struct thread_info {
-	struct task_struct *task;	/* main task structure */
-	struct exec_domain *exec_domain;/* execution domain */
-	unsigned long flags;		/* thread_info flags (see TIF_*) */
-	mm_segment_t addr_limit;	/* user-level address space limit */
-	__u32 cpu;			/* current CPU */
-	int preempt_count;		/* 0=premptable, <0=BUG; will also serve as bh-counter */
-	struct restart_block restart_block;
-};
-
-#define INIT_THREAD_INFO(tsk)			\
-{						\
-	.task		= &tsk,			\
-	.exec_domain	= &default_exec_domain,	\
-	.flags		= 0,			\
-	.cpu		= 0,			\
-	.addr_limit	= KERNEL_DS,		\
-	.preempt_count	= 1,			\
-  	.restart_block	= {			\
-		.fn = do_no_restart_syscall	\
-	}					\
-}
-
-#define init_thread_info        (init_thread_union.thread_info)
-#define init_stack              (init_thread_union.stack)
-
-/* thread information allocation */
-
-#define THREAD_SIZE_ORDER            2
-/* Be sure to hunt all references to this down when you change the size of
- * the kernel stack */
-#define THREAD_SIZE             (PAGE_SIZE << THREAD_SIZE_ORDER)
-#define THREAD_SHIFT            (PAGE_SHIFT + THREAD_SIZE_ORDER)
-
-/* how to get the thread information struct from C */
-#define current_thread_info()	((struct thread_info *)mfctl(30))
-
-#endif /* !__ASSEMBLY */
-
-#define PREEMPT_ACTIVE_BIT	28
-#define PREEMPT_ACTIVE		(1 << PREEMPT_ACTIVE_BIT)
-
-/*
- * thread information flags
- */
-#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
-#define TIF_SIGPENDING		1	/* signal pending */
-#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_POLLING_NRFLAG	3	/* true if poll_idle() is polling TIF_NEED_RESCHED */
-#define TIF_32BIT               4       /* 32 bit binary */
-#define TIF_MEMDIE		5
-#define TIF_RESTORE_SIGMASK	6	/* restore saved signal mask */
-
-#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
-#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
-#define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
-#define _TIF_32BIT		(1 << TIF_32BIT)
-#define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
-
-#define _TIF_USER_WORK_MASK     (_TIF_SIGPENDING | \
-                                 _TIF_NEED_RESCHED | _TIF_RESTORE_SIGMASK)
-
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_PARISC_THREAD_INFO_H */
diff --git a/include/asm-parisc/timex.h b/include/asm-parisc/timex.h
deleted file mode 100644
index 3b68d77273d9..000000000000
--- a/include/asm-parisc/timex.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * linux/include/asm-parisc/timex.h
- *
- * PARISC architecture timex specifications
- */
-#ifndef _ASMPARISC_TIMEX_H
-#define _ASMPARISC_TIMEX_H
-
-#include <asm/system.h>
-
-#define CLOCK_TICK_RATE	1193180 /* Underlying HZ */
-
-typedef unsigned long cycles_t;
-
-static inline cycles_t get_cycles (void)
-{
-	return mfctl(16);
-}
-
-#endif
diff --git a/include/asm-parisc/tlb.h b/include/asm-parisc/tlb.h
deleted file mode 100644
index 383b1db310ee..000000000000
--- a/include/asm-parisc/tlb.h
+++ /dev/null
@@ -1,27 +0,0 @@
-#ifndef _PARISC_TLB_H
-#define _PARISC_TLB_H
-
-#define tlb_flush(tlb)			\
-do {	if ((tlb)->fullmm)		\
-		flush_tlb_mm((tlb)->mm);\
-} while (0)
-
-#define tlb_start_vma(tlb, vma) \
-do {	if (!(tlb)->fullmm)	\
-		flush_cache_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#define tlb_end_vma(tlb, vma)	\
-do {	if (!(tlb)->fullmm)	\
-		flush_tlb_range(vma, vma->vm_start, vma->vm_end); \
-} while (0)
-
-#define __tlb_remove_tlb_entry(tlb, pte, address) \
-	do { } while (0)
-
-#include <asm-generic/tlb.h>
-
-#define __pmd_free_tlb(tlb, pmd)	pmd_free((tlb)->mm, pmd)
-#define __pte_free_tlb(tlb, pte)	pte_free((tlb)->mm, pte)
-
-#endif
diff --git a/include/asm-parisc/tlbflush.h b/include/asm-parisc/tlbflush.h
deleted file mode 100644
index b72ec66db699..000000000000
--- a/include/asm-parisc/tlbflush.h
+++ /dev/null
@@ -1,80 +0,0 @@
-#ifndef _PARISC_TLBFLUSH_H
-#define _PARISC_TLBFLUSH_H
-
-/* TLB flushing routines.... */
-
-#include <linux/mm.h>
-#include <linux/sched.h>
-#include <asm/mmu_context.h>
-
-
-/* This is for the serialisation of PxTLB broadcasts.  At least on the
- * N class systems, only one PxTLB inter processor broadcast can be
- * active at any one time on the Merced bus.  This tlb purge
- * synchronisation is fairly lightweight and harmless so we activate
- * it on all SMP systems not just the N class.  We also need to have
- * preemption disabled on uniprocessor machines, and spin_lock does that
- * nicely.
- */
-extern spinlock_t pa_tlb_lock;
-
-#define purge_tlb_start(x) spin_lock(&pa_tlb_lock)
-#define purge_tlb_end(x) spin_unlock(&pa_tlb_lock)
-
-extern void flush_tlb_all(void);
-extern void flush_tlb_all_local(void *);
-
-/*
- * flush_tlb_mm()
- *
- * XXX This code is NOT valid for HP-UX compatibility processes,
- * (although it will probably work 99% of the time). HP-UX
- * processes are free to play with the space id's and save them
- * over long periods of time, etc. so we have to preserve the
- * space and just flush the entire tlb. We need to check the
- * personality in order to do that, but the personality is not
- * currently being set correctly.
- *
- * Of course, Linux processes could do the same thing, but
- * we don't support that (and the compilers, dynamic linker,
- * etc. do not do that).
- */
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	BUG_ON(mm == &init_mm); /* Should never happen */
-
-#ifdef CONFIG_SMP
-	flush_tlb_all();
-#else
-	if (mm) {
-		if (mm->context != 0)
-			free_sid(mm->context);
-		mm->context = alloc_sid();
-		if (mm == current->active_mm)
-			load_context(mm->context);
-	}
-#endif
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
-	unsigned long addr)
-{
-	/* For one page, it's not worth testing the split_tlb variable */
-
-	mb();
-	mtsp(vma->vm_mm->context,1);
-	purge_tlb_start();
-	pdtlb(addr);
-	pitlb(addr);
-	purge_tlb_end();
-}
-
-void __flush_tlb_range(unsigned long sid,
-	unsigned long start, unsigned long end);
-
-#define flush_tlb_range(vma,start,end) __flush_tlb_range((vma)->vm_mm->context,start,end)
-
-#define flush_tlb_kernel_range(start, end) __flush_tlb_range(0,start,end)
-
-#endif
diff --git a/include/asm-parisc/topology.h b/include/asm-parisc/topology.h
deleted file mode 100644
index d8133eb0b1e7..000000000000
--- a/include/asm-parisc/topology.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_PARISC_TOPOLOGY_H
-#define _ASM_PARISC_TOPOLOGY_H
-
-#include <asm-generic/topology.h>
-
-#endif /* _ASM_PARISC_TOPOLOGY_H */
diff --git a/include/asm-parisc/traps.h b/include/asm-parisc/traps.h
deleted file mode 100644
index 1945f995f2df..000000000000
--- a/include/asm-parisc/traps.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __ASM_TRAPS_H
-#define __ASM_TRAPS_H
-
-#ifdef __KERNEL__
-struct pt_regs;
-
-/* traps.c */
-void parisc_terminate(char *msg, struct pt_regs *regs,
-		int code, unsigned long offset);
-
-/* mm/fault.c */
-void do_page_fault(struct pt_regs *regs, unsigned long code,
-		unsigned long address);
-#endif
-
-#endif
diff --git a/include/asm-parisc/types.h b/include/asm-parisc/types.h
deleted file mode 100644
index 7f5a39bfb4ce..000000000000
--- a/include/asm-parisc/types.h
+++ /dev/null
@@ -1,36 +0,0 @@
-#ifndef _PARISC_TYPES_H
-#define _PARISC_TYPES_H
-
-#include <asm-generic/int-ll64.h>
-
-#ifndef __ASSEMBLY__
-
-typedef unsigned short umode_t;
-
-#endif /* __ASSEMBLY__ */
-
-/*
- * These aren't exported outside the kernel to avoid name space clashes
- */
-#ifdef __KERNEL__
-
-#ifdef CONFIG_64BIT
-#define BITS_PER_LONG 64
-#define SHIFT_PER_LONG 6
-#else
-#define BITS_PER_LONG 32
-#define SHIFT_PER_LONG 5
-#endif
-
-#ifndef __ASSEMBLY__
-
-/* Dma addresses are 32-bits wide.  */
-
-typedef u32 dma_addr_t;
-typedef u64 dma64_addr_t;
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* __KERNEL__ */
-
-#endif
diff --git a/include/asm-parisc/uaccess.h b/include/asm-parisc/uaccess.h
deleted file mode 100644
index 4878b9501f24..000000000000
--- a/include/asm-parisc/uaccess.h
+++ /dev/null
@@ -1,244 +0,0 @@
-#ifndef __PARISC_UACCESS_H
-#define __PARISC_UACCESS_H
-
-/*
- * User space memory access functions
- */
-#include <asm/page.h>
-#include <asm/system.h>
-#include <asm/cache.h>
-#include <asm-generic/uaccess.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-#define KERNEL_DS	((mm_segment_t){0})
-#define USER_DS 	((mm_segment_t){1})
-
-#define segment_eq(a,b)	((a).seg == (b).seg)
-
-#define get_ds()	(KERNEL_DS)
-#define get_fs()	(current_thread_info()->addr_limit)
-#define set_fs(x)	(current_thread_info()->addr_limit = (x))
-
-/*
- * Note that since kernel addresses are in a separate address space on
- * parisc, we don't need to do anything for access_ok().
- * We just let the page fault handler do the right thing. This also means
- * that put_user is the same as __put_user, etc.
- */
-
-extern int __get_kernel_bad(void);
-extern int __get_user_bad(void);
-extern int __put_kernel_bad(void);
-extern int __put_user_bad(void);
-
-static inline long access_ok(int type, const void __user * addr,
-		unsigned long size)
-{
-	return 1;
-}
-
-#define put_user __put_user
-#define get_user __get_user
-
-#if !defined(CONFIG_64BIT)
-#define LDD_KERNEL(ptr)		__get_kernel_bad();
-#define LDD_USER(ptr)		__get_user_bad();
-#define STD_KERNEL(x, ptr)	__put_kernel_asm64(x,ptr)
-#define STD_USER(x, ptr)	__put_user_asm64(x,ptr)
-#define ASM_WORD_INSN		".word\t"
-#else
-#define LDD_KERNEL(ptr)		__get_kernel_asm("ldd",ptr)
-#define LDD_USER(ptr)		__get_user_asm("ldd",ptr)
-#define STD_KERNEL(x, ptr)	__put_kernel_asm("std",x,ptr)
-#define STD_USER(x, ptr)	__put_user_asm("std",x,ptr)
-#define ASM_WORD_INSN		".dword\t"
-#endif
-
-/*
- * The exception table contains two values: the first is an address
- * for an instruction that is allowed to fault, and the second is
- * the address to the fixup routine. 
- */
-
-struct exception_table_entry {
-	unsigned long insn;  /* address of insn that is allowed to fault.   */
-	long fixup;          /* fixup routine */
-};
-
-#define ASM_EXCEPTIONTABLE_ENTRY( fault_addr, except_addr )\
-	".section __ex_table,\"aw\"\n"			   \
-	ASM_WORD_INSN #fault_addr ", " #except_addr "\n\t" \
-	".previous\n"
-
-/*
- * The page fault handler stores, in a per-cpu area, the following information
- * if a fixup routine is available.
- */
-struct exception_data {
-	unsigned long fault_ip;
-	unsigned long fault_space;
-	unsigned long fault_addr;
-};
-
-#define __get_user(x,ptr)                               \
-({                                                      \
-	register long __gu_err __asm__ ("r8") = 0;      \
-	register long __gu_val __asm__ ("r9") = 0;      \
-							\
-	if (segment_eq(get_fs(),KERNEL_DS)) {           \
-	    switch (sizeof(*(ptr))) {                   \
-	    case 1: __get_kernel_asm("ldb",ptr); break; \
-	    case 2: __get_kernel_asm("ldh",ptr); break; \
-	    case 4: __get_kernel_asm("ldw",ptr); break; \
-	    case 8: LDD_KERNEL(ptr); break;		\
-	    default: __get_kernel_bad(); break;         \
-	    }                                           \
-	}                                               \
-	else {                                          \
-	    switch (sizeof(*(ptr))) {                   \
-	    case 1: __get_user_asm("ldb",ptr); break;   \
-	    case 2: __get_user_asm("ldh",ptr); break;   \
-	    case 4: __get_user_asm("ldw",ptr); break;   \
-	    case 8: LDD_USER(ptr);  break;		\
-	    default: __get_user_bad(); break;           \
-	    }                                           \
-	}                                               \
-							\
-	(x) = (__typeof__(*(ptr))) __gu_val;            \
-	__gu_err;                                       \
-})
-
-#define __get_kernel_asm(ldx,ptr)                       \
-	__asm__("\n1:\t" ldx "\t0(%2),%0\n\t"		\
-		ASM_EXCEPTIONTABLE_ENTRY(1b, fixup_get_user_skip_1)\
-		: "=r"(__gu_val), "=r"(__gu_err)        \
-		: "r"(ptr), "1"(__gu_err)		\
-		: "r1");
-
-#define __get_user_asm(ldx,ptr)                         \
-	__asm__("\n1:\t" ldx "\t0(%%sr3,%2),%0\n\t"	\
-		ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_get_user_skip_1)\
-		: "=r"(__gu_val), "=r"(__gu_err)        \
-		: "r"(ptr), "1"(__gu_err)		\
-		: "r1");
-
-#define __put_user(x,ptr)                                       \
-({								\
-	register long __pu_err __asm__ ("r8") = 0;      	\
-        __typeof__(*(ptr)) __x = (__typeof__(*(ptr)))(x);	\
-								\
-	if (segment_eq(get_fs(),KERNEL_DS)) {                   \
-	    switch (sizeof(*(ptr))) {                           \
-	    case 1: __put_kernel_asm("stb",__x,ptr); break;     \
-	    case 2: __put_kernel_asm("sth",__x,ptr); break;     \
-	    case 4: __put_kernel_asm("stw",__x,ptr); break;     \
-	    case 8: STD_KERNEL(__x,ptr); break;			\
-	    default: __put_kernel_bad(); break;			\
-	    }                                                   \
-	}                                                       \
-	else {                                                  \
-	    switch (sizeof(*(ptr))) {                           \
-	    case 1: __put_user_asm("stb",__x,ptr); break;       \
-	    case 2: __put_user_asm("sth",__x,ptr); break;       \
-	    case 4: __put_user_asm("stw",__x,ptr); break;       \
-	    case 8: STD_USER(__x,ptr); break;			\
-	    default: __put_user_bad(); break;			\
-	    }                                                   \
-	}                                                       \
-								\
-	__pu_err;						\
-})
-
-/*
- * The "__put_user/kernel_asm()" macros tell gcc they read from memory
- * instead of writing. This is because they do not write to any memory
- * gcc knows about, so there are no aliasing issues. These macros must
- * also be aware that "fixup_put_user_skip_[12]" are executed in the
- * context of the fault, and any registers used there must be listed
- * as clobbers. In this case only "r1" is used by the current routines.
- * r8/r9 are already listed as err/val.
- */
-
-#define __put_kernel_asm(stx,x,ptr)                         \
-	__asm__ __volatile__ (                              \
-		"\n1:\t" stx "\t%2,0(%1)\n\t"		    \
-		ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_1)\
-		: "=r"(__pu_err)                            \
-		: "r"(ptr), "r"(x), "0"(__pu_err)	    \
-	    	: "r1")
-
-#define __put_user_asm(stx,x,ptr)                           \
-	__asm__ __volatile__ (                              \
-		"\n1:\t" stx "\t%2,0(%%sr3,%1)\n\t"	    \
-		ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_1)\
-		: "=r"(__pu_err)                            \
-		: "r"(ptr), "r"(x), "0"(__pu_err)	    \
-		: "r1")
-
-
-#if !defined(CONFIG_64BIT)
-
-#define __put_kernel_asm64(__val,ptr) do {		    \
-	u64 __val64 = (u64)(__val);			    \
-	u32 hi = (__val64) >> 32;			    \
-	u32 lo = (__val64) & 0xffffffff;		    \
-	__asm__ __volatile__ (				    \
-		"\n1:\tstw %2,0(%1)"			    \
-		"\n2:\tstw %3,4(%1)\n\t"		    \
-		ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\
-		ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\
-		: "=r"(__pu_err)                            \
-		: "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \
-		: "r1");				    \
-} while (0)
-
-#define __put_user_asm64(__val,ptr) do {	    	    \
-	u64 __val64 = (u64)(__val);			    \
-	u32 hi = (__val64) >> 32;			    \
-	u32 lo = (__val64) & 0xffffffff;		    \
-	__asm__ __volatile__ (				    \
-		"\n1:\tstw %2,0(%%sr3,%1)"		    \
-		"\n2:\tstw %3,4(%%sr3,%1)\n\t"		    \
-		ASM_EXCEPTIONTABLE_ENTRY(1b,fixup_put_user_skip_2)\
-		ASM_EXCEPTIONTABLE_ENTRY(2b,fixup_put_user_skip_1)\
-		: "=r"(__pu_err)                            \
-		: "r"(ptr), "r"(hi), "r"(lo), "0"(__pu_err) \
-		: "r1");				    \
-} while (0)
-
-#endif /* !defined(CONFIG_64BIT) */
-
-
-/*
- * Complex access routines -- external declarations
- */
-
-extern unsigned long lcopy_to_user(void __user *, const void *, unsigned long);
-extern unsigned long lcopy_from_user(void *, const void __user *, unsigned long);
-extern unsigned long lcopy_in_user(void __user *, const void __user *, unsigned long);
-extern long lstrncpy_from_user(char *, const char __user *, long);
-extern unsigned lclear_user(void __user *,unsigned long);
-extern long lstrnlen_user(const char __user *,long);
-
-/*
- * Complex access routines -- macros
- */
-
-#define strncpy_from_user lstrncpy_from_user
-#define strnlen_user lstrnlen_user
-#define strlen_user(str) lstrnlen_user(str, 0x7fffffffL)
-#define clear_user lclear_user
-#define __clear_user lclear_user
-
-unsigned long copy_to_user(void __user *dst, const void *src, unsigned long len);
-#define __copy_to_user copy_to_user
-unsigned long copy_from_user(void *dst, const void __user *src, unsigned long len);
-#define __copy_from_user copy_from_user
-unsigned long copy_in_user(void __user *dst, const void __user *src, unsigned long len);
-#define __copy_in_user copy_in_user
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-#endif /* __PARISC_UACCESS_H */
diff --git a/include/asm-parisc/ucontext.h b/include/asm-parisc/ucontext.h
deleted file mode 100644
index 6c8883e4b0bd..000000000000
--- a/include/asm-parisc/ucontext.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_PARISC_UCONTEXT_H
-#define _ASM_PARISC_UCONTEXT_H
-
-struct ucontext {
-	unsigned int	  uc_flags;
-	struct ucontext  *uc_link;
-	stack_t		  uc_stack;
-	struct sigcontext uc_mcontext;
-	sigset_t	  uc_sigmask;	/* mask last for extensibility */
-};
-
-#endif /* !_ASM_PARISC_UCONTEXT_H */
diff --git a/include/asm-parisc/unaligned.h b/include/asm-parisc/unaligned.h
deleted file mode 100644
index dfc5d3321a54..000000000000
--- a/include/asm-parisc/unaligned.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef _ASM_PARISC_UNALIGNED_H
-#define _ASM_PARISC_UNALIGNED_H
-
-#include <linux/unaligned/be_struct.h>
-#include <linux/unaligned/le_byteshift.h>
-#include <linux/unaligned/generic.h>
-#define get_unaligned	__get_unaligned_be
-#define put_unaligned	__put_unaligned_be
-
-#ifdef __KERNEL__
-struct pt_regs;
-void handle_unaligned(struct pt_regs *regs);
-int check_unaligned(struct pt_regs *regs);
-#endif
-
-#endif /* _ASM_PARISC_UNALIGNED_H */
diff --git a/include/asm-parisc/unistd.h b/include/asm-parisc/unistd.h
deleted file mode 100644
index a7d857f0e4f4..000000000000
--- a/include/asm-parisc/unistd.h
+++ /dev/null
@@ -1,991 +0,0 @@
-#ifndef _ASM_PARISC_UNISTD_H_
-#define _ASM_PARISC_UNISTD_H_
-
-/*
- * This file contains the system call numbers.
- */
-
-/*
- *   HP-UX system calls get their native numbers for binary compatibility.
- */
-
-#define __NR_HPUX_exit                    1
-#define __NR_HPUX_fork                    2
-#define __NR_HPUX_read                    3
-#define __NR_HPUX_write                   4
-#define __NR_HPUX_open                    5
-#define __NR_HPUX_close                   6
-#define __NR_HPUX_wait                    7
-#define __NR_HPUX_creat                   8
-#define __NR_HPUX_link                    9
-#define __NR_HPUX_unlink                 10
-#define __NR_HPUX_execv                  11
-#define __NR_HPUX_chdir                  12
-#define __NR_HPUX_time                   13
-#define __NR_HPUX_mknod                  14
-#define __NR_HPUX_chmod                  15
-#define __NR_HPUX_chown                  16
-#define __NR_HPUX_break                  17
-#define __NR_HPUX_lchmod                 18
-#define __NR_HPUX_lseek                  19
-#define __NR_HPUX_getpid                 20
-#define __NR_HPUX_mount                  21
-#define __NR_HPUX_umount                 22
-#define __NR_HPUX_setuid                 23
-#define __NR_HPUX_getuid                 24
-#define __NR_HPUX_stime                  25
-#define __NR_HPUX_ptrace                 26
-#define __NR_HPUX_alarm                  27
-#define __NR_HPUX_oldfstat               28
-#define __NR_HPUX_pause                  29
-#define __NR_HPUX_utime                  30
-#define __NR_HPUX_stty                   31
-#define __NR_HPUX_gtty                   32
-#define __NR_HPUX_access                 33
-#define __NR_HPUX_nice                   34
-#define __NR_HPUX_ftime                  35
-#define __NR_HPUX_sync                   36
-#define __NR_HPUX_kill                   37
-#define __NR_HPUX_stat                   38
-#define __NR_HPUX_setpgrp3               39
-#define __NR_HPUX_lstat                  40
-#define __NR_HPUX_dup                    41
-#define __NR_HPUX_pipe                   42
-#define __NR_HPUX_times                  43
-#define __NR_HPUX_profil                 44
-#define __NR_HPUX_ki_call                45
-#define __NR_HPUX_setgid                 46
-#define __NR_HPUX_getgid                 47
-#define __NR_HPUX_sigsys                 48
-#define __NR_HPUX_reserved1              49
-#define __NR_HPUX_reserved2              50
-#define __NR_HPUX_acct                   51
-#define __NR_HPUX_set_userthreadid       52
-#define __NR_HPUX_oldlock                53
-#define __NR_HPUX_ioctl                  54
-#define __NR_HPUX_reboot                 55
-#define __NR_HPUX_symlink                56
-#define __NR_HPUX_utssys                 57
-#define __NR_HPUX_readlink               58
-#define __NR_HPUX_execve                 59
-#define __NR_HPUX_umask                  60
-#define __NR_HPUX_chroot                 61
-#define __NR_HPUX_fcntl                  62
-#define __NR_HPUX_ulimit                 63
-#define __NR_HPUX_getpagesize            64
-#define __NR_HPUX_mremap                 65
-#define __NR_HPUX_vfork                  66
-#define __NR_HPUX_vread                  67
-#define __NR_HPUX_vwrite                 68
-#define __NR_HPUX_sbrk                   69
-#define __NR_HPUX_sstk                   70
-#define __NR_HPUX_mmap                   71
-#define __NR_HPUX_vadvise                72
-#define __NR_HPUX_munmap                 73
-#define __NR_HPUX_mprotect               74
-#define __NR_HPUX_madvise                75
-#define __NR_HPUX_vhangup                76
-#define __NR_HPUX_swapoff                77
-#define __NR_HPUX_mincore                78
-#define __NR_HPUX_getgroups              79
-#define __NR_HPUX_setgroups              80
-#define __NR_HPUX_getpgrp2               81
-#define __NR_HPUX_setpgrp2               82
-#define __NR_HPUX_setitimer              83
-#define __NR_HPUX_wait3                  84
-#define __NR_HPUX_swapon                 85
-#define __NR_HPUX_getitimer              86
-#define __NR_HPUX_gethostname42          87
-#define __NR_HPUX_sethostname42          88
-#define __NR_HPUX_getdtablesize          89
-#define __NR_HPUX_dup2                   90
-#define __NR_HPUX_getdopt                91
-#define __NR_HPUX_fstat                  92
-#define __NR_HPUX_select                 93
-#define __NR_HPUX_setdopt                94
-#define __NR_HPUX_fsync                  95
-#define __NR_HPUX_setpriority            96
-#define __NR_HPUX_socket_old             97
-#define __NR_HPUX_connect_old            98
-#define __NR_HPUX_accept_old             99
-#define __NR_HPUX_getpriority           100
-#define __NR_HPUX_send_old              101
-#define __NR_HPUX_recv_old              102
-#define __NR_HPUX_socketaddr_old        103
-#define __NR_HPUX_bind_old              104
-#define __NR_HPUX_setsockopt_old        105
-#define __NR_HPUX_listen_old            106
-#define __NR_HPUX_vtimes_old            107
-#define __NR_HPUX_sigvector             108
-#define __NR_HPUX_sigblock              109
-#define __NR_HPUX_siggetmask            110
-#define __NR_HPUX_sigpause              111
-#define __NR_HPUX_sigstack              112
-#define __NR_HPUX_recvmsg_old           113
-#define __NR_HPUX_sendmsg_old           114
-#define __NR_HPUX_vtrace_old            115
-#define __NR_HPUX_gettimeofday          116
-#define __NR_HPUX_getrusage             117
-#define __NR_HPUX_getsockopt_old        118
-#define __NR_HPUX_resuba_old            119
-#define __NR_HPUX_readv                 120
-#define __NR_HPUX_writev                121
-#define __NR_HPUX_settimeofday          122
-#define __NR_HPUX_fchown                123
-#define __NR_HPUX_fchmod                124
-#define __NR_HPUX_recvfrom_old          125
-#define __NR_HPUX_setresuid             126
-#define __NR_HPUX_setresgid             127
-#define __NR_HPUX_rename                128
-#define __NR_HPUX_truncate              129
-#define __NR_HPUX_ftruncate             130
-#define __NR_HPUX_flock_old             131
-#define __NR_HPUX_sysconf               132
-#define __NR_HPUX_sendto_old            133
-#define __NR_HPUX_shutdown_old          134
-#define __NR_HPUX_socketpair_old        135
-#define __NR_HPUX_mkdir                 136
-#define __NR_HPUX_rmdir                 137
-#define __NR_HPUX_utimes_old            138
-#define __NR_HPUX_sigcleanup_old        139
-#define __NR_HPUX_setcore               140
-#define __NR_HPUX_getpeername_old       141
-#define __NR_HPUX_gethostid             142
-#define __NR_HPUX_sethostid             143
-#define __NR_HPUX_getrlimit             144
-#define __NR_HPUX_setrlimit             145
-#define __NR_HPUX_killpg_old            146
-#define __NR_HPUX_cachectl              147
-#define __NR_HPUX_quotactl              148
-#define __NR_HPUX_get_sysinfo           149
-#define __NR_HPUX_getsockname_old       150
-#define __NR_HPUX_privgrp               151
-#define __NR_HPUX_rtprio                152
-#define __NR_HPUX_plock                 153
-#define __NR_HPUX_reserved3             154
-#define __NR_HPUX_lockf                 155
-#define __NR_HPUX_semget                156
-#define __NR_HPUX_osemctl               157
-#define __NR_HPUX_semop                 158
-#define __NR_HPUX_msgget                159
-#define __NR_HPUX_omsgctl               160
-#define __NR_HPUX_msgsnd                161
-#define __NR_HPUX_msgrecv               162
-#define __NR_HPUX_shmget                163
-#define __NR_HPUX_oshmctl               164
-#define __NR_HPUX_shmat                 165
-#define __NR_HPUX_shmdt                 166
-#define __NR_HPUX_m68020_advise         167
-/* [168,189] are for Discless/DUX */
-#define __NR_HPUX_csp                   168
-#define __NR_HPUX_cluster               169
-#define __NR_HPUX_mkrnod                170
-#define __NR_HPUX_test                  171
-#define __NR_HPUX_unsp_open             172
-#define __NR_HPUX_reserved4             173
-#define __NR_HPUX_getcontext_old        174
-#define __NR_HPUX_osetcontext           175
-#define __NR_HPUX_bigio                 176
-#define __NR_HPUX_pipenode              177
-#define __NR_HPUX_lsync                 178
-#define __NR_HPUX_getmachineid          179
-#define __NR_HPUX_cnodeid               180
-#define __NR_HPUX_cnodes                181
-#define __NR_HPUX_swapclients           182
-#define __NR_HPUX_rmt_process           183
-#define __NR_HPUX_dskless_stats         184
-#define __NR_HPUX_sigprocmask           185
-#define __NR_HPUX_sigpending            186
-#define __NR_HPUX_sigsuspend            187
-#define __NR_HPUX_sigaction             188
-#define __NR_HPUX_reserved5             189
-#define __NR_HPUX_nfssvc                190
-#define __NR_HPUX_getfh                 191
-#define __NR_HPUX_getdomainname         192
-#define __NR_HPUX_setdomainname         193
-#define __NR_HPUX_async_daemon          194
-#define __NR_HPUX_getdirentries         195
-#define __NR_HPUX_statfs                196
-#define __NR_HPUX_fstatfs               197
-#define __NR_HPUX_vfsmount              198
-#define __NR_HPUX_reserved6             199
-#define __NR_HPUX_waitpid               200
-/* 201 - 223 missing */
-#define __NR_HPUX_sigsetreturn          224
-#define __NR_HPUX_sigsetstatemask       225
-/* 226 missing */
-#define __NR_HPUX_cs                    227
-#define __NR_HPUX_cds                   228
-#define __NR_HPUX_set_no_trunc          229
-#define __NR_HPUX_pathconf              230
-#define __NR_HPUX_fpathconf             231
-/* 232, 233 missing */
-#define __NR_HPUX_nfs_fcntl             234
-#define __NR_HPUX_ogetacl               235
-#define __NR_HPUX_ofgetacl              236
-#define __NR_HPUX_osetacl               237
-#define __NR_HPUX_ofsetacl              238
-#define __NR_HPUX_pstat                 239
-#define __NR_HPUX_getaudid              240
-#define __NR_HPUX_setaudid              241
-#define __NR_HPUX_getaudproc            242
-#define __NR_HPUX_setaudproc            243
-#define __NR_HPUX_getevent              244
-#define __NR_HPUX_setevent              245
-#define __NR_HPUX_audwrite              246
-#define __NR_HPUX_audswitch             247
-#define __NR_HPUX_audctl                248
-#define __NR_HPUX_ogetaccess            249
-#define __NR_HPUX_fsctl                 250
-/* 251 - 258 missing */
-#define __NR_HPUX_swapfs                259
-#define __NR_HPUX_fss                   260
-/* 261 - 266 missing */
-#define __NR_HPUX_tsync                 267
-#define __NR_HPUX_getnumfds             268
-#define __NR_HPUX_poll                  269
-#define __NR_HPUX_getmsg                270
-#define __NR_HPUX_putmsg                271
-#define __NR_HPUX_fchdir                272
-#define __NR_HPUX_getmount_cnt          273
-#define __NR_HPUX_getmount_entry        274
-#define __NR_HPUX_accept                275
-#define __NR_HPUX_bind                  276
-#define __NR_HPUX_connect               277
-#define __NR_HPUX_getpeername           278
-#define __NR_HPUX_getsockname           279
-#define __NR_HPUX_getsockopt            280
-#define __NR_HPUX_listen                281
-#define __NR_HPUX_recv                  282
-#define __NR_HPUX_recvfrom              283
-#define __NR_HPUX_recvmsg               284
-#define __NR_HPUX_send                  285
-#define __NR_HPUX_sendmsg               286
-#define __NR_HPUX_sendto                287
-#define __NR_HPUX_setsockopt            288
-#define __NR_HPUX_shutdown              289
-#define __NR_HPUX_socket                290
-#define __NR_HPUX_socketpair            291
-#define __NR_HPUX_proc_open             292
-#define __NR_HPUX_proc_close            293
-#define __NR_HPUX_proc_send             294
-#define __NR_HPUX_proc_recv             295
-#define __NR_HPUX_proc_sendrecv         296
-#define __NR_HPUX_proc_syscall          297
-/* 298 - 311 missing */
-#define __NR_HPUX_semctl                312
-#define __NR_HPUX_msgctl                313
-#define __NR_HPUX_shmctl                314
-#define __NR_HPUX_mpctl                 315
-#define __NR_HPUX_exportfs              316
-#define __NR_HPUX_getpmsg               317
-#define __NR_HPUX_putpmsg               318
-/* 319 missing */
-#define __NR_HPUX_msync                 320
-#define __NR_HPUX_msleep                321
-#define __NR_HPUX_mwakeup               322
-#define __NR_HPUX_msem_init             323
-#define __NR_HPUX_msem_remove           324
-#define __NR_HPUX_adjtime               325
-#define __NR_HPUX_kload                 326
-#define __NR_HPUX_fattach               327
-#define __NR_HPUX_fdetach               328
-#define __NR_HPUX_serialize             329
-#define __NR_HPUX_statvfs               330
-#define __NR_HPUX_fstatvfs              331
-#define __NR_HPUX_lchown                332
-#define __NR_HPUX_getsid                333
-#define __NR_HPUX_sysfs                 334
-/* 335, 336 missing */
-#define __NR_HPUX_sched_setparam        337
-#define __NR_HPUX_sched_getparam        338
-#define __NR_HPUX_sched_setscheduler    339
-#define __NR_HPUX_sched_getscheduler    340
-#define __NR_HPUX_sched_yield           341
-#define __NR_HPUX_sched_get_priority_max 342
-#define __NR_HPUX_sched_get_priority_min 343
-#define __NR_HPUX_sched_rr_get_interval 344
-#define __NR_HPUX_clock_settime         345
-#define __NR_HPUX_clock_gettime         346
-#define __NR_HPUX_clock_getres          347
-#define __NR_HPUX_timer_create          348
-#define __NR_HPUX_timer_delete          349
-#define __NR_HPUX_timer_settime         350
-#define __NR_HPUX_timer_gettime         351
-#define __NR_HPUX_timer_getoverrun      352
-#define __NR_HPUX_nanosleep             353
-#define __NR_HPUX_toolbox               354
-/* 355 missing */
-#define __NR_HPUX_getdents              356
-#define __NR_HPUX_getcontext            357
-#define __NR_HPUX_sysinfo               358
-#define __NR_HPUX_fcntl64               359
-#define __NR_HPUX_ftruncate64           360
-#define __NR_HPUX_fstat64               361
-#define __NR_HPUX_getdirentries64       362
-#define __NR_HPUX_getrlimit64           363
-#define __NR_HPUX_lockf64               364
-#define __NR_HPUX_lseek64               365
-#define __NR_HPUX_lstat64               366
-#define __NR_HPUX_mmap64                367
-#define __NR_HPUX_setrlimit64           368
-#define __NR_HPUX_stat64                369
-#define __NR_HPUX_truncate64            370
-#define __NR_HPUX_ulimit64              371
-#define __NR_HPUX_pread                 372
-#define __NR_HPUX_preadv                373
-#define __NR_HPUX_pwrite                374
-#define __NR_HPUX_pwritev               375
-#define __NR_HPUX_pread64               376
-#define __NR_HPUX_preadv64              377
-#define __NR_HPUX_pwrite64              378
-#define __NR_HPUX_pwritev64             379
-#define __NR_HPUX_setcontext            380
-#define __NR_HPUX_sigaltstack           381
-#define __NR_HPUX_waitid                382
-#define __NR_HPUX_setpgrp               383
-#define __NR_HPUX_recvmsg2              384
-#define __NR_HPUX_sendmsg2              385
-#define __NR_HPUX_socket2               386
-#define __NR_HPUX_socketpair2           387
-#define __NR_HPUX_setregid              388
-#define __NR_HPUX_lwp_create            389
-#define __NR_HPUX_lwp_terminate         390
-#define __NR_HPUX_lwp_wait              391
-#define __NR_HPUX_lwp_suspend           392
-#define __NR_HPUX_lwp_resume            393
-/* 394 missing */
-#define __NR_HPUX_lwp_abort_syscall     395
-#define __NR_HPUX_lwp_info              396
-#define __NR_HPUX_lwp_kill              397
-#define __NR_HPUX_ksleep                398
-#define __NR_HPUX_kwakeup               399
-/* 400 missing */
-#define __NR_HPUX_pstat_getlwp          401
-#define __NR_HPUX_lwp_exit              402
-#define __NR_HPUX_lwp_continue          403
-#define __NR_HPUX_getacl                404
-#define __NR_HPUX_fgetacl               405
-#define __NR_HPUX_setacl                406
-#define __NR_HPUX_fsetacl               407
-#define __NR_HPUX_getaccess             408
-#define __NR_HPUX_lwp_mutex_init        409
-#define __NR_HPUX_lwp_mutex_lock_sys    410
-#define __NR_HPUX_lwp_mutex_unlock      411
-#define __NR_HPUX_lwp_cond_init         412
-#define __NR_HPUX_lwp_cond_signal       413
-#define __NR_HPUX_lwp_cond_broadcast    414
-#define __NR_HPUX_lwp_cond_wait_sys     415
-#define __NR_HPUX_lwp_getscheduler      416
-#define __NR_HPUX_lwp_setscheduler      417
-#define __NR_HPUX_lwp_getstate          418
-#define __NR_HPUX_lwp_setstate          419
-#define __NR_HPUX_lwp_detach            420
-#define __NR_HPUX_mlock                 421
-#define __NR_HPUX_munlock               422
-#define __NR_HPUX_mlockall              423
-#define __NR_HPUX_munlockall            424
-#define __NR_HPUX_shm_open              425
-#define __NR_HPUX_shm_unlink            426
-#define __NR_HPUX_sigqueue              427
-#define __NR_HPUX_sigwaitinfo           428
-#define __NR_HPUX_sigtimedwait          429
-#define __NR_HPUX_sigwait               430
-#define __NR_HPUX_aio_read              431
-#define __NR_HPUX_aio_write             432
-#define __NR_HPUX_lio_listio            433
-#define __NR_HPUX_aio_error             434
-#define __NR_HPUX_aio_return            435
-#define __NR_HPUX_aio_cancel            436
-#define __NR_HPUX_aio_suspend           437
-#define __NR_HPUX_aio_fsync             438
-#define __NR_HPUX_mq_open               439
-#define __NR_HPUX_mq_close              440
-#define __NR_HPUX_mq_unlink             441
-#define __NR_HPUX_mq_send               442
-#define __NR_HPUX_mq_receive            443
-#define __NR_HPUX_mq_notify             444
-#define __NR_HPUX_mq_setattr            445
-#define __NR_HPUX_mq_getattr            446
-#define __NR_HPUX_ksem_open             447
-#define __NR_HPUX_ksem_unlink           448
-#define __NR_HPUX_ksem_close            449
-#define __NR_HPUX_ksem_post             450
-#define __NR_HPUX_ksem_wait             451
-#define __NR_HPUX_ksem_read             452
-#define __NR_HPUX_ksem_trywait          453
-#define __NR_HPUX_lwp_rwlock_init       454
-#define __NR_HPUX_lwp_rwlock_destroy    455
-#define __NR_HPUX_lwp_rwlock_rdlock_sys 456
-#define __NR_HPUX_lwp_rwlock_wrlock_sys 457
-#define __NR_HPUX_lwp_rwlock_tryrdlock  458
-#define __NR_HPUX_lwp_rwlock_trywrlock  459
-#define __NR_HPUX_lwp_rwlock_unlock     460
-#define __NR_HPUX_ttrace                461
-#define __NR_HPUX_ttrace_wait           462
-#define __NR_HPUX_lf_wire_mem           463
-#define __NR_HPUX_lf_unwire_mem         464
-#define __NR_HPUX_lf_send_pin_map       465
-#define __NR_HPUX_lf_free_buf           466
-#define __NR_HPUX_lf_wait_nq            467
-#define __NR_HPUX_lf_wakeup_conn_q      468
-#define __NR_HPUX_lf_unused             469
-#define __NR_HPUX_lwp_sema_init         470
-#define __NR_HPUX_lwp_sema_post         471
-#define __NR_HPUX_lwp_sema_wait         472
-#define __NR_HPUX_lwp_sema_trywait      473
-#define __NR_HPUX_lwp_sema_destroy      474
-#define __NR_HPUX_statvfs64             475
-#define __NR_HPUX_fstatvfs64            476
-#define __NR_HPUX_msh_register          477
-#define __NR_HPUX_ptrace64              478
-#define __NR_HPUX_sendfile              479
-#define __NR_HPUX_sendpath              480
-#define __NR_HPUX_sendfile64            481
-#define __NR_HPUX_sendpath64            482
-#define __NR_HPUX_modload               483
-#define __NR_HPUX_moduload              484
-#define __NR_HPUX_modpath               485
-#define __NR_HPUX_getksym               486
-#define __NR_HPUX_modadm                487
-#define __NR_HPUX_modstat               488
-#define __NR_HPUX_lwp_detached_exit     489
-#define __NR_HPUX_crashconf             490
-#define __NR_HPUX_siginhibit            491
-#define __NR_HPUX_sigenable             492
-#define __NR_HPUX_spuctl                493
-#define __NR_HPUX_zerokernelsum         494
-#define __NR_HPUX_nfs_kstat             495
-#define __NR_HPUX_aio_read64            496
-#define __NR_HPUX_aio_write64           497
-#define __NR_HPUX_aio_error64           498
-#define __NR_HPUX_aio_return64          499
-#define __NR_HPUX_aio_cancel64          500
-#define __NR_HPUX_aio_suspend64         501
-#define __NR_HPUX_aio_fsync64           502
-#define __NR_HPUX_lio_listio64          503
-#define __NR_HPUX_recv2                 504
-#define __NR_HPUX_recvfrom2             505
-#define __NR_HPUX_send2                 506
-#define __NR_HPUX_sendto2               507
-#define __NR_HPUX_acl                   508
-#define __NR_HPUX___cnx_p2p_ctl         509
-#define __NR_HPUX___cnx_gsched_ctl      510
-#define __NR_HPUX___cnx_pmon_ctl        511
-
-#define __NR_HPUX_syscalls		512
-
-/*
- * Linux system call numbers.
- *
- * Cary Coutant says that we should just use another syscall gateway
- * page to avoid clashing with the HPUX space, and I think he's right:
- * it will would keep a branch out of our syscall entry path, at the
- * very least.  If we decide to change it later, we can ``just'' tweak
- * the LINUX_GATEWAY_ADDR define at the bottom and make __NR_Linux be
- * 1024 or something.  Oh, and recompile libc. =)
- *
- * 64-bit HPUX binaries get the syscall gateway address passed in a register
- * from the kernel at startup, which seems a sane strategy.
- */
-
-#define __NR_Linux                0
-#define __NR_restart_syscall      (__NR_Linux + 0)
-#define __NR_exit                 (__NR_Linux + 1)
-#define __NR_fork                 (__NR_Linux + 2)
-#define __NR_read                 (__NR_Linux + 3)
-#define __NR_write                (__NR_Linux + 4)
-#define __NR_open                 (__NR_Linux + 5)
-#define __NR_close                (__NR_Linux + 6)
-#define __NR_waitpid              (__NR_Linux + 7)
-#define __NR_creat                (__NR_Linux + 8)
-#define __NR_link                 (__NR_Linux + 9)
-#define __NR_unlink              (__NR_Linux + 10)
-#define __NR_execve              (__NR_Linux + 11)
-#define __NR_chdir               (__NR_Linux + 12)
-#define __NR_time                (__NR_Linux + 13)
-#define __NR_mknod               (__NR_Linux + 14)
-#define __NR_chmod               (__NR_Linux + 15)
-#define __NR_lchown              (__NR_Linux + 16)
-#define __NR_socket              (__NR_Linux + 17)
-#define __NR_stat                (__NR_Linux + 18)
-#define __NR_lseek               (__NR_Linux + 19)
-#define __NR_getpid              (__NR_Linux + 20)
-#define __NR_mount               (__NR_Linux + 21)
-#define __NR_bind                (__NR_Linux + 22)
-#define __NR_setuid              (__NR_Linux + 23)
-#define __NR_getuid              (__NR_Linux + 24)
-#define __NR_stime               (__NR_Linux + 25)
-#define __NR_ptrace              (__NR_Linux + 26)
-#define __NR_alarm               (__NR_Linux + 27)
-#define __NR_fstat               (__NR_Linux + 28)
-#define __NR_pause               (__NR_Linux + 29)
-#define __NR_utime               (__NR_Linux + 30)
-#define __NR_connect             (__NR_Linux + 31)
-#define __NR_listen              (__NR_Linux + 32)
-#define __NR_access              (__NR_Linux + 33)
-#define __NR_nice                (__NR_Linux + 34)
-#define __NR_accept              (__NR_Linux + 35)
-#define __NR_sync                (__NR_Linux + 36)
-#define __NR_kill                (__NR_Linux + 37)
-#define __NR_rename              (__NR_Linux + 38)
-#define __NR_mkdir               (__NR_Linux + 39)
-#define __NR_rmdir               (__NR_Linux + 40)
-#define __NR_dup                 (__NR_Linux + 41)
-#define __NR_pipe                (__NR_Linux + 42)
-#define __NR_times               (__NR_Linux + 43)
-#define __NR_getsockname         (__NR_Linux + 44)
-#define __NR_brk                 (__NR_Linux + 45)
-#define __NR_setgid              (__NR_Linux + 46)
-#define __NR_getgid              (__NR_Linux + 47)
-#define __NR_signal              (__NR_Linux + 48)
-#define __NR_geteuid             (__NR_Linux + 49)
-#define __NR_getegid             (__NR_Linux + 50)
-#define __NR_acct                (__NR_Linux + 51)
-#define __NR_umount2             (__NR_Linux + 52)
-#define __NR_getpeername         (__NR_Linux + 53)
-#define __NR_ioctl               (__NR_Linux + 54)
-#define __NR_fcntl               (__NR_Linux + 55)
-#define __NR_socketpair          (__NR_Linux + 56)
-#define __NR_setpgid             (__NR_Linux + 57)
-#define __NR_send                (__NR_Linux + 58)
-#define __NR_uname               (__NR_Linux + 59)
-#define __NR_umask               (__NR_Linux + 60)
-#define __NR_chroot              (__NR_Linux + 61)
-#define __NR_ustat               (__NR_Linux + 62)
-#define __NR_dup2                (__NR_Linux + 63)
-#define __NR_getppid             (__NR_Linux + 64)
-#define __NR_getpgrp             (__NR_Linux + 65)
-#define __NR_setsid              (__NR_Linux + 66)
-#define __NR_pivot_root          (__NR_Linux + 67)
-#define __NR_sgetmask            (__NR_Linux + 68)
-#define __NR_ssetmask            (__NR_Linux + 69)
-#define __NR_setreuid            (__NR_Linux + 70)
-#define __NR_setregid            (__NR_Linux + 71)
-#define __NR_mincore             (__NR_Linux + 72)
-#define __NR_sigpending          (__NR_Linux + 73)
-#define __NR_sethostname         (__NR_Linux + 74)
-#define __NR_setrlimit           (__NR_Linux + 75)
-#define __NR_getrlimit           (__NR_Linux + 76)
-#define __NR_getrusage           (__NR_Linux + 77)
-#define __NR_gettimeofday        (__NR_Linux + 78)
-#define __NR_settimeofday        (__NR_Linux + 79)
-#define __NR_getgroups           (__NR_Linux + 80)
-#define __NR_setgroups           (__NR_Linux + 81)
-#define __NR_sendto              (__NR_Linux + 82)
-#define __NR_symlink             (__NR_Linux + 83)
-#define __NR_lstat               (__NR_Linux + 84)
-#define __NR_readlink            (__NR_Linux + 85)
-#define __NR_uselib              (__NR_Linux + 86)
-#define __NR_swapon              (__NR_Linux + 87)
-#define __NR_reboot              (__NR_Linux + 88)
-#define __NR_mmap2             (__NR_Linux + 89)
-#define __NR_mmap                (__NR_Linux + 90)
-#define __NR_munmap              (__NR_Linux + 91)
-#define __NR_truncate            (__NR_Linux + 92)
-#define __NR_ftruncate           (__NR_Linux + 93)
-#define __NR_fchmod              (__NR_Linux + 94)
-#define __NR_fchown              (__NR_Linux + 95)
-#define __NR_getpriority         (__NR_Linux + 96)
-#define __NR_setpriority         (__NR_Linux + 97)
-#define __NR_recv                (__NR_Linux + 98)
-#define __NR_statfs              (__NR_Linux + 99)
-#define __NR_fstatfs            (__NR_Linux + 100)
-#define __NR_stat64           (__NR_Linux + 101)
-/* #define __NR_socketcall         (__NR_Linux + 102) */
-#define __NR_syslog             (__NR_Linux + 103)
-#define __NR_setitimer          (__NR_Linux + 104)
-#define __NR_getitimer          (__NR_Linux + 105)
-#define __NR_capget             (__NR_Linux + 106)
-#define __NR_capset             (__NR_Linux + 107)
-#define __NR_pread64            (__NR_Linux + 108)
-#define __NR_pwrite64           (__NR_Linux + 109)
-#define __NR_getcwd             (__NR_Linux + 110)
-#define __NR_vhangup            (__NR_Linux + 111)
-#define __NR_fstat64            (__NR_Linux + 112)
-#define __NR_vfork              (__NR_Linux + 113)
-#define __NR_wait4              (__NR_Linux + 114)
-#define __NR_swapoff            (__NR_Linux + 115)
-#define __NR_sysinfo            (__NR_Linux + 116)
-#define __NR_shutdown           (__NR_Linux + 117)
-#define __NR_fsync              (__NR_Linux + 118)
-#define __NR_madvise            (__NR_Linux + 119)
-#define __NR_clone              (__NR_Linux + 120)
-#define __NR_setdomainname      (__NR_Linux + 121)
-#define __NR_sendfile           (__NR_Linux + 122)
-#define __NR_recvfrom           (__NR_Linux + 123)
-#define __NR_adjtimex           (__NR_Linux + 124)
-#define __NR_mprotect           (__NR_Linux + 125)
-#define __NR_sigprocmask        (__NR_Linux + 126)
-#define __NR_create_module      (__NR_Linux + 127)
-#define __NR_init_module        (__NR_Linux + 128)
-#define __NR_delete_module      (__NR_Linux + 129)
-#define __NR_get_kernel_syms    (__NR_Linux + 130)
-#define __NR_quotactl           (__NR_Linux + 131)
-#define __NR_getpgid            (__NR_Linux + 132)
-#define __NR_fchdir             (__NR_Linux + 133)
-#define __NR_bdflush            (__NR_Linux + 134)
-#define __NR_sysfs              (__NR_Linux + 135)
-#define __NR_personality        (__NR_Linux + 136)
-#define __NR_afs_syscall        (__NR_Linux + 137) /* Syscall for Andrew File System */
-#define __NR_setfsuid           (__NR_Linux + 138)
-#define __NR_setfsgid           (__NR_Linux + 139)
-#define __NR__llseek            (__NR_Linux + 140)
-#define __NR_getdents           (__NR_Linux + 141)
-#define __NR__newselect         (__NR_Linux + 142)
-#define __NR_flock              (__NR_Linux + 143)
-#define __NR_msync              (__NR_Linux + 144)
-#define __NR_readv              (__NR_Linux + 145)
-#define __NR_writev             (__NR_Linux + 146)
-#define __NR_getsid             (__NR_Linux + 147)
-#define __NR_fdatasync          (__NR_Linux + 148)
-#define __NR__sysctl            (__NR_Linux + 149)
-#define __NR_mlock              (__NR_Linux + 150)
-#define __NR_munlock            (__NR_Linux + 151)
-#define __NR_mlockall           (__NR_Linux + 152)
-#define __NR_munlockall         (__NR_Linux + 153)
-#define __NR_sched_setparam             (__NR_Linux + 154)
-#define __NR_sched_getparam             (__NR_Linux + 155)
-#define __NR_sched_setscheduler         (__NR_Linux + 156)
-#define __NR_sched_getscheduler         (__NR_Linux + 157)
-#define __NR_sched_yield                (__NR_Linux + 158)
-#define __NR_sched_get_priority_max     (__NR_Linux + 159)
-#define __NR_sched_get_priority_min     (__NR_Linux + 160)
-#define __NR_sched_rr_get_interval      (__NR_Linux + 161)
-#define __NR_nanosleep          (__NR_Linux + 162)
-#define __NR_mremap             (__NR_Linux + 163)
-#define __NR_setresuid          (__NR_Linux + 164)
-#define __NR_getresuid          (__NR_Linux + 165)
-#define __NR_sigaltstack        (__NR_Linux + 166)
-#define __NR_query_module       (__NR_Linux + 167)
-#define __NR_poll               (__NR_Linux + 168)
-#define __NR_nfsservctl         (__NR_Linux + 169)
-#define __NR_setresgid          (__NR_Linux + 170)
-#define __NR_getresgid          (__NR_Linux + 171)
-#define __NR_prctl              (__NR_Linux + 172)
-#define __NR_rt_sigreturn       (__NR_Linux + 173)
-#define __NR_rt_sigaction       (__NR_Linux + 174)
-#define __NR_rt_sigprocmask     (__NR_Linux + 175)
-#define __NR_rt_sigpending      (__NR_Linux + 176)
-#define __NR_rt_sigtimedwait    (__NR_Linux + 177)
-#define __NR_rt_sigqueueinfo    (__NR_Linux + 178)
-#define __NR_rt_sigsuspend      (__NR_Linux + 179)
-#define __NR_chown              (__NR_Linux + 180)
-#define __NR_setsockopt         (__NR_Linux + 181)
-#define __NR_getsockopt         (__NR_Linux + 182)
-#define __NR_sendmsg            (__NR_Linux + 183)
-#define __NR_recvmsg            (__NR_Linux + 184)
-#define __NR_semop              (__NR_Linux + 185)
-#define __NR_semget             (__NR_Linux + 186)
-#define __NR_semctl             (__NR_Linux + 187)
-#define __NR_msgsnd             (__NR_Linux + 188)
-#define __NR_msgrcv             (__NR_Linux + 189)
-#define __NR_msgget             (__NR_Linux + 190)
-#define __NR_msgctl             (__NR_Linux + 191)
-#define __NR_shmat              (__NR_Linux + 192)
-#define __NR_shmdt              (__NR_Linux + 193)
-#define __NR_shmget             (__NR_Linux + 194)
-#define __NR_shmctl             (__NR_Linux + 195)
-
-#define __NR_getpmsg		(__NR_Linux + 196) /* Somebody *wants* streams? */
-#define __NR_putpmsg		(__NR_Linux + 197)
-
-#define __NR_lstat64            (__NR_Linux + 198)
-#define __NR_truncate64         (__NR_Linux + 199)
-#define __NR_ftruncate64        (__NR_Linux + 200)
-#define __NR_getdents64         (__NR_Linux + 201)
-#define __NR_fcntl64            (__NR_Linux + 202)
-#define __NR_attrctl            (__NR_Linux + 203)
-#define __NR_acl_get            (__NR_Linux + 204)
-#define __NR_acl_set            (__NR_Linux + 205)
-#define __NR_gettid             (__NR_Linux + 206)
-#define __NR_readahead          (__NR_Linux + 207)
-#define __NR_tkill              (__NR_Linux + 208)
-#define __NR_sendfile64         (__NR_Linux + 209)
-#define __NR_futex              (__NR_Linux + 210)
-#define __NR_sched_setaffinity  (__NR_Linux + 211)
-#define __NR_sched_getaffinity  (__NR_Linux + 212)
-#define __NR_set_thread_area    (__NR_Linux + 213)
-#define __NR_get_thread_area    (__NR_Linux + 214)
-#define __NR_io_setup           (__NR_Linux + 215)
-#define __NR_io_destroy         (__NR_Linux + 216)
-#define __NR_io_getevents       (__NR_Linux + 217)
-#define __NR_io_submit          (__NR_Linux + 218)
-#define __NR_io_cancel          (__NR_Linux + 219)
-#define __NR_alloc_hugepages    (__NR_Linux + 220)
-#define __NR_free_hugepages     (__NR_Linux + 221)
-#define __NR_exit_group         (__NR_Linux + 222)
-#define __NR_lookup_dcookie     (__NR_Linux + 223)
-#define __NR_epoll_create       (__NR_Linux + 224)
-#define __NR_epoll_ctl          (__NR_Linux + 225)
-#define __NR_epoll_wait         (__NR_Linux + 226)
-#define __NR_remap_file_pages   (__NR_Linux + 227)
-#define __NR_semtimedop         (__NR_Linux + 228)
-#define __NR_mq_open            (__NR_Linux + 229)
-#define __NR_mq_unlink          (__NR_Linux + 230)
-#define __NR_mq_timedsend       (__NR_Linux + 231)
-#define __NR_mq_timedreceive    (__NR_Linux + 232)
-#define __NR_mq_notify          (__NR_Linux + 233)
-#define __NR_mq_getsetattr      (__NR_Linux + 234)
-#define __NR_waitid		(__NR_Linux + 235)
-#define __NR_fadvise64_64	(__NR_Linux + 236)
-#define __NR_set_tid_address	(__NR_Linux + 237)
-#define __NR_setxattr		(__NR_Linux + 238)
-#define __NR_lsetxattr		(__NR_Linux + 239)
-#define __NR_fsetxattr		(__NR_Linux + 240)
-#define __NR_getxattr		(__NR_Linux + 241)
-#define __NR_lgetxattr		(__NR_Linux + 242)
-#define __NR_fgetxattr		(__NR_Linux + 243)
-#define __NR_listxattr		(__NR_Linux + 244)
-#define __NR_llistxattr		(__NR_Linux + 245)
-#define __NR_flistxattr		(__NR_Linux + 246)
-#define __NR_removexattr	(__NR_Linux + 247)
-#define __NR_lremovexattr	(__NR_Linux + 248)
-#define __NR_fremovexattr	(__NR_Linux + 249)
-#define __NR_timer_create	(__NR_Linux + 250)
-#define __NR_timer_settime	(__NR_Linux + 251)
-#define __NR_timer_gettime	(__NR_Linux + 252)
-#define __NR_timer_getoverrun	(__NR_Linux + 253)
-#define __NR_timer_delete	(__NR_Linux + 254)
-#define __NR_clock_settime	(__NR_Linux + 255)
-#define __NR_clock_gettime	(__NR_Linux + 256)
-#define __NR_clock_getres	(__NR_Linux + 257)
-#define __NR_clock_nanosleep	(__NR_Linux + 258)
-#define __NR_tgkill		(__NR_Linux + 259)
-#define __NR_mbind		(__NR_Linux + 260)
-#define __NR_get_mempolicy	(__NR_Linux + 261)
-#define __NR_set_mempolicy	(__NR_Linux + 262)
-#define __NR_vserver		(__NR_Linux + 263)
-#define __NR_add_key		(__NR_Linux + 264)
-#define __NR_request_key	(__NR_Linux + 265)
-#define __NR_keyctl		(__NR_Linux + 266)
-#define __NR_ioprio_set		(__NR_Linux + 267)
-#define __NR_ioprio_get		(__NR_Linux + 268)
-#define __NR_inotify_init	(__NR_Linux + 269)
-#define __NR_inotify_add_watch	(__NR_Linux + 270)
-#define __NR_inotify_rm_watch	(__NR_Linux + 271)
-#define __NR_migrate_pages	(__NR_Linux + 272)
-#define __NR_pselect6		(__NR_Linux + 273)
-#define __NR_ppoll		(__NR_Linux + 274)
-#define __NR_openat		(__NR_Linux + 275)
-#define __NR_mkdirat		(__NR_Linux + 276)
-#define __NR_mknodat		(__NR_Linux + 277)
-#define __NR_fchownat		(__NR_Linux + 278)
-#define __NR_futimesat		(__NR_Linux + 279)
-#define __NR_fstatat64		(__NR_Linux + 280)
-#define __NR_unlinkat		(__NR_Linux + 281)
-#define __NR_renameat		(__NR_Linux + 282)
-#define __NR_linkat		(__NR_Linux + 283)
-#define __NR_symlinkat		(__NR_Linux + 284)
-#define __NR_readlinkat		(__NR_Linux + 285)
-#define __NR_fchmodat		(__NR_Linux + 286)
-#define __NR_faccessat		(__NR_Linux + 287)
-#define __NR_unshare		(__NR_Linux + 288)
-#define __NR_set_robust_list	(__NR_Linux + 289)
-#define __NR_get_robust_list	(__NR_Linux + 290)
-#define __NR_splice		(__NR_Linux + 291)
-#define __NR_sync_file_range	(__NR_Linux + 292)
-#define __NR_tee		(__NR_Linux + 293)
-#define __NR_vmsplice		(__NR_Linux + 294)
-#define __NR_move_pages		(__NR_Linux + 295)
-#define __NR_getcpu		(__NR_Linux + 296)
-#define __NR_epoll_pwait	(__NR_Linux + 297)
-#define __NR_statfs64		(__NR_Linux + 298)
-#define __NR_fstatfs64		(__NR_Linux + 299)
-#define __NR_kexec_load		(__NR_Linux + 300)
-#define __NR_utimensat		(__NR_Linux + 301)
-#define __NR_signalfd		(__NR_Linux + 302)
-#define __NR_timerfd		(__NR_Linux + 303)
-#define __NR_eventfd		(__NR_Linux + 304)
-#define __NR_fallocate		(__NR_Linux + 305)
-#define __NR_timerfd_create	(__NR_Linux + 306)
-#define __NR_timerfd_settime	(__NR_Linux + 307)
-#define __NR_timerfd_gettime	(__NR_Linux + 308)
-
-#define __NR_Linux_syscalls	(__NR_timerfd_gettime + 1)
-
-
-#define __IGNORE_select		/* newselect */
-#define __IGNORE_fadvise64	/* fadvise64_64 */
-#define __IGNORE_utimes		/* utime */
-
-
-#define HPUX_GATEWAY_ADDR       0xC0000004
-#define LINUX_GATEWAY_ADDR      0x100
-
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-#define SYS_ify(syscall_name)   __NR_##syscall_name
-
-#ifndef ASM_LINE_SEP
-# define ASM_LINE_SEP ;
-#endif
-
-/* Definition taken from glibc 2.3.3
- * sysdeps/unix/sysv/linux/hppa/sysdep.h
- */
-
-#ifdef PIC
-/* WARNING: CANNOT BE USED IN A NOP! */
-# define K_STW_ASM_PIC	"       copy %%r19, %%r4\n"
-# define K_LDW_ASM_PIC	"       copy %%r4, %%r19\n"
-# define K_USING_GR4	"%r4",
-#else
-# define K_STW_ASM_PIC	" \n"
-# define K_LDW_ASM_PIC	" \n"
-# define K_USING_GR4
-#endif
-
-/* GCC has to be warned that a syscall may clobber all the ABI
-   registers listed as "caller-saves", see page 8, Table 2
-   in section 2.2.6 of the PA-RISC RUN-TIME architecture
-   document. However! r28 is the result and will conflict with
-   the clobber list so it is left out. Also the input arguments
-   registers r20 -> r26 will conflict with the list so they
-   are treated specially. Although r19 is clobbered by the syscall
-   we cannot say this because it would violate ABI, thus we say
-   r4 is clobbered and use that register to save/restore r19
-   across the syscall. */
-
-#define K_CALL_CLOB_REGS "%r1", "%r2", K_USING_GR4 \
-	        	 "%r20", "%r29", "%r31"
-
-#undef K_INLINE_SYSCALL
-#define K_INLINE_SYSCALL(name, nr, args...)	({			\
-	long __sys_res;							\
-	{								\
-		register unsigned long __res __asm__("r28");		\
-		K_LOAD_ARGS_##nr(args)					\
-		/* FIXME: HACK stw/ldw r19 around syscall */		\
-		__asm__ volatile(					\
-			K_STW_ASM_PIC					\
-			"	ble  0x100(%%sr2, %%r0)\n"		\
-			"	ldi %1, %%r20\n"			\
-			K_LDW_ASM_PIC					\
-			: "=r" (__res)					\
-			: "i" (SYS_ify(name)) K_ASM_ARGS_##nr   	\
-			: "memory", K_CALL_CLOB_REGS K_CLOB_ARGS_##nr	\
-		);							\
-		__sys_res = (long)__res;				\
-	}								\
-	if ( (unsigned long)__sys_res >= (unsigned long)-4095 ){	\
-		errno = -__sys_res;		        		\
-		__sys_res = -1;						\
-	}								\
-	__sys_res;							\
-})
-
-#define K_LOAD_ARGS_0()
-#define K_LOAD_ARGS_1(r26)					\
-	register unsigned long __r26 __asm__("r26") = (unsigned long)(r26);   \
-	K_LOAD_ARGS_0()
-#define K_LOAD_ARGS_2(r26,r25)					\
-	register unsigned long __r25 __asm__("r25") = (unsigned long)(r25);   \
-	K_LOAD_ARGS_1(r26)
-#define K_LOAD_ARGS_3(r26,r25,r24)				\
-	register unsigned long __r24 __asm__("r24") = (unsigned long)(r24);   \
-	K_LOAD_ARGS_2(r26,r25)
-#define K_LOAD_ARGS_4(r26,r25,r24,r23)				\
-	register unsigned long __r23 __asm__("r23") = (unsigned long)(r23);   \
-	K_LOAD_ARGS_3(r26,r25,r24)
-#define K_LOAD_ARGS_5(r26,r25,r24,r23,r22)			\
-	register unsigned long __r22 __asm__("r22") = (unsigned long)(r22);   \
-	K_LOAD_ARGS_4(r26,r25,r24,r23)
-#define K_LOAD_ARGS_6(r26,r25,r24,r23,r22,r21)			\
-	register unsigned long __r21 __asm__("r21") = (unsigned long)(r21);   \
-	K_LOAD_ARGS_5(r26,r25,r24,r23,r22)
-
-/* Even with zero args we use r20 for the syscall number */
-#define K_ASM_ARGS_0
-#define K_ASM_ARGS_1 K_ASM_ARGS_0, "r" (__r26)
-#define K_ASM_ARGS_2 K_ASM_ARGS_1, "r" (__r25)
-#define K_ASM_ARGS_3 K_ASM_ARGS_2, "r" (__r24)
-#define K_ASM_ARGS_4 K_ASM_ARGS_3, "r" (__r23)
-#define K_ASM_ARGS_5 K_ASM_ARGS_4, "r" (__r22)
-#define K_ASM_ARGS_6 K_ASM_ARGS_5, "r" (__r21)
-
-/* The registers not listed as inputs but clobbered */
-#define K_CLOB_ARGS_6
-#define K_CLOB_ARGS_5 K_CLOB_ARGS_6, "%r21"
-#define K_CLOB_ARGS_4 K_CLOB_ARGS_5, "%r22"
-#define K_CLOB_ARGS_3 K_CLOB_ARGS_4, "%r23"
-#define K_CLOB_ARGS_2 K_CLOB_ARGS_3, "%r24"
-#define K_CLOB_ARGS_1 K_CLOB_ARGS_2, "%r25"
-#define K_CLOB_ARGS_0 K_CLOB_ARGS_1, "%r26"
-
-#define _syscall0(type,name)						\
-type name(void)								\
-{									\
-    return K_INLINE_SYSCALL(name, 0);	                                \
-}
-
-#define _syscall1(type,name,type1,arg1)					\
-type name(type1 arg1)							\
-{									\
-    return K_INLINE_SYSCALL(name, 1, arg1);	                        \
-}
-
-#define _syscall2(type,name,type1,arg1,type2,arg2)			\
-type name(type1 arg1, type2 arg2)					\
-{									\
-    return K_INLINE_SYSCALL(name, 2, arg1, arg2);	                \
-}
-
-#define _syscall3(type,name,type1,arg1,type2,arg2,type3,arg3)		\
-type name(type1 arg1, type2 arg2, type3 arg3)				\
-{									\
-    return K_INLINE_SYSCALL(name, 3, arg1, arg2, arg3);	                \
-}
-
-#define _syscall4(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4) \
-type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4)		\
-{									\
-    return K_INLINE_SYSCALL(name, 4, arg1, arg2, arg3, arg4);	        \
-}
-
-/* select takes 5 arguments */
-#define _syscall5(type,name,type1,arg1,type2,arg2,type3,arg3,type4,arg4,type5,arg5) \
-type name(type1 arg1, type2 arg2, type3 arg3, type4 arg4, type5 arg5)	\
-{									\
-    return K_INLINE_SYSCALL(name, 5, arg1, arg2, arg3, arg4, arg5);	\
-}
-
-#define __ARCH_WANT_OLD_READDIR
-#define __ARCH_WANT_STAT64
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_SGETMASK
-#define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_COMPAT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_SOCKETCALL
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_NICE
-#define __ARCH_WANT_SYS_OLD_GETRLIMIT
-#define __ARCH_WANT_SYS_OLDUMOUNT
-#define __ARCH_WANT_SYS_SIGPENDING
-#define __ARCH_WANT_SYS_SIGPROCMASK
-#define __ARCH_WANT_SYS_RT_SIGACTION
-#define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
-
-#endif /* __ASSEMBLY__ */
-
-#undef STR
-
-/*
- * "Conditional" syscalls
- *
- * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
- * but it doesn't work on all toolchains, so we just do it by hand
- */
-#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
-
-#endif /* __KERNEL__ */
-#endif /* _ASM_PARISC_UNISTD_H_ */
diff --git a/include/asm-parisc/unwind.h b/include/asm-parisc/unwind.h
deleted file mode 100644
index 2f7e6e50a158..000000000000
--- a/include/asm-parisc/unwind.h
+++ /dev/null
@@ -1,77 +0,0 @@
-#ifndef _UNWIND_H_
-#define _UNWIND_H_
-
-#include <linux/list.h>
-
-/* From ABI specifications */
-struct unwind_table_entry {
-	unsigned int region_start;
-	unsigned int region_end;
-	unsigned int Cannot_unwind:1; /* 0 */
-	unsigned int Millicode:1;	/* 1 */
-	unsigned int Millicode_save_sr0:1;	/* 2 */
-	unsigned int Region_description:2;	/* 3..4 */
-	unsigned int reserved1:1;	/* 5 */
-	unsigned int Entry_SR:1;	/* 6 */
-	unsigned int Entry_FR:4;	/* number saved *//* 7..10 */
-	unsigned int Entry_GR:5;	/* number saved *//* 11..15 */
-	unsigned int Args_stored:1;	/* 16 */
-	unsigned int Variable_Frame:1;	/* 17 */
-	unsigned int Separate_Package_Body:1;	/* 18 */
-	unsigned int Frame_Extension_Millicode:1;	/* 19 */
-	unsigned int Stack_Overflow_Check:1;	/* 20 */
-	unsigned int Two_Instruction_SP_Increment:1;	/* 21 */
-	unsigned int Ada_Region:1;	/* 22 */
-	unsigned int cxx_info:1;	/* 23 */
-	unsigned int cxx_try_catch:1;	/* 24 */
-	unsigned int sched_entry_seq:1;	/* 25 */
-	unsigned int reserved2:1;	/* 26 */
-	unsigned int Save_SP:1;	/* 27 */
-	unsigned int Save_RP:1;	/* 28 */
-	unsigned int Save_MRP_in_frame:1;	/* 29 */
-	unsigned int extn_ptr_defined:1;	/* 30 */
-	unsigned int Cleanup_defined:1;	/* 31 */
-	
-	unsigned int MPE_XL_interrupt_marker:1;	/* 0 */
-	unsigned int HP_UX_interrupt_marker:1;	/* 1 */
-	unsigned int Large_frame:1;	/* 2 */
-	unsigned int Pseudo_SP_Set:1;	/* 3 */
-	unsigned int reserved4:1;	/* 4 */
-	unsigned int Total_frame_size:27;	/* 5..31 */
-};
-
-struct unwind_table {
-	struct list_head list;
-	const char *name;
-	unsigned long gp;
-	unsigned long base_addr;
-	unsigned long start;
-	unsigned long end;
-	const struct unwind_table_entry *table;
-	unsigned long length;
-};
-
-struct unwind_frame_info {
-	struct task_struct *t;
-	/* Eventually we would like to be able to get at any of the registers
-	   available; but for now we only try to get the sp and ip for each
-	   frame */
-	/* struct pt_regs regs; */
-	unsigned long sp, ip, rp, r31;
-	unsigned long prev_sp, prev_ip;
-};
-
-struct unwind_table *
-unwind_table_add(const char *name, unsigned long base_addr, 
-		 unsigned long gp, void *start, void *end);
-void
-unwind_table_remove(struct unwind_table *table);
-
-void unwind_frame_init(struct unwind_frame_info *info, struct task_struct *t, 
-		       struct pt_regs *regs);
-void unwind_frame_init_from_blocked_task(struct unwind_frame_info *info, struct task_struct *t);
-void unwind_frame_init_running(struct unwind_frame_info *info, struct pt_regs *regs);
-int unwind_once(struct unwind_frame_info *info);
-int unwind_to_user(struct unwind_frame_info *info);
-
-#endif
diff --git a/include/asm-parisc/user.h b/include/asm-parisc/user.h
deleted file mode 100644
index 80224753e508..000000000000
--- a/include/asm-parisc/user.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* This file should not exist, but lots of generic code still includes
-   it. It's a hangover from old a.out days and the traditional core
-   dump format.  We are ELF-only, and so are our core dumps.  If we
-   need to support HP/UX core format then we'll do it here
-   eventually. */
diff --git a/include/asm-parisc/vga.h b/include/asm-parisc/vga.h
deleted file mode 100644
index 171399a88ca6..000000000000
--- a/include/asm-parisc/vga.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_PARISC_VGA_H__
-#define __ASM_PARISC_VGA_H__
-
-/* nothing */
-
-#endif /* __ASM_PARISC_VGA_H__ */
diff --git a/include/asm-parisc/xor.h b/include/asm-parisc/xor.h
deleted file mode 100644
index c82eb12a5b18..000000000000
--- a/include/asm-parisc/xor.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/xor.h>
-- 
cgit v1.2.3


From a3cdcbfa8fb1fccfe48d359da86e99546610c562 Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Fri, 10 Oct 2008 12:01:37 -0700
Subject: mlx4_core: Add QP range reservation support

To allow allocating an aligned range of consecutive QP numbers, add an
interface to reserve an aligned range of QP numbers and have the QP
allocation function always take a QP number.

This will be used for RSS support in the mlx4_en Ethernet driver and
also potentially by IPoIB RSS support.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/mlx4/qp.c | 21 ++++++++++--
 drivers/net/mlx4/alloc.c        | 74 ++++++++++++++++++++++++++++++++++++++++-
 drivers/net/mlx4/mlx4.h         |  2 ++
 drivers/net/mlx4/qp.c           | 45 +++++++++++++++++--------
 include/linux/mlx4/device.h     |  5 ++-
 5 files changed, 129 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index baa01deb2436..39167a797f99 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -451,6 +451,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			    struct ib_qp_init_attr *init_attr,
 			    struct ib_udata *udata, int sqpn, struct mlx4_ib_qp *qp)
 {
+	int qpn;
 	int err;
 
 	mutex_init(&qp->mutex);
@@ -545,9 +546,17 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		}
 	}
 
-	err = mlx4_qp_alloc(dev->dev, sqpn, &qp->mqp);
+	if (sqpn) {
+		qpn = sqpn;
+	} else {
+		err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn);
+		if (err)
+			goto err_wrid;
+	}
+
+	err = mlx4_qp_alloc(dev->dev, qpn, &qp->mqp);
 	if (err)
-		goto err_wrid;
+		goto err_qpn;
 
 	/*
 	 * Hardware wants QPN written in big-endian order (after
@@ -560,6 +569,10 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 
 	return 0;
 
+err_qpn:
+	if (!sqpn)
+		mlx4_qp_release_range(dev->dev, qpn, 1);
+
 err_wrid:
 	if (pd->uobject) {
 		if (!init_attr->srq)
@@ -655,6 +668,10 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 	mlx4_ib_unlock_cqs(send_cq, recv_cq);
 
 	mlx4_qp_free(dev->dev, &qp->mqp);
+
+	if (!is_sqp(dev, qp))
+		mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1);
+
 	mlx4_mtt_cleanup(dev->dev, &qp->mtt);
 
 	if (is_user) {
diff --git a/drivers/net/mlx4/alloc.c b/drivers/net/mlx4/alloc.c
index 096bca54bcf7..e6c0d5bb5dcb 100644
--- a/drivers/net/mlx4/alloc.c
+++ b/drivers/net/mlx4/alloc.c
@@ -65,10 +65,82 @@ u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap)
 
 void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj)
 {
+	mlx4_bitmap_free_range(bitmap, obj, 1);
+}
+
+static unsigned long find_aligned_range(unsigned long *bitmap,
+					u32 start, u32 nbits,
+					int len, int align)
+{
+	unsigned long end, i;
+
+again:
+	start = ALIGN(start, align);
+
+	while ((start < nbits) && test_bit(start, bitmap))
+		start += align;
+
+	if (start >= nbits)
+		return -1;
+
+	end = start+len;
+	if (end > nbits)
+		return -1;
+
+	for (i = start + 1; i < end; i++) {
+		if (test_bit(i, bitmap)) {
+			start = i + 1;
+			goto again;
+		}
+	}
+
+	return start;
+}
+
+u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align)
+{
+	u32 obj, i;
+
+	if (likely(cnt == 1 && align == 1))
+		return mlx4_bitmap_alloc(bitmap);
+
+	spin_lock(&bitmap->lock);
+
+	obj = find_aligned_range(bitmap->table, bitmap->last,
+				 bitmap->max, cnt, align);
+	if (obj >= bitmap->max) {
+		bitmap->top = (bitmap->top + bitmap->max) & bitmap->mask;
+		obj = find_aligned_range(bitmap->table, 0,
+					 bitmap->max,
+					 cnt, align);
+	}
+
+	if (obj < bitmap->max) {
+		for (i = 0; i < cnt; i++)
+			set_bit(obj + i, bitmap->table);
+		if (obj == bitmap->last) {
+			bitmap->last = (obj + cnt);
+			if (bitmap->last >= bitmap->max)
+				bitmap->last = 0;
+		}
+		obj |= bitmap->top;
+	} else
+		obj = -1;
+
+	spin_unlock(&bitmap->lock);
+
+	return obj;
+}
+
+void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt)
+{
+	u32 i;
+
 	obj &= bitmap->max - 1;
 
 	spin_lock(&bitmap->lock);
-	clear_bit(obj, bitmap->table);
+	for (i = 0; i < cnt; i++)
+		clear_bit(obj + i, bitmap->table);
 	bitmap->last = min(bitmap->last, obj);
 	bitmap->top = (bitmap->top + bitmap->max) & bitmap->mask;
 	spin_unlock(&bitmap->lock);
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index 5337e3ac3e78..b55ddab73f66 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -288,6 +288,8 @@ static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
 
 u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap);
 void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj);
+u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align);
+void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt);
 int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask, u32 reserved);
 void mlx4_bitmap_cleanup(struct mlx4_bitmap *bitmap);
 
diff --git a/drivers/net/mlx4/qp.c b/drivers/net/mlx4/qp.c
index c49a86044bf7..98e0c40ba368 100644
--- a/drivers/net/mlx4/qp.c
+++ b/drivers/net/mlx4/qp.c
@@ -147,19 +147,42 @@ int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 }
 EXPORT_SYMBOL_GPL(mlx4_qp_modify);
 
-int mlx4_qp_alloc(struct mlx4_dev *dev, int sqpn, struct mlx4_qp *qp)
+int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_qp_table *qp_table = &priv->qp_table;
+	int qpn;
+
+	qpn = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align);
+	if (qpn == -1)
+		return -ENOMEM;
+
+	*base = qpn;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_qp_reserve_range);
+
+void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_qp_table *qp_table = &priv->qp_table;
+	if (base_qpn < dev->caps.sqp_start + 8)
+		return;
+
+	mlx4_bitmap_free_range(&qp_table->bitmap, base_qpn, cnt);
+}
+EXPORT_SYMBOL_GPL(mlx4_qp_release_range);
+
+int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_qp_table *qp_table = &priv->qp_table;
 	int err;
 
-	if (sqpn)
-		qp->qpn = sqpn;
-	else {
-		qp->qpn = mlx4_bitmap_alloc(&qp_table->bitmap);
-		if (qp->qpn == -1)
-			return -ENOMEM;
-	}
+	if (!qpn)
+		return -EINVAL;
+
+	qp->qpn = qpn;
 
 	err = mlx4_table_get(dev, &qp_table->qp_table, qp->qpn);
 	if (err)
@@ -208,9 +231,6 @@ err_put_qp:
 	mlx4_table_put(dev, &qp_table->qp_table, qp->qpn);
 
 err_out:
-	if (!sqpn)
-		mlx4_bitmap_free(&qp_table->bitmap, qp->qpn);
-
 	return err;
 }
 EXPORT_SYMBOL_GPL(mlx4_qp_alloc);
@@ -239,9 +259,6 @@ void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp)
 	mlx4_table_put(dev, &qp_table->altc_table, qp->qpn);
 	mlx4_table_put(dev, &qp_table->auxc_table, qp->qpn);
 	mlx4_table_put(dev, &qp_table->qp_table, qp->qpn);
-
-	if (qp->qpn >= dev->caps.sqp_start + 8)
-		mlx4_bitmap_free(&qp_table->bitmap, qp->qpn);
 }
 EXPORT_SYMBOL_GPL(mlx4_qp_free);
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index b2f944468313..d21e879f3c90 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -400,7 +400,10 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 		  int collapsed);
 void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq);
 
-int mlx4_qp_alloc(struct mlx4_dev *dev, int sqpn, struct mlx4_qp *qp);
+int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base);
+void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
+
+int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp);
 void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp);
 
 int mlx4_srq_alloc(struct mlx4_dev *dev, u32 pdn, struct mlx4_mtt *mtt,
-- 
cgit v1.2.3


From db89b4f0dbab837d0f3de2c3e9427a8d5393afa3 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@suse.cz>
Date: Mon, 22 Sep 2008 14:37:34 -0700
Subject: ACPI: catch calls of acpi_driver_data on pointer of wrong type

Catch attempts to use of acpi_driver_data on pointers of wrong type.

akpm: rewritten to use proper C typechecking and remove the
"function"-used-as-lvalue thing.

Signed-off-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/ac.c              | 2 +-
 drivers/acpi/acpi_memhotplug.c | 2 +-
 drivers/acpi/asus_acpi.c       | 2 +-
 drivers/acpi/battery.c         | 2 +-
 drivers/acpi/button.c          | 2 +-
 drivers/acpi/container.c       | 2 +-
 drivers/acpi/ec.c              | 4 ++--
 drivers/acpi/fan.c             | 2 +-
 drivers/acpi/pci_link.c        | 2 +-
 drivers/acpi/pci_root.c        | 2 +-
 drivers/acpi/power.c           | 4 ++--
 drivers/acpi/processor_core.c  | 2 +-
 drivers/acpi/sbs.c             | 2 +-
 drivers/acpi/sbshc.c           | 4 ++--
 drivers/acpi/scan.c            | 4 ++--
 drivers/acpi/thermal.c         | 2 +-
 drivers/acpi/video.c           | 6 +++---
 drivers/misc/asus-laptop.c     | 2 +-
 drivers/misc/eeepc-laptop.c    | 2 +-
 drivers/misc/fujitsu-laptop.c  | 4 ++--
 drivers/misc/intel_menlow.c    | 2 +-
 drivers/misc/thinkpad_acpi.c   | 2 +-
 include/acpi/acpi_bus.h        | 6 +++++-
 23 files changed, 34 insertions(+), 30 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 831883b7d6c9..8b6a84a43b15 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -269,7 +269,7 @@ static int acpi_ac_add(struct acpi_device *device)
 	ac->device = device;
 	strcpy(acpi_device_name(device), ACPI_AC_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_AC_CLASS);
-	acpi_driver_data(device) = ac;
+	device->driver_data = ac;
 
 	result = acpi_ac_get_state(ac);
 	if (result)
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 5f1127ad5a95..afd955fc0dc2 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -403,7 +403,7 @@ static int acpi_memory_device_add(struct acpi_device *device)
 	mem_device->device = device;
 	sprintf(acpi_device_name(device), "%s", ACPI_MEMORY_DEVICE_NAME);
 	sprintf(acpi_device_class(device), "%s", ACPI_MEMORY_DEVICE_CLASS);
-	acpi_driver_data(device) = mem_device;
+	device->driver_data = mem_device;
 
 	/* Get the range from the _CRS */
 	result = acpi_memory_get_device_resources(mem_device);
diff --git a/drivers/acpi/asus_acpi.c b/drivers/acpi/asus_acpi.c
index d3d0886d637f..91571fc0f17d 100644
--- a/drivers/acpi/asus_acpi.c
+++ b/drivers/acpi/asus_acpi.c
@@ -1321,7 +1321,7 @@ static int asus_hotk_add(struct acpi_device *device)
 	hotk->handle = device->handle;
 	strcpy(acpi_device_name(device), ACPI_HOTK_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_HOTK_CLASS);
-	acpi_driver_data(device) = hotk;
+	device->driver_data = hotk;
 	hotk->device = device;
 
 	result = asus_hotk_check();
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index b1c723f9f58d..de8046933bce 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -804,7 +804,7 @@ static int acpi_battery_add(struct acpi_device *device)
 	battery->device = device;
 	strcpy(acpi_device_name(device), ACPI_BATTERY_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_BATTERY_CLASS);
-	acpi_driver_data(device) = battery;
+	device->driver_data = battery;
 	mutex_init(&battery->lock);
 	acpi_battery_update(battery);
 #ifdef CONFIG_ACPI_PROCFS_POWER
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 1dfec413588c..e22033ea2614 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -384,7 +384,7 @@ static int acpi_button_add(struct acpi_device *device)
 		return -ENOMEM;
 
 	button->device = device;
-	acpi_driver_data(device) = button;
+	device->driver_data = button;
 
 	button->input = input = input_allocate_device();
 	if (!input) {
diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c
index 3c25ec7a1871..03ea8478e393 100644
--- a/drivers/acpi/container.c
+++ b/drivers/acpi/container.c
@@ -108,7 +108,7 @@ static int acpi_container_add(struct acpi_device *device)
 	container->handle = device->handle;
 	strcpy(acpi_device_name(device), ACPI_CONTAINER_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_CONTAINER_CLASS);
-	acpi_driver_data(device) = container;
+	device->driver_data = container;
 
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device <%s> bid <%s>\n",
 			  acpi_device_name(device), acpi_device_bid(device)));
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 13593f9f2197..5741d99d6034 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -788,7 +788,7 @@ static int acpi_ec_add(struct acpi_device *device)
 
 	if (!first_ec)
 		first_ec = ec;
-	acpi_driver_data(device) = ec;
+	device->driver_data = ec;
 	acpi_ec_add_fs(device);
 	pr_info(PREFIX "GPE = 0x%lx, I/O: command/status = 0x%lx, data = 0x%lx\n",
 			  ec->gpe, ec->command_addr, ec->data_addr);
@@ -813,7 +813,7 @@ static int acpi_ec_remove(struct acpi_device *device, int type)
 	}
 	mutex_unlock(&ec->lock);
 	acpi_ec_remove_fs(device);
-	acpi_driver_data(device) = NULL;
+	device->driver_data = NULL;
 	if (ec == first_ec)
 		first_ec = NULL;
 	kfree(ec);
diff --git a/drivers/acpi/fan.c b/drivers/acpi/fan.c
index 2655bc1b4eeb..e603e4070702 100644
--- a/drivers/acpi/fan.c
+++ b/drivers/acpi/fan.c
@@ -265,7 +265,7 @@ static int acpi_fan_add(struct acpi_device *device)
 
 	dev_info(&device->dev, "registered as cooling_device%d\n", cdev->id);
 
-	acpi_driver_data(device) = cdev;
+	device->driver_data = cdev;
 	result = sysfs_create_link(&device->dev.kobj,
 				   &cdev->device.kobj,
 				   "thermal_cooling");
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index cf47805a7448..54cd77a0a78e 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -737,7 +737,7 @@ static int acpi_pci_link_add(struct acpi_device *device)
 	link->device = device;
 	strcpy(acpi_device_name(device), ACPI_PCI_LINK_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_PCI_LINK_CLASS);
-	acpi_driver_data(device) = link;
+	device->driver_data = link;
 
 	mutex_lock(&acpi_link_lock);
 	result = acpi_pci_link_get_possible(link);
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index c3fed31166b5..add1a19bbbfe 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -206,7 +206,7 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 	root->device = device;
 	strcpy(acpi_device_name(device), ACPI_PCI_ROOT_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_PCI_ROOT_CLASS);
-	acpi_driver_data(device) = root;
+	device->driver_data = root;
 
 	device->ops.bind = acpi_pci_bind;
 
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 4ab21cb1c8c7..1bef9429189b 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -657,7 +657,7 @@ static int acpi_power_add(struct acpi_device *device)
 	strcpy(resource->name, device->pnp.bus_id);
 	strcpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_POWER_CLASS);
-	acpi_driver_data(device) = resource;
+	device->driver_data = resource;
 
 	/* Evalute the object to get the system level and resource order. */
 	status = acpi_evaluate_object(device->handle, NULL, NULL, &buffer);
@@ -733,7 +733,7 @@ static int acpi_power_resume(struct acpi_device *device)
 	if (!device || !acpi_driver_data(device))
 		return -EINVAL;
 
-	resource = (struct acpi_power_resource *)acpi_driver_data(device);
+	resource = acpi_driver_data(device);
 
 	result = acpi_power_get_state(resource, &state);
 	if (result)
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index ee68ac54c0d4..289461649196 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -818,7 +818,7 @@ static int acpi_processor_add(struct acpi_device *device)
 	pr->handle = device->handle;
 	strcpy(acpi_device_name(device), ACPI_PROCESSOR_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_PROCESSOR_CLASS);
-	acpi_driver_data(device) = pr;
+	device->driver_data = pr;
 
 	return 0;
 }
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index 10a36512647c..d0033250b5a9 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -931,7 +931,7 @@ static int acpi_sbs_add(struct acpi_device *device)
 	sbs->device = device;
 	strcpy(acpi_device_name(device), ACPI_SBS_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_SBS_CLASS);
-	acpi_driver_data(device) = sbs;
+	device->driver_data = sbs;
 
 	result = acpi_charger_add(sbs);
 	if (result)
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index a4e3767b8c64..001d9143a2cb 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -282,7 +282,7 @@ static int acpi_smbus_hc_add(struct acpi_device *device)
 	hc->ec = acpi_driver_data(device->parent);
 	hc->offset = (val >> 8) & 0xff;
 	hc->query_bit = val & 0xff;
-	acpi_driver_data(device) = hc;
+	device->driver_data = hc;
 
 	acpi_ec_add_query_handler(hc->ec, hc->query_bit, NULL, smbus_alarm, hc);
 	printk(KERN_INFO PREFIX "SBS HC: EC = 0x%p, offset = 0x%0x, query_bit = 0x%0x\n",
@@ -303,7 +303,7 @@ static int acpi_smbus_hc_remove(struct acpi_device *device, int type)
 	hc = acpi_driver_data(device);
 	acpi_ec_remove_query_handler(hc->ec, hc->query_bit);
 	kfree(hc);
-	acpi_driver_data(device) = NULL;
+	device->driver_data = NULL;
 	return 0;
 }
 
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index e7b8853c310b..b88536ab040a 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -384,7 +384,7 @@ static int acpi_device_remove(struct device * dev)
 			acpi_drv->ops.remove(acpi_dev, acpi_dev->removal_type);
 	}
 	acpi_dev->driver = NULL;
-	acpi_driver_data(acpi_dev) = NULL;
+	acpi_dev->driver_data = NULL;
 
 	put_device(dev);
 	return 0;
@@ -537,7 +537,7 @@ acpi_bus_driver_init(struct acpi_device *device, struct acpi_driver *driver)
 	result = driver->ops.add(device);
 	if (result) {
 		device->driver = NULL;
-		acpi_driver_data(device) = NULL;
+		device->driver_data = NULL;
 		return result;
 	}
 
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 912703691d36..e052a75c29ce 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -1647,7 +1647,7 @@ static int acpi_thermal_add(struct acpi_device *device)
 	strcpy(tz->name, device->pnp.bus_id);
 	strcpy(acpi_device_name(device), ACPI_THERMAL_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_THERMAL_CLASS);
-	acpi_driver_data(device) = tz;
+	device->driver_data = tz;
 	mutex_init(&tz->lock);
 
 
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index e8a51a1700f7..85c6554bcb4c 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -1491,7 +1491,7 @@ acpi_video_bus_get_one_device(struct acpi_device *device,
 
 		strcpy(acpi_device_name(device), ACPI_VIDEO_DEVICE_NAME);
 		strcpy(acpi_device_class(device), ACPI_VIDEO_CLASS);
-		acpi_driver_data(device) = data;
+		device->driver_data = data;
 
 		data->device_id = device_id;
 		data->video = video;
@@ -1982,7 +1982,7 @@ static int acpi_video_bus_add(struct acpi_device *device)
 	video->device = device;
 	strcpy(acpi_device_name(device), ACPI_VIDEO_BUS_NAME);
 	strcpy(acpi_device_class(device), ACPI_VIDEO_CLASS);
-	acpi_driver_data(device) = video;
+	device->driver_data = video;
 
 	acpi_video_bus_find_cap(video);
 	error = acpi_video_bus_check(video);
@@ -2058,7 +2058,7 @@ static int acpi_video_bus_add(struct acpi_device *device)
 	acpi_video_bus_remove_fs(device);
  err_free_video:
 	kfree(video);
-	acpi_driver_data(device) = NULL;
+	device->driver_data = NULL;
 
 	return error;
 }
diff --git a/drivers/misc/asus-laptop.c b/drivers/misc/asus-laptop.c
index 7c6dfd03de9f..de82f2f5a813 100644
--- a/drivers/misc/asus-laptop.c
+++ b/drivers/misc/asus-laptop.c
@@ -996,7 +996,7 @@ static int asus_hotk_add(struct acpi_device *device)
 	hotk->handle = device->handle;
 	strcpy(acpi_device_name(device), ASUS_HOTK_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ASUS_HOTK_CLASS);
-	acpi_driver_data(device) = hotk;
+	device->driver_data = hotk;
 	hotk->device = device;
 
 	result = asus_hotk_check();
diff --git a/drivers/misc/eeepc-laptop.c b/drivers/misc/eeepc-laptop.c
index 1ee8501e90f1..c1247056116c 100644
--- a/drivers/misc/eeepc-laptop.c
+++ b/drivers/misc/eeepc-laptop.c
@@ -411,7 +411,7 @@ static int eeepc_hotk_add(struct acpi_device *device)
 	ehotk->handle = device->handle;
 	strcpy(acpi_device_name(device), EEEPC_HOTK_DEVICE_NAME);
 	strcpy(acpi_device_class(device), EEEPC_HOTK_CLASS);
-	acpi_driver_data(device) = ehotk;
+	device->driver_data = ehotk;
 	ehotk->device = device;
 	result = eeepc_hotk_check();
 	if (result)
diff --git a/drivers/misc/fujitsu-laptop.c b/drivers/misc/fujitsu-laptop.c
index 3e56203e4947..7b69cfb7de5d 100644
--- a/drivers/misc/fujitsu-laptop.c
+++ b/drivers/misc/fujitsu-laptop.c
@@ -490,7 +490,7 @@ static int acpi_fujitsu_add(struct acpi_device *device)
 	fujitsu->acpi_handle = device->handle;
 	sprintf(acpi_device_name(device), "%s", ACPI_FUJITSU_DEVICE_NAME);
 	sprintf(acpi_device_class(device), "%s", ACPI_FUJITSU_CLASS);
-	acpi_driver_data(device) = fujitsu;
+	device->driver_data = fujitsu;
 
 	status = acpi_install_notify_handler(device->handle,
 					     ACPI_DEVICE_NOTIFY,
@@ -703,7 +703,7 @@ static int acpi_fujitsu_hotkey_add(struct acpi_device *device)
 	sprintf(acpi_device_name(device), "%s",
 		ACPI_FUJITSU_HOTKEY_DEVICE_NAME);
 	sprintf(acpi_device_class(device), "%s", ACPI_FUJITSU_CLASS);
-	acpi_driver_data(device) = fujitsu_hotkey;
+	device->driver_data = fujitsu_hotkey;
 
 	status = acpi_install_notify_handler(device->handle,
 					     ACPI_DEVICE_NOTIFY,
diff --git a/drivers/misc/intel_menlow.c b/drivers/misc/intel_menlow.c
index 80a136352408..cd3ea7faa5b6 100644
--- a/drivers/misc/intel_menlow.c
+++ b/drivers/misc/intel_menlow.c
@@ -175,7 +175,7 @@ static int intel_menlow_memory_add(struct acpi_device *device)
 		goto end;
 	}
 
-	acpi_driver_data(device) = cdev;
+	device->driver_data = cdev;
 	result = sysfs_create_link(&device->dev.kobj,
 				&cdev->device.kobj, "thermal_cooling");
 	if (result)
diff --git a/drivers/misc/thinkpad_acpi.c b/drivers/misc/thinkpad_acpi.c
index 6b9300779a43..62aebaa85913 100644
--- a/drivers/misc/thinkpad_acpi.c
+++ b/drivers/misc/thinkpad_acpi.c
@@ -543,7 +543,7 @@ static int __init setup_acpi_notify(struct ibm_struct *ibm)
 		return -ENODEV;
 	}
 
-	acpi_driver_data(ibm->acpi->device) = ibm;
+	ibm->acpi->device->driver_data = ibm;
 	sprintf(acpi_device_class(ibm->acpi->device), "%s/%s",
 		TPACPI_ACPI_EVENT_PREFIX,
 		ibm->name);
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index a5ac0bc7f52e..47682465f1f5 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -300,7 +300,11 @@ struct acpi_device {
 	enum acpi_bus_removal_type removal_type;	/* indicate for different removal type */
 };
 
-#define acpi_driver_data(d)	((d)->driver_data)
+static inline void *acpi_driver_data(struct acpi_device *d)
+{
+	return d->driver_data;
+}
+
 #define to_acpi_device(d)	container_of(d, struct acpi_device, dev)
 #define to_acpi_driver(d)	container_of(d, struct acpi_driver, drv)
 
-- 
cgit v1.2.3


From 061b1bd394ca8628b7c24eb4658ba3535da4249a Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@suse.de>
Date: Wed, 24 Sep 2008 14:46:44 -0700
Subject: Staging: add TAINT_CRAP for all drivers/staging code

We need to add a flag for all code that is in the drivers/staging/
directory to prevent all other kernel developers from worrying about
issues here, and to notify users that the drivers might not be as good
as they are normally used to.

Based on code from Andreas Gruenbacher and Jeff Mahoney to provide a
TAINT flag for the support level of a kernel module in the Novell
enterprise kernel release.

This is the kernel portion of this feature, the ability for the flag to
be set needs to be done in the build process and will happen in a
follow-up patch.

Cc: Andreas Gruenbacher <agruen@suse.de>
Cc: Jeff Mahoney <jeffm@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 Documentation/sysctl/kernel.txt |  1 +
 include/linux/kernel.h          |  1 +
 kernel/module.c                 | 11 +++++++++++
 kernel/panic.c                  |  6 ++++--
 4 files changed, 17 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index e1ff0d920a5c..bde799e06598 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -369,4 +369,5 @@ can be ORed together:
   2 - A module was force loaded by insmod -f.
       Set by modutils >= 2.4.9 and module-init-tools.
   4 - Unsafe SMP processors: SMP with CPUs not designed for SMP.
+ 64 - A module from drivers/staging was loaded.
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 2651f805ba6d..b36805cb95fb 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -260,6 +260,7 @@ extern enum system_states {
 #define TAINT_DIE			(1<<7)
 #define TAINT_OVERRIDDEN_ACPI_TABLE	(1<<8)
 #define TAINT_WARN			(1<<9)
+#define TAINT_CRAP			(1<<10)
 
 extern void dump_stack(void) __cold;
 
diff --git a/kernel/module.c b/kernel/module.c
index 9db11911e04b..152b1655bbac 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1806,6 +1806,7 @@ static noinline struct module *load_module(void __user *umod,
 	Elf_Ehdr *hdr;
 	Elf_Shdr *sechdrs;
 	char *secstrings, *args, *modmagic, *strtab = NULL;
+	char *staging;
 	unsigned int i;
 	unsigned int symindex = 0;
 	unsigned int strindex = 0;
@@ -1960,6 +1961,14 @@ static noinline struct module *load_module(void __user *umod,
 		goto free_hdr;
 	}
 
+	staging = get_modinfo(sechdrs, infoindex, "staging");
+	if (staging) {
+		add_taint_module(mod, TAINT_CRAP);
+		printk(KERN_WARNING "%s: module is from the staging directory,"
+		       " the quality is unknown, you have been warned.\n",
+		       mod->name);
+	}
+
 	/* Now copy in args */
 	args = strndup_user(uargs, ~0UL >> 1);
 	if (IS_ERR(args)) {
@@ -2556,6 +2565,8 @@ static char *module_flags(struct module *mod, char *buf)
 			buf[bx++] = 'P';
 		if (mod->taints & TAINT_FORCED_MODULE)
 			buf[bx++] = 'F';
+		if (mod->taints & TAINT_CRAP)
+			buf[bx++] = 'C';
 		/*
 		 * TAINT_FORCED_RMMOD: could be added.
 		 * TAINT_UNSAFE_SMP, TAINT_MACHINE_CHECK, TAINT_BAD_PAGE don't
diff --git a/kernel/panic.c b/kernel/panic.c
index 12c5a0a6c89b..98e2047f4db7 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -155,6 +155,7 @@ EXPORT_SYMBOL(panic);
  *  'U' - Userspace-defined naughtiness.
  *  'A' - ACPI table overridden.
  *  'W' - Taint on warning.
+ *  'C' - modules from drivers/staging are loaded.
  *
  *	The string is overwritten by the next call to print_taint().
  */
@@ -163,7 +164,7 @@ const char *print_tainted(void)
 {
 	static char buf[20];
 	if (tainted) {
-		snprintf(buf, sizeof(buf), "Tainted: %c%c%c%c%c%c%c%c%c%c",
+		snprintf(buf, sizeof(buf), "Tainted: %c%c%c%c%c%c%c%c%c%c%c",
 			tainted & TAINT_PROPRIETARY_MODULE ? 'P' : 'G',
 			tainted & TAINT_FORCED_MODULE ? 'F' : ' ',
 			tainted & TAINT_UNSAFE_SMP ? 'S' : ' ',
@@ -173,7 +174,8 @@ const char *print_tainted(void)
 			tainted & TAINT_USER ? 'U' : ' ',
 			tainted & TAINT_DIE ? 'D' : ' ',
 			tainted & TAINT_OVERRIDDEN_ACPI_TABLE ? 'A' : ' ',
-			tainted & TAINT_WARN ? 'W' : ' ');
+			tainted & TAINT_WARN ? 'W' : ' ',
+			tainted & TAINT_CRAP ? 'C' : ' ');
 	}
 	else
 		snprintf(buf, sizeof(buf), "Not tainted");
-- 
cgit v1.2.3


From c865d2f6eb160c15b74245b4891c8e945d67d96c Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bjorn.helgaas@hp.com>
Date: Tue, 19 Aug 2008 16:53:26 -0600
Subject: PNP: convert the last few pnp_info() uses to printk()

There are only a few remaining uses of pnp_info(), so I just
converted them to printk and removed the pnp_err(), pnp_info(),
pnp_warn(), and pnp_dbg() wrappers.

I also removed a couple debug messages that don't seem useful any
more ("driver registered", "driver unregistered", "driver attached").

Signed-off-by: Bjorn Helgaas <bjorn.helgaas@hp.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/pnp/driver.c       |  4 ----
 drivers/pnp/pnpacpi/core.c |  6 +++---
 include/linux/pnp.h        | 10 ----------
 3 files changed, 3 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/pnp/driver.c b/drivers/pnp/driver.c
index d3f869ee1d92..54673a4f5901 100644
--- a/drivers/pnp/driver.c
+++ b/drivers/pnp/driver.c
@@ -114,7 +114,6 @@ static int pnp_device_probe(struct device *dev)
 	} else
 		goto fail;
 
-	dev_dbg(dev, "driver attached\n");
 	return error;
 
 fail:
@@ -210,8 +209,6 @@ struct bus_type pnp_bus_type = {
 
 int pnp_register_driver(struct pnp_driver *drv)
 {
-	pnp_dbg("the driver '%s' has been registered", drv->name);
-
 	drv->driver.name = drv->name;
 	drv->driver.bus = &pnp_bus_type;
 
@@ -221,7 +218,6 @@ int pnp_register_driver(struct pnp_driver *drv)
 void pnp_unregister_driver(struct pnp_driver *drv)
 {
 	driver_unregister(&drv->driver);
-	pnp_dbg("the driver '%s' has been unregistered", drv->name);
 }
 
 /**
diff --git a/drivers/pnp/pnpacpi/core.c b/drivers/pnp/pnpacpi/core.c
index c1b9ea34977b..67c651bcaf71 100644
--- a/drivers/pnp/pnpacpi/core.c
+++ b/drivers/pnp/pnpacpi/core.c
@@ -255,14 +255,14 @@ int pnpacpi_disabled __initdata;
 static int __init pnpacpi_init(void)
 {
 	if (acpi_disabled || pnpacpi_disabled) {
-		pnp_info("PnP ACPI: disabled");
+		printk(KERN_INFO "pnp: PnP ACPI: disabled\n");
 		return 0;
 	}
-	pnp_info("PnP ACPI init");
+	printk(KERN_INFO "pnp: PnP ACPI init\n");
 	pnp_register_protocol(&pnpacpi_protocol);
 	register_acpi_bus_type(&acpi_pnp_bus);
 	acpi_get_devices(NULL, pnpacpi_add_device_handler, NULL, NULL);
-	pnp_info("PnP ACPI: found %d devices", num);
+	printk(KERN_INFO "pnp: PnP ACPI: found %d devices\n", num);
 	unregister_acpi_bus_type(&acpi_pnp_bus);
 	pnp_platform_devices = 1;
 	return 0;
diff --git a/include/linux/pnp.h b/include/linux/pnp.h
index be764e514e35..05daecec16c5 100644
--- a/include/linux/pnp.h
+++ b/include/linux/pnp.h
@@ -483,14 +483,4 @@ static inline void pnp_unregister_driver(struct pnp_driver *drv) { }
 
 #endif /* CONFIG_PNP */
 
-#define pnp_err(format, arg...) printk(KERN_ERR "pnp: " format "\n" , ## arg)
-#define pnp_info(format, arg...) printk(KERN_INFO "pnp: " format "\n" , ## arg)
-#define pnp_warn(format, arg...) printk(KERN_WARNING "pnp: " format "\n" , ## arg)
-
-#ifdef CONFIG_PNP_DEBUG
-#define pnp_dbg(format, arg...) printk(KERN_DEBUG "pnp: " format "\n" , ## arg)
-#else
-#define pnp_dbg(format, arg...) do {} while (0)
-#endif
-
 #endif /* _LINUX_PNP_H */
-- 
cgit v1.2.3


From fa89b6089b5f4c7a5244b642caaca3e72b06ebe4 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Wed, 24 Sep 2008 19:04:32 -0700
Subject: ACPI: remove unused have_arch_parse_srat

This was a workaround for 32bit numa SRAT processing, and we removed those
workarounds, making 32 bit more like 64 bit.  HAVE_ARCH_PARSE_SRAT is no
longer defined anywhere.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 include/linux/acpi.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 702f79dad16a..fd6a452b0ceb 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -94,18 +94,10 @@ int acpi_parse_mcfg (struct acpi_table_header *header);
 void acpi_table_print_madt_entry (struct acpi_subtable_header *madt);
 
 /* the following four functions are architecture-dependent */
-#ifdef CONFIG_HAVE_ARCH_PARSE_SRAT
-#define NR_NODE_MEMBLKS MAX_NUMNODES
-#define acpi_numa_slit_init(slit) do {} while (0)
-#define acpi_numa_processor_affinity_init(pa) do {} while (0)
-#define acpi_numa_memory_affinity_init(ma) do {} while (0)
-#define acpi_numa_arch_fixup() do {} while (0)
-#else
 void acpi_numa_slit_init (struct acpi_table_slit *slit);
 void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa);
 void acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma);
 void acpi_numa_arch_fixup(void);
-#endif
 
 #ifdef CONFIG_ACPI_HOTPLUG_CPU
 /* Arch dependent functions for cpu hotplug support */
-- 
cgit v1.2.3


From 455c8793d2c49eaecad038c8de83dade9fc3759f Mon Sep 17 00:00:00 2001
From: Zhao Yakui <yakui.zhao@intel.com>
Date: Mon, 6 Oct 2008 10:31:36 +0800
Subject: ACPI: Enable EC device immediately after ACPI full initialization

when there is no ECDT table and no _INI object for EC device, it will be
enabled before scanning ACPI device. But it is too late after the following
the commit is merged.
    >commit 7752d5cfe3d11ca0bb9c673ec38bd78ba6578f8e
    > Author: Robert Hancock <hancockr@shaw.ca>
    > Date:   Fri Feb 15 01:27:20 2008 -0800
       >x86: validate against acpi motherboard resources

   After the above commit is merged, OS will check whether MCFG area is
reserved in ACPI motherboard resources by calling the function of
acpi_get_devices when there exists MCFG table. In the acpi_get_devices the _STA
object will be evaluated to check the status of the ACPI device. On some broken
BIOS the MYEC object of EC device is initialized as one, which indicates that
EC operation region is already accessible before enabling EC device.So on these
broken BIOS the EC operation region will be accessed in course of evaluating
the _STA object before enabling EC device, which causes that OS will print the
following warning messages:
    >ACPI Error (evregion-0315): No handler for Region [EC__] (ffff88007f8145e8)
[EmbeddedControl] [20080609]
    >ACPI Error (exfldio-0290): Region EmbeddedControl(3) has no handler [20080321]
    >ACPI Error (psparse-0530): Method parse/execution failed [\_SB_.PCI0.SBRG.
         EC__.BAT1._STA] (Node ffff81013fc17a00), AE_NOT_EXIST
    >ACPI Error (uteval-0233): Method execution failed [\_SB_.PCI0.SBRG.EC__.BAT1.
         _STA] (Node ffff81013fc17a00), AE_NOT_EXIST

Although the above warning message is harmless, it looks confusing.
So it is necessary to enable EC device as early as possible.Maybe it is
appropriate to enable it immediately after ACPI full initialization.

http://bugzilla.kernel.org/show_bug.cgi?id=11255
http://bugzilla.kernel.org/show_bug.cgi?id=11374
http://bugzilla.kernel.org/show_bug.cgi?id=11660

Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Acked-by: Alexey Starikovskiy <astarikovskiy@suse.de>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/bus.c          | 6 ++++++
 drivers/acpi/scan.c         | 4 ----
 include/acpi/acpi_drivers.h | 1 +
 3 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index ccae305ee55d..0e0bbc6209e5 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -749,6 +749,12 @@ static int __init acpi_bus_init(void)
 		goto error1;
 	}
 
+	/*
+	 * Maybe EC region is required at bus_scan/acpi_get_devices. So it
+	 * is necessary to enable it as early as possible.
+	 */
+	acpi_boot_ec_enable();
+
 	printk(KERN_INFO PREFIX "Interpreter enabled\n");
 
 	/* Initialize sleep structures */
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index f6f52c1a2aba..2ae218f5ea59 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1545,7 +1545,6 @@ static int acpi_bus_scan_fixed(struct acpi_device *root)
 	return result;
 }
 
-int __init acpi_boot_ec_enable(void);
 
 static int __init acpi_scan_init(void)
 {
@@ -1579,9 +1578,6 @@ static int __init acpi_scan_init(void)
 	 */
 	result = acpi_bus_scan_fixed(acpi_root);
 
-	/* EC region might be needed at bus_scan, so enable it now */
-	acpi_boot_ec_enable();
-
 	if (!result)
 		result = acpi_bus_scan(acpi_root, &ops);
 
diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h
index e5f38e5ce86f..ab926a70b39f 100644
--- a/include/acpi/acpi_drivers.h
+++ b/include/acpi/acpi_drivers.h
@@ -100,6 +100,7 @@ int acpi_power_transition(struct acpi_device *device, int state);
    -------------------------------------------------------------------------- */
 #ifdef CONFIG_ACPI_EC
 int acpi_ec_ecdt_probe(void);
+int acpi_boot_ec_enable(void);
 #endif
 
 /* --------------------------------------------------------------------------
-- 
cgit v1.2.3


From 27663c5855b10af9ec67bc7dfba001426ba21222 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@linux.intel.com>
Date: Fri, 10 Oct 2008 02:22:59 -0400
Subject: ACPI: Change acpi_evaluate_integer to support 64-bit on 32-bit
 kernels

As of version 2.0, ACPI can return 64-bit integers.  The current
acpi_evaluate_integer only supports 64-bit integers on 64-bit platforms.
Change the argument to take a pointer to an acpi_integer so we support
64-bit integers on all platforms.

lenb: replaced use of "acpi_integer" with "unsigned long long"
lenb: fixed bug in acpi_thermal_trips_update()

Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 arch/ia64/sn/kernel/io_acpi_init.c  |  8 +++----
 drivers/acpi/ac.c                   |  2 +-
 drivers/acpi/acpi_memhotplug.c      |  5 ++---
 drivers/acpi/asus_acpi.c            |  2 +-
 drivers/acpi/bay.c                  |  2 +-
 drivers/acpi/bus.c                  |  4 ++--
 drivers/acpi/button.c               |  4 ++--
 drivers/acpi/container.c            |  2 +-
 drivers/acpi/dock.c                 |  6 +++---
 drivers/acpi/ec.c                   |  7 ++++--
 drivers/acpi/numa.c                 |  2 +-
 drivers/acpi/osl.c                  |  5 ++---
 drivers/acpi/pci_root.c             |  2 +-
 drivers/acpi/pci_slot.c             | 10 ++++-----
 drivers/acpi/power.c                |  2 +-
 drivers/acpi/processor_core.c       |  4 ++--
 drivers/acpi/processor_perflib.c    |  2 +-
 drivers/acpi/processor_throttling.c |  2 +-
 drivers/acpi/sbshc.c                |  2 +-
 drivers/acpi/sleep/main.c           |  2 +-
 drivers/acpi/thermal.c              | 43 +++++++++++++++++++++++--------------
 drivers/acpi/utils.c                |  4 ++--
 drivers/acpi/video.c                | 42 ++++++++++++++++++------------------
 drivers/ata/libata-acpi.c           |  2 +-
 drivers/misc/asus-laptop.c          | 12 +++++------
 drivers/misc/eeepc-laptop.c         |  2 +-
 drivers/misc/fujitsu-laptop.c       |  8 +++----
 drivers/misc/intel_menlow.c         | 27 ++++++++++++-----------
 drivers/pci/hotplug/acpiphp_glue.c  | 14 ++++++------
 drivers/pci/hotplug/acpiphp_ibm.c   |  2 +-
 drivers/pci/hotplug/sgi_hotplug.c   |  4 ++--
 include/acpi/acpi_bus.h             |  2 +-
 32 files changed, 125 insertions(+), 112 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/sn/kernel/io_acpi_init.c b/arch/ia64/sn/kernel/io_acpi_init.c
index 6568942a95f0..a15baacaba43 100644
--- a/arch/ia64/sn/kernel/io_acpi_init.c
+++ b/arch/ia64/sn/kernel/io_acpi_init.c
@@ -232,7 +232,7 @@ exit:
 static unsigned int
 get_host_devfn(acpi_handle device_handle, acpi_handle rootbus_handle)
 {
-	unsigned long adr;
+	unsigned long long adr;
 	acpi_handle child;
 	unsigned int devfn;
 	int function;
@@ -292,8 +292,8 @@ get_host_devfn(acpi_handle device_handle, acpi_handle rootbus_handle)
 static acpi_status
 find_matching_device(acpi_handle handle, u32 lvl, void *context, void **rv)
 {
-	unsigned long bbn = -1;
-	unsigned long adr;
+	unsigned long long bbn = -1;
+	unsigned long long adr;
 	acpi_handle parent = NULL;
 	acpi_status status;
 	unsigned int devfn;
@@ -348,7 +348,7 @@ sn_acpi_get_pcidev_info(struct pci_dev *dev, struct pcidev_info **pcidev_info,
 	unsigned int host_devfn;
 	struct sn_pcidev_match pcidev_match;
 	acpi_handle rootbus_handle;
-	unsigned long segment;
+	unsigned long long segment;
 	acpi_status status;
 
 	rootbus_handle = PCI_CONTROLLER(dev)->acpi_handle;
diff --git a/drivers/acpi/ac.c b/drivers/acpi/ac.c
index 831883b7d6c9..5e57a80c6cf1 100644
--- a/drivers/acpi/ac.c
+++ b/drivers/acpi/ac.c
@@ -85,7 +85,7 @@ struct acpi_ac {
 	struct power_supply charger;
 #endif
 	struct acpi_device * device;
-	unsigned long state;
+	unsigned long long state;
 };
 
 #define to_acpi_ac(x) container_of(x, struct acpi_ac, charger);
diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c
index 5f1127ad5a95..2b773160e9c2 100644
--- a/drivers/acpi/acpi_memhotplug.c
+++ b/drivers/acpi/acpi_memhotplug.c
@@ -194,8 +194,7 @@ acpi_memory_get_device(acpi_handle handle,
 
 static int acpi_memory_check_device(struct acpi_memory_device *mem_device)
 {
-	unsigned long current_status;
-
+	unsigned long long current_status;
 
 	/* Get device present/absent information from the _STA */
 	if (ACPI_FAILURE(acpi_evaluate_integer(mem_device->device->handle, "_STA",
@@ -264,7 +263,7 @@ static int acpi_memory_powerdown_device(struct acpi_memory_device *mem_device)
 	acpi_status status;
 	struct acpi_object_list arg_list;
 	union acpi_object arg;
-	unsigned long current_status;
+	unsigned long long current_status;
 
 
 	/* Issue the _EJ0 command */
diff --git a/drivers/acpi/asus_acpi.c b/drivers/acpi/asus_acpi.c
index d3d0886d637f..4434209e453e 100644
--- a/drivers/acpi/asus_acpi.c
+++ b/drivers/acpi/asus_acpi.c
@@ -753,7 +753,7 @@ static int get_lcd_state(void)
 			/* That's what the AML code does */
 			lcd = out_obj.integer.value >> 8;
 	} else if (hotk->model == F3Sa) {
-		unsigned long tmp;
+		unsigned long long tmp;
 		union acpi_object param;
 		struct acpi_object_list input;
 		acpi_status status;
diff --git a/drivers/acpi/bay.c b/drivers/acpi/bay.c
index 61b6c5beb2d3..23a51e4779f7 100644
--- a/drivers/acpi/bay.c
+++ b/drivers/acpi/bay.c
@@ -90,7 +90,7 @@ static int is_ejectable(acpi_handle handle)
  */
 static int bay_present(struct bay *bay)
 {
-	unsigned long sta;
+	unsigned long long sta;
 	acpi_status status;
 
 	if (bay) {
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index ccae305ee55d..0885fc796fa0 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -77,7 +77,7 @@ EXPORT_SYMBOL(acpi_bus_get_device);
 int acpi_bus_get_status(struct acpi_device *device)
 {
 	acpi_status status = AE_OK;
-	unsigned long sta = 0;
+	unsigned long long sta = 0;
 
 
 	if (!device)
@@ -155,7 +155,7 @@ int acpi_bus_get_power(acpi_handle handle, int *state)
 	int result = 0;
 	acpi_status status = 0;
 	struct acpi_device *device = NULL;
-	unsigned long psc = 0;
+	unsigned long long psc = 0;
 
 
 	result = acpi_bus_get_device(handle, &device);
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 1dfec413588c..baeb661ca953 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -145,7 +145,7 @@ static int acpi_button_state_seq_show(struct seq_file *seq, void *offset)
 {
 	struct acpi_button *button = seq->private;
 	acpi_status status;
-	unsigned long state;
+	unsigned long long state;
 
 	if (!button || !button->device)
 		return 0;
@@ -253,7 +253,7 @@ static int acpi_button_remove_fs(struct acpi_device *device)
    -------------------------------------------------------------------------- */
 static int acpi_lid_send_state(struct acpi_button *button)
 {
-	unsigned long state;
+	unsigned long long state;
 	acpi_status status;
 
 	status = acpi_evaluate_integer(button->device->handle, "_LID", NULL,
diff --git a/drivers/acpi/container.c b/drivers/acpi/container.c
index 3c25ec7a1871..cfa5fd68168a 100644
--- a/drivers/acpi/container.c
+++ b/drivers/acpi/container.c
@@ -76,7 +76,7 @@ static int is_device_present(acpi_handle handle)
 {
 	acpi_handle temp;
 	acpi_status status;
-	unsigned long sta;
+	unsigned long long sta;
 
 
 	status = acpi_get_handle(handle, "_STA", &temp);
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index 7d2edf143f16..94857112b64d 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -229,7 +229,7 @@ EXPORT_SYMBOL_GPL(is_dock_device);
  */
 static int dock_present(struct dock_station *ds)
 {
-	unsigned long sta;
+	unsigned long long sta;
 	acpi_status status;
 
 	if (ds) {
@@ -727,13 +727,13 @@ static DEVICE_ATTR(undock, S_IWUSR, NULL, write_undock);
 static ssize_t show_dock_uid(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
-	unsigned long lbuf;
+	unsigned long long lbuf;
 	acpi_status status = acpi_evaluate_integer(dock_station->handle,
 					"_UID", NULL, &lbuf);
 	if (ACPI_FAILURE(status))
 	    return 0;
 
-	return snprintf(buf, PAGE_SIZE, "%lx\n", lbuf);
+	return snprintf(buf, PAGE_SIZE, "%llx\n", lbuf);
 }
 static DEVICE_ATTR(uid, S_IRUGO, show_dock_uid, NULL);
 
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 13593f9f2197..638a68679a42 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -718,6 +718,7 @@ static acpi_status
 ec_parse_device(acpi_handle handle, u32 Level, void *context, void **retval)
 {
 	acpi_status status;
+	unsigned long long tmp;
 
 	struct acpi_ec *ec = context;
 	status = acpi_walk_resources(handle, METHOD_NAME__CRS,
@@ -727,11 +728,13 @@ ec_parse_device(acpi_handle handle, u32 Level, void *context, void **retval)
 
 	/* Get GPE bit assignment (EC events). */
 	/* TODO: Add support for _GPE returning a package */
-	status = acpi_evaluate_integer(handle, "_GPE", NULL, &ec->gpe);
+	status = acpi_evaluate_integer(handle, "_GPE", NULL, &tmp);
 	if (ACPI_FAILURE(status))
 		return status;
+	ec->gpe = tmp;
 	/* Use the global lock for all EC transactions? */
-	acpi_evaluate_integer(handle, "_GLK", NULL, &ec->global_lock);
+	acpi_evaluate_integer(handle, "_GLK", NULL, &tmp);
+	ec->global_lock = tmp;
 	ec->handle = handle;
 	return AE_CTRL_TERMINATE;
 }
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index cb9864e39bae..25ceae9191ef 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -258,7 +258,7 @@ int __init acpi_numa_init(void)
 
 int acpi_get_pxm(acpi_handle h)
 {
-	unsigned long pxm;
+	unsigned long long pxm;
 	acpi_status status;
 	acpi_handle handle;
 	acpi_handle phandle = h;
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index 235a1386888a..f58fcbbc810d 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -608,7 +608,7 @@ static void acpi_os_derive_pci_id_2(acpi_handle rhandle,	/* upper bound  */
 	acpi_handle handle;
 	struct acpi_pci_id *pci_id = *id;
 	acpi_status status;
-	unsigned long temp;
+	unsigned long long temp;
 	acpi_object_type type;
 
 	acpi_get_parent(chandle, &handle);
@@ -620,8 +620,7 @@ static void acpi_os_derive_pci_id_2(acpi_handle rhandle,	/* upper bound  */
 		if ((ACPI_FAILURE(status)) || (type != ACPI_TYPE_DEVICE))
 			return;
 
-		status =
-		    acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL,
+		status = acpi_evaluate_integer(handle, METHOD_NAME__ADR, NULL,
 					  &temp);
 		if (ACPI_SUCCESS(status)) {
 			u32 val;
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index c3fed31166b5..18ff4e5c8d81 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -190,7 +190,7 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 	struct acpi_pci_root *root = NULL;
 	struct acpi_pci_root *tmp;
 	acpi_status status = AE_OK;
-	unsigned long value = 0;
+	unsigned long long value = 0;
 	acpi_handle handle = NULL;
 	struct acpi_device *child;
 
diff --git a/drivers/acpi/pci_slot.c b/drivers/acpi/pci_slot.c
index d5b4ef898879..9bb84d4596be 100644
--- a/drivers/acpi/pci_slot.c
+++ b/drivers/acpi/pci_slot.c
@@ -76,10 +76,10 @@ static struct acpi_pci_driver acpi_pci_slot_driver = {
 };
 
 static int
-check_slot(acpi_handle handle, unsigned long *sun)
+check_slot(acpi_handle handle, unsigned long long *sun)
 {
 	int device = -1;
-	unsigned long adr, sta;
+	unsigned long long adr, sta;
 	acpi_status status;
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 
@@ -132,7 +132,7 @@ static acpi_status
 register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
 {
 	int device;
-	unsigned long sun;
+	unsigned long long sun;
 	char name[SLOT_NAME_SIZE];
 	struct acpi_pci_slot *slot;
 	struct pci_slot *pci_slot;
@@ -182,7 +182,7 @@ static acpi_status
 walk_p2p_bridge(acpi_handle handle, u32 lvl, void *context, void **rv)
 {
 	int device, function;
-	unsigned long adr;
+	unsigned long long adr;
 	acpi_status status;
 	acpi_handle dummy_handle;
 	acpi_walk_callback user_function;
@@ -239,7 +239,7 @@ static int
 walk_root_bridge(acpi_handle handle, acpi_walk_callback user_function)
 {
 	int seg, bus;
-	unsigned long tmp;
+	unsigned long long tmp;
 	acpi_status status;
 	acpi_handle dummy_handle;
 	struct pci_bus *pci_bus;
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index 4ab21cb1c8c7..89e5d2a8c33a 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -131,7 +131,7 @@ acpi_power_get_context(acpi_handle handle,
 static int acpi_power_get_state(struct acpi_power_resource *resource, int *state)
 {
 	acpi_status status = AE_OK;
-	unsigned long sta = 0;
+	unsigned long long sta = 0;
 
 
 	if (!resource || !state)
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index ee68ac54c0d4..8a2787141f80 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -563,7 +563,7 @@ static int acpi_processor_get_info(struct acpi_processor *pr, unsigned has_uid)
 
 	/* Check if it is a Device with HID and UID */
 	if (has_uid) {
-		unsigned long value;
+		unsigned long long value;
 		status = acpi_evaluate_integer(pr->handle, METHOD_NAME__UID,
 						NULL, &value);
 		if (ACPI_FAILURE(status)) {
@@ -875,7 +875,7 @@ static int acpi_processor_remove(struct acpi_device *device, int type)
 static int is_processor_present(acpi_handle handle)
 {
 	acpi_status status;
-	unsigned long sta = 0;
+	unsigned long long sta = 0;
 
 
 	status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index 80c251ec6d2a..f8129c7277f1 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -126,7 +126,7 @@ static struct notifier_block acpi_ppc_notifier_block = {
 static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
 {
 	acpi_status status = 0;
-	unsigned long ppc = 0;
+	unsigned long long ppc = 0;
 
 
 	if (!pr)
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index a56fc6c4394b..3097b752003d 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -274,7 +274,7 @@ static int acpi_processor_throttling_notifier(unsigned long event, void *data)
 static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
 {
 	acpi_status status = 0;
-	unsigned long tpc = 0;
+	unsigned long long tpc = 0;
 
 	if (!pr)
 		return -EINVAL;
diff --git a/drivers/acpi/sbshc.c b/drivers/acpi/sbshc.c
index a4e3767b8c64..81d23d38ec91 100644
--- a/drivers/acpi/sbshc.c
+++ b/drivers/acpi/sbshc.c
@@ -258,7 +258,7 @@ extern int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
 static int acpi_smbus_hc_add(struct acpi_device *device)
 {
 	int status;
-	unsigned long val;
+	unsigned long long val;
 	struct acpi_smb_hc *hc;
 
 	if (!device)
diff --git a/drivers/acpi/sleep/main.c b/drivers/acpi/sleep/main.c
index d13194a031bf..b32ba565e69e 100644
--- a/drivers/acpi/sleep/main.c
+++ b/drivers/acpi/sleep/main.c
@@ -444,7 +444,7 @@ int acpi_pm_device_sleep_state(struct device *dev, int *d_min_p)
 	acpi_handle handle = DEVICE_ACPI_HANDLE(dev);
 	struct acpi_device *adev;
 	char acpi_method[] = "_SxD";
-	unsigned long d_min, d_max;
+	unsigned long long d_min, d_max;
 
 	if (!handle || ACPI_FAILURE(acpi_bus_get_device(handle, &adev))) {
 		printk(KERN_DEBUG "ACPI handle has no context!\n");
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index 912703691d36..47abb94bdfb9 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -246,18 +246,18 @@ static const struct file_operations acpi_thermal_polling_fops = {
 static int acpi_thermal_get_temperature(struct acpi_thermal *tz)
 {
 	acpi_status status = AE_OK;
-
+	unsigned long long tmp;
 
 	if (!tz)
 		return -EINVAL;
 
 	tz->last_temperature = tz->temperature;
 
-	status =
-	    acpi_evaluate_integer(tz->device->handle, "_TMP", NULL, &tz->temperature);
+	status = acpi_evaluate_integer(tz->device->handle, "_TMP", NULL, &tmp);
 	if (ACPI_FAILURE(status))
 		return -ENODEV;
 
+	tz->temperature = tmp;
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Temperature is %lu dK\n",
 			  tz->temperature));
 
@@ -267,17 +267,16 @@ static int acpi_thermal_get_temperature(struct acpi_thermal *tz)
 static int acpi_thermal_get_polling_frequency(struct acpi_thermal *tz)
 {
 	acpi_status status = AE_OK;
-
+	unsigned long long tmp;
 
 	if (!tz)
 		return -EINVAL;
 
-	status =
-	    acpi_evaluate_integer(tz->device->handle, "_TZP", NULL,
-				  &tz->polling_frequency);
+	status = acpi_evaluate_integer(tz->device->handle, "_TZP", NULL, &tmp);
 	if (ACPI_FAILURE(status))
 		return -ENODEV;
 
+	tz->polling_frequency = tmp;
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Polling frequency is %lu dS\n",
 			  tz->polling_frequency));
 
@@ -356,6 +355,7 @@ do {	\
 static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 {
 	acpi_status status = AE_OK;
+	unsigned long long tmp;
 	struct acpi_handle_list devices;
 	int valid = 0;
 	int i;
@@ -363,7 +363,8 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 	/* Critical Shutdown (required) */
 	if (flag & ACPI_TRIPS_CRITICAL) {
 		status = acpi_evaluate_integer(tz->device->handle,
-				"_CRT", NULL, &tz->trips.critical.temperature);
+				"_CRT", NULL, &tmp);
+		tz->trips.critical.temperature = tmp;
 		/*
 		 * Treat freezing temperatures as invalid as well; some
 		 * BIOSes return really low values and cause reboots at startup.
@@ -399,12 +400,13 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 	/* Critical Sleep (optional) */
 	if (flag & ACPI_TRIPS_HOT) {
 		status = acpi_evaluate_integer(tz->device->handle,
-				"_HOT", NULL, &tz->trips.hot.temperature);
+				"_HOT", NULL, &tmp);
 		if (ACPI_FAILURE(status)) {
 			tz->trips.hot.flags.valid = 0;
 			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 					"No hot threshold\n"));
 		} else {
+			tz->trips.hot.temperature = tmp;
 			tz->trips.hot.flags.valid = 1;
 			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 					"Found hot threshold [%lu]\n",
@@ -418,33 +420,40 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 		if (psv == -1) {
 			status = AE_SUPPORT;
 		} else if (psv > 0) {
-			tz->trips.passive.temperature = CELSIUS_TO_KELVIN(psv);
+			tmp = CELSIUS_TO_KELVIN(psv);
 			status = AE_OK;
 		} else {
 			status = acpi_evaluate_integer(tz->device->handle,
-				"_PSV", NULL, &tz->trips.passive.temperature);
+				"_PSV", NULL, &tmp);
 		}
 
 		if (ACPI_FAILURE(status))
 			tz->trips.passive.flags.valid = 0;
 		else {
+			tz->trips.passive.temperature = tmp;
 			tz->trips.passive.flags.valid = 1;
 			if (flag == ACPI_TRIPS_INIT) {
 				status = acpi_evaluate_integer(
 						tz->device->handle, "_TC1",
-						NULL, &tz->trips.passive.tc1);
+						NULL, &tmp);
 				if (ACPI_FAILURE(status))
 					tz->trips.passive.flags.valid = 0;
+				else
+					tz->trips.passive.tc1 = tmp;
 				status = acpi_evaluate_integer(
 						tz->device->handle, "_TC2",
-						NULL, &tz->trips.passive.tc2);
+						NULL, &tmp);
 				if (ACPI_FAILURE(status))
 					tz->trips.passive.flags.valid = 0;
+				else
+					tz->trips.passive.tc2 = tmp;
 				status = acpi_evaluate_integer(
 						tz->device->handle, "_TSP",
-						NULL, &tz->trips.passive.tsp);
+						NULL, &tmp);
 				if (ACPI_FAILURE(status))
 					tz->trips.passive.flags.valid = 0;
+				else
+					tz->trips.passive.tsp = tmp;
 			}
 		}
 	}
@@ -479,7 +488,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 
 		if (flag & ACPI_TRIPS_ACTIVE) {
 			status = acpi_evaluate_integer(tz->device->handle,
-				name, NULL, &tz->trips.active[i].temperature);
+							name, NULL, &tmp);
 			if (ACPI_FAILURE(status)) {
 				tz->trips.active[i].flags.valid = 0;
 				if (i == 0)
@@ -500,8 +509,10 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 						tz->trips.active[i - 2].temperature :
 						CELSIUS_TO_KELVIN(act));
 				break;
-			} else
+			} else {
+				tz->trips.active[i].temperature = tmp;
 				tz->trips.active[i].flags.valid = 1;
+			}
 		}
 
 		name[2] = 'L';
diff --git a/drivers/acpi/utils.c b/drivers/acpi/utils.c
index 100926143818..e827be36ee8d 100644
--- a/drivers/acpi/utils.c
+++ b/drivers/acpi/utils.c
@@ -256,7 +256,7 @@ EXPORT_SYMBOL(acpi_extract_package);
 acpi_status
 acpi_evaluate_integer(acpi_handle handle,
 		      acpi_string pathname,
-		      struct acpi_object_list *arguments, unsigned long *data)
+		      struct acpi_object_list *arguments, unsigned long long *data)
 {
 	acpi_status status = AE_OK;
 	union acpi_object *element;
@@ -288,7 +288,7 @@ acpi_evaluate_integer(acpi_handle handle,
 	*data = element->integer.value;
 	kfree(element);
 
-	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Return value [%lu]\n", *data));
+	ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Return value [%llu]\n", *data));
 
 	return AE_OK;
 }
diff --git a/drivers/acpi/video.c b/drivers/acpi/video.c
index e8a51a1700f7..79409c9d2ad6 100644
--- a/drivers/acpi/video.c
+++ b/drivers/acpi/video.c
@@ -291,20 +291,20 @@ static int acpi_video_device_lcd_set_level(struct acpi_video_device *device,
 			int level);
 static int acpi_video_device_lcd_get_level_current(
 			struct acpi_video_device *device,
-			unsigned long *level);
+			unsigned long long *level);
 static int acpi_video_get_next_level(struct acpi_video_device *device,
 				     u32 level_current, u32 event);
 static void acpi_video_switch_brightness(struct acpi_video_device *device,
 					 int event);
 static int acpi_video_device_get_state(struct acpi_video_device *device,
-			    unsigned long *state);
+			    unsigned long long *state);
 static int acpi_video_output_get(struct output_device *od);
 static int acpi_video_device_set_state(struct acpi_video_device *device, int state);
 
 /*backlight device sysfs support*/
 static int acpi_video_get_brightness(struct backlight_device *bd)
 {
-	unsigned long cur_level;
+	unsigned long long cur_level;
 	int i;
 	struct acpi_video_device *vd =
 		(struct acpi_video_device *)bl_get_data(bd);
@@ -336,7 +336,7 @@ static struct backlight_ops acpi_backlight_ops = {
 /*video output device sysfs support*/
 static int acpi_video_output_get(struct output_device *od)
 {
-	unsigned long state;
+	unsigned long long state;
 	struct acpi_video_device *vd =
 		(struct acpi_video_device *)dev_get_drvdata(&od->dev);
 	acpi_video_device_get_state(vd, &state);
@@ -370,7 +370,7 @@ static int video_get_cur_state(struct thermal_cooling_device *cdev, char *buf)
 {
 	struct acpi_device *device = cdev->devdata;
 	struct acpi_video_device *video = acpi_driver_data(device);
-	unsigned long level;
+	unsigned long long level;
 	int state;
 
 	acpi_video_device_lcd_get_level_current(video, &level);
@@ -410,7 +410,7 @@ static struct thermal_cooling_device_ops video_cooling_ops = {
 /* device */
 
 static int
-acpi_video_device_query(struct acpi_video_device *device, unsigned long *state)
+acpi_video_device_query(struct acpi_video_device *device, unsigned long long *state)
 {
 	int status;
 
@@ -421,7 +421,7 @@ acpi_video_device_query(struct acpi_video_device *device, unsigned long *state)
 
 static int
 acpi_video_device_get_state(struct acpi_video_device *device,
-			    unsigned long *state)
+			    unsigned long long *state)
 {
 	int status;
 
@@ -436,7 +436,7 @@ acpi_video_device_set_state(struct acpi_video_device *device, int state)
 	int status;
 	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
 	struct acpi_object_list args = { 1, &arg0 };
-	unsigned long ret;
+	unsigned long long ret;
 
 
 	arg0.integer.value = state;
@@ -495,7 +495,7 @@ acpi_video_device_lcd_set_level(struct acpi_video_device *device, int level)
 
 static int
 acpi_video_device_lcd_get_level_current(struct acpi_video_device *device,
-					unsigned long *level)
+					unsigned long long *level)
 {
 	if (device->cap._BQC)
 		return acpi_evaluate_integer(device->dev->handle, "_BQC", NULL,
@@ -549,7 +549,7 @@ static int
 acpi_video_bus_set_POST(struct acpi_video_bus *video, unsigned long option)
 {
 	int status;
-	unsigned long tmp;
+	unsigned long long tmp;
 	union acpi_object arg0 = { ACPI_TYPE_INTEGER };
 	struct acpi_object_list args = { 1, &arg0 };
 
@@ -564,7 +564,7 @@ acpi_video_bus_set_POST(struct acpi_video_bus *video, unsigned long option)
 }
 
 static int
-acpi_video_bus_get_POST(struct acpi_video_bus *video, unsigned long *id)
+acpi_video_bus_get_POST(struct acpi_video_bus *video, unsigned long long *id)
 {
 	int status;
 
@@ -575,7 +575,7 @@ acpi_video_bus_get_POST(struct acpi_video_bus *video, unsigned long *id)
 
 static int
 acpi_video_bus_POST_options(struct acpi_video_bus *video,
-			    unsigned long *options)
+			    unsigned long long *options)
 {
 	int status;
 
@@ -918,7 +918,7 @@ static int acpi_video_device_state_seq_show(struct seq_file *seq, void *offset)
 {
 	int status;
 	struct acpi_video_device *dev = seq->private;
-	unsigned long state;
+	unsigned long long state;
 
 
 	if (!dev)
@@ -927,14 +927,14 @@ static int acpi_video_device_state_seq_show(struct seq_file *seq, void *offset)
 	status = acpi_video_device_get_state(dev, &state);
 	seq_printf(seq, "state:     ");
 	if (ACPI_SUCCESS(status))
-		seq_printf(seq, "0x%02lx\n", state);
+		seq_printf(seq, "0x%02llx\n", state);
 	else
 		seq_printf(seq, "<not supported>\n");
 
 	status = acpi_video_device_query(dev, &state);
 	seq_printf(seq, "query:     ");
 	if (ACPI_SUCCESS(status))
-		seq_printf(seq, "0x%02lx\n", state);
+		seq_printf(seq, "0x%02llx\n", state);
 	else
 		seq_printf(seq, "<not supported>\n");
 
@@ -1217,7 +1217,7 @@ static int acpi_video_bus_ROM_open_fs(struct inode *inode, struct file *file)
 static int acpi_video_bus_POST_info_seq_show(struct seq_file *seq, void *offset)
 {
 	struct acpi_video_bus *video = seq->private;
-	unsigned long options;
+	unsigned long long options;
 	int status;
 
 
@@ -1232,7 +1232,7 @@ static int acpi_video_bus_POST_info_seq_show(struct seq_file *seq, void *offset)
 			printk(KERN_WARNING PREFIX
 			       "This indicates a BIOS bug. Please contact the manufacturer.\n");
 		}
-		printk("%lx\n", options);
+		printk("%llx\n", options);
 		seq_printf(seq, "can POST: <integrated video>");
 		if (options & 2)
 			seq_printf(seq, " <PCI video>");
@@ -1256,7 +1256,7 @@ static int acpi_video_bus_POST_seq_show(struct seq_file *seq, void *offset)
 {
 	struct acpi_video_bus *video = seq->private;
 	int status;
-	unsigned long id;
+	unsigned long long id;
 
 
 	if (!video)
@@ -1303,7 +1303,7 @@ acpi_video_bus_write_POST(struct file *file,
 	struct seq_file *m = file->private_data;
 	struct acpi_video_bus *video = m->private;
 	char str[12] = { 0 };
-	unsigned long opt, options;
+	unsigned long long opt, options;
 
 
 	if (!video || count + 1 > sizeof str)
@@ -1473,7 +1473,7 @@ static int
 acpi_video_bus_get_one_device(struct acpi_device *device,
 			      struct acpi_video_bus *video)
 {
-	unsigned long device_id;
+	unsigned long long device_id;
 	int status;
 	struct acpi_video_device *data;
 	struct acpi_video_device_attrib* attribute;
@@ -1724,7 +1724,7 @@ acpi_video_get_next_level(struct acpi_video_device *device,
 static void
 acpi_video_switch_brightness(struct acpi_video_device *device, int event)
 {
-	unsigned long level_current, level_next;
+	unsigned long long level_current, level_next;
 	if (!device->brightness)
 		return;
 	acpi_video_device_lcd_get_level_current(device, &level_current);
diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index 9330b7922f62..ae451876b8ed 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -180,7 +180,7 @@ static void ata_acpi_handle_hotplug(struct ata_port *ap, struct ata_device *dev,
 	int wait = 0;
 	unsigned long flags;
 	acpi_handle handle, tmphandle;
-	unsigned long sta;
+	unsigned long long sta;
 	acpi_status status;
 
 	if (dev) {
diff --git a/drivers/misc/asus-laptop.c b/drivers/misc/asus-laptop.c
index 7c6dfd03de9f..967ecec82577 100644
--- a/drivers/misc/asus-laptop.c
+++ b/drivers/misc/asus-laptop.c
@@ -280,7 +280,7 @@ static int write_acpi_int(acpi_handle handle, const char *method, int val,
 
 static int read_wireless_status(int mask)
 {
-	ulong status;
+	unsigned long long status;
 	acpi_status rv = AE_OK;
 
 	if (!wireless_status_handle)
@@ -297,7 +297,7 @@ static int read_wireless_status(int mask)
 
 static int read_gps_status(void)
 {
-	ulong status;
+	unsigned long long status;
 	acpi_status rv = AE_OK;
 
 	rv = acpi_evaluate_integer(gps_status_handle, NULL, NULL, &status);
@@ -404,7 +404,7 @@ static void lcd_blank(int blank)
 
 static int read_brightness(struct backlight_device *bd)
 {
-	ulong value;
+	unsigned long long value;
 	acpi_status rv = AE_OK;
 
 	rv = acpi_evaluate_integer(brightness_get_handle, NULL, NULL, &value);
@@ -455,7 +455,7 @@ static ssize_t show_infos(struct device *dev,
 			  struct device_attribute *attr, char *page)
 {
 	int len = 0;
-	ulong temp;
+	unsigned long long temp;
 	char buf[16];		//enough for all info
 	acpi_status rv = AE_OK;
 
@@ -603,7 +603,7 @@ static void set_display(int value)
 
 static int read_display(void)
 {
-	ulong value = 0;
+	unsigned long long value = 0;
 	acpi_status rv = AE_OK;
 
 	/* In most of the case, we know how to set the display, but sometime
@@ -849,7 +849,7 @@ static int asus_hotk_get_info(void)
 {
 	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
 	union acpi_object *model = NULL;
-	ulong bsts_result, hwrs_result;
+	unsigned long long bsts_result, hwrs_result;
 	char *string = NULL;
 	acpi_status status;
 
diff --git a/drivers/misc/eeepc-laptop.c b/drivers/misc/eeepc-laptop.c
index 1ee8501e90f1..616bcbd8def6 100644
--- a/drivers/misc/eeepc-laptop.c
+++ b/drivers/misc/eeepc-laptop.c
@@ -204,7 +204,7 @@ static int write_acpi_int(acpi_handle handle, const char *method, int val,
 static int read_acpi_int(acpi_handle handle, const char *method, int *val)
 {
 	acpi_status status;
-	ulong result;
+	unsigned long long result;
 
 	status = acpi_evaluate_integer(handle, (char *)method, NULL, &result);
 	if (ACPI_FAILURE(status)) {
diff --git a/drivers/misc/fujitsu-laptop.c b/drivers/misc/fujitsu-laptop.c
index 3e56203e4947..efd395a64720 100644
--- a/drivers/misc/fujitsu-laptop.c
+++ b/drivers/misc/fujitsu-laptop.c
@@ -224,7 +224,7 @@ static int set_lcd_level_alt(int level)
 
 static int get_lcd_level(void)
 {
-	unsigned long state = 0;
+	unsigned long long state = 0;
 	acpi_status status = AE_OK;
 
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "get lcd level via GBLL\n");
@@ -246,7 +246,7 @@ static int get_lcd_level(void)
 
 static int get_max_brightness(void)
 {
-	unsigned long state = 0;
+	unsigned long long state = 0;
 	acpi_status status = AE_OK;
 
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "get max lcd level via RBLL\n");
@@ -263,7 +263,7 @@ static int get_max_brightness(void)
 
 static int get_lcd_level_alt(void)
 {
-	unsigned long state = 0;
+	unsigned long long state = 0;
 	acpi_status status = AE_OK;
 
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "get lcd level via GBLS\n");
@@ -384,7 +384,7 @@ static ssize_t store_lcd_level(struct device *dev,
 
 static int get_irb(void)
 {
-	unsigned long state = 0;
+	unsigned long long state = 0;
 	acpi_status status = AE_OK;
 
 	vdbg_printk(FUJLAPTOP_DBG_TRACE, "Get irb\n");
diff --git a/drivers/misc/intel_menlow.c b/drivers/misc/intel_menlow.c
index 80a136352408..bd372ea11b0a 100644
--- a/drivers/misc/intel_menlow.c
+++ b/drivers/misc/intel_menlow.c
@@ -57,7 +57,7 @@ static int memory_get_int_max_bandwidth(struct thermal_cooling_device *cdev,
 {
 	struct acpi_device *device = cdev->devdata;
 	acpi_handle handle = device->handle;
-	unsigned long value;
+	unsigned long long value;
 	struct acpi_object_list arg_list;
 	union acpi_object arg;
 	acpi_status status = AE_OK;
@@ -90,7 +90,7 @@ static int memory_get_cur_bandwidth(struct thermal_cooling_device *cdev,
 {
 	struct acpi_device *device = cdev->devdata;
 	acpi_handle handle = device->handle;
-	unsigned long value;
+	unsigned long long value;
 	struct acpi_object_list arg_list;
 	union acpi_object arg;
 	acpi_status status = AE_OK;
@@ -115,7 +115,7 @@ static int memory_set_cur_bandwidth(struct thermal_cooling_device *cdev,
 	struct acpi_object_list arg_list;
 	union acpi_object arg;
 	acpi_status status;
-	int temp;
+	unsigned long long temp;
 	unsigned long max_state;
 
 	if (memory_get_int_max_bandwidth(cdev, &max_state))
@@ -131,7 +131,7 @@ static int memory_set_cur_bandwidth(struct thermal_cooling_device *cdev,
 
 	status =
 	    acpi_evaluate_integer(handle, MEMORY_SET_BANDWIDTH, &arg_list,
-				  (unsigned long *)&temp);
+				  &temp);
 
 	printk(KERN_INFO
 	       "Bandwidth value was %d: status is %d\n", state, status);
@@ -252,7 +252,8 @@ static DEFINE_MUTEX(intel_menlow_attr_lock);
  * @auxtype : AUX0/AUX1
  * @buf: syfs buffer
  */
-static int sensor_get_auxtrip(acpi_handle handle, int index, int *value)
+static int sensor_get_auxtrip(acpi_handle handle, int index,
+							unsigned long long *value)
 {
 	acpi_status status;
 
@@ -260,7 +261,7 @@ static int sensor_get_auxtrip(acpi_handle handle, int index, int *value)
 		return -EINVAL;
 
 	status = acpi_evaluate_integer(handle, index ? GET_AUX1 : GET_AUX0,
-				       NULL, (unsigned long *)value);
+				       NULL, value);
 	if (ACPI_FAILURE(status))
 		return -EIO;
 
@@ -282,13 +283,13 @@ static int sensor_set_auxtrip(acpi_handle handle, int index, int value)
 	struct acpi_object_list args = {
 		1, &arg
 	};
-	int temp;
+	unsigned long long temp;
 
 	if (index != 0 && index != 1)
 		return -EINVAL;
 
 	status = acpi_evaluate_integer(handle, index ? GET_AUX0 : GET_AUX1,
-				       NULL, (unsigned long *)&temp);
+				       NULL, &temp);
 	if (ACPI_FAILURE(status))
 		return -EIO;
 	if ((index && value < temp) || (!index && value > temp))
@@ -296,7 +297,7 @@ static int sensor_set_auxtrip(acpi_handle handle, int index, int value)
 
 	arg.integer.value = value;
 	status = acpi_evaluate_integer(handle, index ? SET_AUX1 : SET_AUX0,
-				       &args, (unsigned long *)&temp);
+				       &args, &temp);
 	if (ACPI_FAILURE(status))
 		return -EIO;
 
@@ -312,7 +313,7 @@ static ssize_t aux0_show(struct device *dev,
 			 struct device_attribute *dev_attr, char *buf)
 {
 	struct intel_menlow_attribute *attr = to_intel_menlow_attr(dev_attr);
-	int value;
+	unsigned long long value;
 	int result;
 
 	result = sensor_get_auxtrip(attr->handle, 0, &value);
@@ -324,7 +325,7 @@ static ssize_t aux1_show(struct device *dev,
 			 struct device_attribute *dev_attr, char *buf)
 {
 	struct intel_menlow_attribute *attr = to_intel_menlow_attr(dev_attr);
-	int value;
+	unsigned long long value;
 	int result;
 
 	result = sensor_get_auxtrip(attr->handle, 1, &value);
@@ -376,7 +377,7 @@ static ssize_t bios_enabled_show(struct device *dev,
 				 struct device_attribute *attr, char *buf)
 {
 	acpi_status status;
-	unsigned long bios_enabled;
+	unsigned long long bios_enabled;
 
 	status = acpi_evaluate_integer(NULL, BIOS_ENABLED, NULL, &bios_enabled);
 	if (ACPI_FAILURE(status))
@@ -492,7 +493,7 @@ static int __init intel_menlow_module_init(void)
 {
 	int result = -ENODEV;
 	acpi_status status;
-	unsigned long enable;
+	unsigned long long enable;
 
 	if (acpi_disabled)
 		return result;
diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c
index a3e4705dd8f0..3baee56fa81a 100644
--- a/drivers/pci/hotplug/acpiphp_glue.c
+++ b/drivers/pci/hotplug/acpiphp_glue.c
@@ -180,7 +180,7 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
 	struct acpiphp_func *newfunc;
 	acpi_handle tmp;
 	acpi_status status = AE_OK;
-	unsigned long adr, sun;
+	unsigned long long adr, sun;
 	int device, function, retval;
 
 	status = acpi_evaluate_integer(handle, "_ADR", NULL, &adr);
@@ -528,7 +528,7 @@ find_p2p_bridge(acpi_handle handle, u32 lvl, void *context, void **rv)
 {
 	acpi_status status;
 	acpi_handle dummy_handle;
-	unsigned long tmp;
+	unsigned long long tmp;
 	int device, function;
 	struct pci_dev *dev;
 	struct pci_bus *pci_bus = context;
@@ -573,7 +573,7 @@ find_p2p_bridge(acpi_handle handle, u32 lvl, void *context, void **rv)
 static int add_bridge(acpi_handle handle)
 {
 	acpi_status status;
-	unsigned long tmp;
+	unsigned long long tmp;
 	int seg, bus;
 	acpi_handle dummy_handle;
 	struct pci_bus *pci_bus;
@@ -767,7 +767,7 @@ static int get_gsi_base(acpi_handle handle, u32 *gsi_base)
 {
 	acpi_status status;
 	int result = -1;
-	unsigned long gsb;
+	unsigned long long gsb;
 	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
 	union acpi_object *obj;
 	void *table;
@@ -808,7 +808,7 @@ static acpi_status
 ioapic_add(acpi_handle handle, u32 lvl, void *context, void **rv)
 {
 	acpi_status status;
-	unsigned long sta;
+	unsigned long long sta;
 	acpi_handle tmp;
 	struct pci_dev *pdev;
 	u32 gsi_base;
@@ -872,7 +872,7 @@ static acpi_status
 ioapic_remove(acpi_handle handle, u32 lvl, void *context, void **rv)
 {
 	acpi_status status;
-	unsigned long sta;
+	unsigned long long sta;
 	acpi_handle tmp;
 	u32 gsi_base;
 	struct acpiphp_ioapic *pos, *n, *ioapic = NULL;
@@ -1264,7 +1264,7 @@ static int disable_device(struct acpiphp_slot *slot)
 static unsigned int get_slot_status(struct acpiphp_slot *slot)
 {
 	acpi_status status;
-	unsigned long sta = 0;
+	unsigned long long sta = 0;
 	u32 dvid;
 	struct list_head *l;
 	struct acpiphp_func *func;
diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c
index 2b7c45e39370..b291ee68b4f1 100644
--- a/drivers/pci/hotplug/acpiphp_ibm.c
+++ b/drivers/pci/hotplug/acpiphp_ibm.c
@@ -183,7 +183,7 @@ static int ibm_set_attention_status(struct hotplug_slot *slot, u8 status)
 	union acpi_object args[2]; 
 	struct acpi_object_list params = { .pointer = args, .count = 2 };
 	acpi_status stat; 
-	unsigned long rc;
+	unsigned long long rc;
 	union apci_descriptor *ibm_slot;
 
 	ibm_slot = ibm_slot_from_id(hpslot_to_sun(slot));
diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c
index 410fe0394a8e..59f42501acce 100644
--- a/drivers/pci/hotplug/sgi_hotplug.c
+++ b/drivers/pci/hotplug/sgi_hotplug.c
@@ -418,7 +418,7 @@ static int enable_slot(struct hotplug_slot *bss_hotplug_slot)
 	/*
 	 * Add the slot's devices to the ACPI infrastructure */
 	if (SN_ACPI_BASE_SUPPORT() && ssdt) {
-		unsigned long adr;
+		unsigned long long adr;
 		struct acpi_device *pdevice;
 		struct acpi_device *device;
 		acpi_handle phandle;
@@ -510,7 +510,7 @@ static int disable_slot(struct hotplug_slot *bss_hotplug_slot)
 	/* free the ACPI resources for the slot */
 	if (SN_ACPI_BASE_SUPPORT() &&
             PCI_CONTROLLER(slot->pci_bus)->acpi_handle) {
-		unsigned long adr;
+		unsigned long long adr;
 		struct acpi_device *device;
 		acpi_handle phandle;
 		acpi_handle chandle = NULL;
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index a5ac0bc7f52e..c52f10dee367 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -46,7 +46,7 @@ acpi_extract_package(union acpi_object *package,
 acpi_status
 acpi_evaluate_integer(acpi_handle handle,
 		      acpi_string pathname,
-		      struct acpi_object_list *arguments, unsigned long *data);
+		      struct acpi_object_list *arguments, unsigned long long *data);
 acpi_status
 acpi_evaluate_reference(acpi_handle handle,
 			acpi_string pathname,
-- 
cgit v1.2.3


From f0c0a376d0fcd4c5579ecf5e95f88387cba85211 Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Sun, 17 Aug 2008 15:24:38 -0500
Subject: [SCSI] Add helper code so transport classes/driver can control
 queueing (v3)

SCSI-ml manages the queueing limits for the device and host, but
does not do so at the target level. However something something similar
can come in userful when a driver is transitioning a transport object to
the the blocked state, becuase at that time we do not want to queue
io and we do not want the queuecommand to be called again.

The patch adds code similar to the exisiting SCSI_ML_*BUSY handlers.
You can now return SCSI_MLQUEUE_TARGET_BUSY when we hit
a transport level queueing issue like the hw cannot allocate some
resource at the iscsi session/connection level, or the target has temporarily
closed or shrunk the queueing window, or if we are transitioning
to the blocked state.

bnx2i, when they rework their firmware according to netdev
developers requests, will also need to be able to limit queueing at this
level. bnx2i will hook into libiscsi, but will allocate a scsi host per
netdevice/hba, so unlike pure software iscsi/iser which is allocating
a host per session, it cannot set the scsi_host->can_queue and return
SCSI_MLQUEUE_HOST_BUSY to reflect queueing limits on the transport.

The iscsi class/driver can also set a scsi_target->can_queue value which
reflects the max commands the driver/class can support. For iscsi this
reflects the number of commands we can support for each session due to
session/connection hw limits, driver limits, and to also reflect the
session/targets's queueing window.

Changes:
v1 - initial patch.
v2 - Fix scsi_run_queue handling of multiple blocked targets.
Previously we would break from the main loop if a device was added back on
the starved list. We now run over the list and check if any target is
blocked.
v3 - Rediff for scsi-misc.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/scsi/scsi.c        |  10 ++++-
 drivers/scsi/scsi_lib.c    | 104 ++++++++++++++++++++++++++++++++++++++-------
 drivers/scsi/scsi_scan.c   |   1 +
 include/scsi/scsi.h        |   1 +
 include/scsi/scsi_device.h |  10 +++++
 5 files changed, 108 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 2ac3cb2b9081..f8b79d401d58 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -754,8 +754,12 @@ int scsi_dispatch_cmd(struct scsi_cmnd *cmd)
 	}
 	spin_unlock_irqrestore(host->host_lock, flags);
 	if (rtn) {
-		scsi_queue_insert(cmd, (rtn == SCSI_MLQUEUE_DEVICE_BUSY) ?
-						rtn : SCSI_MLQUEUE_HOST_BUSY);
+		if (rtn != SCSI_MLQUEUE_DEVICE_BUSY &&
+		    rtn != SCSI_MLQUEUE_TARGET_BUSY)
+			rtn = SCSI_MLQUEUE_HOST_BUSY;
+
+		scsi_queue_insert(cmd, rtn);
+
 		SCSI_LOG_MLQUEUE(3,
 		    printk("queuecommand : request rejected\n"));
 	}
@@ -800,6 +804,7 @@ static struct scsi_driver *scsi_cmd_to_driver(struct scsi_cmnd *cmd)
 void scsi_finish_command(struct scsi_cmnd *cmd)
 {
 	struct scsi_device *sdev = cmd->device;
+	struct scsi_target *starget = scsi_target(sdev);
 	struct Scsi_Host *shost = sdev->host;
 	struct scsi_driver *drv;
 	unsigned int good_bytes;
@@ -815,6 +820,7 @@ void scsi_finish_command(struct scsi_cmnd *cmd)
 	 * XXX(hch): What about locking?
          */
         shost->host_blocked = 0;
+	starget->target_blocked = 0;
         sdev->device_blocked = 0;
 
 	/*
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 98ee55ced592..91c74c55aa5e 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -114,6 +114,7 @@ int scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 {
 	struct Scsi_Host *host = cmd->device->host;
 	struct scsi_device *device = cmd->device;
+	struct scsi_target *starget = scsi_target(device);
 	struct request_queue *q = device->request_queue;
 	unsigned long flags;
 
@@ -133,10 +134,17 @@ int scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 	 * if a command is requeued with no other commands outstanding
 	 * either for the device or for the host.
 	 */
-	if (reason == SCSI_MLQUEUE_HOST_BUSY)
+	switch (reason) {
+	case SCSI_MLQUEUE_HOST_BUSY:
 		host->host_blocked = host->max_host_blocked;
-	else if (reason == SCSI_MLQUEUE_DEVICE_BUSY)
+		break;
+	case SCSI_MLQUEUE_DEVICE_BUSY:
 		device->device_blocked = device->max_device_blocked;
+		break;
+	case SCSI_MLQUEUE_TARGET_BUSY:
+		starget->target_blocked = starget->max_target_blocked;
+		break;
+	}
 
 	/*
 	 * Decrement the counters, since these commands are no longer
@@ -460,10 +468,12 @@ static void scsi_init_cmd_errh(struct scsi_cmnd *cmd)
 void scsi_device_unbusy(struct scsi_device *sdev)
 {
 	struct Scsi_Host *shost = sdev->host;
+	struct scsi_target *starget = scsi_target(sdev);
 	unsigned long flags;
 
 	spin_lock_irqsave(shost->host_lock, flags);
 	shost->host_busy--;
+	starget->target_busy--;
 	if (unlikely(scsi_host_in_recovery(shost) &&
 		     (shost->host_failed || shost->host_eh_scheduled)))
 		scsi_eh_wakeup(shost);
@@ -519,6 +529,13 @@ static void scsi_single_lun_run(struct scsi_device *current_sdev)
 	spin_unlock_irqrestore(shost->host_lock, flags);
 }
 
+static inline int scsi_target_is_busy(struct scsi_target *starget)
+{
+	return ((starget->can_queue > 0 &&
+		 starget->target_busy >= starget->can_queue) ||
+		 starget->target_blocked);
+}
+
 /*
  * Function:	scsi_run_queue()
  *
@@ -533,7 +550,7 @@ static void scsi_single_lun_run(struct scsi_device *current_sdev)
  */
 static void scsi_run_queue(struct request_queue *q)
 {
-	struct scsi_device *sdev = q->queuedata;
+	struct scsi_device *starved_head = NULL, *sdev = q->queuedata;
 	struct Scsi_Host *shost = sdev->host;
 	unsigned long flags;
 
@@ -560,6 +577,21 @@ static void scsi_run_queue(struct request_queue *q)
 		 */
 		sdev = list_entry(shost->starved_list.next,
 					  struct scsi_device, starved_entry);
+		/*
+		 * The *queue_ready functions can add a device back onto the
+		 * starved list's tail, so we must check for a infinite loop.
+		 */
+		if (sdev == starved_head)
+			break;
+		if (!starved_head)
+			starved_head = sdev;
+
+		if (scsi_target_is_busy(scsi_target(sdev))) {
+			list_move_tail(&sdev->starved_entry,
+				       &shost->starved_list);
+			continue;
+		}
+
 		list_del_init(&sdev->starved_entry);
 		spin_unlock(shost->host_lock);
 
@@ -575,13 +607,6 @@ static void scsi_run_queue(struct request_queue *q)
 		spin_unlock(sdev->request_queue->queue_lock);
 
 		spin_lock(shost->host_lock);
-		if (unlikely(!list_empty(&sdev->starved_entry)))
-			/*
-			 * sdev lost a race, and was put back on the
-			 * starved list. This is unlikely but without this
-			 * in theory we could loop forever.
-			 */
-			break;
 	}
 	spin_unlock_irqrestore(shost->host_lock, flags);
 
@@ -1344,6 +1369,52 @@ static inline int scsi_dev_queue_ready(struct request_queue *q,
 	return 1;
 }
 
+
+/*
+ * scsi_target_queue_ready: checks if there we can send commands to target
+ * @sdev: scsi device on starget to check.
+ *
+ * Called with the host lock held.
+ */
+static inline int scsi_target_queue_ready(struct Scsi_Host *shost,
+					   struct scsi_device *sdev)
+{
+	struct scsi_target *starget = scsi_target(sdev);
+
+	if (starget->single_lun) {
+		if (starget->starget_sdev_user &&
+		    starget->starget_sdev_user != sdev)
+			return 0;
+		starget->starget_sdev_user = sdev;
+	}
+
+	if (starget->target_busy == 0 && starget->target_blocked) {
+		/*
+		 * unblock after target_blocked iterates to zero
+		 */
+		if (--starget->target_blocked == 0) {
+			SCSI_LOG_MLQUEUE(3, starget_printk(KERN_INFO, starget,
+					 "unblocking target at zero depth\n"));
+		} else {
+			blk_plug_device(sdev->request_queue);
+			return 0;
+		}
+	}
+
+	if (scsi_target_is_busy(starget)) {
+		if (list_empty(&sdev->starved_entry)) {
+			list_add_tail(&sdev->starved_entry,
+				      &shost->starved_list);
+			return 0;
+		}
+	}
+
+	/* We're OK to process the command, so we can't be starved */
+	if (!list_empty(&sdev->starved_entry))
+		list_del_init(&sdev->starved_entry);
+	return 1;
+}
+
 /*
  * scsi_host_queue_ready: if we can send requests to shost, return 1 else
  * return 0. We must end up running the queue again whenever 0 is
@@ -1390,6 +1461,7 @@ static void scsi_kill_request(struct request *req, struct request_queue *q)
 {
 	struct scsi_cmnd *cmd = req->special;
 	struct scsi_device *sdev = cmd->device;
+	struct scsi_target *starget = scsi_target(sdev);
 	struct Scsi_Host *shost = sdev->host;
 
 	blkdev_dequeue_request(req);
@@ -1413,6 +1485,7 @@ static void scsi_kill_request(struct request *req, struct request_queue *q)
 	spin_unlock(sdev->request_queue->queue_lock);
 	spin_lock(shost->host_lock);
 	shost->host_busy++;
+	starget->target_busy++;
 	spin_unlock(shost->host_lock);
 	spin_lock(sdev->request_queue->queue_lock);
 
@@ -1550,14 +1623,13 @@ static void scsi_request_fn(struct request_queue *q)
 			goto not_ready;
 		}
 
+		if (!scsi_target_queue_ready(shost, sdev))
+			goto not_ready;
+
 		if (!scsi_host_queue_ready(q, shost, sdev))
 			goto not_ready;
-		if (scsi_target(sdev)->single_lun) {
-			if (scsi_target(sdev)->starget_sdev_user &&
-			    scsi_target(sdev)->starget_sdev_user != sdev)
-				goto not_ready;
-			scsi_target(sdev)->starget_sdev_user = sdev;
-		}
+
+		scsi_target(sdev)->target_busy++;
 		shost->host_busy++;
 
 		/*
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 334862e26a1b..b14dc02c3ded 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -419,6 +419,7 @@ static struct scsi_target *scsi_alloc_target(struct device *parent,
 	dev->type = &scsi_target_type;
 	starget->id = id;
 	starget->channel = channel;
+	starget->can_queue = 0;
 	INIT_LIST_HEAD(&starget->siblings);
 	INIT_LIST_HEAD(&starget->devices);
 	starget->state = STARGET_CREATED;
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index 192f8716aa9e..3a5662b2817e 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -426,6 +426,7 @@ static inline int scsi_is_wlun(unsigned int lun)
 #define SCSI_MLQUEUE_HOST_BUSY   0x1055
 #define SCSI_MLQUEUE_DEVICE_BUSY 0x1056
 #define SCSI_MLQUEUE_EH_RETRY    0x1057
+#define SCSI_MLQUEUE_TARGET_BUSY 0x1058
 
 /*
  *  Use these to separate status msg and our bytes
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index b49e725be039..a37a8148a310 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -238,6 +238,16 @@ struct scsi_target {
 						 * for the device at a time. */
 	unsigned int		pdt_1f_for_no_lun;	/* PDT = 0x1f */
 						/* means no lun present */
+	/* commands actually active on LLD. protected by host lock. */
+	unsigned int		target_busy;
+	/*
+	 * LLDs should set this in the slave_alloc host template callout.
+	 * If set to zero then there is not limit.
+	 */
+	unsigned int		can_queue;
+	unsigned int		target_blocked;
+	unsigned int		max_target_blocked;
+#define SCSI_DEFAULT_TARGET_BLOCKED	3
 
 	char			scsi_level;
 	struct execute_work	ew;
-- 
cgit v1.2.3


From fff9d40ce0eb4b46f3e186823ceab6bc02c3e5d3 Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Tue, 19 Aug 2008 18:45:23 -0500
Subject: [SCSI] fc class: unblock target after calling terminate callback
 (take 2)

When we block a rport and the driver implements the terminate
callback we will fail IO that was running quickly. However
IO that was in the scsi_device/block queue sits there until
the dev_loss_tmo fires, and this can make it look like IO is
lost because new IO will get executed but that IO stuck in
the blocked queue sits there for some time longer.

With this patch when the fast io fail tmo fires, we will
fail the blocked IO and any new IO. This patch also allows
all drivers to partially support the fast io fail tmo. If the
terminate io callback is not implemented, we will still fail blocked
IO and any new IO, so multipath can handle that.

This patch also allows the fc and iscsi classes to implement the
same behavior. The timers are just unfornately named differently.

This patch also fixes the problem where drivers were unblocking
the target in their terminate callback, which was needed for
rport removal, but for fast io fail timeout it would cause
IO to bounce arround the scsi/block layer and the LLD queuecommand.
And it for drivers that could have IO stuck but did not have
a terminate callback the unblock calls in the class will fix
them.

v2.
- fix up bit setting style to meet JamesS's pref.
- Broke out new host byte error changes to make it easier to read.
- added JamesS's ack from list.
v1
- initial patch

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Acked-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/scsi/scsi_transport_fc.c | 47 ++++++++++++++++++++++++----------------
 include/scsi/scsi_transport_fc.h |  6 ++++-
 2 files changed, 33 insertions(+), 20 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index d5f7653bb94b..1e71abf0607a 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -2133,8 +2133,7 @@ fc_attach_transport(struct fc_function_template *ft)
 	SETUP_PRIVATE_RPORT_ATTRIBUTE_RD(roles);
 	SETUP_PRIVATE_RPORT_ATTRIBUTE_RD(port_state);
 	SETUP_PRIVATE_RPORT_ATTRIBUTE_RD(scsi_target_id);
-	if (ft->terminate_rport_io)
-		SETUP_PRIVATE_RPORT_ATTRIBUTE_RW(fast_io_fail_tmo);
+	SETUP_PRIVATE_RPORT_ATTRIBUTE_RW(fast_io_fail_tmo);
 
 	BUG_ON(count > FC_RPORT_NUM_ATTRS);
 
@@ -2328,6 +2327,22 @@ fc_remove_host(struct Scsi_Host *shost)
 }
 EXPORT_SYMBOL(fc_remove_host);
 
+static void fc_terminate_rport_io(struct fc_rport *rport)
+{
+	struct Scsi_Host *shost = rport_to_shost(rport);
+	struct fc_internal *i = to_fc_internal(shost->transportt);
+
+	/* Involve the LLDD if possible to terminate all io on the rport. */
+	if (i->f->terminate_rport_io)
+		i->f->terminate_rport_io(rport);
+
+	/*
+	 * must unblock to flush queued IO. The caller will have set
+	 * the port_state or flags, so that fc_remote_port_chkready will
+	 * fail IO.
+	 */
+	scsi_target_unblock(&rport->dev);
+}
 
 /**
  * fc_starget_delete - called to delete the scsi decendents of an rport
@@ -2340,13 +2355,8 @@ fc_starget_delete(struct work_struct *work)
 {
 	struct fc_rport *rport =
 		container_of(work, struct fc_rport, stgt_delete_work);
-	struct Scsi_Host *shost = rport_to_shost(rport);
-	struct fc_internal *i = to_fc_internal(shost->transportt);
-
-	/* Involve the LLDD if possible to terminate all io on the rport. */
-	if (i->f->terminate_rport_io)
-		i->f->terminate_rport_io(rport);
 
+	fc_terminate_rport_io(rport);
 	scsi_remove_target(&rport->dev);
 }
 
@@ -2372,10 +2382,7 @@ fc_rport_final_delete(struct work_struct *work)
 	if (rport->flags & FC_RPORT_SCAN_PENDING)
 		scsi_flush_work(shost);
 
-	/* involve the LLDD to terminate all pending i/o */
-	if (i->f->terminate_rport_io)
-		i->f->terminate_rport_io(rport);
-
+	fc_terminate_rport_io(rport);
 	/*
 	 * Cancel any outstanding timers. These should really exist
 	 * only when rmmod'ing the LLDD and we're asking for
@@ -2639,7 +2646,8 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel,
 
 				spin_lock_irqsave(shost->host_lock, flags);
 
-				rport->flags &= ~FC_RPORT_DEVLOSS_PENDING;
+				rport->flags &= ~(FC_RPORT_FAST_FAIL_TIMEDOUT |
+						  FC_RPORT_DEVLOSS_PENDING);
 
 				/* if target, initiate a scan */
 				if (rport->scsi_target_id != -1) {
@@ -2702,6 +2710,7 @@ fc_remote_port_add(struct Scsi_Host *shost, int channel,
 			rport->port_id = ids->port_id;
 			rport->roles = ids->roles;
 			rport->port_state = FC_PORTSTATE_ONLINE;
+			rport->flags &= ~FC_RPORT_FAST_FAIL_TIMEDOUT;
 
 			if (fci->f->dd_fcrport_size)
 				memset(rport->dd_data, 0,
@@ -2784,7 +2793,6 @@ void
 fc_remote_port_delete(struct fc_rport  *rport)
 {
 	struct Scsi_Host *shost = rport_to_shost(rport);
-	struct fc_internal *i = to_fc_internal(shost->transportt);
 	int timeout = rport->dev_loss_tmo;
 	unsigned long flags;
 
@@ -2830,7 +2838,7 @@ fc_remote_port_delete(struct fc_rport  *rport)
 
 	/* see if we need to kill io faster than waiting for device loss */
 	if ((rport->fast_io_fail_tmo != -1) &&
-	    (rport->fast_io_fail_tmo < timeout) && (i->f->terminate_rport_io))
+	    (rport->fast_io_fail_tmo < timeout))
 		fc_queue_devloss_work(shost, &rport->fail_io_work,
 					rport->fast_io_fail_tmo * HZ);
 
@@ -2906,7 +2914,8 @@ fc_remote_port_rolechg(struct fc_rport  *rport, u32 roles)
 			fc_flush_devloss(shost);
 
 		spin_lock_irqsave(shost->host_lock, flags);
-		rport->flags &= ~FC_RPORT_DEVLOSS_PENDING;
+		rport->flags &= ~(FC_RPORT_FAST_FAIL_TIMEDOUT |
+				  FC_RPORT_DEVLOSS_PENDING);
 		spin_unlock_irqrestore(shost->host_lock, flags);
 
 		/* ensure any stgt delete functions are done */
@@ -3001,6 +3010,7 @@ fc_timeout_deleted_rport(struct work_struct *work)
 	rport->supported_classes = FC_COS_UNSPECIFIED;
 	rport->roles = FC_PORT_ROLE_UNKNOWN;
 	rport->port_state = FC_PORTSTATE_NOTPRESENT;
+	rport->flags &= ~FC_RPORT_FAST_FAIL_TIMEDOUT;
 
 	/* remove the identifiers that aren't used in the consisting binding */
 	switch (fc_host->tgtid_bind_type) {
@@ -3043,13 +3053,12 @@ fc_timeout_fail_rport_io(struct work_struct *work)
 {
 	struct fc_rport *rport =
 		container_of(work, struct fc_rport, fail_io_work.work);
-	struct Scsi_Host *shost = rport_to_shost(rport);
-	struct fc_internal *i = to_fc_internal(shost->transportt);
 
 	if (rport->port_state != FC_PORTSTATE_BLOCKED)
 		return;
 
-	i->f->terminate_rport_io(rport);
+	rport->flags |= FC_RPORT_FAST_FAIL_TIMEDOUT;
+	fc_terminate_rport_io(rport);
 }
 
 /**
diff --git a/include/scsi/scsi_transport_fc.h b/include/scsi/scsi_transport_fc.h
index 21018a4df452..fb8d01370663 100644
--- a/include/scsi/scsi_transport_fc.h
+++ b/include/scsi/scsi_transport_fc.h
@@ -357,6 +357,7 @@ struct fc_rport {	/* aka fc_starget_attrs */
 /* bit field values for struct fc_rport "flags" field: */
 #define FC_RPORT_DEVLOSS_PENDING	0x01
 #define FC_RPORT_SCAN_PENDING		0x02
+#define FC_RPORT_FAST_FAIL_TIMEDOUT	0x03
 
 #define	dev_to_rport(d)				\
 	container_of(d, struct fc_rport, dev)
@@ -683,7 +684,10 @@ fc_remote_port_chkready(struct fc_rport *rport)
 			result = DID_NO_CONNECT << 16;
 		break;
 	case FC_PORTSTATE_BLOCKED:
-		result = DID_IMM_RETRY << 16;
+		if (rport->flags & FC_RPORT_FAST_FAIL_TIMEDOUT)
+			result = DID_NO_CONNECT << 16;
+		else
+			result = DID_IMM_RETRY << 16;
 		break;
 	default:
 		result = DID_NO_CONNECT << 16;
-- 
cgit v1.2.3


From a4dfaa6f2e55b736adf2719133996f7e7dc309bc Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Tue, 19 Aug 2008 18:45:25 -0500
Subject: [SCSI] scsi: add transport host byte errors (v3)

Currently, if there is a transport problem the iscsi drivers will return
outstanding commands (commands being exeucted by the driver/fw/hw) with
DID_BUS_BUSY and block the session so no new commands can be queued.
Commands that are caught between the failure handling and blocking are
failed with DID_IMM_RETRY or one of the scsi ml queuecommand return values.
When the recovery_timeout fires, the iscsi drivers then fail IO with
DID_NO_CONNECT.

For fcp, some drivers will fail some outstanding IO (disk but possibly not
tape) with DID_BUS_BUSY or DID_ERROR or some other value that causes a retry
and hits the scsi_error.c failfast check, block the rport, and commands
caught in the race are failed with DID_IMM_RETRY. Other drivers, may
hold onto all IO and wait for the terminate_rport_io or dev_loss_tmo_callbk
to be called.

The following patches attempt to unify what upper layers will see drivers
like multipath can make a good guess. This relies on drivers being
hooked into their transport class.

This first patch just defines two new host byte errors so drivers can
return the same value for when a rport/session is blocked and for
when the fast_io_fail_tmo fires.

The idea is that if the LLD/class detects a problem and is going to block
a rport/session, then if the LLD wants or must return the command to scsi-ml,
then it can return it with DID_TRANSPORT_DISRUPTED. This will requeue
the IO into the same scsi queue it came from, until the fast io fail timer
fires and the class decides what to do.

When using multipath and the fast_io_fail_tmo fires then the class
can fail commands with DID_TRANSPORT_FAILFAST or drivers can use
DID_TRANSPORT_FAILFAST in their terminate_rport_io callbacks or
the equivlent in iscsi if we ever implement more advanced recovery methods.
A LLD, like lpfc, could continue to return DID_ERROR and then it will hit
the normal failfast path, so drivers do not have fully be ported to
work better. The point of the patches is that upper layers will
not see a failure that could be recovered from while the rport/session is
blocked until fast_io_fail_tmo/recovery_timeout fires.

V3
Remove some comments.
V2
Fixed patch/diff errors and renamed DID_TRANSPORT_BLOCKED to
DID_TRANSPORT_DISRUPTED.
V1
initial patch.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/scsi/constants.c  |  3 ++-
 drivers/scsi/scsi_error.c | 15 ++++++++++++++-
 include/scsi/scsi.h       |  5 +++++
 3 files changed, 21 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/constants.c b/drivers/scsi/constants.c
index 9785d7384199..4003deefb7d8 100644
--- a/drivers/scsi/constants.c
+++ b/drivers/scsi/constants.c
@@ -1364,7 +1364,8 @@ EXPORT_SYMBOL(scsi_print_sense);
 static const char * const hostbyte_table[]={
 "DID_OK", "DID_NO_CONNECT", "DID_BUS_BUSY", "DID_TIME_OUT", "DID_BAD_TARGET",
 "DID_ABORT", "DID_PARITY", "DID_ERROR", "DID_RESET", "DID_BAD_INTR",
-"DID_PASSTHROUGH", "DID_SOFT_ERROR", "DID_IMM_RETRY", "DID_REQUEUE"};
+"DID_PASSTHROUGH", "DID_SOFT_ERROR", "DID_IMM_RETRY", "DID_REQUEUE",
+"DID_TRANSPORT_DISRUPTED", "DID_TRANSPORT_FAILFAST" };
 #define NUM_HOSTBYTE_STRS ARRAY_SIZE(hostbyte_table)
 
 static const char * const driverbyte_table[]={
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index fecefa05cb62..5bf8be21a165 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -1290,7 +1290,20 @@ int scsi_decide_disposition(struct scsi_cmnd *scmd)
 
 	case DID_REQUEUE:
 		return ADD_TO_MLQUEUE;
-
+	case DID_TRANSPORT_DISRUPTED:
+		/*
+		 * LLD/transport was disrupted during processing of the IO.
+		 * The transport class is now blocked/blocking,
+		 * and the transport will decide what to do with the IO
+		 * based on its timers and recovery capablilities.
+		 */
+		return ADD_TO_MLQUEUE;
+	case DID_TRANSPORT_FAILFAST:
+		/*
+		 * The transport decided to failfast the IO (most likely
+		 * the fast io fail tmo fired), so send IO directly upwards.
+		 */
+		return SUCCESS;
 	case DID_ERROR:
 		if (msg_byte(scmd->result) == COMMAND_COMPLETE &&
 		    status_byte(scmd->result) == RESERVATION_CONFLICT)
diff --git a/include/scsi/scsi.h b/include/scsi/scsi.h
index 3a5662b2817e..a109165714d6 100644
--- a/include/scsi/scsi.h
+++ b/include/scsi/scsi.h
@@ -381,6 +381,11 @@ static inline int scsi_is_wlun(unsigned int lun)
 #define DID_IMM_RETRY   0x0c	/* Retry without decrementing retry count  */
 #define DID_REQUEUE	0x0d	/* Requeue command (no immediate retry) also
 				 * without decrementing the retry count	   */
+#define DID_TRANSPORT_DISRUPTED 0x0e /* Transport error disrupted execution
+				      * and the driver blocked the port to
+				      * recover the link. Transport class will
+				      * retry or fail IO */
+#define DID_TRANSPORT_FAILFAST	0x0f /* Transport class fastfailed the io */
 #define DRIVER_OK       0x00	/* Driver status                           */
 
 /*
-- 
cgit v1.2.3


From f46e307da925a7b71a0018c0510cdc6e588b87fc Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Tue, 19 Aug 2008 18:45:27 -0500
Subject: [SCSI] fc class: Add support for new transport errors

If the target is blocked and fast io fail tmo has not fired
then we requeue with DID_TRANSPORT_DISRUPTED. Once that
tmo fires we fail with DID_TRANSPORT_FAILFAST.

v2
- seperate from
"fc class: unblock target after calling terminate callback"
to make it easier to review.
- Add JamesS's ack from list.
v2
- initial patch

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Acked-by: James Smart <James.Smart@emulex.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 include/scsi/scsi_transport_fc.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/scsi/scsi_transport_fc.h b/include/scsi/scsi_transport_fc.h
index fb8d01370663..49d8913c4f86 100644
--- a/include/scsi/scsi_transport_fc.h
+++ b/include/scsi/scsi_transport_fc.h
@@ -679,15 +679,15 @@ fc_remote_port_chkready(struct fc_rport *rport)
 		if (rport->roles & FC_PORT_ROLE_FCP_TARGET)
 			result = 0;
 		else if (rport->flags & FC_RPORT_DEVLOSS_PENDING)
-			result = DID_IMM_RETRY << 16;
+			result = DID_TRANSPORT_DISRUPTED << 16;
 		else
 			result = DID_NO_CONNECT << 16;
 		break;
 	case FC_PORTSTATE_BLOCKED:
 		if (rport->flags & FC_RPORT_FAST_FAIL_TIMEDOUT)
-			result = DID_NO_CONNECT << 16;
+			result = DID_TRANSPORT_FAILFAST << 16;
 		else
-			result = DID_IMM_RETRY << 16;
+			result = DID_TRANSPORT_DISRUPTED << 16;
 		break;
 	default:
 		result = DID_NO_CONNECT << 16;
-- 
cgit v1.2.3


From 6000a368cd8e6da1caf101411bdb494cd6fb8b09 Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Tue, 19 Aug 2008 18:45:30 -0500
Subject: [SCSI] block: separate failfast into multiple bits.

Multipath is best at handling transport errors. If it gets a device
error then there is not much the multipath layer can do. It will just
access the same device but from a different path.

This patch breaks up failfast into device, transport and driver errors.
The multipath layers (md and dm mutlipath) only ask the lower levels to
fast fail transport errors. The user of failfast, read ahead, will ask
to fast fail on all errors.

Note that blk_noretry_request will return true if any failfast bit
is set. This allows drivers that do not support the multipath failfast
bits to continue to fail on any failfast error like before. Drivers
like scsi that are able to fail fast specific errors can check
for the specific fail fast type. In the next patch I will convert
scsi.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 block/blk-core.c                            | 11 +++++++++--
 drivers/md/dm-mpath.c                       |  2 +-
 drivers/md/multipath.c                      |  4 ++--
 drivers/s390/block/dasd_diag.c              |  2 +-
 drivers/s390/block/dasd_eckd.c              |  2 +-
 drivers/s390/block/dasd_fba.c               |  2 +-
 drivers/scsi/device_handler/scsi_dh_alua.c  |  3 ++-
 drivers/scsi/device_handler/scsi_dh_emc.c   |  3 ++-
 drivers/scsi/device_handler/scsi_dh_hp_sw.c |  6 ++++--
 drivers/scsi/device_handler/scsi_dh_rdac.c  |  3 ++-
 drivers/scsi/scsi_transport_spi.c           |  4 +++-
 include/linux/bio.h                         | 26 +++++++++++++++++---------
 include/linux/blkdev.h                      | 15 ++++++++++++---
 13 files changed, 57 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index 2d053b584410..9e79a485e4f3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1075,8 +1075,15 @@ void init_request_from_bio(struct request *req, struct bio *bio)
 	/*
 	 * inherit FAILFAST from bio (for read-ahead, and explicit FAILFAST)
 	 */
-	if (bio_rw_ahead(bio) || bio_failfast(bio))
-		req->cmd_flags |= REQ_FAILFAST;
+	if (bio_rw_ahead(bio))
+		req->cmd_flags |= (REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+				   REQ_FAILFAST_DRIVER);
+	if (bio_failfast_dev(bio))
+		req->cmd_flags |= REQ_FAILFAST_DEV;
+	if (bio_failfast_transport(bio))
+		req->cmd_flags |= REQ_FAILFAST_TRANSPORT;
+	if (bio_failfast_driver(bio))
+		req->cmd_flags |= REQ_FAILFAST_DRIVER;
 
 	/*
 	 * REQ_BARRIER implies no merging, but lets make it explicit
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 103304c1e3b0..9bf3460c5540 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -849,7 +849,7 @@ static int multipath_map(struct dm_target *ti, struct bio *bio,
 	dm_bio_record(&mpio->details, bio);
 
 	map_context->ptr = mpio;
-	bio->bi_rw |= (1 << BIO_RW_FAILFAST);
+	bio->bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT);
 	r = map_io(m, bio, mpio, 0);
 	if (r < 0 || r == DM_MAPIO_REQUEUE)
 		mempool_free(mpio, m->mpio_pool);
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index 8bb8794129b3..7ae33ebaf7ec 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -176,7 +176,7 @@ static int multipath_make_request (struct request_queue *q, struct bio * bio)
 	mp_bh->bio = *bio;
 	mp_bh->bio.bi_sector += multipath->rdev->data_offset;
 	mp_bh->bio.bi_bdev = multipath->rdev->bdev;
-	mp_bh->bio.bi_rw |= (1 << BIO_RW_FAILFAST);
+	mp_bh->bio.bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT);
 	mp_bh->bio.bi_end_io = multipath_end_request;
 	mp_bh->bio.bi_private = mp_bh;
 	generic_make_request(&mp_bh->bio);
@@ -402,7 +402,7 @@ static void multipathd (mddev_t *mddev)
 			*bio = *(mp_bh->master_bio);
 			bio->bi_sector += conf->multipaths[mp_bh->path].rdev->data_offset;
 			bio->bi_bdev = conf->multipaths[mp_bh->path].rdev->bdev;
-			bio->bi_rw |= (1 << BIO_RW_FAILFAST);
+			bio->bi_rw |= (1 << BIO_RW_FAILFAST_TRANSPORT);
 			bio->bi_end_io = multipath_end_request;
 			bio->bi_private = mp_bh;
 			generic_make_request(bio);
diff --git a/drivers/s390/block/dasd_diag.c b/drivers/s390/block/dasd_diag.c
index 85fcb4371054..7844461a995b 100644
--- a/drivers/s390/block/dasd_diag.c
+++ b/drivers/s390/block/dasd_diag.c
@@ -544,7 +544,7 @@ static struct dasd_ccw_req *dasd_diag_build_cp(struct dasd_device *memdev,
 	}
 	cqr->retries = DIAG_MAX_RETRIES;
 	cqr->buildclk = get_clock();
-	if (req->cmd_flags & REQ_FAILFAST)
+	if (blk_noretry_request(req))
 		set_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags);
 	cqr->startdev = memdev;
 	cqr->memdev = memdev;
diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 49f9d221e23d..2e60d5f968c8 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1700,7 +1700,7 @@ static struct dasd_ccw_req *dasd_eckd_build_cp(struct dasd_device *startdev,
 			recid++;
 		}
 	}
-	if (req->cmd_flags & REQ_FAILFAST)
+	if (blk_noretry_request(req))
 		set_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags);
 	cqr->startdev = startdev;
 	cqr->memdev = startdev;
diff --git a/drivers/s390/block/dasd_fba.c b/drivers/s390/block/dasd_fba.c
index 93d9b6452a94..7d442aeff3d1 100644
--- a/drivers/s390/block/dasd_fba.c
+++ b/drivers/s390/block/dasd_fba.c
@@ -355,7 +355,7 @@ static struct dasd_ccw_req *dasd_fba_build_cp(struct dasd_device * memdev,
 			recid++;
 		}
 	}
-	if (req->cmd_flags & REQ_FAILFAST)
+	if (blk_noretry_request(req))
 		set_bit(DASD_CQR_FLAGS_FAILFAST, &cqr->flags);
 	cqr->startdev = memdev;
 	cqr->memdev = memdev;
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
index 708e475896b9..cb8aa3b58c22 100644
--- a/drivers/scsi/device_handler/scsi_dh_alua.c
+++ b/drivers/scsi/device_handler/scsi_dh_alua.c
@@ -109,7 +109,8 @@ static struct request *get_alua_req(struct scsi_device *sdev,
 	}
 
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->cmd_flags |= REQ_FAILFAST | REQ_NOMERGE;
+	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			 REQ_FAILFAST_DRIVER | REQ_NOMERGE;
 	rq->retries = ALUA_FAILOVER_RETRIES;
 	rq->timeout = ALUA_FAILOVER_TIMEOUT;
 
diff --git a/drivers/scsi/device_handler/scsi_dh_emc.c b/drivers/scsi/device_handler/scsi_dh_emc.c
index 8f45570a8a01..0e572d2c5b0a 100644
--- a/drivers/scsi/device_handler/scsi_dh_emc.c
+++ b/drivers/scsi/device_handler/scsi_dh_emc.c
@@ -303,7 +303,8 @@ static struct request *get_req(struct scsi_device *sdev, int cmd,
 
 	rq->cmd[4] = len;
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->cmd_flags |= REQ_FAILFAST;
+	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			 REQ_FAILFAST_DRIVER;
 	rq->timeout = CLARIION_TIMEOUT;
 	rq->retries = CLARIION_RETRIES;
 
diff --git a/drivers/scsi/device_handler/scsi_dh_hp_sw.c b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
index 5e93c88ad66b..9aec4ca64e56 100644
--- a/drivers/scsi/device_handler/scsi_dh_hp_sw.c
+++ b/drivers/scsi/device_handler/scsi_dh_hp_sw.c
@@ -112,7 +112,8 @@ static int hp_sw_tur(struct scsi_device *sdev, struct hp_sw_dh_data *h)
 		return SCSI_DH_RES_TEMP_UNAVAIL;
 
 	req->cmd_type = REQ_TYPE_BLOCK_PC;
-	req->cmd_flags |= REQ_FAILFAST;
+	req->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			  REQ_FAILFAST_DRIVER;
 	req->cmd_len = COMMAND_SIZE(TEST_UNIT_READY);
 	req->cmd[0] = TEST_UNIT_READY;
 	req->timeout = HP_SW_TIMEOUT;
@@ -204,7 +205,8 @@ static int hp_sw_start_stop(struct scsi_device *sdev, struct hp_sw_dh_data *h)
 		return SCSI_DH_RES_TEMP_UNAVAIL;
 
 	req->cmd_type = REQ_TYPE_BLOCK_PC;
-	req->cmd_flags |= REQ_FAILFAST;
+	req->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			  REQ_FAILFAST_DRIVER;
 	req->cmd_len = COMMAND_SIZE(START_STOP);
 	req->cmd[0] = START_STOP;
 	req->cmd[4] = 1;	/* Start spin cycle */
diff --git a/drivers/scsi/device_handler/scsi_dh_rdac.c b/drivers/scsi/device_handler/scsi_dh_rdac.c
index 50bf95f3b5c4..a43c3ed4df28 100644
--- a/drivers/scsi/device_handler/scsi_dh_rdac.c
+++ b/drivers/scsi/device_handler/scsi_dh_rdac.c
@@ -226,7 +226,8 @@ static struct request *get_rdac_req(struct scsi_device *sdev,
 	}
 
 	rq->cmd_type = REQ_TYPE_BLOCK_PC;
-	rq->cmd_flags |= REQ_FAILFAST | REQ_NOMERGE;
+	rq->cmd_flags |= REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT |
+			 REQ_FAILFAST_DRIVER;
 	rq->retries = RDAC_RETRIES;
 	rq->timeout = RDAC_TIMEOUT;
 
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index b29360ed0bdc..7c2d28924d2a 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -109,7 +109,9 @@ static int spi_execute(struct scsi_device *sdev, const void *cmd,
 	for(i = 0; i < DV_RETRIES; i++) {
 		result = scsi_execute(sdev, cmd, dir, buffer, bufflen,
 				      sense, DV_TIMEOUT, /* retries */ 1,
-				      REQ_FAILFAST);
+				      REQ_FAILFAST_DEV |
+				      REQ_FAILFAST_TRANSPORT |
+				      REQ_FAILFAST_DRIVER);
 		if (result & DRIVER_SENSE) {
 			struct scsi_sense_hdr sshdr_tmp;
 			if (!sshdr)
diff --git a/include/linux/bio.h b/include/linux/bio.h
index ff5b4cf9e2da..1beda208cbfb 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -129,25 +129,30 @@ struct bio {
  * bit 2 -- barrier
  *	Insert a serialization point in the IO queue, forcing previously
  *	submitted IO to be completed before this oen is issued.
- * bit 3 -- fail fast, don't want low level driver retries
- * bit 4 -- synchronous I/O hint: the block layer will unplug immediately
+ * bit 3 -- synchronous I/O hint: the block layer will unplug immediately
  *	Note that this does NOT indicate that the IO itself is sync, just
  *	that the block layer will not postpone issue of this IO by plugging.
- * bit 5 -- metadata request
+ * bit 4 -- metadata request
  *	Used for tracing to differentiate metadata and data IO. May also
  *	get some preferential treatment in the IO scheduler
- * bit 6 -- discard sectors
+ * bit 5 -- discard sectors
  *	Informs the lower level device that this range of sectors is no longer
  *	used by the file system and may thus be freed by the device. Used
  *	for flash based storage.
+ * bit 6 -- fail fast device errors
+ * bit 7 -- fail fast transport errors
+ * bit 8 -- fail fast driver errors
+ *	Don't want driver retries for any fast fail whatever the reason.
  */
 #define BIO_RW		0	/* Must match RW in req flags (blkdev.h) */
 #define BIO_RW_AHEAD	1	/* Must match FAILFAST in req flags */
 #define BIO_RW_BARRIER	2
-#define BIO_RW_FAILFAST	3
-#define BIO_RW_SYNC	4
-#define BIO_RW_META	5
-#define BIO_RW_DISCARD	6
+#define BIO_RW_SYNC	3
+#define BIO_RW_META	4
+#define BIO_RW_DISCARD	5
+#define BIO_RW_FAILFAST_DEV		6
+#define BIO_RW_FAILFAST_TRANSPORT	7
+#define BIO_RW_FAILFAST_DRIVER		8
 
 /*
  * upper 16 bits of bi_rw define the io priority of this bio
@@ -174,7 +179,10 @@ struct bio {
 #define bio_sectors(bio)	((bio)->bi_size >> 9)
 #define bio_barrier(bio)	((bio)->bi_rw & (1 << BIO_RW_BARRIER))
 #define bio_sync(bio)		((bio)->bi_rw & (1 << BIO_RW_SYNC))
-#define bio_failfast(bio)	((bio)->bi_rw & (1 << BIO_RW_FAILFAST))
+#define bio_failfast_dev(bio)	((bio)->bi_rw &	(1 << BIO_RW_FAILFAST_DEV))
+#define bio_failfast_transport(bio)	\
+	((bio)->bi_rw & (1 << BIO_RW_FAILFAST_TRANSPORT))
+#define bio_failfast_driver(bio) ((bio)->bi_rw & (1 << BIO_RW_FAILFAST_DRIVER))
 #define bio_rw_ahead(bio)	((bio)->bi_rw & (1 << BIO_RW_AHEAD))
 #define bio_rw_meta(bio)	((bio)->bi_rw & (1 << BIO_RW_META))
 #define bio_discard(bio)	((bio)->bi_rw & (1 << BIO_RW_DISCARD))
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a92d9e4ea96e..f3491d225268 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -87,7 +87,9 @@ enum {
  */
 enum rq_flag_bits {
 	__REQ_RW,		/* not set, read. set, write */
-	__REQ_FAILFAST,		/* no low level driver retries */
+	__REQ_FAILFAST_DEV,	/* no driver retries of device errors */
+	__REQ_FAILFAST_TRANSPORT, /* no driver retries of transport errors */
+	__REQ_FAILFAST_DRIVER,	/* no driver retries of driver errors */
 	__REQ_DISCARD,		/* request to discard sectors */
 	__REQ_SORTED,		/* elevator knows about this request */
 	__REQ_SOFTBARRIER,	/* may not be passed by ioscheduler */
@@ -111,8 +113,10 @@ enum rq_flag_bits {
 };
 
 #define REQ_RW		(1 << __REQ_RW)
+#define REQ_FAILFAST_DEV	(1 << __REQ_FAILFAST_DEV)
+#define REQ_FAILFAST_TRANSPORT	(1 << __REQ_FAILFAST_TRANSPORT)
+#define REQ_FAILFAST_DRIVER	(1 << __REQ_FAILFAST_DRIVER)
 #define REQ_DISCARD	(1 << __REQ_DISCARD)
-#define REQ_FAILFAST	(1 << __REQ_FAILFAST)
 #define REQ_SORTED	(1 << __REQ_SORTED)
 #define REQ_SOFTBARRIER	(1 << __REQ_SOFTBARRIER)
 #define REQ_HARDBARRIER	(1 << __REQ_HARDBARRIER)
@@ -560,7 +564,12 @@ enum {
 #define blk_special_request(rq)	((rq)->cmd_type == REQ_TYPE_SPECIAL)
 #define blk_sense_request(rq)	((rq)->cmd_type == REQ_TYPE_SENSE)
 
-#define blk_noretry_request(rq)	((rq)->cmd_flags & REQ_FAILFAST)
+#define blk_failfast_dev(rq)	((rq)->cmd_flags & REQ_FAILFAST_DEV)
+#define blk_failfast_transport(rq) ((rq)->cmd_flags & REQ_FAILFAST_TRANSPORT)
+#define blk_failfast_driver(rq)	((rq)->cmd_flags & REQ_FAILFAST_DRIVER)
+#define blk_noretry_request(rq)	(blk_failfast_dev(rq) ||	\
+				 blk_failfast_transport(rq) ||	\
+				 blk_failfast_driver(rq))
 #define blk_rq_started(rq)	((rq)->cmd_flags & REQ_STARTED)
 
 #define blk_account_rq(rq)	(blk_rq_started(rq) && (blk_fs_request(rq) || blk_discard_rq(rq))) 
-- 
cgit v1.2.3


From e5bd7b54e93ef7151469a12b8c28d863b9f8a088 Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Wed, 24 Sep 2008 11:46:10 -0500
Subject: [SCSI] libiscsi: Support drivers initiating session removal

If the driver knows when hardware is removed like with cxgb3i,
bnx2i, qla4xxx and iser then we will want to remove the sessions/devices
that are bound to that device before removing the host.

cxgb3i and in the future bnx2i will remove the host and that will
remove all the sessions on the hba. iser can call iscsi_kill_session
when it gets an event that indicates that a hca is removed.
And when qla4xxx is hooked in to the lib (it is only hooked into
the class right now) it can call iscsi remove host like the
partial offload card drivers.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/infiniband/ulp/iser/iscsi_iser.c |   1 +
 drivers/scsi/iscsi_tcp.c                 |   1 +
 drivers/scsi/libiscsi.c                  | 107 ++++++++++++++++++++++++++++---
 drivers/scsi/qla4xxx/ql4_os.c            |   2 +-
 drivers/scsi/scsi_transport_iscsi.c      |   6 +-
 include/scsi/iscsi_if.h                  |   1 +
 include/scsi/libiscsi.h                  |  13 ++++
 include/scsi/scsi_transport_iscsi.h      |   3 +-
 8 files changed, 121 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 5a1cf2580e16..0474da173eb1 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -378,6 +378,7 @@ static void iscsi_iser_session_destroy(struct iscsi_cls_session *cls_session)
 {
 	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
 
+	iscsi_session_teardown(cls_session);
 	iscsi_host_remove(shost);
 	iscsi_host_free(shost);
 }
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index e960f00da93a..752f42884cc1 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -1885,6 +1885,7 @@ static void iscsi_tcp_session_destroy(struct iscsi_cls_session *cls_session)
 	struct Scsi_Host *shost = iscsi_session_to_shost(cls_session);
 
 	iscsi_r2tpool_free(cls_session->dd_data);
+	iscsi_session_teardown(cls_session);
 
 	iscsi_host_remove(shost);
 	iscsi_host_free(shost);
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index f9539af28f02..390781894be9 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -983,6 +983,38 @@ struct iscsi_task *iscsi_itt_to_ctask(struct iscsi_conn *conn, itt_t itt)
 }
 EXPORT_SYMBOL_GPL(iscsi_itt_to_ctask);
 
+void iscsi_session_failure(struct iscsi_cls_session *cls_session,
+			   enum iscsi_err err)
+{
+	struct iscsi_session *session = cls_session->dd_data;
+	struct iscsi_conn *conn;
+	struct device *dev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&session->lock, flags);
+	conn = session->leadconn;
+	if (session->state == ISCSI_STATE_TERMINATE || !conn) {
+		spin_unlock_irqrestore(&session->lock, flags);
+		return;
+	}
+
+	dev = get_device(&conn->cls_conn->dev);
+	spin_unlock_irqrestore(&session->lock, flags);
+	if (!dev)
+	        return;
+	/*
+	 * if the host is being removed bypass the connection
+	 * recovery initialization because we are going to kill
+	 * the session.
+	 */
+	if (err == ISCSI_ERR_INVALID_HOST)
+		iscsi_conn_error_event(conn->cls_conn, err);
+	else
+		iscsi_conn_failure(conn, err);
+	put_device(dev);
+}
+EXPORT_SYMBOL_GPL(iscsi_session_failure);
+
 void iscsi_conn_failure(struct iscsi_conn *conn, enum iscsi_err err)
 {
 	struct iscsi_session *session = conn->session;
@@ -997,9 +1029,10 @@ void iscsi_conn_failure(struct iscsi_conn *conn, enum iscsi_err err)
 	if (conn->stop_stage == 0)
 		session->state = ISCSI_STATE_FAILED;
 	spin_unlock_irqrestore(&session->lock, flags);
+
 	set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_tx);
 	set_bit(ISCSI_SUSPEND_BIT, &conn->suspend_rx);
-	iscsi_conn_error(conn->cls_conn, err);
+	iscsi_conn_error_event(conn->cls_conn, err);
 }
 EXPORT_SYMBOL_GPL(iscsi_conn_failure);
 
@@ -1905,6 +1938,7 @@ struct Scsi_Host *iscsi_host_alloc(struct scsi_host_template *sht,
 				   int dd_data_size, uint16_t qdepth)
 {
 	struct Scsi_Host *shost;
+	struct iscsi_host *ihost;
 
 	shost = scsi_host_alloc(sht, sizeof(struct iscsi_host) + dd_data_size);
 	if (!shost)
@@ -1919,22 +1953,43 @@ struct Scsi_Host *iscsi_host_alloc(struct scsi_host_template *sht,
 		qdepth = ISCSI_DEF_CMD_PER_LUN;
 	}
 	shost->cmd_per_lun = qdepth;
+
+	ihost = shost_priv(shost);
+	spin_lock_init(&ihost->lock);
+	ihost->state = ISCSI_HOST_SETUP;
+	ihost->num_sessions = 0;
+	init_waitqueue_head(&ihost->session_removal_wq);
 	return shost;
 }
 EXPORT_SYMBOL_GPL(iscsi_host_alloc);
 
+static void iscsi_notify_host_removed(struct iscsi_cls_session *cls_session)
+{
+	iscsi_session_failure(cls_session, ISCSI_ERR_INVALID_HOST);
+}
+
 /**
  * iscsi_host_remove - remove host and sessions
  * @shost: scsi host
  *
- * This will also remove any sessions attached to the host, but if userspace
- * is managing the session at the same time this will break. TODO: add
- * refcounting to the netlink iscsi interface so a rmmod or host hot unplug
- * does not remove the memory from under us.
+ * If there are any sessions left, this will initiate the removal and wait
+ * for the completion.
  */
 void iscsi_host_remove(struct Scsi_Host *shost)
 {
-	iscsi_host_for_each_session(shost, iscsi_session_teardown);
+	struct iscsi_host *ihost = shost_priv(shost);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ihost->lock, flags);
+	ihost->state = ISCSI_HOST_REMOVED;
+	spin_unlock_irqrestore(&ihost->lock, flags);
+
+	iscsi_host_for_each_session(shost, iscsi_notify_host_removed);
+	wait_event_interruptible(ihost->session_removal_wq,
+				 ihost->num_sessions == 0);
+	if (signal_pending(current))
+		flush_signals(current);
+
 	scsi_remove_host(shost);
 }
 EXPORT_SYMBOL_GPL(iscsi_host_remove);
@@ -1950,6 +2005,27 @@ void iscsi_host_free(struct Scsi_Host *shost)
 }
 EXPORT_SYMBOL_GPL(iscsi_host_free);
 
+static void iscsi_host_dec_session_cnt(struct Scsi_Host *shost)
+{
+	struct iscsi_host *ihost = shost_priv(shost);
+	unsigned long flags;
+
+	shost = scsi_host_get(shost);
+	if (!shost) {
+		printk(KERN_ERR "Invalid state. Cannot notify host removal "
+		      "of session teardown event because host already "
+		      "removed.\n");
+		return;
+	}
+
+	spin_lock_irqsave(&ihost->lock, flags);
+	ihost->num_sessions--;
+	if (ihost->num_sessions == 0)
+		wake_up(&ihost->session_removal_wq);
+	spin_unlock_irqrestore(&ihost->lock, flags);
+	scsi_host_put(shost);
+}
+
 /**
  * iscsi_session_setup - create iscsi cls session and host and session
  * @iscsit: iscsi transport template
@@ -1970,9 +2046,19 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost,
 		    uint16_t cmds_max, int cmd_task_size,
 		    uint32_t initial_cmdsn, unsigned int id)
 {
+	struct iscsi_host *ihost = shost_priv(shost);
 	struct iscsi_session *session;
 	struct iscsi_cls_session *cls_session;
 	int cmd_i, scsi_cmds, total_cmds = cmds_max;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ihost->lock, flags);
+	if (ihost->state == ISCSI_HOST_REMOVED) {
+		spin_unlock_irqrestore(&ihost->lock, flags);
+		return NULL;
+	}
+	ihost->num_sessions++;
+	spin_unlock_irqrestore(&ihost->lock, flags);
 
 	if (!total_cmds)
 		total_cmds = ISCSI_DEF_XMIT_CMDS_MAX;
@@ -1985,7 +2071,7 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost,
 		printk(KERN_ERR "iscsi: invalid can_queue of %d. can_queue "
 		       "must be a power of two that is at least %d.\n",
 		       total_cmds, ISCSI_TOTAL_CMDS_MIN);
-		return NULL;
+		goto dec_session_count;
 	}
 
 	if (total_cmds > ISCSI_TOTAL_CMDS_MAX) {
@@ -2009,7 +2095,7 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost,
 	cls_session = iscsi_alloc_session(shost, iscsit,
 					  sizeof(struct iscsi_session));
 	if (!cls_session)
-		return NULL;
+		goto dec_session_count;
 	session = cls_session->dd_data;
 	session->cls_session = cls_session;
 	session->host = shost;
@@ -2048,6 +2134,7 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost,
 
 	if (iscsi_add_session(cls_session, id))
 		goto cls_session_fail;
+
 	return cls_session;
 
 cls_session_fail:
@@ -2056,6 +2143,8 @@ module_get_fail:
 	iscsi_pool_free(&session->cmdpool);
 cmdpool_alloc_fail:
 	iscsi_free_session(cls_session);
+dec_session_count:
+	iscsi_host_dec_session_cnt(shost);
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(iscsi_session_setup);
@@ -2071,6 +2160,7 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
 {
 	struct iscsi_session *session = cls_session->dd_data;
 	struct module *owner = cls_session->transport->owner;
+	struct Scsi_Host *shost = session->host;
 
 	iscsi_pool_free(&session->cmdpool);
 
@@ -2083,6 +2173,7 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
 	kfree(session->ifacename);
 
 	iscsi_destroy_session(cls_session);
+	iscsi_host_dec_session_cnt(shost);
 	module_put(owner);
 }
 EXPORT_SYMBOL_GPL(iscsi_session_teardown);
diff --git a/drivers/scsi/qla4xxx/ql4_os.c b/drivers/scsi/qla4xxx/ql4_os.c
index 4255b36ff968..db7ea3bb4e83 100644
--- a/drivers/scsi/qla4xxx/ql4_os.c
+++ b/drivers/scsi/qla4xxx/ql4_os.c
@@ -353,7 +353,7 @@ void qla4xxx_mark_device_missing(struct scsi_qla_host *ha,
 		      ha->host_no, ddb_entry->bus, ddb_entry->target,
 		      ddb_entry->fw_ddb_index));
 	iscsi_block_session(ddb_entry->sess);
-	iscsi_conn_error(ddb_entry->conn, ISCSI_ERR_CONN_FAILED);
+	iscsi_conn_error_event(ddb_entry->conn, ISCSI_ERR_CONN_FAILED);
 }
 
 static struct srb* qla4xxx_get_new_srb(struct scsi_qla_host *ha,
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index cbaae48f47ed..f9e45f83e467 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -1010,7 +1010,7 @@ int iscsi_recv_pdu(struct iscsi_cls_conn *conn, struct iscsi_hdr *hdr,
 
 	skb = alloc_skb(len, GFP_ATOMIC);
 	if (!skb) {
-		iscsi_conn_error(conn, ISCSI_ERR_CONN_FAILED);
+		iscsi_conn_error_event(conn, ISCSI_ERR_CONN_FAILED);
 		iscsi_cls_conn_printk(KERN_ERR, conn, "can not deliver "
 				      "control PDU: OOM\n");
 		return -ENOMEM;
@@ -1031,7 +1031,7 @@ int iscsi_recv_pdu(struct iscsi_cls_conn *conn, struct iscsi_hdr *hdr,
 }
 EXPORT_SYMBOL_GPL(iscsi_recv_pdu);
 
-void iscsi_conn_error(struct iscsi_cls_conn *conn, enum iscsi_err error)
+void iscsi_conn_error_event(struct iscsi_cls_conn *conn, enum iscsi_err error)
 {
 	struct nlmsghdr	*nlh;
 	struct sk_buff	*skb;
@@ -1063,7 +1063,7 @@ void iscsi_conn_error(struct iscsi_cls_conn *conn, enum iscsi_err error)
 	iscsi_cls_conn_printk(KERN_INFO, conn, "detected conn error (%d)\n",
 			      error);
 }
-EXPORT_SYMBOL_GPL(iscsi_conn_error);
+EXPORT_SYMBOL_GPL(iscsi_conn_error_event);
 
 static int
 iscsi_if_send_reply(int pid, int seq, int type, int done, int multi,
diff --git a/include/scsi/iscsi_if.h b/include/scsi/iscsi_if.h
index 16be12f1cbe8..f274d248a91f 100644
--- a/include/scsi/iscsi_if.h
+++ b/include/scsi/iscsi_if.h
@@ -213,6 +213,7 @@ enum iscsi_err {
 	ISCSI_ERR_DATA_DGST		= ISCSI_ERR_BASE + 15,
 	ISCSI_ERR_PARAM_NOT_FOUND	= ISCSI_ERR_BASE + 16,
 	ISCSI_ERR_NO_SCSI_CMD		= ISCSI_ERR_BASE + 17,
+	ISCSI_ERR_INVALID_HOST		= ISCSI_ERR_BASE + 18,
 };
 
 /*
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 5e75bb7f311c..7d8cd159f592 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -287,6 +287,11 @@ struct iscsi_session {
 	struct iscsi_pool	cmdpool;	/* PDU's pool */
 };
 
+enum {
+	ISCSI_HOST_SETUP,
+	ISCSI_HOST_REMOVED,
+};
+
 struct iscsi_host {
 	char			*initiatorname;
 	/* hw address or netdev iscsi connection is bound to */
@@ -295,6 +300,12 @@ struct iscsi_host {
 	/* local address */
 	int			local_port;
 	char			local_address[ISCSI_ADDRESS_BUF_LEN];
+
+	wait_queue_head_t	session_removal_wq;
+	/* protects sessions and state */
+	spinlock_t		lock;
+	int			num_sessions;
+	int			state;
 };
 
 /*
@@ -351,6 +362,8 @@ extern void iscsi_conn_stop(struct iscsi_cls_conn *, int);
 extern int iscsi_conn_bind(struct iscsi_cls_session *, struct iscsi_cls_conn *,
 			   int);
 extern void iscsi_conn_failure(struct iscsi_conn *conn, enum iscsi_err err);
+extern void iscsi_session_failure(struct iscsi_cls_session *cls_session,
+				  enum iscsi_err err);
 extern int iscsi_conn_get_param(struct iscsi_cls_conn *cls_conn,
 				enum iscsi_param param, char *buf);
 extern void iscsi_suspend_tx(struct iscsi_conn *conn);
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index 8b6c91df4c7a..8749d4d8e244 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -135,7 +135,8 @@ extern int iscsi_unregister_transport(struct iscsi_transport *tt);
 /*
  * control plane upcalls
  */
-extern void iscsi_conn_error(struct iscsi_cls_conn *conn, enum iscsi_err error);
+extern void iscsi_conn_error_event(struct iscsi_cls_conn *conn,
+				   enum iscsi_err error);
 extern int iscsi_recv_pdu(struct iscsi_cls_conn *conn, struct iscsi_hdr *hdr,
 			  char *data, uint32_t data_size);
 
-- 
cgit v1.2.3


From 21536062d98938dfcfbae593a26c154e359749dc Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Wed, 24 Sep 2008 11:46:11 -0500
Subject: [SCSI] iscsi class: fix endpoint id handling

Some endpoint code was using unsigned int and some
was using uint64_t. This converts it all to uint64_t.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/scsi/scsi_transport_iscsi.c | 9 +++++----
 include/scsi/scsi_transport_iscsi.h | 2 +-
 2 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index f9e45f83e467..4a803ebaf508 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -138,7 +138,7 @@ static ssize_t
 show_ep_handle(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev);
-	return sprintf(buf, "%u\n", ep->id);
+	return sprintf(buf, "%llu\n", (unsigned long long) ep->id);
 }
 static ISCSI_ATTR(ep, handle, S_IRUGO, show_ep_handle, NULL);
 
@@ -156,7 +156,7 @@ static struct attribute_group iscsi_endpoint_group = {
 static int iscsi_match_epid(struct device *dev, void *data)
 {
 	struct iscsi_endpoint *ep = iscsi_dev_to_endpoint(dev);
-	unsigned int *epid = (unsigned int *) data;
+	uint64_t *epid = (uint64_t *) data;
 
 	return *epid == ep->id;
 }
@@ -166,7 +166,7 @@ iscsi_create_endpoint(int dd_size)
 {
 	struct device *dev;
 	struct iscsi_endpoint *ep;
-	unsigned int id;
+	uint64_t id;
 	int err;
 
 	for (id = 1; id < ISCSI_MAX_EPID; id++) {
@@ -187,7 +187,8 @@ iscsi_create_endpoint(int dd_size)
 
 	ep->id = id;
 	ep->dev.class = &iscsi_endpoint_class;
-	snprintf(ep->dev.bus_id, BUS_ID_SIZE, "ep-%u", id);
+	snprintf(ep->dev.bus_id, BUS_ID_SIZE, "ep-%llu",
+		 (unsigned long long) id);
 	err = device_register(&ep->dev);
         if (err)
                 goto free_ep;
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index 8749d4d8e244..c667cc396545 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -208,7 +208,7 @@ extern void iscsi_host_for_each_session(struct Scsi_Host *shost,
 struct iscsi_endpoint {
 	void *dd_data;			/* LLD private data */
 	struct device dev;
-	unsigned int id;
+	uint64_t id;
 };
 
 /*
-- 
cgit v1.2.3


From 8e12452549ba2dfa17db97bc495172fac221a7ab Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Wed, 24 Sep 2008 11:46:12 -0500
Subject: [SCSI] libiscsi: rename host reset to target reset

I had this in my patchset to add target reset support, but
it got dropped due to patching conflicts. This initial patch
just renames the function and users. We are actually just
dropping the session, and so this does not have anything to do
with the host exactly. It does for software iscsi because
we allocate a host per session, but for cxgb3i this makes no
sense.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/infiniband/ulp/iser/iscsi_iser.c |  2 +-
 drivers/scsi/iscsi_tcp.c                 |  2 +-
 drivers/scsi/libiscsi.c                  | 10 +++++-----
 include/scsi/libiscsi.h                  |  2 +-
 4 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 0474da173eb1..1e5b6446231d 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -598,7 +598,7 @@ static struct scsi_host_template iscsi_iser_sht = {
 	.cmd_per_lun            = ISCSI_MAX_CMD_PER_LUN,
 	.eh_abort_handler       = iscsi_eh_abort,
 	.eh_device_reset_handler= iscsi_eh_device_reset,
-	.eh_host_reset_handler	= iscsi_eh_host_reset,
+	.eh_target_reset_handler= iscsi_eh_target_reset,
 	.use_clustering         = DISABLE_CLUSTERING,
 	.proc_name              = "iscsi_iser",
 	.this_id                = -1,
diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 752f42884cc1..4f096de81525 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -1909,7 +1909,7 @@ static struct scsi_host_template iscsi_sht = {
 	.cmd_per_lun		= ISCSI_DEF_CMD_PER_LUN,
 	.eh_abort_handler       = iscsi_eh_abort,
 	.eh_device_reset_handler= iscsi_eh_device_reset,
-	.eh_host_reset_handler	= iscsi_eh_host_reset,
+	.eh_target_reset_handler= iscsi_eh_target_reset,
 	.use_clustering         = DISABLE_CLUSTERING,
 	.slave_configure        = iscsi_tcp_slave_configure,
 	.proc_name		= "iscsi_tcp",
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 390781894be9..e3e57cce4886 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1367,7 +1367,7 @@ void iscsi_session_recovery_timedout(struct iscsi_cls_session *cls_session)
 }
 EXPORT_SYMBOL_GPL(iscsi_session_recovery_timedout);
 
-int iscsi_eh_host_reset(struct scsi_cmnd *sc)
+int iscsi_eh_target_reset(struct scsi_cmnd *sc)
 {
 	struct iscsi_cls_session *cls_session;
 	struct iscsi_session *session;
@@ -1381,7 +1381,7 @@ int iscsi_eh_host_reset(struct scsi_cmnd *sc)
 	spin_lock_bh(&session->lock);
 	if (session->state == ISCSI_STATE_TERMINATE) {
 failed:
-		debug_scsi("failing host reset: session terminated "
+		debug_scsi("failing target reset: session terminated "
 			   "[CID %d age %d]\n", conn->id, session->age);
 		spin_unlock_bh(&session->lock);
 		mutex_unlock(&session->eh_mutex);
@@ -1396,7 +1396,7 @@ failed:
 	 */
 	iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
 
-	debug_scsi("iscsi_eh_host_reset wait for relogin\n");
+	debug_scsi("iscsi_eh_target_reset wait for relogin\n");
 	wait_event_interruptible(conn->ehwait,
 				 session->state == ISCSI_STATE_TERMINATE ||
 				 session->state == ISCSI_STATE_LOGGED_IN ||
@@ -1408,14 +1408,14 @@ failed:
 	spin_lock_bh(&session->lock);
 	if (session->state == ISCSI_STATE_LOGGED_IN)
 		iscsi_session_printk(KERN_INFO, session,
-				     "host reset succeeded\n");
+				     "target reset succeeded\n");
 	else
 		goto failed;
 	spin_unlock_bh(&session->lock);
 	mutex_unlock(&session->eh_mutex);
 	return SUCCESS;
 }
-EXPORT_SYMBOL_GPL(iscsi_eh_host_reset);
+EXPORT_SYMBOL_GPL(iscsi_eh_target_reset);
 
 static void iscsi_tmf_timedout(unsigned long data)
 {
diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h
index 7d8cd159f592..61e53f14f7e1 100644
--- a/include/scsi/libiscsi.h
+++ b/include/scsi/libiscsi.h
@@ -313,7 +313,7 @@ struct iscsi_host {
  */
 extern int iscsi_change_queue_depth(struct scsi_device *sdev, int depth);
 extern int iscsi_eh_abort(struct scsi_cmnd *sc);
-extern int iscsi_eh_host_reset(struct scsi_cmnd *sc);
+extern int iscsi_eh_target_reset(struct scsi_cmnd *sc);
 extern int iscsi_eh_device_reset(struct scsi_cmnd *sc);
 extern int iscsi_queuecommand(struct scsi_cmnd *sc,
 			      void (*done)(struct scsi_cmnd *));
-- 
cgit v1.2.3


From 6f481e3cefeb33094e87af176587e6a3027f104e Mon Sep 17 00:00:00 2001
From: Mike Christie <michaelc@cs.wisc.edu>
Date: Wed, 24 Sep 2008 11:46:13 -0500
Subject: [SCSI] iscsi_tcp: return a descriptive error value during connection
 errors

The segment->done functions return a iscsi error value which gives
a lot more info than conn failed, so this patch has us return
that value. I also add a new one for xmit failures.

Signed-off-by: Mike Christie <michaelc@cs.wisc.edu>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
---
 drivers/scsi/iscsi_tcp.c | 12 +++++++-----
 include/scsi/iscsi_if.h  |  1 +
 2 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c
index 4f096de81525..ed6c54cae7b1 100644
--- a/drivers/scsi/iscsi_tcp.c
+++ b/drivers/scsi/iscsi_tcp.c
@@ -979,7 +979,7 @@ iscsi_tcp_recv(read_descriptor_t *rd_desc, struct sk_buff *skb,
 
 error:
 	debug_tcp("Error receiving PDU, errno=%d\n", rc);
-	iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
+	iscsi_conn_failure(conn, rc);
 	return 0;
 }
 
@@ -1098,8 +1098,10 @@ iscsi_xmit(struct iscsi_conn *conn)
 
 	while (1) {
 		rc = iscsi_tcp_xmit_segment(tcp_conn, segment);
-		if (rc < 0)
+		if (rc < 0) {
+			rc = ISCSI_ERR_XMIT_FAILED;
 			goto error;
+		}
 		if (rc == 0)
 			break;
 
@@ -1108,7 +1110,7 @@ iscsi_xmit(struct iscsi_conn *conn)
 		if (segment->total_copied >= segment->total_size) {
 			if (segment->done != NULL) {
 				rc = segment->done(tcp_conn, segment);
-				if (rc < 0)
+				if (rc != 0)
 					goto error;
 			}
 		}
@@ -1123,8 +1125,8 @@ error:
 	/* Transmit error. We could initiate error recovery
 	 * here. */
 	debug_tcp("Error sending PDU, errno=%d\n", rc);
-	iscsi_conn_failure(conn, ISCSI_ERR_CONN_FAILED);
-	return rc;
+	iscsi_conn_failure(conn, rc);
+	return -EIO;
 }
 
 /**
diff --git a/include/scsi/iscsi_if.h b/include/scsi/iscsi_if.h
index f274d248a91f..0c9514de5df7 100644
--- a/include/scsi/iscsi_if.h
+++ b/include/scsi/iscsi_if.h
@@ -214,6 +214,7 @@ enum iscsi_err {
 	ISCSI_ERR_PARAM_NOT_FOUND	= ISCSI_ERR_BASE + 16,
 	ISCSI_ERR_NO_SCSI_CMD		= ISCSI_ERR_BASE + 17,
 	ISCSI_ERR_INVALID_HOST		= ISCSI_ERR_BASE + 18,
+	ISCSI_ERR_XMIT_FAILED		= ISCSI_ERR_BASE + 19,
 };
 
 /*
-- 
cgit v1.2.3


From 69fd3a8d098faf41a04930afa83757c0555ee360 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Sun, 12 Oct 2008 16:18:36 +0200
Subject: [MTD] remove unused mtd parameter in of_mtd_parse_partitions()

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/mtd/maps/physmap_of.c    | 3 +--
 drivers/mtd/nand/fsl_elbc_nand.c | 3 +--
 drivers/mtd/ofpart.c             | 1 -
 include/linux/mtd/partitions.h   | 1 -
 4 files changed, 2 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/maps/physmap_of.c b/drivers/mtd/maps/physmap_of.c
index 49acd4171893..5fcfec034a94 100644
--- a/drivers/mtd/maps/physmap_of.c
+++ b/drivers/mtd/maps/physmap_of.c
@@ -230,8 +230,7 @@ static int __devinit of_flash_probe(struct of_device *dev,
 
 #ifdef CONFIG_MTD_OF_PARTS
 	if (err == 0) {
-		err = of_mtd_parse_partitions(&dev->dev, info->mtd,
-		                              dp, &info->parts);
+		err = of_mtd_parse_partitions(&dev->dev, dp, &info->parts);
 		if (err < 0)
 			return err;
 	}
diff --git a/drivers/mtd/nand/fsl_elbc_nand.c b/drivers/mtd/nand/fsl_elbc_nand.c
index 98ad3cefcaf4..4aa5bd6158da 100644
--- a/drivers/mtd/nand/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/fsl_elbc_nand.c
@@ -918,8 +918,7 @@ static int __devinit fsl_elbc_chip_probe(struct fsl_elbc_ctrl *ctrl,
 
 #ifdef CONFIG_MTD_OF_PARTS
 	if (ret == 0) {
-		ret = of_mtd_parse_partitions(priv->dev, &priv->mtd,
-		                              node, &parts);
+		ret = of_mtd_parse_partitions(priv->dev, node, &parts);
 		if (ret < 0)
 			goto err;
 	}
diff --git a/drivers/mtd/ofpart.c b/drivers/mtd/ofpart.c
index 4f80c2fd89af..9e45b3f39c0e 100644
--- a/drivers/mtd/ofpart.c
+++ b/drivers/mtd/ofpart.c
@@ -20,7 +20,6 @@
 #include <linux/mtd/partitions.h>
 
 int __devinit of_mtd_parse_partitions(struct device *dev,
-                                      struct mtd_info *mtd,
                                       struct device_node *node,
                                       struct mtd_partition **pparts)
 {
diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h
index 5014f7a9f5df..c92b4d439609 100644
--- a/include/linux/mtd/partitions.h
+++ b/include/linux/mtd/partitions.h
@@ -73,7 +73,6 @@ struct device;
 struct device_node;
 
 int __devinit of_mtd_parse_partitions(struct device *dev,
-                                      struct mtd_info *mtd,
                                       struct device_node *node,
                                       struct mtd_partition **pparts);
 
-- 
cgit v1.2.3


From 97e1c18e8d17bd87e1e383b2e9d9fc740332c8e2 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Date: Fri, 18 Jul 2008 12:16:16 -0400
Subject: tracing: Kernel Tracepoints

Implementation of kernel tracepoints. Inspired from the Linux Kernel
Markers. Allows complete typing verification by declaring both tracing
statement inline functions and probe registration/unregistration static
inline functions within the same macro "DEFINE_TRACE". No format string
is required. See the tracepoint Documentation and Samples patches for
usage examples.

Taken from the documentation patch :

"A tracepoint placed in code provides a hook to call a function (probe)
that you can provide at runtime. A tracepoint can be "on" (a probe is
connected to it) or "off" (no probe is attached). When a tracepoint is
"off" it has no effect, except for adding a tiny time penalty (checking
a condition for a branch) and space penalty (adding a few bytes for the
function call at the end of the instrumented function and adds a data
structure in a separate section).  When a tracepoint is "on", the
function you provide is called each time the tracepoint is executed, in
the execution context of the caller. When the function provided ends its
execution, it returns to the caller (continuing from the tracepoint
site).

You can put tracepoints at important locations in the code. They are
lightweight hooks that can pass an arbitrary number of parameters, which
prototypes are described in a tracepoint declaration placed in a header
file."

Addition and removal of tracepoints is synchronized by RCU using the
scheduler (and preempt_disable) as guarantees to find a quiescent state
(this is really RCU "classic"). The update side uses rcu_barrier_sched()
with call_rcu_sched() and the read/execute side uses
"preempt_disable()/preempt_enable()".

We make sure the previous array containing probes, which has been
scheduled for deletion by the rcu callback, is indeed freed before we
proceed to the next update. It therefore limits the rate of modification
of a single tracepoint to one update per RCU period. The objective here
is to permit fast batch add/removal of probes on _different_
tracepoints.

Changelog :
- Use #name ":" #proto as string to identify the tracepoint in the
  tracepoint table. This will make sure not type mismatch happens due to
  connexion of a probe with the wrong type to a tracepoint declared with
  the same name in a different header.
- Add tracepoint_entry_free_old.
- Change __TO_TRACE to get rid of the 'i' iterator.

Masami Hiramatsu <mhiramat@redhat.com> :
Tested on x86-64.

Performance impact of a tracepoint : same as markers, except that it
adds about 70 bytes of instructions in an unlikely branch of each
instrumented function (the for loop, the stack setup and the function
call). It currently adds a memory read, a test and a conditional branch
at the instrumentation site (in the hot path). Immediate values will
eventually change this into a load immediate, test and branch, which
removes the memory read which will make the i-cache impact smaller
(changing the memory read for a load immediate removes 3-4 bytes per
site on x86_32 (depending on mov prefixes), or 7-8 bytes on x86_64, it
also saves the d-cache hit).

About the performance impact of tracepoints (which is comparable to
markers), even without immediate values optimizations, tests done by
Hideo Aoki on ia64 show no regression. His test case was using hackbench
on a kernel where scheduler instrumentation (about 5 events in code
scheduler code) was added.

Quoting Hideo Aoki about Markers :

I evaluated overhead of kernel marker using linux-2.6-sched-fixes git
tree, which includes several markers for LTTng, using an ia64 server.

While the immediate trace mark feature isn't implemented on ia64, there
is no major performance regression. So, I think that we don't have any
issues to propose merging marker point patches into Linus's tree from
the viewpoint of performance impact.

I prepared two kernels to evaluate. The first one was compiled without
CONFIG_MARKERS. The second one was enabled CONFIG_MARKERS.

I downloaded the original hackbench from the following URL:
http://devresources.linux-foundation.org/craiger/hackbench/src/hackbench.c

I ran hackbench 5 times in each condition and calculated the average and
difference between the kernels.

    The parameter of hackbench: every 50 from 50 to 800
    The number of CPUs of the server: 2, 4, and 8

Below is the results. As you can see, major performance regression
wasn't found in any case. Even if number of processes increases,
differences between marker-enabled kernel and marker- disabled kernel
doesn't increase. Moreover, if number of CPUs increases, the differences
doesn't increase either.

Curiously, marker-enabled kernel is better than marker-disabled kernel
in more than half cases, although I guess it comes from the difference
of memory access pattern.

* 2 CPUs

Number of | without      | with         | diff     | diff    |
processes | Marker [Sec] | Marker [Sec] |   [Sec]  |   [%]   |
--------------------------------------------------------------
       50 |      4.811   |       4.872  |  +0.061  |  +1.27  |
      100 |      9.854   |      10.309  |  +0.454  |  +4.61  |
      150 |     15.602   |      15.040  |  -0.562  |  -3.6   |
      200 |     20.489   |      20.380  |  -0.109  |  -0.53  |
      250 |     25.798   |      25.652  |  -0.146  |  -0.56  |
      300 |     31.260   |      30.797  |  -0.463  |  -1.48  |
      350 |     36.121   |      35.770  |  -0.351  |  -0.97  |
      400 |     42.288   |      42.102  |  -0.186  |  -0.44  |
      450 |     47.778   |      47.253  |  -0.526  |  -1.1   |
      500 |     51.953   |      52.278  |  +0.325  |  +0.63  |
      550 |     58.401   |      57.700  |  -0.701  |  -1.2   |
      600 |     63.334   |      63.222  |  -0.112  |  -0.18  |
      650 |     68.816   |      68.511  |  -0.306  |  -0.44  |
      700 |     74.667   |      74.088  |  -0.579  |  -0.78  |
      750 |     78.612   |      79.582  |  +0.970  |  +1.23  |
      800 |     85.431   |      85.263  |  -0.168  |  -0.2   |
--------------------------------------------------------------

* 4 CPUs

Number of | without      | with         | diff     | diff    |
processes | Marker [Sec] | Marker [Sec] |   [Sec]  |   [%]   |
--------------------------------------------------------------
       50 |      2.586   |       2.584  |  -0.003  |  -0.1   |
      100 |      5.254   |       5.283  |  +0.030  |  +0.56  |
      150 |      8.012   |       8.074  |  +0.061  |  +0.76  |
      200 |     11.172   |      11.000  |  -0.172  |  -1.54  |
      250 |     13.917   |      14.036  |  +0.119  |  +0.86  |
      300 |     16.905   |      16.543  |  -0.362  |  -2.14  |
      350 |     19.901   |      20.036  |  +0.135  |  +0.68  |
      400 |     22.908   |      23.094  |  +0.186  |  +0.81  |
      450 |     26.273   |      26.101  |  -0.172  |  -0.66  |
      500 |     29.554   |      29.092  |  -0.461  |  -1.56  |
      550 |     32.377   |      32.274  |  -0.103  |  -0.32  |
      600 |     35.855   |      35.322  |  -0.533  |  -1.49  |
      650 |     39.192   |      38.388  |  -0.804  |  -2.05  |
      700 |     41.744   |      41.719  |  -0.025  |  -0.06  |
      750 |     45.016   |      44.496  |  -0.520  |  -1.16  |
      800 |     48.212   |      47.603  |  -0.609  |  -1.26  |
--------------------------------------------------------------

* 8 CPUs

Number of | without      | with         | diff     | diff    |
processes | Marker [Sec] | Marker [Sec] |   [Sec]  |   [%]   |
--------------------------------------------------------------
       50 |      2.094   |       2.072  |  -0.022  |  -1.07  |
      100 |      4.162   |       4.273  |  +0.111  |  +2.66  |
      150 |      6.485   |       6.540  |  +0.055  |  +0.84  |
      200 |      8.556   |       8.478  |  -0.078  |  -0.91  |
      250 |     10.458   |      10.258  |  -0.200  |  -1.91  |
      300 |     12.425   |      12.750  |  +0.325  |  +2.62  |
      350 |     14.807   |      14.839  |  +0.032  |  +0.22  |
      400 |     16.801   |      16.959  |  +0.158  |  +0.94  |
      450 |     19.478   |      19.009  |  -0.470  |  -2.41  |
      500 |     21.296   |      21.504  |  +0.208  |  +0.98  |
      550 |     23.842   |      23.979  |  +0.137  |  +0.57  |
      600 |     26.309   |      26.111  |  -0.198  |  -0.75  |
      650 |     28.705   |      28.446  |  -0.259  |  -0.9   |
      700 |     31.233   |      31.394  |  +0.161  |  +0.52  |
      750 |     34.064   |      33.720  |  -0.344  |  -1.01  |
      800 |     36.320   |      36.114  |  -0.206  |  -0.57  |
--------------------------------------------------------------

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: 'Peter Zijlstra' <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/asm-generic/vmlinux.lds.h |   6 +-
 include/linux/module.h            |  17 ++
 include/linux/tracepoint.h        | 127 ++++++++++
 init/Kconfig                      |   7 +
 kernel/Makefile                   |   1 +
 kernel/module.c                   |  66 +++++-
 kernel/tracepoint.c               | 476 ++++++++++++++++++++++++++++++++++++++
 7 files changed, 698 insertions(+), 2 deletions(-)
 create mode 100644 include/linux/tracepoint.h
 create mode 100644 kernel/tracepoint.c

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 7440a0dceddb..3d8e472a09c8 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -52,7 +52,10 @@
 	. = ALIGN(8);							\
 	VMLINUX_SYMBOL(__start___markers) = .;				\
 	*(__markers)							\
-	VMLINUX_SYMBOL(__stop___markers) = .;
+	VMLINUX_SYMBOL(__stop___markers) = .;				\
+	VMLINUX_SYMBOL(__start___tracepoints) = .;			\
+	*(__tracepoints)						\
+	VMLINUX_SYMBOL(__stop___tracepoints) = .;
 
 #define RO_DATA(align)							\
 	. = ALIGN((align));						\
@@ -61,6 +64,7 @@
 		*(.rodata) *(.rodata.*)					\
 		*(__vermagic)		/* Kernel version magic */	\
 		*(__markers_strings)	/* Markers: strings */		\
+		*(__tracepoints_strings)/* Tracepoints: strings */	\
 	}								\
 									\
 	.rodata1          : AT(ADDR(.rodata1) - LOAD_OFFSET) {		\
diff --git a/include/linux/module.h b/include/linux/module.h
index 68e09557c951..8b6113503863 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -16,6 +16,7 @@
 #include <linux/kobject.h>
 #include <linux/moduleparam.h>
 #include <linux/marker.h>
+#include <linux/tracepoint.h>
 #include <asm/local.h>
 
 #include <asm/module.h>
@@ -331,6 +332,10 @@ struct module
 	struct marker *markers;
 	unsigned int num_markers;
 #endif
+#ifdef CONFIG_TRACEPOINTS
+	struct tracepoint *tracepoints;
+	unsigned int num_tracepoints;
+#endif
 
 #ifdef CONFIG_MODULE_UNLOAD
 	/* What modules depend on me? */
@@ -454,6 +459,9 @@ extern void print_modules(void);
 
 extern void module_update_markers(void);
 
+extern void module_update_tracepoints(void);
+extern int module_get_iter_tracepoints(struct tracepoint_iter *iter);
+
 #else /* !CONFIG_MODULES... */
 #define EXPORT_SYMBOL(sym)
 #define EXPORT_SYMBOL_GPL(sym)
@@ -558,6 +566,15 @@ static inline void module_update_markers(void)
 {
 }
 
+static inline void module_update_tracepoints(void)
+{
+}
+
+static inline int module_get_iter_tracepoints(struct tracepoint_iter *iter)
+{
+	return 0;
+}
+
 #endif /* CONFIG_MODULES */
 
 struct device_driver;
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
new file mode 100644
index 000000000000..e623a6fca5c3
--- /dev/null
+++ b/include/linux/tracepoint.h
@@ -0,0 +1,127 @@
+#ifndef _LINUX_TRACEPOINT_H
+#define _LINUX_TRACEPOINT_H
+
+/*
+ * Kernel Tracepoint API.
+ *
+ * See Documentation/tracepoint.txt.
+ *
+ * (C) Copyright 2008 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
+ *
+ * Heavily inspired from the Linux Kernel Markers.
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#include <linux/types.h>
+#include <linux/rcupdate.h>
+
+struct module;
+struct tracepoint;
+
+struct tracepoint {
+	const char *name;		/* Tracepoint name */
+	int state;			/* State. */
+	void **funcs;
+} __attribute__((aligned(8)));
+
+
+#define TPPROTO(args...)	args
+#define TPARGS(args...)		args
+
+#ifdef CONFIG_TRACEPOINTS
+
+/*
+ * it_func[0] is never NULL because there is at least one element in the array
+ * when the array itself is non NULL.
+ */
+#define __DO_TRACE(tp, proto, args)					\
+	do {								\
+		void **it_func;						\
+									\
+		rcu_read_lock_sched();					\
+		it_func = rcu_dereference((tp)->funcs);			\
+		if (it_func) {						\
+			do {						\
+				((void(*)(proto))(*it_func))(args);	\
+			} while (*(++it_func));				\
+		}							\
+		rcu_read_unlock_sched();				\
+	} while (0)
+
+/*
+ * Make sure the alignment of the structure in the __tracepoints section will
+ * not add unwanted padding between the beginning of the section and the
+ * structure. Force alignment to the same alignment as the section start.
+ */
+#define DEFINE_TRACE(name, proto, args)					\
+	static inline void trace_##name(proto)				\
+	{								\
+		static const char __tpstrtab_##name[]			\
+		__attribute__((section("__tracepoints_strings")))	\
+		= #name ":" #proto;					\
+		static struct tracepoint __tracepoint_##name		\
+		__attribute__((section("__tracepoints"), aligned(8))) =	\
+		{ __tpstrtab_##name, 0, NULL };				\
+		if (unlikely(__tracepoint_##name.state))		\
+			__DO_TRACE(&__tracepoint_##name,		\
+				TPPROTO(proto), TPARGS(args));		\
+	}								\
+	static inline int register_trace_##name(void (*probe)(proto))	\
+	{								\
+		return tracepoint_probe_register(#name ":" #proto,	\
+			(void *)probe);					\
+	}								\
+	static inline void unregister_trace_##name(void (*probe)(proto))\
+	{								\
+		tracepoint_probe_unregister(#name ":" #proto,		\
+			(void *)probe);					\
+	}
+
+extern void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end);
+
+#else /* !CONFIG_TRACEPOINTS */
+#define DEFINE_TRACE(name, proto, args)			\
+	static inline void _do_trace_##name(struct tracepoint *tp, proto) \
+	{ }								\
+	static inline void trace_##name(proto)				\
+	{ }								\
+	static inline int register_trace_##name(void (*probe)(proto))	\
+	{								\
+		return -ENOSYS;						\
+	}								\
+	static inline void unregister_trace_##name(void (*probe)(proto))\
+	{ }
+
+static inline void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end)
+{ }
+#endif /* CONFIG_TRACEPOINTS */
+
+/*
+ * Connect a probe to a tracepoint.
+ * Internal API, should not be used directly.
+ */
+extern int tracepoint_probe_register(const char *name, void *probe);
+
+/*
+ * Disconnect a probe from a tracepoint.
+ * Internal API, should not be used directly.
+ */
+extern int tracepoint_probe_unregister(const char *name, void *probe);
+
+struct tracepoint_iter {
+	struct module *module;
+	struct tracepoint *tracepoint;
+};
+
+extern void tracepoint_iter_start(struct tracepoint_iter *iter);
+extern void tracepoint_iter_next(struct tracepoint_iter *iter);
+extern void tracepoint_iter_stop(struct tracepoint_iter *iter);
+extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
+extern int tracepoint_get_iter_range(struct tracepoint **tracepoint,
+	struct tracepoint *begin, struct tracepoint *end);
+
+#endif
diff --git a/init/Kconfig b/init/Kconfig
index c11da38837e5..70082678a914 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -771,6 +771,13 @@ config PROFILING
 	  Say Y here to enable the extended profiling support mechanisms used
 	  by profilers such as OProfile.
 
+config TRACEPOINTS
+	bool "Activate tracepoints"
+	default y
+	help
+	  Place an empty function call at each tracepoint site. Can be
+	  dynamically changed for a probe function.
+
 config MARKERS
 	bool "Activate markers"
 	help
diff --git a/kernel/Makefile b/kernel/Makefile
index 4e1d7df7c3e2..8f9ce7ec21b6 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -83,6 +83,7 @@ obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
 obj-$(CONFIG_MARKERS) += marker.o
+obj-$(CONFIG_TRACEPOINTS) += tracepoint.o
 obj-$(CONFIG_LATENCYTOP) += latencytop.o
 obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FTRACE) += trace/
diff --git a/kernel/module.c b/kernel/module.c
index 9db11911e04b..661d73db786e 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -46,6 +46,7 @@
 #include <asm/cacheflush.h>
 #include <linux/license.h>
 #include <asm/sections.h>
+#include <linux/tracepoint.h>
 
 #if 0
 #define DEBUGP printk
@@ -1831,6 +1832,8 @@ static noinline struct module *load_module(void __user *umod,
 #endif
 	unsigned int markersindex;
 	unsigned int markersstringsindex;
+	unsigned int tracepointsindex;
+	unsigned int tracepointsstringsindex;
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
@@ -2117,6 +2120,9 @@ static noinline struct module *load_module(void __user *umod,
 	markersindex = find_sec(hdr, sechdrs, secstrings, "__markers");
  	markersstringsindex = find_sec(hdr, sechdrs, secstrings,
 					"__markers_strings");
+	tracepointsindex = find_sec(hdr, sechdrs, secstrings, "__tracepoints");
+	tracepointsstringsindex = find_sec(hdr, sechdrs, secstrings,
+					"__tracepoints_strings");
 
 	/* Now do relocations. */
 	for (i = 1; i < hdr->e_shnum; i++) {
@@ -2144,6 +2150,12 @@ static noinline struct module *load_module(void __user *umod,
 	mod->num_markers =
 		sechdrs[markersindex].sh_size / sizeof(*mod->markers);
 #endif
+#ifdef CONFIG_TRACEPOINTS
+	mod->tracepoints = (void *)sechdrs[tracepointsindex].sh_addr;
+	mod->num_tracepoints =
+		sechdrs[tracepointsindex].sh_size / sizeof(*mod->tracepoints);
+#endif
+
 
         /* Find duplicate symbols */
 	err = verify_export_symbols(mod);
@@ -2162,11 +2174,16 @@ static noinline struct module *load_module(void __user *umod,
 
 	add_kallsyms(mod, sechdrs, symindex, strindex, secstrings);
 
+	if (!mod->taints) {
 #ifdef CONFIG_MARKERS
-	if (!mod->taints)
 		marker_update_probe_range(mod->markers,
 			mod->markers + mod->num_markers);
 #endif
+#ifdef CONFIG_TRACEPOINTS
+		tracepoint_update_probe_range(mod->tracepoints,
+			mod->tracepoints + mod->num_tracepoints);
+#endif
+	}
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)
 		goto cleanup;
@@ -2717,3 +2734,50 @@ void module_update_markers(void)
 	mutex_unlock(&module_mutex);
 }
 #endif
+
+#ifdef CONFIG_TRACEPOINTS
+void module_update_tracepoints(void)
+{
+	struct module *mod;
+
+	mutex_lock(&module_mutex);
+	list_for_each_entry(mod, &modules, list)
+		if (!mod->taints)
+			tracepoint_update_probe_range(mod->tracepoints,
+				mod->tracepoints + mod->num_tracepoints);
+	mutex_unlock(&module_mutex);
+}
+
+/*
+ * Returns 0 if current not found.
+ * Returns 1 if current found.
+ */
+int module_get_iter_tracepoints(struct tracepoint_iter *iter)
+{
+	struct module *iter_mod;
+	int found = 0;
+
+	mutex_lock(&module_mutex);
+	list_for_each_entry(iter_mod, &modules, list) {
+		if (!iter_mod->taints) {
+			/*
+			 * Sorted module list
+			 */
+			if (iter_mod < iter->module)
+				continue;
+			else if (iter_mod > iter->module)
+				iter->tracepoint = NULL;
+			found = tracepoint_get_iter_range(&iter->tracepoint,
+				iter_mod->tracepoints,
+				iter_mod->tracepoints
+					+ iter_mod->num_tracepoints);
+			if (found) {
+				iter->module = iter_mod;
+				break;
+			}
+		}
+	}
+	mutex_unlock(&module_mutex);
+	return found;
+}
+#endif
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
new file mode 100644
index 000000000000..42e86ddbd2a0
--- /dev/null
+++ b/kernel/tracepoint.c
@@ -0,0 +1,476 @@
+/*
+ * Copyright (C) 2008 Mathieu Desnoyers
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ */
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/types.h>
+#include <linux/jhash.h>
+#include <linux/list.h>
+#include <linux/rcupdate.h>
+#include <linux/tracepoint.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+
+extern struct tracepoint __start___tracepoints[];
+extern struct tracepoint __stop___tracepoints[];
+
+/* Set to 1 to enable tracepoint debug output */
+static const int tracepoint_debug;
+
+/*
+ * tracepoints_mutex nests inside module_mutex. Tracepoints mutex protects the
+ * builtin and module tracepoints and the hash table.
+ */
+static DEFINE_MUTEX(tracepoints_mutex);
+
+/*
+ * Tracepoint hash table, containing the active tracepoints.
+ * Protected by tracepoints_mutex.
+ */
+#define TRACEPOINT_HASH_BITS 6
+#define TRACEPOINT_TABLE_SIZE (1 << TRACEPOINT_HASH_BITS)
+
+/*
+ * Note about RCU :
+ * It is used to to delay the free of multiple probes array until a quiescent
+ * state is reached.
+ * Tracepoint entries modifications are protected by the tracepoints_mutex.
+ */
+struct tracepoint_entry {
+	struct hlist_node hlist;
+	void **funcs;
+	int refcount;	/* Number of times armed. 0 if disarmed. */
+	struct rcu_head rcu;
+	void *oldptr;
+	unsigned char rcu_pending:1;
+	char name[0];
+};
+
+static struct hlist_head tracepoint_table[TRACEPOINT_TABLE_SIZE];
+
+static void free_old_closure(struct rcu_head *head)
+{
+	struct tracepoint_entry *entry = container_of(head,
+		struct tracepoint_entry, rcu);
+	kfree(entry->oldptr);
+	/* Make sure we free the data before setting the pending flag to 0 */
+	smp_wmb();
+	entry->rcu_pending = 0;
+}
+
+static void tracepoint_entry_free_old(struct tracepoint_entry *entry, void *old)
+{
+	if (!old)
+		return;
+	entry->oldptr = old;
+	entry->rcu_pending = 1;
+	/* write rcu_pending before calling the RCU callback */
+	smp_wmb();
+#ifdef CONFIG_PREEMPT_RCU
+	synchronize_sched();	/* Until we have the call_rcu_sched() */
+#endif
+	call_rcu(&entry->rcu, free_old_closure);
+}
+
+static void debug_print_probes(struct tracepoint_entry *entry)
+{
+	int i;
+
+	if (!tracepoint_debug)
+		return;
+
+	for (i = 0; entry->funcs[i]; i++)
+		printk(KERN_DEBUG "Probe %d : %p\n", i, entry->funcs[i]);
+}
+
+static void *
+tracepoint_entry_add_probe(struct tracepoint_entry *entry, void *probe)
+{
+	int nr_probes = 0;
+	void **old, **new;
+
+	WARN_ON(!probe);
+
+	debug_print_probes(entry);
+	old = entry->funcs;
+	if (old) {
+		/* (N -> N+1), (N != 0, 1) probes */
+		for (nr_probes = 0; old[nr_probes]; nr_probes++)
+			if (old[nr_probes] == probe)
+				return ERR_PTR(-EEXIST);
+	}
+	/* + 2 : one for new probe, one for NULL func */
+	new = kzalloc((nr_probes + 2) * sizeof(void *), GFP_KERNEL);
+	if (new == NULL)
+		return ERR_PTR(-ENOMEM);
+	if (old)
+		memcpy(new, old, nr_probes * sizeof(void *));
+	new[nr_probes] = probe;
+	entry->refcount = nr_probes + 1;
+	entry->funcs = new;
+	debug_print_probes(entry);
+	return old;
+}
+
+static void *
+tracepoint_entry_remove_probe(struct tracepoint_entry *entry, void *probe)
+{
+	int nr_probes = 0, nr_del = 0, i;
+	void **old, **new;
+
+	old = entry->funcs;
+
+	debug_print_probes(entry);
+	/* (N -> M), (N > 1, M >= 0) probes */
+	for (nr_probes = 0; old[nr_probes]; nr_probes++) {
+		if ((!probe || old[nr_probes] == probe))
+			nr_del++;
+	}
+
+	if (nr_probes - nr_del == 0) {
+		/* N -> 0, (N > 1) */
+		entry->funcs = NULL;
+		entry->refcount = 0;
+		debug_print_probes(entry);
+		return old;
+	} else {
+		int j = 0;
+		/* N -> M, (N > 1, M > 0) */
+		/* + 1 for NULL */
+		new = kzalloc((nr_probes - nr_del + 1)
+			* sizeof(void *), GFP_KERNEL);
+		if (new == NULL)
+			return ERR_PTR(-ENOMEM);
+		for (i = 0; old[i]; i++)
+			if ((probe && old[i] != probe))
+				new[j++] = old[i];
+		entry->refcount = nr_probes - nr_del;
+		entry->funcs = new;
+	}
+	debug_print_probes(entry);
+	return old;
+}
+
+/*
+ * Get tracepoint if the tracepoint is present in the tracepoint hash table.
+ * Must be called with tracepoints_mutex held.
+ * Returns NULL if not present.
+ */
+static struct tracepoint_entry *get_tracepoint(const char *name)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct tracepoint_entry *e;
+	u32 hash = jhash(name, strlen(name), 0);
+
+	head = &tracepoint_table[hash & ((1 << TRACEPOINT_HASH_BITS)-1)];
+	hlist_for_each_entry(e, node, head, hlist) {
+		if (!strcmp(name, e->name))
+			return e;
+	}
+	return NULL;
+}
+
+/*
+ * Add the tracepoint to the tracepoint hash table. Must be called with
+ * tracepoints_mutex held.
+ */
+static struct tracepoint_entry *add_tracepoint(const char *name)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct tracepoint_entry *e;
+	size_t name_len = strlen(name) + 1;
+	u32 hash = jhash(name, name_len-1, 0);
+
+	head = &tracepoint_table[hash & ((1 << TRACEPOINT_HASH_BITS)-1)];
+	hlist_for_each_entry(e, node, head, hlist) {
+		if (!strcmp(name, e->name)) {
+			printk(KERN_NOTICE
+				"tracepoint %s busy\n", name);
+			return ERR_PTR(-EEXIST);	/* Already there */
+		}
+	}
+	/*
+	 * Using kmalloc here to allocate a variable length element. Could
+	 * cause some memory fragmentation if overused.
+	 */
+	e = kmalloc(sizeof(struct tracepoint_entry) + name_len, GFP_KERNEL);
+	if (!e)
+		return ERR_PTR(-ENOMEM);
+	memcpy(&e->name[0], name, name_len);
+	e->funcs = NULL;
+	e->refcount = 0;
+	e->rcu_pending = 0;
+	hlist_add_head(&e->hlist, head);
+	return e;
+}
+
+/*
+ * Remove the tracepoint from the tracepoint hash table. Must be called with
+ * mutex_lock held.
+ */
+static int remove_tracepoint(const char *name)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct tracepoint_entry *e;
+	int found = 0;
+	size_t len = strlen(name) + 1;
+	u32 hash = jhash(name, len-1, 0);
+
+	head = &tracepoint_table[hash & ((1 << TRACEPOINT_HASH_BITS)-1)];
+	hlist_for_each_entry(e, node, head, hlist) {
+		if (!strcmp(name, e->name)) {
+			found = 1;
+			break;
+		}
+	}
+	if (!found)
+		return -ENOENT;
+	if (e->refcount)
+		return -EBUSY;
+	hlist_del(&e->hlist);
+	/* Make sure the call_rcu has been executed */
+	if (e->rcu_pending)
+		rcu_barrier();
+	kfree(e);
+	return 0;
+}
+
+/*
+ * Sets the probe callback corresponding to one tracepoint.
+ */
+static void set_tracepoint(struct tracepoint_entry **entry,
+	struct tracepoint *elem, int active)
+{
+	WARN_ON(strcmp((*entry)->name, elem->name) != 0);
+
+	/*
+	 * rcu_assign_pointer has a smp_wmb() which makes sure that the new
+	 * probe callbacks array is consistent before setting a pointer to it.
+	 * This array is referenced by __DO_TRACE from
+	 * include/linux/tracepoints.h. A matching smp_read_barrier_depends()
+	 * is used.
+	 */
+	rcu_assign_pointer(elem->funcs, (*entry)->funcs);
+	elem->state = active;
+}
+
+/*
+ * Disable a tracepoint and its probe callback.
+ * Note: only waiting an RCU period after setting elem->call to the empty
+ * function insures that the original callback is not used anymore. This insured
+ * by preempt_disable around the call site.
+ */
+static void disable_tracepoint(struct tracepoint *elem)
+{
+	elem->state = 0;
+}
+
+/**
+ * tracepoint_update_probe_range - Update a probe range
+ * @begin: beginning of the range
+ * @end: end of the range
+ *
+ * Updates the probe callback corresponding to a range of tracepoints.
+ */
+void tracepoint_update_probe_range(struct tracepoint *begin,
+	struct tracepoint *end)
+{
+	struct tracepoint *iter;
+	struct tracepoint_entry *mark_entry;
+
+	mutex_lock(&tracepoints_mutex);
+	for (iter = begin; iter < end; iter++) {
+		mark_entry = get_tracepoint(iter->name);
+		if (mark_entry) {
+			set_tracepoint(&mark_entry, iter,
+					!!mark_entry->refcount);
+		} else {
+			disable_tracepoint(iter);
+		}
+	}
+	mutex_unlock(&tracepoints_mutex);
+}
+
+/*
+ * Update probes, removing the faulty probes.
+ */
+static void tracepoint_update_probes(void)
+{
+	/* Core kernel tracepoints */
+	tracepoint_update_probe_range(__start___tracepoints,
+		__stop___tracepoints);
+	/* tracepoints in modules. */
+	module_update_tracepoints();
+}
+
+/**
+ * tracepoint_probe_register -  Connect a probe to a tracepoint
+ * @name: tracepoint name
+ * @probe: probe handler
+ *
+ * Returns 0 if ok, error value on error.
+ * The probe address must at least be aligned on the architecture pointer size.
+ */
+int tracepoint_probe_register(const char *name, void *probe)
+{
+	struct tracepoint_entry *entry;
+	int ret = 0;
+	void *old;
+
+	mutex_lock(&tracepoints_mutex);
+	entry = get_tracepoint(name);
+	if (!entry) {
+		entry = add_tracepoint(name);
+		if (IS_ERR(entry)) {
+			ret = PTR_ERR(entry);
+			goto end;
+		}
+	}
+	/*
+	 * If we detect that a call_rcu is pending for this tracepoint,
+	 * make sure it's executed now.
+	 */
+	if (entry->rcu_pending)
+		rcu_barrier();
+	old = tracepoint_entry_add_probe(entry, probe);
+	if (IS_ERR(old)) {
+		ret = PTR_ERR(old);
+		goto end;
+	}
+	mutex_unlock(&tracepoints_mutex);
+	tracepoint_update_probes();		/* may update entry */
+	mutex_lock(&tracepoints_mutex);
+	entry = get_tracepoint(name);
+	WARN_ON(!entry);
+	tracepoint_entry_free_old(entry, old);
+end:
+	mutex_unlock(&tracepoints_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tracepoint_probe_register);
+
+/**
+ * tracepoint_probe_unregister -  Disconnect a probe from a tracepoint
+ * @name: tracepoint name
+ * @probe: probe function pointer
+ *
+ * We do not need to call a synchronize_sched to make sure the probes have
+ * finished running before doing a module unload, because the module unload
+ * itself uses stop_machine(), which insures that every preempt disabled section
+ * have finished.
+ */
+int tracepoint_probe_unregister(const char *name, void *probe)
+{
+	struct tracepoint_entry *entry;
+	void *old;
+	int ret = -ENOENT;
+
+	mutex_lock(&tracepoints_mutex);
+	entry = get_tracepoint(name);
+	if (!entry)
+		goto end;
+	if (entry->rcu_pending)
+		rcu_barrier();
+	old = tracepoint_entry_remove_probe(entry, probe);
+	mutex_unlock(&tracepoints_mutex);
+	tracepoint_update_probes();		/* may update entry */
+	mutex_lock(&tracepoints_mutex);
+	entry = get_tracepoint(name);
+	if (!entry)
+		goto end;
+	tracepoint_entry_free_old(entry, old);
+	remove_tracepoint(name);	/* Ignore busy error message */
+	ret = 0;
+end:
+	mutex_unlock(&tracepoints_mutex);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(tracepoint_probe_unregister);
+
+/**
+ * tracepoint_get_iter_range - Get a next tracepoint iterator given a range.
+ * @tracepoint: current tracepoints (in), next tracepoint (out)
+ * @begin: beginning of the range
+ * @end: end of the range
+ *
+ * Returns whether a next tracepoint has been found (1) or not (0).
+ * Will return the first tracepoint in the range if the input tracepoint is
+ * NULL.
+ */
+int tracepoint_get_iter_range(struct tracepoint **tracepoint,
+	struct tracepoint *begin, struct tracepoint *end)
+{
+	if (!*tracepoint && begin != end) {
+		*tracepoint = begin;
+		return 1;
+	}
+	if (*tracepoint >= begin && *tracepoint < end)
+		return 1;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tracepoint_get_iter_range);
+
+static void tracepoint_get_iter(struct tracepoint_iter *iter)
+{
+	int found = 0;
+
+	/* Core kernel tracepoints */
+	if (!iter->module) {
+		found = tracepoint_get_iter_range(&iter->tracepoint,
+				__start___tracepoints, __stop___tracepoints);
+		if (found)
+			goto end;
+	}
+	/* tracepoints in modules. */
+	found = module_get_iter_tracepoints(iter);
+end:
+	if (!found)
+		tracepoint_iter_reset(iter);
+}
+
+void tracepoint_iter_start(struct tracepoint_iter *iter)
+{
+	tracepoint_get_iter(iter);
+}
+EXPORT_SYMBOL_GPL(tracepoint_iter_start);
+
+void tracepoint_iter_next(struct tracepoint_iter *iter)
+{
+	iter->tracepoint++;
+	/*
+	 * iter->tracepoint may be invalid because we blindly incremented it.
+	 * Make sure it is valid by marshalling on the tracepoints, getting the
+	 * tracepoints from following modules if necessary.
+	 */
+	tracepoint_get_iter(iter);
+}
+EXPORT_SYMBOL_GPL(tracepoint_iter_next);
+
+void tracepoint_iter_stop(struct tracepoint_iter *iter)
+{
+}
+EXPORT_SYMBOL_GPL(tracepoint_iter_stop);
+
+void tracepoint_iter_reset(struct tracepoint_iter *iter)
+{
+	iter->module = NULL;
+	iter->tracepoint = NULL;
+}
+EXPORT_SYMBOL_GPL(tracepoint_iter_reset);
-- 
cgit v1.2.3


From 0a16b6075843325dc402edf80c1662838b929aff Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Date: Fri, 18 Jul 2008 12:16:17 -0400
Subject: tracing, sched: LTTng instrumentation - scheduler

Instrument the scheduler activity (sched_switch, migration, wakeups,
wait for a task, signal delivery) and process/thread
creation/destruction (fork, exit, kthread stop). Actually, kthread
creation is not instrumented in this patch because it is architecture
dependent. It allows to connect tracers such as ftrace which detects
scheduling latencies, good/bad scheduler decisions. Tools like LTTng can
export this scheduler information along with instrumentation of the rest
of the kernel activity to perform post-mortem analysis on the scheduler
activity.

About the performance impact of tracepoints (which is comparable to
markers), even without immediate values optimizations, tests done by
Hideo Aoki on ia64 show no regression. His test case was using hackbench
on a kernel where scheduler instrumentation (about 5 events in code
scheduler code) was added. See the "Tracepoints" patch header for
performance result detail.

Changelog :

- Change instrumentation location and parameter to match ftrace
  instrumentation, previously done with kernel markers.

[ mingo@elte.hu: conflict resolutions ]
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Acked-by: 'Peter Zijlstra' <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/trace/sched.h | 45 +++++++++++++++++++++++++++++++++++++++++++++
 kernel/exit.c         | 10 +++++++++-
 kernel/fork.c         |  3 +++
 kernel/kthread.c      |  5 +++++
 kernel/sched.c        | 17 ++++++-----------
 kernel/signal.c       |  3 +++
 6 files changed, 71 insertions(+), 12 deletions(-)
 create mode 100644 include/trace/sched.h

(limited to 'include')

diff --git a/include/trace/sched.h b/include/trace/sched.h
new file mode 100644
index 000000000000..506ae1323656
--- /dev/null
+++ b/include/trace/sched.h
@@ -0,0 +1,45 @@
+#ifndef _TRACE_SCHED_H
+#define _TRACE_SCHED_H
+
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+DEFINE_TRACE(sched_kthread_stop,
+	TPPROTO(struct task_struct *t),
+	TPARGS(t));
+DEFINE_TRACE(sched_kthread_stop_ret,
+	TPPROTO(int ret),
+	TPARGS(ret));
+DEFINE_TRACE(sched_wait_task,
+	TPPROTO(struct rq *rq, struct task_struct *p),
+	TPARGS(rq, p));
+DEFINE_TRACE(sched_wakeup,
+	TPPROTO(struct rq *rq, struct task_struct *p),
+	TPARGS(rq, p));
+DEFINE_TRACE(sched_wakeup_new,
+	TPPROTO(struct rq *rq, struct task_struct *p),
+	TPARGS(rq, p));
+DEFINE_TRACE(sched_switch,
+	TPPROTO(struct rq *rq, struct task_struct *prev,
+		struct task_struct *next),
+	TPARGS(rq, prev, next));
+DEFINE_TRACE(sched_migrate_task,
+	TPPROTO(struct rq *rq, struct task_struct *p, int dest_cpu),
+	TPARGS(rq, p, dest_cpu));
+DEFINE_TRACE(sched_process_free,
+	TPPROTO(struct task_struct *p),
+	TPARGS(p));
+DEFINE_TRACE(sched_process_exit,
+	TPPROTO(struct task_struct *p),
+	TPARGS(p));
+DEFINE_TRACE(sched_process_wait,
+	TPPROTO(struct pid *pid),
+	TPARGS(pid));
+DEFINE_TRACE(sched_process_fork,
+	TPPROTO(struct task_struct *parent, struct task_struct *child),
+	TPARGS(parent, child));
+DEFINE_TRACE(sched_signal_send,
+	TPPROTO(int sig, struct task_struct *p),
+	TPARGS(sig, p));
+
+#endif
diff --git a/kernel/exit.c b/kernel/exit.c
index 85a83c831856..7b71f87f1207 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -47,6 +47,7 @@
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/tracehook.h>
+#include <trace/sched.h>
 
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
@@ -149,7 +150,10 @@ static void __exit_signal(struct task_struct *tsk)
 
 static void delayed_put_task_struct(struct rcu_head *rhp)
 {
-	put_task_struct(container_of(rhp, struct task_struct, rcu));
+	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
+	trace_sched_process_free(tsk);
+	put_task_struct(tsk);
 }
 
 
@@ -1074,6 +1078,8 @@ NORET_TYPE void do_exit(long code)
 
 	if (group_dead)
 		acct_process();
+	trace_sched_process_exit(tsk);
+
 	exit_sem(tsk);
 	exit_files(tsk);
 	exit_fs(tsk);
@@ -1675,6 +1681,8 @@ static long do_wait(enum pid_type type, struct pid *pid, int options,
 	struct task_struct *tsk;
 	int retval;
 
+	trace_sched_process_wait(pid);
+
 	add_wait_queue(&current->signal->wait_chldexit,&wait);
 repeat:
 	/*
diff --git a/kernel/fork.c b/kernel/fork.c
index 30de644a40c4..cfaff92f61ff 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -58,6 +58,7 @@
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
+#include <trace/sched.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -1364,6 +1365,8 @@ long do_fork(unsigned long clone_flags,
 	if (!IS_ERR(p)) {
 		struct completion vfork;
 
+		trace_sched_process_fork(current, p);
+
 		nr = task_pid_vnr(p);
 
 		if (clone_flags & CLONE_PARENT_SETTID)
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 96cff2f8710b..50598e29439a 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -13,6 +13,7 @@
 #include <linux/file.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <trace/sched.h>
 
 #define KTHREAD_NICE_LEVEL (-5)
 
@@ -206,6 +207,8 @@ int kthread_stop(struct task_struct *k)
 	/* It could exit after stop_info.k set, but before wake_up_process. */
 	get_task_struct(k);
 
+	trace_sched_kthread_stop(k);
+
 	/* Must init completion *before* thread sees kthread_stop_info.k */
 	init_completion(&kthread_stop_info.done);
 	smp_wmb();
@@ -221,6 +224,8 @@ int kthread_stop(struct task_struct *k)
 	ret = kthread_stop_info.err;
 	mutex_unlock(&kthread_stop_lock);
 
+	trace_sched_kthread_stop_ret(ret);
+
 	return ret;
 }
 EXPORT_SYMBOL(kthread_stop);
diff --git a/kernel/sched.c b/kernel/sched.c
index 6f230596bd0c..3d1ad130c24e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -71,6 +71,7 @@
 #include <linux/debugfs.h>
 #include <linux/ctype.h>
 #include <linux/ftrace.h>
+#include <trace/sched.h>
 
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
@@ -1936,6 +1937,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
 		 * just go back and repeat.
 		 */
 		rq = task_rq_lock(p, &flags);
+		trace_sched_wait_task(rq, p);
 		running = task_running(rq, p);
 		on_rq = p->se.on_rq;
 		ncsw = 0;
@@ -2297,9 +2299,7 @@ out_activate:
 	success = 1;
 
 out_running:
-	trace_mark(kernel_sched_wakeup,
-		"pid %d state %ld ## rq %p task %p rq->curr %p",
-		p->pid, p->state, rq, p, rq->curr);
+	trace_sched_wakeup(rq, p);
 	check_preempt_curr(rq, p, sync);
 
 	p->state = TASK_RUNNING;
@@ -2432,9 +2432,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags)
 		p->sched_class->task_new(rq, p);
 		inc_nr_running(rq);
 	}
-	trace_mark(kernel_sched_wakeup_new,
-		"pid %d state %ld ## rq %p task %p rq->curr %p",
-		p->pid, p->state, rq, p, rq->curr);
+	trace_sched_wakeup_new(rq, p);
 	check_preempt_curr(rq, p, 0);
 #ifdef CONFIG_SMP
 	if (p->sched_class->task_wake_up)
@@ -2607,11 +2605,7 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	struct mm_struct *mm, *oldmm;
 
 	prepare_task_switch(rq, prev, next);
-	trace_mark(kernel_sched_schedule,
-		"prev_pid %d next_pid %d prev_state %ld "
-		"## rq %p prev %p next %p",
-		prev->pid, next->pid, prev->state,
-		rq, prev, next);
+	trace_sched_switch(rq, prev, next);
 	mm = next->mm;
 	oldmm = prev->active_mm;
 	/*
@@ -2851,6 +2845,7 @@ static void sched_migrate_task(struct task_struct *p, int dest_cpu)
 	    || unlikely(!cpu_active(dest_cpu)))
 		goto out;
 
+	trace_sched_migrate_task(rq, p, dest_cpu);
 	/* force the process onto the specified CPU */
 	if (migrate_task(p, dest_cpu, &req)) {
 		/* Need to wait for migration thread (might exit: take ref). */
diff --git a/kernel/signal.c b/kernel/signal.c
index e661b01d340f..bf40ecc87b26 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -27,6 +27,7 @@
 #include <linux/freezer.h>
 #include <linux/pid_namespace.h>
 #include <linux/nsproxy.h>
+#include <trace/sched.h>
 
 #include <asm/param.h>
 #include <asm/uaccess.h>
@@ -803,6 +804,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 	struct sigpending *pending;
 	struct sigqueue *q;
 
+	trace_sched_signal_send(sig, t);
+
 	assert_spin_locked(&t->sighand->siglock);
 	if (!prepare_signal(sig, t))
 		return 0;
-- 
cgit v1.2.3


From cf569a932217b97e2fc2c48aa597fe29519a0cff Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Wed, 23 Jul 2008 13:48:22 +0200
Subject: sched: clean up tracepoints

make it a bit more structured hence more readable.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/trace/sched.h | 35 +++++++++++++++++++++++------------
 1 file changed, 23 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/trace/sched.h b/include/trace/sched.h
index 506ae1323656..ad47369d01b5 100644
--- a/include/trace/sched.h
+++ b/include/trace/sched.h
@@ -6,40 +6,51 @@
 
 DEFINE_TRACE(sched_kthread_stop,
 	TPPROTO(struct task_struct *t),
-	TPARGS(t));
+		TPARGS(t));
+
 DEFINE_TRACE(sched_kthread_stop_ret,
 	TPPROTO(int ret),
-	TPARGS(ret));
+		TPARGS(ret));
+
 DEFINE_TRACE(sched_wait_task,
 	TPPROTO(struct rq *rq, struct task_struct *p),
-	TPARGS(rq, p));
+		TPARGS(rq, p));
+
 DEFINE_TRACE(sched_wakeup,
 	TPPROTO(struct rq *rq, struct task_struct *p),
-	TPARGS(rq, p));
+		TPARGS(rq, p));
+
 DEFINE_TRACE(sched_wakeup_new,
 	TPPROTO(struct rq *rq, struct task_struct *p),
-	TPARGS(rq, p));
+		TPARGS(rq, p));
+
 DEFINE_TRACE(sched_switch,
 	TPPROTO(struct rq *rq, struct task_struct *prev,
 		struct task_struct *next),
-	TPARGS(rq, prev, next));
+		TPARGS(rq, prev, next));
+
 DEFINE_TRACE(sched_migrate_task,
 	TPPROTO(struct rq *rq, struct task_struct *p, int dest_cpu),
-	TPARGS(rq, p, dest_cpu));
+		TPARGS(rq, p, dest_cpu));
+
 DEFINE_TRACE(sched_process_free,
 	TPPROTO(struct task_struct *p),
-	TPARGS(p));
+		TPARGS(p));
+
 DEFINE_TRACE(sched_process_exit,
 	TPPROTO(struct task_struct *p),
-	TPARGS(p));
+		TPARGS(p));
+
 DEFINE_TRACE(sched_process_wait,
 	TPPROTO(struct pid *pid),
-	TPARGS(pid));
+		TPARGS(pid));
+
 DEFINE_TRACE(sched_process_fork,
 	TPPROTO(struct task_struct *parent, struct task_struct *child),
-	TPARGS(parent, child));
+		TPARGS(parent, child));
+
 DEFINE_TRACE(sched_signal_send,
 	TPPROTO(int sig, struct task_struct *p),
-	TPARGS(sig, p));
+		TPARGS(sig, p));
 
 #endif
-- 
cgit v1.2.3


From 36dcd67ae994fece615b7c700958d215e884b9ae Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Tue, 29 Jul 2008 12:00:59 +0200
Subject: ftrace: ignore functions that cannot be kprobe-ed

kprobes already has an extensive list of annotations for functions
that should not be instrumented. Add notrace annotations to these
functions as well.

This is particularly useful for functions called by the NMI path.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/kprobes.h | 5 +++--
 kernel/notifier.c       | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 0be7795655fa..497b1d1f7a05 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -29,6 +29,7 @@
  *		<jkenisto@us.ibm.com>  and Prasanna S Panchamukhi
  *		<prasanna@in.ibm.com> added function-return probes.
  */
+#include <linux/linkage.h>
 #include <linux/list.h>
 #include <linux/notifier.h>
 #include <linux/smp.h>
@@ -47,7 +48,7 @@
 #define KPROBE_HIT_SSDONE	0x00000008
 
 /* Attach to insert probes on any functions which should be ignored*/
-#define __kprobes	__attribute__((__section__(".kprobes.text")))
+#define __kprobes	__attribute__((__section__(".kprobes.text"))) notrace
 
 struct kprobe;
 struct pt_regs;
@@ -256,7 +257,7 @@ void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
 
 #else /* CONFIG_KPROBES */
 
-#define __kprobes	/**/
+#define __kprobes	notrace
 struct jprobe;
 struct kretprobe;
 
diff --git a/kernel/notifier.c b/kernel/notifier.c
index 823be11584ef..4282c0a40a57 100644
--- a/kernel/notifier.c
+++ b/kernel/notifier.c
@@ -550,7 +550,7 @@ EXPORT_SYMBOL(unregister_reboot_notifier);
 
 static ATOMIC_NOTIFIER_HEAD(die_chain);
 
-int notify_die(enum die_val val, const char *str,
+int notrace notify_die(enum die_val val, const char *str,
 	       struct pt_regs *regs, long err, int trap, int sig)
 {
 	struct die_args args = {
-- 
cgit v1.2.3


From 8da3821ba5634497da63d58a69e24a97697c4a2b Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 14 Aug 2008 15:45:07 -0400
Subject: ftrace: create __mcount_loc section

This patch creates a section in the kernel called "__mcount_loc".
This will hold a list of pointers to the mcount relocation for
each call site of mcount.

For example:

objdump -dr init/main.o
[...]
Disassembly of section .text:

0000000000000000 <do_one_initcall>:
   0:   55                      push   %rbp
[...]
000000000000017b <init_post>:
 17b:   55                      push   %rbp
 17c:   48 89 e5                mov    %rsp,%rbp
 17f:   53                      push   %rbx
 180:   48 83 ec 08             sub    $0x8,%rsp
 184:   e8 00 00 00 00          callq  189 <init_post+0xe>
                        185: R_X86_64_PC32      mcount+0xfffffffffffffffc
[...]

We will add a section to point to each function call.

   .section __mcount_loc,"a",@progbits
[...]
   .quad .text + 0x185
[...]

The offset to of the mcount call site in init_post is an offset from
the start of the section, and not the start of the function init_post.
The mcount relocation is at the call site 0x185 from the start of the
.text section.

  .text + 0x185  == init_post + 0xa

We need a way to add this __mcount_loc section in a way that we do not
lose the relocations after final link.  The .text section here will
be attached to all other .text sections after final link and the
offsets will be meaningless.  We need to keep track of where these
.text sections are.

To do this, we use the start of the first function in the section.
do_one_initcall.  We can make a tmp.s file with this function as a reference
to the start of the .text section.

   .section __mcount_loc,"a",@progbits
[...]
   .quad do_one_initcall + 0x185
[...]

Then we can compile the tmp.s into a tmp.o

  gcc -c tmp.s -o tmp.o

And link it into back into main.o.

  ld -r main.o tmp.o -o tmp_main.o
  mv tmp_main.o main.o

But we have a problem.  What happens if the first function in a section
is not exported, and is a static function. The linker will not let
the tmp.o use it.  This case exists in main.o as well.

Disassembly of section .init.text:

0000000000000000 <set_reset_devices>:
   0:   55                      push   %rbp
   1:   48 89 e5                mov    %rsp,%rbp
   4:   e8 00 00 00 00          callq  9 <set_reset_devices+0x9>
                        5: R_X86_64_PC32        mcount+0xfffffffffffffffc

The first function in .init.text is a static function.

00000000000000a8 t __setup_set_reset_devices
000000000000105f t __setup_str_set_reset_devices
0000000000000000 t set_reset_devices

The lowercase 't' means that set_reset_devices is local and is not exported.
If we simply try to link the tmp.o with the set_reset_devices we end
up with two symbols: one local and one global.

 .section __mcount_loc,"a",@progbits
 .quad set_reset_devices + 0x10

00000000000000a8 t __setup_set_reset_devices
000000000000105f t __setup_str_set_reset_devices
0000000000000000 t set_reset_devices
                 U set_reset_devices

We still have an undefined reference to set_reset_devices, and if we try
to compile the kernel, we will end up with an undefined reference to
set_reset_devices, or even worst, it could be exported someplace else,
and then we will have a reference to the wrong location.

To handle this case, we make an intermediate step using objcopy.
We convert set_reset_devices into a global exported symbol before linking
it with tmp.o and set it back afterwards.

00000000000000a8 t __setup_set_reset_devices
000000000000105f t __setup_str_set_reset_devices
0000000000000000 T set_reset_devices

00000000000000a8 t __setup_set_reset_devices
000000000000105f t __setup_str_set_reset_devices
0000000000000000 T set_reset_devices

00000000000000a8 t __setup_set_reset_devices
000000000000105f t __setup_str_set_reset_devices
0000000000000000 t set_reset_devices

Now we have a section in main.o called __mcount_loc that we can place
somewhere in the kernel using vmlinux.ld.S and access it to convert
all these locations that call mcount into nops before starting SMP
and thus, eliminating the need to do this with kstop_machine.

Note, A well documented perl script (scripts/recordmcount.pl) is used
to do all this in one location.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/asm-generic/vmlinux.lds.h |   8 ++
 kernel/trace/Kconfig              |   8 ++
 scripts/Makefile.build            |   6 +
 scripts/recordmcount.pl           | 280 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 302 insertions(+)
 create mode 100755 scripts/recordmcount.pl

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 3d8e472a09c8..838d9b2a0da1 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -37,6 +37,13 @@
 #define MEM_DISCARD(sec) *(.mem##sec)
 #endif
 
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+#define MCOUNT_REC()	VMLINUX_SYMBOL(__start_mcount_loc) = .; \
+			*(__mcount_loc)				\
+			VMLINUX_SYMBOL(__stop_mcount_loc) = .;
+#else
+#define MCOUNT_REC()
+#endif
 
 /* .data section */
 #define DATA_DATA							\
@@ -192,6 +199,7 @@
 	/* __*init sections */						\
 	__init_rodata : AT(ADDR(__init_rodata) - LOAD_OFFSET) {		\
 		*(.ref.rodata)						\
+		MCOUNT_REC()						\
 		DEV_KEEP(init.rodata)					\
 		DEV_KEEP(exit.rodata)					\
 		CPU_KEEP(init.rodata)					\
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index cae2637d5e68..14d9505178ca 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -7,6 +7,9 @@ config HAVE_FTRACE
 config HAVE_DYNAMIC_FTRACE
 	bool
 
+config HAVE_FTRACE_MCOUNT_RECORD
+	bool
+
 config TRACER_MAX_TRACE
 	bool
 
@@ -122,6 +125,11 @@ config DYNAMIC_FTRACE
 	 were made. If so, it runs stop_machine (stops all CPUS)
 	 and modifies the code to jump over the call to ftrace.
 
+config FTRACE_MCOUNT_RECORD
+	def_bool y
+	depends on DYNAMIC_FTRACE
+	depends on HAVE_FTRACE_MCOUNT_RECORD
+
 config FTRACE_SELFTEST
 	bool
 
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 277cfe0b7100..463ddcc583ed 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -198,10 +198,16 @@ cmd_modversions =							\
 	fi;
 endif
 
+ifdef CONFIG_FTRACE_MCOUNT_RECORD
+cmd_record_mcount = scripts/recordmcount.pl "$(ARCH)" \
+	"$(OBJDUMP)" "$(OBJCOPY)" "$(CC)" "$(LD)" "$(NM)" "$(RM)" "$(MV)" "$(@)";
+endif
+
 define rule_cc_o_c
 	$(call echo-cmd,checksrc) $(cmd_checksrc)			  \
 	$(call echo-cmd,cc_o_c) $(cmd_cc_o_c);				  \
 	$(cmd_modversions)						  \
+	$(cmd_record_mcount)						  \
 	scripts/basic/fixdep $(depfile) $@ '$(call make-cmd,cc_o_c)' >    \
 	                                              $(dot-target).tmp;  \
 	rm -f $(depfile);						  \
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
new file mode 100755
index 000000000000..44b4b23e91b2
--- /dev/null
+++ b/scripts/recordmcount.pl
@@ -0,0 +1,280 @@
+#!/usr/bin/perl -w
+# (c) 2008, Steven Rostedt <srostedt@redhat.com>
+# Licensed under the terms of the GNU GPL License version 2
+#
+# recordmcount.pl - makes a section called __mcount_loc that holds
+#                   all the offsets to the calls to mcount.
+#
+#
+# What we want to end up with is a section in vmlinux called
+# __mcount_loc that contains a list of pointers to all the
+# call sites in the kernel that call mcount. Later on boot up, the kernel
+# will read this list, save the locations and turn them into nops.
+# When tracing or profiling is later enabled, these locations will then
+# be converted back to pointers to some function.
+#
+# This is no easy feat. This script is called just after the original
+# object is compiled and before it is linked.
+#
+# The references to the call sites are offsets from the section of text
+# that the call site is in. Hence, all functions in a section that
+# has a call site to mcount, will have the offset from the beginning of
+# the section and not the beginning of the function.
+#
+# The trick is to find a way to record the beginning of the section.
+# The way we do this is to look at the first function in the section
+# which will also be the location of that section after final link.
+# e.g.
+#
+#  .section ".text.sched"
+#  .globl my_func
+#  my_func:
+#        [...]
+#        call mcount  (offset: 0x5)
+#        [...]
+#        ret
+#  other_func:
+#        [...]
+#        call mcount (offset: 0x1b)
+#        [...]
+#
+# Both relocation offsets for the mcounts in the above example will be
+# offset from .text.sched. If we make another file called tmp.s with:
+#
+#  .section __mcount_loc
+#  .quad  my_func + 0x5
+#  .quad  my_func + 0x1b
+#
+# We can then compile this tmp.s into tmp.o, and link it to the original
+# object.
+#
+# But this gets hard if my_func is not globl (a static function).
+# In such a case we have:
+#
+#  .section ".text.sched"
+#  my_func:
+#        [...]
+#        call mcount  (offset: 0x5)
+#        [...]
+#        ret
+#  .globl my_func
+#  other_func:
+#        [...]
+#        call mcount (offset: 0x1b)
+#        [...]
+#
+# If we make the tmp.s the same as above, when we link together with
+# the original object, we will end up with two symbols for my_func:
+# one local, one global.  After final compile, we will end up with
+# an undefined reference to my_func.
+#
+# Since local objects can reference local variables, we need to find
+# a way to make tmp.o reference the local objects of the original object
+# file after it is linked together. To do this, we convert the my_func
+# into a global symbol before linking tmp.o. Then after we link tmp.o
+# we will only have a single symbol for my_func that is global.
+# We can convert my_func back into a local symbol and we are done.
+#
+# Here are the steps we take:
+#
+# 1) Record all the local symbols by using 'nm'
+# 2) Use objdump to find all the call site offsets and sections for
+#    mcount.
+# 3) Compile the list into its own object.
+# 4) Do we have to deal with local functions? If not, go to step 8.
+# 5) Make an object that converts these local functions to global symbols
+#    with objcopy.
+# 6) Link together this new object with the list object.
+# 7) Convert the local functions back to local symbols and rename
+#    the result as the original object.
+#    End.
+# 8) Link the object with the list object.
+# 9) Move the result back to the original object.
+#    End.
+#
+
+use strict;
+
+my $P = $0;
+$P =~ s@.*/@@g;
+
+my $V = '0.1';
+
+if ($#ARGV < 6) {
+	print "usage: $P arch objdump objcopy cc ld nm rm mv inputfile\n";
+	print "version: $V\n";
+	exit(1);
+}
+
+my ($arch, $objdump, $objcopy, $cc, $ld, $nm, $rm, $mv, $inputfile) = @ARGV;
+
+$objdump = "objdump" if ((length $objdump) == 0);
+$objcopy = "objcopy" if ((length $objcopy) == 0);
+$cc = "gcc" if ((length $cc) == 0);
+$ld = "ld" if ((length $ld) == 0);
+$nm = "nm" if ((length $nm) == 0);
+$rm = "rm" if ((length $rm) == 0);
+$mv = "mv" if ((length $mv) == 0);
+
+#print STDERR "running: $P '$arch' '$objdump' '$objcopy' '$cc' '$ld' " .
+#    "'$nm' '$rm' '$mv' '$inputfile'\n";
+
+my %locals;
+my %convert;
+
+my $type;
+my $section_regex;	# Find the start of a section
+my $function_regex;	# Find the name of a function (return func name)
+my $mcount_regex;	# Find the call site to mcount (return offset)
+
+if ($arch eq "x86_64") {
+    $section_regex = "Disassembly of section";
+    $function_regex = "<(.*?)>:";
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount([+-]0x[0-9a-zA-Z]+)?\$";
+    $type = ".quad";
+} elsif ($arch eq "i386") {
+    $section_regex = "Disassembly of section";
+    $function_regex = "<(.*?)>:";
+    $mcount_regex = "^\\s*([0-9a-fA-F]+):.*\\smcount\$";
+    $type = ".long";
+} else {
+    die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
+}
+
+my $text_found = 0;
+my $read_function = 0;
+my $opened = 0;
+my $text = "";
+my $mcount_section = "__mcount_loc";
+
+my $dirname;
+my $filename;
+my $prefix;
+my $ext;
+
+if ($inputfile =~ m,^(.*)/([^/]*)$,) {
+    $dirname = $1;
+    $filename = $2;
+} else {
+    $dirname = ".";
+    $filename = $inputfile;
+}
+
+if ($filename =~ m,^(.*)(\.\S),) {
+    $prefix = $1;
+    $ext = $2;
+} else {
+    $prefix = $filename;
+    $ext = "";
+}
+
+my $mcount_s = $dirname . "/.tmp_mc_" . $prefix . ".s";
+my $mcount_o = $dirname . "/.tmp_mc_" . $prefix . ".o";
+
+#
+# Step 1: find all the local symbols (static functions).
+#
+open (IN, "$nm $inputfile|") || die "error running $nm";
+while (<IN>) {
+    if (/^[0-9a-fA-F]+\s+t\s+(\S+)/) {
+	$locals{$1} = 1;
+    }
+}
+close(IN);
+
+#
+# Step 2: find the sections and mcount call sites
+#
+open(IN, "$objdump -dr $inputfile|") || die "error running $objdump";
+
+while (<IN>) {
+    # is it a section?
+    if (/$section_regex/) {
+	$read_function = 1;
+	$text_found = 0;
+    # section found, now is this a start of a function?
+    } elsif ($read_function && /$function_regex/) {
+	$read_function = 0;
+	$text_found = 1;
+	$text = $1;
+	# is this function static? If so, note this fact.
+	if (defined $locals{$text}) {
+	    $convert{$text} = 1;
+	}
+    # is this a call site to mcount? If so, print the offset from the section
+    } elsif ($text_found && /$mcount_regex/) {
+	if (!$opened) {
+	    open(FILE, ">$mcount_s") || die "can't create $mcount_s\n";
+	    $opened = 1;
+	    print FILE "\t.section $mcount_section,\"a\",\@progbits\n";
+	}
+	print FILE "\t$type $text + 0x$1\n";
+    }
+}
+
+# If we did not find any mcount callers, we are done (do nothing).
+if (!$opened) {
+    exit(0);
+}
+
+close(FILE);
+
+#
+# Step 3: Compile the file that holds the list of call sites to mcount.
+#
+`$cc -o $mcount_o -c $mcount_s`;
+
+my @converts = keys %convert;
+
+#
+# Step 4: Do we have sections that started with local functions?
+#
+if ($#converts >= 0) {
+    my $globallist = "";
+    my $locallist = "";
+
+    foreach my $con (@converts) {
+	$globallist .= " --globalize-symbol $con";
+	$locallist .= " --localize-symbol $con";
+    }
+
+    my $globalobj = $dirname . "/.tmp_gl_" . $filename;
+    my $globalmix = $dirname . "/.tmp_mx_" . $filename;
+
+    #
+    # Step 5: set up each local function as a global
+    #
+    `$objcopy $globallist $inputfile $globalobj`;
+
+    #
+    # Step 6: Link the global version to our list.
+    #
+    `$ld -r $globalobj $mcount_o -o $globalmix`;
+
+    #
+    # Step 7: Convert the local functions back into local symbols
+    #
+    `$objcopy $locallist $globalmix $inputfile`;
+
+    # Remove the temp files
+    `$rm $globalobj $globalmix`;
+
+} else {
+
+    my $mix = $dirname . "/.tmp_mx_" . $filename;
+
+    #
+    # Step 8: Link the object with our list of call sites object.
+    #
+    `$ld -r $inputfile $mcount_o -o $mix`;
+
+    #
+    # Step 9: Move the result back to the original object.
+    #
+    `$mv $mix $inputfile`;
+}
+
+# Clean up the temp files
+`$rm $mcount_o $mcount_s`;
+
+exit(0);
-- 
cgit v1.2.3


From 68bf21aa15c85d2e9b623dcda2b1ed8893275fa1 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 14 Aug 2008 15:45:08 -0400
Subject: ftrace: mcount call site on boot nops core

This is the infrastructure to the converting the mcount call sites
recorded by the __mcount_loc section into nops on boot. It also allows
for using these sites to enable tracing as normal. When the __mcount_loc
section is used, the "ftraced" kernel thread is disabled.

This uses the current infrastructure to record the mcount call sites
as well as convert them to nops. The mcount function is kept as a stub
on boot up and not converted to the ftrace_record_ip function. We use the
ftrace_record_ip to only record from the table.

This patch does not handle modules. That comes with a later patch.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/asm-x86/ftrace.h |  10 ++++
 include/linux/ftrace.h   |   6 ++
 init/main.c              |   3 +
 kernel/trace/ftrace.c    | 148 +++++++++++++++++++++++++++++++++--------------
 4 files changed, 124 insertions(+), 43 deletions(-)

(limited to 'include')

diff --git a/include/asm-x86/ftrace.h b/include/asm-x86/ftrace.h
index be0e004ad148..1bb6f9bbe1ab 100644
--- a/include/asm-x86/ftrace.h
+++ b/include/asm-x86/ftrace.h
@@ -7,6 +7,16 @@
 
 #ifndef __ASSEMBLY__
 extern void mcount(void);
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/*
+	 * call mcount is "e8 <4 byte offset>"
+	 * The addr points to the 4 byte offset and the caller of this
+	 * function wants the pointer to e8. Simply subtract one.
+	 */
+	return addr - 1;
+}
 #endif
 
 #endif /* CONFIG_FTRACE */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index bb384068272e..d4d6ab453b78 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -162,4 +162,10 @@ static inline void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
 #endif
 
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+extern void ftrace_init(void);
+#else
+static inline void ftrace_init(void) { }
+#endif
+
 #endif /* _LINUX_FTRACE_H */
diff --git a/init/main.c b/init/main.c
index 3820323c4c84..ded1fae965ab 100644
--- a/init/main.c
+++ b/init/main.c
@@ -60,6 +60,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/idr.h>
+#include <linux/ftrace.h>
 
 #include <asm/io.h>
 #include <asm/bugs.h>
@@ -687,6 +688,8 @@ asmlinkage void __init start_kernel(void)
 
 	acpi_early_init(); /* before LAPIC and SMP init */
 
+	ftrace_init();
+
 	/* Do the rest non-__init'ed, we're now alive */
 	rest_init();
 }
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index f6e3af31b403..df96d5990c04 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -792,47 +792,7 @@ static int ftrace_update_code(void)
 	return 1;
 }
 
-static int ftraced(void *ignore)
-{
-	unsigned long usecs;
-
-	while (!kthread_should_stop()) {
-
-		set_current_state(TASK_INTERRUPTIBLE);
-
-		/* check once a second */
-		schedule_timeout(HZ);
-
-		if (unlikely(ftrace_disabled))
-			continue;
-
-		mutex_lock(&ftrace_sysctl_lock);
-		mutex_lock(&ftraced_lock);
-		if (!ftraced_suspend && !ftraced_stop &&
-		    ftrace_update_code()) {
-			usecs = nsecs_to_usecs(ftrace_update_time);
-			if (ftrace_update_tot_cnt > 100000) {
-				ftrace_update_tot_cnt = 0;
-				pr_info("hm, dftrace overflow: %lu change%s"
-					" (%lu total) in %lu usec%s\n",
-					ftrace_update_cnt,
-					ftrace_update_cnt != 1 ? "s" : "",
-					ftrace_update_tot_cnt,
-					usecs, usecs != 1 ? "s" : "");
-				ftrace_disabled = 1;
-				WARN_ON_ONCE(1);
-			}
-		}
-		mutex_unlock(&ftraced_lock);
-		mutex_unlock(&ftrace_sysctl_lock);
-
-		ftrace_shutdown_replenish();
-	}
-	__set_current_state(TASK_RUNNING);
-	return 0;
-}
-
-static int __init ftrace_dyn_table_alloc(void)
+static int __init ftrace_dyn_table_alloc(unsigned long num_to_init)
 {
 	struct ftrace_page *pg;
 	int cnt;
@@ -859,7 +819,9 @@ static int __init ftrace_dyn_table_alloc(void)
 
 	pg = ftrace_pages = ftrace_pages_start;
 
-	cnt = NR_TO_INIT / ENTRIES_PER_PAGE;
+	cnt = num_to_init / ENTRIES_PER_PAGE;
+	pr_info("ftrace: allocating %ld hash entries in %d pages\n",
+		num_to_init, cnt);
 
 	for (i = 0; i < cnt; i++) {
 		pg->next = (void *)get_zeroed_page(GFP_KERNEL);
@@ -1556,6 +1518,104 @@ static __init int ftrace_init_debugfs(void)
 
 fs_initcall(ftrace_init_debugfs);
 
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+static int ftrace_convert_nops(unsigned long *start,
+			       unsigned long *end)
+{
+	unsigned long *p;
+	unsigned long addr;
+	unsigned long flags;
+
+	p = start;
+	while (p < end) {
+		addr = ftrace_call_adjust(*p++);
+		ftrace_record_ip(addr);
+		ftrace_shutdown_replenish();
+	}
+
+	/* p is ignored */
+	local_irq_save(flags);
+	__ftrace_update_code(p);
+	local_irq_restore(flags);
+
+	return 0;
+}
+
+extern unsigned long __start_mcount_loc[];
+extern unsigned long __stop_mcount_loc[];
+
+void __init ftrace_init(void)
+{
+	unsigned long count, addr, flags;
+	int ret;
+
+	/* Keep the ftrace pointer to the stub */
+	addr = (unsigned long)ftrace_stub;
+
+	local_irq_save(flags);
+	ftrace_dyn_arch_init(&addr);
+	local_irq_restore(flags);
+
+	/* ftrace_dyn_arch_init places the return code in addr */
+	if (addr)
+		goto failed;
+
+	count = __stop_mcount_loc - __start_mcount_loc;
+
+	ret = ftrace_dyn_table_alloc(count);
+	if (ret)
+		goto failed;
+
+	last_ftrace_enabled = ftrace_enabled = 1;
+
+	ret = ftrace_convert_nops(__start_mcount_loc,
+				  __stop_mcount_loc);
+
+	return;
+ failed:
+	ftrace_disabled = 1;
+}
+#else /* CONFIG_FTRACE_MCOUNT_RECORD */
+static int ftraced(void *ignore)
+{
+	unsigned long usecs;
+
+	while (!kthread_should_stop()) {
+
+		set_current_state(TASK_INTERRUPTIBLE);
+
+		/* check once a second */
+		schedule_timeout(HZ);
+
+		if (unlikely(ftrace_disabled))
+			continue;
+
+		mutex_lock(&ftrace_sysctl_lock);
+		mutex_lock(&ftraced_lock);
+		if (!ftraced_suspend && !ftraced_stop &&
+		    ftrace_update_code()) {
+			usecs = nsecs_to_usecs(ftrace_update_time);
+			if (ftrace_update_tot_cnt > 100000) {
+				ftrace_update_tot_cnt = 0;
+				pr_info("hm, dftrace overflow: %lu change%s"
+					" (%lu total) in %lu usec%s\n",
+					ftrace_update_cnt,
+					ftrace_update_cnt != 1 ? "s" : "",
+					ftrace_update_tot_cnt,
+					usecs, usecs != 1 ? "s" : "");
+				ftrace_disabled = 1;
+				WARN_ON_ONCE(1);
+			}
+		}
+		mutex_unlock(&ftraced_lock);
+		mutex_unlock(&ftrace_sysctl_lock);
+
+		ftrace_shutdown_replenish();
+	}
+	__set_current_state(TASK_RUNNING);
+	return 0;
+}
+
 static int __init ftrace_dynamic_init(void)
 {
 	struct task_struct *p;
@@ -1572,7 +1632,7 @@ static int __init ftrace_dynamic_init(void)
 		goto failed;
 	}
 
-	ret = ftrace_dyn_table_alloc();
+	ret = ftrace_dyn_table_alloc(NR_TO_INIT);
 	if (ret)
 		goto failed;
 
@@ -1593,6 +1653,8 @@ static int __init ftrace_dynamic_init(void)
 }
 
 core_initcall(ftrace_dynamic_init);
+#endif /* CONFIG_FTRACE_MCOUNT_RECORD */
+
 #else
 # define ftrace_startup()		do { } while (0)
 # define ftrace_shutdown()		do { } while (0)
-- 
cgit v1.2.3


From 90d595fe5ca4b685465c068907e6e554760abea8 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 14 Aug 2008 15:45:09 -0400
Subject: ftrace: enable mcount recording for modules

This patch enables the loading of the __mcount_section of modules and
changing all the callers of mcount into nops.

The modification is done before the init_module function is called, so
again, we do not need to use kstop_machine to make these changes.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h |  3 +++
 kernel/module.c        | 11 +++++++++++
 kernel/trace/ftrace.c  |  5 +++++
 3 files changed, 19 insertions(+)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index d4d6ab453b78..4936489f9ed8 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -164,8 +164,11 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
+extern void ftrace_init_module(unsigned long *start, unsigned long *end);
 #else
 static inline void ftrace_init(void) { }
+static inline void
+ftrace_init_module(unsigned long *start, unsigned long *end) { }
 #endif
 
 #endif /* _LINUX_FTRACE_H */
diff --git a/kernel/module.c b/kernel/module.c
index 661d73db786e..d753fd9d83ec 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -47,6 +47,7 @@
 #include <linux/license.h>
 #include <asm/sections.h>
 #include <linux/tracepoint.h>
+#include <linux/ftrace.h>
 
 #if 0
 #define DEBUGP printk
@@ -1834,6 +1835,7 @@ static noinline struct module *load_module(void __user *umod,
 	unsigned int markersstringsindex;
 	unsigned int tracepointsindex;
 	unsigned int tracepointsstringsindex;
+	unsigned int mcountindex;
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
@@ -2124,6 +2126,9 @@ static noinline struct module *load_module(void __user *umod,
 	tracepointsstringsindex = find_sec(hdr, sechdrs, secstrings,
 					"__tracepoints_strings");
 
+	mcountindex = find_sec(hdr, sechdrs, secstrings,
+			       "__mcount_loc");
+
 	/* Now do relocations. */
 	for (i = 1; i < hdr->e_shnum; i++) {
 		const char *strtab = (char *)sechdrs[strindex].sh_addr;
@@ -2184,6 +2189,12 @@ static noinline struct module *load_module(void __user *umod,
 			mod->tracepoints + mod->num_tracepoints);
 #endif
 	}
+
+	if (mcountindex) {
+		void *mseg = (void *)sechdrs[mcountindex].sh_addr;
+		ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size);
+	}
+
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)
 		goto cleanup;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index df96d5990c04..ea45bb1c0fd6 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1541,6 +1541,11 @@ static int ftrace_convert_nops(unsigned long *start,
 	return 0;
 }
 
+void ftrace_init_module(unsigned long *start, unsigned long *end)
+{
+	ftrace_convert_nops(start, end);
+}
+
 extern unsigned long __start_mcount_loc[];
 extern unsigned long __stop_mcount_loc[];
 
-- 
cgit v1.2.3


From 29e71abf56cebc5c5a4e184a6eb4360cc58554ad Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 14 Aug 2008 15:45:10 -0400
Subject: ftrace: rebuild everything on change to FTRACE_MCOUNT_RECORD

When enabling or disabling CONFIG_FTRACE_MCOUNT_RECORD, we want a full
kernel compile to handle the adding of the __mcount_loc sections.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/kernel.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include')

diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 75d81f157d2e..ecce4a4ccd5f 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -486,4 +486,9 @@ struct sysinfo {
 #define NUMA_BUILD 0
 #endif
 
+/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
+#endif
+
 #endif
-- 
cgit v1.2.3


From 28614889bcb2558a47d02d52394b7fd9795a9547 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 14 Aug 2008 22:47:18 -0400
Subject: ftrace: move notrace to compiler.h

The notrace define belongs in compiler.h so that it can be used in
init.h

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/compiler.h | 2 ++
 include/linux/linkage.h  | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 8322141ee480..98115d9d04da 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -44,6 +44,8 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # error Sorry, your compiler is too old/not recognized.
 #endif
 
+#define notrace __attribute__((no_instrument_function))
+
 /* Intel compiler defines __GNUC__. So we will overwrite implementations
  * coming from above header files here
  */
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index 56ba37394656..9fd1f859021b 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -4,8 +4,6 @@
 #include <linux/compiler.h>
 #include <asm/linkage.h>
 
-#define notrace __attribute__((no_instrument_function))
-
 #ifdef __cplusplus
 #define CPP_ASMLINKAGE extern "C"
 #else
-- 
cgit v1.2.3


From fed1939c64d2288938fdc1c367d49082da65e195 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 14 Aug 2008 22:47:19 -0400
Subject: ftrace: remove old pointers to mcount

When a mcount pointer is recorded into a table, it is used to add or
remove calls to mcount (replacing them with nops). If the code is removed
via removing a module, the pointers still exist.  At modifying the code
a check is always made to make sure the code being replaced is the code
expected. In-other-words, the code being replaced is compared to what
it is expected to be before being replaced.

There is a very small chance that the code being replaced just happens
to look like code that calls mcount (very small since the call to mcount
is relative). To remove this chance, this patch adds ftrace_release to
allow module unloading to remove the pointers to mcount within the module.

Another change for init calls is made to not trace calls marked with
__init. The tracing can not be started until after init is done anyway.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h |  2 ++
 include/linux/init.h   |  2 +-
 kernel/module.c        | 12 ++++++++----
 kernel/trace/ftrace.c  | 32 ++++++++++++++++++++++++++++++--
 4 files changed, 41 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 4936489f9ed8..6b232a2460c0 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -165,10 +165,12 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
 extern void ftrace_init_module(unsigned long *start, unsigned long *end);
+extern void ftrace_release(void *start, unsigned long size);
 #else
 static inline void ftrace_init(void) { }
 static inline void
 ftrace_init_module(unsigned long *start, unsigned long *end) { }
+static inline void ftrace_release(void *start, unsigned long size) { }
 #endif
 
 #endif /* _LINUX_FTRACE_H */
diff --git a/include/linux/init.h b/include/linux/init.h
index 93538b696e3d..27f61f6b3cb9 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -40,7 +40,7 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(.init.text) __cold
+#define __init		__section(.init.text) __cold notrace
 #define __initdata	__section(.init.data)
 #define __initconst	__section(.init.rodata)
 #define __exitdata	__section(.exit.data)
diff --git a/kernel/module.c b/kernel/module.c
index d753fd9d83ec..7576c2d9462f 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1431,6 +1431,9 @@ static void free_module(struct module *mod)
 	/* Module unload stuff */
 	module_unload_free(mod);
 
+	/* release any pointers to mcount in this module */
+	ftrace_release(mod->module_core, mod->core_size);
+
 	/* This may be NULL, but that's OK */
 	module_free(mod, mod->module_init);
 	kfree(mod->args);
@@ -1839,6 +1842,7 @@ static noinline struct module *load_module(void __user *umod,
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
+	void *mseg;
 	struct exception_table_entry *extable;
 	mm_segment_t old_fs;
 
@@ -2190,10 +2194,9 @@ static noinline struct module *load_module(void __user *umod,
 #endif
 	}
 
-	if (mcountindex) {
-		void *mseg = (void *)sechdrs[mcountindex].sh_addr;
-		ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size);
-	}
+	/* sechdrs[0].sh_size is always zero */
+	mseg = (void *)sechdrs[mcountindex].sh_addr;
+	ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size);
 
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)
@@ -2264,6 +2267,7 @@ static noinline struct module *load_module(void __user *umod,
  cleanup:
 	kobject_del(&mod->mkobj.kobj);
 	kobject_put(&mod->mkobj.kobj);
+	ftrace_release(mod->module_core, mod->core_size);
  free_unload:
 	module_unload_free(mod);
 	module_free(mod, mod->module_init);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 8affb6d00ec1..eadd0eaea9b6 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -294,13 +294,37 @@ static inline void ftrace_del_hash(struct dyn_ftrace *node)
 
 static void ftrace_free_rec(struct dyn_ftrace *rec)
 {
-	/* no locking, only called from kstop_machine */
-
 	rec->ip = (unsigned long)ftrace_free_records;
 	ftrace_free_records = rec;
 	rec->flags |= FTRACE_FL_FREE;
 }
 
+void ftrace_release(void *start, unsigned long size)
+{
+	struct dyn_ftrace *rec;
+	struct ftrace_page *pg;
+	unsigned long s = (unsigned long)start;
+	unsigned long e = s + size;
+	int i;
+
+	if (!start)
+		return;
+
+	/* No interrupt should call this */
+	spin_lock(&ftrace_lock);
+
+	for (pg = ftrace_pages_start; pg; pg = pg->next) {
+		for (i = 0; i < pg->index; i++) {
+			rec = &pg->records[i];
+
+			if ((rec->ip >= s) && (rec->ip < e))
+				ftrace_free_rec(rec);
+		}
+	}
+	spin_unlock(&ftrace_lock);
+
+}
+
 static struct dyn_ftrace *ftrace_alloc_dyn_node(unsigned long ip)
 {
 	struct dyn_ftrace *rec;
@@ -1527,7 +1551,9 @@ static int ftrace_convert_nops(unsigned long *start,
 	p = start;
 	while (p < end) {
 		addr = ftrace_call_adjust(*p++);
+		spin_lock(&ftrace_lock);
 		ftrace_record_ip(addr);
+		spin_unlock(&ftrace_lock);
 		ftrace_shutdown_replenish();
 	}
 
@@ -1541,6 +1567,8 @@ static int ftrace_convert_nops(unsigned long *start,
 
 void ftrace_init_module(unsigned long *start, unsigned long *end)
 {
+	if (start == end)
+		return;
 	ftrace_convert_nops(start, end);
 }
 
-- 
cgit v1.2.3


From dd0e545f061f90099a3dcc13aa77e29c6295cf23 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Fri, 1 Aug 2008 12:26:41 -0400
Subject: ftrace: printk formatting infrastructure

This patch adds a feature that can help kernel developers debug their
code using ftrace.

  int ftrace_printk(const char *fmt, ...);

This records into the ftrace buffer using printf formatting. The entry
size in the buffers are still a fixed length. A new type has been added
that allows for more entries to be used for a single recording.

The start of the print is still the same as the other entries.

It returns the number of characters written to the ftrace buffer.

For example:

Having a module with the following code:

static int __init ftrace_print_test(void)
{
        ftrace_printk("jiffies are %ld\n", jiffies);
        return 0;
}

Gives me:

  insmod-5441  3...1 7569us : ftrace_print_test: jiffies are 4296626666

for the latency_trace file and:

          insmod-5441  [03]  1959.370498: ftrace_print_test jiffies are 4296626666

for the trace file.

Note: Only the infrastructure should go into the kernel. It is to help
facilitate debugging for other kernel developers. Calls to ftrace_printk
is not intended to be left in the kernel, and should be frowned upon just
like scattering printks around in the code.

But having this easily at your fingertips helps the debugging go faster
and bugs be solved quicker.

Maybe later on, we can hook this with markers and have their printf format
be sucked into ftrace output.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h        |  10 ++
 kernel/trace/trace.c          | 273 +++++++++++++++++++++++++++++++++++++-----
 kernel/trace/trace.h          |  11 ++
 kernel/trace/trace_selftest.c |  11 +-
 4 files changed, 272 insertions(+), 33 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 6b232a2460c0..f53b975e32fa 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -157,9 +157,18 @@ static inline void __ftrace_enabled_restore(int enabled)
 #ifdef CONFIG_TRACING
 extern void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
+# define ftrace_printk(x...) __ftrace_printk(_THIS_IP_, x)
+extern int
+__ftrace_printk(unsigned long ip, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
 #else
 static inline void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
+static inline int
+ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)))
+{
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
@@ -173,4 +182,5 @@ ftrace_init_module(unsigned long *start, unsigned long *end) { }
 static inline void ftrace_release(void *start, unsigned long size) { }
 #endif
 
+
 #endif /* _LINUX_FTRACE_H */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 76dfe6d2466c..a917bea82715 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -197,12 +197,14 @@ unsigned long nsecs_to_usecs(unsigned long nsecs)
  *  NEED_RESCED - reschedule is requested
  *  HARDIRQ	- inside an interrupt handler
  *  SOFTIRQ	- inside a softirq handler
+ *  CONT	- multiple entries hold the trace item
  */
 enum trace_flag_type {
 	TRACE_FLAG_IRQS_OFF		= 0x01,
 	TRACE_FLAG_NEED_RESCHED		= 0x02,
 	TRACE_FLAG_HARDIRQ		= 0x04,
 	TRACE_FLAG_SOFTIRQ		= 0x08,
+	TRACE_FLAG_CONT			= 0x10,
 };
 
 /*
@@ -1074,6 +1076,7 @@ enum trace_file_type {
 	TRACE_FILE_LAT_FMT	= 1,
 };
 
+/* Return the current entry.  */
 static struct trace_entry *
 trace_entry_idx(struct trace_array *tr, struct trace_array_cpu *data,
 		struct trace_iterator *iter, int cpu)
@@ -1104,8 +1107,58 @@ trace_entry_idx(struct trace_array *tr, struct trace_array_cpu *data,
 	return &array[iter->next_page_idx[cpu]];
 }
 
+/* Increment the index counter of an iterator by one */
+static void trace_iterator_increment(struct trace_iterator *iter, int cpu)
+{
+	iter->idx++;
+	iter->next_idx[cpu]++;
+	iter->next_page_idx[cpu]++;
+
+	if (iter->next_page_idx[cpu] >= ENTRIES_PER_PAGE) {
+		struct trace_array_cpu *data = iter->tr->data[cpu];
+
+		iter->next_page_idx[cpu] = 0;
+		iter->next_page[cpu] =
+			trace_next_list(data, iter->next_page[cpu]);
+	}
+}
+
 static struct trace_entry *
-find_next_entry(struct trace_iterator *iter, int *ent_cpu)
+trace_entry_next(struct trace_array *tr, struct trace_array_cpu *data,
+		 struct trace_iterator *iter, int cpu)
+{
+	struct list_head *next_page;
+	struct trace_entry *ent;
+	int idx, next_idx, next_page_idx;
+
+	ent = trace_entry_idx(tr, tr->data[cpu], iter, cpu);
+
+	if (likely(!ent || ent->type != TRACE_CONT))
+		return ent;
+
+	/* save the iterator details */
+	idx		= iter->idx;
+	next_idx	= iter->next_idx[cpu];
+	next_page_idx	= iter->next_page_idx[cpu];
+	next_page	= iter->next_page[cpu];
+
+	/* find a real entry */
+	do {
+		trace_iterator_increment(iter, cpu);
+		ent = trace_entry_idx(tr, tr->data[cpu], iter, cpu);
+	} while (ent && ent->type != TRACE_CONT);
+
+	/* reset the iterator */
+	iter->idx			= idx;
+	iter->next_idx[cpu]		= next_idx;
+	iter->next_page_idx[cpu]	= next_page_idx;
+	iter->next_page[cpu]		= next_page;
+
+	return ent;
+}
+
+static struct trace_entry *
+__find_next_entry(struct trace_iterator *iter, int *ent_cpu, int inc)
 {
 	struct trace_array *tr = iter->tr;
 	struct trace_entry *ent, *next = NULL;
@@ -1115,7 +1168,23 @@ find_next_entry(struct trace_iterator *iter, int *ent_cpu)
 	for_each_tracing_cpu(cpu) {
 		if (!head_page(tr->data[cpu]))
 			continue;
+
 		ent = trace_entry_idx(tr, tr->data[cpu], iter, cpu);
+
+		if (ent && ent->type == TRACE_CONT) {
+			struct trace_array_cpu *data = tr->data[cpu];
+
+			if (!inc)
+				ent = trace_entry_next(tr, data, iter, cpu);
+			else {
+				while (ent && ent->type == TRACE_CONT) {
+					trace_iterator_increment(iter, cpu);
+					ent = trace_entry_idx(tr, tr->data[cpu],
+							      iter, cpu);
+				}
+			}
+		}
+
 		/*
 		 * Pick the entry with the smallest timestamp:
 		 */
@@ -1131,25 +1200,39 @@ find_next_entry(struct trace_iterator *iter, int *ent_cpu)
 	return next;
 }
 
-static void trace_iterator_increment(struct trace_iterator *iter)
+/* Find the next real entry, without updating the iterator itself */
+static struct trace_entry *
+find_next_entry(struct trace_iterator *iter, int *ent_cpu)
 {
-	iter->idx++;
-	iter->next_idx[iter->cpu]++;
-	iter->next_page_idx[iter->cpu]++;
+	return __find_next_entry(iter, ent_cpu, 0);
+}
+
+/* Find the next real entry, and increment the iterator to the next entry */
+static void *find_next_entry_inc(struct trace_iterator *iter)
+{
+	struct trace_entry *next;
+	int next_cpu = -1;
 
-	if (iter->next_page_idx[iter->cpu] >= ENTRIES_PER_PAGE) {
-		struct trace_array_cpu *data = iter->tr->data[iter->cpu];
+	next = __find_next_entry(iter, &next_cpu, 1);
 
-		iter->next_page_idx[iter->cpu] = 0;
-		iter->next_page[iter->cpu] =
-			trace_next_list(data, iter->next_page[iter->cpu]);
-	}
+	iter->prev_ent = iter->ent;
+	iter->prev_cpu = iter->cpu;
+
+	iter->ent = next;
+	iter->cpu = next_cpu;
+
+	if (next)
+		trace_iterator_increment(iter, iter->cpu);
+
+	return next ? iter : NULL;
 }
 
 static void trace_consume(struct trace_iterator *iter)
 {
 	struct trace_array_cpu *data = iter->tr->data[iter->cpu];
+	struct trace_entry *ent;
 
+ again:
 	data->trace_tail_idx++;
 	if (data->trace_tail_idx >= ENTRIES_PER_PAGE) {
 		data->trace_tail = trace_next_page(data, data->trace_tail);
@@ -1160,25 +1243,11 @@ static void trace_consume(struct trace_iterator *iter)
 	if (data->trace_head == data->trace_tail &&
 	    data->trace_head_idx == data->trace_tail_idx)
 		data->trace_idx = 0;
-}
-
-static void *find_next_entry_inc(struct trace_iterator *iter)
-{
-	struct trace_entry *next;
-	int next_cpu = -1;
-
-	next = find_next_entry(iter, &next_cpu);
-
-	iter->prev_ent = iter->ent;
-	iter->prev_cpu = iter->cpu;
-
-	iter->ent = next;
-	iter->cpu = next_cpu;
-
-	if (next)
-		trace_iterator_increment(iter);
 
-	return next ? iter : NULL;
+	ent = trace_entry_idx(iter->tr, iter->tr->data[iter->cpu],
+			      iter, iter->cpu);
+	if (ent && ent->type == TRACE_CONT)
+		goto again;
 }
 
 static void *s_next(struct seq_file *m, void *v, loff_t *pos)
@@ -1473,6 +1542,26 @@ lat_print_timestamp(struct trace_seq *s, unsigned long long abs_usecs,
 
 static const char state_to_char[] = TASK_STATE_TO_CHAR_STR;
 
+static void
+trace_seq_print_cont(struct trace_seq *s, struct trace_iterator *iter)
+{
+	struct trace_array *tr = iter->tr;
+	struct trace_array_cpu *data = tr->data[iter->cpu];
+	struct trace_entry *ent;
+
+	ent = trace_entry_idx(tr, data, iter, iter->cpu);
+	if (!ent || ent->type != TRACE_CONT) {
+		trace_seq_putc(s, '\n');
+		return;
+	}
+
+	do {
+		trace_seq_printf(s, "%s", ent->cont.buf);
+		trace_iterator_increment(iter, iter->cpu);
+		ent = trace_entry_idx(tr, data, iter, iter->cpu);
+	} while (ent && ent->type == TRACE_CONT);
+}
+
 static int
 print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 {
@@ -1491,6 +1580,10 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 
 	if (!next_entry)
 		next_entry = entry;
+
+	if (entry->type == TRACE_CONT)
+		return 1;
+
 	rel_usecs = ns2usecs(next_entry->field.t - entry->field.t);
 	abs_usecs = ns2usecs(entry->field.t - iter->tr->time_start);
 
@@ -1550,6 +1643,12 @@ print_lat_fmt(struct trace_iterator *iter, unsigned int trace_idx, int cpu)
 		}
 		trace_seq_puts(s, "\n");
 		break;
+	case TRACE_PRINT:
+		seq_print_ip_sym(s, field->print.ip, sym_flags);
+		trace_seq_printf(s, ": %s", field->print.buf);
+		if (field->flags && TRACE_FLAG_CONT)
+			trace_seq_print_cont(s, iter);
+		break;
 	default:
 		trace_seq_printf(s, "Unknown type %d\n", entry->type);
 	}
@@ -1571,6 +1670,10 @@ static int print_trace_fmt(struct trace_iterator *iter)
 	int i;
 
 	entry = iter->ent;
+
+	if (entry->type == TRACE_CONT)
+		return 1;
+
 	field = &entry->field;
 
 	comm = trace_find_cmdline(iter->ent->field.pid);
@@ -1653,6 +1756,12 @@ static int print_trace_fmt(struct trace_iterator *iter)
 		if (!ret)
 			return 0;
 		break;
+	case TRACE_PRINT:
+		seq_print_ip_sym(s, field->print.ip, sym_flags);
+		trace_seq_printf(s, ": %s", field->print.buf);
+		if (field->flags && TRACE_FLAG_CONT)
+			trace_seq_print_cont(s, iter);
+		break;
 	}
 	return 1;
 }
@@ -1666,6 +1775,10 @@ static int print_raw_fmt(struct trace_iterator *iter)
 	int S, T;
 
 	entry = iter->ent;
+
+	if (entry->type == TRACE_CONT)
+		return 1;
+
 	field = &entry->field;
 
 	ret = trace_seq_printf(s, "%d %d %llu ",
@@ -1708,6 +1821,12 @@ static int print_raw_fmt(struct trace_iterator *iter)
 		if (!ret)
 			return 0;
 		break;
+	case TRACE_PRINT:
+		trace_seq_printf(s, "# %lx %s",
+				 field->print.ip, field->print.buf);
+		if (field->flags && TRACE_FLAG_CONT)
+			trace_seq_print_cont(s, iter);
+		break;
 	}
 	return 1;
 }
@@ -1733,6 +1852,10 @@ static int print_hex_fmt(struct trace_iterator *iter)
 	int S, T;
 
 	entry = iter->ent;
+
+	if (entry->type == TRACE_CONT)
+		return 1;
+
 	field = &entry->field;
 
 	SEQ_PUT_HEX_FIELD_RET(s, field->pid);
@@ -1778,6 +1901,10 @@ static int print_bin_fmt(struct trace_iterator *iter)
 	struct trace_field *field;
 
 	entry = iter->ent;
+
+	if (entry->type == TRACE_CONT)
+		return 1;
+
 	field = &entry->field;
 
 	SEQ_PUT_FIELD_RET(s, field->pid);
@@ -2943,6 +3070,94 @@ static __init void tracer_init_debugfs(void)
 #endif
 }
 
+#define TRACE_BUF_SIZE 1024
+#define TRACE_PRINT_BUF_SIZE \
+	(sizeof(struct trace_field) - offsetof(struct trace_field, print.buf))
+#define TRACE_CONT_BUF_SIZE sizeof(struct trace_field)
+
+/**
+ * ftrace_printk - printf formatting in the ftrace buffer
+ * @fmt - the printf format for printing.
+ *
+ * Note: __ftrace_printk is an internal function for ftrace_printk and
+ *       the @ip is passed in via the ftrace_printk macro.
+ *
+ * This function allows a kernel developer to debug fast path sections
+ * that printk is not appropriate for. By scattering in various
+ * printk like tracing in the code, a developer can quickly see
+ * where problems are occurring.
+ *
+ * This is intended as a debugging tool for the developer only.
+ * Please reframe from leaving ftrace_printks scattered around in
+ * your code.
+ */
+int __ftrace_printk(unsigned long ip, const char *fmt, ...)
+{
+	struct trace_array *tr = &global_trace;
+	static DEFINE_SPINLOCK(trace_buf_lock);
+	static char trace_buf[TRACE_BUF_SIZE];
+	struct trace_array_cpu *data;
+	struct trace_entry *entry;
+	unsigned long flags;
+	long disabled;
+	va_list ap;
+	int cpu, len = 0, write, written = 0;
+
+	if (likely(!ftrace_function_enabled))
+		return 0;
+
+	local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+	data = tr->data[cpu];
+	disabled = atomic_inc_return(&data->disabled);
+
+	if (unlikely(disabled != 1 || !ftrace_function_enabled))
+		goto out;
+
+	spin_lock(&trace_buf_lock);
+	va_start(ap, fmt);
+	len = vsnprintf(trace_buf, TRACE_BUF_SIZE, fmt, ap);
+	va_end(ap);
+
+	len = min(len, TRACE_BUF_SIZE-1);
+	trace_buf[len] = 0;
+
+	__raw_spin_lock(&data->lock);
+	entry				= tracing_get_trace_entry(tr, data);
+	tracing_generic_entry_update(entry, flags);
+	entry->type			= TRACE_PRINT;
+	entry->field.print.ip		= ip;
+
+	write = min(len, (int)(TRACE_PRINT_BUF_SIZE-1));
+
+	memcpy(&entry->field.print.buf, trace_buf, write);
+	entry->field.print.buf[write] = 0;
+	written = write;
+
+	if (written != len)
+		entry->field.flags |= TRACE_FLAG_CONT;
+
+	while (written != len) {
+		entry = tracing_get_trace_entry(tr, data);
+
+		entry->type = TRACE_CONT;
+		write = min(len - written, (int)(TRACE_CONT_BUF_SIZE-1));
+		memcpy(&entry->cont.buf, trace_buf+written, write);
+		entry->cont.buf[write] = 0;
+		written += write;
+	}
+	__raw_spin_unlock(&data->lock);
+
+	spin_unlock(&trace_buf_lock);
+
+ out:
+	atomic_dec(&data->disabled);
+	local_irq_restore(flags);
+
+	return len;
+}
+EXPORT_SYMBOL_GPL(__ftrace_printk);
+
 static int trace_alloc_page(void)
 {
 	struct trace_array_cpu *data;
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 6ddd6a6556cf..50b6d7a6f01a 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -13,7 +13,9 @@ enum trace_type {
 	TRACE_FN,
 	TRACE_CTX,
 	TRACE_WAKE,
+	TRACE_CONT,
 	TRACE_STACK,
+	TRACE_PRINT,
 	TRACE_SPECIAL,
 	TRACE_MMIO_RW,
 	TRACE_MMIO_MAP,
@@ -60,6 +62,14 @@ struct stack_entry {
 	unsigned long		caller[FTRACE_STACK_ENTRIES];
 };
 
+/*
+ * ftrace_printk entry:
+ */
+struct print_entry {
+	unsigned long		ip;
+	char			buf[];
+};
+
 /*
  * The trace field - the most basic unit of tracing. This is what
  * is printed in the end as a single line in the trace output, such as:
@@ -77,6 +87,7 @@ struct trace_field {
 		struct ctx_switch_entry		ctx;
 		struct special_entry		special;
 		struct stack_entry		stack;
+		struct print_entry		print;
 		struct mmiotrace_rw		mmiorw;
 		struct mmiotrace_map		mmiomap;
 	};
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 0911b7e073bf..630715bbd572 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -9,7 +9,9 @@ static inline int trace_valid_entry(struct trace_entry *entry)
 	case TRACE_FN:
 	case TRACE_CTX:
 	case TRACE_WAKE:
+	case TRACE_CONT:
 	case TRACE_STACK:
+	case TRACE_PRINT:
 	case TRACE_SPECIAL:
 		return 1;
 	}
@@ -120,11 +122,11 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 					   struct trace_array *tr,
 					   int (*func)(void))
 {
-	unsigned long count;
-	int ret;
 	int save_ftrace_enabled = ftrace_enabled;
 	int save_tracer_enabled = tracer_enabled;
+	unsigned long count;
 	char *func_name;
+	int ret;
 
 	/* The ftrace test PASSED */
 	printk(KERN_CONT "PASSED\n");
@@ -157,6 +159,7 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 	/* enable tracing */
 	tr->ctrl = 1;
 	trace->init(tr);
+
 	/* Sleep for a 1/10 of a second */
 	msleep(100);
 
@@ -212,10 +215,10 @@ int trace_selftest_startup_dynamic_tracing(struct tracer *trace,
 int
 trace_selftest_startup_function(struct tracer *trace, struct trace_array *tr)
 {
-	unsigned long count;
-	int ret;
 	int save_ftrace_enabled = ftrace_enabled;
 	int save_tracer_enabled = tracer_enabled;
+	unsigned long count;
+	int ret;
 
 	/* make sure msleep has been recorded */
 	msleep(1);
-- 
cgit v1.2.3


From 2f2c99dba2398ef7d9c21f7c793180a50e68b1f0 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Fri, 1 Aug 2008 16:45:49 -0400
Subject: ftrace: ftrace_printk doc moved

Based on Randy Dunlap's suggestion, the ftrace_printk kernel-doc belongs
with the ftrace_printk macro that should be used. Not with the
__ftrace_printk internal function.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Acked-by: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h | 19 ++++++++++++++++++-
 kernel/trace/trace.c   | 16 ----------------
 2 files changed, 18 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index f53b975e32fa..018af16bce5c 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -157,7 +157,24 @@ static inline void __ftrace_enabled_restore(int enabled)
 #ifdef CONFIG_TRACING
 extern void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
-# define ftrace_printk(x...) __ftrace_printk(_THIS_IP_, x)
+
+/**
+ * ftrace_printk - printf formatting in the ftrace buffer
+ * @fmt: the printf format for printing
+ *
+ * Note: __ftrace_printk is an internal function for ftrace_printk and
+ *       the @ip is passed in via the ftrace_printk macro.
+ *
+ * This function allows a kernel developer to debug fast path sections
+ * that printk is not appropriate for. By scattering in various
+ * printk like tracing in the code, a developer can quickly see
+ * where problems are occurring.
+ *
+ * This is intended as a debugging tool for the developer only.
+ * Please refrain from leaving ftrace_printks scattered around in
+ * your code.
+ */
+# define ftrace_printk(fmt...) __ftrace_printk(_THIS_IP_, fmt)
 extern int
 __ftrace_printk(unsigned long ip, const char *fmt, ...)
 	__attribute__ ((format (printf, 2, 3)));
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a917bea82715..2597e7e49c35 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -3075,22 +3075,6 @@ static __init void tracer_init_debugfs(void)
 	(sizeof(struct trace_field) - offsetof(struct trace_field, print.buf))
 #define TRACE_CONT_BUF_SIZE sizeof(struct trace_field)
 
-/**
- * ftrace_printk - printf formatting in the ftrace buffer
- * @fmt - the printf format for printing.
- *
- * Note: __ftrace_printk is an internal function for ftrace_printk and
- *       the @ip is passed in via the ftrace_printk macro.
- *
- * This function allows a kernel developer to debug fast path sections
- * that printk is not appropriate for. By scattering in various
- * printk like tracing in the code, a developer can quickly see
- * where problems are occurring.
- *
- * This is intended as a debugging tool for the developer only.
- * Please reframe from leaving ftrace_printks scattered around in
- * your code.
- */
 int __ftrace_printk(unsigned long ip, const char *fmt, ...)
 {
 	struct trace_array *tr = &global_trace;
-- 
cgit v1.2.3


From 3f5a54e371ca20b119b73704f6c01b71295c1714 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 30 Jul 2008 22:36:46 -0400
Subject: ftrace: dump out ftrace buffers to console on panic

At OLS I had a lot of interest to be able to have the ftrace buffers
dumped on panic.  Usually one would expect to uses kexec and examine
the buffers after a new kernel is loaded. But sometimes the resources
do not permit kdump and kexec, so having an option to still see the
sequence of events up to the crash is very advantageous.

This patch adds the option to have the ftrace buffers dumped to the
console in the latency_trace format on a panic. When the option is set,
the default entries per CPU buffer are lowered to 16384, since the writing
to the serial (if that is the console) may take an awful long time
otherwise.

[
 Changes since -v1:
  Got alpine to send correctly (as well as spell check working).
  Removed config option.
  Moved the static variables into ftrace_dump itself.
  Gave printk a log level.
]

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h |   2 +
 kernel/trace/trace.c   | 175 ++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 176 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 018af16bce5c..f7fb92045bf0 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -178,6 +178,7 @@ ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3);
 extern int
 __ftrace_printk(unsigned long ip, const char *fmt, ...)
 	__attribute__ ((format (printf, 2, 3)));
+extern void ftrace_dump(void);
 #else
 static inline void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
@@ -186,6 +187,7 @@ ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)))
 {
 	return 0;
 }
+static inline void ftrace_dump(void) { }
 #endif
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 2597e7e49c35..97513c8ecd67 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -14,6 +14,7 @@
 #include <linux/utsrelease.h>
 #include <linux/kallsyms.h>
 #include <linux/seq_file.h>
+#include <linux/notifier.h>
 #include <linux/debugfs.h>
 #include <linux/pagemap.h>
 #include <linux/hardirq.h>
@@ -22,6 +23,7 @@
 #include <linux/ftrace.h>
 #include <linux/module.h>
 #include <linux/percpu.h>
+#include <linux/kdebug.h>
 #include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/poll.h>
@@ -103,8 +105,15 @@ int				ftrace_function_enabled;
  * trace_nr_entries is the number of entries that is allocated
  * for a buffer. Note, the number of entries is always rounded
  * to ENTRIES_PER_PAGE.
+ *
+ * This number is purposely set to a low number of 16384.
+ * If the dump on oops happens, it will be much appreciated
+ * to not have to wait for all that output. Anyway this can be
+ * boot time and run time configurable.
  */
-static unsigned long		trace_nr_entries = 65536UL;
+#define TRACE_ENTRIES_DEFAULT	16384UL
+
+static unsigned long		trace_nr_entries = TRACE_ENTRIES_DEFAULT;
 
 /* trace_types holds a link list of available tracers. */
 static struct tracer		*trace_types __read_mostly;
@@ -3142,6 +3151,165 @@ int __ftrace_printk(unsigned long ip, const char *fmt, ...)
 }
 EXPORT_SYMBOL_GPL(__ftrace_printk);
 
+static int trace_panic_handler(struct notifier_block *this,
+			       unsigned long event, void *unused)
+{
+	ftrace_dump();
+	return NOTIFY_OK;
+}
+
+static struct notifier_block trace_panic_notifier = {
+	.notifier_call  = trace_panic_handler,
+	.next           = NULL,
+	.priority       = 150   /* priority: INT_MAX >= x >= 0 */
+};
+
+static int trace_die_handler(struct notifier_block *self,
+			     unsigned long val,
+			     void *data)
+{
+	switch (val) {
+	case DIE_OOPS:
+		ftrace_dump();
+		break;
+	default:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block trace_die_notifier = {
+	.notifier_call = trace_die_handler,
+	.priority = 200
+};
+
+/*
+ * printk is set to max of 1024, we really don't need it that big.
+ * Nothing should be printing 1000 characters anyway.
+ */
+#define TRACE_MAX_PRINT		1000
+
+/*
+ * Define here KERN_TRACE so that we have one place to modify
+ * it if we decide to change what log level the ftrace dump
+ * should be at.
+ */
+#define KERN_TRACE		KERN_INFO
+
+static void
+trace_printk_seq(struct trace_seq *s)
+{
+	/* Probably should print a warning here. */
+	if (s->len >= 1000)
+		s->len = 1000;
+
+	/* should be zero ended, but we are paranoid. */
+	s->buffer[s->len] = 0;
+
+	printk(KERN_TRACE "%s", s->buffer);
+
+	trace_seq_reset(s);
+}
+
+
+void ftrace_dump(void)
+{
+	static DEFINE_SPINLOCK(ftrace_dump_lock);
+	/* use static because iter can be a bit big for the stack */
+	static struct trace_iterator iter;
+	struct trace_array_cpu *data;
+	static cpumask_t mask;
+	static int dump_ran;
+	unsigned long flags;
+	int cnt = 0;
+	int cpu;
+
+	/* only one dump */
+	spin_lock_irqsave(&ftrace_dump_lock, flags);
+	if (dump_ran)
+		goto out;
+
+	dump_ran = 1;
+
+	/* No turning back! */
+	ftrace_kill_atomic();
+
+	printk(KERN_TRACE "Dumping ftrace buffer:\n");
+
+	iter.tr = &global_trace;
+	iter.trace = current_trace;
+
+	/*
+	 * We need to stop all tracing on all CPUS to read the
+	 * the next buffer. This is a bit expensive, but is
+	 * not done often. We fill all what we can read,
+	 * and then release the locks again.
+	 */
+
+	cpus_clear(mask);
+
+	for_each_tracing_cpu(cpu) {
+		data = iter.tr->data[cpu];
+
+		if (!head_page(data) || !data->trace_idx)
+			continue;
+
+		atomic_inc(&data->disabled);
+		cpu_set(cpu, mask);
+	}
+
+	for_each_cpu_mask(cpu, mask) {
+		data = iter.tr->data[cpu];
+		__raw_spin_lock(&data->lock);
+
+		if (data->overrun > iter.last_overrun[cpu])
+			iter.overrun[cpu] +=
+				data->overrun - iter.last_overrun[cpu];
+		iter.last_overrun[cpu] = data->overrun;
+	}
+
+	while (!trace_empty(&iter)) {
+
+		if (!cnt)
+			printk(KERN_TRACE "---------------------------------\n");
+
+		cnt++;
+
+		/* reset all but tr, trace, and overruns */
+		memset(&iter.seq, 0,
+		       sizeof(struct trace_iterator) -
+		       offsetof(struct trace_iterator, seq));
+		iter.iter_flags |= TRACE_FILE_LAT_FMT;
+		iter.pos = -1;
+
+		if (find_next_entry_inc(&iter) != NULL) {
+			print_trace_line(&iter);
+			trace_consume(&iter);
+		}
+
+		trace_printk_seq(&iter.seq);
+	}
+
+	if (!cnt)
+		printk(KERN_TRACE "   (ftrace buffer empty)\n");
+	else
+		printk(KERN_TRACE "---------------------------------\n");
+
+	for_each_cpu_mask(cpu, mask) {
+		data = iter.tr->data[cpu];
+		__raw_spin_unlock(&data->lock);
+	}
+
+	for_each_cpu_mask(cpu, mask) {
+		data = iter.tr->data[cpu];
+		atomic_dec(&data->disabled);
+	}
+
+
+ out:
+	spin_unlock_irqrestore(&ftrace_dump_lock, flags);
+}
+
 static int trace_alloc_page(void)
 {
 	struct trace_array_cpu *data;
@@ -3338,6 +3506,11 @@ __init static int tracer_alloc_buffers(void)
 	global_trace.ctrl = tracer_enabled;
 	tracing_disabled = 0;
 
+	atomic_notifier_chain_register(&panic_notifier_list,
+				       &trace_panic_notifier);
+
+	register_die_notifier(&trace_die_notifier);
+
 	return 0;
 
  free_buffers:
-- 
cgit v1.2.3


From 7b928c23fa3e9fa37d1d4ba52ba963f41ee5aae0 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 15 Aug 2008 17:48:02 +0200
Subject: ftrace: build fix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

fix:

 In file included from init/main.c:65:
 include/linux/ftrace.h:166: error: expected ‘,' or ‘;' before ‘{' token
 make[1]: *** [init/main.o] Error 1
 make: *** [init/main.o] Error 2

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index f7fb92045bf0..ce929cb55435 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -183,7 +183,10 @@ extern void ftrace_dump(void);
 static inline void
 ftrace_special(unsigned long arg1, unsigned long arg2, unsigned long arg3) { }
 static inline int
-ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)))
+ftrace_printk(const char *fmt, ...) __attribute__ ((format (printf, 1, 0)));
+
+static inline int
+ftrace_printk(const char *fmt, ...)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From c5131ad6c3cbe8f6674993e29a76cecf8deb4384 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Fri, 15 Aug 2008 18:22:09 +0200
Subject: ftrace: ftrace_kill_atomic() build fix

fix:

 kernel/built-in.o: In function `ftrace_dump':
 (.text+0x2e2ea): undefined reference to `ftrace_kill_atomic'

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ce929cb55435..36c439927ff1 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -36,6 +36,7 @@ extern void ftrace_stub(unsigned long a0, unsigned long a1);
 # define register_ftrace_function(ops) do { } while (0)
 # define unregister_ftrace_function(ops) do { } while (0)
 # define clear_ftrace_function(ops) do { } while (0)
+static inline void ftrace_kill_atomic(void) { }
 #endif /* CONFIG_FTRACE */
 
 #ifdef CONFIG_DYNAMIC_FTRACE
-- 
cgit v1.2.3


From 3700273586ee6a58b95dd07d9f8a02db4a9b476f Mon Sep 17 00:00:00 2001
From: Huang Ying <ying.huang@intel.com>
Date: Mon, 18 Aug 2008 16:24:56 +0800
Subject: ftrace: fix incorrect comment style of __ftrace_enabled_save()

This patch fixes incorrect comment style of __ftrace_enabled_save().

Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 36c439927ff1..8b4cf38c80d2 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -99,9 +99,11 @@ static inline void tracer_disable(void)
 #endif
 }
 
-/* Ftrace disable/restore without lock. Some synchronization mechanism
+/*
+ * Ftrace disable/restore without lock. Some synchronization mechanism
  * must be used to prevent ftrace_enabled to be changed between
- * disable/restore. */
+ * disable/restore.
+ */
 static inline int __ftrace_enabled_save(void)
 {
 #ifdef CONFIG_FTRACE
-- 
cgit v1.2.3


From c0719e5a4b1ccc04180b7a7b71095c9fb7131919 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Sat, 6 Sep 2008 01:06:03 -0400
Subject: ftrace: use ftrace_release for all dynamic ftrace functions

ftrace_release is necessary for all uses of dynamic ftrace and not just
the archs that have CONFIG_FTRACE_MCOUNT_RECORD defined.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 8b4cf38c80d2..5de9903645d5 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -77,8 +77,10 @@ extern void mcount_call(void);
 
 extern int skip_trace(unsigned long ip);
 
-void ftrace_disable_daemon(void);
-void ftrace_enable_daemon(void);
+extern void ftrace_release(void *start, unsigned long size);
+
+extern void ftrace_disable_daemon(void);
+extern void ftrace_enable_daemon(void);
 
 #else
 # define skip_trace(ip)				({ 0; })
@@ -86,6 +88,7 @@ void ftrace_enable_daemon(void);
 # define ftrace_set_filter(buf, len, reset)	do { } while (0)
 # define ftrace_disable_daemon()		do { } while (0)
 # define ftrace_enable_daemon()			do { } while (0)
+static inline void ftrace_release(void *start, unsigned long size) { }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /* totally disable ftrace - can not re-enable after this */
@@ -199,12 +202,10 @@ static inline void ftrace_dump(void) { }
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
 extern void ftrace_init_module(unsigned long *start, unsigned long *end);
-extern void ftrace_release(void *start, unsigned long size);
 #else
 static inline void ftrace_init(void) { }
 static inline void
 ftrace_init_module(unsigned long *start, unsigned long *end) { }
-static inline void ftrace_release(void *start, unsigned long size) { }
 #endif
 
 
-- 
cgit v1.2.3


From 9e57fb35d711331a9b1410c5c56ebeb3733428a0 Mon Sep 17 00:00:00 2001
From: Pekka Paalanen <pq@iki.fi>
Date: Tue, 16 Sep 2008 22:00:34 +0300
Subject: x86 mmiotrace: implement mmiotrace_printk()

Offer mmiotrace users a function to inject markers from inside the kernel.
This depends on the trace_vprintk() patch.

Signed-off-by: Pekka Paalanen <pq@iki.fi>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/mmio-mod.c         | 19 ++++++++++++++++++-
 arch/x86/mm/testmmiotrace.c    |  4 ++++
 include/linux/mmiotrace.h      | 17 +++++++++++++++--
 kernel/trace/trace_mmiotrace.c |  5 +++++
 4 files changed, 42 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 754bd1eaf4f6..5e2e2e72ee80 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -75,7 +75,7 @@ static LIST_HEAD(trace_list);		/* struct remap_trace */
  *   and trace_lock.
  * - Routines depending on is_enabled() must take trace_lock.
  * - trace_list users must hold trace_lock.
- * - is_enabled() guarantees that mmio_trace_record is allowed.
+ * - is_enabled() guarantees that mmio_trace_{rw,mapping} are allowed.
  * - pre/post callbacks assume the effect of is_enabled() being true.
  */
 
@@ -379,6 +379,23 @@ void mmiotrace_iounmap(volatile void __iomem *addr)
 		iounmap_trace_core(addr);
 }
 
+int mmiotrace_printk(const char *fmt, ...)
+{
+	int ret = 0;
+	va_list args;
+	unsigned long flags;
+	va_start(args, fmt);
+
+	spin_lock_irqsave(&trace_lock, flags);
+	if (is_enabled())
+		ret = mmio_trace_printk(fmt, args);
+	spin_unlock_irqrestore(&trace_lock, flags);
+
+	va_end(args);
+	return ret;
+}
+EXPORT_SYMBOL(mmiotrace_printk);
+
 static void clear_trace_list(void)
 {
 	struct remap_trace *trace;
diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
index d877c5b423ef..ab50a8d7402c 100644
--- a/arch/x86/mm/testmmiotrace.c
+++ b/arch/x86/mm/testmmiotrace.c
@@ -3,6 +3,7 @@
  */
 #include <linux/module.h>
 #include <linux/io.h>
+#include <linux/mmiotrace.h>
 
 #define MODULE_NAME "testmmiotrace"
 
@@ -13,6 +14,7 @@ MODULE_PARM_DESC(mmio_address, "Start address of the mapping of 16 kB.");
 static void do_write_test(void __iomem *p)
 {
 	unsigned int i;
+	mmiotrace_printk("Write test.\n");
 	for (i = 0; i < 256; i++)
 		iowrite8(i, p + i);
 	for (i = 1024; i < (5 * 1024); i += 2)
@@ -24,6 +26,7 @@ static void do_write_test(void __iomem *p)
 static void do_read_test(void __iomem *p)
 {
 	unsigned int i;
+	mmiotrace_printk("Read test.\n");
 	for (i = 0; i < 256; i++)
 		ioread8(p + i);
 	for (i = 1024; i < (5 * 1024); i += 2)
@@ -39,6 +42,7 @@ static void do_test(void)
 		pr_err(MODULE_NAME ": could not ioremap, aborting.\n");
 		return;
 	}
+	mmiotrace_printk("ioremap returned %p.\n", p);
 	do_write_test(p);
 	do_read_test(p);
 	iounmap(p);
diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h
index 61d19e1b7a0b..60cc3bf5c538 100644
--- a/include/linux/mmiotrace.h
+++ b/include/linux/mmiotrace.h
@@ -34,11 +34,15 @@ extern void unregister_kmmio_probe(struct kmmio_probe *p);
 /* Called from page fault handler. */
 extern int kmmio_handler(struct pt_regs *regs, unsigned long addr);
 
-/* Called from ioremap.c */
 #ifdef CONFIG_MMIOTRACE
+/* Called from ioremap.c */
 extern void mmiotrace_ioremap(resource_size_t offset, unsigned long size,
 							void __iomem *addr);
 extern void mmiotrace_iounmap(volatile void __iomem *addr);
+
+/* For anyone to insert markers. Remember trailing newline. */
+extern int mmiotrace_printk(const char *fmt, ...)
+				__attribute__ ((format (printf, 1, 2)));
 #else
 static inline void mmiotrace_ioremap(resource_size_t offset,
 					unsigned long size, void __iomem *addr)
@@ -48,7 +52,15 @@ static inline void mmiotrace_ioremap(resource_size_t offset,
 static inline void mmiotrace_iounmap(volatile void __iomem *addr)
 {
 }
-#endif /* CONFIG_MMIOTRACE_HOOKS */
+
+static inline int mmiotrace_printk(const char *fmt, ...)
+				__attribute__ ((format (printf, 1, 0)));
+
+static inline int mmiotrace_printk(const char *fmt, ...)
+{
+	return 0;
+}
+#endif /* CONFIG_MMIOTRACE */
 
 enum mm_io_opcode {
 	MMIO_READ = 0x1,     /* struct mmiotrace_rw */
@@ -81,5 +93,6 @@ extern void enable_mmiotrace(void);
 extern void disable_mmiotrace(void);
 extern void mmio_trace_rw(struct mmiotrace_rw *rw);
 extern void mmio_trace_mapping(struct mmiotrace_map *map);
+extern int mmio_trace_printk(const char *fmt, va_list args);
 
 #endif /* MMIOTRACE_H */
diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c
index ef02747b26d9..767d1faf56e5 100644
--- a/kernel/trace/trace_mmiotrace.c
+++ b/kernel/trace/trace_mmiotrace.c
@@ -335,3 +335,8 @@ void mmio_trace_mapping(struct mmiotrace_map *map)
 	__trace_mmiotrace_map(tr, data, map);
 	preempt_enable();
 }
+
+int mmio_trace_printk(const char *fmt, va_list args)
+{
+	return trace_vprintk(0, fmt, args);
+}
-- 
cgit v1.2.3


From 4427414170a63331a9cc36b9598502c5cdfe453b Mon Sep 17 00:00:00 2001
From: Pekka Paalanen <pq@iki.fi>
Date: Tue, 16 Sep 2008 22:03:56 +0300
Subject: mmiotrace: remove left-over marker cruft

Signed-off-by: Pekka Paalanen <pq@iki.fi>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/mm/mmio-mod.c    | 64 -----------------------------------------------
 include/linux/mmiotrace.h |  3 +--
 2 files changed, 1 insertion(+), 66 deletions(-)

(limited to 'include')

diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 5e2e2e72ee80..2c4baa88f2cb 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -56,13 +56,6 @@ struct remap_trace {
 static DEFINE_PER_CPU(struct trap_reason, pf_reason);
 static DEFINE_PER_CPU(struct mmiotrace_rw, cpu_trace);
 
-#if 0 /* XXX: no way gather this info anymore */
-/* Access to this is not per-cpu. */
-static DEFINE_PER_CPU(atomic_t, dropped);
-#endif
-
-static struct dentry *marker_file;
-
 static DEFINE_MUTEX(mmiotrace_mutex);
 static DEFINE_SPINLOCK(trace_lock);
 static atomic_t mmiotrace_enabled;
@@ -97,44 +90,6 @@ static bool is_enabled(void)
 	return atomic_read(&mmiotrace_enabled);
 }
 
-#if 0 /* XXX: needs rewrite */
-/*
- * Write callback for the debugfs entry:
- * Read a marker and write it to the mmio trace log
- */
-static ssize_t write_marker(struct file *file, const char __user *buffer,
-						size_t count, loff_t *ppos)
-{
-	char *event = NULL;
-	struct mm_io_header *headp;
-	ssize_t len = (count > 65535) ? 65535 : count;
-
-	event = kzalloc(sizeof(*headp) + len, GFP_KERNEL);
-	if (!event)
-		return -ENOMEM;
-
-	headp = (struct mm_io_header *)event;
-	headp->type = MMIO_MAGIC | (MMIO_MARKER << MMIO_OPCODE_SHIFT);
-	headp->data_len = len;
-
-	if (copy_from_user(event + sizeof(*headp), buffer, len)) {
-		kfree(event);
-		return -EFAULT;
-	}
-
-	spin_lock_irq(&trace_lock);
-#if 0 /* XXX: convert this to use tracing */
-	if (is_enabled())
-		relay_write(chan, event, sizeof(*headp) + len);
-	else
-#endif
-		len = -EINVAL;
-	spin_unlock_irq(&trace_lock);
-	kfree(event);
-	return len;
-}
-#endif
-
 static void print_pte(unsigned long address)
 {
 	unsigned int level;
@@ -481,26 +436,12 @@ static void leave_uniprocessor(void)
 }
 #endif
 
-#if 0 /* XXX: out of order */
-static struct file_operations fops_marker = {
-	.owner =	THIS_MODULE,
-	.write =	write_marker
-};
-#endif
-
 void enable_mmiotrace(void)
 {
 	mutex_lock(&mmiotrace_mutex);
 	if (is_enabled())
 		goto out;
 
-#if 0 /* XXX: tracing does not support text entries */
-	marker_file = debugfs_create_file("marker", 0660, dir, NULL,
-								&fops_marker);
-	if (!marker_file)
-		pr_err(NAME "marker file creation failed.\n");
-#endif
-
 	if (nommiotrace)
 		pr_info(NAME "MMIO tracing disabled.\n");
 	enter_uniprocessor();
@@ -525,11 +466,6 @@ void disable_mmiotrace(void)
 
 	clear_trace_list(); /* guarantees: no more kmmio callbacks */
 	leave_uniprocessor();
-	if (marker_file) {
-		debugfs_remove(marker_file);
-		marker_file = NULL;
-	}
-
 	pr_info(NAME "disabled.\n");
 out:
 	mutex_unlock(&mmiotrace_mutex);
diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h
index 60cc3bf5c538..139d7c88d9c9 100644
--- a/include/linux/mmiotrace.h
+++ b/include/linux/mmiotrace.h
@@ -67,8 +67,7 @@ enum mm_io_opcode {
 	MMIO_WRITE = 0x2,    /* struct mmiotrace_rw */
 	MMIO_PROBE = 0x3,    /* struct mmiotrace_map */
 	MMIO_UNPROBE = 0x4,  /* struct mmiotrace_map */
-	MMIO_MARKER = 0x5,   /* raw char data */
-	MMIO_UNKNOWN_OP = 0x6, /* struct mmiotrace_rw */
+	MMIO_UNKNOWN_OP = 0x5, /* struct mmiotrace_rw */
 };
 
 struct mmiotrace_rw {
-- 
cgit v1.2.3


From e98d0eabef2748d88fa58760d104e8e68517406b Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Date: Mon, 29 Sep 2008 11:05:13 -0400
Subject: markers: marker_synchronize_unregister()

Create marker_synchronize_unregister() which must be called before the end of
exit() to make sure every probe callers have exited the non preemptible section
and thus are not executing the probe code anymore.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/marker.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/marker.h b/include/linux/marker.h
index 1290653f9241..889196c7fbb1 100644
--- a/include/linux/marker.h
+++ b/include/linux/marker.h
@@ -160,4 +160,11 @@ extern int marker_probe_unregister_private_data(marker_probe_func *probe,
 extern void *marker_get_private_data(const char *name, marker_probe_func *probe,
 	int num);
 
+/*
+ * marker_synchronize_unregister must be called between the last marker probe
+ * unregistration and the end of module exit to make sure there is no caller
+ * executing a probe when it is freed.
+ */
+#define marker_synchronize_unregister() synchronize_sched()
+
 #endif
-- 
cgit v1.2.3


From 53c8c8fdfd2d2d515bdcb3d0f2a11d1f3f42ece1 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Date: Fri, 3 Oct 2008 11:52:54 -0400
Subject: markers: turn marker_synchronize_unregister() into an inline

Turn marker synchronize unregister into a static inline. There is no
reason to keep it as a macro over a static inline.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/marker.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/marker.h b/include/linux/marker.h
index 889196c7fbb1..38e32e781ed7 100644
--- a/include/linux/marker.h
+++ b/include/linux/marker.h
@@ -13,6 +13,7 @@
  */
 
 #include <linux/types.h>
+#include <linux/rcupdate.h>
 
 struct module;
 struct marker;
@@ -165,6 +166,9 @@ extern void *marker_get_private_data(const char *name, marker_probe_func *probe,
  * unregistration and the end of module exit to make sure there is no caller
  * executing a probe when it is freed.
  */
-#define marker_synchronize_unregister() synchronize_sched()
+static inline void marker_synchronize_unregister(void)
+{
+	synchronize_sched();
+}
 
 #endif
-- 
cgit v1.2.3


From d13744cd6e3fef373a3fe656ac349b4e7c49ff79 Mon Sep 17 00:00:00 2001
From: Frédéric Weisbecker <fweisbec@gmail.com>
Date: Tue, 23 Sep 2008 11:32:08 +0100
Subject: tracing/ftrace: add the boot tracer

Add the boot/initcall tracer.

It's primary purpose is to be able to trace the initcalls.

It is intended to be used with scripts/bootgraph.pl after some small
improvements.

Note that it is not active after its init. To avoid tracing (and so
crashing) before the whole tracing engine init, you have to explicitly
call start_boot_trace() after do_pre_smp_initcalls() to enable it.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h    |  19 +++++++++
 kernel/trace/trace.h      |   4 ++
 kernel/trace/trace_boot.c | 101 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 124 insertions(+)
 create mode 100644 kernel/trace/trace_boot.c

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 5de9903645d5..91954eb6460f 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -5,6 +5,8 @@
 
 #include <linux/linkage.h>
 #include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/types.h>
 
 extern int ftrace_enabled;
 extern int
@@ -209,4 +211,21 @@ ftrace_init_module(unsigned long *start, unsigned long *end) { }
 #endif
 
 
+struct boot_trace {
+	pid_t			caller;
+	initcall_t		func;
+	int			result;
+	unsigned long long	duration;
+};
+
+#ifdef CONFIG_BOOT_TRACER
+extern void trace_boot(struct boot_trace *it);
+extern void start_boot_trace(void);
+#else
+static inline void trace_boot(struct boot_trace *it) { }
+static inline void start_boot_trace(void) { }
+#endif
+
+
+
 #endif /* _LINUX_FTRACE_H */
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index cb2c3fb7dd54..b28bf8812efc 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -6,6 +6,7 @@
 #include <linux/sched.h>
 #include <linux/clocksource.h>
 #include <linux/mmiotrace.h>
+#include <linux/ftrace.h>
 
 enum trace_type {
 	__TRACE_FIRST_TYPE = 0,
@@ -19,6 +20,7 @@ enum trace_type {
 	TRACE_SPECIAL,
 	TRACE_MMIO_RW,
 	TRACE_MMIO_MAP,
+	TRACE_BOOT,
 
 	__TRACE_LAST_TYPE
 };
@@ -30,6 +32,7 @@ struct ftrace_entry {
 	unsigned long		ip;
 	unsigned long		parent_ip;
 };
+extern struct tracer boot_tracer;
 
 /*
  * Context switch trace entry - which task (and prio) we switched from/to:
@@ -108,6 +111,7 @@ struct trace_field {
 		struct print_entry		print;
 		struct mmiotrace_rw		mmiorw;
 		struct mmiotrace_map		mmiomap;
+		struct boot_trace		initcall;
 	};
 };
 
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
new file mode 100644
index 000000000000..c65ef8ffd6b4
--- /dev/null
+++ b/kernel/trace/trace_boot.c
@@ -0,0 +1,101 @@
+/*
+ * ring buffer based initcalls tracer
+ *
+ * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+
+#include "trace.h"
+
+static struct trace_array *boot_trace;
+static int trace_boot_enabled;
+
+
+/* Should be started after do_pre_smp_initcalls() in init/main.c */
+void start_boot_trace(void)
+{
+	trace_boot_enabled = 1;
+}
+
+void stop_boot_trace(struct trace_array *tr)
+{
+	trace_boot_enabled = 0;
+}
+
+static void boot_trace_init(struct trace_array *tr)
+{
+	int cpu;
+	boot_trace = tr;
+
+	trace_boot_enabled = 0;
+
+	for_each_cpu_mask(cpu, cpu_possible_map)
+		tracing_reset(tr->data[cpu]);
+}
+
+static void boot_trace_ctrl_update(struct trace_array *tr)
+{
+	if (tr->ctrl)
+		start_boot_trace();
+	else
+		stop_boot_trace(tr);
+}
+
+static int initcall_print_line(struct trace_iterator *iter)
+{
+	int ret = 1;
+	struct trace_entry *entry = iter->ent;
+	struct boot_trace *it = &entry->field.initcall;
+	struct trace_seq *s = &iter->seq;
+
+	if (iter->ent->type == TRACE_BOOT)
+		ret = trace_seq_printf(s, "%pF called from %i "
+				       "returned %d after %lld msecs\n",
+				       it->func, it->caller, it->result,
+				       it->duration);
+	if (ret)
+		return 1;
+	return 0;
+}
+
+struct tracer boot_tracer __read_mostly =
+{
+	.name		= "initcall",
+	.init		= boot_trace_init,
+	.reset		= stop_boot_trace,
+	.ctrl_update	= boot_trace_ctrl_update,
+	.print_line	= initcall_print_line,
+};
+
+
+void trace_boot(struct boot_trace *it)
+{
+	struct trace_entry *entry;
+	struct trace_array_cpu *data;
+	unsigned long irq_flags;
+	struct trace_array *tr = boot_trace;
+
+	if (!trace_boot_enabled)
+		return;
+
+	preempt_disable();
+	data = tr->data[smp_processor_id()];
+
+	raw_local_irq_save(irq_flags);
+	__raw_spin_lock(&data->lock);
+
+	entry = tracing_get_trace_entry(tr, data);
+	tracing_generic_entry_update(entry, 0);
+	entry->type = TRACE_BOOT;
+	entry->field.initcall = *it;
+
+	__raw_spin_unlock(&data->lock);
+	raw_local_irq_restore(irq_flags);
+	trace_wake_up();
+
+	preempt_enable();
+}
-- 
cgit v1.2.3


From 7a8e76a3829f1067b70f715771ff88baf2fbf3c3 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Mon, 29 Sep 2008 23:02:38 -0400
Subject: tracing: unified trace buffer

This is a unified tracing buffer that implements a ring buffer that
hopefully everyone will eventually be able to use.

The events recorded into the buffer have the following structure:

  struct ring_buffer_event {
	u32 type:2, len:3, time_delta:27;
	u32 array[];
  };

The minimum size of an event is 8 bytes. All events are 4 byte
aligned inside the buffer.

There are 4 types (all internal use for the ring buffer, only
the data type is exported to the interface users).

 RINGBUF_TYPE_PADDING: this type is used to note extra space at the end
	of a buffer page.

 RINGBUF_TYPE_TIME_EXTENT: This type is used when the time between events
	is greater than the 27 bit delta can hold. We add another
	32 bits, and record that in its own event (8 byte size).

 RINGBUF_TYPE_TIME_STAMP: (Not implemented yet). This will hold data to
	help keep the buffer timestamps in sync.

RINGBUF_TYPE_DATA: The event actually holds user data.

The "len" field is only three bits. Since the data must be
4 byte aligned, this field is shifted left by 2, giving a
max length of 28 bytes. If the data load is greater than 28
bytes, the first array field holds the full length of the
data load and the len field is set to zero.

Example, data size of 7 bytes:

	type = RINGBUF_TYPE_DATA
	len = 2
	time_delta: <time-stamp> - <prev_event-time-stamp>
	array[0..1]: <7 bytes of data> <1 byte empty>

This event is saved in 12 bytes of the buffer.

An event with 82 bytes of data:

	type = RINGBUF_TYPE_DATA
	len = 0
	time_delta: <time-stamp> - <prev_event-time-stamp>
	array[0]: 84 (Note the alignment)
	array[1..14]: <82 bytes of data> <2 bytes empty>

The above event is saved in 92 bytes (if my math is correct).
82 bytes of data, 2 bytes empty, 4 byte header, 4 byte length.

Do not reference the above event struct directly. Use the following
functions to gain access to the event table, since the
ring_buffer_event structure may change in the future.

ring_buffer_event_length(event): get the length of the event.
	This is the size of the memory used to record this
	event, and not the size of the data pay load.

ring_buffer_time_delta(event): get the time delta of the event
	This returns the delta time stamp since the last event.
	Note: Even though this is in the header, there should
		be no reason to access this directly, accept
		for debugging.

ring_buffer_event_data(event): get the data from the event
	This is the function to use to get the actual data
	from the event. Note, it is only a pointer to the
	data inside the buffer. This data must be copied to
	another location otherwise you risk it being written
	over in the buffer.

ring_buffer_lock: A way to lock the entire buffer.
ring_buffer_unlock: unlock the buffer.

ring_buffer_alloc: create a new ring buffer. Can choose between
	overwrite or consumer/producer mode. Overwrite will
	overwrite old data, where as consumer producer will
	throw away new data if the consumer catches up with the
	producer.  The consumer/producer is the default.

ring_buffer_free: free the ring buffer.

ring_buffer_resize: resize the buffer. Changes the size of each cpu
	buffer. Note, it is up to the caller to provide that
	the buffer is not being used while this is happening.
	This requirement may go away but do not count on it.

ring_buffer_lock_reserve: locks the ring buffer and allocates an
	entry on the buffer to write to.
ring_buffer_unlock_commit: unlocks the ring buffer and commits it to
	the buffer.

ring_buffer_write: writes some data into the ring buffer.

ring_buffer_peek: Look at a next item in the cpu buffer.
ring_buffer_consume: get the next item in the cpu buffer and
	consume it. That is, this function increments the head
	pointer.

ring_buffer_read_start: Start an iterator of a cpu buffer.
	For now, this disables the cpu buffer, until you issue
	a finish. This is just because we do not want the iterator
	to be overwritten. This restriction may change in the future.
	But note, this is used for static reading of a buffer which
	is usually done "after" a trace. Live readings would want
	to use the ring_buffer_consume above, which will not
	disable the ring buffer.

ring_buffer_read_finish: Finishes the read iterator and reenables
	the ring buffer.

ring_buffer_iter_peek: Look at the next item in the cpu iterator.
ring_buffer_read: Read the iterator and increment it.
ring_buffer_iter_reset: Reset the iterator to point to the beginning
	of the cpu buffer.
ring_buffer_iter_empty: Returns true if the iterator is at the end
	of the cpu buffer.

ring_buffer_size: returns the size in bytes of each cpu buffer.
	Note, the real size is this times the number of CPUs.

ring_buffer_reset_cpu: Sets the cpu buffer to empty
ring_buffer_reset: sets all cpu buffers to empty

ring_buffer_swap_cpu: swaps a cpu buffer from one buffer with a
	cpu buffer of another buffer. This is handy when you
	want to take a snap shot of a running trace on just one
	cpu. Having a backup buffer, to swap with facilitates this.
	Ftrace max latencies use this.

ring_buffer_empty: Returns true if the ring buffer is empty.
ring_buffer_empty_cpu: Returns true if the cpu buffer is empty.

ring_buffer_record_disable: disable all cpu buffers (read only)
ring_buffer_record_disable_cpu: disable a single cpu buffer (read only)
ring_buffer_record_enable: enable all cpu buffers.
ring_buffer_record_enabl_cpu: enable a single cpu buffer.

ring_buffer_entries: The number of entries in a ring buffer.
ring_buffer_overruns: The number of entries removed due to writing wrap.

ring_buffer_time_stamp: Get the time stamp used by the ring buffer
ring_buffer_normalize_time_stamp: normalize the ring buffer time stamp
	into nanosecs.

I still need to implement the GTOD feature. But we need support from
the cpu frequency infrastructure.  But this can be done at a later
time without affecting the ring buffer interface.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ring_buffer.h |  130 ++++
 kernel/trace/Kconfig        |    4 +
 kernel/trace/Makefile       |    1 +
 kernel/trace/ring_buffer.c  | 1672 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 1807 insertions(+)
 create mode 100644 include/linux/ring_buffer.h
 create mode 100644 kernel/trace/ring_buffer.c

(limited to 'include')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
new file mode 100644
index 000000000000..c52375b8330d
--- /dev/null
+++ b/include/linux/ring_buffer.h
@@ -0,0 +1,130 @@
+#ifndef _LINUX_RING_BUFFER_H
+#define _LINUX_RING_BUFFER_H
+
+#include <linux/mm.h>
+#include <linux/seq_file.h>
+
+struct ring_buffer;
+struct ring_buffer_iter;
+
+/*
+ * Don't reference this struct directly, use functions below.
+ */
+struct ring_buffer_event {
+	u32		type:2, len:3, time_delta:27;
+	u32		array[];
+};
+
+/**
+ * enum ring_buffer_type - internal ring buffer types
+ *
+ * @RINGBUF_TYPE_PADDING:	Left over page padding
+ *				 array is ignored
+ *				 size is variable depending on how much
+ *				  padding is needed
+ *
+ * @RINGBUF_TYPE_TIME_EXTEND:	Extend the time delta
+ *				 array[0] = time delta (28 .. 59)
+ *				 size = 8 bytes
+ *
+ * @RINGBUF_TYPE_TIME_STAMP:	Sync time stamp with external clock
+ *				 array[0] = tv_nsec
+ *				 array[1] = tv_sec
+ *				 size = 16 bytes
+ *
+ * @RINGBUF_TYPE_DATA:		Data record
+ *				 If len is zero:
+ *				  array[0] holds the actual length
+ *				  array[1..(length+3)/4-1] holds data
+ *				 else
+ *				  length = len << 2
+ *				  array[0..(length+3)/4] holds data
+ */
+enum ring_buffer_type {
+	RINGBUF_TYPE_PADDING,
+	RINGBUF_TYPE_TIME_EXTEND,
+	/* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
+	RINGBUF_TYPE_TIME_STAMP,
+	RINGBUF_TYPE_DATA,
+};
+
+unsigned ring_buffer_event_length(struct ring_buffer_event *event);
+void *ring_buffer_event_data(struct ring_buffer_event *event);
+
+/**
+ * ring_buffer_event_time_delta - return the delta timestamp of the event
+ * @event: the event to get the delta timestamp of
+ *
+ * The delta timestamp is the 27 bit timestamp since the last event.
+ */
+static inline unsigned
+ring_buffer_event_time_delta(struct ring_buffer_event *event)
+{
+	return event->time_delta;
+}
+
+void ring_buffer_lock(struct ring_buffer *buffer, unsigned long *flags);
+void ring_buffer_unlock(struct ring_buffer *buffer, unsigned long flags);
+
+/*
+ * size is in bytes for each per CPU buffer.
+ */
+struct ring_buffer *
+ring_buffer_alloc(unsigned long size, unsigned flags);
+void ring_buffer_free(struct ring_buffer *buffer);
+
+int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
+
+struct ring_buffer_event *
+ring_buffer_lock_reserve(struct ring_buffer *buffer,
+			 unsigned long length,
+			 unsigned long *flags);
+int ring_buffer_unlock_commit(struct ring_buffer *buffer,
+			      struct ring_buffer_event *event,
+			      unsigned long flags);
+int ring_buffer_write(struct ring_buffer *buffer,
+		      unsigned long length, void *data);
+
+struct ring_buffer_event *
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts);
+struct ring_buffer_event *
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts);
+
+struct ring_buffer_iter *
+ring_buffer_read_start(struct ring_buffer *buffer, int cpu);
+void ring_buffer_read_finish(struct ring_buffer_iter *iter);
+
+struct ring_buffer_event *
+ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts);
+struct ring_buffer_event *
+ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts);
+void ring_buffer_iter_reset(struct ring_buffer_iter *iter);
+int ring_buffer_iter_empty(struct ring_buffer_iter *iter);
+
+unsigned long ring_buffer_size(struct ring_buffer *buffer);
+
+void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu);
+void ring_buffer_reset(struct ring_buffer *buffer);
+
+int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
+			 struct ring_buffer *buffer_b, int cpu);
+
+int ring_buffer_empty(struct ring_buffer *buffer);
+int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
+
+void ring_buffer_record_disable(struct ring_buffer *buffer);
+void ring_buffer_record_enable(struct ring_buffer *buffer);
+void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu);
+void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu);
+
+unsigned long ring_buffer_entries(struct ring_buffer *buffer);
+unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
+
+u64 ring_buffer_time_stamp(int cpu);
+void ring_buffer_normalize_time_stamp(int cpu, u64 *ts);
+
+enum ring_buffer_flags {
+	RB_FL_OVERWRITE		= 1 << 0,
+};
+
+#endif /* _LINUX_RING_BUFFER_H */
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 4feb3c81f94d..396aea11398e 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -18,9 +18,13 @@ config HAVE_FTRACE_MCOUNT_RECORD
 config TRACER_MAX_TRACE
 	bool
 
+config RING_BUFFER
+	bool
+
 config TRACING
 	bool
 	select DEBUG_FS
+	select RING_BUFFER
 	select STACKTRACE
 	select TRACEPOINTS
 
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 35a07f7cfa86..a85dfba88ba0 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -11,6 +11,7 @@ obj-y += trace_selftest_dynamic.o
 endif
 
 obj-$(CONFIG_FTRACE) += libftrace.o
+obj-$(CONFIG_RING_BUFFER) += ring_buffer.o
 
 obj-$(CONFIG_TRACING) += trace.o
 obj-$(CONFIG_CONTEXT_SWITCH_TRACER) += trace_sched_switch.o
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
new file mode 100644
index 000000000000..830a2930dd91
--- /dev/null
+++ b/kernel/trace/ring_buffer.c
@@ -0,0 +1,1672 @@
+/*
+ * Generic ring buffer
+ *
+ * Copyright (C) 2008 Steven Rostedt <srostedt@redhat.com>
+ */
+#include <linux/ring_buffer.h>
+#include <linux/spinlock.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>	/* used for sched_clock() (for now) */
+#include <linux/init.h>
+#include <linux/hash.h>
+#include <linux/list.h>
+#include <linux/fs.h>
+
+/* Up this if you want to test the TIME_EXTENTS and normalization */
+#define DEBUG_SHIFT 0
+
+/* FIXME!!! */
+u64 ring_buffer_time_stamp(int cpu)
+{
+	/* shift to debug/test normalization and TIME_EXTENTS */
+	return sched_clock() << DEBUG_SHIFT;
+}
+
+void ring_buffer_normalize_time_stamp(int cpu, u64 *ts)
+{
+	/* Just stupid testing the normalize function and deltas */
+	*ts >>= DEBUG_SHIFT;
+}
+
+#define RB_EVNT_HDR_SIZE (sizeof(struct ring_buffer_event))
+#define RB_ALIGNMENT_SHIFT	2
+#define RB_ALIGNMENT		(1 << RB_ALIGNMENT_SHIFT)
+#define RB_MAX_SMALL_DATA	28
+
+enum {
+	RB_LEN_TIME_EXTEND = 8,
+	RB_LEN_TIME_STAMP = 16,
+};
+
+/* inline for ring buffer fast paths */
+static inline unsigned
+rb_event_length(struct ring_buffer_event *event)
+{
+	unsigned length;
+
+	switch (event->type) {
+	case RINGBUF_TYPE_PADDING:
+		/* undefined */
+		return -1;
+
+	case RINGBUF_TYPE_TIME_EXTEND:
+		return RB_LEN_TIME_EXTEND;
+
+	case RINGBUF_TYPE_TIME_STAMP:
+		return RB_LEN_TIME_STAMP;
+
+	case RINGBUF_TYPE_DATA:
+		if (event->len)
+			length = event->len << RB_ALIGNMENT_SHIFT;
+		else
+			length = event->array[0];
+		return length + RB_EVNT_HDR_SIZE;
+	default:
+		BUG();
+	}
+	/* not hit */
+	return 0;
+}
+
+/**
+ * ring_buffer_event_length - return the length of the event
+ * @event: the event to get the length of
+ */
+unsigned ring_buffer_event_length(struct ring_buffer_event *event)
+{
+	return rb_event_length(event);
+}
+
+/* inline for ring buffer fast paths */
+static inline void *
+rb_event_data(struct ring_buffer_event *event)
+{
+	BUG_ON(event->type != RINGBUF_TYPE_DATA);
+	/* If length is in len field, then array[0] has the data */
+	if (event->len)
+		return (void *)&event->array[0];
+	/* Otherwise length is in array[0] and array[1] has the data */
+	return (void *)&event->array[1];
+}
+
+/**
+ * ring_buffer_event_data - return the data of the event
+ * @event: the event to get the data from
+ */
+void *ring_buffer_event_data(struct ring_buffer_event *event)
+{
+	return rb_event_data(event);
+}
+
+#define for_each_buffer_cpu(buffer, cpu)		\
+	for_each_cpu_mask(cpu, buffer->cpumask)
+
+#define TS_SHIFT	27
+#define TS_MASK		((1ULL << TS_SHIFT) - 1)
+#define TS_DELTA_TEST	(~TS_MASK)
+
+/*
+ * This hack stolen from mm/slob.c.
+ * We can store per page timing information in the page frame of the page.
+ * Thanks to Peter Zijlstra for suggesting this idea.
+ */
+struct buffer_page {
+	union {
+		struct {
+			unsigned long	 flags;		/* mandatory */
+			atomic_t	 _count;	/* mandatory */
+			u64		 time_stamp;	/* page time stamp */
+			unsigned	 size;		/* size of page data */
+			struct list_head list;		/* list of free pages */
+		};
+		struct page page;
+	};
+};
+
+/*
+ * We need to fit the time_stamp delta into 27 bits.
+ */
+static inline int test_time_stamp(u64 delta)
+{
+	if (delta & TS_DELTA_TEST)
+		return 1;
+	return 0;
+}
+
+#define BUF_PAGE_SIZE PAGE_SIZE
+
+/*
+ * head_page == tail_page && head == tail then buffer is empty.
+ */
+struct ring_buffer_per_cpu {
+	int				cpu;
+	struct ring_buffer		*buffer;
+	spinlock_t			lock;
+	struct lock_class_key		lock_key;
+	struct list_head		pages;
+	unsigned long			head;	/* read from head */
+	unsigned long			tail;	/* write to tail */
+	struct buffer_page		*head_page;
+	struct buffer_page		*tail_page;
+	unsigned long			overrun;
+	unsigned long			entries;
+	u64				write_stamp;
+	u64				read_stamp;
+	atomic_t			record_disabled;
+};
+
+struct ring_buffer {
+	unsigned long			size;
+	unsigned			pages;
+	unsigned			flags;
+	int				cpus;
+	cpumask_t			cpumask;
+	atomic_t			record_disabled;
+
+	struct mutex			mutex;
+
+	struct ring_buffer_per_cpu	**buffers;
+};
+
+struct ring_buffer_iter {
+	struct ring_buffer_per_cpu	*cpu_buffer;
+	unsigned long			head;
+	struct buffer_page		*head_page;
+	u64				read_stamp;
+};
+
+#define RB_WARN_ON(buffer, cond)			\
+	if (unlikely(cond)) {				\
+		atomic_inc(&buffer->record_disabled);	\
+		WARN_ON(1);				\
+		return -1;				\
+	}
+
+/**
+ * check_pages - integrity check of buffer pages
+ * @cpu_buffer: CPU buffer with pages to test
+ *
+ * As a safty measure we check to make sure the data pages have not
+ * been corrupted.
+ */
+static int rb_check_pages(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct list_head *head = &cpu_buffer->pages;
+	struct buffer_page *page, *tmp;
+
+	RB_WARN_ON(cpu_buffer, head->next->prev != head);
+	RB_WARN_ON(cpu_buffer, head->prev->next != head);
+
+	list_for_each_entry_safe(page, tmp, head, list) {
+		RB_WARN_ON(cpu_buffer, page->list.next->prev != &page->list);
+		RB_WARN_ON(cpu_buffer, page->list.prev->next != &page->list);
+	}
+
+	return 0;
+}
+
+static unsigned rb_head_size(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	return cpu_buffer->head_page->size;
+}
+
+static int rb_allocate_pages(struct ring_buffer_per_cpu *cpu_buffer,
+			     unsigned nr_pages)
+{
+	struct list_head *head = &cpu_buffer->pages;
+	struct buffer_page *page, *tmp;
+	unsigned long addr;
+	LIST_HEAD(pages);
+	unsigned i;
+
+	for (i = 0; i < nr_pages; i++) {
+		addr = __get_free_page(GFP_KERNEL);
+		if (!addr)
+			goto free_pages;
+		page = (struct buffer_page *)virt_to_page(addr);
+		list_add(&page->list, &pages);
+	}
+
+	list_splice(&pages, head);
+
+	rb_check_pages(cpu_buffer);
+
+	return 0;
+
+ free_pages:
+	list_for_each_entry_safe(page, tmp, &pages, list) {
+		list_del_init(&page->list);
+		__free_page(&page->page);
+	}
+	return -ENOMEM;
+}
+
+static struct ring_buffer_per_cpu *
+rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	int ret;
+
+	cpu_buffer = kzalloc_node(ALIGN(sizeof(*cpu_buffer), cache_line_size()),
+				  GFP_KERNEL, cpu_to_node(cpu));
+	if (!cpu_buffer)
+		return NULL;
+
+	cpu_buffer->cpu = cpu;
+	cpu_buffer->buffer = buffer;
+	spin_lock_init(&cpu_buffer->lock);
+	INIT_LIST_HEAD(&cpu_buffer->pages);
+
+	ret = rb_allocate_pages(cpu_buffer, buffer->pages);
+	if (ret < 0)
+		goto fail_free_buffer;
+
+	cpu_buffer->head_page
+		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+	cpu_buffer->tail_page
+		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+
+	return cpu_buffer;
+
+ fail_free_buffer:
+	kfree(cpu_buffer);
+	return NULL;
+}
+
+static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct list_head *head = &cpu_buffer->pages;
+	struct buffer_page *page, *tmp;
+
+	list_for_each_entry_safe(page, tmp, head, list) {
+		list_del_init(&page->list);
+		__free_page(&page->page);
+	}
+	kfree(cpu_buffer);
+}
+
+/**
+ * ring_buffer_alloc - allocate a new ring_buffer
+ * @size: the size in bytes that is needed.
+ * @flags: attributes to set for the ring buffer.
+ *
+ * Currently the only flag that is available is the RB_FL_OVERWRITE
+ * flag. This flag means that the buffer will overwrite old data
+ * when the buffer wraps. If this flag is not set, the buffer will
+ * drop data when the tail hits the head.
+ */
+struct ring_buffer *ring_buffer_alloc(unsigned long size, unsigned flags)
+{
+	struct ring_buffer *buffer;
+	int bsize;
+	int cpu;
+
+	/* keep it in its own cache line */
+	buffer = kzalloc(ALIGN(sizeof(*buffer), cache_line_size()),
+			 GFP_KERNEL);
+	if (!buffer)
+		return NULL;
+
+	buffer->pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	buffer->flags = flags;
+
+	/* need at least two pages */
+	if (buffer->pages == 1)
+		buffer->pages++;
+
+	buffer->cpumask = cpu_possible_map;
+	buffer->cpus = nr_cpu_ids;
+
+	bsize = sizeof(void *) * nr_cpu_ids;
+	buffer->buffers = kzalloc(ALIGN(bsize, cache_line_size()),
+				  GFP_KERNEL);
+	if (!buffer->buffers)
+		goto fail_free_buffer;
+
+	for_each_buffer_cpu(buffer, cpu) {
+		buffer->buffers[cpu] =
+			rb_allocate_cpu_buffer(buffer, cpu);
+		if (!buffer->buffers[cpu])
+			goto fail_free_buffers;
+	}
+
+	mutex_init(&buffer->mutex);
+
+	return buffer;
+
+ fail_free_buffers:
+	for_each_buffer_cpu(buffer, cpu) {
+		if (buffer->buffers[cpu])
+			rb_free_cpu_buffer(buffer->buffers[cpu]);
+	}
+	kfree(buffer->buffers);
+
+ fail_free_buffer:
+	kfree(buffer);
+	return NULL;
+}
+
+/**
+ * ring_buffer_free - free a ring buffer.
+ * @buffer: the buffer to free.
+ */
+void
+ring_buffer_free(struct ring_buffer *buffer)
+{
+	int cpu;
+
+	for_each_buffer_cpu(buffer, cpu)
+		rb_free_cpu_buffer(buffer->buffers[cpu]);
+
+	kfree(buffer);
+}
+
+static void rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer);
+
+static void
+rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
+{
+	struct buffer_page *page;
+	struct list_head *p;
+	unsigned i;
+
+	atomic_inc(&cpu_buffer->record_disabled);
+	synchronize_sched();
+
+	for (i = 0; i < nr_pages; i++) {
+		BUG_ON(list_empty(&cpu_buffer->pages));
+		p = cpu_buffer->pages.next;
+		page = list_entry(p, struct buffer_page, list);
+		list_del_init(&page->list);
+		__free_page(&page->page);
+	}
+	BUG_ON(list_empty(&cpu_buffer->pages));
+
+	rb_reset_cpu(cpu_buffer);
+
+	rb_check_pages(cpu_buffer);
+
+	atomic_dec(&cpu_buffer->record_disabled);
+
+}
+
+static void
+rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
+		struct list_head *pages, unsigned nr_pages)
+{
+	struct buffer_page *page;
+	struct list_head *p;
+	unsigned i;
+
+	atomic_inc(&cpu_buffer->record_disabled);
+	synchronize_sched();
+
+	for (i = 0; i < nr_pages; i++) {
+		BUG_ON(list_empty(pages));
+		p = pages->next;
+		page = list_entry(p, struct buffer_page, list);
+		list_del_init(&page->list);
+		list_add_tail(&page->list, &cpu_buffer->pages);
+	}
+	rb_reset_cpu(cpu_buffer);
+
+	rb_check_pages(cpu_buffer);
+
+	atomic_dec(&cpu_buffer->record_disabled);
+}
+
+/**
+ * ring_buffer_resize - resize the ring buffer
+ * @buffer: the buffer to resize.
+ * @size: the new size.
+ *
+ * The tracer is responsible for making sure that the buffer is
+ * not being used while changing the size.
+ * Note: We may be able to change the above requirement by using
+ *  RCU synchronizations.
+ *
+ * Minimum size is 2 * BUF_PAGE_SIZE.
+ *
+ * Returns -1 on failure.
+ */
+int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned nr_pages, rm_pages, new_pages;
+	struct buffer_page *page, *tmp;
+	unsigned long buffer_size;
+	unsigned long addr;
+	LIST_HEAD(pages);
+	int i, cpu;
+
+	size = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+	size *= BUF_PAGE_SIZE;
+	buffer_size = buffer->pages * BUF_PAGE_SIZE;
+
+	/* we need a minimum of two pages */
+	if (size < BUF_PAGE_SIZE * 2)
+		size = BUF_PAGE_SIZE * 2;
+
+	if (size == buffer_size)
+		return size;
+
+	mutex_lock(&buffer->mutex);
+
+	nr_pages = DIV_ROUND_UP(size, BUF_PAGE_SIZE);
+
+	if (size < buffer_size) {
+
+		/* easy case, just free pages */
+		BUG_ON(nr_pages >= buffer->pages);
+
+		rm_pages = buffer->pages - nr_pages;
+
+		for_each_buffer_cpu(buffer, cpu) {
+			cpu_buffer = buffer->buffers[cpu];
+			rb_remove_pages(cpu_buffer, rm_pages);
+		}
+		goto out;
+	}
+
+	/*
+	 * This is a bit more difficult. We only want to add pages
+	 * when we can allocate enough for all CPUs. We do this
+	 * by allocating all the pages and storing them on a local
+	 * link list. If we succeed in our allocation, then we
+	 * add these pages to the cpu_buffers. Otherwise we just free
+	 * them all and return -ENOMEM;
+	 */
+	BUG_ON(nr_pages <= buffer->pages);
+	new_pages = nr_pages - buffer->pages;
+
+	for_each_buffer_cpu(buffer, cpu) {
+		for (i = 0; i < new_pages; i++) {
+			addr = __get_free_page(GFP_KERNEL);
+			if (!addr)
+				goto free_pages;
+			page = (struct buffer_page *)virt_to_page(addr);
+			list_add(&page->list, &pages);
+		}
+	}
+
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+		rb_insert_pages(cpu_buffer, &pages, new_pages);
+	}
+
+	BUG_ON(!list_empty(&pages));
+
+ out:
+	buffer->pages = nr_pages;
+	mutex_unlock(&buffer->mutex);
+
+	return size;
+
+ free_pages:
+	list_for_each_entry_safe(page, tmp, &pages, list) {
+		list_del_init(&page->list);
+		__free_page(&page->page);
+	}
+	return -ENOMEM;
+}
+
+static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	return cpu_buffer->head_page == cpu_buffer->tail_page &&
+		cpu_buffer->head == cpu_buffer->tail;
+}
+
+static inline int rb_null_event(struct ring_buffer_event *event)
+{
+	return event->type == RINGBUF_TYPE_PADDING;
+}
+
+static inline void *rb_page_index(struct buffer_page *page, unsigned index)
+{
+	void *addr = page_address(&page->page);
+
+	return addr + index;
+}
+
+static inline struct ring_buffer_event *
+rb_head_event(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	return rb_page_index(cpu_buffer->head_page,
+			     cpu_buffer->head);
+}
+
+static inline struct ring_buffer_event *
+rb_iter_head_event(struct ring_buffer_iter *iter)
+{
+	return rb_page_index(iter->head_page,
+			     iter->head);
+}
+
+/*
+ * When the tail hits the head and the buffer is in overwrite mode,
+ * the head jumps to the next page and all content on the previous
+ * page is discarded. But before doing so, we update the overrun
+ * variable of the buffer.
+ */
+static void rb_update_overflow(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct ring_buffer_event *event;
+	unsigned long head;
+
+	for (head = 0; head < rb_head_size(cpu_buffer);
+	     head += rb_event_length(event)) {
+
+		event = rb_page_index(cpu_buffer->head_page, head);
+		BUG_ON(rb_null_event(event));
+		/* Only count data entries */
+		if (event->type != RINGBUF_TYPE_DATA)
+			continue;
+		cpu_buffer->overrun++;
+		cpu_buffer->entries--;
+	}
+}
+
+static inline void rb_inc_page(struct ring_buffer_per_cpu *cpu_buffer,
+			       struct buffer_page **page)
+{
+	struct list_head *p = (*page)->list.next;
+
+	if (p == &cpu_buffer->pages)
+		p = p->next;
+
+	*page = list_entry(p, struct buffer_page, list);
+}
+
+static inline void
+rb_add_stamp(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
+{
+	cpu_buffer->tail_page->time_stamp = *ts;
+	cpu_buffer->write_stamp = *ts;
+}
+
+static void rb_reset_read_page(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	cpu_buffer->read_stamp = cpu_buffer->head_page->time_stamp;
+	cpu_buffer->head = 0;
+}
+
+static void
+rb_reset_iter_read_page(struct ring_buffer_iter *iter)
+{
+	iter->read_stamp = iter->head_page->time_stamp;
+	iter->head = 0;
+}
+
+/**
+ * ring_buffer_update_event - update event type and data
+ * @event: the even to update
+ * @type: the type of event
+ * @length: the size of the event field in the ring buffer
+ *
+ * Update the type and data fields of the event. The length
+ * is the actual size that is written to the ring buffer,
+ * and with this, we can determine what to place into the
+ * data field.
+ */
+static inline void
+rb_update_event(struct ring_buffer_event *event,
+			 unsigned type, unsigned length)
+{
+	event->type = type;
+
+	switch (type) {
+
+	case RINGBUF_TYPE_PADDING:
+		break;
+
+	case RINGBUF_TYPE_TIME_EXTEND:
+		event->len =
+			(RB_LEN_TIME_EXTEND + (RB_ALIGNMENT-1))
+			>> RB_ALIGNMENT_SHIFT;
+		break;
+
+	case RINGBUF_TYPE_TIME_STAMP:
+		event->len =
+			(RB_LEN_TIME_STAMP + (RB_ALIGNMENT-1))
+			>> RB_ALIGNMENT_SHIFT;
+		break;
+
+	case RINGBUF_TYPE_DATA:
+		length -= RB_EVNT_HDR_SIZE;
+		if (length > RB_MAX_SMALL_DATA) {
+			event->len = 0;
+			event->array[0] = length;
+		} else
+			event->len =
+				(length + (RB_ALIGNMENT-1))
+				>> RB_ALIGNMENT_SHIFT;
+		break;
+	default:
+		BUG();
+	}
+}
+
+static inline unsigned rb_calculate_event_length(unsigned length)
+{
+	struct ring_buffer_event event; /* Used only for sizeof array */
+
+	/* zero length can cause confusions */
+	if (!length)
+		length = 1;
+
+	if (length > RB_MAX_SMALL_DATA)
+		length += sizeof(event.array[0]);
+
+	length += RB_EVNT_HDR_SIZE;
+	length = ALIGN(length, RB_ALIGNMENT);
+
+	return length;
+}
+
+static struct ring_buffer_event *
+__rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
+		  unsigned type, unsigned long length, u64 *ts)
+{
+	struct buffer_page *head_page, *tail_page;
+	unsigned long tail;
+	struct ring_buffer *buffer = cpu_buffer->buffer;
+	struct ring_buffer_event *event;
+
+	tail_page = cpu_buffer->tail_page;
+	head_page = cpu_buffer->head_page;
+	tail = cpu_buffer->tail;
+
+	if (tail + length > BUF_PAGE_SIZE) {
+		struct buffer_page *next_page = tail_page;
+
+		rb_inc_page(cpu_buffer, &next_page);
+
+		if (next_page == head_page) {
+			if (!(buffer->flags & RB_FL_OVERWRITE))
+				return NULL;
+
+			/* count overflows */
+			rb_update_overflow(cpu_buffer);
+
+			rb_inc_page(cpu_buffer, &head_page);
+			cpu_buffer->head_page = head_page;
+			rb_reset_read_page(cpu_buffer);
+		}
+
+		if (tail != BUF_PAGE_SIZE) {
+			event = rb_page_index(tail_page, tail);
+			/* page padding */
+			event->type = RINGBUF_TYPE_PADDING;
+		}
+
+		tail_page->size = tail;
+		tail_page = next_page;
+		tail_page->size = 0;
+		tail = 0;
+		cpu_buffer->tail_page = tail_page;
+		cpu_buffer->tail = tail;
+		rb_add_stamp(cpu_buffer, ts);
+	}
+
+	BUG_ON(tail + length > BUF_PAGE_SIZE);
+
+	event = rb_page_index(tail_page, tail);
+	rb_update_event(event, type, length);
+
+	return event;
+}
+
+static int
+rb_add_time_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+		  u64 *ts, u64 *delta)
+{
+	struct ring_buffer_event *event;
+	static int once;
+
+	if (unlikely(*delta > (1ULL << 59) && !once++)) {
+		printk(KERN_WARNING "Delta way too big! %llu"
+		       " ts=%llu write stamp = %llu\n",
+		       *delta, *ts, cpu_buffer->write_stamp);
+		WARN_ON(1);
+	}
+
+	/*
+	 * The delta is too big, we to add a
+	 * new timestamp.
+	 */
+	event = __rb_reserve_next(cpu_buffer,
+				  RINGBUF_TYPE_TIME_EXTEND,
+				  RB_LEN_TIME_EXTEND,
+				  ts);
+	if (!event)
+		return -1;
+
+	/* check to see if we went to the next page */
+	if (cpu_buffer->tail) {
+		/* Still on same page, update timestamp */
+		event->time_delta = *delta & TS_MASK;
+		event->array[0] = *delta >> TS_SHIFT;
+		/* commit the time event */
+		cpu_buffer->tail +=
+			rb_event_length(event);
+		cpu_buffer->write_stamp = *ts;
+		*delta = 0;
+	}
+
+	return 0;
+}
+
+static struct ring_buffer_event *
+rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
+		      unsigned type, unsigned long length)
+{
+	struct ring_buffer_event *event;
+	u64 ts, delta;
+
+	ts = ring_buffer_time_stamp(cpu_buffer->cpu);
+
+	if (cpu_buffer->tail) {
+		delta = ts - cpu_buffer->write_stamp;
+
+		if (test_time_stamp(delta)) {
+			int ret;
+
+			ret = rb_add_time_stamp(cpu_buffer, &ts, &delta);
+			if (ret < 0)
+				return NULL;
+		}
+	} else {
+		rb_add_stamp(cpu_buffer, &ts);
+		delta = 0;
+	}
+
+	event = __rb_reserve_next(cpu_buffer, type, length, &ts);
+	if (!event)
+		return NULL;
+
+	/* If the reserve went to the next page, our delta is zero */
+	if (!cpu_buffer->tail)
+		delta = 0;
+
+	event->time_delta = delta;
+
+	return event;
+}
+
+/**
+ * ring_buffer_lock_reserve - reserve a part of the buffer
+ * @buffer: the ring buffer to reserve from
+ * @length: the length of the data to reserve (excluding event header)
+ * @flags: a pointer to save the interrupt flags
+ *
+ * Returns a reseverd event on the ring buffer to copy directly to.
+ * The user of this interface will need to get the body to write into
+ * and can use the ring_buffer_event_data() interface.
+ *
+ * The length is the length of the data needed, not the event length
+ * which also includes the event header.
+ *
+ * Must be paired with ring_buffer_unlock_commit, unless NULL is returned.
+ * If NULL is returned, then nothing has been allocated or locked.
+ */
+struct ring_buffer_event *
+ring_buffer_lock_reserve(struct ring_buffer *buffer,
+			 unsigned long length,
+			 unsigned long *flags)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_event *event;
+	int cpu;
+
+	if (atomic_read(&buffer->record_disabled))
+		return NULL;
+
+	raw_local_irq_save(*flags);
+	cpu = raw_smp_processor_id();
+
+	if (!cpu_isset(cpu, buffer->cpumask))
+		goto out_irq;
+
+	cpu_buffer = buffer->buffers[cpu];
+	spin_lock(&cpu_buffer->lock);
+
+	if (atomic_read(&cpu_buffer->record_disabled))
+		goto no_record;
+
+	length = rb_calculate_event_length(length);
+	if (length > BUF_PAGE_SIZE)
+		return NULL;
+
+	event = rb_reserve_next_event(cpu_buffer, RINGBUF_TYPE_DATA, length);
+	if (!event)
+		goto no_record;
+
+	return event;
+
+ no_record:
+	spin_unlock(&cpu_buffer->lock);
+ out_irq:
+	local_irq_restore(*flags);
+	return NULL;
+}
+
+static void rb_commit(struct ring_buffer_per_cpu *cpu_buffer,
+		      struct ring_buffer_event *event)
+{
+	cpu_buffer->tail += rb_event_length(event);
+	cpu_buffer->tail_page->size = cpu_buffer->tail;
+	cpu_buffer->write_stamp += event->time_delta;
+	cpu_buffer->entries++;
+}
+
+/**
+ * ring_buffer_unlock_commit - commit a reserved
+ * @buffer: The buffer to commit to
+ * @event: The event pointer to commit.
+ * @flags: the interrupt flags received from ring_buffer_lock_reserve.
+ *
+ * This commits the data to the ring buffer, and releases any locks held.
+ *
+ * Must be paired with ring_buffer_lock_reserve.
+ */
+int ring_buffer_unlock_commit(struct ring_buffer *buffer,
+			      struct ring_buffer_event *event,
+			      unsigned long flags)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	int cpu = raw_smp_processor_id();
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	assert_spin_locked(&cpu_buffer->lock);
+
+	rb_commit(cpu_buffer, event);
+
+	spin_unlock(&cpu_buffer->lock);
+	raw_local_irq_restore(flags);
+
+	return 0;
+}
+
+/**
+ * ring_buffer_write - write data to the buffer without reserving
+ * @buffer: The ring buffer to write to.
+ * @length: The length of the data being written (excluding the event header)
+ * @data: The data to write to the buffer.
+ *
+ * This is like ring_buffer_lock_reserve and ring_buffer_unlock_commit as
+ * one function. If you already have the data to write to the buffer, it
+ * may be easier to simply call this function.
+ *
+ * Note, like ring_buffer_lock_reserve, the length is the length of the data
+ * and not the length of the event which would hold the header.
+ */
+int ring_buffer_write(struct ring_buffer *buffer,
+			unsigned long length,
+			void *data)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_event *event;
+	unsigned long event_length, flags;
+	void *body;
+	int ret = -EBUSY;
+	int cpu;
+
+	if (atomic_read(&buffer->record_disabled))
+		return -EBUSY;
+
+	local_irq_save(flags);
+	cpu = raw_smp_processor_id();
+
+	if (!cpu_isset(cpu, buffer->cpumask))
+		goto out_irq;
+
+	cpu_buffer = buffer->buffers[cpu];
+	spin_lock(&cpu_buffer->lock);
+
+	if (atomic_read(&cpu_buffer->record_disabled))
+		goto out;
+
+	event_length = rb_calculate_event_length(length);
+	event = rb_reserve_next_event(cpu_buffer,
+				      RINGBUF_TYPE_DATA, event_length);
+	if (!event)
+		goto out;
+
+	body = rb_event_data(event);
+
+	memcpy(body, data, length);
+
+	rb_commit(cpu_buffer, event);
+
+	ret = 0;
+ out:
+	spin_unlock(&cpu_buffer->lock);
+ out_irq:
+	local_irq_restore(flags);
+
+	return ret;
+}
+
+/**
+ * ring_buffer_lock - lock the ring buffer
+ * @buffer: The ring buffer to lock
+ * @flags: The place to store the interrupt flags
+ *
+ * This locks all the per CPU buffers.
+ *
+ * Must be unlocked by ring_buffer_unlock.
+ */
+void ring_buffer_lock(struct ring_buffer *buffer, unsigned long *flags)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	int cpu;
+
+	local_irq_save(*flags);
+
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+		spin_lock(&cpu_buffer->lock);
+	}
+}
+
+/**
+ * ring_buffer_unlock - unlock a locked buffer
+ * @buffer: The locked buffer to unlock
+ * @flags: The interrupt flags received by ring_buffer_lock
+ */
+void ring_buffer_unlock(struct ring_buffer *buffer, unsigned long flags)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	int cpu;
+
+	for (cpu = buffer->cpus - 1; cpu >= 0; cpu--) {
+		if (!cpu_isset(cpu, buffer->cpumask))
+			continue;
+		cpu_buffer = buffer->buffers[cpu];
+		spin_unlock(&cpu_buffer->lock);
+	}
+
+	local_irq_restore(flags);
+}
+
+/**
+ * ring_buffer_record_disable - stop all writes into the buffer
+ * @buffer: The ring buffer to stop writes to.
+ *
+ * This prevents all writes to the buffer. Any attempt to write
+ * to the buffer after this will fail and return NULL.
+ *
+ * The caller should call synchronize_sched() after this.
+ */
+void ring_buffer_record_disable(struct ring_buffer *buffer)
+{
+	atomic_inc(&buffer->record_disabled);
+}
+
+/**
+ * ring_buffer_record_enable - enable writes to the buffer
+ * @buffer: The ring buffer to enable writes
+ *
+ * Note, multiple disables will need the same number of enables
+ * to truely enable the writing (much like preempt_disable).
+ */
+void ring_buffer_record_enable(struct ring_buffer *buffer)
+{
+	atomic_dec(&buffer->record_disabled);
+}
+
+/**
+ * ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
+ * @buffer: The ring buffer to stop writes to.
+ * @cpu: The CPU buffer to stop
+ *
+ * This prevents all writes to the buffer. Any attempt to write
+ * to the buffer after this will fail and return NULL.
+ *
+ * The caller should call synchronize_sched() after this.
+ */
+void ring_buffer_record_disable_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (!cpu_isset(cpu, buffer->cpumask))
+		return;
+
+	cpu_buffer = buffer->buffers[cpu];
+	atomic_inc(&cpu_buffer->record_disabled);
+}
+
+/**
+ * ring_buffer_record_enable_cpu - enable writes to the buffer
+ * @buffer: The ring buffer to enable writes
+ * @cpu: The CPU to enable.
+ *
+ * Note, multiple disables will need the same number of enables
+ * to truely enable the writing (much like preempt_disable).
+ */
+void ring_buffer_record_enable_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (!cpu_isset(cpu, buffer->cpumask))
+		return;
+
+	cpu_buffer = buffer->buffers[cpu];
+	atomic_dec(&cpu_buffer->record_disabled);
+}
+
+/**
+ * ring_buffer_entries_cpu - get the number of entries in a cpu buffer
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the entries from.
+ */
+unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (!cpu_isset(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	return cpu_buffer->entries;
+}
+
+/**
+ * ring_buffer_overrun_cpu - get the number of overruns in a cpu_buffer
+ * @buffer: The ring buffer
+ * @cpu: The per CPU buffer to get the number of overruns from
+ */
+unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (!cpu_isset(cpu, buffer->cpumask))
+		return 0;
+
+	cpu_buffer = buffer->buffers[cpu];
+	return cpu_buffer->overrun;
+}
+
+/**
+ * ring_buffer_entries - get the number of entries in a buffer
+ * @buffer: The ring buffer
+ *
+ * Returns the total number of entries in the ring buffer
+ * (all CPU entries)
+ */
+unsigned long ring_buffer_entries(struct ring_buffer *buffer)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long entries = 0;
+	int cpu;
+
+	/* if you care about this being correct, lock the buffer */
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+		entries += cpu_buffer->entries;
+	}
+
+	return entries;
+}
+
+/**
+ * ring_buffer_overrun_cpu - get the number of overruns in buffer
+ * @buffer: The ring buffer
+ *
+ * Returns the total number of overruns in the ring buffer
+ * (all CPU entries)
+ */
+unsigned long ring_buffer_overruns(struct ring_buffer *buffer)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long overruns = 0;
+	int cpu;
+
+	/* if you care about this being correct, lock the buffer */
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+		overruns += cpu_buffer->overrun;
+	}
+
+	return overruns;
+}
+
+/**
+ * ring_buffer_iter_reset - reset an iterator
+ * @iter: The iterator to reset
+ *
+ * Resets the iterator, so that it will start from the beginning
+ * again.
+ */
+void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+
+	iter->head_page = cpu_buffer->head_page;
+	iter->head = cpu_buffer->head;
+	rb_reset_iter_read_page(iter);
+}
+
+/**
+ * ring_buffer_iter_empty - check if an iterator has no more to read
+ * @iter: The iterator to check
+ */
+int ring_buffer_iter_empty(struct ring_buffer_iter *iter)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	cpu_buffer = iter->cpu_buffer;
+
+	return iter->head_page == cpu_buffer->tail_page &&
+		iter->head == cpu_buffer->tail;
+}
+
+static void
+rb_update_read_stamp(struct ring_buffer_per_cpu *cpu_buffer,
+		     struct ring_buffer_event *event)
+{
+	u64 delta;
+
+	switch (event->type) {
+	case RINGBUF_TYPE_PADDING:
+		return;
+
+	case RINGBUF_TYPE_TIME_EXTEND:
+		delta = event->array[0];
+		delta <<= TS_SHIFT;
+		delta += event->time_delta;
+		cpu_buffer->read_stamp += delta;
+		return;
+
+	case RINGBUF_TYPE_TIME_STAMP:
+		/* FIXME: not implemented */
+		return;
+
+	case RINGBUF_TYPE_DATA:
+		cpu_buffer->read_stamp += event->time_delta;
+		return;
+
+	default:
+		BUG();
+	}
+	return;
+}
+
+static void
+rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
+			  struct ring_buffer_event *event)
+{
+	u64 delta;
+
+	switch (event->type) {
+	case RINGBUF_TYPE_PADDING:
+		return;
+
+	case RINGBUF_TYPE_TIME_EXTEND:
+		delta = event->array[0];
+		delta <<= TS_SHIFT;
+		delta += event->time_delta;
+		iter->read_stamp += delta;
+		return;
+
+	case RINGBUF_TYPE_TIME_STAMP:
+		/* FIXME: not implemented */
+		return;
+
+	case RINGBUF_TYPE_DATA:
+		iter->read_stamp += event->time_delta;
+		return;
+
+	default:
+		BUG();
+	}
+	return;
+}
+
+static void rb_advance_head(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct ring_buffer_event *event;
+	unsigned length;
+
+	/*
+	 * Check if we are at the end of the buffer.
+	 */
+	if (cpu_buffer->head >= cpu_buffer->head_page->size) {
+		BUG_ON(cpu_buffer->head_page == cpu_buffer->tail_page);
+		rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
+		rb_reset_read_page(cpu_buffer);
+		return;
+	}
+
+	event = rb_head_event(cpu_buffer);
+
+	if (event->type == RINGBUF_TYPE_DATA)
+		cpu_buffer->entries--;
+
+	length = rb_event_length(event);
+
+	/*
+	 * This should not be called to advance the header if we are
+	 * at the tail of the buffer.
+	 */
+	BUG_ON((cpu_buffer->head_page == cpu_buffer->tail_page) &&
+	       (cpu_buffer->head + length > cpu_buffer->tail));
+
+	rb_update_read_stamp(cpu_buffer, event);
+
+	cpu_buffer->head += length;
+
+	/* check for end of page */
+	if ((cpu_buffer->head >= cpu_buffer->head_page->size) &&
+	    (cpu_buffer->head_page != cpu_buffer->tail_page))
+		rb_advance_head(cpu_buffer);
+}
+
+static void rb_advance_iter(struct ring_buffer_iter *iter)
+{
+	struct ring_buffer *buffer;
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_event *event;
+	unsigned length;
+
+	cpu_buffer = iter->cpu_buffer;
+	buffer = cpu_buffer->buffer;
+
+	/*
+	 * Check if we are at the end of the buffer.
+	 */
+	if (iter->head >= iter->head_page->size) {
+		BUG_ON(iter->head_page == cpu_buffer->tail_page);
+		rb_inc_page(cpu_buffer, &iter->head_page);
+		rb_reset_iter_read_page(iter);
+		return;
+	}
+
+	event = rb_iter_head_event(iter);
+
+	length = rb_event_length(event);
+
+	/*
+	 * This should not be called to advance the header if we are
+	 * at the tail of the buffer.
+	 */
+	BUG_ON((iter->head_page == cpu_buffer->tail_page) &&
+	       (iter->head + length > cpu_buffer->tail));
+
+	rb_update_iter_read_stamp(iter, event);
+
+	iter->head += length;
+
+	/* check for end of page padding */
+	if ((iter->head >= iter->head_page->size) &&
+	    (iter->head_page != cpu_buffer->tail_page))
+		rb_advance_iter(iter);
+}
+
+/**
+ * ring_buffer_peek - peek at the next event to be read
+ * @buffer: The ring buffer to read
+ * @cpu: The cpu to peak at
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not consume the data.
+ */
+struct ring_buffer_event *
+ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_event *event;
+
+	if (!cpu_isset(cpu, buffer->cpumask))
+		return NULL;
+
+	cpu_buffer = buffer->buffers[cpu];
+
+ again:
+	if (rb_per_cpu_empty(cpu_buffer))
+		return NULL;
+
+	event = rb_head_event(cpu_buffer);
+
+	switch (event->type) {
+	case RINGBUF_TYPE_PADDING:
+		rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
+		rb_reset_read_page(cpu_buffer);
+		goto again;
+
+	case RINGBUF_TYPE_TIME_EXTEND:
+		/* Internal data, OK to advance */
+		rb_advance_head(cpu_buffer);
+		goto again;
+
+	case RINGBUF_TYPE_TIME_STAMP:
+		/* FIXME: not implemented */
+		rb_advance_head(cpu_buffer);
+		goto again;
+
+	case RINGBUF_TYPE_DATA:
+		if (ts) {
+			*ts = cpu_buffer->read_stamp + event->time_delta;
+			ring_buffer_normalize_time_stamp(cpu_buffer->cpu, ts);
+		}
+		return event;
+
+	default:
+		BUG();
+	}
+
+	return NULL;
+}
+
+/**
+ * ring_buffer_iter_peek - peek at the next event to be read
+ * @iter: The ring buffer iterator
+ * @ts: The timestamp counter of this event.
+ *
+ * This will return the event that will be read next, but does
+ * not increment the iterator.
+ */
+struct ring_buffer_event *
+ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
+{
+	struct ring_buffer *buffer;
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_event *event;
+
+	if (ring_buffer_iter_empty(iter))
+		return NULL;
+
+	cpu_buffer = iter->cpu_buffer;
+	buffer = cpu_buffer->buffer;
+
+ again:
+	if (rb_per_cpu_empty(cpu_buffer))
+		return NULL;
+
+	event = rb_iter_head_event(iter);
+
+	switch (event->type) {
+	case RINGBUF_TYPE_PADDING:
+		rb_inc_page(cpu_buffer, &iter->head_page);
+		rb_reset_iter_read_page(iter);
+		goto again;
+
+	case RINGBUF_TYPE_TIME_EXTEND:
+		/* Internal data, OK to advance */
+		rb_advance_iter(iter);
+		goto again;
+
+	case RINGBUF_TYPE_TIME_STAMP:
+		/* FIXME: not implemented */
+		rb_advance_iter(iter);
+		goto again;
+
+	case RINGBUF_TYPE_DATA:
+		if (ts) {
+			*ts = iter->read_stamp + event->time_delta;
+			ring_buffer_normalize_time_stamp(cpu_buffer->cpu, ts);
+		}
+		return event;
+
+	default:
+		BUG();
+	}
+
+	return NULL;
+}
+
+/**
+ * ring_buffer_consume - return an event and consume it
+ * @buffer: The ring buffer to get the next event from
+ *
+ * Returns the next event in the ring buffer, and that event is consumed.
+ * Meaning, that sequential reads will keep returning a different event,
+ * and eventually empty the ring buffer if the producer is slower.
+ */
+struct ring_buffer_event *
+ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_event *event;
+
+	if (!cpu_isset(cpu, buffer->cpumask))
+		return NULL;
+
+	event = ring_buffer_peek(buffer, cpu, ts);
+	if (!event)
+		return NULL;
+
+	cpu_buffer = buffer->buffers[cpu];
+	rb_advance_head(cpu_buffer);
+
+	return event;
+}
+
+/**
+ * ring_buffer_read_start - start a non consuming read of the buffer
+ * @buffer: The ring buffer to read from
+ * @cpu: The cpu buffer to iterate over
+ *
+ * This starts up an iteration through the buffer. It also disables
+ * the recording to the buffer until the reading is finished.
+ * This prevents the reading from being corrupted. This is not
+ * a consuming read, so a producer is not expected.
+ *
+ * Must be paired with ring_buffer_finish.
+ */
+struct ring_buffer_iter *
+ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	struct ring_buffer_iter *iter;
+
+	if (!cpu_isset(cpu, buffer->cpumask))
+		return NULL;
+
+	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+	if (!iter)
+		return NULL;
+
+	cpu_buffer = buffer->buffers[cpu];
+
+	iter->cpu_buffer = cpu_buffer;
+
+	atomic_inc(&cpu_buffer->record_disabled);
+	synchronize_sched();
+
+	spin_lock(&cpu_buffer->lock);
+	iter->head = cpu_buffer->head;
+	iter->head_page = cpu_buffer->head_page;
+	rb_reset_iter_read_page(iter);
+	spin_unlock(&cpu_buffer->lock);
+
+	return iter;
+}
+
+/**
+ * ring_buffer_finish - finish reading the iterator of the buffer
+ * @iter: The iterator retrieved by ring_buffer_start
+ *
+ * This re-enables the recording to the buffer, and frees the
+ * iterator.
+ */
+void
+ring_buffer_read_finish(struct ring_buffer_iter *iter)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+
+	atomic_dec(&cpu_buffer->record_disabled);
+	kfree(iter);
+}
+
+/**
+ * ring_buffer_read - read the next item in the ring buffer by the iterator
+ * @iter: The ring buffer iterator
+ * @ts: The time stamp of the event read.
+ *
+ * This reads the next event in the ring buffer and increments the iterator.
+ */
+struct ring_buffer_event *
+ring_buffer_read(struct ring_buffer_iter *iter, u64 *ts)
+{
+	struct ring_buffer_event *event;
+
+	event = ring_buffer_iter_peek(iter, ts);
+	if (!event)
+		return NULL;
+
+	rb_advance_iter(iter);
+
+	return event;
+}
+
+/**
+ * ring_buffer_size - return the size of the ring buffer (in bytes)
+ * @buffer: The ring buffer.
+ */
+unsigned long ring_buffer_size(struct ring_buffer *buffer)
+{
+	return BUF_PAGE_SIZE * buffer->pages;
+}
+
+static void
+rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	cpu_buffer->head_page
+		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+	cpu_buffer->tail_page
+		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+
+	cpu_buffer->head = cpu_buffer->tail = 0;
+	cpu_buffer->overrun = 0;
+	cpu_buffer->entries = 0;
+}
+
+/**
+ * ring_buffer_reset_cpu - reset a ring buffer per CPU buffer
+ * @buffer: The ring buffer to reset a per cpu buffer of
+ * @cpu: The CPU buffer to be reset
+ */
+void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = buffer->buffers[cpu];
+	unsigned long flags;
+
+	if (!cpu_isset(cpu, buffer->cpumask))
+		return;
+
+	raw_local_irq_save(flags);
+	spin_lock(&cpu_buffer->lock);
+
+	rb_reset_cpu(cpu_buffer);
+
+	spin_unlock(&cpu_buffer->lock);
+	raw_local_irq_restore(flags);
+}
+
+/**
+ * ring_buffer_reset - reset a ring buffer
+ * @buffer: The ring buffer to reset all cpu buffers
+ */
+void ring_buffer_reset(struct ring_buffer *buffer)
+{
+	unsigned long flags;
+	int cpu;
+
+	ring_buffer_lock(buffer, &flags);
+
+	for_each_buffer_cpu(buffer, cpu)
+		rb_reset_cpu(buffer->buffers[cpu]);
+
+	ring_buffer_unlock(buffer, flags);
+}
+
+/**
+ * rind_buffer_empty - is the ring buffer empty?
+ * @buffer: The ring buffer to test
+ */
+int ring_buffer_empty(struct ring_buffer *buffer)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+	int cpu;
+
+	/* yes this is racy, but if you don't like the race, lock the buffer */
+	for_each_buffer_cpu(buffer, cpu) {
+		cpu_buffer = buffer->buffers[cpu];
+		if (!rb_per_cpu_empty(cpu_buffer))
+			return 0;
+	}
+	return 1;
+}
+
+/**
+ * ring_buffer_empty_cpu - is a cpu buffer of a ring buffer empty?
+ * @buffer: The ring buffer
+ * @cpu: The CPU buffer to test
+ */
+int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer;
+
+	if (!cpu_isset(cpu, buffer->cpumask))
+		return 1;
+
+	cpu_buffer = buffer->buffers[cpu];
+	return rb_per_cpu_empty(cpu_buffer);
+}
+
+/**
+ * ring_buffer_swap_cpu - swap a CPU buffer between two ring buffers
+ * @buffer_a: One buffer to swap with
+ * @buffer_b: The other buffer to swap with
+ *
+ * This function is useful for tracers that want to take a "snapshot"
+ * of a CPU buffer and has another back up buffer lying around.
+ * it is expected that the tracer handles the cpu buffer not being
+ * used at the moment.
+ */
+int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
+			 struct ring_buffer *buffer_b, int cpu)
+{
+	struct ring_buffer_per_cpu *cpu_buffer_a;
+	struct ring_buffer_per_cpu *cpu_buffer_b;
+
+	if (!cpu_isset(cpu, buffer_a->cpumask) ||
+	    !cpu_isset(cpu, buffer_b->cpumask))
+		return -EINVAL;
+
+	/* At least make sure the two buffers are somewhat the same */
+	if (buffer_a->size != buffer_b->size ||
+	    buffer_a->pages != buffer_b->pages)
+		return -EINVAL;
+
+	cpu_buffer_a = buffer_a->buffers[cpu];
+	cpu_buffer_b = buffer_b->buffers[cpu];
+
+	/*
+	 * We can't do a synchronize_sched here because this
+	 * function can be called in atomic context.
+	 * Normally this will be called from the same CPU as cpu.
+	 * If not it's up to the caller to protect this.
+	 */
+	atomic_inc(&cpu_buffer_a->record_disabled);
+	atomic_inc(&cpu_buffer_b->record_disabled);
+
+	buffer_a->buffers[cpu] = cpu_buffer_b;
+	buffer_b->buffers[cpu] = cpu_buffer_a;
+
+	cpu_buffer_b->buffer = buffer_a;
+	cpu_buffer_a->buffer = buffer_b;
+
+	atomic_dec(&cpu_buffer_a->record_disabled);
+	atomic_dec(&cpu_buffer_b->record_disabled);
+
+	return 0;
+}
+
-- 
cgit v1.2.3


From d769041f865330034131525ee6a7f72eb4af2a24 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 1 Oct 2008 00:29:53 -0400
Subject: ring_buffer: implement new locking

The old "lock always" scheme had issues with lockdep, and was not very
efficient anyways.

This patch does a new design to be partially lockless on writes.
Writes will add new entries to the per cpu pages by simply disabling
interrupts. When a write needs to go to another page than it will
grab the lock.

A new "read page" has been added so that the reader can pull out a page
from the ring buffer to read without worrying about the writer writing over
it. This allows us to not take the lock for all reads. The lock is
now only taken when a read needs to go to a new page.

This is far from lockless, and interrupts still need to be disabled,
but it is a step towards a more lockless solution, and it also
solves a lot of the issues that were noticed by the first conversion
of ftrace to the ring buffers.

Note: the ring_buffer_{un}lock API has been removed.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ring_buffer.h |   3 -
 kernel/trace/ring_buffer.c  | 298 +++++++++++++++++++++++++-------------------
 kernel/trace/trace.c        | 113 +++++++++++------
 3 files changed, 247 insertions(+), 167 deletions(-)

(limited to 'include')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index c52375b8330d..536b0ca46a03 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -63,9 +63,6 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event)
 	return event->time_delta;
 }
 
-void ring_buffer_lock(struct ring_buffer *buffer, unsigned long *flags);
-void ring_buffer_unlock(struct ring_buffer *buffer, unsigned long flags);
-
 /*
  * size is in bytes for each per CPU buffer.
  */
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 8e7392fd0db9..9631abf2ae29 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -161,8 +161,10 @@ struct ring_buffer_per_cpu {
 	struct list_head		pages;
 	unsigned long			head;	/* read from head */
 	unsigned long			tail;	/* write to tail */
+	unsigned long			reader;
 	struct buffer_page		*head_page;
 	struct buffer_page		*tail_page;
+	struct buffer_page		*reader_page;
 	unsigned long			overrun;
 	unsigned long			entries;
 	u64				write_stamp;
@@ -260,6 +262,7 @@ static struct ring_buffer_per_cpu *
 rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
+	unsigned long addr;
 	int ret;
 
 	cpu_buffer = kzalloc_node(ALIGN(sizeof(*cpu_buffer), cache_line_size()),
@@ -272,9 +275,16 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 	spin_lock_init(&cpu_buffer->lock);
 	INIT_LIST_HEAD(&cpu_buffer->pages);
 
+	addr = __get_free_page(GFP_KERNEL);
+	if (!addr)
+		goto fail_free_buffer;
+	cpu_buffer->reader_page = (struct buffer_page *)virt_to_page(addr);
+	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+	cpu_buffer->reader_page->size = 0;
+
 	ret = rb_allocate_pages(cpu_buffer, buffer->pages);
 	if (ret < 0)
-		goto fail_free_buffer;
+		goto fail_free_reader;
 
 	cpu_buffer->head_page
 		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
@@ -283,6 +293,9 @@ rb_allocate_cpu_buffer(struct ring_buffer *buffer, int cpu)
 
 	return cpu_buffer;
 
+ fail_free_reader:
+	free_buffer_page(cpu_buffer->reader_page);
+
  fail_free_buffer:
 	kfree(cpu_buffer);
 	return NULL;
@@ -293,6 +306,9 @@ static void rb_free_cpu_buffer(struct ring_buffer_per_cpu *cpu_buffer)
 	struct list_head *head = &cpu_buffer->pages;
 	struct buffer_page *page, *tmp;
 
+	list_del_init(&cpu_buffer->reader_page->list);
+	free_buffer_page(cpu_buffer->reader_page);
+
 	list_for_each_entry_safe(page, tmp, head, list) {
 		list_del_init(&page->list);
 		free_buffer_page(page);
@@ -538,8 +554,10 @@ int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size)
 
 static inline int rb_per_cpu_empty(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	return cpu_buffer->head_page == cpu_buffer->tail_page &&
-		cpu_buffer->head == cpu_buffer->tail;
+	return (cpu_buffer->reader == cpu_buffer->reader_page->size &&
+		(cpu_buffer->tail_page == cpu_buffer->reader_page ||
+		 (cpu_buffer->tail_page == cpu_buffer->head_page &&
+		  cpu_buffer->head == cpu_buffer->tail)));
 }
 
 static inline int rb_null_event(struct ring_buffer_event *event)
@@ -555,10 +573,10 @@ static inline void *rb_page_index(struct buffer_page *page, unsigned index)
 }
 
 static inline struct ring_buffer_event *
-rb_head_event(struct ring_buffer_per_cpu *cpu_buffer)
+rb_reader_event(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	return rb_page_index(cpu_buffer->head_page,
-			     cpu_buffer->head);
+	return rb_page_index(cpu_buffer->reader_page,
+			     cpu_buffer->reader);
 }
 
 static inline struct ring_buffer_event *
@@ -610,15 +628,32 @@ rb_add_stamp(struct ring_buffer_per_cpu *cpu_buffer, u64 *ts)
 	cpu_buffer->write_stamp = *ts;
 }
 
-static void rb_reset_read_page(struct ring_buffer_per_cpu *cpu_buffer)
+static void rb_reset_head_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	cpu_buffer->read_stamp = cpu_buffer->head_page->time_stamp;
 	cpu_buffer->head = 0;
 }
 
-static void
-rb_reset_iter_read_page(struct ring_buffer_iter *iter)
+static void rb_reset_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
+	cpu_buffer->read_stamp = cpu_buffer->reader_page->time_stamp;
+	cpu_buffer->reader = 0;
+}
+
+static inline void rb_inc_iter(struct ring_buffer_iter *iter)
+{
+	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
+
+	/*
+	 * The iterator could be on the reader page (it starts there).
+	 * But the head could have moved, since the reader was
+	 * found. Check for this case and assign the iterator
+	 * to the head page instead of next.
+	 */
+	if (iter->head_page == cpu_buffer->reader_page)
+		iter->head_page = cpu_buffer->head_page;
+	else
+		rb_inc_page(cpu_buffer, &iter->head_page);
+
 	iter->read_stamp = iter->head_page->time_stamp;
 	iter->head = 0;
 }
@@ -693,30 +728,39 @@ static struct ring_buffer_event *
 __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		  unsigned type, unsigned long length, u64 *ts)
 {
-	struct buffer_page *head_page, *tail_page;
+	struct buffer_page *tail_page, *head_page, *reader_page;
 	unsigned long tail;
 	struct ring_buffer *buffer = cpu_buffer->buffer;
 	struct ring_buffer_event *event;
 
+	/* No locking needed for tail page */
 	tail_page = cpu_buffer->tail_page;
-	head_page = cpu_buffer->head_page;
 	tail = cpu_buffer->tail;
 
 	if (tail + length > BUF_PAGE_SIZE) {
 		struct buffer_page *next_page = tail_page;
 
+		spin_lock(&cpu_buffer->lock);
 		rb_inc_page(cpu_buffer, &next_page);
 
+		head_page = cpu_buffer->head_page;
+		reader_page = cpu_buffer->reader_page;
+
+		/* we grabbed the lock before incrementing */
+		WARN_ON(next_page == reader_page);
+
 		if (next_page == head_page) {
-			if (!(buffer->flags & RB_FL_OVERWRITE))
+			if (!(buffer->flags & RB_FL_OVERWRITE)) {
+				spin_unlock(&cpu_buffer->lock);
 				return NULL;
+			}
 
 			/* count overflows */
 			rb_update_overflow(cpu_buffer);
 
 			rb_inc_page(cpu_buffer, &head_page);
 			cpu_buffer->head_page = head_page;
-			rb_reset_read_page(cpu_buffer);
+			rb_reset_head_page(cpu_buffer);
 		}
 
 		if (tail != BUF_PAGE_SIZE) {
@@ -732,6 +776,7 @@ __rb_reserve_next(struct ring_buffer_per_cpu *cpu_buffer,
 		cpu_buffer->tail_page = tail_page;
 		cpu_buffer->tail = tail;
 		rb_add_stamp(cpu_buffer, ts);
+		spin_unlock(&cpu_buffer->lock);
 	}
 
 	BUG_ON(tail + length > BUF_PAGE_SIZE);
@@ -802,7 +847,9 @@ rb_reserve_next_event(struct ring_buffer_per_cpu *cpu_buffer,
 				return NULL;
 		}
 	} else {
+		spin_lock(&cpu_buffer->lock);
 		rb_add_stamp(cpu_buffer, &ts);
+		spin_unlock(&cpu_buffer->lock);
 		delta = 0;
 	}
 
@@ -851,13 +898,12 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
 	cpu = raw_smp_processor_id();
 
 	if (!cpu_isset(cpu, buffer->cpumask))
-		goto out_irq;
+		goto out;
 
 	cpu_buffer = buffer->buffers[cpu];
-	spin_lock(&cpu_buffer->lock);
 
 	if (atomic_read(&cpu_buffer->record_disabled))
-		goto no_record;
+		goto out;
 
 	length = rb_calculate_event_length(length);
 	if (length > BUF_PAGE_SIZE)
@@ -865,13 +911,11 @@ ring_buffer_lock_reserve(struct ring_buffer *buffer,
 
 	event = rb_reserve_next_event(cpu_buffer, RINGBUF_TYPE_DATA, length);
 	if (!event)
-		goto no_record;
+		goto out;
 
 	return event;
 
- no_record:
-	spin_unlock(&cpu_buffer->lock);
- out_irq:
+ out:
 	local_irq_restore(*flags);
 	return NULL;
 }
@@ -904,11 +948,8 @@ int ring_buffer_unlock_commit(struct ring_buffer *buffer,
 
 	cpu_buffer = buffer->buffers[cpu];
 
-	assert_spin_locked(&cpu_buffer->lock);
-
 	rb_commit(cpu_buffer, event);
 
-	spin_unlock(&cpu_buffer->lock);
 	local_irq_restore(flags);
 
 	return 0;
@@ -945,10 +986,9 @@ int ring_buffer_write(struct ring_buffer *buffer,
 	cpu = raw_smp_processor_id();
 
 	if (!cpu_isset(cpu, buffer->cpumask))
-		goto out_irq;
+		goto out;
 
 	cpu_buffer = buffer->buffers[cpu];
-	spin_lock(&cpu_buffer->lock);
 
 	if (atomic_read(&cpu_buffer->record_disabled))
 		goto out;
@@ -967,55 +1007,11 @@ int ring_buffer_write(struct ring_buffer *buffer,
 
 	ret = 0;
  out:
-	spin_unlock(&cpu_buffer->lock);
- out_irq:
 	local_irq_restore(flags);
 
 	return ret;
 }
 
-/**
- * ring_buffer_lock - lock the ring buffer
- * @buffer: The ring buffer to lock
- * @flags: The place to store the interrupt flags
- *
- * This locks all the per CPU buffers.
- *
- * Must be unlocked by ring_buffer_unlock.
- */
-void ring_buffer_lock(struct ring_buffer *buffer, unsigned long *flags)
-{
-	struct ring_buffer_per_cpu *cpu_buffer;
-	int cpu;
-
-	local_irq_save(*flags);
-
-	for_each_buffer_cpu(buffer, cpu) {
-		cpu_buffer = buffer->buffers[cpu];
-		spin_lock(&cpu_buffer->lock);
-	}
-}
-
-/**
- * ring_buffer_unlock - unlock a locked buffer
- * @buffer: The locked buffer to unlock
- * @flags: The interrupt flags received by ring_buffer_lock
- */
-void ring_buffer_unlock(struct ring_buffer *buffer, unsigned long flags)
-{
-	struct ring_buffer_per_cpu *cpu_buffer;
-	int cpu;
-
-	for (cpu = buffer->cpus - 1; cpu >= 0; cpu--) {
-		if (!cpu_isset(cpu, buffer->cpumask))
-			continue;
-		cpu_buffer = buffer->buffers[cpu];
-		spin_unlock(&cpu_buffer->lock);
-	}
-
-	local_irq_restore(flags);
-}
-
 /**
  * ring_buffer_record_disable - stop all writes into the buffer
  * @buffer: The ring buffer to stop writes to.
@@ -1169,9 +1165,18 @@ void ring_buffer_iter_reset(struct ring_buffer_iter *iter)
 {
 	struct ring_buffer_per_cpu *cpu_buffer = iter->cpu_buffer;
 
-	iter->head_page = cpu_buffer->head_page;
-	iter->head = cpu_buffer->head;
-	rb_reset_iter_read_page(iter);
+	/* Iterator usage is expected to have record disabled */
+	if (list_empty(&cpu_buffer->reader_page->list)) {
+		iter->head_page = cpu_buffer->head_page;
+		iter->head = cpu_buffer->head;
+	} else {
+		iter->head_page = cpu_buffer->reader_page;
+		iter->head = cpu_buffer->reader;
+	}
+	if (iter->head)
+		iter->read_stamp = cpu_buffer->read_stamp;
+	else
+		iter->read_stamp = iter->head_page->time_stamp;
 }
 
 /**
@@ -1250,43 +1255,84 @@ rb_update_iter_read_stamp(struct ring_buffer_iter *iter,
 	return;
 }
 
-static void rb_advance_head(struct ring_buffer_per_cpu *cpu_buffer)
+static struct buffer_page *
+rb_get_reader_page(struct ring_buffer_per_cpu *cpu_buffer)
 {
-	struct ring_buffer_event *event;
-	unsigned length;
+	struct buffer_page *reader = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&cpu_buffer->lock, flags);
+
+ again:
+	reader = cpu_buffer->reader_page;
+
+	/* If there's more to read, return this page */
+	if (cpu_buffer->reader < reader->size)
+		goto out;
+
+	/* Never should we have an index greater than the size */
+	WARN_ON(cpu_buffer->reader > reader->size);
+
+	/* check if we caught up to the tail */
+	reader = NULL;
+	if (cpu_buffer->tail_page == cpu_buffer->reader_page)
+		goto out;
 
 	/*
-	 * Check if we are at the end of the buffer.
+	 * Splice the empty reader page into the list around the head.
+	 * Reset the reader page to size zero.
 	 */
-	if (cpu_buffer->head >= cpu_buffer->head_page->size) {
-		BUG_ON(cpu_buffer->head_page == cpu_buffer->tail_page);
-		rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
-		rb_reset_read_page(cpu_buffer);
-		return;
-	}
 
-	event = rb_head_event(cpu_buffer);
+	reader = cpu_buffer->head_page;
+	cpu_buffer->reader_page->list.next = reader->list.next;
+	cpu_buffer->reader_page->list.prev = reader->list.prev;
+	cpu_buffer->reader_page->size = 0;
 
-	if (event->type == RINGBUF_TYPE_DATA)
-		cpu_buffer->entries--;
-
-	length = rb_event_length(event);
+	/* Make the reader page now replace the head */
+	reader->list.prev->next = &cpu_buffer->reader_page->list;
+	reader->list.next->prev = &cpu_buffer->reader_page->list;
 
 	/*
-	 * This should not be called to advance the header if we are
-	 * at the tail of the buffer.
+	 * If the tail is on the reader, then we must set the head
+	 * to the inserted page, otherwise we set it one before.
 	 */
-	BUG_ON((cpu_buffer->head_page == cpu_buffer->tail_page) &&
-	       (cpu_buffer->head + length > cpu_buffer->tail));
+	cpu_buffer->head_page = cpu_buffer->reader_page;
 
-	rb_update_read_stamp(cpu_buffer, event);
+	if (cpu_buffer->tail_page != reader)
+		rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
+
+	/* Finally update the reader page to the new head */
+	cpu_buffer->reader_page = reader;
+	rb_reset_reader_page(cpu_buffer);
+
+	goto again;
+
+ out:
+	spin_unlock_irqrestore(&cpu_buffer->lock, flags);
+
+	return reader;
+}
+
+static void rb_advance_reader(struct ring_buffer_per_cpu *cpu_buffer)
+{
+	struct ring_buffer_event *event;
+	struct buffer_page *reader;
+	unsigned length;
+
+	reader = rb_get_reader_page(cpu_buffer);
 
-	cpu_buffer->head += length;
+	/* This function should not be called when buffer is empty */
+	BUG_ON(!reader);
 
-	/* check for end of page */
-	if ((cpu_buffer->head >= cpu_buffer->head_page->size) &&
-	    (cpu_buffer->head_page != cpu_buffer->tail_page))
-		rb_advance_head(cpu_buffer);
+	event = rb_reader_event(cpu_buffer);
+
+	if (event->type == RINGBUF_TYPE_DATA)
+		cpu_buffer->entries--;
+
+	rb_update_read_stamp(cpu_buffer, event);
+
+	length = rb_event_length(event);
+	cpu_buffer->reader += length;
 }
 
 static void rb_advance_iter(struct ring_buffer_iter *iter)
@@ -1304,8 +1350,7 @@ static void rb_advance_iter(struct ring_buffer_iter *iter)
 	 */
 	if (iter->head >= iter->head_page->size) {
 		BUG_ON(iter->head_page == cpu_buffer->tail_page);
-		rb_inc_page(cpu_buffer, &iter->head_page);
-		rb_reset_iter_read_page(iter);
+		rb_inc_iter(iter);
 		return;
 	}
 
@@ -1344,6 +1389,7 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_event *event;
+	struct buffer_page *reader;
 
 	if (!cpu_isset(cpu, buffer->cpumask))
 		return NULL;
@@ -1351,25 +1397,26 @@ ring_buffer_peek(struct ring_buffer *buffer, int cpu, u64 *ts)
 	cpu_buffer = buffer->buffers[cpu];
 
  again:
-	if (rb_per_cpu_empty(cpu_buffer))
+	reader = rb_get_reader_page(cpu_buffer);
+	if (!reader)
 		return NULL;
 
-	event = rb_head_event(cpu_buffer);
+	event = rb_reader_event(cpu_buffer);
 
 	switch (event->type) {
 	case RINGBUF_TYPE_PADDING:
-		rb_inc_page(cpu_buffer, &cpu_buffer->head_page);
-		rb_reset_read_page(cpu_buffer);
-		goto again;
+		WARN_ON(1);
+		rb_advance_reader(cpu_buffer);
+		return NULL;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
 		/* Internal data, OK to advance */
-		rb_advance_head(cpu_buffer);
+		rb_advance_reader(cpu_buffer);
 		goto again;
 
 	case RINGBUF_TYPE_TIME_STAMP:
 		/* FIXME: not implemented */
-		rb_advance_head(cpu_buffer);
+		rb_advance_reader(cpu_buffer);
 		goto again;
 
 	case RINGBUF_TYPE_DATA:
@@ -1415,8 +1462,7 @@ ring_buffer_iter_peek(struct ring_buffer_iter *iter, u64 *ts)
 
 	switch (event->type) {
 	case RINGBUF_TYPE_PADDING:
-		rb_inc_page(cpu_buffer, &iter->head_page);
-		rb_reset_iter_read_page(iter);
+		rb_inc_iter(iter);
 		goto again;
 
 	case RINGBUF_TYPE_TIME_EXTEND:
@@ -1465,7 +1511,7 @@ ring_buffer_consume(struct ring_buffer *buffer, int cpu, u64 *ts)
 		return NULL;
 
 	cpu_buffer = buffer->buffers[cpu];
-	rb_advance_head(cpu_buffer);
+	rb_advance_reader(cpu_buffer);
 
 	return event;
 }
@@ -1487,6 +1533,7 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_iter *iter;
+	unsigned long flags;
 
 	if (!cpu_isset(cpu, buffer->cpumask))
 		return NULL;
@@ -1502,11 +1549,9 @@ ring_buffer_read_start(struct ring_buffer *buffer, int cpu)
 	atomic_inc(&cpu_buffer->record_disabled);
 	synchronize_sched();
 
-	spin_lock(&cpu_buffer->lock);
-	iter->head = cpu_buffer->head;
-	iter->head_page = cpu_buffer->head_page;
-	rb_reset_iter_read_page(iter);
-	spin_unlock(&cpu_buffer->lock);
+	spin_lock_irqsave(&cpu_buffer->lock, flags);
+	ring_buffer_iter_reset(iter);
+	spin_unlock_irqrestore(&cpu_buffer->lock, flags);
 
 	return iter;
 }
@@ -1562,10 +1607,14 @@ rb_reset_cpu(struct ring_buffer_per_cpu *cpu_buffer)
 {
 	cpu_buffer->head_page
 		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
-	cpu_buffer->tail_page
-		= list_entry(cpu_buffer->pages.next, struct buffer_page, list);
+	cpu_buffer->head_page->size = 0;
+	cpu_buffer->tail_page = cpu_buffer->head_page;
+	cpu_buffer->tail_page->size = 0;
+	INIT_LIST_HEAD(&cpu_buffer->reader_page->list);
+	cpu_buffer->reader_page->size = 0;
+
+	cpu_buffer->head = cpu_buffer->tail = cpu_buffer->reader = 0;
 
-	cpu_buffer->head = cpu_buffer->tail = 0;
 	cpu_buffer->overrun = 0;
 	cpu_buffer->entries = 0;
 }
@@ -1583,13 +1632,11 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
 	if (!cpu_isset(cpu, buffer->cpumask))
 		return;
 
-	local_irq_save(flags);
-	spin_lock(&cpu_buffer->lock);
+	spin_lock_irqsave(&cpu_buffer->lock, flags);
 
 	rb_reset_cpu(cpu_buffer);
 
-	spin_unlock(&cpu_buffer->lock);
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&cpu_buffer->lock, flags);
 }
 
 /**
@@ -1598,15 +1645,10 @@ void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu)
  */
 void ring_buffer_reset(struct ring_buffer *buffer)
 {
-	unsigned long flags;
 	int cpu;
 
-	ring_buffer_lock(buffer, &flags);
-
 	for_each_buffer_cpu(buffer, cpu)
-		rb_reset_cpu(buffer->buffers[cpu]);
-
-	ring_buffer_unlock(buffer, flags);
+		ring_buffer_reset_cpu(buffer, cpu);
 }
 
 /**
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 6a1c76bb56ba..b542f8837801 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -42,6 +42,20 @@
 unsigned long __read_mostly	tracing_max_latency = (cycle_t)ULONG_MAX;
 unsigned long __read_mostly	tracing_thresh;
 
+static DEFINE_PER_CPU(local_t, ftrace_cpu_disabled);
+
+static inline void ftrace_disable_cpu(void)
+{
+	preempt_disable();
+	local_inc(&__get_cpu_var(ftrace_cpu_disabled));
+}
+
+static inline void ftrace_enable_cpu(void)
+{
+	local_dec(&__get_cpu_var(ftrace_cpu_disabled));
+	preempt_enable();
+}
+
 static cpumask_t __read_mostly		tracing_buffer_mask;
 
 #define for_each_tracing_cpu(cpu)	\
@@ -406,7 +420,9 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	tr->buffer = max_tr.buffer;
 	max_tr.buffer = buf;
 
+	ftrace_disable_cpu();
 	ring_buffer_reset(tr->buffer);
+	ftrace_enable_cpu();
 
 	__update_max_tr(tr, tsk, cpu);
 	__raw_spin_unlock(&ftrace_max_lock);
@@ -428,9 +444,13 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)
 	WARN_ON_ONCE(!irqs_disabled());
 	__raw_spin_lock(&ftrace_max_lock);
 
+	ftrace_disable_cpu();
+
 	ring_buffer_reset(max_tr.buffer);
 	ret = ring_buffer_swap_cpu(max_tr.buffer, tr->buffer, cpu);
 
+	ftrace_enable_cpu();
+
 	WARN_ON_ONCE(ret);
 
 	__update_max_tr(tr, tsk, cpu);
@@ -543,7 +563,9 @@ void unregister_tracer(struct tracer *type)
 
 void tracing_reset(struct trace_array *tr, int cpu)
 {
+	ftrace_disable_cpu();
 	ring_buffer_reset_cpu(tr->buffer, cpu);
+	ftrace_enable_cpu();
 }
 
 #define SAVED_CMDLINES 128
@@ -654,6 +676,10 @@ trace_function(struct trace_array *tr, struct trace_array_cpu *data,
 	struct ftrace_entry *entry;
 	unsigned long irq_flags;
 
+	/* If we are reading the ring buffer, don't trace */
+	if (unlikely(local_read(&__get_cpu_var(ftrace_cpu_disabled))))
+		return;
+
 	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
 					 &irq_flags);
 	if (!event)
@@ -870,8 +896,14 @@ enum trace_file_type {
 
 static void trace_iterator_increment(struct trace_iterator *iter, int cpu)
 {
+	/* Don't allow ftrace to trace into the ring buffers */
+	ftrace_disable_cpu();
+
 	iter->idx++;
-	ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
+	if (iter->buffer_iter[iter->cpu])
+		ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
+
+	ftrace_enable_cpu();
 }
 
 static struct trace_entry *
@@ -880,9 +912,19 @@ peek_next_entry(struct trace_iterator *iter, int cpu, u64 *ts)
 	struct ring_buffer_event *event;
 	struct ring_buffer_iter *buf_iter = iter->buffer_iter[cpu];
 
-	event = ring_buffer_iter_peek(buf_iter, ts);
+	/* Don't allow ftrace to trace into the ring buffers */
+	ftrace_disable_cpu();
+
+	if (buf_iter)
+		event = ring_buffer_iter_peek(buf_iter, ts);
+	else
+		event = ring_buffer_peek(iter->tr->buffer, cpu, ts);
+
+	ftrace_enable_cpu();
+
 	return event ? ring_buffer_event_data(event) : NULL;
 }
+
 static struct trace_entry *
 __find_next_entry(struct trace_iterator *iter, int *ent_cpu, u64 *ent_ts)
 {
@@ -938,7 +980,10 @@ static void *find_next_entry_inc(struct trace_iterator *iter)
 
 static void trace_consume(struct trace_iterator *iter)
 {
+	/* Don't allow ftrace to trace into the ring buffers */
+	ftrace_disable_cpu();
 	ring_buffer_consume(iter->tr->buffer, iter->cpu, &iter->ts);
+	ftrace_enable_cpu();
 }
 
 static void *s_next(struct seq_file *m, void *v, loff_t *pos)
@@ -991,10 +1036,14 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 		iter->cpu = 0;
 		iter->idx = -1;
 
+		ftrace_disable_cpu();
+
 		for_each_tracing_cpu(cpu) {
 			ring_buffer_iter_reset(iter->buffer_iter[cpu]);
 		}
 
+		ftrace_enable_cpu();
+
 		for (p = iter; p && l < *pos; p = s_next(m, p, &l))
 			;
 
@@ -1242,7 +1291,16 @@ void trace_seq_print_cont(struct trace_seq *s, struct trace_iterator *iter)
 		cont = (struct trace_field_cont *)ent;
 		if (ok)
 			ok = (trace_seq_printf(s, "%s", cont->buf) > 0);
-		ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
+
+		ftrace_disable_cpu();
+
+		if (iter->buffer_iter[iter->cpu])
+			ring_buffer_read(iter->buffer_iter[iter->cpu], NULL);
+		else
+			ring_buffer_consume(iter->tr->buffer, iter->cpu, NULL);
+
+		ftrace_enable_cpu();
+
 		ent = peek_next_entry(iter, iter->cpu, NULL);
 	} while (ent && ent->type == TRACE_CONT);
 
@@ -1683,9 +1741,15 @@ static int trace_empty(struct trace_iterator *iter)
 	int cpu;
 
 	for_each_tracing_cpu(cpu) {
-		if (!ring_buffer_iter_empty(iter->buffer_iter[cpu]))
-			return 0;
+		if (iter->buffer_iter[cpu]) {
+			if (!ring_buffer_iter_empty(iter->buffer_iter[cpu]))
+				return 0;
+		} else {
+			if (!ring_buffer_empty_cpu(iter->tr->buffer, cpu))
+				return 0;
+		}
 	}
+
 	return TRACE_TYPE_HANDLED;
 }
 
@@ -1776,8 +1840,10 @@ __tracing_open(struct inode *inode, struct file *file, int *ret)
 	iter->pos = -1;
 
 	for_each_tracing_cpu(cpu) {
+
 		iter->buffer_iter[cpu] =
 			ring_buffer_read_start(iter->tr->buffer, cpu);
+
 		if (!iter->buffer_iter[cpu])
 			goto fail_buffer;
 	}
@@ -2341,7 +2407,6 @@ static atomic_t tracing_reader;
 static int tracing_open_pipe(struct inode *inode, struct file *filp)
 {
 	struct trace_iterator *iter;
-	int cpu;
 
 	if (tracing_disabled)
 		return -ENODEV;
@@ -2362,38 +2427,17 @@ static int tracing_open_pipe(struct inode *inode, struct file *filp)
 	iter->trace = current_trace;
 	filp->private_data = iter;
 
-	for_each_tracing_cpu(cpu) {
-		iter->buffer_iter[cpu] =
-			ring_buffer_read_start(iter->tr->buffer, cpu);
-		if (!iter->buffer_iter[cpu])
-			goto fail_buffer;
-	}
-
 	if (iter->trace->pipe_open)
 		iter->trace->pipe_open(iter);
 	mutex_unlock(&trace_types_lock);
 
 	return 0;
-
- fail_buffer:
-	for_each_tracing_cpu(cpu) {
-		if (iter->buffer_iter[cpu])
-			ring_buffer_read_finish(iter->buffer_iter[cpu]);
-	}
-	mutex_unlock(&trace_types_lock);
-
-	return -ENOMEM;
 }
 
 static int tracing_release_pipe(struct inode *inode, struct file *file)
 {
 	struct trace_iterator *iter = file->private_data;
-	int cpu;
 
-	for_each_tracing_cpu(cpu) {
-		if (iter->buffer_iter[cpu])
-			ring_buffer_read_finish(iter->buffer_iter[cpu]);
-	}
 	kfree(iter);
 	atomic_dec(&tracing_reader);
 
@@ -2429,7 +2473,6 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 		  size_t cnt, loff_t *ppos)
 {
 	struct trace_iterator *iter = filp->private_data;
-	unsigned long flags;
 #ifdef CONFIG_FTRACE
 	int ftrace_save;
 #endif
@@ -2528,7 +2571,6 @@ waitagain:
 	ftrace_enabled = 0;
 #endif
 	smp_wmb();
-	ring_buffer_lock(iter->tr->buffer, &flags);
 
 	while (find_next_entry_inc(iter) != NULL) {
 		enum print_line_t ret;
@@ -2547,7 +2589,6 @@ waitagain:
 			break;
 	}
 
-	ring_buffer_unlock(iter->tr->buffer, flags);
 #ifdef CONFIG_FTRACE
 	ftrace_enabled = ftrace_save;
 #endif
@@ -3010,8 +3051,8 @@ void ftrace_dump(void)
 	static struct trace_iterator iter;
 	static cpumask_t mask;
 	static int dump_ran;
-	unsigned long flags, irq_flags;
-	int cnt = 0;
+	unsigned long flags;
+	int cnt = 0, cpu;
 
 	/* only one dump */
 	spin_lock_irqsave(&ftrace_dump_lock, flags);
@@ -3023,6 +3064,10 @@ void ftrace_dump(void)
 	/* No turning back! */
 	ftrace_kill_atomic();
 
+	for_each_tracing_cpu(cpu) {
+		atomic_inc(&global_trace.data[cpu]->disabled);
+	}
+
 	printk(KERN_TRACE "Dumping ftrace buffer:\n");
 
 	iter.tr = &global_trace;
@@ -3037,8 +3082,6 @@ void ftrace_dump(void)
 
 	cpus_clear(mask);
 
-	ring_buffer_lock(iter.tr->buffer, &irq_flags);
-
 	while (!trace_empty(&iter)) {
 
 		if (!cnt)
@@ -3066,8 +3109,6 @@ void ftrace_dump(void)
 	else
 		printk(KERN_TRACE "---------------------------------\n");
 
-	ring_buffer_unlock(iter.tr->buffer, irq_flags);
-
  out:
 	spin_unlock_irqrestore(&ftrace_dump_lock, flags);
 }
-- 
cgit v1.2.3


From cb5ab74204a6e2579d1119bf1348eb806526b12b Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Thu, 2 Oct 2008 12:59:20 +0200
Subject: tracing/fastboot: change the printing of boot tracer according to
 bootgraph.pl

Change the boot tracer printing to make it parsable for
the scripts/bootgraph.pl script.

We have now to output two lines for each initcall, according to the
printk in do_one_initcall() in init/main.c
We need now the call's time and the return's time.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h    |  2 ++
 init/main.c               | 20 +++++++++-----------
 kernel/trace/trace_boot.c | 22 +++++++++++++++-------
 3 files changed, 26 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 91954eb6460f..4455490d91bd 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -216,6 +216,8 @@ struct boot_trace {
 	initcall_t		func;
 	int			result;
 	unsigned long long	duration;
+	ktime_t			calltime;
+	ktime_t			rettime;
 };
 
 #ifdef CONFIG_BOOT_TRACER
diff --git a/init/main.c b/init/main.c
index 1e39a1eab190..61eb66159391 100644
--- a/init/main.c
+++ b/init/main.c
@@ -706,34 +706,32 @@ __setup("initcall_debug", initcall_debug_setup);
 int do_one_initcall(initcall_t fn)
 {
 	int count = preempt_count();
-	ktime_t t0, t1, delta;
+	ktime_t delta;
 	char msgbuf[64];
-	int result;
 	struct boot_trace it;
 
 	if (initcall_debug) {
 		it.caller = task_pid_nr(current);
 		it.func = fn;
 		printk("calling  %pF @ %i\n", fn, it.caller);
-		t0 = ktime_get();
+		it.calltime = ktime_get();
 	}
 
-	result = fn();
+	it.result = fn();
 
 	if (initcall_debug) {
-		t1 = ktime_get();
-		delta = ktime_sub(t1, t0);
-		it.result = result;
+		it.rettime = ktime_get();
+		delta = ktime_sub(it.rettime, it.calltime);
 		it.duration = (unsigned long long) delta.tv64 >> 20;
 		printk("initcall %pF returned %d after %Ld msecs\n", fn,
-			result, it.duration);
+			it.result, it.duration);
 		trace_boot(&it);
 	}
 
 	msgbuf[0] = 0;
 
-	if (result && result != -ENODEV && initcall_debug)
-		sprintf(msgbuf, "error code %d ", result);
+	if (it.result && it.result != -ENODEV && initcall_debug)
+		sprintf(msgbuf, "error code %d ", it.result);
 
 	if (preempt_count() != count) {
 		strlcat(msgbuf, "preemption imbalance ", sizeof(msgbuf));
@@ -747,7 +745,7 @@ int do_one_initcall(initcall_t fn)
 		printk("initcall %pF returned with %s\n", fn, msgbuf);
 	}
 
-	return result;
+	return it.result;
 }
 
 
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index f2dac6f1cf06..7c15f3e68ba3 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -52,16 +52,24 @@ static enum print_line_t initcall_print_line(struct trace_iterator *iter)
 	struct trace_boot *field = (struct trace_boot *)entry;
 	struct boot_trace *it = &field->initcall;
 	struct trace_seq *s = &iter->seq;
+	struct timespec calltime = ktime_to_timespec(it->calltime);
+	struct timespec rettime = ktime_to_timespec(it->rettime);
 
 	if (entry->type == TRACE_BOOT) {
-		ret = trace_seq_printf(s, "%pF called from %i "
-				       "returned %d after %lld msecs\n",
-				       it->func, it->caller, it->result,
-				       it->duration);
-		if (ret)
-			return TRACE_TYPE_HANDLED;
-		else
+		ret = trace_seq_printf(s, "[%5ld.%06ld] calling  %pF @ %i\n",
+					  calltime.tv_sec,
+					  calltime.tv_nsec,
+					  it->func, it->caller);
+		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
+		ret = trace_seq_printf(s, "[%5ld.%06ld] initcall %pF "
+					  "returned %d after %lld msecs\n",
+					  rettime.tv_sec,
+					  rettime.tv_nsec,
+					  it->func, it->result, it->duration);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+		return TRACE_TYPE_HANDLED;
 	}
 	return TRACE_TYPE_UNHANDLED;
 }
-- 
cgit v1.2.3


From 5601020feb0c3010e9e3e0131e9697ac6a06777b Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Thu, 2 Oct 2008 13:26:05 +0200
Subject: tracing/fastboot: get the initcall name before it disappears

After some initcall traces, some initcall names may be inconsistent.
That's because these functions will disappear from the .init section
and also their name from the symbols table.

So we have to copy the name of the function in a buffer large enough
during the trace appending. It is not costly for the ring_buffer because
the number of initcall entries is commonly not really large.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h    |  7 ++++---
 init/main.c               |  3 +--
 kernel/trace/trace_boot.c | 14 ++++++++++----
 3 files changed, 15 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 4455490d91bd..e672e51c40a9 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -7,6 +7,7 @@
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/types.h>
+#include <linux/kallsyms.h>
 
 extern int ftrace_enabled;
 extern int
@@ -213,7 +214,7 @@ ftrace_init_module(unsigned long *start, unsigned long *end) { }
 
 struct boot_trace {
 	pid_t			caller;
-	initcall_t		func;
+	char 			func[KSYM_NAME_LEN];
 	int			result;
 	unsigned long long	duration;
 	ktime_t			calltime;
@@ -221,10 +222,10 @@ struct boot_trace {
 };
 
 #ifdef CONFIG_BOOT_TRACER
-extern void trace_boot(struct boot_trace *it);
+extern void trace_boot(struct boot_trace *it, initcall_t fn);
 extern void start_boot_trace(void);
 #else
-static inline void trace_boot(struct boot_trace *it) { }
+static inline void trace_boot(struct boot_trace *it, initcall_t fn) { }
 static inline void start_boot_trace(void) { }
 #endif
 
diff --git a/init/main.c b/init/main.c
index 61eb66159391..8e96a0ef17f4 100644
--- a/init/main.c
+++ b/init/main.c
@@ -712,7 +712,6 @@ int do_one_initcall(initcall_t fn)
 
 	if (initcall_debug) {
 		it.caller = task_pid_nr(current);
-		it.func = fn;
 		printk("calling  %pF @ %i\n", fn, it.caller);
 		it.calltime = ktime_get();
 	}
@@ -725,7 +724,7 @@ int do_one_initcall(initcall_t fn)
 		it.duration = (unsigned long long) delta.tv64 >> 20;
 		printk("initcall %pF returned %d after %Ld msecs\n", fn,
 			it.result, it.duration);
-		trace_boot(&it);
+		trace_boot(&it, fn);
 	}
 
 	msgbuf[0] = 0;
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index 7c15f3e68ba3..b9dc2c0093ab 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -8,6 +8,7 @@
 #include <linux/init.h>
 #include <linux/debugfs.h>
 #include <linux/ftrace.h>
+#include <linux/kallsyms.h>
 
 #include "trace.h"
 
@@ -56,17 +57,19 @@ static enum print_line_t initcall_print_line(struct trace_iterator *iter)
 	struct timespec rettime = ktime_to_timespec(it->rettime);
 
 	if (entry->type == TRACE_BOOT) {
-		ret = trace_seq_printf(s, "[%5ld.%06ld] calling  %pF @ %i\n",
+		ret = trace_seq_printf(s, "[%5ld.%06ld] calling  %s @ %i\n",
 					  calltime.tv_sec,
 					  calltime.tv_nsec,
 					  it->func, it->caller);
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
-		ret = trace_seq_printf(s, "[%5ld.%06ld] initcall %pF "
+
+		ret = trace_seq_printf(s, "[%5ld.%06ld] initcall %s "
 					  "returned %d after %lld msecs\n",
 					  rettime.tv_sec,
 					  rettime.tv_nsec,
 					  it->func, it->result, it->duration);
+
 		if (!ret)
 			return TRACE_TYPE_PARTIAL_LINE;
 		return TRACE_TYPE_HANDLED;
@@ -83,8 +86,7 @@ struct tracer boot_tracer __read_mostly =
 	.print_line	= initcall_print_line,
 };
 
-
-void trace_boot(struct boot_trace *it)
+void trace_boot(struct boot_trace *it, initcall_t fn)
 {
 	struct ring_buffer_event *event;
 	struct trace_boot *entry;
@@ -95,6 +97,10 @@ void trace_boot(struct boot_trace *it)
 	if (!trace_boot_enabled)
 		return;
 
+	/* Get its name now since this function could
+	 * disappear because it is in the .init section.
+	 */
+	sprint_symbol(it->func, (unsigned long)fn);
 	preempt_disable();
 	data = tr->data[smp_processor_id()];
 
-- 
cgit v1.2.3


From 3e1932ad59726d794a865cc159c0593d54bf0cb6 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Thu, 2 Oct 2008 17:45:47 +0200
Subject: tracing/fastboot: build fix

fix:

 In file included from kernel/sysctl.c:52:
 include/linux/ftrace.h:217: error: 'KSYM_NAME_LEN' undeclared here (not in a function)

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e672e51c40a9..deded114dffd 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1,14 +1,14 @@
 #ifndef _LINUX_FTRACE_H
 #define _LINUX_FTRACE_H
 
-#ifdef CONFIG_FTRACE
-
 #include <linux/linkage.h>
 #include <linux/fs.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/kallsyms.h>
 
+#ifdef CONFIG_FTRACE
+
 extern int ftrace_enabled;
 extern int
 ftrace_enable_sysctl(struct ctl_table *table, int write,
-- 
cgit v1.2.3


From eb7fa935274bb233686fdf7a53f40c5d9ee76ed6 Mon Sep 17 00:00:00 2001
From: Steven Noonan <steven@uplinklabs.net>
Date: Thu, 2 Oct 2008 12:00:07 -0700
Subject: ftrace: ktime.h not included in ftrace.h

Including <linux/ktime.h> eliminates the following error:

include/linux/ftrace.h:220: error: expected specifier-qualifier-list
before 'ktime_t'

Signed-off-by: Steven Noonan <steven@uplinklabs.net>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index deded114dffd..ed53265d1f63 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -3,6 +3,7 @@
 
 #include <linux/linkage.h>
 #include <linux/fs.h>
+#include <linux/ktime.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/kallsyms.h>
-- 
cgit v1.2.3


From 097d036a2f25eecc42435c57e010aaf4a2eed2d9 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <fweisbec@gmail.com>
Date: Fri, 3 Oct 2008 15:39:21 +0200
Subject: tracing/fastboot: only trace non-module initcalls

At this time, only built-in initcalls interest us.
We can't really produce a relevant graph if we include
the modules initcall too.

I had good results after this patch (see svg in attachment).

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h    |  2 ++
 init/main.c               |  1 +
 kernel/trace/trace_boot.c | 11 ++++++++---
 3 files changed, 11 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index ed53265d1f63..5812dba4ee24 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -225,9 +225,11 @@ struct boot_trace {
 #ifdef CONFIG_BOOT_TRACER
 extern void trace_boot(struct boot_trace *it, initcall_t fn);
 extern void start_boot_trace(void);
+extern void stop_boot_trace(void);
 #else
 static inline void trace_boot(struct boot_trace *it, initcall_t fn) { }
 static inline void start_boot_trace(void) { }
+static inline void stop_boot_trace(void) { }
 #endif
 
 
diff --git a/init/main.c b/init/main.c
index 8e96a0ef17f4..e7939de80f3e 100644
--- a/init/main.c
+++ b/init/main.c
@@ -886,6 +886,7 @@ static int __init kernel_init(void * unused)
 	 * we're essentially up and running. Get rid of the
 	 * initmem segments and start the user-mode stuff..
 	 */
+	stop_boot_trace();
 	init_post();
 	return 0;
 }
diff --git a/kernel/trace/trace_boot.c b/kernel/trace/trace_boot.c
index b9dc2c0093ab..a7efe3559654 100644
--- a/kernel/trace/trace_boot.c
+++ b/kernel/trace/trace_boot.c
@@ -22,11 +22,16 @@ void start_boot_trace(void)
 	trace_boot_enabled = 1;
 }
 
-void stop_boot_trace(struct trace_array *tr)
+void stop_boot_trace(void)
 {
 	trace_boot_enabled = 0;
 }
 
+void reset_boot_trace(struct trace_array *tr)
+{
+	stop_boot_trace();
+}
+
 static void boot_trace_init(struct trace_array *tr)
 {
 	int cpu;
@@ -43,7 +48,7 @@ static void boot_trace_ctrl_update(struct trace_array *tr)
 	if (tr->ctrl)
 		start_boot_trace();
 	else
-		stop_boot_trace(tr);
+		stop_boot_trace();
 }
 
 static enum print_line_t initcall_print_line(struct trace_iterator *iter)
@@ -81,7 +86,7 @@ struct tracer boot_tracer __read_mostly =
 {
 	.name		= "initcall",
 	.init		= boot_trace_init,
-	.reset		= stop_boot_trace,
+	.reset		= reset_boot_trace,
 	.ctrl_update	= boot_trace_ctrl_update,
 	.print_line	= initcall_print_line,
 };
-- 
cgit v1.2.3


From ca538f6bbe583406f941f3041d40c41f9a13d1de Mon Sep 17 00:00:00 2001
From: Tim Bird <tim.bird@am.sony.com>
Date: Thu, 9 Oct 2008 15:23:05 -0700
Subject: tracing/fastboot: add better resolution to initcall debug/tracing

Change the time resolution for initcall_debug to microseconds, from
milliseconds.  This is handy to determine which initcalls you want to work
on for faster booting.

One one of my test machines, over 90% of the initcalls are less than a
millisecond and (without this patch) these are all reported as 0 msecs.
Working on the 900 us ones is more important than the 4 us ones.

With 'quiet' on the kernel command line, this adds no significant overhead
to kernel boot time.

Signed-off-by: Tim Bird <tim.bird@am.sony.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/ftrace.h | 4 ++--
 init/main.c            | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 5812dba4ee24..a3d46151be19 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -215,9 +215,9 @@ ftrace_init_module(unsigned long *start, unsigned long *end) { }
 
 struct boot_trace {
 	pid_t			caller;
-	char 			func[KSYM_NAME_LEN];
+	char			func[KSYM_NAME_LEN];
 	int			result;
-	unsigned long long	duration;
+	unsigned long long	duration;		/* usecs */
 	ktime_t			calltime;
 	ktime_t			rettime;
 };
diff --git a/init/main.c b/init/main.c
index e7939de80f3e..b2e7ff4a5349 100644
--- a/init/main.c
+++ b/init/main.c
@@ -721,8 +721,8 @@ int do_one_initcall(initcall_t fn)
 	if (initcall_debug) {
 		it.rettime = ktime_get();
 		delta = ktime_sub(it.rettime, it.calltime);
-		it.duration = (unsigned long long) delta.tv64 >> 20;
-		printk("initcall %pF returned %d after %Ld msecs\n", fn,
+		it.duration = (unsigned long long) delta.tv64 >> 10;
+		printk("initcall %pF returned %d after %Ld usecs\n", fn,
 			it.result, it.duration);
 		trace_boot(&it, fn);
 	}
-- 
cgit v1.2.3


From bfadadfccc19e36f7d600c5ce7b3e5ba5197fbf0 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Date: Fri, 10 Oct 2008 03:48:25 -0400
Subject: markers: fix synchronize marker unregister static inline

Use a #define for synchronize marker unregister to fix include dependencies.

Fixes the slab circular inclusion which triggers when slab.git is combined
with tracing.git, where rcupdate includes slab, which includes markers
which includes rcupdate.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/marker.h | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/marker.h b/include/linux/marker.h
index 38e32e781ed7..889196c7fbb1 100644
--- a/include/linux/marker.h
+++ b/include/linux/marker.h
@@ -13,7 +13,6 @@
  */
 
 #include <linux/types.h>
-#include <linux/rcupdate.h>
 
 struct module;
 struct marker;
@@ -166,9 +165,6 @@ extern void *marker_get_private_data(const char *name, marker_probe_func *probe,
  * unregistration and the end of module exit to make sure there is no caller
  * executing a probe when it is freed.
  */
-static inline void marker_synchronize_unregister(void)
-{
-	synchronize_sched();
-}
+#define marker_synchronize_unregister() synchronize_sched()
 
 #endif
-- 
cgit v1.2.3


From f2461fc82a083dd60062e05e704c5fcc1c658ba1 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Date: Mon, 6 Oct 2008 10:33:00 -0400
Subject: tracepoints: tracepoint_synchronize_unregister()

Create tracepoint_synchronize_unregister() which must be called before the end
of exit() to make sure every probe callers have exited the non preemptible
section and thus are not executing the probe code anymore.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/tracepoint.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index e623a6fca5c3..199f4c207c1e 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -124,4 +124,11 @@ extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
 extern int tracepoint_get_iter_range(struct tracepoint **tracepoint,
 	struct tracepoint *begin, struct tracepoint *end);
 
+/*
+ * tracepoint_synchronize_unregister must be called between the last tracepoint
+ * probe unregistration and the end of module exit to make sure there is no
+ * caller executing a probe when it is freed.
+ */
+#define tracepoint_synchronize_unregister() synchronize_sched()
+
 #endif
-- 
cgit v1.2.3


From 231375cc5cc3549bb413f94a164bdcbd5f9ce943 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Date: Fri, 3 Oct 2008 15:01:33 -0400
Subject: tracepoints: synchronize unregister static inline

Turn tracepoint synchronize unregister into a static inline. There is no
reason to keep it as a macro over a static inline.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/tracepoint.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index 199f4c207c1e..c5bb39c7a770 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -129,6 +129,9 @@ extern int tracepoint_get_iter_range(struct tracepoint **tracepoint,
  * probe unregistration and the end of module exit to make sure there is no
  * caller executing a probe when it is freed.
  */
-#define tracepoint_synchronize_unregister() synchronize_sched()
+static inline void tracepoint_synchronize_unregister(void)
+{
+	synchronize_sched();
+}
 
 #endif
-- 
cgit v1.2.3


From 6028aa01f759a1dae11e5d0e495b3dc9d2b0a47b Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <shimoda.yoshihiro@renesas.com>
Date: Tue, 14 Oct 2008 21:23:26 +0900
Subject: [MTD] [NAND] sh_flctl: add support for Renesas SuperH FLCTL

Several Renesas SuperH CPU has FLCTL. The FLCTL support NAND Flash.
This driver support SH7723.

Signed-off-by: Yoshihiro Shimoda <shimoda.yoshihiro@renesas.com>
Acked-by: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/mtd/nand/Kconfig     |   7 +
 drivers/mtd/nand/Makefile    |   1 +
 drivers/mtd/nand/sh_flctl.c  | 301 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/sh_flctl.h | 125 ++++++++++++++++++
 4 files changed, 434 insertions(+)
 create mode 100644 drivers/mtd/nand/sh_flctl.c
 create mode 100644 include/linux/mtd/sh_flctl.h

(limited to 'include')

diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 82815dd64bf6..89b4d39386ab 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -407,4 +407,11 @@ config MTD_NAND_MXC
 	  This enables the driver for the NAND flash controller on the
 	  MXC processors.
 
+config MTD_NAND_SH_FLCTL
+	tristate "Support for NAND on Renesas SuperH FLCTL"
+	depends on MTD_NAND && SUPERH && CPU_SUBTYPE_SH7723
+	help
+	  Several Renesas SuperH CPU has FLCTL. This option enables support
+	  for NAND Flash using FLCTL. This driver support SH7723.
+
 endif # MTD_NAND
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index e0fee048c1b4..9bfeca324b32 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_MTD_NAND_PASEMI)		+= pasemi_nand.o
 obj-$(CONFIG_MTD_NAND_ORION)		+= orion_nand.o
 obj-$(CONFIG_MTD_NAND_FSL_ELBC)		+= fsl_elbc_nand.o
 obj-$(CONFIG_MTD_NAND_FSL_UPM)		+= fsl_upm.o
+obj-$(CONFIG_MTD_NAND_SH_FLCTL)		+= sh_flctl.o
 obj-$(CONFIG_MTD_NAND_MXC)		+= mxc_nand.o
 
 nand-objs := nand_base.o nand_bbt.o
diff --git a/drivers/mtd/nand/sh_flctl.c b/drivers/mtd/nand/sh_flctl.c
new file mode 100644
index 000000000000..600a76f5580e
--- /dev/null
+++ b/drivers/mtd/nand/sh_flctl.c
@@ -0,0 +1,301 @@
+/*
+ * SuperH FLCTL nand controller
+ *
+ * Copyright © 2008 Renesas Solutions Corp.
+ * Copyright © 2008 Atom Create Engineering Co., Ltd.
+ *
+ * Based on fsl_elbc_nand.c, Copyright © 2006-2007 Freescale Semiconductor
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/sh_flctl.h>
+
+static struct nand_ecclayout flctl_4secc_oob_16 = {
+	.eccbytes = 10,
+	.eccpos = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9},
+	.oobfree = {
+		{.offset = 12,
+		. length = 4} },
+};
+
+static struct nand_ecclayout flctl_4secc_oob_64 = {
+	.eccbytes = 10,
+	.eccpos = {48, 49, 50, 51, 52, 53, 54, 55, 56, 57},
+	.oobfree = {
+		{.offset = 60,
+		. length = 4} },
+};
+
+static uint8_t scan_ff_pattern[] = { 0xff, 0xff };
+
+static struct nand_bbt_descr flctl_4secc_smallpage = {
+	.options = NAND_BBT_SCAN2NDPAGE,
+	.offs = 11,
+	.len = 1,
+	.pattern = scan_ff_pattern,
+};
+
+static struct nand_bbt_descr flctl_4secc_largepage = {
+	.options = 0,
+	.offs = 58,
+	.len = 2,
+	.pattern = scan_ff_pattern,
+};
+
+static void empty_fifo(struct sh_flctl *flctl)
+{
+	writel(0x000c0000, FLINTDMACR(flctl));	/* FIFO Clear */
+	writel(0x00000000, FLINTDMACR(flctl));	/* Clear Error flags */
+}
+
+static void start_translation(struct sh_flctl *flctl)
+{
+	writeb(TRSTRT, FLTRCR(flctl));
+}
+
+static void wait_completion(struct sh_flctl *flctl)
+{
+	uint32_t timeout = LOOP_TIMEOUT_MAX;
+
+	while (timeout--) {
+		if (readb(FLTRCR(flctl)) & TREND) {
+			writeb(0x0, FLTRCR(flctl));
+			return;
+		}
+		udelay(1);
+	}
+
+	printk(KERN_ERR "wait_completion(): Timeout occured \n");
+	writeb(0x0, FLTRCR(flctl));
+}
+
+static void set_addr(struct mtd_info *mtd, int column, int page_addr)
+{
+	struct sh_flctl *flctl = mtd_to_flctl(mtd);
+	uint32_t addr = 0;
+
+	if (column == -1) {
+		addr = page_addr;	/* ERASE1 */
+	} else if (page_addr != -1) {
+		/* SEQIN, READ0, etc.. */
+		if (flctl->page_size) {
+			addr = column & 0x0FFF;
+			addr |= (page_addr & 0xff) << 16;
+			addr |= ((page_addr >> 8) & 0xff) << 24;
+			/* big than 128MB */
+			if (flctl->rw_ADRCNT == ADRCNT2_E) {
+				uint32_t 	addr2;
+				addr2 = (page_addr >> 16) & 0xff;
+				writel(addr2, FLADR2(flctl));
+			}
+		} else {
+			addr = column;
+			addr |= (page_addr & 0xff) << 8;
+			addr |= ((page_addr >> 8) & 0xff) << 16;
+			addr |= ((page_addr >> 16) & 0xff) << 24;
+		}
+	}
+	writel(addr, FLADR(flctl));
+}
+
+static void wait_rfifo_ready(struct sh_flctl *flctl)
+{
+	uint32_t timeout = LOOP_TIMEOUT_MAX;
+
+	while (timeout--) {
+		uint32_t val;
+		/* check FIFO */
+		val = readl(FLDTCNTR(flctl)) >> 16;
+		if (val & 0xFF)
+			return;
+		udelay(1);
+	}
+	printk(KERN_ERR "wait_rfifo_ready(): Timeout occured \n");
+}
+
+static void wait_wfifo_ready(struct sh_flctl *flctl)
+{
+	uint32_t len, timeout = LOOP_TIMEOUT_MAX;
+
+	while (timeout--) {
+		/* check FIFO */
+		len = (readl(FLDTCNTR(flctl)) >> 16) & 0xFF;
+		if (len >= 4)
+			return;
+		udelay(1);
+	}
+	printk(KERN_ERR "wait_wfifo_ready(): Timeout occured \n");
+}
+
+static int wait_recfifo_ready(struct sh_flctl *flctl)
+{
+	uint32_t timeout = LOOP_TIMEOUT_MAX;
+	int checked[4];
+	void __iomem *ecc_reg[4];
+	int i;
+	uint32_t data, size;
+
+	memset(checked, 0, sizeof(checked));
+
+	while (timeout--) {
+		size = readl(FLDTCNTR(flctl)) >> 24;
+		if (size & 0xFF)
+			return 0;	/* success */
+
+		if (readl(FL4ECCCR(flctl)) & _4ECCFA)
+			return 1;	/* can't correct */
+
+		udelay(1);
+		if (!(readl(FL4ECCCR(flctl)) & _4ECCEND))
+			continue;
+
+		/* start error correction */
+		ecc_reg[0] = FL4ECCRESULT0(flctl);
+		ecc_reg[1] = FL4ECCRESULT1(flctl);
+		ecc_reg[2] = FL4ECCRESULT2(flctl);
+		ecc_reg[3] = FL4ECCRESULT3(flctl);
+
+		for (i = 0; i < 3; i++) {
+			data = readl(ecc_reg[i]);
+			if (data != INIT_FL4ECCRESULT_VAL && !checked[i]) {
+				uint8_t org;
+				int index;
+
+				index = data >> 16;
+				org = flctl->done_buff[index];
+				flctl->done_buff[index] = org ^ (data & 0xFF);
+				checked[i] = 1;
+			}
+		}
+
+		writel(0, FL4ECCCR(flctl));
+	}
+
+	printk(KERN_ERR "wait_recfifo_ready(): Timeout occured \n");
+	return 1;	/* timeout */
+}
+
+static void wait_wecfifo_ready(struct sh_flctl *flctl)
+{
+	uint32_t timeout = LOOP_TIMEOUT_MAX;
+	uint32_t len;
+
+	while (timeout--) {
+		/* check FLECFIFO */
+		len = (readl(FLDTCNTR(flctl)) >> 24) & 0xFF;
+		if (len >= 4)
+			return;
+		udelay(1);
+	}
+	printk(KERN_ERR "wait_wecfifo_ready(): Timeout occured \n");
+}
+
+static void read_datareg(struct sh_flctl *flctl, int offset)
+{
+	unsigned long data;
+	unsigned long *buf = (unsigned long *)&flctl->done_buff[offset];
+
+	wait_completion(flctl);
+
+	data = readl(FLDATAR(flctl));
+	*buf = le32_to_cpu(data);
+}
+
+static void read_fiforeg(struct sh_flctl *flctl, int rlen, int offset)
+{
+	int i, len_4align;
+	unsigned long *buf = (unsigned long *)&flctl->done_buff[offset];
+	void *fifo_addr = (void *)FLDTFIFO(flctl);
+
+	len_4align = (rlen + 3) / 4;
+
+	for (i = 0; i < len_4align; i++) {
+		wait_rfifo_ready(flctl);
+		buf[i] = readl(fifo_addr);
+		buf[i] = be32_to_cpu(buf[i]);
+	}
+}
+
+static int read_ecfiforeg(struct sh_flctl *flctl, uint8_t *buff)
+{
+	int i;
+	unsigned long *ecc_buf = (unsigned long *)buff;
+	void *fifo_addr = (void *)FLECFIFO(flctl);
+
+	for (i = 0; i < 4; i++) {
+		if (wait_recfifo_ready(flctl))
+			return 1;
+		ecc_buf[i] = readl(fifo_addr);
+		ecc_buf[i] = be32_to_cpu(ecc_buf[i]);
+	}
+
+	return 0;
+}
+
+static void write_fiforeg(struct sh_flctl *flctl, int rlen, int offset)
+{
+	int i, len_4align;
+	unsigned long *data = (unsigned long *)&flctl->done_buff[offset];
+	void *fifo_addr = (void *)FLDTFIFO(flctl);
+
+	len_4align = (rlen + 3) / 4;
+	for (i = 0; i < len_4align; i++) {
+		wait_wfifo_ready(flctl);
+		writel(cpu_to_be32(data[i]), fifo_addr);
+	}
+}
+
+static void set_cmd_regs(struct mtd_info *mtd, uint32_t cmd, uint32_t flcmcdr_val)
+{
+	struct sh_flctl *flctl = mtd_to_flctl(mtd);
+	uint32_t flcmncr_val = readl(FLCMNCR(flctl));
+	uint32_t flcmdcr_val, addr_len_bytes = 0;
+
+	/* Set SNAND bit if page size is 2048byte */
+	if (flctl->page_size)
+		flcmncr_val |= SNAND_E;
+	else
+		flcmncr_val &= ~SNAND_E;
+
+	/* default FLCMDCR val */
+	flcmdcr_val = DOCMD1_E | DOADR_E;
+
+	/* Set for FLCMDCR */
+	switch (cmd) {
+	case NAND_CMD_ERASE1:
+		addr_len_bytes = flctl->erase_ADRCNT;
+		flcmdcr_val |= DOCMD2_E;
+		break;
+	case NAND_CMD_READ0:
+	case NAND_CMD_READOOB:
+		addr_len_bytes = flctl->rw_ADRCNT;
+		flcmdcr_val |= CDSRC_E;
+		break;
+	case NAND_CMD_SEQIN:
+		/* This case is that cmd is READ0 or READ1 or READ00 */
+		flcmdcr_val &= ~DOADR_E;	/* ONLY execute 1st cmd */
+		break;
+	case NAND_CMD_PAGEPROG:
+		addr_len_bytes = flctl->rw_ADRCNT;
diff --git a/include/linux/mtd/sh_flctl.h b/include/linux/mtd/sh_flctl.h
new file mode 100644
index 000000000000..e77c1cea404d
--- /dev/null
+++ b/include/linux/mtd/sh_flctl.h
@@ -0,0 +1,125 @@
+/*
+ * SuperH FLCTL nand controller
+ *
+ * Copyright © 2008 Renesas Solutions Corp.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#ifndef __SH_FLCTL_H__
+#define __SH_FLCTL_H__
+
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
+#include <linux/mtd/partitions.h>
+
+/* FLCTL registers */
+#define FLCMNCR(f)		(f->reg + 0x0)
+#define FLCMDCR(f)		(f->reg + 0x4)
+#define FLCMCDR(f)		(f->reg + 0x8)
+#define FLADR(f)		(f->reg + 0xC)
+#define FLADR2(f)		(f->reg + 0x3C)
+#define FLDATAR(f)		(f->reg + 0x10)
+#define FLDTCNTR(f)		(f->reg + 0x14)
+#define FLINTDMACR(f)		(f->reg + 0x18)
+#define FLBSYTMR(f)		(f->reg + 0x1C)
+#define FLBSYCNT(f)		(f->reg + 0x20)
+#define FLDTFIFO(f)		(f->reg + 0x24)
+#define FLECFIFO(f)		(f->reg + 0x28)
+#define FLTRCR(f)		(f->reg + 0x2C)
+#define	FL4ECCRESULT0(f)	(f->reg + 0x80)
+#define	FL4ECCRESULT1(f)	(f->reg + 0x84)
+#define	FL4ECCRESULT2(f)	(f->reg + 0x88)
+#define	FL4ECCRESULT3(f)	(f->reg + 0x8C)
+#define	FL4ECCCR(f)		(f->reg + 0x90)
+#define	FL4ECCCNT(f)		(f->reg + 0x94)
+#define	FLERRADR(f)		(f->reg + 0x98)
+
+/* FLCMNCR control bits */
+#define ECCPOS2		(0x1 << 25)
+#define _4ECCCNTEN	(0x1 << 24)
+#define _4ECCEN		(0x1 << 23)
+#define _4ECCCORRECT	(0x1 << 22)
+#define SNAND_E		(0x1 << 18)	/* SNAND (0=512 1=2048)*/
+#define QTSEL_E		(0x1 << 17)
+#define ENDIAN		(0x1 << 16)	/* 1 = little endian */
+#define FCKSEL_E	(0x1 << 15)
+#define ECCPOS_00	(0x00 << 12)
+#define ECCPOS_01	(0x01 << 12)
+#define ECCPOS_02	(0x02 << 12)
+#define ACM_SACCES_MODE	(0x01 << 10)
+#define NANWF_E		(0x1 << 9)
+#define SE_D		(0x1 << 8)	/* Spare area disable */
+#define	CE1_ENABLE	(0x1 << 4)	/* Chip Enable 1 */
+#define	CE0_ENABLE	(0x1 << 3)	/* Chip Enable 0 */
+#define	TYPESEL_SET	(0x1 << 0)
+
+/* FLCMDCR control bits */
+#define ADRCNT2_E	(0x1 << 31)	/* 5byte address enable */
+#define ADRMD_E		(0x1 << 26)	/* Sector address access */
+#define CDSRC_E		(0x1 << 25)	/* Data buffer selection */
+#define DOSR_E		(0x1 << 24)	/* Status read check */
+#define SELRW		(0x1 << 21)	/*  0:read 1:write */
+#define DOADR_E		(0x1 << 20)	/* Address stage execute */
+#define ADRCNT_1	(0x00 << 18)	/* Address data bytes: 1byte */
+#define ADRCNT_2	(0x01 << 18)	/* Address data bytes: 2byte */
+#define ADRCNT_3	(0x02 << 18)	/* Address data bytes: 3byte */
+#define ADRCNT_4	(0x03 << 18)	/* Address data bytes: 4byte */
+#define DOCMD2_E	(0x1 << 17)	/* 2nd cmd stage execute */
+#define DOCMD1_E	(0x1 << 16)	/* 1st cmd stage execute */
+
+/* FLTRCR control bits */
+#define TRSTRT		(0x1 << 0)	/* translation start */
+#define TREND		(0x1 << 1)	/* translation end */
+
+/* FL4ECCCR control bits */
+#define	_4ECCFA		(0x1 << 2)	/* 4 symbols correct fault */
+#define	_4ECCEND	(0x1 << 1)	/* 4 symbols end */
+#define	_4ECCEXST	(0x1 << 0)	/* 4 symbols exist */
+
+#define INIT_FL4ECCRESULT_VAL	0x03FF03FF
+#define LOOP_TIMEOUT_MAX	0x00010000
+
+#define mtd_to_flctl(mtd)	container_of(mtd, struct sh_flctl, mtd)
+
+struct sh_flctl {
+	struct mtd_info		mtd;
+	struct nand_chip	chip;
+	void __iomem		*reg;
+
+	uint8_t	done_buff[2048 + 64];	/* max size 2048 + 64 */
+	int	read_bytes;
+	int	index;
+	int	seqin_column;		/* column in SEQIN cmd */
+	int	seqin_page_addr;	/* page_addr in SEQIN cmd */
+	uint32_t seqin_read_cmd;		/* read cmd in SEQIN cmd */
+	int	erase1_page_addr;	/* page_addr in ERASE1 cmd */
+	uint32_t erase_ADRCNT;		/* bits of FLCMDCR in ERASE1 cmd */
+	uint32_t rw_ADRCNT;	/* bits of FLCMDCR in READ WRITE cmd */
+
+	int	hwecc_cant_correct[4];
+
+	unsigned page_size:1;	/* NAND page size (0 = 512, 1 = 2048) */
+	unsigned hwecc:1;	/* Hardware ECC (0 = disabled, 1 = enabled) */
+};
+
+struct sh_flctl_platform_data {
+	struct mtd_partition	*parts;
+	int			nr_parts;
+	unsigned long		flcmncr_val;
+
+	unsigned has_hwecc:1;
+};
+
+#endif	/* __SH_FLCTL_H__ */
-- 
cgit v1.2.3


From 74baaaaec8b4f22e1ae279f5ecca4ff705b28912 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Tue, 14 Oct 2008 09:21:02 -0400
Subject: vfs: Remove the range_cont writeback mode.

Ext4 was the only user of range_cont writeback mode and ext4 switched
to a different method. So remove the range_cont mode which is not used
in the kernel.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
CC: linux-fsdevel@vger.kernel.org
---
 include/linux/writeback.h | 1 -
 mm/page-writeback.c       | 2 --
 2 files changed, 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 12b15c561a1f..bd91987c065f 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -63,7 +63,6 @@ struct writeback_control {
 	unsigned for_writepages:1;	/* This is a writepages() call */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 	unsigned more_io:1;		/* more io to be dispatched */
-	unsigned range_cont:1;
 };
 
 /*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index c130a137c129..e373f14d26f6 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -961,8 +961,6 @@ retry:
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
 		mapping->writeback_index = index;
 
-	if (wbc->range_cont)
-		wbc->range_start = index << PAGE_CACHE_SHIFT;
 	return ret;
 }
 EXPORT_SYMBOL(write_cache_pages);
-- 
cgit v1.2.3


From 14ac12de07112e727c161644798415368dc4b343 Mon Sep 17 00:00:00 2001
From: "Robert P. J. Day" <rpjday@crashcourse.ca>
Date: Wed, 30 Jul 2008 12:48:53 -0700
Subject: XTENSA: warn about including <asm/rwsem.h> directly.

For consistency with other architectures, warn about including
<asm-xtensa/rwsem.h> directly.

Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Chris Zankel <chris@zankel.net>
---
 include/asm-xtensa/rwsem.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/asm-xtensa/rwsem.h b/include/asm-xtensa/rwsem.h
index 0aad3a587551..e39edf5c86f2 100644
--- a/include/asm-xtensa/rwsem.h
+++ b/include/asm-xtensa/rwsem.h
@@ -13,6 +13,10 @@
 #ifndef _XTENSA_RWSEM_H
 #define _XTENSA_RWSEM_H
 
+#ifndef _LINUX_RWSEM_H
+#error "Please don't include <asm/rwsem.h> directly, use <linux/rwsem.h> instead."
+#endif
+
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <asm/atomic.h>
-- 
cgit v1.2.3


From 40b8606253552109815786e5d4b0de98782d31f5 Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Wed, 15 Oct 2008 14:20:28 +1100
Subject: DECLARE_PER_CPU needs linux/percpu.h

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
---
 include/linux/hrtimer.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 508ce20b8f9c..1e6f731381d9 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -20,6 +20,8 @@
 #include <linux/init.h>
 #include <linux/list.h>
 #include <linux/wait.h>
+#include <linux/percpu.h>
+
 
 struct hrtimer_clock_base;
 struct hrtimer_cpu_base;
-- 
cgit v1.2.3


From 29d434b39c807320fbe4bcdce0ab98a0b9fcb285 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 16 Oct 2008 16:08:57 +0200
Subject: fuse: add include protectors

Add include protectors to include/linux/fuse.h and fs/fuse/fuse_i.h.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
---
 fs/fuse/fuse_i.h     | 5 +++++
 include/linux/fuse.h | 5 +++++
 2 files changed, 10 insertions(+)

(limited to 'include')

diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 3a876076bdd1..35accfdd747f 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -6,6 +6,9 @@
   See the file COPYING.
 */
 
+#ifndef _FS_FUSE_I_H
+#define _FS_FUSE_I_H
+
 #include <linux/fuse.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
@@ -655,3 +658,5 @@ void fuse_set_nowrite(struct inode *inode);
 void fuse_release_nowrite(struct inode *inode);
 
 u64 fuse_get_attr_version(struct fuse_conn *fc);
+
+#endif /* _FS_FUSE_I_H */
diff --git a/include/linux/fuse.h b/include/linux/fuse.h
index 265635dc9908..8bc1101e9b35 100644
--- a/include/linux/fuse.h
+++ b/include/linux/fuse.h
@@ -19,6 +19,9 @@
  *  - add file flags field to fuse_read_in and fuse_write_in
  */
 
+#ifndef _LINUX_FUSE_H
+#define _LINUX_FUSE_H
+
 #include <asm/types.h>
 #include <linux/major.h>
 
@@ -409,3 +412,5 @@ struct fuse_dirent {
 #define FUSE_DIRENT_ALIGN(x) (((x) + sizeof(__u64) - 1) & ~(sizeof(__u64) - 1))
 #define FUSE_DIRENT_SIZE(d) \
 	FUSE_DIRENT_ALIGN(FUSE_NAME_OFFSET + (d)->namelen)
+
+#endif /* _LINUX_FUSE_H */
-- 
cgit v1.2.3


From a7c1b990f71574e077b94ce4582e2cf11cb891fe Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Thu, 16 Oct 2008 16:08:57 +0200
Subject: fuse: implement nonseekable open

Let the client request nonseekable open using FOPEN_NONSEEKABLE and
call nonseekable_open() on the file if requested.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
---
 fs/fuse/file.c       | 2 ++
 include/linux/fuse.h | 7 ++++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 98079aa800e8..34930a964b82 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -101,6 +101,8 @@ void fuse_finish_open(struct inode *inode, struct file *file,
 		file->f_op = &fuse_direct_io_file_operations;
 	if (!(outarg->open_flags & FOPEN_KEEP_CACHE))
 		invalidate_inode_pages2(inode->i_mapping);
+	if (outarg->open_flags & FOPEN_NONSEEKABLE)
+		nonseekable_open(inode, file);
 	ff->fh = outarg->fh;
 	file->private_data = fuse_file_get(ff);
 }
diff --git a/include/linux/fuse.h b/include/linux/fuse.h
index 8bc1101e9b35..350fe9767bbc 100644
--- a/include/linux/fuse.h
+++ b/include/linux/fuse.h
@@ -17,6 +17,9 @@
  *  - add lock_owner field to fuse_setattr_in, fuse_read_in and fuse_write_in
  *  - add blksize field to fuse_attr
  *  - add file flags field to fuse_read_in and fuse_write_in
+ *
+ * 7.10
+ *  - add nonseekable open flag
  */
 
 #ifndef _LINUX_FUSE_H
@@ -29,7 +32,7 @@
 #define FUSE_KERNEL_VERSION 7
 
 /** Minor version number of this interface */
-#define FUSE_KERNEL_MINOR_VERSION 9
+#define FUSE_KERNEL_MINOR_VERSION 10
 
 /** The node ID of the root inode */
 #define FUSE_ROOT_ID 1
@@ -101,9 +104,11 @@ struct fuse_file_lock {
  *
  * FOPEN_DIRECT_IO: bypass page cache for this open file
  * FOPEN_KEEP_CACHE: don't invalidate the data cache on open
+ * FOPEN_NONSEEKABLE: the file is not seekable
  */
 #define FOPEN_DIRECT_IO		(1 << 0)
 #define FOPEN_KEEP_CACHE	(1 << 1)
+#define FOPEN_NONSEEKABLE	(1 << 2)
 
 /**
  * INIT request/reply flags
-- 
cgit v1.2.3


From 17bc6c30cf6bfffd816bdc53682dd46fc34a2cf4 Mon Sep 17 00:00:00 2001
From: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Date: Thu, 16 Oct 2008 10:09:17 -0400
Subject: vfs: Add no_nrwrite_index_update writeback control flag

If no_nrwrite_index_update is set we don't update nr_to_write and
address space writeback_index in write_cache_pages.  This change
enables a file system to skip these updates in write_cache_pages and do
them in the writepages() callback.  This patch will be followed by an
ext4 patch that make use of these new flags.

Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
CC: linux-fsdevel@vger.kernel.org
---
 include/linux/writeback.h |  9 +++++++++
 mm/page-writeback.c       | 10 +++++++---
 2 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index bd91987c065f..e585657e9831 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -63,6 +63,15 @@ struct writeback_control {
 	unsigned for_writepages:1;	/* This is a writepages() call */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 	unsigned more_io:1;		/* more io to be dispatched */
+	/*
+	 * write_cache_pages() won't update wbc->nr_to_write and
+	 * mapping->writeback_index if no_nrwrite_index_update
+	 * is set.  write_cache_pages() may write more than we
+	 * requested and we want to make sure nr_to_write and
+	 * writeback_index are updated in a consistent manner
+	 * so we use a single control to update them
+	 */
+	unsigned no_nrwrite_index_update:1;
 };
 
 /*
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index e373f14d26f6..b40f6d5f8fe9 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -876,6 +876,7 @@ int write_cache_pages(struct address_space *mapping,
 	pgoff_t end;		/* Inclusive */
 	int scanned = 0;
 	int range_whole = 0;
+	long nr_to_write = wbc->nr_to_write;
 
 	if (wbc->nonblocking && bdi_write_congested(bdi)) {
 		wbc->encountered_congestion = 1;
@@ -939,7 +940,7 @@ retry:
 				unlock_page(page);
 				ret = 0;
 			}
-			if (ret || (--(wbc->nr_to_write) <= 0))
+			if (ret || (--nr_to_write <= 0))
 				done = 1;
 			if (wbc->nonblocking && bdi_write_congested(bdi)) {
 				wbc->encountered_congestion = 1;
@@ -958,8 +959,11 @@ retry:
 		index = 0;
 		goto retry;
 	}
-	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
-		mapping->writeback_index = index;
+	if (!wbc->no_nrwrite_index_update) {
+		if (wbc->range_cyclic || (range_whole && nr_to_write > 0))
+			mapping->writeback_index = index;
+		wbc->nr_to_write = nr_to_write;
+	}
 
 	return ret;
 }
-- 
cgit v1.2.3


From 38395738f581ce9417402f28774a8c4650264a00 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:49:42 -0700
Subject: x86: remove irq_vectors_limits

there's no user left.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/asm-x86/mach-generic/irq_vectors_limits.h | 14 --------------
 include/asm-x86/summit/irq_vectors_limits.h       | 14 --------------
 2 files changed, 28 deletions(-)
 delete mode 100644 include/asm-x86/mach-generic/irq_vectors_limits.h
 delete mode 100644 include/asm-x86/summit/irq_vectors_limits.h

(limited to 'include')

diff --git a/include/asm-x86/mach-generic/irq_vectors_limits.h b/include/asm-x86/mach-generic/irq_vectors_limits.h
deleted file mode 100644
index f7870e1a220d..000000000000
--- a/include/asm-x86/mach-generic/irq_vectors_limits.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H
-#define ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H
-
-/*
- * For Summit or generic (i.e. installer) kernels, we have lots of I/O APICs,
- * even with uni-proc kernels, so use a big array.
- *
- * This value should be the same in both the generic and summit subarches.
- * Change one, change 'em both.
- */
-#define NR_IRQS	224
-#define NR_IRQ_VECTORS	1024
-
-#endif /* ASM_X86__MACH_GENERIC__IRQ_VECTORS_LIMITS_H */
diff --git a/include/asm-x86/summit/irq_vectors_limits.h b/include/asm-x86/summit/irq_vectors_limits.h
deleted file mode 100644
index 890ce3f5e09a..000000000000
--- a/include/asm-x86/summit/irq_vectors_limits.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef _ASM_IRQ_VECTORS_LIMITS_H
-#define _ASM_IRQ_VECTORS_LIMITS_H
-
-/*
- * For Summit or generic (i.e. installer) kernels, we have lots of I/O APICs,
- * even with uni-proc kernels, so use a big array.
- *
- * This value should be the same in both the generic and summit subarches.
- * Change one, change 'em both.
- */
-#define NR_IRQS	224
-#define NR_IRQ_VECTORS	1024
-
-#endif /* _ASM_IRQ_VECTORS_LIMITS_H */
-- 
cgit v1.2.3


From 3ddfda11861d305b02ed810b522dcf48b74ca808 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:49:43 -0700
Subject: generic: add dyn_array support

Allow crazy big arrays via bootmem at init stage.
Architectures use CONFIG_HAVE_DYN_ARRAY to enable it.

usage:

| static struct irq_desc irq_desc_init __initdata = {
|        .status = IRQ_DISABLED,
|        .chip = &no_irq_chip,
|        .handle_irq = handle_bad_irq,
|        .depth = 1,
|        .lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
| #ifdef CONFIG_SMP
|        .affinity = CPU_MASK_ALL
| #endif
| };
|
| static void __init init_work(void *data)
| {
|        struct dyn_array *da = data;
|        struct  irq_desc *desc;
|        int i;
|
|        desc = *da->name;
|
|        for (i = 0; i < *da->nr; i++)
|                memcpy(&desc[i], &irq_desc_init, sizeof(struct irq_desc));
| }
|
| struct irq_desc *irq_desc;
| DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);

after pre_alloc_dyn_array() after setup_arch(), the array is ready to be
used.

Via this facility we can replace irq_desc[NR_IRQS] array with dyn_array
irq_desc[nr_irqs].

v2: remove _nopanic in pre_alloc_dyn_array()

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/asm-generic/vmlinux.lds.h |  7 +++++++
 include/linux/init.h              | 23 +++++++++++++++++++++++
 init/main.c                       | 24 ++++++++++++++++++++++++
 3 files changed, 54 insertions(+)

(limited to 'include')

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 7440a0dceddb..7881406c03ec 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -210,6 +210,13 @@
  * All archs are supposed to use RO_DATA() */
 #define RODATA RO_DATA(4096)
 
+#define DYN_ARRAY_INIT(align)							\
+	. = ALIGN((align));						\
+	.dyn_array.init : AT(ADDR(.dyn_array.init) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__dyn_array_start) = .;			\
+		*(.dyn_array.init)					\
+		VMLINUX_SYMBOL(__dyn_array_end) = .;			\
+	}
 #define SECURITY_INIT							\
 	.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__security_initcall_start) = .;		\
diff --git a/include/linux/init.h b/include/linux/init.h
index 93538b696e3d..cf9fa7f174af 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -246,6 +246,29 @@ struct obs_kernel_param {
 
 /* Relies on boot_command_line being set */
 void __init parse_early_param(void);
+
+struct dyn_array {
+	void **name;
+	unsigned long size;
+	unsigned int *nr;
+	unsigned long align;
+	void (*init_work)(void *);
+};
+extern struct dyn_array *__dyn_array_start[], *__dyn_array_end[];
+
+#define DEFINE_DYN_ARRAY(nameX, sizeX, nrX, alignX, init_workX) \
+		static struct dyn_array __dyn_array_##nameX __initdata = \
+		{	.name = (void **)&nameX,\
+			.size = sizeX,\
+			.nr   = &nrX,\
+			.align = alignX,\
+			.init_work = init_workX,\
+		}; \
+		static struct dyn_array *__dyn_array_ptr_##nameX __used \
+		__attribute__((__section__(".dyn_array.init"))) = \
+			&__dyn_array_##nameX
+
+extern void pre_alloc_dyn_array(void);
 #endif /* __ASSEMBLY__ */
 
 /**
diff --git a/init/main.c b/init/main.c
index 27f6bf6108e9..638d3a786412 100644
--- a/init/main.c
+++ b/init/main.c
@@ -536,6 +536,29 @@ void __init __weak thread_info_cache_init(void)
 {
 }
 
+void pre_alloc_dyn_array(void)
+{
+#ifdef CONFIG_HAVE_DYN_ARRAY
+	unsigned long size, phys = 0;
+	struct dyn_array **daa;
+
+	for (daa = __dyn_array_start ; daa < __dyn_array_end; daa++) {
+		struct dyn_array *da = *daa;
+
+		size = da->size * (*da->nr);
+		print_fn_descriptor_symbol("dyna_array %s ", da->name);
+		printk(KERN_CONT "size:%#lx nr:%d align:%#lx",
+			da->size, *da->nr, da->align);
+		*da->name = __alloc_bootmem(size, da->align, phys);
+		phys = virt_to_phys(*da->name);
+		printk(KERN_CONT " ==> [%#lx - %#lx]\n", phys, phys + size);
+
+		if (da->init_work)
+			da->init_work(da);
+	}
+#endif
+}
+
 asmlinkage void __init start_kernel(void)
 {
 	char * command_line;
@@ -567,6 +590,7 @@ asmlinkage void __init start_kernel(void)
 	printk(KERN_NOTICE);
 	printk(linux_banner);
 	setup_arch(&command_line);
+	pre_alloc_dyn_array();
 	mm_init_owner(&init_mm, &init_task);
 	setup_command_line(command_line);
 	unwind_setup();
-- 
cgit v1.2.3


From 1f3fcd4b1adc972d5c6a34cfed98931c46575b49 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:49:44 -0700
Subject: add per_cpu_dyn_array support

allow dyn-array in per_cpu area, allocated dynamically.

usage:

|  /* in .h */
| struct kernel_stat {
|        struct cpu_usage_stat   cpustat;
|        unsigned int *irqs;
| };
|
|  /* in .c */
| DEFINE_PER_CPU(struct kernel_stat, kstat);
|
| DEFINE_PER_CPU_DYN_ARRAY_ADDR(per_cpu__kstat_irqs, per_cpu__kstat.irqs, sizeof(unsigned int), nr_irqs, sizeof(unsigned long), NULL);

after setup_percpu()/per_cpu_alloc_dyn_array(), the dyn_array in
per_cpu area is ready to use.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/setup_percpu.c    |  7 +++--
 include/asm-generic/vmlinux.lds.h |  6 ++++
 include/linux/init.h              | 27 +++++++++++++++--
 init/main.c                       | 63 +++++++++++++++++++++++++++++++++++++--
 4 files changed, 96 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 0e67f72d9316..13ba7a83808d 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -140,7 +140,7 @@ static void __init setup_cpu_pda_map(void)
  */
 void __init setup_per_cpu_areas(void)
 {
-	ssize_t size = PERCPU_ENOUGH_ROOM;
+	ssize_t size, old_size;
 	char *ptr;
 	int cpu;
 
@@ -148,7 +148,8 @@ void __init setup_per_cpu_areas(void)
 	setup_cpu_pda_map();
 
 	/* Copy section for each CPU (we discard the original) */
-	size = PERCPU_ENOUGH_ROOM;
+	old_size = PERCPU_ENOUGH_ROOM;
+	size = old_size + per_cpu_dyn_array_size();
 	printk(KERN_INFO "PERCPU: Allocating %zd bytes of per cpu data\n",
 			  size);
 
@@ -176,6 +177,8 @@ void __init setup_per_cpu_areas(void)
 		per_cpu_offset(cpu) = ptr - __per_cpu_start;
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
 
+		per_cpu_alloc_dyn_array(cpu, ptr + old_size);
+
 	}
 
 	printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d, nr_node_ids %d\n",
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 7881406c03ec..c68eda9d9a90 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -216,6 +216,12 @@
 		VMLINUX_SYMBOL(__dyn_array_start) = .;			\
 		*(.dyn_array.init)					\
 		VMLINUX_SYMBOL(__dyn_array_end) = .;			\
+	}								\
+	. = ALIGN((align));						\
+	.per_cpu_dyn_array.init : AT(ADDR(.per_cpu_dyn_array.init) - LOAD_OFFSET) {	\
+		VMLINUX_SYMBOL(__per_cpu_dyn_array_start) = .;		\
+		*(.per_cpu_dyn_array.init)				\
+		VMLINUX_SYMBOL(__per_cpu_dyn_array_end) = .;		\
 	}
 #define SECURITY_INIT							\
 	.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
diff --git a/include/linux/init.h b/include/linux/init.h
index cf9fa7f174af..332806826b8e 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -255,12 +255,13 @@ struct dyn_array {
 	void (*init_work)(void *);
 };
 extern struct dyn_array *__dyn_array_start[], *__dyn_array_end[];
+extern struct dyn_array *__per_cpu_dyn_array_start[], *__per_cpu_dyn_array_end[];
 
-#define DEFINE_DYN_ARRAY(nameX, sizeX, nrX, alignX, init_workX) \
+#define DEFINE_DYN_ARRAY_ADDR(nameX, addrX, sizeX, nrX, alignX, init_workX) \
 		static struct dyn_array __dyn_array_##nameX __initdata = \
-		{	.name = (void **)&nameX,\
+		{	.name = (void **)&(nameX),\
 			.size = sizeX,\
-			.nr   = &nrX,\
+			.nr   = &(nrX),\
 			.align = alignX,\
 			.init_work = init_workX,\
 		}; \
@@ -268,7 +269,27 @@ extern struct dyn_array *__dyn_array_start[], *__dyn_array_end[];
 		__attribute__((__section__(".dyn_array.init"))) = \
 			&__dyn_array_##nameX
 
+#define DEFINE_DYN_ARRAY(nameX, sizeX, nrX, alignX, init_workX) \
+	DEFINE_DYN_ARRAY_ADDR(nameX, nameX, sizeX, nrX, alignX, init_workX)
+
+#define DEFINE_PER_CPU_DYN_ARRAY_ADDR(nameX, addrX, sizeX, nrX, alignX, init_workX) \
+		static struct dyn_array __per_cpu_dyn_array_##nameX __initdata = \
+		{	.name = (void **)&(addrX),\
+			.size = sizeX,\
+			.nr   = &(nrX),\
+			.align = alignX,\
+			.init_work = init_workX,\
+		}; \
+		static struct dyn_array *__per_cpu_dyn_array_ptr_##nameX __used \
+		__attribute__((__section__(".per_cpu_dyn_array.init"))) = \
+			&__per_cpu_dyn_array_##nameX
+
+#define DEFINE_PER_CPU_DYN_ARRAY(nameX, sizeX, nrX, alignX, init_workX) \
+	DEFINE_PER_CPU_DYN_ARRAY_ADDR(nameX, nameX, nrX, alignX, init_workX)
+
 extern void pre_alloc_dyn_array(void);
+extern unsigned long per_cpu_dyn_array_size(void);
+extern void per_cpu_alloc_dyn_array(int cpu, char *ptr);
 #endif /* __ASSEMBLY__ */
 
 /**
diff --git a/init/main.c b/init/main.c
index 638d3a786412..416bca4f734f 100644
--- a/init/main.c
+++ b/init/main.c
@@ -391,17 +391,19 @@ EXPORT_SYMBOL(__per_cpu_offset);
 
 static void __init setup_per_cpu_areas(void)
 {
-	unsigned long size, i;
+	unsigned long size, i, old_size;
 	char *ptr;
 	unsigned long nr_possible_cpus = num_possible_cpus();
 
 	/* Copy section for each CPU (we discard the original) */
-	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
+	old_size = PERCPU_ENOUGH_ROOM;
+	size = ALIGN(old_size + per_cpu_dyn_array_size(), PAGE_SIZE);
 	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
 
 	for_each_possible_cpu(i) {
 		__per_cpu_offset[i] = ptr - __per_cpu_start;
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
+		per_cpu_alloc_dyn_array(i, ptr + old_size);
 		ptr += size;
 	}
 }
@@ -559,6 +561,63 @@ void pre_alloc_dyn_array(void)
 #endif
 }
 
+unsigned long per_cpu_dyn_array_size(void)
+{
+	unsigned long total_size = 0;
+#ifdef CONFIG_HAVE_DYN_ARRAY
+	unsigned long size;
+	struct dyn_array **daa;
+
+	for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
+		struct dyn_array *da = *daa;
+
+		size = da->size * (*da->nr);
+		print_fn_descriptor_symbol("per_cpu_dyna_array %s ", da->name);
+		printk(KERN_CONT "size:%#lx nr:%d align:%#lx\n",
+			da->size, *da->nr, da->align);
+		total_size += roundup(size, da->align);
+	}
+	if (total_size)
+		printk(KERN_DEBUG "per_cpu_dyna_array total_size: %#lx\n",
+			 total_size);
+#endif
+	return total_size;
+}
+
+void per_cpu_alloc_dyn_array(int cpu, char *ptr)
+{
+#ifdef CONFIG_HAVE_DYN_ARRAY
+	unsigned long size, phys;
+	struct dyn_array **daa;
+	unsigned long addr;
+	void **array;
+
+	phys = virt_to_phys(ptr);
+
+	for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
+		struct dyn_array *da = *daa;
+
+		size = da->size * (*da->nr);
+		print_fn_descriptor_symbol("per_cpu_dyna_array %s ", da->name);
+		printk(KERN_CONT "size:%#lx nr:%d align:%#lx",
+			da->size, *da->nr, da->align);
+
+		phys = roundup(phys, da->align);
+		addr = (unsigned long)da->name;
+		addr += per_cpu_offset(cpu);
+		array = (void **)addr;
+		*array = phys_to_virt(phys);
+		*da->name = *array; /* so init_work could use it directly */
+		printk(KERN_CONT " %p ==> [%#lx - %#lx]\n", array, phys, phys + size);
+		phys += size;
+
+		if (da->init_work) {
+			da->init_work(da);
+		}
+	}
+#endif
+}
+
 asmlinkage void __init start_kernel(void)
 {
 	char * command_line;
-- 
cgit v1.2.3


From 1f8ff037a871690c762d267d8a052529d3102fc9 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:49:45 -0700
Subject: x86: alloc dyn_array all together

so could spare some memory with small alignment in bootmem

also tighten the alignment checking, and make print out less debug info.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/setup_percpu.c | 16 +++++++----
 include/linux/init.h           |  2 +-
 init/main.c                    | 65 ++++++++++++++++++++++++++++++++----------
 3 files changed, 62 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 13ba7a83808d..2b7dab699e83 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -140,26 +140,31 @@ static void __init setup_cpu_pda_map(void)
  */
 void __init setup_per_cpu_areas(void)
 {
-	ssize_t size, old_size;
+	ssize_t size, old_size, da_size;
 	char *ptr;
 	int cpu;
+	unsigned long align = 1;
 
 	/* Setup cpu_pda map */
 	setup_cpu_pda_map();
 
 	/* Copy section for each CPU (we discard the original) */
 	old_size = PERCPU_ENOUGH_ROOM;
-	size = old_size + per_cpu_dyn_array_size();
+	da_size = per_cpu_dyn_array_size(&align);
+	align = max_t(unsigned long, PAGE_SIZE, align);
+	size = roundup(old_size + da_size, align);
 	printk(KERN_INFO "PERCPU: Allocating %zd bytes of per cpu data\n",
 			  size);
 
 	for_each_possible_cpu(cpu) {
 #ifndef CONFIG_NEED_MULTIPLE_NODES
-		ptr = alloc_bootmem_pages(size);
+		ptr = __alloc_bootmem(size, align,
+				 __pa(MAX_DMA_ADDRESS));
 #else
 		int node = early_cpu_to_node(cpu);
 		if (!node_online(node) || !NODE_DATA(node)) {
-			ptr = alloc_bootmem_pages(size);
+			ptr = __alloc_bootmem(size, align,
+					 __pa(MAX_DMA_ADDRESS));
 			printk(KERN_INFO
 			       "cpu %d has no node %d or node-local memory\n",
 				cpu, node);
@@ -168,7 +173,8 @@ void __init setup_per_cpu_areas(void)
 					 cpu, __pa(ptr));
 		}
 		else {
-			ptr = alloc_bootmem_pages_node(NODE_DATA(node), size);
+			ptr = __alloc_bootmem_node(NODE_DATA(node), size, align,
+							__pa(MAX_DMA_ADDRESS));
 			if (ptr)
 				printk(KERN_DEBUG "per cpu data for cpu%d on node%d at %016lx\n",
 					 cpu, node, __pa(ptr));
diff --git a/include/linux/init.h b/include/linux/init.h
index 332806826b8e..59fbb4aaba6a 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -288,7 +288,7 @@ extern struct dyn_array *__per_cpu_dyn_array_start[], *__per_cpu_dyn_array_end[]
 	DEFINE_PER_CPU_DYN_ARRAY_ADDR(nameX, nameX, nrX, alignX, init_workX)
 
 extern void pre_alloc_dyn_array(void);
-extern unsigned long per_cpu_dyn_array_size(void);
+extern unsigned long per_cpu_dyn_array_size(unsigned long *align);
 extern void per_cpu_alloc_dyn_array(int cpu, char *ptr);
 #endif /* __ASSEMBLY__ */
 
diff --git a/init/main.c b/init/main.c
index 416bca4f734f..ab97d0877acc 100644
--- a/init/main.c
+++ b/init/main.c
@@ -394,10 +394,14 @@ static void __init setup_per_cpu_areas(void)
 	unsigned long size, i, old_size;
 	char *ptr;
 	unsigned long nr_possible_cpus = num_possible_cpus();
+	unsigned long align = 1;
+	unsigned da_size;
 
 	/* Copy section for each CPU (we discard the original) */
 	old_size = PERCPU_ENOUGH_ROOM;
-	size = ALIGN(old_size + per_cpu_dyn_array_size(), PAGE_SIZE);
+	da_size = per_cpu_dyn_array_size(&align);
+	align = max_t(unsigned long, PAGE_SIZE, align);
+	size = ALIGN(old_size + da_size, align);
 	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
 
 	for_each_possible_cpu(i) {
@@ -541,45 +545,78 @@ void __init __weak thread_info_cache_init(void)
 void pre_alloc_dyn_array(void)
 {
 #ifdef CONFIG_HAVE_DYN_ARRAY
-	unsigned long size, phys = 0;
+	unsigned long total_size = 0, size, phys;
+	unsigned long max_align = 1;
 	struct dyn_array **daa;
+	char *ptr;
 
+	/* get the total size at first */
 	for (daa = __dyn_array_start ; daa < __dyn_array_end; daa++) {
 		struct dyn_array *da = *daa;
 
 		size = da->size * (*da->nr);
-		print_fn_descriptor_symbol("dyna_array %s ", da->name);
-		printk(KERN_CONT "size:%#lx nr:%d align:%#lx",
+		print_fn_descriptor_symbol("dyn_array %s ", da->name);
+		printk(KERN_CONT "size:%#lx nr:%d align:%#lx\n",
 			da->size, *da->nr, da->align);
-		*da->name = __alloc_bootmem(size, da->align, phys);
-		phys = virt_to_phys(*da->name);
+		total_size += roundup(size, da->align);
+		if (da->align > max_align)
+			max_align = da->align;
+	}
+	if (total_size)
+		printk(KERN_DEBUG "dyn_array total_size: %#lx\n",
+			 total_size);
+	else
+		return;
+
+	/* allocate them all together */
+	max_align = max_t(unsigned long, max_align, PAGE_SIZE);
+	ptr = __alloc_bootmem_nopanic(total_size, max_align, 0);
+	if (!ptr)
+		panic("Can not alloc dyn_alloc\n");
+
+	phys = virt_to_phys(ptr);
+	for (daa = __dyn_array_start ; daa < __dyn_array_end; daa++) {
+		struct dyn_array *da = *daa;
+
+		size = da->size * (*da->nr);
+		print_fn_descriptor_symbol("dyn_array %s ", da->name);
+
+		phys = roundup(phys, da->align);
+		*da->name = phys_to_virt(phys);
 		printk(KERN_CONT " ==> [%#lx - %#lx]\n", phys, phys + size);
 
+		phys += size;
+
 		if (da->init_work)
 			da->init_work(da);
 	}
 #endif
 }
 
-unsigned long per_cpu_dyn_array_size(void)
+unsigned long per_cpu_dyn_array_size(unsigned long *align)
 {
 	unsigned long total_size = 0;
 #ifdef CONFIG_HAVE_DYN_ARRAY
 	unsigned long size;
 	struct dyn_array **daa;
+	unsigned max_align = 1;
 
 	for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
 		struct dyn_array *da = *daa;
 
 		size = da->size * (*da->nr);
-		print_fn_descriptor_symbol("per_cpu_dyna_array %s ", da->name);
+		print_fn_descriptor_symbol("per_cpu_dyn_array %s ", da->name);
 		printk(KERN_CONT "size:%#lx nr:%d align:%#lx\n",
 			da->size, *da->nr, da->align);
 		total_size += roundup(size, da->align);
+		if (da->align > max_align)
+			max_align = da->align;
 	}
-	if (total_size)
-		printk(KERN_DEBUG "per_cpu_dyna_array total_size: %#lx\n",
+	if (total_size) {
+		printk(KERN_DEBUG "per_cpu_dyn_array total_size: %#lx\n",
 			 total_size);
+		*align = max_align;
+	}
 #endif
 	return total_size;
 }
@@ -593,14 +630,11 @@ void per_cpu_alloc_dyn_array(int cpu, char *ptr)
 	void **array;
 
 	phys = virt_to_phys(ptr);
-
 	for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
 		struct dyn_array *da = *daa;
 
 		size = da->size * (*da->nr);
-		print_fn_descriptor_symbol("per_cpu_dyna_array %s ", da->name);
-		printk(KERN_CONT "size:%#lx nr:%d align:%#lx",
-			da->size, *da->nr, da->align);
+		print_fn_descriptor_symbol("per_cpu_dyn_array %s ", da->name);
 
 		phys = roundup(phys, da->align);
 		addr = (unsigned long)da->name;
@@ -608,7 +642,8 @@ void per_cpu_alloc_dyn_array(int cpu, char *ptr)
 		array = (void **)addr;
 		*array = phys_to_virt(phys);
 		*da->name = *array; /* so init_work could use it directly */
-		printk(KERN_CONT " %p ==> [%#lx - %#lx]\n", array, phys, phys + size);
+		printk(KERN_CONT " ==> [%#lx - %#lx]\n", phys, phys + size);
+
 		phys += size;
 
 		if (da->init_work) {
-- 
cgit v1.2.3


From 85c0f90978bf50596dbd23854648020f1f9b5bfd Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:49:47 -0700
Subject: irq: introduce nr_irqs

at this point nr_irqs is equal NR_IRQS

convert a few easy users from NR_IRQS to dynamic nr_irqs.

v2: according to Eric, we need to take care of arch without generic_hardirqs

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/m68k/kernel/ints.c   |  2 ++
 arch/s390/kernel/irq.c    |  2 ++
 arch/sparc/kernel/irq.c   |  3 +++
 include/linux/interrupt.h |  2 ++
 kernel/irq/autoprobe.c    | 10 +++++-----
 kernel/irq/chip.c         | 20 ++++++++++----------
 kernel/irq/handle.c       |  3 ++-
 kernel/irq/manage.c       | 16 ++++++++--------
 kernel/irq/proc.c         |  2 +-
 kernel/irq/resend.c       |  4 ++--
 kernel/irq/spurious.c     |  4 ++--
 11 files changed, 39 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/arch/m68k/kernel/ints.c b/arch/m68k/kernel/ints.c
index 7e8a0d394e61..74453d15692e 100644
--- a/arch/m68k/kernel/ints.c
+++ b/arch/m68k/kernel/ints.c
@@ -46,6 +46,8 @@
 #include <asm/q40ints.h>
 #endif
 
+int nr_irqs = NR_IRQS;
+
 extern u32 auto_irqhandler_fixup[];
 extern u32 user_irqhandler_fixup[];
 extern u16 user_irqvec_fixup[];
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index e7c5bfb7c755..14eb5496c8a8 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -17,6 +17,8 @@
 #include <linux/proc_fs.h>
 #include <linux/profile.h>
 
+int nr_irqs = NR_IRQS;
+
 /*
  * show_interrupts is needed by /proc/interrupts.
  */
diff --git a/arch/sparc/kernel/irq.c b/arch/sparc/kernel/irq.c
index 93e1d1c65290..059598b7e0f0 100644
--- a/arch/sparc/kernel/irq.c
+++ b/arch/sparc/kernel/irq.c
@@ -55,6 +55,9 @@
 #define SMP_NOP2
 #define SMP_NOP3
 #endif /* SMP */
+
+int nr_irqs = NR_IRQS;
+
 unsigned long __raw_local_irq_save(void)
 {
 	unsigned long retval;
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 58ff4e74b2f3..511803853a5b 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -15,6 +15,8 @@
 #include <asm/ptrace.h>
 #include <asm/system.h>
 
+extern int nr_irqs;
+
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
  * linux/ioport.h to select the interrupt line behaviour.  When
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 533068cfb607..c689e9851a80 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -38,7 +38,7 @@ unsigned long probe_irq_on(void)
 	 * something may have generated an irq long ago and we want to
 	 * flush such a longstanding irq before considering it as spurious.
 	 */
-	for (i = NR_IRQS-1; i > 0; i--) {
+	for (i = nr_irqs-1; i > 0; i--) {
 		desc = irq_desc + i;
 
 		spin_lock_irq(&desc->lock);
@@ -68,7 +68,7 @@ unsigned long probe_irq_on(void)
 	 * (we must startup again here because if a longstanding irq
 	 * happened in the previous stage, it may have masked itself)
 	 */
-	for (i = NR_IRQS-1; i > 0; i--) {
+	for (i = nr_irqs-1; i > 0; i--) {
 		desc = irq_desc + i;
 
 		spin_lock_irq(&desc->lock);
@@ -89,7 +89,7 @@ unsigned long probe_irq_on(void)
 	 * Now filter out any obviously spurious interrupts
 	 */
 	mask = 0;
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		unsigned int status;
 
 		desc = irq_desc + i;
@@ -130,7 +130,7 @@ unsigned int probe_irq_mask(unsigned long val)
 	int i;
 
 	mask = 0;
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		struct irq_desc *desc = irq_desc + i;
 		unsigned int status;
 
@@ -173,7 +173,7 @@ int probe_irq_off(unsigned long val)
 {
 	int i, irq_found = 0, nr_irqs = 0;
 
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		struct irq_desc *desc = irq_desc + i;
 		unsigned int status;
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 5203a599d211..bba66e098703 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -27,7 +27,7 @@ void dynamic_irq_init(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
 		return;
 	}
@@ -60,7 +60,7 @@ void dynamic_irq_cleanup(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
 		return;
 	}
@@ -92,7 +92,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
 		return -EINVAL;
 	}
@@ -121,7 +121,7 @@ int set_irq_type(unsigned int irq, unsigned int type)
 	unsigned long flags;
 	int ret = -ENXIO;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR "Trying to set irq type for IRQ%d\n", irq);
 		return -ENODEV;
 	}
@@ -149,7 +149,7 @@ int set_irq_data(unsigned int irq, void *data)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR
 		       "Trying to install controller data for IRQ%d\n", irq);
 		return -EINVAL;
@@ -175,7 +175,7 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR
 		       "Trying to install msi data for IRQ%d\n", irq);
 		return -EINVAL;
@@ -201,7 +201,7 @@ int set_irq_chip_data(unsigned int irq, void *data)
 	struct irq_desc *desc = irq_desc + irq;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS || !desc->chip) {
+	if (irq >= nr_irqs || !desc->chip) {
 		printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
 		return -EINVAL;
 	}
@@ -545,7 +545,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR
 		       "Trying to install type control for IRQ%d\n", irq);
 		return;
@@ -610,7 +610,7 @@ void __init set_irq_noprobe(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR "Trying to mark IRQ%d non-probeable\n", irq);
 
 		return;
@@ -628,7 +628,7 @@ void __init set_irq_probe(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS) {
+	if (irq >= nr_irqs) {
 		printk(KERN_ERR "Trying to mark IRQ%d probeable\n", irq);
 
 		return;
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index f4c8a03a9fbb..e9d022cf593e 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -47,6 +47,7 @@ handle_bad_irq(unsigned int irq, struct irq_desc *desc)
  *
  * Controller mappings for all interrupt sources:
  */
+int nr_irqs = NR_IRQS;
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS-1] = {
 		.status = IRQ_DISABLED,
@@ -265,7 +266,7 @@ void early_init_irq_lock_class(void)
 {
 	int i;
 
-	for (i = 0; i < NR_IRQS; i++)
+	for (i = 0; i < nr_irqs; i++)
 		lockdep_set_class(&irq_desc[i].lock, &irq_desc_lock_class);
 }
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index d363f32dba7d..d5a4333d8f1f 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -34,7 +34,7 @@ void synchronize_irq(unsigned int irq)
 	struct irq_desc *desc = irq_desc + irq;
 	unsigned int status;
 
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return;
 
 	do {
@@ -143,7 +143,7 @@ void disable_irq_nosync(unsigned int irq)
 	struct irq_desc *desc = irq_desc + irq;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return;
 
 	spin_lock_irqsave(&desc->lock, flags);
@@ -171,7 +171,7 @@ void disable_irq(unsigned int irq)
 {
 	struct irq_desc *desc = irq_desc + irq;
 
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return;
 
 	disable_irq_nosync(irq);
@@ -214,7 +214,7 @@ void enable_irq(unsigned int irq)
 	struct irq_desc *desc = irq_desc + irq;
 	unsigned long flags;
 
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return;
 
 	spin_lock_irqsave(&desc->lock, flags);
@@ -290,7 +290,7 @@ int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
 	struct irqaction *action;
 
-	if (irq >= NR_IRQS || irq_desc[irq].status & IRQ_NOREQUEST)
+	if (irq >= nr_irqs || irq_desc[irq].status & IRQ_NOREQUEST)
 		return 0;
 
 	action = irq_desc[irq].action;
@@ -356,7 +356,7 @@ int setup_irq(unsigned int irq, struct irqaction *new)
 	int shared = 0;
 	int ret;
 
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return -EINVAL;
 
 	if (desc->chip == &no_irq_chip)
@@ -515,7 +515,7 @@ void free_irq(unsigned int irq, void *dev_id)
 	unsigned long flags;
 
 	WARN_ON(in_interrupt());
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return;
 
 	desc = irq_desc + irq;
@@ -630,7 +630,7 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	 */
 	if ((irqflags & IRQF_SHARED) && !dev_id)
 		return -EINVAL;
-	if (irq >= NR_IRQS)
+	if (irq >= nr_irqs)
 		return -EINVAL;
 	if (irq_desc[irq].status & IRQ_NOREQUEST)
 		return -EINVAL;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index a09dd29c2fd7..e5225a65a4f9 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -240,7 +240,7 @@ void init_irq_proc(void)
 	/*
 	 * Create entries for all existing IRQs.
 	 */
-	for (i = 0; i < NR_IRQS; i++)
+	for (i = 0; i < nr_irqs; i++)
 		register_irq_proc(i);
 }
 
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index a8046791ba2d..cba8aa5bc7f4 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -33,8 +33,8 @@ static void resend_irqs(unsigned long arg)
 	struct irq_desc *desc;
 	int irq;
 
-	while (!bitmap_empty(irqs_resend, NR_IRQS)) {
-		irq = find_first_bit(irqs_resend, NR_IRQS);
+	while (!bitmap_empty(irqs_resend, nr_irqs)) {
+		irq = find_first_bit(irqs_resend, nr_irqs);
 		clear_bit(irq, irqs_resend);
 		desc = irq_desc + irq;
 		local_irq_disable();
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 19fe9d6ebfe8..e26ca1e90c08 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -91,7 +91,7 @@ static int misrouted_irq(int irq)
 	int i;
 	int ok = 0;
 
-	for (i = 1; i < NR_IRQS; i++) {
+	for (i = 1; i < nr_irqs; i++) {
 		struct irq_desc *desc = irq_desc + i;
 
 		if (i == irq)	/* Already tried */
@@ -107,7 +107,7 @@ static int misrouted_irq(int irq)
 static void poll_spurious_irqs(unsigned long dummy)
 {
 	int i;
-	for (i = 1; i < NR_IRQS; i++) {
+	for (i = 1; i < nr_irqs; i++) {
 		struct irq_desc *desc = irq_desc + i;
 		unsigned int status;
 
-- 
cgit v1.2.3


From 0799e432acfda879eaeef9622426bfa1434f3786 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:49:48 -0700
Subject: x86: use nr_irqs

also add first_free_entry and pin_map_size, which were NR_IRQS derived
constants.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 26 ++++++++++++++------------
 arch/x86/kernel/io_apic_64.c | 33 +++++++++++++++++----------------
 arch/x86/kernel/irq_32.c     |  8 ++++----
 arch/x86/kernel/irq_64.c     |  8 ++++----
 arch/x86/kernel/irqinit_32.c |  2 +-
 arch/x86/kernel/irqinit_64.c |  2 +-
 include/asm-x86/irq.h        |  3 +++
 7 files changed, 44 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index e710289f673e..d382990244f0 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -70,6 +70,7 @@ int timer_through_8259 __initdata;
  */
 int sis_apic_bug = -1;
 
+int first_free_entry = NR_IRQS;
 /*
  * # of IRQ routing registers
  */
@@ -100,6 +101,8 @@ static int disable_timer_pin_1 __initdata;
 #define MAX_PLUS_SHARED_IRQS NR_IRQS
 #define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
 
+int pin_map_size = PIN_MAP_SIZE;
+
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -213,7 +216,6 @@ static void ioapic_mask_entry(int apic, int pin)
  */
 static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 {
-	static int first_free_entry = NR_IRQS;
 	struct irq_pin_list *entry = irq_2_pin + irq;
 
 	while (entry->next)
@@ -222,7 +224,7 @@ static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 	if (entry->pin != -1) {
 		entry->next = first_free_entry;
 		entry = irq_2_pin + entry->next;
-		if (++first_free_entry >= PIN_MAP_SIZE)
+		if (++first_free_entry >= pin_map_size)
 			panic("io_apic.c: whoops");
 	}
 	entry->apic = apic;
@@ -457,7 +459,7 @@ static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
 	int i, j;
 
 	for_each_online_cpu(i) {
-		for (j = 0; j < NR_IRQS; j++) {
+		for (j = 0; j < nr_irqs; j++) {
 			if (!irq_desc[j].action)
 				continue;
 			/* Is it a significant load ?  */
@@ -492,7 +494,7 @@ static void do_irq_balance(void)
 		if (!cpu_online(i))
 			continue;
 		package_index = CPU_TO_PACKAGEINDEX(i);
-		for (j = 0; j < NR_IRQS; j++) {
+		for (j = 0; j < nr_irqs; j++) {
 			unsigned long value_now, delta;
 			/* Is this an active IRQ or balancing disabled ? */
 			if (!irq_desc[j].action || irq_balancing_disabled(j))
@@ -587,7 +589,7 @@ tryanotherirq:
 	 */
 	move_this_load = 0;
 	selected_irq = -1;
-	for (j = 0; j < NR_IRQS; j++) {
+	for (j = 0; j < nr_irqs; j++) {
 		/* Is this an active IRQ? */
 		if (!irq_desc[j].action)
 			continue;
@@ -664,7 +666,7 @@ static int balanced_irq(void *unused)
 	long time_remaining = balanced_irq_interval;
 
 	/* push everything to CPU 0 to give us a starting point.  */
-	for (i = 0 ; i < NR_IRQS ; i++) {
+	for (i = 0 ; i < nr_irqs ; i++) {
 		irq_desc[i].pending_mask = cpumask_of_cpu(0);
 		set_pending_irq(i, cpumask_of_cpu(0));
 	}
@@ -712,8 +714,8 @@ static int __init balanced_irq_init(void)
 		physical_balance = 1;
 
 	for_each_online_cpu(i) {
-		irq_cpu_data[i].irq_delta = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
-		irq_cpu_data[i].last_irq = kzalloc(sizeof(unsigned long) * NR_IRQS, GFP_KERNEL);
+		irq_cpu_data[i].irq_delta = kzalloc(sizeof(unsigned long) * nr_irqs, GFP_KERNEL);
+		irq_cpu_data[i].last_irq = kzalloc(sizeof(unsigned long) * nr_irqs, GFP_KERNEL);
 		if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) {
 			printk(KERN_ERR "balanced_irq_init: out of memory");
 			goto failed;
@@ -1441,7 +1443,7 @@ __apicdebuginit(void) print_IO_APIC(void)
 	}
 	}
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		struct irq_pin_list *entry = irq_2_pin + i;
 		if (entry->pin < 0)
 			continue;
@@ -1621,7 +1623,7 @@ static void __init enable_IO_APIC(void)
 	int i, apic;
 	unsigned long flags;
 
-	for (i = 0; i < PIN_MAP_SIZE; i++) {
+	for (i = 0; i < pin_map_size; i++) {
 		irq_2_pin[i].pin = -1;
 		irq_2_pin[i].next = 0;
 	}
@@ -2005,7 +2007,7 @@ static inline void init_IO_APIC_traps(void)
 	 * Also, we've got to be careful not to trash gate
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
-	for (irq = 0; irq < NR_IRQS ; irq++) {
+	for (irq = 0; irq < nr_irqs ; irq++) {
 		if (IO_APIC_IRQ(irq) && !irq_vector[irq]) {
 			/*
 			 * Hmm.. We don't have an entry for this,
@@ -2449,7 +2451,7 @@ int create_irq(void)
 
 	irq = -ENOSPC;
 	spin_lock_irqsave(&vector_lock, flags);
-	for (new = (NR_IRQS - 1); new >= 0; new--) {
+	for (new = (nr_irqs - 1); new >= 0; new--) {
 		if (platform_legacy_irq(new))
 			continue;
 		if (irq_vector[new] != 0)
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 02063ae042f7..448384c7c1e8 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -132,6 +132,7 @@ DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
 #define MAX_PLUS_SHARED_IRQS NR_IRQS
 #define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
 
+int pin_map_size = PIN_MAP_SIZE;
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -224,7 +225,7 @@ static inline void io_apic_sync(unsigned int apic)
 	int pin;							\
 	struct irq_pin_list *entry = irq_2_pin + irq;			\
 									\
-	BUG_ON(irq >= NR_IRQS);						\
+	BUG_ON(irq >= nr_irqs);						\
 	for (;;) {							\
 		unsigned int reg;					\
 		pin = entry->pin;					\
@@ -301,7 +302,7 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
 	int apic, pin;
 	struct irq_pin_list *entry = irq_2_pin + irq;
 
-	BUG_ON(irq >= NR_IRQS);
+	BUG_ON(irq >= nr_irqs);
 	for (;;) {
 		unsigned int reg;
 		apic = entry->apic;
@@ -358,19 +359,19 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
  * shared ISA-space IRQs, so we have to support them. We are super
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
+int first_free_entry = NR_IRQS;
 static void add_pin_to_irq(unsigned int irq, int apic, int pin)
 {
-	static int first_free_entry = NR_IRQS;
 	struct irq_pin_list *entry = irq_2_pin + irq;
 
-	BUG_ON(irq >= NR_IRQS);
+	BUG_ON(irq >= nr_irqs);
 	while (entry->next)
 		entry = irq_2_pin + entry->next;
 
 	if (entry->pin != -1) {
 		entry->next = first_free_entry;
 		entry = irq_2_pin + entry->next;
-		if (++first_free_entry >= PIN_MAP_SIZE)
+		if (++first_free_entry >= pin_map_size)
 			panic("io_apic.c: ran out of irq_2_pin entries!");
 	}
 	entry->apic = apic;
@@ -634,7 +635,7 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 				best_guess = irq;
 		}
 	}
-	BUG_ON(best_guess >= NR_IRQS);
+	BUG_ON(best_guess >= nr_irqs);
 	return best_guess;
 }
 
@@ -766,7 +767,7 @@ static int pin_2_irq(int idx, int apic, int pin)
 			irq += nr_ioapic_registers[i++];
 		irq += pin;
 	}
-	BUG_ON(irq >= NR_IRQS);
+	BUG_ON(irq >= nr_irqs);
 	return irq;
 }
 
@@ -801,7 +802,7 @@ static int __assign_irq_vector(int irq, cpumask_t mask)
 	int cpu;
 	struct irq_cfg *cfg;
 
-	BUG_ON((unsigned)irq >= NR_IRQS);
+	BUG_ON((unsigned)irq >= nr_irqs);
 	cfg = &irq_cfg[irq];
 
 	/* Only try and allocate irqs on cpus that are present */
@@ -875,7 +876,7 @@ static void __clear_irq_vector(int irq)
 	cpumask_t mask;
 	int cpu, vector;
 
-	BUG_ON((unsigned)irq >= NR_IRQS);
+	BUG_ON((unsigned)irq >= nr_irqs);
 	cfg = &irq_cfg[irq];
 	BUG_ON(!cfg->vector);
 
@@ -895,7 +896,7 @@ void __setup_vector_irq(int cpu)
 	int irq, vector;
 
 	/* Mark the inuse vectors */
-	for (irq = 0; irq < NR_IRQS; ++irq) {
+	for (irq = 0; irq < nr_irqs; ++irq) {
 		if (!cpu_isset(cpu, irq_cfg[irq].domain))
 			continue;
 		vector = irq_cfg[irq].vector;
@@ -1193,7 +1194,7 @@ __apicdebuginit(void) print_IO_APIC(void)
 	}
 	}
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		struct irq_pin_list *entry = irq_2_pin + i;
 		if (entry->pin < 0)
 			continue;
@@ -1366,7 +1367,7 @@ void __init enable_IO_APIC(void)
 	int i, apic;
 	unsigned long flags;
 
-	for (i = 0; i < PIN_MAP_SIZE; i++) {
+	for (i = 0; i < pin_map_size; i++) {
 		irq_2_pin[i].pin = -1;
 		irq_2_pin[i].next = 0;
 	}
@@ -1658,7 +1659,7 @@ static void ir_irq_migration(struct work_struct *work)
 {
 	int irq;
 
-	for (irq = 0; irq < NR_IRQS; irq++) {
+	for (irq = 0; irq < nr_irqs; irq++) {
 		struct irq_desc *desc = irq_desc + irq;
 		if (desc->status & IRQ_MOVE_PENDING) {
 			unsigned long flags;
@@ -1707,7 +1708,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
 		struct irq_desc *desc;
 		struct irq_cfg *cfg;
 		irq = __get_cpu_var(vector_irq)[vector];
-		if (irq >= NR_IRQS)
+		if (irq >= nr_irqs)
 			continue;
 
 		desc = irq_desc + irq;
@@ -1865,7 +1866,7 @@ static inline void init_IO_APIC_traps(void)
 	 * Also, we've got to be careful not to trash gate
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
-	for (irq = 0; irq < NR_IRQS ; irq++) {
+	for (irq = 0; irq < nr_irqs ; irq++) {
 		if (IO_APIC_IRQ(irq) && !irq_cfg[irq].vector) {
 			/*
 			 * Hmm.. We don't have an entry for this,
@@ -2279,7 +2280,7 @@ int create_irq(void)
 
 	irq = -ENOSPC;
 	spin_lock_irqsave(&vector_lock, flags);
-	for (new = (NR_IRQS - 1); new >= 0; new--) {
+	for (new = (nr_irqs - 1); new >= 0; new--) {
 		if (platform_legacy_irq(new))
 			continue;
 		if (irq_cfg[new].vector != 0)
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index b71e02d42f4f..4c7ffb32854c 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -226,7 +226,7 @@ unsigned int do_IRQ(struct pt_regs *regs)
 	int overflow, irq = ~regs->orig_ax;
 	struct irq_desc *desc = irq_desc + irq;
 
-	if (unlikely((unsigned)irq >= NR_IRQS)) {
+	if (unlikely((unsigned)irq >= nr_irqs)) {
 		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
 					__func__, irq);
 		BUG();
@@ -271,7 +271,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
-	if (i < NR_IRQS) {
+	if (i < nr_irqs) {
 		unsigned any_count = 0;
 
 		spin_lock_irqsave(&irq_desc[i].lock, flags);
@@ -303,7 +303,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 skip:
 		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
-	} else if (i == NR_IRQS) {
+	} else if (i == nr_irqs) {
 		seq_printf(p, "NMI: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", nmi_count(j));
@@ -396,7 +396,7 @@ void fixup_irqs(cpumask_t map)
 	unsigned int irq;
 	static int warned;
 
-	for (irq = 0; irq < NR_IRQS; irq++) {
+	for (irq = 0; irq < nr_irqs; irq++) {
 		cpumask_t mask;
 		if (irq == 2)
 			continue;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index f065fe9071b9..e1f0839430d2 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -81,7 +81,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
-	if (i < NR_IRQS) {
+	if (i < nr_irqs) {
 		unsigned any_count = 0;
 
 		spin_lock_irqsave(&irq_desc[i].lock, flags);
@@ -112,7 +112,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 skip:
 		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
-	} else if (i == NR_IRQS) {
+	} else if (i == nr_irqs) {
 		seq_printf(p, "NMI: ");
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", cpu_pda(j)->__nmi_count);
@@ -201,7 +201,7 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 	stack_overflow_check(regs);
 #endif
 
-	if (likely(irq < NR_IRQS))
+	if (likely(irq < nr_irqs))
 		generic_handle_irq(irq);
 	else {
 		if (!disable_apic)
@@ -224,7 +224,7 @@ void fixup_irqs(cpumask_t map)
 	unsigned int irq;
 	static int warned;
 
-	for (irq = 0; irq < NR_IRQS; irq++) {
+	for (irq = 0; irq < nr_irqs; irq++) {
 		cpumask_t mask;
 		int break_affinity = 0;
 		int set_affinity = 1;
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index 9200a1e2752d..65c1c9507707 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -100,7 +100,7 @@ void __init native_init_IRQ(void)
 	 */
 	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
 		int vector = FIRST_EXTERNAL_VECTOR + i;
-		if (i >= NR_IRQS)
+		if (i >= nr_irqs)
 			break;
 		/* SYSCALL_VECTOR was reserved in trap_init. */
 		if (!test_bit(vector, used_vectors))
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index 5b5be9d43c2a..165c5d9b0d1a 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -142,7 +142,7 @@ void __init init_ISA_irqs(void)
 	init_bsp_APIC();
 	init_8259A(0);
 
-	for (i = 0; i < NR_IRQS; i++) {
+	for (i = 0; i < nr_irqs; i++) {
 		irq_desc[i].status = IRQ_DISABLED;
 		irq_desc[i].action = NULL;
 		irq_desc[i].depth = 1;
diff --git a/include/asm-x86/irq.h b/include/asm-x86/irq.h
index 1e5f2909c1db..2a130c44f5de 100644
--- a/include/asm-x86/irq.h
+++ b/include/asm-x86/irq.h
@@ -10,6 +10,9 @@
 #include <asm/apicdef.h>
 #include <asm/irq_vectors.h>
 
+extern int pin_map_size;
+extern int first_free_entry;
+
 static inline int irq_canonicalize(int irq)
 {
 	return ((irq == 2) ? 9 : irq);
-- 
cgit v1.2.3


From d60458b224d6b997a582a05cb8c4b9bed9e17a1d Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:00 -0700
Subject: irq: make irq_desc to use dyn_array

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/irq.h |  4 ++++
 kernel/irq/handle.c | 31 +++++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 1d73d1abb834..5f4b013624dc 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -179,7 +179,11 @@ struct irq_desc {
 	const char		*name;
 } ____cacheline_internodealigned_in_smp;
 
+#ifdef CONFIG_HAVE_DYN_ARRAY
+extern struct irq_desc *irq_desc;
+#else
 extern struct irq_desc irq_desc[NR_IRQS];
+#endif
 
 /*
  * Migration helpers for obsolete names, they will go away:
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index e9d022cf593e..e94eeca09ea9 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -48,6 +48,36 @@ handle_bad_irq(unsigned int irq, struct irq_desc *desc)
  * Controller mappings for all interrupt sources:
  */
 int nr_irqs = NR_IRQS;
+
+#ifdef CONFIG_HAVE_DYN_ARRAY
+static struct irq_desc irq_desc_init __initdata = {
+	.status = IRQ_DISABLED,
+	.chip = &no_irq_chip,
+	.handle_irq = handle_bad_irq,
+	.depth = 1,
+	.lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
+#ifdef CONFIG_SMP
+	.affinity = CPU_MASK_ALL
+#endif
+};
+
+static void __init init_work(void *data)
+{
+	struct dyn_array *da = data;
+	int i;
+	struct  irq_desc *desc;
+
+	desc = *da->name;
+
+	for (i = 0; i < *da->nr; i++)
+		memcpy(&desc[i], &irq_desc_init, sizeof(struct irq_desc));
+}
+
+struct irq_desc *irq_desc;
+DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);
+
+#else
+
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS-1] = {
 		.status = IRQ_DISABLED,
@@ -60,6 +90,7 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 #endif
 	}
 };
+#endif
 
 /*
  * What should we do if we get a hw irq event on an illegal vector?
-- 
cgit v1.2.3


From d17a55ded3393ad3878010bb3a8243a15a8d8df5 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:01 -0700
Subject: irq: make irqs in kernel stat use per_cpu_dyn_array

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/kernel_stat.h | 4 ++++
 kernel/sched.c              | 5 ++++-
 2 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index cf9f40a91c9c..fe1f7fe534b4 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -28,7 +28,11 @@ struct cpu_usage_stat {
 
 struct kernel_stat {
 	struct cpu_usage_stat	cpustat;
+#ifdef CONFIG_HAVE_DYN_ARRAY
+	unsigned int *irqs;
+#else
 	unsigned int irqs[NR_IRQS];
+#endif
 };
 
 DECLARE_PER_CPU(struct kernel_stat, kstat);
diff --git a/kernel/sched.c b/kernel/sched.c
index 6f230596bd0c..b9d713781b5b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4048,9 +4048,12 @@ static inline void idle_balance(int cpu, struct rq *rq)
 #endif
 
 DEFINE_PER_CPU(struct kernel_stat, kstat);
-
 EXPORT_PER_CPU_SYMBOL(kstat);
 
+#ifdef CONFIG_HAVE_DYN_ARRAY
+DEFINE_PER_CPU_DYN_ARRAY_ADDR(per_cpu__kstat_irqs, per_cpu__kstat.irqs, sizeof(unsigned int), nr_irqs, sizeof(unsigned long), NULL);
+#endif
+
 /*
  * Return p->sum_exec_runtime plus any more ns on the sched_clock
  * that have not yet been banked in case the task is currently running.
-- 
cgit v1.2.3


From 71f521bbaf375b685aeea20c6b0ed8600cd6edfe Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:03 -0700
Subject: x86, irq: get nr_irqs from madt

Until now, NR_IRQS was derived from black magic defines that had to
be "large enough" to both accomodate NR_CPUS and MAX_NR_IO_APICs.

This resulted in a way too large irq_desc[] array on most x86 systems.
Especially with larger CPU masks, the size of irq_desc can spiral out
of control quickly.

So be smarter about it and use precise allocation instead: determine the
default maximum possible IRQ number from the ACPI MADT. Use a minimum limit
of at least 32 IRQs for broken BIOSes.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/acpi/boot.c | 30 ++++++++++++++++++++++++++++--
 include/asm-x86/mpspec.h    |  1 +
 2 files changed, 29 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index eb875cdc7367..3e9d163fd92f 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -957,6 +957,29 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 	nr_ioapics++;
 }
 
+int get_nr_irqs_via_madt(void)
+{
+	int idx;
+	int nr = 0;
+
+	for (idx = 0; idx < nr_ioapics; idx++) {
+		if (mp_ioapic_routing[idx].gsi_end > nr)
+			nr = mp_ioapic_routing[idx].gsi_end;
+	}
+
+	nr++;
+
+	/* double it for hotplug and msi and nmi */
+	nr <<= 1;
+
+	/* something wrong ? */
+	if (nr < 32)
+		nr = 32;
+
+	return nr;
+
+}
+
 static void assign_to_mp_irq(struct mp_config_intsrc *m,
 				    struct mp_config_intsrc *mp_irq)
 {
@@ -1254,9 +1277,12 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 		return count;
 	}
 
+
+	nr_irqs = get_nr_irqs_via_madt();
+
 	count =
 	    acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, acpi_parse_int_src_ovr,
-				  NR_IRQ_VECTORS);
+				  nr_irqs);
 	if (count < 0) {
 		printk(KERN_ERR PREFIX
 		       "Error parsing interrupt source overrides entry\n");
@@ -1276,7 +1302,7 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 
 	count =
 	    acpi_table_parse_madt(ACPI_MADT_TYPE_NMI_SOURCE, acpi_parse_nmi_src,
-				  NR_IRQ_VECTORS);
+				  nr_irqs);
 	if (count < 0) {
 		printk(KERN_ERR PREFIX "Error parsing NMI SRC entry\n");
 		/* TBD: Cleanup to allow fallback to MPS */
diff --git a/include/asm-x86/mpspec.h b/include/asm-x86/mpspec.h
index be2241a818f1..a0748021250b 100644
--- a/include/asm-x86/mpspec.h
+++ b/include/asm-x86/mpspec.h
@@ -60,6 +60,7 @@ extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 				   u32 gsi);
 extern void mp_config_acpi_legacy_irqs(void);
 extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
+extern int get_nr_irqs_via_madt(void);
 #ifdef CONFIG_X86_IO_APIC
 extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
 				u32 gsi, int triggering, int polarity);
-- 
cgit v1.2.3


From bfea1238beac9d306eeac081c67de5ca6aec4c7a Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:04 -0700
Subject: x86: remove nr_irq_vectors

remove unused defines derived from the (now obsolete) NR_IRQS define.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/asm-x86/irq_vectors.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'include')

diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h
index c5d2d767a1f3..cb09802ce651 100644
--- a/include/asm-x86/irq_vectors.h
+++ b/include/asm-x86/irq_vectors.h
@@ -116,7 +116,6 @@
 # else
 #  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
 # endif
-# define NR_IRQ_VECTORS NR_IRQS
 
 #elif !defined(CONFIG_X86_VOYAGER)
 
@@ -124,23 +123,15 @@
 
 #  define NR_IRQS		224
 
-#  if (224 >= 32 * NR_CPUS)
-#   define NR_IRQ_VECTORS	NR_IRQS
-#  else
-#   define NR_IRQ_VECTORS	(32 * NR_CPUS)
-#  endif
-
 # else /* IO_APIC || PARAVIRT */
 
 #  define NR_IRQS		16
-#  define NR_IRQ_VECTORS	NR_IRQS
 
 # endif
 
 #else /* !VISWS && !VOYAGER */
 
 # define NR_IRQS		224
-# define NR_IRQ_VECTORS		NR_IRQS
 
 #endif /* VISWS */
 
-- 
cgit v1.2.3


From 08678b0841267c1d00d771fe01548d86043d065e Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:05 -0700
Subject: generic: sparse irqs: use irq_desc() together with dyn_array, instead
 of irq_desc[]

add CONFIG_HAVE_SPARSE_IRQ to for use condensed array.
Get rid of irq_desc[] array assumptions.

Preallocate 32 irq_desc, and irq_desc() will try to get more.

( No change in functionality is expected anywhere, except the odd build
  failure where we missed a code site or where a crossing commit itroduces
  new irq_desc[] usage. )

v2: according to Eric, change get_irq_desc() to irq_desc()

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/Kconfig                        |   4 ++
 arch/x86/Kconfig                    |   1 +
 arch/x86/kernel/io_apic_32.c        |  46 ++++++++----
 arch/x86/kernel/io_apic_64.c        |  75 +++++++++++++-------
 arch/x86/kernel/irq_32.c            |  24 ++++---
 arch/x86/kernel/irq_64.c            |  35 ++++-----
 arch/x86/kernel/irqinit_64.c        |  10 +--
 arch/x86/kernel/visws_quirks.c      |  30 ++++----
 arch/x86/mach-voyager/voyager_smp.c |   4 +-
 drivers/gpio/gpiolib.c              |   2 +-
 drivers/mfd/asic3.c                 |   4 +-
 drivers/mfd/htc-egpio.c             |   2 +-
 drivers/parisc/dino.c               |   6 +-
 drivers/parisc/eisa.c               |   4 +-
 drivers/parisc/gsc.c                |  12 ++--
 drivers/parisc/iosapic.c            |   4 +-
 drivers/parisc/superio.c            |   4 +-
 drivers/pcmcia/hd64465_ss.c         |  12 +++-
 drivers/xen/events.c                |   8 ++-
 include/linux/irq.h                 |  32 ++++++---
 kernel/irq/autoprobe.c              |  10 +--
 kernel/irq/chip.c                   |  32 +++++----
 kernel/irq/handle.c                 | 138 ++++++++++++++++++++++++++++++++----
 kernel/irq/manage.c                 |  35 +++++----
 kernel/irq/migration.c              |  14 ++--
 kernel/irq/proc.c                   |  36 +++++-----
 kernel/irq/resend.c                 |   2 +-
 kernel/irq/spurious.c               |   5 +-
 28 files changed, 404 insertions(+), 187 deletions(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index c1f9febb404f..b36762246265 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -105,3 +105,7 @@ config HAVE_CLK
 
 config HAVE_DYN_ARRAY
 	def_bool n
+
+config HAVE_SPARSE_IRQ
+	def_bool n
+
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 42f98009d752..1004888e9b13 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -34,6 +34,7 @@ config X86
 	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_DYN_ARRAY
+	select HAVE_SPARSE_IRQ if X86_64
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 7f2bcc3dad82..c2160cfdec9b 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -345,6 +345,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
 	struct irq_pin_list *entry = irq_2_pin + irq;
 	unsigned int apicid_value;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, cpumask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -365,7 +366,8 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
 			break;
 		entry = irq_2_pin + entry->next;
 	}
-	irq_desc[irq].affinity = cpumask;
+	desc = irq_to_desc(irq);
+	desc->affinity = cpumask;
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
@@ -475,10 +477,12 @@ static inline void balance_irq(int cpu, int irq)
 static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
 {
 	int i, j;
+	struct irq_desc *desc;
 
 	for_each_online_cpu(i) {
 		for (j = 0; j < nr_irqs; j++) {
-			if (!irq_desc[j].action)
+			desc = irq_to_desc(j);
+			if (!desc->action)
 				continue;
 			/* Is it a significant load ?  */
 			if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i), j) <
@@ -505,6 +509,7 @@ static void do_irq_balance(void)
 	unsigned long tmp_cpu_irq;
 	unsigned long imbalance = 0;
 	cpumask_t allowed_mask, target_cpu_mask, tmp;
+	struct irq_desc *desc;
 
 	for_each_possible_cpu(i) {
 		int package_index;
@@ -515,7 +520,8 @@ static void do_irq_balance(void)
 		for (j = 0; j < nr_irqs; j++) {
 			unsigned long value_now, delta;
 			/* Is this an active IRQ or balancing disabled ? */
-			if (!irq_desc[j].action || irq_balancing_disabled(j))
+			desc = irq_to_desc(j);
+			if (!desc->action || irq_balancing_disabled(j))
 				continue;
 			if (package_index == i)
 				IRQ_DELTA(package_index, j) = 0;
@@ -609,7 +615,8 @@ tryanotherirq:
 	selected_irq = -1;
 	for (j = 0; j < nr_irqs; j++) {
 		/* Is this an active IRQ? */
-		if (!irq_desc[j].action)
+		desc = irq_to_desc(j);
+		if (!desc->action)
 			continue;
 		if (imbalance <= IRQ_DELTA(max_loaded, j))
 			continue;
@@ -682,10 +689,12 @@ static int balanced_irq(void *unused)
 	int i;
 	unsigned long prev_balance_time = jiffies;
 	long time_remaining = balanced_irq_interval;
+	struct irq_desc *desc;
 
 	/* push everything to CPU 0 to give us a starting point.  */
 	for (i = 0 ; i < nr_irqs ; i++) {
-		irq_desc[i].pending_mask = cpumask_of_cpu(0);
+		desc = irq_to_desc(i);
+		desc->pending_mask = cpumask_of_cpu(0);
 		set_pending_irq(i, cpumask_of_cpu(0));
 	}
 
@@ -1254,13 +1263,16 @@ static struct irq_chip ioapic_chip;
 
 static void ioapic_register_intr(int irq, int vector, unsigned long trigger)
 {
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
 	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
 	    trigger == IOAPIC_LEVEL) {
-		irq_desc[irq].status |= IRQ_LEVEL;
+		desc->status |= IRQ_LEVEL;
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
 					 handle_fasteoi_irq, "fasteoi");
 	} else {
-		irq_desc[irq].status &= ~IRQ_LEVEL;
+		desc->status &= ~IRQ_LEVEL;
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
 					 handle_edge_irq, "edge");
 	}
@@ -2027,6 +2039,7 @@ static struct irq_chip ioapic_chip __read_mostly = {
 static inline void init_IO_APIC_traps(void)
 {
 	int irq;
+	struct irq_desc *desc;
 
 	/*
 	 * NOTE! The local APIC isn't very good at handling
@@ -2048,9 +2061,11 @@ static inline void init_IO_APIC_traps(void)
 			 */
 			if (irq < 16)
 				make_8259A_irq(irq);
-			else
+			else {
+				desc = irq_to_desc(irq);
 				/* Strange. Oh, well.. */
-				irq_desc[irq].chip = &no_irq_chip;
+				desc->chip = &no_irq_chip;
+			}
 		}
 	}
 }
@@ -2089,7 +2104,10 @@ static struct irq_chip lapic_chip __read_mostly = {
 
 static void lapic_register_intr(int irq, int vector)
 {
-	irq_desc[irq].status &= ~IRQ_LEVEL;
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	desc->status &= ~IRQ_LEVEL;
 	set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
 				      "edge");
 	set_intr_gate(vector, interrupt[irq]);
@@ -2556,6 +2574,7 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	unsigned int dest;
 	cpumask_t tmp;
 	int vector;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2575,7 +2594,8 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	write_msi_msg(irq, &msg);
-	irq_desc[irq].affinity = mask;
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
 }
 #endif /* CONFIG_SMP */
 
@@ -2649,6 +2669,7 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 {
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2659,7 +2680,8 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 	dest = cpu_mask_to_apicid(mask);
 
 	target_ht_irq(irq, dest);
-	irq_desc[irq].affinity = mask;
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
 }
 #endif
 
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 93a3ffabfe6a..cab5a25d81b1 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -345,6 +345,7 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 	unsigned long flags;
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -361,9 +362,10 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 	 */
 	dest = SET_APIC_LOGICAL_ID(dest);
 
+	desc = irq_to_desc(irq);
 	spin_lock_irqsave(&ioapic_lock, flags);
 	__target_IO_APIC_irq(irq, dest, cfg->vector);
-	irq_desc[irq].affinity = mask;
+	desc->affinity = mask;
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 #endif
@@ -933,14 +935,17 @@ static struct irq_chip ir_ioapic_chip;
 
 static void ioapic_register_intr(int irq, unsigned long trigger)
 {
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
 	if (trigger)
-		irq_desc[irq].status |= IRQ_LEVEL;
+		desc->status |= IRQ_LEVEL;
 	else
-		irq_desc[irq].status &= ~IRQ_LEVEL;
+		desc->status &= ~IRQ_LEVEL;
 
 #ifdef CONFIG_INTR_REMAP
 	if (irq_remapped(irq)) {
-		irq_desc[irq].status |= IRQ_MOVE_PCNTXT;
+		desc->status |= IRQ_MOVE_PCNTXT;
 		if (trigger)
 			set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
 						      handle_fasteoi_irq,
@@ -1596,10 +1601,10 @@ static DECLARE_DELAYED_WORK(ir_migration_work, ir_irq_migration);
 static void migrate_ioapic_irq(int irq, cpumask_t mask)
 {
 	struct irq_cfg *cfg = irq_cfg + irq;
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc;
 	cpumask_t tmp, cleanup_mask;
 	struct irte irte;
-	int modify_ioapic_rte = desc->status & IRQ_LEVEL;
+	int modify_ioapic_rte;
 	unsigned int dest;
 	unsigned long flags;
 
@@ -1616,6 +1621,8 @@ static void migrate_ioapic_irq(int irq, cpumask_t mask)
 	cpus_and(tmp, cfg->domain, mask);
 	dest = cpu_mask_to_apicid(tmp);
 
+	desc = irq_to_desc(irq);
+	modify_ioapic_rte = desc->status & IRQ_LEVEL;
 	if (modify_ioapic_rte) {
 		spin_lock_irqsave(&ioapic_lock, flags);
 		__target_IO_APIC_irq(irq, dest, cfg->vector);
@@ -1637,12 +1644,13 @@ static void migrate_ioapic_irq(int irq, cpumask_t mask)
 		cfg->move_in_progress = 0;
 	}
 
-	irq_desc[irq].affinity = mask;
+	desc->affinity = mask;
 }
 
 static int migrate_irq_remapped_level(int irq)
 {
 	int ret = -1;
+	struct irq_desc *desc = irq_to_desc(irq);
 
 	mask_IO_APIC_irq(irq);
 
@@ -1658,11 +1666,11 @@ static int migrate_irq_remapped_level(int irq)
 	}
 
 	/* everthing is clear. we have right of way */
-	migrate_ioapic_irq(irq, irq_desc[irq].pending_mask);
+	migrate_ioapic_irq(irq, desc->pending_mask);
 
 	ret = 0;
-	irq_desc[irq].status &= ~IRQ_MOVE_PENDING;
-	cpus_clear(irq_desc[irq].pending_mask);
+	desc->status &= ~IRQ_MOVE_PENDING;
+	cpus_clear(desc->pending_mask);
 
 unmask:
 	unmask_IO_APIC_irq(irq);
@@ -1674,7 +1682,7 @@ static void ir_irq_migration(struct work_struct *work)
 	int irq;
 
 	for (irq = 0; irq < nr_irqs; irq++) {
-		struct irq_desc *desc = irq_desc + irq;
+		struct irq_desc *desc = irq_to_desc(irq);
 		if (desc->status & IRQ_MOVE_PENDING) {
 			unsigned long flags;
 
@@ -1686,8 +1694,7 @@ static void ir_irq_migration(struct work_struct *work)
 				continue;
 			}
 
-			desc->chip->set_affinity(irq,
-					         irq_desc[irq].pending_mask);
+			desc->chip->set_affinity(irq, desc->pending_mask);
 			spin_unlock_irqrestore(&desc->lock, flags);
 		}
 	}
@@ -1698,9 +1705,11 @@ static void ir_irq_migration(struct work_struct *work)
  */
 static void set_ir_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
 {
-	if (irq_desc[irq].status & IRQ_LEVEL) {
-		irq_desc[irq].status |= IRQ_MOVE_PENDING;
-		irq_desc[irq].pending_mask = mask;
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	if (desc->status & IRQ_LEVEL) {
+		desc->status |= IRQ_MOVE_PENDING;
+		desc->pending_mask = mask;
 		migrate_irq_remapped_level(irq);
 		return;
 	}
@@ -1725,7 +1734,7 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
 		if (irq >= nr_irqs)
 			continue;
 
-		desc = irq_desc + irq;
+		desc = irq_to_desc(irq);
 		cfg = irq_cfg + irq;
 		spin_lock(&desc->lock);
 		if (!cfg->move_cleanup_count)
@@ -1791,7 +1800,7 @@ static void ack_apic_level(unsigned int irq)
 	irq_complete_move(irq);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	/* If we are moving the irq we need to mask it */
-	if (unlikely(irq_desc[irq].status & IRQ_MOVE_PENDING)) {
+	if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
 		do_unmask_irq = 1;
 		mask_IO_APIC_irq(irq);
 	}
@@ -1868,6 +1877,7 @@ static struct irq_chip ir_ioapic_chip __read_mostly = {
 static inline void init_IO_APIC_traps(void)
 {
 	int irq;
+	struct irq_desc *desc;
 
 	/*
 	 * NOTE! The local APIC isn't very good at handling
@@ -1889,9 +1899,11 @@ static inline void init_IO_APIC_traps(void)
 			 */
 			if (irq < 16)
 				make_8259A_irq(irq);
-			else
+			else {
+				desc = irq_to_desc(irq);
 				/* Strange. Oh, well.. */
-				irq_desc[irq].chip = &no_irq_chip;
+				desc->chip = &no_irq_chip;
+			}
 		}
 	}
 }
@@ -1926,7 +1938,10 @@ static struct irq_chip lapic_chip __read_mostly = {
 
 static void lapic_register_intr(int irq)
 {
-	irq_desc[irq].status &= ~IRQ_LEVEL;
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	desc->status &= ~IRQ_LEVEL;
 	set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
 				      "edge");
 }
@@ -2402,6 +2417,7 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	struct msi_msg msg;
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2421,7 +2437,8 @@ static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	write_msi_msg(irq, &msg);
-	irq_desc[irq].affinity = mask;
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
 }
 
 #ifdef CONFIG_INTR_REMAP
@@ -2435,6 +2452,7 @@ static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 	unsigned int dest;
 	cpumask_t tmp, cleanup_mask;
 	struct irte irte;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2469,7 +2487,8 @@ static void ir_set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 		cfg->move_in_progress = 0;
 	}
 
-	irq_desc[irq].affinity = mask;
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
 }
 #endif
 #endif /* CONFIG_SMP */
@@ -2543,7 +2562,7 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc, int irq)
 
 #ifdef CONFIG_INTR_REMAP
 	if (irq_remapped(irq)) {
-		struct irq_desc *desc = irq_desc + irq;
+		struct irq_desc *desc = irq_to_desc(irq);
 		/*
 		 * irq migration in process context
 		 */
@@ -2655,6 +2674,7 @@ static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
 	struct msi_msg msg;
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2674,7 +2694,8 @@ static void dmar_msi_set_affinity(unsigned int irq, cpumask_t mask)
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
 	dmar_msi_write(irq, &msg);
-	irq_desc[irq].affinity = mask;
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
 }
 #endif /* CONFIG_SMP */
 
@@ -2731,6 +2752,7 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 	struct irq_cfg *cfg = irq_cfg + irq;
 	unsigned int dest;
 	cpumask_t tmp;
+	struct irq_desc *desc;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
@@ -2743,7 +2765,8 @@ static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 	dest = cpu_mask_to_apicid(tmp);
 
 	target_ht_irq(irq, dest, cfg->vector);
-	irq_desc[irq].affinity = mask;
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
 }
 #endif
 
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 4c7ffb32854c..ede513be517d 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -224,7 +224,7 @@ unsigned int do_IRQ(struct pt_regs *regs)
 	struct pt_regs *old_regs;
 	/* high bit used in ret_from_ code */
 	int overflow, irq = ~regs->orig_ax;
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 
 	if (unlikely((unsigned)irq >= nr_irqs)) {
 		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
@@ -273,15 +273,16 @@ int show_interrupts(struct seq_file *p, void *v)
 
 	if (i < nr_irqs) {
 		unsigned any_count = 0;
+		struct irq_desc *desc = irq_to_desc(i);
 
-		spin_lock_irqsave(&irq_desc[i].lock, flags);
+		spin_lock_irqsave(&desc->lock, flags);
 #ifndef CONFIG_SMP
 		any_count = kstat_irqs(i);
 #else
 		for_each_online_cpu(j)
 			any_count |= kstat_cpu(j).irqs[i];
 #endif
-		action = irq_desc[i].action;
+		action = desc->action;
 		if (!action && !any_count)
 			goto skip;
 		seq_printf(p, "%3d: ",i);
@@ -291,8 +292,8 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
-		seq_printf(p, " %8s", irq_desc[i].chip->name);
-		seq_printf(p, "-%-8s", irq_desc[i].name);
+		seq_printf(p, " %8s", desc->chip->name);
+		seq_printf(p, "-%-8s", desc->name);
 
 		if (action) {
 			seq_printf(p, "  %s", action->name);
@@ -302,7 +303,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 		seq_putc(p, '\n');
 skip:
-		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+		spin_unlock_irqrestore(&desc->lock, flags);
 	} else if (i == nr_irqs) {
 		seq_printf(p, "NMI: ");
 		for_each_online_cpu(j)
@@ -398,17 +399,20 @@ void fixup_irqs(cpumask_t map)
 
 	for (irq = 0; irq < nr_irqs; irq++) {
 		cpumask_t mask;
+		struct irq_desc *desc;
+
 		if (irq == 2)
 			continue;
 
-		cpus_and(mask, irq_desc[irq].affinity, map);
+		desc = irq_to_desc(irq);
+		cpus_and(mask, desc->affinity, map);
 		if (any_online_cpu(mask) == NR_CPUS) {
 			printk("Breaking affinity for irq %i\n", irq);
 			mask = map;
 		}
-		if (irq_desc[irq].chip->set_affinity)
-			irq_desc[irq].chip->set_affinity(irq, mask);
-		else if (irq_desc[irq].action && !(warned++))
+		if (desc->chip->set_affinity)
+			desc->chip->set_affinity(irq, mask);
+		else if (desc->action && !(warned++))
 			printk("Cannot set affinity for irq %i\n", irq);
 	}
 
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index e1f0839430d2..738eb65a924e 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -83,15 +83,16 @@ int show_interrupts(struct seq_file *p, void *v)
 
 	if (i < nr_irqs) {
 		unsigned any_count = 0;
+		struct irq_desc *desc = irq_to_desc(i);
 
-		spin_lock_irqsave(&irq_desc[i].lock, flags);
+		spin_lock_irqsave(&desc->lock, flags);
 #ifndef CONFIG_SMP
 		any_count = kstat_irqs(i);
 #else
 		for_each_online_cpu(j)
 			any_count |= kstat_cpu(j).irqs[i];
 #endif
-		action = irq_desc[i].action;
+		action = desc->action;
 		if (!action && !any_count)
 			goto skip;
 		seq_printf(p, "%3d: ",i);
@@ -101,8 +102,8 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
 #endif
-		seq_printf(p, " %8s", irq_desc[i].chip->name);
-		seq_printf(p, "-%-8s", irq_desc[i].name);
+		seq_printf(p, " %8s", desc->chip->name);
+		seq_printf(p, "-%-8s", desc->name);
 
 		if (action) {
 			seq_printf(p, "  %s", action->name);
@@ -111,7 +112,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		}
 		seq_putc(p, '\n');
 skip:
-		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
+		spin_unlock_irqrestore(&desc->lock, flags);
 	} else if (i == nr_irqs) {
 		seq_printf(p, "NMI: ");
 		for_each_online_cpu(j)
@@ -228,37 +229,39 @@ void fixup_irqs(cpumask_t map)
 		cpumask_t mask;
 		int break_affinity = 0;
 		int set_affinity = 1;
+		struct irq_desc *desc;
 
 		if (irq == 2)
 			continue;
 
+		desc = irq_to_desc(irq);
 		/* interrupt's are disabled at this point */
-		spin_lock(&irq_desc[irq].lock);
+		spin_lock(&desc->lock);
 
 		if (!irq_has_action(irq) ||
-		    cpus_equal(irq_desc[irq].affinity, map)) {
-			spin_unlock(&irq_desc[irq].lock);
+		    cpus_equal(desc->affinity, map)) {
+			spin_unlock(&desc->lock);
 			continue;
 		}
 
-		cpus_and(mask, irq_desc[irq].affinity, map);
+		cpus_and(mask, desc->affinity, map);
 		if (cpus_empty(mask)) {
 			break_affinity = 1;
 			mask = map;
 		}
 
-		if (irq_desc[irq].chip->mask)
-			irq_desc[irq].chip->mask(irq);
+		if (desc->chip->mask)
+			desc->chip->mask(irq);
 
-		if (irq_desc[irq].chip->set_affinity)
-			irq_desc[irq].chip->set_affinity(irq, mask);
+		if (desc->chip->set_affinity)
+			desc->chip->set_affinity(irq, mask);
 		else if (!(warned++))
 			set_affinity = 0;
 
-		if (irq_desc[irq].chip->unmask)
-			irq_desc[irq].chip->unmask(irq);
+		if (desc->chip->unmask)
+			desc->chip->unmask(irq);
 
-		spin_unlock(&irq_desc[irq].lock);
+		spin_unlock(&desc->lock);
 
 		if (break_affinity && set_affinity)
 			printk("Broke affinity for irq %i\n", irq);
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index 165c5d9b0d1a..0744b49b4d12 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -143,9 +143,11 @@ void __init init_ISA_irqs(void)
 	init_8259A(0);
 
 	for (i = 0; i < nr_irqs; i++) {
-		irq_desc[i].status = IRQ_DISABLED;
-		irq_desc[i].action = NULL;
-		irq_desc[i].depth = 1;
+		struct irq_desc *desc = irq_to_desc(i);
+
+		desc->status = IRQ_DISABLED;
+		desc->action = NULL;
+		desc->depth = 1;
 
 		if (i < 16) {
 			/*
@@ -157,7 +159,7 @@ void __init init_ISA_irqs(void)
 			/*
 			 * 'high' PCI IRQs filled in on demand
 			 */
-			irq_desc[i].chip = &no_irq_chip;
+			desc->chip = &no_irq_chip;
 		}
 	}
 }
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index 61a97e616f70..9d85ab384435 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -484,10 +484,11 @@ static void disable_cobalt_irq(unsigned int irq)
 static unsigned int startup_cobalt_irq(unsigned int irq)
 {
 	unsigned long flags;
+	struct irq_desc *desc = irq_to_desc(irq);
 
 	spin_lock_irqsave(&cobalt_lock, flags);
-	if ((irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING)))
-		irq_desc[irq].status &= ~(IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING);
+	if ((desc->status & (IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING)))
+		desc->status &= ~(IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING);
 	enable_cobalt_irq(irq);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 	return 0;
@@ -506,9 +507,10 @@ static void ack_cobalt_irq(unsigned int irq)
 static void end_cobalt_irq(unsigned int irq)
 {
 	unsigned long flags;
+	struct irq_desc *desc = irq_to_desc(irq);
 
 	spin_lock_irqsave(&cobalt_lock, flags);
-	if (!(irq_desc[irq].status & (IRQ_DISABLED | IRQ_INPROGRESS)))
+	if (!(desc->status & (IRQ_DISABLED | IRQ_INPROGRESS)))
 		enable_cobalt_irq(irq);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 }
@@ -626,7 +628,7 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 
 	spin_unlock_irqrestore(&i8259A_lock, flags);
 
-	desc = irq_desc + realirq;
+	desc = irq_to_desc(realirq);
 
 	/*
 	 * handle this 'virtual interrupt' as a Cobalt one now.
@@ -662,27 +664,29 @@ void init_VISWS_APIC_irqs(void)
 	int i;
 
 	for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) {
-		irq_desc[i].status = IRQ_DISABLED;
-		irq_desc[i].action = 0;
-		irq_desc[i].depth = 1;
+		struct irq_desc *desc = irq_to_desc(i);
+
+		desc->status = IRQ_DISABLED;
+		desc->action = 0;
+		desc->depth = 1;
 
 		if (i == 0) {
-			irq_desc[i].chip = &cobalt_irq_type;
+			desc->chip = &cobalt_irq_type;
 		}
 		else if (i == CO_IRQ_IDE0) {
-			irq_desc[i].chip = &cobalt_irq_type;
+			desc->chip = &cobalt_irq_type;
 		}
 		else if (i == CO_IRQ_IDE1) {
-			irq_desc[i].chip = &cobalt_irq_type;
+			desc->chip = &cobalt_irq_type;
 		}
 		else if (i == CO_IRQ_8259) {
-			irq_desc[i].chip = &piix4_master_irq_type;
+			desc->chip = &piix4_master_irq_type;
 		}
 		else if (i < CO_IRQ_APIC0) {
-			irq_desc[i].chip = &piix4_virtual_irq_type;
+			desc->chip = &piix4_virtual_irq_type;
 		}
 		else if (IS_CO_APIC(i)) {
-			irq_desc[i].chip = &cobalt_irq_type;
+			desc->chip = &cobalt_irq_type;
 		}
 	}
 
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 199a5f4a873c..0f6e8a6523ae 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -1483,7 +1483,7 @@ static void disable_local_vic_irq(unsigned int irq)
  * the interrupt off to another CPU */
 static void before_handle_vic_irq(unsigned int irq)
 {
-	irq_desc_t *desc = irq_desc + irq;
+	irq_desc_t *desc = irq_to_desc(irq);
 	__u8 cpu = smp_processor_id();
 
 	_raw_spin_lock(&vic_irq_lock);
@@ -1518,7 +1518,7 @@ static void before_handle_vic_irq(unsigned int irq)
 /* Finish the VIC interrupt: basically mask */
 static void after_handle_vic_irq(unsigned int irq)
 {
-	irq_desc_t *desc = irq_desc + irq;
+	irq_desc_t *desc = irq_to_desc(irq);
 
 	_raw_spin_lock(&vic_irq_lock);
 	{
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 8d2940517c99..572d372899d3 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1058,7 +1058,7 @@ static void gpiolib_dbg_show(struct seq_file *s, struct gpio_chip *chip)
 
 		if (!is_out) {
 			int		irq = gpio_to_irq(gpio);
-			struct irq_desc	*desc = irq_desc + irq;
+			struct irq_desc	*desc = irq_to_desc(irq);
 
 			/* This races with request_irq(), set_irq_type(),
 			 * and set_irq_wake() ... but those are "rare".
diff --git a/drivers/mfd/asic3.c b/drivers/mfd/asic3.c
index ba5aa2008273..e4c0db4dc7b1 100644
--- a/drivers/mfd/asic3.c
+++ b/drivers/mfd/asic3.c
@@ -123,7 +123,7 @@ static void asic3_irq_demux(unsigned int irq, struct irq_desc *desc)
 					irqnr = asic->irq_base +
 						(ASIC3_GPIOS_PER_BANK * bank)
 						+ i;
-					desc = irq_desc + irqnr;
+					desc = irq_to_desc(irqnr);
 					desc->handle_irq(irqnr, desc);
 					if (asic->irq_bothedge[bank] & bit)
 						asic3_irq_flip_edge(asic, base,
@@ -136,7 +136,7 @@ static void asic3_irq_demux(unsigned int irq, struct irq_desc *desc)
 		for (i = ASIC3_NUM_GPIOS; i < ASIC3_NR_IRQS; i++) {
 			/* They start at bit 4 and go up */
 			if (status & (1 << (i - ASIC3_NUM_GPIOS + 4))) {
-				desc = irq_desc + asic->irq_base + i;
+				desc = irq_to_desc(asic->irq_base + i);
 				desc->handle_irq(asic->irq_base + i,
 						 desc);
 			}
diff --git a/drivers/mfd/htc-egpio.c b/drivers/mfd/htc-egpio.c
index 6be43172dc65..ad3379fcd194 100644
--- a/drivers/mfd/htc-egpio.c
+++ b/drivers/mfd/htc-egpio.c
@@ -112,7 +112,7 @@ static void egpio_handler(unsigned int irq, struct irq_desc *desc)
 		/* Run irq handler */
 		pr_debug("got IRQ %d\n", irqpin);
 		irq = ei->irq_start + irqpin;
-		desc = &irq_desc[irq];
+		desc = irq_to_desc(irq);
 		desc->handle_irq(irq, desc);
 	}
 }
diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c
index fd56128525d1..3bc54b30c3a1 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -298,7 +298,8 @@ struct pci_port_ops dino_port_ops = {
 
 static void dino_disable_irq(unsigned int irq)
 {
-	struct dino_device *dino_dev = irq_desc[irq].chip_data;
+	struct irq_desc *desc = irq_to_desc(irq);
+	struct dino_device *dino_dev = desc->chip_data;
 	int local_irq = gsc_find_local_irq(irq, dino_dev->global_irq, DINO_LOCAL_IRQS);
 
 	DBG(KERN_WARNING "%s(0x%p, %d)\n", __func__, dino_dev, irq);
@@ -310,7 +311,8 @@ static void dino_disable_irq(unsigned int irq)
 
 static void dino_enable_irq(unsigned int irq)
 {
-	struct dino_device *dino_dev = irq_desc[irq].chip_data;
+	struct irq_desc *desc = irq_to_desc(irq);
+	struct dino_device *dino_dev = desc->chip_data;
 	int local_irq = gsc_find_local_irq(irq, dino_dev->global_irq, DINO_LOCAL_IRQS);
 	u32 tmp;
 
diff --git a/drivers/parisc/eisa.c b/drivers/parisc/eisa.c
index 771cef592542..7891db50c483 100644
--- a/drivers/parisc/eisa.c
+++ b/drivers/parisc/eisa.c
@@ -346,10 +346,10 @@ static int __init eisa_probe(struct parisc_device *dev)
 	}
 	
 	/* Reserve IRQ2 */
-	irq_desc[2].action = &irq2_action;
+	irq_to_desc(2)->action = &irq2_action;
 	
 	for (i = 0; i < 16; i++) {
-		irq_desc[i].chip = &eisa_interrupt_type;
+		irq_to_desc(i)->chip = &eisa_interrupt_type;
 	}
 	
 	EISA_bus = 1;
diff --git a/drivers/parisc/gsc.c b/drivers/parisc/gsc.c
index f7d088b897ee..e76db9e4d504 100644
--- a/drivers/parisc/gsc.c
+++ b/drivers/parisc/gsc.c
@@ -108,7 +108,8 @@ int gsc_find_local_irq(unsigned int irq, int *global_irqs, int limit)
 
 static void gsc_asic_disable_irq(unsigned int irq)
 {
-	struct gsc_asic *irq_dev = irq_desc[irq].chip_data;
+	struct irq_desc *desc = irq_to_desc(irq);
+	struct gsc_asic *irq_dev = desc->chip_data;
 	int local_irq = gsc_find_local_irq(irq, irq_dev->global_irq, 32);
 	u32 imr;
 
@@ -123,7 +124,8 @@ static void gsc_asic_disable_irq(unsigned int irq)
 
 static void gsc_asic_enable_irq(unsigned int irq)
 {
-	struct gsc_asic *irq_dev = irq_desc[irq].chip_data;
+	struct irq_desc *desc = irq_to_desc(irq);
+	struct gsc_asic *irq_dev = desc->chip_data;
 	int local_irq = gsc_find_local_irq(irq, irq_dev->global_irq, 32);
 	u32 imr;
 
@@ -159,12 +161,14 @@ static struct hw_interrupt_type gsc_asic_interrupt_type = {
 int gsc_assign_irq(struct hw_interrupt_type *type, void *data)
 {
 	static int irq = GSC_IRQ_BASE;
+	struct irq_desc *desc;
 
 	if (irq > GSC_IRQ_MAX)
 		return NO_IRQ;
 
-	irq_desc[irq].chip = type;
-	irq_desc[irq].chip_data = data;
+	desc = irq_to_desc(irq);
+	desc->chip = type;
+	desc->chip_data = data;
 	return irq++;
 }
 
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index 6fb3f7979f21..7beffcab2745 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -619,7 +619,9 @@ iosapic_set_irt_data( struct vector_info *vi, u32 *dp0, u32 *dp1)
 
 static struct vector_info *iosapic_get_vector(unsigned int irq)
 {
-	return irq_desc[irq].chip_data;
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	return desc->chip_data;
 }
 
 static void iosapic_disable_irq(unsigned int irq)
diff --git a/drivers/parisc/superio.c b/drivers/parisc/superio.c
index 1e8d2d17f04c..1e93c837514f 100644
--- a/drivers/parisc/superio.c
+++ b/drivers/parisc/superio.c
@@ -363,7 +363,9 @@ int superio_fixup_irq(struct pci_dev *pcidev)
 #endif
 
 	for (i = 0; i < 16; i++) {
-		irq_desc[i].chip = &superio_interrupt_type;
+		struct irq_desc *desc = irq_to_desc(i);
+
+		desc->chip = &superio_interrupt_type;
 	}
 
 	/*
diff --git a/drivers/pcmcia/hd64465_ss.c b/drivers/pcmcia/hd64465_ss.c
index 117dc12ab438..9ef69cdb3183 100644
--- a/drivers/pcmcia/hd64465_ss.c
+++ b/drivers/pcmcia/hd64465_ss.c
@@ -233,15 +233,18 @@ static struct hw_interrupt_type hd64465_ss_irq_type = {
  */
 static void hs_map_irq(hs_socket_t *sp, unsigned int irq)
 {
+	struct irq_desc *desc;
+
     	DPRINTK("hs_map_irq(sock=%d irq=%d)\n", sp->number, irq);
 	
 	if (irq >= HS_NUM_MAPPED_IRQS)
 	    return;
 
+	desc = irq_to_desc(irq);
     	hs_mapped_irq[irq].sock = sp;
 	/* insert ourselves as the irq controller */
-	hs_mapped_irq[irq].old_handler = irq_desc[irq].chip;
-	irq_desc[irq].chip = &hd64465_ss_irq_type;
+	hs_mapped_irq[irq].old_handler = desc->chip;
+	desc->chip = &hd64465_ss_irq_type;
 }
 
 
@@ -250,13 +253,16 @@ static void hs_map_irq(hs_socket_t *sp, unsigned int irq)
  */
 static void hs_unmap_irq(hs_socket_t *sp, unsigned int irq)
 {
+	struct irq_desc *desc;
+
     	DPRINTK("hs_unmap_irq(sock=%d irq=%d)\n", sp->number, irq);
 	
 	if (irq >= HS_NUM_MAPPED_IRQS)
 	    return;
 		
+	desc = irq_to_desc(irq);
 	/* restore the original irq controller */
-	irq_desc[irq].chip = hs_mapped_irq[irq].old_handler;
+	desc->chip = hs_mapped_irq[irq].old_handler;
 }
 
 /*============================================================*/
diff --git a/drivers/xen/events.c b/drivers/xen/events.c
index ed8235187dc0..56ace47f24d6 100644
--- a/drivers/xen/events.c
+++ b/drivers/xen/events.c
@@ -125,7 +125,7 @@ static void bind_evtchn_to_cpu(unsigned int chn, unsigned int cpu)
 
 	BUG_ON(irq == -1);
 #ifdef CONFIG_SMP
-	irq_desc[irq].affinity = cpumask_of_cpu(cpu);
+	irq_to_desc(irq)->affinity = cpumask_of_cpu(cpu);
 #endif
 
 	__clear_bit(chn, cpu_evtchn_mask[cpu_evtchn[chn]]);
@@ -139,8 +139,10 @@ static void init_evtchn_cpu_bindings(void)
 #ifdef CONFIG_SMP
 	int i;
 	/* By default all event channels notify CPU#0. */
-	for (i = 0; i < nr_irqs; i++)
-		irq_desc[i].affinity = cpumask_of_cpu(0);
+	for (i = 0; i < nr_irqs; i++) {
+		struct irq_desc *desc = irq_to_desc(i);
+		desc->affinity = cpumask_of_cpu(0);
+	}
 #endif
 
 	memset(cpu_evtchn, 0, sizeof(cpu_evtchn));
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 5f4b013624dc..80b8200f2adb 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -152,6 +152,10 @@ struct irq_chip {
  * @name:		flow handler name for /proc/interrupts output
  */
 struct irq_desc {
+	unsigned int		irq;
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+	struct irq_desc		*next;
+#endif
 	irq_flow_handler_t	handle_irq;
 	struct irq_chip		*chip;
 	struct msi_desc		*msi_desc;
@@ -179,9 +183,9 @@ struct irq_desc {
 	const char		*name;
 } ____cacheline_internodealigned_in_smp;
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-extern struct irq_desc *irq_desc;
-#else
+extern struct irq_desc *irq_to_desc(unsigned int irq);
+#ifndef CONFIG_HAVE_DYN_ARRAY
+/* could be removed if we get rid of all irq_desc reference */
 extern struct irq_desc irq_desc[NR_IRQS];
 #endif
 
@@ -249,7 +253,10 @@ extern int no_irq_affinity;
 
 static inline int irq_balancing_disabled(unsigned int irq)
 {
-	return irq_desc[irq].status & IRQ_NO_BALANCING_MASK;
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	return desc->status & IRQ_NO_BALANCING_MASK;
 }
 
 /* Handle irq action chains: */
@@ -281,7 +288,7 @@ extern unsigned int __do_IRQ(unsigned int irq);
  */
 static inline void generic_handle_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 
 #ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
 	desc->handle_irq(irq, desc);
@@ -325,7 +332,10 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 static inline void __set_irq_handler_unlocked(int irq,
 					      irq_flow_handler_t handler)
 {
-	irq_desc[irq].handle_irq = handler;
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	desc->handle_irq = handler;
 }
 
 /*
@@ -359,7 +369,7 @@ extern void destroy_irq(unsigned int irq);
 /* Test to see if a driver has successfully requested an irq */
 static inline int irq_has_action(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	return desc->action != NULL;
 }
 
@@ -374,10 +384,10 @@ extern int set_irq_chip_data(unsigned int irq, void *data);
 extern int set_irq_type(unsigned int irq, unsigned int type);
 extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 
-#define get_irq_chip(irq)	(irq_desc[irq].chip)
-#define get_irq_chip_data(irq)	(irq_desc[irq].chip_data)
-#define get_irq_data(irq)	(irq_desc[irq].handler_data)
-#define get_irq_msi(irq)	(irq_desc[irq].msi_desc)
+#define get_irq_chip(irq)	(irq_to_desc(irq)->chip)
+#define get_irq_chip_data(irq)	(irq_to_desc(irq)->chip_data)
+#define get_irq_data(irq)	(irq_to_desc(irq)->handler_data)
+#define get_irq_msi(irq)	(irq_to_desc(irq)->msi_desc)
 
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index c689e9851a80..c45ab718cf07 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -39,7 +39,7 @@ unsigned long probe_irq_on(void)
 	 * flush such a longstanding irq before considering it as spurious.
 	 */
 	for (i = nr_irqs-1; i > 0; i--) {
-		desc = irq_desc + i;
+		desc = irq_to_desc(i);
 
 		spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
@@ -69,7 +69,7 @@ unsigned long probe_irq_on(void)
 	 * happened in the previous stage, it may have masked itself)
 	 */
 	for (i = nr_irqs-1; i > 0; i--) {
-		desc = irq_desc + i;
+		desc = irq_to_desc(i);
 
 		spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
@@ -92,7 +92,7 @@ unsigned long probe_irq_on(void)
 	for (i = 0; i < nr_irqs; i++) {
 		unsigned int status;
 
-		desc = irq_desc + i;
+		desc = irq_to_desc(i);
 		spin_lock_irq(&desc->lock);
 		status = desc->status;
 
@@ -131,7 +131,7 @@ unsigned int probe_irq_mask(unsigned long val)
 
 	mask = 0;
 	for (i = 0; i < nr_irqs; i++) {
-		struct irq_desc *desc = irq_desc + i;
+		struct irq_desc *desc = irq_to_desc(i);
 		unsigned int status;
 
 		spin_lock_irq(&desc->lock);
@@ -174,7 +174,7 @@ int probe_irq_off(unsigned long val)
 	int i, irq_found = 0, nr_irqs = 0;
 
 	for (i = 0; i < nr_irqs; i++) {
-		struct irq_desc *desc = irq_desc + i;
+		struct irq_desc *desc = irq_to_desc(i);
 		unsigned int status;
 
 		spin_lock_irq(&desc->lock);
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index bba66e098703..76c225cf4b26 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -33,7 +33,7 @@ void dynamic_irq_init(unsigned int irq)
 	}
 
 	/* Ensure we don't have left over values from a previous use of this irq */
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->status = IRQ_DISABLED;
 	desc->chip = &no_irq_chip;
@@ -65,7 +65,7 @@ void dynamic_irq_cleanup(unsigned int irq)
 		return;
 	}
 
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	if (desc->action) {
 		spin_unlock_irqrestore(&desc->lock, flags);
@@ -100,7 +100,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 	if (!chip)
 		chip = &no_irq_chip;
 
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	irq_chip_set_defaults(chip);
 	desc->chip = chip;
@@ -126,7 +126,7 @@ int set_irq_type(unsigned int irq, unsigned int type)
 		return -ENODEV;
 	}
 
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 	if (type == IRQ_TYPE_NONE)
 		return 0;
 
@@ -155,7 +155,7 @@ int set_irq_data(unsigned int irq, void *data)
 		return -EINVAL;
 	}
 
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->handler_data = data;
 	spin_unlock_irqrestore(&desc->lock, flags);
@@ -180,7 +180,7 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
 		       "Trying to install msi data for IRQ%d\n", irq);
 		return -EINVAL;
 	}
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->msi_desc = entry;
 	if (entry)
@@ -198,9 +198,10 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
  */
 int set_irq_chip_data(unsigned int irq, void *data)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc;
 	unsigned long flags;
 
+	desc = irq_to_desc(irq);
 	if (irq >= nr_irqs || !desc->chip) {
 		printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
 		return -EINVAL;
@@ -219,8 +220,9 @@ EXPORT_SYMBOL(set_irq_chip_data);
  */
 static void default_enable(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc;
 
+	desc = irq_to_desc(irq);
 	desc->chip->unmask(irq);
 	desc->status &= ~IRQ_MASKED;
 }
@@ -237,7 +239,10 @@ static void default_disable(unsigned int irq)
  */
 static unsigned int default_startup(unsigned int irq)
 {
-	irq_desc[irq].chip->enable(irq);
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	desc->chip->enable(irq);
 
 	return 0;
 }
@@ -247,8 +252,9 @@ static unsigned int default_startup(unsigned int irq)
  */
 static void default_shutdown(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc;
 
+	desc = irq_to_desc(irq);
 	desc->chip->mask(irq);
 	desc->status |= IRQ_MASKED;
 }
@@ -551,7 +557,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		return;
 	}
 
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 
 	if (!handle)
 		handle = handle_bad_irq;
@@ -616,7 +622,7 @@ void __init set_irq_noprobe(unsigned int irq)
 		return;
 	}
 
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->status |= IRQ_NOPROBE;
@@ -634,7 +640,7 @@ void __init set_irq_probe(unsigned int irq)
 		return;
 	}
 
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->status &= ~IRQ_NOPROBE;
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 6ce3bcc2b8f7..9fc33b3378e6 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -18,6 +18,14 @@
 
 #include "internals.h"
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+/*
+ * lockdep: we want to handle all irq_desc locks as a single lock-class:
+ */
+static struct lock_class_key irq_desc_lock_class;
+#endif
+
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
  * @irq:       the interrupt number
@@ -51,7 +59,8 @@ int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
 #ifdef CONFIG_HAVE_DYN_ARRAY
-static struct irq_desc irq_desc_init __initdata = {
+static struct irq_desc irq_desc_init = {
+	.irq = -1U,
 	.status = IRQ_DISABLED,
 	.chip = &no_irq_chip,
 	.handle_irq = handle_bad_irq,
@@ -62,6 +71,27 @@ static struct irq_desc irq_desc_init __initdata = {
 #endif
 };
 
+
+static void init_one_irq_desc(struct irq_desc *desc)
+{
+	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
+#ifdef CONFIG_TRACE_IRQFLAGS
+	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+#endif
+}
+
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+static int nr_irq_desc = 32;
+
+static int __init parse_nr_irq_desc(char *arg)
+{
+	if (arg)
+		nr_irq_desc = simple_strtoul(arg, NULL, 0);
+	return 0;
+}
+
+early_param("nr_irq_desc", parse_nr_irq_desc);
+
 static void __init init_work(void *data)
 {
 	struct dyn_array *da = data;
@@ -71,12 +101,83 @@ static void __init init_work(void *data)
 	desc = *da->name;
 
 	for (i = 0; i < *da->nr; i++)
-		memcpy(&desc[i], &irq_desc_init, sizeof(struct irq_desc));
+		init_one_irq_desc(&desc[i]);
+
+	for (i = 1; i < *da->nr; i++)
+		desc[i-1].next = &desc[i];
 }
 
-struct irq_desc *irq_desc;
+static struct irq_desc *sparse_irqs;
+DEFINE_DYN_ARRAY(sparse_irqs, sizeof(struct irq_desc), nr_irq_desc, PAGE_SIZE, init_work);
+
+extern int after_bootmem;
+extern void *__alloc_bootmem_nopanic(unsigned long size,
+			     unsigned long align,
+			     unsigned long goal);
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+	struct irq_desc *desc, *desc_pri;
+	int i;
+	int count = 0;
+
+	BUG_ON(irq == -1U);
+
+	desc_pri = desc = &sparse_irqs[0];
+	while (desc) {
+		if (desc->irq == irq)
+			return desc;
+
+		if (desc->irq == -1U) {
+			desc->irq = irq;
+			return desc;
+		}
+		desc_pri = desc;
+		desc = desc->next;
+		count++;
+	}
+
+	/*
+	 *  we run out of pre-allocate ones, allocate more
+	 */
+	printk(KERN_DEBUG "try to get more irq_desc %d\n", nr_irq_desc);
+
+	if (after_bootmem)
+		desc = kzalloc(sizeof(struct irq_desc)*nr_irq_desc, GFP_ATOMIC);
+	else
+		desc = __alloc_bootmem_nopanic(sizeof(struct irq_desc)*nr_irq_desc, PAGE_SIZE, 0);
+
+	if (!desc)
+		panic("please boot with nr_irq_desc= %d\n", count * 2);
+
+	for (i = 0; i < nr_irq_desc; i++)
+		init_one_irq_desc(&desc[i]);
+
+	for (i = 1; i < nr_irq_desc; i++)
+		desc[i-1].next = &desc[i];
+
+	desc->irq = irq;
+	desc_pri->next = desc;
+
+	return desc;
+}
+#else
+static void __init init_work(void *data)
+{
+	struct dyn_array *da = data;
+	int i;
+	struct  irq_desc *desc;
+
+	desc = *da->name;
+
+	for (i = 0; i < *da->nr; i++)
+		init_one_irq_desc(&desc[i]);
+
+}
+static struct irq_desc *irq_desc;
 DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);
 
+#endif
+
 #else
 
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
@@ -85,12 +186,23 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 		.chip = &no_irq_chip,
 		.handle_irq = handle_bad_irq,
 		.depth = 1,
-		.lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
+		.lock = __SPIN_LOCK_UNLOCKED(sparse_irqs->lock),
 #ifdef CONFIG_SMP
 		.affinity = CPU_MASK_ALL
 #endif
 	}
 };
+
+#endif
+
+#ifndef CONFIG_HAVE_SPARSE_IRQ
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+	if (irq < nr_irqs)
+		return &irq_desc[irq];
+
+	return NULL;
+}
 #endif
 
 /*
@@ -99,7 +211,10 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
  */
 static void ack_bad(unsigned int irq)
 {
-	print_irq_desc(irq, irq_desc + irq);
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	print_irq_desc(irq, desc);
 	ack_bad_irq(irq);
 }
 
@@ -196,7 +311,7 @@ irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action)
  */
 unsigned int __do_IRQ(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	struct irqaction *action;
 	unsigned int status;
 
@@ -287,19 +402,16 @@ out:
 }
 #endif
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-
-/*
- * lockdep: we want to handle all irq_desc locks as a single lock-class:
- */
-static struct lock_class_key irq_desc_lock_class;
 
+#ifdef CONFIG_TRACE_IRQFLAGS
 void early_init_irq_lock_class(void)
 {
+#ifndef CONFIG_HAVE_DYN_ARRAY
 	int i;
 
 	for (i = 0; i < nr_irqs; i++)
 		lockdep_set_class(&irq_desc[i].lock, &irq_desc_lock_class);
+#endif
 }
-
 #endif
+
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index d5a4333d8f1f..b5943e9f95aa 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -31,7 +31,7 @@ cpumask_t irq_default_affinity = CPU_MASK_ALL;
  */
 void synchronize_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned int status;
 
 	if (irq >= nr_irqs)
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(synchronize_irq);
  */
 int irq_can_set_affinity(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 
 	if (CHECK_IRQ_PER_CPU(desc->status) || !desc->chip ||
 	    !desc->chip->set_affinity)
@@ -81,7 +81,7 @@ int irq_can_set_affinity(unsigned int irq)
  */
 int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 
 	if (!desc->chip->set_affinity)
 		return -EINVAL;
@@ -111,14 +111,16 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 int irq_select_affinity(unsigned int irq)
 {
 	cpumask_t mask;
+	struct irq_desc *desc;
 
 	if (!irq_can_set_affinity(irq))
 		return 0;
 
 	cpus_and(mask, cpu_online_map, irq_default_affinity);
 
-	irq_desc[irq].affinity = mask;
-	irq_desc[irq].chip->set_affinity(irq, mask);
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
+	desc->chip->set_affinity(irq, mask);
 
 	set_balance_irq_affinity(irq, mask);
 	return 0;
@@ -140,7 +142,7 @@ int irq_select_affinity(unsigned int irq)
  */
 void disable_irq_nosync(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
 
 	if (irq >= nr_irqs)
@@ -169,7 +171,7 @@ EXPORT_SYMBOL(disable_irq_nosync);
  */
 void disable_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 
 	if (irq >= nr_irqs)
 		return;
@@ -211,7 +213,7 @@ static void __enable_irq(struct irq_desc *desc, unsigned int irq)
  */
 void enable_irq(unsigned int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
 
 	if (irq >= nr_irqs)
@@ -225,7 +227,7 @@ EXPORT_SYMBOL(enable_irq);
 
 static int set_irq_wake_real(unsigned int irq, unsigned int on)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	int ret = -ENXIO;
 
 	if (desc->chip->set_wake)
@@ -248,7 +250,7 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
  */
 int set_irq_wake(unsigned int irq, unsigned int on)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
 	int ret = 0;
 
@@ -288,12 +290,13 @@ EXPORT_SYMBOL(set_irq_wake);
  */
 int can_request_irq(unsigned int irq, unsigned long irqflags)
 {
+	struct irq_desc *desc = irq_to_desc(irq);
 	struct irqaction *action;
 
-	if (irq >= nr_irqs || irq_desc[irq].status & IRQ_NOREQUEST)
+	if (irq >= nr_irqs || desc->status & IRQ_NOREQUEST)
 		return 0;
 
-	action = irq_desc[irq].action;
+	action = desc->action;
 	if (action)
 		if (irqflags & action->flags & IRQF_SHARED)
 			action = NULL;
@@ -349,7 +352,7 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
  */
 int setup_irq(unsigned int irq, struct irqaction *new)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	struct irqaction *old, **p;
 	const char *old_name = NULL;
 	unsigned long flags;
@@ -518,7 +521,7 @@ void free_irq(unsigned int irq, void *dev_id)
 	if (irq >= nr_irqs)
 		return;
 
-	desc = irq_desc + irq;
+	desc = irq_to_desc(irq);
 	spin_lock_irqsave(&desc->lock, flags);
 	p = &desc->action;
 	for (;;) {
@@ -615,6 +618,7 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 {
 	struct irqaction *action;
 	int retval;
+	struct irq_desc *desc;
 
 #ifdef CONFIG_LOCKDEP
 	/*
@@ -632,7 +636,8 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 		return -EINVAL;
 	if (irq >= nr_irqs)
 		return -EINVAL;
-	if (irq_desc[irq].status & IRQ_NOREQUEST)
+	desc = irq_to_desc(irq);
+	if (desc->status & IRQ_NOREQUEST)
 		return -EINVAL;
 	if (!handler)
 		return -EINVAL;
diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c
index 77b7acc875c5..90b920d3f52b 100644
--- a/kernel/irq/migration.c
+++ b/kernel/irq/migration.c
@@ -3,18 +3,18 @@
 
 void set_pending_irq(unsigned int irq, cpumask_t mask)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
 
 	spin_lock_irqsave(&desc->lock, flags);
 	desc->status |= IRQ_MOVE_PENDING;
-	irq_desc[irq].pending_mask = mask;
+	desc->pending_mask = mask;
 	spin_unlock_irqrestore(&desc->lock, flags);
 }
 
 void move_masked_irq(int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	cpumask_t tmp;
 
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
@@ -30,7 +30,7 @@ void move_masked_irq(int irq)
 
 	desc->status &= ~IRQ_MOVE_PENDING;
 
-	if (unlikely(cpus_empty(irq_desc[irq].pending_mask)))
+	if (unlikely(cpus_empty(desc->pending_mask)))
 		return;
 
 	if (!desc->chip->set_affinity)
@@ -38,7 +38,7 @@ void move_masked_irq(int irq)
 
 	assert_spin_locked(&desc->lock);
 
-	cpus_and(tmp, irq_desc[irq].pending_mask, cpu_online_map);
+	cpus_and(tmp, desc->pending_mask, cpu_online_map);
 
 	/*
 	 * If there was a valid mask to work with, please
@@ -55,12 +55,12 @@ void move_masked_irq(int irq)
 	if (likely(!cpus_empty(tmp))) {
 		desc->chip->set_affinity(irq,tmp);
 	}
-	cpus_clear(irq_desc[irq].pending_mask);
+	cpus_clear(desc->pending_mask);
 }
 
 void move_native_irq(int irq)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
 		return;
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index e5225a65a4f9..c2f356c808f6 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -19,7 +19,7 @@ static struct proc_dir_entry *root_irq_dir;
 
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
-	struct irq_desc *desc = irq_desc + (long)m->private;
+	struct irq_desc *desc = irq_to_desc((long)m->private);
 	cpumask_t *mask = &desc->affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
@@ -43,7 +43,7 @@ static ssize_t irq_affinity_proc_write(struct file *file,
 	cpumask_t new_value;
 	int err;
 
-	if (!irq_desc[irq].chip->set_affinity || no_irq_affinity ||
+	if (!irq_to_desc(irq)->chip->set_affinity || no_irq_affinity ||
 	    irq_balancing_disabled(irq))
 		return -EIO;
 
@@ -132,20 +132,20 @@ static const struct file_operations default_affinity_proc_fops = {
 static int irq_spurious_read(char *page, char **start, off_t off,
 				  int count, int *eof, void *data)
 {
-	struct irq_desc *d = &irq_desc[(long) data];
+	struct irq_desc *desc = irq_to_desc((long) data);
 	return sprintf(page, "count %u\n"
 			     "unhandled %u\n"
 			     "last_unhandled %u ms\n",
-			d->irq_count,
-			d->irqs_unhandled,
-			jiffies_to_msecs(d->last_unhandled));
+			desc->irq_count,
+			desc->irqs_unhandled,
+			jiffies_to_msecs(desc->last_unhandled));
 }
 
 #define MAX_NAMELEN 128
 
 static int name_unique(unsigned int irq, struct irqaction *new_action)
 {
-	struct irq_desc *desc = irq_desc + irq;
+	struct irq_desc *desc = irq_to_desc(irq);
 	struct irqaction *action;
 	unsigned long flags;
 	int ret = 1;
@@ -165,8 +165,9 @@ static int name_unique(unsigned int irq, struct irqaction *new_action)
 void register_handler_proc(unsigned int irq, struct irqaction *action)
 {
 	char name [MAX_NAMELEN];
+	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (!irq_desc[irq].dir || action->dir || !action->name ||
+	if (!desc->dir || action->dir || !action->name ||
 					!name_unique(irq, action))
 		return;
 
@@ -174,7 +175,7 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
 	snprintf(name, MAX_NAMELEN, "%s", action->name);
 
 	/* create /proc/irq/1234/handler/ */
-	action->dir = proc_mkdir(name, irq_desc[irq].dir);
+	action->dir = proc_mkdir(name, desc->dir);
 }
 
 #undef MAX_NAMELEN
@@ -185,25 +186,24 @@ void register_irq_proc(unsigned int irq)
 {
 	char name [MAX_NAMELEN];
 	struct proc_dir_entry *entry;
+	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (!root_irq_dir ||
-		(irq_desc[irq].chip == &no_irq_chip) ||
-			irq_desc[irq].dir)
+	if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir)
 		return;
 
 	memset(name, 0, MAX_NAMELEN);
 	sprintf(name, "%d", irq);
 
 	/* create /proc/irq/1234 */
-	irq_desc[irq].dir = proc_mkdir(name, root_irq_dir);
+	desc->dir = proc_mkdir(name, root_irq_dir);
 
 #ifdef CONFIG_SMP
 	/* create /proc/irq/<irq>/smp_affinity */
-	proc_create_data("smp_affinity", 0600, irq_desc[irq].dir,
+	proc_create_data("smp_affinity", 0600, desc->dir,
 			 &irq_affinity_proc_fops, (void *)(long)irq);
 #endif
 
-	entry = create_proc_entry("spurious", 0444, irq_desc[irq].dir);
+	entry = create_proc_entry("spurious", 0444, desc->dir);
 	if (entry) {
 		entry->data = (void *)(long)irq;
 		entry->read_proc = irq_spurious_read;
@@ -214,8 +214,10 @@ void register_irq_proc(unsigned int irq)
 
 void unregister_handler_proc(unsigned int irq, struct irqaction *action)
 {
-	if (action->dir)
-		remove_proc_entry(action->dir->name, irq_desc[irq].dir);
+	if (action->dir) {
+		struct irq_desc *desc = irq_to_desc(irq);
+		remove_proc_entry(action->dir->name, desc->dir);
+	}
 }
 
 void register_default_affinity_proc(void)
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index cba8aa5bc7f4..89c7117acf2b 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -36,7 +36,7 @@ static void resend_irqs(unsigned long arg)
 	while (!bitmap_empty(irqs_resend, nr_irqs)) {
 		irq = find_first_bit(irqs_resend, nr_irqs);
 		clear_bit(irq, irqs_resend);
-		desc = irq_desc + irq;
+		desc = irq_to_desc(irq);
 		local_irq_disable();
 		desc->handle_irq(irq, desc);
 		local_irq_enable();
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index e26ca1e90c08..b5d906002e1d 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -92,11 +92,12 @@ static int misrouted_irq(int irq)
 	int ok = 0;
 
 	for (i = 1; i < nr_irqs; i++) {
-		struct irq_desc *desc = irq_desc + i;
+		struct irq_desc *desc;
 
 		if (i == irq)	/* Already tried */
 			continue;
 
+		desc = irq_to_desc(i);
 		if (try_one_irq(i, desc))
 			ok = 1;
 	}
@@ -108,7 +109,7 @@ static void poll_spurious_irqs(unsigned long dummy)
 {
 	int i;
 	for (i = 1; i < nr_irqs; i++) {
-		struct irq_desc *desc = irq_desc + i;
+		struct irq_desc *desc = irq_to_desc(i);
 		unsigned int status;
 
 		/* Racy but it doesn't matter */
-- 
cgit v1.2.3


From 3060d6fe28570640c2d7d66d38b9eaa848c3b9e3 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:08 -0700
Subject: x86: put timer_rand_state pointer into irq_desc

irq_timer_state[] is a NR_IRQS sized array that is a side-by array to
the real irq_desc[] array.

Integrate that field into the (now dynamic) irq_desc dynamic array and
save some RAM.

v2: keep the old way to support arch not support irq_desc

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 drivers/char/random.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++----
 include/linux/irq.h   |  2 ++
 2 files changed, 63 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 1610aa64c7cf..60c9c7ee6b2c 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -558,7 +558,7 @@ struct timer_rand_state {
 	unsigned dont_count_entropy:1;
 };
 
-static struct timer_rand_state input_timer_state;
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 
 #ifdef CONFIG_HAVE_DYN_ARRAY
 static struct timer_rand_state **irq_timer_state;
@@ -567,6 +567,51 @@ DEFINE_DYN_ARRAY(irq_timer_state, sizeof(struct timer_rand_state *), nr_irqs, PA
 static struct timer_rand_state *irq_timer_state[NR_IRQS];
 #endif
 
+static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
+{
+	if (irq >= nr_irqs)
+		return NULL;
+
+	return irq_timer_state[irq];
+}
+
+static void set_timer_rand_state(unsigned int irq, struct timer_rand_state *state)
+{
+	if (irq >= nr_irqs)
+		return;
+
+	irq_timer_state[irq] = state;
+}
+
+#else
+
+static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+
+	if (!desc)
+		return NULL;
+
+	return desc->timer_rand_state;
+}
+
+static void set_timer_rand_state(unsigned int irq, struct timer_rand_state *state)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+
+	if (!desc)
+		return;
+
+	desc->timer_rand_state = state;
+}
+#endif
+
+static struct timer_rand_state input_timer_state;
+
 /*
  * This function adds entropy to the entropy "pool" by using timing
  * delays.  It uses the timer_rand_state structure to make an estimate
@@ -654,11 +699,15 @@ EXPORT_SYMBOL_GPL(add_input_randomness);
 
 void add_interrupt_randomness(int irq)
 {
-	if (irq >= nr_irqs || irq_timer_state[irq] == NULL)
+	struct timer_rand_state *state;
+
+	state = get_timer_rand_state(irq);
+
+	if (state == NULL)
 		return;
 
 	DEBUG_ENT("irq event %d\n", irq);
-	add_timer_randomness(irq_timer_state[irq], 0x100 + irq);
+	add_timer_randomness(state, 0x100 + irq);
 }
 
 #ifdef CONFIG_BLOCK
@@ -918,7 +967,14 @@ void rand_initialize_irq(int irq)
 {
 	struct timer_rand_state *state;
 
-	if (irq >= nr_irqs || irq_timer_state[irq])
+#ifndef CONFIG_HAVE_SPARSE_IRQ
+	if (irq >= nr_irqs)
+		return;
+#endif
+
+	state = get_timer_rand_state(irq);
+
+	if (state)
 		return;
 
 	/*
@@ -927,7 +983,7 @@ void rand_initialize_irq(int irq)
 	 */
 	state = kzalloc(sizeof(struct timer_rand_state), GFP_KERNEL);
 	if (state)
-		irq_timer_state[irq] = state;
+		set_timer_rand_state(irq, state);
 }
 
 #ifdef CONFIG_BLOCK
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 80b8200f2adb..60c856aaac0f 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -127,6 +127,7 @@ struct irq_chip {
 	const char	*typename;
 };
 
+struct timer_rand_state;
 /**
  * struct irq_desc - interrupt descriptor
  *
@@ -155,6 +156,7 @@ struct irq_desc {
 	unsigned int		irq;
 #ifdef CONFIG_HAVE_SPARSE_IRQ
 	struct irq_desc		*next;
+	struct timer_rand_state *timer_rand_state;
 #endif
 	irq_flow_handler_t	handle_irq;
 	struct irq_chip		*chip;
-- 
cgit v1.2.3


From 7f95ec9e4c12fd067febfd57532da1166d75d858 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:09 -0700
Subject: x86: move kstat_irqs from kstat to irq_desc

based on Eric's patch ...

together mold it with dyn_array for irq_desc, will allcate kstat_irqs for
nr_irq_desc alltogether if needed. -- at that point nr_cpus is known already.

v2: make sure system without generic_hardirqs works they don't have irq_desc
v3: fix merging
v4: [mingo@elte.hu] fix typo

[ mingo@elte.hu ] irq: build fix

fix:

 arch/x86/xen/spinlock.c: In function 'xen_spin_lock_slow':
 arch/x86/xen/spinlock.c:90: error: 'struct kernel_stat' has no member named 'irqs'

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c   |  2 +-
 arch/x86/kernel/irq_32.c       |  4 +-
 arch/x86/kernel/irq_64.c       |  4 +-
 arch/x86/kernel/visws_quirks.c |  2 +-
 arch/x86/xen/spinlock.c        |  2 +-
 fs/proc/proc_misc.c            |  2 +-
 include/linux/irq.h            |  7 +++
 include/linux/kernel_stat.h    | 22 +++++++---
 kernel/irq/chip.c              | 15 +++----
 kernel/irq/handle.c            | 97 ++++++++++++++++++++++++++++++------------
 kernel/sched.c                 |  5 +--
 11 files changed, 106 insertions(+), 56 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index c2160cfdec9b..204884b1415a 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -526,7 +526,7 @@ static void do_irq_balance(void)
 			if (package_index == i)
 				IRQ_DELTA(package_index, j) = 0;
 			/* Determine the total count per processor per IRQ */
-			value_now = (unsigned long) kstat_cpu(i).irqs[j];
+			value_now = (unsigned long) kstat_irqs_cpu(j, i);
 
 			/* Determine the activity per processor per IRQ */
 			delta = value_now - LAST_CPU_IRQ(i, j);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index ede513be517d..576c5df6cad8 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -280,7 +280,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		any_count = kstat_irqs(i);
 #else
 		for_each_online_cpu(j)
-			any_count |= kstat_cpu(j).irqs[i];
+			any_count |= kstat_irqs_cpu(i, j);
 #endif
 		action = desc->action;
 		if (!action && !any_count)
@@ -290,7 +290,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
 		seq_printf(p, " %8s", desc->chip->name);
 		seq_printf(p, "-%-8s", desc->name);
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 738eb65a924e..4a0a4eb44dcb 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -90,7 +90,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		any_count = kstat_irqs(i);
 #else
 		for_each_online_cpu(j)
-			any_count |= kstat_cpu(j).irqs[i];
+			any_count |= kstat_irqs_cpu(i, j);
 #endif
 		action = desc->action;
 		if (!action && !any_count)
@@ -100,7 +100,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
 		for_each_online_cpu(j)
-			seq_printf(p, "%10u ", kstat_cpu(j).irqs[i]);
+			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
 		seq_printf(p, " %8s", desc->chip->name);
 		seq_printf(p, "-%-8s", desc->name);
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index 9d85ab384435..817aa55a1209 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -633,7 +633,7 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 	/*
 	 * handle this 'virtual interrupt' as a Cobalt one now.
 	 */
-	kstat_cpu(smp_processor_id()).irqs[realirq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	if (likely(desc->action != NULL))
 		handle_IRQ_event(realirq, desc->action);
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index dd71e3a021cd..bb6bc721b13d 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -241,7 +241,7 @@ static noinline int xen_spin_lock_slow(struct raw_spinlock *lock, bool irq_enabl
 		ADD_STATS(taken_slow_spurious, !xen_test_irq_pending(irq));
 	} while (!xen_test_irq_pending(irq)); /* check for spurious wakeups */
 
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(irq_to_desc(irq))++;
 
 out:
 	raw_local_irq_restore(flags);
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index a2173a2a5625..aa069acf61a0 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -532,7 +532,7 @@ static int show_stat(struct seq_file *p, void *v)
 		steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
 		guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
 		for (j = 0; j < nr_irqs; j++) {
-			unsigned int temp = kstat_cpu(i).irqs[j];
+			unsigned int temp = kstat_irqs_cpu(j, i);
 			sum += temp;
 			per_irq_sum[j] += temp;
 		}
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 60c856aaac0f..cbf471aee1ce 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -157,6 +157,11 @@ struct irq_desc {
 #ifdef CONFIG_HAVE_SPARSE_IRQ
 	struct irq_desc		*next;
 	struct timer_rand_state *timer_rand_state;
+#endif
+#ifdef CONFIG_HAVE_DYN_ARRAY
+	unsigned int            *kstat_irqs;
+#else
+	unsigned int            kstat_irqs[NR_CPUS];
 #endif
 	irq_flow_handler_t	handle_irq;
 	struct irq_chip		*chip;
@@ -190,6 +195,8 @@ extern struct irq_desc *irq_to_desc(unsigned int irq);
 /* could be removed if we get rid of all irq_desc reference */
 extern struct irq_desc irq_desc[NR_IRQS];
 #endif
+#define kstat_irqs_this_cpu(DESC) \
+	((DESC)->kstat_irqs[smp_processor_id()])
 
 /*
  * Migration helpers for obsolete names, they will go away:
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index fe1f7fe534b4..f10616712de5 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -28,10 +28,8 @@ struct cpu_usage_stat {
 
 struct kernel_stat {
 	struct cpu_usage_stat	cpustat;
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	unsigned int *irqs;
-#else
-	unsigned int irqs[NR_IRQS];
+#ifndef CONFIG_GENERIC_HARDIRQS
+       unsigned int irqs[NR_IRQS];
 #endif
 };
 
@@ -43,15 +41,25 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 
 extern unsigned long long nr_context_switches(void);
 
+#ifndef CONFIG_GENERIC_HARDIRQS
+static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
+{
+       return kstat_cpu(cpu).irqs[irq];
+}
+#else
+extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu);
+#endif
+
 /*
  * Number of interrupts per specific IRQ source, since bootup
  */
-static inline int kstat_irqs(int irq)
+static inline unsigned int kstat_irqs(unsigned int irq)
 {
-	int cpu, sum = 0;
+	unsigned int sum = 0;
+	int cpu;
 
 	for_each_possible_cpu(cpu)
-		sum += kstat_cpu(cpu).irqs[irq];
+		sum += kstat_irqs_cpu(irq, cpu);
 
 	return sum;
 }
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 76c225cf4b26..2aa3d4b2fce8 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -312,14 +312,13 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 {
 	struct irqaction *action;
 	irqreturn_t action_ret;
-	const unsigned int cpu = smp_processor_id();
 
 	spin_lock(&desc->lock);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	action = desc->action;
 	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
@@ -351,7 +350,6 @@ out_unlock:
 void
 handle_level_irq(unsigned int irq, struct irq_desc *desc)
 {
-	unsigned int cpu = smp_processor_id();
 	struct irqaction *action;
 	irqreturn_t action_ret;
 
@@ -361,7 +359,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	/*
 	 * If its disabled or no action available
@@ -399,7 +397,6 @@ out_unlock:
 void
 handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 {
-	unsigned int cpu = smp_processor_id();
 	struct irqaction *action;
 	irqreturn_t action_ret;
 
@@ -409,7 +406,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 		goto out;
 
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	/*
 	 * If its disabled or no action available
@@ -458,8 +455,6 @@ out:
 void
 handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 {
-	const unsigned int cpu = smp_processor_id();
-
 	spin_lock(&desc->lock);
 
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
@@ -476,7 +471,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		goto out_unlock;
 	}
 
-	kstat_cpu(cpu).irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	/* Start handling the irq */
 	desc->chip->ack(irq);
@@ -531,7 +526,7 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 {
 	irqreturn_t action_ret;
 
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 
 	if (desc->chip->ack)
 		desc->chip->ack(irq);
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 9fc33b3378e6..1f346990f3f8 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -37,7 +37,7 @@ void
 handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 {
 	print_irq_desc(irq, desc);
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 	ack_bad_irq(irq);
 }
 
@@ -80,17 +80,38 @@ static void init_one_irq_desc(struct irq_desc *desc)
 #endif
 }
 
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-static int nr_irq_desc = 32;
+extern int after_bootmem;
+extern void *__alloc_bootmem_nopanic(unsigned long size,
+			     unsigned long align,
+			     unsigned long goal);
 
-static int __init parse_nr_irq_desc(char *arg)
+static void init_kstat_irqs(struct irq_desc *desc, int nr_desc, int nr)
 {
-	if (arg)
-		nr_irq_desc = simple_strtoul(arg, NULL, 0);
-	return 0;
+	unsigned long bytes, total_bytes;
+	char *ptr;
+	int i;
+	unsigned long phys;
+
+	/* Compute how many bytes we need per irq and allocate them */
+	bytes = nr * sizeof(unsigned int);
+	total_bytes = bytes * nr_desc;
+	if (after_bootmem)
+		ptr = kzalloc(total_bytes, GFP_ATOMIC);
+	else
+		ptr = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
+
+	if (!ptr)
+		panic(" can not allocate kstat_irqs\n");
+
+	phys = __pa(ptr);
+	printk(KERN_DEBUG "kstat_irqs ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
+
+	for (i = 0; i < nr_desc; i++) {
+		desc[i].kstat_irqs = (unsigned int *)ptr;
+		ptr += bytes;
+	}
 }
 
-early_param("nr_irq_desc", parse_nr_irq_desc);
 
 static void __init init_work(void *data)
 {
@@ -100,25 +121,44 @@ static void __init init_work(void *data)
 
 	desc = *da->name;
 
-	for (i = 0; i < *da->nr; i++)
+	for (i = 0; i < *da->nr; i++) {
 		init_one_irq_desc(&desc[i]);
+#ifndef CONFIG_HAVE_SPARSE_IRQ
+		desc[i].irq = i;
+#endif
+	}
 
+#ifdef CONFIG_HAVE_SPARSE_IRQ
 	for (i = 1; i < *da->nr; i++)
 		desc[i-1].next = &desc[i];
+#endif
+
+	/* init kstat_irqs, nr_cpu_ids is ready already */
+	init_kstat_irqs(desc, *da->nr, nr_cpu_ids);
 }
 
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+static int nr_irq_desc = 32;
+
+static int __init parse_nr_irq_desc(char *arg)
+{
+	if (arg)
+		nr_irq_desc = simple_strtoul(arg, NULL, 0);
+	return 0;
+}
+
+early_param("nr_irq_desc", parse_nr_irq_desc);
+
 static struct irq_desc *sparse_irqs;
 DEFINE_DYN_ARRAY(sparse_irqs, sizeof(struct irq_desc), nr_irq_desc, PAGE_SIZE, init_work);
 
-extern int after_bootmem;
-extern void *__alloc_bootmem_nopanic(unsigned long size,
-			     unsigned long align,
-			     unsigned long goal);
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	struct irq_desc *desc, *desc_pri;
 	int i;
 	int count = 0;
+	unsigned long phys;
+	unsigned long total_bytes;
 
 	BUG_ON(irq == -1U);
 
@@ -141,38 +181,34 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 	 */
 	printk(KERN_DEBUG "try to get more irq_desc %d\n", nr_irq_desc);
 
+	total_bytes = sizeof(struct irq_desc) * nr_irq_desc;
 	if (after_bootmem)
-		desc = kzalloc(sizeof(struct irq_desc)*nr_irq_desc, GFP_ATOMIC);
+		desc = kzalloc(total_bytes, GFP_ATOMIC);
 	else
-		desc = __alloc_bootmem_nopanic(sizeof(struct irq_desc)*nr_irq_desc, PAGE_SIZE, 0);
+		desc = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
 
 	if (!desc)
 		panic("please boot with nr_irq_desc= %d\n", count * 2);
 
+	phys = __pa(desc);
+	printk(KERN_DEBUG "irq_desc ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
+
 	for (i = 0; i < nr_irq_desc; i++)
 		init_one_irq_desc(&desc[i]);
 
 	for (i = 1; i < nr_irq_desc; i++)
 		desc[i-1].next = &desc[i];
 
+	/* init kstat_irqs, nr_cpu_ids is ready already */
+	init_kstat_irqs(desc, nr_irq_desc, nr_cpu_ids);
+
 	desc->irq = irq;
 	desc_pri->next = desc;
 
 	return desc;
 }
 #else
-static void __init init_work(void *data)
-{
-	struct dyn_array *da = data;
-	int i;
-	struct  irq_desc *desc;
-
-	desc = *da->name;
 
-	for (i = 0; i < *da->nr; i++)
-		init_one_irq_desc(&desc[i]);
-
-}
 static struct irq_desc *irq_desc;
 DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);
 
@@ -315,7 +351,7 @@ unsigned int __do_IRQ(unsigned int irq)
 	struct irqaction *action;
 	unsigned int status;
 
-	kstat_this_cpu.irqs[irq]++;
+	kstat_irqs_this_cpu(desc)++;
 	if (CHECK_IRQ_PER_CPU(desc->status)) {
 		irqreturn_t action_ret;
 
@@ -415,3 +451,10 @@ void early_init_irq_lock_class(void)
 }
 #endif
 
+unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	return desc->kstat_irqs[cpu];
+}
+EXPORT_SYMBOL(kstat_irqs_cpu);
+
diff --git a/kernel/sched.c b/kernel/sched.c
index b9d713781b5b..6f230596bd0c 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -4048,11 +4048,8 @@ static inline void idle_balance(int cpu, struct rq *rq)
 #endif
 
 DEFINE_PER_CPU(struct kernel_stat, kstat);
-EXPORT_PER_CPU_SYMBOL(kstat);
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-DEFINE_PER_CPU_DYN_ARRAY_ADDR(per_cpu__kstat_irqs, per_cpu__kstat.irqs, sizeof(unsigned int), nr_irqs, sizeof(unsigned long), NULL);
-#endif
+EXPORT_PER_CPU_SYMBOL(kstat);
 
 /*
  * Return p->sum_exec_runtime plus any more ns on the sched_clock
-- 
cgit v1.2.3


From 9059d8fa4a3a9153da53da890039f7f956cc9d19 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:10 -0700
Subject: irq: add irq_desc_without_new

add an irq_desc accessor that will not allocate any sparse entry
but returns failure if there's no entry present.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/irq.h | 13 +++++++++++++
 kernel/irq/handle.c | 28 ++++++++++++++++++++++++----
 2 files changed, 37 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index cbf471aee1ce..c9ffef7c3b44 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -191,10 +191,23 @@ struct irq_desc {
 } ____cacheline_internodealigned_in_smp;
 
 extern struct irq_desc *irq_to_desc(unsigned int irq);
+extern struct irq_desc *__irq_to_desc(unsigned int irq);
+
+#ifndef CONFIG_HAVE_SPARSE_IRQ
+
 #ifndef CONFIG_HAVE_DYN_ARRAY
 /* could be removed if we get rid of all irq_desc reference */
 extern struct irq_desc irq_desc[NR_IRQS];
+#else
+extern struct irq_desc *irq_desc;
 #endif
+
+#else
+
+extern struct irq_desc *sparse_irqs;
+
+#endif
+
 #define kstat_irqs_this_cpu(DESC) \
 	((DESC)->kstat_irqs[smp_processor_id()])
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 1f346990f3f8..8e55dbe50afc 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -112,7 +112,6 @@ static void init_kstat_irqs(struct irq_desc *desc, int nr_desc, int nr)
 	}
 }
 
-
 static void __init init_work(void *data)
 {
 	struct dyn_array *da = data;
@@ -149,9 +148,27 @@ static int __init parse_nr_irq_desc(char *arg)
 
 early_param("nr_irq_desc", parse_nr_irq_desc);
 
-static struct irq_desc *sparse_irqs;
+struct irq_desc *sparse_irqs;
 DEFINE_DYN_ARRAY(sparse_irqs, sizeof(struct irq_desc), nr_irq_desc, PAGE_SIZE, init_work);
 
+struct irq_desc *__irq_to_desc(unsigned int irq)
+{
+	struct irq_desc *desc;
+
+	BUG_ON(irq == -1U);
+
+	desc = &sparse_irqs[0];
+	while (desc) {
+		if (desc->irq == irq)
+			return desc;
+
+		if (desc->irq == -1U)
+			return NULL;
+
+		desc = desc->next;
+	}
+	return NULL;
+}
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	struct irq_desc *desc, *desc_pri;
@@ -208,8 +225,7 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 	return desc;
 }
 #else
-
-static struct irq_desc *irq_desc;
+struct irq_desc *irq_desc;
 DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);
 
 #endif
@@ -239,6 +255,10 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 
 	return NULL;
 }
+struct irq_desc *__irq_to_desc(unsigned int irq)
+{
+	return irq_to_desc(irq);
+}
 #endif
 
 /*
-- 
cgit v1.2.3


From 2c6927a38f65b53b62f86158fba29a068c4e8b6a Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:11 -0700
Subject: irq: replace loop with nr_irqs with for_each_irq_desc

There are a handful of loops that go from 0 to nr_irqs and use
get_irq_desc() on them. These would allocate all the irq_desc
entries, regardless of the need for them.

Use the smarter for_each_irq_desc() iterator that will only iterate
over the present ones.

v2: make sure arch without GENERIC_HARDIRQS work too

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_64.c |  6 +++---
 arch/x86/kernel/irq_64.c     |  5 ++---
 arch/x86/kernel/irqinit_64.c | 17 +++++------------
 include/linux/irq.h          |  7 +++++++
 kernel/irq/internals.h       |  4 ++--
 kernel/irq/manage.c          |  2 +-
 kernel/irq/proc.c            | 10 +++++-----
 7 files changed, 25 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 51ef7eb75f2e..708be9724daf 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1871,10 +1871,10 @@ unmask:
 
 static void ir_irq_migration(struct work_struct *work)
 {
-	int irq;
+	unsigned int irq;
+	struct irq_desc *desc;
 
-	for (irq = 0; irq < nr_irqs; irq++) {
-		struct irq_desc *desc = irq_to_desc(irq);
+	for_each_irq_desc(irq, desc) {
 		if (desc->status & IRQ_MOVE_PENDING) {
 			unsigned long flags;
 
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 4a0a4eb44dcb..b3cf55e325f5 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -224,17 +224,16 @@ void fixup_irqs(cpumask_t map)
 {
 	unsigned int irq;
 	static int warned;
+	struct irq_desc *desc;
 
-	for (irq = 0; irq < nr_irqs; irq++) {
+	for_each_irq_desc(irq, desc) {
 		cpumask_t mask;
 		int break_affinity = 0;
 		int set_affinity = 1;
-		struct irq_desc *desc;
 
 		if (irq == 2)
 			continue;
 
-		desc = irq_to_desc(irq);
 		/* interrupt's are disabled at this point */
 		spin_lock(&desc->lock);
 
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index 0744b49b4d12..cd9f42d028d9 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -142,25 +142,18 @@ void __init init_ISA_irqs(void)
 	init_bsp_APIC();
 	init_8259A(0);
 
-	for (i = 0; i < nr_irqs; i++) {
+	for (i = 0; i < 16; i++) {
 		struct irq_desc *desc = irq_to_desc(i);
 
 		desc->status = IRQ_DISABLED;
 		desc->action = NULL;
 		desc->depth = 1;
 
-		if (i < 16) {
-			/*
-			 * 16 old-style INTA-cycle interrupts:
-			 */
-			set_irq_chip_and_handler_name(i, &i8259A_chip,
+		/*
+		 * 16 old-style INTA-cycle interrupts:
+		 */
+		set_irq_chip_and_handler_name(i, &i8259A_chip,
 						      handle_level_irq, "XT");
-		} else {
-			/*
-			 * 'high' PCI IRQs filled in on demand
-			 */
-			desc->chip = &no_irq_chip;
-		}
 	}
 }
 
diff --git a/include/linux/irq.h b/include/linux/irq.h
index c9ffef7c3b44..9de16ca8b8e5 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -202,9 +202,16 @@ extern struct irq_desc irq_desc[NR_IRQS];
 extern struct irq_desc *irq_desc;
 #endif
 
+#ifdef CONFIG_GENERIC_HARDIRQS
+#define for_each_irq_desc(irq, desc)		\
+	for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc = &irq_desc[irq])
+#endif
+
 #else
 
 extern struct irq_desc *sparse_irqs;
+#define for_each_irq_desc(irqX, desc)		\
+	for (desc = sparse_irqs, irqX = desc->irq; desc && irqX != -1U; desc = desc->next, irqX = desc ? desc->irq : -1U)
 
 #endif
 
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 422dd00c8bd3..c9767e641980 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -14,11 +14,11 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		unsigned long flags);
 
 #ifdef CONFIG_PROC_FS
-extern void register_irq_proc(unsigned int irq);
+extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
 extern void register_handler_proc(unsigned int irq, struct irqaction *action);
 extern void unregister_handler_proc(unsigned int irq, struct irqaction *action);
 #else
-static inline void register_irq_proc(unsigned int irq) { }
+static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { }
 static inline void register_handler_proc(unsigned int irq,
 					 struct irqaction *action) { }
 static inline void unregister_handler_proc(unsigned int irq,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index b5943e9f95aa..5070f55fdc16 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -478,7 +478,7 @@ int setup_irq(unsigned int irq, struct irqaction *new)
 	spin_unlock_irqrestore(&desc->lock, flags);
 
 	new->irq = irq;
-	register_irq_proc(irq);
+	register_irq_proc(irq, desc);
 	new->dir = NULL;
 	register_handler_proc(irq, new);
 
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index c2f356c808f6..bc0993d86c8b 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -182,11 +182,10 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
 
 #define MAX_NAMELEN 10
 
-void register_irq_proc(unsigned int irq)
+void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
 	char name [MAX_NAMELEN];
 	struct proc_dir_entry *entry;
-	struct irq_desc *desc = irq_to_desc(irq);
 
 	if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir)
 		return;
@@ -230,7 +229,8 @@ void register_default_affinity_proc(void)
 
 void init_irq_proc(void)
 {
-	int i;
+	unsigned int irq;
+	struct irq_desc *desc;
 
 	/* create /proc/irq */
 	root_irq_dir = proc_mkdir("irq", NULL);
@@ -242,7 +242,7 @@ void init_irq_proc(void)
 	/*
 	 * Create entries for all existing IRQs.
 	 */
-	for (i = 0; i < nr_irqs; i++)
-		register_irq_proc(i);
+	for_each_irq_desc(irq, desc)
+		register_irq_proc(irq, desc);
 }
 
-- 
cgit v1.2.3


From c7fb03a475bd80c642c1345d85c7c550f63514b8 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:12 -0700
Subject: irq, fs/proc: replace loop with nr_irqs for proc/stat

Replace another nr_irqs loop to avoid the allocation of all sparse
irq entries - use for_each_irq_desc instead.

v2: make sure arch without GENERIC_HARDIRQS works too

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 fs/proc/proc_misc.c       | 42 ++++++++++++++++++++++++++++--------------
 include/linux/interrupt.h |  5 +++++
 2 files changed, 33 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index aa069acf61a0..c3cbabe8b38e 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -30,6 +30,7 @@
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/pagemap.h>
+#include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
@@ -501,17 +502,16 @@ static const struct file_operations proc_vmalloc_operations = {
 
 static int show_stat(struct seq_file *p, void *v)
 {
-	int i;
+	int i, j;
 	unsigned long jif;
 	cputime64_t user, nice, system, idle, iowait, irq, softirq, steal;
 	cputime64_t guest;
 	u64 sum = 0;
 	struct timespec boottime;
-	unsigned int *per_irq_sum;
-
-	per_irq_sum = kzalloc(sizeof(unsigned int)*nr_irqs, GFP_KERNEL);
-	if (!per_irq_sum)
-		return -ENOMEM;
+	unsigned int per_irq_sum;
+#ifdef CONFIG_GENERIC_HARDIRQS
+	struct irq_desc *desc;
+#endif
 
 	user = nice = system = idle = iowait =
 		irq = softirq = steal = cputime64_zero;
@@ -520,8 +520,6 @@ static int show_stat(struct seq_file *p, void *v)
 	jif = boottime.tv_sec;
 
 	for_each_possible_cpu(i) {
-		int j;
-
 		user = cputime64_add(user, kstat_cpu(i).cpustat.user);
 		nice = cputime64_add(nice, kstat_cpu(i).cpustat.nice);
 		system = cputime64_add(system, kstat_cpu(i).cpustat.system);
@@ -531,10 +529,12 @@ static int show_stat(struct seq_file *p, void *v)
 		softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
 		steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
 		guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
-		for (j = 0; j < nr_irqs; j++) {
-			unsigned int temp = kstat_irqs_cpu(j, i);
+		for_each_irq_desc(j, desc)
+		{
+			unsigned int temp;
+
+			temp = kstat_irqs_cpu(j, i);
 			sum += temp;
-			per_irq_sum[j] += temp;
 		}
 		sum += arch_irq_stat_cpu(i);
 	}
@@ -577,8 +577,23 @@ static int show_stat(struct seq_file *p, void *v)
 	}
 	seq_printf(p, "intr %llu", (unsigned long long)sum);
 
-	for (i = 0; i < nr_irqs; i++)
-		seq_printf(p, " %u", per_irq_sum[i]);
+	/* sum again ? it could be updated? */
+	for_each_irq_desc(j, desc)
+	{
+		per_irq_sum = 0;
+		for_each_possible_cpu(i) {
+			unsigned int temp;
+
+			temp = kstat_irqs_cpu(j, i);
+			per_irq_sum += temp;
+		}
+
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+		seq_printf(p, " %u:%u", j, per_irq_sum);
+#else
+		seq_printf(p, " %u", per_irq_sum);
+#endif
+	}
 
 	seq_printf(p,
 		"\nctxt %llu\n"
@@ -592,7 +607,6 @@ static int show_stat(struct seq_file *p, void *v)
 		nr_running(),
 		nr_iowait());
 
-	kfree(per_irq_sum);
 	return 0;
 }
 
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 511803853a5b..d4039a0b23f4 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -17,6 +17,11 @@
 
 extern int nr_irqs;
 
+#ifndef CONFIG_GENERIC_HARDIRQS
+#define for_each_irq_desc(irq, desc)		\
+	for (irq = 0; irq < nr_irqs; irq++)
+#endif
+
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
  * linux/ioport.h to select the interrupt line behaviour.  When
-- 
cgit v1.2.3


From 46926b67fc663d357a1a8174328998a9e49da0b8 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:15 -0700
Subject: generic: add irq_desc in function in parameter

So we could remove some duplicated calling to irq_desc

v2: make sure irq_desc in  init/main.c is not used without generic_hardirqs

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/irq_64.c |  6 ++++--
 include/linux/irq.h      |  9 ++++++---
 init/main.c              |  7 +++++++
 kernel/irq/handle.c      | 30 ++++++++++++++++++++++++++++++
 4 files changed, 47 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index a3e36336d914..f58b995b30ee 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -189,6 +189,7 @@ u64 arch_irq_stat(void)
 asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
+	struct irq_desc *desc;
 
 	/* high bit used in ret_from_ code  */
 	unsigned vector = ~regs->orig_ax;
@@ -202,8 +203,9 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 	stack_overflow_check(regs);
 #endif
 
-	if (likely(__irq_to_desc(irq)))
-		generic_handle_irq(irq);
+	desc = __irq_to_desc(irq);
+	if (likely(desc))
+		generic_handle_irq_desc(irq, desc);
 	else {
 		if (!disable_apic)
 			ack_APIC_irq();
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 9de16ca8b8e5..7b59e193a119 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -315,10 +315,8 @@ extern unsigned int __do_IRQ(unsigned int irq);
  * irqchip-style controller then we call the ->handle_irq() handler,
  * and it calls __do_IRQ() if it's attached to an irqtype-style controller.
  */
-static inline void generic_handle_irq(unsigned int irq)
+static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
 #ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
 	desc->handle_irq(irq, desc);
 #else
@@ -329,6 +327,11 @@ static inline void generic_handle_irq(unsigned int irq)
 #endif
 }
 
+static inline void generic_handle_irq(unsigned int irq)
+{
+	generic_handle_irq_desc(irq, irq_to_desc(irq));
+}
+
 /* Handling of unhandled and spurious interrupts: */
 extern void note_interrupt(unsigned int irq, struct irq_desc *desc,
 			   int action_ret);
diff --git a/init/main.c b/init/main.c
index ab97d0877acc..0d2e60144f83 100644
--- a/init/main.c
+++ b/init/main.c
@@ -590,6 +590,13 @@ void pre_alloc_dyn_array(void)
 		if (da->init_work)
 			da->init_work(da);
 	}
+#else
+#ifdef CONFIF_GENERIC_HARDIRQS
+	unsigned int i;
+
+	for (i = 0; i < NR_IRQS; i++)
+		irq_desc[i].irq = i;
+#endif
 #endif
 }
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 8e55dbe50afc..e1d787e9169b 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -197,6 +197,21 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 	 *  we run out of pre-allocate ones, allocate more
 	 */
 	printk(KERN_DEBUG "try to get more irq_desc %d\n", nr_irq_desc);
+	{
+		/* double check if some one mess up the list */
+		struct irq_desc *desc;
+		int count = 0;
+
+		desc = &sparse_irqs[0];
+		while (desc) {
+			printk(KERN_DEBUG "found irq_desc for irq %d\n", desc->irq);
+			if (desc->next)
+				printk(KERN_DEBUG "found irq_desc for irq %d and next will be irq %d\n", desc->irq, desc->next->irq);
+			desc = desc->next;
+			count++;
+		}
+		printk(KERN_DEBUG "all preallocted %d\n", count);
+	}
 
 	total_bytes = sizeof(struct irq_desc) * nr_irq_desc;
 	if (after_bootmem)
@@ -221,6 +236,21 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 
 	desc->irq = irq;
 	desc_pri->next = desc;
+	{
+		/* double check if some one mess up the list */
+		struct irq_desc *desc;
+		int count = 0;
+
+		desc = &sparse_irqs[0];
+		while (desc) {
+			printk(KERN_DEBUG "1 found irq_desc for irq %d\n", desc->irq);
+			if (desc->next)
+				printk(KERN_DEBUG "1 found irq_desc for irq %d and next will be irq %d\n", desc->irq, desc->next->irq);
+			desc = desc->next;
+			count++;
+		}
+		printk(KERN_DEBUG "1 all preallocted %d\n", count);
+	}
 
 	return desc;
 }
-- 
cgit v1.2.3


From cb5bc83225a86ca53bbb889ed8439e4fd6cf44ac Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:17 -0700
Subject: x86_64: rename irq_desc/irq_desc_alloc

change names:

          irq_desc() ==> irq_desc_alloc
	__irq_desc() ==> irq_desc

Also split a few of the uses in lowlevel x86 code.

v2: need to check if desc is null in smp_irq_move_cleanup

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_64.c | 10 +++++++++-
 arch/x86/kernel/irq_64.c     |  4 ++--
 arch/x86/kernel/irqinit_64.c |  3 ++-
 include/linux/irq.h          |  2 +-
 kernel/irq/chip.c            | 21 +++++++++++----------
 kernel/irq/handle.c          | 23 +++++------------------
 kernel/irq/manage.c          | 16 ++++++++--------
 7 files changed, 38 insertions(+), 41 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 1b8cccb5ba25..a054db9ef190 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -1124,7 +1124,12 @@ static void ioapic_register_intr(int irq, unsigned long trigger)
 {
 	struct irq_desc *desc;
 
-	desc = irq_to_desc(irq);
+	/* first time to use this irq_desc */
+	if (irq < 16)
+		desc = irq_to_desc(irq);
+	else
+		desc = irq_to_desc_alloc(irq);
+
 	if (trigger)
 		desc->status |= IRQ_LEVEL;
 	else
@@ -1919,6 +1924,9 @@ asmlinkage void smp_irq_move_cleanup_interrupt(void)
 		irq = __get_cpu_var(vector_irq)[vector];
 
 		desc = irq_to_desc(irq);
+		if (!desc)
+			continue;
+
 		cfg = irq_cfg(irq);
 		spin_lock(&desc->lock);
 		if (!cfg->move_cleanup_count)
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index f337f87c1e16..5d5976e0311a 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -83,7 +83,7 @@ int show_interrupts(struct seq_file *p, void *v)
 
 	if (i < nr_irqs) {
 		unsigned any_count = 0;
-		struct irq_desc *desc = __irq_to_desc(i);
+		struct irq_desc *desc = irq_to_desc(i);
 
 		if (!desc)
 			return 0;
@@ -206,7 +206,7 @@ asmlinkage unsigned int do_IRQ(struct pt_regs *regs)
 	stack_overflow_check(regs);
 #endif
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (likely(desc))
 		generic_handle_irq_desc(irq, desc);
 	else {
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index cd9f42d028d9..d17fbc26d96f 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -143,7 +143,8 @@ void __init init_ISA_irqs(void)
 	init_8259A(0);
 
 	for (i = 0; i < 16; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
+		/* first time call this irq_desc */
+		struct irq_desc *desc = irq_to_desc_alloc(i);
 
 		desc->status = IRQ_DISABLED;
 		desc->action = NULL;
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 7b59e193a119..5fe1b01c11fe 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -191,7 +191,7 @@ struct irq_desc {
 } ____cacheline_internodealigned_in_smp;
 
 extern struct irq_desc *irq_to_desc(unsigned int irq);
-extern struct irq_desc *__irq_to_desc(unsigned int irq);
+extern struct irq_desc *irq_to_desc_alloc(unsigned int irq);
 
 #ifndef CONFIG_HAVE_SPARSE_IRQ
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index a4bb0da9c88c..9fc5e69213de 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -27,7 +27,8 @@ void dynamic_irq_init(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	desc = irq_to_desc(irq);
+	/* first time to use this irq_desc */
+	desc = irq_to_desc_alloc(irq);
 	if (!desc) {
 		WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
 		return;
@@ -60,7 +61,7 @@ void dynamic_irq_cleanup(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc) {
 		WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
 		return;
@@ -92,7 +93,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc) {
 		WARN(1, KERN_ERR "Trying to install chip for IRQ%d\n", irq);
 		return -EINVAL;
@@ -122,7 +123,7 @@ int set_irq_type(unsigned int irq, unsigned int type)
 	unsigned long flags;
 	int ret = -ENXIO;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc) {
 		printk(KERN_ERR "Trying to set irq type for IRQ%d\n", irq);
 		return -ENODEV;
@@ -150,7 +151,7 @@ int set_irq_data(unsigned int irq, void *data)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc) {
 		printk(KERN_ERR
 		       "Trying to install controller data for IRQ%d\n", irq);
@@ -176,7 +177,7 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc) {
 		printk(KERN_ERR
 		       "Trying to install msi data for IRQ%d\n", irq);
@@ -203,7 +204,7 @@ int set_irq_chip_data(unsigned int irq, void *data)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc) {
 		printk(KERN_ERR
 		       "Trying to install chip data for IRQ%d\n", irq);
@@ -554,7 +555,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc) {
 		printk(KERN_ERR
 		       "Trying to install type control for IRQ%d\n", irq);
@@ -618,7 +619,7 @@ void __init set_irq_noprobe(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc) {
 		printk(KERN_ERR "Trying to mark IRQ%d non-probeable\n", irq);
 
@@ -635,7 +636,7 @@ void __init set_irq_probe(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc) {
 		printk(KERN_ERR "Trying to mark IRQ%d probeable\n", irq);
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index e1d787e9169b..d44e3515eae1 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -151,7 +151,7 @@ early_param("nr_irq_desc", parse_nr_irq_desc);
 struct irq_desc *sparse_irqs;
 DEFINE_DYN_ARRAY(sparse_irqs, sizeof(struct irq_desc), nr_irq_desc, PAGE_SIZE, init_work);
 
-struct irq_desc *__irq_to_desc(unsigned int irq)
+struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	struct irq_desc *desc;
 
@@ -169,7 +169,7 @@ struct irq_desc *__irq_to_desc(unsigned int irq)
 	}
 	return NULL;
 }
-struct irq_desc *irq_to_desc(unsigned int irq)
+struct irq_desc *irq_to_desc_alloc(unsigned int irq)
 {
 	struct irq_desc *desc, *desc_pri;
 	int i;
@@ -186,6 +186,7 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 
 		if (desc->irq == -1U) {
 			desc->irq = irq;
+			printk(KERN_DEBUG "found new irq_desc for irq %d\n", desc->irq);
 			return desc;
 		}
 		desc_pri = desc;
@@ -236,21 +237,7 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 
 	desc->irq = irq;
 	desc_pri->next = desc;
-	{
-		/* double check if some one mess up the list */
-		struct irq_desc *desc;
-		int count = 0;
-
-		desc = &sparse_irqs[0];
-		while (desc) {
-			printk(KERN_DEBUG "1 found irq_desc for irq %d\n", desc->irq);
-			if (desc->next)
-				printk(KERN_DEBUG "1 found irq_desc for irq %d and next will be irq %d\n", desc->irq, desc->next->irq);
-			desc = desc->next;
-			count++;
-		}
-		printk(KERN_DEBUG "1 all preallocted %d\n", count);
-	}
+	printk(KERN_DEBUG "1 found new irq_desc for irq %d and pri will be irq %d\n", desc->irq, desc_pri->irq);
 
 	return desc;
 }
@@ -285,7 +272,7 @@ struct irq_desc *irq_to_desc(unsigned int irq)
 
 	return NULL;
 }
-struct irq_desc *__irq_to_desc(unsigned int irq)
+struct irq_desc *irq_to_desc_alloc(unsigned int irq)
 {
 	return irq_to_desc(irq);
 }
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index c0b4d4df6de2..6df49218632a 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -31,7 +31,7 @@ cpumask_t irq_default_affinity = CPU_MASK_ALL;
  */
 void synchronize_irq(unsigned int irq)
 {
-	struct irq_desc *desc = __irq_to_desc(irq);
+	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned int status;
 
 	if (!desc)
@@ -145,7 +145,7 @@ void disable_irq_nosync(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc)
 		return;
 
@@ -174,7 +174,7 @@ void disable_irq(unsigned int irq)
 {
 	struct irq_desc *desc;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc)
 		return;
 
@@ -218,7 +218,7 @@ void enable_irq(unsigned int irq)
 	struct irq_desc *desc;
 	unsigned long flags;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc)
 		return;
 
@@ -296,7 +296,7 @@ int can_request_irq(unsigned int irq, unsigned long irqflags)
 	struct irq_desc *desc;
 	struct irqaction *action;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc)
 		return 0;
 
@@ -366,7 +366,7 @@ int setup_irq(unsigned int irq, struct irqaction *new)
 	int shared = 0;
 	int ret;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc)
 		return -EINVAL;
 
@@ -527,7 +527,7 @@ void free_irq(unsigned int irq, void *dev_id)
 
 	WARN_ON(in_interrupt());
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc)
 		return;
 
@@ -644,7 +644,7 @@ int request_irq(unsigned int irq, irq_handler_t handler,
 	if ((irqflags & IRQF_SHARED) && !dev_id)
 		return -EINVAL;
 
-	desc = __irq_to_desc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc)
 		return -EINVAL;
 
-- 
cgit v1.2.3


From 67fb283e148e9bd761f73691d3173b6eab9ba8db Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:18 -0700
Subject: irq: separate sparse_irqs from sparse_irqs_free

so later don't need compare with -1U

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/irq.h |   2 +-
 kernel/irq/handle.c | 115 ++++++++++++++++++++++++++++------------------------
 2 files changed, 62 insertions(+), 55 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 5fe1b01c11fe..d5749852ee69 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -211,7 +211,7 @@ extern struct irq_desc *irq_desc;
 
 extern struct irq_desc *sparse_irqs;
 #define for_each_irq_desc(irqX, desc)		\
-	for (desc = sparse_irqs, irqX = desc->irq; desc && irqX != -1U; desc = desc->next, irqX = desc ? desc->irq : -1U)
+	for (desc = sparse_irqs, irqX = desc->irq; desc; desc = desc->next, irqX = desc ? desc->irq : -1U)
 
 #endif
 
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index d44e3515eae1..6d174390f3a0 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -112,6 +112,11 @@ static void init_kstat_irqs(struct irq_desc *desc, int nr_desc, int nr)
 	}
 }
 
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+static struct irq_desc *sparse_irqs_free;
+struct irq_desc *sparse_irqs;
+#endif
+
 static void __init init_work(void *data)
 {
 	struct dyn_array *da = data;
@@ -127,13 +132,16 @@ static void __init init_work(void *data)
 #endif
 	}
 
+	/* init kstat_irqs, nr_cpu_ids is ready already */
+	init_kstat_irqs(desc, *da->nr, nr_cpu_ids);
+
 #ifdef CONFIG_HAVE_SPARSE_IRQ
 	for (i = 1; i < *da->nr; i++)
 		desc[i-1].next = &desc[i];
-#endif
 
-	/* init kstat_irqs, nr_cpu_ids is ready already */
-	init_kstat_irqs(desc, *da->nr, nr_cpu_ids);
+	sparse_irqs_free = sparse_irqs;
+	sparse_irqs = NULL;
+#endif
 }
 
 #ifdef CONFIG_HAVE_SPARSE_IRQ
@@ -148,23 +156,17 @@ static int __init parse_nr_irq_desc(char *arg)
 
 early_param("nr_irq_desc", parse_nr_irq_desc);
 
-struct irq_desc *sparse_irqs;
 DEFINE_DYN_ARRAY(sparse_irqs, sizeof(struct irq_desc), nr_irq_desc, PAGE_SIZE, init_work);
 
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	struct irq_desc *desc;
 
-	BUG_ON(irq == -1U);
-
-	desc = &sparse_irqs[0];
+	desc = sparse_irqs;
 	while (desc) {
 		if (desc->irq == irq)
 			return desc;
 
-		if (desc->irq == -1U)
-			return NULL;
-
 		desc = desc->next;
 	}
 	return NULL;
@@ -174,21 +176,12 @@ struct irq_desc *irq_to_desc_alloc(unsigned int irq)
 	struct irq_desc *desc, *desc_pri;
 	int i;
 	int count = 0;
-	unsigned long phys;
-	unsigned long total_bytes;
 
-	BUG_ON(irq == -1U);
-
-	desc_pri = desc = &sparse_irqs[0];
+	desc_pri = desc = sparse_irqs;
 	while (desc) {
 		if (desc->irq == irq)
 			return desc;
 
-		if (desc->irq == -1U) {
-			desc->irq = irq;
-			printk(KERN_DEBUG "found new irq_desc for irq %d\n", desc->irq);
-			return desc;
-		}
 		desc_pri = desc;
 		desc = desc->next;
 		count++;
@@ -197,48 +190,62 @@ struct irq_desc *irq_to_desc_alloc(unsigned int irq)
 	/*
 	 *  we run out of pre-allocate ones, allocate more
 	 */
-	printk(KERN_DEBUG "try to get more irq_desc %d\n", nr_irq_desc);
-	{
-		/* double check if some one mess up the list */
-		struct irq_desc *desc;
-		int count = 0;
-
-		desc = &sparse_irqs[0];
-		while (desc) {
-			printk(KERN_DEBUG "found irq_desc for irq %d\n", desc->irq);
-			if (desc->next)
-				printk(KERN_DEBUG "found irq_desc for irq %d and next will be irq %d\n", desc->irq, desc->next->irq);
-			desc = desc->next;
-			count++;
-		}
-		printk(KERN_DEBUG "all preallocted %d\n", count);
-	}
+	if (!sparse_irqs_free) {
+		unsigned long phys;
+		unsigned long total_bytes;
 
-	total_bytes = sizeof(struct irq_desc) * nr_irq_desc;
-	if (after_bootmem)
-		desc = kzalloc(total_bytes, GFP_ATOMIC);
-	else
-		desc = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
+		printk(KERN_DEBUG "try to get more irq_desc %d\n", nr_irq_desc);
 
-	if (!desc)
-		panic("please boot with nr_irq_desc= %d\n", count * 2);
+		total_bytes = sizeof(struct irq_desc) * nr_irq_desc;
+		if (after_bootmem)
+			desc = kzalloc(total_bytes, GFP_ATOMIC);
+		else
+			desc = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
 
-	phys = __pa(desc);
-	printk(KERN_DEBUG "irq_desc ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
+		if (!desc)
+			panic("please boot with nr_irq_desc= %d\n", count * 2);
 
-	for (i = 0; i < nr_irq_desc; i++)
-		init_one_irq_desc(&desc[i]);
+		phys = __pa(desc);
+		printk(KERN_DEBUG "irq_desc ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
 
-	for (i = 1; i < nr_irq_desc; i++)
-		desc[i-1].next = &desc[i];
+		for (i = 0; i < nr_irq_desc; i++)
+			init_one_irq_desc(&desc[i]);
 
-	/* init kstat_irqs, nr_cpu_ids is ready already */
-	init_kstat_irqs(desc, nr_irq_desc, nr_cpu_ids);
+		for (i = 1; i < nr_irq_desc; i++)
+			desc[i-1].next = &desc[i];
 
-	desc->irq = irq;
-	desc_pri->next = desc;
-	printk(KERN_DEBUG "1 found new irq_desc for irq %d and pri will be irq %d\n", desc->irq, desc_pri->irq);
+		/* init kstat_irqs, nr_cpu_ids is ready already */
+		init_kstat_irqs(desc, nr_irq_desc, nr_cpu_ids);
 
+		sparse_irqs_free = desc;
+	}
+
+	desc = sparse_irqs_free;
+	sparse_irqs_free = sparse_irqs_free->next;
+	desc->next = NULL;
+	if (desc_pri)
+		desc_pri->next = desc;
+	else
+		sparse_irqs = desc;
+	desc->irq = irq;
+	printk(KERN_DEBUG "found new irq_desc for irq %d\n", desc->irq);
+#ifdef CONFIG_HAVE_SPARSE_IRQ_DEBUG
+	{
+		/* dump the results */
+		struct irq_desc *desc;
+		unsigned long phys;
+		unsigned long bytes = sizeof(struct irq_desc);
+		unsigned int irqx;
+
+		printk(KERN_DEBUG "=========================== %d\n", irq);
+		printk(KERN_DEBUG "irq_desc dump after get that for %d\n", irq);
+		for_each_irq_desc(irqx, desc) {
+			phys = __pa(desc);
+			printk(KERN_DEBUG "irq_desc %d ==> [%#lx - %#lx]\n", irqx, phys, phys + bytes);
+		}
+		printk(KERN_DEBUG "===========================\n");
+	}
+#endif
 	return desc;
 }
 #else
-- 
cgit v1.2.3


From e420dfb40c453a9760b86c7f338052bdb4dfa755 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:21 -0700
Subject: x86: put irq_2_iommu pointer into irq_desc

when CONFIG_HAVE_SPARSE_IRQ
preallocate some irq_2_iommu entries, and use get_one_free_irq_2_iomm to
get new one and link to irq_desc if needed.

else will use dyn_array or static array.

v2: <= nr_irqs fix

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 drivers/pci/intr_remapping.c | 213 +++++++++++++++++++++++++++++++++----------
 include/linux/irq.h          |   4 +
 2 files changed, 169 insertions(+), 48 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index 6961be807684..23372c811159 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -19,41 +19,136 @@ struct irq_2_iommu {
 	u8  irte_mask;
 };
 
-#ifdef CONFIG_HAVE_DYNA_ARRAY
-static struct irq_2_iommu *irq_2_iommu;
-DEFINE_DYN_ARRAY(irq_2_iommu, sizeof(struct irq_2_iommu), nr_irqs, PAGE_SIZE, NULL);
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+static struct irq_2_iommu *irq_2_iommuX;
+/* fill one page ? */
+static int nr_irq_2_iommu = 0x100;
+static int irq_2_iommu_index;
+DEFINE_DYN_ARRAY(irq_2_iommuX, sizeof(struct irq_2_iommu), nr_irq_2_iommu, PAGE_SIZE, NULL);
+
+extern void *__alloc_bootmem_nopanic(unsigned long size,
+				     unsigned long align,
+				     unsigned long goal);
+
+static struct irq_2_iommu *get_one_free_irq_2_iommu(int not_used)
+{
+	struct irq_2_iommu *iommu;
+	unsigned long total_bytes;
+
+	if (irq_2_iommu_index >= nr_irq_2_iommu) {
+		/*
+		 *  we run out of pre-allocate ones, allocate more
+		 */
+		printk(KERN_DEBUG "try to get more irq_2_iommu %d\n", nr_irq_2_iommu);
+
+		total_bytes = sizeof(struct irq_2_iommu)*nr_irq_2_iommu;
+
+		if (after_bootmem)
+			iommu = kzalloc(total_bytes, GFP_ATOMIC);
+		else
+			iommu = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
+
+		if (!iommu)
+			panic("can not get more irq_2_iommu\n");
+
+		irq_2_iommuX = iommu;
+		irq_2_iommu_index = 0;
+	}
+
+	iommu = &irq_2_iommuX[irq_2_iommu_index];
+	irq_2_iommu_index++;
+	return iommu;
+}
+
+static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+
+	BUG_ON(!desc);
+
+	return desc->irq_2_iommu;
+}
+
+static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
+{
+	struct irq_desc *desc;
+	struct irq_2_iommu *irq_iommu;
+
+	desc = irq_to_desc(irq);
+
+	BUG_ON(!desc);
+
+	irq_iommu = desc->irq_2_iommu;
+
+	if (!irq_iommu)
+		desc->irq_2_iommu = get_one_free_irq_2_iommu(irq);
+
+	return desc->irq_2_iommu;
+}
+
+#else /* !CONFIG_HAVE_SPARSE_IRQ */
+
+#ifdef CONFIG_HAVE_DYN_ARRAY
+static struct irq_2_iommu *irq_2_iommuX;
+DEFINE_DYN_ARRAY(irq_2_iommuX, sizeof(struct irq_2_iommu), nr_irqs, PAGE_SIZE, NULL);
 #else
-static struct irq_2_iommu irq_2_iommu[NR_IRQS];
+static struct irq_2_iommu irq_2_iommuX[NR_IRQS];
+#endif
+
+static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
+{
+	if (irq < nr_irqs)
+		return &irq_2_iommuX[irq];
+
+	return NULL;
+}
+static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
+{
+	return irq_2_iommu(irq);
+}
 #endif
 
 static DEFINE_SPINLOCK(irq_2_ir_lock);
 
-int irq_remapped(int irq)
+static struct irq_2_iommu *valid_irq_2_iommu(unsigned int irq)
 {
-	if (irq > nr_irqs)
-		return 0;
+	struct irq_2_iommu *irq_iommu;
+
+	irq_iommu = irq_2_iommu(irq);
 
-	if (!irq_2_iommu[irq].iommu)
-		return 0;
+	if (!irq_iommu)
+		return NULL;
 
-	return 1;
+	if (!irq_iommu->iommu)
+		return NULL;
+
+	return irq_iommu;
+}
+
+int irq_remapped(int irq)
+{
+	return valid_irq_2_iommu(irq) != NULL;
 }
 
 int get_irte(int irq, struct irte *entry)
 {
 	int index;
+	struct irq_2_iommu *irq_iommu;
 
-	if (!entry || irq > nr_irqs)
+	if (!entry)
 		return -1;
 
 	spin_lock(&irq_2_ir_lock);
-	if (!irq_2_iommu[irq].iommu) {
+	irq_iommu = valid_irq_2_iommu(irq);
+	if (!irq_iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
 
-	index = irq_2_iommu[irq].irte_index + irq_2_iommu[irq].sub_handle;
-	*entry = *(irq_2_iommu[irq].iommu->ir_table->base + index);
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
+	*entry = *(irq_iommu->iommu->ir_table->base + index);
 
 	spin_unlock(&irq_2_ir_lock);
 	return 0;
@@ -62,6 +157,7 @@ int get_irte(int irq, struct irte *entry)
 int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 {
 	struct ir_table *table = iommu->ir_table;
+	struct irq_2_iommu *irq_iommu;
 	u16 index, start_index;
 	unsigned int mask = 0;
 	int i;
@@ -69,6 +165,12 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 	if (!count)
 		return -1;
 
+#ifndef	CONFIG_HAVE_SPARSE_IRQ
+	/* protect irq_2_iommu_alloc later */
+	if (irq >= nr_irqs)
+		return -1;
+#endif
+
 	/*
 	 * start the IRTE search from index 0.
 	 */
@@ -108,10 +210,11 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 	for (i = index; i < index + count; i++)
 		table->base[i].present = 1;
 
-	irq_2_iommu[irq].iommu = iommu;
-	irq_2_iommu[irq].irte_index =  index;
-	irq_2_iommu[irq].sub_handle = 0;
-	irq_2_iommu[irq].irte_mask = mask;
+	irq_iommu = irq_2_iommu_alloc(irq);
+	irq_iommu->iommu = iommu;
+	irq_iommu->irte_index =  index;
+	irq_iommu->sub_handle = 0;
+	irq_iommu->irte_mask = mask;
 
 	spin_unlock(&irq_2_ir_lock);
 
@@ -132,31 +235,36 @@ static void qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
 int map_irq_to_irte_handle(int irq, u16 *sub_handle)
 {
 	int index;
+	struct irq_2_iommu *irq_iommu;
 
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= nr_irqs || !irq_2_iommu[irq].iommu) {
+	irq_iommu = valid_irq_2_iommu(irq);
+	if (!irq_iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
 
-	*sub_handle = irq_2_iommu[irq].sub_handle;
-	index = irq_2_iommu[irq].irte_index;
+	*sub_handle = irq_iommu->sub_handle;
+	index = irq_iommu->irte_index;
 	spin_unlock(&irq_2_ir_lock);
 	return index;
 }
 
 int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 {
+	struct irq_2_iommu *irq_iommu;
+
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= nr_irqs || irq_2_iommu[irq].iommu) {
+	irq_iommu = valid_irq_2_iommu(irq);
+	if (!irq_iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
 
-	irq_2_iommu[irq].iommu = iommu;
-	irq_2_iommu[irq].irte_index = index;
-	irq_2_iommu[irq].sub_handle = subhandle;
-	irq_2_iommu[irq].irte_mask = 0;
+	irq_iommu->iommu = iommu;
+	irq_iommu->irte_index = index;
+	irq_iommu->sub_handle = subhandle;
+	irq_iommu->irte_mask = 0;
 
 	spin_unlock(&irq_2_ir_lock);
 
@@ -165,16 +273,19 @@ int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 
 int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index)
 {
+	struct irq_2_iommu *irq_iommu;
+
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= nr_irqs || !irq_2_iommu[irq].iommu) {
+	irq_iommu = valid_irq_2_iommu(irq);
+	if (!irq_iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
 
-	irq_2_iommu[irq].iommu = NULL;
-	irq_2_iommu[irq].irte_index = 0;
-	irq_2_iommu[irq].sub_handle = 0;
-	irq_2_iommu[irq].irte_mask = 0;
+	irq_iommu->iommu = NULL;
+	irq_iommu->irte_index = 0;
+	irq_iommu->sub_handle = 0;
+	irq_2_iommu(irq)->irte_mask = 0;
 
 	spin_unlock(&irq_2_ir_lock);
 
@@ -186,16 +297,18 @@ int modify_irte(int irq, struct irte *irte_modified)
 	int index;
 	struct irte *irte;
 	struct intel_iommu *iommu;
+	struct irq_2_iommu *irq_iommu;
 
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= nr_irqs || !irq_2_iommu[irq].iommu) {
+	irq_iommu = valid_irq_2_iommu(irq);
+	if (!irq_iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
 
-	iommu = irq_2_iommu[irq].iommu;
+	iommu = irq_iommu->iommu;
 
-	index = irq_2_iommu[irq].irte_index + irq_2_iommu[irq].sub_handle;
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
 	irte = &iommu->ir_table->base[index];
 
 	set_64bit((unsigned long *)irte, irte_modified->low | (1 << 1));
@@ -211,18 +324,20 @@ int flush_irte(int irq)
 {
 	int index;
 	struct intel_iommu *iommu;
+	struct irq_2_iommu *irq_iommu;
 
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= nr_irqs || !irq_2_iommu[irq].iommu) {
+	irq_iommu = valid_irq_2_iommu(irq);
+	if (!irq_iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
 
-	iommu = irq_2_iommu[irq].iommu;
+	iommu = irq_iommu->iommu;
 
-	index = irq_2_iommu[irq].irte_index + irq_2_iommu[irq].sub_handle;
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
 
-	qi_flush_iec(iommu, index, irq_2_iommu[irq].irte_mask);
+	qi_flush_iec(iommu, index, irq_iommu->irte_mask);
 	spin_unlock(&irq_2_ir_lock);
 
 	return 0;
@@ -254,28 +369,30 @@ int free_irte(int irq)
 	int index, i;
 	struct irte *irte;
 	struct intel_iommu *iommu;
+	struct irq_2_iommu *irq_iommu;
 
 	spin_lock(&irq_2_ir_lock);
-	if (irq >= nr_irqs || !irq_2_iommu[irq].iommu) {
+	irq_iommu = valid_irq_2_iommu(irq);
+	if (!irq_iommu) {
 		spin_unlock(&irq_2_ir_lock);
 		return -1;
 	}
 
-	iommu = irq_2_iommu[irq].iommu;
+	iommu = irq_iommu->iommu;
 
-	index = irq_2_iommu[irq].irte_index + irq_2_iommu[irq].sub_handle;
+	index = irq_iommu->irte_index + irq_iommu->sub_handle;
 	irte = &iommu->ir_table->base[index];
 
-	if (!irq_2_iommu[irq].sub_handle) {
-		for (i = 0; i < (1 << irq_2_iommu[irq].irte_mask); i++)
+	if (!irq_iommu->sub_handle) {
+		for (i = 0; i < (1 << irq_iommu->irte_mask); i++)
 			set_64bit((unsigned long *)irte, 0);
-		qi_flush_iec(iommu, index, irq_2_iommu[irq].irte_mask);
+		qi_flush_iec(iommu, index, irq_iommu->irte_mask);
 	}
 
-	irq_2_iommu[irq].iommu = NULL;
-	irq_2_iommu[irq].irte_index = 0;
-	irq_2_iommu[irq].sub_handle = 0;
-	irq_2_iommu[irq].irte_mask = 0;
+	irq_iommu->iommu = NULL;
+	irq_iommu->irte_index = 0;
+	irq_iommu->sub_handle = 0;
+	irq_iommu->irte_mask = 0;
 
 	spin_unlock(&irq_2_ir_lock);
 
diff --git a/include/linux/irq.h b/include/linux/irq.h
index d5749852ee69..788d5a35a580 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -128,6 +128,7 @@ struct irq_chip {
 };
 
 struct timer_rand_state;
+struct irq_2_iommu;
 /**
  * struct irq_desc - interrupt descriptor
  *
@@ -162,6 +163,9 @@ struct irq_desc {
 	unsigned int            *kstat_irqs;
 #else
 	unsigned int            kstat_irqs[NR_CPUS];
+#endif
+#if defined(CONFIG_INTR_REMAP) && defined(CONFIG_HAVE_SPARSE_IRQ)
+       struct irq_2_iommu      *irq_2_iommu;
 #endif
 	irq_flow_handler_t	handle_irq;
 	struct irq_chip		*chip;
-- 
cgit v1.2.3


From 6d50bc26836e16a9589e0b128d527c29e30d722a Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:22 -0700
Subject: x86: use 28 bits irq NR for pci msi/msix and ht

also print out irq no in /proc/interrups and /proc/stat in hex, so could
tell bus/dev/func.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_64.c | 64 ++++++++++++++++++++++++++++++++++----------
 arch/x86/kernel/irq_64.c     |  2 +-
 drivers/pci/htirq.c          | 22 +++++++++++++--
 fs/proc/proc_misc.c          |  2 +-
 include/linux/irq.h          |  1 +
 5 files changed, 73 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 8ab7ae01773f..b0d4abc55a11 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -2520,17 +2520,21 @@ device_initcall(ioapic_init_sysfs);
 /*
  * Dynamic irq allocate and deallocation
  */
-int create_irq(void)
+unsigned int create_irq_nr(unsigned int irq_want)
 {
 	/* Allocate an unused irq */
-	int irq;
-	int new;
+	unsigned int irq;
+	unsigned int new;
 	unsigned long flags;
 	struct irq_cfg *cfg_new;
 
-	irq = -ENOSPC;
+#ifndef CONFIG_HAVE_SPARSE_IRQ
+	irq_want = nr_irqs - 1;
+#endif
+
+	irq = 0;
 	spin_lock_irqsave(&vector_lock, flags);
-	for (new = (nr_irqs - 1); new >= 0; new--) {
+	for (new = irq_want; new > 0; new--) {
 		if (platform_legacy_irq(new))
 			continue;
 		cfg_new = irq_cfg(new);
@@ -2545,12 +2549,24 @@ int create_irq(void)
 	}
 	spin_unlock_irqrestore(&vector_lock, flags);
 
-	if (irq >= 0) {
+	if (irq > 0) {
 		dynamic_irq_init(irq);
 	}
 	return irq;
 }
 
+int create_irq(void)
+{
+	int irq;
+
+	irq = create_irq_nr(nr_irqs - 1);
+
+	if (irq == 0)
+		irq = -1;
+
+	return irq;
+}
+
 void destroy_irq(unsigned int irq)
 {
 	unsigned long flags;
@@ -2803,13 +2819,29 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc, int irq)
 	return 0;
 }
 
+static unsigned int build_irq_for_pci_dev(struct pci_dev *dev)
+{
+	unsigned int irq;
+
+	irq = dev->bus->number;
+	irq <<= 8;
+	irq |= dev->devfn;
+	irq <<= 12;
+
+	return irq;
+}
+
 int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
 {
-	int irq, ret;
+	unsigned int irq;
+	int ret;
+	unsigned int irq_want;
 
-	irq = create_irq();
-	if (irq < 0)
-		return irq;
+	irq_want = build_irq_for_pci_dev(dev) + 0x100;
+
+	irq = create_irq_nr(irq_want);
+	if (irq == 0)
+		return -1;
 
 #ifdef CONFIG_INTR_REMAP
 	if (!intr_remapping_enabled)
@@ -2836,18 +2868,22 @@ error:
 
 int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	int irq, ret, sub_handle;
+	unsigned int irq;
+	int ret, sub_handle;
 	struct msi_desc *desc;
+	unsigned int irq_want;
+
 #ifdef CONFIG_INTR_REMAP
 	struct intel_iommu *iommu = 0;
 	int index = 0;
 #endif
 
+	irq_want = build_irq_for_pci_dev(dev) + 0x100;
 	sub_handle = 0;
 	list_for_each_entry(desc, &dev->msi_list, list) {
-		irq = create_irq();
-		if (irq < 0)
-			return irq;
+		irq = create_irq_nr(irq_want--);
+		if (irq == 0)
+			return -1;
 #ifdef CONFIG_INTR_REMAP
 		if (!intr_remapping_enabled)
 			goto no_ir;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index 7bd841a9c640..348a11168c2b 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -112,7 +112,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		action = desc->action;
 		if (!action && !any_count)
 			goto skip;
-		seq_printf(p, "%3d: ",i);
+		seq_printf(p, "%#x: ",i);
 #ifndef CONFIG_SMP
 		seq_printf(p, "%10u ", kstat_irqs(i));
 #else
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
index 279c940a0039..7c5aef13fcdb 100644
--- a/drivers/pci/htirq.c
+++ b/drivers/pci/htirq.c
@@ -82,6 +82,18 @@ void unmask_ht_irq(unsigned int irq)
 	write_ht_irq_msg(irq, &msg);
 }
 
+static unsigned int build_irq_for_pci_dev(struct pci_dev *dev)
+{
+	unsigned int irq;
+
+	irq = dev->bus->number;
+	irq <<= 8;
+	irq |= dev->devfn;
+	irq <<= 12;
+
+	return irq;
+}
+
 /**
  * __ht_create_irq - create an irq and attach it to a device.
  * @dev: The hypertransport device to find the irq capability on.
@@ -97,7 +109,8 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 	u32 data;
 	int max_irq;
 	int pos;
-	int irq;
+	unsigned int irq;
+	unsigned int irq_want;
 
 	pos = pci_find_ht_capability(dev, HT_CAPTYPE_IRQ);
 	if (!pos)
@@ -125,8 +138,13 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 	cfg->msg.address_lo = 0xffffffff;
 	cfg->msg.address_hi = 0xffffffff;
 
+	irq_want= build_irq_for_pci_dev(dev);
+#ifdef CONFIG_HAVE_SPARSE_IRQ
+	irq = create_irq_nr(irq_want + idx);
+#else
 	irq = create_irq();
-	if (irq < 0) {
+#endif
+	if (irq == 0) {
 		kfree(cfg);
 		return -EBUSY;
 	}
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 72dd739a7f8a..d68c3592fe4a 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -589,7 +589,7 @@ static int show_stat(struct seq_file *p, void *v)
 		}
 
 #ifdef CONFIG_HAVE_SPARSE_IRQ
-		seq_printf(p, " %u:%u", j, per_irq_sum);
+		seq_printf(p, " %#x:%u", j, per_irq_sum);
 #else
 		seq_printf(p, " %u", per_irq_sum);
 #endif
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 788d5a35a580..704136138dc7 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -399,6 +399,7 @@ extern void set_irq_noprobe(unsigned int irq);
 extern void set_irq_probe(unsigned int irq);
 
 /* Handle dynamic irq creation and destruction */
+extern unsigned int create_irq_nr(unsigned int irq_want);
 extern int create_irq(void);
 extern void destroy_irq(unsigned int irq);
 
-- 
cgit v1.2.3


From 8b8e8c1bf7275eca859fe551dfa484134eaf013b Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:23 -0700
Subject: x86: remove irqbalance in kernel for 32 bit

This has been deprecated for years, the user space irqbalanced utility
works better with numa, has configurable policies, etc...

Signed-off-by: Yinghai Lu <yhlu.kernel@gmai.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/Kconfig                |   8 -
 arch/x86/configs/i386_defconfig |   1 -
 arch/x86/kernel/io_apic_32.c    | 402 ----------------------------------------
 arch/x86/kernel/quirks.c        |   3 -
 include/linux/irq.h             |  14 +-
 kernel/irq/manage.c             |   3 -
 6 files changed, 3 insertions(+), 428 deletions(-)

(limited to 'include')

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1004888e9b13..3e0eaaa1a339 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1254,14 +1254,6 @@ config EFI
   	resultant kernel should continue to boot on existing non-EFI
   	platforms.
 
-config IRQBALANCE
-	def_bool y
-	prompt "Enable kernel irq balancing"
-	depends on X86_32 && SMP && X86_IO_APIC
-	help
-	  The default yes will allow the kernel to do irq load balancing.
-	  Saying no will keep the kernel from doing irq load balancing.
-
 config SECCOMP
 	def_bool y
 	prompt "Enable seccomp to safely compute untrusted bytecode"
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 52d0359719d7..13b8c86ae985 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -287,7 +287,6 @@ CONFIG_MTRR=y
 # CONFIG_MTRR_SANITIZER is not set
 CONFIG_X86_PAT=y
 CONFIG_EFI=y
-# CONFIG_IRQBALANCE is not set
 CONFIG_SECCOMP=y
 # CONFIG_HZ_100 is not set
 # CONFIG_HZ_250 is not set
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 204884b1415a..668edf226067 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -371,408 +371,6 @@ static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-#if defined(CONFIG_IRQBALANCE)
-# include <asm/processor.h>	/* kernel_thread() */
-# include <linux/kernel_stat.h>	/* kstat */
-# include <linux/slab.h>		/* kmalloc() */
-# include <linux/timer.h>
-
-#define IRQBALANCE_CHECK_ARCH -999
-#define MAX_BALANCED_IRQ_INTERVAL	(5*HZ)
-#define MIN_BALANCED_IRQ_INTERVAL	(HZ/2)
-#define BALANCED_IRQ_MORE_DELTA		(HZ/10)
-#define BALANCED_IRQ_LESS_DELTA		(HZ)
-
-static int irqbalance_disabled __read_mostly = IRQBALANCE_CHECK_ARCH;
-static int physical_balance __read_mostly;
-static long balanced_irq_interval __read_mostly = MAX_BALANCED_IRQ_INTERVAL;
-
-static struct irq_cpu_info {
-	unsigned long *last_irq;
-	unsigned long *irq_delta;
-	unsigned long irq;
-} irq_cpu_data[NR_CPUS];
-
-#define CPU_IRQ(cpu)		(irq_cpu_data[cpu].irq)
-#define LAST_CPU_IRQ(cpu, irq)   (irq_cpu_data[cpu].last_irq[irq])
-#define IRQ_DELTA(cpu, irq) 	(irq_cpu_data[cpu].irq_delta[irq])
-
-#define IDLE_ENOUGH(cpu,now) \
-	(idle_cpu(cpu) && ((now) - per_cpu(irq_stat, (cpu)).idle_timestamp > 1))
-
-#define IRQ_ALLOWED(cpu, allowed_mask)	cpu_isset(cpu, allowed_mask)
-
-#define CPU_TO_PACKAGEINDEX(i) (first_cpu(per_cpu(cpu_sibling_map, i)))
-
-static cpumask_t balance_irq_affinity_init __initdata = CPU_MASK_ALL;
-
-static cpumask_t *balance_irq_affinity;
-
-
-static void __init irq_affinity_init_work(void *data)
-{
-	struct dyn_array *da = data;
-
-	int i;
-	struct  balance_irq_affinity *affinity;
-
-	affinity = *da->name;
-
-	for (i = 0; i < *da->nr; i++)
-		memcpy(&affinity[i], &balance_irq_affinity_init,
-			 sizeof(struct balance_irq_affinity));
-
-}
-
-DEFINE_DYN_ARRAY(balance_irq_affinity, sizeof(struct balance_irq_affinity), nr_irqs, PAGE_SIZE, irq_affinity_init_work);
-
-
-void set_balance_irq_affinity(unsigned int irq, cpumask_t mask)
-{
-	balance_irq_affinity[irq] = mask;
-}
-
-static unsigned long move(int curr_cpu, cpumask_t allowed_mask,
-			unsigned long now, int direction)
-{
-	int search_idle = 1;
-	int cpu = curr_cpu;
-
-	goto inside;
-
-	do {
-		if (unlikely(cpu == curr_cpu))
-			search_idle = 0;
-inside:
-		if (direction == 1) {
-			cpu++;
-			if (cpu >= NR_CPUS)
-				cpu = 0;
-		} else {
-			cpu--;
-			if (cpu == -1)
-				cpu = NR_CPUS-1;
-		}
-	} while (!cpu_online(cpu) || !IRQ_ALLOWED(cpu, allowed_mask) ||
-			(search_idle && !IDLE_ENOUGH(cpu, now)));
-
-	return cpu;
-}
-
-static inline void balance_irq(int cpu, int irq)
-{
-	unsigned long now = jiffies;
-	cpumask_t allowed_mask;
-	unsigned int new_cpu;
-
-	if (irqbalance_disabled)
-		return;
-
-	cpus_and(allowed_mask, cpu_online_map, balance_irq_affinity[irq]);
-	new_cpu = move(cpu, allowed_mask, now, 1);
-	if (cpu != new_cpu)
-		set_pending_irq(irq, cpumask_of_cpu(new_cpu));
-}
-
-static inline void rotate_irqs_among_cpus(unsigned long useful_load_threshold)
-{
-	int i, j;
-	struct irq_desc *desc;
-
-	for_each_online_cpu(i) {
-		for (j = 0; j < nr_irqs; j++) {
-			desc = irq_to_desc(j);
-			if (!desc->action)
-				continue;
-			/* Is it a significant load ?  */
-			if (IRQ_DELTA(CPU_TO_PACKAGEINDEX(i), j) <
-						useful_load_threshold)
-				continue;
-			balance_irq(i, j);
-		}
-	}
-	balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
-		balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
-	return;
-}
-
-static void do_irq_balance(void)
-{
-	int i, j;
-	unsigned long max_cpu_irq = 0, min_cpu_irq = (~0);
-	unsigned long move_this_load = 0;
-	int max_loaded = 0, min_loaded = 0;
-	int load;
-	unsigned long useful_load_threshold = balanced_irq_interval + 10;
-	int selected_irq;
-	int tmp_loaded, first_attempt = 1;
-	unsigned long tmp_cpu_irq;
-	unsigned long imbalance = 0;
-	cpumask_t allowed_mask, target_cpu_mask, tmp;
-	struct irq_desc *desc;
-
-	for_each_possible_cpu(i) {
-		int package_index;
-		CPU_IRQ(i) = 0;
-		if (!cpu_online(i))
-			continue;
-		package_index = CPU_TO_PACKAGEINDEX(i);
-		for (j = 0; j < nr_irqs; j++) {
-			unsigned long value_now, delta;
-			/* Is this an active IRQ or balancing disabled ? */
-			desc = irq_to_desc(j);
-			if (!desc->action || irq_balancing_disabled(j))
-				continue;
-			if (package_index == i)
-				IRQ_DELTA(package_index, j) = 0;
-			/* Determine the total count per processor per IRQ */
-			value_now = (unsigned long) kstat_irqs_cpu(j, i);
-
-			/* Determine the activity per processor per IRQ */
-			delta = value_now - LAST_CPU_IRQ(i, j);
-
-			/* Update last_cpu_irq[][] for the next time */
-			LAST_CPU_IRQ(i, j) = value_now;
-
-			/* Ignore IRQs whose rate is less than the clock */
-			if (delta < useful_load_threshold)
-				continue;
-			/* update the load for the processor or package total */
-			IRQ_DELTA(package_index, j) += delta;
-
-			/* Keep track of the higher numbered sibling as well */
-			if (i != package_index)
-				CPU_IRQ(i) += delta;
-			/*
-			 * We have sibling A and sibling B in the package
-			 *
-			 * cpu_irq[A] = load for cpu A + load for cpu B
-			 * cpu_irq[B] = load for cpu B
-			 */
-			CPU_IRQ(package_index) += delta;
-		}
-	}
-	/* Find the least loaded processor package */
-	for_each_online_cpu(i) {
-		if (i != CPU_TO_PACKAGEINDEX(i))
-			continue;
-		if (min_cpu_irq > CPU_IRQ(i)) {
-			min_cpu_irq = CPU_IRQ(i);
-			min_loaded = i;
-		}
-	}
-	max_cpu_irq = ULONG_MAX;
-
-tryanothercpu:
-	/*
-	 * Look for heaviest loaded processor.
-	 * We may come back to get the next heaviest loaded processor.
-	 * Skip processors with trivial loads.
-	 */
-	tmp_cpu_irq = 0;
-	tmp_loaded = -1;
-	for_each_online_cpu(i) {
-		if (i != CPU_TO_PACKAGEINDEX(i))
-			continue;
-		if (max_cpu_irq <= CPU_IRQ(i))
-			continue;
-		if (tmp_cpu_irq < CPU_IRQ(i)) {
-			tmp_cpu_irq = CPU_IRQ(i);
-			tmp_loaded = i;
-		}
-	}
-
-	if (tmp_loaded == -1) {
-	 /*
-	  * In the case of small number of heavy interrupt sources,
-	  * loading some of the cpus too much. We use Ingo's original
-	  * approach to rotate them around.
-	  */
-		if (!first_attempt && imbalance >= useful_load_threshold) {
-			rotate_irqs_among_cpus(useful_load_threshold);
-			return;
-		}
-		goto not_worth_the_effort;
-	}
-
-	first_attempt = 0;		/* heaviest search */
-	max_cpu_irq = tmp_cpu_irq;	/* load */
-	max_loaded = tmp_loaded;	/* processor */
-	imbalance = (max_cpu_irq - min_cpu_irq) / 2;
-
-	/*
-	 * if imbalance is less than approx 10% of max load, then
-	 * observe diminishing returns action. - quit
-	 */
-	if (imbalance < (max_cpu_irq >> 3))
-		goto not_worth_the_effort;
-
-tryanotherirq:
-	/* if we select an IRQ to move that can't go where we want, then
-	 * see if there is another one to try.
-	 */
-	move_this_load = 0;
-	selected_irq = -1;
-	for (j = 0; j < nr_irqs; j++) {
-		/* Is this an active IRQ? */
-		desc = irq_to_desc(j);
-		if (!desc->action)
-			continue;
-		if (imbalance <= IRQ_DELTA(max_loaded, j))
-			continue;
-		/* Try to find the IRQ that is closest to the imbalance
-		 * without going over.
-		 */
-		if (move_this_load < IRQ_DELTA(max_loaded, j)) {
-			move_this_load = IRQ_DELTA(max_loaded, j);
-			selected_irq = j;
-		}
-	}
-	if (selected_irq == -1)
-		goto tryanothercpu;
-
-	imbalance = move_this_load;
-
-	/* For physical_balance case, we accumulated both load
-	 * values in the one of the siblings cpu_irq[],
-	 * to use the same code for physical and logical processors
-	 * as much as possible.
-	 *
-	 * NOTE: the cpu_irq[] array holds the sum of the load for
-	 * sibling A and sibling B in the slot for the lowest numbered
-	 * sibling (A), _AND_ the load for sibling B in the slot for
-	 * the higher numbered sibling.
-	 *
-	 * We seek the least loaded sibling by making the comparison
-	 * (A+B)/2 vs B
-	 */
-	load = CPU_IRQ(min_loaded) >> 1;
-	for_each_cpu_mask(j, per_cpu(cpu_sibling_map, min_loaded)) {
-		if (load > CPU_IRQ(j)) {
-			/* This won't change cpu_sibling_map[min_loaded] */
-			load = CPU_IRQ(j);
-			min_loaded = j;
-		}
-	}
-
-	cpus_and(allowed_mask,
-		cpu_online_map,
-		balance_irq_affinity[selected_irq]);
-	target_cpu_mask = cpumask_of_cpu(min_loaded);
-	cpus_and(tmp, target_cpu_mask, allowed_mask);
-
-	if (!cpus_empty(tmp)) {
-		/* mark for change destination */
-		set_pending_irq(selected_irq, cpumask_of_cpu(min_loaded));
-
-		/* Since we made a change, come back sooner to
-		 * check for more variation.
-		 */
-		balanced_irq_interval = max((long)MIN_BALANCED_IRQ_INTERVAL,
-			balanced_irq_interval - BALANCED_IRQ_LESS_DELTA);
-		return;
-	}
-	goto tryanotherirq;
-
-not_worth_the_effort:
-	/*
-	 * if we did not find an IRQ to move, then adjust the time interval
-	 * upward
-	 */
-	balanced_irq_interval = min((long)MAX_BALANCED_IRQ_INTERVAL,
-		balanced_irq_interval + BALANCED_IRQ_MORE_DELTA);
-	return;
-}
-
-static int balanced_irq(void *unused)
-{
-	int i;
-	unsigned long prev_balance_time = jiffies;
-	long time_remaining = balanced_irq_interval;
-	struct irq_desc *desc;
-
-	/* push everything to CPU 0 to give us a starting point.  */
-	for (i = 0 ; i < nr_irqs ; i++) {
-		desc = irq_to_desc(i);
-		desc->pending_mask = cpumask_of_cpu(0);
-		set_pending_irq(i, cpumask_of_cpu(0));
-	}
-
-	set_freezable();
-	for ( ; ; ) {
-		time_remaining = schedule_timeout_interruptible(time_remaining);
-		try_to_freeze();
-		if (time_after(jiffies,
-				prev_balance_time+balanced_irq_interval)) {
-			preempt_disable();
-			do_irq_balance();
-			prev_balance_time = jiffies;
-			time_remaining = balanced_irq_interval;
-			preempt_enable();
-		}
-	}
-	return 0;
-}
-
-static int __init balanced_irq_init(void)
-{
-	int i;
-	struct cpuinfo_x86 *c;
-	cpumask_t tmp;
-
-	cpus_shift_right(tmp, cpu_online_map, 2);
-	c = &boot_cpu_data;
-	/* When not overwritten by the command line ask subarchitecture. */
-	if (irqbalance_disabled == IRQBALANCE_CHECK_ARCH)
-		irqbalance_disabled = NO_BALANCE_IRQ;
-	if (irqbalance_disabled)
-		return 0;
-
-	 /* disable irqbalance completely if there is only one processor online */
-	if (num_online_cpus() < 2) {
-		irqbalance_disabled = 1;
-		return 0;
-	}
-	/*
-	 * Enable physical balance only if more than 1 physical processor
-	 * is present
-	 */
-	if (smp_num_siblings > 1 && !cpus_empty(tmp))
-		physical_balance = 1;
-
-	for_each_online_cpu(i) {
-		irq_cpu_data[i].irq_delta = kzalloc(sizeof(unsigned long) * nr_irqs, GFP_KERNEL);
-		irq_cpu_data[i].last_irq = kzalloc(sizeof(unsigned long) * nr_irqs, GFP_KERNEL);
-		if (irq_cpu_data[i].irq_delta == NULL || irq_cpu_data[i].last_irq == NULL) {
-			printk(KERN_ERR "balanced_irq_init: out of memory");
-			goto failed;
-		}
-	}
-
-	printk(KERN_INFO "Starting balanced_irq\n");
-	if (!IS_ERR(kthread_run(balanced_irq, NULL, "kirqd")))
-		return 0;
-	printk(KERN_ERR "balanced_irq_init: failed to spawn balanced_irq");
-failed:
-	for_each_possible_cpu(i) {
-		kfree(irq_cpu_data[i].irq_delta);
-		irq_cpu_data[i].irq_delta = NULL;
-		kfree(irq_cpu_data[i].last_irq);
-		irq_cpu_data[i].last_irq = NULL;
-	}
-	return 0;
-}
-
-int __devinit irqbalance_disable(char *str)
-{
-	irqbalance_disabled = 1;
-	return 1;
-}
-
-__setup("noirqbalance", irqbalance_disable);
-
-late_initcall(balanced_irq_init);
-#endif /* CONFIG_IRQBALANCE */
 #endif /* CONFIG_SMP */
 
 #ifndef CONFIG_SMP
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index f6a11b9b1f98..67465ed89310 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -35,9 +35,6 @@ static void __devinit quirk_intel_irqbalance(struct pci_dev *dev)
 	if (!(word & (1 << 13))) {
 		dev_info(&dev->dev, "Intel E7520/7320/7525 detected; "
 			"disabling irq balancing and affinity\n");
-#ifdef CONFIG_IRQBALANCE
-		irqbalance_disable("");
-#endif
 		noirqdebug_setup("");
 #ifdef CONFIG_PROC_FS
 		no_irq_affinity = 1;
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 704136138dc7..2445d2b3d5dc 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -185,7 +185,7 @@ struct irq_desc {
 	cpumask_t		affinity;
 	unsigned int		cpu;
 #endif
-#if defined(CONFIG_GENERIC_PENDING_IRQ) || defined(CONFIG_IRQBALANCE)
+#ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_t		pending_mask;
 #endif
 #ifdef CONFIG_PROC_FS
@@ -241,13 +241,13 @@ extern int setup_irq(unsigned int irq, struct irqaction *new);
 
 #ifdef CONFIG_SMP
 
-#if defined(CONFIG_GENERIC_PENDING_IRQ) || defined(CONFIG_IRQBALANCE)
+#ifdef CONFIG_GENERIC_PENDING_IRQ
 
 void set_pending_irq(unsigned int irq, cpumask_t mask);
 void move_native_irq(int irq);
 void move_masked_irq(int irq);
 
-#else /* CONFIG_GENERIC_PENDING_IRQ || CONFIG_IRQBALANCE */
+#else /* CONFIG_GENERIC_PENDING_IRQ */
 
 static inline void move_irq(int irq)
 {
@@ -274,14 +274,6 @@ static inline void set_pending_irq(unsigned int irq, cpumask_t mask)
 
 #endif /* CONFIG_SMP */
 
-#ifdef CONFIG_IRQBALANCE
-extern void set_balance_irq_affinity(unsigned int irq, cpumask_t mask);
-#else
-static inline void set_balance_irq_affinity(unsigned int irq, cpumask_t mask)
-{
-}
-#endif
-
 extern int no_irq_affinity;
 
 static inline int irq_balancing_disabled(unsigned int irq)
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 6df49218632a..ddc956861a58 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -86,8 +86,6 @@ int irq_set_affinity(unsigned int irq, cpumask_t cpumask)
 	if (!desc->chip->set_affinity)
 		return -EINVAL;
 
-	set_balance_irq_affinity(irq, cpumask);
-
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PCNTXT) {
 		unsigned long flags;
@@ -122,7 +120,6 @@ int irq_select_affinity(unsigned int irq)
 	desc->affinity = mask;
 	desc->chip->set_affinity(irq, mask);
 
-	set_balance_irq_affinity(irq, mask);
 	return 0;
 }
 #endif
-- 
cgit v1.2.3


From 497c9a195db918d3f035e8cb3021e5d4d035516e Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:28 -0700
Subject: x86: make 32bit support per_cpu vector

so we can merge io_apic_32.c and io_apic_64.c

v2: Use cpu_online_map as target cpus for bigsmp, just like 64-bit is doing.

Also remove some unused TARGET_CPUS macro.

v3: need to check if desc is null in smp_irq_move_cleanup

also migration needs to reset vector too, so copy __target_IO_APIC_irq
from 64bit.

(the duplication will go away once the two files are unified.)

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/entry_32.S                |   2 +-
 arch/x86/kernel/io_apic_32.c              | 719 +++++++++++++++++++-----------
 arch/x86/kernel/irq_32.c                  |  18 +-
 arch/x86/kernel/irqinit_32.c              |  41 +-
 arch/x86/lguest/boot.c                    |   2 +-
 arch/x86/mach-generic/bigsmp.c            |   4 +
 arch/x86/mach-generic/es7000.c            |  14 +
 arch/x86/mach-generic/numaq.c             |  14 +
 arch/x86/mach-generic/summit.c            |  14 +
 include/asm-x86/bigsmp/apic.h             |  15 +-
 include/asm-x86/es7000/apic.h             |   3 +-
 include/asm-x86/genapic_32.h              |   2 +
 include/asm-x86/hw_irq.h                  |   6 +-
 include/asm-x86/irq_vectors.h             |  15 +-
 include/asm-x86/mach-default/entry_arch.h |   1 +
 include/asm-x86/mach-default/mach_apic.h  |  15 +-
 include/asm-x86/mach-generic/mach_apic.h  |   1 +
 include/asm-x86/numaq/apic.h              |   2 -
 include/asm-x86/summit/apic.h             |   1 -
 19 files changed, 577 insertions(+), 312 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index b21fbfaffe39..4d82171d0f9c 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -629,7 +629,7 @@ ENTRY(interrupt)
 ENTRY(irq_entries_start)
 	RING0_INT_FRAME
 vector=0
-.rept NR_IRQS
+.rept NR_VECTORS
 	ALIGN
  .if vector
 	CFI_ADJUST_CFA_OFFSET -4
diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 66c0a91362a7..ea33d3c74970 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -48,6 +48,7 @@
 #include <asm/hypertransport.h>
 #include <asm/setup.h>
 
+#include <mach_ipi.h>
 #include <mach_apic.h>
 #include <mach_apicdef.h>
 
@@ -60,7 +61,7 @@ atomic_t irq_mis_count;
 static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };
 
 static DEFINE_SPINLOCK(ioapic_lock);
-DEFINE_SPINLOCK(vector_lock);
+static DEFINE_SPINLOCK(vector_lock);
 
 int timer_through_8259 __initdata;
 
@@ -100,28 +101,32 @@ struct irq_cfg {
 	unsigned int irq;
 	struct irq_cfg *next;
 	struct irq_pin_list *irq_2_pin;
+	cpumask_t domain;
+	cpumask_t old_domain;
+	unsigned move_cleanup_count;
 	u8 vector;
+	u8 move_in_progress : 1;
 };
 
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
 static struct irq_cfg irq_cfg_legacy[] __initdata = {
-	[0]  = { .irq =  0, .vector = IRQ0_VECTOR,  },
-	[1]  = { .irq =  1, .vector = IRQ1_VECTOR,  },
-	[2]  = { .irq =  2, .vector = IRQ2_VECTOR,  },
-	[3]  = { .irq =  3, .vector = IRQ3_VECTOR,  },
-	[4]  = { .irq =  4, .vector = IRQ4_VECTOR,  },
-	[5]  = { .irq =  5, .vector = IRQ5_VECTOR,  },
-	[6]  = { .irq =  6, .vector = IRQ6_VECTOR,  },
-	[7]  = { .irq =  7, .vector = IRQ7_VECTOR,  },
-	[8]  = { .irq =  8, .vector = IRQ8_VECTOR,  },
-	[9]  = { .irq =  9, .vector = IRQ9_VECTOR,  },
-	[10] = { .irq = 10, .vector = IRQ10_VECTOR, },
-	[11] = { .irq = 11, .vector = IRQ11_VECTOR, },
-	[12] = { .irq = 12, .vector = IRQ12_VECTOR, },
-	[13] = { .irq = 13, .vector = IRQ13_VECTOR, },
-	[14] = { .irq = 14, .vector = IRQ14_VECTOR, },
-	[15] = { .irq = 15, .vector = IRQ15_VECTOR, },
+	[0]  = { .irq =  0, .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR,  },
+	[1]  = { .irq =  1, .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR,  },
+	[2]  = { .irq =  2, .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR,  },
+	[3]  = { .irq =  3, .domain = CPU_MASK_ALL, .vector = IRQ3_VECTOR,  },
+	[4]  = { .irq =  4, .domain = CPU_MASK_ALL, .vector = IRQ4_VECTOR,  },
+	[5]  = { .irq =  5, .domain = CPU_MASK_ALL, .vector = IRQ5_VECTOR,  },
+	[6]  = { .irq =  6, .domain = CPU_MASK_ALL, .vector = IRQ6_VECTOR,  },
+	[7]  = { .irq =  7, .domain = CPU_MASK_ALL, .vector = IRQ7_VECTOR,  },
+	[8]  = { .irq =  8, .domain = CPU_MASK_ALL, .vector = IRQ8_VECTOR,  },
+	[9]  = { .irq =  9, .domain = CPU_MASK_ALL, .vector = IRQ9_VECTOR,  },
+	[10] = { .irq = 10, .domain = CPU_MASK_ALL, .vector = IRQ10_VECTOR, },
+	[11] = { .irq = 11, .domain = CPU_MASK_ALL, .vector = IRQ11_VECTOR, },
+	[12] = { .irq = 12, .domain = CPU_MASK_ALL, .vector = IRQ12_VECTOR, },
+	[13] = { .irq = 13, .domain = CPU_MASK_ALL, .vector = IRQ13_VECTOR, },
+	[14] = { .irq = 14, .domain = CPU_MASK_ALL, .vector = IRQ14_VECTOR, },
+	[15] = { .irq = 15, .domain = CPU_MASK_ALL, .vector = IRQ15_VECTOR, },
 };
 
 static struct irq_cfg irq_cfg_init = { .irq =  -1U, };
@@ -263,6 +268,7 @@ static struct irq_cfg *irq_cfg_alloc(unsigned int irq)
 	return cfg;
 }
 
+static int assign_irq_vector(int irq, cpumask_t mask);
 /*
  * Rough estimation of how many shared IRQs there are, can
  * be changed anytime.
@@ -432,6 +438,65 @@ static void ioapic_mask_entry(int apic, int pin)
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
+#ifdef CONFIG_SMP
+static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
+{
+	int apic, pin;
+	struct irq_cfg *cfg;
+	struct irq_pin_list *entry;
+
+	cfg = irq_cfg(irq);
+	entry = cfg->irq_2_pin;
+	for (;;) {
+		unsigned int reg;
+
+		if (!entry)
+			break;
+
+		apic = entry->apic;
+		pin = entry->pin;
+		io_apic_write(apic, 0x11 + pin*2, dest);
+		reg = io_apic_read(apic, 0x10 + pin*2);
+		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
+		reg |= vector;
+		io_apic_modify(apic, 0x10 + pin *2, reg);
+		if (!entry->next)
+			break;
+		entry = entry->next;
+	}
+}
+static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
+{
+	struct irq_cfg *cfg;
+	unsigned long flags;
+	unsigned int dest;
+	cpumask_t tmp;
+
+	cfg = irq_cfg(irq);
+
+	cpus_and(tmp, mask, cpu_online_map);
+	if (cpus_empty(tmp))
+		return;
+
+	if (assign_irq_vector(irq, mask))
+		return;
+
+	cpus_and(tmp, cfg->domain, mask);
+
+	dest = cpu_mask_to_apicid(tmp);
+	/*
+	 * Only the high 8 bits are valid.
+	 */
+	dest = SET_APIC_LOGICAL_ID(dest);
+
+	spin_lock_irqsave(&ioapic_lock, flags);
+	__target_IO_APIC_irq(irq, dest, cfg->vector);
+	irq_to_desc(irq)->affinity = mask;
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+}
+
+#endif /* CONFIG_SMP */
+
 /*
  * The common case is 1:1 IRQ<->pin mappings. Sometimes there are
  * shared ISA-space IRQs, so we have to support them. We are super
@@ -586,45 +651,6 @@ static void clear_IO_APIC(void)
 			clear_IO_APIC_pin(apic, pin);
 }
 
-#ifdef CONFIG_SMP
-static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t cpumask)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	int pin;
-	struct irq_pin_list *entry;
-	unsigned int apicid_value;
-	cpumask_t tmp;
-
-
-	cfg = irq_cfg(irq);
-	entry = cfg->irq_2_pin;
-
-	cpus_and(tmp, cpumask, cpu_online_map);
-	if (cpus_empty(tmp))
-		tmp = TARGET_CPUS;
-
-	cpus_and(cpumask, tmp, CPU_MASK_ALL);
-
-	apicid_value = cpu_mask_to_apicid(cpumask);
-	/* Prepare to do the io_apic_write */
-	apicid_value = apicid_value << 24;
-	spin_lock_irqsave(&ioapic_lock, flags);
-	for (;;) {
-		if (!entry)
-			break;
-		pin = entry->pin;
-		io_apic_write(entry->apic, 0x10 + 1 + pin*2, apicid_value);
-		if (!entry->next)
-			break;
-		entry = entry->next;
-	}
-	irq_to_desc(irq)->affinity = cpumask;
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-}
-
-#endif /* CONFIG_SMP */
-
 #ifndef CONFIG_SMP
 void send_IPI_self(int vector)
 {
@@ -789,32 +815,6 @@ int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
 }
 EXPORT_SYMBOL(IO_APIC_get_PCI_irq_vector);
 
-/*
- * This function currently is only a helper for the i386 smp boot process where
- * we need to reprogram the ioredtbls to cater for the cpus which have come online
- * so mask in all cases should simply be TARGET_CPUS
- */
-#ifdef CONFIG_SMP
-void __init setup_ioapic_dest(void)
-{
-	int pin, ioapic, irq, irq_entry;
-
-	if (skip_ioapic_setup == 1)
-		return;
-
-	for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
-		for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
-			irq_entry = find_irq_entry(ioapic, pin, mp_INT);
-			if (irq_entry == -1)
-				continue;
-			irq = pin_2_irq(irq_entry, ioapic, pin);
-			set_ioapic_affinity_irq(irq, TARGET_CPUS);
-		}
-
-	}
-}
-#endif
-
 #if defined(CONFIG_EISA) || defined(CONFIG_MCA)
 /*
  * EISA Edge/Level control register, ELCR
@@ -1046,47 +1046,138 @@ static inline int IO_APIC_irq_trigger(int irq)
 	return 0;
 }
 
+void lock_vector_lock(void)
+{
+	/* Used to the online set of cpus does not change
+	 * during assign_irq_vector.
+	 */
+	spin_lock(&vector_lock);
+}
 
-static int __assign_irq_vector(int irq)
+void unlock_vector_lock(void)
 {
-	static int current_vector = FIRST_DEVICE_VECTOR, current_offset;
-	int vector, offset;
-	struct irq_cfg *cfg;
+	spin_unlock(&vector_lock);
+}
 
-	cfg = irq_cfg(irq);
-	if (cfg->vector > 0)
-		return cfg->vector;
+static int __assign_irq_vector(int irq, cpumask_t mask)
+{
+        static int current_vector = FIRST_DEVICE_VECTOR, current_offset = 0;
+        unsigned int old_vector;
+        int cpu;
+        struct irq_cfg *cfg;
 
-	vector = current_vector;
-	offset = current_offset;
-next:
-	vector += 8;
-	if (vector >= first_system_vector) {
-		offset = (offset + 1) % 8;
-		vector = FIRST_DEVICE_VECTOR + offset;
-	}
-	if (vector == current_vector)
-		return -ENOSPC;
-	if (test_and_set_bit(vector, used_vectors))
-		goto next;
+        cfg = irq_cfg(irq);
 
-	current_vector = vector;
-	current_offset = offset;
-	cfg->vector = vector;
+        /* Only try and allocate irqs on cpus that are present */
+        cpus_and(mask, mask, cpu_online_map);
 
-	return vector;
-}
+        if ((cfg->move_in_progress) || cfg->move_cleanup_count)
+                return -EBUSY;
 
-static int assign_irq_vector(int irq)
-{
+        old_vector = cfg->vector;
+        if (old_vector) {
+                cpumask_t tmp;
+                cpus_and(tmp, cfg->domain, mask);
+                if (!cpus_empty(tmp))
+                        return 0;
+        }
+
+        for_each_cpu_mask_nr(cpu, mask) {
+                cpumask_t domain, new_mask;
+                int new_cpu;
+                int vector, offset;
+
+                domain = vector_allocation_domain(cpu);
+                cpus_and(new_mask, domain, cpu_online_map);
+
+                vector = current_vector;
+                offset = current_offset;
+next:
+                vector += 8;
+                if (vector >= first_system_vector) {
+                        /* If we run out of vectors on large boxen, must share them. */
+                        offset = (offset + 1) % 8;
+                        vector = FIRST_DEVICE_VECTOR + offset;
+                }
+                if (unlikely(current_vector == vector))
+                        continue;
+		if (vector == SYSCALL_VECTOR)
+                        goto next;
+
+                for_each_cpu_mask_nr(new_cpu, new_mask)
+                        if (per_cpu(vector_irq, new_cpu)[vector] != -1)
+                                goto next;
+                /* Found one! */
+                current_vector = vector;
+                current_offset = offset;
+                if (old_vector) {
+                        cfg->move_in_progress = 1;
+                        cfg->old_domain = cfg->domain;
+                }
+                for_each_cpu_mask_nr(new_cpu, new_mask)
+                        per_cpu(vector_irq, new_cpu)[vector] = irq;
+                cfg->vector = vector;
+                cfg->domain = domain;
+                return 0;
+        }
+        return -ENOSPC;
+}
+
+static int assign_irq_vector(int irq, cpumask_t mask)
+{
+	int err;
 	unsigned long flags;
-	int vector;
 
 	spin_lock_irqsave(&vector_lock, flags);
-	vector = __assign_irq_vector(irq);
+	err = __assign_irq_vector(irq, mask);
 	spin_unlock_irqrestore(&vector_lock, flags);
 
-	return vector;
+	return err;
+}
+
+static void __clear_irq_vector(int irq)
+{
+	struct irq_cfg *cfg;
+	cpumask_t mask;
+	int cpu, vector;
+
+	cfg = irq_cfg(irq);
+	BUG_ON(!cfg->vector);
+
+	vector = cfg->vector;
+	cpus_and(mask, cfg->domain, cpu_online_map);
+	for_each_cpu_mask_nr(cpu, mask)
+		per_cpu(vector_irq, cpu)[vector] = -1;
+
+	cfg->vector = 0;
+	cpus_clear(cfg->domain);
+}
+
+void __setup_vector_irq(int cpu)
+{
+	/* Initialize vector_irq on a new cpu */
+	/* This function must be called with vector_lock held */
+	int irq, vector;
+	struct irq_cfg *cfg;
+
+	/* Mark the inuse vectors */
+	for_each_irq_cfg(cfg) {
+		if (!cpu_isset(cpu, cfg->domain))
+			continue;
+		vector = cfg->vector;
+		irq = cfg->irq;
+		per_cpu(vector_irq, cpu)[vector] = irq;
+	}
+	/* Mark the free vectors */
+	for (vector = 0; vector < NR_VECTORS; ++vector) {
+		irq = per_cpu(vector_irq, cpu)[vector];
+		if (irq < 0)
+			continue;
+
+		cfg = irq_cfg(irq);
+		if (!cpu_isset(cpu, cfg->domain))
+			per_cpu(vector_irq, cpu)[vector] = -1;
+        }
 }
 
 static struct irq_chip ioapic_chip;
@@ -1095,7 +1186,7 @@ static struct irq_chip ioapic_chip;
 #define IOAPIC_EDGE	0
 #define IOAPIC_LEVEL	1
 
-static void ioapic_register_intr(int irq, int vector, unsigned long trigger)
+static void ioapic_register_intr(int irq, unsigned long trigger)
 {
 	struct irq_desc *desc;
 
@@ -1115,79 +1206,109 @@ static void ioapic_register_intr(int irq, int vector, unsigned long trigger)
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
 					 handle_edge_irq, "edge");
 	}
-	set_intr_gate(vector, interrupt[irq]);
 }
 
-static void __init setup_IO_APIC_irqs(void)
+static int setup_ioapic_entry(int apic, int irq,
+			      struct IO_APIC_route_entry *entry,
+			      unsigned int destination, int trigger,
+			      int polarity, int vector)
 {
+	/*
+	 * add it to the IO-APIC irq-routing table:
+	 */
+	memset(entry,0,sizeof(*entry));
+
+	entry->delivery_mode = INT_DELIVERY_MODE;
+	entry->dest_mode = INT_DEST_MODE;
+	entry->dest.logical.logical_dest = destination;
+
+	entry->mask = 0;                                /* enable IRQ */
+	entry->trigger = trigger;
+	entry->polarity = polarity;
+	entry->vector = vector;
+
+	/* Mask level triggered irqs.
+	 * Use IRQ_DELAYED_DISABLE for edge triggered irqs.
+	 */
+	if (trigger)
+		entry->mask = 1;
+
+	return 0;
+}
+
+static void setup_IO_APIC_irq(int apic, int pin, unsigned int irq,
+                              int trigger, int polarity)
+{
+	struct irq_cfg *cfg;
 	struct IO_APIC_route_entry entry;
-	int apic, pin, idx, irq, first_notcon = 1, vector;
+	cpumask_t mask;
+
+	if (!IO_APIC_IRQ(irq))
+		return;
+
+	cfg = irq_cfg(irq);
+
+	mask = TARGET_CPUS;
+	if (assign_irq_vector(irq, mask))
+		return;
+
+	cpus_and(mask, cfg->domain, mask);
+
+	apic_printk(APIC_VERBOSE,KERN_DEBUG
+		    "IOAPIC[%d]: Set routing entry (%d-%d -> 0x%x -> "
+		    "IRQ %d Mode:%i Active:%i)\n",
+		    apic, mp_ioapics[apic].mp_apicid, pin, cfg->vector,
+		    irq, trigger, polarity);
+
+
+	if (setup_ioapic_entry(mp_ioapics[apic].mp_apicid, irq, &entry,
+			       cpu_mask_to_apicid(mask), trigger, polarity,
+			       cfg->vector)) {
+		printk("Failed to setup ioapic entry for ioapic  %d, pin %d\n",
+		       mp_ioapics[apic].mp_apicid, pin);
+		__clear_irq_vector(irq);
+		return;
+	}
+
+	ioapic_register_intr(irq, trigger);
+	if (irq < 16)
+		disable_8259A_irq(irq);
+
+	ioapic_write_entry(apic, pin, entry);
+}
+
+static void __init setup_IO_APIC_irqs(void)
+{
+	int apic, pin, idx, irq, first_notcon = 1;
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
 	for (apic = 0; apic < nr_ioapics; apic++) {
 	for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
 
-		/*
-		 * add it to the IO-APIC irq-routing table:
-		 */
-		memset(&entry, 0, sizeof(entry));
-
-		entry.delivery_mode = INT_DELIVERY_MODE;
-		entry.dest_mode = INT_DEST_MODE;
-		entry.mask = 0;				/* enable IRQ */
-		entry.dest.logical.logical_dest =
-					cpu_mask_to_apicid(TARGET_CPUS);
-
-		idx = find_irq_entry(apic, pin, mp_INT);
+		idx = find_irq_entry(apic,pin,mp_INT);
 		if (idx == -1) {
 			if (first_notcon) {
-				apic_printk(APIC_VERBOSE, KERN_DEBUG
-						" IO-APIC (apicid-pin) %d-%d",
-						mp_ioapics[apic].mp_apicid,
-						pin);
+				apic_printk(APIC_VERBOSE, KERN_DEBUG " IO-APIC (apicid-pin) %d-%d", mp_ioapics[apic].mp_apicid, pin);
 				first_notcon = 0;
 			} else
-				apic_printk(APIC_VERBOSE, ", %d-%d",
-					mp_ioapics[apic].mp_apicid, pin);
+				apic_printk(APIC_VERBOSE, ", %d-%d", mp_ioapics[apic].mp_apicid, pin);
 			continue;
 		}
-
 		if (!first_notcon) {
 			apic_printk(APIC_VERBOSE, " not connected.\n");
 			first_notcon = 1;
 		}
 
-		entry.trigger = irq_trigger(idx);
-		entry.polarity = irq_polarity(idx);
-
-		if (irq_trigger(idx)) {
-			entry.trigger = 1;
-			entry.mask = 1;
-		}
-
 		irq = pin_2_irq(idx, apic, pin);
-		/*
-		 * skip adding the timer int on secondary nodes, which causes
-		 * a small but painful rift in the time-space continuum
-		 */
-		if (multi_timer_check(apic, irq))
-			continue;
-		else
-			add_pin_to_irq(irq, apic, pin);
 
-		if (!apic && !IO_APIC_IRQ(irq))
-			continue;
+                if (multi_timer_check(apic, irq))
+                        continue;
 
-		if (IO_APIC_IRQ(irq)) {
-			vector = assign_irq_vector(irq);
-			entry.vector = vector;
-			ioapic_register_intr(irq, vector, IOAPIC_AUTO);
+		add_pin_to_irq(irq, apic, pin);
 
-			if (!apic && (irq < 16))
-				disable_8259A_irq(irq);
-		}
-		ioapic_write_entry(apic, pin, entry);
+		setup_IO_APIC_irq(apic, pin, irq,
+				  irq_trigger(idx), irq_polarity(idx));
 	}
 	}
 
@@ -1221,7 +1342,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
 	 * The timer IRQ doesn't have to know that behind the
 	 * scene we may have a 8259A-master in AEOI mode ...
 	 */
-	ioapic_register_intr(0, vector, IOAPIC_EDGE);
+	ioapic_register_intr(0, IOAPIC_EDGE);
 
 	/*
 	 * Add it to the IO-APIC irq-routing table:
@@ -1805,8 +1926,10 @@ static unsigned int startup_ioapic_irq(unsigned int irq)
 	return was_pending;
 }
 
+static void irq_complete_move(unsigned int irq);
 static void ack_ioapic_irq(unsigned int irq)
 {
+	irq_complete_move(irq);
 	move_native_irq(irq);
 	ack_APIC_irq();
 }
@@ -1816,6 +1939,7 @@ static void ack_ioapic_quirk_irq(unsigned int irq)
 	unsigned long v;
 	int i;
 
+	irq_complete_move(irq);
 	move_native_irq(irq);
 /*
  * It appears there is an erratum which affects at least version 0x11
@@ -1858,6 +1982,64 @@ static int ioapic_retrigger_irq(unsigned int irq)
 	return 1;
 }
 
+#ifdef CONFIG_SMP
+asmlinkage void smp_irq_move_cleanup_interrupt(void)
+{
+	unsigned vector, me;
+	ack_APIC_irq();
+	irq_enter();
+
+	me = smp_processor_id();
+	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
+		unsigned int irq;
+		struct irq_desc *desc;
+		struct irq_cfg *cfg;
+		irq = __get_cpu_var(vector_irq)[vector];
+
+		desc = irq_to_desc(irq);
+		if (!desc)
+			continue;
+
+		cfg = irq_cfg(irq);
+		spin_lock(&desc->lock);
+		if (!cfg->move_cleanup_count)
+			goto unlock;
+
+		if ((vector == cfg->vector) && cpu_isset(me, cfg->domain))
+			goto unlock;
+
+		__get_cpu_var(vector_irq)[vector] = -1;
+		cfg->move_cleanup_count--;
+unlock:
+		spin_unlock(&desc->lock);
+	}
+
+	irq_exit();
+}
+
+static void irq_complete_move(unsigned int irq)
+{
+	struct irq_cfg *cfg = irq_cfg(irq);
+	unsigned vector, me;
+
+	if (likely(!cfg->move_in_progress))
+		return;
+
+	vector = ~get_irq_regs()->orig_ax;
+	me = smp_processor_id();
+	if ((vector == cfg->vector) && cpu_isset(me, cfg->domain)) {
+		cpumask_t cleanup_mask;
+
+		cpus_and(cleanup_mask, cfg->old_domain, cpu_online_map);
+		cfg->move_cleanup_count = cpus_weight(cleanup_mask);
+		send_IPI_mask(cleanup_mask, IRQ_MOVE_CLEANUP_VECTOR);
+		cfg->move_in_progress = 0;
+	}
+}
+#else
+static inline void irq_complete_move(unsigned int irq) {}
+#endif
+
 static struct irq_chip ioapic_chip __read_mostly = {
 	.name 		= "IO-APIC",
 	.startup 	= startup_ioapic_irq,
@@ -1940,7 +2122,7 @@ static struct irq_chip lapic_chip __read_mostly = {
 	.ack		= ack_lapic_irq,
 };
 
-static void lapic_register_intr(int irq, int vector)
+static void lapic_register_intr(int irq)
 {
 	struct irq_desc *desc;
 
@@ -1948,7 +2130,6 @@ static void lapic_register_intr(int irq, int vector)
 	desc->status &= ~IRQ_LEVEL;
 	set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
 				      "edge");
-	set_intr_gate(vector, interrupt[irq]);
 }
 
 static void __init setup_nmi(void)
@@ -2036,9 +2217,9 @@ static inline void __init unlock_ExtINT_logic(void)
  */
 static inline void __init check_timer(void)
 {
+	struct irq_cfg *cfg = irq_cfg(0);
 	int apic1, pin1, apic2, pin2;
 	int no_pin1 = 0;
-	int vector;
 	unsigned int ver;
 	unsigned long flags;
 
@@ -2051,8 +2232,7 @@ static inline void __init check_timer(void)
 	 * get/set the timer IRQ vector:
 	 */
 	disable_8259A_irq(0);
-	vector = assign_irq_vector(0);
-	set_intr_gate(vector, interrupt[0]);
+	assign_irq_vector(0, TARGET_CPUS);
 
 	/*
 	 * As IRQ0 is to be enabled in the 8259A, the virtual
@@ -2074,7 +2254,7 @@ static inline void __init check_timer(void)
 
 	apic_printk(APIC_QUIET, KERN_INFO "..TIMER: vector=0x%02X "
 		    "apic1=%d pin1=%d apic2=%d pin2=%d\n",
-		    vector, apic1, pin1, apic2, pin2);
+		    cfg->vector, apic1, pin1, apic2, pin2);
 
 	/*
 	 * Some BIOS writers are clueless and report the ExtINTA
@@ -2098,7 +2278,7 @@ static inline void __init check_timer(void)
 		 */
 		if (no_pin1) {
 			add_pin_to_irq(0, apic1, pin1);
-			setup_timer_IRQ0_pin(apic1, pin1, vector);
+			setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
 		}
 		unmask_IO_APIC_irq(0);
 		if (timer_irq_works()) {
@@ -2123,7 +2303,7 @@ static inline void __init check_timer(void)
 		 * legacy devices should be connected to IO APIC #0
 		 */
 		replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
-		setup_timer_IRQ0_pin(apic2, pin2, vector);
+		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
 		unmask_IO_APIC_irq(0);
 		enable_8259A_irq(0);
 		if (timer_irq_works()) {
@@ -2154,8 +2334,8 @@ static inline void __init check_timer(void)
 	apic_printk(APIC_QUIET, KERN_INFO
 		    "...trying to set up timer as Virtual Wire IRQ...\n");
 
-	lapic_register_intr(0, vector);
-	apic_write(APIC_LVT0, APIC_DM_FIXED | vector);	/* Fixed mode */
+	lapic_register_intr(0);
+	apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector);	/* Fixed mode */
 	enable_8259A_irq(0);
 
 	if (timer_irq_works()) {
@@ -2163,7 +2343,7 @@ static inline void __init check_timer(void)
 		goto out;
 	}
 	disable_8259A_irq(0);
-	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector);
+	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
 	apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n");
 
 	apic_printk(APIC_QUIET, KERN_INFO
@@ -2207,12 +2387,6 @@ out:
 
 void __init setup_IO_APIC(void)
 {
-	int i;
-
-	/* Reserve all the system vectors. */
-	for (i = first_system_vector; i < NR_VECTORS; i++)
-		set_bit(i, used_vectors);
-
 	enable_IO_APIC();
 
 	io_apic_irqs = ~PIC_IRQS;
@@ -2334,12 +2508,14 @@ device_initcall(ioapic_init_sysfs);
 unsigned int create_irq_nr(unsigned int irq_want)
 {
 	/* Allocate an unused irq */
-	unsigned int irq, new, vector = 0;
+	unsigned int irq, new;
 	unsigned long flags;
 	struct irq_cfg *cfg_new;
 
+#ifndef CONFIG_HAVE_SPARSE_IRQ
 	/* only can use bus/dev/fn.. when per_cpu vector is used */
 	irq_want = nr_irqs - 1;
+#endif
 
 	irq = 0;
 	spin_lock_irqsave(&vector_lock, flags);
@@ -2351,15 +2527,13 @@ unsigned int create_irq_nr(unsigned int irq_want)
 			continue;
 		if (!cfg_new)
 			cfg_new = irq_cfg_alloc(new);
-		vector = __assign_irq_vector(new);
-		if (likely(vector > 0))
+		if (__assign_irq_vector(new, TARGET_CPUS) == 0)
 			irq = new;
 		break;
 	}
 	spin_unlock_irqrestore(&vector_lock, flags);
 
 	if (irq > 0) {
-		set_intr_gate(vector, interrupt[irq]);
 		dynamic_irq_init(irq);
 	}
 	return irq;
@@ -2377,8 +2551,7 @@ void destroy_irq(unsigned int irq)
 	dynamic_irq_cleanup(irq);
 
 	spin_lock_irqsave(&vector_lock, flags);
-	clear_bit(irq_cfg(irq)->vector, used_vectors);
-	irq_cfg(irq)->vector = 0;
+	__clear_irq_vector(irq);
 	spin_unlock_irqrestore(&vector_lock, flags);
 }
 
@@ -2388,57 +2561,65 @@ void destroy_irq(unsigned int irq)
 #ifdef CONFIG_PCI_MSI
 static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
 {
-	int vector;
+	struct irq_cfg *cfg;
+	int err;
 	unsigned dest;
+	cpumask_t tmp;
 
-	vector = assign_irq_vector(irq);
-	if (vector >= 0) {
-		dest = cpu_mask_to_apicid(TARGET_CPUS);
-
-		msg->address_hi = MSI_ADDR_BASE_HI;
-		msg->address_lo =
-			MSI_ADDR_BASE_LO |
-			((INT_DEST_MODE == 0) ?
-MSI_ADDR_DEST_MODE_PHYSICAL:
-				MSI_ADDR_DEST_MODE_LOGICAL) |
-			((INT_DELIVERY_MODE != dest_LowestPrio) ?
-				MSI_ADDR_REDIRECTION_CPU:
-				MSI_ADDR_REDIRECTION_LOWPRI) |
-			MSI_ADDR_DEST_ID(dest);
+	tmp = TARGET_CPUS;
+	err = assign_irq_vector(irq, tmp);
+	if (err)
+		return err;
 
-		msg->data =
-			MSI_DATA_TRIGGER_EDGE |
-			MSI_DATA_LEVEL_ASSERT |
-			((INT_DELIVERY_MODE != dest_LowestPrio) ?
-MSI_DATA_DELIVERY_FIXED:
-				MSI_DATA_DELIVERY_LOWPRI) |
-			MSI_DATA_VECTOR(vector);
-	}
-	return vector;
+	cfg = irq_cfg(irq);
+	cpus_and(tmp, cfg->domain, tmp);
+	dest = cpu_mask_to_apicid(tmp);
+
+	msg->address_hi = MSI_ADDR_BASE_HI;
+	msg->address_lo =
+		MSI_ADDR_BASE_LO |
+		((INT_DEST_MODE == 0) ?
+			MSI_ADDR_DEST_MODE_PHYSICAL:
+			MSI_ADDR_DEST_MODE_LOGICAL) |
+		((INT_DELIVERY_MODE != dest_LowestPrio) ?
+			MSI_ADDR_REDIRECTION_CPU:
+			MSI_ADDR_REDIRECTION_LOWPRI) |
+		MSI_ADDR_DEST_ID(dest);
+
+	msg->data =
+		MSI_DATA_TRIGGER_EDGE |
+		MSI_DATA_LEVEL_ASSERT |
+		((INT_DELIVERY_MODE != dest_LowestPrio) ?
+			MSI_DATA_DELIVERY_FIXED:
+			MSI_DATA_DELIVERY_LOWPRI) |
+		MSI_DATA_VECTOR(cfg->vector);
+
+	return err;
 }
 
 #ifdef CONFIG_SMP
 static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 {
+	struct irq_cfg *cfg;
 	struct msi_msg msg;
 	unsigned int dest;
 	cpumask_t tmp;
-	int vector;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
-		tmp = TARGET_CPUS;
+		return;
 
-	vector = assign_irq_vector(irq);
-	if (vector < 0)
+	if (assign_irq_vector(irq, mask))
 		return;
 
-	dest = cpu_mask_to_apicid(mask);
+	cfg = irq_cfg(irq);
+	cpus_and(tmp, cfg->domain, mask);
+	dest = cpu_mask_to_apicid(tmp);
 
 	read_msi_msg(irq, &msg);
 
 	msg.data &= ~MSI_DATA_VECTOR_MASK;
-	msg.data |= MSI_DATA_VECTOR(vector);
+	msg.data |= MSI_DATA_VECTOR(cfg->vector);
 	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
@@ -2517,15 +2698,15 @@ void arch_teardown_msi_irq(unsigned int irq)
 
 #ifdef CONFIG_SMP
 
-static void target_ht_irq(unsigned int irq, unsigned int dest)
+static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
 {
 	struct ht_irq_msg msg;
 	fetch_ht_irq_msg(irq, &msg);
 
-	msg.address_lo &= ~(HT_IRQ_LOW_DEST_ID_MASK);
+	msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK | HT_IRQ_LOW_DEST_ID_MASK);
 	msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
 
-	msg.address_lo |= HT_IRQ_LOW_DEST_ID(dest);
+	msg.address_lo |= HT_IRQ_LOW_VECTOR(vector) | HT_IRQ_LOW_DEST_ID(dest);
 	msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);
 
 	write_ht_irq_msg(irq, &msg);
@@ -2533,18 +2714,22 @@ static void target_ht_irq(unsigned int irq, unsigned int dest)
 
 static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
 {
+	struct irq_cfg *cfg;
 	unsigned int dest;
 	cpumask_t tmp;
 
 	cpus_and(tmp, mask, cpu_online_map);
 	if (cpus_empty(tmp))
-		tmp = TARGET_CPUS;
+		return;
 
-	cpus_and(mask, tmp, CPU_MASK_ALL);
+	if (assign_irq_vector(irq, mask))
+		return;
 
-	dest = cpu_mask_to_apicid(mask);
+	cfg = irq_cfg(irq);
+	cpus_and(tmp, cfg->domain, mask);
+	dest = cpu_mask_to_apicid(tmp);
 
-	target_ht_irq(irq, dest);
+	target_ht_irq(irq, dest, cfg->vector);
 	irq_to_desc(irq)->affinity = mask;
 }
 #endif
@@ -2562,16 +2747,18 @@ static struct irq_chip ht_irq_chip = {
 
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 {
-	int vector;
+	struct irq_cfg *cfg;
+	int err;
+	cpumask_t tmp;
 
-	vector = assign_irq_vector(irq);
-	if (vector >= 0) {
+	tmp = TARGET_CPUS;
+	err = assign_irq_vector(irq, tmp);
+	if ( !err) {
 		struct ht_irq_msg msg;
 		unsigned dest;
-		cpumask_t tmp;
 
-		cpus_clear(tmp);
-		cpu_set(vector >> 8, tmp);
+		cfg = irq_cfg(irq);
+		cpus_and(tmp, cfg->domain, tmp);
 		dest = cpu_mask_to_apicid(tmp);
 
 		msg.address_hi = HT_IRQ_HIGH_DEST_ID(dest);
@@ -2579,7 +2766,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 		msg.address_lo =
 			HT_IRQ_LOW_BASE |
 			HT_IRQ_LOW_DEST_ID(dest) |
-			HT_IRQ_LOW_VECTOR(vector) |
+			HT_IRQ_LOW_VECTOR(cfg->vector) |
 			((INT_DEST_MODE == 0) ?
 				HT_IRQ_LOW_DM_PHYSICAL :
 				HT_IRQ_LOW_DM_LOGICAL) |
@@ -2594,7 +2781,7 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 		set_irq_chip_and_handler_name(irq, &ht_irq_chip,
 					      handle_edge_irq, "edge");
 	}
-	return vector;
+	return err;
 }
 #endif /* CONFIG_HT_IRQ */
 
@@ -2705,50 +2892,21 @@ int __init io_apic_get_redir_entries(int ioapic)
 }
 
 
-int io_apic_set_pci_routing(int ioapic, int pin, int irq, int edge_level, int active_high_low)
+int io_apic_set_pci_routing(int ioapic, int pin, int irq, int triggering, int polarity)
 {
-	struct IO_APIC_route_entry entry;
-
 	if (!IO_APIC_IRQ(irq)) {
 		printk(KERN_ERR "IOAPIC[%d]: Invalid reference to IRQ 0\n",
 			ioapic);
 		return -EINVAL;
 	}
 
-	/*
-	 * Generate a PCI IRQ routing entry and program the IOAPIC accordingly.
-	 * Note that we mask (disable) IRQs now -- these get enabled when the
-	 * corresponding device driver registers for this IRQ.
-	 */
-
-	memset(&entry, 0, sizeof(entry));
-
-	entry.delivery_mode = INT_DELIVERY_MODE;
-	entry.dest_mode = INT_DEST_MODE;
-	entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
-	entry.trigger = edge_level;
-	entry.polarity = active_high_low;
-	entry.mask  = 1;
-
 	/*
 	 * IRQs < 16 are already in the irq_2_pin[] map
 	 */
 	if (irq >= 16)
 		add_pin_to_irq(irq, ioapic, pin);
 
-	entry.vector = assign_irq_vector(irq);
-
-	apic_printk(APIC_DEBUG, KERN_DEBUG "IOAPIC[%d]: Set PCI routing entry "
-		"(%d-%d -> 0x%x -> IRQ %d Mode:%i Active:%i)\n", ioapic,
-		mp_ioapics[ioapic].mp_apicid, pin, entry.vector, irq,
-		edge_level, active_high_low);
-
-	ioapic_register_intr(irq, entry.vector, edge_level);
-
-	if (!ioapic && (irq < 16))
-		disable_8259A_irq(irq);
-
-	ioapic_write_entry(ioapic, pin, entry);
+	setup_IO_APIC_irq(ioapic, pin, irq, triggering, polarity);
 
 	return 0;
 }
@@ -2774,6 +2932,47 @@ int acpi_get_override_irq(int bus_irq, int *trigger, int *polarity)
 
 #endif /* CONFIG_ACPI */
 
+/*
+ * This function currently is only a helper for the i386 smp boot process where
+ * we need to reprogram the ioredtbls to cater for the cpus which have come online
+ * so mask in all cases should simply be TARGET_CPUS
+ */
+#ifdef CONFIG_SMP
+void __init setup_ioapic_dest(void)
+{
+	int pin, ioapic, irq, irq_entry;
+	struct irq_cfg *cfg;
+	struct irq_desc *desc;
+
+	if (skip_ioapic_setup == 1)
+		return;
+
+	for (ioapic = 0; ioapic < nr_ioapics; ioapic++) {
+		for (pin = 0; pin < nr_ioapic_registers[ioapic]; pin++) {
+			irq_entry = find_irq_entry(ioapic, pin, mp_INT);
+			if (irq_entry == -1)
+				continue;
+			irq = pin_2_irq(irq_entry, ioapic, pin);
+
+			/* setup_IO_APIC_irqs could fail to get vector for some device
+			 * when you have too many devices, because at that time only boot
+			 * cpu is online.
+			 */
+			cfg = irq_cfg(irq);
+			if (!cfg->vector)
+				setup_IO_APIC_irq(ioapic, pin, irq,
+						  irq_trigger(irq_entry),
+						  irq_polarity(irq_entry));
+			else {
+				desc = irq_to_desc(irq);
+				set_ioapic_affinity_irq(irq, TARGET_CPUS);
+			}
+		}
+
+	}
+}
+#endif
+
 static int __init parse_disable_timer_pin_1(char *arg)
 {
 	disable_timer_pin_1 = 1;
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 0a57e39159a8..b51ffdcfa31a 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -223,21 +223,25 @@ unsigned int do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs;
 	/* high bit used in ret_from_ code */
-	int overflow, irq = ~regs->orig_ax;
+	int overflow;
+	unsigned vector = ~regs->orig_ax;
 	struct irq_desc *desc;
+	unsigned irq;
 
-	desc = irq_to_desc(irq);
-	if (unlikely(!desc)) {
-		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
-					__func__, irq);
-		BUG();
-	}
 
 	old_regs = set_irq_regs(regs);
 	irq_enter();
+	irq = __get_cpu_var(vector_irq)[vector];
 
 	overflow = check_stack_overflow();
 
+	desc = irq_to_desc(irq);
+	if (unlikely(!desc)) {
+		printk(KERN_EMERG "%s: cannot handle IRQ %d vector %#x\n",
+					__func__, irq, vector);
+		BUG();
+	}
+
 	if (!execute_on_irq_stack(overflow, desc, irq)) {
 		if (unlikely(overflow))
 			print_stack_overflow();
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index ded09ac2642e..9092103a18eb 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -90,6 +90,27 @@ static struct irqaction irq2 = {
 	.name = "cascade",
 };
 
+DEFINE_PER_CPU(vector_irq_t, vector_irq) = {
+	[0 ... IRQ0_VECTOR - 1] = -1,
+	[IRQ0_VECTOR] = 0,
+	[IRQ1_VECTOR] = 1,
+	[IRQ2_VECTOR] = 2,
+	[IRQ3_VECTOR] = 3,
+	[IRQ4_VECTOR] = 4,
+	[IRQ5_VECTOR] = 5,
+	[IRQ6_VECTOR] = 6,
+	[IRQ7_VECTOR] = 7,
+	[IRQ8_VECTOR] = 8,
+	[IRQ9_VECTOR] = 9,
+	[IRQ10_VECTOR] = 10,
+	[IRQ11_VECTOR] = 11,
+	[IRQ12_VECTOR] = 12,
+	[IRQ13_VECTOR] = 13,
+	[IRQ14_VECTOR] = 14,
+	[IRQ15_VECTOR] = 15,
+	[IRQ15_VECTOR + 1 ... NR_VECTORS - 1] = -1
+};
+
 /* Overridden in paravirt.c */
 void init_IRQ(void) __attribute__((weak, alias("native_init_IRQ")));
 
@@ -105,22 +126,14 @@ void __init native_init_IRQ(void)
 	 * us. (some of these will be overridden and become
 	 * 'special' SMP interrupts)
 	 */
-	for (i = 0; i < (NR_VECTORS - FIRST_EXTERNAL_VECTOR); i++) {
-		int vector = FIRST_EXTERNAL_VECTOR + i;
-		if (i >= nr_irqs)
-			break;
+	for (i =  FIRST_EXTERNAL_VECTOR; i < NR_VECTORS; i++) {
 		/* SYSCALL_VECTOR was reserved in trap_init. */
-		if (!test_bit(vector, used_vectors))
-			set_intr_gate(vector, interrupt[i]);
+		if (i != SYSCALL_VECTOR)
+			set_intr_gate(i, interrupt[i]);
 	}
 
-#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_SMP)
-	/*
-	 * IRQ0 must be given a fixed assignment and initialized,
-	 * because it's used before the IO-APIC is set up.
-	 */
-	set_intr_gate(FIRST_DEVICE_VECTOR, interrupt[0]);
 
+#if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_SMP)
 	/*
 	 * The reschedule interrupt is a CPU-to-CPU reschedule-helper
 	 * IPI, driven by wakeup.
@@ -135,6 +148,9 @@ void __init native_init_IRQ(void)
 
 	/* IPI for single call function */
 	set_intr_gate(CALL_FUNCTION_SINGLE_VECTOR, call_function_single_interrupt);
+
+	/* Low priority IPI to cleanup after moving an irq */
+	set_intr_gate(IRQ_MOVE_CLEANUP_VECTOR, irq_move_cleanup_interrupt);
 #endif
 
 #ifdef CONFIG_X86_LOCAL_APIC
@@ -168,3 +184,4 @@ void __init native_init_IRQ(void)
 
 	irq_ctx_init(smp_processor_id());
 }
+
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 65f0b8a47bed..48ee4f9435f4 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -582,7 +582,7 @@ static void __init lguest_init_IRQ(void)
 	for (i = 0; i < LGUEST_IRQS; i++) {
 		int vector = FIRST_EXTERNAL_VECTOR + i;
 		if (vector != SYSCALL_VECTOR) {
-			set_intr_gate(vector, interrupt[i]);
+			set_intr_gate(vector, interrupt[vector]);
 			set_irq_chip_and_handler_name(i, &lguest_irq_controller,
 						      handle_level_irq,
 						      "level");
diff --git a/arch/x86/mach-generic/bigsmp.c b/arch/x86/mach-generic/bigsmp.c
index df37fc9d6a26..3c3b471ea496 100644
--- a/arch/x86/mach-generic/bigsmp.c
+++ b/arch/x86/mach-generic/bigsmp.c
@@ -41,6 +41,10 @@ static const struct dmi_system_id bigsmp_dmi_table[] = {
 	 { }
 };
 
+static cpumask_t vector_allocation_domain(int cpu)
+{
+        return cpumask_of_cpu(cpu);
+}
 
 static int probe_bigsmp(void)
 {
diff --git a/arch/x86/mach-generic/es7000.c b/arch/x86/mach-generic/es7000.c
index 6513d41ea21e..28459cab3ddb 100644
--- a/arch/x86/mach-generic/es7000.c
+++ b/arch/x86/mach-generic/es7000.c
@@ -75,4 +75,18 @@ static int __init acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 }
 #endif
 
+static cpumask_t vector_allocation_domain(int cpu)
+{
+	/* Careful. Some cpus do not strictly honor the set of cpus
+	 * specified in the interrupt destination when using lowest
+	 * priority interrupt delivery mode.
+	 *
+	 * In particular there was a hyperthreading cpu observed to
+	 * deliver interrupts to the wrong hyperthread when only one
+	 * hyperthread was specified in the interrupt desitination.
+	 */
+	cpumask_t domain = { { [0] = APIC_ALL_CPUS, } };
+	return domain;
+}
+
 struct genapic __initdata_refok apic_es7000 = APIC_INIT("es7000", probe_es7000);
diff --git a/arch/x86/mach-generic/numaq.c b/arch/x86/mach-generic/numaq.c
index 8cf58394975e..71a309b122e6 100644
--- a/arch/x86/mach-generic/numaq.c
+++ b/arch/x86/mach-generic/numaq.c
@@ -38,4 +38,18 @@ static int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	return 0;
 }
 
+static cpumask_t vector_allocation_domain(int cpu)
+{
+	/* Careful. Some cpus do not strictly honor the set of cpus
+	 * specified in the interrupt destination when using lowest
+	 * priority interrupt delivery mode.
+	 *
+	 * In particular there was a hyperthreading cpu observed to
+	 * deliver interrupts to the wrong hyperthread when only one
+	 * hyperthread was specified in the interrupt desitination.
+	 */
+	cpumask_t domain = { { [0] = APIC_ALL_CPUS, } };
+	return domain;
+}
+
 struct genapic apic_numaq = APIC_INIT("NUMAQ", probe_numaq);
diff --git a/arch/x86/mach-generic/summit.c b/arch/x86/mach-generic/summit.c
index 6ad6b67a723d..6272b5e69da6 100644
--- a/arch/x86/mach-generic/summit.c
+++ b/arch/x86/mach-generic/summit.c
@@ -23,4 +23,18 @@ static int probe_summit(void)
 	return 0;
 }
 
+static cpumask_t vector_allocation_domain(int cpu)
+{
+	/* Careful. Some cpus do not strictly honor the set of cpus
+	 * specified in the interrupt destination when using lowest
+	 * priority interrupt delivery mode.
+	 *
+	 * In particular there was a hyperthreading cpu observed to
+	 * deliver interrupts to the wrong hyperthread when only one
+	 * hyperthread was specified in the interrupt desitination.
+	 */
+	cpumask_t domain = { { [0] = APIC_ALL_CPUS, } };
+	return domain;
+}
+
 struct genapic apic_summit = APIC_INIT("summit", probe_summit);
diff --git a/include/asm-x86/bigsmp/apic.h b/include/asm-x86/bigsmp/apic.h
index 0a9cd7c5ca0c..1d9543b9d358 100644
--- a/include/asm-x86/bigsmp/apic.h
+++ b/include/asm-x86/bigsmp/apic.h
@@ -9,22 +9,17 @@ static inline int apic_id_registered(void)
 	return (1);
 }
 
-/* Round robin the irqs amoung the online cpus */
 static inline cpumask_t target_cpus(void)
 {
-	static unsigned long cpu = NR_CPUS;
-	do {
-		if (cpu >= NR_CPUS)
-			cpu = first_cpu(cpu_online_map);
-		else
-			cpu = next_cpu(cpu, cpu_online_map);
-	} while (cpu >= NR_CPUS);
-	return cpumask_of_cpu(cpu);
+#ifdef CONFIG_SMP
+        return cpu_online_map;
+#else
+        return cpumask_of_cpu(0);
+#endif
 }
 
 #undef APIC_DEST_LOGICAL
 #define APIC_DEST_LOGICAL	0
-#define TARGET_CPUS		(target_cpus())
 #define APIC_DFR_VALUE		(APIC_DFR_FLAT)
 #define INT_DELIVERY_MODE	(dest_Fixed)
 #define INT_DEST_MODE		(0)    /* phys delivery to target proc */
diff --git a/include/asm-x86/es7000/apic.h b/include/asm-x86/es7000/apic.h
index bd2c44d1f7ac..750afada5fbf 100644
--- a/include/asm-x86/es7000/apic.h
+++ b/include/asm-x86/es7000/apic.h
@@ -17,7 +17,6 @@ static inline cpumask_t target_cpus(void)
 	return cpumask_of_cpu(smp_processor_id());
 #endif
 }
-#define TARGET_CPUS	(target_cpus())
 
 #if defined CONFIG_ES7000_CLUSTERED_APIC
 #define APIC_DFR_VALUE		(APIC_DFR_CLUSTER)
@@ -81,7 +80,7 @@ static inline void setup_apic_routing(void)
 	int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id());
 	printk("Enabling APIC mode:  %s.  Using %d I/O APICs, target cpus %lx\n",
 		(apic_version[apic] == 0x14) ?
-		"Physical Cluster" : "Logical Cluster", nr_ioapics, cpus_addr(TARGET_CPUS)[0]);
+		"Physical Cluster" : "Logical Cluster", nr_ioapics, cpus_addr(target_cpus())[0]);
 }
 
 static inline int multi_timer_check(int apic, int irq)
diff --git a/include/asm-x86/genapic_32.h b/include/asm-x86/genapic_32.h
index 34280f027664..6fe4f81bfcf9 100644
--- a/include/asm-x86/genapic_32.h
+++ b/include/asm-x86/genapic_32.h
@@ -57,6 +57,7 @@ struct genapic {
 	unsigned (*get_apic_id)(unsigned long x);
 	unsigned long apic_id_mask;
 	unsigned int (*cpu_mask_to_apicid)(cpumask_t cpumask);
+	cpumask_t (*vector_allocation_domain)(int cpu);
 
 #ifdef CONFIG_SMP
 	/* ipi */
@@ -104,6 +105,7 @@ struct genapic {
 	APICFUNC(get_apic_id)				\
 	.apic_id_mask = APIC_ID_MASK,			\
 	APICFUNC(cpu_mask_to_apicid)			\
+	APICFUNC(vector_allocation_domain)			\
 	APICFUNC(acpi_madt_oem_check)			\
 	IPIFUNC(send_IPI_mask)				\
 	IPIFUNC(send_IPI_allbutself)			\
diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h
index 50f6e0316b50..51c787d17cbc 100644
--- a/include/asm-x86/hw_irq.h
+++ b/include/asm-x86/hw_irq.h
@@ -116,12 +116,12 @@ extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
 
 #ifdef CONFIG_X86_32
 extern void (*const interrupt[NR_IRQS])(void);
-#else
+#endif
+
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
-#endif
 
-#if defined(CONFIG_X86_IO_APIC) && defined(CONFIG_X86_64)
+#ifdef CONFIG_X86_IO_APIC
 extern void lock_vector_lock(void);
 extern void unlock_vector_lock(void);
 extern void __setup_vector_irq(int cpu);
diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h
index cb09802ce651..a8d065d85f57 100644
--- a/include/asm-x86/irq_vectors.h
+++ b/include/asm-x86/irq_vectors.h
@@ -19,19 +19,14 @@
 
 /*
  * Reserve the lowest usable priority level 0x20 - 0x2f for triggering
- * cleanup after irq migration on 64 bit.
+ * cleanup after irq migration.
  */
 #define IRQ_MOVE_CLEANUP_VECTOR	FIRST_EXTERNAL_VECTOR
 
 /*
- * Vectors 0x20-0x2f are used for ISA interrupts on 32 bit.
- * Vectors 0x30-0x3f are used for ISA interrupts on 64 bit.
+ * Vectors 0x30-0x3f are used for ISA interrupts.
  */
-#ifdef CONFIG_X86_32
-#define IRQ0_VECTOR		(FIRST_EXTERNAL_VECTOR)
-#else
 #define IRQ0_VECTOR		(FIRST_EXTERNAL_VECTOR + 0x10)
-#endif
 #define IRQ1_VECTOR		(IRQ0_VECTOR + 1)
 #define IRQ2_VECTOR		(IRQ0_VECTOR + 2)
 #define IRQ3_VECTOR		(IRQ0_VECTOR + 3)
@@ -96,11 +91,7 @@
  * start at 0x31(0x41) to spread out vectors evenly between priority
  * levels. (0x80 is the syscall vector)
  */
-#ifdef CONFIG_X86_32
-# define FIRST_DEVICE_VECTOR	0x31
-#else
-# define FIRST_DEVICE_VECTOR	(IRQ15_VECTOR + 2)
-#endif
+#define FIRST_DEVICE_VECTOR	(IRQ15_VECTOR + 2)
 
 #define NR_VECTORS		256
 
diff --git a/include/asm-x86/mach-default/entry_arch.h b/include/asm-x86/mach-default/entry_arch.h
index 9283b60a1dd2..6b1add8e31dd 100644
--- a/include/asm-x86/mach-default/entry_arch.h
+++ b/include/asm-x86/mach-default/entry_arch.h
@@ -14,6 +14,7 @@ BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
 BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
 BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
 BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
+BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
 #endif
 
 /*
diff --git a/include/asm-x86/mach-default/mach_apic.h b/include/asm-x86/mach-default/mach_apic.h
index 2a330a41b3dd..3c66f2cdaec1 100644
--- a/include/asm-x86/mach-default/mach_apic.h
+++ b/include/asm-x86/mach-default/mach_apic.h
@@ -85,6 +85,20 @@ static inline int apicid_to_node(int logical_apicid)
 	return 0;
 #endif
 }
+
+static inline cpumask_t vector_allocation_domain(int cpu)
+{
+        /* Careful. Some cpus do not strictly honor the set of cpus
+         * specified in the interrupt destination when using lowest
+         * priority interrupt delivery mode.
+         *
+         * In particular there was a hyperthreading cpu observed to
+         * deliver interrupts to the wrong hyperthread when only one
+         * hyperthread was specified in the interrupt desitination.
+         */
+        cpumask_t domain = { { [0] = APIC_ALL_CPUS, } };
+        return domain;
+}
 #endif
 
 static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
@@ -138,6 +152,5 @@ static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
 static inline void enable_apic_mode(void)
 {
 }
-
 #endif /* CONFIG_X86_LOCAL_APIC */
 #endif /* ASM_X86__MACH_DEFAULT__MACH_APIC_H */
diff --git a/include/asm-x86/mach-generic/mach_apic.h b/include/asm-x86/mach-generic/mach_apic.h
index 5d010c6881dd..5085b52da301 100644
--- a/include/asm-x86/mach-generic/mach_apic.h
+++ b/include/asm-x86/mach-generic/mach_apic.h
@@ -24,6 +24,7 @@
 #define check_phys_apicid_present (genapic->check_phys_apicid_present)
 #define check_apicid_used (genapic->check_apicid_used)
 #define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
+#define vector_allocation_domain (genapic->vector_allocation_domain)
 #define enable_apic_mode (genapic->enable_apic_mode)
 #define phys_pkg_id (genapic->phys_pkg_id)
 
diff --git a/include/asm-x86/numaq/apic.h b/include/asm-x86/numaq/apic.h
index a8344ba6ea15..0bf2a06b7a4e 100644
--- a/include/asm-x86/numaq/apic.h
+++ b/include/asm-x86/numaq/apic.h
@@ -12,8 +12,6 @@ static inline cpumask_t target_cpus(void)
 	return CPU_MASK_ALL;
 }
 
-#define TARGET_CPUS (target_cpus())
-
 #define NO_BALANCE_IRQ (1)
 #define esr_disable (1)
 
diff --git a/include/asm-x86/summit/apic.h b/include/asm-x86/summit/apic.h
index c5b2e4b10358..0f68037b8f24 100644
--- a/include/asm-x86/summit/apic.h
+++ b/include/asm-x86/summit/apic.h
@@ -22,7 +22,6 @@ static inline cpumask_t target_cpus(void)
 	 */
 	return cpumask_of_cpu(0);
 }
-#define TARGET_CPUS	(target_cpus())
 
 #define INT_DELIVERY_MODE (dest_LowestPrio)
 #define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
-- 
cgit v1.2.3


From d83e94acd95789829804fd9e442bd18975f4dc89 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:33 -0700
Subject: x86, io-apic: remove union about dest for log/phy

let user decide the meaning of the bits.

This unifies the 32-bit and 64-bit io-apic code a bit.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic_32.c | 18 +++++++-----------
 include/asm-x86/io_apic.h    | 16 ----------------
 2 files changed, 7 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/io_apic_32.c b/arch/x86/kernel/io_apic_32.c
index 3001924bdd36..353e586822af 100644
--- a/arch/x86/kernel/io_apic_32.c
+++ b/arch/x86/kernel/io_apic_32.c
@@ -1224,7 +1224,7 @@ static int setup_ioapic_entry(int apic, int irq,
 
 	entry->delivery_mode = INT_DELIVERY_MODE;
 	entry->dest_mode = INT_DEST_MODE;
-	entry->dest.logical.logical_dest = destination;
+	entry->dest = destination;
 
 	entry->mask = 0;                                /* enable IRQ */
 	entry->trigger = trigger;
@@ -1336,7 +1336,7 @@ static void __init setup_timer_IRQ0_pin(unsigned int apic, unsigned int pin,
 	 */
 	entry.dest_mode = INT_DEST_MODE;
 	entry.mask = 1;					/* mask IRQ now */
-	entry.dest.logical.logical_dest = cpu_mask_to_apicid(TARGET_CPUS);
+	entry.dest = cpu_mask_to_apicid(TARGET_CPUS);
 	entry.delivery_mode = INT_DELIVERY_MODE;
 	entry.polarity = 0;
 	entry.trigger = 0;
@@ -1425,19 +1425,15 @@ __apicdebuginit(void) print_IO_APIC(void)
 
 	printk(KERN_DEBUG ".... IRQ redirection table:\n");
 
-	printk(KERN_DEBUG " NR Log Phy Mask Trig IRR Pol"
-			  " Stat Dest Deli Vect:   \n");
+	printk(KERN_DEBUG " NR Dst Mask Trig IRR Pol"
+			  " Stat Dmod Deli Vect:   \n");
 
 	for (i = 0; i <= reg_01.bits.entries; i++) {
 		struct IO_APIC_route_entry entry;
 
 		entry = ioapic_read_entry(apic, i);
 
-		printk(KERN_DEBUG " %02x %03X %02X  ",
-			i,
-			entry.dest.logical.logical_dest,
-			entry.dest.physical.physical_dest
-		);
+		printk(KERN_DEBUG " %02x %02X  ", i, entry.dest);
 
 		printk("%1d    %1d    %1d   %1d   %1d    %1d    %1d    %02X\n",
 			entry.mask,
@@ -1717,7 +1713,7 @@ void disable_IO_APIC(void)
 		entry.dest_mode       = 0; /* Physical */
 		entry.delivery_mode   = dest_ExtINT; /* ExtInt */
 		entry.vector          = 0;
-		entry.dest.physical.physical_dest = read_apic_id();
+		entry.dest	      = read_apic_id();
 
 		/*
 		 * Add it to the IO-APIC irq-routing table:
@@ -2185,7 +2181,7 @@ static inline void __init unlock_ExtINT_logic(void)
 
 	entry1.dest_mode = 0;			/* physical delivery */
 	entry1.mask = 0;			/* unmask IRQ now */
-	entry1.dest.physical.physical_dest = hard_smp_processor_id();
+	entry1.dest = hard_smp_processor_id();
 	entry1.delivery_mode = dest_ExtINT;
 	entry1.polarity = entry0.polarity;
 	entry1.trigger = 0;
diff --git a/include/asm-x86/io_apic.h b/include/asm-x86/io_apic.h
index 8ec68a50cf10..ce818292d2c7 100644
--- a/include/asm-x86/io_apic.h
+++ b/include/asm-x86/io_apic.h
@@ -87,24 +87,8 @@ struct IO_APIC_route_entry {
 		mask		:  1,	/* 0: enabled, 1: disabled */
 		__reserved_2	: 15;
 
-#ifdef CONFIG_X86_32
-	union {
-		struct {
-			__u32	__reserved_1	: 24,
-				physical_dest	:  4,
-				__reserved_2	:  4;
-		} physical;
-
-		struct {
-			__u32	__reserved_1	: 24,
-				logical_dest	:  8;
-		} logical;
-	} dest;
-#else
 	__u32	__reserved_3	: 24,
 		dest		:  8;
-#endif
-
 } __attribute__ ((packed));
 
 struct IR_IO_APIC_route_entry {
-- 
cgit v1.2.3


From aa45f97b1bb40adae1288669e73350907ffae85e Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:40 -0700
Subject: x86: remove ioapic_force

no user left.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/apic_64.c    | 1 -
 arch/x86/kernel/io_apic_64.c | 2 --
 include/asm-x86/apic.h       | 2 --
 3 files changed, 5 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/apic_64.c b/arch/x86/kernel/apic_64.c
index 4d7a188025b3..cd860856a0b7 100644
--- a/arch/x86/kernel/apic_64.c
+++ b/arch/x86/kernel/apic_64.c
@@ -1813,7 +1813,6 @@ static int __init apic_set_verbosity(char *arg)
 	if (!arg)  {
 #ifdef CONFIG_X86_64
 		skip_ioapic_setup = 0;
-		ioapic_force = 1;
 		return 0;
 #endif
 		return -EINVAL;
diff --git a/arch/x86/kernel/io_apic_64.c b/arch/x86/kernel/io_apic_64.c
index 915af9b87aa4..b70fd8232185 100644
--- a/arch/x86/kernel/io_apic_64.c
+++ b/arch/x86/kernel/io_apic_64.c
@@ -63,8 +63,6 @@
 
 #define __apicdebuginit(type) static type __init
 
-int ioapic_force;
-
 /*
  *      Is the SiS APIC rmw bug present ?
  *      -1 = don't know, 0 = no, 1 = yes
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
index d76a0839abe9..2d970f6bc2a1 100644
--- a/include/asm-x86/apic.h
+++ b/include/asm-x86/apic.h
@@ -40,8 +40,6 @@ extern void generic_apic_probe(void);
 extern unsigned int apic_verbosity;
 extern int local_apic_timer_c2_ok;
 
-extern int ioapic_force;
-
 extern int disable_apic;
 /*
  * Basic functions accessing APICs.
-- 
cgit v1.2.3


From 42379b1122bab7f9aefdbd4b7004a6fa89dfbae5 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:45 -0700
Subject: pci: change msi-x vector to 32bit

we are using 28bit pci (bus/dev/fn + 12 bits) as irq number, so the
cache for irq number should be 32 bit too.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 drivers/scsi/qla2xxx/qla_def.h | 2 +-
 include/linux/pci.h            | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 83c819216771..f25f41a499e5 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2108,7 +2108,7 @@ struct scsi_qla_host;
 
 struct qla_msix_entry {
 	int have_irq;
-	uint16_t msix_vector;
+	uint32_t msix_vector;
 	uint16_t msix_entry;
 };
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 98dc6243a706..1f8db240ca48 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -723,7 +723,7 @@ enum pci_dma_burst_strategy {
 };
 
 struct msix_entry {
-	u16 	vector;	/* kernel uses to write allocated vector */
+	u32	vector;	/* kernel uses to write allocated vector */
 	u16	entry;	/* driver uses to specify entry, OS writes */
 };
 
-- 
cgit v1.2.3


From bcd562607f17b0c9f9ae96af849894dd06645f63 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:46 -0700
Subject: x86: irq: interrupt array size should be NR_VECTORS

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/asm-x86/hw_irq.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h
index 51c787d17cbc..39c7a4745d25 100644
--- a/include/asm-x86/hw_irq.h
+++ b/include/asm-x86/hw_irq.h
@@ -115,7 +115,7 @@ extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
 #endif
 
 #ifdef CONFIG_X86_32
-extern void (*const interrupt[NR_IRQS])(void);
+extern void (*const interrupt[NR_VECTORS])(void);
 #endif
 
 typedef int vector_irq_t[NR_VECTORS];
-- 
cgit v1.2.3


From 29ccbbf232c035b8c7ff0c5060fbe30a66ed9b99 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:49 -0700
Subject: x86: remove first_free_entry/pin_map_size

no user now

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic.c | 7 -------
 arch/x86/kernel/setup.c   | 4 ----
 include/asm-x86/irq.h     | 3 ---
 3 files changed, 14 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index a466b04ad5a4..5de2d38812aa 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -72,13 +72,6 @@ int sis_apic_bug = -1;
 static DEFINE_SPINLOCK(ioapic_lock);
 static DEFINE_SPINLOCK(vector_lock);
 
-int first_free_entry;
-/*
- * Rough estimation of how many shared IRQs there are, can
- * be changed anytime.
- */
-int pin_map_size;
-
 /*
  * # of IRQ routing registers
  */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 02e3a6697977..d90c659b70e9 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1074,10 +1074,6 @@ void __init setup_arch(char **cmdline_p)
 		nr_irqs = 32 * nr_cpu_ids + 224;
 	init_cpu_to_node();
 #endif
-#ifdef CONFIG_X86_IO_APIC
-	pin_map_size = nr_irqs * 2;
-	first_free_entry = nr_irqs;
-#endif
 
 	init_apic_mappings();
 	ioapic_init_mappings();
diff --git a/include/asm-x86/irq.h b/include/asm-x86/irq.h
index 2a130c44f5de..1e5f2909c1db 100644
--- a/include/asm-x86/irq.h
+++ b/include/asm-x86/irq.h
@@ -10,9 +10,6 @@
 #include <asm/apicdef.h>
 #include <asm/irq_vectors.h>
 
-extern int pin_map_size;
-extern int first_free_entry;
-
 static inline int irq_canonicalize(int irq)
 {
 	return ((irq == 2) ? 9 : irq);
-- 
cgit v1.2.3


From 9d6a4d0823b3b8e29156f5e698b5a68687afad32 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Tue, 19 Aug 2008 20:50:52 -0700
Subject: x86: probe nr_irqs even only mptable is used

for !CONFIG_HAVE_SPARSE_IRQ

fix:

 In file included from arch/x86/kernel/early-quirks.c:18:
 include/asm/io_apic.h: In function 'probe_nr_irqs':
 include/asm/io_apic.h:209: error: 'NR_IRQS' undeclared (first use in this function)
 include/asm/io_apic.h:209: error: (Each undeclared identifier is reported only once
 include/asm/io_apic.h:209: error: for each function it appears in.)

v2: fix by Ingo

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/acpi/boot.c | 25 -------------------------
 arch/x86/kernel/io_apic.c   | 43 ++++++++++++++++++++++++++++++-------------
 arch/x86/kernel/setup.c     |  6 +++---
 include/asm-x86/io_apic.h   |  8 ++++++++
 include/asm-x86/mpspec.h    |  1 -
 5 files changed, 41 insertions(+), 42 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 3e9d163fd92f..5fef4fece4a5 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -957,29 +957,6 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 	nr_ioapics++;
 }
 
-int get_nr_irqs_via_madt(void)
-{
-	int idx;
-	int nr = 0;
-
-	for (idx = 0; idx < nr_ioapics; idx++) {
-		if (mp_ioapic_routing[idx].gsi_end > nr)
-			nr = mp_ioapic_routing[idx].gsi_end;
-	}
-
-	nr++;
-
-	/* double it for hotplug and msi and nmi */
-	nr <<= 1;
-
-	/* something wrong ? */
-	if (nr < 32)
-		nr = 32;
-
-	return nr;
-
-}
-
 static void assign_to_mp_irq(struct mp_config_intsrc *m,
 				    struct mp_config_intsrc *mp_irq)
 {
@@ -1278,8 +1255,6 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 	}
 
 
-	nr_irqs = get_nr_irqs_via_madt();
-
 	count =
 	    acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, acpi_parse_int_src_ovr,
 				  nr_irqs);
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index f853b667fa5c..f7e80262cbbb 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -3596,6 +3596,36 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 }
 #endif /* CONFIG_HT_IRQ */
 
+int __init io_apic_get_redir_entries (int ioapic)
+{
+	union IO_APIC_reg_01	reg_01;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ioapic_lock, flags);
+	reg_01.raw = io_apic_read(ioapic, 1);
+	spin_unlock_irqrestore(&ioapic_lock, flags);
+
+	return reg_01.bits.entries;
+}
+
+int __init probe_nr_irqs(void)
+{
+	int idx;
+	int nr = 0;
+
+	for (idx = 0; idx < nr_ioapics; idx++)
+		nr += io_apic_get_redir_entries(idx);
+
+	/* double it for hotplug and msi and nmi */
+	nr <<= 1;
+
+	/* something wrong ? */
+	if (nr < 32)
+		nr = 32;
+
+	return nr;
+}
+
 /* --------------------------------------------------------------------------
                           ACPI-based IOAPIC Configuration
    -------------------------------------------------------------------------- */
@@ -3690,19 +3720,6 @@ int __init io_apic_get_version(int ioapic)
 }
 #endif
 
-int __init io_apic_get_redir_entries (int ioapic)
-{
-	union IO_APIC_reg_01	reg_01;
-	unsigned long flags;
-
-	spin_lock_irqsave(&ioapic_lock, flags);
-	reg_01.raw = io_apic_read(ioapic, 1);
-	spin_unlock_irqrestore(&ioapic_lock, flags);
-
-	return reg_01.bits.entries;
-}
-
-
 int io_apic_set_pci_routing (int ioapic, int pin, int irq, int triggering, int polarity)
 {
 	if (!IO_APIC_IRQ(irq)) {
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index d90c659b70e9..61335306696a 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1069,15 +1069,15 @@ void __init setup_arch(char **cmdline_p)
 	prefill_possible_map();
 
 #ifdef CONFIG_X86_64
-	/* need to wait for nr_cpu_ids settle down */
-	if (nr_irqs == NR_IRQS)
-		nr_irqs = 32 * nr_cpu_ids + 224;
 	init_cpu_to_node();
 #endif
 
 	init_apic_mappings();
 	ioapic_init_mappings();
 
+	/* need to wait for io_apic is mapped */
+	nr_irqs = probe_nr_irqs();
+
 	kvm_guest_init();
 
 	e820_reserve_resources();
diff --git a/include/asm-x86/io_apic.h b/include/asm-x86/io_apic.h
index ce818292d2c7..d35cbd7aa587 100644
--- a/include/asm-x86/io_apic.h
+++ b/include/asm-x86/io_apic.h
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <asm/mpspec.h>
 #include <asm/apicdef.h>
+#include <asm/irq_vectors.h>
 
 /*
  * Intel IO-APIC support for SMP and UP systems.
@@ -187,10 +188,17 @@ extern void restore_IO_APIC_setup(void);
 extern void reinit_intr_remapped_IO_APIC(int);
 #endif
 
+extern int probe_nr_irqs(void);
+
 #else  /* !CONFIG_X86_IO_APIC */
 #define io_apic_assign_pci_irqs 0
 static const int timer_through_8259 = 0;
 static inline void ioapic_init_mappings(void) { }
+
+static inline int probe_nr_irqs(void)
+{
+	return NR_IRQS;
+}
 #endif
 
 #endif /* ASM_X86__IO_APIC_H */
diff --git a/include/asm-x86/mpspec.h b/include/asm-x86/mpspec.h
index a0748021250b..be2241a818f1 100644
--- a/include/asm-x86/mpspec.h
+++ b/include/asm-x86/mpspec.h
@@ -60,7 +60,6 @@ extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 				   u32 gsi);
 extern void mp_config_acpi_legacy_irqs(void);
 extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
-extern int get_nr_irqs_via_madt(void);
 #ifdef CONFIG_X86_IO_APIC
 extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
 				u32 gsi, int triggering, int polarity);
-- 
cgit v1.2.3


From 8c464a4b23ca283b414022ebc77787f3c7040fa7 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Mon, 25 Aug 2008 12:41:19 -0700
Subject: sparseirq: move kstat_irqs from kstat to irq_desc - fix

fix non-sparseirq architectures.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/irq.h         |  4 ++--
 include/linux/kernel_stat.h | 10 ++++++++--
 kernel/irq/chip.c           | 21 ++++++++++++++++++++-
 kernel/irq/handle.c         | 10 ++++++++++
 4 files changed, 40 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 2445d2b3d5dc..93fe9a943e71 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -161,8 +161,6 @@ struct irq_desc {
 #endif
 #ifdef CONFIG_HAVE_DYN_ARRAY
 	unsigned int            *kstat_irqs;
-#else
-	unsigned int            kstat_irqs[NR_CPUS];
 #endif
 #if defined(CONFIG_INTR_REMAP) && defined(CONFIG_HAVE_SPARSE_IRQ)
        struct irq_2_iommu      *irq_2_iommu;
@@ -219,8 +217,10 @@ extern struct irq_desc *sparse_irqs;
 
 #endif
 
+#ifdef CONFIG_HAVE_DYN_ARRAY
 #define kstat_irqs_this_cpu(DESC) \
 	((DESC)->kstat_irqs[smp_processor_id()])
+#endif
 
 /*
  * Migration helpers for obsolete names, they will go away:
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index f10616712de5..21249d8c1293 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -28,7 +28,7 @@ struct cpu_usage_stat {
 
 struct kernel_stat {
 	struct cpu_usage_stat	cpustat;
-#ifndef CONFIG_GENERIC_HARDIRQS
+#ifndef CONFIG_HAVE_DYN_ARRAY
        unsigned int irqs[NR_IRQS];
 #endif
 };
@@ -41,7 +41,13 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 
 extern unsigned long long nr_context_switches(void);
 
-#ifndef CONFIG_GENERIC_HARDIRQS
+#ifndef CONFIG_HAVE_DYN_ARRAY
+#define kstat_irqs_this_cpu(irq) \
+	(kstat_this_cpu.irqs[irq])
+#endif
+
+
+#ifndef CONFIG_HAVE_DYN_ARRAY
 static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
        return kstat_cpu(cpu).irqs[irq];
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 9fc5e69213de..4ef555c50db8 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -327,7 +327,11 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+#ifdef CONFIG_HAVE_DYN_ARRAY
 	kstat_irqs_this_cpu(desc)++;
+#else
+	kstat_irqs_this_cpu(irq)++;
+#endif
 
 	action = desc->action;
 	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
@@ -368,7 +372,11 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+#ifdef CONFIG_HAVE_DYN_ARRAY
 	kstat_irqs_this_cpu(desc)++;
+#else
+	kstat_irqs_this_cpu(irq)++;
+#endif
 
 	/*
 	 * If its disabled or no action available
@@ -415,7 +423,11 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 		goto out;
 
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
+#ifdef CONFIG_HAVE_DYN_ARRAY
 	kstat_irqs_this_cpu(desc)++;
+#else
+	kstat_irqs_this_cpu(irq)++;
+#endif
 
 	/*
 	 * If its disabled or no action available
@@ -479,8 +491,11 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		mask_ack_irq(desc, irq);
 		goto out_unlock;
 	}
-
+#ifdef CONFIG_HAVE_DYN_ARRAY
 	kstat_irqs_this_cpu(desc)++;
+#else
+	kstat_irqs_this_cpu(irq)++;
+#endif
 
 	/* Start handling the irq */
 	desc->chip->ack(irq);
@@ -535,7 +550,11 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 {
 	irqreturn_t action_ret;
 
+#ifdef CONFIG_HAVE_DYN_ARRAY
 	kstat_irqs_this_cpu(desc)++;
+#else
+	kstat_irqs_this_cpu(irq)++;
+#endif
 
 	if (desc->chip->ack)
 		desc->chip->ack(irq);
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index d638a911cbc1..eae69373a9c6 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -34,7 +34,11 @@ void
 handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 {
 	print_irq_desc(irq, desc);
+#ifdef CONFIG_HAVE_DYN_ARRAY
 	kstat_irqs_this_cpu(desc)++;
+#else
+	kstat_irqs_this_cpu(irq)++;
+#endif
 	ack_bad_irq(irq);
 }
 
@@ -401,7 +405,11 @@ unsigned int __do_IRQ(unsigned int irq)
 	struct irqaction *action;
 	unsigned int status;
 
+#ifdef CONFIG_HAVE_DYN_ARRAY
 	kstat_irqs_this_cpu(desc)++;
+#else
+	kstat_irqs_this_cpu(irq)++;
+#endif
 	if (CHECK_IRQ_PER_CPU(desc->status)) {
 		irqreturn_t action_ret;
 
@@ -501,10 +509,12 @@ void early_init_irq_lock_class(void)
 }
 #endif
 
+#ifdef CONFIG_HAVE_DYN_ARRAY
 unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	return desc->kstat_irqs[cpu];
 }
+#endif
 EXPORT_SYMBOL(kstat_irqs_cpu);
 
-- 
cgit v1.2.3


From 1dd6ba2e179773597e20f17f66049a64e6c4b2ec Mon Sep 17 00:00:00 2001
From: Cyrill Gorcunov <gorcunov@gmail.com>
Date: Mon, 25 Aug 2008 21:27:26 +0400
Subject: x86: apic - unify smp_spurious/error_interrupt declaration

According to entry_64.S we do pass pt_regs pointer
into interrupt handlers but don't use them. So we
safely may merge the declarations.

Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/apic.c   | 8 --------
 include/asm-x86/hw_irq.h | 5 -----
 2 files changed, 13 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/apic.c b/arch/x86/kernel/apic.c
index ca5ef71f4208..0556f375e40b 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -1659,11 +1659,7 @@ int __init APIC_init_uniprocessor(void)
 /*
  * This interrupt should _never_ happen with our APIC/SMP architecture
  */
-#ifdef CONFIG_X86_64
-asmlinkage void smp_spurious_interrupt(void)
-#else
 void smp_spurious_interrupt(struct pt_regs *regs)
-#endif
 {
 	u32 v;
 
@@ -1694,11 +1690,7 @@ void smp_spurious_interrupt(struct pt_regs *regs)
 /*
  * This interrupt should never happen with our APIC/SMP architecture
  */
-#ifdef CONFIG_X86_64
-asmlinkage void smp_error_interrupt(void)
-#else
 void smp_error_interrupt(struct pt_regs *regs)
-#endif
 {
 	u32 v, v1;
 
diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h
index 39c7a4745d25..749d042f0556 100644
--- a/include/asm-x86/hw_irq.h
+++ b/include/asm-x86/hw_irq.h
@@ -96,13 +96,8 @@ extern asmlinkage void qic_call_function_interrupt(void);
 
 /* SMP */
 extern void smp_apic_timer_interrupt(struct pt_regs *);
-#ifdef CONFIG_X86_32
 extern void smp_spurious_interrupt(struct pt_regs *);
 extern void smp_error_interrupt(struct pt_regs *);
-#else
-extern asmlinkage void smp_spurious_interrupt(void);
-extern asmlinkage void smp_error_interrupt(void);
-#endif
 #ifdef CONFIG_X86_SMP
 extern void smp_reschedule_interrupt(struct pt_regs *);
 extern void smp_call_function_interrupt(struct pt_regs *);
-- 
cgit v1.2.3


From a11b5abef50722e42a7d13f6b799c4f606fcb797 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Wed, 3 Sep 2008 16:58:31 -0700
Subject: x2apic: fix reserved APIC register accesses in print_local_APIC()

APIC_ARBPRI is a reserved register for XAPIC and beyond.
APIC_RRR is a reserved register except for 82489DX, APIC for Pentium processors.
APIC_EOI is a write only register.
APIC_DFR is reserved in x2apic mode.

Access to these registers in x2apic will result in #GP fault. Fix these
apic register accesses.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Maciej W. Rozycki <macro@linux-mips.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/io_apic.c | 27 ++++++++++++++++++---------
 include/asm-x86/apic.h    | 14 ++++++++++++++
 2 files changed, 32 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index d28128e0392c..93ceb19d1e90 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -1751,21 +1751,30 @@ __apicdebuginit(void) print_local_APIC(void *dummy)
 	printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK);
 
 	if (APIC_INTEGRATED(ver)) {                     /* !82489DX */
-		v = apic_read(APIC_ARBPRI);
-		printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v,
-			v & APIC_ARBPRI_MASK);
+		if (!APIC_XAPIC(ver)) {
+			v = apic_read(APIC_ARBPRI);
+			printk(KERN_DEBUG "... APIC ARBPRI: %08x (%02x)\n", v,
+			       v & APIC_ARBPRI_MASK);
+		}
 		v = apic_read(APIC_PROCPRI);
 		printk(KERN_DEBUG "... APIC PROCPRI: %08x\n", v);
 	}
 
-	v = apic_read(APIC_EOI);
-	printk(KERN_DEBUG "... APIC EOI: %08x\n", v);
-	v = apic_read(APIC_RRR);
-	printk(KERN_DEBUG "... APIC RRR: %08x\n", v);
+	/*
+	 * Remote read supported only in the 82489DX and local APIC for
+	 * Pentium processors.
+	 */
+	if (!APIC_INTEGRATED(ver) || maxlvt == 3) {
+		v = apic_read(APIC_RRR);
+		printk(KERN_DEBUG "... APIC RRR: %08x\n", v);
+	}
+
 	v = apic_read(APIC_LDR);
 	printk(KERN_DEBUG "... APIC LDR: %08x\n", v);
-	v = apic_read(APIC_DFR);
-	printk(KERN_DEBUG "... APIC DFR: %08x\n", v);
+	if (!x2apic_enabled()) {
+		v = apic_read(APIC_DFR);
+		printk(KERN_DEBUG "... APIC DFR: %08x\n", v);
+	}
 	v = apic_read(APIC_SPIV);
 	printk(KERN_DEBUG "... APIC SPIV: %08x\n", v);
 
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
index 2d970f6bc2a1..ef1d72dbdfe0 100644
--- a/include/asm-x86/apic.h
+++ b/include/asm-x86/apic.h
@@ -98,6 +98,20 @@ extern void check_x2apic(void);
 extern void enable_x2apic(void);
 extern void enable_IR_x2apic(void);
 extern void x2apic_icr_write(u32 low, u32 id);
+static inline int x2apic_enabled(void)
+{
+	int msr, msr2;
+
+	if (!cpu_has_x2apic)
+		return 0;
+
+	rdmsr(MSR_IA32_APICBASE, msr, msr2);
+	if (msr & X2APIC_ENABLE)
+		return 1;
+	return 0;
+}
+#else
+#define x2apic_enabled()	0
 #endif
 
 struct apic_ops {
-- 
cgit v1.2.3


From f6dd5c3106fb283e37d915eeb33019ef40510f85 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Wed, 3 Sep 2008 16:58:32 -0700
Subject: dmar: fix using early fixmap mapping for DMAR table parsing

Very early detection of the DMAR tables will setup fixmap mapping. For
parsing these tables later (while enabling dma and/or interrupt remapping),
early fixmap mapping shouldn't be used. Fix it by calling table detection
routines again, which will call generic apci_get_table() for setting up
the correct mapping.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 drivers/pci/dmar.c   | 49 ++++++++++++++++++++++++++++---------------------
 include/linux/dmar.h |  1 -
 2 files changed, 28 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index bd2c01674f5e..f2c5eb6e78f7 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -289,6 +289,24 @@ dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
 	}
 }
 
+/**
+ * dmar_table_detect - checks to see if the platform supports DMAR devices
+ */
+static int __init dmar_table_detect(void)
+{
+	acpi_status status = AE_OK;
+
+	/* if we could find DMAR table, then there are DMAR devices */
+	status = acpi_get_table(ACPI_SIG_DMAR, 0,
+				(struct acpi_table_header **)&dmar_tbl);
+
+	if (ACPI_SUCCESS(status) && !dmar_tbl) {
+		printk (KERN_WARNING PREFIX "Unable to map DMAR\n");
+		status = AE_NOT_FOUND;
+	}
+
+	return (ACPI_SUCCESS(status) ? 1 : 0);
+}
 
 /**
  * parse_dmar_table - parses the DMA reporting table
@@ -300,6 +318,12 @@ parse_dmar_table(void)
 	struct acpi_dmar_header *entry_header;
 	int ret = 0;
 
+	/*
+	 * Do it again, earlier dmar_tbl mapping could be mapped with
+	 * fixed map.
+	 */
+	dmar_table_detect();
+
 	dmar = (struct acpi_table_dmar *)dmar_tbl;
 	if (!dmar)
 		return -ENODEV;
@@ -430,30 +454,11 @@ int __init dmar_table_init(void)
 	return 0;
 }
 
-/**
- * early_dmar_detect - checks to see if the platform supports DMAR devices
- */
-int __init early_dmar_detect(void)
-{
-	acpi_status status = AE_OK;
-
-	/* if we could find DMAR table, then there are DMAR devices */
-	status = acpi_get_table(ACPI_SIG_DMAR, 0,
-				(struct acpi_table_header **)&dmar_tbl);
-
-	if (ACPI_SUCCESS(status) && !dmar_tbl) {
-		printk (KERN_WARNING PREFIX "Unable to map DMAR\n");
-		status = AE_NOT_FOUND;
-	}
-
-	return (ACPI_SUCCESS(status) ? 1 : 0);
-}
-
 void __init detect_intel_iommu(void)
 {
 	int ret;
 
-	ret = early_dmar_detect();
+	ret = dmar_table_detect();
 
 #ifdef CONFIG_DMAR
 	{
@@ -479,14 +484,16 @@ void __init detect_intel_iommu(void)
 			       " x2apic support\n");
 
 			dmar_disabled = 1;
-			return;
+			goto end;
 		}
 
 		if (ret && !no_iommu && !iommu_detected && !swiotlb &&
 		    !dmar_disabled)
 			iommu_detected = 1;
 	}
+end:
 #endif
+	dmar_tbl = NULL;
 }
 
 
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index c360c558e59e..f1984fc3e06d 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -45,7 +45,6 @@ extern struct list_head dmar_drhd_units;
 	list_for_each_entry(drhd, &dmar_drhd_units, list)
 
 extern int dmar_table_init(void);
-extern int early_dmar_detect(void);
 extern int dmar_dev_scope_init(void);
 
 /* Intel IOMMU detection */
-- 
cgit v1.2.3


From 58ac1e76ce77d515bd5cb65dbc465a040da341c6 Mon Sep 17 00:00:00 2001
From: "venkatesh.pallipadi@intel.com" <venkatesh.pallipadi@intel.com>
Date: Fri, 5 Sep 2008 18:02:17 -0700
Subject: x86: HPET_MSI Basic HPET_MSI setup code

Basic HPET MSI setup code. Routines to perform basic MSI read write
in HPET memory map and setting up irq_chip for HPET MSI.

Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Signed-off-by: Shaohua Li <shaohua.li@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/hpet.c    | 54 +++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/io_apic.c | 64 +++++++++++++++++++++++++++++++++++++++++++++++
 include/asm-x86/hpet.h    | 21 ++++++++++++++++
 3 files changed, 139 insertions(+)

(limited to 'include')

diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index f7cb5e9e261e..3f10d16a8348 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -6,6 +6,8 @@
 #include <linux/init.h>
 #include <linux/sysdev.h>
 #include <linux/pm.h>
+#include <linux/interrupt.h>
+#include <linux/cpu.h>
 
 #include <asm/fixmap.h>
 #include <asm/hpet.h>
@@ -25,6 +27,15 @@
 unsigned long hpet_address;
 static void __iomem *hpet_virt_address;
 
+struct hpet_dev {
+	struct clock_event_device evt;
+	unsigned int num;
+	int cpu;
+	unsigned int irq;
+	unsigned int flags;
+	char name[10];
+};
+
 unsigned long hpet_readl(unsigned long a)
 {
 	return readl(hpet_virt_address + a);
@@ -304,6 +315,49 @@ static int hpet_legacy_next_event(unsigned long delta,
 	return hpet_next_event(delta, evt, 0);
 }
 
+/*
+ * HPET MSI Support
+ */
+
+void hpet_msi_unmask(unsigned int irq)
+{
+	struct hpet_dev *hdev = get_irq_data(irq);
+	unsigned long cfg;
+
+	/* unmask it */
+	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
+	cfg |= HPET_TN_FSB;
+	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
+}
+
+void hpet_msi_mask(unsigned int irq)
+{
+	unsigned long cfg;
+	struct hpet_dev *hdev = get_irq_data(irq);
+
+	/* mask it */
+	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
+	cfg &= ~HPET_TN_FSB;
+	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
+}
+
+void hpet_msi_write(unsigned int irq, struct msi_msg *msg)
+{
+	struct hpet_dev *hdev = get_irq_data(irq);
+
+	hpet_writel(msg->data, HPET_Tn_ROUTE(hdev->num));
+	hpet_writel(msg->address_lo, HPET_Tn_ROUTE(hdev->num) + 4);
+}
+
+void hpet_msi_read(unsigned int irq, struct msi_msg *msg)
+{
+	struct hpet_dev *hdev = get_irq_data(irq);
+
+	msg->data = hpet_readl(HPET_Tn_ROUTE(hdev->num));
+	msg->address_lo = hpet_readl(HPET_Tn_ROUTE(hdev->num) + 4);
+	msg->address_hi = 0;
+}
+
 /*
  * Clock source related code
  */
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index d22fecf828b8..77fa155becf6 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -41,6 +41,7 @@
 #endif
 #include <linux/bootmem.h>
 #include <linux/dmar.h>
+#include <linux/hpet.h>
 
 #include <asm/idle.h>
 #include <asm/io.h>
@@ -56,6 +57,7 @@
 #include <asm/hypertransport.h>
 #include <asm/setup.h>
 #include <asm/irq_remapping.h>
+#include <asm/hpet.h>
 
 #include <mach_ipi.h>
 #include <mach_apic.h>
@@ -3522,6 +3524,68 @@ int arch_setup_dmar_msi(unsigned int irq)
 }
 #endif
 
+#ifdef CONFIG_HPET_TIMER
+
+#ifdef CONFIG_SMP
+static void hpet_msi_set_affinity(unsigned int irq, cpumask_t mask)
+{
+	struct irq_cfg *cfg;
+	struct irq_desc *desc;
+	struct msi_msg msg;
+	unsigned int dest;
+	cpumask_t tmp;
+
+	cpus_and(tmp, mask, cpu_online_map);
+	if (cpus_empty(tmp))
+		return;
+
+	if (assign_irq_vector(irq, mask))
+		return;
+
+	cfg = irq_cfg(irq);
+	cpus_and(tmp, cfg->domain, mask);
+	dest = cpu_mask_to_apicid(tmp);
+
+	hpet_msi_read(irq, &msg);
+
+	msg.data &= ~MSI_DATA_VECTOR_MASK;
+	msg.data |= MSI_DATA_VECTOR(cfg->vector);
+	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+	hpet_msi_write(irq, &msg);
+	desc = irq_to_desc(irq);
+	desc->affinity = mask;
+}
+#endif /* CONFIG_SMP */
+
+struct irq_chip hpet_msi_type = {
+	.name = "HPET_MSI",
+	.unmask = hpet_msi_unmask,
+	.mask = hpet_msi_mask,
+	.ack = ack_apic_edge,
+#ifdef CONFIG_SMP
+	.set_affinity = hpet_msi_set_affinity,
+#endif
+	.retrigger = ioapic_retrigger_irq,
+};
+
+int arch_setup_hpet_msi(unsigned int irq)
+{
+	int ret;
+	struct msi_msg msg;
+
+	ret = msi_compose_msg(NULL, irq, &msg);
+	if (ret < 0)
+		return ret;
+
+	hpet_msi_write(irq, &msg);
+	set_irq_chip_and_handler_name(irq, &hpet_msi_type, handle_edge_irq,
+		"edge");
+	return 0;
+}
+#endif
+
 #endif /* CONFIG_PCI_MSI */
 /*
  * Hypertransport interrupt support
diff --git a/include/asm-x86/hpet.h b/include/asm-x86/hpet.h
index cbbbb6d4dd32..58b273f6ef07 100644
--- a/include/asm-x86/hpet.h
+++ b/include/asm-x86/hpet.h
@@ -1,6 +1,8 @@
 #ifndef ASM_X86__HPET_H
 #define ASM_X86__HPET_H
 
+#include <linux/msi.h>
+
 #ifdef CONFIG_HPET_TIMER
 
 #define HPET_MMAP_SIZE		1024
@@ -10,6 +12,11 @@
 #define HPET_CFG		0x010
 #define HPET_STATUS		0x020
 #define HPET_COUNTER		0x0f0
+
+#define HPET_Tn_CFG(n)		(0x100 + 0x20 * n)
+#define HPET_Tn_CMP(n)		(0x108 + 0x20 * n)
+#define HPET_Tn_ROUTE(n)	(0x110 + 0x20 * n)
+
 #define HPET_T0_CFG		0x100
 #define HPET_T0_CMP		0x108
 #define HPET_T0_ROUTE		0x110
@@ -65,6 +72,20 @@ extern void hpet_disable(void);
 extern unsigned long hpet_readl(unsigned long a);
 extern void force_hpet_resume(void);
 
+extern void hpet_msi_unmask(unsigned int irq);
+extern void hpet_msi_mask(unsigned int irq);
+extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg);
+extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg);
+
+#ifdef CONFIG_PCI_MSI
+extern int arch_setup_hpet_msi(unsigned int irq);
+#else
+static inline int arch_setup_hpet_msi(unsigned int irq)
+{
+	return -EINVAL;
+}
+#endif
+
 #ifdef CONFIG_HPET_EMULATE_RTC
 
 #include <linux/interrupt.h>
-- 
cgit v1.2.3


From 4173a0e7371ece227559b44943c6fd456ee470d1 Mon Sep 17 00:00:00 2001
From: Dean Nelson <dcn@sgi.com>
Date: Thu, 2 Oct 2008 12:18:21 -0500
Subject: x86, UV: add uv_setup_irq() and uv_teardown_irq() functions, v3

Provide a means for UV interrupt MMRs to be setup with the message to be sent
when an MSI is raised.

Signed-off-by: Dean Nelson <dcn@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/Makefile    |  2 +-
 arch/x86/kernel/io_apic.c   | 68 +++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/uv_irq.c    | 77 +++++++++++++++++++++++++++++++++++++++++++++
 include/asm-x86/uv/uv_irq.h | 36 +++++++++++++++++++++
 4 files changed, 182 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/kernel/uv_irq.c
 create mode 100644 include/asm-x86/uv/uv_irq.h

(limited to 'include')

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 45cecc59d894..acc0e8bf043e 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -108,7 +108,7 @@ obj-$(CONFIG_MICROCODE)			+= microcode.o
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
         obj-y				+= genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o
-	obj-y				+= bios_uv.o
+	obj-y				+= bios_uv.o uv_irq.o
         obj-y				+= genx2apic_cluster.o
         obj-y				+= genx2apic_phys.o
         obj-$(CONFIG_X86_PM_TIMER)	+= pmtimer_64.o
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 4ee270d30358..260c95a5e6dc 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -58,6 +58,8 @@
 #include <asm/setup.h>
 #include <asm/irq_remapping.h>
 #include <asm/hpet.h>
+#include <asm/uv/uv_hub.h>
+#include <asm/uv/uv_irq.h>
 
 #include <mach_ipi.h>
 #include <mach_apic.h>
@@ -3692,6 +3694,72 @@ int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
 }
 #endif /* CONFIG_HT_IRQ */
 
+#ifdef CONFIG_X86_64
+/*
+ * Re-target the irq to the specified CPU and enable the specified MMR located
+ * on the specified blade to allow the sending of MSIs to the specified CPU.
+ */
+int arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
+		       unsigned long mmr_offset)
+{
+	const cpumask_t *eligible_cpu = get_cpu_mask(cpu);
+	struct irq_cfg *cfg;
+	int mmr_pnode;
+	unsigned long mmr_value;
+	struct uv_IO_APIC_route_entry *entry;
+	unsigned long flags;
+	int err;
+
+	err = assign_irq_vector(irq, *eligible_cpu);
+	if (err != 0)
+		return err;
+
+	spin_lock_irqsave(&vector_lock, flags);
+	set_irq_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
+				      irq_name);
+	spin_unlock_irqrestore(&vector_lock, flags);
+
+	cfg = irq_cfg(irq);
+
+	mmr_value = 0;
+	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
+	BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
+	entry->vector = cfg->vector;
+	entry->delivery_mode = INT_DELIVERY_MODE;
+	entry->dest_mode = INT_DEST_MODE;
+	entry->polarity = 0;
+	entry->trigger = 0;
+	entry->mask = 0;
+	entry->dest = cpu_mask_to_apicid(*eligible_cpu);
+
+	mmr_pnode = uv_blade_to_pnode(mmr_blade);
+	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+
+	return irq;
+}
+
+/*
+ * Disable the specified MMR located on the specified blade so that MSIs are
+ * longer allowed to be sent.
+ */
+void arch_disable_uv_irq(int mmr_blade, unsigned long mmr_offset)
+{
+	unsigned long mmr_value;
+	struct uv_IO_APIC_route_entry *entry;
+	int mmr_pnode;
+
+	mmr_value = 0;
+	entry = (struct uv_IO_APIC_route_entry *)&mmr_value;
+	BUG_ON(sizeof(struct uv_IO_APIC_route_entry) != sizeof(unsigned long));
+
+	entry->mask = 1;
+
+	mmr_pnode = uv_blade_to_pnode(mmr_blade);
+	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
+}
+#endif /* CONFIG_X86_64 */
+
 int __init io_apic_get_redir_entries (int ioapic)
 {
 	union IO_APIC_reg_01	reg_01;
diff --git a/arch/x86/kernel/uv_irq.c b/arch/x86/kernel/uv_irq.c
new file mode 100644
index 000000000000..6bd26c91c30b
--- /dev/null
+++ b/arch/x86/kernel/uv_irq.c
@@ -0,0 +1,77 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * SGI UV IRQ functions
+ *
+ * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/irq.h>
+#include <asm/uv/uv_irq.h>
+
+static void uv_noop(unsigned int irq)
+{
+}
+
+static unsigned int uv_noop_ret(unsigned int irq)
+{
+	return 0;
+}
+
+static void uv_ack_apic(unsigned int irq)
+{
+	ack_APIC_irq();
+}
+
+struct irq_chip uv_irq_chip = {
+	.name		= "UV-CORE",
+	.startup	= uv_noop_ret,
+	.shutdown	= uv_noop,
+	.enable		= uv_noop,
+	.disable	= uv_noop,
+	.ack		= uv_noop,
+	.mask		= uv_noop,
+	.unmask		= uv_noop,
+	.eoi		= uv_ack_apic,
+	.end		= uv_noop,
+};
+
+/*
+ * Set up a mapping of an available irq and vector, and enable the specified
+ * MMR that defines the MSI that is to be sent to the specified CPU when an
+ * interrupt is raised.
+ */
+int uv_setup_irq(char *irq_name, int cpu, int mmr_blade,
+		 unsigned long mmr_offset)
+{
+	int irq;
+	int ret;
+
+	irq = create_irq();
+	if (irq <= 0)
+		return -EBUSY;
+
+	ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset);
+	if (ret != irq)
+		destroy_irq(irq);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(uv_setup_irq);
+
+/*
+ * Tear down a mapping of an irq and vector, and disable the specified MMR that
+ * defined the MSI that was to be sent to the specified CPU when an interrupt
+ * was raised.
+ *
+ * Set mmr_blade and mmr_offset to what was passed in on uv_setup_irq().
+ */
+void uv_teardown_irq(unsigned int irq, int mmr_blade, unsigned long mmr_offset)
+{
+	arch_disable_uv_irq(mmr_blade, mmr_offset);
+	destroy_irq(irq);
+}
+EXPORT_SYMBOL_GPL(uv_teardown_irq);
diff --git a/include/asm-x86/uv/uv_irq.h b/include/asm-x86/uv/uv_irq.h
new file mode 100644
index 000000000000..8bf5f32da9c6
--- /dev/null
+++ b/include/asm-x86/uv/uv_irq.h
@@ -0,0 +1,36 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * SGI UV IRQ definitions
+ *
+ * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
+ */
+
+#ifndef ASM_X86__UV__UV_IRQ_H
+#define ASM_X86__UV__UV_IRQ_H
+
+/* If a generic version of this structure gets defined, eliminate this one. */
+struct uv_IO_APIC_route_entry {
+	__u64	vector		:  8,
+		delivery_mode	:  3,
+		dest_mode	:  1,
+		delivery_status	:  1,
+		polarity	:  1,
+		__reserved_1	:  1,
+		trigger		:  1,
+		mask		:  1,
+		__reserved_2	: 15,
+		dest		: 32;
+};
+
+extern struct irq_chip uv_irq_chip;
+
+extern int arch_enable_uv_irq(char *, unsigned int, int, int, unsigned long);
+extern void arch_disable_uv_irq(int, unsigned long);
+
+extern int uv_setup_irq(char *, int, int, unsigned long);
+extern void uv_teardown_irq(unsigned int, int, unsigned long);
+
+#endif /* ASM_X86__UV__UV_IRQ_H */
-- 
cgit v1.2.3


From a50f70b17541c0060967c6df61133e968bad3652 Mon Sep 17 00:00:00 2001
From: Russ Anderson <rja@sgi.com>
Date: Fri, 3 Oct 2008 11:58:54 -0500
Subject: x86: Add UV EFI table entry v4

Look for a UV entry in the EFI tables.

Signed-off-by: Russ Anderson <rja@sgi.com>
Signed-off-by: Paul Jackson <pj@sgi.com>
Acked-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/efi.c | 4 ++++
 include/linux/efi.h   | 4 ++++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 945a31cdd81f..1119d247fe11 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -366,6 +366,10 @@ void __init efi_init(void)
 					SMBIOS_TABLE_GUID)) {
 			efi.smbios = config_tables[i].table;
 			printk(" SMBIOS=0x%lx ", config_tables[i].table);
+		} else if (!efi_guidcmp(config_tables[i].guid,
+					UV_SYSTEM_TABLE_GUID)) {
+			efi.uv_systab = config_tables[i].table;
+			printk(" UVsystab=0x%lx ", config_tables[i].table);
 		} else if (!efi_guidcmp(config_tables[i].guid,
 					HCDP_TABLE_GUID)) {
 			efi.hcdp = config_tables[i].table;
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 807373d467f7..bb66feb164bd 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -208,6 +208,9 @@ typedef efi_status_t efi_set_virtual_address_map_t (unsigned long memory_map_siz
 #define EFI_GLOBAL_VARIABLE_GUID \
     EFI_GUID(  0x8be4df61, 0x93ca, 0x11d2, 0xaa, 0x0d, 0x00, 0xe0, 0x98, 0x03, 0x2b, 0x8c )
 
+#define UV_SYSTEM_TABLE_GUID \
+    EFI_GUID(  0x3b13a7d4, 0x633e, 0x11dd, 0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93 )
+
 typedef struct {
 	efi_guid_t guid;
 	unsigned long table;
@@ -255,6 +258,7 @@ extern struct efi {
 	unsigned long boot_info;	/* boot info table */
 	unsigned long hcdp;		/* HCDP table */
 	unsigned long uga;		/* UGA table */
+	unsigned long uv_systab;	/* UV system table */
 	efi_get_time_t *get_time;
 	efi_set_time_t *set_time;
 	efi_get_wakeup_time_t *get_wakeup_time;
-- 
cgit v1.2.3


From 7f5942329e0787087a5e4dced838cee711ac2b58 Mon Sep 17 00:00:00 2001
From: Russ Anderson <rja@sgi.com>
Date: Fri, 3 Oct 2008 11:59:15 -0500
Subject: x86: Add UV bios call infrastructure v4

Add the EFI callback function and associated wrapper code.
Initialize SAL system table entry info at boot time.

Signed-off-by: Russ Anderson <rja@sgi.com>
Signed-off-by: Paul Jackson <pj@sgi.com>
Acked-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/bios_uv.c        | 101 +++++++++++++++++++++++++++++++--------
 arch/x86/kernel/genx2apic_uv_x.c |   1 +
 include/asm-x86/efi.h            |  13 +++++
 include/asm-x86/uv/bios.h        |  73 +++++++++++++++-------------
 4 files changed, 135 insertions(+), 53 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c
index fdd585f9c53d..5481eb59f783 100644
--- a/arch/x86/kernel/bios_uv.c
+++ b/arch/x86/kernel/bios_uv.c
@@ -1,8 +1,6 @@
 /*
  * BIOS run time interface routines.
  *
- *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
- *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
  *  the Free Software Foundation; either version 2 of the License, or
@@ -16,33 +14,94 @@
  *  You should have received a copy of the GNU General Public License
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
+ *  Copyright (c) Russ Anderson
  */
 
+#include <linux/efi.h>
+#include <asm/efi.h>
+#include <linux/io.h>
 #include <asm/uv/bios.h>
 
-const char *
-x86_bios_strerror(long status)
+struct uv_systab uv_systab;
+
+s64 uv_bios_call(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3, u64 a4, u64 a5)
 {
-	const char *str;
-	switch (status) {
-	case  0: str = "Call completed without error";	break;
-	case -1: str = "Not implemented";		break;
-	case -2: str = "Invalid argument";		break;
-	case -3: str = "Call completed with error";	break;
-	default: str = "Unknown BIOS status code";	break;
-	}
-	return str;
+	struct uv_systab *tab = &uv_systab;
+
+	if (!tab->function)
+		/*
+		 * BIOS does not support UV systab
+		 */
+		return BIOS_STATUS_UNIMPLEMENTED;
+
+	return efi_call6((void *)__va(tab->function),
+					(u64)which, a1, a2, a3, a4, a5);
 }
 
-long
-x86_bios_freq_base(unsigned long which, unsigned long *ticks_per_second,
-		   unsigned long *drift_info)
+s64 uv_bios_call_irqsave(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
+					u64 a4, u64 a5)
 {
-	struct uv_bios_retval isrv;
+	unsigned long bios_flags;
+	s64 ret;
+
+	local_irq_save(bios_flags);
+	ret = uv_bios_call(which, a1, a2, a3, a4, a5);
+	local_irq_restore(bios_flags);
+
+	return ret;
+}
+
+s64 uv_bios_call_reentrant(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
+					u64 a4, u64 a5)
+{
+	s64 ret;
+
+	preempt_disable();
+	ret = uv_bios_call(which, a1, a2, a3, a4, a5);
+	preempt_enable();
 
-	BIOS_CALL(isrv, BIOS_FREQ_BASE, which, 0, 0, 0, 0, 0, 0);
-	*ticks_per_second = isrv.v0;
-	*drift_info = isrv.v1;
-	return isrv.status;
+	return ret;
+}
+
+long
+x86_bios_freq_base(unsigned long clock_type, unsigned long *ticks_per_second,
+					unsigned long *drift_info)
+{
+	return uv_bios_call(UV_BIOS_FREQ_BASE, clock_type,
+				(u64)ticks_per_second, 0, 0, 0);
 }
 EXPORT_SYMBOL_GPL(x86_bios_freq_base);
+
+
+#ifdef CONFIG_EFI
+void uv_bios_init(void)
+{
+	struct uv_systab *tab;
+
+	if ((efi.uv_systab == EFI_INVALID_TABLE_ADDR) ||
+	    (efi.uv_systab == (unsigned long)NULL)) {
+		printk(KERN_CRIT "No EFI UV System Table.\n");
+		uv_systab.function = (unsigned long)NULL;
+		return;
+	}
+
+	tab = (struct uv_systab *)ioremap(efi.uv_systab,
+					sizeof(struct uv_systab));
+	if (strncmp(tab->signature, "UVST", 4) != 0)
+		printk(KERN_ERR "bad signature in UV system table!");
+
+	/*
+	 * Copy table to permanent spot for later use.
+	 */
+	memcpy(&uv_systab, tab, sizeof(struct uv_systab));
+	iounmap(tab);
+
+	printk(KERN_INFO "EFI UV System Table Revision %d\n", tab->revision);
+}
+#else	/* !CONFIG_EFI */
+
+void uv_bios_init(void) { }
+#endif
+
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index b689075bbe2f..aa2e5e15bf69 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -427,6 +427,7 @@ void __init uv_system_init(void)
 	gnode_upper = (((unsigned long)node_id.s.node_id) &
 		       ~((1 << n_val) - 1)) << m_val;
 
+	uv_bios_init();
 	uv_rtc_init();
 
 	for_each_present_cpu(cpu) {
diff --git a/include/asm-x86/efi.h b/include/asm-x86/efi.h
index ed2de22e8705..313438e63348 100644
--- a/include/asm-x86/efi.h
+++ b/include/asm-x86/efi.h
@@ -94,4 +94,17 @@ extern void efi_reserve_early(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 
+#ifndef CONFIG_EFI
+/*
+ * IF EFI is not configured, have the EFI calls return -ENOSYS.
+ */
+#define efi_call0(_f)					(-ENOSYS)
+#define efi_call1(_f, _a1)				(-ENOSYS)
+#define efi_call2(_f, _a1, _a2)				(-ENOSYS)
+#define efi_call3(_f, _a1, _a2, _a3)			(-ENOSYS)
+#define efi_call4(_f, _a1, _a2, _a3, _a4)		(-ENOSYS)
+#define efi_call5(_f, _a1, _a2, _a3, _a4, _a5)		(-ENOSYS)
+#define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6)	(-ENOSYS)
+#endif /* CONFIG_EFI */
+
 #endif /* ASM_X86__EFI_H */
diff --git a/include/asm-x86/uv/bios.h b/include/asm-x86/uv/bios.h
index 7cd6d7ec1308..f63e46e5337c 100644
--- a/include/asm-x86/uv/bios.h
+++ b/include/asm-x86/uv/bios.h
@@ -2,9 +2,7 @@
 #define ASM_X86__UV__BIOS_H
 
 /*
- * BIOS layer definitions.
- *
- *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
+ * UV BIOS layer definitions.
  *
  *  This program is free software; you can redistribute it and/or modify
  *  it under the terms of the GNU General Public License as published by
@@ -19,50 +17,61 @@
  *  You should have received a copy of the GNU General Public License
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
+ *  Copyright (c) Russ Anderson
  */
 
 #include <linux/rtc.h>
 
-#define BIOS_FREQ_BASE			0x01000001
+/*
+ * Values for the BIOS calls.  It is passed as the first * argument in the
+ * BIOS call.  Passing any other value in the first argument will result
+ * in a BIOS_STATUS_UNIMPLEMENTED return status.
+ */
+enum uv_bios_cmd {
+	UV_BIOS_COMMON,
+	UV_BIOS_GET_SN_INFO,
+	UV_BIOS_FREQ_BASE
+};
 
+/*
+ * Status values returned from a BIOS call.
+ */
 enum {
-	BIOS_FREQ_BASE_PLATFORM = 0,
-	BIOS_FREQ_BASE_INTERVAL_TIMER = 1,
-	BIOS_FREQ_BASE_REALTIME_CLOCK = 2
+	BIOS_STATUS_SUCCESS		=  0,
+	BIOS_STATUS_UNIMPLEMENTED	= -ENOSYS,
+	BIOS_STATUS_EINVAL		= -EINVAL,
+	BIOS_STATUS_UNAVAIL		= -EBUSY
 };
 
-# define BIOS_CALL(result, a0, a1, a2, a3, a4, a5, a6, a7)		\
-	do {								\
-		/* XXX - the real call goes here */			\
-		result.status = BIOS_STATUS_UNIMPLEMENTED;		\
-		isrv.v0 = 0;						\
-		isrv.v1 = 0;						\
-	} while (0)
+/*
+ * The UV system table describes specific firmware
+ * capabilities available to the Linux kernel at runtime.
+ */
+struct uv_systab {
+	char signature[4];	/* must be "UVST" */
+	u32 revision;		/* distinguish different firmware revs */
+	u64 function;		/* BIOS runtime callback function ptr */
+};
 
 enum {
-	BIOS_STATUS_SUCCESS		=  0,
-	BIOS_STATUS_UNIMPLEMENTED	= -1,
-	BIOS_STATUS_EINVAL		= -2,
-	BIOS_STATUS_ERROR		= -3
+	BIOS_FREQ_BASE_PLATFORM = 0,
+	BIOS_FREQ_BASE_INTERVAL_TIMER = 1,
+	BIOS_FREQ_BASE_REALTIME_CLOCK = 2
 };
 
-struct uv_bios_retval {
-	/*
-	 * A zero status value indicates call completed without error.
-	 * A negative status value indicates reason of call failure.
-	 * A positive status value indicates success but an
-	 * informational value should be printed (e.g., "reboot for
-	 * change to take effect").
-	 */
-	s64 status;
-	u64 v0;
-	u64 v1;
-	u64 v2;
-};
+/*
+ * bios calls have 6 parameters
+ */
+extern s64 uv_bios_call(enum uv_bios_cmd, u64, u64, u64, u64, u64);
+extern s64 uv_bios_call_irqsave(enum uv_bios_cmd, u64, u64, u64, u64, u64);
+extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64);
+
+extern void uv_bios_init(void);
 
 extern long
 x86_bios_freq_base(unsigned long which, unsigned long *ticks_per_second,
 		   unsigned long *drift_info);
-extern const char *x86_bios_strerror(long status);
 
 #endif /* ASM_X86__UV__BIOS_H */
-- 
cgit v1.2.3


From 922402f15a85f7a064926eb1db68cc52bc4d4a91 Mon Sep 17 00:00:00 2001
From: Russ Anderson <rja@sgi.com>
Date: Fri, 3 Oct 2008 11:59:33 -0500
Subject: x86: Add UV partition call v4

Add a bios call to return partitioning related info.

Signed-off-by: Russ Anderson <rja@sgi.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/bios_uv.c        | 44 +++++++++++++++++++++++++++++++++++-----
 arch/x86/kernel/genx2apic_uv_x.c | 14 +++++++------
 include/asm-x86/uv/bios.h        | 22 +++++++++++++++++---
 3 files changed, 66 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/bios_uv.c b/arch/x86/kernel/bios_uv.c
index 5481eb59f783..f0dfe6f17e7e 100644
--- a/arch/x86/kernel/bios_uv.c
+++ b/arch/x86/kernel/bios_uv.c
@@ -23,6 +23,7 @@
 #include <asm/efi.h>
 #include <linux/io.h>
 #include <asm/uv/bios.h>
+#include <asm/uv/uv_hub.h>
 
 struct uv_systab uv_systab;
 
@@ -65,14 +66,47 @@ s64 uv_bios_call_reentrant(enum uv_bios_cmd which, u64 a1, u64 a2, u64 a3,
 	return ret;
 }
 
-long
-x86_bios_freq_base(unsigned long clock_type, unsigned long *ticks_per_second,
-					unsigned long *drift_info)
+
+long sn_partition_id;
+EXPORT_SYMBOL_GPL(sn_partition_id);
+long uv_coherency_id;
+EXPORT_SYMBOL_GPL(uv_coherency_id);
+long uv_region_size;
+EXPORT_SYMBOL_GPL(uv_region_size);
+int uv_type;
+
+
+s64 uv_bios_get_sn_info(int fc, int *uvtype, long *partid, long *coher,
+		long *region)
+{
+	s64 ret;
+	u64 v0, v1;
+	union partition_info_u part;
+
+	ret = uv_bios_call_irqsave(UV_BIOS_GET_SN_INFO, fc,
+				(u64)(&v0), (u64)(&v1), 0, 0);
+	if (ret != BIOS_STATUS_SUCCESS)
+		return ret;
+
+	part.val = v0;
+	if (uvtype)
+		*uvtype = part.hub_version;
+	if (partid)
+		*partid = part.partition_id;
+	if (coher)
+		*coher = part.coherence_id;
+	if (region)
+		*region = part.region_size;
+	return ret;
+}
+
+
+s64 uv_bios_freq_base(u64 clock_type, u64 *ticks_per_second)
 {
 	return uv_bios_call(UV_BIOS_FREQ_BASE, clock_type,
-				(u64)ticks_per_second, 0, 0, 0);
+			   (u64)ticks_per_second, 0, 0, 0);
 }
-EXPORT_SYMBOL_GPL(x86_bios_freq_base);
+EXPORT_SYMBOL_GPL(uv_bios_freq_base);
 
 
 #ifdef CONFIG_EFI
diff --git a/arch/x86/kernel/genx2apic_uv_x.c b/arch/x86/kernel/genx2apic_uv_x.c
index aa2e5e15bf69..bfd532843df6 100644
--- a/arch/x86/kernel/genx2apic_uv_x.c
+++ b/arch/x86/kernel/genx2apic_uv_x.c
@@ -341,12 +341,12 @@ static __init void map_mmioh_high(int max_pnode)
 
 static __init void uv_rtc_init(void)
 {
-	long status, ticks_per_sec, drift;
+	long status;
+	u64 ticks_per_sec;
 
-	status =
-	    x86_bios_freq_base(BIOS_FREQ_BASE_REALTIME_CLOCK, &ticks_per_sec,
-					&drift);
-	if (status != 0 || ticks_per_sec < 100000) {
+	status = uv_bios_freq_base(BIOS_FREQ_BASE_REALTIME_CLOCK,
+					&ticks_per_sec);
+	if (status != BIOS_STATUS_SUCCESS || ticks_per_sec < 100000) {
 		printk(KERN_WARNING
 			"unable to determine platform RTC clock frequency, "
 			"guessing.\n");
@@ -428,6 +428,8 @@ void __init uv_system_init(void)
 		       ~((1 << n_val) - 1)) << m_val;
 
 	uv_bios_init();
+	uv_bios_get_sn_info(0, &uv_type, &sn_partition_id,
+			    &uv_coherency_id, &uv_region_size);
 	uv_rtc_init();
 
 	for_each_present_cpu(cpu) {
@@ -449,7 +451,7 @@ void __init uv_system_init(void)
 		uv_cpu_hub_info(cpu)->gpa_mask = (1 << (m_val + n_val)) - 1;
 		uv_cpu_hub_info(cpu)->gnode_upper = gnode_upper;
 		uv_cpu_hub_info(cpu)->global_mmr_base = mmr_base;
-		uv_cpu_hub_info(cpu)->coherency_domain_number = 0;/* ZZZ */
+		uv_cpu_hub_info(cpu)->coherency_domain_number = uv_coherency_id;
 		uv_node_to_blade[nid] = blade;
 		uv_cpu_to_blade[cpu] = blade;
 		max_pnode = max(pnode, max_pnode);
diff --git a/include/asm-x86/uv/bios.h b/include/asm-x86/uv/bios.h
index f63e46e5337c..3b305d897c84 100644
--- a/include/asm-x86/uv/bios.h
+++ b/include/asm-x86/uv/bios.h
@@ -61,6 +61,16 @@ enum {
 	BIOS_FREQ_BASE_REALTIME_CLOCK = 2
 };
 
+union partition_info_u {
+	u64	val;
+	struct {
+		u64	hub_version	:  8,
+			partition_id	: 16,
+			coherence_id	: 16,
+			region_size	: 24;
+	};
+};
+
 /*
  * bios calls have 6 parameters
  */
@@ -68,10 +78,16 @@ extern s64 uv_bios_call(enum uv_bios_cmd, u64, u64, u64, u64, u64);
 extern s64 uv_bios_call_irqsave(enum uv_bios_cmd, u64, u64, u64, u64, u64);
 extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64);
 
+extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *);
+extern s64 uv_bios_freq_base(u64, u64 *);
+
 extern void uv_bios_init(void);
 
-extern long
-x86_bios_freq_base(unsigned long which, unsigned long *ticks_per_second,
-		   unsigned long *drift_info);
+extern int uv_type;
+extern long sn_partition_id;
+extern long uv_coherency_id;
+extern long uv_region_size;
+#define partition_coherence_id()	(uv_coherency_id)
+
 
 #endif /* ASM_X86__UV__BIOS_H */
-- 
cgit v1.2.3


From fc8c2d763bacc02962048fa042e287debb1416aa Mon Sep 17 00:00:00 2001
From: Russ Anderson <rja@sgi.com>
Date: Fri, 3 Oct 2008 11:59:50 -0500
Subject: x86: Add sysfs entries for UV v4

Create /sys/firmware/sgi_uv sysfs entries for partition_id and coherence_id.

Signed-off-by: Russ Anderson <rja@sgi.com>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/x86/kernel/Makefile   |  2 +-
 arch/x86/kernel/uv_sysfs.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++
 include/asm-x86/uv/bios.h  |  1 +
 3 files changed, 74 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/kernel/uv_sysfs.c

(limited to 'include')

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index acc0e8bf043e..cb6ade443f00 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -108,7 +108,7 @@ obj-$(CONFIG_MICROCODE)			+= microcode.o
 # 64 bit specific files
 ifeq ($(CONFIG_X86_64),y)
         obj-y				+= genapic_64.o genapic_flat_64.o genx2apic_uv_x.o tlb_uv.o
-	obj-y				+= bios_uv.o uv_irq.o
+	obj-y				+= bios_uv.o uv_irq.o uv_sysfs.o
         obj-y				+= genx2apic_cluster.o
         obj-y				+= genx2apic_phys.o
         obj-$(CONFIG_X86_PM_TIMER)	+= pmtimer_64.o
diff --git a/arch/x86/kernel/uv_sysfs.c b/arch/x86/kernel/uv_sysfs.c
new file mode 100644
index 000000000000..67f9b9dbf800
--- /dev/null
+++ b/arch/x86/kernel/uv_sysfs.c
@@ -0,0 +1,72 @@
+/*
+ * This file supports the /sys/firmware/sgi_uv interfaces for SGI UV.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
+ *  Copyright (c) Russ Anderson
+ */
+
+#include <linux/sysdev.h>
+#include <asm/uv/bios.h>
+
+struct kobject *sgi_uv_kobj;
+
+static ssize_t partition_id_show(struct kobject *kobj,
+			struct kobj_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%ld\n", sn_partition_id);
+}
+
+static ssize_t coherence_id_show(struct kobject *kobj,
+			struct kobj_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE, "%ld\n", partition_coherence_id());
+}
+
+static struct kobj_attribute partition_id_attr =
+	__ATTR(partition_id, S_IRUGO, partition_id_show, NULL);
+
+static struct kobj_attribute coherence_id_attr =
+	__ATTR(coherence_id, S_IRUGO, coherence_id_show, NULL);
+
+
+static int __init sgi_uv_sysfs_init(void)
+{
+	unsigned long ret;
+
+	if (!sgi_uv_kobj)
+		sgi_uv_kobj = kobject_create_and_add("sgi_uv", firmware_kobj);
+	if (!sgi_uv_kobj) {
+		printk(KERN_WARNING "kobject_create_and_add sgi_uv failed \n");
+		return -EINVAL;
+	}
+
+	ret = sysfs_create_file(sgi_uv_kobj, &partition_id_attr.attr);
+	if (ret) {
+		printk(KERN_WARNING "sysfs_create_file partition_id failed \n");
+		return ret;
+	}
+
+	ret = sysfs_create_file(sgi_uv_kobj, &coherence_id_attr.attr);
+	if (ret) {
+		printk(KERN_WARNING "sysfs_create_file coherence_id failed \n");
+		return ret;
+	}
+
+	return 0;
+}
+
+device_initcall(sgi_uv_sysfs_init);
diff --git a/include/asm-x86/uv/bios.h b/include/asm-x86/uv/bios.h
index 3b305d897c84..215f1969c266 100644
--- a/include/asm-x86/uv/bios.h
+++ b/include/asm-x86/uv/bios.h
@@ -89,5 +89,6 @@ extern long uv_coherency_id;
 extern long uv_region_size;
 #define partition_coherence_id()	(uv_coherency_id)
 
+extern struct kobject *sgi_uv_kobj;	/* /sys/firmware/sgi_uv */
 
 #endif /* ASM_X86__UV__BIOS_H */
-- 
cgit v1.2.3


From 7ef0c30dbf96a8d9a234e90c248eb19df3c031be Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 15 Oct 2008 13:07:35 +0200
Subject: genirq: define nr_irqs for architectures with GENERIC_HARDIRQS=n

Revert the sparse irq changes in m68k/s390/sparc and just define
nr_irqs as NR_IRQS for those architectures.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/m68k/kernel/ints.c   | 3 ---
 arch/s390/kernel/irq.c    | 3 ---
 arch/sparc/kernel/irq.c   | 4 ----
 include/linux/interrupt.h | 8 +++++---
 4 files changed, 5 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/arch/m68k/kernel/ints.c b/arch/m68k/kernel/ints.c
index 44169e4cd91d..7e8a0d394e61 100644
--- a/arch/m68k/kernel/ints.c
+++ b/arch/m68k/kernel/ints.c
@@ -46,9 +46,6 @@
 #include <asm/q40ints.h>
 #endif
 
-int nr_irqs = NR_IRQS;
-EXPORT_SYMBOL(nr_irqs);
-
 extern u32 auto_irqhandler_fixup[];
 extern u32 user_irqhandler_fixup[];
 extern u16 user_irqvec_fixup[];
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index 3624c4a0037a..e7c5bfb7c755 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -17,9 +17,6 @@
 #include <linux/proc_fs.h>
 #include <linux/profile.h>
 
-int nr_irqs = NR_IRQS;
-EXPORT_SYMBOL(nr_irqs);
-
 /*
  * show_interrupts is needed by /proc/interrupts.
  */
diff --git a/arch/sparc/kernel/irq.c b/arch/sparc/kernel/irq.c
index 4b99e3ce3916..93e1d1c65290 100644
--- a/arch/sparc/kernel/irq.c
+++ b/arch/sparc/kernel/irq.c
@@ -55,10 +55,6 @@
 #define SMP_NOP2
 #define SMP_NOP3
 #endif /* SMP */
-
-int nr_irqs = NR_IRQS;
-EXPORT_SYMBOL(nr_irqs);
-
 unsigned long __raw_local_irq_save(void)
 {
 	unsigned long retval;
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index d4039a0b23f4..5a57df2ee922 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -15,11 +15,13 @@
 #include <asm/ptrace.h>
 #include <asm/system.h>
 
-extern int nr_irqs;
-
 #ifndef CONFIG_GENERIC_HARDIRQS
-#define for_each_irq_desc(irq, desc)		\
+# define for_each_irq_desc(irq, desc)		\
 	for (irq = 0; irq < nr_irqs; irq++)
+
+# define nr_irqs		NR_IRQS
+#else
+extern int nr_irqs;
 #endif
 
 /*
-- 
cgit v1.2.3


From 70dd4d992ab324a59cdcd6bedc3f4e729863d514 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 15 Oct 2008 15:39:27 +0200
Subject: genirq: consolidate nr_irqs and for_each_irq_desc()

Move all of those to linux/irq.h where they belong.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/interrupt.h |  9 ---------
 include/linux/irq.h       | 17 ++++++++++++-----
 2 files changed, 12 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 5a57df2ee922..58ff4e74b2f3 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -15,15 +15,6 @@
 #include <asm/ptrace.h>
 #include <asm/system.h>
 
-#ifndef CONFIG_GENERIC_HARDIRQS
-# define for_each_irq_desc(irq, desc)		\
-	for (irq = 0; irq < nr_irqs; irq++)
-
-# define nr_irqs		NR_IRQS
-#else
-extern int nr_irqs;
-#endif
-
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
  * linux/ioport.h to select the interrupt line behaviour.  When
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 93fe9a943e71..dbe8734ae86c 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -11,6 +11,18 @@
 
 #include <linux/smp.h>
 
+#ifndef CONFIG_GENERIC_HARDIRQS
+# define nr_irqs		NR_IRQS
+
+# define for_each_irq_desc(irq, desc)		\
+	for (irq = 0; irq < nr_irqs; irq++)
+#else
+extern int nr_irqs;
+
+# define for_each_irq_desc(irq, desc)		\
+	for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc++)
+#endif
+
 #ifndef CONFIG_S390
 
 #include <linux/linkage.h>
@@ -204,11 +216,6 @@ extern struct irq_desc irq_desc[NR_IRQS];
 extern struct irq_desc *irq_desc;
 #endif
 
-#ifdef CONFIG_GENERIC_HARDIRQS
-#define for_each_irq_desc(irq, desc)		\
-	for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc = &irq_desc[irq])
-#endif
-
 #else
 
 extern struct irq_desc *sparse_irqs;
-- 
cgit v1.2.3


From c6b7674f323622d86316bf7951ad9cae1ce24642 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 15 Oct 2008 14:31:29 +0200
Subject: genirq: use inline function for irq_to_desc

For the non sparse irq case an inline function is perfectly fine.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h | 15 +++++++++++++--
 kernel/irq/handle.c | 14 --------------
 2 files changed, 13 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index dbe8734ae86c..7d1adacaadb4 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -204,8 +204,6 @@ struct irq_desc {
 	const char		*name;
 } ____cacheline_internodealigned_in_smp;
 
-extern struct irq_desc *irq_to_desc(unsigned int irq);
-extern struct irq_desc *irq_to_desc_alloc(unsigned int irq);
 
 #ifndef CONFIG_HAVE_SPARSE_IRQ
 
@@ -216,8 +214,21 @@ extern struct irq_desc irq_desc[NR_IRQS];
 extern struct irq_desc *irq_desc;
 #endif
 
+static inline struct irq_desc *irq_to_desc(unsigned int irq)
+{
+	return (irq < nr_irqs) ? irq_desc + irq : NULL;
+}
+
+static inline struct irq_desc *irq_to_desc_alloc(unsigned int irq)
+{
+	return irq_to_desc(irq);
+}
+
 #else
 
+extern struct irq_desc *irq_to_desc(unsigned int irq);
+extern struct irq_desc *irq_to_desc_alloc(unsigned int irq);
+
 extern struct irq_desc *sparse_irqs;
 #define for_each_irq_desc(irqX, desc)		\
 	for (desc = sparse_irqs, irqX = desc->irq; desc; desc = desc->next, irqX = desc ? desc->irq : -1U)
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index fb6bdb602a93..c19896f895f9 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -262,20 +262,6 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 
 #endif
 
-#ifndef CONFIG_HAVE_SPARSE_IRQ
-struct irq_desc *irq_to_desc(unsigned int irq)
-{
-	if (irq < nr_irqs)
-		return &irq_desc[irq];
-
-	return NULL;
-}
-struct irq_desc *irq_to_desc_alloc(unsigned int irq)
-{
-	return irq_to_desc(irq);
-}
-#endif
-
 /*
  * What should we do if we get a hw irq event on an illegal vector?
  * Each architecture has to answer this themself.
-- 
cgit v1.2.3


From 2cc21ef843d4fb7da122239b644a1f6f0aca60a6 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 15 Oct 2008 14:16:55 +0200
Subject: genirq: remove sparse irq code

This code is not ready, but we need to rip it out instead of rebasing
as we would lose the APIC/IO_APIC unification otherwise.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/io_apic.c    | 130 ++-----------------------------------------
 arch/x86/kernel/irq_32.c     |   8 ---
 arch/x86/kernel/irq_64.c     |   8 ---
 drivers/char/random.c        |  31 -----------
 drivers/pci/htirq.c          |  19 +------
 drivers/pci/intr_remapping.c |  75 -------------------------
 fs/proc/proc_misc.c          |  43 ++------------
 include/linux/irq.h          |  20 -------
 kernel/irq/handle.c          | 114 -------------------------------------
 9 files changed, 10 insertions(+), 438 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index f959acbc0db2..683610517d2a 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -111,9 +111,6 @@ struct irq_cfg;
 struct irq_pin_list;
 struct irq_cfg {
 	unsigned int irq;
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-	struct irq_cfg *next;
-#endif
 	struct irq_pin_list *irq_2_pin;
 	cpumask_t domain;
 	cpumask_t old_domain;
@@ -151,15 +148,6 @@ static void init_one_irq_cfg(struct irq_cfg *cfg)
 
 static struct irq_cfg *irq_cfgx;
 
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-/*
- * Protect the irq_cfgx_free freelist:
- */
-static DEFINE_SPINLOCK(irq_cfg_lock);
-
-static struct irq_cfg *irq_cfgx_free;
-#endif
-
 static void __init init_work(void *data)
 {
 	struct dyn_array *da = data;
@@ -174,114 +162,7 @@ static void __init init_work(void *data)
 	legacy_count = ARRAY_SIZE(irq_cfg_legacy);
 	for (i = legacy_count; i < *da->nr; i++)
 		init_one_irq_cfg(&cfg[i]);
-
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-	for (i = 1; i < *da->nr; i++)
-		cfg[i-1].next = &cfg[i];
-
-	irq_cfgx_free = &irq_cfgx[legacy_count];
-	irq_cfgx[legacy_count - 1].next = NULL;
-#endif
-}
-
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-/* need to be biger than size of irq_cfg_legacy */
-static int nr_irq_cfg = 32;
-
-static int __init parse_nr_irq_cfg(char *arg)
-{
-	if (arg) {
-		nr_irq_cfg = simple_strtoul(arg, NULL, 0);
-		if (nr_irq_cfg < 32)
-			nr_irq_cfg = 32;
-	}
-	return 0;
-}
-
-early_param("nr_irq_cfg", parse_nr_irq_cfg);
-
-#define for_each_irq_cfg(irqX, cfg)           \
-        for (cfg = irq_cfgx, irqX = cfg->irq; cfg; cfg = cfg->next, irqX = cfg ? cfg->irq : -1U)
-
-
-DEFINE_DYN_ARRAY(irq_cfgx, sizeof(struct irq_cfg), nr_irq_cfg, PAGE_SIZE, init_work);
-
-static struct irq_cfg *irq_cfg(unsigned int irq)
-{
-	struct irq_cfg *cfg;
-
-	cfg = irq_cfgx;
-	while (cfg) {
-		if (cfg->irq == irq)
-			return cfg;
-
-		cfg = cfg->next;
-	}
-
-	return NULL;
-}
-
-static struct irq_cfg *irq_cfg_alloc(unsigned int irq)
-{
-	struct irq_cfg *cfg, *cfg_pri;
-	unsigned long flags;
-	int count = 0;
-	int i;
-
-	cfg_pri = cfg = irq_cfgx;
-	while (cfg) {
-		if (cfg->irq == irq)
-			return cfg;
-
-		cfg_pri = cfg;
-		cfg = cfg->next;
-		count++;
-	}
-
-	spin_lock_irqsave(&irq_cfg_lock, flags);
-	if (!irq_cfgx_free) {
-		unsigned long phys;
-		unsigned long total_bytes;
-		/*
-		 *  we run out of pre-allocate ones, allocate more
-		 */
-		printk(KERN_DEBUG "try to get more irq_cfg %d\n", nr_irq_cfg);
-
-		total_bytes = sizeof(struct irq_cfg) * nr_irq_cfg;
-		if (after_bootmem)
-			cfg = kzalloc(total_bytes, GFP_ATOMIC);
-		else
-			cfg = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
-
-		if (!cfg)
-			panic("please boot with nr_irq_cfg= %d\n", count * 2);
-
-		phys = __pa(cfg);
-		printk(KERN_DEBUG "irq_cfg ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
-
-		for (i = 0; i < nr_irq_cfg; i++)
-			init_one_irq_cfg(&cfg[i]);
-
-		for (i = 1; i < nr_irq_cfg; i++)
-			cfg[i-1].next = &cfg[i];
-
-		irq_cfgx_free = cfg;
-	}
-
-	cfg = irq_cfgx_free;
-	irq_cfgx_free = irq_cfgx_free->next;
-	cfg->next = NULL;
-	if (cfg_pri)
-		cfg_pri->next = cfg;
-	else
-		irq_cfgx = cfg;
-	cfg->irq = irq;
-
-	spin_unlock_irqrestore(&irq_cfg_lock, flags);
-
-	return cfg;
 }
-#else
 
 #define for_each_irq_cfg(irq, cfg)		\
 	for (irq = 0, cfg = &irq_cfgx[irq]; irq < nr_irqs; irq++, cfg = &irq_cfgx[irq])
@@ -290,17 +171,16 @@ DEFINE_DYN_ARRAY(irq_cfgx, sizeof(struct irq_cfg), nr_irqs, PAGE_SIZE, init_work
 
 struct irq_cfg *irq_cfg(unsigned int irq)
 {
-        if (irq < nr_irqs)
-                return &irq_cfgx[irq];
+	if (irq < nr_irqs)
+		return &irq_cfgx[irq];
 
-        return NULL;
+	return NULL;
 }
 struct irq_cfg *irq_cfg_alloc(unsigned int irq)
 {
-        return irq_cfg(irq);
+	return irq_cfg(irq);
 }
 
-#endif
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -3068,9 +2948,7 @@ unsigned int create_irq_nr(unsigned int irq_want)
 	unsigned long flags;
 	struct irq_cfg *cfg_new;
 
-#ifndef CONFIG_HAVE_SPARSE_IRQ
 	irq_want = nr_irqs - 1;
-#endif
 
 	irq = 0;
 	spin_lock_irqsave(&vector_lock, flags);
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index 001772ffc918..ccf6c1bf7120 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -272,20 +272,12 @@ int show_interrupts(struct seq_file *p, void *v)
 	struct irq_desc *desc = NULL;
 	int tail = 0;
 
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-	desc = (struct irq_desc *)v;
-	entries = -1U;
-	i = desc->irq;
-	if (!desc->next)
-		tail = 1;
-#else
 	entries = nr_irqs - 1;
 	i = *(loff_t *) v;
 	if (i == nr_irqs)
 		tail = 1;
 	else
 		desc = irq_to_desc(i);
-#endif
 
 	if (i == 0) {
 		seq_printf(p, "           ");
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index ec2661091283..21f53b911113 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -77,20 +77,12 @@ int show_interrupts(struct seq_file *p, void *v)
 	struct irq_desc *desc = NULL;
 	int tail = 0;
 
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-	desc = (struct irq_desc *)v;
-	entries = -1U;
-	i = desc->irq;
-	if (!desc->next)
-		tail = 1;
-#else
 	entries = nr_irqs - 1;
 	i = *(loff_t *) v;
 	if (i == nr_irqs)
 		tail = 1;
 	else
 		desc = irq_to_desc(i);
-#endif
 
 	if (i == 0) {
 		seq_printf(p, "           ");
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 60c9c7ee6b2c..9ce80213007b 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -558,8 +558,6 @@ struct timer_rand_state {
 	unsigned dont_count_entropy:1;
 };
 
-#ifndef CONFIG_HAVE_SPARSE_IRQ
-
 #ifdef CONFIG_HAVE_DYN_ARRAY
 static struct timer_rand_state **irq_timer_state;
 DEFINE_DYN_ARRAY(irq_timer_state, sizeof(struct timer_rand_state *), nr_irqs, PAGE_SIZE, NULL);
@@ -583,33 +581,6 @@ static void set_timer_rand_state(unsigned int irq, struct timer_rand_state *stat
 	irq_timer_state[irq] = state;
 }
 
-#else
-
-static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	if (!desc)
-		return NULL;
-
-	return desc->timer_rand_state;
-}
-
-static void set_timer_rand_state(unsigned int irq, struct timer_rand_state *state)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	if (!desc)
-		return;
-
-	desc->timer_rand_state = state;
-}
-#endif
-
 static struct timer_rand_state input_timer_state;
 
 /*
@@ -967,10 +938,8 @@ void rand_initialize_irq(int irq)
 {
 	struct timer_rand_state *state;
 
-#ifndef CONFIG_HAVE_SPARSE_IRQ
 	if (irq >= nr_irqs)
 		return;
-#endif
 
 	state = get_timer_rand_state(irq);
 
diff --git a/drivers/pci/htirq.c b/drivers/pci/htirq.c
index 9e4929a00832..bf7d6ce9bbb3 100644
--- a/drivers/pci/htirq.c
+++ b/drivers/pci/htirq.c
@@ -82,18 +82,6 @@ void unmask_ht_irq(unsigned int irq)
 	write_ht_irq_msg(irq, &msg);
 }
 
-static unsigned int build_irq_for_pci_dev(struct pci_dev *dev)
-{
-	unsigned int irq;
-
-	irq = dev->bus->number;
-	irq <<= 8;
-	irq |= dev->devfn;
-	irq <<= 12;
-
-	return irq;
-}
-
 /**
  * __ht_create_irq - create an irq and attach it to a device.
  * @dev: The hypertransport device to find the irq capability on.
@@ -110,7 +98,6 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 	int max_irq;
 	int pos;
 	int irq;
-	unsigned int irq_want;
 
 	pos = pci_find_ht_capability(dev, HT_CAPTYPE_IRQ);
 	if (!pos)
@@ -138,12 +125,8 @@ int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
 	cfg->msg.address_lo = 0xffffffff;
 	cfg->msg.address_hi = 0xffffffff;
 
-	irq_want= build_irq_for_pci_dev(dev);
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-	irq = create_irq_nr(irq_want + idx);
-#else
 	irq = create_irq();
-#endif
+
 	if (irq <= 0) {
 		kfree(cfg);
 		return -EBUSY;
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index 2dcf973890c4..0f43b265eee6 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -19,78 +19,6 @@ struct irq_2_iommu {
 	u8  irte_mask;
 };
 
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-static struct irq_2_iommu *irq_2_iommuX;
-/* fill one page ? */
-static int nr_irq_2_iommu = 0x100;
-static int irq_2_iommu_index;
-DEFINE_DYN_ARRAY(irq_2_iommuX, sizeof(struct irq_2_iommu), nr_irq_2_iommu, PAGE_SIZE, NULL);
-
-extern void *__alloc_bootmem_nopanic(unsigned long size,
-				     unsigned long align,
-				     unsigned long goal);
-
-static struct irq_2_iommu *get_one_free_irq_2_iommu(int not_used)
-{
-	struct irq_2_iommu *iommu;
-	unsigned long total_bytes;
-
-	if (irq_2_iommu_index >= nr_irq_2_iommu) {
-		/*
-		 *  we run out of pre-allocate ones, allocate more
-		 */
-		printk(KERN_DEBUG "try to get more irq_2_iommu %d\n", nr_irq_2_iommu);
-
-		total_bytes = sizeof(struct irq_2_iommu)*nr_irq_2_iommu;
-
-		if (after_bootmem)
-			iommu = kzalloc(total_bytes, GFP_ATOMIC);
-		else
-			iommu = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
-
-		if (!iommu)
-			panic("can not get more irq_2_iommu\n");
-
-		irq_2_iommuX = iommu;
-		irq_2_iommu_index = 0;
-	}
-
-	iommu = &irq_2_iommuX[irq_2_iommu_index];
-	irq_2_iommu_index++;
-	return iommu;
-}
-
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	BUG_ON(!desc);
-
-	return desc->irq_2_iommu;
-}
-
-static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
-{
-	struct irq_desc *desc;
-	struct irq_2_iommu *irq_iommu;
-
-	/*
-	 * alloc irq desc if not allocated already.
-	 */
-	desc = irq_to_desc_alloc(irq);
-
-	irq_iommu = desc->irq_2_iommu;
-
-	if (!irq_iommu)
-		desc->irq_2_iommu = get_one_free_irq_2_iommu(irq);
-
-	return desc->irq_2_iommu;
-}
-
-#else /* !CONFIG_HAVE_SPARSE_IRQ */
-
 #ifdef CONFIG_HAVE_DYN_ARRAY
 static struct irq_2_iommu *irq_2_iommuX;
 DEFINE_DYN_ARRAY(irq_2_iommuX, sizeof(struct irq_2_iommu), nr_irqs, PAGE_SIZE, NULL);
@@ -109,7 +37,6 @@ static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
 {
 	return irq_2_iommu(irq);
 }
-#endif
 
 static DEFINE_SPINLOCK(irq_2_ir_lock);
 
@@ -166,11 +93,9 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 	if (!count)
 		return -1;
 
-#ifndef	CONFIG_HAVE_SPARSE_IRQ
 	/* protect irq_2_iommu_alloc later */
 	if (irq >= nr_irqs)
 		return -1;
-#endif
 
 	/*
 	 * start the IRTE search from index 0.
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index d68c3592fe4a..3f5c7b9d1a70 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -529,13 +529,10 @@ static int show_stat(struct seq_file *p, void *v)
 		softirq = cputime64_add(softirq, kstat_cpu(i).cpustat.softirq);
 		steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
 		guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
+
 		for_each_irq_desc(j, desc)
-		{
-			unsigned int temp;
+			sum += kstat_irqs_cpu(j, i);
 
-			temp = kstat_irqs_cpu(j, i);
-			sum += temp;
-		}
 		sum += arch_irq_stat_cpu(i);
 	}
 	sum += arch_irq_stat();
@@ -578,21 +575,13 @@ static int show_stat(struct seq_file *p, void *v)
 	seq_printf(p, "intr %llu", (unsigned long long)sum);
 
 	/* sum again ? it could be updated? */
-	for_each_irq_desc(j, desc)
-	{
+	for_each_irq_desc(j, desc) {
 		per_irq_sum = 0;
-		for_each_possible_cpu(i) {
-			unsigned int temp;
 
-			temp = kstat_irqs_cpu(j, i);
-			per_irq_sum += temp;
-		}
+		for_each_possible_cpu(i)
+			per_irq_sum += kstat_irqs_cpu(j, i);
 
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-		seq_printf(p, " %#x:%u", j, per_irq_sum);
-#else
 		seq_printf(p, " %u", per_irq_sum);
-#endif
 	}
 
 	seq_printf(p,
@@ -645,36 +634,14 @@ static const struct file_operations proc_stat_operations = {
  */
 static void *int_seq_start(struct seq_file *f, loff_t *pos)
 {
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-	struct irq_desc *desc;
-	int irq;
-	int count = *pos;
-
-	for_each_irq_desc(irq, desc) {
-		if (count-- == 0)
-			return desc;
-	}
-
-	return NULL;
-#else
 	return (*pos <= nr_irqs) ? pos : NULL;
-#endif
 }
 
 
 static void *int_seq_next(struct seq_file *f, void *v, loff_t *pos)
 {
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-	struct irq_desc *desc;
-
-	desc = ((struct irq_desc *)v)->next;
-	(*pos)++;
-
-	return desc;
-#else
 	(*pos)++;
 	return (*pos <= nr_irqs) ? pos : NULL;
-#endif
 }
 
 static void int_seq_stop(struct seq_file *f, void *v)
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 7d1adacaadb4..68e0f3f9df30 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -167,15 +167,8 @@ struct irq_2_iommu;
  */
 struct irq_desc {
 	unsigned int		irq;
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-	struct irq_desc		*next;
-	struct timer_rand_state *timer_rand_state;
-#endif
 #ifdef CONFIG_HAVE_DYN_ARRAY
 	unsigned int            *kstat_irqs;
-#endif
-#if defined(CONFIG_INTR_REMAP) && defined(CONFIG_HAVE_SPARSE_IRQ)
-       struct irq_2_iommu      *irq_2_iommu;
 #endif
 	irq_flow_handler_t	handle_irq;
 	struct irq_chip		*chip;
@@ -205,8 +198,6 @@ struct irq_desc {
 } ____cacheline_internodealigned_in_smp;
 
 
-#ifndef CONFIG_HAVE_SPARSE_IRQ
-
 #ifndef CONFIG_HAVE_DYN_ARRAY
 /* could be removed if we get rid of all irq_desc reference */
 extern struct irq_desc irq_desc[NR_IRQS];
@@ -224,17 +215,6 @@ static inline struct irq_desc *irq_to_desc_alloc(unsigned int irq)
 	return irq_to_desc(irq);
 }
 
-#else
-
-extern struct irq_desc *irq_to_desc(unsigned int irq);
-extern struct irq_desc *irq_to_desc_alloc(unsigned int irq);
-
-extern struct irq_desc *sparse_irqs;
-#define for_each_irq_desc(irqX, desc)		\
-	for (desc = sparse_irqs, irqX = desc->irq; desc; desc = desc->next, irqX = desc ? desc->irq : -1U)
-
-#endif
-
 #ifdef CONFIG_HAVE_DYN_ARRAY
 #define kstat_irqs_this_cpu(DESC) \
 	((DESC)->kstat_irqs[smp_processor_id()])
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index c19896f895f9..f837133cdfbe 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -111,15 +111,6 @@ static void init_kstat_irqs(struct irq_desc *desc, int nr_desc, int nr)
 	}
 }
 
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-/*
- * Protect the sparse_irqs_free freelist:
- */
-static DEFINE_SPINLOCK(sparse_irq_lock);
-static struct irq_desc *sparse_irqs_free;
-struct irq_desc *sparse_irqs;
-#endif
-
 static void __init init_work(void *data)
 {
 	struct dyn_array *da = data;
@@ -130,121 +121,16 @@ static void __init init_work(void *data)
 
 	for (i = 0; i < *da->nr; i++) {
 		init_one_irq_desc(&desc[i]);
-#ifndef CONFIG_HAVE_SPARSE_IRQ
 		desc[i].irq = i;
-#endif
 	}
 
 	/* init kstat_irqs, nr_cpu_ids is ready already */
 	init_kstat_irqs(desc, *da->nr, nr_cpu_ids);
-
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-	for (i = 1; i < *da->nr; i++)
-		desc[i-1].next = &desc[i];
-
-	sparse_irqs_free = sparse_irqs;
-	sparse_irqs = NULL;
-#endif
-}
-
-#ifdef CONFIG_HAVE_SPARSE_IRQ
-static int nr_irq_desc = 32;
-
-static int __init parse_nr_irq_desc(char *arg)
-{
-	if (arg)
-		nr_irq_desc = simple_strtoul(arg, NULL, 0);
-	return 0;
-}
-
-early_param("nr_irq_desc", parse_nr_irq_desc);
-
-DEFINE_DYN_ARRAY(sparse_irqs, sizeof(struct irq_desc), nr_irq_desc, PAGE_SIZE, init_work);
-
-struct irq_desc *irq_to_desc(unsigned int irq)
-{
-	struct irq_desc *desc;
-
-	desc = sparse_irqs;
-	while (desc) {
-		if (desc->irq == irq)
-			return desc;
-
-		desc = desc->next;
-	}
-	return NULL;
 }
 
-struct irq_desc *irq_to_desc_alloc(unsigned int irq)
-{
-	struct irq_desc *desc, *desc_pri;
-	unsigned long flags;
-	int count = 0;
-	int i;
-
-	desc_pri = desc = sparse_irqs;
-	while (desc) {
-		if (desc->irq == irq)
-			return desc;
-
-		desc_pri = desc;
-		desc = desc->next;
-		count++;
-	}
-
-	spin_lock_irqsave(&sparse_irq_lock, flags);
-	/*
-	 *  we run out of pre-allocate ones, allocate more
-	 */
-	if (!sparse_irqs_free) {
-		unsigned long phys;
-		unsigned long total_bytes;
-
-		printk(KERN_DEBUG "try to get more irq_desc %d\n", nr_irq_desc);
-
-		total_bytes = sizeof(struct irq_desc) * nr_irq_desc;
-		if (after_bootmem)
-			desc = kzalloc(total_bytes, GFP_ATOMIC);
-		else
-			desc = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
-
-		if (!desc)
-			panic("please boot with nr_irq_desc= %d\n", count * 2);
-
-		phys = __pa(desc);
-		printk(KERN_DEBUG "irq_desc ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
-
-		for (i = 0; i < nr_irq_desc; i++)
-			init_one_irq_desc(&desc[i]);
-
-		for (i = 1; i < nr_irq_desc; i++)
-			desc[i-1].next = &desc[i];
-
-		/* init kstat_irqs, nr_cpu_ids is ready already */
-		init_kstat_irqs(desc, nr_irq_desc, nr_cpu_ids);
-
-		sparse_irqs_free = desc;
-	}
-
-	desc = sparse_irqs_free;
-	sparse_irqs_free = sparse_irqs_free->next;
-	desc->next = NULL;
-	if (desc_pri)
-		desc_pri->next = desc;
-	else
-		sparse_irqs = desc;
-	desc->irq = irq;
-
-	spin_unlock_irqrestore(&sparse_irq_lock, flags);
-
-	return desc;
-}
-#else
 struct irq_desc *irq_desc;
 DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);
 
-#endif
-
 #else
 
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
-- 
cgit v1.2.3


From ee32c9732244bde4b9b59eeac2814c23e2b71f8d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 15 Oct 2008 14:34:09 +0200
Subject: genirq: remove irq_to_desc_alloc

Remove the leftover of sparseirqs.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/io_apic.c    | 6 +-----
 arch/x86/kernel/irqinit_32.c | 2 +-
 arch/x86/kernel/irqinit_64.c | 2 +-
 include/linux/irq.h          | 5 -----
 kernel/irq/chip.c            | 2 +-
 5 files changed, 4 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index 683610517d2a..e03bc0f87eef 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -1257,11 +1257,7 @@ static void ioapic_register_intr(int irq, unsigned long trigger)
 {
 	struct irq_desc *desc;
 
-	/* first time to use this irq_desc */
-	if (irq < 16)
-		desc = irq_to_desc(irq);
-	else
-		desc = irq_to_desc_alloc(irq);
+	desc = irq_to_desc(irq);
 
 	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
 	    trigger == IOAPIC_LEVEL)
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index 9092103a18eb..a8d35998d308 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -70,7 +70,7 @@ void __init init_ISA_irqs (void)
 	 */
 	for (i = 0; i < 16; i++) {
 		/* first time call this irq_desc */
-		struct irq_desc *desc = irq_to_desc_alloc(i);
+		struct irq_desc *desc = irq_to_desc(i);
 
 		desc->status = IRQ_DISABLED;
 		desc->action = NULL;
diff --git a/arch/x86/kernel/irqinit_64.c b/arch/x86/kernel/irqinit_64.c
index d17fbc26d96f..ff0235391285 100644
--- a/arch/x86/kernel/irqinit_64.c
+++ b/arch/x86/kernel/irqinit_64.c
@@ -144,7 +144,7 @@ void __init init_ISA_irqs(void)
 
 	for (i = 0; i < 16; i++) {
 		/* first time call this irq_desc */
-		struct irq_desc *desc = irq_to_desc_alloc(i);
+		struct irq_desc *desc = irq_to_desc(i);
 
 		desc->status = IRQ_DISABLED;
 		desc->action = NULL;
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 68e0f3f9df30..3f33c7790300 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -210,11 +210,6 @@ static inline struct irq_desc *irq_to_desc(unsigned int irq)
 	return (irq < nr_irqs) ? irq_desc + irq : NULL;
 }
 
-static inline struct irq_desc *irq_to_desc_alloc(unsigned int irq)
-{
-	return irq_to_desc(irq);
-}
-
 #ifdef CONFIG_HAVE_DYN_ARRAY
 #define kstat_irqs_this_cpu(DESC) \
 	((DESC)->kstat_irqs[smp_processor_id()])
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 570d1ea1db5d..e6f73dbfcc3d 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -28,7 +28,7 @@ void dynamic_irq_init(unsigned int irq)
 	unsigned long flags;
 
 	/* first time to use this irq_desc */
-	desc = irq_to_desc_alloc(irq);
+	desc = irq_to_desc(irq);
 	if (!desc) {
 		WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
 		return;
-- 
cgit v1.2.3


From d6c88a507ef0b6afdb013cba4e7804ba7324d99a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 15 Oct 2008 15:27:23 +0200
Subject: genirq: revert dynarray

Revert the dynarray changes. They need more thought and polishing.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/Kconfig                      |   4 -
 arch/x86/Kconfig                  |   1 -
 arch/x86/kernel/io_apic.c         | 199 ++++++++++++++------------------------
 arch/x86/kernel/setup_percpu.c    |   8 +-
 arch/x86/kernel/visws_quirks.c    |   2 +-
 arch/x86/kernel/vmlinux_32.lds.S  |   1 -
 arch/x86/kernel/vmlinux_64.lds.S  |   2 -
 arch/x86/xen/spinlock.c           |   2 +-
 drivers/char/random.c             |   5 -
 drivers/pci/intr_remapping.c      |  11 +--
 include/asm-generic/vmlinux.lds.h |  13 ---
 include/linux/init.h              |  43 --------
 include/linux/irq.h               |  15 ---
 include/linux/kernel_stat.h       |  16 ++-
 init/Makefile                     |   2 +-
 init/dyn_array.c                  | 120 -----------------------
 init/main.c                       |  11 +--
 kernel/irq/chip.c                 |  30 +-----
 kernel/irq/handle.c               | 114 ++--------------------
 19 files changed, 103 insertions(+), 496 deletions(-)
 delete mode 100644 init/dyn_array.c

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index c8a7c2eb6490..071004d3a1b1 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -102,7 +102,3 @@ config HAVE_CLK
 	help
 	  The <linux/clk.h> calls support software clock gating and
 	  thus are a key power management tool on many systems.
-
-config HAVE_DYN_ARRAY
-	def_bool n
-
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8636ddf2f4a4..8da6123a60d0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -33,7 +33,6 @@ config X86
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_GENERIC_DMA_COHERENT if X86_32
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
-	select HAVE_DYN_ARRAY
 
 config ARCH_DEFCONFIG
 	string
diff --git a/arch/x86/kernel/io_apic.c b/arch/x86/kernel/io_apic.c
index e03bc0f87eef..6f80dc2f137e 100644
--- a/arch/x86/kernel/io_apic.c
+++ b/arch/x86/kernel/io_apic.c
@@ -107,7 +107,6 @@ static int __init parse_noapic(char *str)
 }
 early_param("noapic", parse_noapic);
 
-struct irq_cfg;
 struct irq_pin_list;
 struct irq_cfg {
 	unsigned int irq;
@@ -120,7 +119,7 @@ struct irq_cfg {
 };
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
-static struct irq_cfg irq_cfg_legacy[] __initdata = {
+static struct irq_cfg irq_cfgx[NR_IRQS] = {
 	[0]  = { .irq =  0, .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR,  },
 	[1]  = { .irq =  1, .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR,  },
 	[2]  = { .irq =  2, .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR,  },
@@ -139,48 +138,26 @@ static struct irq_cfg irq_cfg_legacy[] __initdata = {
 	[15] = { .irq = 15, .domain = CPU_MASK_ALL, .vector = IRQ15_VECTOR, },
 };
 
-static struct irq_cfg irq_cfg_init = { .irq =  -1U, };
-
-static void init_one_irq_cfg(struct irq_cfg *cfg)
-{
-	memcpy(cfg, &irq_cfg_init, sizeof(struct irq_cfg));
-}
-
-static struct irq_cfg *irq_cfgx;
-
-static void __init init_work(void *data)
-{
-	struct dyn_array *da = data;
-	struct irq_cfg *cfg;
-	int legacy_count;
-	int i;
-
-	cfg = *da->name;
-
-	memcpy(cfg, irq_cfg_legacy, sizeof(irq_cfg_legacy));
-
-	legacy_count = ARRAY_SIZE(irq_cfg_legacy);
-	for (i = legacy_count; i < *da->nr; i++)
-		init_one_irq_cfg(&cfg[i]);
-}
-
 #define for_each_irq_cfg(irq, cfg)		\
-	for (irq = 0, cfg = &irq_cfgx[irq]; irq < nr_irqs; irq++, cfg = &irq_cfgx[irq])
+	for (irq = 0, cfg = irq_cfgx; irq < nr_irqs; irq++, cfg++)
 
-DEFINE_DYN_ARRAY(irq_cfgx, sizeof(struct irq_cfg), nr_irqs, PAGE_SIZE, init_work);
-
-struct irq_cfg *irq_cfg(unsigned int irq)
+static struct irq_cfg *irq_cfg(unsigned int irq)
 {
-	if (irq < nr_irqs)
-		return &irq_cfgx[irq];
-
-	return NULL;
+	return irq < nr_irqs ? irq_cfgx + irq : NULL;
 }
-struct irq_cfg *irq_cfg_alloc(unsigned int irq)
+
+static struct irq_cfg *irq_cfg_alloc(unsigned int irq)
 {
 	return irq_cfg(irq);
 }
 
+/*
+ * Rough estimation of how many shared IRQs there are, can be changed
+ * anytime.
+ */
+#define MAX_PLUS_SHARED_IRQS NR_IRQS
+#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)
+
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -193,59 +170,29 @@ struct irq_pin_list {
 	struct irq_pin_list *next;
 };
 
-static struct irq_pin_list *irq_2_pin_head;
-/* fill one page ? */
-static int nr_irq_2_pin = 0x100;
+static struct irq_pin_list irq_2_pin_head[PIN_MAP_SIZE];
 static struct irq_pin_list *irq_2_pin_ptr;
-static void __init irq_2_pin_init_work(void *data)
+
+static void __init irq_2_pin_init(void)
 {
-	struct dyn_array *da = data;
-	struct irq_pin_list *pin;
+	struct irq_pin_list *pin = irq_2_pin_head;
 	int i;
 
-	pin = *da->name;
-
-	for (i = 1; i < *da->nr; i++)
+	for (i = 1; i < PIN_MAP_SIZE; i++)
 		pin[i-1].next = &pin[i];
 
 	irq_2_pin_ptr = &pin[0];
 }
-DEFINE_DYN_ARRAY(irq_2_pin_head, sizeof(struct irq_pin_list), nr_irq_2_pin, PAGE_SIZE, irq_2_pin_init_work);
 
 static struct irq_pin_list *get_one_free_irq_2_pin(void)
 {
-	struct irq_pin_list *pin;
-	int i;
-
-	pin = irq_2_pin_ptr;
-
-	if (pin) {
-		irq_2_pin_ptr = pin->next;
-		pin->next = NULL;
-		return pin;
-	}
-
-	/*
-	 *  we run out of pre-allocate ones, allocate more
-	 */
-	printk(KERN_DEBUG "try to get more irq_2_pin %d\n", nr_irq_2_pin);
-
-	if (after_bootmem)
-		pin = kzalloc(sizeof(struct irq_pin_list)*nr_irq_2_pin,
-				 GFP_ATOMIC);
-	else
-		pin = __alloc_bootmem_nopanic(sizeof(struct irq_pin_list) *
-				nr_irq_2_pin, PAGE_SIZE, 0);
+	struct irq_pin_list *pin = irq_2_pin_ptr;
 
 	if (!pin)
 		panic("can not get more irq_2_pin\n");
 
-	for (i = 1; i < nr_irq_2_pin; i++)
-		pin[i-1].next = &pin[i];
-
 	irq_2_pin_ptr = pin->next;
 	pin->next = NULL;
-
 	return pin;
 }
 
@@ -284,8 +231,9 @@ static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned i
 static inline void io_apic_modify(unsigned int apic, unsigned int reg, unsigned int value)
 {
 	struct io_apic __iomem *io_apic = io_apic_base(apic);
-        if (sis_apic_bug)
-                writel(reg, &io_apic->index);
+
+	if (sis_apic_bug)
+		writel(reg, &io_apic->index);
 	writel(value, &io_apic->data);
 }
 
@@ -1044,11 +992,11 @@ static int pin_2_irq(int idx, int apic, int pin)
 		while (i < apic)
 			irq += nr_ioapic_registers[i++];
 		irq += pin;
-                /*
+		/*
                  * For MPS mode, so far only needed by ES7000 platform
                  */
-                if (ioapic_renumber_irq)
-                        irq = ioapic_renumber_irq(apic, irq);
+		if (ioapic_renumber_irq)
+			irq = ioapic_renumber_irq(apic, irq);
 	}
 
 #ifdef CONFIG_X86_32
@@ -1232,19 +1180,19 @@ static struct irq_chip ir_ioapic_chip;
 #ifdef CONFIG_X86_32
 static inline int IO_APIC_irq_trigger(int irq)
 {
-        int apic, idx, pin;
+	int apic, idx, pin;
 
-        for (apic = 0; apic < nr_ioapics; apic++) {
-                for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
-                        idx = find_irq_entry(apic, pin, mp_INT);
-                        if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin)))
-                                return irq_trigger(idx);
-                }
-        }
-        /*
+	for (apic = 0; apic < nr_ioapics; apic++) {
+		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++) {
+			idx = find_irq_entry(apic, pin, mp_INT);
+			if ((idx != -1) && (irq == pin_2_irq(idx, apic, pin)))
+				return irq_trigger(idx);
+		}
+	}
+	/*
          * nonexistent IRQs are edge default
          */
-        return 0;
+	return 0;
 }
 #else
 static inline int IO_APIC_irq_trigger(int irq)
@@ -1509,8 +1457,8 @@ __apicdebuginit(void) print_IO_APIC(void)
 	reg_01.raw = io_apic_read(apic, 1);
 	if (reg_01.bits.version >= 0x10)
 		reg_02.raw = io_apic_read(apic, 2);
-        if (reg_01.bits.version >= 0x20)
-                reg_03.raw = io_apic_read(apic, 3);
+	if (reg_01.bits.version >= 0x20)
+		reg_03.raw = io_apic_read(apic, 3);
 	spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	printk("\n");
@@ -2089,9 +2037,9 @@ static int ioapic_retrigger_irq(unsigned int irq)
 #else
 static int ioapic_retrigger_irq(unsigned int irq)
 {
-        send_IPI_self(irq_cfg(irq)->vector);
+	send_IPI_self(irq_cfg(irq)->vector);
 
-        return 1;
+	return 1;
 }
 #endif
 
@@ -2189,7 +2137,7 @@ static int migrate_irq_remapped_level(int irq)
 
 	if (io_apic_level_ack_pending(irq)) {
 		/*
-	 	 * Interrupt in progress. Migrating irq now will change the
+		 * Interrupt in progress. Migrating irq now will change the
 		 * vector information in the IO-APIC RTE and that will confuse
 		 * the EOI broadcast performed by cpu.
 		 * So, delay the irq migration to the next instance.
@@ -2426,28 +2374,28 @@ static void ack_apic_level(unsigned int irq)
 }
 
 static struct irq_chip ioapic_chip __read_mostly = {
-	.name 		= "IO-APIC",
-	.startup 	= startup_ioapic_irq,
-	.mask	 	= mask_IO_APIC_irq,
-	.unmask	 	= unmask_IO_APIC_irq,
-	.ack 		= ack_apic_edge,
-	.eoi 		= ack_apic_level,
+	.name		= "IO-APIC",
+	.startup	= startup_ioapic_irq,
+	.mask		= mask_IO_APIC_irq,
+	.unmask		= unmask_IO_APIC_irq,
+	.ack		= ack_apic_edge,
+	.eoi		= ack_apic_level,
 #ifdef CONFIG_SMP
-	.set_affinity 	= set_ioapic_affinity_irq,
+	.set_affinity	= set_ioapic_affinity_irq,
 #endif
 	.retrigger	= ioapic_retrigger_irq,
 };
 
 #ifdef CONFIG_INTR_REMAP
 static struct irq_chip ir_ioapic_chip __read_mostly = {
-	.name 		= "IR-IO-APIC",
-	.startup 	= startup_ioapic_irq,
-	.mask	 	= mask_IO_APIC_irq,
-	.unmask	 	= unmask_IO_APIC_irq,
-	.ack 		= ack_x2apic_edge,
-	.eoi 		= ack_x2apic_level,
+	.name		= "IR-IO-APIC",
+	.startup	= startup_ioapic_irq,
+	.mask		= mask_IO_APIC_irq,
+	.unmask		= unmask_IO_APIC_irq,
+	.ack		= ack_x2apic_edge,
+	.eoi		= ack_x2apic_level,
 #ifdef CONFIG_SMP
-	.set_affinity 	= set_ir_ioapic_affinity_irq,
+	.set_affinity	= set_ir_ioapic_affinity_irq,
 #endif
 	.retrigger	= ioapic_retrigger_irq,
 };
@@ -2636,8 +2584,8 @@ static inline void __init check_timer(void)
 
 	local_irq_save(flags);
 
-        ver = apic_read(APIC_LVR);
-        ver = GET_APIC_VERSION(ver);
+	ver = apic_read(APIC_LVR);
+	ver = GET_APIC_VERSION(ver);
 
 	/*
 	 * get/set the timer IRQ vector:
@@ -2822,12 +2770,12 @@ void __init setup_IO_APIC(void)
 	io_apic_irqs = ~PIC_IRQS;
 
 	apic_printk(APIC_VERBOSE, "ENABLING IO-APIC IRQs\n");
-        /*
+	/*
          * Set up IO-APIC IRQ routing.
          */
 #ifdef CONFIG_X86_32
-        if (!acpi_ioapic)
-                setup_ioapic_ids_from_mpc();
+	if (!acpi_ioapic)
+		setup_ioapic_ids_from_mpc();
 #endif
 	sync_Arb_IDs();
 	setup_IO_APIC_irqs();
@@ -2842,9 +2790,9 @@ void __init setup_IO_APIC(void)
 
 static int __init io_apic_bug_finalize(void)
 {
-        if (sis_apic_bug == -1)
-                sis_apic_bug = 0;
-        return 0;
+	if (sis_apic_bug == -1)
+		sis_apic_bug = 0;
+	return 0;
 }
 
 late_initcall(io_apic_bug_finalize);
@@ -3199,7 +3147,7 @@ static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
 	if (index < 0) {
 		printk(KERN_ERR
 		       "Unable to allocate %d IRTE for PCI %s\n", nvec,
-		        pci_name(dev));
+		       pci_name(dev));
 		return -ENOSPC;
 	}
 	return index;
@@ -3885,23 +3833,24 @@ static struct resource * __init ioapic_setup_resources(void)
 void __init ioapic_init_mappings(void)
 {
 	unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
-	int i;
 	struct resource *ioapic_res;
+	int i;
 
+	irq_2_pin_init();
 	ioapic_res = ioapic_setup_resources();
 	for (i = 0; i < nr_ioapics; i++) {
 		if (smp_found_config) {
 			ioapic_phys = mp_ioapics[i].mp_apicaddr;
 #ifdef CONFIG_X86_32
-                        if (!ioapic_phys) {
-                                printk(KERN_ERR
-                                       "WARNING: bogus zero IO-APIC "
-                                       "address found in MPTABLE, "
-                                       "disabling IO/APIC support!\n");
-                                smp_found_config = 0;
-                                skip_ioapic_setup = 1;
-                                goto fake_ioapic_page;
-                        }
+			if (!ioapic_phys) {
+				printk(KERN_ERR
+				       "WARNING: bogus zero IO-APIC "
+				       "address found in MPTABLE, "
+				       "disabling IO/APIC support!\n");
+				smp_found_config = 0;
+				skip_ioapic_setup = 1;
+				goto fake_ioapic_page;
+			}
 #endif
 		} else {
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 2b7dab699e83..410c88f0bfeb 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -140,7 +140,7 @@ static void __init setup_cpu_pda_map(void)
  */
 void __init setup_per_cpu_areas(void)
 {
-	ssize_t size, old_size, da_size;
+	ssize_t size, old_size;
 	char *ptr;
 	int cpu;
 	unsigned long align = 1;
@@ -150,9 +150,8 @@ void __init setup_per_cpu_areas(void)
 
 	/* Copy section for each CPU (we discard the original) */
 	old_size = PERCPU_ENOUGH_ROOM;
-	da_size = per_cpu_dyn_array_size(&align);
 	align = max_t(unsigned long, PAGE_SIZE, align);
-	size = roundup(old_size + da_size, align);
+	size = roundup(old_size, align);
 	printk(KERN_INFO "PERCPU: Allocating %zd bytes of per cpu data\n",
 			  size);
 
@@ -182,9 +181,6 @@ void __init setup_per_cpu_areas(void)
 #endif
 		per_cpu_offset(cpu) = ptr - __per_cpu_start;
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
-
-		per_cpu_alloc_dyn_array(cpu, ptr + old_size);
-
 	}
 
 	printk(KERN_DEBUG "NR_CPUS: %d, nr_cpu_ids: %d, nr_node_ids %d\n",
diff --git a/arch/x86/kernel/visws_quirks.c b/arch/x86/kernel/visws_quirks.c
index 817aa55a1209..0c9667f0752a 100644
--- a/arch/x86/kernel/visws_quirks.c
+++ b/arch/x86/kernel/visws_quirks.c
@@ -633,7 +633,7 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 	/*
 	 * handle this 'virtual interrupt' as a Cobalt one now.
 	 */
-	kstat_irqs_this_cpu(desc)++;
+	kstat_incr_irqs_this_cpu(realirq, desc);
 
 	if (likely(desc->action != NULL))
 		handle_IRQ_event(realirq, desc->action);
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index c36007ab3940..a9b8560adbc2 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -145,7 +145,6 @@ SECTIONS
 	*(.x86_cpu_dev.init)
 	__x86_cpu_dev_end = .;
   }
-  DYN_ARRAY_INIT(8)
   SECURITY_INIT
   . = ALIGN(4);
   .altinstructions : AT(ADDR(.altinstructions) - LOAD_OFFSET) {
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index 30973dbac8c2..3245ad72594a 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -174,8 +174,6 @@ SECTIONS
   }
   __x86_cpu_dev_end = .;
 
-  DYN_ARRAY_INIT(8)
-
   SECURITY_INIT
 
   . = ALIGN(8);
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index bb6bc721b13d..5601506f2dd9 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -241,7 +241,7 @@ static noinline int xen_spin_lock_slow(struct raw_spinlock *lock, bool irq_enabl
 		ADD_STATS(taken_slow_spurious, !xen_test_irq_pending(irq));
 	} while (!xen_test_irq_pending(irq)); /* check for spurious wakeups */
 
-	kstat_irqs_this_cpu(irq_to_desc(irq))++;
+	kstat_incr_irqs_this_cpu(irq, irq_to_desc(irq));
 
 out:
 	raw_local_irq_restore(flags);
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 9ce80213007b..1137d2976043 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -558,12 +558,7 @@ struct timer_rand_state {
 	unsigned dont_count_entropy:1;
 };
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-static struct timer_rand_state **irq_timer_state;
-DEFINE_DYN_ARRAY(irq_timer_state, sizeof(struct timer_rand_state *), nr_irqs, PAGE_SIZE, NULL);
-#else
 static struct timer_rand_state *irq_timer_state[NR_IRQS];
-#endif
 
 static struct timer_rand_state *get_timer_rand_state(unsigned int irq)
 {
diff --git a/drivers/pci/intr_remapping.c b/drivers/pci/intr_remapping.c
index 0f43b265eee6..950769e87475 100644
--- a/drivers/pci/intr_remapping.c
+++ b/drivers/pci/intr_remapping.c
@@ -19,20 +19,13 @@ struct irq_2_iommu {
 	u8  irte_mask;
 };
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-static struct irq_2_iommu *irq_2_iommuX;
-DEFINE_DYN_ARRAY(irq_2_iommuX, sizeof(struct irq_2_iommu), nr_irqs, PAGE_SIZE, NULL);
-#else
 static struct irq_2_iommu irq_2_iommuX[NR_IRQS];
-#endif
 
 static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
 {
-	if (irq < nr_irqs)
-		return &irq_2_iommuX[irq];
-
-	return NULL;
+	return (irq < nr_irqs) ?: irq_2_iommuX + irq : NULL;
 }
+
 static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
 {
 	return irq_2_iommu(irq);
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index c68eda9d9a90..7440a0dceddb 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -210,19 +210,6 @@
  * All archs are supposed to use RO_DATA() */
 #define RODATA RO_DATA(4096)
 
-#define DYN_ARRAY_INIT(align)							\
-	. = ALIGN((align));						\
-	.dyn_array.init : AT(ADDR(.dyn_array.init) - LOAD_OFFSET) {	\
-		VMLINUX_SYMBOL(__dyn_array_start) = .;			\
-		*(.dyn_array.init)					\
-		VMLINUX_SYMBOL(__dyn_array_end) = .;			\
-	}								\
-	. = ALIGN((align));						\
-	.per_cpu_dyn_array.init : AT(ADDR(.per_cpu_dyn_array.init) - LOAD_OFFSET) {	\
-		VMLINUX_SYMBOL(__per_cpu_dyn_array_start) = .;		\
-		*(.per_cpu_dyn_array.init)				\
-		VMLINUX_SYMBOL(__per_cpu_dyn_array_end) = .;		\
-	}
 #define SECURITY_INIT							\
 	.security_initcall.init : AT(ADDR(.security_initcall.init) - LOAD_OFFSET) { \
 		VMLINUX_SYMBOL(__security_initcall_start) = .;		\
diff --git a/include/linux/init.h b/include/linux/init.h
index 59fbb4aaba6a..70ad53e1eab8 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -247,49 +247,6 @@ struct obs_kernel_param {
 /* Relies on boot_command_line being set */
 void __init parse_early_param(void);
 
-struct dyn_array {
-	void **name;
-	unsigned long size;
-	unsigned int *nr;
-	unsigned long align;
-	void (*init_work)(void *);
-};
-extern struct dyn_array *__dyn_array_start[], *__dyn_array_end[];
-extern struct dyn_array *__per_cpu_dyn_array_start[], *__per_cpu_dyn_array_end[];
-
-#define DEFINE_DYN_ARRAY_ADDR(nameX, addrX, sizeX, nrX, alignX, init_workX) \
-		static struct dyn_array __dyn_array_##nameX __initdata = \
-		{	.name = (void **)&(nameX),\
-			.size = sizeX,\
-			.nr   = &(nrX),\
-			.align = alignX,\
-			.init_work = init_workX,\
-		}; \
-		static struct dyn_array *__dyn_array_ptr_##nameX __used \
-		__attribute__((__section__(".dyn_array.init"))) = \
-			&__dyn_array_##nameX
-
-#define DEFINE_DYN_ARRAY(nameX, sizeX, nrX, alignX, init_workX) \
-	DEFINE_DYN_ARRAY_ADDR(nameX, nameX, sizeX, nrX, alignX, init_workX)
-
-#define DEFINE_PER_CPU_DYN_ARRAY_ADDR(nameX, addrX, sizeX, nrX, alignX, init_workX) \
-		static struct dyn_array __per_cpu_dyn_array_##nameX __initdata = \
-		{	.name = (void **)&(addrX),\
-			.size = sizeX,\
-			.nr   = &(nrX),\
-			.align = alignX,\
-			.init_work = init_workX,\
-		}; \
-		static struct dyn_array *__per_cpu_dyn_array_ptr_##nameX __used \
-		__attribute__((__section__(".per_cpu_dyn_array.init"))) = \
-			&__per_cpu_dyn_array_##nameX
-
-#define DEFINE_PER_CPU_DYN_ARRAY(nameX, sizeX, nrX, alignX, init_workX) \
-	DEFINE_PER_CPU_DYN_ARRAY_ADDR(nameX, nameX, nrX, alignX, init_workX)
-
-extern void pre_alloc_dyn_array(void);
-extern unsigned long per_cpu_dyn_array_size(unsigned long *align);
-extern void per_cpu_alloc_dyn_array(int cpu, char *ptr);
 #endif /* __ASSEMBLY__ */
 
 /**
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 3f33c7790300..38bf89f2ade0 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -139,8 +139,6 @@ struct irq_chip {
 	const char	*typename;
 };
 
-struct timer_rand_state;
-struct irq_2_iommu;
 /**
  * struct irq_desc - interrupt descriptor
  *
@@ -167,9 +165,6 @@ struct irq_2_iommu;
  */
 struct irq_desc {
 	unsigned int		irq;
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	unsigned int            *kstat_irqs;
-#endif
 	irq_flow_handler_t	handle_irq;
 	struct irq_chip		*chip;
 	struct msi_desc		*msi_desc;
@@ -198,23 +193,13 @@ struct irq_desc {
 } ____cacheline_internodealigned_in_smp;
 
 
-#ifndef CONFIG_HAVE_DYN_ARRAY
-/* could be removed if we get rid of all irq_desc reference */
 extern struct irq_desc irq_desc[NR_IRQS];
-#else
-extern struct irq_desc *irq_desc;
-#endif
 
 static inline struct irq_desc *irq_to_desc(unsigned int irq)
 {
 	return (irq < nr_irqs) ? irq_desc + irq : NULL;
 }
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-#define kstat_irqs_this_cpu(DESC) \
-	((DESC)->kstat_irqs[smp_processor_id()])
-#endif
-
 /*
  * Migration helpers for obsolete names, they will go away:
  */
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 21249d8c1293..a9d0d360b776 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -28,9 +28,7 @@ struct cpu_usage_stat {
 
 struct kernel_stat {
 	struct cpu_usage_stat	cpustat;
-#ifndef CONFIG_HAVE_DYN_ARRAY
        unsigned int irqs[NR_IRQS];
-#endif
 };
 
 DECLARE_PER_CPU(struct kernel_stat, kstat);
@@ -41,20 +39,18 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 
 extern unsigned long long nr_context_switches(void);
 
-#ifndef CONFIG_HAVE_DYN_ARRAY
-#define kstat_irqs_this_cpu(irq) \
-	(kstat_this_cpu.irqs[irq])
-#endif
+struct irq_desc;
 
+static inline void kstat_incr_irqs_this_cpu(unsigned int irq,
+					    struct irq_desc *desc)
+{
+	kstat_this_cpu.irqs[irq]++;
+}
 
-#ifndef CONFIG_HAVE_DYN_ARRAY
 static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 {
        return kstat_cpu(cpu).irqs[irq];
 }
-#else
-extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu);
-#endif
 
 /*
  * Number of interrupts per specific IRQ source, since bootup
diff --git a/init/Makefile b/init/Makefile
index dc5eeca6eb6d..4a243df426f7 100644
--- a/init/Makefile
+++ b/init/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the linux kernel.
 #
 
-obj-y                          := main.o dyn_array.o version.o mounts.o
+obj-y                          := main.o version.o mounts.o
 ifneq ($(CONFIG_BLK_DEV_INITRD),y)
 obj-y                          += noinitramfs.o
 else
diff --git a/init/dyn_array.c b/init/dyn_array.c
deleted file mode 100644
index c8d5e2a18588..000000000000
--- a/init/dyn_array.c
+++ /dev/null
@@ -1,120 +0,0 @@
-#include <linux/types.h>
-#include <linux/kernel.h>
-#include <linux/kallsyms.h>
-#include <linux/init.h>
-#include <linux/bootmem.h>
-#include <linux/irq.h>
-
-void __init pre_alloc_dyn_array(void)
-{
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	unsigned long total_size = 0, size, phys;
-	unsigned long max_align = 1;
-	struct dyn_array **daa;
-	char *ptr;
-
-	/* get the total size at first */
-	for (daa = __dyn_array_start ; daa < __dyn_array_end; daa++) {
-		struct dyn_array *da = *daa;
-
-		printk(KERN_DEBUG "dyn_array %pF size:%#lx nr:%d align:%#lx\n",
-			da->name, da->size, *da->nr, da->align);
-		size = da->size * (*da->nr);
-		total_size += roundup(size, da->align);
-		if (da->align > max_align)
-			max_align = da->align;
-	}
-	if (total_size)
-		printk(KERN_DEBUG "dyn_array total_size: %#lx\n",
-			 total_size);
-	else
-		return;
-
-	/* allocate them all together */
-	max_align = max_t(unsigned long, max_align, PAGE_SIZE);
-	ptr = __alloc_bootmem(total_size, max_align, 0);
-	phys = virt_to_phys(ptr);
-
-	for (daa = __dyn_array_start ; daa < __dyn_array_end; daa++) {
-		struct dyn_array *da = *daa;
-
-		size = da->size * (*da->nr);
-		phys = roundup(phys, da->align);
-		printk(KERN_DEBUG "dyn_array %pF ==> [%#lx - %#lx]\n",
-			da->name, phys, phys + size);
-		*da->name = phys_to_virt(phys);
-
-		phys += size;
-
-		if (da->init_work)
-			da->init_work(da);
-	}
-#else
-#ifdef CONFIG_GENERIC_HARDIRQS
-	unsigned int i;
-
-	for (i = 0; i < NR_IRQS; i++)
-		irq_desc[i].irq = i;
-#endif
-#endif
-}
-
-unsigned long __init per_cpu_dyn_array_size(unsigned long *align)
-{
-	unsigned long total_size = 0;
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	unsigned long size;
-	struct dyn_array **daa;
-	unsigned max_align = 1;
-
-	for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
-		struct dyn_array *da = *daa;
-
-		printk(KERN_DEBUG "per_cpu_dyn_array %pF size:%#lx nr:%d align:%#lx\n",
-			da->name, da->size, *da->nr, da->align);
-		size = da->size * (*da->nr);
-		total_size += roundup(size, da->align);
-		if (da->align > max_align)
-			max_align = da->align;
-	}
-	if (total_size) {
-		printk(KERN_DEBUG "per_cpu_dyn_array total_size: %#lx\n",
-			 total_size);
-		*align = max_align;
-	}
-#endif
-	return total_size;
-}
-
-#ifdef CONFIG_SMP
-void __init per_cpu_alloc_dyn_array(int cpu, char *ptr)
-{
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	unsigned long size, phys;
-	struct dyn_array **daa;
-	unsigned long addr;
-	void **array;
-
-	phys = virt_to_phys(ptr);
-	for (daa = __per_cpu_dyn_array_start ; daa < __per_cpu_dyn_array_end; daa++) {
-		struct dyn_array *da = *daa;
-
-		size = da->size * (*da->nr);
-		phys = roundup(phys, da->align);
-		printk(KERN_DEBUG "per_cpu_dyn_array %pF ==> [%#lx - %#lx]\n",
-			da->name, phys, phys + size);
-
-		addr = (unsigned long)da->name;
-		addr += per_cpu_offset(cpu);
-		array = (void **)addr;
-		*array = phys_to_virt(phys);
-		*da->name = *array; /* so init_work could use it directly */
-
-		phys += size;
-
-		if (da->init_work)
-			da->init_work(da);
-	}
-#endif
-}
-#endif
diff --git a/init/main.c b/init/main.c
index e81cf427d9c7..27f6bf6108e9 100644
--- a/init/main.c
+++ b/init/main.c
@@ -391,23 +391,17 @@ EXPORT_SYMBOL(__per_cpu_offset);
 
 static void __init setup_per_cpu_areas(void)
 {
-	unsigned long size, i, old_size;
+	unsigned long size, i;
 	char *ptr;
 	unsigned long nr_possible_cpus = num_possible_cpus();
-	unsigned long align = 1;
-	unsigned da_size;
 
 	/* Copy section for each CPU (we discard the original) */
-	old_size = PERCPU_ENOUGH_ROOM;
-	da_size = per_cpu_dyn_array_size(&align);
-	align = max_t(unsigned long, PAGE_SIZE, align);
-	size = ALIGN(old_size + da_size, align);
+	size = ALIGN(PERCPU_ENOUGH_ROOM, PAGE_SIZE);
 	ptr = alloc_bootmem_pages(size * nr_possible_cpus);
 
 	for_each_possible_cpu(i) {
 		__per_cpu_offset[i] = ptr - __per_cpu_start;
 		memcpy(ptr, __per_cpu_start, __per_cpu_end - __per_cpu_start);
-		per_cpu_alloc_dyn_array(i, ptr + old_size);
 		ptr += size;
 	}
 }
@@ -573,7 +567,6 @@ asmlinkage void __init start_kernel(void)
 	printk(KERN_NOTICE);
 	printk(linux_banner);
 	setup_arch(&command_line);
-	pre_alloc_dyn_array();
 	mm_init_owner(&init_mm, &init_task);
 	setup_command_line(command_line);
 	unwind_setup();
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index e6f73dbfcc3d..d96d6f687c48 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -326,11 +326,7 @@ handle_simple_irq(unsigned int irq, struct irq_desc *desc)
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	kstat_irqs_this_cpu(desc)++;
-#else
-	kstat_irqs_this_cpu(irq)++;
-#endif
+	kstat_incr_irqs_this_cpu(irq, desc);
 
 	action = desc->action;
 	if (unlikely(!action || (desc->status & IRQ_DISABLED)))
@@ -371,11 +367,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	kstat_irqs_this_cpu(desc)++;
-#else
-	kstat_irqs_this_cpu(irq)++;
-#endif
+	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/*
 	 * If its disabled or no action available
@@ -422,11 +414,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 		goto out;
 
 	desc->status &= ~(IRQ_REPLAY | IRQ_WAITING);
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	kstat_irqs_this_cpu(desc)++;
-#else
-	kstat_irqs_this_cpu(irq)++;
-#endif
+	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/*
 	 * If its disabled or no action available
@@ -490,11 +478,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		mask_ack_irq(desc, irq);
 		goto out_unlock;
 	}
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	kstat_irqs_this_cpu(desc)++;
-#else
-	kstat_irqs_this_cpu(irq)++;
-#endif
+	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/* Start handling the irq */
 	desc->chip->ack(irq);
@@ -549,11 +533,7 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 {
 	irqreturn_t action_ret;
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	kstat_irqs_this_cpu(desc)++;
-#else
-	kstat_irqs_this_cpu(irq)++;
-#endif
+	kstat_incr_irqs_this_cpu(irq, desc);
 
 	if (desc->chip->ack)
 		desc->chip->ack(irq);
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index f837133cdfbe..9fe86b3a60a5 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -18,11 +18,6 @@
 
 #include "internals.h"
 
-/*
- * lockdep: we want to handle all irq_desc locks as a single lock-class:
- */
-static struct lock_class_key irq_desc_lock_class;
-
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
  * @irq:       the interrupt number
@@ -30,15 +25,10 @@ static struct lock_class_key irq_desc_lock_class;
  *
  * Handles spurious and unhandled IRQ's. It also prints a debugmessage.
  */
-void
-handle_bad_irq(unsigned int irq, struct irq_desc *desc)
+void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 {
 	print_irq_desc(irq, desc);
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	kstat_irqs_this_cpu(desc)++;
-#else
-	kstat_irqs_this_cpu(irq)++;
-#endif
+	kstat_incr_irqs_this_cpu(irq, desc);
 	ack_bad_irq(irq);
 }
 
@@ -59,80 +49,6 @@ handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-static struct irq_desc irq_desc_init = {
-	.irq = -1U,
-	.status = IRQ_DISABLED,
-	.chip = &no_irq_chip,
-	.handle_irq = handle_bad_irq,
-	.depth = 1,
-	.lock = __SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-#ifdef CONFIG_SMP
-	.affinity = CPU_MASK_ALL
-#endif
-};
-
-
-static void init_one_irq_desc(struct irq_desc *desc)
-{
-	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
-	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-}
-
-extern int after_bootmem;
-extern void *__alloc_bootmem_nopanic(unsigned long size,
-			     unsigned long align,
-			     unsigned long goal);
-
-static void init_kstat_irqs(struct irq_desc *desc, int nr_desc, int nr)
-{
-	unsigned long bytes, total_bytes;
-	char *ptr;
-	int i;
-	unsigned long phys;
-
-	/* Compute how many bytes we need per irq and allocate them */
-	bytes = nr * sizeof(unsigned int);
-	total_bytes = bytes * nr_desc;
-	if (after_bootmem)
-		ptr = kzalloc(total_bytes, GFP_ATOMIC);
-	else
-		ptr = __alloc_bootmem_nopanic(total_bytes, PAGE_SIZE, 0);
-
-	if (!ptr)
-		panic(" can not allocate kstat_irqs\n");
-
-	phys = __pa(ptr);
-	printk(KERN_DEBUG "kstat_irqs ==> [%#lx - %#lx]\n", phys, phys + total_bytes);
-
-	for (i = 0; i < nr_desc; i++) {
-		desc[i].kstat_irqs = (unsigned int *)ptr;
-		ptr += bytes;
-	}
-}
-
-static void __init init_work(void *data)
-{
-	struct dyn_array *da = data;
-	int i;
-	struct  irq_desc *desc;
-
-	desc = *da->name;
-
-	for (i = 0; i < *da->nr; i++) {
-		init_one_irq_desc(&desc[i]);
-		desc[i].irq = i;
-	}
-
-	/* init kstat_irqs, nr_cpu_ids is ready already */
-	init_kstat_irqs(desc, *da->nr, nr_cpu_ids);
-}
-
-struct irq_desc *irq_desc;
-DEFINE_DYN_ARRAY(irq_desc, sizeof(struct irq_desc), nr_irqs, PAGE_SIZE, init_work);
-
-#else
-
 struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	[0 ... NR_IRQS-1] = {
 		.status = IRQ_DISABLED,
@@ -146,8 +62,6 @@ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
 	}
 };
 
-#endif
-
 /*
  * What should we do if we get a hw irq event on an illegal vector?
  * Each architecture has to answer this themself.
@@ -258,11 +172,8 @@ unsigned int __do_IRQ(unsigned int irq)
 	struct irqaction *action;
 	unsigned int status;
 
-#ifdef CONFIG_HAVE_DYN_ARRAY
-	kstat_irqs_this_cpu(desc)++;
-#else
-	kstat_irqs_this_cpu(irq)++;
-#endif
+	kstat_incr_irqs_this_cpu(irq, desc);
+
 	if (CHECK_IRQ_PER_CPU(desc->status)) {
 		irqreturn_t action_ret;
 
@@ -351,23 +262,16 @@ out:
 
 
 #ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * lockdep: we want to handle all irq_desc locks as a single lock-class:
+ */
+static struct lock_class_key irq_desc_lock_class;
+
 void early_init_irq_lock_class(void)
 {
-#ifndef CONFIG_HAVE_DYN_ARRAY
 	int i;
 
 	for (i = 0; i < nr_irqs; i++)
 		lockdep_set_class(&irq_desc[i].lock, &irq_desc_lock_class);
-#endif
 }
 #endif
-
-#ifdef CONFIG_HAVE_DYN_ARRAY
-unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	return desc->kstat_irqs[cpu];
-}
-#endif
-EXPORT_SYMBOL(kstat_irqs_cpu);
-
-- 
cgit v1.2.3


From a1aca5de08a0cb840a90fb3f729a5940f8d21185 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Wed, 15 Oct 2008 19:29:15 +0200
Subject: genirq: remove artifacts from sparseirq removal

Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/Kconfig                     | 1 +
 arch/x86/kernel/acpi/boot.c      | 1 -
 arch/x86/kernel/irqinit_32.c     | 1 -
 arch/x86/kernel/vmlinux_64.lds.S | 1 -
 arch/x86/mm/init_32.c            | 3 ---
 include/linux/init.h             | 1 -
 include/linux/kernel_stat.h      | 2 +-
 7 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/arch/Kconfig b/arch/Kconfig
index 071004d3a1b1..0267babe5eb9 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -102,3 +102,4 @@ config HAVE_CLK
 	help
 	  The <linux/clk.h> calls support software clock gating and
 	  thus are a key power management tool on many systems.
+
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 5fef4fece4a5..0d1c26a583c5 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -1254,7 +1254,6 @@ static int __init acpi_parse_madt_ioapic_entries(void)
 		return count;
 	}
 
-
 	count =
 	    acpi_table_parse_madt(ACPI_MADT_TYPE_INTERRUPT_OVERRIDE, acpi_parse_int_src_ovr,
 				  nr_irqs);
diff --git a/arch/x86/kernel/irqinit_32.c b/arch/x86/kernel/irqinit_32.c
index a8d35998d308..845aa9803e80 100644
--- a/arch/x86/kernel/irqinit_32.c
+++ b/arch/x86/kernel/irqinit_32.c
@@ -184,4 +184,3 @@ void __init native_init_IRQ(void)
 
 	irq_ctx_init(smp_processor_id());
 }
-
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index 3245ad72594a..46e05447405b 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -173,7 +173,6 @@ SECTIONS
 	*(.x86_cpu_dev.init)
   }
   __x86_cpu_dev_end = .;
-
   SECURITY_INIT
 
   . = ALIGN(8);
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 91343c2694b4..8396868e82c5 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -66,7 +66,6 @@ static unsigned long __meminitdata table_end;
 static unsigned long __meminitdata table_top;
 
 static int __initdata after_init_bootmem;
-int after_bootmem;
 
 static __init void *alloc_low_page(unsigned long *phys)
 {
@@ -989,8 +988,6 @@ void __init mem_init(void)
 
 	set_highmem_pages_init();
 
-	after_bootmem = 1;
-
 	codesize =  (unsigned long) &_etext - (unsigned long) &_text;
 	datasize =  (unsigned long) &_edata - (unsigned long) &_etext;
 	initsize =  (unsigned long) &__init_end - (unsigned long) &__init_begin;
diff --git a/include/linux/init.h b/include/linux/init.h
index 70ad53e1eab8..93538b696e3d 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -246,7 +246,6 @@ struct obs_kernel_param {
 
 /* Relies on boot_command_line being set */
 void __init parse_early_param(void);
-
 #endif /* __ASSEMBLY__ */
 
 /**
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index a9d0d360b776..89b6ecd41473 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -28,7 +28,7 @@ struct cpu_usage_stat {
 
 struct kernel_stat {
 	struct cpu_usage_stat	cpustat;
-       unsigned int irqs[NR_IRQS];
+	unsigned int irqs[NR_IRQS];
 };
 
 DECLARE_PER_CPU(struct kernel_stat, kstat);
-- 
cgit v1.2.3


From 811410fdb6b9d82a518542289efe9b2a51e3cbfb Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 16 Oct 2008 14:16:11 +0200
Subject: genirq: add reverse iterator for irq_desc

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/irq.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 38bf89f2ade0..31632aa65d16 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -21,6 +21,10 @@ extern int nr_irqs;
 
 # define for_each_irq_desc(irq, desc)		\
 	for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc++)
+
+# define for_each_irq_desc_reverse(irq, desc)			\
+	for (irq = nr_irqs -1, desc = irq_desc + (nr_irqs -1 );	\
+	     irq > 0; irq--, desc--)
 #endif
 
 #ifndef CONFIG_S390
-- 
cgit v1.2.3


From 2be3b52a5785a6a5c5349fbd315f57595f7074be Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 16 Oct 2008 14:50:27 +0200
Subject: proc: fixup irq iterator

There is no need for irq_desc here. Even for sparse_irq we can
handle this clever in for_each_irq_nr().

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 fs/proc/proc_misc.c | 7 ++-----
 include/linux/irq.h | 3 +++
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 3f5c7b9d1a70..97b4579134d5 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -509,9 +509,6 @@ static int show_stat(struct seq_file *p, void *v)
 	u64 sum = 0;
 	struct timespec boottime;
 	unsigned int per_irq_sum;
-#ifdef CONFIG_GENERIC_HARDIRQS
-	struct irq_desc *desc;
-#endif
 
 	user = nice = system = idle = iowait =
 		irq = softirq = steal = cputime64_zero;
@@ -530,7 +527,7 @@ static int show_stat(struct seq_file *p, void *v)
 		steal = cputime64_add(steal, kstat_cpu(i).cpustat.steal);
 		guest = cputime64_add(guest, kstat_cpu(i).cpustat.guest);
 
-		for_each_irq_desc(j, desc)
+		for_each_irq_nr(j)
 			sum += kstat_irqs_cpu(j, i);
 
 		sum += arch_irq_stat_cpu(i);
@@ -575,7 +572,7 @@ static int show_stat(struct seq_file *p, void *v)
 	seq_printf(p, "intr %llu", (unsigned long long)sum);
 
 	/* sum again ? it could be updated? */
-	for_each_irq_desc(j, desc) {
+	for_each_irq_nr(j) {
 		per_irq_sum = 0;
 
 		for_each_possible_cpu(i)
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 31632aa65d16..0618fb362cb4 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -27,6 +27,9 @@ extern int nr_irqs;
 	     irq > 0; irq--, desc--)
 #endif
 
+#define for_each_irq_nr(irq)			\
+	for (irq = 0; irq < nr_irqs; irq++)
+
 #ifndef CONFIG_S390
 
 #include <linux/linkage.h>
-- 
cgit v1.2.3


From 3e624fc72fba09b6f999a9fbb87b64efccd38036 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Thu, 16 Oct 2008 20:00:24 -0400
Subject: ext4: Replace hackish ext4_mb_poll_new_transaction with commit
 callback

The multiblock allocator needs to be able to release blocks (and issue
a blkdev discard request) when the transaction which freed those
blocks is committed.  Previously this was done via a polling mechanism
when blocks are allocated or freed.  A much better way of doing things
is to create a jbd2 callback function and attaching the list of blocks
to be freed directly to the transaction structure.

Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
---
 fs/ext4/ext4_sb.h     |  3 --
 fs/ext4/mballoc.c     | 85 +++++++++------------------------------------------
 fs/ext4/mballoc.h     |  3 +-
 fs/jbd2/commit.c      |  3 ++
 fs/jbd2/transaction.c |  1 +
 include/linux/jbd2.h  |  9 ++++++
 6 files changed, 29 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/fs/ext4/ext4_sb.h b/fs/ext4/ext4_sb.h
index 6a0b40d43264..445fde603df8 100644
--- a/fs/ext4/ext4_sb.h
+++ b/fs/ext4/ext4_sb.h
@@ -99,9 +99,6 @@ struct ext4_sb_info {
 	struct inode *s_buddy_cache;
 	long s_blocks_reserved;
 	spinlock_t s_reserve_lock;
-	struct list_head s_active_transaction;
-	struct list_head s_closed_transaction;
-	struct list_head s_committed_transaction;
 	spinlock_t s_md_lock;
 	tid_t s_last_transaction;
 	unsigned short *s_mb_offsets, *s_mb_maxs;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index da1da1fe2b14..dfe17a134052 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2523,9 +2523,6 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	}
 
 	spin_lock_init(&sbi->s_md_lock);
-	INIT_LIST_HEAD(&sbi->s_active_transaction);
-	INIT_LIST_HEAD(&sbi->s_closed_transaction);
-	INIT_LIST_HEAD(&sbi->s_committed_transaction);
 	spin_lock_init(&sbi->s_bal_lock);
 
 	sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN;
@@ -2554,6 +2551,8 @@ int ext4_mb_init(struct super_block *sb, int needs_recovery)
 	ext4_mb_init_per_dev_proc(sb);
 	ext4_mb_history_init(sb);
 
+	sbi->s_journal->j_commit_callback = release_blocks_on_commit;
+
 	printk(KERN_INFO "EXT4-fs: mballoc enabled\n");
 	return 0;
 }
@@ -2583,15 +2582,6 @@ int ext4_mb_release(struct super_block *sb)
 	struct ext4_group_info *grinfo;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
-	/* release freed, non-committed blocks */
-	spin_lock(&sbi->s_md_lock);
-	list_splice_init(&sbi->s_closed_transaction,
-			&sbi->s_committed_transaction);
-	list_splice_init(&sbi->s_active_transaction,
-			&sbi->s_committed_transaction);
-	spin_unlock(&sbi->s_md_lock);
-	ext4_mb_free_committed_blocks(sb);
-
 	if (sbi->s_group_info) {
 		for (i = 0; i < sbi->s_groups_count; i++) {
 			grinfo = ext4_get_group_info(sb, i);
@@ -2645,36 +2635,25 @@ int ext4_mb_release(struct super_block *sb)
 	return 0;
 }
 
-static noinline_for_stack void
-ext4_mb_free_committed_blocks(struct super_block *sb)
+/*
+ * This function is called by the jbd2 layer once the commit has finished,
+ * so we know we can free the blocks that were released with that commit.
+ */
+static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 {
+	struct super_block *sb = journal->j_private;
 	struct ext4_buddy e4b;
 	struct ext4_group_info *db;
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	int err, count = 0, count2 = 0;
 	struct ext4_free_data *entry;
 	ext4_fsblk_t discard_block;
+	struct list_head *l, *ltmp;
 
-	if (list_empty(&sbi->s_committed_transaction))
-		return;
-
-	/* there is committed blocks to be freed yet */
-	do {
-		/* get next array of blocks */
-		entry = NULL;
-		spin_lock(&sbi->s_md_lock);
-		if (!list_empty(&sbi->s_committed_transaction)) {
-			entry = list_entry(sbi->s_committed_transaction.next,
-					struct ext4_free_data, list);
-			list_del(&entry->list);
-		}
-		spin_unlock(&sbi->s_md_lock);
-
-		if (entry == NULL)
-			break;
+	list_for_each_safe(l, ltmp, &txn->t_private_list) {
+		entry = list_entry(l, struct ext4_free_data, list);
 
 		mb_debug("gonna free %u blocks in group %lu (0x%p):",
-				entry->count, entry->group, entry);
+			 entry->count, entry->group, entry);
 
 		err = ext4_mb_load_buddy(sb, entry->group, &e4b);
 		/* we expect to find existing buddy because it's pinned */
@@ -2706,7 +2685,7 @@ ext4_mb_free_committed_blocks(struct super_block *sb)
 
 		kmem_cache_free(ext4_free_ext_cachep, entry);
 		ext4_mb_release_desc(&e4b);
-	} while (1);
+	}
 
 	mb_debug("freed %u blocks in %u structures\n", count, count2);
 }
@@ -4348,8 +4327,6 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 		goto out1;
 	}
 
-	ext4_mb_poll_new_transaction(sb, handle);
-
 	*errp = ext4_mb_initialize_context(ac, ar);
 	if (*errp) {
 		ar->len = 0;
@@ -4408,36 +4385,6 @@ out1:
 
 	return block;
 }
-static void ext4_mb_poll_new_transaction(struct super_block *sb,
-						handle_t *handle)
-{
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-
-	if (sbi->s_last_transaction == handle->h_transaction->t_tid)
-		return;
-
-	/* new transaction! time to close last one and free blocks for
-	 * committed transaction. we know that only transaction can be
-	 * active, so previos transaction can be being logged and we
-	 * know that transaction before previous is known to be already
-	 * logged. this means that now we may free blocks freed in all
-	 * transactions before previous one. hope I'm clear enough ... */
-
-	spin_lock(&sbi->s_md_lock);
-	if (sbi->s_last_transaction != handle->h_transaction->t_tid) {
-		mb_debug("new transaction %lu, old %lu\n",
-				(unsigned long) handle->h_transaction->t_tid,
-				(unsigned long) sbi->s_last_transaction);
-		list_splice_init(&sbi->s_closed_transaction,
-				&sbi->s_committed_transaction);
-		list_splice_init(&sbi->s_active_transaction,
-				&sbi->s_closed_transaction);
-		sbi->s_last_transaction = handle->h_transaction->t_tid;
-	}
-	spin_unlock(&sbi->s_md_lock);
-
-	ext4_mb_free_committed_blocks(sb);
-}
 
 /*
  * We can merge two free data extents only if the physical blocks
@@ -4531,9 +4478,9 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 			kmem_cache_free(ext4_free_ext_cachep, entry);
 		}
 	}
-	/* Add the extent to active_transaction list */
+	/* Add the extent to transaction's private list */
 	spin_lock(&sbi->s_md_lock);
-	list_add(&new_entry->list, &sbi->s_active_transaction);
+	list_add(&new_entry->list, &handle->h_transaction->t_private_list);
 	spin_unlock(&sbi->s_md_lock);
 	ext4_unlock_group(sb, group);
 	return 0;
@@ -4562,8 +4509,6 @@ void ext4_mb_free_blocks(handle_t *handle, struct inode *inode,
 
 	*freed = 0;
 
-	ext4_mb_poll_new_transaction(sb, handle);
-
 	sbi = EXT4_SB(sb);
 	es = EXT4_SB(sb)->s_es;
 	if (block < le32_to_cpu(es->s_first_data_block) ||
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 94cb7b9fe3ee..b5dff1fff1e5 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -269,8 +269,6 @@ struct buffer_head *read_block_bitmap(struct super_block *, ext4_group_t);
 
 static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 					ext4_group_t group);
-static void ext4_mb_poll_new_transaction(struct super_block *, handle_t *);
-static void ext4_mb_free_committed_blocks(struct super_block *);
 static void ext4_mb_return_to_preallocation(struct inode *inode,
 					struct ext4_buddy *e4b, sector_t block,
 					int count);
@@ -278,6 +276,7 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *,
 			struct super_block *, struct ext4_prealloc_space *pa);
 static int ext4_mb_init_per_dev_proc(struct super_block *sb);
 static int ext4_mb_destroy_per_dev_proc(struct super_block *sb);
+static void release_blocks_on_commit(journal_t *journal, transaction_t *txn);
 
 
 static inline void ext4_lock_group(struct super_block *sb, ext4_group_t group)
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 0abe02c4242a..8b119e16aa36 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -995,6 +995,9 @@ restart_loop:
 	}
 	spin_unlock(&journal->j_list_lock);
 
+	if (journal->j_commit_callback)
+		journal->j_commit_callback(journal, commit_transaction);
+
 	trace_mark(jbd2_end_commit, "dev %s transaction %d head %d",
 		   journal->j_devname, commit_transaction->t_tid,
 		   journal->j_tail_sequence);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index e5d540588fa9..39b7805a599a 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -52,6 +52,7 @@ jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
 	transaction->t_expires = jiffies + journal->j_commit_interval;
 	spin_lock_init(&transaction->t_handle_lock);
 	INIT_LIST_HEAD(&transaction->t_inode_list);
+	INIT_LIST_HEAD(&transaction->t_private_list);
 
 	/* Set up the commit timer for the new transaction. */
 	journal->j_commit_timer.expires = round_jiffies(transaction->t_expires);
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 463d6f10b64f..c7d106ef22e2 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -641,6 +641,11 @@ struct transaction_s
 	 */
 	int t_handle_count;
 
+	/*
+	 * For use by the filesystem to store fs-specific data
+	 * structures associated with the transaction
+	 */
+	struct list_head	t_private_list;
 };
 
 struct transaction_run_stats_s {
@@ -935,6 +940,10 @@ struct journal_s
 
 	pid_t			j_last_sync_writer;
 
+	/* This function is called when a transaction is closed */
+	void			(*j_commit_callback)(journal_t *,
+						     transaction_t *);
+
 	/*
 	 * Journal statistics
 	 */
-- 
cgit v1.2.3


From 54514a70adefe356afe854e2d3912d46668068e6 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Tue, 23 Sep 2008 22:15:57 -0700
Subject: softirq: Add support for triggering softirq work on softirqs.

This is basically a genericization of Jens Axboe's block layer
remote softirq changes.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 include/linux/interrupt.h |  21 ++++++++
 include/linux/smp.h       |   4 +-
 kernel/softirq.c          | 129 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 153 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 54b3623434ec..35a61dc60d51 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -11,6 +11,8 @@
 #include <linux/hardirq.h>
 #include <linux/sched.h>
 #include <linux/irqflags.h>
+#include <linux/smp.h>
+#include <linux/percpu.h>
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
 #include <asm/system.h>
@@ -273,6 +275,25 @@ extern void softirq_init(void);
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
 
+/* This is the worklist that queues up per-cpu softirq work.
+ *
+ * send_remote_sendirq() adds work to these lists, and
+ * the softirq handler itself dequeues from them.  The queues
+ * are protected by disabling local cpu interrupts and they must
+ * only be accessed by the local cpu that they are for.
+ */
+DECLARE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
+
+/* Try to send a softirq to a remote cpu.  If this cannot be done, the
+ * work will be queued to the local cpu.
+ */
+extern void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq);
+
+/* Like send_remote_softirq(), but the caller must disable local cpu interrupts
+ * and compute the current cpu, passed in as 'this_cpu'.
+ */
+extern void __send_remote_softirq(struct call_single_data *cp, int cpu,
+				  int this_cpu, int softirq);
 
 /* Tasklets --- multithreaded analogue of BHs.
 
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 66484d4a8459..2e4d58b26c06 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -7,6 +7,7 @@
  */
 
 #include <linux/errno.h>
+#include <linux/types.h>
 #include <linux/list.h>
 #include <linux/cpumask.h>
 
@@ -16,7 +17,8 @@ struct call_single_data {
 	struct list_head list;
 	void (*func) (void *info);
 	void *info;
-	unsigned int flags;
+	u16 flags;
+	u16 priv;
 };
 
 #ifdef CONFIG_SMP
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 37d67aa2d56f..83ba21a13bd4 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -6,6 +6,8 @@
  *	Distribute under GPLv2.
  *
  *	Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
+ *
+ *	Remote softirq infrastructure is by Jens Axboe.
  */
 
 #include <linux/module.h>
@@ -474,17 +476,144 @@ void tasklet_kill(struct tasklet_struct *t)
 
 EXPORT_SYMBOL(tasklet_kill);
 
+DEFINE_PER_CPU(struct list_head [NR_SOFTIRQS], softirq_work_list);
+EXPORT_PER_CPU_SYMBOL(softirq_work_list);
+
+static void __local_trigger(struct call_single_data *cp, int softirq)
+{
+	struct list_head *head = &__get_cpu_var(softirq_work_list[softirq]);
+
+	list_add_tail(&cp->list, head);
+
+	/* Trigger the softirq only if the list was previously empty.  */
+	if (head->next == &cp->list)
+		raise_softirq_irqoff(softirq);
+}
+
+#ifdef CONFIG_USE_GENERIC_SMP_HELPERS
+static void remote_softirq_receive(void *data)
+{
+	struct call_single_data *cp = data;
+	unsigned long flags;
+	int softirq;
+
+	softirq = cp->priv;
+
+	local_irq_save(flags);
+	__local_trigger(cp, softirq);
+	local_irq_restore(flags);
+}
+
+static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
+{
+	if (cpu_online(cpu)) {
+		cp->func = remote_softirq_receive;
+		cp->info = cp;
+		cp->flags = 0;
+		cp->priv = softirq;
+
+		__smp_call_function_single(cpu, cp);
+		return 0;
+	}
+	return 1;
+}
+#else /* CONFIG_USE_GENERIC_SMP_HELPERS */
+static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
+{
+	return 1;
+}
+#endif
+
+/**
+ * __send_remote_softirq - try to schedule softirq work on a remote cpu
+ * @cp: private SMP call function data area
+ * @cpu: the remote cpu
+ * @this_cpu: the currently executing cpu
+ * @softirq: the softirq for the work
+ *
+ * Attempt to schedule softirq work on a remote cpu.  If this cannot be
+ * done, the work is instead queued up on the local cpu.
+ *
+ * Interrupts must be disabled.
+ */
+void __send_remote_softirq(struct call_single_data *cp, int cpu, int this_cpu, int softirq)
+{
+	if (cpu == this_cpu || __try_remote_softirq(cp, cpu, softirq))
+		__local_trigger(cp, softirq);
+}
+EXPORT_SYMBOL(__send_remote_softirq);
+
+/**
+ * send_remote_softirq - try to schedule softirq work on a remote cpu
+ * @cp: private SMP call function data area
+ * @cpu: the remote cpu
+ * @softirq: the softirq for the work
+ *
+ * Like __send_remote_softirq except that disabling interrupts and
+ * computing the current cpu is done for the caller.
+ */
+void send_remote_softirq(struct call_single_data *cp, int cpu, int softirq)
+{
+	unsigned long flags;
+	int this_cpu;
+
+	local_irq_save(flags);
+	this_cpu = smp_processor_id();
+	__send_remote_softirq(cp, cpu, this_cpu, softirq);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(send_remote_softirq);
+
+static int __cpuinit remote_softirq_cpu_notify(struct notifier_block *self,
+					       unsigned long action, void *hcpu)
+{
+	/*
+	 * If a CPU goes away, splice its entries to the current CPU
+	 * and trigger a run of the softirq
+	 */
+	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
+		int cpu = (unsigned long) hcpu;
+		int i;
+
+		local_irq_disable();
+		for (i = 0; i < NR_SOFTIRQS; i++) {
+			struct list_head *head = &per_cpu(softirq_work_list[i], cpu);
+			struct list_head *local_head;
+
+			if (list_empty(head))
+				continue;
+
+			local_head = &__get_cpu_var(softirq_work_list[i]);
+			list_splice_init(head, local_head);
+			raise_softirq_irqoff(i);
+		}
+		local_irq_enable();
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata remote_softirq_cpu_notifier = {
+	.notifier_call	= remote_softirq_cpu_notify,
+};
+
 void __init softirq_init(void)
 {
 	int cpu;
 
 	for_each_possible_cpu(cpu) {
+		int i;
+
 		per_cpu(tasklet_vec, cpu).tail =
 			&per_cpu(tasklet_vec, cpu).head;
 		per_cpu(tasklet_hi_vec, cpu).tail =
 			&per_cpu(tasklet_hi_vec, cpu).head;
+		for (i = 0; i < NR_SOFTIRQS; i++)
+			INIT_LIST_HEAD(&per_cpu(softirq_work_list[i], cpu));
 	}
 
+	register_hotcpu_notifier(&remote_softirq_cpu_notifier);
+
 	open_softirq(TASKLET_SOFTIRQ, tasklet_action);
 	open_softirq(HI_SOFTIRQ, tasklet_hi_action);
 }
-- 
cgit v1.2.3


From 8677142710516d986d932d6f1fba7be8382c1fec Mon Sep 17 00:00:00 2001
From: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Date: Mon, 13 Oct 2008 14:19:05 +0200
Subject: block: fix nr_phys_segments miscalculation bug

This fixes the bug reported by Nikanth Karthikesan <knikanth@suse.de>:

http://lkml.org/lkml/2008/10/2/203

The root cause of the bug is that blk_phys_contig_segment
miscalculates q->max_segment_size.

blk_phys_contig_segment checks:

req->biotail->bi_size + next_req->bio->bi_size > q->max_segment_size

But blk_recalc_rq_segments might expect that req->biotail and the
previous bio in the req are supposed be merged into one
segment. blk_recalc_rq_segments might also expect that next_req->bio
and the next bio in the next_req are supposed be merged into one
segment. In such case, we merge two requests that can't be merged
here. Later, blk_rq_map_sg gives more segments than it should.

We need to keep track of segment size in blk_recalc_rq_segments and
use it to see if two requests can be merged. This patch implements it
in the similar way that we used to do for hw merging (virtual
merging).

Signed-off-by: FUJITA Tomonori <fujita.tomonori@lab.ntt.co.jp>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-merge.c   | 20 ++++++++++++++++++--
 include/linux/bio.h |  7 +++++++
 2 files changed, 25 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 908d3e11ac52..8681cd6f9911 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -77,12 +77,20 @@ void blk_recalc_rq_segments(struct request *rq)
 			continue;
 		}
 new_segment:
+		if (nr_phys_segs == 1 && seg_size > rq->bio->bi_seg_front_size)
+			rq->bio->bi_seg_front_size = seg_size;
+
 		nr_phys_segs++;
 		bvprv = bv;
 		seg_size = bv->bv_len;
 		highprv = high;
 	}
 
+	if (nr_phys_segs == 1 && seg_size > rq->bio->bi_seg_front_size)
+		rq->bio->bi_seg_front_size = seg_size;
+	if (seg_size > rq->biotail->bi_seg_back_size)
+		rq->biotail->bi_seg_back_size = seg_size;
+
 	rq->nr_phys_segments = nr_phys_segs;
 }
 
@@ -106,7 +114,8 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 	if (!test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
 		return 0;
 
-	if (bio->bi_size + nxt->bi_size > q->max_segment_size)
+	if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
+	    q->max_segment_size)
 		return 0;
 
 	if (!bio_has_data(bio))
@@ -309,6 +318,8 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 				struct request *next)
 {
 	int total_phys_segments;
+	unsigned int seg_size =
+		req->biotail->bi_seg_back_size + next->bio->bi_seg_front_size;
 
 	/*
 	 * First check if the either of the requests are re-queued
@@ -324,8 +335,13 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 		return 0;
 
 	total_phys_segments = req->nr_phys_segments + next->nr_phys_segments;
-	if (blk_phys_contig_segment(q, req->biotail, next->bio))
+	if (blk_phys_contig_segment(q, req->biotail, next->bio)) {
+		if (req->nr_phys_segments == 1)
+			req->bio->bi_seg_front_size = seg_size;
+		if (next->nr_phys_segments == 1)
+			next->biotail->bi_seg_back_size = seg_size;
 		total_phys_segments--;
+	}
 
 	if (total_phys_segments > q->max_phys_segments)
 		return 0;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index ff5b4cf9e2da..dc3cec386a99 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -79,6 +79,13 @@ struct bio {
 
 	unsigned int		bi_size;	/* residual I/O count */
 
+	/*
+	 * To keep track of the max segment size, we account for the
+	 * sizes of the first and last mergeable segments in this bio.
+	 */
+	unsigned int		bi_seg_front_size;
+	unsigned int		bi_seg_back_size;
+
 	unsigned int		bi_max_vecs;	/* max bvl_vecs we can hold */
 
 	unsigned int		bi_comp_cpu;	/* completion CPU */
-- 
cgit v1.2.3


From 756f8243188e013bd067811cdc0cc60760abfdf9 Mon Sep 17 00:00:00 2001
From: Stefan Raspl <raspl@linux.vnet.ibm.com>
Date: Thu, 16 Oct 2008 08:23:21 +0200
Subject: blktrace: add support for driver data

This patch adds the new api call blk_add_driver_data() to blktrace.
It allows to trace device driver-specific binary data.

Signed-off-by: Stefan Raspl <raspl@linux.vnet.ibm.com>
Signed-off-by: Martin Peschke <mp3@de.ibm.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 include/linux/blktrace_api.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

(limited to 'include')

diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 3a31eb506164..bdf505d33e77 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -24,6 +24,7 @@ enum blktrace_cat {
 	BLK_TC_AHEAD	= 1 << 11,	/* readahead */
 	BLK_TC_META	= 1 << 12,	/* metadata */
 	BLK_TC_DISCARD	= 1 << 13,	/* discard requests */
+	BLK_TC_DRV_DATA	= 1 << 14,	/* binary per-driver data */
 
 	BLK_TC_END	= 1 << 15,	/* only 16-bits, reminder */
 };
@@ -51,6 +52,7 @@ enum blktrace_act {
 	__BLK_TA_BOUNCE,		/* bio was bounced */
 	__BLK_TA_REMAP,			/* bio was remapped */
 	__BLK_TA_ABORT,			/* request aborted */
+	__BLK_TA_DRV_DATA,		/* driver-specific binary data */
 };
 
 /*
@@ -82,6 +84,7 @@ enum blktrace_notify {
 #define BLK_TA_BOUNCE		(__BLK_TA_BOUNCE)
 #define BLK_TA_REMAP		(__BLK_TA_REMAP | BLK_TC_ACT(BLK_TC_QUEUE))
 #define BLK_TA_ABORT		(__BLK_TA_ABORT | BLK_TC_ACT(BLK_TC_QUEUE))
+#define BLK_TA_DRV_DATA	(__BLK_TA_DRV_DATA | BLK_TC_ACT(BLK_TC_DRV_DATA))
 
 #define BLK_TN_PROCESS		(__BLK_TN_PROCESS | BLK_TC_ACT(BLK_TC_NOTIFY))
 #define BLK_TN_TIMESTAMP	(__BLK_TN_TIMESTAMP | BLK_TC_ACT(BLK_TC_NOTIFY))
@@ -317,6 +320,34 @@ static inline void blk_add_trace_remap(struct request_queue *q, struct bio *bio,
 	__blk_add_trace(bt, from, bio->bi_size, bio->bi_rw, BLK_TA_REMAP, !bio_flagged(bio, BIO_UPTODATE), sizeof(r), &r);
 }
 
+/**
+ * blk_add_driver_data - Add binary message with driver-specific data
+ * @q:		queue the io is for
+ * @rq:		io request
+ * @data:	driver-specific data
+ * @len:	length of driver-specific data
+ *
+ * Description:
+ *     Some drivers might want to write driver-specific data per request.
+ *
+ **/
+static inline void blk_add_driver_data(struct request_queue *q,
+				       struct request *rq,
+				       void *data, size_t len)
+{
+	struct blk_trace *bt = q->blk_trace;
+
+	if (likely(!bt))
+		return;
+
+	if (blk_pc_request(rq))
+		__blk_add_trace(bt, 0, rq->data_len, 0, BLK_TA_DRV_DATA,
+				rq->errors, len, data);
+	else
+		__blk_add_trace(bt, rq->hard_sector, rq->hard_nr_sectors << 9,
+				0, BLK_TA_DRV_DATA, rq->errors, len, data);
+}
+
 extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 			   char __user *arg);
 extern int blk_trace_startstop(struct request_queue *q, int start);
@@ -330,6 +361,7 @@ extern int blk_trace_remove(struct request_queue *q);
 #define blk_add_trace_generic(q, rq, rw, what)	do { } while (0)
 #define blk_add_trace_pdu_int(q, what, bio, pdu)	do { } while (0)
 #define blk_add_trace_remap(q, bio, dev, f, t)	do {} while (0)
+#define blk_add_driver_data(q, rq, data, len)	do {} while (0)
 #define do_blk_trace_setup(q, name, dev, buts)	(-ENOTTY)
 #define blk_trace_setup(q, name, dev, arg)	(-ENOTTY)
 #define blk_trace_startstop(q, start)		(-ENOTTY)
-- 
cgit v1.2.3


From 3481f21097cb560392c411377893b5109fbde557 Mon Sep 17 00:00:00 2001
From: Youquan Song <youquan.song@intel.com>
Date: Thu, 16 Oct 2008 16:31:55 -0700
Subject: dmar: context cache and IOTLB invalidation using queued invalidation

Implement context cache invalidate and IOTLB invalidation using
queued invalidation interface. This interface will be used by
DMA remapping, when queued invalidation is supported.

Signed-off-by: Youquan Song <youquan.song@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/pci/dmar.c          | 56 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/intel-iommu.h | 21 +++++++++++++++++
 2 files changed, 77 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index b64cec190542..0f409e23631e 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -645,6 +645,62 @@ void qi_global_iec(struct intel_iommu *iommu)
 	qi_submit_sync(&desc, iommu);
 }
 
+int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
+		     u64 type, int non_present_entry_flush)
+{
+
+	struct qi_desc desc;
+
+	if (non_present_entry_flush) {
+		if (!cap_caching_mode(iommu->cap))
+			return 1;
+		else
+			did = 0;
+	}
+
+	desc.low = QI_CC_FM(fm) | QI_CC_SID(sid) | QI_CC_DID(did)
+			| QI_CC_GRAN(type) | QI_CC_TYPE;
+	desc.high = 0;
+
+	qi_submit_sync(&desc, iommu);
+
+	return 0;
+
+}
+
+int qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
+		   unsigned int size_order, u64 type,
+		   int non_present_entry_flush)
+{
+	u8 dw = 0, dr = 0;
+
+	struct qi_desc desc;
+	int ih = 0;
+
+	if (non_present_entry_flush) {
+		if (!cap_caching_mode(iommu->cap))
+			return 1;
+		else
+			did = 0;
+	}
+
+	if (cap_write_drain(iommu->cap))
+		dw = 1;
+
+	if (cap_read_drain(iommu->cap))
+		dr = 1;
+
+	desc.low = QI_IOTLB_DID(did) | QI_IOTLB_DR(dr) | QI_IOTLB_DW(dw)
+		| QI_IOTLB_GRAN(type) | QI_IOTLB_TYPE;
+	desc.high = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
+		| QI_IOTLB_AM(size_order);
+
+	qi_submit_sync(&desc, iommu);
+
+	return 0;
+
+}
+
 /*
  * Enable Queued Invalidation interface. This is a must to support
  * interrupt-remapping. Also used by DMA-remapping, which replaces
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 2e117f30a76c..0c5f5e49107b 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -127,6 +127,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 
 
 /* IOTLB_REG */
+#define DMA_TLB_FLUSH_GRANU_OFFSET  60
 #define DMA_TLB_GLOBAL_FLUSH (((u64)1) << 60)
 #define DMA_TLB_DSI_FLUSH (((u64)2) << 60)
 #define DMA_TLB_PSI_FLUSH (((u64)3) << 60)
@@ -140,6 +141,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define DMA_TLB_MAX_SIZE (0x3f)
 
 /* INVALID_DESC */
+#define DMA_CCMD_INVL_GRANU_OFFSET  61
 #define DMA_ID_TLB_GLOBAL_FLUSH	(((u64)1) << 3)
 #define DMA_ID_TLB_DSI_FLUSH	(((u64)2) << 3)
 #define DMA_ID_TLB_PSI_FLUSH	(((u64)3) << 3)
@@ -238,6 +240,19 @@ enum {
 #define QI_IWD_STATUS_DATA(d)	(((u64)d) << 32)
 #define QI_IWD_STATUS_WRITE	(((u64)1) << 5)
 
+#define QI_IOTLB_DID(did) 	(((u64)did) << 16)
+#define QI_IOTLB_DR(dr) 	(((u64)dr) << 7)
+#define QI_IOTLB_DW(dw) 	(((u64)dw) << 6)
+#define QI_IOTLB_GRAN(gran) 	(((u64)gran) >> (DMA_TLB_FLUSH_GRANU_OFFSET-4))
+#define QI_IOTLB_ADDR(addr)	(((u64)addr) & PAGE_MASK_4K)
+#define QI_IOTLB_IH(ih)		(((u64)ih) << 6)
+#define QI_IOTLB_AM(am)		(((u8)am))
+
+#define QI_CC_FM(fm)		(((u64)fm) << 48)
+#define QI_CC_SID(sid)		(((u64)sid) << 32)
+#define QI_CC_DID(did)		(((u64)did) << 16)
+#define QI_CC_GRAN(gran)	(((u64)gran) >> (DMA_CCMD_INVL_GRANU_OFFSET-4))
+
 struct qi_desc {
 	u64 low, high;
 };
@@ -303,6 +318,12 @@ extern void free_iommu(struct intel_iommu *iommu);
 extern int dmar_enable_qi(struct intel_iommu *iommu);
 extern void qi_global_iec(struct intel_iommu *iommu);
 
+extern int qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid,
+			        u8 fm, u64 type, int non_present_entry_flush);
+extern int qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
+			  unsigned int size_order, u64 type,
+			  int non_present_entry_flush);
+
 extern void qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu);
 
 void intel_iommu_domain_exit(struct dmar_domain *domain);
-- 
cgit v1.2.3


From a77b67d4023770805141014b8fa9eb5467457817 Mon Sep 17 00:00:00 2001
From: Youquan Song <youquan.song@intel.com>
Date: Thu, 16 Oct 2008 16:31:56 -0700
Subject: dmar: Use queued invalidation interface for IOTLB and context
 invalidation

If queued invalidation interface is available and enabled, queued invalidation
interface will be used instead of the register based interface.

According to Vt-d2 specification, when queued invalidation is enabled,
invalidation command submit works only through invalidation queue and not
through the command registers interface.

Signed-off-by: Youquan Song <youquan.song@intel.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/pci/intel-iommu.c   | 95 +++++++++++++++++++++------------------------
 include/linux/intel-iommu.h |  8 ++++
 2 files changed, 53 insertions(+), 50 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index fc5f2dbf5323..509470419130 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -567,27 +567,6 @@ static int __iommu_flush_context(struct intel_iommu *iommu,
 	return 0;
 }
 
-static int inline iommu_flush_context_global(struct intel_iommu *iommu,
-	int non_present_entry_flush)
-{
-	return __iommu_flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL,
-		non_present_entry_flush);
-}
-
-static int inline iommu_flush_context_domain(struct intel_iommu *iommu, u16 did,
-	int non_present_entry_flush)
-{
-	return __iommu_flush_context(iommu, did, 0, 0, DMA_CCMD_DOMAIN_INVL,
-		non_present_entry_flush);
-}
-
-static int inline iommu_flush_context_device(struct intel_iommu *iommu,
-	u16 did, u16 source_id, u8 function_mask, int non_present_entry_flush)
-{
-	return __iommu_flush_context(iommu, did, source_id, function_mask,
-		DMA_CCMD_DEVICE_INVL, non_present_entry_flush);
-}
-
 /* return value determine if we need a write buffer flush */
 static int __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
 	u64 addr, unsigned int size_order, u64 type,
@@ -660,20 +639,6 @@ static int __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
 	return 0;
 }
 
-static int inline iommu_flush_iotlb_global(struct intel_iommu *iommu,
-	int non_present_entry_flush)
-{
-	return __iommu_flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH,
-		non_present_entry_flush);
-}
-
-static int inline iommu_flush_iotlb_dsi(struct intel_iommu *iommu, u16 did,
-	int non_present_entry_flush)
-{
-	return __iommu_flush_iotlb(iommu, did, 0, 0, DMA_TLB_DSI_FLUSH,
-		non_present_entry_flush);
-}
-
 static int iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
 	u64 addr, unsigned int pages, int non_present_entry_flush)
 {
@@ -684,8 +649,9 @@ static int iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
 
 	/* Fallback to domain selective flush if no PSI support */
 	if (!cap_pgsel_inv(iommu->cap))
-		return iommu_flush_iotlb_dsi(iommu, did,
-			non_present_entry_flush);
+		return iommu->flush.flush_iotlb(iommu, did, 0, 0,
+						DMA_TLB_DSI_FLUSH,
+						non_present_entry_flush);
 
 	/*
 	 * PSI requires page size to be 2 ^ x, and the base address is naturally
@@ -694,11 +660,12 @@ static int iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
 	mask = ilog2(__roundup_pow_of_two(pages));
 	/* Fallback to domain selective flush if size is too big */
 	if (mask > cap_max_amask_val(iommu->cap))
-		return iommu_flush_iotlb_dsi(iommu, did,
-			non_present_entry_flush);
+		return iommu->flush.flush_iotlb(iommu, did, 0, 0,
+			DMA_TLB_DSI_FLUSH, non_present_entry_flush);
 
-	return __iommu_flush_iotlb(iommu, did, addr, mask,
-		DMA_TLB_PSI_FLUSH, non_present_entry_flush);
+	return iommu->flush.flush_iotlb(iommu, did, addr, mask,
+					DMA_TLB_PSI_FLUSH,
+					non_present_entry_flush);
 }
 
 static void iommu_disable_protect_mem_regions(struct intel_iommu *iommu)
@@ -1204,11 +1171,13 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	__iommu_flush_cache(iommu, context, sizeof(*context));
 
 	/* it's a non-present to present mapping */
-	if (iommu_flush_context_device(iommu, domain->id,
-			(((u16)bus) << 8) | devfn, DMA_CCMD_MASK_NOBIT, 1))
+	if (iommu->flush.flush_context(iommu, domain->id,
+		(((u16)bus) << 8) | devfn, DMA_CCMD_MASK_NOBIT,
+		DMA_CCMD_DEVICE_INVL, 1))
 		iommu_flush_write_buffer(iommu);
 	else
-		iommu_flush_iotlb_dsi(iommu, 0, 0);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_DSI_FLUSH, 0);
+
 	spin_unlock_irqrestore(&iommu->lock, flags);
 	return 0;
 }
@@ -1310,8 +1279,10 @@ domain_page_mapping(struct dmar_domain *domain, dma_addr_t iova,
 static void detach_domain_for_dev(struct dmar_domain *domain, u8 bus, u8 devfn)
 {
 	clear_context_table(domain->iommu, bus, devfn);
-	iommu_flush_context_global(domain->iommu, 0);
-	iommu_flush_iotlb_global(domain->iommu, 0);
+	domain->iommu->flush.flush_context(domain->iommu, 0, 0, 0,
+					   DMA_CCMD_GLOBAL_INVL, 0);
+	domain->iommu->flush.flush_iotlb(domain->iommu, 0, 0, 0,
+					 DMA_TLB_GLOBAL_FLUSH, 0);
 }
 
 static void domain_remove_dev_info(struct dmar_domain *domain)
@@ -1662,6 +1633,28 @@ int __init init_dmars(void)
 		}
 	}
 
+	for_each_drhd_unit(drhd) {
+		if (drhd->ignored)
+			continue;
+
+		iommu = drhd->iommu;
+		if (dmar_enable_qi(iommu)) {
+			/*
+			 * Queued Invalidate not enabled, use Register Based
+			 * Invalidate
+			 */
+			iommu->flush.flush_context = __iommu_flush_context;
+			iommu->flush.flush_iotlb = __iommu_flush_iotlb;
+			printk(KERN_INFO "IOMMU 0x%Lx: using Register based "
+			       "invalidation\n", drhd->reg_base_addr);
+		} else {
+			iommu->flush.flush_context = qi_flush_context;
+			iommu->flush.flush_iotlb = qi_flush_iotlb;
+			printk(KERN_INFO "IOMMU 0x%Lx: using Queued "
+			       "invalidation\n", drhd->reg_base_addr);
+		}
+	}
+
 	/*
 	 * For each rmrr
 	 *   for each dev attached to rmrr
@@ -1714,9 +1707,10 @@ int __init init_dmars(void)
 
 		iommu_set_root_entry(iommu);
 
-		iommu_flush_context_global(iommu, 0);
-		iommu_flush_iotlb_global(iommu, 0);
-
+		iommu->flush.flush_context(iommu, 0, 0, 0, DMA_CCMD_GLOBAL_INVL,
+					   0);
+		iommu->flush.flush_iotlb(iommu, 0, 0, 0, DMA_TLB_GLOBAL_FLUSH,
+					 0);
 		iommu_disable_protect_mem_regions(iommu);
 
 		ret = iommu_enable_translation(iommu);
@@ -1891,7 +1885,8 @@ static void flush_unmaps(void)
 			struct intel_iommu *iommu =
 				deferred_flush[i].domain[0]->iommu;
 
-			iommu_flush_iotlb_global(iommu, 0);
+			iommu->flush.flush_iotlb(iommu, 0, 0, 0,
+						 DMA_TLB_GLOBAL_FLUSH, 0);
 			for (j = 0; j < deferred_flush[i].next; j++) {
 				__free_iova(&deferred_flush[i].domain[j]->iovad,
 						deferred_flush[i].iova[j]);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 0c5f5e49107b..afb0d2a5b7cd 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -278,6 +278,13 @@ struct ir_table {
 };
 #endif
 
+struct iommu_flush {
+	int (*flush_context)(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
+		u64 type, int non_present_entry_flush);
+	int (*flush_iotlb)(struct intel_iommu *iommu, u16 did, u64 addr,
+		unsigned int size_order, u64 type, int non_present_entry_flush);
+};
+
 struct intel_iommu {
 	void __iomem	*reg; /* Pointer to hardware regs, virtual addr */
 	u64		cap;
@@ -297,6 +304,7 @@ struct intel_iommu {
 	unsigned char name[7];    /* Device Name */
 	struct msi_msg saved_msg;
 	struct sys_device sysdev;
+	struct iommu_flush flush;
 #endif
 	struct q_inval  *qi;            /* Queued invalidation info */
 #ifdef CONFIG_INTR_REMAP
-- 
cgit v1.2.3


From f73e2d13a16cc88c4faa4729967f92bfeec8a142 Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Fri, 17 Oct 2008 14:03:08 +0200
Subject: block: remove __generic_unplug_device() from exports

The only out-of-core user is IDE, and that should be using
blk_start_queueing() instead.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/blk-core.c       | 1 -
 block/blk.h            | 1 +
 drivers/ide/ide-io.c   | 4 ++--
 include/linux/blkdev.h | 1 -
 4 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/block/blk-core.c b/block/blk-core.c
index fcbd56dd41fa..81a496004976 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -257,7 +257,6 @@ void __generic_unplug_device(struct request_queue *q)
 
 	q->request_fn(q);
 }
-EXPORT_SYMBOL(__generic_unplug_device);
 
 /**
  * generic_unplug_device - fire a request queue
diff --git a/block/blk.h b/block/blk.h
index e5c579769963..d2e49af90db5 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -20,6 +20,7 @@ void blk_unplug_timeout(unsigned long data);
 void blk_rq_timed_out_timer(unsigned long data);
 void blk_delete_timer(struct request *);
 void blk_add_timer(struct request *);
+void __generic_unplug_device(struct request_queue *);
 
 /*
  * Internal atomic flags for request handling
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 77c6eaeacefa..7162d67562af 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -1493,8 +1493,8 @@ void ide_do_drive_cmd(ide_drive_t *drive, struct request *rq)
 
 	spin_lock_irqsave(&ide_lock, flags);
 	hwgroup->rq = NULL;
-	__elv_add_request(drive->queue, rq, ELEVATOR_INSERT_FRONT, 1);
-	__generic_unplug_device(drive->queue);
+	__elv_add_request(drive->queue, rq, ELEVATOR_INSERT_FRONT, 0);
+	blk_start_queueing(drive->queue);
 	spin_unlock_irqrestore(&ide_lock, flags);
 }
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a92d9e4ea96e..8eed8b15f992 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -856,7 +856,6 @@ extern void blk_ordered_complete_seq(struct request_queue *, unsigned, int);
 extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *);
 extern void blk_dump_rq_flags(struct request *, char *);
 extern void generic_unplug_device(struct request_queue *);
-extern void __generic_unplug_device(struct request_queue *);
 extern long nr_blockdev_pages(void);
 
 int blk_get_queue(struct request_queue *);
-- 
cgit v1.2.3


From 8b81ef589ad1483dd977ef47fe00d4ce4d91a0ab Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@ericvh-desktop.austin.ibm.com>
Date: Mon, 13 Oct 2008 18:45:25 -0500
Subject: 9p: consolidate transport structure

Right now there is a transport module structure which provides per-transport
type functions and data and a transport structure which contains per-instance
public data as well as function pointers to instance specific functions.

This patch moves public transport visible instance data to the client
structure (which in some cases had duplicate data) and consolidates the
functions into the transport module structure.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 fs/9p/v9fs.c               |   2 +-
 include/net/9p/client.h    |  19 ++++-
 include/net/9p/transport.h |  55 ++----------
 net/9p/client.c            |  21 ++---
 net/9p/mod.c               |   1 +
 net/9p/trans_fd.c          | 205 ++++++++++++++++++++-------------------------
 net/9p/trans_virtio.c      |  50 +++++------
 7 files changed, 146 insertions(+), 207 deletions(-)

(limited to 'include')

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index c061c3f18e7c..b6b85cf01e0d 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -30,8 +30,8 @@
 #include <linux/parser.h>
 #include <linux/idr.h>
 #include <net/9p/9p.h>
-#include <net/9p/transport.h>
 #include <net/9p/client.h>
+#include <net/9p/transport.h>
 #include "v9fs.h"
 #include "v9fs_vfs.h"
 
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index c936dd14de41..c35fb548e7cf 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -26,6 +26,22 @@
 #ifndef NET_9P_CLIENT_H
 #define NET_9P_CLIENT_H
 
+/**
+ * enum p9_trans_status - different states of underlying transports
+ * @Connected: transport is connected and healthy
+ * @Disconnected: transport has been disconnected
+ * @Hung: transport is connected by wedged
+ *
+ * This enumeration details the various states a transport
+ * instatiation can be in.
+ */
+
+enum p9_trans_status {
+	Connected,
+	Disconnected,
+	Hung,
+};
+
 /**
  * struct p9_client - per client instance state
  * @lock: protect @fidlist
@@ -48,7 +64,8 @@ struct p9_client {
 	int msize;
 	unsigned char dotu;
 	struct p9_trans_module *trans_mod;
-	struct p9_trans *trans;
+	enum p9_trans_status status;
+	void *trans;
 	struct p9_conn *conn;
 
 	struct p9_idpool *fidpool;
diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h
index 3ca737120a90..3e0f2f6beba2 100644
--- a/include/net/9p/transport.h
+++ b/include/net/9p/transport.h
@@ -26,52 +26,6 @@
 #ifndef NET_9P_TRANSPORT_H
 #define NET_9P_TRANSPORT_H
 
-#include <linux/module.h>
-
-/**
- * enum p9_trans_status - different states of underlying transports
- * @Connected: transport is connected and healthy
- * @Disconnected: transport has been disconnected
- * @Hung: transport is connected by wedged
- *
- * This enumeration details the various states a transport
- * instatiation can be in.
- */
-
-enum p9_trans_status {
-	Connected,
-	Disconnected,
-	Hung,
-};
-
-/**
- * struct p9_trans - per-transport state and API
- * @status: transport &p9_trans_status
- * @msize: negotiated maximum packet size (duplicate from client)
- * @extended: negotiated protocol extensions (duplicate from client)
- * @priv: transport private data
- * @close: member function to disconnect and close the transport
- * @rpc: member function to issue a request to the transport
- *
- * This is the basic API for a transport instance.  It is used as
- * a handle by the client to issue requests.  This interface is currently
- * in flux during reorganization.
- *
- * Bugs: there is lots of duplicated data here and its not clear that
- * the member functions need to be per-instance versus per transport
- * module.
- */
-
-struct p9_trans {
-	enum p9_trans_status status;
-	int msize;
-	unsigned char extended;
-	void *priv;
-	void (*close) (struct p9_trans *);
-	int (*rpc) (struct p9_trans *t, struct p9_fcall *tc,
-							struct p9_fcall **rc);
-};
-
 /**
  * struct p9_trans_module - transport module interface
  * @list: used to maintain a list of currently available transports
@@ -79,12 +33,14 @@ struct p9_trans {
  * @maxsize: transport provided maximum packet size
  * @def: set if this transport should be considered the default
  * @create: member function to create a new connection on this transport
+ * @close: member function to disconnect and close the transport
+ * @rpc: member function to issue a request to the transport
  *
  * This is the basic API for a transport module which is registered by the
  * transport module with the 9P core network module and used by the client
  * to instantiate a new connection on a transport.
  *
- * Bugs: the transport module list isn't protected.
+ * BUGS: the transport module list isn't protected.
  */
 
 struct p9_trans_module {
@@ -92,8 +48,11 @@ struct p9_trans_module {
 	char *name;		/* name of transport */
 	int maxsize;		/* max message size of transport */
 	int def;		/* this transport should be default */
-	struct p9_trans * (*create)(const char *, char *, int, unsigned char);
 	struct module *owner;
+	int (*create)(struct p9_client *, const char *, char *);
+	void (*close) (struct p9_client *);
+	int (*rpc) (struct p9_client *t, struct p9_fcall *tc,
+							struct p9_fcall **rc);
 };
 
 void v9fs_register_trans(struct p9_trans_module *m);
diff --git a/net/9p/client.c b/net/9p/client.c
index e053e06028a5..f1a52a7ed724 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -33,8 +33,8 @@
 #include <linux/uaccess.h>
 #include <net/9p/9p.h>
 #include <linux/parser.h>
-#include <net/9p/transport.h>
 #include <net/9p/client.h>
+#include <net/9p/transport.h>
 
 static struct p9_fid *p9_fid_create(struct p9_client *clnt);
 static void p9_fid_destroy(struct p9_fid *fid);
@@ -136,7 +136,7 @@ int
 p9_client_rpc(struct p9_client *c, struct p9_fcall *tc,
 	struct p9_fcall **rc)
 {
-	return c->trans->rpc(c->trans, tc, rc);
+	return c->trans_mod->rpc(c, tc, rc);
 }
 
 struct p9_client *p9_client_create(const char *dev_name, char *options)
@@ -179,13 +179,9 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 		clnt, clnt->trans_mod, clnt->msize, clnt->dotu);
 
 
-	clnt->trans = clnt->trans_mod->create(dev_name, options, clnt->msize,
-								clnt->dotu);
-	if (IS_ERR(clnt->trans)) {
-		err = PTR_ERR(clnt->trans);
-		clnt->trans = NULL;
+	err = clnt->trans_mod->create(clnt, dev_name, options);
+	if (err)
 		goto error;
-	}
 
 	if ((clnt->msize+P9_IOHDRSZ) > clnt->trans_mod->maxsize)
 		clnt->msize = clnt->trans_mod->maxsize-P9_IOHDRSZ;
@@ -233,11 +229,8 @@ void p9_client_destroy(struct p9_client *clnt)
 
 	P9_DPRINTK(P9_DEBUG_9P, "clnt %p\n", clnt);
 
-	if (clnt->trans) {
-		clnt->trans->close(clnt->trans);
-		kfree(clnt->trans);
-		clnt->trans = NULL;
-	}
+	if (clnt->trans_mod)
+		clnt->trans_mod->close(clnt);
 
 	v9fs_put_trans(clnt->trans_mod);
 
@@ -254,7 +247,7 @@ EXPORT_SYMBOL(p9_client_destroy);
 void p9_client_disconnect(struct p9_client *clnt)
 {
 	P9_DPRINTK(P9_DEBUG_9P, "clnt %p\n", clnt);
-	clnt->trans->status = Disconnected;
+	clnt->status = Disconnected;
 }
 EXPORT_SYMBOL(p9_client_disconnect);
 
diff --git a/net/9p/mod.c b/net/9p/mod.c
index 1084feb24cb0..cf8a4128cd5c 100644
--- a/net/9p/mod.c
+++ b/net/9p/mod.c
@@ -29,6 +29,7 @@
 #include <net/9p/9p.h>
 #include <linux/fs.h>
 #include <linux/parser.h>
+#include <net/9p/client.h>
 #include <net/9p/transport.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index f84592345573..d09389f08382 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -39,6 +39,7 @@
 #include <linux/file.h>
 #include <linux/parser.h>
 #include <net/9p/9p.h>
+#include <net/9p/client.h>
 #include <net/9p/transport.h>
 
 #define P9_PORT 564
@@ -146,7 +147,7 @@ struct p9_poll_wait {
  * @mux_list: list link for mux to manage multiple connections (?)
  * @msize: maximum size for connection (dup)
  * @extended: 9p2000.u flag (dup)
- * @trans: reference to transport instance for this connection
+ * @client: reference to client instance for this connection
  * @tagpool: id accounting for transactions
  * @err: error state
  * @req_list: accounting for requests which have been sent
@@ -171,7 +172,7 @@ struct p9_conn {
 	struct list_head mux_list;
 	int msize;
 	unsigned char extended;
-	struct p9_trans *trans;
+	struct p9_client *client;
 	struct p9_idpool *tagpool;
 	int err;
 	struct list_head req_list;
@@ -214,8 +215,8 @@ static void p9_read_work(struct work_struct *work);
 static void p9_write_work(struct work_struct *work);
 static void p9_pollwait(struct file *filp, wait_queue_head_t *wait_address,
 								poll_table *p);
-static int p9_fd_write(struct p9_trans *trans, void *v, int len);
-static int p9_fd_read(struct p9_trans *trans, void *v, int len);
+static int p9_fd_write(struct p9_client *client, void *v, int len);
+static int p9_fd_read(struct p9_client *client, void *v, int len);
 
 static DEFINE_SPINLOCK(p9_poll_lock);
 static LIST_HEAD(p9_poll_pending_list);
@@ -223,7 +224,7 @@ static struct workqueue_struct *p9_mux_wq;
 static struct task_struct *p9_poll_task;
 
 static void p9_conn_destroy(struct p9_conn *);
-static unsigned int p9_fd_poll(struct p9_trans *trans,
+static unsigned int p9_fd_poll(struct p9_client *client,
 						struct poll_table_struct *pt);
 
 #ifdef P9_NONBLOCK
@@ -271,27 +272,26 @@ static void p9_mux_poll_stop(struct p9_conn *m)
 
 /**
  * p9_conn_create - allocate and initialize the per-session mux data
- * @trans: transport structure
+ * @client: client instance
  *
  * Note: Creates the polling task if this is the first session.
  */
 
-static struct p9_conn *p9_conn_create(struct p9_trans *trans)
+static struct p9_conn *p9_conn_create(struct p9_client *client)
 {
 	int i, n;
 	struct p9_conn *m;
 
-	P9_DPRINTK(P9_DEBUG_MUX, "transport %p msize %d\n", trans,
-								trans->msize);
+	P9_DPRINTK(P9_DEBUG_MUX, "client %p msize %d\n", client, client->msize);
 	m = kzalloc(sizeof(struct p9_conn), GFP_KERNEL);
 	if (!m)
 		return ERR_PTR(-ENOMEM);
 
 	spin_lock_init(&m->lock);
 	INIT_LIST_HEAD(&m->mux_list);
-	m->msize = trans->msize;
-	m->extended = trans->extended;
-	m->trans = trans;
+	m->msize = client->msize;
+	m->extended = client->dotu;
+	m->client = client;
 	m->tagpool = p9_idpool_create();
 	if (IS_ERR(m->tagpool)) {
 		kfree(m);
@@ -305,7 +305,7 @@ static struct p9_conn *p9_conn_create(struct p9_trans *trans)
 	INIT_LIST_HEAD(&m->poll_pending_link);
 	init_poll_funcptr(&m->pt, p9_pollwait);
 
-	n = p9_fd_poll(trans, &m->pt);
+	n = p9_fd_poll(client, &m->pt);
 	if (n & POLLIN) {
 		P9_DPRINTK(P9_DEBUG_MUX, "mux %p can read\n", m);
 		set_bit(Rpending, &m->wsched);
@@ -345,7 +345,7 @@ static void p9_conn_destroy(struct p9_conn *m)
 
 	p9_conn_cancel(m, -ECONNRESET);
 
-	m->trans = NULL;
+	m->client = NULL;
 	p9_idpool_destroy(m->tagpool);
 	kfree(m);
 }
@@ -420,7 +420,7 @@ static void p9_poll_mux(struct p9_conn *m)
 	if (m->err < 0)
 		return;
 
-	n = p9_fd_poll(m->trans, NULL);
+	n = p9_fd_poll(m->client, NULL);
 	if (n < 0 || n & (POLLERR | POLLHUP | POLLNVAL)) {
 		P9_DPRINTK(P9_DEBUG_MUX, "error mux %p err %d\n", m, n);
 		if (n >= 0)
@@ -533,7 +533,7 @@ again:
 	P9_DPRINTK(P9_DEBUG_MUX, "mux %p pos %d size %d\n", m, m->wpos,
 								m->wsize);
 	clear_bit(Wpending, &m->wsched);
-	err = p9_fd_write(m->trans, m->wbuf + m->wpos, m->wsize - m->wpos);
+	err = p9_fd_write(m->client, m->wbuf + m->wpos, m->wsize - m->wpos);
 	P9_DPRINTK(P9_DEBUG_MUX, "mux %p sent %d bytes\n", m, err);
 	if (err == -EAGAIN) {
 		clear_bit(Wworksched, &m->wsched);
@@ -555,7 +555,7 @@ again:
 		if (test_and_clear_bit(Wpending, &m->wsched))
 			n = POLLOUT;
 		else
-			n = p9_fd_poll(m->trans, NULL);
+			n = p9_fd_poll(m->client, NULL);
 
 		if (n & POLLOUT) {
 			P9_DPRINTK(P9_DEBUG_MUX, "schedule write work %p\n", m);
@@ -640,7 +640,7 @@ static void p9_read_work(struct work_struct *work)
 	}
 
 	clear_bit(Rpending, &m->wsched);
-	err = p9_fd_read(m->trans, m->rbuf + m->rpos, m->msize - m->rpos);
+	err = p9_fd_read(m->client, m->rbuf + m->rpos, m->msize - m->rpos);
 	P9_DPRINTK(P9_DEBUG_MUX, "mux %p got %d bytes\n", m, err);
 	if (err == -EAGAIN) {
 		clear_bit(Rworksched, &m->wsched);
@@ -735,7 +735,7 @@ static void p9_read_work(struct work_struct *work)
 		if (test_and_clear_bit(Rpending, &m->wsched))
 			n = POLLIN;
 		else
-			n = p9_fd_poll(m->trans, NULL);
+			n = p9_fd_poll(m->client, NULL);
 
 		if (n & POLLIN) {
 			P9_DPRINTK(P9_DEBUG_MUX, "schedule read work %p\n", m);
@@ -819,7 +819,7 @@ static struct p9_req *p9_send_request(struct p9_conn *m,
 	if (test_and_clear_bit(Wpending, &m->wsched))
 		n = POLLOUT;
 	else
-		n = p9_fd_poll(m->trans, NULL);
+		n = p9_fd_poll(m->client, NULL);
 
 	if (n & POLLOUT && !test_and_set_bit(Wworksched, &m->wsched))
 		queue_work(p9_mux_wq, &m->wq);
@@ -933,16 +933,16 @@ p9_conn_rpc_cb(struct p9_req *req, void *a)
 /**
  * p9_fd_rpc- sends 9P request and waits until a response is available.
  *	The function can be interrupted.
- * @t: transport data
+ * @client: client instance
  * @tc: request to be sent
  * @rc: pointer where a pointer to the response is stored
  *
  */
 
 int
-p9_fd_rpc(struct p9_trans *t, struct p9_fcall *tc, struct p9_fcall **rc)
+p9_fd_rpc(struct p9_client *client, struct p9_fcall *tc, struct p9_fcall **rc)
 {
-	struct p9_trans_fd *p = t->priv;
+	struct p9_trans_fd *p = client->trans;
 	struct p9_conn *m = p->conn;
 	int err, sigpending;
 	unsigned long flags;
@@ -975,7 +975,7 @@ p9_fd_rpc(struct p9_trans *t, struct p9_fcall *tc, struct p9_fcall **rc)
 	if (r.err < 0)
 		err = r.err;
 
-	if (err == -ERESTARTSYS && m->trans->status == Connected
+	if (err == -ERESTARTSYS && client->status == Connected
 							&& m->err == 0) {
 		if (p9_mux_flush_request(m, req)) {
 			/* wait until we get response of the flush message */
@@ -984,7 +984,7 @@ p9_fd_rpc(struct p9_trans *t, struct p9_fcall *tc, struct p9_fcall **rc)
 				err = wait_event_interruptible(r.wqueue,
 					r.rcall || r.err);
 			} while (!r.rcall && !r.err && err == -ERESTARTSYS &&
-				m->trans->status == Connected && !m->err);
+				client->status == Connected && !m->err);
 
 			err = -ERESTARTSYS;
 		}
@@ -1133,7 +1133,7 @@ static int parse_opts(char *params, struct p9_fd_opts *opts)
 	return 0;
 }
 
-static int p9_fd_open(struct p9_trans *trans, int rfd, int wfd)
+static int p9_fd_open(struct p9_client *client, int rfd, int wfd)
 {
 	struct p9_trans_fd *ts = kmalloc(sizeof(struct p9_trans_fd),
 					   GFP_KERNEL);
@@ -1151,13 +1151,13 @@ static int p9_fd_open(struct p9_trans *trans, int rfd, int wfd)
 		return -EIO;
 	}
 
-	trans->priv = ts;
-	trans->status = Connected;
+	client->trans = ts;
+	client->status = Connected;
 
 	return 0;
 }
 
-static int p9_socket_open(struct p9_trans *trans, struct socket *csocket)
+static int p9_socket_open(struct p9_client *client, struct socket *csocket)
 {
 	int fd, ret;
 
@@ -1168,33 +1168,33 @@ static int p9_socket_open(struct p9_trans *trans, struct socket *csocket)
 		return fd;
 	}
 
-	ret = p9_fd_open(trans, fd, fd);
+	ret = p9_fd_open(client, fd, fd);
 	if (ret < 0) {
 		P9_EPRINTK(KERN_ERR, "p9_socket_open: failed to open fd\n");
 		sockfd_put(csocket);
 		return ret;
 	}
 
-	((struct p9_trans_fd *)trans->priv)->rd->f_flags |= O_NONBLOCK;
+	((struct p9_trans_fd *)client->trans)->rd->f_flags |= O_NONBLOCK;
 
 	return 0;
 }
 
 /**
  * p9_fd_read- read from a fd
- * @trans: transport instance state
+ * @client: client instance
  * @v: buffer to receive data into
  * @len: size of receive buffer
  *
  */
 
-static int p9_fd_read(struct p9_trans *trans, void *v, int len)
+static int p9_fd_read(struct p9_client *client, void *v, int len)
 {
 	int ret;
 	struct p9_trans_fd *ts = NULL;
 
-	if (trans && trans->status != Disconnected)
-		ts = trans->priv;
+	if (client && client->status != Disconnected)
+		ts = client->trans;
 
 	if (!ts)
 		return -EREMOTEIO;
@@ -1204,26 +1204,26 @@ static int p9_fd_read(struct p9_trans *trans, void *v, int len)
 
 	ret = kernel_read(ts->rd, ts->rd->f_pos, v, len);
 	if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN)
-		trans->status = Disconnected;
+		client->status = Disconnected;
 	return ret;
 }
 
 /**
  * p9_fd_write - write to a socket
- * @trans: transport instance state
+ * @client: client instance
  * @v: buffer to send data from
  * @len: size of send buffer
  *
  */
 
-static int p9_fd_write(struct p9_trans *trans, void *v, int len)
+static int p9_fd_write(struct p9_client *client, void *v, int len)
 {
 	int ret;
 	mm_segment_t oldfs;
 	struct p9_trans_fd *ts = NULL;
 
-	if (trans && trans->status != Disconnected)
-		ts = trans->priv;
+	if (client && client->status != Disconnected)
+		ts = client->trans;
 
 	if (!ts)
 		return -EREMOTEIO;
@@ -1238,18 +1238,18 @@ static int p9_fd_write(struct p9_trans *trans, void *v, int len)
 	set_fs(oldfs);
 
 	if (ret <= 0 && ret != -ERESTARTSYS && ret != -EAGAIN)
-		trans->status = Disconnected;
+		client->status = Disconnected;
 	return ret;
 }
 
 static unsigned int
-p9_fd_poll(struct p9_trans *trans, struct poll_table_struct *pt)
+p9_fd_poll(struct p9_client *client, struct poll_table_struct *pt)
 {
 	int ret, n;
 	struct p9_trans_fd *ts = NULL;
 
-	if (trans && trans->status == Connected)
-		ts = trans->priv;
+	if (client && client->status == Connected)
+		ts = client->trans;
 
 	if (!ts)
 		return -EREMOTEIO;
@@ -1275,30 +1275,31 @@ p9_fd_poll(struct p9_trans *trans, struct poll_table_struct *pt)
 }
 
 /**
- * p9_fd_close - shutdown socket
- * @trans: private socket structure
+ * p9_fd_close - shutdown file descriptor transport
+ * @client: client instance
  *
  */
 
-static void p9_fd_close(struct p9_trans *trans)
+static void p9_fd_close(struct p9_client *client)
 {
 	struct p9_trans_fd *ts;
 
-	if (!trans)
+	if (!client)
 		return;
 
-	ts = xchg(&trans->priv, NULL);
-
+	ts = client->trans;
 	if (!ts)
 		return;
 
+	client->status = Disconnected;
+
 	p9_conn_destroy(ts->conn);
 
-	trans->status = Disconnected;
 	if (ts->rd)
 		fput(ts->rd);
 	if (ts->wr)
 		fput(ts->wr);
+
 	kfree(ts);
 }
 
@@ -1319,31 +1320,23 @@ static inline int valid_ipaddr4(const char *buf)
 	return 0;
 }
 
-static struct p9_trans *
-p9_trans_create_tcp(const char *addr, char *args, int msize, unsigned char dotu)
+static int
+p9_fd_create_tcp(struct p9_client *client, const char *addr, char *args)
 {
 	int err;
-	struct p9_trans *trans;
 	struct socket *csocket;
 	struct sockaddr_in sin_server;
 	struct p9_fd_opts opts;
-	struct p9_trans_fd *p;
+	struct p9_trans_fd *p = NULL; /* this gets allocated in p9_fd_open */
 
 	err = parse_opts(args, &opts);
 	if (err < 0)
-		return ERR_PTR(err);
+		return err;
 
 	if (valid_ipaddr4(addr) < 0)
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 
 	csocket = NULL;
-	trans = kmalloc(sizeof(struct p9_trans), GFP_KERNEL);
-	if (!trans)
-		return ERR_PTR(-ENOMEM);
-	trans->msize = msize;
-	trans->extended = dotu;
-	trans->rpc = p9_fd_rpc;
-	trans->close = p9_fd_close;
 
 	sin_server.sin_family = AF_INET;
 	sin_server.sin_addr.s_addr = in_aton(addr);
@@ -1366,45 +1359,38 @@ p9_trans_create_tcp(const char *addr, char *args, int msize, unsigned char dotu)
 		goto error;
 	}
 
-	err = p9_socket_open(trans, csocket);
+	err = p9_socket_open(client, csocket);
 	if (err < 0)
 		goto error;
 
-	p = (struct p9_trans_fd *) trans->priv;
-	p->conn = p9_conn_create(trans);
+	p = (struct p9_trans_fd *) client->trans;
+	p->conn = p9_conn_create(client);
 	if (IS_ERR(p->conn)) {
 		err = PTR_ERR(p->conn);
 		p->conn = NULL;
 		goto error;
 	}
 
-	return trans;
+	return 0;
 
 error:
 	if (csocket)
 		sock_release(csocket);
 
-	kfree(trans);
-	return ERR_PTR(err);
+	kfree(p);
+
+	return err;
 }
 
-static struct p9_trans *
-p9_trans_create_unix(const char *addr, char *args, int msize,
-							unsigned char dotu)
+static int
+p9_fd_create_unix(struct p9_client *client, const char *addr, char *args)
 {
 	int err;
 	struct socket *csocket;
 	struct sockaddr_un sun_server;
-	struct p9_trans *trans;
-	struct p9_trans_fd *p;
+	struct p9_trans_fd *p = NULL; /* this gets allocated in p9_fd_open */
 
 	csocket = NULL;
-	trans = kmalloc(sizeof(struct p9_trans), GFP_KERNEL);
-	if (!trans)
-		return ERR_PTR(-ENOMEM);
-
-	trans->rpc = p9_fd_rpc;
-	trans->close = p9_fd_close;
 
 	if (strlen(addr) > UNIX_PATH_MAX) {
 		P9_EPRINTK(KERN_ERR, "p9_trans_unix: address too long: %s\n",
@@ -1425,79 +1411,68 @@ p9_trans_create_unix(const char *addr, char *args, int msize,
 		goto error;
 	}
 
-	err = p9_socket_open(trans, csocket);
+	err = p9_socket_open(client, csocket);
 	if (err < 0)
 		goto error;
 
-	trans->msize = msize;
-	trans->extended = dotu;
-	p = (struct p9_trans_fd *) trans->priv;
-	p->conn = p9_conn_create(trans);
+	p = (struct p9_trans_fd *) client->trans;
+	p->conn = p9_conn_create(client);
 	if (IS_ERR(p->conn)) {
 		err = PTR_ERR(p->conn);
 		p->conn = NULL;
 		goto error;
 	}
 
-	return trans;
+	return 0;
 
 error:
 	if (csocket)
 		sock_release(csocket);
 
-	kfree(trans);
-	return ERR_PTR(err);
+	kfree(p);
+	return err;
 }
 
-static struct p9_trans *
-p9_trans_create_fd(const char *name, char *args, int msize,
-							unsigned char extended)
+static int
+p9_fd_create(struct p9_client *client, const char *addr, char *args)
 {
 	int err;
-	struct p9_trans *trans;
 	struct p9_fd_opts opts;
-	struct p9_trans_fd *p;
+	struct p9_trans_fd *p = NULL; /* this get allocated in p9_fd_open */
 
 	parse_opts(args, &opts);
 
 	if (opts.rfd == ~0 || opts.wfd == ~0) {
 		printk(KERN_ERR "v9fs: Insufficient options for proto=fd\n");
-		return ERR_PTR(-ENOPROTOOPT);
+		return -ENOPROTOOPT;
 	}
 
-	trans = kmalloc(sizeof(struct p9_trans), GFP_KERNEL);
-	if (!trans)
-		return ERR_PTR(-ENOMEM);
-
-	trans->rpc = p9_fd_rpc;
-	trans->close = p9_fd_close;
-
-	err = p9_fd_open(trans, opts.rfd, opts.wfd);
+	err = p9_fd_open(client, opts.rfd, opts.wfd);
 	if (err < 0)
 		goto error;
 
-	trans->msize = msize;
-	trans->extended = extended;
-	p = (struct p9_trans_fd *) trans->priv;
-	p->conn = p9_conn_create(trans);
+	p = (struct p9_trans_fd *) client->trans;
+	p->conn = p9_conn_create(client);
 	if (IS_ERR(p->conn)) {
 		err = PTR_ERR(p->conn);
 		p->conn = NULL;
 		goto error;
 	}
 
-	return trans;
+	return 0;
 
 error:
-	kfree(trans);
-	return ERR_PTR(err);
+	kfree(p);
+	return err;
 }
 
 static struct p9_trans_module p9_tcp_trans = {
 	.name = "tcp",
 	.maxsize = MAX_SOCK_BUF,
 	.def = 1,
-	.create = p9_trans_create_tcp,
+	.create = p9_fd_create_tcp,
+	.close = p9_fd_close,
+	.rpc = p9_fd_rpc,
 	.owner = THIS_MODULE,
 };
 
@@ -1505,7 +1480,9 @@ static struct p9_trans_module p9_unix_trans = {
 	.name = "unix",
 	.maxsize = MAX_SOCK_BUF,
 	.def = 0,
-	.create = p9_trans_create_unix,
+	.create = p9_fd_create_unix,
+	.close = p9_fd_close,
+	.rpc = p9_fd_rpc,
 	.owner = THIS_MODULE,
 };
 
@@ -1513,7 +1490,9 @@ static struct p9_trans_module p9_fd_trans = {
 	.name = "fd",
 	.maxsize = MAX_SOCK_BUF,
 	.def = 0,
-	.create = p9_trans_create_fd,
+	.create = p9_fd_create,
+	.close = p9_fd_close,
+	.rpc = p9_fd_rpc,
 	.owner = THIS_MODULE,
 };
 
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 94912e077a55..72493f04a76d 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -41,6 +41,7 @@
 #include <linux/file.h>
 #include <net/9p/9p.h>
 #include <linux/parser.h>
+#include <net/9p/client.h>
 #include <net/9p/transport.h>
 #include <linux/scatterlist.h>
 #include <linux/virtio.h>
@@ -55,7 +56,6 @@ static int chan_index;
 
 #define P9_INIT_MAXTAG	16
 
-
 /**
  * enum p9_req_status_t - virtio request status
  * @REQ_STATUS_IDLE: request slot unused
@@ -197,9 +197,9 @@ static unsigned int rest_of_page(void *data)
  *
  */
 
-static void p9_virtio_close(struct p9_trans *trans)
+static void p9_virtio_close(struct p9_client *client)
 {
-	struct virtio_chan *chan = trans->priv;
+	struct virtio_chan *chan = client->trans;
 	int count;
 	unsigned long flags;
 
@@ -215,7 +215,7 @@ static void p9_virtio_close(struct p9_trans *trans)
 	chan->inuse = false;
 	mutex_unlock(&virtio_9p_lock);
 
-	kfree(trans);
+	client->trans = NULL;
 }
 
 /**
@@ -292,17 +292,17 @@ pack_sg_list(struct scatterlist *sg, int start, int limit, char *data,
  */
 
 static int
-p9_virtio_rpc(struct p9_trans *t, struct p9_fcall *tc, struct p9_fcall **rc)
+p9_virtio_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc)
 {
 	int in, out;
 	int n, err, size;
-	struct virtio_chan *chan = t->priv;
+	struct virtio_chan *chan = c->trans;
 	char *rdata;
 	struct p9_req_t *req;
 	unsigned long flags;
 
 	if (*rc == NULL) {
-		*rc = kmalloc(sizeof(struct p9_fcall) + t->msize, GFP_KERNEL);
+		*rc = kmalloc(sizeof(struct p9_fcall) + c->msize, GFP_KERNEL);
 		if (!*rc)
 			return -ENOMEM;
 	}
@@ -325,7 +325,7 @@ p9_virtio_rpc(struct p9_trans *t, struct p9_fcall *tc, struct p9_fcall **rc)
 	P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio rpc tag %d\n", n);
 
 	out = pack_sg_list(chan->sg, 0, VIRTQUEUE_NUM, tc->sdata, tc->size);
-	in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM-out, rdata, t->msize);
+	in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM-out, rdata, c->msize);
 
 	req->status = REQ_STATUS_SENT;
 
@@ -341,7 +341,7 @@ p9_virtio_rpc(struct p9_trans *t, struct p9_fcall *tc, struct p9_fcall **rc)
 
 	size = le32_to_cpu(*(__le32 *) rdata);
 
-	err = p9_deserialize_fcall(rdata, size, *rc, t->extended);
+	err = p9_deserialize_fcall(rdata, size, *rc, c->dotu);
 	if (err < 0) {
 		P9_DPRINTK(P9_DEBUG_TRANS,
 			"9p debug: virtio rpc deserialize returned %d\n", err);
@@ -352,8 +352,8 @@ p9_virtio_rpc(struct p9_trans *t, struct p9_fcall *tc, struct p9_fcall **rc)
 	if ((p9_debug_level&P9_DEBUG_FCALL) == P9_DEBUG_FCALL) {
 		char buf[150];
 
-		p9_printfcall(buf, sizeof(buf), *rc, t->extended);
-		printk(KERN_NOTICE ">>> %p %s\n", t, buf);
+		p9_printfcall(buf, sizeof(buf), *rc, c->dotu);
+		printk(KERN_NOTICE ">>> %p %s\n", c, buf);
 	}
 #endif
 
@@ -422,10 +422,9 @@ fail:
 
 /**
  * p9_virtio_create - allocate a new virtio channel
+ * @client: client instance invoking this transport
  * @devname: string identifying the channel to connect to (unused)
  * @args: args passed from sys_mount() for per-transport options (unused)
- * @msize: requested maximum packet size
- * @extended: 9p2000.u enabled flag
  *
  * This sets up a transport channel for 9p communication.  Right now
  * we only match the first available channel, but eventually we couldlook up
@@ -441,11 +440,9 @@ fail:
  *
  */
 
-static struct p9_trans *
-p9_virtio_create(const char *devname, char *args, int msize,
-							unsigned char extended)
+static int
+p9_virtio_create(struct p9_client *client, const char *devname, char *args)
 {
-	struct p9_trans *trans;
 	struct virtio_chan *chan = channels;
 	int index = 0;
 
@@ -463,30 +460,21 @@ p9_virtio_create(const char *devname, char *args, int msize,
 
 	if (index >= MAX_9P_CHAN) {
 		printk(KERN_ERR "9p: no channels available\n");
-		return ERR_PTR(-ENODEV);
+		return -ENODEV;
 	}
 
 	chan->tagpool = p9_idpool_create();
 	if (IS_ERR(chan->tagpool)) {
 		printk(KERN_ERR "9p: couldn't allocate tagpool\n");
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 	}
 	p9_idpool_get(chan->tagpool); /* reserve tag 0 */
 	chan->max_tag = 0;
 	chan->reqs = NULL;
 
-	trans = kmalloc(sizeof(struct p9_trans), GFP_KERNEL);
-	if (!trans) {
-		printk(KERN_ERR "9p: couldn't allocate transport\n");
-		return ERR_PTR(-ENOMEM);
-	}
-	trans->extended = extended;
-	trans->msize = msize;
-	trans->close = p9_virtio_close;
-	trans->rpc = p9_virtio_rpc;
-	trans->priv = chan;
+	client->trans = (void *)chan;
 
-	return trans;
+	return 0;
 }
 
 /**
@@ -526,6 +514,8 @@ static struct virtio_driver p9_virtio_drv = {
 static struct p9_trans_module p9_virtio_trans = {
 	.name = "virtio",
 	.create = p9_virtio_create,
+	.close = p9_virtio_close,
+	.rpc = p9_virtio_rpc,
 	.maxsize = PAGE_SIZE*16,
 	.def = 0,
 	.owner = THIS_MODULE,
-- 
cgit v1.2.3


From fea511a644fb0fb938309c6ab286725ac31b87e2 Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Mon, 13 Oct 2008 18:45:23 -0500
Subject: 9p: move request management to client code

The virtio transport uses a simplified request management system
that I want to use for all transports.  This patch adapts and moves the
exisiting code for managing requests to the client common code.
Later patches will apply these mechanisms to the other transports.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/client.h |  77 ++++++++++++++++++++++++
 net/9p/client.c         | 152 ++++++++++++++++++++++++++++++++++++++++++++++++
 net/9p/trans_virtio.c   | 136 +++----------------------------------------
 3 files changed, 238 insertions(+), 127 deletions(-)

(limited to 'include')

diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index c35fb548e7cf..140cf1d58452 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -26,6 +26,9 @@
 #ifndef NET_9P_CLIENT_H
 #define NET_9P_CLIENT_H
 
+/* Number of requests per row */
+#define P9_ROW_MAXTAG 255
+
 /**
  * enum p9_trans_status - different states of underlying transports
  * @Connected: transport is connected and healthy
@@ -42,6 +45,62 @@ enum p9_trans_status {
 	Hung,
 };
 
+/**
+ * enum p9_req_status_t - virtio request status
+ * @REQ_STATUS_IDLE: request slot unused
+ * @REQ_STATUS_ALLOC: request has been allocated but not sent
+ * @REQ_STATUS_SENT: request sent to server
+ * @REQ_STATUS_FLSH: a flush has been sent for this request
+ * @REQ_STATUS_RCVD: response received from server
+ * @REQ_STATUS_FLSHD: request has been flushed
+ * @REQ_STATUS_ERR: request encountered an error on the client side
+ *
+ * The @REQ_STATUS_IDLE state is used to mark a request slot as unused
+ * but use is actually tracked by the idpool structure which handles tag
+ * id allocation.
+ *
+ */
+
+enum p9_req_status_t {
+	REQ_STATUS_IDLE,
+	REQ_STATUS_ALLOC,
+	REQ_STATUS_SENT,
+	REQ_STATUS_FLSH,
+	REQ_STATUS_RCVD,
+	REQ_STATUS_FLSHD,
+	REQ_STATUS_ERROR,
+};
+
+/**
+ * struct p9_req_t - request slots
+ * @status: status of this request slot
+ * @t_err: transport error
+ * @wq: wait_queue for the client to block on for this request
+ * @tc: the request fcall structure
+ * @rc: the response fcall structure
+ * @aux: transport specific data (provided for trans_fd migration)
+ *
+ * Transport use an array to track outstanding requests
+ * instead of a list.  While this may incurr overhead during initial
+ * allocation or expansion, it makes request lookup much easier as the
+ * tag id is a index into an array.  (We use tag+1 so that we can accomodate
+ * the -1 tag for the T_VERSION request).
+ * This also has the nice effect of only having to allocate wait_queues
+ * once, instead of constantly allocating and freeing them.  Its possible
+ * other resources could benefit from this scheme as well.
+ *
+ */
+
+struct p9_req_t {
+	int status;
+	int t_err;
+	wait_queue_head_t *wq;
+	struct p9_fcall *tc;
+	struct p9_fcall *rc;
+	u16 flush_tag;
+	void *aux;
+};
+
 /**
  * struct p9_client - per client instance state
  * @lock: protect @fidlist
@@ -52,9 +111,20 @@ enum p9_trans_status {
  * @conn: connection state information used by trans_fd
  * @fidpool: fid handle accounting for session
  * @fidlist: List of active fid handles
+ * @tagpool - transaction id accounting for session
+ * @reqs - 2D array of requests
+ * @max_tag - current maximum tag id allocated
  *
  * The client structure is used to keep track of various per-client
  * state that has been instantiated.
+ * In order to minimize per-transaction overhead we use a
+ * simple array to lookup requests instead of a hash table
+ * or linked list.  In order to support larger number of
+ * transactions, we make this a 2D array, allocating new rows
+ * when we need to grow the total number of the transactions.
+ *
+ * Each row is 256 requests and we'll support up to 256 rows for
+ * a total of 64k concurrent requests per session.
  *
  * Bugs: duplicated data and potentially unnecessary elements.
  */
@@ -70,6 +140,10 @@ struct p9_client {
 
 	struct p9_idpool *fidpool;
 	struct list_head fidlist;
+
+	struct p9_idpool *tagpool;
+	struct p9_req_t *reqs[P9_ROW_MAXTAG];
+	int max_tag;
 };
 
 /**
@@ -131,4 +205,7 @@ struct p9_stat *p9_client_stat(struct p9_fid *fid);
 int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst);
 struct p9_stat *p9_client_dirread(struct p9_fid *fid, u64 offset);
 
+struct p9_req_t *p9_tag_alloc(struct p9_client *, u16);
+struct p9_req_t *p9_tag_lookup(struct p9_client *, u16);
+
 #endif /* NET_9P_CLIENT_H */
diff --git a/net/9p/client.c b/net/9p/client.c
index 712d4f336adc..867031934f75 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -120,6 +120,154 @@ static int parse_opts(char *opts, struct p9_client *clnt)
 	return ret;
 }
 
+/**
+ * p9_tag_alloc - lookup/allocate a request by tag
+ * @c: client session to lookup tag within
+ * @tag: numeric id for transaction
+ *
+ * this is a simple array lookup, but will grow the
+ * request_slots as necessary to accomodate transaction
+ * ids which did not previously have a slot.
+ *
+ * this code relies on the client spinlock to manage locks, its
+ * possible we should switch to something else, but I'd rather
+ * stick with something low-overhead for the common case.
+ *
+ */
+
+struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
+{
+	unsigned long flags;
+	int row, col;
+
+	/* This looks up the original request by tag so we know which
+	 * buffer to read the data into */
+	tag++;
+
+	if (tag >= c->max_tag) {
+		spin_lock_irqsave(&c->lock, flags);
+		/* check again since original check was outside of lock */
+		while (tag >= c->max_tag) {
+			row = (tag / P9_ROW_MAXTAG);
+			c->reqs[row] = kcalloc(P9_ROW_MAXTAG,
+					sizeof(struct p9_req_t), GFP_ATOMIC);
+
+			if (!c->reqs[row]) {
+				printk(KERN_ERR "Couldn't grow tag array\n");
+				BUG();
+			}
+			for (col = 0; col < P9_ROW_MAXTAG; col++) {
+				c->reqs[row][col].status = REQ_STATUS_IDLE;
+				c->reqs[row][col].flush_tag = P9_NOTAG;
+				c->reqs[row][col].wq = kmalloc(
+					sizeof(wait_queue_head_t), GFP_ATOMIC);
+				if (!c->reqs[row][col].wq) {
+					printk(KERN_ERR
+						"Couldn't grow tag array\n");
+					BUG();
+				}
+				init_waitqueue_head(c->reqs[row][col].wq);
+			}
+			c->max_tag += P9_ROW_MAXTAG;
+		}
+		spin_unlock_irqrestore(&c->lock, flags);
+	}
+	row = tag / P9_ROW_MAXTAG;
+	col = tag % P9_ROW_MAXTAG;
+
+	c->reqs[row][col].status = REQ_STATUS_ALLOC;
+	c->reqs[row][col].flush_tag = P9_NOTAG;
+
+	return &c->reqs[row][col];
+}
+EXPORT_SYMBOL(p9_tag_alloc);
+
+/**
+ * p9_tag_lookup - lookup a request by tag
+ * @c: client session to lookup tag within
+ * @tag: numeric id for transaction
+ *
+ */
+
+struct p9_req_t *p9_tag_lookup(struct p9_client *c, u16 tag)
+{
+	int row, col;
+
+	/* This looks up the original request by tag so we know which
+	 * buffer to read the data into */
+	tag++;
+
+	BUG_ON(tag >= c->max_tag);
+
+	row = tag / P9_ROW_MAXTAG;
+	col = tag % P9_ROW_MAXTAG;
+
+	return &c->reqs[row][col];
+}
+EXPORT_SYMBOL(p9_tag_lookup);
+
+/**
+ * p9_tag_init - setup tags structure and contents
+ * @tags: tags structure from the client struct
+ *
+ * This initializes the tags structure for each client instance.
+ *
+ */
+
+static int p9_tag_init(struct p9_client *c)
+{
+	int err = 0;
+
+	c->tagpool = p9_idpool_create();
+	if (IS_ERR(c->tagpool)) {
+		err = PTR_ERR(c->tagpool);
+		c->tagpool = NULL;
+		goto error;
+	}
+
+	p9_idpool_get(c->tagpool); /* reserve tag 0 */
+
+	c->max_tag = 0;
+error:
+	return err;
+}
+
+/**
+ * p9_tag_cleanup - cleans up tags structure and reclaims resources
+ * @tags: tags structure from the client struct
+ *
+ * This frees resources associated with the tags structure
+ *
+ */
+static void p9_tag_cleanup(struct p9_client *c)
+{
+	int row, col;
+
+	/* check to insure all requests are idle */
+	for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
+		for (col = 0; col < P9_ROW_MAXTAG; col++) {
+			if (c->reqs[row][col].status != REQ_STATUS_IDLE) {
+				P9_DPRINTK(P9_DEBUG_MUX,
+				  "Attempting to cleanup non-free tag %d,%d\n",
+				  row, col);
+				/* TODO: delay execution of cleanup */
+				return;
+			}
+		}
+	}
+
+	if (c->tagpool)
+		p9_idpool_destroy(c->tagpool);
+
+	/* free requests associated with tags */
+	for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
+		for (col = 0; col < P9_ROW_MAXTAG; col++)
+			kfree(c->reqs[row][col].wq);
+		kfree(c->reqs[row]);
+	}
+	c->max_tag = 0;
+}
+
 static struct p9_fid *p9_fid_create(struct p9_client *clnt)
 {
 	int err;
@@ -209,6 +357,8 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 		goto error;
 	}
 
+	p9_tag_init(clnt);
+
 	err = parse_opts(options, clnt);
 	if (err < 0)
 		goto error;
@@ -285,6 +435,8 @@ void p9_client_destroy(struct p9_client *clnt)
 	if (clnt->fidpool)
 		p9_idpool_destroy(clnt->fidpool);
 
+	p9_tag_cleanup(clnt);
+
 	kfree(clnt);
 }
 EXPORT_SYMBOL(p9_client_destroy);
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 72493f04a76d..36bce45e4e44 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -1,12 +1,10 @@
 /*
- * The Guest 9p transport driver
+ * The Virtio 9p transport driver
  *
  * This is a block based transport driver based on the lguest block driver
  * code.
  *
- */
-/*
- *  Copyright (C) 2007 Eric Van Hensbergen, IBM Corporation
+ *  Copyright (C) 2007, 2008 Eric Van Hensbergen, IBM Corporation
  *
  *  Based on virtio console driver
  *  Copyright (C) 2006, 2007 Rusty Russell, IBM Corporation
@@ -54,49 +52,6 @@ static DEFINE_MUTEX(virtio_9p_lock);
 /* global which tracks highest initialized channel */
 static int chan_index;
 
-#define P9_INIT_MAXTAG	16
-
-/**
- * enum p9_req_status_t - virtio request status
- * @REQ_STATUS_IDLE: request slot unused
- * @REQ_STATUS_SENT: request sent to server
- * @REQ_STATUS_RCVD: response received from server
- * @REQ_STATUS_FLSH: request has been flushed
- *
- * The @REQ_STATUS_IDLE state is used to mark a request slot as unused
- * but use is actually tracked by the idpool structure which handles tag
- * id allocation.
- *
- */
-
-enum p9_req_status_t {
-	REQ_STATUS_IDLE,
-	REQ_STATUS_SENT,
-	REQ_STATUS_RCVD,
-	REQ_STATUS_FLSH,
-};
-
-/**
- * struct p9_req_t - virtio request slots
- * @status: status of this request slot
- * @wq: wait_queue for the client to block on for this request
- *
- * The virtio transport uses an array to track outstanding requests
- * instead of a list.  While this may incurr overhead during initial
- * allocation or expansion, it makes request lookup much easier as the
- * tag id is a index into an array.  (We use tag+1 so that we can accomodate
- * the -1 tag for the T_VERSION request).
- * This also has the nice effect of only having to allocate wait_queues
- * once, instead of constantly allocating and freeing them.  Its possible
- * other resources could benefit from this scheme as well.
- *
- */
-
-struct p9_req_t {
-	int status;
-	wait_queue_head_t *wq;
-};
-
 /**
  * struct virtio_chan - per-instance transport information
  * @initialized: whether the channel is initialized
@@ -121,67 +76,14 @@ static struct virtio_chan {
 
 	spinlock_t lock;
 
+	struct p9_client *client;
 	struct virtio_device *vdev;
 	struct virtqueue *vq;
 
-	struct p9_idpool *tagpool;
-	struct p9_req_t *reqs;
-	int max_tag;
-
 	/* Scatterlist: can be too big for stack. */
 	struct scatterlist sg[VIRTQUEUE_NUM];
 } channels[MAX_9P_CHAN];
 
-/**
- * p9_lookup_tag - Lookup requests by tag
- * @c: virtio channel to lookup tag within
- * @tag: numeric id for transaction
- *
- * this is a simple array lookup, but will grow the
- * request_slots as necessary to accomodate transaction
- * ids which did not previously have a slot.
- *
- * Bugs: there is currently no upper limit on request slots set
- * here, but that should be constrained by the id accounting.
- */
-
-static struct p9_req_t *p9_lookup_tag(struct virtio_chan *c, u16 tag)
-{
-	/* This looks up the original request by tag so we know which
-	 * buffer to read the data into */
-	tag++;
-
-	while (tag >= c->max_tag) {
-		int old_max = c->max_tag;
-		int count;
-
-		if (c->max_tag)
-			c->max_tag *= 2;
-		else
-			c->max_tag = P9_INIT_MAXTAG;
-
-		c->reqs = krealloc(c->reqs, sizeof(struct p9_req_t)*c->max_tag,
-								GFP_ATOMIC);
-		if (!c->reqs) {
-			printk(KERN_ERR "Couldn't grow tag array\n");
-			BUG();
-		}
-		for (count = old_max; count < c->max_tag; count++) {
-			c->reqs[count].status = REQ_STATUS_IDLE;
-			c->reqs[count].wq = kmalloc(sizeof(wait_queue_head_t),
-								GFP_ATOMIC);
-			if (!c->reqs[count].wq) {
-				printk(KERN_ERR "Couldn't grow tag array\n");
-				BUG();
-			}
-			init_waitqueue_head(c->reqs[count].wq);
-		}
-	}
-
-	return &c->reqs[tag];
-}
-
-
 /* How many bytes left in this page. */
 static unsigned int rest_of_page(void *data)
 {
@@ -200,22 +102,10 @@ static unsigned int rest_of_page(void *data)
 static void p9_virtio_close(struct p9_client *client)
 {
 	struct virtio_chan *chan = client->trans;
-	int count;
-	unsigned long flags;
-
-	spin_lock_irqsave(&chan->lock, flags);
-	p9_idpool_destroy(chan->tagpool);
-	for (count = 0; count < chan->max_tag; count++)
-		kfree(chan->reqs[count].wq);
-	kfree(chan->reqs);
-	chan->max_tag = 0;
-	spin_unlock_irqrestore(&chan->lock, flags);
 
 	mutex_lock(&virtio_9p_lock);
 	chan->inuse = false;
 	mutex_unlock(&virtio_9p_lock);
-
-	client->trans = NULL;
 }
 
 /**
@@ -241,7 +131,7 @@ static void req_done(struct virtqueue *vq)
 
 	spin_lock_irqsave(&chan->lock, flags);
 	while ((rc = chan->vq->vq_ops->get_buf(chan->vq, &len)) != NULL) {
-		req = p9_lookup_tag(chan, rc->tag);
+		req = p9_tag_lookup(chan->client, rc->tag);
 		req->status = REQ_STATUS_RCVD;
 		wake_up(req->wq);
 	}
@@ -311,13 +201,13 @@ p9_virtio_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc)
 
 	n = P9_NOTAG;
 	if (tc->id != P9_TVERSION) {
-		n = p9_idpool_get(chan->tagpool);
+		n = p9_idpool_get(c->tagpool);
 		if (n < 0)
 			return -ENOMEM;
 	}
 
 	spin_lock_irqsave(&chan->lock, flags);
-	req = p9_lookup_tag(chan, n);
+	req = p9_tag_alloc(c, n);
 	spin_unlock_irqrestore(&chan->lock, flags);
 
 	p9_set_tag(tc, n);
@@ -357,8 +247,8 @@ p9_virtio_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc)
 	}
 #endif
 
-	if (n != P9_NOTAG && p9_idpool_check(n, chan->tagpool))
-		p9_idpool_put(n, chan->tagpool);
+	if (n != P9_NOTAG && p9_idpool_check(n, c->tagpool))
+		p9_idpool_put(n, c->tagpool);
 
 	req->status = REQ_STATUS_IDLE;
 
@@ -463,16 +353,8 @@ p9_virtio_create(struct p9_client *client, const char *devname, char *args)
 		return -ENODEV;
 	}
 
-	chan->tagpool = p9_idpool_create();
-	if (IS_ERR(chan->tagpool)) {
-		printk(KERN_ERR "9p: couldn't allocate tagpool\n");
-		return -ENOMEM;
-	}
-	p9_idpool_get(chan->tagpool); /* reserve tag 0 */
-	chan->max_tag = 0;
-	chan->reqs = NULL;
-
 	client->trans = (void *)chan;
+	chan->client = client;
 
 	return 0;
 }
-- 
cgit v1.2.3


From 673d62cdaac6ffbce980a349d3174b3929ceb9e5 Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Mon, 13 Oct 2008 18:45:22 -0500
Subject: 9p: apply common request code to trans_fd

Apply the now common p9_req_t structure to the fd transport.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/client.h |  10 +-
 net/9p/client.c         |  21 ++++
 net/9p/trans_fd.c       | 262 ++++++++++++++++++------------------------------
 net/9p/trans_virtio.c   |   5 +-
 4 files changed, 126 insertions(+), 172 deletions(-)

(limited to 'include')

diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index 140cf1d58452..4fecaabd17bd 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -49,11 +49,12 @@ enum p9_trans_status {
  * enum p9_req_status_t - virtio request status
  * @REQ_STATUS_IDLE: request slot unused
  * @REQ_STATUS_ALLOC: request has been allocated but not sent
+ * @REQ_STATUS_UNSENT: request waiting to be sent
  * @REQ_STATUS_SENT: request sent to server
  * @REQ_STATUS_FLSH: a flush has been sent for this request
  * @REQ_STATUS_RCVD: response received from server
  * @REQ_STATUS_FLSHD: request has been flushed
- * @REQ_STATUS_ERR: request encountered an error on the client side
+ * @REQ_STATUS_ERROR: request encountered an error on the client side
  *
  * The @REQ_STATUS_IDLE state is used to mark a request slot as unused
  * but use is actually tracked by the idpool structure which handles tag
@@ -64,6 +65,7 @@ enum p9_trans_status {
 enum p9_req_status_t {
 	REQ_STATUS_IDLE,
 	REQ_STATUS_ALLOC,
+	REQ_STATUS_UNSENT,
 	REQ_STATUS_SENT,
 	REQ_STATUS_FLSH,
 	REQ_STATUS_RCVD,
@@ -79,6 +81,8 @@ enum p9_req_status_t {
  * @tc: the request fcall structure
  * @rc: the response fcall structure
  * @aux: transport specific data (provided for trans_fd migration)
+ * @tag: tag on request (BUG: redundant)
+ * @req_list: link for higher level objects to chain requests
  *
  * Transport use an array to track outstanding requests
  * instead of a list.  While this may incurr overhead during initial
@@ -99,6 +103,9 @@ struct p9_req_t {
 	struct p9_fcall *rc;
 	u16 flush_tag;
 	void *aux;
+
+	int tag;
+	struct list_head req_list;
 };
 
 /**
@@ -207,5 +214,6 @@ struct p9_stat *p9_client_dirread(struct p9_fid *fid, u64 offset);
 
 struct p9_req_t *p9_tag_alloc(struct p9_client *, u16);
 struct p9_req_t *p9_tag_lookup(struct p9_client *, u16);
+void p9_free_req(struct p9_client *, struct p9_req_t *);
 
 #endif /* NET_9P_CLIENT_H */
diff --git a/net/9p/client.c b/net/9p/client.c
index 867031934f75..f2d07ef9e6a4 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -268,6 +268,27 @@ static void p9_tag_cleanup(struct p9_client *c)
 	c->max_tag = 0;
 }
 
+/**
+ * p9_free_req - free a request and clean-up as necessary
+ * c: client state
+ * r: request to release
+ *
+ */
+
+void p9_free_req(struct p9_client *c, struct p9_req_t *r)
+{
+	r->flush_tag = P9_NOTAG;
+	r->status = REQ_STATUS_IDLE;
+	if (r->tc->tag != P9_NOTAG && p9_idpool_check(r->tc->tag, c->tagpool))
+		p9_idpool_put(r->tc->tag, c->tagpool);
+
+	/* if this was a flush request we have to free response fcall */
+	if (r->tc->id == P9_TFLUSH) {
+		kfree(r->tc);
+		kfree(r->rc);
+	}
+}
+
 static struct p9_fid *p9_fid_create(struct p9_client *clnt)
 {
 	int err;
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 6243093934b2..cc9bc739e9d3 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -44,7 +44,6 @@
 
 #define P9_PORT 564
 #define MAX_SOCK_BUF (64*1024)
-#define ERREQFLUSH	1
 #define MAXPOLLWADDR	2
 
 /**
@@ -99,38 +98,6 @@ enum {
 	Wpending = 8,		/* can write */
 };
 
-enum {
-	None,
-	Flushing,
-	Flushed,
-};
-
-/**
- * struct p9_req - fd mux encoding of an rpc transaction
- * @lock: protects req_list
- * @tag: numeric tag for rpc transaction
- * @tcall: request &p9_fcall structure
- * @rcall: response &p9_fcall structure
- * @err: error state
- * @flush: flag to indicate RPC has been flushed
- * @req_list: list link for higher level objects to chain requests
- * @m: connection this request was issued on
- * @wqueue: wait queue that client is blocked on for this rpc
- *
- */
-
-struct p9_req {
-	spinlock_t lock;
-	int tag;
-	struct p9_fcall *tcall;
-	struct p9_fcall *rcall;
-	int err;
-	int flush;
-	struct list_head req_list;
-	struct p9_conn *m;
-	wait_queue_head_t wqueue;
-};
-
 struct p9_poll_wait {
 	struct p9_conn *conn;
 	wait_queue_t wait;
@@ -139,7 +106,6 @@ struct p9_poll_wait {
 
 /**
  * struct p9_conn - fd mux connection state information
- * @lock: protects mux_list (?)
  * @mux_list: list link for mux to manage multiple connections (?)
  * @client: reference to client instance for this connection
  * @err: error state
@@ -161,7 +127,6 @@ struct p9_poll_wait {
  */
 
 struct p9_conn {
-	spinlock_t lock; /* protect lock structure */
 	struct list_head mux_list;
 	struct p9_client *client;
 	int err;
@@ -205,64 +170,41 @@ static void p9_mux_poll_stop(struct p9_conn *m)
 	spin_unlock_irqrestore(&p9_poll_lock, flags);
 }
 
-static void p9_mux_free_request(struct p9_conn *m, struct p9_req *req)
-{
-	if (req->tag != P9_NOTAG &&
-	    p9_idpool_check(req->tag, m->client->tagpool))
-		p9_idpool_put(req->tag, m->client->tagpool);
-	kfree(req);
-}
-
-static void p9_conn_rpc_cb(struct p9_req *req);
+static void p9_conn_rpc_cb(struct p9_client *, struct p9_req_t *);
 
-static void p9_mux_flush_cb(struct p9_req *freq)
+static void p9_mux_flush_cb(struct p9_client *client, struct p9_req_t *freq)
 {
-	int tag;
-	struct p9_conn *m = freq->m;
-	struct p9_req *req, *rreq, *rptr;
+	struct p9_conn *m = client->trans;
+	struct p9_req_t *req;
 
 	P9_DPRINTK(P9_DEBUG_MUX, "mux %p tc %p rc %p err %d oldtag %d\n", m,
-		freq->tcall, freq->rcall, freq->err,
-		freq->tcall->params.tflush.oldtag);
-
-	spin_lock(&m->lock);
-	tag = freq->tcall->params.tflush.oldtag;
-	req = NULL;
-	list_for_each_entry_safe(rreq, rptr, &m->req_list, req_list) {
-		if (rreq->tag == tag) {
-			req = rreq;
-			list_del(&req->req_list);
-			break;
-		}
-	}
-	spin_unlock(&m->lock);
+		freq->tc, freq->rc, freq->t_err,
+		freq->tc->params.tflush.oldtag);
 
+	req = p9_tag_lookup(client, freq->tc->params.tflush.oldtag);
 	if (req) {
-		spin_lock(&req->lock);
-		req->flush = Flushed;
-		spin_unlock(&req->lock);
-
-		p9_conn_rpc_cb(req);
+		req->status = REQ_STATUS_FLSHD;
+		list_del(&req->req_list);
+		p9_conn_rpc_cb(client, req);
 	}
 
-	kfree(freq->tcall);
-	kfree(freq->rcall);
-	p9_mux_free_request(m, freq);
+	p9_free_req(client, freq);
 }
 
-static void p9_conn_rpc_cb(struct p9_req *req)
+static void p9_conn_rpc_cb(struct p9_client *client, struct p9_req_t *req)
 {
 	P9_DPRINTK(P9_DEBUG_MUX, "req %p\n", req);
 
-	if (req->tcall->id == P9_TFLUSH) { /* flush callback */
+	if (req->tc->id == P9_TFLUSH) { /* flush callback */
 		P9_DPRINTK(P9_DEBUG_MUX, "flush req %p\n", req);
-		p9_mux_flush_cb(req);
+		p9_mux_flush_cb(client, req);
 	} else {			/* normal wakeup path */
 		P9_DPRINTK(P9_DEBUG_MUX, "normal req %p\n", req);
-		if (req->flush != None && !req->err)
-			req->err = -ERESTARTSYS;
+		if (!req->t_err && (req->status == REQ_STATUS_FLSHD ||
+				 req->status == REQ_STATUS_FLSH))
+			req->t_err = -ERESTARTSYS;
 
-		wake_up(&req->wqueue);
+		wake_up(req->wq);
 	}
 }
 
@@ -275,59 +217,62 @@ static void p9_conn_rpc_cb(struct p9_req *req)
 
 void p9_conn_cancel(struct p9_conn *m, int err)
 {
-	struct p9_req *req, *rtmp;
+	struct p9_req_t *req, *rtmp;
 	LIST_HEAD(cancel_list);
 
 	P9_DPRINTK(P9_DEBUG_ERROR, "mux %p err %d\n", m, err);
 	m->err = err;
-	spin_lock(&m->lock);
+	spin_lock(&m->client->lock);
 	list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) {
+		req->status = REQ_STATUS_ERROR;
+		if (!req->t_err)
+			req->t_err = err;
 		list_move(&req->req_list, &cancel_list);
 	}
 	list_for_each_entry_safe(req, rtmp, &m->unsent_req_list, req_list) {
+		req->status = REQ_STATUS_ERROR;
+		if (!req->t_err)
+			req->t_err = err;
 		list_move(&req->req_list, &cancel_list);
 	}
-	spin_unlock(&m->lock);
+	spin_unlock(&m->client->lock);
 
 	list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) {
 		list_del(&req->req_list);
-		if (!req->err)
-			req->err = err;
-
-		p9_conn_rpc_cb(req);
+		p9_conn_rpc_cb(m->client, req);
 	}
 }
 
-static void process_request(struct p9_conn *m, struct p9_req *req)
+static void process_request(struct p9_conn *m, struct p9_req_t *req)
 {
 	int ecode;
 	struct p9_str *ename;
 
-	if (!req->err && req->rcall->id == P9_RERROR) {
-		ecode = req->rcall->params.rerror.errno;
-		ename = &req->rcall->params.rerror.error;
+	if (!req->t_err && req->rc->id == P9_RERROR) {
+		ecode = req->rc->params.rerror.errno;
+		ename = &req->rc->params.rerror.error;
 
 		P9_DPRINTK(P9_DEBUG_MUX, "Rerror %.*s\n", ename->len,
 								ename->str);
 
 		if (m->client->dotu)
-			req->err = -ecode;
+			req->t_err = -ecode;
 
-		if (!req->err) {
-			req->err = p9_errstr2errno(ename->str, ename->len);
+		if (!req->t_err) {
+			req->t_err = p9_errstr2errno(ename->str, ename->len);
 
 			/* string match failed */
-			if (!req->err) {
-				PRINT_FCALL_ERROR("unknown error", req->rcall);
-				req->err = -ESERVERFAULT;
+			if (!req->t_err) {
+				PRINT_FCALL_ERROR("unknown error", req->rc);
+				req->t_err = -ESERVERFAULT;
 			}
 		}
-	} else if (req->tcall && req->rcall->id != req->tcall->id + 1) {
+	} else if (req->tc && req->rc->id != req->tc->id + 1) {
 		P9_DPRINTK(P9_DEBUG_ERROR,
 				"fcall mismatch: expected %d, got %d\n",
-				req->tcall->id + 1, req->rcall->id);
-		if (!req->err)
-			req->err = -EIO;
+				req->tc->id + 1, req->rc->id);
+		if (!req->t_err)
+			req->t_err = -EIO;
 	}
 }
 
@@ -401,7 +346,7 @@ static void p9_read_work(struct work_struct *work)
 {
 	int n, err;
 	struct p9_conn *m;
-	struct p9_req *req, *rptr, *rreq;
+	struct p9_req_t *req;
 	struct p9_fcall *rcall;
 	char *rbuf;
 
@@ -488,24 +433,19 @@ static void p9_read_work(struct work_struct *work)
 		P9_DPRINTK(P9_DEBUG_MUX, "mux %p fcall id %d tag %d\n", m,
 							rcall->id, rcall->tag);
 
-		req = NULL;
-		spin_lock(&m->lock);
-		list_for_each_entry_safe(rreq, rptr, &m->req_list, req_list) {
-			if (rreq->tag == rcall->tag) {
-				req = rreq;
-				if (req->flush != Flushing)
-					list_del(&req->req_list);
-				break;
-			}
-		}
-		spin_unlock(&m->lock);
+		req = p9_tag_lookup(m->client, rcall->tag);
 
 		if (req) {
-			req->rcall = rcall;
+			if (req->status != REQ_STATUS_FLSH) {
+				list_del(&req->req_list);
+				req->status = REQ_STATUS_RCVD;
+			}
+
+			req->rc = rcall;
 			process_request(m, req);
 
-			if (req->flush != Flushing)
-				p9_conn_rpc_cb(req);
+			if (req->status != REQ_STATUS_FLSH)
+				p9_conn_rpc_cb(m->client, req);
 		} else {
 			if (err >= 0 && rcall->id != P9_RFLUSH)
 				P9_DPRINTK(P9_DEBUG_ERROR,
@@ -580,7 +520,7 @@ static void p9_write_work(struct work_struct *work)
 {
 	int n, err;
 	struct p9_conn *m;
-	struct p9_req *req;
+	struct p9_req_t *req;
 
 	m = container_of(work, struct p9_conn, wq);
 
@@ -595,18 +535,16 @@ static void p9_write_work(struct work_struct *work)
 			return;
 		}
 
-		spin_lock(&m->lock);
-again:
-		req = list_entry(m->unsent_req_list.next, struct p9_req,
+		spin_lock(&m->client->lock);
+		req = list_entry(m->unsent_req_list.next, struct p9_req_t,
 			       req_list);
+		req->status = REQ_STATUS_SENT;
 		list_move_tail(&req->req_list, &m->req_list);
-		if (req->err == ERREQFLUSH)
-			goto again;
 
-		m->wbuf = req->tcall->sdata;
-		m->wsize = req->tcall->size;
+		m->wbuf = req->tc->sdata;
+		m->wsize = req->tc->size;
 		m->wpos = 0;
-		spin_unlock(&m->lock);
+		spin_unlock(&m->client->lock);
 	}
 
 	P9_DPRINTK(P9_DEBUG_MUX, "mux %p pos %d size %d\n", m, m->wpos,
@@ -725,7 +663,6 @@ static struct p9_conn *p9_conn_create(struct p9_client *client)
 	if (!m)
 		return ERR_PTR(-ENOMEM);
 
-	spin_lock_init(&m->lock);
 	INIT_LIST_HEAD(&m->mux_list);
 	m->client = client;
 
@@ -812,30 +749,27 @@ static void p9_poll_mux(struct p9_conn *m)
  *
  */
 
-static struct p9_req *p9_send_request(struct p9_conn *m, struct p9_fcall *tc)
+static struct p9_req_t *p9_send_request(struct p9_conn *m, struct p9_fcall *tc)
 {
+	int tag;
 	int n;
-	struct p9_req *req;
+	struct p9_req_t *req;
 
 	P9_DPRINTK(P9_DEBUG_MUX, "mux %p task %p tcall %p id %d\n", m, current,
 		tc, tc->id);
 	if (m->err < 0)
 		return ERR_PTR(m->err);
 
-	req = kmalloc(sizeof(struct p9_req), GFP_KERNEL);
-	if (!req)
-		return ERR_PTR(-ENOMEM);
-
-	n = P9_NOTAG;
+	tag = P9_NOTAG;
 	if (tc->id != P9_TVERSION) {
-		n = p9_idpool_get(m->client->tagpool);
-		if (n < 0) {
-			kfree(req);
+		tag = p9_idpool_get(m->client->tagpool);
+		if (tag < 0)
 			return ERR_PTR(-ENOMEM);
-		}
 	}
 
-	p9_set_tag(tc, n);
+	p9_set_tag(tc, tag);
+
+	req = p9_tag_alloc(m->client, tag);
 
 #ifdef CONFIG_NET_9P_DEBUG
 	if ((p9_debug_level&P9_DEBUG_FCALL) == P9_DEBUG_FCALL) {
@@ -846,18 +780,15 @@ static struct p9_req *p9_send_request(struct p9_conn *m, struct p9_fcall *tc)
 	}
 #endif
 
-	spin_lock_init(&req->lock);
-	req->m = m;
-	init_waitqueue_head(&req->wqueue);
-	req->tag = n;
-	req->tcall = tc;
-	req->rcall = NULL;
-	req->err = 0;
-	req->flush = None;
+	req->tag = tag;
+	req->tc = tc;
+	req->rc = NULL;
+	req->t_err = 0;
+	req->status = REQ_STATUS_UNSENT;
 
-	spin_lock(&m->lock);
+	spin_lock(&m->client->lock);
 	list_add_tail(&req->req_list, &m->unsent_req_list);
-	spin_unlock(&m->lock);
+	spin_unlock(&m->client->lock);
 
 	if (test_and_clear_bit(Wpending, &m->wsched))
 		n = POLLOUT;
@@ -871,39 +802,36 @@ static struct p9_req *p9_send_request(struct p9_conn *m, struct p9_fcall *tc)
 }
 
 static int
-p9_mux_flush_request(struct p9_conn *m, struct p9_req *req)
+p9_mux_flush_request(struct p9_conn *m, struct p9_req_t *req)
 {
 	struct p9_fcall *fc;
-	struct p9_req *rreq, *rptr;
+	struct p9_req_t *rreq, *rptr;
 
 	P9_DPRINTK(P9_DEBUG_MUX, "mux %p req %p tag %d\n", m, req, req->tag);
 
 	/* if a response was received for a request, do nothing */
-	spin_lock(&req->lock);
-	if (req->rcall || req->err) {
-		spin_unlock(&req->lock);
+	if (req->rc || req->t_err) {
 		P9_DPRINTK(P9_DEBUG_MUX,
 			"mux %p req %p response already received\n", m, req);
 		return 0;
 	}
 
-	req->flush = Flushing;
-	spin_unlock(&req->lock);
+	req->status = REQ_STATUS_FLSH;
 
-	spin_lock(&m->lock);
+	spin_lock(&m->client->lock);
 	/* if the request is not sent yet, just remove it from the list */
 	list_for_each_entry_safe(rreq, rptr, &m->unsent_req_list, req_list) {
 		if (rreq->tag == req->tag) {
 			P9_DPRINTK(P9_DEBUG_MUX,
 			   "mux %p req %p request is not sent yet\n", m, req);
 			list_del(&rreq->req_list);
-			req->flush = Flushed;
-			spin_unlock(&m->lock);
-			p9_conn_rpc_cb(req);
+			req->status = REQ_STATUS_FLSHD;
+			spin_unlock(&m->client->lock);
+			p9_conn_rpc_cb(m->client, req);
 			return 0;
 		}
 	}
-	spin_unlock(&m->lock);
+	spin_unlock(&m->client->lock);
 
 	clear_thread_flag(TIF_SIGPENDING);
 	fc = p9_create_tflush(req->tag);
@@ -927,7 +855,7 @@ p9_fd_rpc(struct p9_client *client, struct p9_fcall *tc, struct p9_fcall **rc)
 	struct p9_conn *m = p->conn;
 	int err, sigpending;
 	unsigned long flags;
-	struct p9_req *req;
+	struct p9_req_t *req;
 
 	if (rc)
 		*rc = NULL;
@@ -945,10 +873,10 @@ p9_fd_rpc(struct p9_client *client, struct p9_fcall *tc, struct p9_fcall **rc)
 		return err;
 	}
 
-	err = wait_event_interruptible(req->wqueue, req->rcall != NULL ||
-								req->err < 0);
-	if (req->err < 0)
-		err = req->err;
+	err = wait_event_interruptible(*req->wq, req->rc != NULL ||
+								req->t_err < 0);
+	if (req->t_err < 0)
+		err = req->t_err;
 
 	if (err == -ERESTARTSYS && client->status == Connected
 							&& m->err == 0) {
@@ -956,9 +884,9 @@ p9_fd_rpc(struct p9_client *client, struct p9_fcall *tc, struct p9_fcall **rc)
 			/* wait until we get response of the flush message */
 			do {
 				clear_thread_flag(TIF_SIGPENDING);
-				err = wait_event_interruptible(req->wqueue,
-					req->rcall || req->err);
-			} while (!req->rcall && !req->err &&
+				err = wait_event_interruptible(*req->wq,
+					req->rc || req->t_err);
+			} while (!req->rc && !req->t_err &&
 					err == -ERESTARTSYS &&
 					client->status == Connected && !m->err);
 
@@ -974,11 +902,11 @@ p9_fd_rpc(struct p9_client *client, struct p9_fcall *tc, struct p9_fcall **rc)
 	}
 
 	if (rc)
-		*rc = req->rcall;
+		*rc = req->rc;
 	else
-		kfree(req->rcall);
+		kfree(req->rc);
 
-	p9_mux_free_request(m, req);
+	p9_free_req(client, req);
 	if (err > 0)
 		err = -EIO;
 
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 36bce45e4e44..e18de14c30d5 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -247,10 +247,7 @@ p9_virtio_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc)
 	}
 #endif
 
-	if (n != P9_NOTAG && p9_idpool_check(n, c->tagpool))
-		p9_idpool_put(n, c->tagpool);
-
-	req->status = REQ_STATUS_IDLE;
+	p9_free_req(c, req);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 91b8534fa8f5e01f249b1bf8df0a2540053549ad Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Mon, 13 Oct 2008 18:45:21 -0500
Subject: 9p: make rpc code common and rework flush code

This code moves the rpc function to the common client base,
reorganizes the flush code to be more simple and stable, and
makes the necessary adjustments to the underlying transports
to adapt to the new structure.

This reduces the overall amount of code duplication between the
transports and should make adding new transports more straightforward.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/client.h    |   3 +-
 include/net/9p/transport.h |   8 +-
 net/9p/client.c            | 265 +++++++++++++++++++++++++++++++++++++++++---
 net/9p/trans_fd.c          | 268 ++++++---------------------------------------
 net/9p/trans_virtio.c      |  85 ++++----------
 5 files changed, 316 insertions(+), 313 deletions(-)

(limited to 'include')

diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index 4fecaabd17bd..6a71d9067818 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -212,8 +212,7 @@ struct p9_stat *p9_client_stat(struct p9_fid *fid);
 int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst);
 struct p9_stat *p9_client_dirread(struct p9_fid *fid, u64 offset);
 
-struct p9_req_t *p9_tag_alloc(struct p9_client *, u16);
 struct p9_req_t *p9_tag_lookup(struct p9_client *, u16);
-void p9_free_req(struct p9_client *, struct p9_req_t *);
+void p9_client_cb(struct p9_client *c, struct p9_req_t *req);
 
 #endif /* NET_9P_CLIENT_H */
diff --git a/include/net/9p/transport.h b/include/net/9p/transport.h
index 3e0f2f6beba2..6d5886efb102 100644
--- a/include/net/9p/transport.h
+++ b/include/net/9p/transport.h
@@ -33,8 +33,8 @@
  * @maxsize: transport provided maximum packet size
  * @def: set if this transport should be considered the default
  * @create: member function to create a new connection on this transport
- * @close: member function to disconnect and close the transport
- * @rpc: member function to issue a request to the transport
+ * @request: member function to issue a request to the transport
+ * @cancel: member function to cancel a request (if it hasn't been sent)
  *
  * This is the basic API for a transport module which is registered by the
  * transport module with the 9P core network module and used by the client
@@ -51,8 +51,8 @@ struct p9_trans_module {
 	struct module *owner;
 	int (*create)(struct p9_client *, const char *, char *);
 	void (*close) (struct p9_client *);
-	int (*rpc) (struct p9_client *t, struct p9_fcall *tc,
-							struct p9_fcall **rc);
+	int (*request) (struct p9_client *, struct p9_req_t *req);
+	int (*cancel) (struct p9_client *, struct p9_req_t *req);
 };
 
 void v9fs_register_trans(struct p9_trans_module *m);
diff --git a/net/9p/client.c b/net/9p/client.c
index f2d07ef9e6a4..29934febecdb 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -55,6 +55,9 @@ static const match_table_t tokens = {
 	{Opt_err, NULL},
 };
 
+static int
+p9_client_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc);
+
 /**
  * v9fs_parse_options - parse mount options into session structure
  * @options: options string passed from mount
@@ -268,6 +271,36 @@ static void p9_tag_cleanup(struct p9_client *c)
 	c->max_tag = 0;
 }
 
+/**
+ * p9_client_flush - flush (cancel) a request
+ * c: client state
+ * req: request to cancel
+ *
+ * This sents a flush for a particular requests and links
+ * the flush request to the original request.  The current
+ * code only supports a single flush request although the protocol
+ * allows for multiple flush requests to be sent for a single request.
+ *
+ */
+
+static int p9_client_flush(struct p9_client *c, struct p9_req_t *req)
+{
+	struct p9_fcall *tc, *rc = NULL;
+	int err;
+
+	P9_DPRINTK(P9_DEBUG_9P, "client %p tag %d\n", c, req->tc->tag);
+
+	tc = p9_create_tflush(req->tc->tag);
+	if (IS_ERR(tc))
+		return PTR_ERR(tc);
+
+	err = p9_client_rpc(c, tc, &rc);
+
+	/* we don't free anything here because RPC isn't complete */
+
+	return err;
+}
+
 /**
  * p9_free_req - free a request and clean-up as necessary
  * c: client state
@@ -289,6 +322,224 @@ void p9_free_req(struct p9_client *c, struct p9_req_t *r)
 	}
 }
 
+/**
+ * p9_client_cb - call back from transport to client
+ * c: client state
+ * req: request received
+ *
+ */
+void p9_client_cb(struct p9_client *c, struct p9_req_t *req)
+{
+	struct p9_req_t *other_req;
+	unsigned long flags;
+
+	P9_DPRINTK(P9_DEBUG_MUX, ": %d\n", req->tc->tag);
+
+	if (req->status == REQ_STATUS_ERROR)
+		wake_up(req->wq);
+
+	if (req->tc->id == P9_TFLUSH) { /* flush receive path */
+		P9_DPRINTK(P9_DEBUG_MUX, "flush: %d\n", req->tc->tag);
+		spin_lock_irqsave(&c->lock, flags);
+		other_req = p9_tag_lookup(c, req->tc->params.tflush.oldtag);
+		if (other_req->flush_tag != req->tc->tag) /* stale flush */
+			spin_unlock_irqrestore(&c->lock, flags);
+		else {
+			BUG_ON(other_req->status != REQ_STATUS_FLSH);
+			other_req->status = REQ_STATUS_FLSHD;
+			spin_unlock_irqrestore(&c->lock, flags);
+			wake_up(other_req->wq);
+		}
+		p9_free_req(c, req);
+	} else { 				/* normal receive path */
+		P9_DPRINTK(P9_DEBUG_MUX, "normal: %d\n", req->tc->tag);
+		spin_lock_irqsave(&c->lock, flags);
+		if (req->status != REQ_STATUS_FLSHD)
+			req->status = REQ_STATUS_RCVD;
+		req->flush_tag = P9_NOTAG;
+		spin_unlock_irqrestore(&c->lock, flags);
+		wake_up(req->wq);
+		P9_DPRINTK(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag);
+	}
+}
+EXPORT_SYMBOL(p9_client_cb);
+
+/**
+ * p9_client_rpc - issue a request and wait for a response
+ * @c: client session
+ * @tc: &p9_fcall request to transmit
+ * @rc: &p9_fcall to put reponse into
+ *
+ * Returns 0 on success, error code on failure
+ */
+
+static int
+p9_client_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc)
+{
+	int tag, err, size;
+	char *rdata;
+	struct p9_req_t *req;
+	unsigned long flags;
+	int sigpending;
+	int flushed = 0;
+
+	P9_DPRINTK(P9_DEBUG_9P, "client %p tc %p rc %p\n", c, tc, rc);
+
+	if (c->status != Connected)
+		return -EIO;
+
+	if (signal_pending(current)) {
+		sigpending = 1;
+		clear_thread_flag(TIF_SIGPENDING);
+	} else
+		sigpending = 0;
+
+	tag = P9_NOTAG;
+	if (tc->id != P9_TVERSION) {
+		tag = p9_idpool_get(c->tagpool);
+		if (tag < 0)
+			return -ENOMEM;
+	}
+
+	req = p9_tag_alloc(c, tag);
+
+	/* if this is a flush request, backlink flush request now to
+	 * avoid race conditions later. */
+	if (tc->id == P9_TFLUSH) {
+		struct p9_req_t *other_req =
+				p9_tag_lookup(c, tc->params.tflush.oldtag);
+		if (other_req->status == REQ_STATUS_FLSH)
+			other_req->flush_tag = tag;
+	}
+
+	p9_set_tag(tc, tag);
+
+	/*
+	 * if client passed in a pre-allocated response fcall struct
+	 * then we just use that, otherwise we allocate one.
+	 */
+
+	if (rc == NULL)
+		req->rc = NULL;
+	else
+		req->rc = *rc;
+	if (req->rc == NULL) {
+		req->rc = kmalloc(sizeof(struct p9_fcall) + c->msize,
+								GFP_KERNEL);
+		if (!req->rc) {
+			err = -ENOMEM;
+			p9_idpool_put(tag, c->tagpool);
+			p9_free_req(c, req);
+			goto reterr;
+		}
+		*rc = req->rc;
+	}
+
+	rdata = (char *)req->rc+sizeof(struct p9_fcall);
+
+	req->tc = tc;
+	P9_DPRINTK(P9_DEBUG_9P, "request: tc: %p rc: %p\n", req->tc, req->rc);
+
+	err = c->trans_mod->request(c, req);
+	if (err < 0) {
+		c->status = Disconnected;
+		goto reterr;
+	}
+
+	/* if it was a flush we just transmitted, return our tag */
+	if (tc->id == P9_TFLUSH)
+		return 0;
+again:
+	P9_DPRINTK(P9_DEBUG_9P, "wait %p tag: %d\n", req->wq, tag);
+	err = wait_event_interruptible(*req->wq,
+						req->status >= REQ_STATUS_RCVD);
+	P9_DPRINTK(P9_DEBUG_9P, "wait %p tag: %d returned %d (flushed=%d)\n",
+						req->wq, tag, err, flushed);
+
+	if (req->status == REQ_STATUS_ERROR) {
+		P9_DPRINTK(P9_DEBUG_9P, "req_status error %d\n", req->t_err);
+		err = req->t_err;
+	} else if (err == -ERESTARTSYS && flushed) {
+		P9_DPRINTK(P9_DEBUG_9P, "flushed - going again\n");
+		goto again;
+	} else if (req->status == REQ_STATUS_FLSHD) {
+		P9_DPRINTK(P9_DEBUG_9P, "flushed - erestartsys\n");
+		err = -ERESTARTSYS;
+	}
+
+	if ((err == -ERESTARTSYS) && (c->status == Connected) && (!flushed)) {
+		P9_DPRINTK(P9_DEBUG_9P, "flushing\n");
+		spin_lock_irqsave(&c->lock, flags);
+		if (req->status == REQ_STATUS_SENT)
+			req->status = REQ_STATUS_FLSH;
+		spin_unlock_irqrestore(&c->lock, flags);
+		sigpending = 1;
+		flushed = 1;
+		clear_thread_flag(TIF_SIGPENDING);
+
+		if (c->trans_mod->cancel(c, req)) {
+			err = p9_client_flush(c, req);
+			if (err == 0)
+				goto again;
+		}
+	}
+
+	if (sigpending) {
+		spin_lock_irqsave(&current->sighand->siglock, flags);
+		recalc_sigpending();
+		spin_unlock_irqrestore(&current->sighand->siglock, flags);
+	}
+
+	if (err < 0)
+		goto reterr;
+
+	size = le32_to_cpu(*(__le32 *) rdata);
+
+	err = p9_deserialize_fcall(rdata, size, req->rc, c->dotu);
+	if (err < 0) {
+		P9_DPRINTK(P9_DEBUG_9P,
+			"9p debug: client rpc deserialize returned %d\n", err);
+		goto reterr;
+	}
+
+#ifdef CONFIG_NET_9P_DEBUG
+	if ((p9_debug_level&P9_DEBUG_FCALL) == P9_DEBUG_FCALL) {
+		char buf[150];
+
+		p9_printfcall(buf, sizeof(buf), req->rc, c->dotu);
+		printk(KERN_NOTICE ">>> %p %s\n", c, buf);
+	}
+#endif
+
+	if (req->rc->id == P9_RERROR) {
+		int ecode = req->rc->params.rerror.errno;
+		struct p9_str *ename = &req->rc->params.rerror.error;
+
+		P9_DPRINTK(P9_DEBUG_MUX, "Rerror %.*s\n", ename->len,
+								ename->str);
+
+		if (c->dotu)
+			err = -ecode;
+
+		if (!err) {
+			err = p9_errstr2errno(ename->str, ename->len);
+
+			/* string match failed */
+			if (!err) {
+				PRINT_FCALL_ERROR("unknown error", req->rc);
+				err = -ESERVERFAULT;
+			}
+		}
+	} else
+		err = 0;
+
+reterr:
+	p9_free_req(c, req);
+
+	P9_DPRINTK(P9_DEBUG_9P, "returning %d\n", err);
+	return err;
+}
+
 static struct p9_fid *p9_fid_create(struct p9_client *clnt)
 {
 	int err;
@@ -339,20 +590,6 @@ static void p9_fid_destroy(struct p9_fid *fid)
 	kfree(fid);
 }
 
-/**
- * p9_client_rpc - sends 9P request and waits until a response is available.
- *      The function can be interrupted.
- * @c: client data
- * @tc: request to be sent
- * @rc: pointer where a pointer to the response is stored
- */
-int
-p9_client_rpc(struct p9_client *c, struct p9_fcall *tc,
-	struct p9_fcall **rc)
-{
-	return c->trans_mod->rpc(c, tc, rc);
-}
-
 struct p9_client *p9_client_create(const char *dev_name, char *options)
 {
 	int err, n;
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 627e3f097fc5..6bfc013f8b6f 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -174,44 +174,6 @@ static void p9_mux_poll_stop(struct p9_conn *m)
 	spin_unlock_irqrestore(&p9_poll_lock, flags);
 }
 
-static void p9_conn_rpc_cb(struct p9_client *, struct p9_req_t *);
-
-static void p9_mux_flush_cb(struct p9_client *client, struct p9_req_t *freq)
-{
-	struct p9_conn *m = client->trans;
-	struct p9_req_t *req;
-
-	P9_DPRINTK(P9_DEBUG_MUX, "mux %p tc %p rc %p err %d oldtag %d\n", m,
-		freq->tc, freq->rc, freq->t_err,
-		freq->tc->params.tflush.oldtag);
-
-	req = p9_tag_lookup(client, freq->tc->params.tflush.oldtag);
-	if (req) {
-		req->status = REQ_STATUS_FLSHD;
-		list_del(&req->req_list);
-		p9_conn_rpc_cb(client, req);
-	}
-
-	p9_free_req(client, freq);
-}
-
-static void p9_conn_rpc_cb(struct p9_client *client, struct p9_req_t *req)
-{
-	P9_DPRINTK(P9_DEBUG_MUX, "req %p\n", req);
-
-	if (req->tc->id == P9_TFLUSH) { /* flush callback */
-		P9_DPRINTK(P9_DEBUG_MUX, "flush req %p\n", req);
-		p9_mux_flush_cb(client, req);
-	} else {			/* normal wakeup path */
-		P9_DPRINTK(P9_DEBUG_MUX, "normal req %p\n", req);
-		if (!req->t_err && (req->status == REQ_STATUS_FLSHD ||
-				 req->status == REQ_STATUS_FLSH))
-			req->t_err = -ERESTARTSYS;
-
-		wake_up(req->wq);
-	}
-}
-
 /**
  * p9_conn_cancel - cancel all pending requests with error
  * @m: mux data
@@ -222,11 +184,12 @@ static void p9_conn_rpc_cb(struct p9_client *client, struct p9_req_t *req)
 void p9_conn_cancel(struct p9_conn *m, int err)
 {
 	struct p9_req_t *req, *rtmp;
+	unsigned long flags;
 	LIST_HEAD(cancel_list);
 
 	P9_DPRINTK(P9_DEBUG_ERROR, "mux %p err %d\n", m, err);
 	m->err = err;
-	spin_lock(&m->client->lock);
+	spin_lock_irqsave(&m->client->lock, flags);
 	list_for_each_entry_safe(req, rtmp, &m->req_list, req_list) {
 		req->status = REQ_STATUS_ERROR;
 		if (!req->t_err)
@@ -239,44 +202,12 @@ void p9_conn_cancel(struct p9_conn *m, int err)
 			req->t_err = err;
 		list_move(&req->req_list, &cancel_list);
 	}
-	spin_unlock(&m->client->lock);
+	spin_unlock_irqrestore(&m->client->lock, flags);
 
 	list_for_each_entry_safe(req, rtmp, &cancel_list, req_list) {
 		list_del(&req->req_list);
-		p9_conn_rpc_cb(m->client, req);
-	}
-}
-
-static void process_request(struct p9_conn *m, struct p9_req_t *req)
-{
-	int ecode;
-	struct p9_str *ename;
-
-	if (!req->t_err && req->rc->id == P9_RERROR) {
-		ecode = req->rc->params.rerror.errno;
-		ename = &req->rc->params.rerror.error;
-
-		P9_DPRINTK(P9_DEBUG_MUX, "Rerror %.*s\n", ename->len,
-								ename->str);
-
-		if (m->client->dotu)
-			req->t_err = -ecode;
-
-		if (!req->t_err) {
-			req->t_err = p9_errstr2errno(ename->str, ename->len);
-
-			/* string match failed */
-			if (!req->t_err) {
-				PRINT_FCALL_ERROR("unknown error", req->rc);
-				req->t_err = -ESERVERFAULT;
-			}
-		}
-	} else if (req->tc && req->rc->id != req->tc->id + 1) {
-		P9_DPRINTK(P9_DEBUG_ERROR,
-				"fcall mismatch: expected %d, got %d\n",
-				req->tc->id + 1, req->rc->id);
-		if (!req->t_err)
-			req->t_err = -EIO;
+		P9_DPRINTK(P9_DEBUG_ERROR, "call back req %p\n", req);
+		p9_client_cb(m->client, req);
 	}
 }
 
@@ -421,41 +352,13 @@ static void p9_read_work(struct work_struct *work)
 	/* not an else because some packets (like clunk) have no payload */
 	if ((m->req) && (m->rpos == m->rsize)) { /* packet is read in */
 		P9_DPRINTK(P9_DEBUG_MUX, "got new packet\n");
-		m->rbuf = (char *)m->req->rc + sizeof(struct p9_fcall);
-		err = p9_deserialize_fcall(m->rbuf, m->rsize, m->req->rc,
-							m->client->dotu);
-		if (err < 0) {
-			m->req = NULL;
-			goto error;
-		}
-
-#ifdef CONFIG_NET_9P_DEBUG
-		if ((p9_debug_level&P9_DEBUG_FCALL) == P9_DEBUG_FCALL) {
-			char buf[150];
-
-			p9_printfcall(buf, sizeof(buf), m->req->rc,
-				m->client->dotu);
-			printk(KERN_NOTICE ">>> %p %s\n", m, buf);
-		}
-#endif
 
-		P9_DPRINTK(P9_DEBUG_MUX, "mux %p fcall id %d tag %d\n", m,
-					m->req->rc->id, m->req->rc->tag);
+		list_del(&m->req->req_list);
+		p9_client_cb(m->client, m->req);
 
 		m->rbuf = NULL;
 		m->rpos = 0;
 		m->rsize = 0;
-
-		if (m->req->status != REQ_STATUS_FLSH) {
-			list_del(&m->req->req_list);
-			m->req->status = REQ_STATUS_RCVD;
-		}
-
-		process_request(m, m->req);
-
-		if (m->req->status != REQ_STATUS_FLSH)
-			p9_conn_rpc_cb(m->client, m->req);
-
 		m->req = NULL;
 	}
 
@@ -741,57 +644,41 @@ static void p9_poll_mux(struct p9_conn *m)
 }
 
 /**
- * p9_send_request - send 9P request
+ * p9_fd_request - send 9P request
  * The function can sleep until the request is scheduled for sending.
  * The function can be interrupted. Return from the function is not
- * a guarantee that the request is sent successfully. Can return errors
- * that can be retrieved by PTR_ERR macros.
+ * a guarantee that the request is sent successfully.
  *
- * @m: mux data
- * @tc: request to be sent
+ * @client: client instance
+ * @req: request to be sent
  *
  */
 
-static struct p9_req_t *p9_send_request(struct p9_conn *m, struct p9_fcall *tc)
+static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
 {
-	int tag;
 	int n;
-	struct p9_req_t *req;
+	struct p9_trans_fd *ts = client->trans;
+	struct p9_conn *m = ts->conn;
 
 	P9_DPRINTK(P9_DEBUG_MUX, "mux %p task %p tcall %p id %d\n", m, current,
-		tc, tc->id);
+		req->tc, req->tc->id);
 	if (m->err < 0)
-		return ERR_PTR(m->err);
-
-	tag = P9_NOTAG;
-	if (tc->id != P9_TVERSION) {
-		tag = p9_idpool_get(m->client->tagpool);
-		if (tag < 0)
-			return ERR_PTR(-ENOMEM);
-	}
-
-	p9_set_tag(tc, tag);
-
-	req = p9_tag_alloc(m->client, tag);
+		return m->err;
 
 #ifdef CONFIG_NET_9P_DEBUG
 	if ((p9_debug_level&P9_DEBUG_FCALL) == P9_DEBUG_FCALL) {
 		char buf[150];
 
-		p9_printfcall(buf, sizeof(buf), tc, m->client->dotu);
+		p9_printfcall(buf, sizeof(buf), req->tc, client->dotu);
 		printk(KERN_NOTICE "<<< %p %s\n", m, buf);
 	}
 #endif
 
-	req->tag = tag;
-	req->tc = tc;
-	req->rc = NULL;
-	req->t_err = 0;
 	req->status = REQ_STATUS_UNSENT;
 
-	spin_lock(&m->client->lock);
+	spin_lock(&client->lock);
 	list_add_tail(&req->req_list, &m->unsent_req_list);
-	spin_unlock(&m->client->lock);
+	spin_unlock(&client->lock);
 
 	if (test_and_clear_bit(Wpending, &m->wsched))
 		n = POLLOUT;
@@ -801,17 +688,20 @@ static struct p9_req_t *p9_send_request(struct p9_conn *m, struct p9_fcall *tc)
 	if (n & POLLOUT && !test_and_set_bit(Wworksched, &m->wsched))
 		queue_work(p9_mux_wq, &m->wq);
 
-	return req;
+	return 0;
 }
 
-static int
-p9_mux_flush_request(struct p9_conn *m, struct p9_req_t *req)
+static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
 {
-	struct p9_fcall *fc;
-	struct p9_req_t *rreq, *rptr;
+	struct p9_trans_fd *ts = client->trans;
+	struct p9_conn *m = ts->conn;
 
 	P9_DPRINTK(P9_DEBUG_MUX, "mux %p req %p tag %d\n", m, req, req->tag);
 
+	spin_lock(&client->lock);
+	list_del(&req->req_list);
+	spin_unlock(&client->lock);
+
 	/* if a response was received for a request, do nothing */
 	if (req->rc || req->t_err) {
 		P9_DPRINTK(P9_DEBUG_MUX,
@@ -819,103 +709,14 @@ p9_mux_flush_request(struct p9_conn *m, struct p9_req_t *req)
 		return 0;
 	}
 
-	req->status = REQ_STATUS_FLSH;
-
-	spin_lock(&m->client->lock);
-	/* if the request is not sent yet, just remove it from the list */
-	list_for_each_entry_safe(rreq, rptr, &m->unsent_req_list, req_list) {
-		if (rreq->tag == req->tag) {
-			P9_DPRINTK(P9_DEBUG_MUX,
-			   "mux %p req %p request is not sent yet\n", m, req);
-			list_del(&rreq->req_list);
-			req->status = REQ_STATUS_FLSHD;
-			spin_unlock(&m->client->lock);
-			p9_conn_rpc_cb(m->client, req);
-			return 0;
-		}
+	if (req->status == REQ_STATUS_UNSENT) {
+		req->status = REQ_STATUS_FLSHD;
+		return 0;
 	}
-	spin_unlock(&m->client->lock);
 
-	clear_thread_flag(TIF_SIGPENDING);
-	fc = p9_create_tflush(req->tag);
-	p9_send_request(m, fc);
 	return 1;
 }
 
-/**
- * p9_fd_rpc- sends 9P request and waits until a response is available.
- *	The function can be interrupted.
- * @client: client instance
- * @tc: request to be sent
- * @rc: pointer where a pointer to the response is stored
- *
- */
-
-int
-p9_fd_rpc(struct p9_client *client, struct p9_fcall *tc, struct p9_fcall **rc)
-{
-	struct p9_trans_fd *p = client->trans;
-	struct p9_conn *m = p->conn;
-	int err, sigpending;
-	unsigned long flags;
-	struct p9_req_t *req;
-
-	if (rc)
-		*rc = NULL;
-
-	sigpending = 0;
-	if (signal_pending(current)) {
-		sigpending = 1;
-		clear_thread_flag(TIF_SIGPENDING);
-	}
-
-	req = p9_send_request(m, tc);
-	if (IS_ERR(req)) {
-		err = PTR_ERR(req);
-		P9_DPRINTK(P9_DEBUG_MUX, "error %d\n", err);
-		return err;
-	}
-
-	err = wait_event_interruptible(*req->wq, req->rc != NULL ||
-								req->t_err < 0);
-	if (req->t_err < 0)
-		err = req->t_err;
-
-	if (err == -ERESTARTSYS && client->status == Connected
-							&& m->err == 0) {
-		if (p9_mux_flush_request(m, req)) {
-			/* wait until we get response of the flush message */
-			do {
-				clear_thread_flag(TIF_SIGPENDING);
-				err = wait_event_interruptible(*req->wq,
-					req->rc || req->t_err);
-			} while (!req->rc && !req->t_err &&
-					err == -ERESTARTSYS &&
-					client->status == Connected && !m->err);
-
-			err = -ERESTARTSYS;
-		}
-		sigpending = 1;
-	}
-
-	if (sigpending) {
-		spin_lock_irqsave(&current->sighand->siglock, flags);
-		recalc_sigpending();
-		spin_unlock_irqrestore(&current->sighand->siglock, flags);
-	}
-
-	if (rc)
-		*rc = req->rc;
-	else
-		kfree(req->rc);
-
-	p9_free_req(client, req);
-	if (err > 0)
-		err = -EIO;
-
-	return err;
-}
-
 /**
  * parse_options - parse mount options into session structure
  * @options: options string passed from mount
@@ -1243,7 +1044,8 @@ static struct p9_trans_module p9_tcp_trans = {
 	.def = 1,
 	.create = p9_fd_create_tcp,
 	.close = p9_fd_close,
-	.rpc = p9_fd_rpc,
+	.request = p9_fd_request,
+	.cancel = p9_fd_cancel,
 	.owner = THIS_MODULE,
 };
 
@@ -1253,7 +1055,8 @@ static struct p9_trans_module p9_unix_trans = {
 	.def = 0,
 	.create = p9_fd_create_unix,
 	.close = p9_fd_close,
-	.rpc = p9_fd_rpc,
+	.request = p9_fd_request,
+	.cancel = p9_fd_cancel,
 	.owner = THIS_MODULE,
 };
 
@@ -1263,7 +1066,8 @@ static struct p9_trans_module p9_fd_trans = {
 	.def = 0,
 	.create = p9_fd_create,
 	.close = p9_fd_close,
-	.rpc = p9_fd_rpc,
+	.request = p9_fd_request,
+	.cancel = p9_fd_cancel,
 	.owner = THIS_MODULE,
 };
 
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index e18de14c30d5..2d7781ec663b 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -126,17 +126,16 @@ static void req_done(struct virtqueue *vq)
 	struct virtio_chan *chan = vq->vdev->priv;
 	struct p9_fcall *rc;
 	unsigned int len;
-	unsigned long flags;
 	struct p9_req_t *req;
 
-	spin_lock_irqsave(&chan->lock, flags);
+	P9_DPRINTK(P9_DEBUG_TRANS, ": request done\n");
+
 	while ((rc = chan->vq->vq_ops->get_buf(chan->vq, &len)) != NULL) {
+		P9_DPRINTK(P9_DEBUG_TRANS, ": rc %p\n", rc);
+		P9_DPRINTK(P9_DEBUG_TRANS, ": lookup tag %d\n", rc->tag);
 		req = p9_tag_lookup(chan->client, rc->tag);
-		req->status = REQ_STATUS_RCVD;
-		wake_up(req->wq);
+		p9_client_cb(chan->client, req);
 	}
-	/* In case queue is stopped waiting for more buffers. */
-	spin_unlock_irqrestore(&chan->lock, flags);
 }
 
 /**
@@ -173,8 +172,14 @@ pack_sg_list(struct scatterlist *sg, int start, int limit, char *data,
 	return index-start;
 }
 
+/* We don't currently allow canceling of virtio requests */
+static int p9_virtio_cancel(struct p9_client *client, struct p9_req_t *req)
+{
+	return 1;
+}
+
 /**
- * p9_virtio_rpc - issue a request and wait for a response
+ * p9_virtio_request - issue a request
  * @t: transport state
  * @tc: &p9_fcall request to transmit
  * @rc: &p9_fcall to put reponse into
@@ -182,44 +187,22 @@ pack_sg_list(struct scatterlist *sg, int start, int limit, char *data,
  */
 
 static int
-p9_virtio_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc)
+p9_virtio_request(struct p9_client *client, struct p9_req_t *req)
 {
 	int in, out;
-	int n, err, size;
-	struct virtio_chan *chan = c->trans;
-	char *rdata;
-	struct p9_req_t *req;
-	unsigned long flags;
-
-	if (*rc == NULL) {
-		*rc = kmalloc(sizeof(struct p9_fcall) + c->msize, GFP_KERNEL);
-		if (!*rc)
-			return -ENOMEM;
-	}
-
-	rdata = (char *)*rc+sizeof(struct p9_fcall);
-
-	n = P9_NOTAG;
-	if (tc->id != P9_TVERSION) {
-		n = p9_idpool_get(c->tagpool);
-		if (n < 0)
-			return -ENOMEM;
-	}
-
-	spin_lock_irqsave(&chan->lock, flags);
-	req = p9_tag_alloc(c, n);
-	spin_unlock_irqrestore(&chan->lock, flags);
-
-	p9_set_tag(tc, n);
+	struct virtio_chan *chan = client->trans;
+	char *rdata = (char *)req->rc+sizeof(struct p9_fcall);
 
-	P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio rpc tag %d\n", n);
+	P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request\n");
 
-	out = pack_sg_list(chan->sg, 0, VIRTQUEUE_NUM, tc->sdata, tc->size);
-	in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM-out, rdata, c->msize);
+	out = pack_sg_list(chan->sg, 0, VIRTQUEUE_NUM, req->tc->sdata,
+								req->tc->size);
+	in = pack_sg_list(chan->sg, out, VIRTQUEUE_NUM-out, rdata,
+								client->msize);
 
 	req->status = REQ_STATUS_SENT;
 
-	if (chan->vq->vq_ops->add_buf(chan->vq, chan->sg, out, in, tc)) {
+	if (chan->vq->vq_ops->add_buf(chan->vq, chan->sg, out, in, req->tc)) {
 		P9_DPRINTK(P9_DEBUG_TRANS,
 			"9p debug: virtio rpc add_buf returned failure");
 		return -EIO;
@@ -227,28 +210,7 @@ p9_virtio_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc)
 
 	chan->vq->vq_ops->kick(chan->vq);
 
-	wait_event(*req->wq, req->status == REQ_STATUS_RCVD);
-
-	size = le32_to_cpu(*(__le32 *) rdata);
-
-	err = p9_deserialize_fcall(rdata, size, *rc, c->dotu);
-	if (err < 0) {
-		P9_DPRINTK(P9_DEBUG_TRANS,
-			"9p debug: virtio rpc deserialize returned %d\n", err);
-		return err;
-	}
-
-#ifdef CONFIG_NET_9P_DEBUG
-	if ((p9_debug_level&P9_DEBUG_FCALL) == P9_DEBUG_FCALL) {
-		char buf[150];
-
-		p9_printfcall(buf, sizeof(buf), *rc, c->dotu);
-		printk(KERN_NOTICE ">>> %p %s\n", c, buf);
-	}
-#endif
-
-	p9_free_req(c, req);
-
+	P9_DPRINTK(P9_DEBUG_TRANS, "9p debug: virtio request kicked\n");
 	return 0;
 }
 
@@ -394,7 +356,8 @@ static struct p9_trans_module p9_virtio_trans = {
 	.name = "virtio",
 	.create = p9_virtio_create,
 	.close = p9_virtio_close,
-	.rpc = p9_virtio_rpc,
+	.request = p9_virtio_request,
+	.cancel = p9_virtio_cancel,
 	.maxsize = PAGE_SIZE*16,
 	.def = 0,
 	.owner = THIS_MODULE,
-- 
cgit v1.2.3


From 0fc9655ec67ec5d4dfd08e469e0e9f0a494bf5bc Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Mon, 13 Oct 2008 20:36:17 -0500
Subject: 9p: consolidate read/write functions

Currently there are two separate versions of read and write.  One for
dealing with user buffers and the other for dealing with kernel buffers.
There is a tremendous amount of code duplication in the otherwise
identical versions of these functions.  This patch adds an additional
user buffer parameter to read and write and conditionalizes handling of
the buffer on whether the kernel buffer or the user buffer is populated.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 fs/9p/vfs_file.c        |   4 +-
 include/net/9p/client.h |  10 ++--
 net/9p/client.c         | 150 +++++++++---------------------------------------
 3 files changed, 34 insertions(+), 130 deletions(-)

(limited to 'include')

diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 52944d2249a4..3819a195de8f 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -136,7 +136,7 @@ v9fs_file_read(struct file *filp, char __user * data, size_t count,
 
 	P9_DPRINTK(P9_DEBUG_VFS, "\n");
 	fid = filp->private_data;
-	ret = p9_client_uread(fid, data, *offset, count);
+	ret = p9_client_read(fid, NULL, data, *offset, count);
 	if (ret > 0)
 		*offset += ret;
 
@@ -164,7 +164,7 @@ v9fs_file_write(struct file *filp, const char __user * data,
 		(int)count, (int)*offset);
 
 	fid = filp->private_data;
-	ret = p9_client_uwrite(fid, data, *offset, count);
+	ret = p9_client_write(fid, NULL, data, *offset, count);
 	if (ret > 0) {
 		invalidate_inode_pages2_range(inode->i_mapping, *offset,
 								*offset+ret);
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index 6a71d9067818..c70a0f0b448d 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -201,13 +201,11 @@ int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode,
 							char *extension);
 int p9_client_clunk(struct p9_fid *fid);
 int p9_client_remove(struct p9_fid *fid);
-int p9_client_read(struct p9_fid *fid, char *data, u64 offset, u32 count);
+int p9_client_read(struct p9_fid *fid, char *data, char __user *udata,
+							u64 offset, u32 count);
 int p9_client_readn(struct p9_fid *fid, char *data, u64 offset, u32 count);
-int p9_client_write(struct p9_fid *fid, char *data, u64 offset, u32 count);
-int p9_client_uread(struct p9_fid *fid, char __user *data, u64 offset,
-								u32 count);
-int p9_client_uwrite(struct p9_fid *fid, const char __user *data, u64 offset,
-								u32 count);
+int p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
+							u64 offset, u32 count);
 struct p9_stat *p9_client_stat(struct p9_fid *fid);
 int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst);
 struct p9_stat *p9_client_dirread(struct p9_fid *fid, u64 offset);
diff --git a/net/9p/client.c b/net/9p/client.c
index 29934febecdb..5fc3aa1eb39b 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -1016,7 +1016,9 @@ done:
 }
 EXPORT_SYMBOL(p9_client_remove);
 
-int p9_client_read(struct p9_fid *fid, char *data, u64 offset, u32 count)
+int
+p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset,
+								u32 count)
 {
 	int err, n, rsize, total;
 	struct p9_fcall *tc, *rc;
@@ -1053,125 +1055,21 @@ int p9_client_read(struct p9_fid *fid, char *data, u64 offset, u32 count)
 		if (n > count)
 			n = count;
 
-		memmove(data, rc->params.rread.data, n);
-		count -= n;
-		data += n;
-		offset += n;
-		total += n;
-		kfree(tc);
-		tc = NULL;
-		kfree(rc);
-		rc = NULL;
-	} while (count > 0 && n == rsize);
-
-	return total;
-
-error:
-	kfree(tc);
-	kfree(rc);
-	return err;
-}
-EXPORT_SYMBOL(p9_client_read);
-
-int p9_client_write(struct p9_fid *fid, char *data, u64 offset, u32 count)
-{
-	int err, n, rsize, total;
-	struct p9_fcall *tc, *rc;
-	struct p9_client *clnt;
-
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d offset %llu count %d\n", fid->fid,
-					(long long unsigned) offset, count);
-	err = 0;
-	tc = NULL;
-	rc = NULL;
-	clnt = fid->clnt;
-	total = 0;
-
-	rsize = fid->iounit;
-	if (!rsize || rsize > clnt->msize-P9_IOHDRSZ)
-		rsize = clnt->msize - P9_IOHDRSZ;
-
-	do {
-		if (count < rsize)
-			rsize = count;
-
-		tc = p9_create_twrite(fid->fid, offset, rsize, data);
-		if (IS_ERR(tc)) {
-			err = PTR_ERR(tc);
-			tc = NULL;
-			goto error;
+		if (data) {
+			memmove(data, rc->params.rread.data, n);
+			data += n;
 		}
 
-		err = p9_client_rpc(clnt, tc, &rc);
-		if (err)
-			goto error;
-
-		n = rc->params.rread.count;
-		count -= n;
-		data += n;
-		offset += n;
-		total += n;
-		kfree(tc);
-		tc = NULL;
-		kfree(rc);
-		rc = NULL;
-	} while (count > 0);
-
-	return total;
-
-error:
-	kfree(tc);
-	kfree(rc);
-	return err;
-}
-EXPORT_SYMBOL(p9_client_write);
-
-int
-p9_client_uread(struct p9_fid *fid, char __user *data, u64 offset, u32 count)
-{
-	int err, n, rsize, total;
-	struct p9_fcall *tc, *rc;
-	struct p9_client *clnt;
-
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d offset %llu count %d\n", fid->fid,
-					(long long unsigned) offset, count);
-	err = 0;
-	tc = NULL;
-	rc = NULL;
-	clnt = fid->clnt;
-	total = 0;
-
-	rsize = fid->iounit;
-	if (!rsize || rsize > clnt->msize-P9_IOHDRSZ)
-		rsize = clnt->msize - P9_IOHDRSZ;
-
-	do {
-		if (count < rsize)
-			rsize = count;
-
-		tc = p9_create_tread(fid->fid, offset, rsize);
-		if (IS_ERR(tc)) {
-			err = PTR_ERR(tc);
-			tc = NULL;
-			goto error;
-		}
-
-		err = p9_client_rpc(clnt, tc, &rc);
-		if (err)
-			goto error;
-
-		n = rc->params.rread.count;
-		if (n > count)
-			n = count;
-
-		err = copy_to_user(data, rc->params.rread.data, n);
-		if (err) {
-			err = -EFAULT;
-			goto error;
+		if (udata) {
+			err = copy_to_user(udata, rc->params.rread.data, n);
+			if (err) {
+				err = -EFAULT;
+				goto error;
+			}
+			udata += n;
 		}
 
 		count -= n;
-		data += n;
 		offset += n;
 		total += n;
 		kfree(tc);
@@ -1187,11 +1085,11 @@ error:
 	kfree(rc);
 	return err;
 }
-EXPORT_SYMBOL(p9_client_uread);
+EXPORT_SYMBOL(p9_client_read);
 
 int
-p9_client_uwrite(struct p9_fid *fid, const char __user *data, u64 offset,
-								   u32 count)
+p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
+							u64 offset, u32 count)
 {
 	int err, n, rsize, total;
 	struct p9_fcall *tc, *rc;
@@ -1213,7 +1111,10 @@ p9_client_uwrite(struct p9_fid *fid, const char __user *data, u64 offset,
 		if (count < rsize)
 			rsize = count;
 
-		tc = p9_create_twrite_u(fid->fid, offset, rsize, data);
+		if (data)
+			tc = p9_create_twrite(fid->fid, offset, rsize, data);
+		else
+			tc = p9_create_twrite_u(fid->fid, offset, rsize, udata);
 		if (IS_ERR(tc)) {
 			err = PTR_ERR(tc);
 			tc = NULL;
@@ -1226,7 +1127,12 @@ p9_client_uwrite(struct p9_fid *fid, const char __user *data, u64 offset,
 
 		n = rc->params.rread.count;
 		count -= n;
-		data += n;
+
+		if (data)
+			data += n;
+		else
+			udata += n;
+
 		offset += n;
 		total += n;
 		kfree(tc);
@@ -1242,7 +1148,7 @@ error:
 	kfree(rc);
 	return err;
 }
-EXPORT_SYMBOL(p9_client_uwrite);
+EXPORT_SYMBOL(p9_client_write);
 
 int p9_client_readn(struct p9_fid *fid, char *data, u64 offset, u32 count)
 {
@@ -1253,7 +1159,7 @@ int p9_client_readn(struct p9_fid *fid, char *data, u64 offset, u32 count)
 	n = 0;
 	total = 0;
 	while (count) {
-		n = p9_client_read(fid, data, offset, count);
+		n = p9_client_read(fid, data, NULL, offset, count);
 		if (n <= 0)
 			break;
 
-- 
cgit v1.2.3


From fbedadc16e5c888e4df9df3b1757de4993508d35 Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Mon, 13 Oct 2008 20:36:16 -0500
Subject: 9p: move readn meta-function from client to fs layer

There are a couple of methods in the client code which aren't actually
wire operations.  To keep things organized cleaner, these operations are
being moved to the fs layer.

This patch moves the readn meta-function (which executes multiple wire
reads until a buffer is full) to the fs layer.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 fs/9p/v9fs.c            |  2 +-
 fs/9p/v9fs_vfs.h        |  2 ++
 fs/9p/vfs_addr.c        |  5 +----
 fs/9p/vfs_file.c        | 57 +++++++++++++++++++++++++++++++++++++++++++++----
 include/net/9p/client.h |  1 -
 net/9p/client.c         | 26 ----------------------
 6 files changed, 57 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index b6b85cf01e0d..24eb01087b6d 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -234,7 +234,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	if (!v9ses->clnt->dotu)
 		v9ses->flags &= ~V9FS_EXTENDED;
 
-	v9ses->maxdata = v9ses->clnt->msize;
+	v9ses->maxdata = v9ses->clnt->msize - P9_IOHDRSZ;
 
 	/* for legacy mode, fall back to V9FS_ACCESS_ANY */
 	if (!v9fs_extended(v9ses) &&
diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index 57997fa14e69..046cff377f10 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -52,3 +52,5 @@ int v9fs_file_open(struct inode *inode, struct file *file);
 void v9fs_inode2stat(struct inode *inode, struct p9_stat *stat);
 void v9fs_dentry_release(struct dentry *);
 int v9fs_uflags2omode(int uflags, int extended);
+
+ssize_t v9fs_file_readn(struct file *, char *, char __user *, u32, u64);
diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c
index 97d3aed57983..6fcb1e7095cf 100644
--- a/fs/9p/vfs_addr.c
+++ b/fs/9p/vfs_addr.c
@@ -38,7 +38,6 @@
 
 #include "v9fs.h"
 #include "v9fs_vfs.h"
-#include "fid.h"
 
 /**
  * v9fs_vfs_readpage - read an entire page in from 9P
@@ -53,14 +52,12 @@ static int v9fs_vfs_readpage(struct file *filp, struct page *page)
 	int retval;
 	loff_t offset;
 	char *buffer;
-	struct p9_fid *fid;
 
 	P9_DPRINTK(P9_DEBUG_VFS, "\n");
-	fid = filp->private_data;
 	buffer = kmap(page);
 	offset = page_offset(page);
 
-	retval = p9_client_readn(fid, buffer, offset, PAGE_CACHE_SIZE);
+	retval = v9fs_file_readn(filp, buffer, NULL, offset, PAGE_CACHE_SIZE);
 	if (retval < 0)
 		goto done;
 
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 3819a195de8f..4d6d7657fb75 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -120,23 +120,72 @@ static int v9fs_file_lock(struct file *filp, int cmd, struct file_lock *fl)
 }
 
 /**
- * v9fs_file_read - read from a file
+ * v9fs_file_readn - read from a file
  * @filp: file pointer to read
  * @data: data buffer to read data into
+ * @udata: user data buffer to read data into
  * @count: size of buffer
  * @offset: offset at which to read data
  *
  */
+
+ssize_t
+v9fs_file_readn(struct file *filp, char *data, char __user *udata, u32 count,
+	       u64 offset)
+{
+	int n, total;
+	struct p9_fid *fid = filp->private_data;
+
+	P9_DPRINTK(P9_DEBUG_9P, "fid %d offset %llu count %d\n", fid->fid,
+					(long long unsigned) offset, count);
+
+	n = 0;
+	total = 0;
+	do {
+		n = p9_client_read(fid, data, udata, offset, count);
+		if (n <= 0)
+			break;
+
+		if (data)
+			data += n;
+		if (udata)
+			udata += n;
+
+		offset += n;
+		count -= n;
+		total += n;
+	} while (count > 0 && n == (fid->clnt->msize - P9_IOHDRSZ));
+
+	if (n < 0)
+		total = n;
+
+	return total;
+}
+
+/**
+ * v9fs_file_read - read from a file
+ * @filp: file pointer to read
+ * @udata: user data buffer to read data into
+ * @count: size of buffer
+ * @offset: offset at which to read data
+ *
+ */
+
 static ssize_t
-v9fs_file_read(struct file *filp, char __user * data, size_t count,
+v9fs_file_read(struct file *filp, char __user *udata, size_t count,
 	       loff_t * offset)
 {
 	int ret;
 	struct p9_fid *fid;
 
-	P9_DPRINTK(P9_DEBUG_VFS, "\n");
+	P9_DPRINTK(P9_DEBUG_VFS, "count %d offset %lld\n", count, *offset);
 	fid = filp->private_data;
-	ret = p9_client_read(fid, NULL, data, *offset, count);
+
+	if (count > (fid->clnt->msize - P9_IOHDRSZ))
+		ret = v9fs_file_readn(filp, NULL, udata, count, *offset);
+	else
+		ret = p9_client_read(fid, NULL, udata, *offset, count);
+
 	if (ret > 0)
 		*offset += ret;
 
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index c70a0f0b448d..bb8b0ede132d 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -203,7 +203,6 @@ int p9_client_clunk(struct p9_fid *fid);
 int p9_client_remove(struct p9_fid *fid);
 int p9_client_read(struct p9_fid *fid, char *data, char __user *udata,
 							u64 offset, u32 count);
-int p9_client_readn(struct p9_fid *fid, char *data, u64 offset, u32 count);
 int p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
 							u64 offset, u32 count);
 struct p9_stat *p9_client_stat(struct p9_fid *fid);
diff --git a/net/9p/client.c b/net/9p/client.c
index 5fc3aa1eb39b..d5ea042eabb0 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -1150,32 +1150,6 @@ error:
 }
 EXPORT_SYMBOL(p9_client_write);
 
-int p9_client_readn(struct p9_fid *fid, char *data, u64 offset, u32 count)
-{
-	int n, total;
-
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d offset %llu count %d\n", fid->fid,
-					(long long unsigned) offset, count);
-	n = 0;
-	total = 0;
-	while (count) {
-		n = p9_client_read(fid, data, NULL, offset, count);
-		if (n <= 0)
-			break;
-
-		data += n;
-		offset += n;
-		count -= n;
-		total += n;
-	}
-
-	if (n < 0)
-		total = n;
-
-	return total;
-}
-EXPORT_SYMBOL(p9_client_readn);
-
 static struct p9_stat *p9_clone_stat(struct p9_stat *st, int dotu)
 {
 	int n;
-- 
cgit v1.2.3


From 06b55b464ee5b305aca75cb7d9424b184bf07f68 Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Mon, 13 Oct 2008 20:36:15 -0500
Subject: 9p: move dirread to fs layer

Currently reading a directory is implemented in the client code.
This function is not actually a wire operation, but a meta operation
which calls read operations and processes the results.

This patch moves this functionality to the fs layer and calls component
wire operations instead of constructing their packets.  This provides a
cleaner separation and will help when we reorganize the client functions
and protocol processing methods.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 fs/9p/vfs_dir.c         |  54 +++++++++++++++++--------
 include/net/9p/client.h |   5 ---
 net/9p/client.c         | 103 ------------------------------------------------
 3 files changed, 38 insertions(+), 124 deletions(-)

(limited to 'include')

diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index e298fe194093..d7d0ac5a2ca3 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -69,32 +69,54 @@ static inline int dt_type(struct p9_stat *mistat)
 static int v9fs_dir_readdir(struct file *filp, void *dirent, filldir_t filldir)
 {
 	int over;
+	struct p9_stat st;
+	int err;
 	struct p9_fid *fid;
-	struct v9fs_session_info *v9ses;
-	struct inode *inode;
-	struct p9_stat *st;
+	int buflen;
+	char *statbuf;
+	int n, i = 0;
 
 	P9_DPRINTK(P9_DEBUG_VFS, "name %s\n", filp->f_path.dentry->d_name.name);
-	inode = filp->f_path.dentry->d_inode;
-	v9ses = v9fs_inode2v9ses(inode);
 	fid = filp->private_data;
-	while ((st = p9_client_dirread(fid, filp->f_pos)) != NULL) {
-		if (IS_ERR(st))
-			return PTR_ERR(st);
 
-		over = filldir(dirent, st->name.str, st->name.len, filp->f_pos,
-			v9fs_qid2ino(&st->qid), dt_type(st));
+	buflen = fid->clnt->msize - P9_IOHDRSZ;
+	statbuf = kmalloc(buflen, GFP_KERNEL);
+	if (!statbuf)
+		return -ENOMEM;
 
-		if (over)
+	while (1) {
+		err = v9fs_file_readn(filp, statbuf, NULL, fid->rdir_fpos,
+									buflen);
+		if (err <= 0)
 			break;
 
-		filp->f_pos += st->size;
-		kfree(st);
-		st = NULL;
+		n = err;
+		while (i < n) {
+			err = p9_deserialize_stat(statbuf + i, buflen-i, &st,
+							fid->clnt->dotu);
+			if (!err) {
+				err = -EIO;
+				goto free_and_exit;
+			}
+
+			i += err;
+			fid->rdir_fpos += err;
+
+			over = filldir(dirent, st.name.str, st.name.len,
+			    filp->f_pos, v9fs_qid2ino(&st.qid), dt_type(&st));
+
+			filp->f_pos += st.size;
+
+			if (over) {
+				err = 0;
+				goto free_and_exit;
+			}
+		}
 	}
 
-	kfree(st);
-	return 0;
+free_and_exit:
+	kfree(statbuf);
+	return err;
 }
 
 
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index bb8b0ede132d..eeb7d922816e 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -163,8 +163,6 @@ struct p9_client {
  * @uid: the numeric uid of the local user who owns this handle
  * @aux: transport specific information (unused?)
  * @rdir_fpos: tracks offset of file position when reading directory contents
- * @rdir_pos: (unused?)
- * @rdir_fcall: holds response of last directory read request
  * @flist: per-client-instance fid tracking
  * @dlist: per-dentry fid tracking
  *
@@ -181,8 +179,6 @@ struct p9_fid {
 	void *aux;
 
 	int rdir_fpos;
-	int rdir_pos;
-	struct p9_fcall *rdir_fcall;
 	struct list_head flist;
 	struct list_head dlist;	/* list of all fids attached to a dentry */
 };
@@ -207,7 +203,6 @@ int p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
 							u64 offset, u32 count);
 struct p9_stat *p9_client_stat(struct p9_fid *fid);
 int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst);
-struct p9_stat *p9_client_dirread(struct p9_fid *fid, u64 offset);
 
 struct p9_req_t *p9_tag_lookup(struct p9_client *, u16);
 void p9_client_cb(struct p9_client *c, struct p9_req_t *req);
diff --git a/net/9p/client.c b/net/9p/client.c
index d5ea042eabb0..90ee9efeede3 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -559,8 +559,6 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt)
 	memset(&fid->qid, 0, sizeof(struct p9_qid));
 	fid->mode = -1;
 	fid->rdir_fpos = 0;
-	fid->rdir_pos = 0;
-	fid->rdir_fcall = NULL;
 	fid->uid = current->fsuid;
 	fid->clnt = clnt;
 	fid->aux = NULL;
@@ -586,7 +584,6 @@ static void p9_fid_destroy(struct p9_fid *fid)
 	spin_lock(&clnt->lock);
 	list_del(&fid->flist);
 	spin_unlock(&clnt->lock);
-	kfree(fid->rdir_fcall);
 	kfree(fid);
 }
 
@@ -1261,103 +1258,3 @@ done:
 	return err;
 }
 EXPORT_SYMBOL(p9_client_wstat);
-
-struct p9_stat *p9_client_dirread(struct p9_fid *fid, u64 offset)
-{
-	int err, n, m;
-	struct p9_fcall *tc, *rc;
-	struct p9_client *clnt;
-	struct p9_stat st, *ret;
-
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d offset %llu\n", fid->fid,
-						(long long unsigned) offset);
-	err = 0;
-	tc = NULL;
-	rc = NULL;
-	ret = NULL;
-	clnt = fid->clnt;
-
-	/* if the offset is below or above the current response, free it */
-	if (offset < fid->rdir_fpos || (fid->rdir_fcall &&
-		offset >= fid->rdir_fpos+fid->rdir_fcall->params.rread.count)) {
-		fid->rdir_pos = 0;
-		if (fid->rdir_fcall)
-			fid->rdir_fpos += fid->rdir_fcall->params.rread.count;
-
-		kfree(fid->rdir_fcall);
-		fid->rdir_fcall = NULL;
-		if (offset < fid->rdir_fpos)
-			fid->rdir_fpos = 0;
-	}
-
-	if (!fid->rdir_fcall) {
-		n = fid->iounit;
-		if (!n || n > clnt->msize-P9_IOHDRSZ)
-			n = clnt->msize - P9_IOHDRSZ;
-
-		while (1) {
-			if (fid->rdir_fcall) {
-				fid->rdir_fpos +=
-					fid->rdir_fcall->params.rread.count;
-				kfree(fid->rdir_fcall);
-				fid->rdir_fcall = NULL;
-			}
-
-			tc = p9_create_tread(fid->fid, fid->rdir_fpos, n);
-			if (IS_ERR(tc)) {
-				err = PTR_ERR(tc);
-				tc = NULL;
-				goto error;
-			}
-
-			err = p9_client_rpc(clnt, tc, &rc);
-			if (err)
-				goto error;
-
-			n = rc->params.rread.count;
-			if (n == 0)
-				goto done;
-
-			fid->rdir_fcall = rc;
-			rc = NULL;
-			if (offset >= fid->rdir_fpos &&
-						offset < fid->rdir_fpos+n)
-				break;
-		}
-
-		fid->rdir_pos = 0;
-	}
-
-	m = offset - fid->rdir_fpos;
-	if (m < 0)
-		goto done;
-
-	n = p9_deserialize_stat(fid->rdir_fcall->params.rread.data + m,
-		fid->rdir_fcall->params.rread.count - m, &st, clnt->dotu);
-
-	if (!n) {
-		err = -EIO;
-		goto error;
-	}
-
-	fid->rdir_pos += n;
-	st.size = n;
-	ret = p9_clone_stat(&st, clnt->dotu);
-	if (IS_ERR(ret)) {
-		err = PTR_ERR(ret);
-		ret = NULL;
-		goto error;
-	}
-
-done:
-	kfree(tc);
-	kfree(rc);
-	return ret;
-
-error:
-	kfree(tc);
-	kfree(rc);
-	kfree(ret);
-	return ERR_PTR(err);
-}
-EXPORT_SYMBOL(p9_client_dirread);
-- 
cgit v1.2.3


From ace51c4dd2f968f427c4627023759ae7e3786cba Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Mon, 13 Oct 2008 20:40:27 -0500
Subject: 9p: add new protocol support code

This adds a new protocol processing support code based on Anthony Liguori's
9p library code.  This code performs protocol marshalling/unmarshalling using
printf like strings to represent protocol elements.  It is my intent to use
them to replace the current functions in conv.c as well as the
p9_create_* functions.

This should make the client implementation much more clear, and also make it
much easier to add new protocol extensions by limiting the number of places
in which changes need to be made.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/9p.h |   8 +-
 net/9p/Makefile     |   1 +
 net/9p/protocol.c   | 457 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 net/9p/protocol.h   |  31 ++++
 4 files changed, 496 insertions(+), 1 deletion(-)
 create mode 100644 net/9p/protocol.c
 create mode 100644 net/9p/protocol.h

(limited to 'include')

diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index fb163e2e0de6..f9e25268b70f 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -509,6 +509,8 @@ struct p9_rwstat {
  * @size: prefixed length of the structure
  * @id: protocol operating identifier of type &p9_msg_t
  * @tag: transaction id of the request
+ * @offset: used by marshalling routines to track currentposition in buffer
+ * @capacity: used by marshalling routines to track total capacity
  * @sdata: payload
  * @params: per-operation parameters
  *
@@ -523,7 +525,11 @@ struct p9_fcall {
 	u32 size;
 	u8 id;
 	u16 tag;
-	void *sdata;
+
+	size_t offset;
+	size_t capacity;
+
+	uint8_t *sdata;
 
 	union {
 		struct p9_tversion tversion;
diff --git a/net/9p/Makefile b/net/9p/Makefile
index 519219480db1..84c23499a293 100644
--- a/net/9p/Makefile
+++ b/net/9p/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_NET_9P_VIRTIO) += 9pnet_virtio.o
 	error.o \
 	fcprint.o \
 	util.o \
+	protocol.o \
 	trans_fd.o \
 
 9pnet_virtio-objs := \
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
new file mode 100644
index 000000000000..43e98220e9a4
--- /dev/null
+++ b/net/9p/protocol.c
@@ -0,0 +1,457 @@
+/*
+ * net/9p/protocol.c
+ *
+ * 9P Protocol Support Code
+ *
+ *  Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  Base on code from Anthony Liguori <aliguori@us.ibm.com>
+ *  Copyright (C) 2008 by IBM, Corp.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include "protocol.h"
+
+#ifndef MIN
+#define MIN(a, b) (((a) < (b)) ? (a) : (b))
+#endif
+
+#ifndef MAX
+#define MAX(a, b) (((a) > (b)) ? (a) : (b))
+#endif
+
+#ifndef offset_of
+#define offset_of(type, memb) \
+	((unsigned long)(&((type *)0)->memb))
+#endif
+#ifndef container_of
+#define container_of(obj, type, memb) \
+	((type *)(((char *)obj) - offset_of(type, memb)))
+#endif
+
+static int
+p9pdu_writef(struct p9_fcall *pdu, int optional, const char *fmt, ...);
+
+void p9stat_free(struct p9_wstat *stbuf)
+{
+	kfree(stbuf->name);
+	kfree(stbuf->uid);
+	kfree(stbuf->gid);
+	kfree(stbuf->muid);
+	kfree(stbuf->extension);
+}
+EXPORT_SYMBOL(p9stat_free);
+
+static size_t pdu_read(struct p9_fcall *pdu, void *data, size_t size)
+{
+	size_t len = MIN(pdu->size - pdu->offset, size);
+	memcpy(data, &pdu->sdata[pdu->offset], len);
+	pdu->offset += len;
+	return size - len;
+}
+
+static size_t pdu_write(struct p9_fcall *pdu, const void *data, size_t size)
+{
+	size_t len = MIN(pdu->capacity - pdu->size, size);
+	memcpy(&pdu->sdata[pdu->size], data, len);
+	pdu->size += len;
+	return size - len;
+}
+
+/*
+	b - int8_t
+	w - int16_t
+	d - int32_t
+	q - int64_t
+	s - string
+	S - stat
+	Q - qid
+	D - data blob (int32_t size followed by void *, results are not freed)
+	T - array of strings (int16_t count, followed by strings)
+	R - array of qids (int16_t count, followed by qids)
+	? - if optional = 1, continue parsing
+*/
+
+static int
+p9pdu_vreadf(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap)
+{
+	const char *ptr;
+	int errcode = 0;
+
+	for (ptr = fmt; *ptr; ptr++) {
+		switch (*ptr) {
+		case 'b':{
+				int8_t *val = va_arg(ap, int8_t *);
+				if (pdu_read(pdu, val, sizeof(*val))) {
+					errcode = -EFAULT;
+					break;
+				}
+			}
+			break;
+		case 'w':{
+				int16_t *val = va_arg(ap, int16_t *);
+				if (pdu_read(pdu, val, sizeof(*val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = cpu_to_le16(*val);
+			}
+			break;
+		case 'd':{
+				int32_t *val = va_arg(ap, int32_t *);
+				if (pdu_read(pdu, val, sizeof(*val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = cpu_to_le32(*val);
+			}
+			break;
+		case 'q':{
+				int64_t *val = va_arg(ap, int64_t *);
+				if (pdu_read(pdu, val, sizeof(*val))) {
+					errcode = -EFAULT;
+					break;
+				}
+				*val = cpu_to_le64(*val);
+			}
+			break;
+		case 's':{
+				char **ptr = va_arg(ap, char **);
+				int16_t len;
+				int size;
+
+				errcode = p9pdu_readf(pdu, optional, "w", &len);
+				if (errcode)
+					break;
+
+				size = MAX(len, 0);
+
+				*ptr = kmalloc(size + 1, GFP_KERNEL);
+				if (*ptr == NULL) {
+					errcode = -EFAULT;
+					break;
+				}
+				if (pdu_read(pdu, *ptr, size)) {
+					errcode = -EFAULT;
+					kfree(*ptr);
+					*ptr = NULL;
+				} else
+					(*ptr)[size] = 0;
+			}
+			break;
+		case 'Q':{
+				struct p9_qid *qid =
+				    va_arg(ap, struct p9_qid *);
+
+				errcode = p9pdu_readf(pdu, optional, "bdq",
+						      &qid->type, &qid->version,
+						      &qid->path);
+			}
+			break;
+		case 'S':{
+				struct p9_wstat *stbuf =
+				    va_arg(ap, struct p9_wstat *);
+
+				stbuf->extension = NULL;
+				stbuf->n_uid = stbuf->n_gid = stbuf->n_muid =
+				    -1;
+
+				errcode =
+				    p9pdu_readf(pdu, optional,
+						"wwdQdddqssss?sddd",
+						&stbuf->size, &stbuf->type,
+						&stbuf->dev, &stbuf->qid,
+						&stbuf->mode, &stbuf->atime,
+						&stbuf->mtime, &stbuf->length,
+						&stbuf->name, &stbuf->uid,
+						&stbuf->gid, &stbuf->muid,
+						&stbuf->extension,
+						&stbuf->n_uid, &stbuf->n_gid,
+						&stbuf->n_muid);
+				if (errcode)
+					p9stat_free(stbuf);
+			}
+			break;
+		case 'D':{
+				int32_t *count = va_arg(ap, int32_t *);
+				void **data = va_arg(ap, void **);
+
+				errcode =
+				    p9pdu_readf(pdu, optional, "d", count);
+				if (!errcode) {
+					*count =
+					    MIN(*count,
+						pdu->size - pdu->offset);
+					*data = &pdu->sdata[pdu->offset];
+				}
+			}
+			break;
+		case 'T':{
+				int16_t *nwname = va_arg(ap, int16_t *);
+				char ***wnames = va_arg(ap, char ***);
+
+				errcode =
+				    p9pdu_readf(pdu, optional, "w", nwname);
+				if (!errcode) {
+					*wnames =
+					    kmalloc(sizeof(char *) * *nwname,
+						    GFP_KERNEL);
+					if (!*wnames)
+						errcode = -ENOMEM;
+				}
+
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < *nwname; i++) {
+						errcode =
+						    p9pdu_readf(pdu, optional,
+								"s",
+								&(*wnames)[i]);
+						if (errcode)
+							break;
+					}
+				}
+
+				if (errcode) {
+					if (*wnames) {
+						int i;
+
+						for (i = 0; i < *nwname; i++)
+							kfree((*wnames)[i]);
+					}
+					kfree(*wnames);
+					*wnames = NULL;
+				}
+			}
+			break;
+		case 'R':{
+				int16_t *nwqid = va_arg(ap, int16_t *);
+				struct p9_qid **wqids =
+				    va_arg(ap, struct p9_qid **);
+
+				*wqids = NULL;
+
+				errcode =
+				    p9pdu_readf(pdu, optional, "w", nwqid);
+				if (!errcode) {
+					*wqids =
+					    kmalloc(*nwqid *
+						    sizeof(struct p9_qid),
+						    GFP_KERNEL);
+					if (*wqids == NULL)
+						errcode = -ENOMEM;
+				}
+
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < *nwqid; i++) {
+						errcode =
+						    p9pdu_readf(pdu, optional,
+								"Q",
+								&(*wqids)[i]);
+						if (errcode)
+							break;
+					}
+				}
+
+				if (errcode) {
+					kfree(*wqids);
+					*wqids = NULL;
+				}
+			}
+			break;
+		case '?':
+			if (!optional)
+				return 0;
+			break;
+		default:
+			BUG();
+			break;
+		}
+
+		if (errcode)
+			break;
+	}
+
+	return errcode;
+}
+
+int
+p9pdu_vwritef(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap)
+{
+	const char *ptr;
+	int errcode = 0;
+
+	for (ptr = fmt; *ptr; ptr++) {
+		switch (*ptr) {
+		case 'b':{
+				int8_t val = va_arg(ap, int);
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'w':{
+				int16_t val = va_arg(ap, int);
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'd':{
+				int32_t val = va_arg(ap, int32_t);
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'q':{
+				int64_t val = va_arg(ap, int64_t);
+				if (pdu_write(pdu, &val, sizeof(val)))
+					errcode = -EFAULT;
+			}
+			break;
+		case 's':{
+				const char *ptr = va_arg(ap, const char *);
+				int16_t len = 0;
+
+				if (ptr)
+					len = MIN(strlen(ptr), USHORT_MAX);
+
+				errcode = p9pdu_writef(pdu, optional, "w", len);
+				if (!errcode && pdu_write(pdu, ptr, len))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'Q':{
+				const struct p9_qid *qid =
+				    va_arg(ap, const struct p9_qid *);
+				errcode =
+				    p9pdu_writef(pdu, optional, "bdq",
+						 qid->type, qid->version,
+						 qid->path);
+			} break;
+		case 'S':{
+				const struct p9_wstat *stbuf =
+				    va_arg(ap, const struct p9_wstat *);
+				errcode =
+				    p9pdu_writef(pdu, optional,
+						 "wwdQdddqssss?sddd",
+						 stbuf->size, stbuf->type,
+						 stbuf->dev, stbuf->qid,
+						 stbuf->mode, stbuf->atime,
+						 stbuf->mtime, stbuf->length,
+						 stbuf->name, stbuf->uid,
+						 stbuf->gid, stbuf->muid,
+						 stbuf->extension, stbuf->n_uid,
+						 stbuf->n_gid, stbuf->n_muid);
+			} break;
+		case 'D':{
+				int32_t count = va_arg(ap, int32_t);
+				const void *data = va_arg(ap, const void *);
+
+				errcode =
+				    p9pdu_writef(pdu, optional, "d", count);
+				if (!errcode && pdu_write(pdu, data, count))
+					errcode = -EFAULT;
+			}
+			break;
+		case 'T':{
+				int16_t nwname = va_arg(ap, int);
+				const char **wnames = va_arg(ap, const char **);
+
+				errcode =
+				    p9pdu_writef(pdu, optional, "w", nwname);
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < nwname; i++) {
+						errcode =
+						    p9pdu_writef(pdu, optional,
+								 "s",
+								 wnames[i]);
+						if (errcode)
+							break;
+					}
+				}
+			}
+			break;
+		case 'R':{
+				int16_t nwqid = va_arg(ap, int);
+				struct p9_qid *wqids =
+				    va_arg(ap, struct p9_qid *);
+
+				errcode =
+				    p9pdu_writef(pdu, optional, "w", nwqid);
+				if (!errcode) {
+					int i;
+
+					for (i = 0; i < nwqid; i++) {
+						errcode =
+						    p9pdu_writef(pdu, optional,
+								 "Q",
+								 &wqids[i]);
+						if (errcode)
+							break;
+					}
+				}
+			}
+			break;
+		case '?':
+			if (!optional)
+				return 0;
+			break;
+		default:
+			BUG();
+			break;
+		}
+
+		if (errcode)
+			break;
+	}
+
+	return errcode;
+}
+
+int p9pdu_readf(struct p9_fcall *pdu, int optional, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = p9pdu_vreadf(pdu, optional, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
+
+static int
+p9pdu_writef(struct p9_fcall *pdu, int optional, const char *fmt, ...)
+{
+	va_list ap;
+	int ret;
+
+	va_start(ap, fmt);
+	ret = p9pdu_vwritef(pdu, optional, fmt, ap);
+	va_end(ap);
+
+	return ret;
+}
diff --git a/net/9p/protocol.h b/net/9p/protocol.h
new file mode 100644
index 000000000000..596ee10d506f
--- /dev/null
+++ b/net/9p/protocol.h
@@ -0,0 +1,31 @@
+/*
+ * net/9p/protocol.h
+ *
+ * 9P Protocol Support Code
+ *
+ *  Copyright (C) 2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *
+ *  Base on code from Anthony Liguori <aliguori@us.ibm.com>
+ *  Copyright (C) 2008 by IBM, Corp.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+int
+p9pdu_vwritef(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap);
+
+int p9pdu_readf(struct p9_fcall *pdu, int optional, const char *fmt, ...);
-- 
cgit v1.2.3


From 51d71f9f7a639c8a39401de1ec5ce9b0b6476c99 Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Thu, 16 Oct 2008 08:29:31 -0500
Subject: 9p: remove 9p fcall debug prints

One of the current debug options allows users to get a verbose dump of fcalls.
This isn't really necessary as correctly parsed protocol frames can be printed
as part of the code in the client functions.  The consolidated printfcalls
structure would require new entries to be added for every extension.  This
patch removes the debug print methods and their use.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/9p.h |   1 -
 net/9p/Makefile     |   1 -
 net/9p/client.c     |   9 --
 net/9p/fcprint.c    | 366 ----------------------------------------------------
 net/9p/trans_fd.c   |   9 --
 5 files changed, 386 deletions(-)
 delete mode 100644 net/9p/fcprint.c

(limited to 'include')

diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index f9e25268b70f..46d0b8f8e5ec 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -590,7 +590,6 @@ struct p9_fcall *p9_create_tstat(u32 fid);
 struct p9_fcall *p9_create_twstat(u32 fid, struct p9_wstat *wstat,
 	int dotu);
 
-int p9_printfcall(char *buf, int buflen, struct p9_fcall *fc, int dotu);
 int p9_errstr2errno(char *errstr, int len);
 
 struct p9_idpool *p9_idpool_create(void);
diff --git a/net/9p/Makefile b/net/9p/Makefile
index 84c23499a293..c3302d88b808 100644
--- a/net/9p/Makefile
+++ b/net/9p/Makefile
@@ -6,7 +6,6 @@ obj-$(CONFIG_NET_9P_VIRTIO) += 9pnet_virtio.o
 	client.o \
 	conv.o \
 	error.o \
-	fcprint.o \
 	util.o \
 	protocol.o \
 	trans_fd.o \
diff --git a/net/9p/client.c b/net/9p/client.c
index a9982df00a3a..6004fded6682 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -502,15 +502,6 @@ again:
 		goto reterr;
 	}
 
-#ifdef CONFIG_NET_9P_DEBUG
-	if ((p9_debug_level&P9_DEBUG_FCALL) == P9_DEBUG_FCALL) {
-		char buf[150];
-
-		p9_printfcall(buf, sizeof(buf), req->rc, c->dotu);
-		printk(KERN_NOTICE ">>> %p %s\n", c, buf);
-	}
-#endif
-
 	if (req->rc->id == P9_RERROR) {
 		int ecode = req->rc->params.rerror.errno;
 		struct p9_str *ename = &req->rc->params.rerror.error;
diff --git a/net/9p/fcprint.c b/net/9p/fcprint.c
deleted file mode 100644
index 53dd8e28dd8a..000000000000
--- a/net/9p/fcprint.c
+++ /dev/null
@@ -1,366 +0,0 @@
-/*
- *  net/9p/fcprint.c
- *
- *  Print 9P call.
- *
- *  Copyright (C) 2005 by Latchesar Ionkov <lucho@ionkov.net>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2
- *  as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to:
- *  Free Software Foundation
- *  51 Franklin Street, Fifth Floor
- *  Boston, MA  02111-1301  USA
- *
- */
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/idr.h>
-#include <net/9p/9p.h>
-
-#ifdef CONFIG_NET_9P_DEBUG
-
-static int
-p9_printqid(char *buf, int buflen, struct p9_qid *q)
-{
-	int n;
-	char b[10];
-
-	n = 0;
-	if (q->type & P9_QTDIR)
-		b[n++] = 'd';
-	if (q->type & P9_QTAPPEND)
-		b[n++] = 'a';
-	if (q->type & P9_QTAUTH)
-		b[n++] = 'A';
-	if (q->type & P9_QTEXCL)
-		b[n++] = 'l';
-	if (q->type & P9_QTTMP)
-		b[n++] = 't';
-	if (q->type & P9_QTSYMLINK)
-		b[n++] = 'L';
-	b[n] = '\0';
-
-	return scnprintf(buf, buflen, "(%.16llx %x %s)",
-					(long long int) q->path, q->version, b);
-}
-
-static int
-p9_printperm(char *buf, int buflen, int perm)
-{
-	int n;
-	char b[15];
-
-	n = 0;
-	if (perm & P9_DMDIR)
-		b[n++] = 'd';
-	if (perm & P9_DMAPPEND)
-		b[n++] = 'a';
-	if (perm & P9_DMAUTH)
-		b[n++] = 'A';
-	if (perm & P9_DMEXCL)
-		b[n++] = 'l';
-	if (perm & P9_DMTMP)
-		b[n++] = 't';
-	if (perm & P9_DMDEVICE)
-		b[n++] = 'D';
-	if (perm & P9_DMSOCKET)
-		b[n++] = 'S';
-	if (perm & P9_DMNAMEDPIPE)
-		b[n++] = 'P';
-	if (perm & P9_DMSYMLINK)
-		b[n++] = 'L';
-	b[n] = '\0';
-
-	return scnprintf(buf, buflen, "%s%03o", b, perm&077);
-}
-
-static int
-p9_printstat(char *buf, int buflen, struct p9_stat *st, int extended)
-{
-	int n;
-
-	n = scnprintf(buf, buflen, "'%.*s' '%.*s'", st->name.len,
-		st->name.str, st->uid.len, st->uid.str);
-	if (extended)
-		n += scnprintf(buf+n, buflen-n, "(%d)", st->n_uid);
-
-	n += scnprintf(buf+n, buflen-n, " '%.*s'", st->gid.len, st->gid.str);
-	if (extended)
-		n += scnprintf(buf+n, buflen-n, "(%d)", st->n_gid);
-
-	n += scnprintf(buf+n, buflen-n, " '%.*s'", st->muid.len, st->muid.str);
-	if (extended)
-		n += scnprintf(buf+n, buflen-n, "(%d)", st->n_muid);
-
-	n += scnprintf(buf+n, buflen-n, " q ");
-	n += p9_printqid(buf+n, buflen-n, &st->qid);
-	n += scnprintf(buf+n, buflen-n, " m ");
-	n += p9_printperm(buf+n, buflen-n, st->mode);
-	n += scnprintf(buf+n, buflen-n, " at %d mt %d l %lld",
-		st->atime, st->mtime, (long long int) st->length);
-
-	if (extended)
-		n += scnprintf(buf+n, buflen-n, " ext '%.*s'",
-			st->extension.len, st->extension.str);
-
-	return n;
-}
-
-static int
-p9_dumpdata(char *buf, int buflen, u8 *data, int datalen)
-{
-	int i, n;
-
-	i = n = 0;
-	while (i < datalen) {
-		n += scnprintf(buf + n, buflen - n, "%02x", data[i]);
-		if (i%4 == 3)
-			n += scnprintf(buf + n, buflen - n, " ");
-		if (i%32 == 31)
-			n += scnprintf(buf + n, buflen - n, "\n");
-
-		i++;
-	}
-	n += scnprintf(buf + n, buflen - n, "\n");
-
-	return n;
-}
-
-static int
-p9_printdata(char *buf, int buflen, u8 *data, int datalen)
-{
-	return p9_dumpdata(buf, buflen, data, datalen < 16?datalen:16);
-}
-
-/**
- * p9_printfcall - decode and print a protocol structure into a buffer
- * @buf: buffer to deposit decoded structure into
- * @buflen: available space in buffer
- * @fc: protocol rpc structure of type &p9_fcall
- * @extended: whether or not session is operating with extended protocol
- */
-
-int
-p9_printfcall(char *buf, int buflen, struct p9_fcall *fc, int extended)
-{
-	int i, ret, type, tag;
-
-	if (!fc)
-		return scnprintf(buf, buflen, "<NULL>");
-
-	type = fc->id;
-	tag = fc->tag;
-
-	ret = 0;
-	switch (type) {
-	case P9_TVERSION:
-		ret += scnprintf(buf+ret, buflen-ret,
-				"Tversion tag %u msize %u version '%.*s'", tag,
-				fc->params.tversion.msize,
-				fc->params.tversion.version.len,
-				fc->params.tversion.version.str);
-		break;
-
-	case P9_RVERSION:
-		ret += scnprintf(buf+ret, buflen-ret,
-				"Rversion tag %u msize %u version '%.*s'", tag,
-				fc->params.rversion.msize,
-				fc->params.rversion.version.len,
-				fc->params.rversion.version.str);
-		break;
-
-	case P9_TAUTH:
-		ret += scnprintf(buf+ret, buflen-ret,
-			"Tauth tag %u afid %d uname '%.*s' aname '%.*s'", tag,
-			fc->params.tauth.afid, fc->params.tauth.uname.len,
-			fc->params.tauth.uname.str, fc->params.tauth.aname.len,
-			fc->params.tauth.aname.str);
-		break;
-
-	case P9_RAUTH:
-		ret += scnprintf(buf+ret, buflen-ret, "Rauth tag %u qid ", tag);
-		p9_printqid(buf+ret, buflen-ret, &fc->params.rauth.qid);
-		break;
-
-	case P9_TATTACH:
-		ret += scnprintf(buf+ret, buflen-ret,
-		 "Tattach tag %u fid %d afid %d uname '%.*s' aname '%.*s'", tag,
-		 fc->params.tattach.fid, fc->params.tattach.afid,
-		 fc->params.tattach.uname.len, fc->params.tattach.uname.str,
-		 fc->params.tattach.aname.len, fc->params.tattach.aname.str);
-		break;
-
-	case P9_RATTACH:
-		ret += scnprintf(buf+ret, buflen-ret, "Rattach tag %u qid ",
-									tag);
-		p9_printqid(buf+ret, buflen-ret, &fc->params.rattach.qid);
-		break;
-
-	case P9_RERROR:
-		ret += scnprintf(buf+ret, buflen-ret,
-				"Rerror tag %u ename '%.*s'", tag,
-				fc->params.rerror.error.len,
-				fc->params.rerror.error.str);
-		if (extended)
-			ret += scnprintf(buf+ret, buflen-ret, " ecode %d\n",
-				fc->params.rerror.errno);
-		break;
-
-	case P9_TFLUSH:
-		ret += scnprintf(buf+ret, buflen-ret, "Tflush tag %u oldtag %u",
-			tag, fc->params.tflush.oldtag);
-		break;
-
-	case P9_RFLUSH:
-		ret += scnprintf(buf+ret, buflen-ret, "Rflush tag %u", tag);
-		break;
-
-	case P9_TWALK:
-		ret += scnprintf(buf+ret, buflen-ret,
-			"Twalk tag %u fid %d newfid %d nwname %d", tag,
-			fc->params.twalk.fid, fc->params.twalk.newfid,
-			fc->params.twalk.nwname);
-		for (i = 0; i < fc->params.twalk.nwname; i++)
-			ret += scnprintf(buf+ret, buflen-ret, " '%.*s'",
-				fc->params.twalk.wnames[i].len,
-				fc->params.twalk.wnames[i].str);
-		break;
-
-	case P9_RWALK:
-		ret += scnprintf(buf+ret, buflen-ret, "Rwalk tag %u nwqid %d",
-			tag, fc->params.rwalk.nwqid);
-		for (i = 0; i < fc->params.rwalk.nwqid; i++)
-			ret += p9_printqid(buf+ret, buflen-ret,
-				&fc->params.rwalk.wqids[i]);
-		break;
-
-	case P9_TOPEN:
-		ret += scnprintf(buf+ret, buflen-ret,
-			"Topen tag %u fid %d mode %d", tag,
-			fc->params.topen.fid, fc->params.topen.mode);
-		break;
-
-	case P9_ROPEN:
-		ret += scnprintf(buf+ret, buflen-ret, "Ropen tag %u", tag);
-		ret += p9_printqid(buf+ret, buflen-ret, &fc->params.ropen.qid);
-		ret += scnprintf(buf+ret, buflen-ret, " iounit %d",
-			fc->params.ropen.iounit);
-		break;
-
-	case P9_TCREATE:
-		ret += scnprintf(buf+ret, buflen-ret,
-			"Tcreate tag %u fid %d name '%.*s' perm ", tag,
-			fc->params.tcreate.fid, fc->params.tcreate.name.len,
-			fc->params.tcreate.name.str);
-
-		ret += p9_printperm(buf+ret, buflen-ret,
-						fc->params.tcreate.perm);
-		ret += scnprintf(buf+ret, buflen-ret, " mode %d",
-			fc->params.tcreate.mode);
-		break;
-
-	case P9_RCREATE:
-		ret += scnprintf(buf+ret, buflen-ret, "Rcreate tag %u", tag);
-		ret += p9_printqid(buf+ret, buflen-ret,
-						&fc->params.rcreate.qid);
-		ret += scnprintf(buf+ret, buflen-ret, " iounit %d",
-			fc->params.rcreate.iounit);
-		break;
-
-	case P9_TREAD:
-		ret += scnprintf(buf+ret, buflen-ret,
-			"Tread tag %u fid %d offset %lld count %u", tag,
-			fc->params.tread.fid,
-			(long long int) fc->params.tread.offset,
-			fc->params.tread.count);
-		break;
-
-	case P9_RREAD:
-		ret += scnprintf(buf+ret, buflen-ret,
-			"Rread tag %u count %u data ", tag,
-			fc->params.rread.count);
-		ret += p9_printdata(buf+ret, buflen-ret, fc->params.rread.data,
-			fc->params.rread.count);
-		break;
-
-	case P9_TWRITE:
-		ret += scnprintf(buf+ret, buflen-ret,
-			"Twrite tag %u fid %d offset %lld count %u data ",
-			tag, fc->params.twrite.fid,
-			(long long int) fc->params.twrite.offset,
-			fc->params.twrite.count);
-		ret += p9_printdata(buf+ret, buflen-ret, fc->params.twrite.data,
-			fc->params.twrite.count);
-		break;
-
-	case P9_RWRITE:
-		ret += scnprintf(buf+ret, buflen-ret, "Rwrite tag %u count %u",
-			tag, fc->params.rwrite.count);
-		break;
-
-	case P9_TCLUNK:
-		ret += scnprintf(buf+ret, buflen-ret, "Tclunk tag %u fid %d",
-			tag, fc->params.tclunk.fid);
-		break;
-
-	case P9_RCLUNK:
-		ret += scnprintf(buf+ret, buflen-ret, "Rclunk tag %u", tag);
-		break;
-
-	case P9_TREMOVE:
-		ret += scnprintf(buf+ret, buflen-ret, "Tremove tag %u fid %d",
-			tag, fc->params.tremove.fid);
-		break;
-
-	case P9_RREMOVE:
-		ret += scnprintf(buf+ret, buflen-ret, "Rremove tag %u", tag);
-		break;
-
-	case P9_TSTAT:
-		ret += scnprintf(buf+ret, buflen-ret, "Tstat tag %u fid %d",
-			tag, fc->params.tstat.fid);
-		break;
-
-	case P9_RSTAT:
-		ret += scnprintf(buf+ret, buflen-ret, "Rstat tag %u ", tag);
-		ret += p9_printstat(buf+ret, buflen-ret, &fc->params.rstat.stat,
-			extended);
-		break;
-
-	case P9_TWSTAT:
-		ret += scnprintf(buf+ret, buflen-ret, "Twstat tag %u fid %d ",
-			tag, fc->params.twstat.fid);
-		ret += p9_printstat(buf+ret, buflen-ret,
-					&fc->params.twstat.stat, extended);
-		break;
-
-	case P9_RWSTAT:
-		ret += scnprintf(buf+ret, buflen-ret, "Rwstat tag %u", tag);
-		break;
-
-	default:
-		ret += scnprintf(buf+ret, buflen-ret, "unknown type %d", type);
-		break;
-	}
-
-	return ret;
-}
-#else
-int
-p9_printfcall(char *buf, int buflen, struct p9_fcall *fc, int extended)
-{
-	return 0;
-}
-#endif /* CONFIG_NET_9P_DEBUG */
-EXPORT_SYMBOL(p9_printfcall);
-
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index c07f2ab8d0f7..95c9b949d1a5 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -650,15 +650,6 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
 	if (m->err < 0)
 		return m->err;
 
-#ifdef CONFIG_NET_9P_DEBUG
-	if ((p9_debug_level&P9_DEBUG_FCALL) == P9_DEBUG_FCALL) {
-		char buf[150];
-
-		p9_printfcall(buf, sizeof(buf), req->tc, client->dotu);
-		printk(KERN_NOTICE "<<< %p %s\n", m, buf);
-	}
-#endif
-
 	req->status = REQ_STATUS_UNSENT;
 
 	spin_lock(&client->lock);
-- 
cgit v1.2.3


From cb198131b0e7aba755ac164744536d461e86ab82 Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Thu, 16 Oct 2008 08:29:31 -0500
Subject: 9p: remove unnecessary tag field from p9_req_t structure

This removes the vestigial tag field from the p9_req_t structure.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/client.h | 2 --
 net/9p/trans_fd.c       | 2 +-
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index eeb7d922816e..475ef5cf1644 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -81,7 +81,6 @@ enum p9_req_status_t {
  * @tc: the request fcall structure
  * @rc: the response fcall structure
  * @aux: transport specific data (provided for trans_fd migration)
- * @tag: tag on request (BUG: redundant)
  * @req_list: link for higher level objects to chain requests
  *
  * Transport use an array to track outstanding requests
@@ -104,7 +103,6 @@ struct p9_req_t {
 	u16 flush_tag;
 	void *aux;
 
-	int tag;
 	struct list_head req_list;
 };
 
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index 95c9b949d1a5..e147ec539585 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -672,7 +672,7 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
 	struct p9_trans_fd *ts = client->trans;
 	struct p9_conn *m = ts->conn;
 
-	P9_DPRINTK(P9_DEBUG_MUX, "mux %p req %p tag %d\n", m, req, req->tag);
+	P9_DPRINTK(P9_DEBUG_MUX, "mux %p req %p\n", m, req);
 
 	spin_lock(&client->lock);
 	list_del(&req->req_list);
-- 
cgit v1.2.3


From 51a87c552dfd428e304c865e24ecbe091556f226 Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Thu, 16 Oct 2008 08:30:07 -0500
Subject: 9p: rework client code to use new protocol support functions

Now that the new protocol functions are in place, this patch switches
the client code to using the new support code.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 fs/9p/v9fs_vfs.h        |   4 +-
 fs/9p/vfs_dir.c         |   4 +-
 fs/9p/vfs_file.c        |   2 +-
 fs/9p/vfs_inode.c       |  38 +-
 fs/9p/vfs_super.c       |   6 +-
 include/net/9p/9p.h     |   7 +-
 include/net/9p/client.h |   7 +-
 net/9p/client.c         | 931 +++++++++++++++++++++++-------------------------
 net/9p/protocol.c       |  85 ++++-
 net/9p/protocol.h       |   5 +-
 net/9p/trans_fd.c       |  62 ++--
 net/9p/util.c           |   4 +
 12 files changed, 611 insertions(+), 544 deletions(-)

(limited to 'include')

diff --git a/fs/9p/v9fs_vfs.h b/fs/9p/v9fs_vfs.h
index 046cff377f10..c295ba786edd 100644
--- a/fs/9p/v9fs_vfs.h
+++ b/fs/9p/v9fs_vfs.h
@@ -46,10 +46,10 @@ extern struct dentry_operations v9fs_cached_dentry_operations;
 
 struct inode *v9fs_get_inode(struct super_block *sb, int mode);
 ino_t v9fs_qid2ino(struct p9_qid *qid);
-void v9fs_stat2inode(struct p9_stat *, struct inode *, struct super_block *);
+void v9fs_stat2inode(struct p9_wstat *, struct inode *, struct super_block *);
 int v9fs_dir_release(struct inode *inode, struct file *filp);
 int v9fs_file_open(struct inode *inode, struct file *file);
-void v9fs_inode2stat(struct inode *inode, struct p9_stat *stat);
+void v9fs_inode2stat(struct inode *inode, struct p9_wstat *stat);
 void v9fs_dentry_release(struct dentry *);
 int v9fs_uflags2omode(int uflags, int extended);
 
diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index d7d0ac5a2ca3..276aed625929 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -85,8 +85,8 @@ static int v9fs_dir_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		return -ENOMEM;
 
 	while (1) {
-		err = v9fs_file_readn(filp, statbuf, NULL, fid->rdir_fpos,
-									buflen);
+		err = v9fs_file_readn(filp, statbuf, NULL, buflen,
+								fid->rdir_fpos);
 		if (err <= 0)
 			break;
 
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 3fd28bbafc87..041c52692284 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -136,7 +136,7 @@ v9fs_file_readn(struct file *filp, char *data, char __user *udata, u32 count,
 	int n, total;
 	struct p9_fid *fid = filp->private_data;
 
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d offset %llu count %d\n", fid->fid,
+	P9_DPRINTK(P9_DEBUG_VFS, "fid %d offset %llu count %d\n", fid->fid,
 					(long long unsigned) offset, count);
 
 	n = 0;
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index e83aa5ebe861..e96d84aafbe2 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -334,7 +334,7 @@ v9fs_inode_from_fid(struct v9fs_session_info *v9ses, struct p9_fid *fid,
 {
 	int err, umode;
 	struct inode *ret;
-	struct p9_stat *st;
+	struct p9_wstat *st;
 
 	ret = NULL;
 	st = p9_client_stat(fid);
@@ -417,6 +417,8 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 	struct p9_fid *dfid, *ofid, *fid;
 	struct inode *inode;
 
+	P9_DPRINTK(P9_DEBUG_VFS, "name %s\n", dentry->d_name.name);
+
 	err = 0;
 	ofid = NULL;
 	fid = NULL;
@@ -424,6 +426,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 	dfid = v9fs_fid_clone(dentry->d_parent);
 	if (IS_ERR(dfid)) {
 		err = PTR_ERR(dfid);
+		P9_DPRINTK(P9_DEBUG_VFS, "fid clone failed %d\n", err);
 		dfid = NULL;
 		goto error;
 	}
@@ -432,18 +435,22 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 	ofid = p9_client_walk(dfid, 0, NULL, 1);
 	if (IS_ERR(ofid)) {
 		err = PTR_ERR(ofid);
+		P9_DPRINTK(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
 		ofid = NULL;
 		goto error;
 	}
 
 	err = p9_client_fcreate(ofid, name, perm, mode, extension);
-	if (err < 0)
+	if (err < 0) {
+		P9_DPRINTK(P9_DEBUG_VFS, "p9_client_fcreate failed %d\n", err);
 		goto error;
+	}
 
 	/* now walk from the parent so we can get unopened fid */
 	fid = p9_client_walk(dfid, 1, &name, 0);
 	if (IS_ERR(fid)) {
 		err = PTR_ERR(fid);
+		P9_DPRINTK(P9_DEBUG_VFS, "p9_client_walk failed %d\n", err);
 		fid = NULL;
 		goto error;
 	} else
@@ -453,6 +460,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 	inode = v9fs_inode_from_fid(v9ses, fid, dir->i_sb);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		P9_DPRINTK(P9_DEBUG_VFS, "inode creation failed %d\n", err);
 		goto error;
 	}
 
@@ -734,7 +742,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
 	int err;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid;
-	struct p9_stat *st;
+	struct p9_wstat *st;
 
 	P9_DPRINTK(P9_DEBUG_VFS, "dentry: %p\n", dentry);
 	err = -EPERM;
@@ -815,10 +823,9 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr)
  */
 
 void
-v9fs_stat2inode(struct p9_stat *stat, struct inode *inode,
+v9fs_stat2inode(struct p9_wstat *stat, struct inode *inode,
 	struct super_block *sb)
 {
-	int n;
 	char ext[32];
 	struct v9fs_session_info *v9ses = sb->s_fs_info;
 
@@ -842,11 +849,7 @@ v9fs_stat2inode(struct p9_stat *stat, struct inode *inode,
 		int major = -1;
 		int minor = -1;
 
-		n = stat->extension.len;
-		if (n > sizeof(ext)-1)
-			n = sizeof(ext)-1;
-		memmove(ext, stat->extension.str, n);
-		ext[n] = 0;
+		strncpy(ext, stat->extension, sizeof(ext));
 		sscanf(ext, "%c %u %u", &type, &major, &minor);
 		switch (type) {
 		case 'c':
@@ -857,8 +860,8 @@ v9fs_stat2inode(struct p9_stat *stat, struct inode *inode,
 			break;
 		default:
 			P9_DPRINTK(P9_DEBUG_ERROR,
-				"Unknown special type %c (%.*s)\n", type,
-				stat->extension.len, stat->extension.str);
+				"Unknown special type %c %s\n", type,
+				stat->extension);
 		};
 		inode->i_rdev = MKDEV(major, minor);
 	} else
@@ -904,7 +907,7 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid;
-	struct p9_stat *st;
+	struct p9_wstat *st;
 
 	P9_DPRINTK(P9_DEBUG_VFS, " %s\n", dentry->d_name.name);
 	retval = -EPERM;
@@ -926,15 +929,10 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen)
 	}
 
 	/* copy extension buffer into buffer */
-	if (st->extension.len < buflen)
-		buflen = st->extension.len + 1;
-
-	memmove(buffer, st->extension.str, buflen - 1);
-	buffer[buflen-1] = 0;
+	strncpy(buffer, st->extension, buflen);
 
 	P9_DPRINTK(P9_DEBUG_VFS,
-		"%s -> %.*s (%s)\n", dentry->d_name.name, st->extension.len,
-		st->extension.str, buffer);
+		"%s -> %s (%s)\n", dentry->d_name.name, st->extension, buffer);
 
 	retval = buflen;
 
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index bf59c3960494..d6cb1a0ca724 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -111,7 +111,7 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 	struct inode *inode = NULL;
 	struct dentry *root = NULL;
 	struct v9fs_session_info *v9ses = NULL;
-	struct p9_stat *st = NULL;
+	struct p9_wstat *st = NULL;
 	int mode = S_IRWXUGO | S_ISVTX;
 	uid_t uid = current->fsuid;
 	gid_t gid = current->fsgid;
@@ -161,10 +161,14 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags,
 
 	sb->s_root = root;
 	root->d_inode->i_ino = v9fs_qid2ino(&st->qid);
+
 	v9fs_stat2inode(st, root->d_inode, sb);
+
 	v9fs_fid_add(root, fid);
+	p9stat_free(st);
 	kfree(st);
 
+P9_DPRINTK(P9_DEBUG_VFS, " return simple set mount\n");
 	return simple_set_mnt(mnt, sb);
 
 release_sb:
diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index 46d0b8f8e5ec..56c15aee6e61 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -39,6 +39,7 @@
  * @P9_DEBUG_TRANS: transport tracing
  * @P9_DEBUG_SLABS: memory management tracing
  * @P9_DEBUG_FCALL: verbose dump of protocol messages
+ * @P9_DEBUG_FID: fid allocation/deallocation tracking
  *
  * These flags are passed at mount time to turn on various levels of
  * verbosity and tracing which will be output to the system logs.
@@ -53,13 +54,17 @@ enum p9_debug_flags {
 	P9_DEBUG_TRANS =	(1<<6),
 	P9_DEBUG_SLABS =      	(1<<7),
 	P9_DEBUG_FCALL =	(1<<8),
+	P9_DEBUG_FID =		(1<<9),
 };
 
 extern unsigned int p9_debug_level;
 
 #define P9_DPRINTK(level, format, arg...) \
 do {  \
-	if ((p9_debug_level & level) == level) \
+	if (level == P9_DEBUG_9P) \
+		printk(KERN_NOTICE "(%8.8d) " \
+		format , task_pid_nr(current) , ## arg); \
+	else if ((p9_debug_level & level) == level) \
 		printk(KERN_NOTICE "-- %s (%d): " \
 		format , __func__, task_pid_nr(current) , ## arg); \
 } while (0)
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index 475ef5cf1644..1e49b4d1030b 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -77,6 +77,7 @@ enum p9_req_status_t {
  * struct p9_req_t - request slots
  * @status: status of this request slot
  * @t_err: transport error
+ * @flush_tag: tag of request being flushed (for flush requests)
  * @wq: wait_queue for the client to block on for this request
  * @tc: the request fcall structure
  * @rc: the response fcall structure
@@ -97,10 +98,10 @@ enum p9_req_status_t {
 struct p9_req_t {
 	int status;
 	int t_err;
+	u16 flush_tag;
 	wait_queue_head_t *wq;
 	struct p9_fcall *tc;
 	struct p9_fcall *rc;
-	u16 flush_tag;
 	void *aux;
 
 	struct list_head req_list;
@@ -199,10 +200,12 @@ int p9_client_read(struct p9_fid *fid, char *data, char __user *udata,
 							u64 offset, u32 count);
 int p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
 							u64 offset, u32 count);
-struct p9_stat *p9_client_stat(struct p9_fid *fid);
+struct p9_wstat *p9_client_stat(struct p9_fid *fid);
 int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst);
 
 struct p9_req_t *p9_tag_lookup(struct p9_client *, u16);
 void p9_client_cb(struct p9_client *c, struct p9_req_t *req);
 
+void p9stat_free(struct p9_wstat *);
+
 #endif /* NET_9P_CLIENT_H */
diff --git a/net/9p/client.c b/net/9p/client.c
index 6004fded6682..2a166bfb95a3 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -35,6 +35,7 @@
 #include <linux/parser.h>
 #include <net/9p/client.h>
 #include <net/9p/transport.h>
+#include "protocol.h"
 
 /*
   * Client Option Parsing (code inspired by NFS code)
@@ -55,8 +56,8 @@ static const match_table_t tokens = {
 	{Opt_err, NULL},
 };
 
-static int
-p9_client_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc);
+static struct p9_req_t *
+p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...);
 
 /**
  * v9fs_parse_options - parse mount options into session structure
@@ -138,10 +139,11 @@ static int parse_opts(char *opts, struct p9_client *clnt)
  *
  */
 
-struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
+static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
 {
 	unsigned long flags;
 	int row, col;
+	struct p9_req_t *req;
 
 	/* This looks up the original request by tag so we know which
 	 * buffer to read the data into */
@@ -157,19 +159,11 @@ struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
 
 			if (!c->reqs[row]) {
 				printk(KERN_ERR "Couldn't grow tag array\n");
-				BUG();
+				return ERR_PTR(-ENOMEM);
 			}
 			for (col = 0; col < P9_ROW_MAXTAG; col++) {
 				c->reqs[row][col].status = REQ_STATUS_IDLE;
-				c->reqs[row][col].flush_tag = P9_NOTAG;
-				c->reqs[row][col].wq = kmalloc(
-					sizeof(wait_queue_head_t), GFP_ATOMIC);
-				if (!c->reqs[row][col].wq) {
-					printk(KERN_ERR
-						"Couldn't grow tag array\n");
-					BUG();
-				}
-				init_waitqueue_head(c->reqs[row][col].wq);
+				c->reqs[row][col].tc = NULL;
 			}
 			c->max_tag += P9_ROW_MAXTAG;
 		}
@@ -178,12 +172,39 @@ struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
 	row = tag / P9_ROW_MAXTAG;
 	col = tag % P9_ROW_MAXTAG;
 
-	c->reqs[row][col].status = REQ_STATUS_ALLOC;
-	c->reqs[row][col].flush_tag = P9_NOTAG;
+	req = &c->reqs[row][col];
+	if (!req->tc) {
+		req->wq = kmalloc(sizeof(wait_queue_head_t), GFP_KERNEL);
+		if (!req->wq) {
+			printk(KERN_ERR "Couldn't grow tag array\n");
+			return ERR_PTR(-ENOMEM);
+		}
+		init_waitqueue_head(req->wq);
+		req->tc = kmalloc(sizeof(struct p9_fcall)+c->msize,
+								GFP_KERNEL);
+		req->rc = kmalloc(sizeof(struct p9_fcall)+c->msize,
+								GFP_KERNEL);
+		if ((!req->tc) || (!req->rc)) {
+			printk(KERN_ERR "Couldn't grow tag array\n");
+			kfree(req->tc);
+			kfree(req->rc);
+			return ERR_PTR(-ENOMEM);
+		}
+		req->tc->sdata = (char *) req->tc + sizeof(struct p9_fcall);
+		req->tc->capacity = c->msize;
+		req->rc->sdata = (char *) req->rc + sizeof(struct p9_fcall);
+		req->rc->capacity = c->msize;
+	}
+
+	p9pdu_reset(req->tc);
+	p9pdu_reset(req->rc);
+
+	req->flush_tag = 0;
+	req->tc->tag = tag-1;
+	req->status = REQ_STATUS_ALLOC;
 
 	return &c->reqs[row][col];
 }
-EXPORT_SYMBOL(p9_tag_alloc);
 
 /**
  * p9_tag_lookup - lookup a request by tag
@@ -264,43 +285,16 @@ static void p9_tag_cleanup(struct p9_client *c)
 
 	/* free requests associated with tags */
 	for (row = 0; row < (c->max_tag/P9_ROW_MAXTAG); row++) {
-		for (col = 0; col < P9_ROW_MAXTAG; col++)
+		for (col = 0; col < P9_ROW_MAXTAG; col++) {
 			kfree(c->reqs[row][col].wq);
+			kfree(c->reqs[row][col].tc);
+			kfree(c->reqs[row][col].rc);
+		}
 		kfree(c->reqs[row]);
 	}
 	c->max_tag = 0;
 }
 
-/**
- * p9_client_flush - flush (cancel) a request
- * c: client state
- * req: request to cancel
- *
- * This sents a flush for a particular requests and links
- * the flush request to the original request.  The current
- * code only supports a single flush request although the protocol
- * allows for multiple flush requests to be sent for a single request.
- *
- */
-
-static int p9_client_flush(struct p9_client *c, struct p9_req_t *req)
-{
-	struct p9_fcall *tc, *rc = NULL;
-	int err;
-
-	P9_DPRINTK(P9_DEBUG_9P, "client %p tag %d\n", c, req->tc->tag);
-
-	tc = p9_create_tflush(req->tc->tag);
-	if (IS_ERR(tc))
-		return PTR_ERR(tc);
-
-	err = p9_client_rpc(c, tc, &rc);
-
-	/* we don't free anything here because RPC isn't complete */
-
-	return err;
-}
-
 /**
  * p9_free_req - free a request and clean-up as necessary
  * c: client state
@@ -308,15 +302,17 @@ static int p9_client_flush(struct p9_client *c, struct p9_req_t *req)
  *
  */
 
-void p9_free_req(struct p9_client *c, struct p9_req_t *r)
+static void p9_free_req(struct p9_client *c, struct p9_req_t *r)
 {
-	r->flush_tag = P9_NOTAG;
+	int tag = r->tc->tag;
+	P9_DPRINTK(P9_DEBUG_MUX, "clnt %p req %p tag: %d\n", c, r, tag);
+
 	r->status = REQ_STATUS_IDLE;
-	if (r->tc->tag != P9_NOTAG && p9_idpool_check(r->tc->tag, c->tagpool))
-		p9_idpool_put(r->tc->tag, c->tagpool);
+	if (tag != P9_NOTAG && p9_idpool_check(tag, c->tagpool))
+		p9_idpool_put(tag, c->tagpool);
 
 	/* if this was a flush request we have to free response fcall */
-	if (r->tc->id == P9_TFLUSH) {
+	if (r->rc->id == P9_RFLUSH) {
 		kfree(r->tc);
 		kfree(r->rc);
 	}
@@ -333,30 +329,28 @@ void p9_client_cb(struct p9_client *c, struct p9_req_t *req)
 	struct p9_req_t *other_req;
 	unsigned long flags;
 
-	P9_DPRINTK(P9_DEBUG_MUX, ": %d\n", req->tc->tag);
+	P9_DPRINTK(P9_DEBUG_MUX, " tag %d\n", req->tc->tag);
 
 	if (req->status == REQ_STATUS_ERROR)
 		wake_up(req->wq);
 
-	if (req->tc->id == P9_TFLUSH) { /* flush receive path */
-		P9_DPRINTK(P9_DEBUG_MUX, "flush: %d\n", req->tc->tag);
+	if (req->flush_tag) { 			/* flush receive path */
+		P9_DPRINTK(P9_DEBUG_9P, "<<< RFLUSH %d\n", req->tc->tag);
 		spin_lock_irqsave(&c->lock, flags);
-		other_req = p9_tag_lookup(c, req->tc->params.tflush.oldtag);
-		if (other_req->flush_tag != req->tc->tag) /* stale flush */
+		other_req = p9_tag_lookup(c, req->flush_tag);
+		if (other_req->status != REQ_STATUS_FLSH) /* stale flush */
 			spin_unlock_irqrestore(&c->lock, flags);
 		else {
-			BUG_ON(other_req->status != REQ_STATUS_FLSH);
 			other_req->status = REQ_STATUS_FLSHD;
 			spin_unlock_irqrestore(&c->lock, flags);
 			wake_up(other_req->wq);
 		}
 		p9_free_req(c, req);
 	} else { 				/* normal receive path */
-		P9_DPRINTK(P9_DEBUG_MUX, "normal: %d\n", req->tc->tag);
+		P9_DPRINTK(P9_DEBUG_MUX, "normal: tag %d\n", req->tc->tag);
 		spin_lock_irqsave(&c->lock, flags);
 		if (req->status != REQ_STATUS_FLSHD)
 			req->status = REQ_STATUS_RCVD;
-		req->flush_tag = P9_NOTAG;
 		spin_unlock_irqrestore(&c->lock, flags);
 		wake_up(req->wq);
 		P9_DPRINTK(P9_DEBUG_MUX, "wakeup: %d\n", req->tc->tag);
@@ -364,29 +358,165 @@ void p9_client_cb(struct p9_client *c, struct p9_req_t *req)
 }
 EXPORT_SYMBOL(p9_client_cb);
 
+/**
+ * p9_parse_header - parse header arguments out of a packet
+ * @pdu: packet to parse
+ * @size: size of packet
+ * @type: type of request
+ * @tag: tag of packet
+ * @rewind: set if we need to rewind offset afterwards
+ */
+
+int
+p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type, int16_t *tag,
+								int rewind)
+{
+	int8_t r_type;
+	int16_t r_tag;
+	int32_t r_size;
+	int offset = pdu->offset;
+	int err;
+
+	pdu->offset = 0;
+	if (pdu->size == 0)
+		pdu->size = 7;
+
+	err = p9pdu_readf(pdu, 0, "dbw", &r_size, &r_type, &r_tag);
+	if (err)
+		goto rewind_and_exit;
+
+	pdu->size = r_size;
+	pdu->id = r_type;
+	pdu->tag = r_tag;
+
+	P9_DPRINTK(P9_DEBUG_MUX, "pdu: type: %d tag: %d size=%d offset=%d\n",
+				pdu->id, pdu->tag, pdu->size, pdu->offset);
+
+	if (type)
+		*type = r_type;
+	if (tag)
+		*tag = r_tag;
+	if (size)
+		*size = r_size;
+
+
+rewind_and_exit:
+	if (rewind)
+		pdu->offset = offset;
+	return err;
+}
+EXPORT_SYMBOL(p9_parse_header);
+
+/**
+ * p9_check_errors - check 9p packet for error return and process it
+ * @c: current client instance
+ * @req: request to parse and check for error conditions
+ *
+ * returns error code if one is discovered, otherwise returns 0
+ *
+ * this will have to be more complicated if we have multiple
+ * error packet types
+ */
+
+static int p9_check_errors(struct p9_client *c, struct p9_req_t *req)
+{
+	int8_t type;
+	int err;
+
+	err = p9_parse_header(req->rc, NULL, &type, NULL, 0);
+	if (err) {
+		P9_DPRINTK(P9_DEBUG_ERROR, "couldn't parse header %d\n", err);
+		return err;
+	}
+
+	if (type == P9_RERROR) {
+		int ecode;
+		char *ename;
+
+		err = p9pdu_readf(req->rc, c->dotu, "s?d", &ename, &ecode);
+		if (err) {
+			P9_DPRINTK(P9_DEBUG_ERROR, "couldn't parse error%d\n",
+									err);
+			return err;
+		}
+
+		if (c->dotu)
+			err = -ecode;
+
+		if (!err) {
+			err = p9_errstr2errno(ename, strlen(ename));
+
+			/* string match failed */
+			if (!err)
+				err = -ESERVERFAULT;
+		}
+
+		P9_DPRINTK(P9_DEBUG_9P, "<<< RERROR (%d) %s\n", -ecode, ename);
+
+		kfree(ename);
+	} else
+		err = 0;
+
+	return err;
+}
+
+/**
+ * p9_client_flush - flush (cancel) a request
+ * c: client state
+ * req: request to cancel
+ *
+ * This sents a flush for a particular requests and links
+ * the flush request to the original request.  The current
+ * code only supports a single flush request although the protocol
+ * allows for multiple flush requests to be sent for a single request.
+ *
+ */
+
+static int p9_client_flush(struct p9_client *c, struct p9_req_t *oldreq)
+{
+	struct p9_req_t *req;
+	int16_t oldtag;
+	int err;
+
+	err = p9_parse_header(oldreq->tc, NULL, NULL, &oldtag, 1);
+	if (err)
+		return err;
+
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TFLUSH tag %d\n", oldtag);
+
+	req = p9_client_rpc(c, P9_TFLUSH, "w", oldtag);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	req->flush_tag = oldtag;
+
+	/* we don't free anything here because RPC isn't complete */
+	return 0;
+}
+
 /**
  * p9_client_rpc - issue a request and wait for a response
  * @c: client session
- * @tc: &p9_fcall request to transmit
- * @rc: &p9_fcall to put reponse into
+ * @type: type of request
+ * @fmt: protocol format string (see protocol.c)
  *
- * Returns 0 on success, error code on failure
+ * Returns request structure (which client must free using p9_free_req)
  */
 
-static int
-p9_client_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc)
+static struct p9_req_t *
+p9_client_rpc(struct p9_client *c, int8_t type, const char *fmt, ...)
 {
-	int tag, err, size;
-	char *rdata;
+	va_list ap;
+	int tag, err;
 	struct p9_req_t *req;
 	unsigned long flags;
 	int sigpending;
 	int flushed = 0;
 
-	P9_DPRINTK(P9_DEBUG_9P, "client %p tc %p rc %p\n", c, tc, rc);
+	P9_DPRINTK(P9_DEBUG_MUX, "client %p op %d\n", c, type);
 
 	if (c->status != Connected)
-		return -EIO;
+		return ERR_PTR(-EIO);
 
 	if (signal_pending(current)) {
 		sigpending = 1;
@@ -395,50 +525,22 @@ p9_client_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc)
 		sigpending = 0;
 
 	tag = P9_NOTAG;
-	if (tc->id != P9_TVERSION) {
+	if (type != P9_TVERSION) {
 		tag = p9_idpool_get(c->tagpool);
 		if (tag < 0)
-			return -ENOMEM;
+			return ERR_PTR(-ENOMEM);
 	}
 
 	req = p9_tag_alloc(c, tag);
+	if (IS_ERR(req))
+		return req;
 
-	/* if this is a flush request, backlink flush request now to
-	 * avoid race conditions later. */
-	if (tc->id == P9_TFLUSH) {
-		struct p9_req_t *other_req =
-				p9_tag_lookup(c, tc->params.tflush.oldtag);
-		if (other_req->status == REQ_STATUS_FLSH)
-			other_req->flush_tag = tag;
-	}
-
-	p9_set_tag(tc, tag);
-
-	/*
-	 * if client passed in a pre-allocated response fcall struct
-	 * then we just use that, otherwise we allocate one.
-	 */
-
-	if (rc == NULL)
-		req->rc = NULL;
-	else
-		req->rc = *rc;
-	if (req->rc == NULL) {
-		req->rc = kmalloc(sizeof(struct p9_fcall) + c->msize,
-								GFP_KERNEL);
-		if (!req->rc) {
-			err = -ENOMEM;
-			p9_idpool_put(tag, c->tagpool);
-			p9_free_req(c, req);
-			goto reterr;
-		}
-		*rc = req->rc;
-	}
-
-	rdata = (char *)req->rc+sizeof(struct p9_fcall);
-
-	req->tc = tc;
-	P9_DPRINTK(P9_DEBUG_9P, "request: tc: %p rc: %p\n", req->tc, req->rc);
+	/* marshall the data */
+	p9pdu_prepare(req->tc, tag, type);
+	va_start(ap, fmt);
+	err = p9pdu_vwritef(req->tc, c->dotu, fmt, ap);
+	va_end(ap);
+	p9pdu_finalize(req->tc);
 
 	err = c->trans_mod->request(c, req);
 	if (err < 0) {
@@ -447,28 +549,28 @@ p9_client_rpc(struct p9_client *c, struct p9_fcall *tc, struct p9_fcall **rc)
 	}
 
 	/* if it was a flush we just transmitted, return our tag */
-	if (tc->id == P9_TFLUSH)
-		return 0;
+	if (type == P9_TFLUSH)
+		return req;
 again:
-	P9_DPRINTK(P9_DEBUG_9P, "wait %p tag: %d\n", req->wq, tag);
+	P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d\n", req->wq, tag);
 	err = wait_event_interruptible(*req->wq,
 						req->status >= REQ_STATUS_RCVD);
-	P9_DPRINTK(P9_DEBUG_9P, "wait %p tag: %d returned %d (flushed=%d)\n",
+	P9_DPRINTK(P9_DEBUG_MUX, "wait %p tag: %d returned %d (flushed=%d)\n",
 						req->wq, tag, err, flushed);
 
 	if (req->status == REQ_STATUS_ERROR) {
-		P9_DPRINTK(P9_DEBUG_9P, "req_status error %d\n", req->t_err);
+		P9_DPRINTK(P9_DEBUG_ERROR, "req_status error %d\n", req->t_err);
 		err = req->t_err;
 	} else if (err == -ERESTARTSYS && flushed) {
-		P9_DPRINTK(P9_DEBUG_9P, "flushed - going again\n");
+		P9_DPRINTK(P9_DEBUG_MUX, "flushed - going again\n");
 		goto again;
 	} else if (req->status == REQ_STATUS_FLSHD) {
-		P9_DPRINTK(P9_DEBUG_9P, "flushed - erestartsys\n");
+		P9_DPRINTK(P9_DEBUG_MUX, "flushed - erestartsys\n");
 		err = -ERESTARTSYS;
 	}
 
 	if ((err == -ERESTARTSYS) && (c->status == Connected) && (!flushed)) {
-		P9_DPRINTK(P9_DEBUG_9P, "flushing\n");
+		P9_DPRINTK(P9_DEBUG_MUX, "flushing\n");
 		spin_lock_irqsave(&c->lock, flags);
 		if (req->status == REQ_STATUS_SENT)
 			req->status = REQ_STATUS_FLSH;
@@ -493,42 +595,17 @@ again:
 	if (err < 0)
 		goto reterr;
 
-	size = le32_to_cpu(*(__le32 *) rdata);
-
-	err = p9_deserialize_fcall(rdata, size, req->rc, c->dotu);
-	if (err < 0) {
-		P9_DPRINTK(P9_DEBUG_9P,
-			"9p debug: client rpc deserialize returned %d\n", err);
-		goto reterr;
+	err = p9_check_errors(c, req);
+	if (!err) {
+		P9_DPRINTK(P9_DEBUG_MUX, "exit: client %p op %d\n", c, type);
+		return req;
 	}
 
-	if (req->rc->id == P9_RERROR) {
-		int ecode = req->rc->params.rerror.errno;
-		struct p9_str *ename = &req->rc->params.rerror.error;
-
-		P9_DPRINTK(P9_DEBUG_MUX, "Rerror %.*s\n", ename->len,
-								ename->str);
-
-		if (c->dotu)
-			err = -ecode;
-
-		if (!err) {
-			err = p9_errstr2errno(ename->str, ename->len);
-
-			/* string match failed */
-			if (!err) {
-				PRINT_FCALL_ERROR("unknown error", req->rc);
-				err = -ESERVERFAULT;
-			}
-		}
-	} else
-		err = 0;
-
 reterr:
+	P9_DPRINTK(P9_DEBUG_MUX, "exit: client %p op %d error: %d\n", c, type,
+									err);
 	p9_free_req(c, req);
-
-	P9_DPRINTK(P9_DEBUG_9P, "returning %d\n", err);
-	return err;
+	return ERR_PTR(err);
 }
 
 static struct p9_fid *p9_fid_create(struct p9_client *clnt)
@@ -536,7 +613,7 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt)
 	int err;
 	struct p9_fid *fid;
 
-	P9_DPRINTK(P9_DEBUG_9P, "clnt %p\n", clnt);
+	P9_DPRINTK(P9_DEBUG_FID, "clnt %p\n", clnt);
 	fid = kmalloc(sizeof(struct p9_fid), GFP_KERNEL);
 	if (!fid)
 		return ERR_PTR(-ENOMEM);
@@ -569,7 +646,7 @@ static void p9_fid_destroy(struct p9_fid *fid)
 {
 	struct p9_client *clnt;
 
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d\n", fid->fid);
+	P9_DPRINTK(P9_DEBUG_FID, "fid %d\n", fid->fid);
 	clnt = fid->clnt;
 	p9_idpool_put(fid->fid, clnt->fidpool);
 	spin_lock(&clnt->lock);
@@ -578,49 +655,46 @@ static void p9_fid_destroy(struct p9_fid *fid)
 	kfree(fid);
 }
 
-static int p9_client_version(struct p9_client *clnt)
+int p9_client_version(struct p9_client *c)
 {
 	int err = 0;
-	struct p9_fcall *tc, *rc;
-	struct p9_str *version;
+	struct p9_req_t *req;
+	char *version;
+	int msize;
 
-	P9_DPRINTK(P9_DEBUG_9P, "%p\n", clnt);
-	err = 0;
-	tc = NULL;
-	rc = NULL;
-
-	tc = p9_create_tversion(clnt->msize,
-					clnt->dotu ? "9P2000.u" : "9P2000");
-	if (IS_ERR(tc)) {
-		err = PTR_ERR(tc);
-		tc = NULL;
-		goto error;
-	}
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TVERSION msize %d extended %d\n",
+							c->msize, c->dotu);
+	req = p9_client_rpc(c, P9_TVERSION, "ds", c->msize,
+				c->dotu ? "9P2000.u" : "9P2000");
+	if (IS_ERR(req))
+		return PTR_ERR(req);
 
-	err = p9_client_rpc(clnt, tc, &rc);
-	if (err)
+	err = p9pdu_readf(req->rc, c->dotu, "ds", &msize, &version);
+	if (err) {
+		P9_DPRINTK(P9_DEBUG_9P, "version error %d\n", err);
 		goto error;
+	}
 
-	version = &rc->params.rversion.version;
-	if (version->len == 8 && !memcmp(version->str, "9P2000.u", 8))
-		clnt->dotu = 1;
-	else if (version->len == 6 && !memcmp(version->str, "9P2000", 6))
-		clnt->dotu = 0;
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RVERSION msize %d %s\n", msize, version);
+	if (!memcmp(version, "9P2000.u", 8))
+		c->dotu = 1;
+	else if (!memcmp(version, "9P2000", 6))
+		c->dotu = 0;
 	else {
 		err = -EREMOTEIO;
 		goto error;
 	}
 
-	if (rc->params.rversion.msize < clnt->msize)
-		clnt->msize = rc->params.rversion.msize;
+	if (msize < c->msize)
+		c->msize = msize;
 
 error:
-	kfree(tc);
-	kfree(rc);
+	kfree(version);
+	p9_free_req(c, req);
 
 	return err;
 }
-EXPORT_SYMBOL(p9_client_auth);
+EXPORT_SYMBOL(p9_client_version);
 
 struct p9_client *p9_client_create(const char *dev_name, char *options)
 {
@@ -656,7 +730,7 @@ struct p9_client *p9_client_create(const char *dev_name, char *options)
 		goto error;
 	}
 
-	P9_DPRINTK(P9_DEBUG_9P, "clnt %p trans %p msize %d dotu %d\n",
+	P9_DPRINTK(P9_DEBUG_MUX, "clnt %p trans %p msize %d dotu %d\n",
 		clnt, clnt->trans_mod, clnt->msize, clnt->dotu);
 
 	err = clnt->trans_mod->create(clnt, dev_name, options);
@@ -682,7 +756,7 @@ void p9_client_destroy(struct p9_client *clnt)
 {
 	struct p9_fid *fid, *fidptr;
 
-	P9_DPRINTK(P9_DEBUG_9P, "clnt %p\n", clnt);
+	P9_DPRINTK(P9_DEBUG_MUX, "clnt %p\n", clnt);
 
 	if (clnt->trans_mod)
 		clnt->trans_mod->close(clnt);
@@ -712,14 +786,13 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
 	char *uname, u32 n_uname, char *aname)
 {
 	int err;
-	struct p9_fcall *tc, *rc;
+	struct p9_req_t *req;
 	struct p9_fid *fid;
+	struct p9_qid qid;
 
-	P9_DPRINTK(P9_DEBUG_9P, "clnt %p afid %d uname %s aname %s\n",
-		clnt, afid?afid->fid:-1, uname, aname);
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TATTACH afid %d uname %s aname %s\n",
+					afid ? afid->fid : -1, uname, aname);
 	err = 0;
-	tc = NULL;
-	rc = NULL;
 
 	fid = p9_fid_create(clnt);
 	if (IS_ERR(fid)) {
@@ -728,73 +801,75 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
 		goto error;
 	}
 
-	tc = p9_create_tattach(fid->fid, afid?afid->fid:P9_NOFID, uname, aname,
-		n_uname, clnt->dotu);
-	if (IS_ERR(tc)) {
-		err = PTR_ERR(tc);
-		tc = NULL;
+	req = p9_client_rpc(clnt, P9_TATTACH, "ddss?d", fid->fid,
+			afid ? afid->fid : P9_NOFID, uname, aname, n_uname);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
 		goto error;
 	}
 
-	err = p9_client_rpc(clnt, tc, &rc);
-	if (err)
+	err = p9pdu_readf(req->rc, clnt->dotu, "Q", &qid);
+	if (err) {
+		p9_free_req(clnt, req);
 		goto error;
+	}
 
-	memmove(&fid->qid, &rc->params.rattach.qid, sizeof(struct p9_qid));
-	kfree(tc);
-	kfree(rc);
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RATTACH qid %x.%llx.%x\n",
+					qid.type, qid.path, qid.version);
+
+	memmove(&fid->qid, &qid, sizeof(struct p9_qid));
+
+	p9_free_req(clnt, req);
 	return fid;
 
 error:
-	kfree(tc);
-	kfree(rc);
 	if (fid)
 		p9_fid_destroy(fid);
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(p9_client_attach);
 
-struct p9_fid *p9_client_auth(struct p9_client *clnt, char *uname,
-	u32 n_uname, char *aname)
+struct p9_fid *
+p9_client_auth(struct p9_client *clnt, char *uname, u32 n_uname, char *aname)
 {
 	int err;
-	struct p9_fcall *tc, *rc;
-	struct p9_fid *fid;
+	struct p9_req_t *req;
+	struct p9_qid qid;
+	struct p9_fid *afid;
 
-	P9_DPRINTK(P9_DEBUG_9P, "clnt %p uname %s aname %s\n", clnt, uname,
-									aname);
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TAUTH uname %s aname %s\n", uname, aname);
 	err = 0;
-	tc = NULL;
-	rc = NULL;
 
-	fid = p9_fid_create(clnt);
-	if (IS_ERR(fid)) {
-		err = PTR_ERR(fid);
-		fid = NULL;
+	afid = p9_fid_create(clnt);
+	if (IS_ERR(afid)) {
+		err = PTR_ERR(afid);
+		afid = NULL;
 		goto error;
 	}
 
-	tc = p9_create_tauth(fid->fid, uname, aname, n_uname, clnt->dotu);
-	if (IS_ERR(tc)) {
-		err = PTR_ERR(tc);
-		tc = NULL;
+	req = p9_client_rpc(clnt, P9_TAUTH, "dss?d",
+			afid ? afid->fid : P9_NOFID, uname, aname, n_uname);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
 		goto error;
 	}
 
-	err = p9_client_rpc(clnt, tc, &rc);
-	if (err)
+	err = p9pdu_readf(req->rc, clnt->dotu, "Q", &qid);
+	if (err) {
+		p9_free_req(clnt, req);
 		goto error;
+	}
 
-	memmove(&fid->qid, &rc->params.rauth.qid, sizeof(struct p9_qid));
-	kfree(tc);
-	kfree(rc);
-	return fid;
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RAUTH qid %x.%llx.%x\n",
+					qid.type, qid.path, qid.version);
+
+	memmove(&afid->qid, &qid, sizeof(struct p9_qid));
+	p9_free_req(clnt, req);
+	return afid;
 
 error:
-	kfree(tc);
-	kfree(rc);
-	if (fid)
-		p9_fid_destroy(fid);
+	if (afid)
+		p9_fid_destroy(afid);
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(p9_client_auth);
@@ -803,15 +878,13 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames,
 	int clone)
 {
 	int err;
-	struct p9_fcall *tc, *rc;
 	struct p9_client *clnt;
 	struct p9_fid *fid;
+	struct p9_qid *wqids;
+	struct p9_req_t *req;
+	int16_t nwqids, count;
 
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d nwname %d wname[0] %s\n",
-		oldfid->fid, nwname, wnames?wnames[0]:NULL);
 	err = 0;
-	tc = NULL;
-	rc = NULL;
 	clnt = oldfid->clnt;
 	if (clone) {
 		fid = p9_fid_create(clnt);
@@ -825,53 +898,46 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames,
 	} else
 		fid = oldfid;
 
-	tc = p9_create_twalk(oldfid->fid, fid->fid, nwname, wnames);
-	if (IS_ERR(tc)) {
-		err = PTR_ERR(tc);
-		tc = NULL;
+
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TWALK fids %d,%d nwname %d wname[0] %s\n",
+		oldfid->fid, fid->fid, nwname, wnames ? wnames[0] : NULL);
+
+	req = p9_client_rpc(clnt, P9_TWALK, "ddT", oldfid->fid, fid->fid,
+								nwname, wnames);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
 		goto error;
 	}
 
-	err = p9_client_rpc(clnt, tc, &rc);
-	if (err) {
-		if (rc && rc->id == P9_RWALK)
-			goto clunk_fid;
-		else
-			goto error;
-	}
+	err = p9pdu_readf(req->rc, clnt->dotu, "R", &nwqids, &wqids);
+	p9_free_req(clnt, req);
+	if (err)
+		goto clunk_fid;
 
-	if (rc->params.rwalk.nwqid != nwname) {
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RWALK nwqid %d:\n", nwqids);
+
+	if (nwqids != nwname) {
 		err = -ENOENT;
 		goto clunk_fid;
 	}
 
+	for (count = 0; count < nwqids; count++)
+		P9_DPRINTK(P9_DEBUG_9P, "<<<     [%d] %x.%llx.%x\n",
+			count, wqids[count].type, wqids[count].path,
+			wqids[count].version);
+
 	if (nwname)
-		memmove(&fid->qid,
-			&rc->params.rwalk.wqids[rc->params.rwalk.nwqid - 1],
-			sizeof(struct p9_qid));
+		memmove(&fid->qid, &wqids[nwqids - 1], sizeof(struct p9_qid));
 	else
 		fid->qid = oldfid->qid;
 
-	kfree(tc);
-	kfree(rc);
 	return fid;
 
 clunk_fid:
-	kfree(tc);
-	kfree(rc);
-	rc = NULL;
-	tc = p9_create_tclunk(fid->fid);
-	if (IS_ERR(tc)) {
-		err = PTR_ERR(tc);
-		tc = NULL;
-		goto error;
-	}
-
-	p9_client_rpc(clnt, tc, &rc);
+	p9_client_clunk(fid);
+	fid = NULL;
 
 error:
-	kfree(tc);
-	kfree(rc);
 	if (fid && (fid != oldfid))
 		p9_fid_destroy(fid);
 
@@ -882,35 +948,36 @@ EXPORT_SYMBOL(p9_client_walk);
 int p9_client_open(struct p9_fid *fid, int mode)
 {
 	int err;
-	struct p9_fcall *tc, *rc;
 	struct p9_client *clnt;
+	struct p9_req_t *req;
+	struct p9_qid qid;
+	int iounit;
 
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d mode %d\n", fid->fid, mode);
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TOPEN fid %d mode %d\n", fid->fid, mode);
 	err = 0;
-	tc = NULL;
-	rc = NULL;
 	clnt = fid->clnt;
 
 	if (fid->mode != -1)
 		return -EINVAL;
 
-	tc = p9_create_topen(fid->fid, mode);
-	if (IS_ERR(tc)) {
-		err = PTR_ERR(tc);
-		tc = NULL;
-		goto done;
+	req = p9_client_rpc(clnt, P9_TOPEN, "db", fid->fid, mode);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
 	}
 
-	err = p9_client_rpc(clnt, tc, &rc);
+	err = p9pdu_readf(req->rc, clnt->dotu, "Qd", &qid, &iounit);
+	p9_free_req(clnt, req);
 	if (err)
-		goto done;
+		goto error;
+
+	P9_DPRINTK(P9_DEBUG_9P, "<<< ROPEN qid %x.%llx.%x iounit %x\n",
+				qid.type, qid.path, qid.version, iounit);
 
 	fid->mode = mode;
-	fid->iounit = rc->params.ropen.iounit;
+	fid->iounit = iounit;
 
-done:
-	kfree(tc);
-	kfree(rc);
+error:
 	return err;
 }
 EXPORT_SYMBOL(p9_client_open);
@@ -919,37 +986,38 @@ int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode,
 		     char *extension)
 {
 	int err;
-	struct p9_fcall *tc, *rc;
 	struct p9_client *clnt;
+	struct p9_req_t *req;
+	struct p9_qid qid;
+	int iounit;
 
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d name %s perm %d mode %d\n", fid->fid,
-		name, perm, mode);
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TCREATE fid %d name %s perm %d mode %d\n",
+						fid->fid, name, perm, mode);
 	err = 0;
-	tc = NULL;
-	rc = NULL;
 	clnt = fid->clnt;
 
 	if (fid->mode != -1)
 		return -EINVAL;
 
-	tc = p9_create_tcreate(fid->fid, name, perm, mode, extension,
-							       clnt->dotu);
-	if (IS_ERR(tc)) {
-		err = PTR_ERR(tc);
-		tc = NULL;
-		goto done;
+	req = p9_client_rpc(clnt, P9_TCREATE, "dsdb?s", fid->fid, name, perm,
+				mode, extension);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
 	}
 
-	err = p9_client_rpc(clnt, tc, &rc);
+	err = p9pdu_readf(req->rc, clnt->dotu, "Qd", &qid, &iounit);
+	p9_free_req(clnt, req);
 	if (err)
-		goto done;
+		goto error;
+
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RCREATE qid %x.%llx.%x iounit %x\n",
+				qid.type, qid.path, qid.version, iounit);
 
 	fid->mode = mode;
-	fid->iounit = rc->params.ropen.iounit;
+	fid->iounit = iounit;
 
-done:
-	kfree(tc);
-	kfree(rc);
+error:
 	return err;
 }
 EXPORT_SYMBOL(p9_client_fcreate);
@@ -957,31 +1025,25 @@ EXPORT_SYMBOL(p9_client_fcreate);
 int p9_client_clunk(struct p9_fid *fid)
 {
 	int err;
-	struct p9_fcall *tc, *rc;
 	struct p9_client *clnt;
+	struct p9_req_t *req;
 
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d\n", fid->fid);
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TCLUNK fid %d\n", fid->fid);
 	err = 0;
-	tc = NULL;
-	rc = NULL;
 	clnt = fid->clnt;
 
-	tc = p9_create_tclunk(fid->fid);
-	if (IS_ERR(tc)) {
-		err = PTR_ERR(tc);
-		tc = NULL;
-		goto done;
+	req = p9_client_rpc(clnt, P9_TCLUNK, "d", fid->fid);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
 	}
 
-	err = p9_client_rpc(clnt, tc, &rc);
-	if (err)
-		goto done;
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RCLUNK fid %d\n", fid->fid);
 
+	p9_free_req(clnt, req);
 	p9_fid_destroy(fid);
 
-done:
-	kfree(tc);
-	kfree(rc);
+error:
 	return err;
 }
 EXPORT_SYMBOL(p9_client_clunk);
@@ -989,31 +1051,25 @@ EXPORT_SYMBOL(p9_client_clunk);
 int p9_client_remove(struct p9_fid *fid)
 {
 	int err;
-	struct p9_fcall *tc, *rc;
 	struct p9_client *clnt;
+	struct p9_req_t *req;
 
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d\n", fid->fid);
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TREMOVE fid %d\n", fid->fid);
 	err = 0;
-	tc = NULL;
-	rc = NULL;
 	clnt = fid->clnt;
 
-	tc = p9_create_tremove(fid->fid);
-	if (IS_ERR(tc)) {
-		err = PTR_ERR(tc);
-		tc = NULL;
-		goto done;
+	req = p9_client_rpc(clnt, P9_TREMOVE, "d", fid->fid);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
 	}
 
-	err = p9_client_rpc(clnt, tc, &rc);
-	if (err)
-		goto done;
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RREMOVE fid %d\n", fid->fid);
 
+	p9_free_req(clnt, req);
 	p9_fid_destroy(fid);
 
-done:
-	kfree(tc);
-	kfree(rc);
+error:
 	return err;
 }
 EXPORT_SYMBOL(p9_client_remove);
@@ -1022,15 +1078,14 @@ int
 p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset,
 								u32 count)
 {
-	int err, n, rsize, total;
-	struct p9_fcall *tc, *rc;
+	int err, rsize, total;
 	struct p9_client *clnt;
+	struct p9_req_t *req;
+	char *dataptr;
 
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d offset %llu %d\n", fid->fid,
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %d\n", fid->fid,
 					(long long unsigned) offset, count);
 	err = 0;
-	tc = NULL;
-	rc = NULL;
 	clnt = fid->clnt;
 	total = 0;
 
@@ -1038,53 +1093,40 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset,
 	if (!rsize || rsize > clnt->msize-P9_IOHDRSZ)
 		rsize = clnt->msize - P9_IOHDRSZ;
 
-	do {
-		if (count < rsize)
-			rsize = count;
+	if (count < rsize)
+		rsize = count;
 
-		tc = p9_create_tread(fid->fid, offset, rsize);
-		if (IS_ERR(tc)) {
-			err = PTR_ERR(tc);
-			tc = NULL;
-			goto error;
-		}
+	req = p9_client_rpc(clnt, P9_TREAD, "dqd", fid->fid, offset, rsize);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
 
-		err = p9_client_rpc(clnt, tc, &rc);
-		if (err)
-			goto error;
+	err = p9pdu_readf(req->rc, clnt->dotu, "D", &count, &dataptr);
+	if (err)
+		goto free_and_error;
 
-		n = rc->params.rread.count;
-		if (n > count)
-			n = count;
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
 
-		if (data) {
-			memmove(data, rc->params.rread.data, n);
-			data += n;
-		}
+	if (data) {
+		memmove(data, dataptr, count);
+		data += count;
+	}
 
-		if (udata) {
-			err = copy_to_user(udata, rc->params.rread.data, n);
-			if (err) {
-				err = -EFAULT;
-				goto error;
-			}
-			udata += n;
+	if (udata) {
+		err = copy_to_user(udata, dataptr, count);
+		if (err) {
+			err = -EFAULT;
+			goto free_and_error;
 		}
+	}
 
-		count -= n;
-		offset += n;
-		total += n;
-		kfree(tc);
-		tc = NULL;
-		kfree(rc);
-		rc = NULL;
-	} while (count > 0 && n == rsize);
-
-	return total;
+	p9_free_req(clnt, req);
+	return count;
 
+free_and_error:
+	p9_free_req(clnt, req);
 error:
-	kfree(tc);
-	kfree(rc);
 	return err;
 }
 EXPORT_SYMBOL(p9_client_read);
@@ -1093,15 +1135,13 @@ int
 p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
 							u64 offset, u32 count)
 {
-	int err, n, rsize, total;
-	struct p9_fcall *tc, *rc;
+	int err, rsize, total;
 	struct p9_client *clnt;
+	struct p9_req_t *req;
 
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d offset %llu count %d\n", fid->fid,
-					(long long unsigned) offset, count);
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %d\n",
+				fid->fid, (long long unsigned) offset, count);
 	err = 0;
-	tc = NULL;
-	rc = NULL;
 	clnt = fid->clnt;
 	total = 0;
 
@@ -1109,129 +1149,70 @@ p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
 	if (!rsize || rsize > clnt->msize-P9_IOHDRSZ)
 		rsize = clnt->msize - P9_IOHDRSZ;
 
-	do {
-		if (count < rsize)
-			rsize = count;
-
-		if (data)
-			tc = p9_create_twrite(fid->fid, offset, rsize, data);
-		else
-			tc = p9_create_twrite_u(fid->fid, offset, rsize, udata);
-		if (IS_ERR(tc)) {
-			err = PTR_ERR(tc);
-			tc = NULL;
-			goto error;
-		}
-
-		err = p9_client_rpc(clnt, tc, &rc);
-		if (err)
-			goto error;
-
-		n = rc->params.rread.count;
-		count -= n;
-
-		if (data)
-			data += n;
-		else
-			udata += n;
+	if (count < rsize)
+		rsize = count;
+	if (data)
+		req = p9_client_rpc(clnt, P9_TWRITE, "dqD", fid->fid, offset,
+								rsize, data);
+	else
+		req = p9_client_rpc(clnt, P9_TWRITE, "dqU", fid->fid, offset,
+								rsize, udata);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
+	}
 
-		offset += n;
-		total += n;
-		kfree(tc);
-		tc = NULL;
-		kfree(rc);
-		rc = NULL;
-	} while (count > 0);
+	err = p9pdu_readf(req->rc, clnt->dotu, "d", &count);
+	if (err)
+		goto free_and_error;
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);
 
-	return total;
+	p9_free_req(clnt, req);
+	return count;
 
+free_and_error:
+	p9_free_req(clnt, req);
 error:
-	kfree(tc);
-	kfree(rc);
 	return err;
 }
 EXPORT_SYMBOL(p9_client_write);
 
-static struct p9_stat *p9_clone_stat(struct p9_stat *st, int dotu)
+struct p9_wstat *p9_client_stat(struct p9_fid *fid)
 {
-	int n;
-	char *p;
-	struct p9_stat *ret;
-
-	n = sizeof(struct p9_stat) + st->name.len + st->uid.len + st->gid.len +
-		st->muid.len;
+	int err;
+	struct p9_client *clnt;
+	struct p9_wstat *ret = kmalloc(sizeof(struct p9_wstat), GFP_KERNEL);
+	struct p9_req_t *req;
+	u16 ignored;
 
-	if (dotu)
-		n += st->extension.len;
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TSTAT fid %d\n", fid->fid);
 
-	ret = kmalloc(n, GFP_KERNEL);
 	if (!ret)
 		return ERR_PTR(-ENOMEM);
 
-	memmove(ret, st, sizeof(struct p9_stat));
-	p = ((char *) ret) + sizeof(struct p9_stat);
-	memmove(p, st->name.str, st->name.len);
-	ret->name.str = p;
-	p += st->name.len;
-	memmove(p, st->uid.str, st->uid.len);
-	ret->uid.str = p;
-	p += st->uid.len;
-	memmove(p, st->gid.str, st->gid.len);
-	ret->gid.str = p;
-	p += st->gid.len;
-	memmove(p, st->muid.str, st->muid.len);
-	ret->muid.str = p;
-	p += st->muid.len;
-
-	if (dotu) {
-		memmove(p, st->extension.str, st->extension.len);
-		ret->extension.str = p;
-		p += st->extension.len;
-	}
-
-	return ret;
-}
-
-struct p9_stat *p9_client_stat(struct p9_fid *fid)
-{
-	int err;
-	struct p9_fcall *tc, *rc;
-	struct p9_client *clnt;
-	struct p9_stat *ret;
-
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d\n", fid->fid);
 	err = 0;
-	tc = NULL;
-	rc = NULL;
-	ret = NULL;
 	clnt = fid->clnt;
 
-	tc = p9_create_tstat(fid->fid);
-	if (IS_ERR(tc)) {
-		err = PTR_ERR(tc);
-		tc = NULL;
+	req = p9_client_rpc(clnt, P9_TSTAT, "d", fid->fid);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
 		goto error;
 	}
 
-	err = p9_client_rpc(clnt, tc, &rc);
+	err = p9pdu_readf(req->rc, clnt->dotu, "wS", &ignored, ret);
+	p9_free_req(clnt, req);
 	if (err)
 		goto error;
 
-	ret = p9_clone_stat(&rc->params.rstat.stat, clnt->dotu);
-	if (IS_ERR(ret)) {
-		err = PTR_ERR(ret);
-		ret = NULL;
-		goto error;
-	}
+	P9_DPRINTK(P9_DEBUG_9P,
+		"<<< RSTAT sz=%x type=%x dev=%x qid=%2.2x %4.4x %8.8llx"
+		" mode=%8.8x uid=%d gid=%d size=%lld %s\n",
+		ret->size, ret->type, ret->dev, ret->qid.type,
+		ret->qid.version, ret->qid.path, ret->mode,
+		ret->n_uid, ret->n_gid, ret->length, ret->name);
 
-	kfree(tc);
-	kfree(rc);
 	return ret;
-
 error:
-	kfree(tc);
-	kfree(rc);
-	kfree(ret);
 	return ERR_PTR(err);
 }
 EXPORT_SYMBOL(p9_client_stat);
@@ -1239,27 +1220,23 @@ EXPORT_SYMBOL(p9_client_stat);
 int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst)
 {
 	int err;
-	struct p9_fcall *tc, *rc;
+	struct p9_req_t *req;
 	struct p9_client *clnt;
 
-	P9_DPRINTK(P9_DEBUG_9P, "fid %d\n", fid->fid);
+	P9_DPRINTK(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", fid->fid);
 	err = 0;
-	tc = NULL;
-	rc = NULL;
 	clnt = fid->clnt;
 
-	tc = p9_create_twstat(fid->fid, wst, clnt->dotu);
-	if (IS_ERR(tc)) {
-		err = PTR_ERR(tc);
-		tc = NULL;
-		goto done;
+	req = p9_client_rpc(clnt, P9_TWSTAT, "dwS", fid->fid, 0, wst);
+	if (IS_ERR(req)) {
+		err = PTR_ERR(req);
+		goto error;
 	}
 
-	err = p9_client_rpc(clnt, tc, &rc);
+	P9_DPRINTK(P9_DEBUG_9P, "<<< RWSTAT fid %d\n", fid->fid);
 
-done:
-	kfree(tc);
-	kfree(rc);
+	p9_free_req(clnt, req);
+error:
 	return err;
 }
 EXPORT_SYMBOL(p9_client_wstat);
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 43e98220e9a4..4ebeffd21d3d 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -27,6 +27,7 @@
 
 #include <linux/module.h>
 #include <linux/errno.h>
+#include <linux/uaccess.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 #include "protocol.h"
@@ -51,6 +52,38 @@
 static int
 p9pdu_writef(struct p9_fcall *pdu, int optional, const char *fmt, ...);
 
+#define PACKET_DEBUG 0
+
+void
+p9pdu_dump(int way, struct p9_fcall *pdu)
+{
+	int i, n;
+	u8 *data = pdu->sdata;
+	int datalen = pdu->size;
+	char buf[255];
+	int buflen = 255;
+
+	i = n = 0;
+	if (datalen > (buflen-16))
+		datalen = buflen-16;
+	while (i < datalen) {
+		n += scnprintf(buf + n, buflen - n, "%02x ", data[i]);
+		if (i%4 == 3)
+			n += scnprintf(buf + n, buflen - n, " ");
+		if (i%32 == 31)
+			n += scnprintf(buf + n, buflen - n, "\n");
+
+		i++;
+	}
+	n += scnprintf(buf + n, buflen - n, "\n");
+
+	if (way)
+		printk(KERN_NOTICE "[[(%d)[ %s\n", datalen, buf);
+	else
+		printk(KERN_NOTICE "]](%d)] %s\n", datalen, buf);
+}
+EXPORT_SYMBOL(p9pdu_dump);
+
 void p9stat_free(struct p9_wstat *stbuf)
 {
 	kfree(stbuf->name);
@@ -77,6 +110,18 @@ static size_t pdu_write(struct p9_fcall *pdu, const void *data, size_t size)
 	return size - len;
 }
 
+static size_t
+pdu_write_u(struct p9_fcall *pdu, const char __user *udata, size_t size)
+{
+	size_t len = MIN(pdu->capacity - pdu->size, size);
+	int err = copy_from_user(&pdu->sdata[pdu->size], udata, len);
+	if (err)
+		printk(KERN_WARNING "pdu_write_u returning: %d\n", err);
+
+	pdu->size += len;
+	return size - len;
+}
+
 /*
 	b - int8_t
 	w - int16_t
@@ -174,7 +219,6 @@ p9pdu_vreadf(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap)
 				stbuf->extension = NULL;
 				stbuf->n_uid = stbuf->n_gid = stbuf->n_muid =
 				    -1;
-
 				errcode =
 				    p9pdu_readf(pdu, optional,
 						"wwdQdddqssss?sddd",
@@ -332,7 +376,6 @@ p9pdu_vwritef(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap)
 		case 's':{
 				const char *ptr = va_arg(ap, const char *);
 				int16_t len = 0;
-
 				if (ptr)
 					len = MIN(strlen(ptr), USHORT_MAX);
 
@@ -356,7 +399,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap)
 				    p9pdu_writef(pdu, optional,
 						 "wwdQdddqssss?sddd",
 						 stbuf->size, stbuf->type,
-						 stbuf->dev, stbuf->qid,
+						 stbuf->dev, &stbuf->qid,
 						 stbuf->mode, stbuf->atime,
 						 stbuf->mtime, stbuf->length,
 						 stbuf->name, stbuf->uid,
@@ -374,6 +417,16 @@ p9pdu_vwritef(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap)
 					errcode = -EFAULT;
 			}
 			break;
+		case 'U':{
+				int32_t count = va_arg(ap, int32_t);
+				const char __user *udata =
+						va_arg(ap, const void *);
+				errcode =
+				    p9pdu_writef(pdu, optional, "d", count);
+				if (!errcode && pdu_write_u(pdu, udata, count))
+					errcode = -EFAULT;
+			}
+			break;
 		case 'T':{
 				int16_t nwname = va_arg(ap, int);
 				const char **wnames = va_arg(ap, const char **);
@@ -455,3 +508,29 @@ p9pdu_writef(struct p9_fcall *pdu, int optional, const char *fmt, ...)
 
 	return ret;
 }
+
+int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type)
+{
+	return p9pdu_writef(pdu, 0, "dbw", 0, type, tag);
+}
+
+int p9pdu_finalize(struct p9_fcall *pdu)
+{
+	int size = pdu->size;
+	int err;
+
+	pdu->size = 0;
+	err = p9pdu_writef(pdu, 0, "d", size);
+	pdu->size = size;
+
+	if (PACKET_DEBUG)
+		p9pdu_dump(0, pdu);
+
+	return err;
+}
+
+void p9pdu_reset(struct p9_fcall *pdu)
+{
+	pdu->offset = 0;
+	pdu->size = 0;
+}
diff --git a/net/9p/protocol.h b/net/9p/protocol.h
index 596ee10d506f..ccde462e7ac5 100644
--- a/net/9p/protocol.h
+++ b/net/9p/protocol.h
@@ -27,5 +27,8 @@
 
 int
 p9pdu_vwritef(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap);
-
 int p9pdu_readf(struct p9_fcall *pdu, int optional, const char *fmt, ...);
+int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type);
+int p9pdu_finalize(struct p9_fcall *pdu);
+void p9pdu_dump(int, struct p9_fcall *);
+void p9pdu_reset(struct p9_fcall *pdu);
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index e147ec539585..e8ebe2cb7e8b 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -181,7 +181,7 @@ static void p9_mux_poll_stop(struct p9_conn *m)
  *
  */
 
-void p9_conn_cancel(struct p9_conn *m, int err)
+static void p9_conn_cancel(struct p9_conn *m, int err)
 {
 	struct p9_req_t *req, *rtmp;
 	unsigned long flags;
@@ -287,7 +287,7 @@ static void p9_read_work(struct work_struct *work)
 	if (m->err < 0)
 		return;
 
-	P9_DPRINTK(P9_DEBUG_MUX, "start mux %p pos %d\n", m, m->rpos);
+	P9_DPRINTK(P9_DEBUG_TRANS, "start mux %p pos %d\n", m, m->rpos);
 
 	if (!m->rbuf) {
 		m->rbuf = m->tmp_buf;
@@ -296,11 +296,11 @@ static void p9_read_work(struct work_struct *work)
 	}
 
 	clear_bit(Rpending, &m->wsched);
-	P9_DPRINTK(P9_DEBUG_MUX, "read mux %p pos %d size: %d = %d\n", m,
+	P9_DPRINTK(P9_DEBUG_TRANS, "read mux %p pos %d size: %d = %d\n", m,
 					m->rpos, m->rsize, m->rsize-m->rpos);
 	err = p9_fd_read(m->client, m->rbuf + m->rpos,
 						m->rsize - m->rpos);
-	P9_DPRINTK(P9_DEBUG_MUX, "mux %p got %d bytes\n", m, err);
+	P9_DPRINTK(P9_DEBUG_TRANS, "mux %p got %d bytes\n", m, err);
 	if (err == -EAGAIN) {
 		clear_bit(Rworksched, &m->wsched);
 		return;
@@ -313,7 +313,7 @@ static void p9_read_work(struct work_struct *work)
 
 	if ((!m->req) && (m->rpos == m->rsize)) { /* header read in */
 		u16 tag;
-		P9_DPRINTK(P9_DEBUG_MUX, "got new header\n");
+		P9_DPRINTK(P9_DEBUG_TRANS, "got new header\n");
 
 		n = le32_to_cpu(*(__le32 *) m->rbuf); /* read packet size */
 		if (n >= m->client->msize) {
@@ -324,8 +324,8 @@ static void p9_read_work(struct work_struct *work)
 		}
 
 		tag = le16_to_cpu(*(__le16 *) (m->rbuf+5)); /* read tag */
-		P9_DPRINTK(P9_DEBUG_MUX, "mux %p pkt: size: %d bytes tag: %d\n",
-								 m, n, tag);
+		P9_DPRINTK(P9_DEBUG_TRANS,
+			"mux %p pkt: size: %d bytes tag: %d\n", m, n, tag);
 
 		m->req = p9_tag_lookup(m->client, tag);
 		if (!m->req) {
@@ -351,7 +351,7 @@ static void p9_read_work(struct work_struct *work)
 
 	/* not an else because some packets (like clunk) have no payload */
 	if ((m->req) && (m->rpos == m->rsize)) { /* packet is read in */
-		P9_DPRINTK(P9_DEBUG_MUX, "got new packet\n");
+		P9_DPRINTK(P9_DEBUG_TRANS, "got new packet\n");
 
 		list_del(&m->req->req_list);
 		p9_client_cb(m->client, m->req);
@@ -369,7 +369,7 @@ static void p9_read_work(struct work_struct *work)
 			n = p9_fd_poll(m->client, NULL);
 
 		if (n & POLLIN) {
-			P9_DPRINTK(P9_DEBUG_MUX, "schedule read work %p\n", m);
+			P9_DPRINTK(P9_DEBUG_TRANS, "sched read work %p\n", m);
 			queue_work(p9_mux_wq, &m->rq);
 		} else
 			clear_bit(Rworksched, &m->wsched);
@@ -453,11 +453,11 @@ static void p9_write_work(struct work_struct *work)
 		spin_unlock(&m->client->lock);
 	}
 
-	P9_DPRINTK(P9_DEBUG_MUX, "mux %p pos %d size %d\n", m, m->wpos,
+	P9_DPRINTK(P9_DEBUG_TRANS, "mux %p pos %d size %d\n", m, m->wpos,
 								m->wsize);
 	clear_bit(Wpending, &m->wsched);
 	err = p9_fd_write(m->client, m->wbuf + m->wpos, m->wsize - m->wpos);
-	P9_DPRINTK(P9_DEBUG_MUX, "mux %p sent %d bytes\n", m, err);
+	P9_DPRINTK(P9_DEBUG_TRANS, "mux %p sent %d bytes\n", m, err);
 	if (err == -EAGAIN) {
 		clear_bit(Wworksched, &m->wsched);
 		return;
@@ -481,7 +481,7 @@ static void p9_write_work(struct work_struct *work)
 			n = p9_fd_poll(m->client, NULL);
 
 		if (n & POLLOUT) {
-			P9_DPRINTK(P9_DEBUG_MUX, "schedule write work %p\n", m);
+			P9_DPRINTK(P9_DEBUG_TRANS, "sched write work %p\n", m);
 			queue_work(p9_mux_wq, &m->wq);
 		} else
 			clear_bit(Wworksched, &m->wsched);
@@ -558,7 +558,8 @@ static struct p9_conn *p9_conn_create(struct p9_client *client)
 	int n;
 	struct p9_conn *m;
 
-	P9_DPRINTK(P9_DEBUG_MUX, "client %p msize %d\n", client, client->msize);
+	P9_DPRINTK(P9_DEBUG_TRANS, "client %p msize %d\n", client,
+								client->msize);
 	m = kzalloc(sizeof(struct p9_conn), GFP_KERNEL);
 	if (!m)
 		return ERR_PTR(-ENOMEM);
@@ -575,12 +576,12 @@ static struct p9_conn *p9_conn_create(struct p9_client *client)
 
 	n = p9_fd_poll(client, &m->pt);
 	if (n & POLLIN) {
-		P9_DPRINTK(P9_DEBUG_MUX, "mux %p can read\n", m);
+		P9_DPRINTK(P9_DEBUG_TRANS, "mux %p can read\n", m);
 		set_bit(Rpending, &m->wsched);
 	}
 
 	if (n & POLLOUT) {
-		P9_DPRINTK(P9_DEBUG_MUX, "mux %p can write\n", m);
+		P9_DPRINTK(P9_DEBUG_TRANS, "mux %p can write\n", m);
 		set_bit(Wpending, &m->wsched);
 	}
 
@@ -602,7 +603,7 @@ static void p9_poll_mux(struct p9_conn *m)
 
 	n = p9_fd_poll(m->client, NULL);
 	if (n < 0 || n & (POLLERR | POLLHUP | POLLNVAL)) {
-		P9_DPRINTK(P9_DEBUG_MUX, "error mux %p err %d\n", m, n);
+		P9_DPRINTK(P9_DEBUG_TRANS, "error mux %p err %d\n", m, n);
 		if (n >= 0)
 			n = -ECONNRESET;
 		p9_conn_cancel(m, n);
@@ -610,19 +611,19 @@ static void p9_poll_mux(struct p9_conn *m)
 
 	if (n & POLLIN) {
 		set_bit(Rpending, &m->wsched);
-		P9_DPRINTK(P9_DEBUG_MUX, "mux %p can read\n", m);
+		P9_DPRINTK(P9_DEBUG_TRANS, "mux %p can read\n", m);
 		if (!test_and_set_bit(Rworksched, &m->wsched)) {
-			P9_DPRINTK(P9_DEBUG_MUX, "schedule read work %p\n", m);
+			P9_DPRINTK(P9_DEBUG_TRANS, "sched read work %p\n", m);
 			queue_work(p9_mux_wq, &m->rq);
 		}
 	}
 
 	if (n & POLLOUT) {
 		set_bit(Wpending, &m->wsched);
-		P9_DPRINTK(P9_DEBUG_MUX, "mux %p can write\n", m);
+		P9_DPRINTK(P9_DEBUG_TRANS, "mux %p can write\n", m);
 		if ((m->wsize || !list_empty(&m->unsent_req_list))
 		    && !test_and_set_bit(Wworksched, &m->wsched)) {
-			P9_DPRINTK(P9_DEBUG_MUX, "schedule write work %p\n", m);
+			P9_DPRINTK(P9_DEBUG_TRANS, "sched write work %p\n", m);
 			queue_work(p9_mux_wq, &m->wq);
 		}
 	}
@@ -645,8 +646,8 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
 	struct p9_trans_fd *ts = client->trans;
 	struct p9_conn *m = ts->conn;
 
-	P9_DPRINTK(P9_DEBUG_MUX, "mux %p task %p tcall %p id %d\n", m, current,
-		req->tc, req->tc->id);
+	P9_DPRINTK(P9_DEBUG_TRANS, "mux %p task %p tcall %p id %d\n", m,
+						current, req->tc, req->tc->id);
 	if (m->err < 0)
 		return m->err;
 
@@ -672,19 +673,12 @@ static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
 	struct p9_trans_fd *ts = client->trans;
 	struct p9_conn *m = ts->conn;
 
-	P9_DPRINTK(P9_DEBUG_MUX, "mux %p req %p\n", m, req);
+	P9_DPRINTK(P9_DEBUG_TRANS, "mux %p req %p\n", m, req);
 
 	spin_lock(&client->lock);
 	list_del(&req->req_list);
 	spin_unlock(&client->lock);
 
-	/* if a response was received for a request, do nothing */
-	if (req->rc || req->t_err) {
-		P9_DPRINTK(P9_DEBUG_MUX,
-			"mux %p req %p response already received\n", m, req);
-		return 0;
-	}
-
 	if (req->status == REQ_STATUS_UNSENT) {
 		req->status = REQ_STATUS_FLSHD;
 		return 0;
@@ -809,7 +803,7 @@ static int p9_socket_open(struct p9_client *client, struct socket *csocket)
 
 static void p9_conn_destroy(struct p9_conn *m)
 {
-	P9_DPRINTK(P9_DEBUG_MUX, "mux %p prev %p next %p\n", m,
+	P9_DPRINTK(P9_DEBUG_TRANS, "mux %p prev %p next %p\n", m,
 		m->mux_list.prev, m->mux_list.next);
 
 	p9_mux_poll_stop(m);
@@ -1060,7 +1054,7 @@ static int p9_poll_proc(void *a)
 {
 	unsigned long flags;
 
-	P9_DPRINTK(P9_DEBUG_MUX, "start %p\n", current);
+	P9_DPRINTK(P9_DEBUG_TRANS, "start %p\n", current);
  repeat:
 	spin_lock_irqsave(&p9_poll_lock, flags);
 	while (!list_empty(&p9_poll_pending_list)) {
@@ -1078,7 +1072,7 @@ static int p9_poll_proc(void *a)
 
 	set_current_state(TASK_INTERRUPTIBLE);
 	if (list_empty(&p9_poll_pending_list)) {
-		P9_DPRINTK(P9_DEBUG_MUX, "sleeping...\n");
+		P9_DPRINTK(P9_DEBUG_TRANS, "sleeping...\n");
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -1086,7 +1080,7 @@ static int p9_poll_proc(void *a)
 	if (!kthread_should_stop())
 		goto repeat;
 
-	P9_DPRINTK(P9_DEBUG_MUX, "finish\n");
+	P9_DPRINTK(P9_DEBUG_TRANS, "finish\n");
 	return 0;
 }
 
diff --git a/net/9p/util.c b/net/9p/util.c
index 958fc58cd1ff..dc4ec05ad93d 100644
--- a/net/9p/util.c
+++ b/net/9p/util.c
@@ -105,6 +105,7 @@ retry:
 	else if (error)
 		return -1;
 
+	P9_DPRINTK(P9_DEBUG_MUX, " id %d pool %p\n", i, p);
 	return i;
 }
 EXPORT_SYMBOL(p9_idpool_get);
@@ -121,6 +122,9 @@ EXPORT_SYMBOL(p9_idpool_get);
 void p9_idpool_put(int id, struct p9_idpool *p)
 {
 	unsigned long flags;
+
+	P9_DPRINTK(P9_DEBUG_MUX, " id %d pool %p\n", id, p);
+
 	spin_lock_irqsave(&p->lock, flags);
 	idr_remove(&p->pool, id);
 	spin_unlock_irqrestore(&p->lock, flags);
-- 
cgit v1.2.3


From 02da398b950c5d079c20afaa23f322383e96070a Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Thu, 16 Oct 2008 08:29:30 -0500
Subject: 9p: eliminate depricated conv functions

Remove depricated conv functions which have been replaced with new
protocol routines.

This patch also reworks the one instance of the file-system code which
directly calls conversion routines (to accomplish unpacking dirreads).

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 fs/9p/vfs_dir.c         |   20 +-
 include/net/9p/9p.h     |  107 +----
 include/net/9p/client.h |    2 +
 net/9p/Makefile         |    1 -
 net/9p/conv.c           | 1054 -----------------------------------------------
 net/9p/protocol.c       |   13 +
 6 files changed, 37 insertions(+), 1160 deletions(-)
 delete mode 100644 net/9p/conv.c

(limited to 'include')

diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c
index 276aed625929..873cd31baa47 100644
--- a/fs/9p/vfs_dir.c
+++ b/fs/9p/vfs_dir.c
@@ -45,7 +45,7 @@
  *
  */
 
-static inline int dt_type(struct p9_stat *mistat)
+static inline int dt_type(struct p9_wstat *mistat)
 {
 	unsigned long perm = mistat->mode;
 	int rettype = DT_REG;
@@ -69,7 +69,7 @@ static inline int dt_type(struct p9_stat *mistat)
 static int v9fs_dir_readdir(struct file *filp, void *dirent, filldir_t filldir)
 {
 	int over;
-	struct p9_stat st;
+	struct p9_wstat st;
 	int err;
 	struct p9_fid *fid;
 	int buflen;
@@ -92,20 +92,24 @@ static int v9fs_dir_readdir(struct file *filp, void *dirent, filldir_t filldir)
 
 		n = err;
 		while (i < n) {
-			err = p9_deserialize_stat(statbuf + i, buflen-i, &st,
+			err = p9stat_read(statbuf + i, buflen-i, &st,
 							fid->clnt->dotu);
-			if (!err) {
+			if (err) {
+				P9_DPRINTK(P9_DEBUG_VFS, "returned %d\n", err);
 				err = -EIO;
+				p9stat_free(&st);
 				goto free_and_exit;
 			}
 
-			i += err;
-			fid->rdir_fpos += err;
+			i += st.size+2;
+			fid->rdir_fpos += st.size+2;
 
-			over = filldir(dirent, st.name.str, st.name.len,
+			over = filldir(dirent, st.name, strlen(st.name),
 			    filp->f_pos, v9fs_qid2ino(&st.qid), dt_type(&st));
 
-			filp->f_pos += st.size;
+			filp->f_pos += st.size+2;
+
+			p9stat_free(&st);
 
 			if (over) {
 				err = 0;
diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index 56c15aee6e61..cb5bc731e885 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -61,21 +61,18 @@ extern unsigned int p9_debug_level;
 
 #define P9_DPRINTK(level, format, arg...) \
 do {  \
-	if (level == P9_DEBUG_9P) \
-		printk(KERN_NOTICE "(%8.8d) " \
-		format , task_pid_nr(current) , ## arg); \
-	else if ((p9_debug_level & level) == level) \
-		printk(KERN_NOTICE "-- %s (%d): " \
-		format , __func__, task_pid_nr(current) , ## arg); \
+	if ((p9_debug_level & level) == level) {\
+		if (level == P9_DEBUG_9P) \
+			printk(KERN_NOTICE "(%8.8d) " \
+			format , task_pid_nr(current) , ## arg); \
+		else \
+			printk(KERN_NOTICE "-- %s (%d): " \
+			format , __func__, task_pid_nr(current) , ## arg); \
+	} \
 } while (0)
 
-#define PRINT_FCALL_ERROR(s, fcall) P9_DPRINTK(P9_DEBUG_ERROR,   \
-	"%s: %.*s\n", s, fcall?fcall->params.rerror.error.len:0, \
-	fcall?fcall->params.rerror.error.str:"");
-
 #else
 #define P9_DPRINTK(level, format, arg...)  do { } while (0)
-#define PRINT_FCALL_ERROR(s, fcall) do { } while (0)
 #endif
 
 #define P9_EPRINTK(level, format, arg...) \
@@ -330,33 +327,6 @@ struct p9_qid {
  * See Also: http://plan9.bell-labs.com/magic/man2html/2/stat
  */
 
-struct p9_stat {
-	u16 size;
-	u16 type;
-	u32 dev;
-	struct p9_qid qid;
-	u32 mode;
-	u32 atime;
-	u32 mtime;
-	u64 length;
-	struct p9_str name;
-	struct p9_str uid;
-	struct p9_str gid;
-	struct p9_str muid;
-	struct p9_str extension;	/* 9p2000.u extensions */
-	u32 n_uid;			/* 9p2000.u extensions */
-	u32 n_gid;			/* 9p2000.u extensions */
-	u32 n_muid;			/* 9p2000.u extensions */
-};
-
-/*
- * file metadata (stat) structure used to create Twstat message
- * The is identical to &p9_stat, but the strings don't point to
- * the same memory block and should be freed separately
- *
- * See Also: http://plan9.bell-labs.com/magic/man2html/2/stat
- */
-
 struct p9_wstat {
 	u16 size;
 	u16 type;
@@ -498,12 +468,12 @@ struct p9_tstat {
 };
 
 struct p9_rstat {
-	struct p9_stat stat;
+	struct p9_wstat stat;
 };
 
 struct p9_twstat {
 	u32 fid;
-	struct p9_stat stat;
+	struct p9_wstat stat;
 };
 
 struct p9_rwstat {
@@ -517,7 +487,6 @@ struct p9_rwstat {
  * @offset: used by marshalling routines to track currentposition in buffer
  * @capacity: used by marshalling routines to track total capacity
  * @sdata: payload
- * @params: per-operation parameters
  *
  * &p9_fcall represents the structure for all 9P RPC
  * transactions.  Requests are packaged into fcalls, and reponses
@@ -535,66 +504,10 @@ struct p9_fcall {
 	size_t capacity;
 
 	uint8_t *sdata;
-
-	union {
-		struct p9_tversion tversion;
-		struct p9_rversion rversion;
-		struct p9_tauth tauth;
-		struct p9_rauth rauth;
-		struct p9_rerror rerror;
-		struct p9_tflush tflush;
-		struct p9_rflush rflush;
-		struct p9_tattach tattach;
-		struct p9_rattach rattach;
-		struct p9_twalk twalk;
-		struct p9_rwalk rwalk;
-		struct p9_topen topen;
-		struct p9_ropen ropen;
-		struct p9_tcreate tcreate;
-		struct p9_rcreate rcreate;
-		struct p9_tread tread;
-		struct p9_rread rread;
-		struct p9_twrite twrite;
-		struct p9_rwrite rwrite;
-		struct p9_tclunk tclunk;
-		struct p9_rclunk rclunk;
-		struct p9_tremove tremove;
-		struct p9_rremove rremove;
-		struct p9_tstat tstat;
-		struct p9_rstat rstat;
-		struct p9_twstat twstat;
-		struct p9_rwstat rwstat;
-	} params;
 };
 
 struct p9_idpool;
 
-int p9_deserialize_stat(void *buf, u32 buflen, struct p9_stat *stat,
-	int dotu);
-int p9_deserialize_fcall(void *buf, u32 buflen, struct p9_fcall *fc, int dotu);
-void p9_set_tag(struct p9_fcall *fc, u16 tag);
-struct p9_fcall *p9_create_tversion(u32 msize, char *version);
-struct p9_fcall *p9_create_tattach(u32 fid, u32 afid, char *uname,
-	char *aname, u32 n_uname, int dotu);
-struct p9_fcall *p9_create_tauth(u32 afid, char *uname, char *aname,
-	u32 n_uname, int dotu);
-struct p9_fcall *p9_create_tflush(u16 oldtag);
-struct p9_fcall *p9_create_twalk(u32 fid, u32 newfid, u16 nwname,
-	char **wnames);
-struct p9_fcall *p9_create_topen(u32 fid, u8 mode);
-struct p9_fcall *p9_create_tcreate(u32 fid, char *name, u32 perm, u8 mode,
-	char *extension, int dotu);
-struct p9_fcall *p9_create_tread(u32 fid, u64 offset, u32 count);
-struct p9_fcall *p9_create_twrite(u32 fid, u64 offset, u32 count,
-	const char *data);
-struct p9_fcall *p9_create_twrite_u(u32 fid, u64 offset, u32 count,
-	const char __user *data);
-struct p9_fcall *p9_create_tclunk(u32 fid);
-struct p9_fcall *p9_create_tremove(u32 fid);
-struct p9_fcall *p9_create_tstat(u32 fid);
-struct p9_fcall *p9_create_twstat(u32 fid, struct p9_wstat *wstat,
-	int dotu);
-
 int p9_errstr2errno(char *errstr, int len);
 
 struct p9_idpool *p9_idpool_create(void);
diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index 1e49b4d1030b..1f17f3d93727 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -206,6 +206,8 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst);
 struct p9_req_t *p9_tag_lookup(struct p9_client *, u16);
 void p9_client_cb(struct p9_client *c, struct p9_req_t *req);
 
+int p9stat_read(char *, int, struct p9_wstat *, int);
 void p9stat_free(struct p9_wstat *);
 
+
 #endif /* NET_9P_CLIENT_H */
diff --git a/net/9p/Makefile b/net/9p/Makefile
index c3302d88b808..1041b7bd12e2 100644
--- a/net/9p/Makefile
+++ b/net/9p/Makefile
@@ -4,7 +4,6 @@ obj-$(CONFIG_NET_9P_VIRTIO) += 9pnet_virtio.o
 9pnet-objs := \
 	mod.o \
 	client.o \
-	conv.o \
 	error.o \
 	util.o \
 	protocol.o \
diff --git a/net/9p/conv.c b/net/9p/conv.c
deleted file mode 100644
index 5ad3a3bd73b2..000000000000
--- a/net/9p/conv.c
+++ /dev/null
@@ -1,1054 +0,0 @@
-/*
- * net/9p/conv.c
- *
- * 9P protocol conversion functions
- *
- *  Copyright (C) 2004, 2005 by Latchesar Ionkov <lucho@ionkov.net>
- *  Copyright (C) 2004 by Eric Van Hensbergen <ericvh@gmail.com>
- *  Copyright (C) 2002 by Ron Minnich <rminnich@lanl.gov>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2
- *  as published by the Free Software Foundation.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to:
- *  Free Software Foundation
- *  51 Franklin Street, Fifth Floor
- *  Boston, MA  02111-1301  USA
- *
- */
-
-#include <linux/module.h>
-#include <linux/errno.h>
-#include <linux/fs.h>
-#include <linux/sched.h>
-#include <linux/idr.h>
-#include <linux/uaccess.h>
-#include <net/9p/9p.h>
-
-/*
- * Buffer to help with string parsing
- */
-struct cbuf {
-	unsigned char *sp;
-	unsigned char *p;
-	unsigned char *ep;
-};
-
-static inline void buf_init(struct cbuf *buf, void *data, int datalen)
-{
-	buf->sp = buf->p = data;
-	buf->ep = data + datalen;
-}
-
-static inline int buf_check_overflow(struct cbuf *buf)
-{
-	return buf->p > buf->ep;
-}
-
-static int buf_check_size(struct cbuf *buf, int len)
-{
-	if (buf->p + len > buf->ep) {
-		if (buf->p < buf->ep) {
-			P9_EPRINTK(KERN_ERR,
-				"buffer overflow: want %d has %d\n", len,
-				(int)(buf->ep - buf->p));
-			dump_stack();
-			buf->p = buf->ep + 1;
-		}
-
-		return 0;
-	}
-
-	return 1;
-}
-
-static void *buf_alloc(struct cbuf *buf, int len)
-{
-	void *ret = NULL;
-
-	if (buf_check_size(buf, len)) {
-		ret = buf->p;
-		buf->p += len;
-	}
-
-	return ret;
-}
-
-static void buf_put_int8(struct cbuf *buf, u8 val)
-{
-	if (buf_check_size(buf, 1)) {
-		buf->p[0] = val;
-		buf->p++;
-	}
-}
-
-static void buf_put_int16(struct cbuf *buf, u16 val)
-{
-	if (buf_check_size(buf, 2)) {
-		*(__le16 *) buf->p = cpu_to_le16(val);
-		buf->p += 2;
-	}
-}
-
-static void buf_put_int32(struct cbuf *buf, u32 val)
-{
-	if (buf_check_size(buf, 4)) {
-		*(__le32 *)buf->p = cpu_to_le32(val);
-		buf->p += 4;
-	}
-}
-
-static void buf_put_int64(struct cbuf *buf, u64 val)
-{
-	if (buf_check_size(buf, 8)) {
-		*(__le64 *)buf->p = cpu_to_le64(val);
-		buf->p += 8;
-	}
-}
-
-static char *buf_put_stringn(struct cbuf *buf, const char *s, u16 slen)
-{
-	char *ret;
-
-	ret = NULL;
-	if (buf_check_size(buf, slen + 2)) {
-		buf_put_int16(buf, slen);
-		ret = buf->p;
-		memcpy(buf->p, s, slen);
-		buf->p += slen;
-	}
-
-	return ret;
-}
-
-static u8 buf_get_int8(struct cbuf *buf)
-{
-	u8 ret = 0;
-
-	if (buf_check_size(buf, 1)) {
-		ret = buf->p[0];
-		buf->p++;
-	}
-
-	return ret;
-}
-
-static u16 buf_get_int16(struct cbuf *buf)
-{
-	u16 ret = 0;
-
-	if (buf_check_size(buf, 2)) {
-		ret = le16_to_cpu(*(__le16 *)buf->p);
-		buf->p += 2;
-	}
-
-	return ret;
-}
-
-static u32 buf_get_int32(struct cbuf *buf)
-{
-	u32 ret = 0;
-
-	if (buf_check_size(buf, 4)) {
-		ret = le32_to_cpu(*(__le32 *)buf->p);
-		buf->p += 4;
-	}
-
-	return ret;
-}
-
-static u64 buf_get_int64(struct cbuf *buf)
-{
-	u64 ret = 0;
-
-	if (buf_check_size(buf, 8)) {
-		ret = le64_to_cpu(*(__le64 *)buf->p);
-		buf->p += 8;
-	}
-
-	return ret;
-}
-
-static void buf_get_str(struct cbuf *buf, struct p9_str *vstr)
-{
-	vstr->len = buf_get_int16(buf);
-	if (!buf_check_overflow(buf) && buf_check_size(buf, vstr->len)) {
-		vstr->str = buf->p;
-		buf->p += vstr->len;
-	} else {
-		vstr->len = 0;
-		vstr->str = NULL;
-	}
-}
-
-static void buf_get_qid(struct cbuf *bufp, struct p9_qid *qid)
-{
-	qid->type = buf_get_int8(bufp);
-	qid->version = buf_get_int32(bufp);
-	qid->path = buf_get_int64(bufp);
-}
-
-/**
- * p9_size_wstat - calculate the size of a variable length stat struct
- * @wstat: metadata (stat) structure
- * @dotu: non-zero if 9P2000.u
- *
- */
-
-static int p9_size_wstat(struct p9_wstat *wstat, int dotu)
-{
-	int size = 0;
-
-	if (wstat == NULL) {
-		P9_EPRINTK(KERN_ERR, "p9_size_stat: got a NULL stat pointer\n");
-		return 0;
-	}
-
-	size =			/* 2 + *//* size[2] */
-	    2 +			/* type[2] */
-	    4 +			/* dev[4] */
-	    1 +			/* qid.type[1] */
-	    4 +			/* qid.vers[4] */
-	    8 +			/* qid.path[8] */
-	    4 +			/* mode[4] */
-	    4 +			/* atime[4] */
-	    4 +			/* mtime[4] */
-	    8 +			/* length[8] */
-	    8;			/* minimum sum of string lengths */
-
-	if (wstat->name)
-		size += strlen(wstat->name);
-	if (wstat->uid)
-		size += strlen(wstat->uid);
-	if (wstat->gid)
-		size += strlen(wstat->gid);
-	if (wstat->muid)
-		size += strlen(wstat->muid);
-
-	if (dotu) {
-		size += 4 +	/* n_uid[4] */
-		    4 +		/* n_gid[4] */
-		    4 +		/* n_muid[4] */
-		    2;		/* string length of extension[4] */
-		if (wstat->extension)
-			size += strlen(wstat->extension);
-	}
-
-	return size;
-}
-
-/**
- * buf_get_stat - safely decode a recieved metadata (stat) structure
- * @bufp: buffer to deserialize
- * @stat: metadata (stat) structure
- * @dotu: non-zero if 9P2000.u
- *
- */
-
-static void
-buf_get_stat(struct cbuf *bufp, struct p9_stat *stat, int dotu)
-{
-	stat->size = buf_get_int16(bufp);
-	stat->type = buf_get_int16(bufp);
-	stat->dev = buf_get_int32(bufp);
-	stat->qid.type = buf_get_int8(bufp);
-	stat->qid.version = buf_get_int32(bufp);
-	stat->qid.path = buf_get_int64(bufp);
-	stat->mode = buf_get_int32(bufp);
-	stat->atime = buf_get_int32(bufp);
-	stat->mtime = buf_get_int32(bufp);
-	stat->length = buf_get_int64(bufp);
-	buf_get_str(bufp, &stat->name);
-	buf_get_str(bufp, &stat->uid);
-	buf_get_str(bufp, &stat->gid);
-	buf_get_str(bufp, &stat->muid);
-
-	if (dotu) {
-		buf_get_str(bufp, &stat->extension);
-		stat->n_uid = buf_get_int32(bufp);
-		stat->n_gid = buf_get_int32(bufp);
-		stat->n_muid = buf_get_int32(bufp);
-	}
-}
-
-/**
- * p9_deserialize_stat - decode a received metadata structure
- * @buf: buffer to deserialize
- * @buflen: length of received buffer
- * @stat: metadata structure to decode into
- * @dotu: non-zero if 9P2000.u
- *
- * Note: stat will point to the buf region.
- */
-
-int
-p9_deserialize_stat(void *buf, u32 buflen, struct p9_stat *stat,
-		int dotu)
-{
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-	unsigned char *p;
-
-	buf_init(bufp, buf, buflen);
-	p = bufp->p;
-	buf_get_stat(bufp, stat, dotu);
-
-	if (buf_check_overflow(bufp))
-		return 0;
-	else
-		return bufp->p - p;
-}
-EXPORT_SYMBOL(p9_deserialize_stat);
-
-/**
- * deserialize_fcall - unmarshal a response
- * @buf: recieved buffer
- * @buflen: length of received buffer
- * @rcall: fcall structure to populate
- * @rcalllen: length of fcall structure to populate
- * @dotu: non-zero if 9P2000.u
- *
- */
-
-int
-p9_deserialize_fcall(void *buf, u32 buflen, struct p9_fcall *rcall,
-		       int dotu)
-{
-
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-	int i = 0;
-
-	buf_init(bufp, buf, buflen);
-
-	rcall->size = buf_get_int32(bufp);
-	rcall->id = buf_get_int8(bufp);
-	rcall->tag = buf_get_int16(bufp);
-
-	P9_DPRINTK(P9_DEBUG_CONV, "size %d id %d tag %d\n", rcall->size,
-							rcall->id, rcall->tag);
-
-	switch (rcall->id) {
-	default:
-		P9_EPRINTK(KERN_ERR, "unknown message type: %d\n", rcall->id);
-		return -EPROTO;
-	case P9_RVERSION:
-		rcall->params.rversion.msize = buf_get_int32(bufp);
-		buf_get_str(bufp, &rcall->params.rversion.version);
-		break;
-	case P9_RFLUSH:
-		break;
-	case P9_RATTACH:
-		rcall->params.rattach.qid.type = buf_get_int8(bufp);
-		rcall->params.rattach.qid.version = buf_get_int32(bufp);
-		rcall->params.rattach.qid.path = buf_get_int64(bufp);
-		break;
-	case P9_RWALK:
-		rcall->params.rwalk.nwqid = buf_get_int16(bufp);
-		if (rcall->params.rwalk.nwqid > P9_MAXWELEM) {
-			P9_EPRINTK(KERN_ERR,
-					"Rwalk with more than %d qids: %d\n",
-					P9_MAXWELEM, rcall->params.rwalk.nwqid);
-			return -EPROTO;
-		}
-
-		for (i = 0; i < rcall->params.rwalk.nwqid; i++)
-			buf_get_qid(bufp, &rcall->params.rwalk.wqids[i]);
-		break;
-	case P9_ROPEN:
-		buf_get_qid(bufp, &rcall->params.ropen.qid);
-		rcall->params.ropen.iounit = buf_get_int32(bufp);
-		break;
-	case P9_RCREATE:
-		buf_get_qid(bufp, &rcall->params.rcreate.qid);
-		rcall->params.rcreate.iounit = buf_get_int32(bufp);
-		break;
-	case P9_RREAD:
-		rcall->params.rread.count = buf_get_int32(bufp);
-		rcall->params.rread.data = bufp->p;
-		buf_check_size(bufp, rcall->params.rread.count);
-		break;
-	case P9_RWRITE:
-		rcall->params.rwrite.count = buf_get_int32(bufp);
-		break;
-	case P9_RCLUNK:
-		break;
-	case P9_RREMOVE:
-		break;
-	case P9_RSTAT:
-		buf_get_int16(bufp);
-		buf_get_stat(bufp, &rcall->params.rstat.stat, dotu);
-		break;
-	case P9_RWSTAT:
-		break;
-	case P9_RERROR:
-		buf_get_str(bufp, &rcall->params.rerror.error);
-		if (dotu)
-			rcall->params.rerror.errno = buf_get_int16(bufp);
-		break;
-	}
-
-	if (buf_check_overflow(bufp)) {
-		P9_DPRINTK(P9_DEBUG_ERROR, "buffer overflow\n");
-		return -EIO;
-	}
-
-	return bufp->p - bufp->sp;
-}
-EXPORT_SYMBOL(p9_deserialize_fcall);
-
-static inline void p9_put_int8(struct cbuf *bufp, u8 val, u8 * p)
-{
-	*p = val;
-	buf_put_int8(bufp, val);
-}
-
-static inline void p9_put_int16(struct cbuf *bufp, u16 val, u16 * p)
-{
-	*p = val;
-	buf_put_int16(bufp, val);
-}
-
-static inline void p9_put_int32(struct cbuf *bufp, u32 val, u32 * p)
-{
-	*p = val;
-	buf_put_int32(bufp, val);
-}
-
-static inline void p9_put_int64(struct cbuf *bufp, u64 val, u64 * p)
-{
-	*p = val;
-	buf_put_int64(bufp, val);
-}
-
-static void
-p9_put_str(struct cbuf *bufp, char *data, struct p9_str *str)
-{
-	int len;
-	char *s;
-
-	if (data)
-		len = strlen(data);
-	else
-		len = 0;
-
-	s = buf_put_stringn(bufp, data, len);
-	if (str) {
-		str->len = len;
-		str->str = s;
-	}
-}
-
-static int
-p9_put_data(struct cbuf *bufp, const char *data, int count,
-		   unsigned char **pdata)
-{
-	*pdata = buf_alloc(bufp, count);
-	if (*pdata == NULL)
-		return -ENOMEM;
-	memmove(*pdata, data, count);
-	return 0;
-}
-
-static int
-p9_put_user_data(struct cbuf *bufp, const char __user *data, int count,
-		   unsigned char **pdata)
-{
-	*pdata = buf_alloc(bufp, count);
-	if (*pdata == NULL)
-		return -ENOMEM;
-	return copy_from_user(*pdata, data, count);
-}
-
-static void
-p9_put_wstat(struct cbuf *bufp, struct p9_wstat *wstat,
-	       struct p9_stat *stat, int statsz, int dotu)
-{
-	p9_put_int16(bufp, statsz, &stat->size);
-	p9_put_int16(bufp, wstat->type, &stat->type);
-	p9_put_int32(bufp, wstat->dev, &stat->dev);
-	p9_put_int8(bufp, wstat->qid.type, &stat->qid.type);
-	p9_put_int32(bufp, wstat->qid.version, &stat->qid.version);
-	p9_put_int64(bufp, wstat->qid.path, &stat->qid.path);
-	p9_put_int32(bufp, wstat->mode, &stat->mode);
-	p9_put_int32(bufp, wstat->atime, &stat->atime);
-	p9_put_int32(bufp, wstat->mtime, &stat->mtime);
-	p9_put_int64(bufp, wstat->length, &stat->length);
-
-	p9_put_str(bufp, wstat->name, &stat->name);
-	p9_put_str(bufp, wstat->uid, &stat->uid);
-	p9_put_str(bufp, wstat->gid, &stat->gid);
-	p9_put_str(bufp, wstat->muid, &stat->muid);
-
-	if (dotu) {
-		p9_put_str(bufp, wstat->extension, &stat->extension);
-		p9_put_int32(bufp, wstat->n_uid, &stat->n_uid);
-		p9_put_int32(bufp, wstat->n_gid, &stat->n_gid);
-		p9_put_int32(bufp, wstat->n_muid, &stat->n_muid);
-	}
-}
-
-static struct p9_fcall *
-p9_create_common(struct cbuf *bufp, u32 size, u8 id)
-{
-	struct p9_fcall *fc;
-
-	size += 4 + 1 + 2;	/* size[4] id[1] tag[2] */
-	fc = kmalloc(sizeof(struct p9_fcall) + size, GFP_KERNEL);
-	if (!fc)
-		return ERR_PTR(-ENOMEM);
-
-	fc->sdata = (char *)fc + sizeof(*fc);
-
-	buf_init(bufp, (char *)fc->sdata, size);
-	p9_put_int32(bufp, size, &fc->size);
-	p9_put_int8(bufp, id, &fc->id);
-	p9_put_int16(bufp, P9_NOTAG, &fc->tag);
-
-	return fc;
-}
-
-/**
- * p9_set_tag - set the tag field of an &p9_fcall structure
- * @fc: fcall structure to set tag within
- * @tag: tag id to set
- */
-
-void p9_set_tag(struct p9_fcall *fc, u16 tag)
-{
-	fc->tag = tag;
-	*(__le16 *) (fc->sdata + 5) = cpu_to_le16(tag);
-}
-EXPORT_SYMBOL(p9_set_tag);
-
-/**
- * p9_create_tversion - allocates and creates a T_VERSION request
- * @msize: requested maximum data size
- * @version: version string to negotiate
- *
- */
-struct p9_fcall *p9_create_tversion(u32 msize, char *version)
-{
-	int size;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	size = 4 + 2 + strlen(version);	/* msize[4] version[s] */
-	fc = p9_create_common(bufp, size, P9_TVERSION);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, msize, &fc->params.tversion.msize);
-	p9_put_str(bufp, version, &fc->params.tversion.version);
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_tversion);
-
-/**
- * p9_create_tauth - allocates and creates a T_AUTH request
- * @afid: handle to use for authentication protocol
- * @uname: user name attempting to authenticate
- * @aname: mount specifier for remote server
- * @n_uname: numeric id for user attempting to authneticate
- * @dotu: 9P2000.u extension flag
- *
- */
-
-struct p9_fcall *p9_create_tauth(u32 afid, char *uname, char *aname,
-	u32 n_uname, int dotu)
-{
-	int size;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	/* afid[4] uname[s] aname[s] */
-	size = 4 + 2 + 2;
-	if (uname)
-		size += strlen(uname);
-
-	if (aname)
-		size += strlen(aname);
-
-	if (dotu)
-		size += 4;	/* n_uname */
-
-	fc = p9_create_common(bufp, size, P9_TAUTH);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, afid, &fc->params.tauth.afid);
-	p9_put_str(bufp, uname, &fc->params.tauth.uname);
-	p9_put_str(bufp, aname, &fc->params.tauth.aname);
-	if (dotu)
-		p9_put_int32(bufp, n_uname, &fc->params.tauth.n_uname);
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_tauth);
-
-/**
- * p9_create_tattach - allocates and creates a T_ATTACH request
- * @fid: handle to use for the new mount point
- * @afid: handle to use for authentication protocol
- * @uname: user name attempting to attach
- * @aname: mount specifier for remote server
- * @n_uname: numeric id for user attempting to attach
- * @n_uname: numeric id for user attempting to attach
- * @dotu: 9P2000.u extension flag
- *
- */
-
-struct p9_fcall *
-p9_create_tattach(u32 fid, u32 afid, char *uname, char *aname,
-	u32 n_uname, int dotu)
-{
-	int size;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	/* fid[4] afid[4] uname[s] aname[s] */
-	size = 4 + 4 + 2 + 2;
-	if (uname)
-		size += strlen(uname);
-
-	if (aname)
-		size += strlen(aname);
-
-	if (dotu)
-		size += 4;	/* n_uname */
-
-	fc = p9_create_common(bufp, size, P9_TATTACH);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, fid, &fc->params.tattach.fid);
-	p9_put_int32(bufp, afid, &fc->params.tattach.afid);
-	p9_put_str(bufp, uname, &fc->params.tattach.uname);
-	p9_put_str(bufp, aname, &fc->params.tattach.aname);
-	if (dotu)
-		p9_put_int32(bufp, n_uname, &fc->params.tattach.n_uname);
-
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_tattach);
-
-/**
- * p9_create_tflush - allocates and creates a T_FLUSH request
- * @oldtag: tag id for the transaction we are attempting to cancel
- *
- */
-
-struct p9_fcall *p9_create_tflush(u16 oldtag)
-{
-	int size;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	size = 2;		/* oldtag[2] */
-	fc = p9_create_common(bufp, size, P9_TFLUSH);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int16(bufp, oldtag, &fc->params.tflush.oldtag);
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_tflush);
-
-/**
- * p9_create_twalk - allocates and creates a T_FLUSH request
- * @fid: handle we are traversing from
- * @newfid: a new handle for this transaction
- * @nwname: number of path elements to traverse
- * @wnames: array of path elements
- *
- */
-
-struct p9_fcall *p9_create_twalk(u32 fid, u32 newfid, u16 nwname,
-				     char **wnames)
-{
-	int i, size;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	if (nwname > P9_MAXWELEM) {
-		P9_DPRINTK(P9_DEBUG_ERROR, "nwname > %d\n", P9_MAXWELEM);
-		return NULL;
-	}
-
-	size = 4 + 4 + 2;	/* fid[4] newfid[4] nwname[2] ... */
-	for (i = 0; i < nwname; i++) {
-		size += 2 + strlen(wnames[i]);	/* wname[s] */
-	}
-
-	fc = p9_create_common(bufp, size, P9_TWALK);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, fid, &fc->params.twalk.fid);
-	p9_put_int32(bufp, newfid, &fc->params.twalk.newfid);
-	p9_put_int16(bufp, nwname, &fc->params.twalk.nwname);
-	for (i = 0; i < nwname; i++) {
-		p9_put_str(bufp, wnames[i], &fc->params.twalk.wnames[i]);
-	}
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_twalk);
-
-/**
- * p9_create_topen - allocates and creates a T_OPEN request
- * @fid: handle we are trying to open
- * @mode: what mode we are trying to open the file in
- *
- */
-
-struct p9_fcall *p9_create_topen(u32 fid, u8 mode)
-{
-	int size;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	size = 4 + 1;		/* fid[4] mode[1] */
-	fc = p9_create_common(bufp, size, P9_TOPEN);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, fid, &fc->params.topen.fid);
-	p9_put_int8(bufp, mode, &fc->params.topen.mode);
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_topen);
-
-/**
- * p9_create_tcreate - allocates and creates a T_CREATE request
- * @fid: handle of directory we are trying to create in
- * @name: name of the file we are trying to create
- * @perm: permissions for the file we are trying to create
- * @mode: what mode we are trying to open the file in
- * @extension: 9p2000.u extension string (for special files)
- * @dotu: 9p2000.u enabled flag
- *
- * Note: Plan 9 create semantics include opening the resulting file
- * which is why mode is included.
- */
-
-struct p9_fcall *p9_create_tcreate(u32 fid, char *name, u32 perm, u8 mode,
-	char *extension, int dotu)
-{
-	int size;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	/* fid[4] name[s] perm[4] mode[1] */
-	size = 4 + 2 + strlen(name) + 4 + 1;
-	if (dotu) {
-		size += 2 +			/* extension[s] */
-		    (extension == NULL ? 0 : strlen(extension));
-	}
-
-	fc = p9_create_common(bufp, size, P9_TCREATE);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, fid, &fc->params.tcreate.fid);
-	p9_put_str(bufp, name, &fc->params.tcreate.name);
-	p9_put_int32(bufp, perm, &fc->params.tcreate.perm);
-	p9_put_int8(bufp, mode, &fc->params.tcreate.mode);
-	if (dotu)
-		p9_put_str(bufp, extension, &fc->params.tcreate.extension);
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_tcreate);
-
-/**
- * p9_create_tread - allocates and creates a T_READ request
- * @fid: handle of the file we are trying to read
- * @offset: offset to start reading from
- * @count: how many bytes to read
- */
-
-struct p9_fcall *p9_create_tread(u32 fid, u64 offset, u32 count)
-{
-	int size;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	size = 4 + 8 + 4;	/* fid[4] offset[8] count[4] */
-	fc = p9_create_common(bufp, size, P9_TREAD);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, fid, &fc->params.tread.fid);
-	p9_put_int64(bufp, offset, &fc->params.tread.offset);
-	p9_put_int32(bufp, count, &fc->params.tread.count);
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_tread);
-
-/**
- * p9_create_twrite - allocates and creates a T_WRITE request from the kernel
- * @fid: handle of the file we are trying to write
- * @offset: offset to start writing at
- * @count: how many bytes to write
- * @data: data to write
- *
- * This function will create a requst with data buffers from the kernel
- * such as the page cache.
- */
-
-struct p9_fcall *p9_create_twrite(u32 fid, u64 offset, u32 count,
-				      const char *data)
-{
-	int size, err;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	/* fid[4] offset[8] count[4] data[count] */
-	size = 4 + 8 + 4 + count;
-	fc = p9_create_common(bufp, size, P9_TWRITE);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, fid, &fc->params.twrite.fid);
-	p9_put_int64(bufp, offset, &fc->params.twrite.offset);
-	p9_put_int32(bufp, count, &fc->params.twrite.count);
-	err = p9_put_data(bufp, data, count, &fc->params.twrite.data);
-	if (err) {
-		kfree(fc);
-		fc = ERR_PTR(err);
-		goto error;
-	}
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_twrite);
-
-/**
- * p9_create_twrite_u - allocates and creates a T_WRITE request from userspace
- * @fid: handle of the file we are trying to write
- * @offset: offset to start writing at
- * @count: how many bytes to write
- * @data: data to write
- *
- * This function will create a request with data buffers from userspace
- */
-
-struct p9_fcall *p9_create_twrite_u(u32 fid, u64 offset, u32 count,
-				      const char __user *data)
-{
-	int size, err;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	/* fid[4] offset[8] count[4] data[count] */
-	size = 4 + 8 + 4 + count;
-	fc = p9_create_common(bufp, size, P9_TWRITE);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, fid, &fc->params.twrite.fid);
-	p9_put_int64(bufp, offset, &fc->params.twrite.offset);
-	p9_put_int32(bufp, count, &fc->params.twrite.count);
-	err = p9_put_user_data(bufp, data, count, &fc->params.twrite.data);
-	if (err) {
-		kfree(fc);
-		fc = ERR_PTR(err);
-		goto error;
-	}
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_twrite_u);
-
-/**
- * p9_create_tclunk - allocate a request to forget about a file handle
- * @fid: handle of the file we closing or forgetting about
- *
- * clunk is used both to close open files and to discard transient handles
- * which may be created during meta-data operations and hierarchy traversal.
- */
-
-struct p9_fcall *p9_create_tclunk(u32 fid)
-{
-	int size;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	size = 4;		/* fid[4] */
-	fc = p9_create_common(bufp, size, P9_TCLUNK);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, fid, &fc->params.tclunk.fid);
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_tclunk);
-
-/**
- * p9_create_tremove - allocate and create a request to remove a file
- * @fid: handle of the file or directory we are removing
- *
- */
-
-struct p9_fcall *p9_create_tremove(u32 fid)
-{
-	int size;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	size = 4;		/* fid[4] */
-	fc = p9_create_common(bufp, size, P9_TREMOVE);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, fid, &fc->params.tremove.fid);
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_tremove);
-
-/**
- * p9_create_tstat - allocate and populate a request for attributes
- * @fid: handle of the file or directory we are trying to get the attributes of
- *
- */
-
-struct p9_fcall *p9_create_tstat(u32 fid)
-{
-	int size;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	size = 4;		/* fid[4] */
-	fc = p9_create_common(bufp, size, P9_TSTAT);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, fid, &fc->params.tstat.fid);
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_tstat);
-
-/**
- * p9_create_tstat - allocate and populate a request to change attributes
- * @fid: handle of the file or directory we are trying to change
- * @wstat: &p9_stat structure with attributes we wish to set
- * @dotu: 9p2000.u enabled flag
- *
- */
-
-struct p9_fcall *p9_create_twstat(u32 fid, struct p9_wstat *wstat,
-				      int dotu)
-{
-	int size, statsz;
-	struct p9_fcall *fc;
-	struct cbuf buffer;
-	struct cbuf *bufp = &buffer;
-
-	statsz = p9_size_wstat(wstat, dotu);
-	size = 4 + 2 + 2 + statsz;	/* fid[4] stat[n] */
-	fc = p9_create_common(bufp, size, P9_TWSTAT);
-	if (IS_ERR(fc))
-		goto error;
-
-	p9_put_int32(bufp, fid, &fc->params.twstat.fid);
-	buf_put_int16(bufp, statsz + 2);
-	p9_put_wstat(bufp, wstat, &fc->params.twstat.stat, statsz, dotu);
-
-	if (buf_check_overflow(bufp)) {
-		kfree(fc);
-		fc = ERR_PTR(-ENOMEM);
-	}
-error:
-	return fc;
-}
-EXPORT_SYMBOL(p9_create_twstat);
-
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 4ebeffd21d3d..92cb60bb191b 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -509,6 +509,19 @@ p9pdu_writef(struct p9_fcall *pdu, int optional, const char *fmt, ...)
 	return ret;
 }
 
+int p9stat_read(char *buf, int len, struct p9_wstat *st, int dotu)
+{
+	struct p9_fcall fake_pdu;
+
+	fake_pdu.size = len;
+	fake_pdu.capacity = len;
+	fake_pdu.sdata = buf;
+	fake_pdu.offset = 0;
+
+	return p9pdu_readf(&fake_pdu, dotu, "S", st);
+}
+EXPORT_SYMBOL(p9stat_read);
+
 int p9pdu_prepare(struct p9_fcall *pdu, int16_t tag, int8_t type)
 {
 	return p9pdu_writef(pdu, 0, "dbw", 0, type, tag);
-- 
cgit v1.2.3


From fe11edfaabf1787c05d782a7b33e6497d1118b1d Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Fri, 17 Oct 2008 18:09:11 +0200
Subject: ide: IDE_AFLAG_MEDIA_CHANGED -> IDE_DFLAG_MEDIA_CHANGED

There should be no functional changes caused by this patch.

Acked-by: Borislav Petkov <petkovbb@gmail.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
---
 drivers/ide/ide-cd.c       | 6 +++---
 drivers/ide/ide-cd_ioctl.c | 4 ++--
 drivers/ide/ide-floppy.c   | 6 +++---
 include/linux/ide.h        | 4 ++--
 4 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 3308b1cd3a33..7dc1a17a4dd8 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -99,7 +99,7 @@ static void ide_cd_put(struct cdrom_info *cd)
 /* Mark that we've seen a media change and invalidate our internal buffers. */
 static void cdrom_saw_media_change(ide_drive_t *drive)
 {
-	drive->atapi_flags |= IDE_AFLAG_MEDIA_CHANGED;
+	drive->dev_flags |= IDE_DFLAG_MEDIA_CHANGED;
 	drive->atapi_flags &= ~IDE_AFLAG_TOC_VALID;
 }
 
@@ -1986,8 +1986,8 @@ static int ide_cdrom_setup(ide_drive_t *drive)
 	if (!drive->queue->unplug_delay)
 		drive->queue->unplug_delay = 1;
 
-	drive->atapi_flags = IDE_AFLAG_MEDIA_CHANGED | IDE_AFLAG_NO_EJECT |
-		       ide_cd_flags(id);
+	drive->dev_flags |= IDE_DFLAG_MEDIA_CHANGED;
+	drive->atapi_flags = IDE_AFLAG_NO_EJECT | ide_cd_flags(id);
 
 	if ((drive->atapi_flags & IDE_AFLAG_VERTOS_300_SSD) &&
 	    fw_rev[4] == '1' && fw_rev[6] <= '2')
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index 74231b41f611..37d89ead13dd 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -86,8 +86,8 @@ int ide_cdrom_check_media_change_real(struct cdrom_device_info *cdi,
 
 	if (slot_nr == CDSL_CURRENT) {
 		(void) cdrom_check_status(drive, NULL);
-		retval = (drive->atapi_flags & IDE_AFLAG_MEDIA_CHANGED) ? 1 : 0;
-		drive->atapi_flags &= ~IDE_AFLAG_MEDIA_CHANGED;
+		retval = (drive->dev_flags & IDE_DFLAG_MEDIA_CHANGED) ? 1 : 0;
+		drive->dev_flags &= ~IDE_DFLAG_MEDIA_CHANGED;
 		return retval;
 	} else {
 		return -EINVAL;
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index 3271e56d091c..df410c7191ac 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -689,8 +689,8 @@ static int idefloppy_open(struct inode *inode, struct file *filp)
 			goto out_put_floppy;
 		}
 
-		drive->atapi_flags |= IDE_AFLAG_MEDIA_CHANGED;
 		ide_set_media_lock(drive, disk, 1);
+		drive->dev_flags |= IDE_DFLAG_MEDIA_CHANGED;
 		check_disk_change(inode->i_bdev);
 	} else if (drive->atapi_flags & IDE_AFLAG_FORMAT_IN_PROGRESS) {
 		ret = -EBUSY;
@@ -747,8 +747,8 @@ static int idefloppy_media_changed(struct gendisk *disk)
 		drive->dev_flags &= ~IDE_DFLAG_ATTACH;
 		return 0;
 	}
-	ret = !!(drive->atapi_flags & IDE_AFLAG_MEDIA_CHANGED);
-	drive->atapi_flags &= ~IDE_AFLAG_MEDIA_CHANGED;
+	ret = !!(drive->dev_flags & IDE_DFLAG_MEDIA_CHANGED);
+	drive->dev_flags &= ~IDE_DFLAG_MEDIA_CHANGED;
 	return ret;
 }
 
diff --git a/include/linux/ide.h b/include/linux/ide.h
index c47e371554c1..155a57f55c60 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -464,7 +464,6 @@ struct ide_acpi_hwif_link;
 /* ATAPI device flags */
 enum {
 	IDE_AFLAG_DRQ_INTERRUPT		= (1 << 0),
-	IDE_AFLAG_MEDIA_CHANGED		= (1 << 1),
 	/* Drive cannot lock the door. */
 	IDE_AFLAG_NO_DOORLOCK		= (1 << 2),
 
@@ -578,7 +577,8 @@ enum {
 	/* don't unload heads */
 	IDE_DFLAG_NO_UNLOAD		= (1 << 27),
 	/* heads unloaded, please don't reset port */
-	IDE_DFLAG_PARKED		= (1 << 28)
+	IDE_DFLAG_PARKED		= (1 << 28),
+	IDE_DFLAG_MEDIA_CHANGED		= (1 << 29),
 };
 
 struct ide_drive_s {
-- 
cgit v1.2.3


From da167876bd0f71f1c646e5dd98997544d8d90e8e Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Fri, 17 Oct 2008 18:09:11 +0200
Subject: ide: IDE_AFLAG_WP -> IDE_DFLAG_WP

There should be no functional changes caused by this patch.

Acked-by: Borislav Petkov <petkovbb@gmail.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
---
 drivers/ide/ide-floppy.c | 8 ++++----
 include/linux/ide.h      | 4 ++--
 2 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index df410c7191ac..8078e0826cd3 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -410,11 +410,11 @@ static int ide_floppy_get_flexible_disk_page(ide_drive_t *drive)
 	}
 
 	if (pc.buf[3] & 0x80)
-		drive->atapi_flags |= IDE_AFLAG_WP;
+		drive->dev_flags |= IDE_DFLAG_WP;
 	else
-		drive->atapi_flags &= ~IDE_AFLAG_WP;
+		drive->dev_flags &= ~IDE_DFLAG_WP;
 
-	set_disk_ro(disk, !!(drive->atapi_flags & IDE_AFLAG_WP));
+	set_disk_ro(disk, !!(drive->dev_flags & IDE_DFLAG_WP));
 
 	page = &pc.buf[8];
 
@@ -684,7 +684,7 @@ static int idefloppy_open(struct inode *inode, struct file *filp)
 			goto out_put_floppy;
 		}
 
-		if ((drive->atapi_flags & IDE_AFLAG_WP) && (filp->f_mode & 2)) {
+		if ((drive->dev_flags & IDE_DFLAG_WP) && (filp->f_mode & 2)) {
 			ret = -EROFS;
 			goto out_put_floppy;
 		}
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 155a57f55c60..bd0a4d36b6d3 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -503,8 +503,6 @@ enum {
 	IDE_AFLAG_CLIK_DRIVE		= (1 << 19),
 	/* Requires BH algorithm for packets */
 	IDE_AFLAG_ZIP_DRIVE		= (1 << 20),
-	/* Write protect */
-	IDE_AFLAG_WP			= (1 << 21),
 	/* Supports format progress report */
 	IDE_AFLAG_SRFP			= (1 << 22),
 
@@ -579,6 +577,8 @@ enum {
 	/* heads unloaded, please don't reset port */
 	IDE_DFLAG_PARKED		= (1 << 28),
 	IDE_DFLAG_MEDIA_CHANGED		= (1 << 29),
+	/* write protect */
+	IDE_DFLAG_WP			= (1 << 30),
 };
 
 struct ide_drive_s {
-- 
cgit v1.2.3


From e01286282eef85e4783b06fb2e0ed84fc111eb32 Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Fri, 17 Oct 2008 18:09:11 +0200
Subject: ide: IDE_AFLAG_FORMAT_IN_PROGRESS -> IDE_DFLAG_FORMAT_IN_PROGRESS

There should be no functional changes caused by this patch.

Acked-by: Borislav Petkov <petkovbb@gmail.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
---
 drivers/ide/ide-floppy.c       | 6 +++---
 drivers/ide/ide-floppy_ioctl.c | 6 +++---
 include/linux/ide.h            | 3 +--
 3 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index 8078e0826cd3..2cf98b531fd9 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -664,7 +664,7 @@ static int idefloppy_open(struct inode *inode, struct file *filp)
 	floppy->openers++;
 
 	if (floppy->openers == 1) {
-		drive->atapi_flags &= ~IDE_AFLAG_FORMAT_IN_PROGRESS;
+		drive->dev_flags &= ~IDE_DFLAG_FORMAT_IN_PROGRESS;
 		/* Just in case */
 
 		if (ide_do_test_unit_ready(drive, disk))
@@ -692,7 +692,7 @@ static int idefloppy_open(struct inode *inode, struct file *filp)
 		ide_set_media_lock(drive, disk, 1);
 		drive->dev_flags |= IDE_DFLAG_MEDIA_CHANGED;
 		check_disk_change(inode->i_bdev);
-	} else if (drive->atapi_flags & IDE_AFLAG_FORMAT_IN_PROGRESS) {
+	} else if (drive->dev_flags & IDE_DFLAG_FORMAT_IN_PROGRESS) {
 		ret = -EBUSY;
 		goto out_put_floppy;
 	}
@@ -714,7 +714,7 @@ static int idefloppy_release(struct inode *inode, struct file *filp)
 
 	if (floppy->openers == 1) {
 		ide_set_media_lock(drive, disk, 0);
-		drive->atapi_flags &= ~IDE_AFLAG_FORMAT_IN_PROGRESS;
+		drive->dev_flags &= ~IDE_DFLAG_FORMAT_IN_PROGRESS;
 	}
 
 	floppy->openers--;
diff --git a/drivers/ide/ide-floppy_ioctl.c b/drivers/ide/ide-floppy_ioctl.c
index a3a7a0809e2b..b1f391df6cca 100644
--- a/drivers/ide/ide-floppy_ioctl.c
+++ b/drivers/ide/ide-floppy_ioctl.c
@@ -138,11 +138,11 @@ static int ide_floppy_format_unit(ide_drive_t *drive, int __user *arg)
 
 	if (floppy->openers > 1) {
 		/* Don't format if someone is using the disk */
-		drive->atapi_flags &= ~IDE_AFLAG_FORMAT_IN_PROGRESS;
+		drive->dev_flags &= ~IDE_DFLAG_FORMAT_IN_PROGRESS;
 		return -EBUSY;
 	}
 
-	drive->atapi_flags |= IDE_AFLAG_FORMAT_IN_PROGRESS;
+	drive->dev_flags |= IDE_DFLAG_FORMAT_IN_PROGRESS;
 
 	/*
 	 * Send ATAPI_FORMAT_UNIT to the drive.
@@ -174,7 +174,7 @@ static int ide_floppy_format_unit(ide_drive_t *drive, int __user *arg)
 
 out:
 	if (err)
-		drive->atapi_flags &= ~IDE_AFLAG_FORMAT_IN_PROGRESS;
+		drive->dev_flags &= ~IDE_DFLAG_FORMAT_IN_PROGRESS;
 	return err;
 }
 
diff --git a/include/linux/ide.h b/include/linux/ide.h
index bd0a4d36b6d3..d111c3ebbbae 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -497,8 +497,6 @@ enum {
 	IDE_AFLAG_LE_SPEED_FIELDS	= (1 << 17),
 
 	/* ide-floppy */
-	/* Format in progress */
-	IDE_AFLAG_FORMAT_IN_PROGRESS	= (1 << 18),
 	/* Avoid commands not supported in Clik drive */
 	IDE_AFLAG_CLIK_DRIVE		= (1 << 19),
 	/* Requires BH algorithm for packets */
@@ -579,6 +577,7 @@ enum {
 	IDE_DFLAG_MEDIA_CHANGED		= (1 << 29),
 	/* write protect */
 	IDE_DFLAG_WP			= (1 << 30),
+	IDE_DFLAG_FORMAT_IN_PROGRESS	= (1 << 31),
 };
 
 struct ide_drive_s {
-- 
cgit v1.2.3


From 42619d35c7af2f88cad56425fe3981f1f65ff0bd Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Fri, 17 Oct 2008 18:09:11 +0200
Subject: ide: remove IDE_AFLAG_NO_DOORLOCKING

Just use IDE_DFLAG_DOORLOCKING instead.

There should be no functional changes caused by this patch.

Acked-by: Borislav Petkov <petkovbb@gmail.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
---
 drivers/ide/ide-atapi.c    | 2 +-
 drivers/ide/ide-cd.c       | 2 +-
 drivers/ide/ide-cd_ioctl.c | 4 ++--
 drivers/ide/ide-floppy.c   | 2 +-
 drivers/ide/ide-probe.c    | 1 +
 drivers/ide/ide-tape.c     | 2 +-
 include/linux/ide.h        | 2 --
 7 files changed, 7 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-atapi.c b/drivers/ide/ide-atapi.c
index 2e305714c209..4e58b9e7a58a 100644
--- a/drivers/ide/ide-atapi.c
+++ b/drivers/ide/ide-atapi.c
@@ -191,7 +191,7 @@ int ide_set_media_lock(ide_drive_t *drive, struct gendisk *disk, int on)
 {
 	struct ide_atapi_pc pc;
 
-	if (drive->atapi_flags & IDE_AFLAG_NO_DOORLOCK)
+	if ((drive->dev_flags & IDE_DFLAG_DOORLOCKING) == 0)
 		return 0;
 
 	ide_init_pc(&pc);
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 7dc1a17a4dd8..2f4cc10391e5 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -1732,7 +1732,7 @@ static int ide_cdrom_probe_capabilities(ide_drive_t *drive)
 		return 0;
 
 	if ((buf[8 + 6] & 0x01) == 0)
-		drive->atapi_flags |= IDE_AFLAG_NO_DOORLOCK;
+		drive->dev_flags &= ~IDE_DFLAG_DOORLOCKING;
 	if (buf[8 + 6] & 0x08)
 		drive->atapi_flags &= ~IDE_AFLAG_NO_EJECT;
 	if (buf[8 + 3] & 0x01)
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index 37d89ead13dd..df3df0041eb6 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -136,7 +136,7 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 		sense = &my_sense;
 
 	/* If the drive cannot lock the door, just pretend. */
-	if (drive->atapi_flags & IDE_AFLAG_NO_DOORLOCK) {
+	if ((drive->dev_flags & IDE_DFLAG_DOORLOCKING) == 0) {
 		stat = 0;
 	} else {
 		unsigned char cmd[BLK_MAX_CDB];
@@ -157,7 +157,7 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 	    (sense->asc == 0x24 || sense->asc == 0x20)) {
 		printk(KERN_ERR "%s: door locking not supported\n",
 			drive->name);
-		drive->atapi_flags |= IDE_AFLAG_NO_DOORLOCK;
+		drive->dev_flags &= ~IDE_DFLAG_DOORLOCKING;
 		stat = 0;
 	}
 
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index 2cf98b531fd9..791a9d6f371c 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -592,7 +592,7 @@ static void idefloppy_setup(ide_drive_t *drive)
 		blk_queue_max_sectors(drive->queue, 64);
 		drive->atapi_flags |= IDE_AFLAG_CLIK_DRIVE;
 		/* IOMEGA Clik! drives do not support lock/unlock commands */
-		drive->atapi_flags |= IDE_AFLAG_NO_DOORLOCK;
+		drive->dev_flags &= ~IDE_DFLAG_DOORLOCKING;
 	}
 
 	(void) ide_floppy_get_capacity(drive);
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 19f8c7770a25..1649ea54f76c 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -208,6 +208,7 @@ static inline void do_identify (ide_drive_t *drive, u8 cmd)
 		drive->ready_stat = 0;
 		if (ata_id_cdb_intr(id))
 			drive->atapi_flags |= IDE_AFLAG_DRQ_INTERRUPT;
+		drive->dev_flags |= IDE_DFLAG_DOORLOCKING;
 		/* we don't do head unloading on ATAPI devices */
 		drive->dev_flags |= IDE_DFLAG_NO_UNLOAD;
 		return;
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index d879c7797cde..a99e28f45156 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -2108,7 +2108,7 @@ static void idetape_get_mode_sense_results(ide_drive_t *drive)
 
 	/* device lacks locking support according to capabilities page */
 	if ((caps[6] & 1) == 0)
-		drive->atapi_flags |= IDE_AFLAG_NO_DOORLOCK;
+		drive->dev_flags &= ~IDE_DFLAG_DOORLOCKING;
 
 	if (caps[7] & 0x02)
 		tape->blk_size = 512;
diff --git a/include/linux/ide.h b/include/linux/ide.h
index d111c3ebbbae..ba51a93fa547 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -464,8 +464,6 @@ struct ide_acpi_hwif_link;
 /* ATAPI device flags */
 enum {
 	IDE_AFLAG_DRQ_INTERRUPT		= (1 << 0),
-	/* Drive cannot lock the door. */
-	IDE_AFLAG_NO_DOORLOCK		= (1 << 2),
 
 	/* ide-cd */
 	/* Drive cannot eject the disc. */
-- 
cgit v1.2.3


From 79cb380397c834a35952d8497651d93b543ef968 Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Fri, 17 Oct 2008 18:09:13 +0200
Subject: ide: allow device drivers to specify per-device type /proc settings

Turn ide_driver_t's 'proc' field into ->proc_entries method
(and also 'settings' field into ->proc_devsets method).  Then
update all device drivers accordingly.

There should be no functional changes caused by this patch.

Acked-by: Borislav Petkov <petkovbb@gmail.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
---
 drivers/ide/ide-cd.c        | 14 ++++++++++++--
 drivers/ide/ide-gd-floppy.c | 16 ++++++++++++++--
 drivers/ide/ide-gd.c        | 16 ++++++++++++++--
 drivers/ide/ide-proc.c      |  6 +++---
 drivers/ide/ide-tape.c      | 14 ++++++++++++--
 drivers/scsi/ide-scsi.c     | 26 +++++++++++++++++---------
 include/linux/ide.h         |  4 ++--
 7 files changed, 74 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 2f4cc10391e5..32073666b9ca 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -1908,6 +1908,16 @@ static const struct ide_proc_devset idecd_settings[] = {
 	IDE_PROC_DEVSET(dsc_overlap, 0, 1),
 	{ 0 },
 };
+
+static ide_proc_entry_t *ide_cd_proc_entries(ide_drive_t *drive)
+{
+	return idecd_proc;
+}
+
+static const struct ide_proc_devset *ide_cd_proc_devsets(ide_drive_t *drive)
+{
+	return idecd_settings;
+}
 #endif
 
 static const struct cd_list_entry ide_cd_quirks_list[] = {
@@ -2069,8 +2079,8 @@ static ide_driver_t ide_cdrom_driver = {
 	.end_request		= ide_end_request,
 	.error			= __ide_error,
 #ifdef CONFIG_IDE_PROC_FS
-	.proc			= idecd_proc,
-	.settings		= idecd_settings,
+	.proc_entries		= ide_cd_proc_entries,
+	.proc_devsets		= ide_cd_proc_devsets,
 #endif
 };
 
diff --git a/drivers/ide/ide-gd-floppy.c b/drivers/ide/ide-gd-floppy.c
index 986253418794..082800b9a558 100644
--- a/drivers/ide/ide-gd-floppy.c
+++ b/drivers/ide/ide-gd-floppy.c
@@ -77,6 +77,18 @@ static void ide_disk_release(struct kref *kref)
 	kfree(idkp);
 }
 
+#ifdef CONFIG_IDE_PROC_FS
+static ide_proc_entry_t *ide_floppy_proc_entries(ide_drive_t *drive)
+{
+	return ide_floppy_proc;
+}
+
+static const struct ide_proc_devset *ide_floppy_proc_devsets(ide_drive_t *drive)
+{
+	return ide_floppy_settings;
+}
+#endif
+
 static ide_driver_t ide_gd_driver = {
 	.gen_driver = {
 		.owner		= THIS_MODULE,
@@ -90,8 +102,8 @@ static ide_driver_t ide_gd_driver = {
 	.end_request		= ide_floppy_end_request,
 	.error			= __ide_error,
 #ifdef CONFIG_IDE_PROC_FS
-	.proc			= ide_floppy_proc,
-	.settings		= ide_floppy_settings,
+	.proc_entries		= ide_floppy_proc_entries,
+	.proc_devsets		= ide_floppy_proc_devsets,
 #endif
 };
 
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index c08500270b9d..a3d4ad7db2af 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -119,6 +119,18 @@ static void ide_gd_shutdown(ide_drive_t *drive)
 	drive->gendev.bus->suspend(&drive->gendev, PMSG_SUSPEND);
 }
 
+#ifdef CONFIG_IDE_PROC_FS
+static ide_proc_entry_t *ide_disk_proc_entries(ide_drive_t *drive)
+{
+	return ide_disk_proc;
+}
+
+static const struct ide_proc_devset *ide_disk_proc_devsets(ide_drive_t *drive)
+{
+	return ide_disk_settings;
+}
+#endif
+
 static ide_driver_t ide_gd_driver = {
 	.gen_driver = {
 		.owner		= THIS_MODULE,
@@ -134,8 +146,8 @@ static ide_driver_t ide_gd_driver = {
 	.end_request		= ide_end_request,
 	.error			= __ide_error,
 #ifdef CONFIG_IDE_PROC_FS
-	.proc			= ide_disk_proc,
-	.settings		= ide_disk_settings,
+	.proc_entries		= ide_disk_proc_entries,
+	.proc_devsets		= ide_disk_proc_devsets,
 #endif
 };
 
diff --git a/drivers/ide/ide-proc.c b/drivers/ide/ide-proc.c
index b26926487cc0..c31d0dd7a532 100644
--- a/drivers/ide/ide-proc.c
+++ b/drivers/ide/ide-proc.c
@@ -567,10 +567,10 @@ static void ide_remove_proc_entries(struct proc_dir_entry *dir, ide_proc_entry_t
 void ide_proc_register_driver(ide_drive_t *drive, ide_driver_t *driver)
 {
 	mutex_lock(&ide_setting_mtx);
-	drive->settings = driver->settings;
+	drive->settings = driver->proc_devsets(drive);
 	mutex_unlock(&ide_setting_mtx);
 
-	ide_add_proc_entries(drive->proc, driver->proc, drive);
+	ide_add_proc_entries(drive->proc, driver->proc_entries(drive), drive);
 }
 
 EXPORT_SYMBOL(ide_proc_register_driver);
@@ -591,7 +591,7 @@ void ide_proc_unregister_driver(ide_drive_t *drive, ide_driver_t *driver)
 {
 	unsigned long flags;
 
-	ide_remove_proc_entries(drive->proc, driver->proc);
+	ide_remove_proc_entries(drive->proc, driver->proc_entries(drive));
 
 	mutex_lock(&ide_setting_mtx);
 	spin_lock_irqsave(&ide_lock, flags);
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index a99e28f45156..b2b2e5e8d38e 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -2298,6 +2298,16 @@ static ide_proc_entry_t idetape_proc[] = {
 	{ "name",	S_IFREG|S_IRUGO,	proc_idetape_read_name,	NULL },
 	{ NULL, 0, NULL, NULL }
 };
+
+static ide_proc_entry_t *ide_tape_proc_entries(ide_drive_t *drive)
+{
+	return idetape_proc;
+}
+
+static const struct ide_proc_devset *ide_tape_proc_devsets(ide_drive_t *drive)
+{
+	return idetape_settings;
+}
 #endif
 
 static int ide_tape_probe(ide_drive_t *);
@@ -2315,8 +2325,8 @@ static ide_driver_t idetape_driver = {
 	.end_request		= idetape_end_request,
 	.error			= __ide_error,
 #ifdef CONFIG_IDE_PROC_FS
-	.proc			= idetape_proc,
-	.settings		= idetape_settings,
+	.proc_entries		= ide_tape_proc_entries,
+	.proc_devsets		= ide_tape_proc_devsets,
 #endif
 };
 
diff --git a/drivers/scsi/ide-scsi.c b/drivers/scsi/ide-scsi.c
index 740bad435995..afc96e844a25 100644
--- a/drivers/scsi/ide-scsi.c
+++ b/drivers/scsi/ide-scsi.c
@@ -343,6 +343,11 @@ static ide_startstop_t idescsi_do_request (ide_drive_t *drive, struct request *r
 }
 
 #ifdef CONFIG_IDE_PROC_FS
+static ide_proc_entry_t idescsi_proc[] = {
+	{ "capacity", S_IFREG|S_IRUGO, proc_ide_read_capacity, NULL },
+	{ NULL, 0, NULL, NULL }
+};
+
 #define ide_scsi_devset_get(name, field) \
 static int get_##name(ide_drive_t *drive) \
 { \
@@ -378,6 +383,16 @@ static const struct ide_proc_devset idescsi_settings[] = {
 	IDE_PROC_DEVSET(transform, 0,	 3),
 	{ 0 },
 };
+
+static ide_proc_entry_t *ide_scsi_proc_entries(ide_drive_t *drive)
+{
+	return idescsi_proc;
+}
+
+static const struct ide_proc_devset *ide_scsi_proc_devsets(ide_drive_t *drive)
+{
+	return idescsi_settings;
+}
 #endif
 
 /*
@@ -419,13 +434,6 @@ static void ide_scsi_remove(ide_drive_t *drive)
 
 static int ide_scsi_probe(ide_drive_t *);
 
-#ifdef CONFIG_IDE_PROC_FS
-static ide_proc_entry_t idescsi_proc[] = {
-	{ "capacity", S_IFREG|S_IRUGO, proc_ide_read_capacity, NULL },
-	{ NULL, 0, NULL, NULL }
-};
-#endif
-
 static ide_driver_t idescsi_driver = {
 	.gen_driver = {
 		.owner		= THIS_MODULE,
@@ -439,8 +447,8 @@ static ide_driver_t idescsi_driver = {
 	.end_request		= idescsi_end_request,
 	.error                  = idescsi_atapi_error,
 #ifdef CONFIG_IDE_PROC_FS
-	.proc			= idescsi_proc,
-	.settings		= idescsi_settings,
+	.proc_entries		= ide_scsi_proc_entries,
+	.proc_devsets		= ide_scsi_proc_devsets,
 #endif
 };
 
diff --git a/include/linux/ide.h b/include/linux/ide.h
index ba51a93fa547..488808891acb 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -1120,8 +1120,8 @@ struct ide_driver_s {
 	void		(*resume)(ide_drive_t *);
 	void		(*shutdown)(ide_drive_t *);
 #ifdef CONFIG_IDE_PROC_FS
-	ide_proc_entry_t		*proc;
-	const struct ide_proc_devset	*settings;
+	ide_proc_entry_t *		(*proc_entries)(ide_drive_t *);
+	const struct ide_proc_devset *	(*proc_devsets)(ide_drive_t *);
 #endif
 };
 
-- 
cgit v1.2.3


From 806f80a6fc203ad0bde84e5a9e94572617d2ae45 Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Fri, 17 Oct 2008 18:09:14 +0200
Subject: ide: add generic ATA/ATAPI disk driver

* Add struct ide_disk_ops containing protocol specific methods.

* Add 'struct ide_disk_ops *' to ide_drive_t.

* Convert ide-{disk,floppy} drivers to use struct ide_disk_ops.

* Merge ide-{disk,floppy} drivers into generic ide-gd driver.

While at it:
- ide_disk_init_capacity() -> ide_disk_get_capacity()

Acked-by: Borislav Petkov <petkovbb@gmail.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
---
 drivers/ide/Kconfig            |  64 ++++-----
 drivers/ide/Makefile           |  19 ++-
 drivers/ide/ide-disk.c         |  39 +++++-
 drivers/ide/ide-disk.h         |  24 ++--
 drivers/ide/ide-disk_ioctl.c   |   4 +-
 drivers/ide/ide-floppy.c       |  45 ++++--
 drivers/ide/ide-floppy.h       |  58 ++------
 drivers/ide/ide-floppy_ioctl.c |   9 +-
 drivers/ide/ide-gd-floppy.c    | 309 -----------------------------------------
 drivers/ide/ide-gd.c           | 122 +++++++++++++---
 drivers/ide/ide-gd.h           |  44 ++++++
 drivers/leds/Kconfig           |   2 +-
 include/linux/ide.h            |  19 +++
 13 files changed, 303 insertions(+), 455 deletions(-)
 delete mode 100644 drivers/ide/ide-gd-floppy.c
 create mode 100644 drivers/ide/ide-gd.h

(limited to 'include')

diff --git a/drivers/ide/Kconfig b/drivers/ide/Kconfig
index 74a369a6116f..faa974e615da 100644
--- a/drivers/ide/Kconfig
+++ b/drivers/ide/Kconfig
@@ -84,21 +84,40 @@ config BLK_DEV_IDE_SATA
 
 	  If unsure, say N.
 
-config BLK_DEV_IDEDISK
-	tristate "Include IDE/ATA-2 DISK support"
-	---help---
-	  This will include enhanced support for MFM/RLL/IDE hard disks.  If
-	  you have a MFM/RLL/IDE disk, and there is no special reason to use
-	  the old hard disk driver instead, say Y.  If you have an SCSI-only
-	  system, you can say N here.
+config IDE_GD
+	tristate "generic ATA/ATAPI disk support"
+	default y
+	help
+	  Support for ATA/ATAPI disks (including ATAPI floppy drives).
 
-	  To compile this driver as a module, choose M here: the
-	  module will be called ide-disk.
-	  Do not compile this driver as a module if your root file system
-	  (the one containing the directory /) is located on the IDE disk.
+	  To compile this driver as a module, choose M here.
+	  The module will be called ide-gd_mod.
 
 	  If unsure, say Y.
 
+config IDE_GD_ATA
+	bool "ATA disk support"
+	depends on IDE_GD
+	default y
+	help
+	  This will include support for ATA hard disks.
+
+	  If unsure, say Y.
+
+config IDE_GD_ATAPI
+	bool "ATAPI floppy support"
+	depends on IDE_GD
+	select IDE_ATAPI
+	help
+	  This will include support for ATAPI floppy drives
+	  (i.e. Iomega ZIP or MKE LS-120).
+
+	  For information about jumper settings and the question
+	  of when a ZIP drive uses a partition table, see
+	  <http://www.win.tue.nl/~aeb/linux/zip/zip-1.html>.
+
+	  If unsure, say N.
+
 config BLK_DEV_IDECS
 	tristate "PCMCIA IDE support"
 	depends on PCMCIA
@@ -163,29 +182,6 @@ config BLK_DEV_IDETAPE
 	  To compile this driver as a module, choose M here: the
 	  module will be called ide-tape.
 
-config BLK_DEV_IDEFLOPPY
-	tristate "Include IDE/ATAPI FLOPPY support"
-	select IDE_ATAPI
-	---help---
-	  If you have an IDE floppy drive which uses the ATAPI protocol,
-	  answer Y.  ATAPI is a newer protocol used by IDE CD-ROM/tape/floppy
-	  drives, similar to the SCSI protocol.
-
-	  The LS-120 and the IDE/ATAPI Iomega ZIP drive are also supported by
-	  this driver. For information about jumper settings and the question
-	  of when a ZIP drive uses a partition table, see
-	  <http://www.win.tue.nl/~aeb/linux/zip/zip-1.html>.
-	  (ATAPI PD-CD/CDR drives are not supported by this driver; support
-	  for PD-CD/CDR drives is available if you answer Y to
-	  "SCSI emulation support", below).
-
-	  If you say Y here, the FLOPPY drive will be identified along with
-	  other IDE devices, as "hdb" or "hdc", or something similar (check
-	  the boot messages with dmesg).
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called ide-floppy.
-
 config BLK_DEV_IDESCSI
 	tristate "SCSI emulation support (DEPRECATED)"
 	depends on SCSI
diff --git a/drivers/ide/Makefile b/drivers/ide/Makefile
index 7eeeab597959..093d3248ca89 100644
--- a/drivers/ide/Makefile
+++ b/drivers/ide/Makefile
@@ -37,18 +37,25 @@ obj-$(CONFIG_IDE_H8300)			+= h8300/
 obj-$(CONFIG_IDE_GENERIC)		+= ide-generic.o
 obj-$(CONFIG_BLK_DEV_IDEPNP)		+= ide-pnp.o
 
-ide-disk_mod-y += ide-gd.o ide-disk.o ide-disk_ioctl.o
+ide-gd_mod-y += ide-gd.o
 ide-cd_mod-y += ide-cd.o ide-cd_ioctl.o ide-cd_verbose.o
-ide-floppy_mod-y += ide-gd-floppy.o ide-floppy.o ide-floppy_ioctl.o
 
+ifeq ($(CONFIG_IDE_GD_ATA), y)
+	ide-gd_mod-y += ide-disk.o ide-disk_ioctl.o
 ifeq ($(CONFIG_IDE_PROC_FS), y)
-	ide-disk_mod-y += ide-disk_proc.o
-	ide-floppy_mod-y += ide-floppy_proc.o
+	ide-gd_mod-y += ide-disk_proc.o
+endif
+endif
+
+ifeq ($(CONFIG_IDE_GD_ATAPI), y)
+	ide-gd_mod-y += ide-floppy.o ide-floppy_ioctl.o
+ifeq ($(CONFIG_IDE_PROC_FS), y)
+	ide-gd_mod-y += ide-floppy_proc.o
+endif
 endif
 
-obj-$(CONFIG_BLK_DEV_IDEDISK)		+= ide-disk_mod.o
+obj-$(CONFIG_IDE_GD)			+= ide-gd_mod.o
 obj-$(CONFIG_BLK_DEV_IDECD)		+= ide-cd_mod.o
-obj-$(CONFIG_BLK_DEV_IDEFLOPPY)		+= ide-floppy_mod.o
 obj-$(CONFIG_BLK_DEV_IDETAPE)		+= ide-tape.o
 
 ifeq ($(CONFIG_BLK_DEV_IDECS), y)
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 751be7af22c2..223750c1b5a6 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -184,8 +184,8 @@ static ide_startstop_t __ide_do_rw_disk(ide_drive_t *drive, struct request *rq,
  * 1073741822 == 549756 MB or 48bit addressing fake drive
  */
 
-ide_startstop_t ide_do_rw_disk(ide_drive_t *drive, struct request *rq,
-			       sector_t block)
+static ide_startstop_t ide_do_rw_disk(ide_drive_t *drive, struct request *rq,
+				      sector_t block)
 {
 	ide_hwif_t *hwif = HWIF(drive);
 
@@ -333,7 +333,7 @@ static void idedisk_check_hpa(ide_drive_t *drive)
 	}
 }
 
-void ide_disk_init_capacity(ide_drive_t *drive)
+static int ide_disk_get_capacity(ide_drive_t *drive)
 {
 	u16 *id = drive->id;
 	int lba;
@@ -382,6 +382,8 @@ void ide_disk_init_capacity(ide_drive_t *drive)
 		} else
 			drive->dev_flags &= ~IDE_DFLAG_LBA48;
 	}
+
+	return 0;
 }
 
 static void idedisk_prepare_flush(struct request_queue *q, struct request *rq)
@@ -590,7 +592,12 @@ ide_ext_devset_rw(wcache, wcache);
 
 ide_ext_devset_rw_sync(nowerr, nowerr);
 
-void ide_disk_setup(ide_drive_t *drive)
+static int ide_disk_check(ide_drive_t *drive, const char *s)
+{
+	return 1;
+}
+
+static void ide_disk_setup(ide_drive_t *drive)
 {
 	struct ide_disk_obj *idkp = drive->driver_data;
 	ide_hwif_t *hwif = drive->hwif;
@@ -626,7 +633,7 @@ void ide_disk_setup(ide_drive_t *drive)
 			 drive->queue->max_sectors / 2);
 
 	/* calculate drive capacity, and select LBA if possible */
-	ide_disk_init_capacity(drive);
+	ide_disk_get_capacity(drive);
 
 	/*
 	 * if possible, give fdisk access to more of the drive,
@@ -682,7 +689,7 @@ void ide_disk_setup(ide_drive_t *drive)
 		drive->dev_flags |= IDE_DFLAG_ATTACH;
 }
 
-void ide_disk_flush(ide_drive_t *drive)
+static void ide_disk_flush(ide_drive_t *drive)
 {
 	if (ata_id_flush_enabled(drive->id) == 0 ||
 	    (drive->dev_flags & IDE_DFLAG_WCACHE) == 0)
@@ -692,7 +699,13 @@ void ide_disk_flush(ide_drive_t *drive)
 		printk(KERN_INFO "%s: wcache flush failed!\n", drive->name);
 }
 
-int ide_disk_set_doorlock(ide_drive_t *drive, int on)
+static int ide_disk_init_media(ide_drive_t *drive, struct gendisk *disk)
+{
+	return 0;
+}
+
+static int ide_disk_set_doorlock(ide_drive_t *drive, struct gendisk *disk,
+				 int on)
 {
 	ide_task_t task;
 	int ret;
@@ -711,3 +724,15 @@ int ide_disk_set_doorlock(ide_drive_t *drive, int on)
 
 	return ret;
 }
+
+const struct ide_disk_ops ide_ata_disk_ops = {
+	.check		= ide_disk_check,
+	.get_capacity	= ide_disk_get_capacity,
+	.setup		= ide_disk_setup,
+	.flush		= ide_disk_flush,
+	.init_media	= ide_disk_init_media,
+	.set_doorlock	= ide_disk_set_doorlock,
+	.do_request	= ide_do_rw_disk,
+	.end_request	= ide_end_request,
+	.ioctl		= ide_disk_ioctl,
+};
diff --git a/drivers/ide/ide-disk.h b/drivers/ide/ide-disk.h
index 104ad71288a5..b234b0feaf7b 100644
--- a/drivers/ide/ide-disk.h
+++ b/drivers/ide/ide-disk.h
@@ -1,22 +1,11 @@
 #ifndef __IDE_DISK_H
 #define __IDE_DISK_H
 
-struct ide_disk_obj {
-	ide_drive_t	*drive;
-	ide_driver_t	*driver;
-	struct gendisk	*disk;
-	struct kref	kref;
-	unsigned int	openers;	/* protected by BKL for now */
-};
-
-sector_t ide_gd_capacity(ide_drive_t *);
+#include "ide-gd.h"
 
+#ifdef CONFIG_IDE_GD_ATA
 /* ide-disk.c */
-void ide_disk_init_capacity(ide_drive_t *);
-void ide_disk_setup(ide_drive_t *);
-void ide_disk_flush(ide_drive_t *);
-int ide_disk_set_doorlock(ide_drive_t *, int);
-ide_startstop_t ide_do_rw_disk(ide_drive_t *, struct request *, sector_t);
+extern const struct ide_disk_ops ide_ata_disk_ops;
 ide_decl_devset(address);
 ide_decl_devset(multcount);
 ide_decl_devset(nowerr);
@@ -24,12 +13,17 @@ ide_decl_devset(wcache);
 ide_decl_devset(acoustic);
 
 /* ide-disk_ioctl.c */
-int ide_disk_ioctl(struct inode *, struct file *, unsigned int, unsigned long);
+int ide_disk_ioctl(ide_drive_t *, struct inode *, struct file *, unsigned int,
+		   unsigned long);
 
 #ifdef CONFIG_IDE_PROC_FS
 /* ide-disk_proc.c */
 extern ide_proc_entry_t ide_disk_proc[];
 extern const struct ide_proc_devset ide_disk_settings[];
 #endif
+#else
+#define ide_disk_proc		NULL
+#define ide_disk_settings	NULL
+#endif
 
 #endif /* __IDE_DISK_H */
diff --git a/drivers/ide/ide-disk_ioctl.c b/drivers/ide/ide-disk_ioctl.c
index e6624eda9e69..a49698bcf966 100644
--- a/drivers/ide/ide-disk_ioctl.c
+++ b/drivers/ide/ide-disk_ioctl.c
@@ -13,12 +13,10 @@ static const struct ide_ioctl_devset ide_disk_ioctl_settings[] = {
 { 0 }
 };
 
-int ide_disk_ioctl(struct inode *inode, struct file *file,
+int ide_disk_ioctl(ide_drive_t *drive, struct inode *inode, struct file *file,
 		   unsigned int cmd, unsigned long arg)
 {
 	struct block_device *bdev = inode->i_bdev;
-	struct ide_disk_obj *idkp = ide_drv_g(bdev->bd_disk, ide_disk_obj);
-	ide_drive_t *drive = idkp->drive;
 	int err;
 
 	err = ide_setting_ioctl(drive, bdev, cmd, arg, ide_disk_ioctl_settings);
diff --git a/drivers/ide/ide-floppy.c b/drivers/ide/ide-floppy.c
index 802e0968e32f..58746c748c12 100644
--- a/drivers/ide/ide-floppy.c
+++ b/drivers/ide/ide-floppy.c
@@ -68,7 +68,7 @@
  * Used to finish servicing a request. For read/write requests, we will call
  * ide_end_request to pass to the next buffer.
  */
-int ide_floppy_end_request(ide_drive_t *drive, int uptodate, int nsecs)
+static int ide_floppy_end_request(ide_drive_t *drive, int uptodate, int nsecs)
 {
 	idefloppy_floppy_t *floppy = drive->driver_data;
 	struct request *rq = HWGROUP(drive)->rq;
@@ -280,13 +280,12 @@ static void idefloppy_blockpc_cmd(idefloppy_floppy_t *floppy,
 	pc->req_xfer = pc->buf_size = rq->data_len;
 }
 
-ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, struct request *rq,
-				      sector_t block_s)
+static ide_startstop_t ide_floppy_do_request(ide_drive_t *drive,
+					     struct request *rq, sector_t block)
 {
 	idefloppy_floppy_t *floppy = drive->driver_data;
 	ide_hwif_t *hwif = drive->hwif;
 	struct ide_atapi_pc *pc;
-	unsigned long block = (unsigned long)block_s;
 
 	ide_debug_log(IDE_DBG_FUNC, "%s: dev: %s, cmd: 0x%x, cmd_type: %x, "
 		      "errors: %d\n",
@@ -316,7 +315,7 @@ ide_startstop_t ide_floppy_do_request(ide_drive_t *drive, struct request *rq,
 			return ide_stopped;
 		}
 		pc = &floppy->queued_pc;
-		idefloppy_create_rw_cmd(drive, pc, rq, block);
+		idefloppy_create_rw_cmd(drive, pc, rq, (unsigned long)block);
 	} else if (blk_special_request(rq)) {
 		pc = (struct ide_atapi_pc *) rq->buffer;
 	} else if (blk_pc_request(rq)) {
@@ -406,7 +405,7 @@ static int ide_floppy_get_flexible_disk_page(ide_drive_t *drive)
  * Determine if a media is present in the floppy drive, and if so, its LBA
  * capacity.
  */
-int ide_floppy_get_capacity(ide_drive_t *drive)
+static int ide_floppy_get_capacity(ide_drive_t *drive)
 {
 	idefloppy_floppy_t *floppy = drive->driver_data;
 	struct gendisk *disk = floppy->disk;
@@ -505,9 +504,9 @@ int ide_floppy_get_capacity(ide_drive_t *drive)
 	return rc;
 }
 
-void ide_floppy_setup(ide_drive_t *drive)
+static void ide_floppy_setup(ide_drive_t *drive)
 {
-	struct ide_floppy_obj *floppy = drive->driver_data;
+	struct ide_disk_obj *floppy = drive->driver_data;
 	u16 *id = drive->id;
 
 	drive->pc_callback	 = ide_floppy_callback;
@@ -547,3 +546,33 @@ void ide_floppy_setup(ide_drive_t *drive)
 
 	drive->dev_flags |= IDE_DFLAG_ATTACH;
 }
+
+static void ide_floppy_flush(ide_drive_t *drive)
+{
+}
+
+static int ide_floppy_init_media(ide_drive_t *drive, struct gendisk *disk)
+{
+	int ret = 0;
+
+	if (ide_do_test_unit_ready(drive, disk))
+		ide_do_start_stop(drive, disk, 1);
+
+	ret = ide_floppy_get_capacity(drive);
+
+	set_capacity(disk, ide_gd_capacity(drive));
+
+	return ret;
+}
+
+const struct ide_disk_ops ide_atapi_disk_ops = {
+	.check		= ide_check_atapi_device,
+	.get_capacity	= ide_floppy_get_capacity,
+	.setup		= ide_floppy_setup,
+	.flush		= ide_floppy_flush,
+	.init_media	= ide_floppy_init_media,
+	.set_doorlock	= ide_set_media_lock,
+	.do_request	= ide_floppy_do_request,
+	.end_request	= ide_floppy_end_request,
+	.ioctl		= ide_floppy_ioctl,
+};
diff --git a/drivers/ide/ide-floppy.h b/drivers/ide/ide-floppy.h
index b965da2f41ce..acebc8c5a827 100644
--- a/drivers/ide/ide-floppy.h
+++ b/drivers/ide/ide-floppy.h
@@ -1,48 +1,10 @@
 #ifndef __IDE_FLOPPY_H
 #define __IDE_FLOPPY_H
 
-#define DRV_NAME "ide-floppy"
-#define PFX DRV_NAME ": "
+#include "ide-gd.h"
 
-/* define to see debug info */
-#define IDEFLOPPY_DEBUG_LOG	0
-
-#if IDEFLOPPY_DEBUG_LOG
-#define ide_debug_log(lvl, fmt, args...) __ide_debug_log(lvl, fmt, args)
-#else
-#define ide_debug_log(lvl, fmt, args...) do {} while (0)
-#endif
-
-/*
- * Most of our global data which we need to save even as we leave the driver
- * due to an interrupt or a timer event is stored in a variable of type
- * idefloppy_floppy_t, defined below.
- */
-typedef struct ide_floppy_obj {
-	ide_drive_t	*drive;
-	ide_driver_t	*driver;
-	struct gendisk	*disk;
-	struct kref	kref;
-	unsigned int	openers;	/* protected by BKL for now */
-
-	/* Last failed packet command */
-	struct ide_atapi_pc *failed_pc;
-	/* used for blk_{fs,pc}_request() requests */
-	struct ide_atapi_pc queued_pc;
-
-	/* Last error information */
-	u8 sense_key, asc, ascq;
-
-	int progress_indication;
-
-	/* Device information */
-	/* Current format */
-	int blocks, block_size, bs_factor;
-	/* Last format capacity descriptor */
-	u8 cap_desc[8];
-	/* Copy of the flexible disk page */
-	u8 flexible_disk_page[32];
-} idefloppy_floppy_t;
+#ifdef CONFIG_IDE_GD_ATAPI
+typedef struct ide_disk_obj idefloppy_floppy_t;
 
 /*
  * Pages of the SELECT SENSE / MODE SENSE packet commands.
@@ -57,23 +19,23 @@ typedef struct ide_floppy_obj {
 #define	IDEFLOPPY_IOCTL_FORMAT_START		0x4602
 #define IDEFLOPPY_IOCTL_FORMAT_GET_PROGRESS	0x4603
 
-sector_t ide_gd_capacity(ide_drive_t *);
-
 /* ide-floppy.c */
+extern const struct ide_disk_ops ide_atapi_disk_ops;
 void ide_floppy_create_mode_sense_cmd(struct ide_atapi_pc *, u8);
 void ide_floppy_create_read_capacity_cmd(struct ide_atapi_pc *);
-int ide_floppy_get_capacity(ide_drive_t *);
-void ide_floppy_setup(ide_drive_t *);
-ide_startstop_t ide_floppy_do_request(ide_drive_t *, struct request *, sector_t);
-int ide_floppy_end_request(ide_drive_t *, int, int);
 
 /* ide-floppy_ioctl.c */
-int ide_floppy_ioctl(struct inode *, struct file *, unsigned, unsigned long);
+int ide_floppy_ioctl(ide_drive_t *, struct inode *, struct file *, unsigned int,
+		     unsigned long);
 
 #ifdef CONFIG_IDE_PROC_FS
 /* ide-floppy_proc.c */
 extern ide_proc_entry_t ide_floppy_proc[];
 extern const struct ide_proc_devset ide_floppy_settings[];
 #endif
+#else
+#define ide_floppy_proc		NULL
+#define ide_floppy_settings	NULL
+#endif
 
 #endif /*__IDE_FLOPPY_H */
diff --git a/drivers/ide/ide-floppy_ioctl.c b/drivers/ide/ide-floppy_ioctl.c
index b1f391df6cca..e8aa0a5bf5dc 100644
--- a/drivers/ide/ide-floppy_ioctl.c
+++ b/drivers/ide/ide-floppy_ioctl.c
@@ -33,7 +33,7 @@
 
 static int ide_floppy_get_format_capacities(ide_drive_t *drive, int __user *arg)
 {
-	struct ide_floppy_obj *floppy = drive->driver_data;
+	struct ide_disk_obj *floppy = drive->driver_data;
 	struct ide_atapi_pc pc;
 	u8 header_len, desc_cnt;
 	int i, blocks, length, u_array_size, u_index;
@@ -260,13 +260,10 @@ static int ide_floppy_format_ioctl(ide_drive_t *drive, struct file *file,
 	}
 }
 
-int ide_floppy_ioctl(struct inode *inode, struct file *file,
-		    unsigned int cmd, unsigned long arg)
+int ide_floppy_ioctl(ide_drive_t *drive, struct inode *inode,
+		     struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct block_device *bdev = inode->i_bdev;
-	struct ide_floppy_obj *floppy = ide_drv_g(bdev->bd_disk,
-						     ide_floppy_obj);
-	ide_drive_t *drive = floppy->drive;
 	struct ide_atapi_pc pc;
 	void __user *argp = (void __user *)arg;
 	int err;
diff --git a/drivers/ide/ide-gd-floppy.c b/drivers/ide/ide-gd-floppy.c
deleted file mode 100644
index 082800b9a558..000000000000
--- a/drivers/ide/ide-gd-floppy.c
+++ /dev/null
@@ -1,309 +0,0 @@
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/genhd.h>
-#include <linux/mutex.h>
-#include <linux/ide.h>
-#include <linux/hdreg.h>
-
-#include "ide-floppy.h"
-
-#define IDEFLOPPY_VERSION "1.00"
-
-/* module parameters */
-static unsigned long debug_mask;
-module_param(debug_mask, ulong, 0644);
-
-static DEFINE_MUTEX(ide_disk_ref_mutex);
-
-static void ide_disk_release(struct kref *);
-
-static struct ide_floppy_obj *ide_disk_get(struct gendisk *disk)
-{
-	struct ide_floppy_obj *idkp = NULL;
-
-	mutex_lock(&ide_disk_ref_mutex);
-	idkp = ide_drv_g(disk, ide_floppy_obj);
-	if (idkp) {
-		if (ide_device_get(idkp->drive))
-			idkp = NULL;
-		else
-			kref_get(&idkp->kref);
-	}
-	mutex_unlock(&ide_disk_ref_mutex);
-	return idkp;
-}
-
-static void ide_disk_put(struct ide_floppy_obj *idkp)
-{
-	ide_drive_t *drive = idkp->drive;
-
-	mutex_lock(&ide_disk_ref_mutex);
-	kref_put(&idkp->kref, ide_disk_release);
-	ide_device_put(drive);
-	mutex_unlock(&ide_disk_ref_mutex);
-}
-
-sector_t ide_gd_capacity(ide_drive_t *drive)
-{
-	return drive->capacity64;
-}
-
-static int ide_gd_probe(ide_drive_t *);
-
-static void ide_gd_remove(ide_drive_t *drive)
-{
-	struct ide_floppy_obj *idkp = drive->driver_data;
-	struct gendisk *g = idkp->disk;
-
-	ide_proc_unregister_driver(drive, idkp->driver);
-
-	del_gendisk(g);
-
-	ide_disk_put(idkp);
-}
-
-static void ide_disk_release(struct kref *kref)
-{
-	struct ide_floppy_obj *idkp = to_ide_drv(kref, ide_floppy_obj);
-	ide_drive_t *drive = idkp->drive;
-	struct gendisk *g = idkp->disk;
-
-	drive->driver_data = NULL;
-	g->private_data = NULL;
-	put_disk(g);
-	kfree(idkp);
-}
-
-#ifdef CONFIG_IDE_PROC_FS
-static ide_proc_entry_t *ide_floppy_proc_entries(ide_drive_t *drive)
-{
-	return ide_floppy_proc;
-}
-
-static const struct ide_proc_devset *ide_floppy_proc_devsets(ide_drive_t *drive)
-{
-	return ide_floppy_settings;
-}
-#endif
-
-static ide_driver_t ide_gd_driver = {
-	.gen_driver = {
-		.owner		= THIS_MODULE,
-		.name		= "ide-floppy",
-		.bus		= &ide_bus_type,
-	},
-	.probe			= ide_gd_probe,
-	.remove			= ide_gd_remove,
-	.version		= IDEFLOPPY_VERSION,
-	.do_request		= ide_floppy_do_request,
-	.end_request		= ide_floppy_end_request,
-	.error			= __ide_error,
-#ifdef CONFIG_IDE_PROC_FS
-	.proc_entries		= ide_floppy_proc_entries,
-	.proc_devsets		= ide_floppy_proc_devsets,
-#endif
-};
-
-static int ide_gd_open(struct inode *inode, struct file *filp)
-{
-	struct gendisk *disk = inode->i_bdev->bd_disk;
-	struct ide_floppy_obj *idkp;
-	ide_drive_t *drive;
-	int ret = 0;
-
-	idkp = ide_disk_get(disk);
-	if (idkp == NULL)
-		return -ENXIO;
-
-	drive = idkp->drive;
-
-	ide_debug_log(IDE_DBG_FUNC, "Call %s\n", __func__);
-
-	idkp->openers++;
-
-	if (idkp->openers == 1) {
-		drive->dev_flags &= ~IDE_DFLAG_FORMAT_IN_PROGRESS;
-		/* Just in case */
-
-		if (ide_do_test_unit_ready(drive, disk))
-			ide_do_start_stop(drive, disk, 1);
-
-		ret = ide_floppy_get_capacity(drive);
-
-		set_capacity(disk, ide_gd_capacity(drive));
-
-		if (ret && (filp->f_flags & O_NDELAY) == 0) {
-		    /*
-		     * Allow O_NDELAY to open a drive without a disk, or with an
-		     * unreadable disk, so that we can get the format capacity
-		     * of the drive or begin the format - Sam
-		     */
-			ret = -EIO;
-			goto out_put_idkp;
-		}
-
-		if ((drive->dev_flags & IDE_DFLAG_WP) && (filp->f_mode & 2)) {
-			ret = -EROFS;
-			goto out_put_idkp;
-		}
-
-		ide_set_media_lock(drive, disk, 1);
-		drive->dev_flags |= IDE_DFLAG_MEDIA_CHANGED;
-		check_disk_change(inode->i_bdev);
-	} else if (drive->dev_flags & IDE_DFLAG_FORMAT_IN_PROGRESS) {
-		ret = -EBUSY;
-		goto out_put_idkp;
-	}
-	return 0;
-
-out_put_idkp:
-	idkp->openers--;
-	ide_disk_put(idkp);
-	return ret;
-}
-
-static int ide_gd_release(struct inode *inode, struct file *filp)
-{
-	struct gendisk *disk = inode->i_bdev->bd_disk;
-	struct ide_floppy_obj *idkp = ide_drv_g(disk, ide_floppy_obj);
-	ide_drive_t *drive = idkp->drive;
-
-	ide_debug_log(IDE_DBG_FUNC, "Call %s\n", __func__);
-
-	if (idkp->openers == 1) {
-		ide_set_media_lock(drive, disk, 0);
-		drive->dev_flags &= ~IDE_DFLAG_FORMAT_IN_PROGRESS;
-	}
-
-	idkp->openers--;
-
-	ide_disk_put(idkp);
-
-	return 0;
-}
-
-static int ide_gd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
-{
-	struct ide_floppy_obj *idkp = ide_drv_g(bdev->bd_disk, ide_floppy_obj);
-	ide_drive_t *drive = idkp->drive;
-
-	geo->heads = drive->bios_head;
-	geo->sectors = drive->bios_sect;
-	geo->cylinders = (u16)drive->bios_cyl; /* truncate */
-	return 0;
-}
-
-static int ide_gd_media_changed(struct gendisk *disk)
-{
-	struct ide_floppy_obj *idkp = ide_drv_g(disk, ide_floppy_obj);
-	ide_drive_t *drive = idkp->drive;
-	int ret;
-
-	/* do not scan partitions twice if this is a removable device */
-	if (drive->dev_flags & IDE_DFLAG_ATTACH) {
-		drive->dev_flags &= ~IDE_DFLAG_ATTACH;
-		return 0;
-	}
-
-	ret = !!(drive->dev_flags & IDE_DFLAG_MEDIA_CHANGED);
-	drive->dev_flags &= ~IDE_DFLAG_MEDIA_CHANGED;
-
-	return ret;
-}
-
-static int ide_gd_revalidate_disk(struct gendisk *disk)
-{
-	struct ide_floppy_obj *idkp = ide_drv_g(disk, ide_floppy_obj);
-	set_capacity(disk, ide_gd_capacity(idkp->drive));
-	return 0;
-}
-
-static struct block_device_operations ide_gd_ops = {
-	.owner			= THIS_MODULE,
-	.open			= ide_gd_open,
-	.release		= ide_gd_release,
-	.ioctl			= ide_floppy_ioctl,
-	.getgeo			= ide_gd_getgeo,
-	.media_changed		= ide_gd_media_changed,
-	.revalidate_disk	= ide_gd_revalidate_disk
-};
-
-static int ide_gd_probe(ide_drive_t *drive)
-{
-	struct ide_floppy_obj *idkp;
-	struct gendisk *g;
-
-	if (!strstr("ide-floppy", drive->driver_req))
-		goto failed;
-
-	if (drive->media != ide_floppy)
-		goto failed;
-
-	if (!ide_check_atapi_device(drive, DRV_NAME)) {
-		printk(KERN_ERR PFX "%s: not supported by this version of "
-		       DRV_NAME "\n", drive->name);
-		goto failed;
-	}
-	idkp = kzalloc(sizeof(*idkp), GFP_KERNEL);
-	if (!idkp) {
-		printk(KERN_ERR PFX "%s: Can't allocate a floppy structure\n",
-		       drive->name);
-		goto failed;
-	}
-
-	g = alloc_disk_node(1 << PARTN_BITS, hwif_to_node(drive->hwif));
-	if (!g)
-		goto out_free_idkp;
-
-	ide_init_disk(g, drive);
-
-	kref_init(&idkp->kref);
-
-	idkp->drive = drive;
-	idkp->driver = &ide_gd_driver;
-	idkp->disk = g;
-
-	g->private_data = &idkp->driver;
-
-	drive->driver_data = idkp;
-
-	drive->debug_mask = debug_mask;
-
-	ide_floppy_setup(drive);
-
-	set_capacity(g, ide_gd_capacity(drive));
-
-	g->minors = 1 << PARTN_BITS;
-	g->driverfs_dev = &drive->gendev;
-	if (drive->dev_flags & IDE_DFLAG_REMOVABLE)
-		g->flags = GENHD_FL_REMOVABLE;
-	g->fops = &ide_gd_ops;
-	add_disk(g);
-	return 0;
-
-out_free_idkp:
-	kfree(idkp);
-failed:
-	return -ENODEV;
-}
-
-static int __init ide_gd_init(void)
-{
-	printk(KERN_INFO DRV_NAME " driver " IDEFLOPPY_VERSION "\n");
-	return driver_register(&ide_gd_driver.gen_driver);
-}
-
-static void __exit ide_gd_exit(void)
-{
-	driver_unregister(&ide_gd_driver.gen_driver);
-}
-
-MODULE_ALIAS("ide:*m-floppy*");
-MODULE_ALIAS("ide-floppy");
-module_init(ide_gd_init);
-module_exit(ide_gd_exit);
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("ATAPI FLOPPY Driver");
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index a3d4ad7db2af..d44898f46c33 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -15,9 +15,14 @@
 #endif
 
 #include "ide-disk.h"
+#include "ide-floppy.h"
 
 #define IDE_GD_VERSION	"1.18"
 
+/* module parameters */
+static unsigned long debug_mask;
+module_param(debug_mask, ulong, 0644);
+
 static DEFINE_MUTEX(ide_disk_ref_mutex);
 
 static void ide_disk_release(struct kref *);
@@ -64,7 +69,7 @@ static void ide_gd_remove(ide_drive_t *drive)
 
 	del_gendisk(g);
 
-	ide_disk_flush(drive);
+	drive->disk_ops->flush(drive);
 
 	ide_disk_put(idkp);
 }
@@ -75,6 +80,7 @@ static void ide_disk_release(struct kref *kref)
 	ide_drive_t *drive = idkp->drive;
 	struct gendisk *g = idkp->disk;
 
+	drive->disk_ops = NULL;
 	drive->driver_data = NULL;
 	g->private_data = NULL;
 	put_disk(g);
@@ -89,7 +95,7 @@ static void ide_disk_release(struct kref *kref)
 static void ide_gd_resume(ide_drive_t *drive)
 {
 	if (ata_id_hpa_enabled(drive->id))
-		ide_disk_init_capacity(drive);
+		(void)drive->disk_ops->get_capacity(drive);
 }
 
 static void ide_gd_shutdown(ide_drive_t *drive)
@@ -110,7 +116,7 @@ static void ide_gd_shutdown(ide_drive_t *drive)
 #else
 	if (system_state == SYSTEM_RESTART) {
 #endif
-		ide_disk_flush(drive);
+		drive->disk_ops->flush(drive);
 		return;
 	}
 
@@ -122,19 +128,31 @@ static void ide_gd_shutdown(ide_drive_t *drive)
 #ifdef CONFIG_IDE_PROC_FS
 static ide_proc_entry_t *ide_disk_proc_entries(ide_drive_t *drive)
 {
-	return ide_disk_proc;
+	return (drive->media == ide_disk) ? ide_disk_proc : ide_floppy_proc;
 }
 
 static const struct ide_proc_devset *ide_disk_proc_devsets(ide_drive_t *drive)
 {
-	return ide_disk_settings;
+	return (drive->media == ide_disk) ? ide_disk_settings
+					  : ide_floppy_settings;
 }
 #endif
 
+static ide_startstop_t ide_gd_do_request(ide_drive_t *drive,
+					 struct request *rq, sector_t sector)
+{
+	return drive->disk_ops->do_request(drive, rq, sector);
+}
+
+static int ide_gd_end_request(ide_drive_t *drive, int uptodate, int nrsecs)
+{
+	return drive->disk_ops->end_request(drive, uptodate, nrsecs);
+}
+
 static ide_driver_t ide_gd_driver = {
 	.gen_driver = {
 		.owner		= THIS_MODULE,
-		.name		= "ide-disk",
+		.name		= "ide-gd",
 		.bus		= &ide_bus_type,
 	},
 	.probe			= ide_gd_probe,
@@ -142,8 +160,8 @@ static ide_driver_t ide_gd_driver = {
 	.resume			= ide_gd_resume,
 	.shutdown		= ide_gd_shutdown,
 	.version		= IDE_GD_VERSION,
-	.do_request		= ide_do_rw_disk,
-	.end_request		= ide_end_request,
+	.do_request		= ide_gd_do_request,
+	.end_request		= ide_gd_end_request,
 	.error			= __ide_error,
 #ifdef CONFIG_IDE_PROC_FS
 	.proc_entries		= ide_disk_proc_entries,
@@ -156,6 +174,7 @@ static int ide_gd_open(struct inode *inode, struct file *filp)
 	struct gendisk *disk = inode->i_bdev->bd_disk;
 	struct ide_disk_obj *idkp;
 	ide_drive_t *drive;
+	int ret = 0;
 
 	idkp = ide_disk_get(disk);
 	if (idkp == NULL)
@@ -163,19 +182,49 @@ static int ide_gd_open(struct inode *inode, struct file *filp)
 
 	drive = idkp->drive;
 
+	ide_debug_log(IDE_DBG_FUNC, "Call %s\n", __func__);
+
 	idkp->openers++;
 
 	if ((drive->dev_flags & IDE_DFLAG_REMOVABLE) && idkp->openers == 1) {
+		drive->dev_flags &= ~IDE_DFLAG_FORMAT_IN_PROGRESS;
+		/* Just in case */
+
+		ret = drive->disk_ops->init_media(drive, disk);
+
+		/*
+		 * Allow O_NDELAY to open a drive without a disk, or with an
+		 * unreadable disk, so that we can get the format capacity
+		 * of the drive or begin the format - Sam
+		 */
+		if (ret && (filp->f_flags & O_NDELAY) == 0) {
+			ret = -EIO;
+			goto out_put_idkp;
+		}
+
+		if ((drive->dev_flags & IDE_DFLAG_WP) && (filp->f_mode & 2)) {
+			ret = -EROFS;
+			goto out_put_idkp;
+		}
+
 		/*
 		 * Ignore the return code from door_lock,
 		 * since the open() has already succeeded,
 		 * and the door_lock is irrelevant at this point.
 		 */
-		ide_disk_set_doorlock(drive, 1);
+		drive->disk_ops->set_doorlock(drive, disk, 1);
 		drive->dev_flags |= IDE_DFLAG_MEDIA_CHANGED;
 		check_disk_change(inode->i_bdev);
+	} else if (drive->dev_flags & IDE_DFLAG_FORMAT_IN_PROGRESS) {
+		ret = -EBUSY;
+		goto out_put_idkp;
 	}
 	return 0;
+
+out_put_idkp:
+	idkp->openers--;
+	ide_disk_put(idkp);
+	return ret;
 }
 
 static int ide_gd_release(struct inode *inode, struct file *filp)
@@ -184,11 +233,15 @@ static int ide_gd_release(struct inode *inode, struct file *filp)
 	struct ide_disk_obj *idkp = ide_drv_g(disk, ide_disk_obj);
 	ide_drive_t *drive = idkp->drive;
 
+	ide_debug_log(IDE_DBG_FUNC, "Call %s\n", __func__);
+
 	if (idkp->openers == 1)
-		ide_disk_flush(drive);
+		drive->disk_ops->flush(drive);
 
-	if ((drive->dev_flags & IDE_DFLAG_REMOVABLE) && idkp->openers == 1)
-		ide_disk_set_doorlock(drive, 0);
+	if ((drive->dev_flags & IDE_DFLAG_REMOVABLE) && idkp->openers == 1) {
+		drive->disk_ops->set_doorlock(drive, disk, 0);
+		drive->dev_flags &= ~IDE_DFLAG_FORMAT_IN_PROGRESS;
+	}
 
 	idkp->openers--;
 
@@ -233,11 +286,21 @@ static int ide_gd_revalidate_disk(struct gendisk *disk)
 	return 0;
 }
 
+static int ide_gd_ioctl(struct inode *inode, struct file *file,
+			     unsigned int cmd, unsigned long arg)
+{
+	struct block_device *bdev = inode->i_bdev;
+	struct ide_disk_obj *idkp = ide_drv_g(bdev->bd_disk, ide_disk_obj);
+	ide_drive_t *drive = idkp->drive;
+
+	return drive->disk_ops->ioctl(drive, inode, file, cmd, arg);
+}
+
 static struct block_device_operations ide_gd_ops = {
 	.owner			= THIS_MODULE,
 	.open			= ide_gd_open,
 	.release		= ide_gd_release,
-	.ioctl			= ide_disk_ioctl,
+	.ioctl			= ide_gd_ioctl,
 	.getgeo			= ide_gd_getgeo,
 	.media_changed		= ide_gd_media_changed,
 	.revalidate_disk	= ide_gd_revalidate_disk
@@ -245,19 +308,37 @@ static struct block_device_operations ide_gd_ops = {
 
 static int ide_gd_probe(ide_drive_t *drive)
 {
+	const struct ide_disk_ops *disk_ops = NULL;
 	struct ide_disk_obj *idkp;
 	struct gendisk *g;
 
 	/* strstr("foo", "") is non-NULL */
-	if (!strstr("ide-disk", drive->driver_req))
+	if (!strstr("ide-gd", drive->driver_req))
+		goto failed;
+
+#ifdef CONFIG_IDE_GD_ATA
+	if (drive->media == ide_disk)
+		disk_ops = &ide_ata_disk_ops;
+#endif
+#ifdef CONFIG_IDE_GD_ATAPI
+	if (drive->media == ide_floppy)
+		disk_ops = &ide_atapi_disk_ops;
+#endif
+	if (disk_ops == NULL)
 		goto failed;
 
-	if (drive->media != ide_disk)
+	if (disk_ops->check(drive, DRV_NAME) == 0) {
+		printk(KERN_ERR PFX "%s: not supported by this driver\n",
+			drive->name);
 		goto failed;
+	}
 
 	idkp = kzalloc(sizeof(*idkp), GFP_KERNEL);
-	if (!idkp)
+	if (!idkp) {
+		printk(KERN_ERR PFX "%s: can't allocate a disk structure\n",
+			drive->name);
 		goto failed;
+	}
 
 	g = alloc_disk_node(IDE_DISK_MINORS, hwif_to_node(drive->hwif));
 	if (!g)
@@ -274,8 +355,10 @@ static int ide_gd_probe(ide_drive_t *drive)
 	g->private_data = &idkp->driver;
 
 	drive->driver_data = idkp;
+	drive->debug_mask = debug_mask;
+	drive->disk_ops = disk_ops;
 
-	ide_disk_setup(drive);
+	disk_ops->setup(drive);
 
 	set_capacity(g, ide_gd_capacity(drive));
 
@@ -296,6 +379,7 @@ failed:
 
 static int __init ide_gd_init(void)
 {
+	printk(KERN_INFO DRV_NAME " driver " IDE_GD_VERSION "\n");
 	return driver_register(&ide_gd_driver.gen_driver);
 }
 
@@ -306,7 +390,9 @@ static void __exit ide_gd_exit(void)
 
 MODULE_ALIAS("ide:*m-disk*");
 MODULE_ALIAS("ide-disk");
+MODULE_ALIAS("ide:*m-floppy*");
+MODULE_ALIAS("ide-floppy");
 module_init(ide_gd_init);
 module_exit(ide_gd_exit);
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("ATA DISK Driver");
+MODULE_DESCRIPTION("generic ATA/ATAPI disk driver");
diff --git a/drivers/ide/ide-gd.h b/drivers/ide/ide-gd.h
new file mode 100644
index 000000000000..7d3d101713e0
--- /dev/null
+++ b/drivers/ide/ide-gd.h
@@ -0,0 +1,44 @@
+#ifndef __IDE_GD_H
+#define __IDE_GD_H
+
+#define DRV_NAME "ide-gd"
+#define PFX DRV_NAME ": "
+
+/* define to see debug info */
+#define IDE_GD_DEBUG_LOG	0
+
+#if IDE_GD_DEBUG_LOG
+#define ide_debug_log(lvl, fmt, args...) __ide_debug_log(lvl, fmt, args)
+#else
+#define ide_debug_log(lvl, fmt, args...) do {} while (0)
+#endif
+
+struct ide_disk_obj {
+	ide_drive_t	*drive;
+	ide_driver_t	*driver;
+	struct gendisk	*disk;
+	struct kref	kref;
+	unsigned int	openers;	/* protected by BKL for now */
+
+	/* Last failed packet command */
+	struct ide_atapi_pc *failed_pc;
+	/* used for blk_{fs,pc}_request() requests */
+	struct ide_atapi_pc queued_pc;
+
+	/* Last error information */
+	u8 sense_key, asc, ascq;
+
+	int progress_indication;
+
+	/* Device information */
+	/* Current format */
+	int blocks, block_size, bs_factor;
+	/* Last format capacity descriptor */
+	u8 cap_desc[8];
+	/* Copy of the flexible disk page */
+	u8 flexible_disk_page[32];
+};
+
+sector_t ide_gd_capacity(ide_drive_t *);
+
+#endif /* __IDE_GD_H */
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index e3e40427e00e..c7ff1e11ea85 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -179,7 +179,7 @@ config LEDS_TRIGGER_TIMER
 
 config LEDS_TRIGGER_IDE_DISK
 	bool "LED IDE Disk Trigger"
-	depends on LEDS_TRIGGERS && BLK_DEV_IDEDISK
+	depends on LEDS_TRIGGERS && IDE_GD_ATA
 	help
 	  This allows LEDs to be controlled by IDE disk activity.
 	  If unsure, say Y.
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 488808891acb..89e53cfbc787 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -461,6 +461,23 @@ struct ide_acpi_drive_link;
 struct ide_acpi_hwif_link;
 #endif
 
+struct ide_drive_s;
+
+struct ide_disk_ops {
+	int		(*check)(struct ide_drive_s *, const char *);
+	int		(*get_capacity)(struct ide_drive_s *);
+	void		(*setup)(struct ide_drive_s *);
+	void		(*flush)(struct ide_drive_s *);
+	int		(*init_media)(struct ide_drive_s *, struct gendisk *);
+	int		(*set_doorlock)(struct ide_drive_s *, struct gendisk *,
+					int);
+	ide_startstop_t	(*do_request)(struct ide_drive_s *, struct request *,
+				      sector_t);
+	int		(*end_request)(struct ide_drive_s *, int, int);
+	int		(*ioctl)(struct ide_drive_s *, struct inode *,
+				 struct file *, unsigned int, unsigned long);
+};
+
 /* ATAPI device flags */
 enum {
 	IDE_AFLAG_DRQ_INTERRUPT		= (1 << 0),
@@ -594,6 +611,8 @@ struct ide_drive_s {
 #endif
 	struct hwif_s		*hwif;	/* actually (ide_hwif_t *) */
 
+	const struct ide_disk_ops *disk_ops;
+
 	unsigned long dev_flags;
 
 	unsigned long sleep;		/* sleep until this time */
-- 
cgit v1.2.3


From 30c7ed5aba72bb7357282cf8f411b2e74d82081c Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Fri, 17 Oct 2008 18:09:14 +0200
Subject: ide: fix support for IDE PCI controllers using MMIO on frv

Just include <asm-generic/ide_iops.h> for __ide_mm_*() instead of
defining them to normal I/O helpers so PCI bus <-> CPU byte-swapping
is done as needed.

Cc: David Howells <dhowells@redhat.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
---
 include/asm-frv/ide.h | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/asm-frv/ide.h b/include/asm-frv/ide.h
index 7ebcc56a2229..361076611855 100644
--- a/include/asm-frv/ide.h
+++ b/include/asm-frv/ide.h
@@ -18,15 +18,7 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 
-/****************************************************************************/
-/*
- * some bits needed for parts of the IDE subsystem to compile
- */
-#define __ide_mm_insw(port, addr, n)	insw((unsigned long) (port), addr, n)
-#define __ide_mm_insl(port, addr, n)	insl((unsigned long) (port), addr, n)
-#define __ide_mm_outsw(port, addr, n)	outsw((unsigned long) (port), addr, n)
-#define __ide_mm_outsl(port, addr, n)	outsl((unsigned long) (port), addr, n)
-
+#include <asm-generic/ide_iops.h>
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_IDE_H */
-- 
cgit v1.2.3


From dc10f6119636a5ff13b633e722e720fe0253202b Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Fri, 17 Oct 2008 18:09:15 +0200
Subject: ide: remove M68K_IDE_SWAPW define from <asm-m68k/ide.h>

Since we solved this by overriding default ->{in,out}put_data
methods in {q40,falcon}ide M68K_IDE_SWAP define can go away.

Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Roman Zippel <zippel@linux-m68k.org>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
---
 include/asm-m68k/ide.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'include')

diff --git a/include/asm-m68k/ide.h b/include/asm-m68k/ide.h
index 1daf6cbdd9f0..b996a3c8cff5 100644
--- a/include/asm-m68k/ide.h
+++ b/include/asm-m68k/ide.h
@@ -92,15 +92,6 @@
 #define outsw_swapw(port, addr, n)	raw_outsw_swapw((u16 *)port, addr, n)
 #endif
 
-
-/* Q40 and Atari have byteswapped IDE busses and since many interesting
- * values in the identification string are text, chars and words they
- * happened to be almost correct without swapping.. However *_capacity
- * is needed for drives over 8 GB. RZ */
-#if defined(CONFIG_Q40) || defined(CONFIG_ATARI)
-#define M68K_IDE_SWAPW  (MACH_IS_Q40 || MACH_IS_ATARI)
-#endif
-
 #ifdef CONFIG_BLK_DEV_FALCON_IDE
 #define IDE_ARCH_LOCK
 
-- 
cgit v1.2.3


From 21f45eb1d381aad30094751c60ae8171d6223a66 Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
Date: Fri, 17 Oct 2008 18:09:15 +0200
Subject: ide: remove unused macros from <asm-parisc/ide.h>

Acked-by: Kyle McMartin <kyle@mcmartin.ca>
Signed-off-by: Bartlomiej Zolnierkiewicz <bzolnier@gmail.com>
---
 include/asm-parisc/ide.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/asm-parisc/ide.h b/include/asm-parisc/ide.h
index c246ef75017d..81700a2321cf 100644
--- a/include/asm-parisc/ide.h
+++ b/include/asm-parisc/ide.h
@@ -13,10 +13,6 @@
 
 #ifdef __KERNEL__
 
-#define ide_request_irq(irq,hand,flg,dev,id)	request_irq((irq),(hand),(flg),(dev),(id))
-#define ide_free_irq(irq,dev_id)		free_irq((irq), (dev_id))
-#define ide_request_region(from,extent,name)	request_region((from), (extent), (name))
-#define ide_release_region(from,extent)		release_region((from), (extent))
 /* Generic I/O and MEMIO string operations.  */
 
 #define __ide_insw	insw
-- 
cgit v1.2.3


From 719254faa17ffedc87ba0fadb9b34e535c9758d5 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 17 Oct 2008 09:59:47 +0200
Subject: NOHZ: unify the nohz function calls in irq_enter()

We have two separate nohz function calls in irq_enter() for no good
reason. Just call a single NOHZ function from irq_enter() and call
the bits in the tick code.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/tick.h     |  7 +++----
 kernel/softirq.c         | 10 +++-------
 kernel/time/tick-sched.c | 13 ++++++++++++-
 3 files changed, 18 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/tick.h b/include/linux/tick.h
index 98921a3e1aa8..b6ec8189ac0c 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -96,9 +96,11 @@ extern cpumask_t *tick_get_broadcast_oneshot_mask(void);
 extern void tick_clock_notify(void);
 extern int tick_check_oneshot_change(int allow_nohz);
 extern struct tick_sched *tick_get_tick_sched(int cpu);
+extern void tick_check_idle(int cpu);
 # else
 static inline void tick_clock_notify(void) { }
 static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
+static inline void tick_check_idle(int cpu) { }
 # endif
 
 #else /* CONFIG_GENERIC_CLOCKEVENTS */
@@ -106,26 +108,23 @@ static inline void tick_init(void) { }
 static inline void tick_cancel_sched_timer(int cpu) { }
 static inline void tick_clock_notify(void) { }
 static inline int tick_check_oneshot_change(int allow_nohz) { return 0; }
+static inline void tick_check_idle(int cpu) { }
 #endif /* !CONFIG_GENERIC_CLOCKEVENTS */
 
 # ifdef CONFIG_NO_HZ
 extern void tick_nohz_stop_sched_tick(int inidle);
 extern void tick_nohz_restart_sched_tick(void);
-extern void tick_nohz_update_jiffies(void);
 extern ktime_t tick_nohz_get_sleep_length(void);
-extern void tick_nohz_stop_idle(int cpu);
 extern u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time);
 # else
 static inline void tick_nohz_stop_sched_tick(int inidle) { }
 static inline void tick_nohz_restart_sched_tick(void) { }
-static inline void tick_nohz_update_jiffies(void) { }
 static inline ktime_t tick_nohz_get_sleep_length(void)
 {
 	ktime_t len = { .tv64 = NSEC_PER_SEC/HZ };
 
 	return len;
 }
-static inline void tick_nohz_stop_idle(int cpu) { }
 static inline u64 get_cpu_idle_time_us(int cpu, u64 *unused) { return -1; }
 # endif /* !NO_HZ */
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 37d67aa2d56f..d410014279e7 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -265,16 +265,12 @@ asmlinkage void do_softirq(void)
  */
 void irq_enter(void)
 {
-#ifdef CONFIG_NO_HZ
 	int cpu = smp_processor_id();
+
 	if (idle_cpu(cpu) && !in_interrupt())
-		tick_nohz_stop_idle(cpu);
-#endif
+		tick_check_idle(cpu);
+
 	__irq_enter();
-#ifdef CONFIG_NO_HZ
-	if (idle_cpu(cpu))
-		tick_nohz_update_jiffies();
-#endif
 }
 
 #ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index b711ffcb106c..fdcf3f93bb8d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -155,7 +155,7 @@ void tick_nohz_update_jiffies(void)
 	touch_softlockup_watchdog();
 }
 
-void tick_nohz_stop_idle(int cpu)
+static void tick_nohz_stop_idle(int cpu)
 {
 	struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
 
@@ -558,6 +558,17 @@ static inline void tick_nohz_switch_to_nohz(void) { }
 
 #endif /* NO_HZ */
 
+/*
+ * Called from irq_enter to notify about the possible interruption of idle()
+ */
+void tick_check_idle(int cpu)
+{
+#ifdef CONFIG_NO_HZ
+	tick_nohz_stop_idle(cpu);
+	tick_nohz_update_jiffies();
+#endif
+}
+
 /*
  * High resolution timer specific code
  */
-- 
cgit v1.2.3


From 504e518953a330c8d44a95bdd65a5c9f50f1012e Mon Sep 17 00:00:00 2001
From: Neil Brown <neilb@suse.de>
Date: Thu, 16 Oct 2008 14:15:16 +1100
Subject: Make nfs_file_cred more robust.

As not all files have an associated open_context (e.g. device special
files), it is safest to test for the existence of the open context
before de-referencing it.

Signed-off-by: NeilBrown <neilb@suse.de>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/nfs4proc.c      | 6 ++++--
 include/linux/nfs_fs.h | 8 ++++++--
 2 files changed, 10 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c910413eaeca..83e700a2b0c0 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1659,8 +1659,10 @@ nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 		struct nfs_open_context *ctx;
 
 		ctx = nfs_file_open_context(sattr->ia_file);
-		cred = ctx->cred;
-		state = ctx->state;
+		if (ctx) {
+			cred = ctx->cred;
+			state = ctx->state;
+		}
 	}
 
 	status = nfs4_do_setattr(inode, cred, fattr, sattr, state);
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index ac8d0233b05c..4eaa8347a0d9 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -367,8 +367,12 @@ static inline struct nfs_open_context *nfs_file_open_context(struct file *filp)
 
 static inline struct rpc_cred *nfs_file_cred(struct file *file)
 {
-	if (file != NULL)
-		return nfs_file_open_context(file)->cred;
+	if (file != NULL) {
+		struct nfs_open_context *ctx =
+			nfs_file_open_context(file);
+		if (ctx)
+			return ctx->cred;
+	}
 	return NULL;
 }
 
-- 
cgit v1.2.3


From e7f4b8f1a5893ff8296b5b581e16a0b96f60a3b5 Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Fri, 17 Oct 2008 16:20:07 -0500
Subject: 9p: Improve debug support

The new debug support lacks some of the information that the previous fcprint
code provided -- this patch focuses on better presentation of debug data along
with more helpful debug along error paths.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/9p.h |  4 +--
 net/9p/client.c     | 76 ++++++++++++++++++++++++++++++++++++++---------------
 net/9p/protocol.c   | 21 ++++++++++-----
 3 files changed, 72 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index cb5bc731e885..d2c60c73619d 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -27,8 +27,6 @@
 #ifndef NET_9P_H
 #define NET_9P_H
 
-#ifdef CONFIG_NET_9P_DEBUG
-
 /**
  * enum p9_debug_flags - bits for mount time debug parameter
  * @P9_DEBUG_ERROR: more verbose error messages including original error string
@@ -55,10 +53,12 @@ enum p9_debug_flags {
 	P9_DEBUG_SLABS =      	(1<<7),
 	P9_DEBUG_FCALL =	(1<<8),
 	P9_DEBUG_FID =		(1<<9),
+	P9_DEBUG_PKT =		(1<<10),
 };
 
 extern unsigned int p9_debug_level;
 
+#ifdef CONFIG_NET_9P_DEBUG
 #define P9_DPRINTK(level, format, arg...) \
 do {  \
 	if ((p9_debug_level & level) == level) {\
diff --git a/net/9p/client.c b/net/9p/client.c
index 2a166bfb95a3..bbac2f72b4d2 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -389,8 +389,8 @@ p9_parse_header(struct p9_fcall *pdu, int32_t *size, int8_t *type, int16_t *tag,
 	pdu->id = r_type;
 	pdu->tag = r_tag;
 
-	P9_DPRINTK(P9_DEBUG_MUX, "pdu: type: %d tag: %d size=%d offset=%d\n",
-				pdu->id, pdu->tag, pdu->size, pdu->offset);
+	P9_DPRINTK(P9_DEBUG_9P, "<<< size=%d type: %d tag: %d\n", pdu->size,
+							pdu->id, pdu->tag);
 
 	if (type)
 		*type = r_type;
@@ -672,6 +672,7 @@ int p9_client_version(struct p9_client *c)
 	err = p9pdu_readf(req->rc, c->dotu, "ds", &msize, &version);
 	if (err) {
 		P9_DPRINTK(P9_DEBUG_9P, "version error %d\n", err);
+		p9pdu_dump(1, req->rc);
 		goto error;
 	}
 
@@ -810,6 +811,7 @@ struct p9_fid *p9_client_attach(struct p9_client *clnt, struct p9_fid *afid,
 
 	err = p9pdu_readf(req->rc, clnt->dotu, "Q", &qid);
 	if (err) {
+		p9pdu_dump(1, req->rc);
 		p9_free_req(clnt, req);
 		goto error;
 	}
@@ -856,6 +858,7 @@ p9_client_auth(struct p9_client *clnt, char *uname, u32 n_uname, char *aname)
 
 	err = p9pdu_readf(req->rc, clnt->dotu, "Q", &qid);
 	if (err) {
+		p9pdu_dump(1, req->rc);
 		p9_free_req(clnt, req);
 		goto error;
 	}
@@ -910,9 +913,12 @@ struct p9_fid *p9_client_walk(struct p9_fid *oldfid, int nwname, char **wnames,
 	}
 
 	err = p9pdu_readf(req->rc, clnt->dotu, "R", &nwqids, &wqids);
-	p9_free_req(clnt, req);
-	if (err)
+	if (err) {
+		p9pdu_dump(1, req->rc);
+		p9_free_req(clnt, req);
 		goto clunk_fid;
+	}
+	p9_free_req(clnt, req);
 
 	P9_DPRINTK(P9_DEBUG_9P, "<<< RWALK nwqid %d:\n", nwqids);
 
@@ -967,9 +973,10 @@ int p9_client_open(struct p9_fid *fid, int mode)
 	}
 
 	err = p9pdu_readf(req->rc, clnt->dotu, "Qd", &qid, &iounit);
-	p9_free_req(clnt, req);
-	if (err)
-		goto error;
+	if (err) {
+		p9pdu_dump(1, req->rc);
+		goto free_and_error;
+	}
 
 	P9_DPRINTK(P9_DEBUG_9P, "<<< ROPEN qid %x.%llx.%x iounit %x\n",
 				qid.type, qid.path, qid.version, iounit);
@@ -977,6 +984,8 @@ int p9_client_open(struct p9_fid *fid, int mode)
 	fid->mode = mode;
 	fid->iounit = iounit;
 
+free_and_error:
+	p9_free_req(clnt, req);
 error:
 	return err;
 }
@@ -1007,9 +1016,10 @@ int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode,
 	}
 
 	err = p9pdu_readf(req->rc, clnt->dotu, "Qd", &qid, &iounit);
-	p9_free_req(clnt, req);
-	if (err)
-		goto error;
+	if (err) {
+		p9pdu_dump(1, req->rc);
+		goto free_and_error;
+	}
 
 	P9_DPRINTK(P9_DEBUG_9P, "<<< RCREATE qid %x.%llx.%x iounit %x\n",
 				qid.type, qid.path, qid.version, iounit);
@@ -1017,6 +1027,8 @@ int p9_client_fcreate(struct p9_fid *fid, char *name, u32 perm, int mode,
 	fid->mode = mode;
 	fid->iounit = iounit;
 
+free_and_error:
+	p9_free_req(clnt, req);
 error:
 	return err;
 }
@@ -1103,8 +1115,10 @@ p9_client_read(struct p9_fid *fid, char *data, char __user *udata, u64 offset,
 	}
 
 	err = p9pdu_readf(req->rc, clnt->dotu, "D", &count, &dataptr);
-	if (err)
+	if (err) {
+		p9pdu_dump(1, req->rc);
 		goto free_and_error;
+	}
 
 	P9_DPRINTK(P9_DEBUG_9P, "<<< RREAD count %d\n", count);
 
@@ -1163,8 +1177,11 @@ p9_client_write(struct p9_fid *fid, char *data, const char __user *udata,
 	}
 
 	err = p9pdu_readf(req->rc, clnt->dotu, "d", &count);
-	if (err)
+	if (err) {
+		p9pdu_dump(1, req->rc);
 		goto free_and_error;
+	}
+
 	P9_DPRINTK(P9_DEBUG_9P, "<<< RWRITE count %d\n", count);
 
 	p9_free_req(clnt, req);
@@ -1200,20 +1217,27 @@ struct p9_wstat *p9_client_stat(struct p9_fid *fid)
 	}
 
 	err = p9pdu_readf(req->rc, clnt->dotu, "wS", &ignored, ret);
-	p9_free_req(clnt, req);
-	if (err)
-		goto error;
+	if (err) {
+		ret = ERR_PTR(err);
+		p9pdu_dump(1, req->rc);
+		goto free_and_error;
+	}
 
 	P9_DPRINTK(P9_DEBUG_9P,
-		"<<< RSTAT sz=%x type=%x dev=%x qid=%2.2x %4.4x %8.8llx"
-		" mode=%8.8x uid=%d gid=%d size=%lld %s\n",
+		"<<< RSTAT sz=%x type=%x dev=%x qid=%x.%llx.%x\n"
+		"<<<    mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n"
+		"<<<    name=%s uid=%s gid=%s muid=%s extension=(%s)\n"
+		"<<<    uid=%d gid=%d n_muid=%d\n",
 		ret->size, ret->type, ret->dev, ret->qid.type,
-		ret->qid.version, ret->qid.path, ret->mode,
-		ret->n_uid, ret->n_gid, ret->length, ret->name);
+		ret->qid.path, ret->qid.version, ret->mode,
+		ret->atime, ret->mtime, ret->length, ret->name,
+		ret->uid, ret->gid, ret->muid, ret->extension,
+		ret->n_uid, ret->n_gid, ret->n_muid);
 
-	return ret;
+free_and_error:
+	p9_free_req(clnt, req);
 error:
-	return ERR_PTR(err);
+	return ret;
 }
 EXPORT_SYMBOL(p9_client_stat);
 
@@ -1224,6 +1248,16 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst)
 	struct p9_client *clnt;
 
 	P9_DPRINTK(P9_DEBUG_9P, ">>> TWSTAT fid %d\n", fid->fid);
+	P9_DPRINTK(P9_DEBUG_9P,
+		"     sz=%x type=%x dev=%x qid=%x.%llx.%x\n"
+		"     mode=%8.8x atime=%8.8x mtime=%8.8x length=%llx\n"
+		"     name=%s uid=%s gid=%s muid=%s extension=(%s)\n"
+		"     uid=%d gid=%d n_muid=%d\n",
+		wst->size, wst->type, wst->dev, wst->qid.type,
+		wst->qid.path, wst->qid.version, wst->mode,
+		wst->atime, wst->mtime, wst->length, wst->name,
+		wst->uid, wst->gid, wst->muid, wst->extension,
+		wst->n_uid, wst->n_gid, wst->n_muid);
 	err = 0;
 	clnt = fid->clnt;
 
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 92cb60bb191b..84fa21271876 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -28,6 +28,7 @@
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/uaccess.h>
+#include <linux/sched.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 #include "protocol.h"
@@ -52,8 +53,6 @@
 static int
 p9pdu_writef(struct p9_fcall *pdu, int optional, const char *fmt, ...);
 
-#define PACKET_DEBUG 0
-
 void
 p9pdu_dump(int way, struct p9_fcall *pdu)
 {
@@ -78,9 +77,9 @@ p9pdu_dump(int way, struct p9_fcall *pdu)
 	n += scnprintf(buf + n, buflen - n, "\n");
 
 	if (way)
-		printk(KERN_NOTICE "[[(%d)[ %s\n", datalen, buf);
+		P9_DPRINTK(P9_DEBUG_PKT, "[[[(%d) %s\n", datalen, buf);
 	else
-		printk(KERN_NOTICE "]](%d)] %s\n", datalen, buf);
+		P9_DPRINTK(P9_DEBUG_PKT, "]]](%d) %s\n", datalen, buf);
 }
 EXPORT_SYMBOL(p9pdu_dump);
 
@@ -512,13 +511,20 @@ p9pdu_writef(struct p9_fcall *pdu, int optional, const char *fmt, ...)
 int p9stat_read(char *buf, int len, struct p9_wstat *st, int dotu)
 {
 	struct p9_fcall fake_pdu;
+	int ret;
 
 	fake_pdu.size = len;
 	fake_pdu.capacity = len;
 	fake_pdu.sdata = buf;
 	fake_pdu.offset = 0;
 
-	return p9pdu_readf(&fake_pdu, dotu, "S", st);
+	ret = p9pdu_readf(&fake_pdu, dotu, "S", st);
+	if (ret) {
+		P9_DPRINTK(P9_DEBUG_9P, "<<< p9stat_read failed: %d\n", ret);
+		p9pdu_dump(1, &fake_pdu);
+	}
+
+	return ret;
 }
 EXPORT_SYMBOL(p9stat_read);
 
@@ -536,9 +542,12 @@ int p9pdu_finalize(struct p9_fcall *pdu)
 	err = p9pdu_writef(pdu, 0, "d", size);
 	pdu->size = size;
 
-	if (PACKET_DEBUG)
+	if ((p9_debug_level & P9_DEBUG_PKT) == P9_DEBUG_PKT)
 		p9pdu_dump(0, pdu);
 
+	P9_DPRINTK(P9_DEBUG_9P, ">>> size=%d type: %d tag: %d\n", pdu->size,
+							pdu->id, pdu->tag);
+
 	return err;
 }
 
-- 
cgit v1.2.3


From 97854829b97093ae172144a2597fc49ea203dcf3 Mon Sep 17 00:00:00 2001
From: Manu Abraham <abraham.manu@gmail.com>
Date: Tue, 14 Oct 2008 19:48:07 -0300
Subject: V4L/DVB (9195): Frontend API Fix: 32APSK is a valid modulation for
 the DVB-S2 delivery

Signed-off-by: Manu Abraham <manu@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/dvb/dvb-core/dvb_frontend.c | 1 +
 include/linux/dvb/frontend.h              | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/drivers/media/dvb/dvb-core/dvb_frontend.c b/drivers/media/dvb/dvb-core/dvb_frontend.c
index f170e822fadc..72ce7935f253 100644
--- a/drivers/media/dvb/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb/dvb-core/dvb_frontend.c
@@ -1063,6 +1063,7 @@ void dtv_property_adv_params_sync(struct dvb_frontend *fe)
 	switch(c->modulation) {
 	case PSK_8:
 	case APSK_16:
+	case APSK_32:
 	case QPSK:
 		p->u.qpsk.symbol_rate = c->symbol_rate;
 		p->u.qpsk.fec_inner = c->fec_inner;
diff --git a/include/linux/dvb/frontend.h b/include/linux/dvb/frontend.h
index 6e4ace270276..38942f731b9b 100644
--- a/include/linux/dvb/frontend.h
+++ b/include/linux/dvb/frontend.h
@@ -166,6 +166,7 @@ typedef enum fe_modulation {
 	VSB_16,
 	PSK_8,
 	APSK_16,
+	APSK_32,
 	DQPSK,
 } fe_modulation_t;
 
-- 
cgit v1.2.3


From 5ba4ecc8b0166de4363cc31aa68d52abe0dff8de Mon Sep 17 00:00:00 2001
From: Manu Abraham <abraham.manu@gmail.com>
Date: Tue, 14 Oct 2008 19:50:03 -0300
Subject: V4L/DVB (9196): Add support for DSS delivery

Signed-off-by: Manu Abraham <manu@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 include/linux/dvb/frontend.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/dvb/frontend.h b/include/linux/dvb/frontend.h
index 38942f731b9b..79a8ed8e6a7d 100644
--- a/include/linux/dvb/frontend.h
+++ b/include/linux/dvb/frontend.h
@@ -296,6 +296,7 @@ typedef enum fe_delivery_system {
 	SYS_DVBC_ANNEX_AC,
 	SYS_DVBC_ANNEX_B,
 	SYS_DVBT,
+	SYS_DSS,
 	SYS_DVBS,
 	SYS_DVBS2,
 	SYS_DVBH,
-- 
cgit v1.2.3


From 7b31b57a37ab694b9693a0359bf8ed0967188533 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Mon, 13 Oct 2008 07:38:03 -0300
Subject: V4L/DVB (9209): v4l2: add comment to the v4l2-i2c-drv headers.

Looking at these headers as they appear in the kernel makes you
wonder why it is done that way. Refer to the v4l-dvb repository
where the full unstripped header can be found to understand the
reasoning behind this.

Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 include/media/v4l2-i2c-drv-legacy.h | 11 +++++++++++
 include/media/v4l2-i2c-drv.h        | 11 +++++++++++
 2 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/include/media/v4l2-i2c-drv-legacy.h b/include/media/v4l2-i2c-drv-legacy.h
index 975ffbf4e2c5..e65dd9d84e8b 100644
--- a/include/media/v4l2-i2c-drv-legacy.h
+++ b/include/media/v4l2-i2c-drv-legacy.h
@@ -21,6 +21,17 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+/* NOTE: the full version of this header is in the v4l-dvb repository
+ * and allows v4l i2c drivers to be compiled on older kernels as well.
+ * The version of this header as it appears in the kernel is a stripped
+ * version (without all the backwards compatibility stuff) and so it
+ * looks a bit odd.
+ *
+ * If you look at the full version then you will understand the reason
+ * for introducing this header since you really don't want to have all
+ * the tricky backwards compatibility code in each and every i2c driver.
+ */
+
 struct v4l2_i2c_driver_data {
 	const char * const name;
 	int driverid;
diff --git a/include/media/v4l2-i2c-drv.h b/include/media/v4l2-i2c-drv.h
index 40ecef29801d..efdc8bf27f87 100644
--- a/include/media/v4l2-i2c-drv.h
+++ b/include/media/v4l2-i2c-drv.h
@@ -21,6 +21,17 @@
  * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
+/* NOTE: the full version of this header is in the v4l-dvb repository
+ * and allows v4l i2c drivers to be compiled on older kernels as well.
+ * The version of this header as it appears in the kernel is a stripped
+ * version (without all the backwards compatibility stuff) and so it
+ * looks a bit odd.
+ *
+ * If you look at the full version then you will understand the reason
+ * for introducing this header since you really don't want to have all
+ * the tricky backwards compatibility code in each and every i2c driver.
+ */
+
 #ifndef __V4L2_I2C_DRV_H__
 #define __V4L2_I2C_DRV_H__
 
-- 
cgit v1.2.3


From 363c35fc448943c3d6121332d28bcda2d2fbf87c Mon Sep 17 00:00:00 2001
From: Steven Toth <stoth@linuxtv.org>
Date: Sat, 11 Oct 2008 11:05:50 -0300
Subject: V4L/DVB (9222): S2API: Add Multiple-frontend on a single adapter
 support.

A detailed description from the original patches 2 years ago:

"The WinTV-HVR3000 has a single transport bus which is shared between
a DVB-T and DVB-S modulator. These patches build on the bus acquisition
cx88 work from a few weeks ago to add support for this.

So to applications the HVR3000 looks like this:
/dev/dvb/adapter0/fe0 (cx24123 DVB-S demod)
/dev/dvb/adapter0/fe1 (cx22702 DVB-T demod)

Additional boards continue as before, eg:
/dev/dvb/adapter1/fe0 (lgdt3302 ATSC demod)

The basic change is removing the single instance of the videobuf_dvb in
cx8802_dev and saa7134_dev(?) and replacing it with a list and some
supporting functions.

*NOTE* This branch was taken before v4l-dvb was closed for 2.6.19 so
two or three current cx88 patches appear to be reversed by this tree,
this will be cleaned up in the near future. The patches missing change
the mutex handing to core->lock, fix an enumeration problem."

It should be recognised that a number of people have been maintaining
this patchset. Significant levels of Kudos to everyone one involved,
including but not limited to:

Darron Broad
Fabio M. Di Nitto
Carlo Scarfoglio
Hans Werner

Without the work of these people, and countless others, my two year old
patches would of died on the Mercurial linuxtv.org vine a long time
ago.

TODO: Revise these patches a little further so that the need for
demux1 and dvr0 is optional, not mandatory on the HVR3000.

HISTORY (darron):
This is the last update to MFE prepared by Hans which is based
upon the `scratchpad' diff created by Carlo.
All MFE work prior to that point must be attributed to Fabio
who ported and maintained Steve's original patch up to that
time.

Signed-off-by: Steven Toth <stoth@linuxtv.org>
Signed-off-by: Darron Broad <darron@kewl.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/dvb/dvb-core/dvb_frontend.c |  24 +-
 drivers/media/dvb/dvb-core/dvb_frontend.h |   1 +
 drivers/media/video/cx23885/cx23885-dvb.c | 115 ++++----
 drivers/media/video/cx23885/cx23885.h     |   2 +-
 drivers/media/video/cx88/cx88-cards.c     |  11 +-
 drivers/media/video/cx88/cx88-dvb.c       | 423 +++++++++++++++++++++---------
 drivers/media/video/cx88/cx88-i2c.c       |  15 +-
 drivers/media/video/cx88/cx88-input.c     |   1 +
 drivers/media/video/cx88/cx88-mpeg.c      |  22 +-
 drivers/media/video/cx88/cx88.h           |   4 +-
 drivers/media/video/saa7134/saa7134-dvb.c | 205 ++++++++-------
 drivers/media/video/saa7134/saa7134.h     |   2 +-
 drivers/media/video/videobuf-dvb.c        | 171 ++++++++++--
 include/media/videobuf-dvb.h              |  36 ++-
 14 files changed, 713 insertions(+), 319 deletions(-)

(limited to 'include')

diff --git a/drivers/media/dvb/dvb-core/dvb_frontend.c b/drivers/media/dvb/dvb-core/dvb_frontend.c
index 72ce7935f253..26671757c70b 100644
--- a/drivers/media/dvb/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb/dvb-core/dvb_frontend.c
@@ -212,8 +212,9 @@ static int dvb_frontend_get_event(struct dvb_frontend *fe,
 
 static void dvb_frontend_init(struct dvb_frontend *fe)
 {
-	dprintk ("DVB: initialising frontend %i (%s)...\n",
+	dprintk ("DVB: initialising adapter %i frontend %i (%s)...\n",
 		 fe->dvb->num,
+		 fe->id,
 		 fe->ops.info.name);
 
 	if (fe->ops.init)
@@ -686,7 +687,7 @@ static int dvb_frontend_start(struct dvb_frontend *fe)
 	mb();
 
 	fe_thread = kthread_run(dvb_frontend_thread, fe,
-		"kdvb-fe-%i", fe->dvb->num);
+		"kdvb-ad-%i-fe-%i", fe->dvb->num,fe->id);
 	if (IS_ERR(fe_thread)) {
 		ret = PTR_ERR(fe_thread);
 		printk("dvb_frontend_start: failed to start kthread (%d)\n", ret);
@@ -710,8 +711,8 @@ static void dvb_frontend_get_frequeny_limits(struct dvb_frontend *fe,
 		*freq_max = min(fe->ops.info.frequency_max, fe->ops.tuner_ops.info.frequency_max);
 
 	if (*freq_min == 0 || *freq_max == 0)
-		printk(KERN_WARNING "DVB: frontend %u frequency limits undefined - fix the driver\n",
-		       fe->dvb->num);
+		printk(KERN_WARNING "DVB: adapter %i frontend %u frequency limits undefined - fix the driver\n",
+		       fe->dvb->num,fe->id);
 }
 
 static int dvb_frontend_check_parameters(struct dvb_frontend *fe,
@@ -724,8 +725,8 @@ static int dvb_frontend_check_parameters(struct dvb_frontend *fe,
 	dvb_frontend_get_frequeny_limits(fe, &freq_min, &freq_max);
 	if ((freq_min && parms->frequency < freq_min) ||
 	    (freq_max && parms->frequency > freq_max)) {
-		printk(KERN_WARNING "DVB: frontend %u frequency %u out of range (%u..%u)\n",
-		       fe->dvb->num, parms->frequency, freq_min, freq_max);
+		printk(KERN_WARNING "DVB: adapter %i frontend %i frequency %u out of range (%u..%u)\n",
+		       fe->dvb->num, fe->id, parms->frequency, freq_min, freq_max);
 		return -EINVAL;
 	}
 
@@ -735,8 +736,8 @@ static int dvb_frontend_check_parameters(struct dvb_frontend *fe,
 		     parms->u.qpsk.symbol_rate < fe->ops.info.symbol_rate_min) ||
 		    (fe->ops.info.symbol_rate_max &&
 		     parms->u.qpsk.symbol_rate > fe->ops.info.symbol_rate_max)) {
-			printk(KERN_WARNING "DVB: frontend %u symbol rate %u out of range (%u..%u)\n",
-			       fe->dvb->num, parms->u.qpsk.symbol_rate,
+			printk(KERN_WARNING "DVB: adapter %i frontend %i symbol rate %u out of range (%u..%u)\n",
+			       fe->dvb->num, fe->id, parms->u.qpsk.symbol_rate,
 			       fe->ops.info.symbol_rate_min, fe->ops.info.symbol_rate_max);
 			return -EINVAL;
 		}
@@ -746,8 +747,8 @@ static int dvb_frontend_check_parameters(struct dvb_frontend *fe,
 		     parms->u.qam.symbol_rate < fe->ops.info.symbol_rate_min) ||
 		    (fe->ops.info.symbol_rate_max &&
 		     parms->u.qam.symbol_rate > fe->ops.info.symbol_rate_max)) {
-			printk(KERN_WARNING "DVB: frontend %u symbol rate %u out of range (%u..%u)\n",
-			       fe->dvb->num, parms->u.qam.symbol_rate,
+			printk(KERN_WARNING "DVB: adapter %i frontend %i symbol rate %u out of range (%u..%u)\n",
+			       fe->dvb->num, fe->id, parms->u.qam.symbol_rate,
 			       fe->ops.info.symbol_rate_min, fe->ops.info.symbol_rate_max);
 			return -EINVAL;
 		}
@@ -1807,8 +1808,9 @@ int dvb_register_frontend(struct dvb_adapter* dvb,
 	fe->dvb = dvb;
 	fepriv->inversion = INVERSION_OFF;
 
-	printk ("DVB: registering frontend %i (%s)...\n",
+	printk ("DVB: registering adapter %i frontend %i (%s)...\n",
 		fe->dvb->num,
+		fe->id,
 		fe->ops.info.name);
 
 	dvb_register_device (fe->dvb, &fepriv->dvbdev, &dvbdev_template,
diff --git a/drivers/media/dvb/dvb-core/dvb_frontend.h b/drivers/media/dvb/dvb-core/dvb_frontend.h
index 3055301ff3ca..db4a63b0a32e 100644
--- a/drivers/media/dvb/dvb-core/dvb_frontend.h
+++ b/drivers/media/dvb/dvb-core/dvb_frontend.h
@@ -222,6 +222,7 @@ struct dvb_frontend {
 	struct dtv_frontend_properties dtv_property_cache;
 #define DVB_FRONTEND_COMPONENT_TUNER 0
 	int (*callback)(void *adapter_priv, int component, int cmd, int arg);
+	int id;
 };
 
 extern int dvb_register_frontend(struct dvb_adapter *dvb,
diff --git a/drivers/media/video/cx23885/cx23885-dvb.c b/drivers/media/video/cx23885/cx23885-dvb.c
index 24bd18327aa0..fe1218fd44cb 100644
--- a/drivers/media/video/cx23885/cx23885-dvb.c
+++ b/drivers/media/video/cx23885/cx23885-dvb.c
@@ -312,48 +312,53 @@ static int dvb_register(struct cx23885_tsport *port)
 {
 	struct cx23885_dev *dev = port->dev;
 	struct cx23885_i2c *i2c_bus = NULL;
+	struct videobuf_dvb_frontend *fe0;
+
+	fe0 = videobuf_dvb_get_frontend(&port->frontends, 0);
+	if (!fe0)
+		return -EINVAL;
 
 	/* init struct videobuf_dvb */
-	port->dvb.name = dev->name;
+	fe0->dvb.name = dev->name;
 
 	/* init frontend */
 	switch (dev->board) {
 	case CX23885_BOARD_HAUPPAUGE_HVR1250:
 		i2c_bus = &dev->i2c_bus[0];
-		port->dvb.frontend = dvb_attach(s5h1409_attach,
+		fe0->dvb.frontend = dvb_attach(s5h1409_attach,
 						&hauppauge_generic_config,
 						&i2c_bus->i2c_adap);
-		if (port->dvb.frontend != NULL) {
-			dvb_attach(mt2131_attach, port->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			dvb_attach(mt2131_attach, fe0->dvb.frontend,
 				   &i2c_bus->i2c_adap,
 				   &hauppauge_generic_tunerconfig, 0);
 		}
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1800:
 		i2c_bus = &dev->i2c_bus[0];
-		switch (alt_tuner) {
+		switch (alt_tuner) { // XXXXXX multifrontend?
 		case 1:
-			port->dvb.frontend =
+			fe0->dvb.frontend =
 				dvb_attach(s5h1409_attach,
 					   &hauppauge_ezqam_config,
 					   &i2c_bus->i2c_adap);
-			if (port->dvb.frontend != NULL) {
-				dvb_attach(tda829x_attach, port->dvb.frontend,
+			if (fe0->dvb.frontend != NULL) {
+				dvb_attach(tda829x_attach, fe0->dvb.frontend,
 					   &dev->i2c_bus[1].i2c_adap, 0x42,
 					   &tda829x_no_probe);
-				dvb_attach(tda18271_attach, port->dvb.frontend,
+				dvb_attach(tda18271_attach, fe0->dvb.frontend,
 					   0x60, &dev->i2c_bus[1].i2c_adap,
 					   &hauppauge_tda18271_config);
 			}
 			break;
 		case 0:
 		default:
-			port->dvb.frontend =
+			fe0->dvb.frontend =
 				dvb_attach(s5h1409_attach,
 					   &hauppauge_generic_config,
 					   &i2c_bus->i2c_adap);
-			if (port->dvb.frontend != NULL)
-				dvb_attach(mt2131_attach, port->dvb.frontend,
+			if (fe0->dvb.frontend != NULL)
+				dvb_attach(mt2131_attach, fe0->dvb.frontend,
 					   &i2c_bus->i2c_adap,
 					   &hauppauge_generic_tunerconfig, 0);
 			break;
@@ -361,42 +366,42 @@ static int dvb_register(struct cx23885_tsport *port)
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1800lp:
 		i2c_bus = &dev->i2c_bus[0];
-		port->dvb.frontend = dvb_attach(s5h1409_attach,
+		fe0->dvb.frontend = dvb_attach(s5h1409_attach,
 						&hauppauge_hvr1800lp_config,
 						&i2c_bus->i2c_adap);
-		if (port->dvb.frontend != NULL) {
-			dvb_attach(mt2131_attach, port->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			dvb_attach(mt2131_attach, fe0->dvb.frontend,
 				   &i2c_bus->i2c_adap,
 				   &hauppauge_generic_tunerconfig, 0);
 		}
 		break;
 	case CX23885_BOARD_DVICO_FUSIONHDTV_5_EXP:
 		i2c_bus = &dev->i2c_bus[0];
-		port->dvb.frontend = dvb_attach(lgdt330x_attach,
+		fe0->dvb.frontend = dvb_attach(lgdt330x_attach,
 						&fusionhdtv_5_express,
 						&i2c_bus->i2c_adap);
-		if (port->dvb.frontend != NULL) {
-			dvb_attach(simple_tuner_attach, port->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 				   &i2c_bus->i2c_adap, 0x61,
 				   TUNER_LG_TDVS_H06XF);
 		}
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1500Q:
 		i2c_bus = &dev->i2c_bus[1];
-		port->dvb.frontend = dvb_attach(s5h1409_attach,
+		fe0->dvb.frontend = dvb_attach(s5h1409_attach,
 						&hauppauge_hvr1500q_config,
 						&dev->i2c_bus[0].i2c_adap);
-		if (port->dvb.frontend != NULL)
-			dvb_attach(xc5000_attach, port->dvb.frontend,
+		if (fe0->dvb.frontend != NULL)
+			dvb_attach(xc5000_attach, fe0->dvb.frontend,
 				   &i2c_bus->i2c_adap,
 				   &hauppauge_hvr1500q_tunerconfig);
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1500:
 		i2c_bus = &dev->i2c_bus[1];
-		port->dvb.frontend = dvb_attach(s5h1409_attach,
+		fe0->dvb.frontend = dvb_attach(s5h1409_attach,
 						&hauppauge_hvr1500_config,
 						&dev->i2c_bus[0].i2c_adap);
-		if (port->dvb.frontend != NULL) {
+		if (fe0->dvb.frontend != NULL) {
 			struct dvb_frontend *fe;
 			struct xc2028_config cfg = {
 				.i2c_adap  = &i2c_bus->i2c_adap,
@@ -409,7 +414,7 @@ static int dvb_register(struct cx23885_tsport *port)
 			};
 
 			fe = dvb_attach(xc2028_attach,
-					port->dvb.frontend, &cfg);
+					fe0->dvb.frontend, &cfg);
 			if (fe != NULL && fe->ops.tuner_ops.set_config != NULL)
 				fe->ops.tuner_ops.set_config(fe, &ctl);
 		}
@@ -417,24 +422,24 @@ static int dvb_register(struct cx23885_tsport *port)
 	case CX23885_BOARD_HAUPPAUGE_HVR1200:
 	case CX23885_BOARD_HAUPPAUGE_HVR1700:
 		i2c_bus = &dev->i2c_bus[0];
-		port->dvb.frontend = dvb_attach(tda10048_attach,
+		fe0->dvb.frontend = dvb_attach(tda10048_attach,
 			&hauppauge_hvr1200_config,
 			&i2c_bus->i2c_adap);
-		if (port->dvb.frontend != NULL) {
-			dvb_attach(tda829x_attach, port->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			dvb_attach(tda829x_attach, fe0->dvb.frontend,
 				&dev->i2c_bus[1].i2c_adap, 0x42,
 				&tda829x_no_probe);
-			dvb_attach(tda18271_attach, port->dvb.frontend,
+			dvb_attach(tda18271_attach, fe0->dvb.frontend,
 				0x60, &dev->i2c_bus[1].i2c_adap,
 				&hauppauge_hvr1200_tuner_config);
 		}
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1400:
 		i2c_bus = &dev->i2c_bus[0];
-		port->dvb.frontend = dvb_attach(dib7000p_attach,
+		fe0->dvb.frontend = dvb_attach(dib7000p_attach,
 			&i2c_bus->i2c_adap,
 			0x12, &hauppauge_hvr1400_dib7000_config);
-		if (port->dvb.frontend != NULL) {
+		if (fe0->dvb.frontend != NULL) {
 			struct dvb_frontend *fe;
 			struct xc2028_config cfg = {
 				.i2c_adap  = &dev->i2c_bus[1].i2c_adap,
@@ -449,7 +454,7 @@ static int dvb_register(struct cx23885_tsport *port)
 			};
 
 			fe = dvb_attach(xc2028_attach,
-					port->dvb.frontend, &cfg);
+					fe0->dvb.frontend, &cfg);
 			if (fe != NULL && fe->ops.tuner_ops.set_config != NULL)
 				fe->ops.tuner_ops.set_config(fe, &ctl);
 		}
@@ -457,25 +462,25 @@ static int dvb_register(struct cx23885_tsport *port)
 	case CX23885_BOARD_DVICO_FUSIONHDTV_7_DUAL_EXP:
 		i2c_bus = &dev->i2c_bus[port->nr - 1];
 
-		port->dvb.frontend = dvb_attach(s5h1409_attach,
+		fe0->dvb.frontend = dvb_attach(s5h1409_attach,
 						&dvico_s5h1409_config,
 						&i2c_bus->i2c_adap);
-		if (port->dvb.frontend == NULL)
-			port->dvb.frontend = dvb_attach(s5h1411_attach,
+		if (fe0->dvb.frontend == NULL)
+			fe0->dvb.frontend = dvb_attach(s5h1411_attach,
 							&dvico_s5h1411_config,
 							&i2c_bus->i2c_adap);
-		if (port->dvb.frontend != NULL)
-			dvb_attach(xc5000_attach, port->dvb.frontend,
+		if (fe0->dvb.frontend != NULL)
+			dvb_attach(xc5000_attach, fe0->dvb.frontend,
 				   &i2c_bus->i2c_adap,
 				   &dvico_xc5000_tunerconfig);
 		break;
 	case CX23885_BOARD_DVICO_FUSIONHDTV_DVB_T_DUAL_EXP: {
 		i2c_bus = &dev->i2c_bus[port->nr - 1];
 
-		port->dvb.frontend = dvb_attach(zl10353_attach,
+		fe0->dvb.frontend = dvb_attach(zl10353_attach,
 					       &dvico_fusionhdtv_xc3028,
 					       &i2c_bus->i2c_adap);
-		if (port->dvb.frontend != NULL) {
+		if (fe0->dvb.frontend != NULL) {
 			struct dvb_frontend      *fe;
 			struct xc2028_config	  cfg = {
 				.i2c_adap  = &i2c_bus->i2c_adap,
@@ -487,7 +492,7 @@ static int dvb_register(struct cx23885_tsport *port)
 				.demod       = XC3028_FE_ZARLINK456,
 			};
 
-			fe = dvb_attach(xc2028_attach, port->dvb.frontend,
+			fe = dvb_attach(xc2028_attach, fe0->dvb.frontend,
 					&cfg);
 			if (fe != NULL && fe->ops.tuner_ops.set_config != NULL)
 				fe->ops.tuner_ops.set_config(fe, &ctl);
@@ -497,10 +502,10 @@ static int dvb_register(struct cx23885_tsport *port)
 	case CX23885_BOARD_LEADTEK_WINFAST_PXDVR3200_H:
 		i2c_bus = &dev->i2c_bus[0];
 
-		port->dvb.frontend = dvb_attach(zl10353_attach,
+		fe0->dvb.frontend = dvb_attach(zl10353_attach,
 			&dvico_fusionhdtv_xc3028,
 			&i2c_bus->i2c_adap);
-		if (port->dvb.frontend != NULL) {
+		if (fe0->dvb.frontend != NULL) {
 			struct dvb_frontend      *fe;
 			struct xc2028_config	  cfg = {
 				.i2c_adap  = &dev->i2c_bus[1].i2c_adap,
@@ -512,7 +517,7 @@ static int dvb_register(struct cx23885_tsport *port)
 				.demod       = XC3028_FE_ZARLINK456,
 			};
 
-			fe = dvb_attach(xc2028_attach, port->dvb.frontend,
+			fe = dvb_attach(xc2028_attach, fe0->dvb.frontend,
 				&cfg);
 			if (fe != NULL && fe->ops.tuner_ops.set_config != NULL)
 				fe->ops.tuner_ops.set_config(fe, &ctl);
@@ -523,29 +528,36 @@ static int dvb_register(struct cx23885_tsport *port)
 		       dev->name);
 		break;
 	}
-	if (NULL == port->dvb.frontend) {
+	if (NULL == fe0->dvb.frontend) {
 		printk("%s: frontend initialization failed\n", dev->name);
 		return -1;
 	}
 	/* define general-purpose callback pointer */
-	port->dvb.frontend->callback = cx23885_tuner_callback;
+	fe0->dvb.frontend->callback = cx23885_tuner_callback;
 
 	/* Put the analog decoder in standby to keep it quiet */
 	cx23885_call_i2c_clients(i2c_bus, TUNER_SET_STANDBY, NULL);
 
-	if (port->dvb.frontend->ops.analog_ops.standby)
-		port->dvb.frontend->ops.analog_ops.standby(port->dvb.frontend);
+	if (fe0->dvb.frontend->ops.analog_ops.standby)
+		fe0->dvb.frontend->ops.analog_ops.standby(fe0->dvb.frontend);
 
 	/* register everything */
-	return videobuf_dvb_register(&port->dvb, THIS_MODULE, port,
+	return videobuf_dvb_register_bus(&port->frontends, THIS_MODULE, port,
 				     &dev->pci->dev, adapter_nr);
+
 }
 
 int cx23885_dvb_register(struct cx23885_tsport *port)
 {
+
+	struct videobuf_dvb_frontend *fe0;
 	struct cx23885_dev *dev = port->dev;
 	int err;
 
+	fe0 = videobuf_dvb_get_frontend(&port->frontends, 0);
+	if (!fe0)
+		err = -EINVAL;
+
 	dprintk(1, "%s\n", __func__);
 	dprintk(1, " ->being probed by Card=%d Name=%s, PCI %02x:%02x\n",
 		dev->board,
@@ -557,7 +569,7 @@ int cx23885_dvb_register(struct cx23885_tsport *port)
 
 	/* dvb stuff */
 	printk("%s: cx23885 based dvb card\n", dev->name);
-	videobuf_queue_sg_init(&port->dvb.dvbq, &dvb_qops, &dev->pci->dev, &port->slock,
+	videobuf_queue_sg_init(&fe0->dvb.dvbq, &dvb_qops, &dev->pci->dev, &port->slock,
 			    V4L2_BUF_TYPE_VIDEO_CAPTURE, V4L2_FIELD_TOP,
 			    sizeof(struct cx23885_buffer), port);
 	err = dvb_register(port);
@@ -569,9 +581,12 @@ int cx23885_dvb_register(struct cx23885_tsport *port)
 
 int cx23885_dvb_unregister(struct cx23885_tsport *port)
 {
+	struct videobuf_dvb_frontend *fe0;
+
+	fe0 = videobuf_dvb_get_frontend(&port->frontends, 0);
 	/* dvb */
-	if(port->dvb.frontend)
-		videobuf_dvb_unregister(&port->dvb);
+	if(fe0->dvb.frontend)
+		videobuf_dvb_unregister_bus(&port->frontends);
 
 	return 0;
 }
diff --git a/drivers/media/video/cx23885/cx23885.h b/drivers/media/video/cx23885/cx23885.h
index ba4e0aaed463..aa34bf9ea4d9 100644
--- a/drivers/media/video/cx23885/cx23885.h
+++ b/drivers/media/video/cx23885/cx23885.h
@@ -225,7 +225,7 @@ struct cx23885_tsport {
 	int                        nr;
 	int                        sram_chno;
 
-	struct videobuf_dvb        dvb;
+	struct videobuf_dvb_frontends frontends;
 
 	/* dma queues */
 	struct cx23885_dmaqueue    mpegq;
diff --git a/drivers/media/video/cx88/cx88-cards.c b/drivers/media/video/cx88/cx88-cards.c
index 5da04e811ca2..638d9ec38d7f 100644
--- a/drivers/media/video/cx88/cx88-cards.c
+++ b/drivers/media/video/cx88/cx88-cards.c
@@ -1291,6 +1291,7 @@ static const struct cx88_board cx88_boards[] = {
 			.gpio0  = 0x84bf,
 		}},
 		.mpeg           = CX88_MPEG_DVB,
+		.num_frontends	= 2,
 	},
 	[CX88_BOARD_NORWOOD_MICRO] = {
 		.name           = "Norwood Micro TV Tuner",
@@ -1761,6 +1762,7 @@ static const struct cx88_board cx88_boards[] = {
 		} },
 		/* fixme: Add radio support */
 		.mpeg           = CX88_MPEG_DVB,
+		.num_frontends	= 2,
 	},
 	[CX88_BOARD_HAUPPAUGE_HVR4000LITE] = {
 		.name           = "Hauppauge WinTV-HVR4000(Lite) DVB-S/S2",
@@ -3002,12 +3004,17 @@ struct cx88_core *cx88_core_create(struct pci_dev *pci, int nr)
 		cx88_card_list(core, pci);
 	}
 
+	memset(&core->board, 0, sizeof(core->board));
 	memcpy(&core->board, &cx88_boards[core->boardnr], sizeof(core->board));
 
-	info_printk(core, "subsystem: %04x:%04x, board: %s [card=%d,%s]\n",
+	if (!core->board.num_frontends)
+		core->board.num_frontends=1;
+
+	info_printk(core, "subsystem: %04x:%04x, board: %s [card=%d,%s], frontend(s): %d\n",
 		pci->subsystem_vendor, pci->subsystem_device, core->board.name,
 		core->boardnr, card[core->nr] == core->boardnr ?
-		"insmod option" : "autodetected");
+		"insmod option" : "autodetected",
+		core->board.num_frontends);
 
 	if (tuner[core->nr] != UNSET)
 		core->board.tuner_type = tuner[core->nr];
diff --git a/drivers/media/video/cx88/cx88-dvb.c b/drivers/media/video/cx88/cx88-dvb.c
index 344ed2626e59..099de66c72c4 100644
--- a/drivers/media/video/cx88/cx88-dvb.c
+++ b/drivers/media/video/cx88/cx88-dvb.c
@@ -116,13 +116,24 @@ static int cx88_dvb_bus_ctrl(struct dvb_frontend* fe, int acquire)
 	struct cx8802_dev *dev= fe->dvb->priv;
 	struct cx8802_driver *drv = NULL;
 	int ret = 0;
+	int fe_id;
+
+	fe_id = videobuf_dvb_find_frontend(&dev->frontends, fe);
+	if (!fe_id) {
+		printk(KERN_ERR "%s() No frontend found\n", __FUNCTION__);
+		return -EINVAL;
+	}
+
 
 	drv = cx8802_get_driver(dev, CX88_MPEG_DVB);
 	if (drv) {
-		if (acquire)
+		if (acquire){
+			dev->frontends.active_fe_id = fe_id;
 			ret = drv->request_acquire(drv);
-		else
+		} else {
 			ret = drv->request_release(drv);
+			dev->frontends.active_fe_id = 0;
+		}
 	}
 
 	return ret;
@@ -396,7 +407,7 @@ static int tevii_dvbs_set_voltage(struct dvb_frontend *fe,
 			cx_write(MO_GP0_IO, 0x00006060);
 			break;
 		case SEC_VOLTAGE_OFF:
-			printk("LNB Voltage SEC_VOLTAGE_off\n");
+		   	printk("LNB Voltage SEC_VOLTAGE_off\n");
 			break;
 	}
 
@@ -483,6 +494,7 @@ static struct xc5000_config dvico_fusionhdtv7_tuner_config = {
 static int attach_xc3028(u8 addr, struct cx8802_dev *dev)
 {
 	struct dvb_frontend *fe;
+	struct videobuf_dvb_frontend *fe0 = NULL;
 	struct xc2028_ctrl ctl;
 	struct xc2028_config cfg = {
 		.i2c_adap  = &dev->core->i2c_adap,
@@ -490,7 +502,12 @@ static int attach_xc3028(u8 addr, struct cx8802_dev *dev)
 		.ctrl      = &ctl,
 	};
 
-	if (!dev->dvb.frontend) {
+/* Get the first frontend */
+	fe0 = videobuf_dvb_get_frontend(&dev->frontends, 1);
+	if (!fe0)
+		return -EINVAL;
+
+	if (!fe0->dvb.frontend) {
 		printk(KERN_ERR "%s/2: dvb frontend not attached. "
 				"Can't attach xc3028\n",
 		       dev->core->name);
@@ -504,10 +521,13 @@ static int attach_xc3028(u8 addr, struct cx8802_dev *dev)
 	 */
 	cx88_setup_xc3028(dev->core, &ctl);
 
-	fe = dvb_attach(xc2028_attach, dev->dvb.frontend, &cfg);
+	fe = dvb_attach(xc2028_attach, fe0->dvb.frontend, &cfg);
 	if (!fe) {
 		printk(KERN_ERR "%s/2: xc3028 attach failed\n",
 		       dev->core->name);
+		dvb_frontend_detach(fe0->dvb.frontend);
+		dvb_unregister_frontend(fe0->dvb.frontend);
+		fe0->dvb.frontend = NULL;
 		return -EINVAL;
 	}
 
@@ -532,8 +552,10 @@ static int cx24116_reset_device(struct dvb_frontend *fe)
 	struct cx88_core *core = dev->core;
 
 	/* Reset the part */
+	/* Put the cx24116 into reset */
 	cx_write(MO_SRST_IO, 0);
 	msleep(10);
+	/* Take the cx24116 out of reset */
 	cx_write(MO_SRST_IO, 1);
 	msleep(10);
 
@@ -573,20 +595,28 @@ static struct stv0288_config tevii_tuner_earda_config = {
 
 static int dvb_register(struct cx8802_dev *dev)
 {
+	//struct cx88_core *core = dev->core;
+
+	///* init struct videobuf_dvb */
+	//fe->dvb.name = core->name;
+	//dev->ts_gen_cntrl = 0x0c;
+
 	struct cx88_core *core = dev->core;
+	struct videobuf_dvb_frontend *fe0, *fe1 = NULL;
 
-	/* init struct videobuf_dvb */
-	dev->dvb.name = core->name;
-	dev->ts_gen_cntrl = 0x0c;
+	/* Get the first frontend */
+	fe0 = videobuf_dvb_get_frontend(&dev->frontends, 1);
+	if (!fe0)
+		return -EINVAL;
 
 	/* init frontend */
 	switch (core->boardnr) {
 	case CX88_BOARD_HAUPPAUGE_DVB_T1:
-		dev->dvb.frontend = dvb_attach(cx22702_attach,
+		fe0->dvb.frontend = dvb_attach(cx22702_attach,
 					       &connexant_refboard_config,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(dvb_pll_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(dvb_pll_attach, fe0->dvb.frontend,
 					0x61, &core->i2c_adap,
 					DVB_PLL_THOMSON_DTT759X))
 				goto frontend_detach;
@@ -596,11 +626,11 @@ static int dvb_register(struct cx8802_dev *dev)
 	case CX88_BOARD_CONEXANT_DVB_T1:
 	case CX88_BOARD_KWORLD_DVB_T_CX22702:
 	case CX88_BOARD_WINFAST_DTV1000:
-		dev->dvb.frontend = dvb_attach(cx22702_attach,
+		fe0->dvb.frontend = dvb_attach(cx22702_attach,
 					       &connexant_refboard_config,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(dvb_pll_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(dvb_pll_attach, fe0->dvb.frontend,
 					0x60, &core->i2c_adap,
 					DVB_PLL_THOMSON_DTT7579))
 				goto frontend_detach;
@@ -610,33 +640,65 @@ static int dvb_register(struct cx8802_dev *dev)
 	case CX88_BOARD_HAUPPAUGE_HVR1100:
 	case CX88_BOARD_HAUPPAUGE_HVR1100LP:
 	case CX88_BOARD_HAUPPAUGE_HVR1300:
-	case CX88_BOARD_HAUPPAUGE_HVR3000:
-		dev->dvb.frontend = dvb_attach(cx22702_attach,
+		fe0->dvb.frontend = dvb_attach(cx22702_attach,
 					       &hauppauge_hvr_config,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 				   &core->i2c_adap, 0x61,
 				   TUNER_PHILIPS_FMD1216ME_MK3))
 				goto frontend_detach;
 		}
 		break;
+	case CX88_BOARD_HAUPPAUGE_HVR3000:
+		/* DVB-S init */
+		fe0->dvb.frontend = dvb_attach(cx24123_attach,
+			       &hauppauge_novas_config,
+			       &dev->core->i2c_adap);
+		if (fe0->dvb.frontend) {
+			if (!dvb_attach(isl6421_attach, fe0->dvb.frontend,
+			&dev->core->i2c_adap, 0x08, ISL6421_DCL, 0x00)) {
+				dprintk( 1, "%s(): HVR3000 - DVB-S LNB Init: failed\n", __FUNCTION__);
+			}
+		} else {
+			dprintk( 1, "%s(): HVR3000 - DVB-S Init: failed\n", __FUNCTION__);
+		}
+		/* DVB-T init */
+		fe1 = videobuf_dvb_get_frontend(&dev->frontends, 2);
+		if (fe1) {
+			fe1->dvb.frontend = dvb_attach(cx22702_attach,
+				&hauppauge_hvr_config,
+				&dev->core->i2c_adap);
+			if (fe1->dvb.frontend) {
+				fe1->dvb.frontend->id = 1;
+				if(!dvb_attach(simple_tuner_attach, fe1->dvb.frontend,
+						&dev->core->i2c_adap, 0x61,
+						TUNER_PHILIPS_FMD1216ME_MK3)) {
+					dprintk( 1, "%s(): HVR3000 - DVB-T misc Init: failed\n", __FUNCTION__);
+				}
+			} else {
+				dprintk( 1, "%s(): HVR3000 - DVB-T Init: failed\n", __FUNCTION__);
+			}
+		} else {
+			dprintk( 1, "%s(): HVR3000 - DVB-T Init: can't find frontend 2.\n", __FUNCTION__);
+		}
+		break;
 	case CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_PLUS:
-		dev->dvb.frontend = dvb_attach(mt352_attach,
+		fe0->dvb.frontend = dvb_attach(mt352_attach,
 					       &dvico_fusionhdtv,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(dvb_pll_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(dvb_pll_attach, fe0->dvb.frontend,
 					0x60, NULL, DVB_PLL_THOMSON_DTT7579))
 				goto frontend_detach;
 			break;
 		}
 		/* ZL10353 replaces MT352 on later cards */
-		dev->dvb.frontend = dvb_attach(zl10353_attach,
+		fe0->dvb.frontend = dvb_attach(zl10353_attach,
 					       &dvico_fusionhdtv_plus_v1_1,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(dvb_pll_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(dvb_pll_attach, fe0->dvb.frontend,
 					0x60, NULL, DVB_PLL_THOMSON_DTT7579))
 				goto frontend_detach;
 		}
@@ -644,31 +706,31 @@ static int dvb_register(struct cx8802_dev *dev)
 	case CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_DUAL:
 		/* The tin box says DEE1601, but it seems to be DTT7579
 		 * compatible, with a slightly different MT352 AGC gain. */
-		dev->dvb.frontend = dvb_attach(mt352_attach,
+		fe0->dvb.frontend = dvb_attach(mt352_attach,
 					       &dvico_fusionhdtv_dual,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(dvb_pll_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(dvb_pll_attach, fe0->dvb.frontend,
 					0x61, NULL, DVB_PLL_THOMSON_DTT7579))
 				goto frontend_detach;
 			break;
 		}
 		/* ZL10353 replaces MT352 on later cards */
-		dev->dvb.frontend = dvb_attach(zl10353_attach,
+		fe0->dvb.frontend = dvb_attach(zl10353_attach,
 					       &dvico_fusionhdtv_plus_v1_1,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(dvb_pll_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(dvb_pll_attach, fe0->dvb.frontend,
 					0x61, NULL, DVB_PLL_THOMSON_DTT7579))
 				goto frontend_detach;
 		}
 		break;
 	case CX88_BOARD_DVICO_FUSIONHDTV_DVB_T1:
-		dev->dvb.frontend = dvb_attach(mt352_attach,
+		fe0->dvb.frontend = dvb_attach(mt352_attach,
 					       &dvico_fusionhdtv,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(dvb_pll_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(dvb_pll_attach, fe0->dvb.frontend,
 					0x61, NULL, DVB_PLL_LG_Z201))
 				goto frontend_detach;
 		}
@@ -676,11 +738,11 @@ static int dvb_register(struct cx8802_dev *dev)
 	case CX88_BOARD_KWORLD_DVB_T:
 	case CX88_BOARD_DNTV_LIVE_DVB_T:
 	case CX88_BOARD_ADSTECH_DVB_T_PCI:
-		dev->dvb.frontend = dvb_attach(mt352_attach,
+		fe0->dvb.frontend = dvb_attach(mt352_attach,
 					       &dntv_live_dvbt_config,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(dvb_pll_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(dvb_pll_attach, fe0->dvb.frontend,
 					0x61, NULL, DVB_PLL_UNKNOWN_1))
 				goto frontend_detach;
 		}
@@ -688,10 +750,10 @@ static int dvb_register(struct cx8802_dev *dev)
 	case CX88_BOARD_DNTV_LIVE_DVB_T_PRO:
 #if defined(CONFIG_VIDEO_CX88_VP3054) || (defined(CONFIG_VIDEO_CX88_VP3054_MODULE) && defined(MODULE))
 		/* MT352 is on a secondary I2C bus made from some GPIO lines */
-		dev->dvb.frontend = dvb_attach(mt352_attach, &dntv_live_dvbt_pro_config,
+		fe0->dvb.frontend = dvb_attach(mt352_attach, &dntv_live_dvbt_pro_config,
 					       &dev->vp3054->adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 					&core->i2c_adap, 0x61,
 					TUNER_PHILIPS_FMD1216ME_MK3))
 				goto frontend_detach;
@@ -702,22 +764,22 @@ static int dvb_register(struct cx8802_dev *dev)
 #endif
 		break;
 	case CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_HYBRID:
-		dev->dvb.frontend = dvb_attach(zl10353_attach,
+		fe0->dvb.frontend = dvb_attach(zl10353_attach,
 					       &dvico_fusionhdtv_hybrid,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 				   &core->i2c_adap, 0x61,
 				   TUNER_THOMSON_FE6600))
 				goto frontend_detach;
 		}
 		break;
 	case CX88_BOARD_DVICO_FUSIONHDTV_DVB_T_PRO:
-		dev->dvb.frontend = dvb_attach(zl10353_attach,
+		fe0->dvb.frontend = dvb_attach(zl10353_attach,
 					       &dvico_fusionhdtv_xc3028,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend == NULL)
-			dev->dvb.frontend = dvb_attach(mt352_attach,
+		if (fe0->dvb.frontend == NULL)
+			fe0->dvb.frontend = dvb_attach(mt352_attach,
 						&dvico_fusionhdtv_mt352_xc3028,
 						&core->i2c_adap);
 		/*
@@ -725,16 +787,16 @@ static int dvb_register(struct cx8802_dev *dev)
 		 * We must not permit gate_ctrl to be performed, or
 		 * the xc3028 cannot communicate on the bus.
 		 */
-		if (dev->dvb.frontend)
-			dev->dvb.frontend->ops.i2c_gate_ctrl = NULL;
+		if (fe0->dvb.frontend)
+			fe0->dvb.frontend->ops.i2c_gate_ctrl = NULL;
 		if (attach_xc3028(0x61, dev) < 0)
 			return -EINVAL;
 		break;
 	case CX88_BOARD_PCHDTV_HD3000:
-		dev->dvb.frontend = dvb_attach(or51132_attach, &pchdtv_hd3000,
+		fe0->dvb.frontend = dvb_attach(or51132_attach, &pchdtv_hd3000,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 					&core->i2c_adap, 0x61,
 					TUNER_THOMSON_DTT761X))
 				goto frontend_detach;
@@ -751,11 +813,11 @@ static int dvb_register(struct cx8802_dev *dev)
 
 		/* Select RF connector callback */
 		fusionhdtv_3_gold.pll_rf_set = lgdt330x_pll_rf_set;
-		dev->dvb.frontend = dvb_attach(lgdt330x_attach,
+		fe0->dvb.frontend = dvb_attach(lgdt330x_attach,
 					       &fusionhdtv_3_gold,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 					&core->i2c_adap, 0x61,
 					TUNER_MICROTUNE_4042FI5))
 				goto frontend_detach;
@@ -769,11 +831,11 @@ static int dvb_register(struct cx8802_dev *dev)
 		mdelay(100);
 		cx_set(MO_GP0_IO, 9);
 		mdelay(200);
-		dev->dvb.frontend = dvb_attach(lgdt330x_attach,
+		fe0->dvb.frontend = dvb_attach(lgdt330x_attach,
 					       &fusionhdtv_3_gold,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 					&core->i2c_adap, 0x61,
 					TUNER_THOMSON_DTT761X))
 				goto frontend_detach;
@@ -787,15 +849,15 @@ static int dvb_register(struct cx8802_dev *dev)
 		mdelay(100);
 		cx_set(MO_GP0_IO, 1);
 		mdelay(200);
-		dev->dvb.frontend = dvb_attach(lgdt330x_attach,
+		fe0->dvb.frontend = dvb_attach(lgdt330x_attach,
 					       &fusionhdtv_5_gold,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 					&core->i2c_adap, 0x61,
 					TUNER_LG_TDVS_H06XF))
 				goto frontend_detach;
-			if (!dvb_attach(tda9887_attach, dev->dvb.frontend,
+			if (!dvb_attach(tda9887_attach, fe0->dvb.frontend,
 				   &core->i2c_adap, 0x43))
 				goto frontend_detach;
 		}
@@ -808,25 +870,25 @@ static int dvb_register(struct cx8802_dev *dev)
 		mdelay(100);
 		cx_set(MO_GP0_IO, 1);
 		mdelay(200);
-		dev->dvb.frontend = dvb_attach(lgdt330x_attach,
+		fe0->dvb.frontend = dvb_attach(lgdt330x_attach,
 					       &pchdtv_hd5500,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 					&core->i2c_adap, 0x61,
 					TUNER_LG_TDVS_H06XF))
 				goto frontend_detach;
-			if (!dvb_attach(tda9887_attach, dev->dvb.frontend,
+			if (!dvb_attach(tda9887_attach, fe0->dvb.frontend,
 				   &core->i2c_adap, 0x43))
 				goto frontend_detach;
 		}
 		break;
 	case CX88_BOARD_ATI_HDTVWONDER:
-		dev->dvb.frontend = dvb_attach(nxt200x_attach,
+		fe0->dvb.frontend = dvb_attach(nxt200x_attach,
 					       &ati_hdtvwonder,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 					&core->i2c_adap, 0x61,
 					TUNER_PHILIPS_TUV1236D))
 				goto frontend_detach;
@@ -834,49 +896,49 @@ static int dvb_register(struct cx8802_dev *dev)
 		break;
 	case CX88_BOARD_HAUPPAUGE_NOVASPLUS_S1:
 	case CX88_BOARD_HAUPPAUGE_NOVASE2_S1:
-		dev->dvb.frontend = dvb_attach(cx24123_attach,
+		fe0->dvb.frontend = dvb_attach(cx24123_attach,
 					       &hauppauge_novas_config,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend) {
-			if (!dvb_attach(isl6421_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend) {
+			if (!dvb_attach(isl6421_attach, fe0->dvb.frontend,
 					&core->i2c_adap, 0x08, ISL6421_DCL, 0x00))
 				goto frontend_detach;
 		}
 		break;
 	case CX88_BOARD_KWORLD_DVBS_100:
-		dev->dvb.frontend = dvb_attach(cx24123_attach,
+		fe0->dvb.frontend = dvb_attach(cx24123_attach,
 					       &kworld_dvbs_100_config,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend) {
-			core->prev_set_voltage = dev->dvb.frontend->ops.set_voltage;
-			dev->dvb.frontend->ops.set_voltage = kworld_dvbs_100_set_voltage;
+		if (fe0->dvb.frontend) {
+			core->prev_set_voltage = fe0->dvb.frontend->ops.set_voltage;
+			fe0->dvb.frontend->ops.set_voltage = kworld_dvbs_100_set_voltage;
 		}
 		break;
 	case CX88_BOARD_GENIATECH_DVBS:
-		dev->dvb.frontend = dvb_attach(cx24123_attach,
+		fe0->dvb.frontend = dvb_attach(cx24123_attach,
 					       &geniatech_dvbs_config,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend) {
-			core->prev_set_voltage = dev->dvb.frontend->ops.set_voltage;
-			dev->dvb.frontend->ops.set_voltage = geniatech_dvbs_set_voltage;
+		if (fe0->dvb.frontend) {
+			core->prev_set_voltage = fe0->dvb.frontend->ops.set_voltage;
+			fe0->dvb.frontend->ops.set_voltage = geniatech_dvbs_set_voltage;
 		}
 		break;
 	case CX88_BOARD_PINNACLE_PCTV_HD_800i:
-		dev->dvb.frontend = dvb_attach(s5h1409_attach,
+		fe0->dvb.frontend = dvb_attach(s5h1409_attach,
 					       &pinnacle_pctv_hd_800i_config,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(xc5000_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(xc5000_attach, fe0->dvb.frontend,
 					&core->i2c_adap,
 					&pinnacle_pctv_hd_800i_tuner_config))
 				goto frontend_detach;
 		}
 		break;
 	case CX88_BOARD_DVICO_FUSIONHDTV_5_PCI_NANO:
-		dev->dvb.frontend = dvb_attach(s5h1409_attach,
+		fe0->dvb.frontend = dvb_attach(s5h1409_attach,
 						&dvico_hdtv5_pci_nano_config,
 						&core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
+		if (fe0->dvb.frontend != NULL) {
 			struct dvb_frontend *fe;
 			struct xc2028_config cfg = {
 				.i2c_adap  = &core->i2c_adap,
@@ -889,17 +951,17 @@ static int dvb_register(struct cx8802_dev *dev)
 			};
 
 			fe = dvb_attach(xc2028_attach,
-					dev->dvb.frontend, &cfg);
+					fe0->dvb.frontend, &cfg);
 			if (fe != NULL && fe->ops.tuner_ops.set_config != NULL)
 				fe->ops.tuner_ops.set_config(fe, &ctl);
 		}
 		break;
 	 case CX88_BOARD_PINNACLE_HYBRID_PCTV:
-		dev->dvb.frontend = dvb_attach(zl10353_attach,
+		fe0->dvb.frontend = dvb_attach(zl10353_attach,
 					       &cx88_pinnacle_hybrid_pctv,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend) {
-			dev->dvb.frontend->ops.i2c_gate_ctrl = NULL;
+		if (fe0->dvb.frontend) {
+			fe0->dvb.frontend->ops.i2c_gate_ctrl = NULL;
 			if (attach_xc3028(0x61, dev) < 0)
 				goto frontend_detach;
 		}
@@ -907,85 +969,116 @@ static int dvb_register(struct cx8802_dev *dev)
 	 case CX88_BOARD_GENIATECH_X8000_MT:
 		dev->ts_gen_cntrl = 0x00;
 
-		dev->dvb.frontend = dvb_attach(zl10353_attach,
+		fe0->dvb.frontend = dvb_attach(zl10353_attach,
 					       &cx88_geniatech_x8000_mt,
 					       &core->i2c_adap);
 		if (attach_xc3028(0x61, dev) < 0)
 			goto frontend_detach;
 		break;
 	 case CX88_BOARD_KWORLD_ATSC_120:
-		dev->dvb.frontend = dvb_attach(s5h1409_attach,
+		fe0->dvb.frontend = dvb_attach(s5h1409_attach,
 					       &kworld_atsc_120_config,
 					       &core->i2c_adap);
 		if (attach_xc3028(0x61, dev) < 0)
 			goto frontend_detach;
 		break;
 	case CX88_BOARD_DVICO_FUSIONHDTV_7_GOLD:
-		dev->dvb.frontend = dvb_attach(s5h1411_attach,
+		fe0->dvb.frontend = dvb_attach(s5h1411_attach,
 					       &dvico_fusionhdtv7_config,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(xc5000_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(xc5000_attach, fe0->dvb.frontend,
 					&core->i2c_adap,
 					&dvico_fusionhdtv7_tuner_config))
 				goto frontend_detach;
 		}
 		break;
 	case CX88_BOARD_HAUPPAUGE_HVR4000:
+		/* DVB-S/S2 Init */
+		fe0->dvb.frontend = dvb_attach(cx24116_attach,
+			&hauppauge_hvr4000_config,
+			&dev->core->i2c_adap);
+		if (fe0->dvb.frontend) {
+			if(!dvb_attach(isl6421_attach, fe0->dvb.frontend,
+				&dev->core->i2c_adap, 0x08, ISL6421_DCL, 0x00)) {
+				dprintk( 1, "%s(): HVR4000 - DVB-S LNB Init: failed\n", __FUNCTION__);
+			}
+		} else {
+			dprintk( 1, "%s(): HVR4000 - DVB-S Init: failed\n", __FUNCTION__);
+		}
+		/* DVB-T Init */
+		fe1 = videobuf_dvb_get_frontend(&dev->frontends, 2);
+		if (fe1) {
+			fe1->dvb.frontend = dvb_attach(cx22702_attach,
+				&hauppauge_hvr_config,
+				&dev->core->i2c_adap);
+			if (fe1->dvb.frontend) {
+				fe1->dvb.frontend->id = 1;
+				if(!dvb_attach(simple_tuner_attach, fe1->dvb.frontend,
+					&dev->core->i2c_adap, 0x61,
+					TUNER_PHILIPS_FMD1216ME_MK3)) {
+					dprintk( 1, "%s(): HVR4000 - DVB-T misc Init: failed\n", __FUNCTION__);
+				}
+			} else {
+				dprintk( 1, "%s(): HVR4000 - DVB-T Init: failed\n", __FUNCTION__);
+			}
+		} else {
+			dprintk( 1, "%s(): HVR4000 - DVB-T Init: can't find frontend 2.\n", __FUNCTION__);
+		}
+		break;
 	case CX88_BOARD_HAUPPAUGE_HVR4000LITE:
-		/* Support for DVB-S only, not DVB-T support */
-		dev->dvb.frontend = dvb_attach(cx24116_attach,
+		fe0->dvb.frontend = dvb_attach(cx24116_attach,
 			&hauppauge_hvr4000_config,
 			&dev->core->i2c_adap);
-		if (dev->dvb.frontend) {
-			dvb_attach(isl6421_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend) {
+			dvb_attach(isl6421_attach, fe0->dvb.frontend,
 				&dev->core->i2c_adap,
 				0x08, ISL6421_DCL, 0x00);
 		}
 		break;
 	case CX88_BOARD_TEVII_S420:
-		dev->dvb.frontend = dvb_attach(stv0299_attach,
+		fe0->dvb.frontend = dvb_attach(stv0299_attach,
 						&tevii_tuner_sharp_config,
 						&core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			if (!dvb_attach(dvb_pll_attach, dev->dvb.frontend, 0x60,
+		if (fe0->dvb.frontend != NULL) {
+			if (!dvb_attach(dvb_pll_attach, fe0->dvb.frontend, 0x60,
 					&core->i2c_adap, DVB_PLL_OPERA1))
 				goto frontend_detach;
-			core->prev_set_voltage = dev->dvb.frontend->ops.set_voltage;
-			dev->dvb.frontend->ops.set_voltage = tevii_dvbs_set_voltage;
+			core->prev_set_voltage = fe0->dvb.frontend->ops.set_voltage;
+			fe0->dvb.frontend->ops.set_voltage = tevii_dvbs_set_voltage;
 
 		} else {
-			dev->dvb.frontend = dvb_attach(stv0288_attach,
+			fe0->dvb.frontend = dvb_attach(stv0288_attach,
 							    &tevii_tuner_earda_config,
 							    &core->i2c_adap);
-				if (dev->dvb.frontend != NULL) {
-					if (!dvb_attach(stb6000_attach, dev->dvb.frontend, 0x61,
+				if (fe0->dvb.frontend != NULL) {
+					if (!dvb_attach(stb6000_attach, fe0->dvb.frontend, 0x61,
 						&core->i2c_adap))
 					goto frontend_detach;
-				core->prev_set_voltage = dev->dvb.frontend->ops.set_voltage;
-				dev->dvb.frontend->ops.set_voltage = tevii_dvbs_set_voltage;
+				core->prev_set_voltage = fe0->dvb.frontend->ops.set_voltage;
+				fe0->dvb.frontend->ops.set_voltage = tevii_dvbs_set_voltage;
 
 			}
 		}
 		break;
 	case CX88_BOARD_TEVII_S460:
-		dev->dvb.frontend = dvb_attach(cx24116_attach,
+		fe0->dvb.frontend = dvb_attach(cx24116_attach,
 					       &tevii_s460_config,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			core->prev_set_voltage = dev->dvb.frontend->ops.set_voltage;
-			dev->dvb.frontend->ops.set_voltage = tevii_dvbs_set_voltage;
+		if (fe0->dvb.frontend != NULL) {
+			core->prev_set_voltage = fe0->dvb.frontend->ops.set_voltage;
+			fe0->dvb.frontend->ops.set_voltage = tevii_dvbs_set_voltage;
 		}
 		break;
 	case CX88_BOARD_OMICOM_SS4_PCI:
 	case CX88_BOARD_TBS_8920:
 	case CX88_BOARD_PROF_7300:
-		dev->dvb.frontend = dvb_attach(cx24116_attach,
+		fe0->dvb.frontend = dvb_attach(cx24116_attach,
 					       &hauppauge_hvr4000_config,
 					       &core->i2c_adap);
-		if (dev->dvb.frontend != NULL) {
-			core->prev_set_voltage = dev->dvb.frontend->ops.set_voltage;
-			dev->dvb.frontend->ops.set_voltage = tevii_dvbs_set_voltage;
+		if (fe0->dvb.frontend != NULL) {
+			core->prev_set_voltage = fe0->dvb.frontend->ops.set_voltage;
+			fe0->dvb.frontend->ops.set_voltage = tevii_dvbs_set_voltage;
 		}
 		break;
 	default:
@@ -993,29 +1086,32 @@ static int dvb_register(struct cx8802_dev *dev)
 		       core->name);
 		break;
 	}
-	if (NULL == dev->dvb.frontend) {
+
+        if ( (NULL == fe0->dvb.frontend) || (fe1 && NULL == fe1->dvb.frontend) ) {
 		printk(KERN_ERR
 		       "%s/2: frontend initialization failed\n",
 		       core->name);
 		return -EINVAL;
 	}
 	/* define general-purpose callback pointer */
-	dev->dvb.frontend->callback = cx88_tuner_callback;
+	fe0->dvb.frontend->callback = cx88_tuner_callback;
 
 	/* Ensure all frontends negotiate bus access */
-	dev->dvb.frontend->ops.ts_bus_ctrl = cx88_dvb_bus_ctrl;
+	fe0->dvb.frontend->ops.ts_bus_ctrl = cx88_dvb_bus_ctrl;
+	if (fe1)
+		fe1->dvb.frontend->ops.ts_bus_ctrl = cx88_dvb_bus_ctrl;
 
 	/* Put the analog decoder in standby to keep it quiet */
 	cx88_call_i2c_clients(core, TUNER_SET_STANDBY, NULL);
 
 	/* register everything */
-	return videobuf_dvb_register(&dev->dvb, THIS_MODULE, dev,
-				     &dev->pci->dev, adapter_nr);
+	return videobuf_dvb_register_bus(&dev->frontends, THIS_MODULE, dev,
+		&dev->pci->dev, adapter_nr);
 
 frontend_detach:
-	if (dev->dvb.frontend) {
-		dvb_frontend_detach(dev->dvb.frontend);
-		dev->dvb.frontend = NULL;
+	if (fe0->dvb.frontend) {
+		dvb_frontend_detach(fe0->dvb.frontend);
+		fe0->dvb.frontend = NULL;
 	}
 	return -EINVAL;
 }
@@ -1039,6 +1135,66 @@ static int cx8802_dvb_advise_acquire(struct cx8802_driver *drv)
 		cx_clear(MO_GP0_IO, 0x00000004);
 		udelay(1000);
 		break;
+
+	case CX88_BOARD_HAUPPAUGE_HVR3000: /* ? */
+		if(core->dvbdev->frontends.active_fe_id == 1) {
+			/* DVB-S/S2 Enabled */
+
+			/* Toggle reset on cx22702 leaving i2c active */
+			cx_write(MO_GP0_IO, core->board.input[0].gpio0);
+			udelay(1000);
+			cx_clear(MO_GP0_IO, 0x00000080);
+			udelay(50);
+			cx_set(MO_GP0_IO, 0x00000080); /* cx22702 out of reset */
+			cx_set(MO_GP0_IO, 0x00000004); /* tri-state the cx22702 pins */
+			udelay(1000);
+
+			cx_write(MO_SRST_IO, 1); /* Take the cx24116/cx24123 out of reset */
+			core->dvbdev->ts_gen_cntrl = 0x02; /* Parallel IO */
+		} else
+		if (core->dvbdev->frontends.active_fe_id == 2) {
+			/* DVB-T Enabled */
+
+			/* Put the cx24116/cx24123 into reset */
+			cx_write(MO_SRST_IO, 0);
+
+			/* cx22702 out of reset and enable it */
+			cx_set(MO_GP0_IO,   0x00000080);
+			cx_clear(MO_GP0_IO, 0x00000004);
+			core->dvbdev->ts_gen_cntrl = 0x0c; /* Serial IO */
+			udelay(1000);
+		}
+		break;
+	case CX88_BOARD_HAUPPAUGE_HVR4000:
+		if(core->dvbdev->frontends.active_fe_id == 1) {
+			/* DVB-S/S2 Enabled */
+
+			/* Toggle reset on cx22702 leaving i2c active */
+			cx_write(MO_GP0_IO, (core->board.input[0].gpio0 & 0x0000ff00) | 0x00000080);
+			udelay(1000);
+			cx_clear(MO_GP0_IO, 0x00000080);
+			udelay(50);
+			cx_set(MO_GP0_IO, 0x00000080); /* cx22702 out of reset */
+			cx_set(MO_GP0_IO, 0x00000004); /* tri-state the cx22702 pins */
+			udelay(1000);
+
+			cx_write(MO_SRST_IO, 1); /* Take the cx24116/cx24123 out of reset */
+			core->dvbdev->ts_gen_cntrl = 0x02; /* Parallel IO */
+		} else
+		if (core->dvbdev->frontends.active_fe_id == 2) {
+			/* DVB-T Enabled */
+
+			/* Put the cx24116/cx24123 into reset */
+			cx_write(MO_SRST_IO, 0);
+
+			/* cx22702 out of reset and enable it */
+			cx_set(MO_GP0_IO,   0x00000080);
+			cx_clear(MO_GP0_IO, 0x00000004);
+			core->dvbdev->ts_gen_cntrl = 0x0c; /* Serial IO */
+			udelay(1000);
+		}
+		break;
+
 	default:
 		err = -ENODEV;
 	}
@@ -1056,6 +1212,9 @@ static int cx8802_dvb_advise_release(struct cx8802_driver *drv)
 	case CX88_BOARD_HAUPPAUGE_HVR1300:
 		/* Do Nothing, leave the cx22702 on the bus. */
 		break;
+	case CX88_BOARD_HAUPPAUGE_HVR3000:
+	case CX88_BOARD_HAUPPAUGE_HVR4000:
+		break;
 	default:
 		err = -ENODEV;
 	}
@@ -1066,7 +1225,8 @@ static int cx8802_dvb_probe(struct cx8802_driver *drv)
 {
 	struct cx88_core *core = drv->core;
 	struct cx8802_dev *dev = drv->core->dvbdev;
-	int err;
+	int err,i;
+	struct videobuf_dvb_frontend *fe;
 
 	dprintk( 1, "%s\n", __func__);
 	dprintk( 1, " ->being probed by Card=%d Name=%s, PCI %02x:%02x\n",
@@ -1086,12 +1246,23 @@ static int cx8802_dvb_probe(struct cx8802_driver *drv)
 
 	/* dvb stuff */
 	printk(KERN_INFO "%s/2: cx2388x based DVB/ATSC card\n", core->name);
-	videobuf_queue_sg_init(&dev->dvb.dvbq, &dvb_qops,
+	dev->ts_gen_cntrl = 0x0c;
+
+	for (i = 1; i <= core->board.num_frontends; i++) {
+		fe = videobuf_dvb_get_frontend(&core->dvbdev->frontends, i);
+		if (!fe) {
+			printk(KERN_ERR "%s() failed to get frontend(%d)\n", __FUNCTION__, i);
+			continue;
+		}
+		videobuf_queue_sg_init(&fe->dvb.dvbq, &dvb_qops,
 			    &dev->pci->dev, &dev->slock,
 			    V4L2_BUF_TYPE_VIDEO_CAPTURE,
 			    V4L2_FIELD_TOP,
 			    sizeof(struct cx88_buffer),
 			    dev);
+		/* init struct videobuf_dvb */
+		fe->dvb.name = dev->core->name;
+	}
 	err = dvb_register(dev);
 	if (err != 0)
 		printk(KERN_ERR "%s/2: dvb_register failed (err = %d)\n",
@@ -1105,9 +1276,7 @@ static int cx8802_dvb_remove(struct cx8802_driver *drv)
 {
 	struct cx8802_dev *dev = drv->core->dvbdev;
 
-	/* dvb */
-	if (dev->dvb.frontend)
-		videobuf_dvb_unregister(&dev->dvb);
+	videobuf_dvb_unregister_bus(&dev->frontends);
 
 	vp3054_i2c_remove(dev);
 
diff --git a/drivers/media/video/cx88/cx88-i2c.c b/drivers/media/video/cx88/cx88-i2c.c
index 8e74d64fdcd2..582769de26b5 100644
--- a/drivers/media/video/cx88/cx88-i2c.c
+++ b/drivers/media/video/cx88/cx88-i2c.c
@@ -116,18 +116,23 @@ static int detach_inform(struct i2c_client *client)
 
 void cx88_call_i2c_clients(struct cx88_core *core, unsigned int cmd, void *arg)
 {
+	struct videobuf_dvb_frontend *fe0 = NULL;
 	if (0 != core->i2c_rc)
 		return;
 
 #if defined(CONFIG_VIDEO_CX88_DVB) || defined(CONFIG_VIDEO_CX88_DVB_MODULE)
-	if ( (core->dvbdev) && (core->dvbdev->dvb.frontend) ) {
-		if (core->dvbdev->dvb.frontend->ops.i2c_gate_ctrl)
-			core->dvbdev->dvb.frontend->ops.i2c_gate_ctrl(core->dvbdev->dvb.frontend, 1);
+	if (core->dvbdev) {
+		/* Get the first frontend and assume that all I2C is routed through it */
+		/* TODO: Get _THIS_FE_ then find the right i2c_gate_ctrl for it */
+		fe0 = videobuf_dvb_get_frontend(&core->dvbdev->frontends, 1);
+
+		if (fe0 && fe0->dvb.frontend && fe0->dvb.frontend->ops.i2c_gate_ctrl)
+			fe0->dvb.frontend->ops.i2c_gate_ctrl(fe0->dvb.frontend, 1);
 
 		i2c_clients_command(&core->i2c_adap, cmd, arg);
 
-		if (core->dvbdev->dvb.frontend->ops.i2c_gate_ctrl)
-			core->dvbdev->dvb.frontend->ops.i2c_gate_ctrl(core->dvbdev->dvb.frontend, 0);
+		if (fe0 && fe0->dvb.frontend && fe0->dvb.frontend->ops.i2c_gate_ctrl)
+			fe0->dvb.frontend->ops.i2c_gate_ctrl(fe0->dvb.frontend, 0);
 	} else
 #endif
 		i2c_clients_command(&core->i2c_adap, cmd, arg);
diff --git a/drivers/media/video/cx88/cx88-input.c b/drivers/media/video/cx88/cx88-input.c
index 8683d104de72..17150cb88c80 100644
--- a/drivers/media/video/cx88/cx88-input.c
+++ b/drivers/media/video/cx88/cx88-input.c
@@ -495,6 +495,7 @@ void cx88_ir_irq(struct cx88_core *core)
 	case CX88_BOARD_PINNACLE_PCTV_HD_800i:
 		ircode = ir_decode_biphase(ir->samples, ir->scount, 5, 7);
 		ir_dprintk("biphase decoded: %x\n", ircode);
+//TODO Darron has other code here
 		if ((ircode & 0xfffff000) != 0x3000)
 			break;
 		ir_input_keydown(ir->input, &ir->ir, ircode & 0x3f, ircode);
diff --git a/drivers/media/video/cx88/cx88-mpeg.c b/drivers/media/video/cx88/cx88-mpeg.c
index a6b061c2644a..22c2a88fbf1c 100644
--- a/drivers/media/video/cx88/cx88-mpeg.c
+++ b/drivers/media/video/cx88/cx88-mpeg.c
@@ -768,7 +768,8 @@ static int __devinit cx8802_probe(struct pci_dev *pci_dev,
 {
 	struct cx8802_dev *dev;
 	struct cx88_core  *core;
-	int err;
+	struct videobuf_dvb_frontend *demod;
+	int err,i;
 
 	/* general setup */
 	core = cx88_core_get(pci_dev);
@@ -781,6 +782,11 @@ static int __devinit cx8802_probe(struct pci_dev *pci_dev,
 	if (!core->board.mpeg)
 		goto fail_core;
 
+	if (!core->board.num_frontends) {
+		printk(KERN_ERR "%s() .num_frontends should be non-zero, err = %d\n", __FUNCTION__, err);
+		goto fail_core;
+	}
+
 	err = -ENOMEM;
 	dev = kzalloc(sizeof(*dev),GFP_KERNEL);
 	if (NULL == dev)
@@ -795,6 +801,20 @@ static int __devinit cx8802_probe(struct pci_dev *pci_dev,
 	INIT_LIST_HEAD(&dev->drvlist);
 	list_add_tail(&dev->devlist,&cx8802_devlist);
 
+	mutex_init(&dev->frontends.lock);
+	INIT_LIST_HEAD(&dev->frontends.frontend.felist);
+
+	printk(KERN_INFO "%s() allocating %d frontend(s)\n", __FUNCTION__, core->board.num_frontends);
+
+	for (i = 1; i <= core->board.num_frontends; i++) {
+		demod = videobuf_dvb_alloc_frontend(dev, &dev->frontends, i);
+		if(demod == NULL) {
+			printk(KERN_ERR "%s() failed to alloc\n", __FUNCTION__);
+			err = -ENOMEM;
+			goto fail_free;
+		}
+	}
+
 	/* Maintain a reference so cx88-video can query the 8802 device. */
 	core->dvbdev = dev;
 
diff --git a/drivers/media/video/cx88/cx88.h b/drivers/media/video/cx88/cx88.h
index dbf01b8b57a5..063f7b57e42a 100644
--- a/drivers/media/video/cx88/cx88.h
+++ b/drivers/media/video/cx88/cx88.h
@@ -261,6 +261,7 @@ struct cx88_board {
 	struct cx88_input       radio;
 	enum cx88_board_type    mpeg;
 	unsigned int            audio_chip;
+	int			num_frontends;
 };
 
 struct cx88_subid {
@@ -356,6 +357,7 @@ struct cx88_core {
 	struct cx8802_dev          *dvbdev;
 	enum cx88_board_type       active_type_id;
 	int			   active_ref;
+	int			   active_fe_id;
 };
 
 struct cx8800_dev;
@@ -490,7 +492,7 @@ struct cx8802_dev {
 
 #if defined(CONFIG_VIDEO_CX88_DVB) || defined(CONFIG_VIDEO_CX88_DVB_MODULE)
 	/* for dvb only */
-	struct videobuf_dvb        dvb;
+	struct videobuf_dvb_frontends frontends;
 #endif
 
 #if defined(CONFIG_VIDEO_CX88_VP3054) || \
diff --git a/drivers/media/video/saa7134/saa7134-dvb.c b/drivers/media/video/saa7134/saa7134-dvb.c
index 87c10983266f..8ada0497fa03 100644
--- a/drivers/media/video/saa7134/saa7134-dvb.c
+++ b/drivers/media/video/saa7134/saa7134-dvb.c
@@ -535,11 +535,15 @@ static int configure_tda827x_fe(struct saa7134_dev *dev,
 				struct tda1004x_config *cdec_conf,
 				struct tda827x_config *tuner_conf)
 {
-	dev->dvb.frontend = dvb_attach(tda10046_attach, cdec_conf, &dev->i2c_adap);
-	if (dev->dvb.frontend) {
+	struct videobuf_dvb_frontend *fe0;
+
+	fe0 = videobuf_dvb_get_frontend(&dev->frontends, 0);
+
+	fe0->dvb.frontend = dvb_attach(tda10046_attach, cdec_conf, &dev->i2c_adap);
+	if (fe0->dvb.frontend) {
 		if (cdec_conf->i2c_gate)
-			dev->dvb.frontend->ops.i2c_gate_ctrl = tda8290_i2c_gate_ctrl;
-		if (dvb_attach(tda827x_attach, dev->dvb.frontend,
+			fe0->dvb.frontend->ops.i2c_gate_ctrl = tda8290_i2c_gate_ctrl;
+		if (dvb_attach(tda827x_attach, fe0->dvb.frontend,
 			       cdec_conf->tuner_address,
 			       &dev->i2c_adap, tuner_conf))
 			return 0;
@@ -944,12 +948,18 @@ static int dvb_init(struct saa7134_dev *dev)
 {
 	int ret;
 	int attach_xc3028 = 0;
+	struct videobuf_dvb_frontend *fe0;
+
+	/* Get the first frontend */
+	fe0 = videobuf_dvb_get_frontend(&dev->frontends, 0);
+	if (!fe0)
+		return -EINVAL;
 
 	/* init struct videobuf_dvb */
 	dev->ts.nr_bufs    = 32;
 	dev->ts.nr_packets = 32*4;
-	dev->dvb.name = dev->name;
-	videobuf_queue_sg_init(&dev->dvb.dvbq, &saa7134_ts_qops,
+	fe0->dvb.name = dev->name;
+	videobuf_queue_sg_init(&fe0->dvb.dvbq, &saa7134_ts_qops,
 			    &dev->pci->dev, &dev->slock,
 			    V4L2_BUF_TYPE_VIDEO_CAPTURE,
 			    V4L2_FIELD_ALTERNATE,
@@ -959,47 +969,47 @@ static int dvb_init(struct saa7134_dev *dev)
 	switch (dev->board) {
 	case SAA7134_BOARD_PINNACLE_300I_DVBT_PAL:
 		dprintk("pinnacle 300i dvb setup\n");
-		dev->dvb.frontend = dvb_attach(mt352_attach, &pinnacle_300i,
+		fe0->dvb.frontend = dvb_attach(mt352_attach, &pinnacle_300i,
 					       &dev->i2c_adap);
-		if (dev->dvb.frontend) {
-			dev->dvb.frontend->ops.tuner_ops.set_params = mt352_pinnacle_tuner_set_params;
+		if (fe0->dvb.frontend) {
+			fe0->dvb.frontend->ops.tuner_ops.set_params = mt352_pinnacle_tuner_set_params;
 		}
 		break;
 	case SAA7134_BOARD_AVERMEDIA_777:
 	case SAA7134_BOARD_AVERMEDIA_A16AR:
 		dprintk("avertv 777 dvb setup\n");
-		dev->dvb.frontend = dvb_attach(mt352_attach, &avermedia_777,
+		fe0->dvb.frontend = dvb_attach(mt352_attach, &avermedia_777,
 					       &dev->i2c_adap);
-		if (dev->dvb.frontend) {
-			dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend) {
+			dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 				   &dev->i2c_adap, 0x61,
 				   TUNER_PHILIPS_TD1316);
 		}
 		break;
 	case SAA7134_BOARD_AVERMEDIA_A16D:
 		dprintk("AverMedia A16D dvb setup\n");
-		dev->dvb.frontend = dvb_attach(mt352_attach,
+		fe0->dvb.frontend = dvb_attach(mt352_attach,
 						&avermedia_xc3028_mt352_dev,
 						&dev->i2c_adap);
 		attach_xc3028 = 1;
 		break;
 	case SAA7134_BOARD_MD7134:
-		dev->dvb.frontend = dvb_attach(tda10046_attach,
+		fe0->dvb.frontend = dvb_attach(tda10046_attach,
 					       &medion_cardbus,
 					       &dev->i2c_adap);
-		if (dev->dvb.frontend) {
-			dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend) {
+			dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 				   &dev->i2c_adap, medion_cardbus.tuner_address,
 				   TUNER_PHILIPS_FMD1216ME_MK3);
 		}
 		break;
 	case SAA7134_BOARD_PHILIPS_TOUGH:
-		dev->dvb.frontend = dvb_attach(tda10046_attach,
+		fe0->dvb.frontend = dvb_attach(tda10046_attach,
 					       &philips_tu1216_60_config,
 					       &dev->i2c_adap);
-		if (dev->dvb.frontend) {
-			dev->dvb.frontend->ops.tuner_ops.init = philips_tu1216_init;
-			dev->dvb.frontend->ops.tuner_ops.set_params = philips_tda6651_pll_set;
+		if (fe0->dvb.frontend) {
+			fe0->dvb.frontend->ops.tuner_ops.init = philips_tu1216_init;
+			fe0->dvb.frontend->ops.tuner_ops.set_params = philips_tda6651_pll_set;
 		}
 		break;
 	case SAA7134_BOARD_FLYDVBTDUO:
@@ -1010,24 +1020,24 @@ static int dvb_init(struct saa7134_dev *dev)
 		break;
 	case SAA7134_BOARD_PHILIPS_EUROPA:
 	case SAA7134_BOARD_VIDEOMATE_DVBT_300:
-		dev->dvb.frontend = dvb_attach(tda10046_attach,
+		fe0->dvb.frontend = dvb_attach(tda10046_attach,
 					       &philips_europa_config,
 					       &dev->i2c_adap);
-		if (dev->dvb.frontend) {
-			dev->original_demod_sleep = dev->dvb.frontend->ops.sleep;
-			dev->dvb.frontend->ops.sleep = philips_europa_demod_sleep;
-			dev->dvb.frontend->ops.tuner_ops.init = philips_europa_tuner_init;
-			dev->dvb.frontend->ops.tuner_ops.sleep = philips_europa_tuner_sleep;
-			dev->dvb.frontend->ops.tuner_ops.set_params = philips_td1316_tuner_set_params;
+		if (fe0->dvb.frontend) {
+			dev->original_demod_sleep = fe0->dvb.frontend->ops.sleep;
+			fe0->dvb.frontend->ops.sleep = philips_europa_demod_sleep;
+			fe0->dvb.frontend->ops.tuner_ops.init = philips_europa_tuner_init;
+			fe0->dvb.frontend->ops.tuner_ops.sleep = philips_europa_tuner_sleep;
+			fe0->dvb.frontend->ops.tuner_ops.set_params = philips_td1316_tuner_set_params;
 		}
 		break;
 	case SAA7134_BOARD_VIDEOMATE_DVBT_200:
-		dev->dvb.frontend = dvb_attach(tda10046_attach,
+		fe0->dvb.frontend = dvb_attach(tda10046_attach,
 					       &philips_tu1216_61_config,
 					       &dev->i2c_adap);
-		if (dev->dvb.frontend) {
-			dev->dvb.frontend->ops.tuner_ops.init = philips_tu1216_init;
-			dev->dvb.frontend->ops.tuner_ops.set_params = philips_tda6651_pll_set;
+		if (fe0->dvb.frontend) {
+			fe0->dvb.frontend->ops.tuner_ops.init = philips_tu1216_init;
+			fe0->dvb.frontend->ops.tuner_ops.set_params = philips_tda6651_pll_set;
 		}
 		break;
 	case SAA7134_BOARD_KWORLD_DVBT_210:
@@ -1060,20 +1070,20 @@ static int dvb_init(struct saa7134_dev *dev)
 					 &tda827x_cfg_0) < 0)
 			goto dettach_frontend;
 		break;
-	case SAA7134_BOARD_FLYDVB_TRIO:
+	case SAA7134_BOARD_FLYDVB_TRIO: // XXXXXX multifrontend
 		if (!use_frontend) {	/* terrestrial */
 			if (configure_tda827x_fe(dev, &lifeview_trio_config,
 						 &tda827x_cfg_0) < 0)
 				goto dettach_frontend;
 		} else {  		/* satellite */
-			dev->dvb.frontend = dvb_attach(tda10086_attach, &flydvbs, &dev->i2c_adap);
-			if (dev->dvb.frontend) {
-				if (dvb_attach(tda826x_attach, dev->dvb.frontend, 0x63,
+			fe0->dvb.frontend = dvb_attach(tda10086_attach, &flydvbs, &dev->i2c_adap);
+			if (fe0->dvb.frontend) {
+				if (dvb_attach(tda826x_attach, fe0->dvb.frontend, 0x63,
 									&dev->i2c_adap, 0) == NULL) {
 					wprintk("%s: Lifeview Trio, No tda826x found!\n", __func__);
 					goto dettach_frontend;
 				}
-				if (dvb_attach(isl6421_attach, dev->dvb.frontend, &dev->i2c_adap,
+				if (dvb_attach(isl6421_attach, fe0->dvb.frontend, &dev->i2c_adap,
 										0x08, 0, 0) == NULL) {
 					wprintk("%s: Lifeview Trio, No ISL6421 found!\n", __func__);
 					goto dettach_frontend;
@@ -1083,11 +1093,11 @@ static int dvb_init(struct saa7134_dev *dev)
 		break;
 	case SAA7134_BOARD_ADS_DUO_CARDBUS_PTV331:
 	case SAA7134_BOARD_FLYDVBT_HYBRID_CARDBUS:
-		dev->dvb.frontend = dvb_attach(tda10046_attach,
+		fe0->dvb.frontend = dvb_attach(tda10046_attach,
 					       &ads_tech_duo_config,
 					       &dev->i2c_adap);
-		if (dev->dvb.frontend) {
-			if (dvb_attach(tda827x_attach,dev->dvb.frontend,
+		if (fe0->dvb.frontend) {
+			if (dvb_attach(tda827x_attach,fe0->dvb.frontend,
 				   ads_tech_duo_config.tuner_address, &dev->i2c_adap,
 								&ads_duo_cfg) == NULL) {
 				wprintk("no tda827x tuner found at addr: %02x\n",
@@ -1108,15 +1118,15 @@ static int dvb_init(struct saa7134_dev *dev)
 						 &tda827x_cfg_0) < 0)
 				goto dettach_frontend;
 		} else {        /* satellite */
-			dev->dvb.frontend = dvb_attach(tda10086_attach,
+			fe0->dvb.frontend = dvb_attach(tda10086_attach,
 							&flydvbs, &dev->i2c_adap);
-			if (dev->dvb.frontend) {
-				struct dvb_frontend *fe = dev->dvb.frontend;
+			if (fe0->dvb.frontend) {
+				struct dvb_frontend *fe = fe0->dvb.frontend;
 				u8 dev_id = dev->eedata[2];
 				u8 data = 0xc4;
 				struct i2c_msg msg = {.addr = 0x08, .flags = 0, .len = 1};
 
-				if (dvb_attach(tda826x_attach, dev->dvb.frontend,
+				if (dvb_attach(tda826x_attach, fe0->dvb.frontend,
 						0x60, &dev->i2c_adap, 0) == NULL) {
 					wprintk("%s: Medion Quadro, no tda826x "
 						"found !\n", __func__);
@@ -1150,31 +1160,31 @@ static int dvb_init(struct saa7134_dev *dev)
 		}
 		break;
 	case SAA7134_BOARD_AVERMEDIA_AVERTVHD_A180:
-		dev->dvb.frontend = dvb_attach(nxt200x_attach, &avertvhda180,
+		fe0->dvb.frontend = dvb_attach(nxt200x_attach, &avertvhda180,
 					       &dev->i2c_adap);
-		if (dev->dvb.frontend)
-			dvb_attach(dvb_pll_attach, dev->dvb.frontend, 0x61,
+		if (fe0->dvb.frontend)
+			dvb_attach(dvb_pll_attach, fe0->dvb.frontend, 0x61,
 				   NULL, DVB_PLL_TDHU2);
 		break;
 	case SAA7134_BOARD_ADS_INSTANT_HDTV_PCI:
 	case SAA7134_BOARD_KWORLD_ATSC110:
-		dev->dvb.frontend = dvb_attach(nxt200x_attach, &kworldatsc110,
+		fe0->dvb.frontend = dvb_attach(nxt200x_attach, &kworldatsc110,
 					       &dev->i2c_adap);
-		if (dev->dvb.frontend)
-			dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+		if (fe0->dvb.frontend)
+			dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 				   &dev->i2c_adap, 0x61,
 				   TUNER_PHILIPS_TUV1236D);
 		break;
 	case SAA7134_BOARD_FLYDVBS_LR300:
-		dev->dvb.frontend = dvb_attach(tda10086_attach, &flydvbs,
+		fe0->dvb.frontend = dvb_attach(tda10086_attach, &flydvbs,
 					       &dev->i2c_adap);
-		if (dev->dvb.frontend) {
-			if (dvb_attach(tda826x_attach, dev->dvb.frontend, 0x60,
+		if (fe0->dvb.frontend) {
+			if (dvb_attach(tda826x_attach, fe0->dvb.frontend, 0x60,
 				       &dev->i2c_adap, 0) == NULL) {
 				wprintk("%s: No tda826x found!\n", __func__);
 				goto dettach_frontend;
 			}
-			if (dvb_attach(isl6421_attach, dev->dvb.frontend,
+			if (dvb_attach(isl6421_attach, fe0->dvb.frontend,
 				       &dev->i2c_adap, 0x08, 0, 0) == NULL) {
 				wprintk("%s: No ISL6421 found!\n", __func__);
 				goto dettach_frontend;
@@ -1182,25 +1192,25 @@ static int dvb_init(struct saa7134_dev *dev)
 		}
 		break;
 	case SAA7134_BOARD_ASUS_EUROPA2_HYBRID:
-		dev->dvb.frontend = dvb_attach(tda10046_attach,
+		fe0->dvb.frontend = dvb_attach(tda10046_attach,
 					       &medion_cardbus,
 					       &dev->i2c_adap);
-		if (dev->dvb.frontend) {
-			dev->original_demod_sleep = dev->dvb.frontend->ops.sleep;
-			dev->dvb.frontend->ops.sleep = philips_europa_demod_sleep;
+		if (fe0->dvb.frontend) {
+			dev->original_demod_sleep = fe0->dvb.frontend->ops.sleep;
+			fe0->dvb.frontend->ops.sleep = philips_europa_demod_sleep;
 
-			dvb_attach(simple_tuner_attach, dev->dvb.frontend,
+			dvb_attach(simple_tuner_attach, fe0->dvb.frontend,
 				   &dev->i2c_adap, medion_cardbus.tuner_address,
 				   TUNER_PHILIPS_FMD1216ME_MK3);
 		}
 		break;
 	case SAA7134_BOARD_VIDEOMATE_DVBT_200A:
-		dev->dvb.frontend = dvb_attach(tda10046_attach,
+		fe0->dvb.frontend = dvb_attach(tda10046_attach,
 				&philips_europa_config,
 				&dev->i2c_adap);
-		if (dev->dvb.frontend) {
-			dev->dvb.frontend->ops.tuner_ops.init = philips_td1316_tuner_init;
-			dev->dvb.frontend->ops.tuner_ops.set_params = philips_td1316_tuner_set_params;
+		if (fe0->dvb.frontend) {
+			fe0->dvb.frontend->ops.tuner_ops.init = philips_td1316_tuner_init;
+			fe0->dvb.frontend->ops.tuner_ops.set_params = philips_td1316_tuner_set_params;
 		}
 		break;
 	case SAA7134_BOARD_CINERGY_HT_PCMCIA:
@@ -1239,15 +1249,15 @@ static int dvb_init(struct saa7134_dev *dev)
 			goto dettach_frontend;
 		break;
 	case SAA7134_BOARD_PHILIPS_SNAKE:
-		dev->dvb.frontend = dvb_attach(tda10086_attach, &flydvbs,
+		fe0->dvb.frontend = dvb_attach(tda10086_attach, &flydvbs,
 						&dev->i2c_adap);
-		if (dev->dvb.frontend) {
-			if (dvb_attach(tda826x_attach, dev->dvb.frontend, 0x60,
+		if (fe0->dvb.frontend) {
+			if (dvb_attach(tda826x_attach, fe0->dvb.frontend, 0x60,
 					&dev->i2c_adap, 0) == NULL) {
 				wprintk("%s: No tda826x found!\n", __func__);
 				goto dettach_frontend;
 			}
-			if (dvb_attach(lnbp21_attach, dev->dvb.frontend,
+			if (dvb_attach(lnbp21_attach, fe0->dvb.frontend,
 					&dev->i2c_adap, 0, 0) == NULL) {
 				wprintk("%s: No lnbp21 found!\n", __func__);
 				goto dettach_frontend;
@@ -1269,24 +1279,24 @@ static int dvb_init(struct saa7134_dev *dev)
 		saa7134_set_gpio(dev, 25, 0);
 		msleep(10);
 		saa7134_set_gpio(dev, 25, 1);
-		dev->dvb.frontend = dvb_attach(mt352_attach,
+		fe0->dvb.frontend = dvb_attach(mt352_attach,
 						&avermedia_xc3028_mt352_dev,
 						&dev->i2c_adap);
 		attach_xc3028 = 1;
 		break;
 	case SAA7134_BOARD_MD7134_BRIDGE_2:
-		dev->dvb.frontend = dvb_attach(tda10086_attach,
+		fe0->dvb.frontend = dvb_attach(tda10086_attach,
 						&sd1878_4m, &dev->i2c_adap);
-		if (dev->dvb.frontend) {
+		if (fe0->dvb.frontend) {
 			struct dvb_frontend *fe;
-			if (dvb_attach(dvb_pll_attach, dev->dvb.frontend, 0x60,
+			if (dvb_attach(dvb_pll_attach, fe0->dvb.frontend, 0x60,
 				  &dev->i2c_adap, DVB_PLL_PHILIPS_SD1878_TDA8261) == NULL) {
 				wprintk("%s: MD7134 DVB-S, no SD1878 "
 					"found !\n", __func__);
 				goto dettach_frontend;
 			}
 			/* we need to open the i2c gate (we know it exists) */
-			fe = dev->dvb.frontend;
+			fe = fe0->dvb.frontend;
 			fe->ops.i2c_gate_ctrl(fe, 1);
 			if (dvb_attach(isl6405_attach, fe,
 					&dev->i2c_adap, 0x08, 0, 0) == NULL) {
@@ -1305,7 +1315,7 @@ static int dvb_init(struct saa7134_dev *dev)
 		saa7134_set_gpio(dev, 25, 0);
 		msleep(10);
 		saa7134_set_gpio(dev, 25, 1);
-		dev->dvb.frontend = dvb_attach(mt352_attach,
+		fe0->dvb.frontend = dvb_attach(mt352_attach,
 						&avermedia_xc3028_mt352_dev,
 						&dev->i2c_adap);
 		attach_xc3028 = 1;
@@ -1316,17 +1326,17 @@ static int dvb_init(struct saa7134_dev *dev)
 							&tda827x_cfg_2) < 0)
 				goto dettach_frontend;
 		} else {  		/* satellite */
-			dev->dvb.frontend = dvb_attach(tda10086_attach,
+			fe0->dvb.frontend = dvb_attach(tda10086_attach,
 						&flydvbs, &dev->i2c_adap);
-			if (dev->dvb.frontend) {
+			if (fe0->dvb.frontend) {
 				if (dvb_attach(tda826x_attach,
-						dev->dvb.frontend, 0x60,
+						fe0->dvb.frontend, 0x60,
 						&dev->i2c_adap, 0) == NULL) {
 					wprintk("%s: Asus Tiger 3in1, no "
 						"tda826x found!\n", __func__);
 					goto dettach_frontend;
 				}
-				if (dvb_attach(lnbp21_attach, dev->dvb.frontend,
+				if (dvb_attach(lnbp21_attach, fe0->dvb.frontend,
 						&dev->i2c_adap, 0, 0) == NULL) {
 					wprintk("%s: Asus Tiger 3in1, no lnbp21"
 						" found!\n", __func__);
@@ -1352,10 +1362,10 @@ static int dvb_init(struct saa7134_dev *dev)
 			.i2c_addr  = 0x61,
 		};
 
-		if (!dev->dvb.frontend)
+		if (!fe0->dvb.frontend)
 			return -1;
 
-		fe = dvb_attach(xc2028_attach, dev->dvb.frontend, &cfg);
+		fe = dvb_attach(xc2028_attach, fe0->dvb.frontend, &cfg);
 		if (!fe) {
 			printk(KERN_ERR "%s/2: xc3028 attach failed\n",
 			       dev->name);
@@ -1363,40 +1373,47 @@ static int dvb_init(struct saa7134_dev *dev)
 		}
 	}
 
-	if (NULL == dev->dvb.frontend) {
+	if (NULL == fe0->dvb.frontend) {
 		printk(KERN_ERR "%s/dvb: frontend initialization failed\n", dev->name);
 		return -1;
 	}
 	/* define general-purpose callback pointer */
-	dev->dvb.frontend->callback = saa7134_tuner_callback;
+	fe0->dvb.frontend->callback = saa7134_tuner_callback;
 
 	/* register everything else */
-	ret = videobuf_dvb_register(&dev->dvb, THIS_MODULE, dev, &dev->pci->dev,
-				    adapter_nr);
+	ret = videobuf_dvb_register_bus(&dev->frontends, THIS_MODULE, dev,
+		&dev->pci->dev, adapter_nr);
 
 	/* this sequence is necessary to make the tda1004x load its firmware
 	 * and to enter analog mode of hybrid boards
 	 */
 	if (!ret) {
-		if (dev->dvb.frontend->ops.init)
-			dev->dvb.frontend->ops.init(dev->dvb.frontend);
-		if (dev->dvb.frontend->ops.sleep)
-			dev->dvb.frontend->ops.sleep(dev->dvb.frontend);
-		if (dev->dvb.frontend->ops.tuner_ops.sleep)
-			dev->dvb.frontend->ops.tuner_ops.sleep(dev->dvb.frontend);
+		if (fe0->dvb.frontend->ops.init)
+			fe0->dvb.frontend->ops.init(fe0->dvb.frontend);
+		if (fe0->dvb.frontend->ops.sleep)
+			fe0->dvb.frontend->ops.sleep(fe0->dvb.frontend);
+		if (fe0->dvb.frontend->ops.tuner_ops.sleep)
+			fe0->dvb.frontend->ops.tuner_ops.sleep(fe0->dvb.frontend);
 	}
 	return ret;
 
 dettach_frontend:
-	if (dev->dvb.frontend)
-		dvb_frontend_detach(dev->dvb.frontend);
-	dev->dvb.frontend = NULL;
+	if (fe0->dvb.frontend)
+		dvb_frontend_detach(fe0->dvb.frontend);
+	fe0->dvb.frontend = NULL;
 
 	return -1;
 }
 
 static int dvb_fini(struct saa7134_dev *dev)
 {
+	struct videobuf_dvb_frontend *fe0;
+
+	/* Get the first frontend */
+	fe0 = videobuf_dvb_get_frontend(&dev->frontends, 1);
+	if (!fe0)
+		return -EINVAL;
+
 	/* FIXME: I suspect that this code is bogus, since the entry for
 	   Pinnacle 300I DVB-T PAL already defines the proper init to allow
 	   the detection of mt2032 (TDA9887_PORT2_INACTIVE)
@@ -1416,7 +1433,7 @@ static int dvb_fini(struct saa7134_dev *dev)
 			u8 data = 0x80;
 			struct i2c_msg msg = {.addr = 0x08, .buf = &data, .flags = 0, .len = 1};
 			struct dvb_frontend *fe;
-			fe = dev->dvb.frontend;
+			fe = fe0->dvb.frontend;
 			if (fe->ops.i2c_gate_ctrl) {
 				fe->ops.i2c_gate_ctrl(fe, 1);
 				i2c_transfer(&dev->i2c_adap, &msg, 1);
@@ -1424,8 +1441,8 @@ static int dvb_fini(struct saa7134_dev *dev)
 			}
 		}
 	}
-	if (dev->dvb.frontend)
-		videobuf_dvb_unregister(&dev->dvb);
+	if (fe0->dvb.frontend)
+		videobuf_dvb_unregister_bus(&dev->frontends);
 	return 0;
 }
 
diff --git a/drivers/media/video/saa7134/saa7134.h b/drivers/media/video/saa7134/saa7134.h
index 491ab1f8fdd3..24096d6e1ef8 100644
--- a/drivers/media/video/saa7134/saa7134.h
+++ b/drivers/media/video/saa7134/saa7134.h
@@ -581,7 +581,7 @@ struct saa7134_dev {
 
 #if defined(CONFIG_VIDEO_SAA7134_DVB) || defined(CONFIG_VIDEO_SAA7134_DVB_MODULE)
 	/* SAA7134_MPEG_DVB only */
-	struct videobuf_dvb        dvb;
+	struct videobuf_dvb_frontends frontends;
 	int (*original_demod_sleep)(struct dvb_frontend *fe);
 	int (*original_set_voltage)(struct dvb_frontend *fe, fe_sec_voltage_t voltage);
 	int (*original_set_high_voltage)(struct dvb_frontend *fe, long arg);
diff --git a/drivers/media/video/videobuf-dvb.c b/drivers/media/video/videobuf-dvb.c
index b56cffcbfd45..194fb765e58b 100644
--- a/drivers/media/video/videobuf-dvb.c
+++ b/drivers/media/video/videobuf-dvb.c
@@ -135,29 +135,75 @@ static int videobuf_dvb_stop_feed(struct dvb_demux_feed *feed)
 }
 
 /* ------------------------------------------------------------------ */
+/* Register a single adapter and one or more frontends */
+int videobuf_dvb_register_bus(struct videobuf_dvb_frontends *f,
+			  struct module *module,
+			  void *adapter_priv,
+			  struct device *device,
+			  short *adapter_nr) //NEW
+{
+	struct list_head *list, *q;
+	struct videobuf_dvb_frontend *fe;
+	int res = -EINVAL;
+
+	fe = videobuf_dvb_get_frontend(f, 1);
+	if (!fe) {
+		printk(KERN_WARNING "Unable to register the adapter which has no frontends\n");
+		goto err;
+	}
+
+	/* Bring up the adapter */
+	res = videobuf_dvb_register_adapter(f, module, adapter_priv, device, fe->dvb.name, adapter_nr); //NEW
+	if (res < 0) {
+		printk(KERN_WARNING "videobuf_dvb_register_adapter failed (errno = %d)\n", res);
+		goto err;
+	}
 
-int videobuf_dvb_register(struct videobuf_dvb *dvb,
+	/* Attach all of the frontends to the adapter */
+	mutex_lock(&f->lock);
+	list_for_each_safe(list, q, &f->frontend.felist) {
+		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
+
+		res = videobuf_dvb_register_frontend(&f->adapter, &fe->dvb);
+		if (res < 0) {
+			printk(KERN_WARNING "%s: videobuf_dvb_register_frontend failed (errno = %d)\n",
+				fe->dvb.name, res);
+		}
+	}
+	mutex_unlock(&f->lock);
+
+err:
+	return res;
+}
+
+int videobuf_dvb_register_adapter(struct videobuf_dvb_frontends *fe,
 			  struct module *module,
 			  void *adapter_priv,
 			  struct device *device,
-			  short *adapter_nr)
+			  char *adapter_name,
+			  short *adapter_nr) //NEW
 {
 	int result;
 
-	mutex_init(&dvb->lock);
+	mutex_init(&fe->lock);
 
 	/* register adapter */
-	result = dvb_register_adapter(&dvb->adapter, dvb->name, module, device,
-				      adapter_nr);
+	result = dvb_register_adapter(&fe->adapter, adapter_name, module, device, adapter_nr);
 	if (result < 0) {
 		printk(KERN_WARNING "%s: dvb_register_adapter failed (errno = %d)\n",
-		       dvb->name, result);
-		goto fail_adapter;
+		       adapter_name, result);
 	}
-	dvb->adapter.priv = adapter_priv;
+	fe->adapter.priv = adapter_priv;
+
+	return result;
+}
+
+int videobuf_dvb_register_frontend(struct dvb_adapter *adapter, struct videobuf_dvb *dvb)
+{
+	int result;
 
 	/* register frontend */
-	result = dvb_register_frontend(&dvb->adapter, dvb->frontend);
+	result = dvb_register_frontend(adapter, dvb->frontend);
 	if (result < 0) {
 		printk(KERN_WARNING "%s: dvb_register_frontend failed (errno = %d)\n",
 		       dvb->name, result);
@@ -183,7 +229,9 @@ int videobuf_dvb_register(struct videobuf_dvb *dvb,
 	dvb->dmxdev.filternum    = 256;
 	dvb->dmxdev.demux        = &dvb->demux.dmx;
 	dvb->dmxdev.capabilities = 0;
-	result = dvb_dmxdev_init(&dvb->dmxdev, &dvb->adapter);
+	//result = dvb_dmxdev_init(&dvb->dmxdev, &dvb->adapter);
+	result = dvb_dmxdev_init(&dvb->dmxdev, adapter);
+
 	if (result < 0) {
 		printk(KERN_WARNING "%s: dvb_dmxdev_init failed (errno = %d)\n",
 		       dvb->name, result);
@@ -214,7 +262,7 @@ int videobuf_dvb_register(struct videobuf_dvb *dvb,
 	}
 
 	/* register network adapter */
-	dvb_net_init(&dvb->adapter, &dvb->net, &dvb->demux.dmx);
+	dvb_net_init(adapter, &dvb->net, &dvb->demux.dmx);
 	return 0;
 
 fail_fe_conn:
@@ -230,24 +278,101 @@ fail_dmx:
 fail_frontend:
 	dvb_frontend_detach(dvb->frontend);
 	dvb_unregister_adapter(&dvb->adapter);
-fail_adapter:
+
 	return result;
 }
 
-void videobuf_dvb_unregister(struct videobuf_dvb *dvb)
+void videobuf_dvb_unregister_bus(struct videobuf_dvb_frontends *f)
 {
-	dvb_net_release(&dvb->net);
-	dvb->demux.dmx.remove_frontend(&dvb->demux.dmx, &dvb->fe_mem);
-	dvb->demux.dmx.remove_frontend(&dvb->demux.dmx, &dvb->fe_hw);
-	dvb_dmxdev_release(&dvb->dmxdev);
-	dvb_dmx_release(&dvb->demux);
-	dvb_unregister_frontend(dvb->frontend);
-	dvb_frontend_detach(dvb->frontend);
-	dvb_unregister_adapter(&dvb->adapter);
+	struct list_head *list, *q;
+	struct videobuf_dvb_frontend *fe;
+
+	mutex_lock(&f->lock);
+	list_for_each_safe(list, q, &f->frontend.felist) {
+		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
+
+		dvb_net_release(&fe->dvb.net);
+		fe->dvb.demux.dmx.remove_frontend(&fe->dvb.demux.dmx, &fe->dvb.fe_mem);
+		fe->dvb.demux.dmx.remove_frontend(&fe->dvb.demux.dmx, &fe->dvb.fe_hw);
+		dvb_dmxdev_release(&fe->dvb.dmxdev);
+		dvb_dmx_release(&fe->dvb.demux);
+		dvb_unregister_frontend(fe->dvb.frontend);
+		dvb_frontend_detach(fe->dvb.frontend);
+
+		list_del(list);
+		kfree(fe);
+	}
+	mutex_unlock(&f->lock);
+
+	dvb_unregister_adapter(&f->adapter);
+}
+
+struct videobuf_dvb_frontend * videobuf_dvb_get_frontend(struct videobuf_dvb_frontends *f, int id)
+{
+	struct list_head *list, *q;
+	struct videobuf_dvb_frontend *fe, *ret = NULL;
+
+	mutex_lock(&f->lock);
+
+	list_for_each_safe(list, q, &f->frontend.felist) {
+		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
+		if (fe->id == id) {
+			ret = fe;
+			break;
+		}
+	}
+
+	mutex_unlock(&f->lock);
+
+	return ret;
+}
+
+int videobuf_dvb_find_frontend(struct videobuf_dvb_frontends *f, struct dvb_frontend *p)
+{
+	struct list_head *list, *q;
+	struct videobuf_dvb_frontend *fe = NULL;
+	int ret = 0;
+
+	mutex_lock(&f->lock);
+
+	list_for_each_safe(list, q, &f->frontend.felist) {
+		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
+		if (fe->dvb.frontend == p) {
+			ret = fe->id;
+			break;
+		}
+	}
+
+	mutex_unlock(&f->lock);
+
+	return ret;
+}
+
+struct videobuf_dvb_frontend * videobuf_dvb_alloc_frontend(void *private, struct videobuf_dvb_frontends *f, int id)
+{
+	struct videobuf_dvb_frontend *fe;
+
+	fe = kzalloc(sizeof(struct videobuf_dvb_frontend),GFP_KERNEL);
+	if (fe == NULL)
+		goto fail_alloc;
+
+	fe->dev = private;
+	fe->id = id;
+	mutex_init(&fe->dvb.lock);
+
+	mutex_lock(&f->lock);
+	list_add_tail(&fe->felist,&f->frontend.felist);
+	mutex_unlock(&f->lock);
+
+fail_alloc:
+	return fe;
 }
 
-EXPORT_SYMBOL(videobuf_dvb_register);
-EXPORT_SYMBOL(videobuf_dvb_unregister);
+EXPORT_SYMBOL(videobuf_dvb_register_bus);
+EXPORT_SYMBOL(videobuf_dvb_unregister_bus);
+EXPORT_SYMBOL(videobuf_dvb_alloc_frontend);
+EXPORT_SYMBOL(videobuf_dvb_get_frontend);
+EXPORT_SYMBOL(videobuf_dvb_find_frontend);
 
 /* ------------------------------------------------------------------ */
 /*
diff --git a/include/media/videobuf-dvb.h b/include/media/videobuf-dvb.h
index b77748696329..09547ec3f3c3 100644
--- a/include/media/videobuf-dvb.h
+++ b/include/media/videobuf-dvb.h
@@ -24,12 +24,42 @@ struct videobuf_dvb {
 	struct dvb_net             net;
 };
 
-int videobuf_dvb_register(struct videobuf_dvb *dvb,
+struct videobuf_dvb_frontend {
+	void *dev;
+	struct list_head felist;
+	int id;
+	struct videobuf_dvb dvb;
+};
+
+struct videobuf_dvb_frontends {
+	struct mutex lock;
+	struct dvb_adapter adapter;
+	int active_fe_id; /* Indicates which frontend in the felist is in use */
+	struct videobuf_dvb_frontend frontend;
+};
+
+int videobuf_dvb_register_bus(struct videobuf_dvb_frontends *f,
 			  struct module *module,
 			  void *adapter_priv,
 			  struct device *device,
-			  short *adapter_nr);
-void videobuf_dvb_unregister(struct videobuf_dvb *dvb);
+			  short *adapter_nr);   //NEW
+
+void videobuf_dvb_unregister_bus(struct videobuf_dvb_frontends *f);
+
+int videobuf_dvb_register_adapter(struct videobuf_dvb_frontends *f,
+			  struct module *module,
+			  void *adapter_priv,
+			  struct device *device,
+			  char *adapter_name,
+			  short *adapter_nr);   //NEW
+
+int videobuf_dvb_register_frontend(struct dvb_adapter *adapter, struct videobuf_dvb *dvb);
+
+struct videobuf_dvb_frontend * videobuf_dvb_alloc_frontend(void *private, struct videobuf_dvb_frontends *f, int id);
+
+struct videobuf_dvb_frontend * videobuf_dvb_get_frontend(struct videobuf_dvb_frontends *f, int id);
+int videobuf_dvb_find_frontend(struct videobuf_dvb_frontends *f, struct dvb_frontend *p);
+
 
 /*
  * Local variables:
-- 
cgit v1.2.3


From 8e739090d6cdd43ddf938a3899c4f929db8d5ba8 Mon Sep 17 00:00:00 2001
From: Darron Broad <darron@kewl.org>
Date: Sat, 11 Oct 2008 11:31:41 -0300
Subject: V4L/DVB (9225): MFE: Add configurable gate control

This adds a configurable (one per card) gate control option
for multi-frontend. Prior to this point gate control was
assumed to be on the primary frontend, this is a fault
when the gate to the analogue section is on the secondary
which is the default for both the HVR-3000 and HVR-4000
in MFE.

Signed-off-by: Darron Broad <darron@kewl.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/cx88/cx88-dvb.c |  7 ++++++-
 drivers/media/video/cx88/cx88-i2c.c | 20 +++++++++++---------
 include/media/videobuf-dvb.h        |  1 +
 3 files changed, 18 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/media/video/cx88/cx88-dvb.c b/drivers/media/video/cx88/cx88-dvb.c
index 58128687e5cc..9bb7bee0da6d 100644
--- a/drivers/media/video/cx88/cx88-dvb.c
+++ b/drivers/media/video/cx88/cx88-dvb.c
@@ -608,7 +608,10 @@ static int dvb_register(struct cx8802_dev *dev)
 	if (!fe0)
 		return -EINVAL;
 
-	/* init frontend */
+	/* multi-frontend gate control is undefined or defaults to fe0 */
+	dev->frontends.gate = 0;
+
+	/* init frontend(s) */
 	switch (core->boardnr) {
 	case CX88_BOARD_HAUPPAUGE_DVB_T1:
 		fe0->dvb.frontend = dvb_attach(cx22702_attach,
@@ -665,6 +668,7 @@ static int dvb_register(struct cx8802_dev *dev)
 		/* DVB-T init */
 		fe1 = videobuf_dvb_get_frontend(&dev->frontends, 2);
 		if (fe1) {
+			dev->frontends.gate = 2;
 			fe1->dvb.frontend = dvb_attach(cx22702_attach,
 				&hauppauge_hvr_config,
 				&dev->core->i2c_adap);
@@ -1008,6 +1012,7 @@ static int dvb_register(struct cx8802_dev *dev)
 		/* DVB-T Init */
 		fe1 = videobuf_dvb_get_frontend(&dev->frontends, 2);
 		if (fe1) {
+			dev->frontends.gate = 2;
 			fe1->dvb.frontend = dvb_attach(cx22702_attach,
 				&hauppauge_hvr_config,
 				&dev->core->i2c_adap);
diff --git a/drivers/media/video/cx88/cx88-i2c.c b/drivers/media/video/cx88/cx88-i2c.c
index 582769de26b5..01de23007095 100644
--- a/drivers/media/video/cx88/cx88-i2c.c
+++ b/drivers/media/video/cx88/cx88-i2c.c
@@ -116,23 +116,25 @@ static int detach_inform(struct i2c_client *client)
 
 void cx88_call_i2c_clients(struct cx88_core *core, unsigned int cmd, void *arg)
 {
-	struct videobuf_dvb_frontend *fe0 = NULL;
+	struct videobuf_dvb_frontends *f = &core->dvbdev->frontends;
+	struct videobuf_dvb_frontend *fe = NULL;
 	if (0 != core->i2c_rc)
 		return;
 
 #if defined(CONFIG_VIDEO_CX88_DVB) || defined(CONFIG_VIDEO_CX88_DVB_MODULE)
-	if (core->dvbdev) {
-		/* Get the first frontend and assume that all I2C is routed through it */
-		/* TODO: Get _THIS_FE_ then find the right i2c_gate_ctrl for it */
-		fe0 = videobuf_dvb_get_frontend(&core->dvbdev->frontends, 1);
+	if (core->dvbdev && f) {
+		if(f->gate <= 1) /* undefined or fe0 */
+			fe = videobuf_dvb_get_frontend(f, 1);
+		else
+			fe = videobuf_dvb_get_frontend(f, f->gate);
 
-		if (fe0 && fe0->dvb.frontend && fe0->dvb.frontend->ops.i2c_gate_ctrl)
-			fe0->dvb.frontend->ops.i2c_gate_ctrl(fe0->dvb.frontend, 1);
+		if (fe && fe->dvb.frontend && fe->dvb.frontend->ops.i2c_gate_ctrl)
+			fe->dvb.frontend->ops.i2c_gate_ctrl(fe->dvb.frontend, 1);
 
 		i2c_clients_command(&core->i2c_adap, cmd, arg);
 
-		if (fe0 && fe0->dvb.frontend && fe0->dvb.frontend->ops.i2c_gate_ctrl)
-			fe0->dvb.frontend->ops.i2c_gate_ctrl(fe0->dvb.frontend, 0);
+		if (fe && fe->dvb.frontend && fe->dvb.frontend->ops.i2c_gate_ctrl)
+			fe->dvb.frontend->ops.i2c_gate_ctrl(fe->dvb.frontend, 0);
 	} else
 #endif
 		i2c_clients_command(&core->i2c_adap, cmd, arg);
diff --git a/include/media/videobuf-dvb.h b/include/media/videobuf-dvb.h
index 09547ec3f3c3..47bc2c5e7ba9 100644
--- a/include/media/videobuf-dvb.h
+++ b/include/media/videobuf-dvb.h
@@ -36,6 +36,7 @@ struct videobuf_dvb_frontends {
 	struct dvb_adapter adapter;
 	int active_fe_id; /* Indicates which frontend in the felist is in use */
 	struct videobuf_dvb_frontend frontend;
+	int gate; /* Frontend with gate control 0=!MFE,1=fe0,2=fe1 etc */
 };
 
 int videobuf_dvb_register_bus(struct videobuf_dvb_frontends *f,
-- 
cgit v1.2.3


From 59b1842da1c6f33ad2e8da82d3dfb3445751d964 Mon Sep 17 00:00:00 2001
From: Darron Broad <darron@kewl.org>
Date: Sat, 11 Oct 2008 11:44:05 -0300
Subject: V4L/DVB (9227): MFE: Add multi-frontend mutual exclusion

This add frontend R/W mutual exclusion.
Prior to this point in time it was possible to open both
frontends simultaneously which an MFE card cannot support.

In order to stop this, a delayed open is performed which
has the following function:

-  Return EBUSY after a configurable amount of time
   if a frontend is unavailable due to the other being
   in use.

-  Only allow opening of a frontend if the kernel thread
   of the other has stopped.

This solution was chosen to allow switching between
frontends to work as seamlessly as possible. When both
frontends are actually opened simultaneously then one
will only open, but if quick switching is performed
between one of many then the new open will succeed in
a clean fashion rather than interrupting a kernel
thread.

Signed-off-by: Darron Broad <darron@kewl.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/dvb/dvb-core/dvb_frontend.c | 43 ++++++++++++++++++++++++++++++-
 drivers/media/dvb/dvb-core/dvbdev.c       |  3 +++
 drivers/media/dvb/dvb-core/dvbdev.h       |  4 +++
 drivers/media/video/cx23885/cx23885-dvb.c |  2 +-
 drivers/media/video/cx88/cx88-dvb.c       | 11 +++-----
 drivers/media/video/saa7134/saa7134-dvb.c |  2 +-
 drivers/media/video/videobuf-dvb.c        |  9 ++++---
 include/media/videobuf-dvb.h              |  6 +++--
 8 files changed, 65 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/media/dvb/dvb-core/dvb_frontend.c b/drivers/media/dvb/dvb-core/dvb_frontend.c
index 26671757c70b..62696f865576 100644
--- a/drivers/media/dvb/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb/dvb-core/dvb_frontend.c
@@ -47,6 +47,7 @@ static int dvb_shutdown_timeout;
 static int dvb_force_auto_inversion;
 static int dvb_override_tune_delay;
 static int dvb_powerdown_on_sleep = 1;
+static int dvb_mfe_wait_time = 5;
 
 module_param_named(frontend_debug, dvb_frontend_debug, int, 0644);
 MODULE_PARM_DESC(frontend_debug, "Turn on/off frontend core debugging (default:off).");
@@ -58,6 +59,8 @@ module_param(dvb_override_tune_delay, int, 0644);
 MODULE_PARM_DESC(dvb_override_tune_delay, "0: normal (default), >0 => delay in milliseconds to wait for lock after a tune attempt");
 module_param(dvb_powerdown_on_sleep, int, 0644);
 MODULE_PARM_DESC(dvb_powerdown_on_sleep, "0: do not power down, 1: turn LNB voltage off on sleep (default)");
+module_param(dvb_mfe_wait_time, int, 0644);
+MODULE_PARM_DESC(dvb_mfe_wait_time, "Wait up to <mfe_wait_time> seconds on open() for multi-frontend to become available (default:5 seconds)");
 
 #define dprintk if (dvb_frontend_debug) printk
 
@@ -1706,13 +1709,46 @@ static int dvb_frontend_open(struct inode *inode, struct file *file)
 	struct dvb_device *dvbdev = file->private_data;
 	struct dvb_frontend *fe = dvbdev->priv;
 	struct dvb_frontend_private *fepriv = fe->frontend_priv;
+	struct dvb_adapter *adapter = fe->dvb;
+	struct dvb_device *mfedev;
+	struct dvb_frontend *mfe;
+	struct dvb_frontend_private *mfepriv;
+	int mferetry;
 	int ret;
 
 	dprintk ("%s\n", __func__);
 
+	if (adapter->mfe_shared) {
+		mutex_lock (&adapter->mfe_lock);
+		if (adapter->mfe_dvbdev != dvbdev) {
+			if (adapter->mfe_dvbdev) {
+				mfedev = adapter->mfe_dvbdev;
+				mfe = mfedev->priv;
+				mfepriv = mfe->frontend_priv;
+				mutex_unlock (&adapter->mfe_lock);
+				mferetry = (dvb_mfe_wait_time << 1);
+				while (mferetry-- && (mfedev->users != -1 || mfepriv->thread != NULL)) {
+					if(msleep_interruptible(500)) {
+						if(signal_pending(current))
+							return -EINTR;
+					}
+				}
+				mutex_lock (&adapter->mfe_lock);
+				mfedev = adapter->mfe_dvbdev;
+				mfe = mfedev->priv;
+				mfepriv = mfe->frontend_priv;
+				if (mfedev->users != -1 || mfepriv->thread != NULL) {
+					ret = -EBUSY;
+					goto err0;
+				}
+			}
+			adapter->mfe_dvbdev = dvbdev;
+		}
+	}
+
 	if (dvbdev->users == -1 && fe->ops.ts_bus_ctrl) {
 		if ((ret = fe->ops.ts_bus_ctrl(fe, 1)) < 0)
-			return ret;
+			goto err0;
 	}
 
 	if ((ret = dvb_generic_open (inode, file)) < 0)
@@ -1732,6 +1768,8 @@ static int dvb_frontend_open(struct inode *inode, struct file *file)
 		fepriv->events.eventr = fepriv->events.eventw = 0;
 	}
 
+	if (adapter->mfe_shared)
+		mutex_unlock (&adapter->mfe_lock);
 	return ret;
 
 err2:
@@ -1739,6 +1777,9 @@ err2:
 err1:
 	if (dvbdev->users == -1 && fe->ops.ts_bus_ctrl)
 		fe->ops.ts_bus_ctrl(fe, 0);
+err0:
+	if (adapter->mfe_shared)
+		mutex_unlock (&adapter->mfe_lock);
 	return ret;
 }
 
diff --git a/drivers/media/dvb/dvb-core/dvbdev.c b/drivers/media/dvb/dvb-core/dvbdev.c
index 665776d72a48..a113744a56cc 100644
--- a/drivers/media/dvb/dvb-core/dvbdev.c
+++ b/drivers/media/dvb/dvb-core/dvbdev.c
@@ -326,6 +326,9 @@ int dvb_register_adapter(struct dvb_adapter *adap, const char *name,
 	adap->name = name;
 	adap->module = module;
 	adap->device = device;
+	adap->mfe_shared = 0;
+	adap->mfe_dvbdev = NULL;
+	mutex_init (&adap->mfe_lock);
 
 	list_add_tail (&adap->list_head, &dvb_adapter_list);
 
diff --git a/drivers/media/dvb/dvb-core/dvbdev.h b/drivers/media/dvb/dvb-core/dvbdev.h
index 89d12dc477a7..574e336bac35 100644
--- a/drivers/media/dvb/dvb-core/dvbdev.h
+++ b/drivers/media/dvb/dvb-core/dvbdev.h
@@ -62,6 +62,10 @@ struct dvb_adapter {
 	struct device *device;
 
 	struct module *module;
+
+	int mfe_shared;			/* indicates mutually exclusive frontends */
+	struct dvb_device *mfe_dvbdev;	/* frontend device in use */
+	struct mutex mfe_lock;		/* access lock for thread creation */
 };
 
 
diff --git a/drivers/media/video/cx23885/cx23885-dvb.c b/drivers/media/video/cx23885/cx23885-dvb.c
index c14878f74bcc..78851526db68 100644
--- a/drivers/media/video/cx23885/cx23885-dvb.c
+++ b/drivers/media/video/cx23885/cx23885-dvb.c
@@ -556,7 +556,7 @@ static int dvb_register(struct cx23885_tsport *port)
 
 	/* register everything */
 	return videobuf_dvb_register_bus(&port->frontends, THIS_MODULE, port,
-				     &dev->pci->dev, adapter_nr);
+		&dev->pci->dev, adapter_nr, 0);
 
 }
 
diff --git a/drivers/media/video/cx88/cx88-dvb.c b/drivers/media/video/cx88/cx88-dvb.c
index 9bb7bee0da6d..0dd0ff9227fb 100644
--- a/drivers/media/video/cx88/cx88-dvb.c
+++ b/drivers/media/video/cx88/cx88-dvb.c
@@ -594,14 +594,9 @@ static struct stv0288_config tevii_tuner_earda_config = {
 
 static int dvb_register(struct cx8802_dev *dev)
 {
-	//struct cx88_core *core = dev->core;
-
-	///* init struct videobuf_dvb */
-	//fe->dvb.name = core->name;
-	//dev->ts_gen_cntrl = 0x0c;
-
 	struct cx88_core *core = dev->core;
 	struct videobuf_dvb_frontend *fe0, *fe1 = NULL;
+	int mfe_shared = 0; /* bus not shared by default */
 
 	/* Get the first frontend */
 	fe0 = videobuf_dvb_get_frontend(&dev->frontends, 1);
@@ -669,6 +664,7 @@ static int dvb_register(struct cx8802_dev *dev)
 		fe1 = videobuf_dvb_get_frontend(&dev->frontends, 2);
 		if (fe1) {
 			dev->frontends.gate = 2;
+			mfe_shared = 1;
 			fe1->dvb.frontend = dvb_attach(cx22702_attach,
 				&hauppauge_hvr_config,
 				&dev->core->i2c_adap);
@@ -1013,6 +1009,7 @@ static int dvb_register(struct cx8802_dev *dev)
 		fe1 = videobuf_dvb_get_frontend(&dev->frontends, 2);
 		if (fe1) {
 			dev->frontends.gate = 2;
+			mfe_shared = 1;
 			fe1->dvb.frontend = dvb_attach(cx22702_attach,
 				&hauppauge_hvr_config,
 				&dev->core->i2c_adap);
@@ -1110,7 +1107,7 @@ static int dvb_register(struct cx8802_dev *dev)
 
 	/* register everything */
 	return videobuf_dvb_register_bus(&dev->frontends, THIS_MODULE, dev,
-		&dev->pci->dev, adapter_nr);
+		&dev->pci->dev, adapter_nr, mfe_shared);
 
 frontend_detach:
 	if (fe0->dvb.frontend) {
diff --git a/drivers/media/video/saa7134/saa7134-dvb.c b/drivers/media/video/saa7134/saa7134-dvb.c
index 30ae0cbe78a0..d2d238912fbf 100644
--- a/drivers/media/video/saa7134/saa7134-dvb.c
+++ b/drivers/media/video/saa7134/saa7134-dvb.c
@@ -1395,7 +1395,7 @@ static int dvb_init(struct saa7134_dev *dev)
 
 	/* register everything else */
 	ret = videobuf_dvb_register_bus(&dev->frontends, THIS_MODULE, dev,
-		&dev->pci->dev, adapter_nr);
+		&dev->pci->dev, adapter_nr, 0);
 
 	/* this sequence is necessary to make the tda1004x load its firmware
 	 * and to enter analog mode of hybrid boards
diff --git a/drivers/media/video/videobuf-dvb.c b/drivers/media/video/videobuf-dvb.c
index a0a80e1e79e3..af0b75cda6fd 100644
--- a/drivers/media/video/videobuf-dvb.c
+++ b/drivers/media/video/videobuf-dvb.c
@@ -140,7 +140,8 @@ int videobuf_dvb_register_bus(struct videobuf_dvb_frontends *f,
 			  struct module *module,
 			  void *adapter_priv,
 			  struct device *device,
-			  short *adapter_nr) //NEW
+			  short *adapter_nr,
+			  int mfe_shared)
 {
 	struct list_head *list, *q;
 	struct videobuf_dvb_frontend *fe;
@@ -153,7 +154,7 @@ int videobuf_dvb_register_bus(struct videobuf_dvb_frontends *f,
 	}
 
 	/* Bring up the adapter */
-	res = videobuf_dvb_register_adapter(f, module, adapter_priv, device, fe->dvb.name, adapter_nr); //NEW
+	res = videobuf_dvb_register_adapter(f, module, adapter_priv, device, fe->dvb.name, adapter_nr, mfe_shared);
 	if (res < 0) {
 		printk(KERN_WARNING "videobuf_dvb_register_adapter failed (errno = %d)\n", res);
 		goto err;
@@ -181,7 +182,8 @@ int videobuf_dvb_register_adapter(struct videobuf_dvb_frontends *fe,
 			  void *adapter_priv,
 			  struct device *device,
 			  char *adapter_name,
-			  short *adapter_nr) //NEW
+			  short *adapter_nr,
+			  int mfe_shared)
 {
 	int result;
 
@@ -194,6 +196,7 @@ int videobuf_dvb_register_adapter(struct videobuf_dvb_frontends *fe,
 		       adapter_name, result);
 	}
 	fe->adapter.priv = adapter_priv;
+	fe->adapter.mfe_shared = mfe_shared;
 
 	return result;
 }
diff --git a/include/media/videobuf-dvb.h b/include/media/videobuf-dvb.h
index 47bc2c5e7ba9..1a401f7320b9 100644
--- a/include/media/videobuf-dvb.h
+++ b/include/media/videobuf-dvb.h
@@ -43,7 +43,8 @@ int videobuf_dvb_register_bus(struct videobuf_dvb_frontends *f,
 			  struct module *module,
 			  void *adapter_priv,
 			  struct device *device,
-			  short *adapter_nr);   //NEW
+			  short *adapter_nr,
+			  int mfe_shared);
 
 void videobuf_dvb_unregister_bus(struct videobuf_dvb_frontends *f);
 
@@ -52,7 +53,8 @@ int videobuf_dvb_register_adapter(struct videobuf_dvb_frontends *f,
 			  void *adapter_priv,
 			  struct device *device,
 			  char *adapter_name,
-			  short *adapter_nr);   //NEW
+			  short *adapter_nr,
+			  int mfe_shared);
 
 int videobuf_dvb_register_frontend(struct dvb_adapter *adapter, struct videobuf_dvb *dvb);
 
-- 
cgit v1.2.3


From 2a1d245b70f3f966f96767aaea1a2db6823e2f6e Mon Sep 17 00:00:00 2001
From: Jean Delvare <khali@linux-fr.org>
Date: Wed, 15 Oct 2008 14:47:36 -0300
Subject: V4L/DVB (9240): saa7127: Fix two typos

Signed-off-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/saa7127.c | 2 +-
 include/linux/i2c-id.h        | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/media/video/saa7127.c b/drivers/media/video/saa7127.c
index d0e83fe0ff51..cc02fb18efa7 100644
--- a/drivers/media/video/saa7127.c
+++ b/drivers/media/video/saa7127.c
@@ -29,7 +29,7 @@
  * Note: the saa7126 is identical to the saa7127, and the saa7128 is
  * identical to the saa7129, except that the saa7126 and saa7128 have
  * macrovision anti-taping support. This driver will almost certainly
- * work find for those chips, except of course for the missing anti-taping
+ * work fine for those chips, except of course for the missing anti-taping
  * support.
  *
  * This program is free software; you can redistribute it and/or modify
diff --git a/include/linux/i2c-id.h b/include/linux/i2c-id.h
index 493435bcdbe5..01d67ba9e985 100644
--- a/include/linux/i2c-id.h
+++ b/include/linux/i2c-id.h
@@ -60,7 +60,7 @@
 #define I2C_DRIVERID_WM8775	69	/* wm8775 audio processor	*/
 #define I2C_DRIVERID_CS53L32A	70	/* cs53l32a audio processor	*/
 #define I2C_DRIVERID_CX25840	71	/* cx2584x video encoder	*/
-#define I2C_DRIVERID_SAA7127	72	/* saa7124 video encoder	*/
+#define I2C_DRIVERID_SAA7127	72	/* saa7127 video encoder	*/
 #define I2C_DRIVERID_SAA711X	73	/* saa711x video encoders	*/
 #define I2C_DRIVERID_AKITAIOEXP	74	/* IO Expander on Sharp SL-C1000 */
 #define I2C_DRIVERID_INFRARED	75	/* I2C InfraRed on Video boards */
-- 
cgit v1.2.3


From 50c616fd0b43f50379aa70da96fd350312367367 Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Date: Thu, 16 Oct 2008 19:49:27 -0300
Subject: V4L/DVB (9241): soc-camera: move sensor power management to
 soc_camera_platform.c

Switching sensors on and off is now done by sensor drivers themselves,
typically using platform-provided hooks. Update soc_camera_platform.c to
do the same. Also remove a refundant struct soc_camera_platform_info
definition from soc_camera_platform.c.

Tested-by: Magnus Damm <damm@igel.co.jp>
Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/soc_camera_platform.c | 20 +++++++++++---------
 include/media/soc_camera_platform.h       |  1 +
 2 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/media/video/soc_camera_platform.c b/drivers/media/video/soc_camera_platform.c
index 1adc257ebdb9..bb7a9d480e8f 100644
--- a/drivers/media/video/soc_camera_platform.c
+++ b/drivers/media/video/soc_camera_platform.c
@@ -18,15 +18,7 @@
 #include <linux/videodev2.h>
 #include <media/v4l2-common.h>
 #include <media/soc_camera.h>
-
-struct soc_camera_platform_info {
-	int iface;
-	char *format_name;
-	unsigned long format_depth;
-	struct v4l2_pix_format format;
-	unsigned long bus_param;
-	int (*set_capture)(struct soc_camera_platform_info *info, int enable);
-};
+#include <media/soc_camera_platform.h>
 
 struct soc_camera_platform_priv {
 	struct soc_camera_platform_info *info;
@@ -44,11 +36,21 @@ soc_camera_platform_get_info(struct soc_camera_device *icd)
 
 static int soc_camera_platform_init(struct soc_camera_device *icd)
 {
+	struct soc_camera_platform_info *p = soc_camera_platform_get_info(icd);
+
+	if (p->power)
+		p->power(1);
+
 	return 0;
 }
 
 static int soc_camera_platform_release(struct soc_camera_device *icd)
 {
+	struct soc_camera_platform_info *p = soc_camera_platform_get_info(icd);
+
+	if (p->power)
+		p->power(0);
+
 	return 0;
 }
 
diff --git a/include/media/soc_camera_platform.h b/include/media/soc_camera_platform.h
index 851f18220984..7c81ad32b1e5 100644
--- a/include/media/soc_camera_platform.h
+++ b/include/media/soc_camera_platform.h
@@ -9,6 +9,7 @@ struct soc_camera_platform_info {
 	unsigned long format_depth;
 	struct v4l2_pix_format format;
 	unsigned long bus_param;
+	void (*power)(int);
 	int (*set_capture)(struct soc_camera_platform_info *info, int enable);
 };
 
-- 
cgit v1.2.3


From 073afdd793243fff9f342c2606b9864052e9e3e5 Mon Sep 17 00:00:00 2001
From: Magnus Damm <damm@igel.co.jp>
Date: Thu, 16 Oct 2008 19:51:47 -0300
Subject: V4L/DVB (9245): video: add header to soc_camera_platform include file

Update the soc_camera_platform header with licensing information.

Signed-off-by: Magnus Damm <damm@igel.co.jp>
Signed-off-by: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 include/media/soc_camera_platform.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include')

diff --git a/include/media/soc_camera_platform.h b/include/media/soc_camera_platform.h
index 7c81ad32b1e5..1d092b4678aa 100644
--- a/include/media/soc_camera_platform.h
+++ b/include/media/soc_camera_platform.h
@@ -1,3 +1,13 @@
+/*
+ * Generic Platform Camera Driver Header
+ *
+ * Copyright (C) 2008 Magnus Damm
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
 #ifndef __SOC_CAMERA_H__
 #define __SOC_CAMERA_H__
 
-- 
cgit v1.2.3


From 7bdf84fc47f2d2ed2194b6ade480d043207c4098 Mon Sep 17 00:00:00 2001
From: Darron Broad <darron@kewl.org>
Date: Wed, 15 Oct 2008 13:43:41 -0300
Subject: V4L/DVB (9265): videobuf: data storage optimisation

To optimise data storage redundant vars are removed.

Signed-off-by: Darron Broad <darron@kewl.org>
Signed-off-by: Steven Toth <stoth@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/cx23885/cx23885-core.c |  2 +-
 drivers/media/video/cx88/cx88-mpeg.c       |  2 +-
 drivers/media/video/saa7134/saa7134-dvb.c  |  2 +-
 drivers/media/video/videobuf-dvb.c         | 11 +++++------
 include/media/videobuf-dvb.h               |  5 ++---
 5 files changed, 10 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/media/video/cx23885/cx23885-core.c b/drivers/media/video/cx23885/cx23885-core.c
index 110e2ed2061d..8f6fb2add7de 100644
--- a/drivers/media/video/cx23885/cx23885-core.c
+++ b/drivers/media/video/cx23885/cx23885-core.c
@@ -643,7 +643,7 @@ static int cx23885_init_tsport(struct cx23885_dev *dev,
 	init_timer(&port->mpegq.timeout);
 
 	mutex_init(&port->frontends.lock);
-	INIT_LIST_HEAD(&port->frontends.frontend.felist);
+	INIT_LIST_HEAD(&port->frontends.felist);
 	port->frontends.active_fe_id = 0;
 
 	/* This should be hardcoded allow a single frontend
diff --git a/drivers/media/video/cx88/cx88-mpeg.c b/drivers/media/video/cx88/cx88-mpeg.c
index 1d8c8dd3006a..512041451d38 100644
--- a/drivers/media/video/cx88/cx88-mpeg.c
+++ b/drivers/media/video/cx88/cx88-mpeg.c
@@ -802,7 +802,7 @@ static int __devinit cx8802_probe(struct pci_dev *pci_dev,
 	list_add_tail(&dev->devlist,&cx8802_devlist);
 
 	mutex_init(&dev->frontends.lock);
-	INIT_LIST_HEAD(&dev->frontends.frontend.felist);
+	INIT_LIST_HEAD(&dev->frontends.felist);
 
 	printk(KERN_INFO "%s() allocating %d frontend(s)\n", __func__, core->board.num_frontends);
 
diff --git a/drivers/media/video/saa7134/saa7134-dvb.c b/drivers/media/video/saa7134/saa7134-dvb.c
index d2d238912fbf..7d95a6928772 100644
--- a/drivers/media/video/saa7134/saa7134-dvb.c
+++ b/drivers/media/video/saa7134/saa7134-dvb.c
@@ -953,7 +953,7 @@ static int dvb_init(struct saa7134_dev *dev)
 
 	/* FIXME: add support for multi-frontend */
 	mutex_init(&dev->frontends.lock);
-	INIT_LIST_HEAD(&dev->frontends.frontend.felist);
+	INIT_LIST_HEAD(&dev->frontends.felist);
 	dev->frontends.active_fe_id = 0;
 
 	printk(KERN_INFO "%s() allocating 1 frontend\n", __func__);
diff --git a/drivers/media/video/videobuf-dvb.c b/drivers/media/video/videobuf-dvb.c
index af0b75cda6fd..fc4cfaa7bf5f 100644
--- a/drivers/media/video/videobuf-dvb.c
+++ b/drivers/media/video/videobuf-dvb.c
@@ -162,9 +162,8 @@ int videobuf_dvb_register_bus(struct videobuf_dvb_frontends *f,
 
 	/* Attach all of the frontends to the adapter */
 	mutex_lock(&f->lock);
-	list_for_each_safe(list, q, &f->frontend.felist) {
+	list_for_each_safe(list, q, &f->felist) {
 		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
-
 		res = videobuf_dvb_register_frontend(&f->adapter, &fe->dvb);
 		if (res < 0) {
 			printk(KERN_WARNING "%s: videobuf_dvb_register_frontend failed (errno = %d)\n",
@@ -290,7 +289,7 @@ void videobuf_dvb_unregister_bus(struct videobuf_dvb_frontends *f)
 	struct videobuf_dvb_frontend *fe;
 
 	mutex_lock(&f->lock);
-	list_for_each_safe(list, q, &f->frontend.felist) {
+	list_for_each_safe(list, q, &f->felist) {
 		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
 
 		dvb_net_release(&fe->dvb.net);
@@ -316,7 +315,7 @@ struct videobuf_dvb_frontend * videobuf_dvb_get_frontend(struct videobuf_dvb_fro
 
 	mutex_lock(&f->lock);
 
-	list_for_each_safe(list, q, &f->frontend.felist) {
+	list_for_each_safe(list, q, &f->felist) {
 		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
 		if (fe->id == id) {
 			ret = fe;
@@ -337,7 +336,7 @@ int videobuf_dvb_find_frontend(struct videobuf_dvb_frontends *f, struct dvb_fron
 
 	mutex_lock(&f->lock);
 
-	list_for_each_safe(list, q, &f->frontend.felist) {
+	list_for_each_safe(list, q, &f->felist) {
 		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
 		if (fe->dvb.frontend == p) {
 			ret = fe->id;
@@ -363,7 +362,7 @@ struct videobuf_dvb_frontend * videobuf_dvb_alloc_frontend(void *private, struct
 	mutex_init(&fe->dvb.lock);
 
 	mutex_lock(&f->lock);
-	list_add_tail(&fe->felist,&f->frontend.felist);
+	list_add_tail(&fe->felist,&f->felist);
 	mutex_unlock(&f->lock);
 
 fail_alloc:
diff --git a/include/media/videobuf-dvb.h b/include/media/videobuf-dvb.h
index 1a401f7320b9..069215c77a65 100644
--- a/include/media/videobuf-dvb.h
+++ b/include/media/videobuf-dvb.h
@@ -16,7 +16,6 @@ struct videobuf_dvb {
 	int                        nfeeds;
 
 	/* videobuf_dvb_(un)register manges this */
-	struct dvb_adapter         adapter;
 	struct dvb_demux           demux;
 	struct dmxdev              dmxdev;
 	struct dmx_frontend        fe_hw;
@@ -25,17 +24,17 @@ struct videobuf_dvb {
 };
 
 struct videobuf_dvb_frontend {
-	void *dev;
 	struct list_head felist;
+	void *dev;
 	int id;
 	struct videobuf_dvb dvb;
 };
 
 struct videobuf_dvb_frontends {
+	struct list_head felist;
 	struct mutex lock;
 	struct dvb_adapter adapter;
 	int active_fe_id; /* Indicates which frontend in the felist is in use */
-	struct videobuf_dvb_frontend frontend;
 	int gate; /* Frontend with gate control 0=!MFE,1=fe0,2=fe1 etc */
 };
 
-- 
cgit v1.2.3


From 953cafc04e9ef9d2fd9f8afb3b3bbde1f8bb9317 Mon Sep 17 00:00:00 2001
From: Darron Broad <darron@kewl.org>
Date: Wed, 15 Oct 2008 14:14:30 -0300
Subject: V4L/DVB (9268): tuner: add FMD1216MEX tuner

This tuner was already supported by proxy as an FMD1216ME, however,
the MEX uses a different FM Radio IF so this addition is now required.

Signed-off-by: Darron Broad <darron@kewl.org>
Signed-off-by: Steven Toth <stoth@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 Documentation/video4linux/CARDLIST.tuner   |  1 +
 drivers/media/common/tuners/tuner-simple.c |  2 ++
 drivers/media/common/tuners/tuner-types.c  | 33 +++++++++++++++++++++++++++++-
 drivers/media/video/tveeprom.c             |  2 +-
 include/media/tuner.h                      |  1 +
 5 files changed, 37 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/Documentation/video4linux/CARDLIST.tuner b/Documentation/video4linux/CARDLIST.tuner
index 30bbdda68d03..691d2f37dc57 100644
--- a/Documentation/video4linux/CARDLIST.tuner
+++ b/Documentation/video4linux/CARDLIST.tuner
@@ -75,3 +75,4 @@ tuner=73 - Samsung TCPG 6121P30A
 tuner=75 - Philips TEA5761 FM Radio
 tuner=76 - Xceive 5000 tuner
 tuner=77 - TCL tuner MF02GIP-5N-E
+tuner=78 - Philips FMD1216MEX MK3 Hybrid Tuner
diff --git a/drivers/media/common/tuners/tuner-simple.c b/drivers/media/common/tuners/tuner-simple.c
index 2a1aac1cc755..fb3f3b3adaba 100644
--- a/drivers/media/common/tuners/tuner-simple.c
+++ b/drivers/media/common/tuners/tuner-simple.c
@@ -493,6 +493,7 @@ static int simple_radio_bandswitch(struct dvb_frontend *fe, u8 *buffer)
 	case TUNER_PHILIPS_FM1216ME_MK3:
 	case TUNER_PHILIPS_FM1236_MK3:
 	case TUNER_PHILIPS_FMD1216ME_MK3:
+	case TUNER_PHILIPS_FMD1216MEX_MK3:
 	case TUNER_LG_NTSC_TAPE:
 	case TUNER_PHILIPS_FM1256_IH3:
 	case TUNER_TCL_MF02GIP_5N:
@@ -767,6 +768,7 @@ static void simple_set_dvb(struct dvb_frontend *fe, u8 *buf,
 
 	switch (priv->type) {
 	case TUNER_PHILIPS_FMD1216ME_MK3:
+	case TUNER_PHILIPS_FMD1216MEX_MK3:
 		if (params->u.ofdm.bandwidth == BANDWIDTH_8_MHZ &&
 		    params->frequency >= 158870000)
 			buf[3] |= 0x08;
diff --git a/drivers/media/common/tuners/tuner-types.c b/drivers/media/common/tuners/tuner-types.c
index 04961a1f44be..7c0bc064c008 100644
--- a/drivers/media/common/tuners/tuner-types.c
+++ b/drivers/media/common/tuners/tuner-types.c
@@ -946,7 +946,7 @@ static struct tuner_params tuner_tena_9533_di_params[] = {
 	},
 };
 
-/* ------------ TUNER_PHILIPS_FMD1216ME_MK3 - Philips PAL ------------ */
+/* ------------ TUNER_PHILIPS_FMD1216ME(X)_MK3 - Philips PAL ------------ */
 
 static struct tuner_range tuner_philips_fmd1216me_mk3_pal_ranges[] = {
 	{ 16 * 160.00 /*MHz*/, 0x86, 0x51, },
@@ -984,6 +984,27 @@ static struct tuner_params tuner_philips_fmd1216me_mk3_params[] = {
 	},
 };
 
+static struct tuner_params tuner_philips_fmd1216mex_mk3_params[] = {
+	{
+		.type   = TUNER_PARAM_TYPE_PAL,
+		.ranges = tuner_philips_fmd1216me_mk3_pal_ranges,
+		.count  = ARRAY_SIZE(tuner_philips_fmd1216me_mk3_pal_ranges),
+		.has_tda9887 = 1,
+		.port1_active = 1,
+		.port2_active = 1,
+		.port2_fm_high_sensitivity = 1,
+		.port2_invert_for_secam_lc = 1,
+		.port1_set_for_fm_mono = 1,
+		.radio_if = 1,
+		.fm_gain_normal = 1,
+	},
+	{
+		.type   = TUNER_PARAM_TYPE_DIGITAL,
+		.ranges = tuner_philips_fmd1216me_mk3_dvb_ranges,
+		.count  = ARRAY_SIZE(tuner_philips_fmd1216me_mk3_dvb_ranges),
+		.iffreq = 16 * 36.125, /*MHz*/
+	},
+};
 
 /* ------ TUNER_LG_TDVS_H06XF - LG INNOTEK / INFINEON ATSC ----- */
 
@@ -1663,6 +1684,16 @@ struct tunertype tuners[] = {
 		.params = tuner_tcl_mf02gip_5n_params,
 		.count  = ARRAY_SIZE(tuner_tcl_mf02gip_5n_params),
 	},
+	[TUNER_PHILIPS_FMD1216MEX_MK3] = { /* Philips PAL */
+		.name   = "Philips FMD1216MEX MK3 Hybrid Tuner",
+		.params = tuner_philips_fmd1216mex_mk3_params,
+		.count  = ARRAY_SIZE(tuner_philips_fmd1216mex_mk3_params),
+		.min = 16 *  50.87,
+		.max = 16 * 858.00,
+		.stepsize = 166667,
+		.initdata = tua603x_agc112,
+		.sleepdata = (u8[]){ 4, 0x9c, 0x60, 0x85, 0x54 },
+	},
 };
 EXPORT_SYMBOL(tuners);
 
diff --git a/drivers/media/video/tveeprom.c b/drivers/media/video/tveeprom.c
index bcc32fa92a81..3b0b84c2e451 100644
--- a/drivers/media/video/tveeprom.c
+++ b/drivers/media/video/tveeprom.c
@@ -242,7 +242,7 @@ hauppauge_tuner[] =
 	{ TUNER_ABSENT,        		"TCL M2523_3DBH_E"},
 	{ TUNER_ABSENT,        		"TCL M2523_3DIH_E"},
 	{ TUNER_ABSENT,        		"TCL MFPE05_2_U"},
-	{ TUNER_PHILIPS_FMD1216ME_MK3,	"Philips FMD1216MEX"},
+	{ TUNER_PHILIPS_FMD1216MEX_MK3,	"Philips FMD1216MEX"},
 	{ TUNER_ABSENT,        		"Philips FRH2036B"},
 	{ TUNER_ABSENT,        		"Panasonic ENGF75_01GF"},
 	{ TUNER_ABSENT,        		"MaxLinear MXL5005"},
diff --git a/include/media/tuner.h b/include/media/tuner.h
index 67c1f514d0e2..7d4e2db78076 100644
--- a/include/media/tuner.h
+++ b/include/media/tuner.h
@@ -123,6 +123,7 @@
 #define TUNER_TEA5761			75	/* Only FM Radio Tuner */
 #define TUNER_XC5000			76	/* Xceive Silicon Tuner */
 #define TUNER_TCL_MF02GIP_5N		77	/* TCL MF02GIP_5N */
+#define TUNER_PHILIPS_FMD1216MEX_MK3	78
 
 /* tv card specific */
 #define TDA9887_PRESENT 		(1<<0)
-- 
cgit v1.2.3


From 96b7a1a838fb5b8746fc22f4ff3cef358bf59f35 Mon Sep 17 00:00:00 2001
From: Darron Broad <darron@kewl.org>
Date: Wed, 15 Oct 2008 20:26:34 -0300
Subject: V4L/DVB (9271): videobuf: data storage optimisation (2)

To optimise data storage even further one other redundant
var has been removed.

This also removes a redundant assignment.

Signed-off-by: Steven Toth <stoth@linuxtv.org>
Signed-off-by: Darron Broad <darron@kewl.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/cx23885/cx23885-dvb.c | 2 +-
 drivers/media/video/cx88/cx88-mpeg.c      | 2 +-
 drivers/media/video/saa7134/saa7134-dvb.c | 2 +-
 drivers/media/video/videobuf-dvb.c        | 7 ++-----
 include/media/videobuf-dvb.h              | 3 +--
 5 files changed, 6 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/drivers/media/video/cx23885/cx23885-dvb.c b/drivers/media/video/cx23885/cx23885-dvb.c
index 8e9871106afa..e1aac07b3158 100644
--- a/drivers/media/video/cx23885/cx23885-dvb.c
+++ b/drivers/media/video/cx23885/cx23885-dvb.c
@@ -571,7 +571,7 @@ int cx23885_dvb_register(struct cx23885_tsport *port)
 		port->num_frontends);
 
 	for (i = 1; i <= port->num_frontends; i++) {
-		if (videobuf_dvb_alloc_frontend(dev,
+		if (videobuf_dvb_alloc_frontend(
 			&port->frontends, i) == NULL) {
 			printk(KERN_ERR "%s() failed to alloc\n", __func__);
 			return -ENOMEM;
diff --git a/drivers/media/video/cx88/cx88-mpeg.c b/drivers/media/video/cx88/cx88-mpeg.c
index 512041451d38..6df5cf314186 100644
--- a/drivers/media/video/cx88/cx88-mpeg.c
+++ b/drivers/media/video/cx88/cx88-mpeg.c
@@ -807,7 +807,7 @@ static int __devinit cx8802_probe(struct pci_dev *pci_dev,
 	printk(KERN_INFO "%s() allocating %d frontend(s)\n", __func__, core->board.num_frontends);
 
 	for (i = 1; i <= core->board.num_frontends; i++) {
-		demod = videobuf_dvb_alloc_frontend(dev, &dev->frontends, i);
+		demod = videobuf_dvb_alloc_frontend(&dev->frontends, i);
 		if(demod == NULL) {
 			printk(KERN_ERR "%s() failed to alloc\n", __func__);
 			err = -ENOMEM;
diff --git a/drivers/media/video/saa7134/saa7134-dvb.c b/drivers/media/video/saa7134/saa7134-dvb.c
index 7d95a6928772..8c46115d4c79 100644
--- a/drivers/media/video/saa7134/saa7134-dvb.c
+++ b/drivers/media/video/saa7134/saa7134-dvb.c
@@ -958,7 +958,7 @@ static int dvb_init(struct saa7134_dev *dev)
 
 	printk(KERN_INFO "%s() allocating 1 frontend\n", __func__);
 
-	if (videobuf_dvb_alloc_frontend(dev, &dev->frontends, 1) == NULL) {
+	if (videobuf_dvb_alloc_frontend(&dev->frontends, 1) == NULL) {
 		printk(KERN_ERR "%s() failed to alloc\n", __func__);
 		return -ENOMEM;
 	}
diff --git a/drivers/media/video/videobuf-dvb.c b/drivers/media/video/videobuf-dvb.c
index 7c74845af267..36b1e67ac330 100644
--- a/drivers/media/video/videobuf-dvb.c
+++ b/drivers/media/video/videobuf-dvb.c
@@ -307,10 +307,8 @@ void videobuf_dvb_unregister_bus(struct videobuf_dvb_frontends *f)
 			dvb_dmx_release(&fe->dvb.demux);
 			dvb_unregister_frontend(fe->dvb.frontend);
 		}
-		if(fe->dvb.frontend) {	/* always allocated, may have been reset */
+		if(fe->dvb.frontend) /* always allocated, may have been reset */
 			dvb_frontend_detach(fe->dvb.frontend);
-			fe->dvb.frontend = NULL;
-		}
 		list_del(list);
 		kfree(fe);
 	}
@@ -360,7 +358,7 @@ int videobuf_dvb_find_frontend(struct videobuf_dvb_frontends *f, struct dvb_fron
 	return ret;
 }
 
-struct videobuf_dvb_frontend * videobuf_dvb_alloc_frontend(void *private, struct videobuf_dvb_frontends *f, int id)
+struct videobuf_dvb_frontend * videobuf_dvb_alloc_frontend(struct videobuf_dvb_frontends *f, int id)
 {
 	struct videobuf_dvb_frontend *fe;
 
@@ -368,7 +366,6 @@ struct videobuf_dvb_frontend * videobuf_dvb_alloc_frontend(void *private, struct
 	if (fe == NULL)
 		goto fail_alloc;
 
-	fe->dev = private;
 	fe->id = id;
 	mutex_init(&fe->dvb.lock);
 
diff --git a/include/media/videobuf-dvb.h b/include/media/videobuf-dvb.h
index 069215c77a65..52ddda90d3f6 100644
--- a/include/media/videobuf-dvb.h
+++ b/include/media/videobuf-dvb.h
@@ -25,7 +25,6 @@ struct videobuf_dvb {
 
 struct videobuf_dvb_frontend {
 	struct list_head felist;
-	void *dev;
 	int id;
 	struct videobuf_dvb dvb;
 };
@@ -57,7 +56,7 @@ int videobuf_dvb_register_adapter(struct videobuf_dvb_frontends *f,
 
 int videobuf_dvb_register_frontend(struct dvb_adapter *adapter, struct videobuf_dvb *dvb);
 
-struct videobuf_dvb_frontend * videobuf_dvb_alloc_frontend(void *private, struct videobuf_dvb_frontends *f, int id);
+struct videobuf_dvb_frontend * videobuf_dvb_alloc_frontend(struct videobuf_dvb_frontends *f, int id);
 
 struct videobuf_dvb_frontend * videobuf_dvb_get_frontend(struct videobuf_dvb_frontends *f, int id);
 int videobuf_dvb_find_frontend(struct videobuf_dvb_frontends *f, struct dvb_frontend *p);
-- 
cgit v1.2.3


From dcadd0826fce17e77cd6260569cbb3dd681c868c Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab@redhat.com>
Date: Fri, 17 Oct 2008 13:02:47 -0300
Subject: V4L/DVB (9276): videobuf-dvb: two functions are now static

This patch marks those two functions as static:
	static int videobuf_dvb_register_adapter(struct videobuf_dvb_frontends *fe,
	static int videobuf_dvb_register_frontend(struct dvb_adapter *adapter,

Since MFE patches changed their calls by videobuf_dvb_register_bus.

To avoid having to declare the prototypes, the patch moves
videobuf_dvb_register_bus() to be after the declaration of the above functions
used there.

Cc: Steven Toth <stoth@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/videobuf-dvb.c | 108 +++++++++++++++++--------------------
 include/media/videobuf-dvb.h       |  10 ----
 2 files changed, 50 insertions(+), 68 deletions(-)

(limited to 'include')

diff --git a/drivers/media/video/videobuf-dvb.c b/drivers/media/video/videobuf-dvb.c
index adf7674b4a02..917277d36605 100644
--- a/drivers/media/video/videobuf-dvb.c
+++ b/drivers/media/video/videobuf-dvb.c
@@ -133,55 +133,7 @@ static int videobuf_dvb_stop_feed(struct dvb_demux_feed *feed)
 	return err;
 }
 
-/* ------------------------------------------------------------------ */
-/* Register a single adapter and one or more frontends */
-int videobuf_dvb_register_bus(struct videobuf_dvb_frontends *f,
-			  struct module *module,
-			  void *adapter_priv,
-			  struct device *device,
-			  short *adapter_nr,
-			  int mfe_shared)
-{
-	struct list_head *list, *q;
-	struct videobuf_dvb_frontend *fe;
-	int res;
-
-	fe = videobuf_dvb_get_frontend(f, 1);
-	if (!fe) {
-		printk(KERN_WARNING "Unable to register the adapter which has no frontends\n");
-		return -EINVAL;
-	}
-
-	/* Bring up the adapter */
-	res = videobuf_dvb_register_adapter(f, module, adapter_priv, device,
-		fe->dvb.name, adapter_nr, mfe_shared);
-	if (res < 0) {
-		printk(KERN_WARNING "videobuf_dvb_register_adapter failed (errno = %d)\n", res);
-		return res;
-	}
-
-	/* Attach all of the frontends to the adapter */
-	mutex_lock(&f->lock);
-	list_for_each_safe(list, q, &f->felist) {
-		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
-		res = videobuf_dvb_register_frontend(&f->adapter, &fe->dvb);
-		if (res < 0) {
-			printk(KERN_WARNING "%s: videobuf_dvb_register_frontend failed (errno = %d)\n",
-				fe->dvb.name, res);
-			goto err;
-		}
-	}
-	mutex_unlock(&f->lock);
-	return 0;
-
-err:
-	mutex_unlock(&f->lock);
-	videobuf_dvb_unregister_bus(f);
-	return res;
-}
-EXPORT_SYMBOL(videobuf_dvb_register_bus);
-
-int videobuf_dvb_register_adapter(struct videobuf_dvb_frontends *fe,
+static int videobuf_dvb_register_adapter(struct videobuf_dvb_frontends *fe,
 			  struct module *module,
 			  void *adapter_priv,
 			  struct device *device,
@@ -206,7 +158,7 @@ int videobuf_dvb_register_adapter(struct videobuf_dvb_frontends *fe,
 	return result;
 }
 
-int videobuf_dvb_register_frontend(struct dvb_adapter *adapter,
+static int videobuf_dvb_register_frontend(struct dvb_adapter *adapter,
 	struct videobuf_dvb *dvb)
 {
 	int result;
@@ -294,6 +246,54 @@ fail_frontend:
 	return result;
 }
 
+/* ------------------------------------------------------------------ */
+/* Register a single adapter and one or more frontends */
+int videobuf_dvb_register_bus(struct videobuf_dvb_frontends *f,
+			  struct module *module,
+			  void *adapter_priv,
+			  struct device *device,
+			  short *adapter_nr,
+			  int mfe_shared)
+{
+	struct list_head *list, *q;
+	struct videobuf_dvb_frontend *fe;
+	int res;
+
+	fe = videobuf_dvb_get_frontend(f, 1);
+	if (!fe) {
+		printk(KERN_WARNING "Unable to register the adapter which has no frontends\n");
+		return -EINVAL;
+	}
+
+	/* Bring up the adapter */
+	res = videobuf_dvb_register_adapter(f, module, adapter_priv, device,
+		fe->dvb.name, adapter_nr, mfe_shared);
+	if (res < 0) {
+		printk(KERN_WARNING "videobuf_dvb_register_adapter failed (errno = %d)\n", res);
+		return res;
+	}
+
+	/* Attach all of the frontends to the adapter */
+	mutex_lock(&f->lock);
+	list_for_each_safe(list, q, &f->felist) {
+		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
+		res = videobuf_dvb_register_frontend(&f->adapter, &fe->dvb);
+		if (res < 0) {
+			printk(KERN_WARNING "%s: videobuf_dvb_register_frontend failed (errno = %d)\n",
+				fe->dvb.name, res);
+			goto err;
+		}
+	}
+	mutex_unlock(&f->lock);
+	return 0;
+
+err:
+	mutex_unlock(&f->lock);
+	videobuf_dvb_unregister_bus(f);
+	return res;
+}
+EXPORT_SYMBOL(videobuf_dvb_register_bus);
+
 void videobuf_dvb_unregister_bus(struct videobuf_dvb_frontends *f)
 {
 	struct list_head *list, *q;
@@ -389,11 +389,3 @@ fail_alloc:
 	return fe;
 }
 EXPORT_SYMBOL(videobuf_dvb_alloc_frontend);
-
-/* ------------------------------------------------------------------ */
-/*
- * Local variables:
- * c-basic-offset: 8
- * compile-command: "make DVB=1"
- * End:
- */
diff --git a/include/media/videobuf-dvb.h b/include/media/videobuf-dvb.h
index 52ddda90d3f6..80471c2b6343 100644
--- a/include/media/videobuf-dvb.h
+++ b/include/media/videobuf-dvb.h
@@ -46,16 +46,6 @@ int videobuf_dvb_register_bus(struct videobuf_dvb_frontends *f,
 
 void videobuf_dvb_unregister_bus(struct videobuf_dvb_frontends *f);
 
-int videobuf_dvb_register_adapter(struct videobuf_dvb_frontends *f,
-			  struct module *module,
-			  void *adapter_priv,
-			  struct device *device,
-			  char *adapter_name,
-			  short *adapter_nr,
-			  int mfe_shared);
-
-int videobuf_dvb_register_frontend(struct dvb_adapter *adapter, struct videobuf_dvb *dvb);
-
 struct videobuf_dvb_frontend * videobuf_dvb_alloc_frontend(struct videobuf_dvb_frontends *f, int id);
 
 struct videobuf_dvb_frontend * videobuf_dvb_get_frontend(struct videobuf_dvb_frontends *f, int id);
-- 
cgit v1.2.3


From ddb7f4cb819fb6b9df261ce4c80b3c6f4852620d Mon Sep 17 00:00:00 2001
From: "Carlos R. Mafra" <crmafra2@gmail.com>
Date: Wed, 30 Jul 2008 12:29:37 -0700
Subject: drm: remove #define's for non-linux systems

There is no point in considering FreeBSD et al.  in the linux kernel
source code.

Signed-off-by: Carlos R. Mafra <crmafra@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 include/drm/drm.h | 17 -----------------
 1 file changed, 17 deletions(-)

(limited to 'include')

diff --git a/include/drm/drm.h b/include/drm/drm.h
index 38d3c6b8276a..0864c6920941 100644
--- a/include/drm/drm.h
+++ b/include/drm/drm.h
@@ -36,7 +36,6 @@
 #ifndef _DRM_H_
 #define _DRM_H_
 
-#if defined(__linux__)
 #if defined(__KERNEL__)
 #endif
 #include <asm/ioctl.h>		/* For _IO* macros */
@@ -46,22 +45,6 @@
 #define DRM_IOC_WRITE		_IOC_WRITE
 #define DRM_IOC_READWRITE	_IOC_READ|_IOC_WRITE
 #define DRM_IOC(dir, group, nr, size) _IOC(dir, group, nr, size)
-#elif defined(__FreeBSD__) || defined(__NetBSD__) || defined(__OpenBSD__)
-#if defined(__FreeBSD__) && defined(IN_MODULE)
-/* Prevent name collision when including sys/ioccom.h */
-#undef ioctl
-#include <sys/ioccom.h>
-#define ioctl(a,b,c)		xf86ioctl(a,b,c)
-#else
-#include <sys/ioccom.h>
-#endif				/* __FreeBSD__ && xf86ioctl */
-#define DRM_IOCTL_NR(n)		((n) & 0xff)
-#define DRM_IOC_VOID		IOC_VOID
-#define DRM_IOC_READ		IOC_OUT
-#define DRM_IOC_WRITE		IOC_IN
-#define DRM_IOC_READWRITE	IOC_INOUT
-#define DRM_IOC(dir, group, nr, size) _IOC(dir, group, nr, size)
-#endif
 
 #define DRM_MAJOR       226
 #define DRM_MAX_MINOR   15
-- 
cgit v1.2.3


From 0a3e67a4caac273a3bfc4ced3da364830b1ab241 Mon Sep 17 00:00:00 2001
From: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Tue, 30 Sep 2008 12:14:26 -0700
Subject: drm: Rework vblank-wait handling to allow interrupt reduction.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Previously, drivers supporting vblank interrupt waits would run the interrupt
all the time, or all the time that any 3d client was running, preventing the
CPU from sleeping for long when the system was otherwise idle.  Now, interrupts
are disabled any time that no client is waiting on a vblank event. The new
method uses vblank counters on the chipsets when the interrupts are turned
off, rather than counting interrupts, so that we can continue to present
accurate vblank numbers.

Co-author: Michel Dänzer <michel@tungstengraphics.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_drv.c           |   2 +
 drivers/gpu/drm/drm_irq.c           | 447 ++++++++++++++++++++++++++++++------
 drivers/gpu/drm/i915/i915_dma.c     |   5 +-
 drivers/gpu/drm/i915/i915_drv.c     |  11 +-
 drivers/gpu/drm/i915/i915_drv.h     |  20 +-
 drivers/gpu/drm/i915/i915_irq.c     | 395 ++++++++++++++++++++-----------
 drivers/gpu/drm/mga/mga_drv.c       |  29 +--
 drivers/gpu/drm/mga/mga_drv.h       |   6 +-
 drivers/gpu/drm/mga/mga_irq.c       |  74 ++++--
 drivers/gpu/drm/r128/r128_drv.c     |  29 +--
 drivers/gpu/drm/r128/r128_drv.h     |  11 +-
 drivers/gpu/drm/r128/r128_irq.c     |  55 +++--
 drivers/gpu/drm/radeon/radeon_cp.c  |   2 +-
 drivers/gpu/drm/radeon/radeon_drv.c |  32 ++-
 drivers/gpu/drm/radeon/radeon_drv.h |  27 ++-
 drivers/gpu/drm/radeon/radeon_irq.c | 268 +++++++++++++--------
 drivers/gpu/drm/via/via_drv.c       |  26 ++-
 drivers/gpu/drm/via/via_drv.h       |  16 +-
 drivers/gpu/drm/via/via_irq.c       | 102 ++++----
 include/drm/drm.h                   |  15 ++
 include/drm/drmP.h                  |  90 +++++++-
 21 files changed, 1189 insertions(+), 473 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 452c2d866ec5..fb45fe7aeb8c 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -116,6 +116,8 @@ static struct drm_ioctl_desc drm_ioctls[] = {
 
 	DRM_IOCTL_DEF(DRM_IOCTL_WAIT_VBLANK, drm_wait_vblank, 0),
 
+	DRM_IOCTL_DEF(DRM_IOCTL_MODESET_CTL, drm_modeset_ctl, 0),
+
 	DRM_IOCTL_DEF(DRM_IOCTL_UPDATE_DRAW, drm_update_drawable_info, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 };
 
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index 61ed5158f783..d0c13d954f52 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -71,19 +71,131 @@ int drm_irq_by_busid(struct drm_device *dev, void *data,
 	return 0;
 }
 
+static void vblank_disable_fn(unsigned long arg)
+{
+	struct drm_device *dev = (struct drm_device *)arg;
+	unsigned long irqflags;
+	int i;
+
+	if (!dev->vblank_disable_allowed)
+		return;
+
+	for (i = 0; i < dev->num_crtcs; i++) {
+		spin_lock_irqsave(&dev->vbl_lock, irqflags);
+		if (atomic_read(&dev->vblank_refcount[i]) == 0 &&
+		    dev->vblank_enabled[i]) {
+			DRM_DEBUG("disabling vblank on crtc %d\n", i);
+			dev->last_vblank[i] =
+				dev->driver->get_vblank_counter(dev, i);
+			dev->driver->disable_vblank(dev, i);
+			dev->vblank_enabled[i] = 0;
+		}
+		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
+	}
+}
+
+static void drm_vblank_cleanup(struct drm_device *dev)
+{
+	/* Bail if the driver didn't call drm_vblank_init() */
+	if (dev->num_crtcs == 0)
+		return;
+
+	del_timer(&dev->vblank_disable_timer);
+
+	vblank_disable_fn((unsigned long)dev);
+
+	drm_free(dev->vbl_queue, sizeof(*dev->vbl_queue) * dev->num_crtcs,
+		 DRM_MEM_DRIVER);
+	drm_free(dev->vbl_sigs, sizeof(*dev->vbl_sigs) * dev->num_crtcs,
+		 DRM_MEM_DRIVER);
+	drm_free(dev->_vblank_count, sizeof(*dev->_vblank_count) *
+		 dev->num_crtcs, DRM_MEM_DRIVER);
+	drm_free(dev->vblank_refcount, sizeof(*dev->vblank_refcount) *
+		 dev->num_crtcs, DRM_MEM_DRIVER);
+	drm_free(dev->vblank_enabled, sizeof(*dev->vblank_enabled) *
+		 dev->num_crtcs, DRM_MEM_DRIVER);
+	drm_free(dev->last_vblank, sizeof(*dev->last_vblank) * dev->num_crtcs,
+		 DRM_MEM_DRIVER);
+	drm_free(dev->vblank_inmodeset, sizeof(*dev->vblank_inmodeset) *
+		 dev->num_crtcs, DRM_MEM_DRIVER);
+
+	dev->num_crtcs = 0;
+}
+
+int drm_vblank_init(struct drm_device *dev, int num_crtcs)
+{
+	int i, ret = -ENOMEM;
+
+	setup_timer(&dev->vblank_disable_timer, vblank_disable_fn,
+		    (unsigned long)dev);
+	spin_lock_init(&dev->vbl_lock);
+	atomic_set(&dev->vbl_signal_pending, 0);
+	dev->num_crtcs = num_crtcs;
+
+	dev->vbl_queue = drm_alloc(sizeof(wait_queue_head_t) * num_crtcs,
+				   DRM_MEM_DRIVER);
+	if (!dev->vbl_queue)
+		goto err;
+
+	dev->vbl_sigs = drm_alloc(sizeof(struct list_head) * num_crtcs,
+				  DRM_MEM_DRIVER);
+	if (!dev->vbl_sigs)
+		goto err;
+
+	dev->_vblank_count = drm_alloc(sizeof(atomic_t) * num_crtcs,
+				      DRM_MEM_DRIVER);
+	if (!dev->_vblank_count)
+		goto err;
+
+	dev->vblank_refcount = drm_alloc(sizeof(atomic_t) * num_crtcs,
+					 DRM_MEM_DRIVER);
+	if (!dev->vblank_refcount)
+		goto err;
+
+	dev->vblank_enabled = drm_calloc(num_crtcs, sizeof(int),
+					 DRM_MEM_DRIVER);
+	if (!dev->vblank_enabled)
+		goto err;
+
+	dev->last_vblank = drm_calloc(num_crtcs, sizeof(u32), DRM_MEM_DRIVER);
+	if (!dev->last_vblank)
+		goto err;
+
+	dev->vblank_inmodeset = drm_calloc(num_crtcs, sizeof(int),
+					 DRM_MEM_DRIVER);
+	if (!dev->vblank_inmodeset)
+		goto err;
+
+	/* Zero per-crtc vblank stuff */
+	for (i = 0; i < num_crtcs; i++) {
+		init_waitqueue_head(&dev->vbl_queue[i]);
+		INIT_LIST_HEAD(&dev->vbl_sigs[i]);
+		atomic_set(&dev->_vblank_count[i], 0);
+		atomic_set(&dev->vblank_refcount[i], 0);
+	}
+
+	dev->vblank_disable_allowed = 0;
+
+	return 0;
+
+err:
+	drm_vblank_cleanup(dev);
+	return ret;
+}
+EXPORT_SYMBOL(drm_vblank_init);
+
 /**
  * Install IRQ handler.
  *
  * \param dev DRM device.
- * \param irq IRQ number.
  *
- * Initializes the IRQ related data, and setups drm_device::vbl_queue. Installs the handler, calling the driver
+ * Initializes the IRQ related data. Installs the handler, calling the driver
  * \c drm_driver_irq_preinstall() and \c drm_driver_irq_postinstall() functions
  * before and after the installation.
  */
-static int drm_irq_install(struct drm_device * dev)
+int drm_irq_install(struct drm_device *dev)
 {
-	int ret;
+	int ret = 0;
 	unsigned long sh_flags = 0;
 
 	if (!drm_core_check_feature(dev, DRIVER_HAVE_IRQ))
@@ -109,17 +221,6 @@ static int drm_irq_install(struct drm_device * dev)
 
 	DRM_DEBUG("irq=%d\n", dev->pdev->irq);
 
-	if (drm_core_check_feature(dev, DRIVER_IRQ_VBL)) {
-		init_waitqueue_head(&dev->vbl_queue);
-
-		spin_lock_init(&dev->vbl_lock);
-
-		INIT_LIST_HEAD(&dev->vbl_sigs);
-		INIT_LIST_HEAD(&dev->vbl_sigs2);
-
-		dev->vbl_pending = 0;
-	}
-
 	/* Before installing handler */
 	dev->driver->irq_preinstall(dev);
 
@@ -141,10 +242,16 @@ static int drm_irq_install(struct drm_device * dev)
 	}
 
 	/* After installing handler */
-	dev->driver->irq_postinstall(dev);
+	ret = dev->driver->irq_postinstall(dev);
+	if (ret < 0) {
+		mutex_lock(&dev->struct_mutex);
+		dev->irq_enabled = 0;
+		mutex_unlock(&dev->struct_mutex);
+	}
 
-	return 0;
+	return ret;
 }
+EXPORT_SYMBOL(drm_irq_install);
 
 /**
  * Uninstall the IRQ handler.
@@ -174,11 +281,12 @@ int drm_irq_uninstall(struct drm_device * dev)
 
 	free_irq(dev->pdev->irq, dev);
 
+	drm_vblank_cleanup(dev);
+
 	dev->locked_tasklet_func = NULL;
 
 	return 0;
 }
-
 EXPORT_SYMBOL(drm_irq_uninstall);
 
 /**
@@ -217,6 +325,174 @@ int drm_control(struct drm_device *dev, void *data,
 	}
 }
 
+/**
+ * drm_vblank_count - retrieve "cooked" vblank counter value
+ * @dev: DRM device
+ * @crtc: which counter to retrieve
+ *
+ * Fetches the "cooked" vblank count value that represents the number of
+ * vblank events since the system was booted, including lost events due to
+ * modesetting activity.
+ */
+u32 drm_vblank_count(struct drm_device *dev, int crtc)
+{
+	return atomic_read(&dev->_vblank_count[crtc]);
+}
+EXPORT_SYMBOL(drm_vblank_count);
+
+/**
+ * drm_update_vblank_count - update the master vblank counter
+ * @dev: DRM device
+ * @crtc: counter to update
+ *
+ * Call back into the driver to update the appropriate vblank counter
+ * (specified by @crtc).  Deal with wraparound, if it occurred, and
+ * update the last read value so we can deal with wraparound on the next
+ * call if necessary.
+ *
+ * Only necessary when going from off->on, to account for frames we
+ * didn't get an interrupt for.
+ *
+ * Note: caller must hold dev->vbl_lock since this reads & writes
+ * device vblank fields.
+ */
+static void drm_update_vblank_count(struct drm_device *dev, int crtc)
+{
+	u32 cur_vblank, diff;
+
+	/*
+	 * Interrupts were disabled prior to this call, so deal with counter
+	 * wrap if needed.
+	 * NOTE!  It's possible we lost a full dev->max_vblank_count events
+	 * here if the register is small or we had vblank interrupts off for
+	 * a long time.
+	 */
+	cur_vblank = dev->driver->get_vblank_counter(dev, crtc);
+	diff = cur_vblank - dev->last_vblank[crtc];
+	if (cur_vblank < dev->last_vblank[crtc]) {
+		diff += dev->max_vblank_count;
+
+		DRM_DEBUG("last_vblank[%d]=0x%x, cur_vblank=0x%x => diff=0x%x\n",
+			  crtc, dev->last_vblank[crtc], cur_vblank, diff);
+	}
+
+	DRM_DEBUG("enabling vblank interrupts on crtc %d, missed %d\n",
+		  crtc, diff);
+
+	atomic_add(diff, &dev->_vblank_count[crtc]);
+}
+
+/**
+ * drm_vblank_get - get a reference count on vblank events
+ * @dev: DRM device
+ * @crtc: which CRTC to own
+ *
+ * Acquire a reference count on vblank events to avoid having them disabled
+ * while in use.
+ *
+ * RETURNS
+ * Zero on success, nonzero on failure.
+ */
+int drm_vblank_get(struct drm_device *dev, int crtc)
+{
+	unsigned long irqflags;
+	int ret = 0;
+
+	spin_lock_irqsave(&dev->vbl_lock, irqflags);
+	/* Going from 0->1 means we have to enable interrupts again */
+	if (atomic_add_return(1, &dev->vblank_refcount[crtc]) == 1 &&
+	    !dev->vblank_enabled[crtc]) {
+		ret = dev->driver->enable_vblank(dev, crtc);
+		DRM_DEBUG("enabling vblank on crtc %d, ret: %d\n", crtc, ret);
+		if (ret)
+			atomic_dec(&dev->vblank_refcount[crtc]);
+		else {
+			dev->vblank_enabled[crtc] = 1;
+			drm_update_vblank_count(dev, crtc);
+		}
+	}
+	spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_vblank_get);
+
+/**
+ * drm_vblank_put - give up ownership of vblank events
+ * @dev: DRM device
+ * @crtc: which counter to give up
+ *
+ * Release ownership of a given vblank counter, turning off interrupts
+ * if possible.
+ */
+void drm_vblank_put(struct drm_device *dev, int crtc)
+{
+	/* Last user schedules interrupt disable */
+	if (atomic_dec_and_test(&dev->vblank_refcount[crtc]))
+		mod_timer(&dev->vblank_disable_timer, jiffies + 5*DRM_HZ);
+}
+EXPORT_SYMBOL(drm_vblank_put);
+
+/**
+ * drm_modeset_ctl - handle vblank event counter changes across mode switch
+ * @DRM_IOCTL_ARGS: standard ioctl arguments
+ *
+ * Applications should call the %_DRM_PRE_MODESET and %_DRM_POST_MODESET
+ * ioctls around modesetting so that any lost vblank events are accounted for.
+ *
+ * Generally the counter will reset across mode sets.  If interrupts are
+ * enabled around this call, we don't have to do anything since the counter
+ * will have already been incremented.
+ */
+int drm_modeset_ctl(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv)
+{
+	struct drm_modeset_ctl *modeset = data;
+	unsigned long irqflags;
+	int crtc, ret = 0;
+
+	/* If drm_vblank_init() hasn't been called yet, just no-op */
+	if (!dev->num_crtcs)
+		goto out;
+
+	crtc = modeset->crtc;
+	if (crtc >= dev->num_crtcs) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	/*
+	 * To avoid all the problems that might happen if interrupts
+	 * were enabled/disabled around or between these calls, we just
+	 * have the kernel take a reference on the CRTC (just once though
+	 * to avoid corrupting the count if multiple, mismatch calls occur),
+	 * so that interrupts remain enabled in the interim.
+	 */
+	switch (modeset->cmd) {
+	case _DRM_PRE_MODESET:
+		if (!dev->vblank_inmodeset[crtc]) {
+			dev->vblank_inmodeset[crtc] = 1;
+			drm_vblank_get(dev, crtc);
+		}
+		break;
+	case _DRM_POST_MODESET:
+		if (dev->vblank_inmodeset[crtc]) {
+			spin_lock_irqsave(&dev->vbl_lock, irqflags);
+			dev->vblank_disable_allowed = 1;
+			dev->vblank_inmodeset[crtc] = 0;
+			spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
+			drm_vblank_put(dev, crtc);
+		}
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+out:
+	return ret;
+}
+
 /**
  * Wait for VBLANK.
  *
@@ -236,12 +512,12 @@ int drm_control(struct drm_device *dev, void *data,
  *
  * If a signal is not requested, then calls vblank_wait().
  */
-int drm_wait_vblank(struct drm_device *dev, void *data, struct drm_file *file_priv)
+int drm_wait_vblank(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv)
 {
 	union drm_wait_vblank *vblwait = data;
-	struct timeval now;
 	int ret = 0;
-	unsigned int flags, seq;
+	unsigned int flags, seq, crtc;
 
 	if ((!dev->pdev->irq) || (!dev->irq_enabled))
 		return -EINVAL;
@@ -255,13 +531,17 @@ int drm_wait_vblank(struct drm_device *dev, void *data, struct drm_file *file_pr
 	}
 
 	flags = vblwait->request.type & _DRM_VBLANK_FLAGS_MASK;
+	crtc = flags & _DRM_VBLANK_SECONDARY ? 1 : 0;
 
-	if (!drm_core_check_feature(dev, (flags & _DRM_VBLANK_SECONDARY) ?
-				    DRIVER_IRQ_VBL2 : DRIVER_IRQ_VBL))
+	if (crtc >= dev->num_crtcs)
 		return -EINVAL;
 
-	seq = atomic_read((flags & _DRM_VBLANK_SECONDARY) ? &dev->vbl_received2
-			  : &dev->vbl_received);
+	ret = drm_vblank_get(dev, crtc);
+	if (ret) {
+		DRM_ERROR("failed to acquire vblank counter, %d\n", ret);
+		return ret;
+	}
+	seq = drm_vblank_count(dev, crtc);
 
 	switch (vblwait->request.type & _DRM_VBLANK_TYPES_MASK) {
 	case _DRM_VBLANK_RELATIVE:
@@ -270,7 +550,8 @@ int drm_wait_vblank(struct drm_device *dev, void *data, struct drm_file *file_pr
 	case _DRM_VBLANK_ABSOLUTE:
 		break;
 	default:
-		return -EINVAL;
+		ret = -EINVAL;
+		goto done;
 	}
 
 	if ((flags & _DRM_VBLANK_NEXTONMISS) &&
@@ -280,8 +561,7 @@ int drm_wait_vblank(struct drm_device *dev, void *data, struct drm_file *file_pr
 
 	if (flags & _DRM_VBLANK_SIGNAL) {
 		unsigned long irqflags;
-		struct list_head *vbl_sigs = (flags & _DRM_VBLANK_SECONDARY)
-				      ? &dev->vbl_sigs2 : &dev->vbl_sigs;
+		struct list_head *vbl_sigs = &dev->vbl_sigs[crtc];
 		struct drm_vbl_sig *vbl_sig;
 
 		spin_lock_irqsave(&dev->vbl_lock, irqflags);
@@ -302,22 +582,29 @@ int drm_wait_vblank(struct drm_device *dev, void *data, struct drm_file *file_pr
 			}
 		}
 
-		if (dev->vbl_pending >= 100) {
+		if (atomic_read(&dev->vbl_signal_pending) >= 100) {
 			spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
-			return -EBUSY;
+			ret = -EBUSY;
+			goto done;
 		}
 
-		dev->vbl_pending++;
-
 		spin_unlock_irqrestore(&dev->vbl_lock, irqflags);
 
-		if (!
-		    (vbl_sig =
-		     drm_alloc(sizeof(struct drm_vbl_sig), DRM_MEM_DRIVER))) {
-			return -ENOMEM;
+		vbl_sig = drm_calloc(1, sizeof(struct drm_vbl_sig),
+				     DRM_MEM_DRIVER);
+		if (!vbl_sig) {
+			ret = -ENOMEM;
+			goto done;
+		}
+
+		ret = drm_vblank_get(dev, crtc);
+		if (ret) {
+			drm_free(vbl_sig, sizeof(struct drm_vbl_sig),
+				 DRM_MEM_DRIVER);
+			return ret;
 		}
 
-		memset((void *)vbl_sig, 0, sizeof(*vbl_sig));
+		atomic_inc(&dev->vbl_signal_pending);
 
 		vbl_sig->sequence = vblwait->request.sequence;
 		vbl_sig->info.si_signo = vblwait->request.signal;
@@ -331,20 +618,29 @@ int drm_wait_vblank(struct drm_device *dev, void *data, struct drm_file *file_pr
 
 		vblwait->reply.sequence = seq;
 	} else {
-		if (flags & _DRM_VBLANK_SECONDARY) {
-			if (dev->driver->vblank_wait2)
-				ret = dev->driver->vblank_wait2(dev, &vblwait->request.sequence);
-		} else if (dev->driver->vblank_wait)
-			ret =
-			    dev->driver->vblank_wait(dev,
-						     &vblwait->request.sequence);
-
-		do_gettimeofday(&now);
-		vblwait->reply.tval_sec = now.tv_sec;
-		vblwait->reply.tval_usec = now.tv_usec;
+		DRM_DEBUG("waiting on vblank count %d, crtc %d\n",
+			  vblwait->request.sequence, crtc);
+		DRM_WAIT_ON(ret, dev->vbl_queue[crtc], 3 * DRM_HZ,
+			    ((drm_vblank_count(dev, crtc)
+			      - vblwait->request.sequence) <= (1 << 23)));
+
+		if (ret != -EINTR) {
+			struct timeval now;
+
+			do_gettimeofday(&now);
+
+			vblwait->reply.tval_sec = now.tv_sec;
+			vblwait->reply.tval_usec = now.tv_usec;
+			vblwait->reply.sequence = drm_vblank_count(dev, crtc);
+			DRM_DEBUG("returning %d to client\n",
+				  vblwait->reply.sequence);
+		} else {
+			DRM_DEBUG("vblank wait interrupted by signal\n");
+		}
 	}
 
-      done:
+done:
+	drm_vblank_put(dev, crtc);
 	return ret;
 }
 
@@ -352,44 +648,57 @@ int drm_wait_vblank(struct drm_device *dev, void *data, struct drm_file *file_pr
  * Send the VBLANK signals.
  *
  * \param dev DRM device.
+ * \param crtc CRTC where the vblank event occurred
  *
  * Sends a signal for each task in drm_device::vbl_sigs and empties the list.
  *
  * If a signal is not requested, then calls vblank_wait().
  */
-void drm_vbl_send_signals(struct drm_device * dev)
+static void drm_vbl_send_signals(struct drm_device *dev, int crtc)
 {
+	struct drm_vbl_sig *vbl_sig, *tmp;
+	struct list_head *vbl_sigs;
+	unsigned int vbl_seq;
 	unsigned long flags;
-	int i;
 
 	spin_lock_irqsave(&dev->vbl_lock, flags);
 
-	for (i = 0; i < 2; i++) {
-		struct drm_vbl_sig *vbl_sig, *tmp;
-		struct list_head *vbl_sigs = i ? &dev->vbl_sigs2 : &dev->vbl_sigs;
-		unsigned int vbl_seq = atomic_read(i ? &dev->vbl_received2 :
-						   &dev->vbl_received);
+	vbl_sigs = &dev->vbl_sigs[crtc];
+	vbl_seq = drm_vblank_count(dev, crtc);
 
-		list_for_each_entry_safe(vbl_sig, tmp, vbl_sigs, head) {
-			if ((vbl_seq - vbl_sig->sequence) <= (1 << 23)) {
-				vbl_sig->info.si_code = vbl_seq;
-				send_sig_info(vbl_sig->info.si_signo,
-					      &vbl_sig->info, vbl_sig->task);
+	list_for_each_entry_safe(vbl_sig, tmp, vbl_sigs, head) {
+	    if ((vbl_seq - vbl_sig->sequence) <= (1 << 23)) {
+		vbl_sig->info.si_code = vbl_seq;
+		send_sig_info(vbl_sig->info.si_signo,
+			      &vbl_sig->info, vbl_sig->task);
 
-				list_del(&vbl_sig->head);
-
-				drm_free(vbl_sig, sizeof(*vbl_sig),
-					 DRM_MEM_DRIVER);
+		list_del(&vbl_sig->head);
 
-				dev->vbl_pending--;
-			}
-		}
+		drm_free(vbl_sig, sizeof(*vbl_sig),
+			 DRM_MEM_DRIVER);
+		atomic_dec(&dev->vbl_signal_pending);
+		drm_vblank_put(dev, crtc);
+	    }
 	}
 
 	spin_unlock_irqrestore(&dev->vbl_lock, flags);
 }
 
-EXPORT_SYMBOL(drm_vbl_send_signals);
+/**
+ * drm_handle_vblank - handle a vblank event
+ * @dev: DRM device
+ * @crtc: where this event occurred
+ *
+ * Drivers should call this routine in their vblank interrupt handlers to
+ * update the vblank counter and send any signals that may be pending.
+ */
+void drm_handle_vblank(struct drm_device *dev, int crtc)
+{
+	atomic_inc(&dev->_vblank_count[crtc]);
+	DRM_WAKEUP(&dev->vbl_queue[crtc]);
+	drm_vbl_send_signals(dev, crtc);
+}
+EXPORT_SYMBOL(drm_handle_vblank);
 
 /**
  * Tasklet wrapper function.
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 29115450ee46..63c6803d471b 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -673,7 +673,7 @@ static int i915_getparam(struct drm_device *dev, void *data,
 
 	switch (param->param) {
 	case I915_PARAM_IRQ_ACTIVE:
-		value = dev->irq_enabled;
+		value = dev->pdev->irq ? 1 : 0;
 		break;
 	case I915_PARAM_ALLOW_BATCHBUFFER:
 		value = dev_priv->allow_batchbuffer ? 1 : 0;
@@ -808,7 +808,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	 * and the registers being closely associated.
 	 */
 	if (!IS_I945G(dev) && !IS_I945GM(dev))
-		pci_enable_msi(dev->pdev);
+		if (pci_enable_msi(dev->pdev))
+			DRM_ERROR("failed to enable MSI\n");
 
 	intel_opregion_init(dev);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index eff66ed3e58e..37af03f4db36 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -85,10 +85,8 @@ static struct drm_driver driver = {
 	/* don't use mtrr's here, the Xserver or user space app should
 	 * deal with them for intel hardware.
 	 */
-	.driver_features =
-	    DRIVER_USE_AGP | DRIVER_REQUIRE_AGP | /* DRIVER_USE_MTRR |*/
-	    DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_IRQ_VBL |
-	    DRIVER_IRQ_VBL2,
+	.driver_features = DRIVER_USE_AGP | DRIVER_REQUIRE_AGP |
+		DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED,
 	.load = i915_driver_load,
 	.unload = i915_driver_unload,
 	.lastclose = i915_driver_lastclose,
@@ -96,8 +94,9 @@ static struct drm_driver driver = {
 	.suspend = i915_suspend,
 	.resume = i915_resume,
 	.device_is_agp = i915_driver_device_is_agp,
-	.vblank_wait = i915_driver_vblank_wait,
-	.vblank_wait2 = i915_driver_vblank_wait2,
+	.get_vblank_counter = i915_get_vblank_counter,
+	.enable_vblank = i915_enable_vblank,
+	.disable_vblank = i915_disable_vblank,
 	.irq_preinstall = i915_driver_irq_preinstall,
 	.irq_postinstall = i915_driver_irq_postinstall,
 	.irq_uninstall = i915_driver_irq_uninstall,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 71326ca9367a..d1a02bead458 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -83,10 +83,15 @@ struct mem_block {
 typedef struct _drm_i915_vbl_swap {
 	struct list_head head;
 	drm_drawable_t drw_id;
-	unsigned int pipe;
+	unsigned int plane;
 	unsigned int sequence;
 } drm_i915_vbl_swap_t;
 
+struct opregion_header;
+struct opregion_acpi;
+struct opregion_swsci;
+struct opregion_asle;
+
 struct intel_opregion {
 	struct opregion_header *header;
 	struct opregion_acpi *acpi;
@@ -105,7 +110,7 @@ typedef struct drm_i915_private {
 	drm_dma_handle_t *status_page_dmah;
 	void *hw_status_page;
 	dma_addr_t dma_status_page;
-	unsigned long counter;
+	uint32_t counter;
 	unsigned int status_gfx_addr;
 	drm_local_map_t hws_map;
 
@@ -247,16 +252,17 @@ extern int i915_irq_emit(struct drm_device *dev, void *data,
 extern int i915_irq_wait(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
 
-extern int i915_driver_vblank_wait(struct drm_device *dev, unsigned int *sequence);
-extern int i915_driver_vblank_wait2(struct drm_device *dev, unsigned int *sequence);
 extern irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS);
 extern void i915_driver_irq_preinstall(struct drm_device * dev);
-extern void i915_driver_irq_postinstall(struct drm_device * dev);
+extern int i915_driver_irq_postinstall(struct drm_device *dev);
 extern void i915_driver_irq_uninstall(struct drm_device * dev);
 extern int i915_vblank_pipe_set(struct drm_device *dev, void *data,
 				struct drm_file *file_priv);
 extern int i915_vblank_pipe_get(struct drm_device *dev, void *data,
 				struct drm_file *file_priv);
+extern int i915_enable_vblank(struct drm_device *dev, int crtc);
+extern void i915_disable_vblank(struct drm_device *dev, int crtc);
+extern u32 i915_get_vblank_counter(struct drm_device *dev, int crtc);
 extern int i915_vblank_swap(struct drm_device *dev, void *data,
 			    struct drm_file *file_priv);
 extern void i915_enable_irq(drm_i915_private_t *dev_priv, u32 mask);
@@ -278,6 +284,10 @@ extern void i915_mem_release(struct drm_device * dev,
 extern int i915_save_state(struct drm_device *dev);
 extern int i915_restore_state(struct drm_device *dev);
 
+/* i915_suspend.c */
+extern int i915_save_state(struct drm_device *dev);
+extern int i915_restore_state(struct drm_device *dev);
+
 /* i915_opregion.c */
 extern int intel_opregion_init(struct drm_device *dev);
 extern void intel_opregion_free(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index ae7d3a82a6d1..f8759597233b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -35,9 +35,8 @@
 
 /** These are the interrupts used by the driver */
 #define I915_INTERRUPT_ENABLE_MASK (I915_USER_INTERRUPT |		\
-				    I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT | \
-				    I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT | \
 				    I915_ASLE_INTERRUPT |		\
+				    I915_DISPLAY_PIPE_A_EVENT_INTERRUPT | \
 				    I915_DISPLAY_PIPE_B_EVENT_INTERRUPT)
 
 void
@@ -60,6 +59,64 @@ i915_disable_irq(drm_i915_private_t *dev_priv, u32 mask)
 	}
 }
 
+/**
+ * i915_get_pipe - return the the pipe associated with a given plane
+ * @dev: DRM device
+ * @plane: plane to look for
+ *
+ * The Intel Mesa & 2D drivers call the vblank routines with a plane number
+ * rather than a pipe number, since they may not always be equal.  This routine
+ * maps the given @plane back to a pipe number.
+ */
+static int
+i915_get_pipe(struct drm_device *dev, int plane)
+{
+	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+	u32 dspcntr;
+
+	dspcntr = plane ? I915_READ(DSPBCNTR) : I915_READ(DSPACNTR);
+
+	return dspcntr & DISPPLANE_SEL_PIPE_MASK ? 1 : 0;
+}
+
+/**
+ * i915_get_plane - return the the plane associated with a given pipe
+ * @dev: DRM device
+ * @pipe: pipe to look for
+ *
+ * The Intel Mesa & 2D drivers call the vblank routines with a plane number
+ * rather than a plane number, since they may not always be equal.  This routine
+ * maps the given @pipe back to a plane number.
+ */
+static int
+i915_get_plane(struct drm_device *dev, int pipe)
+{
+	if (i915_get_pipe(dev, 0) == pipe)
+		return 0;
+	return 1;
+}
+
+/**
+ * i915_pipe_enabled - check if a pipe is enabled
+ * @dev: DRM device
+ * @pipe: pipe to check
+ *
+ * Reading certain registers when the pipe is disabled can hang the chip.
+ * Use this routine to make sure the PLL is running and the pipe is active
+ * before reading such registers if unsure.
+ */
+static int
+i915_pipe_enabled(struct drm_device *dev, int pipe)
+{
+	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+	unsigned long pipeconf = pipe ? PIPEBCONF : PIPEACONF;
+
+	if (I915_READ(pipeconf) & PIPEACONF_ENABLE)
+		return 1;
+
+	return 0;
+}
+
 /**
  * Emit blits for scheduled buffer swaps.
  *
@@ -71,8 +128,7 @@ static void i915_vblank_tasklet(struct drm_device *dev)
 	unsigned long irqflags;
 	struct list_head *list, *tmp, hits, *hit;
 	int nhits, nrects, slice[2], upper[2], lower[2], i;
-	unsigned counter[2] = { atomic_read(&dev->vbl_received),
-				atomic_read(&dev->vbl_received2) };
+	unsigned counter[2];
 	struct drm_drawable_info *drw;
 	drm_i915_sarea_t *sarea_priv = dev_priv->sarea_priv;
 	u32 cpp = dev_priv->cpp;
@@ -94,6 +150,9 @@ static void i915_vblank_tasklet(struct drm_device *dev)
 		src_pitch >>= 2;
 	}
 
+	counter[0] = drm_vblank_count(dev, 0);
+	counter[1] = drm_vblank_count(dev, 1);
+
 	DRM_DEBUG("\n");
 
 	INIT_LIST_HEAD(&hits);
@@ -106,12 +165,14 @@ static void i915_vblank_tasklet(struct drm_device *dev)
 	list_for_each_safe(list, tmp, &dev_priv->vbl_swaps.head) {
 		drm_i915_vbl_swap_t *vbl_swap =
 			list_entry(list, drm_i915_vbl_swap_t, head);
+		int pipe = i915_get_pipe(dev, vbl_swap->plane);
 
-		if ((counter[vbl_swap->pipe] - vbl_swap->sequence) > (1<<23))
+		if ((counter[pipe] - vbl_swap->sequence) > (1<<23))
 			continue;
 
 		list_del(list);
 		dev_priv->swaps_pending--;
+		drm_vblank_put(dev, pipe);
 
 		spin_unlock(&dev_priv->swaps_lock);
 		spin_lock(&dev->drw_lock);
@@ -204,7 +265,7 @@ static void i915_vblank_tasklet(struct drm_device *dev)
 			drm_i915_vbl_swap_t *swap_hit =
 				list_entry(hit, drm_i915_vbl_swap_t, head);
 			struct drm_clip_rect *rect;
-			int num_rects, pipe;
+			int num_rects, plane;
 			unsigned short top, bottom;
 
 			drw = drm_get_drawable_info(dev, swap_hit->drw_id);
@@ -213,9 +274,9 @@ static void i915_vblank_tasklet(struct drm_device *dev)
 				continue;
 
 			rect = drw->rects;
-			pipe = swap_hit->pipe;
-			top = upper[pipe];
-			bottom = lower[pipe];
+			plane = swap_hit->plane;
+			top = upper[plane];
+			bottom = lower[plane];
 
 			for (num_rects = drw->num_rects; num_rects--; rect++) {
 				int y1 = max(rect->y1, top);
@@ -252,22 +313,54 @@ static void i915_vblank_tasklet(struct drm_device *dev)
 	}
 }
 
+u32 i915_get_vblank_counter(struct drm_device *dev, int plane)
+{
+	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+	unsigned long high_frame;
+	unsigned long low_frame;
+	u32 high1, high2, low, count;
+	int pipe;
+
+	pipe = i915_get_pipe(dev, plane);
+	high_frame = pipe ? PIPEBFRAMEHIGH : PIPEAFRAMEHIGH;
+	low_frame = pipe ? PIPEBFRAMEPIXEL : PIPEAFRAMEPIXEL;
+
+	if (!i915_pipe_enabled(dev, pipe)) {
+		DRM_ERROR("trying to get vblank count for disabled pipe %d\n", pipe);
+		return 0;
+	}
+
+	/*
+	 * High & low register fields aren't synchronized, so make sure
+	 * we get a low value that's stable across two reads of the high
+	 * register.
+	 */
+	do {
+		high1 = ((I915_READ(high_frame) & PIPE_FRAME_HIGH_MASK) >>
+			 PIPE_FRAME_HIGH_SHIFT);
+		low =  ((I915_READ(low_frame) & PIPE_FRAME_LOW_MASK) >>
+			PIPE_FRAME_LOW_SHIFT);
+		high2 = ((I915_READ(high_frame) & PIPE_FRAME_HIGH_MASK) >>
+			 PIPE_FRAME_HIGH_SHIFT);
+	} while (high1 != high2);
+
+	count = (high1 << 8) | low;
+
+	return count;
+}
+
 irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	u32 pipea_stats, pipeb_stats;
 	u32 iir;
-
-	pipea_stats = I915_READ(PIPEASTAT);
-	pipeb_stats = I915_READ(PIPEBSTAT);
+	u32 pipea_stats, pipeb_stats;
+	int vblank = 0;
 
 	if (dev->pdev->msi_enabled)
 		I915_WRITE(IMR, ~0);
 	iir = I915_READ(IIR);
 
-	DRM_DEBUG("iir=%08x\n", iir);
-
 	if (iir == 0) {
 		if (dev->pdev->msi_enabled) {
 			I915_WRITE(IMR, dev_priv->irq_mask_reg);
@@ -276,48 +369,56 @@ irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS)
 		return IRQ_NONE;
 	}
 
-	I915_WRITE(PIPEASTAT, pipea_stats);
-	I915_WRITE(PIPEBSTAT, pipeb_stats);
-
-	I915_WRITE(IIR, iir);
-	if (dev->pdev->msi_enabled)
-		I915_WRITE(IMR, dev_priv->irq_mask_reg);
-	(void) I915_READ(IIR); /* Flush posted writes */
-
-	dev_priv->sarea_priv->last_dispatch = READ_BREADCRUMB(dev_priv);
-
-	if (iir & I915_USER_INTERRUPT)
-		DRM_WAKEUP(&dev_priv->irq_queue);
-
-	if (iir & (I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT |
-		   I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT)) {
-		int vblank_pipe = dev_priv->vblank_pipe;
-
-		if ((vblank_pipe &
-		     (DRM_I915_VBLANK_PIPE_A | DRM_I915_VBLANK_PIPE_B))
-		    == (DRM_I915_VBLANK_PIPE_A | DRM_I915_VBLANK_PIPE_B)) {
-			if (iir & I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT)
-				atomic_inc(&dev->vbl_received);
-			if (iir & I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT)
-				atomic_inc(&dev->vbl_received2);
-		} else if (((iir & I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT) &&
-			    (vblank_pipe & DRM_I915_VBLANK_PIPE_A)) ||
-			   ((iir & I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT) &&
-			    (vblank_pipe & DRM_I915_VBLANK_PIPE_B)))
-			atomic_inc(&dev->vbl_received);
+	/*
+	 * Clear the PIPE(A|B)STAT regs before the IIR otherwise
+	 * we may get extra interrupts.
+	 */
+	if (iir & I915_DISPLAY_PIPE_A_EVENT_INTERRUPT) {
+		pipea_stats = I915_READ(PIPEASTAT);
+		if (!(dev_priv->vblank_pipe & DRM_I915_VBLANK_PIPE_A))
+			pipea_stats &= ~(PIPE_START_VBLANK_INTERRUPT_ENABLE |
+					 PIPE_VBLANK_INTERRUPT_ENABLE);
+		else if (pipea_stats & (PIPE_START_VBLANK_INTERRUPT_STATUS|
+					PIPE_VBLANK_INTERRUPT_STATUS)) {
+			vblank++;
+			drm_handle_vblank(dev, i915_get_plane(dev, 0));
+		}
 
-		DRM_WAKEUP(&dev->vbl_queue);
-		drm_vbl_send_signals(dev);
+		I915_WRITE(PIPEASTAT, pipea_stats);
+	}
+	if (iir & I915_DISPLAY_PIPE_B_EVENT_INTERRUPT) {
+		pipeb_stats = I915_READ(PIPEBSTAT);
+		/* Ack the event */
+		I915_WRITE(PIPEBSTAT, pipeb_stats);
+
+		/* The vblank interrupt gets enabled even if we didn't ask for
+		   it, so make sure it's shut down again */
+		if (!(dev_priv->vblank_pipe & DRM_I915_VBLANK_PIPE_B))
+			pipeb_stats &= ~(PIPE_START_VBLANK_INTERRUPT_ENABLE |
+					 PIPE_VBLANK_INTERRUPT_ENABLE);
+		else if (pipeb_stats & (PIPE_START_VBLANK_INTERRUPT_STATUS|
+					PIPE_VBLANK_INTERRUPT_STATUS)) {
+			vblank++;
+			drm_handle_vblank(dev, i915_get_plane(dev, 1));
+		}
 
-		if (dev_priv->swaps_pending > 0)
-			drm_locked_tasklet(dev, i915_vblank_tasklet);
+		if (pipeb_stats & I915_LEGACY_BLC_EVENT_STATUS)
+			opregion_asle_intr(dev);
+		I915_WRITE(PIPEBSTAT, pipeb_stats);
 	}
 
 	if (iir & I915_ASLE_INTERRUPT)
 		opregion_asle_intr(dev);
 
-	if (iir & I915_DISPLAY_PIPE_B_EVENT_INTERRUPT)
-		opregion_asle_intr(dev);
+	dev_priv->sarea_priv->last_dispatch = READ_BREADCRUMB(dev_priv);
+
+	if (dev->pdev->msi_enabled)
+		I915_WRITE(IMR, dev_priv->irq_mask_reg);
+	I915_WRITE(IIR, iir);
+	(void) I915_READ(IIR);
+
+	if (vblank && dev_priv->swaps_pending > 0)
+		drm_locked_tasklet(dev, i915_vblank_tasklet);
 
 	return IRQ_HANDLED;
 }
@@ -358,7 +459,7 @@ static void i915_user_irq_get(struct drm_device *dev)
 	spin_unlock(&dev_priv->user_irq_lock);
 }
 
-static void i915_user_irq_put(struct drm_device *dev)
+void i915_user_irq_put(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
@@ -395,41 +496,10 @@ static int i915_wait_irq(struct drm_device * dev, int irq_nr)
 	}
 
 	dev_priv->sarea_priv->last_dispatch = READ_BREADCRUMB(dev_priv);
-	return ret;
-}
-
-static int i915_driver_vblank_do_wait(struct drm_device *dev, unsigned int *sequence,
-				      atomic_t *counter)
-{
-	drm_i915_private_t *dev_priv = dev->dev_private;
-	unsigned int cur_vblank;
-	int ret = 0;
-
-	if (!dev_priv) {
-		DRM_ERROR("called with no initialization\n");
-		return -EINVAL;
-	}
-
-	DRM_WAIT_ON(ret, dev->vbl_queue, 3 * DRM_HZ,
-		    (((cur_vblank = atomic_read(counter))
-			- *sequence) <= (1<<23)));
-
-	*sequence = cur_vblank;
 
 	return ret;
 }
 
-
-int i915_driver_vblank_wait(struct drm_device *dev, unsigned int *sequence)
-{
-	return i915_driver_vblank_do_wait(dev, sequence, &dev->vbl_received);
-}
-
-int i915_driver_vblank_wait2(struct drm_device *dev, unsigned int *sequence)
-{
-	return i915_driver_vblank_do_wait(dev, sequence, &dev->vbl_received2);
-}
-
 /* Needs the lock as it touches the ring.
  */
 int i915_irq_emit(struct drm_device *dev, void *data,
@@ -472,40 +542,88 @@ int i915_irq_wait(struct drm_device *dev, void *data,
 	return i915_wait_irq(dev, irqwait->irq_seq);
 }
 
+int i915_enable_vblank(struct drm_device *dev, int plane)
+{
+	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+	int pipe = i915_get_pipe(dev, plane);
+	u32	pipestat_reg = 0;
+	u32	pipestat;
+
+	switch (pipe) {
+	case 0:
+		pipestat_reg = PIPEASTAT;
+		i915_enable_irq(dev_priv, I915_DISPLAY_PIPE_A_EVENT_INTERRUPT);
+		break;
+	case 1:
+		pipestat_reg = PIPEBSTAT;
+		i915_enable_irq(dev_priv, I915_DISPLAY_PIPE_B_EVENT_INTERRUPT);
+		break;
+	default:
+		DRM_ERROR("tried to enable vblank on non-existent pipe %d\n",
+			  pipe);
+		break;
+	}
+
+	if (pipestat_reg) {
+		pipestat = I915_READ(pipestat_reg);
+		if (IS_I965G(dev))
+			pipestat |= PIPE_START_VBLANK_INTERRUPT_ENABLE;
+		else
+			pipestat |= PIPE_VBLANK_INTERRUPT_ENABLE;
+		/* Clear any stale interrupt status */
+		pipestat |= (PIPE_START_VBLANK_INTERRUPT_STATUS |
+			     PIPE_VBLANK_INTERRUPT_STATUS);
+		I915_WRITE(pipestat_reg, pipestat);
+	}
+
+	return 0;
+}
+
+void i915_disable_vblank(struct drm_device *dev, int plane)
+{
+	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+	int pipe = i915_get_pipe(dev, plane);
+	u32	pipestat_reg = 0;
+	u32	pipestat;
+
+	switch (pipe) {
+	case 0:
+		pipestat_reg = PIPEASTAT;
+		i915_disable_irq(dev_priv, I915_DISPLAY_PIPE_A_EVENT_INTERRUPT);
+		break;
+	case 1:
+		pipestat_reg = PIPEBSTAT;
+		i915_disable_irq(dev_priv, I915_DISPLAY_PIPE_B_EVENT_INTERRUPT);
+		break;
+	default:
+		DRM_ERROR("tried to disable vblank on non-existent pipe %d\n",
+			  pipe);
+		break;
+	}
+
+	if (pipestat_reg) {
+		pipestat = I915_READ(pipestat_reg);
+		pipestat &= ~(PIPE_START_VBLANK_INTERRUPT_ENABLE |
+			      PIPE_VBLANK_INTERRUPT_ENABLE);
+		/* Clear any stale interrupt status */
+		pipestat |= (PIPE_START_VBLANK_INTERRUPT_STATUS |
+			     PIPE_VBLANK_INTERRUPT_STATUS);
+		I915_WRITE(pipestat_reg, pipestat);
+	}
+}
+
 /* Set the vblank monitor pipe
  */
 int i915_vblank_pipe_set(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	drm_i915_vblank_pipe_t *pipe = data;
-	u32 enable_mask = 0, disable_mask = 0;
 
 	if (!dev_priv) {
 		DRM_ERROR("called with no initialization\n");
 		return -EINVAL;
 	}
 
-	if (pipe->pipe & ~(DRM_I915_VBLANK_PIPE_A|DRM_I915_VBLANK_PIPE_B)) {
-		DRM_ERROR("called with invalid pipe 0x%x\n", pipe->pipe);
-		return -EINVAL;
-	}
-
-	if (pipe->pipe & DRM_I915_VBLANK_PIPE_A)
-		enable_mask |= I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT;
-	else
-		disable_mask |= I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT;
-
-	if (pipe->pipe & DRM_I915_VBLANK_PIPE_B)
-		enable_mask |= I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT;
-	else
-		disable_mask |= I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT;
-
-	i915_enable_irq(dev_priv, enable_mask);
-	i915_disable_irq(dev_priv, disable_mask);
-
-	dev_priv->vblank_pipe = pipe->pipe;
-
 	return 0;
 }
 
@@ -514,19 +632,13 @@ int i915_vblank_pipe_get(struct drm_device *dev, void *data,
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	drm_i915_vblank_pipe_t *pipe = data;
-	u16 flag;
 
 	if (!dev_priv) {
 		DRM_ERROR("called with no initialization\n");
 		return -EINVAL;
 	}
 
-	flag = I915_READ(IMR);
-	pipe->pipe = 0;
-	if (flag & I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT)
-		pipe->pipe |= DRM_I915_VBLANK_PIPE_A;
-	if (flag & I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT)
-		pipe->pipe |= DRM_I915_VBLANK_PIPE_B;
+	pipe->pipe = DRM_I915_VBLANK_PIPE_A | DRM_I915_VBLANK_PIPE_B;
 
 	return 0;
 }
@@ -540,9 +652,10 @@ int i915_vblank_swap(struct drm_device *dev, void *data,
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	drm_i915_vblank_swap_t *swap = data;
 	drm_i915_vbl_swap_t *vbl_swap;
-	unsigned int pipe, seqtype, curseq;
+	unsigned int pipe, seqtype, curseq, plane;
 	unsigned long irqflags;
 	struct list_head *list;
+	int ret;
 
 	if (!dev_priv) {
 		DRM_ERROR("%s called with no initialization\n", __func__);
@@ -560,7 +673,8 @@ int i915_vblank_swap(struct drm_device *dev, void *data,
 		return -EINVAL;
 	}
 
-	pipe = (swap->seqtype & _DRM_VBLANK_SECONDARY) ? 1 : 0;
+	plane = (swap->seqtype & _DRM_VBLANK_SECONDARY) ? 1 : 0;
+	pipe = i915_get_pipe(dev, plane);
 
 	seqtype = swap->seqtype & (_DRM_VBLANK_RELATIVE | _DRM_VBLANK_ABSOLUTE);
 
@@ -579,7 +693,14 @@ int i915_vblank_swap(struct drm_device *dev, void *data,
 
 	spin_unlock_irqrestore(&dev->drw_lock, irqflags);
 
-	curseq = atomic_read(pipe ? &dev->vbl_received2 : &dev->vbl_received);
+	/*
+	 * We take the ref here and put it when the swap actually completes
+	 * in the tasklet.
+	 */
+	ret = drm_vblank_get(dev, pipe);
+	if (ret)
+		return ret;
+	curseq = drm_vblank_count(dev, pipe);
 
 	if (seqtype == _DRM_VBLANK_RELATIVE)
 		swap->sequence += curseq;
@@ -589,6 +710,7 @@ int i915_vblank_swap(struct drm_device *dev, void *data,
 			swap->sequence = curseq + 1;
 		} else {
 			DRM_DEBUG("Missed target sequence\n");
+			drm_vblank_put(dev, pipe);
 			return -EINVAL;
 		}
 	}
@@ -599,7 +721,7 @@ int i915_vblank_swap(struct drm_device *dev, void *data,
 		vbl_swap = list_entry(list, drm_i915_vbl_swap_t, head);
 
 		if (vbl_swap->drw_id == swap->drawable &&
-		    vbl_swap->pipe == pipe &&
+		    vbl_swap->plane == plane &&
 		    vbl_swap->sequence == swap->sequence) {
 			spin_unlock_irqrestore(&dev_priv->swaps_lock, irqflags);
 			DRM_DEBUG("Already scheduled\n");
@@ -611,6 +733,7 @@ int i915_vblank_swap(struct drm_device *dev, void *data,
 
 	if (dev_priv->swaps_pending >= 100) {
 		DRM_DEBUG("Too many swaps queued\n");
+		drm_vblank_put(dev, pipe);
 		return -EBUSY;
 	}
 
@@ -618,13 +741,14 @@ int i915_vblank_swap(struct drm_device *dev, void *data,
 
 	if (!vbl_swap) {
 		DRM_ERROR("Failed to allocate memory to queue swap\n");
+		drm_vblank_put(dev, pipe);
 		return -ENOMEM;
 	}
 
 	DRM_DEBUG("\n");
 
 	vbl_swap->drw_id = swap->drawable;
-	vbl_swap->pipe = pipe;
+	vbl_swap->plane = plane;
 	vbl_swap->sequence = swap->sequence;
 
 	spin_lock_irqsave(&dev_priv->swaps_lock, irqflags);
@@ -643,28 +767,32 @@ void i915_driver_irq_preinstall(struct drm_device * dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
-	I915_WRITE(HWSTAM, 0xfffe);
-	I915_WRITE(IMR, 0x0);
+	I915_WRITE(HWSTAM, 0xeffe);
+	I915_WRITE(IMR, 0xffffffff);
 	I915_WRITE(IER, 0x0);
 }
 
-void i915_driver_irq_postinstall(struct drm_device * dev)
+int i915_driver_irq_postinstall(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+	int ret, num_pipes = 2;
 
 	spin_lock_init(&dev_priv->swaps_lock);
 	INIT_LIST_HEAD(&dev_priv->vbl_swaps.head);
 	dev_priv->swaps_pending = 0;
 
-	if (!dev_priv->vblank_pipe)
-		dev_priv->vblank_pipe = DRM_I915_VBLANK_PIPE_A;
-
 	/* Set initial unmasked IRQs to just the selected vblank pipes. */
 	dev_priv->irq_mask_reg = ~0;
-	if (dev_priv->vblank_pipe & DRM_I915_VBLANK_PIPE_A)
-		dev_priv->irq_mask_reg &= ~I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT;
-	if (dev_priv->vblank_pipe & DRM_I915_VBLANK_PIPE_B)
-		dev_priv->irq_mask_reg &= ~I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT;
+
+	ret = drm_vblank_init(dev, num_pipes);
+	if (ret)
+		return ret;
+
+	dev_priv->vblank_pipe = DRM_I915_VBLANK_PIPE_A | DRM_I915_VBLANK_PIPE_B;
+	dev_priv->irq_mask_reg &= ~I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT;
+	dev_priv->irq_mask_reg &= ~I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT;
+
+	dev->max_vblank_count = 0xffffff; /* only 24 bits of frame count */
 
 	dev_priv->irq_mask_reg &= I915_INTERRUPT_ENABLE_MASK;
 
@@ -673,22 +801,29 @@ void i915_driver_irq_postinstall(struct drm_device * dev)
 	(void) I915_READ(IER);
 
 	opregion_enable_asle(dev);
-
 	DRM_INIT_WAITQUEUE(&dev_priv->irq_queue);
+
+	return 0;
 }
 
 void i915_driver_irq_uninstall(struct drm_device * dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
-	u16 temp;
+	u32 temp;
 
 	if (!dev_priv)
 		return;
 
-	I915_WRITE(HWSTAM, 0xffff);
-	I915_WRITE(IMR, 0xffff);
+	dev_priv->vblank_pipe = 0;
+
+	I915_WRITE(HWSTAM, 0xffffffff);
+	I915_WRITE(IMR, 0xffffffff);
 	I915_WRITE(IER, 0x0);
 
+	temp = I915_READ(PIPEASTAT);
+	I915_WRITE(PIPEASTAT, temp);
+	temp = I915_READ(PIPEBSTAT);
+	I915_WRITE(PIPEBSTAT, temp);
 	temp = I915_READ(IIR);
 	I915_WRITE(IIR, temp);
 }
diff --git a/drivers/gpu/drm/mga/mga_drv.c b/drivers/gpu/drm/mga/mga_drv.c
index 5572939fc7d1..97ee566ef749 100644
--- a/drivers/gpu/drm/mga/mga_drv.c
+++ b/drivers/gpu/drm/mga/mga_drv.c
@@ -45,15 +45,16 @@ static struct pci_device_id pciidlist[] = {
 static struct drm_driver driver = {
 	.driver_features =
 	    DRIVER_USE_AGP | DRIVER_USE_MTRR | DRIVER_PCI_DMA |
-	    DRIVER_HAVE_DMA | DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED |
-	    DRIVER_IRQ_VBL,
+	    DRIVER_HAVE_DMA | DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED,
 	.dev_priv_size = sizeof(drm_mga_buf_priv_t),
 	.load = mga_driver_load,
 	.unload = mga_driver_unload,
 	.lastclose = mga_driver_lastclose,
 	.dma_quiescent = mga_driver_dma_quiescent,
 	.device_is_agp = mga_driver_device_is_agp,
-	.vblank_wait = mga_driver_vblank_wait,
+	.get_vblank_counter = mga_get_vblank_counter,
+	.enable_vblank = mga_enable_vblank,
+	.disable_vblank = mga_disable_vblank,
 	.irq_preinstall = mga_driver_irq_preinstall,
 	.irq_postinstall = mga_driver_irq_postinstall,
 	.irq_uninstall = mga_driver_irq_uninstall,
@@ -64,20 +65,20 @@ static struct drm_driver driver = {
 	.ioctls = mga_ioctls,
 	.dma_ioctl = mga_dma_buffers,
 	.fops = {
-		 .owner = THIS_MODULE,
-		 .open = drm_open,
-		 .release = drm_release,
-		 .ioctl = drm_ioctl,
-		 .mmap = drm_mmap,
-		 .poll = drm_poll,
-		 .fasync = drm_fasync,
+		.owner = THIS_MODULE,
+		.open = drm_open,
+		.release = drm_release,
+		.ioctl = drm_ioctl,
+		.mmap = drm_mmap,
+		.poll = drm_poll,
+		.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
-		 .compat_ioctl = mga_compat_ioctl,
+		.compat_ioctl = mga_compat_ioctl,
 #endif
-		 },
+	},
 	.pci_driver = {
-		 .name = DRIVER_NAME,
-		 .id_table = pciidlist,
+		.name = DRIVER_NAME,
+		.id_table = pciidlist,
 	},
 
 	.name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/mga/mga_drv.h b/drivers/gpu/drm/mga/mga_drv.h
index f6ebd24bd587..88257c276eb9 100644
--- a/drivers/gpu/drm/mga/mga_drv.h
+++ b/drivers/gpu/drm/mga/mga_drv.h
@@ -120,6 +120,7 @@ typedef struct drm_mga_private {
 	u32 clear_cmd;
 	u32 maccess;
 
+	atomic_t vbl_received;          /**< Number of vblanks received. */
 	wait_queue_head_t fence_queue;
 	atomic_t last_fence_retired;
 	u32 next_fence_to_post;
@@ -181,11 +182,14 @@ extern int mga_warp_install_microcode(drm_mga_private_t * dev_priv);
 extern int mga_warp_init(drm_mga_private_t * dev_priv);
 
 				/* mga_irq.c */
+extern int mga_enable_vblank(struct drm_device *dev, int crtc);
+extern void mga_disable_vblank(struct drm_device *dev, int crtc);
+extern u32 mga_get_vblank_counter(struct drm_device *dev, int crtc);
 extern int mga_driver_fence_wait(struct drm_device * dev, unsigned int *sequence);
 extern int mga_driver_vblank_wait(struct drm_device * dev, unsigned int *sequence);
 extern irqreturn_t mga_driver_irq_handler(DRM_IRQ_ARGS);
 extern void mga_driver_irq_preinstall(struct drm_device * dev);
-extern void mga_driver_irq_postinstall(struct drm_device * dev);
+extern int mga_driver_irq_postinstall(struct drm_device *dev);
 extern void mga_driver_irq_uninstall(struct drm_device * dev);
 extern long mga_compat_ioctl(struct file *filp, unsigned int cmd,
 			     unsigned long arg);
diff --git a/drivers/gpu/drm/mga/mga_irq.c b/drivers/gpu/drm/mga/mga_irq.c
index 9302cb8f0f83..bab42f41188b 100644
--- a/drivers/gpu/drm/mga/mga_irq.c
+++ b/drivers/gpu/drm/mga/mga_irq.c
@@ -1,5 +1,6 @@
 /* mga_irq.c -- IRQ handling for radeon -*- linux-c -*-
- *
+ */
+/*
  * Copyright (C) The Weather Channel, Inc.  2002.  All Rights Reserved.
  *
  * The Weather Channel (TM) funded Tungsten Graphics to develop the
@@ -35,6 +36,18 @@
 #include "mga_drm.h"
 #include "mga_drv.h"
 
+u32 mga_get_vblank_counter(struct drm_device *dev, int crtc)
+{
+	const drm_mga_private_t *const dev_priv =
+		(drm_mga_private_t *) dev->dev_private;
+
+	if (crtc != 0)
+		return 0;
+
+	return atomic_read(&dev_priv->vbl_received);
+}
+
+
 irqreturn_t mga_driver_irq_handler(DRM_IRQ_ARGS)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
@@ -47,9 +60,8 @@ irqreturn_t mga_driver_irq_handler(DRM_IRQ_ARGS)
 	/* VBLANK interrupt */
 	if (status & MGA_VLINEPEN) {
 		MGA_WRITE(MGA_ICLEAR, MGA_VLINEICLR);
-		atomic_inc(&dev->vbl_received);
-		DRM_WAKEUP(&dev->vbl_queue);
-		drm_vbl_send_signals(dev);
+		atomic_inc(&dev_priv->vbl_received);
+		drm_handle_vblank(dev, 0);
 		handled = 1;
 	}
 
@@ -58,6 +70,7 @@ irqreturn_t mga_driver_irq_handler(DRM_IRQ_ARGS)
 		const u32 prim_start = MGA_READ(MGA_PRIMADDRESS);
 		const u32 prim_end = MGA_READ(MGA_PRIMEND);
 
+
 		MGA_WRITE(MGA_ICLEAR, MGA_SOFTRAPICLR);
 
 		/* In addition to clearing the interrupt-pending bit, we
@@ -72,28 +85,39 @@ irqreturn_t mga_driver_irq_handler(DRM_IRQ_ARGS)
 		handled = 1;
 	}
 
-	if (handled) {
+	if (handled)
 		return IRQ_HANDLED;
-	}
 	return IRQ_NONE;
 }
 
-int mga_driver_vblank_wait(struct drm_device * dev, unsigned int *sequence)
+int mga_enable_vblank(struct drm_device *dev, int crtc)
 {
-	unsigned int cur_vblank;
-	int ret = 0;
+	drm_mga_private_t *dev_priv = (drm_mga_private_t *) dev->dev_private;
 
-	/* Assume that the user has missed the current sequence number
-	 * by about a day rather than she wants to wait for years
-	 * using vertical blanks...
-	 */
-	DRM_WAIT_ON(ret, dev->vbl_queue, 3 * DRM_HZ,
-		    (((cur_vblank = atomic_read(&dev->vbl_received))
-		      - *sequence) <= (1 << 23)));
+	if (crtc != 0) {
+		DRM_ERROR("tried to enable vblank on non-existent crtc %d\n",
+			  crtc);
+		return 0;
+	}
 
-	*sequence = cur_vblank;
+	MGA_WRITE(MGA_IEN, MGA_VLINEIEN | MGA_SOFTRAPEN);
+	return 0;
+}
 
-	return ret;
+
+void mga_disable_vblank(struct drm_device *dev, int crtc)
+{
+	if (crtc != 0) {
+		DRM_ERROR("tried to disable vblank on non-existent crtc %d\n",
+			  crtc);
+	}
+
+	/* Do *NOT* disable the vertical refresh interrupt.  MGA doesn't have
+	 * a nice hardware counter that tracks the number of refreshes when
+	 * the interrupt is disabled, and the kernel doesn't know the refresh
+	 * rate to calculate an estimate.
+	 */
+	/* MGA_WRITE(MGA_IEN, MGA_VLINEIEN | MGA_SOFTRAPEN); */
 }
 
 int mga_driver_fence_wait(struct drm_device * dev, unsigned int *sequence)
@@ -125,14 +149,22 @@ void mga_driver_irq_preinstall(struct drm_device * dev)
 	MGA_WRITE(MGA_ICLEAR, ~0);
 }
 
-void mga_driver_irq_postinstall(struct drm_device * dev)
+int mga_driver_irq_postinstall(struct drm_device *dev)
 {
 	drm_mga_private_t *dev_priv = (drm_mga_private_t *) dev->dev_private;
+	int ret;
+
+	ret = drm_vblank_init(dev, 1);
+	if (ret)
+		return ret;
 
 	DRM_INIT_WAITQUEUE(&dev_priv->fence_queue);
 
-	/* Turn on vertical blank interrupt and soft trap interrupt. */
-	MGA_WRITE(MGA_IEN, MGA_VLINEIEN | MGA_SOFTRAPEN);
+	/* Turn on soft trap interrupt.  Vertical blank interrupts are enabled
+	 * in mga_enable_vblank.
+	 */
+	MGA_WRITE(MGA_IEN, MGA_SOFTRAPEN);
+	return 0;
 }
 
 void mga_driver_irq_uninstall(struct drm_device * dev)
diff --git a/drivers/gpu/drm/r128/r128_drv.c b/drivers/gpu/drm/r128/r128_drv.c
index 6108e7587e12..3265d53ba91f 100644
--- a/drivers/gpu/drm/r128/r128_drv.c
+++ b/drivers/gpu/drm/r128/r128_drv.c
@@ -43,12 +43,13 @@ static struct pci_device_id pciidlist[] = {
 static struct drm_driver driver = {
 	.driver_features =
 	    DRIVER_USE_AGP | DRIVER_USE_MTRR | DRIVER_PCI_DMA | DRIVER_SG |
-	    DRIVER_HAVE_DMA | DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED |
-	    DRIVER_IRQ_VBL,
+	    DRIVER_HAVE_DMA | DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED,
 	.dev_priv_size = sizeof(drm_r128_buf_priv_t),
 	.preclose = r128_driver_preclose,
 	.lastclose = r128_driver_lastclose,
-	.vblank_wait = r128_driver_vblank_wait,
+	.get_vblank_counter = r128_get_vblank_counter,
+	.enable_vblank = r128_enable_vblank,
+	.disable_vblank = r128_disable_vblank,
 	.irq_preinstall = r128_driver_irq_preinstall,
 	.irq_postinstall = r128_driver_irq_postinstall,
 	.irq_uninstall = r128_driver_irq_uninstall,
@@ -59,21 +60,20 @@ static struct drm_driver driver = {
 	.ioctls = r128_ioctls,
 	.dma_ioctl = r128_cce_buffers,
 	.fops = {
-		 .owner = THIS_MODULE,
-		 .open = drm_open,
-		 .release = drm_release,
-		 .ioctl = drm_ioctl,
-		 .mmap = drm_mmap,
-		 .poll = drm_poll,
-		 .fasync = drm_fasync,
+		.owner = THIS_MODULE,
+		.open = drm_open,
+		.release = drm_release,
+		.ioctl = drm_ioctl,
+		.mmap = drm_mmap,
+		.poll = drm_poll,
+		.fasync = drm_fasync,
 #ifdef CONFIG_COMPAT
-		 .compat_ioctl = r128_compat_ioctl,
+		.compat_ioctl = r128_compat_ioctl,
 #endif
 	},
-
 	.pci_driver = {
-		 .name = DRIVER_NAME,
-		 .id_table = pciidlist,
+		.name = DRIVER_NAME,
+		.id_table = pciidlist,
 	},
 
 	.name = DRIVER_NAME,
@@ -87,6 +87,7 @@ static struct drm_driver driver = {
 static int __init r128_init(void)
 {
 	driver.num_ioctls = r128_max_ioctl;
+
 	return drm_init(&driver);
 }
 
diff --git a/drivers/gpu/drm/r128/r128_drv.h b/drivers/gpu/drm/r128/r128_drv.h
index 011105e51ac6..5898b274279d 100644
--- a/drivers/gpu/drm/r128/r128_drv.h
+++ b/drivers/gpu/drm/r128/r128_drv.h
@@ -29,7 +29,7 @@
  *    Rickard E. (Rik) Faith <faith@valinux.com>
  *    Kevin E. Martin <martin@valinux.com>
  *    Gareth Hughes <gareth@valinux.com>
- *    Michel Dänzer <daenzerm@student.ethz.ch>
+ *    Michel D�zer <daenzerm@student.ethz.ch>
  */
 
 #ifndef __R128_DRV_H__
@@ -97,6 +97,8 @@ typedef struct drm_r128_private {
 	u32 crtc_offset;
 	u32 crtc_offset_cntl;
 
+	atomic_t vbl_received;
+
 	u32 color_fmt;
 	unsigned int front_offset;
 	unsigned int front_pitch;
@@ -149,11 +151,12 @@ extern int r128_wait_ring(drm_r128_private_t * dev_priv, int n);
 extern int r128_do_cce_idle(drm_r128_private_t * dev_priv);
 extern int r128_do_cleanup_cce(struct drm_device * dev);
 
-extern int r128_driver_vblank_wait(struct drm_device * dev, unsigned int *sequence);
-
+extern int r128_enable_vblank(struct drm_device *dev, int crtc);
+extern void r128_disable_vblank(struct drm_device *dev, int crtc);
+extern u32 r128_get_vblank_counter(struct drm_device *dev, int crtc);
 extern irqreturn_t r128_driver_irq_handler(DRM_IRQ_ARGS);
 extern void r128_driver_irq_preinstall(struct drm_device * dev);
-extern void r128_driver_irq_postinstall(struct drm_device * dev);
+extern int r128_driver_irq_postinstall(struct drm_device *dev);
 extern void r128_driver_irq_uninstall(struct drm_device * dev);
 extern void r128_driver_lastclose(struct drm_device * dev);
 extern void r128_driver_preclose(struct drm_device * dev,
diff --git a/drivers/gpu/drm/r128/r128_irq.c b/drivers/gpu/drm/r128/r128_irq.c
index c76fdca7662d..d7349012a680 100644
--- a/drivers/gpu/drm/r128/r128_irq.c
+++ b/drivers/gpu/drm/r128/r128_irq.c
@@ -35,6 +35,16 @@
 #include "r128_drm.h"
 #include "r128_drv.h"
 
+u32 r128_get_vblank_counter(struct drm_device *dev, int crtc)
+{
+	const drm_r128_private_t *dev_priv = dev->dev_private;
+
+	if (crtc != 0)
+		return 0;
+
+	return atomic_read(&dev_priv->vbl_received);
+}
+
 irqreturn_t r128_driver_irq_handler(DRM_IRQ_ARGS)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
@@ -46,30 +56,38 @@ irqreturn_t r128_driver_irq_handler(DRM_IRQ_ARGS)
 	/* VBLANK interrupt */
 	if (status & R128_CRTC_VBLANK_INT) {
 		R128_WRITE(R128_GEN_INT_STATUS, R128_CRTC_VBLANK_INT_AK);
-		atomic_inc(&dev->vbl_received);
-		DRM_WAKEUP(&dev->vbl_queue);
-		drm_vbl_send_signals(dev);
+		atomic_inc(&dev_priv->vbl_received);
+		drm_handle_vblank(dev, 0);
 		return IRQ_HANDLED;
 	}
 	return IRQ_NONE;
 }
 
-int r128_driver_vblank_wait(struct drm_device * dev, unsigned int *sequence)
+int r128_enable_vblank(struct drm_device *dev, int crtc)
 {
-	unsigned int cur_vblank;
-	int ret = 0;
+	drm_r128_private_t *dev_priv = dev->dev_private;
 
-	/* Assume that the user has missed the current sequence number
-	 * by about a day rather than she wants to wait for years
-	 * using vertical blanks...
-	 */
-	DRM_WAIT_ON(ret, dev->vbl_queue, 3 * DRM_HZ,
-		    (((cur_vblank = atomic_read(&dev->vbl_received))
-		      - *sequence) <= (1 << 23)));
+	if (crtc != 0) {
+		DRM_ERROR("%s:  bad crtc %d\n", __func__, crtc);
+		return -EINVAL;
+	}
 
-	*sequence = cur_vblank;
+	R128_WRITE(R128_GEN_INT_CNTL, R128_CRTC_VBLANK_INT_EN);
+	return 0;
+}
+
+void r128_disable_vblank(struct drm_device *dev, int crtc)
+{
+	if (crtc != 0)
+		DRM_ERROR("%s:  bad crtc %d\n", __func__, crtc);
 
-	return ret;
+	/*
+	 * FIXME: implement proper interrupt disable by using the vblank
+	 * counter register (if available)
+	 *
+	 * R128_WRITE(R128_GEN_INT_CNTL,
+	 *            R128_READ(R128_GEN_INT_CNTL) & ~R128_CRTC_VBLANK_INT_EN);
+	 */
 }
 
 void r128_driver_irq_preinstall(struct drm_device * dev)
@@ -82,12 +100,9 @@ void r128_driver_irq_preinstall(struct drm_device * dev)
 	R128_WRITE(R128_GEN_INT_STATUS, R128_CRTC_VBLANK_INT_AK);
 }
 
-void r128_driver_irq_postinstall(struct drm_device * dev)
+int r128_driver_irq_postinstall(struct drm_device *dev)
 {
-	drm_r128_private_t *dev_priv = (drm_r128_private_t *) dev->dev_private;
-
-	/* Turn on VBL interrupt */
-	R128_WRITE(R128_GEN_INT_CNTL, R128_CRTC_VBLANK_INT_EN);
+	return drm_vblank_init(dev, 1);
 }
 
 void r128_driver_irq_uninstall(struct drm_device * dev)
diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index e1678cae9ccb..6157cd4bb436 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -1287,7 +1287,7 @@ static int radeon_do_resume_cp(struct drm_device * dev)
 	radeon_cp_init_ring_buffer(dev, dev_priv);
 
 	radeon_do_engine_reset(dev);
-	radeon_enable_interrupt(dev);
+	radeon_irq_set_state(dev, RADEON_SW_INT_ENABLE, 1);
 
 	DRM_DEBUG("radeon_do_resume_cp() complete\n");
 
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 637bd7faf132..71af746a4e47 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -52,6 +52,28 @@ static int dri_library_name(struct drm_device *dev, char *buf)
 		        "r300"));
 }
 
+static int radeon_suspend(struct drm_device *dev, pm_message_t state)
+{
+	drm_radeon_private_t *dev_priv = dev->dev_private;
+
+	/* Disable *all* interrupts */
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS690)
+		RADEON_WRITE(R500_DxMODE_INT_MASK, 0);
+	RADEON_WRITE(RADEON_GEN_INT_CNTL, 0);
+	return 0;
+}
+
+static int radeon_resume(struct drm_device *dev)
+{
+	drm_radeon_private_t *dev_priv = dev->dev_private;
+
+	/* Restore interrupt registers */
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS690)
+		RADEON_WRITE(R500_DxMODE_INT_MASK, dev_priv->r500_disp_irq_reg);
+	RADEON_WRITE(RADEON_GEN_INT_CNTL, dev_priv->irq_enable_reg);
+	return 0;
+}
+
 static struct pci_device_id pciidlist[] = {
 	radeon_PCI_IDS
 };
@@ -59,8 +81,7 @@ static struct pci_device_id pciidlist[] = {
 static struct drm_driver driver = {
 	.driver_features =
 	    DRIVER_USE_AGP | DRIVER_USE_MTRR | DRIVER_PCI_DMA | DRIVER_SG |
-	    DRIVER_HAVE_IRQ | DRIVER_HAVE_DMA | DRIVER_IRQ_SHARED |
-	    DRIVER_IRQ_VBL | DRIVER_IRQ_VBL2,
+	    DRIVER_HAVE_IRQ | DRIVER_HAVE_DMA | DRIVER_IRQ_SHARED,
 	.dev_priv_size = sizeof(drm_radeon_buf_priv_t),
 	.load = radeon_driver_load,
 	.firstopen = radeon_driver_firstopen,
@@ -69,8 +90,11 @@ static struct drm_driver driver = {
 	.postclose = radeon_driver_postclose,
 	.lastclose = radeon_driver_lastclose,
 	.unload = radeon_driver_unload,
-	.vblank_wait = radeon_driver_vblank_wait,
-	.vblank_wait2 = radeon_driver_vblank_wait2,
+	.suspend = radeon_suspend,
+	.resume = radeon_resume,
+	.get_vblank_counter = radeon_get_vblank_counter,
+	.enable_vblank = radeon_enable_vblank,
+	.disable_vblank = radeon_disable_vblank,
 	.dri_library_name = dri_library_name,
 	.irq_preinstall = radeon_driver_irq_preinstall,
 	.irq_postinstall = radeon_driver_irq_postinstall,
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index 099381693175..d7e9c6cc6a1a 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -378,17 +378,17 @@ extern void radeon_mem_release(struct drm_file *file_priv,
 			       struct mem_block *heap);
 
 				/* radeon_irq.c */
+extern void radeon_irq_set_state(struct drm_device *dev, u32 mask, int state);
 extern int radeon_irq_emit(struct drm_device *dev, void *data, struct drm_file *file_priv);
 extern int radeon_irq_wait(struct drm_device *dev, void *data, struct drm_file *file_priv);
 
 extern void radeon_do_release(struct drm_device * dev);
-extern int radeon_driver_vblank_wait(struct drm_device * dev,
-				     unsigned int *sequence);
-extern int radeon_driver_vblank_wait2(struct drm_device * dev,
-				      unsigned int *sequence);
+extern u32 radeon_get_vblank_counter(struct drm_device *dev, int crtc);
+extern int radeon_enable_vblank(struct drm_device *dev, int crtc);
+extern void radeon_disable_vblank(struct drm_device *dev, int crtc);
 extern irqreturn_t radeon_driver_irq_handler(DRM_IRQ_ARGS);
 extern void radeon_driver_irq_preinstall(struct drm_device * dev);
-extern void radeon_driver_irq_postinstall(struct drm_device * dev);
+extern int radeon_driver_irq_postinstall(struct drm_device *dev);
 extern void radeon_driver_irq_uninstall(struct drm_device * dev);
 extern void radeon_enable_interrupt(struct drm_device *dev);
 extern int radeon_vblank_crtc_get(struct drm_device *dev);
@@ -397,19 +397,22 @@ extern int radeon_vblank_crtc_set(struct drm_device *dev, int64_t value);
 extern int radeon_driver_load(struct drm_device *dev, unsigned long flags);
 extern int radeon_driver_unload(struct drm_device *dev);
 extern int radeon_driver_firstopen(struct drm_device *dev);
-extern void radeon_driver_preclose(struct drm_device * dev, struct drm_file *file_priv);
-extern void radeon_driver_postclose(struct drm_device * dev, struct drm_file * filp);
+extern void radeon_driver_preclose(struct drm_device *dev,
+				   struct drm_file *file_priv);
+extern void radeon_driver_postclose(struct drm_device *dev,
+				    struct drm_file *file_priv);
 extern void radeon_driver_lastclose(struct drm_device * dev);
-extern int radeon_driver_open(struct drm_device * dev, struct drm_file * filp_priv);
+extern int radeon_driver_open(struct drm_device *dev,
+			      struct drm_file *file_priv);
 extern long radeon_compat_ioctl(struct file *filp, unsigned int cmd,
 				unsigned long arg);
 
 /* r300_cmdbuf.c */
 extern void r300_init_reg_flags(struct drm_device *dev);
 
-extern int r300_do_cp_cmdbuf(struct drm_device * dev,
+extern int r300_do_cp_cmdbuf(struct drm_device *dev,
 			     struct drm_file *file_priv,
-			     drm_radeon_kcmd_buffer_t * cmdbuf);
+			     drm_radeon_kcmd_buffer_t *cmdbuf);
 
 /* Flags for stats.boxes
  */
@@ -623,6 +626,7 @@ extern int r300_do_cp_cmdbuf(struct drm_device * dev,
 #	define RADEON_SW_INT_TEST		(1 << 25)
 #	define RADEON_SW_INT_TEST_ACK		(1 << 25)
 #	define RADEON_SW_INT_FIRE		(1 << 26)
+#       define R500_DISPLAY_INT_STATUS          (1 << 0)
 
 #define RADEON_HOST_PATH_CNTL		0x0130
 #	define RADEON_HDP_SOFT_RESET		(1 << 26)
@@ -1116,6 +1120,9 @@ extern int r300_do_cp_cmdbuf(struct drm_device * dev,
 
 #define R200_VAP_PVS_CNTL_1               0x22D0
 
+#define RADEON_CRTC_CRNT_FRAME 0x0214
+#define RADEON_CRTC2_CRNT_FRAME 0x0314
+
 #define R500_D1CRTC_STATUS 0x609c
 #define R500_D2CRTC_STATUS 0x689c
 #define R500_CRTC_V_BLANK (1<<0)
diff --git a/drivers/gpu/drm/radeon/radeon_irq.c b/drivers/gpu/drm/radeon/radeon_irq.c
index ee40d197deb7..5079f7054a2f 100644
--- a/drivers/gpu/drm/radeon/radeon_irq.c
+++ b/drivers/gpu/drm/radeon/radeon_irq.c
@@ -27,7 +27,7 @@
  *
  * Authors:
  *    Keith Whitwell <keith@tungstengraphics.com>
- *    Michel Dänzer <michel@daenzer.net>
+ *    Michel D�zer <michel@daenzer.net>
  */
 
 #include "drmP.h"
@@ -35,12 +35,128 @@
 #include "radeon_drm.h"
 #include "radeon_drv.h"
 
-static __inline__ u32 radeon_acknowledge_irqs(drm_radeon_private_t * dev_priv,
-					      u32 mask)
+void radeon_irq_set_state(struct drm_device *dev, u32 mask, int state)
 {
-	u32 irqs = RADEON_READ(RADEON_GEN_INT_STATUS) & mask;
+	drm_radeon_private_t *dev_priv = dev->dev_private;
+
+	if (state)
+		dev_priv->irq_enable_reg |= mask;
+	else
+		dev_priv->irq_enable_reg &= ~mask;
+
+	RADEON_WRITE(RADEON_GEN_INT_CNTL, dev_priv->irq_enable_reg);
+}
+
+static void r500_vbl_irq_set_state(struct drm_device *dev, u32 mask, int state)
+{
+	drm_radeon_private_t *dev_priv = dev->dev_private;
+
+	if (state)
+		dev_priv->r500_disp_irq_reg |= mask;
+	else
+		dev_priv->r500_disp_irq_reg &= ~mask;
+
+	RADEON_WRITE(R500_DxMODE_INT_MASK, dev_priv->r500_disp_irq_reg);
+}
+
+int radeon_enable_vblank(struct drm_device *dev, int crtc)
+{
+	drm_radeon_private_t *dev_priv = dev->dev_private;
+
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS690) {
+		switch (crtc) {
+		case 0:
+			r500_vbl_irq_set_state(dev, R500_D1MODE_INT_MASK, 1);
+			break;
+		case 1:
+			r500_vbl_irq_set_state(dev, R500_D2MODE_INT_MASK, 1);
+			break;
+		default:
+			DRM_ERROR("tried to enable vblank on non-existent crtc %d\n",
+				  crtc);
+			return EINVAL;
+		}
+	} else {
+		switch (crtc) {
+		case 0:
+			radeon_irq_set_state(dev, RADEON_CRTC_VBLANK_MASK, 1);
+			break;
+		case 1:
+			radeon_irq_set_state(dev, RADEON_CRTC2_VBLANK_MASK, 1);
+			break;
+		default:
+			DRM_ERROR("tried to enable vblank on non-existent crtc %d\n",
+				  crtc);
+			return EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+void radeon_disable_vblank(struct drm_device *dev, int crtc)
+{
+	drm_radeon_private_t *dev_priv = dev->dev_private;
+
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS690) {
+		switch (crtc) {
+		case 0:
+			r500_vbl_irq_set_state(dev, R500_D1MODE_INT_MASK, 0);
+			break;
+		case 1:
+			r500_vbl_irq_set_state(dev, R500_D2MODE_INT_MASK, 0);
+			break;
+		default:
+			DRM_ERROR("tried to enable vblank on non-existent crtc %d\n",
+				  crtc);
+			break;
+		}
+	} else {
+		switch (crtc) {
+		case 0:
+			radeon_irq_set_state(dev, RADEON_CRTC_VBLANK_MASK, 0);
+			break;
+		case 1:
+			radeon_irq_set_state(dev, RADEON_CRTC2_VBLANK_MASK, 0);
+			break;
+		default:
+			DRM_ERROR("tried to enable vblank on non-existent crtc %d\n",
+				  crtc);
+			break;
+		}
+	}
+}
+
+static inline u32 radeon_acknowledge_irqs(drm_radeon_private_t *dev_priv, u32 *r500_disp_int)
+{
+	u32 irqs = RADEON_READ(RADEON_GEN_INT_STATUS);
+	u32 irq_mask = RADEON_SW_INT_TEST;
+
+	*r500_disp_int = 0;
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS690) {
+		/* vbl interrupts in a different place */
+
+		if (irqs & R500_DISPLAY_INT_STATUS) {
+			/* if a display interrupt */
+			u32 disp_irq;
+
+			disp_irq = RADEON_READ(R500_DISP_INTERRUPT_STATUS);
+
+			*r500_disp_int = disp_irq;
+			if (disp_irq & R500_D1_VBLANK_INTERRUPT)
+				RADEON_WRITE(R500_D1MODE_VBLANK_STATUS, R500_VBLANK_ACK);
+			if (disp_irq & R500_D2_VBLANK_INTERRUPT)
+				RADEON_WRITE(R500_D2MODE_VBLANK_STATUS, R500_VBLANK_ACK);
+		}
+		irq_mask |= R500_DISPLAY_INT_STATUS;
+	} else
+		irq_mask |= RADEON_CRTC_VBLANK_STAT | RADEON_CRTC2_VBLANK_STAT;
+
+	irqs &=	irq_mask;
+
 	if (irqs)
 		RADEON_WRITE(RADEON_GEN_INT_STATUS, irqs);
+
 	return irqs;
 }
 
@@ -68,44 +184,33 @@ irqreturn_t radeon_driver_irq_handler(DRM_IRQ_ARGS)
 	drm_radeon_private_t *dev_priv =
 	    (drm_radeon_private_t *) dev->dev_private;
 	u32 stat;
+	u32 r500_disp_int;
 
 	/* Only consider the bits we're interested in - others could be used
 	 * outside the DRM
 	 */
-	stat = radeon_acknowledge_irqs(dev_priv, (RADEON_SW_INT_TEST_ACK |
-						  RADEON_CRTC_VBLANK_STAT |
-						  RADEON_CRTC2_VBLANK_STAT));
+	stat = radeon_acknowledge_irqs(dev_priv, &r500_disp_int);
 	if (!stat)
 		return IRQ_NONE;
 
 	stat &= dev_priv->irq_enable_reg;
 
 	/* SW interrupt */
-	if (stat & RADEON_SW_INT_TEST) {
+	if (stat & RADEON_SW_INT_TEST)
 		DRM_WAKEUP(&dev_priv->swi_queue);
-	}
 
 	/* VBLANK interrupt */
-	if (stat & (RADEON_CRTC_VBLANK_STAT|RADEON_CRTC2_VBLANK_STAT)) {
-		int vblank_crtc = dev_priv->vblank_crtc;
-
-		if ((vblank_crtc &
-		     (DRM_RADEON_VBLANK_CRTC1 | DRM_RADEON_VBLANK_CRTC2)) ==
-		    (DRM_RADEON_VBLANK_CRTC1 | DRM_RADEON_VBLANK_CRTC2)) {
-			if (stat & RADEON_CRTC_VBLANK_STAT)
-				atomic_inc(&dev->vbl_received);
-			if (stat & RADEON_CRTC2_VBLANK_STAT)
-				atomic_inc(&dev->vbl_received2);
-		} else if (((stat & RADEON_CRTC_VBLANK_STAT) &&
-			   (vblank_crtc & DRM_RADEON_VBLANK_CRTC1)) ||
-			   ((stat & RADEON_CRTC2_VBLANK_STAT) &&
-			    (vblank_crtc & DRM_RADEON_VBLANK_CRTC2)))
-			atomic_inc(&dev->vbl_received);
-
-		DRM_WAKEUP(&dev->vbl_queue);
-		drm_vbl_send_signals(dev);
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS690) {
+		if (r500_disp_int & R500_D1_VBLANK_INTERRUPT)
+			drm_handle_vblank(dev, 0);
+		if (r500_disp_int & R500_D2_VBLANK_INTERRUPT)
+			drm_handle_vblank(dev, 1);
+	} else {
+		if (stat & RADEON_CRTC_VBLANK_STAT)
+			drm_handle_vblank(dev, 0);
+		if (stat & RADEON_CRTC2_VBLANK_STAT)
+			drm_handle_vblank(dev, 1);
 	}
-
 	return IRQ_HANDLED;
 }
 
@@ -144,54 +249,31 @@ static int radeon_wait_irq(struct drm_device * dev, int swi_nr)
 	return ret;
 }
 
-static int radeon_driver_vblank_do_wait(struct drm_device * dev,
-					unsigned int *sequence, int crtc)
+u32 radeon_get_vblank_counter(struct drm_device *dev, int crtc)
 {
-	drm_radeon_private_t *dev_priv =
-	    (drm_radeon_private_t *) dev->dev_private;
-	unsigned int cur_vblank;
-	int ret = 0;
-	int ack = 0;
-	atomic_t *counter;
+	drm_radeon_private_t *dev_priv = dev->dev_private;
+
 	if (!dev_priv) {
 		DRM_ERROR("called with no initialization\n");
 		return -EINVAL;
 	}
 
-	if (crtc == DRM_RADEON_VBLANK_CRTC1) {
-		counter = &dev->vbl_received;
-		ack |= RADEON_CRTC_VBLANK_STAT;
-	} else if (crtc == DRM_RADEON_VBLANK_CRTC2) {
-		counter = &dev->vbl_received2;
-		ack |= RADEON_CRTC2_VBLANK_STAT;
-	} else
+	if (crtc < 0 || crtc > 1) {
+		DRM_ERROR("Invalid crtc %d\n", crtc);
 		return -EINVAL;
+	}
 
-	radeon_acknowledge_irqs(dev_priv, ack);
-
-	dev_priv->stats.boxes |= RADEON_BOX_WAIT_IDLE;
-
-	/* Assume that the user has missed the current sequence number
-	 * by about a day rather than she wants to wait for years
-	 * using vertical blanks...
-	 */
-	DRM_WAIT_ON(ret, dev->vbl_queue, 3 * DRM_HZ,
-		    (((cur_vblank = atomic_read(counter))
-		      - *sequence) <= (1 << 23)));
-
-	*sequence = cur_vblank;
-
-	return ret;
-}
-
-int radeon_driver_vblank_wait(struct drm_device *dev, unsigned int *sequence)
-{
-	return radeon_driver_vblank_do_wait(dev, sequence, DRM_RADEON_VBLANK_CRTC1);
-}
-
-int radeon_driver_vblank_wait2(struct drm_device *dev, unsigned int *sequence)
-{
-	return radeon_driver_vblank_do_wait(dev, sequence, DRM_RADEON_VBLANK_CRTC2);
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS690) {
+		if (crtc == 0)
+			return RADEON_READ(R500_D1CRTC_FRAME_COUNT);
+		else
+			return RADEON_READ(R500_D2CRTC_FRAME_COUNT);
+	} else {
+		if (crtc == 0)
+			return RADEON_READ(RADEON_CRTC_CRNT_FRAME);
+		else
+			return RADEON_READ(RADEON_CRTC2_CRNT_FRAME);
+	}
 }
 
 /* Needs the lock as it touches the ring.
@@ -234,46 +316,41 @@ int radeon_irq_wait(struct drm_device *dev, void *data, struct drm_file *file_pr
 	return radeon_wait_irq(dev, irqwait->irq_seq);
 }
 
-void radeon_enable_interrupt(struct drm_device *dev)
-{
-	drm_radeon_private_t *dev_priv = (drm_radeon_private_t *) dev->dev_private;
-
-	dev_priv->irq_enable_reg = RADEON_SW_INT_ENABLE;
-	if (dev_priv->vblank_crtc & DRM_RADEON_VBLANK_CRTC1)
-		dev_priv->irq_enable_reg |= RADEON_CRTC_VBLANK_MASK;
-
-	if (dev_priv->vblank_crtc & DRM_RADEON_VBLANK_CRTC2)
-		dev_priv->irq_enable_reg |= RADEON_CRTC2_VBLANK_MASK;
-
-	RADEON_WRITE(RADEON_GEN_INT_CNTL, dev_priv->irq_enable_reg);
-	dev_priv->irq_enabled = 1;
-}
-
 /* drm_dma.h hooks
 */
 void radeon_driver_irq_preinstall(struct drm_device * dev)
 {
 	drm_radeon_private_t *dev_priv =
 	    (drm_radeon_private_t *) dev->dev_private;
+	u32 dummy;
 
 	/* Disable *all* interrupts */
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS690)
+		RADEON_WRITE(R500_DxMODE_INT_MASK, 0);
 	RADEON_WRITE(RADEON_GEN_INT_CNTL, 0);
 
 	/* Clear bits if they're already high */
-	radeon_acknowledge_irqs(dev_priv, (RADEON_SW_INT_TEST_ACK |
-					   RADEON_CRTC_VBLANK_STAT |
-					   RADEON_CRTC2_VBLANK_STAT));
+	radeon_acknowledge_irqs(dev_priv, &dummy);
 }
 
-void radeon_driver_irq_postinstall(struct drm_device * dev)
+int radeon_driver_irq_postinstall(struct drm_device *dev)
 {
 	drm_radeon_private_t *dev_priv =
 	    (drm_radeon_private_t *) dev->dev_private;
+	int ret;
 
 	atomic_set(&dev_priv->swi_emitted, 0);
 	DRM_INIT_WAITQUEUE(&dev_priv->swi_queue);
 
-	radeon_enable_interrupt(dev);
+	ret = drm_vblank_init(dev, 2);
+	if (ret)
+		return ret;
+
+	dev->max_vblank_count = 0x001fffff;
+
+	radeon_irq_set_state(dev, RADEON_SW_INT_ENABLE, 1);
+
+	return 0;
 }
 
 void radeon_driver_irq_uninstall(struct drm_device * dev)
@@ -285,6 +362,8 @@ void radeon_driver_irq_uninstall(struct drm_device * dev)
 
 	dev_priv->irq_enabled = 0;
 
+	if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_RS690)
+		RADEON_WRITE(R500_DxMODE_INT_MASK, 0);
 	/* Disable *all* interrupts */
 	RADEON_WRITE(RADEON_GEN_INT_CNTL, 0);
 }
@@ -293,18 +372,8 @@ void radeon_driver_irq_uninstall(struct drm_device * dev)
 int radeon_vblank_crtc_get(struct drm_device *dev)
 {
 	drm_radeon_private_t *dev_priv = (drm_radeon_private_t *) dev->dev_private;
-	u32 flag;
-	u32 value;
-
-	flag = RADEON_READ(RADEON_GEN_INT_CNTL);
-	value = 0;
-
-	if (flag & RADEON_CRTC_VBLANK_MASK)
-		value |= DRM_RADEON_VBLANK_CRTC1;
 
-	if (flag & RADEON_CRTC2_VBLANK_MASK)
-		value |= DRM_RADEON_VBLANK_CRTC2;
-	return value;
+	return dev_priv->vblank_crtc;
 }
 
 int radeon_vblank_crtc_set(struct drm_device *dev, int64_t value)
@@ -315,6 +384,5 @@ int radeon_vblank_crtc_set(struct drm_device *dev, int64_t value)
 		return -EINVAL;
 	}
 	dev_priv->vblank_crtc = (unsigned int)value;
-	radeon_enable_interrupt(dev);
 	return 0;
 }
diff --git a/drivers/gpu/drm/via/via_drv.c b/drivers/gpu/drm/via/via_drv.c
index 80c01cdfa37d..0993b441fc42 100644
--- a/drivers/gpu/drm/via/via_drv.c
+++ b/drivers/gpu/drm/via/via_drv.c
@@ -40,11 +40,13 @@ static struct pci_device_id pciidlist[] = {
 static struct drm_driver driver = {
 	.driver_features =
 	    DRIVER_USE_AGP | DRIVER_USE_MTRR | DRIVER_HAVE_IRQ |
-	    DRIVER_IRQ_SHARED | DRIVER_IRQ_VBL,
+	    DRIVER_IRQ_SHARED,
 	.load = via_driver_load,
 	.unload = via_driver_unload,
 	.context_dtor = via_final_context,
-	.vblank_wait = via_driver_vblank_wait,
+	.get_vblank_counter = via_get_vblank_counter,
+	.enable_vblank = via_enable_vblank,
+	.disable_vblank = via_disable_vblank,
 	.irq_preinstall = via_driver_irq_preinstall,
 	.irq_postinstall = via_driver_irq_postinstall,
 	.irq_uninstall = via_driver_irq_uninstall,
@@ -59,17 +61,17 @@ static struct drm_driver driver = {
 	.get_reg_ofs = drm_core_get_reg_ofs,
 	.ioctls = via_ioctls,
 	.fops = {
-		 .owner = THIS_MODULE,
-		 .open = drm_open,
-		 .release = drm_release,
-		 .ioctl = drm_ioctl,
-		 .mmap = drm_mmap,
-		 .poll = drm_poll,
-		 .fasync = drm_fasync,
-	},
+		.owner = THIS_MODULE,
+		.open = drm_open,
+		.release = drm_release,
+		.ioctl = drm_ioctl,
+		.mmap = drm_mmap,
+		.poll = drm_poll,
+		.fasync = drm_fasync,
+		},
 	.pci_driver = {
-		 .name = DRIVER_NAME,
-		 .id_table = pciidlist,
+		.name = DRIVER_NAME,
+		.id_table = pciidlist,
 	},
 
 	.name = DRIVER_NAME,
diff --git a/drivers/gpu/drm/via/via_drv.h b/drivers/gpu/drm/via/via_drv.h
index 2daae81874cd..cafcb844a223 100644
--- a/drivers/gpu/drm/via/via_drv.h
+++ b/drivers/gpu/drm/via/via_drv.h
@@ -75,6 +75,7 @@ typedef struct drm_via_private {
 	struct timeval last_vblank;
 	int last_vblank_valid;
 	unsigned usec_per_vblank;
+	atomic_t vbl_received;
 	drm_via_state_t hc_state;
 	char pci_buf[VIA_PCI_BUF_SIZE];
 	const uint32_t *fire_offsets[VIA_FIRE_BUF_SIZE];
@@ -130,21 +131,24 @@ extern int via_init_context(struct drm_device * dev, int context);
 extern int via_final_context(struct drm_device * dev, int context);
 
 extern int via_do_cleanup_map(struct drm_device * dev);
-extern int via_driver_vblank_wait(struct drm_device * dev, unsigned int *sequence);
+extern u32 via_get_vblank_counter(struct drm_device *dev, int crtc);
+extern int via_enable_vblank(struct drm_device *dev, int crtc);
+extern void via_disable_vblank(struct drm_device *dev, int crtc);
 
 extern irqreturn_t via_driver_irq_handler(DRM_IRQ_ARGS);
 extern void via_driver_irq_preinstall(struct drm_device * dev);
-extern void via_driver_irq_postinstall(struct drm_device * dev);
+extern int via_driver_irq_postinstall(struct drm_device *dev);
 extern void via_driver_irq_uninstall(struct drm_device * dev);
 
 extern int via_dma_cleanup(struct drm_device * dev);
 extern void via_init_command_verifier(void);
 extern int via_driver_dma_quiescent(struct drm_device * dev);
-extern void via_init_futex(drm_via_private_t * dev_priv);
-extern void via_cleanup_futex(drm_via_private_t * dev_priv);
-extern void via_release_futex(drm_via_private_t * dev_priv, int context);
+extern void via_init_futex(drm_via_private_t *dev_priv);
+extern void via_cleanup_futex(drm_via_private_t *dev_priv);
+extern void via_release_futex(drm_via_private_t *dev_priv, int context);
 
-extern void via_reclaim_buffers_locked(struct drm_device *dev, struct drm_file *file_priv);
+extern void via_reclaim_buffers_locked(struct drm_device *dev,
+				       struct drm_file *file_priv);
 extern void via_lastclose(struct drm_device *dev);
 
 extern void via_dmablit_handler(struct drm_device *dev, int engine, int from_irq);
diff --git a/drivers/gpu/drm/via/via_irq.c b/drivers/gpu/drm/via/via_irq.c
index c6bb978a1106..1b966fbdb49f 100644
--- a/drivers/gpu/drm/via/via_irq.c
+++ b/drivers/gpu/drm/via/via_irq.c
@@ -43,7 +43,7 @@
 #define VIA_REG_INTERRUPT       0x200
 
 /* VIA_REG_INTERRUPT */
-#define VIA_IRQ_GLOBAL          (1 << 31)
+#define VIA_IRQ_GLOBAL	  (1 << 31)
 #define VIA_IRQ_VBLANK_ENABLE   (1 << 19)
 #define VIA_IRQ_VBLANK_PENDING  (1 << 3)
 #define VIA_IRQ_HQV0_ENABLE     (1 << 11)
@@ -68,16 +68,15 @@
 
 static maskarray_t via_pro_group_a_irqs[] = {
 	{VIA_IRQ_HQV0_ENABLE, VIA_IRQ_HQV0_PENDING, 0x000003D0, 0x00008010,
-	 0x00000000},
+	 0x00000000 },
 	{VIA_IRQ_HQV1_ENABLE, VIA_IRQ_HQV1_PENDING, 0x000013D0, 0x00008010,
-	 0x00000000},
+	 0x00000000 },
 	{VIA_IRQ_DMA0_TD_ENABLE, VIA_IRQ_DMA0_TD_PENDING, VIA_PCI_DMA_CSR0,
 	 VIA_DMA_CSR_TA | VIA_DMA_CSR_TD, 0x00000008},
 	{VIA_IRQ_DMA1_TD_ENABLE, VIA_IRQ_DMA1_TD_PENDING, VIA_PCI_DMA_CSR1,
 	 VIA_DMA_CSR_TA | VIA_DMA_CSR_TD, 0x00000008},
 };
-static int via_num_pro_group_a =
-    sizeof(via_pro_group_a_irqs) / sizeof(maskarray_t);
+static int via_num_pro_group_a = ARRAY_SIZE(via_pro_group_a_irqs);
 static int via_irqmap_pro_group_a[] = {0, 1, -1, 2, -1, 3};
 
 static maskarray_t via_unichrome_irqs[] = {
@@ -86,14 +85,24 @@ static maskarray_t via_unichrome_irqs[] = {
 	{VIA_IRQ_DMA1_TD_ENABLE, VIA_IRQ_DMA1_TD_PENDING, VIA_PCI_DMA_CSR1,
 	 VIA_DMA_CSR_TA | VIA_DMA_CSR_TD, 0x00000008}
 };
-static int via_num_unichrome = sizeof(via_unichrome_irqs) / sizeof(maskarray_t);
+static int via_num_unichrome = ARRAY_SIZE(via_unichrome_irqs);
 static int via_irqmap_unichrome[] = {-1, -1, -1, 0, -1, 1};
 
+
 static unsigned time_diff(struct timeval *now, struct timeval *then)
 {
 	return (now->tv_usec >= then->tv_usec) ?
-	    now->tv_usec - then->tv_usec :
-	    1000000 - (then->tv_usec - now->tv_usec);
+		now->tv_usec - then->tv_usec :
+		1000000 - (then->tv_usec - now->tv_usec);
+}
+
+u32 via_get_vblank_counter(struct drm_device *dev, int crtc)
+{
+	drm_via_private_t *dev_priv = dev->dev_private;
+	if (crtc != 0)
+		return 0;
+
+	return atomic_read(&dev_priv->vbl_received);
 }
 
 irqreturn_t via_driver_irq_handler(DRM_IRQ_ARGS)
@@ -108,23 +117,22 @@ irqreturn_t via_driver_irq_handler(DRM_IRQ_ARGS)
 
 	status = VIA_READ(VIA_REG_INTERRUPT);
 	if (status & VIA_IRQ_VBLANK_PENDING) {
-		atomic_inc(&dev->vbl_received);
-		if (!(atomic_read(&dev->vbl_received) & 0x0F)) {
+		atomic_inc(&dev_priv->vbl_received);
+		if (!(atomic_read(&dev_priv->vbl_received) & 0x0F)) {
 			do_gettimeofday(&cur_vblank);
 			if (dev_priv->last_vblank_valid) {
 				dev_priv->usec_per_vblank =
-				    time_diff(&cur_vblank,
-					      &dev_priv->last_vblank) >> 4;
+					time_diff(&cur_vblank,
+						  &dev_priv->last_vblank) >> 4;
 			}
 			dev_priv->last_vblank = cur_vblank;
 			dev_priv->last_vblank_valid = 1;
 		}
-		if (!(atomic_read(&dev->vbl_received) & 0xFF)) {
+		if (!(atomic_read(&dev_priv->vbl_received) & 0xFF)) {
 			DRM_DEBUG("US per vblank is: %u\n",
 				  dev_priv->usec_per_vblank);
 		}
-		DRM_WAKEUP(&dev->vbl_queue);
-		drm_vbl_send_signals(dev);
+		drm_handle_vblank(dev, 0);
 		handled = 1;
 	}
 
@@ -145,6 +153,7 @@ irqreturn_t via_driver_irq_handler(DRM_IRQ_ARGS)
 	/* Acknowlege interrupts */
 	VIA_WRITE(VIA_REG_INTERRUPT, status);
 
+
 	if (handled)
 		return IRQ_HANDLED;
 	else
@@ -163,31 +172,34 @@ static __inline__ void viadrv_acknowledge_irqs(drm_via_private_t * dev_priv)
 	}
 }
 
-int via_driver_vblank_wait(struct drm_device * dev, unsigned int *sequence)
+int via_enable_vblank(struct drm_device *dev, int crtc)
 {
-	drm_via_private_t *dev_priv = (drm_via_private_t *) dev->dev_private;
-	unsigned int cur_vblank;
-	int ret = 0;
+	drm_via_private_t *dev_priv = dev->dev_private;
+	u32 status;
 
-	DRM_DEBUG("\n");
-	if (!dev_priv) {
-		DRM_ERROR("called with no initialization\n");
+	if (crtc != 0) {
+		DRM_ERROR("%s:  bad crtc %d\n", __func__, crtc);
 		return -EINVAL;
 	}
 
-	viadrv_acknowledge_irqs(dev_priv);
+	status = VIA_READ(VIA_REG_INTERRUPT);
+	VIA_WRITE(VIA_REG_INTERRUPT, status & VIA_IRQ_VBLANK_ENABLE);
+
+	VIA_WRITE8(0x83d4, 0x11);
+	VIA_WRITE8(0x83d5, VIA_READ8(0x83d5) | 0x30);
 
-	/* Assume that the user has missed the current sequence number
-	 * by about a day rather than she wants to wait for years
-	 * using vertical blanks...
-	 */
+	return 0;
+}
 
-	DRM_WAIT_ON(ret, dev->vbl_queue, 3 * DRM_HZ,
-		    (((cur_vblank = atomic_read(&dev->vbl_received)) -
-		      *sequence) <= (1 << 23)));
+void via_disable_vblank(struct drm_device *dev, int crtc)
+{
+	drm_via_private_t *dev_priv = dev->dev_private;
 
-	*sequence = cur_vblank;
-	return ret;
+	VIA_WRITE8(0x83d4, 0x11);
+	VIA_WRITE8(0x83d5, VIA_READ8(0x83d5) & ~0x30);
+
+	if (crtc != 0)
+		DRM_ERROR("%s:  bad crtc %d\n", __func__, crtc);
 }
 
 static int
@@ -239,6 +251,7 @@ via_driver_irq_wait(struct drm_device * dev, unsigned int irq, int force_sequenc
 	return ret;
 }
 
+
 /*
  * drm_dma.h hooks
  */
@@ -292,23 +305,25 @@ void via_driver_irq_preinstall(struct drm_device * dev)
 	}
 }
 
-void via_driver_irq_postinstall(struct drm_device * dev)
+int via_driver_irq_postinstall(struct drm_device *dev)
 {
 	drm_via_private_t *dev_priv = (drm_via_private_t *) dev->dev_private;
 	u32 status;
 
-	DRM_DEBUG("\n");
-	if (dev_priv) {
-		status = VIA_READ(VIA_REG_INTERRUPT);
-		VIA_WRITE(VIA_REG_INTERRUPT, status | VIA_IRQ_GLOBAL
-			  | dev_priv->irq_enable_mask);
+	DRM_DEBUG("via_driver_irq_postinstall\n");
+	if (!dev_priv)
+		return -EINVAL;
 
-		/* Some magic, oh for some data sheets ! */
+	drm_vblank_init(dev, 1);
+	status = VIA_READ(VIA_REG_INTERRUPT);
+	VIA_WRITE(VIA_REG_INTERRUPT, status | VIA_IRQ_GLOBAL
+		  | dev_priv->irq_enable_mask);
 
-		VIA_WRITE8(0x83d4, 0x11);
-		VIA_WRITE8(0x83d5, VIA_READ8(0x83d5) | 0x30);
+	/* Some magic, oh for some data sheets ! */
+	VIA_WRITE8(0x83d4, 0x11);
+	VIA_WRITE8(0x83d5, VIA_READ8(0x83d5) | 0x30);
 
-	}
+	return 0;
 }
 
 void via_driver_irq_uninstall(struct drm_device * dev)
@@ -352,7 +367,8 @@ int via_wait_irq(struct drm_device *dev, void *data, struct drm_file *file_priv)
 
 	switch (irqwait->request.type & ~VIA_IRQ_FLAGS_MASK) {
 	case VIA_IRQ_RELATIVE:
-		irqwait->request.sequence += atomic_read(&cur_irq->irq_received);
+		irqwait->request.sequence +=
+			atomic_read(&cur_irq->irq_received);
 		irqwait->request.type &= ~_DRM_VBLANK_RELATIVE;
 	case VIA_IRQ_ABSOLUTE:
 		break;
diff --git a/include/drm/drm.h b/include/drm/drm.h
index 0864c6920941..15e55039b7f1 100644
--- a/include/drm/drm.h
+++ b/include/drm/drm.h
@@ -454,6 +454,7 @@ struct drm_irq_busid {
 enum drm_vblank_seq_type {
 	_DRM_VBLANK_ABSOLUTE = 0x0,	/**< Wait for specific vblank sequence number */
 	_DRM_VBLANK_RELATIVE = 0x1,	/**< Wait for given number of vblanks */
+	_DRM_VBLANK_FLIP = 0x8000000,   /**< Scheduled buffer swap should flip */
 	_DRM_VBLANK_NEXTONMISS = 0x10000000,	/**< If missed, wait for next vblank */
 	_DRM_VBLANK_SECONDARY = 0x20000000,	/**< Secondary display controller */
 	_DRM_VBLANK_SIGNAL = 0x40000000	/**< Send signal instead of blocking */
@@ -486,6 +487,19 @@ union drm_wait_vblank {
 	struct drm_wait_vblank_reply reply;
 };
 
+#define _DRM_PRE_MODESET 1
+#define _DRM_POST_MODESET 2
+
+/**
+ * DRM_IOCTL_MODESET_CTL ioctl argument type
+ *
+ * \sa drmModesetCtl().
+ */
+struct drm_modeset_ctl {
+	uint32_t crtc;
+	uint32_t cmd;
+};
+
 /**
  * DRM_IOCTL_AGP_ENABLE ioctl argument type.
  *
@@ -570,6 +584,7 @@ struct drm_set_version {
 #define DRM_IOCTL_GET_CLIENT            DRM_IOWR(0x05, struct drm_client)
 #define DRM_IOCTL_GET_STATS             DRM_IOR( 0x06, struct drm_stats)
 #define DRM_IOCTL_SET_VERSION		DRM_IOWR(0x07, struct drm_set_version)
+#define DRM_IOCTL_MODESET_CTL           DRM_IOW(0x08, struct drm_modeset_ctl)
 
 #define DRM_IOCTL_SET_UNIQUE		DRM_IOW( 0x10, struct drm_unique)
 #define DRM_IOCTL_AUTH_MAGIC		DRM_IOW( 0x11, struct drm_auth)
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 1c1b13e29223..e79ce0781f0b 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -580,10 +580,53 @@ struct drm_driver {
 	int (*kernel_context_switch) (struct drm_device *dev, int old,
 				      int new);
 	void (*kernel_context_switch_unlock) (struct drm_device *dev);
-	int (*vblank_wait) (struct drm_device *dev, unsigned int *sequence);
-	int (*vblank_wait2) (struct drm_device *dev, unsigned int *sequence);
 	int (*dri_library_name) (struct drm_device *dev, char *buf);
 
+	/**
+	 * get_vblank_counter - get raw hardware vblank counter
+	 * @dev: DRM device
+	 * @crtc: counter to fetch
+	 *
+	 * Driver callback for fetching a raw hardware vblank counter
+	 * for @crtc.  If a device doesn't have a hardware counter, the
+	 * driver can simply return the value of drm_vblank_count and
+	 * make the enable_vblank() and disable_vblank() hooks into no-ops,
+	 * leaving interrupts enabled at all times.
+	 *
+	 * Wraparound handling and loss of events due to modesetting is dealt
+	 * with in the DRM core code.
+	 *
+	 * RETURNS
+	 * Raw vblank counter value.
+	 */
+	u32 (*get_vblank_counter) (struct drm_device *dev, int crtc);
+
+	/**
+	 * enable_vblank - enable vblank interrupt events
+	 * @dev: DRM device
+	 * @crtc: which irq to enable
+	 *
+	 * Enable vblank interrupts for @crtc.  If the device doesn't have
+	 * a hardware vblank counter, this routine should be a no-op, since
+	 * interrupts will have to stay on to keep the count accurate.
+	 *
+	 * RETURNS
+	 * Zero on success, appropriate errno if the given @crtc's vblank
+	 * interrupt cannot be enabled.
+	 */
+	int (*enable_vblank) (struct drm_device *dev, int crtc);
+
+	/**
+	 * disable_vblank - disable vblank interrupt events
+	 * @dev: DRM device
+	 * @crtc: which irq to enable
+	 *
+	 * Disable vblank interrupts for @crtc.  If the device doesn't have
+	 * a hardware vblank counter, this routine should be a no-op, since
+	 * interrupts will have to stay on to keep the count accurate.
+	 */
+	void (*disable_vblank) (struct drm_device *dev, int crtc);
+
 	/**
 	 * Called by \c drm_device_is_agp.  Typically used to determine if a
 	 * card is really attached to AGP or not.
@@ -601,7 +644,7 @@ struct drm_driver {
 
 	irqreturn_t(*irq_handler) (DRM_IRQ_ARGS);
 	void (*irq_preinstall) (struct drm_device *dev);
-	void (*irq_postinstall) (struct drm_device *dev);
+	int (*irq_postinstall) (struct drm_device *dev);
 	void (*irq_uninstall) (struct drm_device *dev);
 	void (*reclaim_buffers) (struct drm_device *dev,
 				 struct drm_file * file_priv);
@@ -730,13 +773,28 @@ struct drm_device {
 	/** \name VBLANK IRQ support */
 	/*@{ */
 
-	wait_queue_head_t vbl_queue;	/**< VBLANK wait queue */
-	atomic_t vbl_received;
-	atomic_t vbl_received2;		/**< number of secondary VBLANK interrupts */
+	/*
+	 * At load time, disabling the vblank interrupt won't be allowed since
+	 * old clients may not call the modeset ioctl and therefore misbehave.
+	 * Once the modeset ioctl *has* been called though, we can safely
+	 * disable them when unused.
+	 */
+	int vblank_disable_allowed;
+
+	wait_queue_head_t *vbl_queue;   /**< VBLANK wait queue */
+	atomic_t *_vblank_count;        /**< number of VBLANK interrupts (driver must alloc the right number of counters) */
 	spinlock_t vbl_lock;
-	struct list_head vbl_sigs;		/**< signal list to send on VBLANK */
-	struct list_head vbl_sigs2;	/**< signals to send on secondary VBLANK */
-	unsigned int vbl_pending;
+	struct list_head *vbl_sigs;	/**< signal list to send on VBLANK */
+	atomic_t vbl_signal_pending;    /* number of signals pending on all crtcs*/
+	atomic_t *vblank_refcount;      /* number of users of vblank interruptsper crtc */
+	u32 *last_vblank;               /* protected by dev->vbl_lock, used */
+					/* for wraparound handling */
+	int *vblank_enabled;            /* so we don't call enable more than
+					   once per disable */
+	int *vblank_inmodeset;          /* Display driver is setting mode */
+	struct timer_list vblank_disable_timer;
+
+	u32 max_vblank_count;           /**< size of vblank counter register */
 	spinlock_t tasklet_lock;	/**< For drm_locked_tasklet */
 	void (*locked_tasklet_func)(struct drm_device *dev);
 
@@ -757,6 +815,7 @@ struct drm_device {
 	struct pci_controller *hose;
 #endif
 	struct drm_sg_mem *sg;	/**< Scatter gather memory */
+	int num_crtcs;                  /**< Number of CRTCs on this device */
 	void *dev_private;		/**< device private data */
 	struct drm_sigdata sigdata;	   /**< For block_all_signals */
 	sigset_t sigmask;
@@ -990,10 +1049,19 @@ extern void drm_driver_irq_preinstall(struct drm_device *dev);
 extern void drm_driver_irq_postinstall(struct drm_device *dev);
 extern void drm_driver_irq_uninstall(struct drm_device *dev);
 
+extern int drm_vblank_init(struct drm_device *dev, int num_crtcs);
 extern int drm_wait_vblank(struct drm_device *dev, void *data,
-			   struct drm_file *file_priv);
+			   struct drm_file *filp);
 extern int drm_vblank_wait(struct drm_device *dev, unsigned int *vbl_seq);
-extern void drm_vbl_send_signals(struct drm_device *dev);
+extern void drm_locked_tasklet(struct drm_device *dev,
+			       void(*func)(struct drm_device *));
+extern u32 drm_vblank_count(struct drm_device *dev, int crtc);
+extern void drm_handle_vblank(struct drm_device *dev, int crtc);
+extern int drm_vblank_get(struct drm_device *dev, int crtc);
+extern void drm_vblank_put(struct drm_device *dev, int crtc);
+/* Modesetting support */
+extern int drm_modeset_ctl(struct drm_device *dev, void *data,
+			   struct drm_file *file_priv);
 extern void drm_locked_tasklet(struct drm_device *dev, void(*func)(struct drm_device*));
 
 				/* AGP/GART support (drm_agpsupport.h) */
-- 
cgit v1.2.3


From 673a394b1e3b69be886ff24abfd6df97c52e8d08 Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Wed, 30 Jul 2008 12:06:12 -0700
Subject: drm: Add GEM ("graphics execution manager") to i915 driver.

GEM allows the creation of persistent buffer objects accessible by the
graphics device through new ioctls for managing execution of commands on the
device.  The userland API is almost entirely driver-specific to ensure that
any driver building on this model can easily map the interface to individual
driver requirements.

GEM is used by the 2d driver for managing its internal state allocations and
will be used for pixmap storage to reduce memory consumption and enable
zero-copy GLX_EXT_texture_from_pixmap, and in the 3d driver is used to enable
GL_EXT_framebuffer_object and GL_ARB_pixel_buffer_object.

Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/Makefile               |    5 +-
 drivers/gpu/drm/drm_agpsupport.c       |   51 +-
 drivers/gpu/drm/drm_cache.c            |   76 +
 drivers/gpu/drm/drm_drv.c              |    4 +
 drivers/gpu/drm/drm_fops.c             |    6 +
 drivers/gpu/drm/drm_gem.c              |  420 ++++++
 drivers/gpu/drm/drm_memory.c           |    2 +
 drivers/gpu/drm/drm_mm.c               |    5 +-
 drivers/gpu/drm/drm_proc.c             |  135 +-
 drivers/gpu/drm/drm_stub.c             |   10 +
 drivers/gpu/drm/i915/Makefile          |    6 +-
 drivers/gpu/drm/i915/i915_dma.c        |   94 +-
 drivers/gpu/drm/i915/i915_drv.c        |   11 +-
 drivers/gpu/drm/i915/i915_drv.h        |  253 +++-
 drivers/gpu/drm/i915/i915_gem.c        | 2497 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_gem_debug.c  |  201 +++
 drivers/gpu/drm/i915/i915_gem_proc.c   |  292 ++++
 drivers/gpu/drm/i915/i915_gem_tiling.c |  256 ++++
 drivers/gpu/drm/i915/i915_irq.c        |   19 +-
 drivers/gpu/drm/i915/i915_reg.h        |   37 +-
 include/drm/drm.h                      |   31 +
 include/drm/drmP.h                     |  151 ++
 include/drm/i915_drm.h                 |  332 +++++
 23 files changed, 4832 insertions(+), 62 deletions(-)
 create mode 100644 drivers/gpu/drm/drm_cache.c
 create mode 100644 drivers/gpu/drm/drm_gem.c
 create mode 100644 drivers/gpu/drm/i915/i915_gem.c
 create mode 100644 drivers/gpu/drm/i915/i915_gem_debug.c
 create mode 100644 drivers/gpu/drm/i915/i915_gem_proc.c
 create mode 100644 drivers/gpu/drm/i915/i915_gem_tiling.c

(limited to 'include')

diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index e9f9a97ae00a..74da99495e21 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -4,8 +4,9 @@
 
 ccflags-y := -Iinclude/drm
 
-drm-y       :=	drm_auth.o drm_bufs.o drm_context.o drm_dma.o drm_drawable.o \
-		drm_drv.o drm_fops.o drm_ioctl.o drm_irq.o \
+drm-y       :=	drm_auth.o drm_bufs.o drm_cache.o \
+		drm_context.o drm_dma.o drm_drawable.o \
+		drm_drv.o drm_fops.o drm_gem.o drm_ioctl.o drm_irq.o \
 		drm_lock.o drm_memory.o drm_proc.o drm_stub.o drm_vm.o \
 		drm_agpsupport.o drm_scatter.o ati_pcigart.o drm_pci.o \
 		drm_sysfs.o drm_hashtab.o drm_sman.o drm_mm.o
diff --git a/drivers/gpu/drm/drm_agpsupport.c b/drivers/gpu/drm/drm_agpsupport.c
index aefa5ac4c0b1..2639be2db9e5 100644
--- a/drivers/gpu/drm/drm_agpsupport.c
+++ b/drivers/gpu/drm/drm_agpsupport.c
@@ -33,6 +33,7 @@
 
 #include "drmP.h"
 #include <linux/module.h>
+#include <asm/agp.h>
 
 #if __OS_HAS_AGP
 
@@ -452,4 +453,52 @@ int drm_agp_unbind_memory(DRM_AGP_MEM * handle)
 	return agp_unbind_memory(handle);
 }
 
-#endif				/* __OS_HAS_AGP */
+/**
+ * Binds a collection of pages into AGP memory at the given offset, returning
+ * the AGP memory structure containing them.
+ *
+ * No reference is held on the pages during this time -- it is up to the
+ * caller to handle that.
+ */
+DRM_AGP_MEM *
+drm_agp_bind_pages(struct drm_device *dev,
+		   struct page **pages,
+		   unsigned long num_pages,
+		   uint32_t gtt_offset)
+{
+	DRM_AGP_MEM *mem;
+	int ret, i;
+
+	DRM_DEBUG("\n");
+
+	mem = drm_agp_allocate_memory(dev->agp->bridge, num_pages,
+				      AGP_USER_MEMORY);
+	if (mem == NULL) {
+		DRM_ERROR("Failed to allocate memory for %ld pages\n",
+			  num_pages);
+		return NULL;
+	}
+
+	for (i = 0; i < num_pages; i++)
+		mem->memory[i] = phys_to_gart(page_to_phys(pages[i]));
+	mem->page_count = num_pages;
+
+	mem->is_flushed = true;
+	ret = drm_agp_bind_memory(mem, gtt_offset / PAGE_SIZE);
+	if (ret != 0) {
+		DRM_ERROR("Failed to bind AGP memory: %d\n", ret);
+		agp_free_memory(mem);
+		return NULL;
+	}
+
+	return mem;
+}
+EXPORT_SYMBOL(drm_agp_bind_pages);
+
+void drm_agp_chipset_flush(struct drm_device *dev)
+{
+	agp_flush_chipset(dev->agp->bridge);
+}
+EXPORT_SYMBOL(drm_agp_chipset_flush);
+
+#endif /* __OS_HAS_AGP */
diff --git a/drivers/gpu/drm/drm_cache.c b/drivers/gpu/drm/drm_cache.c
new file mode 100644
index 000000000000..9475f7d9901d
--- /dev/null
+++ b/drivers/gpu/drm/drm_cache.c
@@ -0,0 +1,76 @@
+/**************************************************************************
+ *
+ * Copyright (c) 2006-2007 Tungsten Graphics, Inc., Cedar Park, TX., USA
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+/*
+ * Authors: Thomas Hellström <thomas-at-tungstengraphics-dot-com>
+ */
+
+#include "drmP.h"
+
+#if defined(CONFIG_X86)
+static void
+drm_clflush_page(struct page *page)
+{
+	uint8_t *page_virtual;
+	unsigned int i;
+
+	if (unlikely(page == NULL))
+		return;
+
+	page_virtual = kmap_atomic(page, KM_USER0);
+	for (i = 0; i < PAGE_SIZE; i += boot_cpu_data.x86_clflush_size)
+		clflush(page_virtual + i);
+	kunmap_atomic(page_virtual, KM_USER0);
+}
+#endif
+
+static void
+drm_clflush_ipi_handler(void *null)
+{
+	wbinvd();
+}
+
+void
+drm_clflush_pages(struct page *pages[], unsigned long num_pages)
+{
+
+#if defined(CONFIG_X86)
+	if (cpu_has_clflush) {
+		unsigned long i;
+
+		mb();
+		for (i = 0; i < num_pages; ++i)
+			drm_clflush_page(*pages++);
+		mb();
+
+		return;
+	}
+#endif
+
+	if (on_each_cpu(drm_clflush_ipi_handler, NULL, 1) != 0)
+		DRM_ERROR("Timed out waiting for cache flush.\n");
+}
+EXPORT_SYMBOL(drm_clflush_pages);
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index fb45fe7aeb8c..96f416afc3f6 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -119,6 +119,10 @@ static struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_MODESET_CTL, drm_modeset_ctl, 0),
 
 	DRM_IOCTL_DEF(DRM_IOCTL_UPDATE_DRAW, drm_update_drawable_info, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
+
+	DRM_IOCTL_DEF(DRM_IOCTL_GEM_CLOSE, drm_gem_close_ioctl, 0),
+	DRM_IOCTL_DEF(DRM_IOCTL_GEM_FLINK, drm_gem_flink_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_IOCTL_GEM_OPEN, drm_gem_open_ioctl, DRM_AUTH),
 };
 
 #define DRM_CORE_IOCTL_COUNT	ARRAY_SIZE( drm_ioctls )
diff --git a/drivers/gpu/drm/drm_fops.c b/drivers/gpu/drm/drm_fops.c
index dcf8b4dc9549..0d46627663b1 100644
--- a/drivers/gpu/drm/drm_fops.c
+++ b/drivers/gpu/drm/drm_fops.c
@@ -256,6 +256,9 @@ static int drm_open_helper(struct inode *inode, struct file *filp,
 
 	INIT_LIST_HEAD(&priv->lhead);
 
+	if (dev->driver->driver_features & DRIVER_GEM)
+		drm_gem_open(dev, priv);
+
 	if (dev->driver->open) {
 		ret = dev->driver->open(dev, priv);
 		if (ret < 0)
@@ -400,6 +403,9 @@ int drm_release(struct inode *inode, struct file *filp)
 		dev->driver->reclaim_buffers(dev, file_priv);
 	}
 
+	if (dev->driver->driver_features & DRIVER_GEM)
+		drm_gem_release(dev, file_priv);
+
 	drm_fasync(-1, filp, 0);
 
 	mutex_lock(&dev->ctxlist_mutex);
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
new file mode 100644
index 000000000000..434155b387e9
--- /dev/null
+++ b/drivers/gpu/drm/drm_gem.c
@@ -0,0 +1,420 @@
+/*
+ * Copyright © 2008 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ *    Eric Anholt <eric@anholt.net>
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/uaccess.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/module.h>
+#include <linux/mman.h>
+#include <linux/pagemap.h>
+#include "drmP.h"
+
+/** @file drm_gem.c
+ *
+ * This file provides some of the base ioctls and library routines for
+ * the graphics memory manager implemented by each device driver.
+ *
+ * Because various devices have different requirements in terms of
+ * synchronization and migration strategies, implementing that is left up to
+ * the driver, and all that the general API provides should be generic --
+ * allocating objects, reading/writing data with the cpu, freeing objects.
+ * Even there, platform-dependent optimizations for reading/writing data with
+ * the CPU mean we'll likely hook those out to driver-specific calls.  However,
+ * the DRI2 implementation wants to have at least allocate/mmap be generic.
+ *
+ * The goal was to have swap-backed object allocation managed through
+ * struct file.  However, file descriptors as handles to a struct file have
+ * two major failings:
+ * - Process limits prevent more than 1024 or so being used at a time by
+ *   default.
+ * - Inability to allocate high fds will aggravate the X Server's select()
+ *   handling, and likely that of many GL client applications as well.
+ *
+ * This led to a plan of using our own integer IDs (called handles, following
+ * DRM terminology) to mimic fds, and implement the fd syscalls we need as
+ * ioctls.  The objects themselves will still include the struct file so
+ * that we can transition to fds if the required kernel infrastructure shows
+ * up at a later date, and as our interface with shmfs for memory allocation.
+ */
+
+/**
+ * Initialize the GEM device fields
+ */
+
+int
+drm_gem_init(struct drm_device *dev)
+{
+	spin_lock_init(&dev->object_name_lock);
+	idr_init(&dev->object_name_idr);
+	atomic_set(&dev->object_count, 0);
+	atomic_set(&dev->object_memory, 0);
+	atomic_set(&dev->pin_count, 0);
+	atomic_set(&dev->pin_memory, 0);
+	atomic_set(&dev->gtt_count, 0);
+	atomic_set(&dev->gtt_memory, 0);
+	return 0;
+}
+
+/**
+ * Allocate a GEM object of the specified size with shmfs backing store
+ */
+struct drm_gem_object *
+drm_gem_object_alloc(struct drm_device *dev, size_t size)
+{
+	struct drm_gem_object *obj;
+
+	BUG_ON((size & (PAGE_SIZE - 1)) != 0);
+
+	obj = kcalloc(1, sizeof(*obj), GFP_KERNEL);
+
+	obj->dev = dev;
+	obj->filp = shmem_file_setup("drm mm object", size, 0);
+	if (IS_ERR(obj->filp)) {
+		kfree(obj);
+		return NULL;
+	}
+
+	kref_init(&obj->refcount);
+	kref_init(&obj->handlecount);
+	obj->size = size;
+	if (dev->driver->gem_init_object != NULL &&
+	    dev->driver->gem_init_object(obj) != 0) {
+		fput(obj->filp);
+		kfree(obj);
+		return NULL;
+	}
+	atomic_inc(&dev->object_count);
+	atomic_add(obj->size, &dev->object_memory);
+	return obj;
+}
+EXPORT_SYMBOL(drm_gem_object_alloc);
+
+/**
+ * Removes the mapping from handle to filp for this object.
+ */
+static int
+drm_gem_handle_delete(struct drm_file *filp, int handle)
+{
+	struct drm_device *dev;
+	struct drm_gem_object *obj;
+
+	/* This is gross. The idr system doesn't let us try a delete and
+	 * return an error code.  It just spews if you fail at deleting.
+	 * So, we have to grab a lock around finding the object and then
+	 * doing the delete on it and dropping the refcount, or the user
+	 * could race us to double-decrement the refcount and cause a
+	 * use-after-free later.  Given the frequency of our handle lookups,
+	 * we may want to use ida for number allocation and a hash table
+	 * for the pointers, anyway.
+	 */
+	spin_lock(&filp->table_lock);
+
+	/* Check if we currently have a reference on the object */
+	obj = idr_find(&filp->object_idr, handle);
+	if (obj == NULL) {
+		spin_unlock(&filp->table_lock);
+		return -EINVAL;
+	}
+	dev = obj->dev;
+
+	/* Release reference and decrement refcount. */
+	idr_remove(&filp->object_idr, handle);
+	spin_unlock(&filp->table_lock);
+
+	mutex_lock(&dev->struct_mutex);
+	drm_gem_object_handle_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
+/**
+ * Create a handle for this object. This adds a handle reference
+ * to the object, which includes a regular reference count. Callers
+ * will likely want to dereference the object afterwards.
+ */
+int
+drm_gem_handle_create(struct drm_file *file_priv,
+		       struct drm_gem_object *obj,
+		       int *handlep)
+{
+	int	ret;
+
+	/*
+	 * Get the user-visible handle using idr.
+	 */
+again:
+	/* ensure there is space available to allocate a handle */
+	if (idr_pre_get(&file_priv->object_idr, GFP_KERNEL) == 0)
+		return -ENOMEM;
+
+	/* do the allocation under our spinlock */
+	spin_lock(&file_priv->table_lock);
+	ret = idr_get_new_above(&file_priv->object_idr, obj, 1, handlep);
+	spin_unlock(&file_priv->table_lock);
+	if (ret == -EAGAIN)
+		goto again;
+
+	if (ret != 0)
+		return ret;
+
+	drm_gem_object_handle_reference(obj);
+	return 0;
+}
+EXPORT_SYMBOL(drm_gem_handle_create);
+
+/** Returns a reference to the object named by the handle. */
+struct drm_gem_object *
+drm_gem_object_lookup(struct drm_device *dev, struct drm_file *filp,
+		      int handle)
+{
+	struct drm_gem_object *obj;
+
+	spin_lock(&filp->table_lock);
+
+	/* Check if we currently have a reference on the object */
+	obj = idr_find(&filp->object_idr, handle);
+	if (obj == NULL) {
+		spin_unlock(&filp->table_lock);
+		return NULL;
+	}
+
+	drm_gem_object_reference(obj);
+
+	spin_unlock(&filp->table_lock);
+
+	return obj;
+}
+EXPORT_SYMBOL(drm_gem_object_lookup);
+
+/**
+ * Releases the handle to an mm object.
+ */
+int
+drm_gem_close_ioctl(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv)
+{
+	struct drm_gem_close *args = data;
+	int ret;
+
+	if (!(dev->driver->driver_features & DRIVER_GEM))
+		return -ENODEV;
+
+	ret = drm_gem_handle_delete(file_priv, args->handle);
+
+	return ret;
+}
+
+/**
+ * Create a global name for an object, returning the name.
+ *
+ * Note that the name does not hold a reference; when the object
+ * is freed, the name goes away.
+ */
+int
+drm_gem_flink_ioctl(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv)
+{
+	struct drm_gem_flink *args = data;
+	struct drm_gem_object *obj;
+	int ret;
+
+	if (!(dev->driver->driver_features & DRIVER_GEM))
+		return -ENODEV;
+
+	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
+	if (obj == NULL)
+		return -EINVAL;
+
+again:
+	if (idr_pre_get(&dev->object_name_idr, GFP_KERNEL) == 0)
+		return -ENOMEM;
+
+	spin_lock(&dev->object_name_lock);
+	if (obj->name) {
+		spin_unlock(&dev->object_name_lock);
+		return -EEXIST;
+	}
+	ret = idr_get_new_above(&dev->object_name_idr, obj, 1,
+				 &obj->name);
+	spin_unlock(&dev->object_name_lock);
+	if (ret == -EAGAIN)
+		goto again;
+
+	if (ret != 0) {
+		mutex_lock(&dev->struct_mutex);
+		drm_gem_object_unreference(obj);
+		mutex_unlock(&dev->struct_mutex);
+		return ret;
+	}
+
+	/*
+	 * Leave the reference from the lookup around as the
+	 * name table now holds one
+	 */
+	args->name = (uint64_t) obj->name;
+
+	return 0;
+}
+
+/**
+ * Open an object using the global name, returning a handle and the size.
+ *
+ * This handle (of course) holds a reference to the object, so the object
+ * will not go away until the handle is deleted.
+ */
+int
+drm_gem_open_ioctl(struct drm_device *dev, void *data,
+		   struct drm_file *file_priv)
+{
+	struct drm_gem_open *args = data;
+	struct drm_gem_object *obj;
+	int ret;
+	int handle;
+
+	if (!(dev->driver->driver_features & DRIVER_GEM))
+		return -ENODEV;
+
+	spin_lock(&dev->object_name_lock);
+	obj = idr_find(&dev->object_name_idr, (int) args->name);
+	if (obj)
+		drm_gem_object_reference(obj);
+	spin_unlock(&dev->object_name_lock);
+	if (!obj)
+		return -ENOENT;
+
+	ret = drm_gem_handle_create(file_priv, obj, &handle);
+	mutex_lock(&dev->struct_mutex);
+	drm_gem_object_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	args->handle = handle;
+	args->size = obj->size;
+
+	return 0;
+}
+
+/**
+ * Called at device open time, sets up the structure for handling refcounting
+ * of mm objects.
+ */
+void
+drm_gem_open(struct drm_device *dev, struct drm_file *file_private)
+{
+	idr_init(&file_private->object_idr);
+	spin_lock_init(&file_private->table_lock);
+}
+
+/**
+ * Called at device close to release the file's
+ * handle references on objects.
+ */
+static int
+drm_gem_object_release_handle(int id, void *ptr, void *data)
+{
+	struct drm_gem_object *obj = ptr;
+
+	drm_gem_object_handle_unreference(obj);
+
+	return 0;
+}
+
+/**
+ * Called at close time when the filp is going away.
+ *
+ * Releases any remaining references on objects by this filp.
+ */
+void
+drm_gem_release(struct drm_device *dev, struct drm_file *file_private)
+{
+	mutex_lock(&dev->struct_mutex);
+	idr_for_each(&file_private->object_idr,
+		     &drm_gem_object_release_handle, NULL);
+
+	idr_destroy(&file_private->object_idr);
+	mutex_unlock(&dev->struct_mutex);
+}
+
+/**
+ * Called after the last reference to the object has been lost.
+ *
+ * Frees the object
+ */
+void
+drm_gem_object_free(struct kref *kref)
+{
+	struct drm_gem_object *obj = (struct drm_gem_object *) kref;
+	struct drm_device *dev = obj->dev;
+
+	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
+
+	if (dev->driver->gem_free_object != NULL)
+		dev->driver->gem_free_object(obj);
+
+	fput(obj->filp);
+	atomic_dec(&dev->object_count);
+	atomic_sub(obj->size, &dev->object_memory);
+	kfree(obj);
+}
+EXPORT_SYMBOL(drm_gem_object_free);
+
+/**
+ * Called after the last handle to the object has been closed
+ *
+ * Removes any name for the object. Note that this must be
+ * called before drm_gem_object_free or we'll be touching
+ * freed memory
+ */
+void
+drm_gem_object_handle_free(struct kref *kref)
+{
+	struct drm_gem_object *obj = container_of(kref,
+						  struct drm_gem_object,
+						  handlecount);
+	struct drm_device *dev = obj->dev;
+
+	/* Remove any name for this object */
+	spin_lock(&dev->object_name_lock);
+	if (obj->name) {
+		idr_remove(&dev->object_name_idr, obj->name);
+		spin_unlock(&dev->object_name_lock);
+		/*
+		 * The object name held a reference to this object, drop
+		 * that now.
+		 */
+		drm_gem_object_unreference(obj);
+	} else
+		spin_unlock(&dev->object_name_lock);
+
+}
+EXPORT_SYMBOL(drm_gem_object_handle_free);
+
diff --git a/drivers/gpu/drm/drm_memory.c b/drivers/gpu/drm/drm_memory.c
index 0177012845c6..803bc9e7ce3c 100644
--- a/drivers/gpu/drm/drm_memory.c
+++ b/drivers/gpu/drm/drm_memory.c
@@ -133,6 +133,7 @@ int drm_free_agp(DRM_AGP_MEM * handle, int pages)
 {
 	return drm_agp_free_memory(handle) ? 0 : -EINVAL;
 }
+EXPORT_SYMBOL(drm_free_agp);
 
 /** Wrapper around agp_bind_memory() */
 int drm_bind_agp(DRM_AGP_MEM * handle, unsigned int start)
@@ -145,6 +146,7 @@ int drm_unbind_agp(DRM_AGP_MEM * handle)
 {
 	return drm_agp_unbind_memory(handle);
 }
+EXPORT_SYMBOL(drm_unbind_agp);
 
 #else  /*  __OS_HAS_AGP  */
 static inline void *agp_remap(unsigned long offset, unsigned long size,
diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index dcff9e9b52e3..217ad7dc7076 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -169,6 +169,7 @@ struct drm_mm_node *drm_mm_get_block(struct drm_mm_node * parent,
 
 	return child;
 }
+EXPORT_SYMBOL(drm_mm_get_block);
 
 /*
  * Put a block. Merge with the previous and / or next block if they are free.
@@ -217,6 +218,7 @@ void drm_mm_put_block(struct drm_mm_node * cur)
 		drm_free(cur, sizeof(*cur), DRM_MEM_MM);
 	}
 }
+EXPORT_SYMBOL(drm_mm_put_block);
 
 struct drm_mm_node *drm_mm_search_free(const struct drm_mm * mm,
 				  unsigned long size,
@@ -265,6 +267,7 @@ int drm_mm_clean(struct drm_mm * mm)
 
 	return (head->next->next == head);
 }
+EXPORT_SYMBOL(drm_mm_search_free);
 
 int drm_mm_init(struct drm_mm * mm, unsigned long start, unsigned long size)
 {
@@ -273,7 +276,7 @@ int drm_mm_init(struct drm_mm * mm, unsigned long start, unsigned long size)
 
 	return drm_mm_create_tail_node(mm, start, size);
 }
-
+EXPORT_SYMBOL(drm_mm_init);
 
 void drm_mm_takedown(struct drm_mm * mm)
 {
diff --git a/drivers/gpu/drm/drm_proc.c b/drivers/gpu/drm/drm_proc.c
index 93b1e0475c93..d490db4c0de0 100644
--- a/drivers/gpu/drm/drm_proc.c
+++ b/drivers/gpu/drm/drm_proc.c
@@ -49,6 +49,10 @@ static int drm_queues_info(char *buf, char **start, off_t offset,
 			   int request, int *eof, void *data);
 static int drm_bufs_info(char *buf, char **start, off_t offset,
 			 int request, int *eof, void *data);
+static int drm_gem_name_info(char *buf, char **start, off_t offset,
+			     int request, int *eof, void *data);
+static int drm_gem_object_info(char *buf, char **start, off_t offset,
+			       int request, int *eof, void *data);
 #if DRM_DEBUG_CODE
 static int drm_vma_info(char *buf, char **start, off_t offset,
 			int request, int *eof, void *data);
@@ -60,13 +64,16 @@ static int drm_vma_info(char *buf, char **start, off_t offset,
 static struct drm_proc_list {
 	const char *name;	/**< file name */
 	int (*f) (char *, char **, off_t, int, int *, void *);		/**< proc callback*/
+	u32 driver_features; /**< Required driver features for this entry */
 } drm_proc_list[] = {
-	{"name", drm_name_info},
-	{"mem", drm_mem_info},
-	{"vm", drm_vm_info},
-	{"clients", drm_clients_info},
-	{"queues", drm_queues_info},
-	{"bufs", drm_bufs_info},
+	{"name", drm_name_info, 0},
+	{"mem", drm_mem_info, 0},
+	{"vm", drm_vm_info, 0},
+	{"clients", drm_clients_info, 0},
+	{"queues", drm_queues_info, 0},
+	{"bufs", drm_bufs_info, 0},
+	{"gem_names", drm_gem_name_info, DRIVER_GEM},
+	{"gem_objects", drm_gem_object_info, DRIVER_GEM},
 #if DRM_DEBUG_CODE
 	{"vma", drm_vma_info},
 #endif
@@ -90,8 +97,9 @@ static struct drm_proc_list {
 int drm_proc_init(struct drm_minor *minor, int minor_id,
 		  struct proc_dir_entry *root)
 {
+	struct drm_device *dev = minor->dev;
 	struct proc_dir_entry *ent;
-	int i, j;
+	int i, j, ret;
 	char name[64];
 
 	sprintf(name, "%d", minor_id);
@@ -102,23 +110,42 @@ int drm_proc_init(struct drm_minor *minor, int minor_id,
 	}
 
 	for (i = 0; i < DRM_PROC_ENTRIES; i++) {
+		u32 features = drm_proc_list[i].driver_features;
+
+		if (features != 0 &&
+		    (dev->driver->driver_features & features) != features)
+			continue;
+
 		ent = create_proc_entry(drm_proc_list[i].name,
 					S_IFREG | S_IRUGO, minor->dev_root);
 		if (!ent) {
 			DRM_ERROR("Cannot create /proc/dri/%s/%s\n",
 				  name, drm_proc_list[i].name);
-			for (j = 0; j < i; j++)
-				remove_proc_entry(drm_proc_list[i].name,
-						  minor->dev_root);
-			remove_proc_entry(name, root);
-			minor->dev_root = NULL;
-			return -1;
+			ret = -1;
+			goto fail;
 		}
 		ent->read_proc = drm_proc_list[i].f;
 		ent->data = minor;
 	}
 
+	if (dev->driver->proc_init) {
+		ret = dev->driver->proc_init(minor);
+		if (ret) {
+			DRM_ERROR("DRM: Driver failed to initialize "
+				  "/proc/dri.\n");
+			goto fail;
+		}
+	}
+
 	return 0;
+ fail:
+
+	for (j = 0; j < i; j++)
+		remove_proc_entry(drm_proc_list[i].name,
+				  minor->dev_root);
+	remove_proc_entry(name, root);
+	minor->dev_root = NULL;
+	return ret;
 }
 
 /**
@@ -133,12 +160,16 @@ int drm_proc_init(struct drm_minor *minor, int minor_id,
  */
 int drm_proc_cleanup(struct drm_minor *minor, struct proc_dir_entry *root)
 {
+	struct drm_device *dev = minor->dev;
 	int i;
 	char name[64];
 
 	if (!root || !minor->dev_root)
 		return 0;
 
+	if (dev->driver->proc_cleanup)
+		dev->driver->proc_cleanup(minor);
+
 	for (i = 0; i < DRM_PROC_ENTRIES; i++)
 		remove_proc_entry(drm_proc_list[i].name, minor->dev_root);
 	sprintf(name, "%d", minor->index);
@@ -480,6 +511,84 @@ static int drm_clients_info(char *buf, char **start, off_t offset,
 	return ret;
 }
 
+struct drm_gem_name_info_data {
+       int                     len;
+       char                    *buf;
+       int                     eof;
+};
+
+static int drm_gem_one_name_info(int id, void *ptr, void *data)
+{
+	struct drm_gem_object *obj = ptr;
+	struct drm_gem_name_info_data   *nid = data;
+
+	DRM_INFO("name %d size %d\n", obj->name, obj->size);
+	if (nid->eof)
+		return 0;
+
+	nid->len += sprintf(&nid->buf[nid->len],
+			    "%6d%9d%8d%9d\n",
+			    obj->name, obj->size,
+			    atomic_read(&obj->handlecount.refcount),
+			    atomic_read(&obj->refcount.refcount));
+	if (nid->len > DRM_PROC_LIMIT) {
+		nid->eof = 1;
+		return 0;
+	}
+	return 0;
+}
+
+static int drm_gem_name_info(char *buf, char **start, off_t offset,
+			     int request, int *eof, void *data)
+{
+	struct drm_minor *minor = (struct drm_minor *) data;
+	struct drm_device *dev = minor->dev;
+	struct drm_gem_name_info_data nid;
+
+	if (offset > DRM_PROC_LIMIT) {
+		*eof = 1;
+		return 0;
+	}
+
+	nid.len = sprintf(buf, "  name     size handles refcount\n");
+	nid.buf = buf;
+	nid.eof = 0;
+	idr_for_each(&dev->object_name_idr, drm_gem_one_name_info, &nid);
+
+	*start = &buf[offset];
+	*eof = 0;
+	if (nid.len > request + offset)
+		return request;
+	*eof = 1;
+	return nid.len - offset;
+}
+
+static int drm_gem_object_info(char *buf, char **start, off_t offset,
+			       int request, int *eof, void *data)
+{
+	struct drm_minor *minor = (struct drm_minor *) data;
+	struct drm_device *dev = minor->dev;
+	int len = 0;
+
+	if (offset > DRM_PROC_LIMIT) {
+		*eof = 1;
+		return 0;
+	}
+
+	*start = &buf[offset];
+	*eof = 0;
+	DRM_PROC_PRINT("%d objects\n", atomic_read(&dev->object_count));
+	DRM_PROC_PRINT("%d object bytes\n", atomic_read(&dev->object_memory));
+	DRM_PROC_PRINT("%d pinned\n", atomic_read(&dev->pin_count));
+	DRM_PROC_PRINT("%d pin bytes\n", atomic_read(&dev->pin_memory));
+	DRM_PROC_PRINT("%d gtt bytes\n", atomic_read(&dev->gtt_memory));
+	DRM_PROC_PRINT("%d gtt total\n", dev->gtt_total);
+	if (len > request + offset)
+		return request;
+	*eof = 1;
+	return len - offset;
+}
+
 #if DRM_DEBUG_CODE
 
 static int drm__vma_info(char *buf, char **start, off_t offset, int request,
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index c2f584f3b46c..82f4657b8879 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -152,6 +152,15 @@ static int drm_fill_in_dev(struct drm_device * dev, struct pci_dev *pdev,
 		goto error_out_unreg;
 	}
 
+	if (driver->driver_features & DRIVER_GEM) {
+		retcode = drm_gem_init(dev);
+		if (retcode) {
+			DRM_ERROR("Cannot initialize graphics execution "
+				  "manager (GEM)\n");
+			goto error_out_unreg;
+		}
+	}
+
 	return 0;
 
       error_out_unreg:
@@ -317,6 +326,7 @@ int drm_put_dev(struct drm_device * dev)
 int drm_put_minor(struct drm_minor **minor_p)
 {
 	struct drm_minor *minor = *minor_p;
+
 	DRM_DEBUG("release secondary minor %d\n", minor->index);
 
 	if (minor->type == DRM_MINOR_LEGACY)
diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index c4bbda662e26..5ba78e4fd2b5 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -4,7 +4,11 @@
 
 ccflags-y := -Iinclude/drm
 i915-y := i915_drv.o i915_dma.o i915_irq.o i915_mem.o i915_opregion.o \
-          i915_suspend.o
+          i915_suspend.o \
+	  i915_gem.o \
+	  i915_gem_debug.o \
+	  i915_gem_proc.o \
+	  i915_gem_tiling.o
 
 i915-$(CONFIG_COMPAT)   += i915_ioc32.o
 
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 63c6803d471b..f167ff68a4bf 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -170,24 +170,31 @@ static int i915_initialize(struct drm_device * dev, drm_i915_init_t * init)
 	dev_priv->sarea_priv = (drm_i915_sarea_t *)
 	    ((u8 *) dev_priv->sarea->handle + init->sarea_priv_offset);
 
-	dev_priv->ring.Start = init->ring_start;
-	dev_priv->ring.End = init->ring_end;
-	dev_priv->ring.Size = init->ring_size;
-	dev_priv->ring.tail_mask = dev_priv->ring.Size - 1;
+	if (init->ring_size != 0) {
+		if (dev_priv->ring.ring_obj != NULL) {
+			i915_dma_cleanup(dev);
+			DRM_ERROR("Client tried to initialize ringbuffer in "
+				  "GEM mode\n");
+			return -EINVAL;
+		}
 
-	dev_priv->ring.map.offset = init->ring_start;
-	dev_priv->ring.map.size = init->ring_size;
-	dev_priv->ring.map.type = 0;
-	dev_priv->ring.map.flags = 0;
-	dev_priv->ring.map.mtrr = 0;
+		dev_priv->ring.Size = init->ring_size;
+		dev_priv->ring.tail_mask = dev_priv->ring.Size - 1;
 
-	drm_core_ioremap(&dev_priv->ring.map, dev);
+		dev_priv->ring.map.offset = init->ring_start;
+		dev_priv->ring.map.size = init->ring_size;
+		dev_priv->ring.map.type = 0;
+		dev_priv->ring.map.flags = 0;
+		dev_priv->ring.map.mtrr = 0;
 
-	if (dev_priv->ring.map.handle == NULL) {
-		i915_dma_cleanup(dev);
-		DRM_ERROR("can not ioremap virtual address for"
-			  " ring buffer\n");
-		return -ENOMEM;
+		drm_core_ioremap(&dev_priv->ring.map, dev);
+
+		if (dev_priv->ring.map.handle == NULL) {
+			i915_dma_cleanup(dev);
+			DRM_ERROR("can not ioremap virtual address for"
+				  " ring buffer\n");
+			return -ENOMEM;
+		}
 	}
 
 	dev_priv->ring.virtual_start = dev_priv->ring.map.handle;
@@ -377,9 +384,10 @@ static int i915_emit_cmds(struct drm_device * dev, int __user * buffer, int dwor
 	return 0;
 }
 
-static int i915_emit_box(struct drm_device * dev,
-			 struct drm_clip_rect __user * boxes,
-			 int i, int DR1, int DR4)
+int
+i915_emit_box(struct drm_device *dev,
+	      struct drm_clip_rect __user *boxes,
+	      int i, int DR1, int DR4)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct drm_clip_rect box;
@@ -681,6 +689,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_LAST_DISPATCH:
 		value = READ_BREADCRUMB(dev_priv);
 		break;
+	case I915_PARAM_HAS_GEM:
+		value = 1;
+		break;
 	default:
 		DRM_ERROR("Unknown parameter %d\n", param->param);
 		return -EINVAL;
@@ -784,6 +795,7 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 	memset(dev_priv, 0, sizeof(drm_i915_private_t));
 
 	dev->dev_private = (void *)dev_priv;
+	dev_priv->dev = dev;
 
 	/* Add register map (needed for suspend/resume) */
 	base = drm_get_resource_start(dev, mmio_bar);
@@ -793,6 +805,8 @@ int i915_driver_load(struct drm_device *dev, unsigned long flags)
 			 _DRM_KERNEL | _DRM_DRIVER,
 			 &dev_priv->mmio_map);
 
+	i915_gem_load(dev);
+
 	/* Init HWS */
 	if (!I915_NEED_GFX_HWS(dev)) {
 		ret = i915_init_phys_hws(dev);
@@ -838,6 +852,25 @@ int i915_driver_unload(struct drm_device *dev)
 	return 0;
 }
 
+int i915_driver_open(struct drm_device *dev, struct drm_file *file_priv)
+{
+	struct drm_i915_file_private *i915_file_priv;
+
+	DRM_DEBUG("\n");
+	i915_file_priv = (struct drm_i915_file_private *)
+	    drm_alloc(sizeof(*i915_file_priv), DRM_MEM_FILES);
+
+	if (!i915_file_priv)
+		return -ENOMEM;
+
+	file_priv->driver_priv = i915_file_priv;
+
+	i915_file_priv->mm.last_gem_seqno = 0;
+	i915_file_priv->mm.last_gem_throttle_seqno = 0;
+
+	return 0;
+}
+
 void i915_driver_lastclose(struct drm_device * dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
@@ -845,6 +878,8 @@ void i915_driver_lastclose(struct drm_device * dev)
 	if (!dev_priv)
 		return;
 
+	i915_gem_lastclose(dev);
+
 	if (dev_priv->agp_heap)
 		i915_mem_takedown(&(dev_priv->agp_heap));
 
@@ -857,6 +892,13 @@ void i915_driver_preclose(struct drm_device * dev, struct drm_file *file_priv)
 	i915_mem_release(dev, file_priv, dev_priv->agp_heap);
 }
 
+void i915_driver_postclose(struct drm_device *dev, struct drm_file *file_priv)
+{
+	struct drm_i915_file_private *i915_file_priv = file_priv->driver_priv;
+
+	drm_free(i915_file_priv, sizeof(*i915_file_priv), DRM_MEM_FILES);
+}
+
 struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_I915_INIT, i915_dma_init, DRM_AUTH|DRM_MASTER|DRM_ROOT_ONLY),
 	DRM_IOCTL_DEF(DRM_I915_FLUSH, i915_flush_ioctl, DRM_AUTH),
@@ -875,6 +917,22 @@ struct drm_ioctl_desc i915_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_I915_GET_VBLANK_PIPE,  i915_vblank_pipe_get, DRM_AUTH ),
 	DRM_IOCTL_DEF(DRM_I915_VBLANK_SWAP, i915_vblank_swap, DRM_AUTH),
 	DRM_IOCTL_DEF(DRM_I915_HWS_ADDR, i915_set_status_page, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_I915_GEM_INIT, i915_gem_init_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_I915_GEM_EXECBUFFER, i915_gem_execbuffer, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_I915_GEM_PIN, i915_gem_pin_ioctl, DRM_AUTH|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_I915_GEM_UNPIN, i915_gem_unpin_ioctl, DRM_AUTH|DRM_ROOT_ONLY),
+	DRM_IOCTL_DEF(DRM_I915_GEM_BUSY, i915_gem_busy_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_I915_GEM_THROTTLE, i915_gem_throttle_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_I915_GEM_ENTERVT, i915_gem_entervt_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_I915_GEM_LEAVEVT, i915_gem_leavevt_ioctl, DRM_AUTH),
+	DRM_IOCTL_DEF(DRM_I915_GEM_CREATE, i915_gem_create_ioctl, 0),
+	DRM_IOCTL_DEF(DRM_I915_GEM_PREAD, i915_gem_pread_ioctl, 0),
+	DRM_IOCTL_DEF(DRM_I915_GEM_PWRITE, i915_gem_pwrite_ioctl, 0),
+	DRM_IOCTL_DEF(DRM_I915_GEM_MMAP, i915_gem_mmap_ioctl, 0),
+	DRM_IOCTL_DEF(DRM_I915_GEM_SET_DOMAIN, i915_gem_set_domain_ioctl, 0),
+	DRM_IOCTL_DEF(DRM_I915_GEM_SW_FINISH, i915_gem_sw_finish_ioctl, 0),
+	DRM_IOCTL_DEF(DRM_I915_GEM_SET_TILING, i915_gem_set_tiling, 0),
+	DRM_IOCTL_DEF(DRM_I915_GEM_GET_TILING, i915_gem_get_tiling, 0),
 };
 
 int i915_max_ioctl = DRM_ARRAY_SIZE(i915_ioctls);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 37af03f4db36..a80ead215282 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -85,12 +85,15 @@ static struct drm_driver driver = {
 	/* don't use mtrr's here, the Xserver or user space app should
 	 * deal with them for intel hardware.
 	 */
-	.driver_features = DRIVER_USE_AGP | DRIVER_REQUIRE_AGP |
-		DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED,
+	.driver_features =
+	    DRIVER_USE_AGP | DRIVER_REQUIRE_AGP | /* DRIVER_USE_MTRR |*/
+	    DRIVER_HAVE_IRQ | DRIVER_IRQ_SHARED | DRIVER_GEM,
 	.load = i915_driver_load,
 	.unload = i915_driver_unload,
+	.open = i915_driver_open,
 	.lastclose = i915_driver_lastclose,
 	.preclose = i915_driver_preclose,
+	.postclose = i915_driver_postclose,
 	.suspend = i915_suspend,
 	.resume = i915_resume,
 	.device_is_agp = i915_driver_device_is_agp,
@@ -104,6 +107,10 @@ static struct drm_driver driver = {
 	.reclaim_buffers = drm_core_reclaim_buffers,
 	.get_map_ofs = drm_core_get_map_ofs,
 	.get_reg_ofs = drm_core_get_reg_ofs,
+	.proc_init = i915_gem_proc_init,
+	.proc_cleanup = i915_gem_proc_cleanup,
+	.gem_init_object = i915_gem_init_object,
+	.gem_free_object = i915_gem_free_object,
 	.ioctls = i915_ioctls,
 	.fops = {
 		 .owner = THIS_MODULE,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d1a02bead458..87b071ab8647 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -39,7 +39,7 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20060119"
+#define DRIVER_DATE		"20080730"
 
 enum pipe {
 	PIPE_A = 0,
@@ -60,16 +60,23 @@ enum pipe {
 #define DRIVER_MINOR		6
 #define DRIVER_PATCHLEVEL	0
 
+#define WATCH_COHERENCY	0
+#define WATCH_BUF	0
+#define WATCH_EXEC	0
+#define WATCH_LRU	0
+#define WATCH_RELOC	0
+#define WATCH_INACTIVE	0
+#define WATCH_PWRITE	0
+
 typedef struct _drm_i915_ring_buffer {
 	int tail_mask;
-	unsigned long Start;
-	unsigned long End;
 	unsigned long Size;
 	u8 *virtual_start;
 	int head;
 	int tail;
 	int space;
 	drm_local_map_t map;
+	struct drm_gem_object *ring_obj;
 } drm_i915_ring_buffer_t;
 
 struct mem_block {
@@ -101,6 +108,8 @@ struct intel_opregion {
 };
 
 typedef struct drm_i915_private {
+	struct drm_device *dev;
+
 	drm_local_map_t *sarea;
 	drm_local_map_t *mmio_map;
 
@@ -113,6 +122,7 @@ typedef struct drm_i915_private {
 	uint32_t counter;
 	unsigned int status_gfx_addr;
 	drm_local_map_t hws_map;
+	struct drm_gem_object *hws_obj;
 
 	unsigned int cpp;
 	int back_offset;
@@ -122,7 +132,6 @@ typedef struct drm_i915_private {
 
 	wait_queue_head_t irq_queue;
 	atomic_t irq_received;
-	atomic_t irq_emitted;
 	/** Protects user_irq_refcount and irq_mask_reg */
 	spinlock_t user_irq_lock;
 	/** Refcount for i915_user_irq_get() versus i915_user_irq_put(). */
@@ -230,8 +239,174 @@ typedef struct drm_i915_private {
 	u8 saveDACMASK;
 	u8 saveDACDATA[256*3]; /* 256 3-byte colors */
 	u8 saveCR[37];
+
+	struct {
+		struct drm_mm gtt_space;
+
+		/**
+		 * List of objects currently involved in rendering from the
+		 * ringbuffer.
+		 *
+		 * A reference is held on the buffer while on this list.
+		 */
+		struct list_head active_list;
+
+		/**
+		 * List of objects which are not in the ringbuffer but which
+		 * still have a write_domain which needs to be flushed before
+		 * unbinding.
+		 *
+		 * A reference is held on the buffer while on this list.
+		 */
+		struct list_head flushing_list;
+
+		/**
+		 * LRU list of objects which are not in the ringbuffer and
+		 * are ready to unbind, but are still in the GTT.
+		 *
+		 * A reference is not held on the buffer while on this list,
+		 * as merely being GTT-bound shouldn't prevent its being
+		 * freed, and we'll pull it off the list in the free path.
+		 */
+		struct list_head inactive_list;
+
+		/**
+		 * List of breadcrumbs associated with GPU requests currently
+		 * outstanding.
+		 */
+		struct list_head request_list;
+
+		/**
+		 * We leave the user IRQ off as much as possible,
+		 * but this means that requests will finish and never
+		 * be retired once the system goes idle. Set a timer to
+		 * fire periodically while the ring is running. When it
+		 * fires, go retire requests.
+		 */
+		struct delayed_work retire_work;
+
+		uint32_t next_gem_seqno;
+
+		/**
+		 * Waiting sequence number, if any
+		 */
+		uint32_t waiting_gem_seqno;
+
+		/**
+		 * Last seq seen at irq time
+		 */
+		uint32_t irq_gem_seqno;
+
+		/**
+		 * Flag if the X Server, and thus DRM, is not currently in
+		 * control of the device.
+		 *
+		 * This is set between LeaveVT and EnterVT.  It needs to be
+		 * replaced with a semaphore.  It also needs to be
+		 * transitioned away from for kernel modesetting.
+		 */
+		int suspended;
+
+		/**
+		 * Flag if the hardware appears to be wedged.
+		 *
+		 * This is set when attempts to idle the device timeout.
+		 * It prevents command submission from occuring and makes
+		 * every pending request fail
+		 */
+		int wedged;
+
+		/** Bit 6 swizzling required for X tiling */
+		uint32_t bit_6_swizzle_x;
+		/** Bit 6 swizzling required for Y tiling */
+		uint32_t bit_6_swizzle_y;
+	} mm;
 } drm_i915_private_t;
 
+/** driver private structure attached to each drm_gem_object */
+struct drm_i915_gem_object {
+	struct drm_gem_object *obj;
+
+	/** Current space allocated to this object in the GTT, if any. */
+	struct drm_mm_node *gtt_space;
+
+	/** This object's place on the active/flushing/inactive lists */
+	struct list_head list;
+
+	/**
+	 * This is set if the object is on the active or flushing lists
+	 * (has pending rendering), and is not set if it's on inactive (ready
+	 * to be unbound).
+	 */
+	int active;
+
+	/**
+	 * This is set if the object has been written to since last bound
+	 * to the GTT
+	 */
+	int dirty;
+
+	/** AGP memory structure for our GTT binding. */
+	DRM_AGP_MEM *agp_mem;
+
+	struct page **page_list;
+
+	/**
+	 * Current offset of the object in GTT space.
+	 *
+	 * This is the same as gtt_space->start
+	 */
+	uint32_t gtt_offset;
+
+	/** Boolean whether this object has a valid gtt offset. */
+	int gtt_bound;
+
+	/** How many users have pinned this object in GTT space */
+	int pin_count;
+
+	/** Breadcrumb of last rendering to the buffer. */
+	uint32_t last_rendering_seqno;
+
+	/** Current tiling mode for the object. */
+	uint32_t tiling_mode;
+
+	/**
+	 * Flagging of which individual pages are valid in GEM_DOMAIN_CPU when
+	 * GEM_DOMAIN_CPU is not in the object's read domain.
+	 */
+	uint8_t *page_cpu_valid;
+};
+
+/**
+ * Request queue structure.
+ *
+ * The request queue allows us to note sequence numbers that have been emitted
+ * and may be associated with active buffers to be retired.
+ *
+ * By keeping this list, we can avoid having to do questionable
+ * sequence-number comparisons on buffer last_rendering_seqnos, and associate
+ * an emission time with seqnos for tracking how far ahead of the GPU we are.
+ */
+struct drm_i915_gem_request {
+	/** GEM sequence number associated with this request. */
+	uint32_t seqno;
+
+	/** Time at which this request was emitted, in jiffies. */
+	unsigned long emitted_jiffies;
+
+	/** Cache domains that were flushed at the start of the request. */
+	uint32_t flush_domains;
+
+	struct list_head list;
+};
+
+struct drm_i915_file_private {
+	struct {
+		uint32_t last_gem_seqno;
+		uint32_t last_gem_throttle_seqno;
+	} mm;
+};
+
 extern struct drm_ioctl_desc i915_ioctls[];
 extern int i915_max_ioctl;
 
@@ -239,18 +414,26 @@ extern int i915_max_ioctl;
 extern void i915_kernel_lost_context(struct drm_device * dev);
 extern int i915_driver_load(struct drm_device *, unsigned long flags);
 extern int i915_driver_unload(struct drm_device *);
+extern int i915_driver_open(struct drm_device *dev, struct drm_file *file_priv);
 extern void i915_driver_lastclose(struct drm_device * dev);
 extern void i915_driver_preclose(struct drm_device *dev,
 				 struct drm_file *file_priv);
+extern void i915_driver_postclose(struct drm_device *dev,
+				  struct drm_file *file_priv);
 extern int i915_driver_device_is_agp(struct drm_device * dev);
 extern long i915_compat_ioctl(struct file *filp, unsigned int cmd,
 			      unsigned long arg);
+extern int i915_emit_box(struct drm_device *dev,
+			 struct drm_clip_rect __user *boxes,
+			 int i, int DR1, int DR4);
 
 /* i915_irq.c */
 extern int i915_irq_emit(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
 extern int i915_irq_wait(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
+void i915_user_irq_get(struct drm_device *dev);
+void i915_user_irq_put(struct drm_device *dev);
 
 extern irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS);
 extern void i915_driver_irq_preinstall(struct drm_device * dev);
@@ -279,6 +462,67 @@ extern int i915_mem_destroy_heap(struct drm_device *dev, void *data,
 extern void i915_mem_takedown(struct mem_block **heap);
 extern void i915_mem_release(struct drm_device * dev,
 			     struct drm_file *file_priv, struct mem_block *heap);
+/* i915_gem.c */
+int i915_gem_init_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int i915_gem_create_ioctl(struct drm_device *dev, void *data,
+			  struct drm_file *file_priv);
+int i915_gem_pread_ioctl(struct drm_device *dev, void *data,
+			 struct drm_file *file_priv);
+int i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
+			  struct drm_file *file_priv);
+int i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+int i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
+			     struct drm_file *file_priv);
+int i915_gem_execbuffer(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int i915_gem_pin_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv);
+int i915_gem_unpin_ioctl(struct drm_device *dev, void *data,
+			 struct drm_file *file_priv);
+int i915_gem_busy_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
+			    struct drm_file *file_priv);
+int i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
+			   struct drm_file *file_priv);
+int i915_gem_leavevt_ioctl(struct drm_device *dev, void *data,
+			   struct drm_file *file_priv);
+int i915_gem_set_tiling(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int i915_gem_get_tiling(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+void i915_gem_load(struct drm_device *dev);
+int i915_gem_proc_init(struct drm_minor *minor);
+void i915_gem_proc_cleanup(struct drm_minor *minor);
+int i915_gem_init_object(struct drm_gem_object *obj);
+void i915_gem_free_object(struct drm_gem_object *obj);
+int i915_gem_object_pin(struct drm_gem_object *obj, uint32_t alignment);
+void i915_gem_object_unpin(struct drm_gem_object *obj);
+void i915_gem_lastclose(struct drm_device *dev);
+uint32_t i915_get_gem_seqno(struct drm_device *dev);
+void i915_gem_retire_requests(struct drm_device *dev);
+void i915_gem_retire_work_handler(struct work_struct *work);
+void i915_gem_clflush_object(struct drm_gem_object *obj);
+
+/* i915_gem_tiling.c */
+void i915_gem_detect_bit_6_swizzle(struct drm_device *dev);
+
+/* i915_gem_debug.c */
+void i915_gem_dump_object(struct drm_gem_object *obj, int len,
+			  const char *where, uint32_t mark);
+#if WATCH_INACTIVE
+void i915_verify_inactive(struct drm_device *dev, char *file, int line);
+#else
+#define i915_verify_inactive(dev, file, line)
+#endif
+void i915_gem_object_check_coherency(struct drm_gem_object *obj, int handle);
+void i915_gem_dump_object(struct drm_gem_object *obj, int len,
+			  const char *where, uint32_t mark);
+void i915_dump_lru(struct drm_device *dev, const char *where);
 
 /* i915_suspend.c */
 extern int i915_save_state(struct drm_device *dev);
@@ -347,6 +591,7 @@ extern void opregion_enable_asle(struct drm_device *dev);
  */
 #define READ_HWSP(dev_priv, reg)  (((volatile u32*)(dev_priv->hw_status_page))[reg])
 #define READ_BREADCRUMB(dev_priv) READ_HWSP(dev_priv, 5)
+#define I915_GEM_HWS_INDEX		0x10
 
 extern int i915_wait_ring(struct drm_device * dev, int n, const char *caller);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
new file mode 100644
index 000000000000..90ae8a0369f7
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -0,0 +1,2497 @@
+/*
+ * Copyright © 2008 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ *    Eric Anholt <eric@anholt.net>
+ *
+ */
+
+#include "drmP.h"
+#include "drm.h"
+#include "i915_drm.h"
+#include "i915_drv.h"
+#include <linux/swap.h>
+
+static int
+i915_gem_object_set_domain(struct drm_gem_object *obj,
+			    uint32_t read_domains,
+			    uint32_t write_domain);
+static int
+i915_gem_object_set_domain_range(struct drm_gem_object *obj,
+				 uint64_t offset,
+				 uint64_t size,
+				 uint32_t read_domains,
+				 uint32_t write_domain);
+static int
+i915_gem_set_domain(struct drm_gem_object *obj,
+		    struct drm_file *file_priv,
+		    uint32_t read_domains,
+		    uint32_t write_domain);
+static int i915_gem_object_get_page_list(struct drm_gem_object *obj);
+static void i915_gem_object_free_page_list(struct drm_gem_object *obj);
+static int i915_gem_object_wait_rendering(struct drm_gem_object *obj);
+
+int
+i915_gem_init_ioctl(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_init *args = data;
+
+	mutex_lock(&dev->struct_mutex);
+
+	if (args->gtt_start >= args->gtt_end ||
+	    (args->gtt_start & (PAGE_SIZE - 1)) != 0 ||
+	    (args->gtt_end & (PAGE_SIZE - 1)) != 0) {
+		mutex_unlock(&dev->struct_mutex);
+		return -EINVAL;
+	}
+
+	drm_mm_init(&dev_priv->mm.gtt_space, args->gtt_start,
+	    args->gtt_end - args->gtt_start);
+
+	dev->gtt_total = (uint32_t) (args->gtt_end - args->gtt_start);
+
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
+
+/**
+ * Creates a new mm object and returns a handle to it.
+ */
+int
+i915_gem_create_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv)
+{
+	struct drm_i915_gem_create *args = data;
+	struct drm_gem_object *obj;
+	int handle, ret;
+
+	args->size = roundup(args->size, PAGE_SIZE);
+
+	/* Allocate the new object */
+	obj = drm_gem_object_alloc(dev, args->size);
+	if (obj == NULL)
+		return -ENOMEM;
+
+	ret = drm_gem_handle_create(file_priv, obj, &handle);
+	mutex_lock(&dev->struct_mutex);
+	drm_gem_object_handle_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
+
+	if (ret)
+		return ret;
+
+	args->handle = handle;
+
+	return 0;
+}
+
+/**
+ * Reads data from the object referenced by handle.
+ *
+ * On error, the contents of *data are undefined.
+ */
+int
+i915_gem_pread_ioctl(struct drm_device *dev, void *data,
+		     struct drm_file *file_priv)
+{
+	struct drm_i915_gem_pread *args = data;
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+	ssize_t read;
+	loff_t offset;
+	int ret;
+
+	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
+	if (obj == NULL)
+		return -EBADF;
+	obj_priv = obj->driver_private;
+
+	/* Bounds check source.
+	 *
+	 * XXX: This could use review for overflow issues...
+	 */
+	if (args->offset > obj->size || args->size > obj->size ||
+	    args->offset + args->size > obj->size) {
+		drm_gem_object_unreference(obj);
+		return -EINVAL;
+	}
+
+	mutex_lock(&dev->struct_mutex);
+
+	ret = i915_gem_object_set_domain_range(obj, args->offset, args->size,
+					       I915_GEM_DOMAIN_CPU, 0);
+	if (ret != 0) {
+		drm_gem_object_unreference(obj);
+		mutex_unlock(&dev->struct_mutex);
+	}
+
+	offset = args->offset;
+
+	read = vfs_read(obj->filp, (char __user *)(uintptr_t)args->data_ptr,
+			args->size, &offset);
+	if (read != args->size) {
+		drm_gem_object_unreference(obj);
+		mutex_unlock(&dev->struct_mutex);
+		if (read < 0)
+			return read;
+		else
+			return -EINVAL;
+	}
+
+	drm_gem_object_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
+static int
+i915_gem_gtt_pwrite(struct drm_device *dev, struct drm_gem_object *obj,
+		    struct drm_i915_gem_pwrite *args,
+		    struct drm_file *file_priv)
+{
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	ssize_t remain;
+	loff_t offset;
+	char __user *user_data;
+	char *vaddr;
+	int i, o, l;
+	int ret = 0;
+	unsigned long pfn;
+	unsigned long unwritten;
+
+	user_data = (char __user *) (uintptr_t) args->data_ptr;
+	remain = args->size;
+	if (!access_ok(VERIFY_READ, user_data, remain))
+		return -EFAULT;
+
+
+	mutex_lock(&dev->struct_mutex);
+	ret = i915_gem_object_pin(obj, 0);
+	if (ret) {
+		mutex_unlock(&dev->struct_mutex);
+		return ret;
+	}
+	ret = i915_gem_set_domain(obj, file_priv,
+				  I915_GEM_DOMAIN_GTT, I915_GEM_DOMAIN_GTT);
+	if (ret)
+		goto fail;
+
+	obj_priv = obj->driver_private;
+	offset = obj_priv->gtt_offset + args->offset;
+	obj_priv->dirty = 1;
+
+	while (remain > 0) {
+		/* Operation in this page
+		 *
+		 * i = page number
+		 * o = offset within page
+		 * l = bytes to copy
+		 */
+		i = offset >> PAGE_SHIFT;
+		o = offset & (PAGE_SIZE-1);
+		l = remain;
+		if ((o + l) > PAGE_SIZE)
+			l = PAGE_SIZE - o;
+
+		pfn = (dev->agp->base >> PAGE_SHIFT) + i;
+
+#ifdef CONFIG_HIGHMEM
+		/* kmap_atomic can't map IO pages on non-HIGHMEM kernels
+		 */
+		vaddr = kmap_atomic_pfn(pfn, KM_USER0);
+#if WATCH_PWRITE
+		DRM_INFO("pwrite i %d o %d l %d pfn %ld vaddr %p\n",
+			 i, o, l, pfn, vaddr);
+#endif
+		unwritten = __copy_from_user_inatomic_nocache(vaddr + o,
+							      user_data, l);
+		kunmap_atomic(vaddr, KM_USER0);
+
+		if (unwritten)
+#endif /* CONFIG_HIGHMEM */
+		{
+			vaddr = ioremap(pfn << PAGE_SHIFT, PAGE_SIZE);
+#if WATCH_PWRITE
+			DRM_INFO("pwrite slow i %d o %d l %d "
+				 "pfn %ld vaddr %p\n",
+				 i, o, l, pfn, vaddr);
+#endif
+			if (vaddr == NULL) {
+				ret = -EFAULT;
+				goto fail;
+			}
+			unwritten = __copy_from_user(vaddr + o, user_data, l);
+#if WATCH_PWRITE
+			DRM_INFO("unwritten %ld\n", unwritten);
+#endif
+			iounmap(vaddr);
+			if (unwritten) {
+				ret = -EFAULT;
+				goto fail;
+			}
+		}
+
+		remain -= l;
+		user_data += l;
+		offset += l;
+	}
+#if WATCH_PWRITE && 1
+	i915_gem_clflush_object(obj);
+	i915_gem_dump_object(obj, args->offset + args->size, __func__, ~0);
+	i915_gem_clflush_object(obj);
+#endif
+
+fail:
+	i915_gem_object_unpin(obj);
+	mutex_unlock(&dev->struct_mutex);
+
+	return ret;
+}
+
+int
+i915_gem_shmem_pwrite(struct drm_device *dev, struct drm_gem_object *obj,
+		      struct drm_i915_gem_pwrite *args,
+		      struct drm_file *file_priv)
+{
+	int ret;
+	loff_t offset;
+	ssize_t written;
+
+	mutex_lock(&dev->struct_mutex);
+
+	ret = i915_gem_set_domain(obj, file_priv,
+				  I915_GEM_DOMAIN_CPU, I915_GEM_DOMAIN_CPU);
+	if (ret) {
+		mutex_unlock(&dev->struct_mutex);
+		return ret;
+	}
+
+	offset = args->offset;
+
+	written = vfs_write(obj->filp,
+			    (char __user *)(uintptr_t) args->data_ptr,
+			    args->size, &offset);
+	if (written != args->size) {
+		mutex_unlock(&dev->struct_mutex);
+		if (written < 0)
+			return written;
+		else
+			return -EINVAL;
+	}
+
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
+/**
+ * Writes data to the object referenced by handle.
+ *
+ * On error, the contents of the buffer that were to be modified are undefined.
+ */
+int
+i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv)
+{
+	struct drm_i915_gem_pwrite *args = data;
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+	int ret = 0;
+
+	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
+	if (obj == NULL)
+		return -EBADF;
+	obj_priv = obj->driver_private;
+
+	/* Bounds check destination.
+	 *
+	 * XXX: This could use review for overflow issues...
+	 */
+	if (args->offset > obj->size || args->size > obj->size ||
+	    args->offset + args->size > obj->size) {
+		drm_gem_object_unreference(obj);
+		return -EINVAL;
+	}
+
+	/* We can only do the GTT pwrite on untiled buffers, as otherwise
+	 * it would end up going through the fenced access, and we'll get
+	 * different detiling behavior between reading and writing.
+	 * pread/pwrite currently are reading and writing from the CPU
+	 * perspective, requiring manual detiling by the client.
+	 */
+	if (obj_priv->tiling_mode == I915_TILING_NONE &&
+	    dev->gtt_total != 0)
+		ret = i915_gem_gtt_pwrite(dev, obj, args, file_priv);
+	else
+		ret = i915_gem_shmem_pwrite(dev, obj, args, file_priv);
+
+#if WATCH_PWRITE
+	if (ret)
+		DRM_INFO("pwrite failed %d\n", ret);
+#endif
+
+	drm_gem_object_unreference(obj);
+
+	return ret;
+}
+
+/**
+ * Called when user space prepares to use an object
+ */
+int
+i915_gem_set_domain_ioctl(struct drm_device *dev, void *data,
+			  struct drm_file *file_priv)
+{
+	struct drm_i915_gem_set_domain *args = data;
+	struct drm_gem_object *obj;
+	int ret;
+
+	if (!(dev->driver->driver_features & DRIVER_GEM))
+		return -ENODEV;
+
+	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
+	if (obj == NULL)
+		return -EBADF;
+
+	mutex_lock(&dev->struct_mutex);
+#if WATCH_BUF
+	DRM_INFO("set_domain_ioctl %p(%d), %08x %08x\n",
+		 obj, obj->size, args->read_domains, args->write_domain);
+#endif
+	ret = i915_gem_set_domain(obj, file_priv,
+				  args->read_domains, args->write_domain);
+	drm_gem_object_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
+	return ret;
+}
+
+/**
+ * Called when user space has done writes to this buffer
+ */
+int
+i915_gem_sw_finish_ioctl(struct drm_device *dev, void *data,
+		      struct drm_file *file_priv)
+{
+	struct drm_i915_gem_sw_finish *args = data;
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+	int ret = 0;
+
+	if (!(dev->driver->driver_features & DRIVER_GEM))
+		return -ENODEV;
+
+	mutex_lock(&dev->struct_mutex);
+	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
+	if (obj == NULL) {
+		mutex_unlock(&dev->struct_mutex);
+		return -EBADF;
+	}
+
+#if WATCH_BUF
+	DRM_INFO("%s: sw_finish %d (%p %d)\n",
+		 __func__, args->handle, obj, obj->size);
+#endif
+	obj_priv = obj->driver_private;
+
+	/* Pinned buffers may be scanout, so flush the cache */
+	if ((obj->write_domain & I915_GEM_DOMAIN_CPU) && obj_priv->pin_count) {
+		i915_gem_clflush_object(obj);
+		drm_agp_chipset_flush(dev);
+	}
+	drm_gem_object_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
+	return ret;
+}
+
+/**
+ * Maps the contents of an object, returning the address it is mapped
+ * into.
+ *
+ * While the mapping holds a reference on the contents of the object, it doesn't
+ * imply a ref on the object itself.
+ */
+int
+i915_gem_mmap_ioctl(struct drm_device *dev, void *data,
+		   struct drm_file *file_priv)
+{
+	struct drm_i915_gem_mmap *args = data;
+	struct drm_gem_object *obj;
+	loff_t offset;
+	unsigned long addr;
+
+	if (!(dev->driver->driver_features & DRIVER_GEM))
+		return -ENODEV;
+
+	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
+	if (obj == NULL)
+		return -EBADF;
+
+	offset = args->offset;
+
+	down_write(&current->mm->mmap_sem);
+	addr = do_mmap(obj->filp, 0, args->size,
+		       PROT_READ | PROT_WRITE, MAP_SHARED,
+		       args->offset);
+	up_write(&current->mm->mmap_sem);
+	mutex_lock(&dev->struct_mutex);
+	drm_gem_object_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
+	if (IS_ERR((void *)addr))
+		return addr;
+
+	args->addr_ptr = (uint64_t) addr;
+
+	return 0;
+}
+
+static void
+i915_gem_object_free_page_list(struct drm_gem_object *obj)
+{
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	int page_count = obj->size / PAGE_SIZE;
+	int i;
+
+	if (obj_priv->page_list == NULL)
+		return;
+
+
+	for (i = 0; i < page_count; i++)
+		if (obj_priv->page_list[i] != NULL) {
+			if (obj_priv->dirty)
+				set_page_dirty(obj_priv->page_list[i]);
+			mark_page_accessed(obj_priv->page_list[i]);
+			page_cache_release(obj_priv->page_list[i]);
+		}
+	obj_priv->dirty = 0;
+
+	drm_free(obj_priv->page_list,
+		 page_count * sizeof(struct page *),
+		 DRM_MEM_DRIVER);
+	obj_priv->page_list = NULL;
+}
+
+static void
+i915_gem_object_move_to_active(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+
+	/* Add a reference if we're newly entering the active list. */
+	if (!obj_priv->active) {
+		drm_gem_object_reference(obj);
+		obj_priv->active = 1;
+	}
+	/* Move from whatever list we were on to the tail of execution. */
+	list_move_tail(&obj_priv->list,
+		       &dev_priv->mm.active_list);
+}
+
+
+static void
+i915_gem_object_move_to_inactive(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+	if (obj_priv->pin_count != 0)
+		list_del_init(&obj_priv->list);
+	else
+		list_move_tail(&obj_priv->list, &dev_priv->mm.inactive_list);
+
+	if (obj_priv->active) {
+		obj_priv->active = 0;
+		drm_gem_object_unreference(obj);
+	}
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+}
+
+/**
+ * Creates a new sequence number, emitting a write of it to the status page
+ * plus an interrupt, which will trigger i915_user_interrupt_handler.
+ *
+ * Must be called with struct_lock held.
+ *
+ * Returned sequence numbers are nonzero on success.
+ */
+static uint32_t
+i915_add_request(struct drm_device *dev, uint32_t flush_domains)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_request *request;
+	uint32_t seqno;
+	int was_empty;
+	RING_LOCALS;
+
+	request = drm_calloc(1, sizeof(*request), DRM_MEM_DRIVER);
+	if (request == NULL)
+		return 0;
+
+	/* Grab the seqno we're going to make this request be, and bump the
+	 * next (skipping 0 so it can be the reserved no-seqno value).
+	 */
+	seqno = dev_priv->mm.next_gem_seqno;
+	dev_priv->mm.next_gem_seqno++;
+	if (dev_priv->mm.next_gem_seqno == 0)
+		dev_priv->mm.next_gem_seqno++;
+
+	BEGIN_LP_RING(4);
+	OUT_RING(MI_STORE_DWORD_INDEX);
+	OUT_RING(I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
+	OUT_RING(seqno);
+
+	OUT_RING(MI_USER_INTERRUPT);
+	ADVANCE_LP_RING();
+
+	DRM_DEBUG("%d\n", seqno);
+
+	request->seqno = seqno;
+	request->emitted_jiffies = jiffies;
+	request->flush_domains = flush_domains;
+	was_empty = list_empty(&dev_priv->mm.request_list);
+	list_add_tail(&request->list, &dev_priv->mm.request_list);
+
+	if (was_empty)
+		schedule_delayed_work(&dev_priv->mm.retire_work, HZ);
+	return seqno;
+}
+
+/**
+ * Command execution barrier
+ *
+ * Ensures that all commands in the ring are finished
+ * before signalling the CPU
+ */
+uint32_t
+i915_retire_commands(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	uint32_t cmd = MI_FLUSH | MI_NO_WRITE_FLUSH;
+	uint32_t flush_domains = 0;
+	RING_LOCALS;
+
+	/* The sampler always gets flushed on i965 (sigh) */
+	if (IS_I965G(dev))
+		flush_domains |= I915_GEM_DOMAIN_SAMPLER;
+	BEGIN_LP_RING(2);
+	OUT_RING(cmd);
+	OUT_RING(0); /* noop */
+	ADVANCE_LP_RING();
+	return flush_domains;
+}
+
+/**
+ * Moves buffers associated only with the given active seqno from the active
+ * to inactive list, potentially freeing them.
+ */
+static void
+i915_gem_retire_request(struct drm_device *dev,
+			struct drm_i915_gem_request *request)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+
+	/* Move any buffers on the active list that are no longer referenced
+	 * by the ringbuffer to the flushing/inactive lists as appropriate.
+	 */
+	while (!list_empty(&dev_priv->mm.active_list)) {
+		struct drm_gem_object *obj;
+		struct drm_i915_gem_object *obj_priv;
+
+		obj_priv = list_first_entry(&dev_priv->mm.active_list,
+					    struct drm_i915_gem_object,
+					    list);
+		obj = obj_priv->obj;
+
+		/* If the seqno being retired doesn't match the oldest in the
+		 * list, then the oldest in the list must still be newer than
+		 * this seqno.
+		 */
+		if (obj_priv->last_rendering_seqno != request->seqno)
+			return;
+#if WATCH_LRU
+		DRM_INFO("%s: retire %d moves to inactive list %p\n",
+			 __func__, request->seqno, obj);
+#endif
+
+		if (obj->write_domain != 0) {
+			list_move_tail(&obj_priv->list,
+				       &dev_priv->mm.flushing_list);
+		} else {
+			i915_gem_object_move_to_inactive(obj);
+		}
+	}
+
+	if (request->flush_domains != 0) {
+		struct drm_i915_gem_object *obj_priv, *next;
+
+		/* Clear the write domain and activity from any buffers
+		 * that are just waiting for a flush matching the one retired.
+		 */
+		list_for_each_entry_safe(obj_priv, next,
+					 &dev_priv->mm.flushing_list, list) {
+			struct drm_gem_object *obj = obj_priv->obj;
+
+			if (obj->write_domain & request->flush_domains) {
+				obj->write_domain = 0;
+				i915_gem_object_move_to_inactive(obj);
+			}
+		}
+
+	}
+}
+
+/**
+ * Returns true if seq1 is later than seq2.
+ */
+static int
+i915_seqno_passed(uint32_t seq1, uint32_t seq2)
+{
+	return (int32_t)(seq1 - seq2) >= 0;
+}
+
+uint32_t
+i915_get_gem_seqno(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+
+	return READ_HWSP(dev_priv, I915_GEM_HWS_INDEX);
+}
+
+/**
+ * This function clears the request list as sequence numbers are passed.
+ */
+void
+i915_gem_retire_requests(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	uint32_t seqno;
+
+	seqno = i915_get_gem_seqno(dev);
+
+	while (!list_empty(&dev_priv->mm.request_list)) {
+		struct drm_i915_gem_request *request;
+		uint32_t retiring_seqno;
+
+		request = list_first_entry(&dev_priv->mm.request_list,
+					   struct drm_i915_gem_request,
+					   list);
+		retiring_seqno = request->seqno;
+
+		if (i915_seqno_passed(seqno, retiring_seqno) ||
+		    dev_priv->mm.wedged) {
+			i915_gem_retire_request(dev, request);
+
+			list_del(&request->list);
+			drm_free(request, sizeof(*request), DRM_MEM_DRIVER);
+		} else
+			break;
+	}
+}
+
+void
+i915_gem_retire_work_handler(struct work_struct *work)
+{
+	drm_i915_private_t *dev_priv;
+	struct drm_device *dev;
+
+	dev_priv = container_of(work, drm_i915_private_t,
+				mm.retire_work.work);
+	dev = dev_priv->dev;
+
+	mutex_lock(&dev->struct_mutex);
+	i915_gem_retire_requests(dev);
+	if (!list_empty(&dev_priv->mm.request_list))
+		schedule_delayed_work(&dev_priv->mm.retire_work, HZ);
+	mutex_unlock(&dev->struct_mutex);
+}
+
+/**
+ * Waits for a sequence number to be signaled, and cleans up the
+ * request and object lists appropriately for that event.
+ */
+int
+i915_wait_request(struct drm_device *dev, uint32_t seqno)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	int ret = 0;
+
+	BUG_ON(seqno == 0);
+
+	if (!i915_seqno_passed(i915_get_gem_seqno(dev), seqno)) {
+		dev_priv->mm.waiting_gem_seqno = seqno;
+		i915_user_irq_get(dev);
+		ret = wait_event_interruptible(dev_priv->irq_queue,
+					       i915_seqno_passed(i915_get_gem_seqno(dev),
+								 seqno) ||
+					       dev_priv->mm.wedged);
+		i915_user_irq_put(dev);
+		dev_priv->mm.waiting_gem_seqno = 0;
+	}
+	if (dev_priv->mm.wedged)
+		ret = -EIO;
+
+	if (ret && ret != -ERESTARTSYS)
+		DRM_ERROR("%s returns %d (awaiting %d at %d)\n",
+			  __func__, ret, seqno, i915_get_gem_seqno(dev));
+
+	/* Directly dispatch request retiring.  While we have the work queue
+	 * to handle this, the waiter on a request often wants an associated
+	 * buffer to have made it to the inactive list, and we would need
+	 * a separate wait queue to handle that.
+	 */
+	if (ret == 0)
+		i915_gem_retire_requests(dev);
+
+	return ret;
+}
+
+static void
+i915_gem_flush(struct drm_device *dev,
+	       uint32_t invalidate_domains,
+	       uint32_t flush_domains)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	uint32_t cmd;
+	RING_LOCALS;
+
+#if WATCH_EXEC
+	DRM_INFO("%s: invalidate %08x flush %08x\n", __func__,
+		  invalidate_domains, flush_domains);
+#endif
+
+	if (flush_domains & I915_GEM_DOMAIN_CPU)
+		drm_agp_chipset_flush(dev);
+
+	if ((invalidate_domains | flush_domains) & ~(I915_GEM_DOMAIN_CPU |
+						     I915_GEM_DOMAIN_GTT)) {
+		/*
+		 * read/write caches:
+		 *
+		 * I915_GEM_DOMAIN_RENDER is always invalidated, but is
+		 * only flushed if MI_NO_WRITE_FLUSH is unset.  On 965, it is
+		 * also flushed at 2d versus 3d pipeline switches.
+		 *
+		 * read-only caches:
+		 *
+		 * I915_GEM_DOMAIN_SAMPLER is flushed on pre-965 if
+		 * MI_READ_FLUSH is set, and is always flushed on 965.
+		 *
+		 * I915_GEM_DOMAIN_COMMAND may not exist?
+		 *
+		 * I915_GEM_DOMAIN_INSTRUCTION, which exists on 965, is
+		 * invalidated when MI_EXE_FLUSH is set.
+		 *
+		 * I915_GEM_DOMAIN_VERTEX, which exists on 965, is
+		 * invalidated with every MI_FLUSH.
+		 *
+		 * TLBs:
+		 *
+		 * On 965, TLBs associated with I915_GEM_DOMAIN_COMMAND
+		 * and I915_GEM_DOMAIN_CPU in are invalidated at PTE write and
+		 * I915_GEM_DOMAIN_RENDER and I915_GEM_DOMAIN_SAMPLER
+		 * are flushed at any MI_FLUSH.
+		 */
+
+		cmd = MI_FLUSH | MI_NO_WRITE_FLUSH;
+		if ((invalidate_domains|flush_domains) &
+		    I915_GEM_DOMAIN_RENDER)
+			cmd &= ~MI_NO_WRITE_FLUSH;
+		if (!IS_I965G(dev)) {
+			/*
+			 * On the 965, the sampler cache always gets flushed
+			 * and this bit is reserved.
+			 */
+			if (invalidate_domains & I915_GEM_DOMAIN_SAMPLER)
+				cmd |= MI_READ_FLUSH;
+		}
+		if (invalidate_domains & I915_GEM_DOMAIN_INSTRUCTION)
+			cmd |= MI_EXE_FLUSH;
+
+#if WATCH_EXEC
+		DRM_INFO("%s: queue flush %08x to ring\n", __func__, cmd);
+#endif
+		BEGIN_LP_RING(2);
+		OUT_RING(cmd);
+		OUT_RING(0); /* noop */
+		ADVANCE_LP_RING();
+	}
+}
+
+/**
+ * Ensures that all rendering to the object has completed and the object is
+ * safe to unbind from the GTT or access from the CPU.
+ */
+static int
+i915_gem_object_wait_rendering(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	int ret;
+
+	/* If there are writes queued to the buffer, flush and
+	 * create a new seqno to wait for.
+	 */
+	if (obj->write_domain & ~(I915_GEM_DOMAIN_CPU|I915_GEM_DOMAIN_GTT)) {
+		uint32_t write_domain = obj->write_domain;
+#if WATCH_BUF
+		DRM_INFO("%s: flushing object %p from write domain %08x\n",
+			  __func__, obj, write_domain);
+#endif
+		i915_gem_flush(dev, 0, write_domain);
+
+		i915_gem_object_move_to_active(obj);
+		obj_priv->last_rendering_seqno = i915_add_request(dev,
+								  write_domain);
+		BUG_ON(obj_priv->last_rendering_seqno == 0);
+#if WATCH_LRU
+		DRM_INFO("%s: flush moves to exec list %p\n", __func__, obj);
+#endif
+	}
+
+	/* If there is rendering queued on the buffer being evicted, wait for
+	 * it.
+	 */
+	if (obj_priv->active) {
+#if WATCH_BUF
+		DRM_INFO("%s: object %p wait for seqno %08x\n",
+			  __func__, obj, obj_priv->last_rendering_seqno);
+#endif
+		ret = i915_wait_request(dev, obj_priv->last_rendering_seqno);
+		if (ret != 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * Unbinds an object from the GTT aperture.
+ */
+static int
+i915_gem_object_unbind(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	int ret = 0;
+
+#if WATCH_BUF
+	DRM_INFO("%s:%d %p\n", __func__, __LINE__, obj);
+	DRM_INFO("gtt_space %p\n", obj_priv->gtt_space);
+#endif
+	if (obj_priv->gtt_space == NULL)
+		return 0;
+
+	if (obj_priv->pin_count != 0) {
+		DRM_ERROR("Attempting to unbind pinned buffer\n");
+		return -EINVAL;
+	}
+
+	/* Wait for any rendering to complete
+	 */
+	ret = i915_gem_object_wait_rendering(obj);
+	if (ret) {
+		DRM_ERROR("wait_rendering failed: %d\n", ret);
+		return ret;
+	}
+
+	/* Move the object to the CPU domain to ensure that
+	 * any possible CPU writes while it's not in the GTT
+	 * are flushed when we go to remap it. This will
+	 * also ensure that all pending GPU writes are finished
+	 * before we unbind.
+	 */
+	ret = i915_gem_object_set_domain(obj, I915_GEM_DOMAIN_CPU,
+					 I915_GEM_DOMAIN_CPU);
+	if (ret) {
+		DRM_ERROR("set_domain failed: %d\n", ret);
+		return ret;
+	}
+
+	if (obj_priv->agp_mem != NULL) {
+		drm_unbind_agp(obj_priv->agp_mem);
+		drm_free_agp(obj_priv->agp_mem, obj->size / PAGE_SIZE);
+		obj_priv->agp_mem = NULL;
+	}
+
+	BUG_ON(obj_priv->active);
+
+	i915_gem_object_free_page_list(obj);
+
+	if (obj_priv->gtt_space) {
+		atomic_dec(&dev->gtt_count);
+		atomic_sub(obj->size, &dev->gtt_memory);
+
+		drm_mm_put_block(obj_priv->gtt_space);
+		obj_priv->gtt_space = NULL;
+	}
+
+	/* Remove ourselves from the LRU list if present. */
+	if (!list_empty(&obj_priv->list))
+		list_del_init(&obj_priv->list);
+
+	return 0;
+}
+
+static int
+i915_gem_evict_something(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+	int ret = 0;
+
+	for (;;) {
+		/* If there's an inactive buffer available now, grab it
+		 * and be done.
+		 */
+		if (!list_empty(&dev_priv->mm.inactive_list)) {
+			obj_priv = list_first_entry(&dev_priv->mm.inactive_list,
+						    struct drm_i915_gem_object,
+						    list);
+			obj = obj_priv->obj;
+			BUG_ON(obj_priv->pin_count != 0);
+#if WATCH_LRU
+			DRM_INFO("%s: evicting %p\n", __func__, obj);
+#endif
+			BUG_ON(obj_priv->active);
+
+			/* Wait on the rendering and unbind the buffer. */
+			ret = i915_gem_object_unbind(obj);
+			break;
+		}
+
+		/* If we didn't get anything, but the ring is still processing
+		 * things, wait for one of those things to finish and hopefully
+		 * leave us a buffer to evict.
+		 */
+		if (!list_empty(&dev_priv->mm.request_list)) {
+			struct drm_i915_gem_request *request;
+
+			request = list_first_entry(&dev_priv->mm.request_list,
+						   struct drm_i915_gem_request,
+						   list);
+
+			ret = i915_wait_request(dev, request->seqno);
+			if (ret)
+				break;
+
+			/* if waiting caused an object to become inactive,
+			 * then loop around and wait for it. Otherwise, we
+			 * assume that waiting freed and unbound something,
+			 * so there should now be some space in the GTT
+			 */
+			if (!list_empty(&dev_priv->mm.inactive_list))
+				continue;
+			break;
+		}
+
+		/* If we didn't have anything on the request list but there
+		 * are buffers awaiting a flush, emit one and try again.
+		 * When we wait on it, those buffers waiting for that flush
+		 * will get moved to inactive.
+		 */
+		if (!list_empty(&dev_priv->mm.flushing_list)) {
+			obj_priv = list_first_entry(&dev_priv->mm.flushing_list,
+						    struct drm_i915_gem_object,
+						    list);
+			obj = obj_priv->obj;
+
+			i915_gem_flush(dev,
+				       obj->write_domain,
+				       obj->write_domain);
+			i915_add_request(dev, obj->write_domain);
+
+			obj = NULL;
+			continue;
+		}
+
+		DRM_ERROR("inactive empty %d request empty %d "
+			  "flushing empty %d\n",
+			  list_empty(&dev_priv->mm.inactive_list),
+			  list_empty(&dev_priv->mm.request_list),
+			  list_empty(&dev_priv->mm.flushing_list));
+		/* If we didn't do any of the above, there's nothing to be done
+		 * and we just can't fit it in.
+		 */
+		return -ENOMEM;
+	}
+	return ret;
+}
+
+static int
+i915_gem_object_get_page_list(struct drm_gem_object *obj)
+{
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	int page_count, i;
+	struct address_space *mapping;
+	struct inode *inode;
+	struct page *page;
+	int ret;
+
+	if (obj_priv->page_list)
+		return 0;
+
+	/* Get the list of pages out of our struct file.  They'll be pinned
+	 * at this point until we release them.
+	 */
+	page_count = obj->size / PAGE_SIZE;
+	BUG_ON(obj_priv->page_list != NULL);
+	obj_priv->page_list = drm_calloc(page_count, sizeof(struct page *),
+					 DRM_MEM_DRIVER);
+	if (obj_priv->page_list == NULL) {
+		DRM_ERROR("Faled to allocate page list\n");
+		return -ENOMEM;
+	}
+
+	inode = obj->filp->f_path.dentry->d_inode;
+	mapping = inode->i_mapping;
+	for (i = 0; i < page_count; i++) {
+		page = read_mapping_page(mapping, i, NULL);
+		if (IS_ERR(page)) {
+			ret = PTR_ERR(page);
+			DRM_ERROR("read_mapping_page failed: %d\n", ret);
+			i915_gem_object_free_page_list(obj);
+			return ret;
+		}
+		obj_priv->page_list[i] = page;
+	}
+	return 0;
+}
+
+/**
+ * Finds free space in the GTT aperture and binds the object there.
+ */
+static int
+i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment)
+{
+	struct drm_device *dev = obj->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	struct drm_mm_node *free_space;
+	int page_count, ret;
+
+	if (alignment == 0)
+		alignment = PAGE_SIZE;
+	if (alignment & (PAGE_SIZE - 1)) {
+		DRM_ERROR("Invalid object alignment requested %u\n", alignment);
+		return -EINVAL;
+	}
+
+ search_free:
+	free_space = drm_mm_search_free(&dev_priv->mm.gtt_space,
+					obj->size, alignment, 0);
+	if (free_space != NULL) {
+		obj_priv->gtt_space = drm_mm_get_block(free_space, obj->size,
+						       alignment);
+		if (obj_priv->gtt_space != NULL) {
+			obj_priv->gtt_space->private = obj;
+			obj_priv->gtt_offset = obj_priv->gtt_space->start;
+		}
+	}
+	if (obj_priv->gtt_space == NULL) {
+		/* If the gtt is empty and we're still having trouble
+		 * fitting our object in, we're out of memory.
+		 */
+#if WATCH_LRU
+		DRM_INFO("%s: GTT full, evicting something\n", __func__);
+#endif
+		if (list_empty(&dev_priv->mm.inactive_list) &&
+		    list_empty(&dev_priv->mm.flushing_list) &&
+		    list_empty(&dev_priv->mm.active_list)) {
+			DRM_ERROR("GTT full, but LRU list empty\n");
+			return -ENOMEM;
+		}
+
+		ret = i915_gem_evict_something(dev);
+		if (ret != 0) {
+			DRM_ERROR("Failed to evict a buffer %d\n", ret);
+			return ret;
+		}
+		goto search_free;
+	}
+
+#if WATCH_BUF
+	DRM_INFO("Binding object of size %d at 0x%08x\n",
+		 obj->size, obj_priv->gtt_offset);
+#endif
+	ret = i915_gem_object_get_page_list(obj);
+	if (ret) {
+		drm_mm_put_block(obj_priv->gtt_space);
+		obj_priv->gtt_space = NULL;
+		return ret;
+	}
+
+	page_count = obj->size / PAGE_SIZE;
+	/* Create an AGP memory structure pointing at our pages, and bind it
+	 * into the GTT.
+	 */
+	obj_priv->agp_mem = drm_agp_bind_pages(dev,
+					       obj_priv->page_list,
+					       page_count,
+					       obj_priv->gtt_offset);
+	if (obj_priv->agp_mem == NULL) {
+		i915_gem_object_free_page_list(obj);
+		drm_mm_put_block(obj_priv->gtt_space);
+		obj_priv->gtt_space = NULL;
+		return -ENOMEM;
+	}
+	atomic_inc(&dev->gtt_count);
+	atomic_add(obj->size, &dev->gtt_memory);
+
+	/* Assert that the object is not currently in any GPU domain. As it
+	 * wasn't in the GTT, there shouldn't be any way it could have been in
+	 * a GPU cache
+	 */
+	BUG_ON(obj->read_domains & ~(I915_GEM_DOMAIN_CPU|I915_GEM_DOMAIN_GTT));
+	BUG_ON(obj->write_domain & ~(I915_GEM_DOMAIN_CPU|I915_GEM_DOMAIN_GTT));
+
+	return 0;
+}
+
+void
+i915_gem_clflush_object(struct drm_gem_object *obj)
+{
+	struct drm_i915_gem_object	*obj_priv = obj->driver_private;
+
+	/* If we don't have a page list set up, then we're not pinned
+	 * to GPU, and we can ignore the cache flush because it'll happen
+	 * again at bind time.
+	 */
+	if (obj_priv->page_list == NULL)
+		return;
+
+	drm_clflush_pages(obj_priv->page_list, obj->size / PAGE_SIZE);
+}
+
+/*
+ * Set the next domain for the specified object. This
+ * may not actually perform the necessary flushing/invaliding though,
+ * as that may want to be batched with other set_domain operations
+ *
+ * This is (we hope) the only really tricky part of gem. The goal
+ * is fairly simple -- track which caches hold bits of the object
+ * and make sure they remain coherent. A few concrete examples may
+ * help to explain how it works. For shorthand, we use the notation
+ * (read_domains, write_domain), e.g. (CPU, CPU) to indicate the
+ * a pair of read and write domain masks.
+ *
+ * Case 1: the batch buffer
+ *
+ *	1. Allocated
+ *	2. Written by CPU
+ *	3. Mapped to GTT
+ *	4. Read by GPU
+ *	5. Unmapped from GTT
+ *	6. Freed
+ *
+ *	Let's take these a step at a time
+ *
+ *	1. Allocated
+ *		Pages allocated from the kernel may still have
+ *		cache contents, so we set them to (CPU, CPU) always.
+ *	2. Written by CPU (using pwrite)
+ *		The pwrite function calls set_domain (CPU, CPU) and
+ *		this function does nothing (as nothing changes)
+ *	3. Mapped by GTT
+ *		This function asserts that the object is not
+ *		currently in any GPU-based read or write domains
+ *	4. Read by GPU
+ *		i915_gem_execbuffer calls set_domain (COMMAND, 0).
+ *		As write_domain is zero, this function adds in the
+ *		current read domains (CPU+COMMAND, 0).
+ *		flush_domains is set to CPU.
+ *		invalidate_domains is set to COMMAND
+ *		clflush is run to get data out of the CPU caches
+ *		then i915_dev_set_domain calls i915_gem_flush to
+ *		emit an MI_FLUSH and drm_agp_chipset_flush
+ *	5. Unmapped from GTT
+ *		i915_gem_object_unbind calls set_domain (CPU, CPU)
+ *		flush_domains and invalidate_domains end up both zero
+ *		so no flushing/invalidating happens
+ *	6. Freed
+ *		yay, done
+ *
+ * Case 2: The shared render buffer
+ *
+ *	1. Allocated
+ *	2. Mapped to GTT
+ *	3. Read/written by GPU
+ *	4. set_domain to (CPU,CPU)
+ *	5. Read/written by CPU
+ *	6. Read/written by GPU
+ *
+ *	1. Allocated
+ *		Same as last example, (CPU, CPU)
+ *	2. Mapped to GTT
+ *		Nothing changes (assertions find that it is not in the GPU)
+ *	3. Read/written by GPU
+ *		execbuffer calls set_domain (RENDER, RENDER)
+ *		flush_domains gets CPU
+ *		invalidate_domains gets GPU
+ *		clflush (obj)
+ *		MI_FLUSH and drm_agp_chipset_flush
+ *	4. set_domain (CPU, CPU)
+ *		flush_domains gets GPU
+ *		invalidate_domains gets CPU
+ *		wait_rendering (obj) to make sure all drawing is complete.
+ *		This will include an MI_FLUSH to get the data from GPU
+ *		to memory
+ *		clflush (obj) to invalidate the CPU cache
+ *		Another MI_FLUSH in i915_gem_flush (eliminate this somehow?)
+ *	5. Read/written by CPU
+ *		cache lines are loaded and dirtied
+ *	6. Read written by GPU
+ *		Same as last GPU access
+ *
+ * Case 3: The constant buffer
+ *
+ *	1. Allocated
+ *	2. Written by CPU
+ *	3. Read by GPU
+ *	4. Updated (written) by CPU again
+ *	5. Read by GPU
+ *
+ *	1. Allocated
+ *		(CPU, CPU)
+ *	2. Written by CPU
+ *		(CPU, CPU)
+ *	3. Read by GPU
+ *		(CPU+RENDER, 0)
+ *		flush_domains = CPU
+ *		invalidate_domains = RENDER
+ *		clflush (obj)
+ *		MI_FLUSH
+ *		drm_agp_chipset_flush
+ *	4. Updated (written) by CPU again
+ *		(CPU, CPU)
+ *		flush_domains = 0 (no previous write domain)
+ *		invalidate_domains = 0 (no new read domains)
+ *	5. Read by GPU
+ *		(CPU+RENDER, 0)
+ *		flush_domains = CPU
+ *		invalidate_domains = RENDER
+ *		clflush (obj)
+ *		MI_FLUSH
+ *		drm_agp_chipset_flush
+ */
+static int
+i915_gem_object_set_domain(struct drm_gem_object *obj,
+			    uint32_t read_domains,
+			    uint32_t write_domain)
+{
+	struct drm_device		*dev = obj->dev;
+	struct drm_i915_gem_object	*obj_priv = obj->driver_private;
+	uint32_t			invalidate_domains = 0;
+	uint32_t			flush_domains = 0;
+	int				ret;
+
+#if WATCH_BUF
+	DRM_INFO("%s: object %p read %08x -> %08x write %08x -> %08x\n",
+		 __func__, obj,
+		 obj->read_domains, read_domains,
+		 obj->write_domain, write_domain);
+#endif
+	/*
+	 * If the object isn't moving to a new write domain,
+	 * let the object stay in multiple read domains
+	 */
+	if (write_domain == 0)
+		read_domains |= obj->read_domains;
+	else
+		obj_priv->dirty = 1;
+
+	/*
+	 * Flush the current write domain if
+	 * the new read domains don't match. Invalidate
+	 * any read domains which differ from the old
+	 * write domain
+	 */
+	if (obj->write_domain && obj->write_domain != read_domains) {
+		flush_domains |= obj->write_domain;
+		invalidate_domains |= read_domains & ~obj->write_domain;
+	}
+	/*
+	 * Invalidate any read caches which may have
+	 * stale data. That is, any new read domains.
+	 */
+	invalidate_domains |= read_domains & ~obj->read_domains;
+	if ((flush_domains | invalidate_domains) & I915_GEM_DOMAIN_CPU) {
+#if WATCH_BUF
+		DRM_INFO("%s: CPU domain flush %08x invalidate %08x\n",
+			 __func__, flush_domains, invalidate_domains);
+#endif
+		/*
+		 * If we're invaliding the CPU cache and flushing a GPU cache,
+		 * then pause for rendering so that the GPU caches will be
+		 * flushed before the cpu cache is invalidated
+		 */
+		if ((invalidate_domains & I915_GEM_DOMAIN_CPU) &&
+		    (flush_domains & ~(I915_GEM_DOMAIN_CPU |
+				       I915_GEM_DOMAIN_GTT))) {
+			ret = i915_gem_object_wait_rendering(obj);
+			if (ret)
+				return ret;
+		}
+		i915_gem_clflush_object(obj);
+	}
+
+	if ((write_domain | flush_domains) != 0)
+		obj->write_domain = write_domain;
+
+	/* If we're invalidating the CPU domain, clear the per-page CPU
+	 * domain list as well.
+	 */
+	if (obj_priv->page_cpu_valid != NULL &&
+	    (write_domain != 0 ||
+	     read_domains & I915_GEM_DOMAIN_CPU)) {
+		drm_free(obj_priv->page_cpu_valid, obj->size / PAGE_SIZE,
+			 DRM_MEM_DRIVER);
+		obj_priv->page_cpu_valid = NULL;
+	}
+	obj->read_domains = read_domains;
+
+	dev->invalidate_domains |= invalidate_domains;
+	dev->flush_domains |= flush_domains;
+#if WATCH_BUF
+	DRM_INFO("%s: read %08x write %08x invalidate %08x flush %08x\n",
+		 __func__,
+		 obj->read_domains, obj->write_domain,
+		 dev->invalidate_domains, dev->flush_domains);
+#endif
+	return 0;
+}
+
+/**
+ * Set the read/write domain on a range of the object.
+ *
+ * Currently only implemented for CPU reads, otherwise drops to normal
+ * i915_gem_object_set_domain().
+ */
+static int
+i915_gem_object_set_domain_range(struct drm_gem_object *obj,
+				 uint64_t offset,
+				 uint64_t size,
+				 uint32_t read_domains,
+				 uint32_t write_domain)
+{
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	int ret, i;
+
+	if (obj->read_domains & I915_GEM_DOMAIN_CPU)
+		return 0;
+
+	if (read_domains != I915_GEM_DOMAIN_CPU ||
+	    write_domain != 0)
+		return i915_gem_object_set_domain(obj,
+						  read_domains, write_domain);
+
+	/* Wait on any GPU rendering to the object to be flushed. */
+	if (obj->write_domain & ~(I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT)) {
+		ret = i915_gem_object_wait_rendering(obj);
+		if (ret)
+			return ret;
+	}
+
+	if (obj_priv->page_cpu_valid == NULL) {
+		obj_priv->page_cpu_valid = drm_calloc(1, obj->size / PAGE_SIZE,
+						      DRM_MEM_DRIVER);
+	}
+
+	/* Flush the cache on any pages that are still invalid from the CPU's
+	 * perspective.
+	 */
+	for (i = offset / PAGE_SIZE; i <= (offset + size - 1) / PAGE_SIZE; i++) {
+		if (obj_priv->page_cpu_valid[i])
+			continue;
+
+		drm_clflush_pages(obj_priv->page_list + i, 1);
+
+		obj_priv->page_cpu_valid[i] = 1;
+	}
+
+	return 0;
+}
+
+/**
+ * Once all of the objects have been set in the proper domain,
+ * perform the necessary flush and invalidate operations.
+ *
+ * Returns the write domains flushed, for use in flush tracking.
+ */
+static uint32_t
+i915_gem_dev_set_domain(struct drm_device *dev)
+{
+	uint32_t flush_domains = dev->flush_domains;
+
+	/*
+	 * Now that all the buffers are synced to the proper domains,
+	 * flush and invalidate the collected domains
+	 */
+	if (dev->invalidate_domains | dev->flush_domains) {
+#if WATCH_EXEC
+		DRM_INFO("%s: invalidate_domains %08x flush_domains %08x\n",
+			  __func__,
+			 dev->invalidate_domains,
+			 dev->flush_domains);
+#endif
+		i915_gem_flush(dev,
+			       dev->invalidate_domains,
+			       dev->flush_domains);
+		dev->invalidate_domains = 0;
+		dev->flush_domains = 0;
+	}
+
+	return flush_domains;
+}
+
+/**
+ * Pin an object to the GTT and evaluate the relocations landing in it.
+ */
+static int
+i915_gem_object_pin_and_relocate(struct drm_gem_object *obj,
+				 struct drm_file *file_priv,
+				 struct drm_i915_gem_exec_object *entry)
+{
+	struct drm_device *dev = obj->dev;
+	struct drm_i915_gem_relocation_entry reloc;
+	struct drm_i915_gem_relocation_entry __user *relocs;
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	int i, ret;
+	uint32_t last_reloc_offset = -1;
+	void *reloc_page = NULL;
+
+	/* Choose the GTT offset for our buffer and put it there. */
+	ret = i915_gem_object_pin(obj, (uint32_t) entry->alignment);
+	if (ret)
+		return ret;
+
+	entry->offset = obj_priv->gtt_offset;
+
+	relocs = (struct drm_i915_gem_relocation_entry __user *)
+		 (uintptr_t) entry->relocs_ptr;
+	/* Apply the relocations, using the GTT aperture to avoid cache
+	 * flushing requirements.
+	 */
+	for (i = 0; i < entry->relocation_count; i++) {
+		struct drm_gem_object *target_obj;
+		struct drm_i915_gem_object *target_obj_priv;
+		uint32_t reloc_val, reloc_offset, *reloc_entry;
+		int ret;
+
+		ret = copy_from_user(&reloc, relocs + i, sizeof(reloc));
+		if (ret != 0) {
+			i915_gem_object_unpin(obj);
+			return ret;
+		}
+
+		target_obj = drm_gem_object_lookup(obj->dev, file_priv,
+						   reloc.target_handle);
+		if (target_obj == NULL) {
+			i915_gem_object_unpin(obj);
+			return -EBADF;
+		}
+		target_obj_priv = target_obj->driver_private;
+
+		/* The target buffer should have appeared before us in the
+		 * exec_object list, so it should have a GTT space bound by now.
+		 */
+		if (target_obj_priv->gtt_space == NULL) {
+			DRM_ERROR("No GTT space found for object %d\n",
+				  reloc.target_handle);
+			drm_gem_object_unreference(target_obj);
+			i915_gem_object_unpin(obj);
+			return -EINVAL;
+		}
+
+		if (reloc.offset > obj->size - 4) {
+			DRM_ERROR("Relocation beyond object bounds: "
+				  "obj %p target %d offset %d size %d.\n",
+				  obj, reloc.target_handle,
+				  (int) reloc.offset, (int) obj->size);
+			drm_gem_object_unreference(target_obj);
+			i915_gem_object_unpin(obj);
+			return -EINVAL;
+		}
+		if (reloc.offset & 3) {
+			DRM_ERROR("Relocation not 4-byte aligned: "
+				  "obj %p target %d offset %d.\n",
+				  obj, reloc.target_handle,
+				  (int) reloc.offset);
+			drm_gem_object_unreference(target_obj);
+			i915_gem_object_unpin(obj);
+			return -EINVAL;
+		}
+
+		if (reloc.write_domain && target_obj->pending_write_domain &&
+		    reloc.write_domain != target_obj->pending_write_domain) {
+			DRM_ERROR("Write domain conflict: "
+				  "obj %p target %d offset %d "
+				  "new %08x old %08x\n",
+				  obj, reloc.target_handle,
+				  (int) reloc.offset,
+				  reloc.write_domain,
+				  target_obj->pending_write_domain);
+			drm_gem_object_unreference(target_obj);
+			i915_gem_object_unpin(obj);
+			return -EINVAL;
+		}
+
+#if WATCH_RELOC
+		DRM_INFO("%s: obj %p offset %08x target %d "
+			 "read %08x write %08x gtt %08x "
+			 "presumed %08x delta %08x\n",
+			 __func__,
+			 obj,
+			 (int) reloc.offset,
+			 (int) reloc.target_handle,
+			 (int) reloc.read_domains,
+			 (int) reloc.write_domain,
+			 (int) target_obj_priv->gtt_offset,
+			 (int) reloc.presumed_offset,
+			 reloc.delta);
+#endif
+
+		target_obj->pending_read_domains |= reloc.read_domains;
+		target_obj->pending_write_domain |= reloc.write_domain;
+
+		/* If the relocation already has the right value in it, no
+		 * more work needs to be done.
+		 */
+		if (target_obj_priv->gtt_offset == reloc.presumed_offset) {
+			drm_gem_object_unreference(target_obj);
+			continue;
+		}
+
+		/* Now that we're going to actually write some data in,
+		 * make sure that any rendering using this buffer's contents
+		 * is completed.
+		 */
+		i915_gem_object_wait_rendering(obj);
+
+		/* As we're writing through the gtt, flush
+		 * any CPU writes before we write the relocations
+		 */
+		if (obj->write_domain & I915_GEM_DOMAIN_CPU) {
+			i915_gem_clflush_object(obj);
+			drm_agp_chipset_flush(dev);
+			obj->write_domain = 0;
+		}
+
+		/* Map the page containing the relocation we're going to
+		 * perform.
+		 */
+		reloc_offset = obj_priv->gtt_offset + reloc.offset;
+		if (reloc_page == NULL ||
+		    (last_reloc_offset & ~(PAGE_SIZE - 1)) !=
+		    (reloc_offset & ~(PAGE_SIZE - 1))) {
+			if (reloc_page != NULL)
+				iounmap(reloc_page);
+
+			reloc_page = ioremap(dev->agp->base +
+					     (reloc_offset & ~(PAGE_SIZE - 1)),
+					     PAGE_SIZE);
+			last_reloc_offset = reloc_offset;
+			if (reloc_page == NULL) {
+				drm_gem_object_unreference(target_obj);
+				i915_gem_object_unpin(obj);
+				return -ENOMEM;
+			}
+		}
+
+		reloc_entry = (uint32_t *)((char *)reloc_page +
+					   (reloc_offset & (PAGE_SIZE - 1)));
+		reloc_val = target_obj_priv->gtt_offset + reloc.delta;
+
+#if WATCH_BUF
+		DRM_INFO("Applied relocation: %p@0x%08x %08x -> %08x\n",
+			  obj, (unsigned int) reloc.offset,
+			  readl(reloc_entry), reloc_val);
+#endif
+		writel(reloc_val, reloc_entry);
+
+		/* Write the updated presumed offset for this entry back out
+		 * to the user.
+		 */
+		reloc.presumed_offset = target_obj_priv->gtt_offset;
+		ret = copy_to_user(relocs + i, &reloc, sizeof(reloc));
+		if (ret != 0) {
+			drm_gem_object_unreference(target_obj);
+			i915_gem_object_unpin(obj);
+			return ret;
+		}
+
+		drm_gem_object_unreference(target_obj);
+	}
+
+	if (reloc_page != NULL)
+		iounmap(reloc_page);
+
+#if WATCH_BUF
+	if (0)
+		i915_gem_dump_object(obj, 128, __func__, ~0);
+#endif
+	return 0;
+}
+
+/** Dispatch a batchbuffer to the ring
+ */
+static int
+i915_dispatch_gem_execbuffer(struct drm_device *dev,
+			      struct drm_i915_gem_execbuffer *exec,
+			      uint64_t exec_offset)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_clip_rect __user *boxes = (struct drm_clip_rect __user *)
+					     (uintptr_t) exec->cliprects_ptr;
+	int nbox = exec->num_cliprects;
+	int i = 0, count;
+	uint32_t	exec_start, exec_len;
+	RING_LOCALS;
+
+	exec_start = (uint32_t) exec_offset + exec->batch_start_offset;
+	exec_len = (uint32_t) exec->batch_len;
+
+	if ((exec_start | exec_len) & 0x7) {
+		DRM_ERROR("alignment\n");
+		return -EINVAL;
+	}
+
+	if (!exec_start)
+		return -EINVAL;
+
+	count = nbox ? nbox : 1;
+
+	for (i = 0; i < count; i++) {
+		if (i < nbox) {
+			int ret = i915_emit_box(dev, boxes, i,
+						exec->DR1, exec->DR4);
+			if (ret)
+				return ret;
+		}
+
+		if (IS_I830(dev) || IS_845G(dev)) {
+			BEGIN_LP_RING(4);
+			OUT_RING(MI_BATCH_BUFFER);
+			OUT_RING(exec_start | MI_BATCH_NON_SECURE);
+			OUT_RING(exec_start + exec_len - 4);
+			OUT_RING(0);
+			ADVANCE_LP_RING();
+		} else {
+			BEGIN_LP_RING(2);
+			if (IS_I965G(dev)) {
+				OUT_RING(MI_BATCH_BUFFER_START |
+					 (2 << 6) |
+					 MI_BATCH_NON_SECURE_I965);
+				OUT_RING(exec_start);
+			} else {
+				OUT_RING(MI_BATCH_BUFFER_START |
+					 (2 << 6));
+				OUT_RING(exec_start | MI_BATCH_NON_SECURE);
+			}
+			ADVANCE_LP_RING();
+		}
+	}
+
+	/* XXX breadcrumb */
+	return 0;
+}
+
+/* Throttle our rendering by waiting until the ring has completed our requests
+ * emitted over 20 msec ago.
+ *
+ * This should get us reasonable parallelism between CPU and GPU but also
+ * relatively low latency when blocking on a particular request to finish.
+ */
+static int
+i915_gem_ring_throttle(struct drm_device *dev, struct drm_file *file_priv)
+{
+	struct drm_i915_file_private *i915_file_priv = file_priv->driver_priv;
+	int ret = 0;
+	uint32_t seqno;
+
+	mutex_lock(&dev->struct_mutex);
+	seqno = i915_file_priv->mm.last_gem_throttle_seqno;
+	i915_file_priv->mm.last_gem_throttle_seqno =
+		i915_file_priv->mm.last_gem_seqno;
+	if (seqno)
+		ret = i915_wait_request(dev, seqno);
+	mutex_unlock(&dev->struct_mutex);
+	return ret;
+}
+
+int
+i915_gem_execbuffer(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_file_private *i915_file_priv = file_priv->driver_priv;
+	struct drm_i915_gem_execbuffer *args = data;
+	struct drm_i915_gem_exec_object *exec_list = NULL;
+	struct drm_gem_object **object_list = NULL;
+	struct drm_gem_object *batch_obj;
+	int ret, i, pinned = 0;
+	uint64_t exec_offset;
+	uint32_t seqno, flush_domains;
+
+#if WATCH_EXEC
+	DRM_INFO("buffers_ptr %d buffer_count %d len %08x\n",
+		  (int) args->buffers_ptr, args->buffer_count, args->batch_len);
+#endif
+
+	/* Copy in the exec list from userland */
+	exec_list = drm_calloc(sizeof(*exec_list), args->buffer_count,
+			       DRM_MEM_DRIVER);
+	object_list = drm_calloc(sizeof(*object_list), args->buffer_count,
+				 DRM_MEM_DRIVER);
+	if (exec_list == NULL || object_list == NULL) {
+		DRM_ERROR("Failed to allocate exec or object list "
+			  "for %d buffers\n",
+			  args->buffer_count);
+		ret = -ENOMEM;
+		goto pre_mutex_err;
+	}
+	ret = copy_from_user(exec_list,
+			     (struct drm_i915_relocation_entry __user *)
+			     (uintptr_t) args->buffers_ptr,
+			     sizeof(*exec_list) * args->buffer_count);
+	if (ret != 0) {
+		DRM_ERROR("copy %d exec entries failed %d\n",
+			  args->buffer_count, ret);
+		goto pre_mutex_err;
+	}
+
+	mutex_lock(&dev->struct_mutex);
+
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+
+	if (dev_priv->mm.wedged) {
+		DRM_ERROR("Execbuf while wedged\n");
+		mutex_unlock(&dev->struct_mutex);
+		return -EIO;
+	}
+
+	if (dev_priv->mm.suspended) {
+		DRM_ERROR("Execbuf while VT-switched.\n");
+		mutex_unlock(&dev->struct_mutex);
+		return -EBUSY;
+	}
+
+	/* Zero the gloabl flush/invalidate flags. These
+	 * will be modified as each object is bound to the
+	 * gtt
+	 */
+	dev->invalidate_domains = 0;
+	dev->flush_domains = 0;
+
+	/* Look up object handles and perform the relocations */
+	for (i = 0; i < args->buffer_count; i++) {
+		object_list[i] = drm_gem_object_lookup(dev, file_priv,
+						       exec_list[i].handle);
+		if (object_list[i] == NULL) {
+			DRM_ERROR("Invalid object handle %d at index %d\n",
+				   exec_list[i].handle, i);
+			ret = -EBADF;
+			goto err;
+		}
+
+		object_list[i]->pending_read_domains = 0;
+		object_list[i]->pending_write_domain = 0;
+		ret = i915_gem_object_pin_and_relocate(object_list[i],
+						       file_priv,
+						       &exec_list[i]);
+		if (ret) {
+			DRM_ERROR("object bind and relocate failed %d\n", ret);
+			goto err;
+		}
+		pinned = i + 1;
+	}
+
+	/* Set the pending read domains for the batch buffer to COMMAND */
+	batch_obj = object_list[args->buffer_count-1];
+	batch_obj->pending_read_domains = I915_GEM_DOMAIN_COMMAND;
+	batch_obj->pending_write_domain = 0;
+
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+
+	for (i = 0; i < args->buffer_count; i++) {
+		struct drm_gem_object *obj = object_list[i];
+		struct drm_i915_gem_object *obj_priv = obj->driver_private;
+
+		if (obj_priv->gtt_space == NULL) {
+			/* We evicted the buffer in the process of validating
+			 * our set of buffers in.  We could try to recover by
+			 * kicking them everything out and trying again from
+			 * the start.
+			 */
+			ret = -ENOMEM;
+			goto err;
+		}
+
+		/* make sure all previous memory operations have passed */
+		ret = i915_gem_object_set_domain(obj,
+						 obj->pending_read_domains,
+						 obj->pending_write_domain);
+		if (ret)
+			goto err;
+	}
+
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+
+	/* Flush/invalidate caches and chipset buffer */
+	flush_domains = i915_gem_dev_set_domain(dev);
+
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+
+#if WATCH_COHERENCY
+	for (i = 0; i < args->buffer_count; i++) {
+		i915_gem_object_check_coherency(object_list[i],
+						exec_list[i].handle);
+	}
+#endif
+
+	exec_offset = exec_list[args->buffer_count - 1].offset;
+
+#if WATCH_EXEC
+	i915_gem_dump_object(object_list[args->buffer_count - 1],
+			      args->batch_len,
+			      __func__,
+			      ~0);
+#endif
+
+	(void)i915_add_request(dev, flush_domains);
+
+	/* Exec the batchbuffer */
+	ret = i915_dispatch_gem_execbuffer(dev, args, exec_offset);
+	if (ret) {
+		DRM_ERROR("dispatch failed %d\n", ret);
+		goto err;
+	}
+
+	/*
+	 * Ensure that the commands in the batch buffer are
+	 * finished before the interrupt fires
+	 */
+	flush_domains = i915_retire_commands(dev);
+
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+
+	/*
+	 * Get a seqno representing the execution of the current buffer,
+	 * which we can wait on.  We would like to mitigate these interrupts,
+	 * likely by only creating seqnos occasionally (so that we have
+	 * *some* interrupts representing completion of buffers that we can
+	 * wait on when trying to clear up gtt space).
+	 */
+	seqno = i915_add_request(dev, flush_domains);
+	BUG_ON(seqno == 0);
+	i915_file_priv->mm.last_gem_seqno = seqno;
+	for (i = 0; i < args->buffer_count; i++) {
+		struct drm_gem_object *obj = object_list[i];
+		struct drm_i915_gem_object *obj_priv = obj->driver_private;
+
+		i915_gem_object_move_to_active(obj);
+		obj_priv->last_rendering_seqno = seqno;
+#if WATCH_LRU
+		DRM_INFO("%s: move to exec list %p\n", __func__, obj);
+#endif
+	}
+#if WATCH_LRU
+	i915_dump_lru(dev, __func__);
+#endif
+
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+
+	/* Copy the new buffer offsets back to the user's exec list. */
+	ret = copy_to_user((struct drm_i915_relocation_entry __user *)
+			   (uintptr_t) args->buffers_ptr,
+			   exec_list,
+			   sizeof(*exec_list) * args->buffer_count);
+	if (ret)
+		DRM_ERROR("failed to copy %d exec entries "
+			  "back to user (%d)\n",
+			   args->buffer_count, ret);
+err:
+	if (object_list != NULL) {
+		for (i = 0; i < pinned; i++)
+			i915_gem_object_unpin(object_list[i]);
+
+		for (i = 0; i < args->buffer_count; i++)
+			drm_gem_object_unreference(object_list[i]);
+	}
+	mutex_unlock(&dev->struct_mutex);
+
+pre_mutex_err:
+	drm_free(object_list, sizeof(*object_list) * args->buffer_count,
+		 DRM_MEM_DRIVER);
+	drm_free(exec_list, sizeof(*exec_list) * args->buffer_count,
+		 DRM_MEM_DRIVER);
+
+	return ret;
+}
+
+int
+i915_gem_object_pin(struct drm_gem_object *obj, uint32_t alignment)
+{
+	struct drm_device *dev = obj->dev;
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	int ret;
+
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+	if (obj_priv->gtt_space == NULL) {
+		ret = i915_gem_object_bind_to_gtt(obj, alignment);
+		if (ret != 0) {
+			DRM_ERROR("Failure to bind: %d", ret);
+			return ret;
+		}
+	}
+	obj_priv->pin_count++;
+
+	/* If the object is not active and not pending a flush,
+	 * remove it from the inactive list
+	 */
+	if (obj_priv->pin_count == 1) {
+		atomic_inc(&dev->pin_count);
+		atomic_add(obj->size, &dev->pin_memory);
+		if (!obj_priv->active &&
+		    (obj->write_domain & ~(I915_GEM_DOMAIN_CPU |
+					   I915_GEM_DOMAIN_GTT)) == 0 &&
+		    !list_empty(&obj_priv->list))
+			list_del_init(&obj_priv->list);
+	}
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+
+	return 0;
+}
+
+void
+i915_gem_object_unpin(struct drm_gem_object *obj)
+{
+	struct drm_device *dev = obj->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+	obj_priv->pin_count--;
+	BUG_ON(obj_priv->pin_count < 0);
+	BUG_ON(obj_priv->gtt_space == NULL);
+
+	/* If the object is no longer pinned, and is
+	 * neither active nor being flushed, then stick it on
+	 * the inactive list
+	 */
+	if (obj_priv->pin_count == 0) {
+		if (!obj_priv->active &&
+		    (obj->write_domain & ~(I915_GEM_DOMAIN_CPU |
+					   I915_GEM_DOMAIN_GTT)) == 0)
+			list_move_tail(&obj_priv->list,
+				       &dev_priv->mm.inactive_list);
+		atomic_dec(&dev->pin_count);
+		atomic_sub(obj->size, &dev->pin_memory);
+	}
+	i915_verify_inactive(dev, __FILE__, __LINE__);
+}
+
+int
+i915_gem_pin_ioctl(struct drm_device *dev, void *data,
+		   struct drm_file *file_priv)
+{
+	struct drm_i915_gem_pin *args = data;
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+	int ret;
+
+	mutex_lock(&dev->struct_mutex);
+
+	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
+	if (obj == NULL) {
+		DRM_ERROR("Bad handle in i915_gem_pin_ioctl(): %d\n",
+			  args->handle);
+		mutex_unlock(&dev->struct_mutex);
+		return -EBADF;
+	}
+	obj_priv = obj->driver_private;
+
+	ret = i915_gem_object_pin(obj, args->alignment);
+	if (ret != 0) {
+		drm_gem_object_unreference(obj);
+		mutex_unlock(&dev->struct_mutex);
+		return ret;
+	}
+
+	/* XXX - flush the CPU caches for pinned objects
+	 * as the X server doesn't manage domains yet
+	 */
+	if (obj->write_domain & I915_GEM_DOMAIN_CPU) {
+		i915_gem_clflush_object(obj);
+		drm_agp_chipset_flush(dev);
+		obj->write_domain = 0;
+	}
+	args->offset = obj_priv->gtt_offset;
+	drm_gem_object_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
+int
+i915_gem_unpin_ioctl(struct drm_device *dev, void *data,
+		     struct drm_file *file_priv)
+{
+	struct drm_i915_gem_pin *args = data;
+	struct drm_gem_object *obj;
+
+	mutex_lock(&dev->struct_mutex);
+
+	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
+	if (obj == NULL) {
+		DRM_ERROR("Bad handle in i915_gem_unpin_ioctl(): %d\n",
+			  args->handle);
+		mutex_unlock(&dev->struct_mutex);
+		return -EBADF;
+	}
+
+	i915_gem_object_unpin(obj);
+
+	drm_gem_object_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
+	return 0;
+}
+
+int
+i915_gem_busy_ioctl(struct drm_device *dev, void *data,
+		    struct drm_file *file_priv)
+{
+	struct drm_i915_gem_busy *args = data;
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+
+	mutex_lock(&dev->struct_mutex);
+	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
+	if (obj == NULL) {
+		DRM_ERROR("Bad handle in i915_gem_busy_ioctl(): %d\n",
+			  args->handle);
+		mutex_unlock(&dev->struct_mutex);
+		return -EBADF;
+	}
+
+	obj_priv = obj->driver_private;
+	args->busy = obj_priv->active;
+
+	drm_gem_object_unreference(obj);
+	mutex_unlock(&dev->struct_mutex);
+	return 0;
+}
+
+int
+i915_gem_throttle_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv)
+{
+    return i915_gem_ring_throttle(dev, file_priv);
+}
+
+int i915_gem_init_object(struct drm_gem_object *obj)
+{
+	struct drm_i915_gem_object *obj_priv;
+
+	obj_priv = drm_calloc(1, sizeof(*obj_priv), DRM_MEM_DRIVER);
+	if (obj_priv == NULL)
+		return -ENOMEM;
+
+	/*
+	 * We've just allocated pages from the kernel,
+	 * so they've just been written by the CPU with
+	 * zeros. They'll need to be clflushed before we
+	 * use them with the GPU.
+	 */
+	obj->write_domain = I915_GEM_DOMAIN_CPU;
+	obj->read_domains = I915_GEM_DOMAIN_CPU;
+
+	obj->driver_private = obj_priv;
+	obj_priv->obj = obj;
+	INIT_LIST_HEAD(&obj_priv->list);
+	return 0;
+}
+
+void i915_gem_free_object(struct drm_gem_object *obj)
+{
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+
+	while (obj_priv->pin_count > 0)
+		i915_gem_object_unpin(obj);
+
+	i915_gem_object_unbind(obj);
+
+	drm_free(obj_priv->page_cpu_valid, 1, DRM_MEM_DRIVER);
+	drm_free(obj->driver_private, 1, DRM_MEM_DRIVER);
+}
+
+static int
+i915_gem_set_domain(struct drm_gem_object *obj,
+		    struct drm_file *file_priv,
+		    uint32_t read_domains,
+		    uint32_t write_domain)
+{
+	struct drm_device *dev = obj->dev;
+	int ret;
+	uint32_t flush_domains;
+
+	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
+
+	ret = i915_gem_object_set_domain(obj, read_domains, write_domain);
+	if (ret)
+		return ret;
+	flush_domains = i915_gem_dev_set_domain(obj->dev);
+
+	if (flush_domains & ~(I915_GEM_DOMAIN_CPU|I915_GEM_DOMAIN_GTT))
+		(void) i915_add_request(dev, flush_domains);
+
+	return 0;
+}
+
+/** Unbinds all objects that are on the given buffer list. */
+static int
+i915_gem_evict_from_list(struct drm_device *dev, struct list_head *head)
+{
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+	int ret;
+
+	while (!list_empty(head)) {
+		obj_priv = list_first_entry(head,
+					    struct drm_i915_gem_object,
+					    list);
+		obj = obj_priv->obj;
+
+		if (obj_priv->pin_count != 0) {
+			DRM_ERROR("Pinned object in unbind list\n");
+			mutex_unlock(&dev->struct_mutex);
+			return -EINVAL;
+		}
+
+		ret = i915_gem_object_unbind(obj);
+		if (ret != 0) {
+			DRM_ERROR("Error unbinding object in LeaveVT: %d\n",
+				  ret);
+			mutex_unlock(&dev->struct_mutex);
+			return ret;
+		}
+	}
+
+
+	return 0;
+}
+
+static int
+i915_gem_idle(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	uint32_t seqno, cur_seqno, last_seqno;
+	int stuck, ret;
+
+	if (dev_priv->mm.suspended)
+		return 0;
+
+	/* Hack!  Don't let anybody do execbuf while we don't control the chip.
+	 * We need to replace this with a semaphore, or something.
+	 */
+	dev_priv->mm.suspended = 1;
+
+	i915_kernel_lost_context(dev);
+
+	/* Flush the GPU along with all non-CPU write domains
+	 */
+	i915_gem_flush(dev, ~(I915_GEM_DOMAIN_CPU|I915_GEM_DOMAIN_GTT),
+		       ~(I915_GEM_DOMAIN_CPU|I915_GEM_DOMAIN_GTT));
+	seqno = i915_add_request(dev, ~(I915_GEM_DOMAIN_CPU |
+					I915_GEM_DOMAIN_GTT));
+
+	if (seqno == 0) {
+		mutex_unlock(&dev->struct_mutex);
+		return -ENOMEM;
+	}
+
+	dev_priv->mm.waiting_gem_seqno = seqno;
+	last_seqno = 0;
+	stuck = 0;
+	for (;;) {
+		cur_seqno = i915_get_gem_seqno(dev);
+		if (i915_seqno_passed(cur_seqno, seqno))
+			break;
+		if (last_seqno == cur_seqno) {
+			if (stuck++ > 100) {
+				DRM_ERROR("hardware wedged\n");
+				dev_priv->mm.wedged = 1;
+				DRM_WAKEUP(&dev_priv->irq_queue);
+				break;
+			}
+		}
+		msleep(10);
+		last_seqno = cur_seqno;
+	}
+	dev_priv->mm.waiting_gem_seqno = 0;
+
+	i915_gem_retire_requests(dev);
+
+	/* Active and flushing should now be empty as we've
+	 * waited for a sequence higher than any pending execbuffer
+	 */
+	BUG_ON(!list_empty(&dev_priv->mm.active_list));
+	BUG_ON(!list_empty(&dev_priv->mm.flushing_list));
+
+	/* Request should now be empty as we've also waited
+	 * for the last request in the list
+	 */
+	BUG_ON(!list_empty(&dev_priv->mm.request_list));
+
+	/* Move all buffers out of the GTT. */
+	ret = i915_gem_evict_from_list(dev, &dev_priv->mm.inactive_list);
+	if (ret)
+		return ret;
+
+	BUG_ON(!list_empty(&dev_priv->mm.active_list));
+	BUG_ON(!list_empty(&dev_priv->mm.flushing_list));
+	BUG_ON(!list_empty(&dev_priv->mm.inactive_list));
+	BUG_ON(!list_empty(&dev_priv->mm.request_list));
+	return 0;
+}
+
+static int
+i915_gem_init_hws(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+	int ret;
+
+	/* If we need a physical address for the status page, it's already
+	 * initialized at driver load time.
+	 */
+	if (!I915_NEED_GFX_HWS(dev))
+		return 0;
+
+	obj = drm_gem_object_alloc(dev, 4096);
+	if (obj == NULL) {
+		DRM_ERROR("Failed to allocate status page\n");
+		return -ENOMEM;
+	}
+	obj_priv = obj->driver_private;
+
+	ret = i915_gem_object_pin(obj, 4096);
+	if (ret != 0) {
+		drm_gem_object_unreference(obj);
+		return ret;
+	}
+
+	dev_priv->status_gfx_addr = obj_priv->gtt_offset;
+	dev_priv->hws_map.offset = dev->agp->base + obj_priv->gtt_offset;
+	dev_priv->hws_map.size = 4096;
+	dev_priv->hws_map.type = 0;
+	dev_priv->hws_map.flags = 0;
+	dev_priv->hws_map.mtrr = 0;
+
+	drm_core_ioremap(&dev_priv->hws_map, dev);
+	if (dev_priv->hws_map.handle == NULL) {
+		DRM_ERROR("Failed to map status page.\n");
+		memset(&dev_priv->hws_map, 0, sizeof(dev_priv->hws_map));
+		drm_gem_object_unreference(obj);
+		return -EINVAL;
+	}
+	dev_priv->hws_obj = obj;
+	dev_priv->hw_status_page = dev_priv->hws_map.handle;
+	memset(dev_priv->hw_status_page, 0, PAGE_SIZE);
+	I915_WRITE(HWS_PGA, dev_priv->status_gfx_addr);
+	DRM_DEBUG("hws offset: 0x%08x\n", dev_priv->status_gfx_addr);
+
+	return 0;
+}
+
+static int
+i915_gem_init_ringbuffer(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+	int ret;
+
+	ret = i915_gem_init_hws(dev);
+	if (ret != 0)
+		return ret;
+
+	obj = drm_gem_object_alloc(dev, 128 * 1024);
+	if (obj == NULL) {
+		DRM_ERROR("Failed to allocate ringbuffer\n");
+		return -ENOMEM;
+	}
+	obj_priv = obj->driver_private;
+
+	ret = i915_gem_object_pin(obj, 4096);
+	if (ret != 0) {
+		drm_gem_object_unreference(obj);
+		return ret;
+	}
+
+	/* Set up the kernel mapping for the ring. */
+	dev_priv->ring.Size = obj->size;
+	dev_priv->ring.tail_mask = obj->size - 1;
+
+	dev_priv->ring.map.offset = dev->agp->base + obj_priv->gtt_offset;
+	dev_priv->ring.map.size = obj->size;
+	dev_priv->ring.map.type = 0;
+	dev_priv->ring.map.flags = 0;
+	dev_priv->ring.map.mtrr = 0;
+
+	drm_core_ioremap(&dev_priv->ring.map, dev);
+	if (dev_priv->ring.map.handle == NULL) {
+		DRM_ERROR("Failed to map ringbuffer.\n");
+		memset(&dev_priv->ring, 0, sizeof(dev_priv->ring));
+		drm_gem_object_unreference(obj);
+		return -EINVAL;
+	}
+	dev_priv->ring.ring_obj = obj;
+	dev_priv->ring.virtual_start = dev_priv->ring.map.handle;
+
+	/* Stop the ring if it's running. */
+	I915_WRITE(PRB0_CTL, 0);
+	I915_WRITE(PRB0_HEAD, 0);
+	I915_WRITE(PRB0_TAIL, 0);
+	I915_WRITE(PRB0_START, 0);
+
+	/* Initialize the ring. */
+	I915_WRITE(PRB0_START, obj_priv->gtt_offset);
+	I915_WRITE(PRB0_CTL,
+		   ((obj->size - 4096) & RING_NR_PAGES) |
+		   RING_NO_REPORT |
+		   RING_VALID);
+
+	/* Update our cache of the ring state */
+	i915_kernel_lost_context(dev);
+
+	return 0;
+}
+
+static void
+i915_gem_cleanup_ringbuffer(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+
+	if (dev_priv->ring.ring_obj == NULL)
+		return;
+
+	drm_core_ioremapfree(&dev_priv->ring.map, dev);
+
+	i915_gem_object_unpin(dev_priv->ring.ring_obj);
+	drm_gem_object_unreference(dev_priv->ring.ring_obj);
+	dev_priv->ring.ring_obj = NULL;
+	memset(&dev_priv->ring, 0, sizeof(dev_priv->ring));
+
+	if (dev_priv->hws_obj != NULL) {
+		i915_gem_object_unpin(dev_priv->hws_obj);
+		drm_gem_object_unreference(dev_priv->hws_obj);
+		dev_priv->hws_obj = NULL;
+		memset(&dev_priv->hws_map, 0, sizeof(dev_priv->hws_map));
+
+		/* Write high address into HWS_PGA when disabling. */
+		I915_WRITE(HWS_PGA, 0x1ffff000);
+	}
+}
+
+int
+i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	int ret;
+
+	if (dev_priv->mm.wedged) {
+		DRM_ERROR("Reenabling wedged hardware, good luck\n");
+		dev_priv->mm.wedged = 0;
+	}
+
+	ret = i915_gem_init_ringbuffer(dev);
+	if (ret != 0)
+		return ret;
+
+	mutex_lock(&dev->struct_mutex);
+	BUG_ON(!list_empty(&dev_priv->mm.active_list));
+	BUG_ON(!list_empty(&dev_priv->mm.flushing_list));
+	BUG_ON(!list_empty(&dev_priv->mm.inactive_list));
+	BUG_ON(!list_empty(&dev_priv->mm.request_list));
+	dev_priv->mm.suspended = 0;
+	mutex_unlock(&dev->struct_mutex);
+	return 0;
+}
+
+int
+i915_gem_leavevt_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
+{
+	int ret;
+
+	mutex_lock(&dev->struct_mutex);
+	ret = i915_gem_idle(dev);
+	if (ret == 0)
+		i915_gem_cleanup_ringbuffer(dev);
+	mutex_unlock(&dev->struct_mutex);
+
+	return 0;
+}
+
+void
+i915_gem_lastclose(struct drm_device *dev)
+{
+	int ret;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+
+	mutex_lock(&dev->struct_mutex);
+
+	if (dev_priv->ring.ring_obj != NULL) {
+		ret = i915_gem_idle(dev);
+		if (ret)
+			DRM_ERROR("failed to idle hardware: %d\n", ret);
+
+		i915_gem_cleanup_ringbuffer(dev);
+	}
+
+	mutex_unlock(&dev->struct_mutex);
+}
+
+void
+i915_gem_load(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+
+	INIT_LIST_HEAD(&dev_priv->mm.active_list);
+	INIT_LIST_HEAD(&dev_priv->mm.flushing_list);
+	INIT_LIST_HEAD(&dev_priv->mm.inactive_list);
+	INIT_LIST_HEAD(&dev_priv->mm.request_list);
+	INIT_DELAYED_WORK(&dev_priv->mm.retire_work,
+			  i915_gem_retire_work_handler);
+	dev_priv->mm.next_gem_seqno = 1;
+
+	i915_gem_detect_bit_6_swizzle(dev);
+}
diff --git a/drivers/gpu/drm/i915/i915_gem_debug.c b/drivers/gpu/drm/i915/i915_gem_debug.c
new file mode 100644
index 000000000000..131c088f8c8a
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_debug.c
@@ -0,0 +1,201 @@
+/*
+ * Copyright © 2008 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ *    Keith Packard <keithp@keithp.com>
+ *
+ */
+
+#include "drmP.h"
+#include "drm.h"
+#include "i915_drm.h"
+#include "i915_drv.h"
+
+#if WATCH_INACTIVE
+void
+i915_verify_inactive(struct drm_device *dev, char *file, int line)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+
+	list_for_each_entry(obj_priv, &dev_priv->mm.inactive_list, list) {
+		obj = obj_priv->obj;
+		if (obj_priv->pin_count || obj_priv->active ||
+		    (obj->write_domain & ~(I915_GEM_DOMAIN_CPU |
+					   I915_GEM_DOMAIN_GTT)))
+			DRM_ERROR("inactive %p (p %d a %d w %x)  %s:%d\n",
+				  obj,
+				  obj_priv->pin_count, obj_priv->active,
+				  obj->write_domain, file, line);
+	}
+}
+#endif /* WATCH_INACTIVE */
+
+
+#if WATCH_BUF | WATCH_EXEC | WATCH_PWRITE
+static void
+i915_gem_dump_page(struct page *page, uint32_t start, uint32_t end,
+		   uint32_t bias, uint32_t mark)
+{
+	uint32_t *mem = kmap_atomic(page, KM_USER0);
+	int i;
+	for (i = start; i < end; i += 4)
+		DRM_INFO("%08x: %08x%s\n",
+			  (int) (bias + i), mem[i / 4],
+			  (bias + i == mark) ? " ********" : "");
+	kunmap_atomic(mem, KM_USER0);
+	/* give syslog time to catch up */
+	msleep(1);
+}
+
+void
+i915_gem_dump_object(struct drm_gem_object *obj, int len,
+		     const char *where, uint32_t mark)
+{
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	int page;
+
+	DRM_INFO("%s: object at offset %08x\n", where, obj_priv->gtt_offset);
+	for (page = 0; page < (len + PAGE_SIZE-1) / PAGE_SIZE; page++) {
+		int page_len, chunk, chunk_len;
+
+		page_len = len - page * PAGE_SIZE;
+		if (page_len > PAGE_SIZE)
+			page_len = PAGE_SIZE;
+
+		for (chunk = 0; chunk < page_len; chunk += 128) {
+			chunk_len = page_len - chunk;
+			if (chunk_len > 128)
+				chunk_len = 128;
+			i915_gem_dump_page(obj_priv->page_list[page],
+					   chunk, chunk + chunk_len,
+					   obj_priv->gtt_offset +
+					   page * PAGE_SIZE,
+					   mark);
+		}
+	}
+}
+#endif
+
+#if WATCH_LRU
+void
+i915_dump_lru(struct drm_device *dev, const char *where)
+{
+	drm_i915_private_t		*dev_priv = dev->dev_private;
+	struct drm_i915_gem_object	*obj_priv;
+
+	DRM_INFO("active list %s {\n", where);
+	list_for_each_entry(obj_priv, &dev_priv->mm.active_list,
+			    list)
+	{
+		DRM_INFO("    %p: %08x\n", obj_priv,
+			 obj_priv->last_rendering_seqno);
+	}
+	DRM_INFO("}\n");
+	DRM_INFO("flushing list %s {\n", where);
+	list_for_each_entry(obj_priv, &dev_priv->mm.flushing_list,
+			    list)
+	{
+		DRM_INFO("    %p: %08x\n", obj_priv,
+			 obj_priv->last_rendering_seqno);
+	}
+	DRM_INFO("}\n");
+	DRM_INFO("inactive %s {\n", where);
+	list_for_each_entry(obj_priv, &dev_priv->mm.inactive_list, list) {
+		DRM_INFO("    %p: %08x\n", obj_priv,
+			 obj_priv->last_rendering_seqno);
+	}
+	DRM_INFO("}\n");
+}
+#endif
+
+
+#if WATCH_COHERENCY
+void
+i915_gem_object_check_coherency(struct drm_gem_object *obj, int handle)
+{
+	struct drm_device *dev = obj->dev;
+	struct drm_i915_gem_object *obj_priv = obj->driver_private;
+	int page;
+	uint32_t *gtt_mapping;
+	uint32_t *backing_map = NULL;
+	int bad_count = 0;
+
+	DRM_INFO("%s: checking coherency of object %p@0x%08x (%d, %dkb):\n",
+		 __func__, obj, obj_priv->gtt_offset, handle,
+		 obj->size / 1024);
+
+	gtt_mapping = ioremap(dev->agp->base + obj_priv->gtt_offset,
+			      obj->size);
+	if (gtt_mapping == NULL) {
+		DRM_ERROR("failed to map GTT space\n");
+		return;
+	}
+
+	for (page = 0; page < obj->size / PAGE_SIZE; page++) {
+		int i;
+
+		backing_map = kmap_atomic(obj_priv->page_list[page], KM_USER0);
+
+		if (backing_map == NULL) {
+			DRM_ERROR("failed to map backing page\n");
+			goto out;
+		}
+
+		for (i = 0; i < PAGE_SIZE / 4; i++) {
+			uint32_t cpuval = backing_map[i];
+			uint32_t gttval = readl(gtt_mapping +
+						page * 1024 + i);
+
+			if (cpuval != gttval) {
+				DRM_INFO("incoherent CPU vs GPU at 0x%08x: "
+					 "0x%08x vs 0x%08x\n",
+					 (int)(obj_priv->gtt_offset +
+					       page * PAGE_SIZE + i * 4),
+					 cpuval, gttval);
+				if (bad_count++ >= 8) {
+					DRM_INFO("...\n");
+					goto out;
+				}
+			}
+		}
+		kunmap_atomic(backing_map, KM_USER0);
+		backing_map = NULL;
+	}
+
+ out:
+	if (backing_map != NULL)
+		kunmap_atomic(backing_map, KM_USER0);
+	iounmap(gtt_mapping);
+
+	/* give syslog time to catch up */
+	msleep(1);
+
+	/* Directly flush the object, since we just loaded values with the CPU
+	 * from the backing pages and we don't want to disturb the cache
+	 * management that we're trying to observe.
+	 */
+
+	i915_gem_clflush_object(obj);
+}
+#endif
diff --git a/drivers/gpu/drm/i915/i915_gem_proc.c b/drivers/gpu/drm/i915/i915_gem_proc.c
new file mode 100644
index 000000000000..15d4160415b0
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_proc.c
@@ -0,0 +1,292 @@
+/*
+ * Copyright © 2008 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ *    Eric Anholt <eric@anholt.net>
+ *    Keith Packard <keithp@keithp.com>
+ *
+ */
+
+#include "drmP.h"
+#include "drm.h"
+#include "i915_drm.h"
+#include "i915_drv.h"
+
+static int i915_gem_active_info(char *buf, char **start, off_t offset,
+				int request, int *eof, void *data)
+{
+	struct drm_minor *minor = (struct drm_minor *) data;
+	struct drm_device *dev = minor->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *obj_priv;
+	int len = 0;
+
+	if (offset > DRM_PROC_LIMIT) {
+		*eof = 1;
+		return 0;
+	}
+
+	*start = &buf[offset];
+	*eof = 0;
+	DRM_PROC_PRINT("Active:\n");
+	list_for_each_entry(obj_priv, &dev_priv->mm.active_list,
+			    list)
+	{
+		struct drm_gem_object *obj = obj_priv->obj;
+		if (obj->name) {
+			DRM_PROC_PRINT("    %p(%d): %08x %08x %d\n",
+				       obj, obj->name,
+				       obj->read_domains, obj->write_domain,
+				       obj_priv->last_rendering_seqno);
+		} else {
+			DRM_PROC_PRINT("       %p: %08x %08x %d\n",
+				       obj,
+				       obj->read_domains, obj->write_domain,
+				       obj_priv->last_rendering_seqno);
+		}
+	}
+	if (len > request + offset)
+		return request;
+	*eof = 1;
+	return len - offset;
+}
+
+static int i915_gem_flushing_info(char *buf, char **start, off_t offset,
+				  int request, int *eof, void *data)
+{
+	struct drm_minor *minor = (struct drm_minor *) data;
+	struct drm_device *dev = minor->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *obj_priv;
+	int len = 0;
+
+	if (offset > DRM_PROC_LIMIT) {
+		*eof = 1;
+		return 0;
+	}
+
+	*start = &buf[offset];
+	*eof = 0;
+	DRM_PROC_PRINT("Flushing:\n");
+	list_for_each_entry(obj_priv, &dev_priv->mm.flushing_list,
+			    list)
+	{
+		struct drm_gem_object *obj = obj_priv->obj;
+		if (obj->name) {
+			DRM_PROC_PRINT("    %p(%d): %08x %08x %d\n",
+				       obj, obj->name,
+				       obj->read_domains, obj->write_domain,
+				       obj_priv->last_rendering_seqno);
+		} else {
+			DRM_PROC_PRINT("       %p: %08x %08x %d\n", obj,
+				       obj->read_domains, obj->write_domain,
+				       obj_priv->last_rendering_seqno);
+		}
+	}
+	if (len > request + offset)
+		return request;
+	*eof = 1;
+	return len - offset;
+}
+
+static int i915_gem_inactive_info(char *buf, char **start, off_t offset,
+				  int request, int *eof, void *data)
+{
+	struct drm_minor *minor = (struct drm_minor *) data;
+	struct drm_device *dev = minor->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *obj_priv;
+	int len = 0;
+
+	if (offset > DRM_PROC_LIMIT) {
+		*eof = 1;
+		return 0;
+	}
+
+	*start = &buf[offset];
+	*eof = 0;
+	DRM_PROC_PRINT("Inactive:\n");
+	list_for_each_entry(obj_priv, &dev_priv->mm.inactive_list,
+			    list)
+	{
+		struct drm_gem_object *obj = obj_priv->obj;
+		if (obj->name) {
+			DRM_PROC_PRINT("    %p(%d): %08x %08x %d\n",
+				       obj, obj->name,
+				       obj->read_domains, obj->write_domain,
+				       obj_priv->last_rendering_seqno);
+		} else {
+			DRM_PROC_PRINT("       %p: %08x %08x %d\n", obj,
+				       obj->read_domains, obj->write_domain,
+				       obj_priv->last_rendering_seqno);
+		}
+	}
+	if (len > request + offset)
+		return request;
+	*eof = 1;
+	return len - offset;
+}
+
+static int i915_gem_request_info(char *buf, char **start, off_t offset,
+				 int request, int *eof, void *data)
+{
+	struct drm_minor *minor = (struct drm_minor *) data;
+	struct drm_device *dev = minor->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_i915_gem_request *gem_request;
+	int len = 0;
+
+	if (offset > DRM_PROC_LIMIT) {
+		*eof = 1;
+		return 0;
+	}
+
+	*start = &buf[offset];
+	*eof = 0;
+	DRM_PROC_PRINT("Request:\n");
+	list_for_each_entry(gem_request, &dev_priv->mm.request_list,
+			    list)
+	{
+		DRM_PROC_PRINT("    %d @ %d %08x\n",
+			       gem_request->seqno,
+			       (int) (jiffies - gem_request->emitted_jiffies),
+			       gem_request->flush_domains);
+	}
+	if (len > request + offset)
+		return request;
+	*eof = 1;
+	return len - offset;
+}
+
+static int i915_gem_seqno_info(char *buf, char **start, off_t offset,
+			       int request, int *eof, void *data)
+{
+	struct drm_minor *minor = (struct drm_minor *) data;
+	struct drm_device *dev = minor->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	int len = 0;
+
+	if (offset > DRM_PROC_LIMIT) {
+		*eof = 1;
+		return 0;
+	}
+
+	*start = &buf[offset];
+	*eof = 0;
+	DRM_PROC_PRINT("Current sequence: %d\n", i915_get_gem_seqno(dev));
+	DRM_PROC_PRINT("Waiter sequence:  %d\n",
+		       dev_priv->mm.waiting_gem_seqno);
+	DRM_PROC_PRINT("IRQ sequence:     %d\n", dev_priv->mm.irq_gem_seqno);
+	if (len > request + offset)
+		return request;
+	*eof = 1;
+	return len - offset;
+}
+
+
+static int i915_interrupt_info(char *buf, char **start, off_t offset,
+			       int request, int *eof, void *data)
+{
+	struct drm_minor *minor = (struct drm_minor *) data;
+	struct drm_device *dev = minor->dev;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	int len = 0;
+
+	if (offset > DRM_PROC_LIMIT) {
+		*eof = 1;
+		return 0;
+	}
+
+	*start = &buf[offset];
+	*eof = 0;
+	DRM_PROC_PRINT("Interrupt enable:    %08x\n",
+		       I915_READ(IER));
+	DRM_PROC_PRINT("Interrupt identity:  %08x\n",
+		       I915_READ(IIR));
+	DRM_PROC_PRINT("Interrupt mask:      %08x\n",
+		       I915_READ(IMR));
+	DRM_PROC_PRINT("Pipe A stat:         %08x\n",
+		       I915_READ(PIPEASTAT));
+	DRM_PROC_PRINT("Pipe B stat:         %08x\n",
+		       I915_READ(PIPEBSTAT));
+	DRM_PROC_PRINT("Interrupts received: %d\n",
+		       atomic_read(&dev_priv->irq_received));
+	DRM_PROC_PRINT("Current sequence:    %d\n",
+		       i915_get_gem_seqno(dev));
+	DRM_PROC_PRINT("Waiter sequence:     %d\n",
+		       dev_priv->mm.waiting_gem_seqno);
+	DRM_PROC_PRINT("IRQ sequence:        %d\n",
+		       dev_priv->mm.irq_gem_seqno);
+	if (len > request + offset)
+		return request;
+	*eof = 1;
+	return len - offset;
+}
+
+static struct drm_proc_list {
+	/** file name */
+	const char *name;
+	/** proc callback*/
+	int (*f) (char *, char **, off_t, int, int *, void *);
+} i915_gem_proc_list[] = {
+	{"i915_gem_active", i915_gem_active_info},
+	{"i915_gem_flushing", i915_gem_flushing_info},
+	{"i915_gem_inactive", i915_gem_inactive_info},
+	{"i915_gem_request", i915_gem_request_info},
+	{"i915_gem_seqno", i915_gem_seqno_info},
+	{"i915_gem_interrupt", i915_interrupt_info},
+};
+
+#define I915_GEM_PROC_ENTRIES ARRAY_SIZE(i915_gem_proc_list)
+
+int i915_gem_proc_init(struct drm_minor *minor)
+{
+	struct proc_dir_entry *ent;
+	int i, j;
+
+	for (i = 0; i < I915_GEM_PROC_ENTRIES; i++) {
+		ent = create_proc_entry(i915_gem_proc_list[i].name,
+					S_IFREG | S_IRUGO, minor->dev_root);
+		if (!ent) {
+			DRM_ERROR("Cannot create /proc/dri/.../%s\n",
+				  i915_gem_proc_list[i].name);
+			for (j = 0; j < i; j++)
+				remove_proc_entry(i915_gem_proc_list[i].name,
+						  minor->dev_root);
+			return -1;
+		}
+		ent->read_proc = i915_gem_proc_list[i].f;
+		ent->data = minor;
+	}
+	return 0;
+}
+
+void i915_gem_proc_cleanup(struct drm_minor *minor)
+{
+	int i;
+
+	if (!minor->dev_root)
+		return;
+
+	for (i = 0; i < I915_GEM_PROC_ENTRIES; i++)
+		remove_proc_entry(i915_gem_proc_list[i].name, minor->dev_root);
+}
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
new file mode 100644
index 000000000000..0c1b3a0834e1
--- /dev/null
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -0,0 +1,256 @@
+/*
+ * Copyright © 2008 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ *
+ * Authors:
+ *    Eric Anholt <eric@anholt.net>
+ *
+ */
+
+#include "drmP.h"
+#include "drm.h"
+#include "i915_drm.h"
+#include "i915_drv.h"
+
+/** @file i915_gem_tiling.c
+ *
+ * Support for managing tiling state of buffer objects.
+ *
+ * The idea behind tiling is to increase cache hit rates by rearranging
+ * pixel data so that a group of pixel accesses are in the same cacheline.
+ * Performance improvement from doing this on the back/depth buffer are on
+ * the order of 30%.
+ *
+ * Intel architectures make this somewhat more complicated, though, by
+ * adjustments made to addressing of data when the memory is in interleaved
+ * mode (matched pairs of DIMMS) to improve memory bandwidth.
+ * For interleaved memory, the CPU sends every sequential 64 bytes
+ * to an alternate memory channel so it can get the bandwidth from both.
+ *
+ * The GPU also rearranges its accesses for increased bandwidth to interleaved
+ * memory, and it matches what the CPU does for non-tiled.  However, when tiled
+ * it does it a little differently, since one walks addresses not just in the
+ * X direction but also Y.  So, along with alternating channels when bit
+ * 6 of the address flips, it also alternates when other bits flip --  Bits 9
+ * (every 512 bytes, an X tile scanline) and 10 (every two X tile scanlines)
+ * are common to both the 915 and 965-class hardware.
+ *
+ * The CPU also sometimes XORs in higher bits as well, to improve
+ * bandwidth doing strided access like we do so frequently in graphics.  This
+ * is called "Channel XOR Randomization" in the MCH documentation.  The result
+ * is that the CPU is XORing in either bit 11 or bit 17 to bit 6 of its address
+ * decode.
+ *
+ * All of this bit 6 XORing has an effect on our memory management,
+ * as we need to make sure that the 3d driver can correctly address object
+ * contents.
+ *
+ * If we don't have interleaved memory, all tiling is safe and no swizzling is
+ * required.
+ *
+ * When bit 17 is XORed in, we simply refuse to tile at all.  Bit
+ * 17 is not just a page offset, so as we page an objet out and back in,
+ * individual pages in it will have different bit 17 addresses, resulting in
+ * each 64 bytes being swapped with its neighbor!
+ *
+ * Otherwise, if interleaved, we have to tell the 3d driver what the address
+ * swizzling it needs to do is, since it's writing with the CPU to the pages
+ * (bit 6 and potentially bit 11 XORed in), and the GPU is reading from the
+ * pages (bit 6, 9, and 10 XORed in), resulting in a cumulative bit swizzling
+ * required by the CPU of XORing in bit 6, 9, 10, and potentially 11, in order
+ * to match what the GPU expects.
+ */
+
+/**
+ * Detects bit 6 swizzling of address lookup between IGD access and CPU
+ * access through main memory.
+ */
+void
+i915_gem_detect_bit_6_swizzle(struct drm_device *dev)
+{
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	uint32_t swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
+	uint32_t swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
+
+	if (!IS_I9XX(dev)) {
+		/* As far as we know, the 865 doesn't have these bit 6
+		 * swizzling issues.
+		 */
+		swizzle_x = I915_BIT_6_SWIZZLE_NONE;
+		swizzle_y = I915_BIT_6_SWIZZLE_NONE;
+	} else if (!IS_I965G(dev) || IS_I965GM(dev)) {
+		uint32_t dcc;
+
+		/* On 915-945 and GM965, channel interleave by the CPU is
+		 * determined by DCC.  The CPU will alternate based on bit 6
+		 * in interleaved mode, and the GPU will then also alternate
+		 * on bit 6, 9, and 10 for X, but the CPU may also optionally
+		 * alternate based on bit 17 (XOR not disabled and XOR
+		 * bit == 17).
+		 */
+		dcc = I915_READ(DCC);
+		switch (dcc & DCC_ADDRESSING_MODE_MASK) {
+		case DCC_ADDRESSING_MODE_SINGLE_CHANNEL:
+		case DCC_ADDRESSING_MODE_DUAL_CHANNEL_ASYMMETRIC:
+			swizzle_x = I915_BIT_6_SWIZZLE_NONE;
+			swizzle_y = I915_BIT_6_SWIZZLE_NONE;
+			break;
+		case DCC_ADDRESSING_MODE_DUAL_CHANNEL_INTERLEAVED:
+			if (IS_I915G(dev) || IS_I915GM(dev) ||
+			    dcc & DCC_CHANNEL_XOR_DISABLE) {
+				swizzle_x = I915_BIT_6_SWIZZLE_9_10;
+				swizzle_y = I915_BIT_6_SWIZZLE_9;
+			} else if (IS_I965GM(dev)) {
+				/* GM965 only does bit 11-based channel
+				 * randomization
+				 */
+				swizzle_x = I915_BIT_6_SWIZZLE_9_10_11;
+				swizzle_y = I915_BIT_6_SWIZZLE_9_11;
+			} else {
+				/* Bit 17 or perhaps other swizzling */
+				swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
+				swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
+			}
+			break;
+		}
+		if (dcc == 0xffffffff) {
+			DRM_ERROR("Couldn't read from MCHBAR.  "
+				  "Disabling tiling.\n");
+			swizzle_x = I915_BIT_6_SWIZZLE_UNKNOWN;
+			swizzle_y = I915_BIT_6_SWIZZLE_UNKNOWN;
+		}
+	} else {
+		/* The 965, G33, and newer, have a very flexible memory
+		 * configuration.  It will enable dual-channel mode
+		 * (interleaving) on as much memory as it can, and the GPU
+		 * will additionally sometimes enable different bit 6
+		 * swizzling for tiled objects from the CPU.
+		 *
+		 * Here's what I found on the G965:
+		 *    slot fill         memory size  swizzling
+		 * 0A   0B   1A   1B    1-ch   2-ch
+		 * 512  0    0    0     512    0     O
+		 * 512  0    512  0     16     1008  X
+		 * 512  0    0    512   16     1008  X
+		 * 0    512  0    512   16     1008  X
+		 * 1024 1024 1024 0     2048   1024  O
+		 *
+		 * We could probably detect this based on either the DRB
+		 * matching, which was the case for the swizzling required in
+		 * the table above, or from the 1-ch value being less than
+		 * the minimum size of a rank.
+		 */
+		if (I915_READ16(C0DRB3) != I915_READ16(C1DRB3)) {
+			swizzle_x = I915_BIT_6_SWIZZLE_NONE;
+			swizzle_y = I915_BIT_6_SWIZZLE_NONE;
+		} else {
+			swizzle_x = I915_BIT_6_SWIZZLE_9_10;
+			swizzle_y = I915_BIT_6_SWIZZLE_9;
+		}
+	}
+
+	dev_priv->mm.bit_6_swizzle_x = swizzle_x;
+	dev_priv->mm.bit_6_swizzle_y = swizzle_y;
+}
+
+/**
+ * Sets the tiling mode of an object, returning the required swizzling of
+ * bit 6 of addresses in the object.
+ */
+int
+i915_gem_set_tiling(struct drm_device *dev, void *data,
+		   struct drm_file *file_priv)
+{
+	struct drm_i915_gem_set_tiling *args = data;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+
+	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
+	if (obj == NULL)
+		return -EINVAL;
+	obj_priv = obj->driver_private;
+
+	mutex_lock(&dev->struct_mutex);
+
+	if (args->tiling_mode == I915_TILING_NONE) {
+		obj_priv->tiling_mode = I915_TILING_NONE;
+		args->swizzle_mode = I915_BIT_6_SWIZZLE_NONE;
+	} else {
+		if (args->tiling_mode == I915_TILING_X)
+			args->swizzle_mode = dev_priv->mm.bit_6_swizzle_x;
+		else
+			args->swizzle_mode = dev_priv->mm.bit_6_swizzle_y;
+		/* If we can't handle the swizzling, make it untiled. */
+		if (args->swizzle_mode == I915_BIT_6_SWIZZLE_UNKNOWN) {
+			args->tiling_mode = I915_TILING_NONE;
+			args->swizzle_mode = I915_BIT_6_SWIZZLE_NONE;
+		}
+	}
+	obj_priv->tiling_mode = args->tiling_mode;
+
+	mutex_unlock(&dev->struct_mutex);
+
+	drm_gem_object_unreference(obj);
+
+	return 0;
+}
+
+/**
+ * Returns the current tiling mode and required bit 6 swizzling for the object.
+ */
+int
+i915_gem_get_tiling(struct drm_device *dev, void *data,
+		   struct drm_file *file_priv)
+{
+	struct drm_i915_gem_get_tiling *args = data;
+	drm_i915_private_t *dev_priv = dev->dev_private;
+	struct drm_gem_object *obj;
+	struct drm_i915_gem_object *obj_priv;
+
+	obj = drm_gem_object_lookup(dev, file_priv, args->handle);
+	if (obj == NULL)
+		return -EINVAL;
+	obj_priv = obj->driver_private;
+
+	mutex_lock(&dev->struct_mutex);
+
+	args->tiling_mode = obj_priv->tiling_mode;
+	switch (obj_priv->tiling_mode) {
+	case I915_TILING_X:
+		args->swizzle_mode = dev_priv->mm.bit_6_swizzle_x;
+		break;
+	case I915_TILING_Y:
+		args->swizzle_mode = dev_priv->mm.bit_6_swizzle_y;
+		break;
+	case I915_TILING_NONE:
+		args->swizzle_mode = I915_BIT_6_SWIZZLE_NONE;
+		break;
+	default:
+		DRM_ERROR("unknown tiling mode\n");
+	}
+
+	mutex_unlock(&dev->struct_mutex);
+
+	drm_gem_object_unreference(obj);
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index f8759597233b..f295bdf16e2d 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -407,15 +407,20 @@ irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS)
 		I915_WRITE(PIPEBSTAT, pipeb_stats);
 	}
 
-	if (iir & I915_ASLE_INTERRUPT)
-		opregion_asle_intr(dev);
+	I915_WRITE(IIR, iir);
+	if (dev->pdev->msi_enabled)
+		I915_WRITE(IMR, dev_priv->irq_mask_reg);
+	(void) I915_READ(IIR); /* Flush posted writes */
 
 	dev_priv->sarea_priv->last_dispatch = READ_BREADCRUMB(dev_priv);
 
-	if (dev->pdev->msi_enabled)
-		I915_WRITE(IMR, dev_priv->irq_mask_reg);
-	I915_WRITE(IIR, iir);
-	(void) I915_READ(IIR);
+	if (iir & I915_USER_INTERRUPT) {
+		dev_priv->mm.irq_gem_seqno = i915_get_gem_seqno(dev);
+		DRM_WAKEUP(&dev_priv->irq_queue);
+	}
+
+	if (iir & I915_ASLE_INTERRUPT)
+		opregion_asle_intr(dev);
 
 	if (vblank && dev_priv->swaps_pending > 0)
 		drm_locked_tasklet(dev, i915_vblank_tasklet);
@@ -449,7 +454,7 @@ static int i915_emit_irq(struct drm_device * dev)
 	return dev_priv->counter;
 }
 
-static void i915_user_irq_get(struct drm_device *dev)
+void i915_user_irq_get(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 43ad2cb8b9f5..5c2d9f206d05 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -25,19 +25,6 @@
 #ifndef _I915_REG_H_
 #define _I915_REG_H_
 
-/* MCH MMIO space */
-/** 915-945 and GM965 MCH register controlling DRAM channel access */
-#define DCC		0x200
-#define DCC_ADDRESSING_MODE_SINGLE_CHANNEL		(0 << 0)
-#define DCC_ADDRESSING_MODE_DUAL_CHANNEL_ASYMMETRIC	(1 << 0)
-#define DCC_ADDRESSING_MODE_DUAL_CHANNEL_INTERLEAVED	(2 << 0)
-#define DCC_ADDRESSING_MODE_MASK			(3 << 0)
-#define DCC_CHANNEL_XOR_DISABLE				(1 << 10)
-
-/** 965 MCH register controlling DRAM channel configuration */
-#define CHDECMISC		0x111
-#define CHDECMISC_FLEXMEMORY		(1 << 1)
-
 /*
  * The Bridge device's PCI config space has information about the
  * fb aperture size and the amount of pre-reserved memory.
@@ -516,6 +503,30 @@
 #define PALETTE_A		0x0a000
 #define PALETTE_B		0x0a800
 
+/* MCH MMIO space */
+
+/*
+ * MCHBAR mirror.
+ *
+ * This mirrors the MCHBAR MMIO space whose location is determined by
+ * device 0 function 0's pci config register 0x44 or 0x48 and matches it in
+ * every way.  It is not accessible from the CP register read instructions.
+ *
+ */
+#define MCHBAR_MIRROR_BASE	0x10000
+
+/** 915-945 and GM965 MCH register controlling DRAM channel access */
+#define DCC			0x10200
+#define DCC_ADDRESSING_MODE_SINGLE_CHANNEL		(0 << 0)
+#define DCC_ADDRESSING_MODE_DUAL_CHANNEL_ASYMMETRIC	(1 << 0)
+#define DCC_ADDRESSING_MODE_DUAL_CHANNEL_INTERLEAVED	(2 << 0)
+#define DCC_ADDRESSING_MODE_MASK			(3 << 0)
+#define DCC_CHANNEL_XOR_DISABLE				(1 << 10)
+
+/** 965 MCH register controlling DRAM channel configuration */
+#define C0DRB3			0x10206
+#define C1DRB3			0x10606
+
 /*
  * Overlay regs
  */
diff --git a/include/drm/drm.h b/include/drm/drm.h
index 15e55039b7f1..f46ba4b57da4 100644
--- a/include/drm/drm.h
+++ b/include/drm/drm.h
@@ -570,6 +570,34 @@ struct drm_set_version {
 	int drm_dd_minor;
 };
 
+/** DRM_IOCTL_GEM_CLOSE ioctl argument type */
+struct drm_gem_close {
+	/** Handle of the object to be closed. */
+	uint32_t handle;
+	uint32_t pad;
+};
+
+/** DRM_IOCTL_GEM_FLINK ioctl argument type */
+struct drm_gem_flink {
+	/** Handle for the object being named */
+	uint32_t handle;
+
+	/** Returned global name */
+	uint32_t name;
+};
+
+/** DRM_IOCTL_GEM_OPEN ioctl argument type */
+struct drm_gem_open {
+	/** Name of object being opened */
+	uint32_t name;
+
+	/** Returned handle for the object */
+	uint32_t handle;
+
+	/** Returned size of the object */
+	uint64_t size;
+};
+
 #define DRM_IOCTL_BASE			'd'
 #define DRM_IO(nr)			_IO(DRM_IOCTL_BASE,nr)
 #define DRM_IOR(nr,type)		_IOR(DRM_IOCTL_BASE,nr,type)
@@ -585,6 +613,9 @@ struct drm_set_version {
 #define DRM_IOCTL_GET_STATS             DRM_IOR( 0x06, struct drm_stats)
 #define DRM_IOCTL_SET_VERSION		DRM_IOWR(0x07, struct drm_set_version)
 #define DRM_IOCTL_MODESET_CTL           DRM_IOW(0x08, struct drm_modeset_ctl)
+#define DRM_IOCTL_GEM_CLOSE		DRM_IOW (0x09, struct drm_gem_close)
+#define DRM_IOCTL_GEM_FLINK		DRM_IOWR(0x0a, struct drm_gem_flink)
+#define DRM_IOCTL_GEM_OPEN		DRM_IOWR(0x0b, struct drm_gem_open)
 
 #define DRM_IOCTL_SET_UNIQUE		DRM_IOW( 0x10, struct drm_unique)
 #define DRM_IOCTL_AUTH_MAGIC		DRM_IOW( 0x11, struct drm_auth)
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index e79ce0781f0b..1469a1bd8821 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -104,6 +104,7 @@ struct drm_device;
 #define DRIVER_DMA_QUEUE   0x200
 #define DRIVER_FB_DMA      0x400
 #define DRIVER_IRQ_VBL2    0x800
+#define DRIVER_GEM         0x1000
 
 /***********************************************************************/
 /** \name Begin the DRM... */
@@ -387,6 +388,10 @@ struct drm_file {
 	struct drm_minor *minor;
 	int remove_auth_on_close;
 	unsigned long lock_count;
+	/** Mapping of mm object handles to object pointers. */
+	struct idr object_idr;
+	/** Lock for synchronization of access to object_idr. */
+	spinlock_t table_lock;
 	struct file *filp;
 	void *driver_priv;
 };
@@ -557,6 +562,56 @@ struct drm_ati_pcigart_info {
 	int table_size;
 };
 
+/**
+ * This structure defines the drm_mm memory object, which will be used by the
+ * DRM for its buffer objects.
+ */
+struct drm_gem_object {
+	/** Reference count of this object */
+	struct kref refcount;
+
+	/** Handle count of this object. Each handle also holds a reference */
+	struct kref handlecount;
+
+	/** Related drm device */
+	struct drm_device *dev;
+
+	/** File representing the shmem storage */
+	struct file *filp;
+
+	/**
+	 * Size of the object, in bytes.  Immutable over the object's
+	 * lifetime.
+	 */
+	size_t size;
+
+	/**
+	 * Global name for this object, starts at 1. 0 means unnamed.
+	 * Access is covered by the object_name_lock in the related drm_device
+	 */
+	int name;
+
+	/**
+	 * Memory domains. These monitor which caches contain read/write data
+	 * related to the object. When transitioning from one set of domains
+	 * to another, the driver is called to ensure that caches are suitably
+	 * flushed and invalidated
+	 */
+	uint32_t read_domains;
+	uint32_t write_domain;
+
+	/**
+	 * While validating an exec operation, the
+	 * new read/write domain values are computed here.
+	 * They will be transferred to the above values
+	 * at the point that any cache flushing occurs
+	 */
+	uint32_t pending_read_domains;
+	uint32_t pending_write_domain;
+
+	void *driver_private;
+};
+
 /**
  * DRM driver structure. This structure represent the common code for
  * a family of cards. There will one drm_device for each card present
@@ -657,6 +712,18 @@ struct drm_driver {
 	void (*set_version) (struct drm_device *dev,
 			     struct drm_set_version *sv);
 
+	int (*proc_init)(struct drm_minor *minor);
+	void (*proc_cleanup)(struct drm_minor *minor);
+
+	/**
+	 * Driver-specific constructor for drm_gem_objects, to set up
+	 * obj->driver_private.
+	 *
+	 * Returns 0 on success.
+	 */
+	int (*gem_init_object) (struct drm_gem_object *obj);
+	void (*gem_free_object) (struct drm_gem_object *obj);
+
 	int major;
 	int minor;
 	int patchlevel;
@@ -830,6 +897,22 @@ struct drm_device {
 	spinlock_t drw_lock;
 	struct idr drw_idr;
 	/*@} */
+
+	/** \name GEM information */
+	/*@{ */
+	spinlock_t object_name_lock;
+	struct idr object_name_idr;
+	atomic_t object_count;
+	atomic_t object_memory;
+	atomic_t pin_count;
+	atomic_t pin_memory;
+	atomic_t gtt_count;
+	atomic_t gtt_memory;
+	uint32_t gtt_total;
+	uint32_t invalidate_domains;    /* domains pending invalidation */
+	uint32_t flush_domains;         /* domains pending flush */
+	/*@} */
+
 };
 
 static __inline__ int drm_core_check_feature(struct drm_device *dev,
@@ -926,6 +1009,10 @@ extern void *drm_realloc(void *oldpt, size_t oldsize, size_t size, int area);
 extern DRM_AGP_MEM *drm_alloc_agp(struct drm_device *dev, int pages, u32 type);
 extern int drm_free_agp(DRM_AGP_MEM * handle, int pages);
 extern int drm_bind_agp(DRM_AGP_MEM * handle, unsigned int start);
+extern DRM_AGP_MEM *drm_agp_bind_pages(struct drm_device *dev,
+				       struct page **pages,
+				       unsigned long num_pages,
+				       uint32_t gtt_offset);
 extern int drm_unbind_agp(DRM_AGP_MEM * handle);
 
 				/* Misc. IOCTL support (drm_ioctl.h) */
@@ -988,6 +1075,9 @@ extern int drm_getmagic(struct drm_device *dev, void *data,
 extern int drm_authmagic(struct drm_device *dev, void *data,
 			 struct drm_file *file_priv);
 
+/* Cache management (drm_cache.c) */
+void drm_clflush_pages(struct page *pages[], unsigned long num_pages);
+
 				/* Locking IOCTL support (drm_lock.h) */
 extern int drm_lock(struct drm_device *dev, void *data,
 		    struct drm_file *file_priv);
@@ -1094,6 +1184,7 @@ extern DRM_AGP_MEM *drm_agp_allocate_memory(struct agp_bridge_data *bridge, size
 extern int drm_agp_free_memory(DRM_AGP_MEM * handle);
 extern int drm_agp_bind_memory(DRM_AGP_MEM * handle, off_t start);
 extern int drm_agp_unbind_memory(DRM_AGP_MEM * handle);
+extern void drm_agp_chipset_flush(struct drm_device *dev);
 
 				/* Stub support (drm_stub.h) */
 extern int drm_get_dev(struct pci_dev *pdev, const struct pci_device_id *ent,
@@ -1156,6 +1247,66 @@ extern unsigned long drm_mm_tail_space(struct drm_mm *mm);
 extern int drm_mm_remove_space_from_tail(struct drm_mm *mm, unsigned long size);
 extern int drm_mm_add_space_to_tail(struct drm_mm *mm, unsigned long size);
 
+/* Graphics Execution Manager library functions (drm_gem.c) */
+int drm_gem_init(struct drm_device *dev);
+void drm_gem_object_free(struct kref *kref);
+struct drm_gem_object *drm_gem_object_alloc(struct drm_device *dev,
+					    size_t size);
+void drm_gem_object_handle_free(struct kref *kref);
+
+static inline void
+drm_gem_object_reference(struct drm_gem_object *obj)
+{
+	kref_get(&obj->refcount);
+}
+
+static inline void
+drm_gem_object_unreference(struct drm_gem_object *obj)
+{
+	if (obj == NULL)
+		return;
+
+	kref_put(&obj->refcount, drm_gem_object_free);
+}
+
+int drm_gem_handle_create(struct drm_file *file_priv,
+			  struct drm_gem_object *obj,
+			  int *handlep);
+
+static inline void
+drm_gem_object_handle_reference(struct drm_gem_object *obj)
+{
+	drm_gem_object_reference(obj);
+	kref_get(&obj->handlecount);
+}
+
+static inline void
+drm_gem_object_handle_unreference(struct drm_gem_object *obj)
+{
+	if (obj == NULL)
+		return;
+
+	/*
+	 * Must bump handle count first as this may be the last
+	 * ref, in which case the object would disappear before we
+	 * checked for a name
+	 */
+	kref_put(&obj->handlecount, drm_gem_object_handle_free);
+	drm_gem_object_unreference(obj);
+}
+
+struct drm_gem_object *drm_gem_object_lookup(struct drm_device *dev,
+					     struct drm_file *filp,
+					     int handle);
+int drm_gem_close_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int drm_gem_flink_ioctl(struct drm_device *dev, void *data,
+			struct drm_file *file_priv);
+int drm_gem_open_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv);
+void drm_gem_open(struct drm_device *dev, struct drm_file *file_private);
+void drm_gem_release(struct drm_device *dev, struct drm_file *file_private);
+
 extern void drm_core_ioremap(struct drm_map *map, struct drm_device *dev);
 extern void drm_core_ioremap_wc(struct drm_map *map, struct drm_device *dev);
 extern void drm_core_ioremapfree(struct drm_map *map, struct drm_device *dev);
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index 05c66cf03a9e..59d08fca25a4 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -143,6 +143,22 @@ typedef struct _drm_i915_sarea {
 #define DRM_I915_GET_VBLANK_PIPE	0x0e
 #define DRM_I915_VBLANK_SWAP	0x0f
 #define DRM_I915_HWS_ADDR	0x11
+#define DRM_I915_GEM_INIT	0x13
+#define DRM_I915_GEM_EXECBUFFER	0x14
+#define DRM_I915_GEM_PIN	0x15
+#define DRM_I915_GEM_UNPIN	0x16
+#define DRM_I915_GEM_BUSY	0x17
+#define DRM_I915_GEM_THROTTLE	0x18
+#define DRM_I915_GEM_ENTERVT	0x19
+#define DRM_I915_GEM_LEAVEVT	0x1a
+#define DRM_I915_GEM_CREATE	0x1b
+#define DRM_I915_GEM_PREAD	0x1c
+#define DRM_I915_GEM_PWRITE	0x1d
+#define DRM_I915_GEM_MMAP	0x1e
+#define DRM_I915_GEM_SET_DOMAIN	0x1f
+#define DRM_I915_GEM_SW_FINISH	0x20
+#define DRM_I915_GEM_SET_TILING	0x21
+#define DRM_I915_GEM_GET_TILING	0x22
 
 #define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
 #define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
@@ -160,6 +176,20 @@ typedef struct _drm_i915_sarea {
 #define DRM_IOCTL_I915_SET_VBLANK_PIPE	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
 #define DRM_IOCTL_I915_GET_VBLANK_PIPE	DRM_IOR( DRM_COMMAND_BASE + DRM_I915_GET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
 #define DRM_IOCTL_I915_VBLANK_SWAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_VBLANK_SWAP, drm_i915_vblank_swap_t)
+#define DRM_IOCTL_I915_GEM_PIN		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_PIN, struct drm_i915_gem_pin)
+#define DRM_IOCTL_I915_GEM_UNPIN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_UNPIN, struct drm_i915_gem_unpin)
+#define DRM_IOCTL_I915_GEM_BUSY		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_BUSY, struct drm_i915_gem_busy)
+#define DRM_IOCTL_I915_GEM_THROTTLE	DRM_IO ( DRM_COMMAND_BASE + DRM_I915_GEM_THROTTLE)
+#define DRM_IOCTL_I915_GEM_ENTERVT	DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_ENTERVT)
+#define DRM_IOCTL_I915_GEM_LEAVEVT	DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_LEAVEVT)
+#define DRM_IOCTL_I915_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE, struct drm_i915_gem_create)
+#define DRM_IOCTL_I915_GEM_PREAD	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PREAD, struct drm_i915_gem_pread)
+#define DRM_IOCTL_I915_GEM_PWRITE	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
+#define DRM_IOCTL_I915_GEM_MMAP		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
+#define DRM_IOCTL_I915_GEM_SET_DOMAIN	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain)
+#define DRM_IOCTL_I915_GEM_SW_FINISH	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
+#define DRM_IOCTL_I915_GEM_SET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
+#define DRM_IOCTL_I915_GEM_GET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_TILING, struct drm_i915_gem_get_tiling)
 
 /* Allow drivers to submit batchbuffers directly to hardware, relying
  * on the security mechanisms provided by hardware.
@@ -200,6 +230,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_IRQ_ACTIVE            1
 #define I915_PARAM_ALLOW_BATCHBUFFER     2
 #define I915_PARAM_LAST_DISPATCH         3
+#define I915_PARAM_HAS_GEM               5
 
 typedef struct drm_i915_getparam {
 	int param;
@@ -267,4 +298,305 @@ typedef struct drm_i915_hws_addr {
 	uint64_t addr;
 } drm_i915_hws_addr_t;
 
+struct drm_i915_gem_init {
+	/**
+	 * Beginning offset in the GTT to be managed by the DRM memory
+	 * manager.
+	 */
+	uint64_t gtt_start;
+	/**
+	 * Ending offset in the GTT to be managed by the DRM memory
+	 * manager.
+	 */
+	uint64_t gtt_end;
+};
+
+struct drm_i915_gem_create {
+	/**
+	 * Requested size for the object.
+	 *
+	 * The (page-aligned) allocated size for the object will be returned.
+	 */
+	uint64_t size;
+	/**
+	 * Returned handle for the object.
+	 *
+	 * Object handles are nonzero.
+	 */
+	uint32_t handle;
+	uint32_t pad;
+};
+
+struct drm_i915_gem_pread {
+	/** Handle for the object being read. */
+	uint32_t handle;
+	uint32_t pad;
+	/** Offset into the object to read from */
+	uint64_t offset;
+	/** Length of data to read */
+	uint64_t size;
+	/**
+	 * Pointer to write the data into.
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	uint64_t data_ptr;
+};
+
+struct drm_i915_gem_pwrite {
+	/** Handle for the object being written to. */
+	uint32_t handle;
+	uint32_t pad;
+	/** Offset into the object to write to */
+	uint64_t offset;
+	/** Length of data to write */
+	uint64_t size;
+	/**
+	 * Pointer to read the data from.
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	uint64_t data_ptr;
+};
+
+struct drm_i915_gem_mmap {
+	/** Handle for the object being mapped. */
+	uint32_t handle;
+	uint32_t pad;
+	/** Offset in the object to map. */
+	uint64_t offset;
+	/**
+	 * Length of data to map.
+	 *
+	 * The value will be page-aligned.
+	 */
+	uint64_t size;
+	/**
+	 * Returned pointer the data was mapped at.
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	uint64_t addr_ptr;
+};
+
+struct drm_i915_gem_set_domain {
+	/** Handle for the object */
+	uint32_t handle;
+
+	/** New read domains */
+	uint32_t read_domains;
+
+	/** New write domain */
+	uint32_t write_domain;
+};
+
+struct drm_i915_gem_sw_finish {
+	/** Handle for the object */
+	uint32_t handle;
+};
+
+struct drm_i915_gem_relocation_entry {
+	/**
+	 * Handle of the buffer being pointed to by this relocation entry.
+	 *
+	 * It's appealing to make this be an index into the mm_validate_entry
+	 * list to refer to the buffer, but this allows the driver to create
+	 * a relocation list for state buffers and not re-write it per
+	 * exec using the buffer.
+	 */
+	uint32_t target_handle;
+
+	/**
+	 * Value to be added to the offset of the target buffer to make up
+	 * the relocation entry.
+	 */
+	uint32_t delta;
+
+	/** Offset in the buffer the relocation entry will be written into */
+	uint64_t offset;
+
+	/**
+	 * Offset value of the target buffer that the relocation entry was last
+	 * written as.
+	 *
+	 * If the buffer has the same offset as last time, we can skip syncing
+	 * and writing the relocation.  This value is written back out by
+	 * the execbuffer ioctl when the relocation is written.
+	 */
+	uint64_t presumed_offset;
+
+	/**
+	 * Target memory domains read by this operation.
+	 */
+	uint32_t read_domains;
+
+	/**
+	 * Target memory domains written by this operation.
+	 *
+	 * Note that only one domain may be written by the whole
+	 * execbuffer operation, so that where there are conflicts,
+	 * the application will get -EINVAL back.
+	 */
+	uint32_t write_domain;
+};
+
+/** @{
+ * Intel memory domains
+ *
+ * Most of these just align with the various caches in
+ * the system and are used to flush and invalidate as
+ * objects end up cached in different domains.
+ */
+/** CPU cache */
+#define I915_GEM_DOMAIN_CPU		0x00000001
+/** Render cache, used by 2D and 3D drawing */
+#define I915_GEM_DOMAIN_RENDER		0x00000002
+/** Sampler cache, used by texture engine */
+#define I915_GEM_DOMAIN_SAMPLER		0x00000004
+/** Command queue, used to load batch buffers */
+#define I915_GEM_DOMAIN_COMMAND		0x00000008
+/** Instruction cache, used by shader programs */
+#define I915_GEM_DOMAIN_INSTRUCTION	0x00000010
+/** Vertex address cache */
+#define I915_GEM_DOMAIN_VERTEX		0x00000020
+/** GTT domain - aperture and scanout */
+#define I915_GEM_DOMAIN_GTT		0x00000040
+/** @} */
+
+struct drm_i915_gem_exec_object {
+	/**
+	 * User's handle for a buffer to be bound into the GTT for this
+	 * operation.
+	 */
+	uint32_t handle;
+
+	/** Number of relocations to be performed on this buffer */
+	uint32_t relocation_count;
+	/**
+	 * Pointer to array of struct drm_i915_gem_relocation_entry containing
+	 * the relocations to be performed in this buffer.
+	 */
+	uint64_t relocs_ptr;
+
+	/** Required alignment in graphics aperture */
+	uint64_t alignment;
+
+	/**
+	 * Returned value of the updated offset of the object, for future
+	 * presumed_offset writes.
+	 */
+	uint64_t offset;
+};
+
+struct drm_i915_gem_execbuffer {
+	/**
+	 * List of buffers to be validated with their relocations to be
+	 * performend on them.
+	 *
+	 * This is a pointer to an array of struct drm_i915_gem_validate_entry.
+	 *
+	 * These buffers must be listed in an order such that all relocations
+	 * a buffer is performing refer to buffers that have already appeared
+	 * in the validate list.
+	 */
+	uint64_t buffers_ptr;
+	uint32_t buffer_count;
+
+	/** Offset in the batchbuffer to start execution from. */
+	uint32_t batch_start_offset;
+	/** Bytes used in batchbuffer from batch_start_offset */
+	uint32_t batch_len;
+	uint32_t DR1;
+	uint32_t DR4;
+	uint32_t num_cliprects;
+	/** This is a struct drm_clip_rect *cliprects */
+	uint64_t cliprects_ptr;
+};
+
+struct drm_i915_gem_pin {
+	/** Handle of the buffer to be pinned. */
+	uint32_t handle;
+	uint32_t pad;
+
+	/** alignment required within the aperture */
+	uint64_t alignment;
+
+	/** Returned GTT offset of the buffer. */
+	uint64_t offset;
+};
+
+struct drm_i915_gem_unpin {
+	/** Handle of the buffer to be unpinned. */
+	uint32_t handle;
+	uint32_t pad;
+};
+
+struct drm_i915_gem_busy {
+	/** Handle of the buffer to check for busy */
+	uint32_t handle;
+
+	/** Return busy status (1 if busy, 0 if idle) */
+	uint32_t busy;
+};
+
+#define I915_TILING_NONE	0
+#define I915_TILING_X		1
+#define I915_TILING_Y		2
+
+#define I915_BIT_6_SWIZZLE_NONE		0
+#define I915_BIT_6_SWIZZLE_9		1
+#define I915_BIT_6_SWIZZLE_9_10		2
+#define I915_BIT_6_SWIZZLE_9_11		3
+#define I915_BIT_6_SWIZZLE_9_10_11	4
+/* Not seen by userland */
+#define I915_BIT_6_SWIZZLE_UNKNOWN	5
+
+struct drm_i915_gem_set_tiling {
+	/** Handle of the buffer to have its tiling state updated */
+	uint32_t handle;
+
+	/**
+	 * Tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
+	 * I915_TILING_Y).
+	 *
+	 * This value is to be set on request, and will be updated by the
+	 * kernel on successful return with the actual chosen tiling layout.
+	 *
+	 * The tiling mode may be demoted to I915_TILING_NONE when the system
+	 * has bit 6 swizzling that can't be managed correctly by GEM.
+	 *
+	 * Buffer contents become undefined when changing tiling_mode.
+	 */
+	uint32_t tiling_mode;
+
+	/**
+	 * Stride in bytes for the object when in I915_TILING_X or
+	 * I915_TILING_Y.
+	 */
+	uint32_t stride;
+
+	/**
+	 * Returned address bit 6 swizzling required for CPU access through
+	 * mmap mapping.
+	 */
+	uint32_t swizzle_mode;
+};
+
+struct drm_i915_gem_get_tiling {
+	/** Handle of the buffer to get tiling state for. */
+	uint32_t handle;
+
+	/**
+	 * Current tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
+	 * I915_TILING_Y).
+	 */
+	uint32_t tiling_mode;
+
+	/**
+	 * Returned address bit 6 swizzling required for CPU access through
+	 * mmap mapping.
+	 */
+	uint32_t swizzle_mode;
+};
+
 #endif				/* _I915_DRM_H_ */
-- 
cgit v1.2.3


From ed4c9c4acf948b42b138747fcb8843ecb1a24ce4 Mon Sep 17 00:00:00 2001
From: Kristian Høgsberg <krh@redhat.com>
Date: Wed, 20 Aug 2008 11:08:52 -0400
Subject: i915: Add chip set ID param.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Kristian Høgsberg <krh@redhat.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/i915/i915_dma.c | 3 +++
 include/drm/i915_drm.h          | 1 +
 2 files changed, 4 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index f167ff68a4bf..ea85d71cab04 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -689,6 +689,9 @@ static int i915_getparam(struct drm_device *dev, void *data,
 	case I915_PARAM_LAST_DISPATCH:
 		value = READ_BREADCRUMB(dev_priv);
 		break;
+	case I915_PARAM_CHIPSET_ID:
+		value = dev->pci_device;
+		break;
 	case I915_PARAM_HAS_GEM:
 		value = 1;
 		break;
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index 59d08fca25a4..eb4b35031a55 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -230,6 +230,7 @@ typedef struct drm_i915_irq_wait {
 #define I915_PARAM_IRQ_ACTIVE            1
 #define I915_PARAM_ALLOW_BATCHBUFFER     2
 #define I915_PARAM_LAST_DISPATCH         3
+#define I915_PARAM_CHIPSET_ID            4
 #define I915_PARAM_HAS_GEM               5
 
 typedef struct drm_i915_getparam {
-- 
cgit v1.2.3


From dbb19d302baa8ba518599701914f600935fc53fa Mon Sep 17 00:00:00 2001
From: Kristian Høgsberg <krh@redhat.com>
Date: Wed, 20 Aug 2008 11:04:27 -0400
Subject: i915 gem: install and uninstall irq handler in entervt and leavevt
 ioctls.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Kristian Høgsberg <krh@redhat.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/i915/i915_gem.c | 5 +++++
 include/drm/drmP.h              | 1 +
 2 files changed, 6 insertions(+)

(limited to 'include')

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index bb6e5a37efa2..5fe50343de11 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2443,6 +2443,9 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
 	BUG_ON(!list_empty(&dev_priv->mm.request_list));
 	dev_priv->mm.suspended = 0;
 	mutex_unlock(&dev->struct_mutex);
+
+	drm_irq_install(dev);
+
 	return 0;
 }
 
@@ -2458,6 +2461,8 @@ i915_gem_leavevt_ioctl(struct drm_device *dev, void *data,
 		i915_gem_cleanup_ringbuffer(dev);
 	mutex_unlock(&dev->struct_mutex);
 
+	drm_irq_uninstall(dev);
+
 	return 0;
 }
 
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 1469a1bd8821..51ee72c962b1 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1134,6 +1134,7 @@ extern void drm_core_reclaim_buffers(struct drm_device *dev,
 extern int drm_control(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
 extern irqreturn_t drm_irq_handler(DRM_IRQ_ARGS);
+extern int drm_irq_install(struct drm_device *dev);
 extern int drm_irq_uninstall(struct drm_device *dev);
 extern void drm_driver_irq_preinstall(struct drm_device *dev);
 extern void drm_driver_irq_postinstall(struct drm_device *dev);
-- 
cgit v1.2.3


From 9bfbd5cb72c9edb8504a4a7a0aa89cdb2fcb4845 Mon Sep 17 00:00:00 2001
From: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Mon, 15 Sep 2008 15:00:33 -0700
Subject: drm: kill drm_device->irq

Like the last patch but adds a macro to get at the irq value instead of
dereferencing pdev directly.  Should  make things easier for the BSD guys and
if we ever support non-PCI devices.

Signed-off-by:  Jesse Barnes <jbarnes@virtuousgeek.org>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_irq.c             | 7 ++-----
 drivers/gpu/drm/drm_stub.c            | 1 -
 drivers/gpu/drm/mga/mga_state.c       | 2 +-
 drivers/gpu/drm/r128/r128_state.c     | 2 +-
 drivers/gpu/drm/radeon/radeon_state.c | 2 +-
 drivers/gpu/drm/via/via_irq.c         | 3 ---
 drivers/gpu/drm/via/via_mm.c          | 3 +--
 include/drm/drmP.h                    | 6 +++++-
 8 files changed, 11 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index d0c13d954f52..4091b9e291f9 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -228,12 +228,9 @@ int drm_irq_install(struct drm_device *dev)
 	if (drm_core_check_feature(dev, DRIVER_IRQ_SHARED))
 		sh_flags = IRQF_SHARED;
 
-	ret = request_irq(dev->pdev->irq, dev->driver->irq_handler,
+	ret = request_irq(drm_dev_to_irq(dev), dev->driver->irq_handler,
 			  sh_flags, dev->devname, dev);
-	/* Expose the device irq number to drivers that want to export it for
-	 * whatever reason.
-	 */
-	dev->irq = dev->pdev->irq;
+
 	if (ret < 0) {
 		mutex_lock(&dev->struct_mutex);
 		dev->irq_enabled = 0;
diff --git a/drivers/gpu/drm/drm_stub.c b/drivers/gpu/drm/drm_stub.c
index 82f4657b8879..141e33004a76 100644
--- a/drivers/gpu/drm/drm_stub.c
+++ b/drivers/gpu/drm/drm_stub.c
@@ -107,7 +107,6 @@ static int drm_fill_in_dev(struct drm_device * dev, struct pci_dev *pdev,
 #ifdef __alpha__
 	dev->hose = pdev->sysdata;
 #endif
-	dev->irq = pdev->irq;
 
 	if (drm_ht_create(&dev->map_hash, 12)) {
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/mga/mga_state.c b/drivers/gpu/drm/mga/mga_state.c
index d3f8aade07b3..b710fab21cb3 100644
--- a/drivers/gpu/drm/mga/mga_state.c
+++ b/drivers/gpu/drm/mga/mga_state.c
@@ -1022,7 +1022,7 @@ static int mga_getparam(struct drm_device *dev, void *data, struct drm_file *fil
 
 	switch (param->param) {
 	case MGA_PARAM_IRQ_NR:
-		value = dev->irq;
+		value = drm_dev_to_irq(dev);
 		break;
 	case MGA_PARAM_CARD_TYPE:
 		value = dev_priv->chipset;
diff --git a/drivers/gpu/drm/r128/r128_state.c b/drivers/gpu/drm/r128/r128_state.c
index 51a9afce7b9b..f7a5b5740764 100644
--- a/drivers/gpu/drm/r128/r128_state.c
+++ b/drivers/gpu/drm/r128/r128_state.c
@@ -1629,7 +1629,7 @@ static int r128_getparam(struct drm_device *dev, void *data, struct drm_file *fi
 
 	switch (param->param) {
 	case R128_PARAM_IRQ_NR:
-		value = dev->irq;
+		value = drm_dev_to_irq(dev);
 		break;
 	default:
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/radeon_state.c b/drivers/gpu/drm/radeon/radeon_state.c
index 11c146b49211..5d7153fcc7b0 100644
--- a/drivers/gpu/drm/radeon/radeon_state.c
+++ b/drivers/gpu/drm/radeon/radeon_state.c
@@ -2997,7 +2997,7 @@ static int radeon_cp_getparam(struct drm_device *dev, void *data, struct drm_fil
 		value = GET_SCRATCH(2);
 		break;
 	case RADEON_PARAM_IRQ_NR:
-		value = dev->irq;
+		value = drm_dev_to_irq(dev);
 		break;
 	case RADEON_PARAM_GART_BASE:
 		value = dev_priv->gart_vm_start;
diff --git a/drivers/gpu/drm/via/via_irq.c b/drivers/gpu/drm/via/via_irq.c
index 1b966fbdb49f..665d319b927b 100644
--- a/drivers/gpu/drm/via/via_irq.c
+++ b/drivers/gpu/drm/via/via_irq.c
@@ -354,9 +354,6 @@ int via_wait_irq(struct drm_device *dev, void *data, struct drm_file *file_priv)
 	drm_via_irq_t *cur_irq = dev_priv->via_irqs;
 	int force_sequence;
 
-	if (!dev->irq)
-		return -EINVAL;
-
 	if (irqwait->request.irq >= dev_priv->num_irqs) {
 		DRM_ERROR("Trying to wait on unknown irq %d\n",
 			  irqwait->request.irq);
diff --git a/drivers/gpu/drm/via/via_mm.c b/drivers/gpu/drm/via/via_mm.c
index e64094916e4f..f694cb5ededc 100644
--- a/drivers/gpu/drm/via/via_mm.c
+++ b/drivers/gpu/drm/via/via_mm.c
@@ -93,8 +93,7 @@ int via_final_context(struct drm_device *dev, int context)
 	/* Last context, perform cleanup */
 	if (dev->ctx_count == 1 && dev->dev_private) {
 		DRM_DEBUG("Last Context\n");
-		if (dev->irq)
-			drm_irq_uninstall(dev);
+		drm_irq_uninstall(dev);
 		via_cleanup_futex(dev_priv);
 		via_do_cleanup_map(dev);
 	}
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 51ee72c962b1..90a9e0247d58 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -824,7 +824,6 @@ struct drm_device {
 
 	/** \name Context support */
 	/*@{ */
-	int irq;			/**< Interrupt used by board */
 	int irq_enabled;		/**< True if irq handler is enabled */
 	__volatile__ long context_flag;	/**< Context swapping flag */
 	__volatile__ long interrupt_flag; /**< Interruption handler flag */
@@ -915,6 +914,11 @@ struct drm_device {
 
 };
 
+static inline int drm_dev_to_irq(struct drm_device *dev)
+{
+	return dev->pdev->irq;
+}
+
 static __inline__ int drm_core_check_feature(struct drm_device *dev,
 					     int feature)
 {
-- 
cgit v1.2.3


From ba1eb1d825fdef40f69871caf8e5842d00efbbc5 Mon Sep 17 00:00:00 2001
From: Keith Packard <keithp@keithp.com>
Date: Tue, 14 Oct 2008 19:55:10 -0700
Subject: i915: Map status page cached for chips with GTT-based HWS location.

This should improve performance by avoiding uncached reads by the CPU (the
point of having a status page), and may improve stability.  This patch only
affects G33, GM45 and G45 chips as those are the only ones using GTT-based
HWS mappings.

Signed-off-by: Keith Packard <keithp@keithp.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/drm_agpsupport.c |  5 +++--
 drivers/gpu/drm/i915/i915_drv.h  |  3 +++
 drivers/gpu/drm/i915/i915_gem.c  | 28 +++++++++++++++-------------
 include/drm/drmP.h               |  3 ++-
 4 files changed, 23 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/drm_agpsupport.c b/drivers/gpu/drm/drm_agpsupport.c
index 2639be2db9e5..3d33b8252b58 100644
--- a/drivers/gpu/drm/drm_agpsupport.c
+++ b/drivers/gpu/drm/drm_agpsupport.c
@@ -464,7 +464,8 @@ DRM_AGP_MEM *
 drm_agp_bind_pages(struct drm_device *dev,
 		   struct page **pages,
 		   unsigned long num_pages,
-		   uint32_t gtt_offset)
+		   uint32_t gtt_offset,
+		   u32 type)
 {
 	DRM_AGP_MEM *mem;
 	int ret, i;
@@ -472,7 +473,7 @@ drm_agp_bind_pages(struct drm_device *dev,
 	DRM_DEBUG("\n");
 
 	mem = drm_agp_allocate_memory(dev->agp->bridge, num_pages,
-				      AGP_USER_MEMORY);
+				      type);
 	if (mem == NULL) {
 		DRM_ERROR("Failed to allocate memory for %ld pages\n",
 			  num_pages);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index da7c0072ad4c..eae4ed3956e0 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -373,6 +373,9 @@ struct drm_i915_gem_object {
 	/** Current tiling mode for the object. */
 	uint32_t tiling_mode;
 
+	/** AGP mapping type (AGP_USER_MEMORY or AGP_USER_CACHED_MEMORY */
+	uint32_t agp_type;
+
 	/**
 	 * Flagging of which individual pages are valid in GEM_DOMAIN_CPU when
 	 * GEM_DOMAIN_CPU is not in the object's read domain.
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 94b9bdce0c75..99a86249bb1b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1159,7 +1159,8 @@ i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment)
 	obj_priv->agp_mem = drm_agp_bind_pages(dev,
 					       obj_priv->page_list,
 					       page_count,
-					       obj_priv->gtt_offset);
+					       obj_priv->gtt_offset,
+					       obj_priv->agp_type);
 	if (obj_priv->agp_mem == NULL) {
 		i915_gem_object_free_page_list(obj);
 		drm_mm_put_block(obj_priv->gtt_space);
@@ -2142,6 +2143,8 @@ int i915_gem_init_object(struct drm_gem_object *obj)
 	obj->write_domain = I915_GEM_DOMAIN_CPU;
 	obj->read_domains = I915_GEM_DOMAIN_CPU;
 
+	obj_priv->agp_type = AGP_USER_MEMORY;
+
 	obj->driver_private = obj_priv;
 	obj_priv->obj = obj;
 	INIT_LIST_HEAD(&obj_priv->list);
@@ -2311,6 +2314,7 @@ i915_gem_init_hws(struct drm_device *dev)
 		return -ENOMEM;
 	}
 	obj_priv = obj->driver_private;
+	obj_priv->agp_type = AGP_USER_CACHED_MEMORY;
 
 	ret = i915_gem_object_pin(obj, 4096);
 	if (ret != 0) {
@@ -2319,25 +2323,18 @@ i915_gem_init_hws(struct drm_device *dev)
 	}
 
 	dev_priv->status_gfx_addr = obj_priv->gtt_offset;
-	dev_priv->hws_map.offset = dev->agp->base + obj_priv->gtt_offset;
-	dev_priv->hws_map.size = 4096;
-	dev_priv->hws_map.type = 0;
-	dev_priv->hws_map.flags = 0;
-	dev_priv->hws_map.mtrr = 0;
 
-	/* Ioremapping here is the wrong thing to do.  We want cached access.
-	 */
-	drm_core_ioremap_wc(&dev_priv->hws_map, dev);
-	if (dev_priv->hws_map.handle == NULL) {
+	dev_priv->hw_status_page = kmap(obj_priv->page_list[0]);
+	if (dev_priv->hw_status_page == NULL) {
 		DRM_ERROR("Failed to map status page.\n");
 		memset(&dev_priv->hws_map, 0, sizeof(dev_priv->hws_map));
 		drm_gem_object_unreference(obj);
 		return -EINVAL;
 	}
 	dev_priv->hws_obj = obj;
-	dev_priv->hw_status_page = dev_priv->hws_map.handle;
 	memset(dev_priv->hw_status_page, 0, PAGE_SIZE);
 	I915_WRITE(HWS_PGA, dev_priv->status_gfx_addr);
+	I915_READ(HWS_PGA); /* posting read */
 	DRM_DEBUG("hws offset: 0x%08x\n", dev_priv->status_gfx_addr);
 
 	return 0;
@@ -2456,10 +2453,15 @@ i915_gem_cleanup_ringbuffer(struct drm_device *dev)
 	memset(&dev_priv->ring, 0, sizeof(dev_priv->ring));
 
 	if (dev_priv->hws_obj != NULL) {
-		i915_gem_object_unpin(dev_priv->hws_obj);
-		drm_gem_object_unreference(dev_priv->hws_obj);
+		struct drm_gem_object *obj = dev_priv->hws_obj;
+		struct drm_i915_gem_object *obj_priv = obj->driver_private;
+
+		kunmap(obj_priv->page_list[0]);
+		i915_gem_object_unpin(obj);
+		drm_gem_object_unreference(obj);
 		dev_priv->hws_obj = NULL;
 		memset(&dev_priv->hws_map, 0, sizeof(dev_priv->hws_map));
+		dev_priv->hw_status_page = NULL;
 
 		/* Write high address into HWS_PGA when disabling. */
 		I915_WRITE(HWS_PGA, 0x1ffff000);
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 90a9e0247d58..59c796b46ee7 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1016,7 +1016,8 @@ extern int drm_bind_agp(DRM_AGP_MEM * handle, unsigned int start);
 extern DRM_AGP_MEM *drm_agp_bind_pages(struct drm_device *dev,
 				       struct page **pages,
 				       unsigned long num_pages,
-				       uint32_t gtt_offset);
+				       uint32_t gtt_offset,
+				       uint32_t type);
 extern int drm_unbind_agp(DRM_AGP_MEM * handle);
 
 				/* Misc. IOCTL support (drm_ioctl.h) */
-- 
cgit v1.2.3


From f0738e92403466d45cfb5008da668260c77fff4b Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexdeucher@gmail.com>
Date: Thu, 16 Oct 2008 17:12:02 +1000
Subject: drm/radeon: add support for RS740 IGP chipsets.

This adds support for the HS2100 IGP chipset.

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/radeon/radeon_cp.c  | 24 ++++++++++++++++--------
 drivers/gpu/drm/radeon/radeon_drv.h |  4 +++-
 include/drm/drm_pciids.h            |  4 ++++
 3 files changed, 23 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index 6157cd4bb436..e6e0c2933efd 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -71,7 +71,8 @@ static u32 RS690_READ_MCIND(drm_radeon_private_t *dev_priv, int addr)
 
 static u32 IGP_READ_MCIND(drm_radeon_private_t *dev_priv, int addr)
 {
-	if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690)
+	if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||
+	    ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS740))
 		return RS690_READ_MCIND(dev_priv, addr);
 	else
 		return RS480_READ_MCIND(dev_priv, addr);
@@ -82,7 +83,8 @@ u32 radeon_read_fb_location(drm_radeon_private_t *dev_priv)
 
 	if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV515)
 		return R500_READ_MCIND(dev_priv, RV515_MC_FB_LOCATION);
-	else if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690)
+	else if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||
+		 ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS740))
 		return RS690_READ_MCIND(dev_priv, RS690_MC_FB_LOCATION);
 	else if ((dev_priv->flags & RADEON_FAMILY_MASK) > CHIP_RV515)
 		return R500_READ_MCIND(dev_priv, R520_MC_FB_LOCATION);
@@ -94,7 +96,8 @@ static void radeon_write_fb_location(drm_radeon_private_t *dev_priv, u32 fb_loc)
 {
 	if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV515)
 		R500_WRITE_MCIND(RV515_MC_FB_LOCATION, fb_loc);
-	else if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690)
+	else if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||
+		 ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS740))
 		RS690_WRITE_MCIND(RS690_MC_FB_LOCATION, fb_loc);
 	else if ((dev_priv->flags & RADEON_FAMILY_MASK) > CHIP_RV515)
 		R500_WRITE_MCIND(R520_MC_FB_LOCATION, fb_loc);
@@ -106,7 +109,8 @@ static void radeon_write_agp_location(drm_radeon_private_t *dev_priv, u32 agp_lo
 {
 	if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV515)
 		R500_WRITE_MCIND(RV515_MC_AGP_LOCATION, agp_loc);
-	else if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690)
+	else if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||
+		 ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS740))
 		RS690_WRITE_MCIND(RS690_MC_AGP_LOCATION, agp_loc);
 	else if ((dev_priv->flags & RADEON_FAMILY_MASK) > CHIP_RV515)
 		R500_WRITE_MCIND(R520_MC_AGP_LOCATION, agp_loc);
@@ -122,7 +126,8 @@ static void radeon_write_agp_base(drm_radeon_private_t *dev_priv, u64 agp_base)
 	if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV515) {
 		R500_WRITE_MCIND(RV515_MC_AGP_BASE, agp_base_lo);
 		R500_WRITE_MCIND(RV515_MC_AGP_BASE_2, agp_base_hi);
-	} else if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) {
+	} else if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||
+		 ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS740)) {
 		RS690_WRITE_MCIND(RS690_MC_AGP_BASE, agp_base_lo);
 		RS690_WRITE_MCIND(RS690_MC_AGP_BASE_2, agp_base_hi);
 	} else if ((dev_priv->flags & RADEON_FAMILY_MASK) > CHIP_RV515) {
@@ -364,8 +369,9 @@ static void radeon_cp_load_microcode(drm_radeon_private_t * dev_priv)
 			RADEON_WRITE(RADEON_CP_ME_RAM_DATAL,
 				     R420_cp_microcode[i][0]);
 		}
-	} else if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) {
-		DRM_INFO("Loading RS690 Microcode\n");
+	} else if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||
+		   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS740)) {
+		DRM_INFO("Loading RS690/RS740 Microcode\n");
 		for (i = 0; i < 256; i++) {
 			RADEON_WRITE(RADEON_CP_ME_RAM_DATAH,
 				     RS690_cp_microcode[i][1]);
@@ -720,7 +726,8 @@ static void radeon_set_igpgart(drm_radeon_private_t * dev_priv, int on)
 			  dev_priv->gart_size);
 
 		temp = IGP_READ_MCIND(dev_priv, RS480_MC_MISC_CNTL);
-		if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690)
+		if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||
+		    ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS740))
 			IGP_WRITE_MCIND(RS480_MC_MISC_CNTL, (RS480_GART_INDEX_REG_EN |
 							     RS690_BLOCK_GFX_D3_EN));
 		else
@@ -813,6 +820,7 @@ static void radeon_set_pcigart(drm_radeon_private_t * dev_priv, int on)
 	u32 tmp;
 
 	if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||
+	    ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS740) ||
 	    (dev_priv->flags & RADEON_IS_IGPGART)) {
 		radeon_set_igpgart(dev_priv, on);
 		return;
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index d7e9c6cc6a1a..9d752bc0602b 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -125,6 +125,7 @@ enum radeon_family {
 	CHIP_RV410,
 	CHIP_RS480,
 	CHIP_RS690,
+	CHIP_RS740,
 	CHIP_RV515,
 	CHIP_R520,
 	CHIP_RV530,
@@ -1207,7 +1208,8 @@ do {								\
 
 #define IGP_WRITE_MCIND(addr, val)				\
 do {									\
-	if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690)       \
+	if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||   \
+	    ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS740))      \
 		RS690_WRITE_MCIND(addr, val);				\
 	else								\
 		RS480_WRITE_MCIND(addr, val);				\
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 135bd19499fc..e3a7b93fdefc 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -237,6 +237,10 @@
 	{0x1002, 0x7835, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS300|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x791e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS690|RADEON_IS_IGP|RADEON_NEW_MEMMAP|RADEON_IS_IGPGART}, \
 	{0x1002, 0x791f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS690|RADEON_IS_IGP|RADEON_NEW_MEMMAP|RADEON_IS_IGPGART}, \
+	{0x1002, 0x796c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS740|RADEON_IS_IGP|RADEON_NEW_MEMMAP|RADEON_IS_IGPGART}, \
+	{0x1002, 0x796d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS740|RADEON_IS_IGP|RADEON_NEW_MEMMAP|RADEON_IS_IGPGART}, \
+	{0x1002, 0x796e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS740|RADEON_IS_IGP|RADEON_NEW_MEMMAP|RADEON_IS_IGPGART}, \
+	{0x1002, 0x796f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS740|RADEON_IS_IGP|RADEON_NEW_MEMMAP|RADEON_IS_IGPGART}, \
 	{0, 0, 0}
 
 #define r128_PCI_IDS \
-- 
cgit v1.2.3


From b2ceddfa52cbeb244b90096f1e8d3e9f7e0ce299 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexdeucher@gmail.com>
Date: Fri, 17 Oct 2008 09:19:33 +1000
Subject: radeon: add RS400 family support.

This adds support for the RS400 family of IGPs for Intel CPUs.

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/radeon/radeon_cp.c  | 6 ++++--
 drivers/gpu/drm/radeon/radeon_drv.h | 1 +
 include/drm/drm_pciids.h            | 6 ++++--
 3 files changed, 9 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index e6e0c2933efd..a83d7615ba7f 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -133,9 +133,10 @@ static void radeon_write_agp_base(drm_radeon_private_t *dev_priv, u64 agp_base)
 	} else if ((dev_priv->flags & RADEON_FAMILY_MASK) > CHIP_RV515) {
 		R500_WRITE_MCIND(R520_MC_AGP_BASE, agp_base_lo);
 		R500_WRITE_MCIND(R520_MC_AGP_BASE_2, agp_base_hi);
-	} else if ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS480) {
+	} else if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS400) ||
+		   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS480)) {
 		RADEON_WRITE(RADEON_AGP_BASE, agp_base_lo);
-		RADEON_WRITE(RS480_AGP_BASE_2, 0);
+		RADEON_WRITE(RS480_AGP_BASE_2, agp_base_hi);
 	} else {
 		RADEON_WRITE(RADEON_AGP_BASE, agp_base_lo);
 		if ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_R200)
@@ -352,6 +353,7 @@ static void radeon_cp_load_microcode(drm_radeon_private_t * dev_priv)
 		   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_R350) ||
 		   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV350) ||
 		   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV380) ||
+		   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS400) ||
 		   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS480)) {
 		DRM_INFO("Loading R300 Microcode\n");
 		for (i = 0; i < 256; i++) {
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index 9d752bc0602b..9278429af9ed 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -123,6 +123,7 @@ enum radeon_family {
 	CHIP_RV380,
 	CHIP_R420,
 	CHIP_RV410,
+	CHIP_RS400,
 	CHIP_RS480,
 	CHIP_RS690,
 	CHIP_RS740,
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index e3a7b93fdefc..401cc8b7e88c 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -113,8 +113,10 @@
 	{0x1002, 0x5964, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5965, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280}, \
 	{0x1002, 0x5969, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV100}, \
-	{0x1002, 0x5a61, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
-	{0x1002, 0x5a62, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS480|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5a41, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5a42, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5a61, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_IGPGART}, \
+	{0x1002, 0x5a62, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS400|RADEON_IS_IGP|RADEON_IS_MOBILITY|RADEON_IS_IGPGART}, \
 	{0x1002, 0x5b60, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5b62, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5b63, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
-- 
cgit v1.2.3


From edc6f389f6ae9cb7621270a8ddbb1892bd8df125 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexdeucher@gmail.com>
Date: Fri, 17 Oct 2008 09:21:45 +1000
Subject: radeon: fix PCI bus mastering support enables.

Someone noticed these registers moved around for later chips,
so we redo the codepaths per-chip. PCIE chips don't appear to
require explicit enables.

Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/radeon/radeon_cp.c  | 16 ++++++++++++--
 drivers/gpu/drm/radeon/radeon_drv.h | 25 +++++++++++++++++++++
 include/drm/drm_pciids.h            | 44 ++++++++++++++++++-------------------
 3 files changed, 61 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/gpu/drm/radeon/radeon_cp.c b/drivers/gpu/drm/radeon/radeon_cp.c
index a83d7615ba7f..59a2132a8f57 100644
--- a/drivers/gpu/drm/radeon/radeon_cp.c
+++ b/drivers/gpu/drm/radeon/radeon_cp.c
@@ -363,6 +363,7 @@ static void radeon_cp_load_microcode(drm_radeon_private_t * dev_priv)
 				     R300_cp_microcode[i][0]);
 		}
 	} else if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_R420) ||
+		   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_R423) ||
 		   ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV410)) {
 		DRM_INFO("Loading R400 Microcode\n");
 		for (i = 0; i < 256; i++) {
@@ -652,8 +653,18 @@ static void radeon_cp_init_ring_buffer(struct drm_device * dev,
 	RADEON_WRITE(RADEON_SCRATCH_UMSK, 0x7);
 
 	/* Turn on bus mastering */
-	tmp = RADEON_READ(RADEON_BUS_CNTL) & ~RADEON_BUS_MASTER_DIS;
-	RADEON_WRITE(RADEON_BUS_CNTL, tmp);
+	if (((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS400) ||
+	    ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS690) ||
+	    ((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RS740)) {
+		/* rs400, rs690/rs740 */
+		tmp = RADEON_READ(RADEON_BUS_CNTL) & ~RS400_BUS_MASTER_DIS;
+		RADEON_WRITE(RADEON_BUS_CNTL, tmp);
+	} else if (!(((dev_priv->flags & RADEON_FAMILY_MASK) == CHIP_RV380) ||
+		    ((dev_priv->flags & RADEON_FAMILY_MASK) >= CHIP_R423))) {
+		/* r1xx, r2xx, r300, r(v)350, r420/r481, rs480 */
+		tmp = RADEON_READ(RADEON_BUS_CNTL) & ~RADEON_BUS_MASTER_DIS;
+		RADEON_WRITE(RADEON_BUS_CNTL, tmp);
+	} /* PCIE cards appears to not need this */
 
 	dev_priv->sarea_priv->last_frame = dev_priv->scratch[0] = 0;
 	RADEON_WRITE(RADEON_LAST_FRAME_REG, dev_priv->sarea_priv->last_frame);
@@ -1719,6 +1730,7 @@ int radeon_driver_load(struct drm_device *dev, unsigned long flags)
 	case CHIP_R300:
 	case CHIP_R350:
 	case CHIP_R420:
+	case CHIP_R423:
 	case CHIP_RV410:
 	case CHIP_RV515:
 	case CHIP_R520:
diff --git a/drivers/gpu/drm/radeon/radeon_drv.h b/drivers/gpu/drm/radeon/radeon_drv.h
index 9278429af9ed..4dbb813910c3 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.h
+++ b/drivers/gpu/drm/radeon/radeon_drv.h
@@ -122,6 +122,7 @@ enum radeon_family {
 	CHIP_RV350,
 	CHIP_RV380,
 	CHIP_R420,
+	CHIP_R423,
 	CHIP_RV410,
 	CHIP_RS400,
 	CHIP_RS480,
@@ -439,8 +440,31 @@ extern int r300_do_cp_cmdbuf(struct drm_device *dev,
 #	define RADEON_SCISSOR_1_ENABLE		(1 << 29)
 #	define RADEON_SCISSOR_2_ENABLE		(1 << 30)
 
+/*
+ * PCIE radeons (rv370/rv380, rv410, r423/r430/r480, r5xx)
+ * don't have an explicit bus mastering disable bit.  It's handled
+ * by the PCI D-states.  PMI_BM_DIS disables D-state bus master
+ * handling, not bus mastering itself.
+ */
 #define RADEON_BUS_CNTL			0x0030
+/* r1xx, r2xx, r300, r(v)350, r420/r481, rs480 */
 #	define RADEON_BUS_MASTER_DIS		(1 << 6)
+/* rs400, rs690/rs740 */
+#	define RS400_BUS_MASTER_DIS		(1 << 14)
+#	define RS400_MSI_REARM		        (1 << 20)
+/* see RS480_MSI_REARM in AIC_CNTL for rs480 */
+
+#define RADEON_BUS_CNTL1		0x0034
+#	define RADEON_PMI_BM_DIS		(1 << 2)
+#	define RADEON_PMI_INT_DIS		(1 << 3)
+
+#define RV370_BUS_CNTL			0x004c
+#	define RV370_PMI_BM_DIS		        (1 << 5)
+#	define RV370_PMI_INT_DIS		(1 << 6)
+
+#define RADEON_MSI_REARM_EN		0x0160
+/* rv370/rv380, rv410, r423/r430/r480, r5xx */
+#	define RV370_MSI_REARM_EN		(1 << 0)
 
 #define RADEON_CLOCK_CNTL_DATA		0x000c
 #	define RADEON_PLL_WR_EN			(1 << 7)
@@ -913,6 +937,7 @@ extern int r300_do_cp_cmdbuf(struct drm_device *dev,
 
 #define RADEON_AIC_CNTL			0x01d0
 #	define RADEON_PCIGART_TRANSLATE_EN	(1 << 0)
+#	define RS480_MSI_REARM	                (1 << 3)
 #define RADEON_AIC_STAT			0x01d4
 #define RADEON_AIC_PT_BASE		0x01d8
 #define RADEON_AIC_LO_ADDR		0x01dc
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 401cc8b7e88c..da04109741e8 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -84,18 +84,18 @@
 	{0x1002, 0x5462, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x5464, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x5657, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5548, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5549, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x554A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x554B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x554C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x554D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x554E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x554F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5550, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5551, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5552, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5554, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5548, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5549, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x554A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x554B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x554C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x554D, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x554E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x554F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5550, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5551, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5552, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5554, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x564A, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x564B, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x564F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
@@ -124,16 +124,16 @@
 	{0x1002, 0x5b65, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV380|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5c61, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280|RADEON_IS_MOBILITY}, \
 	{0x1002, 0x5c63, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV280|RADEON_IS_MOBILITY}, \
-	{0x1002, 0x5d48, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5d49, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5d4a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5d4c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5d4d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5d4e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5d4f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5d50, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5d52, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
-	{0x1002, 0x5d57, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R420|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5d48, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5d49, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5d4a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5d4c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5d4d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5d4e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5d4f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5d50, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5d52, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x5d57, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R423|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5e48, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5e4a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x5e4b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV410|RADEON_NEW_MEMMAP}, \
-- 
cgit v1.2.3


From 5b775f672cc993ba9dba5626811ab1f2ac42883b Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@suse.de>
Date: Tue, 26 Aug 2008 16:22:06 -0700
Subject: USB: add USB test and measurement class driver

This driver was originaly written by Stefan Kopp, but massively
reworked by Greg for submission.

Thanks to Felipe Balbi <me@felipebalbi.com> for lots of work in cleaning
up this driver.

Thanks to Oliver Neukum <oliver@neukum.org> for reviewing previous
versions and pointing out problems.


Cc: Stefan Kopp <stefan_kopp@agilent.com>
Cc: Marcel Janssen <korgull@home.nl>
Cc: Felipe Balbi <me@felipebalbi.com>
Cc: Oliver Neukum <oliver@neukum.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 Documentation/ABI/stable/sysfs-driver-usb-usbtmc |   62 ++
 Documentation/devices.txt                        |    3 +
 Documentation/ioctl-number.txt                   |    2 +
 drivers/usb/class/Kconfig                        |   10 +
 drivers/usb/class/Makefile                       |    1 +
 drivers/usb/class/usbtmc.c                       | 1087 ++++++++++++++++++++++
 include/linux/usb/Kbuild                         |    2 +-
 include/linux/usb/tmc.h                          |   43 +
 8 files changed, 1209 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/ABI/stable/sysfs-driver-usb-usbtmc
 create mode 100644 drivers/usb/class/usbtmc.c
 create mode 100644 include/linux/usb/tmc.h

(limited to 'include')

diff --git a/Documentation/ABI/stable/sysfs-driver-usb-usbtmc b/Documentation/ABI/stable/sysfs-driver-usb-usbtmc
new file mode 100644
index 000000000000..9a75fb22187d
--- /dev/null
+++ b/Documentation/ABI/stable/sysfs-driver-usb-usbtmc
@@ -0,0 +1,62 @@
+What:		/sys/bus/usb/drivers/usbtmc/devices/*/interface_capabilities
+What:		/sys/bus/usb/drivers/usbtmc/devices/*/device_capabilities
+Date:		August 2008
+Contact:	Greg Kroah-Hartman <gregkh@suse.de>
+Description:
+		These files show the various USB TMC capabilities as described
+		by the device itself.  The full description of the bitfields
+		can be found in the USB TMC documents from the USB-IF entitled
+		"Universal Serial Bus Test and Measurement Class Specification
+		(USBTMC) Revision 1.0" section 4.2.1.8.
+
+		The files are read only.
+
+
+What:		/sys/bus/usb/drivers/usbtmc/devices/*/usb488_interface_capabilities
+What:		/sys/bus/usb/drivers/usbtmc/devices/*/usb488_device_capabilities
+Date:		August 2008
+Contact:	Greg Kroah-Hartman <gregkh@suse.de>
+Description:
+		These files show the various USB TMC capabilities as described
+		by the device itself.  The full description of the bitfields
+		can be found in the USB TMC documents from the USB-IF entitled
+		"Universal Serial Bus Test and Measurement Class, Subclass
+		USB488 Specification (USBTMC-USB488) Revision 1.0" section
+		4.2.2.
+
+		The files are read only.
+
+
+What:		/sys/bus/usb/drivers/usbtmc/devices/*/TermChar
+Date:		August 2008
+Contact:	Greg Kroah-Hartman <gregkh@suse.de>
+Description:
+		This file is the TermChar value to be sent to the USB TMC
+		device as described by the document, "Universal Serial Bus Test
+		and Measurement Class Specification
+		(USBTMC) Revision 1.0" as published by the USB-IF.
+
+		Note that the TermCharEnabled file determines if this value is
+		sent to the device or not.
+
+
+What:		/sys/bus/usb/drivers/usbtmc/devices/*/TermCharEnabled
+Date:		August 2008
+Contact:	Greg Kroah-Hartman <gregkh@suse.de>
+Description:
+		This file determines if the TermChar is to be sent to the
+		device on every transaction or not.  For more details about
+		this, please see the document, "Universal Serial Bus Test and
+		Measurement Class Specification (USBTMC) Revision 1.0" as
+		published by the USB-IF.
+
+
+What:		/sys/bus/usb/drivers/usbtmc/devices/*/auto_abort
+Date:		August 2008
+Contact:	Greg Kroah-Hartman <gregkh@suse.de>
+Description:
+		This file determines if the the transaction of the USB TMC
+		device is to be automatically aborted if there is any error.
+		For more details about this, please see the document,
+		"Universal Serial Bus Test and Measurement Class Specification
+		(USBTMC) Revision 1.0" as published by the USB-IF.
diff --git a/Documentation/devices.txt b/Documentation/devices.txt
index 05c80645e4ee..2be08240ee80 100644
--- a/Documentation/devices.txt
+++ b/Documentation/devices.txt
@@ -2571,6 +2571,9 @@ Your cooperation is appreciated.
 		160 = /dev/usb/legousbtower0	1st USB Legotower device
 		    ...
 		175 = /dev/usb/legousbtower15	16th USB Legotower device
+		176 = /dev/usb/usbtmc1	First USB TMC device
+		   ...
+		192 = /dev/usb/usbtmc16	16th USB TMC device
 		240 = /dev/usb/dabusb0	First daubusb device
 		    ...
 		243 = /dev/usb/dabusb3	Fourth dabusb device
diff --git a/Documentation/ioctl-number.txt b/Documentation/ioctl-number.txt
index 1c6b545635a2..f8deb85eef6e 100644
--- a/Documentation/ioctl-number.txt
+++ b/Documentation/ioctl-number.txt
@@ -110,6 +110,8 @@ Code	Seq#	Include File		Comments
 'W'	00-1F	linux/wanrouter.h	conflict!
 'X'	all	linux/xfs_fs.h
 'Y'	all	linux/cyclades.h
+'['	00-07	linux/usb/usbtmc.h	USB Test and Measurement Devices
+					<mailto:gregkh@suse.de>
 'a'	all				ATM on linux
 					<http://lrcwww.epfl.ch/linux-atm/magic.html>
 'b'	00-FF				bit3 vme host bridge
diff --git a/drivers/usb/class/Kconfig b/drivers/usb/class/Kconfig
index 66f17ed88cb5..2519e320098f 100644
--- a/drivers/usb/class/Kconfig
+++ b/drivers/usb/class/Kconfig
@@ -40,3 +40,13 @@ config USB_WDM
 	  To compile this driver as a module, choose M here: the
 	  module will be called cdc-wdm.
 
+config USB_TMC
+	tristate "USB Test and Measurement Class support"
+	depends on USB
+	help
+	  Say Y here if you want to connect a USB device that follows
+	  the USB.org specification for USB Test and Measurement devices
+	  to your computer's USB port.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called usbtmc.
diff --git a/drivers/usb/class/Makefile b/drivers/usb/class/Makefile
index 535d59a30600..32e85277b5cf 100644
--- a/drivers/usb/class/Makefile
+++ b/drivers/usb/class/Makefile
@@ -6,3 +6,4 @@
 obj-$(CONFIG_USB_ACM)		+= cdc-acm.o
 obj-$(CONFIG_USB_PRINTER)	+= usblp.o
 obj-$(CONFIG_USB_WDM)		+= cdc-wdm.o
+obj-$(CONFIG_USB_TMC)		+= usbtmc.o
diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
new file mode 100644
index 000000000000..543811f6e6e8
--- /dev/null
+++ b/drivers/usb/class/usbtmc.c
@@ -0,0 +1,1087 @@
+/**
+ * drivers/usb/class/usbtmc.c - USB Test & Measurment class driver
+ *
+ * Copyright (C) 2007 Stefan Kopp, Gechingen, Germany
+ * Copyright (C) 2008 Novell, Inc.
+ * Copyright (C) 2008 Greg Kroah-Hartman <gregkh@suse.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * The GNU General Public License is available at
+ * http://www.gnu.org/copyleft/gpl.html.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/kref.h>
+#include <linux/mutex.h>
+#include <linux/usb.h>
+#include <linux/usb/tmc.h>
+
+
+#define USBTMC_MINOR_BASE	176
+
+/*
+ * Size of driver internal IO buffer. Must be multiple of 4 and at least as
+ * large as wMaxPacketSize (which is usually 512 bytes).
+ */
+#define USBTMC_SIZE_IOBUFFER	2048
+
+/* Default USB timeout (in milliseconds) */
+#define USBTMC_TIMEOUT		10
+
+/*
+ * Maximum number of read cycles to empty bulk in endpoint during CLEAR and
+ * ABORT_BULK_IN requests. Ends the loop if (for whatever reason) a short
+ * packet is never read.
+ */
+#define USBTMC_MAX_READS_TO_CLEAR_BULK_IN	100
+
+static struct usb_device_id usbtmc_devices[] = {
+	{ USB_INTERFACE_INFO(USB_CLASS_APP_SPEC, 3, 0), },
+	{ 0, } /* terminating entry */
+};
+
+/*
+ * This structure is the capabilities for the device
+ * See section 4.2.1.8 of the USBTMC specification for details.
+ */
+struct usbtmc_dev_capabilities {
+	__u8 interface_capabilities;
+	__u8 device_capabilities;
+	__u8 usb488_interface_capabilities;
+	__u8 usb488_device_capabilities;
+};
+
+/* This structure holds private data for each USBTMC device. One copy is
+ * allocated for each USBTMC device in the driver's probe function.
+ */
+struct usbtmc_device_data {
+	const struct usb_device_id *id;
+	struct usb_device *usb_dev;
+	struct usb_interface *intf;
+
+	unsigned int bulk_in;
+	unsigned int bulk_out;
+
+	u8 bTag;
+	u8 bTag_last_write;	/* needed for abort */
+	u8 bTag_last_read;	/* needed for abort */
+
+	/* attributes from the USB TMC spec for this device */
+	u8 TermChar;
+	bool TermCharEnabled;
+	bool auto_abort;
+
+	struct usbtmc_dev_capabilities	capabilities;
+	struct kref kref;
+	struct mutex io_mutex;	/* only one i/o function running at a time */
+};
+#define to_usbtmc_data(d) container_of(d, struct usbtmc_device_data, kref)
+
+/* Forward declarations */
+static struct usb_driver usbtmc_driver;
+
+static void usbtmc_delete(struct kref *kref)
+{
+	struct usbtmc_device_data *data = to_usbtmc_data(kref);
+
+	usb_put_dev(data->usb_dev);
+	kfree(data);
+}
+
+static int usbtmc_open(struct inode *inode, struct file *filp)
+{
+	struct usb_interface *intf;
+	struct usbtmc_device_data *data;
+	int retval = -ENODEV;
+
+	intf = usb_find_interface(&usbtmc_driver, iminor(inode));
+	if (!intf) {
+		printk(KERN_ERR KBUILD_MODNAME
+		       ": can not find device for minor %d", iminor(inode));
+		goto exit;
+	}
+
+	data = usb_get_intfdata(intf);
+	kref_get(&data->kref);
+
+	/* Store pointer in file structure's private data field */
+	filp->private_data = data;
+
+exit:
+	return retval;
+}
+
+static int usbtmc_release(struct inode *inode, struct file *file)
+{
+	struct usbtmc_device_data *data = file->private_data;
+
+	kref_put(&data->kref, usbtmc_delete);
+	return 0;
+}
+
+static int usbtmc_ioctl_abort_bulk_in(struct usbtmc_device_data *data)
+{
+	char *buffer;
+	struct device *dev;
+	int rv;
+	int n;
+	int actual;
+	struct usb_host_interface *current_setting;
+	int max_size;
+
+	dev = &data->intf->dev;
+	buffer = kmalloc(USBTMC_SIZE_IOBUFFER, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	rv = usb_control_msg(data->usb_dev,
+			     usb_rcvctrlpipe(data->usb_dev, 0),
+			     USBTMC_REQUEST_INITIATE_ABORT_BULK_IN,
+			     USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_ENDPOINT,
+			     data->bTag_last_read, data->bulk_in,
+			     buffer, 2, USBTMC_TIMEOUT);
+
+	if (rv < 0) {
+		dev_err(dev, "usb_control_msg returned %d\n", rv);
+		goto exit;
+	}
+
+	dev_dbg(dev, "INITIATE_ABORT_BULK_IN returned %x\n", buffer[0]);
+
+	if (buffer[0] == USBTMC_STATUS_FAILED) {
+		rv = 0;
+		goto exit;
+	}
+
+	if (buffer[0] != USBTMC_STATUS_SUCCESS) {
+		dev_err(dev, "INITIATE_ABORT_BULK_IN returned %x\n",
+			buffer[0]);
+		rv = -EPERM;
+		goto exit;
+	}
+
+	max_size = 0;
+	current_setting = data->intf->cur_altsetting;
+	for (n = 0; n < current_setting->desc.bNumEndpoints; n++)
+		if (current_setting->endpoint[n].desc.bEndpointAddress ==
+			data->bulk_in)
+			max_size = le16_to_cpu(current_setting->endpoint[n].
+						desc.wMaxPacketSize);
+
+	if (max_size == 0) {
+		dev_err(dev, "Couldn't get wMaxPacketSize\n");
+		rv = -EPERM;
+		goto exit;
+	}
+
+	dev_dbg(&data->intf->dev, "wMaxPacketSize is %d\n", max_size);
+
+	n = 0;
+
+	do {
+		dev_dbg(dev, "Reading from bulk in EP\n");
+
+		rv = usb_bulk_msg(data->usb_dev,
+				  usb_rcvbulkpipe(data->usb_dev,
+						  data->bulk_in),
+				  buffer, USBTMC_SIZE_IOBUFFER,
+				  &actual, USBTMC_TIMEOUT);
+
+		n++;
+
+		if (rv < 0) {
+			dev_err(dev, "usb_bulk_msg returned %d\n", rv);
+			goto exit;
+		}
+	} while ((actual == max_size) &&
+		 (n < USBTMC_MAX_READS_TO_CLEAR_BULK_IN));
+
+	if (actual == max_size) {
+		dev_err(dev, "Couldn't clear device buffer within %d cycles\n",
+			USBTMC_MAX_READS_TO_CLEAR_BULK_IN);
+		rv = -EPERM;
+		goto exit;
+	}
+
+	n = 0;
+
+usbtmc_abort_bulk_in_status:
+	rv = usb_control_msg(data->usb_dev,
+			     usb_rcvctrlpipe(data->usb_dev, 0),
+			     USBTMC_REQUEST_CHECK_ABORT_BULK_IN_STATUS,
+			     USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_ENDPOINT,
+			     0, data->bulk_in, buffer, 0x08,
+			     USBTMC_TIMEOUT);
+
+	if (rv < 0) {
+		dev_err(dev, "usb_control_msg returned %d\n", rv);
+		goto exit;
+	}
+
+	dev_dbg(dev, "INITIATE_ABORT_BULK_IN returned %x\n", buffer[0]);
+
+	if (buffer[0] == USBTMC_STATUS_SUCCESS) {
+		rv = 0;
+		goto exit;
+	}
+
+	if (buffer[0] != USBTMC_STATUS_PENDING) {
+		dev_err(dev, "INITIATE_ABORT_BULK_IN returned %x\n", buffer[0]);
+		rv = -EPERM;
+		goto exit;
+	}
+
+	if (buffer[1] == 1)
+		do {
+			dev_dbg(dev, "Reading from bulk in EP\n");
+
+			rv = usb_bulk_msg(data->usb_dev,
+					  usb_rcvbulkpipe(data->usb_dev,
+							  data->bulk_in),
+					  buffer, USBTMC_SIZE_IOBUFFER,
+					  &actual, USBTMC_TIMEOUT);
+
+			n++;
+
+			if (rv < 0) {
+				dev_err(dev, "usb_bulk_msg returned %d\n", rv);
+				goto exit;
+			}
+		} while ((actual = max_size) &&
+			 (n < USBTMC_MAX_READS_TO_CLEAR_BULK_IN));
+
+	if (actual == max_size) {
+		dev_err(dev, "Couldn't clear device buffer within %d cycles\n",
+			USBTMC_MAX_READS_TO_CLEAR_BULK_IN);
+		rv = -EPERM;
+		goto exit;
+	}
+
+	goto usbtmc_abort_bulk_in_status;
+
+exit:
+	kfree(buffer);
+	return rv;
+
+}
+
+static int usbtmc_ioctl_abort_bulk_out(struct usbtmc_device_data *data)
+{
+	struct device *dev;
+	u8 *buffer;
+	int rv;
+	int n;
+
+	dev = &data->intf->dev;
+
+	buffer = kmalloc(8, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	rv = usb_control_msg(data->usb_dev,
+			     usb_rcvctrlpipe(data->usb_dev, 0),
+			     USBTMC_REQUEST_INITIATE_ABORT_BULK_OUT,
+			     USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_ENDPOINT,
+			     data->bTag_last_write, data->bulk_out,
+			     buffer, 2, USBTMC_TIMEOUT);
+
+	if (rv < 0) {
+		dev_err(dev, "usb_control_msg returned %d\n", rv);
+		goto exit;
+	}
+
+	dev_dbg(dev, "INITIATE_ABORT_BULK_OUT returned %x\n", buffer[0]);
+
+	if (buffer[0] != USBTMC_STATUS_SUCCESS) {
+		dev_err(dev, "INITIATE_ABORT_BULK_OUT returned %x\n",
+			buffer[0]);
+		rv = -EPERM;
+		goto exit;
+	}
+
+	n = 0;
+
+usbtmc_abort_bulk_out_check_status:
+	rv = usb_control_msg(data->usb_dev,
+			     usb_rcvctrlpipe(data->usb_dev, 0),
+			     USBTMC_REQUEST_CHECK_ABORT_BULK_OUT_STATUS,
+			     USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_ENDPOINT,
+			     0, data->bulk_out, buffer, 0x08,
+			     USBTMC_TIMEOUT);
+	n++;
+	if (rv < 0) {
+		dev_err(dev, "usb_control_msg returned %d\n", rv);
+		goto exit;
+	}
+
+	dev_dbg(dev, "CHECK_ABORT_BULK_OUT returned %x\n", buffer[0]);
+
+	if (buffer[0] == USBTMC_STATUS_SUCCESS)
+		goto usbtmc_abort_bulk_out_clear_halt;
+
+	if ((buffer[0] == USBTMC_STATUS_PENDING) &&
+	    (n < USBTMC_MAX_READS_TO_CLEAR_BULK_IN))
+		goto usbtmc_abort_bulk_out_check_status;
+
+	rv = -EPERM;
+	goto exit;
+
+usbtmc_abort_bulk_out_clear_halt:
+	rv = usb_control_msg(data->usb_dev,
+			     usb_sndctrlpipe(data->usb_dev, 0),
+			     USB_REQ_CLEAR_FEATURE,
+			     USB_DIR_OUT | USB_TYPE_STANDARD |
+			     USB_RECIP_ENDPOINT,
+			     USB_ENDPOINT_HALT, data->bulk_out, buffer,
+			     0, USBTMC_TIMEOUT);
+
+	if (rv < 0) {
+		dev_err(dev, "usb_control_msg returned %d\n", rv);
+		goto exit;
+	}
+	rv = 0;
+
+exit:
+	kfree(buffer);
+	return rv;
+}
+
+static ssize_t usbtmc_read(struct file *filp, char __user *buf,
+			   size_t count, loff_t *f_pos)
+{
+	struct usbtmc_device_data *data;
+	struct device *dev;
+	unsigned long int n_characters;
+	u8 *buffer;
+	int actual;
+	int done;
+	int remaining;
+	int retval;
+	int this_part;
+
+	/* Get pointer to private data structure */
+	data = filp->private_data;
+	dev = &data->intf->dev;
+
+	buffer = kmalloc(USBTMC_SIZE_IOBUFFER, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	mutex_lock(&data->io_mutex);
+
+	remaining = count;
+	done = 0;
+
+	while (remaining > 0) {
+		if (remaining > USBTMC_SIZE_IOBUFFER - 12 - 3)
+			this_part = USBTMC_SIZE_IOBUFFER - 12 - 3;
+		else
+			this_part = remaining;
+
+		/* Setup IO buffer for DEV_DEP_MSG_IN message
+		 * Refer to class specs for details
+		 */
+		buffer[0] = 2;
+		buffer[1] = data->bTag;
+		buffer[2] = ~(data->bTag);
+		buffer[3] = 0; /* Reserved */
+		buffer[4] = (this_part - 12 - 3) & 255;
+		buffer[5] = ((this_part - 12 - 3) >> 8) & 255;
+		buffer[6] = ((this_part - 12 - 3) >> 16) & 255;
+		buffer[7] = ((this_part - 12 - 3) >> 24) & 255;
+		buffer[8] = data->TermCharEnabled * 2;
+		/* Use term character? */
+		buffer[9] = data->TermChar;
+		buffer[10] = 0; /* Reserved */
+		buffer[11] = 0; /* Reserved */
+
+		/* Send bulk URB */
+		retval = usb_bulk_msg(data->usb_dev,
+				      usb_sndbulkpipe(data->usb_dev,
+						      data->bulk_out),
+				      buffer, 12, &actual, USBTMC_TIMEOUT);
+
+		/* Store bTag (in case we need to abort) */
+		data->bTag_last_write = data->bTag;
+
+		/* Increment bTag -- and increment again if zero */
+		data->bTag++;
+		if (!data->bTag)
+			(data->bTag)++;
+
+		if (retval < 0) {
+			dev_err(dev, "usb_bulk_msg returned %d\n", retval);
+			if (data->auto_abort)
+				usbtmc_ioctl_abort_bulk_out(data);
+			goto exit;
+		}
+
+		/* Send bulk URB */
+		retval = usb_bulk_msg(data->usb_dev,
+				      usb_rcvbulkpipe(data->usb_dev,
+						      data->bulk_in),
+				      buffer, USBTMC_SIZE_IOBUFFER, &actual,
+				      USBTMC_TIMEOUT);
+
+		/* Store bTag (in case we need to abort) */
+		data->bTag_last_read = data->bTag;
+
+		if (retval < 0) {
+			dev_err(dev, "Unable to read data, error %d\n", retval);
+			if (data->auto_abort)
+				usbtmc_ioctl_abort_bulk_in(data);
+			goto exit;
+		}
+
+		/* How many characters did the instrument send? */
+		n_characters = buffer[4] +
+			       (buffer[5] << 8) +
+			       (buffer[6] << 16) +
+			       (buffer[7] << 24);
+
+		/* Copy buffer to user space */
+		if (copy_to_user(buf + done, &buffer[12], n_characters)) {
+			/* There must have been an addressing problem */
+			retval = -EFAULT;
+			goto exit;
+		}
+
+		done += n_characters;
+		if (n_characters < USBTMC_SIZE_IOBUFFER)
+			remaining = 0;
+	}
+
+	/* Update file position value */
+	*f_pos = *f_pos + done;
+	retval = done;
+
+exit:
+	mutex_unlock(&data->io_mutex);
+	kfree(buffer);
+	return retval;
+}
+
+static ssize_t usbtmc_write(struct file *filp, const char __user *buf,
+			    size_t count, loff_t *f_pos)
+{
+	struct usbtmc_device_data *data;
+	u8 *buffer;
+	int retval;
+	int actual;
+	unsigned long int n_bytes;
+	int n;
+	int remaining;
+	int done;
+	int this_part;
+
+	data = filp->private_data;
+
+	buffer = kmalloc(USBTMC_SIZE_IOBUFFER, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	mutex_lock(&data->io_mutex);
+
+	remaining = count;
+	done = 0;
+
+	while (remaining > 0) {
+		if (remaining > USBTMC_SIZE_IOBUFFER - 12) {
+			this_part = USBTMC_SIZE_IOBUFFER - 12;
+			buffer[8] = 0;
+		} else {
+			this_part = remaining;
+			buffer[8] = 1;
+		}
+
+		/* Setup IO buffer for DEV_DEP_MSG_OUT message */
+		buffer[0] = 1;
+		buffer[1] = data->bTag;
+		buffer[2] = ~(data->bTag);
+		buffer[3] = 0; /* Reserved */
+		buffer[4] = this_part & 255;
+		buffer[5] = (this_part >> 8) & 255;
+		buffer[6] = (this_part >> 16) & 255;
+		buffer[7] = (this_part >> 24) & 255;
+		/* buffer[8] is set above... */
+		buffer[9] = 0; /* Reserved */
+		buffer[10] = 0; /* Reserved */
+		buffer[11] = 0; /* Reserved */
+
+		if (copy_from_user(&buffer[12], buf + done, this_part)) {
+			retval = -EFAULT;
+			goto exit;
+		}
+
+		n_bytes = 12 + this_part;
+		if (this_part % 4)
+			n_bytes += 4 - this_part % 4;
+			for (n = 12 + this_part; n < n_bytes; n++)
+				buffer[n] = 0;
+
+		retval = usb_bulk_msg(data->usb_dev,
+				      usb_sndbulkpipe(data->usb_dev,
+						      data->bulk_out),
+				      buffer, n_bytes, &actual, USBTMC_TIMEOUT);
+
+		data->bTag_last_write = data->bTag;
+		data->bTag++;
+
+		if (!data->bTag)
+			data->bTag++;
+
+		if (retval < 0) {
+			dev_err(&data->intf->dev,
+				"Unable to send data, error %d\n", retval);
+			if (data->auto_abort)
+				usbtmc_ioctl_abort_bulk_out(data);
+			goto exit;
+		}
+
+		remaining -= this_part;
+		done += this_part;
+	}
+
+	retval = count;
+exit:
+	mutex_unlock(&data->io_mutex);
+	kfree(buffer);
+	return retval;
+}
+
+static int usbtmc_ioctl_clear(struct usbtmc_device_data *data)
+{
+	struct usb_host_interface *current_setting;
+	struct usb_endpoint_descriptor *desc;
+	struct device *dev;
+	u8 *buffer;
+	int rv;
+	int n;
+	int actual;
+	int max_size;
+
+	dev = &data->intf->dev;
+
+	dev_dbg(dev, "Sending INITIATE_CLEAR request\n");
+
+	buffer = kmalloc(USBTMC_SIZE_IOBUFFER, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	rv = usb_control_msg(data->usb_dev,
+			     usb_rcvctrlpipe(data->usb_dev, 0),
+			     USBTMC_REQUEST_INITIATE_CLEAR,
+			     USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
+			     0, 0, buffer, 1, USBTMC_TIMEOUT);
+	if (rv < 0) {
+		dev_err(dev, "usb_control_msg returned %d\n", rv);
+		goto exit;
+	}
+
+	dev_dbg(dev, "INITIATE_CLEAR returned %x\n", buffer[0]);
+
+	if (buffer[0] != USBTMC_STATUS_SUCCESS) {
+		dev_err(dev, "INITIATE_CLEAR returned %x\n", buffer[0]);
+		rv = -EPERM;
+		goto exit;
+	}
+
+	max_size = 0;
+	current_setting = data->intf->cur_altsetting;
+	for (n = 0; n < current_setting->desc.bNumEndpoints; n++) {
+		desc = &current_setting->endpoint[n].desc;
+		if (desc->bEndpointAddress == data->bulk_in)
+			max_size = le16_to_cpu(desc->wMaxPacketSize);
+	}
+
+	if (max_size == 0) {
+		dev_err(dev, "Couldn't get wMaxPacketSize\n");
+		rv = -EPERM;
+		goto exit;
+	}
+
+	dev_dbg(dev, "wMaxPacketSize is %d\n", max_size);
+
+	n = 0;
+
+usbtmc_clear_check_status:
+
+	dev_dbg(dev, "Sending CHECK_CLEAR_STATUS request\n");
+
+	rv = usb_control_msg(data->usb_dev,
+			     usb_rcvctrlpipe(data->usb_dev, 0),
+			     USBTMC_REQUEST_CHECK_CLEAR_STATUS,
+			     USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
+			     0, 0, buffer, 2, USBTMC_TIMEOUT);
+	if (rv < 0) {
+		dev_err(dev, "usb_control_msg returned %d\n", rv);
+		goto exit;
+	}
+
+	dev_dbg(dev, "CHECK_CLEAR_STATUS returned %x\n", buffer[0]);
+
+	if (buffer[0] == USBTMC_STATUS_SUCCESS)
+		goto usbtmc_clear_bulk_out_halt;
+
+	if (buffer[0] != USBTMC_STATUS_PENDING) {
+		dev_err(dev, "CHECK_CLEAR_STATUS returned %x\n", buffer[0]);
+		rv = -EPERM;
+		goto exit;
+	}
+
+	if (buffer[1] == 1)
+		do {
+			dev_dbg(dev, "Reading from bulk in EP\n");
+
+			rv = usb_bulk_msg(data->usb_dev,
+					  usb_rcvbulkpipe(data->usb_dev,
+							  data->bulk_in),
+					  buffer, USBTMC_SIZE_IOBUFFER,
+					  &actual, USBTMC_TIMEOUT);
+			n++;
+
+			if (rv < 0) {
+				dev_err(dev, "usb_control_msg returned %d\n",
+					rv);
+				goto exit;
+			}
+		} while ((actual == max_size) &&
+			  (n < USBTMC_MAX_READS_TO_CLEAR_BULK_IN));
+
+	if (actual == max_size) {
+		dev_err(dev, "Couldn't clear device buffer within %d cycles\n",
+			USBTMC_MAX_READS_TO_CLEAR_BULK_IN);
+		rv = -EPERM;
+		goto exit;
+	}
+
+	goto usbtmc_clear_check_status;
+
+usbtmc_clear_bulk_out_halt:
+
+	rv = usb_control_msg(data->usb_dev,
+			     usb_sndctrlpipe(data->usb_dev, 0),
+			     USB_REQ_CLEAR_FEATURE,
+			     USB_DIR_OUT | USB_TYPE_STANDARD |
+			     USB_RECIP_ENDPOINT,
+			     USB_ENDPOINT_HALT,
+			     data->bulk_out, buffer, 0,
+			     USBTMC_TIMEOUT);
+	if (rv < 0) {
+		dev_err(dev, "usb_control_msg returned %d\n", rv);
+		goto exit;
+	}
+	rv = 0;
+
+exit:
+	kfree(buffer);
+	return rv;
+}
+
+static int usbtmc_ioctl_clear_out_halt(struct usbtmc_device_data *data)
+{
+	u8 *buffer;
+	int rv;
+
+	buffer = kmalloc(2, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	rv = usb_control_msg(data->usb_dev,
+			     usb_sndctrlpipe(data->usb_dev, 0),
+			     USB_REQ_CLEAR_FEATURE,
+			     USB_DIR_OUT | USB_TYPE_STANDARD |
+			     USB_RECIP_ENDPOINT,
+			     USB_ENDPOINT_HALT, data->bulk_out,
+			     buffer, 0, USBTMC_TIMEOUT);
+
+	if (rv < 0) {
+		dev_err(&data->usb_dev->dev, "usb_control_msg returned %d\n",
+			rv);
+		goto exit;
+	}
+	rv = 0;
+
+exit:
+	kfree(buffer);
+	return rv;
+}
+
+static int usbtmc_ioctl_clear_in_halt(struct usbtmc_device_data *data)
+{
+	u8 *buffer;
+	int rv;
+
+	buffer = kmalloc(2, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	rv = usb_control_msg(data->usb_dev, usb_sndctrlpipe(data->usb_dev, 0),
+			     USB_REQ_CLEAR_FEATURE,
+			     USB_DIR_OUT | USB_TYPE_STANDARD |
+			     USB_RECIP_ENDPOINT,
+			     USB_ENDPOINT_HALT, data->bulk_in, buffer, 0,
+			     USBTMC_TIMEOUT);
+
+	if (rv < 0) {
+		dev_err(&data->usb_dev->dev, "usb_control_msg returned %d\n",
+			rv);
+		goto exit;
+	}
+	rv = 0;
+
+exit:
+	kfree(buffer);
+	return rv;
+}
+
+static int get_capabilities(struct usbtmc_device_data *data)
+{
+	struct device *dev = &data->usb_dev->dev;
+	char *buffer;
+	int rv;
+
+	buffer = kmalloc(0x18, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	rv = usb_control_msg(data->usb_dev, usb_rcvctrlpipe(data->usb_dev, 0),
+			     USBTMC_REQUEST_GET_CAPABILITIES,
+			     USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
+			     0, 0, buffer, 0x18, USBTMC_TIMEOUT);
+	if (rv < 0) {
+		dev_err(dev, "usb_control_msg returned %d\n", rv);
+		return rv;
+	}
+
+	dev_dbg(dev, "GET_CAPABILITIES returned %x\n", buffer[0]);
+	dev_dbg(dev, "Interface capabilities are %x\n", buffer[4]);
+	dev_dbg(dev, "Device capabilities are %x\n", buffer[5]);
+	dev_dbg(dev, "USB488 interface capabilities are %x\n", buffer[14]);
+	dev_dbg(dev, "USB488 device capabilities are %x\n", buffer[15]);
+	if (buffer[0] != USBTMC_STATUS_SUCCESS) {
+		dev_err(dev, "GET_CAPABILITIES returned %x\n", buffer[0]);
+		return -EPERM;
+	}
+
+	data->capabilities.interface_capabilities = buffer[4];
+	data->capabilities.device_capabilities = buffer[5];
+	data->capabilities.usb488_interface_capabilities = buffer[14];
+	data->capabilities.usb488_device_capabilities = buffer[15];
+
+	kfree(buffer);
+	return 0;
+}
+
+#define capability_attribute(name)					\
+static ssize_t show_##name(struct device *dev,				\
+			   struct device_attribute *attr, char *buf)	\
+{									\
+	struct usb_interface *intf = to_usb_interface(dev);		\
+	struct usbtmc_device_data *data = usb_get_intfdata(intf);	\
+									\
+	return sprintf(buf, "%d\n", data->capabilities.name);		\
+}									\
+static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
+
+capability_attribute(interface_capabilities);
+capability_attribute(device_capabilities);
+capability_attribute(usb488_interface_capabilities);
+capability_attribute(usb488_device_capabilities);
+
+static struct attribute *capability_attrs[] = {
+	&dev_attr_interface_capabilities.attr,
+	&dev_attr_device_capabilities.attr,
+	&dev_attr_usb488_interface_capabilities.attr,
+	&dev_attr_usb488_device_capabilities.attr,
+	NULL,
+};
+
+static struct attribute_group capability_attr_grp = {
+	.attrs = capability_attrs,
+};
+
+static ssize_t show_TermChar(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	struct usb_interface *intf = to_usb_interface(dev);
+	struct usbtmc_device_data *data = usb_get_intfdata(intf);
+
+	return sprintf(buf, "%c\n", data->TermChar);
+}
+
+static ssize_t store_TermChar(struct device *dev,
+			      struct device_attribute *attr,
+			      const char *buf, size_t count)
+{
+	struct usb_interface *intf = to_usb_interface(dev);
+	struct usbtmc_device_data *data = usb_get_intfdata(intf);
+
+	if (count < 1)
+		return -EINVAL;
+	data->TermChar = buf[0];
+	return count;
+}
+static DEVICE_ATTR(TermChar, S_IRUGO, show_TermChar, store_TermChar);
+
+#define data_attribute(name)						\
+static ssize_t show_##name(struct device *dev,				\
+			   struct device_attribute *attr, char *buf)	\
+{									\
+	struct usb_interface *intf = to_usb_interface(dev);		\
+	struct usbtmc_device_data *data = usb_get_intfdata(intf);	\
+									\
+	return sprintf(buf, "%d\n", data->name);			\
+}									\
+static ssize_t store_##name(struct device *dev,				\
+			    struct device_attribute *attr,		\
+			    const char *buf, size_t count)		\
+{									\
+	struct usb_interface *intf = to_usb_interface(dev);		\
+	struct usbtmc_device_data *data = usb_get_intfdata(intf);	\
+	ssize_t result;							\
+	unsigned val;							\
+									\
+	result = sscanf(buf, "%u\n", &val);				\
+	if (result != 1)						\
+		result = -EINVAL;					\
+	data->name = val;						\
+	if (result < 0)							\
+		return result;						\
+	else								\
+		return count;						\
+}									\
+static DEVICE_ATTR(name, S_IRUGO, show_##name, store_##name)
+
+data_attribute(TermCharEnabled);
+data_attribute(auto_abort);
+
+static struct attribute *data_attrs[] = {
+	&dev_attr_TermChar.attr,
+	&dev_attr_TermCharEnabled.attr,
+	&dev_attr_auto_abort.attr,
+	NULL,
+};
+
+static struct attribute_group data_attr_grp = {
+	.attrs = data_attrs,
+};
+
+static int usbtmc_ioctl_indicator_pulse(struct usbtmc_device_data *data)
+{
+	struct device *dev;
+	u8 *buffer;
+	int rv;
+
+	dev = &data->intf->dev;
+
+	buffer = kmalloc(2, GFP_KERNEL);
+	if (!buffer)
+		return -ENOMEM;
+
+	rv = usb_control_msg(data->usb_dev,
+			     usb_rcvctrlpipe(data->usb_dev, 0),
+			     USBTMC_REQUEST_INDICATOR_PULSE,
+			     USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
+			     0, 0, buffer, 0x01, USBTMC_TIMEOUT);
+
+	if (rv < 0) {
+		dev_err(dev, "usb_control_msg returned %d\n", rv);
+		goto exit;
+	}
+
+	dev_dbg(dev, "INDICATOR_PULSE returned %x\n", buffer[0]);
+
+	if (buffer[0] != USBTMC_STATUS_SUCCESS) {
+		dev_err(dev, "INDICATOR_PULSE returned %x\n", buffer[0]);
+		rv = -EPERM;
+		goto exit;
+	}
+	rv = 0;
+
+exit:
+	kfree(buffer);
+	return rv;
+}
+
+static long usbtmc_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct usbtmc_device_data *data;
+	int retval = -EBADRQC;
+
+	data = file->private_data;
+	mutex_lock(&data->io_mutex);
+
+	switch (cmd) {
+	case USBTMC_IOCTL_CLEAR_OUT_HALT:
+		retval = usbtmc_ioctl_clear_out_halt(data);
+
+	case USBTMC_IOCTL_CLEAR_IN_HALT:
+		retval = usbtmc_ioctl_clear_in_halt(data);
+
+	case USBTMC_IOCTL_INDICATOR_PULSE:
+		retval = usbtmc_ioctl_indicator_pulse(data);
+
+	case USBTMC_IOCTL_CLEAR:
+		retval = usbtmc_ioctl_clear(data);
+
+	case USBTMC_IOCTL_ABORT_BULK_OUT:
+		retval = usbtmc_ioctl_abort_bulk_out(data);
+
+	case USBTMC_IOCTL_ABORT_BULK_IN:
+		retval = usbtmc_ioctl_abort_bulk_in(data);
+	}
+
+	mutex_unlock(&data->io_mutex);
+	return retval;
+}
+
+static struct file_operations fops = {
+	.owner		= THIS_MODULE,
+	.read		= usbtmc_read,
+	.write		= usbtmc_write,
+	.open		= usbtmc_open,
+	.release	= usbtmc_release,
+	.unlocked_ioctl	= usbtmc_ioctl,
+};
+
+static struct usb_class_driver usbtmc_class = {
+	.name =		"usbtmc%d",
+	.fops =		&fops,
+	.minor_base =	USBTMC_MINOR_BASE,
+};
+
+
+static int usbtmc_probe(struct usb_interface *intf,
+			const struct usb_device_id *id)
+{
+	struct usbtmc_device_data *data;
+	struct usb_host_interface *iface_desc;
+	struct usb_endpoint_descriptor *endpoint;
+	int n;
+	int retcode;
+
+	dev_dbg(&intf->dev, "%s called\n", __func__);
+
+	data = kmalloc(sizeof(struct usbtmc_device_data), GFP_KERNEL);
+	if (!data) {
+		dev_err(&intf->dev, "Unable to allocate kernel memory\n");
+		return -ENOMEM;
+	}
+
+	data->intf = intf;
+	data->id = id;
+	data->usb_dev = usb_get_dev(interface_to_usbdev(intf));
+	usb_set_intfdata(intf, data);
+	kref_init(&data->kref);
+	mutex_init(&data->io_mutex);
+
+	/* Initialize USBTMC bTag and other fields */
+	data->bTag	= 1;
+	data->TermCharEnabled = 0;
+	data->TermChar = '\n';
+
+	/* USBTMC devices have only one setting, so use that */
+	iface_desc = data->intf->cur_altsetting;
+
+	/* Find bulk in endpoint */
+	for (n = 0; n < iface_desc->desc.bNumEndpoints; n++) {
+		endpoint = &iface_desc->endpoint[n].desc;
+
+		if (usb_endpoint_is_bulk_in(endpoint)) {
+			data->bulk_in = endpoint->bEndpointAddress;
+			dev_dbg(&intf->dev, "Found bulk in endpoint at %u\n",
+				data->bulk_in);
+			break;
+		}
+	}
+
+	/* Find bulk out endpoint */
+	for (n = 0; n < iface_desc->desc.bNumEndpoints; n++) {
+		endpoint = &iface_desc->endpoint[n].desc;
+
+		if (usb_endpoint_is_bulk_out(endpoint)) {
+			data->bulk_out = endpoint->bEndpointAddress;
+			dev_dbg(&intf->dev, "Found Bulk out endpoint at %u\n",
+				data->bulk_out);
+			break;
+		}
+	}
+
+	retcode = get_capabilities(data);
+	if (retcode)
+		dev_err(&intf->dev, "can't read capabilities\n");
+	else
+		retcode = sysfs_create_group(&intf->dev.kobj,
+					     &capability_attr_grp);
+
+	retcode = sysfs_create_group(&intf->dev.kobj, &data_attr_grp);
+
+	retcode = usb_register_dev(intf, &usbtmc_class);
+	if (retcode) {
+		dev_err(&intf->dev, "Not able to get a minor"
+			" (base %u, slice default): %d\n", USBTMC_MINOR_BASE,
+			retcode);
+		goto error_register;
+	}
+	dev_dbg(&intf->dev, "Using minor number %d\n", intf->minor);
+
+	return 0;
+
+error_register:
+	sysfs_remove_group(&intf->dev.kobj, &capability_attr_grp);
+	sysfs_remove_group(&intf->dev.kobj, &data_attr_grp);
+	kref_put(&data->kref, usbtmc_delete);
+	return retcode;
+}
+
+static void usbtmc_disconnect(struct usb_interface *intf)
+{
+	struct usbtmc_device_data *data;
+
+	dev_dbg(&intf->dev, "usbtmc_disconnect called\n");
+
+	data = usb_get_intfdata(intf);
+	usb_deregister_dev(intf, &usbtmc_class);
+	sysfs_remove_group(&intf->dev.kobj, &capability_attr_grp);
+	sysfs_remove_group(&intf->dev.kobj, &data_attr_grp);
+	kref_put(&data->kref, usbtmc_delete);
+}
+
+static struct usb_driver usbtmc_driver = {
+	.name		= "usbtmc",
+	.id_table	= usbtmc_devices,
+	.probe		= usbtmc_probe,
+	.disconnect	= usbtmc_disconnect
+};
+
+static int __init usbtmc_init(void)
+{
+	int retcode;
+
+	retcode = usb_register(&usbtmc_driver);
+	if (retcode)
+		printk(KERN_ERR KBUILD_MODNAME": Unable to register driver\n");
+	return retcode;
+}
+module_init(usbtmc_init);
+
+static void __exit usbtmc_exit(void)
+{
+	usb_deregister(&usbtmc_driver);
+}
+module_exit(usbtmc_exit);
+
+MODULE_LICENSE("GPL");
diff --git a/include/linux/usb/Kbuild b/include/linux/usb/Kbuild
index 42e84fc315e3..29fd73b0bffc 100644
--- a/include/linux/usb/Kbuild
+++ b/include/linux/usb/Kbuild
@@ -4,4 +4,4 @@ header-y += ch9.h
 header-y += gadgetfs.h
 header-y += midi.h
 header-y += g_printer.h
-
+header-y += tmc.h
diff --git a/include/linux/usb/tmc.h b/include/linux/usb/tmc.h
new file mode 100644
index 000000000000..c045ae12556c
--- /dev/null
+++ b/include/linux/usb/tmc.h
@@ -0,0 +1,43 @@
+/*
+ * Copyright (C) 2007 Stefan Kopp, Gechingen, Germany
+ * Copyright (C) 2008 Novell, Inc.
+ * Copyright (C) 2008 Greg Kroah-Hartman <gregkh@suse.de>
+ *
+ * This file holds USB constants defined by the USB Device Class
+ * Definition for Test and Measurement devices published by the USB-IF.
+ *
+ * It also has the ioctl definitions for the usbtmc kernel driver that
+ * userspace needs to know about.
+ */
+
+#ifndef __LINUX_USB_TMC_H
+#define __LINUX_USB_TMC_H
+
+/* USB TMC status values */
+#define USBTMC_STATUS_SUCCESS				0x01
+#define USBTMC_STATUS_PENDING				0x02
+#define USBTMC_STATUS_FAILED				0x80
+#define USBTMC_STATUS_TRANSFER_NOT_IN_PROGRESS		0x81
+#define USBTMC_STATUS_SPLIT_NOT_IN_PROGRESS		0x82
+#define USBTMC_STATUS_SPLIT_IN_PROGRESS			0x83
+
+/* USB TMC requests values */
+#define USBTMC_REQUEST_INITIATE_ABORT_BULK_OUT		1
+#define USBTMC_REQUEST_CHECK_ABORT_BULK_OUT_STATUS	2
+#define USBTMC_REQUEST_INITIATE_ABORT_BULK_IN		3
+#define USBTMC_REQUEST_CHECK_ABORT_BULK_IN_STATUS	4
+#define USBTMC_REQUEST_INITIATE_CLEAR			5
+#define USBTMC_REQUEST_CHECK_CLEAR_STATUS		6
+#define USBTMC_REQUEST_GET_CAPABILITIES			7
+#define USBTMC_REQUEST_INDICATOR_PULSE			64
+
+/* Request values for USBTMC driver's ioctl entry point */
+#define USBTMC_IOC_NR			91
+#define USBTMC_IOCTL_INDICATOR_PULSE	_IO(USBTMC_IOC_NR, 1)
+#define USBTMC_IOCTL_CLEAR		_IO(USBTMC_IOC_NR, 2)
+#define USBTMC_IOCTL_ABORT_BULK_OUT	_IO(USBTMC_IOC_NR, 3)
+#define USBTMC_IOCTL_ABORT_BULK_IN	_IO(USBTMC_IOC_NR, 4)
+#define USBTMC_IOCTL_CLEAR_OUT_HALT	_IO(USBTMC_IOC_NR, 6)
+#define USBTMC_IOCTL_CLEAR_IN_HALT	_IO(USBTMC_IOC_NR, 7)
+
+#endif
-- 
cgit v1.2.3


From 55b447bf79ad25591437d24b78caa9d0ae4fec82 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oliver@neukum.org>
Date: Tue, 29 Jul 2008 15:26:15 +0200
Subject: USB: kill URBs permanently

looking at usb_kill_urb() it seems to me that it is unnecessarily lenient.
In the use case of disconnect() you never want to use the URB again
(for the same device) But leaving urb->reject elevated will make it easier
to avoid races between read/write and disconnect.

Signed-off-by: Oliver Neukum <oneukum@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/usb/core/urb.c | 56 ++++++++++++++++++++++++++++++++++++++++++++------
 include/linux/usb.h    |  2 ++
 2 files changed, 52 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index 47111e88f791..a7945ab208c2 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -522,6 +522,7 @@ int usb_unlink_urb(struct urb *urb)
 }
 EXPORT_SYMBOL_GPL(usb_unlink_urb);
 
+static DEFINE_MUTEX(usb_reject_mutex);
 /**
  * usb_kill_urb - cancel a transfer request and wait for it to finish
  * @urb: pointer to URB describing a previously submitted request,
@@ -544,24 +545,67 @@ EXPORT_SYMBOL_GPL(usb_unlink_urb);
  */
 void usb_kill_urb(struct urb *urb)
 {
-	static DEFINE_MUTEX(reject_mutex);
-
 	might_sleep();
 	if (!(urb && urb->dev && urb->ep))
 		return;
-	mutex_lock(&reject_mutex);
+	mutex_lock(&usb_reject_mutex);
 	++urb->reject;
-	mutex_unlock(&reject_mutex);
+	mutex_unlock(&usb_reject_mutex);
 
 	usb_hcd_unlink_urb(urb, -ENOENT);
 	wait_event(usb_kill_urb_queue, atomic_read(&urb->use_count) == 0);
 
-	mutex_lock(&reject_mutex);
+	mutex_lock(&usb_reject_mutex);
 	--urb->reject;
-	mutex_unlock(&reject_mutex);
+	mutex_unlock(&usb_reject_mutex);
 }
 EXPORT_SYMBOL_GPL(usb_kill_urb);
 
+/**
+ * usb_poison_urb - reliably kill a transfer and prevent further use of an URB
+ * @urb: pointer to URB describing a previously submitted request,
+ *	may be NULL
+ *
+ * This routine cancels an in-progress request.  It is guaranteed that
+ * upon return all completion handlers will have finished and the URB
+ * will be totally idle and cannot be reused.  These features make
+ * this an ideal way to stop I/O in a disconnect() callback.
+ * If the request has not already finished or been unlinked
+ * the completion handler will see urb->status == -ENOENT.
+ *
+ * After and while the routine runs, attempts to resubmit the URB will fail
+ * with error -EPERM.  Thus even if the URB's completion handler always
+ * tries to resubmit, it will not succeed and the URB will become idle.
+ *
+ * This routine may not be used in an interrupt context (such as a bottom
+ * half or a completion handler), or when holding a spinlock, or in other
+ * situations where the caller can't schedule().
+ */
+void usb_poison_urb(struct urb *urb)
+{
+	might_sleep();
+	if (!(urb && urb->dev && urb->ep))
+		return;
+	mutex_lock(&usb_reject_mutex);
+	++urb->reject;
+	mutex_unlock(&usb_reject_mutex);
+
+	usb_hcd_unlink_urb(urb, -ENOENT);
+	wait_event(usb_kill_urb_queue, atomic_read(&urb->use_count) == 0);
+}
+EXPORT_SYMBOL_GPL(usb_poison_urb);
+
+void usb_unpoison_urb(struct urb *urb)
+{
+	if (!urb)
+		return;
+
+	mutex_lock(&usb_reject_mutex);
+	--urb->reject;
+	mutex_unlock(&usb_reject_mutex);
+}
+EXPORT_SYMBOL_GPL(usb_unpoison_urb);
+
 /**
  * usb_kill_anchored_urbs - cancel transfer requests en masse
  * @anchor: anchor the requests are bound to
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 94ac74aba6b6..3371c91e7ff4 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1459,6 +1459,8 @@ extern struct urb *usb_get_urb(struct urb *urb);
 extern int usb_submit_urb(struct urb *urb, gfp_t mem_flags);
 extern int usb_unlink_urb(struct urb *urb);
 extern void usb_kill_urb(struct urb *urb);
+extern void usb_poison_urb(struct urb *urb);
+extern void usb_unpoison_urb(struct urb *urb);
 extern void usb_kill_anchored_urbs(struct usb_anchor *anchor);
 extern void usb_unlink_anchored_urbs(struct usb_anchor *anchor);
 extern void usb_anchor_urb(struct urb *urb, struct usb_anchor *anchor);
-- 
cgit v1.2.3


From 6a2839bedc1502b3f0366cc3ad1099a1d92cf8fb Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oliver@neukum.org>
Date: Tue, 29 Jul 2008 16:18:47 +0200
Subject: USB: extend poisoning to anchors

this extends the poisoning concept to anchors. This way poisoning
will work with fire and forget drivers.

Signed-off-by: Oliver Neukum <oneukum@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/usb/core/urb.c | 57 ++++++++++++++++++++++++++++++++++++++++++--------
 include/linux/usb.h    |  2 ++
 2 files changed, 50 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index a7945ab208c2..eebc070c3cc7 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -10,6 +10,8 @@
 
 #define to_urb(d) container_of(d, struct urb, kref)
 
+static DEFINE_SPINLOCK(usb_reject_lock);
+
 static void urb_destroy(struct kref *kref)
 {
 	struct urb *urb = to_urb(kref);
@@ -127,6 +129,13 @@ void usb_anchor_urb(struct urb *urb, struct usb_anchor *anchor)
 	usb_get_urb(urb);
 	list_add_tail(&urb->anchor_list, &anchor->urb_list);
 	urb->anchor = anchor;
+
+	if (unlikely(anchor->poisoned)) {
+		spin_lock(&usb_reject_lock);
+		urb->reject++;
+		spin_unlock(&usb_reject_lock);
+	}
+
 	spin_unlock_irqrestore(&anchor->lock, flags);
 }
 EXPORT_SYMBOL_GPL(usb_anchor_urb);
@@ -522,7 +531,6 @@ int usb_unlink_urb(struct urb *urb)
 }
 EXPORT_SYMBOL_GPL(usb_unlink_urb);
 
-static DEFINE_MUTEX(usb_reject_mutex);
 /**
  * usb_kill_urb - cancel a transfer request and wait for it to finish
  * @urb: pointer to URB describing a previously submitted request,
@@ -548,16 +556,16 @@ void usb_kill_urb(struct urb *urb)
 	might_sleep();
 	if (!(urb && urb->dev && urb->ep))
 		return;
-	mutex_lock(&usb_reject_mutex);
+	spin_lock_irq(&usb_reject_lock);
 	++urb->reject;
-	mutex_unlock(&usb_reject_mutex);
+	spin_unlock_irq(&usb_reject_lock);
 
 	usb_hcd_unlink_urb(urb, -ENOENT);
 	wait_event(usb_kill_urb_queue, atomic_read(&urb->use_count) == 0);
 
-	mutex_lock(&usb_reject_mutex);
+	spin_lock_irq(&usb_reject_lock);
 	--urb->reject;
-	mutex_unlock(&usb_reject_mutex);
+	spin_unlock_irq(&usb_reject_lock);
 }
 EXPORT_SYMBOL_GPL(usb_kill_urb);
 
@@ -586,9 +594,9 @@ void usb_poison_urb(struct urb *urb)
 	might_sleep();
 	if (!(urb && urb->dev && urb->ep))
 		return;
-	mutex_lock(&usb_reject_mutex);
+	spin_lock_irq(&usb_reject_lock);
 	++urb->reject;
-	mutex_unlock(&usb_reject_mutex);
+	spin_unlock_irq(&usb_reject_lock);
 
 	usb_hcd_unlink_urb(urb, -ENOENT);
 	wait_event(usb_kill_urb_queue, atomic_read(&urb->use_count) == 0);
@@ -597,12 +605,14 @@ EXPORT_SYMBOL_GPL(usb_poison_urb);
 
 void usb_unpoison_urb(struct urb *urb)
 {
+	unsigned long flags;
+
 	if (!urb)
 		return;
 
-	mutex_lock(&usb_reject_mutex);
+	spin_lock_irqsave(&usb_reject_lock, flags);
 	--urb->reject;
-	mutex_unlock(&usb_reject_mutex);
+	spin_unlock_irqrestore(&usb_reject_lock, flags);
 }
 EXPORT_SYMBOL_GPL(usb_unpoison_urb);
 
@@ -633,6 +643,35 @@ void usb_kill_anchored_urbs(struct usb_anchor *anchor)
 }
 EXPORT_SYMBOL_GPL(usb_kill_anchored_urbs);
 
+
+/**
+ * usb_poison_anchored_urbs - cease all traffic from an anchor
+ * @anchor: anchor the requests are bound to
+ *
+ * this allows all outstanding URBs to be poisoned starting
+ * from the back of the queue. Newly added URBs will also be
+ * poisoned
+ */
+void usb_poison_anchored_urbs(struct usb_anchor *anchor)
+{
+	struct urb *victim;
+
+	spin_lock_irq(&anchor->lock);
+	anchor->poisoned = 1;
+	while (!list_empty(&anchor->urb_list)) {
+		victim = list_entry(anchor->urb_list.prev, struct urb,
+				    anchor_list);
+		/* we must make sure the URB isn't freed before we kill it*/
+		usb_get_urb(victim);
+		spin_unlock_irq(&anchor->lock);
+		/* this will unanchor the URB */
+		usb_poison_urb(victim);
+		usb_put_urb(victim);
+		spin_lock_irq(&anchor->lock);
+	}
+	spin_unlock_irq(&anchor->lock);
+}
+EXPORT_SYMBOL_GPL(usb_poison_anchored_urbs);
 /**
  * usb_unlink_anchored_urbs - asynchronously cancel transfer requests en masse
  * @anchor: anchor the requests are bound to
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 3371c91e7ff4..d97927970f54 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1135,6 +1135,7 @@ struct usb_anchor {
 	struct list_head urb_list;
 	wait_queue_head_t wait;
 	spinlock_t lock;
+	unsigned int poisoned:1;
 };
 
 static inline void init_usb_anchor(struct usb_anchor *anchor)
@@ -1462,6 +1463,7 @@ extern void usb_kill_urb(struct urb *urb);
 extern void usb_poison_urb(struct urb *urb);
 extern void usb_unpoison_urb(struct urb *urb);
 extern void usb_kill_anchored_urbs(struct usb_anchor *anchor);
+extern void usb_poison_anchored_urbs(struct usb_anchor *anchor);
 extern void usb_unlink_anchored_urbs(struct usb_anchor *anchor);
 extern void usb_anchor_urb(struct urb *urb, struct usb_anchor *anchor);
 extern void usb_unanchor_urb(struct urb *urb);
-- 
cgit v1.2.3


From 60beed95e38793c0baff7f94433c1f639d8d5efd Mon Sep 17 00:00:00 2001
From: David Brownell <dbrownell@users.sourceforge.net>
Date: Mon, 18 Aug 2008 17:38:22 -0700
Subject: usb gadget: function activation/deactivation

Add a new mechanism to the composite gadget framework, letting
functions deactivate (and reactivate) themselves.  Think of it
as a refcounted wrapper for the software pullup control.

A key example of why to use this mechanism involves functions that
require a userspace daemon.  Those functions shuld use this new
mechanism to prevent the gadget from enumerating until those daemons
are activated.  Without this mechanism, hosts would see devices that
malfunction until the relevant daemons start.

Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/usb/gadget/composite.c | 64 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/usb/composite.h  | 11 ++++++--
 2 files changed, 73 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 85c876c1f150..f79fdb839cb8 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -127,6 +127,70 @@ done:
 	return value;
 }
 
+/**
+ * usb_function_deactivate - prevent function and gadget enumeration
+ * @function: the function that isn't yet ready to respond
+ *
+ * Blocks response of the gadget driver to host enumeration by
+ * preventing the data line pullup from being activated.  This is
+ * normally called during @bind() processing to change from the
+ * initial "ready to respond" state, or when a required resource
+ * becomes available.
+ *
+ * For example, drivers that serve as a passthrough to a userspace
+ * daemon can block enumeration unless that daemon (such as an OBEX,
+ * MTP, or print server) is ready to handle host requests.
+ *
+ * Not all systems support software control of their USB peripheral
+ * data pullups.
+ *
+ * Returns zero on success, else negative errno.
+ */
+int usb_function_deactivate(struct usb_function *function)
+{
+	struct usb_composite_dev	*cdev = function->config->cdev;
+	int				status = 0;
+
+	spin_lock(&cdev->lock);
+
+	if (cdev->deactivations == 0)
+		status = usb_gadget_disconnect(cdev->gadget);
+	if (status == 0)
+		cdev->deactivations++;
+
+	spin_unlock(&cdev->lock);
+	return status;
+}
+
+/**
+ * usb_function_activate - allow function and gadget enumeration
+ * @function: function on which usb_function_activate() was called
+ *
+ * Reverses effect of usb_function_deactivate().  If no more functions
+ * are delaying their activation, the gadget driver will respond to
+ * host enumeration procedures.
+ *
+ * Returns zero on success, else negative errno.
+ */
+int usb_function_activate(struct usb_function *function)
+{
+	struct usb_composite_dev	*cdev = function->config->cdev;
+	int				status = 0;
+
+	spin_lock(&cdev->lock);
+
+	if (WARN_ON(cdev->deactivations == 0))
+		status = -EINVAL;
+	else {
+		cdev->deactivations--;
+		if (cdev->deactivations == 0)
+			status = usb_gadget_connect(cdev->gadget);
+	}
+
+	spin_unlock(&cdev->lock);
+	return status;
+}
+
 /**
  * usb_interface_id() - allocate an unused interface ID
  * @config: configuration associated with the interface
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index c932390c6da0..935c380ffe47 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -130,6 +130,9 @@ struct usb_function {
 
 int usb_add_function(struct usb_configuration *, struct usb_function *);
 
+int usb_function_deactivate(struct usb_function *);
+int usb_function_activate(struct usb_function *);
+
 int usb_interface_id(struct usb_configuration *, struct usb_function *);
 
 /**
@@ -316,9 +319,13 @@ struct usb_composite_dev {
 	struct usb_composite_driver	*driver;
 	u8				next_string_id;
 
-	spinlock_t			lock;
+	/* the gadget driver won't enable the data pullup
+	 * while the deactivation count is nonzero.
+	 */
+	unsigned			deactivations;
 
-	/* REVISIT use and existence of lock ... */
+	/* protects at least deactivation count */
+	spinlock_t			lock;
 };
 
 extern int usb_string_id(struct usb_composite_dev *c);
-- 
cgit v1.2.3


From 3086775a4916b0fe128d924d83f4e7d7c39e4d0e Mon Sep 17 00:00:00 2001
From: Felipe Balbi <felipe.balbi@nokia.com>
Date: Mon, 18 Aug 2008 17:39:30 -0700
Subject: usb gadget: cdc obex glue

The following patch introduces a new f_obex.c function driver.
It allows userspace obex servers to use usb as transport layer
for their messages.

[ dbrownell@users.sourceforge.net: various fixes and cleanups ]

Signed-off-by: Felipe Balbi <felipe.balbi@nokia.com>
Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 Documentation/DocBook/gadget.tmpl |   3 +
 drivers/usb/gadget/Kconfig        |   8 +-
 drivers/usb/gadget/f_obex.c       | 446 ++++++++++++++++++++++++++++++++++++++
 drivers/usb/gadget/serial.c       |  14 ++
 drivers/usb/gadget/u_serial.h     |   1 +
 include/linux/usb/cdc.h           |   9 +
 6 files changed, 479 insertions(+), 2 deletions(-)
 create mode 100644 drivers/usb/gadget/f_obex.c

(limited to 'include')

diff --git a/Documentation/DocBook/gadget.tmpl b/Documentation/DocBook/gadget.tmpl
index ea3bc9565e6a..6ef2f0073e5a 100644
--- a/Documentation/DocBook/gadget.tmpl
+++ b/Documentation/DocBook/gadget.tmpl
@@ -557,6 +557,9 @@ Near-term plans include converting all of them, except for "gadgetfs".
 </para>
 
 !Edrivers/usb/gadget/f_acm.c
+!Edrivers/usb/gadget/f_ecm.c
+!Edrivers/usb/gadget/f_subset.c
+!Edrivers/usb/gadget/f_obex.c
 !Edrivers/usb/gadget/f_serial.c
 
 </sect1>
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index 5dda2dc708db..80a7c02dc951 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -576,19 +576,23 @@ config USB_FILE_STORAGE_TEST
 	  normal operation.
 
 config USB_G_SERIAL
-	tristate "Serial Gadget (with CDC ACM support)"
+	tristate "Serial Gadget (with CDC ACM and CDC OBEX support)"
 	help
 	  The Serial Gadget talks to the Linux-USB generic serial driver.
 	  This driver supports a CDC-ACM module option, which can be used
 	  to interoperate with MS-Windows hosts or with the Linux-USB
 	  "cdc-acm" driver.
 
+	  This driver also supports a CDC-OBEX option.  You will need a
+	  user space OBEX server talking to /dev/ttyGS*, since the kernel
+	  itself doesn't implement the OBEX protocol.
+
 	  Say "y" to link the driver statically, or "m" to build a
 	  dynamically linked module called "g_serial".
 
 	  For more information, see Documentation/usb/gadget_serial.txt
 	  which includes instructions and a "driver info file" needed to
-	  make MS-Windows work with this driver.
+	  make MS-Windows work with CDC ACM.
 
 config USB_MIDI_GADGET
 	tristate "MIDI Gadget (EXPERIMENTAL)"
diff --git a/drivers/usb/gadget/f_obex.c b/drivers/usb/gadget/f_obex.c
new file mode 100644
index 000000000000..86241b2ca8f4
--- /dev/null
+++ b/drivers/usb/gadget/f_obex.c
@@ -0,0 +1,446 @@
+/*
+ * f_obex.c -- USB CDC OBEX function driver
+ *
+ * Copyright (C) 2008 Nokia Corporation
+ * Contact: Felipe Balbi <felipe.balbi@nokia.com>
+ *
+ * Based on f_acm.c by Al Borchers and David Brownell.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+/* #define VERBOSE_DEBUG */
+
+#include <linux/kernel.h>
+#include <linux/utsname.h>
+#include <linux/device.h>
+
+#include "u_serial.h"
+#include "gadget_chips.h"
+
+
+/*
+ * This CDC OBEX function support just packages a TTY-ish byte stream.
+ * A user mode server will put it into "raw" mode and handle all the
+ * relevant protocol details ... this is just a kernel passthrough.
+ *
+ * REVISIT this driver shouldn't actually activate before that user mode
+ * server is ready to respond!  When the "serial gadget" utility code
+ * adds open/close notifications, this driver should use them with new
+ * (TBS) composite gadget hooks that wrap usb_gadget_disconnect() and
+ * usb_gadget_connect() calls with refcounts ... disconnect() when we
+ * bind, then connect() when the user server code is ready to respond.
+ */
+
+struct obex_ep_descs {
+	struct usb_endpoint_descriptor	*obex_in;
+	struct usb_endpoint_descriptor	*obex_out;
+};
+
+struct f_obex {
+	struct gserial			port;
+	u8				ctrl_id;
+	u8				data_id;
+	u8				port_num;
+
+	struct obex_ep_descs		fs;
+	struct obex_ep_descs		hs;
+};
+
+static inline struct f_obex *func_to_obex(struct usb_function *f)
+{
+	return container_of(f, struct f_obex, port.func);
+}
+
+/*-------------------------------------------------------------------------*/
+
+#define OBEX_CTRL_IDX	0
+#define OBEX_DATA_IDX	1
+
+static struct usb_string obex_string_defs[] = {
+	[OBEX_CTRL_IDX].s	= "CDC Object Exchange (OBEX)",
+	[OBEX_DATA_IDX].s	= "CDC OBEX Data",
+	{  },	/* end of list */
+};
+
+static struct usb_gadget_strings obex_string_table = {
+	.language		= 0x0409,	/* en-US */
+	.strings		= obex_string_defs,
+};
+
+static struct usb_gadget_strings *obex_strings[] = {
+	&obex_string_table,
+	NULL,
+};
+
+/*-------------------------------------------------------------------------*/
+
+static struct usb_interface_descriptor obex_control_intf __initdata = {
+	.bLength		= sizeof(obex_control_intf),
+	.bDescriptorType	= USB_DT_INTERFACE,
+	.bInterfaceNumber	= 0,
+
+	.bAlternateSetting	= 0,
+	.bNumEndpoints		= 0,
+	.bInterfaceClass	= USB_CLASS_COMM,
+	.bInterfaceSubClass	= USB_CDC_SUBCLASS_OBEX,
+};
+
+static struct usb_interface_descriptor obex_data_nop_intf __initdata = {
+	.bLength		= sizeof(obex_data_nop_intf),
+	.bDescriptorType	= USB_DT_INTERFACE,
+	.bInterfaceNumber	= 1,
+
+	.bAlternateSetting	= 0,
+	.bNumEndpoints		= 0,
+	.bInterfaceClass	= USB_CLASS_CDC_DATA,
+};
+
+static struct usb_interface_descriptor obex_data_intf __initdata = {
+	.bLength		= sizeof(obex_data_intf),
+	.bDescriptorType	= USB_DT_INTERFACE,
+	.bInterfaceNumber	= 2,
+
+	.bAlternateSetting	= 1,
+	.bNumEndpoints		= 2,
+	.bInterfaceClass	= USB_CLASS_CDC_DATA,
+};
+
+static struct usb_cdc_header_desc obex_cdc_header_desc __initdata = {
+	.bLength		= sizeof(obex_cdc_header_desc),
+	.bDescriptorType	= USB_DT_CS_INTERFACE,
+	.bDescriptorSubType	= USB_CDC_HEADER_TYPE,
+	.bcdCDC			= __constant_cpu_to_le16(0x0120),
+};
+
+static struct usb_cdc_union_desc obex_cdc_union_desc __initdata = {
+	.bLength		= sizeof(obex_cdc_union_desc),
+	.bDescriptorType	= USB_DT_CS_INTERFACE,
+	.bDescriptorSubType	= USB_CDC_UNION_TYPE,
+	.bMasterInterface0	= 1,
+	.bSlaveInterface0	= 2,
+};
+
+static struct usb_cdc_obex_desc obex_desc __initdata = {
+	.bLength		= sizeof(obex_desc),
+	.bDescriptorType	= USB_DT_CS_INTERFACE,
+	.bDescriptorSubType	= USB_CDC_OBEX_TYPE,
+	.bcdVersion		= __constant_cpu_to_le16(0x0100),
+};
+
+/* High-Speed Support */
+
+static struct usb_endpoint_descriptor obex_hs_ep_out_desc __initdata = {
+	.bLength		= USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType	= USB_DT_ENDPOINT,
+
+	.bEndpointAddress	= USB_DIR_OUT,
+	.bmAttributes		= USB_ENDPOINT_XFER_BULK,
+	.wMaxPacketSize		= __constant_cpu_to_le16(512),
+};
+
+static struct usb_endpoint_descriptor obex_hs_ep_in_desc __initdata = {
+	.bLength		= USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType	= USB_DT_ENDPOINT,
+
+	.bEndpointAddress	= USB_DIR_IN,
+	.bmAttributes		= USB_ENDPOINT_XFER_BULK,
+	.wMaxPacketSize		= __constant_cpu_to_le16(512),
+};
+
+static struct usb_descriptor_header *hs_function[] __initdata = {
+	(struct usb_descriptor_header *) &obex_control_intf,
+	(struct usb_descriptor_header *) &obex_cdc_header_desc,
+	(struct usb_descriptor_header *) &obex_desc,
+	(struct usb_descriptor_header *) &obex_cdc_union_desc,
+
+	(struct usb_descriptor_header *) &obex_data_nop_intf,
+	(struct usb_descriptor_header *) &obex_data_intf,
+	(struct usb_descriptor_header *) &obex_hs_ep_in_desc,
+	(struct usb_descriptor_header *) &obex_hs_ep_out_desc,
+	NULL,
+};
+
+/* Full-Speed Support */
+
+static struct usb_endpoint_descriptor obex_fs_ep_in_desc __initdata = {
+	.bLength		= USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType	= USB_DT_ENDPOINT,
+
+	.bEndpointAddress	= USB_DIR_IN,
+	.bmAttributes		= USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_endpoint_descriptor obex_fs_ep_out_desc __initdata = {
+	.bLength		= USB_DT_ENDPOINT_SIZE,
+	.bDescriptorType	= USB_DT_ENDPOINT,
+
+	.bEndpointAddress	= USB_DIR_OUT,
+	.bmAttributes		= USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usb_descriptor_header *fs_function[] __initdata = {
+	(struct usb_descriptor_header *) &obex_control_intf,
+	(struct usb_descriptor_header *) &obex_cdc_header_desc,
+	(struct usb_descriptor_header *) &obex_desc,
+	(struct usb_descriptor_header *) &obex_cdc_union_desc,
+
+	(struct usb_descriptor_header *) &obex_data_nop_intf,
+	(struct usb_descriptor_header *) &obex_data_intf,
+	(struct usb_descriptor_header *) &obex_fs_ep_in_desc,
+	(struct usb_descriptor_header *) &obex_fs_ep_out_desc,
+	NULL,
+};
+
+/*-------------------------------------------------------------------------*/
+
+static int obex_set_alt(struct usb_function *f, unsigned intf, unsigned alt)
+{
+	struct f_obex		*obex = func_to_obex(f);
+	struct usb_composite_dev *cdev = f->config->cdev;
+
+	if (intf == obex->ctrl_id) {
+		if (alt != 0)
+			goto fail;
+		/* NOP */
+		DBG(cdev, "reset obex ttyGS%d control\n", obex->port_num);
+
+	} else if (intf == obex->data_id) {
+		if (alt > 1)
+			goto fail;
+
+		if (obex->port.in->driver_data) {
+			DBG(cdev, "reset obex ttyGS%d\n", obex->port_num);
+			gserial_disconnect(&obex->port);
+		}
+
+		if (!obex->port.in_desc) {
+			DBG(cdev, "init obex ttyGS%d\n", obex->port_num);
+			obex->port.in_desc = ep_choose(cdev->gadget,
+					obex->hs.obex_in, obex->fs.obex_in);
+			obex->port.out_desc = ep_choose(cdev->gadget,
+					obex->hs.obex_out, obex->fs.obex_out);
+		}
+
+		if (alt == 1) {
+			DBG(cdev, "activate obex ttyGS%d\n", obex->port_num);
+			gserial_connect(&obex->port, obex->port_num);
+		}
+
+	} else
+		goto fail;
+
+	return 0;
+
+fail:
+	return -EINVAL;
+}
+
+static int obex_get_alt(struct usb_function *f, unsigned intf)
+{
+	struct f_obex		*obex = func_to_obex(f);
+
+	if (intf == obex->ctrl_id)
+		return 0;
+
+	return obex->port.in->driver_data ? 1 : 0;
+}
+
+static void obex_disable(struct usb_function *f)
+{
+	struct f_obex	*obex = func_to_obex(f);
+	struct usb_composite_dev *cdev = f->config->cdev;
+
+	DBG(cdev, "obex ttyGS%d disable\n", obex->port_num);
+	gserial_disconnect(&obex->port);
+}
+
+/*-------------------------------------------------------------------------*/
+
+static int __init
+obex_bind(struct usb_configuration *c, struct usb_function *f)
+{
+	struct usb_composite_dev *cdev = c->cdev;
+	struct f_obex		*obex = func_to_obex(f);
+	int			status;
+	struct usb_ep		*ep;
+
+	/* allocate instance-specific interface IDs, and patch descriptors */
+
+	status = usb_interface_id(c, f);
+	if (status < 0)
+		goto fail;
+	obex->ctrl_id = status;
+
+	obex_control_intf.bInterfaceNumber = status;
+	obex_cdc_union_desc.bMasterInterface0 = status;
+
+	status = usb_interface_id(c, f);
+	if (status < 0)
+		goto fail;
+	obex->data_id = status;
+
+	obex_data_nop_intf.bInterfaceNumber = status;
+	obex_data_intf.bInterfaceNumber = status;
+	obex_cdc_union_desc.bSlaveInterface0 = status;
+
+	/* allocate instance-specific endpoints */
+
+	ep = usb_ep_autoconfig(cdev->gadget, &obex_fs_ep_in_desc);
+	if (!ep)
+		goto fail;
+	obex->port.in = ep;
+	ep->driver_data = cdev;	/* claim */
+
+	ep = usb_ep_autoconfig(cdev->gadget, &obex_fs_ep_out_desc);
+	if (!ep)
+		goto fail;
+	obex->port.out = ep;
+	ep->driver_data = cdev;	/* claim */
+
+	/* copy descriptors, and track endpoint copies */
+	f->descriptors = usb_copy_descriptors(fs_function);
+
+	obex->fs.obex_in = usb_find_endpoint(fs_function,
+			f->descriptors, &obex_fs_ep_in_desc);
+	obex->fs.obex_out = usb_find_endpoint(fs_function,
+			f->descriptors, &obex_fs_ep_out_desc);
+
+	/* support all relevant hardware speeds... we expect that when
+	 * hardware is dual speed, all bulk-capable endpoints work at
+	 * both speeds
+	 */
+	if (gadget_is_dualspeed(c->cdev->gadget)) {
+
+		obex_hs_ep_in_desc.bEndpointAddress =
+				obex_fs_ep_in_desc.bEndpointAddress;
+		obex_hs_ep_out_desc.bEndpointAddress =
+				obex_fs_ep_out_desc.bEndpointAddress;
+
+		/* copy descriptors, and track endpoint copies */
+		f->hs_descriptors = usb_copy_descriptors(hs_function);
+
+		obex->hs.obex_in = usb_find_endpoint(hs_function,
+				f->descriptors, &obex_hs_ep_in_desc);
+		obex->hs.obex_out = usb_find_endpoint(hs_function,
+				f->descriptors, &obex_hs_ep_out_desc);
+	}
+
+	DBG(cdev, "obex ttyGS%d: %s speed IN/%s OUT/%s\n",
+			obex->port_num,
+			gadget_is_dualspeed(c->cdev->gadget) ? "dual" : "full",
+			obex->port.in->name, obex->port.out->name);
+
+	return 0;
+
+fail:
+	/* we might as well release our claims on endpoints */
+	if (obex->port.out)
+		obex->port.out->driver_data = NULL;
+	if (obex->port.in)
+		obex->port.in->driver_data = NULL;
+
+	ERROR(cdev, "%s/%p: can't bind, err %d\n", f->name, f, status);
+
+	return status;
+}
+
+static void
+obex_unbind(struct usb_configuration *c, struct usb_function *f)
+{
+	if (gadget_is_dualspeed(c->cdev->gadget))
+		usb_free_descriptors(f->hs_descriptors);
+	usb_free_descriptors(f->descriptors);
+	kfree(func_to_obex(f));
+}
+
+/* Some controllers can't support CDC OBEX ... */
+static inline bool can_support_obex(struct usb_configuration *c)
+{
+	/* Since the first interface is a NOP, we can ignore the
+	 * issue of multi-interface support on most controllers.
+	 *
+	 * Altsettings are mandatory, however...
+	 */
+	if (!gadget_supports_altsettings(c->cdev->gadget))
+		return false;
+
+	/* everything else is *probably* fine ... */
+	return true;
+}
+
+/**
+ * obex_bind_config - add a CDC OBEX function to a configuration
+ * @c: the configuration to support the CDC OBEX instance
+ * @port_num: /dev/ttyGS* port this interface will use
+ * Context: single threaded during gadget setup
+ *
+ * Returns zero on success, else negative errno.
+ *
+ * Caller must have called @gserial_setup() with enough ports to
+ * handle all the ones it binds.  Caller is also responsible
+ * for calling @gserial_cleanup() before module unload.
+ */
+int __init obex_bind_config(struct usb_configuration *c, u8 port_num)
+{
+	struct f_obex	*obex;
+	int		status;
+
+	if (!can_support_obex(c))
+		return -EINVAL;
+
+	/* maybe allocate device-global string IDs, and patch descriptors */
+	if (obex_string_defs[OBEX_CTRL_IDX].id == 0) {
+		status = usb_string_id(c->cdev);
+		if (status < 0)
+			return status;
+		obex_string_defs[OBEX_CTRL_IDX].id = status;
+
+		obex_control_intf.iInterface = status;
+
+		status = usb_string_id(c->cdev);
+		if (status < 0)
+			return status;
+		obex_string_defs[OBEX_DATA_IDX].id = status;
+
+		obex_data_nop_intf.iInterface =
+			obex_data_intf.iInterface = status;
+	}
+
+	/* allocate and initialize one new instance */
+	obex = kzalloc(sizeof *obex, GFP_KERNEL);
+	if (!obex)
+		return -ENOMEM;
+
+	obex->port_num = port_num;
+
+	obex->port.func.name = "obex";
+	obex->port.func.strings = obex_strings;
+	/* descriptors are per-instance copies */
+	obex->port.func.bind = obex_bind;
+	obex->port.func.unbind = obex_unbind;
+	obex->port.func.set_alt = obex_set_alt;
+	obex->port.func.get_alt = obex_get_alt;
+	obex->port.func.disable = obex_disable;
+
+	status = usb_add_function(c, &obex->port.func);
+	if (status)
+		kfree(obex);
+
+	return status;
+}
+
+MODULE_AUTHOR("Felipe Balbi");
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/gadget/serial.c b/drivers/usb/gadget/serial.c
index 3faa7a7022df..2dee848b2f59 100644
--- a/drivers/usb/gadget/serial.c
+++ b/drivers/usb/gadget/serial.c
@@ -43,6 +43,7 @@
 #include "epautoconf.c"
 
 #include "f_acm.c"
+#include "f_obex.c"
 #include "f_serial.c"
 #include "u_serial.c"
 
@@ -56,6 +57,7 @@
 #define GS_VENDOR_ID			0x0525	/* NetChip */
 #define GS_PRODUCT_ID			0xa4a6	/* Linux-USB Serial Gadget */
 #define GS_CDC_PRODUCT_ID		0xa4a7	/* ... as CDC-ACM */
+#define GS_CDC_OBEX_PRODUCT_ID		0xa4a9	/* ... as CDC-OBEX */
 
 /* string IDs are assigned dynamically */
 
@@ -125,6 +127,10 @@ static int use_acm = true;
 module_param(use_acm, bool, 0);
 MODULE_PARM_DESC(use_acm, "Use CDC ACM, default=yes");
 
+static int use_obex = false;
+module_param(use_obex, bool, 0);
+MODULE_PARM_DESC(use_obex, "Use CDC OBEX, default=no");
+
 static unsigned n_ports = 1;
 module_param(n_ports, uint, 0);
 MODULE_PARM_DESC(n_ports, "number of ports to create, default=1");
@@ -139,6 +145,8 @@ static int __init serial_bind_config(struct usb_configuration *c)
 	for (i = 0; i < n_ports && status == 0; i++) {
 		if (use_acm)
 			status = acm_bind_config(c, i);
+		else if (use_obex)
+			status = obex_bind_config(c, i);
 		else
 			status = gser_bind_config(c, i);
 	}
@@ -249,6 +257,12 @@ static int __init init(void)
 		device_desc.bDeviceClass = USB_CLASS_COMM;
 		device_desc.idProduct =
 				__constant_cpu_to_le16(GS_CDC_PRODUCT_ID);
+	} else if (use_obex) {
+		serial_config_driver.label = "CDC OBEX config";
+		serial_config_driver.bConfigurationValue = 3;
+		device_desc.bDeviceClass = USB_CLASS_COMM;
+		device_desc.idProduct =
+			__constant_cpu_to_le16(GS_CDC_OBEX_PRODUCT_ID);
 	} else {
 		serial_config_driver.label = "Generic Serial config";
 		serial_config_driver.bConfigurationValue = 1;
diff --git a/drivers/usb/gadget/u_serial.h b/drivers/usb/gadget/u_serial.h
index af3910d01aea..300f0ed9475d 100644
--- a/drivers/usb/gadget/u_serial.h
+++ b/drivers/usb/gadget/u_serial.h
@@ -62,5 +62,6 @@ void gserial_disconnect(struct gserial *);
 /* functions are bound to configurations by a config or gadget driver */
 int acm_bind_config(struct usb_configuration *c, u8 port_num);
 int gser_bind_config(struct usb_configuration *c, u8 port_num);
+int obex_bind_config(struct usb_configuration *c, u8 port_num);
 
 #endif /* __U_SERIAL_H */
diff --git a/include/linux/usb/cdc.h b/include/linux/usb/cdc.h
index ca228bb94218..18a729343ffa 100644
--- a/include/linux/usb/cdc.h
+++ b/include/linux/usb/cdc.h
@@ -160,6 +160,15 @@ struct usb_cdc_mdlm_detail_desc {
 	__u8	bDetailData[0];
 } __attribute__ ((packed));
 
+/* "OBEX Control Model Functional Descriptor" */
+struct usb_cdc_obex_desc {
+	__u8	bLength;
+	__u8	bDescriptorType;
+	__u8	bDescriptorSubType;
+
+	__le16	bcdVersion;
+} __attribute__ ((packed));
+
 /*-------------------------------------------------------------------------*/
 
 /*
-- 
cgit v1.2.3


From 0b14c3881d4b91272b779f4037e263d392de058f Mon Sep 17 00:00:00 2001
From: Geoff Levand <geoff@infradead.org>
Date: Sat, 20 Sep 2008 14:41:47 -0700
Subject: USB: Fix spelling in usb/serial.h

Fixes a minor typo in the comments for usb_set_serial_data.

Signed-off-by: Geoff Levand <geoff@infradead.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/usb/serial.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 655341d0f534..0b8617a9176d 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -192,7 +192,7 @@ static inline void usb_set_serial_data(struct usb_serial *serial, void *data)
  * The driver.owner field should be set to the module owner of this driver.
  * The driver.name field should be set to the name of this driver (remember
  * it will show up in sysfs, so it needs to be short and to the point.
- * Useing the module name is a good idea.)
+ * Using the module name is a good idea.)
  */
 struct usb_serial_driver {
 	const char *description;
-- 
cgit v1.2.3


From cbc30118d7a376dab4113f299c0c8f035737a5c3 Mon Sep 17 00:00:00 2001
From: Stephen Ware <stephen.ware@eqware.net>
Date: Tue, 30 Sep 2008 11:39:38 -0700
Subject: usb: vstusb.c : new driver for spectrometers used by Vernier Software
 & Technology, Inc.

This patch adds the vstusb driver to the drivers/usb/misc directory.
This driver provides support for Vernier Software & Technology
spectrometers, all made by Ocean Optics. The driver provides both IOCTL
and read()/write() methods for sending raw data to spectrometers across
the bulk channel. Each method allows for a configured timeout.

From: Stephen Ware <stephen.ware@eqware.net>
Signed-off-by: Dennis O'Brien <dennis.obrien@eqware.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 Documentation/ioctl-number.txt |   1 +
 drivers/usb/misc/Kconfig       |  15 +
 drivers/usb/misc/Makefile      |   1 +
 drivers/usb/misc/vstusb.c      | 768 +++++++++++++++++++++++++++++++++++++++++
 include/linux/usb/Kbuild       |   1 +
 include/linux/usb/vstusb.h     |  71 ++++
 6 files changed, 857 insertions(+)
 create mode 100644 drivers/usb/misc/vstusb.c
 create mode 100644 include/linux/usb/vstusb.h

(limited to 'include')

diff --git a/Documentation/ioctl-number.txt b/Documentation/ioctl-number.txt
index f8deb85eef6e..b880ce5dbd33 100644
--- a/Documentation/ioctl-number.txt
+++ b/Documentation/ioctl-number.txt
@@ -92,6 +92,7 @@ Code	Seq#	Include File		Comments
 'J'	00-1F	drivers/scsi/gdth_ioctl.h
 'K'	all	linux/kd.h
 'L'	00-1F	linux/loop.h
+'L'	20-2F	driver/usb/misc/vstusb.h
 'L'	E0-FF	linux/ppdd.h		encrypted disk device driver
 					<http://linux01.gwdg.de/~alatham/ppdd.html>
 'M'	all	linux/soundcard.h
diff --git a/drivers/usb/misc/Kconfig b/drivers/usb/misc/Kconfig
index 25e1157ab176..e463db5d8188 100644
--- a/drivers/usb/misc/Kconfig
+++ b/drivers/usb/misc/Kconfig
@@ -280,3 +280,18 @@ config USB_ISIGHTFW
 	  The firmware for this driver must be extracted from the MacOS
 	  driver beforehand. Tools for doing so are available at
 	  http://bersace03.free.fr
+
+config USB_VST
+	tristate "USB VST driver"
+	depends on USB
+	help
+	  This driver is intended for Vernier Software Technologies
+	  bulk usb devices such as their Ocean-Optics spectrometers or
+	  Labquest.
+	  It is a bulk channel driver with configurable read and write
+	  timeouts.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called vstusb.
+
+
diff --git a/drivers/usb/misc/Makefile b/drivers/usb/misc/Makefile
index 39ce4a16b3d4..1334f7bdd7be 100644
--- a/drivers/usb/misc/Makefile
+++ b/drivers/usb/misc/Makefile
@@ -27,6 +27,7 @@ obj-$(CONFIG_USB_TEST)		+= usbtest.o
 obj-$(CONFIG_USB_TRANCEVIBRATOR)	+= trancevibrator.o
 obj-$(CONFIG_USB_USS720)	+= uss720.o
 obj-$(CONFIG_USB_SEVSEG)	+= usbsevseg.o
+obj-$(CONFIG_USB_VST)		+= vstusb.o
 
 obj-$(CONFIG_USB_SISUSBVGA)	+= sisusbvga/
 
diff --git a/drivers/usb/misc/vstusb.c b/drivers/usb/misc/vstusb.c
new file mode 100644
index 000000000000..5ad75e4a0323
--- /dev/null
+++ b/drivers/usb/misc/vstusb.c
@@ -0,0 +1,768 @@
+/*****************************************************************************
+ *  File: drivers/usb/misc/vstusb.c
+ *
+ *  Purpose: Support for the bulk USB Vernier Spectrophotometers
+ *
+ *  Author:     Johnnie Peters
+ *              Axian Consulting
+ *              Beaverton, OR, USA 97005
+ *
+ *  Modified by:     EQware Engineering, Inc.
+ *                   Oregon City, OR, USA 97045
+ *
+ *  Copyright:  2007, 2008
+ *              Vernier Software & Technology
+ *              Beaverton, OR, USA 97005
+ *
+ *  Web:        www.vernier.com
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ *
+ *****************************************************************************/
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/uaccess.h>
+#include <linux/usb.h>
+
+#include <linux/usb/vstusb.h>
+
+#define DRIVER_VERSION "VST USB Driver Version 1.5"
+#define DRIVER_DESC "Vernier Software Technology Bulk USB Driver"
+
+#ifdef CONFIG_USB_DYNAMIC_MINORS
+	#define VSTUSB_MINOR_BASE	0
+#else
+	#define VSTUSB_MINOR_BASE	199
+#endif
+
+#define USB_VENDOR_OCEANOPTICS	0x2457
+#define USB_VENDOR_VERNIER	0x08F7	/* Vernier Software & Technology */
+
+#define USB_PRODUCT_USB2000	0x1002
+#define USB_PRODUCT_ADC1000_FW	0x1003	/* firmware download (renumerates) */
+#define USB_PRODUCT_ADC1000	0x1004
+#define USB_PRODUCT_HR2000_FW	0x1009	/* firmware download (renumerates) */
+#define USB_PRODUCT_HR2000	0x100A
+#define USB_PRODUCT_HR4000_FW	0x1011	/* firmware download (renumerates) */
+#define USB_PRODUCT_HR4000	0x1012
+#define USB_PRODUCT_USB650	0x1014	/* "Red Tide" */
+#define USB_PRODUCT_QE65000	0x1018
+#define USB_PRODUCT_USB4000	0x1022
+#define USB_PRODUCT_USB325	0x1024	/* "Vernier Spectrometer" */
+
+#define USB_PRODUCT_LABPRO	0x0001
+#define USB_PRODUCT_LABQUEST	0x0005
+
+static struct usb_device_id id_table[] = {
+	{ USB_DEVICE(USB_VENDOR_OCEANOPTICS, USB_PRODUCT_USB2000)},
+	{ USB_DEVICE(USB_VENDOR_OCEANOPTICS, USB_PRODUCT_HR4000)},
+	{ USB_DEVICE(USB_VENDOR_OCEANOPTICS, USB_PRODUCT_USB650)},
+	{ USB_DEVICE(USB_VENDOR_OCEANOPTICS, USB_PRODUCT_USB4000)},
+	{ USB_DEVICE(USB_VENDOR_OCEANOPTICS, USB_PRODUCT_USB325)},
+	{ USB_DEVICE(USB_VENDOR_VERNIER, USB_PRODUCT_LABQUEST)},
+	{ USB_DEVICE(USB_VENDOR_VERNIER, USB_PRODUCT_LABPRO)},
+	{},
+};
+
+MODULE_DEVICE_TABLE(usb, id_table);
+
+struct vstusb_device {
+	struct mutex            lock;
+	struct usb_device       *usb_dev;
+	char                    present;
+	char                    isopen;
+	struct usb_anchor       submitted;
+	int                     rd_pipe;
+	int                     rd_timeout_ms;
+	int                     wr_pipe;
+	int                     wr_timeout_ms;
+};
+
+static struct usb_driver vstusb_driver;
+
+static int vstusb_open(struct inode *inode, struct file *file)
+{
+	struct vstusb_device *vstdev;
+	struct usb_interface *interface;
+
+	interface = usb_find_interface(&vstusb_driver, iminor(inode));
+
+	if (!interface) {
+		printk(KERN_ERR KBUILD_MODNAME
+		       ": %s - error, can't find device for minor %d\n",
+		       __func__, iminor(inode));
+		return -ENODEV;
+	}
+
+	vstdev = usb_get_intfdata(interface);
+
+	if (!vstdev)
+		return -ENODEV;
+
+	/* lock this device */
+	mutex_lock(&vstdev->lock);
+
+	/* can only open one time */
+	if ((!vstdev->present) || (vstdev->isopen)) {
+		mutex_unlock(&vstdev->lock);
+		return -EBUSY;
+	}
+
+	vstdev->isopen = 1;
+
+	/* save device in the file's private structure */
+	file->private_data = vstdev;
+
+	dev_dbg(&vstdev->usb_dev->dev, "%s: opened\n", __func__);
+
+	mutex_unlock(&vstdev->lock);
+
+	return 0;
+}
+
+static int vstusb_close(struct inode *inode, struct file *file)
+{
+	struct vstusb_device *vstdev;
+
+	vstdev = file->private_data;
+
+	if (vstdev == NULL)
+		return -ENODEV;
+
+	mutex_lock(&vstdev->lock);
+
+	vstdev->isopen = 0;
+	file->private_data = NULL;
+
+	/* if device is no longer present */
+	if (!vstdev->present) {
+		mutex_unlock(&vstdev->lock);
+		kfree(vstdev);
+	} else
+		mutex_unlock(&vstdev->lock);
+
+	return 0;
+}
+
+static void usb_api_blocking_completion(struct urb *urb)
+{
+	struct completion *completeit = urb->context;
+
+	complete(completeit);
+}
+
+static int vstusb_fill_and_send_urb(struct urb *urb,
+				    struct usb_device *usb_dev,
+				    unsigned int pipe, void *data,
+				    unsigned int len, struct completion *done)
+{
+	struct usb_host_endpoint *ep;
+	struct usb_host_endpoint **hostep;
+	unsigned int pipend;
+
+	int status;
+
+	hostep = usb_pipein(pipe) ? usb_dev->ep_in : usb_dev->ep_out;
+	pipend = usb_pipeendpoint(pipe);
+	ep = hostep[pipend];
+
+	if (!ep || (len == 0))
+		return -EINVAL;
+
+	if ((ep->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK)
+	    == USB_ENDPOINT_XFER_INT) {
+		pipe = (pipe & ~(3 << 30)) | (PIPE_INTERRUPT << 30);
+		usb_fill_int_urb(urb, usb_dev, pipe, data, len,
+				 (usb_complete_t)usb_api_blocking_completion,
+				 NULL, ep->desc.bInterval);
+	} else
+		usb_fill_bulk_urb(urb, usb_dev, pipe, data, len,
+				  (usb_complete_t)usb_api_blocking_completion,
+				  NULL);
+
+	init_completion(done);
+	urb->context = done;
+	urb->actual_length = 0;
+	status = usb_submit_urb(urb, GFP_KERNEL);
+
+	return status;
+}
+
+static int vstusb_complete_urb(struct urb *urb, struct completion *done,
+			       int timeout, int *actual_length)
+{
+	unsigned long expire;
+	int status;
+
+	expire = timeout ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT;
+	if (!wait_for_completion_interruptible_timeout(done, expire)) {
+		usb_kill_urb(urb);
+		status = urb->status == -ENOENT ? -ETIMEDOUT : urb->status;
+
+		dev_dbg(&urb->dev->dev,
+			"%s timed out on ep%d%s len=%d/%d, urb status = %d\n",
+			current->comm,
+			usb_pipeendpoint(urb->pipe),
+			usb_pipein(urb->pipe) ? "in" : "out",
+			urb->actual_length,
+			urb->transfer_buffer_length,
+			urb->status);
+
+	} else {
+		if (signal_pending(current)) {
+			/* if really an error */
+			if (urb->status && !((urb->status == -ENOENT)     ||
+					     (urb->status == -ECONNRESET) ||
+					     (urb->status == -ESHUTDOWN))) {
+				status = -EINTR;
+				usb_kill_urb(urb);
+			} else {
+				status = 0;
+			}
+
+			dev_dbg(&urb->dev->dev,
+				"%s: signal pending on ep%d%s len=%d/%d,"
+				"urb status = %d\n",
+				current->comm,
+				usb_pipeendpoint(urb->pipe),
+				usb_pipein(urb->pipe) ? "in" : "out",
+				urb->actual_length,
+				urb->transfer_buffer_length,
+				urb->status);
+
+		} else {
+			status = urb->status;
+		}
+	}
+
+	if (actual_length)
+		*actual_length = urb->actual_length;
+
+	return status;
+}
+
+static ssize_t vstusb_read(struct file *file, char __user *buffer,
+			   size_t count, loff_t *ppos)
+{
+	struct vstusb_device *vstdev;
+	int cnt = -1;
+	void *buf;
+	int retval = 0;
+
+	struct urb              *urb;
+	struct usb_device       *dev;
+	unsigned int            pipe;
+	int                     timeout;
+
+	DECLARE_COMPLETION_ONSTACK(done);
+
+	vstdev = file->private_data;
+
+	if (vstdev == NULL)
+		return -ENODEV;
+
+	/* verify that we actually want to read some data */
+	if (count == 0)
+		return -EINVAL;
+
+	/* lock this object */
+	if (mutex_lock_interruptible(&vstdev->lock))
+		return -ERESTARTSYS;
+
+	/* anyone home */
+	if (!vstdev->present) {
+		mutex_unlock(&vstdev->lock);
+		printk(KERN_ERR KBUILD_MODNAME
+		       ": %s: device not present\n", __func__);
+		return -ENODEV;
+	}
+
+	/* pull out the necessary data */
+	dev =     vstdev->usb_dev;
+	pipe =    usb_rcvbulkpipe(dev, vstdev->rd_pipe);
+	timeout = vstdev->rd_timeout_ms;
+
+	buf = kmalloc(count, GFP_KERNEL);
+	if (buf == NULL) {
+		mutex_unlock(&vstdev->lock);
+		return -ENOMEM;
+	}
+
+	urb = usb_alloc_urb(0, GFP_KERNEL);
+	if (!urb) {
+		kfree(buf);
+		mutex_unlock(&vstdev->lock);
+		return -ENOMEM;
+	}
+
+	usb_anchor_urb(urb, &vstdev->submitted);
+	retval = vstusb_fill_and_send_urb(urb, dev, pipe, buf, count, &done);
+	mutex_unlock(&vstdev->lock);
+	if (retval) {
+		usb_unanchor_urb(urb);
+		dev_err(&dev->dev, "%s: error %d filling and sending urb %d\n",
+			__func__, retval, pipe);
+		goto exit;
+	}
+
+	retval = vstusb_complete_urb(urb, &done, timeout, &cnt);
+	if (retval) {
+		dev_err(&dev->dev, "%s: error %d completing urb %d\n",
+			__func__, retval, pipe);
+		goto exit;
+	}
+
+	if (copy_to_user(buffer, buf, cnt)) {
+		dev_err(&dev->dev, "%s: can't copy_to_user\n", __func__);
+		retval = -EFAULT;
+	} else {
+		retval = cnt;
+		dev_dbg(&dev->dev, "%s: read %d bytes from pipe %d\n",
+			__func__, cnt, pipe);
+	}
+
+exit:
+	usb_free_urb(urb);
+	kfree(buf);
+	return retval;
+}
+
+static ssize_t vstusb_write(struct file *file, const char __user *buffer,
+			    size_t count, loff_t *ppos)
+{
+	struct vstusb_device *vstdev;
+	int cnt = -1;
+	void *buf;
+	int retval = 0;
+
+	struct urb              *urb;
+	struct usb_device       *dev;
+	unsigned int            pipe;
+	int                     timeout;
+
+	DECLARE_COMPLETION_ONSTACK(done);
+
+	vstdev = file->private_data;
+
+	if (vstdev == NULL)
+		return -ENODEV;
+
+	/* verify that we actually have some data to write */
+	if (count == 0)
+		return retval;
+
+	/* lock this object */
+	if (mutex_lock_interruptible(&vstdev->lock))
+		return -ERESTARTSYS;
+
+	/* anyone home */
+	if (!vstdev->present) {
+		mutex_unlock(&vstdev->lock);
+		printk(KERN_ERR KBUILD_MODNAME
+		       ": %s: device not present\n", __func__);
+		return -ENODEV;
+	}
+
+	/* pull out the necessary data */
+	dev =     vstdev->usb_dev;
+	pipe =    usb_sndbulkpipe(dev, vstdev->wr_pipe);
+	timeout = vstdev->wr_timeout_ms;
+
+	buf = kmalloc(count, GFP_KERNEL);
+	if (buf == NULL) {
+		mutex_unlock(&vstdev->lock);
+		return -ENOMEM;
+	}
+
+	urb = usb_alloc_urb(0, GFP_KERNEL);
+	if (!urb) {
+		kfree(buf);
+		mutex_unlock(&vstdev->lock);
+		return -ENOMEM;
+	}
+
+	if (copy_from_user(buf, buffer, count)) {
+		dev_err(&dev->dev, "%s: can't copy_from_user\n", __func__);
+		retval = -EFAULT;
+		goto exit;
+	}
+
+	usb_anchor_urb(urb, &vstdev->submitted);
+	retval = vstusb_fill_and_send_urb(urb, dev, pipe, buf, count, &done);
+	mutex_unlock(&vstdev->lock);
+	if (retval) {
+		usb_unanchor_urb(urb);
+		dev_err(&dev->dev, "%s: error %d filling and sending urb %d\n",
+			__func__, retval, pipe);
+		goto exit;
+	}
+
+	retval = vstusb_complete_urb(urb, &done, timeout, &cnt);
+	if (retval) {
+		dev_err(&dev->dev, "%s: error %d completing urb %d\n",
+			__func__, retval, pipe);
+		goto exit;
+	} else {
+		retval = cnt;
+		dev_dbg(&dev->dev, "%s: sent %d bytes to pipe %d\n",
+			__func__, cnt, pipe);
+	}
+
+exit:
+	usb_free_urb(urb);
+	kfree(buf);
+	return retval;
+}
+
+static long vstusb_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	int retval = 0;
+	int cnt = -1;
+	void __user *data = (void __user *)arg;
+	struct vstusb_args usb_data;
+
+	struct vstusb_device *vstdev;
+	void *buffer = NULL; /* must be initialized. buffer is
+			      *	referenced on exit but not all
+			      * ioctls allocate it */
+
+	struct urb              *urb = NULL; /* must be initialized. urb is
+					      *	referenced on exit but not all
+					      * ioctls allocate it */
+	struct usb_device       *dev;
+	unsigned int            pipe;
+	int                     timeout;
+
+	DECLARE_COMPLETION_ONSTACK(done);
+
+	vstdev = file->private_data;
+
+	if (_IOC_TYPE(cmd) != VST_IOC_MAGIC) {
+		dev_warn(&vstdev->usb_dev->dev,
+			 "%s: ioctl command %x, bad ioctl magic %x, "
+			 "expected %x\n", __func__, cmd,
+			 _IOC_TYPE(cmd), VST_IOC_MAGIC);
+		return -EINVAL;
+	}
+
+	if (vstdev == NULL)
+		return -ENODEV;
+
+	if (copy_from_user(&usb_data, data, sizeof(struct vstusb_args))) {
+		dev_err(&vstdev->usb_dev->dev, "%s: can't copy_from_user\n",
+			__func__);
+		return -EFAULT;
+	}
+
+	/* lock this object */
+	if (mutex_lock_interruptible(&vstdev->lock)) {
+		retval = -ERESTARTSYS;
+		goto exit;
+	}
+
+	/* anyone home */
+	if (!vstdev->present) {
+		mutex_unlock(&vstdev->lock);
+		dev_err(&vstdev->usb_dev->dev, "%s: device not present\n",
+			__func__);
+		retval = -ENODEV;
+		goto exit;
+	}
+
+	/* pull out the necessary data */
+	dev = vstdev->usb_dev;
+
+	switch (cmd) {
+
+	case IOCTL_VSTUSB_CONFIG_RW:
+
+		vstdev->rd_pipe = usb_data.rd_pipe;
+		vstdev->rd_timeout_ms = usb_data.rd_timeout_ms;
+		vstdev->wr_pipe = usb_data.wr_pipe;
+		vstdev->wr_timeout_ms = usb_data.wr_timeout_ms;
+
+		mutex_unlock(&vstdev->lock);
+
+		dev_dbg(&dev->dev, "%s: setting pipes/timeouts, "
+			"rdpipe = %d, rdtimeout = %d, "
+			"wrpipe = %d, wrtimeout = %d\n", __func__,
+			vstdev->rd_pipe, vstdev->rd_timeout_ms,
+			vstdev->wr_pipe, vstdev->wr_timeout_ms);
+		break;
+
+	case IOCTL_VSTUSB_SEND_PIPE:
+
+		if (usb_data.count == 0) {
+			mutex_unlock(&vstdev->lock);
+			retval = -EINVAL;
+			goto exit;
+		}
+
+		buffer = kmalloc(usb_data.count, GFP_KERNEL);
+		if (buffer == NULL) {
+			mutex_unlock(&vstdev->lock);
+			retval = -ENOMEM;
+			goto exit;
+		}
+
+		urb = usb_alloc_urb(0, GFP_KERNEL);
+		if (!urb) {
+			mutex_unlock(&vstdev->lock);
+			retval = -ENOMEM;
+			goto exit;
+		}
+
+		timeout = usb_data.timeout_ms;
+
+		pipe = usb_sndbulkpipe(dev, usb_data.pipe);
+
+		if (copy_from_user(buffer, usb_data.buffer, usb_data.count)) {
+			dev_err(&dev->dev, "%s: can't copy_from_user\n",
+				__func__);
+			mutex_unlock(&vstdev->lock);
+			retval = -EFAULT;
+			goto exit;
+		}
+
+		usb_anchor_urb(urb, &vstdev->submitted);
+		retval = vstusb_fill_and_send_urb(urb, dev, pipe, buffer,
+						  usb_data.count, &done);
+		mutex_unlock(&vstdev->lock);
+		if (retval) {
+			usb_unanchor_urb(urb);
+			dev_err(&dev->dev,
+				"%s: error %d filling and sending urb %d\n",
+				__func__, retval, pipe);
+			goto exit;
+		}
+
+		retval = vstusb_complete_urb(urb, &done, timeout, &cnt);
+		if (retval) {
+			dev_err(&dev->dev, "%s: error %d completing urb %d\n",
+				__func__, retval, pipe);
+		}
+
+		break;
+	case IOCTL_VSTUSB_RECV_PIPE:
+
+		if (usb_data.count == 0) {
+			mutex_unlock(&vstdev->lock);
+			retval = -EINVAL;
+			goto exit;
+		}
+
+		buffer = kmalloc(usb_data.count, GFP_KERNEL);
+		if (buffer == NULL) {
+			mutex_unlock(&vstdev->lock);
+			retval = -ENOMEM;
+			goto exit;
+		}
+
+		urb = usb_alloc_urb(0, GFP_KERNEL);
+		if (!urb) {
+			mutex_unlock(&vstdev->lock);
+			retval = -ENOMEM;
+			goto exit;
+		}
+
+		timeout = usb_data.timeout_ms;
+
+		pipe = usb_rcvbulkpipe(dev, usb_data.pipe);
+
+		usb_anchor_urb(urb, &vstdev->submitted);
+		retval = vstusb_fill_and_send_urb(urb, dev, pipe, buffer,
+						  usb_data.count, &done);
+		mutex_unlock(&vstdev->lock);
+		if (retval) {
+			usb_unanchor_urb(urb);
+			dev_err(&dev->dev,
+				"%s: error %d filling and sending urb %d\n",
+				__func__, retval, pipe);
+			goto exit;
+		}
+
+		retval = vstusb_complete_urb(urb, &done, timeout, &cnt);
+		if (retval) {
+			dev_err(&dev->dev, "%s: error %d completing urb %d\n",
+				__func__, retval, pipe);
+			goto exit;
+		}
+
+		if (copy_to_user(usb_data.buffer, buffer, cnt)) {
+			dev_err(&dev->dev, "%s: can't copy_to_user\n",
+				__func__);
+			retval = -EFAULT;
+			goto exit;
+		}
+
+		usb_data.count = cnt;
+		if (copy_to_user(data, &usb_data, sizeof(struct vstusb_args))) {
+			dev_err(&dev->dev, "%s: can't copy_to_user\n",
+				__func__);
+			retval = -EFAULT;
+		} else {
+			dev_dbg(&dev->dev, "%s: recv %d bytes from pipe %d\n",
+				__func__, usb_data.count, usb_data.pipe);
+		}
+
+		break;
+
+	default:
+		mutex_unlock(&vstdev->lock);
+		dev_warn(&dev->dev, "ioctl_vstusb: invalid ioctl cmd %x\n",
+			 cmd);
+		return -EINVAL;
+		break;
+	}
+exit:
+	usb_free_urb(urb);
+	kfree(buffer);
+	return retval;
+}
+
+static const struct file_operations vstusb_fops = {
+	.owner =                THIS_MODULE,
+	.read =                 vstusb_read,
+	.write =                vstusb_write,
+	.unlocked_ioctl =       vstusb_ioctl,
+	.compat_ioctl =         vstusb_ioctl,
+	.open =                 vstusb_open,
+	.release =              vstusb_close,
+};
+
+static struct usb_class_driver usb_vstusb_class = {
+	.name =         "usb/vstusb%d",
+	.fops =         &vstusb_fops,
+	.minor_base =   VSTUSB_MINOR_BASE,
+};
+
+static int vstusb_probe(struct usb_interface *intf,
+			const struct usb_device_id *id)
+{
+	struct usb_device *dev = interface_to_usbdev(intf);
+	struct vstusb_device *vstdev;
+	int i;
+	int retval = 0;
+
+	/* allocate memory for our device state and intialize it */
+
+	vstdev = kzalloc(sizeof(*vstdev), GFP_KERNEL);
+	if (vstdev == NULL)
+		return -ENOMEM;
+
+	mutex_init(&vstdev->lock);
+
+	i = dev->descriptor.bcdDevice;
+
+	dev_dbg(&intf->dev, "Version %1d%1d.%1d%1d found at address %d\n",
+		(i & 0xF000) >> 12, (i & 0xF00) >> 8,
+		(i & 0xF0) >> 4, (i & 0xF), dev->devnum);
+
+	vstdev->present = 1;
+	vstdev->isopen = 0;
+	vstdev->usb_dev = dev;
+	init_usb_anchor(&vstdev->submitted);
+
+	usb_set_intfdata(intf, vstdev);
+	retval = usb_register_dev(intf, &usb_vstusb_class);
+	if (retval) {
+		dev_err(&intf->dev,
+			"%s: Not able to get a minor for this device.\n",
+			__func__);
+		usb_set_intfdata(intf, NULL);
+		kfree(vstdev);
+		return retval;
+	}
+
+	/* let the user know what node this device is now attached to */
+	dev_info(&intf->dev,
+		 "VST USB Device #%d now attached to major %d minor %d\n",
+		 (intf->minor - VSTUSB_MINOR_BASE), USB_MAJOR, intf->minor);
+
+	dev_info(&intf->dev, "%s, %s\n", DRIVER_DESC, DRIVER_VERSION);
+
+	return retval;
+}
+
+static void vstusb_disconnect(struct usb_interface *intf)
+{
+	struct vstusb_device *vstdev = usb_get_intfdata(intf);
+
+	usb_deregister_dev(intf, &usb_vstusb_class);
+	usb_set_intfdata(intf, NULL);
+
+	if (vstdev) {
+
+		mutex_lock(&vstdev->lock);
+		vstdev->present = 0;
+
+		usb_kill_anchored_urbs(&vstdev->submitted);
+
+		/* if the device is not opened, then we clean up right now */
+		if (!vstdev->isopen) {
+			mutex_unlock(&vstdev->lock);
+			kfree(vstdev);
+		} else
+			mutex_unlock(&vstdev->lock);
+
+	}
+}
+
+static int vstusb_suspend(struct usb_interface *intf, pm_message_t message)
+{
+	struct vstusb_device *vstdev = usb_get_intfdata(intf);
+	int time;
+	if (!vstdev)
+		return 0;
+
+	mutex_lock(&vstdev->lock);
+	time = usb_wait_anchor_empty_timeout(&vstdev->submitted, 1000);
+	if (!time)
+		usb_kill_anchored_urbs(&vstdev->submitted);
+	mutex_unlock(&vstdev->lock);
+
+	return 0;
+}
+
+static int vstusb_resume(struct usb_interface *intf)
+{
+	return 0;
+}
+
+static struct usb_driver vstusb_driver = {
+	.name =         "vstusb",
+	.probe =        vstusb_probe,
+	.disconnect =   vstusb_disconnect,
+	.suspend =      vstusb_suspend,
+	.resume =       vstusb_resume,
+	.id_table = id_table,
+};
+
+static int __init vstusb_init(void)
+{
+	int rc;
+
+	rc = usb_register(&vstusb_driver);
+	if (rc)
+		printk(KERN_ERR "%s: failed to register (%d)", __func__, rc);
+
+	return rc;
+}
+
+static void __exit vstusb_exit(void)
+{
+	usb_deregister(&vstusb_driver);
+}
+
+module_init(vstusb_init);
+module_exit(vstusb_exit);
+
+MODULE_AUTHOR("Dennis O'Brien/Stephen Ware");
+MODULE_DESCRIPTION(DRIVER_VERSION);
+MODULE_LICENSE("GPL");
diff --git a/include/linux/usb/Kbuild b/include/linux/usb/Kbuild
index 29fd73b0bffc..54c446309a2a 100644
--- a/include/linux/usb/Kbuild
+++ b/include/linux/usb/Kbuild
@@ -5,3 +5,4 @@ header-y += gadgetfs.h
 header-y += midi.h
 header-y += g_printer.h
 header-y += tmc.h
+header-y += vstusb.h
diff --git a/include/linux/usb/vstusb.h b/include/linux/usb/vstusb.h
new file mode 100644
index 000000000000..1cfac67191ff
--- /dev/null
+++ b/include/linux/usb/vstusb.h
@@ -0,0 +1,71 @@
+/*****************************************************************************
+ *  File: drivers/usb/misc/vstusb.h
+ *
+ *  Purpose: Support for the bulk USB Vernier Spectrophotometers
+ *
+ *  Author:     EQware Engineering, Inc.
+ *              Oregon City, OR, USA 97045
+ *
+ *  Copyright:  2007, 2008
+ *              Vernier Software & Technology
+ *              Beaverton, OR, USA 97005
+ *
+ *  Web:        www.vernier.com
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2 as
+ *  published by the Free Software Foundation.
+ *
+ *****************************************************************************/
+/*****************************************************************************
+ *
+ *  The vstusb module is a standard usb 'client' driver running on top of the
+ *  standard usb host controller stack.
+ *
+ *  In general, vstusb supports standard bulk usb pipes.  It supports multiple
+ *  devices and multiple pipes per device.
+ *
+ *  The vstusb driver supports two interfaces:
+ *  1 - ioctl SEND_PIPE/RECV_PIPE - a general bulk write/read msg
+ *  	interface to any pipe with timeout support;
+ *  2 - standard read/write with ioctl config - offers standard read/write
+ *  	interface with ioctl configured pipes and timeouts.
+ *
+ *  Both interfaces can be signal from other process and will abort its i/o
+ *  operation.
+ *
+ *  A timeout of 0 means NO timeout.  The user can still terminate the read via
+ *  signal.
+ *
+ *  If using multiple threads with this driver, the user should ensure that
+ *  any reads, writes, or ioctls are complete before closing the device.
+ *  Changing read/write timeouts or pipes takes effect on next read/write.
+ *
+ *****************************************************************************/
+
+struct vstusb_args {
+	union {
+		/* this struct is used for IOCTL_VSTUSB_SEND_PIPE,	*
+		 * IOCTL_VSTUSB_RECV_PIPE, and read()/write() fops	*/
+		struct {
+			void __user	*buffer;
+			size_t          count;
+			unsigned int    timeout_ms;
+			int             pipe;
+		};
+
+		/* this one is used for IOCTL_VSTUSB_CONFIG_RW  	*/
+		struct {
+			int rd_pipe;
+			int rd_timeout_ms;
+			int wr_pipe;
+			int wr_timeout_ms;
+		};
+	};
+};
+
+#define VST_IOC_MAGIC 'L'
+#define VST_IOC_FIRST 0x20
+#define IOCTL_VSTUSB_SEND_PIPE	_IO(VST_IOC_MAGIC, VST_IOC_FIRST)
+#define IOCTL_VSTUSB_RECV_PIPE	_IO(VST_IOC_MAGIC, VST_IOC_FIRST + 1)
+#define IOCTL_VSTUSB_CONFIG_RW	_IO(VST_IOC_MAGIC, VST_IOC_FIRST + 2)
-- 
cgit v1.2.3


From 1987625226a918cd20c334ffce5e2a224cba0718 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oliver@neukum.org>
Date: Mon, 25 Aug 2008 22:40:25 +0200
Subject: USB: anchor API changes needed for btusb

This extends the anchor API as btusb needs for autosuspend.


Signed-off-by: Oliver Neukum <oneukum@suse.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
---
 drivers/usb/core/urb.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/usb.h    |  3 +++
 2 files changed, 73 insertions(+)

(limited to 'include')

diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index eebc070c3cc7..175d528f4029 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -716,3 +716,73 @@ int usb_wait_anchor_empty_timeout(struct usb_anchor *anchor,
 				  msecs_to_jiffies(timeout));
 }
 EXPORT_SYMBOL_GPL(usb_wait_anchor_empty_timeout);
+
+/**
+ * usb_get_from_anchor - get an anchor's oldest urb
+ * @anchor: the anchor whose urb you want
+ *
+ * this will take the oldest urb from an anchor,
+ * unanchor and return it
+ */
+struct urb *usb_get_from_anchor(struct usb_anchor *anchor)
+{
+	struct urb *victim;
+	unsigned long flags;
+
+	spin_lock_irqsave(&anchor->lock, flags);
+	if (!list_empty(&anchor->urb_list)) {
+		victim = list_entry(anchor->urb_list.next, struct urb,
+				    anchor_list);
+		usb_get_urb(victim);
+		spin_unlock_irqrestore(&anchor->lock, flags);
+		usb_unanchor_urb(victim);
+	} else {
+		spin_unlock_irqrestore(&anchor->lock, flags);
+		victim = NULL;
+	}
+
+	return victim;
+}
+
+EXPORT_SYMBOL_GPL(usb_get_from_anchor);
+
+/**
+ * usb_scuttle_anchored_urbs - unanchor all an anchor's urbs
+ * @anchor: the anchor whose urbs you want to unanchor
+ *
+ * use this to get rid of all an anchor's urbs
+ */
+void usb_scuttle_anchored_urbs(struct usb_anchor *anchor)
+{
+	struct urb *victim;
+	unsigned long flags;
+
+	spin_lock_irqsave(&anchor->lock, flags);
+	while (!list_empty(&anchor->urb_list)) {
+		victim = list_entry(anchor->urb_list.prev, struct urb,
+				    anchor_list);
+		usb_get_urb(victim);
+		spin_unlock_irqrestore(&anchor->lock, flags);
+		/* this may free the URB */
+		usb_unanchor_urb(victim);
+		usb_put_urb(victim);
+		spin_lock_irqsave(&anchor->lock, flags);
+	}
+	spin_unlock_irqrestore(&anchor->lock, flags);
+}
+
+EXPORT_SYMBOL_GPL(usb_scuttle_anchored_urbs);
+
+/**
+ * usb_anchor_empty - is an anchor empty
+ * @anchor: the anchor you want to query
+ *
+ * returns 1 if the anchor has no urbs associated with it
+ */
+int usb_anchor_empty(struct usb_anchor *anchor)
+{
+	return list_empty(&anchor->urb_list);
+}
+
+EXPORT_SYMBOL_GPL(usb_anchor_empty);
+
diff --git a/include/linux/usb.h b/include/linux/usb.h
index d97927970f54..8fa973bede5e 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1469,6 +1469,9 @@ extern void usb_anchor_urb(struct urb *urb, struct usb_anchor *anchor);
 extern void usb_unanchor_urb(struct urb *urb);
 extern int usb_wait_anchor_empty_timeout(struct usb_anchor *anchor,
 					 unsigned int timeout);
+extern struct urb *usb_get_from_anchor(struct usb_anchor *anchor);
+extern void usb_scuttle_anchored_urbs(struct usb_anchor *anchor);
+extern int usb_anchor_empty(struct usb_anchor *anchor);
 
 /**
  * usb_urb_dir_in - check if an URB describes an IN transfer
-- 
cgit v1.2.3


From aaf7ea20000436df3cbb397ccb734ad1e2e5164d Mon Sep 17 00:00:00 2001
From: Mike Rapoport <mike@compulab.co.il>
Date: Wed, 15 Oct 2008 08:38:49 +0200
Subject: [MTD] [NAND] GPIO NAND flash driver

The patch adds support for NAND flashes connected to GPIOs.

Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
Signed-off-by: Mike Rapoport <mike@compulab.co.il>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 drivers/mtd/nand/Kconfig      |   6 +
 drivers/mtd/nand/Makefile     |   1 +
 drivers/mtd/nand/gpio.c       | 375 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/nand-gpio.h |  19 +++
 4 files changed, 401 insertions(+)
 create mode 100644 drivers/mtd/nand/gpio.c
 create mode 100644 include/linux/mtd/nand-gpio.h

(limited to 'include')

diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 89b4d39386ab..b9eed9925462 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -56,6 +56,12 @@ config MTD_NAND_H1900
 	help
 	  This enables the driver for the iPAQ h1900 flash.
 
+config MTD_NAND_GPIO
+	tristate "GPIO NAND Flash driver"
+	depends on GENERIC_GPIO
+	help
+	  This enables a GPIO based NAND flash driver.
+
 config MTD_NAND_SPIA
 	tristate "NAND Flash device on SPIA board"
 	depends on ARCH_P720T
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 9bfeca324b32..b661586afbfc 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_MTD_NAND_NANDSIM)		+= nandsim.o
 obj-$(CONFIG_MTD_NAND_CS553X)		+= cs553x_nand.o
 obj-$(CONFIG_MTD_NAND_NDFC)		+= ndfc.o
 obj-$(CONFIG_MTD_NAND_ATMEL)		+= atmel_nand.o
+obj-$(CONFIG_MTD_NAND_GPIO)		+= gpio.o
 obj-$(CONFIG_MTD_NAND_CM_X270)		+= cmx270_nand.o
 obj-$(CONFIG_MTD_NAND_BASLER_EXCITE)	+= excite_nandflash.o
 obj-$(CONFIG_MTD_NAND_PXA3xx)		+= pxa3xx_nand.o
diff --git a/drivers/mtd/nand/gpio.c b/drivers/mtd/nand/gpio.c
new file mode 100644
index 000000000000..8f902e75aa85
--- /dev/null
+++ b/drivers/mtd/nand/gpio.c
@@ -0,0 +1,375 @@
+/*
+ * drivers/mtd/nand/gpio.c
+ *
+ * Updated, and converted to generic GPIO based driver by Russell King.
+ *
+ * Written by Ben Dooks <ben@simtec.co.uk>
+ *   Based on 2.4 version by Mark Whittaker
+ *
+ * © 2004 Simtec Electronics
+ *
+ * Device driver for NAND connected via GPIO
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/gpio.h>
+#include <linux/io.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/nand-gpio.h>
+
+struct gpiomtd {
+	void __iomem		*io_sync;
+	struct mtd_info		mtd_info;
+	struct nand_chip	nand_chip;
+	struct gpio_nand_platdata plat;
+};
+
+#define gpio_nand_getpriv(x) container_of(x, struct gpiomtd, mtd_info)
+
+
+#ifdef CONFIG_ARM
+/* gpio_nand_dosync()
+ *
+ * Make sure the GPIO state changes occur in-order with writes to NAND
+ * memory region.
+ * Needed on PXA due to bus-reordering within the SoC itself (see section on
+ * I/O ordering in PXA manual (section 2.3, p35)
+ */
+static void gpio_nand_dosync(struct gpiomtd *gpiomtd)
+{
+	unsigned long tmp;
+
+	if (gpiomtd->io_sync) {
+		/*
+		 * Linux memory barriers don't cater for what's required here.
+		 * What's required is what's here - a read from a separate
+		 * region with a dependency on that read.
+		 */
+		tmp = readl(gpiomtd->io_sync);
+		asm volatile("mov %1, %0\n" : "=r" (tmp) : "r" (tmp));
+	}
+}
+#else
+static inline void gpio_nand_dosync(struct gpiomtd *gpiomtd) {}
+#endif
+
+static void gpio_nand_cmd_ctrl(struct mtd_info *mtd, int cmd, unsigned int ctrl)
+{
+	struct gpiomtd *gpiomtd = gpio_nand_getpriv(mtd);
+
+	gpio_nand_dosync(gpiomtd);
+
+	if (ctrl & NAND_CTRL_CHANGE) {
+		gpio_set_value(gpiomtd->plat.gpio_nce, !(ctrl & NAND_NCE));
+		gpio_set_value(gpiomtd->plat.gpio_cle, !!(ctrl & NAND_CLE));
+		gpio_set_value(gpiomtd->plat.gpio_ale, !!(ctrl & NAND_ALE));
+		gpio_nand_dosync(gpiomtd);
+	}
+	if (cmd == NAND_CMD_NONE)
+		return;
+
+	writeb(cmd, gpiomtd->nand_chip.IO_ADDR_W);
+	gpio_nand_dosync(gpiomtd);
+}
+
+static void gpio_nand_writebuf(struct mtd_info *mtd, const u_char *buf, int len)
+{
+	struct nand_chip *this = mtd->priv;
+
+	writesb(this->IO_ADDR_W, buf, len);
+}
+
+static void gpio_nand_readbuf(struct mtd_info *mtd, u_char *buf, int len)
+{
+	struct nand_chip *this = mtd->priv;
+
+	readsb(this->IO_ADDR_R, buf, len);
+}
+
+static int gpio_nand_verifybuf(struct mtd_info *mtd, const u_char *buf, int len)
+{
+	struct nand_chip *this = mtd->priv;
+	unsigned char read, *p = (unsigned char *) buf;
+	int i, err = 0;
+
+	for (i = 0; i < len; i++) {
+		read = readb(this->IO_ADDR_R);
+		if (read != p[i]) {
+			pr_debug("%s: err at %d (read %04x vs %04x)\n",
+			       __func__, i, read, p[i]);
+			err = -EFAULT;
+		}
+	}
+	return err;
+}
+
+static void gpio_nand_writebuf16(struct mtd_info *mtd, const u_char *buf,
+				 int len)
+{
+	struct nand_chip *this = mtd->priv;
+
+	if (IS_ALIGNED((unsigned long)buf, 2)) {
+		writesw(this->IO_ADDR_W, buf, len>>1);
+	} else {
+		int i;
+		unsigned short *ptr = (unsigned short *)buf;
+
+		for (i = 0; i < len; i += 2, ptr++)
+			writew(*ptr, this->IO_ADDR_W);
+	}
+}
+
+static void gpio_nand_readbuf16(struct mtd_info *mtd, u_char *buf, int len)
+{
+	struct nand_chip *this = mtd->priv;
+
+	if (IS_ALIGNED((unsigned long)buf, 2)) {
+		readsw(this->IO_ADDR_R, buf, len>>1);
+	} else {
+		int i;
+		unsigned short *ptr = (unsigned short *)buf;
+
+		for (i = 0; i < len; i += 2, ptr++)
+			*ptr = readw(this->IO_ADDR_R);
+	}
+}
+
+static int gpio_nand_verifybuf16(struct mtd_info *mtd, const u_char *buf,
+				 int len)
+{
+	struct nand_chip *this = mtd->priv;
+	unsigned short read, *p = (unsigned short *) buf;
+	int i, err = 0;
+	len >>= 1;
+
+	for (i = 0; i < len; i++) {
+		read = readw(this->IO_ADDR_R);
+		if (read != p[i]) {
+			pr_debug("%s: err at %d (read %04x vs %04x)\n",
+			       __func__, i, read, p[i]);
+			err = -EFAULT;
+		}
+	}
+	return err;
+}
+
+
+static int gpio_nand_devready(struct mtd_info *mtd)
+{
+	struct gpiomtd *gpiomtd = gpio_nand_getpriv(mtd);
+	return gpio_get_value(gpiomtd->plat.gpio_rdy);
+}
+
+static int __devexit gpio_nand_remove(struct platform_device *dev)
+{
+	struct gpiomtd *gpiomtd = platform_get_drvdata(dev);
+	struct resource *res;
+
+	nand_release(&gpiomtd->mtd_info);
+
+	res = platform_get_resource(dev, IORESOURCE_MEM, 1);
+	iounmap(gpiomtd->io_sync);
+	if (res)
+		release_mem_region(res->start, res->end - res->start + 1);
+
+	res = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	iounmap(gpiomtd->nand_chip.IO_ADDR_R);
+	release_mem_region(res->start, res->end - res->start + 1);
+
+	if (gpio_is_valid(gpiomtd->plat.gpio_nwp))
+		gpio_set_value(gpiomtd->plat.gpio_nwp, 0);
+	gpio_set_value(gpiomtd->plat.gpio_nce, 1);
+
+	gpio_free(gpiomtd->plat.gpio_cle);
+	gpio_free(gpiomtd->plat.gpio_ale);
+	gpio_free(gpiomtd->plat.gpio_nce);
+	if (gpio_is_valid(gpiomtd->plat.gpio_nwp))
+		gpio_free(gpiomtd->plat.gpio_nwp);
+	gpio_free(gpiomtd->plat.gpio_rdy);
+
+	kfree(gpiomtd);
+
+	return 0;
+}
+
+static void __iomem *request_and_remap(struct resource *res, size_t size,
+					const char *name, int *err)
+{
+	void __iomem *ptr;
+
+	if (!request_mem_region(res->start, res->end - res->start + 1, name)) {
+		*err = -EBUSY;
+		return NULL;
+	}
+
+	ptr = ioremap(res->start, size);
+	if (!ptr) {
+		release_mem_region(res->start, res->end - res->start + 1);
+		*err = -ENOMEM;
+	}
+	return ptr;
+}
+
+static int __devinit gpio_nand_probe(struct platform_device *dev)
+{
+	struct gpiomtd *gpiomtd;
+	struct nand_chip *this;
+	struct resource *res0, *res1;
+	int ret;
+
+	if (!dev->dev.platform_data)
+		return -EINVAL;
+
+	res0 = platform_get_resource(dev, IORESOURCE_MEM, 0);
+	if (!res0)
+		return -EINVAL;
+
+	gpiomtd = kzalloc(sizeof(*gpiomtd), GFP_KERNEL);
+	if (gpiomtd == NULL) {
+		dev_err(&dev->dev, "failed to create NAND MTD\n");
+		return -ENOMEM;
+	}
+
+	this = &gpiomtd->nand_chip;
+	this->IO_ADDR_R = request_and_remap(res0, 2, "NAND", &ret);
+	if (!this->IO_ADDR_R) {
+		dev_err(&dev->dev, "unable to map NAND\n");
+		goto err_map;
+	}
+
+	res1 = platform_get_resource(dev, IORESOURCE_MEM, 1);
+	if (res1) {
+		gpiomtd->io_sync = request_and_remap(res1, 4, "NAND sync", &ret);
+		if (!gpiomtd->io_sync) {
+			dev_err(&dev->dev, "unable to map sync NAND\n");
+			goto err_sync;
+		}
+	}
+
+	memcpy(&gpiomtd->plat, dev->dev.platform_data, sizeof(gpiomtd->plat));
+
+	ret = gpio_request(gpiomtd->plat.gpio_nce, "NAND NCE");
+	if (ret)
+		goto err_nce;
+	gpio_direction_output(gpiomtd->plat.gpio_nce, 1);
+	if (gpio_is_valid(gpiomtd->plat.gpio_nwp)) {
+		ret = gpio_request(gpiomtd->plat.gpio_nwp, "NAND NWP");
+		if (ret)
+			goto err_nwp;
+		gpio_direction_output(gpiomtd->plat.gpio_nwp, 1);
+	}
+	ret = gpio_request(gpiomtd->plat.gpio_ale, "NAND ALE");
+	if (ret)
+		goto err_ale;
+	gpio_direction_output(gpiomtd->plat.gpio_ale, 0);
+	ret = gpio_request(gpiomtd->plat.gpio_cle, "NAND CLE");
+	if (ret)
+		goto err_cle;
+	gpio_direction_output(gpiomtd->plat.gpio_cle, 0);
+	ret = gpio_request(gpiomtd->plat.gpio_rdy, "NAND RDY");
+	if (ret)
+		goto err_rdy;
+	gpio_direction_input(gpiomtd->plat.gpio_rdy);
+
+
+	this->IO_ADDR_W  = this->IO_ADDR_R;
+	this->ecc.mode   = NAND_ECC_SOFT;
+	this->options    = gpiomtd->plat.options;
+	this->chip_delay = gpiomtd->plat.chip_delay;
+
+	/* install our routines */
+	this->cmd_ctrl   = gpio_nand_cmd_ctrl;
+	this->dev_ready  = gpio_nand_devready;
+
+	if (this->options & NAND_BUSWIDTH_16) {
+		this->read_buf   = gpio_nand_readbuf16;
+		this->write_buf  = gpio_nand_writebuf16;
+		this->verify_buf = gpio_nand_verifybuf16;
+	} else {
+		this->read_buf   = gpio_nand_readbuf;
+		this->write_buf  = gpio_nand_writebuf;
+		this->verify_buf = gpio_nand_verifybuf;
+	}
+
+	/* set the mtd private data for the nand driver */
+	gpiomtd->mtd_info.priv = this;
+	gpiomtd->mtd_info.owner = THIS_MODULE;
+
+	if (nand_scan(&gpiomtd->mtd_info, 1)) {
+		dev_err(&dev->dev, "no nand chips found?\n");
+		ret = -ENXIO;
+		goto err_wp;
+	}
+
+	if (gpiomtd->plat.adjust_parts)
+		gpiomtd->plat.adjust_parts(&gpiomtd->plat,
+					   gpiomtd->mtd_info.size);
+
+	add_mtd_partitions(&gpiomtd->mtd_info, gpiomtd->plat.parts,
+			   gpiomtd->plat.num_parts);
+	platform_set_drvdata(dev, gpiomtd);
+
+	return 0;
+
+err_wp:
+	if (gpio_is_valid(gpiomtd->plat.gpio_nwp))
+		gpio_set_value(gpiomtd->plat.gpio_nwp, 0);
+	gpio_free(gpiomtd->plat.gpio_rdy);
+err_rdy:
+	gpio_free(gpiomtd->plat.gpio_cle);
+err_cle:
+	gpio_free(gpiomtd->plat.gpio_ale);
+err_ale:
+	if (gpio_is_valid(gpiomtd->plat.gpio_nwp))
+		gpio_free(gpiomtd->plat.gpio_nwp);
+err_nwp:
+	gpio_free(gpiomtd->plat.gpio_nce);
+err_nce:
+	iounmap(gpiomtd->io_sync);
+	if (res1)
+		release_mem_region(res1->start, res1->end - res1->start + 1);
+err_sync:
+	iounmap(gpiomtd->nand_chip.IO_ADDR_R);
+	release_mem_region(res0->start, res0->end - res0->start + 1);
+err_map:
+	kfree(gpiomtd);
+	return ret;
+}
+
+static struct platform_driver gpio_nand_driver = {
+	.probe		= gpio_nand_probe,
+	.remove		= gpio_nand_remove,
+	.driver		= {
+		.name	= "gpio-nand",
+	},
+};
+
+static int __init gpio_nand_init(void)
+{
+	printk(KERN_INFO "GPIO NAND driver, © 2004 Simtec Electronics\n");
+
+	return platform_driver_register(&gpio_nand_driver);
+}
+
+static void __exit gpio_nand_exit(void)
+{
+	platform_driver_unregister(&gpio_nand_driver);
+}
+
+module_init(gpio_nand_init);
+module_exit(gpio_nand_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Ben Dooks <ben@simtec.co.uk>");
+MODULE_DESCRIPTION("GPIO NAND Driver");
diff --git a/include/linux/mtd/nand-gpio.h b/include/linux/mtd/nand-gpio.h
new file mode 100644
index 000000000000..51534e50f7fc
--- /dev/null
+++ b/include/linux/mtd/nand-gpio.h
@@ -0,0 +1,19 @@
+#ifndef __LINUX_MTD_NAND_GPIO_H
+#define __LINUX_MTD_NAND_GPIO_H
+
+#include <linux/mtd/nand.h>
+
+struct gpio_nand_platdata {
+	int	gpio_nce;
+	int	gpio_nwp;
+	int	gpio_cle;
+	int	gpio_ale;
+	int	gpio_rdy;
+	void	(*adjust_parts)(struct gpio_nand_platdata *, size_t);
+	struct mtd_partition *parts;
+	unsigned int num_parts;
+	unsigned int options;
+	int	chip_delay;
+};
+
+#endif
-- 
cgit v1.2.3


From dd3a1db900f2a215a7d7dd71b836e149a6cf5fed Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 16 Oct 2008 18:20:58 +0200
Subject: genirq: improve include files

Move the irq_desc related iterators out of irq.h, into irqnr.h, also
available via interrupt.h.

This way non-genirq (and even non-hardirq) architectures get the
common definitions and iterators.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 include/linux/interrupt.h |  1 +
 include/linux/irq.h       | 20 +-------------------
 include/linux/irqnr.h     | 24 ++++++++++++++++++++++++
 3 files changed, 26 insertions(+), 19 deletions(-)
 create mode 100644 include/linux/irqnr.h

(limited to 'include')

diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 58ff4e74b2f3..72fcfcff5637 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -8,6 +8,7 @@
 #include <linux/preempt.h>
 #include <linux/cpumask.h>
 #include <linux/irqreturn.h>
+#include <linux/irqnr.h>
 #include <linux/hardirq.h>
 #include <linux/sched.h>
 #include <linux/irqflags.h>
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 0618fb362cb4..d058c57be02d 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -11,25 +11,6 @@
 
 #include <linux/smp.h>
 
-#ifndef CONFIG_GENERIC_HARDIRQS
-# define nr_irqs		NR_IRQS
-
-# define for_each_irq_desc(irq, desc)		\
-	for (irq = 0; irq < nr_irqs; irq++)
-#else
-extern int nr_irqs;
-
-# define for_each_irq_desc(irq, desc)		\
-	for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc++)
-
-# define for_each_irq_desc_reverse(irq, desc)			\
-	for (irq = nr_irqs -1, desc = irq_desc + (nr_irqs -1 );	\
-	     irq > 0; irq--, desc--)
-#endif
-
-#define for_each_irq_nr(irq)			\
-	for (irq = 0; irq < nr_irqs; irq++)
-
 #ifndef CONFIG_S390
 
 #include <linux/linkage.h>
@@ -37,6 +18,7 @@ extern int nr_irqs;
 #include <linux/spinlock.h>
 #include <linux/cpumask.h>
 #include <linux/irqreturn.h>
+#include <linux/irqnr.h>
 #include <linux/errno.h>
 
 #include <asm/irq.h>
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
new file mode 100644
index 000000000000..3171ddc3b39d
--- /dev/null
+++ b/include/linux/irqnr.h
@@ -0,0 +1,24 @@
+#ifndef _LINUX_IRQNR_H
+#define _LINUX_IRQNR_H
+
+#ifndef CONFIG_GENERIC_HARDIRQS
+#include <asm/irq.h>
+# define nr_irqs		NR_IRQS
+
+# define for_each_irq_desc(irq, desc)		\
+	for (irq = 0; irq < nr_irqs; irq++)
+#else
+extern int nr_irqs;
+
+# define for_each_irq_desc(irq, desc)		\
+	for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc++)
+
+# define for_each_irq_desc_reverse(irq, desc)			\
+	for (irq = nr_irqs -1, desc = irq_desc + (nr_irqs -1 );	\
+	     irq > 0; irq--, desc--)
+#endif
+
+#define for_each_irq_nr(irq)			\
+	for (irq = 0; irq < nr_irqs; irq++)
+
+#endif
-- 
cgit v1.2.3


From 5b6985ce8ec7127b4d60ad450b64ca8b82748a3b Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Thu, 16 Oct 2008 18:02:32 -0700
Subject: intel-iommu: IA64 support

The current Intel IOMMU code assumes that both host page size and Intel
IOMMU page size are 4KiB. The first patch supports variable page size.
This provides support for IA64 which has multiple page sizes.

This patch also adds some other code hooks for IA64 platform including
DMAR_OPERATION_TIMEOUT definition.

[dwmw2: some cleanup]
Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: David Woodhouse <David.Woodhouse@intel.com>
---
 arch/x86/kernel/pci-dma.c     |  16 ------
 drivers/pci/dmar.c            |  19 ++++---
 drivers/pci/intel-iommu.c     | 128 ++++++++++++++++++++++--------------------
 drivers/pci/quirks.c          |  14 +++++
 include/asm-x86/iommu.h       |   4 ++
 include/linux/dma_remapping.h |  27 +++++----
 include/linux/intel-iommu.h   |  39 +++++++------
 7 files changed, 131 insertions(+), 116 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 192624820217..1972266e8ba5 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -9,8 +9,6 @@
 #include <asm/calgary.h>
 #include <asm/amd_iommu.h>
 
-static int forbid_dac __read_mostly;
-
 struct dma_mapping_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
@@ -293,17 +291,3 @@ void pci_iommu_shutdown(void)
 }
 /* Must execute after PCI subsystem */
 fs_initcall(pci_iommu_init);
-
-#ifdef CONFIG_PCI
-/* Many VIA bridges seem to corrupt data for DAC. Disable it here */
-
-static __devinit void via_no_dac(struct pci_dev *dev)
-{
-	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) {
-		printk(KERN_INFO "PCI: VIA PCI bridge detected."
-				 "Disabling DAC.\n");
-		forbid_dac = 1;
-	}
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac);
-#endif
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 44d6c7081b8f..b65173828bc2 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -277,14 +277,15 @@ dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
 		drhd = (struct acpi_dmar_hardware_unit *)header;
 		printk (KERN_INFO PREFIX
 			"DRHD (flags: 0x%08x)base: 0x%016Lx\n",
-			drhd->flags, drhd->address);
+			drhd->flags, (unsigned long long)drhd->address);
 		break;
 	case ACPI_DMAR_TYPE_RESERVED_MEMORY:
 		rmrr = (struct acpi_dmar_reserved_memory *)header;
 
 		printk (KERN_INFO PREFIX
 			"RMRR base: 0x%016Lx end: 0x%016Lx\n",
-			rmrr->base_address, rmrr->end_address);
+			(unsigned long long)rmrr->base_address,
+			(unsigned long long)rmrr->end_address);
 		break;
 	}
 }
@@ -304,7 +305,7 @@ parse_dmar_table(void)
 	if (!dmar)
 		return -ENODEV;
 
-	if (dmar->width < PAGE_SHIFT_4K - 1) {
+	if (dmar->width < PAGE_SHIFT - 1) {
 		printk(KERN_WARNING PREFIX "Invalid DMAR haw\n");
 		return -EINVAL;
 	}
@@ -493,7 +494,7 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 
 	iommu->seq_id = iommu_allocated++;
 
-	iommu->reg = ioremap(drhd->reg_base_addr, PAGE_SIZE_4K);
+	iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE);
 	if (!iommu->reg) {
 		printk(KERN_ERR "IOMMU: can't map the region\n");
 		goto error;
@@ -504,8 +505,8 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 	/* the registers might be more than one page */
 	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
 		cap_max_fault_reg_offset(iommu->cap));
-	map_size = PAGE_ALIGN_4K(map_size);
-	if (map_size > PAGE_SIZE_4K) {
+	map_size = VTD_PAGE_ALIGN(map_size);
+	if (map_size > VTD_PAGE_SIZE) {
 		iounmap(iommu->reg);
 		iommu->reg = ioremap(drhd->reg_base_addr, map_size);
 		if (!iommu->reg) {
@@ -516,8 +517,10 @@ int alloc_iommu(struct dmar_drhd_unit *drhd)
 
 	ver = readl(iommu->reg + DMAR_VER_REG);
 	pr_debug("IOMMU %llx: ver %d:%d cap %llx ecap %llx\n",
-		drhd->reg_base_addr, DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
-		iommu->cap, iommu->ecap);
+		(unsigned long long)drhd->reg_base_addr,
+		DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
+		(unsigned long long)iommu->cap,
+		(unsigned long long)iommu->ecap);
 
 	spin_lock_init(&iommu->register_lock);
 
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 509470419130..2bf96babbc4f 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -18,6 +18,7 @@
  * Author: Ashok Raj <ashok.raj@intel.com>
  * Author: Shaohua Li <shaohua.li@intel.com>
  * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
+ * Author: Fenghua Yu <fenghua.yu@intel.com>
  */
 
 #include <linux/init.h>
@@ -35,11 +36,13 @@
 #include <linux/timer.h>
 #include <linux/iova.h>
 #include <linux/intel-iommu.h>
-#include <asm/proto.h> /* force_iommu in this header in x86-64*/
 #include <asm/cacheflush.h>
 #include <asm/iommu.h>
 #include "pci.h"
 
+#define ROOT_SIZE		VTD_PAGE_SIZE
+#define CONTEXT_SIZE		VTD_PAGE_SIZE
+
 #define IS_GFX_DEVICE(pdev) ((pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY)
 #define IS_ISA_DEVICE(pdev) ((pdev->class >> 8) == PCI_CLASS_BRIDGE_ISA)
 
@@ -199,7 +202,7 @@ static struct context_entry * device_to_context_entry(struct intel_iommu *iommu,
 			spin_unlock_irqrestore(&iommu->lock, flags);
 			return NULL;
 		}
-		__iommu_flush_cache(iommu, (void *)context, PAGE_SIZE_4K);
+		__iommu_flush_cache(iommu, (void *)context, CONTEXT_SIZE);
 		phy_addr = virt_to_phys((void *)context);
 		set_root_value(root, phy_addr);
 		set_root_present(root);
@@ -345,7 +348,7 @@ static struct dma_pte * addr_to_dma_pte(struct dmar_domain *domain, u64 addr)
 				return NULL;
 			}
 			__iommu_flush_cache(domain->iommu, tmp_page,
-					PAGE_SIZE_4K);
+					PAGE_SIZE);
 			dma_set_pte_addr(*pte, virt_to_phys(tmp_page));
 			/*
 			 * high level table always sets r/w, last level page
@@ -408,13 +411,13 @@ static void dma_pte_clear_range(struct dmar_domain *domain, u64 start, u64 end)
 	start &= (((u64)1) << addr_width) - 1;
 	end &= (((u64)1) << addr_width) - 1;
 	/* in case it's partial page */
-	start = PAGE_ALIGN_4K(start);
-	end &= PAGE_MASK_4K;
+	start = PAGE_ALIGN(start);
+	end &= PAGE_MASK;
 
 	/* we don't need lock here, nobody else touches the iova range */
 	while (start < end) {
 		dma_pte_clear_one(domain, start);
-		start += PAGE_SIZE_4K;
+		start += VTD_PAGE_SIZE;
 	}
 }
 
@@ -468,7 +471,7 @@ static int iommu_alloc_root_entry(struct intel_iommu *iommu)
 	if (!root)
 		return -ENOMEM;
 
-	__iommu_flush_cache(iommu, root, PAGE_SIZE_4K);
+	__iommu_flush_cache(iommu, root, ROOT_SIZE);
 
 	spin_lock_irqsave(&iommu->lock, flags);
 	iommu->root_entry = root;
@@ -634,7 +637,8 @@ static int __iommu_flush_iotlb(struct intel_iommu *iommu, u16 did,
 		printk(KERN_ERR"IOMMU: flush IOTLB failed\n");
 	if (DMA_TLB_IAIG(val) != DMA_TLB_IIRG(type))
 		pr_debug("IOMMU: tlb flush request %Lx, actual %Lx\n",
-			DMA_TLB_IIRG(type), DMA_TLB_IAIG(val));
+			(unsigned long long)DMA_TLB_IIRG(type),
+			(unsigned long long)DMA_TLB_IAIG(val));
 	/* flush context entry will implictly flush write buffer */
 	return 0;
 }
@@ -644,7 +648,7 @@ static int iommu_flush_iotlb_psi(struct intel_iommu *iommu, u16 did,
 {
 	unsigned int mask;
 
-	BUG_ON(addr & (~PAGE_MASK_4K));
+	BUG_ON(addr & (~VTD_PAGE_MASK));
 	BUG_ON(pages == 0);
 
 	/* Fallback to domain selective flush if no PSI support */
@@ -798,7 +802,7 @@ void dmar_msi_read(int irq, struct msi_msg *msg)
 }
 
 static int iommu_page_fault_do_one(struct intel_iommu *iommu, int type,
-		u8 fault_reason, u16 source_id, u64 addr)
+		u8 fault_reason, u16 source_id, unsigned long long addr)
 {
 	const char *reason;
 
@@ -1051,9 +1055,9 @@ static void dmar_init_reserved_ranges(void)
 			if (!r->flags || !(r->flags & IORESOURCE_MEM))
 				continue;
 			addr = r->start;
-			addr &= PAGE_MASK_4K;
+			addr &= PAGE_MASK;
 			size = r->end - addr;
-			size = PAGE_ALIGN_4K(size);
+			size = PAGE_ALIGN(size);
 			iova = reserve_iova(&reserved_iova_list, IOVA_PFN(addr),
 				IOVA_PFN(size + addr) - 1);
 			if (!iova)
@@ -1115,7 +1119,7 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	domain->pgd = (struct dma_pte *)alloc_pgtable_page();
 	if (!domain->pgd)
 		return -ENOMEM;
-	__iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE_4K);
+	__iommu_flush_cache(iommu, domain->pgd, PAGE_SIZE);
 	return 0;
 }
 
@@ -1131,7 +1135,7 @@ static void domain_exit(struct dmar_domain *domain)
 	/* destroy iovas */
 	put_iova_domain(&domain->iovad);
 	end = DOMAIN_MAX_ADDR(domain->gaw);
-	end = end & (~PAGE_MASK_4K);
+	end = end & (~PAGE_MASK);
 
 	/* clear ptes */
 	dma_pte_clear_range(domain, 0, end);
@@ -1252,22 +1256,25 @@ domain_page_mapping(struct dmar_domain *domain, dma_addr_t iova,
 	u64 start_pfn, end_pfn;
 	struct dma_pte *pte;
 	int index;
+	int addr_width = agaw_to_width(domain->agaw);
+
+	hpa &= (((u64)1) << addr_width) - 1;
 
 	if ((prot & (DMA_PTE_READ|DMA_PTE_WRITE)) == 0)
 		return -EINVAL;
-	iova &= PAGE_MASK_4K;
-	start_pfn = ((u64)hpa) >> PAGE_SHIFT_4K;
-	end_pfn = (PAGE_ALIGN_4K(((u64)hpa) + size)) >> PAGE_SHIFT_4K;
+	iova &= PAGE_MASK;
+	start_pfn = ((u64)hpa) >> VTD_PAGE_SHIFT;
+	end_pfn = (VTD_PAGE_ALIGN(((u64)hpa) + size)) >> VTD_PAGE_SHIFT;
 	index = 0;
 	while (start_pfn < end_pfn) {
-		pte = addr_to_dma_pte(domain, iova + PAGE_SIZE_4K * index);
+		pte = addr_to_dma_pte(domain, iova + VTD_PAGE_SIZE * index);
 		if (!pte)
 			return -ENOMEM;
 		/* We don't need lock here, nobody else
 		 * touches the iova range
 		 */
 		BUG_ON(dma_pte_addr(*pte));
-		dma_set_pte_addr(*pte, start_pfn << PAGE_SHIFT_4K);
+		dma_set_pte_addr(*pte, start_pfn << VTD_PAGE_SHIFT);
 		dma_set_pte_prot(*pte, prot);
 		__iommu_flush_cache(domain->iommu, pte, sizeof(*pte));
 		start_pfn++;
@@ -1445,11 +1452,13 @@ error:
 	return find_domain(pdev);
 }
 
-static int iommu_prepare_identity_map(struct pci_dev *pdev, u64 start, u64 end)
+static int iommu_prepare_identity_map(struct pci_dev *pdev,
+				      unsigned long long start,
+				      unsigned long long end)
 {
 	struct dmar_domain *domain;
 	unsigned long size;
-	u64 base;
+	unsigned long long base;
 	int ret;
 
 	printk(KERN_INFO
@@ -1461,9 +1470,9 @@ static int iommu_prepare_identity_map(struct pci_dev *pdev, u64 start, u64 end)
 		return -ENOMEM;
 
 	/* The address might not be aligned */
-	base = start & PAGE_MASK_4K;
+	base = start & PAGE_MASK;
 	size = end - base;
-	size = PAGE_ALIGN_4K(size);
+	size = PAGE_ALIGN(size);
 	if (!reserve_iova(&domain->iovad, IOVA_PFN(base),
 			IOVA_PFN(base + size) - 1)) {
 		printk(KERN_ERR "IOMMU: reserve iova failed\n");
@@ -1732,8 +1741,8 @@ error:
 static inline u64 aligned_size(u64 host_addr, size_t size)
 {
 	u64 addr;
-	addr = (host_addr & (~PAGE_MASK_4K)) + size;
-	return PAGE_ALIGN_4K(addr);
+	addr = (host_addr & (~PAGE_MASK)) + size;
+	return PAGE_ALIGN(addr);
 }
 
 struct iova *
@@ -1747,7 +1756,7 @@ iommu_alloc_iova(struct dmar_domain *domain, size_t size, u64 end)
 		return NULL;
 
 	piova = alloc_iova(&domain->iovad,
-			size >> PAGE_SHIFT_4K, IOVA_PFN(end), 1);
+			size >> PAGE_SHIFT, IOVA_PFN(end), 1);
 	return piova;
 }
 
@@ -1807,12 +1816,12 @@ get_valid_domain_for_dev(struct pci_dev *pdev)
 	return domain;
 }
 
-static dma_addr_t
+dma_addr_t
 intel_map_single(struct device *hwdev, phys_addr_t paddr, size_t size, int dir)
 {
 	struct pci_dev *pdev = to_pci_dev(hwdev);
 	struct dmar_domain *domain;
-	unsigned long start_paddr;
+	phys_addr_t start_paddr;
 	struct iova *iova;
 	int prot = 0;
 	int ret;
@@ -1831,7 +1840,7 @@ intel_map_single(struct device *hwdev, phys_addr_t paddr, size_t size, int dir)
 	if (!iova)
 		goto error;
 
-	start_paddr = iova->pfn_lo << PAGE_SHIFT_4K;
+	start_paddr = (phys_addr_t)iova->pfn_lo << PAGE_SHIFT;
 
 	/*
 	 * Check if DMAR supports zero-length reads on write only
@@ -1849,27 +1858,23 @@ intel_map_single(struct device *hwdev, phys_addr_t paddr, size_t size, int dir)
 	 * is not a big problem
 	 */
 	ret = domain_page_mapping(domain, start_paddr,
-		((u64)paddr) & PAGE_MASK_4K, size, prot);
+		((u64)paddr) & PAGE_MASK, size, prot);
 	if (ret)
 		goto error;
 
-	pr_debug("Device %s request: %lx@%llx mapping: %lx@%llx, dir %d\n",
-		pci_name(pdev), size, (u64)paddr,
-		size, (u64)start_paddr, dir);
-
 	/* it's a non-present to present mapping */
 	ret = iommu_flush_iotlb_psi(domain->iommu, domain->id,
-			start_paddr, size >> PAGE_SHIFT_4K, 1);
+			start_paddr, size >> VTD_PAGE_SHIFT, 1);
 	if (ret)
 		iommu_flush_write_buffer(domain->iommu);
 
-	return (start_paddr + ((u64)paddr & (~PAGE_MASK_4K)));
+	return start_paddr + ((u64)paddr & (~PAGE_MASK));
 
 error:
 	if (iova)
 		__free_iova(&domain->iovad, iova);
 	printk(KERN_ERR"Device %s request: %lx@%llx dir %d --- failed\n",
-		pci_name(pdev), size, (u64)paddr, dir);
+		pci_name(pdev), size, (unsigned long long)paddr, dir);
 	return 0;
 }
 
@@ -1931,8 +1936,8 @@ static void add_unmap(struct dmar_domain *dom, struct iova *iova)
 	spin_unlock_irqrestore(&async_umap_flush_lock, flags);
 }
 
-static void intel_unmap_single(struct device *dev, dma_addr_t dev_addr,
-	size_t size, int dir)
+void intel_unmap_single(struct device *dev, dma_addr_t dev_addr, size_t size,
+			int dir)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct dmar_domain *domain;
@@ -1948,11 +1953,11 @@ static void intel_unmap_single(struct device *dev, dma_addr_t dev_addr,
 	if (!iova)
 		return;
 
-	start_addr = iova->pfn_lo << PAGE_SHIFT_4K;
+	start_addr = iova->pfn_lo << PAGE_SHIFT;
 	size = aligned_size((u64)dev_addr, size);
 
 	pr_debug("Device %s unmapping: %lx@%llx\n",
-		pci_name(pdev), size, (u64)start_addr);
+		pci_name(pdev), size, (unsigned long long)start_addr);
 
 	/*  clear the whole page */
 	dma_pte_clear_range(domain, start_addr, start_addr + size);
@@ -1960,7 +1965,7 @@ static void intel_unmap_single(struct device *dev, dma_addr_t dev_addr,
 	dma_pte_free_pagetable(domain, start_addr, start_addr + size);
 	if (intel_iommu_strict) {
 		if (iommu_flush_iotlb_psi(domain->iommu,
-			domain->id, start_addr, size >> PAGE_SHIFT_4K, 0))
+			domain->id, start_addr, size >> VTD_PAGE_SHIFT, 0))
 			iommu_flush_write_buffer(domain->iommu);
 		/* free iova */
 		__free_iova(&domain->iovad, iova);
@@ -1973,13 +1978,13 @@ static void intel_unmap_single(struct device *dev, dma_addr_t dev_addr,
 	}
 }
 
-static void * intel_alloc_coherent(struct device *hwdev, size_t size,
-		       dma_addr_t *dma_handle, gfp_t flags)
+void *intel_alloc_coherent(struct device *hwdev, size_t size,
+			   dma_addr_t *dma_handle, gfp_t flags)
 {
 	void *vaddr;
 	int order;
 
-	size = PAGE_ALIGN_4K(size);
+	size = PAGE_ALIGN(size);
 	order = get_order(size);
 	flags &= ~(GFP_DMA | GFP_DMA32);
 
@@ -1995,12 +2000,12 @@ static void * intel_alloc_coherent(struct device *hwdev, size_t size,
 	return NULL;
 }
 
-static void intel_free_coherent(struct device *hwdev, size_t size,
-	void *vaddr, dma_addr_t dma_handle)
+void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
+			 dma_addr_t dma_handle)
 {
 	int order;
 
-	size = PAGE_ALIGN_4K(size);
+	size = PAGE_ALIGN(size);
 	order = get_order(size);
 
 	intel_unmap_single(hwdev, dma_handle, size, DMA_BIDIRECTIONAL);
@@ -2008,8 +2013,9 @@ static void intel_free_coherent(struct device *hwdev, size_t size,
 }
 
 #define SG_ENT_VIRT_ADDRESS(sg)	(sg_virt((sg)))
-static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
-	int nelems, int dir)
+
+void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
+		    int nelems, int dir)
 {
 	int i;
 	struct pci_dev *pdev = to_pci_dev(hwdev);
@@ -2033,7 +2039,7 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
 		size += aligned_size((u64)addr, sg->length);
 	}
 
-	start_addr = iova->pfn_lo << PAGE_SHIFT_4K;
+	start_addr = iova->pfn_lo << PAGE_SHIFT;
 
 	/*  clear the whole page */
 	dma_pte_clear_range(domain, start_addr, start_addr + size);
@@ -2041,7 +2047,7 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
 	dma_pte_free_pagetable(domain, start_addr, start_addr + size);
 
 	if (iommu_flush_iotlb_psi(domain->iommu, domain->id, start_addr,
-			size >> PAGE_SHIFT_4K, 0))
+			size >> VTD_PAGE_SHIFT, 0))
 		iommu_flush_write_buffer(domain->iommu);
 
 	/* free iova */
@@ -2062,8 +2068,8 @@ static int intel_nontranslate_map_sg(struct device *hddev,
 	return nelems;
 }
 
-static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist,
-				int nelems, int dir)
+int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems,
+		 int dir)
 {
 	void *addr;
 	int i;
@@ -2107,14 +2113,14 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist,
 	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
 		prot |= DMA_PTE_WRITE;
 
-	start_addr = iova->pfn_lo << PAGE_SHIFT_4K;
+	start_addr = iova->pfn_lo << PAGE_SHIFT;
 	offset = 0;
 	for_each_sg(sglist, sg, nelems, i) {
 		addr = SG_ENT_VIRT_ADDRESS(sg);
 		addr = (void *)virt_to_phys(addr);
 		size = aligned_size((u64)addr, sg->length);
 		ret = domain_page_mapping(domain, start_addr + offset,
-			((u64)addr) & PAGE_MASK_4K,
+			((u64)addr) & PAGE_MASK,
 			size, prot);
 		if (ret) {
 			/*  clear the page */
@@ -2128,14 +2134,14 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist,
 			return 0;
 		}
 		sg->dma_address = start_addr + offset +
-				((u64)addr & (~PAGE_MASK_4K));
+				((u64)addr & (~PAGE_MASK));
 		sg->dma_length = sg->length;
 		offset += size;
 	}
 
 	/* it's a non-present to present mapping */
 	if (iommu_flush_iotlb_psi(domain->iommu, domain->id,
-			start_addr, offset >> PAGE_SHIFT_4K, 1))
+			start_addr, offset >> VTD_PAGE_SHIFT, 1))
 		iommu_flush_write_buffer(domain->iommu);
 	return nelems;
 }
@@ -2175,7 +2181,6 @@ static inline int iommu_devinfo_cache_init(void)
 					 sizeof(struct device_domain_info),
 					 0,
 					 SLAB_HWCACHE_ALIGN,
-
 					 NULL);
 	if (!iommu_devinfo_cache) {
 		printk(KERN_ERR "Couldn't create devinfo cache\n");
@@ -2193,7 +2198,6 @@ static inline int iommu_iova_cache_init(void)
 					 sizeof(struct iova),
 					 0,
 					 SLAB_HWCACHE_ALIGN,
-
 					 NULL);
 	if (!iommu_iova_cache) {
 		printk(KERN_ERR "Couldn't create iova cache\n");
@@ -2322,7 +2326,7 @@ void intel_iommu_domain_exit(struct dmar_domain *domain)
 		return;
 
 	end = DOMAIN_MAX_ADDR(domain->gaw);
-	end = end & (~PAGE_MASK_4K);
+	end = end & (~VTD_PAGE_MASK);
 
 	/* clear ptes */
 	dma_pte_clear_range(domain, 0, end);
@@ -2418,6 +2422,6 @@ u64 intel_iommu_iova_to_pfn(struct dmar_domain *domain, u64 iova)
 	if (pte)
 		pfn = dma_pte_addr(*pte);
 
-	return pfn >> PAGE_SHIFT_4K;
+	return pfn >> VTD_PAGE_SHIFT;
 }
 EXPORT_SYMBOL_GPL(intel_iommu_iova_to_pfn);
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index e872ac925b4b..832175d9ca25 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -35,6 +35,20 @@ static void __devinit quirk_mellanox_tavor(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX,PCI_DEVICE_ID_MELLANOX_TAVOR,quirk_mellanox_tavor);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MELLANOX,PCI_DEVICE_ID_MELLANOX_TAVOR_BRIDGE,quirk_mellanox_tavor);
 
+/* Many VIA bridges seem to corrupt data for DAC. Disable it here */
+int forbid_dac __read_mostly;
+EXPORT_SYMBOL(forbid_dac);
+
+static __devinit void via_no_dac(struct pci_dev *dev)
+{
+	if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) {
+		dev_info(&dev->dev,
+			"VIA PCI bridge detected. Disabling DAC.\n");
+		forbid_dac = 1;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac);
+
 /* Deal with broken BIOS'es that neglect to enable passive release,
    which can cause problems in combination with the 82441FX/PPro MTRRs */
 static void quirk_passive_release(struct pci_dev *dev)
diff --git a/include/asm-x86/iommu.h b/include/asm-x86/iommu.h
index 961e746da977..2daaffcda52f 100644
--- a/include/asm-x86/iommu.h
+++ b/include/asm-x86/iommu.h
@@ -7,9 +7,13 @@ extern struct dma_mapping_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 extern int dmar_disabled;
+extern int forbid_dac;
 
 extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len);
 
+/* 10 seconds */
+#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
+
 #ifdef CONFIG_GART_IOMMU
 extern int gart_iommu_aperture;
 extern int gart_iommu_aperture_allowed;
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index bff5c65f81dc..952df39c989d 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -2,15 +2,14 @@
 #define _DMA_REMAPPING_H
 
 /*
- * We need a fixed PAGE_SIZE of 4K irrespective of
- * arch PAGE_SIZE for IOMMU page tables.
+ * VT-d hardware uses 4KiB page size regardless of host page size.
  */
-#define PAGE_SHIFT_4K		(12)
-#define PAGE_SIZE_4K		(1UL << PAGE_SHIFT_4K)
-#define PAGE_MASK_4K		(((u64)-1) << PAGE_SHIFT_4K)
-#define PAGE_ALIGN_4K(addr)	(((addr) + PAGE_SIZE_4K - 1) & PAGE_MASK_4K)
+#define VTD_PAGE_SHIFT		(12)
+#define VTD_PAGE_SIZE		(1UL << VTD_PAGE_SHIFT)
+#define VTD_PAGE_MASK		(((u64)-1) << VTD_PAGE_SHIFT)
+#define VTD_PAGE_ALIGN(addr)	(((addr) + VTD_PAGE_SIZE - 1) & VTD_PAGE_MASK)
 
-#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT_4K)
+#define IOVA_PFN(addr)		((addr) >> PAGE_SHIFT)
 #define DMA_32BIT_PFN		IOVA_PFN(DMA_32BIT_MASK)
 #define DMA_64BIT_PFN		IOVA_PFN(DMA_64BIT_MASK)
 
@@ -25,7 +24,7 @@ struct root_entry {
 	u64	val;
 	u64	rsvd1;
 };
-#define ROOT_ENTRY_NR (PAGE_SIZE_4K/sizeof(struct root_entry))
+#define ROOT_ENTRY_NR (VTD_PAGE_SIZE/sizeof(struct root_entry))
 static inline bool root_present(struct root_entry *root)
 {
 	return (root->val & 1);
@@ -36,7 +35,7 @@ static inline void set_root_present(struct root_entry *root)
 }
 static inline void set_root_value(struct root_entry *root, unsigned long value)
 {
-	root->val |= value & PAGE_MASK_4K;
+	root->val |= value & VTD_PAGE_MASK;
 }
 
 struct context_entry;
@@ -45,7 +44,7 @@ get_context_addr_from_root(struct root_entry *root)
 {
 	return (struct context_entry *)
 		(root_present(root)?phys_to_virt(
-		root->val & PAGE_MASK_4K):
+		root->val & VTD_PAGE_MASK) :
 		NULL);
 }
 
@@ -67,7 +66,7 @@ struct context_entry {
 #define context_present(c) ((c).lo & 1)
 #define context_fault_disable(c) (((c).lo >> 1) & 1)
 #define context_translation_type(c) (((c).lo >> 2) & 3)
-#define context_address_root(c) ((c).lo & PAGE_MASK_4K)
+#define context_address_root(c) ((c).lo & VTD_PAGE_MASK)
 #define context_address_width(c) ((c).hi &  7)
 #define context_domain_id(c) (((c).hi >> 8) & ((1 << 16) - 1))
 
@@ -81,7 +80,7 @@ struct context_entry {
 	} while (0)
 #define CONTEXT_TT_MULTI_LEVEL 0
 #define context_set_address_root(c, val) \
-	do {(c).lo |= (val) & PAGE_MASK_4K;} while (0)
+	do {(c).lo |= (val) & VTD_PAGE_MASK; } while (0)
 #define context_set_address_width(c, val) do {(c).hi |= (val) & 7;} while (0)
 #define context_set_domain_id(c, val) \
 	do {(c).hi |= ((val) & ((1 << 16) - 1)) << 8;} while (0)
@@ -107,9 +106,9 @@ struct dma_pte {
 #define dma_set_pte_writable(p) do {(p).val |= DMA_PTE_WRITE;} while (0)
 #define dma_set_pte_prot(p, prot) \
 		do {(p).val = ((p).val & ~3) | ((prot) & 3); } while (0)
-#define dma_pte_addr(p) ((p).val & PAGE_MASK_4K)
+#define dma_pte_addr(p) ((p).val & VTD_PAGE_MASK)
 #define dma_set_pte_addr(p, addr) do {\
-		(p).val |= ((addr) & PAGE_MASK_4K); } while (0)
+		(p).val |= ((addr) & VTD_PAGE_MASK); } while (0)
 #define dma_pte_present(p) (((p).val & 3) != 0)
 
 struct intel_iommu;
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index afb0d2a5b7cd..3d017cfd245b 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -29,6 +29,7 @@
 #include <linux/io.h>
 #include <linux/dma_remapping.h>
 #include <asm/cacheflush.h>
+#include <asm/iommu.h>
 
 /*
  * Intel IOMMU register specification per version 1.0 public spec.
@@ -202,22 +203,21 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define dma_frcd_type(d) ((d >> 30) & 1)
 #define dma_frcd_fault_reason(c) (c & 0xff)
 #define dma_frcd_source_id(c) (c & 0xffff)
-#define dma_frcd_page_addr(d) (d & (((u64)-1) << 12)) /* low 64 bit */
-
-#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000) /* 10sec */
-
-#define IOMMU_WAIT_OP(iommu, offset, op, cond, sts) \
-{\
-	cycles_t start_time = get_cycles();\
-	while (1) {\
-		sts = op (iommu->reg + offset);\
-		if (cond)\
-			break;\
+/* low 64 bit */
+#define dma_frcd_page_addr(d) (d & (((u64)-1) << PAGE_SHIFT))
+
+#define IOMMU_WAIT_OP(iommu, offset, op, cond, sts)			\
+do {									\
+	cycles_t start_time = get_cycles();				\
+	while (1) {							\
+		sts = op(iommu->reg + offset);				\
+		if (cond)						\
+			break;						\
 		if (DMAR_OPERATION_TIMEOUT < (get_cycles() - start_time))\
-			panic("DMAR hardware is malfunctioning\n");\
-		cpu_relax();\
-	}\
-}
+			panic("DMAR hardware is malfunctioning\n");	\
+		cpu_relax();						\
+	}								\
+} while (0)
 
 #define QI_LENGTH	256	/* queue length */
 
@@ -244,7 +244,7 @@ enum {
 #define QI_IOTLB_DR(dr) 	(((u64)dr) << 7)
 #define QI_IOTLB_DW(dw) 	(((u64)dw) << 6)
 #define QI_IOTLB_GRAN(gran) 	(((u64)gran) >> (DMA_TLB_FLUSH_GRANU_OFFSET-4))
-#define QI_IOTLB_ADDR(addr)	(((u64)addr) & PAGE_MASK_4K)
+#define QI_IOTLB_ADDR(addr)	(((u64)addr) & VTD_PAGE_MASK)
 #define QI_IOTLB_IH(ih)		(((u64)ih) << 6)
 #define QI_IOTLB_AM(am)		(((u8)am))
 
@@ -353,4 +353,11 @@ static inline int intel_iommu_found(void)
 }
 #endif /* CONFIG_DMAR */
 
+extern void *intel_alloc_coherent(struct device *, size_t, dma_addr_t *, gfp_t);
+extern void intel_free_coherent(struct device *, size_t, void *, dma_addr_t);
+extern dma_addr_t intel_map_single(struct device *, phys_addr_t, size_t, int);
+extern void intel_unmap_single(struct device *, dma_addr_t, size_t, int);
+extern int intel_map_sg(struct device *, struct scatterlist *, int, int);
+extern void intel_unmap_sg(struct device *, struct scatterlist *, int, int);
+
 #endif
-- 
cgit v1.2.3


From 1c1b6ffce5737d764cc474b9bd6677bb9a344094 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dbaryshkov@gmail.com>
Date: Wed, 24 Sep 2008 23:36:23 +0200
Subject: mfd: provide and use setup hook for tc6393xb

Instead of using bitfields for initial gpio setup,
provide generic setup/teardown hooks that can be used
to set the gpio states, register child devices, etc.

Signed-off-by: Dmitry Baryshkov <dbaryshkov@gmail.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 arch/arm/mach-pxa/include/mach/tosa.h |  2 --
 arch/arm/mach-pxa/tosa.c              | 35 +++++++++++++++++++++++++++++------
 drivers/mfd/tc6393xb.c                | 21 ++++++++++++++-------
 include/linux/mfd/tc6393xb.h          |  4 ++--
 4 files changed, 45 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-pxa/include/mach/tosa.h b/arch/arm/mach-pxa/include/mach/tosa.h
index a72803f0461b..8bce6d8615b9 100644
--- a/arch/arm/mach-pxa/include/mach/tosa.h
+++ b/arch/arm/mach-pxa/include/mach/tosa.h
@@ -59,8 +59,6 @@
  * TC6393XB GPIOs
  */
 #define TOSA_TC6393XB_GPIO_BASE		(NR_BUILTIN_GPIO + 2 * 12)
-#define TOSA_TC6393XB_GPIO(i)		(TOSA_TC6393XB_GPIO_BASE + (i))
-#define TOSA_TC6393XB_GPIO_BIT(gpio)	(1 << (gpio - TOSA_TC6393XB_GPIO_BASE))
 
 #define TOSA_GPIO_TG_ON			(TOSA_TC6393XB_GPIO_BASE + 0)
 #define TOSA_GPIO_L_MUTE		(TOSA_TC6393XB_GPIO_BASE + 1)
diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index 130e37e4ebdd..fac846b0d070 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -706,16 +706,39 @@ static struct tmio_nand_data tosa_tc6393xb_nand_config = {
 	.badblock_pattern = &tosa_tc6393xb_nand_bbt,
 };
 
-static struct tc6393xb_platform_data tosa_tc6393xb_setup = {
+static int tosa_tc6393xb_setup(struct platform_device *dev)
+{
+	int rc;
+
+	rc = gpio_request(TOSA_GPIO_CARD_VCC_ON, "CARD_VCC_ON");
+	if (rc)
+		goto err_req;
+
+	rc = gpio_direction_output(TOSA_GPIO_CARD_VCC_ON, 1);
+	if (rc)
+		goto err_dir;
+
+	return rc;
+
+err_dir:
+	gpio_free(TOSA_GPIO_CARD_VCC_ON);
+err_req:
+	return rc;
+}
+
+static void tosa_tc6393xb_teardown(struct platform_device *dev)
+{
+	gpio_free(TOSA_GPIO_CARD_VCC_ON);
+}
+
+static struct tc6393xb_platform_data tosa_tc6393xb_data = {
 	.scr_pll2cr	= 0x0cc1,
 	.scr_gper	= 0x3300,
-	.scr_gpo_dsr	=
-		TOSA_TC6393XB_GPIO_BIT(TOSA_GPIO_CARD_VCC_ON),
-	.scr_gpo_doecr	=
-		TOSA_TC6393XB_GPIO_BIT(TOSA_GPIO_CARD_VCC_ON),
 
 	.irq_base	= IRQ_BOARD_START,
 	.gpio_base	= TOSA_TC6393XB_GPIO_BASE,
+	.setup		= tosa_tc6393xb_setup,
+	.teardown	= tosa_tc6393xb_teardown,
 
 	.enable		= tosa_tc6393xb_enable,
 	.disable	= tosa_tc6393xb_disable,
@@ -730,7 +753,7 @@ static struct platform_device tc6393xb_device = {
 	.name	= "tc6393xb",
 	.id	= -1,
 	.dev	= {
-		.platform_data	= &tosa_tc6393xb_setup,
+		.platform_data	= &tosa_tc6393xb_data,
 	},
 	.num_resources	= ARRAY_SIZE(tc6393xb_resources),
 	.resource	= tc6393xb_resources,
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index e4c1c788b5f8..83dc703f3767 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -460,13 +460,6 @@ static int __devinit tc6393xb_probe(struct platform_device *dev)
 
 	tc6393xb->suspend_state.fer = 0;
 
-	for (i = 0; i < 3; i++) {
-		tc6393xb->suspend_state.gpo_dsr[i] =
-			(tcpd->scr_gpo_dsr >> (8 * i)) & 0xff;
-		tc6393xb->suspend_state.gpo_doecr[i] =
-			(tcpd->scr_gpo_doecr >> (8 * i)) & 0xff;
-	}
-
 	tc6393xb->suspend_state.ccr = SCR_CCR_UNK1 |
 					SCR_CCR_HCLK_48;
 
@@ -488,6 +481,12 @@ static int __devinit tc6393xb_probe(struct platform_device *dev)
 
 	tc6393xb_attach_irq(dev);
 
+	if (tcpd->setup) {
+		ret = tcpd->setup(dev);
+		if (ret)
+			goto err_setup;
+	}
+
 	tc6393xb_cells[TC6393XB_CELL_NAND].driver_data = tcpd->nand_data;
 	tc6393xb_cells[TC6393XB_CELL_NAND].platform_data =
 		&tc6393xb_cells[TC6393XB_CELL_NAND];
@@ -506,6 +505,10 @@ static int __devinit tc6393xb_probe(struct platform_device *dev)
 	if (!ret)
 		return 0;
 
+	if (tcpd->teardown)
+		tcpd->teardown(dev);
+
+err_setup:
 	tc6393xb_detach_irq(dev);
 
 err_gpio_add:
@@ -535,6 +538,10 @@ static int __devexit tc6393xb_remove(struct platform_device *dev)
 	int ret;
 
 	mfd_remove_devices(&dev->dev);
+
+	if (tcpd->teardown)
+		tcpd->teardown(dev);
+
 	tc6393xb_detach_irq(dev);
 
 	if (tc6393xb->gpio.base != -1) {
diff --git a/include/linux/mfd/tc6393xb.h b/include/linux/mfd/tc6393xb.h
index fec7b3f7a81f..1fa820646d98 100644
--- a/include/linux/mfd/tc6393xb.h
+++ b/include/linux/mfd/tc6393xb.h
@@ -21,8 +21,6 @@
 struct tc6393xb_platform_data {
 	u16	scr_pll2cr;	/* PLL2 Control */
 	u16	scr_gper;	/* GP Enable */
-	u32	scr_gpo_doecr;	/* GPO Data OE Control */
-	u32	scr_gpo_dsr;	/* GPO Data Set */
 
 	int	(*enable)(struct platform_device *dev);
 	int	(*disable)(struct platform_device *dev);
@@ -31,6 +29,8 @@ struct tc6393xb_platform_data {
 
 	int	irq_base;	/* base for subdevice irqs */
 	int	gpio_base;
+	int	(*setup)(struct platform_device *dev);
+	void	(*teardown)(struct platform_device *dev);
 
 	struct tmio_nand_data	*nand_data;
 };
-- 
cgit v1.2.3


From f98a0bd0e4b77b12e49ce01f4c9f04503931c291 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dbaryshkov@gmail.com>
Date: Wed, 24 Sep 2008 23:46:10 +0200
Subject: mfd: do tcb6393xb state restore on resume only if requested

As requested by Ian make state restore only if it's requested
by platform data: some platforms do correctly save the state of
the chip during suspend/resume, but some (like tosa) incorrectly
power off the chip at suspend, so the driver supports restoring
some bits of the tc6393xb state (not full, merely enough to support
resume on tosa). With this patch this code is disabled by default.

Signed-off-by: Dmitry Baryshkov <dbaryshkov@gmail.com>
Acked-by: Ian Molton <spyro@f2s.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 arch/arm/mach-pxa/tosa.c     |  2 ++
 drivers/mfd/tc6393xb.c       | 74 ++++++++++++++++++++------------------------
 include/linux/mfd/tc6393xb.h |  4 +++
 3 files changed, 40 insertions(+), 40 deletions(-)

(limited to 'include')

diff --git a/arch/arm/mach-pxa/tosa.c b/arch/arm/mach-pxa/tosa.c
index fac846b0d070..a6c4694359ca 100644
--- a/arch/arm/mach-pxa/tosa.c
+++ b/arch/arm/mach-pxa/tosa.c
@@ -746,6 +746,8 @@ static struct tc6393xb_platform_data tosa_tc6393xb_data = {
 	.resume		= tosa_tc6393xb_resume,
 
 	.nand_data	= &tosa_tc6393xb_nand_config,
+
+	.resume_restore = 1,
 };
 
 
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index 83dc703f3767..c3c64aeeb12a 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -369,41 +369,12 @@ static void tc6393xb_detach_irq(struct platform_device *dev)
 
 /*--------------------------------------------------------------------------*/
 
-static int tc6393xb_hw_init(struct platform_device *dev)
-{
-	struct tc6393xb_platform_data *tcpd = dev->dev.platform_data;
-	struct tc6393xb *tc6393xb = platform_get_drvdata(dev);
-	int i;
-
-	iowrite8(tc6393xb->suspend_state.fer,	tc6393xb->scr + SCR_FER);
-	iowrite16(tcpd->scr_pll2cr,		tc6393xb->scr + SCR_PLL2CR);
-	iowrite16(tc6393xb->suspend_state.ccr,	tc6393xb->scr + SCR_CCR);
-	iowrite16(SCR_MCR_RDY_OPENDRAIN | SCR_MCR_RDY_UNK | SCR_MCR_RDY_EN |
-		  SCR_MCR_INT_OPENDRAIN | SCR_MCR_INT_UNK | SCR_MCR_INT_EN |
-		  BIT(15),			tc6393xb->scr + SCR_MCR);
-	iowrite16(tcpd->scr_gper,		tc6393xb->scr + SCR_GPER);
-	iowrite8(0,				tc6393xb->scr + SCR_IRR);
-	iowrite8(0xbf,				tc6393xb->scr + SCR_IMR);
-
-	for (i = 0; i < 3; i++) {
-		iowrite8(tc6393xb->suspend_state.gpo_dsr[i],
-					tc6393xb->scr + SCR_GPO_DSR(i));
-		iowrite8(tc6393xb->suspend_state.gpo_doecr[i],
-					tc6393xb->scr + SCR_GPO_DOECR(i));
-		iowrite8(tc6393xb->suspend_state.gpi_bcr[i],
-					tc6393xb->scr + SCR_GPI_BCR(i));
-	}
-
-	return 0;
-}
-
 static int __devinit tc6393xb_probe(struct platform_device *dev)
 {
 	struct tc6393xb_platform_data *tcpd = dev->dev.platform_data;
 	struct tc6393xb *tc6393xb;
 	struct resource *iomem, *rscr;
 	int ret, temp;
-	int i;
 
 	iomem = platform_get_resource(dev, IORESOURCE_MEM, 0);
 	if (!iomem)
@@ -458,14 +429,16 @@ static int __devinit tc6393xb_probe(struct platform_device *dev)
 	if (ret)
 		goto err_enable;
 
-	tc6393xb->suspend_state.fer = 0;
-
-	tc6393xb->suspend_state.ccr = SCR_CCR_UNK1 |
-					SCR_CCR_HCLK_48;
-
-	ret = tc6393xb_hw_init(dev);
-	if (ret)
-		goto err_hw_init;
+	iowrite8(0,				tc6393xb->scr + SCR_FER);
+	iowrite16(tcpd->scr_pll2cr,		tc6393xb->scr + SCR_PLL2CR);
+	iowrite16(SCR_CCR_UNK1 | SCR_CCR_HCLK_48,
+						tc6393xb->scr + SCR_CCR);
+	iowrite16(SCR_MCR_RDY_OPENDRAIN | SCR_MCR_RDY_UNK | SCR_MCR_RDY_EN |
+		  SCR_MCR_INT_OPENDRAIN | SCR_MCR_INT_UNK | SCR_MCR_INT_EN |
+		  BIT(15),			tc6393xb->scr + SCR_MCR);
+	iowrite16(tcpd->scr_gper,		tc6393xb->scr + SCR_GPER);
+	iowrite8(0,				tc6393xb->scr + SCR_IRR);
+	iowrite8(0xbf,				tc6393xb->scr + SCR_IMR);
 
 	printk(KERN_INFO "Toshiba tc6393xb revision %d at 0x%08lx, irq %d\n",
 			tmio_ioread8(tc6393xb->scr + SCR_REVID),
@@ -514,7 +487,6 @@ err_setup:
 err_gpio_add:
 	if (tc6393xb->gpio.base != -1)
 		temp = gpiochip_remove(&tc6393xb->gpio);
-err_hw_init:
 	tcpd->disable(dev);
 err_clk_enable:
 	clk_disable(tc6393xb->clk);
@@ -592,15 +564,37 @@ static int tc6393xb_resume(struct platform_device *dev)
 	struct tc6393xb_platform_data *tcpd = dev->dev.platform_data;
 	struct tc6393xb *tc6393xb = platform_get_drvdata(dev);
 	int ret;
+	int i;
 
 	clk_enable(tc6393xb->clk);
 
 	ret = tcpd->resume(dev);
-
 	if (ret)
 		return ret;
 
-	return tc6393xb_hw_init(dev);
+	if (!tcpd->resume_restore)
+		return 0;
+
+	iowrite8(tc6393xb->suspend_state.fer,	tc6393xb->scr + SCR_FER);
+	iowrite16(tcpd->scr_pll2cr,		tc6393xb->scr + SCR_PLL2CR);
+	iowrite16(tc6393xb->suspend_state.ccr,	tc6393xb->scr + SCR_CCR);
+	iowrite16(SCR_MCR_RDY_OPENDRAIN | SCR_MCR_RDY_UNK | SCR_MCR_RDY_EN |
+		  SCR_MCR_INT_OPENDRAIN | SCR_MCR_INT_UNK | SCR_MCR_INT_EN |
+		  BIT(15),			tc6393xb->scr + SCR_MCR);
+	iowrite16(tcpd->scr_gper,		tc6393xb->scr + SCR_GPER);
+	iowrite8(0,				tc6393xb->scr + SCR_IRR);
+	iowrite8(0xbf,				tc6393xb->scr + SCR_IMR);
+
+	for (i = 0; i < 3; i++) {
+		iowrite8(tc6393xb->suspend_state.gpo_dsr[i],
+					tc6393xb->scr + SCR_GPO_DSR(i));
+		iowrite8(tc6393xb->suspend_state.gpo_doecr[i],
+					tc6393xb->scr + SCR_GPO_DOECR(i));
+		iowrite8(tc6393xb->suspend_state.gpi_bcr[i],
+					tc6393xb->scr + SCR_GPI_BCR(i));
+	}
+
+	return 0;
 }
 #else
 #define tc6393xb_suspend NULL
diff --git a/include/linux/mfd/tc6393xb.h b/include/linux/mfd/tc6393xb.h
index 1fa820646d98..3ce10ae0f397 100644
--- a/include/linux/mfd/tc6393xb.h
+++ b/include/linux/mfd/tc6393xb.h
@@ -33,6 +33,10 @@ struct tc6393xb_platform_data {
 	void	(*teardown)(struct platform_device *dev);
 
 	struct tmio_nand_data	*nand_data;
+
+	unsigned resume_restore : 1; /* make special actions
+					to preserve the state
+					on suspend/resume */
 };
 
 /*
-- 
cgit v1.2.3


From 51a55623565c6ca864f7cf19e87c2d4bde1c0c5e Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dbaryshkov@gmail.com>
Date: Fri, 3 Oct 2008 20:11:36 +0200
Subject: mfd: add OHCI cell to tc6393xb

Add information regarding OHCI cell of the tc6393xb

Signed-off-by: Dmitry Baryshkov <dbaryshkov@gmail.com>
Acked-by: Ian Molton <spyro@f2s.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/tc6393xb.c       | 87 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/tc6393xb.h |  1 +
 2 files changed, 88 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index c3c64aeeb12a..6197db7d4859 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -113,6 +113,7 @@ struct tc6393xb {
 enum {
 	TC6393XB_CELL_NAND,
 	TC6393XB_CELL_MMC,
+	TC6393XB_CELL_OHCI,
 };
 
 /*--------------------------------------------------------------------------*/
@@ -170,6 +171,78 @@ static struct resource __devinitdata tc6393xb_mmc_resources[] = {
 	},
 };
 
+const static struct resource tc6393xb_ohci_resources[] = {
+	{
+		.start	= 0x3000,
+		.end	= 0x31ff,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.start	= 0x0300,
+		.end	= 0x03ff,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.start	= 0x010000,
+		.end	= 0x017fff,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.start	= 0x018000,
+		.end	= 0x01ffff,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.start	= IRQ_TC6393_OHCI,
+		.end	= IRQ_TC6393_OHCI,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static int tc6393xb_ohci_enable(struct platform_device *dev)
+{
+	struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent);
+	unsigned long flags;
+	u16 ccr;
+	u8 fer;
+
+	spin_lock_irqsave(&tc6393xb->lock, flags);
+
+	ccr = tmio_ioread16(tc6393xb->scr + SCR_CCR);
+	ccr |= SCR_CCR_USBCK;
+	tmio_iowrite16(ccr, tc6393xb->scr + SCR_CCR);
+
+	fer = tmio_ioread8(tc6393xb->scr + SCR_FER);
+	fer |= SCR_FER_USBEN;
+	tmio_iowrite8(fer, tc6393xb->scr + SCR_FER);
+
+	spin_unlock_irqrestore(&tc6393xb->lock, flags);
+
+	return 0;
+}
+
+static int tc6393xb_ohci_disable(struct platform_device *dev)
+{
+	struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent);
+	unsigned long flags;
+	u16 ccr;
+	u8 fer;
+
+	spin_lock_irqsave(&tc6393xb->lock, flags);
+
+	fer = tmio_ioread8(tc6393xb->scr + SCR_FER);
+	fer &= ~SCR_FER_USBEN;
+	tmio_iowrite8(fer, tc6393xb->scr + SCR_FER);
+
+	ccr = tmio_ioread16(tc6393xb->scr + SCR_CCR);
+	ccr &= ~SCR_CCR_USBCK;
+	tmio_iowrite16(ccr, tc6393xb->scr + SCR_CCR);
+
+	spin_unlock_irqrestore(&tc6393xb->lock, flags);
+
+	return 0;
+}
+
 static struct mfd_cell __devinitdata tc6393xb_cells[] = {
 	[TC6393XB_CELL_NAND] = {
 		.name = "tmio-nand",
@@ -182,6 +255,15 @@ static struct mfd_cell __devinitdata tc6393xb_cells[] = {
 		.num_resources = ARRAY_SIZE(tc6393xb_mmc_resources),
 		.resources = tc6393xb_mmc_resources,
 	},
+	[TC6393XB_CELL_OHCI] = {
+		.name = "tmio-ohci",
+		.num_resources = ARRAY_SIZE(tc6393xb_ohci_resources),
+		.resources = tc6393xb_ohci_resources,
+		.enable = tc6393xb_ohci_enable,
+		.suspend = tc6393xb_ohci_disable,
+		.resume = tc6393xb_ohci_enable,
+		.disable = tc6393xb_ohci_disable,
+	},
 };
 
 /*--------------------------------------------------------------------------*/
@@ -470,6 +552,11 @@ static int __devinit tc6393xb_probe(struct platform_device *dev)
 	tc6393xb_cells[TC6393XB_CELL_MMC].data_size =
 		sizeof(tc6393xb_cells[TC6393XB_CELL_MMC]);
 
+	tc6393xb_cells[TC6393XB_CELL_OHCI].platform_data =
+		&tc6393xb_cells[TC6393XB_CELL_OHCI];
+	tc6393xb_cells[TC6393XB_CELL_OHCI].data_size =
+		sizeof(tc6393xb_cells[TC6393XB_CELL_OHCI]);
+
 
 	ret = mfd_add_devices(&dev->dev, dev->id,
 			tc6393xb_cells, ARRAY_SIZE(tc6393xb_cells),
diff --git a/include/linux/mfd/tc6393xb.h b/include/linux/mfd/tc6393xb.h
index 3ce10ae0f397..4437736ebe19 100644
--- a/include/linux/mfd/tc6393xb.h
+++ b/include/linux/mfd/tc6393xb.h
@@ -44,6 +44,7 @@ struct tc6393xb_platform_data {
  */
 #define	IRQ_TC6393_NAND		0
 #define	IRQ_TC6393_MMC		1
+#define	IRQ_TC6393_OHCI		2
 
 #define	TC6393XB_NR_IRQS	8
 
-- 
cgit v1.2.3


From 9e78cfe53f3c2bc1b37870697c3cde1543fefa8b Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dbaryshkov@gmail.com>
Date: Sat, 4 Oct 2008 00:50:36 +0200
Subject: mfd: support tmiofb cell on tc6393xb

Add support for tmiofb cell found in tc6393xb chip.

Signed-off-by: Dmitry Baryshkov <dbaryshkov@gmail.com>
Cc: Ian Molton <spyro@f2s.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/tc6393xb.c       | 114 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/tc6393xb.h |   8 +++
 2 files changed, 122 insertions(+)

(limited to 'include')

diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index 6197db7d4859..f856e9463a9f 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -114,6 +114,7 @@ enum {
 	TC6393XB_CELL_NAND,
 	TC6393XB_CELL_MMC,
 	TC6393XB_CELL_OHCI,
+	TC6393XB_CELL_FB,
 };
 
 /*--------------------------------------------------------------------------*/
@@ -199,6 +200,29 @@ const static struct resource tc6393xb_ohci_resources[] = {
 	},
 };
 
+static struct resource __devinitdata tc6393xb_fb_resources[] = {
+	{
+		.start	= 0x5000,
+		.end	= 0x51ff,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.start	= 0x0500,
+		.end	= 0x05ff,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.start	= 0x100000,
+		.end	= 0x1fffff,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.start	= IRQ_TC6393_FB,
+		.end	= IRQ_TC6393_FB,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
 static int tc6393xb_ohci_enable(struct platform_device *dev)
 {
 	struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent);
@@ -243,6 +267,81 @@ static int tc6393xb_ohci_disable(struct platform_device *dev)
 	return 0;
 }
 
+static int tc6393xb_fb_enable(struct platform_device *dev)
+{
+	struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent);
+	unsigned long flags;
+	u16 ccr;
+
+	spin_lock_irqsave(&tc6393xb->lock, flags);
+
+	ccr = tmio_ioread16(tc6393xb->scr + SCR_CCR);
+	ccr &= ~SCR_CCR_MCLK_MASK;
+	ccr |= SCR_CCR_MCLK_48;
+	tmio_iowrite16(ccr, tc6393xb->scr + SCR_CCR);
+
+	spin_unlock_irqrestore(&tc6393xb->lock, flags);
+
+	return 0;
+}
+
+static int tc6393xb_fb_disable(struct platform_device *dev)
+{
+	struct tc6393xb *tc6393xb = dev_get_drvdata(dev->dev.parent);
+	unsigned long flags;
+	u16 ccr;
+
+	spin_lock_irqsave(&tc6393xb->lock, flags);
+
+	ccr = tmio_ioread16(tc6393xb->scr + SCR_CCR);
+	ccr &= ~SCR_CCR_MCLK_MASK;
+	ccr |= SCR_CCR_MCLK_OFF;
+	tmio_iowrite16(ccr, tc6393xb->scr + SCR_CCR);
+
+	spin_unlock_irqrestore(&tc6393xb->lock, flags);
+
+	return 0;
+}
+
+int tc6393xb_lcd_set_power(struct platform_device *fb, bool on)
+{
+	struct platform_device *dev = to_platform_device(fb->dev.parent);
+	struct tc6393xb *tc6393xb = platform_get_drvdata(dev);
+	u8 fer;
+	unsigned long flags;
+
+	spin_lock_irqsave(&tc6393xb->lock, flags);
+
+	fer = ioread8(tc6393xb->scr + SCR_FER);
+	if (on)
+		fer |= SCR_FER_SLCDEN;
+	else
+		fer &= ~SCR_FER_SLCDEN;
+	iowrite8(fer, tc6393xb->scr + SCR_FER);
+
+	spin_unlock_irqrestore(&tc6393xb->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(tc6393xb_lcd_set_power);
+
+int tc6393xb_lcd_mode(struct platform_device *fb,
+					const struct fb_videomode *mode) {
+	struct platform_device *dev = to_platform_device(fb->dev.parent);
+	struct tc6393xb *tc6393xb = platform_get_drvdata(dev);
+	unsigned long flags;
+
+	spin_lock_irqsave(&tc6393xb->lock, flags);
+
+	iowrite16(mode->pixclock, tc6393xb->scr + SCR_PLL1CR + 0);
+	iowrite16(mode->pixclock >> 16, tc6393xb->scr + SCR_PLL1CR + 2);
+
+	spin_unlock_irqrestore(&tc6393xb->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(tc6393xb_lcd_mode);
+
 static struct mfd_cell __devinitdata tc6393xb_cells[] = {
 	[TC6393XB_CELL_NAND] = {
 		.name = "tmio-nand",
@@ -264,6 +363,15 @@ static struct mfd_cell __devinitdata tc6393xb_cells[] = {
 		.resume = tc6393xb_ohci_enable,
 		.disable = tc6393xb_ohci_disable,
 	},
+	[TC6393XB_CELL_FB] = {
+		.name = "tmio-fb",
+		.num_resources = ARRAY_SIZE(tc6393xb_fb_resources),
+		.resources = tc6393xb_fb_resources,
+		.enable = tc6393xb_fb_enable,
+		.suspend = tc6393xb_fb_disable,
+		.resume = tc6393xb_fb_enable,
+		.disable = tc6393xb_fb_disable,
+	},
 };
 
 /*--------------------------------------------------------------------------*/
@@ -547,6 +655,7 @@ static int __devinit tc6393xb_probe(struct platform_device *dev)
 		&tc6393xb_cells[TC6393XB_CELL_NAND];
 	tc6393xb_cells[TC6393XB_CELL_NAND].data_size =
 		sizeof(tc6393xb_cells[TC6393XB_CELL_NAND]);
+
 	tc6393xb_cells[TC6393XB_CELL_MMC].platform_data =
 		&tc6393xb_cells[TC6393XB_CELL_MMC];
 	tc6393xb_cells[TC6393XB_CELL_MMC].data_size =
@@ -557,6 +666,11 @@ static int __devinit tc6393xb_probe(struct platform_device *dev)
 	tc6393xb_cells[TC6393XB_CELL_OHCI].data_size =
 		sizeof(tc6393xb_cells[TC6393XB_CELL_OHCI]);
 
+	tc6393xb_cells[TC6393XB_CELL_FB].driver_data = tcpd->fb_data;
+	tc6393xb_cells[TC6393XB_CELL_FB].platform_data =
+		&tc6393xb_cells[TC6393XB_CELL_FB];
+	tc6393xb_cells[TC6393XB_CELL_FB].data_size =
+		sizeof(tc6393xb_cells[TC6393XB_CELL_FB]);
 
 	ret = mfd_add_devices(&dev->dev, dev->id,
 			tc6393xb_cells, ARRAY_SIZE(tc6393xb_cells),
diff --git a/include/linux/mfd/tc6393xb.h b/include/linux/mfd/tc6393xb.h
index 4437736ebe19..626e448205c5 100644
--- a/include/linux/mfd/tc6393xb.h
+++ b/include/linux/mfd/tc6393xb.h
@@ -17,6 +17,8 @@
 #ifndef MFD_TC6393XB_H
 #define MFD_TC6393XB_H
 
+#include <linux/fb.h>
+
 /* Also one should provide the CK3P6MI clock */
 struct tc6393xb_platform_data {
 	u16	scr_pll2cr;	/* PLL2 Control */
@@ -33,18 +35,24 @@ struct tc6393xb_platform_data {
 	void	(*teardown)(struct platform_device *dev);
 
 	struct tmio_nand_data	*nand_data;
+	struct tmio_fb_data	*fb_data;
 
 	unsigned resume_restore : 1; /* make special actions
 					to preserve the state
 					on suspend/resume */
 };
 
+extern int tc6393xb_lcd_mode(struct platform_device *fb,
+			     const struct fb_videomode *mode);
+extern int tc6393xb_lcd_set_power(struct platform_device *fb, bool on);
+
 /*
  * Relative to irq_base
  */
 #define	IRQ_TC6393_NAND		0
 #define	IRQ_TC6393_MMC		1
 #define	IRQ_TC6393_OHCI		2
+#define	IRQ_TC6393_FB		4
 
 #define	TC6393XB_NR_IRQS	8
 
-- 
cgit v1.2.3


From a603a7fa8717fb778bba91b5a879babf333dc6a3 Mon Sep 17 00:00:00 2001
From: David Brownell <dbrownell@users.sourceforge.net>
Date: Wed, 15 Oct 2008 12:15:39 +0200
Subject: mfd: TWL4030 core driver

This patch adds the core of the TWL4030 driver, which supports
chips including the TPS65950.  These chips are multi-function; see

  http://focus.ti.com/docs/prod/folders/print/tps65950.html

Public specs are in the works.  For now, the block diagram on
the second page of the datasheet is fairly informative.

There are some known issues with this core code.  Most notably,
the IRQ dispatching needs simplification (to use more of genirq),
generalization (integrating support for secondary IRQ dispatch
as well as primary, and removing the build dependency on OMAP),
and then probably updating to leverage threaded IRQ support
(expected to arrive in mainline "soon").

Once the core is in mainline, drivers for other parts of this
chip can follow its lead and start swimming upstream too.

Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/Kconfig         |   14 +
 drivers/mfd/Makefile        |    2 +
 drivers/mfd/twl4030-core.c  | 1257 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/i2c/twl4030.h |  339 ++++++++++++
 4 files changed, 1612 insertions(+)
 create mode 100644 drivers/mfd/twl4030-core.c
 create mode 100644 include/linux/i2c/twl4030.h

(limited to 'include')

diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 5eff8ad834d6..cccda99328f3 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -59,6 +59,20 @@ config UCB1400_CORE
 	  To compile this driver as a module, choose M here: the
 	  module will be called ucb1400_core.
 
+config TWL4030_CORE
+	bool "Texas Instruments TWL4030/TPS659x0 Support"
+	depends on I2C=y && GENERIC_HARDIRQS && (ARCH_OMAP2 || ARCH_OMAP3)
+	help
+	  Say yes here if you have TWL4030 family chip on your board.
+	  This core driver provides register access and IRQ handling
+	  facilities, and registers devices for the various functions
+	  so that function-specific drivers can bind to them.
+
+	  These multi-function chips are found on many OMAP2 and OMAP3
+	  boards, providing power management, RTC, GPIO, keypad, a
+	  high speed USB OTG transceiver, an audio codec (on most
+	  versions) and many other features.
+
 config MFD_TMIO
 	bool
 	default n
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 759b1fe1c891..68e237b830ad 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -17,6 +17,8 @@ wm8350-objs			:= wm8350-core.o wm8350-regmap.o wm8350-gpio.o
 obj-$(CONFIG_MFD_WM8350)	+= wm8350.o
 obj-$(CONFIG_MFD_WM8350_I2C)	+= wm8350-i2c.o
 
+obj-$(CONFIG_TWL4030_CORE)	+= twl4030-core.o
+
 obj-$(CONFIG_MFD_CORE)		+= mfd-core.o
 
 obj-$(CONFIG_MCP)		+= mcp-core.o
diff --git a/drivers/mfd/twl4030-core.c b/drivers/mfd/twl4030-core.c
new file mode 100644
index 000000000000..4af1624987c5
--- /dev/null
+++ b/drivers/mfd/twl4030-core.c
@@ -0,0 +1,1257 @@
+/*
+ * twl4030_core.c - driver for TWL4030/TPS659x0 PM and audio CODEC devices
+ *
+ * Copyright (C) 2005-2006 Texas Instruments, Inc.
+ *
+ * Modifications to defer interrupt handling to a kernel thread:
+ * Copyright (C) 2006 MontaVista Software, Inc.
+ *
+ * Based on tlv320aic23.c:
+ * Copyright (c) by Kai Svahn <kai.svahn@nokia.com>
+ *
+ * Code cleanup and modifications to IRQ handler.
+ * by syed khasim <x0khasim@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/random.h>
+#include <linux/kthread.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+
+#include <linux/i2c.h>
+#include <linux/i2c/twl4030.h>
+
+
+/*
+ * The TWL4030 "Triton 2" is one of a family of a multi-function "Power
+ * Management and System Companion Device" chips originally designed for
+ * use in OMAP2 and OMAP 3 based systems.  Its control interfaces use I2C,
+ * often at around 3 Mbit/sec, including for interrupt handling.
+ *
+ * This driver core provides genirq support for the interrupts emitted,
+ * by the various modules, and exports register access primitives.
+ *
+ * FIXME this driver currently requires use of the first interrupt line
+ * (and associated registers).
+ */
+
+#define DRIVER_NAME			"twl4030"
+
+#if defined(CONFIG_TWL4030_BCI_BATTERY) || \
+	defined(CONFIG_TWL4030_BCI_BATTERY_MODULE)
+#define twl_has_bci()		true
+#else
+#define twl_has_bci()		false
+#endif
+
+#if defined(CONFIG_KEYBOARD_TWL4030) || defined(CONFIG_KEYBOARD_TWL4030_MODULE)
+#define twl_has_keypad()	true
+#else
+#define twl_has_keypad()	false
+#endif
+
+#if defined(CONFIG_GPIO_TWL4030) || defined(CONFIG_GPIO_TWL4030_MODULE)
+#define twl_has_gpio()	true
+#else
+#define twl_has_gpio()	false
+#endif
+
+#if defined(CONFIG_TWL4030_MADC) || defined(CONFIG_TWL4030_MADC_MODULE)
+#define twl_has_madc()	true
+#else
+#define twl_has_madc()	false
+#endif
+
+#if defined(CONFIG_RTC_DRV_TWL4030) || defined(CONFIG_RTC_DRV_TWL4030_MODULE)
+#define twl_has_rtc()	true
+#else
+#define twl_has_rtc()	false
+#endif
+
+#if defined(CONFIG_TWL4030_USB) || defined(CONFIG_TWL4030_USB_MODULE)
+#define twl_has_usb()	true
+#else
+#define twl_has_usb()	false
+#endif
+
+static inline void activate_irq(int irq)
+{
+#ifdef CONFIG_ARM
+	/* ARM requires an extra step to clear IRQ_NOREQUEST, which it
+	 * sets on behalf of every irq_chip.  Also sets IRQ_NOPROBE.
+	 */
+	set_irq_flags(irq, IRQF_VALID);
+#else
+	/* same effect on other architectures */
+	set_irq_noprobe(irq);
+#endif
+}
+
+/* Primary Interrupt Handler on TWL4030 Registers */
+
+/* Register Definitions */
+
+#define REG_PIH_ISR_P1			(0x1)
+#define REG_PIH_ISR_P2			(0x2)
+#define REG_PIH_SIR			(0x3)
+
+/* Triton Core internal information (BEGIN) */
+
+/* Last - for index max*/
+#define TWL4030_MODULE_LAST		TWL4030_MODULE_SECURED_REG
+
+#define TWL4030_NUM_SLAVES		4
+
+
+/* Base Address defns for twl4030_map[] */
+
+/* subchip/slave 0 - USB ID */
+#define TWL4030_BASEADD_USB		0x0000
+
+/* subchip/slave 1 - AUD ID */
+#define TWL4030_BASEADD_AUDIO_VOICE	0x0000
+#define TWL4030_BASEADD_GPIO		0x0098
+#define TWL4030_BASEADD_INTBR		0x0085
+#define TWL4030_BASEADD_PIH		0x0080
+#define TWL4030_BASEADD_TEST		0x004C
+
+/* subchip/slave 2 - AUX ID */
+#define TWL4030_BASEADD_INTERRUPTS	0x00B9
+#define TWL4030_BASEADD_LED		0x00EE
+#define TWL4030_BASEADD_MADC		0x0000
+#define TWL4030_BASEADD_MAIN_CHARGE	0x0074
+#define TWL4030_BASEADD_PRECHARGE	0x00AA
+#define TWL4030_BASEADD_PWM0		0x00F8
+#define TWL4030_BASEADD_PWM1		0x00FB
+#define TWL4030_BASEADD_PWMA		0x00EF
+#define TWL4030_BASEADD_PWMB		0x00F1
+#define TWL4030_BASEADD_KEYPAD		0x00D2
+
+/* subchip/slave 3 - POWER ID */
+#define TWL4030_BASEADD_BACKUP		0x0014
+#define TWL4030_BASEADD_INT		0x002E
+#define TWL4030_BASEADD_PM_MASTER	0x0036
+#define TWL4030_BASEADD_PM_RECEIVER	0x005B
+#define TWL4030_BASEADD_RTC		0x001C
+#define TWL4030_BASEADD_SECURED_REG	0x0000
+
+/* Triton Core internal information (END) */
+
+
+/* Few power values */
+#define R_CFG_BOOT			0x05
+#define R_PROTECT_KEY			0x0E
+
+/* access control values for R_PROTECT_KEY */
+#define KEY_UNLOCK1			0xce
+#define KEY_UNLOCK2			0xec
+#define KEY_LOCK			0x00
+
+/* some fields in R_CFG_BOOT */
+#define HFCLK_FREQ_19p2_MHZ		(1 << 0)
+#define HFCLK_FREQ_26_MHZ		(2 << 0)
+#define HFCLK_FREQ_38p4_MHZ		(3 << 0)
+#define HIGH_PERF_SQ			(1 << 3)
+
+
+/*----------------------------------------------------------------------*/
+
+/**
+ * struct twl4030_mod_iregs - TWL module IMR/ISR regs to mask/clear at init
+ * @mod_no: TWL4030 module number (e.g., TWL4030_MODULE_GPIO)
+ * @sih_ctrl: address of module SIH_CTRL register
+ * @reg_cnt: number of IMR/ISR regs
+ * @imrs: pointer to array of TWL module interrupt mask register indices
+ * @isrs: pointer to array of TWL module interrupt status register indices
+ *
+ * Ties together TWL4030 modules and lists of IMR/ISR registers to mask/clear
+ * during twl_init_irq().
+ */
+struct twl4030_mod_iregs {
+	const u8 mod_no;
+	const u8 sih_ctrl;
+	const u8 reg_cnt;
+	const u8 *imrs;
+	const u8 *isrs;
+};
+
+/* TWL4030 INT module interrupt mask registers */
+static const u8 __initconst twl4030_int_imr_regs[] = {
+	TWL4030_INT_PWR_IMR1,
+	TWL4030_INT_PWR_IMR2,
+};
+
+/* TWL4030 INT module interrupt status registers */
+static const u8 __initconst twl4030_int_isr_regs[] = {
+	TWL4030_INT_PWR_ISR1,
+	TWL4030_INT_PWR_ISR2,
+};
+
+/* TWL4030 INTERRUPTS module interrupt mask registers */
+static const u8 __initconst twl4030_interrupts_imr_regs[] = {
+	TWL4030_INTERRUPTS_BCIIMR1A,
+	TWL4030_INTERRUPTS_BCIIMR1B,
+	TWL4030_INTERRUPTS_BCIIMR2A,
+	TWL4030_INTERRUPTS_BCIIMR2B,
+};
+
+/* TWL4030 INTERRUPTS module interrupt status registers */
+static const u8 __initconst twl4030_interrupts_isr_regs[] = {
+	TWL4030_INTERRUPTS_BCIISR1A,
+	TWL4030_INTERRUPTS_BCIISR1B,
+	TWL4030_INTERRUPTS_BCIISR2A,
+	TWL4030_INTERRUPTS_BCIISR2B,
+};
+
+/* TWL4030 MADC module interrupt mask registers */
+static const u8 __initconst twl4030_madc_imr_regs[] = {
+	TWL4030_MADC_IMR1,
+	TWL4030_MADC_IMR2,
+};
+
+/* TWL4030 MADC module interrupt status registers */
+static const u8 __initconst twl4030_madc_isr_regs[] = {
+	TWL4030_MADC_ISR1,
+	TWL4030_MADC_ISR2,
+};
+
+/* TWL4030 keypad module interrupt mask registers */
+static const u8 __initconst twl4030_keypad_imr_regs[] = {
+	TWL4030_KEYPAD_KEYP_IMR1,
+	TWL4030_KEYPAD_KEYP_IMR2,
+};
+
+/* TWL4030 keypad module interrupt status registers */
+static const u8 __initconst twl4030_keypad_isr_regs[] = {
+	TWL4030_KEYPAD_KEYP_ISR1,
+	TWL4030_KEYPAD_KEYP_ISR2,
+};
+
+/* TWL4030 GPIO module interrupt mask registers */
+static const u8 __initconst twl4030_gpio_imr_regs[] = {
+	REG_GPIO_IMR1A,
+	REG_GPIO_IMR1B,
+	REG_GPIO_IMR2A,
+	REG_GPIO_IMR2B,
+	REG_GPIO_IMR3A,
+	REG_GPIO_IMR3B,
+};
+
+/* TWL4030 GPIO module interrupt status registers */
+static const u8 __initconst twl4030_gpio_isr_regs[] = {
+	REG_GPIO_ISR1A,
+	REG_GPIO_ISR1B,
+	REG_GPIO_ISR2A,
+	REG_GPIO_ISR2B,
+	REG_GPIO_ISR3A,
+	REG_GPIO_ISR3B,
+};
+
+/* TWL4030 modules that have IMR/ISR registers that must be masked/cleared */
+static const struct twl4030_mod_iregs __initconst twl4030_mod_regs[] = {
+	{
+		.mod_no	  = TWL4030_MODULE_INT,
+		.sih_ctrl = TWL4030_INT_PWR_SIH_CTRL,
+		.reg_cnt  = ARRAY_SIZE(twl4030_int_imr_regs),
+		.imrs	  = twl4030_int_imr_regs,
+		.isrs	  = twl4030_int_isr_regs,
+	},
+	{
+		.mod_no	  = TWL4030_MODULE_INTERRUPTS,
+		.sih_ctrl = TWL4030_INTERRUPTS_BCISIHCTRL,
+		.reg_cnt  = ARRAY_SIZE(twl4030_interrupts_imr_regs),
+		.imrs	  = twl4030_interrupts_imr_regs,
+		.isrs	  = twl4030_interrupts_isr_regs,
+	},
+	{
+		.mod_no	  = TWL4030_MODULE_MADC,
+		.sih_ctrl = TWL4030_MADC_SIH_CTRL,
+		.reg_cnt  = ARRAY_SIZE(twl4030_madc_imr_regs),
+		.imrs	  = twl4030_madc_imr_regs,
+		.isrs	  = twl4030_madc_isr_regs,
+	},
+	{
+		.mod_no	  = TWL4030_MODULE_KEYPAD,
+		.sih_ctrl = TWL4030_KEYPAD_KEYP_SIH_CTRL,
+		.reg_cnt  = ARRAY_SIZE(twl4030_keypad_imr_regs),
+		.imrs	  = twl4030_keypad_imr_regs,
+		.isrs	  = twl4030_keypad_isr_regs,
+	},
+	{
+		.mod_no	  = TWL4030_MODULE_GPIO,
+		.sih_ctrl = REG_GPIO_SIH_CTRL,
+		.reg_cnt  = ARRAY_SIZE(twl4030_gpio_imr_regs),
+		.imrs	  = twl4030_gpio_imr_regs,
+		.isrs	  = twl4030_gpio_isr_regs,
+	},
+};
+
+/*----------------------------------------------------------------*/
+
+/* is driver active, bound to a chip? */
+static bool inuse;
+
+/* Structure for each TWL4030 Slave */
+struct twl4030_client {
+	struct i2c_client *client;
+	u8 address;
+
+	/* max numb of i2c_msg required is for read =2 */
+	struct i2c_msg xfer_msg[2];
+
+	/* To lock access to xfer_msg */
+	struct mutex xfer_lock;
+};
+
+static struct twl4030_client twl4030_modules[TWL4030_NUM_SLAVES];
+
+
+/* mapping the module id to slave id and base address */
+struct twl4030mapping {
+	unsigned char sid;	/* Slave ID */
+	unsigned char base;	/* base address */
+};
+
+static struct twl4030mapping twl4030_map[TWL4030_MODULE_LAST + 1] = {
+	/*
+	 * NOTE:  don't change this table without updating the
+	 * <linux/i2c/twl4030.h> defines for TWL4030_MODULE_*
+	 * so they continue to match the order in this table.
+	 */
+
+	{ 0, TWL4030_BASEADD_USB },
+
+	{ 1, TWL4030_BASEADD_AUDIO_VOICE },
+	{ 1, TWL4030_BASEADD_GPIO },
+	{ 1, TWL4030_BASEADD_INTBR },
+	{ 1, TWL4030_BASEADD_PIH },
+	{ 1, TWL4030_BASEADD_TEST },
+
+	{ 2, TWL4030_BASEADD_KEYPAD },
+	{ 2, TWL4030_BASEADD_MADC },
+	{ 2, TWL4030_BASEADD_INTERRUPTS },
+	{ 2, TWL4030_BASEADD_LED },
+	{ 2, TWL4030_BASEADD_MAIN_CHARGE },
+	{ 2, TWL4030_BASEADD_PRECHARGE },
+	{ 2, TWL4030_BASEADD_PWM0 },
+	{ 2, TWL4030_BASEADD_PWM1 },
+	{ 2, TWL4030_BASEADD_PWMA },
+	{ 2, TWL4030_BASEADD_PWMB },
+
+	{ 3, TWL4030_BASEADD_BACKUP },
+	{ 3, TWL4030_BASEADD_INT },
+	{ 3, TWL4030_BASEADD_PM_MASTER },
+	{ 3, TWL4030_BASEADD_PM_RECEIVER },
+	{ 3, TWL4030_BASEADD_RTC },
+	{ 3, TWL4030_BASEADD_SECURED_REG },
+};
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * TWL4030 doesn't have PIH mask, hence dummy function for mask
+ * and unmask of the (eight) interrupts reported at that level ...
+ * masking is only available from SIH (secondary) modules.
+ */
+
+static void twl4030_i2c_ackirq(unsigned int irq)
+{
+}
+
+static void twl4030_i2c_disableint(unsigned int irq)
+{
+}
+
+static void twl4030_i2c_enableint(unsigned int irq)
+{
+}
+
+static struct irq_chip twl4030_irq_chip = {
+	.name	= "twl4030",
+	.ack	= twl4030_i2c_ackirq,
+	.mask	= twl4030_i2c_disableint,
+	.unmask	= twl4030_i2c_enableint,
+};
+
+/*----------------------------------------------------------------------*/
+
+/* Exported Functions */
+
+/**
+ * twl4030_i2c_write - Writes a n bit register in TWL4030
+ * @mod_no: module number
+ * @value: an array of num_bytes+1 containing data to write
+ * @reg: register address (just offset will do)
+ * @num_bytes: number of bytes to transfer
+ *
+ * IMPORTANT: for 'value' parameter: Allocate value num_bytes+1 and
+ * valid data starts at Offset 1.
+ *
+ * Returns the result of operation - 0 is success
+ */
+int twl4030_i2c_write(u8 mod_no, u8 *value, u8 reg, u8 num_bytes)
+{
+	int ret;
+	int sid;
+	struct twl4030_client *twl;
+	struct i2c_msg *msg;
+
+	if (unlikely(mod_no > TWL4030_MODULE_LAST)) {
+		pr_err("%s: invalid module number %d\n", DRIVER_NAME, mod_no);
+		return -EPERM;
+	}
+	sid = twl4030_map[mod_no].sid;
+	twl = &twl4030_modules[sid];
+
+	if (unlikely(!inuse)) {
+		pr_err("%s: client %d is not initialized\n", DRIVER_NAME, sid);
+		return -EPERM;
+	}
+	mutex_lock(&twl->xfer_lock);
+	/*
+	 * [MSG1]: fill the register address data
+	 * fill the data Tx buffer
+	 */
+	msg = &twl->xfer_msg[0];
+	msg->addr = twl->address;
+	msg->len = num_bytes + 1;
+	msg->flags = 0;
+	msg->buf = value;
+	/* over write the first byte of buffer with the register address */
+	*value = twl4030_map[mod_no].base + reg;
+	ret = i2c_transfer(twl->client->adapter, twl->xfer_msg, 1);
+	mutex_unlock(&twl->xfer_lock);
+
+	/* i2cTransfer returns num messages.translate it pls.. */
+	if (ret >= 0)
+		ret = 0;
+	return ret;
+}
+EXPORT_SYMBOL(twl4030_i2c_write);
+
+/**
+ * twl4030_i2c_read - Reads a n bit register in TWL4030
+ * @mod_no: module number
+ * @value: an array of num_bytes containing data to be read
+ * @reg: register address (just offset will do)
+ * @num_bytes: number of bytes to transfer
+ *
+ * Returns result of operation - num_bytes is success else failure.
+ */
+int twl4030_i2c_read(u8 mod_no, u8 *value, u8 reg, u8 num_bytes)
+{
+	int ret;
+	u8 val;
+	int sid;
+	struct twl4030_client *twl;
+	struct i2c_msg *msg;
+
+	if (unlikely(mod_no > TWL4030_MODULE_LAST)) {
+		pr_err("%s: invalid module number %d\n", DRIVER_NAME, mod_no);
+		return -EPERM;
+	}
+	sid = twl4030_map[mod_no].sid;
+	twl = &twl4030_modules[sid];
+
+	if (unlikely(!inuse)) {
+		pr_err("%s: client %d is not initialized\n", DRIVER_NAME, sid);
+		return -EPERM;
+	}
+	mutex_lock(&twl->xfer_lock);
+	/* [MSG1] fill the register address data */
+	msg = &twl->xfer_msg[0];
+	msg->addr = twl->address;
+	msg->len = 1;
+	msg->flags = 0;	/* Read the register value */
+	val = twl4030_map[mod_no].base + reg;
+	msg->buf = &val;
+	/* [MSG2] fill the data rx buffer */
+	msg = &twl->xfer_msg[1];
+	msg->addr = twl->address;
+	msg->flags = I2C_M_RD;	/* Read the register value */
+	msg->len = num_bytes;	/* only n bytes */
+	msg->buf = value;
+	ret = i2c_transfer(twl->client->adapter, twl->xfer_msg, 2);
+	mutex_unlock(&twl->xfer_lock);
+
+	/* i2cTransfer returns num messages.translate it pls.. */
+	if (ret >= 0)
+		ret = 0;
+	return ret;
+}
+EXPORT_SYMBOL(twl4030_i2c_read);
+
+/**
+ * twl4030_i2c_write_u8 - Writes a 8 bit register in TWL4030
+ * @mod_no: module number
+ * @value: the value to be written 8 bit
+ * @reg: register address (just offset will do)
+ *
+ * Returns result of operation - 0 is success
+ */
+int twl4030_i2c_write_u8(u8 mod_no, u8 value, u8 reg)
+{
+
+	/* 2 bytes offset 1 contains the data offset 0 is used by i2c_write */
+	u8 temp_buffer[2] = { 0 };
+	/* offset 1 contains the data */
+	temp_buffer[1] = value;
+	return twl4030_i2c_write(mod_no, temp_buffer, reg, 1);
+}
+EXPORT_SYMBOL(twl4030_i2c_write_u8);
+
+/**
+ * twl4030_i2c_read_u8 - Reads a 8 bit register from TWL4030
+ * @mod_no: module number
+ * @value: the value read 8 bit
+ * @reg: register address (just offset will do)
+ *
+ * Returns result of operation - 0 is success
+ */
+int twl4030_i2c_read_u8(u8 mod_no, u8 *value, u8 reg)
+{
+	return twl4030_i2c_read(mod_no, value, reg, 1);
+}
+EXPORT_SYMBOL(twl4030_i2c_read_u8);
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * do_twl4030_module_irq() is the desc->handle method for each of the twl4030
+ * module interrupts that doesn't chain to another irq_chip (GPIO, power, etc).
+ * It executes in kernel thread context.  On entry, cpu interrupts are disabled.
+ */
+static void do_twl4030_module_irq(unsigned int irq, irq_desc_t *desc)
+{
+	struct irqaction *action;
+	const unsigned int cpu = smp_processor_id();
+
+	/*
+	 * Earlier this was desc->triggered = 1;
+	 */
+	desc->status |= IRQ_LEVEL;
+
+	/*
+	 * The desc->handle method would normally call the desc->chip->ack
+	 * method here, but we won't bother since our ack method is NULL.
+	 */
+
+	if (!desc->depth) {
+		kstat_cpu(cpu).irqs[irq]++;
+
+		action = desc->action;
+		if (action) {
+			int ret;
+			int status = 0;
+			int retval = 0;
+
+			local_irq_enable();
+
+			do {
+				/* Call the ISR with cpu interrupts enabled */
+				ret = action->handler(irq, action->dev_id);
+				if (ret == IRQ_HANDLED)
+					status |= action->flags;
+				retval |= ret;
+				action = action->next;
+			} while (action);
+
+			if (status & IRQF_SAMPLE_RANDOM)
+				add_interrupt_randomness(irq);
+
+			local_irq_disable();
+
+			if (retval != IRQ_HANDLED)
+				printk(KERN_ERR "ISR for TWL4030 module"
+					" irq %d can't handle interrupt\n",
+					irq);
+
+			/*
+			 * Here is where we should call the unmask method, but
+			 * again we won't bother since it is NULL.
+			 */
+		} else
+			printk(KERN_CRIT "TWL4030 module irq %d has no ISR"
+					" but can't be masked!\n", irq);
+	} else
+		printk(KERN_CRIT "TWL4030 module irq %d is disabled but can't"
+				" be masked!\n", irq);
+}
+
+static unsigned twl4030_irq_base;
+
+static struct completion irq_event;
+
+/*
+ * This thread processes interrupts reported by the Primary Interrupt Handler.
+ */
+static int twl4030_irq_thread(void *data)
+{
+	long irq = (long)data;
+	irq_desc_t *desc = irq_desc + irq;
+	static unsigned i2c_errors;
+	const static unsigned max_i2c_errors = 100;
+
+	daemonize("twl4030-irq");
+	current->flags |= PF_NOFREEZE;
+
+	while (!kthread_should_stop()) {
+		int ret;
+		int module_irq;
+		u8 pih_isr;
+
+		/* Wait for IRQ, then read PIH irq status (also blocking) */
+		wait_for_completion_interruptible(&irq_event);
+
+		ret = twl4030_i2c_read_u8(TWL4030_MODULE_PIH, &pih_isr,
+					  REG_PIH_ISR_P1);
+		if (ret) {
+			pr_warning("%s: I2C error %d reading PIH ISR\n",
+					DRIVER_NAME, ret);
+			if (++i2c_errors >= max_i2c_errors) {
+				printk(KERN_ERR "Maximum I2C error count"
+						" exceeded.  Terminating %s.\n",
+						__func__);
+				break;
+			}
+			complete(&irq_event);
+			continue;
+		}
+
+		/* these handlers deal with the relevant SIH irq status */
+		local_irq_disable();
+		for (module_irq = twl4030_irq_base;
+				pih_isr;
+				pih_isr >>= 1, module_irq++) {
+			if (pih_isr & 0x1) {
+				irq_desc_t *d = irq_desc + module_irq;
+
+				d->handle_irq(module_irq, d);
+			}
+		}
+		local_irq_enable();
+
+		desc->chip->unmask(irq);
+	}
+
+	return 0;
+}
+
+/*
+ * do_twl4030_irq() is the desc->handle method for the twl4030 interrupt.
+ * This is a chained interrupt, so there is no desc->action method for it.
+ * Now we need to query the interrupt controller in the twl4030 to determine
+ * which module is generating the interrupt request.  However, we can't do i2c
+ * transactions in interrupt context, so we must defer that work to a kernel
+ * thread.  All we do here is acknowledge and mask the interrupt and wakeup
+ * the kernel thread.
+ */
+static void do_twl4030_irq(unsigned int irq, irq_desc_t *desc)
+{
+	const unsigned int cpu = smp_processor_id();
+
+	/*
+	 * Earlier this was desc->triggered = 1;
+	 */
+	desc->status |= IRQ_LEVEL;
+
+	/*
+	 * Acknowledge, clear _AND_ disable the interrupt.
+	 */
+	desc->chip->ack(irq);
+
+	if (!desc->depth) {
+		kstat_cpu(cpu).irqs[irq]++;
+
+		complete(&irq_event);
+	}
+}
+
+static struct task_struct * __init start_twl4030_irq_thread(long irq)
+{
+	struct task_struct *thread;
+
+	init_completion(&irq_event);
+	thread = kthread_run(twl4030_irq_thread, (void *)irq,
+			     "twl4030 irq %ld", irq);
+	if (!thread)
+		pr_err("%s: could not create twl4030 irq %ld thread!\n",
+		       DRIVER_NAME, irq);
+
+	return thread;
+}
+
+/*----------------------------------------------------------------------*/
+
+static int add_children(struct twl4030_platform_data *pdata)
+{
+	struct platform_device	*pdev = NULL;
+	struct twl4030_client	*twl = NULL;
+	int			status = 0;
+
+	if (twl_has_bci() && pdata->bci) {
+		twl = &twl4030_modules[3];
+
+		pdev = platform_device_alloc("twl4030_bci", -1);
+		if (!pdev) {
+			pr_debug("%s: can't alloc bci dev\n", DRIVER_NAME);
+			status = -ENOMEM;
+			goto err;
+		}
+
+		if (status == 0) {
+			pdev->dev.parent = &twl->client->dev;
+			status = platform_device_add_data(pdev, pdata->bci,
+					sizeof(*pdata->bci));
+			if (status < 0) {
+				dev_dbg(&twl->client->dev,
+					"can't add bci data, %d\n",
+					status);
+				goto err;
+			}
+		}
+
+		if (status == 0) {
+			struct resource r = {
+				.start = TWL4030_PWRIRQ_CHG_PRES,
+				.flags = IORESOURCE_IRQ,
+			};
+
+			status = platform_device_add_resources(pdev, &r, 1);
+		}
+
+		if (status == 0)
+			status = platform_device_add(pdev);
+
+		if (status < 0) {
+			platform_device_put(pdev);
+			dev_dbg(&twl->client->dev,
+					"can't create bci dev, %d\n",
+					status);
+			goto err;
+		}
+	}
+
+	if (twl_has_gpio() && pdata->gpio) {
+		twl = &twl4030_modules[1];
+
+		pdev = platform_device_alloc("twl4030_gpio", -1);
+		if (!pdev) {
+			pr_debug("%s: can't alloc gpio dev\n", DRIVER_NAME);
+			status = -ENOMEM;
+			goto err;
+		}
+
+		/* more driver model init */
+		if (status == 0) {
+			pdev->dev.parent = &twl->client->dev;
+			/* device_init_wakeup(&pdev->dev, 1); */
+
+			status = platform_device_add_data(pdev, pdata->gpio,
+					sizeof(*pdata->gpio));
+			if (status < 0) {
+				dev_dbg(&twl->client->dev,
+					"can't add gpio data, %d\n",
+					status);
+				goto err;
+			}
+		}
+
+		/* GPIO module IRQ */
+		if (status == 0) {
+			struct resource	r = {
+				.start = pdata->irq_base + 0,
+				.flags = IORESOURCE_IRQ,
+			};
+
+			status = platform_device_add_resources(pdev, &r, 1);
+		}
+
+		if (status == 0)
+			status = platform_device_add(pdev);
+
+		if (status < 0) {
+			platform_device_put(pdev);
+			dev_dbg(&twl->client->dev,
+					"can't create gpio dev, %d\n",
+					status);
+			goto err;
+		}
+	}
+
+	if (twl_has_keypad() && pdata->keypad) {
+		pdev = platform_device_alloc("twl4030_keypad", -1);
+		if (pdev) {
+			twl = &twl4030_modules[2];
+			pdev->dev.parent = &twl->client->dev;
+			device_init_wakeup(&pdev->dev, 1);
+			status = platform_device_add_data(pdev, pdata->keypad,
+					sizeof(*pdata->keypad));
+			if (status < 0) {
+				dev_dbg(&twl->client->dev,
+					"can't add keypad data, %d\n",
+					status);
+				platform_device_put(pdev);
+				goto err;
+			}
+			status = platform_device_add(pdev);
+			if (status < 0) {
+				platform_device_put(pdev);
+				dev_dbg(&twl->client->dev,
+						"can't create keypad dev, %d\n",
+						status);
+				goto err;
+			}
+		} else {
+			pr_debug("%s: can't alloc keypad dev\n", DRIVER_NAME);
+			status = -ENOMEM;
+			goto err;
+		}
+	}
+
+	if (twl_has_madc() && pdata->madc) {
+		pdev = platform_device_alloc("twl4030_madc", -1);
+		if (pdev) {
+			twl = &twl4030_modules[2];
+			pdev->dev.parent = &twl->client->dev;
+			device_init_wakeup(&pdev->dev, 1);
+			status = platform_device_add_data(pdev, pdata->madc,
+					sizeof(*pdata->madc));
+			if (status < 0) {
+				platform_device_put(pdev);
+				dev_dbg(&twl->client->dev,
+					"can't add madc data, %d\n",
+					status);
+				goto err;
+			}
+			status = platform_device_add(pdev);
+			if (status < 0) {
+				platform_device_put(pdev);
+				dev_dbg(&twl->client->dev,
+						"can't create madc dev, %d\n",
+						status);
+				goto err;
+			}
+		} else {
+			pr_debug("%s: can't alloc madc dev\n", DRIVER_NAME);
+			status = -ENOMEM;
+			goto err;
+		}
+	}
+
+	if (twl_has_rtc()) {
+		twl = &twl4030_modules[3];
+
+		pdev = platform_device_alloc("twl4030_rtc", -1);
+		if (!pdev) {
+			pr_debug("%s: can't alloc rtc dev\n", DRIVER_NAME);
+			status = -ENOMEM;
+		} else {
+			pdev->dev.parent = &twl->client->dev;
+			device_init_wakeup(&pdev->dev, 1);
+		}
+
+		/*
+		 * REVISIT platform_data here currently might use of
+		 * "msecure" line ... but for now we just expect board
+		 * setup to tell the chip "we are secure" at all times.
+		 * Eventually, Linux might become more aware of such
+		 * HW security concerns, and "least privilege".
+		 */
+
+		/* RTC module IRQ */
+		if (status == 0) {
+			struct resource	r = {
+				/* REVISIT don't hard-wire this stuff */
+				.start = TWL4030_PWRIRQ_RTC,
+				.flags = IORESOURCE_IRQ,
+			};
+
+			status = platform_device_add_resources(pdev, &r, 1);
+		}
+
+		if (status == 0)
+			status = platform_device_add(pdev);
+
+		if (status < 0) {
+			platform_device_put(pdev);
+			dev_dbg(&twl->client->dev,
+					"can't create rtc dev, %d\n",
+					status);
+			goto err;
+		}
+	}
+
+	if (twl_has_usb() && pdata->usb) {
+		twl = &twl4030_modules[0];
+
+		pdev = platform_device_alloc("twl4030_usb", -1);
+		if (!pdev) {
+			pr_debug("%s: can't alloc usb dev\n", DRIVER_NAME);
+			status = -ENOMEM;
+			goto err;
+		}
+
+		if (status == 0) {
+			pdev->dev.parent = &twl->client->dev;
+			device_init_wakeup(&pdev->dev, 1);
+			status = platform_device_add_data(pdev, pdata->usb,
+					sizeof(*pdata->usb));
+			if (status < 0) {
+				platform_device_put(pdev);
+				dev_dbg(&twl->client->dev,
+					"can't add usb data, %d\n",
+					status);
+				goto err;
+			}
+		}
+
+		if (status == 0) {
+			struct resource r = {
+				.start = TWL4030_PWRIRQ_USB_PRES,
+				.flags = IORESOURCE_IRQ,
+			};
+
+			status = platform_device_add_resources(pdev, &r, 1);
+		}
+
+		if (status == 0)
+			status = platform_device_add(pdev);
+
+		if (status < 0) {
+			platform_device_put(pdev);
+			dev_dbg(&twl->client->dev,
+					"can't create usb dev, %d\n",
+					status);
+		}
+	}
+
+err:
+	if (status)
+		pr_err("failed to add twl4030's children (status %d)\n", status);
+	return status;
+}
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * These three functions initialize the on-chip clock framework,
+ * letting it generate the right frequencies for USB, MADC, and
+ * other purposes.
+ */
+static inline int __init protect_pm_master(void)
+{
+	int e = 0;
+
+	e = twl4030_i2c_write_u8(TWL4030_MODULE_PM_MASTER, KEY_LOCK,
+			R_PROTECT_KEY);
+	return e;
+}
+
+static inline int __init unprotect_pm_master(void)
+{
+	int e = 0;
+
+	e |= twl4030_i2c_write_u8(TWL4030_MODULE_PM_MASTER, KEY_UNLOCK1,
+			R_PROTECT_KEY);
+	e |= twl4030_i2c_write_u8(TWL4030_MODULE_PM_MASTER, KEY_UNLOCK2,
+			R_PROTECT_KEY);
+	return e;
+}
+
+static void __init clocks_init(void)
+{
+	int e = 0;
+	struct clk *osc;
+	u32 rate;
+	u8 ctrl = HFCLK_FREQ_26_MHZ;
+
+#if defined(CONFIG_ARCH_OMAP2) || defined(CONFIG_ARCH_OMAP3)
+	if (cpu_is_omap2430())
+		osc = clk_get(NULL, "osc_ck");
+	else
+		osc = clk_get(NULL, "osc_sys_ck");
+#else
+	/* REVISIT for non-OMAP systems, pass the clock rate from
+	 * board init code, using platform_data.
+	 */
+	osc = ERR_PTR(-EIO);
+#endif
+	if (IS_ERR(osc)) {
+		printk(KERN_WARNING "Skipping twl4030 internal clock init and "
+				"using bootloader value (unknown osc rate)\n");
+		return;
+	}
+
+	rate = clk_get_rate(osc);
+	clk_put(osc);
+
+	switch (rate) {
+	case 19200000:
+		ctrl = HFCLK_FREQ_19p2_MHZ;
+		break;
+	case 26000000:
+		ctrl = HFCLK_FREQ_26_MHZ;
+		break;
+	case 38400000:
+		ctrl = HFCLK_FREQ_38p4_MHZ;
+		break;
+	}
+
+	ctrl |= HIGH_PERF_SQ;
+	e |= unprotect_pm_master();
+	/* effect->MADC+USB ck en */
+	e |= twl4030_i2c_write_u8(TWL4030_MODULE_PM_MASTER, ctrl, R_CFG_BOOT);
+	e |= protect_pm_master();
+
+	if (e < 0)
+		pr_err("%s: clock init err [%d]\n", DRIVER_NAME, e);
+}
+
+/*----------------------------------------------------------------------*/
+
+/**
+ * twl4030_i2c_clear_isr - clear TWL4030 SIH ISR regs via read + write
+ * @mod_no: TWL4030 module number
+ * @reg: register index to clear
+ * @cor: value of the <module>_SIH_CTRL.COR bit (1 or 0)
+ *
+ * Either reads (cor == 1) or writes (cor == 0) to a TWL4030 interrupt
+ * status register to ensure that any prior interrupts are cleared.
+ * Returns the status from the I2C read operation.
+ */
+static int __init twl4030_i2c_clear_isr(u8 mod_no, u8 reg, u8 cor)
+{
+	u8 tmp;
+
+	return (cor) ? twl4030_i2c_read_u8(mod_no, &tmp, reg) :
+		twl4030_i2c_write_u8(mod_no, 0xff, reg);
+}
+
+/**
+ * twl4030_read_cor_bit - are TWL module ISRs cleared by reads or writes?
+ * @mod_no: TWL4030 module number
+ * @reg: register index to clear
+ *
+ * Returns 1 if the TWL4030 SIH interrupt status registers (ISRs) for
+ * the specified TWL module are cleared by reads, or 0 if cleared by
+ * writes.
+ */
+static int twl4030_read_cor_bit(u8 mod_no, u8 reg)
+{
+	u8 tmp = 0;
+
+	WARN_ON(twl4030_i2c_read_u8(mod_no, &tmp, reg) < 0);
+
+	tmp &= TWL4030_SIH_CTRL_COR_MASK;
+	tmp >>= __ffs(TWL4030_SIH_CTRL_COR_MASK);
+
+	return tmp;
+}
+
+/**
+ * twl4030_mask_clear_intrs - mask and clear all TWL4030 interrupts
+ * @t: pointer to twl4030_mod_iregs array
+ * @t_sz: ARRAY_SIZE(t) (starting at 1)
+ *
+ * Mask all TWL4030 interrupt mask registers (IMRs) and clear all
+ * interrupt status registers (ISRs).  No return value, but will WARN if
+ * any I2C operations fail.
+ */
+static void __init twl4030_mask_clear_intrs(const struct twl4030_mod_iregs *t,
+					    const u8 t_sz)
+{
+	int i, j;
+
+	/*
+	 * N.B. - further efficiency is possible here.  Eight I2C
+	 * operations on BCI and GPIO modules are avoidable if I2C
+	 * burst read/write transactions were implemented.  Would
+	 * probably save about 1ms of boot time and a small amount of
+	 * power.
+	 */
+	for (i = 0; i < t_sz; i++) {
+		const struct twl4030_mod_iregs tmr = t[i];
+		int cor;
+
+		/* Are ISRs cleared by reads or writes? */
+		cor = twl4030_read_cor_bit(tmr.mod_no, tmr.sih_ctrl);
+
+		for (j = 0; j < tmr.reg_cnt; j++) {
+
+			/* Mask interrupts at the TWL4030 */
+			WARN_ON(twl4030_i2c_write_u8(tmr.mod_no, 0xff,
+						     tmr.imrs[j]) < 0);
+
+			/* Clear TWL4030 ISRs */
+			WARN_ON(twl4030_i2c_clear_isr(tmr.mod_no,
+						      tmr.isrs[j], cor) < 0);
+		}
+	}
+}
+
+
+static void twl_init_irq(int irq_num, unsigned irq_base, unsigned irq_end)
+{
+	int	i;
+
+	/*
+	 * Mask and clear all TWL4030 interrupts since initially we do
+	 * not have any TWL4030 module interrupt handlers present
+	 */
+	twl4030_mask_clear_intrs(twl4030_mod_regs,
+				 ARRAY_SIZE(twl4030_mod_regs));
+
+	twl4030_irq_base = irq_base;
+
+	/* install an irq handler for each of the PIH modules */
+	for (i = irq_base; i < irq_end; i++) {
+		set_irq_chip_and_handler(i, &twl4030_irq_chip,
+				do_twl4030_module_irq);
+		activate_irq(i);
+	}
+
+	/* install an irq handler to demultiplex the TWL4030 interrupt */
+	set_irq_data(irq_num, start_twl4030_irq_thread(irq_num));
+	set_irq_chained_handler(irq_num, do_twl4030_irq);
+}
+
+/*----------------------------------------------------------------------*/
+
+static int twl4030_remove(struct i2c_client *client)
+{
+	unsigned i;
+
+	/* FIXME undo twl_init_irq() */
+	if (twl4030_irq_base) {
+		dev_err(&client->dev, "can't yet clean up IRQs?\n");
+		return -ENOSYS;
+	}
+
+	for (i = 0; i < TWL4030_NUM_SLAVES; i++) {
+		struct twl4030_client	*twl = &twl4030_modules[i];
+
+		if (twl->client && twl->client != client)
+			i2c_unregister_device(twl->client);
+		twl4030_modules[i].client = NULL;
+	}
+	inuse = false;
+	return 0;
+}
+
+/* NOTE:  this driver only handles a single twl4030/tps659x0 chip */
+static int
+twl4030_probe(struct i2c_client *client, const struct i2c_device_id *id)
+{
+	int				status;
+	unsigned			i;
+	struct twl4030_platform_data	*pdata = client->dev.platform_data;
+
+	if (!pdata) {
+		dev_dbg(&client->dev, "no platform data?\n");
+		return -EINVAL;
+	}
+
+	if (i2c_check_functionality(client->adapter, I2C_FUNC_I2C) == 0) {
+		dev_dbg(&client->dev, "can't talk I2C?\n");
+		return -EIO;
+	}
+
+	if (inuse || twl4030_irq_base) {
+		dev_dbg(&client->dev, "driver is already in use\n");
+		return -EBUSY;
+	}
+
+	for (i = 0; i < TWL4030_NUM_SLAVES; i++) {
+		struct twl4030_client	*twl = &twl4030_modules[i];
+
+		twl->address = client->addr + i;
+		if (i == 0)
+			twl->client = client;
+		else {
+			twl->client = i2c_new_dummy(client->adapter,
+					twl->address);
+			if (!twl->client) {
+				dev_err(&twl->client->dev,
+					"can't attach client %d\n", i);
+				status = -ENOMEM;
+				goto fail;
+			}
+			strlcpy(twl->client->name, id->name,
+					sizeof(twl->client->name));
+		}
+		mutex_init(&twl->xfer_lock);
+	}
+	inuse = true;
+
+	/* setup clock framework */
+	clocks_init();
+
+	/* Maybe init the T2 Interrupt subsystem */
+	if (client->irq
+			&& pdata->irq_base
+			&& pdata->irq_end > pdata->irq_base) {
+		twl_init_irq(client->irq, pdata->irq_base, pdata->irq_end);
+		dev_info(&client->dev, "IRQ %d chains IRQs %d..%d\n",
+				client->irq, pdata->irq_base, pdata->irq_end - 1);
+	}
+
+	status = add_children(pdata);
+fail:
+	if (status < 0)
+		twl4030_remove(client);
+	return status;
+}
+
+static const struct i2c_device_id twl4030_ids[] = {
+	{ "twl4030", 0 },	/* "Triton 2" */
+	{ "tps65950", 0 },	/* catalog version of twl4030 */
+	{ "tps65930", 0 },	/* fewer LDOs and DACs; no charger */
+	{ "tps65920", 0 },	/* fewer LDOs; no codec or charger */
+	{ "twl5030", 0 },	/* T2 updated */
+	{ /* end of list */ },
+};
+MODULE_DEVICE_TABLE(i2c, twl4030_ids);
+
+/* One Client Driver , 4 Clients */
+static struct i2c_driver twl4030_driver = {
+	.driver.name	= DRIVER_NAME,
+	.id_table	= twl4030_ids,
+	.probe		= twl4030_probe,
+	.remove		= twl4030_remove,
+};
+
+static int __init twl4030_init(void)
+{
+	return i2c_add_driver(&twl4030_driver);
+}
+subsys_initcall(twl4030_init);
+
+static void __exit twl4030_exit(void)
+{
+	i2c_del_driver(&twl4030_driver);
+}
+module_exit(twl4030_exit);
+
+MODULE_AUTHOR("Texas Instruments, Inc.");
+MODULE_DESCRIPTION("I2C Core interface for TWL4030");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/i2c/twl4030.h b/include/linux/i2c/twl4030.h
new file mode 100644
index 000000000000..cdb453162a97
--- /dev/null
+++ b/include/linux/i2c/twl4030.h
@@ -0,0 +1,339 @@
+/*
+ * twl4030.h - header for TWL4030 PM and audio CODEC device
+ *
+ * Copyright (C) 2005-2006 Texas Instruments, Inc.
+ *
+ * Based on tlv320aic23.c:
+ * Copyright (c) by Kai Svahn <kai.svahn@nokia.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ */
+
+#ifndef __TWL4030_H_
+#define __TWL4030_H_
+
+/*
+ * Using the twl4030 core we address registers using a pair
+ *	{ module id, relative register offset }
+ * which that core then maps to the relevant
+ *	{ i2c slave, absolute register address }
+ *
+ * The module IDs are meaningful only to the twl4030 core code,
+ * which uses them as array indices to look up the first register
+ * address each module uses within a given i2c slave.
+ */
+
+/* Slave 0 (i2c address 0x48) */
+#define TWL4030_MODULE_USB		0x00
+
+/* Slave 1 (i2c address 0x49) */
+#define TWL4030_MODULE_AUDIO_VOICE	0x01
+#define TWL4030_MODULE_GPIO		0x02
+#define TWL4030_MODULE_INTBR		0x03
+#define TWL4030_MODULE_PIH		0x04
+#define TWL4030_MODULE_TEST		0x05
+
+/* Slave 2 (i2c address 0x4a) */
+#define TWL4030_MODULE_KEYPAD		0x06
+#define TWL4030_MODULE_MADC		0x07
+#define TWL4030_MODULE_INTERRUPTS	0x08
+#define TWL4030_MODULE_LED		0x09
+#define TWL4030_MODULE_MAIN_CHARGE	0x0A
+#define TWL4030_MODULE_PRECHARGE	0x0B
+#define TWL4030_MODULE_PWM0		0x0C
+#define TWL4030_MODULE_PWM1		0x0D
+#define TWL4030_MODULE_PWMA		0x0E
+#define TWL4030_MODULE_PWMB		0x0F
+
+/* Slave 3 (i2c address 0x4b) */
+#define TWL4030_MODULE_BACKUP		0x10
+#define TWL4030_MODULE_INT		0x11
+#define TWL4030_MODULE_PM_MASTER	0x12
+#define TWL4030_MODULE_PM_RECEIVER	0x13
+#define TWL4030_MODULE_RTC		0x14
+#define TWL4030_MODULE_SECURED_REG	0x15
+
+/*
+ * Read and write single 8-bit registers
+ */
+int twl4030_i2c_write_u8(u8 mod_no, u8 val, u8 reg);
+int twl4030_i2c_read_u8(u8 mod_no, u8 *val, u8 reg);
+
+/*
+ * Read and write several 8-bit registers at once.
+ *
+ * IMPORTANT:  For twl4030_i2c_write(), allocate num_bytes + 1
+ * for the value, and populate your data starting at offset 1.
+ */
+int twl4030_i2c_write(u8 mod_no, u8 *value, u8 reg, u8 num_bytes);
+int twl4030_i2c_read(u8 mod_no, u8 *value, u8 reg, u8 num_bytes);
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * NOTE:  at up to 1024 registers, this is a big chip.
+ *
+ * Avoid putting register declarations in this file, instead of into
+ * a driver-private file, unless some of the registers in a block
+ * need to be shared with other drivers.  One example is blocks that
+ * have Secondary IRQ Handler (SIH) registers.
+ */
+
+#define TWL4030_SIH_CTRL_EXCLEN_MASK	BIT(0)
+#define TWL4030_SIH_CTRL_PENDDIS_MASK	BIT(1)
+#define TWL4030_SIH_CTRL_COR_MASK	BIT(2)
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * GPIO Block Register offsets (use TWL4030_MODULE_GPIO)
+ */
+
+#define REG_GPIODATAIN1			0x0
+#define REG_GPIODATAIN2			0x1
+#define REG_GPIODATAIN3			0x2
+#define REG_GPIODATADIR1		0x3
+#define REG_GPIODATADIR2		0x4
+#define REG_GPIODATADIR3		0x5
+#define REG_GPIODATAOUT1		0x6
+#define REG_GPIODATAOUT2		0x7
+#define REG_GPIODATAOUT3		0x8
+#define REG_CLEARGPIODATAOUT1		0x9
+#define REG_CLEARGPIODATAOUT2		0xA
+#define REG_CLEARGPIODATAOUT3		0xB
+#define REG_SETGPIODATAOUT1		0xC
+#define REG_SETGPIODATAOUT2		0xD
+#define REG_SETGPIODATAOUT3		0xE
+#define REG_GPIO_DEBEN1			0xF
+#define REG_GPIO_DEBEN2			0x10
+#define REG_GPIO_DEBEN3			0x11
+#define REG_GPIO_CTRL			0x12
+#define REG_GPIOPUPDCTR1		0x13
+#define REG_GPIOPUPDCTR2		0x14
+#define REG_GPIOPUPDCTR3		0x15
+#define REG_GPIOPUPDCTR4		0x16
+#define REG_GPIOPUPDCTR5		0x17
+#define REG_GPIO_ISR1A			0x19
+#define REG_GPIO_ISR2A			0x1A
+#define REG_GPIO_ISR3A			0x1B
+#define REG_GPIO_IMR1A			0x1C
+#define REG_GPIO_IMR2A			0x1D
+#define REG_GPIO_IMR3A			0x1E
+#define REG_GPIO_ISR1B			0x1F
+#define REG_GPIO_ISR2B			0x20
+#define REG_GPIO_ISR3B			0x21
+#define REG_GPIO_IMR1B			0x22
+#define REG_GPIO_IMR2B			0x23
+#define REG_GPIO_IMR3B			0x24
+#define REG_GPIO_EDR1			0x28
+#define REG_GPIO_EDR2			0x29
+#define REG_GPIO_EDR3			0x2A
+#define REG_GPIO_EDR4			0x2B
+#define REG_GPIO_EDR5			0x2C
+#define REG_GPIO_SIH_CTRL		0x2D
+
+/* Up to 18 signals are available as GPIOs, when their
+ * pins are not assigned to another use (such as ULPI/USB).
+ */
+#define TWL4030_GPIO_MAX		18
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * Keypad register offsets (use TWL4030_MODULE_KEYPAD)
+ * ... SIH/interrupt only
+ */
+
+#define TWL4030_KEYPAD_KEYP_ISR1	0x11
+#define TWL4030_KEYPAD_KEYP_IMR1	0x12
+#define TWL4030_KEYPAD_KEYP_ISR2	0x13
+#define TWL4030_KEYPAD_KEYP_IMR2	0x14
+#define TWL4030_KEYPAD_KEYP_SIR		0x15	/* test register */
+#define TWL4030_KEYPAD_KEYP_EDR		0x16
+#define TWL4030_KEYPAD_KEYP_SIH_CTRL	0x17
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * Multichannel ADC register offsets (use TWL4030_MODULE_MADC)
+ * ... SIH/interrupt only
+ */
+
+#define TWL4030_MADC_ISR1		0x61
+#define TWL4030_MADC_IMR1		0x62
+#define TWL4030_MADC_ISR2		0x63
+#define TWL4030_MADC_IMR2		0x64
+#define TWL4030_MADC_SIR		0x65	/* test register */
+#define TWL4030_MADC_EDR		0x66
+#define TWL4030_MADC_SIH_CTRL		0x67
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * Battery charger register offsets (use TWL4030_MODULE_INTERRUPTS)
+ */
+
+#define TWL4030_INTERRUPTS_BCIISR1A	0x0
+#define TWL4030_INTERRUPTS_BCIISR2A	0x1
+#define TWL4030_INTERRUPTS_BCIIMR1A	0x2
+#define TWL4030_INTERRUPTS_BCIIMR2A	0x3
+#define TWL4030_INTERRUPTS_BCIISR1B	0x4
+#define TWL4030_INTERRUPTS_BCIISR2B	0x5
+#define TWL4030_INTERRUPTS_BCIIMR1B	0x6
+#define TWL4030_INTERRUPTS_BCIIMR2B	0x7
+#define TWL4030_INTERRUPTS_BCISIR1	0x8	/* test register */
+#define TWL4030_INTERRUPTS_BCISIR2	0x9	/* test register */
+#define TWL4030_INTERRUPTS_BCIEDR1	0xa
+#define TWL4030_INTERRUPTS_BCIEDR2	0xb
+#define TWL4030_INTERRUPTS_BCIEDR3	0xc
+#define TWL4030_INTERRUPTS_BCISIHCTRL	0xd
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * Power Interrupt block register offsets (use TWL4030_MODULE_INT)
+ */
+
+#define TWL4030_INT_PWR_ISR1		0x0
+#define TWL4030_INT_PWR_IMR1		0x1
+#define TWL4030_INT_PWR_ISR2		0x2
+#define TWL4030_INT_PWR_IMR2		0x3
+#define TWL4030_INT_PWR_SIR		0x4	/* test register */
+#define TWL4030_INT_PWR_EDR1		0x5
+#define TWL4030_INT_PWR_EDR2		0x6
+#define TWL4030_INT_PWR_SIH_CTRL	0x7
+
+/*----------------------------------------------------------------------*/
+
+struct twl4030_bci_platform_data {
+	int *battery_tmp_tbl;
+	unsigned int tblsize;
+};
+
+/* TWL4030_GPIO_MAX (18) GPIOs, with interrupts */
+struct twl4030_gpio_platform_data {
+	int		gpio_base;
+	unsigned	irq_base, irq_end;
+
+	/* For gpio-N, bit (1 << N) in "pullups" is set if that pullup
+	 * should be enabled.  Else, if that bit is set in "pulldowns",
+	 * that pulldown is enabled.  Don't waste power by letting any
+	 * digital inputs float...
+	 */
+	u32		pullups;
+	u32		pulldowns;
+
+	int		(*setup)(struct device *dev,
+				unsigned gpio, unsigned ngpio);
+	int		(*teardown)(struct device *dev,
+				unsigned gpio, unsigned ngpio);
+};
+
+struct twl4030_madc_platform_data {
+	int		irq_line;
+};
+
+struct twl4030_keypad_data {
+	int rows;
+	int cols;
+	int *keymap;
+	int irq;
+	unsigned int keymapsize;
+	unsigned int rep:1;
+};
+
+enum twl4030_usb_mode {
+	T2_USB_MODE_ULPI = 1,
+	T2_USB_MODE_CEA2011_3PIN = 2,
+};
+
+struct twl4030_usb_data {
+	enum twl4030_usb_mode	usb_mode;
+};
+
+struct twl4030_platform_data {
+	unsigned				irq_base, irq_end;
+	struct twl4030_bci_platform_data	*bci;
+	struct twl4030_gpio_platform_data	*gpio;
+	struct twl4030_madc_platform_data	*madc;
+	struct twl4030_keypad_data		*keypad;
+	struct twl4030_usb_data			*usb;
+
+	/* REVISIT more to come ... _nothing_ should be hard-wired */
+};
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * FIXME completely stop using TWL4030_IRQ_BASE ... instead, pass the
+ * IRQ data to subsidiary devices using platform device resources.
+ */
+
+/* IRQ information-need base */
+#include <mach/irqs.h>
+/* TWL4030 interrupts */
+
+/* #define TWL4030_MODIRQ_GPIO		(TWL4030_IRQ_BASE + 0) */
+#define TWL4030_MODIRQ_KEYPAD		(TWL4030_IRQ_BASE + 1)
+#define TWL4030_MODIRQ_BCI		(TWL4030_IRQ_BASE + 2)
+#define TWL4030_MODIRQ_MADC		(TWL4030_IRQ_BASE + 3)
+/* #define TWL4030_MODIRQ_USB		(TWL4030_IRQ_BASE + 4) */
+#define TWL4030_MODIRQ_PWR		(TWL4030_IRQ_BASE + 5)
+
+#define TWL4030_PWRIRQ_PWRBTN		(TWL4030_PWR_IRQ_BASE + 0)
+#define TWL4030_PWRIRQ_CHG_PRES		(TWL4030_PWR_IRQ_BASE + 1)
+#define TWL4030_PWRIRQ_USB_PRES		(TWL4030_PWR_IRQ_BASE + 2)
+#define TWL4030_PWRIRQ_RTC		(TWL4030_PWR_IRQ_BASE + 3)
+#define TWL4030_PWRIRQ_HOT_DIE		(TWL4030_PWR_IRQ_BASE + 4)
+#define TWL4030_PWRIRQ_PWROK_TIMEOUT	(TWL4030_PWR_IRQ_BASE + 5)
+#define TWL4030_PWRIRQ_MBCHG		(TWL4030_PWR_IRQ_BASE + 6)
+#define TWL4030_PWRIRQ_SC_DETECT	(TWL4030_PWR_IRQ_BASE + 7)
+
+/* Rest are unsued currently*/
+
+/* Offsets to Power Registers */
+#define TWL4030_VDAC_DEV_GRP		0x3B
+#define TWL4030_VDAC_DEDICATED		0x3E
+#define TWL4030_VAUX1_DEV_GRP		0x17
+#define TWL4030_VAUX1_DEDICATED		0x1A
+#define TWL4030_VAUX2_DEV_GRP		0x1B
+#define TWL4030_VAUX2_DEDICATED		0x1E
+#define TWL4030_VAUX3_DEV_GRP		0x1F
+#define TWL4030_VAUX3_DEDICATED		0x22
+
+/* TWL4030 GPIO interrupt definitions */
+
+#define TWL4030_GPIO_IRQ_NO(n)		(TWL4030_GPIO_IRQ_BASE + (n))
+#define TWL4030_GPIO_IS_ENABLE		1
+
+/*
+ * Exported TWL4030 GPIO APIs
+ *
+ * WARNING -- use standard GPIO and IRQ calls instead; these will vanish.
+ */
+int twl4030_get_gpio_datain(int gpio);
+int twl4030_request_gpio(int gpio);
+int twl4030_set_gpio_debounce(int gpio, int enable);
+int twl4030_free_gpio(int gpio);
+
+#if defined(CONFIG_TWL4030_BCI_BATTERY) || \
+	defined(CONFIG_TWL4030_BCI_BATTERY_MODULE)
+	extern int twl4030charger_usb_en(int enable);
+#else
+	static inline int twl4030charger_usb_en(int enable) { return 0; }
+#endif
+
+#endif /* End of __TWL4030_H */
-- 
cgit v1.2.3


From 26b8f5e1e2d1229c186d8e61d26513c43a058c5e Mon Sep 17 00:00:00 2001
From: Eric Miao <eric.miao@marvell.com>
Date: Wed, 15 Oct 2008 12:20:06 +0200
Subject: mfd: add base support for Dialog DA9030/DA9034 PMICs

DA9030 (a.k.a ARAVA) and DA9034 (a.k.a MICCO) are PMICs designed by
Dialog Semiconductor, usually found on PXA-based platforms. These
PMICs are I2C-based, multi-function devices, usually with LEDs, PWMs
for backlight, BUCKs and LDOs, ADCs and touchscreen controller (on
DA9034).

This is the base support for the I2C operations, event registration
and handling, sub-devices management.

Signed-off-by: Mike Rapoport <mike@compulab.co.il>
Signed-off-by: Eric Miao <eric.miao@marvell.com>
Signed-off-by: Liam Girdwood <lrg@kernel.org>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/da903x.c       | 563 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/da903x.h | 201 ++++++++++++++++
 2 files changed, 764 insertions(+)
 create mode 100644 drivers/mfd/da903x.c
 create mode 100644 include/linux/mfd/da903x.h

(limited to 'include')

diff --git a/drivers/mfd/da903x.c b/drivers/mfd/da903x.c
new file mode 100644
index 000000000000..b57326ae464d
--- /dev/null
+++ b/drivers/mfd/da903x.c
@@ -0,0 +1,563 @@
+/*
+ * Base driver for Dialog Semiconductor DA9030/DA9034
+ *
+ * Copyright (C) 2008 Compulab, Ltd.
+ * 	Mike Rapoport <mike@compulab.co.il>
+ *
+ * Copyright (C) 2006-2008 Marvell International Ltd.
+ * 	Eric Miao <eric.miao@marvell.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/i2c.h>
+#include <linux/mfd/da903x.h>
+
+#define DA9030_CHIP_ID		0x00
+#define DA9030_EVENT_A		0x01
+#define DA9030_EVENT_B		0x02
+#define DA9030_EVENT_C		0x03
+#define DA9030_STATUS		0x04
+#define DA9030_IRQ_MASK_A	0x05
+#define DA9030_IRQ_MASK_B	0x06
+#define DA9030_IRQ_MASK_C	0x07
+#define DA9030_SYS_CTRL_A	0x08
+#define DA9030_SYS_CTRL_B	0x09
+#define DA9030_FAULT_LOG	0x0a
+
+#define DA9034_CHIP_ID		0x00
+#define DA9034_EVENT_A		0x01
+#define DA9034_EVENT_B		0x02
+#define DA9034_EVENT_C		0x03
+#define DA9034_EVENT_D		0x04
+#define DA9034_STATUS_A		0x05
+#define DA9034_STATUS_B		0x06
+#define DA9034_IRQ_MASK_A	0x07
+#define DA9034_IRQ_MASK_B	0x08
+#define DA9034_IRQ_MASK_C	0x09
+#define DA9034_IRQ_MASK_D	0x0a
+#define DA9034_SYS_CTRL_A	0x0b
+#define DA9034_SYS_CTRL_B	0x0c
+#define DA9034_FAULT_LOG	0x0d
+
+struct da903x_chip;
+
+struct da903x_chip_ops {
+	int	(*init_chip)(struct da903x_chip *);
+	int	(*unmask_events)(struct da903x_chip *, unsigned int events);
+	int	(*mask_events)(struct da903x_chip *, unsigned int events);
+	int	(*read_events)(struct da903x_chip *, unsigned int *events);
+	int	(*read_status)(struct da903x_chip *, unsigned int *status);
+};
+
+struct da903x_chip {
+	struct i2c_client	*client;
+	struct device		*dev;
+	struct da903x_chip_ops	*ops;
+
+	int			type;
+	uint32_t		events_mask;
+
+	struct mutex		lock;
+	struct work_struct	irq_work;
+
+	struct blocking_notifier_head notifier_list;
+};
+
+static inline int __da903x_read(struct i2c_client *client,
+				int reg, uint8_t *val)
+{
+	int ret;
+
+	ret = i2c_smbus_read_byte_data(client, reg);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed reading at 0x%02x\n", reg);
+		return ret;
+	}
+
+	*val = (uint8_t)ret;
+	return 0;
+}
+
+static inline int __da903x_reads(struct i2c_client *client, int reg,
+				 int len, uint8_t *val)
+{
+	int ret;
+
+	ret = i2c_smbus_read_i2c_block_data(client, reg, len, val);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed reading from 0x%02x\n", reg);
+		return ret;
+	}
+	return 0;
+}
+
+static inline int __da903x_write(struct i2c_client *client,
+				 int reg, uint8_t val)
+{
+	int ret;
+
+	ret = i2c_smbus_write_byte_data(client, reg, val);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed writing 0x%02x to 0x%02x\n",
+				val, reg);
+		return ret;
+	}
+	return 0;
+}
+
+static inline int __da903x_writes(struct i2c_client *client, int reg,
+				  int len, uint8_t *val)
+{
+	int ret;
+
+	ret = i2c_smbus_write_i2c_block_data(client, reg, len, val);
+	if (ret < 0) {
+		dev_err(&client->dev, "failed writings to 0x%02x\n", reg);
+		return ret;
+	}
+	return 0;
+}
+
+int da903x_register_notifier(struct device *dev, struct notifier_block *nb,
+				unsigned int events)
+{
+	struct da903x_chip *chip = dev_get_drvdata(dev);
+
+	chip->ops->unmask_events(chip, events);
+	return blocking_notifier_chain_register(&chip->notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(da903x_register_notifier);
+
+int da903x_unregister_notifier(struct device *dev, struct notifier_block *nb,
+				unsigned int events)
+{
+	struct da903x_chip *chip = dev_get_drvdata(dev);
+
+	chip->ops->mask_events(chip, events);
+	return blocking_notifier_chain_unregister(&chip->notifier_list, nb);
+}
+EXPORT_SYMBOL_GPL(da903x_unregister_notifier);
+
+int da903x_write(struct device *dev, int reg, uint8_t val)
+{
+	return __da903x_write(to_i2c_client(dev), reg, val);
+}
+EXPORT_SYMBOL_GPL(da903x_write);
+
+int da903x_read(struct device *dev, int reg, uint8_t *val)
+{
+	return __da903x_read(to_i2c_client(dev), reg, val);
+}
+EXPORT_SYMBOL_GPL(da903x_read);
+
+int da903x_set_bits(struct device *dev, int reg, uint8_t bit_mask)
+{
+	struct da903x_chip *chip = dev_get_drvdata(dev);
+	uint8_t reg_val;
+	int ret = 0;
+
+	mutex_lock(&chip->lock);
+
+	ret = __da903x_read(chip->client, reg, &reg_val);
+	if (ret)
+		goto out;
+
+	if ((reg_val & bit_mask) == 0) {
+		reg_val |= bit_mask;
+		ret = __da903x_write(chip->client, reg, reg_val);
+	}
+out:
+	mutex_unlock(&chip->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(da903x_set_bits);
+
+int da903x_clr_bits(struct device *dev, int reg, uint8_t bit_mask)
+{
+	struct da903x_chip *chip = dev_get_drvdata(dev);
+	uint8_t reg_val;
+	int ret = 0;
+
+	mutex_lock(&chip->lock);
+
+	ret = __da903x_read(chip->client, reg, &reg_val);
+	if (ret)
+		goto out;
+
+	if (reg_val & bit_mask) {
+		reg_val &= ~bit_mask;
+		ret = __da903x_write(chip->client, reg, reg_val);
+	}
+out:
+	mutex_unlock(&chip->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(da903x_clr_bits);
+
+int da903x_update(struct device *dev, int reg, uint8_t val, uint8_t mask)
+{
+	struct da903x_chip *chip = dev_get_drvdata(dev);
+	uint8_t reg_val;
+	int ret = 0;
+
+	mutex_lock(&chip->lock);
+
+	ret = __da903x_read(chip->client, reg, &reg_val);
+	if (ret)
+		goto out;
+
+	if ((reg_val & mask) != val) {
+		reg_val = (reg_val & ~mask) | val;
+		ret = __da903x_write(chip->client, reg, reg_val);
+	}
+out:
+	mutex_unlock(&chip->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(da903x_update);
+
+int da903x_query_status(struct device *dev, unsigned int sbits)
+{
+	struct da903x_chip *chip = dev_get_drvdata(dev);
+	unsigned int status = 0;
+
+	chip->ops->read_status(chip, &status);
+	return ((status & sbits) == sbits);
+}
+EXPORT_SYMBOL(da903x_query_status);
+
+static int __devinit da9030_init_chip(struct da903x_chip *chip)
+{
+	uint8_t chip_id;
+	int err;
+
+	err = __da903x_read(chip->client, DA9030_CHIP_ID, &chip_id);
+	if (err)
+		return err;
+
+	err = __da903x_write(chip->client, DA9030_SYS_CTRL_A, 0xE8);
+	if (err)
+		return err;
+
+	dev_info(chip->dev, "DA9030 (CHIP ID: 0x%02x) detected\n", chip_id);
+	return 0;
+}
+
+static int da9030_unmask_events(struct da903x_chip *chip, unsigned int events)
+{
+	uint8_t v[3];
+
+	chip->events_mask &= ~events;
+
+	v[0] = (chip->events_mask & 0xff);
+	v[1] = (chip->events_mask >> 8) & 0xff;
+	v[2] = (chip->events_mask >> 16) & 0xff;
+
+	return __da903x_writes(chip->client, DA9030_IRQ_MASK_A, 3, v);
+}
+
+static int da9030_mask_events(struct da903x_chip *chip, unsigned int events)
+{
+	uint8_t v[3];
+
+	chip->events_mask &= ~events;
+
+	v[0] = (chip->events_mask & 0xff);
+	v[1] = (chip->events_mask >> 8) & 0xff;
+	v[2] = (chip->events_mask >> 16) & 0xff;
+
+	return __da903x_writes(chip->client, DA9030_IRQ_MASK_A, 3, v);
+}
+
+static int da9030_read_events(struct da903x_chip *chip, unsigned int *events)
+{
+	uint8_t v[3] = {0, 0, 0};
+	int ret;
+
+	ret = __da903x_reads(chip->client, DA9030_EVENT_A, 3, v);
+	if (ret < 0)
+		return ret;
+
+	*events = (v[2] << 16) | (v[1] << 8) | v[0];
+	return 0;
+}
+
+static int da9030_read_status(struct da903x_chip *chip, unsigned int *status)
+{
+	return __da903x_read(chip->client, DA9030_STATUS, (uint8_t *)status);
+}
+
+static int da9034_init_chip(struct da903x_chip *chip)
+{
+	uint8_t chip_id;
+	int err;
+
+	err = __da903x_read(chip->client, DA9034_CHIP_ID, &chip_id);
+	if (err)
+		return err;
+
+	err = __da903x_write(chip->client, DA9034_SYS_CTRL_A, 0xE8);
+	if (err)
+		return err;
+
+	/* avoid SRAM power off during sleep*/
+	__da903x_write(chip->client, 0x10, 0x07);
+	__da903x_write(chip->client, 0x11, 0xff);
+	__da903x_write(chip->client, 0x12, 0xff);
+
+	/* Enable the ONKEY power down functionality */
+	__da903x_write(chip->client, DA9034_SYS_CTRL_B, 0x20);
+	__da903x_write(chip->client, DA9034_SYS_CTRL_A, 0x60);
+
+	/* workaround to make LEDs work */
+	__da903x_write(chip->client, 0x90, 0x01);
+	__da903x_write(chip->client, 0xB0, 0x08);
+
+	/* make ADTV1 and SDTV1 effective */
+	__da903x_write(chip->client, 0x20, 0x00);
+
+	dev_info(chip->dev, "DA9034 (CHIP ID: 0x%02x) detected\n", chip_id);
+	return 0;
+}
+
+static int da9034_unmask_events(struct da903x_chip *chip, unsigned int events)
+{
+	uint8_t v[4];
+
+	chip->events_mask &= ~events;
+
+	v[0] = (chip->events_mask & 0xff);
+	v[1] = (chip->events_mask >> 8) & 0xff;
+	v[2] = (chip->events_mask >> 16) & 0xff;
+	v[3] = (chip->events_mask >> 24) & 0xff;
+
+	return __da903x_writes(chip->client, DA9034_IRQ_MASK_A, 4, v);
+}
+
+static int da9034_mask_events(struct da903x_chip *chip, unsigned int events)
+{
+	uint8_t v[4];
+
+	chip->events_mask |= events;
+
+	v[0] = (chip->events_mask & 0xff);
+	v[1] = (chip->events_mask >> 8) & 0xff;
+	v[2] = (chip->events_mask >> 16) & 0xff;
+	v[3] = (chip->events_mask >> 24) & 0xff;
+
+	return __da903x_writes(chip->client, DA9034_IRQ_MASK_A, 4, v);
+}
+
+static int da9034_read_events(struct da903x_chip *chip, unsigned int *events)
+{
+	uint8_t v[4] = {0, 0, 0, 0};
+	int ret;
+
+	ret = __da903x_reads(chip->client, DA9034_EVENT_A, 4, v);
+	if (ret < 0)
+		return ret;
+
+	*events = (v[3] << 24) | (v[2] << 16) | (v[1] << 8) | v[0];
+	return 0;
+}
+
+static int da9034_read_status(struct da903x_chip *chip, unsigned int *status)
+{
+	uint8_t v[2] = {0, 0};
+	int ret = 0;
+
+	ret = __da903x_reads(chip->client, DA9034_STATUS_A, 2, v);
+	if (ret)
+		return ret;
+
+	*status = (v[1] << 8) | v[0];
+	return 0;
+}
+
+static void da903x_irq_work(struct work_struct *work)
+{
+	struct da903x_chip *chip =
+		container_of(work, struct da903x_chip, irq_work);
+	unsigned int events = 0;
+
+	while (1) {
+		if (chip->ops->read_events(chip, &events))
+			break;
+
+		events &= ~chip->events_mask;
+		if (events == 0)
+			break;
+
+		blocking_notifier_call_chain(
+				&chip->notifier_list, events, NULL);
+	}
+	enable_irq(chip->client->irq);
+}
+
+static int da903x_irq_handler(int irq, void *data)
+{
+	struct da903x_chip *chip = data;
+
+	disable_irq_nosync(irq);
+	(void)schedule_work(&chip->irq_work);
+
+	return IRQ_HANDLED;
+}
+
+static struct da903x_chip_ops da903x_ops[] = {
+	[0] = {
+		.init_chip	= da9030_init_chip,
+		.unmask_events	= da9030_unmask_events,
+		.mask_events	= da9030_mask_events,
+		.read_events	= da9030_read_events,
+		.read_status	= da9030_read_status,
+	},
+	[1] = {
+		.init_chip	= da9034_init_chip,
+		.unmask_events	= da9034_unmask_events,
+		.mask_events	= da9034_mask_events,
+		.read_events	= da9034_read_events,
+		.read_status	= da9034_read_status,
+	}
+};
+
+static const struct i2c_device_id da903x_id_table[] = {
+	{ "da9030", 0 },
+	{ "da9034", 1 },
+	{ },
+};
+MODULE_DEVICE_TABLE(i2c, da903x_id_table);
+
+static int __devexit __remove_subdev(struct device *dev, void *unused)
+{
+	platform_device_unregister(to_platform_device(dev));
+	return 0;
+}
+
+static int __devexit da903x_remove_subdevs(struct da903x_chip *chip)
+{
+	return device_for_each_child(chip->dev, NULL, __remove_subdev);
+}
+
+static int __devinit da903x_add_subdevs(struct da903x_chip *chip,
+					struct da903x_platform_data *pdata)
+{
+	struct da903x_subdev_info *subdev;
+	struct platform_device *pdev;
+	int i, ret = 0;
+
+	for (i = 0; i < pdata->num_subdevs; i++) {
+		subdev = &pdata->subdevs[i];
+
+		pdev = platform_device_alloc(subdev->name, subdev->id);
+
+		pdev->dev.parent = chip->dev;
+		pdev->dev.platform_data = subdev->platform_data;
+
+		ret = platform_device_add(pdev);
+		if (ret)
+			goto failed;
+	}
+	return 0;
+
+failed:
+	da903x_remove_subdevs(chip);
+	return ret;
+}
+
+static int __devinit da903x_probe(struct i2c_client *client,
+				  const struct i2c_device_id *id)
+{
+	struct da903x_platform_data *pdata = client->dev.platform_data;
+	struct da903x_chip *chip;
+	unsigned int tmp;
+	int ret;
+
+	chip = kzalloc(sizeof(struct da903x_chip), GFP_KERNEL);
+	if (chip == NULL)
+		return -ENOMEM;
+
+	chip->client = client;
+	chip->dev = &client->dev;
+	chip->ops = &da903x_ops[id->driver_data];
+
+	mutex_init(&chip->lock);
+	INIT_WORK(&chip->irq_work, da903x_irq_work);
+	BLOCKING_INIT_NOTIFIER_HEAD(&chip->notifier_list);
+
+	i2c_set_clientdata(client, chip);
+
+	ret = chip->ops->init_chip(chip);
+	if (ret)
+		goto out_free_chip;
+
+	/* mask and clear all IRQs */
+	chip->events_mask = 0xffffffff;
+	chip->ops->mask_events(chip, chip->events_mask);
+	chip->ops->read_events(chip, &tmp);
+
+	ret = request_irq(client->irq, da903x_irq_handler,
+			IRQF_DISABLED | IRQF_TRIGGER_FALLING,
+			"da903x", chip);
+	if (ret) {
+		dev_err(&client->dev, "failed to request irq %d\n",
+				client->irq);
+		goto out_free_chip;
+	}
+
+	ret = da903x_add_subdevs(chip, pdata);
+	if (ret)
+		goto out_free_irq;
+
+	return 0;
+
+out_free_irq:
+	free_irq(client->irq, chip);
+out_free_chip:
+	i2c_set_clientdata(client, NULL);
+	kfree(chip);
+	return ret;
+}
+
+static int __devexit da903x_remove(struct i2c_client *client)
+{
+	struct da903x_chip *chip = i2c_get_clientdata(client);
+
+	da903x_remove_subdevs(chip);
+	kfree(chip);
+	return 0;
+}
+
+static struct i2c_driver da903x_driver = {
+	.driver	= {
+		.name	= "da903x",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= da903x_probe,
+	.remove		= __devexit_p(da903x_remove),
+	.id_table	= da903x_id_table,
+};
+
+static int __init da903x_init(void)
+{
+	return i2c_add_driver(&da903x_driver);
+}
+module_init(da903x_init);
+
+static void __exit da903x_exit(void)
+{
+	i2c_del_driver(&da903x_driver);
+}
+module_exit(da903x_exit);
+
+MODULE_DESCRIPTION("PMIC Driver for Dialog Semiconductor DA9034");
+MODULE_AUTHOR("Eric Miao <eric.miao@marvell.com>"
+	      "Mike Rapoport <mike@compulab.co.il>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/mfd/da903x.h b/include/linux/mfd/da903x.h
new file mode 100644
index 000000000000..cad314c12439
--- /dev/null
+++ b/include/linux/mfd/da903x.h
@@ -0,0 +1,201 @@
+#ifndef __LINUX_PMIC_DA903X_H
+#define __LINUX_PMIC_DA903X_H
+
+/* Unified sub device IDs for DA9030/DA9034 */
+enum {
+	DA9030_ID_LED_1,
+	DA9030_ID_LED_2,
+	DA9030_ID_LED_3,
+	DA9030_ID_LED_4,
+	DA9030_ID_LED_PC,
+	DA9030_ID_VIBRA,
+	DA9030_ID_WLED,
+	DA9030_ID_BUCK1,
+	DA9030_ID_BUCK2,
+	DA9030_ID_LDO1,
+	DA9030_ID_LDO2,
+	DA9030_ID_LDO3,
+	DA9030_ID_LDO4,
+	DA9030_ID_LDO5,
+	DA9030_ID_LDO6,
+	DA9030_ID_LDO7,
+	DA9030_ID_LDO8,
+	DA9030_ID_LDO9,
+	DA9030_ID_LDO10,
+	DA9030_ID_LDO11,
+	DA9030_ID_LDO12,
+	DA9030_ID_LDO13,
+	DA9030_ID_LDO14,
+	DA9030_ID_LDO15,
+	DA9030_ID_LDO16,
+	DA9030_ID_LDO17,
+	DA9030_ID_LDO18,
+	DA9030_ID_LDO19,
+	DA9030_ID_LDO_INT,	/* LDO Internal */
+
+	DA9034_ID_LED_1,
+	DA9034_ID_LED_2,
+	DA9034_ID_VIBRA,
+	DA9034_ID_WLED,
+	DA9034_ID_TOUCH,
+
+	DA9034_ID_BUCK1,
+	DA9034_ID_BUCK2,
+	DA9034_ID_LDO1,
+	DA9034_ID_LDO2,
+	DA9034_ID_LDO3,
+	DA9034_ID_LDO4,
+	DA9034_ID_LDO5,
+	DA9034_ID_LDO6,
+	DA9034_ID_LDO7,
+	DA9034_ID_LDO8,
+	DA9034_ID_LDO9,
+	DA9034_ID_LDO10,
+	DA9034_ID_LDO11,
+	DA9034_ID_LDO12,
+	DA9034_ID_LDO13,
+	DA9034_ID_LDO14,
+	DA9034_ID_LDO15,
+};
+
+/*
+ * DA9030/DA9034 LEDs sub-devices uses generic "struct led_info"
+ * as the platform_data
+ */
+
+/* DA9030 flags for "struct led_info"
+ */
+#define DA9030_LED_RATE_ON	(0 << 5)
+#define DA9030_LED_RATE_052S	(1 << 5)
+#define DA9030_LED_DUTY_1_16	(0 << 3)
+#define DA9030_LED_DUTY_1_8	(1 << 3)
+#define DA9030_LED_DUTY_1_4	(2 << 3)
+#define DA9030_LED_DUTY_1_2	(3 << 3)
+
+#define DA9030_VIBRA_MODE_1P3V	(0 << 1)
+#define DA9030_VIBRA_MODE_2P7V	(1 << 1)
+#define DA9030_VIBRA_FREQ_1HZ	(0 << 2)
+#define DA9030_VIBRA_FREQ_2HZ	(1 << 2)
+#define DA9030_VIBRA_FREQ_4HZ	(2 << 2)
+#define DA9030_VIBRA_FREQ_8HZ	(3 << 2)
+#define DA9030_VIBRA_DUTY_ON	(0 << 4)
+#define DA9030_VIBRA_DUTY_75P	(1 << 4)
+#define DA9030_VIBRA_DUTY_50P	(2 << 4)
+#define DA9030_VIBRA_DUTY_25P	(3 << 4)
+
+/* DA9034 flags for "struct led_info" */
+#define DA9034_LED_RAMP		(1 << 7)
+
+/* DA9034 touch screen platform data */
+struct da9034_touch_pdata {
+	int	interval_ms;	/* sampling interval while pen down */
+	int	x_inverted;
+	int	y_inverted;
+};
+
+struct da903x_subdev_info {
+	int		id;
+	const char	*name;
+	void		*platform_data;
+};
+
+struct da903x_platform_data {
+	int num_subdevs;
+	struct da903x_subdev_info *subdevs;
+};
+
+/* bit definitions for DA9030 events */
+#define DA9030_EVENT_ONKEY		(1 << 0)
+#define	DA9030_EVENT_PWREN		(1 << 1)
+#define	DA9030_EVENT_EXTON		(1 << 2)
+#define	DA9030_EVENT_CHDET		(1 << 3)
+#define	DA9030_EVENT_TBAT		(1 << 4)
+#define	DA9030_EVENT_VBATMON		(1 << 5)
+#define	DA9030_EVENT_VBATMON_TXON	(1 << 6)
+#define	DA9030_EVENT_CHIOVER		(1 << 7)
+#define	DA9030_EVENT_TCTO		(1 << 8)
+#define	DA9030_EVENT_CCTO		(1 << 9)
+#define	DA9030_EVENT_ADC_READY		(1 << 10)
+#define	DA9030_EVENT_VBUS_4P4		(1 << 11)
+#define	DA9030_EVENT_VBUS_4P0		(1 << 12)
+#define	DA9030_EVENT_SESS_VALID		(1 << 13)
+#define	DA9030_EVENT_SRP_DETECT		(1 << 14)
+#define	DA9030_EVENT_WATCHDOG		(1 << 15)
+#define	DA9030_EVENT_LDO15		(1 << 16)
+#define	DA9030_EVENT_LDO16		(1 << 17)
+#define	DA9030_EVENT_LDO17		(1 << 18)
+#define	DA9030_EVENT_LDO18		(1 << 19)
+#define	DA9030_EVENT_LDO19		(1 << 20)
+#define	DA9030_EVENT_BUCK2		(1 << 21)
+
+/* bit definitions for DA9034 events */
+#define DA9034_EVENT_ONKEY		(1 << 0)
+#define DA9034_EVENT_EXTON		(1 << 2)
+#define DA9034_EVENT_CHDET		(1 << 3)
+#define DA9034_EVENT_TBAT		(1 << 4)
+#define DA9034_EVENT_VBATMON		(1 << 5)
+#define DA9034_EVENT_REV_IOVER		(1 << 6)
+#define DA9034_EVENT_CH_IOVER		(1 << 7)
+#define DA9034_EVENT_CH_TCTO		(1 << 8)
+#define DA9034_EVENT_CH_CCTO		(1 << 9)
+#define DA9034_EVENT_USB_DEV		(1 << 10)
+#define DA9034_EVENT_OTGCP_IOVER	(1 << 11)
+#define DA9034_EVENT_VBUS_4P55		(1 << 12)
+#define DA9034_EVENT_VBUS_3P8		(1 << 13)
+#define DA9034_EVENT_SESS_1P8		(1 << 14)
+#define DA9034_EVENT_SRP_READY		(1 << 15)
+#define DA9034_EVENT_ADC_MAN		(1 << 16)
+#define DA9034_EVENT_ADC_AUTO4		(1 << 17)
+#define DA9034_EVENT_ADC_AUTO5		(1 << 18)
+#define DA9034_EVENT_ADC_AUTO6		(1 << 19)
+#define DA9034_EVENT_PEN_DOWN		(1 << 20)
+#define DA9034_EVENT_TSI_READY		(1 << 21)
+#define DA9034_EVENT_UART_TX		(1 << 22)
+#define DA9034_EVENT_UART_RX		(1 << 23)
+#define DA9034_EVENT_HEADSET		(1 << 25)
+#define DA9034_EVENT_HOOKSWITCH		(1 << 26)
+#define DA9034_EVENT_WATCHDOG		(1 << 27)
+
+extern int da903x_register_notifier(struct device *dev,
+		struct notifier_block *nb, unsigned int events);
+extern int da903x_unregister_notifier(struct device *dev,
+		struct notifier_block *nb, unsigned int events);
+
+/* Status Query Interface */
+#define DA9030_STATUS_ONKEY		(1 << 0)
+#define DA9030_STATUS_PWREN1		(1 << 1)
+#define DA9030_STATUS_EXTON		(1 << 2)
+#define DA9030_STATUS_CHDET		(1 << 3)
+#define DA9030_STATUS_TBAT		(1 << 4)
+#define DA9030_STATUS_VBATMON		(1 << 5)
+#define DA9030_STATUS_VBATMON_TXON	(1 << 6)
+#define DA9030_STATUS_MCLKDET		(1 << 7)
+
+#define DA9034_STATUS_ONKEY		(1 << 0)
+#define DA9034_STATUS_EXTON		(1 << 2)
+#define DA9034_STATUS_CHDET		(1 << 3)
+#define DA9034_STATUS_TBAT		(1 << 4)
+#define DA9034_STATUS_VBATMON		(1 << 5)
+#define DA9034_STATUS_PEN_DOWN		(1 << 6)
+#define DA9034_STATUS_MCLKDET		(1 << 7)
+#define DA9034_STATUS_USB_DEV		(1 << 8)
+#define DA9034_STATUS_HEADSET		(1 << 9)
+#define DA9034_STATUS_HOOKSWITCH	(1 << 10)
+#define DA9034_STATUS_REMCON		(1 << 11)
+#define DA9034_STATUS_VBUS_VALID_4P55	(1 << 12)
+#define DA9034_STATUS_VBUS_VALID_3P8	(1 << 13)
+#define DA9034_STATUS_SESS_VALID_1P8	(1 << 14)
+#define DA9034_STATUS_SRP_READY		(1 << 15)
+
+extern int da903x_query_status(struct device *dev, unsigned int status);
+
+
+/* NOTE: the two functions below are not intended for use outside
+ * of the DA9034 sub-device drivers
+ */
+extern int da903x_write(struct device *dev, int reg, uint8_t val);
+extern int da903x_read(struct device *dev, int reg, uint8_t *val);
+extern int da903x_update(struct device *dev, int reg, uint8_t val, uint8_t mask);
+extern int da903x_set_bits(struct device *dev, int reg, uint8_t bit_mask);
+extern int da903x_clr_bits(struct device *dev, int reg, uint8_t bit_mask);
+#endif /* __LINUX_PMIC_DA903X_H */
-- 
cgit v1.2.3


From 7acb706ca97fce84bda4a902a33de2f3dae10260 Mon Sep 17 00:00:00 2001
From: Ian Molton <spyro@f2s.com>
Date: Thu, 9 Oct 2008 20:06:09 +0200
Subject: mfd: update TMIO drivers to use the clock API

This patch updates the remaining two TMIO drivers to use the clock API
rather than callback hooks into platform code.

Signed-off-by: Ian Molton <spyro@f2s.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/t7l66xb.c        | 40 +++++++++++++++++++++++++++++--------
 drivers/mfd/tc6387xb.c       | 47 +++++++++++++++++++++++++++-----------------
 include/linux/mfd/t7l66xb.h  |  2 --
 include/linux/mfd/tc6387xb.h |  3 ---
 4 files changed, 61 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/drivers/mfd/t7l66xb.c b/drivers/mfd/t7l66xb.c
index 49a0fffc02af..9f7024c0f8ec 100644
--- a/drivers/mfd/t7l66xb.c
+++ b/drivers/mfd/t7l66xb.c
@@ -24,8 +24,10 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/err.h>
 #include <linux/io.h>
 #include <linux/irq.h>
+#include <linux/clk.h>
 #include <linux/platform_device.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/tmio.h>
@@ -56,6 +58,8 @@ struct t7l66xb {
 	spinlock_t		lock;
 
 	struct resource		rscr;
+	struct clk		*clk48m;
+	struct clk		*clk32k;
 	int			irq;
 	int			irq_base;
 };
@@ -65,13 +69,11 @@ struct t7l66xb {
 static int t7l66xb_mmc_enable(struct platform_device *mmc)
 {
 	struct platform_device *dev = to_platform_device(mmc->dev.parent);
-	struct t7l66xb_platform_data   *pdata = dev->dev.platform_data;
 	struct t7l66xb *t7l66xb = platform_get_drvdata(dev);
 	unsigned long flags;
 	u8 dev_ctl;
 
-	if (pdata->enable_clk32k)
-		pdata->enable_clk32k(dev);
+	clk_enable(t7l66xb->clk32k);
 
 	spin_lock_irqsave(&t7l66xb->lock, flags);
 
@@ -87,7 +89,6 @@ static int t7l66xb_mmc_enable(struct platform_device *mmc)
 static int t7l66xb_mmc_disable(struct platform_device *mmc)
 {
 	struct platform_device *dev = to_platform_device(mmc->dev.parent);
-	struct t7l66xb_platform_data   *pdata = dev->dev.platform_data;
 	struct t7l66xb *t7l66xb = platform_get_drvdata(dev);
 	unsigned long flags;
 	u8 dev_ctl;
@@ -100,8 +101,7 @@ static int t7l66xb_mmc_disable(struct platform_device *mmc)
 
 	spin_unlock_irqrestore(&t7l66xb->lock, flags);
 
-	if (pdata->disable_clk32k)
-		pdata->disable_clk32k(dev);
+	clk_disable(t7l66xb->clk32k);
 
 	return 0;
 }
@@ -258,18 +258,22 @@ static void t7l66xb_detach_irq(struct platform_device *dev)
 #ifdef CONFIG_PM
 static int t7l66xb_suspend(struct platform_device *dev, pm_message_t state)
 {
+	struct t7l66xb *t7l66xb = platform_get_drvdata(dev);
 	struct t7l66xb_platform_data *pdata = dev->dev.platform_data;
 
 	if (pdata && pdata->suspend)
 		pdata->suspend(dev);
+	clk_disable(t7l66xb->clk48m);
 
 	return 0;
 }
 
 static int t7l66xb_resume(struct platform_device *dev)
 {
+	struct t7l66xb *t7l66xb = platform_get_drvdata(dev);
 	struct t7l66xb_platform_data *pdata = dev->dev.platform_data;
 
+	clk_enable(t7l66xb->clk48m);
 	if (pdata && pdata->resume)
 		pdata->resume(dev);
 
@@ -309,6 +313,19 @@ static int t7l66xb_probe(struct platform_device *dev)
 
 	t7l66xb->irq_base = pdata->irq_base;
 
+	t7l66xb->clk32k = clk_get(&dev->dev, "CLK_CK32K");
+	if (IS_ERR(t7l66xb->clk32k)) {
+		ret = PTR_ERR(t7l66xb->clk32k);
+		goto err_clk32k_get;
+	}
+
+	t7l66xb->clk48m = clk_get(&dev->dev, "CLK_CK48M");
+	if (IS_ERR(t7l66xb->clk48m)) {
+		ret = PTR_ERR(t7l66xb->clk48m);
+		clk_put(t7l66xb->clk32k);
+		goto err_clk48m_get;
+	}
+
 	rscr = &t7l66xb->rscr;
 	rscr->name = "t7l66xb-core";
 	rscr->start = iomem->start;
@@ -325,6 +342,8 @@ static int t7l66xb_probe(struct platform_device *dev)
 		goto err_ioremap;
 	}
 
+	clk_enable(t7l66xb->clk48m);
+
 	if (pdata && pdata->enable)
 		pdata->enable(dev);
 
@@ -359,9 +378,13 @@ static int t7l66xb_probe(struct platform_device *dev)
 	iounmap(t7l66xb->scr);
 err_ioremap:
 	release_resource(&t7l66xb->rscr);
-err_noirq:
 err_request_scr:
 	kfree(t7l66xb);
+	clk_put(t7l66xb->clk48m);
+err_clk48m_get:
+	clk_put(t7l66xb->clk32k);
+err_clk32k_get:
+err_noirq:
 	return ret;
 }
 
@@ -372,7 +395,8 @@ static int t7l66xb_remove(struct platform_device *dev)
 	int ret;
 
 	ret = pdata->disable(dev);
-
+	clk_disable(t7l66xb->clk48m);
+	clk_put(t7l66xb->clk48m);
 	t7l66xb_detach_irq(dev);
 	iounmap(t7l66xb->scr);
 	release_resource(&t7l66xb->rscr);
diff --git a/drivers/mfd/tc6387xb.c b/drivers/mfd/tc6387xb.c
index a22b21ac6cf8..43222c12fec1 100644
--- a/drivers/mfd/tc6387xb.c
+++ b/drivers/mfd/tc6387xb.c
@@ -12,6 +12,7 @@
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/mfd/core.h>
 #include <linux/mfd/tmio.h>
@@ -24,18 +25,22 @@ enum {
 #ifdef CONFIG_PM
 static int tc6387xb_suspend(struct platform_device *dev, pm_message_t state)
 {
-	struct tc6387xb_platform_data *pdata = platform_get_drvdata(dev);
+	struct clk *clk32k = platform_get_drvdata(dev);
+	struct tc6387xb_platform_data *pdata = dev->dev.platform_data;
 
 	if (pdata && pdata->suspend)
 		pdata->suspend(dev);
+	clk_disable(clk32k);
 
 	return 0;
 }
 
 static int tc6387xb_resume(struct platform_device *dev)
 {
-	struct tc6387xb_platform_data *pdata = platform_get_drvdata(dev);
+	struct clk *clk32k = platform_get_drvdata(dev);
+	struct tc6387xb_platform_data *pdata = dev->dev.platform_data;
 
+	clk_enable(clk32k);
 	if (pdata && pdata->resume)
 		pdata->resume(dev);
 
@@ -51,10 +56,9 @@ static int tc6387xb_resume(struct platform_device *dev)
 static int tc6387xb_mmc_enable(struct platform_device *mmc)
 {
 	struct platform_device *dev      = to_platform_device(mmc->dev.parent);
-	struct tc6387xb_platform_data *tc6387xb = dev->dev.platform_data;
+	struct clk *clk32k = platform_get_drvdata(dev);
 
-	if (tc6387xb->enable_clk32k)
-		tc6387xb->enable_clk32k(dev);
+	clk_enable(clk32k);
 
 	return 0;
 }
@@ -62,10 +66,9 @@ static int tc6387xb_mmc_enable(struct platform_device *mmc)
 static int tc6387xb_mmc_disable(struct platform_device *mmc)
 {
 	struct platform_device *dev      = to_platform_device(mmc->dev.parent);
-	struct tc6387xb_platform_data *tc6387xb = dev->dev.platform_data;
+	struct clk *clk32k = platform_get_drvdata(dev);
 
-	if (tc6387xb->disable_clk32k)
-		tc6387xb->disable_clk32k(dev);
+	clk_disable(clk32k);
 
 	return 0;
 }
@@ -102,14 +105,14 @@ static struct mfd_cell tc6387xb_cells[] = {
 
 static int tc6387xb_probe(struct platform_device *dev)
 {
-	struct tc6387xb_platform_data *data = platform_get_drvdata(dev);
+	struct tc6387xb_platform_data *pdata = dev->dev.platform_data;
 	struct resource *iomem;
+	struct clk *clk32k;
 	int irq, ret;
 
 	iomem = platform_get_resource(dev, IORESOURCE_MEM, 0);
 	if (!iomem) {
-		ret = -EINVAL;
-		goto err_resource;
+		return -EINVAL;
 	}
 
 	ret  = platform_get_irq(dev, 0);
@@ -118,8 +121,15 @@ static int tc6387xb_probe(struct platform_device *dev)
 	else
 		goto err_resource;
 
-	if (data && data->enable)
-		data->enable(dev);
+	clk32k = clk_get(&dev->dev, "CLK_CK32K");
+	if (IS_ERR(clk32k)) {
+		ret = PTR_ERR(clk32k);
+		goto err_resource;
+	}
+	platform_set_drvdata(dev, clk32k);
+
+	if (pdata && pdata->enable)
+		pdata->enable(dev);
 
 	printk(KERN_INFO "Toshiba tc6387xb initialised\n");
 
@@ -134,18 +144,19 @@ static int tc6387xb_probe(struct platform_device *dev)
 	if (!ret)
 		return 0;
 
+	clk_put(clk32k);
 err_resource:
 	return ret;
 }
 
 static int tc6387xb_remove(struct platform_device *dev)
 {
-	struct tc6387xb_platform_data *data = platform_get_drvdata(dev);
-
-	if (data && data->disable)
-		data->disable(dev);
+	struct clk *clk32k = platform_get_drvdata(dev);
 
-	/* FIXME - free the resources! */
+	mfd_remove_devices(&dev->dev);
+	clk_disable(clk32k);
+	clk_put(clk32k);
+	platform_set_drvdata(dev, NULL);
 
 	return 0;
 }
diff --git a/include/linux/mfd/t7l66xb.h b/include/linux/mfd/t7l66xb.h
index e83c7f2036f9..b4629818aea5 100644
--- a/include/linux/mfd/t7l66xb.h
+++ b/include/linux/mfd/t7l66xb.h
@@ -15,8 +15,6 @@
 #include <linux/mfd/tmio.h>
 
 struct t7l66xb_platform_data {
-	int (*enable_clk32k)(struct platform_device *dev);
-	void (*disable_clk32k)(struct platform_device *dev);
 	int (*enable)(struct platform_device *dev);
 	int (*disable)(struct platform_device *dev);
 	int (*suspend)(struct platform_device *dev);
diff --git a/include/linux/mfd/tc6387xb.h b/include/linux/mfd/tc6387xb.h
index fa06e0610b8e..b4888209494a 100644
--- a/include/linux/mfd/tc6387xb.h
+++ b/include/linux/mfd/tc6387xb.h
@@ -11,9 +11,6 @@
 #define MFD_TC6387XB_H
 
 struct tc6387xb_platform_data {
-	int (*enable_clk32k)(struct platform_device *dev);
-	void (*disable_clk32k)(struct platform_device *dev);
-
 	int (*enable)(struct platform_device *dev);
 	int (*disable)(struct platform_device *dev);
 	int (*suspend)(struct platform_device *dev);
-- 
cgit v1.2.3


From 7994b1c55ec19238067a47f09b0463db3a48c33c Mon Sep 17 00:00:00 2001
From: Magnus Damm <damm@igel.co.jp>
Date: Thu, 9 Oct 2008 18:47:27 +0900
Subject: video: remove unused sh_mobile_lcdc platform data

Remove lddckr from the platform data, these days we calculate the
register value from clock source and clock dividers anyway.

Signed-off-by: Magnus Damm <damm@igel.co.jp>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
---
 drivers/video/sh_mobile_lcdcfb.c | 1 -
 include/video/sh_mobile_lcdc.h   | 1 -
 2 files changed, 2 deletions(-)

(limited to 'include')

diff --git a/drivers/video/sh_mobile_lcdcfb.c b/drivers/video/sh_mobile_lcdcfb.c
index b7468bacce80..399a8a75ab0b 100644
--- a/drivers/video/sh_mobile_lcdcfb.c
+++ b/drivers/video/sh_mobile_lcdcfb.c
@@ -589,7 +589,6 @@ static int __init sh_mobile_lcdc_probe(struct platform_device *pdev)
 		goto err1;
 	}
 
-	priv->lddckr = pdata->lddckr;
 	priv->base = ioremap_nocache(res->start, (res->end - res->start) + 1);
 
 	for (i = 0; i < j; i++) {
diff --git a/include/video/sh_mobile_lcdc.h b/include/video/sh_mobile_lcdc.h
index 130102f663f5..bfb42dbc5cc8 100644
--- a/include/video/sh_mobile_lcdc.h
+++ b/include/video/sh_mobile_lcdc.h
@@ -64,7 +64,6 @@ struct sh_mobile_lcdc_chan_cfg {
 };
 
 struct sh_mobile_lcdc_info {
-	unsigned long lddckr;
 	int clock_source;
 	struct sh_mobile_lcdc_chan_cfg ch[2];
 };
-- 
cgit v1.2.3


From f400f510df4e29bd00ffe07981ec703070cb9e19 Mon Sep 17 00:00:00 2001
From: Magnus Damm <damm@igel.co.jp>
Date: Thu, 9 Oct 2008 18:48:16 +0900
Subject: video: add sh_mobile_lcdc platform flags

Add platform data flags for detailed lcd display configuration.

Signed-off-by: Magnus Damm <damm@igel.co.jp>
Signed-off-by: Paul Mundt <lethal@linux-sh.org>
---
 drivers/video/sh_mobile_lcdcfb.c | 5 +++++
 include/video/sh_mobile_lcdc.h   | 7 +++++++
 2 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/drivers/video/sh_mobile_lcdcfb.c b/drivers/video/sh_mobile_lcdcfb.c
index 399a8a75ab0b..efff672fd7b8 100644
--- a/drivers/video/sh_mobile_lcdcfb.c
+++ b/drivers/video/sh_mobile_lcdcfb.c
@@ -262,6 +262,11 @@ static int sh_mobile_lcdc_start(struct sh_mobile_lcdc_priv *priv)
 		tmp = ch->ldmt1r_value;
 		tmp |= (lcd_cfg->sync & FB_SYNC_VERT_HIGH_ACT) ? 0 : 1 << 28;
 		tmp |= (lcd_cfg->sync & FB_SYNC_HOR_HIGH_ACT) ? 0 : 1 << 27;
+		tmp |= (ch->cfg.flags & LCDC_FLAGS_DWPOL) ? 1 << 26 : 0;
+		tmp |= (ch->cfg.flags & LCDC_FLAGS_DIPOL) ? 1 << 25 : 0;
+		tmp |= (ch->cfg.flags & LCDC_FLAGS_DAPOL) ? 1 << 24 : 0;
+		tmp |= (ch->cfg.flags & LCDC_FLAGS_HSCNT) ? 1 << 17 : 0;
+		tmp |= (ch->cfg.flags & LCDC_FLAGS_DWCNT) ? 1 << 16 : 0;
 		lcdc_write_chan(ch, LDMT1R, tmp);
 
 		/* setup SYS bus */
diff --git a/include/video/sh_mobile_lcdc.h b/include/video/sh_mobile_lcdc.h
index bfb42dbc5cc8..1a4bc6ada606 100644
--- a/include/video/sh_mobile_lcdc.h
+++ b/include/video/sh_mobile_lcdc.h
@@ -28,6 +28,12 @@ enum { LCDC_CHAN_DISABLED = 0,
 
 enum { LCDC_CLK_BUS, LCDC_CLK_PERIPHERAL, LCDC_CLK_EXTERNAL };
 
+#define LCDC_FLAGS_DWPOL (1 << 0) /* Rising edge dot clock data latch */
+#define LCDC_FLAGS_DIPOL (1 << 1) /* Active low display enable polarity */
+#define LCDC_FLAGS_DAPOL (1 << 2) /* Active low display data polarity */
+#define LCDC_FLAGS_HSCNT (1 << 3) /* Disable HSYNC during VBLANK */
+#define LCDC_FLAGS_DWCNT (1 << 4) /* Disable dotclock during blanking */
+
 struct sh_mobile_lcdc_sys_bus_cfg {
 	unsigned long ldmt2r;
 	unsigned long ldmt3r;
@@ -57,6 +63,7 @@ struct sh_mobile_lcdc_chan_cfg {
 	int bpp;
 	int interface_type; /* selects RGBn or SYSn I/F, see above */
 	int clock_divider;
+	unsigned long flags; /* LCDC_FLAGS_... */
 	struct fb_videomode lcd_cfg;
 	struct sh_mobile_lcdc_lcd_size_cfg lcd_size_cfg;
 	struct sh_mobile_lcdc_board_cfg board_cfg;
-- 
cgit v1.2.3


From 10a03a42d140a029bcba531df2897839f3569871 Mon Sep 17 00:00:00 2001
From: Patrick McHardy <kaber@trash.net>
Date: Mon, 20 Oct 2008 03:31:54 -0700
Subject: netfilter: netns: use NFPROTO_NUMPROTO instead of NUMPROTO for tables
 array

The netfilter families have been decoupled from regular protocol families.

Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/x_tables.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/net/netns/x_tables.h b/include/net/netns/x_tables.h
index 0cb63ed2c1fc..b8093971ccb4 100644
--- a/include/net/netns/x_tables.h
+++ b/include/net/netns/x_tables.h
@@ -2,9 +2,9 @@
 #define __NETNS_X_TABLES_H
 
 #include <linux/list.h>
-#include <linux/net.h>
+#include <linux/netfilter.h>
 
 struct netns_xt {
-	struct list_head tables[NPROTO];
+	struct list_head tables[NFPROTO_NUMPROTO];
 };
 #endif
-- 
cgit v1.2.3


From 592aa999d6a272856c9bfbdaac0cfba1bb37c24c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 20 Oct 2008 16:38:19 +0200
Subject: hrtimers: add missing docbook comments to struct hrtimer

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/linux/hrtimer.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index cb25c1cc2352..58bca8e9bae1 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -103,9 +103,14 @@ enum hrtimer_cb_mode {
 /**
  * struct hrtimer - the basic hrtimer structure
  * @node:	red black tree node for time ordered insertion
- * @expires:	the absolute expiry time in the hrtimers internal
+ * @_expires:	the absolute expiry time in the hrtimers internal
  *		representation. The time is related to the clock on
- *		which the timer is based.
+ *		which the timer is based. Is setup by adding
+ *		slack to the _softexpires value. For non range timers
+ *		identical to _softexpires.
+ * @_softexpires: the absolute earliest expiry time of the hrtimer.
+ *		The time which was given as expiry time when the timer
+ *		was armed.
  * @function:	timer expiry callback function
  * @base:	pointer to the timer base (per cpu and per clock)
  * @state:	state information (See bit values above)
-- 
cgit v1.2.3


From 62695a84eb8f2e718bf4dfb21700afaa7a08e0ea Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Sat, 18 Oct 2008 20:26:09 -0700
Subject: vmscan: move isolate_lru_page() to vmscan.c

On large memory systems, the VM can spend way too much time scanning
through pages that it cannot (or should not) evict from memory.  Not only
does it use up CPU time, but it also provokes lock contention and can
leave large systems under memory presure in a catatonic state.

This patch series improves VM scalability by:

1) putting filesystem backed, swap backed and unevictable pages
   onto their own LRUs, so the system only scans the pages that it
   can/should evict from memory

2) switching to two handed clock replacement for the anonymous LRUs,
   so the number of pages that need to be scanned when the system
   starts swapping is bound to a reasonable number

3) keeping unevictable pages off the LRU completely, so the
   VM does not waste CPU time scanning them. ramfs, ramdisk,
   SHM_LOCKED shared memory segments and mlock()ed VMA pages
   are keept on the unevictable list.

This patch:

isolate_lru_page logically belongs to be in vmscan.c than migrate.c.

It is tough, because we don't need that function without memory migration
so there is a valid argument to have it in migrate.c.  However a
subsequent patch needs to make use of it in the core mm, so we can happily
move it to vmscan.c.

Also, make the function a little more generic by not requiring that it
adds an isolated page to a given list.  Callers can do that.

	Note that we now have '__isolate_lru_page()', that does
	something quite different, visible outside of vmscan.c
	for use with memory controller.  Methinks we need to
	rationalize these names/purposes.	--lts

[akpm@linux-foundation.org: fix mm/memory_hotplug.c build]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/migrate.h |  3 ---
 mm/internal.h           |  2 ++
 mm/memory_hotplug.c     |  3 ++-
 mm/mempolicy.c          |  9 +++++++--
 mm/migrate.c            | 34 +++-------------------------------
 mm/vmscan.c             | 45 +++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 59 insertions(+), 37 deletions(-)

(limited to 'include')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 03aea612d284..3f34005068d4 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -7,7 +7,6 @@
 typedef struct page *new_page_t(struct page *, unsigned long private, int **);
 
 #ifdef CONFIG_MIGRATION
-extern int isolate_lru_page(struct page *p, struct list_head *pagelist);
 extern int putback_lru_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
 			struct page *, struct page *);
@@ -21,8 +20,6 @@ extern int migrate_vmas(struct mm_struct *mm,
 		const nodemask_t *from, const nodemask_t *to,
 		unsigned long flags);
 #else
-static inline int isolate_lru_page(struct page *p, struct list_head *list)
-					{ return -ENOSYS; }
 static inline int putback_lru_pages(struct list_head *l) { return 0; }
 static inline int migrate_pages(struct list_head *l, new_page_t x,
 		unsigned long private) { return -ENOSYS; }
diff --git a/mm/internal.h b/mm/internal.h
index 1f43f7416972..4e8e78b978b5 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -39,6 +39,8 @@ static inline void __put_page(struct page *page)
 	atomic_dec(&page->_count);
 }
 
+extern int isolate_lru_page(struct page *page);
+
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
 
 /*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c299d083d8e2..3b4975815141 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -658,8 +658,9 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		 * We can skip free pages. And we can only deal with pages on
 		 * LRU.
 		 */
-		ret = isolate_lru_page(page, &source);
+		ret = isolate_lru_page(page);
 		if (!ret) { /* Success */
+			list_add_tail(&page->lru, &source);
 			move_pages--;
 		} else {
 			/* Becasue we don't have big zone->lock. we should
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 83369058ec13..71b47491487d 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -93,6 +93,8 @@
 #include <asm/tlbflush.h>
 #include <asm/uaccess.h>
 
+#include "internal.h"
+
 /* Internal flags */
 #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0)	/* Skip checks for continuous vmas */
 #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1)		/* Invert check for nodemask */
@@ -762,8 +764,11 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist,
 	/*
 	 * Avoid migrating a page that is shared with others.
 	 */
-	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1)
-		isolate_lru_page(page, pagelist);
+	if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
+		if (!isolate_lru_page(page)) {
+			list_add_tail(&page->lru, pagelist);
+		}
+	}
 }
 
 static struct page *new_node_page(struct page *page, unsigned long node, int **x)
diff --git a/mm/migrate.c b/mm/migrate.c
index 2a80136b23bb..da73742e52a5 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -36,36 +36,6 @@
 
 #define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
 
-/*
- * Isolate one page from the LRU lists. If successful put it onto
- * the indicated list with elevated page count.
- *
- * Result:
- *  -EBUSY: page not on LRU list
- *  0: page removed from LRU list and added to the specified list.
- */
-int isolate_lru_page(struct page *page, struct list_head *pagelist)
-{
-	int ret = -EBUSY;
-
-	if (PageLRU(page)) {
-		struct zone *zone = page_zone(page);
-
-		spin_lock_irq(&zone->lru_lock);
-		if (PageLRU(page) && get_page_unless_zero(page)) {
-			ret = 0;
-			ClearPageLRU(page);
-			if (PageActive(page))
-				del_page_from_active_list(zone, page);
-			else
-				del_page_from_inactive_list(zone, page);
-			list_add_tail(&page->lru, pagelist);
-		}
-		spin_unlock_irq(&zone->lru_lock);
-	}
-	return ret;
-}
-
 /*
  * migrate_prep() needs to be called before we start compiling a list of pages
  * to be migrated using isolate_lru_page().
@@ -914,7 +884,9 @@ static int do_move_pages(struct mm_struct *mm, struct page_to_node *pm,
 				!migrate_all)
 			goto put_and_set;
 
-		err = isolate_lru_page(page, &pagelist);
+		err = isolate_lru_page(page);
+		if (!err)
+			list_add_tail(&page->lru, &pagelist);
 put_and_set:
 		/*
 		 * Either remove the duplicate refcount from
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1ff1a58e7c10..1fd4912a596c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -844,6 +844,51 @@ static unsigned long clear_active_flags(struct list_head *page_list)
 	return nr_active;
 }
 
+/**
+ * isolate_lru_page - tries to isolate a page from its LRU list
+ * @page: page to isolate from its LRU list
+ *
+ * Isolates a @page from an LRU list, clears PageLRU and adjusts the
+ * vmstat statistic corresponding to whatever LRU list the page was on.
+ *
+ * Returns 0 if the page was removed from an LRU list.
+ * Returns -EBUSY if the page was not on an LRU list.
+ *
+ * The returned page will have PageLRU() cleared.  If it was found on
+ * the active list, it will have PageActive set.  That flag may need
+ * to be cleared by the caller before letting the page go.
+ *
+ * The vmstat statistic corresponding to the list on which the page was
+ * found will be decremented.
+ *
+ * Restrictions:
+ * (1) Must be called with an elevated refcount on the page. This is a
+ *     fundamentnal difference from isolate_lru_pages (which is called
+ *     without a stable reference).
+ * (2) the lru_lock must not be held.
+ * (3) interrupts must be enabled.
+ */
+int isolate_lru_page(struct page *page)
+{
+	int ret = -EBUSY;
+
+	if (PageLRU(page)) {
+		struct zone *zone = page_zone(page);
+
+		spin_lock_irq(&zone->lru_lock);
+		if (PageLRU(page) && get_page_unless_zero(page)) {
+			ret = 0;
+			ClearPageLRU(page);
+			if (PageActive(page))
+				del_page_from_active_list(zone, page);
+			else
+				del_page_from_inactive_list(zone, page);
+		}
+		spin_unlock_irq(&zone->lru_lock);
+	}
+	return ret;
+}
+
 /*
  * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
  * of reclaimed pages
-- 
cgit v1.2.3


From b69408e88bd86b98feb7b9a38fd865e1ddb29827 Mon Sep 17 00:00:00 2001
From: Christoph Lameter <cl@linux-foundation.org>
Date: Sat, 18 Oct 2008 20:26:14 -0700
Subject: vmscan: Use an indexed array for LRU variables

Currently we are defining explicit variables for the inactive and active
list.  An indexed array can be more generic and avoid repeating similar
code in several places in the reclaim code.

We are saving a few bytes in terms of code size:

Before:

   text    data     bss     dec     hex filename
4097753  573120 4092484 8763357  85b7dd vmlinux

After:

   text    data     bss     dec     hex filename
4097729  573120 4092484 8763333  85b7c5 vmlinux

Having an easy way to add new lru lists may ease future work on the
reclaim code.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |  17 ++-----
 include/linux/mm_inline.h  |  49 +++++++++++++-----
 include/linux/mmzone.h     |  26 +++++++---
 mm/memcontrol.c            | 115 ++++++++++++++++---------------------------
 mm/page_alloc.c            |   9 ++--
 mm/swap.c                  |   2 +-
 mm/vmscan.c                | 120 +++++++++++++++++++++------------------------
 mm/vmstat.c                |   3 +-
 8 files changed, 171 insertions(+), 170 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index fdf3967e1397..a6ac0d491fe6 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -69,10 +69,8 @@ extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
 extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
 							int priority);
 
-extern long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
-				struct zone *zone, int priority);
-extern long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
-				struct zone *zone, int priority);
+extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
+					int priority, enum lru_list lru);
 
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
 static inline void page_reset_bad_cgroup(struct page *page)
@@ -159,14 +157,9 @@ static inline void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
 {
 }
 
-static inline long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
-					struct zone *zone, int priority)
-{
-	return 0;
-}
-
-static inline long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
-					struct zone *zone, int priority)
+static inline long mem_cgroup_calc_reclaim(struct mem_cgroup *mem,
+					struct zone *zone, int priority,
+					enum lru_list lru)
 {
 	return 0;
 }
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 895bc4e93039..2704729777ef 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -1,40 +1,67 @@
+static inline void
+add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l)
+{
+	list_add(&page->lru, &zone->lru[l].list);
+	__inc_zone_state(zone, NR_LRU_BASE + l);
+}
+
+static inline void
+del_page_from_lru_list(struct zone *zone, struct page *page, enum lru_list l)
+{
+	list_del(&page->lru);
+	__dec_zone_state(zone, NR_LRU_BASE + l);
+}
+
 static inline void
 add_page_to_active_list(struct zone *zone, struct page *page)
 {
-	list_add(&page->lru, &zone->active_list);
-	__inc_zone_state(zone, NR_ACTIVE);
+	add_page_to_lru_list(zone, page, LRU_ACTIVE);
 }
 
 static inline void
 add_page_to_inactive_list(struct zone *zone, struct page *page)
 {
-	list_add(&page->lru, &zone->inactive_list);
-	__inc_zone_state(zone, NR_INACTIVE);
+	add_page_to_lru_list(zone, page, LRU_INACTIVE);
 }
 
 static inline void
 del_page_from_active_list(struct zone *zone, struct page *page)
 {
-	list_del(&page->lru);
-	__dec_zone_state(zone, NR_ACTIVE);
+	del_page_from_lru_list(zone, page, LRU_ACTIVE);
 }
 
 static inline void
 del_page_from_inactive_list(struct zone *zone, struct page *page)
 {
-	list_del(&page->lru);
-	__dec_zone_state(zone, NR_INACTIVE);
+	del_page_from_lru_list(zone, page, LRU_INACTIVE);
 }
 
 static inline void
 del_page_from_lru(struct zone *zone, struct page *page)
 {
+	enum lru_list l = LRU_INACTIVE;
+
 	list_del(&page->lru);
 	if (PageActive(page)) {
 		__ClearPageActive(page);
-		__dec_zone_state(zone, NR_ACTIVE);
-	} else {
-		__dec_zone_state(zone, NR_INACTIVE);
+		l = LRU_ACTIVE;
 	}
+	__dec_zone_state(zone, NR_LRU_BASE + l);
 }
 
+/**
+ * page_lru - which LRU list should a page be on?
+ * @page: the page to test
+ *
+ * Returns the LRU list a page should be on, as an index
+ * into the array of LRU lists.
+ */
+static inline enum lru_list page_lru(struct page *page)
+{
+	enum lru_list lru = LRU_BASE;
+
+	if (PageActive(page))
+		lru += LRU_ACTIVE;
+
+	return lru;
+}
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 428328a05fa1..156e18f3919b 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -81,8 +81,9 @@ struct zone_padding {
 enum zone_stat_item {
 	/* First 128 byte cacheline (assuming 64 bit words) */
 	NR_FREE_PAGES,
-	NR_INACTIVE,
-	NR_ACTIVE,
+	NR_LRU_BASE,
+	NR_INACTIVE = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
+	NR_ACTIVE,	/*  "     "     "   "       "         */
 	NR_ANON_PAGES,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
 			   only modified from process context */
@@ -107,6 +108,19 @@ enum zone_stat_item {
 #endif
 	NR_VM_ZONE_STAT_ITEMS };
 
+enum lru_list {
+	LRU_BASE,
+	LRU_INACTIVE=LRU_BASE,	/* must match order of NR_[IN]ACTIVE */
+	LRU_ACTIVE,		/*  "     "     "   "       "        */
+	NR_LRU_LISTS };
+
+#define for_each_lru(l) for (l = 0; l < NR_LRU_LISTS; l++)
+
+static inline int is_active_lru(enum lru_list l)
+{
+	return (l == LRU_ACTIVE);
+}
+
 struct per_cpu_pages {
 	int count;		/* number of pages in the list */
 	int high;		/* high watermark, emptying needed */
@@ -251,10 +265,10 @@ struct zone {
 
 	/* Fields commonly accessed by the page reclaim scanner */
 	spinlock_t		lru_lock;	
-	struct list_head	active_list;
-	struct list_head	inactive_list;
-	unsigned long		nr_scan_active;
-	unsigned long		nr_scan_inactive;
+	struct {
+		struct list_head list;
+		unsigned long nr_scan;
+	} lru[NR_LRU_LISTS];
 	unsigned long		pages_scanned;	   /* since last reclaim */
 	unsigned long		flags;		   /* zone flags, see below */
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 36896f3eb7f5..c0cbd7790c51 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -32,6 +32,7 @@
 #include <linux/fs.h>
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
+#include <linux/mm_inline.h>
 
 #include <asm/uaccess.h>
 
@@ -85,22 +86,13 @@ static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
 /*
  * per-zone information in memory controller.
  */
-
-enum mem_cgroup_zstat_index {
-	MEM_CGROUP_ZSTAT_ACTIVE,
-	MEM_CGROUP_ZSTAT_INACTIVE,
-
-	NR_MEM_CGROUP_ZSTAT,
-};
-
 struct mem_cgroup_per_zone {
 	/*
 	 * spin_lock to protect the per cgroup LRU
 	 */
 	spinlock_t		lru_lock;
-	struct list_head	active_list;
-	struct list_head	inactive_list;
-	unsigned long count[NR_MEM_CGROUP_ZSTAT];
+	struct list_head	lists[NR_LRU_LISTS];
+	unsigned long		count[NR_LRU_LISTS];
 };
 /* Macro for accessing counter */
 #define MEM_CGROUP_ZSTAT(mz, idx)	((mz)->count[(idx)])
@@ -227,7 +219,7 @@ page_cgroup_zoneinfo(struct page_cgroup *pc)
 }
 
 static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
-					enum mem_cgroup_zstat_index idx)
+					enum lru_list idx)
 {
 	int nid, zid;
 	struct mem_cgroup_per_zone *mz;
@@ -297,11 +289,9 @@ static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
 			struct page_cgroup *pc)
 {
 	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+	int lru = !!from;
 
-	if (from)
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
-	else
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1;
+	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
 
 	mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, false);
 	list_del(&pc->lru);
@@ -310,37 +300,35 @@ static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
 static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
 				struct page_cgroup *pc)
 {
-	int to = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+	int lru = LRU_INACTIVE;
+
+	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+		lru += LRU_ACTIVE;
+
+	MEM_CGROUP_ZSTAT(mz, lru) += 1;
+	list_add(&pc->lru, &mz->lists[lru]);
 
-	if (!to) {
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
-		list_add(&pc->lru, &mz->inactive_list);
-	} else {
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;
-		list_add(&pc->lru, &mz->active_list);
-	}
 	mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);
 }
 
 static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
 {
-	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
 	struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
+	int lru = LRU_INACTIVE;
 
-	if (from)
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) -= 1;
-	else
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) -= 1;
+	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+		lru += LRU_ACTIVE;
 
-	if (active) {
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;
+	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+
+	if (active)
 		pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
-		list_move(&pc->lru, &mz->active_list);
-	} else {
-		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
+	else
 		pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
-		list_move(&pc->lru, &mz->inactive_list);
-	}
+
+	lru = !!active;
+	MEM_CGROUP_ZSTAT(mz, lru) += 1;
+	list_move(&pc->lru, &mz->lists[lru]);
 }
 
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
@@ -412,8 +400,8 @@ long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
 {
 	unsigned long active, inactive;
 	/* active and inactive are the number of pages. 'long' is ok.*/
-	active = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_ACTIVE);
-	inactive = mem_cgroup_get_all_zonestat(mem, MEM_CGROUP_ZSTAT_INACTIVE);
+	active = mem_cgroup_get_all_zonestat(mem, LRU_ACTIVE);
+	inactive = mem_cgroup_get_all_zonestat(mem, LRU_INACTIVE);
 	return (long) (active / (inactive + 1));
 }
 
@@ -444,28 +432,17 @@ void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem, int priority)
  * (see include/linux/mmzone.h)
  */
 
-long mem_cgroup_calc_reclaim_active(struct mem_cgroup *mem,
-				   struct zone *zone, int priority)
+long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
+					int priority, enum lru_list lru)
 {
-	long nr_active;
+	long nr_pages;
 	int nid = zone->zone_pgdat->node_id;
 	int zid = zone_idx(zone);
 	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
 
-	nr_active = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE);
-	return (nr_active >> priority);
-}
-
-long mem_cgroup_calc_reclaim_inactive(struct mem_cgroup *mem,
-					struct zone *zone, int priority)
-{
-	long nr_inactive;
-	int nid = zone->zone_pgdat->node_id;
-	int zid = zone_idx(zone);
-	struct mem_cgroup_per_zone *mz = mem_cgroup_zoneinfo(mem, nid, zid);
+	nr_pages = MEM_CGROUP_ZSTAT(mz, lru);
 
-	nr_inactive = MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE);
-	return (nr_inactive >> priority);
+	return (nr_pages >> priority);
 }
 
 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
@@ -484,14 +461,11 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 	int nid = z->zone_pgdat->node_id;
 	int zid = zone_idx(z);
 	struct mem_cgroup_per_zone *mz;
+	int lru = !!active;
 
 	BUG_ON(!mem_cont);
 	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
-	if (active)
-		src = &mz->active_list;
-	else
-		src = &mz->inactive_list;
-
+	src = &mz->lists[lru];
 
 	spin_lock(&mz->lru_lock);
 	scan = 0;
@@ -863,7 +837,7 @@ int mem_cgroup_resize_limit(struct mem_cgroup *memcg, unsigned long long val)
 #define FORCE_UNCHARGE_BATCH	(128)
 static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
 			    struct mem_cgroup_per_zone *mz,
-			    int active)
+			    enum lru_list lru)
 {
 	struct page_cgroup *pc;
 	struct page *page;
@@ -871,10 +845,7 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
 	unsigned long flags;
 	struct list_head *list;
 
-	if (active)
-		list = &mz->active_list;
-	else
-		list = &mz->inactive_list;
+	list = &mz->lists[lru];
 
 	spin_lock_irqsave(&mz->lru_lock, flags);
 	while (!list_empty(list)) {
@@ -922,11 +893,10 @@ static int mem_cgroup_force_empty(struct mem_cgroup *mem)
 		for_each_node_state(node, N_POSSIBLE)
 			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 				struct mem_cgroup_per_zone *mz;
+				enum lru_list l;
 				mz = mem_cgroup_zoneinfo(mem, node, zid);
-				/* drop all page_cgroup in active_list */
-				mem_cgroup_force_empty_list(mem, mz, 1);
-				/* drop all page_cgroup in inactive_list */
-				mem_cgroup_force_empty_list(mem, mz, 0);
+				for_each_lru(l)
+					mem_cgroup_force_empty_list(mem, mz, l);
 			}
 	}
 	ret = 0;
@@ -1015,9 +985,9 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 		unsigned long active, inactive;
 
 		inactive = mem_cgroup_get_all_zonestat(mem_cont,
-						MEM_CGROUP_ZSTAT_INACTIVE);
+						LRU_INACTIVE);
 		active = mem_cgroup_get_all_zonestat(mem_cont,
-						MEM_CGROUP_ZSTAT_ACTIVE);
+						LRU_ACTIVE);
 		cb->fill(cb, "active", (active) * PAGE_SIZE);
 		cb->fill(cb, "inactive", (inactive) * PAGE_SIZE);
 	}
@@ -1062,6 +1032,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 {
 	struct mem_cgroup_per_node *pn;
 	struct mem_cgroup_per_zone *mz;
+	enum lru_list l;
 	int zone, tmp = node;
 	/*
 	 * This routine is called against possible nodes.
@@ -1082,9 +1053,9 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		mz = &pn->zoneinfo[zone];
-		INIT_LIST_HEAD(&mz->active_list);
-		INIT_LIST_HEAD(&mz->inactive_list);
 		spin_lock_init(&mz->lru_lock);
+		for_each_lru(l)
+			INIT_LIST_HEAD(&mz->lists[l]);
 	}
 	return 0;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9eb9eb928285..ee7a96ef40dc 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3414,6 +3414,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
 		unsigned long size, realsize, memmap_pages;
+		enum lru_list l;
 
 		size = zone_spanned_pages_in_node(nid, j, zones_size);
 		realsize = size - zone_absent_pages_in_node(nid, j,
@@ -3465,10 +3466,10 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 		zone->prev_priority = DEF_PRIORITY;
 
 		zone_pcp_init(zone);
-		INIT_LIST_HEAD(&zone->active_list);
-		INIT_LIST_HEAD(&zone->inactive_list);
-		zone->nr_scan_active = 0;
-		zone->nr_scan_inactive = 0;
+		for_each_lru(l) {
+			INIT_LIST_HEAD(&zone->lru[l].list);
+			zone->lru[l].nr_scan = 0;
+		}
 		zap_zone_vm_stats(zone);
 		zone->flags = 0;
 		if (!size)
diff --git a/mm/swap.c b/mm/swap.c
index 9e0cb3118079..82c2b3a76f94 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -117,7 +117,7 @@ static void pagevec_move_tail(struct pagevec *pvec)
 			spin_lock(&zone->lru_lock);
 		}
 		if (PageLRU(page) && !PageActive(page)) {
-			list_move_tail(&page->lru, &zone->inactive_list);
+			list_move_tail(&page->lru, &zone->lru[LRU_INACTIVE].list);
 			pgmoved++;
 		}
 	}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1fd4912a596c..46fdaa546b8d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -819,10 +819,10 @@ static unsigned long isolate_pages_global(unsigned long nr,
 					int active)
 {
 	if (active)
-		return isolate_lru_pages(nr, &z->active_list, dst,
+		return isolate_lru_pages(nr, &z->lru[LRU_ACTIVE].list, dst,
 						scanned, order, mode);
 	else
-		return isolate_lru_pages(nr, &z->inactive_list, dst,
+		return isolate_lru_pages(nr, &z->lru[LRU_INACTIVE].list, dst,
 						scanned, order, mode);
 }
 
@@ -973,10 +973,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 			VM_BUG_ON(PageLRU(page));
 			SetPageLRU(page);
 			list_del(&page->lru);
-			if (PageActive(page))
-				add_page_to_active_list(zone, page);
-			else
-				add_page_to_inactive_list(zone, page);
+			add_page_to_lru_list(zone, page, page_lru(page));
 			if (!pagevec_add(&pvec, page)) {
 				spin_unlock_irq(&zone->lru_lock);
 				__pagevec_release(&pvec);
@@ -1144,8 +1141,8 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	int pgdeactivate = 0;
 	unsigned long pgscanned;
 	LIST_HEAD(l_hold);	/* The pages which were snipped off */
-	LIST_HEAD(l_inactive);	/* Pages to go onto the inactive_list */
-	LIST_HEAD(l_active);	/* Pages to go onto the active_list */
+	LIST_HEAD(l_active);
+	LIST_HEAD(l_inactive);
 	struct page *page;
 	struct pagevec pvec;
 	int reclaim_mapped = 0;
@@ -1194,7 +1191,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		VM_BUG_ON(!PageActive(page));
 		ClearPageActive(page);
 
-		list_move(&page->lru, &zone->inactive_list);
+		list_move(&page->lru, &zone->lru[LRU_INACTIVE].list);
 		mem_cgroup_move_lists(page, false);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
@@ -1224,7 +1221,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		SetPageLRU(page);
 		VM_BUG_ON(!PageActive(page));
 
-		list_move(&page->lru, &zone->active_list);
+		list_move(&page->lru, &zone->lru[LRU_ACTIVE].list);
 		mem_cgroup_move_lists(page, true);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
@@ -1244,65 +1241,64 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	pagevec_release(&pvec);
 }
 
+static unsigned long shrink_list(enum lru_list l, unsigned long nr_to_scan,
+	struct zone *zone, struct scan_control *sc, int priority)
+{
+	if (l == LRU_ACTIVE) {
+		shrink_active_list(nr_to_scan, zone, sc, priority);
+		return 0;
+	}
+	return shrink_inactive_list(nr_to_scan, zone, sc);
+}
+
 /*
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
  */
 static unsigned long shrink_zone(int priority, struct zone *zone,
 				struct scan_control *sc)
 {
-	unsigned long nr_active;
-	unsigned long nr_inactive;
+	unsigned long nr[NR_LRU_LISTS];
 	unsigned long nr_to_scan;
 	unsigned long nr_reclaimed = 0;
+	enum lru_list l;
 
 	if (scan_global_lru(sc)) {
 		/*
 		 * Add one to nr_to_scan just to make sure that the kernel
 		 * will slowly sift through the active list.
 		 */
-		zone->nr_scan_active +=
-			(zone_page_state(zone, NR_ACTIVE) >> priority) + 1;
-		nr_active = zone->nr_scan_active;
-		zone->nr_scan_inactive +=
-			(zone_page_state(zone, NR_INACTIVE) >> priority) + 1;
-		nr_inactive = zone->nr_scan_inactive;
-		if (nr_inactive >= sc->swap_cluster_max)
-			zone->nr_scan_inactive = 0;
-		else
-			nr_inactive = 0;
-
-		if (nr_active >= sc->swap_cluster_max)
-			zone->nr_scan_active = 0;
-		else
-			nr_active = 0;
+		for_each_lru(l) {
+			zone->lru[l].nr_scan += (zone_page_state(zone,
+					NR_LRU_BASE + l)  >> priority) + 1;
+			nr[l] = zone->lru[l].nr_scan;
+			if (nr[l] >= sc->swap_cluster_max)
+				zone->lru[l].nr_scan = 0;
+			else
+				nr[l] = 0;
+		}
 	} else {
 		/*
 		 * This reclaim occurs not because zone memory shortage but
 		 * because memory controller hits its limit.
 		 * Then, don't modify zone reclaim related data.
 		 */
-		nr_active = mem_cgroup_calc_reclaim_active(sc->mem_cgroup,
-					zone, priority);
+		nr[LRU_ACTIVE] = mem_cgroup_calc_reclaim(sc->mem_cgroup,
+					zone, priority, LRU_ACTIVE);
 
-		nr_inactive = mem_cgroup_calc_reclaim_inactive(sc->mem_cgroup,
-					zone, priority);
+		nr[LRU_INACTIVE] = mem_cgroup_calc_reclaim(sc->mem_cgroup,
+					zone, priority, LRU_INACTIVE);
 	}
 
-
-	while (nr_active || nr_inactive) {
-		if (nr_active) {
-			nr_to_scan = min(nr_active,
+	while (nr[LRU_ACTIVE] || nr[LRU_INACTIVE]) {
+		for_each_lru(l) {
+			if (nr[l]) {
+				nr_to_scan = min(nr[l],
 					(unsigned long)sc->swap_cluster_max);
-			nr_active -= nr_to_scan;
-			shrink_active_list(nr_to_scan, zone, sc, priority);
-		}
+				nr[l] -= nr_to_scan;
 
-		if (nr_inactive) {
-			nr_to_scan = min(nr_inactive,
-					(unsigned long)sc->swap_cluster_max);
-			nr_inactive -= nr_to_scan;
-			nr_reclaimed += shrink_inactive_list(nr_to_scan, zone,
-								sc);
+				nr_reclaimed += shrink_list(l, nr_to_scan,
+							zone, sc, priority);
+			}
 		}
 	}
 
@@ -1819,6 +1815,7 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 {
 	struct zone *zone;
 	unsigned long nr_to_scan, ret = 0;
+	enum lru_list l;
 
 	for_each_zone(zone) {
 
@@ -1828,28 +1825,25 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 		if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
 			continue;
 
-		/* For pass = 0 we don't shrink the active list */
-		if (pass > 0) {
-			zone->nr_scan_active +=
-				(zone_page_state(zone, NR_ACTIVE) >> prio) + 1;
-			if (zone->nr_scan_active >= nr_pages || pass > 3) {
-				zone->nr_scan_active = 0;
+		for_each_lru(l) {
+			/* For pass = 0 we don't shrink the active list */
+			if (pass == 0 && l == LRU_ACTIVE)
+				continue;
+
+			zone->lru[l].nr_scan +=
+				(zone_page_state(zone, NR_LRU_BASE + l)
+								>> prio) + 1;
+			if (zone->lru[l].nr_scan >= nr_pages || pass > 3) {
+				zone->lru[l].nr_scan = 0;
 				nr_to_scan = min(nr_pages,
-					zone_page_state(zone, NR_ACTIVE));
-				shrink_active_list(nr_to_scan, zone, sc, prio);
+					zone_page_state(zone,
+							NR_LRU_BASE + l));
+				ret += shrink_list(l, nr_to_scan, zone,
+								sc, prio);
+				if (ret >= nr_pages)
+					return ret;
 			}
 		}
-
-		zone->nr_scan_inactive +=
-			(zone_page_state(zone, NR_INACTIVE) >> prio) + 1;
-		if (zone->nr_scan_inactive >= nr_pages || pass > 3) {
-			zone->nr_scan_inactive = 0;
-			nr_to_scan = min(nr_pages,
-				zone_page_state(zone, NR_INACTIVE));
-			ret += shrink_inactive_list(nr_to_scan, zone, sc);
-			if (ret >= nr_pages)
-				return ret;
-		}
 	}
 
 	return ret;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index d7826af2fb07..52c0335c1b71 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -696,7 +696,8 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   zone->pages_low,
 		   zone->pages_high,
 		   zone->pages_scanned,
-		   zone->nr_scan_active, zone->nr_scan_inactive,
+		   zone->lru[LRU_ACTIVE].nr_scan,
+		   zone->lru[LRU_INACTIVE].nr_scan,
 		   zone->spanned_pages,
 		   zone->present_pages);
 
-- 
cgit v1.2.3


From f04e9ebbe4909f9a41efd55149bc353299f4e83b Mon Sep 17 00:00:00 2001
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Date: Sat, 18 Oct 2008 20:26:19 -0700
Subject: swap: use an array for the LRU pagevecs

Turn the pagevecs into an array just like the LRUs.  This significantly
cleans up the source code and reduces the size of the kernel by about 13kB
after all the LRU lists have been created further down in the split VM
patch series.

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagevec.h | 13 ++++++--
 include/linux/swap.h    | 18 +++++++++--
 mm/migrate.c            | 11 +------
 mm/swap.c               | 79 +++++++++++++++++--------------------------------
 4 files changed, 55 insertions(+), 66 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index 8eb7fa76c1d0..6b8f11bcc948 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -23,8 +23,7 @@ struct pagevec {
 void __pagevec_release(struct pagevec *pvec);
 void __pagevec_release_nonlru(struct pagevec *pvec);
 void __pagevec_free(struct pagevec *pvec);
-void __pagevec_lru_add(struct pagevec *pvec);
-void __pagevec_lru_add_active(struct pagevec *pvec);
+void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru);
 void pagevec_strip(struct pagevec *pvec);
 unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
 		pgoff_t start, unsigned nr_pages);
@@ -81,6 +80,16 @@ static inline void pagevec_free(struct pagevec *pvec)
 		__pagevec_free(pvec);
 }
 
+static inline void __pagevec_lru_add(struct pagevec *pvec)
+{
+	____pagevec_lru_add(pvec, LRU_INACTIVE);
+}
+
+static inline void __pagevec_lru_add_active(struct pagevec *pvec)
+{
+	____pagevec_lru_add(pvec, LRU_ACTIVE);
+}
+
 static inline void pagevec_lru_add(struct pagevec *pvec)
 {
 	if (pagevec_count(pvec))
diff --git a/include/linux/swap.h b/include/linux/swap.h
index de40f169a4e4..fcc169610d09 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -171,8 +171,8 @@ extern unsigned int nr_free_pagecache_pages(void);
 
 
 /* linux/mm/swap.c */
-extern void lru_cache_add(struct page *);
-extern void lru_cache_add_active(struct page *);
+extern void __lru_cache_add(struct page *, enum lru_list lru);
+extern void lru_cache_add_lru(struct page *, enum lru_list lru);
 extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
@@ -180,6 +180,20 @@ extern int lru_add_drain_all(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void swap_setup(void);
 
+/**
+ * lru_cache_add: add a page to the page lists
+ * @page: the page to add
+ */
+static inline void lru_cache_add(struct page *page)
+{
+	__lru_cache_add(page, LRU_INACTIVE);
+}
+
+static inline void lru_cache_add_active(struct page *page)
+{
+	__lru_cache_add(page, LRU_ACTIVE);
+}
+
 /* linux/mm/vmscan.c */
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask);
diff --git a/mm/migrate.c b/mm/migrate.c
index da73742e52a5..ad15b5ef2599 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -55,16 +55,7 @@ int migrate_prep(void)
 
 static inline void move_to_lru(struct page *page)
 {
-	if (PageActive(page)) {
-		/*
-		 * lru_cache_add_active checks that
-		 * the PG_active bit is off.
-		 */
-		ClearPageActive(page);
-		lru_cache_add_active(page);
-	} else {
-		lru_cache_add(page);
-	}
+	lru_cache_add_lru(page, page_lru(page));
 	put_page(page);
 }
 
diff --git a/mm/swap.c b/mm/swap.c
index 82c2b3a76f94..e3045040dc3e 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -34,8 +34,7 @@
 /* How many pages do we try to swap or page in/out together? */
 int page_cluster;
 
-static DEFINE_PER_CPU(struct pagevec, lru_add_pvecs);
-static DEFINE_PER_CPU(struct pagevec, lru_add_active_pvecs);
+static DEFINE_PER_CPU(struct pagevec[NR_LRU_LISTS], lru_add_pvecs);
 static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
 
 /*
@@ -186,28 +185,29 @@ void mark_page_accessed(struct page *page)
 
 EXPORT_SYMBOL(mark_page_accessed);
 
-/**
- * lru_cache_add: add a page to the page lists
- * @page: the page to add
- */
-void lru_cache_add(struct page *page)
+void __lru_cache_add(struct page *page, enum lru_list lru)
 {
-	struct pagevec *pvec = &get_cpu_var(lru_add_pvecs);
+	struct pagevec *pvec = &get_cpu_var(lru_add_pvecs)[lru];
 
 	page_cache_get(page);
 	if (!pagevec_add(pvec, page))
-		__pagevec_lru_add(pvec);
+		____pagevec_lru_add(pvec, lru);
 	put_cpu_var(lru_add_pvecs);
 }
 
-void lru_cache_add_active(struct page *page)
+/**
+ * lru_cache_add_lru - add a page to a page list
+ * @page: the page to be added to the LRU.
+ * @lru: the LRU list to which the page is added.
+ */
+void lru_cache_add_lru(struct page *page, enum lru_list lru)
 {
-	struct pagevec *pvec = &get_cpu_var(lru_add_active_pvecs);
+	if (PageActive(page)) {
+		ClearPageActive(page);
+	}
 
-	page_cache_get(page);
-	if (!pagevec_add(pvec, page))
-		__pagevec_lru_add_active(pvec);
-	put_cpu_var(lru_add_active_pvecs);
+	VM_BUG_ON(PageLRU(page) || PageActive(page));
+	__lru_cache_add(page, lru);
 }
 
 /*
@@ -217,15 +217,15 @@ void lru_cache_add_active(struct page *page)
  */
 static void drain_cpu_pagevecs(int cpu)
 {
+	struct pagevec *pvecs = per_cpu(lru_add_pvecs, cpu);
 	struct pagevec *pvec;
+	int lru;
 
-	pvec = &per_cpu(lru_add_pvecs, cpu);
-	if (pagevec_count(pvec))
-		__pagevec_lru_add(pvec);
-
-	pvec = &per_cpu(lru_add_active_pvecs, cpu);
-	if (pagevec_count(pvec))
-		__pagevec_lru_add_active(pvec);
+	for_each_lru(lru) {
+		pvec = &pvecs[lru - LRU_BASE];
+		if (pagevec_count(pvec))
+			____pagevec_lru_add(pvec, lru);
+	}
 
 	pvec = &per_cpu(lru_rotate_pvecs, cpu);
 	if (pagevec_count(pvec)) {
@@ -380,7 +380,7 @@ void __pagevec_release_nonlru(struct pagevec *pvec)
  * Add the passed pages to the LRU, then drop the caller's refcount
  * on them.  Reinitialises the caller's pagevec.
  */
-void __pagevec_lru_add(struct pagevec *pvec)
+void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
 {
 	int i;
 	struct zone *zone = NULL;
@@ -397,7 +397,9 @@ void __pagevec_lru_add(struct pagevec *pvec)
 		}
 		VM_BUG_ON(PageLRU(page));
 		SetPageLRU(page);
-		add_page_to_inactive_list(zone, page);
+		if (is_active_lru(lru))
+			SetPageActive(page);
+		add_page_to_lru_list(zone, page, lru);
 	}
 	if (zone)
 		spin_unlock_irq(&zone->lru_lock);
@@ -405,34 +407,7 @@ void __pagevec_lru_add(struct pagevec *pvec)
 	pagevec_reinit(pvec);
 }
 
-EXPORT_SYMBOL(__pagevec_lru_add);
-
-void __pagevec_lru_add_active(struct pagevec *pvec)
-{
-	int i;
-	struct zone *zone = NULL;
-
-	for (i = 0; i < pagevec_count(pvec); i++) {
-		struct page *page = pvec->pages[i];
-		struct zone *pagezone = page_zone(page);
-
-		if (pagezone != zone) {
-			if (zone)
-				spin_unlock_irq(&zone->lru_lock);
-			zone = pagezone;
-			spin_lock_irq(&zone->lru_lock);
-		}
-		VM_BUG_ON(PageLRU(page));
-		SetPageLRU(page);
-		VM_BUG_ON(PageActive(page));
-		SetPageActive(page);
-		add_page_to_active_list(zone, page);
-	}
-	if (zone)
-		spin_unlock_irq(&zone->lru_lock);
-	release_pages(pvec->pages, pvec->nr, pvec->cold);
-	pagevec_reinit(pvec);
-}
+EXPORT_SYMBOL(____pagevec_lru_add);
 
 /*
  * Try to drop buffers from the pages in a pagevec
-- 
cgit v1.2.3


From 68a22394c286a2daf06ee8d65d8835f738faefa5 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Sat, 18 Oct 2008 20:26:23 -0700
Subject: vmscan: free swap space on swap-in/activation

If vm_swap_full() (swap space more than 50% full), the system will free
swap space at swapin time.  With this patch, the system will also free the
swap space in the pageout code, when we decide that the page is not a
candidate for swapout (and just wasting swap space).

Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: MinChan Kim <minchan.kim@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagevec.h |  1 +
 include/linux/swap.h    |  6 ++++++
 mm/swap.c               | 24 ++++++++++++++++++++++++
 mm/swapfile.c           | 25 ++++++++++++++++++++++---
 mm/vmscan.c             |  7 +++++++
 5 files changed, 60 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index 6b8f11bcc948..fea3a982ee55 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -25,6 +25,7 @@ void __pagevec_release_nonlru(struct pagevec *pvec);
 void __pagevec_free(struct pagevec *pvec);
 void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru);
 void pagevec_strip(struct pagevec *pvec);
+void pagevec_swap_free(struct pagevec *pvec);
 unsigned pagevec_lookup(struct pagevec *pvec, struct address_space *mapping,
 		pgoff_t start, unsigned nr_pages);
 unsigned pagevec_lookup_tag(struct pagevec *pvec,
diff --git a/include/linux/swap.h b/include/linux/swap.h
index fcc169610d09..833be56ad835 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -265,6 +265,7 @@ extern sector_t swapdev_block(int, pgoff_t);
 extern struct swap_info_struct *get_swap_info_struct(unsigned);
 extern int can_share_swap_page(struct page *);
 extern int remove_exclusive_swap_page(struct page *);
+extern int remove_exclusive_swap_page_ref(struct page *);
 struct backing_dev_info;
 
 /* linux/mm/thrash.c */
@@ -353,6 +354,11 @@ static inline int remove_exclusive_swap_page(struct page *p)
 	return 0;
 }
 
+static inline int remove_exclusive_swap_page_ref(struct page *page)
+{
+	return 0;
+}
+
 static inline swp_entry_t get_swap_page(void)
 {
 	swp_entry_t entry;
diff --git a/mm/swap.c b/mm/swap.c
index e3045040dc3e..88a394872677 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -427,6 +427,30 @@ void pagevec_strip(struct pagevec *pvec)
 	}
 }
 
+/**
+ * pagevec_swap_free - try to free swap space from the pages in a pagevec
+ * @pvec: pagevec with swapcache pages to free the swap space of
+ *
+ * The caller needs to hold an extra reference to each page and
+ * not hold the page lock on the pages.  This function uses a
+ * trylock on the page lock so it may not always free the swap
+ * space associated with a page.
+ */
+void pagevec_swap_free(struct pagevec *pvec)
+{
+	int i;
+
+	for (i = 0; i < pagevec_count(pvec); i++) {
+		struct page *page = pvec->pages[i];
+
+		if (PageSwapCache(page) && trylock_page(page)) {
+			if (PageSwapCache(page))
+				remove_exclusive_swap_page_ref(page);
+			unlock_page(page);
+		}
+	}
+}
+
 /**
  * pagevec_lookup - gang pagecache lookup
  * @pvec:	Where the resulting pages are placed
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 1e330f2998fa..2a97fafa3d89 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -344,7 +344,7 @@ int can_share_swap_page(struct page *page)
  * Work out if there are any other processes sharing this
  * swap cache page. Free it if you can. Return success.
  */
-int remove_exclusive_swap_page(struct page *page)
+static int remove_exclusive_swap_page_count(struct page *page, int count)
 {
 	int retval;
 	struct swap_info_struct * p;
@@ -357,7 +357,7 @@ int remove_exclusive_swap_page(struct page *page)
 		return 0;
 	if (PageWriteback(page))
 		return 0;
-	if (page_count(page) != 2) /* 2: us + cache */
+	if (page_count(page) != count) /* us + cache + ptes */
 		return 0;
 
 	entry.val = page_private(page);
@@ -370,7 +370,7 @@ int remove_exclusive_swap_page(struct page *page)
 	if (p->swap_map[swp_offset(entry)] == 1) {
 		/* Recheck the page count with the swapcache lock held.. */
 		spin_lock_irq(&swapper_space.tree_lock);
-		if ((page_count(page) == 2) && !PageWriteback(page)) {
+		if ((page_count(page) == count) && !PageWriteback(page)) {
 			__delete_from_swap_cache(page);
 			SetPageDirty(page);
 			retval = 1;
@@ -387,6 +387,25 @@ int remove_exclusive_swap_page(struct page *page)
 	return retval;
 }
 
+/*
+ * Most of the time the page should have two references: one for the
+ * process and one for the swap cache.
+ */
+int remove_exclusive_swap_page(struct page *page)
+{
+	return remove_exclusive_swap_page_count(page, 2);
+}
+
+/*
+ * The pageout code holds an extra reference to the page.  That raises
+ * the reference count to test for to 2 for a page that is only in the
+ * swap cache plus 1 for each process that maps the page.
+ */
+int remove_exclusive_swap_page_ref(struct page *page)
+{
+	return remove_exclusive_swap_page_count(page, 2 + page_mapcount(page));
+}
+
 /*
  * Free the swap entry like above, but also try to
  * free the page cache entry if it is the last user.
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 46fdaa546b8d..e656035d3406 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -647,6 +647,9 @@ free_it:
 		continue;
 
 activate_locked:
+		/* Not a candidate for swapping, so reclaim swap space. */
+		if (PageSwapCache(page) && vm_swap_full())
+			remove_exclusive_swap_page_ref(page);
 		SetPageActive(page);
 		pgactivate++;
 keep_locked:
@@ -1228,6 +1231,8 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 			__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
 			pgmoved = 0;
 			spin_unlock_irq(&zone->lru_lock);
+			if (vm_swap_full())
+				pagevec_swap_free(&pvec);
 			__pagevec_release(&pvec);
 			spin_lock_irq(&zone->lru_lock);
 		}
@@ -1237,6 +1242,8 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	__count_zone_vm_events(PGREFILL, zone, pgscanned);
 	__count_vm_events(PGDEACTIVATE, pgdeactivate);
 	spin_unlock_irq(&zone->lru_lock);
+	if (vm_swap_full())
+		pagevec_swap_free(&pvec);
 
 	pagevec_release(&pvec);
 }
-- 
cgit v1.2.3


From b2e185384f534781fd22f5ce170b2ad26f97df70 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Sat, 18 Oct 2008 20:26:30 -0700
Subject: define page_file_cache() function

Define page_file_cache() function to answer the question:
	is page backed by a file?

Originally part of Rik van Riel's split-lru patch.  Extracted to make
available for other, independent reclaim patches.

Moved inline function to linux/mm_inline.h where it will be needed by
subsequent "split LRU" and "noreclaim" patches.

Unfortunately this needs to use a page flag, since the PG_swapbacked state
needs to be preserved all the way to the point where the page is last
removed from the LRU.  Trying to derive the status from other info in the
page resulted in wrong VM statistics in earlier split VM patchsets.

The total number of page flags in use on a 32 bit machine after this patch
is 19.

[akpm@linux-foundation.org: fix up out-of-order merge fallout]
[hugh@veritas.com: splitlru: shmem_getpage SetPageSwapBacked sooner[
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: MinChan Kim <minchan.kim@gmail.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm_inline.h  | 27 +++++++++++++++++++++++++++
 include/linux/page-flags.h |  8 ++++++--
 mm/memory.c                |  3 +++
 mm/migrate.c               |  2 ++
 mm/page_alloc.c            |  2 ++
 mm/shmem.c                 |  1 +
 mm/swap_state.c            |  3 +++
 7 files changed, 44 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 2704729777ef..96e970485b6c 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -1,3 +1,28 @@
+#ifndef LINUX_MM_INLINE_H
+#define LINUX_MM_INLINE_H
+
+/**
+ * page_is_file_cache - should the page be on a file LRU or anon LRU?
+ * @page: the page to test
+ *
+ * Returns !0 if @page is page cache page backed by a regular filesystem,
+ * or 0 if @page is anonymous, tmpfs or otherwise ram or swap backed.
+ * Used by functions that manipulate the LRU lists, to sort a page
+ * onto the right LRU list.
+ *
+ * We would like to get this info without a page flag, but the state
+ * needs to survive until the page is last deleted from the LRU, which
+ * could be as far down as __page_cache_release.
+ */
+static inline int page_is_file_cache(struct page *page)
+{
+	if (PageSwapBacked(page))
+		return 0;
+
+	/* The page is page cache backed by a normal filesystem. */
+	return 1;
+}
+
 static inline void
 add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l)
 {
@@ -65,3 +90,5 @@ static inline enum lru_list page_lru(struct page *page)
 
 	return lru;
 }
+
+#endif
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index c74d3e875314..57b688cfb5e2 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -93,6 +93,7 @@ enum pageflags {
 	PG_mappedtodisk,	/* Has blocks allocated on-disk */
 	PG_reclaim,		/* To be reclaimed asap */
 	PG_buddy,		/* Page is free, on buddy lists */
+	PG_swapbacked,		/* Page is backed by RAM/swap */
 #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR
 	PG_uncached,		/* Page has been mapped as uncached */
 #endif
@@ -176,6 +177,7 @@ PAGEFLAG(SavePinned, savepinned);			/* Xen */
 PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
 PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private)
 	__SETPAGEFLAG(Private, private)
+PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
 
 __PAGEFLAG(SlobPage, slob_page)
 __PAGEFLAG(SlobFree, slob_free)
@@ -334,7 +336,8 @@ static inline void __ClearPageTail(struct page *page)
  * Flags checked in bad_page().  Pages on the free list should not have
  * these flags set.  It they are, there is a problem.
  */
-#define PAGE_FLAGS_CLEAR_WHEN_BAD (PAGE_FLAGS | 1 << PG_reclaim | 1 << PG_dirty)
+#define PAGE_FLAGS_CLEAR_WHEN_BAD (PAGE_FLAGS | \
+		1 << PG_reclaim | 1 << PG_dirty | 1 << PG_swapbacked)
 
 /*
  * Flags checked when a page is freed.  Pages being freed should not have
@@ -347,7 +350,8 @@ static inline void __ClearPageTail(struct page *page)
  * Pages being prepped should not have these flags set.  It they are, there
  * is a problem.
  */
-#define PAGE_FLAGS_CHECK_AT_PREP (PAGE_FLAGS | 1 << PG_reserved | 1 << PG_dirty)
+#define PAGE_FLAGS_CHECK_AT_PREP (PAGE_FLAGS | \
+		1 << PG_reserved | 1 << PG_dirty | 1 << PG_swapbacked)
 
 #endif /* !__GENERATING_BOUNDS_H */
 #endif	/* PAGE_FLAGS_H */
diff --git a/mm/memory.c b/mm/memory.c
index 1002f473f497..7512933dcc10 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1888,6 +1888,7 @@ gotten:
 		ptep_clear_flush_notify(vma, address, page_table);
 		set_pte_at(mm, address, page_table, entry);
 		update_mmu_cache(vma, address, entry);
+		SetPageSwapBacked(new_page);
 		lru_cache_add_active(new_page);
 		page_add_new_anon_rmap(new_page, vma, address);
 
@@ -2382,6 +2383,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!pte_none(*page_table))
 		goto release;
 	inc_mm_counter(mm, anon_rss);
+	SetPageSwapBacked(page);
 	lru_cache_add_active(page);
 	page_add_new_anon_rmap(page, vma, address);
 	set_pte_at(mm, address, page_table, entry);
@@ -2523,6 +2525,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		set_pte_at(mm, address, page_table, entry);
 		if (anon) {
                         inc_mm_counter(mm, anon_rss);
+			SetPageSwapBacked(page);
                         lru_cache_add_active(page);
                         page_add_new_anon_rmap(page, vma, address);
 		} else {
diff --git a/mm/migrate.c b/mm/migrate.c
index ad15b5ef2599..c07327487111 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -572,6 +572,8 @@ static int move_to_new_page(struct page *newpage, struct page *page)
 	/* Prepare mapping for the new page.*/
 	newpage->index = page->index;
 	newpage->mapping = page->mapping;
+	if (PageSwapBacked(page))
+		SetPageSwapBacked(newpage);
 
 	mapping = page_mapping(page);
 	if (!mapping)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ee7a96ef40dc..2099904d6cc4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -462,6 +462,8 @@ static inline int free_pages_check(struct page *page)
 		bad_page(page);
 	if (PageDirty(page))
 		__ClearPageDirty(page);
+	if (PageSwapBacked(page))
+		__ClearPageSwapBacked(page);
 	/*
 	 * For now, we report if PG_reserved was found set, but do not
 	 * clear it, and do not free the page.  But we shall soon need
diff --git a/mm/shmem.c b/mm/shmem.c
index d87958a5f03e..fd421ed703ed 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1367,6 +1367,7 @@ repeat:
 				error = -ENOMEM;
 				goto failed;
 			}
+			SetPageSwapBacked(filepage);
 
 			/* Precharge page while we can wait, compensate after */
 			error = mem_cgroup_cache_charge(filepage, current->mm,
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 797c3831cbec..7a3ece0b5a3b 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -75,6 +75,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask)
 	BUG_ON(!PageLocked(page));
 	BUG_ON(PageSwapCache(page));
 	BUG_ON(PagePrivate(page));
+	BUG_ON(!PageSwapBacked(page));
 	error = radix_tree_preload(gfp_mask);
 	if (!error) {
 		page_cache_get(page);
@@ -303,6 +304,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * May fail (-ENOMEM) if radix-tree node allocation failed.
 		 */
 		set_page_locked(new_page);
+		SetPageSwapBacked(new_page);
 		err = add_to_swap_cache(new_page, entry, gfp_mask & GFP_KERNEL);
 		if (likely(!err)) {
 			/*
@@ -312,6 +314,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			swap_readpage(NULL, new_page);
 			return new_page;
 		}
+		ClearPageSwapBacked(new_page);
 		clear_page_locked(new_page);
 		swap_free(entry);
 	} while (err != -ENOMEM);
-- 
cgit v1.2.3


From 4f98a2fee8acdb4ac84545df98cccecfd130f8db Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Sat, 18 Oct 2008 20:26:32 -0700
Subject: vmscan: split LRU lists into anon & file sets

Split the LRU lists in two, one set for pages that are backed by real file
systems ("file") and one for pages that are backed by memory and swap
("anon").  The latter includes tmpfs.

The advantage of doing this is that the VM will not have to scan over lots
of anonymous pages (which we generally do not want to swap out), just to
find the page cache pages that it should evict.

This patch has the infrastructure and a basic policy to balance how much
we scan the anon lists and how much we scan the file lists.  The big
policy changes are in separate patches.

[lee.schermerhorn@hp.com: collect lru meminfo statistics from correct offset]
[kosaki.motohiro@jp.fujitsu.com: prevent incorrect oom under split_lru]
[kosaki.motohiro@jp.fujitsu.com: fix pagevec_move_tail() doesn't treat unevictable page]
[hugh@veritas.com: memcg swapbacked pages active]
[hugh@veritas.com: splitlru: BDI_CAP_SWAP_BACKED]
[akpm@linux-foundation.org: fix /proc/vmstat units]
[nishimura@mxp.nes.nec.co.jp: memcg: fix handling of shmem migration]
[kosaki.motohiro@jp.fujitsu.com: adjust Quicklists field of /proc/meminfo]
[kosaki.motohiro@jp.fujitsu.com: fix style issue of get_scan_ratio()]
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/node.c         |  56 +++---
 fs/cifs/file.c              |   4 +-
 fs/nfs/dir.c                |   2 +-
 fs/ntfs/file.c              |   4 +-
 fs/proc/proc_misc.c         |  77 ++++----
 fs/ramfs/file-nommu.c       |   4 +-
 include/linux/backing-dev.h |  13 ++
 include/linux/memcontrol.h  |   2 +-
 include/linux/mm_inline.h   |  50 ++++--
 include/linux/mmzone.h      |  47 ++++-
 include/linux/pagevec.h     |  29 ++-
 include/linux/swap.h        |  20 ++-
 include/linux/vmstat.h      |  10 ++
 mm/filemap.c                |  22 ++-
 mm/hugetlb.c                |  10 +-
 mm/memcontrol.c             |  88 ++++++----
 mm/memory.c                 |   6 +-
 mm/page-writeback.c         |   8 +-
 mm/page_alloc.c             |  25 ++-
 mm/readahead.c              |   2 +-
 mm/shmem.c                  |   2 +-
 mm/swap.c                   |  14 +-
 mm/swap_state.c             |   4 +-
 mm/vmscan.c                 | 416 +++++++++++++++++++++++---------------------
 mm/vmstat.c                 |  14 +-
 25 files changed, 562 insertions(+), 367 deletions(-)

(limited to 'include')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 5116b78c6325..fc7e9bf0cdbc 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -61,34 +61,44 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
 	si_meminfo_node(&i, nid);
 
 	n = sprintf(buf, "\n"
-		       "Node %d MemTotal:     %8lu kB\n"
-		       "Node %d MemFree:      %8lu kB\n"
-		       "Node %d MemUsed:      %8lu kB\n"
-		       "Node %d Active:       %8lu kB\n"
-		       "Node %d Inactive:     %8lu kB\n"
+		       "Node %d MemTotal:       %8lu kB\n"
+		       "Node %d MemFree:        %8lu kB\n"
+		       "Node %d MemUsed:        %8lu kB\n"
+		       "Node %d Active:         %8lu kB\n"
+		       "Node %d Inactive:       %8lu kB\n"
+		       "Node %d Active(anon):   %8lu kB\n"
+		       "Node %d Inactive(anon): %8lu kB\n"
+		       "Node %d Active(file):   %8lu kB\n"
+		       "Node %d Inactive(file): %8lu kB\n"
 #ifdef CONFIG_HIGHMEM
-		       "Node %d HighTotal:    %8lu kB\n"
-		       "Node %d HighFree:     %8lu kB\n"
-		       "Node %d LowTotal:     %8lu kB\n"
-		       "Node %d LowFree:      %8lu kB\n"
+		       "Node %d HighTotal:      %8lu kB\n"
+		       "Node %d HighFree:       %8lu kB\n"
+		       "Node %d LowTotal:       %8lu kB\n"
+		       "Node %d LowFree:        %8lu kB\n"
 #endif
-		       "Node %d Dirty:        %8lu kB\n"
-		       "Node %d Writeback:    %8lu kB\n"
-		       "Node %d FilePages:    %8lu kB\n"
-		       "Node %d Mapped:       %8lu kB\n"
-		       "Node %d AnonPages:    %8lu kB\n"
-		       "Node %d PageTables:   %8lu kB\n"
-		       "Node %d NFS_Unstable: %8lu kB\n"
-		       "Node %d Bounce:       %8lu kB\n"
-		       "Node %d WritebackTmp: %8lu kB\n"
-		       "Node %d Slab:         %8lu kB\n"
-		       "Node %d SReclaimable: %8lu kB\n"
-		       "Node %d SUnreclaim:   %8lu kB\n",
+		       "Node %d Dirty:          %8lu kB\n"
+		       "Node %d Writeback:      %8lu kB\n"
+		       "Node %d FilePages:      %8lu kB\n"
+		       "Node %d Mapped:         %8lu kB\n"
+		       "Node %d AnonPages:      %8lu kB\n"
+		       "Node %d PageTables:     %8lu kB\n"
+		       "Node %d NFS_Unstable:   %8lu kB\n"
+		       "Node %d Bounce:         %8lu kB\n"
+		       "Node %d WritebackTmp:   %8lu kB\n"
+		       "Node %d Slab:           %8lu kB\n"
+		       "Node %d SReclaimable:   %8lu kB\n"
+		       "Node %d SUnreclaim:     %8lu kB\n",
 		       nid, K(i.totalram),
 		       nid, K(i.freeram),
 		       nid, K(i.totalram - i.freeram),
-		       nid, K(node_page_state(nid, NR_ACTIVE)),
-		       nid, K(node_page_state(nid, NR_INACTIVE)),
+		       nid, K(node_page_state(nid, NR_ACTIVE_ANON) +
+				node_page_state(nid, NR_ACTIVE_FILE)),
+		       nid, K(node_page_state(nid, NR_INACTIVE_ANON) +
+				node_page_state(nid, NR_INACTIVE_FILE)),
+		       nid, K(node_page_state(nid, NR_ACTIVE_ANON)),
+		       nid, K(node_page_state(nid, NR_INACTIVE_ANON)),
+		       nid, K(node_page_state(nid, NR_ACTIVE_FILE)),
+		       nid, K(node_page_state(nid, NR_INACTIVE_FILE)),
 #ifdef CONFIG_HIGHMEM
 		       nid, K(i.totalhigh),
 		       nid, K(i.freehigh),
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index c4a8a0605125..62d8bd8f14c0 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -1791,7 +1791,7 @@ static void cifs_copy_cache_pages(struct address_space *mapping,
 		SetPageUptodate(page);
 		unlock_page(page);
 		if (!pagevec_add(plru_pvec, page))
-			__pagevec_lru_add(plru_pvec);
+			__pagevec_lru_add_file(plru_pvec);
 		data += PAGE_CACHE_SIZE;
 	}
 	return;
@@ -1925,7 +1925,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		bytes_read = 0;
 	}
 
-	pagevec_lru_add(&lru_pvec);
+	pagevec_lru_add_file(&lru_pvec);
 
 /* need to free smb_read_data buf before exit */
 	if (smb_read_data) {
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 2ab70d46ecbc..efdba2e802d7 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1517,7 +1517,7 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
 	if (!add_to_page_cache(page, dentry->d_inode->i_mapping, 0,
 							GFP_KERNEL)) {
 		pagevec_add(&lru_pvec, page);
-		pagevec_lru_add(&lru_pvec);
+		pagevec_lru_add_file(&lru_pvec);
 		SetPageUptodate(page);
 		unlock_page(page);
 	} else
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index d020866d4232..3140a4429af1 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -439,7 +439,7 @@ static inline int __ntfs_grab_cache_pages(struct address_space *mapping,
 			pages[nr] = *cached_page;
 			page_cache_get(*cached_page);
 			if (unlikely(!pagevec_add(lru_pvec, *cached_page)))
-				__pagevec_lru_add(lru_pvec);
+				__pagevec_lru_add_file(lru_pvec);
 			*cached_page = NULL;
 		}
 		index++;
@@ -2084,7 +2084,7 @@ err_out:
 						OSYNC_METADATA|OSYNC_DATA);
 		}
   	}
-	pagevec_lru_add(&lru_pvec);
+	pagevec_lru_add_file(&lru_pvec);
 	ntfs_debug("Done.  Returning %s (written 0x%lx, status %li).",
 			written ? "written" : "status", (unsigned long)written,
 			(long)status);
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 59ea42e1ef03..b8edb2860557 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -136,6 +136,8 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 	unsigned long allowed;
 	struct vmalloc_info vmi;
 	long cached;
+	unsigned long pages[NR_LRU_LISTS];
+	int lru;
 
 /*
  * display in kilobytes.
@@ -154,51 +156,62 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 
 	get_vmalloc_info(&vmi);
 
+	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
+		pages[lru] = global_page_state(NR_LRU_BASE + lru);
+
 	/*
 	 * Tagged format, for easy grepping and expansion.
 	 */
 	len = sprintf(page,
-		"MemTotal:     %8lu kB\n"
-		"MemFree:      %8lu kB\n"
-		"Buffers:      %8lu kB\n"
-		"Cached:       %8lu kB\n"
-		"SwapCached:   %8lu kB\n"
-		"Active:       %8lu kB\n"
-		"Inactive:     %8lu kB\n"
+		"MemTotal:       %8lu kB\n"
+		"MemFree:        %8lu kB\n"
+		"Buffers:        %8lu kB\n"
+		"Cached:         %8lu kB\n"
+		"SwapCached:     %8lu kB\n"
+		"Active:         %8lu kB\n"
+		"Inactive:       %8lu kB\n"
+		"Active(anon):   %8lu kB\n"
+		"Inactive(anon): %8lu kB\n"
+		"Active(file):   %8lu kB\n"
+		"Inactive(file): %8lu kB\n"
 #ifdef CONFIG_HIGHMEM
-		"HighTotal:    %8lu kB\n"
-		"HighFree:     %8lu kB\n"
-		"LowTotal:     %8lu kB\n"
-		"LowFree:      %8lu kB\n"
+		"HighTotal:      %8lu kB\n"
+		"HighFree:       %8lu kB\n"
+		"LowTotal:       %8lu kB\n"
+		"LowFree:        %8lu kB\n"
 #endif
-		"SwapTotal:    %8lu kB\n"
-		"SwapFree:     %8lu kB\n"
-		"Dirty:        %8lu kB\n"
-		"Writeback:    %8lu kB\n"
-		"AnonPages:    %8lu kB\n"
-		"Mapped:       %8lu kB\n"
-		"Slab:         %8lu kB\n"
-		"SReclaimable: %8lu kB\n"
-		"SUnreclaim:   %8lu kB\n"
-		"PageTables:   %8lu kB\n"
+		"SwapTotal:      %8lu kB\n"
+		"SwapFree:       %8lu kB\n"
+		"Dirty:          %8lu kB\n"
+		"Writeback:      %8lu kB\n"
+		"AnonPages:      %8lu kB\n"
+		"Mapped:         %8lu kB\n"
+		"Slab:           %8lu kB\n"
+		"SReclaimable:   %8lu kB\n"
+		"SUnreclaim:     %8lu kB\n"
+		"PageTables:     %8lu kB\n"
 #ifdef CONFIG_QUICKLIST
-		"Quicklists:   %8lu kB\n"
+		"Quicklists:     %8lu kB\n"
 #endif
-		"NFS_Unstable: %8lu kB\n"
-		"Bounce:       %8lu kB\n"
-		"WritebackTmp: %8lu kB\n"
-		"CommitLimit:  %8lu kB\n"
-		"Committed_AS: %8lu kB\n"
-		"VmallocTotal: %8lu kB\n"
-		"VmallocUsed:  %8lu kB\n"
-		"VmallocChunk: %8lu kB\n",
+		"NFS_Unstable:   %8lu kB\n"
+		"Bounce:         %8lu kB\n"
+		"WritebackTmp:   %8lu kB\n"
+		"CommitLimit:    %8lu kB\n"
+		"Committed_AS:   %8lu kB\n"
+		"VmallocTotal:   %8lu kB\n"
+		"VmallocUsed:    %8lu kB\n"
+		"VmallocChunk:   %8lu kB\n",
 		K(i.totalram),
 		K(i.freeram),
 		K(i.bufferram),
 		K(cached),
 		K(total_swapcache_pages),
-		K(global_page_state(NR_ACTIVE)),
-		K(global_page_state(NR_INACTIVE)),
+		K(pages[LRU_ACTIVE_ANON]   + pages[LRU_ACTIVE_FILE]),
+		K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]),
+		K(pages[LRU_ACTIVE_ANON]),
+		K(pages[LRU_INACTIVE_ANON]),
+		K(pages[LRU_ACTIVE_FILE]),
+		K(pages[LRU_INACTIVE_FILE]),
 #ifdef CONFIG_HIGHMEM
 		K(i.totalhigh),
 		K(i.freehigh),
diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c
index 5145cb9125af..76acdbc34611 100644
--- a/fs/ramfs/file-nommu.c
+++ b/fs/ramfs/file-nommu.c
@@ -112,12 +112,12 @@ int ramfs_nommu_expand_for_mapping(struct inode *inode, size_t newsize)
 			goto add_error;
 
 		if (!pagevec_add(&lru_pvec, page))
-			__pagevec_lru_add(&lru_pvec);
+			__pagevec_lru_add_file(&lru_pvec);
 
 		unlock_page(page);
 	}
 
-	pagevec_lru_add(&lru_pvec);
+	pagevec_lru_add_file(&lru_pvec);
 	return 0;
 
  fsize_exceeded:
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 0a24d5550eb3..bee52abb8a4d 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -175,6 +175,8 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
  * BDI_CAP_READ_MAP:       Can be mapped for reading
  * BDI_CAP_WRITE_MAP:      Can be mapped for writing
  * BDI_CAP_EXEC_MAP:       Can be mapped for execution
+ *
+ * BDI_CAP_SWAP_BACKED:    Count shmem/tmpfs objects as swap-backed.
  */
 #define BDI_CAP_NO_ACCT_DIRTY	0x00000001
 #define BDI_CAP_NO_WRITEBACK	0x00000002
@@ -184,6 +186,7 @@ int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio);
 #define BDI_CAP_WRITE_MAP	0x00000020
 #define BDI_CAP_EXEC_MAP	0x00000040
 #define BDI_CAP_NO_ACCT_WB	0x00000080
+#define BDI_CAP_SWAP_BACKED	0x00000100
 
 #define BDI_CAP_VMFLAGS \
 	(BDI_CAP_READ_MAP | BDI_CAP_WRITE_MAP | BDI_CAP_EXEC_MAP)
@@ -248,6 +251,11 @@ static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi)
 				      BDI_CAP_NO_WRITEBACK));
 }
 
+static inline bool bdi_cap_swap_backed(struct backing_dev_info *bdi)
+{
+	return bdi->capabilities & BDI_CAP_SWAP_BACKED;
+}
+
 static inline bool mapping_cap_writeback_dirty(struct address_space *mapping)
 {
 	return bdi_cap_writeback_dirty(mapping->backing_dev_info);
@@ -258,4 +266,9 @@ static inline bool mapping_cap_account_dirty(struct address_space *mapping)
 	return bdi_cap_account_dirty(mapping->backing_dev_info);
 }
 
+static inline bool mapping_cap_swap_backed(struct address_space *mapping)
+{
+	return bdi_cap_swap_backed(mapping->backing_dev_info);
+}
+
 #endif		/* _LINUX_BACKING_DEV_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index a6ac0d491fe6..8d8f05c1515a 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -44,7 +44,7 @@ extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					unsigned long *scanned, int order,
 					int mode, struct zone *z,
 					struct mem_cgroup *mem_cont,
-					int active);
+					int active, int file);
 extern void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask);
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem);
 
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 96e970485b6c..2eb599465d56 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -5,7 +5,7 @@
  * page_is_file_cache - should the page be on a file LRU or anon LRU?
  * @page: the page to test
  *
- * Returns !0 if @page is page cache page backed by a regular filesystem,
+ * Returns LRU_FILE if @page is page cache page backed by a regular filesystem,
  * or 0 if @page is anonymous, tmpfs or otherwise ram or swap backed.
  * Used by functions that manipulate the LRU lists, to sort a page
  * onto the right LRU list.
@@ -20,7 +20,7 @@ static inline int page_is_file_cache(struct page *page)
 		return 0;
 
 	/* The page is page cache backed by a normal filesystem. */
-	return 1;
+	return LRU_FILE;
 }
 
 static inline void
@@ -38,39 +38,64 @@ del_page_from_lru_list(struct zone *zone, struct page *page, enum lru_list l)
 }
 
 static inline void
-add_page_to_active_list(struct zone *zone, struct page *page)
+add_page_to_inactive_anon_list(struct zone *zone, struct page *page)
 {
-	add_page_to_lru_list(zone, page, LRU_ACTIVE);
+	add_page_to_lru_list(zone, page, LRU_INACTIVE_ANON);
 }
 
 static inline void
-add_page_to_inactive_list(struct zone *zone, struct page *page)
+add_page_to_active_anon_list(struct zone *zone, struct page *page)
 {
-	add_page_to_lru_list(zone, page, LRU_INACTIVE);
+	add_page_to_lru_list(zone, page, LRU_ACTIVE_ANON);
 }
 
 static inline void
-del_page_from_active_list(struct zone *zone, struct page *page)
+add_page_to_inactive_file_list(struct zone *zone, struct page *page)
 {
-	del_page_from_lru_list(zone, page, LRU_ACTIVE);
+	add_page_to_lru_list(zone, page, LRU_INACTIVE_FILE);
 }
 
 static inline void
-del_page_from_inactive_list(struct zone *zone, struct page *page)
+add_page_to_active_file_list(struct zone *zone, struct page *page)
 {
-	del_page_from_lru_list(zone, page, LRU_INACTIVE);
+	add_page_to_lru_list(zone, page, LRU_ACTIVE_FILE);
+}
+
+static inline void
+del_page_from_inactive_anon_list(struct zone *zone, struct page *page)
+{
+	del_page_from_lru_list(zone, page, LRU_INACTIVE_ANON);
+}
+
+static inline void
+del_page_from_active_anon_list(struct zone *zone, struct page *page)
+{
+	del_page_from_lru_list(zone, page, LRU_ACTIVE_ANON);
+}
+
+static inline void
+del_page_from_inactive_file_list(struct zone *zone, struct page *page)
+{
+	del_page_from_lru_list(zone, page, LRU_INACTIVE_FILE);
+}
+
+static inline void
+del_page_from_active_file_list(struct zone *zone, struct page *page)
+{
+	del_page_from_lru_list(zone, page, LRU_INACTIVE_FILE);
 }
 
 static inline void
 del_page_from_lru(struct zone *zone, struct page *page)
 {
-	enum lru_list l = LRU_INACTIVE;
+	enum lru_list l = LRU_BASE;
 
 	list_del(&page->lru);
 	if (PageActive(page)) {
 		__ClearPageActive(page);
-		l = LRU_ACTIVE;
+		l += LRU_ACTIVE;
 	}
+	l += page_is_file_cache(page);
 	__dec_zone_state(zone, NR_LRU_BASE + l);
 }
 
@@ -87,6 +112,7 @@ static inline enum lru_list page_lru(struct page *page)
 
 	if (PageActive(page))
 		lru += LRU_ACTIVE;
+	lru += page_is_file_cache(page);
 
 	return lru;
 }
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 156e18f3919b..59a4c8fd6ebd 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -82,21 +82,23 @@ enum zone_stat_item {
 	/* First 128 byte cacheline (assuming 64 bit words) */
 	NR_FREE_PAGES,
 	NR_LRU_BASE,
-	NR_INACTIVE = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
-	NR_ACTIVE,	/*  "     "     "   "       "         */
+	NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
+	NR_ACTIVE_ANON,		/*  "     "     "   "       "         */
+	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
+	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
 	NR_ANON_PAGES,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
 			   only modified from process context */
 	NR_FILE_PAGES,
 	NR_FILE_DIRTY,
 	NR_WRITEBACK,
-	/* Second 128 byte cacheline */
 	NR_SLAB_RECLAIMABLE,
 	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,		/* used for pagetables */
 	NR_UNSTABLE_NFS,	/* NFS unstable pages */
 	NR_BOUNCE,
 	NR_VMSCAN_WRITE,
+	/* Second 128 byte cacheline */
 	NR_WRITEBACK_TEMP,	/* Writeback using temporary buffers */
 #ifdef CONFIG_NUMA
 	NUMA_HIT,		/* allocated in intended node */
@@ -108,17 +110,36 @@ enum zone_stat_item {
 #endif
 	NR_VM_ZONE_STAT_ITEMS };
 
+/*
+ * We do arithmetic on the LRU lists in various places in the code,
+ * so it is important to keep the active lists LRU_ACTIVE higher in
+ * the array than the corresponding inactive lists, and to keep
+ * the *_FILE lists LRU_FILE higher than the corresponding _ANON lists.
+ *
+ * This has to be kept in sync with the statistics in zone_stat_item
+ * above and the descriptions in vmstat_text in mm/vmstat.c
+ */
+#define LRU_BASE 0
+#define LRU_ACTIVE 1
+#define LRU_FILE 2
+
 enum lru_list {
-	LRU_BASE,
-	LRU_INACTIVE=LRU_BASE,	/* must match order of NR_[IN]ACTIVE */
-	LRU_ACTIVE,		/*  "     "     "   "       "        */
+	LRU_INACTIVE_ANON = LRU_BASE,
+	LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE,
+	LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE,
+	LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE,
 	NR_LRU_LISTS };
 
 #define for_each_lru(l) for (l = 0; l < NR_LRU_LISTS; l++)
 
+static inline int is_file_lru(enum lru_list l)
+{
+	return (l == LRU_INACTIVE_FILE || l == LRU_ACTIVE_FILE);
+}
+
 static inline int is_active_lru(enum lru_list l)
 {
-	return (l == LRU_ACTIVE);
+	return (l == LRU_ACTIVE_ANON || l == LRU_ACTIVE_FILE);
 }
 
 struct per_cpu_pages {
@@ -269,6 +290,18 @@ struct zone {
 		struct list_head list;
 		unsigned long nr_scan;
 	} lru[NR_LRU_LISTS];
+
+	/*
+	 * The pageout code in vmscan.c keeps track of how many of the
+	 * mem/swap backed and file backed pages are refeferenced.
+	 * The higher the rotated/scanned ratio, the more valuable
+	 * that cache is.
+	 *
+	 * The anon LRU stats live in [0], file LRU stats in [1]
+	 */
+	unsigned long		recent_rotated[2];
+	unsigned long		recent_scanned[2];
+
 	unsigned long		pages_scanned;	   /* since last reclaim */
 	unsigned long		flags;		   /* zone flags, see below */
 
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index fea3a982ee55..5fc96a4e760f 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -81,20 +81,37 @@ static inline void pagevec_free(struct pagevec *pvec)
 		__pagevec_free(pvec);
 }
 
-static inline void __pagevec_lru_add(struct pagevec *pvec)
+static inline void __pagevec_lru_add_anon(struct pagevec *pvec)
 {
-	____pagevec_lru_add(pvec, LRU_INACTIVE);
+	____pagevec_lru_add(pvec, LRU_INACTIVE_ANON);
 }
 
-static inline void __pagevec_lru_add_active(struct pagevec *pvec)
+static inline void __pagevec_lru_add_active_anon(struct pagevec *pvec)
 {
-	____pagevec_lru_add(pvec, LRU_ACTIVE);
+	____pagevec_lru_add(pvec, LRU_ACTIVE_ANON);
 }
 
-static inline void pagevec_lru_add(struct pagevec *pvec)
+static inline void __pagevec_lru_add_file(struct pagevec *pvec)
+{
+	____pagevec_lru_add(pvec, LRU_INACTIVE_FILE);
+}
+
+static inline void __pagevec_lru_add_active_file(struct pagevec *pvec)
+{
+	____pagevec_lru_add(pvec, LRU_ACTIVE_FILE);
+}
+
+
+static inline void pagevec_lru_add_file(struct pagevec *pvec)
+{
+	if (pagevec_count(pvec))
+		__pagevec_lru_add_file(pvec);
+}
+
+static inline void pagevec_lru_add_anon(struct pagevec *pvec)
 {
 	if (pagevec_count(pvec))
-		__pagevec_lru_add(pvec);
+		__pagevec_lru_add_anon(pvec);
 }
 
 #endif /* _LINUX_PAGEVEC_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 833be56ad835..7d09d79997a4 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -184,14 +184,24 @@ extern void swap_setup(void);
  * lru_cache_add: add a page to the page lists
  * @page: the page to add
  */
-static inline void lru_cache_add(struct page *page)
+static inline void lru_cache_add_anon(struct page *page)
 {
-	__lru_cache_add(page, LRU_INACTIVE);
+	__lru_cache_add(page, LRU_INACTIVE_ANON);
 }
 
-static inline void lru_cache_add_active(struct page *page)
+static inline void lru_cache_add_active_anon(struct page *page)
 {
-	__lru_cache_add(page, LRU_ACTIVE);
+	__lru_cache_add(page, LRU_ACTIVE_ANON);
+}
+
+static inline void lru_cache_add_file(struct page *page)
+{
+	__lru_cache_add(page, LRU_INACTIVE_FILE);
+}
+
+static inline void lru_cache_add_active_file(struct page *page)
+{
+	__lru_cache_add(page, LRU_ACTIVE_FILE);
 }
 
 /* linux/mm/vmscan.c */
@@ -199,7 +209,7 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask);
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
 							gfp_t gfp_mask);
-extern int __isolate_lru_page(struct page *page, int mode);
+extern int __isolate_lru_page(struct page *page, int mode, int file);
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;
 extern int remove_mapping(struct address_space *mapping, struct page *page);
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 58334d439516..ff5179f2b153 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -159,6 +159,16 @@ static inline unsigned long zone_page_state(struct zone *zone,
 	return x;
 }
 
+extern unsigned long global_lru_pages(void);
+
+static inline unsigned long zone_lru_pages(struct zone *zone)
+{
+	return (zone_page_state(zone, NR_ACTIVE_ANON)
+		+ zone_page_state(zone, NR_ACTIVE_FILE)
+		+ zone_page_state(zone, NR_INACTIVE_ANON)
+		+ zone_page_state(zone, NR_INACTIVE_FILE));
+}
+
 #ifdef CONFIG_NUMA
 /*
  * Determine the per node value of a stat item. This function
diff --git a/mm/filemap.c b/mm/filemap.c
index 903bf316912a..a1ddd2557af2 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -33,6 +33,7 @@
 #include <linux/cpuset.h>
 #include <linux/hardirq.h> /* for BUG_ON(!in_atomic()) only */
 #include <linux/memcontrol.h>
+#include <linux/mm_inline.h> /* for page_is_file_cache() */
 #include "internal.h"
 
 /*
@@ -492,9 +493,24 @@ EXPORT_SYMBOL(add_to_page_cache_locked);
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 				pgoff_t offset, gfp_t gfp_mask)
 {
-	int ret = add_to_page_cache(page, mapping, offset, gfp_mask);
-	if (ret == 0)
-		lru_cache_add(page);
+	int ret;
+
+	/*
+	 * Splice_read and readahead add shmem/tmpfs pages into the page cache
+	 * before shmem_readpage has a chance to mark them as SwapBacked: they
+	 * need to go on the active_anon lru below, and mem_cgroup_cache_charge
+	 * (called in add_to_page_cache) needs to know where they're going too.
+	 */
+	if (mapping_cap_swap_backed(mapping))
+		SetPageSwapBacked(page);
+
+	ret = add_to_page_cache(page, mapping, offset, gfp_mask);
+	if (ret == 0) {
+		if (page_is_file_cache(page))
+			lru_cache_add_file(page);
+		else
+			lru_cache_add_active_anon(page);
+	}
 	return ret;
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 38633864a93e..2fc7fddd9b1f 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1459,11 +1459,11 @@ int hugetlb_report_meminfo(char *buf)
 {
 	struct hstate *h = &default_hstate;
 	return sprintf(buf,
-			"HugePages_Total: %5lu\n"
-			"HugePages_Free:  %5lu\n"
-			"HugePages_Rsvd:  %5lu\n"
-			"HugePages_Surp:  %5lu\n"
-			"Hugepagesize:    %5lu kB\n",
+			"HugePages_Total:   %5lu\n"
+			"HugePages_Free:    %5lu\n"
+			"HugePages_Rsvd:    %5lu\n"
+			"HugePages_Surp:    %5lu\n"
+			"Hugepagesize:   %8lu kB\n",
 			h->nr_huge_pages,
 			h->free_huge_pages,
 			h->resv_huge_pages,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c0cbd7790c51..27e9e75f4eab 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -162,6 +162,7 @@ struct page_cgroup {
 };
 #define PAGE_CGROUP_FLAG_CACHE	(0x1)	/* charged as cache */
 #define PAGE_CGROUP_FLAG_ACTIVE (0x2)	/* page is active in this cgroup */
+#define PAGE_CGROUP_FLAG_FILE	(0x4)	/* page is file system backed */
 
 static int page_cgroup_nid(struct page_cgroup *pc)
 {
@@ -177,6 +178,7 @@ enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
 	MEM_CGROUP_CHARGE_TYPE_MAPPED,
 	MEM_CGROUP_CHARGE_TYPE_FORCE,	/* used by force_empty */
+	MEM_CGROUP_CHARGE_TYPE_SHMEM,	/* used by page migration of shmem */
 };
 
 /*
@@ -288,8 +290,12 @@ static void unlock_page_cgroup(struct page *page)
 static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
 			struct page_cgroup *pc)
 {
-	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
-	int lru = !!from;
+	int lru = LRU_BASE;
+
+	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+		lru += LRU_ACTIVE;
+	if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+		lru += LRU_FILE;
 
 	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
 
@@ -300,10 +306,12 @@ static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
 static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
 				struct page_cgroup *pc)
 {
-	int lru = LRU_INACTIVE;
+	int lru = LRU_BASE;
 
 	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
 		lru += LRU_ACTIVE;
+	if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+		lru += LRU_FILE;
 
 	MEM_CGROUP_ZSTAT(mz, lru) += 1;
 	list_add(&pc->lru, &mz->lists[lru]);
@@ -314,10 +322,9 @@ static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
 static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
 {
 	struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
-	int lru = LRU_INACTIVE;
-
-	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
-		lru += LRU_ACTIVE;
+	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+	int file = pc->flags & PAGE_CGROUP_FLAG_FILE;
+	int lru = LRU_FILE * !!file + !!from;
 
 	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
 
@@ -326,7 +333,7 @@ static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
 	else
 		pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
 
-	lru = !!active;
+	lru = LRU_FILE * !!file + !!active;
 	MEM_CGROUP_ZSTAT(mz, lru) += 1;
 	list_move(&pc->lru, &mz->lists[lru]);
 }
@@ -390,21 +397,6 @@ int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
 	return (int)((rss * 100L) / total);
 }
 
-/*
- * This function is called from vmscan.c. In page reclaiming loop. balance
- * between active and inactive list is calculated. For memory controller
- * page reclaiming, we should use using mem_cgroup's imbalance rather than
- * zone's global lru imbalance.
- */
-long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
-{
-	unsigned long active, inactive;
-	/* active and inactive are the number of pages. 'long' is ok.*/
-	active = mem_cgroup_get_all_zonestat(mem, LRU_ACTIVE);
-	inactive = mem_cgroup_get_all_zonestat(mem, LRU_INACTIVE);
-	return (long) (active / (inactive + 1));
-}
-
 /*
  * prev_priority control...this will be used in memory reclaim path.
  */
@@ -450,7 +442,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					unsigned long *scanned, int order,
 					int mode, struct zone *z,
 					struct mem_cgroup *mem_cont,
-					int active)
+					int active, int file)
 {
 	unsigned long nr_taken = 0;
 	struct page *page;
@@ -461,7 +453,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 	int nid = z->zone_pgdat->node_id;
 	int zid = zone_idx(z);
 	struct mem_cgroup_per_zone *mz;
-	int lru = !!active;
+	int lru = LRU_FILE * !!file + !!active;
 
 	BUG_ON(!mem_cont);
 	mz = mem_cgroup_zoneinfo(mem_cont, nid, zid);
@@ -477,6 +469,9 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 		if (unlikely(!PageLRU(page)))
 			continue;
 
+		/*
+		 * TODO: play better with lumpy reclaim, grabbing anything.
+		 */
 		if (PageActive(page) && !active) {
 			__mem_cgroup_move_lists(pc, true);
 			continue;
@@ -489,7 +484,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 		scan++;
 		list_move(&pc->lru, &pc_list);
 
-		if (__isolate_lru_page(page, mode) == 0) {
+		if (__isolate_lru_page(page, mode, file) == 0) {
 			list_move(&page->lru, dst);
 			nr_taken++;
 		}
@@ -575,10 +570,16 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 	 * If a page is accounted as a page cache, insert to inactive list.
 	 * If anon, insert to active list.
 	 */
-	if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE)
+	if (ctype == MEM_CGROUP_CHARGE_TYPE_CACHE) {
 		pc->flags = PAGE_CGROUP_FLAG_CACHE;
-	else
+		if (page_is_file_cache(page))
+			pc->flags |= PAGE_CGROUP_FLAG_FILE;
+		else
+			pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
+	} else if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
 		pc->flags = PAGE_CGROUP_FLAG_ACTIVE;
+	else /* MEM_CGROUP_CHARGE_TYPE_SHMEM */
+		pc->flags = PAGE_CGROUP_FLAG_CACHE | PAGE_CGROUP_FLAG_ACTIVE;
 
 	lock_page_cgroup(page);
 	if (unlikely(page_get_page_cgroup(page))) {
@@ -737,8 +738,12 @@ int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
 	if (pc) {
 		mem = pc->mem_cgroup;
 		css_get(&mem->css);
-		if (pc->flags & PAGE_CGROUP_FLAG_CACHE)
-			ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+		if (pc->flags & PAGE_CGROUP_FLAG_CACHE) {
+			if (page_is_file_cache(page))
+				ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
+			else
+				ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
+		}
 	}
 	unlock_page_cgroup(page);
 	if (mem) {
@@ -982,14 +987,21 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 	}
 	/* showing # of active pages */
 	{
-		unsigned long active, inactive;
-
-		inactive = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_INACTIVE);
-		active = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_ACTIVE);
-		cb->fill(cb, "active", (active) * PAGE_SIZE);
-		cb->fill(cb, "inactive", (inactive) * PAGE_SIZE);
+		unsigned long active_anon, inactive_anon;
+		unsigned long active_file, inactive_file;
+
+		inactive_anon = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_INACTIVE_ANON);
+		active_anon = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_ACTIVE_ANON);
+		inactive_file = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_INACTIVE_FILE);
+		active_file = mem_cgroup_get_all_zonestat(mem_cont,
+						LRU_ACTIVE_FILE);
+		cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE);
+		cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE);
+		cb->fill(cb, "active_file", (active_file) * PAGE_SIZE);
+		cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE);
 	}
 	return 0;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 7512933dcc10..71cdefd1ef14 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1889,7 +1889,7 @@ gotten:
 		set_pte_at(mm, address, page_table, entry);
 		update_mmu_cache(vma, address, entry);
 		SetPageSwapBacked(new_page);
-		lru_cache_add_active(new_page);
+		lru_cache_add_active_anon(new_page);
 		page_add_new_anon_rmap(new_page, vma, address);
 
 		if (old_page) {
@@ -2384,7 +2384,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto release;
 	inc_mm_counter(mm, anon_rss);
 	SetPageSwapBacked(page);
-	lru_cache_add_active(page);
+	lru_cache_add_active_anon(page);
 	page_add_new_anon_rmap(page, vma, address);
 	set_pte_at(mm, address, page_table, entry);
 
@@ -2526,7 +2526,7 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		if (anon) {
                         inc_mm_counter(mm, anon_rss);
 			SetPageSwapBacked(page);
-                        lru_cache_add_active(page);
+                        lru_cache_add_active_anon(page);
                         page_add_new_anon_rmap(page, vma, address);
 		} else {
 			inc_mm_counter(mm, file_rss);
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index b40f6d5f8fe9..2970e35fd03f 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -329,9 +329,7 @@ static unsigned long highmem_dirtyable_memory(unsigned long total)
 		struct zone *z =
 			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
 
-		x += zone_page_state(z, NR_FREE_PAGES)
-			+ zone_page_state(z, NR_INACTIVE)
-			+ zone_page_state(z, NR_ACTIVE);
+		x += zone_page_state(z, NR_FREE_PAGES) + zone_lru_pages(z);
 	}
 	/*
 	 * Make sure that the number of highmem pages is never larger
@@ -355,9 +353,7 @@ unsigned long determine_dirtyable_memory(void)
 {
 	unsigned long x;
 
-	x = global_page_state(NR_FREE_PAGES)
-		+ global_page_state(NR_INACTIVE)
-		+ global_page_state(NR_ACTIVE);
+	x = global_page_state(NR_FREE_PAGES) + global_lru_pages();
 
 	if (!vm_highmem_is_dirtyable)
 		x -= highmem_dirtyable_memory(x);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2099904d6cc4..740a16a32c22 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1864,10 +1864,13 @@ void show_free_areas(void)
 		}
 	}
 
-	printk("Active:%lu inactive:%lu dirty:%lu writeback:%lu unstable:%lu\n"
+	printk("Active_anon:%lu active_file:%lu inactive_anon%lu\n"
+		" inactive_file:%lu dirty:%lu writeback:%lu unstable:%lu\n"
 		" free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n",
-		global_page_state(NR_ACTIVE),
-		global_page_state(NR_INACTIVE),
+		global_page_state(NR_ACTIVE_ANON),
+		global_page_state(NR_ACTIVE_FILE),
+		global_page_state(NR_INACTIVE_ANON),
+		global_page_state(NR_INACTIVE_FILE),
 		global_page_state(NR_FILE_DIRTY),
 		global_page_state(NR_WRITEBACK),
 		global_page_state(NR_UNSTABLE_NFS),
@@ -1890,8 +1893,10 @@ void show_free_areas(void)
 			" min:%lukB"
 			" low:%lukB"
 			" high:%lukB"
-			" active:%lukB"
-			" inactive:%lukB"
+			" active_anon:%lukB"
+			" inactive_anon:%lukB"
+			" active_file:%lukB"
+			" inactive_file:%lukB"
 			" present:%lukB"
 			" pages_scanned:%lu"
 			" all_unreclaimable? %s"
@@ -1901,8 +1906,10 @@ void show_free_areas(void)
 			K(zone->pages_min),
 			K(zone->pages_low),
 			K(zone->pages_high),
-			K(zone_page_state(zone, NR_ACTIVE)),
-			K(zone_page_state(zone, NR_INACTIVE)),
+			K(zone_page_state(zone, NR_ACTIVE_ANON)),
+			K(zone_page_state(zone, NR_INACTIVE_ANON)),
+			K(zone_page_state(zone, NR_ACTIVE_FILE)),
+			K(zone_page_state(zone, NR_INACTIVE_FILE)),
 			K(zone->present_pages),
 			zone->pages_scanned,
 			(zone_is_all_unreclaimable(zone) ? "yes" : "no")
@@ -3472,6 +3479,10 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 			INIT_LIST_HEAD(&zone->lru[l].list);
 			zone->lru[l].nr_scan = 0;
 		}
+		zone->recent_rotated[0] = 0;
+		zone->recent_rotated[1] = 0;
+		zone->recent_scanned[0] = 0;
+		zone->recent_scanned[1] = 0;
 		zap_zone_vm_stats(zone);
 		zone->flags = 0;
 		if (!size)
diff --git a/mm/readahead.c b/mm/readahead.c
index 6cbd9a72fde2..bec83c15a78f 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -229,7 +229,7 @@ int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
  */
 unsigned long max_sane_readahead(unsigned long nr)
 {
-	return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE)
+	return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE_FILE)
 		+ node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2);
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index fd421ed703ed..fc2ccf79a776 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -199,7 +199,7 @@ static struct vm_operations_struct shmem_vm_ops;
 
 static struct backing_dev_info shmem_backing_dev_info  __read_mostly = {
 	.ra_pages	= 0,	/* No readahead */
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
 	.unplug_io_fn	= default_unplug_io_fn,
 };
 
diff --git a/mm/swap.c b/mm/swap.c
index 88a394872677..0b1974a08974 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -116,7 +116,8 @@ static void pagevec_move_tail(struct pagevec *pvec)
 			spin_lock(&zone->lru_lock);
 		}
 		if (PageLRU(page) && !PageActive(page)) {
-			list_move_tail(&page->lru, &zone->lru[LRU_INACTIVE].list);
+			int lru = page_is_file_cache(page);
+			list_move_tail(&page->lru, &zone->lru[lru].list);
 			pgmoved++;
 		}
 	}
@@ -157,11 +158,18 @@ void activate_page(struct page *page)
 
 	spin_lock_irq(&zone->lru_lock);
 	if (PageLRU(page) && !PageActive(page)) {
-		del_page_from_inactive_list(zone, page);
+		int file = page_is_file_cache(page);
+		int lru = LRU_BASE + file;
+		del_page_from_lru_list(zone, page, lru);
+
 		SetPageActive(page);
-		add_page_to_active_list(zone, page);
+		lru += LRU_ACTIVE;
+		add_page_to_lru_list(zone, page, lru);
 		__count_vm_event(PGACTIVATE);
 		mem_cgroup_move_lists(page, true);
+
+		zone->recent_rotated[!!file]++;
+		zone->recent_scanned[!!file]++;
 	}
 	spin_unlock_irq(&zone->lru_lock);
 }
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 7a3ece0b5a3b..ea62084ed402 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -33,7 +33,7 @@ static const struct address_space_operations swap_aops = {
 };
 
 static struct backing_dev_info swap_backing_dev_info = {
-	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
+	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
 	.unplug_io_fn	= swap_unplug_io_fn,
 };
 
@@ -310,7 +310,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			/*
 			 * Initiate read into locked page and return.
 			 */
-			lru_cache_add_active(new_page);
+			lru_cache_add_active_anon(new_page);
 			swap_readpage(NULL, new_page);
 			return new_page;
 		}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e656035d3406..d10d2f9a33f3 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -78,7 +78,7 @@ struct scan_control {
 	unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst,
 			unsigned long *scanned, int order, int mode,
 			struct zone *z, struct mem_cgroup *mem_cont,
-			int active);
+			int active, int file);
 };
 
 #define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
@@ -680,7 +680,7 @@ keep:
  *
  * returns 0 on success, -ve errno on failure.
  */
-int __isolate_lru_page(struct page *page, int mode)
+int __isolate_lru_page(struct page *page, int mode, int file)
 {
 	int ret = -EINVAL;
 
@@ -696,6 +696,9 @@ int __isolate_lru_page(struct page *page, int mode)
 	if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode))
 		return ret;
 
+	if (mode != ISOLATE_BOTH && (!page_is_file_cache(page) != !file))
+		return ret;
+
 	ret = -EBUSY;
 	if (likely(get_page_unless_zero(page))) {
 		/*
@@ -726,12 +729,13 @@ int __isolate_lru_page(struct page *page, int mode)
  * @scanned:	The number of pages that were scanned.
  * @order:	The caller's attempted allocation order
  * @mode:	One of the LRU isolation modes
+ * @file:	True [1] if isolating file [!anon] pages
  *
  * returns how many pages were moved onto *@dst.
  */
 static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		struct list_head *src, struct list_head *dst,
-		unsigned long *scanned, int order, int mode)
+		unsigned long *scanned, int order, int mode, int file)
 {
 	unsigned long nr_taken = 0;
 	unsigned long scan;
@@ -748,7 +752,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 		VM_BUG_ON(!PageLRU(page));
 
-		switch (__isolate_lru_page(page, mode)) {
+		switch (__isolate_lru_page(page, mode, file)) {
 		case 0:
 			list_move(&page->lru, dst);
 			nr_taken++;
@@ -791,10 +795,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 				break;
 
 			cursor_page = pfn_to_page(pfn);
+
 			/* Check that we have not crossed a zone boundary. */
 			if (unlikely(page_zone_id(cursor_page) != zone_id))
 				continue;
-			switch (__isolate_lru_page(cursor_page, mode)) {
+			switch (__isolate_lru_page(cursor_page, mode, file)) {
 			case 0:
 				list_move(&cursor_page->lru, dst);
 				nr_taken++;
@@ -819,30 +824,37 @@ static unsigned long isolate_pages_global(unsigned long nr,
 					unsigned long *scanned, int order,
 					int mode, struct zone *z,
 					struct mem_cgroup *mem_cont,
-					int active)
+					int active, int file)
 {
+	int lru = LRU_BASE;
 	if (active)
-		return isolate_lru_pages(nr, &z->lru[LRU_ACTIVE].list, dst,
-						scanned, order, mode);
-	else
-		return isolate_lru_pages(nr, &z->lru[LRU_INACTIVE].list, dst,
-						scanned, order, mode);
+		lru += LRU_ACTIVE;
+	if (file)
+		lru += LRU_FILE;
+	return isolate_lru_pages(nr, &z->lru[lru].list, dst, scanned, order,
+								mode, !!file);
 }
 
 /*
  * clear_active_flags() is a helper for shrink_active_list(), clearing
  * any active bits from the pages in the list.
  */
-static unsigned long clear_active_flags(struct list_head *page_list)
+static unsigned long clear_active_flags(struct list_head *page_list,
+					unsigned int *count)
 {
 	int nr_active = 0;
+	int lru;
 	struct page *page;
 
-	list_for_each_entry(page, page_list, lru)
+	list_for_each_entry(page, page_list, lru) {
+		lru = page_is_file_cache(page);
 		if (PageActive(page)) {
+			lru += LRU_ACTIVE;
 			ClearPageActive(page);
 			nr_active++;
 		}
+		count[lru]++;
+	}
 
 	return nr_active;
 }
@@ -880,12 +892,12 @@ int isolate_lru_page(struct page *page)
 
 		spin_lock_irq(&zone->lru_lock);
 		if (PageLRU(page) && get_page_unless_zero(page)) {
+			int lru = LRU_BASE;
 			ret = 0;
 			ClearPageLRU(page);
-			if (PageActive(page))
-				del_page_from_active_list(zone, page);
-			else
-				del_page_from_inactive_list(zone, page);
+
+			lru += page_is_file_cache(page) + !!PageActive(page);
+			del_page_from_lru_list(zone, page, lru);
 		}
 		spin_unlock_irq(&zone->lru_lock);
 	}
@@ -897,7 +909,7 @@ int isolate_lru_page(struct page *page)
  * of reclaimed pages
  */
 static unsigned long shrink_inactive_list(unsigned long max_scan,
-				struct zone *zone, struct scan_control *sc)
+			struct zone *zone, struct scan_control *sc, int file)
 {
 	LIST_HEAD(page_list);
 	struct pagevec pvec;
@@ -914,20 +926,32 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		unsigned long nr_scan;
 		unsigned long nr_freed;
 		unsigned long nr_active;
+		unsigned int count[NR_LRU_LISTS] = { 0, };
+		int mode = (sc->order > PAGE_ALLOC_COSTLY_ORDER) ?
+					ISOLATE_BOTH : ISOLATE_INACTIVE;
 
 		nr_taken = sc->isolate_pages(sc->swap_cluster_max,
-			     &page_list, &nr_scan, sc->order,
-			     (sc->order > PAGE_ALLOC_COSTLY_ORDER)?
-					     ISOLATE_BOTH : ISOLATE_INACTIVE,
-				zone, sc->mem_cgroup, 0);
-		nr_active = clear_active_flags(&page_list);
+			     &page_list, &nr_scan, sc->order, mode,
+				zone, sc->mem_cgroup, 0, file);
+		nr_active = clear_active_flags(&page_list, count);
 		__count_vm_events(PGDEACTIVATE, nr_active);
 
-		__mod_zone_page_state(zone, NR_ACTIVE, -nr_active);
-		__mod_zone_page_state(zone, NR_INACTIVE,
-						-(nr_taken - nr_active));
-		if (scan_global_lru(sc))
+		__mod_zone_page_state(zone, NR_ACTIVE_FILE,
+						-count[LRU_ACTIVE_FILE]);
+		__mod_zone_page_state(zone, NR_INACTIVE_FILE,
+						-count[LRU_INACTIVE_FILE]);
+		__mod_zone_page_state(zone, NR_ACTIVE_ANON,
+						-count[LRU_ACTIVE_ANON]);
+		__mod_zone_page_state(zone, NR_INACTIVE_ANON,
+						-count[LRU_INACTIVE_ANON]);
+
+		if (scan_global_lru(sc)) {
 			zone->pages_scanned += nr_scan;
+			zone->recent_scanned[0] += count[LRU_INACTIVE_ANON];
+			zone->recent_scanned[0] += count[LRU_ACTIVE_ANON];
+			zone->recent_scanned[1] += count[LRU_INACTIVE_FILE];
+			zone->recent_scanned[1] += count[LRU_ACTIVE_FILE];
+		}
 		spin_unlock_irq(&zone->lru_lock);
 
 		nr_scanned += nr_scan;
@@ -947,7 +971,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 			 * The attempt at page out may have made some
 			 * of the pages active, mark them inactive again.
 			 */
-			nr_active = clear_active_flags(&page_list);
+			nr_active = clear_active_flags(&page_list, count);
 			count_vm_events(PGDEACTIVATE, nr_active);
 
 			nr_freed += shrink_page_list(&page_list, sc,
@@ -977,6 +1001,10 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 			SetPageLRU(page);
 			list_del(&page->lru);
 			add_page_to_lru_list(zone, page, page_lru(page));
+			if (PageActive(page) && scan_global_lru(sc)) {
+				int file = !!page_is_file_cache(page);
+				zone->recent_rotated[file]++;
+			}
 			if (!pagevec_add(&pvec, page)) {
 				spin_unlock_irq(&zone->lru_lock);
 				__pagevec_release(&pvec);
@@ -1007,115 +1035,7 @@ static inline void note_zone_scanning_priority(struct zone *zone, int priority)
 
 static inline int zone_is_near_oom(struct zone *zone)
 {
-	return zone->pages_scanned >= (zone_page_state(zone, NR_ACTIVE)
-				+ zone_page_state(zone, NR_INACTIVE))*3;
-}
-
-/*
- * Determine we should try to reclaim mapped pages.
- * This is called only when sc->mem_cgroup is NULL.
- */
-static int calc_reclaim_mapped(struct scan_control *sc, struct zone *zone,
-				int priority)
-{
-	long mapped_ratio;
-	long distress;
-	long swap_tendency;
-	long imbalance;
-	int reclaim_mapped = 0;
-	int prev_priority;
-
-	if (scan_global_lru(sc) && zone_is_near_oom(zone))
-		return 1;
-	/*
-	 * `distress' is a measure of how much trouble we're having
-	 * reclaiming pages.  0 -> no problems.  100 -> great trouble.
-	 */
-	if (scan_global_lru(sc))
-		prev_priority = zone->prev_priority;
-	else
-		prev_priority = mem_cgroup_get_reclaim_priority(sc->mem_cgroup);
-
-	distress = 100 >> min(prev_priority, priority);
-
-	/*
-	 * The point of this algorithm is to decide when to start
-	 * reclaiming mapped memory instead of just pagecache.  Work out
-	 * how much memory
-	 * is mapped.
-	 */
-	if (scan_global_lru(sc))
-		mapped_ratio = ((global_page_state(NR_FILE_MAPPED) +
-				global_page_state(NR_ANON_PAGES)) * 100) /
-					vm_total_pages;
-	else
-		mapped_ratio = mem_cgroup_calc_mapped_ratio(sc->mem_cgroup);
-
-	/*
-	 * Now decide how much we really want to unmap some pages.  The
-	 * mapped ratio is downgraded - just because there's a lot of
-	 * mapped memory doesn't necessarily mean that page reclaim
-	 * isn't succeeding.
-	 *
-	 * The distress ratio is important - we don't want to start
-	 * going oom.
-	 *
-	 * A 100% value of vm_swappiness overrides this algorithm
-	 * altogether.
-	 */
-	swap_tendency = mapped_ratio / 2 + distress + sc->swappiness;
-
-	/*
-	 * If there's huge imbalance between active and inactive
-	 * (think active 100 times larger than inactive) we should
-	 * become more permissive, or the system will take too much
-	 * cpu before it start swapping during memory pressure.
-	 * Distress is about avoiding early-oom, this is about
-	 * making swappiness graceful despite setting it to low
-	 * values.
-	 *
-	 * Avoid div by zero with nr_inactive+1, and max resulting
-	 * value is vm_total_pages.
-	 */
-	if (scan_global_lru(sc)) {
-		imbalance  = zone_page_state(zone, NR_ACTIVE);
-		imbalance /= zone_page_state(zone, NR_INACTIVE) + 1;
-	} else
-		imbalance = mem_cgroup_reclaim_imbalance(sc->mem_cgroup);
-
-	/*
-	 * Reduce the effect of imbalance if swappiness is low,
-	 * this means for a swappiness very low, the imbalance
-	 * must be much higher than 100 for this logic to make
-	 * the difference.
-	 *
-	 * Max temporary value is vm_total_pages*100.
-	 */
-	imbalance *= (vm_swappiness + 1);
-	imbalance /= 100;
-
-	/*
-	 * If not much of the ram is mapped, makes the imbalance
-	 * less relevant, it's high priority we refill the inactive
-	 * list with mapped pages only in presence of high ratio of
-	 * mapped pages.
-	 *
-	 * Max temporary value is vm_total_pages*100.
-	 */
-	imbalance *= mapped_ratio;
-	imbalance /= 100;
-
-	/* apply imbalance feedback to swap_tendency */
-	swap_tendency += imbalance;
-
-	/*
-	 * Now use this metric to decide whether to start moving mapped
-	 * memory onto the inactive list.
-	 */
-	if (swap_tendency >= 100)
-		reclaim_mapped = 1;
-
-	return reclaim_mapped;
+	return zone->pages_scanned >= (zone_lru_pages(zone) * 3);
 }
 
 /*
@@ -1138,7 +1058,7 @@ static int calc_reclaim_mapped(struct scan_control *sc, struct zone *zone,
 
 
 static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
-				struct scan_control *sc, int priority)
+			struct scan_control *sc, int priority, int file)
 {
 	unsigned long pgmoved;
 	int pgdeactivate = 0;
@@ -1148,43 +1068,42 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	LIST_HEAD(l_inactive);
 	struct page *page;
 	struct pagevec pvec;
-	int reclaim_mapped = 0;
-
-	if (sc->may_swap)
-		reclaim_mapped = calc_reclaim_mapped(sc, zone, priority);
+	enum lru_list lru;
 
 	lru_add_drain();
 	spin_lock_irq(&zone->lru_lock);
 	pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
 					ISOLATE_ACTIVE, zone,
-					sc->mem_cgroup, 1);
+					sc->mem_cgroup, 1, file);
 	/*
 	 * zone->pages_scanned is used for detect zone's oom
 	 * mem_cgroup remembers nr_scan by itself.
 	 */
-	if (scan_global_lru(sc))
+	if (scan_global_lru(sc)) {
 		zone->pages_scanned += pgscanned;
+		zone->recent_scanned[!!file] += pgmoved;
+	}
 
-	__mod_zone_page_state(zone, NR_ACTIVE, -pgmoved);
+	if (file)
+		__mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
+	else
+		__mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved);
 	spin_unlock_irq(&zone->lru_lock);
 
 	while (!list_empty(&l_hold)) {
 		cond_resched();
 		page = lru_to_page(&l_hold);
 		list_del(&page->lru);
-		if (page_mapped(page)) {
-			if (!reclaim_mapped ||
-			    (total_swap_pages == 0 && PageAnon(page)) ||
-			    page_referenced(page, 0, sc->mem_cgroup)) {
-				list_add(&page->lru, &l_active);
-				continue;
-			}
-		}
 		list_add(&page->lru, &l_inactive);
 	}
 
+	/*
+	 * Now put the pages back on the appropriate [file or anon] inactive
+	 * and active lists.
+	 */
 	pagevec_init(&pvec, 1);
 	pgmoved = 0;
+	lru = LRU_BASE + file * LRU_FILE;
 	spin_lock_irq(&zone->lru_lock);
 	while (!list_empty(&l_inactive)) {
 		page = lru_to_page(&l_inactive);
@@ -1194,11 +1113,11 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		VM_BUG_ON(!PageActive(page));
 		ClearPageActive(page);
 
-		list_move(&page->lru, &zone->lru[LRU_INACTIVE].list);
+		list_move(&page->lru, &zone->lru[lru].list);
 		mem_cgroup_move_lists(page, false);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
-			__mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
+			__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
 			spin_unlock_irq(&zone->lru_lock);
 			pgdeactivate += pgmoved;
 			pgmoved = 0;
@@ -1208,7 +1127,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 			spin_lock_irq(&zone->lru_lock);
 		}
 	}
-	__mod_zone_page_state(zone, NR_INACTIVE, pgmoved);
+	__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
 	pgdeactivate += pgmoved;
 	if (buffer_heads_over_limit) {
 		spin_unlock_irq(&zone->lru_lock);
@@ -1217,6 +1136,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	}
 
 	pgmoved = 0;
+	lru = LRU_ACTIVE + file * LRU_FILE;
 	while (!list_empty(&l_active)) {
 		page = lru_to_page(&l_active);
 		prefetchw_prev_lru_page(page, &l_active, flags);
@@ -1224,11 +1144,11 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		SetPageLRU(page);
 		VM_BUG_ON(!PageActive(page));
 
-		list_move(&page->lru, &zone->lru[LRU_ACTIVE].list);
+		list_move(&page->lru, &zone->lru[lru].list);
 		mem_cgroup_move_lists(page, true);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
-			__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
+			__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
 			pgmoved = 0;
 			spin_unlock_irq(&zone->lru_lock);
 			if (vm_swap_full())
@@ -1237,7 +1157,8 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 			spin_lock_irq(&zone->lru_lock);
 		}
 	}
-	__mod_zone_page_state(zone, NR_ACTIVE, pgmoved);
+	__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
+	zone->recent_rotated[!!file] += pgmoved;
 
 	__count_zone_vm_events(PGREFILL, zone, pgscanned);
 	__count_vm_events(PGDEACTIVATE, pgdeactivate);
@@ -1248,16 +1169,103 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	pagevec_release(&pvec);
 }
 
-static unsigned long shrink_list(enum lru_list l, unsigned long nr_to_scan,
+static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 	struct zone *zone, struct scan_control *sc, int priority)
 {
-	if (l == LRU_ACTIVE) {
-		shrink_active_list(nr_to_scan, zone, sc, priority);
+	int file = is_file_lru(lru);
+
+	if (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE) {
+		shrink_active_list(nr_to_scan, zone, sc, priority, file);
 		return 0;
 	}
-	return shrink_inactive_list(nr_to_scan, zone, sc);
+	return shrink_inactive_list(nr_to_scan, zone, sc, file);
+}
+
+/*
+ * Determine how aggressively the anon and file LRU lists should be
+ * scanned.  The relative value of each set of LRU lists is determined
+ * by looking at the fraction of the pages scanned we did rotate back
+ * onto the active list instead of evict.
+ *
+ * percent[0] specifies how much pressure to put on ram/swap backed
+ * memory, while percent[1] determines pressure on the file LRUs.
+ */
+static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
+					unsigned long *percent)
+{
+	unsigned long anon, file, free;
+	unsigned long anon_prio, file_prio;
+	unsigned long ap, fp;
+
+	anon  = zone_page_state(zone, NR_ACTIVE_ANON) +
+		zone_page_state(zone, NR_INACTIVE_ANON);
+	file  = zone_page_state(zone, NR_ACTIVE_FILE) +
+		zone_page_state(zone, NR_INACTIVE_FILE);
+	free  = zone_page_state(zone, NR_FREE_PAGES);
+
+	/* If we have no swap space, do not bother scanning anon pages. */
+	if (nr_swap_pages <= 0) {
+		percent[0] = 0;
+		percent[1] = 100;
+		return;
+	}
+
+	/* If we have very few page cache pages, force-scan anon pages. */
+	if (unlikely(file + free <= zone->pages_high)) {
+		percent[0] = 100;
+		percent[1] = 0;
+		return;
+	}
+
+	/*
+	 * OK, so we have swap space and a fair amount of page cache
+	 * pages.  We use the recently rotated / recently scanned
+	 * ratios to determine how valuable each cache is.
+	 *
+	 * Because workloads change over time (and to avoid overflow)
+	 * we keep these statistics as a floating average, which ends
+	 * up weighing recent references more than old ones.
+	 *
+	 * anon in [0], file in [1]
+	 */
+	if (unlikely(zone->recent_scanned[0] > anon / 4)) {
+		spin_lock_irq(&zone->lru_lock);
+		zone->recent_scanned[0] /= 2;
+		zone->recent_rotated[0] /= 2;
+		spin_unlock_irq(&zone->lru_lock);
+	}
+
+	if (unlikely(zone->recent_scanned[1] > file / 4)) {
+		spin_lock_irq(&zone->lru_lock);
+		zone->recent_scanned[1] /= 2;
+		zone->recent_rotated[1] /= 2;
+		spin_unlock_irq(&zone->lru_lock);
+	}
+
+	/*
+	 * With swappiness at 100, anonymous and file have the same priority.
+	 * This scanning priority is essentially the inverse of IO cost.
+	 */
+	anon_prio = sc->swappiness;
+	file_prio = 200 - sc->swappiness;
+
+	/*
+	 *                  anon       recent_rotated[0]
+	 * %anon = 100 * ----------- / ----------------- * IO cost
+	 *               anon + file      rotate_sum
+	 */
+	ap = (anon_prio + 1) * (zone->recent_scanned[0] + 1);
+	ap /= zone->recent_rotated[0] + 1;
+
+	fp = (file_prio + 1) * (zone->recent_scanned[1] + 1);
+	fp /= zone->recent_rotated[1] + 1;
+
+	/* Normalize to percentages */
+	percent[0] = 100 * ap / (ap + fp + 1);
+	percent[1] = 100 - percent[0];
 }
 
+
 /*
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
  */
@@ -1267,36 +1275,43 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 	unsigned long nr[NR_LRU_LISTS];
 	unsigned long nr_to_scan;
 	unsigned long nr_reclaimed = 0;
+	unsigned long percent[2];	/* anon @ 0; file @ 1 */
 	enum lru_list l;
 
-	if (scan_global_lru(sc)) {
-		/*
-		 * Add one to nr_to_scan just to make sure that the kernel
-		 * will slowly sift through the active list.
-		 */
-		for_each_lru(l) {
-			zone->lru[l].nr_scan += (zone_page_state(zone,
-					NR_LRU_BASE + l)  >> priority) + 1;
+	get_scan_ratio(zone, sc, percent);
+
+	for_each_lru(l) {
+		if (scan_global_lru(sc)) {
+			int file = is_file_lru(l);
+			int scan;
+			/*
+			 * Add one to nr_to_scan just to make sure that the
+			 * kernel will slowly sift through each list.
+			 */
+			scan = zone_page_state(zone, NR_LRU_BASE + l);
+			if (priority) {
+				scan >>= priority;
+				scan = (scan * percent[file]) / 100;
+			}
+			zone->lru[l].nr_scan += scan + 1;
 			nr[l] = zone->lru[l].nr_scan;
 			if (nr[l] >= sc->swap_cluster_max)
 				zone->lru[l].nr_scan = 0;
 			else
 				nr[l] = 0;
+		} else {
+			/*
+			 * This reclaim occurs not because zone memory shortage
+			 * but because memory controller hits its limit.
+			 * Don't modify zone reclaim related data.
+			 */
+			nr[l] = mem_cgroup_calc_reclaim(sc->mem_cgroup, zone,
+								priority, l);
 		}
-	} else {
-		/*
-		 * This reclaim occurs not because zone memory shortage but
-		 * because memory controller hits its limit.
-		 * Then, don't modify zone reclaim related data.
-		 */
-		nr[LRU_ACTIVE] = mem_cgroup_calc_reclaim(sc->mem_cgroup,
-					zone, priority, LRU_ACTIVE);
-
-		nr[LRU_INACTIVE] = mem_cgroup_calc_reclaim(sc->mem_cgroup,
-					zone, priority, LRU_INACTIVE);
 	}
 
-	while (nr[LRU_ACTIVE] || nr[LRU_INACTIVE]) {
+	while (nr[LRU_ACTIVE_ANON] || nr[LRU_INACTIVE_ANON] ||
+			nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) {
 		for_each_lru(l) {
 			if (nr[l]) {
 				nr_to_scan = min(nr[l],
@@ -1369,7 +1384,7 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
 
 	return nr_reclaimed;
 }
- 
+
 /*
  * This is the main entry point to direct page reclaim.
  *
@@ -1412,8 +1427,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 				continue;
 
-			lru_pages += zone_page_state(zone, NR_ACTIVE)
-					+ zone_page_state(zone, NR_INACTIVE);
+			lru_pages += zone_lru_pages(zone);
 		}
 	}
 
@@ -1615,8 +1629,7 @@ loop_again:
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 
-			lru_pages += zone_page_state(zone, NR_ACTIVE)
-					+ zone_page_state(zone, NR_INACTIVE);
+			lru_pages += zone_lru_pages(zone);
 		}
 
 		/*
@@ -1660,8 +1673,7 @@ loop_again:
 			if (zone_is_all_unreclaimable(zone))
 				continue;
 			if (nr_slab == 0 && zone->pages_scanned >=
-				(zone_page_state(zone, NR_ACTIVE)
-				+ zone_page_state(zone, NR_INACTIVE)) * 6)
+						(zone_lru_pages(zone) * 6))
 					zone_set_flag(zone,
 						      ZONE_ALL_UNRECLAIMABLE);
 			/*
@@ -1715,7 +1727,7 @@ out:
 
 /*
  * The background pageout daemon, started as a kernel thread
- * from the init process. 
+ * from the init process.
  *
  * This basically trickles out pages so that we have _some_
  * free memory available even if there is no other activity
@@ -1809,6 +1821,14 @@ void wakeup_kswapd(struct zone *zone, int order)
 	wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
+unsigned long global_lru_pages(void)
+{
+	return global_page_state(NR_ACTIVE_ANON)
+		+ global_page_state(NR_ACTIVE_FILE)
+		+ global_page_state(NR_INACTIVE_ANON)
+		+ global_page_state(NR_INACTIVE_FILE);
+}
+
 #ifdef CONFIG_PM
 /*
  * Helper function for shrink_all_memory().  Tries to reclaim 'nr_pages' pages
@@ -1834,7 +1854,8 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 
 		for_each_lru(l) {
 			/* For pass = 0 we don't shrink the active list */
-			if (pass == 0 && l == LRU_ACTIVE)
+			if (pass == 0 &&
+				(l == LRU_ACTIVE || l == LRU_ACTIVE_FILE))
 				continue;
 
 			zone->lru[l].nr_scan +=
@@ -1856,11 +1877,6 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 	return ret;
 }
 
-static unsigned long count_lru_pages(void)
-{
-	return global_page_state(NR_ACTIVE) + global_page_state(NR_INACTIVE);
-}
-
 /*
  * Try to free `nr_pages' of memory, system-wide, and return the number of
  * freed pages.
@@ -1886,7 +1902,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 
 	current->reclaim_state = &reclaim_state;
 
-	lru_pages = count_lru_pages();
+	lru_pages = global_lru_pages();
 	nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
 	/* If slab caches are huge, it's better to hit them first */
 	while (nr_slab >= lru_pages) {
@@ -1929,7 +1945,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 
 			reclaim_state.reclaimed_slab = 0;
 			shrink_slab(sc.nr_scanned, sc.gfp_mask,
-					count_lru_pages());
+					global_lru_pages());
 			ret += reclaim_state.reclaimed_slab;
 			if (ret >= nr_pages)
 				goto out;
@@ -1946,7 +1962,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 	if (!ret) {
 		do {
 			reclaim_state.reclaimed_slab = 0;
-			shrink_slab(nr_pages, sc.gfp_mask, count_lru_pages());
+			shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages());
 			ret += reclaim_state.reclaimed_slab;
 		} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
 	}
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 52c0335c1b71..27400b7da7c4 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -619,8 +619,10 @@ const struct seq_operations pagetypeinfo_op = {
 static const char * const vmstat_text[] = {
 	/* Zoned VM counters */
 	"nr_free_pages",
-	"nr_inactive",
-	"nr_active",
+	"nr_inactive_anon",
+	"nr_active_anon",
+	"nr_inactive_file",
+	"nr_active_file",
 	"nr_anon_pages",
 	"nr_mapped",
 	"nr_file_pages",
@@ -688,7 +690,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   "\n        min      %lu"
 		   "\n        low      %lu"
 		   "\n        high     %lu"
-		   "\n        scanned  %lu (a: %lu i: %lu)"
+		   "\n        scanned  %lu (aa: %lu ia: %lu af: %lu if: %lu)"
 		   "\n        spanned  %lu"
 		   "\n        present  %lu",
 		   zone_page_state(zone, NR_FREE_PAGES),
@@ -696,8 +698,10 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   zone->pages_low,
 		   zone->pages_high,
 		   zone->pages_scanned,
-		   zone->lru[LRU_ACTIVE].nr_scan,
-		   zone->lru[LRU_INACTIVE].nr_scan,
+		   zone->lru[LRU_ACTIVE_ANON].nr_scan,
+		   zone->lru[LRU_INACTIVE_ANON].nr_scan,
+		   zone->lru[LRU_ACTIVE_FILE].nr_scan,
+		   zone->lru[LRU_INACTIVE_FILE].nr_scan,
 		   zone->spanned_pages,
 		   zone->present_pages);
 
-- 
cgit v1.2.3


From 556adecba110bf5f1db6c6b56416cfab5bcab698 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@redhat.com>
Date: Sat, 18 Oct 2008 20:26:34 -0700
Subject: vmscan: second chance replacement for anonymous pages

We avoid evicting and scanning anonymous pages for the most part, but
under some workloads we can end up with most of memory filled with
anonymous pages.  At that point, we suddenly need to clear the referenced
bits on all of memory, which can take ages on very large memory systems.

We can reduce the maximum number of pages that need to be scanned by not
taking the referenced state into account when deactivating an anonymous
page.  After all, every anonymous page starts out referenced, so why
check?

If an anonymous page gets referenced again before it reaches the end of
the inactive list, we move it back to the active list.

To keep the maximum amount of necessary work reasonable, we scale the
active to inactive ratio with the size of memory, using the formula
active:inactive ratio = sqrt(memory in GB * 10).

Kswapd CPU use now seems to scale by the amount of pageout bandwidth,
instead of by the amount of memory present in the system.

[kamezawa.hiroyu@jp.fujitsu.com: fix OOM with memcg]
[kamezawa.hiroyu@jp.fujitsu.com: memcg: lru scan fix]
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm_inline.h | 19 +++++++++++++++++++
 include/linux/mmzone.h    |  6 ++++++
 mm/page_alloc.c           | 41 +++++++++++++++++++++++++++++++++++++++++
 mm/vmscan.c               | 38 ++++++++++++++++++++++++++++++++++----
 mm/vmstat.c               |  6 ++++--
 5 files changed, 104 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 2eb599465d56..f451fedd1e75 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -117,4 +117,23 @@ static inline enum lru_list page_lru(struct page *page)
 	return lru;
 }
 
+/**
+ * inactive_anon_is_low - check if anonymous pages need to be deactivated
+ * @zone: zone to check
+ *
+ * Returns true if the zone does not have enough inactive anon pages,
+ * meaning some active anon pages need to be deactivated.
+ */
+static inline int inactive_anon_is_low(struct zone *zone)
+{
+	unsigned long active, inactive;
+
+	active = zone_page_state(zone, NR_ACTIVE_ANON);
+	inactive = zone_page_state(zone, NR_INACTIVE_ANON);
+
+	if (inactive * zone->inactive_ratio < active)
+		return 1;
+
+	return 0;
+}
 #endif
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 59a4c8fd6ebd..9c5111f49a32 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -323,6 +323,12 @@ struct zone {
 	 */
 	int prev_priority;
 
+	/*
+	 * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
+	 * this zone's LRU.  Maintained by the pageout code.
+	 */
+	unsigned int inactive_ratio;
+
 
 	ZONE_PADDING(_pad2_)
 	/* Rarely used or read-mostly fields */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 740a16a32c22..79c0981b1d32 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4263,6 +4263,46 @@ void setup_per_zone_pages_min(void)
 	calculate_totalreserve_pages();
 }
 
+/**
+ * setup_per_zone_inactive_ratio - called when min_free_kbytes changes.
+ *
+ * The inactive anon list should be small enough that the VM never has to
+ * do too much work, but large enough that each inactive page has a chance
+ * to be referenced again before it is swapped out.
+ *
+ * The inactive_anon ratio is the target ratio of ACTIVE_ANON to
+ * INACTIVE_ANON pages on this zone's LRU, maintained by the
+ * pageout code. A zone->inactive_ratio of 3 means 3:1 or 25% of
+ * the anonymous pages are kept on the inactive list.
+ *
+ * total     target    max
+ * memory    ratio     inactive anon
+ * -------------------------------------
+ *   10MB       1         5MB
+ *  100MB       1        50MB
+ *    1GB       3       250MB
+ *   10GB      10       0.9GB
+ *  100GB      31         3GB
+ *    1TB     101        10GB
+ *   10TB     320        32GB
+ */
+void setup_per_zone_inactive_ratio(void)
+{
+	struct zone *zone;
+
+	for_each_zone(zone) {
+		unsigned int gb, ratio;
+
+		/* Zone size in gigabytes */
+		gb = zone->present_pages >> (30 - PAGE_SHIFT);
+		ratio = int_sqrt(10 * gb);
+		if (!ratio)
+			ratio = 1;
+
+		zone->inactive_ratio = ratio;
+	}
+}
+
 /*
  * Initialise min_free_kbytes.
  *
@@ -4300,6 +4340,7 @@ static int __init init_per_zone_pages_min(void)
 		min_free_kbytes = 65536;
 	setup_per_zone_pages_min();
 	setup_per_zone_lowmem_reserve();
+	setup_per_zone_inactive_ratio();
 	return 0;
 }
 module_init(init_per_zone_pages_min)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d10d2f9a33f3..c82ee9a33cfc 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1090,6 +1090,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		__mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved);
 	spin_unlock_irq(&zone->lru_lock);
 
+	pgmoved = 0;
 	while (!list_empty(&l_hold)) {
 		cond_resched();
 		page = lru_to_page(&l_hold);
@@ -1097,6 +1098,13 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		list_add(&page->lru, &l_inactive);
 	}
 
+	/*
+	 * Count the referenced pages as rotated, even when they are moved
+	 * to the inactive list.  This helps balance scan pressure between
+	 * file and anonymous pages in get_scan_ratio.
+ 	 */
+	zone->recent_rotated[!!file] += pgmoved;
+
 	/*
 	 * Now put the pages back on the appropriate [file or anon] inactive
 	 * and active lists.
@@ -1158,7 +1166,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		}
 	}
 	__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
-	zone->recent_rotated[!!file] += pgmoved;
 
 	__count_zone_vm_events(PGREFILL, zone, pgscanned);
 	__count_vm_events(PGDEACTIVATE, pgdeactivate);
@@ -1174,7 +1181,13 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 {
 	int file = is_file_lru(lru);
 
-	if (lru == LRU_ACTIVE_ANON || lru == LRU_ACTIVE_FILE) {
+	if (lru == LRU_ACTIVE_FILE) {
+		shrink_active_list(nr_to_scan, zone, sc, priority, file);
+		return 0;
+	}
+
+	if (lru == LRU_ACTIVE_ANON &&
+	    (!scan_global_lru(sc) || inactive_anon_is_low(zone))) {
 		shrink_active_list(nr_to_scan, zone, sc, priority, file);
 		return 0;
 	}
@@ -1310,8 +1323,8 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 		}
 	}
 
-	while (nr[LRU_ACTIVE_ANON] || nr[LRU_INACTIVE_ANON] ||
-			nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) {
+	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
+					nr[LRU_INACTIVE_FILE]) {
 		for_each_lru(l) {
 			if (nr[l]) {
 				nr_to_scan = min(nr[l],
@@ -1324,6 +1337,15 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 		}
 	}
 
+	/*
+	 * Even if we did not try to evict anon pages at all, we want to
+	 * rebalance the anon lru active/inactive ratio.
+	 */
+	if (!scan_global_lru(sc) || inactive_anon_is_low(zone))
+		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
+	else if (!scan_global_lru(sc))
+		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
+
 	throttle_vm_writeout(sc->gfp_mask);
 	return nr_reclaimed;
 }
@@ -1617,6 +1639,14 @@ loop_again:
 			    priority != DEF_PRIORITY)
 				continue;
 
+			/*
+			 * Do some background aging of the anon list, to give
+			 * pages a chance to be referenced before reclaiming.
+			 */
+			if (inactive_anon_is_low(zone))
+				shrink_active_list(SWAP_CLUSTER_MAX, zone,
+							&sc, priority, 0);
+
 			if (!zone_watermark_ok(zone, order, zone->pages_high,
 					       0, 0)) {
 				end_zone = i;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 27400b7da7c4..4380b0dba6d9 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -738,10 +738,12 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 	seq_printf(m,
 		   "\n  all_unreclaimable: %u"
 		   "\n  prev_priority:     %i"
-		   "\n  start_pfn:         %lu",
+		   "\n  start_pfn:         %lu"
+		   "\n  inactive_ratio:    %u",
 			   zone_is_all_unreclaimable(zone),
 		   zone->prev_priority,
-		   zone->zone_start_pfn);
+		   zone->zone_start_pfn,
+		   zone->inactive_ratio);
 	seq_putc(m, '\n');
 }
 
-- 
cgit v1.2.3


From 8a7a8544a4f6554ec2d8048ac9f9672f442db5a2 Mon Sep 17 00:00:00 2001
From: Lee Schermerhorn <lee.schermerhorn@hp.com>
Date: Sat, 18 Oct 2008 20:26:37 -0700
Subject: pageflag helpers for configed-out flags

Define proper false/noop inline functions for noreclaim page flags when
!defined(CONFIG_UNEVICTABLE_LRU)

Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page-flags.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 57b688cfb5e2..3d31616dcd23 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -162,6 +162,18 @@ static inline int Page##uname(struct page *page) 			\
 #define TESTSCFLAG(uname, lname)					\
 	TESTSETFLAG(uname, lname) TESTCLEARFLAG(uname, lname)
 
+#define SETPAGEFLAG_NOOP(uname)						\
+static inline void SetPage##uname(struct page *page) {  }
+
+#define CLEARPAGEFLAG_NOOP(uname)					\
+static inline void ClearPage##uname(struct page *page) {  }
+
+#define __CLEARPAGEFLAG_NOOP(uname)					\
+static inline void __ClearPage##uname(struct page *page) {  }
+
+#define TESTCLEARFLAG_FALSE(uname)					\
+static inline int TestClearPage##uname(struct page *page) { return 0; }
+
 struct page;	/* forward declaration */
 
 TESTPAGEFLAG(Locked, locked)
-- 
cgit v1.2.3


From 894bc310419ac95f4fa4142dc364401a7e607f65 Mon Sep 17 00:00:00 2001
From: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Date: Sat, 18 Oct 2008 20:26:39 -0700
Subject: Unevictable LRU Infrastructure

When the system contains lots of mlocked or otherwise unevictable pages,
the pageout code (kswapd) can spend lots of time scanning over these
pages.  Worse still, the presence of lots of unevictable pages can confuse
kswapd into thinking that more aggressive pageout modes are required,
resulting in all kinds of bad behaviour.

Infrastructure to manage pages excluded from reclaim--i.e., hidden from
vmscan.  Based on a patch by Larry Woodman of Red Hat.  Reworked to
maintain "unevictable" pages on a separate per-zone LRU list, to "hide"
them from vmscan.

Kosaki Motohiro added the support for the memory controller unevictable
lru list.

Pages on the unevictable list have both PG_unevictable and PG_lru set.
Thus, PG_unevictable is analogous to and mutually exclusive with
PG_active--it specifies which LRU list the page is on.

The unevictable infrastructure is enabled by a new mm Kconfig option
[CONFIG_]UNEVICTABLE_LRU.

A new function 'page_evictable(page, vma)' in vmscan.c tests whether or
not a page may be evictable.  Subsequent patches will add the various
!evictable tests.  We'll want to keep these tests light-weight for use in
shrink_active_list() and, possibly, the fault path.

To avoid races between tasks putting pages [back] onto an LRU list and
tasks that might be moving the page from non-evictable to evictable state,
the new function 'putback_lru_page()' -- inverse to 'isolate_lru_page()'
-- tests the "evictability" of a page after placing it on the LRU, before
dropping the reference.  If the page has become unevictable,
putback_lru_page() will redo the 'putback', thus moving the page to the
unevictable list.  This way, we avoid "stranding" evictable pages on the
unevictable list.

[akpm@linux-foundation.org: fix fallout from out-of-order merge]
[riel@redhat.com: fix UNEVICTABLE_LRU and !PROC_PAGE_MONITOR build]
[nishimura@mxp.nes.nec.co.jp: remove redundant mapping check]
[kosaki.motohiro@jp.fujitsu.com: unevictable-lru-infrastructure: putback_lru_page()/unevictable page handling rework]
[kosaki.motohiro@jp.fujitsu.com: kill unnecessary lock_page() in vmscan.c]
[kosaki.motohiro@jp.fujitsu.com: revert migration change of unevictable lru infrastructure]
[kosaki.motohiro@jp.fujitsu.com: revert to unevictable-lru-infrastructure-kconfig-fix.patch]
[kosaki.motohiro@jp.fujitsu.com: restore patch failure of vmstat-unevictable-and-mlocked-pages-vm-events.patch]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Debugged-by: Benjamin Kidwell <benjkidwell@yahoo.com>
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h |   2 +-
 include/linux/mm_inline.h  |  23 ++++---
 include/linux/mmzone.h     |  24 +++++++-
 include/linux/page-flags.h |  22 ++++++-
 include/linux/pagevec.h    |   1 -
 include/linux/swap.h       |  12 ++++
 mm/Kconfig                 |  11 ++++
 mm/internal.h              |  26 ++++++++
 mm/memcontrol.c            |  73 +++++++++++++---------
 mm/mempolicy.c             |   2 +-
 mm/migrate.c               |  31 +++++-----
 mm/swap.c                  |  42 +++++++++++--
 mm/vmscan.c                | 149 +++++++++++++++++++++++++++++++++++++++++----
 13 files changed, 345 insertions(+), 73 deletions(-)

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 8d8f05c1515a..ee1b2fcb4410 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -34,9 +34,9 @@ extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask);
 extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 					gfp_t gfp_mask);
+extern void mem_cgroup_move_lists(struct page *page, enum lru_list lru);
 extern void mem_cgroup_uncharge_page(struct page *page);
 extern void mem_cgroup_uncharge_cache_page(struct page *page);
-extern void mem_cgroup_move_lists(struct page *page, bool active);
 extern int mem_cgroup_shrink_usage(struct mm_struct *mm, gfp_t gfp_mask);
 
 extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index f451fedd1e75..67d7697fd019 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -91,11 +91,16 @@ del_page_from_lru(struct zone *zone, struct page *page)
 	enum lru_list l = LRU_BASE;
 
 	list_del(&page->lru);
-	if (PageActive(page)) {
-		__ClearPageActive(page);
-		l += LRU_ACTIVE;
+	if (PageUnevictable(page)) {
+		__ClearPageUnevictable(page);
+		l = LRU_UNEVICTABLE;
+	} else {
+		if (PageActive(page)) {
+			__ClearPageActive(page);
+			l += LRU_ACTIVE;
+		}
+		l += page_is_file_cache(page);
 	}
-	l += page_is_file_cache(page);
 	__dec_zone_state(zone, NR_LRU_BASE + l);
 }
 
@@ -110,9 +115,13 @@ static inline enum lru_list page_lru(struct page *page)
 {
 	enum lru_list lru = LRU_BASE;
 
-	if (PageActive(page))
-		lru += LRU_ACTIVE;
-	lru += page_is_file_cache(page);
+	if (PageUnevictable(page))
+		lru = LRU_UNEVICTABLE;
+	else {
+		if (PageActive(page))
+			lru += LRU_ACTIVE;
+		lru += page_is_file_cache(page);
+	}
 
 	return lru;
 }
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9c5111f49a32..d1f60d5fe2ea 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -86,6 +86,11 @@ enum zone_stat_item {
 	NR_ACTIVE_ANON,		/*  "     "     "   "       "         */
 	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
 	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
+#ifdef CONFIG_UNEVICTABLE_LRU
+	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
+#else
+	NR_UNEVICTABLE = NR_ACTIVE_FILE, /* avoid compiler errors in dead code */
+#endif
 	NR_ANON_PAGES,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
 			   only modified from process context */
@@ -128,10 +133,18 @@ enum lru_list {
 	LRU_ACTIVE_ANON = LRU_BASE + LRU_ACTIVE,
 	LRU_INACTIVE_FILE = LRU_BASE + LRU_FILE,
 	LRU_ACTIVE_FILE = LRU_BASE + LRU_FILE + LRU_ACTIVE,
-	NR_LRU_LISTS };
+#ifdef CONFIG_UNEVICTABLE_LRU
+	LRU_UNEVICTABLE,
+#else
+	LRU_UNEVICTABLE = LRU_ACTIVE_FILE, /* avoid compiler errors in dead code */
+#endif
+	NR_LRU_LISTS
+};
 
 #define for_each_lru(l) for (l = 0; l < NR_LRU_LISTS; l++)
 
+#define for_each_evictable_lru(l) for (l = 0; l <= LRU_ACTIVE_FILE; l++)
+
 static inline int is_file_lru(enum lru_list l)
 {
 	return (l == LRU_INACTIVE_FILE || l == LRU_ACTIVE_FILE);
@@ -142,6 +155,15 @@ static inline int is_active_lru(enum lru_list l)
 	return (l == LRU_ACTIVE_ANON || l == LRU_ACTIVE_FILE);
 }
 
+static inline int is_unevictable_lru(enum lru_list l)
+{
+#ifdef CONFIG_UNEVICTABLE_LRU
+	return (l == LRU_UNEVICTABLE);
+#else
+	return 0;
+#endif
+}
+
 struct per_cpu_pages {
 	int count;		/* number of pages in the list */
 	int high;		/* high watermark, emptying needed */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 3d31616dcd23..ec1a1baad348 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -94,6 +94,9 @@ enum pageflags {
 	PG_reclaim,		/* To be reclaimed asap */
 	PG_buddy,		/* Page is free, on buddy lists */
 	PG_swapbacked,		/* Page is backed by RAM/swap */
+#ifdef CONFIG_UNEVICTABLE_LRU
+	PG_unevictable,		/* Page is "unevictable"  */
+#endif
 #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR
 	PG_uncached,		/* Page has been mapped as uncached */
 #endif
@@ -182,6 +185,7 @@ PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
 PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
 PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru)
 PAGEFLAG(Active, active) __CLEARPAGEFLAG(Active, active)
+	TESTCLEARFLAG(Active, active)
 __PAGEFLAG(Slab, slab)
 PAGEFLAG(Checked, checked)		/* Used by some filesystems */
 PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned)	/* Xen */
@@ -225,6 +229,15 @@ PAGEFLAG(SwapCache, swapcache)
 PAGEFLAG_FALSE(SwapCache)
 #endif
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable)
+	TESTCLEARFLAG(Unevictable, unevictable)
+#else
+PAGEFLAG_FALSE(Unevictable) TESTCLEARFLAG_FALSE(Unevictable)
+	SETPAGEFLAG_NOOP(Unevictable) CLEARPAGEFLAG_NOOP(Unevictable)
+	__CLEARPAGEFLAG_NOOP(Unevictable)
+#endif
+
 #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR
 PAGEFLAG(Uncached, uncached)
 #else
@@ -340,9 +353,16 @@ static inline void __ClearPageTail(struct page *page)
 
 #endif /* !PAGEFLAGS_EXTENDED */
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+#define __PG_UNEVICTABLE (1 << PG_unevictable)
+#else
+#define __PG_UNEVICTABLE 0
+#endif
+
 #define PAGE_FLAGS	(1 << PG_lru   | 1 << PG_private   | 1 << PG_locked | \
 			 1 << PG_buddy | 1 << PG_writeback | \
-			 1 << PG_slab  | 1 << PG_swapcache | 1 << PG_active)
+			 1 << PG_slab  | 1 << PG_swapcache | 1 << PG_active | \
+			 __PG_UNEVICTABLE)
 
 /*
  * Flags checked in bad_page().  Pages on the free list should not have
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index 5fc96a4e760f..e90a2cb02915 100644
--- a/include/linux/pagevec.h
+++ b/include/linux/pagevec.h
@@ -101,7 +101,6 @@ static inline void __pagevec_lru_add_active_file(struct pagevec *pvec)
 	____pagevec_lru_add(pvec, LRU_ACTIVE_FILE);
 }
 
-
 static inline void pagevec_lru_add_file(struct pagevec *pvec)
 {
 	if (pagevec_count(pvec))
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7d09d79997a4..a2113044d20a 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -180,6 +180,8 @@ extern int lru_add_drain_all(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void swap_setup(void);
 
+extern void add_page_to_unevictable_list(struct page *page);
+
 /**
  * lru_cache_add: add a page to the page lists
  * @page: the page to add
@@ -228,6 +230,16 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
 }
 #endif
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+extern int page_evictable(struct page *page, struct vm_area_struct *vma);
+#else
+static inline int page_evictable(struct page *page,
+						struct vm_area_struct *vma)
+{
+	return 1;
+}
+#endif
+
 extern int kswapd_run(int nid);
 
 #ifdef CONFIG_MMU
diff --git a/mm/Kconfig b/mm/Kconfig
index 1a501a4de95c..5b5790f8a816 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -209,5 +209,16 @@ config VIRT_TO_BUS
 	def_bool y
 	depends on !ARCH_NO_VIRT_TO_BUS
 
+config UNEVICTABLE_LRU
+	bool "Add LRU list to track non-evictable pages"
+	default y
+	depends on MMU
+	help
+	  Keeps unevictable pages off of the active and inactive pageout
+	  lists, so kswapd will not waste CPU time or have its balancing
+	  algorithms thrown off by scanning these pages.  Selecting this
+	  will use one page flag and increase the code size a little,
+	  say Y unless you know what you are doing.
+
 config MMU_NOTIFIER
 	bool
diff --git a/mm/internal.h b/mm/internal.h
index 4e8e78b978b5..3db17b2a1ac6 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -39,8 +39,15 @@ static inline void __put_page(struct page *page)
 	atomic_dec(&page->_count);
 }
 
+/*
+ * in mm/vmscan.c:
+ */
 extern int isolate_lru_page(struct page *page);
+extern void putback_lru_page(struct page *page);
 
+/*
+ * in mm/page_alloc.c
+ */
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
 
 /*
@@ -54,6 +61,25 @@ static inline unsigned long page_order(struct page *page)
 	return page_private(page);
 }
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+/*
+ * unevictable_migrate_page() called only from migrate_page_copy() to
+ * migrate unevictable flag to new page.
+ * Note that the old page has been isolated from the LRU lists at this
+ * point so we don't need to worry about LRU statistics.
+ */
+static inline void unevictable_migrate_page(struct page *new, struct page *old)
+{
+	if (TestClearPageUnevictable(old))
+		SetPageUnevictable(new);
+}
+#else
+static inline void unevictable_migrate_page(struct page *new, struct page *old)
+{
+}
+#endif
+
+
 /*
  * FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
  * so all functions starting at paging_init should be marked __init
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 27e9e75f4eab..82c065e7551e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -160,9 +160,10 @@ struct page_cgroup {
 	struct mem_cgroup *mem_cgroup;
 	int flags;
 };
-#define PAGE_CGROUP_FLAG_CACHE	(0x1)	/* charged as cache */
-#define PAGE_CGROUP_FLAG_ACTIVE (0x2)	/* page is active in this cgroup */
-#define PAGE_CGROUP_FLAG_FILE	(0x4)	/* page is file system backed */
+#define PAGE_CGROUP_FLAG_CACHE	   (0x1)	/* charged as cache */
+#define PAGE_CGROUP_FLAG_ACTIVE    (0x2)	/* page is active in this cgroup */
+#define PAGE_CGROUP_FLAG_FILE	   (0x4)	/* page is file system backed */
+#define PAGE_CGROUP_FLAG_UNEVICTABLE (0x8)	/* page is unevictableable */
 
 static int page_cgroup_nid(struct page_cgroup *pc)
 {
@@ -292,10 +293,14 @@ static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
 {
 	int lru = LRU_BASE;
 
-	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
-		lru += LRU_ACTIVE;
-	if (pc->flags & PAGE_CGROUP_FLAG_FILE)
-		lru += LRU_FILE;
+	if (pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE)
+		lru = LRU_UNEVICTABLE;
+	else {
+		if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+			lru += LRU_ACTIVE;
+		if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+			lru += LRU_FILE;
+	}
 
 	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
 
@@ -308,10 +313,14 @@ static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
 {
 	int lru = LRU_BASE;
 
-	if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
-		lru += LRU_ACTIVE;
-	if (pc->flags & PAGE_CGROUP_FLAG_FILE)
-		lru += LRU_FILE;
+	if (pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE)
+		lru = LRU_UNEVICTABLE;
+	else {
+		if (pc->flags & PAGE_CGROUP_FLAG_ACTIVE)
+			lru += LRU_ACTIVE;
+		if (pc->flags & PAGE_CGROUP_FLAG_FILE)
+			lru += LRU_FILE;
+	}
 
 	MEM_CGROUP_ZSTAT(mz, lru) += 1;
 	list_add(&pc->lru, &mz->lists[lru]);
@@ -319,21 +328,31 @@ static void __mem_cgroup_add_list(struct mem_cgroup_per_zone *mz,
 	mem_cgroup_charge_statistics(pc->mem_cgroup, pc->flags, true);
 }
 
-static void __mem_cgroup_move_lists(struct page_cgroup *pc, bool active)
+static void __mem_cgroup_move_lists(struct page_cgroup *pc, enum lru_list lru)
 {
 	struct mem_cgroup_per_zone *mz = page_cgroup_zoneinfo(pc);
-	int from = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
-	int file = pc->flags & PAGE_CGROUP_FLAG_FILE;
-	int lru = LRU_FILE * !!file + !!from;
+	int active    = pc->flags & PAGE_CGROUP_FLAG_ACTIVE;
+	int file      = pc->flags & PAGE_CGROUP_FLAG_FILE;
+	int unevictable = pc->flags & PAGE_CGROUP_FLAG_UNEVICTABLE;
+	enum lru_list from = unevictable ? LRU_UNEVICTABLE :
+				(LRU_FILE * !!file + !!active);
 
-	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+	if (lru == from)
+		return;
 
-	if (active)
-		pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
-	else
+	MEM_CGROUP_ZSTAT(mz, from) -= 1;
+
+	if (is_unevictable_lru(lru)) {
 		pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
+		pc->flags |= PAGE_CGROUP_FLAG_UNEVICTABLE;
+	} else {
+		if (is_active_lru(lru))
+			pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
+		else
+			pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
+		pc->flags &= ~PAGE_CGROUP_FLAG_UNEVICTABLE;
+	}
 
-	lru = LRU_FILE * !!file + !!active;
 	MEM_CGROUP_ZSTAT(mz, lru) += 1;
 	list_move(&pc->lru, &mz->lists[lru]);
 }
@@ -351,7 +370,7 @@ int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
 /*
  * This routine assumes that the appropriate zone's lru lock is already held
  */
-void mem_cgroup_move_lists(struct page *page, bool active)
+void mem_cgroup_move_lists(struct page *page, enum lru_list lru)
 {
 	struct page_cgroup *pc;
 	struct mem_cgroup_per_zone *mz;
@@ -374,7 +393,7 @@ void mem_cgroup_move_lists(struct page *page, bool active)
 	if (pc) {
 		mz = page_cgroup_zoneinfo(pc);
 		spin_lock_irqsave(&mz->lru_lock, flags);
-		__mem_cgroup_move_lists(pc, active);
+		__mem_cgroup_move_lists(pc, lru);
 		spin_unlock_irqrestore(&mz->lru_lock, flags);
 	}
 	unlock_page_cgroup(page);
@@ -472,12 +491,10 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 		/*
 		 * TODO: play better with lumpy reclaim, grabbing anything.
 		 */
-		if (PageActive(page) && !active) {
-			__mem_cgroup_move_lists(pc, true);
-			continue;
-		}
-		if (!PageActive(page) && active) {
-			__mem_cgroup_move_lists(pc, false);
+		if (PageUnevictable(page) ||
+		    (PageActive(page) && !active) ||
+		    (!PageActive(page) && active)) {
+			__mem_cgroup_move_lists(pc, page_lru(page));
 			continue;
 		}
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 71b47491487d..36f42573a335 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2202,7 +2202,7 @@ static void gather_stats(struct page *page, void *private, int pte_dirty)
 	if (PageSwapCache(page))
 		md->swapcache++;
 
-	if (PageActive(page))
+	if (PageActive(page) || PageUnevictable(page))
 		md->active++;
 
 	if (PageWriteback(page))
diff --git a/mm/migrate.c b/mm/migrate.c
index c07327487111..b10237d8b459 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -53,14 +53,9 @@ int migrate_prep(void)
 	return 0;
 }
 
-static inline void move_to_lru(struct page *page)
-{
-	lru_cache_add_lru(page, page_lru(page));
-	put_page(page);
-}
-
 /*
- * Add isolated pages on the list back to the LRU.
+ * Add isolated pages on the list back to the LRU under page lock
+ * to avoid leaking evictable pages back onto unevictable list.
  *
  * returns the number of pages put back.
  */
@@ -72,7 +67,7 @@ int putback_lru_pages(struct list_head *l)
 
 	list_for_each_entry_safe(page, page2, l, lru) {
 		list_del(&page->lru);
-		move_to_lru(page);
+		putback_lru_page(page);
 		count++;
 	}
 	return count;
@@ -354,8 +349,11 @@ static void migrate_page_copy(struct page *newpage, struct page *page)
 		SetPageReferenced(newpage);
 	if (PageUptodate(page))
 		SetPageUptodate(newpage);
-	if (PageActive(page))
+	if (TestClearPageActive(page)) {
+		VM_BUG_ON(PageUnevictable(page));
 		SetPageActive(newpage);
+	} else
+		unevictable_migrate_page(newpage, page);
 	if (PageChecked(page))
 		SetPageChecked(newpage);
 	if (PageMappedToDisk(page))
@@ -376,7 +374,6 @@ static void migrate_page_copy(struct page *newpage, struct page *page)
 #ifdef CONFIG_SWAP
 	ClearPageSwapCache(page);
 #endif
-	ClearPageActive(page);
 	ClearPagePrivate(page);
 	set_page_private(page, 0);
 	page->mapping = NULL;
@@ -555,6 +552,10 @@ static int fallback_migrate_page(struct address_space *mapping,
  *
  * The new page will have replaced the old page if this function
  * is successful.
+ *
+ * Return value:
+ *   < 0 - error code
+ *  == 0 - success
  */
 static int move_to_new_page(struct page *newpage, struct page *page)
 {
@@ -617,9 +618,10 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	if (!newpage)
 		return -ENOMEM;
 
-	if (page_count(page) == 1)
+	if (page_count(page) == 1) {
 		/* page was freed from under us. So we are done. */
 		goto move_newpage;
+	}
 
 	charge = mem_cgroup_prepare_migration(page, newpage);
 	if (charge == -ENOMEM) {
@@ -693,7 +695,6 @@ rcu_unlock:
 		rcu_read_unlock();
 
 unlock:
-
 	unlock_page(page);
 
 	if (rc != -EAGAIN) {
@@ -704,17 +705,19 @@ unlock:
  		 * restored.
  		 */
  		list_del(&page->lru);
- 		move_to_lru(page);
+		putback_lru_page(page);
 	}
 
 move_newpage:
 	if (!charge)
 		mem_cgroup_end_migration(newpage);
+
 	/*
 	 * Move the new page to the LRU. If migration was not successful
 	 * then this will free the page.
 	 */
-	move_to_lru(newpage);
+	putback_lru_page(newpage);
+
 	if (result) {
 		if (rc)
 			*result = rc;
diff --git a/mm/swap.c b/mm/swap.c
index 0b1974a08974..fee6b973f143 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -115,7 +115,7 @@ static void pagevec_move_tail(struct pagevec *pvec)
 			zone = pagezone;
 			spin_lock(&zone->lru_lock);
 		}
-		if (PageLRU(page) && !PageActive(page)) {
+		if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
 			int lru = page_is_file_cache(page);
 			list_move_tail(&page->lru, &zone->lru[lru].list);
 			pgmoved++;
@@ -136,7 +136,7 @@ static void pagevec_move_tail(struct pagevec *pvec)
 void  rotate_reclaimable_page(struct page *page)
 {
 	if (!PageLocked(page) && !PageDirty(page) && !PageActive(page) &&
-	    PageLRU(page)) {
+	    !PageUnevictable(page) && PageLRU(page)) {
 		struct pagevec *pvec;
 		unsigned long flags;
 
@@ -157,7 +157,7 @@ void activate_page(struct page *page)
 	struct zone *zone = page_zone(page);
 
 	spin_lock_irq(&zone->lru_lock);
-	if (PageLRU(page) && !PageActive(page)) {
+	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
 		int file = page_is_file_cache(page);
 		int lru = LRU_BASE + file;
 		del_page_from_lru_list(zone, page, lru);
@@ -166,7 +166,7 @@ void activate_page(struct page *page)
 		lru += LRU_ACTIVE;
 		add_page_to_lru_list(zone, page, lru);
 		__count_vm_event(PGACTIVATE);
-		mem_cgroup_move_lists(page, true);
+		mem_cgroup_move_lists(page, lru);
 
 		zone->recent_rotated[!!file]++;
 		zone->recent_scanned[!!file]++;
@@ -183,7 +183,8 @@ void activate_page(struct page *page)
  */
 void mark_page_accessed(struct page *page)
 {
-	if (!PageActive(page) && PageReferenced(page) && PageLRU(page)) {
+	if (!PageActive(page) && !PageUnevictable(page) &&
+			PageReferenced(page) && PageLRU(page)) {
 		activate_page(page);
 		ClearPageReferenced(page);
 	} else if (!PageReferenced(page)) {
@@ -211,13 +212,38 @@ void __lru_cache_add(struct page *page, enum lru_list lru)
 void lru_cache_add_lru(struct page *page, enum lru_list lru)
 {
 	if (PageActive(page)) {
+		VM_BUG_ON(PageUnevictable(page));
 		ClearPageActive(page);
+	} else if (PageUnevictable(page)) {
+		VM_BUG_ON(PageActive(page));
+		ClearPageUnevictable(page);
 	}
 
-	VM_BUG_ON(PageLRU(page) || PageActive(page));
+	VM_BUG_ON(PageLRU(page) || PageActive(page) || PageUnevictable(page));
 	__lru_cache_add(page, lru);
 }
 
+/**
+ * add_page_to_unevictable_list - add a page to the unevictable list
+ * @page:  the page to be added to the unevictable list
+ *
+ * Add page directly to its zone's unevictable list.  To avoid races with
+ * tasks that might be making the page evictable, through eg. munlock,
+ * munmap or exit, while it's not on the lru, we want to add the page
+ * while it's locked or otherwise "invisible" to other tasks.  This is
+ * difficult to do when using the pagevec cache, so bypass that.
+ */
+void add_page_to_unevictable_list(struct page *page)
+{
+	struct zone *zone = page_zone(page);
+
+	spin_lock_irq(&zone->lru_lock);
+	SetPageUnevictable(page);
+	SetPageLRU(page);
+	add_page_to_lru_list(zone, page, LRU_UNEVICTABLE);
+	spin_unlock_irq(&zone->lru_lock);
+}
+
 /*
  * Drain pages out of the cpu's pagevecs.
  * Either "cpu" is the current CPU, and preemption has already been
@@ -316,6 +342,7 @@ void release_pages(struct page **pages, int nr, int cold)
 
 		if (PageLRU(page)) {
 			struct zone *pagezone = page_zone(page);
+
 			if (pagezone != zone) {
 				if (zone)
 					spin_unlock_irqrestore(&zone->lru_lock,
@@ -392,6 +419,7 @@ void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
 {
 	int i;
 	struct zone *zone = NULL;
+	VM_BUG_ON(is_unevictable_lru(lru));
 
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
@@ -403,6 +431,8 @@ void ____pagevec_lru_add(struct pagevec *pvec, enum lru_list lru)
 			zone = pagezone;
 			spin_lock_irq(&zone->lru_lock);
 		}
+		VM_BUG_ON(PageActive(page));
+		VM_BUG_ON(PageUnevictable(page));
 		VM_BUG_ON(PageLRU(page));
 		SetPageLRU(page);
 		if (is_active_lru(lru))
diff --git a/mm/vmscan.c b/mm/vmscan.c
index a8347b677e74..154b9b608da6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -470,6 +470,79 @@ int remove_mapping(struct address_space *mapping, struct page *page)
 	return 0;
 }
 
+/**
+ * putback_lru_page - put previously isolated page onto appropriate LRU list
+ * @page: page to be put back to appropriate lru list
+ *
+ * Add previously isolated @page to appropriate LRU list.
+ * Page may still be unevictable for other reasons.
+ *
+ * lru_lock must not be held, interrupts must be enabled.
+ */
+#ifdef CONFIG_UNEVICTABLE_LRU
+void putback_lru_page(struct page *page)
+{
+	int lru;
+	int active = !!TestClearPageActive(page);
+
+	VM_BUG_ON(PageLRU(page));
+
+redo:
+	ClearPageUnevictable(page);
+
+	if (page_evictable(page, NULL)) {
+		/*
+		 * For evictable pages, we can use the cache.
+		 * In event of a race, worst case is we end up with an
+		 * unevictable page on [in]active list.
+		 * We know how to handle that.
+		 */
+		lru = active + page_is_file_cache(page);
+		lru_cache_add_lru(page, lru);
+	} else {
+		/*
+		 * Put unevictable pages directly on zone's unevictable
+		 * list.
+		 */
+		lru = LRU_UNEVICTABLE;
+		add_page_to_unevictable_list(page);
+	}
+	mem_cgroup_move_lists(page, lru);
+
+	/*
+	 * page's status can change while we move it among lru. If an evictable
+	 * page is on unevictable list, it never be freed. To avoid that,
+	 * check after we added it to the list, again.
+	 */
+	if (lru == LRU_UNEVICTABLE && page_evictable(page, NULL)) {
+		if (!isolate_lru_page(page)) {
+			put_page(page);
+			goto redo;
+		}
+		/* This means someone else dropped this page from LRU
+		 * So, it will be freed or putback to LRU again. There is
+		 * nothing to do here.
+		 */
+	}
+
+	put_page(page);		/* drop ref from isolate */
+}
+
+#else /* CONFIG_UNEVICTABLE_LRU */
+
+void putback_lru_page(struct page *page)
+{
+	int lru;
+	VM_BUG_ON(PageLRU(page));
+
+	lru = !!TestClearPageActive(page) + page_is_file_cache(page);
+	lru_cache_add_lru(page, lru);
+	mem_cgroup_move_lists(page, lru);
+	put_page(page);
+}
+#endif /* CONFIG_UNEVICTABLE_LRU */
+
+
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -503,6 +576,12 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 		sc->nr_scanned++;
 
+		if (unlikely(!page_evictable(page, NULL))) {
+			unlock_page(page);
+			putback_lru_page(page);
+			continue;
+		}
+
 		if (!sc->may_swap && page_mapped(page))
 			goto keep_locked;
 
@@ -602,7 +681,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * possible for a page to have PageDirty set, but it is actually
 		 * clean (all its buffers are clean).  This happens if the
 		 * buffers were written out directly, with submit_bh(). ext3
-		 * will do this, as well as the blockdev mapping. 
+		 * will do this, as well as the blockdev mapping.
 		 * try_to_release_page() will discover that cleanness and will
 		 * drop the buffers and mark the page clean - it can be freed.
 		 *
@@ -650,6 +729,7 @@ activate_locked:
 		/* Not a candidate for swapping, so reclaim swap space. */
 		if (PageSwapCache(page) && vm_swap_full())
 			remove_exclusive_swap_page_ref(page);
+		VM_BUG_ON(PageActive(page));
 		SetPageActive(page);
 		pgactivate++;
 keep_locked:
@@ -699,6 +779,14 @@ int __isolate_lru_page(struct page *page, int mode, int file)
 	if (mode != ISOLATE_BOTH && (!page_is_file_cache(page) != !file))
 		return ret;
 
+	/*
+	 * When this function is being called for lumpy reclaim, we
+	 * initially look into all LRU pages, active, inactive and
+	 * unevictable; only give shrink_page_list evictable pages.
+	 */
+	if (PageUnevictable(page))
+		return ret;
+
 	ret = -EBUSY;
 	if (likely(get_page_unless_zero(page))) {
 		/*
@@ -810,7 +898,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 				/* else it is being freed elsewhere */
 				list_move(&cursor_page->lru, src);
 			default:
-				break;
+				break;	/* ! on LRU or wrong list */
 			}
 		}
 	}
@@ -870,8 +958,9 @@ static unsigned long clear_active_flags(struct list_head *page_list,
  * Returns -EBUSY if the page was not on an LRU list.
  *
  * The returned page will have PageLRU() cleared.  If it was found on
- * the active list, it will have PageActive set.  That flag may need
- * to be cleared by the caller before letting the page go.
+ * the active list, it will have PageActive set.  If it was found on
+ * the unevictable list, it will have the PageUnevictable bit set. That flag
+ * may need to be cleared by the caller before letting the page go.
  *
  * The vmstat statistic corresponding to the list on which the page was
  * found will be decremented.
@@ -892,11 +981,10 @@ int isolate_lru_page(struct page *page)
 
 		spin_lock_irq(&zone->lru_lock);
 		if (PageLRU(page) && get_page_unless_zero(page)) {
-			int lru = LRU_BASE;
+			int lru = page_lru(page);
 			ret = 0;
 			ClearPageLRU(page);
 
-			lru += page_is_file_cache(page) + !!PageActive(page);
 			del_page_from_lru_list(zone, page, lru);
 		}
 		spin_unlock_irq(&zone->lru_lock);
@@ -1008,11 +1096,20 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		 * Put back any unfreeable pages.
 		 */
 		while (!list_empty(&page_list)) {
+			int lru;
 			page = lru_to_page(&page_list);
 			VM_BUG_ON(PageLRU(page));
-			SetPageLRU(page);
 			list_del(&page->lru);
-			add_page_to_lru_list(zone, page, page_lru(page));
+			if (unlikely(!page_evictable(page, NULL))) {
+				spin_unlock_irq(&zone->lru_lock);
+				putback_lru_page(page);
+				spin_lock_irq(&zone->lru_lock);
+				continue;
+			}
+			SetPageLRU(page);
+			lru = page_lru(page);
+			add_page_to_lru_list(zone, page, lru);
+			mem_cgroup_move_lists(page, lru);
 			if (PageActive(page) && scan_global_lru(sc)) {
 				int file = !!page_is_file_cache(page);
 				zone->recent_rotated[file]++;
@@ -1107,6 +1204,11 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		page = lru_to_page(&l_hold);
 		list_del(&page->lru);
 
+		if (unlikely(!page_evictable(page, NULL))) {
+			putback_lru_page(page);
+			continue;
+		}
+
 		/* page_referenced clears PageReferenced */
 		if (page_mapping_inuse(page) &&
 		    page_referenced(page, 0, sc->mem_cgroup))
@@ -1140,7 +1242,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		ClearPageActive(page);
 
 		list_move(&page->lru, &zone->lru[lru].list);
-		mem_cgroup_move_lists(page, false);
+		mem_cgroup_move_lists(page, lru);
 		pgmoved++;
 		if (!pagevec_add(&pvec, page)) {
 			__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
@@ -1286,7 +1388,7 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 
 	get_scan_ratio(zone, sc, percent);
 
-	for_each_lru(l) {
+	for_each_evictable_lru(l) {
 		if (scan_global_lru(sc)) {
 			int file = is_file_lru(l);
 			int scan;
@@ -1318,7 +1420,7 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
 					nr[LRU_INACTIVE_FILE]) {
-		for_each_lru(l) {
+		for_each_evictable_lru(l) {
 			if (nr[l]) {
 				nr_to_scan = min(nr[l],
 					(unsigned long)sc->swap_cluster_max);
@@ -1875,8 +1977,8 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 		if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
 			continue;
 
-		for_each_lru(l) {
-			/* For pass = 0 we don't shrink the active list */
+		for_each_evictable_lru(l) {
+			/* For pass = 0, we don't shrink the active list */
 			if (pass == 0 &&
 				(l == LRU_ACTIVE || l == LRU_ACTIVE_FILE))
 				continue;
@@ -2213,3 +2315,24 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	return ret;
 }
 #endif
+
+#ifdef CONFIG_UNEVICTABLE_LRU
+/*
+ * page_evictable - test whether a page is evictable
+ * @page: the page to test
+ * @vma: the VMA in which the page is or will be mapped, may be NULL
+ *
+ * Test whether page is evictable--i.e., should be placed on active/inactive
+ * lists vs unevictable list.
+ *
+ * Reasons page might not be evictable:
+ * TODO - later patches
+ */
+int page_evictable(struct page *page, struct vm_area_struct *vma)
+{
+
+	/* TODO:  test page [!]evictable conditions */
+
+	return 1;
+}
+#endif
-- 
cgit v1.2.3


From bbfd28eee9fbd73e780b19beb3dc562befbb94fa Mon Sep 17 00:00:00 2001
From: Lee Schermerhorn <lee.schermerhorn@hp.com>
Date: Sat, 18 Oct 2008 20:26:40 -0700
Subject: unevictable lru: add event counting with statistics

Fix to unevictable-lru-page-statistics.patch

Add unevictable lru infrastructure vm events to the statistics patch.
Rename the "NORECL_" and "noreclaim_" symbols and text strings to
"UNEVICTABLE_" and "unevictable_", respectively.

Currently, both the infrastructure and the mlocked pages event are
added by a single patch later in the series.  This makes it difficult
to add or rework the incremental patches.  The events actually "belong"
with the stats, so pull them up to here.

Also, restore the event counting to putback_lru_page().  This was removed
from previous patch in series where it was "misplaced".  The actual events
weren't defined that early.

Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Rik van Riel <riel@redhat.com>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmstat.h | 5 +++++
 mm/vmscan.c            | 6 ++++++
 mm/vmstat.c            | 5 +++++
 3 files changed, 16 insertions(+)

(limited to 'include')

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index ff5179f2b153..135840cd7feb 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -40,6 +40,11 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
 #ifdef CONFIG_HUGETLB_PAGE
 		HTLB_BUDDY_PGALLOC, HTLB_BUDDY_PGALLOC_FAIL,
+#endif
+#ifdef CONFIG_UNEVICTABLE_LRU
+		UNEVICTABLE_PGCULLED,	/* culled to noreclaim list */
+		UNEVICTABLE_PGSCANNED,	/* scanned for reclaimability */
+		UNEVICTABLE_PGRESCUED,	/* rescued from noreclaim list */
 #endif
 		NR_VM_EVENT_ITEMS
 };
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 154b9b608da6..2804d23e2da7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -484,6 +484,7 @@ void putback_lru_page(struct page *page)
 {
 	int lru;
 	int active = !!TestClearPageActive(page);
+	int was_unevictable = PageUnevictable(page);
 
 	VM_BUG_ON(PageLRU(page));
 
@@ -525,6 +526,11 @@ redo:
 		 */
 	}
 
+	if (was_unevictable && lru != LRU_UNEVICTABLE)
+		count_vm_event(UNEVICTABLE_PGRESCUED);
+	else if (!was_unevictable && lru == LRU_UNEVICTABLE)
+		count_vm_event(UNEVICTABLE_PGCULLED);
+
 	put_page(page);		/* drop ref from isolate */
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 4380b0dba6d9..6cb08cdd4f03 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -677,6 +677,11 @@ static const char * const vmstat_text[] = {
 	"htlb_buddy_alloc_success",
 	"htlb_buddy_alloc_fail",
 #endif
+#ifdef CONFIG_UNEVICTABLE_LRU
+	"unevictable_pgs_culled",
+	"unevictable_pgs_scanned",
+	"unevictable_pgs_rescued",
+#endif
 #endif
 };
 
-- 
cgit v1.2.3


From ba9ddf49391645e6bb93219131a40446538a5e76 Mon Sep 17 00:00:00 2001
From: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Date: Sat, 18 Oct 2008 20:26:42 -0700
Subject: Ramfs and Ram Disk pages are unevictable

Christoph Lameter pointed out that ram disk pages also clutter the LRU
lists.  When vmscan finds them dirty and tries to clean them, the ram disk
writeback function just redirties the page so that it goes back onto the
active list.  Round and round she goes...

With the ram disk driver [rd.c] replaced by the newer 'brd.c', this is no
longer the case, as ram disk pages are no longer maintained on the lru.
[This makes them unmigratable for defrag or memory hot remove, but that
can be addressed by a separate patch series.] However, the ramfs pages
behave like ram disk pages used to, so:

Define new address_space flag [shares address_space flags member with
mapping's gfp mask] to indicate that the address space contains all
unevictable pages.  This will provide for efficient testing of ramfs pages
in page_evictable().

Also provide wrapper functions to set/test the unevictable state to
minimize #ifdefs in ramfs driver and any other users of this facility.

Set the unevictable state on address_space structures for new ramfs
inodes.  Test the unevictable state in page_evictable() to cull
unevictable pages.

These changes depend on [CONFIG_]UNEVICTABLE_LRU.

[riel@redhat.com: undo the brd.c part]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Debugged-by: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/ramfs/inode.c        |  1 +
 include/linux/pagemap.h | 22 ++++++++++++++++++++++
 mm/vmscan.c             |  5 +++++
 3 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index b13123424e49..f031d1c925f0 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -61,6 +61,7 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev)
 		inode->i_mapping->a_ops = &ramfs_aops;
 		inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info;
 		mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER);
+		mapping_set_unevictable(inode->i_mapping);
 		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 		switch (mode & S_IFMT) {
 		default:
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 5da31c12101c..09164d2c5c27 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -32,6 +32,28 @@ static inline void mapping_set_error(struct address_space *mapping, int error)
 	}
 }
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+#define AS_UNEVICTABLE	(__GFP_BITS_SHIFT + 2)	/* e.g., ramdisk, SHM_LOCK */
+
+static inline void mapping_set_unevictable(struct address_space *mapping)
+{
+	set_bit(AS_UNEVICTABLE, &mapping->flags);
+}
+
+static inline int mapping_unevictable(struct address_space *mapping)
+{
+	if (mapping && (mapping->flags & AS_UNEVICTABLE))
+		return 1;
+	return 0;
+}
+#else
+static inline void mapping_set_unevictable(struct address_space *mapping) { }
+static inline int mapping_unevictable(struct address_space *mapping)
+{
+	return 0;
+}
+#endif
+
 static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 {
 	return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2804d23e2da7..9babfbc1ddc8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2332,11 +2332,16 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
  * lists vs unevictable list.
  *
  * Reasons page might not be evictable:
+ * (1) page's mapping marked unevictable
+ *
  * TODO - later patches
  */
 int page_evictable(struct page *page, struct vm_area_struct *vma)
 {
 
+	if (mapping_unevictable(page_mapping(page)))
+		return 0;
+
 	/* TODO:  test page [!]evictable conditions */
 
 	return 1;
-- 
cgit v1.2.3


From 89e004ea55abe201b29e2d6e35124101f1288ef7 Mon Sep 17 00:00:00 2001
From: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Date: Sat, 18 Oct 2008 20:26:43 -0700
Subject: SHM_LOCKED pages are unevictable

Shmem segments locked into memory via shmctl(SHM_LOCKED) should not be
kept on the normal LRU, since scanning them is a waste of time and might
throw off kswapd's balancing algorithms.  Place them on the unevictable
LRU list instead.

Use the AS_UNEVICTABLE flag to mark address_space of SHM_LOCKed shared
memory regions as unevictable.  Then these pages will be culled off the
normal LRU lists during vmscan.

Add new wrapper function to clear the mapping's unevictable state when/if
shared memory segment is munlocked.

Add 'scan_mapping_unevictable_page()' to mm/vmscan.c to scan all pages in
the shmem segment's mapping [struct address_space] for evictability now
that they're no longer locked.  If so, move them to the appropriate zone
lru list.

Changes depend on [CONFIG_]UNEVICTABLE_LRU.

[kosaki.motohiro@jp.fujitsu.com: revert shm change]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Kosaki Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h      |  4 +--
 include/linux/pagemap.h | 12 +++++--
 include/linux/swap.h    |  4 +++
 ipc/shm.c               |  4 +++
 mm/shmem.c              |  4 +++
 mm/vmscan.c             | 89 +++++++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 112 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index c61ba10768ea..40236290e2ae 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -700,10 +700,10 @@ static inline int page_mapped(struct page *page)
 extern void show_free_areas(void);
 
 #ifdef CONFIG_SHMEM
-int shmem_lock(struct file *file, int lock, struct user_struct *user);
+extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
 #else
 static inline int shmem_lock(struct file *file, int lock,
-			     struct user_struct *user)
+			    struct user_struct *user)
 {
 	return 0;
 }
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 09164d2c5c27..4b6c4d8d26b8 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -40,14 +40,20 @@ static inline void mapping_set_unevictable(struct address_space *mapping)
 	set_bit(AS_UNEVICTABLE, &mapping->flags);
 }
 
+static inline void mapping_clear_unevictable(struct address_space *mapping)
+{
+	clear_bit(AS_UNEVICTABLE, &mapping->flags);
+}
+
 static inline int mapping_unevictable(struct address_space *mapping)
 {
-	if (mapping && (mapping->flags & AS_UNEVICTABLE))
-		return 1;
-	return 0;
+	if (likely(mapping))
+		return test_bit(AS_UNEVICTABLE, &mapping->flags);
+	return !!mapping;
 }
 #else
 static inline void mapping_set_unevictable(struct address_space *mapping) { }
+static inline void mapping_clear_unevictable(struct address_space *mapping) { }
 static inline int mapping_unevictable(struct address_space *mapping)
 {
 	return 0;
diff --git a/include/linux/swap.h b/include/linux/swap.h
index a2113044d20a..7edb4cbc29f9 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -232,12 +232,16 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
 
 #ifdef CONFIG_UNEVICTABLE_LRU
 extern int page_evictable(struct page *page, struct vm_area_struct *vma);
+extern void scan_mapping_unevictable_pages(struct address_space *);
 #else
 static inline int page_evictable(struct page *page,
 						struct vm_area_struct *vma)
 {
 	return 1;
 }
+static inline void scan_mapping_unevictable_pages(struct address_space *mapping)
+{
+}
 #endif
 
 extern int kswapd_run(int nid);
diff --git a/ipc/shm.c b/ipc/shm.c
index e77ec698cf40..0add3fa5f547 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -737,6 +737,10 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf)
 	case SHM_LOCK:
 	case SHM_UNLOCK:
 	{
+		struct file *uninitialized_var(shm_file);
+
+		lru_add_drain_all();  /* drain pagevecs to lru lists */
+
 		shp = shm_lock_check(ns, shmid);
 		if (IS_ERR(shp)) {
 			err = PTR_ERR(shp);
diff --git a/mm/shmem.c b/mm/shmem.c
index fc2ccf79a776..d38d7e61fcd0 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1477,12 +1477,16 @@ int shmem_lock(struct file *file, int lock, struct user_struct *user)
 		if (!user_shm_lock(inode->i_size, user))
 			goto out_nomem;
 		info->flags |= VM_LOCKED;
+		mapping_set_unevictable(file->f_mapping);
 	}
 	if (!lock && (info->flags & VM_LOCKED) && user) {
 		user_shm_unlock(inode->i_size, user);
 		info->flags &= ~VM_LOCKED;
+		mapping_clear_unevictable(file->f_mapping);
+		scan_mapping_unevictable_pages(file->f_mapping);
 	}
 	retval = 0;
+
 out_nomem:
 	spin_unlock(&info->lock);
 	return retval;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 9babfbc1ddc8..dfb342e0db9b 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2346,4 +2346,93 @@ int page_evictable(struct page *page, struct vm_area_struct *vma)
 
 	return 1;
 }
+
+/**
+ * check_move_unevictable_page - check page for evictability and move to appropriate zone lru list
+ * @page: page to check evictability and move to appropriate lru list
+ * @zone: zone page is in
+ *
+ * Checks a page for evictability and moves the page to the appropriate
+ * zone lru list.
+ *
+ * Restrictions: zone->lru_lock must be held, page must be on LRU and must
+ * have PageUnevictable set.
+ */
+static void check_move_unevictable_page(struct page *page, struct zone *zone)
+{
+	VM_BUG_ON(PageActive(page));
+
+retry:
+	ClearPageUnevictable(page);
+	if (page_evictable(page, NULL)) {
+		enum lru_list l = LRU_INACTIVE_ANON + page_is_file_cache(page);
+		__dec_zone_state(zone, NR_UNEVICTABLE);
+		list_move(&page->lru, &zone->lru[l].list);
+		__inc_zone_state(zone, NR_INACTIVE_ANON + l);
+		__count_vm_event(UNEVICTABLE_PGRESCUED);
+	} else {
+		/*
+		 * rotate unevictable list
+		 */
+		SetPageUnevictable(page);
+		list_move(&page->lru, &zone->lru[LRU_UNEVICTABLE].list);
+		if (page_evictable(page, NULL))
+			goto retry;
+	}
+}
+
+/**
+ * scan_mapping_unevictable_pages - scan an address space for evictable pages
+ * @mapping: struct address_space to scan for evictable pages
+ *
+ * Scan all pages in mapping.  Check unevictable pages for
+ * evictability and move them to the appropriate zone lru list.
+ */
+void scan_mapping_unevictable_pages(struct address_space *mapping)
+{
+	pgoff_t next = 0;
+	pgoff_t end   = (i_size_read(mapping->host) + PAGE_CACHE_SIZE - 1) >>
+			 PAGE_CACHE_SHIFT;
+	struct zone *zone;
+	struct pagevec pvec;
+
+	if (mapping->nrpages == 0)
+		return;
+
+	pagevec_init(&pvec, 0);
+	while (next < end &&
+		pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
+		int i;
+		int pg_scanned = 0;
+
+		zone = NULL;
+
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+			pgoff_t page_index = page->index;
+			struct zone *pagezone = page_zone(page);
+
+			pg_scanned++;
+			if (page_index > next)
+				next = page_index;
+			next++;
+
+			if (pagezone != zone) {
+				if (zone)
+					spin_unlock_irq(&zone->lru_lock);
+				zone = pagezone;
+				spin_lock_irq(&zone->lru_lock);
+			}
+
+			if (PageLRU(page) && PageUnevictable(page))
+				check_move_unevictable_page(page, zone);
+		}
+		if (zone)
+			spin_unlock_irq(&zone->lru_lock);
+		pagevec_release(&pvec);
+
+		count_vm_events(UNEVICTABLE_PGSCANNED, pg_scanned);
+	}
+
+}
 #endif
-- 
cgit v1.2.3


From b291f000393f5a0b679012b39d79fbc85c018233 Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Sat, 18 Oct 2008 20:26:44 -0700
Subject: mlock: mlocked pages are unevictable

Make sure that mlocked pages also live on the unevictable LRU, so kswapd
will not scan them over and over again.

This is achieved through various strategies:

1) add yet another page flag--PG_mlocked--to indicate that
   the page is locked for efficient testing in vmscan and,
   optionally, fault path.  This allows early culling of
   unevictable pages, preventing them from getting to
   page_referenced()/try_to_unmap().  Also allows separate
   accounting of mlock'd pages, as Nick's original patch
   did.

   Note:  Nick's original mlock patch used a PG_mlocked
   flag.  I had removed this in favor of the PG_unevictable
   flag + an mlock_count [new page struct member].  I
   restored the PG_mlocked flag to eliminate the new
   count field.

2) add the mlock/unevictable infrastructure to mm/mlock.c,
   with internal APIs in mm/internal.h.  This is a rework
   of Nick's original patch to these files, taking into
   account that mlocked pages are now kept on unevictable
   LRU list.

3) update vmscan.c:page_evictable() to check PageMlocked()
   and, if vma passed in, the vm_flags.  Note that the vma
   will only be passed in for new pages in the fault path;
   and then only if the "cull unevictable pages in fault
   path" patch is included.

4) add try_to_unlock() to rmap.c to walk a page's rmap and
   ClearPageMlocked() if no other vmas have it mlocked.
   Reuses as much of try_to_unmap() as possible.  This
   effectively replaces the use of one of the lru list links
   as an mlock count.  If this mechanism let's pages in mlocked
   vmas leak through w/o PG_mlocked set [I don't know that it
   does], we should catch them later in try_to_unmap().  One
   hopes this will be rare, as it will be relatively expensive.

Original mm/internal.h, mm/rmap.c and mm/mlock.c changes:
Signed-off-by: Nick Piggin <npiggin@suse.de>

splitlru: introduce __get_user_pages():

  New munlock processing need to GUP_FLAGS_IGNORE_VMA_PERMISSIONS.
  because current get_user_pages() can't grab PROT_NONE pages theresore it
  cause PROT_NONE pages can't munlock.

[akpm@linux-foundation.org: fix this for pagemap-pass-mm-into-pagewalkers.patch]
[akpm@linux-foundation.org: untangle patch interdependencies]
[akpm@linux-foundation.org: fix things after out-of-order merging]
[hugh@veritas.com: fix page-flags mess]
[lee.schermerhorn@hp.com: fix munlock page table walk - now requires 'mm']
[kosaki.motohiro@jp.fujitsu.com: build fix]
[kosaki.motohiro@jp.fujitsu.com: fix truncate race and sevaral comments]
[kosaki.motohiro@jp.fujitsu.com: splitlru: introduce __get_user_pages()]
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Dave Hansen <dave@linux.vnet.ibm.com>
Cc: Matt Mackall <mpm@selenic.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm.h         |   5 +
 include/linux/page-flags.h |  19 ++-
 include/linux/rmap.h       |  14 ++
 mm/internal.h              |  71 ++++++++
 mm/memory.c                |  56 ++++++-
 mm/migrate.c               |   2 +
 mm/mlock.c                 | 394 ++++++++++++++++++++++++++++++++++++++++++---
 mm/mmap.c                  |   2 -
 mm/nommu.c                 |  44 +++--
 mm/page_alloc.c            |   6 +-
 mm/rmap.c                  | 257 ++++++++++++++++++++++++-----
 mm/swap.c                  |   2 +-
 mm/vmscan.c                |  36 +++--
 13 files changed, 817 insertions(+), 91 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 40236290e2ae..ffee2f743418 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -131,6 +131,11 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_SequentialReadHint(v)	((v)->vm_flags & VM_SEQ_READ)
 #define VM_RandomReadHint(v)		((v)->vm_flags & VM_RAND_READ)
 
+/*
+ * special vmas that are non-mergable, non-mlock()able
+ */
+#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP)
+
 /*
  * mapping from the currently active vm_flags protection bits (the
  * low four bits) to a page protection mask..
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index ec1a1baad348..b12f93a3c345 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -96,6 +96,7 @@ enum pageflags {
 	PG_swapbacked,		/* Page is backed by RAM/swap */
 #ifdef CONFIG_UNEVICTABLE_LRU
 	PG_unevictable,		/* Page is "unevictable"  */
+	PG_mlocked,		/* Page is vma mlocked */
 #endif
 #ifdef CONFIG_IA64_UNCACHED_ALLOCATOR
 	PG_uncached,		/* Page has been mapped as uncached */
@@ -232,7 +233,17 @@ PAGEFLAG_FALSE(SwapCache)
 #ifdef CONFIG_UNEVICTABLE_LRU
 PAGEFLAG(Unevictable, unevictable) __CLEARPAGEFLAG(Unevictable, unevictable)
 	TESTCLEARFLAG(Unevictable, unevictable)
+
+#define MLOCK_PAGES 1
+PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked)
+	TESTSCFLAG(Mlocked, mlocked)
+
 #else
+
+#define MLOCK_PAGES 0
+PAGEFLAG_FALSE(Mlocked)
+	SETPAGEFLAG_NOOP(Mlocked) TESTCLEARFLAG_FALSE(Mlocked)
+
 PAGEFLAG_FALSE(Unevictable) TESTCLEARFLAG_FALSE(Unevictable)
 	SETPAGEFLAG_NOOP(Unevictable) CLEARPAGEFLAG_NOOP(Unevictable)
 	__CLEARPAGEFLAG_NOOP(Unevictable)
@@ -354,15 +365,17 @@ static inline void __ClearPageTail(struct page *page)
 #endif /* !PAGEFLAGS_EXTENDED */
 
 #ifdef CONFIG_UNEVICTABLE_LRU
-#define __PG_UNEVICTABLE (1 << PG_unevictable)
+#define __PG_UNEVICTABLE	(1 << PG_unevictable)
+#define __PG_MLOCKED		(1 << PG_mlocked)
 #else
-#define __PG_UNEVICTABLE 0
+#define __PG_UNEVICTABLE	0
+#define __PG_MLOCKED		0
 #endif
 
 #define PAGE_FLAGS	(1 << PG_lru   | 1 << PG_private   | 1 << PG_locked | \
 			 1 << PG_buddy | 1 << PG_writeback | \
 			 1 << PG_slab  | 1 << PG_swapcache | 1 << PG_active | \
-			 __PG_UNEVICTABLE)
+			 __PG_UNEVICTABLE | __PG_MLOCKED)
 
 /*
  * Flags checked in bad_page().  Pages on the free list should not have
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index fed6f5e0b411..955667e6a52d 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -117,6 +117,19 @@ unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
  */
 int page_mkclean(struct page *);
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+/*
+ * called in munlock()/munmap() path to check for other vmas holding
+ * the page mlocked.
+ */
+int try_to_munlock(struct page *);
+#else
+static inline int try_to_munlock(struct page *page)
+{
+	return 0;	/* a.k.a. SWAP_SUCCESS */
+}
+#endif
+
 #else	/* !CONFIG_MMU */
 
 #define anon_vma_init()		do {} while (0)
@@ -140,5 +153,6 @@ static inline int page_mkclean(struct page *page)
 #define SWAP_SUCCESS	0
 #define SWAP_AGAIN	1
 #define SWAP_FAIL	2
+#define SWAP_MLOCK	3
 
 #endif	/* _LINUX_RMAP_H */
diff --git a/mm/internal.h b/mm/internal.h
index 3db17b2a1ac6..4ebf0bef9a39 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -61,6 +61,10 @@ static inline unsigned long page_order(struct page *page)
 	return page_private(page);
 }
 
+extern int mlock_vma_pages_range(struct vm_area_struct *vma,
+			unsigned long start, unsigned long end);
+extern void munlock_vma_pages_all(struct vm_area_struct *vma);
+
 #ifdef CONFIG_UNEVICTABLE_LRU
 /*
  * unevictable_migrate_page() called only from migrate_page_copy() to
@@ -79,6 +83,65 @@ static inline void unevictable_migrate_page(struct page *new, struct page *old)
 }
 #endif
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+/*
+ * Called only in fault path via page_evictable() for a new page
+ * to determine if it's being mapped into a LOCKED vma.
+ * If so, mark page as mlocked.
+ */
+static inline int is_mlocked_vma(struct vm_area_struct *vma, struct page *page)
+{
+	VM_BUG_ON(PageLRU(page));
+
+	if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED))
+		return 0;
+
+	SetPageMlocked(page);
+	return 1;
+}
+
+/*
+ * must be called with vma's mmap_sem held for read, and page locked.
+ */
+extern void mlock_vma_page(struct page *page);
+
+/*
+ * Clear the page's PageMlocked().  This can be useful in a situation where
+ * we want to unconditionally remove a page from the pagecache -- e.g.,
+ * on truncation or freeing.
+ *
+ * It is legal to call this function for any page, mlocked or not.
+ * If called for a page that is still mapped by mlocked vmas, all we do
+ * is revert to lazy LRU behaviour -- semantics are not broken.
+ */
+extern void __clear_page_mlock(struct page *page);
+static inline void clear_page_mlock(struct page *page)
+{
+	if (unlikely(TestClearPageMlocked(page)))
+		__clear_page_mlock(page);
+}
+
+/*
+ * mlock_migrate_page - called only from migrate_page_copy() to
+ * migrate the Mlocked page flag
+ */
+static inline void mlock_migrate_page(struct page *newpage, struct page *page)
+{
+	if (TestClearPageMlocked(page))
+		SetPageMlocked(newpage);
+}
+
+
+#else /* CONFIG_UNEVICTABLE_LRU */
+static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
+{
+	return 0;
+}
+static inline void clear_page_mlock(struct page *page) { }
+static inline void mlock_vma_page(struct page *page) { }
+static inline void mlock_migrate_page(struct page *new, struct page *old) { }
+
+#endif /* CONFIG_UNEVICTABLE_LRU */
 
 /*
  * FLATMEM and DISCONTIGMEM configurations use alloc_bootmem_node,
@@ -148,4 +211,12 @@ static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
 }
 #endif /* CONFIG_SPARSEMEM */
 
+#define GUP_FLAGS_WRITE                  0x1
+#define GUP_FLAGS_FORCE                  0x2
+#define GUP_FLAGS_IGNORE_VMA_PERMISSIONS 0x4
+
+int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		     unsigned long start, int len, int flags,
+		     struct page **pages, struct vm_area_struct **vmas);
+
 #endif
diff --git a/mm/memory.c b/mm/memory.c
index 71cdefd1ef14..9fef7272fb9e 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -64,6 +64,8 @@
 
 #include "internal.h"
 
+#include "internal.h"
+
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 /* use the per-pgdat data instead for discontigmem - mbligh */
 unsigned long max_mapnr;
@@ -1129,12 +1131,17 @@ static inline int use_zero_page(struct vm_area_struct *vma)
 	return !vma->vm_ops || !vma->vm_ops->fault;
 }
 
-int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-		unsigned long start, int len, int write, int force,
+
+
+int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		     unsigned long start, int len, int flags,
 		struct page **pages, struct vm_area_struct **vmas)
 {
 	int i;
-	unsigned int vm_flags;
+	unsigned int vm_flags = 0;
+	int write = !!(flags & GUP_FLAGS_WRITE);
+	int force = !!(flags & GUP_FLAGS_FORCE);
+	int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
 
 	if (len <= 0)
 		return 0;
@@ -1158,7 +1165,9 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			pud_t *pud;
 			pmd_t *pmd;
 			pte_t *pte;
-			if (write) /* user gate pages are read-only */
+
+			/* user gate pages are read-only */
+			if (!ignore && write)
 				return i ? : -EFAULT;
 			if (pg > TASK_SIZE)
 				pgd = pgd_offset_k(pg);
@@ -1190,8 +1199,9 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			continue;
 		}
 
-		if (!vma || (vma->vm_flags & (VM_IO | VM_PFNMAP))
-				|| !(vm_flags & vma->vm_flags))
+		if (!vma ||
+		    (vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
+		    (!ignore && !(vm_flags & vma->vm_flags)))
 			return i ? : -EFAULT;
 
 		if (is_vm_hugetlb_page(vma)) {
@@ -1266,6 +1276,23 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	} while (len);
 	return i;
 }
+
+int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		unsigned long start, int len, int write, int force,
+		struct page **pages, struct vm_area_struct **vmas)
+{
+	int flags = 0;
+
+	if (write)
+		flags |= GUP_FLAGS_WRITE;
+	if (force)
+		flags |= GUP_FLAGS_FORCE;
+
+	return __get_user_pages(tsk, mm,
+				start, len, flags,
+				pages, vmas);
+}
+
 EXPORT_SYMBOL(get_user_pages);
 
 pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
@@ -1858,6 +1885,15 @@ gotten:
 	new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
 	if (!new_page)
 		goto oom;
+	/*
+	 * Don't let another task, with possibly unlocked vma,
+	 * keep the mlocked page.
+	 */
+	if (vma->vm_flags & VM_LOCKED) {
+		lock_page(old_page);	/* for LRU manipulation */
+		clear_page_mlock(old_page);
+		unlock_page(old_page);
+	}
 	cow_user_page(new_page, old_page, address, vma);
 	__SetPageUptodate(new_page);
 
@@ -2325,7 +2361,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	page_add_anon_rmap(page, vma, address);
 
 	swap_free(entry);
-	if (vm_swap_full())
+	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
 		remove_exclusive_swap_page(page);
 	unlock_page(page);
 
@@ -2465,6 +2501,12 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 				ret = VM_FAULT_OOM;
 				goto out;
 			}
+			/*
+			 * Don't let another task, with possibly unlocked vma,
+			 * keep the mlocked page.
+			 */
+			if (vma->vm_flags & VM_LOCKED)
+				clear_page_mlock(vmf.page);
 			copy_user_highpage(page, vmf.page, address, vma);
 			__SetPageUptodate(page);
 		} else {
diff --git a/mm/migrate.c b/mm/migrate.c
index b10237d8b459..6802a7a3dfec 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -371,6 +371,8 @@ static void migrate_page_copy(struct page *newpage, struct page *page)
 		__set_page_dirty_nobuffers(newpage);
  	}
 
+	mlock_migrate_page(newpage, page);
+
 #ifdef CONFIG_SWAP
 	ClearPageSwapCache(page);
 #endif
diff --git a/mm/mlock.c b/mm/mlock.c
index 01fbe93eff5c..8746fe3f9730 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -8,10 +8,18 @@
 #include <linux/capability.h>
 #include <linux/mman.h>
 #include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
+#include <linux/pagemap.h>
 #include <linux/mempolicy.h>
 #include <linux/syscalls.h>
 #include <linux/sched.h>
 #include <linux/module.h>
+#include <linux/rmap.h>
+#include <linux/mmzone.h>
+#include <linux/hugetlb.h>
+
+#include "internal.h"
 
 int can_do_mlock(void)
 {
@@ -23,17 +31,360 @@ int can_do_mlock(void)
 }
 EXPORT_SYMBOL(can_do_mlock);
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+/*
+ * Mlocked pages are marked with PageMlocked() flag for efficient testing
+ * in vmscan and, possibly, the fault path; and to support semi-accurate
+ * statistics.
+ *
+ * An mlocked page [PageMlocked(page)] is unevictable.  As such, it will
+ * be placed on the LRU "unevictable" list, rather than the [in]active lists.
+ * The unevictable list is an LRU sibling list to the [in]active lists.
+ * PageUnevictable is set to indicate the unevictable state.
+ *
+ * When lazy mlocking via vmscan, it is important to ensure that the
+ * vma's VM_LOCKED status is not concurrently being modified, otherwise we
+ * may have mlocked a page that is being munlocked. So lazy mlock must take
+ * the mmap_sem for read, and verify that the vma really is locked
+ * (see mm/rmap.c).
+ */
+
+/*
+ *  LRU accounting for clear_page_mlock()
+ */
+void __clear_page_mlock(struct page *page)
+{
+	VM_BUG_ON(!PageLocked(page));
+
+	if (!page->mapping) {	/* truncated ? */
+		return;
+	}
+
+	if (!isolate_lru_page(page)) {
+		putback_lru_page(page);
+	} else {
+		/*
+		 * Page not on the LRU yet.  Flush all pagevecs and retry.
+		 */
+		lru_add_drain_all();
+		if (!isolate_lru_page(page))
+			putback_lru_page(page);
+	}
+}
+
+/*
+ * Mark page as mlocked if not already.
+ * If page on LRU, isolate and putback to move to unevictable list.
+ */
+void mlock_vma_page(struct page *page)
+{
+	BUG_ON(!PageLocked(page));
+
+	if (!TestSetPageMlocked(page) && !isolate_lru_page(page))
+		putback_lru_page(page);
+}
+
+/*
+ * called from munlock()/munmap() path with page supposedly on the LRU.
+ *
+ * Note:  unlike mlock_vma_page(), we can't just clear the PageMlocked
+ * [in try_to_munlock()] and then attempt to isolate the page.  We must
+ * isolate the page to keep others from messing with its unevictable
+ * and mlocked state while trying to munlock.  However, we pre-clear the
+ * mlocked state anyway as we might lose the isolation race and we might
+ * not get another chance to clear PageMlocked.  If we successfully
+ * isolate the page and try_to_munlock() detects other VM_LOCKED vmas
+ * mapping the page, it will restore the PageMlocked state, unless the page
+ * is mapped in a non-linear vma.  So, we go ahead and SetPageMlocked(),
+ * perhaps redundantly.
+ * If we lose the isolation race, and the page is mapped by other VM_LOCKED
+ * vmas, we'll detect this in vmscan--via try_to_munlock() or try_to_unmap()
+ * either of which will restore the PageMlocked state by calling
+ * mlock_vma_page() above, if it can grab the vma's mmap sem.
+ */
+static void munlock_vma_page(struct page *page)
+{
+	BUG_ON(!PageLocked(page));
+
+	if (TestClearPageMlocked(page) && !isolate_lru_page(page)) {
+		try_to_munlock(page);
+		putback_lru_page(page);
+	}
+}
+
+/*
+ * mlock a range of pages in the vma.
+ *
+ * This takes care of making the pages present too.
+ *
+ * vma->vm_mm->mmap_sem must be held for write.
+ */
+static int __mlock_vma_pages_range(struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long addr = start;
+	struct page *pages[16]; /* 16 gives a reasonable batch */
+	int write = !!(vma->vm_flags & VM_WRITE);
+	int nr_pages = (end - start) / PAGE_SIZE;
+	int ret;
+
+	VM_BUG_ON(start & ~PAGE_MASK || end & ~PAGE_MASK);
+	VM_BUG_ON(start < vma->vm_start || end > vma->vm_end);
+	VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
+
+	lru_add_drain_all();	/* push cached pages to LRU */
+
+	while (nr_pages > 0) {
+		int i;
+
+		cond_resched();
+
+		/*
+		 * get_user_pages makes pages present if we are
+		 * setting mlock. and this extra reference count will
+		 * disable migration of this page.  However, page may
+		 * still be truncated out from under us.
+		 */
+		ret = get_user_pages(current, mm, addr,
+				min_t(int, nr_pages, ARRAY_SIZE(pages)),
+				write, 0, pages, NULL);
+		/*
+		 * This can happen for, e.g., VM_NONLINEAR regions before
+		 * a page has been allocated and mapped at a given offset,
+		 * or for addresses that map beyond end of a file.
+		 * We'll mlock the the pages if/when they get faulted in.
+		 */
+		if (ret < 0)
+			break;
+		if (ret == 0) {
+			/*
+			 * We know the vma is there, so the only time
+			 * we cannot get a single page should be an
+			 * error (ret < 0) case.
+			 */
+			WARN_ON(1);
+			break;
+		}
+
+		lru_add_drain();	/* push cached pages to LRU */
+
+		for (i = 0; i < ret; i++) {
+			struct page *page = pages[i];
+
+			lock_page(page);
+			/*
+			 * Because we lock page here and migration is blocked
+			 * by the elevated reference, we need only check for
+			 * page truncation (file-cache only).
+			 */
+			if (page->mapping)
+				mlock_vma_page(page);
+			unlock_page(page);
+			put_page(page);		/* ref from get_user_pages() */
+
+			/*
+			 * here we assume that get_user_pages() has given us
+			 * a list of virtually contiguous pages.
+			 */
+			addr += PAGE_SIZE;	/* for next get_user_pages() */
+			nr_pages--;
+		}
+	}
+
+	lru_add_drain_all();	/* to update stats */
+
+	return 0;	/* count entire vma as locked_vm */
+}
+
+/*
+ * private structure for munlock page table walk
+ */
+struct munlock_page_walk {
+	struct vm_area_struct *vma;
+	pmd_t                 *pmd; /* for migration_entry_wait() */
+};
+
+/*
+ * munlock normal pages for present ptes
+ */
+static int __munlock_pte_handler(pte_t *ptep, unsigned long addr,
+				   unsigned long end, struct mm_walk *walk)
+{
+	struct munlock_page_walk *mpw = walk->private;
+	swp_entry_t entry;
+	struct page *page;
+	pte_t pte;
+
+retry:
+	pte = *ptep;
+	/*
+	 * If it's a swap pte, we might be racing with page migration.
+	 */
+	if (unlikely(!pte_present(pte))) {
+		if (!is_swap_pte(pte))
+			goto out;
+		entry = pte_to_swp_entry(pte);
+		if (is_migration_entry(entry)) {
+			migration_entry_wait(mpw->vma->vm_mm, mpw->pmd, addr);
+			goto retry;
+		}
+		goto out;
+	}
+
+	page = vm_normal_page(mpw->vma, addr, pte);
+	if (!page)
+		goto out;
+
+	lock_page(page);
+	if (!page->mapping) {
+		unlock_page(page);
+		goto retry;
+	}
+	munlock_vma_page(page);
+	unlock_page(page);
+
+out:
+	return 0;
+}
+
+/*
+ * Save pmd for pte handler for waiting on migration entries
+ */
+static int __munlock_pmd_handler(pmd_t *pmd, unsigned long addr,
+				 unsigned long end, struct mm_walk *walk)
+{
+	struct munlock_page_walk *mpw = walk->private;
+
+	mpw->pmd = pmd;
+	return 0;
+}
+
+
+/*
+ * munlock a range of pages in the vma using standard page table walk.
+ *
+ * vma->vm_mm->mmap_sem must be held for write.
+ */
+static void __munlock_vma_pages_range(struct vm_area_struct *vma,
+			      unsigned long start, unsigned long end)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct munlock_page_walk mpw = {
+		.vma = vma,
+	};
+	struct mm_walk munlock_page_walk = {
+		.pmd_entry = __munlock_pmd_handler,
+		.pte_entry = __munlock_pte_handler,
+		.private = &mpw,
+		.mm = mm,
+	};
+
+	VM_BUG_ON(start & ~PAGE_MASK || end & ~PAGE_MASK);
+	VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
+	VM_BUG_ON(start < vma->vm_start);
+	VM_BUG_ON(end > vma->vm_end);
+
+	lru_add_drain_all();	/* push cached pages to LRU */
+	walk_page_range(start, end, &munlock_page_walk);
+	lru_add_drain_all();	/* to update stats */
+}
+
+#else /* CONFIG_UNEVICTABLE_LRU */
+
+/*
+ * Just make pages present if VM_LOCKED.  No-op if unlocking.
+ */
+static int __mlock_vma_pages_range(struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+	if (vma->vm_flags & VM_LOCKED)
+		make_pages_present(start, end);
+	return 0;
+}
+
+/*
+ * munlock a range of pages in the vma -- no-op.
+ */
+static void __munlock_vma_pages_range(struct vm_area_struct *vma,
+			      unsigned long start, unsigned long end)
+{
+}
+#endif /* CONFIG_UNEVICTABLE_LRU */
+
+/*
+ * mlock all pages in this vma range.  For mmap()/mremap()/...
+ */
+int mlock_vma_pages_range(struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+	int nr_pages = (end - start) / PAGE_SIZE;
+	BUG_ON(!(vma->vm_flags & VM_LOCKED));
+
+	/*
+	 * filter unlockable vmas
+	 */
+	if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+		goto no_mlock;
+
+	if (!((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
+			is_vm_hugetlb_page(vma) ||
+			vma == get_gate_vma(current)))
+		return __mlock_vma_pages_range(vma, start, end);
+
+	/*
+	 * User mapped kernel pages or huge pages:
+	 * make these pages present to populate the ptes, but
+	 * fall thru' to reset VM_LOCKED--no need to unlock, and
+	 * return nr_pages so these don't get counted against task's
+	 * locked limit.  huge pages are already counted against
+	 * locked vm limit.
+	 */
+	make_pages_present(start, end);
+
+no_mlock:
+	vma->vm_flags &= ~VM_LOCKED;	/* and don't come back! */
+	return nr_pages;		/* pages NOT mlocked */
+}
+
+
+/*
+ * munlock all pages in vma.   For munmap() and exit().
+ */
+void munlock_vma_pages_all(struct vm_area_struct *vma)
+{
+	vma->vm_flags &= ~VM_LOCKED;
+	__munlock_vma_pages_range(vma, vma->vm_start, vma->vm_end);
+}
+
+/*
+ * mlock_fixup  - handle mlock[all]/munlock[all] requests.
+ *
+ * Filters out "special" vmas -- VM_LOCKED never gets set for these, and
+ * munlock is a no-op.  However, for some special vmas, we go ahead and
+ * populate the ptes via make_pages_present().
+ *
+ * For vmas that pass the filters, merge/split as appropriate.
+ */
 static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	unsigned long start, unsigned long end, unsigned int newflags)
 {
-	struct mm_struct * mm = vma->vm_mm;
+	struct mm_struct *mm = vma->vm_mm;
 	pgoff_t pgoff;
-	int pages;
+	int nr_pages;
 	int ret = 0;
-
-	if (newflags == vma->vm_flags) {
-		*prev = vma;
-		goto out;
+	int lock = newflags & VM_LOCKED;
+
+	if (newflags == vma->vm_flags ||
+			(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+		goto out;	/* don't set VM_LOCKED,  don't count */
+
+	if ((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
+			is_vm_hugetlb_page(vma) ||
+			vma == get_gate_vma(current)) {
+		if (lock)
+			make_pages_present(start, end);
+		goto out;	/* don't set VM_LOCKED,  don't count */
 	}
 
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
@@ -44,8 +395,6 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 		goto success;
 	}
 
-	*prev = vma;
-
 	if (start != vma->vm_start) {
 		ret = split_vma(mm, vma, start, 1);
 		if (ret)
@@ -59,25 +408,32 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	}
 
 success:
+	/*
+	 * Keep track of amount of locked VM.
+	 */
+	nr_pages = (end - start) >> PAGE_SHIFT;
+	if (!lock)
+		nr_pages = -nr_pages;
+	mm->locked_vm += nr_pages;
+
 	/*
 	 * vm_flags is protected by the mmap_sem held in write mode.
 	 * It's okay if try_to_unmap_one unmaps a page just after we
-	 * set VM_LOCKED, make_pages_present below will bring it back.
+	 * set VM_LOCKED, __mlock_vma_pages_range will bring it back.
 	 */
 	vma->vm_flags = newflags;
 
-	/*
-	 * Keep track of amount of locked VM.
-	 */
-	pages = (end - start) >> PAGE_SHIFT;
-	if (newflags & VM_LOCKED) {
-		pages = -pages;
-		if (!(newflags & VM_IO))
-			ret = make_pages_present(start, end);
-	}
+	if (lock) {
+		ret = __mlock_vma_pages_range(vma, start, end);
+		if (ret > 0) {
+			mm->locked_vm -= ret;
+			ret = 0;
+		}
+	} else
+		__munlock_vma_pages_range(vma, start, end);
 
-	mm->locked_vm -= pages;
 out:
+	*prev = vma;
 	return ret;
 }
 
diff --git a/mm/mmap.c b/mm/mmap.c
index e7a5a68a9c2e..7bdfd2661f17 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -662,8 +662,6 @@ again:			remove_next = 1 + (end > next->vm_end);
  * If the vma has a ->close operation then the driver probably needs to release
  * per-vma resources, so we don't attempt to merge those.
  */
-#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP)
-
 static inline int is_mergeable_vma(struct vm_area_struct *vma,
 			struct file *file, unsigned long vm_flags)
 {
diff --git a/mm/nommu.c b/mm/nommu.c
index ed75bc962fbe..2696b24f2bb3 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -34,6 +34,8 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
+#include "internal.h"
+
 void *high_memory;
 struct page *mem_map;
 unsigned long max_mapnr;
@@ -128,20 +130,16 @@ unsigned int kobjsize(const void *objp)
 	return PAGE_SIZE << compound_order(page);
 }
 
-/*
- * get a list of pages in an address range belonging to the specified process
- * and indicate the VMA that covers each page
- * - this is potentially dodgy as we may end incrementing the page count of a
- *   slab page or a secondary page from a compound page
- * - don't permit access to VMAs that don't support it, such as I/O mappings
- */
-int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
-	unsigned long start, int len, int write, int force,
-	struct page **pages, struct vm_area_struct **vmas)
+int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+		     unsigned long start, int len, int flags,
+		struct page **pages, struct vm_area_struct **vmas)
 {
 	struct vm_area_struct *vma;
 	unsigned long vm_flags;
 	int i;
+	int write = !!(flags & GUP_FLAGS_WRITE);
+	int force = !!(flags & GUP_FLAGS_FORCE);
+	int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
 
 	/* calculate required read or write permissions.
 	 * - if 'force' is set, we only require the "MAY" flags.
@@ -156,7 +154,7 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 
 		/* protect what we can, including chardevs */
 		if (vma->vm_flags & (VM_IO | VM_PFNMAP) ||
-		    !(vm_flags & vma->vm_flags))
+		    (!ignore && !(vm_flags & vma->vm_flags)))
 			goto finish_or_fault;
 
 		if (pages) {
@@ -174,6 +172,30 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 finish_or_fault:
 	return i ? : -EFAULT;
 }
+
+
+/*
+ * get a list of pages in an address range belonging to the specified process
+ * and indicate the VMA that covers each page
+ * - this is potentially dodgy as we may end incrementing the page count of a
+ *   slab page or a secondary page from a compound page
+ * - don't permit access to VMAs that don't support it, such as I/O mappings
+ */
+int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+	unsigned long start, int len, int write, int force,
+	struct page **pages, struct vm_area_struct **vmas)
+{
+	int flags = 0;
+
+	if (write)
+		flags |= GUP_FLAGS_WRITE;
+	if (force)
+		flags |= GUP_FLAGS_FORCE;
+
+	return __get_user_pages(tsk, mm,
+				start, len, flags,
+				pages, vmas);
+}
 EXPORT_SYMBOL(get_user_pages);
 
 DEFINE_RWLOCK(vmlist_lock);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4125230a1b2c..5886586fde6c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -616,7 +616,11 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
 
 	page->flags &= ~(1 << PG_uptodate | 1 << PG_error | 1 << PG_reclaim |
 			1 << PG_referenced | 1 << PG_arch_1 |
-			1 << PG_owner_priv_1 | 1 << PG_mappedtodisk);
+			1 << PG_owner_priv_1 | 1 << PG_mappedtodisk
+#ifdef CONFIG_UNEVICTABLE_LRU
+			| 1 << PG_mlocked
+#endif
+			);
 	set_page_private(page, 0);
 	set_page_refcounted(page);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index e8d639b16c6d..7e60df99018e 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -53,6 +53,8 @@
 
 #include <asm/tlbflush.h>
 
+#include "internal.h"
+
 struct kmem_cache *anon_vma_cachep;
 
 /**
@@ -290,6 +292,32 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm,
 	return NULL;
 }
 
+/**
+ * page_mapped_in_vma - check whether a page is really mapped in a VMA
+ * @page: the page to test
+ * @vma: the VMA to test
+ *
+ * Returns 1 if the page is mapped into the page tables of the VMA, 0
+ * if the page is not mapped into the page tables of this VMA.  Only
+ * valid for normal file or anonymous VMAs.
+ */
+static int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
+{
+	unsigned long address;
+	pte_t *pte;
+	spinlock_t *ptl;
+
+	address = vma_address(page, vma);
+	if (address == -EFAULT)		/* out of vma range */
+		return 0;
+	pte = page_check_address(page, vma->vm_mm, address, &ptl, 1);
+	if (!pte)			/* the page is not in this mm */
+		return 0;
+	pte_unmap_unlock(pte, ptl);
+
+	return 1;
+}
+
 /*
  * Subfunctions of page_referenced: page_referenced_one called
  * repeatedly from either page_referenced_anon or page_referenced_file.
@@ -311,10 +339,17 @@ static int page_referenced_one(struct page *page,
 	if (!pte)
 		goto out;
 
+	/*
+	 * Don't want to elevate referenced for mlocked page that gets this far,
+	 * in order that it progresses to try_to_unmap and is moved to the
+	 * unevictable list.
+	 */
 	if (vma->vm_flags & VM_LOCKED) {
-		referenced++;
 		*mapcount = 1;	/* break early from loop */
-	} else if (ptep_clear_flush_young_notify(vma, address, pte))
+		goto out_unmap;
+	}
+
+	if (ptep_clear_flush_young_notify(vma, address, pte))
 		referenced++;
 
 	/* Pretend the page is referenced if the task has the
@@ -323,6 +358,7 @@ static int page_referenced_one(struct page *page,
 			rwsem_is_locked(&mm->mmap_sem))
 		referenced++;
 
+out_unmap:
 	(*mapcount)--;
 	pte_unmap_unlock(pte, ptl);
 out:
@@ -412,11 +448,6 @@ static int page_referenced_file(struct page *page,
 		 */
 		if (mem_cont && !mm_match_cgroup(vma->vm_mm, mem_cont))
 			continue;
-		if ((vma->vm_flags & (VM_LOCKED|VM_MAYSHARE))
-				  == (VM_LOCKED|VM_MAYSHARE)) {
-			referenced++;
-			break;
-		}
 		referenced += page_referenced_one(page, vma, &mapcount);
 		if (!mapcount)
 			break;
@@ -739,11 +770,16 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
 	 * If it's recently referenced (perhaps page_referenced
 	 * skipped over this mm) then we should reactivate it.
 	 */
-	if (!migration && ((vma->vm_flags & VM_LOCKED) ||
-			(ptep_clear_flush_young_notify(vma, address, pte)))) {
-		ret = SWAP_FAIL;
-		goto out_unmap;
-	}
+	if (!migration) {
+		if (vma->vm_flags & VM_LOCKED) {
+			ret = SWAP_MLOCK;
+			goto out_unmap;
+		}
+		if (ptep_clear_flush_young_notify(vma, address, pte)) {
+			ret = SWAP_FAIL;
+			goto out_unmap;
+		}
+  	}
 
 	/* Nuke the page table entry. */
 	flush_cache_page(vma, address, page_to_pfn(page));
@@ -824,12 +860,17 @@ out:
  * For very sparsely populated VMAs this is a little inefficient - chances are
  * there there won't be many ptes located within the scan cluster.  In this case
  * maybe we could scan further - to the end of the pte page, perhaps.
+ *
+ * Mlocked pages:  check VM_LOCKED under mmap_sem held for read, if we can
+ * acquire it without blocking.  If vma locked, mlock the pages in the cluster,
+ * rather than unmapping them.  If we encounter the "check_page" that vmscan is
+ * trying to unmap, return SWAP_MLOCK, else default SWAP_AGAIN.
  */
 #define CLUSTER_SIZE	min(32*PAGE_SIZE, PMD_SIZE)
 #define CLUSTER_MASK	(~(CLUSTER_SIZE - 1))
 
-static void try_to_unmap_cluster(unsigned long cursor,
-	unsigned int *mapcount, struct vm_area_struct *vma)
+static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
+		struct vm_area_struct *vma, struct page *check_page)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
@@ -841,6 +882,8 @@ static void try_to_unmap_cluster(unsigned long cursor,
 	struct page *page;
 	unsigned long address;
 	unsigned long end;
+	int ret = SWAP_AGAIN;
+	int locked_vma = 0;
 
 	address = (vma->vm_start + cursor) & CLUSTER_MASK;
 	end = address + CLUSTER_SIZE;
@@ -851,15 +894,26 @@ static void try_to_unmap_cluster(unsigned long cursor,
 
 	pgd = pgd_offset(mm, address);
 	if (!pgd_present(*pgd))
-		return;
+		return ret;
 
 	pud = pud_offset(pgd, address);
 	if (!pud_present(*pud))
-		return;
+		return ret;
 
 	pmd = pmd_offset(pud, address);
 	if (!pmd_present(*pmd))
-		return;
+		return ret;
+
+	/*
+	 * MLOCK_PAGES => feature is configured.
+	 * if we can acquire the mmap_sem for read, and vma is VM_LOCKED,
+	 * keep the sem while scanning the cluster for mlocking pages.
+	 */
+	if (MLOCK_PAGES && down_read_trylock(&vma->vm_mm->mmap_sem)) {
+		locked_vma = (vma->vm_flags & VM_LOCKED);
+		if (!locked_vma)
+			up_read(&vma->vm_mm->mmap_sem); /* don't need it */
+	}
 
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
 
@@ -872,6 +926,13 @@ static void try_to_unmap_cluster(unsigned long cursor,
 		page = vm_normal_page(vma, address, *pte);
 		BUG_ON(!page || PageAnon(page));
 
+		if (locked_vma) {
+			mlock_vma_page(page);   /* no-op if already mlocked */
+			if (page == check_page)
+				ret = SWAP_MLOCK;
+			continue;	/* don't unmap */
+		}
+
 		if (ptep_clear_flush_young_notify(vma, address, pte))
 			continue;
 
@@ -893,39 +954,104 @@ static void try_to_unmap_cluster(unsigned long cursor,
 		(*mapcount)--;
 	}
 	pte_unmap_unlock(pte - 1, ptl);
+	if (locked_vma)
+		up_read(&vma->vm_mm->mmap_sem);
+	return ret;
 }
 
-static int try_to_unmap_anon(struct page *page, int migration)
+/*
+ * common handling for pages mapped in VM_LOCKED vmas
+ */
+static int try_to_mlock_page(struct page *page, struct vm_area_struct *vma)
+{
+	int mlocked = 0;
+
+	if (down_read_trylock(&vma->vm_mm->mmap_sem)) {
+		if (vma->vm_flags & VM_LOCKED) {
+			mlock_vma_page(page);
+			mlocked++;	/* really mlocked the page */
+		}
+		up_read(&vma->vm_mm->mmap_sem);
+	}
+	return mlocked;
+}
+
+/**
+ * try_to_unmap_anon - unmap or unlock anonymous page using the object-based
+ * rmap method
+ * @page: the page to unmap/unlock
+ * @unlock:  request for unlock rather than unmap [unlikely]
+ * @migration:  unmapping for migration - ignored if @unlock
+ *
+ * Find all the mappings of a page using the mapping pointer and the vma chains
+ * contained in the anon_vma struct it points to.
+ *
+ * This function is only called from try_to_unmap/try_to_munlock for
+ * anonymous pages.
+ * When called from try_to_munlock(), the mmap_sem of the mm containing the vma
+ * where the page was found will be held for write.  So, we won't recheck
+ * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
+ * 'LOCKED.
+ */
+static int try_to_unmap_anon(struct page *page, int unlock, int migration)
 {
 	struct anon_vma *anon_vma;
 	struct vm_area_struct *vma;
+	unsigned int mlocked = 0;
 	int ret = SWAP_AGAIN;
 
+	if (MLOCK_PAGES && unlikely(unlock))
+		ret = SWAP_SUCCESS;	/* default for try_to_munlock() */
+
 	anon_vma = page_lock_anon_vma(page);
 	if (!anon_vma)
 		return ret;
 
 	list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
-		ret = try_to_unmap_one(page, vma, migration);
-		if (ret == SWAP_FAIL || !page_mapped(page))
-			break;
+		if (MLOCK_PAGES && unlikely(unlock)) {
+			if (!((vma->vm_flags & VM_LOCKED) &&
+			      page_mapped_in_vma(page, vma)))
+				continue;  /* must visit all unlocked vmas */
+			ret = SWAP_MLOCK;  /* saw at least one mlocked vma */
+		} else {
+			ret = try_to_unmap_one(page, vma, migration);
+			if (ret == SWAP_FAIL || !page_mapped(page))
+				break;
+		}
+		if (ret == SWAP_MLOCK) {
+			mlocked = try_to_mlock_page(page, vma);
+			if (mlocked)
+				break;	/* stop if actually mlocked page */
+		}
 	}
 
 	page_unlock_anon_vma(anon_vma);
+
+	if (mlocked)
+		ret = SWAP_MLOCK;	/* actually mlocked the page */
+	else if (ret == SWAP_MLOCK)
+		ret = SWAP_AGAIN;	/* saw VM_LOCKED vma */
+
 	return ret;
 }
 
 /**
- * try_to_unmap_file - unmap file page using the object-based rmap method
- * @page: the page to unmap
- * @migration: migration flag
+ * try_to_unmap_file - unmap/unlock file page using the object-based rmap method
+ * @page: the page to unmap/unlock
+ * @unlock:  request for unlock rather than unmap [unlikely]
+ * @migration:  unmapping for migration - ignored if @unlock
  *
  * Find all the mappings of a page using the mapping pointer and the vma chains
  * contained in the address_space struct it points to.
  *
- * This function is only called from try_to_unmap for object-based pages.
+ * This function is only called from try_to_unmap/try_to_munlock for
+ * object-based pages.
+ * When called from try_to_munlock(), the mmap_sem of the mm containing the vma
+ * where the page was found will be held for write.  So, we won't recheck
+ * vm_flags for that VMA.  That should be OK, because that vma shouldn't be
+ * 'LOCKED.
  */
-static int try_to_unmap_file(struct page *page, int migration)
+static int try_to_unmap_file(struct page *page, int unlock, int migration)
 {
 	struct address_space *mapping = page->mapping;
 	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
@@ -936,20 +1062,44 @@ static int try_to_unmap_file(struct page *page, int migration)
 	unsigned long max_nl_cursor = 0;
 	unsigned long max_nl_size = 0;
 	unsigned int mapcount;
+	unsigned int mlocked = 0;
+
+	if (MLOCK_PAGES && unlikely(unlock))
+		ret = SWAP_SUCCESS;	/* default for try_to_munlock() */
 
 	spin_lock(&mapping->i_mmap_lock);
 	vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) {
-		ret = try_to_unmap_one(page, vma, migration);
-		if (ret == SWAP_FAIL || !page_mapped(page))
-			goto out;
+		if (MLOCK_PAGES && unlikely(unlock)) {
+			if (!(vma->vm_flags & VM_LOCKED))
+				continue;	/* must visit all vmas */
+			ret = SWAP_MLOCK;
+		} else {
+			ret = try_to_unmap_one(page, vma, migration);
+			if (ret == SWAP_FAIL || !page_mapped(page))
+				goto out;
+		}
+		if (ret == SWAP_MLOCK) {
+			mlocked = try_to_mlock_page(page, vma);
+			if (mlocked)
+				break;  /* stop if actually mlocked page */
+		}
 	}
 
+	if (mlocked)
+		goto out;
+
 	if (list_empty(&mapping->i_mmap_nonlinear))
 		goto out;
 
 	list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
 						shared.vm_set.list) {
-		if ((vma->vm_flags & VM_LOCKED) && !migration)
+		if (MLOCK_PAGES && unlikely(unlock)) {
+			if (!(vma->vm_flags & VM_LOCKED))
+				continue;	/* must visit all vmas */
+			ret = SWAP_MLOCK;	/* leave mlocked == 0 */
+			goto out;		/* no need to look further */
+		}
+		if (!MLOCK_PAGES && !migration && (vma->vm_flags & VM_LOCKED))
 			continue;
 		cursor = (unsigned long) vma->vm_private_data;
 		if (cursor > max_nl_cursor)
@@ -959,7 +1109,7 @@ static int try_to_unmap_file(struct page *page, int migration)
 			max_nl_size = cursor;
 	}
 
-	if (max_nl_size == 0) {	/* any nonlinears locked or reserved */
+	if (max_nl_size == 0) {	/* all nonlinears locked or reserved ? */
 		ret = SWAP_FAIL;
 		goto out;
 	}
@@ -983,12 +1133,16 @@ static int try_to_unmap_file(struct page *page, int migration)
 	do {
 		list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
 						shared.vm_set.list) {
-			if ((vma->vm_flags & VM_LOCKED) && !migration)
+			if (!MLOCK_PAGES && !migration &&
+			    (vma->vm_flags & VM_LOCKED))
 				continue;
 			cursor = (unsigned long) vma->vm_private_data;
 			while ( cursor < max_nl_cursor &&
 				cursor < vma->vm_end - vma->vm_start) {
-				try_to_unmap_cluster(cursor, &mapcount, vma);
+				ret = try_to_unmap_cluster(cursor, &mapcount,
+								vma, page);
+				if (ret == SWAP_MLOCK)
+					mlocked = 2;	/* to return below */
 				cursor += CLUSTER_SIZE;
 				vma->vm_private_data = (void *) cursor;
 				if ((int)mapcount <= 0)
@@ -1009,6 +1163,10 @@ static int try_to_unmap_file(struct page *page, int migration)
 		vma->vm_private_data = NULL;
 out:
 	spin_unlock(&mapping->i_mmap_lock);
+	if (mlocked)
+		ret = SWAP_MLOCK;	/* actually mlocked the page */
+	else if (ret == SWAP_MLOCK)
+		ret = SWAP_AGAIN;	/* saw VM_LOCKED vma */
 	return ret;
 }
 
@@ -1024,6 +1182,7 @@ out:
  * SWAP_SUCCESS	- we succeeded in removing all mappings
  * SWAP_AGAIN	- we missed a mapping, try again later
  * SWAP_FAIL	- the page is unswappable
+ * SWAP_MLOCK	- page is mlocked.
  */
 int try_to_unmap(struct page *page, int migration)
 {
@@ -1032,12 +1191,36 @@ int try_to_unmap(struct page *page, int migration)
 	BUG_ON(!PageLocked(page));
 
 	if (PageAnon(page))
-		ret = try_to_unmap_anon(page, migration);
+		ret = try_to_unmap_anon(page, 0, migration);
 	else
-		ret = try_to_unmap_file(page, migration);
-
-	if (!page_mapped(page))
+		ret = try_to_unmap_file(page, 0, migration);
+	if (ret != SWAP_MLOCK && !page_mapped(page))
 		ret = SWAP_SUCCESS;
 	return ret;
 }
 
+#ifdef CONFIG_UNEVICTABLE_LRU
+/**
+ * try_to_munlock - try to munlock a page
+ * @page: the page to be munlocked
+ *
+ * Called from munlock code.  Checks all of the VMAs mapping the page
+ * to make sure nobody else has this page mlocked. The page will be
+ * returned with PG_mlocked cleared if no other vmas have it mlocked.
+ *
+ * Return values are:
+ *
+ * SWAP_SUCCESS	- no vma's holding page mlocked.
+ * SWAP_AGAIN	- page mapped in mlocked vma -- couldn't acquire mmap sem
+ * SWAP_MLOCK	- page is now mlocked.
+ */
+int try_to_munlock(struct page *page)
+{
+	VM_BUG_ON(!PageLocked(page) || PageLRU(page));
+
+	if (PageAnon(page))
+		return try_to_unmap_anon(page, 1, 0);
+	else
+		return try_to_unmap_file(page, 1, 0);
+}
+#endif
diff --git a/mm/swap.c b/mm/swap.c
index fee6b973f143..bc58c1369dd6 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -278,7 +278,7 @@ void lru_add_drain(void)
 	put_cpu();
 }
 
-#ifdef CONFIG_NUMA
+#if defined(CONFIG_NUMA) || defined(CONFIG_UNEVICTABLE_LRU)
 static void lru_add_drain_per_cpu(struct work_struct *dummy)
 {
 	lru_add_drain();
diff --git a/mm/vmscan.c b/mm/vmscan.c
index dfb342e0db9b..e5aaaad159ef 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -582,11 +582,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 
 		sc->nr_scanned++;
 
-		if (unlikely(!page_evictable(page, NULL))) {
-			unlock_page(page);
-			putback_lru_page(page);
-			continue;
-		}
+		if (unlikely(!page_evictable(page, NULL)))
+			goto cull_mlocked;
 
 		if (!sc->may_swap && page_mapped(page))
 			goto keep_locked;
@@ -624,9 +621,19 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * Anonymous process memory has backing store?
 		 * Try to allocate it some swap space here.
 		 */
-		if (PageAnon(page) && !PageSwapCache(page))
+		if (PageAnon(page) && !PageSwapCache(page)) {
+			switch (try_to_munlock(page)) {
+			case SWAP_FAIL:		/* shouldn't happen */
+			case SWAP_AGAIN:
+				goto keep_locked;
+			case SWAP_MLOCK:
+				goto cull_mlocked;
+			case SWAP_SUCCESS:
+				; /* fall thru'; add to swap cache */
+			}
 			if (!add_to_swap(page, GFP_ATOMIC))
 				goto activate_locked;
+		}
 #endif /* CONFIG_SWAP */
 
 		mapping = page_mapping(page);
@@ -641,6 +648,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				goto activate_locked;
 			case SWAP_AGAIN:
 				goto keep_locked;
+			case SWAP_MLOCK:
+				goto cull_mlocked;
 			case SWAP_SUCCESS:
 				; /* try to free the page below */
 			}
@@ -731,6 +740,11 @@ free_it:
 		}
 		continue;
 
+cull_mlocked:
+		unlock_page(page);
+		putback_lru_page(page);
+		continue;
+
 activate_locked:
 		/* Not a candidate for swapping, so reclaim swap space. */
 		if (PageSwapCache(page) && vm_swap_full())
@@ -742,7 +756,7 @@ keep_locked:
 		unlock_page(page);
 keep:
 		list_add(&page->lru, &ret_pages);
-		VM_BUG_ON(PageLRU(page));
+		VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
 	}
 	list_splice(&ret_pages, page_list);
 	if (pagevec_count(&freed_pvec))
@@ -2329,12 +2343,13 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
  * @vma: the VMA in which the page is or will be mapped, may be NULL
  *
  * Test whether page is evictable--i.e., should be placed on active/inactive
- * lists vs unevictable list.
+ * lists vs unevictable list.  The vma argument is !NULL when called from the
+ * fault path to determine how to instantate a new page.
  *
  * Reasons page might not be evictable:
  * (1) page's mapping marked unevictable
+ * (2) page is part of an mlocked VMA
  *
- * TODO - later patches
  */
 int page_evictable(struct page *page, struct vm_area_struct *vma)
 {
@@ -2342,7 +2357,8 @@ int page_evictable(struct page *page, struct vm_area_struct *vma)
 	if (mapping_unevictable(page_mapping(page)))
 		return 0;
 
-	/* TODO:  test page [!]evictable conditions */
+	if (PageMlocked(page) || (vma && is_mlocked_vma(vma, page)))
+		return 0;
 
 	return 1;
 }
-- 
cgit v1.2.3


From 5344b7e648980cc2ca613ec03a56a8222ff48820 Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Sat, 18 Oct 2008 20:26:51 -0700
Subject: vmstat: mlocked pages statistics

Add NR_MLOCK zone page state, which provides a (conservative) count of
mlocked pages (actually, the number of mlocked pages moved off the LRU).

Reworked by lts to fit in with the modified mlock page support in the
Reclaim Scalability series.

[kosaki.motohiro@jp.fujitsu.com: fix incorrect Mlocked field of /proc/meminfo]
[lee.schermerhorn@hp.com: mlocked-pages: add event counting with statistics]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/node.c    |  4 +++-
 fs/proc/proc_misc.c    |  2 ++
 include/linux/mmzone.h |  2 ++
 include/linux/vmstat.h |  4 ++++
 mm/internal.h          | 16 +++++++++++++---
 mm/mlock.c             | 41 ++++++++++++++++++++++++++++++++++++-----
 mm/vmstat.c            |  5 +++++
 7 files changed, 65 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 11a9a05cf554..fb45d88a2446 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -71,7 +71,8 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
 		       "Node %d Active(file):   %8lu kB\n"
 		       "Node %d Inactive(file): %8lu kB\n"
 #ifdef CONFIG_UNEVICTABLE_LRU
-		       "Node %d Noreclaim:      %8lu kB\n"
+		       "Node %d Unevictable:    %8lu kB\n"
+		       "Node %d Mlocked:        %8lu kB\n"
 #endif
 #ifdef CONFIG_HIGHMEM
 		       "Node %d HighTotal:      %8lu kB\n"
@@ -104,6 +105,7 @@ static ssize_t node_read_meminfo(struct sys_device * dev,
 		       nid, K(node_page_state(nid, NR_INACTIVE_FILE)),
 #ifdef CONFIG_UNEVICTABLE_LRU
 		       nid, K(node_page_state(nid, NR_UNEVICTABLE)),
+		       nid, K(node_page_state(nid, NR_MLOCK)),
 #endif
 #ifdef CONFIG_HIGHMEM
 		       nid, K(i.totalhigh),
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 6dd60eaea997..61b25f4eabe6 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -176,6 +176,7 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 		"Inactive(file): %8lu kB\n"
 #ifdef CONFIG_UNEVICTABLE_LRU
 		"Unevictable:    %8lu kB\n"
+		"Mlocked:        %8lu kB\n"
 #endif
 #ifdef CONFIG_HIGHMEM
 		"HighTotal:      %8lu kB\n"
@@ -217,6 +218,7 @@ static int meminfo_read_proc(char *page, char **start, off_t off,
 		K(pages[LRU_INACTIVE_FILE]),
 #ifdef CONFIG_UNEVICTABLE_LRU
 		K(pages[LRU_UNEVICTABLE]),
+		K(global_page_state(NR_MLOCK)),
 #endif
 #ifdef CONFIG_HIGHMEM
 		K(i.totalhigh),
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index d1f60d5fe2ea..da2d053a95f1 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -88,8 +88,10 @@ enum zone_stat_item {
 	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
 #ifdef CONFIG_UNEVICTABLE_LRU
 	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
+	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
 #else
 	NR_UNEVICTABLE = NR_ACTIVE_FILE, /* avoid compiler errors in dead code */
+	NR_MLOCK = NR_ACTIVE_FILE,
 #endif
 	NR_ANON_PAGES,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 135840cd7feb..05b805020be2 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -45,6 +45,10 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		UNEVICTABLE_PGCULLED,	/* culled to noreclaim list */
 		UNEVICTABLE_PGSCANNED,	/* scanned for reclaimability */
 		UNEVICTABLE_PGRESCUED,	/* rescued from noreclaim list */
+		UNEVICTABLE_PGMLOCKED,
+		UNEVICTABLE_PGMUNLOCKED,
+		UNEVICTABLE_PGCLEARED,	/* on COW, page truncate */
+		UNEVICTABLE_PGSTRANDED,	/* unable to isolate on unlock */
 #endif
 		NR_VM_EVENT_ITEMS
 };
diff --git a/mm/internal.h b/mm/internal.h
index 48e32f790571..1cfbf2e2bc9e 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -101,7 +101,10 @@ static inline int is_mlocked_vma(struct vm_area_struct *vma, struct page *page)
 	if (likely((vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) != VM_LOCKED))
 		return 0;
 
-	SetPageMlocked(page);
+	if (!TestSetPageMlocked(page)) {
+		inc_zone_page_state(page, NR_MLOCK);
+		count_vm_event(UNEVICTABLE_PGMLOCKED);
+	}
 	return 1;
 }
 
@@ -128,12 +131,19 @@ static inline void clear_page_mlock(struct page *page)
 
 /*
  * mlock_migrate_page - called only from migrate_page_copy() to
- * migrate the Mlocked page flag
+ * migrate the Mlocked page flag; update statistics.
  */
 static inline void mlock_migrate_page(struct page *newpage, struct page *page)
 {
-	if (TestClearPageMlocked(page))
+	if (TestClearPageMlocked(page)) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		__dec_zone_page_state(page, NR_MLOCK);
 		SetPageMlocked(newpage);
+		__inc_zone_page_state(newpage, NR_MLOCK);
+		local_irq_restore(flags);
+	}
 }
 
 
diff --git a/mm/mlock.c b/mm/mlock.c
index 8b478350a2a1..bce1b22c36c2 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -60,6 +60,8 @@ void __clear_page_mlock(struct page *page)
 		return;
 	}
 
+	dec_zone_page_state(page, NR_MLOCK);
+	count_vm_event(UNEVICTABLE_PGCLEARED);
 	if (!isolate_lru_page(page)) {
 		putback_lru_page(page);
 	} else {
@@ -69,6 +71,9 @@ void __clear_page_mlock(struct page *page)
 		lru_add_drain_all();
 		if (!isolate_lru_page(page))
 			putback_lru_page(page);
+		else if (PageUnevictable(page))
+			count_vm_event(UNEVICTABLE_PGSTRANDED);
+
 	}
 }
 
@@ -80,8 +85,12 @@ void mlock_vma_page(struct page *page)
 {
 	BUG_ON(!PageLocked(page));
 
-	if (!TestSetPageMlocked(page) && !isolate_lru_page(page))
-		putback_lru_page(page);
+	if (!TestSetPageMlocked(page)) {
+		inc_zone_page_state(page, NR_MLOCK);
+		count_vm_event(UNEVICTABLE_PGMLOCKED);
+		if (!isolate_lru_page(page))
+			putback_lru_page(page);
+	}
 }
 
 /*
@@ -106,9 +115,31 @@ static void munlock_vma_page(struct page *page)
 {
 	BUG_ON(!PageLocked(page));
 
-	if (TestClearPageMlocked(page) && !isolate_lru_page(page)) {
-		try_to_munlock(page);
-		putback_lru_page(page);
+	if (TestClearPageMlocked(page)) {
+		dec_zone_page_state(page, NR_MLOCK);
+		if (!isolate_lru_page(page)) {
+			int ret = try_to_munlock(page);
+			/*
+			 * did try_to_unlock() succeed or punt?
+			 */
+			if (ret == SWAP_SUCCESS || ret == SWAP_AGAIN)
+				count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+
+			putback_lru_page(page);
+		} else {
+			/*
+			 * We lost the race.  let try_to_unmap() deal
+			 * with it.  At least we get the page state and
+			 * mlock stats right.  However, page is still on
+			 * the noreclaim list.  We'll fix that up when
+			 * the page is eventually freed or we scan the
+			 * noreclaim list.
+			 */
+			if (PageUnevictable(page))
+				count_vm_event(UNEVICTABLE_PGSTRANDED);
+			else
+				count_vm_event(UNEVICTABLE_PGMUNLOCKED);
+		}
 	}
 }
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6db2f6319313..9e28abc0a0b9 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -625,6 +625,7 @@ static const char * const vmstat_text[] = {
 	"nr_active_file",
 #ifdef CONFIG_UNEVICTABLE_LRU
 	"nr_unevictable",
+	"nr_mlock",
 #endif
 	"nr_anon_pages",
 	"nr_mapped",
@@ -684,6 +685,10 @@ static const char * const vmstat_text[] = {
 	"unevictable_pgs_culled",
 	"unevictable_pgs_scanned",
 	"unevictable_pgs_rescued",
+	"unevictable_pgs_mlocked",
+	"unevictable_pgs_munlocked",
+	"unevictable_pgs_cleared",
+	"unevictable_pgs_stranded",
 #endif
 #endif
 };
-- 
cgit v1.2.3


From 64d6519dda3905dfb94d3f93c07c5f263f41813f Mon Sep 17 00:00:00 2001
From: Lee Schermerhorn <lee.schermerhorn@hp.com>
Date: Sat, 18 Oct 2008 20:26:52 -0700
Subject: swap: cull unevictable pages in fault path

In the fault paths that install new anonymous pages, check whether the
page is evictable or not using lru_cache_add_active_or_unevictable().  If
the page is evictable, just add it to the active lru list [via the pagevec
cache], else add it to the unevictable list.

This "proactive" culling in the fault path mimics the handling of mlocked
pages in Nick Piggin's series to keep mlocked pages off the lru lists.

Notes:

1) This patch is optional--e.g., if one is concerned about the
   additional test in the fault path.  We can defer the moving of
   nonreclaimable pages until when vmscan [shrink_*_list()]
   encounters them.  Vmscan will only need to handle such pages
   once, but if there are a lot of them it could impact system
   performance.

2) The 'vma' argument to page_evictable() is require to notice that
   we're faulting a page into an mlock()ed vma w/o having to scan the
   page's rmap in the fault path.   Culling mlock()ed anon pages is
   currently the only reason for this patch.

3) We can't cull swap pages in read_swap_cache_async() because the
   vma argument doesn't necessarily correspond to the swap cache
   offset passed in by swapin_readahead().  This could [did!] result
   in mlocking pages in non-VM_LOCKED vmas if [when] we tried to
   cull in this path.

4) Move set_pte_at() to after where we add page to lru to keep it
   hidden from other tasks that might walk the page table.
   We already do it in this order in do_anonymous() page.  And,
   these are COW'd anon pages.  Is this safe?

[riel@redhat.com: undo an overzealous code cleanup]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swap.h |  2 ++
 mm/memory.c          | 18 ++++++++++--------
 mm/swap.c            | 21 +++++++++++++++++++++
 3 files changed, 33 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 7edb4cbc29f9..07eda69412fb 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -173,6 +173,8 @@ extern unsigned int nr_free_pagecache_pages(void);
 /* linux/mm/swap.c */
 extern void __lru_cache_add(struct page *, enum lru_list lru);
 extern void lru_cache_add_lru(struct page *, enum lru_list lru);
+extern void lru_cache_add_active_or_unevictable(struct page *,
+					struct vm_area_struct *);
 extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
diff --git a/mm/memory.c b/mm/memory.c
index 9fef7272fb9e..450127f4c582 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1922,12 +1922,13 @@ gotten:
 		 * thread doing COW.
 		 */
 		ptep_clear_flush_notify(vma, address, page_table);
-		set_pte_at(mm, address, page_table, entry);
-		update_mmu_cache(vma, address, entry);
 		SetPageSwapBacked(new_page);
-		lru_cache_add_active_anon(new_page);
+		lru_cache_add_active_or_unevictable(new_page, vma);
 		page_add_new_anon_rmap(new_page, vma, address);
 
+//TODO:  is this safe?  do_anonymous_page() does it this way.
+		set_pte_at(mm, address, page_table, entry);
+		update_mmu_cache(vma, address, entry);
 		if (old_page) {
 			/*
 			 * Only after switching the pte to the new page may
@@ -2420,7 +2421,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto release;
 	inc_mm_counter(mm, anon_rss);
 	SetPageSwapBacked(page);
-	lru_cache_add_active_anon(page);
+	lru_cache_add_active_or_unevictable(page, vma);
 	page_add_new_anon_rmap(page, vma, address);
 	set_pte_at(mm, address, page_table, entry);
 
@@ -2564,12 +2565,11 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		entry = mk_pte(page, vma->vm_page_prot);
 		if (flags & FAULT_FLAG_WRITE)
 			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
-		set_pte_at(mm, address, page_table, entry);
 		if (anon) {
-                        inc_mm_counter(mm, anon_rss);
+			inc_mm_counter(mm, anon_rss);
 			SetPageSwapBacked(page);
-                        lru_cache_add_active_anon(page);
-                        page_add_new_anon_rmap(page, vma, address);
+			lru_cache_add_active_or_unevictable(page, vma);
+			page_add_new_anon_rmap(page, vma, address);
 		} else {
 			inc_mm_counter(mm, file_rss);
 			page_add_file_rmap(page);
@@ -2578,6 +2578,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 				get_page(dirty_page);
 			}
 		}
+//TODO:  is this safe?  do_anonymous_page() does it this way.
+		set_pte_at(mm, address, page_table, entry);
 
 		/* no need to invalidate: a not-present page won't be cached */
 		update_mmu_cache(vma, address, entry);
diff --git a/mm/swap.c b/mm/swap.c
index bc58c1369dd6..2152e48a7b8f 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -31,6 +31,8 @@
 #include <linux/backing-dev.h>
 #include <linux/memcontrol.h>
 
+#include "internal.h"
+
 /* How many pages do we try to swap or page in/out together? */
 int page_cluster;
 
@@ -244,6 +246,25 @@ void add_page_to_unevictable_list(struct page *page)
 	spin_unlock_irq(&zone->lru_lock);
 }
 
+/**
+ * lru_cache_add_active_or_unevictable
+ * @page:  the page to be added to LRU
+ * @vma:   vma in which page is mapped for determining reclaimability
+ *
+ * place @page on active or unevictable LRU list, depending on
+ * page_evictable().  Note that if the page is not evictable,
+ * it goes directly back onto it's zone's unevictable list.  It does
+ * NOT use a per cpu pagevec.
+ */
+void lru_cache_add_active_or_unevictable(struct page *page,
+					struct vm_area_struct *vma)
+{
+	if (page_evictable(page, vma))
+		lru_cache_add_lru(page, LRU_ACTIVE + page_is_file_cache(page));
+	else
+		add_page_to_unevictable_list(page);
+}
+
 /*
  * Drain pages out of the cpu's pagevecs.
  * Either "cpu" is the current CPU, and preemption has already been
-- 
cgit v1.2.3


From af936a1606246a10c145feac3770f6287f483f02 Mon Sep 17 00:00:00 2001
From: Lee Schermerhorn <lee.schermerhorn@hp.com>
Date: Sat, 18 Oct 2008 20:26:53 -0700
Subject: vmscan: unevictable LRU scan sysctl

This patch adds a function to scan individual or all zones' unevictable
lists and move any pages that have become evictable onto the respective
zone's inactive list, where shrink_inactive_list() will deal with them.

Adds sysctl to scan all nodes, and per node attributes to individual
nodes' zones.

Kosaki: If evictable page found in unevictable lru when write
/proc/sys/vm/scan_unevictable_pages, print filename and file offset of
these pages.

[akpm@linux-foundation.org: fix one CONFIG_MMU=n build error]
[kosaki.motohiro@jp.fujitsu.com: adapt vmscan-unevictable-lru-scan-sysctl.patch to new sysfs API]
Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/base/node.c  |   5 ++
 include/linux/rmap.h |   3 +
 include/linux/swap.h |  15 +++++
 kernel/sysctl.c      |  10 ++++
 mm/rmap.c            |   4 +-
 mm/vmscan.c          | 166 +++++++++++++++++++++++++++++++++++++++++++++++++++
 6 files changed, 201 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index fb45d88a2446..f5207090885a 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -13,6 +13,7 @@
 #include <linux/nodemask.h>
 #include <linux/cpu.h>
 #include <linux/device.h>
+#include <linux/swap.h>
 
 static struct sysdev_class node_class = {
 	.name = "node",
@@ -191,6 +192,8 @@ int register_node(struct node *node, int num, struct node *parent)
 		sysdev_create_file(&node->sysdev, &attr_meminfo);
 		sysdev_create_file(&node->sysdev, &attr_numastat);
 		sysdev_create_file(&node->sysdev, &attr_distance);
+
+		scan_unevictable_register_node(node);
 	}
 	return error;
 }
@@ -210,6 +213,8 @@ void unregister_node(struct node *node)
 	sysdev_remove_file(&node->sysdev, &attr_numastat);
 	sysdev_remove_file(&node->sysdev, &attr_distance);
 
+	scan_unevictable_unregister_node(node);
+
 	sysdev_unregister(&node->sysdev);
 }
 
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 955667e6a52d..1da48db8db09 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -75,6 +75,9 @@ void anon_vma_unlink(struct vm_area_struct *);
 void anon_vma_link(struct vm_area_struct *);
 void __anon_vma_link(struct vm_area_struct *);
 
+extern struct anon_vma *page_lock_anon_vma(struct page *page);
+extern void page_unlock_anon_vma(struct anon_vma *anon_vma);
+
 /*
  * rmap interfaces called when adding or removing pte of page
  */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 07eda69412fb..a3af95b2cb6d 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -7,6 +7,7 @@
 #include <linux/list.h>
 #include <linux/memcontrol.h>
 #include <linux/sched.h>
+#include <linux/node.h>
 
 #include <asm/atomic.h>
 #include <asm/page.h>
@@ -235,15 +236,29 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
 #ifdef CONFIG_UNEVICTABLE_LRU
 extern int page_evictable(struct page *page, struct vm_area_struct *vma);
 extern void scan_mapping_unevictable_pages(struct address_space *);
+
+extern unsigned long scan_unevictable_pages;
+extern int scan_unevictable_handler(struct ctl_table *, int, struct file *,
+					void __user *, size_t *, loff_t *);
+extern int scan_unevictable_register_node(struct node *node);
+extern void scan_unevictable_unregister_node(struct node *node);
 #else
 static inline int page_evictable(struct page *page,
 						struct vm_area_struct *vma)
 {
 	return 1;
 }
+
 static inline void scan_mapping_unevictable_pages(struct address_space *mapping)
 {
 }
+
+static inline int scan_unevictable_register_node(struct node *node)
+{
+	return 0;
+}
+
+static inline void scan_unevictable_unregister_node(struct node *node) { }
 #endif
 
 extern int kswapd_run(int nid);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 617d41e4d6a0..b3cc73931d1f 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -833,6 +833,16 @@ static struct ctl_table kern_table[] = {
 		.proc_handler   = &proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_UNEVICTABLE_LRU
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "scan_unevictable_pages",
+		.data		= &scan_unevictable_pages,
+		.maxlen		= sizeof(scan_unevictable_pages),
+		.mode		= 0644,
+		.proc_handler	= &scan_unevictable_handler,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
diff --git a/mm/rmap.c b/mm/rmap.c
index 7e60df99018e..7e90bebbeb6c 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -181,7 +181,7 @@ void __init anon_vma_init(void)
  * Getting a lock on a stable anon_vma from a page off the LRU is
  * tricky: page_lock_anon_vma rely on RCU to guard against the races.
  */
-static struct anon_vma *page_lock_anon_vma(struct page *page)
+struct anon_vma *page_lock_anon_vma(struct page *page)
 {
 	struct anon_vma *anon_vma;
 	unsigned long anon_mapping;
@@ -201,7 +201,7 @@ out:
 	return NULL;
 }
 
-static void page_unlock_anon_vma(struct anon_vma *anon_vma)
+void page_unlock_anon_vma(struct anon_vma *anon_vma)
 {
 	spin_unlock(&anon_vma->lock);
 	rcu_read_unlock();
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e5aaaad159ef..ca64e3e0c518 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -39,6 +39,7 @@
 #include <linux/freezer.h>
 #include <linux/memcontrol.h>
 #include <linux/delayacct.h>
+#include <linux/sysctl.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -2363,6 +2364,39 @@ int page_evictable(struct page *page, struct vm_area_struct *vma)
 	return 1;
 }
 
+static void show_page_path(struct page *page)
+{
+	char buf[256];
+	if (page_is_file_cache(page)) {
+		struct address_space *mapping = page->mapping;
+		struct dentry *dentry;
+		pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+
+		spin_lock(&mapping->i_mmap_lock);
+		dentry = d_find_alias(mapping->host);
+		printk(KERN_INFO "rescued: %s %lu\n",
+		       dentry_path(dentry, buf, 256), pgoff);
+		spin_unlock(&mapping->i_mmap_lock);
+	} else {
+#if defined(CONFIG_MM_OWNER) && defined(CONFIG_MMU)
+		struct anon_vma *anon_vma;
+		struct vm_area_struct *vma;
+
+		anon_vma = page_lock_anon_vma(page);
+		if (!anon_vma)
+			return;
+
+		list_for_each_entry(vma, &anon_vma->head, anon_vma_node) {
+			printk(KERN_INFO "rescued: anon %s\n",
+			       vma->vm_mm->owner->comm);
+			break;
+		}
+		page_unlock_anon_vma(anon_vma);
+#endif
+	}
+}
+
+
 /**
  * check_move_unevictable_page - check page for evictability and move to appropriate zone lru list
  * @page: page to check evictability and move to appropriate lru list
@@ -2382,6 +2416,9 @@ retry:
 	ClearPageUnevictable(page);
 	if (page_evictable(page, NULL)) {
 		enum lru_list l = LRU_INACTIVE_ANON + page_is_file_cache(page);
+
+		show_page_path(page);
+
 		__dec_zone_state(zone, NR_UNEVICTABLE);
 		list_move(&page->lru, &zone->lru[l].list);
 		__inc_zone_state(zone, NR_INACTIVE_ANON + l);
@@ -2451,4 +2488,133 @@ void scan_mapping_unevictable_pages(struct address_space *mapping)
 	}
 
 }
+
+/**
+ * scan_zone_unevictable_pages - check unevictable list for evictable pages
+ * @zone - zone of which to scan the unevictable list
+ *
+ * Scan @zone's unevictable LRU lists to check for pages that have become
+ * evictable.  Move those that have to @zone's inactive list where they
+ * become candidates for reclaim, unless shrink_inactive_zone() decides
+ * to reactivate them.  Pages that are still unevictable are rotated
+ * back onto @zone's unevictable list.
+ */
+#define SCAN_UNEVICTABLE_BATCH_SIZE 16UL /* arbitrary lock hold batch size */
+void scan_zone_unevictable_pages(struct zone *zone)
+{
+	struct list_head *l_unevictable = &zone->lru[LRU_UNEVICTABLE].list;
+	unsigned long scan;
+	unsigned long nr_to_scan = zone_page_state(zone, NR_UNEVICTABLE);
+
+	while (nr_to_scan > 0) {
+		unsigned long batch_size = min(nr_to_scan,
+						SCAN_UNEVICTABLE_BATCH_SIZE);
+
+		spin_lock_irq(&zone->lru_lock);
+		for (scan = 0;  scan < batch_size; scan++) {
+			struct page *page = lru_to_page(l_unevictable);
+
+			if (!trylock_page(page))
+				continue;
+
+			prefetchw_prev_lru_page(page, l_unevictable, flags);
+
+			if (likely(PageLRU(page) && PageUnevictable(page)))
+				check_move_unevictable_page(page, zone);
+
+			unlock_page(page);
+		}
+		spin_unlock_irq(&zone->lru_lock);
+
+		nr_to_scan -= batch_size;
+	}
+}
+
+
+/**
+ * scan_all_zones_unevictable_pages - scan all unevictable lists for evictable pages
+ *
+ * A really big hammer:  scan all zones' unevictable LRU lists to check for
+ * pages that have become evictable.  Move those back to the zones'
+ * inactive list where they become candidates for reclaim.
+ * This occurs when, e.g., we have unswappable pages on the unevictable lists,
+ * and we add swap to the system.  As such, it runs in the context of a task
+ * that has possibly/probably made some previously unevictable pages
+ * evictable.
+ */
+void scan_all_zones_unevictable_pages(void)
+{
+	struct zone *zone;
+
+	for_each_zone(zone) {
+		scan_zone_unevictable_pages(zone);
+	}
+}
+
+/*
+ * scan_unevictable_pages [vm] sysctl handler.  On demand re-scan of
+ * all nodes' unevictable lists for evictable pages
+ */
+unsigned long scan_unevictable_pages;
+
+int scan_unevictable_handler(struct ctl_table *table, int write,
+			   struct file *file, void __user *buffer,
+			   size_t *length, loff_t *ppos)
+{
+	proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
+
+	if (write && *(unsigned long *)table->data)
+		scan_all_zones_unevictable_pages();
+
+	scan_unevictable_pages = 0;
+	return 0;
+}
+
+/*
+ * per node 'scan_unevictable_pages' attribute.  On demand re-scan of
+ * a specified node's per zone unevictable lists for evictable pages.
+ */
+
+static ssize_t read_scan_unevictable_node(struct sys_device *dev,
+					  struct sysdev_attribute *attr,
+					  char *buf)
+{
+	return sprintf(buf, "0\n");	/* always zero; should fit... */
+}
+
+static ssize_t write_scan_unevictable_node(struct sys_device *dev,
+					   struct sysdev_attribute *attr,
+					const char *buf, size_t count)
+{
+	struct zone *node_zones = NODE_DATA(dev->id)->node_zones;
+	struct zone *zone;
+	unsigned long res;
+	unsigned long req = strict_strtoul(buf, 10, &res);
+
+	if (!req)
+		return 1;	/* zero is no-op */
+
+	for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) {
+		if (!populated_zone(zone))
+			continue;
+		scan_zone_unevictable_pages(zone);
+	}
+	return 1;
+}
+
+
+static SYSDEV_ATTR(scan_unevictable_pages, S_IRUGO | S_IWUSR,
+			read_scan_unevictable_node,
+			write_scan_unevictable_node);
+
+int scan_unevictable_register_node(struct node *node)
+{
+	return sysdev_create_file(&node->sysdev, &attr_scan_unevictable_pages);
+}
+
+void scan_unevictable_unregister_node(struct node *node)
+{
+	sysdev_remove_file(&node->sysdev, &attr_scan_unevictable_pages);
+}
+
 #endif
-- 
cgit v1.2.3


From 985737cf2ea096ea946aed82c7484d40defc71a8 Mon Sep 17 00:00:00 2001
From: Lee Schermerhorn <lee.schermerhorn@hp.com>
Date: Sat, 18 Oct 2008 20:26:53 -0700
Subject: mlock: count attempts to free mlocked page

Allow free of mlock()ed pages.  This shouldn't happen, but during
developement, it occasionally did.

This patch allows us to survive that condition, while keeping the
statistics and events correct for debug.

Signed-off-by: Lee Schermerhorn <lee.schermerhorn@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/vmstat.h |  1 +
 mm/internal.h          | 17 +++++++++++++++++
 mm/page_alloc.c        |  1 +
 mm/vmstat.c            |  1 +
 4 files changed, 20 insertions(+)

(limited to 'include')

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 05b805020be2..9cd3ab0f554d 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -49,6 +49,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		UNEVICTABLE_PGMUNLOCKED,
 		UNEVICTABLE_PGCLEARED,	/* on COW, page truncate */
 		UNEVICTABLE_PGSTRANDED,	/* unable to isolate on unlock */
+		UNEVICTABLE_MLOCKFREED,
 #endif
 		NR_VM_EVENT_ITEMS
 };
diff --git a/mm/internal.h b/mm/internal.h
index 1cfbf2e2bc9e..e4e728bdf324 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -146,6 +146,22 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page)
 	}
 }
 
+/*
+ * free_page_mlock() -- clean up attempts to free and mlocked() page.
+ * Page should not be on lru, so no need to fix that up.
+ * free_pages_check() will verify...
+ */
+static inline void free_page_mlock(struct page *page)
+{
+	if (unlikely(TestClearPageMlocked(page))) {
+		unsigned long flags;
+
+		local_irq_save(flags);
+		__dec_zone_page_state(page, NR_MLOCK);
+		__count_vm_event(UNEVICTABLE_MLOCKFREED);
+		local_irq_restore(flags);
+	}
+}
 
 #else /* CONFIG_UNEVICTABLE_LRU */
 static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
@@ -155,6 +171,7 @@ static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
 static inline void clear_page_mlock(struct page *page) { }
 static inline void mlock_vma_page(struct page *page) { }
 static inline void mlock_migrate_page(struct page *new, struct page *old) { }
+static inline void free_page_mlock(struct page *page) { }
 
 #endif /* CONFIG_UNEVICTABLE_LRU */
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 5886586fde6c..cfbadad75d1d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -454,6 +454,7 @@ static inline void __free_one_page(struct page *page,
 
 static inline int free_pages_check(struct page *page)
 {
+	free_page_mlock(page);
 	if (unlikely(page_mapcount(page) |
 		(page->mapping != NULL)  |
 		(page_get_page_cgroup(page) != NULL) |
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 9e28abc0a0b9..9343227c5c60 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -689,6 +689,7 @@ static const char * const vmstat_text[] = {
 	"unevictable_pgs_munlocked",
 	"unevictable_pgs_cleared",
 	"unevictable_pgs_stranded",
+	"unevictable_pgs_mlockfreed",
 #endif
 #endif
 };
-- 
cgit v1.2.3


From 902d2e8ae0de29f483840ba1134af27343b9564d Mon Sep 17 00:00:00 2001
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Date: Sat, 18 Oct 2008 20:26:54 -0700
Subject: vmscan: kill unused lru functions

Several LRU manupuration function are not used now.  So they can be
removed.

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/mm_inline.h | 48 -----------------------------------------------
 1 file changed, 48 deletions(-)

(limited to 'include')

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 67d7697fd019..c948350c378e 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -37,54 +37,6 @@ del_page_from_lru_list(struct zone *zone, struct page *page, enum lru_list l)
 	__dec_zone_state(zone, NR_LRU_BASE + l);
 }
 
-static inline void
-add_page_to_inactive_anon_list(struct zone *zone, struct page *page)
-{
-	add_page_to_lru_list(zone, page, LRU_INACTIVE_ANON);
-}
-
-static inline void
-add_page_to_active_anon_list(struct zone *zone, struct page *page)
-{
-	add_page_to_lru_list(zone, page, LRU_ACTIVE_ANON);
-}
-
-static inline void
-add_page_to_inactive_file_list(struct zone *zone, struct page *page)
-{
-	add_page_to_lru_list(zone, page, LRU_INACTIVE_FILE);
-}
-
-static inline void
-add_page_to_active_file_list(struct zone *zone, struct page *page)
-{
-	add_page_to_lru_list(zone, page, LRU_ACTIVE_FILE);
-}
-
-static inline void
-del_page_from_inactive_anon_list(struct zone *zone, struct page *page)
-{
-	del_page_from_lru_list(zone, page, LRU_INACTIVE_ANON);
-}
-
-static inline void
-del_page_from_active_anon_list(struct zone *zone, struct page *page)
-{
-	del_page_from_lru_list(zone, page, LRU_ACTIVE_ANON);
-}
-
-static inline void
-del_page_from_inactive_file_list(struct zone *zone, struct page *page)
-{
-	del_page_from_lru_list(zone, page, LRU_INACTIVE_FILE);
-}
-
-static inline void
-del_page_from_active_file_list(struct zone *zone, struct page *page)
-{
-	del_page_from_lru_list(zone, page, LRU_INACTIVE_FILE);
-}
-
 static inline void
 del_page_from_lru(struct zone *zone, struct page *page)
 {
-- 
cgit v1.2.3


From f45840b5c128445da70e7ec33adc47b4a12bdaf4 Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Sat, 18 Oct 2008 20:26:57 -0700
Subject: mm: pagecache insertion fewer atomics

Setting and clearing the page locked when inserting it into swapcache /
pagecache when it has no other references can use non-atomic page flags
operations because no other CPU may be operating on it at this time.

This saves one atomic operation when inserting a page into pagecache.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h | 14 +++++++-------
 mm/swap_state.c         |  4 ++--
 2 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 4b6c4d8d26b8..7334b2b6c4c6 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -299,14 +299,14 @@ extern int __lock_page_killable(struct page *page);
 extern void __lock_page_nosync(struct page *page);
 extern void unlock_page(struct page *page);
 
-static inline void set_page_locked(struct page *page)
+static inline void __set_page_locked(struct page *page)
 {
-	set_bit(PG_locked, &page->flags);
+	__set_bit(PG_locked, &page->flags);
 }
 
-static inline void clear_page_locked(struct page *page)
+static inline void __clear_page_locked(struct page *page)
 {
-	clear_bit(PG_locked, &page->flags);
+	__clear_bit(PG_locked, &page->flags);
 }
 
 static inline int trylock_page(struct page *page)
@@ -438,17 +438,17 @@ extern void __remove_from_page_cache(struct page *page);
 
 /*
  * Like add_to_page_cache_locked, but used to add newly allocated pages:
- * the page is new, so we can just run set_page_locked() against it.
+ * the page is new, so we can just run __set_page_locked() against it.
  */
 static inline int add_to_page_cache(struct page *page,
 		struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask)
 {
 	int error;
 
-	set_page_locked(page);
+	__set_page_locked(page);
 	error = add_to_page_cache_locked(page, mapping, offset, gfp_mask);
 	if (unlikely(error))
-		clear_page_locked(page);
+		__clear_page_locked(page);
 	return error;
 }
 
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 43cda7b4b808..3353c9029cef 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -303,7 +303,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 		 * re-using the just freed swap entry for an existing page.
 		 * May fail (-ENOMEM) if radix-tree node allocation failed.
 		 */
-		set_page_locked(new_page);
+		__set_page_locked(new_page);
 		SetPageSwapBacked(new_page);
 		err = add_to_swap_cache(new_page, entry, gfp_mask & GFP_KERNEL);
 		if (likely(!err)) {
@@ -315,7 +315,7 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask,
 			return new_page;
 		}
 		ClearPageSwapBacked(new_page);
-		clear_page_locked(new_page);
+		__clear_page_locked(new_page);
 		swap_free(entry);
 	} while (err != -ENOMEM);
 
-- 
cgit v1.2.3


From 8413ac9d8c9a1366a4f57880723126cd24e5a5c3 Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Sat, 18 Oct 2008 20:26:59 -0700
Subject: mm: page lock use lock bitops

trylock_page, unlock_page open and close a critical section. Hence,
we can use the lock bitops to get the desired memory ordering.

Also, mark trylock as likely to succeed (and remove the annotation from
callers).

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pagemap.h |  2 +-
 mm/filemap.c            | 13 +++++--------
 mm/swapfile.c           |  2 +-
 3 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 7334b2b6c4c6..709742be02f0 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -311,7 +311,7 @@ static inline void __clear_page_locked(struct page *page)
 
 static inline int trylock_page(struct page *page)
 {
-	return !test_and_set_bit(PG_locked, &page->flags);
+	return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
 }
 
 /*
diff --git a/mm/filemap.c b/mm/filemap.c
index a1ddd2557af2..e1b23fda48de 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -573,17 +573,14 @@ EXPORT_SYMBOL(wait_on_page_bit);
  * mechananism between PageLocked pages and PageWriteback pages is shared.
  * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
  *
- * The first mb is necessary to safely close the critical section opened by the
- * test_and_set_bit() to lock the page; the second mb is necessary to enforce
- * ordering between the clear_bit and the read of the waitqueue (to avoid SMP
- * races with a parallel wait_on_page_locked()).
+ * The mb is necessary to enforce ordering between the clear_bit and the read
+ * of the waitqueue (to avoid SMP races with a parallel wait_on_page_locked()).
  */
 void unlock_page(struct page *page)
 {
-	smp_mb__before_clear_bit();
-	if (!test_and_clear_bit(PG_locked, &page->flags))
-		BUG();
-	smp_mb__after_clear_bit(); 
+	VM_BUG_ON(!PageLocked(page));
+	clear_bit_unlock(PG_locked, &page->flags);
+	smp_mb__after_clear_bit();
 	wake_up_page(page, PG_locked);
 }
 EXPORT_SYMBOL(unlock_page);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2a97fafa3d89..90cb67a5417c 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -422,7 +422,7 @@ void free_swap_and_cache(swp_entry_t entry)
 	if (p) {
 		if (swap_entry_free(p, swp_offset(entry)) == 1) {
 			page = find_get_page(&swapper_space, entry.val);
-			if (page && unlikely(!trylock_page(page))) {
+			if (page && !trylock_page(page)) {
 				page_cache_release(page);
 				page = NULL;
 			}
-- 
cgit v1.2.3


From 51b07fc3c5c830bb49c80fc5eac041e1f66a72e7 Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Sat, 18 Oct 2008 20:27:00 -0700
Subject: fs: buffer lock use lock bitops

trylock_buffer and unlock_buffer open and close a critical section.
Hence, we can use the lock bitops to get the desired memory ordering.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/buffer.c                 | 3 +--
 include/linux/buffer_head.h | 2 +-
 2 files changed, 2 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/fs/buffer.c b/fs/buffer.c
index ac78d4c19b3b..6569fda5cfed 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -76,8 +76,7 @@ EXPORT_SYMBOL(__lock_buffer);
 
 void unlock_buffer(struct buffer_head *bh)
 {
-	smp_mb__before_clear_bit();
-	clear_buffer_locked(bh);
+	clear_bit_unlock(BH_Lock, &bh->b_state);
 	smp_mb__after_clear_bit();
 	wake_up_bit(&bh->b_state, BH_Lock);
 }
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index eadaab44015f..3ce64b90118c 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -322,7 +322,7 @@ static inline void wait_on_buffer(struct buffer_head *bh)
 
 static inline int trylock_buffer(struct buffer_head *bh)
 {
-	return likely(!test_and_set_bit(BH_Lock, &bh->b_state));
+	return likely(!test_and_set_bit_lock(BH_Lock, &bh->b_state));
 }
 
 static inline void lock_buffer(struct buffer_head *bh)
-- 
cgit v1.2.3


From db64fe02258f1507e13fe5212a989922323685ce Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Sat, 18 Oct 2008 20:27:03 -0700
Subject: mm: rewrite vmap layer

Rewrite the vmap allocator to use rbtrees and lazy tlb flushing, and
provide a fast, scalable percpu frontend for small vmaps (requires a
slightly different API, though).

The biggest problem with vmap is actually vunmap.  Presently this requires
a global kernel TLB flush, which on most architectures is a broadcast IPI
to all CPUs to flush the cache.  This is all done under a global lock.  As
the number of CPUs increases, so will the number of vunmaps a scaled
workload will want to perform, and so will the cost of a global TLB flush.
 This gives terrible quadratic scalability characteristics.

Another problem is that the entire vmap subsystem works under a single
lock.  It is a rwlock, but it is actually taken for write in all the fast
paths, and the read locking would likely never be run concurrently anyway,
so it's just pointless.

This is a rewrite of vmap subsystem to solve those problems.  The existing
vmalloc API is implemented on top of the rewritten subsystem.

The TLB flushing problem is solved by using lazy TLB unmapping.  vmap
addresses do not have to be flushed immediately when they are vunmapped,
because the kernel will not reuse them again (would be a use-after-free)
until they are reallocated.  So the addresses aren't allocated again until
a subsequent TLB flush.  A single TLB flush then can flush multiple
vunmaps from each CPU.

XEN and PAT and such do not like deferred TLB flushing because they can't
always handle multiple aliasing virtual addresses to a physical address.
They now call vm_unmap_aliases() in order to flush any deferred mappings.
That call is very expensive (well, actually not a lot more expensive than
a single vunmap under the old scheme), however it should be OK if not
called too often.

The virtual memory extent information is stored in an rbtree rather than a
linked list to improve the algorithmic scalability.

There is a per-CPU allocator for small vmaps, which amortizes or avoids
global locking.

To use the per-CPU interface, the vm_map_ram / vm_unmap_ram interfaces
must be used in place of vmap and vunmap.  Vmalloc does not use these
interfaces at the moment, so it will not be quite so scalable (although it
will use lazy TLB flushing).

As a quick test of performance, I ran a test that loops in the kernel,
linearly mapping then touching then unmapping 4 pages.  Different numbers
of tests were run in parallel on an 4 core, 2 socket opteron.  Results are
in nanoseconds per map+touch+unmap.

threads           vanilla         vmap rewrite
1                 14700           2900
2                 33600           3000
4                 49500           2800
8                 70631           2900

So with a 8 cores, the rewritten version is already 25x faster.

In a slightly more realistic test (although with an older and less
scalable version of the patch), I ripped the not-very-good vunmap batching
code out of XFS, and implemented the large buffer mapping with vm_map_ram
and vm_unmap_ram...  along with a couple of other tricks, I was able to
speed up a large directory workload by 20x on a 64 CPU system.  I believe
vmap/vunmap is actually sped up a lot more than 20x on such a system, but
I'm running into other locks now.  vmap is pretty well blown off the
profiles.

Before:
1352059 total                                      0.1401
798784 _write_lock                              8320.6667 <- vmlist_lock
529313 default_idle                             1181.5022
 15242 smp_call_function                         15.8771  <- vmap tlb flushing
  2472 __get_vm_area_node                         1.9312  <- vmap
  1762 remove_vm_area                             4.5885  <- vunmap
   316 map_vm_area                                0.2297  <- vmap
   312 kfree                                      0.1950
   300 _spin_lock                                 3.1250
   252 sn_send_IPI_phys                           0.4375  <- tlb flushing
   238 vmap                                       0.8264  <- vmap
   216 find_lock_page                             0.5192
   196 find_next_bit                              0.3603
   136 sn2_send_IPI                               0.2024
   130 pio_phys_write_mmr                         2.0312
   118 unmap_kernel_range                         0.1229

After:
 78406 total                                      0.0081
 40053 default_idle                              89.4040
 33576 ia64_spinlock_contention                 349.7500
  1650 _spin_lock                                17.1875
   319 __reg_op                                   0.5538
   281 _atomic_dec_and_lock                       1.0977
   153 mutex_unlock                               1.5938
   123 iget_locked                                0.1671
   117 xfs_dir_lookup                             0.1662
   117 dput                                       0.1406
   114 xfs_iget_core                              0.0268
    92 xfs_da_hashname                            0.1917
    75 d_alloc                                    0.0670
    68 vmap_page_range                            0.0462 <- vmap
    58 kmem_cache_alloc                           0.0604
    57 memset                                     0.0540
    52 rb_next                                    0.1625
    50 __copy_user                                0.0208
    49 bitmap_find_free_region                    0.2188 <- vmap
    46 ia64_sn_udelay                             0.1106
    45 find_inode_fast                            0.1406
    42 memcmp                                     0.2188
    42 finish_task_switch                         0.1094
    42 __d_lookup                                 0.0410
    40 radix_tree_lookup_slot                     0.1250
    37 _spin_unlock_irqrestore                    0.3854
    36 xfs_bmapi                                  0.0050
    36 kmem_cache_free                            0.0256
    35 xfs_vn_getattr                             0.0322
    34 radix_tree_lookup                          0.1062
    33 __link_path_walk                           0.0035
    31 xfs_da_do_buf                              0.0091
    30 _xfs_buf_find                              0.0204
    28 find_get_page                              0.0875
    27 xfs_iread                                  0.0241
    27 __strncpy_from_user                        0.2812
    26 _xfs_buf_initialize                        0.0406
    24 _xfs_buf_lookup_pages                      0.0179
    24 vunmap_page_range                          0.0250 <- vunmap
    23 find_lock_page                             0.0799
    22 vm_map_ram                                 0.0087 <- vmap
    20 kfree                                      0.0125
    19 put_page                                   0.0330
    18 __kmalloc                                  0.0176
    17 xfs_da_node_lookup_int                     0.0086
    17 _read_lock                                 0.0885
    17 page_waitqueue                             0.0664

vmap has gone from being the top 5 on the profiles and flushing the crap
out of all TLBs, to using less than 1% of kernel time.

[akpm@linux-foundation.org: cleanups, section fix]
[akpm@linux-foundation.org: fix build on alpha]
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Krzysztof Helt <krzysztof.h1@poczta.fm>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/mm/pageattr.c   |   2 +
 arch/x86/xen/enlighten.c |   1 +
 arch/x86/xen/mmu.c       |   1 +
 include/linux/vmalloc.h  |  15 +-
 init/main.c              |   2 +
 mm/vmalloc.c             | 975 ++++++++++++++++++++++++++++++++++++++++-------
 6 files changed, 862 insertions(+), 134 deletions(-)

(limited to 'include')

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a9ec89c3fbca..407d8784f669 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -792,6 +792,8 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 	/* Must avoid aliasing mappings in the highmem code */
 	kmap_flush_unused();
 
+	vm_unmap_aliases();
+
 	cpa.vaddr = addr;
 	cpa.numpages = numpages;
 	cpa.mask_set = mask_set;
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0013a729b41d..b61534c7a4c4 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -871,6 +871,7 @@ static void xen_alloc_ptpage(struct mm_struct *mm, unsigned long pfn, unsigned l
 			/* make sure there are no stray mappings of
 			   this page */
 			kmap_flush_unused();
+			vm_unmap_aliases();
 	}
 }
 
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index ae173f6edd8b..d4d52f5a1cf7 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -846,6 +846,7 @@ static void __xen_pgd_pin(struct mm_struct *mm, pgd_t *pgd)
 		/* re-enable interrupts for kmap_flush_unused */
 		xen_mc_issue(0);
 		kmap_flush_unused();
+		vm_unmap_aliases();
 		xen_mc_batch();
 	}
 
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 328eb4022727..4c28c4d564e2 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -2,6 +2,7 @@
 #define _LINUX_VMALLOC_H
 
 #include <linux/spinlock.h>
+#include <linux/init.h>
 #include <asm/page.h>		/* pgprot_t */
 
 struct vm_area_struct;		/* vma defining user mapping in mm_types.h */
@@ -23,7 +24,6 @@ struct vm_area_struct;		/* vma defining user mapping in mm_types.h */
 #endif
 
 struct vm_struct {
-	/* keep next,addr,size together to speedup lookups */
 	struct vm_struct	*next;
 	void			*addr;
 	unsigned long		size;
@@ -37,6 +37,19 @@ struct vm_struct {
 /*
  *	Highlevel APIs for driver use
  */
+extern void vm_unmap_ram(const void *mem, unsigned int count);
+extern void *vm_map_ram(struct page **pages, unsigned int count,
+				int node, pgprot_t prot);
+extern void vm_unmap_aliases(void);
+
+#ifdef CONFIG_MMU
+extern void __init vmalloc_init(void);
+#else
+static inline void vmalloc_init(void)
+{
+}
+#endif
+
 extern void *vmalloc(unsigned long size);
 extern void *vmalloc_user(unsigned long size);
 extern void *vmalloc_node(unsigned long size, int node);
diff --git a/init/main.c b/init/main.c
index 27f6bf6108e9..4371d11721f6 100644
--- a/init/main.c
+++ b/init/main.c
@@ -27,6 +27,7 @@
 #include <linux/gfp.h>
 #include <linux/percpu.h>
 #include <linux/kmod.h>
+#include <linux/vmalloc.h>
 #include <linux/kernel_stat.h>
 #include <linux/start_kernel.h>
 #include <linux/security.h>
@@ -642,6 +643,7 @@ asmlinkage void __init start_kernel(void)
 		initrd_start = 0;
 	}
 #endif
+	vmalloc_init();
 	vfs_caches_init_early();
 	cpuset_init_early();
 	mem_init();
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index bba06c41fc59..712ae47af0bf 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -8,6 +8,7 @@
  *  Numa awareness, Christoph Lameter, SGI, June 2005
  */
 
+#include <linux/vmalloc.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/highmem.h>
@@ -18,16 +19,17 @@
 #include <linux/debugobjects.h>
 #include <linux/vmalloc.h>
 #include <linux/kallsyms.h>
+#include <linux/list.h>
+#include <linux/rbtree.h>
+#include <linux/radix-tree.h>
+#include <linux/rcupdate.h>
 
+#include <asm/atomic.h>
 #include <asm/uaccess.h>
 #include <asm/tlbflush.h>
 
 
-DEFINE_RWLOCK(vmlist_lock);
-struct vm_struct *vmlist;
-
-static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
-			    int node, void *caller);
+/*** Page table manipulation functions ***/
 
 static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end)
 {
@@ -40,8 +42,7 @@ static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end)
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static inline void vunmap_pmd_range(pud_t *pud, unsigned long addr,
-						unsigned long end)
+static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -55,8 +56,7 @@ static inline void vunmap_pmd_range(pud_t *pud, unsigned long addr,
 	} while (pmd++, addr = next, addr != end);
 }
 
-static inline void vunmap_pud_range(pgd_t *pgd, unsigned long addr,
-						unsigned long end)
+static void vunmap_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -70,12 +70,10 @@ static inline void vunmap_pud_range(pgd_t *pgd, unsigned long addr,
 	} while (pud++, addr = next, addr != end);
 }
 
-void unmap_kernel_range(unsigned long addr, unsigned long size)
+static void vunmap_page_range(unsigned long addr, unsigned long end)
 {
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long start = addr;
-	unsigned long end = addr + size;
 
 	BUG_ON(addr >= end);
 	pgd = pgd_offset_k(addr);
@@ -86,35 +84,36 @@ void unmap_kernel_range(unsigned long addr, unsigned long size)
 			continue;
 		vunmap_pud_range(pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
-	flush_tlb_kernel_range(start, end);
-}
-
-static void unmap_vm_area(struct vm_struct *area)
-{
-	unmap_kernel_range((unsigned long)area->addr, area->size);
 }
 
 static int vmap_pte_range(pmd_t *pmd, unsigned long addr,
-			unsigned long end, pgprot_t prot, struct page ***pages)
+		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
 {
 	pte_t *pte;
 
+	/*
+	 * nr is a running index into the array which helps higher level
+	 * callers keep track of where we're up to.
+	 */
+
 	pte = pte_alloc_kernel(pmd, addr);
 	if (!pte)
 		return -ENOMEM;
 	do {
-		struct page *page = **pages;
-		WARN_ON(!pte_none(*pte));
-		if (!page)
+		struct page *page = pages[*nr];
+
+		if (WARN_ON(!pte_none(*pte)))
+			return -EBUSY;
+		if (WARN_ON(!page))
 			return -ENOMEM;
 		set_pte_at(&init_mm, addr, pte, mk_pte(page, prot));
-		(*pages)++;
+		(*nr)++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	return 0;
 }
 
-static inline int vmap_pmd_range(pud_t *pud, unsigned long addr,
-			unsigned long end, pgprot_t prot, struct page ***pages)
+static int vmap_pmd_range(pud_t *pud, unsigned long addr,
+		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
 {
 	pmd_t *pmd;
 	unsigned long next;
@@ -124,14 +123,14 @@ static inline int vmap_pmd_range(pud_t *pud, unsigned long addr,
 		return -ENOMEM;
 	do {
 		next = pmd_addr_end(addr, end);
-		if (vmap_pte_range(pmd, addr, next, prot, pages))
+		if (vmap_pte_range(pmd, addr, next, prot, pages, nr))
 			return -ENOMEM;
 	} while (pmd++, addr = next, addr != end);
 	return 0;
 }
 
-static inline int vmap_pud_range(pgd_t *pgd, unsigned long addr,
-			unsigned long end, pgprot_t prot, struct page ***pages)
+static int vmap_pud_range(pgd_t *pgd, unsigned long addr,
+		unsigned long end, pgprot_t prot, struct page **pages, int *nr)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -141,44 +140,49 @@ static inline int vmap_pud_range(pgd_t *pgd, unsigned long addr,
 		return -ENOMEM;
 	do {
 		next = pud_addr_end(addr, end);
-		if (vmap_pmd_range(pud, addr, next, prot, pages))
+		if (vmap_pmd_range(pud, addr, next, prot, pages, nr))
 			return -ENOMEM;
 	} while (pud++, addr = next, addr != end);
 	return 0;
 }
 
-int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages)
+/*
+ * Set up page tables in kva (addr, end). The ptes shall have prot "prot", and
+ * will have pfns corresponding to the "pages" array.
+ *
+ * Ie. pte at addr+N*PAGE_SIZE shall point to pfn corresponding to pages[N]
+ */
+static int vmap_page_range(unsigned long addr, unsigned long end,
+				pgprot_t prot, struct page **pages)
 {
 	pgd_t *pgd;
 	unsigned long next;
-	unsigned long addr = (unsigned long) area->addr;
-	unsigned long end = addr + area->size - PAGE_SIZE;
-	int err;
+	int err = 0;
+	int nr = 0;
 
 	BUG_ON(addr >= end);
 	pgd = pgd_offset_k(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = vmap_pud_range(pgd, addr, next, prot, pages);
+		err = vmap_pud_range(pgd, addr, next, prot, pages, &nr);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
-	flush_cache_vmap((unsigned long) area->addr, end);
-	return err;
+	flush_cache_vmap(addr, end);
+
+	if (unlikely(err))
+		return err;
+	return nr;
 }
-EXPORT_SYMBOL_GPL(map_vm_area);
 
 /*
- * Map a vmalloc()-space virtual address to the physical page.
+ * Walk a vmap address to the struct page it maps.
  */
 struct page *vmalloc_to_page(const void *vmalloc_addr)
 {
 	unsigned long addr = (unsigned long) vmalloc_addr;
 	struct page *page = NULL;
 	pgd_t *pgd = pgd_offset_k(addr);
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *ptep, pte;
 
 	/*
 	 * XXX we might need to change this if we add VIRTUAL_BUG_ON for
@@ -188,10 +192,12 @@ struct page *vmalloc_to_page(const void *vmalloc_addr)
 			!is_module_address(addr));
 
 	if (!pgd_none(*pgd)) {
-		pud = pud_offset(pgd, addr);
+		pud_t *pud = pud_offset(pgd, addr);
 		if (!pud_none(*pud)) {
-			pmd = pmd_offset(pud, addr);
+			pmd_t *pmd = pmd_offset(pud, addr);
 			if (!pmd_none(*pmd)) {
+				pte_t *ptep, pte;
+
 				ptep = pte_offset_map(pmd, addr);
 				pte = *ptep;
 				if (pte_present(pte))
@@ -213,13 +219,751 @@ unsigned long vmalloc_to_pfn(const void *vmalloc_addr)
 }
 EXPORT_SYMBOL(vmalloc_to_pfn);
 
-static struct vm_struct *
-__get_vm_area_node(unsigned long size, unsigned long flags, unsigned long start,
-		unsigned long end, int node, gfp_t gfp_mask, void *caller)
+
+/*** Global kva allocator ***/
+
+#define VM_LAZY_FREE	0x01
+#define VM_LAZY_FREEING	0x02
+#define VM_VM_AREA	0x04
+
+struct vmap_area {
+	unsigned long va_start;
+	unsigned long va_end;
+	unsigned long flags;
+	struct rb_node rb_node;		/* address sorted rbtree */
+	struct list_head list;		/* address sorted list */
+	struct list_head purge_list;	/* "lazy purge" list */
+	void *private;
+	struct rcu_head rcu_head;
+};
+
+static DEFINE_SPINLOCK(vmap_area_lock);
+static struct rb_root vmap_area_root = RB_ROOT;
+static LIST_HEAD(vmap_area_list);
+
+static struct vmap_area *__find_vmap_area(unsigned long addr)
 {
-	struct vm_struct **p, *tmp, *area;
-	unsigned long align = 1;
+	struct rb_node *n = vmap_area_root.rb_node;
+
+	while (n) {
+		struct vmap_area *va;
+
+		va = rb_entry(n, struct vmap_area, rb_node);
+		if (addr < va->va_start)
+			n = n->rb_left;
+		else if (addr > va->va_start)
+			n = n->rb_right;
+		else
+			return va;
+	}
+
+	return NULL;
+}
+
+static void __insert_vmap_area(struct vmap_area *va)
+{
+	struct rb_node **p = &vmap_area_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct rb_node *tmp;
+
+	while (*p) {
+		struct vmap_area *tmp;
+
+		parent = *p;
+		tmp = rb_entry(parent, struct vmap_area, rb_node);
+		if (va->va_start < tmp->va_end)
+			p = &(*p)->rb_left;
+		else if (va->va_end > tmp->va_start)
+			p = &(*p)->rb_right;
+		else
+			BUG();
+	}
+
+	rb_link_node(&va->rb_node, parent, p);
+	rb_insert_color(&va->rb_node, &vmap_area_root);
+
+	/* address-sort this list so it is usable like the vmlist */
+	tmp = rb_prev(&va->rb_node);
+	if (tmp) {
+		struct vmap_area *prev;
+		prev = rb_entry(tmp, struct vmap_area, rb_node);
+		list_add_rcu(&va->list, &prev->list);
+	} else
+		list_add_rcu(&va->list, &vmap_area_list);
+}
+
+static void purge_vmap_area_lazy(void);
+
+/*
+ * Allocate a region of KVA of the specified size and alignment, within the
+ * vstart and vend.
+ */
+static struct vmap_area *alloc_vmap_area(unsigned long size,
+				unsigned long align,
+				unsigned long vstart, unsigned long vend,
+				int node, gfp_t gfp_mask)
+{
+	struct vmap_area *va;
+	struct rb_node *n;
+	unsigned long addr;
+	int purged = 0;
+
+	BUG_ON(size & ~PAGE_MASK);
+
+	addr = ALIGN(vstart, align);
+
+	va = kmalloc_node(sizeof(struct vmap_area),
+			gfp_mask & GFP_RECLAIM_MASK, node);
+	if (unlikely(!va))
+		return ERR_PTR(-ENOMEM);
+
+retry:
+	spin_lock(&vmap_area_lock);
+	/* XXX: could have a last_hole cache */
+	n = vmap_area_root.rb_node;
+	if (n) {
+		struct vmap_area *first = NULL;
+
+		do {
+			struct vmap_area *tmp;
+			tmp = rb_entry(n, struct vmap_area, rb_node);
+			if (tmp->va_end >= addr) {
+				if (!first && tmp->va_start < addr + size)
+					first = tmp;
+				n = n->rb_left;
+			} else {
+				first = tmp;
+				n = n->rb_right;
+			}
+		} while (n);
+
+		if (!first)
+			goto found;
+
+		if (first->va_end < addr) {
+			n = rb_next(&first->rb_node);
+			if (n)
+				first = rb_entry(n, struct vmap_area, rb_node);
+			else
+				goto found;
+		}
+
+		while (addr + size >= first->va_start && addr + size <= vend) {
+			addr = ALIGN(first->va_end + PAGE_SIZE, align);
+
+			n = rb_next(&first->rb_node);
+			if (n)
+				first = rb_entry(n, struct vmap_area, rb_node);
+			else
+				goto found;
+		}
+	}
+found:
+	if (addr + size > vend) {
+		spin_unlock(&vmap_area_lock);
+		if (!purged) {
+			purge_vmap_area_lazy();
+			purged = 1;
+			goto retry;
+		}
+		if (printk_ratelimit())
+			printk(KERN_WARNING "vmap allocation failed: "
+				 "use vmalloc=<size> to increase size.\n");
+		return ERR_PTR(-EBUSY);
+	}
+
+	BUG_ON(addr & (align-1));
+
+	va->va_start = addr;
+	va->va_end = addr + size;
+	va->flags = 0;
+	__insert_vmap_area(va);
+	spin_unlock(&vmap_area_lock);
+
+	return va;
+}
+
+static void rcu_free_va(struct rcu_head *head)
+{
+	struct vmap_area *va = container_of(head, struct vmap_area, rcu_head);
+
+	kfree(va);
+}
+
+static void __free_vmap_area(struct vmap_area *va)
+{
+	BUG_ON(RB_EMPTY_NODE(&va->rb_node));
+	rb_erase(&va->rb_node, &vmap_area_root);
+	RB_CLEAR_NODE(&va->rb_node);
+	list_del_rcu(&va->list);
+
+	call_rcu(&va->rcu_head, rcu_free_va);
+}
+
+/*
+ * Free a region of KVA allocated by alloc_vmap_area
+ */
+static void free_vmap_area(struct vmap_area *va)
+{
+	spin_lock(&vmap_area_lock);
+	__free_vmap_area(va);
+	spin_unlock(&vmap_area_lock);
+}
+
+/*
+ * Clear the pagetable entries of a given vmap_area
+ */
+static void unmap_vmap_area(struct vmap_area *va)
+{
+	vunmap_page_range(va->va_start, va->va_end);
+}
+
+/*
+ * lazy_max_pages is the maximum amount of virtual address space we gather up
+ * before attempting to purge with a TLB flush.
+ *
+ * There is a tradeoff here: a larger number will cover more kernel page tables
+ * and take slightly longer to purge, but it will linearly reduce the number of
+ * global TLB flushes that must be performed. It would seem natural to scale
+ * this number up linearly with the number of CPUs (because vmapping activity
+ * could also scale linearly with the number of CPUs), however it is likely
+ * that in practice, workloads might be constrained in other ways that mean
+ * vmap activity will not scale linearly with CPUs. Also, I want to be
+ * conservative and not introduce a big latency on huge systems, so go with
+ * a less aggressive log scale. It will still be an improvement over the old
+ * code, and it will be simple to change the scale factor if we find that it
+ * becomes a problem on bigger systems.
+ */
+static unsigned long lazy_max_pages(void)
+{
+	unsigned int log;
+
+	log = fls(num_online_cpus());
+
+	return log * (32UL * 1024 * 1024 / PAGE_SIZE);
+}
+
+static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);
+
+/*
+ * Purges all lazily-freed vmap areas.
+ *
+ * If sync is 0 then don't purge if there is already a purge in progress.
+ * If force_flush is 1, then flush kernel TLBs between *start and *end even
+ * if we found no lazy vmap areas to unmap (callers can use this to optimise
+ * their own TLB flushing).
+ * Returns with *start = min(*start, lowest purged address)
+ *              *end = max(*end, highest purged address)
+ */
+static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
+					int sync, int force_flush)
+{
+	static DEFINE_SPINLOCK(purge_lock);
+	LIST_HEAD(valist);
+	struct vmap_area *va;
+	int nr = 0;
+
+	/*
+	 * If sync is 0 but force_flush is 1, we'll go sync anyway but callers
+	 * should not expect such behaviour. This just simplifies locking for
+	 * the case that isn't actually used at the moment anyway.
+	 */
+	if (!sync && !force_flush) {
+		if (!spin_trylock(&purge_lock))
+			return;
+	} else
+		spin_lock(&purge_lock);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(va, &vmap_area_list, list) {
+		if (va->flags & VM_LAZY_FREE) {
+			if (va->va_start < *start)
+				*start = va->va_start;
+			if (va->va_end > *end)
+				*end = va->va_end;
+			nr += (va->va_end - va->va_start) >> PAGE_SHIFT;
+			unmap_vmap_area(va);
+			list_add_tail(&va->purge_list, &valist);
+			va->flags |= VM_LAZY_FREEING;
+			va->flags &= ~VM_LAZY_FREE;
+		}
+	}
+	rcu_read_unlock();
+
+	if (nr) {
+		BUG_ON(nr > atomic_read(&vmap_lazy_nr));
+		atomic_sub(nr, &vmap_lazy_nr);
+	}
+
+	if (nr || force_flush)
+		flush_tlb_kernel_range(*start, *end);
+
+	if (nr) {
+		spin_lock(&vmap_area_lock);
+		list_for_each_entry(va, &valist, purge_list)
+			__free_vmap_area(va);
+		spin_unlock(&vmap_area_lock);
+	}
+	spin_unlock(&purge_lock);
+}
+
+/*
+ * Kick off a purge of the outstanding lazy areas.
+ */
+static void purge_vmap_area_lazy(void)
+{
+	unsigned long start = ULONG_MAX, end = 0;
+
+	__purge_vmap_area_lazy(&start, &end, 0, 0);
+}
+
+/*
+ * Free and unmap a vmap area
+ */
+static void free_unmap_vmap_area(struct vmap_area *va)
+{
+	va->flags |= VM_LAZY_FREE;
+	atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr);
+	if (unlikely(atomic_read(&vmap_lazy_nr) > lazy_max_pages()))
+		purge_vmap_area_lazy();
+}
+
+static struct vmap_area *find_vmap_area(unsigned long addr)
+{
+	struct vmap_area *va;
+
+	spin_lock(&vmap_area_lock);
+	va = __find_vmap_area(addr);
+	spin_unlock(&vmap_area_lock);
+
+	return va;
+}
+
+static void free_unmap_vmap_area_addr(unsigned long addr)
+{
+	struct vmap_area *va;
+
+	va = find_vmap_area(addr);
+	BUG_ON(!va);
+	free_unmap_vmap_area(va);
+}
+
+
+/*** Per cpu kva allocator ***/
+
+/*
+ * vmap space is limited especially on 32 bit architectures. Ensure there is
+ * room for at least 16 percpu vmap blocks per CPU.
+ */
+/*
+ * If we had a constant VMALLOC_START and VMALLOC_END, we'd like to be able
+ * to #define VMALLOC_SPACE		(VMALLOC_END-VMALLOC_START). Guess
+ * instead (we just need a rough idea)
+ */
+#if BITS_PER_LONG == 32
+#define VMALLOC_SPACE		(128UL*1024*1024)
+#else
+#define VMALLOC_SPACE		(128UL*1024*1024*1024)
+#endif
+
+#define VMALLOC_PAGES		(VMALLOC_SPACE / PAGE_SIZE)
+#define VMAP_MAX_ALLOC		BITS_PER_LONG	/* 256K with 4K pages */
+#define VMAP_BBMAP_BITS_MAX	1024	/* 4MB with 4K pages */
+#define VMAP_BBMAP_BITS_MIN	(VMAP_MAX_ALLOC*2)
+#define VMAP_MIN(x, y)		((x) < (y) ? (x) : (y)) /* can't use min() */
+#define VMAP_MAX(x, y)		((x) > (y) ? (x) : (y)) /* can't use max() */
+#define VMAP_BBMAP_BITS		VMAP_MIN(VMAP_BBMAP_BITS_MAX,		\
+					VMAP_MAX(VMAP_BBMAP_BITS_MIN,	\
+						VMALLOC_PAGES / NR_CPUS / 16))
+
+#define VMAP_BLOCK_SIZE		(VMAP_BBMAP_BITS * PAGE_SIZE)
+
+struct vmap_block_queue {
+	spinlock_t lock;
+	struct list_head free;
+	struct list_head dirty;
+	unsigned int nr_dirty;
+};
+
+struct vmap_block {
+	spinlock_t lock;
+	struct vmap_area *va;
+	struct vmap_block_queue *vbq;
+	unsigned long free, dirty;
+	DECLARE_BITMAP(alloc_map, VMAP_BBMAP_BITS);
+	DECLARE_BITMAP(dirty_map, VMAP_BBMAP_BITS);
+	union {
+		struct {
+			struct list_head free_list;
+			struct list_head dirty_list;
+		};
+		struct rcu_head rcu_head;
+	};
+};
+
+/* Queue of free and dirty vmap blocks, for allocation and flushing purposes */
+static DEFINE_PER_CPU(struct vmap_block_queue, vmap_block_queue);
+
+/*
+ * Radix tree of vmap blocks, indexed by address, to quickly find a vmap block
+ * in the free path. Could get rid of this if we change the API to return a
+ * "cookie" from alloc, to be passed to free. But no big deal yet.
+ */
+static DEFINE_SPINLOCK(vmap_block_tree_lock);
+static RADIX_TREE(vmap_block_tree, GFP_ATOMIC);
+
+/*
+ * We should probably have a fallback mechanism to allocate virtual memory
+ * out of partially filled vmap blocks. However vmap block sizing should be
+ * fairly reasonable according to the vmalloc size, so it shouldn't be a
+ * big problem.
+ */
+
+static unsigned long addr_to_vb_idx(unsigned long addr)
+{
+	addr -= VMALLOC_START & ~(VMAP_BLOCK_SIZE-1);
+	addr /= VMAP_BLOCK_SIZE;
+	return addr;
+}
+
+static struct vmap_block *new_vmap_block(gfp_t gfp_mask)
+{
+	struct vmap_block_queue *vbq;
+	struct vmap_block *vb;
+	struct vmap_area *va;
+	unsigned long vb_idx;
+	int node, err;
+
+	node = numa_node_id();
+
+	vb = kmalloc_node(sizeof(struct vmap_block),
+			gfp_mask & GFP_RECLAIM_MASK, node);
+	if (unlikely(!vb))
+		return ERR_PTR(-ENOMEM);
+
+	va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE,
+					VMALLOC_START, VMALLOC_END,
+					node, gfp_mask);
+	if (unlikely(IS_ERR(va))) {
+		kfree(vb);
+		return ERR_PTR(PTR_ERR(va));
+	}
+
+	err = radix_tree_preload(gfp_mask);
+	if (unlikely(err)) {
+		kfree(vb);
+		free_vmap_area(va);
+		return ERR_PTR(err);
+	}
+
+	spin_lock_init(&vb->lock);
+	vb->va = va;
+	vb->free = VMAP_BBMAP_BITS;
+	vb->dirty = 0;
+	bitmap_zero(vb->alloc_map, VMAP_BBMAP_BITS);
+	bitmap_zero(vb->dirty_map, VMAP_BBMAP_BITS);
+	INIT_LIST_HEAD(&vb->free_list);
+	INIT_LIST_HEAD(&vb->dirty_list);
+
+	vb_idx = addr_to_vb_idx(va->va_start);
+	spin_lock(&vmap_block_tree_lock);
+	err = radix_tree_insert(&vmap_block_tree, vb_idx, vb);
+	spin_unlock(&vmap_block_tree_lock);
+	BUG_ON(err);
+	radix_tree_preload_end();
+
+	vbq = &get_cpu_var(vmap_block_queue);
+	vb->vbq = vbq;
+	spin_lock(&vbq->lock);
+	list_add(&vb->free_list, &vbq->free);
+	spin_unlock(&vbq->lock);
+	put_cpu_var(vmap_cpu_blocks);
+
+	return vb;
+}
+
+static void rcu_free_vb(struct rcu_head *head)
+{
+	struct vmap_block *vb = container_of(head, struct vmap_block, rcu_head);
+
+	kfree(vb);
+}
+
+static void free_vmap_block(struct vmap_block *vb)
+{
+	struct vmap_block *tmp;
+	unsigned long vb_idx;
+
+	spin_lock(&vb->vbq->lock);
+	if (!list_empty(&vb->free_list))
+		list_del(&vb->free_list);
+	if (!list_empty(&vb->dirty_list))
+		list_del(&vb->dirty_list);
+	spin_unlock(&vb->vbq->lock);
+
+	vb_idx = addr_to_vb_idx(vb->va->va_start);
+	spin_lock(&vmap_block_tree_lock);
+	tmp = radix_tree_delete(&vmap_block_tree, vb_idx);
+	spin_unlock(&vmap_block_tree_lock);
+	BUG_ON(tmp != vb);
+
+	free_unmap_vmap_area(vb->va);
+	call_rcu(&vb->rcu_head, rcu_free_vb);
+}
+
+static void *vb_alloc(unsigned long size, gfp_t gfp_mask)
+{
+	struct vmap_block_queue *vbq;
+	struct vmap_block *vb;
+	unsigned long addr = 0;
+	unsigned int order;
+
+	BUG_ON(size & ~PAGE_MASK);
+	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
+	order = get_order(size);
+
+again:
+	rcu_read_lock();
+	vbq = &get_cpu_var(vmap_block_queue);
+	list_for_each_entry_rcu(vb, &vbq->free, free_list) {
+		int i;
+
+		spin_lock(&vb->lock);
+		i = bitmap_find_free_region(vb->alloc_map,
+						VMAP_BBMAP_BITS, order);
+
+		if (i >= 0) {
+			addr = vb->va->va_start + (i << PAGE_SHIFT);
+			BUG_ON(addr_to_vb_idx(addr) !=
+					addr_to_vb_idx(vb->va->va_start));
+			vb->free -= 1UL << order;
+			if (vb->free == 0) {
+				spin_lock(&vbq->lock);
+				list_del_init(&vb->free_list);
+				spin_unlock(&vbq->lock);
+			}
+			spin_unlock(&vb->lock);
+			break;
+		}
+		spin_unlock(&vb->lock);
+	}
+	put_cpu_var(vmap_cpu_blocks);
+	rcu_read_unlock();
+
+	if (!addr) {
+		vb = new_vmap_block(gfp_mask);
+		if (IS_ERR(vb))
+			return vb;
+		goto again;
+	}
+
+	return (void *)addr;
+}
+
+static void vb_free(const void *addr, unsigned long size)
+{
+	unsigned long offset;
+	unsigned long vb_idx;
+	unsigned int order;
+	struct vmap_block *vb;
+
+	BUG_ON(size & ~PAGE_MASK);
+	BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC);
+	order = get_order(size);
+
+	offset = (unsigned long)addr & (VMAP_BLOCK_SIZE - 1);
+
+	vb_idx = addr_to_vb_idx((unsigned long)addr);
+	rcu_read_lock();
+	vb = radix_tree_lookup(&vmap_block_tree, vb_idx);
+	rcu_read_unlock();
+	BUG_ON(!vb);
+
+	spin_lock(&vb->lock);
+	bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order);
+	if (!vb->dirty) {
+		spin_lock(&vb->vbq->lock);
+		list_add(&vb->dirty_list, &vb->vbq->dirty);
+		spin_unlock(&vb->vbq->lock);
+	}
+	vb->dirty += 1UL << order;
+	if (vb->dirty == VMAP_BBMAP_BITS) {
+		BUG_ON(vb->free || !list_empty(&vb->free_list));
+		spin_unlock(&vb->lock);
+		free_vmap_block(vb);
+	} else
+		spin_unlock(&vb->lock);
+}
+
+/**
+ * vm_unmap_aliases - unmap outstanding lazy aliases in the vmap layer
+ *
+ * The vmap/vmalloc layer lazily flushes kernel virtual mappings primarily
+ * to amortize TLB flushing overheads. What this means is that any page you
+ * have now, may, in a former life, have been mapped into kernel virtual
+ * address by the vmap layer and so there might be some CPUs with TLB entries
+ * still referencing that page (additional to the regular 1:1 kernel mapping).
+ *
+ * vm_unmap_aliases flushes all such lazy mappings. After it returns, we can
+ * be sure that none of the pages we have control over will have any aliases
+ * from the vmap layer.
+ */
+void vm_unmap_aliases(void)
+{
+	unsigned long start = ULONG_MAX, end = 0;
+	int cpu;
+	int flush = 0;
+
+	for_each_possible_cpu(cpu) {
+		struct vmap_block_queue *vbq = &per_cpu(vmap_block_queue, cpu);
+		struct vmap_block *vb;
+
+		rcu_read_lock();
+		list_for_each_entry_rcu(vb, &vbq->free, free_list) {
+			int i;
+
+			spin_lock(&vb->lock);
+			i = find_first_bit(vb->dirty_map, VMAP_BBMAP_BITS);
+			while (i < VMAP_BBMAP_BITS) {
+				unsigned long s, e;
+				int j;
+				j = find_next_zero_bit(vb->dirty_map,
+					VMAP_BBMAP_BITS, i);
+
+				s = vb->va->va_start + (i << PAGE_SHIFT);
+				e = vb->va->va_start + (j << PAGE_SHIFT);
+				vunmap_page_range(s, e);
+				flush = 1;
+
+				if (s < start)
+					start = s;
+				if (e > end)
+					end = e;
+
+				i = j;
+				i = find_next_bit(vb->dirty_map,
+							VMAP_BBMAP_BITS, i);
+			}
+			spin_unlock(&vb->lock);
+		}
+		rcu_read_unlock();
+	}
+
+	__purge_vmap_area_lazy(&start, &end, 1, flush);
+}
+EXPORT_SYMBOL_GPL(vm_unmap_aliases);
+
+/**
+ * vm_unmap_ram - unmap linear kernel address space set up by vm_map_ram
+ * @mem: the pointer returned by vm_map_ram
+ * @count: the count passed to that vm_map_ram call (cannot unmap partial)
+ */
+void vm_unmap_ram(const void *mem, unsigned int count)
+{
+	unsigned long size = count << PAGE_SHIFT;
+	unsigned long addr = (unsigned long)mem;
+
+	BUG_ON(!addr);
+	BUG_ON(addr < VMALLOC_START);
+	BUG_ON(addr > VMALLOC_END);
+	BUG_ON(addr & (PAGE_SIZE-1));
+
+	debug_check_no_locks_freed(mem, size);
+
+	if (likely(count <= VMAP_MAX_ALLOC))
+		vb_free(mem, size);
+	else
+		free_unmap_vmap_area_addr(addr);
+}
+EXPORT_SYMBOL(vm_unmap_ram);
+
+/**
+ * vm_map_ram - map pages linearly into kernel virtual address (vmalloc space)
+ * @pages: an array of pointers to the pages to be mapped
+ * @count: number of pages
+ * @node: prefer to allocate data structures on this node
+ * @prot: memory protection to use. PAGE_KERNEL for regular RAM
+ * @returns: a pointer to the address that has been mapped, or NULL on failure
+ */
+void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
+{
+	unsigned long size = count << PAGE_SHIFT;
 	unsigned long addr;
+	void *mem;
+
+	if (likely(count <= VMAP_MAX_ALLOC)) {
+		mem = vb_alloc(size, GFP_KERNEL);
+		if (IS_ERR(mem))
+			return NULL;
+		addr = (unsigned long)mem;
+	} else {
+		struct vmap_area *va;
+		va = alloc_vmap_area(size, PAGE_SIZE,
+				VMALLOC_START, VMALLOC_END, node, GFP_KERNEL);
+		if (IS_ERR(va))
+			return NULL;
+
+		addr = va->va_start;
+		mem = (void *)addr;
+	}
+	if (vmap_page_range(addr, addr + size, prot, pages) < 0) {
+		vm_unmap_ram(mem, count);
+		return NULL;
+	}
+	return mem;
+}
+EXPORT_SYMBOL(vm_map_ram);
+
+void __init vmalloc_init(void)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct vmap_block_queue *vbq;
+
+		vbq = &per_cpu(vmap_block_queue, i);
+		spin_lock_init(&vbq->lock);
+		INIT_LIST_HEAD(&vbq->free);
+		INIT_LIST_HEAD(&vbq->dirty);
+		vbq->nr_dirty = 0;
+	}
+}
+
+void unmap_kernel_range(unsigned long addr, unsigned long size)
+{
+	unsigned long end = addr + size;
+	vunmap_page_range(addr, end);
+	flush_tlb_kernel_range(addr, end);
+}
+
+int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages)
+{
+	unsigned long addr = (unsigned long)area->addr;
+	unsigned long end = addr + area->size - PAGE_SIZE;
+	int err;
+
+	err = vmap_page_range(addr, end, prot, *pages);
+	if (err > 0) {
+		*pages += err;
+		err = 0;
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(map_vm_area);
+
+/*** Old vmalloc interfaces ***/
+DEFINE_RWLOCK(vmlist_lock);
+struct vm_struct *vmlist;
+
+static struct vm_struct *__get_vm_area_node(unsigned long size,
+		unsigned long flags, unsigned long start, unsigned long end,
+		int node, gfp_t gfp_mask, void *caller)
+{
+	static struct vmap_area *va;
+	struct vm_struct *area;
+	struct vm_struct *tmp, **p;
+	unsigned long align = 1;
 
 	BUG_ON(in_interrupt());
 	if (flags & VM_IOREMAP) {
@@ -232,13 +976,12 @@ __get_vm_area_node(unsigned long size, unsigned long flags, unsigned long start,
 
 		align = 1ul << bit;
 	}
-	addr = ALIGN(start, align);
+
 	size = PAGE_ALIGN(size);
 	if (unlikely(!size))
 		return NULL;
 
 	area = kmalloc_node(sizeof(*area), gfp_mask & GFP_RECLAIM_MASK, node);
-
 	if (unlikely(!area))
 		return NULL;
 
@@ -247,48 +990,32 @@ __get_vm_area_node(unsigned long size, unsigned long flags, unsigned long start,
 	 */
 	size += PAGE_SIZE;
 
-	write_lock(&vmlist_lock);
-	for (p = &vmlist; (tmp = *p) != NULL ;p = &tmp->next) {
-		if ((unsigned long)tmp->addr < addr) {
-			if((unsigned long)tmp->addr + tmp->size >= addr)
-				addr = ALIGN(tmp->size + 
-					     (unsigned long)tmp->addr, align);
-			continue;
-		}
-		if ((size + addr) < addr)
-			goto out;
-		if (size + addr <= (unsigned long)tmp->addr)
-			goto found;
-		addr = ALIGN(tmp->size + (unsigned long)tmp->addr, align);
-		if (addr > end - size)
-			goto out;
+	va = alloc_vmap_area(size, align, start, end, node, gfp_mask);
+	if (IS_ERR(va)) {
+		kfree(area);
+		return NULL;
 	}
-	if ((size + addr) < addr)
-		goto out;
-	if (addr > end - size)
-		goto out;
-
-found:
-	area->next = *p;
-	*p = area;
 
 	area->flags = flags;
-	area->addr = (void *)addr;
+	area->addr = (void *)va->va_start;
 	area->size = size;
 	area->pages = NULL;
 	area->nr_pages = 0;
 	area->phys_addr = 0;
 	area->caller = caller;
+	va->private = area;
+	va->flags |= VM_VM_AREA;
+
+	write_lock(&vmlist_lock);
+	for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) {
+		if (tmp->addr >= area->addr)
+			break;
+	}
+	area->next = *p;
+	*p = area;
 	write_unlock(&vmlist_lock);
 
 	return area;
-
-out:
-	write_unlock(&vmlist_lock);
-	kfree(area);
-	if (printk_ratelimit())
-		printk(KERN_WARNING "allocation failed: out of vmalloc space - use vmalloc=<size> to increase size.\n");
-	return NULL;
 }
 
 struct vm_struct *__get_vm_area(unsigned long size, unsigned long flags,
@@ -328,39 +1055,15 @@ struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags,
 				  gfp_mask, __builtin_return_address(0));
 }
 
-/* Caller must hold vmlist_lock */
-static struct vm_struct *__find_vm_area(const void *addr)
+static struct vm_struct *find_vm_area(const void *addr)
 {
-	struct vm_struct *tmp;
+	struct vmap_area *va;
 
-	for (tmp = vmlist; tmp != NULL; tmp = tmp->next) {
-		 if (tmp->addr == addr)
-			break;
-	}
-
-	return tmp;
-}
-
-/* Caller must hold vmlist_lock */
-static struct vm_struct *__remove_vm_area(const void *addr)
-{
-	struct vm_struct **p, *tmp;
+	va = find_vmap_area((unsigned long)addr);
+	if (va && va->flags & VM_VM_AREA)
+		return va->private;
 
-	for (p = &vmlist ; (tmp = *p) != NULL ;p = &tmp->next) {
-		 if (tmp->addr == addr)
-			 goto found;
-	}
 	return NULL;
-
-found:
-	unmap_vm_area(tmp);
-	*p = tmp->next;
-
-	/*
-	 * Remove the guard page.
-	 */
-	tmp->size -= PAGE_SIZE;
-	return tmp;
 }
 
 /**
@@ -373,11 +1076,24 @@ found:
  */
 struct vm_struct *remove_vm_area(const void *addr)
 {
-	struct vm_struct *v;
-	write_lock(&vmlist_lock);
-	v = __remove_vm_area(addr);
-	write_unlock(&vmlist_lock);
-	return v;
+	struct vmap_area *va;
+
+	va = find_vmap_area((unsigned long)addr);
+	if (va && va->flags & VM_VM_AREA) {
+		struct vm_struct *vm = va->private;
+		struct vm_struct *tmp, **p;
+		free_unmap_vmap_area(va);
+		vm->size -= PAGE_SIZE;
+
+		write_lock(&vmlist_lock);
+		for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next)
+			;
+		*p = tmp->next;
+		write_unlock(&vmlist_lock);
+
+		return vm;
+	}
+	return NULL;
 }
 
 static void __vunmap(const void *addr, int deallocate_pages)
@@ -487,6 +1203,8 @@ void *vmap(struct page **pages, unsigned int count,
 }
 EXPORT_SYMBOL(vmap);
 
+static void *__vmalloc_node(unsigned long size, gfp_t gfp_mask, pgprot_t prot,
+			    int node, void *caller);
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, int node, void *caller)
 {
@@ -613,10 +1331,8 @@ void *vmalloc_user(unsigned long size)
 
 	ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
 	if (ret) {
-		write_lock(&vmlist_lock);
-		area = __find_vm_area(ret);
+		area = find_vm_area(ret);
 		area->flags |= VM_USERMAP;
-		write_unlock(&vmlist_lock);
 	}
 	return ret;
 }
@@ -696,10 +1412,8 @@ void *vmalloc_32_user(unsigned long size)
 
 	ret = __vmalloc(size, GFP_VMALLOC32 | __GFP_ZERO, PAGE_KERNEL);
 	if (ret) {
-		write_lock(&vmlist_lock);
-		area = __find_vm_area(ret);
+		area = find_vm_area(ret);
 		area->flags |= VM_USERMAP;
-		write_unlock(&vmlist_lock);
 	}
 	return ret;
 }
@@ -800,26 +1514,25 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 	struct vm_struct *area;
 	unsigned long uaddr = vma->vm_start;
 	unsigned long usize = vma->vm_end - vma->vm_start;
-	int ret;
 
 	if ((PAGE_SIZE-1) & (unsigned long)addr)
 		return -EINVAL;
 
-	read_lock(&vmlist_lock);
-	area = __find_vm_area(addr);
+	area = find_vm_area(addr);
 	if (!area)
-		goto out_einval_locked;
+		return -EINVAL;
 
 	if (!(area->flags & VM_USERMAP))
-		goto out_einval_locked;
+		return -EINVAL;
 
 	if (usize + (pgoff << PAGE_SHIFT) > area->size - PAGE_SIZE)
-		goto out_einval_locked;
-	read_unlock(&vmlist_lock);
+		return -EINVAL;
 
 	addr += pgoff << PAGE_SHIFT;
 	do {
 		struct page *page = vmalloc_to_page(addr);
+		int ret;
+
 		ret = vm_insert_page(vma, uaddr, page);
 		if (ret)
 			return ret;
@@ -832,11 +1545,7 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 	/* Prevent "things" like memory migration? VM_flags need a cleanup... */
 	vma->vm_flags |= VM_RESERVED;
 
-	return ret;
-
-out_einval_locked:
-	read_unlock(&vmlist_lock);
-	return -EINVAL;
+	return 0;
 }
 EXPORT_SYMBOL(remap_vmalloc_range);
 
-- 
cgit v1.2.3


From e575f111dc0f27044e170580e7de50985ab3e011 Mon Sep 17 00:00:00 2001
From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Date: Sat, 18 Oct 2008 20:27:08 -0700
Subject: coredump_filter: add hugepage dumping

Presently hugepage's vma has a VM_RESERVED flag in order not to be
swapped.  But a VM_RESERVED vma isn't core dumped because this flag is
often used for some kernel vmas (e.g.  vmalloc, sound related).

Thus hugepages are never dumped and it can't be debugged easily.  Many
developers want hugepages to be included into core-dump.

However, We can't read generic VM_RESERVED area because this area is often
IO mapping area.  then these area reading may change device state.  it is
definitly undesiable side-effect.

So adding a hugepage specific bit to the coredump filter is better.  It
will be able to hugepage core dumping and doesn't cause any side-effect to
any i/o devices.

In additional, libhugetlb use hugetlb private mapping pages as anonymous
page.  Then, hugepage private mapping pages should be core dumped by
default.

Then, /proc/[pid]/core_dump_filter has two new bits.

 - bit 5 mean hugetlb private mapping pages are dumped or not. (default: yes)
 - bit 6 mean hugetlb shared mapping pages are dumped or not.  (default: no)

I tested by following method.

% ulimit -c unlimited
% ./crash_hugepage  50
% ./crash_hugepage  50  -p
% ls -lh
% gdb ./crash_hugepage core
%
% echo 0x43 > /proc/self/coredump_filter
% ./crash_hugepage  50
% ./crash_hugepage  50  -p
% ls -lh
% gdb ./crash_hugepage core

#include <stdlib.h>
#include <stdio.h>
#include <unistd.h>
#include <sys/mman.h>
#include <string.h>

#include "hugetlbfs.h"

int main(int argc, char** argv){
	char* p;
	int ch;
	int mmap_flags = MAP_SHARED;
	int fd;
	int nr_pages;

	while((ch = getopt(argc, argv, "p")) != -1) {
		switch (ch) {
		case 'p':
			mmap_flags &= ~MAP_SHARED;
			mmap_flags |= MAP_PRIVATE;
			break;
		default:
			/* nothing*/
			break;
		}
	}
	argc -= optind;
	argv += optind;

	if (argc == 0){
		printf("need # of pages\n");
		exit(1);
	}

	nr_pages = atoi(argv[0]);
	if (nr_pages < 2) {
		printf("nr_pages must >2\n");
		exit(1);
	}

	fd = hugetlbfs_unlinked_fd();
	p = mmap(NULL, nr_pages * gethugepagesize(),
		 PROT_READ|PROT_WRITE, mmap_flags, fd, 0);

	sleep(2);

	*(p + gethugepagesize()) = 1; /* COW */
	sleep(2);

	/* crash! */
	*(int*)0 = 1;

	return 0;
}

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Reviewed-by: Kawai Hidehiro <hidehiro.kawai.ez@hitachi.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: William Irwin <wli@holomorphy.com>
Cc: Adam Litke <agl@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/filesystems/proc.txt | 15 ++++++++++-----
 fs/binfmt_elf.c                    | 12 ++++++++++--
 include/linux/sched.h              |  7 +++++--
 3 files changed, 25 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index c032bf39e8b9..02cb7faeed6b 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -2412,24 +2412,29 @@ will be dumped when the <pid> process is dumped. coredump_filter is a bitmask
 of memory types. If a bit of the bitmask is set, memory segments of the
 corresponding memory type are dumped, otherwise they are not dumped.
 
-The following 4 memory types are supported:
+The following 7 memory types are supported:
   - (bit 0) anonymous private memory
   - (bit 1) anonymous shared memory
   - (bit 2) file-backed private memory
   - (bit 3) file-backed shared memory
   - (bit 4) ELF header pages in file-backed private memory areas (it is
             effective only if the bit 2 is cleared)
+  - (bit 5) hugetlb private memory
+  - (bit 6) hugetlb shared memory
 
   Note that MMIO pages such as frame buffer are never dumped and vDSO pages
   are always dumped regardless of the bitmask status.
 
-Default value of coredump_filter is 0x3; this means all anonymous memory
-segments are dumped.
+  Note bit 0-4 doesn't effect any hugetlb memory. hugetlb memory are only
+  effected by bit 5-6.
+
+Default value of coredump_filter is 0x23; this means all anonymous memory
+segments and hugetlb private memory are dumped.
 
 If you don't want to dump all shared memory segments attached to pid 1234,
-write 1 to the process's proc file.
+write 0x21 to the process's proc file.
 
-  $ echo 0x1 > /proc/1234/coredump_filter
+  $ echo 0x21 > /proc/1234/coredump_filter
 
 When a new process is created, the process inherits the bitmask status from its
 parent. It is useful to set up coredump_filter before the program runs.
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index c76afa26edf7..e2159063198a 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1156,16 +1156,24 @@ static int dump_seek(struct file *file, loff_t off)
 static unsigned long vma_dump_size(struct vm_area_struct *vma,
 				   unsigned long mm_flags)
 {
+#define FILTER(type)	(mm_flags & (1UL << MMF_DUMP_##type))
+
 	/* The vma can be set up to tell us the answer directly.  */
 	if (vma->vm_flags & VM_ALWAYSDUMP)
 		goto whole;
 
+	/* Hugetlb memory check */
+	if (vma->vm_flags & VM_HUGETLB) {
+		if ((vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_SHARED))
+			goto whole;
+		if (!(vma->vm_flags & VM_SHARED) && FILTER(HUGETLB_PRIVATE))
+			goto whole;
+	}
+
 	/* Do not dump I/O mapped devices or special mappings */
 	if (vma->vm_flags & (VM_IO | VM_RESERVED))
 		return 0;
 
-#define FILTER(type)	(mm_flags & (1UL << MMF_DUMP_##type))
-
 	/* By default, dump shared memory if mapped from an anonymous file. */
 	if (vma->vm_flags & VM_SHARED) {
 		if (vma->vm_file->f_path.dentry->d_inode->i_nlink == 0 ?
diff --git a/include/linux/sched.h b/include/linux/sched.h
index c226c7b82946..017cc914ef1f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -403,12 +403,15 @@ extern int get_dumpable(struct mm_struct *mm);
 #define MMF_DUMP_MAPPED_PRIVATE	4
 #define MMF_DUMP_MAPPED_SHARED	5
 #define MMF_DUMP_ELF_HEADERS	6
+#define MMF_DUMP_HUGETLB_PRIVATE 7
+#define MMF_DUMP_HUGETLB_SHARED  8
 #define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
-#define MMF_DUMP_FILTER_BITS	5
+#define MMF_DUMP_FILTER_BITS	7
 #define MMF_DUMP_FILTER_MASK \
 	(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
 #define MMF_DUMP_FILTER_DEFAULT \
-	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED))
+	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED) |\
+	 (1 << MMF_DUMP_HUGETLB_PRIVATE))
 
 struct sighand_struct {
 	atomic_t		count;
-- 
cgit v1.2.3


From 83224b08372be48d5fcefedc4886457da29130c8 Mon Sep 17 00:00:00 2001
From: Matt Helsley <matthltc@us.ibm.com>
Date: Sat, 18 Oct 2008 20:27:18 -0700
Subject: container freezer: add TIF_FREEZE flag to all architectures

This patch series introduces a cgroup subsystem that utilizes the swsusp
freezer to freeze a group of tasks.  It's immediately useful for batch job
management scripts.  It should also be useful in the future for
implementing container checkpoint/restart.

The freezer subsystem in the container filesystem defines a cgroup file
named freezer.state.  Reading freezer.state will return the current state
of the cgroup.  Writing "FROZEN" to the state file will freeze all tasks
in the cgroup.  Subsequently writing "RUNNING" will unfreeze the tasks in
the cgroup.

* Examples of usage :

   # mkdir /containers/freezer
   # mount -t cgroup -ofreezer freezer  /containers
   # mkdir /containers/0
   # echo $some_pid > /containers/0/tasks

to get status of the freezer subsystem :

   # cat /containers/0/freezer.state
   RUNNING

to freeze all tasks in the container :

   # echo FROZEN > /containers/0/freezer.state
   # cat /containers/0/freezer.state
   FREEZING
   # cat /containers/0/freezer.state
   FROZEN

to unfreeze all tasks in the container :

   # echo RUNNING > /containers/0/freezer.state
   # cat /containers/0/freezer.state
   RUNNING

This patch:

The first step in making the refrigerator() available to all
architectures, even for those without power management.

The purpose of such a change is to be able to use the refrigerator() in a
new control group subsystem which will implement a control group freezer.

[akpm@linux-foundation.org: fix sparc]
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Matt Helsley <matthltc@us.ibm.com>
Acked-by: Pavel Machek <pavel@suse.cz>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Acked-by: Rafael J. Wysocki <rjw@sisk.pl>
Acked-by: Nigel Cunningham <nigel@tuxonice.net>
Tested-by: Matt Helsley <matthltc@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/include/asm/thread_info.h     | 2 ++
 arch/avr32/include/asm/thread_info.h     | 1 +
 arch/h8300/include/asm/thread_info.h     | 2 ++
 arch/m68knommu/include/asm/thread_info.h | 2 ++
 arch/s390/include/asm/thread_info.h      | 2 ++
 arch/sparc/include/asm/thread_info_32.h  | 2 ++
 arch/sparc/include/asm/thread_info_64.h  | 2 ++
 include/asm-cris/thread_info.h           | 2 ++
 include/asm-m68k/thread_info.h           | 1 +
 include/asm-parisc/thread_info.h         | 2 ++
 include/asm-um/thread_info.h             | 2 ++
 include/asm-xtensa/thread_info.h         | 2 ++
 12 files changed, 22 insertions(+)

(limited to 'include')

diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h
index 15fda4344424..d069526bd767 100644
--- a/arch/alpha/include/asm/thread_info.h
+++ b/arch/alpha/include/asm/thread_info.h
@@ -74,12 +74,14 @@ register struct thread_info *__current_thread_info __asm__("$8");
 #define TIF_UAC_SIGBUS		7
 #define TIF_MEMDIE		8
 #define TIF_RESTORE_SIGMASK	9	/* restore signal mask in do_signal */
+#define TIF_FREEZE		16	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
+#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 /* Work to do on interrupt/exception return.  */
 #define _TIF_WORK_MASK		(_TIF_SIGPENDING | _TIF_NEED_RESCHED)
diff --git a/arch/avr32/include/asm/thread_info.h b/arch/avr32/include/asm/thread_info.h
index 294b25f9323d..4442f8d2d423 100644
--- a/arch/avr32/include/asm/thread_info.h
+++ b/arch/avr32/include/asm/thread_info.h
@@ -96,6 +96,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_MEMDIE		(1 << TIF_MEMDIE)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
 #define _TIF_CPU_GOING_TO_SLEEP (1 << TIF_CPU_GOING_TO_SLEEP)
+#define _TIF_FREEZE		(1 << TIF_FREEZE)
 
 /* Note: The masks below must never span more than 16 bits! */
 
diff --git a/arch/h8300/include/asm/thread_info.h b/arch/h8300/include/asm/thread_info.h
index aafd4d322ec3..700014d2155f 100644
--- a/arch/h8300/include/asm/thread_info.h
+++ b/arch/h8300/include/asm/thread_info.h
@@ -89,6 +89,7 @@ static inline struct thread_info *current_thread_info(void)
 					   TIF_NEED_RESCHED */
 #define TIF_MEMDIE		4
 #define TIF_RESTORE_SIGMASK	5	/* restore signal mask in do_signal() */
+#define TIF_FREEZE		16	/* is freezing for suspend */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -96,6 +97,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
+#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 
diff --git a/arch/m68knommu/include/asm/thread_info.h b/arch/m68knommu/include/asm/thread_info.h
index 0c9bc095f3f0..82529f424ea3 100644
--- a/arch/m68knommu/include/asm/thread_info.h
+++ b/arch/m68knommu/include/asm/thread_info.h
@@ -84,12 +84,14 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_POLLING_NRFLAG	3	/* true if poll_idle() is polling
 					   TIF_NEED_RESCHED */
 #define TIF_MEMDIE		4
+#define TIF_FREEZE		16	/* is freezing for suspend */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
+#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 
diff --git a/arch/s390/include/asm/thread_info.h b/arch/s390/include/asm/thread_info.h
index ea40a9d690fc..de3fad60c682 100644
--- a/arch/s390/include/asm/thread_info.h
+++ b/arch/s390/include/asm/thread_info.h
@@ -99,6 +99,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_31BIT		18	/* 32bit process */ 
 #define TIF_MEMDIE		19
 #define TIF_RESTORE_SIGMASK	20	/* restore signal mask in do_signal() */
+#define TIF_FREEZE		21	/* thread is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
@@ -112,6 +113,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_USEDFPU		(1<<TIF_USEDFPU)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_31BIT		(1<<TIF_31BIT)
+#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/sparc/include/asm/thread_info_32.h b/arch/sparc/include/asm/thread_info_32.h
index 29899fd5b1b2..80fe547c3f45 100644
--- a/arch/sparc/include/asm/thread_info_32.h
+++ b/arch/sparc/include/asm/thread_info_32.h
@@ -135,6 +135,7 @@ BTFIXUPDEF_CALL(void, free_thread_info, struct thread_info *)
 #define TIF_POLLING_NRFLAG	9	/* true if poll_idle() is polling
 					 * TIF_NEED_RESCHED */
 #define TIF_MEMDIE		10
+#define TIF_FREEZE		11	/* is freezing for suspend */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
@@ -148,6 +149,7 @@ BTFIXUPDEF_CALL(void, free_thread_info, struct thread_info *)
 #define _TIF_DO_NOTIFY_RESUME_MASK	(_TIF_NOTIFY_RESUME | \
 					 _TIF_SIGPENDING | \
 					 _TIF_RESTORE_SIGMASK)
+#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #endif /* __KERNEL__ */
 
diff --git a/arch/sparc/include/asm/thread_info_64.h b/arch/sparc/include/asm/thread_info_64.h
index c0a737d7292c..639ac805448a 100644
--- a/arch/sparc/include/asm/thread_info_64.h
+++ b/arch/sparc/include/asm/thread_info_64.h
@@ -237,6 +237,7 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define TIF_ABI_PENDING		12
 #define TIF_MEMDIE		13
 #define TIF_POLLING_NRFLAG	14
+#define TIF_FREEZE		15	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
@@ -249,6 +250,7 @@ register struct thread_info *current_thread_info_reg asm("g6");
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_ABI_PENDING	(1<<TIF_ABI_PENDING)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
+#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_USER_WORK_MASK	((0xff << TI_FLAG_WSAVED_SHIFT) | \
 				 _TIF_DO_NOTIFY_RESUME_MASK | \
diff --git a/include/asm-cris/thread_info.h b/include/asm-cris/thread_info.h
index 7efe1000f99d..cee97f14af3b 100644
--- a/include/asm-cris/thread_info.h
+++ b/include/asm-cris/thread_info.h
@@ -88,6 +88,7 @@ struct thread_info {
 #define TIF_RESTORE_SIGMASK	9	/* restore signal mask in do_signal() */
 #define TIF_POLLING_NRFLAG	16	/* true if poll_idle() is polling TIF_NEED_RESCHED */
 #define TIF_MEMDIE		17
+#define TIF_FREEZE		18	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1<<TIF_NOTIFY_RESUME)
@@ -95,6 +96,7 @@ struct thread_info {
 #define _TIF_NEED_RESCHED	(1<<TIF_NEED_RESCHED)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
+#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 #define _TIF_ALLWORK_MASK	0x0000FFFF	/* work to do on any return to u-space */
diff --git a/include/asm-m68k/thread_info.h b/include/asm-m68k/thread_info.h
index abc002798a2b..af0fda46e94b 100644
--- a/include/asm-m68k/thread_info.h
+++ b/include/asm-m68k/thread_info.h
@@ -52,5 +52,6 @@ struct thread_info {
 #define TIF_DELAYED_TRACE	14	/* single step a syscall */
 #define TIF_SYSCALL_TRACE	15	/* syscall trace active */
 #define TIF_MEMDIE		16
+#define TIF_FREEZE		17	/* thread is freezing for suspend */
 
 #endif	/* _ASM_M68K_THREAD_INFO_H */
diff --git a/include/asm-parisc/thread_info.h b/include/asm-parisc/thread_info.h
index 9f812741c355..0407959da489 100644
--- a/include/asm-parisc/thread_info.h
+++ b/include/asm-parisc/thread_info.h
@@ -58,6 +58,7 @@ struct thread_info {
 #define TIF_32BIT               4       /* 32 bit binary */
 #define TIF_MEMDIE		5
 #define TIF_RESTORE_SIGMASK	6	/* restore saved signal mask */
+#define TIF_FREEZE		7	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
@@ -65,6 +66,7 @@ struct thread_info {
 #define _TIF_POLLING_NRFLAG	(1 << TIF_POLLING_NRFLAG)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
+#define _TIF_FREEZE		(1 << TIF_FREEZE)
 
 #define _TIF_USER_WORK_MASK     (_TIF_SIGPENDING | \
                                  _TIF_NEED_RESCHED | _TIF_RESTORE_SIGMASK)
diff --git a/include/asm-um/thread_info.h b/include/asm-um/thread_info.h
index e07e72846c7a..62274ab9471f 100644
--- a/include/asm-um/thread_info.h
+++ b/include/asm-um/thread_info.h
@@ -69,6 +69,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_MEMDIE	 	5
 #define TIF_SYSCALL_AUDIT	6
 #define TIF_RESTORE_SIGMASK	7
+#define TIF_FREEZE		16	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
@@ -77,5 +78,6 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_MEMDIE		(1 << TIF_MEMDIE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
+#define _TIF_FREEZE		(1 << TIF_FREEZE)
 
 #endif
diff --git a/include/asm-xtensa/thread_info.h b/include/asm-xtensa/thread_info.h
index 7e4131dd546c..0f4fe1faf9ba 100644
--- a/include/asm-xtensa/thread_info.h
+++ b/include/asm-xtensa/thread_info.h
@@ -134,6 +134,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_MEMDIE		5
 #define TIF_RESTORE_SIGMASK	6	/* restore signal mask in do_signal() */
 #define TIF_POLLING_NRFLAG	16	/* true if poll_idle() is polling TIF_NEED_RESCHED */
+#define TIF_FREEZE		17	/* is freezing for suspend */
 
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING		(1<<TIF_SIGPENDING)
@@ -142,6 +143,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_IRET		(1<<TIF_IRET)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_RESTORE_SIGMASK	(1<<TIF_RESTORE_SIGMASK)
+#define _TIF_FREEZE		(1<<TIF_FREEZE)
 
 #define _TIF_WORK_MASK		0x0000FFFE	/* work to do on interrupt/exception return */
 #define _TIF_ALLWORK_MASK	0x0000FFFF	/* work to do on any return to u-space */
-- 
cgit v1.2.3


From 8174f1503f4bf7e9a14b3fbbfdb30c6be6e29f77 Mon Sep 17 00:00:00 2001
From: Matt Helsley <matthltc@us.ibm.com>
Date: Sat, 18 Oct 2008 20:27:19 -0700
Subject: container freezer: make refrigerator always available

Now that the TIF_FREEZE flag is available in all architectures, extract
the refrigerator() and freeze_task() from kernel/power/process.c and make
it available to all.

The refrigerator() can now be used in a control group subsystem
implementing a control group freezer.

Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Matt Helsley <matthltc@us.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Matt Helsley <matthltc@us.ibm.com>
Cc: "Rafael J. Wysocki" <rjw@sisk.pl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/freezer.h |  14 ++++--
 kernel/Makefile         |   1 +
 kernel/freezer.c        | 122 ++++++++++++++++++++++++++++++++++++++++++++++++
 kernel/power/Kconfig    |   3 ++
 kernel/power/process.c  | 116 ---------------------------------------------
 5 files changed, 137 insertions(+), 119 deletions(-)
 create mode 100644 kernel/freezer.c

(limited to 'include')

diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index deddeedf3257..17e3bb42dd3c 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -6,7 +6,7 @@
 #include <linux/sched.h>
 #include <linux/wait.h>
 
-#ifdef CONFIG_PM_SLEEP
+#ifdef CONFIG_FREEZER
 /*
  * Check if a process has been frozen
  */
@@ -39,6 +39,11 @@ static inline void clear_freeze_flag(struct task_struct *p)
 	clear_tsk_thread_flag(p, TIF_FREEZE);
 }
 
+static inline bool should_send_signal(struct task_struct *p)
+{
+	return !(p->flags & PF_FREEZER_NOSIG);
+}
+
 /*
  * Wake up a frozen process
  *
@@ -75,6 +80,9 @@ static inline int try_to_freeze(void)
 		return 0;
 }
 
+extern bool freeze_task(struct task_struct *p, bool sig_only);
+extern void cancel_freezing(struct task_struct *p);
+
 /*
  * The PF_FREEZER_SKIP flag should be set by a vfork parent right before it
  * calls wait_for_completion(&vfork) and reset right after it returns from this
@@ -166,7 +174,7 @@ static inline void set_freezable_with_signal(void)
 	} while (try_to_freeze());					\
 	__retval;							\
 })
-#else /* !CONFIG_PM_SLEEP */
+#else /* !CONFIG_FREEZER */
 static inline int frozen(struct task_struct *p) { return 0; }
 static inline int freezing(struct task_struct *p) { return 0; }
 static inline void set_freeze_flag(struct task_struct *p) {}
@@ -191,6 +199,6 @@ static inline void set_freezable_with_signal(void) {}
 #define wait_event_freezable_timeout(wq, condition, timeout)		\
 		wait_event_interruptible_timeout(wq, condition, timeout)
 
-#endif /* !CONFIG_PM_SLEEP */
+#endif /* !CONFIG_FREEZER */
 
 #endif	/* FREEZER_H_INCLUDED */
diff --git a/kernel/Makefile b/kernel/Makefile
index 4e1d7df7c3e2..e8194d15d5f4 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -24,6 +24,7 @@ CFLAGS_REMOVE_sched_clock.o = -pg
 CFLAGS_REMOVE_sched.o = -mno-spe -pg
 endif
 
+obj-$(CONFIG_FREEZER) += freezer.o
 obj-$(CONFIG_PROFILING) += profile.o
 obj-$(CONFIG_SYSCTL_SYSCALL_CHECK) += sysctl_check.o
 obj-$(CONFIG_STACKTRACE) += stacktrace.o
diff --git a/kernel/freezer.c b/kernel/freezer.c
new file mode 100644
index 000000000000..cb0931f89306
--- /dev/null
+++ b/kernel/freezer.c
@@ -0,0 +1,122 @@
+/*
+ * kernel/freezer.c - Function to freeze a process
+ *
+ * Originally from kernel/power/process.c
+ */
+
+#include <linux/interrupt.h>
+#include <linux/suspend.h>
+#include <linux/module.h>
+#include <linux/syscalls.h>
+#include <linux/freezer.h>
+
+/*
+ * freezing is complete, mark current process as frozen
+ */
+static inline void frozen_process(void)
+{
+	if (!unlikely(current->flags & PF_NOFREEZE)) {
+		current->flags |= PF_FROZEN;
+		wmb();
+	}
+	clear_freeze_flag(current);
+}
+
+/* Refrigerator is place where frozen processes are stored :-). */
+void refrigerator(void)
+{
+	/* Hmm, should we be allowed to suspend when there are realtime
+	   processes around? */
+	long save;
+
+	task_lock(current);
+	if (freezing(current)) {
+		frozen_process();
+		task_unlock(current);
+	} else {
+		task_unlock(current);
+		return;
+	}
+	save = current->state;
+	pr_debug("%s entered refrigerator\n", current->comm);
+
+	spin_lock_irq(&current->sighand->siglock);
+	recalc_sigpending(); /* We sent fake signal, clean it up */
+	spin_unlock_irq(&current->sighand->siglock);
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (!frozen(current))
+			break;
+		schedule();
+	}
+	pr_debug("%s left refrigerator\n", current->comm);
+	__set_current_state(save);
+}
+EXPORT_SYMBOL(refrigerator);
+
+static void fake_signal_wake_up(struct task_struct *p)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&p->sighand->siglock, flags);
+	signal_wake_up(p, 0);
+	spin_unlock_irqrestore(&p->sighand->siglock, flags);
+}
+
+/**
+ *	freeze_task - send a freeze request to given task
+ *	@p: task to send the request to
+ *	@sig_only: if set, the request will only be sent if the task has the
+ *		PF_FREEZER_NOSIG flag unset
+ *	Return value: 'false', if @sig_only is set and the task has
+ *		PF_FREEZER_NOSIG set or the task is frozen, 'true', otherwise
+ *
+ *	The freeze request is sent by setting the tasks's TIF_FREEZE flag and
+ *	either sending a fake signal to it or waking it up, depending on whether
+ *	or not it has PF_FREEZER_NOSIG set.  If @sig_only is set and the task
+ *	has PF_FREEZER_NOSIG set (ie. it is a typical kernel thread), its
+ *	TIF_FREEZE flag will not be set.
+ */
+bool freeze_task(struct task_struct *p, bool sig_only)
+{
+	/*
+	 * We first check if the task is freezing and next if it has already
+	 * been frozen to avoid the race with frozen_process() which first marks
+	 * the task as frozen and next clears its TIF_FREEZE.
+	 */
+	if (!freezing(p)) {
+		rmb();
+		if (frozen(p))
+			return false;
+
+		if (!sig_only || should_send_signal(p))
+			set_freeze_flag(p);
+		else
+			return false;
+	}
+
+	if (should_send_signal(p)) {
+		if (!signal_pending(p))
+			fake_signal_wake_up(p);
+	} else if (sig_only) {
+		return false;
+	} else {
+		wake_up_state(p, TASK_INTERRUPTIBLE);
+	}
+
+	return true;
+}
+
+void cancel_freezing(struct task_struct *p)
+{
+	unsigned long flags;
+
+	if (freezing(p)) {
+		pr_debug("  clean up: %s\n", p->comm);
+		clear_freeze_flag(p);
+		spin_lock_irqsave(&p->sighand->siglock, flags);
+		recalc_sigpending_and_wake(p);
+		spin_unlock_irqrestore(&p->sighand->siglock, flags);
+	}
+}
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index dcd165f92a88..ebdd7f55273d 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -85,6 +85,9 @@ config PM_SLEEP
 	depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE
 	default y
 
+config FREEZER
+	def_bool PM_SLEEP
+
 config SUSPEND
 	bool "Suspend to RAM and standby"
 	depends on PM && ARCH_SUSPEND_POSSIBLE
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 278946aecaf0..444cea80fde8 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -28,121 +28,6 @@ static inline int freezeable(struct task_struct * p)
 	return 1;
 }
 
-/*
- * freezing is complete, mark current process as frozen
- */
-static inline void frozen_process(void)
-{
-	if (!unlikely(current->flags & PF_NOFREEZE)) {
-		current->flags |= PF_FROZEN;
-		wmb();
-	}
-	clear_freeze_flag(current);
-}
-
-/* Refrigerator is place where frozen processes are stored :-). */
-void refrigerator(void)
-{
-	/* Hmm, should we be allowed to suspend when there are realtime
-	   processes around? */
-	long save;
-
-	task_lock(current);
-	if (freezing(current)) {
-		frozen_process();
-		task_unlock(current);
-	} else {
-		task_unlock(current);
-		return;
-	}
-	save = current->state;
-	pr_debug("%s entered refrigerator\n", current->comm);
-
-	spin_lock_irq(&current->sighand->siglock);
-	recalc_sigpending(); /* We sent fake signal, clean it up */
-	spin_unlock_irq(&current->sighand->siglock);
-
-	for (;;) {
-		set_current_state(TASK_UNINTERRUPTIBLE);
-		if (!frozen(current))
-			break;
-		schedule();
-	}
-	pr_debug("%s left refrigerator\n", current->comm);
-	__set_current_state(save);
-}
-
-static void fake_signal_wake_up(struct task_struct *p)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&p->sighand->siglock, flags);
-	signal_wake_up(p, 0);
-	spin_unlock_irqrestore(&p->sighand->siglock, flags);
-}
-
-static inline bool should_send_signal(struct task_struct *p)
-{
-	return !(p->flags & PF_FREEZER_NOSIG);
-}
-
-/**
- *	freeze_task - send a freeze request to given task
- *	@p: task to send the request to
- *	@sig_only: if set, the request will only be sent if the task has the
- *		PF_FREEZER_NOSIG flag unset
- *	Return value: 'false', if @sig_only is set and the task has
- *		PF_FREEZER_NOSIG set or the task is frozen, 'true', otherwise
- *
- *	The freeze request is sent by setting the tasks's TIF_FREEZE flag and
- *	either sending a fake signal to it or waking it up, depending on whether
- *	or not it has PF_FREEZER_NOSIG set.  If @sig_only is set and the task
- *	has PF_FREEZER_NOSIG set (ie. it is a typical kernel thread), its
- *	TIF_FREEZE flag will not be set.
- */
-static bool freeze_task(struct task_struct *p, bool sig_only)
-{
-	/*
-	 * We first check if the task is freezing and next if it has already
-	 * been frozen to avoid the race with frozen_process() which first marks
-	 * the task as frozen and next clears its TIF_FREEZE.
-	 */
-	if (!freezing(p)) {
-		rmb();
-		if (frozen(p))
-			return false;
-
-		if (!sig_only || should_send_signal(p))
-			set_freeze_flag(p);
-		else
-			return false;
-	}
-
-	if (should_send_signal(p)) {
-		if (!signal_pending(p))
-			fake_signal_wake_up(p);
-	} else if (sig_only) {
-		return false;
-	} else {
-		wake_up_state(p, TASK_INTERRUPTIBLE);
-	}
-
-	return true;
-}
-
-static void cancel_freezing(struct task_struct *p)
-{
-	unsigned long flags;
-
-	if (freezing(p)) {
-		pr_debug("  clean up: %s\n", p->comm);
-		clear_freeze_flag(p);
-		spin_lock_irqsave(&p->sighand->siglock, flags);
-		recalc_sigpending_and_wake(p);
-		spin_unlock_irqrestore(&p->sighand->siglock, flags);
-	}
-}
-
 static int try_to_freeze_tasks(bool sig_only)
 {
 	struct task_struct *g, *p;
@@ -264,4 +149,3 @@ void thaw_processes(void)
 	printk("done.\n");
 }
 
-EXPORT_SYMBOL(refrigerator);
-- 
cgit v1.2.3


From dc52ddc0e6f45b04780b26fc0813509f8e798c42 Mon Sep 17 00:00:00 2001
From: Matt Helsley <matthltc@us.ibm.com>
Date: Sat, 18 Oct 2008 20:27:21 -0700
Subject: container freezer: implement freezer cgroup subsystem

This patch implements a new freezer subsystem in the control groups
framework.  It provides a way to stop and resume execution of all tasks in
a cgroup by writing in the cgroup filesystem.

The freezer subsystem in the container filesystem defines a file named
freezer.state.  Writing "FROZEN" to the state file will freeze all tasks
in the cgroup.  Subsequently writing "RUNNING" will unfreeze the tasks in
the cgroup.  Reading will return the current state.

* Examples of usage :

   # mkdir /containers/freezer
   # mount -t cgroup -ofreezer freezer  /containers
   # mkdir /containers/0
   # echo $some_pid > /containers/0/tasks

to get status of the freezer subsystem :

   # cat /containers/0/freezer.state
   RUNNING

to freeze all tasks in the container :

   # echo FROZEN > /containers/0/freezer.state
   # cat /containers/0/freezer.state
   FREEZING
   # cat /containers/0/freezer.state
   FROZEN

to unfreeze all tasks in the container :

   # echo RUNNING > /containers/0/freezer.state
   # cat /containers/0/freezer.state
   RUNNING

This is the basic mechanism which should do the right thing for user space
task in a simple scenario.

It's important to note that freezing can be incomplete.  In that case we
return EBUSY.  This means that some tasks in the cgroup are busy doing
something that prevents us from completely freezing the cgroup at this
time.  After EBUSY, the cgroup will remain partially frozen -- reflected
by freezer.state reporting "FREEZING" when read.  The state will remain
"FREEZING" until one of these things happens:

	1) Userspace cancels the freezing operation by writing "RUNNING" to
		the freezer.state file
	2) Userspace retries the freezing operation by writing "FROZEN" to
		the freezer.state file (writing "FREEZING" is not legal
		and returns EIO)
	3) The tasks that blocked the cgroup from entering the "FROZEN"
		state disappear from the cgroup's set of tasks.

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: export thaw_process]
Signed-off-by: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Matt Helsley <matthltc@us.ibm.com>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Tested-by: Matt Helsley <matthltc@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/alpha/Kconfig            |   1 +
 arch/arm/Kconfig              |   2 +
 arch/avr32/Kconfig            |   2 +
 arch/blackfin/Kconfig         |   3 +
 arch/cris/Kconfig             |   2 +
 arch/frv/Kconfig              |   2 +
 arch/h8300/Kconfig            |   2 +
 arch/ia64/Kconfig             |   2 +
 arch/m32r/Kconfig             |   2 +
 arch/m68k/Kconfig             |   2 +
 arch/m68knommu/Kconfig        |   2 +
 arch/mips/Kconfig             |   2 +
 arch/mn10300/Kconfig          |   2 +
 arch/parisc/Kconfig           |   2 +
 arch/powerpc/Kconfig          |   2 +
 arch/s390/Kconfig             |   2 +
 arch/sh/Kconfig               |   2 +
 arch/sparc/Kconfig            |   2 +
 arch/sparc64/Kconfig          |   1 +
 arch/um/Kconfig               |   2 +
 arch/x86/Kconfig              |   1 +
 arch/xtensa/Kconfig           |   1 +
 include/linux/cgroup_subsys.h |   6 +
 include/linux/freezer.h       |  29 ++--
 init/Kconfig                  |   7 +
 kernel/Kconfig.freezer        |   2 +
 kernel/Makefile               |   1 +
 kernel/cgroup_freezer.c       | 366 ++++++++++++++++++++++++++++++++++++++++++
 kernel/freezer.c              |  32 ++++
 kernel/power/Kconfig          |   3 -
 30 files changed, 465 insertions(+), 22 deletions(-)
 create mode 100644 kernel/Kconfig.freezer
 create mode 100644 kernel/cgroup_freezer.c

(limited to 'include')

diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index a0f642b6a4b9..6110197757a3 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -70,6 +70,7 @@ config AUTO_IRQ_AFFINITY
 	default y
 
 source "init/Kconfig"
+source "kernel/Kconfig.freezer"
 
 
 menu "System setup"
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 4853f9df37bd..df39d20f7425 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -192,6 +192,8 @@ config VECTORS_BASE
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "System Type"
 
 choice
diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index 7c239a916275..33a5b2969eb4 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -72,6 +72,8 @@ config GENERIC_BUG
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "System Type and features"
 
 source "kernel/time/Kconfig"
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index 8102c79aaa94..29e71ed6b8a7 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -64,8 +64,11 @@ config HARDWARE_PM
 	depends on OPROFILE
 
 source "init/Kconfig"
+
 source "kernel/Kconfig.preempt"
 
+source "kernel/Kconfig.freezer"
+
 menu "Blackfin Processor Options"
 
 comment "Processor and Board Settings"
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index 9389d38f222f..07335e719bf8 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -62,6 +62,8 @@ config HZ
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "General setup"
 
 source "fs/Kconfig.binfmt"
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index a5aac1b07562..9d1552a9ee2c 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -66,6 +66,8 @@ mainmenu "Fujitsu FR-V Kernel Configuration"
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 
 menu "Fujitsu FR-V system setup"
 
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index c7966746fbfe..bd1995403c67 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -90,6 +90,8 @@ config HZ
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 source "arch/h8300/Kconfig.cpu"
 
 menu "Executable file formats"
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 3b7aa38254a8..912c57db2d21 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -7,6 +7,8 @@ mainmenu "IA-64 Linux Kernel Configuration"
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "Processor type and features"
 
 config IA64
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index 00289c178f89..dbaed4a63815 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -42,6 +42,8 @@ config HZ
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 
 menu "Processor type and features"
 
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 677c93a490f6..836fb66f080d 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -62,6 +62,8 @@ mainmenu "Linux/68k Kernel Configuration"
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "Platform dependent setup"
 
 config EISA
diff --git a/arch/m68knommu/Kconfig b/arch/m68knommu/Kconfig
index 0a8998315e5e..76b66feb74df 100644
--- a/arch/m68knommu/Kconfig
+++ b/arch/m68knommu/Kconfig
@@ -75,6 +75,8 @@ config NO_IOPORT
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "Processor type and features"
 
 choice
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index b905744d7915..5f149b030c0f 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1885,6 +1885,8 @@ config PROBE_INITRD_HEADER
 	  add initrd or initramfs image to the kernel image.
 	  Otherwise, say N.
 
+source "kernel/Kconfig.freezer"
+
 menu "Bus options (PCI, PCMCIA, EISA, ISA, TC)"
 
 config HW_HAS_EISA
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index dd557c9cf001..9a9f43358879 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -68,6 +68,8 @@ mainmenu "Matsushita MN10300/AM33 Kernel Configuration"
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 
 menu "Matsushita MN10300 system setup"
 
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 8313fccced5e..2bd1f6ef5db0 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -90,6 +90,8 @@ config ARCH_MAY_HAVE_PC_FDC
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 
 menu "Processor type and features"
 
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 380baa1780e9..9391199d9e77 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -230,6 +230,8 @@ config PPC_OF_PLATFORM_PCI
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 source "arch/powerpc/sysdev/Kconfig"
 source "arch/powerpc/platforms/Kconfig"
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index bc581d8a7cd9..70b7645ce745 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -78,6 +78,8 @@ config S390
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "Base setup"
 
 comment "Processor type and features"
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 5131d50f851a..2ed5713b7540 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -106,6 +106,8 @@ config IO_TRAPPED
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "System type"
 
 #
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 97671dac12a6..e594559c8dba 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -37,6 +37,8 @@ config HZ
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 menu "General machine setup"
 
 config SMP
diff --git a/arch/sparc64/Kconfig b/arch/sparc64/Kconfig
index 5446e2a499b1..035b15af90d8 100644
--- a/arch/sparc64/Kconfig
+++ b/arch/sparc64/Kconfig
@@ -96,6 +96,7 @@ config GENERIC_HARDIRQS_NO__DO_IRQ
 	def_bool y
 
 source "init/Kconfig"
+source "kernel/Kconfig.freezer"
 
 menu "Processor type and features"
 
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 6976812cfb18..393bccfe1785 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -229,6 +229,8 @@ endmenu
 
 source "init/Kconfig"
 
+source "kernel/Kconfig.freezer"
+
 source "drivers/block/Kconfig"
 
 source "arch/um/Kconfig.char"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index bd3c2c53873e..49349ba77d80 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -193,6 +193,7 @@ config X86_TRAMPOLINE
 config KTIME_SCALAR
 	def_bool X86_32
 source "init/Kconfig"
+source "kernel/Kconfig.freezer"
 
 menu "Processor type and features"
 
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 02e417d3d8e9..a213260b51e5 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -55,6 +55,7 @@ config HZ
 	default 100
 
 source "init/Kconfig"
+source "kernel/Kconfig.freezer"
 
 menu "Processor type and features"
 
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index e2877454ec82..9c22396e8b50 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -48,3 +48,9 @@ SUBSYS(devices)
 #endif
 
 /* */
+
+#ifdef CONFIG_CGROUP_FREEZER
+SUBSYS(freezer)
+#endif
+
+/* */
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index 17e3bb42dd3c..8f225339eee9 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -46,26 +46,11 @@ static inline bool should_send_signal(struct task_struct *p)
 
 /*
  * Wake up a frozen process
- *
- * task_lock() is taken to prevent the race with refrigerator() which may
- * occur if the freezing of tasks fails.  Namely, without the lock, if the
- * freezing of tasks failed, thaw_tasks() might have run before a task in
- * refrigerator() could call frozen_process(), in which case the task would be
- * frozen and no one would thaw it.
  */
-static inline int thaw_process(struct task_struct *p)
-{
-	task_lock(p);
-	if (frozen(p)) {
-		p->flags &= ~PF_FROZEN;
-		task_unlock(p);
-		wake_up_process(p);
-		return 1;
-	}
-	clear_freeze_flag(p);
-	task_unlock(p);
-	return 0;
-}
+extern int __thaw_process(struct task_struct *p);
+
+/* Takes and releases task alloc lock using task_lock() */
+extern int thaw_process(struct task_struct *p);
 
 extern void refrigerator(void);
 extern int freeze_processes(void);
@@ -83,6 +68,12 @@ static inline int try_to_freeze(void)
 extern bool freeze_task(struct task_struct *p, bool sig_only);
 extern void cancel_freezing(struct task_struct *p);
 
+#ifdef CONFIG_CGROUP_FREEZER
+extern int cgroup_frozen(struct task_struct *task);
+#else /* !CONFIG_CGROUP_FREEZER */
+static inline int cgroup_frozen(struct task_struct *task) { return 0; }
+#endif /* !CONFIG_CGROUP_FREEZER */
+
 /*
  * The PF_FREEZER_SKIP flag should be set by a vfork parent right before it
  * calls wait_for_completion(&vfork) and reset right after it returns from this
diff --git a/init/Kconfig b/init/Kconfig
index 5ceff3249a2d..8828ed0b2051 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -299,6 +299,13 @@ config CGROUP_NS
           for instance virtual servers and checkpoint/restart
           jobs.
 
+config CGROUP_FREEZER
+        bool "control group freezer subsystem"
+        depends on CGROUPS
+        help
+          Provides a way to freeze and unfreeze all tasks in a
+	  cgroup.
+
 config CGROUP_DEVICE
 	bool "Device controller for cgroups"
 	depends on CGROUPS && EXPERIMENTAL
diff --git a/kernel/Kconfig.freezer b/kernel/Kconfig.freezer
new file mode 100644
index 000000000000..a3bb4cb52539
--- /dev/null
+++ b/kernel/Kconfig.freezer
@@ -0,0 +1,2 @@
+config FREEZER
+	def_bool PM_SLEEP || CGROUP_FREEZER
diff --git a/kernel/Makefile b/kernel/Makefile
index e8194d15d5f4..066550aa61c5 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_BACKTRACE_SELF_TEST) += backtracetest.o
 obj-$(CONFIG_COMPAT) += compat.o
 obj-$(CONFIG_CGROUPS) += cgroup.o
 obj-$(CONFIG_CGROUP_DEBUG) += cgroup_debug.o
+obj-$(CONFIG_CGROUP_FREEZER) += cgroup_freezer.o
 obj-$(CONFIG_CPUSETS) += cpuset.o
 obj-$(CONFIG_CGROUP_NS) += ns_cgroup.o
 obj-$(CONFIG_UTS_NS) += utsname.o
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
new file mode 100644
index 000000000000..b08722de610c
--- /dev/null
+++ b/kernel/cgroup_freezer.c
@@ -0,0 +1,366 @@
+/*
+ * cgroup_freezer.c -  control group freezer subsystem
+ *
+ * Copyright IBM Corporation, 2007
+ *
+ * Author : Cedric Le Goater <clg@fr.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2.1 of the GNU Lesser General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+#include <linux/module.h>
+#include <linux/cgroup.h>
+#include <linux/fs.h>
+#include <linux/uaccess.h>
+#include <linux/freezer.h>
+#include <linux/seq_file.h>
+
+enum freezer_state {
+	STATE_RUNNING = 0,
+	STATE_FREEZING,
+	STATE_FROZEN,
+};
+
+struct freezer {
+	struct cgroup_subsys_state css;
+	enum freezer_state state;
+	spinlock_t lock; /* protects _writes_ to state */
+};
+
+static inline struct freezer *cgroup_freezer(
+		struct cgroup *cgroup)
+{
+	return container_of(
+		cgroup_subsys_state(cgroup, freezer_subsys_id),
+		struct freezer, css);
+}
+
+static inline struct freezer *task_freezer(struct task_struct *task)
+{
+	return container_of(task_subsys_state(task, freezer_subsys_id),
+			    struct freezer, css);
+}
+
+int cgroup_frozen(struct task_struct *task)
+{
+	struct freezer *freezer;
+	enum freezer_state state;
+
+	task_lock(task);
+	freezer = task_freezer(task);
+	state = freezer->state;
+	task_unlock(task);
+
+	return state == STATE_FROZEN;
+}
+
+/*
+ * cgroups_write_string() limits the size of freezer state strings to
+ * CGROUP_LOCAL_BUFFER_SIZE
+ */
+static const char *freezer_state_strs[] = {
+	"RUNNING",
+	"FREEZING",
+	"FROZEN",
+};
+
+/*
+ * State diagram
+ * Transitions are caused by userspace writes to the freezer.state file.
+ * The values in parenthesis are state labels. The rest are edge labels.
+ *
+ * (RUNNING) --FROZEN--> (FREEZING) --FROZEN--> (FROZEN)
+ *    ^ ^                     |                       |
+ *    | \_______RUNNING_______/                       |
+ *    \_____________________________RUNNING___________/
+ */
+
+struct cgroup_subsys freezer_subsys;
+
+/* Locks taken and their ordering
+ * ------------------------------
+ * css_set_lock
+ * cgroup_mutex (AKA cgroup_lock)
+ * task->alloc_lock (AKA task_lock)
+ * freezer->lock
+ * task->sighand->siglock
+ *
+ * cgroup code forces css_set_lock to be taken before task->alloc_lock
+ *
+ * freezer_create(), freezer_destroy():
+ * cgroup_mutex [ by cgroup core ]
+ *
+ * can_attach():
+ * cgroup_mutex
+ *
+ * cgroup_frozen():
+ * task->alloc_lock (to get task's cgroup)
+ *
+ * freezer_fork() (preserving fork() performance means can't take cgroup_mutex):
+ * task->alloc_lock (to get task's cgroup)
+ * freezer->lock
+ *  sighand->siglock (if the cgroup is freezing)
+ *
+ * freezer_read():
+ * cgroup_mutex
+ *  freezer->lock
+ *   read_lock css_set_lock (cgroup iterator start)
+ *
+ * freezer_write() (freeze):
+ * cgroup_mutex
+ *  freezer->lock
+ *   read_lock css_set_lock (cgroup iterator start)
+ *    sighand->siglock
+ *
+ * freezer_write() (unfreeze):
+ * cgroup_mutex
+ *  freezer->lock
+ *   read_lock css_set_lock (cgroup iterator start)
+ *    task->alloc_lock (to prevent races with freeze_task())
+ *     sighand->siglock
+ */
+static struct cgroup_subsys_state *freezer_create(struct cgroup_subsys *ss,
+						  struct cgroup *cgroup)
+{
+	struct freezer *freezer;
+
+	freezer = kzalloc(sizeof(struct freezer), GFP_KERNEL);
+	if (!freezer)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&freezer->lock);
+	freezer->state = STATE_RUNNING;
+	return &freezer->css;
+}
+
+static void freezer_destroy(struct cgroup_subsys *ss,
+			    struct cgroup *cgroup)
+{
+	kfree(cgroup_freezer(cgroup));
+}
+
+
+static int freezer_can_attach(struct cgroup_subsys *ss,
+			      struct cgroup *new_cgroup,
+			      struct task_struct *task)
+{
+	struct freezer *freezer;
+	int retval = 0;
+
+	/*
+	 * The call to cgroup_lock() in the freezer.state write method prevents
+	 * a write to that file racing against an attach, and hence the
+	 * can_attach() result will remain valid until the attach completes.
+	 */
+	freezer = cgroup_freezer(new_cgroup);
+	if (freezer->state == STATE_FROZEN)
+		retval = -EBUSY;
+	return retval;
+}
+
+static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
+{
+	struct freezer *freezer;
+
+	task_lock(task);
+	freezer = task_freezer(task);
+	task_unlock(task);
+
+	BUG_ON(freezer->state == STATE_FROZEN);
+	spin_lock_irq(&freezer->lock);
+	/* Locking avoids race with FREEZING -> RUNNING transitions. */
+	if (freezer->state == STATE_FREEZING)
+		freeze_task(task, true);
+	spin_unlock_irq(&freezer->lock);
+}
+
+/*
+ * caller must hold freezer->lock
+ */
+static void check_if_frozen(struct cgroup *cgroup,
+			     struct freezer *freezer)
+{
+	struct cgroup_iter it;
+	struct task_struct *task;
+	unsigned int nfrozen = 0, ntotal = 0;
+
+	cgroup_iter_start(cgroup, &it);
+	while ((task = cgroup_iter_next(cgroup, &it))) {
+		ntotal++;
+		/*
+		 * Task is frozen or will freeze immediately when next it gets
+		 * woken
+		 */
+		if (frozen(task) ||
+		    (task_is_stopped_or_traced(task) && freezing(task)))
+			nfrozen++;
+	}
+
+	/*
+	 * Transition to FROZEN when no new tasks can be added ensures
+	 * that we never exist in the FROZEN state while there are unfrozen
+	 * tasks.
+	 */
+	if (nfrozen == ntotal)
+		freezer->state = STATE_FROZEN;
+	cgroup_iter_end(cgroup, &it);
+}
+
+static int freezer_read(struct cgroup *cgroup, struct cftype *cft,
+			struct seq_file *m)
+{
+	struct freezer *freezer;
+	enum freezer_state state;
+
+	if (!cgroup_lock_live_group(cgroup))
+		return -ENODEV;
+
+	freezer = cgroup_freezer(cgroup);
+	spin_lock_irq(&freezer->lock);
+	state = freezer->state;
+	if (state == STATE_FREEZING) {
+		/* We change from FREEZING to FROZEN lazily if the cgroup was
+		 * only partially frozen when we exitted write. */
+		check_if_frozen(cgroup, freezer);
+		state = freezer->state;
+	}
+	spin_unlock_irq(&freezer->lock);
+	cgroup_unlock();
+
+	seq_puts(m, freezer_state_strs[state]);
+	seq_putc(m, '\n');
+	return 0;
+}
+
+static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
+{
+	struct cgroup_iter it;
+	struct task_struct *task;
+	unsigned int num_cant_freeze_now = 0;
+
+	freezer->state = STATE_FREEZING;
+	cgroup_iter_start(cgroup, &it);
+	while ((task = cgroup_iter_next(cgroup, &it))) {
+		if (!freeze_task(task, true))
+			continue;
+		if (task_is_stopped_or_traced(task) && freezing(task))
+			/*
+			 * The freeze flag is set so these tasks will
+			 * immediately go into the fridge upon waking.
+			 */
+			continue;
+		if (!freezing(task) && !freezer_should_skip(task))
+			num_cant_freeze_now++;
+	}
+	cgroup_iter_end(cgroup, &it);
+
+	return num_cant_freeze_now ? -EBUSY : 0;
+}
+
+static int unfreeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
+{
+	struct cgroup_iter it;
+	struct task_struct *task;
+
+	cgroup_iter_start(cgroup, &it);
+	while ((task = cgroup_iter_next(cgroup, &it))) {
+		int do_wake;
+
+		task_lock(task);
+		do_wake = __thaw_process(task);
+		task_unlock(task);
+		if (do_wake)
+			wake_up_process(task);
+	}
+	cgroup_iter_end(cgroup, &it);
+	freezer->state = STATE_RUNNING;
+
+	return 0;
+}
+
+static int freezer_change_state(struct cgroup *cgroup,
+				enum freezer_state goal_state)
+{
+	struct freezer *freezer;
+	int retval = 0;
+
+	freezer = cgroup_freezer(cgroup);
+	spin_lock_irq(&freezer->lock);
+	check_if_frozen(cgroup, freezer); /* may update freezer->state */
+	if (goal_state == freezer->state)
+		goto out;
+	switch (freezer->state) {
+	case STATE_RUNNING:
+		retval = try_to_freeze_cgroup(cgroup, freezer);
+		break;
+	case STATE_FREEZING:
+		if (goal_state == STATE_FROZEN) {
+			/* Userspace is retrying after
+			 * "/bin/echo FROZEN > freezer.state" returned -EBUSY */
+			retval = try_to_freeze_cgroup(cgroup, freezer);
+			break;
+		}
+		/* state == FREEZING and goal_state == RUNNING, so unfreeze */
+	case STATE_FROZEN:
+		retval = unfreeze_cgroup(cgroup, freezer);
+		break;
+	default:
+		break;
+	}
+out:
+	spin_unlock_irq(&freezer->lock);
+
+	return retval;
+}
+
+static int freezer_write(struct cgroup *cgroup,
+			 struct cftype *cft,
+			 const char *buffer)
+{
+	int retval;
+	enum freezer_state goal_state;
+
+	if (strcmp(buffer, freezer_state_strs[STATE_RUNNING]) == 0)
+		goal_state = STATE_RUNNING;
+	else if (strcmp(buffer, freezer_state_strs[STATE_FROZEN]) == 0)
+		goal_state = STATE_FROZEN;
+	else
+		return -EIO;
+
+	if (!cgroup_lock_live_group(cgroup))
+		return -ENODEV;
+	retval = freezer_change_state(cgroup, goal_state);
+	cgroup_unlock();
+	return retval;
+}
+
+static struct cftype files[] = {
+	{
+		.name = "state",
+		.read_seq_string = freezer_read,
+		.write_string = freezer_write,
+	},
+};
+
+static int freezer_populate(struct cgroup_subsys *ss, struct cgroup *cgroup)
+{
+	return cgroup_add_files(cgroup, ss, files, ARRAY_SIZE(files));
+}
+
+struct cgroup_subsys freezer_subsys = {
+	.name		= "freezer",
+	.create		= freezer_create,
+	.destroy	= freezer_destroy,
+	.populate	= freezer_populate,
+	.subsys_id	= freezer_subsys_id,
+	.can_attach	= freezer_can_attach,
+	.attach		= NULL,
+	.fork		= freezer_fork,
+	.exit		= NULL,
+};
diff --git a/kernel/freezer.c b/kernel/freezer.c
index cb0931f89306..ba6248b323ef 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -120,3 +120,35 @@ void cancel_freezing(struct task_struct *p)
 		spin_unlock_irqrestore(&p->sighand->siglock, flags);
 	}
 }
+
+/*
+ * Wake up a frozen process
+ *
+ * task_lock() is needed to prevent the race with refrigerator() which may
+ * occur if the freezing of tasks fails.  Namely, without the lock, if the
+ * freezing of tasks failed, thaw_tasks() might have run before a task in
+ * refrigerator() could call frozen_process(), in which case the task would be
+ * frozen and no one would thaw it.
+ */
+int __thaw_process(struct task_struct *p)
+{
+	if (frozen(p)) {
+		p->flags &= ~PF_FROZEN;
+		return 1;
+	}
+	clear_freeze_flag(p);
+	return 0;
+}
+
+int thaw_process(struct task_struct *p)
+{
+	task_lock(p);
+	if (__thaw_process(p) == 1) {
+		task_unlock(p);
+		wake_up_process(p);
+		return 1;
+	}
+	task_unlock(p);
+	return 0;
+}
+EXPORT_SYMBOL(thaw_process);
diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig
index ebdd7f55273d..dcd165f92a88 100644
--- a/kernel/power/Kconfig
+++ b/kernel/power/Kconfig
@@ -85,9 +85,6 @@ config PM_SLEEP
 	depends on SUSPEND || HIBERNATION || XEN_SAVE_RESTORE
 	default y
 
-config FREEZER
-	def_bool PM_SLEEP
-
 config SUSPEND
 	bool "Suspend to RAM and standby"
 	depends on PM && ARCH_SUSPEND_POSSIBLE
-- 
cgit v1.2.3


From 3e680aae4e53ab54cdbb0c29257dae0cbb158e1c Mon Sep 17 00:00:00 2001
From: Krzysztof Helt <krzysztof.h1@wp.pl>
Date: Sat, 18 Oct 2008 20:27:51 -0700
Subject: fb: convert lock/unlock_kernel() into local fb mutex

Change lock_kernel()/unlock_kernel() to local fb mutex.  Each frame buffer
instance has its own mutex.

The one line try_to_load() function is unrolled to request_module() in two
places for readability.

[righi.andrea@gmail.com: fb: fix NULL pointer BUG dereference in fb_open()]
Signed-off-by: Krzysztof Helt <krzysztof.h1@wp.pl>
Signed-off-by: Andrea Righi <righi.andrea@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/video/fbmem.c | 39 ++++++++++++++++++++-------------------
 include/linux/fb.h    |  1 +
 2 files changed, 21 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/drivers/video/fbmem.c b/drivers/video/fbmem.c
index 2a0f013dc37b..cd5f20da738a 100644
--- a/drivers/video/fbmem.c
+++ b/drivers/video/fbmem.c
@@ -1018,12 +1018,12 @@ fb_ioctl(struct file *file, unsigned int cmd,
 	void __user *argp = (void __user *)arg;
 	long ret = 0;
 
-	lock_kernel();
 	info = registered_fb[fbidx];
+	mutex_lock(&info->lock);
 	fb = info->fbops;
 
 	if (!fb) {
-		unlock_kernel();
+		mutex_unlock(&info->lock);
 		return -ENODEV;
 	}
 	switch (cmd) {
@@ -1126,7 +1126,7 @@ fb_ioctl(struct file *file, unsigned int cmd,
 		else
 			ret = fb->fb_ioctl(info, cmd, arg);
 	}
-	unlock_kernel();
+	mutex_unlock(&info->lock);
 	return ret;
 }
 
@@ -1253,7 +1253,7 @@ fb_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	struct fb_ops *fb = info->fbops;
 	long ret = -ENOIOCTLCMD;
 
-	lock_kernel();
+	mutex_lock(&info->lock);
 	switch(cmd) {
 	case FBIOGET_VSCREENINFO:
 	case FBIOPUT_VSCREENINFO:
@@ -1279,7 +1279,7 @@ fb_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			ret = fb->fb_compat_ioctl(info, cmd, arg);
 		break;
 	}
-	unlock_kernel();
+	mutex_unlock(&info->lock);
 	return ret;
 }
 #endif
@@ -1301,13 +1301,13 @@ fb_mmap(struct file *file, struct vm_area_struct * vma)
 		return -ENODEV;
 	if (fb->fb_mmap) {
 		int res;
-		lock_kernel();
+		mutex_lock(&info->lock);
 		res = fb->fb_mmap(info, vma);
-		unlock_kernel();
+		mutex_unlock(&info->lock);
 		return res;
 	}
 
-	lock_kernel();
+	mutex_lock(&info->lock);
 
 	/* frame buffer memory */
 	start = info->fix.smem_start;
@@ -1316,13 +1316,13 @@ fb_mmap(struct file *file, struct vm_area_struct * vma)
 		/* memory mapped io */
 		off -= len;
 		if (info->var.accel_flags) {
-			unlock_kernel();
+			mutex_unlock(&info->lock);
 			return -EINVAL;
 		}
 		start = info->fix.mmio_start;
 		len = PAGE_ALIGN((start & ~PAGE_MASK) + info->fix.mmio_len);
 	}
-	unlock_kernel();
+	mutex_unlock(&info->lock);
 	start &= PAGE_MASK;
 	if ((vma->vm_end - vma->vm_start + off) > len)
 		return -EINVAL;
@@ -1346,13 +1346,13 @@ fb_open(struct inode *inode, struct file *file)
 
 	if (fbidx >= FB_MAX)
 		return -ENODEV;
-	lock_kernel();
-	if (!(info = registered_fb[fbidx]))
+	info = registered_fb[fbidx];
+	if (!info)
 		request_module("fb%d", fbidx);
-	if (!(info = registered_fb[fbidx])) {
-		res = -ENODEV;
-		goto out;
-	}
+	info = registered_fb[fbidx];
+	if (!info)
+		return -ENODEV;
+	mutex_lock(&info->lock);
 	if (!try_module_get(info->fbops->owner)) {
 		res = -ENODEV;
 		goto out;
@@ -1368,7 +1368,7 @@ fb_open(struct inode *inode, struct file *file)
 		fb_deferred_io_open(info, inode, file);
 #endif
 out:
-	unlock_kernel();
+	mutex_unlock(&info->lock);
 	return res;
 }
 
@@ -1377,11 +1377,11 @@ fb_release(struct inode *inode, struct file *file)
 {
 	struct fb_info * const info = file->private_data;
 
-	lock_kernel();
+	mutex_lock(&info->lock);
 	if (info->fbops->fb_release)
 		info->fbops->fb_release(info,1);
 	module_put(info->fbops->owner);
-	unlock_kernel();
+	mutex_unlock(&info->lock);
 	return 0;
 }
 
@@ -1460,6 +1460,7 @@ register_framebuffer(struct fb_info *fb_info)
 		if (!registered_fb[i])
 			break;
 	fb_info->node = i;
+	mutex_init(&fb_info->lock);
 
 	fb_info->dev = device_create(fb_class, fb_info->device,
 				     MKDEV(FB_MAJOR, i), NULL, "fb%d", i);
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 531ccd5f5960..75a81eaf3430 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -808,6 +808,7 @@ struct fb_tile_ops {
 struct fb_info {
 	int node;
 	int flags;
+	struct mutex lock;		/* Lock for open/release/ioctl funcs */
 	struct fb_var_screeninfo var;	/* Current var */
 	struct fb_fix_screeninfo fix;	/* Current fix */
 	struct fb_monspecs monspecs;	/* Current Monitor specs */
-- 
cgit v1.2.3


From 0e4fb5e283870757024294bc4567a7c59d936f0b Mon Sep 17 00:00:00 2001
From: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Date: Sat, 18 Oct 2008 20:27:57 -0700
Subject: ext3: add an option to control error handling on file data

If the journal doesn't abort when it gets an IO error in file data blocks,
the file data corruption will spread silently.  Because most of
applications and commands do buffered writes without fsync(), they don't
notice the IO error.  It's scary for mission critical systems.  On the
other hand, if the journal aborts whenever it gets an IO error in file
data blocks, the system will easily become inoperable.  So this patch
introduces a filesystem option to determine whether it aborts the journal
or just call printk() when it gets an IO error in file data.

If you mount a ext3 fs with data_err=abort option, it aborts on file data
write error.  If you mount it with data_err=ignore, it doesn't abort, just
call printk().  data_err=ignore is the default.

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: Jan Kara <jack@ucw.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 Documentation/filesystems/ext3.txt |  5 +++++
 fs/ext3/super.c                    | 16 ++++++++++++++++
 fs/jbd/commit.c                    |  2 ++
 include/linux/ext3_fs.h            |  2 ++
 include/linux/jbd.h                |  3 +++
 5 files changed, 28 insertions(+)

(limited to 'include')

diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index 295f26cd895a..9dd2a3bb2acc 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -96,6 +96,11 @@ errors=remount-ro(*)	Remount the filesystem read-only on an error.
 errors=continue		Keep going on a filesystem error.
 errors=panic		Panic and halt the machine if an error occurs.
 
+data_err=ignore(*)	Just print an error message if an error occurs
+			in a file data buffer in ordered mode.
+data_err=abort		Abort the journal if an error occurs in a file
+			data buffer in ordered mode.
+
 grpid			Give objects the same group ID as their creator.
 bsdgroups
 
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 399a96a6c556..3a260af5544d 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -625,6 +625,9 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
 		seq_puts(seq, ",data=writeback");
 
+	if (test_opt(sb, DATA_ERR_ABORT))
+		seq_puts(seq, ",data_err=abort");
+
 	ext3_show_quota_options(seq, sb);
 
 	return 0;
@@ -754,6 +757,7 @@ enum {
 	Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
 	Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
 	Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
+	Opt_data_err_abort, Opt_data_err_ignore,
 	Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
 	Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
 	Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
@@ -796,6 +800,8 @@ static const match_table_t tokens = {
 	{Opt_data_journal, "data=journal"},
 	{Opt_data_ordered, "data=ordered"},
 	{Opt_data_writeback, "data=writeback"},
+	{Opt_data_err_abort, "data_err=abort"},
+	{Opt_data_err_ignore, "data_err=ignore"},
 	{Opt_offusrjquota, "usrjquota="},
 	{Opt_usrjquota, "usrjquota=%s"},
 	{Opt_offgrpjquota, "grpjquota="},
@@ -1011,6 +1017,12 @@ static int parse_options (char *options, struct super_block *sb,
 				sbi->s_mount_opt |= data_opt;
 			}
 			break;
+		case Opt_data_err_abort:
+			set_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+			break;
+		case Opt_data_err_ignore:
+			clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+			break;
 #ifdef CONFIG_QUOTA
 		case Opt_usrjquota:
 			qtype = USRQUOTA;
@@ -1986,6 +1998,10 @@ static void ext3_init_journal_params(struct super_block *sb, journal_t *journal)
 		journal->j_flags |= JFS_BARRIER;
 	else
 		journal->j_flags &= ~JFS_BARRIER;
+	if (test_opt(sb, DATA_ERR_ABORT))
+		journal->j_flags |= JFS_ABORT_ON_SYNCDATA_ERR;
+	else
+		journal->j_flags &= ~JFS_ABORT_ON_SYNCDATA_ERR;
 	spin_unlock(&journal->j_state_lock);
 }
 
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index d6a6659f3e46..25719d902c51 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -482,6 +482,8 @@ void journal_commit_transaction(journal_t *journal)
 		printk(KERN_WARNING
 			"JBD: Detected IO errors while flushing file data "
 			"on %s\n", bdevname(journal->j_fs_dev, b));
+		if (journal->j_flags & JFS_ABORT_ON_SYNCDATA_ERR)
+			journal_abort(journal, err);
 		err = 0;
 	}
 
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 159d9b476cd7..d14f02918483 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -380,6 +380,8 @@ struct ext3_inode {
 #define EXT3_MOUNT_QUOTA		0x80000 /* Some quota option set */
 #define EXT3_MOUNT_USRQUOTA		0x100000 /* "old" user quota */
 #define EXT3_MOUNT_GRPQUOTA		0x200000 /* "old" group quota */
+#define EXT3_MOUNT_DATA_ERR_ABORT	0x400000 /* Abort on file data write
+						  * error in ordered mode */
 
 /* Compatibility, for having both ext2_fs.h and ext3_fs.h included at once */
 #ifndef _LINUX_EXT2_FS_H
diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index 7ebbcb1c9ba4..35d4f6342fac 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -816,6 +816,9 @@ struct journal_s
 #define JFS_FLUSHED	0x008	/* The journal superblock has been flushed */
 #define JFS_LOADED	0x010	/* The journal superblock has been loaded */
 #define JFS_BARRIER	0x020	/* Use IDE barriers */
+#define JFS_ABORT_ON_SYNCDATA_ERR	0x040  /* Abort the journal on file
+						* data write error in ordered
+						* mode */
 
 /*
  * Function declarations for the journaling transaction and buffer
-- 
cgit v1.2.3


From 146aa1bd0511f88ddb4e92fafa2b8aad4f2f65f3 Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Sat, 18 Oct 2008 20:28:03 -0700
Subject: cgroups: fix probable race with put_css_set[_taskexit] and
 find_css_set

put_css_set_taskexit may be called when find_css_set is called on other
cpu.  And the race will occur:

put_css_set_taskexit side                    find_css_set side

                                        |
atomic_dec_and_test(&kref->refcount)    |
    /* kref->refcount = 0 */            |
....................................................................
                                        |  read_lock(&css_set_lock)
                                        |  find_existing_css_set
                                        |  get_css_set
                                        |  read_unlock(&css_set_lock);
....................................................................
__release_css_set                       |
....................................................................
                                        | /* use a released css_set */
                                        |

[put_css_set is the same. But in the current code, all put_css_set are
put into cgroup mutex critical region as the same as find_css_set.]

[akpm@linux-foundation.org: repair comments]
[menage@google.com: eliminate race in css_set refcounting]
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Paul Menage <menage@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cgroup.h |  3 +--
 kernel/cgroup.c        | 43 ++++++++++++++++++++-----------------------
 kernel/cgroup_debug.c  |  4 ++--
 3 files changed, 23 insertions(+), 27 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 30934e4bfaab..7166023e07d2 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -9,7 +9,6 @@
  */
 
 #include <linux/sched.h>
-#include <linux/kref.h>
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/rcupdate.h>
@@ -149,7 +148,7 @@ struct cgroup {
 struct css_set {
 
 	/* Reference count */
-	struct kref ref;
+	atomic_t refcount;
 
 	/*
 	 * List running through all cgroup groups in the same hash
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 8c6e1c17e6d3..1e49218457e0 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -241,7 +241,6 @@ static void unlink_css_set(struct css_set *cg)
 	struct cg_cgroup_link *link;
 	struct cg_cgroup_link *saved_link;
 
-	write_lock(&css_set_lock);
 	hlist_del(&cg->hlist);
 	css_set_count--;
 
@@ -251,16 +250,25 @@ static void unlink_css_set(struct css_set *cg)
 		list_del(&link->cgrp_link_list);
 		kfree(link);
 	}
-
-	write_unlock(&css_set_lock);
 }
 
-static void __release_css_set(struct kref *k, int taskexit)
+static void __put_css_set(struct css_set *cg, int taskexit)
 {
 	int i;
-	struct css_set *cg = container_of(k, struct css_set, ref);
-
+	/*
+	 * Ensure that the refcount doesn't hit zero while any readers
+	 * can see it. Similar to atomic_dec_and_lock(), but for an
+	 * rwlock
+	 */
+	if (atomic_add_unless(&cg->refcount, -1, 1))
+		return;
+	write_lock(&css_set_lock);
+	if (!atomic_dec_and_test(&cg->refcount)) {
+		write_unlock(&css_set_lock);
+		return;
+	}
 	unlink_css_set(cg);
+	write_unlock(&css_set_lock);
 
 	rcu_read_lock();
 	for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
@@ -276,32 +284,22 @@ static void __release_css_set(struct kref *k, int taskexit)
 	kfree(cg);
 }
 
-static void release_css_set(struct kref *k)
-{
-	__release_css_set(k, 0);
-}
-
-static void release_css_set_taskexit(struct kref *k)
-{
-	__release_css_set(k, 1);
-}
-
 /*
  * refcounted get/put for css_set objects
  */
 static inline void get_css_set(struct css_set *cg)
 {
-	kref_get(&cg->ref);
+	atomic_inc(&cg->refcount);
 }
 
 static inline void put_css_set(struct css_set *cg)
 {
-	kref_put(&cg->ref, release_css_set);
+	__put_css_set(cg, 0);
 }
 
 static inline void put_css_set_taskexit(struct css_set *cg)
 {
-	kref_put(&cg->ref, release_css_set_taskexit);
+	__put_css_set(cg, 1);
 }
 
 /*
@@ -427,7 +425,7 @@ static struct css_set *find_css_set(
 		return NULL;
 	}
 
-	kref_init(&res->ref);
+	atomic_set(&res->refcount, 1);
 	INIT_LIST_HEAD(&res->cg_links);
 	INIT_LIST_HEAD(&res->tasks);
 	INIT_HLIST_NODE(&res->hlist);
@@ -1728,7 +1726,7 @@ int cgroup_task_count(const struct cgroup *cgrp)
 
 	read_lock(&css_set_lock);
 	list_for_each_entry(link, &cgrp->css_sets, cgrp_link_list) {
-		count += atomic_read(&link->cg->ref.refcount);
+		count += atomic_read(&link->cg->refcount);
 	}
 	read_unlock(&css_set_lock);
 	return count;
@@ -2495,8 +2493,7 @@ static void __init cgroup_init_subsys(struct cgroup_subsys *ss)
 int __init cgroup_init_early(void)
 {
 	int i;
-	kref_init(&init_css_set.ref);
-	kref_get(&init_css_set.ref);
+	atomic_set(&init_css_set.refcount, 1);
 	INIT_LIST_HEAD(&init_css_set.cg_links);
 	INIT_LIST_HEAD(&init_css_set.tasks);
 	INIT_HLIST_NODE(&init_css_set.hlist);
diff --git a/kernel/cgroup_debug.c b/kernel/cgroup_debug.c
index c3dc3aba4c02..daca6209202d 100644
--- a/kernel/cgroup_debug.c
+++ b/kernel/cgroup_debug.c
@@ -57,7 +57,7 @@ static u64 current_css_set_refcount_read(struct cgroup *cont,
 	u64 count;
 
 	rcu_read_lock();
-	count = atomic_read(&current->cgroups->ref.refcount);
+	count = atomic_read(&current->cgroups->refcount);
 	rcu_read_unlock();
 	return count;
 }
@@ -90,7 +90,7 @@ static struct cftype files[] =  {
 	{
 		.name = "releasable",
 		.read_u64 = releasable_read,
-	}
+	},
 };
 
 static int debug_populate(struct cgroup_subsys *ss, struct cgroup *cont)
-- 
cgit v1.2.3


From cc31edceee04a7b87f2be48f9489ebb72d264844 Mon Sep 17 00:00:00 2001
From: Paul Menage <menage@google.com>
Date: Sat, 18 Oct 2008 20:28:04 -0700
Subject: cgroups: convert tasks file to use a seq_file with shared pid array

Rather than pre-generating the entire text for the "tasks" file each
time the file is opened, we instead just generate/update the array of
process ids and use a seq_file to report these to userspace.  All open
file handles on the same "tasks" file can share a pid array, which may
be updated any time that no thread is actively reading the array.  By
sharing the array, the potential for userspace to DoS the system by
opening many handles on the same "tasks" file is removed.

[Based on a patch by Lai Jiangshan, extended to use seq_file]

Signed-off-by: Paul Menage <menage@google.com>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cgroup.h |  10 +++
 kernel/cgroup.c        | 222 +++++++++++++++++++++++++++++++------------------
 2 files changed, 149 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 7166023e07d2..8ab91880a0ad 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -14,6 +14,7 @@
 #include <linux/rcupdate.h>
 #include <linux/cgroupstats.h>
 #include <linux/prio_heap.h>
+#include <linux/rwsem.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -136,6 +137,15 @@ struct cgroup {
 	 * release_list_lock
 	 */
 	struct list_head release_list;
+
+	/* pids_mutex protects the fields below */
+	struct rw_semaphore pids_mutex;
+	/* Array of process ids in the cgroup */
+	pid_t *tasks_pids;
+	/* How many files are using the current tasks_pids array */
+	int pids_use_count;
+	/* Length of the current tasks_pids array */
+	int pids_length;
 };
 
 /* A css_set is a structure holding pointers to a set of
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 1e49218457e0..046c1609606b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -868,6 +868,14 @@ static struct super_operations cgroup_ops = {
 	.remount_fs = cgroup_remount,
 };
 
+static void init_cgroup_housekeeping(struct cgroup *cgrp)
+{
+	INIT_LIST_HEAD(&cgrp->sibling);
+	INIT_LIST_HEAD(&cgrp->children);
+	INIT_LIST_HEAD(&cgrp->css_sets);
+	INIT_LIST_HEAD(&cgrp->release_list);
+	init_rwsem(&cgrp->pids_mutex);
+}
 static void init_cgroup_root(struct cgroupfs_root *root)
 {
 	struct cgroup *cgrp = &root->top_cgroup;
@@ -876,10 +884,7 @@ static void init_cgroup_root(struct cgroupfs_root *root)
 	root->number_of_cgroups = 1;
 	cgrp->root = root;
 	cgrp->top_cgroup = cgrp;
-	INIT_LIST_HEAD(&cgrp->sibling);
-	INIT_LIST_HEAD(&cgrp->children);
-	INIT_LIST_HEAD(&cgrp->css_sets);
-	INIT_LIST_HEAD(&cgrp->release_list);
+	init_cgroup_housekeeping(cgrp);
 }
 
 static int cgroup_test_super(struct super_block *sb, void *data)
@@ -1995,16 +2000,7 @@ int cgroup_scan_tasks(struct cgroup_scanner *scan)
  * but we cannot guarantee that the information we produce is correct
  * unless we produce it entirely atomically.
  *
- * Upon tasks file open(), a struct ctr_struct is allocated, that
- * will have a pointer to an array (also allocated here).  The struct
- * ctr_struct * is stored in file->private_data.  Its resources will
- * be freed by release() when the file is closed.  The array is used
- * to sprintf the PIDs and then used by read().
  */
-struct ctr_struct {
-	char *buf;
-	int bufsz;
-};
 
 /*
  * Load into 'pidarray' up to 'npids' of the tasks using cgroup
@@ -2086,42 +2082,132 @@ static int cmppid(const void *a, const void *b)
 	return *(pid_t *)a - *(pid_t *)b;
 }
 
+
 /*
- * Convert array 'a' of 'npids' pid_t's to a string of newline separated
- * decimal pids in 'buf'.  Don't write more than 'sz' chars, but return
- * count 'cnt' of how many chars would be written if buf were large enough.
+ * seq_file methods for the "tasks" file. The seq_file position is the
+ * next pid to display; the seq_file iterator is a pointer to the pid
+ * in the cgroup->tasks_pids array.
  */
-static int pid_array_to_buf(char *buf, int sz, pid_t *a, int npids)
+
+static void *cgroup_tasks_start(struct seq_file *s, loff_t *pos)
 {
-	int cnt = 0;
-	int i;
+	/*
+	 * Initially we receive a position value that corresponds to
+	 * one more than the last pid shown (or 0 on the first call or
+	 * after a seek to the start). Use a binary-search to find the
+	 * next pid to display, if any
+	 */
+	struct cgroup *cgrp = s->private;
+	int index = 0, pid = *pos;
+	int *iter;
 
-	for (i = 0; i < npids; i++)
-		cnt += snprintf(buf + cnt, max(sz - cnt, 0), "%d\n", a[i]);
-	return cnt;
+	down_read(&cgrp->pids_mutex);
+	if (pid) {
+		int end = cgrp->pids_length;
+		int i;
+		while (index < end) {
+			int mid = (index + end) / 2;
+			if (cgrp->tasks_pids[mid] == pid) {
+				index = mid;
+				break;
+			} else if (cgrp->tasks_pids[mid] <= pid)
+				index = mid + 1;
+			else
+				end = mid;
+		}
+	}
+	/* If we're off the end of the array, we're done */
+	if (index >= cgrp->pids_length)
+		return NULL;
+	/* Update the abstract position to be the actual pid that we found */
+	iter = cgrp->tasks_pids + index;
+	*pos = *iter;
+	return iter;
+}
+
+static void cgroup_tasks_stop(struct seq_file *s, void *v)
+{
+	struct cgroup *cgrp = s->private;
+	up_read(&cgrp->pids_mutex);
 }
 
+static void *cgroup_tasks_next(struct seq_file *s, void *v, loff_t *pos)
+{
+	struct cgroup *cgrp = s->private;
+	int *p = v;
+	int *end = cgrp->tasks_pids + cgrp->pids_length;
+
+	/*
+	 * Advance to the next pid in the array. If this goes off the
+	 * end, we're done
+	 */
+	p++;
+	if (p >= end) {
+		return NULL;
+	} else {
+		*pos = *p;
+		return p;
+	}
+}
+
+static int cgroup_tasks_show(struct seq_file *s, void *v)
+{
+	return seq_printf(s, "%d\n", *(int *)v);
+}
+
+static struct seq_operations cgroup_tasks_seq_operations = {
+	.start = cgroup_tasks_start,
+	.stop = cgroup_tasks_stop,
+	.next = cgroup_tasks_next,
+	.show = cgroup_tasks_show,
+};
+
+static void release_cgroup_pid_array(struct cgroup *cgrp)
+{
+	down_write(&cgrp->pids_mutex);
+	BUG_ON(!cgrp->pids_use_count);
+	if (!--cgrp->pids_use_count) {
+		kfree(cgrp->tasks_pids);
+		cgrp->tasks_pids = NULL;
+		cgrp->pids_length = 0;
+	}
+	up_write(&cgrp->pids_mutex);
+}
+
+static int cgroup_tasks_release(struct inode *inode, struct file *file)
+{
+	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
+
+	if (!(file->f_mode & FMODE_READ))
+		return 0;
+
+	release_cgroup_pid_array(cgrp);
+	return seq_release(inode, file);
+}
+
+static struct file_operations cgroup_tasks_operations = {
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.write = cgroup_file_write,
+	.release = cgroup_tasks_release,
+};
+
 /*
- * Handle an open on 'tasks' file.  Prepare a buffer listing the
+ * Handle an open on 'tasks' file.  Prepare an array containing the
  * process id's of tasks currently attached to the cgroup being opened.
- *
- * Does not require any specific cgroup mutexes, and does not take any.
  */
+
 static int cgroup_tasks_open(struct inode *unused, struct file *file)
 {
 	struct cgroup *cgrp = __d_cgrp(file->f_dentry->d_parent);
-	struct ctr_struct *ctr;
 	pid_t *pidarray;
 	int npids;
-	char c;
+	int retval;
 
+	/* Nothing to do for write-only files */
 	if (!(file->f_mode & FMODE_READ))
 		return 0;
 
-	ctr = kmalloc(sizeof(*ctr), GFP_KERNEL);
-	if (!ctr)
-		goto err0;
-
 	/*
 	 * If cgroup gets more users after we read count, we won't have
 	 * enough space - tough.  This race is indistinguishable to the
@@ -2129,57 +2215,31 @@ static int cgroup_tasks_open(struct inode *unused, struct file *file)
 	 * show up until sometime later on.
 	 */
 	npids = cgroup_task_count(cgrp);
-	if (npids) {
-		pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
-		if (!pidarray)
-			goto err1;
-
-		npids = pid_array_load(pidarray, npids, cgrp);
-		sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);
-
-		/* Call pid_array_to_buf() twice, first just to get bufsz */
-		ctr->bufsz = pid_array_to_buf(&c, sizeof(c), pidarray, npids) + 1;
-		ctr->buf = kmalloc(ctr->bufsz, GFP_KERNEL);
-		if (!ctr->buf)
-			goto err2;
-		ctr->bufsz = pid_array_to_buf(ctr->buf, ctr->bufsz, pidarray, npids);
-
-		kfree(pidarray);
-	} else {
-		ctr->buf = NULL;
-		ctr->bufsz = 0;
-	}
-	file->private_data = ctr;
-	return 0;
-
-err2:
-	kfree(pidarray);
-err1:
-	kfree(ctr);
-err0:
-	return -ENOMEM;
-}
-
-static ssize_t cgroup_tasks_read(struct cgroup *cgrp,
-				    struct cftype *cft,
-				    struct file *file, char __user *buf,
-				    size_t nbytes, loff_t *ppos)
-{
-	struct ctr_struct *ctr = file->private_data;
+	pidarray = kmalloc(npids * sizeof(pid_t), GFP_KERNEL);
+	if (!pidarray)
+		return -ENOMEM;
+	npids = pid_array_load(pidarray, npids, cgrp);
+	sort(pidarray, npids, sizeof(pid_t), cmppid, NULL);
 
-	return simple_read_from_buffer(buf, nbytes, ppos, ctr->buf, ctr->bufsz);
-}
+	/*
+	 * Store the array in the cgroup, freeing the old
+	 * array if necessary
+	 */
+	down_write(&cgrp->pids_mutex);
+	kfree(cgrp->tasks_pids);
+	cgrp->tasks_pids = pidarray;
+	cgrp->pids_length = npids;
+	cgrp->pids_use_count++;
+	up_write(&cgrp->pids_mutex);
 
-static int cgroup_tasks_release(struct inode *unused_inode,
-					struct file *file)
-{
-	struct ctr_struct *ctr;
+	file->f_op = &cgroup_tasks_operations;
 
-	if (file->f_mode & FMODE_READ) {
-		ctr = file->private_data;
-		kfree(ctr->buf);
-		kfree(ctr);
+	retval = seq_open(file, &cgroup_tasks_seq_operations);
+	if (retval) {
+		release_cgroup_pid_array(cgrp);
+		return retval;
 	}
+	((struct seq_file *)file->private_data)->private = cgrp;
 	return 0;
 }
 
@@ -2208,7 +2268,6 @@ static struct cftype files[] = {
 	{
 		.name = "tasks",
 		.open = cgroup_tasks_open,
-		.read = cgroup_tasks_read,
 		.write_u64 = cgroup_tasks_write,
 		.release = cgroup_tasks_release,
 		.private = FILE_TASKLIST,
@@ -2298,10 +2357,7 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 
 	mutex_lock(&cgroup_mutex);
 
-	INIT_LIST_HEAD(&cgrp->sibling);
-	INIT_LIST_HEAD(&cgrp->children);
-	INIT_LIST_HEAD(&cgrp->css_sets);
-	INIT_LIST_HEAD(&cgrp->release_list);
+	init_cgroup_housekeeping(cgrp);
 
 	cgrp->parent = parent;
 	cgrp->root = parent->root;
-- 
cgit v1.2.3


From 886465f407e57d6c3c81013c919ea670ce1ae0d0 Mon Sep 17 00:00:00 2001
From: Paul Menage <menage@google.com>
Date: Sat, 18 Oct 2008 20:28:05 -0700
Subject: cgroups: fix declaration of cgroup_mm_owner_callbacks

The choice of real/dummy declaration for cgroup_mm_owner_callbacks()
shouldn't be based on CONFIG_MM_OWNER, but on CONFIG_CGROUPS.  Otherwise
kernel/exit.c fails to compile when something other than a cgroups
controller selects CONFIG_MM_OWNER

Signed-off-by: Paul Menage <menage@google.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/cgroup.h | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 8ab91880a0ad..8b00f6643e93 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -403,6 +403,9 @@ void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it);
 int cgroup_scan_tasks(struct cgroup_scanner *scan);
 int cgroup_attach_task(struct cgroup *, struct task_struct *);
 
+void cgroup_mm_owner_callbacks(struct task_struct *old,
+			       struct task_struct *new);
+
 #else /* !CONFIG_CGROUPS */
 
 static inline int cgroup_init_early(void) { return 0; }
@@ -421,15 +424,9 @@ static inline int cgroupstats_build(struct cgroupstats *stats,
 	return -EINVAL;
 }
 
+static inline void cgroup_mm_owner_callbacks(struct task_struct *old,
+					     struct task_struct *new) {}
+
 #endif /* !CONFIG_CGROUPS */
 
-#ifdef CONFIG_MM_OWNER
-extern void
-cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new);
-#else /* !CONFIG_MM_OWNER */
-static inline void
-cgroup_mm_owner_callbacks(struct task_struct *old, struct task_struct *new)
-{
-}
-#endif /* CONFIG_MM_OWNER */
 #endif /* _LINUX_CGROUP_H */
-- 
cgit v1.2.3


From 52d4b9ac0b985168009c2a57098324e67bae171f Mon Sep 17 00:00:00 2001
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Date: Sat, 18 Oct 2008 20:28:16 -0700
Subject: memcg: allocate all page_cgroup at boot

Allocate all page_cgroup at boot and remove page_cgroup poitner from
struct page.  This patch adds an interface as

 struct page_cgroup *lookup_page_cgroup(struct page*)

All FLATMEM/DISCONTIGMEM/SPARSEMEM  and MEMORY_HOTPLUG is supported.

Remove page_cgroup pointer reduces the amount of memory by
 - 4 bytes per PAGE_SIZE.
 - 8 bytes per PAGE_SIZE
if memory controller is disabled. (even if configured.)

On usual 8GB x86-32 server, this saves 8MB of NORMAL_ZONE memory.
On my x86-64 server with 48GB of memory, this saves 96MB of memory.
I think this reduction makes sense.

By pre-allocation, kmalloc/kfree in charge/uncharge are removed.
This means
  - we're not necessary to be afraid of kmalloc faiulre.
    (this can happen because of gfp_mask type.)
  - we can avoid calling kmalloc/kfree.
  - we can avoid allocating tons of small objects which can be fragmented.
  - we can know what amount of memory will be used for this extra-lru handling.

I added printk message as

	"allocated %ld bytes of page_cgroup"
        "please try cgroup_disable=memory option if you don't want"

maybe enough informative for users.

Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Reviewed-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/memcontrol.h  |  13 +--
 include/linux/mm_types.h    |   3 -
 include/linux/mmzone.h      |  14 ++-
 include/linux/page_cgroup.h | 103 ++++++++++++++++++
 mm/Makefile                 |   3 +-
 mm/memcontrol.c             | 247 ++++++++++++++------------------------------
 mm/page_alloc.c             |  12 +--
 mm/page_cgroup.c            | 237 ++++++++++++++++++++++++++++++++++++++++++
 8 files changed, 438 insertions(+), 194 deletions(-)
 create mode 100644 include/linux/page_cgroup.h
 create mode 100644 mm/page_cgroup.c

(limited to 'include')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ee1b2fcb4410..1fbe14d39521 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -27,9 +27,6 @@ struct mm_struct;
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 
-#define page_reset_bad_cgroup(page)	((page)->page_cgroup = 0)
-
-extern struct page_cgroup *page_get_page_cgroup(struct page *page);
 extern int mem_cgroup_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask);
 extern int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
@@ -72,16 +69,8 @@ extern void mem_cgroup_record_reclaim_priority(struct mem_cgroup *mem,
 extern long mem_cgroup_calc_reclaim(struct mem_cgroup *mem, struct zone *zone,
 					int priority, enum lru_list lru);
 
-#else /* CONFIG_CGROUP_MEM_RES_CTLR */
-static inline void page_reset_bad_cgroup(struct page *page)
-{
-}
-
-static inline struct page_cgroup *page_get_page_cgroup(struct page *page)
-{
-	return NULL;
-}
 
+#else /* CONFIG_CGROUP_MEM_RES_CTLR */
 static inline int mem_cgroup_charge(struct page *page,
 					struct mm_struct *mm, gfp_t gfp_mask)
 {
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 9d49fa36bbef..fe825471d5aa 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -94,9 +94,6 @@ struct page {
 	void *virtual;			/* Kernel virtual address (NULL if
 					   not kmapped, ie. highmem) */
 #endif /* WANT_PAGE_VIRTUAL */
-#ifdef CONFIG_CGROUP_MEM_RES_CTLR
-	unsigned long page_cgroup;
-#endif
 };
 
 /*
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index da2d053a95f1..35a7b5e19465 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -601,8 +601,11 @@ typedef struct pglist_data {
 	struct zone node_zones[MAX_NR_ZONES];
 	struct zonelist node_zonelists[MAX_ZONELISTS];
 	int nr_zones;
-#ifdef CONFIG_FLAT_NODE_MEM_MAP
+#ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
 	struct page *node_mem_map;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+	struct page_cgroup *node_page_cgroup;
+#endif
 #endif
 	struct bootmem_data *bdata;
 #ifdef CONFIG_MEMORY_HOTPLUG
@@ -931,6 +934,7 @@ static inline unsigned long early_pfn_to_nid(unsigned long pfn)
 #endif
 
 struct page;
+struct page_cgroup;
 struct mem_section {
 	/*
 	 * This is, logically, a pointer to an array of struct
@@ -948,6 +952,14 @@ struct mem_section {
 
 	/* See declaration of similar field in struct zone */
 	unsigned long *pageblock_flags;
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+	/*
+	 * If !SPARSEMEM, pgdat doesn't have page_cgroup pointer. We use
+	 * section. (see memcontrol.h/page_cgroup.h about this.)
+	 */
+	struct page_cgroup *page_cgroup;
+	unsigned long pad;
+#endif
 };
 
 #ifdef CONFIG_SPARSEMEM_EXTREME
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
new file mode 100644
index 000000000000..0fd39f2231ec
--- /dev/null
+++ b/include/linux/page_cgroup.h
@@ -0,0 +1,103 @@
+#ifndef __LINUX_PAGE_CGROUP_H
+#define __LINUX_PAGE_CGROUP_H
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+#include <linux/bit_spinlock.h>
+/*
+ * Page Cgroup can be considered as an extended mem_map.
+ * A page_cgroup page is associated with every page descriptor. The
+ * page_cgroup helps us identify information about the cgroup
+ * All page cgroups are allocated at boot or memory hotplug event,
+ * then the page cgroup for pfn always exists.
+ */
+struct page_cgroup {
+	unsigned long flags;
+	struct mem_cgroup *mem_cgroup;
+	struct page *page;
+	struct list_head lru;		/* per cgroup LRU list */
+};
+
+void __init pgdat_page_cgroup_init(struct pglist_data *pgdat);
+void __init page_cgroup_init(void);
+struct page_cgroup *lookup_page_cgroup(struct page *page);
+
+enum {
+	/* flags for mem_cgroup */
+	PCG_LOCK,  /* page cgroup is locked */
+	PCG_CACHE, /* charged as cache */
+	PCG_USED, /* this object is in use. */
+	/* flags for LRU placement */
+	PCG_ACTIVE, /* page is active in this cgroup */
+	PCG_FILE, /* page is file system backed */
+	PCG_UNEVICTABLE, /* page is unevictableable */
+};
+
+#define TESTPCGFLAG(uname, lname)			\
+static inline int PageCgroup##uname(struct page_cgroup *pc)	\
+	{ return test_bit(PCG_##lname, &pc->flags); }
+
+#define SETPCGFLAG(uname, lname)			\
+static inline void SetPageCgroup##uname(struct page_cgroup *pc)\
+	{ set_bit(PCG_##lname, &pc->flags);  }
+
+#define CLEARPCGFLAG(uname, lname)			\
+static inline void ClearPageCgroup##uname(struct page_cgroup *pc)	\
+	{ clear_bit(PCG_##lname, &pc->flags);  }
+
+/* Cache flag is set only once (at allocation) */
+TESTPCGFLAG(Cache, CACHE)
+
+TESTPCGFLAG(Used, USED)
+CLEARPCGFLAG(Used, USED)
+
+/* LRU management flags (from global-lru definition) */
+TESTPCGFLAG(File, FILE)
+SETPCGFLAG(File, FILE)
+CLEARPCGFLAG(File, FILE)
+
+TESTPCGFLAG(Active, ACTIVE)
+SETPCGFLAG(Active, ACTIVE)
+CLEARPCGFLAG(Active, ACTIVE)
+
+TESTPCGFLAG(Unevictable, UNEVICTABLE)
+SETPCGFLAG(Unevictable, UNEVICTABLE)
+CLEARPCGFLAG(Unevictable, UNEVICTABLE)
+
+static inline int page_cgroup_nid(struct page_cgroup *pc)
+{
+	return page_to_nid(pc->page);
+}
+
+static inline enum zone_type page_cgroup_zid(struct page_cgroup *pc)
+{
+	return page_zonenum(pc->page);
+}
+
+static inline void lock_page_cgroup(struct page_cgroup *pc)
+{
+	bit_spin_lock(PCG_LOCK, &pc->flags);
+}
+
+static inline int trylock_page_cgroup(struct page_cgroup *pc)
+{
+	return bit_spin_trylock(PCG_LOCK, &pc->flags);
+}
+
+static inline void unlock_page_cgroup(struct page_cgroup *pc)
+{
+	bit_spin_unlock(PCG_LOCK, &pc->flags);
+}
+
+#else /* CONFIG_CGROUP_MEM_RES_CTLR */
+struct page_cgroup;
+
+static inline void pgdat_page_cgroup_init(struct pglist_data *pgdat)
+{
+}
+
+static inline struct page_cgroup *lookup_page_cgroup(struct page *page)
+{
+	return NULL;
+}
+#endif
+#endif
diff --git a/mm/Makefile b/mm/Makefile
index da4ccf015aea..c06b45a1ff5f 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -33,5 +33,4 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(CONFIG_SMP) += allocpercpu.o
 obj-$(CONFIG_QUICKLIST) += quicklist.o
-obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o
-
+obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 031682e7ef0c..d4a92b63e98e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -33,11 +33,11 @@
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
 #include <linux/mm_inline.h>
+#include <linux/page_cgroup.h>
 
 #include <asm/uaccess.h>
 
 struct cgroup_subsys mem_cgroup_subsys __read_mostly;
-static struct kmem_cache *page_cgroup_cache __read_mostly;
 #define MEM_CGROUP_RECLAIM_RETRIES	5
 
 /*
@@ -135,79 +135,6 @@ struct mem_cgroup {
 };
 static struct mem_cgroup init_mem_cgroup;
 
-/*
- * We use the lower bit of the page->page_cgroup pointer as a bit spin
- * lock.  We need to ensure that page->page_cgroup is at least two
- * byte aligned (based on comments from Nick Piggin).  But since
- * bit_spin_lock doesn't actually set that lock bit in a non-debug
- * uniprocessor kernel, we should avoid setting it here too.
- */
-#define PAGE_CGROUP_LOCK_BIT 	0x0
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
-#define PAGE_CGROUP_LOCK 	(1 << PAGE_CGROUP_LOCK_BIT)
-#else
-#define PAGE_CGROUP_LOCK	0x0
-#endif
-
-/*
- * A page_cgroup page is associated with every page descriptor. The
- * page_cgroup helps us identify information about the cgroup
- */
-struct page_cgroup {
-	struct list_head lru;		/* per cgroup LRU list */
-	struct page *page;
-	struct mem_cgroup *mem_cgroup;
-	unsigned long flags;
-};
-
-enum {
-	/* flags for mem_cgroup */
-	PCG_CACHE, /* charged as cache */
-	/* flags for LRU placement */
-	PCG_ACTIVE, /* page is active in this cgroup */
-	PCG_FILE, /* page is file system backed */
-	PCG_UNEVICTABLE, /* page is unevictableable */
-};
-
-#define TESTPCGFLAG(uname, lname)			\
-static inline int PageCgroup##uname(struct page_cgroup *pc)	\
-	{ return test_bit(PCG_##lname, &pc->flags); }
-
-#define SETPCGFLAG(uname, lname)			\
-static inline void SetPageCgroup##uname(struct page_cgroup *pc)\
-	{ set_bit(PCG_##lname, &pc->flags);  }
-
-#define CLEARPCGFLAG(uname, lname)			\
-static inline void ClearPageCgroup##uname(struct page_cgroup *pc)	\
-	{ clear_bit(PCG_##lname, &pc->flags);  }
-
-
-/* Cache flag is set only once (at allocation) */
-TESTPCGFLAG(Cache, CACHE)
-
-/* LRU management flags (from global-lru definition) */
-TESTPCGFLAG(File, FILE)
-SETPCGFLAG(File, FILE)
-CLEARPCGFLAG(File, FILE)
-
-TESTPCGFLAG(Active, ACTIVE)
-SETPCGFLAG(Active, ACTIVE)
-CLEARPCGFLAG(Active, ACTIVE)
-
-TESTPCGFLAG(Unevictable, UNEVICTABLE)
-SETPCGFLAG(Unevictable, UNEVICTABLE)
-CLEARPCGFLAG(Unevictable, UNEVICTABLE)
-
-static int page_cgroup_nid(struct page_cgroup *pc)
-{
-	return page_to_nid(pc->page);
-}
-
-static enum zone_type page_cgroup_zid(struct page_cgroup *pc)
-{
-	return page_zonenum(pc->page);
-}
-
 enum charge_type {
 	MEM_CGROUP_CHARGE_TYPE_CACHE = 0,
 	MEM_CGROUP_CHARGE_TYPE_MAPPED,
@@ -216,12 +143,18 @@ enum charge_type {
 	NR_CHARGE_TYPE,
 };
 
+/* only for here (for easy reading.) */
+#define PCGF_CACHE	(1UL << PCG_CACHE)
+#define PCGF_USED	(1UL << PCG_USED)
+#define PCGF_ACTIVE	(1UL << PCG_ACTIVE)
+#define PCGF_LOCK	(1UL << PCG_LOCK)
+#define PCGF_FILE	(1UL << PCG_FILE)
 static const unsigned long
 pcg_default_flags[NR_CHARGE_TYPE] = {
-	((1 << PCG_CACHE) | (1 << PCG_FILE)),
-	((1 << PCG_ACTIVE)),
-	((1 << PCG_ACTIVE) | (1 << PCG_CACHE)),
-	0,
+	PCGF_CACHE | PCGF_FILE | PCGF_USED | PCGF_LOCK, /* File Cache */
+	PCGF_ACTIVE | PCGF_USED | PCGF_LOCK, /* Anon */
+	PCGF_ACTIVE | PCGF_CACHE | PCGF_USED | PCGF_LOCK, /* Shmem */
+	0, /* FORCE */
 };
 
 /*
@@ -303,37 +236,6 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 				struct mem_cgroup, css);
 }
 
-static inline int page_cgroup_locked(struct page *page)
-{
-	return bit_spin_is_locked(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static void page_assign_page_cgroup(struct page *page, struct page_cgroup *pc)
-{
-	VM_BUG_ON(!page_cgroup_locked(page));
-	page->page_cgroup = ((unsigned long)pc | PAGE_CGROUP_LOCK);
-}
-
-struct page_cgroup *page_get_page_cgroup(struct page *page)
-{
-	return (struct page_cgroup *) (page->page_cgroup & ~PAGE_CGROUP_LOCK);
-}
-
-static void lock_page_cgroup(struct page *page)
-{
-	bit_spin_lock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static int try_lock_page_cgroup(struct page *page)
-{
-	return bit_spin_trylock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
-static void unlock_page_cgroup(struct page *page)
-{
-	bit_spin_unlock(PAGE_CGROUP_LOCK_BIT, &page->page_cgroup);
-}
-
 static void __mem_cgroup_remove_list(struct mem_cgroup_per_zone *mz,
 			struct page_cgroup *pc)
 {
@@ -436,17 +338,16 @@ void mem_cgroup_move_lists(struct page *page, enum lru_list lru)
 	 * safely get to page_cgroup without it, so just try_lock it:
 	 * mem_cgroup_isolate_pages allows for page left on wrong list.
 	 */
-	if (!try_lock_page_cgroup(page))
+	pc = lookup_page_cgroup(page);
+	if (!trylock_page_cgroup(pc))
 		return;
-
-	pc = page_get_page_cgroup(page);
-	if (pc) {
+	if (pc && PageCgroupUsed(pc)) {
 		mz = page_cgroup_zoneinfo(pc);
 		spin_lock_irqsave(&mz->lru_lock, flags);
 		__mem_cgroup_move_lists(pc, lru);
 		spin_unlock_irqrestore(&mz->lru_lock, flags);
 	}
-	unlock_page_cgroup(page);
+	unlock_page_cgroup(pc);
 }
 
 /*
@@ -533,6 +434,8 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 	list_for_each_entry_safe_reverse(pc, tmp, src, lru) {
 		if (scan >= nr_to_scan)
 			break;
+		if (unlikely(!PageCgroupUsed(pc)))
+			continue;
 		page = pc->page;
 
 		if (unlikely(!PageLRU(page)))
@@ -576,26 +479,27 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 {
 	struct mem_cgroup *mem;
 	struct page_cgroup *pc;
-	unsigned long flags;
 	unsigned long nr_retries = MEM_CGROUP_RECLAIM_RETRIES;
 	struct mem_cgroup_per_zone *mz;
+	unsigned long flags;
 
-	pc = kmem_cache_alloc(page_cgroup_cache, gfp_mask);
-	if (unlikely(pc == NULL))
-		goto err;
-
+	pc = lookup_page_cgroup(page);
+	/* can happen at boot */
+	if (unlikely(!pc))
+		return 0;
+	prefetchw(pc);
 	/*
 	 * We always charge the cgroup the mm_struct belongs to.
 	 * The mm_struct's mem_cgroup changes on task migration if the
 	 * thread group leader migrates. It's possible that mm is not
 	 * set, if so charge the init_mm (happens for pagecache usage).
 	 */
+
 	if (likely(!memcg)) {
 		rcu_read_lock();
 		mem = mem_cgroup_from_task(rcu_dereference(mm->owner));
 		if (unlikely(!mem)) {
 			rcu_read_unlock();
-			kmem_cache_free(page_cgroup_cache, pc);
 			return 0;
 		}
 		/*
@@ -631,36 +535,33 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 		}
 	}
 
+
+	lock_page_cgroup(pc);
+	if (unlikely(PageCgroupUsed(pc))) {
+		unlock_page_cgroup(pc);
+		res_counter_uncharge(&mem->res, PAGE_SIZE);
+		css_put(&mem->css);
+
+		goto done;
+	}
 	pc->mem_cgroup = mem;
-	pc->page = page;
 	/*
 	 * If a page is accounted as a page cache, insert to inactive list.
 	 * If anon, insert to active list.
 	 */
 	pc->flags = pcg_default_flags[ctype];
 
-	lock_page_cgroup(page);
-	if (unlikely(page_get_page_cgroup(page))) {
-		unlock_page_cgroup(page);
-		res_counter_uncharge(&mem->res, PAGE_SIZE);
-		css_put(&mem->css);
-		kmem_cache_free(page_cgroup_cache, pc);
-		goto done;
-	}
-	page_assign_page_cgroup(page, pc);
-
 	mz = page_cgroup_zoneinfo(pc);
+
 	spin_lock_irqsave(&mz->lru_lock, flags);
 	__mem_cgroup_add_list(mz, pc);
 	spin_unlock_irqrestore(&mz->lru_lock, flags);
+	unlock_page_cgroup(pc);
 
-	unlock_page_cgroup(page);
 done:
 	return 0;
 out:
 	css_put(&mem->css);
-	kmem_cache_free(page_cgroup_cache, pc);
-err:
 	return -ENOMEM;
 }
 
@@ -668,7 +569,8 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask)
 {
 	if (mem_cgroup_subsys.disabled)
 		return 0;
-
+	if (PageCompound(page))
+		return 0;
 	/*
 	 * If already mapped, we don't have to account.
 	 * If page cache, page->mapping has address_space.
@@ -689,7 +591,8 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 {
 	if (mem_cgroup_subsys.disabled)
 		return 0;
-
+	if (PageCompound(page))
+		return 0;
 	/*
 	 * Corner case handling. This is called from add_to_page_cache()
 	 * in usual. But some FS (shmem) precharges this page before calling it
@@ -702,15 +605,16 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 	if (!(gfp_mask & __GFP_WAIT)) {
 		struct page_cgroup *pc;
 
-		lock_page_cgroup(page);
-		pc = page_get_page_cgroup(page);
-		if (pc) {
-			VM_BUG_ON(pc->page != page);
-			VM_BUG_ON(!pc->mem_cgroup);
-			unlock_page_cgroup(page);
+
+		pc = lookup_page_cgroup(page);
+		if (!pc)
+			return 0;
+		lock_page_cgroup(pc);
+		if (PageCgroupUsed(pc)) {
+			unlock_page_cgroup(pc);
 			return 0;
 		}
-		unlock_page_cgroup(page);
+		unlock_page_cgroup(pc);
 	}
 
 	if (unlikely(!mm))
@@ -741,37 +645,39 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	/*
 	 * Check if our page_cgroup is valid
 	 */
-	lock_page_cgroup(page);
-	pc = page_get_page_cgroup(page);
-	if (unlikely(!pc))
-		goto unlock;
-
-	VM_BUG_ON(pc->page != page);
+	pc = lookup_page_cgroup(page);
+	if (unlikely(!pc || !PageCgroupUsed(pc)))
+		return;
 
-	if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED)
-	    && ((PageCgroupCache(pc) || page_mapped(page))))
-		goto unlock;
+	lock_page_cgroup(pc);
+	if ((ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED && page_mapped(page))
+	     || !PageCgroupUsed(pc)) {
+		/* This happens at race in zap_pte_range() and do_swap_page()*/
+		unlock_page_cgroup(pc);
+		return;
+	}
+	ClearPageCgroupUsed(pc);
+	mem = pc->mem_cgroup;
 
 	mz = page_cgroup_zoneinfo(pc);
 	spin_lock_irqsave(&mz->lru_lock, flags);
 	__mem_cgroup_remove_list(mz, pc);
 	spin_unlock_irqrestore(&mz->lru_lock, flags);
+	unlock_page_cgroup(pc);
 
-	page_assign_page_cgroup(page, NULL);
-	unlock_page_cgroup(page);
-
-	mem = pc->mem_cgroup;
 	res_counter_uncharge(&mem->res, PAGE_SIZE);
 	css_put(&mem->css);
 
-	kmem_cache_free(page_cgroup_cache, pc);
 	return;
-unlock:
-	unlock_page_cgroup(page);
 }
 
 void mem_cgroup_uncharge_page(struct page *page)
 {
+	/* early check. */
+	if (page_mapped(page))
+		return;
+	if (page->mapping && !PageAnon(page))
+		return;
 	__mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_MAPPED);
 }
 
@@ -795,9 +701,9 @@ int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
 	if (mem_cgroup_subsys.disabled)
 		return 0;
 
-	lock_page_cgroup(page);
-	pc = page_get_page_cgroup(page);
-	if (pc) {
+	pc = lookup_page_cgroup(page);
+	lock_page_cgroup(pc);
+	if (PageCgroupUsed(pc)) {
 		mem = pc->mem_cgroup;
 		css_get(&mem->css);
 		if (PageCgroupCache(pc)) {
@@ -807,7 +713,7 @@ int mem_cgroup_prepare_migration(struct page *page, struct page *newpage)
 				ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
 		}
 	}
-	unlock_page_cgroup(page);
+	unlock_page_cgroup(pc);
 	if (mem) {
 		ret = mem_cgroup_charge_common(newpage, NULL, GFP_KERNEL,
 			ctype, mem);
@@ -832,7 +738,7 @@ void mem_cgroup_end_migration(struct page *newpage)
 	 */
 	if (!newpage->mapping)
 		__mem_cgroup_uncharge_common(newpage,
-					 MEM_CGROUP_CHARGE_TYPE_FORCE);
+				MEM_CGROUP_CHARGE_TYPE_FORCE);
 	else if (PageAnon(newpage))
 		mem_cgroup_uncharge_page(newpage);
 }
@@ -918,6 +824,8 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
 	while (!list_empty(list)) {
 		pc = list_entry(list->prev, struct page_cgroup, lru);
 		page = pc->page;
+		if (!PageCgroupUsed(pc))
+			break;
 		get_page(page);
 		spin_unlock_irqrestore(&mz->lru_lock, flags);
 		/*
@@ -932,8 +840,10 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *mem,
 				count = FORCE_UNCHARGE_BATCH;
 				cond_resched();
 			}
-		} else
-			cond_resched();
+		} else {
+			spin_lock_irqsave(&mz->lru_lock, flags);
+			break;
+		}
 		spin_lock_irqsave(&mz->lru_lock, flags);
 	}
 	spin_unlock_irqrestore(&mz->lru_lock, flags);
@@ -957,6 +867,8 @@ static int mem_cgroup_force_empty(struct mem_cgroup *mem)
 	while (mem->res.usage > 0) {
 		if (atomic_read(&mem->css.cgroup->count) > 0)
 			goto out;
+		/* This is for making all *used* pages to be on LRU. */
+		lru_add_drain_all();
 		for_each_node_state(node, N_POSSIBLE)
 			for (zid = 0; zid < MAX_NR_ZONES; zid++) {
 				struct mem_cgroup_per_zone *mz;
@@ -965,6 +877,7 @@ static int mem_cgroup_force_empty(struct mem_cgroup *mem)
 				for_each_lru(l)
 					mem_cgroup_force_empty_list(mem, mz, l);
 			}
+		cond_resched();
 	}
 	ret = 0;
 out:
@@ -1175,8 +1088,8 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	int node;
 
 	if (unlikely((cont->parent) == NULL)) {
+		page_cgroup_init();
 		mem = &init_mem_cgroup;
-		page_cgroup_cache = KMEM_CACHE(page_cgroup, SLAB_PANIC);
 	} else {
 		mem = mem_cgroup_alloc();
 		if (!mem)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f2fc44ec1d44..d0a240fbb8bf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -44,7 +44,7 @@
 #include <linux/backing-dev.h>
 #include <linux/fault-inject.h>
 #include <linux/page-isolation.h>
-#include <linux/memcontrol.h>
+#include <linux/page_cgroup.h>
 #include <linux/debugobjects.h>
 
 #include <asm/tlbflush.h>
@@ -223,17 +223,12 @@ static inline int bad_range(struct zone *zone, struct page *page)
 
 static void bad_page(struct page *page)
 {
-	void *pc = page_get_page_cgroup(page);
-
 	printk(KERN_EMERG "Bad page state in process '%s'\n" KERN_EMERG
 		"page:%p flags:0x%0*lx mapping:%p mapcount:%d count:%d\n",
 		current->comm, page, (int)(2*sizeof(unsigned long)),
 		(unsigned long)page->flags, page->mapping,
 		page_mapcount(page), page_count(page));
-	if (pc) {
-		printk(KERN_EMERG "cgroup:%p\n", pc);
-		page_reset_bad_cgroup(page);
-	}
+
 	printk(KERN_EMERG "Trying to fix it up, but a reboot is needed\n"
 		KERN_EMERG "Backtrace:\n");
 	dump_stack();
@@ -457,7 +452,6 @@ static inline int free_pages_check(struct page *page)
 	free_page_mlock(page);
 	if (unlikely(page_mapcount(page) |
 		(page->mapping != NULL)  |
-		(page_get_page_cgroup(page) != NULL) |
 		(page_count(page) != 0)  |
 		(page->flags & PAGE_FLAGS_CHECK_AT_FREE)))
 		bad_page(page);
@@ -603,7 +597,6 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
 {
 	if (unlikely(page_mapcount(page) |
 		(page->mapping != NULL)  |
-		(page_get_page_cgroup(page) != NULL) |
 		(page_count(page) != 0)  |
 		(page->flags & PAGE_FLAGS_CHECK_AT_PREP)))
 		bad_page(page);
@@ -3438,6 +3431,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat,
 	pgdat->nr_zones = 0;
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	pgdat->kswapd_max_order = 0;
+	pgdat_page_cgroup_init(pgdat);
 	
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
new file mode 100644
index 000000000000..5d86550701f2
--- /dev/null
+++ b/mm/page_cgroup.c
@@ -0,0 +1,237 @@
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/bootmem.h>
+#include <linux/bit_spinlock.h>
+#include <linux/page_cgroup.h>
+#include <linux/hash.h>
+#include <linux/memory.h>
+
+static void __meminit
+__init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
+{
+	pc->flags = 0;
+	pc->mem_cgroup = NULL;
+	pc->page = pfn_to_page(pfn);
+}
+static unsigned long total_usage;
+
+#if !defined(CONFIG_SPARSEMEM)
+
+
+void __init pgdat_page_cgroup_init(struct pglist_data *pgdat)
+{
+	pgdat->node_page_cgroup = NULL;
+}
+
+struct page_cgroup *lookup_page_cgroup(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+	unsigned long offset;
+	struct page_cgroup *base;
+
+	base = NODE_DATA(page_to_nid(page))->node_page_cgroup;
+	if (unlikely(!base))
+		return NULL;
+
+	offset = pfn - NODE_DATA(page_to_nid(page))->node_start_pfn;
+	return base + offset;
+}
+
+static int __init alloc_node_page_cgroup(int nid)
+{
+	struct page_cgroup *base, *pc;
+	unsigned long table_size;
+	unsigned long start_pfn, nr_pages, index;
+
+	start_pfn = NODE_DATA(nid)->node_start_pfn;
+	nr_pages = NODE_DATA(nid)->node_spanned_pages;
+
+	table_size = sizeof(struct page_cgroup) * nr_pages;
+
+	base = __alloc_bootmem_node_nopanic(NODE_DATA(nid),
+			table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	if (!base)
+		return -ENOMEM;
+	for (index = 0; index < nr_pages; index++) {
+		pc = base + index;
+		__init_page_cgroup(pc, start_pfn + index);
+	}
+	NODE_DATA(nid)->node_page_cgroup = base;
+	total_usage += table_size;
+	return 0;
+}
+
+void __init page_cgroup_init(void)
+{
+
+	int nid, fail;
+
+	for_each_online_node(nid)  {
+		fail = alloc_node_page_cgroup(nid);
+		if (fail)
+			goto fail;
+	}
+	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
+	printk(KERN_INFO "please try cgroup_disable=memory option if you"
+	" don't want\n");
+	return;
+fail:
+	printk(KERN_CRIT "allocation of page_cgroup was failed.\n");
+	printk(KERN_CRIT "please try cgroup_disable=memory boot option\n");
+	panic("Out of memory");
+}
+
+#else /* CONFIG_FLAT_NODE_MEM_MAP */
+
+struct page_cgroup *lookup_page_cgroup(struct page *page)
+{
+	unsigned long pfn = page_to_pfn(page);
+	struct mem_section *section = __pfn_to_section(pfn);
+
+	return section->page_cgroup + pfn;
+}
+
+int __meminit init_section_page_cgroup(unsigned long pfn)
+{
+	struct mem_section *section;
+	struct page_cgroup *base, *pc;
+	unsigned long table_size;
+	int nid, index;
+
+	section = __pfn_to_section(pfn);
+
+	if (section->page_cgroup)
+		return 0;
+
+	nid = page_to_nid(pfn_to_page(pfn));
+
+	table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
+	base = kmalloc_node(table_size, GFP_KERNEL, nid);
+	if (!base)
+		base = vmalloc_node(table_size, nid);
+
+	if (!base) {
+		printk(KERN_ERR "page cgroup allocation failure\n");
+		return -ENOMEM;
+	}
+
+	for (index = 0; index < PAGES_PER_SECTION; index++) {
+		pc = base + index;
+		__init_page_cgroup(pc, pfn + index);
+	}
+
+	section = __pfn_to_section(pfn);
+	section->page_cgroup = base - pfn;
+	total_usage += table_size;
+	return 0;
+}
+#ifdef CONFIG_MEMORY_HOTPLUG
+void __free_page_cgroup(unsigned long pfn)
+{
+	struct mem_section *ms;
+	struct page_cgroup *base;
+
+	ms = __pfn_to_section(pfn);
+	if (!ms || !ms->page_cgroup)
+		return;
+	base = ms->page_cgroup + pfn;
+	ms->page_cgroup = NULL;
+	if (is_vmalloc_addr(base))
+		vfree(base);
+	else
+		kfree(base);
+}
+
+int online_page_cgroup(unsigned long start_pfn,
+			unsigned long nr_pages,
+			int nid)
+{
+	unsigned long start, end, pfn;
+	int fail = 0;
+
+	start = start_pfn & (PAGES_PER_SECTION - 1);
+	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
+
+	for (pfn = start; !fail && pfn < end; pfn += PAGES_PER_SECTION) {
+		if (!pfn_present(pfn))
+			continue;
+		fail = init_section_page_cgroup(pfn);
+	}
+	if (!fail)
+		return 0;
+
+	/* rollback */
+	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
+		__free_page_cgroup(pfn);
+
+	return -ENOMEM;
+}
+
+int offline_page_cgroup(unsigned long start_pfn,
+		unsigned long nr_pages, int nid)
+{
+	unsigned long start, end, pfn;
+
+	start = start_pfn & (PAGES_PER_SECTION - 1);
+	end = ALIGN(start_pfn + nr_pages, PAGES_PER_SECTION);
+
+	for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION)
+		__free_page_cgroup(pfn);
+	return 0;
+
+}
+
+static int page_cgroup_callback(struct notifier_block *self,
+			       unsigned long action, void *arg)
+{
+	struct memory_notify *mn = arg;
+	int ret = 0;
+	switch (action) {
+	case MEM_GOING_ONLINE:
+		ret = online_page_cgroup(mn->start_pfn,
+				   mn->nr_pages, mn->status_change_nid);
+		break;
+	case MEM_CANCEL_ONLINE:
+	case MEM_OFFLINE:
+		offline_page_cgroup(mn->start_pfn,
+				mn->nr_pages, mn->status_change_nid);
+		break;
+	case MEM_GOING_OFFLINE:
+		break;
+	case MEM_ONLINE:
+	case MEM_CANCEL_OFFLINE:
+		break;
+	}
+	ret = notifier_from_errno(ret);
+	return ret;
+}
+
+#endif
+
+void __init page_cgroup_init(void)
+{
+	unsigned long pfn;
+	int fail = 0;
+
+	for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
+		if (!pfn_present(pfn))
+			continue;
+		fail = init_section_page_cgroup(pfn);
+	}
+	if (fail) {
+		printk(KERN_CRIT "try cgroup_disable=memory boot option\n");
+		panic("Out of memory");
+	} else {
+		hotplug_memory_notifier(page_cgroup_callback, 0);
+	}
+	printk(KERN_INFO "allocated %ld bytes of page_cgroup\n", total_usage);
+	printk(KERN_INFO "please try cgroup_disable=memory option if you don't"
+	" want\n");
+}
+
+void __init pgdat_page_cgroup_init(struct pglist_data *pgdat)
+{
+	return;
+}
+
+#endif
-- 
cgit v1.2.3


From 3eda20118000941e7e8994fc5fac8706d8c10f00 Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Sat, 18 Oct 2008 20:28:19 -0700
Subject: seq_file: add seq_cpumask_list(), seq_nodemask_list()

seq_cpumask_list(), seq_nodemask_list() are very like seq_cpumask(),
seq_nodemask(), but they print human readable string.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Paul Menage <menage@google.com>
Cc: Paul Jackson <pj@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/seq_file.c            | 16 ++++++++++++++++
 include/linux/seq_file.h | 13 +++++++++++++
 2 files changed, 29 insertions(+)

(limited to 'include')

diff --git a/fs/seq_file.c b/fs/seq_file.c
index 11c85fec6b4f..eba2eabcd2b8 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -465,6 +465,22 @@ int seq_bitmap(struct seq_file *m, unsigned long *bits, unsigned int nr_bits)
 }
 EXPORT_SYMBOL(seq_bitmap);
 
+int seq_bitmap_list(struct seq_file *m, unsigned long *bits,
+		unsigned int nr_bits)
+{
+	if (m->count < m->size) {
+		int len = bitmap_scnlistprintf(m->buf + m->count,
+				m->size - m->count, bits, nr_bits);
+		if (m->count + len < m->size) {
+			m->count += len;
+			return 0;
+		}
+	}
+	m->count = m->size;
+	return -1;
+}
+EXPORT_SYMBOL(seq_bitmap_list);
+
 static void *single_start(struct seq_file *p, loff_t *pos)
 {
 	return NULL + (*pos == 0);
diff --git a/include/linux/seq_file.h b/include/linux/seq_file.h
index a1783b229ef4..dc50bcc282a8 100644
--- a/include/linux/seq_file.h
+++ b/include/linux/seq_file.h
@@ -60,6 +60,19 @@ static inline int seq_nodemask(struct seq_file *m, nodemask_t *mask)
 	return seq_bitmap(m, mask->bits, MAX_NUMNODES);
 }
 
+int seq_bitmap_list(struct seq_file *m, unsigned long *bits,
+		unsigned int nr_bits);
+
+static inline int seq_cpumask_list(struct seq_file *m, cpumask_t *mask)
+{
+	return seq_bitmap_list(m, mask->bits, NR_CPUS);
+}
+
+static inline int seq_nodemask_list(struct seq_file *m, nodemask_t *mask)
+{
+	return seq_bitmap_list(m, mask->bits, MAX_NUMNODES);
+}
+
 int single_open(struct file *, int (*)(struct seq_file *, void *), void *);
 int single_release(struct inode *, struct file *);
 void *__seq_open_private(struct file *, const struct seq_operations *, int);
-- 
cgit v1.2.3


From c4596435404976b0ded9cdf18b456ca2e1408ddd Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Sat, 18 Oct 2008 20:28:21 -0700
Subject: bitmask: remove bitmap_scnprintf_len()

bitmap_scnprintf_len() is not used now, so we remove it.

Otherwise we have to maintain it and make its return
value always equal to bitmap_scnprintf()'s return value.

Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Paul Menage <menage@google.com>
Cc: Paul Jackson <pj@sgi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bitmap.h |  1 -
 lib/bitmap.c           | 11 -----------
 2 files changed, 12 deletions(-)

(limited to 'include')

diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 89781fd48859..1abfe664c444 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -110,7 +110,6 @@ extern int __bitmap_weight(const unsigned long *bitmap, int bits);
 
 extern int bitmap_scnprintf(char *buf, unsigned int len,
 			const unsigned long *src, int nbits);
-extern int bitmap_scnprintf_len(unsigned int nr_bits);
 extern int __bitmap_parse(const char *buf, unsigned int buflen, int is_user,
 			unsigned long *dst, int nbits);
 extern int bitmap_parse_user(const char __user *ubuf, unsigned int ulen,
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 06fb57c86de0..482df94ea21e 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -315,17 +315,6 @@ int bitmap_scnprintf(char *buf, unsigned int buflen,
 }
 EXPORT_SYMBOL(bitmap_scnprintf);
 
-/**
- * bitmap_scnprintf_len - return buffer length needed to convert
- * bitmap to an ASCII hex string
- * @nr_bits: number of bits to be converted
- */
-int bitmap_scnprintf_len(unsigned int nr_bits)
-{
-	unsigned int nr_nibbles = ALIGN(nr_bits, 4) / 4;
-	return nr_nibbles + ALIGN(nr_nibbles, CHUNKSZ / 4) / (CHUNKSZ / 4) - 1;
-}
-
 /**
  * __bitmap_parse - convert an ASCII hex string into a bitmap.
  * @buf: pointer to buffer containing string.
-- 
cgit v1.2.3


From b747c8c102cc0677a7a8056a093f58d7c9b500e7 Mon Sep 17 00:00:00 2001
From: Adrian Bunk <bunk@kernel.org>
Date: Sat, 18 Oct 2008 20:28:21 -0700
Subject: make ptrace_untrace() static

ptrace_untrace() can now become static.

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Roland McGrath <roland@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/ptrace.h | 1 -
 kernel/ptrace.c        | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index ea7416c901d1..22641d5d45df 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -94,7 +94,6 @@ extern void ptrace_notify(int exit_code);
 extern void __ptrace_link(struct task_struct *child,
 			  struct task_struct *new_parent);
 extern void __ptrace_unlink(struct task_struct *child);
-extern void ptrace_untrace(struct task_struct *child);
 #define PTRACE_MODE_READ   1
 #define PTRACE_MODE_ATTACH 2
 /* Returns 0 on success, -errno on denial. */
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 356699a96d56..1e68e4c39e2c 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -45,7 +45,7 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent)
  * TASK_TRACED, resume it now.
  * Requires that irqs be disabled.
  */
-void ptrace_untrace(struct task_struct *child)
+static void ptrace_untrace(struct task_struct *child)
 {
 	spin_lock(&child->sighand->siglock);
 	if (task_is_traced(child)) {
-- 
cgit v1.2.3


From 656eb2cd5da153762f2e8419ca117ce12ef522c3 Mon Sep 17 00:00:00 2001
From: Roland McGrath <roland@redhat.com>
Date: Sat, 18 Oct 2008 20:28:23 -0700
Subject: add CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS

This adds a kconfig option to change the /proc/PID/coredump_filter default.
Fedora has been carrying a trivial patch to change the hard-wired value for
this default, since Fedora 8.  The default default can't change safely
because there are old GDB versions out there (all before 6.7) that are
confused by the core dump files created by the MMF_DUMP_ELF_HEADERS setting.

Signed-off-by: Roland McGrath <roland@redhat.com>
Cc: Michael Kerrisk <mtk.manpages@googlemail.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Kawai Hidehiro <hidehiro.kawai.ez@hitachi.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: David Jones <davej@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/Kconfig.binfmt     | 22 ++++++++++++++++++++++
 include/linux/sched.h |  8 +++++++-
 2 files changed, 29 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 801db1341811..ce9fb3fbfae4 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -40,6 +40,28 @@ config BINFMT_ELF_FDPIC
 
 	  It is also possible to run FDPIC ELF binaries on MMU linux also.
 
+config CORE_DUMP_DEFAULT_ELF_HEADERS
+	bool "Write ELF core dumps with partial segments"
+	default n
+	depends on BINFMT_ELF
+	help
+	  ELF core dump files describe each memory mapping of the crashed
+	  process, and can contain or omit the memory contents of each one.
+	  The contents of an unmodified text mapping are omitted by default.
+
+	  For an unmodified text mapping of an ELF object, including just
+	  the first page of the file in a core dump makes it possible to
+	  identify the build ID bits in the file, without paying the i/o
+	  cost and disk space to dump all the text.  However, versions of
+	  GDB before 6.7 are confused by ELF core dump files in this format.
+
+	  The core dump behavior can be controlled per process using
+	  the /proc/PID/coredump_filter pseudo-file; this setting is
+	  inherited.  See Documentation/filesystems/proc.txt for details.
+
+	  This config option changes the default setting of coredump_filter
+	  seen at boot time.  If unsure, say N.
+
 config BINFMT_FLAT
 	bool "Kernel support for flat binaries"
 	depends on !MMU && (!FRV || BROKEN)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 017cc914ef1f..f52dbd3587a7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -411,7 +411,13 @@ extern int get_dumpable(struct mm_struct *mm);
 	(((1 << MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
 #define MMF_DUMP_FILTER_DEFAULT \
 	((1 << MMF_DUMP_ANON_PRIVATE) |	(1 << MMF_DUMP_ANON_SHARED) |\
-	 (1 << MMF_DUMP_HUGETLB_PRIVATE))
+	 (1 << MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF)
+
+#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS
+# define MMF_DUMP_MASK_DEFAULT_ELF	(1 << MMF_DUMP_ELF_HEADERS)
+#else
+# define MMF_DUMP_MASK_DEFAULT_ELF	0
+#endif
 
 struct sighand_struct {
 	atomic_t		count;
-- 
cgit v1.2.3


From 57cac4d1880527e0baf6c2fda529d2ad1d815aec Mon Sep 17 00:00:00 2001
From: Vivek Goyal <vgoyal@redhat.com>
Date: Sat, 18 Oct 2008 20:28:25 -0700
Subject: kdump: make elfcorehdr_addr independent of CONFIG_PROC_VMCORE

o elfcorehdr_addr is used by not only the code under CONFIG_PROC_VMCORE
  but also by the code which is not inside CONFIG_PROC_VMCORE.  For
  example, is_kdump_kernel() is used by powerpc code to determine if
  kernel is booting after a panic then use previous kernel's TCE table.
  So even if CONFIG_PROC_VMCORE is not set in second kernel, one should be
  able to correctly determine that we are booting after a panic and setup
  calgary iommu accordingly.

o So remove the assumption that elfcorehdr_addr is under
  CONFIG_PROC_VMCORE.

o Move definition of elfcorehdr_addr to arch dependent crash files.
  (Unfortunately crash dump does not have an arch independent file
  otherwise that would have been the best place).

o kexec.c is not the right place as one can Have CRASH_DUMP enabled in
  second kernel without KEXEC being enabled.

o I don't see sh setup code parsing the command line for
  elfcorehdr_addr.  I am wondering how does vmcore interface work on sh.
  Anyway, I am atleast defining elfcoredhr_addr so that compilation is not
  broken on sh.

Signed-off-by: Vivek Goyal <vgoyal@redhat.com>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Simon Horman <horms@verge.net.au>
Acked-by: Paul Mundt <lethal@linux-sh.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/kernel/crash_dump.c    |  4 ++++
 arch/ia64/kernel/setup.c         |  9 ++++++++-
 arch/powerpc/kernel/crash_dump.c | 10 ++++++++--
 arch/sh/kernel/crash_dump.c      |  3 +++
 arch/x86/kernel/crash_dump_32.c  |  3 +++
 arch/x86/kernel/crash_dump_64.c  |  3 +++
 arch/x86/kernel/setup.c          |  8 +++++++-
 fs/proc/vmcore.c                 |  3 ---
 include/linux/crash_dump.h       | 14 ++++++++++----
 9 files changed, 46 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/crash_dump.c b/arch/ia64/kernel/crash_dump.c
index da60e90eeeb1..23e91290e41f 100644
--- a/arch/ia64/kernel/crash_dump.c
+++ b/arch/ia64/kernel/crash_dump.c
@@ -8,10 +8,14 @@
 
 #include <linux/errno.h>
 #include <linux/types.h>
+#include <linux/crash_dump.h>
 
 #include <asm/page.h>
 #include <asm/uaccess.h>
 
+/* Stores the physical address of elf header of crash image. */
+unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
+
 /**
  * copy_oldmem_page - copy one page from "oldmem"
  * @pfn: page frame number to be copied
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index de636b215677..a0286be6c235 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -478,7 +478,12 @@ static __init int setup_nomca(char *s)
 }
 early_param("nomca", setup_nomca);
 
-#ifdef CONFIG_PROC_VMCORE
+/*
+ * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
+ * is_kdump_kernel() to determine if we are booting after a panic. Hence
+ * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE.
+ */
+#ifdef CONFIG_CRASH_DUMP
 /* elfcorehdr= specifies the location of elf core header
  * stored by the crashed kernel.
  */
@@ -491,7 +496,9 @@ static int __init parse_elfcorehdr(char *arg)
 	return 0;
 }
 early_param("elfcorehdr", parse_elfcorehdr);
+#endif
 
+#ifdef CONFIG_PROC_VMCORE
 int __init reserve_elfcorehdr(unsigned long *start, unsigned long *end)
 {
 	unsigned long length;
diff --git a/arch/powerpc/kernel/crash_dump.c b/arch/powerpc/kernel/crash_dump.c
index a323c9b32ee1..97e056379728 100644
--- a/arch/powerpc/kernel/crash_dump.c
+++ b/arch/powerpc/kernel/crash_dump.c
@@ -27,6 +27,9 @@
 #define DBG(fmt...)
 #endif
 
+/* Stores the physical address of elf header of crash image. */
+unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
+
 void __init reserve_kdump_trampoline(void)
 {
 	lmb_reserve(0, KDUMP_RESERVE_LIMIT);
@@ -66,7 +69,11 @@ void __init setup_kdump_trampoline(void)
 	DBG(" <- setup_kdump_trampoline()\n");
 }
 
-#ifdef CONFIG_PROC_VMCORE
+/*
+ * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
+ * is_kdump_kernel() to determine if we are booting after a panic. Hence
+ * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE.
+ */
 static int __init parse_elfcorehdr(char *p)
 {
 	if (p)
@@ -75,7 +82,6 @@ static int __init parse_elfcorehdr(char *p)
 	return 1;
 }
 __setup("elfcorehdr=", parse_elfcorehdr);
-#endif
 
 static int __init parse_savemaxmem(char *p)
 {
diff --git a/arch/sh/kernel/crash_dump.c b/arch/sh/kernel/crash_dump.c
index 4a2ecbe27d8e..95d216255565 100644
--- a/arch/sh/kernel/crash_dump.c
+++ b/arch/sh/kernel/crash_dump.c
@@ -10,6 +10,9 @@
 #include <linux/io.h>
 #include <asm/uaccess.h>
 
+/* Stores the physical address of elf header of crash image. */
+unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
+
 /**
  * copy_oldmem_page - copy one page from "oldmem"
  * @pfn: page frame number to be copied
diff --git a/arch/x86/kernel/crash_dump_32.c b/arch/x86/kernel/crash_dump_32.c
index 72d0c56c1b48..f7cdb3b457aa 100644
--- a/arch/x86/kernel/crash_dump_32.c
+++ b/arch/x86/kernel/crash_dump_32.c
@@ -13,6 +13,9 @@
 
 static void *kdump_buf_page;
 
+/* Stores the physical address of elf header of crash image. */
+unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
+
 /**
  * copy_oldmem_page - copy one page from "oldmem"
  * @pfn: page frame number to be copied
diff --git a/arch/x86/kernel/crash_dump_64.c b/arch/x86/kernel/crash_dump_64.c
index e90a60ef10c2..045b36cada65 100644
--- a/arch/x86/kernel/crash_dump_64.c
+++ b/arch/x86/kernel/crash_dump_64.c
@@ -10,6 +10,9 @@
 #include <linux/uaccess.h>
 #include <linux/io.h>
 
+/* Stores the physical address of elf header of crash image. */
+unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
+
 /**
  * copy_oldmem_page - copy one page from "oldmem"
  * @pfn: page frame number to be copied
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 2255782e8d4b..b2c97874ec0f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -561,7 +561,13 @@ static void __init reserve_standard_io_resources(void)
 
 }
 
-#ifdef CONFIG_PROC_VMCORE
+/*
+ * Note: elfcorehdr_addr is not just limited to vmcore. It is also used by
+ * is_kdump_kernel() to determine if we are booting after a panic. Hence
+ * ifdef it under CONFIG_CRASH_DUMP and not CONFIG_PROC_VMCORE.
+ */
+
+#ifdef CONFIG_CRASH_DUMP
 /* elfcorehdr= specifies the location of elf core header
  * stored by the crashed kernel. This option will be passed
  * by kexec loader to the capture kernel.
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 841368b87a29..4c65ca432d30 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -32,9 +32,6 @@ static size_t elfcorebuf_sz;
 /* Total size of vmcore file. */
 static u64 vmcore_size;
 
-/* Stores the physical address of elf header of crash image. */
-unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
-
 struct proc_dir_entry *proc_vmcore = NULL;
 
 /* Reads a page from the oldmem device from given offset. */
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 025e4f575103..de027d1db745 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -9,11 +9,7 @@
 
 #define ELFCORE_ADDR_MAX	(-1ULL)
 
-#ifdef CONFIG_PROC_VMCORE
 extern unsigned long long elfcorehdr_addr;
-#else
-static const unsigned long long elfcorehdr_addr = ELFCORE_ADDR_MAX;
-#endif
 
 extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
 						unsigned long, int);
@@ -28,6 +24,16 @@ extern struct proc_dir_entry *proc_vmcore;
 
 #define vmcore_elf_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x))
 
+/*
+ * is_kdump_kernel() checks whether this kernel is booting after a panic of
+ * previous kernel or not. This is determined by checking if previous kernel
+ * has passed the elf core header address on command line.
+ *
+ * This is not just a test if CONFIG_CRASH_DUMP is enabled or not. It will
+ * return 1 if CONFIG_CRASH_DUMP=y and if kernel is booting after a panic of
+ * previous kernel.
+ */
+
 static inline int is_kdump_kernel(void)
 {
 	return (elfcorehdr_addr != ELFCORE_ADDR_MAX) ? 1 : 0;
-- 
cgit v1.2.3


From 85a0ee342e0c06c19d78fdf48307211c6cf18fcb Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@verge.net.au>
Date: Sat, 18 Oct 2008 20:28:29 -0700
Subject: kdump: add is_vmcore_usable() and vmcore_unusable()

The usage of elfcorehdr_addr has changed recently such that being set to
ELFCORE_ADDR_MAX is used by is_kdump_kernel() to indicate if the code is
executing in a kernel executed as a crash kernel.

However, arch/ia64/kernel/setup.c:reserve_elfcorehdr will rest
elfcorehdr_addr to ELFCORE_ADDR_MAX on error, which means any subsequent
calls to is_kdump_kernel() will return 0, even though they should return
1.

Ok, at this point in time there are no subsequent calls, but I think its
fair to say that there is ample scope for error or at the very least
confusion.

This patch add an extra state, ELFCORE_ADDR_ERR, which indicates that
elfcorehdr_addr was passed on the command line, and thus execution is
taking place in a crashdump kernel, but vmcore can't be used for some
reason.  This is tested for using is_vmcore_usable() and set using
vmcore_unusable().  A subsequent patch makes use of this new code.

To summarise, the states that elfcorehdr_addr can now be in are as follows:

ELFCORE_ADDR_MAX: not a crashdump kernel
ELFCORE_ADDR_ERR: crashdump kernel but vmcore is unusable
any other value:  crash dump kernel and vmcore is usable

Signed-off-by: Simon Horman <horms@verge.net.au>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/ia64/kernel/setup.c   |  4 ++--
 fs/proc/vmcore.c           |  2 +-
 include/linux/crash_dump.h | 24 ++++++++++++++++++++++++
 3 files changed, 27 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index a0286be6c235..60286522d54a 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -509,11 +509,11 @@ int __init reserve_elfcorehdr(unsigned long *start, unsigned long *end)
 	 * to work properly.
 	 */
 
-	if (elfcorehdr_addr >= ELFCORE_ADDR_MAX)
+	if (!is_vmcore_usable())
 		return -EINVAL;
 
 	if ((length = vmcore_find_descriptor_size(elfcorehdr_addr)) == 0) {
-		elfcorehdr_addr = ELFCORE_ADDR_MAX;
+		vmcore_unusable();
 		return -EINVAL;
 	}
 
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 4c65ca432d30..cd9ca67f841b 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -644,7 +644,7 @@ static int __init vmcore_init(void)
 	int rc = 0;
 
 	/* If elfcorehdr= has been passed in cmdline, then capture the dump.*/
-	if (!(elfcorehdr_addr < ELFCORE_ADDR_MAX))
+	if (!(is_vmcore_usable()))
 		return rc;
 	rc = parse_crash_elf_headers();
 	if (rc) {
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index de027d1db745..0acf3b737e2e 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -8,6 +8,7 @@
 #include <linux/proc_fs.h>
 
 #define ELFCORE_ADDR_MAX	(-1ULL)
+#define ELFCORE_ADDR_ERR	(-2ULL)
 
 extern unsigned long long elfcorehdr_addr;
 
@@ -38,6 +39,29 @@ static inline int is_kdump_kernel(void)
 {
 	return (elfcorehdr_addr != ELFCORE_ADDR_MAX) ? 1 : 0;
 }
+
+/* is_vmcore_usable() checks if the kernel is booting after a panic and
+ * the vmcore region is usable.
+ *
+ * This makes use of the fact that due to alignment -2ULL is not
+ * a valid pointer, much in the vain of IS_ERR(), except
+ * dealing directly with an unsigned long long rather than a pointer.
+ */
+
+static inline int is_vmcore_usable(void)
+{
+	return is_kdump_kernel() && elfcorehdr_addr != ELFCORE_ADDR_ERR ? 1 : 0;
+}
+
+/* vmcore_unusable() marks the vmcore as unusable,
+ * without disturbing the logic of is_kdump_kernel()
+ */
+
+static inline void vmcore_unusable(void)
+{
+	if (is_kdump_kernel())
+		elfcorehdr_addr = ELFCORE_ADDR_ERR;
+}
 #else /* !CONFIG_CRASH_DUMP */
 static inline int is_kdump_kernel(void) { return 0; }
 #endif /* CONFIG_CRASH_DUMP */
-- 
cgit v1.2.3


From b8e465f4945bc0e9f324e3bbe15f5180a8e9a6fe Mon Sep 17 00:00:00 2001
From: Harvey Harrison <harvey.harrison@gmail.com>
Date: Sat, 18 Oct 2008 20:28:35 -0700
Subject: byteorder: add new headers for make headers-install

Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/Kbuild | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index bf9aca548f14..e531783e5d78 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -183,6 +183,7 @@ unifdef-y += auto_fs.h
 unifdef-y += auxvec.h
 unifdef-y += binfmts.h
 unifdef-y += blktrace_api.h
+unifdef-y += byteorder.h
 unifdef-y += capability.h
 unifdef-y += capi.h
 unifdef-y += cciss_ioctl.h
@@ -340,6 +341,7 @@ unifdef-y += soundcard.h
 unifdef-y += stat.h
 unifdef-y += stddef.h
 unifdef-y += string.h
+unifdef-y += swab.h
 unifdef-y += synclink.h
 unifdef-y += sysctl.h
 unifdef-y += tcp.h
-- 
cgit v1.2.3


From acf0108a84edae22b99655eb2f6f6c9f7ec4d449 Mon Sep 17 00:00:00 2001
From: Harvey Harrison <harvey.harrison@gmail.com>
Date: Sat, 18 Oct 2008 20:28:36 -0700
Subject: byteorder: use generic C version for value byteswapping

This makes the new implementation of the byteorder helpers match the old
in how it degraded when an arch-defined version was not available:

1) swab()
	- look for arch defined
	- if not, use generic c version

2) swabp()
	- look for arch-defined
	- if not, deref pointer and use swab()

3) swabs()
	- look for arch defined
	- if not, use swabp

Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/swab.h | 10 ----------
 1 file changed, 10 deletions(-)

(limited to 'include')

diff --git a/include/linux/swab.h b/include/linux/swab.h
index 270d5c208a89..bbed279f3b32 100644
--- a/include/linux/swab.h
+++ b/include/linux/swab.h
@@ -47,8 +47,6 @@ static inline __attribute_const__ __u16 ___swab16(__u16 val)
 {
 #ifdef __arch_swab16
 	return __arch_swab16(val);
-#elif defined(__arch_swab16p)
-	return __arch_swab16p(&val);
 #else
 	return __const_swab16(val);
 #endif
@@ -58,8 +56,6 @@ static inline __attribute_const__ __u32 ___swab32(__u32 val)
 {
 #ifdef __arch_swab32
 	return __arch_swab32(val);
-#elif defined(__arch_swab32p)
-	return __arch_swab32p(&val);
 #else
 	return __const_swab32(val);
 #endif
@@ -69,8 +65,6 @@ static inline __attribute_const__ __u64 ___swab64(__u64 val)
 {
 #ifdef __arch_swab64
 	return __arch_swab64(val);
-#elif defined(__arch_swab64p)
-	return __arch_swab64p(&val);
 #elif defined(__SWAB_64_THRU_32__)
 	__u32 h = val >> 32;
 	__u32 l = val & ((1ULL << 32) - 1);
@@ -84,8 +78,6 @@ static inline __attribute_const__ __u32 ___swahw32(__u32 val)
 {
 #ifdef __arch_swahw32
 	return __arch_swahw32(val);
-#elif defined(__arch_swahw32p)
-	return __arch_swahw32p(&val);
 #else
 	return __const_swahw32(val);
 #endif
@@ -95,8 +87,6 @@ static inline __attribute_const__ __u32 ___swahb32(__u32 val)
 {
 #ifdef __arch_swahb32
 	return __arch_swahb32(val);
-#elif defined(__arch_swahb32p)
-	return __arch_swahb32p(&val);
 #else
 	return __const_swahb32(val);
 #endif
-- 
cgit v1.2.3


From 1d8cca44b6a244b7e378546d719041819049a0f9 Mon Sep 17 00:00:00 2001
From: Harvey Harrison <harvey.harrison@gmail.com>
Date: Sat, 18 Oct 2008 20:28:37 -0700
Subject: byteorder: provide swabb.h generically in asm/byteorder.h

This is needed during the transition to the new byteorder headers as the
swabb.h functionality will be provided from asm/byteorder.h in the new
version.  To avoid breakage on arches still using the old implementation,
provide swabb.h from asm/byteorder.h as well.

Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/byteorder/Kbuild          | 1 +
 include/linux/byteorder/big_endian.h    | 1 +
 include/linux/byteorder/little_endian.h | 1 +
 3 files changed, 3 insertions(+)

(limited to 'include')

diff --git a/include/linux/byteorder/Kbuild b/include/linux/byteorder/Kbuild
index 1133d5f9d818..fbaa7f9cee32 100644
--- a/include/linux/byteorder/Kbuild
+++ b/include/linux/byteorder/Kbuild
@@ -1,3 +1,4 @@
 unifdef-y += big_endian.h
 unifdef-y += little_endian.h
 unifdef-y += swab.h
+unifdef-y += swabb.h
diff --git a/include/linux/byteorder/big_endian.h b/include/linux/byteorder/big_endian.h
index 44f95b92393b..1cba3f3efe5f 100644
--- a/include/linux/byteorder/big_endian.h
+++ b/include/linux/byteorder/big_endian.h
@@ -10,6 +10,7 @@
 
 #include <linux/types.h>
 #include <linux/byteorder/swab.h>
+#include <linux/byteorder/swabb.h>
 
 #define __constant_htonl(x) ((__force __be32)(__u32)(x))
 #define __constant_ntohl(x) ((__force __u32)(__be32)(x))
diff --git a/include/linux/byteorder/little_endian.h b/include/linux/byteorder/little_endian.h
index 4cc170a31762..cedc1b5a289c 100644
--- a/include/linux/byteorder/little_endian.h
+++ b/include/linux/byteorder/little_endian.h
@@ -10,6 +10,7 @@
 
 #include <linux/types.h>
 #include <linux/byteorder/swab.h>
+#include <linux/byteorder/swabb.h>
 
 #define __constant_htonl(x) ((__force __be32)___constant_swab32((x)))
 #define __constant_ntohl(x) ___constant_swab32((__force __be32)(x))
-- 
cgit v1.2.3


From fdd2e5f88a259a537bb239e0c03c973cb6ea402a Mon Sep 17 00:00:00 2001
From: Adrian Bunk <bunk@kernel.org>
Date: Sat, 18 Oct 2008 20:28:38 -0700
Subject: make mm/rmap.c:anon_vma_cachep static

This patch makes the needlessly global anon_vma_cachep static.

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Hugh Dickins <hugh@veritas.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/rmap.h | 12 ------------
 mm/rmap.c            | 12 +++++++++++-
 2 files changed, 11 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 1da48db8db09..89f0564b10c8 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -39,18 +39,6 @@ struct anon_vma {
 
 #ifdef CONFIG_MMU
 
-extern struct kmem_cache *anon_vma_cachep;
-
-static inline struct anon_vma *anon_vma_alloc(void)
-{
-	return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
-}
-
-static inline void anon_vma_free(struct anon_vma *anon_vma)
-{
-	kmem_cache_free(anon_vma_cachep, anon_vma);
-}
-
 static inline void anon_vma_lock(struct vm_area_struct *vma)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
diff --git a/mm/rmap.c b/mm/rmap.c
index 8701d5fce732..10993942d6c9 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -55,7 +55,17 @@
 
 #include "internal.h"
 
-struct kmem_cache *anon_vma_cachep;
+static struct kmem_cache *anon_vma_cachep;
+
+static inline struct anon_vma *anon_vma_alloc(void)
+{
+	return kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL);
+}
+
+static inline void anon_vma_free(struct anon_vma *anon_vma)
+{
+	kmem_cache_free(anon_vma_cachep, anon_vma);
+}
 
 /**
  * anon_vma_prepare - attach an anon_vma to a memory region
-- 
cgit v1.2.3


From 357c6e63590895dc87cc9300f5a1c27544ea69e8 Mon Sep 17 00:00:00 2001
From: Adrian Bunk <bunk@kernel.org>
Date: Sat, 18 Oct 2008 20:28:42 -0700
Subject: rtc: use bcd2bin/bin2bcd

Change various rtc related code to use the new bcd2bin/bin2bcd functions
instead of the obsolete BCD_TO_BIN/BIN_TO_BCD/BCD2BIN/BIN2BCD macros.

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Acked-by: Alessandro Zummo <a.zummo@towertech.it>
Cc: David Brownell <david-b@pacbell.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/kernel/rtc.c     | 20 ++++++++++----------
 drivers/char/ds1286.c     | 34 +++++++++++++++++-----------------
 drivers/char/ds1302.c     | 24 ++++++++++++------------
 drivers/char/ip27-rtc.c   | 24 ++++++++++++------------
 drivers/char/rtc.c        | 40 ++++++++++++++++++++--------------------
 include/asm-generic/rtc.h | 24 ++++++++++++------------
 6 files changed, 83 insertions(+), 83 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 0a23b5795b25..dd6f2b71561b 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -52,7 +52,7 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 
 	cmos_minutes = CMOS_READ(RTC_MINUTES);
 	if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
-		BCD_TO_BIN(cmos_minutes);
+		cmos_minutes = bcd2bin(cmos_minutes);
 
 	/*
 	 * since we're only adjusting minutes and seconds,
@@ -69,8 +69,8 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 
 	if (abs(real_minutes - cmos_minutes) < 30) {
 		if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-			BIN_TO_BCD(real_seconds);
-			BIN_TO_BCD(real_minutes);
+			real_seconds = bin2bcd(real_seconds);
+			real_minutes = bin2bcd(real_minutes);
 		}
 		CMOS_WRITE(real_seconds,RTC_SECONDS);
 		CMOS_WRITE(real_minutes,RTC_MINUTES);
@@ -124,16 +124,16 @@ unsigned long mach_get_cmos_time(void)
 	WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY));
 
 	if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) {
-		BCD_TO_BIN(sec);
-		BCD_TO_BIN(min);
-		BCD_TO_BIN(hour);
-		BCD_TO_BIN(day);
-		BCD_TO_BIN(mon);
-		BCD_TO_BIN(year);
+		sec = bcd2bin(sec);
+		min = bcd2bin(min);
+		hour = bcd2bin(hour);
+		day = bcd2bin(day);
+		mon = bcd2bin(mon);
+		year = bcd2bin(year);
 	}
 
 	if (century) {
-		BCD_TO_BIN(century);
+		century = bcd2bin(century);
 		year += century * 100;
 		printk(KERN_INFO "Extended CMOS year: %d\n", century * 100);
 	} else
diff --git a/drivers/char/ds1286.c b/drivers/char/ds1286.c
index 5329d482b582..0a826d7be10e 100644
--- a/drivers/char/ds1286.c
+++ b/drivers/char/ds1286.c
@@ -210,8 +210,8 @@ static int ds1286_ioctl(struct inode *inode, struct file *file,
 		if (sec != 0)
 			return -EINVAL;
 
-		min = BIN2BCD(min);
-		min = BIN2BCD(hrs);
+		min = bin2bcd(min);
+		min = bin2bcd(hrs);
 
 		spin_lock(&ds1286_lock);
 		rtc_write(hrs, RTC_HOURS_ALARM);
@@ -353,7 +353,7 @@ static int ds1286_proc_output(char *buf)
 
 	ds1286_get_time(&tm);
 	hundredth = rtc_read(RTC_HUNDREDTH_SECOND);
-	BCD_TO_BIN(hundredth);
+	hundredth = bcd2bin(hundredth);
 
 	p += sprintf(p,
 	             "rtc_time\t: %02d:%02d:%02d.%02d\n"
@@ -477,12 +477,12 @@ static void ds1286_get_time(struct rtc_time *rtc_tm)
 	rtc_write(save_control, RTC_CMD);
 	spin_unlock_irqrestore(&ds1286_lock, flags);
 
-	BCD_TO_BIN(rtc_tm->tm_sec);
-	BCD_TO_BIN(rtc_tm->tm_min);
-	BCD_TO_BIN(rtc_tm->tm_hour);
-	BCD_TO_BIN(rtc_tm->tm_mday);
-	BCD_TO_BIN(rtc_tm->tm_mon);
-	BCD_TO_BIN(rtc_tm->tm_year);
+	rtc_tm->tm_sec = bcd2bin(rtc_tm->tm_sec);
+	rtc_tm->tm_min = bcd2bin(rtc_tm->tm_min);
+	rtc_tm->tm_hour = bcd2bin(rtc_tm->tm_hour);
+	rtc_tm->tm_mday = bcd2bin(rtc_tm->tm_mday);
+	rtc_tm->tm_mon = bcd2bin(rtc_tm->tm_mon);
+	rtc_tm->tm_year = bcd2bin(rtc_tm->tm_year);
 
 	/*
 	 * Account for differences between how the RTC uses the values
@@ -531,12 +531,12 @@ static int ds1286_set_time(struct rtc_time *rtc_tm)
 	if (yrs >= 100)
 		yrs -= 100;
 
-	BIN_TO_BCD(sec);
-	BIN_TO_BCD(min);
-	BIN_TO_BCD(hrs);
-	BIN_TO_BCD(day);
-	BIN_TO_BCD(mon);
-	BIN_TO_BCD(yrs);
+	sec = bin2bcd(sec);
+	min = bin2bcd(min);
+	hrs = bin2bcd(hrs);
+	day = bin2bcd(day);
+	mon = bin2bcd(mon);
+	yrs = bin2bcd(yrs);
 
 	spin_lock_irqsave(&ds1286_lock, flags);
 	save_control = rtc_read(RTC_CMD);
@@ -572,8 +572,8 @@ static void ds1286_get_alm_time(struct rtc_time *alm_tm)
 	cmd = rtc_read(RTC_CMD);
 	spin_unlock_irqrestore(&ds1286_lock, flags);
 
-	BCD_TO_BIN(alm_tm->tm_min);
-	BCD_TO_BIN(alm_tm->tm_hour);
+	alm_tm->tm_min = bcd2bin(alm_tm->tm_min);
+	alm_tm->tm_hour = bcd2bin(alm_tm->tm_hour);
 	alm_tm->tm_sec = 0;
 }
 
diff --git a/drivers/char/ds1302.c b/drivers/char/ds1302.c
index c5e67a623951..170693c93c73 100644
--- a/drivers/char/ds1302.c
+++ b/drivers/char/ds1302.c
@@ -131,12 +131,12 @@ get_rtc_time(struct rtc_time *rtc_tm)
 
 	local_irq_restore(flags);
 
-	BCD_TO_BIN(rtc_tm->tm_sec);
-	BCD_TO_BIN(rtc_tm->tm_min);
-	BCD_TO_BIN(rtc_tm->tm_hour);
-	BCD_TO_BIN(rtc_tm->tm_mday);
-	BCD_TO_BIN(rtc_tm->tm_mon);
-	BCD_TO_BIN(rtc_tm->tm_year);
+	rtc_tm->tm_sec = bcd2bin(rtc_tm->tm_sec);
+	rtc_tm->tm_min = bcd2bin(rtc_tm->tm_min);
+	rtc_tm->tm_hour = bcd2bin(rtc_tm->tm_hour);
+	rtc_tm->tm_mday = bcd2bin(rtc_tm->tm_mday);
+	rtc_tm->tm_mon = bcd2bin(rtc_tm->tm_mon);
+	rtc_tm->tm_year = bcd2bin(rtc_tm->tm_year);
 
 	/*
 	 * Account for differences between how the RTC uses the values
@@ -211,12 +211,12 @@ static long rtc_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 			else
 				yrs -= 1900;	/* RTC (70, 71, ... 99) */
 
-			BIN_TO_BCD(sec);
-			BIN_TO_BCD(min);
-			BIN_TO_BCD(hrs);
-			BIN_TO_BCD(day);
-			BIN_TO_BCD(mon);
-			BIN_TO_BCD(yrs);
+			sec = bin2bcd(sec);
+			min = bin2bcd(min);
+			hrs = bin2bcd(hrs);
+			day = bin2bcd(day);
+			mon = bin2bcd(mon);
+			yrs = bin2bcd(yrs);
 
 			lock_kernel();
 			local_irq_save(flags);
diff --git a/drivers/char/ip27-rtc.c b/drivers/char/ip27-rtc.c
index ec9d0443d92c..2abd881b4cbc 100644
--- a/drivers/char/ip27-rtc.c
+++ b/drivers/char/ip27-rtc.c
@@ -130,12 +130,12 @@ static long rtc_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		if (yrs >= 100)
 			yrs -= 100;
 
-		sec = BIN2BCD(sec);
-		min = BIN2BCD(min);
-		hrs = BIN2BCD(hrs);
-		day = BIN2BCD(day);
-		mon = BIN2BCD(mon);
-		yrs = BIN2BCD(yrs);
+		sec = bin2bcd(sec);
+		min = bin2bcd(min);
+		hrs = bin2bcd(hrs);
+		day = bin2bcd(day);
+		mon = bin2bcd(mon);
+		yrs = bin2bcd(yrs);
 
 		spin_lock_irq(&rtc_lock);
 		rtc->control |= M48T35_RTC_SET;
@@ -311,12 +311,12 @@ static void get_rtc_time(struct rtc_time *rtc_tm)
 	rtc->control &= ~M48T35_RTC_READ;
 	spin_unlock_irq(&rtc_lock);
 
-	rtc_tm->tm_sec = BCD2BIN(rtc_tm->tm_sec);
-	rtc_tm->tm_min = BCD2BIN(rtc_tm->tm_min);
-	rtc_tm->tm_hour = BCD2BIN(rtc_tm->tm_hour);
-	rtc_tm->tm_mday = BCD2BIN(rtc_tm->tm_mday);
-	rtc_tm->tm_mon = BCD2BIN(rtc_tm->tm_mon);
-	rtc_tm->tm_year = BCD2BIN(rtc_tm->tm_year);
+	rtc_tm->tm_sec = bcd2bin(rtc_tm->tm_sec);
+	rtc_tm->tm_min = bcd2bin(rtc_tm->tm_min);
+	rtc_tm->tm_hour = bcd2bin(rtc_tm->tm_hour);
+	rtc_tm->tm_mday = bcd2bin(rtc_tm->tm_mday);
+	rtc_tm->tm_mon = bcd2bin(rtc_tm->tm_mon);
+	rtc_tm->tm_year = bcd2bin(rtc_tm->tm_year);
 
 	/*
 	 * Account for differences between how the RTC uses the values
diff --git a/drivers/char/rtc.c b/drivers/char/rtc.c
index 17683de95717..32dc89720d58 100644
--- a/drivers/char/rtc.c
+++ b/drivers/char/rtc.c
@@ -518,17 +518,17 @@ static int rtc_do_ioctl(unsigned int cmd, unsigned long arg, int kernel)
 		if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY) ||
 							RTC_ALWAYS_BCD) {
 			if (sec < 60)
-				BIN_TO_BCD(sec);
+				sec = bin2bcd(sec);
 			else
 				sec = 0xff;
 
 			if (min < 60)
-				BIN_TO_BCD(min);
+				min = bin2bcd(min);
 			else
 				min = 0xff;
 
 			if (hrs < 24)
-				BIN_TO_BCD(hrs);
+				hrs = bin2bcd(hrs);
 			else
 				hrs = 0xff;
 		}
@@ -614,12 +614,12 @@ static int rtc_do_ioctl(unsigned int cmd, unsigned long arg, int kernel)
 
 		if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY)
 		    || RTC_ALWAYS_BCD) {
-			BIN_TO_BCD(sec);
-			BIN_TO_BCD(min);
-			BIN_TO_BCD(hrs);
-			BIN_TO_BCD(day);
-			BIN_TO_BCD(mon);
-			BIN_TO_BCD(yrs);
+			sec = bin2bcd(sec);
+			min = bin2bcd(min);
+			hrs = bin2bcd(hrs);
+			day = bin2bcd(day);
+			mon = bin2bcd(mon);
+			yrs = bin2bcd(yrs);
 		}
 
 		save_control = CMOS_READ(RTC_CONTROL);
@@ -1099,7 +1099,7 @@ no_irq:
 	spin_unlock_irq(&rtc_lock);
 
 	if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
-		BCD_TO_BIN(year);       /* This should never happen... */
+		year = bcd2bin(year);       /* This should never happen... */
 
 	if (year < 20) {
 		epoch = 2000;
@@ -1352,13 +1352,13 @@ static void rtc_get_rtc_time(struct rtc_time *rtc_tm)
 	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-		BCD_TO_BIN(rtc_tm->tm_sec);
-		BCD_TO_BIN(rtc_tm->tm_min);
-		BCD_TO_BIN(rtc_tm->tm_hour);
-		BCD_TO_BIN(rtc_tm->tm_mday);
-		BCD_TO_BIN(rtc_tm->tm_mon);
-		BCD_TO_BIN(rtc_tm->tm_year);
-		BCD_TO_BIN(rtc_tm->tm_wday);
+		rtc_tm->tm_sec = bcd2bin(rtc_tm->tm_sec);
+		rtc_tm->tm_min = bcd2bin(rtc_tm->tm_min);
+		rtc_tm->tm_hour = bcd2bin(rtc_tm->tm_hour);
+		rtc_tm->tm_mday = bcd2bin(rtc_tm->tm_mday);
+		rtc_tm->tm_mon = bcd2bin(rtc_tm->tm_mon);
+		rtc_tm->tm_year = bcd2bin(rtc_tm->tm_year);
+		rtc_tm->tm_wday = bcd2bin(rtc_tm->tm_wday);
 	}
 
 #ifdef CONFIG_MACH_DECSTATION
@@ -1392,9 +1392,9 @@ static void get_rtc_alm_time(struct rtc_time *alm_tm)
 	spin_unlock_irq(&rtc_lock);
 
 	if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD) {
-		BCD_TO_BIN(alm_tm->tm_sec);
-		BCD_TO_BIN(alm_tm->tm_min);
-		BCD_TO_BIN(alm_tm->tm_hour);
+		alm_tm->tm_sec = bcd2bin(alm_tm->tm_sec);
+		alm_tm->tm_min = bcd2bin(alm_tm->tm_min);
+		alm_tm->tm_hour = bcd2bin(alm_tm->tm_hour);
 	}
 }
 
diff --git a/include/asm-generic/rtc.h b/include/asm-generic/rtc.h
index 71ef3f0b9685..89061c1a67d4 100644
--- a/include/asm-generic/rtc.h
+++ b/include/asm-generic/rtc.h
@@ -84,12 +84,12 @@ static inline unsigned int get_rtc_time(struct rtc_time *time)
 
 	if (!(ctrl & RTC_DM_BINARY) || RTC_ALWAYS_BCD)
 	{
-		BCD_TO_BIN(time->tm_sec);
-		BCD_TO_BIN(time->tm_min);
-		BCD_TO_BIN(time->tm_hour);
-		BCD_TO_BIN(time->tm_mday);
-		BCD_TO_BIN(time->tm_mon);
-		BCD_TO_BIN(time->tm_year);
+		time->tm_sec = bcd2bin(time->tm_sec);
+		time->tm_min = bcd2bin(time->tm_min);
+		time->tm_hour = bcd2bin(time->tm_hour);
+		time->tm_mday = bcd2bin(time->tm_mday);
+		time->tm_mon = bcd2bin(time->tm_mon);
+		time->tm_year = bcd2bin(time->tm_year);
 	}
 
 #ifdef CONFIG_MACH_DECSTATION
@@ -159,12 +159,12 @@ static inline int set_rtc_time(struct rtc_time *time)
 
 	if (!(CMOS_READ(RTC_CONTROL) & RTC_DM_BINARY)
 	    || RTC_ALWAYS_BCD) {
-		BIN_TO_BCD(sec);
-		BIN_TO_BCD(min);
-		BIN_TO_BCD(hrs);
-		BIN_TO_BCD(day);
-		BIN_TO_BCD(mon);
-		BIN_TO_BCD(yrs);
+		sec = bin2bcd(sec);
+		min = bin2bcd(min);
+		hrs = bin2bcd(hrs);
+		day = bin2bcd(day);
+		mon = bin2bcd(mon);
+		yrs = bin2bcd(yrs);
 	}
 
 	save_control = CMOS_READ(RTC_CONTROL);
-- 
cgit v1.2.3


From a0098efd6ee4e8c04d82d761aa1bb9ec7a0aa32d Mon Sep 17 00:00:00 2001
From: Adrian Bunk <bunk@kernel.org>
Date: Sat, 18 Oct 2008 20:28:47 -0700
Subject: remove the obsolete BCD*BIN/BIN*BCD macros

Remove the following obsolete macros:

- BCD2BIN
- BIN2BCD
- BCD_TO_BIN
- BIN_TO_BCD

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bcd.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/bcd.h b/include/linux/bcd.h
index 7ac518e3c152..75f6d6e699a0 100644
--- a/include/linux/bcd.h
+++ b/include/linux/bcd.h
@@ -15,11 +15,4 @@
 unsigned bcd2bin(unsigned char val) __attribute_const__;
 unsigned char bin2bcd(unsigned val) __attribute_const__;
 
-#define BCD2BIN(val)	bcd2bin(val)
-#define BIN2BCD(val)	bin2bcd(val)
-
-/* backwards compat */
-#define BCD_TO_BIN(val) ((val)=BCD2BIN(val))
-#define BIN_TO_BCD(val) ((val)=BIN2BCD(val))
-
 #endif /* _BCD_H */
-- 
cgit v1.2.3


From 5a85a7dda15f88b7f9c96c67fe826b5d0486d601 Mon Sep 17 00:00:00 2001
From: Adrian Bunk <bunk@kernel.org>
Date: Sat, 18 Oct 2008 20:28:48 -0700
Subject: include/linux/bcd.h: remove comments

- the macros are gone
- there's no more code in this file,
  LGPL + GPL = GPL,
  and the code that was moved to lib/bcd.c is anyway trivial

Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/bcd.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/bcd.h b/include/linux/bcd.h
index 75f6d6e699a0..22ea563ba3eb 100644
--- a/include/linux/bcd.h
+++ b/include/linux/bcd.h
@@ -1,12 +1,3 @@
-/* Permission is hereby granted to copy, modify and redistribute this code
- * in terms of the GNU Library General Public License, Version 2 or later,
- * at your option.
- */
-
-/* macros to translate to/from binary and binary-coded decimal (frequently
- * found in RTC chips).
- */
-
 #ifndef _BCD_H
 #define _BCD_H
 
-- 
cgit v1.2.3


From 01e8ef11bc1a74e65678ed55795f59266d4add01 Mon Sep 17 00:00:00 2001
From: Parag Warudkar <parag.lkml@gmail.com>
Date: Sat, 18 Oct 2008 20:28:50 -0700
Subject: x86: sysfs: kill owner field from attribute

Tejun's commit 7b595756ec1f49e0049a9e01a1298d53a7faaa15 made sysfs
attribute->owner unnecessary.  But the field was left in the structure to
ease the merge.  It's been over a year since that change and it is now
time to start killing attribute->owner along with its users - one arch at
a time!

This patch is attempt #1 to get rid of attribute->owner only for
CONFIG_X86_64 or CONFIG_X86_32 .  We will deal with other arches later on
as and when possible - avr32 will be the next since that is something I
can test.  Compile (make allyesconfig / make allmodconfig / custom config)
and boot tested.

akpm: the idea is that we put the declaration of sttribute.owner inside
`#ifndef CONFIG_X86'.  But that proved to be too ambitious for now because
new usages kept on turning up in subsystem trees.

[akpm: remove the ifdef for now]
Signed-off-by: Parag Warudkar <parag.lkml@gmail.com>
Cc: Greg KH <greg@kroah.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Tejun Heo <htejun@gmail.com>
Cc: Len Brown <lenb@kernel.org>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Jean Delvare <khali@linux-fr.org>
Cc: Roland Dreier <rolandd@cisco.com>
Cc: David Brownell <david-b@pacbell.net>
Cc: Alessandro Zummo <a.zummo@towertech.it>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/acpi/battery.c              | 2 +-
 drivers/acpi/sbs.c                  | 2 +-
 drivers/acpi/system.c               | 1 -
 drivers/block/aoe/aoeblk.c          | 2 +-
 drivers/block/nbd.c                 | 2 +-
 drivers/firmware/iscsi_ibft.c       | 1 -
 drivers/i2c/chips/at24.c            | 1 -
 drivers/i2c/chips/ds1682.c          | 1 -
 drivers/infiniband/core/cm.c        | 2 +-
 drivers/memstick/core/mspro_block.c | 1 -
 drivers/power/power_supply_sysfs.c  | 2 +-
 drivers/rtc/rtc-cmos.c              | 1 -
 drivers/rtc/rtc-ds1305.c            | 1 -
 drivers/rtc/rtc-ds1307.c            | 1 -
 drivers/rtc/rtc-ds1511.c            | 1 -
 drivers/rtc/rtc-m48t59.c            | 1 -
 drivers/rtc/rtc-stk17ta8.c          | 1 -
 drivers/scsi/arcmsr/arcmsr_attr.c   | 3 ---
 drivers/w1/slaves/w1_ds2760.c       | 1 -
 include/linux/sysfs.h               | 5 +++--
 20 files changed, 9 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index b1c723f9f58d..70f7f60929ca 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -431,7 +431,7 @@ static ssize_t acpi_battery_alarm_store(struct device *dev,
 }
 
 static struct device_attribute alarm_attr = {
-	.attr = {.name = "alarm", .mode = 0644, .owner = THIS_MODULE},
+	.attr = {.name = "alarm", .mode = 0644},
 	.show = acpi_battery_alarm_show,
 	.store = acpi_battery_alarm_store,
 };
diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
index 10a36512647c..7b011e7e29fe 100644
--- a/drivers/acpi/sbs.c
+++ b/drivers/acpi/sbs.c
@@ -463,7 +463,7 @@ static ssize_t acpi_battery_alarm_store(struct device *dev,
 }
 
 static struct device_attribute alarm_attr = {
-	.attr = {.name = "alarm", .mode = 0644, .owner = THIS_MODULE},
+	.attr = {.name = "alarm", .mode = 0644},
 	.show = acpi_battery_alarm_show,
 	.store = acpi_battery_alarm_store,
 };
diff --git a/drivers/acpi/system.c b/drivers/acpi/system.c
index 91dec448b3ed..24e80fd927e2 100644
--- a/drivers/acpi/system.c
+++ b/drivers/acpi/system.c
@@ -115,7 +115,6 @@ static void acpi_table_attr_init(struct acpi_table_attr *table_attr,
 	table_attr->attr.read = acpi_table_show;
 	table_attr->attr.attr.name = table_attr->name;
 	table_attr->attr.attr.mode = 0444;
-	table_attr->attr.attr.owner = THIS_MODULE;
 
 	return;
 }
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index b82654e883a7..d876ad861237 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -90,7 +90,7 @@ static DEVICE_ATTR(state, S_IRUGO, aoedisk_show_state, NULL);
 static DEVICE_ATTR(mac, S_IRUGO, aoedisk_show_mac, NULL);
 static DEVICE_ATTR(netif, S_IRUGO, aoedisk_show_netif, NULL);
 static struct device_attribute dev_attr_firmware_version = {
-	.attr = { .name = "firmware-version", .mode = S_IRUGO, .owner = THIS_MODULE },
+	.attr = { .name = "firmware-version", .mode = S_IRUGO },
 	.show = aoedisk_show_fwver,
 };
 
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 7b3351260d56..9034ca585afd 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -391,7 +391,7 @@ static ssize_t pid_show(struct device *dev,
 }
 
 static struct device_attribute pid_attr = {
-	.attr = { .name = "pid", .mode = S_IRUGO, .owner = THIS_MODULE },
+	.attr = { .name = "pid", .mode = S_IRUGO},
 	.show = pid_show,
 };
 
diff --git a/drivers/firmware/iscsi_ibft.c b/drivers/firmware/iscsi_ibft.c
index deb154aa47c4..4353414a0b77 100644
--- a/drivers/firmware/iscsi_ibft.c
+++ b/drivers/firmware/iscsi_ibft.c
@@ -732,7 +732,6 @@ static int __init ibft_create_attribute(struct ibft_kobject *kobj_data,
 
 	attr->attr.name = name;
 	attr->attr.mode = S_IRUSR;
-	attr->attr.owner = THIS_MODULE;
 
 	attr->hdr = hdr;
 	attr->show = show;
diff --git a/drivers/i2c/chips/at24.c b/drivers/i2c/chips/at24.c
index 2a4acb269569..d4775528abc6 100644
--- a/drivers/i2c/chips/at24.c
+++ b/drivers/i2c/chips/at24.c
@@ -460,7 +460,6 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	 */
 	at24->bin.attr.name = "eeprom";
 	at24->bin.attr.mode = chip.flags & AT24_FLAG_IRUGO ? S_IRUGO : S_IRUSR;
-	at24->bin.attr.owner = THIS_MODULE;
 	at24->bin.read = at24_bin_read;
 	at24->bin.size = chip.byte_len;
 
diff --git a/drivers/i2c/chips/ds1682.c b/drivers/i2c/chips/ds1682.c
index 23be4d42cb02..f3ee4a1abb77 100644
--- a/drivers/i2c/chips/ds1682.c
+++ b/drivers/i2c/chips/ds1682.c
@@ -190,7 +190,6 @@ static struct bin_attribute ds1682_eeprom_attr = {
 	.attr = {
 		.name = "eeprom",
 		.mode = S_IRUGO | S_IWUSR,
-		.owner = THIS_MODULE,
 	},
 	.size = DS1682_EEPROM_SIZE,
 	.read = ds1682_eeprom_read,
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index a78d35aecee3..f1e82a92e61e 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -122,7 +122,7 @@ struct cm_counter_attribute {
 
 #define CM_COUNTER_ATTR(_name, _index) \
 struct cm_counter_attribute cm_##_name##_counter_attr = { \
-	.attr = { .name = __stringify(_name), .mode = 0444, .owner = THIS_MODULE }, \
+	.attr = { .name = __stringify(_name), .mode = 0444 }, \
 	.index = _index \
 }
 
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index 6e291bf8237a..5263913e0c69 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -1044,7 +1044,6 @@ static int mspro_block_read_attributes(struct memstick_dev *card)
 
 		s_attr->dev_attr.attr.name = s_attr->name;
 		s_attr->dev_attr.attr.mode = S_IRUGO;
-		s_attr->dev_attr.attr.owner = THIS_MODULE;
 		s_attr->dev_attr.show = mspro_block_attr_show(s_attr->id);
 
 		if (!rc)
diff --git a/drivers/power/power_supply_sysfs.c b/drivers/power/power_supply_sysfs.c
index fe2aeb11939b..23ae8460f5c1 100644
--- a/drivers/power/power_supply_sysfs.c
+++ b/drivers/power/power_supply_sysfs.c
@@ -30,7 +30,7 @@
 
 #define POWER_SUPPLY_ATTR(_name)					\
 {									\
-	.attr = { .name = #_name, .mode = 0444, .owner = THIS_MODULE },	\
+	.attr = { .name = #_name, .mode = 0444 },	\
 	.show = power_supply_show_property,				\
 	.store = NULL,							\
 }
diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
index 957365e4a746..5549231179a2 100644
--- a/drivers/rtc/rtc-cmos.c
+++ b/drivers/rtc/rtc-cmos.c
@@ -592,7 +592,6 @@ static struct bin_attribute nvram = {
 	.attr = {
 		.name	= "nvram",
 		.mode	= S_IRUGO | S_IWUSR,
-		.owner	= THIS_MODULE,
 	},
 
 	.read	= cmos_nvram_read,
diff --git a/drivers/rtc/rtc-ds1305.c b/drivers/rtc/rtc-ds1305.c
index 57b470f3fc0b..fc372df6534b 100644
--- a/drivers/rtc/rtc-ds1305.c
+++ b/drivers/rtc/rtc-ds1305.c
@@ -606,7 +606,6 @@ ds1305_nvram_write(struct kobject *kobj, struct bin_attribute *attr,
 static struct bin_attribute nvram = {
 	.attr.name	= "nvram",
 	.attr.mode	= S_IRUGO | S_IWUSR,
-	.attr.owner	= THIS_MODULE,
 	.read		= ds1305_nvram_read,
 	.write		= ds1305_nvram_write,
 	.size		= DS1305_NVRAM_LEN,
diff --git a/drivers/rtc/rtc-ds1307.c b/drivers/rtc/rtc-ds1307.c
index cad23bcfebd4..162330b9d1dc 100644
--- a/drivers/rtc/rtc-ds1307.c
+++ b/drivers/rtc/rtc-ds1307.c
@@ -551,7 +551,6 @@ static struct bin_attribute nvram = {
 	.attr = {
 		.name	= "nvram",
 		.mode	= S_IRUGO | S_IWUSR,
-		.owner	= THIS_MODULE,
 	},
 
 	.read	= ds1307_nvram_read,
diff --git a/drivers/rtc/rtc-ds1511.c b/drivers/rtc/rtc-ds1511.c
index 7bb0a962ad21..25caada78398 100644
--- a/drivers/rtc/rtc-ds1511.c
+++ b/drivers/rtc/rtc-ds1511.c
@@ -481,7 +481,6 @@ static struct bin_attribute ds1511_nvram_attr = {
 	.attr = {
 		.name = "nvram",
 		.mode = S_IRUGO | S_IWUGO,
-		.owner = THIS_MODULE,
 	},
 	.size = DS1511_RAM_MAX,
 	.read = ds1511_nvram_read,
diff --git a/drivers/rtc/rtc-m48t59.c b/drivers/rtc/rtc-m48t59.c
index ed671e29e07d..04b63dab6932 100644
--- a/drivers/rtc/rtc-m48t59.c
+++ b/drivers/rtc/rtc-m48t59.c
@@ -360,7 +360,6 @@ static struct bin_attribute m48t59_nvram_attr = {
 	.attr = {
 		.name = "nvram",
 		.mode = S_IRUGO | S_IWUSR,
-		.owner = THIS_MODULE,
 	},
 	.read = m48t59_nvram_read,
 	.write = m48t59_nvram_write,
diff --git a/drivers/rtc/rtc-stk17ta8.c b/drivers/rtc/rtc-stk17ta8.c
index 0947f8c23957..f4cd46e15af9 100644
--- a/drivers/rtc/rtc-stk17ta8.c
+++ b/drivers/rtc/rtc-stk17ta8.c
@@ -280,7 +280,6 @@ static struct bin_attribute stk17ta8_nvram_attr = {
 	.attr = {
 		.name = "nvram",
 		.mode = S_IRUGO | S_IWUSR,
-		.owner = THIS_MODULE,
 	},
 	.size = RTC_OFFSET,
 	.read = stk17ta8_nvram_read,
diff --git a/drivers/scsi/arcmsr/arcmsr_attr.c b/drivers/scsi/arcmsr/arcmsr_attr.c
index 69f8346aa288..5877f29a6005 100644
--- a/drivers/scsi/arcmsr/arcmsr_attr.c
+++ b/drivers/scsi/arcmsr/arcmsr_attr.c
@@ -189,7 +189,6 @@ static struct bin_attribute arcmsr_sysfs_message_read_attr = {
 	.attr = {
 		.name = "mu_read",
 		.mode = S_IRUSR ,
-		.owner = THIS_MODULE,
 	},
 	.size = 1032,
 	.read = arcmsr_sysfs_iop_message_read,
@@ -199,7 +198,6 @@ static struct bin_attribute arcmsr_sysfs_message_write_attr = {
 	.attr = {
 		.name = "mu_write",
 		.mode = S_IWUSR,
-		.owner = THIS_MODULE,
 	},
 	.size = 1032,
 	.write = arcmsr_sysfs_iop_message_write,
@@ -209,7 +207,6 @@ static struct bin_attribute arcmsr_sysfs_message_clear_attr = {
 	.attr = {
 		.name = "mu_clear",
 		.mode = S_IWUSR,
-		.owner = THIS_MODULE,
 	},
 	.size = 1,
 	.write = arcmsr_sysfs_iop_message_clear,
diff --git a/drivers/w1/slaves/w1_ds2760.c b/drivers/w1/slaves/w1_ds2760.c
index ed6b0576208c..1f09d4e4144c 100644
--- a/drivers/w1/slaves/w1_ds2760.c
+++ b/drivers/w1/slaves/w1_ds2760.c
@@ -80,7 +80,6 @@ static struct bin_attribute w1_ds2760_bin_attr = {
 	.attr = {
 		.name = "w1_slave",
 		.mode = S_IRUGO,
-		.owner = THIS_MODULE,
 	},
 	.size = DS2760_DATA_SIZE,
 	.read = w1_ds2760_read_bin,
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index b330e289d71f..9d68fed50f11 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -21,8 +21,9 @@ struct kobject;
 struct module;
 
 /* FIXME
- * The *owner field is no longer used, but leave around
- * until the tree gets cleaned up fully.
+ * The *owner field is no longer used.
+ * x86 tree has been cleaned up. The owner
+ * attribute is still left for other arches.
  */
 struct attribute {
 	const char		*name;
-- 
cgit v1.2.3


From edbc25caaa492a82e19baa915f1f6b0a0db6554d Mon Sep 17 00:00:00 2001
From: Milton Miller <miltonm@bga.com>
Date: Thu, 10 Jul 2008 16:29:37 -0500
Subject: PCI: remove dynids.use_driver_data

The driver flag dynids.use_driver_data is almost consistently not set,
and causes more problems than it solves.  It was initially intended as a
flag to indicate whether a driver's usage of driver_data had been
carefully inspected and was ready for values from userspace.  That audit
was never done, so most drivers just get a 0 for driver_data when new
IDs are added from userspace via sysfs.  So remove the flag, allowing
drivers to see the data directly (a followon patch validates the passed
driver_data value against what the drivers expect).

Acked-by: Greg Kroah-Hartman <gregkh@suse.de>
Acked-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/i2c/busses/i2c-amd756.c | 1 -
 drivers/i2c/busses/i2c-viapro.c | 1 -
 drivers/pci/pci-driver.c        | 3 +--
 drivers/scsi/ipr.c              | 1 -
 include/linux/pci.h             | 1 -
 5 files changed, 1 insertion(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/i2c/busses/i2c-amd756.c b/drivers/i2c/busses/i2c-amd756.c
index 1ea39254dac6..a3542b053c8e 100644
--- a/drivers/i2c/busses/i2c-amd756.c
+++ b/drivers/i2c/busses/i2c-amd756.c
@@ -412,7 +412,6 @@ static struct pci_driver amd756_driver = {
 	.id_table	= amd756_ids,
 	.probe		= amd756_probe,
 	.remove		= __devexit_p(amd756_remove),
-	.dynids.use_driver_data = 1,
 };
 
 static int __init amd756_init(void)
diff --git a/drivers/i2c/busses/i2c-viapro.c b/drivers/i2c/busses/i2c-viapro.c
index 73dc52e114eb..2324780484c0 100644
--- a/drivers/i2c/busses/i2c-viapro.c
+++ b/drivers/i2c/busses/i2c-viapro.c
@@ -483,7 +483,6 @@ static struct pci_driver vt596_driver = {
 	.name		= "vt596_smbus",
 	.id_table	= vt596_ids,
 	.probe		= vt596_probe,
-	.dynids.use_driver_data = 1,
 };
 
 static int __init i2c_vt596_init(void)
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index a13f53486114..4940a53c56a3 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -65,8 +65,7 @@ store_new_id(struct device_driver *driver, const char *buf, size_t count)
 	dynid->id.subdevice = subdevice;
 	dynid->id.class = class;
 	dynid->id.class_mask = class_mask;
-	dynid->id.driver_data = pdrv->dynids.use_driver_data ?
-		driver_data : 0UL;
+	dynid->id.driver_data = driver_data;
 
 	spin_lock(&pdrv->dynids.lock);
 	list_add_tail(&dynid->node, &pdrv->dynids.list);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index d30eb7ba018e..098739deb02e 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -7859,7 +7859,6 @@ static struct pci_driver ipr_driver = {
 	.remove = ipr_remove,
 	.shutdown = ipr_shutdown,
 	.err_handler = &ipr_err_handler,
-	.dynids.use_driver_data = 1
 };
 
 /**
diff --git a/include/linux/pci.h b/include/linux/pci.h
index acf8f24037cd..c989f58d09bf 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -347,7 +347,6 @@ struct pci_bus_region {
 struct pci_dynids {
 	spinlock_t lock;            /* protects list, index */
 	struct list_head list;      /* for IDs added at runtime */
-	unsigned int use_driver_data:1; /* pci_device_id->driver_data is used */
 };
 
 /* ---------------------------------------------------------------- */
-- 
cgit v1.2.3


From 0235c4fc7fc6f621dc0dd89eba102ad5aa373390 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rjw@sisk.pl>
Date: Mon, 18 Aug 2008 21:38:00 +0200
Subject: PCI PM: Introduce function pci_wake_from_d3

Many device drivers use the following sequence of statements to enable
the device to wake up the system while being in the D3_hot or D3_cold
low power state:

        pci_enable_wake(pdev, PCI_D3hot, 1);
        pci_enable_wake(pdev, PCI_D3cold, 1);

However, the second call is not necessary if the first one succeeds (the
ordering of the statements above doesn't matter here) and it may even be
harmful, because we are not supposed to enable PME# after the wake-up
power has been enabled for the device.

To allow drivers to overcome this problem, introduce function
pci_wake_from_d3() that will enable the device to wake up the system
from any of D3_hot and D3_cold as long as the wake-up from at least one
of them is supported.

Acked-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/pci/pci.c   | 22 ++++++++++++++++++++++
 include/linux/pci.h |  1 +
 2 files changed, 23 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index dbe9f39f4436..2797112c9400 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1126,6 +1126,27 @@ int pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable)
 	return pme_done ? 0 : error;
 }
 
+/**
+ * pci_wake_from_d3 - enable/disable device to wake up from D3_hot or D3_cold
+ * @dev: PCI device to prepare
+ * @enable: True to enable wake-up event generation; false to disable
+ *
+ * Many drivers want the device to wake up the system from D3_hot or D3_cold
+ * and this function allows them to set that up cleanly - pci_enable_wake()
+ * should not be called twice in a row to enable wake-up due to PCI PM vs ACPI
+ * ordering constraints.
+ *
+ * This function only returns error code if the device is not capable of
+ * generating PME# from both D3_hot and D3_cold, and the platform is unable to
+ * enable wake-up power for it.
+ */
+int pci_wake_from_d3(struct pci_dev *dev, bool enable)
+{
+	return pci_pme_capable(dev, PCI_D3cold) ?
+			pci_enable_wake(dev, PCI_D3cold, enable) :
+			pci_enable_wake(dev, PCI_D3hot, enable);
+}
+
 /**
  * pci_target_state - find an appropriate low power state for a given PCI dev
  * @dev: PCI device
@@ -1942,6 +1963,7 @@ EXPORT_SYMBOL(pci_restore_state);
 EXPORT_SYMBOL(pci_pme_capable);
 EXPORT_SYMBOL(pci_pme_active);
 EXPORT_SYMBOL(pci_enable_wake);
+EXPORT_SYMBOL(pci_wake_from_d3);
 EXPORT_SYMBOL(pci_target_state);
 EXPORT_SYMBOL(pci_prepare_to_sleep);
 EXPORT_SYMBOL(pci_back_from_sleep);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index c989f58d09bf..f7e7dbc09194 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -644,6 +644,7 @@ pci_power_t pci_choose_state(struct pci_dev *dev, pm_message_t state);
 bool pci_pme_capable(struct pci_dev *dev, pci_power_t state);
 void pci_pme_active(struct pci_dev *dev, bool enable);
 int pci_enable_wake(struct pci_dev *dev, pci_power_t state, int enable);
+int pci_wake_from_d3(struct pci_dev *dev, bool enable);
 pci_power_t pci_target_state(struct pci_dev *dev);
 int pci_prepare_to_sleep(struct pci_dev *dev);
 int pci_back_from_sleep(struct pci_dev *dev);
-- 
cgit v1.2.3


From 16dbef4a831782466b10d4ae56837c5ba17d1948 Mon Sep 17 00:00:00 2001
From: Yinghai Lu <yhlu.kernel@gmail.com>
Date: Fri, 15 Aug 2008 19:36:45 -0700
Subject: PCI: change MSI-x vector to 32bit

We are using 28bit pci (bus/dev/fn + 12 bits) as irq number, so the
cache for irq number should be 32 bit too.

Signed-off-by: Yinghai Lu <yhlu.kernel@gmail.com>
Cc: Andrew Vasquez <andrew.vasquez@qlogic.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/scsi/qla2xxx/qla_def.h | 2 +-
 include/linux/pci.h            | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 83c819216771..f25f41a499e5 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -2108,7 +2108,7 @@ struct scsi_qla_host;
 
 struct qla_msix_entry {
 	int have_irq;
-	uint16_t msix_vector;
+	uint32_t msix_vector;
 	uint16_t msix_entry;
 };
 
diff --git a/include/linux/pci.h b/include/linux/pci.h
index f7e7dbc09194..8a4d0bebc311 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -725,7 +725,7 @@ enum pci_dma_burst_strategy {
 };
 
 struct msix_entry {
-	u16 	vector;	/* kernel uses to write allocated vector */
+	u32	vector;	/* kernel uses to write allocated vector */
 	u16	entry;	/* driver uses to specify entry, OS writes */
 };
 
-- 
cgit v1.2.3


From 37a84ec668ba251ae02cf2c2c664baf6b247ae1f Mon Sep 17 00:00:00 2001
From: Seth Heasley <seth.heasley@intel.com>
Date: Thu, 28 Aug 2008 15:40:59 -0700
Subject: x86/PCI: irq and pci_ids patch for Intel Ibex Peak DeviceIDs

This patch updates the Intel Ibex Peak (PCH) LPC and SMBus Controller
DeviceIDs.

The LPC Controller ID is set by Firmware within the range of
0x3b00-3b1f.  This range is included in pci_ids.h using min and max
values, and irq.c now has code to handle the range (in lieu of 32
additions to a SWITCH statement).

The SMBus Controller ID is a fixed-value and will not change.

Signed-off-by: Seth Heasley <seth.heasley@intel.com>
Acked-by: Jean Delvare <khali@linux-fr.org>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 arch/x86/pci/irq.c      | 11 +++++++++--
 include/linux/pci_ids.h |  6 +++---
 2 files changed, 12 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/x86/pci/irq.c b/arch/x86/pci/irq.c
index 52a1de1128c1..bf69dbe08bff 100644
--- a/arch/x86/pci/irq.c
+++ b/arch/x86/pci/irq.c
@@ -590,13 +590,20 @@ static __init int intel_router_probe(struct irq_router *r, struct pci_dev *route
 	case PCI_DEVICE_ID_INTEL_ICH10_1:
 	case PCI_DEVICE_ID_INTEL_ICH10_2:
 	case PCI_DEVICE_ID_INTEL_ICH10_3:
-	case PCI_DEVICE_ID_INTEL_PCH_0:
-	case PCI_DEVICE_ID_INTEL_PCH_1:
 		r->name = "PIIX/ICH";
 		r->get = pirq_piix_get;
 		r->set = pirq_piix_set;
 		return 1;
 	}
+
+	if ((device >= PCI_DEVICE_ID_INTEL_PCH_LPC_MIN) && 
+		(device <= PCI_DEVICE_ID_INTEL_PCH_LPC_MAX)) {
+		r->name = "PIIX/ICH";
+		r->get = pirq_piix_get;
+		r->set = pirq_piix_set;
+		return 1;
+	}
+
 	return 0;
 }
 
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 8edddc240e4f..e5d344bfcb7e 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2454,9 +2454,9 @@
 #define PCI_DEVICE_ID_INTEL_ICH10_3	0x3a1a
 #define PCI_DEVICE_ID_INTEL_ICH10_4	0x3a30
 #define PCI_DEVICE_ID_INTEL_ICH10_5	0x3a60
-#define PCI_DEVICE_ID_INTEL_PCH_0	0x3b10
-#define PCI_DEVICE_ID_INTEL_PCH_1	0x3b11
-#define PCI_DEVICE_ID_INTEL_PCH_2	0x3b30
+#define PCI_DEVICE_ID_INTEL_PCH_LPC_MIN	0x3b00
+#define PCI_DEVICE_ID_INTEL_PCH_LPC_MAX	0x3b1f
+#define PCI_DEVICE_ID_INTEL_PCH_SMBUS	0x3b30
 #define PCI_DEVICE_ID_INTEL_IOAT_SNB	0x402f
 #define PCI_DEVICE_ID_INTEL_5100_16	0x65f0
 #define PCI_DEVICE_ID_INTEL_5100_21	0x65f5
-- 
cgit v1.2.3


From c322b28a04c084a467a862766f74c40c917a721c Mon Sep 17 00:00:00 2001
From: "Zhao, Yu" <yu.zhao@intel.com>
Date: Mon, 13 Oct 2008 19:36:05 +0800
Subject: PCI: use same arg names in PCI_VDEVICE comment

This cleanup makes the argument names in PCI_VDEVICE comment consistent
with those used in its definition.

Signed-off-by: Yu Zhao <yu.zhao@intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 include/linux/pci.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 8a4d0bebc311..008005674b60 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -455,8 +455,8 @@ struct pci_driver {
 
 /**
  * PCI_VDEVICE - macro used to describe a specific pci device in short form
- * @vend: the vendor name
- * @dev: the 16 bit PCI Device ID
+ * @vendor: the vendor name
+ * @device: the 16 bit PCI Device ID
  *
  * This macro is used to create a struct pci_device_id that matches a
  * specific PCI device.  The subvendor, and subdevice fields will be set
-- 
cgit v1.2.3


From 58c3a727cb73b75a9104d295f096cca12959a5a5 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yu.zhao@intel.com>
Date: Tue, 14 Oct 2008 14:02:53 +0800
Subject: PCI: support PCIe ARI capability

This patch adds support for PCI Express Alternative Routing-ID
Interpretation (ARI) capability.

The ARI capability extends the Function Number field of the PCI Express
Endpoint by reusing the Device Number which is otherwise hardwired to 0.
With ARI, an Endpoint can have up to 256 functions.

Signed-off-by: Yu Zhao <yu.zhao@intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/pci/pci.c        | 32 ++++++++++++++++++++++++++++++++
 drivers/pci/pci.h        | 12 ++++++++++++
 drivers/pci/probe.c      |  3 +++
 include/linux/pci.h      |  1 +
 include/linux/pci_regs.h | 14 ++++++++++++++
 5 files changed, 62 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 553ca6657955..4db261e13e69 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1299,6 +1299,38 @@ void pci_pm_init(struct pci_dev *dev)
 	}
 }
 
+/**
+ * pci_enable_ari - enable ARI forwarding if hardware support it
+ * @dev: the PCI device
+ */
+void pci_enable_ari(struct pci_dev *dev)
+{
+	int pos;
+	u32 cap;
+	u16 ctrl;
+
+	if (!dev->is_pcie)
+		return;
+
+	if (dev->pcie_type != PCI_EXP_TYPE_ROOT_PORT &&
+	    dev->pcie_type != PCI_EXP_TYPE_DOWNSTREAM)
+		return;
+
+	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	if (!pos)
+		return;
+
+	pci_read_config_dword(dev, pos + PCI_EXP_DEVCAP2, &cap);
+	if (!(cap & PCI_EXP_DEVCAP2_ARI))
+		return;
+
+	pci_read_config_word(dev, pos + PCI_EXP_DEVCTL2, &ctrl);
+	ctrl |= PCI_EXP_DEVCTL2_ARI;
+	pci_write_config_word(dev, pos + PCI_EXP_DEVCTL2, ctrl);
+
+	dev->ari_enabled = 1;
+}
+
 int
 pci_get_interrupt_pin(struct pci_dev *dev, struct pci_dev **bridge)
 {
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 601abdc8dd9f..39684c1415c5 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -151,4 +151,16 @@ struct pci_slot_attribute {
 };
 #define to_pci_slot_attr(s) container_of(s, struct pci_slot_attribute, attr)
 
+extern void pci_enable_ari(struct pci_dev *dev);
+/**
+ * pci_ari_enabled - query ARI forwarding status
+ * @dev: the PCI device
+ *
+ * Returns 1 if ARI forwarding is enabled, or 0 if not enabled;
+ */
+static inline int pci_ari_enabled(struct pci_dev *dev)
+{
+	return dev->ari_enabled;
+}
+
 #endif /* DRIVERS_PCI_H */
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 8c158b9abd41..3141e8deeac4 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1025,6 +1025,9 @@ static void pci_init_capabilities(struct pci_dev *dev)
 
 	/* Vital Product Data */
 	pci_vpd_pci22_init(dev);
+
+	/* Alternative Routing-ID Forwarding */
+	pci_enable_ari(dev);
 }
 
 void pci_device_add(struct pci_dev *dev, struct pci_bus *bus)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 008005674b60..7e9a1f0715e6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -214,6 +214,7 @@ struct pci_dev {
 	unsigned int	broken_parity_status:1;	/* Device generates false positive parity */
 	unsigned int 	msi_enabled:1;
 	unsigned int	msix_enabled:1;
+	unsigned int	ari_enabled:1;	/* ARI forwarding */
 	unsigned int	is_managed:1;
 	unsigned int	is_pcie:1;
 	pci_dev_flags_t dev_flags;
diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h
index 450684f7eaac..eb6686b88f9a 100644
--- a/include/linux/pci_regs.h
+++ b/include/linux/pci_regs.h
@@ -419,6 +419,10 @@
 #define  PCI_EXP_RTCTL_CRSSVE	0x10	/* CRS Software Visibility Enable */
 #define PCI_EXP_RTCAP		30	/* Root Capabilities */
 #define PCI_EXP_RTSTA		32	/* Root Status */
+#define PCI_EXP_DEVCAP2		36	/* Device Capabilities 2 */
+#define  PCI_EXP_DEVCAP2_ARI	0x20	/* Alternative Routing-ID */
+#define PCI_EXP_DEVCTL2		40	/* Device Control 2 */
+#define  PCI_EXP_DEVCTL2_ARI	0x20	/* Alternative Routing-ID */
 
 /* Extended Capabilities (PCI-X 2.0 and Express) */
 #define PCI_EXT_CAP_ID(header)		(header & 0x0000ffff)
@@ -429,6 +433,7 @@
 #define PCI_EXT_CAP_ID_VC	2
 #define PCI_EXT_CAP_ID_DSN	3
 #define PCI_EXT_CAP_ID_PWR	4
+#define PCI_EXT_CAP_ID_ARI	14
 
 /* Advanced Error Reporting */
 #define PCI_ERR_UNCOR_STATUS	4	/* Uncorrectable Error Status */
@@ -536,5 +541,14 @@
 #define HT_CAPTYPE_GEN3		0xD0	/* Generation 3 hypertransport configuration */
 #define HT_CAPTYPE_PM		0xE0	/* Hypertransport powermanagement configuration */
 
+/* Alternative Routing-ID Interpretation */
+#define PCI_ARI_CAP		0x04	/* ARI Capability Register */
+#define  PCI_ARI_CAP_MFVC	0x0001	/* MFVC Function Groups Capability */
+#define  PCI_ARI_CAP_ACS	0x0002	/* ACS Function Groups Capability */
+#define  PCI_ARI_CAP_NFN(x)	(((x) >> 8) & 0xff) /* Next Function Number */
+#define PCI_ARI_CTRL		0x06	/* ARI Control Register */
+#define  PCI_ARI_CTRL_MFVC	0x0001	/* MFVC Function Groups Enable */
+#define  PCI_ARI_CTRL_ACS	0x0002	/* ACS Function Groups Enable */
+#define  PCI_ARI_CTRL_FG(x)	(((x) >> 4) & 7) /* Function Group */
 
 #endif /* LINUX_PCI_REGS_H */
-- 
cgit v1.2.3


From aa42d7c6138afdc54f74e971456a0fbfec16b77b Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@infradead.org>
Date: Sun, 28 Sep 2008 16:36:11 -0700
Subject: PCI: introduce an pci_ioremap(pdev, barnr) function

A common thing in many PCI drivers is to ioremap() an entire bar.  This
is a slightly fragile thing right now, needing both an address and a
size, and many driver writers do.. various things there.

This patch introduces an pci_ioremap() function taking just a PCI device
struct and the bar number as arguments, and figures this all out itself,
in one place.  In addition, we can add various sanity checks to this
function (the patch already checks to make sure that the bar in question
really is a MEM bar; few to no drivers do that sort of thing).

Hopefully with this type of API we get less chance of mistakes in
drivers with ioremap() operations.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 include/linux/pci.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 7e9a1f0715e6..46ad282ffe4d 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1119,5 +1119,18 @@ static inline void pci_mmcfg_early_init(void) { }
 static inline void pci_mmcfg_late_init(void) { }
 #endif
 
+static inline void * pci_ioremap_bar(struct pci_dev *pdev, int bar)
+{
+	/*
+	 * Make sure the BAR is actually a memory resource, not an IO resource
+	 */
+	if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) {
+		WARN_ON(1);
+		return NULL;
+	}
+	return ioremap_nocache(pci_resource_start(pdev, bar),
+				     pci_resource_len(pdev, bar));
+}
+
 #endif /* __KERNEL__ */
 #endif /* LINUX_PCI_H */
-- 
cgit v1.2.3


From 0927678f55c9a50c296f7e6dae85e87b8236e155 Mon Sep 17 00:00:00 2001
From: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Sat, 18 Oct 2008 17:33:19 -0700
Subject: PCI: use pci_find_ext_capability everywhere

Remove some open coded (and buggy) versions of pci_find_ext_capability
in favor of the real routine in the PCI core.

Tested-by: Tomasz Czernecki <czernecki@gmail.com>
Acked-by: Andrew Vasquez <andrew.vasquez@qlogic.com>
Reviewed-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/pci/pcie/aer/aerdrv.c      |  6 ++---
 drivers/pci/pcie/aer/aerdrv_core.c | 47 ++++++++------------------------------
 drivers/pci/pcie/portdrv_core.c    | 23 ++++---------------
 drivers/scsi/qla2xxx/qla_os.c      |  5 ++--
 include/linux/aer.h                |  4 ----
 5 files changed, 20 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/pcie/aer/aerdrv.c b/drivers/pci/pcie/aer/aerdrv.c
index 77036f46acfe..e390707661dd 100644
--- a/drivers/pci/pcie/aer/aerdrv.c
+++ b/drivers/pci/pcie/aer/aerdrv.c
@@ -105,7 +105,7 @@ static irqreturn_t aer_irq(int irq, void *context)
 	unsigned long flags;
 	int pos;
 
-	pos = pci_find_aer_capability(pdev->port);
+	pos = pci_find_ext_capability(pdev->port, PCI_EXT_CAP_ID_ERR);
 	/*
 	 * Must lock access to Root Error Status Reg, Root Error ID Reg,
 	 * and Root error producer/consumer index
@@ -252,7 +252,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	u32 status;
 	int pos;
 
-	pos = pci_find_aer_capability(dev);
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
 
 	/* Disable Root's interrupt in response to error messages */
 	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, 0);
@@ -316,7 +316,7 @@ static void aer_error_resume(struct pci_dev *dev)
 	pci_write_config_word(dev, pos + PCI_EXP_DEVSTA, reg16);
 
 	/* Clean AER Root Error Status */
-	pos = pci_find_aer_capability(dev);
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
 	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
 	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask);
 	if (dev->error_state == pci_channel_io_normal)
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index ee5e7b5176d0..1ff21f6045d6 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -28,36 +28,6 @@
 static int forceload;
 module_param(forceload, bool, 0);
 
-#define PCI_CFG_SPACE_SIZE	(0x100)
-int pci_find_aer_capability(struct pci_dev *dev)
-{
-	int pos;
-	u32 reg32 = 0;
-
-	/* Check if it's a pci-express device */
-	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
-	if (!pos)
-		return 0;
-
-	/* Check if it supports pci-express AER */
-	pos = PCI_CFG_SPACE_SIZE;
-	while (pos) {
-		if (pci_read_config_dword(dev, pos, &reg32))
-			return 0;
-
-		/* some broken boards return ~0 */
-		if (reg32 == 0xffffffff)
-			return 0;
-
-		if (PCI_EXT_CAP_ID(reg32) == PCI_EXT_CAP_ID_ERR)
-			break;
-
-		pos = reg32 >> 20;
-	}
-
-	return pos;
-}
-
 int pci_enable_pcie_error_reporting(struct pci_dev *dev)
 {
 	u16 reg16 = 0;
@@ -67,6 +37,10 @@ int pci_enable_pcie_error_reporting(struct pci_dev *dev)
 	if (!pos)
 		return -EIO;
 
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	if (!pos)
+		return -EIO;
+
 	pci_read_config_word(dev, pos+PCI_EXP_DEVCTL, &reg16);
 	reg16 = reg16 |
 		PCI_EXP_DEVCTL_CERE |
@@ -102,7 +76,7 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 	int pos;
 	u32 status, mask;
 
-	pos = pci_find_aer_capability(dev);
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
 	if (!pos)
 		return -EIO;
 
@@ -123,7 +97,7 @@ int pci_cleanup_aer_correct_error_status(struct pci_dev *dev)
 	int pos;
 	u32 status;
 
-	pos = pci_find_aer_capability(dev);
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
 	if (!pos)
 		return -EIO;
 
@@ -502,7 +476,7 @@ static void handle_error_source(struct pcie_device * aerdev,
 		 * Correctable error does not need software intevention.
 		 * No need to go through error recovery process.
 		 */
-		pos = pci_find_aer_capability(dev);
+		pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
 		if (pos)
 			pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS,
 					info.status);
@@ -542,7 +516,7 @@ void aer_enable_rootport(struct aer_rpc *rpc)
 	reg16 &= ~(SYSTEM_ERROR_INTR_ON_MESG_MASK);
 	pci_write_config_word(pdev, pos + PCI_EXP_RTCTL, reg16);
 
-	aer_pos = pci_find_aer_capability(pdev);
+	aer_pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
 	/* Clear error status */
 	pci_read_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, &reg32);
 	pci_write_config_dword(pdev, aer_pos + PCI_ERR_ROOT_STATUS, reg32);
@@ -579,7 +553,7 @@ static void disable_root_aer(struct aer_rpc *rpc)
 	u32 reg32;
 	int pos;
 
-	pos = pci_find_aer_capability(pdev);
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ERR);
 	/* Disable Root's interrupt in response to error messages */
 	pci_write_config_dword(pdev, pos + PCI_ERR_ROOT_COMMAND, 0);
 
@@ -618,7 +592,7 @@ static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
 {
 	int pos;
 
-	pos = pci_find_aer_capability(dev);
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
 
 	/* The device might not support AER */
 	if (!pos)
@@ -755,7 +729,6 @@ int aer_init(struct pcie_device *dev)
 	return AER_SUCCESS;
 }
 
-EXPORT_SYMBOL_GPL(pci_find_aer_capability);
 EXPORT_SYMBOL_GPL(pci_enable_pcie_error_reporting);
 EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting);
 EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status);
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index 890f0d2b370a..2e091e014829 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -195,24 +195,11 @@ static int get_port_device_capability(struct pci_dev *dev)
 	/* PME Capable - root port capability */
 	if (((reg16 >> 4) & PORT_TYPE_MASK) == PCIE_RC_PORT)
 		services |= PCIE_PORT_SERVICE_PME;
-	
-	pos = PCI_CFG_SPACE_SIZE;
-	while (pos) {
-		pci_read_config_dword(dev, pos, &reg32);
-		switch (reg32 & 0xffff) {
-		case PCI_EXT_CAP_ID_ERR:
-			services |= PCIE_PORT_SERVICE_AER;
-			pos = reg32 >> 20;
-			break;
-		case PCI_EXT_CAP_ID_VC:
-			services |= PCIE_PORT_SERVICE_VC;
-			pos = reg32 >> 20;
-			break;
-		default:
-			pos = 0;
-			break;
-		}
-	}
+
+	if (pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR))
+		services |= PCIE_PORT_SERVICE_AER;
+	if (pci_find_ext_capability(dev, PCI_EXT_CAP_ID_VC))
+		services |= PCIE_PORT_SERVICE_VC;
 
 	return services;
 }
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 2aed4721c0d0..21dd182ad512 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -1566,9 +1566,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 			goto probe_out;
 	}
 
-	if (pci_find_aer_capability(pdev))
-		if (pci_enable_pcie_error_reporting(pdev))
-			goto probe_out;
+	/* This may fail but that's ok */
+	pci_enable_pcie_error_reporting(pdev);
 
 	host = scsi_host_alloc(sht, sizeof(scsi_qla_host_t));
 	if (host == NULL) {
diff --git a/include/linux/aer.h b/include/linux/aer.h
index f2518141de88..a2383a72356a 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -18,10 +18,6 @@ static inline int pci_enable_pcie_error_reporting(struct pci_dev *dev)
 {
 	return -EINVAL;
 }
-static inline int pci_find_aer_capability(struct pci_dev *dev)
-{
-	return 0;
-}
 static inline int pci_disable_pcie_error_reporting(struct pci_dev *dev)
 {
 	return -EINVAL;
-- 
cgit v1.2.3


From 270c66be9b4a6f2be53ef3aec5dc8e7b07782ec9 Mon Sep 17 00:00:00 2001
From: Yu Zhao <yu.zhao@intel.com>
Date: Sun, 19 Oct 2008 20:35:20 +0800
Subject: PCI: fix AER capability check

The 'use pci_find_ext_capability everywhere' cleanup brought a new bug,
which makes the AER stop working.  Fix it by actually using find_ext_cap
instead of just find_cap.  Drop the unused config space size define while
we're at it.

Signed-off-by: Yu Zhao <yu.zhao@intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 Documentation/PCI/pcieaer-howto.txt | 11 +++--------
 drivers/pci/pcie/aer/aerdrv_core.c  |  4 ++--
 drivers/pci/pcie/portdrv.h          |  1 -
 include/linux/aer.h                 |  1 -
 4 files changed, 5 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/PCI/pcieaer-howto.txt b/Documentation/PCI/pcieaer-howto.txt
index 16c251230c82..ddeb14beacc8 100644
--- a/Documentation/PCI/pcieaer-howto.txt
+++ b/Documentation/PCI/pcieaer-howto.txt
@@ -203,22 +203,17 @@ to mmio_enabled.
 
 3.3 helper functions
 
-3.3.1 int pci_find_aer_capability(struct pci_dev *dev);
-pci_find_aer_capability locates the PCI Express AER capability
-in the device configuration space. If the device doesn't support
-PCI-Express AER, the function returns 0.
-
-3.3.2 int pci_enable_pcie_error_reporting(struct pci_dev *dev);
+3.3.1 int pci_enable_pcie_error_reporting(struct pci_dev *dev);
 pci_enable_pcie_error_reporting enables the device to send error
 messages to root port when an error is detected. Note that devices
 don't enable the error reporting by default, so device drivers need
 call this function to enable it.
 
-3.3.3 int pci_disable_pcie_error_reporting(struct pci_dev *dev);
+3.3.2 int pci_disable_pcie_error_reporting(struct pci_dev *dev);
 pci_disable_pcie_error_reporting disables the device to send error
 messages to root port when an error is detected.
 
-3.3.4 int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);
+3.3.3 int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);
 pci_cleanup_aer_uncorrect_error_status cleanups the uncorrectable
 error status register.
 
diff --git a/drivers/pci/pcie/aer/aerdrv_core.c b/drivers/pci/pcie/aer/aerdrv_core.c
index 1ff21f6045d6..dfc63d01f20a 100644
--- a/drivers/pci/pcie/aer/aerdrv_core.c
+++ b/drivers/pci/pcie/aer/aerdrv_core.c
@@ -33,11 +33,11 @@ int pci_enable_pcie_error_reporting(struct pci_dev *dev)
 	u16 reg16 = 0;
 	int pos;
 
-	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
 	if (!pos)
 		return -EIO;
 
-	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+	pos = pci_find_capability(dev, PCI_CAP_ID_EXP);
 	if (!pos)
 		return -EIO;
 
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
index 3656e0349dd1..2529f3f2ea5a 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -25,7 +25,6 @@
 #define PCIE_CAPABILITIES_REG		0x2
 #define PCIE_SLOT_CAPABILITIES_REG	0x14
 #define PCIE_PORT_DEVICE_MAXSERVICES	4
-#define PCI_CFG_SPACE_SIZE		256
 
 #define get_descriptor_id(type, service) (((type - 4) << 4) | service)
 
diff --git a/include/linux/aer.h b/include/linux/aer.h
index a2383a72356a..f7df1eefc107 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -10,7 +10,6 @@
 #if defined(CONFIG_PCIEAER)
 /* pci-e port driver needs this function to enable aer */
 extern int pci_enable_pcie_error_reporting(struct pci_dev *dev);
-extern int pci_find_aer_capability(struct pci_dev *dev);
 extern int pci_disable_pcie_error_reporting(struct pci_dev *dev);
 extern int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev);
 #else
-- 
cgit v1.2.3


From 96499871f45b9126157b1a5c512d6e30f1635225 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 20 Oct 2008 19:45:43 +0200
Subject: PCI: fix pci_ioremap_bar() on s390

s390 doesn't have ioremap_*, so protect the definition of the new
pci_ioremap_bar function with CONFIG_HAS_IOMEM to avoid build breakage.

Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 include/linux/pci.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 46ad282ffe4d..085187be29c7 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1119,6 +1119,7 @@ static inline void pci_mmcfg_early_init(void) { }
 static inline void pci_mmcfg_late_init(void) { }
 #endif
 
+#ifdef CONFIG_HAS_IOMEM
 static inline void * pci_ioremap_bar(struct pci_dev *pdev, int bar)
 {
 	/*
@@ -1131,6 +1132,7 @@ static inline void * pci_ioremap_bar(struct pci_dev *pdev, int bar)
 	return ioremap_nocache(pci_resource_start(pdev, bar),
 				     pci_resource_len(pdev, bar));
 }
+#endif
 
 #endif /* __KERNEL__ */
 #endif /* LINUX_PCI_H */
-- 
cgit v1.2.3


From 326bb8a5a12c6298a6bf6c74af490b1858b2f12c Mon Sep 17 00:00:00 2001
From: Trent Piepho <tpiepho@freescale.com>
Date: Mon, 13 Oct 2008 10:13:01 +0100
Subject: leds: Make default trigger fields const

The default_trigger fields of struct gpio_led and thus struct
led_classdev are pretty much always assigned from a string literal,
which means the string can't be modified.  Which is fine, since there is
no reason to modify the string and in fact it never is.

But they should be marked const to prevent such code from being added,
to prevent warnings if -Wwrite-strings is used, when assigned from a
constant string other than a string literal (which produces a warning
under current kernel compiler flags), and for general good coding
practices.

Signed-off-by: Trent Piepho <tpiepho@freescale.com>
Signed-off-by: Richard Purdie <rpurdie@linux.intel.com>
---
 include/linux/leds.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/linux/leds.h b/include/linux/leds.h
index d41ccb56146a..d3a73f5a48c3 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -123,7 +123,7 @@ extern void ledtrig_ide_activity(void);
  */
 struct led_info {
 	const char	*name;
-	char		*default_trigger;
+	const char	*default_trigger;
 	int		flags;
 };
 
@@ -135,7 +135,7 @@ struct led_platform_data {
 /* For the leds-gpio driver */
 struct gpio_led {
 	const char *name;
-	char *default_trigger;
+	const char *default_trigger;
 	unsigned 	gpio;
 	u8 		active_low;
 };
-- 
cgit v1.2.3


From f6f286f33e843862c559bfea9281318c4cdec6b0 Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Mon, 20 Oct 2008 14:41:03 -0700
Subject: fix WARN() for PPC

powerpc doesn't use the generic WARN_ON infrastructure.  The newly
introduced WARN() as a result didn't print the message, this patch adds
the printk for this specific case.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/bug.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 0f6dabd4b517..12c07c1866b2 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -41,7 +41,7 @@ extern void warn_slowpath(const char *file, const int line,
 #define __WARN() warn_on_slowpath(__FILE__, __LINE__)
 #define __WARN_printf(arg...) warn_slowpath(__FILE__, __LINE__, arg)
 #else
-#define __WARN_printf(arg...) __WARN()
+#define __WARN_printf(arg...) do { printk(arg); __WARN(); } while (0)
 #endif
 
 #ifndef WARN_ON
-- 
cgit v1.2.3


From a5598ca0d49821912a5053c05f07fd650671eb6d Mon Sep 17 00:00:00 2001
From: Carl Love <cel@us.ibm.com>
Date: Tue, 14 Oct 2008 23:37:01 +0000
Subject: powerpc/oprofile: Fix mutex locking for cell spu-oprofile

The issue is the SPU code is not holding the kernel mutex lock while
adding samples to the kernel buffer.

This patch creates per SPU buffers to hold the data.  Data
is added to the buffers from in interrupt context.  The data
is periodically pushed to the kernel buffer via a new Oprofile
function oprofile_put_buff(). The oprofile_put_buff() function
is called via a work queue enabling the funtion to acquire the
mutex lock.

The existing user controls for adjusting the per CPU buffer
size is used to control the size of the per SPU buffers.
Similarly, overflows of the SPU buffers are reported by
incrementing the per CPU buffer stats.  This eliminates the
need to have architecture specific controls for the per SPU
buffers which is not acceptable to the OProfile user tool
maintainer.

The export of the oprofile add_event_entry() is removed as it
is no longer needed given this patch.

Note, this patch has not addressed the issue of indexing arrays
by the spu number.  This still needs to be fixed as the spu
numbering is not guarenteed to be 0 to max_num_spus-1.

Signed-off-by: Carl Love <carll@us.ibm.com>
Signed-off-by: Maynard Johnson <maynardj@us.ibm.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Acked-by: Robert Richter <robert.richter@amd.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
---
 arch/powerpc/oprofile/cell/pr_util.h       |  13 ++
 arch/powerpc/oprofile/cell/spu_profiler.c  |   4 +-
 arch/powerpc/oprofile/cell/spu_task_sync.c | 236 +++++++++++++++++++++++++----
 drivers/oprofile/buffer_sync.c             |  24 +++
 drivers/oprofile/cpu_buffer.c              |  15 +-
 drivers/oprofile/event_buffer.h            |   7 +
 include/linux/oprofile.h                   |  16 +-
 7 files changed, 279 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/arch/powerpc/oprofile/cell/pr_util.h b/arch/powerpc/oprofile/cell/pr_util.h
index 22e4e8d4eb2c..628009c01958 100644
--- a/arch/powerpc/oprofile/cell/pr_util.h
+++ b/arch/powerpc/oprofile/cell/pr_util.h
@@ -24,6 +24,11 @@
 #define SKIP_GENERIC_SYNC 0
 #define SYNC_START_ERROR -1
 #define DO_GENERIC_SYNC 1
+#define SPUS_PER_NODE   8
+#define DEFAULT_TIMER_EXPIRE  (HZ / 10)
+
+extern struct delayed_work spu_work;
+extern int spu_prof_running;
 
 struct spu_overlay_info {	/* map of sections within an SPU overlay */
 	unsigned int vma;	/* SPU virtual memory address from elf */
@@ -62,6 +67,14 @@ struct vma_to_fileoffset_map {	/* map of sections within an SPU program */
 
 };
 
+struct spu_buffer {
+	int last_guard_val;
+	int ctx_sw_seen;
+	unsigned long *buff;
+	unsigned int head, tail;
+};
+
+
 /* The three functions below are for maintaining and accessing
  * the vma-to-fileoffset map.
  */
diff --git a/arch/powerpc/oprofile/cell/spu_profiler.c b/arch/powerpc/oprofile/cell/spu_profiler.c
index 380d7e217531..6edaebd5099a 100644
--- a/arch/powerpc/oprofile/cell/spu_profiler.c
+++ b/arch/powerpc/oprofile/cell/spu_profiler.c
@@ -23,12 +23,11 @@
 
 static u32 *samples;
 
-static int spu_prof_running;
+int spu_prof_running;
 static unsigned int profiling_interval;
 
 #define NUM_SPU_BITS_TRBUF 16
 #define SPUS_PER_TB_ENTRY   4
-#define SPUS_PER_NODE	     8
 
 #define SPU_PC_MASK	     0xFFFF
 
@@ -208,6 +207,7 @@ int start_spu_profiling(unsigned int cycles_reset)
 
 	spu_prof_running = 1;
 	hrtimer_start(&timer, kt, HRTIMER_MODE_REL);
+	schedule_delayed_work(&spu_work, DEFAULT_TIMER_EXPIRE);
 
 	return 0;
 }
diff --git a/arch/powerpc/oprofile/cell/spu_task_sync.c b/arch/powerpc/oprofile/cell/spu_task_sync.c
index 2a9b4a049329..2949126d28d1 100644
--- a/arch/powerpc/oprofile/cell/spu_task_sync.c
+++ b/arch/powerpc/oprofile/cell/spu_task_sync.c
@@ -35,7 +35,102 @@ static DEFINE_SPINLOCK(buffer_lock);
 static DEFINE_SPINLOCK(cache_lock);
 static int num_spu_nodes;
 int spu_prof_num_nodes;
-int last_guard_val[MAX_NUMNODES * 8];
+
+struct spu_buffer spu_buff[MAX_NUMNODES * SPUS_PER_NODE];
+struct delayed_work spu_work;
+static unsigned max_spu_buff;
+
+static void spu_buff_add(unsigned long int value, int spu)
+{
+	/* spu buff is a circular buffer.  Add entries to the
+	 * head.  Head is the index to store the next value.
+	 * The buffer is full when there is one available entry
+	 * in the queue, i.e. head and tail can't be equal.
+	 * That way we can tell the difference between the
+	 * buffer being full versus empty.
+	 *
+	 *  ASSUPTION: the buffer_lock is held when this function
+	 *             is called to lock the buffer, head and tail.
+	 */
+	int full = 1;
+
+	if (spu_buff[spu].head >= spu_buff[spu].tail) {
+		if ((spu_buff[spu].head - spu_buff[spu].tail)
+		    <  (max_spu_buff - 1))
+			full = 0;
+
+	} else if (spu_buff[spu].tail > spu_buff[spu].head) {
+		if ((spu_buff[spu].tail - spu_buff[spu].head)
+		    > 1)
+			full = 0;
+	}
+
+	if (!full) {
+		spu_buff[spu].buff[spu_buff[spu].head] = value;
+		spu_buff[spu].head++;
+
+		if (spu_buff[spu].head >= max_spu_buff)
+			spu_buff[spu].head = 0;
+	} else {
+		/* From the user's perspective make the SPU buffer
+		 * size management/overflow look like we are using
+		 * per cpu buffers.  The user uses the same
+		 * per cpu parameter to adjust the SPU buffer size.
+		 * Increment the sample_lost_overflow to inform
+		 * the user the buffer size needs to be increased.
+		 */
+		oprofile_cpu_buffer_inc_smpl_lost();
+	}
+}
+
+/* This function copies the per SPU buffers to the
+ * OProfile kernel buffer.
+ */
+void sync_spu_buff(void)
+{
+	int spu;
+	unsigned long flags;
+	int curr_head;
+
+	for (spu = 0; spu < num_spu_nodes; spu++) {
+		/* In case there was an issue and the buffer didn't
+		 * get created skip it.
+		 */
+		if (spu_buff[spu].buff == NULL)
+			continue;
+
+		/* Hold the lock to make sure the head/tail
+		 * doesn't change while spu_buff_add() is
+		 * deciding if the buffer is full or not.
+		 * Being a little paranoid.
+		 */
+		spin_lock_irqsave(&buffer_lock, flags);
+		curr_head = spu_buff[spu].head;
+		spin_unlock_irqrestore(&buffer_lock, flags);
+
+		/* Transfer the current contents to the kernel buffer.
+		 * data can still be added to the head of the buffer.
+		 */
+		oprofile_put_buff(spu_buff[spu].buff,
+				  spu_buff[spu].tail,
+				  curr_head, max_spu_buff);
+
+		spin_lock_irqsave(&buffer_lock, flags);
+		spu_buff[spu].tail = curr_head;
+		spin_unlock_irqrestore(&buffer_lock, flags);
+	}
+
+}
+
+static void wq_sync_spu_buff(struct work_struct *work)
+{
+	/* move data from spu buffers to kernel buffer */
+	sync_spu_buff();
+
+	/* only reschedule if profiling is not done */
+	if (spu_prof_running)
+		schedule_delayed_work(&spu_work, DEFAULT_TIMER_EXPIRE);
+}
 
 /* Container for caching information about an active SPU task. */
 struct cached_info {
@@ -305,14 +400,21 @@ static int process_context_switch(struct spu *spu, unsigned long objectId)
 
 	/* Record context info in event buffer */
 	spin_lock_irqsave(&buffer_lock, flags);
-	add_event_entry(ESCAPE_CODE);
-	add_event_entry(SPU_CTX_SWITCH_CODE);
-	add_event_entry(spu->number);
-	add_event_entry(spu->pid);
-	add_event_entry(spu->tgid);
-	add_event_entry(app_dcookie);
-	add_event_entry(spu_cookie);
-	add_event_entry(offset);
+	spu_buff_add(ESCAPE_CODE, spu->number);
+	spu_buff_add(SPU_CTX_SWITCH_CODE, spu->number);
+	spu_buff_add(spu->number, spu->number);
+	spu_buff_add(spu->pid, spu->number);
+	spu_buff_add(spu->tgid, spu->number);
+	spu_buff_add(app_dcookie, spu->number);
+	spu_buff_add(spu_cookie, spu->number);
+	spu_buff_add(offset, spu->number);
+
+	/* Set flag to indicate SPU PC data can now be written out.  If
+	 * the SPU program counter data is seen before an SPU context
+	 * record is seen, the postprocessing will fail.
+	 */
+	spu_buff[spu->number].ctx_sw_seen = 1;
+
 	spin_unlock_irqrestore(&buffer_lock, flags);
 	smp_wmb();	/* insure spu event buffer updates are written */
 			/* don't want entries intermingled... */
@@ -360,6 +462,47 @@ static int number_of_online_nodes(void)
         return nodes;
 }
 
+static int oprofile_spu_buff_create(void)
+{
+	int spu;
+
+	max_spu_buff = oprofile_get_cpu_buffer_size();
+
+	for (spu = 0; spu < num_spu_nodes; spu++) {
+		/* create circular buffers to store the data in.
+		 * use locks to manage accessing the buffers
+		 */
+		spu_buff[spu].head = 0;
+		spu_buff[spu].tail = 0;
+
+		/*
+		 * Create a buffer for each SPU.  Can't reliably
+		 * create a single buffer for all spus due to not
+		 * enough contiguous kernel memory.
+		 */
+
+		spu_buff[spu].buff = kzalloc((max_spu_buff
+					      * sizeof(unsigned long)),
+					     GFP_KERNEL);
+
+		if (!spu_buff[spu].buff) {
+			printk(KERN_ERR "SPU_PROF: "
+			       "%s, line %d:  oprofile_spu_buff_create "
+		       "failed to allocate spu buffer %d.\n",
+			       __func__, __LINE__, spu);
+
+			/* release the spu buffers that have been allocated */
+			while (spu >= 0) {
+				kfree(spu_buff[spu].buff);
+				spu_buff[spu].buff = 0;
+				spu--;
+			}
+			return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
 /* The main purpose of this function is to synchronize
  * OProfile with SPUFS by registering to be notified of
  * SPU task switches.
@@ -372,20 +515,35 @@ static int number_of_online_nodes(void)
  */
 int spu_sync_start(void)
 {
-	int k;
+	int spu;
 	int ret = SKIP_GENERIC_SYNC;
 	int register_ret;
 	unsigned long flags = 0;
 
 	spu_prof_num_nodes = number_of_online_nodes();
 	num_spu_nodes = spu_prof_num_nodes * 8;
+	INIT_DELAYED_WORK(&spu_work, wq_sync_spu_buff);
+
+	/* create buffer for storing the SPU data to put in
+	 * the kernel buffer.
+	 */
+	ret = oprofile_spu_buff_create();
+	if (ret)
+		goto out;
 
 	spin_lock_irqsave(&buffer_lock, flags);
-	add_event_entry(ESCAPE_CODE);
-	add_event_entry(SPU_PROFILING_CODE);
-	add_event_entry(num_spu_nodes);
+	for (spu = 0; spu < num_spu_nodes; spu++) {
+		spu_buff_add(ESCAPE_CODE, spu);
+		spu_buff_add(SPU_PROFILING_CODE, spu);
+		spu_buff_add(num_spu_nodes, spu);
+	}
 	spin_unlock_irqrestore(&buffer_lock, flags);
 
+	for (spu = 0; spu < num_spu_nodes; spu++) {
+		spu_buff[spu].ctx_sw_seen = 0;
+		spu_buff[spu].last_guard_val = 0;
+	}
+
 	/* Register for SPU events  */
 	register_ret = spu_switch_event_register(&spu_active);
 	if (register_ret) {
@@ -393,8 +551,6 @@ int spu_sync_start(void)
 		goto out;
 	}
 
-	for (k = 0; k < (MAX_NUMNODES * 8); k++)
-		last_guard_val[k] = 0;
 	pr_debug("spu_sync_start -- running.\n");
 out:
 	return ret;
@@ -446,13 +602,20 @@ void spu_sync_buffer(int spu_num, unsigned int *samples,
 		 * use.	 We need to discard samples taken during the time
 		 * period which an overlay occurs (i.e., guard value changes).
 		 */
-		if (grd_val && grd_val != last_guard_val[spu_num]) {
-			last_guard_val[spu_num] = grd_val;
+		if (grd_val && grd_val != spu_buff[spu_num].last_guard_val) {
+			spu_buff[spu_num].last_guard_val = grd_val;
 			/* Drop the rest of the samples. */
 			break;
 		}
 
-		add_event_entry(file_offset | spu_num_shifted);
+		/* We must ensure that the SPU context switch has been written
+		 * out before samples for the SPU.  Otherwise, the SPU context
+		 * information is not available and the postprocessing of the
+		 * SPU PC will fail with no available anonymous map information.
+		 */
+		if (spu_buff[spu_num].ctx_sw_seen)
+			spu_buff_add((file_offset | spu_num_shifted),
+					 spu_num);
 	}
 	spin_unlock(&buffer_lock);
 out:
@@ -463,20 +626,41 @@ out:
 int spu_sync_stop(void)
 {
 	unsigned long flags = 0;
-	int ret = spu_switch_event_unregister(&spu_active);
-	if (ret) {
+	int ret;
+	int k;
+
+	ret = spu_switch_event_unregister(&spu_active);
+
+	if (ret)
 		printk(KERN_ERR "SPU_PROF: "
-			"%s, line %d: spu_switch_event_unregister returned %d\n",
-			__func__, __LINE__, ret);
-		goto out;
-	}
+		       "%s, line %d: spu_switch_event_unregister "	\
+		       "returned %d\n",
+		       __func__, __LINE__, ret);
+
+	/* flush any remaining data in the per SPU buffers */
+	sync_spu_buff();
 
 	spin_lock_irqsave(&cache_lock, flags);
 	ret = release_cached_info(RELEASE_ALL);
 	spin_unlock_irqrestore(&cache_lock, flags);
-out:
+
+	/* remove scheduled work queue item rather then waiting
+	 * for every queued entry to execute.  Then flush pending
+	 * system wide buffer to event buffer.
+	 */
+	cancel_delayed_work(&spu_work);
+
+	for (k = 0; k < num_spu_nodes; k++) {
+		spu_buff[k].ctx_sw_seen = 0;
+
+		/*
+		 * spu_sys_buff will be null if there was a problem
+		 * allocating the buffer.  Only delete if it exists.
+		 */
+		kfree(spu_buff[k].buff);
+		spu_buff[k].buff = 0;
+	}
 	pr_debug("spu_sync_stop -- done.\n");
 	return ret;
 }
 
-
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index ed982273fb8b..37681700b61a 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -628,3 +628,27 @@ void sync_buffer(int cpu)
 
 	mutex_unlock(&buffer_mutex);
 }
+
+/* The function can be used to add a buffer worth of data directly to
+ * the kernel buffer. The buffer is assumed to be a circular buffer.
+ * Take the entries from index start and end at index end, wrapping
+ * at max_entries.
+ */
+void oprofile_put_buff(unsigned long *buf, unsigned int start,
+		       unsigned int stop, unsigned int max)
+{
+	int i;
+
+	i = start;
+
+	mutex_lock(&buffer_mutex);
+	while (i != stop) {
+		add_event_entry(buf[i++]);
+
+		if (i >= max)
+			i = 0;
+	}
+
+	mutex_unlock(&buffer_mutex);
+}
+
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index e1bd5a937f6c..7ba39fe20a8a 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -38,13 +38,26 @@ static int work_enabled;
 void free_cpu_buffers(void)
 {
 	int i;
- 
+
 	for_each_online_cpu(i) {
 		vfree(per_cpu(cpu_buffer, i).buffer);
 		per_cpu(cpu_buffer, i).buffer = NULL;
 	}
 }
 
+unsigned long oprofile_get_cpu_buffer_size(void)
+{
+	return fs_cpu_buffer_size;
+}
+
+void oprofile_cpu_buffer_inc_smpl_lost(void)
+{
+	struct oprofile_cpu_buffer *cpu_buf
+		= &__get_cpu_var(cpu_buffer);
+
+	cpu_buf->sample_lost_overflow++;
+}
+
 int alloc_cpu_buffers(void)
 {
 	int i;
diff --git a/drivers/oprofile/event_buffer.h b/drivers/oprofile/event_buffer.h
index 5076ed1ebd8f..84bf324c5771 100644
--- a/drivers/oprofile/event_buffer.h
+++ b/drivers/oprofile/event_buffer.h
@@ -17,6 +17,13 @@ int alloc_event_buffer(void);
 
 void free_event_buffer(void);
  
+/**
+ * Add data to the event buffer.
+ * The data passed is free-form, but typically consists of
+ * file offsets, dcookies, context information, and ESCAPE codes.
+ */
+void add_event_entry(unsigned long data);
+
 /* wake up the process sleeping on the event file */
 void wake_up_buffer_waiter(void);
 
diff --git a/include/linux/oprofile.h b/include/linux/oprofile.h
index bcb8f725427c..5231861f357d 100644
--- a/include/linux/oprofile.h
+++ b/include/linux/oprofile.h
@@ -85,13 +85,6 @@ int oprofile_arch_init(struct oprofile_operations * ops);
  */
 void oprofile_arch_exit(void);
 
-/**
- * Add data to the event buffer.
- * The data passed is free-form, but typically consists of
- * file offsets, dcookies, context information, and ESCAPE codes.
- */
-void add_event_entry(unsigned long data);
-
 /**
  * Add a sample. This may be called from any context. Pass
  * smp_processor_id() as cpu.
@@ -162,5 +155,14 @@ int oprofilefs_ulong_from_user(unsigned long * val, char const __user * buf, siz
 
 /** lock for read/write safety */
 extern spinlock_t oprofilefs_lock;
+
+/**
+ * Add the contents of a circular buffer to the event buffer.
+ */
+void oprofile_put_buff(unsigned long *buf, unsigned int start,
+			unsigned int stop, unsigned int max);
+
+unsigned long oprofile_get_cpu_buffer_size(void);
+void oprofile_cpu_buffer_inc_smpl_lost(void);
  
 #endif /* OPROFILE_H */
-- 
cgit v1.2.3


From aeb5d727062a0238a2f96c9c380fbd2be4640c6f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 2 Sep 2008 15:28:45 -0400
Subject: [PATCH] introduce fmode_t, do annotations

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/bsg.c                         |  7 ++++---
 block/cmd-filter.c                  |  2 +-
 block/scsi_ioctl.c                  |  5 +++--
 drivers/block/amiflop.c             |  4 ++--
 drivers/block/ataflop.c             |  4 ++--
 drivers/block/floppy.c              |  4 ++--
 drivers/block/paride/pf.c           |  2 +-
 drivers/block/paride/pt.c           |  2 +-
 drivers/block/pktcdvd.c             |  2 +-
 drivers/block/swim3.c               |  4 ++--
 drivers/char/nvram.c                |  6 +++---
 drivers/ide/ide-floppy_ioctl.c      |  2 +-
 drivers/ide/ide-gd.c                |  2 +-
 drivers/md/dm-ioctl.c               |  4 ++--
 drivers/md/dm-table.c               | 12 ++++++------
 drivers/mtd/mtdchar.c               | 10 +++++-----
 drivers/parisc/eisa_eeprom.c        |  2 +-
 fs/block_dev.c                      | 10 +++++-----
 fs/fifo.c                           |  6 +++---
 fs/file_table.c                     |  4 ++--
 fs/hostfs/hostfs_kern.c             |  5 +++--
 fs/locks.c                          |  3 ++-
 fs/open.c                           |  2 +-
 fs/proc/base.c                      |  4 ++--
 fs/reiserfs/journal.c               |  2 +-
 include/linux/blkdev.h              |  3 ++-
 include/linux/device-mapper.h       |  8 ++++----
 include/linux/file.h                |  4 ++--
 include/linux/fs.h                  | 16 ++++++++--------
 include/linux/fsnotify.h            |  2 +-
 include/linux/types.h               |  1 +
 ipc/shm.c                           |  2 +-
 sound/core/oss/pcm_oss.c            |  2 +-
 sound/oss/au1550_ac97.c             |  2 +-
 sound/oss/dmasound/dmasound.h       |  4 ++--
 sound/oss/dmasound/dmasound_atari.c |  4 ++--
 sound/oss/dmasound/dmasound_core.c  | 10 +++++-----
 sound/oss/msnd.h                    |  2 +-
 sound/oss/sound_config.h            | 20 ++++++--------------
 sound/oss/swarm_cs4297a.c           |  2 +-
 sound/oss/vwsnd.c                   |  2 +-
 41 files changed, 96 insertions(+), 98 deletions(-)

(limited to 'include')

diff --git a/block/bsg.c b/block/bsg.c
index 034112bfe1f3..2d36b127f384 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -173,7 +173,7 @@ unlock:
 
 static int blk_fill_sgv4_hdr_rq(struct request_queue *q, struct request *rq,
 				struct sg_io_v4 *hdr, struct bsg_device *bd,
-				int has_write_perm)
+				fmode_t has_write_perm)
 {
 	if (hdr->request_len > BLK_MAX_CDB) {
 		rq->cmd = kzalloc(hdr->request_len, GFP_KERNEL);
@@ -242,7 +242,7 @@ bsg_validate_sgv4_hdr(struct request_queue *q, struct sg_io_v4 *hdr, int *rw)
  * map sg_io_v4 to a request.
  */
 static struct request *
-bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, int has_write_perm)
+bsg_map_hdr(struct bsg_device *bd, struct sg_io_v4 *hdr, fmode_t has_write_perm)
 {
 	struct request_queue *q = bd->queue;
 	struct request *rq, *next_rq = NULL;
@@ -601,7 +601,8 @@ bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 }
 
 static int __bsg_write(struct bsg_device *bd, const char __user *buf,
-		       size_t count, ssize_t *bytes_written, int has_write_perm)
+		       size_t count, ssize_t *bytes_written,
+		       fmode_t has_write_perm)
 {
 	struct bsg_command *bc;
 	struct request *rq;
diff --git a/block/cmd-filter.c b/block/cmd-filter.c
index e669aed4c6bc..504b275e1b90 100644
--- a/block/cmd-filter.c
+++ b/block/cmd-filter.c
@@ -27,7 +27,7 @@
 #include <linux/cdrom.h>
 
 int blk_verify_command(struct blk_cmd_filter *filter,
-		       unsigned char *cmd, int has_write_perm)
+		       unsigned char *cmd, fmode_t has_write_perm)
 {
 	/* root can do any command. */
 	if (capable(CAP_SYS_RAWIO))
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index c34272a348fe..c525905f9d35 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -384,7 +384,8 @@ int sg_scsi_ioctl(struct file *file, struct request_queue *q,
 		  struct gendisk *disk, struct scsi_ioctl_command __user *sic)
 {
 	struct request *rq;
-	int err, write_perm = 0;
+	int err;
+	fmode_t write_perm = 0;
 	unsigned int in_len, out_len, bytes, opcode, cmdlen;
 	char *buffer = NULL, sense[SCSI_SENSE_BUFFERSIZE];
 
@@ -428,7 +429,7 @@ int sg_scsi_ioctl(struct file *file, struct request_queue *q,
 
 	/* scsi_ioctl passes NULL */
 	if (file && (file->f_mode & FMODE_WRITE))
-		write_perm = 1;
+		write_perm = FMODE_WRITE;
 
 	err = blk_verify_command(&q->cmd_filter, rq->cmd, write_perm);
 	if (err)
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index 7516baff3bb9..d19c5a939fe8 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1560,9 +1560,9 @@ static int floppy_open(struct inode *inode, struct file *filp)
 	if (fd_ref[drive] && old_dev != system)
 		return -EBUSY;
 
-	if (filp && filp->f_mode & 3) {
+	if (filp && filp->f_mode & (FMODE_READ|FMODE_WRITE)) {
 		check_disk_change(inode->i_bdev);
-		if (filp->f_mode & 2 ) {
+		if (filp->f_mode & FMODE_WRITE ) {
 			int wrprot;
 
 			get_fdc(drive);
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 432cf4018291..e1db285b72cd 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1826,9 +1826,9 @@ static int floppy_open( struct inode *inode, struct file *filp )
 	if (filp->f_flags & O_NDELAY)
 		return 0;
 
-	if (filp->f_mode & 3) {
+	if (filp->f_mode & (FMODE_READ|FMODE_WRITE)) {
 		check_disk_change(inode->i_bdev);
-		if (filp->f_mode & 2) {
+		if (filp->f_mode & FMODE_WRITE) {
 			if (p->wpstat) {
 				if (p->ref < 0)
 					p->ref = 0;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 2cea27aba9a0..ae3ef8945f3f 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3761,14 +3761,14 @@ static int floppy_open(struct inode *inode, struct file *filp)
 		UFDCS->rawcmd = 2;
 
 	if (!(filp->f_flags & O_NDELAY)) {
-		if (filp->f_mode & 3) {
+		if (filp->f_mode & (FMODE_READ|FMODE_WRITE)) {
 			UDRS->last_checked = 0;
 			check_disk_change(inode->i_bdev);
 			if (UTESTF(FD_DISK_CHANGED))
 				goto out;
 		}
 		res = -EROFS;
-		if ((filp->f_mode & 2) && !(UTESTF(FD_DISK_WRITABLE)))
+		if ((filp->f_mode & FMODE_WRITE) && !(UTESTF(FD_DISK_WRITABLE)))
 			goto out;
 	}
 	mutex_unlock(&open_lock);
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index e7fe6ca97dd8..a902d84fd330 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -305,7 +305,7 @@ static int pf_open(struct inode *inode, struct file *file)
 	if (pf->media_status == PF_NM)
 		return -ENODEV;
 
-	if ((pf->media_status == PF_RO) && (file->f_mode & 2))
+	if ((pf->media_status == PF_RO) && (file->f_mode & FMODE_WRITE))
 		return -EROFS;
 
 	pf->access++;
diff --git a/drivers/block/paride/pt.c b/drivers/block/paride/pt.c
index 5ae229656eaa..1e4006e18f03 100644
--- a/drivers/block/paride/pt.c
+++ b/drivers/block/paride/pt.c
@@ -667,7 +667,7 @@ static int pt_open(struct inode *inode, struct file *file)
 		goto out;
 
 	err = -EROFS;
-	if ((!(tape->flags & PT_WRITE_OK)) && (file->f_mode & 2))
+	if ((!(tape->flags & PT_WRITE_OK)) && (file->f_mode & FMODE_WRITE))
 		goto out;
 
 	if (!(iminor(inode) & 128))
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 195ca7c720f5..4d581e8ba9f6 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2320,7 +2320,7 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 /*
  * called at open time.
  */
-static int pkt_open_dev(struct pktcdvd_device *pd, int write)
+static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 {
 	int ret;
 	long lba;
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 730ccea78e45..a53ca54bee12 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -908,13 +908,13 @@ static int floppy_open(struct inode *inode, struct file *filp)
 		return -EBUSY;
 
 	if (err == 0 && (filp->f_flags & O_NDELAY) == 0
-	    && (filp->f_mode & 3)) {
+	    && (filp->f_mode & (FMODE_READ|FMODE_WRITE))) {
 		check_disk_change(inode->i_bdev);
 		if (fs->ejected)
 			err = -ENXIO;
 	}
 
-	if (err == 0 && (filp->f_mode & 2)) {
+	if (err == 0 && (filp->f_mode & FMODE_WRITE)) {
 		if (fs->write_prot < 0)
 			fs->write_prot = swim3_readbit(fs, WRITE_PROT);
 		if (fs->write_prot)
diff --git a/drivers/char/nvram.c b/drivers/char/nvram.c
index 39f6357e3b5d..8054ee839b3c 100644
--- a/drivers/char/nvram.c
+++ b/drivers/char/nvram.c
@@ -338,7 +338,7 @@ nvram_open(struct inode *inode, struct file *file)
 
 	if ((nvram_open_cnt && (file->f_flags & O_EXCL)) ||
 	    (nvram_open_mode & NVRAM_EXCL) ||
-	    ((file->f_mode & 2) && (nvram_open_mode & NVRAM_WRITE))) {
+	    ((file->f_mode & FMODE_WRITE) && (nvram_open_mode & NVRAM_WRITE))) {
 		spin_unlock(&nvram_state_lock);
 		unlock_kernel();
 		return -EBUSY;
@@ -346,7 +346,7 @@ nvram_open(struct inode *inode, struct file *file)
 
 	if (file->f_flags & O_EXCL)
 		nvram_open_mode |= NVRAM_EXCL;
-	if (file->f_mode & 2)
+	if (file->f_mode & FMODE_WRITE)
 		nvram_open_mode |= NVRAM_WRITE;
 	nvram_open_cnt++;
 
@@ -366,7 +366,7 @@ nvram_release(struct inode *inode, struct file *file)
 	/* if only one instance is open, clear the EXCL bit */
 	if (nvram_open_mode & NVRAM_EXCL)
 		nvram_open_mode &= ~NVRAM_EXCL;
-	if (file->f_mode & 2)
+	if (file->f_mode & FMODE_WRITE)
 		nvram_open_mode &= ~NVRAM_WRITE;
 
 	spin_unlock(&nvram_state_lock);
diff --git a/drivers/ide/ide-floppy_ioctl.c b/drivers/ide/ide-floppy_ioctl.c
index 409e4c15f9b7..0d5f5054ab64 100644
--- a/drivers/ide/ide-floppy_ioctl.c
+++ b/drivers/ide/ide-floppy_ioctl.c
@@ -250,7 +250,7 @@ static int ide_floppy_format_ioctl(ide_drive_t *drive, struct file *file,
 	case IDEFLOPPY_IOCTL_FORMAT_GET_CAPACITY:
 		return ide_floppy_get_format_capacities(drive, argp);
 	case IDEFLOPPY_IOCTL_FORMAT_START:
-		if (!(file->f_mode & 2))
+		if (!(file->f_mode & FMODE_WRITE))
 			return -EPERM;
 		return ide_floppy_format_unit(drive, (int __user *)argp);
 	case IDEFLOPPY_IOCTL_FORMAT_GET_PROGRESS:
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index d44898f46c33..d367473098f9 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -202,7 +202,7 @@ static int ide_gd_open(struct inode *inode, struct file *filp)
 			goto out_put_idkp;
 		}
 
-		if ((drive->dev_flags & IDE_DFLAG_WP) && (filp->f_mode & 2)) {
+		if ((drive->dev_flags & IDE_DFLAG_WP) && (filp->f_mode & FMODE_WRITE)) {
 			ret = -EROFS;
 			goto out_put_idkp;
 		}
diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
index dca401dc70a0..777c948180f9 100644
--- a/drivers/md/dm-ioctl.c
+++ b/drivers/md/dm-ioctl.c
@@ -988,9 +988,9 @@ static int dev_wait(struct dm_ioctl *param, size_t param_size)
 	return r;
 }
 
-static inline int get_mode(struct dm_ioctl *param)
+static inline fmode_t get_mode(struct dm_ioctl *param)
 {
-	int mode = FMODE_READ | FMODE_WRITE;
+	fmode_t mode = FMODE_READ | FMODE_WRITE;
 
 	if (param->flags & DM_READONLY_FLAG)
 		mode = FMODE_READ;
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index a740a6950f59..7c8671b06fe3 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -43,7 +43,7 @@ struct dm_table {
 	 * device.  This should be a combination of FMODE_READ
 	 * and FMODE_WRITE.
 	 */
-	int mode;
+	fmode_t mode;
 
 	/* a list of devices used by this table */
 	struct list_head devices;
@@ -217,7 +217,7 @@ static int alloc_targets(struct dm_table *t, unsigned int num)
 	return 0;
 }
 
-int dm_table_create(struct dm_table **result, int mode,
+int dm_table_create(struct dm_table **result, fmode_t mode,
 		    unsigned num_targets, struct mapped_device *md)
 {
 	struct dm_table *t = kzalloc(sizeof(*t), GFP_KERNEL);
@@ -395,7 +395,7 @@ static int check_device_area(struct dm_dev_internal *dd, sector_t start,
  * careful to leave things as they were if we fail to reopen the
  * device.
  */
-static int upgrade_mode(struct dm_dev_internal *dd, int new_mode,
+static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 			struct mapped_device *md)
 {
 	int r;
@@ -421,7 +421,7 @@ static int upgrade_mode(struct dm_dev_internal *dd, int new_mode,
  */
 static int __table_get_device(struct dm_table *t, struct dm_target *ti,
 			      const char *path, sector_t start, sector_t len,
-			      int mode, struct dm_dev **result)
+			      fmode_t mode, struct dm_dev **result)
 {
 	int r;
 	dev_t uninitialized_var(dev);
@@ -537,7 +537,7 @@ void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev)
 EXPORT_SYMBOL_GPL(dm_set_device_limits);
 
 int dm_get_device(struct dm_target *ti, const char *path, sector_t start,
-		  sector_t len, int mode, struct dm_dev **result)
+		  sector_t len, fmode_t mode, struct dm_dev **result)
 {
 	int r = __table_get_device(ti->table, ti, path,
 				   start, len, mode, result);
@@ -887,7 +887,7 @@ struct list_head *dm_table_get_devices(struct dm_table *t)
 	return &t->devices;
 }
 
-int dm_table_get_mode(struct dm_table *t)
+fmode_t dm_table_get_mode(struct dm_table *t)
 {
 	return t->mode;
 }
diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 963840e9b5bf..bcffeda2df3d 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -96,7 +96,7 @@ static int mtd_open(struct inode *inode, struct file *file)
 		return -ENODEV;
 
 	/* You can't open the RO devices RW */
-	if ((file->f_mode & 2) && (minor & 1))
+	if ((file->f_mode & FMODE_WRITE) && (minor & 1))
 		return -EACCES;
 
 	lock_kernel();
@@ -114,7 +114,7 @@ static int mtd_open(struct inode *inode, struct file *file)
 	}
 
 	/* You can't open it RW if it's not a writeable device */
-	if ((file->f_mode & 2) && !(mtd->flags & MTD_WRITEABLE)) {
+	if ((file->f_mode & FMODE_WRITE) && !(mtd->flags & MTD_WRITEABLE)) {
 		put_mtd_device(mtd);
 		ret = -EACCES;
 		goto out;
@@ -144,7 +144,7 @@ static int mtd_close(struct inode *inode, struct file *file)
 	DEBUG(MTD_DEBUG_LEVEL0, "MTD_close\n");
 
 	/* Only sync if opened RW */
-	if ((file->f_mode & 2) && mtd->sync)
+	if ((file->f_mode & FMODE_WRITE) && mtd->sync)
 		mtd->sync(mtd);
 
 	put_mtd_device(mtd);
@@ -443,7 +443,7 @@ static int mtd_ioctl(struct inode *inode, struct file *file,
 	{
 		struct erase_info *erase;
 
-		if(!(file->f_mode & 2))
+		if(!(file->f_mode & FMODE_WRITE))
 			return -EPERM;
 
 		erase=kzalloc(sizeof(struct erase_info),GFP_KERNEL);
@@ -497,7 +497,7 @@ static int mtd_ioctl(struct inode *inode, struct file *file,
 		struct mtd_oob_buf __user *user_buf = argp;
 	        uint32_t retlen;
 
-		if(!(file->f_mode & 2))
+		if(!(file->f_mode & FMODE_WRITE))
 			return -EPERM;
 
 		if (copy_from_user(&buf, argp, sizeof(struct mtd_oob_buf)))
diff --git a/drivers/parisc/eisa_eeprom.c b/drivers/parisc/eisa_eeprom.c
index 5ac207932fd7..685d94e69d44 100644
--- a/drivers/parisc/eisa_eeprom.c
+++ b/drivers/parisc/eisa_eeprom.c
@@ -86,7 +86,7 @@ static int eisa_eeprom_open(struct inode *inode, struct file *file)
 {
 	cycle_kernel_lock();
 
-	if (file->f_mode & 2)
+	if (file->f_mode & FMODE_WRITE)
 		return -EINVAL;
    
 	return 0;
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 218408eed1bb..8897f3b02e98 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -840,7 +840,7 @@ EXPORT_SYMBOL_GPL(bd_release_from_disk);
  * to be used for internal purposes.  If you ever need it - reconsider
  * your API.
  */
-struct block_device *open_by_devnum(dev_t dev, unsigned mode)
+struct block_device *open_by_devnum(dev_t dev, fmode_t mode)
 {
 	struct block_device *bdev = bdget(dev);
 	int err = -ENOMEM;
@@ -975,7 +975,7 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);
 
-static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags,
+static int __blkdev_get(struct block_device *bdev, fmode_t mode, unsigned flags,
 			int for_part);
 static int __blkdev_put(struct block_device *bdev, int for_part);
 
@@ -1104,7 +1104,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 	return ret;
 }
 
-static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags,
+static int __blkdev_get(struct block_device *bdev, fmode_t mode, unsigned flags,
 			int for_part)
 {
 	/*
@@ -1123,7 +1123,7 @@ static int __blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags,
 	return do_open(bdev, &fake_file, for_part);
 }
 
-int blkdev_get(struct block_device *bdev, mode_t mode, unsigned flags)
+int blkdev_get(struct block_device *bdev, fmode_t mode, unsigned flags)
 {
 	return __blkdev_get(bdev, mode, flags, 0);
 }
@@ -1315,7 +1315,7 @@ EXPORT_SYMBOL(lookup_bdev);
 struct block_device *open_bdev_excl(const char *path, int flags, void *holder)
 {
 	struct block_device *bdev;
-	mode_t mode = FMODE_READ;
+	fmode_t mode = FMODE_READ;
 	int error = 0;
 
 	bdev = lookup_bdev(path);
diff --git a/fs/fifo.c b/fs/fifo.c
index 987bf9411495..f8f97b8b6d44 100644
--- a/fs/fifo.c
+++ b/fs/fifo.c
@@ -51,7 +51,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
 	filp->f_mode &= (FMODE_READ | FMODE_WRITE);
 
 	switch (filp->f_mode) {
-	case 1:
+	case FMODE_READ:
 	/*
 	 *  O_RDONLY
 	 *  POSIX.1 says that O_NONBLOCK means return with the FIFO
@@ -76,7 +76,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
 		}
 		break;
 	
-	case 2:
+	case FMODE_WRITE:
 	/*
 	 *  O_WRONLY
 	 *  POSIX.1 says that O_NONBLOCK means return -1 with
@@ -98,7 +98,7 @@ static int fifo_open(struct inode *inode, struct file *filp)
 		}
 		break;
 	
-	case 3:
+	case FMODE_READ | FMODE_WRITE:
 	/*
 	 *  O_RDWR
 	 *  POSIX.1 leaves this case "undefined" when O_NONBLOCK is set.
diff --git a/fs/file_table.c b/fs/file_table.c
index f45a4493f9e7..efc06faede6c 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -161,7 +161,7 @@ EXPORT_SYMBOL(get_empty_filp);
  * code should be moved into this function.
  */
 struct file *alloc_file(struct vfsmount *mnt, struct dentry *dentry,
-		mode_t mode, const struct file_operations *fop)
+		fmode_t mode, const struct file_operations *fop)
 {
 	struct file *file;
 	struct path;
@@ -193,7 +193,7 @@ EXPORT_SYMBOL(alloc_file);
  * of this should be moving to alloc_file().
  */
 int init_file(struct file *file, struct vfsmount *mnt, struct dentry *dentry,
-	   mode_t mode, const struct file_operations *fop)
+	   fmode_t mode, const struct file_operations *fop)
 {
 	int error = 0;
 	file->f_path.dentry = dentry;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index d6ecabf4d231..7f34f4385de0 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -20,7 +20,7 @@
 struct hostfs_inode_info {
 	char *host_filename;
 	int fd;
-	int mode;
+	fmode_t mode;
 	struct inode vfs_inode;
 };
 
@@ -373,7 +373,8 @@ int hostfs_readdir(struct file *file, void *ent, filldir_t filldir)
 int hostfs_file_open(struct inode *ino, struct file *file)
 {
 	char *name;
-	int mode = 0, r = 0, w = 0, fd;
+	fmode_t mode = 0;
+	int r = 0, w = 0, fd;
 
 	mode = file->f_mode & (FMODE_READ | FMODE_WRITE);
 	if ((mode & HOSTFS_I(ino)->mode) == mode)
diff --git a/fs/locks.c b/fs/locks.c
index 5eb259e3cd38..20457486d6b2 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1580,7 +1580,8 @@ asmlinkage long sys_flock(unsigned int fd, unsigned int cmd)
 	cmd &= ~LOCK_NB;
 	unlock = (cmd == LOCK_UN);
 
-	if (!unlock && !(cmd & LOCK_MAND) && !(filp->f_mode & 3))
+	if (!unlock && !(cmd & LOCK_MAND) &&
+	    !(filp->f_mode & (FMODE_READ|FMODE_WRITE)))
 		goto out_putf;
 
 	error = flock_make_lock(filp, &lock, cmd);
diff --git a/fs/open.c b/fs/open.c
index 5596049863bf..83cdb9dee0c1 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -798,7 +798,7 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt,
 	int error;
 
 	f->f_flags = flags;
-	f->f_mode = ((flags+1) & O_ACCMODE) | FMODE_LSEEK |
+	f->f_mode = (__force fmode_t)((flags+1) & O_ACCMODE) | FMODE_LSEEK |
 				FMODE_PREAD | FMODE_PWRITE;
 	inode = dentry->d_inode;
 	if (f->f_mode & FMODE_WRITE) {
diff --git a/fs/proc/base.c b/fs/proc/base.c
index b5918ae8ca79..486cf3fe7139 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1712,9 +1712,9 @@ static struct dentry *proc_fd_instantiate(struct inode *dir,
 	file = fcheck_files(files, fd);
 	if (!file)
 		goto out_unlock;
-	if (file->f_mode & 1)
+	if (file->f_mode & FMODE_READ)
 		inode->i_mode |= S_IRUSR | S_IXUSR;
-	if (file->f_mode & 2)
+	if (file->f_mode & FMODE_WRITE)
 		inode->i_mode |= S_IWUSR | S_IXUSR;
 	spin_unlock(&files->file_lock);
 	put_files_struct(files);
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index c21df71943a6..b89d193a00d9 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2593,7 +2593,7 @@ static int journal_init_dev(struct super_block *super,
 {
 	int result;
 	dev_t jdev;
-	int blkdev_mode = FMODE_READ | FMODE_WRITE;
+	fmode_t blkdev_mode = FMODE_READ | FMODE_WRITE;
 	char b[BDEVNAME_SIZE];
 
 	result = 0;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b4fe68fe3a57..a4413ec3cb3a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -910,7 +910,8 @@ static inline int sb_issue_discard(struct super_block *sb,
 * command filter functions
 */
 extern int blk_verify_command(struct blk_cmd_filter *filter,
-			      unsigned char *cmd, int has_write_perm);
+			      unsigned char *cmd, fmode_t has_write_perm);
+extern void blk_unregister_filter(struct gendisk *disk);
 extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter);
 
 #define MAX_PHYS_SEGMENTS 128
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 08d783592b73..3f8d4e763672 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -85,7 +85,7 @@ void dm_set_device_limits(struct dm_target *ti, struct block_device *bdev);
 
 struct dm_dev {
 	struct block_device *bdev;
-	int mode;
+	fmode_t mode;
 	char name[16];
 };
 
@@ -95,7 +95,7 @@ struct dm_dev {
  * FIXME: too many arguments.
  */
 int dm_get_device(struct dm_target *ti, const char *path, sector_t start,
-		  sector_t len, int mode, struct dm_dev **result);
+		  sector_t len, fmode_t mode, struct dm_dev **result);
 void dm_put_device(struct dm_target *ti, struct dm_dev *d);
 
 /*
@@ -223,7 +223,7 @@ int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo);
 /*
  * First create an empty table.
  */
-int dm_table_create(struct dm_table **result, int mode,
+int dm_table_create(struct dm_table **result, fmode_t mode,
 		    unsigned num_targets, struct mapped_device *md);
 
 /*
@@ -254,7 +254,7 @@ void dm_table_put(struct dm_table *t);
  */
 sector_t dm_table_get_size(struct dm_table *t);
 unsigned int dm_table_get_num_targets(struct dm_table *t);
-int dm_table_get_mode(struct dm_table *t);
+fmode_t dm_table_get_mode(struct dm_table *t);
 struct mapped_device *dm_table_get_md(struct dm_table *t);
 
 /*
diff --git a/include/linux/file.h b/include/linux/file.h
index a20259e248a5..335a0a5c316e 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -19,10 +19,10 @@ struct file_operations;
 struct vfsmount;
 struct dentry;
 extern int init_file(struct file *, struct vfsmount *mnt,
-		struct dentry *dentry, mode_t mode,
+		struct dentry *dentry, fmode_t mode,
 		const struct file_operations *fop);
 extern struct file *alloc_file(struct vfsmount *, struct dentry *dentry,
-		mode_t mode, const struct file_operations *fop);
+		fmode_t mode, const struct file_operations *fop);
 
 static inline void fput_light(struct file *file, int fput_needed)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a6a625be13fc..60a7a581ba91 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -63,18 +63,18 @@ extern int dir_notify_enable;
 #define MAY_ACCESS 16
 #define MAY_OPEN 32
 
-#define FMODE_READ 1
-#define FMODE_WRITE 2
+#define FMODE_READ ((__force fmode_t)1)
+#define FMODE_WRITE ((__force fmode_t)2)
 
 /* Internal kernel extensions */
-#define FMODE_LSEEK	4
-#define FMODE_PREAD	8
+#define FMODE_LSEEK	((__force fmode_t)4)
+#define FMODE_PREAD	((__force fmode_t)8)
 #define FMODE_PWRITE	FMODE_PREAD	/* These go hand in hand */
 
 /* File is being opened for execution. Primary users of this flag are
    distributed filesystems that can use it to achieve correct ETXTBUSY
    behavior for cross-node execution/opening_for_writing of files */
-#define FMODE_EXEC	16
+#define FMODE_EXEC	((__force fmode_t)16)
 
 #define RW_MASK		1
 #define RWA_MASK	2
@@ -825,7 +825,7 @@ struct file {
 	const struct file_operations	*f_op;
 	atomic_long_t		f_count;
 	unsigned int 		f_flags;
-	mode_t			f_mode;
+	fmode_t			f_mode;
 	loff_t			f_pos;
 	struct fown_struct	f_owner;
 	unsigned int		f_uid, f_gid;
@@ -1714,7 +1714,7 @@ extern struct block_device *bdget(dev_t);
 extern void bd_set_size(struct block_device *, loff_t size);
 extern void bd_forget(struct inode *inode);
 extern void bdput(struct block_device *);
-extern struct block_device *open_by_devnum(dev_t, unsigned);
+extern struct block_device *open_by_devnum(dev_t, fmode_t);
 #else
 static inline void bd_forget(struct inode *inode) {}
 #endif
@@ -1729,7 +1729,7 @@ extern int blkdev_driver_ioctl(struct inode *inode, struct file *file,
 			       struct gendisk *disk, unsigned cmd,
 			       unsigned long arg);
 extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
-extern int blkdev_get(struct block_device *, mode_t, unsigned);
+extern int blkdev_get(struct block_device *, fmode_t, unsigned);
 extern int blkdev_put(struct block_device *);
 extern int bd_claim(struct block_device *, void *);
 extern void bd_release(struct block_device *);
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index a89513188ce7..00fbd5b245c9 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -188,7 +188,7 @@ static inline void fsnotify_close(struct file *file)
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = dentry->d_inode;
 	const char *name = dentry->d_name.name;
-	mode_t mode = file->f_mode;
+	fmode_t mode = file->f_mode;
 	u32 mask = (mode & FMODE_WRITE) ? IN_CLOSE_WRITE : IN_CLOSE_NOWRITE;
 
 	if (S_ISDIR(inode->i_mode))
diff --git a/include/linux/types.h b/include/linux/types.h
index f24f7beb47df..1d98330b1f2c 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -190,6 +190,7 @@ typedef __u32 __bitwise __wsum;
 
 #ifdef __KERNEL__
 typedef unsigned __bitwise__ gfp_t;
+typedef unsigned __bitwise__ fmode_t;
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
 typedef u64 phys_addr_t;
diff --git a/ipc/shm.c b/ipc/shm.c
index 0add3fa5f547..867e5d6a55c2 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -817,7 +817,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg, ulong *raddr)
 	struct ipc_namespace *ns;
 	struct shm_file_data *sfd;
 	struct path path;
-	mode_t f_mode;
+	fmode_t f_mode;
 
 	err = -EINVAL;
 	if (shmid < 0)
diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index 1af62b8b86c6..e17836680f49 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -2283,7 +2283,7 @@ static int snd_pcm_oss_open_file(struct file *file,
 	int idx, err;
 	struct snd_pcm_oss_file *pcm_oss_file;
 	struct snd_pcm_substream *substream;
-	unsigned int f_mode = file->f_mode;
+	fmode_t f_mode = file->f_mode;
 
 	if (rpcm_oss_file)
 		*rpcm_oss_file = NULL;
diff --git a/sound/oss/au1550_ac97.c b/sound/oss/au1550_ac97.c
index 23018a7c063a..81e1f443d094 100644
--- a/sound/oss/au1550_ac97.c
+++ b/sound/oss/au1550_ac97.c
@@ -93,7 +93,7 @@ static struct au1550_state {
 	spinlock_t      lock;
 	struct mutex open_mutex;
 	struct mutex sem;
-	mode_t          open_mode;
+	fmode_t          open_mode;
 	wait_queue_head_t open_wait;
 
 	struct dmabuf {
diff --git a/sound/oss/dmasound/dmasound.h b/sound/oss/dmasound/dmasound.h
index d978b0096564..1cb13fe56ec4 100644
--- a/sound/oss/dmasound/dmasound.h
+++ b/sound/oss/dmasound/dmasound.h
@@ -129,7 +129,7 @@ typedef struct {
     int (*mixer_ioctl)(u_int, u_long);	/* optional */
     int (*write_sq_setup)(void);	/* optional */
     int (*read_sq_setup)(void);		/* optional */
-    int (*sq_open)(mode_t);		/* optional */
+    int (*sq_open)(fmode_t);		/* optional */
     int (*state_info)(char *, size_t);	/* optional */
     void (*abort_read)(void);		/* optional */
     int min_dsp_speed;
@@ -235,7 +235,7 @@ struct sound_queue {
      */
     int active;
     wait_queue_head_t action_queue, open_queue, sync_queue;
-    int open_mode;
+    fmode_t open_mode;
     int busy, syncing, xruns, died;
 };
 
diff --git a/sound/oss/dmasound/dmasound_atari.c b/sound/oss/dmasound/dmasound_atari.c
index 285239d64b82..4d45bd63718b 100644
--- a/sound/oss/dmasound/dmasound_atari.c
+++ b/sound/oss/dmasound/dmasound_atari.c
@@ -143,7 +143,7 @@ static int AtaMixerIoctl(u_int cmd, u_long arg);
 static int TTMixerIoctl(u_int cmd, u_long arg);
 static int FalconMixerIoctl(u_int cmd, u_long arg);
 static int AtaWriteSqSetup(void);
-static int AtaSqOpen(mode_t mode);
+static int AtaSqOpen(fmode_t mode);
 static int TTStateInfo(char *buffer, size_t space);
 static int FalconStateInfo(char *buffer, size_t space);
 
@@ -1461,7 +1461,7 @@ static int AtaWriteSqSetup(void)
 	return 0 ;
 }
 
-static int AtaSqOpen(mode_t mode)
+static int AtaSqOpen(fmode_t mode)
 {
 	write_sq_ignore_int = 1;
 	return 0 ;
diff --git a/sound/oss/dmasound/dmasound_core.c b/sound/oss/dmasound/dmasound_core.c
index 95fc5c681755..b8239f3168fb 100644
--- a/sound/oss/dmasound/dmasound_core.c
+++ b/sound/oss/dmasound/dmasound_core.c
@@ -212,7 +212,7 @@ static int irq_installed;
 #endif /* MODULE */
 
 /* control over who can modify resources shared between play/record */
-static mode_t shared_resource_owner;
+static fmode_t shared_resource_owner;
 static int shared_resources_initialised;
 
     /*
@@ -668,7 +668,7 @@ static inline void sq_init_waitqueue(struct sound_queue *sq)
 
 #if 0 /* blocking open() */
 static inline void sq_wake_up(struct sound_queue *sq, struct file *file,
-			      mode_t mode)
+			      fmode_t mode)
 {
 	if (file->f_mode & mode) {
 		sq->busy = 0; /* CHECK: IS THIS OK??? */
@@ -677,7 +677,7 @@ static inline void sq_wake_up(struct sound_queue *sq, struct file *file,
 }
 #endif
 
-static int sq_open2(struct sound_queue *sq, struct file *file, mode_t mode,
+static int sq_open2(struct sound_queue *sq, struct file *file, fmode_t mode,
 		    int numbufs, int bufsize)
 {
 	int rc = 0;
@@ -891,10 +891,10 @@ static int sq_release(struct inode *inode, struct file *file)
    is the owner - if we have problems.
 */
 
-static int shared_resources_are_mine(mode_t md)
+static int shared_resources_are_mine(fmode_t md)
 {
 	if (shared_resource_owner)
-		return (shared_resource_owner & md ) ;
+		return (shared_resource_owner & md) != 0;
 	else {
 		shared_resource_owner = md ;
 		return 1 ;
diff --git a/sound/oss/msnd.h b/sound/oss/msnd.h
index 61b3955481c5..c8be47ec2b7e 100644
--- a/sound/oss/msnd.h
+++ b/sound/oss/msnd.h
@@ -211,7 +211,7 @@ typedef struct multisound_dev {
 
 	/* State variables */
 	enum { msndClassic, msndPinnacle } type;
-	mode_t mode;
+	fmode_t mode;
 	unsigned long flags;
 #define F_RESETTING			0
 #define F_HAVEDIGITAL			1
diff --git a/sound/oss/sound_config.h b/sound/oss/sound_config.h
index 1a00a3210616..55271fbe7f49 100644
--- a/sound/oss/sound_config.h
+++ b/sound/oss/sound_config.h
@@ -110,24 +110,16 @@ struct channel_info {
 #define OPEN_WRITE	PCM_ENABLE_OUTPUT
 #define OPEN_READWRITE	(OPEN_READ|OPEN_WRITE)
 
-#if OPEN_READ == FMODE_READ && OPEN_WRITE == FMODE_WRITE
-
-static inline int translate_mode(struct file *file)
-{
-	return file->f_mode;
-}
-
-#else
-
 static inline int translate_mode(struct file *file)
 {
-	return ((file->f_mode & FMODE_READ) ? OPEN_READ : 0) |
-		((file->f_mode & FMODE_WRITE) ? OPEN_WRITE : 0);
+	if (OPEN_READ == (__force int)FMODE_READ &&
+	    OPEN_WRITE == (__force int)FMODE_WRITE)
+		return (__force int)(file->f_mode & (FMODE_READ | FMODE_WRITE));
+	else
+		return ((file->f_mode & FMODE_READ) ? OPEN_READ : 0) |
+			((file->f_mode & FMODE_WRITE) ? OPEN_WRITE : 0);
 }
 
-#endif
-
-
 #include "sound_calls.h"
 #include "dev_table.h"
 
diff --git a/sound/oss/swarm_cs4297a.c b/sound/oss/swarm_cs4297a.c
index 044453a4ee5b..41562ecde5bb 100644
--- a/sound/oss/swarm_cs4297a.c
+++ b/sound/oss/swarm_cs4297a.c
@@ -295,7 +295,7 @@ struct cs4297a_state {
 	struct mutex open_mutex;
 	struct mutex open_sem_adc;
 	struct mutex open_sem_dac;
-	mode_t open_mode;
+	fmode_t open_mode;
 	wait_queue_head_t open_wait;
 	wait_queue_head_t open_wait_adc;
 	wait_queue_head_t open_wait_dac;
diff --git a/sound/oss/vwsnd.c b/sound/oss/vwsnd.c
index dcbb3f739e61..78b8acc7c3b9 100644
--- a/sound/oss/vwsnd.c
+++ b/sound/oss/vwsnd.c
@@ -1509,7 +1509,7 @@ typedef struct vwsnd_dev {
 	struct mutex open_mutex;
 	struct mutex io_mutex;
 	struct mutex mix_mutex;
-	mode_t		open_mode;
+	fmode_t		open_mode;
 	wait_queue_head_t open_wait;
 
 	lithium_t	lith;
-- 
cgit v1.2.3


From 86d434dede14108dd917b25af0f29c0cb28b8d18 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 26 Aug 2007 19:50:05 -0400
Subject: [PATCH] eliminate use of ->f_flags in block methods

store needed information in f_mode

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/block/ataflop.c |  6 +++---
 drivers/block/floppy.c  | 15 ++++-----------
 drivers/block/swim3.c   |  6 +++---
 drivers/block/ub.c      |  2 +-
 drivers/cdrom/cdrom.c   |  4 ++--
 drivers/ide/ide-gd.c    |  2 +-
 drivers/scsi/sd.c       |  2 +-
 fs/block_dev.c          |  7 +++++++
 include/linux/fs.h      |  4 ++++
 9 files changed, 26 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index e1db285b72cd..85d56a26f7c6 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1813,17 +1813,17 @@ static int floppy_open( struct inode *inode, struct file *filp )
 	if (p->ref && p->type != type)
 		return -EBUSY;
 
-	if (p->ref == -1 || (p->ref && filp->f_flags & O_EXCL))
+	if (p->ref == -1 || (p->ref && filp->f_mode & FMODE_EXCL))
 		return -EBUSY;
 
-	if (filp->f_flags & O_EXCL)
+	if (filp->f_mode & FMODE_EXCL)
 		p->ref = -1;
 	else
 		p->ref++;
 
 	p->type = type;
 
-	if (filp->f_flags & O_NDELAY)
+	if (filp->f_mode & FMODE_NDELAY)
 		return 0;
 
 	if (filp->f_mode & (FMODE_READ|FMODE_WRITE)) {
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index ae3ef8945f3f..5d60c05a736a 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3453,7 +3453,7 @@ static int fd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 static int fd_ioctl(struct inode *inode, struct file *filp, unsigned int cmd,
 		    unsigned long param)
 {
-#define FD_IOCTL_ALLOWED ((filp) && (filp)->private_data)
+#define FD_IOCTL_ALLOWED ((filp) && (filp)->f_mode & (FMODE_WRITE|FMODE_WRITE_IOCTL))
 #define OUT(c,x) case c: outparam = (const char *) (x); break
 #define IN(c,x,tag) case c: *(x) = inparam. tag ; return 0
 
@@ -3690,7 +3690,6 @@ static int floppy_open(struct inode *inode, struct file *filp)
 	int res = -EBUSY;
 	char *tmp;
 
-	filp->private_data = (void *)0;
 	mutex_lock(&open_lock);
 	old_dev = UDRS->fd_device;
 	if (opened_bdev[drive] && opened_bdev[drive] != inode->i_bdev)
@@ -3701,10 +3700,10 @@ static int floppy_open(struct inode *inode, struct file *filp)
 		USETF(FD_VERIFY);
 	}
 
-	if (UDRS->fd_ref == -1 || (UDRS->fd_ref && (filp->f_flags & O_EXCL)))
+	if (UDRS->fd_ref == -1 || (UDRS->fd_ref && (filp->f_mode & FMODE_EXCL)))
 		goto out2;
 
-	if (filp->f_flags & O_EXCL)
+	if (filp->f_mode & FMODE_EXCL)
 		UDRS->fd_ref = -1;
 	else
 		UDRS->fd_ref++;
@@ -3751,16 +3750,10 @@ static int floppy_open(struct inode *inode, struct file *filp)
 			buffer_track = -1;
 	}
 
-	/* Allow ioctls if we have write-permissions even if read-only open.
-	 * Needed so that programs such as fdrawcmd still can work on write
-	 * protected disks */
-	if ((filp->f_mode & FMODE_WRITE) || !file_permission(filp, MAY_WRITE))
-		filp->private_data = (void *)8;
-
 	if (UFDCS->rawcmd == 1)
 		UFDCS->rawcmd = 2;
 
-	if (!(filp->f_flags & O_NDELAY)) {
+	if (!(filp->f_mode & FMODE_NDELAY)) {
 		if (filp->f_mode & (FMODE_READ|FMODE_WRITE)) {
 			UDRS->last_checked = 0;
 			check_disk_change(inode->i_bdev);
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index a53ca54bee12..5c45d5556ae8 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -904,10 +904,10 @@ static int floppy_open(struct inode *inode, struct file *filp)
 		swim3_action(fs, SETMFM);
 		swim3_select(fs, RELAX);
 
-	} else if (fs->ref_count == -1 || filp->f_flags & O_EXCL)
+	} else if (fs->ref_count == -1 || filp->f_mode & FMODE_EXCL)
 		return -EBUSY;
 
-	if (err == 0 && (filp->f_flags & O_NDELAY) == 0
+	if (err == 0 && (filp->f_mode & FMODE_NDELAY) == 0
 	    && (filp->f_mode & (FMODE_READ|FMODE_WRITE))) {
 		check_disk_change(inode->i_bdev);
 		if (fs->ejected)
@@ -930,7 +930,7 @@ static int floppy_open(struct inode *inode, struct file *filp)
 		return err;
 	}
 
-	if (filp->f_flags & O_EXCL)
+	if (filp->f_mode & FMODE_EXCL)
 		fs->ref_count = -1;
 	else
 		++fs->ref_count;
diff --git a/drivers/block/ub.c b/drivers/block/ub.c
index f60e41833f69..85d41eb67c0b 100644
--- a/drivers/block/ub.c
+++ b/drivers/block/ub.c
@@ -1691,7 +1691,7 @@ static int ub_bd_open(struct inode *inode, struct file *filp)
 	 * under some pretty murky conditions (a failure of READ CAPACITY).
 	 * We may need it one day.
 	 */
-	if (lun->removable && lun->changed && !(filp->f_flags & O_NDELAY)) {
+	if (lun->removable && lun->changed && !(filp->f_mode & FMODE_NDELAY)) {
 		rc = -ENOMEDIUM;
 		goto err_open;
 	}
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index d47f2f80accd..4feefa622aed 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -982,7 +982,7 @@ int cdrom_open(struct cdrom_device_info *cdi, struct inode *ip, struct file *fp)
 	/* if this was a O_NONBLOCK open and we should honor the flags,
 	 * do a quick open without drive/disc integrity checks. */
 	cdi->use_count++;
-	if ((fp->f_flags & O_NONBLOCK) && (cdi->options & CDO_USE_FFLAGS)) {
+	if ((fp->f_mode & FMODE_NDELAY) && (cdi->options & CDO_USE_FFLAGS)) {
 		ret = cdi->ops->open(cdi, 1);
 	} else {
 		ret = open_for_data(cdi);
@@ -1205,7 +1205,7 @@ int cdrom_release(struct cdrom_device_info *cdi, struct file *fp)
 	}
 
 	opened_for_data = !(cdi->options & CDO_USE_FFLAGS) ||
-		!(fp && fp->f_flags & O_NONBLOCK);
+		!(fp && fp->f_mode & FMODE_NDELAY);
 
 	/*
 	 * flush cache on last write release
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index d367473098f9..66bbb0a22f57 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -197,7 +197,7 @@ static int ide_gd_open(struct inode *inode, struct file *filp)
 		 * unreadable disk, so that we can get the format capacity
 		 * of the drive or begin the format - Sam
 		 */
-		if (ret && (filp->f_flags & O_NDELAY) == 0) {
+		if (ret && (filp->f_mode & FMODE_NDELAY) == 0) {
 			ret = -EIO;
 			goto out_put_idkp;
 		}
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 7c4d2e68df1c..202c1ed9abd7 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -640,7 +640,7 @@ static int sd_open(struct inode *inode, struct file *filp)
 	 */
 	retval = -ENOMEDIUM;
 	if (sdev->removable && !sdkp->media_present &&
-	    !(filp->f_flags & O_NDELAY))
+	    !(filp->f_mode & FMODE_NDELAY))
 		goto error_out;
 
 	/*
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8897f3b02e98..b9022694e9f7 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1007,6 +1007,13 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 		return ret;
 	}
 
+	if (file->f_flags & O_NDELAY)
+		file->f_mode |= FMODE_NDELAY;
+	if (file->f_flags & O_EXCL)
+		file->f_mode |= FMODE_EXCL;
+	if ((file->f_flags & O_ACCMODE) == 3)
+		file->f_mode |= FMODE_WRITE_IOCTL;
+
 	ret = -ENXIO;
 	file->f_mapping = bdev->bd_inode->i_mapping;
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 60a7a581ba91..5ab5579a5162 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -76,6 +76,10 @@ extern int dir_notify_enable;
    behavior for cross-node execution/opening_for_writing of files */
 #define FMODE_EXEC	((__force fmode_t)16)
 
+#define FMODE_NDELAY	((__force fmode_t)32)
+#define FMODE_EXCL	((__force fmode_t)64)
+#define FMODE_WRITE_IOCTL	((__force fmode_t)128)
+
 #define RW_MASK		1
 #define RWA_MASK	2
 #define READ 0
-- 
cgit v1.2.3


From e915e872ed921d707bc32b3f2184d43abfa8c9e2 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 2 Sep 2008 17:16:41 -0400
Subject: [PATCH] switch sg_scsi_ioctl() to passing fmode_t

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/scsi_ioctl.c        | 13 ++++---------
 drivers/scsi/scsi_ioctl.c |  2 +-
 drivers/scsi/sg.c         |  2 +-
 include/linux/blkdev.h    |  4 ++--
 4 files changed, 8 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 9a441559118d..375e25df8adc 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -379,12 +379,11 @@ out:
  *      bytes in one int) where the lowest byte is the SCSI status.
  */
 #define OMAX_SB_LEN 16          /* For backward compatibility */
-int sg_scsi_ioctl(struct file *file, struct request_queue *q,
-		  struct gendisk *disk, struct scsi_ioctl_command __user *sic)
+int sg_scsi_ioctl(struct request_queue *q, struct gendisk *disk, fmode_t mode,
+		struct scsi_ioctl_command __user *sic)
 {
 	struct request *rq;
 	int err;
-	fmode_t write_perm = 0;
 	unsigned int in_len, out_len, bytes, opcode, cmdlen;
 	char *buffer = NULL, sense[SCSI_SENSE_BUFFERSIZE];
 
@@ -426,11 +425,7 @@ int sg_scsi_ioctl(struct file *file, struct request_queue *q,
 	if (in_len && copy_from_user(buffer, sic->data + cmdlen, in_len))
 		goto error;
 
-	/* scsi_ioctl passes NULL */
-	if (file && (file->f_mode & FMODE_WRITE))
-		write_perm = FMODE_WRITE;
-
-	err = blk_verify_command(&q->cmd_filter, rq->cmd, write_perm);
+	err = blk_verify_command(&q->cmd_filter, rq->cmd, mode & FMODE_WRITE);
 	if (err)
 		goto error;
 
@@ -636,7 +631,7 @@ int scsi_cmd_ioctl(struct file *file, struct request_queue *q,
 			if (!arg)
 				break;
 
-			err = sg_scsi_ioctl(file, q, bd_disk, arg);
+			err = sg_scsi_ioctl(q, bd_disk, file ? file->f_mode : 0, arg);
 			break;
 		case CDROMCLOSETRAY:
 			err = blk_send_start_stop(q, bd_disk, 0x03);
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 28b19ef26309..1f08f5a2f8fd 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -237,7 +237,7 @@ int scsi_ioctl(struct scsi_device *sdev, int cmd, void __user *arg)
 	case SCSI_IOCTL_SEND_COMMAND:
 		if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
 			return -EACCES;
-		return sg_scsi_ioctl(NULL, sdev->request_queue, NULL, arg);
+		return sg_scsi_ioctl(sdev->request_queue, NULL, 0, arg);
 	case SCSI_IOCTL_DOORLOCK:
 		return scsi_set_medium_removal(sdev, SCSI_REMOVAL_PREVENT);
 	case SCSI_IOCTL_DOORUNLOCK:
diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 93bd59a1ed79..9adf35bd8b56 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1059,7 +1059,7 @@ sg_ioctl(struct inode *inode, struct file *filp,
 			if (sg_allow_access(filp, &opcode))
 				return -EPERM;
 		}
-		return sg_scsi_ioctl(filp, sdp->device->request_queue, NULL, p);
+		return sg_scsi_ioctl(sdp->device->request_queue, NULL, filp->f_mode, p);
 	case SG_SET_DEBUG:
 		result = get_user(val, ip);
 		if (result)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a4413ec3cb3a..8945c30e9936 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -719,8 +719,8 @@ extern int blk_remove_plug(struct request_queue *);
 extern void blk_recount_segments(struct request_queue *, struct bio *);
 extern int scsi_cmd_ioctl(struct file *, struct request_queue *,
 			  struct gendisk *, unsigned int, void __user *);
-extern int sg_scsi_ioctl(struct file *, struct request_queue *,
-		struct gendisk *, struct scsi_ioctl_command __user *);
+extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
+			 struct scsi_ioctl_command __user *);
 
 /*
  * Temporary export, until SCSI gets fixed up.
-- 
cgit v1.2.3


From 74f3c8aff36ad6552ea609c8b20bfd588fa16f38 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 27 Aug 2007 15:38:10 -0400
Subject: [PATCH] switch scsi_cmd_ioctl() to passing fmode_t

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/bsg.c                    |  2 +-
 block/scsi_ioctl.c             | 10 +++++-----
 drivers/block/cciss.c          |  3 ++-
 drivers/block/ub.c             |  2 +-
 drivers/block/virtio_blk.c     |  4 ++--
 drivers/cdrom/cdrom.c          |  2 +-
 drivers/ide/ide-floppy_ioctl.c |  4 ++--
 drivers/scsi/sd.c              |  3 ++-
 drivers/scsi/st.c              |  4 ++--
 include/linux/blkdev.h         |  4 ++--
 10 files changed, 20 insertions(+), 18 deletions(-)

(limited to 'include')

diff --git a/block/bsg.c b/block/bsg.c
index 2d36b127f384..e8bd2475682a 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -914,7 +914,7 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case SG_EMULATED_HOST:
 	case SCSI_IOCTL_SEND_COMMAND: {
 		void __user *uarg = (void __user *) arg;
-		return scsi_cmd_ioctl(file, bd->queue, NULL, cmd, uarg);
+		return scsi_cmd_ioctl(bd->queue, NULL, file->f_mode, cmd, uarg);
 	}
 	case SG_IO: {
 		struct request *rq;
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
index 375e25df8adc..5963cf91a3a0 100644
--- a/block/scsi_ioctl.c
+++ b/block/scsi_ioctl.c
@@ -517,8 +517,8 @@ static inline int blk_send_start_stop(struct request_queue *q,
 	return __blk_send_generic(q, bd_disk, GPCMD_START_STOP_UNIT, data);
 }
 
-int scsi_cmd_ioctl(struct file *file, struct request_queue *q,
-		   struct gendisk *bd_disk, unsigned int cmd, void __user *arg)
+int scsi_cmd_ioctl(struct request_queue *q, struct gendisk *bd_disk, fmode_t mode,
+		   unsigned int cmd, void __user *arg)
 {
 	int err;
 
@@ -559,7 +559,7 @@ int scsi_cmd_ioctl(struct file *file, struct request_queue *q,
 			err = -EFAULT;
 			if (copy_from_user(&hdr, arg, sizeof(hdr)))
 				break;
-			err = sg_io(q, bd_disk, &hdr, file ? file->f_mode : 0);
+			err = sg_io(q, bd_disk, &hdr, mode);
 			if (err == -EFAULT)
 				break;
 
@@ -607,7 +607,7 @@ int scsi_cmd_ioctl(struct file *file, struct request_queue *q,
 			hdr.cmdp = ((struct cdrom_generic_command __user*) arg)->cmd;
 			hdr.cmd_len = sizeof(cgc.cmd);
 
-			err = sg_io(q, bd_disk, &hdr, file ? file->f_mode : 0);
+			err = sg_io(q, bd_disk, &hdr, mode);
 			if (err == -EFAULT)
 				break;
 
@@ -631,7 +631,7 @@ int scsi_cmd_ioctl(struct file *file, struct request_queue *q,
 			if (!arg)
 				break;
 
-			err = sg_scsi_ioctl(q, bd_disk, file ? file->f_mode : 0, arg);
+			err = sg_scsi_ioctl(q, bd_disk, mode, arg);
 			break;
 		case CDROMCLOSETRAY:
 			err = blk_send_start_stop(q, bd_disk, 0x03);
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index 1e1f9153000c..d9b1c15b8113 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -1232,7 +1232,8 @@ static int cciss_ioctl(struct inode *inode, struct file *filep,
 	case SG_EMULATED_HOST:
 	case SG_IO:
 	case SCSI_IOCTL_SEND_COMMAND:
-		return scsi_cmd_ioctl(filep, disk->queue, disk, cmd, argp);
+		return scsi_cmd_ioctl(disk->queue, disk,
+				      filep ? filep->f_mode : 0, cmd, argp);
 
 	/* scsi_cmd_ioctl would normally handle these, below, but */
 	/* they aren't a good fit for cciss, as CD-ROMs are */
diff --git a/drivers/block/ub.c b/drivers/block/ub.c
index 85d41eb67c0b..bc04330f3683 100644
--- a/drivers/block/ub.c
+++ b/drivers/block/ub.c
@@ -1729,7 +1729,7 @@ static int ub_bd_ioctl(struct inode *inode, struct file *filp,
 	struct gendisk *disk = inode->i_bdev->bd_disk;
 	void __user *usermem = (void __user *) arg;
 
-	return scsi_cmd_ioctl(filp, disk->queue, disk, cmd, usermem);
+	return scsi_cmd_ioctl(disk->queue, disk, filp ? filp->f_mode : 0, cmd, usermem);
 }
 
 /*
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 6ec5fc052786..7643cd16fd67 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -149,8 +149,8 @@ static void do_virtblk_request(struct request_queue *q)
 static int virtblk_ioctl(struct inode *inode, struct file *filp,
 			 unsigned cmd, unsigned long data)
 {
-	return scsi_cmd_ioctl(filp, inode->i_bdev->bd_disk->queue,
-			      inode->i_bdev->bd_disk, cmd,
+	return scsi_cmd_ioctl(inode->i_bdev->bd_disk->queue,
+			      inode->i_bdev->bd_disk, filp->f_mode, cmd,
 			      (void __user *)data);
 }
 
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 4feefa622aed..e286eb5d1f6a 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -2672,7 +2672,7 @@ int cdrom_ioctl(struct file * file, struct cdrom_device_info *cdi,
 	/*
 	 * Try the generic SCSI command ioctl's first.
 	 */
-	ret = scsi_cmd_ioctl(file, disk->queue, disk, cmd, argp);
+	ret = scsi_cmd_ioctl(disk->queue, disk, file ? file->f_mode : 0, cmd, argp);
 	if (ret != -ENOTTY)
 		return ret;
 
diff --git a/drivers/ide/ide-floppy_ioctl.c b/drivers/ide/ide-floppy_ioctl.c
index 0d5f5054ab64..3c9da4ac9341 100644
--- a/drivers/ide/ide-floppy_ioctl.c
+++ b/drivers/ide/ide-floppy_ioctl.c
@@ -280,8 +280,8 @@ int ide_floppy_ioctl(ide_drive_t *drive, struct inode *inode,
 	 * and CDROM_SEND_PACKET (legacy) ioctls
 	 */
 	if (cmd != CDROM_SEND_PACKET && cmd != SCSI_IOCTL_SEND_COMMAND)
-		err = scsi_cmd_ioctl(file, bdev->bd_disk->queue,
-					bdev->bd_disk, cmd, argp);
+		err = scsi_cmd_ioctl(bdev->bd_disk->queue, bdev->bd_disk,
+				file ? file->f_mode : 0, cmd, argp);
 
 	if (err == -ENOTTY)
 		err = generic_ide_ioctl(drive, file, bdev, cmd, arg);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 202c1ed9abd7..5d74413f591a 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -775,7 +775,8 @@ static int sd_ioctl(struct inode * inode, struct file * filp,
 		case SCSI_IOCTL_GET_BUS_NUMBER:
 			return scsi_ioctl(sdp, cmd, p);
 		default:
-			error = scsi_cmd_ioctl(filp, disk->queue, disk, cmd, p);
+			error = scsi_cmd_ioctl(disk->queue, disk,
+					filp ? filp->f_mode : 0, cmd, p);
 			if (error != -ENOTTY)
 				return error;
 	}
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 5c28d08f18f4..8dffac9f3419 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -3567,8 +3567,8 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 			    !capable(CAP_SYS_RAWIO))
 				i = -EPERM;
 			else
-				i = scsi_cmd_ioctl(file, STp->disk->queue,
-						   STp->disk, cmd_in, p);
+				i = scsi_cmd_ioctl(STp->disk->queue, STp->disk,
+						   file->f_mode, cmd_in, p);
 			if (i != -ENOTTY)
 				return i;
 			break;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 8945c30e9936..48f41b991adb 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -717,8 +717,8 @@ extern void blk_plug_device(struct request_queue *);
 extern void blk_plug_device_unlocked(struct request_queue *);
 extern int blk_remove_plug(struct request_queue *);
 extern void blk_recount_segments(struct request_queue *, struct bio *);
-extern int scsi_cmd_ioctl(struct file *, struct request_queue *,
-			  struct gendisk *, unsigned int, void __user *);
+extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t,
+			  unsigned int, void __user *);
 extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
 			 struct scsi_ioctl_command __user *);
 
-- 
cgit v1.2.3


From 1bddd9e6453ef1c7bc5b6f4ddbf7d31f4aee7a44 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 2 Sep 2008 17:19:43 -0400
Subject: [PATCH] lose the unused file argument in generic_ide_ioctl()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/ide/ide-cd.c           | 2 +-
 drivers/ide/ide-disk_ioctl.c   | 2 +-
 drivers/ide/ide-floppy_ioctl.c | 2 +-
 drivers/ide/ide-ioctls.c       | 3 +--
 drivers/ide/ide-tape.c         | 2 +-
 drivers/scsi/ide-scsi.c        | 2 +-
 include/linux/ide.h            | 3 +--
 7 files changed, 7 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 13265a8827da..cd21b34fe509 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -2174,7 +2174,7 @@ static int idecd_ioctl(struct inode *inode, struct file *file,
 		break;
 	}
 
-	err = generic_ide_ioctl(info->drive, file, bdev, cmd, arg);
+	err = generic_ide_ioctl(info->drive, bdev, cmd, arg);
 	if (err == -EINVAL)
 		err = cdrom_ioctl(file, &info->devinfo, inode, cmd, arg);
 
diff --git a/drivers/ide/ide-disk_ioctl.c b/drivers/ide/ide-disk_ioctl.c
index a49698bcf966..41832af400d6 100644
--- a/drivers/ide/ide-disk_ioctl.c
+++ b/drivers/ide/ide-disk_ioctl.c
@@ -23,5 +23,5 @@ int ide_disk_ioctl(ide_drive_t *drive, struct inode *inode, struct file *file,
 	if (err != -EOPNOTSUPP)
 		return err;
 
-	return generic_ide_ioctl(drive, file, bdev, cmd, arg);
+	return generic_ide_ioctl(drive, bdev, cmd, arg);
 }
diff --git a/drivers/ide/ide-floppy_ioctl.c b/drivers/ide/ide-floppy_ioctl.c
index 3c9da4ac9341..5af70a2c9ef8 100644
--- a/drivers/ide/ide-floppy_ioctl.c
+++ b/drivers/ide/ide-floppy_ioctl.c
@@ -284,7 +284,7 @@ int ide_floppy_ioctl(ide_drive_t *drive, struct inode *inode,
 				file ? file->f_mode : 0, cmd, argp);
 
 	if (err == -ENOTTY)
-		err = generic_ide_ioctl(drive, file, bdev, cmd, arg);
+		err = generic_ide_ioctl(drive, bdev, cmd, arg);
 
 	return err;
 }
diff --git a/drivers/ide/ide-ioctls.c b/drivers/ide/ide-ioctls.c
index a90945f49792..fcde16bb53a7 100644
--- a/drivers/ide/ide-ioctls.c
+++ b/drivers/ide/ide-ioctls.c
@@ -240,8 +240,7 @@ static int generic_drive_reset(ide_drive_t *drive)
 	return ret;
 }
 
-int generic_ide_ioctl(ide_drive_t *drive, struct file *file,
-		      struct block_device *bdev,
+int generic_ide_ioctl(ide_drive_t *drive, struct block_device *bdev,
 		      unsigned int cmd, unsigned long arg)
 {
 	int err;
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index b2b2e5e8d38e..2b263281ffea 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -2368,7 +2368,7 @@ static int idetape_ioctl(struct inode *inode, struct file *file,
 	struct block_device *bdev = inode->i_bdev;
 	struct ide_tape_obj *tape = ide_drv_g(bdev->bd_disk, ide_tape_obj);
 	ide_drive_t *drive = tape->drive;
-	int err = generic_ide_ioctl(drive, file, bdev, cmd, arg);
+	int err = generic_ide_ioctl(drive, bdev, cmd, arg);
 	if (err == -EINVAL)
 		err = idetape_blkdev_ioctl(drive, cmd, arg);
 	return err;
diff --git a/drivers/scsi/ide-scsi.c b/drivers/scsi/ide-scsi.c
index afc96e844a25..5bcc04e82c28 100644
--- a/drivers/scsi/ide-scsi.c
+++ b/drivers/scsi/ide-scsi.c
@@ -478,7 +478,7 @@ static int idescsi_ide_ioctl(struct inode *inode, struct file *file,
 {
 	struct block_device *bdev = inode->i_bdev;
 	struct ide_scsi_obj *scsi = ide_scsi_g(bdev->bd_disk);
-	return generic_ide_ioctl(scsi->drive, file, bdev, cmd, arg);
+	return generic_ide_ioctl(scsi->drive, bdev, cmd, arg);
 }
 
 static struct block_device_operations idescsi_ops = {
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 89e53cfbc787..0d03e83f7194 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -1158,8 +1158,7 @@ struct ide_ioctl_devset {
 int ide_setting_ioctl(ide_drive_t *, struct block_device *, unsigned int,
 		      unsigned long, const struct ide_ioctl_devset *);
 
-int generic_ide_ioctl(ide_drive_t *, struct file *, struct block_device *,
-		      unsigned, unsigned long);
+int generic_ide_ioctl(ide_drive_t *, struct block_device *, unsigned, unsigned long);
 
 extern int ide_vlb_clk;
 extern int ide_pci_clk;
-- 
cgit v1.2.3


From 647b3d0084158c47b1aea8f34d13cab9cd0a5b49 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 28 Aug 2007 22:15:59 -0400
Subject: [PATCH] lose unused arguments in dm ioctl callbacks

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/md/dm-linear.c        | 3 +--
 drivers/md/dm-mpath.c         | 3 +--
 drivers/md/dm.c               | 2 +-
 include/linux/device-mapper.h | 3 +--
 4 files changed, 4 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 6449bcdf84ca..fa358385eed3 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -110,8 +110,7 @@ static int linear_status(struct dm_target *ti, status_type_t type,
 	return 0;
 }
 
-static int linear_ioctl(struct dm_target *ti, struct inode *inode,
-			struct file *filp, unsigned int cmd,
+static int linear_ioctl(struct dm_target *ti, unsigned int cmd,
 			unsigned long arg)
 {
 	struct linear_c *lc = (struct linear_c *) ti->private;
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 9bf3460c5540..c681d5e5f45c 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1395,8 +1395,7 @@ error:
 	return -EINVAL;
 }
 
-static int multipath_ioctl(struct dm_target *ti, struct inode *inode,
-			   struct file *filp, unsigned int cmd,
+static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
 			   unsigned long arg)
 {
 	struct multipath *m = (struct multipath *) ti->private;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 327de03a5bdf..5f0f4c8bcd3e 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -345,7 +345,7 @@ static int dm_blk_ioctl(struct inode *inode, struct file *file,
 	}
 
 	if (tgt->type->ioctl)
-		r = tgt->type->ioctl(tgt, inode, file, cmd, arg);
+		r = tgt->type->ioctl(tgt, cmd, arg);
 
 out:
 	dm_table_put(map);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 3f8d4e763672..a567bbc5293a 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -69,8 +69,7 @@ typedef int (*dm_status_fn) (struct dm_target *ti, status_type_t status_type,
 
 typedef int (*dm_message_fn) (struct dm_target *ti, unsigned argc, char **argv);
 
-typedef int (*dm_ioctl_fn) (struct dm_target *ti, struct inode *inode,
-			    struct file *filp, unsigned int cmd,
+typedef int (*dm_ioctl_fn) (struct dm_target *ti, unsigned int cmd,
 			    unsigned long arg);
 
 typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm,
-- 
cgit v1.2.3


From 08f85851215100d0eebf026810955ee6ad456c38 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 8 Oct 2007 13:26:20 -0400
Subject: [PATCH] move block_device_operations to blkdev.h

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ext2/xip.c          |  1 +
 include/linux/blkdev.h | 17 +++++++++++++++++
 include/linux/fs.h     | 15 +--------------
 3 files changed, 19 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/ext2/xip.c b/fs/ext2/xip.c
index 4fb94c20041b..b72b85884223 100644
--- a/fs/ext2/xip.c
+++ b/fs/ext2/xip.c
@@ -11,6 +11,7 @@
 #include <linux/buffer_head.h>
 #include <linux/ext2_fs_sb.h>
 #include <linux/ext2_fs.h>
+#include <linux/blkdev.h>
 #include "ext2.h"
 #include "xip.h"
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 48f41b991adb..48ec8862a11a 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1057,6 +1057,23 @@ static inline int blk_integrity_rq(struct request *rq)
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
+struct file;
+struct inode;
+
+struct block_device_operations {
+	int (*open) (struct inode *, struct file *);
+	int (*release) (struct inode *, struct file *);
+	int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
+	long (*unlocked_ioctl) (struct file *, unsigned, unsigned long);
+	long (*compat_ioctl) (struct file *, unsigned, unsigned long);
+	int (*direct_access) (struct block_device *, sector_t,
+						void **, unsigned long *);
+	int (*media_changed) (struct gendisk *);
+	int (*revalidate_disk) (struct gendisk *);
+	int (*getgeo)(struct block_device *, struct hd_geometry *);
+	struct module *owner;
+};
+
 #else /* CONFIG_BLOCK */
 /*
  * stubs for when the block layer is configured out
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5ab5579a5162..58bbf689fef7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1270,20 +1270,7 @@ int generic_osync_inode(struct inode *, struct address_space *, int);
  * to have different dirent layouts depending on the binary type.
  */
 typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned);
-
-struct block_device_operations {
-	int (*open) (struct inode *, struct file *);
-	int (*release) (struct inode *, struct file *);
-	int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
-	long (*unlocked_ioctl) (struct file *, unsigned, unsigned long);
-	long (*compat_ioctl) (struct file *, unsigned, unsigned long);
-	int (*direct_access) (struct block_device *, sector_t,
-						void **, unsigned long *);
-	int (*media_changed) (struct gendisk *);
-	int (*revalidate_disk) (struct gendisk *);
-	int (*getgeo)(struct block_device *, struct hd_geometry *);
-	struct module *owner;
-};
+struct block_device_operations;
 
 /* These macros are for out of kernel modules to test that
  * the kernel supports the unlocked_ioctl and compat_ioctl
-- 
cgit v1.2.3


From bbc1cc978404105da23d505163ce9fd5598ed5b1 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 7 Oct 2007 17:54:28 -0400
Subject: [PATCH] switch cdrom_{open,release,ioctl} to sane APIs

... convert to it in callers

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/block/paride/pcd.c |  8 +++++---
 drivers/cdrom/cdrom.c      | 23 +++++++++++------------
 drivers/cdrom/gdrom.c      |  7 ++++---
 drivers/cdrom/viocd.c      |  8 +++++---
 drivers/ide/ide-cd.c       |  7 ++++---
 drivers/scsi/sr.c          | 11 ++++-------
 include/linux/cdrom.h      | 10 +++++-----
 7 files changed, 38 insertions(+), 36 deletions(-)

(limited to 'include')

diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index b8a994a2b013..8bd557e2a659 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -226,20 +226,22 @@ static int pcd_warned;		/* Have we logged a phase warning ? */
 static int pcd_block_open(struct inode *inode, struct file *file)
 {
 	struct pcd_unit *cd = inode->i_bdev->bd_disk->private_data;
-	return cdrom_open(&cd->info, inode, file);
+	return cdrom_open(&cd->info, inode->i_bdev, file->f_mode);
 }
 
 static int pcd_block_release(struct inode *inode, struct file *file)
 {
 	struct pcd_unit *cd = inode->i_bdev->bd_disk->private_data;
-	return cdrom_release(&cd->info, file);
+	cdrom_release(&cd->info, file ? file->f_mode : 0);
+	return 0;
 }
 
 static int pcd_block_ioctl(struct inode *inode, struct file *file,
 				unsigned cmd, unsigned long arg)
 {
 	struct pcd_unit *cd = inode->i_bdev->bd_disk->private_data;
-	return cdrom_ioctl(file, &cd->info, inode, cmd, arg);
+	return cdrom_ioctl(&cd->info, inode->i_bdev,
+			   file ? file->f_mode : 0, cmd, arg);
 }
 
 static int pcd_block_media_changed(struct gendisk *disk)
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index e286eb5d1f6a..d16b02423d61 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -973,7 +973,7 @@ static int cdrom_close_write(struct cdrom_device_info *cdi)
  * is in their own interest: device control becomes a lot easier
  * this way.
  */
-int cdrom_open(struct cdrom_device_info *cdi, struct inode *ip, struct file *fp)
+int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t mode)
 {
 	int ret;
 
@@ -982,14 +982,14 @@ int cdrom_open(struct cdrom_device_info *cdi, struct inode *ip, struct file *fp)
 	/* if this was a O_NONBLOCK open and we should honor the flags,
 	 * do a quick open without drive/disc integrity checks. */
 	cdi->use_count++;
-	if ((fp->f_mode & FMODE_NDELAY) && (cdi->options & CDO_USE_FFLAGS)) {
+	if ((mode & FMODE_NDELAY) && (cdi->options & CDO_USE_FFLAGS)) {
 		ret = cdi->ops->open(cdi, 1);
 	} else {
 		ret = open_for_data(cdi);
 		if (ret)
 			goto err;
 		cdrom_mmc3_profile(cdi);
-		if (fp->f_mode & FMODE_WRITE) {
+		if (mode & FMODE_WRITE) {
 			ret = -EROFS;
 			if (cdrom_open_write(cdi))
 				goto err_release;
@@ -1007,7 +1007,7 @@ int cdrom_open(struct cdrom_device_info *cdi, struct inode *ip, struct file *fp)
 			cdi->name, cdi->use_count);
 	/* Do this on open.  Don't wait for mount, because they might
 	    not be mounting, but opening with O_NONBLOCK */
-	check_disk_change(ip->i_bdev);
+	check_disk_change(bdev);
 	return 0;
 err_release:
 	if (CDROM_CAN(CDC_LOCK) && cdi->options & CDO_LOCK) {
@@ -1184,7 +1184,7 @@ static int check_for_audio_disc(struct cdrom_device_info * cdi,
 	return 0;
 }
 
-int cdrom_release(struct cdrom_device_info *cdi, struct file *fp)
+void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode)
 {
 	struct cdrom_device_ops *cdo = cdi->ops;
 	int opened_for_data;
@@ -1205,7 +1205,7 @@ int cdrom_release(struct cdrom_device_info *cdi, struct file *fp)
 	}
 
 	opened_for_data = !(cdi->options & CDO_USE_FFLAGS) ||
-		!(fp && fp->f_mode & FMODE_NDELAY);
+		!(mode & FMODE_NDELAY);
 
 	/*
 	 * flush cache on last write release
@@ -1219,7 +1219,6 @@ int cdrom_release(struct cdrom_device_info *cdi, struct file *fp)
 		    cdi->options & CDO_AUTO_EJECT && CDROM_CAN(CDC_OPEN_TRAY))
 			cdo->tray_move(cdi, 1);
 	}
-	return 0;
 }
 
 static int cdrom_read_mech_status(struct cdrom_device_info *cdi, 
@@ -2662,17 +2661,17 @@ static int cdrom_ioctl_audioctl(struct cdrom_device_info *cdi,
  * these days.
  * ATAPI / SCSI specific code now mainly resides in mmc_ioctl().
  */
-int cdrom_ioctl(struct file * file, struct cdrom_device_info *cdi,
-		struct inode *ip, unsigned int cmd, unsigned long arg)
+int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
+		fmode_t mode, unsigned int cmd, unsigned long arg)
 {
 	void __user *argp = (void __user *)arg;
 	int ret;
-	struct gendisk *disk = ip->i_bdev->bd_disk;
+	struct gendisk *disk = bdev->bd_disk;
 
 	/*
 	 * Try the generic SCSI command ioctl's first.
 	 */
-	ret = scsi_cmd_ioctl(disk->queue, disk, file ? file->f_mode : 0, cmd, argp);
+	ret = scsi_cmd_ioctl(disk->queue, disk, mode, cmd, argp);
 	if (ret != -ENOTTY)
 		return ret;
 
@@ -2696,7 +2695,7 @@ int cdrom_ioctl(struct file * file, struct cdrom_device_info *cdi,
 	case CDROM_SELECT_DISC:
 		return cdrom_ioctl_select_disc(cdi, arg);
 	case CDROMRESET:
-		return cdrom_ioctl_reset(cdi, ip->i_bdev);
+		return cdrom_ioctl_reset(cdi, bdev);
 	case CDROM_LOCKDOOR:
 		return cdrom_ioctl_lock_door(cdi, arg);
 	case CDROM_DEBUG:
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index d6ba77a2dd7b..0959edf2afdb 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -492,12 +492,12 @@ static struct cdrom_device_ops gdrom_ops = {
 
 static int gdrom_bdops_open(struct inode *inode, struct file *file)
 {
-	return cdrom_open(gd.cd_info, inode, file);
+	return cdrom_open(gd.cd_info, inode->i_bdev, file->f_mode);
 }
 
 static int gdrom_bdops_release(struct inode *inode, struct file *file)
 {
-	return cdrom_release(gd.cd_info, file);
+	return cdrom_release(gd.cd_info, file ? file->f_mode : 0);
 }
 
 static int gdrom_bdops_mediachanged(struct gendisk *disk)
@@ -508,7 +508,8 @@ static int gdrom_bdops_mediachanged(struct gendisk *disk)
 static int gdrom_bdops_ioctl(struct inode *inode, struct file *file,
 	unsigned cmd, unsigned long arg)
 {
-	return cdrom_ioctl(file, gd.cd_info, inode, cmd, arg);
+	return cdrom_ioctl(gd.cd_info, inode->i_bdev,
+			file ? file->f_mode : 0, cmd, arg);
 }
 
 static struct block_device_operations gdrom_bdops = {
diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c
index 031e0e1a1a3b..abc4079c3f41 100644
--- a/drivers/cdrom/viocd.c
+++ b/drivers/cdrom/viocd.c
@@ -154,20 +154,22 @@ static const struct file_operations proc_viocd_operations = {
 static int viocd_blk_open(struct inode *inode, struct file *file)
 {
 	struct disk_info *di = inode->i_bdev->bd_disk->private_data;
-	return cdrom_open(&di->viocd_info, inode, file);
+	return cdrom_open(&di->viocd_info, inode->i_bdev, file->f_mode);
 }
 
 static int viocd_blk_release(struct inode *inode, struct file *file)
 {
 	struct disk_info *di = inode->i_bdev->bd_disk->private_data;
-	return cdrom_release(&di->viocd_info, file);
+	cdrom_release(&di->viocd_info, file ? file->f_mode : 0);
+	return 0;
 }
 
 static int viocd_blk_ioctl(struct inode *inode, struct file *file,
 		unsigned cmd, unsigned long arg)
 {
 	struct disk_info *di = inode->i_bdev->bd_disk->private_data;
-	return cdrom_ioctl(file, &di->viocd_info, inode, cmd, arg);
+	return cdrom_ioctl(&di->viocd_info, inode->i_bdev,
+			   file ? file->f_mode : 0, cmd, arg);
 }
 
 static int viocd_blk_media_changed(struct gendisk *disk)
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index cd21b34fe509..87d90200b169 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -2099,7 +2099,7 @@ static int idecd_open(struct inode *inode, struct file *file)
 	if (!info)
 		return -ENXIO;
 
-	rc = cdrom_open(&info->devinfo, inode, file);
+	rc = cdrom_open(&info->devinfo, inode->i_bdev, file->f_mode);
 
 	if (rc < 0)
 		ide_cd_put(info);
@@ -2112,7 +2112,7 @@ static int idecd_release(struct inode *inode, struct file *file)
 	struct gendisk *disk = inode->i_bdev->bd_disk;
 	struct cdrom_info *info = ide_drv_g(disk, cdrom_info);
 
-	cdrom_release(&info->devinfo, file);
+	cdrom_release(&info->devinfo, file ? file->f_mode : 0);
 
 	ide_cd_put(info);
 
@@ -2176,7 +2176,8 @@ static int idecd_ioctl(struct inode *inode, struct file *file,
 
 	err = generic_ide_ioctl(info->drive, bdev, cmd, arg);
 	if (err == -EINVAL)
-		err = cdrom_ioctl(file, &info->devinfo, inode, cmd, arg);
+		err = cdrom_ioctl(&info->devinfo, bdev,
+				  file ? file->f_mode : 0, cmd, arg);
 
 	return err;
 }
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 0f17009c99d2..b92e2dac9aa9 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -480,7 +480,7 @@ static int sr_block_open(struct inode *inode, struct file *file)
 	if(!(cd = scsi_cd_get(disk)))
 		return -ENXIO;
 
-	if((ret = cdrom_open(&cd->cdi, inode, file)) != 0)
+	if((ret = cdrom_open(&cd->cdi, inode->i_bdev, file->f_mode)) != 0)
 		scsi_cd_put(cd);
 
 	return ret;
@@ -488,12 +488,8 @@ static int sr_block_open(struct inode *inode, struct file *file)
 
 static int sr_block_release(struct inode *inode, struct file *file)
 {
-	int ret;
 	struct scsi_cd *cd = scsi_cd(inode->i_bdev->bd_disk);
-	ret = cdrom_release(&cd->cdi, file);
-	if(ret)
-		return ret;
-	
+	cdrom_release(&cd->cdi, file ? file->f_mode : 0);
 	scsi_cd_put(cd);
 
 	return 0;
@@ -517,7 +513,8 @@ static int sr_block_ioctl(struct inode *inode, struct file *file, unsigned cmd,
 		return scsi_ioctl(sdev, cmd, argp);
 	}
 
-	ret = cdrom_ioctl(file, &cd->cdi, inode, cmd, arg);
+	ret = cdrom_ioctl(&cd->cdi, inode->i_bdev,
+			  file ? file->f_mode : 0, cmd, arg);
 	if (ret != -ENOSYS)
 		return ret;
 
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index 5db265ea60f6..0b49e08d3cb0 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -987,11 +987,11 @@ struct cdrom_device_ops {
 };
 
 /* the general block_device operations structure: */
-extern int cdrom_open(struct cdrom_device_info *cdi, struct inode *ip,
-			struct file *fp);
-extern int cdrom_release(struct cdrom_device_info *cdi, struct file *fp);
-extern int cdrom_ioctl(struct file *file, struct cdrom_device_info *cdi,
-		struct inode *ip, unsigned int cmd, unsigned long arg);
+extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev,
+			fmode_t mode);
+extern void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode);
+extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
+		       fmode_t mode, unsigned int cmd, unsigned long arg);
 extern int cdrom_media_changed(struct cdrom_device_info *);
 
 extern int register_cdrom(struct cdrom_device_info *cdi);
-- 
cgit v1.2.3


From 633a08b81206122469365b4c72eaeb71f04f2cb4 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 29 Aug 2007 20:34:12 -0400
Subject: [PATCH] introduce __blkdev_driver_ioctl()

Analog of blkdev_driver_ioctl() with sane arguments.  For
now uses fake struct file, by the end of the series it won't
and blkdev_driver_ioctl() will become a wrapper around it.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/ioctl.c           | 31 +++++++++++++++++++++++++++++++
 drivers/block/pktcdvd.c |  4 ++--
 drivers/md/dm-linear.c  | 10 +---------
 drivers/md/dm-mpath.c   | 11 +++--------
 include/linux/blkdev.h  |  2 ++
 5 files changed, 39 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/block/ioctl.c b/block/ioctl.c
index 38bee321e1fa..9a26ace6d042 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -283,6 +283,37 @@ int blkdev_driver_ioctl(struct inode *inode, struct file *file,
 }
 EXPORT_SYMBOL_GPL(blkdev_driver_ioctl);
 
+int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
+			unsigned cmd, unsigned long arg)
+{
+	struct gendisk *disk = bdev->bd_disk;
+	int ret;
+	/* you bet it'll go away by the end of patch series */
+	struct file fake_file = {};
+	struct dentry fake_dentry = {};
+	fake_file.f_mode = mode;
+	fake_file.f_path.dentry = &fake_dentry;
+	fake_dentry.d_inode = bdev->bd_inode;
+
+	if (disk->fops->unlocked_ioctl)
+		return disk->fops->unlocked_ioctl(&fake_file, cmd, arg);
+
+	if (disk->fops->ioctl) {
+		lock_kernel();
+		ret = disk->fops->ioctl(bdev->bd_inode, &fake_file, cmd, arg);
+		unlock_kernel();
+		return ret;
+	}
+
+	return -ENOTTY;
+}
+/*
+ * For the record: _GPL here is only because somebody decided to slap it
+ * on the previous export.  Sheer idiocy, since it wasn't copyrightable
+ * at all and could be open-coded without any exports by anybody who cares.
+ */
+EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl);
+
 /*
  * always keep this in sync with compat_blkdev_ioctl() and
  * compat_blkdev_locked_ioctl()
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index bdd49abcb546..a0ba4023953b 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2819,8 +2819,8 @@ static int pkt_ioctl(struct inode *inode, struct file *file, unsigned int cmd, u
 	case CDROM_LAST_WRITTEN:
 	case CDROM_SEND_PACKET:
 	case SCSI_IOCTL_SEND_COMMAND:
-		return blkdev_driver_ioctl(pd->bdev->bd_inode, pd->bdev->bd_disk,
-					file, cmd, arg);
+		return __blkdev_driver_ioctl(pd->bdev, file ? file->f_mode : 0,
+					cmd, arg);
 
 	default:
 		VPRINTK(DRIVER_NAME": Unknown ioctl for %s (%x)\n", pd->name, cmd);
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index fa358385eed3..373442b1e98f 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -114,15 +114,7 @@ static int linear_ioctl(struct dm_target *ti, unsigned int cmd,
 			unsigned long arg)
 {
 	struct linear_c *lc = (struct linear_c *) ti->private;
-	struct block_device *bdev = lc->dev->bdev;
-	struct file fake_file = {};
-	struct dentry fake_dentry = {};
-
-	fake_file.f_mode = lc->dev->mode;
-	fake_file.f_path.dentry = &fake_dentry;
-	fake_dentry.d_inode = bdev->bd_inode;
-
-	return blkdev_driver_ioctl(bdev->bd_inode, &fake_file, bdev->bd_disk, cmd, arg);
+	return __blkdev_driver_ioctl(lc->dev->bdev, lc->dev->mode, cmd, arg);
 }
 
 static int linear_merge(struct dm_target *ti, struct bvec_merge_data *bvm,
diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index c681d5e5f45c..d85c65a46433 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -1400,13 +1400,10 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
 {
 	struct multipath *m = (struct multipath *) ti->private;
 	struct block_device *bdev = NULL;
+	fmode_t mode = 0;
 	unsigned long flags;
-	struct file fake_file = {};
-	struct dentry fake_dentry = {};
 	int r = 0;
 
-	fake_file.f_path.dentry = &fake_dentry;
-
 	spin_lock_irqsave(&m->lock, flags);
 
 	if (!m->current_pgpath)
@@ -1414,8 +1411,7 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
 
 	if (m->current_pgpath) {
 		bdev = m->current_pgpath->path.dev->bdev;
-		fake_dentry.d_inode = bdev->bd_inode;
-		fake_file.f_mode = m->current_pgpath->path.dev->mode;
+		mode = m->current_pgpath->path.dev->mode;
 	}
 
 	if (m->queue_io)
@@ -1425,8 +1421,7 @@ static int multipath_ioctl(struct dm_target *ti, unsigned int cmd,
 
 	spin_unlock_irqrestore(&m->lock, flags);
 
-	return r ? : blkdev_driver_ioctl(bdev->bd_inode, &fake_file,
-					 bdev->bd_disk, cmd, arg);
+	return r ? : __blkdev_driver_ioctl(bdev, mode, cmd, arg);
 }
 
 /*-----------------------------------------------------------------
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 48ec8862a11a..2bad616b9949 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1074,6 +1074,8 @@ struct block_device_operations {
 	struct module *owner;
 };
 
+extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int,
+				 unsigned long);
 #else /* CONFIG_BLOCK */
 /*
  * stubs for when the block layer is configured out
-- 
cgit v1.2.3


From 83ff6fe8580a7c834dba4389d742332fff9b9929 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 2 Mar 2008 08:15:49 -0500
Subject: [PATCH] don't mess with file in scsi_nonblockable_ioctl()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/scsi/scsi_ioctl.c | 4 ++--
 drivers/scsi/sd.c         | 3 ++-
 drivers/scsi/sr.c         | 3 ++-
 drivers/scsi/st.c         | 3 ++-
 include/scsi/scsi_ioctl.h | 2 +-
 5 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 1f08f5a2f8fd..dc1cfb2fd76b 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -277,14 +277,14 @@ EXPORT_SYMBOL(scsi_ioctl);
  * @filp: either NULL or a &struct file which must have the O_NONBLOCK flag.
  */
 int scsi_nonblockable_ioctl(struct scsi_device *sdev, int cmd,
-			    void __user *arg, struct file *filp)
+			    void __user *arg, int ndelay)
 {
 	int val, result;
 
 	/* The first set of iocts may be executed even if we're doing
 	 * error processing, as long as the device was opened
 	 * non-blocking */
-	if (filp && (filp->f_flags & O_NONBLOCK)) {
+	if (ndelay) {
 		if (scsi_host_in_recovery(sdev->host))
 			return -ENODEV;
 	} else if (!scsi_block_when_processing_errors(sdev))
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 5d74413f591a..5a18528a69d0 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -761,7 +761,8 @@ static int sd_ioctl(struct inode * inode, struct file * filp,
 	 * may try and take the device offline, in which case all further
 	 * access to the device is prohibited.
 	 */
-	error = scsi_nonblockable_ioctl(sdp, cmd, p, filp);
+	error = scsi_nonblockable_ioctl(sdp, cmd, p,
+					filp ? filp->f_flags & O_NDELAY : 0);
 	if (!scsi_block_when_processing_errors(sdp) || !error)
 		return error;
 
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index b92e2dac9aa9..2fb8d4d2d6f6 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -524,7 +524,8 @@ static int sr_block_ioctl(struct inode *inode, struct file *file, unsigned cmd,
 	 * case fall through to scsi_ioctl, which will return ENDOEV again
 	 * if it doesn't recognise the ioctl
 	 */
-	ret = scsi_nonblockable_ioctl(sdev, cmd, argp, NULL);
+	ret = scsi_nonblockable_ioctl(sdev, cmd, argp,
+					file ? file->f_flags & O_NDELAY : 0);
 	if (ret != -ENODEV)
 		return ret;
 	return scsi_ioctl(sdev, cmd, argp);
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 8dffac9f3419..c959bdc55f4f 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -3263,7 +3263,8 @@ static long st_ioctl(struct file *file, unsigned int cmd_in, unsigned long arg)
 	 * may try and take the device offline, in which case all further
 	 * access to the device is prohibited.
 	 */
-	retval = scsi_nonblockable_ioctl(STp->device, cmd_in, p, file);
+	retval = scsi_nonblockable_ioctl(STp->device, cmd_in, p,
+					file->f_flags & O_NDELAY);
 	if (!scsi_block_when_processing_errors(STp->device) || retval != -ENODEV)
 		goto out;
 	retval = 0;
diff --git a/include/scsi/scsi_ioctl.h b/include/scsi/scsi_ioctl.h
index edb9525386da..b9006848b813 100644
--- a/include/scsi/scsi_ioctl.h
+++ b/include/scsi/scsi_ioctl.h
@@ -42,7 +42,7 @@ typedef struct scsi_fctargaddress {
 
 extern int scsi_ioctl(struct scsi_device *, int, void __user *);
 extern int scsi_nonblockable_ioctl(struct scsi_device *sdev, int cmd,
-				   void __user *arg, struct file *filp);
+				   void __user *arg, int ndelay);
 
 #endif /* __KERNEL__ */
 #endif /* _SCSI_IOCTL_H */
-- 
cgit v1.2.3


From badf8082c33d18b118d3a6f1b32d5ea6b97d3839 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 16 Oct 2008 10:23:20 -0400
Subject: [PATCH] switch ide_disk_ops ->ioctl() to sane prototype

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/ide/ide-disk.h         |  2 +-
 drivers/ide/ide-disk_ioctl.c   |  3 +--
 drivers/ide/ide-floppy.h       |  4 ++--
 drivers/ide/ide-floppy_ioctl.c | 13 ++++++-------
 drivers/ide/ide-gd.c           |  2 +-
 include/linux/ide.h            |  4 ++--
 6 files changed, 13 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/drivers/ide/ide-disk.h b/drivers/ide/ide-disk.h
index b234b0feaf7b..d511dab7c4aa 100644
--- a/drivers/ide/ide-disk.h
+++ b/drivers/ide/ide-disk.h
@@ -13,7 +13,7 @@ ide_decl_devset(wcache);
 ide_decl_devset(acoustic);
 
 /* ide-disk_ioctl.c */
-int ide_disk_ioctl(ide_drive_t *, struct inode *, struct file *, unsigned int,
+int ide_disk_ioctl(ide_drive_t *, struct block_device *, fmode_t, unsigned int,
 		   unsigned long);
 
 #ifdef CONFIG_IDE_PROC_FS
diff --git a/drivers/ide/ide-disk_ioctl.c b/drivers/ide/ide-disk_ioctl.c
index 41832af400d6..7b783dd7c0be 100644
--- a/drivers/ide/ide-disk_ioctl.c
+++ b/drivers/ide/ide-disk_ioctl.c
@@ -13,10 +13,9 @@ static const struct ide_ioctl_devset ide_disk_ioctl_settings[] = {
 { 0 }
 };
 
-int ide_disk_ioctl(ide_drive_t *drive, struct inode *inode, struct file *file,
+int ide_disk_ioctl(ide_drive_t *drive, struct block_device *bdev, fmode_t mode,
 		   unsigned int cmd, unsigned long arg)
 {
-	struct block_device *bdev = inode->i_bdev;
 	int err;
 
 	err = ide_setting_ioctl(drive, bdev, cmd, arg, ide_disk_ioctl_settings);
diff --git a/drivers/ide/ide-floppy.h b/drivers/ide/ide-floppy.h
index c17124dd6079..6dd2beb48434 100644
--- a/drivers/ide/ide-floppy.h
+++ b/drivers/ide/ide-floppy.h
@@ -23,8 +23,8 @@ void ide_floppy_create_mode_sense_cmd(struct ide_atapi_pc *, u8);
 void ide_floppy_create_read_capacity_cmd(struct ide_atapi_pc *);
 
 /* ide-floppy_ioctl.c */
-int ide_floppy_ioctl(ide_drive_t *, struct inode *, struct file *, unsigned int,
-		     unsigned long);
+int ide_floppy_ioctl(ide_drive_t *, struct block_device *, fmode_t,
+		     unsigned int, unsigned long);
 
 #ifdef CONFIG_IDE_PROC_FS
 /* ide-floppy_proc.c */
diff --git a/drivers/ide/ide-floppy_ioctl.c b/drivers/ide/ide-floppy_ioctl.c
index 5af70a2c9ef8..2bc51ff73fee 100644
--- a/drivers/ide/ide-floppy_ioctl.c
+++ b/drivers/ide/ide-floppy_ioctl.c
@@ -241,7 +241,7 @@ static int ide_floppy_lockdoor(ide_drive_t *drive, struct ide_atapi_pc *pc,
 	return 0;
 }
 
-static int ide_floppy_format_ioctl(ide_drive_t *drive, struct file *file,
+static int ide_floppy_format_ioctl(ide_drive_t *drive, fmode_t mode,
 				   unsigned int cmd, void __user *argp)
 {
 	switch (cmd) {
@@ -250,7 +250,7 @@ static int ide_floppy_format_ioctl(ide_drive_t *drive, struct file *file,
 	case IDEFLOPPY_IOCTL_FORMAT_GET_CAPACITY:
 		return ide_floppy_get_format_capacities(drive, argp);
 	case IDEFLOPPY_IOCTL_FORMAT_START:
-		if (!(file->f_mode & FMODE_WRITE))
+		if (!(mode & FMODE_WRITE))
 			return -EPERM;
 		return ide_floppy_format_unit(drive, (int __user *)argp);
 	case IDEFLOPPY_IOCTL_FORMAT_GET_PROGRESS:
@@ -260,10 +260,9 @@ static int ide_floppy_format_ioctl(ide_drive_t *drive, struct file *file,
 	}
 }
 
-int ide_floppy_ioctl(ide_drive_t *drive, struct inode *inode,
-		     struct file *file, unsigned int cmd, unsigned long arg)
+int ide_floppy_ioctl(ide_drive_t *drive, struct block_device *bdev,
+		     fmode_t mode, unsigned int cmd, unsigned long arg)
 {
-	struct block_device *bdev = inode->i_bdev;
 	struct ide_atapi_pc pc;
 	void __user *argp = (void __user *)arg;
 	int err;
@@ -271,7 +270,7 @@ int ide_floppy_ioctl(ide_drive_t *drive, struct inode *inode,
 	if (cmd == CDROMEJECT || cmd == CDROM_LOCKDOOR)
 		return ide_floppy_lockdoor(drive, &pc, arg, cmd);
 
-	err = ide_floppy_format_ioctl(drive, file, cmd, argp);
+	err = ide_floppy_format_ioctl(drive, mode, cmd, argp);
 	if (err != -ENOTTY)
 		return err;
 
@@ -281,7 +280,7 @@ int ide_floppy_ioctl(ide_drive_t *drive, struct inode *inode,
 	 */
 	if (cmd != CDROM_SEND_PACKET && cmd != SCSI_IOCTL_SEND_COMMAND)
 		err = scsi_cmd_ioctl(bdev->bd_disk->queue, bdev->bd_disk,
-				file ? file->f_mode : 0, cmd, argp);
+				mode, cmd, argp);
 
 	if (err == -ENOTTY)
 		err = generic_ide_ioctl(drive, bdev, cmd, arg);
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index 66bbb0a22f57..948af08abe23 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -293,7 +293,7 @@ static int ide_gd_ioctl(struct inode *inode, struct file *file,
 	struct ide_disk_obj *idkp = ide_drv_g(bdev->bd_disk, ide_disk_obj);
 	ide_drive_t *drive = idkp->drive;
 
-	return drive->disk_ops->ioctl(drive, inode, file, cmd, arg);
+	return drive->disk_ops->ioctl(drive, bdev, file ? file->f_mode : 0, cmd, arg);
 }
 
 static struct block_device_operations ide_gd_ops = {
diff --git a/include/linux/ide.h b/include/linux/ide.h
index 0d03e83f7194..54525be4b5f8 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -474,8 +474,8 @@ struct ide_disk_ops {
 	ide_startstop_t	(*do_request)(struct ide_drive_s *, struct request *,
 				      sector_t);
 	int		(*end_request)(struct ide_drive_s *, int, int);
-	int		(*ioctl)(struct ide_drive_s *, struct inode *,
-				 struct file *, unsigned int, unsigned long);
+	int		(*ioctl)(struct ide_drive_s *, struct block_device *,
+				 fmode_t, unsigned int, unsigned long);
 };
 
 /* ATAPI device flags */
-- 
cgit v1.2.3


From d4430d62fa77208824a37fe6f85ab2831d274769 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 2 Mar 2008 09:09:22 -0500
Subject: [PATCH] beginning of methods conversion

To keep the size of changesets sane we split the switch by drivers;
to keep the damn thing bisectable we do the following:
	1) rename the affected methods, add ones with correct
prototypes, make (few) callers handle both.  That's this changeset.
	2) for each driver convert to new methods.  *ALL* drivers
are converted in this series.
	3) kill the old (renamed) methods.

Note that it _is_ a flagday; all in-tree drivers are converted and by the
end of this series no trace of old methods remain.  The only reason why
we do that this way is to keep the damn thing bisectable and allow per-driver
debugging if anything goes wrong.

New methods:
	open(bdev, mode)
	release(disk, mode)
	ioctl(bdev, mode, cmd, arg)		/* Called without BKL */
	compat_ioctl(bdev, mode, cmd, arg)
	locked_ioctl(bdev, mode, cmd, arg)	/* Called with BKL, legacy */

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 arch/um/drivers/ubd_kern.c          |  6 +++---
 block/compat_ioctl.c                | 17 +++++++++--------
 block/ioctl.c                       | 35 ++++++++++++++++++++++++++---------
 drivers/block/DAC960.c              |  2 +-
 drivers/block/amiflop.c             |  6 +++---
 drivers/block/aoe/aoeblk.c          |  4 ++--
 drivers/block/ataflop.c             |  6 +++---
 drivers/block/brd.c                 |  2 +-
 drivers/block/cciss.c               |  8 ++++----
 drivers/block/cpqarray.c            |  6 +++---
 drivers/block/floppy.c              |  6 +++---
 drivers/block/loop.c                |  8 ++++----
 drivers/block/nbd.c                 |  2 +-
 drivers/block/paride/pcd.c          |  6 +++---
 drivers/block/paride/pd.c           |  6 +++---
 drivers/block/paride/pf.c           |  6 +++---
 drivers/block/pktcdvd.c             |  6 +++---
 drivers/block/swim3.c               |  6 +++---
 drivers/block/ub.c                  |  6 +++---
 drivers/block/viodasd.c             |  4 ++--
 drivers/block/virtio_blk.c          |  2 +-
 drivers/block/xd.c                  |  2 +-
 drivers/block/xen-blkfront.c        |  4 ++--
 drivers/block/xsysace.c             |  4 ++--
 drivers/block/z2ram.c               |  4 ++--
 drivers/cdrom/gdrom.c               |  6 +++---
 drivers/cdrom/viocd.c               |  6 +++---
 drivers/ide/ide-cd.c                |  6 +++---
 drivers/ide/ide-gd.c                |  6 +++---
 drivers/ide/ide-tape.c              |  6 +++---
 drivers/md/dm.c                     |  6 +++---
 drivers/md/md.c                     |  6 +++---
 drivers/memstick/core/mspro_block.c |  4 ++--
 drivers/message/i2o/i2o_block.c     |  6 +++---
 drivers/mmc/card/block.c            |  4 ++--
 drivers/mtd/mtd_blkdevs.c           |  6 +++---
 drivers/s390/block/dasd.c           |  8 ++++----
 drivers/s390/block/dcssblk.c        |  4 ++--
 drivers/s390/char/tape_block.c      |  6 +++---
 drivers/scsi/ide-scsi.c             |  6 +++---
 drivers/scsi/sd.c                   |  8 ++++----
 drivers/scsi/sr.c                   |  6 +++---
 fs/block_dev.c                      | 18 +++++++++++++++---
 include/linux/blkdev.h              | 15 ++++++++++-----
 include/linux/fs.h                  |  1 +
 45 files changed, 167 insertions(+), 131 deletions(-)

(limited to 'include')

diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index b58fb8941d8d..72569cc3cbb7 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -108,9 +108,9 @@ static int ubd_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 
 static struct block_device_operations ubd_blops = {
         .owner		= THIS_MODULE,
-        .open		= ubd_open,
-        .release	= ubd_release,
-        .ioctl		= ubd_ioctl,
+        .__open		= ubd_open,
+        .__release	= ubd_release,
+        .__ioctl		= ubd_ioctl,
 	.getgeo		= ubd_getgeo,
 };
 
diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 1e559fba7bdf..576c4fd15463 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -708,17 +708,17 @@ static int compat_blkdev_driver_ioctl(struct inode *inode, struct file *file,
 		return -ENOIOCTLCMD;
 	}
 
-	if (disk->fops->unlocked_ioctl)
-		return disk->fops->unlocked_ioctl(file, cmd, arg);
+	if (disk->fops->__unlocked_ioctl)
+		return disk->fops->__unlocked_ioctl(file, cmd, arg);
 
-	if (disk->fops->ioctl) {
+	if (disk->fops->__ioctl) {
 		lock_kernel();
-		ret = disk->fops->ioctl(inode, file, cmd, arg);
+		ret = disk->fops->__ioctl(inode, file, cmd, arg);
 		unlock_kernel();
 		return ret;
 	}
 
-	return -ENOTTY;
+	return __blkdev_driver_ioctl(inode->i_bdev, file->f_mode, cmd, arg);
 }
 
 static int compat_blkdev_locked_ioctl(struct inode *inode, struct file *file,
@@ -805,10 +805,11 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 
 	lock_kernel();
 	ret = compat_blkdev_locked_ioctl(inode, file, bdev, cmd, arg);
-	/* FIXME: why do we assume -> compat_ioctl needs the BKL? */
-	if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl)
-		ret = disk->fops->compat_ioctl(file, cmd, arg);
+	if (ret == -ENOIOCTLCMD && disk->fops->__compat_ioctl)
+		ret = disk->fops->__compat_ioctl(file, cmd, arg);
 	unlock_kernel();
+	if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl)
+		ret = disk->fops->compat_ioctl(bdev, file->f_mode, cmd, arg);
 
 	if (ret != -ENOIOCTLCMD)
 		return ret;
diff --git a/block/ioctl.c b/block/ioctl.c
index 9a26ace6d042..01ff463bc801 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -269,17 +269,24 @@ int blkdev_driver_ioctl(struct inode *inode, struct file *file,
 			struct gendisk *disk, unsigned cmd, unsigned long arg)
 {
 	int ret;
-	if (disk->fops->unlocked_ioctl)
-		return disk->fops->unlocked_ioctl(file, cmd, arg);
+	fmode_t mode = 0;
+	if (file) {
+		mode = file->f_mode;
+		if (file->f_flags & O_NDELAY)
+			mode |= FMODE_NDELAY_NOW;
+	}
+
+	if (disk->fops->__unlocked_ioctl)
+		return disk->fops->__unlocked_ioctl(file, cmd, arg);
 
-	if (disk->fops->ioctl) {
+	if (disk->fops->__ioctl) {
 		lock_kernel();
-		ret = disk->fops->ioctl(inode, file, cmd, arg);
+		ret = disk->fops->__ioctl(inode, file, cmd, arg);
 		unlock_kernel();
 		return ret;
 	}
 
-	return -ENOTTY;
+	return __blkdev_driver_ioctl(inode->i_bdev, mode, cmd, arg);
 }
 EXPORT_SYMBOL_GPL(blkdev_driver_ioctl);
 
@@ -295,12 +302,22 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
 	fake_file.f_path.dentry = &fake_dentry;
 	fake_dentry.d_inode = bdev->bd_inode;
 
-	if (disk->fops->unlocked_ioctl)
-		return disk->fops->unlocked_ioctl(&fake_file, cmd, arg);
+	if (disk->fops->__unlocked_ioctl)
+		return disk->fops->__unlocked_ioctl(&fake_file, cmd, arg);
+
+	if (disk->fops->__ioctl) {
+		lock_kernel();
+		ret = disk->fops->__ioctl(bdev->bd_inode, &fake_file, cmd, arg);
+		unlock_kernel();
+		return ret;
+	}
+
+	if (disk->fops->ioctl)
+		return disk->fops->ioctl(bdev, mode, cmd, arg);
 
-	if (disk->fops->ioctl) {
+	if (disk->fops->locked_ioctl) {
 		lock_kernel();
-		ret = disk->fops->ioctl(bdev->bd_inode, &fake_file, cmd, arg);
+		ret = disk->fops->locked_ioctl(bdev, mode, cmd, arg);
 		unlock_kernel();
 		return ret;
 	}
diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index a002a381df92..4b90ebfa6676 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -153,7 +153,7 @@ static int DAC960_revalidate_disk(struct gendisk *disk)
 
 static struct block_device_operations DAC960_BlockDeviceOperations = {
 	.owner			= THIS_MODULE,
-	.open			= DAC960_open,
+	.__open			= DAC960_open,
 	.getgeo			= DAC960_getgeo,
 	.media_changed		= DAC960_media_changed,
 	.revalidate_disk	= DAC960_revalidate_disk,
diff --git a/drivers/block/amiflop.c b/drivers/block/amiflop.c
index d19c5a939fe8..d5da4e3cb2ad 100644
--- a/drivers/block/amiflop.c
+++ b/drivers/block/amiflop.c
@@ -1648,9 +1648,9 @@ static int amiga_floppy_change(struct gendisk *disk)
 
 static struct block_device_operations floppy_fops = {
 	.owner		= THIS_MODULE,
-	.open		= floppy_open,
-	.release	= floppy_release,
-	.ioctl		= fd_ioctl,
+	.__open		= floppy_open,
+	.__release	= floppy_release,
+	.__ioctl		= fd_ioctl,
 	.getgeo		= fd_getgeo,
 	.media_changed	= amiga_floppy_change,
 };
diff --git a/drivers/block/aoe/aoeblk.c b/drivers/block/aoe/aoeblk.c
index d876ad861237..d4d9796d5ddd 100644
--- a/drivers/block/aoe/aoeblk.c
+++ b/drivers/block/aoe/aoeblk.c
@@ -239,8 +239,8 @@ aoeblk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 }
 
 static struct block_device_operations aoe_bdops = {
-	.open = aoeblk_open,
-	.release = aoeblk_release,
+	.__open = aoeblk_open,
+	.__release = aoeblk_release,
 	.getgeo = aoeblk_getgeo,
 	.owner = THIS_MODULE,
 };
diff --git a/drivers/block/ataflop.c b/drivers/block/ataflop.c
index 85d56a26f7c6..30166774327d 100644
--- a/drivers/block/ataflop.c
+++ b/drivers/block/ataflop.c
@@ -1857,9 +1857,9 @@ static int floppy_release( struct inode * inode, struct file * filp )
 
 static struct block_device_operations floppy_fops = {
 	.owner		= THIS_MODULE,
-	.open		= floppy_open,
-	.release	= floppy_release,
-	.ioctl		= fd_ioctl,
+	.__open		= floppy_open,
+	.__release	= floppy_release,
+	.__ioctl		= fd_ioctl,
 	.media_changed	= check_floppy_change,
 	.revalidate_disk= floppy_revalidate,
 };
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index d070d492e385..2ea99f947667 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -376,7 +376,7 @@ static int brd_ioctl(struct inode *inode, struct file *file,
 
 static struct block_device_operations brd_fops = {
 	.owner =		THIS_MODULE,
-	.ioctl =		brd_ioctl,
+	.__ioctl =		brd_ioctl,
 #ifdef CONFIG_BLK_DEV_XIP
 	.direct_access =	brd_direct_access,
 #endif
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index d9b1c15b8113..781b745181d2 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -197,12 +197,12 @@ static long cciss_compat_ioctl(struct file *f, unsigned cmd, unsigned long arg);
 
 static struct block_device_operations cciss_fops = {
 	.owner = THIS_MODULE,
-	.open = cciss_open,
-	.release = cciss_release,
-	.ioctl = cciss_ioctl,
+	.__open = cciss_open,
+	.__release = cciss_release,
+	.__ioctl = cciss_ioctl,
 	.getgeo = cciss_getgeo,
 #ifdef CONFIG_COMPAT
-	.compat_ioctl = cciss_compat_ioctl,
+	.__compat_ioctl = cciss_compat_ioctl,
 #endif
 	.revalidate_disk = cciss_revalidate,
 };
diff --git a/drivers/block/cpqarray.c b/drivers/block/cpqarray.c
index 3d967525e9a9..b71334b968b6 100644
--- a/drivers/block/cpqarray.c
+++ b/drivers/block/cpqarray.c
@@ -195,9 +195,9 @@ static inline ctlr_info_t *get_host(struct gendisk *disk)
 
 static struct block_device_operations ida_fops  = {
 	.owner		= THIS_MODULE,
-	.open		= ida_open,
-	.release	= ida_release,
-	.ioctl		= ida_ioctl,
+	.__open		= ida_open,
+	.__release	= ida_release,
+	.__ioctl		= ida_ioctl,
 	.getgeo		= ida_getgeo,
 	.revalidate_disk= ida_revalidate,
 };
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 5d60c05a736a..72363df58953 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -3902,9 +3902,9 @@ static int floppy_revalidate(struct gendisk *disk)
 
 static struct block_device_operations floppy_fops = {
 	.owner			= THIS_MODULE,
-	.open			= floppy_open,
-	.release		= floppy_release,
-	.ioctl			= fd_ioctl,
+	.__open			= floppy_open,
+	.__release		= floppy_release,
+	.__ioctl			= fd_ioctl,
 	.getgeo			= fd_getgeo,
 	.media_changed		= check_floppy_change,
 	.revalidate_disk	= floppy_revalidate,
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index d3a25b027ff9..6faca2b7ae37 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1355,11 +1355,11 @@ static int lo_release(struct inode *inode, struct file *file)
 
 static struct block_device_operations lo_fops = {
 	.owner =	THIS_MODULE,
-	.open =		lo_open,
-	.release =	lo_release,
-	.ioctl =	lo_ioctl,
+	.__open =		lo_open,
+	.__release =	lo_release,
+	.__ioctl =	lo_ioctl,
 #ifdef CONFIG_COMPAT
-	.compat_ioctl =	lo_compat_ioctl,
+	.__compat_ioctl =	lo_compat_ioctl,
 #endif
 };
 
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 9034ca585afd..36015e0945b1 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -691,7 +691,7 @@ static int nbd_ioctl(struct inode *inode, struct file *file,
 static struct block_device_operations nbd_fops =
 {
 	.owner =	THIS_MODULE,
-	.ioctl =	nbd_ioctl,
+	.__ioctl =	nbd_ioctl,
 };
 
 /*
diff --git a/drivers/block/paride/pcd.c b/drivers/block/paride/pcd.c
index 8bd557e2a659..6e6dcc1d4328 100644
--- a/drivers/block/paride/pcd.c
+++ b/drivers/block/paride/pcd.c
@@ -252,9 +252,9 @@ static int pcd_block_media_changed(struct gendisk *disk)
 
 static struct block_device_operations pcd_bdops = {
 	.owner		= THIS_MODULE,
-	.open		= pcd_block_open,
-	.release	= pcd_block_release,
-	.ioctl		= pcd_block_ioctl,
+	.__open		= pcd_block_open,
+	.__release	= pcd_block_release,
+	.__ioctl		= pcd_block_ioctl,
 	.media_changed	= pcd_block_media_changed,
 };
 
diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 5fdfa7c888ce..b3023844947c 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -807,9 +807,9 @@ static int pd_revalidate(struct gendisk *p)
 
 static struct block_device_operations pd_fops = {
 	.owner		= THIS_MODULE,
-	.open		= pd_open,
-	.release	= pd_release,
-	.ioctl		= pd_ioctl,
+	.__open		= pd_open,
+	.__release	= pd_release,
+	.__ioctl		= pd_ioctl,
 	.getgeo		= pd_getgeo,
 	.media_changed	= pd_check_media,
 	.revalidate_disk= pd_revalidate
diff --git a/drivers/block/paride/pf.c b/drivers/block/paride/pf.c
index a902d84fd330..e08ca5161ad8 100644
--- a/drivers/block/paride/pf.c
+++ b/drivers/block/paride/pf.c
@@ -264,9 +264,9 @@ static char *pf_buf;		/* buffer for request in progress */
 
 static struct block_device_operations pf_fops = {
 	.owner		= THIS_MODULE,
-	.open		= pf_open,
-	.release	= pf_release,
-	.ioctl		= pf_ioctl,
+	.__open		= pf_open,
+	.__release	= pf_release,
+	.__ioctl		= pf_ioctl,
 	.getgeo		= pf_getgeo,
 	.media_changed	= pf_check_media,
 };
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index a0ba4023953b..33ac8ddf4912 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2847,9 +2847,9 @@ static int pkt_media_changed(struct gendisk *disk)
 
 static struct block_device_operations pktcdvd_ops = {
 	.owner =		THIS_MODULE,
-	.open =			pkt_open,
-	.release =		pkt_close,
-	.ioctl =		pkt_ioctl,
+	.__open =			pkt_open,
+	.__release =		pkt_close,
+	.__ioctl =		pkt_ioctl,
 	.media_changed =	pkt_media_changed,
 };
 
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 5c45d5556ae8..9398af86a7aa 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -998,9 +998,9 @@ static int floppy_revalidate(struct gendisk *disk)
 }
 
 static struct block_device_operations floppy_fops = {
-	.open		= floppy_open,
-	.release	= floppy_release,
-	.ioctl		= floppy_ioctl,
+	.__open		= floppy_open,
+	.__release	= floppy_release,
+	.__ioctl		= floppy_ioctl,
 	.media_changed	= floppy_check_change,
 	.revalidate_disk= floppy_revalidate,
 };
diff --git a/drivers/block/ub.c b/drivers/block/ub.c
index bc04330f3683..5261773407da 100644
--- a/drivers/block/ub.c
+++ b/drivers/block/ub.c
@@ -1791,9 +1791,9 @@ static int ub_bd_media_changed(struct gendisk *disk)
 
 static struct block_device_operations ub_bd_fops = {
 	.owner		= THIS_MODULE,
-	.open		= ub_bd_open,
-	.release	= ub_bd_release,
-	.ioctl		= ub_bd_ioctl,
+	.__open		= ub_bd_open,
+	.__release	= ub_bd_release,
+	.__ioctl		= ub_bd_ioctl,
 	.media_changed	= ub_bd_media_changed,
 	.revalidate_disk = ub_bd_revalidate,
 };
diff --git a/drivers/block/viodasd.c b/drivers/block/viodasd.c
index 1730d29e6044..7f7beec29ebb 100644
--- a/drivers/block/viodasd.c
+++ b/drivers/block/viodasd.c
@@ -221,8 +221,8 @@ static int viodasd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
  */
 static struct block_device_operations viodasd_fops = {
 	.owner = THIS_MODULE,
-	.open = viodasd_open,
-	.release = viodasd_release,
+	.__open = viodasd_open,
+	.__release = viodasd_release,
 	.getgeo = viodasd_getgeo,
 };
 
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 7643cd16fd67..10f157ea7b0b 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -180,7 +180,7 @@ static int virtblk_getgeo(struct block_device *bd, struct hd_geometry *geo)
 }
 
 static struct block_device_operations virtblk_fops = {
-	.ioctl  = virtblk_ioctl,
+	.__ioctl  = virtblk_ioctl,
 	.owner  = THIS_MODULE,
 	.getgeo = virtblk_getgeo,
 };
diff --git a/drivers/block/xd.c b/drivers/block/xd.c
index 624d30f7da3f..316fa1da4b9c 100644
--- a/drivers/block/xd.c
+++ b/drivers/block/xd.c
@@ -132,7 +132,7 @@ static int xd_getgeo(struct block_device *bdev, struct hd_geometry *geo);
 
 static struct block_device_operations xd_fops = {
 	.owner	= THIS_MODULE,
-	.ioctl	= xd_ioctl,
+	.__ioctl	= xd_ioctl,
 	.getgeo = xd_getgeo,
 };
 static DECLARE_WAIT_QUEUE_HEAD(xd_wait_int);
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 1a50ae70f716..7efac80c8dde 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1041,8 +1041,8 @@ static int blkif_release(struct inode *inode, struct file *filep)
 static struct block_device_operations xlvbd_block_fops =
 {
 	.owner = THIS_MODULE,
-	.open = blkif_open,
-	.release = blkif_release,
+	.__open = blkif_open,
+	.__release = blkif_release,
 	.getgeo = blkif_getgeo,
 	.ioctl = blkif_ioctl,
 };
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index 4a7a059ebaf7..e4efe5b7ec22 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -919,8 +919,8 @@ static int ace_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 
 static struct block_device_operations ace_fops = {
 	.owner = THIS_MODULE,
-	.open = ace_open,
-	.release = ace_release,
+	.__open = ace_open,
+	.__release = ace_release,
 	.media_changed = ace_media_changed,
 	.revalidate_disk = ace_revalidate_disk,
 	.getgeo = ace_getgeo,
diff --git a/drivers/block/z2ram.c b/drivers/block/z2ram.c
index be20a67f1fa8..4860d0f36870 100644
--- a/drivers/block/z2ram.c
+++ b/drivers/block/z2ram.c
@@ -314,8 +314,8 @@ z2_release( struct inode *inode, struct file *filp )
 static struct block_device_operations z2_fops =
 {
 	.owner		= THIS_MODULE,
-	.open		= z2_open,
-	.release	= z2_release,
+	.__open		= z2_open,
+	.__release	= z2_release,
 };
 
 static struct kobject *z2_find(dev_t dev, int *part, void *data)
diff --git a/drivers/cdrom/gdrom.c b/drivers/cdrom/gdrom.c
index 0959edf2afdb..ab0c637f58be 100644
--- a/drivers/cdrom/gdrom.c
+++ b/drivers/cdrom/gdrom.c
@@ -514,10 +514,10 @@ static int gdrom_bdops_ioctl(struct inode *inode, struct file *file,
 
 static struct block_device_operations gdrom_bdops = {
 	.owner			= THIS_MODULE,
-	.open			= gdrom_bdops_open,
-	.release		= gdrom_bdops_release,
+	.__open			= gdrom_bdops_open,
+	.__release		= gdrom_bdops_release,
 	.media_changed		= gdrom_bdops_mediachanged,
-	.ioctl			= gdrom_bdops_ioctl,
+	.__ioctl			= gdrom_bdops_ioctl,
 };
 
 static irqreturn_t gdrom_command_interrupt(int irq, void *dev_id)
diff --git a/drivers/cdrom/viocd.c b/drivers/cdrom/viocd.c
index abc4079c3f41..57c2dced3e9d 100644
--- a/drivers/cdrom/viocd.c
+++ b/drivers/cdrom/viocd.c
@@ -180,9 +180,9 @@ static int viocd_blk_media_changed(struct gendisk *disk)
 
 struct block_device_operations viocd_fops = {
 	.owner =		THIS_MODULE,
-	.open =			viocd_blk_open,
-	.release =		viocd_blk_release,
-	.ioctl =		viocd_blk_ioctl,
+	.__open =			viocd_blk_open,
+	.__release =		viocd_blk_release,
+	.__ioctl =		viocd_blk_ioctl,
 	.media_changed =	viocd_blk_media_changed,
 };
 
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 87d90200b169..3533984355a6 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -2200,9 +2200,9 @@ static int idecd_revalidate_disk(struct gendisk *disk)
 
 static struct block_device_operations idecd_ops = {
 	.owner			= THIS_MODULE,
-	.open			= idecd_open,
-	.release		= idecd_release,
-	.ioctl			= idecd_ioctl,
+	.__open			= idecd_open,
+	.__release		= idecd_release,
+	.__ioctl			= idecd_ioctl,
 	.media_changed		= idecd_media_changed,
 	.revalidate_disk	= idecd_revalidate_disk
 };
diff --git a/drivers/ide/ide-gd.c b/drivers/ide/ide-gd.c
index 948af08abe23..d118bbed7cd3 100644
--- a/drivers/ide/ide-gd.c
+++ b/drivers/ide/ide-gd.c
@@ -298,9 +298,9 @@ static int ide_gd_ioctl(struct inode *inode, struct file *file,
 
 static struct block_device_operations ide_gd_ops = {
 	.owner			= THIS_MODULE,
-	.open			= ide_gd_open,
-	.release		= ide_gd_release,
-	.ioctl			= ide_gd_ioctl,
+	.__open			= ide_gd_open,
+	.__release		= ide_gd_release,
+	.__ioctl			= ide_gd_ioctl,
 	.getgeo			= ide_gd_getgeo,
 	.media_changed		= ide_gd_media_changed,
 	.revalidate_disk	= ide_gd_revalidate_disk
diff --git a/drivers/ide/ide-tape.c b/drivers/ide/ide-tape.c
index 2b263281ffea..c5df53c4838c 100644
--- a/drivers/ide/ide-tape.c
+++ b/drivers/ide/ide-tape.c
@@ -2376,9 +2376,9 @@ static int idetape_ioctl(struct inode *inode, struct file *file,
 
 static struct block_device_operations idetape_block_ops = {
 	.owner		= THIS_MODULE,
-	.open		= idetape_open,
-	.release	= idetape_release,
-	.ioctl		= idetape_ioctl,
+	.__open		= idetape_open,
+	.__release	= idetape_release,
+	.__ioctl		= idetape_ioctl,
 };
 
 static int ide_tape_probe(ide_drive_t *drive)
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 5f0f4c8bcd3e..8b4c92b1b6db 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1698,9 +1698,9 @@ int dm_noflush_suspending(struct dm_target *ti)
 EXPORT_SYMBOL_GPL(dm_noflush_suspending);
 
 static struct block_device_operations dm_blk_dops = {
-	.open = dm_blk_open,
-	.release = dm_blk_close,
-	.ioctl = dm_blk_ioctl,
+	.__open = dm_blk_open,
+	.__release = dm_blk_close,
+	.__ioctl = dm_blk_ioctl,
 	.getgeo = dm_blk_getgeo,
 	.owner = THIS_MODULE
 };
diff --git a/drivers/md/md.c b/drivers/md/md.c
index aaa3d465de4e..21b04d39ba3b 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5046,9 +5046,9 @@ static int md_revalidate(struct gendisk *disk)
 static struct block_device_operations md_fops =
 {
 	.owner		= THIS_MODULE,
-	.open		= md_open,
-	.release	= md_release,
-	.ioctl		= md_ioctl,
+	.__open		= md_open,
+	.__release	= md_release,
+	.__ioctl		= md_ioctl,
 	.getgeo		= md_getgeo,
 	.media_changed	= md_media_changed,
 	.revalidate_disk= md_revalidate,
diff --git a/drivers/memstick/core/mspro_block.c b/drivers/memstick/core/mspro_block.c
index 5263913e0c69..fbe5919789d0 100644
--- a/drivers/memstick/core/mspro_block.c
+++ b/drivers/memstick/core/mspro_block.c
@@ -237,8 +237,8 @@ static int mspro_block_bd_getgeo(struct block_device *bdev,
 }
 
 static struct block_device_operations ms_block_bdops = {
-	.open    = mspro_block_bd_open,
-	.release = mspro_block_bd_release,
+	.__open    = mspro_block_bd_open,
+	.__release = mspro_block_bd_release,
 	.getgeo  = mspro_block_bd_getgeo,
 	.owner   = THIS_MODULE
 };
diff --git a/drivers/message/i2o/i2o_block.c b/drivers/message/i2o/i2o_block.c
index 81483de8c0fd..71500dda8eb3 100644
--- a/drivers/message/i2o/i2o_block.c
+++ b/drivers/message/i2o/i2o_block.c
@@ -931,9 +931,9 @@ static void i2o_block_request_fn(struct request_queue *q)
 /* I2O Block device operations definition */
 static struct block_device_operations i2o_block_fops = {
 	.owner = THIS_MODULE,
-	.open = i2o_block_open,
-	.release = i2o_block_release,
-	.ioctl = i2o_block_ioctl,
+	.__open = i2o_block_open,
+	.__release = i2o_block_release,
+	.__ioctl = i2o_block_ioctl,
 	.getgeo = i2o_block_getgeo,
 	.media_changed = i2o_block_media_changed
 };
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 24c97d3d16bb..8cba06f5e11d 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -130,8 +130,8 @@ mmc_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 }
 
 static struct block_device_operations mmc_bdops = {
-	.open			= mmc_blk_open,
-	.release		= mmc_blk_release,
+	.__open			= mmc_blk_open,
+	.__release		= mmc_blk_release,
 	.getgeo			= mmc_blk_getgeo,
 	.owner			= THIS_MODULE,
 };
diff --git a/drivers/mtd/mtd_blkdevs.c b/drivers/mtd/mtd_blkdevs.c
index 681d5aca2af4..b00d07c53753 100644
--- a/drivers/mtd/mtd_blkdevs.c
+++ b/drivers/mtd/mtd_blkdevs.c
@@ -213,9 +213,9 @@ static int blktrans_ioctl(struct inode *inode, struct file *file,
 
 static struct block_device_operations mtd_blktrans_ops = {
 	.owner		= THIS_MODULE,
-	.open		= blktrans_open,
-	.release	= blktrans_release,
-	.ioctl		= blktrans_ioctl,
+	.__open		= blktrans_open,
+	.__release	= blktrans_release,
+	.__ioctl		= blktrans_ioctl,
 	.getgeo		= blktrans_getgeo,
 };
 
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 0a225ccda026..6bf68e5fe89f 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -2087,10 +2087,10 @@ static int dasd_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 struct block_device_operations
 dasd_device_operations = {
 	.owner		= THIS_MODULE,
-	.open		= dasd_open,
-	.release	= dasd_release,
-	.ioctl		= dasd_ioctl,
-	.compat_ioctl	= dasd_compat_ioctl,
+	.__open		= dasd_open,
+	.__release	= dasd_release,
+	.__ioctl		= dasd_ioctl,
+	.__compat_ioctl	= dasd_compat_ioctl,
 	.getgeo		= dasd_getgeo,
 };
 
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index a7ff167d5b81..413460cc3dd8 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -42,8 +42,8 @@ static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 static int dcssblk_major;
 static struct block_device_operations dcssblk_devops = {
 	.owner   	= THIS_MODULE,
-	.open    	= dcssblk_open,
-	.release 	= dcssblk_release,
+	.__open    	= dcssblk_open,
+	.__release 	= dcssblk_release,
 	.direct_access 	= dcssblk_direct_access,
 };
 
diff --git a/drivers/s390/char/tape_block.c b/drivers/s390/char/tape_block.c
index a25b8bf54f41..f1a741c9a6f0 100644
--- a/drivers/s390/char/tape_block.c
+++ b/drivers/s390/char/tape_block.c
@@ -52,9 +52,9 @@ static int tapeblock_revalidate_disk(struct gendisk *);
 
 static struct block_device_operations tapeblock_fops = {
 	.owner		 = THIS_MODULE,
-	.open		 = tapeblock_open,
-	.release	 = tapeblock_release,
-	.ioctl           = tapeblock_ioctl,
+	.__open		 = tapeblock_open,
+	.__release	 = tapeblock_release,
+	.__ioctl           = tapeblock_ioctl,
 	.media_changed   = tapeblock_medium_changed,
 	.revalidate_disk = tapeblock_revalidate_disk,
 };
diff --git a/drivers/scsi/ide-scsi.c b/drivers/scsi/ide-scsi.c
index 5bcc04e82c28..9069afbad9d3 100644
--- a/drivers/scsi/ide-scsi.c
+++ b/drivers/scsi/ide-scsi.c
@@ -483,9 +483,9 @@ static int idescsi_ide_ioctl(struct inode *inode, struct file *file,
 
 static struct block_device_operations idescsi_ops = {
 	.owner		= THIS_MODULE,
-	.open		= idescsi_ide_open,
-	.release	= idescsi_ide_release,
-	.ioctl		= idescsi_ide_ioctl,
+	.__open		= idescsi_ide_open,
+	.__release	= idescsi_ide_release,
+	.__ioctl		= idescsi_ide_ioctl,
 };
 
 static int idescsi_slave_configure(struct scsi_device * sdp)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 5a18528a69d0..c8b95e8d2859 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -962,12 +962,12 @@ static long sd_compat_ioctl(struct file *file, unsigned int cmd, unsigned long a
 
 static struct block_device_operations sd_fops = {
 	.owner			= THIS_MODULE,
-	.open			= sd_open,
-	.release		= sd_release,
-	.ioctl			= sd_ioctl,
+	.__open			= sd_open,
+	.__release		= sd_release,
+	.__ioctl			= sd_ioctl,
 	.getgeo			= sd_getgeo,
 #ifdef CONFIG_COMPAT
-	.compat_ioctl		= sd_compat_ioctl,
+	.__compat_ioctl		= sd_compat_ioctl,
 #endif
 	.media_changed		= sd_media_changed,
 	.revalidate_disk	= sd_revalidate_disk,
diff --git a/drivers/scsi/sr.c b/drivers/scsi/sr.c
index 2fb8d4d2d6f6..9446cbf4de84 100644
--- a/drivers/scsi/sr.c
+++ b/drivers/scsi/sr.c
@@ -540,9 +540,9 @@ static int sr_block_media_changed(struct gendisk *disk)
 static struct block_device_operations sr_bdops =
 {
 	.owner		= THIS_MODULE,
-	.open		= sr_block_open,
-	.release	= sr_block_release,
-	.ioctl		= sr_block_ioctl,
+	.__open		= sr_block_open,
+	.__release	= sr_block_release,
+	.__ioctl		= sr_block_ioctl,
 	.media_changed	= sr_block_media_changed,
 	/* 
 	 * No compat_ioctl for now because sr_block_ioctl never
diff --git a/fs/block_dev.c b/fs/block_dev.c
index b9022694e9f7..73b6ce47c861 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1033,8 +1033,13 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 		bdev->bd_contains = bdev;
 		if (!partno) {
 			struct backing_dev_info *bdi;
+			if (disk->fops->__open) {
+				ret = disk->fops->__open(bdev->bd_inode, file);
+				if (ret)
+					goto out_first;
+			}
 			if (disk->fops->open) {
-				ret = disk->fops->open(bdev->bd_inode, file);
+				ret = disk->fops->open(bdev, file->f_mode);
 				if (ret)
 					goto out_clear;
 			}
@@ -1074,8 +1079,13 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 		part = NULL;
 		disk = NULL;
 		if (bdev->bd_contains == bdev) {
+			if (bdev->bd_disk->fops->__open) {
+				ret = bdev->bd_disk->fops->__open(bdev->bd_inode, file);
+				if (ret)
+					goto out;
+			}
 			if (bdev->bd_disk->fops->open) {
-				ret = bdev->bd_disk->fops->open(bdev->bd_inode, file);
+				ret = bdev->bd_disk->fops->open(bdev, file->f_mode);
 				if (ret)
 					goto out_unlock_bdev;
 			}
@@ -1184,8 +1194,10 @@ static int __blkdev_put(struct block_device *bdev, int for_part)
 		kill_bdev(bdev);
 	}
 	if (bdev->bd_contains == bdev) {
+		if (disk->fops->__release)
+			ret = disk->fops->__release(bd_inode, NULL);
 		if (disk->fops->release)
-			ret = disk->fops->release(bd_inode, NULL);
+			ret = disk->fops->release(disk, 0);
 	}
 	if (!bdev->bd_openers) {
 		struct module *owner = disk->fops->owner;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2bad616b9949..b573186ff1a1 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1061,11 +1061,16 @@ struct file;
 struct inode;
 
 struct block_device_operations {
-	int (*open) (struct inode *, struct file *);
-	int (*release) (struct inode *, struct file *);
-	int (*ioctl) (struct inode *, struct file *, unsigned, unsigned long);
-	long (*unlocked_ioctl) (struct file *, unsigned, unsigned long);
-	long (*compat_ioctl) (struct file *, unsigned, unsigned long);
+	int (*__open) (struct inode *, struct file *);
+	int (*__release) (struct inode *, struct file *);
+	int (*__ioctl) (struct inode *, struct file *, unsigned, unsigned long);
+	long (*__unlocked_ioctl) (struct file *, unsigned, unsigned long);
+	long (*__compat_ioctl) (struct file *, unsigned, unsigned long);
+	int (*open) (struct block_device *, fmode_t);
+	int (*release) (struct gendisk *, fmode_t);
+	int (*locked_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*direct_access) (struct block_device *, sector_t,
 						void **, unsigned long *);
 	int (*media_changed) (struct gendisk *);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 58bbf689fef7..b5894604ba5e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -79,6 +79,7 @@ extern int dir_notify_enable;
 #define FMODE_NDELAY	((__force fmode_t)32)
 #define FMODE_EXCL	((__force fmode_t)64)
 #define FMODE_WRITE_IOCTL	((__force fmode_t)128)
+#define FMODE_NDELAY_NOW	((__force fmode_t)256)
 
 #define RW_MASK		1
 #define RWA_MASK	2
-- 
cgit v1.2.3


From 90b8f2824ce68dd87d304641a1d5a048dfff39f5 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 2 Mar 2008 10:43:36 -0500
Subject: [PATCH] end of methods switch: remove the old ones

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/compat_ioctl.c   | 12 ------------
 block/ioctl.c          | 26 --------------------------
 fs/block_dev.c         | 13 -------------
 include/linux/blkdev.h |  8 --------
 4 files changed, 59 deletions(-)

(limited to 'include')

diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 576c4fd15463..fd537fdb25a3 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -708,16 +708,6 @@ static int compat_blkdev_driver_ioctl(struct inode *inode, struct file *file,
 		return -ENOIOCTLCMD;
 	}
 
-	if (disk->fops->__unlocked_ioctl)
-		return disk->fops->__unlocked_ioctl(file, cmd, arg);
-
-	if (disk->fops->__ioctl) {
-		lock_kernel();
-		ret = disk->fops->__ioctl(inode, file, cmd, arg);
-		unlock_kernel();
-		return ret;
-	}
-
 	return __blkdev_driver_ioctl(inode->i_bdev, file->f_mode, cmd, arg);
 }
 
@@ -805,8 +795,6 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 
 	lock_kernel();
 	ret = compat_blkdev_locked_ioctl(inode, file, bdev, cmd, arg);
-	if (ret == -ENOIOCTLCMD && disk->fops->__compat_ioctl)
-		ret = disk->fops->__compat_ioctl(file, cmd, arg);
 	unlock_kernel();
 	if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl)
 		ret = disk->fops->compat_ioctl(bdev, file->f_mode, cmd, arg);
diff --git a/block/ioctl.c b/block/ioctl.c
index 01ff463bc801..0db89f95b15f 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -276,16 +276,6 @@ int blkdev_driver_ioctl(struct inode *inode, struct file *file,
 			mode |= FMODE_NDELAY_NOW;
 	}
 
-	if (disk->fops->__unlocked_ioctl)
-		return disk->fops->__unlocked_ioctl(file, cmd, arg);
-
-	if (disk->fops->__ioctl) {
-		lock_kernel();
-		ret = disk->fops->__ioctl(inode, file, cmd, arg);
-		unlock_kernel();
-		return ret;
-	}
-
 	return __blkdev_driver_ioctl(inode->i_bdev, mode, cmd, arg);
 }
 EXPORT_SYMBOL_GPL(blkdev_driver_ioctl);
@@ -295,22 +285,6 @@ int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
 {
 	struct gendisk *disk = bdev->bd_disk;
 	int ret;
-	/* you bet it'll go away by the end of patch series */
-	struct file fake_file = {};
-	struct dentry fake_dentry = {};
-	fake_file.f_mode = mode;
-	fake_file.f_path.dentry = &fake_dentry;
-	fake_dentry.d_inode = bdev->bd_inode;
-
-	if (disk->fops->__unlocked_ioctl)
-		return disk->fops->__unlocked_ioctl(&fake_file, cmd, arg);
-
-	if (disk->fops->__ioctl) {
-		lock_kernel();
-		ret = disk->fops->__ioctl(bdev->bd_inode, &fake_file, cmd, arg);
-		unlock_kernel();
-		return ret;
-	}
 
 	if (disk->fops->ioctl)
 		return disk->fops->ioctl(bdev, mode, cmd, arg);
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 73b6ce47c861..55124ac8c7ad 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1033,11 +1033,6 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 		bdev->bd_contains = bdev;
 		if (!partno) {
 			struct backing_dev_info *bdi;
-			if (disk->fops->__open) {
-				ret = disk->fops->__open(bdev->bd_inode, file);
-				if (ret)
-					goto out_first;
-			}
 			if (disk->fops->open) {
 				ret = disk->fops->open(bdev, file->f_mode);
 				if (ret)
@@ -1079,11 +1074,6 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 		part = NULL;
 		disk = NULL;
 		if (bdev->bd_contains == bdev) {
-			if (bdev->bd_disk->fops->__open) {
-				ret = bdev->bd_disk->fops->__open(bdev->bd_inode, file);
-				if (ret)
-					goto out;
-			}
 			if (bdev->bd_disk->fops->open) {
 				ret = bdev->bd_disk->fops->open(bdev, file->f_mode);
 				if (ret)
@@ -1180,7 +1170,6 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 static int __blkdev_put(struct block_device *bdev, int for_part)
 {
 	int ret = 0;
-	struct inode *bd_inode = bdev->bd_inode;
 	struct gendisk *disk = bdev->bd_disk;
 	struct block_device *victim = NULL;
 
@@ -1194,8 +1183,6 @@ static int __blkdev_put(struct block_device *bdev, int for_part)
 		kill_bdev(bdev);
 	}
 	if (bdev->bd_contains == bdev) {
-		if (disk->fops->__release)
-			ret = disk->fops->__release(bd_inode, NULL);
 		if (disk->fops->release)
 			ret = disk->fops->release(disk, 0);
 	}
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b573186ff1a1..a135256b272c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1057,15 +1057,7 @@ static inline int blk_integrity_rq(struct request *rq)
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
-struct file;
-struct inode;
-
 struct block_device_operations {
-	int (*__open) (struct inode *, struct file *);
-	int (*__release) (struct inode *, struct file *);
-	int (*__ioctl) (struct inode *, struct file *, unsigned, unsigned long);
-	long (*__unlocked_ioctl) (struct file *, unsigned, unsigned long);
-	long (*__compat_ioctl) (struct file *, unsigned, unsigned long);
 	int (*open) (struct block_device *, fmode_t);
 	int (*release) (struct gendisk *, fmode_t);
 	int (*locked_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-- 
cgit v1.2.3


From 9a1c3542768b5a58e45a9216921cd10a3bae1205 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 22 Feb 2008 20:40:24 -0500
Subject: [PATCH] pass fmode_t to blkdev_put()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/block/pktcdvd.c         |  8 ++++----
 drivers/char/raw.c              |  4 ++--
 drivers/md/dm-table.c           |  4 ++--
 drivers/md/md.c                 |  4 ++--
 drivers/s390/block/dasd_genhd.c |  2 +-
 fs/block_dev.c                  | 22 +++++++++++-----------
 fs/ext3/super.c                 |  4 ++--
 fs/ext4/super.c                 |  4 ++--
 fs/jfs/jfs_logmgr.c             |  4 ++--
 fs/ocfs2/cluster/heartbeat.c    |  4 ++--
 fs/partitions/check.c           |  2 +-
 fs/reiserfs/journal.c           |  4 ++--
 include/linux/fs.h              |  2 +-
 kernel/power/swap.c             |  8 ++++----
 14 files changed, 38 insertions(+), 38 deletions(-)

(limited to 'include')

diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 90548da9c1cb..ce8c71901923 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2381,7 +2381,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 out_unclaim:
 	bd_release(pd->bdev);
 out_putdev:
-	blkdev_put(pd->bdev);
+	blkdev_put(pd->bdev, FMODE_READ);
 out:
 	return ret;
 }
@@ -2399,7 +2399,7 @@ static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
 
 	pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
 	bd_release(pd->bdev);
-	blkdev_put(pd->bdev);
+	blkdev_put(pd->bdev, FMODE_READ);
 
 	pkt_shrink_pktlist(pd);
 }
@@ -2790,7 +2790,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	return 0;
 
 out_mem:
-	blkdev_put(bdev);
+	blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 	/* This is safe: open() is still holding a reference. */
 	module_put(THIS_MODULE);
 	return ret;
@@ -2975,7 +2975,7 @@ static int pkt_remove_dev(dev_t pkt_dev)
 	pkt_debugfs_dev_remove(pd);
 	pkt_sysfs_dev_remove(pd);
 
-	blkdev_put(pd->bdev);
+	blkdev_put(pd->bdev, FMODE_READ|FMODE_WRITE);
 
 	remove_proc_entry(pd->name, pkt_proc);
 	DPRINTK(DRIVER_NAME": writer %s unmapped\n", pd->name);
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index e139372d0e69..bfd59e6bf54f 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -87,7 +87,7 @@ static int raw_open(struct inode *inode, struct file *filp)
 out2:
 	bd_release(bdev);
 out1:
-	blkdev_put(bdev);
+	blkdev_put(bdev, filp->f_mode);
 out:
 	mutex_unlock(&raw_mutex);
 	return err;
@@ -112,7 +112,7 @@ static int raw_release(struct inode *inode, struct file *filp)
 	mutex_unlock(&raw_mutex);
 
 	bd_release(bdev);
-	blkdev_put(bdev);
+	blkdev_put(bdev, filp->f_mode);
 	return 0;
 }
 
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 7c8671b06fe3..dd8bd2e867cd 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -357,7 +357,7 @@ static int open_dev(struct dm_dev_internal *d, dev_t dev,
 		return PTR_ERR(bdev);
 	r = bd_claim_by_disk(bdev, _claim_ptr, dm_disk(md));
 	if (r)
-		blkdev_put(bdev);
+		blkdev_put(bdev, d->dm_dev.mode);
 	else
 		d->dm_dev.bdev = bdev;
 	return r;
@@ -372,7 +372,7 @@ static void close_dev(struct dm_dev_internal *d, struct mapped_device *md)
 		return;
 
 	bd_release_from_disk(d->dm_dev.bdev, dm_disk(md));
-	blkdev_put(d->dm_dev.bdev);
+	blkdev_put(d->dm_dev.bdev, d->dm_dev.mode);
 	d->dm_dev.bdev = NULL;
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 06ea991c7a40..c1a837ca193c 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -1520,7 +1520,7 @@ static int lock_rdev(mdk_rdev_t *rdev, dev_t dev, int shared)
 	if (err) {
 		printk(KERN_ERR "md: could not bd_claim %s.\n",
 			bdevname(bdev, b));
-		blkdev_put(bdev);
+		blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 		return err;
 	}
 	if (!shared)
@@ -1536,7 +1536,7 @@ static void unlock_rdev(mdk_rdev_t *rdev)
 	if (!bdev)
 		MD_BUG();
 	bd_release(bdev);
-	blkdev_put(bdev);
+	blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 }
 
 void md_autodetect_dev(dev_t dev);
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index aee6565aaf98..3c1b6915c9ad 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -152,7 +152,7 @@ void dasd_destroy_partitions(struct dasd_block *block)
 
 	invalidate_partition(block->gdp, 0);
 	/* Matching blkdev_put to the blkdev_get in dasd_scan_partitions. */
-	blkdev_put(bdev);
+	blkdev_put(bdev, FMODE_READ);
 	set_capacity(block->gdp, 0);
 }
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 55124ac8c7ad..05131baf3cf8 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -977,7 +977,7 @@ EXPORT_SYMBOL(bd_set_size);
 
 static int __blkdev_get(struct block_device *bdev, fmode_t mode, unsigned flags,
 			int for_part);
-static int __blkdev_put(struct block_device *bdev, int for_part);
+static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
 /*
  * bd_mutex locking:
@@ -1095,7 +1095,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 	bdev->bd_part = NULL;
 	bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
 	if (bdev != bdev->bd_contains)
-		__blkdev_put(bdev->bd_contains, 1);
+		__blkdev_put(bdev->bd_contains, file->f_mode, 1);
 	bdev->bd_contains = NULL;
  out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
@@ -1163,11 +1163,11 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	if (!(res = bd_claim(bdev, filp)))
 		return 0;
 
-	blkdev_put(bdev);
+	blkdev_put(bdev, filp->f_mode);
 	return res;
 }
 
-static int __blkdev_put(struct block_device *bdev, int for_part)
+static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 {
 	int ret = 0;
 	struct gendisk *disk = bdev->bd_disk;
@@ -1184,7 +1184,7 @@ static int __blkdev_put(struct block_device *bdev, int for_part)
 	}
 	if (bdev->bd_contains == bdev) {
 		if (disk->fops->release)
-			ret = disk->fops->release(disk, 0);
+			ret = disk->fops->release(disk, mode);
 	}
 	if (!bdev->bd_openers) {
 		struct module *owner = disk->fops->owner;
@@ -1203,13 +1203,13 @@ static int __blkdev_put(struct block_device *bdev, int for_part)
 	mutex_unlock(&bdev->bd_mutex);
 	bdput(bdev);
 	if (victim)
-		__blkdev_put(victim, 1);
+		__blkdev_put(victim, mode, 1);
 	return ret;
 }
 
-int blkdev_put(struct block_device *bdev)
+int blkdev_put(struct block_device *bdev, fmode_t mode)
 {
-	return __blkdev_put(bdev, 0);
+	return __blkdev_put(bdev, mode, 0);
 }
 EXPORT_SYMBOL(blkdev_put);
 
@@ -1218,7 +1218,7 @@ static int blkdev_close(struct inode * inode, struct file * filp)
 	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
 	if (bdev->bd_holder == filp)
 		bd_release(bdev);
-	return blkdev_put(bdev);
+	return blkdev_put(bdev, filp->f_mode);
 }
 
 static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
@@ -1343,7 +1343,7 @@ struct block_device *open_bdev_excl(const char *path, int flags, void *holder)
 	return bdev;
 	
 blkdev_put:
-	blkdev_put(bdev);
+	blkdev_put(bdev, mode);
 	return ERR_PTR(error);
 }
 
@@ -1359,7 +1359,7 @@ EXPORT_SYMBOL(open_bdev_excl);
 void close_bdev_excl(struct block_device *bdev)
 {
 	bd_release(bdev);
-	blkdev_put(bdev);
+	blkdev_put(bdev, 0);	/* move up in the next patches */
 }
 
 EXPORT_SYMBOL(close_bdev_excl);
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 3a260af5544d..15c38e69b694 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -347,7 +347,7 @@ fail:
 static int ext3_blkdev_put(struct block_device *bdev)
 {
 	bd_release(bdev);
-	return blkdev_put(bdev);
+	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 }
 
 static int ext3_blkdev_remove(struct ext3_sb_info *sbi)
@@ -2066,7 +2066,7 @@ static journal_t *ext3_get_dev_journal(struct super_block *sb,
 	if (bd_claim(bdev, sb)) {
 		printk(KERN_ERR
 		        "EXT3: failed to claim external journal device.\n");
-		blkdev_put(bdev);
+		blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 		return NULL;
 	}
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 9b2b2bc4ec17..c12cf7a657a9 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -399,7 +399,7 @@ fail:
 static int ext4_blkdev_put(struct block_device *bdev)
 {
 	bd_release(bdev);
-	return blkdev_put(bdev);
+	return blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 }
 
 static int ext4_blkdev_remove(struct ext4_sb_info *sbi)
@@ -2553,7 +2553,7 @@ static journal_t *ext4_get_dev_journal(struct super_block *sb,
 	if (bd_claim(bdev, sb)) {
 		printk(KERN_ERR
 			"EXT4: failed to claim external journal device.\n");
-		blkdev_put(bdev);
+		blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 		return NULL;
 	}
 
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index cd2ec2988b59..335c4de6552d 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1168,7 +1168,7 @@ journal_found:
 	bd_release(bdev);
 
       close:		/* close external log device */
-	blkdev_put(bdev);
+	blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 
       free:		/* free log descriptor */
 	mutex_unlock(&jfs_log_mutex);
@@ -1514,7 +1514,7 @@ int lmLogClose(struct super_block *sb)
 	rc = lmLogShutdown(log);
 
 	bd_release(bdev);
-	blkdev_put(bdev);
+	blkdev_put(bdev, FMODE_READ|FMODE_WRITE);
 
 	kfree(log);
 
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 7dce1612553e..4b6fdf591eed 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -976,7 +976,7 @@ static void o2hb_region_release(struct config_item *item)
 	}
 
 	if (reg->hr_bdev)
-		blkdev_put(reg->hr_bdev);
+		blkdev_put(reg->hr_bdev, FMODE_READ|FMODE_WRITE);
 
 	if (reg->hr_slots)
 		kfree(reg->hr_slots);
@@ -1358,7 +1358,7 @@ out:
 		iput(inode);
 	if (ret < 0) {
 		if (reg->hr_bdev) {
-			blkdev_put(reg->hr_bdev);
+			blkdev_put(reg->hr_bdev, FMODE_READ|FMODE_WRITE);
 			reg->hr_bdev = NULL;
 		}
 	}
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index cfb0c80690aa..5a35ff2e1a9b 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -488,7 +488,7 @@ void register_disk(struct gendisk *disk)
 	err = blkdev_get(bdev, FMODE_READ, 0);
 	if (err < 0)
 		goto exit;
-	blkdev_put(bdev);
+	blkdev_put(bdev, FMODE_READ);
 
 exit:
 	/* announce disk after possible partitions are created */
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index b89d193a00d9..3261518478f4 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2575,7 +2575,7 @@ static int release_journal_dev(struct super_block *super,
 	if (journal->j_dev_bd != NULL) {
 		if (journal->j_dev_bd->bd_dev != super->s_dev)
 			bd_release(journal->j_dev_bd);
-		result = blkdev_put(journal->j_dev_bd);
+		result = blkdev_put(journal->j_dev_bd, 0); /* move up */
 		journal->j_dev_bd = NULL;
 	}
 
@@ -2618,7 +2618,7 @@ static int journal_init_dev(struct super_block *super,
 		} else if (jdev != super->s_dev) {
 			result = bd_claim(journal->j_dev_bd, journal);
 			if (result) {
-				blkdev_put(journal->j_dev_bd);
+				blkdev_put(journal->j_dev_bd, blkdev_mode);
 				return result;
 			}
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b5894604ba5e..04c8dc41f454 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1722,7 +1722,7 @@ extern int blkdev_driver_ioctl(struct inode *inode, struct file *file,
 			       unsigned long arg);
 extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
 extern int blkdev_get(struct block_device *, fmode_t, unsigned);
-extern int blkdev_put(struct block_device *);
+extern int blkdev_put(struct block_device *, fmode_t);
 extern int bd_claim(struct block_device *, void *);
 extern void bd_release(struct block_device *);
 #ifdef CONFIG_SYSFS
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 80ccac849e46..7b9d611c1106 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -178,7 +178,7 @@ static int swsusp_swap_check(void) /* This is called before saving image */
 
 	res = set_blocksize(resume_bdev, PAGE_SIZE);
 	if (res < 0)
-		blkdev_put(resume_bdev);
+		blkdev_put(resume_bdev, FMODE_WRITE);
 
 	return res;
 }
@@ -574,7 +574,7 @@ int swsusp_read(unsigned int *flags_p)
 		error = load_image(&handle, &snapshot, header->pages - 1);
 	release_swap_reader(&handle);
 
-	blkdev_put(resume_bdev);
+	blkdev_put(resume_bdev, FMODE_READ);
 
 	if (!error)
 		pr_debug("PM: Image successfully loaded\n");
@@ -609,7 +609,7 @@ int swsusp_check(void)
 			return -EINVAL;
 		}
 		if (error)
-			blkdev_put(resume_bdev);
+			blkdev_put(resume_bdev, FMODE_READ);
 		else
 			pr_debug("PM: Signature found, resuming\n");
 	} else {
@@ -633,7 +633,7 @@ void swsusp_close(void)
 		return;
 	}
 
-	blkdev_put(resume_bdev);
+	blkdev_put(resume_bdev, 0); /* move up */
 }
 
 static int swsusp_header_init(void)
-- 
cgit v1.2.3


From 30c40d2c01f68c7eb1a41ab3552bdaf5dbf300d4 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 22 Feb 2008 19:50:45 -0500
Subject: [PATCH] propagate mode through open_bdev_excl/close_bdev_excl

replace open_bdev_excl/close_bdev_excl with variants taking fmode_t.
superblock gets the value used to mount it stored in sb->s_mode

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/mtd/devices/block2mtd.c |  4 ++--
 fs/block_dev.c                  | 24 +++++++++++-------------
 fs/reiserfs/journal.c           |  3 ++-
 fs/super.c                      | 14 ++++++++++----
 fs/xfs/linux-2.6/xfs_super.c    |  4 ++--
 include/linux/fs.h              |  6 ++++--
 6 files changed, 31 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/drivers/mtd/devices/block2mtd.c b/drivers/mtd/devices/block2mtd.c
index 91fbba767635..8c295f40d2ac 100644
--- a/drivers/mtd/devices/block2mtd.c
+++ b/drivers/mtd/devices/block2mtd.c
@@ -224,7 +224,7 @@ static void block2mtd_free_device(struct block2mtd_dev *dev)
 	if (dev->blkdev) {
 		invalidate_mapping_pages(dev->blkdev->bd_inode->i_mapping,
 					0, -1);
-		close_bdev_excl(dev->blkdev);
+		close_bdev_exclusive(dev->blkdev, FMODE_READ|FMODE_WRITE);
 	}
 
 	kfree(dev);
@@ -246,7 +246,7 @@ static struct block2mtd_dev *add_device(char *devname, int erase_size)
 		return NULL;
 
 	/* Get a handle on the device */
-	bdev = open_bdev_excl(devname, O_RDWR, NULL);
+	bdev = open_bdev_exclusive(devname, FMODE_READ|FMODE_WRITE, NULL);
 #ifndef MODULE
 	if (IS_ERR(bdev)) {
 
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 05131baf3cf8..4b595904cefd 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1309,32 +1309,29 @@ fail:
 EXPORT_SYMBOL(lookup_bdev);
 
 /**
- * open_bdev_excl  -  open a block device by name and set it up for use
+ * open_bdev_exclusive  -  open a block device by name and set it up for use
  *
  * @path:	special file representing the block device
- * @flags:	%MS_RDONLY for opening read-only
+ * @mode:	FMODE_... combination to pass be used
  * @holder:	owner for exclusion
  *
  * Open the blockdevice described by the special file at @path, claim it
  * for the @holder.
  */
-struct block_device *open_bdev_excl(const char *path, int flags, void *holder)
+struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *holder)
 {
 	struct block_device *bdev;
-	fmode_t mode = FMODE_READ;
 	int error = 0;
 
 	bdev = lookup_bdev(path);
 	if (IS_ERR(bdev))
 		return bdev;
 
-	if (!(flags & MS_RDONLY))
-		mode |= FMODE_WRITE;
 	error = blkdev_get(bdev, mode, 0);
 	if (error)
 		return ERR_PTR(error);
 	error = -EACCES;
-	if (!(flags & MS_RDONLY) && bdev_read_only(bdev))
+	if ((mode & FMODE_WRITE) && bdev_read_only(bdev))
 		goto blkdev_put;
 	error = bd_claim(bdev, holder);
 	if (error)
@@ -1347,22 +1344,23 @@ blkdev_put:
 	return ERR_PTR(error);
 }
 
-EXPORT_SYMBOL(open_bdev_excl);
+EXPORT_SYMBOL(open_bdev_exclusive);
 
 /**
- * close_bdev_excl  -  release a blockdevice openen by open_bdev_excl()
+ * close_bdev_exclusive  -  close a blockdevice opened by open_bdev_exclusive()
  *
  * @bdev:	blockdevice to close
+ * @mode:	mode, must match that used to open.
  *
- * This is the counterpart to open_bdev_excl().
+ * This is the counterpart to open_bdev_exclusive().
  */
-void close_bdev_excl(struct block_device *bdev)
+void close_bdev_exclusive(struct block_device *bdev, fmode_t mode)
 {
 	bd_release(bdev);
-	blkdev_put(bdev, 0);	/* move up in the next patches */
+	blkdev_put(bdev, mode);
 }
 
-EXPORT_SYMBOL(close_bdev_excl);
+EXPORT_SYMBOL(close_bdev_exclusive);
 
 int __invalidate_device(struct block_device *bdev)
 {
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 3261518478f4..70b896076676 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2628,7 +2628,8 @@ static int journal_init_dev(struct super_block *super,
 		return 0;
 	}
 
-	journal->j_dev_bd = open_bdev_excl(jdev_name, 0, journal);
+	journal->j_dev_bd = open_bdev_exclusive(jdev_name,
+						FMODE_READ|FMODE_WRITE, journal);
 	if (IS_ERR(journal->j_dev_bd)) {
 		result = PTR_ERR(journal->j_dev_bd);
 		journal->j_dev_bd = NULL;
diff --git a/fs/super.c b/fs/super.c
index e931ae9511fe..0d77ac20d03e 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -760,9 +760,13 @@ int get_sb_bdev(struct file_system_type *fs_type,
 {
 	struct block_device *bdev;
 	struct super_block *s;
+	fmode_t mode = FMODE_READ;
 	int error = 0;
 
-	bdev = open_bdev_excl(dev_name, flags, fs_type);
+	if (!(flags & MS_RDONLY))
+		mode |= FMODE_WRITE;
+
+	bdev = open_bdev_exclusive(dev_name, mode, fs_type);
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 
@@ -785,11 +789,12 @@ int get_sb_bdev(struct file_system_type *fs_type,
 			goto error_bdev;
 		}
 
-		close_bdev_excl(bdev);
+		close_bdev_exclusive(bdev, mode);
 	} else {
 		char b[BDEVNAME_SIZE];
 
 		s->s_flags = flags;
+		s->s_mode = mode;
 		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
 		sb_set_blocksize(s, block_size(bdev));
 		error = fill_super(s, data, flags & MS_SILENT ? 1 : 0);
@@ -807,7 +812,7 @@ int get_sb_bdev(struct file_system_type *fs_type,
 error_s:
 	error = PTR_ERR(s);
 error_bdev:
-	close_bdev_excl(bdev);
+	close_bdev_exclusive(bdev, mode);
 error:
 	return error;
 }
@@ -817,10 +822,11 @@ EXPORT_SYMBOL(get_sb_bdev);
 void kill_block_super(struct super_block *sb)
 {
 	struct block_device *bdev = sb->s_bdev;
+	fmode_t mode = sb->s_mode;
 
 	generic_shutdown_super(sb);
 	sync_blockdev(bdev);
-	close_bdev_excl(bdev);
+	close_bdev_exclusive(bdev, mode);
 }
 
 EXPORT_SYMBOL(kill_block_super);
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index e39013619b26..37ebe36056eb 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -589,7 +589,7 @@ xfs_blkdev_get(
 {
 	int			error = 0;
 
-	*bdevp = open_bdev_excl(name, 0, mp);
+	*bdevp = open_bdev_exclusive(name, FMODE_READ|FMODE_WRITE, mp);
 	if (IS_ERR(*bdevp)) {
 		error = PTR_ERR(*bdevp);
 		printk("XFS: Invalid device [%s], error=%d\n", name, error);
@@ -603,7 +603,7 @@ xfs_blkdev_put(
 	struct block_device	*bdev)
 {
 	if (bdev)
-		close_bdev_excl(bdev);
+		close_bdev_exclusive(bdev, FMODE_READ|FMODE_WRITE);
 }
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 04c8dc41f454..c6766314dc5e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1157,6 +1157,7 @@ struct super_block {
 	char s_id[32];				/* Informational name */
 
 	void 			*s_fs_info;	/* Filesystem private info */
+	fmode_t			s_mode;
 
 	/*
 	 * The next field is for VFS *only*. No filesystems have any business
@@ -1753,9 +1754,10 @@ extern void chrdev_show(struct seq_file *,off_t);
 extern const char *__bdevname(dev_t, char *buffer);
 extern const char *bdevname(struct block_device *bdev, char *buffer);
 extern struct block_device *lookup_bdev(const char *);
-extern struct block_device *open_bdev_excl(const char *, int, void *);
-extern void close_bdev_excl(struct block_device *);
+extern struct block_device *open_bdev_exclusive(const char *, fmode_t, void *);
+extern void close_bdev_exclusive(struct block_device *, fmode_t);
 extern void blkdev_show(struct seq_file *,off_t);
+
 #else
 #define BLKDEV_MAJOR_HASH_SIZE	0
 #endif
-- 
cgit v1.2.3


From e5eb8caa83a76191feb9705c1a0a689ca260b91e Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 8 Oct 2007 13:24:05 -0400
Subject: [PATCH] remember mode of reiserfs journal

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/reiserfs/journal.c          | 6 ++++--
 include/linux/reiserfs_fs_sb.h | 1 +
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index 70b896076676..9643c3bbeb3b 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -2575,7 +2575,7 @@ static int release_journal_dev(struct super_block *super,
 	if (journal->j_dev_bd != NULL) {
 		if (journal->j_dev_bd->bd_dev != super->s_dev)
 			bd_release(journal->j_dev_bd);
-		result = blkdev_put(journal->j_dev_bd, 0); /* move up */
+		result = blkdev_put(journal->j_dev_bd, journal->j_dev_mode);
 		journal->j_dev_bd = NULL;
 	}
 
@@ -2608,6 +2608,7 @@ static int journal_init_dev(struct super_block *super,
 	/* there is no "jdev" option and journal is on separate device */
 	if ((!jdev_name || !jdev_name[0])) {
 		journal->j_dev_bd = open_by_devnum(jdev, blkdev_mode);
+		journal->j_dev_mode = blkdev_mode;
 		if (IS_ERR(journal->j_dev_bd)) {
 			result = PTR_ERR(journal->j_dev_bd);
 			journal->j_dev_bd = NULL;
@@ -2628,8 +2629,9 @@ static int journal_init_dev(struct super_block *super,
 		return 0;
 	}
 
+	journal->j_dev_mode = blkdev_mode;
 	journal->j_dev_bd = open_bdev_exclusive(jdev_name,
-						FMODE_READ|FMODE_WRITE, journal);
+						blkdev_mode, journal);
 	if (IS_ERR(journal->j_dev_bd)) {
 		result = PTR_ERR(journal->j_dev_bd);
 		journal->j_dev_bd = NULL;
diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h
index 315517e8bfa1..bda6b562a1e0 100644
--- a/include/linux/reiserfs_fs_sb.h
+++ b/include/linux/reiserfs_fs_sb.h
@@ -178,6 +178,7 @@ struct reiserfs_journal {
 	struct reiserfs_journal_cnode *j_first;	/*  oldest journal block.  start here for traverse */
 
 	struct block_device *j_dev_bd;
+	fmode_t j_dev_mode;
 	int j_1st_reserved_block;	/* first block on s_dev of reserved area journal */
 
 	unsigned long j_state;
-- 
cgit v1.2.3


From 572c48921574dbe6dceb958cf965aa962baefde4 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 8 Oct 2007 13:24:05 -0400
Subject: [PATCH] sanitize blkdev_get() and friends

* get rid of fake struct file/struct dentry in __blkdev_get()
* merge __blkdev_get() and do_open()
* get rid of flags argument of blkdev_get()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/block/pktcdvd.c         |  4 +--
 drivers/char/raw.c              |  2 +-
 drivers/s390/block/dasd_genhd.c |  2 +-
 fs/block_dev.c                  | 65 ++++++++++++++---------------------------
 fs/ocfs2/cluster/heartbeat.c    |  2 +-
 fs/partitions/check.c           |  2 +-
 include/linux/fs.h              |  2 +-
 kernel/power/swap.c             |  2 +-
 8 files changed, 30 insertions(+), 51 deletions(-)

(limited to 'include')

diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index ce8c71901923..f20bf359b84f 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -2332,7 +2332,7 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 	 * so bdget() can't fail.
 	 */
 	bdget(pd->bdev->bd_dev);
-	if ((ret = blkdev_get(pd->bdev, FMODE_READ, O_RDONLY)))
+	if ((ret = blkdev_get(pd->bdev, FMODE_READ)))
 		goto out;
 
 	if ((ret = bd_claim(pd->bdev, pd)))
@@ -2765,7 +2765,7 @@ static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
 	bdev = bdget(dev);
 	if (!bdev)
 		return -ENOMEM;
-	ret = blkdev_get(bdev, FMODE_READ, O_RDONLY | O_NONBLOCK);
+	ret = blkdev_get(bdev, FMODE_READ | FMODE_NDELAY);
 	if (ret)
 		return ret;
 
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index bfd59e6bf54f..f3cf5eb9b7fb 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -65,7 +65,7 @@ static int raw_open(struct inode *inode, struct file *filp)
 	if (!bdev)
 		goto out;
 	igrab(bdev->bd_inode);
-	err = blkdev_get(bdev, filp->f_mode, 0);
+	err = blkdev_get(bdev, filp->f_mode);
 	if (err)
 		goto out;
 	err = bd_claim(bdev, raw_open);
diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
index 3c1b6915c9ad..e99d566b69cc 100644
--- a/drivers/s390/block/dasd_genhd.c
+++ b/drivers/s390/block/dasd_genhd.c
@@ -99,7 +99,7 @@ int dasd_scan_partitions(struct dasd_block *block)
 	struct block_device *bdev;
 
 	bdev = bdget_disk(block->gdp, 0);
-	if (!bdev || blkdev_get(bdev, FMODE_READ, 1) < 0)
+	if (!bdev || blkdev_get(bdev, FMODE_READ) < 0)
 		return -ENODEV;
 	/*
 	 * See fs/partition/check.c:register_disk,rescan_partitions
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 4b595904cefd..b89c956e04f6 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -844,9 +844,8 @@ struct block_device *open_by_devnum(dev_t dev, fmode_t mode)
 {
 	struct block_device *bdev = bdget(dev);
 	int err = -ENOMEM;
-	int flags = mode & FMODE_WRITE ? O_RDWR : O_RDONLY;
 	if (bdev)
-		err = blkdev_get(bdev, mode, flags);
+		err = blkdev_get(bdev, mode);
 	return err ? ERR_PTR(err) : bdev;
 }
 
@@ -975,8 +974,6 @@ void bd_set_size(struct block_device *bdev, loff_t size)
 }
 EXPORT_SYMBOL(bd_set_size);
 
-static int __blkdev_get(struct block_device *bdev, fmode_t mode, unsigned flags,
-			int for_part);
 static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
 
 /*
@@ -986,7 +983,7 @@ static int __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);
  *    mutex_lock_nested(whole->bd_mutex, 1)
  */
 
-static int do_open(struct block_device *bdev, struct file *file, int for_part)
+static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 {
 	struct gendisk *disk;
 	struct hd_struct *part = NULL;
@@ -994,9 +991,9 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 	int partno;
 	int perm = 0;
 
-	if (file->f_mode & FMODE_READ)
+	if (mode & FMODE_READ)
 		perm |= MAY_READ;
-	if (file->f_mode & FMODE_WRITE)
+	if (mode & FMODE_WRITE)
 		perm |= MAY_WRITE;
 	/*
 	 * hooks: /n/, see "layering violations".
@@ -1007,15 +1004,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 		return ret;
 	}
 
-	if (file->f_flags & O_NDELAY)
-		file->f_mode |= FMODE_NDELAY;
-	if (file->f_flags & O_EXCL)
-		file->f_mode |= FMODE_EXCL;
-	if ((file->f_flags & O_ACCMODE) == 3)
-		file->f_mode |= FMODE_WRITE_IOCTL;
-
 	ret = -ENXIO;
-	file->f_mapping = bdev->bd_inode->i_mapping;
 
 	lock_kernel();
 
@@ -1034,7 +1023,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 		if (!partno) {
 			struct backing_dev_info *bdi;
 			if (disk->fops->open) {
-				ret = disk->fops->open(bdev, file->f_mode);
+				ret = disk->fops->open(bdev, mode);
 				if (ret)
 					goto out_clear;
 			}
@@ -1054,7 +1043,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 			if (!whole)
 				goto out_clear;
 			BUG_ON(for_part);
-			ret = __blkdev_get(whole, file->f_mode, file->f_flags, 1);
+			ret = __blkdev_get(whole, mode, 1);
 			if (ret)
 				goto out_clear;
 			bdev->bd_contains = whole;
@@ -1075,7 +1064,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 		disk = NULL;
 		if (bdev->bd_contains == bdev) {
 			if (bdev->bd_disk->fops->open) {
-				ret = bdev->bd_disk->fops->open(bdev, file->f_mode);
+				ret = bdev->bd_disk->fops->open(bdev, mode);
 				if (ret)
 					goto out_unlock_bdev;
 			}
@@ -1095,7 +1084,7 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 	bdev->bd_part = NULL;
 	bdev->bd_inode->i_data.backing_dev_info = &default_backing_dev_info;
 	if (bdev != bdev->bd_contains)
-		__blkdev_put(bdev->bd_contains, file->f_mode, 1);
+		__blkdev_put(bdev->bd_contains, mode, 1);
 	bdev->bd_contains = NULL;
  out_unlock_bdev:
 	mutex_unlock(&bdev->bd_mutex);
@@ -1111,28 +1100,9 @@ static int do_open(struct block_device *bdev, struct file *file, int for_part)
 	return ret;
 }
 
-static int __blkdev_get(struct block_device *bdev, fmode_t mode, unsigned flags,
-			int for_part)
-{
-	/*
-	 * This crockload is due to bad choice of ->open() type.
-	 * It will go away.
-	 * For now, block device ->open() routine must _not_
-	 * examine anything in 'inode' argument except ->i_rdev.
-	 */
-	struct file fake_file = {};
-	struct dentry fake_dentry = {};
-	fake_file.f_mode = mode;
-	fake_file.f_flags = flags;
-	fake_file.f_path.dentry = &fake_dentry;
-	fake_dentry.d_inode = bdev->bd_inode;
-
-	return do_open(bdev, &fake_file, for_part);
-}
-
-int blkdev_get(struct block_device *bdev, fmode_t mode, unsigned flags)
+int blkdev_get(struct block_device *bdev, fmode_t mode)
 {
-	return __blkdev_get(bdev, mode, flags, 0);
+	return __blkdev_get(bdev, mode, 0);
 }
 EXPORT_SYMBOL(blkdev_get);
 
@@ -1149,15 +1119,24 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 	 */
 	filp->f_flags |= O_LARGEFILE;
 
+	if (filp->f_flags & O_NDELAY)
+		filp->f_mode |= FMODE_NDELAY;
+	if (filp->f_flags & O_EXCL)
+		filp->f_mode |= FMODE_EXCL;
+	if ((filp->f_flags & O_ACCMODE) == 3)
+		filp->f_mode |= FMODE_WRITE_IOCTL;
+
 	bdev = bd_acquire(inode);
 	if (bdev == NULL)
 		return -ENOMEM;
 
-	res = do_open(bdev, filp, 0);
+	filp->f_mapping = bdev->bd_inode->i_mapping;
+
+	res = blkdev_get(bdev, filp->f_mode);
 	if (res)
 		return res;
 
-	if (!(filp->f_flags & O_EXCL) )
+	if (!(filp->f_mode & FMODE_EXCL))
 		return 0;
 
 	if (!(res = bd_claim(bdev, filp)))
@@ -1327,7 +1306,7 @@ struct block_device *open_bdev_exclusive(const char *path, fmode_t mode, void *h
 	if (IS_ERR(bdev))
 		return bdev;
 
-	error = blkdev_get(bdev, mode, 0);
+	error = blkdev_get(bdev, mode);
 	if (error)
 		return ERR_PTR(error);
 	error = -EACCES;
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 4b6fdf591eed..6ebaa58e2c03 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -1268,7 +1268,7 @@ static ssize_t o2hb_region_dev_write(struct o2hb_region *reg,
 		goto out;
 
 	reg->hr_bdev = I_BDEV(filp->f_mapping->host);
-	ret = blkdev_get(reg->hr_bdev, FMODE_WRITE | FMODE_READ, 0);
+	ret = blkdev_get(reg->hr_bdev, FMODE_WRITE | FMODE_READ);
 	if (ret) {
 		reg->hr_bdev = NULL;
 		goto out;
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 5a35ff2e1a9b..633f7a0ebb2c 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -485,7 +485,7 @@ void register_disk(struct gendisk *disk)
 		goto exit;
 
 	bdev->bd_invalidated = 1;
-	err = blkdev_get(bdev, FMODE_READ, 0);
+	err = blkdev_get(bdev, FMODE_READ);
 	if (err < 0)
 		goto exit;
 	blkdev_put(bdev, FMODE_READ);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c6766314dc5e..cb78e389699b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1722,7 +1722,7 @@ extern int blkdev_driver_ioctl(struct inode *inode, struct file *file,
 			       struct gendisk *disk, unsigned cmd,
 			       unsigned long arg);
 extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
-extern int blkdev_get(struct block_device *, fmode_t, unsigned);
+extern int blkdev_get(struct block_device *, fmode_t);
 extern int blkdev_put(struct block_device *, fmode_t);
 extern int bd_claim(struct block_device *, void *);
 extern void bd_release(struct block_device *);
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index 178b001a4f17..b7713b53d07a 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -172,7 +172,7 @@ static int swsusp_swap_check(void) /* This is called before saving image */
 		return res;
 
 	root_swap = res;
-	res = blkdev_get(resume_bdev, FMODE_WRITE, O_RDWR);
+	res = blkdev_get(resume_bdev, FMODE_WRITE);
 	if (res)
 		return res;
 
-- 
cgit v1.2.3


From e436fdae70a31102d2be32969b80fe8545edebd9 Mon Sep 17 00:00:00 2001
From: Al Viro <al@aretha.pdmi.ras.ru>
Date: Thu, 18 Sep 2008 03:38:12 -0400
Subject: [PATCH] get rid of blkdev_driver_ioctl()

convert remaining callers to __blkdev_driver_ioctl()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/ioctl.c      | 29 ++++++++++-------------------
 include/linux/fs.h |  3 ---
 2 files changed, 10 insertions(+), 22 deletions(-)

(limited to 'include')

diff --git a/block/ioctl.c b/block/ioctl.c
index 0db89f95b15f..b4e0abed1b4b 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -265,21 +265,6 @@ static int blkdev_locked_ioctl(struct file *file, struct block_device *bdev,
 	return -ENOIOCTLCMD;
 }
 
-int blkdev_driver_ioctl(struct inode *inode, struct file *file,
-			struct gendisk *disk, unsigned cmd, unsigned long arg)
-{
-	int ret;
-	fmode_t mode = 0;
-	if (file) {
-		mode = file->f_mode;
-		if (file->f_flags & O_NDELAY)
-			mode |= FMODE_NDELAY_NOW;
-	}
-
-	return __blkdev_driver_ioctl(inode->i_bdev, mode, cmd, arg);
-}
-EXPORT_SYMBOL_GPL(blkdev_driver_ioctl);
-
 int __blkdev_driver_ioctl(struct block_device *bdev, fmode_t mode,
 			unsigned cmd, unsigned long arg)
 {
@@ -315,13 +300,19 @@ int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
 	struct block_device *bdev = inode->i_bdev;
 	struct gendisk *disk = bdev->bd_disk;
 	int ret, n;
+	fmode_t mode = 0;
+	if (file) {
+		mode = file->f_mode;
+		if (file->f_flags & O_NDELAY)
+			mode |= FMODE_NDELAY_NOW;
+	}
 
 	switch(cmd) {
 	case BLKFLSBUF:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EACCES;
 
-		ret = blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+		ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
 		/* -EINVAL to handle old uncorrected drivers */
 		if (ret != -EINVAL && ret != -ENOTTY)
 			return ret;
@@ -333,7 +324,7 @@ int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
 		return 0;
 
 	case BLKROSET:
-		ret = blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+		ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
 		/* -EINVAL to handle old uncorrected drivers */
 		if (ret != -EINVAL && ret != -ENOTTY)
 			return ret;
@@ -349,7 +340,7 @@ int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
 	case BLKDISCARD: {
 		uint64_t range[2];
 
-		if (!(file->f_mode & FMODE_WRITE))
+		if (!(mode & FMODE_WRITE))
 			return -EBADF;
 
 		if (copy_from_user(range, (void __user *)arg, sizeof(range)))
@@ -387,6 +378,6 @@ int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
 	if (ret != -ENOIOCTLCMD)
 		return ret;
 
-	return blkdev_driver_ioctl(inode, file, disk, cmd, arg);
+	ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg);
 }
 EXPORT_SYMBOL_GPL(blkdev_ioctl);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cb78e389699b..11de682c65a1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1718,9 +1718,6 @@ extern const struct file_operations def_fifo_fops;
 #ifdef CONFIG_BLOCK
 extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
 extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long);
-extern int blkdev_driver_ioctl(struct inode *inode, struct file *file,
-			       struct gendisk *disk, unsigned cmd,
-			       unsigned long arg);
 extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
 extern int blkdev_get(struct block_device *, fmode_t);
 extern int blkdev_put(struct block_device *, fmode_t);
-- 
cgit v1.2.3


From 56b26add02b4bdea81d5e0ebda60db1fe3311ad4 Mon Sep 17 00:00:00 2001
From: Al Viro <al@aretha.pdmi.ras.ru>
Date: Fri, 19 Sep 2008 03:17:36 -0400
Subject: [PATCH] kill the rest of struct file propagation in block ioctls

Now we can switch blkdev_ioctl() block_device/mode

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 block/compat_ioctl.c | 10 +++++-----
 block/ioctl.c        |  9 +--------
 drivers/char/raw.c   |  2 +-
 fs/block_dev.c       |  8 ++++++--
 include/linux/fs.h   |  2 +-
 5 files changed, 14 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/block/compat_ioctl.c b/block/compat_ioctl.c
index 5b3db0640d87..3098c92402fd 100644
--- a/block/compat_ioctl.c
+++ b/block/compat_ioctl.c
@@ -177,7 +177,7 @@ struct compat_blkpg_ioctl_arg {
 	compat_caddr_t data;
 };
 
-static int compat_blkpg_ioctl(struct inode *inode, struct file *file,
+static int compat_blkpg_ioctl(struct block_device *bdev, fmode_t mode,
 		unsigned int cmd, struct compat_blkpg_ioctl_arg __user *ua32)
 {
 	struct blkpg_ioctl_arg __user *a = compat_alloc_user_space(sizeof(*a));
@@ -196,7 +196,7 @@ static int compat_blkpg_ioctl(struct inode *inode, struct file *file,
 	if (err)
 		return err;
 
-	return blkdev_ioctl(inode, file, cmd, (unsigned long)a);
+	return blkdev_ioctl(bdev, mode, cmd, (unsigned long)a);
 }
 
 #define BLKBSZGET_32		_IOR(0x12, 112, int)
@@ -715,13 +715,13 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 	 * but we call blkdev_ioctl, which gets the lock for us
 	 */
 	case BLKRRPART:
-		return blkdev_ioctl(inode, file, cmd,
+		return blkdev_ioctl(bdev, mode, cmd,
 				(unsigned long)compat_ptr(arg));
 	case BLKBSZSET_32:
-		return blkdev_ioctl(inode, file, BLKBSZSET,
+		return blkdev_ioctl(bdev, mode, BLKBSZSET,
 				(unsigned long)compat_ptr(arg));
 	case BLKPG:
-		return compat_blkpg_ioctl(inode, file, cmd, compat_ptr(arg));
+		return compat_blkpg_ioctl(bdev, mode, cmd, compat_ptr(arg));
 	case BLKRAGET:
 	case BLKFRAGET:
 		if (!arg)
diff --git a/block/ioctl.c b/block/ioctl.c
index 14b7f2c10662..c832d639b6e2 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -230,20 +230,13 @@ EXPORT_SYMBOL_GPL(__blkdev_driver_ioctl);
  * always keep this in sync with compat_blkdev_ioctl() and
  * compat_blkdev_locked_ioctl()
  */
-int blkdev_ioctl(struct inode *inode, struct file *file, unsigned cmd,
+int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 			unsigned long arg)
 {
-	struct block_device *bdev = inode->i_bdev;
 	struct gendisk *disk = bdev->bd_disk;
 	struct backing_dev_info *bdi;
 	loff_t size;
 	int ret, n;
-	fmode_t mode = 0;
-	if (file) {
-		mode = file->f_mode;
-		if (file->f_flags & O_NDELAY)
-			mode |= FMODE_NDELAY_NOW;
-	}
 
 	switch(cmd) {
 	case BLKFLSBUF:
diff --git a/drivers/char/raw.c b/drivers/char/raw.c
index f3cf5eb9b7fb..96adf28a17e4 100644
--- a/drivers/char/raw.c
+++ b/drivers/char/raw.c
@@ -125,7 +125,7 @@ raw_ioctl(struct inode *inode, struct file *filp,
 {
 	struct block_device *bdev = filp->private_data;
 
-	return blkdev_ioctl(bdev->bd_inode, NULL, command, arg);
+	return blkdev_ioctl(bdev, 0, command, arg);
 }
 
 static void bind_device(struct raw_config_request *rq)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index b89c956e04f6..05865b93f7e1 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1202,7 +1202,11 @@ static int blkdev_close(struct inode * inode, struct file * filp)
 
 static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 {
-	return blkdev_ioctl(file->f_mapping->host, file, cmd, arg);
+	struct block_device *bdev = I_BDEV(file->f_mapping->host);
+	fmode_t mode = file->f_mode;
+	if (file->f_flags & O_NDELAY)
+		mode |= FMODE_NDELAY_NOW;
+	return blkdev_ioctl(bdev, mode, cmd, arg);
 }
 
 static const struct address_space_operations def_blk_aops = {
@@ -1238,7 +1242,7 @@ int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)
 	int res;
 	mm_segment_t old_fs = get_fs();
 	set_fs(KERNEL_DS);
-	res = blkdev_ioctl(bdev->bd_inode, NULL, cmd, arg);
+	res = blkdev_ioctl(bdev, 0, cmd, arg);
 	set_fs(old_fs);
 	return res;
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 11de682c65a1..ff536e106b4e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1717,7 +1717,7 @@ extern const struct file_operations bad_sock_fops;
 extern const struct file_operations def_fifo_fops;
 #ifdef CONFIG_BLOCK
 extern int ioctl_by_bdev(struct block_device *, unsigned, unsigned long);
-extern int blkdev_ioctl(struct inode *, struct file *, unsigned, unsigned long);
+extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long);
 extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long);
 extern int blkdev_get(struct block_device *, fmode_t);
 extern int blkdev_put(struct block_device *, fmode_t);
-- 
cgit v1.2.3


From e9f95e637320efe1936b647308ddf4ec5b8e0311 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Tue, 21 Oct 2008 15:49:59 +0200
Subject: genirq: fix off by one and coding style

Fix off-by-one in for_each_irq_desc_reverse().

Impact is near zero in practice, because nothing substantial wants to
iterate down to IRQ#0 - but fix it nevertheless.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/irq.c | 4 ++--
 include/linux/irqnr.h | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include')

diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index ccf6c503fc3b..d1d4dc52f649 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -36,7 +36,7 @@ void ack_bad_irq(unsigned int irq)
 }
 
 #ifdef CONFIG_X86_32
-# define irq_stats(x)		(&per_cpu(irq_stat,x))
+# define irq_stats(x)		(&per_cpu(irq_stat, x))
 #else
 # define irq_stats(x)		cpu_pda(x)
 #endif
@@ -113,7 +113,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (i == 0) {
 		seq_printf(p, "           ");
 		for_each_online_cpu(j)
-			seq_printf(p, "CPU%-8d",j);
+			seq_printf(p, "CPU%-8d", j);
 		seq_putc(p, '\n');
 	}
 
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index 3171ddc3b39d..452c280c8115 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -13,9 +13,9 @@ extern int nr_irqs;
 # define for_each_irq_desc(irq, desc)		\
 	for (irq = 0, desc = irq_desc; irq < nr_irqs; irq++, desc++)
 
-# define for_each_irq_desc_reverse(irq, desc)			\
-	for (irq = nr_irqs -1, desc = irq_desc + (nr_irqs -1 );	\
-	     irq > 0; irq--, desc--)
+# define for_each_irq_desc_reverse(irq, desc)				\
+	for (irq = nr_irqs - 1, desc = irq_desc + (nr_irqs - 1);	\
+	     irq >= 0; irq--, desc--)
 #endif
 
 #define for_each_irq_nr(irq)			\
-- 
cgit v1.2.3


From 00c81d23d330207d0fb99ca0c6682265d287816c Mon Sep 17 00:00:00 2001
From: Chris Zankel <chris@zankel.net>
Date: Tue, 21 Oct 2008 09:08:31 -0700
Subject: xtensa: Fix io regions

The uncached area starts at e000.0000 and spans 1GB. Also add an IOADDR
macro to determine the bypass region to access the IO space.

Signed-off-by: Chris Zankel <chris@zankel.net>
---
 include/asm-xtensa/io.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/include/asm-xtensa/io.h b/include/asm-xtensa/io.h
index 47c3616ea9ac..07b7299dab20 100644
--- a/include/asm-xtensa/io.h
+++ b/include/asm-xtensa/io.h
@@ -18,10 +18,12 @@
 
 #include <linux/types.h>
 
-#define XCHAL_KIO_CACHED_VADDR	0xf0000000
-#define XCHAL_KIO_BYPASS_VADDR	0xf8000000
+#define XCHAL_KIO_CACHED_VADDR	0xe0000000
+#define XCHAL_KIO_BYPASS_VADDR	0xf0000000
 #define XCHAL_KIO_PADDR		0xf0000000
-#define XCHAL_KIO_SIZE		0x08000000
+#define XCHAL_KIO_SIZE		0x10000000
+
+#define IOADDR(x)		(XCHAL_KIO_BYPASS_VADDR + (x))
 
 /*
  * swap functions to change byte order from little-endian to big-endian and
-- 
cgit v1.2.3


From 0025427eee4b5c005b4ac7a6489adc773e38611d Mon Sep 17 00:00:00 2001
From: Chris Zankel <chris@zankel.net>
Date: Tue, 21 Oct 2008 09:11:43 -0700
Subject: xtensa: Add config files for Diamond 232L - Rev B processor variant

The Diamond 232L processor is a pre-configured Xtensa processor tailored
for Linux application.

Signed-off-by: Chris Zankel <chris@zankel.net>
---
 arch/xtensa/Kconfig                         |   7 +-
 arch/xtensa/Makefile                        |   1 +
 include/asm-xtensa/variant-dc232b/core.h    | 424 ++++++++++++++++++++++++++++
 include/asm-xtensa/variant-dc232b/tie-asm.h | 122 ++++++++
 include/asm-xtensa/variant-dc232b/tie.h     | 131 +++++++++
 5 files changed, 684 insertions(+), 1 deletion(-)
 create mode 100644 include/asm-xtensa/variant-dc232b/core.h
 create mode 100644 include/asm-xtensa/variant-dc232b/tie-asm.h
 create mode 100644 include/asm-xtensa/variant-dc232b/tie.h

(limited to 'include')

diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 02e417d3d8e9..2369ec6b089b 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -63,7 +63,12 @@ choice
 	default XTENSA_VARIANT_FSF
 
 config XTENSA_VARIANT_FSF
-	bool "fsf"
+	bool "fsf - default (not generic) configuration"
+
+config XTENSA_VARIANT_DC232B
+	bool "dc232b - Diamond 232L Standard Core Rev.B (LE)"
+	help
+	This variant refers to Tensilica's Diamond 232L Standard core Rev.B (LE).
 endchoice
 
 config MMU
diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index 4bd1e14c6b90..015b6b2a26b9 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -14,6 +14,7 @@
 # (Use VAR=<xtensa_config> to use another default compiler.)
 
 variant-$(CONFIG_XTENSA_VARIANT_FSF)		:= fsf
+variant-$(CONFIG_XTENSA_VARIANT_DC232B)		:= dc232b
 variant-$(CONFIG_XTENSA_VARIANT_LINUX_CUSTOM)	:= custom
 
 VARIANT = $(variant-y)
diff --git a/include/asm-xtensa/variant-dc232b/core.h b/include/asm-xtensa/variant-dc232b/core.h
new file mode 100644
index 000000000000..525bd3d90154
--- /dev/null
+++ b/include/asm-xtensa/variant-dc232b/core.h
@@ -0,0 +1,424 @@
+/*
+ * Xtensa processor core configuration information.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (c) 1999-2007 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_CORE_CONFIGURATION_H
+#define _XTENSA_CORE_CONFIGURATION_H
+
+
+/****************************************************************************
+	    Parameters Useful for Any Code, USER or PRIVILEGED
+ ****************************************************************************/
+
+/*
+ *  Note:  Macros of the form XCHAL_HAVE_*** have a value of 1 if the option is
+ *  configured, and a value of 0 otherwise.  These macros are always defined.
+ */
+
+
+/*----------------------------------------------------------------------
+				ISA
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_HAVE_BE			0	/* big-endian byte ordering */
+#define XCHAL_HAVE_WINDOWED		1	/* windowed registers option */
+#define XCHAL_NUM_AREGS			32	/* num of physical addr regs */
+#define XCHAL_NUM_AREGS_LOG2		5	/* log2(XCHAL_NUM_AREGS) */
+#define XCHAL_MAX_INSTRUCTION_SIZE	3	/* max instr bytes (3..8) */
+#define XCHAL_HAVE_DEBUG		1	/* debug option */
+#define XCHAL_HAVE_DENSITY		1	/* 16-bit instructions */
+#define XCHAL_HAVE_LOOPS		1	/* zero-overhead loops */
+#define XCHAL_HAVE_NSA			1	/* NSA/NSAU instructions */
+#define XCHAL_HAVE_MINMAX		1	/* MIN/MAX instructions */
+#define XCHAL_HAVE_SEXT			1	/* SEXT instruction */
+#define XCHAL_HAVE_CLAMPS		1	/* CLAMPS instruction */
+#define XCHAL_HAVE_MUL16		1	/* MUL16S/MUL16U instructions */
+#define XCHAL_HAVE_MUL32		1	/* MULL instruction */
+#define XCHAL_HAVE_MUL32_HIGH		0	/* MULUH/MULSH instructions */
+#define XCHAL_HAVE_DIV32		1	/* QUOS/QUOU/REMS/REMU instructions */
+#define XCHAL_HAVE_L32R			1	/* L32R instruction */
+#define XCHAL_HAVE_ABSOLUTE_LITERALS	1	/* non-PC-rel (extended) L32R */
+#define XCHAL_HAVE_CONST16		0	/* CONST16 instruction */
+#define XCHAL_HAVE_ADDX			1	/* ADDX#/SUBX# instructions */
+#define XCHAL_HAVE_WIDE_BRANCHES	0	/* B*.W18 or B*.W15 instr's */
+#define XCHAL_HAVE_PREDICTED_BRANCHES	0	/* B[EQ/EQZ/NE/NEZ]T instr's */
+#define XCHAL_HAVE_CALL4AND12		1	/* (obsolete option) */
+#define XCHAL_HAVE_ABS			1	/* ABS instruction */
+/*#define XCHAL_HAVE_POPC		0*/	/* POPC instruction */
+/*#define XCHAL_HAVE_CRC		0*/	/* CRC instruction */
+#define XCHAL_HAVE_RELEASE_SYNC		1	/* L32AI/S32RI instructions */
+#define XCHAL_HAVE_S32C1I		1	/* S32C1I instruction */
+#define XCHAL_HAVE_SPECULATION		0	/* speculation */
+#define XCHAL_HAVE_FULL_RESET		1	/* all regs/state reset */
+#define XCHAL_NUM_CONTEXTS		1	/* */
+#define XCHAL_NUM_MISC_REGS		2	/* num of scratch regs (0..4) */
+#define XCHAL_HAVE_TAP_MASTER		0	/* JTAG TAP control instr's */
+#define XCHAL_HAVE_PRID			1	/* processor ID register */
+#define XCHAL_HAVE_THREADPTR		1	/* THREADPTR register */
+#define XCHAL_HAVE_BOOLEANS		0	/* boolean registers */
+#define XCHAL_HAVE_CP			1	/* CPENABLE reg (coprocessor) */
+#define XCHAL_CP_MAXCFG			8	/* max allowed cp id plus one */
+#define XCHAL_HAVE_MAC16		1	/* MAC16 package */
+#define XCHAL_HAVE_VECTORFPU2005	0	/* vector floating-point pkg */
+#define XCHAL_HAVE_FP			0	/* floating point pkg */
+#define XCHAL_HAVE_VECTRA1		0	/* Vectra I  pkg */
+#define XCHAL_HAVE_VECTRALX		0	/* Vectra LX pkg */
+#define XCHAL_HAVE_HIFI2		0	/* HiFi2 Audio Engine pkg */
+
+
+/*----------------------------------------------------------------------
+				MISC
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_NUM_WRITEBUFFER_ENTRIES	8	/* size of write buffer */
+#define XCHAL_INST_FETCH_WIDTH		4	/* instr-fetch width in bytes */
+#define XCHAL_DATA_WIDTH		4	/* data width in bytes */
+/*  In T1050, applies to selected core load and store instructions (see ISA): */
+#define XCHAL_UNALIGNED_LOAD_EXCEPTION	1	/* unaligned loads cause exc. */
+#define XCHAL_UNALIGNED_STORE_EXCEPTION	1	/* unaligned stores cause exc.*/
+
+#define XCHAL_SW_VERSION		701001	/* sw version of this header */
+
+#define XCHAL_CORE_ID			"dc232b"	/* alphanum core name
+						   (CoreID) set in the Xtensa
+						   Processor Generator */
+
+#define XCHAL_CORE_DESCRIPTION		"Diamond 232L Standard Core Rev.B (LE)"
+#define XCHAL_BUILD_UNIQUE_ID		0x0000BEEF	/* 22-bit sw build ID */
+
+/*
+ *  These definitions describe the hardware targeted by this software.
+ */
+#define XCHAL_HW_CONFIGID0		0xC56307FE	/* ConfigID hi 32 bits*/
+#define XCHAL_HW_CONFIGID1		0x0D40BEEF	/* ConfigID lo 32 bits*/
+#define XCHAL_HW_VERSION_NAME		"LX2.1.1"	/* full version name */
+#define XCHAL_HW_VERSION_MAJOR		2210	/* major ver# of targeted hw */
+#define XCHAL_HW_VERSION_MINOR		1	/* minor ver# of targeted hw */
+#define XCHAL_HW_VERSION		221001	/* major*100+minor */
+#define XCHAL_HW_REL_LX2		1
+#define XCHAL_HW_REL_LX2_1		1
+#define XCHAL_HW_REL_LX2_1_1		1
+#define XCHAL_HW_CONFIGID_RELIABLE	1
+/*  If software targets a *range* of hardware versions, these are the bounds: */
+#define XCHAL_HW_MIN_VERSION_MAJOR	2210	/* major v of earliest tgt hw */
+#define XCHAL_HW_MIN_VERSION_MINOR	1	/* minor v of earliest tgt hw */
+#define XCHAL_HW_MIN_VERSION		221001	/* earliest targeted hw */
+#define XCHAL_HW_MAX_VERSION_MAJOR	2210	/* major v of latest tgt hw */
+#define XCHAL_HW_MAX_VERSION_MINOR	1	/* minor v of latest tgt hw */
+#define XCHAL_HW_MAX_VERSION		221001	/* latest targeted hw */
+
+
+/*----------------------------------------------------------------------
+				CACHE
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_ICACHE_LINESIZE		32	/* I-cache line size in bytes */
+#define XCHAL_DCACHE_LINESIZE		32	/* D-cache line size in bytes */
+#define XCHAL_ICACHE_LINEWIDTH		5	/* log2(I line size in bytes) */
+#define XCHAL_DCACHE_LINEWIDTH		5	/* log2(D line size in bytes) */
+
+#define XCHAL_ICACHE_SIZE		16384	/* I-cache size in bytes or 0 */
+#define XCHAL_DCACHE_SIZE		16384	/* D-cache size in bytes or 0 */
+
+#define XCHAL_DCACHE_IS_WRITEBACK	1	/* writeback feature */
+
+
+
+
+/****************************************************************************
+    Parameters Useful for PRIVILEGED (Supervisory or Non-Virtualized) Code
+ ****************************************************************************/
+
+
+#ifndef XTENSA_HAL_NON_PRIVILEGED_ONLY
+
+/*----------------------------------------------------------------------
+				CACHE
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_HAVE_PIF			1	/* any outbound PIF present */
+
+/*  If present, cache size in bytes == (ways * 2^(linewidth + setwidth)).  */
+
+/*  Number of cache sets in log2(lines per way):  */
+#define XCHAL_ICACHE_SETWIDTH		7
+#define XCHAL_DCACHE_SETWIDTH		7
+
+/*  Cache set associativity (number of ways):  */
+#define XCHAL_ICACHE_WAYS		4
+#define XCHAL_DCACHE_WAYS		4
+
+/*  Cache features:  */
+#define XCHAL_ICACHE_LINE_LOCKABLE	1
+#define XCHAL_DCACHE_LINE_LOCKABLE	1
+#define XCHAL_ICACHE_ECC_PARITY		0
+#define XCHAL_DCACHE_ECC_PARITY		0
+
+/*  Number of encoded cache attr bits (see <xtensa/hal.h> for decoded bits):  */
+#define XCHAL_CA_BITS			4
+
+
+/*----------------------------------------------------------------------
+			INTERNAL I/D RAM/ROMs and XLMI
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_NUM_INSTROM		0	/* number of core instr. ROMs */
+#define XCHAL_NUM_INSTRAM		0	/* number of core instr. RAMs */
+#define XCHAL_NUM_DATAROM		0	/* number of core data ROMs */
+#define XCHAL_NUM_DATARAM		0	/* number of core data RAMs */
+#define XCHAL_NUM_URAM			0	/* number of core unified RAMs*/
+#define XCHAL_NUM_XLMI			0	/* number of core XLMI ports */
+
+
+/*----------------------------------------------------------------------
+			INTERRUPTS and TIMERS
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_HAVE_INTERRUPTS		1	/* interrupt option */
+#define XCHAL_HAVE_HIGHPRI_INTERRUPTS	1	/* med/high-pri. interrupts */
+#define XCHAL_HAVE_NMI			1	/* non-maskable interrupt */
+#define XCHAL_HAVE_CCOUNT		1	/* CCOUNT reg. (timer option) */
+#define XCHAL_NUM_TIMERS		3	/* number of CCOMPAREn regs */
+#define XCHAL_NUM_INTERRUPTS		22	/* number of interrupts */
+#define XCHAL_NUM_INTERRUPTS_LOG2	5	/* ceil(log2(NUM_INTERRUPTS)) */
+#define XCHAL_NUM_EXTINTERRUPTS		17	/* num of external interrupts */
+#define XCHAL_NUM_INTLEVELS		6	/* number of interrupt levels
+						   (not including level zero) */
+#define XCHAL_EXCM_LEVEL		3	/* level masked by PS.EXCM */
+	/* (always 1 in XEA1; levels 2 .. EXCM_LEVEL are "medium priority") */
+
+/*  Masks of interrupts at each interrupt level:  */
+#define XCHAL_INTLEVEL1_MASK		0x001F80FF
+#define XCHAL_INTLEVEL2_MASK		0x00000100
+#define XCHAL_INTLEVEL3_MASK		0x00200E00
+#define XCHAL_INTLEVEL4_MASK		0x00001000
+#define XCHAL_INTLEVEL5_MASK		0x00002000
+#define XCHAL_INTLEVEL6_MASK		0x00000000
+#define XCHAL_INTLEVEL7_MASK		0x00004000
+
+/*  Masks of interrupts at each range 1..n of interrupt levels:  */
+#define XCHAL_INTLEVEL1_ANDBELOW_MASK	0x001F80FF
+#define XCHAL_INTLEVEL2_ANDBELOW_MASK	0x001F81FF
+#define XCHAL_INTLEVEL3_ANDBELOW_MASK	0x003F8FFF
+#define XCHAL_INTLEVEL4_ANDBELOW_MASK	0x003F9FFF
+#define XCHAL_INTLEVEL5_ANDBELOW_MASK	0x003FBFFF
+#define XCHAL_INTLEVEL6_ANDBELOW_MASK	0x003FBFFF
+#define XCHAL_INTLEVEL7_ANDBELOW_MASK	0x003FFFFF
+
+/*  Level of each interrupt:  */
+#define XCHAL_INT0_LEVEL		1
+#define XCHAL_INT1_LEVEL		1
+#define XCHAL_INT2_LEVEL		1
+#define XCHAL_INT3_LEVEL		1
+#define XCHAL_INT4_LEVEL		1
+#define XCHAL_INT5_LEVEL		1
+#define XCHAL_INT6_LEVEL		1
+#define XCHAL_INT7_LEVEL		1
+#define XCHAL_INT8_LEVEL		2
+#define XCHAL_INT9_LEVEL		3
+#define XCHAL_INT10_LEVEL		3
+#define XCHAL_INT11_LEVEL		3
+#define XCHAL_INT12_LEVEL		4
+#define XCHAL_INT13_LEVEL		5
+#define XCHAL_INT14_LEVEL		7
+#define XCHAL_INT15_LEVEL		1
+#define XCHAL_INT16_LEVEL		1
+#define XCHAL_INT17_LEVEL		1
+#define XCHAL_INT18_LEVEL		1
+#define XCHAL_INT19_LEVEL		1
+#define XCHAL_INT20_LEVEL		1
+#define XCHAL_INT21_LEVEL		3
+#define XCHAL_DEBUGLEVEL		6	/* debug interrupt level */
+#define XCHAL_HAVE_DEBUG_EXTERN_INT	1	/* OCD external db interrupt */
+#define XCHAL_NMILEVEL			7	/* NMI "level" (for use with
+						   EXCSAVE/EPS/EPC_n, RFI n) */
+
+/*  Type of each interrupt:  */
+#define XCHAL_INT0_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT1_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT2_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT3_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT4_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT5_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT6_TYPE 	XTHAL_INTTYPE_TIMER
+#define XCHAL_INT7_TYPE 	XTHAL_INTTYPE_SOFTWARE
+#define XCHAL_INT8_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT9_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT10_TYPE 	XTHAL_INTTYPE_TIMER
+#define XCHAL_INT11_TYPE 	XTHAL_INTTYPE_SOFTWARE
+#define XCHAL_INT12_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT13_TYPE 	XTHAL_INTTYPE_TIMER
+#define XCHAL_INT14_TYPE 	XTHAL_INTTYPE_NMI
+#define XCHAL_INT15_TYPE 	XTHAL_INTTYPE_EXTERN_EDGE
+#define XCHAL_INT16_TYPE 	XTHAL_INTTYPE_EXTERN_EDGE
+#define XCHAL_INT17_TYPE 	XTHAL_INTTYPE_EXTERN_EDGE
+#define XCHAL_INT18_TYPE 	XTHAL_INTTYPE_EXTERN_EDGE
+#define XCHAL_INT19_TYPE 	XTHAL_INTTYPE_EXTERN_EDGE
+#define XCHAL_INT20_TYPE 	XTHAL_INTTYPE_EXTERN_EDGE
+#define XCHAL_INT21_TYPE 	XTHAL_INTTYPE_EXTERN_EDGE
+
+/*  Masks of interrupts for each type of interrupt:  */
+#define XCHAL_INTTYPE_MASK_UNCONFIGURED	0xFFC00000
+#define XCHAL_INTTYPE_MASK_SOFTWARE	0x00000880
+#define XCHAL_INTTYPE_MASK_EXTERN_EDGE	0x003F8000
+#define XCHAL_INTTYPE_MASK_EXTERN_LEVEL	0x0000133F
+#define XCHAL_INTTYPE_MASK_TIMER	0x00002440
+#define XCHAL_INTTYPE_MASK_NMI		0x00004000
+#define XCHAL_INTTYPE_MASK_WRITE_ERROR	0x00000000
+
+/*  Interrupt numbers assigned to specific interrupt sources:  */
+#define XCHAL_TIMER0_INTERRUPT		6	/* CCOMPARE0 */
+#define XCHAL_TIMER1_INTERRUPT		10	/* CCOMPARE1 */
+#define XCHAL_TIMER2_INTERRUPT		13	/* CCOMPARE2 */
+#define XCHAL_TIMER3_INTERRUPT		XTHAL_TIMER_UNCONFIGURED
+#define XCHAL_NMI_INTERRUPT		14	/* non-maskable interrupt */
+
+/*  Interrupt numbers for levels at which only one interrupt is configured:  */
+#define XCHAL_INTLEVEL2_NUM		8
+#define XCHAL_INTLEVEL4_NUM		12
+#define XCHAL_INTLEVEL5_NUM		13
+#define XCHAL_INTLEVEL7_NUM		14
+/*  (There are many interrupts each at level(s) 1, 3.)  */
+
+
+/*
+ *  External interrupt vectors/levels.
+ *  These macros describe how Xtensa processor interrupt numbers
+ *  (as numbered internally, eg. in INTERRUPT and INTENABLE registers)
+ *  map to external BInterrupt<n> pins, for those interrupts
+ *  configured as external (level-triggered, edge-triggered, or NMI).
+ *  See the Xtensa processor databook for more details.
+ */
+
+/*  Core interrupt numbers mapped to each EXTERNAL interrupt number:  */
+#define XCHAL_EXTINT0_NUM		0	/* (intlevel 1) */
+#define XCHAL_EXTINT1_NUM		1	/* (intlevel 1) */
+#define XCHAL_EXTINT2_NUM		2	/* (intlevel 1) */
+#define XCHAL_EXTINT3_NUM		3	/* (intlevel 1) */
+#define XCHAL_EXTINT4_NUM		4	/* (intlevel 1) */
+#define XCHAL_EXTINT5_NUM		5	/* (intlevel 1) */
+#define XCHAL_EXTINT6_NUM		8	/* (intlevel 2) */
+#define XCHAL_EXTINT7_NUM		9	/* (intlevel 3) */
+#define XCHAL_EXTINT8_NUM		12	/* (intlevel 4) */
+#define XCHAL_EXTINT9_NUM		14	/* (intlevel 7) */
+#define XCHAL_EXTINT10_NUM		15	/* (intlevel 1) */
+#define XCHAL_EXTINT11_NUM		16	/* (intlevel 1) */
+#define XCHAL_EXTINT12_NUM		17	/* (intlevel 1) */
+#define XCHAL_EXTINT13_NUM		18	/* (intlevel 1) */
+#define XCHAL_EXTINT14_NUM		19	/* (intlevel 1) */
+#define XCHAL_EXTINT15_NUM		20	/* (intlevel 1) */
+#define XCHAL_EXTINT16_NUM		21	/* (intlevel 3) */
+
+
+/*----------------------------------------------------------------------
+			EXCEPTIONS and VECTORS
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_XEA_VERSION		2	/* Xtensa Exception Architecture
+						   number: 1 == XEA1 (old)
+							   2 == XEA2 (new)
+							   0 == XEAX (extern) */
+#define XCHAL_HAVE_XEA1			0	/* Exception Architecture 1 */
+#define XCHAL_HAVE_XEA2			1	/* Exception Architecture 2 */
+#define XCHAL_HAVE_XEAX			0	/* External Exception Arch. */
+#define XCHAL_HAVE_EXCEPTIONS		1	/* exception option */
+#define XCHAL_HAVE_MEM_ECC_PARITY	0	/* local memory ECC/parity */
+#define XCHAL_HAVE_VECTOR_SELECT	1	/* relocatable vectors */
+#define XCHAL_HAVE_VECBASE		1	/* relocatable vectors */
+#define XCHAL_VECBASE_RESET_VADDR	0xD0000000  /* VECBASE reset value */
+#define XCHAL_VECBASE_RESET_PADDR	0x00000000
+#define XCHAL_RESET_VECBASE_OVERLAP	0
+
+#define XCHAL_RESET_VECTOR0_VADDR	0xFE000000
+#define XCHAL_RESET_VECTOR0_PADDR	0xFE000000
+#define XCHAL_RESET_VECTOR1_VADDR	0xD8000500
+#define XCHAL_RESET_VECTOR1_PADDR	0x00000500
+#define XCHAL_RESET_VECTOR_VADDR	0xFE000000
+#define XCHAL_RESET_VECTOR_PADDR	0xFE000000
+#define XCHAL_USER_VECOFS		0x00000340
+#define XCHAL_USER_VECTOR_VADDR		0xD0000340
+#define XCHAL_USER_VECTOR_PADDR		0x00000340
+#define XCHAL_KERNEL_VECOFS		0x00000300
+#define XCHAL_KERNEL_VECTOR_VADDR	0xD0000300
+#define XCHAL_KERNEL_VECTOR_PADDR	0x00000300
+#define XCHAL_DOUBLEEXC_VECOFS		0x000003C0
+#define XCHAL_DOUBLEEXC_VECTOR_VADDR	0xD00003C0
+#define XCHAL_DOUBLEEXC_VECTOR_PADDR	0x000003C0
+#define XCHAL_WINDOW_OF4_VECOFS		0x00000000
+#define XCHAL_WINDOW_UF4_VECOFS		0x00000040
+#define XCHAL_WINDOW_OF8_VECOFS		0x00000080
+#define XCHAL_WINDOW_UF8_VECOFS		0x000000C0
+#define XCHAL_WINDOW_OF12_VECOFS	0x00000100
+#define XCHAL_WINDOW_UF12_VECOFS	0x00000140
+#define XCHAL_WINDOW_VECTORS_VADDR	0xD0000000
+#define XCHAL_WINDOW_VECTORS_PADDR	0x00000000
+#define XCHAL_INTLEVEL2_VECOFS		0x00000180
+#define XCHAL_INTLEVEL2_VECTOR_VADDR	0xD0000180
+#define XCHAL_INTLEVEL2_VECTOR_PADDR	0x00000180
+#define XCHAL_INTLEVEL3_VECOFS		0x000001C0
+#define XCHAL_INTLEVEL3_VECTOR_VADDR	0xD00001C0
+#define XCHAL_INTLEVEL3_VECTOR_PADDR	0x000001C0
+#define XCHAL_INTLEVEL4_VECOFS		0x00000200
+#define XCHAL_INTLEVEL4_VECTOR_VADDR	0xD0000200
+#define XCHAL_INTLEVEL4_VECTOR_PADDR	0x00000200
+#define XCHAL_INTLEVEL5_VECOFS		0x00000240
+#define XCHAL_INTLEVEL5_VECTOR_VADDR	0xD0000240
+#define XCHAL_INTLEVEL5_VECTOR_PADDR	0x00000240
+#define XCHAL_INTLEVEL6_VECOFS		0x00000280
+#define XCHAL_INTLEVEL6_VECTOR_VADDR	0xD0000280
+#define XCHAL_INTLEVEL6_VECTOR_PADDR	0x00000280
+#define XCHAL_DEBUG_VECOFS		XCHAL_INTLEVEL6_VECOFS
+#define XCHAL_DEBUG_VECTOR_VADDR	XCHAL_INTLEVEL6_VECTOR_VADDR
+#define XCHAL_DEBUG_VECTOR_PADDR	XCHAL_INTLEVEL6_VECTOR_PADDR
+#define XCHAL_NMI_VECOFS		0x000002C0
+#define XCHAL_NMI_VECTOR_VADDR		0xD00002C0
+#define XCHAL_NMI_VECTOR_PADDR		0x000002C0
+#define XCHAL_INTLEVEL7_VECOFS		XCHAL_NMI_VECOFS
+#define XCHAL_INTLEVEL7_VECTOR_VADDR	XCHAL_NMI_VECTOR_VADDR
+#define XCHAL_INTLEVEL7_VECTOR_PADDR	XCHAL_NMI_VECTOR_PADDR
+
+
+/*----------------------------------------------------------------------
+				DEBUG
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_HAVE_OCD			1	/* OnChipDebug option */
+#define XCHAL_NUM_IBREAK		2	/* number of IBREAKn regs */
+#define XCHAL_NUM_DBREAK		2	/* number of DBREAKn regs */
+#define XCHAL_HAVE_OCD_DIR_ARRAY	1	/* faster OCD option */
+
+
+/*----------------------------------------------------------------------
+				MMU
+  ----------------------------------------------------------------------*/
+
+/*  See core-matmap.h header file for more details.  */
+
+#define XCHAL_HAVE_TLBS			1	/* inverse of HAVE_CACHEATTR */
+#define XCHAL_HAVE_SPANNING_WAY		0	/* one way maps I+D 4GB vaddr */
+#define XCHAL_HAVE_IDENTITY_MAP		0	/* vaddr == paddr always */
+#define XCHAL_HAVE_CACHEATTR		0	/* CACHEATTR register present */
+#define XCHAL_HAVE_MIMIC_CACHEATTR	0	/* region protection */
+#define XCHAL_HAVE_XLT_CACHEATTR	0	/* region prot. w/translation */
+#define XCHAL_HAVE_PTP_MMU		1	/* full MMU (with page table
+						   [autorefill] and protection)
+						   usable for an MMU-based OS */
+/*  If none of the above last 4 are set, it's a custom TLB configuration.  */
+#define XCHAL_ITLB_ARF_ENTRIES_LOG2	2	/* log2(autorefill way size) */
+#define XCHAL_DTLB_ARF_ENTRIES_LOG2	2	/* log2(autorefill way size) */
+
+#define XCHAL_MMU_ASID_BITS		8	/* number of bits in ASIDs */
+#define XCHAL_MMU_RINGS			4	/* number of rings (1..4) */
+#define XCHAL_MMU_RING_BITS		2	/* num of bits in RING field */
+
+#endif /* !XTENSA_HAL_NON_PRIVILEGED_ONLY */
+
+
+#endif /* _XTENSA_CORE_CONFIGURATION_H */
+
diff --git a/include/asm-xtensa/variant-dc232b/tie-asm.h b/include/asm-xtensa/variant-dc232b/tie-asm.h
new file mode 100644
index 000000000000..ed4f53f529db
--- /dev/null
+++ b/include/asm-xtensa/variant-dc232b/tie-asm.h
@@ -0,0 +1,122 @@
+/*
+ * This header file contains assembly-language definitions (assembly
+ * macros, etc.) for this specific Xtensa processor's TIE extensions
+ * and options.  It is customized to this Xtensa processor configuration.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1999-2007 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_CORE_TIE_ASM_H
+#define _XTENSA_CORE_TIE_ASM_H
+
+/*  Selection parameter values for save-area save/restore macros:  */
+/*  Option vs. TIE:  */
+#define XTHAL_SAS_TIE	0x0001	/* custom extension or coprocessor */
+#define XTHAL_SAS_OPT	0x0002	/* optional (and not a coprocessor) */
+/*  Whether used automatically by compiler:  */
+#define XTHAL_SAS_NOCC	0x0004	/* not used by compiler w/o special opts/code */
+#define XTHAL_SAS_CC	0x0008	/* used by compiler without special opts/code */
+/*  ABI handling across function calls:  */
+#define XTHAL_SAS_CALR	0x0010	/* caller-saved */
+#define XTHAL_SAS_CALE	0x0020	/* callee-saved */
+#define XTHAL_SAS_GLOB	0x0040	/* global across function calls (in thread) */
+/*  Misc  */
+#define XTHAL_SAS_ALL	0xFFFF	/* include all default NCP contents */
+
+
+
+/* Macro to save all non-coprocessor (extra) custom TIE and optional state
+ * (not including zero-overhead loop registers).
+ * Save area ptr (clobbered):  ptr  (1 byte aligned)
+ * Scratch regs  (clobbered):  at1..at4  (only first XCHAL_NCP_NUM_ATMPS needed)
+ */
+	.macro xchal_ncp_store  ptr at1 at2 at3 at4  continue=0 ofs=-1 select=XTHAL_SAS_ALL
+	xchal_sa_start	\continue, \ofs
+	.ifeq (XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 1024-8, 4, 4
+	rsr	\at1, ACCLO		// MAC16 accumulator
+	rsr	\at2, ACCHI
+	s32i	\at1, \ptr, .Lxchal_ofs_ + 0
+	s32i	\at2, \ptr, .Lxchal_ofs_ + 4
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 8
+	.endif
+	.ifeq (XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 1024-16, 4, 4
+	rsr	\at1, M0		// MAC16 registers
+	rsr	\at2, M1
+	s32i	\at1, \ptr, .Lxchal_ofs_ + 0
+	s32i	\at2, \ptr, .Lxchal_ofs_ + 4
+	rsr	\at1, M2
+	rsr	\at2, M3
+	s32i	\at1, \ptr, .Lxchal_ofs_ + 8
+	s32i	\at2, \ptr, .Lxchal_ofs_ + 12
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 16
+	.endif
+	.ifeq (XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 1024-4, 4, 4
+	rsr	\at1, SCOMPARE1		// conditional store option
+	s32i	\at1, \ptr, .Lxchal_ofs_ + 0
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 4
+	.endif
+	.ifeq (XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_GLOB) & ~\select
+	xchal_sa_align	\ptr, 0, 1024-4, 4, 4
+	rur	\at1, THREADPTR		// threadptr option
+	s32i	\at1, \ptr, .Lxchal_ofs_ + 0
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 4
+	.endif
+	.endm	// xchal_ncp_store
+
+/* Macro to save all non-coprocessor (extra) custom TIE and optional state
+ * (not including zero-overhead loop registers).
+ * Save area ptr (clobbered):  ptr  (1 byte aligned)
+ * Scratch regs  (clobbered):  at1..at4  (only first XCHAL_NCP_NUM_ATMPS needed)
+ */
+	.macro xchal_ncp_load  ptr at1 at2 at3 at4  continue=0 ofs=-1 select=XTHAL_SAS_ALL
+	xchal_sa_start	\continue, \ofs
+	.ifeq (XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 1024-8, 4, 4
+	l32i	\at1, \ptr, .Lxchal_ofs_ + 0
+	l32i	\at2, \ptr, .Lxchal_ofs_ + 4
+	wsr	\at1, ACCLO		// MAC16 accumulator
+	wsr	\at2, ACCHI
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 8
+	.endif
+	.ifeq (XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 1024-16, 4, 4
+	l32i	\at1, \ptr, .Lxchal_ofs_ + 0
+	l32i	\at2, \ptr, .Lxchal_ofs_ + 4
+	wsr	\at1, M0		// MAC16 registers
+	wsr	\at2, M1
+	l32i	\at1, \ptr, .Lxchal_ofs_ + 8
+	l32i	\at2, \ptr, .Lxchal_ofs_ + 12
+	wsr	\at1, M2
+	wsr	\at2, M3
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 16
+	.endif
+	.ifeq (XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 1024-4, 4, 4
+	l32i	\at1, \ptr, .Lxchal_ofs_ + 0
+	wsr	\at1, SCOMPARE1		// conditional store option
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 4
+	.endif
+	.ifeq (XTHAL_SAS_OPT | XTHAL_SAS_CC | XTHAL_SAS_GLOB) & ~\select
+	xchal_sa_align	\ptr, 0, 1024-4, 4, 4
+	l32i	\at1, \ptr, .Lxchal_ofs_ + 0
+	wur	\at1, THREADPTR		// threadptr option
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 4
+	.endif
+	.endm	// xchal_ncp_load
+
+
+
+#define XCHAL_NCP_NUM_ATMPS	2
+
+
+#define XCHAL_SA_NUM_ATMPS	2
+
+#endif /*_XTENSA_CORE_TIE_ASM_H*/
+
diff --git a/include/asm-xtensa/variant-dc232b/tie.h b/include/asm-xtensa/variant-dc232b/tie.h
new file mode 100644
index 000000000000..018e81af4393
--- /dev/null
+++ b/include/asm-xtensa/variant-dc232b/tie.h
@@ -0,0 +1,131 @@
+/*
+ * This header file describes this specific Xtensa processor's TIE extensions
+ * that extend basic Xtensa core functionality.  It is customized to this
+ * Xtensa processor configuration.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1999-2007 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_CORE_TIE_H
+#define _XTENSA_CORE_TIE_H
+
+#define XCHAL_CP_NUM			1	/* number of coprocessors */
+#define XCHAL_CP_MAX			8	/* max CP ID + 1 (0 if none) */
+#define XCHAL_CP_MASK			0x80	/* bitmask of all CPs by ID */
+#define XCHAL_CP_PORT_MASK		0x80	/* bitmask of only port CPs */
+
+/*  Basic parameters of each coprocessor:  */
+#define XCHAL_CP7_NAME			"XTIOP"
+#define XCHAL_CP7_IDENT			XTIOP
+#define XCHAL_CP7_SA_SIZE		0	/* size of state save area */
+#define XCHAL_CP7_SA_ALIGN		1	/* min alignment of save area */
+#define XCHAL_CP_ID_XTIOP		7	/* coprocessor ID (0..7) */
+
+/*  Filler info for unassigned coprocessors, to simplify arrays etc:  */
+#define XCHAL_CP0_SA_SIZE		0
+#define XCHAL_CP0_SA_ALIGN		1
+#define XCHAL_CP1_SA_SIZE		0
+#define XCHAL_CP1_SA_ALIGN		1
+#define XCHAL_CP2_SA_SIZE		0
+#define XCHAL_CP2_SA_ALIGN		1
+#define XCHAL_CP3_SA_SIZE		0
+#define XCHAL_CP3_SA_ALIGN		1
+#define XCHAL_CP4_SA_SIZE		0
+#define XCHAL_CP4_SA_ALIGN		1
+#define XCHAL_CP5_SA_SIZE		0
+#define XCHAL_CP5_SA_ALIGN		1
+#define XCHAL_CP6_SA_SIZE		0
+#define XCHAL_CP6_SA_ALIGN		1
+
+/*  Save area for non-coprocessor optional and custom (TIE) state:  */
+#define XCHAL_NCP_SA_SIZE		32
+#define XCHAL_NCP_SA_ALIGN		4
+
+/*  Total save area for optional and custom state (NCP + CPn):  */
+#define XCHAL_TOTAL_SA_SIZE		32	/* with 16-byte align padding */
+#define XCHAL_TOTAL_SA_ALIGN		4	/* actual minimum alignment */
+
+/*
+ * Detailed contents of save areas.
+ * NOTE:  caller must define the XCHAL_SA_REG macro (not defined here)
+ * before expanding the XCHAL_xxx_SA_LIST() macros.
+ *
+ * XCHAL_SA_REG(s,ccused,abikind,kind,opt,name,galign,align,asize,
+ *		dbnum,base,regnum,bitsz,gapsz,reset,x...)
+ *
+ *	s = passed from XCHAL_*_LIST(s), eg. to select how to expand
+ *	ccused = set if used by compiler without special options or code
+ *	abikind = 0 (caller-saved), 1 (callee-saved), or 2 (thread-global)
+ *	kind = 0 (special reg), 1 (TIE user reg), or 2 (TIE regfile reg)
+ *	opt = 0 (custom TIE extension or coprocessor), or 1 (optional reg)
+ *	name = lowercase reg name (no quotes)
+ *	galign = group byte alignment (power of 2) (galign >= align)
+ *	align = register byte alignment (power of 2)
+ *	asize = allocated size in bytes (asize*8 == bitsz + gapsz + padsz)
+ *	  (not including any pad bytes required to galign this or next reg)
+ *	dbnum = unique target number f/debug (see <xtensa-libdb-macros.h>)
+ *	base = reg shortname w/o index (or sr=special, ur=TIE user reg)
+ *	regnum = reg index in regfile, or special/TIE-user reg number
+ *	bitsz = number of significant bits (regfile width, or ur/sr mask bits)
+ *	gapsz = intervening bits, if bitsz bits not stored contiguously
+ *	(padsz = pad bits at end [TIE regfile] or at msbits [ur,sr] of asize)
+ *	reset = register reset value (or 0 if undefined at reset)
+ *	x = reserved for future use (0 until then)
+ *
+ *  To filter out certain registers, e.g. to expand only the non-global
+ *  registers used by the compiler, you can do something like this:
+ *
+ *  #define XCHAL_SA_REG(s,ccused,p...)	SELCC##ccused(p)
+ *  #define SELCC0(p...)
+ *  #define SELCC1(abikind,p...)	SELAK##abikind(p)
+ *  #define SELAK0(p...)		REG(p)
+ *  #define SELAK1(p...)		REG(p)
+ *  #define SELAK2(p...)
+ *  #define REG(kind,tie,name,galn,aln,asz,csz,dbnum,base,rnum,bsz,rst,x...) \
+ *		...what you want to expand...
+ */
+
+#define XCHAL_NCP_SA_NUM	8
+#define XCHAL_NCP_SA_LIST(s)	\
+ XCHAL_SA_REG(s,1,0,0,1,          acclo, 4, 4, 4,0x0210,  sr,16 , 32,0,0,0) \
+ XCHAL_SA_REG(s,1,0,0,1,          acchi, 4, 4, 4,0x0211,  sr,17 ,  8,0,0,0) \
+ XCHAL_SA_REG(s,0,0,0,1,             m0, 4, 4, 4,0x0220,  sr,32 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,0,1,             m1, 4, 4, 4,0x0221,  sr,33 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,0,1,             m2, 4, 4, 4,0x0222,  sr,34 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,0,1,             m3, 4, 4, 4,0x0223,  sr,35 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,0,1,      scompare1, 4, 4, 4,0x020C,  sr,12 , 32,0,0,0) \
+ XCHAL_SA_REG(s,1,2,1,1,      threadptr, 4, 4, 4,0x03E7,  ur,231, 32,0,0,0)
+
+#define XCHAL_CP0_SA_NUM	0
+#define XCHAL_CP0_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP1_SA_NUM	0
+#define XCHAL_CP1_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP2_SA_NUM	0
+#define XCHAL_CP2_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP3_SA_NUM	0
+#define XCHAL_CP3_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP4_SA_NUM	0
+#define XCHAL_CP4_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP5_SA_NUM	0
+#define XCHAL_CP5_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP6_SA_NUM	0
+#define XCHAL_CP6_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP7_SA_NUM	0
+#define XCHAL_CP7_SA_LIST(s)	/* empty */
+
+/* Byte length of instruction from its first nibble (op0 field), per FLIX.  */
+#define XCHAL_OP0_FORMAT_LENGTHS	3,3,3,3,3,3,3,3,2,2,2,2,2,2,3,3
+
+#endif /*_XTENSA_CORE_TIE_H*/
+
-- 
cgit v1.2.3


From 96014a957c7a39392315ce117466549d69eb63b2 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@nokia.com>
Date: Sat, 18 Oct 2008 12:23:45 -0300
Subject: V4L/DVB (9318): v4l2-int-if: Add command to get slave private data.

vidioc_int_g_priv is used to get master's slave-related private data
structure. The structure can contain for example master's configuration
specific to slave.

Signed-off-by: Sakari Ailus <sakari.ailus@nokia.com>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 include/media/v4l2-int-device.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/media/v4l2-int-device.h b/include/media/v4l2-int-device.h
index c8b80e0f0651..d9a0053654db 100644
--- a/include/media/v4l2-int-device.h
+++ b/include/media/v4l2-int-device.h
@@ -184,6 +184,11 @@ enum v4l2_int_ioctl_num {
 	vidioc_int_dev_exit_num,
 	/* Set device power state: 0 is off, non-zero is on. */
 	vidioc_int_s_power_num,
+	/*
+	* Get slave private data, e.g. platform-specific slave
+	* configuration used by the master.
+	*/
+	vidioc_int_g_priv_num,
 	/* Get slave interface parameters. */
 	vidioc_int_g_ifparm_num,
 	/* Does the slave need to be reset after VIDIOC_DQBUF? */
@@ -267,6 +272,7 @@ V4L2_INT_WRAPPER_1(s_parm, struct v4l2_streamparm, *);
 V4L2_INT_WRAPPER_0(dev_init);
 V4L2_INT_WRAPPER_0(dev_exit);
 V4L2_INT_WRAPPER_1(s_power, int, );
+V4L2_INT_WRAPPER_1(g_priv, void, *);
 V4L2_INT_WRAPPER_1(g_ifparm, struct v4l2_ifparm, *);
 V4L2_INT_WRAPPER_1(g_needs_reset, void, *);
 
-- 
cgit v1.2.3


From 621a3739f3b8c7427a789d3b2fe86a80ff234225 Mon Sep 17 00:00:00 2001
From: Sameer Venkatraman <sameerv@ti.com>
Date: Sat, 18 Oct 2008 12:25:28 -0300
Subject: V4L/DVB (9319): v4l2-int-if: Add cropcap, g_crop and s_crop commands.

Signed-off-by: Sameer Venkatraman <sameerv@ti.com>
Signed-off-by: Mohit Jalori <mjalori@ti.com>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 include/media/v4l2-int-device.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include')

diff --git a/include/media/v4l2-int-device.h b/include/media/v4l2-int-device.h
index d9a0053654db..cee941c39aa2 100644
--- a/include/media/v4l2-int-device.h
+++ b/include/media/v4l2-int-device.h
@@ -170,6 +170,9 @@ enum v4l2_int_ioctl_num {
 	vidioc_int_queryctrl_num,
 	vidioc_int_g_ctrl_num,
 	vidioc_int_s_ctrl_num,
+	vidioc_int_cropcap_num,
+	vidioc_int_g_crop_num,
+	vidioc_int_s_crop_num,
 	vidioc_int_g_parm_num,
 	vidioc_int_s_parm_num,
 
@@ -266,6 +269,9 @@ V4L2_INT_WRAPPER_1(try_fmt_cap, struct v4l2_format, *);
 V4L2_INT_WRAPPER_1(queryctrl, struct v4l2_queryctrl, *);
 V4L2_INT_WRAPPER_1(g_ctrl, struct v4l2_control, *);
 V4L2_INT_WRAPPER_1(s_ctrl, struct v4l2_control, *);
+V4L2_INT_WRAPPER_1(cropcap, struct v4l2_cropcap, *);
+V4L2_INT_WRAPPER_1(g_crop, struct v4l2_crop, *);
+V4L2_INT_WRAPPER_1(s_crop, struct v4l2_crop, *);
 V4L2_INT_WRAPPER_1(g_parm, struct v4l2_streamparm, *);
 V4L2_INT_WRAPPER_1(s_parm, struct v4l2_streamparm, *);
 
-- 
cgit v1.2.3


From 733d710b09748a79f70cbb58547d036d28ec566e Mon Sep 17 00:00:00 2001
From: Sergio Aguirre <saaguirre@ti.com>
Date: Sat, 18 Oct 2008 12:26:47 -0300
Subject: V4L/DVB (9320): v4l2: Add 10-bit RAW Bayer formats

Add 10-bit raw bayer format expanded to 16 bits. Adds also definition
for 10-bit raw bayer format dpcm-compressed to 8 bits.

Signed-off-by: Sergio Aguirre <saaguirre@ti.com>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 include/linux/videodev2.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h
index d4b03034ee73..4669d7e72e75 100644
--- a/include/linux/videodev2.h
+++ b/include/linux/videodev2.h
@@ -315,6 +315,13 @@ struct v4l2_pix_format {
 /* see http://www.siliconimaging.com/RGB%20Bayer.htm */
 #define V4L2_PIX_FMT_SBGGR8  v4l2_fourcc('B', 'A', '8', '1') /*  8  BGBG.. GRGR.. */
 #define V4L2_PIX_FMT_SGBRG8  v4l2_fourcc('G', 'B', 'R', 'G') /*  8  GBGB.. RGRG.. */
+/*
+ * 10bit raw bayer, expanded to 16 bits
+ * xxxxrrrrrrrrrrxxxxgggggggggg xxxxggggggggggxxxxbbbbbbbbbb...
+ */
+#define V4L2_PIX_FMT_SGRBG10 v4l2_fourcc('B', 'A', '1', '0')
+/* 10bit raw bayer DPCM compressed to 8 bits */
+#define V4L2_PIX_FMT_SGRBG10DPCM8 v4l2_fourcc('B', 'D', '1', '0')
 #define V4L2_PIX_FMT_SBGGR16 v4l2_fourcc('B', 'Y', 'R', '2') /* 16  BGBG.. GRGR.. */
 
 /* compressed formats */
-- 
cgit v1.2.3


From 84389910d0f760cea22a5e58ee16b3b9713d456d Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@nokia.com>
Date: Sat, 18 Oct 2008 12:27:50 -0300
Subject: V4L/DVB (9321): v4l2-int-if: Define new power state changes

Use enum v4l2_power instead of int as second argument to
vidioc_int_s_power. The new functionality is that standby state is also
recognised.

Signed-off-by: Sakari Ailus <sakari.ailus@nokia.com>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 include/media/v4l2-int-device.h | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

(limited to 'include')

diff --git a/include/media/v4l2-int-device.h b/include/media/v4l2-int-device.h
index cee941c39aa2..3351dcffb465 100644
--- a/include/media/v4l2-int-device.h
+++ b/include/media/v4l2-int-device.h
@@ -96,6 +96,12 @@ int v4l2_int_ioctl_1(struct v4l2_int_device *d, int cmd, void *arg);
  *
  */
 
+enum v4l2_power {
+	V4L2_POWER_OFF = 0,
+	V4L2_POWER_ON,
+	V4L2_POWER_STANDBY,
+};
+
 /* Slave interface type. */
 enum v4l2_if_type {
 	/*
@@ -185,7 +191,7 @@ enum v4l2_int_ioctl_num {
 	vidioc_int_dev_init_num = 1000,
 	/* Delinitialise the device at slave detach. */
 	vidioc_int_dev_exit_num,
-	/* Set device power state: 0 is off, non-zero is on. */
+	/* Set device power state. */
 	vidioc_int_s_power_num,
 	/*
 	* Get slave private data, e.g. platform-specific slave
@@ -277,7 +283,7 @@ V4L2_INT_WRAPPER_1(s_parm, struct v4l2_streamparm, *);
 
 V4L2_INT_WRAPPER_0(dev_init);
 V4L2_INT_WRAPPER_0(dev_exit);
-V4L2_INT_WRAPPER_1(s_power, int, );
+V4L2_INT_WRAPPER_1(s_power, enum v4l2_power, );
 V4L2_INT_WRAPPER_1(g_priv, void, *);
 V4L2_INT_WRAPPER_1(g_ifparm, struct v4l2_ifparm, *);
 V4L2_INT_WRAPPER_1(g_needs_reset, void, *);
-- 
cgit v1.2.3


From 36499e525f6d2c0aba7c7f619d7a6081c56707ca Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@nokia.com>
Date: Sat, 18 Oct 2008 12:28:36 -0300
Subject: V4L/DVB (9322): v4l2-int-if: Export more interfaces to modules

Export v4l2_int_device_try_attach_all. This allows initiating the
initialisation of int if device after the drivers have been registered.

Also allow drivers to call ioctls if v4l2-int-if was compiled as
module.

Signed-off-by: Sakari Ailus <sakari.ailus@nokia.com>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/v4l2-int-device.c | 5 ++++-
 include/media/v4l2-int-device.h       | 2 ++
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/media/video/v4l2-int-device.c b/drivers/media/video/v4l2-int-device.c
index 0e4549922f26..a935bae538ef 100644
--- a/drivers/media/video/v4l2-int-device.c
+++ b/drivers/media/video/v4l2-int-device.c
@@ -32,7 +32,7 @@
 static DEFINE_MUTEX(mutex);
 static LIST_HEAD(int_list);
 
-static void v4l2_int_device_try_attach_all(void)
+void v4l2_int_device_try_attach_all(void)
 {
 	struct v4l2_int_device *m, *s;
 
@@ -66,6 +66,7 @@ static void v4l2_int_device_try_attach_all(void)
 		}
 	}
 }
+EXPORT_SYMBOL_GPL(v4l2_int_device_try_attach_all);
 
 static int ioctl_sort_cmp(const void *a, const void *b)
 {
@@ -144,6 +145,7 @@ int v4l2_int_ioctl_0(struct v4l2_int_device *d, int cmd)
 		find_ioctl(d->u.slave, cmd,
 			   (v4l2_int_ioctl_func *)no_such_ioctl_0))(d);
 }
+EXPORT_SYMBOL_GPL(v4l2_int_ioctl_0);
 
 static int no_such_ioctl_1(struct v4l2_int_device *d, void *arg)
 {
@@ -156,5 +158,6 @@ int v4l2_int_ioctl_1(struct v4l2_int_device *d, int cmd, void *arg)
 		find_ioctl(d->u.slave, cmd,
 			   (v4l2_int_ioctl_func *)no_such_ioctl_1))(d, arg);
 }
+EXPORT_SYMBOL_GPL(v4l2_int_ioctl_1);
 
 MODULE_LICENSE("GPL");
diff --git a/include/media/v4l2-int-device.h b/include/media/v4l2-int-device.h
index 3351dcffb465..b5cee8909238 100644
--- a/include/media/v4l2-int-device.h
+++ b/include/media/v4l2-int-device.h
@@ -84,6 +84,8 @@ struct v4l2_int_device {
 	void *priv;
 };
 
+void v4l2_int_device_try_attach_all(void);
+
 int v4l2_int_device_register(struct v4l2_int_device *d);
 void v4l2_int_device_unregister(struct v4l2_int_device *d);
 
-- 
cgit v1.2.3


From f496bc716613378f2a3f9097a8e3ea4e4e30e79d Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@nokia.com>
Date: Sat, 18 Oct 2008 12:29:15 -0300
Subject: V4L/DVB (9323): v4l2-int-if: Add enum_framesizes and
 enum_frameintervals ioctls.

Signed-off-by: Sakari Ailus <sakari.ailus@nokia.com>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 include/media/v4l2-int-device.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include')

diff --git a/include/media/v4l2-int-device.h b/include/media/v4l2-int-device.h
index b5cee8909238..9c2df41dbf92 100644
--- a/include/media/v4l2-int-device.h
+++ b/include/media/v4l2-int-device.h
@@ -204,6 +204,8 @@ enum v4l2_int_ioctl_num {
 	vidioc_int_g_ifparm_num,
 	/* Does the slave need to be reset after VIDIOC_DQBUF? */
 	vidioc_int_g_needs_reset_num,
+	vidioc_int_enum_framesizes_num,
+	vidioc_int_enum_frameintervals_num,
 
 	/*
 	 *
@@ -289,6 +291,8 @@ V4L2_INT_WRAPPER_1(s_power, enum v4l2_power, );
 V4L2_INT_WRAPPER_1(g_priv, void, *);
 V4L2_INT_WRAPPER_1(g_ifparm, struct v4l2_ifparm, *);
 V4L2_INT_WRAPPER_1(g_needs_reset, void, *);
+V4L2_INT_WRAPPER_1(enum_framesizes, struct v4l2_frmsizeenum, *);
+V4L2_INT_WRAPPER_1(enum_frameintervals, struct v4l2_frmivalenum, *);
 
 V4L2_INT_WRAPPER_0(reset);
 V4L2_INT_WRAPPER_0(init);
-- 
cgit v1.2.3


From d5fbf32f381ad841d9d9537aa1b6f74796703361 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Sat, 18 Oct 2008 13:39:53 -0300
Subject: V4L/DVB (9324): v4l2: add video_ioctl2_unlocked for unlocked_ioctl
 support.

Based on an older patch from Sakari Ailus.

Cc: Sakari Ailus <sakari.ailus@nokia.com>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/v4l2-ioctl.c | 11 +++++++++--
 include/media/v4l2-ioctl.h       |  4 +++-
 2 files changed, 12 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/media/video/v4l2-ioctl.c b/drivers/media/video/v4l2-ioctl.c
index 155c9d77a463..0417844d4079 100644
--- a/drivers/media/video/v4l2-ioctl.c
+++ b/drivers/media/video/v4l2-ioctl.c
@@ -630,8 +630,8 @@ static int __video_do_ioctl(struct inode *inode, struct file *file,
 {
 	struct video_device *vfd = video_devdata(file);
 	const struct v4l2_ioctl_ops *ops = vfd->ioctl_ops;
-	void                 *fh = file->private_data;
-	int                  ret = -EINVAL;
+	void *fh = file->private_data;
+	int ret = -EINVAL;
 
 	if ((vfd->debug & V4L2_DEBUG_IOCTL) &&
 				!(vfd->debug & V4L2_DEBUG_IOCTL_ARG)) {
@@ -1861,3 +1861,10 @@ out:
 	return err;
 }
 EXPORT_SYMBOL(video_ioctl2);
+
+long video_ioctl2_unlocked(struct file *file,
+		 unsigned int cmd, unsigned long arg)
+{
+	return video_ioctl2(file->f_path.dentry->d_inode, file, cmd, arg);
+}
+EXPORT_SYMBOL(video_ioctl2_unlocked);
diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h
index 0bef03add796..3e11dfe38dc3 100644
--- a/include/media/v4l2-ioctl.h
+++ b/include/media/v4l2-ioctl.h
@@ -285,7 +285,9 @@ extern long v4l_compat_ioctl32(struct file *file, unsigned int cmd,
 				unsigned long arg);
 
 extern int video_ioctl2(struct inode *inode, struct file *file,
-			  unsigned int cmd, unsigned long arg);
+			unsigned int cmd, unsigned long arg);
+extern long video_ioctl2_unlocked(struct file *file,
+			unsigned int cmd, unsigned long arg);
 
 /* Include support for obsoleted stuff */
 extern int video_usercopy(struct inode *inode, struct file *file,
-- 
cgit v1.2.3


From b1f88407f3767f924cae1d521e815e568996a4ef Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab@redhat.com>
Date: Tue, 21 Oct 2008 11:27:20 -0300
Subject: V4L/DVB (9330): Get rid of inode parameter at
 v4l_compat_translate_ioctl()

The inode parameter at v4l_compat_translate_ioctl() were just passed over several
places just to keep compatible with fops.ioctl. However, it weren't used anywere.

This patch gets hid of this unused parameter.

Cc: Laurent Pinchart <laurent.pinchart@skynet.be>
Cc: Mike Isely <isely@pobox.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/common/saa7146_video.c       |  12 +-
 drivers/media/video/pvrusb2/pvrusb2-v4l2.c |  11 +-
 drivers/media/video/uvc/uvc_v4l2.c         |  12 +-
 drivers/media/video/v4l1-compat.c          | 221 +++++++++++++----------------
 drivers/media/video/v4l2-ioctl.c           |   6 +-
 include/media/v4l2-ioctl.h                 |   6 +-
 6 files changed, 130 insertions(+), 138 deletions(-)

(limited to 'include')

diff --git a/drivers/media/common/saa7146_video.c b/drivers/media/common/saa7146_video.c
index 99be9e5c85f7..fe0bd55977e3 100644
--- a/drivers/media/common/saa7146_video.c
+++ b/drivers/media/common/saa7146_video.c
@@ -834,7 +834,7 @@ static int video_end(struct saa7146_fh *fh, struct file *file)
  * copying is done already, arg is a kernel pointer.
  */
 
-int saa7146_video_do_ioctl(struct inode *inode, struct file *file, unsigned int cmd, void *arg)
+static int __saa7146_video_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 {
 	struct saa7146_fh *fh  = file->private_data;
 	struct saa7146_dev *dev = fh->dev;
@@ -1215,12 +1215,18 @@ int saa7146_video_do_ioctl(struct inode *inode, struct file *file, unsigned int
 	}
 #endif
 	default:
-		return v4l_compat_translate_ioctl(inode,file,cmd,arg,
-						  saa7146_video_do_ioctl);
+		return v4l_compat_translate_ioctl(file, cmd, arg,
+						  __saa7146_video_do_ioctl);
 	}
 	return 0;
 }
 
+int saa7146_video_do_ioctl(struct inode *inode, struct file *file,
+				    unsigned int cmd, void *arg)
+{
+	return __saa7146_video_do_ioctl(file, cmd, arg);
+}
+
 /*********************************************************************************/
 /* buffer handling functions                                                  */
 
diff --git a/drivers/media/video/pvrusb2/pvrusb2-v4l2.c b/drivers/media/video/pvrusb2/pvrusb2-v4l2.c
index 43ef7ba75c8b..97ed95957992 100644
--- a/drivers/media/video/pvrusb2/pvrusb2-v4l2.c
+++ b/drivers/media/video/pvrusb2/pvrusb2-v4l2.c
@@ -168,7 +168,7 @@ static const char *get_v4l_name(int v4l_type)
  * This is part of Video 4 Linux API. The procedure handles ioctl() calls.
  *
  */
-static int pvr2_v4l2_do_ioctl(struct inode *inode, struct file *file,
+static int __pvr2_v4l2_do_ioctl(struct file *file,
 			      unsigned int cmd, void *arg)
 {
 	struct pvr2_v4l2_fh *fh = file->private_data;
@@ -863,8 +863,8 @@ static int pvr2_v4l2_do_ioctl(struct inode *inode, struct file *file,
 #endif
 
 	default :
-		ret = v4l_compat_translate_ioctl(inode,file,cmd,
-						 arg,pvr2_v4l2_do_ioctl);
+		ret = v4l_compat_translate_ioctl(file, cmd,
+						 arg, __pvr2_v4l2_do_ioctl);
 	}
 
 	pvr2_hdw_commit_ctl(hdw);
@@ -890,6 +890,11 @@ static int pvr2_v4l2_do_ioctl(struct inode *inode, struct file *file,
 	return ret;
 }
 
+static int pvr2_v4l2_do_ioctl(struct inode *inode, struct file *file,
+			      unsigned int cmd, void *arg)
+{
+	return __pvr2_v4l2_do_ioctl(file, cmd, arg);
+}
 
 static void pvr2_v4l2_dev_destroy(struct pvr2_v4l2_dev *dip)
 {
diff --git a/drivers/media/video/uvc/uvc_v4l2.c b/drivers/media/video/uvc/uvc_v4l2.c
index 78e4c4e09d89..758dfefaba8d 100644
--- a/drivers/media/video/uvc/uvc_v4l2.c
+++ b/drivers/media/video/uvc/uvc_v4l2.c
@@ -464,7 +464,7 @@ static int uvc_v4l2_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static int uvc_v4l2_do_ioctl(struct inode *inode, struct file *file,
+static int __uvc_v4l2_do_ioctl(struct file *file,
 		     unsigned int cmd, void *arg)
 {
 	struct video_device *vdev = video_devdata(file);
@@ -978,8 +978,8 @@ static int uvc_v4l2_do_ioctl(struct inode *inode, struct file *file,
 		return uvc_xu_ctrl_query(video, arg, 1);
 
 	default:
-		if ((ret = v4l_compat_translate_ioctl(inode, file, cmd, arg,
-			uvc_v4l2_do_ioctl)) == -ENOIOCTLCMD)
+		if ((ret = v4l_compat_translate_ioctl(file, cmd, arg,
+			__uvc_v4l2_do_ioctl)) == -ENOIOCTLCMD)
 			uvc_trace(UVC_TRACE_IOCTL, "Unknown ioctl 0x%08x\n",
 				  cmd);
 		return ret;
@@ -988,6 +988,12 @@ static int uvc_v4l2_do_ioctl(struct inode *inode, struct file *file,
 	return ret;
 }
 
+static int uvc_v4l2_do_ioctl(struct inode *inode, struct file *file,
+			      unsigned int cmd, void *arg)
+{
+	return __uvc_v4l2_do_ioctl(file, cmd, arg);
+}
+
 static int uvc_v4l2_ioctl(struct inode *inode, struct file *file,
 		     unsigned int cmd, unsigned long arg)
 {
diff --git a/drivers/media/video/v4l1-compat.c b/drivers/media/video/v4l1-compat.c
index 928cb4037372..f13c0a9d684f 100644
--- a/drivers/media/video/v4l1-compat.c
+++ b/drivers/media/video/v4l1-compat.c
@@ -57,8 +57,7 @@ MODULE_LICENSE("GPL");
  */
 
 static int
-get_v4l_control(struct inode            *inode,
-		struct file             *file,
+get_v4l_control(struct file             *file,
 		int			cid,
 		v4l2_kioctl             drv)
 {
@@ -67,12 +66,12 @@ get_v4l_control(struct inode            *inode,
 	int			err;
 
 	qctrl2.id = cid;
-	err = drv(inode, file, VIDIOC_QUERYCTRL, &qctrl2);
+	err = drv(file, VIDIOC_QUERYCTRL, &qctrl2);
 	if (err < 0)
 		dprintk("VIDIOC_QUERYCTRL: %d\n", err);
 	if (err == 0 && !(qctrl2.flags & V4L2_CTRL_FLAG_DISABLED)) {
 		ctrl2.id = qctrl2.id;
-		err = drv(inode, file, VIDIOC_G_CTRL, &ctrl2);
+		err = drv(file, VIDIOC_G_CTRL, &ctrl2);
 		if (err < 0) {
 			dprintk("VIDIOC_G_CTRL: %d\n", err);
 			return 0;
@@ -85,8 +84,7 @@ get_v4l_control(struct inode            *inode,
 }
 
 static int
-set_v4l_control(struct inode            *inode,
-		struct file             *file,
+set_v4l_control(struct file             *file,
 		int			cid,
 		int			value,
 		v4l2_kioctl             drv)
@@ -96,7 +94,7 @@ set_v4l_control(struct inode            *inode,
 	int			err;
 
 	qctrl2.id = cid;
-	err = drv(inode, file, VIDIOC_QUERYCTRL, &qctrl2);
+	err = drv(file, VIDIOC_QUERYCTRL, &qctrl2);
 	if (err < 0)
 		dprintk("VIDIOC_QUERYCTRL: %d\n", err);
 	if (err == 0 &&
@@ -114,7 +112,7 @@ set_v4l_control(struct inode            *inode,
 			 + 32767)
 			/ 65535;
 		ctrl2.value += qctrl2.minimum;
-		err = drv(inode, file, VIDIOC_S_CTRL, &ctrl2);
+		err = drv(file, VIDIOC_S_CTRL, &ctrl2);
 		if (err < 0)
 			dprintk("VIDIOC_S_CTRL: %d\n", err);
 	}
@@ -222,7 +220,6 @@ static int poll_one(struct file *file, struct poll_wqueues *pwq)
 }
 
 static int count_inputs(
-			struct inode *inode,
 			struct file *file,
 			v4l2_kioctl drv)
 {
@@ -232,14 +229,13 @@ static int count_inputs(
 	for (i = 0;; i++) {
 		memset(&input2, 0, sizeof(input2));
 		input2.index = i;
-		if (0 != drv(inode, file, VIDIOC_ENUMINPUT, &input2))
+		if (0 != drv(file, VIDIOC_ENUMINPUT, &input2))
 			break;
 	}
 	return i;
 }
 
 static int check_size(
-		struct inode *inode,
 		struct file *file,
 		v4l2_kioctl drv,
 		int *maxw,
@@ -252,14 +248,14 @@ static int check_size(
 	memset(&fmt2, 0, sizeof(fmt2));
 
 	desc2.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	if (0 != drv(inode, file, VIDIOC_ENUM_FMT, &desc2))
+	if (0 != drv(file, VIDIOC_ENUM_FMT, &desc2))
 		goto done;
 
 	fmt2.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
 	fmt2.fmt.pix.width       = 10000;
 	fmt2.fmt.pix.height      = 10000;
 	fmt2.fmt.pix.pixelformat = desc2.pixelformat;
-	if (0 != drv(inode, file, VIDIOC_TRY_FMT, &fmt2))
+	if (0 != drv(file, VIDIOC_TRY_FMT, &fmt2))
 		goto done;
 
 	*maxw = fmt2.fmt.pix.width;
@@ -273,7 +269,6 @@ done:
 
 static noinline int v4l1_compat_get_capabilities(
 					struct video_capability *cap,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -289,13 +284,13 @@ static noinline int v4l1_compat_get_capabilities(
 	memset(cap, 0, sizeof(*cap));
 	memset(&fbuf, 0, sizeof(fbuf));
 
-	err = drv(inode, file, VIDIOC_QUERYCAP, cap2);
+	err = drv(file, VIDIOC_QUERYCAP, cap2);
 	if (err < 0) {
 		dprintk("VIDIOCGCAP / VIDIOC_QUERYCAP: %d\n", err);
 		goto done;
 	}
 	if (cap2->capabilities & V4L2_CAP_VIDEO_OVERLAY) {
-		err = drv(inode, file, VIDIOC_G_FBUF, &fbuf);
+		err = drv(file, VIDIOC_G_FBUF, &fbuf);
 		if (err < 0) {
 			dprintk("VIDIOCGCAP / VIDIOC_G_FBUF: %d\n", err);
 			memset(&fbuf, 0, sizeof(fbuf));
@@ -317,8 +312,8 @@ static noinline int v4l1_compat_get_capabilities(
 	if (fbuf.capability & V4L2_FBUF_CAP_LIST_CLIPPING)
 		cap->type |= VID_TYPE_CLIPPING;
 
-	cap->channels  = count_inputs(inode, file, drv);
-	check_size(inode, file, drv,
+	cap->channels  = count_inputs(file, drv);
+	check_size(file, drv,
 		   &cap->maxwidth, &cap->maxheight);
 	cap->audios    =  0; /* FIXME */
 	cap->minwidth  = 48; /* FIXME */
@@ -331,7 +326,6 @@ done:
 
 static noinline int v4l1_compat_get_frame_buffer(
 					struct video_buffer *buffer,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -341,7 +335,7 @@ static noinline int v4l1_compat_get_frame_buffer(
 	memset(buffer, 0, sizeof(*buffer));
 	memset(&fbuf, 0, sizeof(fbuf));
 
-	err = drv(inode, file, VIDIOC_G_FBUF, &fbuf);
+	err = drv(file, VIDIOC_G_FBUF, &fbuf);
 	if (err < 0) {
 		dprintk("VIDIOCGFBUF / VIDIOC_G_FBUF: %d\n", err);
 		goto done;
@@ -386,7 +380,6 @@ done:
 
 static noinline int v4l1_compat_set_frame_buffer(
 					struct video_buffer *buffer,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -415,7 +408,7 @@ static noinline int v4l1_compat_set_frame_buffer(
 		break;
 	}
 	fbuf.fmt.bytesperline = buffer->bytesperline;
-	err = drv(inode, file, VIDIOC_S_FBUF, &fbuf);
+	err = drv(file, VIDIOC_S_FBUF, &fbuf);
 	if (err < 0)
 		dprintk("VIDIOCSFBUF / VIDIOC_S_FBUF: %d\n", err);
 	return err;
@@ -423,7 +416,6 @@ static noinline int v4l1_compat_set_frame_buffer(
 
 static noinline int v4l1_compat_get_win_cap_dimensions(
 					struct video_window *win,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -438,7 +430,7 @@ static noinline int v4l1_compat_get_win_cap_dimensions(
 	memset(win, 0, sizeof(*win));
 
 	fmt->type = V4L2_BUF_TYPE_VIDEO_OVERLAY;
-	err = drv(inode, file, VIDIOC_G_FMT, fmt);
+	err = drv(file, VIDIOC_G_FMT, fmt);
 	if (err < 0)
 		dprintk("VIDIOCGWIN / VIDIOC_G_WIN: %d\n", err);
 	if (err == 0) {
@@ -453,7 +445,7 @@ static noinline int v4l1_compat_get_win_cap_dimensions(
 	}
 
 	fmt->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	err = drv(inode, file, VIDIOC_G_FMT, fmt);
+	err = drv(file, VIDIOC_G_FMT, fmt);
 	if (err < 0) {
 		dprintk("VIDIOCGWIN / VIDIOC_G_FMT: %d\n", err);
 		goto done;
@@ -472,7 +464,6 @@ done:
 
 static noinline int v4l1_compat_set_win_cap_dimensions(
 					struct video_window *win,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -485,8 +476,8 @@ static noinline int v4l1_compat_set_win_cap_dimensions(
 		return err;
 	}
 	fmt->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	drv(inode, file, VIDIOC_STREAMOFF, &fmt->type);
-	err1 = drv(inode, file, VIDIOC_G_FMT, fmt);
+	drv(file, VIDIOC_STREAMOFF, &fmt->type);
+	err1 = drv(file, VIDIOC_G_FMT, fmt);
 	if (err1 < 0)
 		dprintk("VIDIOCSWIN / VIDIOC_G_FMT: %d\n", err1);
 	if (err1 == 0) {
@@ -494,7 +485,7 @@ static noinline int v4l1_compat_set_win_cap_dimensions(
 		fmt->fmt.pix.height = win->height;
 		fmt->fmt.pix.field  = V4L2_FIELD_ANY;
 		fmt->fmt.pix.bytesperline = 0;
-		err = drv(inode, file, VIDIOC_S_FMT, fmt);
+		err = drv(file, VIDIOC_S_FMT, fmt);
 		if (err < 0)
 			dprintk("VIDIOCSWIN / VIDIOC_S_FMT #1: %d\n",
 				err);
@@ -511,7 +502,7 @@ static noinline int v4l1_compat_set_win_cap_dimensions(
 	fmt->fmt.win.chromakey = win->chromakey;
 	fmt->fmt.win.clips     = (void __user *)win->clips;
 	fmt->fmt.win.clipcount = win->clipcount;
-	err2 = drv(inode, file, VIDIOC_S_FMT, fmt);
+	err2 = drv(file, VIDIOC_S_FMT, fmt);
 	if (err2 < 0)
 		dprintk("VIDIOCSWIN / VIDIOC_S_FMT #2: %d\n", err2);
 
@@ -525,7 +516,6 @@ static noinline int v4l1_compat_set_win_cap_dimensions(
 
 static noinline int v4l1_compat_turn_preview_on_off(
 					int *on,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -536,9 +526,9 @@ static noinline int v4l1_compat_turn_preview_on_off(
 		/* dirty hack time.  But v4l1 has no STREAMOFF
 		 * equivalent in the API, and this one at
 		 * least comes close ... */
-		drv(inode, file, VIDIOC_STREAMOFF, &captype);
+		drv(file, VIDIOC_STREAMOFF, &captype);
 	}
-	err = drv(inode, file, VIDIOC_OVERLAY, on);
+	err = drv(file, VIDIOC_OVERLAY, on);
 	if (err < 0)
 		dprintk("VIDIOCCAPTURE / VIDIOC_PREVIEW: %d\n", err);
 	return err;
@@ -546,7 +536,6 @@ static noinline int v4l1_compat_turn_preview_on_off(
 
 static noinline int v4l1_compat_get_input_info(
 					struct video_channel *chan,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -556,7 +545,7 @@ static noinline int v4l1_compat_get_input_info(
 
 	memset(&input2, 0, sizeof(input2));
 	input2.index = chan->channel;
-	err = drv(inode, file, VIDIOC_ENUMINPUT, &input2);
+	err = drv(file, VIDIOC_ENUMINPUT, &input2);
 	if (err < 0) {
 		dprintk("VIDIOCGCHAN / VIDIOC_ENUMINPUT: "
 			"channel=%d err=%d\n", chan->channel, err);
@@ -578,7 +567,7 @@ static noinline int v4l1_compat_get_input_info(
 		break;
 	}
 	chan->norm = 0;
-	err = drv(inode, file, VIDIOC_G_STD, &sid);
+	err = drv(file, VIDIOC_G_STD, &sid);
 	if (err < 0)
 		dprintk("VIDIOCGCHAN / VIDIOC_G_STD: %d\n", err);
 	if (err == 0) {
@@ -595,14 +584,13 @@ done:
 
 static noinline int v4l1_compat_set_input(
 					struct video_channel *chan,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
 	int err;
 	v4l2_std_id sid = 0;
 
-	err = drv(inode, file, VIDIOC_S_INPUT, &chan->channel);
+	err = drv(file, VIDIOC_S_INPUT, &chan->channel);
 	if (err < 0)
 		dprintk("VIDIOCSCHAN / VIDIOC_S_INPUT: %d\n", err);
 	switch (chan->norm) {
@@ -617,7 +605,7 @@ static noinline int v4l1_compat_set_input(
 		break;
 	}
 	if (0 != sid) {
-		err = drv(inode, file, VIDIOC_S_STD, &sid);
+		err = drv(file, VIDIOC_S_STD, &sid);
 		if (err < 0)
 			dprintk("VIDIOCSCHAN / VIDIOC_S_STD: %d\n", err);
 	}
@@ -626,7 +614,6 @@ static noinline int v4l1_compat_set_input(
 
 static noinline int v4l1_compat_get_picture(
 					struct video_picture *pict,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -639,19 +626,19 @@ static noinline int v4l1_compat_get_picture(
 		return err;
 	}
 
-	pict->brightness = get_v4l_control(inode, file,
+	pict->brightness = get_v4l_control(file,
 					   V4L2_CID_BRIGHTNESS, drv);
-	pict->hue = get_v4l_control(inode, file,
+	pict->hue = get_v4l_control(file,
 				    V4L2_CID_HUE, drv);
-	pict->contrast = get_v4l_control(inode, file,
+	pict->contrast = get_v4l_control(file,
 					 V4L2_CID_CONTRAST, drv);
-	pict->colour = get_v4l_control(inode, file,
+	pict->colour = get_v4l_control(file,
 				       V4L2_CID_SATURATION, drv);
-	pict->whiteness = get_v4l_control(inode, file,
+	pict->whiteness = get_v4l_control(file,
 					  V4L2_CID_WHITENESS, drv);
 
 	fmt->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	err = drv(inode, file, VIDIOC_G_FMT, fmt);
+	err = drv(file, VIDIOC_G_FMT, fmt);
 	if (err < 0) {
 		dprintk("VIDIOCGPICT / VIDIOC_G_FMT: %d\n", err);
 		goto done;
@@ -669,7 +656,6 @@ done:
 
 static noinline int v4l1_compat_set_picture(
 					struct video_picture *pict,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -685,15 +671,15 @@ static noinline int v4l1_compat_set_picture(
 	}
 	memset(&fbuf, 0, sizeof(fbuf));
 
-	set_v4l_control(inode, file,
+	set_v4l_control(file,
 			V4L2_CID_BRIGHTNESS, pict->brightness, drv);
-	set_v4l_control(inode, file,
+	set_v4l_control(file,
 			V4L2_CID_HUE, pict->hue, drv);
-	set_v4l_control(inode, file,
+	set_v4l_control(file,
 			V4L2_CID_CONTRAST, pict->contrast, drv);
-	set_v4l_control(inode, file,
+	set_v4l_control(file,
 			V4L2_CID_SATURATION, pict->colour, drv);
-	set_v4l_control(inode, file,
+	set_v4l_control(file,
 			V4L2_CID_WHITENESS, pict->whiteness, drv);
 	/*
 	 * V4L1 uses this ioctl to set both memory capture and overlay
@@ -703,7 +689,7 @@ static noinline int v4l1_compat_set_picture(
 	 */
 
 	fmt->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	err = drv(inode, file, VIDIOC_G_FMT, fmt);
+	err = drv(file, VIDIOC_G_FMT, fmt);
 	/* If VIDIOC_G_FMT failed, then the driver likely doesn't
 	   support memory capture.  Trying to set the memory capture
 	   parameters would be pointless.  */
@@ -714,13 +700,13 @@ static noinline int v4l1_compat_set_picture(
 		 palette_to_pixelformat(pict->palette)) {
 		fmt->fmt.pix.pixelformat = palette_to_pixelformat(
 			pict->palette);
-		mem_err = drv(inode, file, VIDIOC_S_FMT, fmt);
+		mem_err = drv(file, VIDIOC_S_FMT, fmt);
 		if (mem_err < 0)
 			dprintk("VIDIOCSPICT / VIDIOC_S_FMT: %d\n",
 				mem_err);
 	}
 
-	err = drv(inode, file, VIDIOC_G_FBUF, &fbuf);
+	err = drv(file, VIDIOC_G_FBUF, &fbuf);
 	/* If VIDIOC_G_FBUF failed, then the driver likely doesn't
 	   support overlay.  Trying to set the overlay parameters
 	   would be quite pointless.  */
@@ -731,7 +717,7 @@ static noinline int v4l1_compat_set_picture(
 		 palette_to_pixelformat(pict->palette)) {
 		fbuf.fmt.pixelformat = palette_to_pixelformat(
 			pict->palette);
-		ovl_err = drv(inode, file, VIDIOC_S_FBUF, &fbuf);
+		ovl_err = drv(file, VIDIOC_S_FBUF, &fbuf);
 		if (ovl_err < 0)
 			dprintk("VIDIOCSPICT / VIDIOC_S_FBUF: %d\n",
 				ovl_err);
@@ -752,7 +738,6 @@ static noinline int v4l1_compat_set_picture(
 
 static noinline int v4l1_compat_get_tuner(
 					struct video_tuner *tun,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -762,7 +747,7 @@ static noinline int v4l1_compat_get_tuner(
 	v4l2_std_id    		sid;
 
 	memset(&tun2, 0, sizeof(tun2));
-	err = drv(inode, file, VIDIOC_G_TUNER, &tun2);
+	err = drv(file, VIDIOC_G_TUNER, &tun2);
 	if (err < 0) {
 		dprintk("VIDIOCGTUNER / VIDIOC_G_TUNER: %d\n", err);
 		goto done;
@@ -778,7 +763,7 @@ static noinline int v4l1_compat_get_tuner(
 	for (i = 0; i < 64; i++) {
 		memset(&std2, 0, sizeof(std2));
 		std2.index = i;
-		if (0 != drv(inode, file, VIDIOC_ENUMSTD, &std2))
+		if (0 != drv(file, VIDIOC_ENUMSTD, &std2))
 			break;
 		if (std2.id & V4L2_STD_PAL)
 			tun->flags |= VIDEO_TUNER_PAL;
@@ -788,7 +773,7 @@ static noinline int v4l1_compat_get_tuner(
 			tun->flags |= VIDEO_TUNER_SECAM;
 	}
 
-	err = drv(inode, file, VIDIOC_G_STD, &sid);
+	err = drv(file, VIDIOC_G_STD, &sid);
 	if (err < 0)
 		dprintk("VIDIOCGTUNER / VIDIOC_G_STD: %d\n", err);
 	if (err == 0) {
@@ -811,7 +796,6 @@ done:
 
 static noinline int v4l1_compat_select_tuner(
 					struct video_tuner *tun,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -821,7 +805,7 @@ static noinline int v4l1_compat_select_tuner(
 
 	t.index = tun->tuner;
 
-	err = drv(inode, file, VIDIOC_S_INPUT, &t);
+	err = drv(file, VIDIOC_S_INPUT, &t);
 	if (err < 0)
 		dprintk("VIDIOCSTUNER / VIDIOC_S_INPUT: %d\n", err);
 	return err;
@@ -829,7 +813,6 @@ static noinline int v4l1_compat_select_tuner(
 
 static noinline int v4l1_compat_get_frequency(
 					unsigned long *freq,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -838,7 +821,7 @@ static noinline int v4l1_compat_get_frequency(
 	memset(&freq2, 0, sizeof(freq2));
 
 	freq2.tuner = 0;
-	err = drv(inode, file, VIDIOC_G_FREQUENCY, &freq2);
+	err = drv(file, VIDIOC_G_FREQUENCY, &freq2);
 	if (err < 0)
 		dprintk("VIDIOCGFREQ / VIDIOC_G_FREQUENCY: %d\n", err);
 	if (0 == err)
@@ -848,7 +831,6 @@ static noinline int v4l1_compat_get_frequency(
 
 static noinline int v4l1_compat_set_frequency(
 					unsigned long *freq,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -856,9 +838,9 @@ static noinline int v4l1_compat_set_frequency(
 	struct v4l2_frequency   freq2;
 	memset(&freq2, 0, sizeof(freq2));
 
-	drv(inode, file, VIDIOC_G_FREQUENCY, &freq2);
+	drv(file, VIDIOC_G_FREQUENCY, &freq2);
 	freq2.frequency = *freq;
-	err = drv(inode, file, VIDIOC_S_FREQUENCY, &freq2);
+	err = drv(file, VIDIOC_S_FREQUENCY, &freq2);
 	if (err < 0)
 		dprintk("VIDIOCSFREQ / VIDIOC_S_FREQUENCY: %d\n", err);
 	return err;
@@ -866,7 +848,6 @@ static noinline int v4l1_compat_set_frequency(
 
 static noinline int v4l1_compat_get_audio(
 					struct video_audio *aud,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -876,7 +857,7 @@ static noinline int v4l1_compat_get_audio(
 	struct v4l2_tuner	tun2;
 	memset(&aud2, 0, sizeof(aud2));
 
-	err = drv(inode, file, VIDIOC_G_AUDIO, &aud2);
+	err = drv(file, VIDIOC_G_AUDIO, &aud2);
 	if (err < 0) {
 		dprintk("VIDIOCGAUDIO / VIDIOC_G_AUDIO: %d\n", err);
 		goto done;
@@ -886,27 +867,27 @@ static noinline int v4l1_compat_get_audio(
 	aud->name[sizeof(aud->name) - 1] = 0;
 	aud->audio = aud2.index;
 	aud->flags = 0;
-	i = get_v4l_control(inode, file, V4L2_CID_AUDIO_VOLUME, drv);
+	i = get_v4l_control(file, V4L2_CID_AUDIO_VOLUME, drv);
 	if (i >= 0) {
 		aud->volume = i;
 		aud->flags |= VIDEO_AUDIO_VOLUME;
 	}
-	i = get_v4l_control(inode, file, V4L2_CID_AUDIO_BASS, drv);
+	i = get_v4l_control(file, V4L2_CID_AUDIO_BASS, drv);
 	if (i >= 0) {
 		aud->bass = i;
 		aud->flags |= VIDEO_AUDIO_BASS;
 	}
-	i = get_v4l_control(inode, file, V4L2_CID_AUDIO_TREBLE, drv);
+	i = get_v4l_control(file, V4L2_CID_AUDIO_TREBLE, drv);
 	if (i >= 0) {
 		aud->treble = i;
 		aud->flags |= VIDEO_AUDIO_TREBLE;
 	}
-	i = get_v4l_control(inode, file, V4L2_CID_AUDIO_BALANCE, drv);
+	i = get_v4l_control(file, V4L2_CID_AUDIO_BALANCE, drv);
 	if (i >= 0) {
 		aud->balance = i;
 		aud->flags |= VIDEO_AUDIO_BALANCE;
 	}
-	i = get_v4l_control(inode, file, V4L2_CID_AUDIO_MUTE, drv);
+	i = get_v4l_control(file, V4L2_CID_AUDIO_MUTE, drv);
 	if (i >= 0) {
 		if (i)
 			aud->flags |= VIDEO_AUDIO_MUTE;
@@ -914,13 +895,13 @@ static noinline int v4l1_compat_get_audio(
 	}
 	aud->step = 1;
 	qctrl2.id = V4L2_CID_AUDIO_VOLUME;
-	if (drv(inode, file, VIDIOC_QUERYCTRL, &qctrl2) == 0 &&
+	if (drv(file, VIDIOC_QUERYCTRL, &qctrl2) == 0 &&
 	    !(qctrl2.flags & V4L2_CTRL_FLAG_DISABLED))
 		aud->step = qctrl2.step;
 	aud->mode = 0;
 
 	memset(&tun2, 0, sizeof(tun2));
-	err = drv(inode, file, VIDIOC_G_TUNER, &tun2);
+	err = drv(file, VIDIOC_G_TUNER, &tun2);
 	if (err < 0) {
 		dprintk("VIDIOCGAUDIO / VIDIOC_G_TUNER: %d\n", err);
 		err = 0;
@@ -939,7 +920,6 @@ done:
 
 static noinline int v4l1_compat_set_audio(
 					struct video_audio *aud,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -951,24 +931,24 @@ static noinline int v4l1_compat_set_audio(
 	memset(&tun2, 0, sizeof(tun2));
 
 	aud2.index = aud->audio;
-	err = drv(inode, file, VIDIOC_S_AUDIO, &aud2);
+	err = drv(file, VIDIOC_S_AUDIO, &aud2);
 	if (err < 0) {
 		dprintk("VIDIOCSAUDIO / VIDIOC_S_AUDIO: %d\n", err);
 		goto done;
 	}
 
-	set_v4l_control(inode, file, V4L2_CID_AUDIO_VOLUME,
+	set_v4l_control(file, V4L2_CID_AUDIO_VOLUME,
 			aud->volume, drv);
-	set_v4l_control(inode, file, V4L2_CID_AUDIO_BASS,
+	set_v4l_control(file, V4L2_CID_AUDIO_BASS,
 			aud->bass, drv);
-	set_v4l_control(inode, file, V4L2_CID_AUDIO_TREBLE,
+	set_v4l_control(file, V4L2_CID_AUDIO_TREBLE,
 			aud->treble, drv);
-	set_v4l_control(inode, file, V4L2_CID_AUDIO_BALANCE,
+	set_v4l_control(file, V4L2_CID_AUDIO_BALANCE,
 			aud->balance, drv);
-	set_v4l_control(inode, file, V4L2_CID_AUDIO_MUTE,
+	set_v4l_control(file, V4L2_CID_AUDIO_MUTE,
 			!!(aud->flags & VIDEO_AUDIO_MUTE), drv);
 
-	err = drv(inode, file, VIDIOC_G_TUNER, &tun2);
+	err = drv(file, VIDIOC_G_TUNER, &tun2);
 	if (err < 0)
 		dprintk("VIDIOCSAUDIO / VIDIOC_G_TUNER: %d\n", err);
 	if (err == 0) {
@@ -985,7 +965,7 @@ static noinline int v4l1_compat_set_audio(
 			tun2.audmode = V4L2_TUNER_MODE_LANG2;
 			break;
 		}
-		err = drv(inode, file, VIDIOC_S_TUNER, &tun2);
+		err = drv(file, VIDIOC_S_TUNER, &tun2);
 		if (err < 0)
 			dprintk("VIDIOCSAUDIO / VIDIOC_S_TUNER: %d\n", err);
 	}
@@ -996,7 +976,6 @@ done:
 
 static noinline int v4l1_compat_capture_frame(
 					struct video_mmap *mm,
-					struct inode *inode,
 					struct file *file,
 					v4l2_kioctl drv)
 {
@@ -1013,7 +992,7 @@ static noinline int v4l1_compat_capture_frame(
 	memset(&buf, 0, sizeof(buf));
 
 	fmt->type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	err = drv(inode, file, VIDIOC_G_FMT, fmt);
+	err = drv(file, VIDIOC_G_FMT, fmt);
 	if (err < 0) {
 		dprintk("VIDIOCMCAPTURE / VIDIOC_G_FMT: %d\n", err);
 		goto done;
@@ -1029,7 +1008,7 @@ static noinline int v4l1_compat_capture_frame(
 			palette_to_pixelformat(mm->format);
 		fmt->fmt.pix.field = V4L2_FIELD_ANY;
 		fmt->fmt.pix.bytesperline = 0;
-		err = drv(inode, file, VIDIOC_S_FMT, fmt);
+		err = drv(file, VIDIOC_S_FMT, fmt);
 		if (err < 0) {
 			dprintk("VIDIOCMCAPTURE / VIDIOC_S_FMT: %d\n", err);
 			goto done;
@@ -1037,17 +1016,17 @@ static noinline int v4l1_compat_capture_frame(
 	}
 	buf.index = mm->frame;
 	buf.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	err = drv(inode, file, VIDIOC_QUERYBUF, &buf);
+	err = drv(file, VIDIOC_QUERYBUF, &buf);
 	if (err < 0) {
 		dprintk("VIDIOCMCAPTURE / VIDIOC_QUERYBUF: %d\n", err);
 		goto done;
 	}
-	err = drv(inode, file, VIDIOC_QBUF, &buf);
+	err = drv(file, VIDIOC_QBUF, &buf);
 	if (err < 0) {
 		dprintk("VIDIOCMCAPTURE / VIDIOC_QBUF: %d\n", err);
 		goto done;
 	}
-	err = drv(inode, file, VIDIOC_STREAMON, &captype);
+	err = drv(file, VIDIOC_STREAMON, &captype);
 	if (err < 0)
 		dprintk("VIDIOCMCAPTURE / VIDIOC_STREAMON: %d\n", err);
 done:
@@ -1057,7 +1036,6 @@ done:
 
 static noinline int v4l1_compat_sync(
 				int *i,
-				struct inode *inode,
 				struct file *file,
 				v4l2_kioctl drv)
 {
@@ -1069,7 +1047,7 @@ static noinline int v4l1_compat_sync(
 	memset(&buf, 0, sizeof(buf));
 	buf.index = *i;
 	buf.type = V4L2_BUF_TYPE_VIDEO_CAPTURE;
-	err = drv(inode, file, VIDIOC_QUERYBUF, &buf);
+	err = drv(file, VIDIOC_QUERYBUF, &buf);
 	if (err < 0) {
 		/*  No such buffer */
 		dprintk("VIDIOCSYNC / VIDIOC_QUERYBUF: %d\n", err);
@@ -1082,7 +1060,7 @@ static noinline int v4l1_compat_sync(
 	}
 
 	/* make sure capture actually runs so we don't block forever */
-	err = drv(inode, file, VIDIOC_STREAMON, &captype);
+	err = drv(file, VIDIOC_STREAMON, &captype);
 	if (err < 0) {
 		dprintk("VIDIOCSYNC / VIDIOC_STREAMON: %d\n", err);
 		goto done;
@@ -1096,7 +1074,7 @@ static noinline int v4l1_compat_sync(
 		if (err < 0 ||	/* error or sleep was interrupted  */
 		    err == 0)	/* timeout? Shouldn't occur.  */
 			break;
-		err = drv(inode, file, VIDIOC_QUERYBUF, &buf);
+		err = drv(file, VIDIOC_QUERYBUF, &buf);
 		if (err < 0)
 			dprintk("VIDIOCSYNC / VIDIOC_QUERYBUF: %d\n", err);
 	}
@@ -1104,7 +1082,7 @@ static noinline int v4l1_compat_sync(
 	if (!(buf.flags & V4L2_BUF_FLAG_DONE)) /* not done */
 		goto done;
 	do {
-		err = drv(inode, file, VIDIOC_DQBUF, &buf);
+		err = drv(file, VIDIOC_DQBUF, &buf);
 		if (err < 0)
 			dprintk("VIDIOCSYNC / VIDIOC_DQBUF: %d\n", err);
 	} while (err == 0 && buf.index != *i);
@@ -1114,7 +1092,6 @@ done:
 
 static noinline int v4l1_compat_get_vbi_format(
 				struct vbi_format *fmt,
-				struct inode *inode,
 				struct file *file,
 				v4l2_kioctl drv)
 {
@@ -1128,7 +1105,7 @@ static noinline int v4l1_compat_get_vbi_format(
 	}
 	fmt2->type = V4L2_BUF_TYPE_VBI_CAPTURE;
 
-	err = drv(inode, file, VIDIOC_G_FMT, fmt2);
+	err = drv(file, VIDIOC_G_FMT, fmt2);
 	if (err < 0) {
 		dprintk("VIDIOCGVBIFMT / VIDIOC_G_FMT: %d\n", err);
 		goto done;
@@ -1153,7 +1130,6 @@ done:
 
 static noinline int v4l1_compat_set_vbi_format(
 				struct vbi_format *fmt,
-				struct inode *inode,
 				struct file *file,
 				v4l2_kioctl drv)
 {
@@ -1179,7 +1155,7 @@ static noinline int v4l1_compat_set_vbi_format(
 	fmt2->fmt.vbi.start[1]         = fmt->start[1];
 	fmt2->fmt.vbi.count[1]         = fmt->count[1];
 	fmt2->fmt.vbi.flags            = fmt->flags;
-	err = drv(inode, file, VIDIOC_TRY_FMT, fmt2);
+	err = drv(file, VIDIOC_TRY_FMT, fmt2);
 	if (err < 0) {
 		dprintk("VIDIOCSVBIFMT / VIDIOC_TRY_FMT: %d\n", err);
 		goto done;
@@ -1196,7 +1172,7 @@ static noinline int v4l1_compat_set_vbi_format(
 		err = -EINVAL;
 		goto done;
 	}
-	err = drv(inode, file, VIDIOC_S_FMT, fmt2);
+	err = drv(file, VIDIOC_S_FMT, fmt2);
 	if (err < 0)
 		dprintk("VIDIOCSVBIFMT / VIDIOC_S_FMT: %d\n", err);
 done:
@@ -1208,8 +1184,7 @@ done:
  *	This function is exported.
  */
 int
-v4l_compat_translate_ioctl(struct inode         *inode,
-			   struct file		*file,
+v4l_compat_translate_ioctl(struct file		*file,
 			   int			cmd,
 			   void			*arg,
 			   v4l2_kioctl          drv)
@@ -1218,64 +1193,64 @@ v4l_compat_translate_ioctl(struct inode         *inode,
 
 	switch (cmd) {
 	case VIDIOCGCAP:	/* capability */
-		err = v4l1_compat_get_capabilities(arg, inode, file, drv);
+		err = v4l1_compat_get_capabilities(arg, file, drv);
 		break;
 	case VIDIOCGFBUF: /*  get frame buffer  */
-		err = v4l1_compat_get_frame_buffer(arg, inode, file, drv);
+		err = v4l1_compat_get_frame_buffer(arg, file, drv);
 		break;
 	case VIDIOCSFBUF: /*  set frame buffer  */
-		err = v4l1_compat_set_frame_buffer(arg, inode, file, drv);
+		err = v4l1_compat_set_frame_buffer(arg, file, drv);
 		break;
 	case VIDIOCGWIN: /*  get window or capture dimensions  */
-		err = v4l1_compat_get_win_cap_dimensions(arg, inode, file, drv);
+		err = v4l1_compat_get_win_cap_dimensions(arg, file, drv);
 		break;
 	case VIDIOCSWIN: /*  set window and/or capture dimensions  */
-		err = v4l1_compat_set_win_cap_dimensions(arg, inode, file, drv);
+		err = v4l1_compat_set_win_cap_dimensions(arg, file, drv);
 		break;
 	case VIDIOCCAPTURE: /*  turn on/off preview  */
-		err = v4l1_compat_turn_preview_on_off(arg, inode, file, drv);
+		err = v4l1_compat_turn_preview_on_off(arg, file, drv);
 		break;
 	case VIDIOCGCHAN: /*  get input information  */
-		err = v4l1_compat_get_input_info(arg, inode, file, drv);
+		err = v4l1_compat_get_input_info(arg, file, drv);
 		break;
 	case VIDIOCSCHAN: /*  set input  */
-		err = v4l1_compat_set_input(arg, inode, file, drv);
+		err = v4l1_compat_set_input(arg, file, drv);
 		break;
 	case VIDIOCGPICT: /*  get tone controls & partial capture format  */
-		err = v4l1_compat_get_picture(arg, inode, file, drv);
+		err = v4l1_compat_get_picture(arg, file, drv);
 		break;
 	case VIDIOCSPICT: /*  set tone controls & partial capture format  */
-		err = v4l1_compat_set_picture(arg, inode, file, drv);
+		err = v4l1_compat_set_picture(arg, file, drv);
 		break;
 	case VIDIOCGTUNER: /*  get tuner information  */
-		err = v4l1_compat_get_tuner(arg, inode, file, drv);
+		err = v4l1_compat_get_tuner(arg, file, drv);
 		break;
 	case VIDIOCSTUNER: /*  select a tuner input  */
-		err = v4l1_compat_select_tuner(arg, inode, file, drv);
+		err = v4l1_compat_select_tuner(arg, file, drv);
 		break;
 	case VIDIOCGFREQ: /*  get frequency  */
-		err = v4l1_compat_get_frequency(arg, inode, file, drv);
+		err = v4l1_compat_get_frequency(arg, file, drv);
 		break;
 	case VIDIOCSFREQ: /*  set frequency  */
-		err = v4l1_compat_set_frequency(arg, inode, file, drv);
+		err = v4l1_compat_set_frequency(arg, file, drv);
 		break;
 	case VIDIOCGAUDIO: /*  get audio properties/controls  */
-		err = v4l1_compat_get_audio(arg, inode, file, drv);
+		err = v4l1_compat_get_audio(arg, file, drv);
 		break;
 	case VIDIOCSAUDIO: /*  set audio controls  */
-		err = v4l1_compat_set_audio(arg, inode, file, drv);
+		err = v4l1_compat_set_audio(arg, file, drv);
 		break;
 	case VIDIOCMCAPTURE: /*  capture a frame  */
-		err = v4l1_compat_capture_frame(arg, inode, file, drv);
+		err = v4l1_compat_capture_frame(arg, file, drv);
 		break;
 	case VIDIOCSYNC: /*  wait for a frame  */
-		err = v4l1_compat_sync(arg, inode, file, drv);
+		err = v4l1_compat_sync(arg, file, drv);
 		break;
 	case VIDIOCGVBIFMT: /* query VBI data capture format */
-		err = v4l1_compat_get_vbi_format(arg, inode, file, drv);
+		err = v4l1_compat_get_vbi_format(arg, file, drv);
 		break;
 	case VIDIOCSVBIFMT:
-		err = v4l1_compat_set_vbi_format(arg, inode, file, drv);
+		err = v4l1_compat_set_vbi_format(arg, file, drv);
 		break;
 	default:
 		err = -ENOIOCTLCMD;
diff --git a/drivers/media/video/v4l2-ioctl.c b/drivers/media/video/v4l2-ioctl.c
index 0417844d4079..5b3e251b9396 100644
--- a/drivers/media/video/v4l2-ioctl.c
+++ b/drivers/media/video/v4l2-ioctl.c
@@ -625,7 +625,7 @@ static int check_fmt(const struct v4l2_ioctl_ops *ops, enum v4l2_buf_type type)
 	return -EINVAL;
 }
 
-static int __video_do_ioctl(struct inode *inode, struct file *file,
+static int __video_do_ioctl(struct file *file,
 		unsigned int cmd, void *arg)
 {
 	struct video_device *vfd = video_devdata(file);
@@ -675,7 +675,7 @@ static int __video_do_ioctl(struct inode *inode, struct file *file,
 	 V4L2 ioctls.
 	 ********************************************************/
 	if (_IOC_TYPE(cmd) == 'v' && _IOC_NR(cmd) < BASE_VIDIOCPRIVATE)
-		return v4l_compat_translate_ioctl(inode, file, cmd, arg,
+		return v4l_compat_translate_ioctl(file, cmd, arg,
 						__video_do_ioctl);
 #endif
 
@@ -1832,7 +1832,7 @@ int video_ioctl2(struct inode *inode, struct file *file,
 	}
 
 	/* Handles IOCTL */
-	err = __video_do_ioctl(inode, file, cmd, parg);
+	err = __video_do_ioctl(file, cmd, parg);
 	if (err == -ENOIOCTLCMD)
 		err = -EINVAL;
 	if (is_ext_ctrl) {
diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h
index 3e11dfe38dc3..7a919433a423 100644
--- a/include/media/v4l2-ioctl.h
+++ b/include/media/v4l2-ioctl.h
@@ -271,13 +271,13 @@ extern const char *v4l2_field_names[];
 extern const char *v4l2_type_names[];
 
 /*  Compatibility layer interface  --  v4l1-compat module */
-typedef int (*v4l2_kioctl)(struct inode *inode, struct file *file,
+typedef int (*v4l2_kioctl)(struct file *file,
 			   unsigned int cmd, void *arg);
 #ifdef CONFIG_VIDEO_V4L1_COMPAT
-int v4l_compat_translate_ioctl(struct inode *inode, struct file *file,
+int v4l_compat_translate_ioctl(struct file *file,
 			       int cmd, void *arg, v4l2_kioctl driver_ioctl);
 #else
-#define v4l_compat_translate_ioctl(inode, file, cmd, arg, ioctl) (-EINVAL)
+#define v4l_compat_translate_ioctl(file, cmd, arg, ioctl) (-EINVAL)
 #endif
 
 /* 32 Bits compatibility layer for 64 bits processors */
-- 
cgit v1.2.3


From 8a522c916d3c3b29a38bd3c8fc3df826d22a9444 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab@redhat.com>
Date: Tue, 21 Oct 2008 11:58:39 -0300
Subject: V4L/DVB (9331): Remove unused inode parameter from video_ioctl2

inode is never used on video_ioctl2. Remove it and rename the function to
__video_ioctl2. This allows its usage directly as a callback at
fops.unlocked_ioctl.

Since we still need a callback with inode to be used with fops.ioctl,
this patch adds video_ioctl2() that is just a call to __video_ioctl2().

Also, this patch adds some comments about video_ioctl2 and __video_ioctl2
usage at v4l2-ioctl.h.

Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/ivtv/ivtv-ioctl.c |  2 +-
 drivers/media/video/v4l2-ioctl.c      | 12 ++++++------
 include/media/v4l2-ioctl.h            | 20 +++++++++++++++-----
 3 files changed, 22 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/media/video/ivtv/ivtv-ioctl.c b/drivers/media/video/ivtv/ivtv-ioctl.c
index 09a75abcb478..4bae38d21ef6 100644
--- a/drivers/media/video/ivtv/ivtv-ioctl.c
+++ b/drivers/media/video/ivtv/ivtv-ioctl.c
@@ -1830,7 +1830,7 @@ static long ivtv_serialized_ioctl(struct ivtv *itv, struct file *filp,
 
 	if (ivtv_debug & IVTV_DBGFLG_IOCTL)
 		vfd->debug = V4L2_DEBUG_IOCTL | V4L2_DEBUG_IOCTL_ARG;
-	ret = video_ioctl2_unlocked(filp, cmd, arg);
+	ret = __video_ioctl2(filp, cmd, arg);
 	vfd->debug = 0;
 	return ret;
 }
diff --git a/drivers/media/video/v4l2-ioctl.c b/drivers/media/video/v4l2-ioctl.c
index 5b3e251b9396..710e1a40c422 100644
--- a/drivers/media/video/v4l2-ioctl.c
+++ b/drivers/media/video/v4l2-ioctl.c
@@ -1768,7 +1768,7 @@ static int __video_do_ioctl(struct file *file,
 	return ret;
 }
 
-int video_ioctl2(struct inode *inode, struct file *file,
+int __video_ioctl2(struct file *file,
 	       unsigned int cmd, unsigned long arg)
 {
 	char	sbuf[128];
@@ -1860,11 +1860,11 @@ out:
 	kfree(mbuf);
 	return err;
 }
-EXPORT_SYMBOL(video_ioctl2);
+EXPORT_SYMBOL(__video_ioctl2);
 
-long video_ioctl2_unlocked(struct file *file,
-		 unsigned int cmd, unsigned long arg)
+int video_ioctl2(struct inode *inode, struct file *file,
+	       unsigned int cmd, unsigned long arg)
 {
-	return video_ioctl2(file->f_path.dentry->d_inode, file, cmd, arg);
+	return __video_ioctl2(file, cmd, arg);
 }
-EXPORT_SYMBOL(video_ioctl2_unlocked);
+EXPORT_SYMBOL(video_ioctl2);
diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h
index 7a919433a423..e6ba25b3d7c8 100644
--- a/include/media/v4l2-ioctl.h
+++ b/include/media/v4l2-ioctl.h
@@ -284,15 +284,25 @@ int v4l_compat_translate_ioctl(struct file *file,
 extern long v4l_compat_ioctl32(struct file *file, unsigned int cmd,
 				unsigned long arg);
 
-extern int video_ioctl2(struct inode *inode, struct file *file,
-			unsigned int cmd, unsigned long arg);
-extern long video_ioctl2_unlocked(struct file *file,
-			unsigned int cmd, unsigned long arg);
-
 /* Include support for obsoleted stuff */
 extern int video_usercopy(struct inode *inode, struct file *file,
 			  unsigned int cmd, unsigned long arg,
 			  int (*func)(struct inode *inode, struct file *file,
 				      unsigned int cmd, void *arg));
 
+/* Standard handlers for V4L ioctl's */
+
+/* This prototype is used on fops.unlocked_ioctl */
+extern int __video_ioctl2(struct file *file,
+			unsigned int cmd, unsigned long arg);
+
+/* This prototype is used on fops.ioctl
+ * Since fops.ioctl enables Kernel Big Lock, it is preferred
+ * to use __video_ioctl2 instead.
+ * It should be noticed that there's no lock code inside
+ * video_ioctl2().
+ */
+extern int video_ioctl2(struct inode *inode, struct file *file,
+			unsigned int cmd, unsigned long arg);
+
 #endif /* _V4L2_IOCTL_H */
-- 
cgit v1.2.3


From 878595f6e7225c996523965b61ce3fe29addca9d Mon Sep 17 00:00:00 2001
From: Darron Broad <darron@kewl.org>
Date: Tue, 21 Oct 2008 11:28:46 -0300
Subject: V4L/DVB (9335): videobuf: split unregister bus creating
 self-contained frontend de-allocator

This creates a self contained frontend de-allocator
for the instances where an adapter has not been
registered yet frontend de-allocation may
be required.

Signed-off-by: Darron Broad <darron@kewl.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab@redhat.com>
---
 drivers/media/video/videobuf-dvb.c | 52 +++++++++++++++++++++-----------------
 include/media/videobuf-dvb.h       |  1 +
 2 files changed, 30 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/media/video/videobuf-dvb.c b/drivers/media/video/videobuf-dvb.c
index 917277d36605..0e7dcba8e4ae 100644
--- a/drivers/media/video/videobuf-dvb.c
+++ b/drivers/media/video/videobuf-dvb.c
@@ -296,29 +296,7 @@ EXPORT_SYMBOL(videobuf_dvb_register_bus);
 
 void videobuf_dvb_unregister_bus(struct videobuf_dvb_frontends *f)
 {
-	struct list_head *list, *q;
-	struct videobuf_dvb_frontend *fe;
-
-	mutex_lock(&f->lock);
-	list_for_each_safe(list, q, &f->felist) {
-		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
-		if (fe->dvb.net.dvbdev) {
-			dvb_net_release(&fe->dvb.net);
-			fe->dvb.demux.dmx.remove_frontend(&fe->dvb.demux.dmx,
-				&fe->dvb.fe_mem);
-			fe->dvb.demux.dmx.remove_frontend(&fe->dvb.demux.dmx,
-				&fe->dvb.fe_hw);
-			dvb_dmxdev_release(&fe->dvb.dmxdev);
-			dvb_dmx_release(&fe->dvb.demux);
-			dvb_unregister_frontend(fe->dvb.frontend);
-		}
-		if (fe->dvb.frontend)
-			/* always allocated, may have been reset */
-			dvb_frontend_detach(fe->dvb.frontend);
-		list_del(list);
-		kfree(fe);
-	}
-	mutex_unlock(&f->lock);
+	videobuf_dvb_dealloc_frontends(f);
 
 	dvb_unregister_adapter(&f->adapter);
 }
@@ -389,3 +367,31 @@ fail_alloc:
 	return fe;
 }
 EXPORT_SYMBOL(videobuf_dvb_alloc_frontend);
+
+void videobuf_dvb_dealloc_frontends(struct videobuf_dvb_frontends *f)
+{
+	struct list_head *list, *q;
+	struct videobuf_dvb_frontend *fe;
+
+	mutex_lock(&f->lock);
+	list_for_each_safe(list, q, &f->felist) {
+		fe = list_entry(list, struct videobuf_dvb_frontend, felist);
+		if (fe->dvb.net.dvbdev) {
+			dvb_net_release(&fe->dvb.net);
+			fe->dvb.demux.dmx.remove_frontend(&fe->dvb.demux.dmx,
+				&fe->dvb.fe_mem);
+			fe->dvb.demux.dmx.remove_frontend(&fe->dvb.demux.dmx,
+				&fe->dvb.fe_hw);
+			dvb_dmxdev_release(&fe->dvb.dmxdev);
+			dvb_dmx_release(&fe->dvb.demux);
+			dvb_unregister_frontend(fe->dvb.frontend);
+		}
+		if (fe->dvb.frontend)
+			/* always allocated, may have been reset */
+			dvb_frontend_detach(fe->dvb.frontend);
+		list_del(list); /* remove list entry */
+		kfree(fe);	/* free frontend allocation */
+	}
+	mutex_unlock(&f->lock);
+}
+EXPORT_SYMBOL(videobuf_dvb_dealloc_frontends);
diff --git a/include/media/videobuf-dvb.h b/include/media/videobuf-dvb.h
index 80471c2b6343..6ba4f1271d23 100644
--- a/include/media/videobuf-dvb.h
+++ b/include/media/videobuf-dvb.h
@@ -47,6 +47,7 @@ int videobuf_dvb_register_bus(struct videobuf_dvb_frontends *f,
 void videobuf_dvb_unregister_bus(struct videobuf_dvb_frontends *f);
 
 struct videobuf_dvb_frontend * videobuf_dvb_alloc_frontend(struct videobuf_dvb_frontends *f, int id);
+void videobuf_dvb_dealloc_frontends(struct videobuf_dvb_frontends *f);
 
 struct videobuf_dvb_frontend * videobuf_dvb_get_frontend(struct videobuf_dvb_frontends *f, int id);
 int videobuf_dvb_find_frontend(struct videobuf_dvb_frontends *f, struct dvb_frontend *p);
-- 
cgit v1.2.3


From d63a5ce3c0d25c96bdadc78792e5b48b846e899d Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Tue, 21 Oct 2008 17:44:57 +0100
Subject: dm: publish array_too_big

Move array_too_big to include/linux/device-mapper.h because it is
used by targets.

Remove the test from dm-raid1 as the number of mirror legs is limited
such that it can never fail.  (Even for stripes it seems rather
unlikely.)

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/dm-raid1.c         | 3 ---
 drivers/md/dm-stripe.c        | 4 ++--
 drivers/md/dm.h               | 9 ---------
 include/linux/device-mapper.h | 3 +++
 4 files changed, 5 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 29913e42c4ab..ecfd82169cb3 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1315,9 +1315,6 @@ static struct mirror_set *alloc_context(unsigned int nr_mirrors,
 	size_t len;
 	struct mirror_set *ms = NULL;
 
-	if (array_too_big(sizeof(*ms), sizeof(ms->mirror[0]), nr_mirrors))
-		return NULL;
-
 	len = sizeof(*ms) + (sizeof(ms->mirror[0]) * nr_mirrors);
 
 	ms = kzalloc(len, GFP_KERNEL);
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index b745d8ac625b..287e24584730 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -60,8 +60,8 @@ static inline struct stripe_c *alloc_context(unsigned int stripes)
 {
 	size_t len;
 
-	if (array_too_big(sizeof(struct stripe_c), sizeof(struct stripe),
-			  stripes))
+	if (dm_array_too_big(sizeof(struct stripe_c), sizeof(struct stripe),
+			     stripes))
 		return NULL;
 
 	len = sizeof(struct stripe_c) + (sizeof(struct stripe) * stripes);
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index cd189da2b2fa..0ade60cdef42 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -62,15 +62,6 @@ void dm_put_target_type(struct target_type *t);
 int dm_target_iterate(void (*iter_func)(struct target_type *tt,
 					void *param), void *param);
 
-/*-----------------------------------------------------------------
- * Useful inlines.
- *---------------------------------------------------------------*/
-static inline int array_too_big(unsigned long fixed, unsigned long obj,
-				unsigned long num)
-{
-	return (num > (ULONG_MAX - fixed) / obj);
-}
-
 int dm_split_args(int *argc, char ***argvp, char *input);
 
 /*
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 08d783592b73..dfb30db475ed 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -354,6 +354,9 @@ void *dm_vcalloc(unsigned long nmemb, unsigned long elem_size);
  */
 #define dm_round_up(n, sz) (dm_div_up((n), (sz)) * (sz))
 
+#define dm_array_too_big(fixed, obj, num) \
+	((num) > (UINT_MAX - (fixed)) / (obj))
+
 static inline sector_t to_sector(unsigned long n)
 {
 	return (n >> SECTOR_SHIFT);
-- 
cgit v1.2.3


From 1f965b19437017cea6d3f3f46acdc5acae5fd011 Mon Sep 17 00:00:00 2001
From: Heinz Mauelshagen <hjm@redhat.com>
Date: Tue, 21 Oct 2008 17:45:06 +0100
Subject: dm raid1: separate region_hash interface part1

Separate the region hash code from raid1 so it can be shared by forthcoming
targets.  Use BUG_ON() for failed async dm_io() calls.

Signed-off-by: Heinz Mauelshagen <hjm@redhat.com>
Signed-off-by: Alasdair G Kergon <agk@redhat.com>
---
 drivers/md/Makefile            |   2 +-
 drivers/md/dm-raid1.c          | 789 ++++++-----------------------------------
 drivers/md/dm-region-hash.c    | 704 ++++++++++++++++++++++++++++++++++++
 include/linux/dm-region-hash.h | 104 ++++++
 4 files changed, 912 insertions(+), 687 deletions(-)
 create mode 100644 drivers/md/dm-region-hash.c
 create mode 100644 include/linux/dm-region-hash.h

(limited to 'include')

diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index f1ef33dfd8cf..1c615804ea76 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -34,7 +34,7 @@ obj-$(CONFIG_DM_CRYPT)		+= dm-crypt.o
 obj-$(CONFIG_DM_DELAY)		+= dm-delay.o
 obj-$(CONFIG_DM_MULTIPATH)	+= dm-multipath.o dm-round-robin.o
 obj-$(CONFIG_DM_SNAPSHOT)	+= dm-snapshot.o
-obj-$(CONFIG_DM_MIRROR)		+= dm-mirror.o dm-log.o
+obj-$(CONFIG_DM_MIRROR)		+= dm-mirror.o dm-log.o dm-region-hash.o
 obj-$(CONFIG_DM_ZERO)		+= dm-zero.o
 
 quiet_cmd_unroll = UNROLL  $@
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index f358853af5cf..92dcc06832a4 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -1,118 +1,36 @@
 /*
  * Copyright (C) 2003 Sistina Software Limited.
+ * Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved.
  *
  * This file is released under the GPL.
  */
 
-#include <linux/device-mapper.h>
-
 #include "dm-bio-list.h"
 #include "dm-bio-record.h"
 
-#include <linux/ctype.h>
 #include <linux/init.h>
 #include <linux/mempool.h>
 #include <linux/module.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
-#include <linux/time.h>
-#include <linux/vmalloc.h>
 #include <linux/workqueue.h>
-#include <linux/log2.h>
-#include <linux/hardirq.h>
+#include <linux/device-mapper.h>
 #include <linux/dm-io.h>
 #include <linux/dm-dirty-log.h>
 #include <linux/dm-kcopyd.h>
+#include <linux/dm-region-hash.h>
 
 #define DM_MSG_PREFIX "raid1"
+
+#define MAX_RECOVERY 1	/* Maximum number of regions recovered in parallel. */
 #define DM_IO_PAGES 64
+#define DM_KCOPYD_PAGES 64
 
 #define DM_RAID1_HANDLE_ERRORS 0x01
 #define errors_handled(p)	((p)->features & DM_RAID1_HANDLE_ERRORS)
 
 static DECLARE_WAIT_QUEUE_HEAD(_kmirrord_recovery_stopped);
 
-/*-----------------------------------------------------------------
- * Region hash
- *
- * The mirror splits itself up into discrete regions.  Each
- * region can be in one of three states: clean, dirty,
- * nosync.  There is no need to put clean regions in the hash.
- *
- * In addition to being present in the hash table a region _may_
- * be present on one of three lists.
- *
- *   clean_regions: Regions on this list have no io pending to
- *   them, they are in sync, we are no longer interested in them,
- *   they are dull.  rh_update_states() will remove them from the
- *   hash table.
- *
- *   quiesced_regions: These regions have been spun down, ready
- *   for recovery.  rh_recovery_start() will remove regions from
- *   this list and hand them to kmirrord, which will schedule the
- *   recovery io with kcopyd.
- *
- *   recovered_regions: Regions that kcopyd has successfully
- *   recovered.  rh_update_states() will now schedule any delayed
- *   io, up the recovery_count, and remove the region from the
- *   hash.
- *
- * There are 2 locks:
- *   A rw spin lock 'hash_lock' protects just the hash table,
- *   this is never held in write mode from interrupt context,
- *   which I believe means that we only have to disable irqs when
- *   doing a write lock.
- *
- *   An ordinary spin lock 'region_lock' that protects the three
- *   lists in the region_hash, with the 'state', 'list' and
- *   'bhs_delayed' fields of the regions.  This is used from irq
- *   context, so all other uses will have to suspend local irqs.
- *---------------------------------------------------------------*/
-struct mirror_set;
-struct region_hash {
-	struct mirror_set *ms;
-	uint32_t region_size;
-	unsigned region_shift;
-
-	/* holds persistent region state */
-	struct dm_dirty_log *log;
-
-	/* hash table */
-	rwlock_t hash_lock;
-	mempool_t *region_pool;
-	unsigned int mask;
-	unsigned int nr_buckets;
-	struct list_head *buckets;
-
-	spinlock_t region_lock;
-	atomic_t recovery_in_flight;
-	struct semaphore recovery_count;
-	struct list_head clean_regions;
-	struct list_head quiesced_regions;
-	struct list_head recovered_regions;
-	struct list_head failed_recovered_regions;
-};
-
-enum {
-	RH_CLEAN,
-	RH_DIRTY,
-	RH_NOSYNC,
-	RH_RECOVERING
-};
-
-struct region {
-	struct region_hash *rh;	/* FIXME: can we get rid of this ? */
-	region_t key;
-	int state;
-
-	struct list_head hash_list;
-	struct list_head list;
-
-	atomic_t pending;
-	struct bio_list delayed_bios;
-};
-
-
 /*-----------------------------------------------------------------
  * Mirror set structures.
  *---------------------------------------------------------------*/
@@ -133,8 +51,7 @@ struct mirror {
 struct mirror_set {
 	struct dm_target *ti;
 	struct list_head list;
-	struct region_hash rh;
-	struct dm_kcopyd_client *kcopyd_client;
+
 	uint64_t features;
 
 	spinlock_t lock;	/* protects the lists */
@@ -142,6 +59,8 @@ struct mirror_set {
 	struct bio_list writes;
 	struct bio_list failures;
 
+	struct dm_region_hash *rh;
+	struct dm_kcopyd_client *kcopyd_client;
 	struct dm_io_client *io_client;
 	mempool_t *read_record_pool;
 
@@ -160,25 +79,14 @@ struct mirror_set {
 
 	struct work_struct trigger_event;
 
-	unsigned int nr_mirrors;
+	unsigned nr_mirrors;
 	struct mirror mirror[0];
 };
 
-/*
- * Conversion fns
- */
-static inline region_t bio_to_region(struct region_hash *rh, struct bio *bio)
+static void wakeup_mirrord(void *context)
 {
-	return (bio->bi_sector - rh->ms->ti->begin) >> rh->region_shift;
-}
+	struct mirror_set *ms = context;
 
-static inline sector_t region_to_sector(struct region_hash *rh, region_t region)
-{
-	return region << rh->region_shift;
-}
-
-static void wake(struct mirror_set *ms)
-{
 	queue_work(ms->kmirrord_wq, &ms->kmirrord_work);
 }
 
@@ -187,7 +95,7 @@ static void delayed_wake_fn(unsigned long data)
 	struct mirror_set *ms = (struct mirror_set *) data;
 
 	clear_bit(0, &ms->timer_pending);
-	wake(ms);
+	wakeup_mirrord(ms);
 }
 
 static void delayed_wake(struct mirror_set *ms)
@@ -201,473 +109,34 @@ static void delayed_wake(struct mirror_set *ms)
 	add_timer(&ms->timer);
 }
 
-/* FIXME move this */
-static void queue_bio(struct mirror_set *ms, struct bio *bio, int rw);
-
-#define MIN_REGIONS 64
-#define MAX_RECOVERY 1
-static int rh_init(struct region_hash *rh, struct mirror_set *ms,
-		   struct dm_dirty_log *log, uint32_t region_size,
-		   region_t nr_regions)
-{
-	unsigned int nr_buckets, max_buckets;
-	size_t i;
-
-	/*
-	 * Calculate a suitable number of buckets for our hash
-	 * table.
-	 */
-	max_buckets = nr_regions >> 6;
-	for (nr_buckets = 128u; nr_buckets < max_buckets; nr_buckets <<= 1)
-		;
-	nr_buckets >>= 1;
-
-	rh->ms = ms;
-	rh->log = log;
-	rh->region_size = region_size;
-	rh->region_shift = ffs(region_size) - 1;
-	rwlock_init(&rh->hash_lock);
-	rh->mask = nr_buckets - 1;
-	rh->nr_buckets = nr_buckets;
-
-	rh->buckets = vmalloc(nr_buckets * sizeof(*rh->buckets));
-	if (!rh->buckets) {
-		DMERR("unable to allocate region hash memory");
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < nr_buckets; i++)
-		INIT_LIST_HEAD(rh->buckets + i);
-
-	spin_lock_init(&rh->region_lock);
-	sema_init(&rh->recovery_count, 0);
-	atomic_set(&rh->recovery_in_flight, 0);
-	INIT_LIST_HEAD(&rh->clean_regions);
-	INIT_LIST_HEAD(&rh->quiesced_regions);
-	INIT_LIST_HEAD(&rh->recovered_regions);
-	INIT_LIST_HEAD(&rh->failed_recovered_regions);
-
-	rh->region_pool = mempool_create_kmalloc_pool(MIN_REGIONS,
-						      sizeof(struct region));
-	if (!rh->region_pool) {
-		vfree(rh->buckets);
-		rh->buckets = NULL;
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static void rh_exit(struct region_hash *rh)
-{
-	unsigned int h;
-	struct region *reg, *nreg;
-
-	BUG_ON(!list_empty(&rh->quiesced_regions));
-	for (h = 0; h < rh->nr_buckets; h++) {
-		list_for_each_entry_safe(reg, nreg, rh->buckets + h, hash_list) {
-			BUG_ON(atomic_read(&reg->pending));
-			mempool_free(reg, rh->region_pool);
-		}
-	}
-
-	if (rh->log)
-		dm_dirty_log_destroy(rh->log);
-	if (rh->region_pool)
-		mempool_destroy(rh->region_pool);
-	vfree(rh->buckets);
-}
-
-#define RH_HASH_MULT 2654435387U
-
-static inline unsigned int rh_hash(struct region_hash *rh, region_t region)
-{
-	return (unsigned int) ((region * RH_HASH_MULT) >> 12) & rh->mask;
-}
-
-static struct region *__rh_lookup(struct region_hash *rh, region_t region)
-{
-	struct region *reg;
-
-	list_for_each_entry (reg, rh->buckets + rh_hash(rh, region), hash_list)
-		if (reg->key == region)
-			return reg;
-
-	return NULL;
-}
-
-static void __rh_insert(struct region_hash *rh, struct region *reg)
-{
-	unsigned int h = rh_hash(rh, reg->key);
-	list_add(&reg->hash_list, rh->buckets + h);
-}
-
-static struct region *__rh_alloc(struct region_hash *rh, region_t region)
-{
-	struct region *reg, *nreg;
-
-	read_unlock(&rh->hash_lock);
-	nreg = mempool_alloc(rh->region_pool, GFP_ATOMIC);
-	if (unlikely(!nreg))
-		nreg = kmalloc(sizeof(struct region), GFP_NOIO);
-	nreg->state = rh->log->type->in_sync(rh->log, region, 1) ?
-		RH_CLEAN : RH_NOSYNC;
-	nreg->rh = rh;
-	nreg->key = region;
-
-	INIT_LIST_HEAD(&nreg->list);
-
-	atomic_set(&nreg->pending, 0);
-	bio_list_init(&nreg->delayed_bios);
-	write_lock_irq(&rh->hash_lock);
-
-	reg = __rh_lookup(rh, region);
-	if (reg)
-		/* we lost the race */
-		mempool_free(nreg, rh->region_pool);
-
-	else {
-		__rh_insert(rh, nreg);
-		if (nreg->state == RH_CLEAN) {
-			spin_lock(&rh->region_lock);
-			list_add(&nreg->list, &rh->clean_regions);
-			spin_unlock(&rh->region_lock);
-		}
-		reg = nreg;
-	}
-	write_unlock_irq(&rh->hash_lock);
-	read_lock(&rh->hash_lock);
-
-	return reg;
-}
-
-static inline struct region *__rh_find(struct region_hash *rh, region_t region)
-{
-	struct region *reg;
-
-	reg = __rh_lookup(rh, region);
-	if (!reg)
-		reg = __rh_alloc(rh, region);
-
-	return reg;
-}
-
-static int rh_state(struct region_hash *rh, region_t region, int may_block)
-{
-	int r;
-	struct region *reg;
-
-	read_lock(&rh->hash_lock);
-	reg = __rh_lookup(rh, region);
-	read_unlock(&rh->hash_lock);
-
-	if (reg)
-		return reg->state;
-
-	/*
-	 * The region wasn't in the hash, so we fall back to the
-	 * dirty log.
-	 */
-	r = rh->log->type->in_sync(rh->log, region, may_block);
-
-	/*
-	 * Any error from the dirty log (eg. -EWOULDBLOCK) gets
-	 * taken as a RH_NOSYNC
-	 */
-	return r == 1 ? RH_CLEAN : RH_NOSYNC;
-}
-
-static inline int rh_in_sync(struct region_hash *rh,
-			     region_t region, int may_block)
-{
-	int state = rh_state(rh, region, may_block);
-	return state == RH_CLEAN || state == RH_DIRTY;
-}
-
-static void dispatch_bios(struct mirror_set *ms, struct bio_list *bio_list)
-{
-	struct bio *bio;
-
-	while ((bio = bio_list_pop(bio_list))) {
-		queue_bio(ms, bio, WRITE);
-	}
-}
-
-static void complete_resync_work(struct region *reg, int success)
-{
-	struct region_hash *rh = reg->rh;
-
-	rh->log->type->set_region_sync(rh->log, reg->key, success);
-
-	/*
-	 * Dispatch the bios before we call 'wake_up_all'.
-	 * This is important because if we are suspending,
-	 * we want to know that recovery is complete and
-	 * the work queue is flushed.  If we wake_up_all
-	 * before we dispatch_bios (queue bios and call wake()),
-	 * then we risk suspending before the work queue
-	 * has been properly flushed.
-	 */
-	dispatch_bios(rh->ms, &reg->delayed_bios);
-	if (atomic_dec_and_test(&rh->recovery_in_flight))
-		wake_up_all(&_kmirrord_recovery_stopped);
-	up(&rh->recovery_count);
-}
-
-static void rh_update_states(struct region_hash *rh)
-{
-	struct region *reg, *next;
-
-	LIST_HEAD(clean);
-	LIST_HEAD(recovered);
-	LIST_HEAD(failed_recovered);
-
-	/*
-	 * Quickly grab the lists.
-	 */
-	write_lock_irq(&rh->hash_lock);
-	spin_lock(&rh->region_lock);
-	if (!list_empty(&rh->clean_regions)) {
-		list_splice_init(&rh->clean_regions, &clean);
-
-		list_for_each_entry(reg, &clean, list)
-			list_del(&reg->hash_list);
-	}
-
-	if (!list_empty(&rh->recovered_regions)) {
-		list_splice_init(&rh->recovered_regions, &recovered);
-
-		list_for_each_entry (reg, &recovered, list)
-			list_del(&reg->hash_list);
-	}
-
-	if (!list_empty(&rh->failed_recovered_regions)) {
-		list_splice_init(&rh->failed_recovered_regions,
-				 &failed_recovered);
-
-		list_for_each_entry(reg, &failed_recovered, list)
-			list_del(&reg->hash_list);
-	}
-
-	spin_unlock(&rh->region_lock);
-	write_unlock_irq(&rh->hash_lock);
-
-	/*
-	 * All the regions on the recovered and clean lists have
-	 * now been pulled out of the system, so no need to do
-	 * any more locking.
-	 */
-	list_for_each_entry_safe (reg, next, &recovered, list) {
-		rh->log->type->clear_region(rh->log, reg->key);
-		complete_resync_work(reg, 1);
-		mempool_free(reg, rh->region_pool);
-	}
-
-	list_for_each_entry_safe(reg, next, &failed_recovered, list) {
-		complete_resync_work(reg, errors_handled(rh->ms) ? 0 : 1);
-		mempool_free(reg, rh->region_pool);
-	}
-
-	list_for_each_entry_safe(reg, next, &clean, list) {
-		rh->log->type->clear_region(rh->log, reg->key);
-		mempool_free(reg, rh->region_pool);
-	}
-
-	rh->log->type->flush(rh->log);
-}
-
-static void rh_inc(struct region_hash *rh, region_t region)
-{
-	struct region *reg;
-
-	read_lock(&rh->hash_lock);
-	reg = __rh_find(rh, region);
-
-	spin_lock_irq(&rh->region_lock);
-	atomic_inc(&reg->pending);
-
-	if (reg->state == RH_CLEAN) {
-		reg->state = RH_DIRTY;
-		list_del_init(&reg->list);	/* take off the clean list */
-		spin_unlock_irq(&rh->region_lock);
-
-		rh->log->type->mark_region(rh->log, reg->key);
-	} else
-		spin_unlock_irq(&rh->region_lock);
-
-
-	read_unlock(&rh->hash_lock);
-}
-
-static void rh_inc_pending(struct region_hash *rh, struct bio_list *bios)
+static void wakeup_all_recovery_waiters(void *context)
 {
-	struct bio *bio;
-
-	for (bio = bios->head; bio; bio = bio->bi_next)
-		rh_inc(rh, bio_to_region(rh, bio));
+	wake_up_all(&_kmirrord_recovery_stopped);
 }
 
-static void rh_dec(struct region_hash *rh, region_t region)
+static void queue_bio(struct mirror_set *ms, struct bio *bio, int rw)
 {
 	unsigned long flags;
-	struct region *reg;
 	int should_wake = 0;
+	struct bio_list *bl;
 
-	read_lock(&rh->hash_lock);
-	reg = __rh_lookup(rh, region);
-	read_unlock(&rh->hash_lock);
-
-	spin_lock_irqsave(&rh->region_lock, flags);
-	if (atomic_dec_and_test(&reg->pending)) {
-		/*
-		 * There is no pending I/O for this region.
-		 * We can move the region to corresponding list for next action.
-		 * At this point, the region is not yet connected to any list.
-		 *
-		 * If the state is RH_NOSYNC, the region should be kept off
-		 * from clean list.
-		 * The hash entry for RH_NOSYNC will remain in memory
-		 * until the region is recovered or the map is reloaded.
-		 */
-
-		/* do nothing for RH_NOSYNC */
-		if (reg->state == RH_RECOVERING) {
-			list_add_tail(&reg->list, &rh->quiesced_regions);
-		} else if (reg->state == RH_DIRTY) {
-			reg->state = RH_CLEAN;
-			list_add(&reg->list, &rh->clean_regions);
-		}
-		should_wake = 1;
-	}
-	spin_unlock_irqrestore(&rh->region_lock, flags);
+	bl = (rw == WRITE) ? &ms->writes : &ms->reads;
+	spin_lock_irqsave(&ms->lock, flags);
+	should_wake = !(bl->head);
+	bio_list_add(bl, bio);
+	spin_unlock_irqrestore(&ms->lock, flags);
 
 	if (should_wake)
-		wake(rh->ms);
+		wakeup_mirrord(ms);
 }
 
-/*
- * Starts quiescing a region in preparation for recovery.
- */
-static int __rh_recovery_prepare(struct region_hash *rh)
+static void dispatch_bios(void *context, struct bio_list *bio_list)
 {
-	int r;
-	struct region *reg;
-	region_t region;
-
-	/*
-	 * Ask the dirty log what's next.
-	 */
-	r = rh->log->type->get_resync_work(rh->log, &region);
-	if (r <= 0)
-		return r;
-
-	/*
-	 * Get this region, and start it quiescing by setting the
-	 * recovering flag.
-	 */
-	read_lock(&rh->hash_lock);
-	reg = __rh_find(rh, region);
-	read_unlock(&rh->hash_lock);
-
-	spin_lock_irq(&rh->region_lock);
-	reg->state = RH_RECOVERING;
-
-	/* Already quiesced ? */
-	if (atomic_read(&reg->pending))
-		list_del_init(&reg->list);
-	else
-		list_move(&reg->list, &rh->quiesced_regions);
-
-	spin_unlock_irq(&rh->region_lock);
-
-	return 1;
-}
-
-static void rh_recovery_prepare(struct region_hash *rh)
-{
-	/* Extra reference to avoid race with rh_stop_recovery */
-	atomic_inc(&rh->recovery_in_flight);
-
-	while (!down_trylock(&rh->recovery_count)) {
-		atomic_inc(&rh->recovery_in_flight);
-		if (__rh_recovery_prepare(rh) <= 0) {
-			atomic_dec(&rh->recovery_in_flight);
-			up(&rh->recovery_count);
-			break;
-		}
-	}
-
-	/* Drop the extra reference */
-	if (atomic_dec_and_test(&rh->recovery_in_flight))
-		wake_up_all(&_kmirrord_recovery_stopped);
-}
-
-/*
- * Returns any quiesced regions.
- */
-static struct region *rh_recovery_start(struct region_hash *rh)
-{
-	struct region *reg = NULL;
-
-	spin_lock_irq(&rh->region_lock);
-	if (!list_empty(&rh->quiesced_regions)) {
-		reg = list_entry(rh->quiesced_regions.next,
-				 struct region, list);
-		list_del_init(&reg->list);	/* remove from the quiesced list */
-	}
-	spin_unlock_irq(&rh->region_lock);
-
-	return reg;
-}
-
-static void rh_recovery_end(struct region *reg, int success)
-{
-	struct region_hash *rh = reg->rh;
-
-	spin_lock_irq(&rh->region_lock);
-	if (success)
-		list_add(&reg->list, &reg->rh->recovered_regions);
-	else {
-		reg->state = RH_NOSYNC;
-		list_add(&reg->list, &reg->rh->failed_recovered_regions);
-	}
-	spin_unlock_irq(&rh->region_lock);
-
-	wake(rh->ms);
-}
-
-static int rh_flush(struct region_hash *rh)
-{
-	return rh->log->type->flush(rh->log);
-}
-
-static void rh_delay(struct region_hash *rh, struct bio *bio)
-{
-	struct region *reg;
-
-	read_lock(&rh->hash_lock);
-	reg = __rh_find(rh, bio_to_region(rh, bio));
-	bio_list_add(&reg->delayed_bios, bio);
-	read_unlock(&rh->hash_lock);
-}
-
-static void rh_stop_recovery(struct region_hash *rh)
-{
-	int i;
-
-	/* wait for any recovering regions */
-	for (i = 0; i < MAX_RECOVERY; i++)
-		down(&rh->recovery_count);
-}
-
-static void rh_start_recovery(struct region_hash *rh)
-{
-	int i;
-
-	for (i = 0; i < MAX_RECOVERY; i++)
-		up(&rh->recovery_count);
+	struct mirror_set *ms = context;
+	struct bio *bio;
 
-	wake(rh->ms);
+	while ((bio = bio_list_pop(bio_list)))
+		queue_bio(ms, bio, WRITE);
 }
 
 #define MIN_READ_RECORDS 20
@@ -777,8 +246,8 @@ out:
 static void recovery_complete(int read_err, unsigned long write_err,
 			      void *context)
 {
-	struct region *reg = (struct region *)context;
-	struct mirror_set *ms = reg->rh->ms;
+	struct dm_region *reg = context;
+	struct mirror_set *ms = dm_rh_region_context(reg);
 	int m, bit = 0;
 
 	if (read_err) {
@@ -804,31 +273,33 @@ static void recovery_complete(int read_err, unsigned long write_err,
 		}
 	}
 
-	rh_recovery_end(reg, !(read_err || write_err));
+	dm_rh_recovery_end(reg, !(read_err || write_err));
 }
 
-static int recover(struct mirror_set *ms, struct region *reg)
+static int recover(struct mirror_set *ms, struct dm_region *reg)
 {
 	int r;
-	unsigned int i;
+	unsigned i;
 	struct dm_io_region from, to[DM_KCOPYD_MAX_REGIONS], *dest;
 	struct mirror *m;
 	unsigned long flags = 0;
+	region_t key = dm_rh_get_region_key(reg);
+	sector_t region_size = dm_rh_get_region_size(ms->rh);
 
 	/* fill in the source */
 	m = get_default_mirror(ms);
 	from.bdev = m->dev->bdev;
-	from.sector = m->offset + region_to_sector(reg->rh, reg->key);
-	if (reg->key == (ms->nr_regions - 1)) {
+	from.sector = m->offset + dm_rh_region_to_sector(ms->rh, key);
+	if (key == (ms->nr_regions - 1)) {
 		/*
 		 * The final region may be smaller than
 		 * region_size.
 		 */
-		from.count = ms->ti->len & (reg->rh->region_size - 1);
+		from.count = ms->ti->len & (region_size - 1);
 		if (!from.count)
-			from.count = reg->rh->region_size;
+			from.count = region_size;
 	} else
-		from.count = reg->rh->region_size;
+		from.count = region_size;
 
 	/* fill in the destinations */
 	for (i = 0, dest = to; i < ms->nr_mirrors; i++) {
@@ -837,7 +308,7 @@ static int recover(struct mirror_set *ms, struct region *reg)
 
 		m = ms->mirror + i;
 		dest->bdev = m->dev->bdev;
-		dest->sector = m->offset + region_to_sector(reg->rh, reg->key);
+		dest->sector = m->offset + dm_rh_region_to_sector(ms->rh, key);
 		dest->count = from.count;
 		dest++;
 	}
@@ -854,22 +325,22 @@ static int recover(struct mirror_set *ms, struct region *reg)
 
 static void do_recovery(struct mirror_set *ms)
 {
+	struct dm_region *reg;
+	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
 	int r;
-	struct region *reg;
-	struct dm_dirty_log *log = ms->rh.log;
 
 	/*
 	 * Start quiescing some regions.
 	 */
-	rh_recovery_prepare(&ms->rh);
+	dm_rh_recovery_prepare(ms->rh);
 
 	/*
 	 * Copy any already quiesced regions.
 	 */
-	while ((reg = rh_recovery_start(&ms->rh))) {
+	while ((reg = dm_rh_recovery_start(ms->rh))) {
 		r = recover(ms, reg);
 		if (r)
-			rh_recovery_end(reg, 0);
+			dm_rh_recovery_end(reg, 0);
 	}
 
 	/*
@@ -910,9 +381,10 @@ static int default_ok(struct mirror *m)
 
 static int mirror_available(struct mirror_set *ms, struct bio *bio)
 {
-	region_t region = bio_to_region(&ms->rh, bio);
+	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
+	region_t region = dm_rh_bio_to_region(ms->rh, bio);
 
-	if (ms->rh.log->type->in_sync(ms->rh.log, region, 0))
+	if (log->type->in_sync(log, region, 0))
 		return choose_mirror(ms,  bio->bi_sector) ? 1 : 0;
 
 	return 0;
@@ -986,7 +458,14 @@ static void read_async_bio(struct mirror *m, struct bio *bio)
 
 	map_region(&io, m, bio);
 	bio_set_m(bio, m);
-	(void) dm_io(&io_req, 1, &io, NULL);
+	BUG_ON(dm_io(&io_req, 1, &io, NULL));
+}
+
+static inline int region_in_sync(struct mirror_set *ms, region_t region,
+				 int may_block)
+{
+	int state = dm_rh_get_state(ms->rh, region, may_block);
+	return state == DM_RH_CLEAN || state == DM_RH_DIRTY;
 }
 
 static void do_reads(struct mirror_set *ms, struct bio_list *reads)
@@ -996,13 +475,13 @@ static void do_reads(struct mirror_set *ms, struct bio_list *reads)
 	struct mirror *m;
 
 	while ((bio = bio_list_pop(reads))) {
-		region = bio_to_region(&ms->rh, bio);
+		region = dm_rh_bio_to_region(ms->rh, bio);
 		m = get_default_mirror(ms);
 
 		/*
 		 * We can only read balance if the region is in sync.
 		 */
-		if (likely(rh_in_sync(&ms->rh, region, 1)))
+		if (likely(region_in_sync(ms, region, 1)))
 			m = choose_mirror(ms, bio->bi_sector);
 		else if (m && atomic_read(&m->error_count))
 			m = NULL;
@@ -1025,57 +504,6 @@ static void do_reads(struct mirror_set *ms, struct bio_list *reads)
  * NOSYNC:	increment pending, just write to the default mirror
  *---------------------------------------------------------------*/
 
-/* __bio_mark_nosync
- * @ms
- * @bio
- * @done
- * @error
- *
- * The bio was written on some mirror(s) but failed on other mirror(s).
- * We can successfully endio the bio but should avoid the region being
- * marked clean by setting the state RH_NOSYNC.
- *
- * This function is _not_ safe in interrupt context!
- */
-static void __bio_mark_nosync(struct mirror_set *ms,
-			      struct bio *bio, unsigned done, int error)
-{
-	unsigned long flags;
-	struct region_hash *rh = &ms->rh;
-	struct dm_dirty_log *log = ms->rh.log;
-	struct region *reg;
-	region_t region = bio_to_region(rh, bio);
-	int recovering = 0;
-
-	/* We must inform the log that the sync count has changed. */
-	log->type->set_region_sync(log, region, 0);
-	ms->in_sync = 0;
-
-	read_lock(&rh->hash_lock);
-	reg = __rh_find(rh, region);
-	read_unlock(&rh->hash_lock);
-
-	/* region hash entry should exist because write was in-flight */
-	BUG_ON(!reg);
-	BUG_ON(!list_empty(&reg->list));
-
-	spin_lock_irqsave(&rh->region_lock, flags);
-	/*
-	 * Possible cases:
-	 *   1) RH_DIRTY
-	 *   2) RH_NOSYNC: was dirty, other preceeding writes failed
-	 *   3) RH_RECOVERING: flushing pending writes
-	 * Either case, the region should have not been connected to list.
-	 */
-	recovering = (reg->state == RH_RECOVERING);
-	reg->state = RH_NOSYNC;
-	BUG_ON(!list_empty(&reg->list));
-	spin_unlock_irqrestore(&rh->region_lock, flags);
-
-	bio_endio(bio, error);
-	if (recovering)
-		complete_resync_work(reg, 0);
-}
 
 static void write_callback(unsigned long error, void *context)
 {
@@ -1120,7 +548,7 @@ static void write_callback(unsigned long error, void *context)
 		bio_list_add(&ms->failures, bio);
 		spin_unlock_irqrestore(&ms->lock, flags);
 		if (should_wake)
-			wake(ms);
+			wakeup_mirrord(ms);
 		return;
 	}
 out:
@@ -1150,7 +578,7 @@ static void do_write(struct mirror_set *ms, struct bio *bio)
 	 */
 	bio_set_m(bio, get_default_mirror(ms));
 
-	(void) dm_io(&io_req, ms->nr_mirrors, io, NULL);
+	BUG_ON(dm_io(&io_req, ms->nr_mirrors, io, NULL));
 }
 
 static void do_writes(struct mirror_set *ms, struct bio_list *writes)
@@ -1170,18 +598,19 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	bio_list_init(&recover);
 
 	while ((bio = bio_list_pop(writes))) {
-		state = rh_state(&ms->rh, bio_to_region(&ms->rh, bio), 1);
+		state = dm_rh_get_state(ms->rh,
+					dm_rh_bio_to_region(ms->rh, bio), 1);
 		switch (state) {
-		case RH_CLEAN:
-		case RH_DIRTY:
+		case DM_RH_CLEAN:
+		case DM_RH_DIRTY:
 			this_list = &sync;
 			break;
 
-		case RH_NOSYNC:
+		case DM_RH_NOSYNC:
 			this_list = &nosync;
 			break;
 
-		case RH_RECOVERING:
+		case DM_RH_RECOVERING:
 			this_list = &recover;
 			break;
 		}
@@ -1194,9 +623,9 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	 * be written to (writes to recover regions are going to
 	 * be delayed).
 	 */
-	rh_inc_pending(&ms->rh, &sync);
-	rh_inc_pending(&ms->rh, &nosync);
-	ms->log_failure = rh_flush(&ms->rh) ? 1 : 0;
+	dm_rh_inc_pending(ms->rh, &sync);
+	dm_rh_inc_pending(ms->rh, &nosync);
+	ms->log_failure = dm_rh_flush(ms->rh) ? 1 : 0;
 
 	/*
 	 * Dispatch io.
@@ -1205,13 +634,13 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 		spin_lock_irq(&ms->lock);
 		bio_list_merge(&ms->failures, &sync);
 		spin_unlock_irq(&ms->lock);
-		wake(ms);
+		wakeup_mirrord(ms);
 	} else
 		while ((bio = bio_list_pop(&sync)))
 			do_write(ms, bio);
 
 	while ((bio = bio_list_pop(&recover)))
-		rh_delay(&ms->rh, bio);
+		dm_rh_delay(ms->rh, bio);
 
 	while ((bio = bio_list_pop(&nosync))) {
 		map_bio(get_default_mirror(ms), bio);
@@ -1228,7 +657,8 @@ static void do_failures(struct mirror_set *ms, struct bio_list *failures)
 
 	if (!ms->log_failure) {
 		while ((bio = bio_list_pop(failures)))
-			__bio_mark_nosync(ms, bio, bio->bi_size, 0);
+			ms->in_sync = 0;
+			dm_rh_mark_nosync(ms->rh, bio, bio->bi_size, 0);
 		return;
 	}
 
@@ -1281,8 +711,8 @@ static void trigger_event(struct work_struct *work)
  *---------------------------------------------------------------*/
 static void do_mirror(struct work_struct *work)
 {
-	struct mirror_set *ms =container_of(work, struct mirror_set,
-					    kmirrord_work);
+	struct mirror_set *ms = container_of(work, struct mirror_set,
+					     kmirrord_work);
 	struct bio_list reads, writes, failures;
 	unsigned long flags;
 
@@ -1295,7 +725,7 @@ static void do_mirror(struct work_struct *work)
 	bio_list_init(&ms->failures);
 	spin_unlock_irqrestore(&ms->lock, flags);
 
-	rh_update_states(&ms->rh);
+	dm_rh_update_states(ms->rh, errors_handled(ms));
 	do_recovery(ms);
 	do_reads(ms, &reads);
 	do_writes(ms, &writes);
@@ -1304,7 +734,6 @@ static void do_mirror(struct work_struct *work)
 	dm_table_unplug_all(ms->ti->table);
 }
 
-
 /*-----------------------------------------------------------------
  * Target functions
  *---------------------------------------------------------------*/
@@ -1351,7 +780,11 @@ static struct mirror_set *alloc_context(unsigned int nr_mirrors,
  		return NULL;
 	}
 
-	if (rh_init(&ms->rh, ms, dl, region_size, ms->nr_regions)) {
+	ms->rh = dm_region_hash_create(ms, dispatch_bios, wakeup_mirrord,
+				       wakeup_all_recovery_waiters,
+				       ms->ti->begin, MAX_RECOVERY,
+				       dl, region_size, ms->nr_regions);
+	if (IS_ERR(ms->rh)) {
 		ti->error = "Error creating dirty region hash";
 		dm_io_client_destroy(ms->io_client);
 		mempool_destroy(ms->read_record_pool);
@@ -1369,7 +802,7 @@ static void free_context(struct mirror_set *ms, struct dm_target *ti,
 		dm_put_device(ti, ms->mirror[m].dev);
 
 	dm_io_client_destroy(ms->io_client);
-	rh_exit(&ms->rh);
+	dm_region_hash_destroy(ms->rh);
 	mempool_destroy(ms->read_record_pool);
 	kfree(ms);
 }
@@ -1409,10 +842,10 @@ static int get_mirror(struct mirror_set *ms, struct dm_target *ti,
  * Create dirty log: log_type #log_params <log_params>
  */
 static struct dm_dirty_log *create_dirty_log(struct dm_target *ti,
-					  unsigned int argc, char **argv,
-					  unsigned int *args_used)
+					     unsigned argc, char **argv,
+					     unsigned *args_used)
 {
-	unsigned int param_count;
+	unsigned param_count;
 	struct dm_dirty_log *dl;
 
 	if (argc < 2) {
@@ -1543,7 +976,7 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	ti->private = ms;
- 	ti->split_io = ms->rh.region_size;
+	ti->split_io = dm_rh_get_region_size(ms->rh);
 
 	ms->kmirrord_wq = create_singlethread_workqueue("kmirrord");
 	if (!ms->kmirrord_wq) {
@@ -1578,11 +1011,11 @@ static int mirror_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 		goto err_destroy_wq;
 	}
 
-	r = dm_kcopyd_client_create(DM_IO_PAGES, &ms->kcopyd_client);
+	r = dm_kcopyd_client_create(DM_KCOPYD_PAGES, &ms->kcopyd_client);
 	if (r)
 		goto err_destroy_wq;
 
-	wake(ms);
+	wakeup_mirrord(ms);
 	return 0;
 
 err_destroy_wq:
@@ -1603,22 +1036,6 @@ static void mirror_dtr(struct dm_target *ti)
 	free_context(ms, ti, ms->nr_mirrors);
 }
 
-static void queue_bio(struct mirror_set *ms, struct bio *bio, int rw)
-{
-	unsigned long flags;
-	int should_wake = 0;
-	struct bio_list *bl;
-
-	bl = (rw == WRITE) ? &ms->writes : &ms->reads;
-	spin_lock_irqsave(&ms->lock, flags);
-	should_wake = !(bl->head);
-	bio_list_add(bl, bio);
-	spin_unlock_irqrestore(&ms->lock, flags);
-
-	if (should_wake)
-		wake(ms);
-}
-
 /*
  * Mirror mapping function
  */
@@ -1629,16 +1046,16 @@ static int mirror_map(struct dm_target *ti, struct bio *bio,
 	struct mirror *m;
 	struct mirror_set *ms = ti->private;
 	struct dm_raid1_read_record *read_record = NULL;
+	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
 
 	if (rw == WRITE) {
 		/* Save region for mirror_end_io() handler */
-		map_context->ll = bio_to_region(&ms->rh, bio);
+		map_context->ll = dm_rh_bio_to_region(ms->rh, bio);
 		queue_bio(ms, bio, rw);
 		return DM_MAPIO_SUBMITTED;
 	}
 
-	r = ms->rh.log->type->in_sync(ms->rh.log,
-				      bio_to_region(&ms->rh, bio), 0);
+	r = log->type->in_sync(log, dm_rh_bio_to_region(ms->rh, bio), 0);
 	if (r < 0 && r != -EWOULDBLOCK)
 		return r;
 
@@ -1686,7 +1103,7 @@ static int mirror_end_io(struct dm_target *ti, struct bio *bio,
 	 * We need to dec pending if this was a write.
 	 */
 	if (rw == WRITE) {
-		rh_dec(&ms->rh, map_context->ll);
+		dm_rh_dec(ms->rh, map_context->ll);
 		return error;
 	}
 
@@ -1742,7 +1159,7 @@ out:
 static void mirror_presuspend(struct dm_target *ti)
 {
 	struct mirror_set *ms = (struct mirror_set *) ti->private;
-	struct dm_dirty_log *log = ms->rh.log;
+	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
 
 	atomic_set(&ms->suspend, 1);
 
@@ -1750,10 +1167,10 @@ static void mirror_presuspend(struct dm_target *ti)
 	 * We must finish up all the work that we've
 	 * generated (i.e. recovery work).
 	 */
-	rh_stop_recovery(&ms->rh);
+	dm_rh_stop_recovery(ms->rh);
 
 	wait_event(_kmirrord_recovery_stopped,
-		   !atomic_read(&ms->rh.recovery_in_flight));
+		   !dm_rh_recovery_in_flight(ms->rh));
 
 	if (log->type->presuspend && log->type->presuspend(log))
 		/* FIXME: need better error handling */
@@ -1771,7 +1188,7 @@ static void mirror_presuspend(struct dm_target *ti)
 static void mirror_postsuspend(struct dm_target *ti)
 {
 	struct mirror_set *ms = ti->private;
-	struct dm_dirty_log *log = ms->rh.log;
+	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
 
 	if (log->type->postsuspend && log->type->postsuspend(log))
 		/* FIXME: need better error handling */
@@ -1781,13 +1198,13 @@ static void mirror_postsuspend(struct dm_target *ti)
 static void mirror_resume(struct dm_target *ti)
 {
 	struct mirror_set *ms = ti->private;
-	struct dm_dirty_log *log = ms->rh.log;
+	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
 
 	atomic_set(&ms->suspend, 0);
 	if (log->type->resume && log->type->resume(log))
 		/* FIXME: need better error handling */
 		DMWARN("log resume failed");
-	rh_start_recovery(&ms->rh);
+	dm_rh_start_recovery(ms->rh);
 }
 
 /*
@@ -1819,7 +1236,7 @@ static int mirror_status(struct dm_target *ti, status_type_t type,
 {
 	unsigned int m, sz = 0;
 	struct mirror_set *ms = (struct mirror_set *) ti->private;
-	struct dm_dirty_log *log = ms->rh.log;
+	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
 	char buffer[ms->nr_mirrors + 1];
 
 	switch (type) {
@@ -1832,15 +1249,15 @@ static int mirror_status(struct dm_target *ti, status_type_t type,
 		buffer[m] = '\0';
 
 		DMEMIT("%llu/%llu 1 %s ",
-		      (unsigned long long)log->type->get_sync_count(ms->rh.log),
+		      (unsigned long long)log->type->get_sync_count(log),
 		      (unsigned long long)ms->nr_regions, buffer);
 
-		sz += log->type->status(ms->rh.log, type, result+sz, maxlen-sz);
+		sz += log->type->status(log, type, result+sz, maxlen-sz);
 
 		break;
 
 	case STATUSTYPE_TABLE:
-		sz = log->type->status(ms->rh.log, type, result, maxlen);
+		sz = log->type->status(log, type, result, maxlen);
 
 		DMEMIT("%d", ms->nr_mirrors);
 		for (m = 0; m < ms->nr_mirrors; m++)
diff --git a/drivers/md/dm-region-hash.c b/drivers/md/dm-region-hash.c
new file mode 100644
index 000000000000..59f8d9df9e1a
--- /dev/null
+++ b/drivers/md/dm-region-hash.c
@@ -0,0 +1,704 @@
+/*
+ * Copyright (C) 2003 Sistina Software Limited.
+ * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
+ *
+ * This file is released under the GPL.
+ */
+
+#include <linux/dm-dirty-log.h>
+#include <linux/dm-region-hash.h>
+
+#include <linux/ctype.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+
+#include "dm.h"
+#include "dm-bio-list.h"
+
+#define	DM_MSG_PREFIX	"region hash"
+
+/*-----------------------------------------------------------------
+ * Region hash
+ *
+ * The mirror splits itself up into discrete regions.  Each
+ * region can be in one of three states: clean, dirty,
+ * nosync.  There is no need to put clean regions in the hash.
+ *
+ * In addition to being present in the hash table a region _may_
+ * be present on one of three lists.
+ *
+ *   clean_regions: Regions on this list have no io pending to
+ *   them, they are in sync, we are no longer interested in them,
+ *   they are dull.  dm_rh_update_states() will remove them from the
+ *   hash table.
+ *
+ *   quiesced_regions: These regions have been spun down, ready
+ *   for recovery.  rh_recovery_start() will remove regions from
+ *   this list and hand them to kmirrord, which will schedule the
+ *   recovery io with kcopyd.
+ *
+ *   recovered_regions: Regions that kcopyd has successfully
+ *   recovered.  dm_rh_update_states() will now schedule any delayed
+ *   io, up the recovery_count, and remove the region from the
+ *   hash.
+ *
+ * There are 2 locks:
+ *   A rw spin lock 'hash_lock' protects just the hash table,
+ *   this is never held in write mode from interrupt context,
+ *   which I believe means that we only have to disable irqs when
+ *   doing a write lock.
+ *
+ *   An ordinary spin lock 'region_lock' that protects the three
+ *   lists in the region_hash, with the 'state', 'list' and
+ *   'delayed_bios' fields of the regions.  This is used from irq
+ *   context, so all other uses will have to suspend local irqs.
+ *---------------------------------------------------------------*/
+struct dm_region_hash {
+	uint32_t region_size;
+	unsigned region_shift;
+
+	/* holds persistent region state */
+	struct dm_dirty_log *log;
+
+	/* hash table */
+	rwlock_t hash_lock;
+	mempool_t *region_pool;
+	unsigned mask;
+	unsigned nr_buckets;
+	unsigned prime;
+	unsigned shift;
+	struct list_head *buckets;
+
+	unsigned max_recovery; /* Max # of regions to recover in parallel */
+
+	spinlock_t region_lock;
+	atomic_t recovery_in_flight;
+	struct semaphore recovery_count;
+	struct list_head clean_regions;
+	struct list_head quiesced_regions;
+	struct list_head recovered_regions;
+	struct list_head failed_recovered_regions;
+
+	void *context;
+	sector_t target_begin;
+
+	/* Callback function to schedule bios writes */
+	void (*dispatch_bios)(void *context, struct bio_list *bios);
+
+	/* Callback function to wakeup callers worker thread. */
+	void (*wakeup_workers)(void *context);
+
+	/* Callback function to wakeup callers recovery waiters. */
+	void (*wakeup_all_recovery_waiters)(void *context);
+};
+
+struct dm_region {
+	struct dm_region_hash *rh;	/* FIXME: can we get rid of this ? */
+	region_t key;
+	int state;
+
+	struct list_head hash_list;
+	struct list_head list;
+
+	atomic_t pending;
+	struct bio_list delayed_bios;
+};
+
+/*
+ * Conversion fns
+ */
+static region_t dm_rh_sector_to_region(struct dm_region_hash *rh, sector_t sector)
+{
+	return sector >> rh->region_shift;
+}
+
+sector_t dm_rh_region_to_sector(struct dm_region_hash *rh, region_t region)
+{
+	return region << rh->region_shift;
+}
+EXPORT_SYMBOL_GPL(dm_rh_region_to_sector);
+
+region_t dm_rh_bio_to_region(struct dm_region_hash *rh, struct bio *bio)
+{
+	return dm_rh_sector_to_region(rh, bio->bi_sector - rh->target_begin);
+}
+EXPORT_SYMBOL_GPL(dm_rh_bio_to_region);
+
+void *dm_rh_region_context(struct dm_region *reg)
+{
+	return reg->rh->context;
+}
+EXPORT_SYMBOL_GPL(dm_rh_region_context);
+
+region_t dm_rh_get_region_key(struct dm_region *reg)
+{
+	return reg->key;
+}
+EXPORT_SYMBOL_GPL(dm_rh_get_region_key);
+
+sector_t dm_rh_get_region_size(struct dm_region_hash *rh)
+{
+	return rh->region_size;
+}
+EXPORT_SYMBOL_GPL(dm_rh_get_region_size);
+
+/*
+ * FIXME: shall we pass in a structure instead of all these args to
+ * dm_region_hash_create()????
+ */
+#define RH_HASH_MULT 2654435387U
+#define RH_HASH_SHIFT 12
+
+#define MIN_REGIONS 64
+struct dm_region_hash *dm_region_hash_create(
+		void *context, void (*dispatch_bios)(void *context,
+						     struct bio_list *bios),
+		void (*wakeup_workers)(void *context),
+		void (*wakeup_all_recovery_waiters)(void *context),
+		sector_t target_begin, unsigned max_recovery,
+		struct dm_dirty_log *log, uint32_t region_size,
+		region_t nr_regions)
+{
+	struct dm_region_hash *rh;
+	unsigned nr_buckets, max_buckets;
+	size_t i;
+
+	/*
+	 * Calculate a suitable number of buckets for our hash
+	 * table.
+	 */
+	max_buckets = nr_regions >> 6;
+	for (nr_buckets = 128u; nr_buckets < max_buckets; nr_buckets <<= 1)
+		;
+	nr_buckets >>= 1;
+
+	rh = kmalloc(sizeof(*rh), GFP_KERNEL);
+	if (!rh) {
+		DMERR("unable to allocate region hash memory");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	rh->context = context;
+	rh->dispatch_bios = dispatch_bios;
+	rh->wakeup_workers = wakeup_workers;
+	rh->wakeup_all_recovery_waiters = wakeup_all_recovery_waiters;
+	rh->target_begin = target_begin;
+	rh->max_recovery = max_recovery;
+	rh->log = log;
+	rh->region_size = region_size;
+	rh->region_shift = ffs(region_size) - 1;
+	rwlock_init(&rh->hash_lock);
+	rh->mask = nr_buckets - 1;
+	rh->nr_buckets = nr_buckets;
+
+	rh->shift = RH_HASH_SHIFT;
+	rh->prime = RH_HASH_MULT;
+
+	rh->buckets = vmalloc(nr_buckets * sizeof(*rh->buckets));
+	if (!rh->buckets) {
+		DMERR("unable to allocate region hash bucket memory");
+		kfree(rh);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	for (i = 0; i < nr_buckets; i++)
+		INIT_LIST_HEAD(rh->buckets + i);
+
+	spin_lock_init(&rh->region_lock);
+	sema_init(&rh->recovery_count, 0);
+	atomic_set(&rh->recovery_in_flight, 0);
+	INIT_LIST_HEAD(&rh->clean_regions);
+	INIT_LIST_HEAD(&rh->quiesced_regions);
+	INIT_LIST_HEAD(&rh->recovered_regions);
+	INIT_LIST_HEAD(&rh->failed_recovered_regions);
+
+	rh->region_pool = mempool_create_kmalloc_pool(MIN_REGIONS,
+						      sizeof(struct dm_region));
+	if (!rh->region_pool) {
+		vfree(rh->buckets);
+		kfree(rh);
+		rh = ERR_PTR(-ENOMEM);
+	}
+
+	return rh;
+}
+EXPORT_SYMBOL_GPL(dm_region_hash_create);
+
+void dm_region_hash_destroy(struct dm_region_hash *rh)
+{
+	unsigned h;
+	struct dm_region *reg, *nreg;
+
+	BUG_ON(!list_empty(&rh->quiesced_regions));
+	for (h = 0; h < rh->nr_buckets; h++) {
+		list_for_each_entry_safe(reg, nreg, rh->buckets + h,
+					 hash_list) {
+			BUG_ON(atomic_read(&reg->pending));
+			mempool_free(reg, rh->region_pool);
+		}
+	}
+
+	if (rh->log)
+		dm_dirty_log_destroy(rh->log);
+
+	if (rh->region_pool)
+		mempool_destroy(rh->region_pool);
+
+	vfree(rh->buckets);
+	kfree(rh);
+}
+EXPORT_SYMBOL_GPL(dm_region_hash_destroy);
+
+struct dm_dirty_log *dm_rh_dirty_log(struct dm_region_hash *rh)
+{
+	return rh->log;
+}
+EXPORT_SYMBOL_GPL(dm_rh_dirty_log);
+
+static unsigned rh_hash(struct dm_region_hash *rh, region_t region)
+{
+	return (unsigned) ((region * rh->prime) >> rh->shift) & rh->mask;
+}
+
+static struct dm_region *__rh_lookup(struct dm_region_hash *rh, region_t region)
+{
+	struct dm_region *reg;
+	struct list_head *bucket = rh->buckets + rh_hash(rh, region);
+
+	list_for_each_entry(reg, bucket, hash_list)
+		if (reg->key == region)
+			return reg;
+
+	return NULL;
+}
+
+static void __rh_insert(struct dm_region_hash *rh, struct dm_region *reg)
+{
+	list_add(&reg->hash_list, rh->buckets + rh_hash(rh, reg->key));
+}
+
+static struct dm_region *__rh_alloc(struct dm_region_hash *rh, region_t region)
+{
+	struct dm_region *reg, *nreg;
+
+	nreg = mempool_alloc(rh->region_pool, GFP_ATOMIC);
+	if (unlikely(!nreg))
+		nreg = kmalloc(sizeof(*nreg), GFP_NOIO);
+
+	nreg->state = rh->log->type->in_sync(rh->log, region, 1) ?
+		      DM_RH_CLEAN : DM_RH_NOSYNC;
+	nreg->rh = rh;
+	nreg->key = region;
+	INIT_LIST_HEAD(&nreg->list);
+	atomic_set(&nreg->pending, 0);
+	bio_list_init(&nreg->delayed_bios);
+
+	write_lock_irq(&rh->hash_lock);
+	reg = __rh_lookup(rh, region);
+	if (reg)
+		/* We lost the race. */
+		mempool_free(nreg, rh->region_pool);
+	else {
+		__rh_insert(rh, nreg);
+		if (nreg->state == DM_RH_CLEAN) {
+			spin_lock(&rh->region_lock);
+			list_add(&nreg->list, &rh->clean_regions);
+			spin_unlock(&rh->region_lock);
+		}
+
+		reg = nreg;
+	}
+	write_unlock_irq(&rh->hash_lock);
+
+	return reg;
+}
+
+static struct dm_region *__rh_find(struct dm_region_hash *rh, region_t region)
+{
+	struct dm_region *reg;
+
+	reg = __rh_lookup(rh, region);
+	if (!reg) {
+		read_unlock(&rh->hash_lock);
+		reg = __rh_alloc(rh, region);
+		read_lock(&rh->hash_lock);
+	}
+
+	return reg;
+}
+
+int dm_rh_get_state(struct dm_region_hash *rh, region_t region, int may_block)
+{
+	int r;
+	struct dm_region *reg;
+
+	read_lock(&rh->hash_lock);
+	reg = __rh_lookup(rh, region);
+	read_unlock(&rh->hash_lock);
+
+	if (reg)
+		return reg->state;
+
+	/*
+	 * The region wasn't in the hash, so we fall back to the
+	 * dirty log.
+	 */
+	r = rh->log->type->in_sync(rh->log, region, may_block);
+
+	/*
+	 * Any error from the dirty log (eg. -EWOULDBLOCK) gets
+	 * taken as a DM_RH_NOSYNC
+	 */
+	return r == 1 ? DM_RH_CLEAN : DM_RH_NOSYNC;
+}
+EXPORT_SYMBOL_GPL(dm_rh_get_state);
+
+static void complete_resync_work(struct dm_region *reg, int success)
+{
+	struct dm_region_hash *rh = reg->rh;
+
+	rh->log->type->set_region_sync(rh->log, reg->key, success);
+
+	/*
+	 * Dispatch the bios before we call 'wake_up_all'.
+	 * This is important because if we are suspending,
+	 * we want to know that recovery is complete and
+	 * the work queue is flushed.  If we wake_up_all
+	 * before we dispatch_bios (queue bios and call wake()),
+	 * then we risk suspending before the work queue
+	 * has been properly flushed.
+	 */
+	rh->dispatch_bios(rh->context, &reg->delayed_bios);
+	if (atomic_dec_and_test(&rh->recovery_in_flight))
+		rh->wakeup_all_recovery_waiters(rh->context);
+	up(&rh->recovery_count);
+}
+
+/* dm_rh_mark_nosync
+ * @ms
+ * @bio
+ * @done
+ * @error
+ *
+ * The bio was written on some mirror(s) but failed on other mirror(s).
+ * We can successfully endio the bio but should avoid the region being
+ * marked clean by setting the state DM_RH_NOSYNC.
+ *
+ * This function is _not_ safe in interrupt context!
+ */
+void dm_rh_mark_nosync(struct dm_region_hash *rh,
+		       struct bio *bio, unsigned done, int error)
+{
+	unsigned long flags;
+	struct dm_dirty_log *log = rh->log;
+	struct dm_region *reg;
+	region_t region = dm_rh_bio_to_region(rh, bio);
+	int recovering = 0;
+
+	/* We must inform the log that the sync count has changed. */
+	log->type->set_region_sync(log, region, 0);
+
+	read_lock(&rh->hash_lock);
+	reg = __rh_find(rh, region);
+	read_unlock(&rh->hash_lock);
+
+	/* region hash entry should exist because write was in-flight */
+	BUG_ON(!reg);
+	BUG_ON(!list_empty(&reg->list));
+
+	spin_lock_irqsave(&rh->region_lock, flags);
+	/*
+	 * Possible cases:
+	 *   1) DM_RH_DIRTY
+	 *   2) DM_RH_NOSYNC: was dirty, other preceeding writes failed
+	 *   3) DM_RH_RECOVERING: flushing pending writes
+	 * Either case, the region should have not been connected to list.
+	 */
+	recovering = (reg->state == DM_RH_RECOVERING);
+	reg->state = DM_RH_NOSYNC;
+	BUG_ON(!list_empty(&reg->list));
+	spin_unlock_irqrestore(&rh->region_lock, flags);
+
+	bio_endio(bio, error);
+	if (recovering)
+		complete_resync_work(reg, 0);
+}
+EXPORT_SYMBOL_GPL(dm_rh_mark_nosync);
+
+void dm_rh_update_states(struct dm_region_hash *rh, int errors_handled)
+{
+	struct dm_region *reg, *next;
+
+	LIST_HEAD(clean);
+	LIST_HEAD(recovered);
+	LIST_HEAD(failed_recovered);
+
+	/*
+	 * Quickly grab the lists.
+	 */
+	write_lock_irq(&rh->hash_lock);
+	spin_lock(&rh->region_lock);
+	if (!list_empty(&rh->clean_regions)) {
+		list_splice_init(&rh->clean_regions, &clean);
+
+		list_for_each_entry(reg, &clean, list)
+			list_del(&reg->hash_list);
+	}
+
+	if (!list_empty(&rh->recovered_regions)) {
+		list_splice_init(&rh->recovered_regions, &recovered);
+
+		list_for_each_entry(reg, &recovered, list)
+			list_del(&reg->hash_list);
+	}
+
+	if (!list_empty(&rh->failed_recovered_regions)) {
+		list_splice_init(&rh->failed_recovered_regions,
+				 &failed_recovered);
+
+		list_for_each_entry(reg, &failed_recovered, list)
+			list_del(&reg->hash_list);
+	}
+
+	spin_unlock(&rh->region_lock);
+	write_unlock_irq(&rh->hash_lock);
+
+	/*
+	 * All the regions on the recovered and clean lists have
+	 * now been pulled out of the system, so no need to do
+	 * any more locking.
+	 */
+	list_for_each_entry_safe(reg, next, &recovered, list) {
+		rh->log->type->clear_region(rh->log, reg->key);
+		complete_resync_work(reg, 1);
+		mempool_free(reg, rh->region_pool);
+	}
+
+	list_for_each_entry_safe(reg, next, &failed_recovered, list) {
+		complete_resync_work(reg, errors_handled ? 0 : 1);
+		mempool_free(reg, rh->region_pool);
+	}
+
+	list_for_each_entry_safe(reg, next, &clean, list) {
+		rh->log->type->clear_region(rh->log, reg->key);
+		mempool_free(reg, rh->region_pool);
+	}
+
+	rh->log->type->flush(rh->log);
+}
+EXPORT_SYMBOL_GPL(dm_rh_update_states);
+
+static void rh_inc(struct dm_region_hash *rh, region_t region)
+{
+	struct dm_region *reg;
+
+	read_lock(&rh->hash_lock);
+	reg = __rh_find(rh, region);
+
+	spin_lock_irq(&rh->region_lock);
+	atomic_inc(&reg->pending);
+
+	if (reg->state == DM_RH_CLEAN) {
+		reg->state = DM_RH_DIRTY;
+		list_del_init(&reg->list);	/* take off the clean list */
+		spin_unlock_irq(&rh->region_lock);
+
+		rh->log->type->mark_region(rh->log, reg->key);
+	} else
+		spin_unlock_irq(&rh->region_lock);
+
+
+	read_unlock(&rh->hash_lock);
+}
+
+void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios)
+{
+	struct bio *bio;
+
+	for (bio = bios->head; bio; bio = bio->bi_next)
+		rh_inc(rh, dm_rh_bio_to_region(rh, bio));
+}
+EXPORT_SYMBOL_GPL(dm_rh_inc_pending);
+
+void dm_rh_dec(struct dm_region_hash *rh, region_t region)
+{
+	unsigned long flags;
+	struct dm_region *reg;
+	int should_wake = 0;
+
+	read_lock(&rh->hash_lock);
+	reg = __rh_lookup(rh, region);
+	read_unlock(&rh->hash_lock);
+
+	spin_lock_irqsave(&rh->region_lock, flags);
+	if (atomic_dec_and_test(&reg->pending)) {
+		/*
+		 * There is no pending I/O for this region.
+		 * We can move the region to corresponding list for next action.
+		 * At this point, the region is not yet connected to any list.
+		 *
+		 * If the state is DM_RH_NOSYNC, the region should be kept off
+		 * from clean list.
+		 * The hash entry for DM_RH_NOSYNC will remain in memory
+		 * until the region is recovered or the map is reloaded.
+		 */
+
+		/* do nothing for DM_RH_NOSYNC */
+		if (reg->state == DM_RH_RECOVERING) {
+			list_add_tail(&reg->list, &rh->quiesced_regions);
+		} else if (reg->state == DM_RH_DIRTY) {
+			reg->state = DM_RH_CLEAN;
+			list_add(&reg->list, &rh->clean_regions);
+		}
+		should_wake = 1;
+	}
+	spin_unlock_irqrestore(&rh->region_lock, flags);
+
+	if (should_wake)
+		rh->wakeup_workers(rh->context);
+}
+EXPORT_SYMBOL_GPL(dm_rh_dec);
+
+/*
+ * Starts quiescing a region in preparation for recovery.
+ */
+static int __rh_recovery_prepare(struct dm_region_hash *rh)
+{
+	int r;
+	region_t region;
+	struct dm_region *reg;
+
+	/*
+	 * Ask the dirty log what's next.
+	 */
+	r = rh->log->type->get_resync_work(rh->log, &region);
+	if (r <= 0)
+		return r;
+
+	/*
+	 * Get this region, and start it quiescing by setting the
+	 * recovering flag.
+	 */
+	read_lock(&rh->hash_lock);
+	reg = __rh_find(rh, region);
+	read_unlock(&rh->hash_lock);
+
+	spin_lock_irq(&rh->region_lock);
+	reg->state = DM_RH_RECOVERING;
+
+	/* Already quiesced ? */
+	if (atomic_read(&reg->pending))
+		list_del_init(&reg->list);
+	else
+		list_move(&reg->list, &rh->quiesced_regions);
+
+	spin_unlock_irq(&rh->region_lock);
+
+	return 1;
+}
+
+void dm_rh_recovery_prepare(struct dm_region_hash *rh)
+{
+	/* Extra reference to avoid race with dm_rh_stop_recovery */
+	atomic_inc(&rh->recovery_in_flight);
+
+	while (!down_trylock(&rh->recovery_count)) {
+		atomic_inc(&rh->recovery_in_flight);
+		if (__rh_recovery_prepare(rh) <= 0) {
+			atomic_dec(&rh->recovery_in_flight);
+			up(&rh->recovery_count);
+			break;
+		}
+	}
+
+	/* Drop the extra reference */
+	if (atomic_dec_and_test(&rh->recovery_in_flight))
+		rh->wakeup_all_recovery_waiters(rh->context);
+}
+EXPORT_SYMBOL_GPL(dm_rh_recovery_prepare);
+
+/*
+ * Returns any quiesced regions.
+ */
+struct dm_region *dm_rh_recovery_start(struct dm_region_hash *rh)
+{
+	struct dm_region *reg = NULL;
+
+	spin_lock_irq(&rh->region_lock);
+	if (!list_empty(&rh->quiesced_regions)) {
+		reg = list_entry(rh->quiesced_regions.next,
+				 struct dm_region, list);
+		list_del_init(&reg->list);  /* remove from the quiesced list */
+	}
+	spin_unlock_irq(&rh->region_lock);
+
+	return reg;
+}
+EXPORT_SYMBOL_GPL(dm_rh_recovery_start);
+
+void dm_rh_recovery_end(struct dm_region *reg, int success)
+{
+	struct dm_region_hash *rh = reg->rh;
+
+	spin_lock_irq(&rh->region_lock);
+	if (success)
+		list_add(&reg->list, &reg->rh->recovered_regions);
+	else {
+		reg->state = DM_RH_NOSYNC;
+		list_add(&reg->list, &reg->rh->failed_recovered_regions);
+	}
+	spin_unlock_irq(&rh->region_lock);
+
+	rh->wakeup_workers(rh->context);
+}
+EXPORT_SYMBOL_GPL(dm_rh_recovery_end);
+
+/* Return recovery in flight count. */
+int dm_rh_recovery_in_flight(struct dm_region_hash *rh)
+{
+	return atomic_read(&rh->recovery_in_flight);
+}
+EXPORT_SYMBOL_GPL(dm_rh_recovery_in_flight);
+
+int dm_rh_flush(struct dm_region_hash *rh)
+{
+	return rh->log->type->flush(rh->log);
+}
+EXPORT_SYMBOL_GPL(dm_rh_flush);
+
+void dm_rh_delay(struct dm_region_hash *rh, struct bio *bio)
+{
+	struct dm_region *reg;
+
+	read_lock(&rh->hash_lock);
+	reg = __rh_find(rh, dm_rh_bio_to_region(rh, bio));
+	bio_list_add(&reg->delayed_bios, bio);
+	read_unlock(&rh->hash_lock);
+}
+EXPORT_SYMBOL_GPL(dm_rh_delay);
+
+void dm_rh_stop_recovery(struct dm_region_hash *rh)
+{
+	int i;
+
+	/* wait for any recovering regions */
+	for (i = 0; i < rh->max_recovery; i++)
+		down(&rh->recovery_count);
+}
+EXPORT_SYMBOL_GPL(dm_rh_stop_recovery);
+
+void dm_rh_start_recovery(struct dm_region_hash *rh)
+{
+	int i;
+
+	for (i = 0; i < rh->max_recovery; i++)
+		up(&rh->recovery_count);
+
+	rh->wakeup_workers(rh->context);
+}
+EXPORT_SYMBOL_GPL(dm_rh_start_recovery);
+
+MODULE_DESCRIPTION(DM_NAME " region hash");
+MODULE_AUTHOR("Joe Thornber/Heinz Mauelshagen <dm-devel@redhat.com>");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/dm-region-hash.h b/include/linux/dm-region-hash.h
new file mode 100644
index 000000000000..a9e652a41373
--- /dev/null
+++ b/include/linux/dm-region-hash.h
@@ -0,0 +1,104 @@
+/*
+ * Copyright (C) 2003 Sistina Software Limited.
+ * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
+ *
+ * Device-Mapper dirty region hash interface.
+ *
+ * This file is released under the GPL.
+ */
+
+#ifndef DM_REGION_HASH_H
+#define DM_REGION_HASH_H
+
+#include <linux/dm-dirty-log.h>
+
+/*-----------------------------------------------------------------
+ * Region hash
+ *----------------------------------------------------------------*/
+struct dm_region_hash;
+struct dm_region;
+
+/*
+ * States a region can have.
+ */
+enum dm_rh_region_states {
+	DM_RH_CLEAN	 = 0x01,	/* No writes in flight. */
+	DM_RH_DIRTY	 = 0x02,	/* Writes in flight. */
+	DM_RH_NOSYNC	 = 0x04,	/* Out of sync. */
+	DM_RH_RECOVERING = 0x08,	/* Under resynchronization. */
+};
+
+/*
+ * Region hash create/destroy.
+ */
+struct bio_list;
+struct dm_region_hash *dm_region_hash_create(
+		void *context, void (*dispatch_bios)(void *context,
+						     struct bio_list *bios),
+		void (*wakeup_workers)(void *context),
+		void (*wakeup_all_recovery_waiters)(void *context),
+		sector_t target_begin, unsigned max_recovery,
+		struct dm_dirty_log *log, uint32_t region_size,
+		region_t nr_regions);
+void dm_region_hash_destroy(struct dm_region_hash *rh);
+
+struct dm_dirty_log *dm_rh_dirty_log(struct dm_region_hash *rh);
+
+/*
+ * Conversion functions.
+ */
+region_t dm_rh_bio_to_region(struct dm_region_hash *rh, struct bio *bio);
+sector_t dm_rh_region_to_sector(struct dm_region_hash *rh, region_t region);
+void *dm_rh_region_context(struct dm_region *reg);
+
+/*
+ * Get region size and key (ie. number of the region).
+ */
+sector_t dm_rh_get_region_size(struct dm_region_hash *rh);
+region_t dm_rh_get_region_key(struct dm_region *reg);
+
+/*
+ * Get/set/update region state (and dirty log).
+ *
+ */
+int dm_rh_get_state(struct dm_region_hash *rh, region_t region, int may_block);
+void dm_rh_set_state(struct dm_region_hash *rh, region_t region,
+		     enum dm_rh_region_states state, int may_block);
+
+/* Non-zero errors_handled leaves the state of the region NOSYNC */
+void dm_rh_update_states(struct dm_region_hash *rh, int errors_handled);
+
+/* Flush the region hash and dirty log. */
+int dm_rh_flush(struct dm_region_hash *rh);
+
+/* Inc/dec pending count on regions. */
+void dm_rh_inc_pending(struct dm_region_hash *rh, struct bio_list *bios);
+void dm_rh_dec(struct dm_region_hash *rh, region_t region);
+
+/* Delay bios on regions. */
+void dm_rh_delay(struct dm_region_hash *rh, struct bio *bio);
+
+void dm_rh_mark_nosync(struct dm_region_hash *rh,
+		       struct bio *bio, unsigned done, int error);
+
+/*
+ * Region recovery control.
+ */
+
+/* Prepare some regions for recovery by starting to quiesce them. */
+void dm_rh_recovery_prepare(struct dm_region_hash *rh);
+
+/* Try fetching a quiesced region for recovery. */
+struct dm_region *dm_rh_recovery_start(struct dm_region_hash *rh);
+
+/* Report recovery end on a region. */
+void dm_rh_recovery_end(struct dm_region *reg, int error);
+
+/* Returns number of regions with recovery work outstanding. */
+int dm_rh_recovery_in_flight(struct dm_region_hash *rh);
+
+/* Start/stop recovery. */
+void dm_rh_start_recovery(struct dm_region_hash *rh);
+void dm_rh_stop_recovery(struct dm_region_hash *rh);
+
+#endif /* DM_REGION_HASH_H */
-- 
cgit v1.2.3


From 5e458cc0f4770eea45d3c07110f01b3a94c72aa5 Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Wed, 22 Oct 2008 10:00:13 -0500
Subject: module: simplify load_module.

Linus' recent catch of stack overflow in load_module lead me to look
at the code.  A couple of helpers to get a section address and get
objects from a section can help clean things up a little.

(And in case you're wondering, the stack size also dropped from 328 to
284 bytes).

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/module.h |   2 +-
 kernel/module.c        | 235 +++++++++++++++++++++----------------------------
 2 files changed, 100 insertions(+), 137 deletions(-)

(limited to 'include')

diff --git a/include/linux/module.h b/include/linux/module.h
index 5d2970cdce93..eddf27db442b 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -277,7 +277,7 @@ struct module
 
 	/* Exception table */
 	unsigned int num_exentries;
-	const struct exception_table_entry *extable;
+	struct exception_table_entry *extable;
 
 	/* Startup function. */
 	int (*init)(void);
diff --git a/kernel/module.c b/kernel/module.c
index 0d8d21ee792c..3d256681ab64 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -132,6 +132,29 @@ static unsigned int find_sec(Elf_Ehdr *hdr,
 	return 0;
 }
 
+/* Find a module section, or NULL. */
+static void *section_addr(Elf_Ehdr *hdr, Elf_Shdr *shdrs,
+			  const char *secstrings, const char *name)
+{
+	/* Section 0 has sh_addr 0. */
+	return (void *)shdrs[find_sec(hdr, shdrs, secstrings, name)].sh_addr;
+}
+
+/* Find a module section, or NULL.  Fill in number of "objects" in section. */
+static void *section_objs(Elf_Ehdr *hdr,
+			  Elf_Shdr *sechdrs,
+			  const char *secstrings,
+			  const char *name,
+			  size_t object_size,
+			  unsigned int *num)
+{
+	unsigned int sec = find_sec(hdr, sechdrs, secstrings, name);
+
+	/* Section 0 has sh_addr 0 and sh_size 0. */
+	*num = sechdrs[sec].sh_size / object_size;
+	return (void *)sechdrs[sec].sh_addr;
+}
+
 /* Provided by the linker */
 extern const struct kernel_symbol __start___ksymtab[];
 extern const struct kernel_symbol __stop___ksymtab[];
@@ -1789,32 +1812,20 @@ static inline void add_kallsyms(struct module *mod,
 }
 #endif /* CONFIG_KALLSYMS */
 
-#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG
-static void dynamic_printk_setup(Elf_Shdr *sechdrs, unsigned int verboseindex)
+static void dynamic_printk_setup(struct mod_debug *debug, unsigned int num)
 {
-	struct mod_debug *debug_info;
-	unsigned long pos, end;
-	unsigned int num_verbose;
-
-	pos = sechdrs[verboseindex].sh_addr;
-	num_verbose = sechdrs[verboseindex].sh_size /
-				sizeof(struct mod_debug);
-	end = pos + (num_verbose * sizeof(struct mod_debug));
+#ifdef CONFIG_DYNAMIC_PRINTK_DEBUG
+	unsigned int i;
 
-	for (; pos < end; pos += sizeof(struct mod_debug)) {
-		debug_info = (struct mod_debug *)pos;
-		register_dynamic_debug_module(debug_info->modname,
-			debug_info->type, debug_info->logical_modname,
-			debug_info->flag_names, debug_info->hash,
-			debug_info->hash2);
+	for (i = 0; i < num; i++) {
+		register_dynamic_debug_module(debug[i].modname,
+					      debug[i].type,
+					      debug[i].logical_modname,
+					      debug[i].flag_names,
+					      debug[i].hash, debug[i].hash2);
 	}
-}
-#else
-static inline void dynamic_printk_setup(Elf_Shdr *sechdrs,
-					unsigned int verboseindex)
-{
-}
 #endif /* CONFIG_DYNAMIC_PRINTK_DEBUG */
+}
 
 static void *module_alloc_update_bounds(unsigned long size)
 {
@@ -1843,37 +1854,14 @@ static noinline struct module *load_module(void __user *umod,
 	unsigned int i;
 	unsigned int symindex = 0;
 	unsigned int strindex = 0;
-	unsigned int setupindex;
-	unsigned int exindex;
-	unsigned int exportindex;
-	unsigned int modindex;
-	unsigned int obsparmindex;
-	unsigned int infoindex;
-	unsigned int gplindex;
-	unsigned int crcindex;
-	unsigned int gplcrcindex;
-	unsigned int versindex;
-	unsigned int pcpuindex;
-	unsigned int gplfutureindex;
-	unsigned int gplfuturecrcindex;
+	unsigned int modindex, versindex, infoindex, pcpuindex;
 	unsigned int unwindex = 0;
-#ifdef CONFIG_UNUSED_SYMBOLS
-	unsigned int unusedindex;
-	unsigned int unusedcrcindex;
-	unsigned int unusedgplindex;
-	unsigned int unusedgplcrcindex;
-#endif
-	unsigned int markersindex;
-	unsigned int markersstringsindex;
-	unsigned int verboseindex;
-	unsigned int tracepointsindex;
-	unsigned int tracepointsstringsindex;
-	unsigned int mcountindex;
+	unsigned int num_kp, num_mcount;
+	struct kernel_param *kp;
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
-	void *mseg;
-	struct exception_table_entry *extable;
+	unsigned long *mseg;
 	mm_segment_t old_fs;
 
 	DEBUGP("load_module: umod=%p, len=%lu, uargs=%p\n",
@@ -1937,6 +1925,7 @@ static noinline struct module *load_module(void __user *umod,
 		err = -ENOEXEC;
 		goto free_hdr;
 	}
+	/* This is temporary: point mod into copy of data. */
 	mod = (void *)sechdrs[modindex].sh_addr;
 
 	if (symindex == 0) {
@@ -1946,22 +1935,6 @@ static noinline struct module *load_module(void __user *umod,
 		goto free_hdr;
 	}
 
-	/* Optional sections */
-	exportindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab");
-	gplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl");
-	gplfutureindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_gpl_future");
-	crcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab");
-	gplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl");
-	gplfuturecrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_gpl_future");
-#ifdef CONFIG_UNUSED_SYMBOLS
-	unusedindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused");
-	unusedgplindex = find_sec(hdr, sechdrs, secstrings, "__ksymtab_unused_gpl");
-	unusedcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused");
-	unusedgplcrcindex = find_sec(hdr, sechdrs, secstrings, "__kcrctab_unused_gpl");
-#endif
-	setupindex = find_sec(hdr, sechdrs, secstrings, "__param");
-	exindex = find_sec(hdr, sechdrs, secstrings, "__ex_table");
-	obsparmindex = find_sec(hdr, sechdrs, secstrings, "__obsparm");
 	versindex = find_sec(hdr, sechdrs, secstrings, "__versions");
 	infoindex = find_sec(hdr, sechdrs, secstrings, ".modinfo");
 	pcpuindex = find_pcpusec(hdr, sechdrs, secstrings);
@@ -2117,42 +2090,57 @@ static noinline struct module *load_module(void __user *umod,
 	if (err < 0)
 		goto cleanup;
 
-	/* Set up EXPORTed & EXPORT_GPLed symbols (section 0 is 0 length) */
-	mod->num_syms = sechdrs[exportindex].sh_size / sizeof(*mod->syms);
-	mod->syms = (void *)sechdrs[exportindex].sh_addr;
-	if (crcindex)
-		mod->crcs = (void *)sechdrs[crcindex].sh_addr;
-	mod->num_gpl_syms = sechdrs[gplindex].sh_size / sizeof(*mod->gpl_syms);
-	mod->gpl_syms = (void *)sechdrs[gplindex].sh_addr;
-	if (gplcrcindex)
-		mod->gpl_crcs = (void *)sechdrs[gplcrcindex].sh_addr;
-	mod->num_gpl_future_syms = sechdrs[gplfutureindex].sh_size /
-					sizeof(*mod->gpl_future_syms);
-	mod->gpl_future_syms = (void *)sechdrs[gplfutureindex].sh_addr;
-	if (gplfuturecrcindex)
-		mod->gpl_future_crcs = (void *)sechdrs[gplfuturecrcindex].sh_addr;
+	/* Now we've got everything in the final locations, we can
+	 * find optional sections. */
+	kp = section_objs(hdr, sechdrs, secstrings, "__param", sizeof(*kp),
+			  &num_kp);
+	mod->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab",
+				 sizeof(*mod->syms), &mod->num_syms);
+	mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab");
+	mod->gpl_syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab_gpl",
+				     sizeof(*mod->gpl_syms),
+				     &mod->num_gpl_syms);
+	mod->gpl_crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab_gpl");
+	mod->gpl_future_syms = section_objs(hdr, sechdrs, secstrings,
+					    "__ksymtab_gpl_future",
+					    sizeof(*mod->gpl_future_syms),
+					    &mod->num_gpl_future_syms);
+	mod->gpl_future_crcs = section_addr(hdr, sechdrs, secstrings,
+					    "__kcrctab_gpl_future");
 
 #ifdef CONFIG_UNUSED_SYMBOLS
-	mod->num_unused_syms = sechdrs[unusedindex].sh_size /
-					sizeof(*mod->unused_syms);
-	mod->num_unused_gpl_syms = sechdrs[unusedgplindex].sh_size /
-					sizeof(*mod->unused_gpl_syms);
-	mod->unused_syms = (void *)sechdrs[unusedindex].sh_addr;
-	if (unusedcrcindex)
-		mod->unused_crcs = (void *)sechdrs[unusedcrcindex].sh_addr;
-	mod->unused_gpl_syms = (void *)sechdrs[unusedgplindex].sh_addr;
-	if (unusedgplcrcindex)
-		mod->unused_gpl_crcs
-			= (void *)sechdrs[unusedgplcrcindex].sh_addr;
+	mod->unused_syms = section_objs(hdr, sechdrs, secstrings,
+					"__ksymtab_unused",
+					sizeof(*mod->unused_syms),
+					&mod->num_unused_syms);
+	mod->unused_crcs = section_addr(hdr, sechdrs, secstrings,
+					"__kcrctab_unused");
+	mod->unused_gpl_syms = section_objs(hdr, sechdrs, secstrings,
+					    "__ksymtab_unused_gpl",
+					    sizeof(*mod->unused_gpl_syms),
+					    &mod->num_unused_gpl_syms);
+	mod->unused_gpl_crcs = section_addr(hdr, sechdrs, secstrings,
+					    "__kcrctab_unused_gpl");
+#endif
+
+#ifdef CONFIG_MARKERS
+	mod->markers = section_objs(hdr, sechdrs, secstrings, "__markers",
+				    sizeof(*mod->markers), &mod->num_markers);
+#endif
+#ifdef CONFIG_TRACEPOINTS
+	mod->tracepoints = section_objs(hdr, sechdrs, secstrings,
+					"__tracepoints",
+					sizeof(*mod->tracepoints),
+					&mod->num_tracepoints);
 #endif
 
 #ifdef CONFIG_MODVERSIONS
-	if ((mod->num_syms && !crcindex)
-	    || (mod->num_gpl_syms && !gplcrcindex)
-	    || (mod->num_gpl_future_syms && !gplfuturecrcindex)
+	if ((mod->num_syms && !mod->crcs)
+	    || (mod->num_gpl_syms && !mod->gpl_crcs)
+	    || (mod->num_gpl_future_syms && !mod->gpl_future_crcs)
 #ifdef CONFIG_UNUSED_SYMBOLS
-	    || (mod->num_unused_syms && !unusedcrcindex)
-	    || (mod->num_unused_gpl_syms && !unusedgplcrcindex)
+	    || (mod->num_unused_syms && !mod->unused_crcs)
+	    || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs)
 #endif
 		) {
 		printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name);
@@ -2161,16 +2149,6 @@ static noinline struct module *load_module(void __user *umod,
 			goto cleanup;
 	}
 #endif
-	markersindex = find_sec(hdr, sechdrs, secstrings, "__markers");
- 	markersstringsindex = find_sec(hdr, sechdrs, secstrings,
-					"__markers_strings");
-	verboseindex = find_sec(hdr, sechdrs, secstrings, "__verbose");
-	tracepointsindex = find_sec(hdr, sechdrs, secstrings, "__tracepoints");
-	tracepointsstringsindex = find_sec(hdr, sechdrs, secstrings,
-					"__tracepoints_strings");
-
-	mcountindex = find_sec(hdr, sechdrs, secstrings,
-			       "__mcount_loc");
 
 	/* Now do relocations. */
 	for (i = 1; i < hdr->e_shnum; i++) {
@@ -2193,28 +2171,16 @@ static noinline struct module *load_module(void __user *umod,
 		if (err < 0)
 			goto cleanup;
 	}
-#ifdef CONFIG_MARKERS
-	mod->markers = (void *)sechdrs[markersindex].sh_addr;
-	mod->num_markers =
-		sechdrs[markersindex].sh_size / sizeof(*mod->markers);
-#endif
-#ifdef CONFIG_TRACEPOINTS
-	mod->tracepoints = (void *)sechdrs[tracepointsindex].sh_addr;
-	mod->num_tracepoints =
-		sechdrs[tracepointsindex].sh_size / sizeof(*mod->tracepoints);
-#endif
-
 
         /* Find duplicate symbols */
 	err = verify_export_symbols(mod);
-
 	if (err < 0)
 		goto cleanup;
 
   	/* Set up and sort exception table */
-	mod->num_exentries = sechdrs[exindex].sh_size / sizeof(*mod->extable);
-	mod->extable = extable = (void *)sechdrs[exindex].sh_addr;
-	sort_extable(extable, extable + mod->num_exentries);
+	mod->extable = section_objs(hdr, sechdrs, secstrings, "__ex_table",
+				    sizeof(*mod->extable), &mod->num_exentries);
+	sort_extable(mod->extable, mod->extable + mod->num_exentries);
 
 	/* Finally, copy percpu area over. */
 	percpu_modcopy(mod->percpu, (void *)sechdrs[pcpuindex].sh_addr,
@@ -2223,11 +2189,17 @@ static noinline struct module *load_module(void __user *umod,
 	add_kallsyms(mod, sechdrs, symindex, strindex, secstrings);
 
 	if (!mod->taints) {
+		struct mod_debug *debug;
+		unsigned int num_debug;
+
 #ifdef CONFIG_MARKERS
 		marker_update_probe_range(mod->markers,
 			mod->markers + mod->num_markers);
 #endif
-	dynamic_printk_setup(sechdrs, verboseindex);
+		debug = section_objs(hdr, sechdrs, secstrings, "__verbose",
+				     sizeof(*debug), &num_debug);
+		dynamic_printk_setup(debug, num_debug);
+
 #ifdef CONFIG_TRACEPOINTS
 		tracepoint_update_probe_range(mod->tracepoints,
 			mod->tracepoints + mod->num_tracepoints);
@@ -2235,8 +2207,9 @@ static noinline struct module *load_module(void __user *umod,
 	}
 
 	/* sechdrs[0].sh_size is always zero */
-	mseg = (void *)sechdrs[mcountindex].sh_addr;
-	ftrace_init_module(mseg, mseg + sechdrs[mcountindex].sh_size);
+	mseg = section_objs(hdr, sechdrs, secstrings, "__mcount_loc",
+			    sizeof(*mseg), &num_mcount);
+	ftrace_init_module(mseg, mseg + num_mcount);
 
 	err = module_finalize(hdr, sechdrs, mod);
 	if (err < 0)
@@ -2261,7 +2234,7 @@ static noinline struct module *load_module(void __user *umod,
 	set_fs(old_fs);
 
 	mod->args = args;
-	if (obsparmindex)
+	if (section_addr(hdr, sechdrs, secstrings, "__obsparm"))
 		printk(KERN_WARNING "%s: Ignoring obsolete parameters\n",
 		       mod->name);
 
@@ -2270,21 +2243,11 @@ static noinline struct module *load_module(void __user *umod,
          * strong_try_module_get() will fail. */
 	stop_machine(__link_module, mod, NULL);
 
-	/* Size of section 0 is 0, so this works well if no params */
-	err = parse_args(mod->name, mod->args,
-			 (struct kernel_param *)
-			 sechdrs[setupindex].sh_addr,
-			 sechdrs[setupindex].sh_size
-			 / sizeof(struct kernel_param),
-			 NULL);
+	err = parse_args(mod->name, mod->args, kp, num_kp, NULL);
 	if (err < 0)
 		goto unlink;
 
-	err = mod_sysfs_setup(mod,
-			      (struct kernel_param *)
-			      sechdrs[setupindex].sh_addr,
-			      sechdrs[setupindex].sh_size
-			      / sizeof(struct kernel_param));
+	err = mod_sysfs_setup(mod, kp, num_kp);
 	if (err < 0)
 		goto unlink;
 	add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
-- 
cgit v1.2.3


From 730b69d225259565c705f5f5a11cb1aba69568f1 Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Wed, 22 Oct 2008 10:00:22 -0500
Subject: module: check kernel param length at compile time, not runtime

The kparam code tries to handle over-length parameter prefixes at
runtime.  Not only would I bet this has never been tested, it's not
clear that truncating names is a good idea either.

So let's check at compile time.  We need to move the #define to
moduleparam.h to do this, though.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/module.h      | 2 +-
 include/linux/moduleparam.h | 6 +++++-
 kernel/params.c             | 7 ++-----
 3 files changed, 8 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/module.h b/include/linux/module.h
index eddf27db442b..196b499270da 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -29,7 +29,7 @@
 #define MODULE_SYMBOL_PREFIX ""
 #endif
 
-#define MODULE_NAME_LEN (64 - sizeof(unsigned long))
+#define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN
 
 struct kernel_symbol
 {
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index ec624381c844..1eefe6d61b86 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -13,6 +13,9 @@
 #define MODULE_PARAM_PREFIX KBUILD_MODNAME "."
 #endif
 
+/* Chosen so that structs with an unsigned long line up. */
+#define MAX_PARAM_PREFIX_LEN (64 - sizeof(unsigned long))
+
 #ifdef MODULE
 #define ___module_cat(a,b) __mod_ ## a ## b
 #define __module_cat(a,b) ___module_cat(a,b)
@@ -79,7 +82,8 @@ struct kparam_array
 #define __module_param_call(prefix, name, set, get, arg, perm)		\
 	/* Default value instead of permissions? */			\
 	static int __param_perm_check_##name __attribute__((unused)) =	\
-	BUILD_BUG_ON_ZERO((perm) < 0 || (perm) > 0777 || ((perm) & 2));	\
+	BUILD_BUG_ON_ZERO((perm) < 0 || (perm) > 0777 || ((perm) & 2))	\
+	+ BUILD_BUG_ON_ZERO(sizeof(""prefix) > MAX_PARAM_PREFIX_LEN);	\
 	static const char __param_str_##name[] = prefix #name;		\
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used								\
diff --git a/kernel/params.c b/kernel/params.c
index afc46a23eb6d..aca07e1a050f 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -585,17 +585,14 @@ static void __init param_sysfs_builtin(void)
 {
 	struct kernel_param *kp, *kp_begin = NULL;
 	unsigned int i, name_len, count = 0;
-	char modname[MODULE_NAME_LEN + 1] = "";
+	char modname[MODULE_NAME_LEN] = "";
 
 	for (i=0; i < __stop___param - __start___param; i++) {
 		char *dot;
-		size_t max_name_len;
 
 		kp = &__start___param[i];
-		max_name_len =
-			min_t(size_t, MODULE_NAME_LEN, strlen(kp->name));
 
-		dot = memchr(kp->name, '.', max_name_len);
+		dot = strchr(kp->name, '.');
 		if (!dot) {
 			DEBUGP("couldn't find period in first %d characters "
 			       "of %s\n", MODULE_NAME_LEN, kp->name);
-- 
cgit v1.2.3


From 9b473de87209fa86eb421b23386693b461612f30 Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Wed, 22 Oct 2008 10:00:22 -0500
Subject: param: Fix duplicate module prefixes

Instead of insisting each new module_param sysfs entry is unique,
handle the case where it already exists (for builtin modules).

The current code assumes that all identical prefixes are together in
the section: true for normal uses, but not necessarily so if someone
overrides MODULE_PARAM_PREFIX.  More importantly, it's not true with
the new "core_param()" code which uses "kernel" as a prefix.

This simplifies the caller for the builtin case, at a slight loss of
efficiency (we do the lookup every time to see if the directory
exists).

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Greg Kroah-Hartman <gregkh@suse.de>
---
 include/linux/module.h |   2 +-
 kernel/params.c        | 261 ++++++++++++++++++++++++++-----------------------
 2 files changed, 142 insertions(+), 121 deletions(-)

(limited to 'include')

diff --git a/include/linux/module.h b/include/linux/module.h
index 196b499270da..3bfed013350b 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -60,6 +60,7 @@ struct module_kobject
 	struct kobject kobj;
 	struct module *mod;
 	struct kobject *drivers_dir;
+	struct module_param_attrs *mp;
 };
 
 /* These are either module local, or the kernel's dummy ones. */
@@ -242,7 +243,6 @@ struct module
 
 	/* Sysfs stuff. */
 	struct module_kobject mkobj;
-	struct module_param_attrs *param_attrs;
 	struct module_attribute *modinfo_attrs;
 	const char *version;
 	const char *srcversion;
diff --git a/kernel/params.c b/kernel/params.c
index aca07e1a050f..f27c992a4625 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -373,6 +373,8 @@ int param_get_string(char *buffer, struct kernel_param *kp)
 }
 
 /* sysfs output in /sys/modules/XYZ/parameters/ */
+#define to_module_attr(n) container_of(n, struct module_attribute, attr);
+#define to_module_kobject(n) container_of(n, struct module_kobject, kobj);
 
 extern struct kernel_param __start___param[], __stop___param[];
 
@@ -384,6 +386,7 @@ struct param_attribute
 
 struct module_param_attrs
 {
+	unsigned int num;
 	struct attribute_group grp;
 	struct param_attribute attrs[0];
 };
@@ -434,69 +437,84 @@ static ssize_t param_attr_store(struct module_attribute *mattr,
 
 #ifdef CONFIG_SYSFS
 /*
- * param_sysfs_setup - setup sysfs support for one module or KBUILD_MODNAME
- * @mk: struct module_kobject (contains parent kobject)
- * @kparam: array of struct kernel_param, the actual parameter definitions
- * @num_params: number of entries in array
- * @name_skip: offset where the parameter name start in kparam[].name. Needed for built-in "modules"
+ * add_sysfs_param - add a parameter to sysfs
+ * @mk: struct module_kobject
+ * @kparam: the actual parameter definition to add to sysfs
+ * @name: name of parameter
  *
- * Create a kobject for a (per-module) group of parameters, and create files
- * in sysfs. A pointer to the param_kobject is returned on success,
- * NULL if there's no parameter to export, or other ERR_PTR(err).
+ * Create a kobject if for a (per-module) parameter if mp NULL, and
+ * create file in sysfs.  Returns an error on out of memory.  Always cleans up
+ * if there's an error.
  */
-static __modinit struct module_param_attrs *
-param_sysfs_setup(struct module_kobject *mk,
-		  struct kernel_param *kparam,
-		  unsigned int num_params,
-		  unsigned int name_skip)
+static __modinit int add_sysfs_param(struct module_kobject *mk,
+				     struct kernel_param *kp,
+				     const char *name)
 {
-	struct module_param_attrs *mp;
-	unsigned int valid_attrs = 0;
-	unsigned int i, size[2];
-	struct param_attribute *pattr;
-	struct attribute **gattr;
-	int err;
-
-	for (i=0; i<num_params; i++) {
-		if (kparam[i].perm)
-			valid_attrs++;
+	struct module_param_attrs *new;
+	struct attribute **attrs;
+	int err, num;
+
+	/* We don't bother calling this with invisible parameters. */
+	BUG_ON(!kp->perm);
+
+	if (!mk->mp) {
+		num = 0;
+		attrs = NULL;
+	} else {
+		num = mk->mp->num;
+		attrs = mk->mp->grp.attrs;
 	}
 
-	if (!valid_attrs)
-		return NULL;
-
-	size[0] = ALIGN(sizeof(*mp) +
-			valid_attrs * sizeof(mp->attrs[0]),
-			sizeof(mp->grp.attrs[0]));
-	size[1] = (valid_attrs + 1) * sizeof(mp->grp.attrs[0]);
-
-	mp = kzalloc(size[0] + size[1], GFP_KERNEL);
-	if (!mp)
-		return ERR_PTR(-ENOMEM);
+	/* Enlarge. */
+	new = krealloc(mk->mp,
+		       sizeof(*mk->mp) + sizeof(mk->mp->attrs[0]) * (num+1),
+		       GFP_KERNEL);
+	if (!new) {
+		kfree(mk->mp);
+		err = -ENOMEM;
+		goto fail;
+	}
+	attrs = krealloc(attrs, sizeof(new->grp.attrs[0])*(num+2), GFP_KERNEL);
+	if (!attrs) {
+		err = -ENOMEM;
+		goto fail_free_new;
+	}
 
-	mp->grp.name = "parameters";
-	mp->grp.attrs = (void *)mp + size[0];
+	/* Sysfs wants everything zeroed. */
+	memset(new, 0, sizeof(*new));
+	memset(&new->attrs[num], 0, sizeof(new->attrs[num]));
+	memset(&attrs[num], 0, sizeof(attrs[num]));
+	new->grp.name = "parameters";
+	new->grp.attrs = attrs;
+
+	/* Tack new one on the end. */
+	new->attrs[num].param = kp;
+	new->attrs[num].mattr.show = param_attr_show;
+	new->attrs[num].mattr.store = param_attr_store;
+	new->attrs[num].mattr.attr.name = (char *)name;
+	new->attrs[num].mattr.attr.mode = kp->perm;
+	new->num = num+1;
+
+	/* Fix up all the pointers, since krealloc can move us */
+	for (num = 0; num < new->num; num++)
+		new->grp.attrs[num] = &new->attrs[num].mattr.attr;
+	new->grp.attrs[num] = NULL;
+
+	mk->mp = new;
+	return 0;
 
-	pattr = &mp->attrs[0];
-	gattr = &mp->grp.attrs[0];
-	for (i = 0; i < num_params; i++) {
-		struct kernel_param *kp = &kparam[i];
-		if (kp->perm) {
-			pattr->param = kp;
-			pattr->mattr.show = param_attr_show;
-			pattr->mattr.store = param_attr_store;
-			pattr->mattr.attr.name = (char *)&kp->name[name_skip];
-			pattr->mattr.attr.mode = kp->perm;
-			*(gattr++) = &(pattr++)->mattr.attr;
-		}
-	}
-	*gattr = NULL;
+fail_free_new:
+	kfree(new);
+fail:
+	mk->mp = NULL;
+	return err;
+}
 
-	if ((err = sysfs_create_group(&mk->kobj, &mp->grp))) {
-		kfree(mp);
-		return ERR_PTR(err);
-	}
-	return mp;
+static void free_module_param_attrs(struct module_kobject *mk)
+{
+	kfree(mk->mp->grp.attrs);
+	kfree(mk->mp);
+	mk->mp = NULL;
 }
 
 #ifdef CONFIG_MODULES
@@ -506,21 +524,33 @@ param_sysfs_setup(struct module_kobject *mk,
  * @kparam: module parameters (array)
  * @num_params: number of module parameters
  *
- * Adds sysfs entries for module parameters, and creates a link from
- * /sys/module/[mod->name]/parameters to /sys/parameters/[mod->name]/
+ * Adds sysfs entries for module parameters under
+ * /sys/module/[mod->name]/parameters/
  */
 int module_param_sysfs_setup(struct module *mod,
 			     struct kernel_param *kparam,
 			     unsigned int num_params)
 {
-	struct module_param_attrs *mp;
+	int i, err;
+	bool params = false;
+
+	for (i = 0; i < num_params; i++) {
+		if (kparam[i].perm == 0)
+			continue;
+		err = add_sysfs_param(&mod->mkobj, &kparam[i], kparam[i].name);
+		if (err)
+			return err;
+		params = true;
+	}
 
-	mp = param_sysfs_setup(&mod->mkobj, kparam, num_params, 0);
-	if (IS_ERR(mp))
-		return PTR_ERR(mp);
+	if (!params)
+		return 0;
 
-	mod->param_attrs = mp;
-	return 0;
+	/* Create the param group. */
+	err = sysfs_create_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp);
+	if (err)
+		free_module_param_attrs(&mod->mkobj);
+	return err;
 }
 
 /*
@@ -532,43 +562,55 @@ int module_param_sysfs_setup(struct module *mod,
  */
 void module_param_sysfs_remove(struct module *mod)
 {
-	if (mod->param_attrs) {
-		sysfs_remove_group(&mod->mkobj.kobj,
-				   &mod->param_attrs->grp);
+	if (mod->mkobj.mp) {
+		sysfs_remove_group(&mod->mkobj.kobj, &mod->mkobj.mp->grp);
 		/* We are positive that no one is using any param
 		 * attrs at this point.  Deallocate immediately. */
-		kfree(mod->param_attrs);
-		mod->param_attrs = NULL;
+		free_module_param_attrs(&mod->mkobj);
 	}
 }
 #endif
 
-/*
- * kernel_param_sysfs_setup - wrapper for built-in params support
- */
-static void __init kernel_param_sysfs_setup(const char *name,
-					    struct kernel_param *kparam,
-					    unsigned int num_params,
-					    unsigned int name_skip)
+static void __init kernel_add_sysfs_param(const char *name,
+					  struct kernel_param *kparam,
+					  unsigned int name_skip)
 {
 	struct module_kobject *mk;
-	int ret;
+	struct kobject *kobj;
+	int err;
 
-	mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
-	BUG_ON(!mk);
-
-	mk->mod = THIS_MODULE;
-	mk->kobj.kset = module_kset;
-	ret = kobject_init_and_add(&mk->kobj, &module_ktype, NULL, "%s", name);
-	if (ret) {
-		kobject_put(&mk->kobj);
-		printk(KERN_ERR "Module '%s' failed to be added to sysfs, "
-		      "error number %d\n", name, ret);
-		printk(KERN_ERR	"The system will be unstable now.\n");
-		return;
+	kobj = kset_find_obj(module_kset, name);
+	if (kobj) {
+		/* We already have one.  Remove params so we can add more. */
+		mk = to_module_kobject(kobj);
+		/* We need to remove it before adding parameters. */
+		sysfs_remove_group(&mk->kobj, &mk->mp->grp);
+	} else {
+		mk = kzalloc(sizeof(struct module_kobject), GFP_KERNEL);
+		BUG_ON(!mk);
+
+		mk->mod = THIS_MODULE;
+		mk->kobj.kset = module_kset;
+		err = kobject_init_and_add(&mk->kobj, &module_ktype, NULL,
+					   "%s", name);
+		if (err) {
+			kobject_put(&mk->kobj);
+			printk(KERN_ERR "Module '%s' failed add to sysfs, "
+			       "error number %d\n", name, err);
+			printk(KERN_ERR	"The system will be unstable now.\n");
+			return;
+		}
+		/* So that exit path is even. */
+		kobject_get(&mk->kobj);
 	}
-	param_sysfs_setup(mk, kparam, num_params, name_skip);
+
+	/* These should not fail at boot. */
+	err = add_sysfs_param(mk, kparam, kparam->name + name_skip);
+	BUG_ON(err);
+	err = sysfs_create_group(&mk->kobj, &mk->mp->grp);
+	BUG_ON(err);
 	kobject_uevent(&mk->kobj, KOBJ_ADD);
+	kobject_put(&mk->kobj);
 }
 
 /*
@@ -579,18 +621,19 @@ static void __init kernel_param_sysfs_setup(const char *name,
  * The "module" name (KBUILD_MODNAME) is stored before a dot, the
  * "parameter" name is stored behind a dot in kernel_param->name. So,
  * extract the "module" name for all built-in kernel_param-eters,
- * and for all who have the same, call kernel_param_sysfs_setup.
+ * and for all who have the same, call kernel_add_sysfs_param.
  */
 static void __init param_sysfs_builtin(void)
 {
-	struct kernel_param *kp, *kp_begin = NULL;
-	unsigned int i, name_len, count = 0;
-	char modname[MODULE_NAME_LEN] = "";
+	struct kernel_param *kp;
+	unsigned int name_len;
+	char modname[MODULE_NAME_LEN];
 
-	for (i=0; i < __stop___param - __start___param; i++) {
+	for (kp = __start___param; kp < __stop___param; kp++) {
 		char *dot;
 
-		kp = &__start___param[i];
+		if (kp->perm == 0)
+			continue;
 
 		dot = strchr(kp->name, '.');
 		if (!dot) {
@@ -599,37 +642,15 @@ static void __init param_sysfs_builtin(void)
 			continue;
 		}
 		name_len = dot - kp->name;
-
- 		/* new kbuild_modname? */
-		if (strlen(modname) != name_len
-		    || strncmp(modname, kp->name, name_len) != 0) {
-			/* add a new kobject for previous kernel_params. */
-			if (count)
-				kernel_param_sysfs_setup(modname,
-							 kp_begin,
-							 count,
-							 strlen(modname)+1);
-
-			strncpy(modname, kp->name, name_len);
-			modname[name_len] = '\0';
-			count = 0;
-			kp_begin = kp;
-		}
-		count++;
+		strncpy(modname, kp->name, name_len);
+		modname[name_len] = '\0';
+		kernel_add_sysfs_param(modname, kp, name_len+1);
 	}
-
-	/* last kernel_params need to be registered as well */
-	if (count)
-		kernel_param_sysfs_setup(modname, kp_begin, count,
-					 strlen(modname)+1);
 }
 
 
 /* module-related sysfs stuff */
 
-#define to_module_attr(n) container_of(n, struct module_attribute, attr);
-#define to_module_kobject(n) container_of(n, struct module_kobject, kobj);
-
 static ssize_t module_attr_show(struct kobject *kobj,
 				struct attribute *attr,
 				char *buf)
-- 
cgit v1.2.3


From 67e67ceaac5bf55dbdceb704ff2d763d438b5373 Mon Sep 17 00:00:00 2001
From: Rusty Russell <rusty@rustcorp.com.au>
Date: Wed, 22 Oct 2008 10:00:23 -0500
Subject: core_param() for genuinely core kernel parameters

There are a lot of one-liner uses of __setup() in the kernel: they're
cumbersome and not queryable (definitely not settable) via /sys.  Yet
it's ugly to simplify them to module_param(), because by default that
inserts a prefix of the module name (usually filename).

So, introduce a "core_param".  The parameter gets no prefix, but
appears in /sys/module/kernel/parameters/ (if non-zero perms arg).  I
thought about using the name "core", but that's more common than
"kernel".  And if you create a module called "kernel", you will die
a horrible death.

Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
---
 include/linux/moduleparam.h | 19 +++++++++++++++++++
 kernel/params.c             | 14 +++++++-------
 2 files changed, 26 insertions(+), 7 deletions(-)

(limited to 'include')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 1eefe6d61b86..e4af3399ef48 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -104,6 +104,25 @@ struct kparam_array
 #define module_param(name, type, perm)				\
 	module_param_named(name, name, type, perm)
 
+#ifndef MODULE
+/**
+ * core_param - define a historical core kernel parameter.
+ * @name: the name of the cmdline and sysfs parameter (often the same as var)
+ * @var: the variable
+ * @type: the type (for param_set_##type and param_get_##type)
+ * @perm: visibility in sysfs
+ *
+ * core_param is just like module_param(), but cannot be modular and
+ * doesn't add a prefix (such as "printk.").  This is for compatibility
+ * with __setup(), and it makes sense as truly core parameters aren't
+ * tied to the particular file they're in.
+ */
+#define core_param(name, var, type, perm)				\
+	param_check_##type(name, &(var));				\
+	__module_param_call("", name, param_set_##type, param_get_##type, \
+			    &var, perm)
+#endif /* !MODULE */
+
 /* Actually copy string: maxlen param is usually sizeof(string). */
 #define module_param_string(name, string, len, perm)			\
 	static const struct kparam_string __param_string_##name		\
diff --git a/kernel/params.c b/kernel/params.c
index f27c992a4625..b077f1b045d3 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -637,14 +637,14 @@ static void __init param_sysfs_builtin(void)
 
 		dot = strchr(kp->name, '.');
 		if (!dot) {
-			DEBUGP("couldn't find period in first %d characters "
-			       "of %s\n", MODULE_NAME_LEN, kp->name);
-			continue;
+			/* This happens for core_param() */
+			strcpy(modname, "kernel");
+			name_len = 0;
+		} else {
+			name_len = dot - kp->name + 1;
+			strlcpy(modname, kp->name, name_len);
 		}
-		name_len = dot - kp->name;
-		strncpy(modname, kp->name, name_len);
-		modname[name_len] = '\0';
-		kernel_add_sysfs_param(modname, kp, name_len+1);
+		kernel_add_sysfs_param(modname, kp, name_len);
 	}
 }
 
-- 
cgit v1.2.3


From 0d557dc97f4bb501f086a03d0f00b99a7855d794 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 13 Oct 2008 23:50:09 +0200
Subject: workqueue: introduce create_rt_workqueue

create_rt_workqueue will create a real time prioritized workqueue.
This is needed for the conversion of stop_machine to a workqueue based
implementation.
This patch adds yet another parameter to __create_workqueue_key to tell
it that we want an rt workqueue.
However it looks like we rather should have something like "int type"
instead of singlethread, freezable and rt.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Ingo Molnar <mingo@elte.hu>
---
 include/linux/workqueue.h | 18 ++++++++++--------
 kernel/workqueue.c        |  7 ++++++-
 2 files changed, 16 insertions(+), 9 deletions(-)

(limited to 'include')

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 5c158c477ac7..89a5a1231ffb 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -149,11 +149,11 @@ struct execute_work {
 
 extern struct workqueue_struct *
 __create_workqueue_key(const char *name, int singlethread,
-		       int freezeable, struct lock_class_key *key,
+		       int freezeable, int rt, struct lock_class_key *key,
 		       const char *lock_name);
 
 #ifdef CONFIG_LOCKDEP
-#define __create_workqueue(name, singlethread, freezeable)	\
+#define __create_workqueue(name, singlethread, freezeable, rt)	\
 ({								\
 	static struct lock_class_key __key;			\
 	const char *__lock_name;				\
@@ -164,17 +164,19 @@ __create_workqueue_key(const char *name, int singlethread,
 		__lock_name = #name;				\
 								\
 	__create_workqueue_key((name), (singlethread),		\
-			       (freezeable), &__key,		\
+			       (freezeable), (rt), &__key,	\
 			       __lock_name);			\
 })
 #else
-#define __create_workqueue(name, singlethread, freezeable)	\
-	__create_workqueue_key((name), (singlethread), (freezeable), NULL, NULL)
+#define __create_workqueue(name, singlethread, freezeable, rt)	\
+	__create_workqueue_key((name), (singlethread), (freezeable), (rt), \
+			       NULL, NULL)
 #endif
 
-#define create_workqueue(name) __create_workqueue((name), 0, 0)
-#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1)
-#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0)
+#define create_workqueue(name) __create_workqueue((name), 0, 0, 0)
+#define create_rt_workqueue(name) __create_workqueue((name), 0, 0, 1)
+#define create_freezeable_workqueue(name) __create_workqueue((name), 1, 1, 0)
+#define create_singlethread_workqueue(name) __create_workqueue((name), 1, 0, 0)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 714afad46539..f928f2a87b9b 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -62,6 +62,7 @@ struct workqueue_struct {
 	const char *name;
 	int singlethread;
 	int freezeable;		/* Freeze threads during suspend */
+	int rt;
 #ifdef CONFIG_LOCKDEP
 	struct lockdep_map lockdep_map;
 #endif
@@ -766,6 +767,7 @@ init_cpu_workqueue(struct workqueue_struct *wq, int cpu)
 
 static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 {
+	struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 };
 	struct workqueue_struct *wq = cwq->wq;
 	const char *fmt = is_single_threaded(wq) ? "%s" : "%s/%d";
 	struct task_struct *p;
@@ -781,7 +783,8 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 	 */
 	if (IS_ERR(p))
 		return PTR_ERR(p);
-
+	if (cwq->wq->rt)
+		sched_setscheduler_nocheck(p, SCHED_FIFO, &param);
 	cwq->thread = p;
 
 	return 0;
@@ -801,6 +804,7 @@ static void start_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu)
 struct workqueue_struct *__create_workqueue_key(const char *name,
 						int singlethread,
 						int freezeable,
+						int rt,
 						struct lock_class_key *key,
 						const char *lock_name)
 {
@@ -822,6 +826,7 @@ struct workqueue_struct *__create_workqueue_key(const char *name,
 	lockdep_init_map(&wq->lockdep_map, lock_name, key, 0);
 	wq->singlethread = singlethread;
 	wq->freezeable = freezeable;
+	wq->rt = rt;
 	INIT_LIST_HEAD(&wq->list);
 
 	if (singlethread) {
-- 
cgit v1.2.3


From a30d46c042c8a17ef25de02f439fbd120ab8a8de Mon Sep 17 00:00:00 2001
From: David Brownell <dbrownell@users.sourceforge.net>
Date: Mon, 20 Oct 2008 23:46:28 +0200
Subject: mfd: twl4030 IRQ handling update

- Move it into a separate file; clean and streamline it
 - Restructure the init code for reuse during secondary dispatch
 - Support both levels (primary, secondary) of IRQ dispatch
 - Use a workqueue for irq mask/unmask and trigger configuration

Code for two subchips currently share that secondary handler code.
One is the power subchip; its IRQs are now handled by this core,
courtesy of this patch.  The other is the GPIO module, which will
be supported through a later patch.

There are also minor changes to the header file, mostly related
to GPIO support; nothing yet in mainline cares about those.  A
few references to OMAP-specific symbols are disabled; when they
can all be removed, the TWL4030 support ceases being OMAP-specific.

Signed-off-by: David Brownell <dbrownell@users.sourceforge.net>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Samuel Ortiz <sameo@openedhand.com>
---
 drivers/mfd/Makefile        |   2 +-
 drivers/mfd/twl4030-core.c  | 421 +------------------------
 drivers/mfd/twl4030-irq.c   | 743 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/i2c/twl4030.h |  28 +-
 4 files changed, 777 insertions(+), 417 deletions(-)
 create mode 100644 drivers/mfd/twl4030-irq.c

(limited to 'include')

diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 68e237b830ad..0acefe8aff87 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -17,7 +17,7 @@ wm8350-objs			:= wm8350-core.o wm8350-regmap.o wm8350-gpio.o
 obj-$(CONFIG_MFD_WM8350)	+= wm8350.o
 obj-$(CONFIG_MFD_WM8350_I2C)	+= wm8350-i2c.o
 
-obj-$(CONFIG_TWL4030_CORE)	+= twl4030-core.o
+obj-$(CONFIG_TWL4030_CORE)	+= twl4030-core.o twl4030-irq.o
 
 obj-$(CONFIG_MFD_CORE)		+= mfd-core.o
 
diff --git a/drivers/mfd/twl4030-core.c b/drivers/mfd/twl4030-core.c
index fd9a0160202c..dd843c4fbcc7 100644
--- a/drivers/mfd/twl4030-core.c
+++ b/drivers/mfd/twl4030-core.c
@@ -27,15 +27,11 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
  */
 
-#include <linux/kernel_stat.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/random.h>
-#include <linux/kthread.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/err.h>
 
 #include <linux/i2c.h>
 #include <linux/i2c/twl4030.h>
@@ -93,26 +89,6 @@
 #define twl_has_usb()	false
 #endif
 
-static inline void activate_irq(int irq)
-{
-#ifdef CONFIG_ARM
-	/* ARM requires an extra step to clear IRQ_NOREQUEST, which it
-	 * sets on behalf of every irq_chip.  Also sets IRQ_NOPROBE.
-	 */
-	set_irq_flags(irq, IRQF_VALID);
-#else
-	/* same effect on other architectures */
-	set_irq_noprobe(irq);
-#endif
-}
-
-/* Primary Interrupt Handler on TWL4030 Registers */
-
-/* Register Definitions */
-
-#define REG_PIH_ISR_P1			(0x1)
-#define REG_PIH_ISR_P2			(0x2)
-#define REG_PIH_SIR			(0x3)
 
 /* Triton Core internal information (BEGIN) */
 
@@ -175,138 +151,6 @@ static inline void activate_irq(int irq)
 
 /*----------------------------------------------------------------------*/
 
-/**
- * struct twl4030_mod_iregs - TWL module IMR/ISR regs to mask/clear at init
- * @mod_no: TWL4030 module number (e.g., TWL4030_MODULE_GPIO)
- * @sih_ctrl: address of module SIH_CTRL register
- * @reg_cnt: number of IMR/ISR regs
- * @imrs: pointer to array of TWL module interrupt mask register indices
- * @isrs: pointer to array of TWL module interrupt status register indices
- *
- * Ties together TWL4030 modules and lists of IMR/ISR registers to mask/clear
- * during twl_init_irq().
- */
-struct twl4030_mod_iregs {
-	const u8 mod_no;
-	const u8 sih_ctrl;
-	const u8 reg_cnt;
-	const u8 *imrs;
-	const u8 *isrs;
-};
-
-/* TWL4030 INT module interrupt mask registers */
-static const u8 __initconst twl4030_int_imr_regs[] = {
-	TWL4030_INT_PWR_IMR1,
-	TWL4030_INT_PWR_IMR2,
-};
-
-/* TWL4030 INT module interrupt status registers */
-static const u8 __initconst twl4030_int_isr_regs[] = {
-	TWL4030_INT_PWR_ISR1,
-	TWL4030_INT_PWR_ISR2,
-};
-
-/* TWL4030 INTERRUPTS module interrupt mask registers */
-static const u8 __initconst twl4030_interrupts_imr_regs[] = {
-	TWL4030_INTERRUPTS_BCIIMR1A,
-	TWL4030_INTERRUPTS_BCIIMR1B,
-	TWL4030_INTERRUPTS_BCIIMR2A,
-	TWL4030_INTERRUPTS_BCIIMR2B,
-};
-
-/* TWL4030 INTERRUPTS module interrupt status registers */
-static const u8 __initconst twl4030_interrupts_isr_regs[] = {
-	TWL4030_INTERRUPTS_BCIISR1A,
-	TWL4030_INTERRUPTS_BCIISR1B,
-	TWL4030_INTERRUPTS_BCIISR2A,
-	TWL4030_INTERRUPTS_BCIISR2B,
-};
-
-/* TWL4030 MADC module interrupt mask registers */
-static const u8 __initconst twl4030_madc_imr_regs[] = {
-	TWL4030_MADC_IMR1,
-	TWL4030_MADC_IMR2,
-};
-
-/* TWL4030 MADC module interrupt status registers */
-static const u8 __initconst twl4030_madc_isr_regs[] = {
-	TWL4030_MADC_ISR1,
-	TWL4030_MADC_ISR2,
-};
-
-/* TWL4030 keypad module interrupt mask registers */
-static const u8 __initconst twl4030_keypad_imr_regs[] = {
-	TWL4030_KEYPAD_KEYP_IMR1,
-	TWL4030_KEYPAD_KEYP_IMR2,
-};
-
-/* TWL4030 keypad module interrupt status registers */
-static const u8 __initconst twl4030_keypad_isr_regs[] = {
-	TWL4030_KEYPAD_KEYP_ISR1,
-	TWL4030_KEYPAD_KEYP_ISR2,
-};
-
-/* TWL4030 GPIO module interrupt mask registers */
-static const u8 __initconst twl4030_gpio_imr_regs[] = {
-	REG_GPIO_IMR1A,
-	REG_GPIO_IMR1B,
-	REG_GPIO_IMR2A,
-	REG_GPIO_IMR2B,
-	REG_GPIO_IMR3A,
-	REG_GPIO_IMR3B,
-};
-
-/* TWL4030 GPIO module interrupt status registers */
-static const u8 __initconst twl4030_gpio_isr_regs[] = {
-	REG_GPIO_ISR1A,
-	REG_GPIO_ISR1B,
-	REG_GPIO_ISR2A,
-	REG_GPIO_ISR2B,
-	REG_GPIO_ISR3A,
-	REG_GPIO_ISR3B,
-};
-
-/* TWL4030 modules that have IMR/ISR registers that must be masked/cleared */
-static const struct twl4030_mod_iregs __initconst twl4030_mod_regs[] = {
-	{
-		.mod_no	  = TWL4030_MODULE_INT,
-		.sih_ctrl = TWL4030_INT_PWR_SIH_CTRL,
-		.reg_cnt  = ARRAY_SIZE(twl4030_int_imr_regs),
-		.imrs	  = twl4030_int_imr_regs,
-		.isrs	  = twl4030_int_isr_regs,
-	},
-	{
-		.mod_no	  = TWL4030_MODULE_INTERRUPTS,
-		.sih_ctrl = TWL4030_INTERRUPTS_BCISIHCTRL,
-		.reg_cnt  = ARRAY_SIZE(twl4030_interrupts_imr_regs),
-		.imrs	  = twl4030_interrupts_imr_regs,
-		.isrs	  = twl4030_interrupts_isr_regs,
-	},
-	{
-		.mod_no	  = TWL4030_MODULE_MADC,
-		.sih_ctrl = TWL4030_MADC_SIH_CTRL,
-		.reg_cnt  = ARRAY_SIZE(twl4030_madc_imr_regs),
-		.imrs	  = twl4030_madc_imr_regs,
-		.isrs	  = twl4030_madc_isr_regs,
-	},
-	{
-		.mod_no	  = TWL4030_MODULE_KEYPAD,
-		.sih_ctrl = TWL4030_KEYPAD_KEYP_SIH_CTRL,
-		.reg_cnt  = ARRAY_SIZE(twl4030_keypad_imr_regs),
-		.imrs	  = twl4030_keypad_imr_regs,
-		.isrs	  = twl4030_keypad_isr_regs,
-	},
-	{
-		.mod_no	  = TWL4030_MODULE_GPIO,
-		.sih_ctrl = REG_GPIO_SIH_CTRL,
-		.reg_cnt  = ARRAY_SIZE(twl4030_gpio_imr_regs),
-		.imrs	  = twl4030_gpio_imr_regs,
-		.isrs	  = twl4030_gpio_isr_regs,
-	},
-};
-
-/*----------------------------------------------------------------*/
-
 /* is driver active, bound to a chip? */
 static bool inuse;
 
@@ -367,33 +211,6 @@ static struct twl4030mapping twl4030_map[TWL4030_MODULE_LAST + 1] = {
 
 /*----------------------------------------------------------------------*/
 
-/*
- * TWL4030 doesn't have PIH mask, hence dummy function for mask
- * and unmask of the (eight) interrupts reported at that level ...
- * masking is only available from SIH (secondary) modules.
- */
-
-static void twl4030_i2c_ackirq(unsigned int irq)
-{
-}
-
-static void twl4030_i2c_disableint(unsigned int irq)
-{
-}
-
-static void twl4030_i2c_enableint(unsigned int irq)
-{
-}
-
-static struct irq_chip twl4030_irq_chip = {
-	.name	= "twl4030",
-	.ack	= twl4030_i2c_ackirq,
-	.mask	= twl4030_i2c_disableint,
-	.unmask	= twl4030_i2c_enableint,
-};
-
-/*----------------------------------------------------------------------*/
-
 /* Exported Functions */
 
 /**
@@ -535,108 +352,11 @@ EXPORT_SYMBOL(twl4030_i2c_read_u8);
 
 /*----------------------------------------------------------------------*/
 
-static unsigned twl4030_irq_base;
-
-static struct completion irq_event;
-
-/*
- * This thread processes interrupts reported by the Primary Interrupt Handler.
- */
-static int twl4030_irq_thread(void *data)
-{
-	long irq = (long)data;
-	irq_desc_t *desc = irq_desc + irq;
-	static unsigned i2c_errors;
-	const static unsigned max_i2c_errors = 100;
-
-	current->flags |= PF_NOFREEZE;
-
-	while (!kthread_should_stop()) {
-		int ret;
-		int module_irq;
-		u8 pih_isr;
-
-		/* Wait for IRQ, then read PIH irq status (also blocking) */
-		wait_for_completion_interruptible(&irq_event);
-
-		ret = twl4030_i2c_read_u8(TWL4030_MODULE_PIH, &pih_isr,
-					  REG_PIH_ISR_P1);
-		if (ret) {
-			pr_warning("%s: I2C error %d reading PIH ISR\n",
-					DRIVER_NAME, ret);
-			if (++i2c_errors >= max_i2c_errors) {
-				printk(KERN_ERR "Maximum I2C error count"
-						" exceeded.  Terminating %s.\n",
-						__func__);
-				break;
-			}
-			complete(&irq_event);
-			continue;
-		}
-
-		/* these handlers deal with the relevant SIH irq status */
-		local_irq_disable();
-		for (module_irq = twl4030_irq_base;
-				pih_isr;
-				pih_isr >>= 1, module_irq++) {
-			if (pih_isr & 0x1) {
-				irq_desc_t *d = irq_desc + module_irq;
-
-				d->handle_irq(module_irq, d);
-			}
-		}
-		local_irq_enable();
-
-		desc->chip->unmask(irq);
-	}
-
-	return 0;
-}
-
 /*
- * do_twl4030_irq() is the desc->handle method for the twl4030 interrupt.
- * This is a chained interrupt, so there is no desc->action method for it.
- * Now we need to query the interrupt controller in the twl4030 to determine
- * which module is generating the interrupt request.  However, we can't do i2c
- * transactions in interrupt context, so we must defer that work to a kernel
- * thread.  All we do here is acknowledge and mask the interrupt and wakeup
- * the kernel thread.
+ * NOTE:  We know the first 8 IRQs after pdata->base_irq are
+ * for the PIH, and the next are for the PWR_INT SIH, since
+ * that's how twl_init_irq() sets things up.
  */
-static void do_twl4030_irq(unsigned int irq, irq_desc_t *desc)
-{
-	const unsigned int cpu = smp_processor_id();
-
-	/*
-	 * Earlier this was desc->triggered = 1;
-	 */
-	desc->status |= IRQ_LEVEL;
-
-	/*
-	 * Acknowledge, clear _AND_ disable the interrupt.
-	 */
-	desc->chip->ack(irq);
-
-	if (!desc->depth) {
-		kstat_cpu(cpu).irqs[irq]++;
-
-		complete(&irq_event);
-	}
-}
-
-static struct task_struct * __init start_twl4030_irq_thread(long irq)
-{
-	struct task_struct *thread;
-
-	init_completion(&irq_event);
-	thread = kthread_run(twl4030_irq_thread, (void *)irq, "twl4030-irq");
-	if (!thread)
-		pr_err("%s: could not create twl4030 irq %ld thread!\n",
-		       DRIVER_NAME, irq);
-
-	return thread;
-}
-
-/*----------------------------------------------------------------------*/
 
 static int add_children(struct twl4030_platform_data *pdata)
 {
@@ -668,7 +388,7 @@ static int add_children(struct twl4030_platform_data *pdata)
 
 		if (status == 0) {
 			struct resource r = {
-				.start = TWL4030_PWRIRQ_CHG_PRES,
+				.start = pdata->irq_base + 8 + 1,
 				.flags = IORESOURCE_IRQ,
 			};
 
@@ -817,8 +537,7 @@ static int add_children(struct twl4030_platform_data *pdata)
 		/* RTC module IRQ */
 		if (status == 0) {
 			struct resource	r = {
-				/* REVISIT don't hard-wire this stuff */
-				.start = TWL4030_PWRIRQ_RTC,
+				.start = pdata->irq_base + 8 + 3,
 				.flags = IORESOURCE_IRQ,
 			};
 
@@ -863,7 +582,7 @@ static int add_children(struct twl4030_platform_data *pdata)
 
 		if (status == 0) {
 			struct resource r = {
-				.start = TWL4030_PWRIRQ_USB_PRES,
+				.start = pdata->irq_base + 8 + 2,
 				.flags = IORESOURCE_IRQ,
 			};
 
@@ -965,123 +684,17 @@ static void __init clocks_init(void)
 
 /*----------------------------------------------------------------------*/
 
-/**
- * twl4030_i2c_clear_isr - clear TWL4030 SIH ISR regs via read + write
- * @mod_no: TWL4030 module number
- * @reg: register index to clear
- * @cor: value of the <module>_SIH_CTRL.COR bit (1 or 0)
- *
- * Either reads (cor == 1) or writes (cor == 0) to a TWL4030 interrupt
- * status register to ensure that any prior interrupts are cleared.
- * Returns the status from the I2C read operation.
- */
-static int __init twl4030_i2c_clear_isr(u8 mod_no, u8 reg, u8 cor)
-{
-	u8 tmp;
-
-	return (cor) ? twl4030_i2c_read_u8(mod_no, &tmp, reg) :
-		twl4030_i2c_write_u8(mod_no, 0xff, reg);
-}
-
-/**
- * twl4030_read_cor_bit - are TWL module ISRs cleared by reads or writes?
- * @mod_no: TWL4030 module number
- * @reg: register index to clear
- *
- * Returns 1 if the TWL4030 SIH interrupt status registers (ISRs) for
- * the specified TWL module are cleared by reads, or 0 if cleared by
- * writes.
- */
-static int twl4030_read_cor_bit(u8 mod_no, u8 reg)
-{
-	u8 tmp = 0;
-
-	WARN_ON(twl4030_i2c_read_u8(mod_no, &tmp, reg) < 0);
-
-	tmp &= TWL4030_SIH_CTRL_COR_MASK;
-	tmp >>= __ffs(TWL4030_SIH_CTRL_COR_MASK);
-
-	return tmp;
-}
-
-/**
- * twl4030_mask_clear_intrs - mask and clear all TWL4030 interrupts
- * @t: pointer to twl4030_mod_iregs array
- * @t_sz: ARRAY_SIZE(t) (starting at 1)
- *
- * Mask all TWL4030 interrupt mask registers (IMRs) and clear all
- * interrupt status registers (ISRs).  No return value, but will WARN if
- * any I2C operations fail.
- */
-static void __init twl4030_mask_clear_intrs(const struct twl4030_mod_iregs *t,
-					    const u8 t_sz)
-{
-	int i, j;
-
-	/*
-	 * N.B. - further efficiency is possible here.  Eight I2C
-	 * operations on BCI and GPIO modules are avoidable if I2C
-	 * burst read/write transactions were implemented.  Would
-	 * probably save about 1ms of boot time and a small amount of
-	 * power.
-	 */
-	for (i = 0; i < t_sz; i++) {
-		const struct twl4030_mod_iregs tmr = t[i];
-		int cor;
-
-		/* Are ISRs cleared by reads or writes? */
-		cor = twl4030_read_cor_bit(tmr.mod_no, tmr.sih_ctrl);
-
-		for (j = 0; j < tmr.reg_cnt; j++) {
-
-			/* Mask interrupts at the TWL4030 */
-			WARN_ON(twl4030_i2c_write_u8(tmr.mod_no, 0xff,
-						     tmr.imrs[j]) < 0);
-
-			/* Clear TWL4030 ISRs */
-			WARN_ON(twl4030_i2c_clear_isr(tmr.mod_no,
-						      tmr.isrs[j], cor) < 0);
-		}
-	}
-}
-
-
-static void twl_init_irq(int irq_num, unsigned irq_base, unsigned irq_end)
-{
-	int	i;
-
-	/*
-	 * Mask and clear all TWL4030 interrupts since initially we do
-	 * not have any TWL4030 module interrupt handlers present
-	 */
-	twl4030_mask_clear_intrs(twl4030_mod_regs,
-				 ARRAY_SIZE(twl4030_mod_regs));
-
-	twl4030_irq_base = irq_base;
-
-	/* install an irq handler for each of the PIH modules */
-	for (i = irq_base; i < irq_end; i++) {
-		set_irq_chip_and_handler(i, &twl4030_irq_chip,
-				handle_simple_irq);
-		activate_irq(i);
-	}
-
-	/* install an irq handler to demultiplex the TWL4030 interrupt */
-	set_irq_data(irq_num, start_twl4030_irq_thread(irq_num));
-	set_irq_chained_handler(irq_num, do_twl4030_irq);
-}
-
-/*----------------------------------------------------------------------*/
+int twl_init_irq(int irq_num, unsigned irq_base, unsigned irq_end);
+int twl_exit_irq(void);
 
 static int twl4030_remove(struct i2c_client *client)
 {
 	unsigned i;
+	int status;
 
-	/* FIXME undo twl_init_irq() */
-	if (twl4030_irq_base) {
-		dev_err(&client->dev, "can't yet clean up IRQs?\n");
-		return -ENOSYS;
-	}
+	status = twl_exit_irq();
+	if (status < 0)
+		return status;
 
 	for (i = 0; i < TWL4030_NUM_SLAVES; i++) {
 		struct twl4030_client	*twl = &twl4030_modules[i];
@@ -1112,7 +725,7 @@ twl4030_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		return -EIO;
 	}
 
-	if (inuse || twl4030_irq_base) {
+	if (inuse) {
 		dev_dbg(&client->dev, "driver is already in use\n");
 		return -EBUSY;
 	}
@@ -1146,9 +759,9 @@ twl4030_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	if (client->irq
 			&& pdata->irq_base
 			&& pdata->irq_end > pdata->irq_base) {
-		twl_init_irq(client->irq, pdata->irq_base, pdata->irq_end);
-		dev_info(&client->dev, "IRQ %d chains IRQs %d..%d\n",
-				client->irq, pdata->irq_base, pdata->irq_end - 1);
+		status = twl_init_irq(client->irq, pdata->irq_base, pdata->irq_end);
+		if (status < 0)
+			goto fail;
 	}
 
 	status = add_children(pdata);
diff --git a/drivers/mfd/twl4030-irq.c b/drivers/mfd/twl4030-irq.c
new file mode 100644
index 000000000000..fae868a8d499
--- /dev/null
+++ b/drivers/mfd/twl4030-irq.c
@@ -0,0 +1,743 @@
+/*
+ * twl4030-irq.c - TWL4030/TPS659x0 irq support
+ *
+ * Copyright (C) 2005-2006 Texas Instruments, Inc.
+ *
+ * Modifications to defer interrupt handling to a kernel thread:
+ * Copyright (C) 2006 MontaVista Software, Inc.
+ *
+ * Based on tlv320aic23.c:
+ * Copyright (c) by Kai Svahn <kai.svahn@nokia.com>
+ *
+ * Code cleanup and modifications to IRQ handler.
+ * by syed khasim <x0khasim@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kthread.h>
+
+#include <linux/i2c/twl4030.h>
+
+
+/*
+ * TWL4030 IRQ handling has two stages in hardware, and thus in software.
+ * The Primary Interrupt Handler (PIH) stage exposes status bits saying
+ * which Secondary Interrupt Handler (SIH) stage is raising an interrupt.
+ * SIH modules are more traditional IRQ components, which support per-IRQ
+ * enable/disable and trigger controls; they do most of the work.
+ *
+ * These chips are designed to support IRQ handling from two different
+ * I2C masters.  Each has a dedicated IRQ line, and dedicated IRQ status
+ * and mask registers in the PIH and SIH modules.
+ *
+ * We set up IRQs starting at a platform-specified base, always starting
+ * with PIH and the SIH for PWR_INT and then usually adding GPIO:
+ *	base + 0  .. base + 7	PIH
+ *	base + 8  .. base + 15	SIH for PWR_INT
+ *	base + 16 .. base + 33	SIH for GPIO
+ */
+
+/* PIH register offsets */
+#define REG_PIH_ISR_P1			0x01
+#define REG_PIH_ISR_P2			0x02
+#define REG_PIH_SIR			0x03	/* for testing */
+
+
+/* Linux could (eventually) use either IRQ line */
+static int irq_line;
+
+struct sih {
+	char	name[8];
+	u8	module;			/* module id */
+	u8	control_offset;		/* for SIH_CTRL */
+	bool	set_cor;
+
+	u8	bits;			/* valid in isr/imr */
+	u8	bytes_ixr;		/* bytelen of ISR/IMR/SIR */
+
+	u8	edr_offset;
+	u8	bytes_edr;		/* bytelen of EDR */
+
+	/* SIR ignored -- set interrupt, for testing only */
+	struct irq_data {
+		u8	isr_offset;
+		u8	imr_offset;
+	} mask[2];
+	/* + 2 bytes padding */
+};
+
+#define SIH_INITIALIZER(modname, nbits) \
+	.module		= TWL4030_MODULE_ ## modname, \
+	.control_offset = TWL4030_ ## modname ## _SIH_CTRL, \
+	.bits		= nbits, \
+	.bytes_ixr	= DIV_ROUND_UP(nbits, 8), \
+	.edr_offset	= TWL4030_ ## modname ## _EDR, \
+	.bytes_edr	= DIV_ROUND_UP((2*(nbits)), 8), \
+	.mask = { { \
+		.isr_offset	= TWL4030_ ## modname ## _ISR1, \
+		.imr_offset	= TWL4030_ ## modname ## _IMR1, \
+	}, \
+	{ \
+		.isr_offset	= TWL4030_ ## modname ## _ISR2, \
+		.imr_offset	= TWL4030_ ## modname ## _IMR2, \
+	}, },
+
+/* register naming policies are inconsistent ... */
+#define TWL4030_INT_PWR_EDR		TWL4030_INT_PWR_EDR1
+#define TWL4030_MODULE_KEYPAD_KEYP	TWL4030_MODULE_KEYPAD
+#define TWL4030_MODULE_INT_PWR		TWL4030_MODULE_INT
+
+
+/* Order in this table matches order in PIH_ISR.  That is,
+ * BIT(n) in PIH_ISR is sih_modules[n].
+ */
+static const struct sih sih_modules[6] = {
+	[0] = {
+		.name		= "gpio",
+		.module		= TWL4030_MODULE_GPIO,
+		.control_offset	= REG_GPIO_SIH_CTRL,
+		.set_cor	= true,
+		.bits		= TWL4030_GPIO_MAX,
+		.bytes_ixr	= 3,
+		/* Note: *all* of these IRQs default to no-trigger */
+		.edr_offset	= REG_GPIO_EDR1,
+		.bytes_edr	= 5,
+		.mask = { {
+			.isr_offset	= REG_GPIO_ISR1A,
+			.imr_offset	= REG_GPIO_IMR1A,
+		}, {
+			.isr_offset	= REG_GPIO_ISR1B,
+			.imr_offset	= REG_GPIO_IMR1B,
+		}, },
+	},
+	[1] = {
+		.name		= "keypad",
+		.set_cor	= true,
+		SIH_INITIALIZER(KEYPAD_KEYP, 4)
+	},
+	[2] = {
+		.name		= "bci",
+		.module		= TWL4030_MODULE_INTERRUPTS,
+		.control_offset	= TWL4030_INTERRUPTS_BCISIHCTRL,
+		.bits		= 12,
+		.bytes_ixr	= 2,
+		.edr_offset	= TWL4030_INTERRUPTS_BCIEDR1,
+		/* Note: most of these IRQs default to no-trigger */
+		.bytes_edr	= 3,
+		.mask = { {
+			.isr_offset	= TWL4030_INTERRUPTS_BCIISR1A,
+			.imr_offset	= TWL4030_INTERRUPTS_BCIIMR1A,
+		}, {
+			.isr_offset	= TWL4030_INTERRUPTS_BCIISR1B,
+			.imr_offset	= TWL4030_INTERRUPTS_BCIIMR1B,
+		}, },
+	},
+	[3] = {
+		.name		= "madc",
+		SIH_INITIALIZER(MADC, 4)
+	},
+	[4] = {
+		/* USB doesn't use the same SIH organization */
+		.name		= "usb",
+	},
+	[5] = {
+		.name		= "power",
+		.set_cor	= true,
+		SIH_INITIALIZER(INT_PWR, 8)
+	},
+		/* there are no SIH modules #6 or #7 ... */
+};
+
+#undef TWL4030_MODULE_KEYPAD_KEYP
+#undef TWL4030_MODULE_INT_PWR
+#undef TWL4030_INT_PWR_EDR
+
+/*----------------------------------------------------------------------*/
+
+static unsigned twl4030_irq_base;
+
+static struct completion irq_event;
+
+/*
+ * This thread processes interrupts reported by the Primary Interrupt Handler.
+ */
+static int twl4030_irq_thread(void *data)
+{
+	long irq = (long)data;
+	irq_desc_t *desc = irq_desc + irq;
+	static unsigned i2c_errors;
+	const static unsigned max_i2c_errors = 100;
+
+	current->flags |= PF_NOFREEZE;
+
+	while (!kthread_should_stop()) {
+		int ret;
+		int module_irq;
+		u8 pih_isr;
+
+		/* Wait for IRQ, then read PIH irq status (also blocking) */
+		wait_for_completion_interruptible(&irq_event);
+
+		ret = twl4030_i2c_read_u8(TWL4030_MODULE_PIH, &pih_isr,
+					  REG_PIH_ISR_P1);
+		if (ret) {
+			pr_warning("twl4030: I2C error %d reading PIH ISR\n",
+					ret);
+			if (++i2c_errors >= max_i2c_errors) {
+				printk(KERN_ERR "Maximum I2C error count"
+						" exceeded.  Terminating %s.\n",
+						__func__);
+				break;
+			}
+			complete(&irq_event);
+			continue;
+		}
+
+		/* these handlers deal with the relevant SIH irq status */
+		local_irq_disable();
+		for (module_irq = twl4030_irq_base;
+				pih_isr;
+				pih_isr >>= 1, module_irq++) {
+			if (pih_isr & 0x1) {
+				irq_desc_t *d = irq_desc + module_irq;
+
+				/* These can't be masked ... always warn
+				 * if we get any surprises.
+				 */
+				if (d->status & IRQ_DISABLED)
+					note_interrupt(module_irq, d,
+							IRQ_NONE);
+				else
+					d->handle_irq(module_irq, d);
+			}
+		}
+		local_irq_enable();
+
+		desc->chip->unmask(irq);
+	}
+
+	return 0;
+}
+
+/*
+ * handle_twl4030_pih() is the desc->handle method for the twl4030 interrupt.
+ * This is a chained interrupt, so there is no desc->action method for it.
+ * Now we need to query the interrupt controller in the twl4030 to determine
+ * which module is generating the interrupt request.  However, we can't do i2c
+ * transactions in interrupt context, so we must defer that work to a kernel
+ * thread.  All we do here is acknowledge and mask the interrupt and wakeup
+ * the kernel thread.
+ */
+static void handle_twl4030_pih(unsigned int irq, irq_desc_t *desc)
+{
+	/* Acknowledge, clear *AND* mask the interrupt... */
+	desc->chip->ack(irq);
+	complete(&irq_event);
+}
+
+static struct task_struct *start_twl4030_irq_thread(long irq)
+{
+	struct task_struct *thread;
+
+	init_completion(&irq_event);
+	thread = kthread_run(twl4030_irq_thread, (void *)irq, "twl4030-irq");
+	if (!thread)
+		pr_err("twl4030: could not create irq %ld thread!\n", irq);
+
+	return thread;
+}
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * twl4030_init_sih_modules() ... start from a known state where no
+ * IRQs will be coming in, and where we can quickly enable them then
+ * handle them as they arrive.  Mask all IRQs: maybe init SIH_CTRL.
+ *
+ * NOTE:  we don't touch EDR registers here; they stay with hardware
+ * defaults or whatever the last value was.  Note that when both EDR
+ * bits for an IRQ are clear, that's as if its IMR bit is set...
+ */
+static int twl4030_init_sih_modules(unsigned line)
+{
+	const struct sih *sih;
+	u8 buf[4];
+	int i;
+	int status;
+
+	/* line 0 == int1_n signal; line 1 == int2_n signal */
+	if (line > 1)
+		return -EINVAL;
+
+	irq_line = line;
+
+	/* disable all interrupts on our line */
+	memset(buf, 0xff, sizeof buf);
+	sih = sih_modules;
+	for (i = 0; i < ARRAY_SIZE(sih_modules); i++, sih++) {
+
+		/* skip USB -- it's funky */
+		if (!sih->bytes_ixr)
+			continue;
+
+		status = twl4030_i2c_write(sih->module, buf,
+				sih->mask[line].imr_offset, sih->bytes_ixr);
+		if (status < 0)
+			pr_err("twl4030: err %d initializing %s %s\n",
+					status, sih->name, "IMR");
+
+		/* Maybe disable "exclusive" mode; buffer second pending irq;
+		 * set Clear-On-Read (COR) bit.
+		 *
+		 * NOTE that sometimes COR polarity is documented as being
+		 * inverted:  for MADC and BCI, COR=1 means "clear on write".
+		 * And for PWR_INT it's not documented...
+		 */
+		if (sih->set_cor) {
+			status = twl4030_i2c_write_u8(sih->module,
+					TWL4030_SIH_CTRL_COR_MASK,
+					sih->control_offset);
+			if (status < 0)
+				pr_err("twl4030: err %d initializing %s %s\n",
+						status, sih->name, "SIH_CTRL");
+		}
+	}
+
+	sih = sih_modules;
+	for (i = 0; i < ARRAY_SIZE(sih_modules); i++, sih++) {
+		u8 rxbuf[4];
+		int j;
+
+		/* skip USB */
+		if (!sih->bytes_ixr)
+			continue;
+
+		/* Clear pending interrupt status.  Either the read was
+		 * enough, or we need to write those bits.  Repeat, in
+		 * case an IRQ is pending (PENDDIS=0) ... that's not
+		 * uncommon with PWR_INT.PWRON.
+		 */
+		for (j = 0; j < 2; j++) {
+			status = twl4030_i2c_read(sih->module, rxbuf,
+				sih->mask[line].isr_offset, sih->bytes_ixr);
+			if (status < 0)
+				pr_err("twl4030: err %d initializing %s %s\n",
+					status, sih->name, "ISR");
+
+			if (!sih->set_cor)
+				status = twl4030_i2c_write(sih->module, buf,
+					sih->mask[line].isr_offset,
+					sih->bytes_ixr);
+			/* else COR=1 means read sufficed.
+			 * (for most SIH modules...)
+			 */
+		}
+	}
+
+	return 0;
+}
+
+static inline void activate_irq(int irq)
+{
+#ifdef CONFIG_ARM
+	/* ARM requires an extra step to clear IRQ_NOREQUEST, which it
+	 * sets on behalf of every irq_chip.  Also sets IRQ_NOPROBE.
+	 */
+	set_irq_flags(irq, IRQF_VALID);
+#else
+	/* same effect on other architectures */
+	set_irq_noprobe(irq);
+#endif
+}
+
+/*----------------------------------------------------------------------*/
+
+static DEFINE_SPINLOCK(sih_agent_lock);
+
+static struct workqueue_struct *wq;
+
+struct sih_agent {
+	int			irq_base;
+	const struct sih	*sih;
+
+	u32			imr;
+	bool			imr_change_pending;
+	struct work_struct	mask_work;
+
+	u32			edge_change;
+	struct work_struct	edge_work;
+};
+
+static void twl4030_sih_do_mask(struct work_struct *work)
+{
+	struct sih_agent	*agent;
+	const struct sih	*sih;
+	union {
+		u8	bytes[4];
+		u32	word;
+	}			imr;
+	int			status;
+
+	agent = container_of(work, struct sih_agent, mask_work);
+
+	/* see what work we have */
+	spin_lock_irq(&sih_agent_lock);
+	if (agent->imr_change_pending) {
+		sih = agent->sih;
+		/* byte[0] gets overwritten as we write ... */
+		imr.word = cpu_to_le32(agent->imr << 8);
+		agent->imr_change_pending = false;
+	} else
+		sih = NULL;
+	spin_unlock_irq(&sih_agent_lock);
+	if (!sih)
+		return;
+
+	/* write the whole mask ... simpler than subsetting it */
+	status = twl4030_i2c_write(sih->module, imr.bytes,
+			sih->mask[irq_line].imr_offset, sih->bytes_ixr);
+	if (status)
+		pr_err("twl4030: %s, %s --> %d\n", __func__,
+				"write", status);
+}
+
+static void twl4030_sih_do_edge(struct work_struct *work)
+{
+	struct sih_agent	*agent;
+	const struct sih	*sih;
+	u8			bytes[6];
+	u32			edge_change;
+	int			status;
+
+	agent = container_of(work, struct sih_agent, edge_work);
+
+	/* see what work we have */
+	spin_lock_irq(&sih_agent_lock);
+	edge_change = agent->edge_change;
+	agent->edge_change = 0;;
+	sih = edge_change ? agent->sih : NULL;
+	spin_unlock_irq(&sih_agent_lock);
+	if (!sih)
+		return;
+
+	/* Read, reserving first byte for write scratch.  Yes, this
+	 * could be cached for some speedup ... but be careful about
+	 * any processor on the other IRQ line, EDR registers are
+	 * shared.
+	 */
+	status = twl4030_i2c_read(sih->module, bytes + 1,
+			sih->edr_offset, sih->bytes_edr);
+	if (status) {
+		pr_err("twl4030: %s, %s --> %d\n", __func__,
+				"read", status);
+		return;
+	}
+
+	/* Modify only the bits we know must change */
+	while (edge_change) {
+		int		i = fls(edge_change) - 1;
+		struct irq_desc	*d = irq_desc + i + agent->irq_base;
+		int		byte = 1 + (i >> 2);
+		int		off = (i & 0x3) * 2;
+
+		bytes[byte] &= ~(0x03 << off);
+
+		spin_lock_irq(&d->lock);
+		if (d->status & IRQ_TYPE_EDGE_RISING)
+			bytes[byte] |= BIT(off + 1);
+		if (d->status & IRQ_TYPE_EDGE_FALLING)
+			bytes[byte] |= BIT(off + 0);
+		spin_unlock_irq(&d->lock);
+
+		edge_change &= ~BIT(i);
+	}
+
+	/* Write */
+	status = twl4030_i2c_write(sih->module, bytes,
+			sih->edr_offset, sih->bytes_edr);
+	if (status)
+		pr_err("twl4030: %s, %s --> %d\n", __func__,
+				"write", status);
+}
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * All irq_chip methods get issued from code holding irq_desc[irq].lock,
+ * which can't perform the underlying I2C operations (because they sleep).
+ * So we must hand them off to a thread (workqueue) and cope with asynch
+ * completion, potentially including some re-ordering, of these requests.
+ */
+
+static void twl4030_sih_mask(unsigned irq)
+{
+	struct sih_agent *sih = get_irq_chip_data(irq);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sih_agent_lock, flags);
+	sih->imr |= BIT(irq - sih->irq_base);
+	sih->imr_change_pending = true;
+	queue_work(wq, &sih->mask_work);
+	spin_unlock_irqrestore(&sih_agent_lock, flags);
+}
+
+static void twl4030_sih_unmask(unsigned irq)
+{
+	struct sih_agent *sih = get_irq_chip_data(irq);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sih_agent_lock, flags);
+	sih->imr &= ~BIT(irq - sih->irq_base);
+	sih->imr_change_pending = true;
+	queue_work(wq, &sih->mask_work);
+	spin_unlock_irqrestore(&sih_agent_lock, flags);
+}
+
+static int twl4030_sih_set_type(unsigned irq, unsigned trigger)
+{
+	struct sih_agent *sih = get_irq_chip_data(irq);
+	struct irq_desc *desc = irq_desc + irq;
+	unsigned long flags;
+
+	if (trigger & ~(IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
+		return -EINVAL;
+
+	spin_lock_irqsave(&sih_agent_lock, flags);
+	if ((desc->status & IRQ_TYPE_SENSE_MASK) != trigger) {
+		desc->status &= ~IRQ_TYPE_SENSE_MASK;
+		desc->status |= trigger;
+		sih->edge_change |= BIT(irq - sih->irq_base);
+		queue_work(wq, &sih->edge_work);
+	}
+	spin_unlock_irqrestore(&sih_agent_lock, flags);
+	return 0;
+}
+
+static struct irq_chip twl4030_sih_irq_chip = {
+	.name		= "twl4030",
+	.mask		= twl4030_sih_mask,
+	.unmask		= twl4030_sih_unmask,
+	.set_type	= twl4030_sih_set_type,
+};
+
+/*----------------------------------------------------------------------*/
+
+static inline int sih_read_isr(const struct sih *sih)
+{
+	int status;
+	union {
+		u8 bytes[4];
+		u32 word;
+	} isr;
+
+	/* FIXME need retry-on-error ... */
+
+	isr.word = 0;
+	status = twl4030_i2c_read(sih->module, isr.bytes,
+			sih->mask[irq_line].isr_offset, sih->bytes_ixr);
+
+	return (status < 0) ? status : le32_to_cpu(isr.word);
+}
+
+/*
+ * Generic handler for SIH interrupts ... we "know" this is called
+ * in task context, with IRQs enabled.
+ */
+static void handle_twl4030_sih(unsigned irq, struct irq_desc *desc)
+{
+	struct sih_agent *agent = get_irq_data(irq);
+	const struct sih *sih = agent->sih;
+	int isr;
+
+	/* reading ISR acks the IRQs, using clear-on-read mode */
+	local_irq_enable();
+	isr = sih_read_isr(sih);
+	local_irq_disable();
+
+	if (isr < 0) {
+		pr_err("twl4030: %s SIH, read ISR error %d\n",
+			sih->name, isr);
+		/* REVISIT:  recover; eventually mask it all, etc */
+		return;
+	}
+
+	while (isr) {
+		irq = fls(isr);
+		irq--;
+		isr &= ~BIT(irq);
+
+		if (irq < sih->bits)
+			generic_handle_irq(agent->irq_base + irq);
+		else
+			pr_err("twl4030: %s SIH, invalid ISR bit %d\n",
+				sih->name, irq);
+	}
+}
+
+static unsigned twl4030_irq_next;
+
+/* returns the first IRQ used by this SIH bank,
+ * or negative errno
+ */
+int twl4030_sih_setup(int module)
+{
+	int			sih_mod;
+	const struct sih	*sih = NULL;
+	struct sih_agent	*agent;
+	int			i, irq;
+	int			status = -EINVAL;
+	unsigned		irq_base = twl4030_irq_next;
+
+	/* only support modules with standard clear-on-read for now */
+	for (sih_mod = 0, sih = sih_modules;
+			sih_mod < ARRAY_SIZE(sih_modules);
+			sih_mod++, sih++) {
+		if (sih->module == module && sih->set_cor) {
+			if (!WARN((irq_base + sih->bits) > NR_IRQS,
+					"irq %d for %s too big\n",
+					irq_base + sih->bits,
+					sih->name))
+				status = 0;
+			break;
+		}
+	}
+	if (status < 0)
+		return status;
+
+	agent = kzalloc(sizeof *agent, GFP_KERNEL);
+	if (!agent)
+		return -ENOMEM;
+
+	status = 0;
+
+	agent->irq_base = irq_base;
+	agent->sih = sih;
+	agent->imr = ~0;
+	INIT_WORK(&agent->mask_work, twl4030_sih_do_mask);
+	INIT_WORK(&agent->edge_work, twl4030_sih_do_edge);
+
+	for (i = 0; i < sih->bits; i++) {
+		irq = irq_base + i;
+
+		set_irq_chip_and_handler(irq, &twl4030_sih_irq_chip,
+				handle_edge_irq);
+		set_irq_chip_data(irq, agent);
+		activate_irq(irq);
+	}
+
+	status = irq_base;
+	twl4030_irq_next += i;
+
+	/* replace generic PIH handler (handle_simple_irq) */
+	irq = sih_mod + twl4030_irq_base;
+	set_irq_data(irq, agent);
+	set_irq_chained_handler(irq, handle_twl4030_sih);
+
+	pr_info("twl4030: %s (irq %d) chaining IRQs %d..%d\n", sih->name,
+			irq, irq_base, twl4030_irq_next - 1);
+
+	return status;
+}
+
+/* FIXME need a call to reverse twl4030_sih_setup() ... */
+
+
+/*----------------------------------------------------------------------*/
+
+/* FIXME pass in which interrupt line we'll use ... */
+#define twl_irq_line	0
+
+int twl_init_irq(int irq_num, unsigned irq_base, unsigned irq_end)
+{
+	static struct irq_chip	twl4030_irq_chip;
+
+	int			status;
+	int			i;
+	struct task_struct	*task;
+
+	/*
+	 * Mask and clear all TWL4030 interrupts since initially we do
+	 * not have any TWL4030 module interrupt handlers present
+	 */
+	status = twl4030_init_sih_modules(twl_irq_line);
+	if (status < 0)
+		return status;
+
+	wq = create_singlethread_workqueue("twl4030-irqchip");
+	if (!wq) {
+		pr_err("twl4030: workqueue FAIL\n");
+		return -ESRCH;
+	}
+
+	twl4030_irq_base = irq_base;
+
+	/* install an irq handler for each of the SIH modules;
+	 * clone dummy irq_chip since PIH can't *do* anything
+	 */
+	twl4030_irq_chip = dummy_irq_chip;
+	twl4030_irq_chip.name = "twl4030";
+
+	twl4030_sih_irq_chip.ack = dummy_irq_chip.ack;
+
+	for (i = irq_base; i < irq_end; i++) {
+		set_irq_chip_and_handler(i, &twl4030_irq_chip,
+				handle_simple_irq);
+		activate_irq(i);
+	}
+	twl4030_irq_next = i;
+	pr_info("twl4030: %s (irq %d) chaining IRQs %d..%d\n", "PIH",
+			irq_num, irq_base, twl4030_irq_next - 1);
+
+	/* ... and the PWR_INT module ... */
+	status = twl4030_sih_setup(TWL4030_MODULE_INT);
+	if (status < 0) {
+		pr_err("twl4030: sih_setup PWR INT --> %d\n", status);
+		goto fail;
+	}
+
+	/* install an irq handler to demultiplex the TWL4030 interrupt */
+	task = start_twl4030_irq_thread(irq_num);
+	if (!task) {
+		pr_err("twl4030: irq thread FAIL\n");
+		status = -ESRCH;
+		goto fail;
+	}
+
+	set_irq_data(irq_num, task);
+	set_irq_chained_handler(irq_num, handle_twl4030_pih);
+
+	return status;
+
+fail:
+	for (i = irq_base; i < irq_end; i++)
+		set_irq_chip_and_handler(i, NULL, NULL);
+	destroy_workqueue(wq);
+	wq = NULL;
+	return status;
+}
+
+int twl_exit_irq(void)
+{
+	/* FIXME undo twl_init_irq() */
+	if (twl4030_irq_base) {
+		pr_err("twl4030: can't yet clean up IRQs?\n");
+		return -ENOSYS;
+	}
+	return 0;
+}
diff --git a/include/linux/i2c/twl4030.h b/include/linux/i2c/twl4030.h
index cdb453162a97..fb604dcd38f1 100644
--- a/include/linux/i2c/twl4030.h
+++ b/include/linux/i2c/twl4030.h
@@ -228,6 +228,12 @@ struct twl4030_gpio_platform_data {
 	int		gpio_base;
 	unsigned	irq_base, irq_end;
 
+	/* package the two LED signals as output-only GPIOs? */
+	bool		use_leds;
+
+	/* gpio-n should control VMMC(n+1) if BIT(n) in mmc_cd is set */
+	u8		mmc_cd;
+
 	/* For gpio-N, bit (1 << N) in "pullups" is set if that pullup
 	 * should be enabled.  Else, if that bit is set in "pulldowns",
 	 * that pulldown is enabled.  Don't waste power by letting any
@@ -277,6 +283,8 @@ struct twl4030_platform_data {
 
 /*----------------------------------------------------------------------*/
 
+int twl4030_sih_setup(int module);
+
 /*
  * FIXME completely stop using TWL4030_IRQ_BASE ... instead, pass the
  * IRQ data to subsidiary devices using platform device resources.
@@ -291,16 +299,16 @@ struct twl4030_platform_data {
 #define TWL4030_MODIRQ_BCI		(TWL4030_IRQ_BASE + 2)
 #define TWL4030_MODIRQ_MADC		(TWL4030_IRQ_BASE + 3)
 /* #define TWL4030_MODIRQ_USB		(TWL4030_IRQ_BASE + 4) */
-#define TWL4030_MODIRQ_PWR		(TWL4030_IRQ_BASE + 5)
+/* #define TWL4030_MODIRQ_PWR		(TWL4030_IRQ_BASE + 5) */
 
 #define TWL4030_PWRIRQ_PWRBTN		(TWL4030_PWR_IRQ_BASE + 0)
-#define TWL4030_PWRIRQ_CHG_PRES		(TWL4030_PWR_IRQ_BASE + 1)
-#define TWL4030_PWRIRQ_USB_PRES		(TWL4030_PWR_IRQ_BASE + 2)
-#define TWL4030_PWRIRQ_RTC		(TWL4030_PWR_IRQ_BASE + 3)
-#define TWL4030_PWRIRQ_HOT_DIE		(TWL4030_PWR_IRQ_BASE + 4)
-#define TWL4030_PWRIRQ_PWROK_TIMEOUT	(TWL4030_PWR_IRQ_BASE + 5)
-#define TWL4030_PWRIRQ_MBCHG		(TWL4030_PWR_IRQ_BASE + 6)
-#define TWL4030_PWRIRQ_SC_DETECT	(TWL4030_PWR_IRQ_BASE + 7)
+/* #define TWL4030_PWRIRQ_CHG_PRES		(TWL4030_PWR_IRQ_BASE + 1) */
+/* #define TWL4030_PWRIRQ_USB_PRES		(TWL4030_PWR_IRQ_BASE + 2) */
+/* #define TWL4030_PWRIRQ_RTC		(TWL4030_PWR_IRQ_BASE + 3) */
+/* #define TWL4030_PWRIRQ_HOT_DIE		(TWL4030_PWR_IRQ_BASE + 4) */
+/* #define TWL4030_PWRIRQ_PWROK_TIMEOUT	(TWL4030_PWR_IRQ_BASE + 5) */
+/* #define TWL4030_PWRIRQ_MBCHG		(TWL4030_PWR_IRQ_BASE + 6) */
+/* #define TWL4030_PWRIRQ_SC_DETECT	(TWL4030_PWR_IRQ_BASE + 7) */
 
 /* Rest are unsued currently*/
 
@@ -317,17 +325,13 @@ struct twl4030_platform_data {
 /* TWL4030 GPIO interrupt definitions */
 
 #define TWL4030_GPIO_IRQ_NO(n)		(TWL4030_GPIO_IRQ_BASE + (n))
-#define TWL4030_GPIO_IS_ENABLE		1
 
 /*
  * Exported TWL4030 GPIO APIs
  *
  * WARNING -- use standard GPIO and IRQ calls instead; these will vanish.
  */
-int twl4030_get_gpio_datain(int gpio);
-int twl4030_request_gpio(int gpio);
 int twl4030_set_gpio_debounce(int gpio, int enable);
-int twl4030_free_gpio(int gpio);
 
 #if defined(CONFIG_TWL4030_BCI_BATTERY) || \
 	defined(CONFIG_TWL4030_BCI_BATTERY_MODULE)
-- 
cgit v1.2.3


From 27471fdb32e77ecb92f09d4ac5757785b4dc33bc Mon Sep 17 00:00:00 2001
From: Andy Henroid <andrew.d.henroid@intel.com>
Date: Thu, 9 Oct 2008 11:45:22 -0700
Subject: i7300_idle driver v1.55

The Intel 7300 Memory Controller supports dynamic throttling of memory which can
be used to save power when system is idle. This driver does the memory
throttling when all CPUs are idle on such a system.

Refer to "Intel 7300 Memory Controller Hub (MCH)" datasheet
for the config space description.

Signed-off-by: Andy Henroid <andrew.d.henroid@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
---
 MAINTAINERS               |   6 +
 arch/x86/Kconfig          |   2 +
 drivers/Makefile          |   1 +
 drivers/dma/ioat_dma.c    |   3 +
 drivers/idle/Kconfig      |  16 ++
 drivers/idle/Makefile     |   2 +
 drivers/idle/i7300_idle.c | 674 ++++++++++++++++++++++++++++++++++++++++++++++
 include/asm-x86/idle.h    |   1 +
 include/linux/pci_ids.h   |   1 +
 9 files changed, 706 insertions(+)
 create mode 100644 drivers/idle/Kconfig
 create mode 100644 drivers/idle/Makefile
 create mode 100644 drivers/idle/i7300_idle.c

(limited to 'include')

diff --git a/MAINTAINERS b/MAINTAINERS
index 8dae4555f10e..43f71b0d2a2b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2078,6 +2078,12 @@ L:	linux-ide@vger.kernel.org
 L:	linux-scsi@vger.kernel.org
 S:	Orphan
 
+IDLE-I7300
+P:	Andy Henroid
+M:	andrew.d.henroid@intel.com
+L:	linux-pm@lists.linux-foundation.org
+S:	Supported
+
 IEEE 1394 SUBSYSTEM (drivers/ieee1394)
 P:	Ben Collins
 M:	ben.collins@ubuntu.com
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index ed92864d1325..19cdfe1f237a 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1536,6 +1536,8 @@ source "arch/x86/kernel/cpu/cpufreq/Kconfig"
 
 source "drivers/cpuidle/Kconfig"
 
+source "drivers/idle/Kconfig"
+
 endmenu
 
 
diff --git a/drivers/Makefile b/drivers/Makefile
index 2735bde73475..f443a8a9d46e 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -82,6 +82,7 @@ obj-$(CONFIG_EISA)		+= eisa/
 obj-y				+= lguest/
 obj-$(CONFIG_CPU_FREQ)		+= cpufreq/
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle/
+obj-y				+= idle/
 obj-$(CONFIG_MMC)		+= mmc/
 obj-$(CONFIG_MEMSTICK)		+= memstick/
 obj-$(CONFIG_NEW_LEDS)		+= leds/
diff --git a/drivers/dma/ioat_dma.c b/drivers/dma/ioat_dma.c
index bc8c6e3470ca..f8396cafa05f 100644
--- a/drivers/dma/ioat_dma.c
+++ b/drivers/dma/ioat_dma.c
@@ -171,6 +171,9 @@ static int ioat_dma_enumerate_channels(struct ioatdma_device *device)
 	xfercap_scale = readb(device->reg_base + IOAT_XFERCAP_OFFSET);
 	xfercap = (xfercap_scale == 0 ? -1 : (1UL << xfercap_scale));
 
+#if CONFIG_I7300_IDLE_IOAT_CHANNEL
+	device->common.chancnt--;
+#endif
 	for (i = 0; i < device->common.chancnt; i++) {
 		ioat_chan = kzalloc(sizeof(*ioat_chan), GFP_KERNEL);
 		if (!ioat_chan) {
diff --git a/drivers/idle/Kconfig b/drivers/idle/Kconfig
new file mode 100644
index 000000000000..f5b26dd579e4
--- /dev/null
+++ b/drivers/idle/Kconfig
@@ -0,0 +1,16 @@
+
+menu "Memory power savings"
+
+config I7300_IDLE_IOAT_CHANNEL
+	bool
+
+config I7300_IDLE
+	tristate "Intel chipset idle power saving driver"
+	select I7300_IDLE_IOAT_CHANNEL
+	depends on X86_64
+	help
+	  Enable idle power savings with certain Intel server chipsets.
+	  The chipset must have I/O AT support, such as the Intel 7300.
+	  The power savings depends on the type and quantity of DRAM devices.
+
+endmenu
diff --git a/drivers/idle/Makefile b/drivers/idle/Makefile
new file mode 100644
index 000000000000..5f68fc377e21
--- /dev/null
+++ b/drivers/idle/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_I7300_IDLE)			+= i7300_idle.o
+
diff --git a/drivers/idle/i7300_idle.c b/drivers/idle/i7300_idle.c
new file mode 100644
index 000000000000..59d1bbc3cd3c
--- /dev/null
+++ b/drivers/idle/i7300_idle.c
@@ -0,0 +1,674 @@
+/*
+ * (C) Copyright 2008 Intel Corporation
+ * Authors:
+ * Andy Henroid <andrew.d.henroid@intel.com>
+ * Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
+ */
+
+/*
+ * Save DIMM power on Intel 7300-based platforms when all CPUs/cores
+ * are idle, using the DIMM thermal throttling capability.
+ *
+ * This driver depends on the Intel integrated DMA controller (I/O AT).
+ * If the driver for I/O AT (drivers/dma/ioatdma*) is also enabled,
+ * this driver should work cooperatively.
+ */
+
+/* #define DEBUG */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/sched.h>
+#include <linux/notifier.h>
+#include <linux/cpumask.h>
+#include <linux/ktime.h>
+#include <linux/delay.h>
+#include <linux/debugfs.h>
+#include <linux/stop_machine.h>
+
+#include <asm/idle.h>
+
+#include "../dma/ioatdma_hw.h"
+#include "../dma/ioatdma_registers.h"
+
+#define I7300_IDLE_DRIVER_VERSION	"1.55"
+#define I7300_PRINT			"i7300_idle:"
+
+static int debug;
+module_param_named(debug, debug, uint, 0644);
+MODULE_PARM_DESC(debug, "Enable debug printks in this driver");
+
+#define dprintk(fmt, arg...) \
+	do { if (debug) printk(KERN_INFO I7300_PRINT fmt, ##arg); } while (0)
+
+/*
+ * Value to set THRTLOW to when initiating throttling
+ *  0 = No throttling
+ *  1 = Throttle when > 4 activations per eval window (Maximum throttling)
+ *  2 = Throttle when > 8 activations
+ *  168 = Throttle when > 168 activations (Minimum throttling)
+ */
+#define MAX_THRTLWLIMIT		168
+static uint i7300_idle_thrtlowlm = 1;
+module_param_named(thrtlwlimit, i7300_idle_thrtlowlm, uint, 0644);
+MODULE_PARM_DESC(thrtlwlimit,
+		"Value for THRTLOWLM activation field "
+		"(0 = disable throttle, 1 = Max throttle, 168 = Min throttle)");
+
+/*
+ * simple invocation and duration statistics
+ */
+static unsigned long total_starts;
+static unsigned long total_us;
+
+#ifdef DEBUG
+static unsigned long past_skip;
+#endif
+
+static struct pci_dev *fbd_dev;
+
+static spinlock_t i7300_idle_lock;
+static int i7300_idle_active;
+
+static u8 i7300_idle_thrtctl_saved;
+static u8 i7300_idle_thrtlow_saved;
+static u32 i7300_idle_mc_saved;
+
+static cpumask_t idle_cpumask;
+static ktime_t start_ktime;
+static unsigned long avg_idle_us;
+
+static struct dentry *debugfs_dir;
+
+/* Begin: I/O AT Helper routines */
+
+#define IOAT_CHANBASE(ioat_ctl, chan) (ioat_ctl + 0x80 + 0x80 * chan)
+/* Snoop control (disable snoops when coherency is not important) */
+#define IOAT_DESC_SADDR_SNP_CTL (1UL << 1)
+#define IOAT_DESC_DADDR_SNP_CTL (1UL << 2)
+
+static struct pci_dev *ioat_dev;
+static struct ioat_dma_descriptor *ioat_desc; /* I/O AT desc & data (1 page) */
+static unsigned long ioat_desc_phys;
+static u8 *ioat_iomap; /* I/O AT memory-mapped control regs (aka CB_BAR) */
+static u8 *ioat_chanbase;
+
+/* Start I/O AT memory copy */
+static int i7300_idle_ioat_start(void)
+{
+	u32 err;
+	/* Clear error (due to circular descriptor pointer) */
+	err = readl(ioat_chanbase + IOAT_CHANERR_OFFSET);
+	if (err)
+		writel(err, ioat_chanbase + IOAT_CHANERR_OFFSET);
+
+	writeb(IOAT_CHANCMD_START, ioat_chanbase + IOAT1_CHANCMD_OFFSET);
+	return 0;
+}
+
+/* Stop I/O AT memory copy */
+static void i7300_idle_ioat_stop(void)
+{
+	int i;
+	u8 sts;
+
+	for (i = 0; i < 5; i++) {
+		writeb(IOAT_CHANCMD_RESET,
+			ioat_chanbase + IOAT1_CHANCMD_OFFSET);
+
+		udelay(10);
+
+		sts = readq(ioat_chanbase + IOAT1_CHANSTS_OFFSET) &
+			IOAT_CHANSTS_DMA_TRANSFER_STATUS;
+
+		if (sts != IOAT_CHANSTS_DMA_TRANSFER_STATUS_ACTIVE)
+			break;
+
+	}
+
+	if (i == 5)
+		dprintk("failed to suspend+reset I/O AT after 5 retries\n");
+
+}
+
+/* Test I/O AT by copying 1024 byte from 2k to 1k */
+static int __init i7300_idle_ioat_selftest(u8 *ctl,
+		struct ioat_dma_descriptor *desc, unsigned long desc_phys)
+{
+	u64 chan_sts;
+
+	memset(desc, 0, 2048);
+	memset((u8 *) desc + 2048, 0xab, 1024);
+
+	desc[0].size = 1024;
+	desc[0].ctl = 0;
+	desc[0].src_addr = desc_phys + 2048;
+	desc[0].dst_addr = desc_phys + 1024;
+	desc[0].next = 0;
+
+	writeb(IOAT_CHANCMD_RESET, ioat_chanbase + IOAT1_CHANCMD_OFFSET);
+	writeb(IOAT_CHANCMD_START, ioat_chanbase + IOAT1_CHANCMD_OFFSET);
+
+	udelay(1000);
+
+	chan_sts = readq(ioat_chanbase + IOAT1_CHANSTS_OFFSET) &
+			IOAT_CHANSTS_DMA_TRANSFER_STATUS;
+
+	if (chan_sts != IOAT_CHANSTS_DMA_TRANSFER_STATUS_DONE) {
+		/* Not complete, reset the channel */
+		writeb(IOAT_CHANCMD_RESET,
+		       ioat_chanbase + IOAT1_CHANCMD_OFFSET);
+		return -1;
+	}
+
+	if (*(u32 *) ((u8 *) desc + 3068) != 0xabababab ||
+	    *(u32 *) ((u8 *) desc + 2044) != 0xabababab) {
+		dprintk("Data values src 0x%x, dest 0x%x, memset 0x%x\n",
+			*(u32 *) ((u8 *) desc + 2048),
+			*(u32 *) ((u8 *) desc + 1024),
+			*(u32 *) ((u8 *) desc + 3072));
+		return -1;
+	}
+	return 0;
+}
+
+static struct device dummy_dma_dev = {
+	.bus_id = "fallback device",
+	.coherent_dma_mask = DMA_64BIT_MASK,
+	.dma_mask = &dummy_dma_dev.coherent_dma_mask,
+};
+
+/* Setup and initialize I/O AT */
+/* This driver needs I/O AT as the throttling takes effect only when there is
+ * some memory activity. We use I/O AT to set up a dummy copy, while all CPUs
+ * go idle and memory is throttled.
+ */
+static int __init i7300_idle_ioat_init(void)
+{
+	u8 ver, chan_count, ioat_chan;
+	u16 chan_ctl;
+
+	ioat_iomap = (u8 *) ioremap_nocache(pci_resource_start(ioat_dev, 0),
+					    pci_resource_len(ioat_dev, 0));
+
+	if (!ioat_iomap) {
+		printk(KERN_ERR I7300_PRINT "failed to map I/O AT registers\n");
+		goto err_ret;
+	}
+
+	ver = readb(ioat_iomap + IOAT_VER_OFFSET);
+	if (ver != IOAT_VER_1_2) {
+		printk(KERN_ERR I7300_PRINT "unknown I/O AT version (%u.%u)\n",
+			ver >> 4, ver & 0xf);
+		goto err_unmap;
+	}
+
+	chan_count = readb(ioat_iomap + IOAT_CHANCNT_OFFSET);
+	if (!chan_count) {
+		printk(KERN_ERR I7300_PRINT "unexpected # of I/O AT channels "
+			"(%u)\n",
+			chan_count);
+		goto err_unmap;
+	}
+
+	ioat_chan = chan_count - 1;
+	ioat_chanbase = IOAT_CHANBASE(ioat_iomap, ioat_chan);
+
+	chan_ctl = readw(ioat_chanbase + IOAT_CHANCTRL_OFFSET);
+	if (chan_ctl & IOAT_CHANCTRL_CHANNEL_IN_USE) {
+		printk(KERN_ERR I7300_PRINT "channel %d in use\n", ioat_chan);
+		goto err_unmap;
+	}
+
+	writew(IOAT_CHANCTRL_CHANNEL_IN_USE,
+		ioat_chanbase + IOAT_CHANCTRL_OFFSET);
+
+	ioat_desc = (struct ioat_dma_descriptor *)dma_alloc_coherent(
+			&dummy_dma_dev, 4096,
+			(dma_addr_t *)&ioat_desc_phys, GFP_KERNEL);
+	if (!ioat_desc) {
+		printk(KERN_ERR I7300_PRINT "failed to allocate I/O AT desc\n");
+		goto err_mark_unused;
+	}
+
+	writel(ioat_desc_phys & 0xffffffffUL,
+	       ioat_chanbase + IOAT1_CHAINADDR_OFFSET_LOW);
+	writel(ioat_desc_phys >> 32,
+	       ioat_chanbase + IOAT1_CHAINADDR_OFFSET_HIGH);
+
+	if (i7300_idle_ioat_selftest(ioat_iomap, ioat_desc, ioat_desc_phys)) {
+		printk(KERN_ERR I7300_PRINT "I/O AT self-test failed\n");
+		goto err_free;
+	}
+
+	/* Setup circular I/O AT descriptor chain */
+	ioat_desc[0].ctl = IOAT_DESC_SADDR_SNP_CTL | IOAT_DESC_DADDR_SNP_CTL;
+	ioat_desc[0].src_addr = ioat_desc_phys + 2048;
+	ioat_desc[0].dst_addr = ioat_desc_phys + 3072;
+	ioat_desc[0].size = 128;
+	ioat_desc[0].next = ioat_desc_phys + sizeof(struct ioat_dma_descriptor);
+
+	ioat_desc[1].ctl = ioat_desc[0].ctl;
+	ioat_desc[1].src_addr = ioat_desc[0].src_addr;
+	ioat_desc[1].dst_addr = ioat_desc[0].dst_addr;
+	ioat_desc[1].size = ioat_desc[0].size;
+	ioat_desc[1].next = ioat_desc_phys;
+
+	return 0;
+
+err_free:
+	dma_free_coherent(&dummy_dma_dev, 4096, (void *)ioat_desc, 0);
+err_mark_unused:
+	writew(0, ioat_chanbase + IOAT_CHANCTRL_OFFSET);
+err_unmap:
+	iounmap(ioat_iomap);
+err_ret:
+	return -ENODEV;
+}
+
+/* Cleanup I/O AT */
+static void __exit i7300_idle_ioat_exit(void)
+{
+	int i;
+	u64 chan_sts;
+
+	i7300_idle_ioat_stop();
+
+	/* Wait for a while for the channel to halt before releasing */
+	for (i = 0; i < 10; i++) {
+		writeb(IOAT_CHANCMD_RESET,
+		       ioat_chanbase + IOAT1_CHANCMD_OFFSET);
+
+		chan_sts = readq(ioat_chanbase + IOAT1_CHANSTS_OFFSET) &
+			IOAT_CHANSTS_DMA_TRANSFER_STATUS;
+
+		if (chan_sts != IOAT_CHANSTS_DMA_TRANSFER_STATUS_ACTIVE) {
+			writew(0, ioat_chanbase + IOAT_CHANCTRL_OFFSET);
+			break;
+		}
+		udelay(1000);
+	}
+
+	chan_sts = readq(ioat_chanbase + IOAT1_CHANSTS_OFFSET) &
+			IOAT_CHANSTS_DMA_TRANSFER_STATUS;
+
+	/*
+	 * We tried to reset multiple times. If IO A/T channel is still active
+	 * flag an error and return without cleanup. Memory leak is better
+	 * than random corruption in that extreme error situation.
+	 */
+	if (chan_sts == IOAT_CHANSTS_DMA_TRANSFER_STATUS_ACTIVE) {
+		printk(KERN_ERR I7300_PRINT "Unable to stop IO A/T channels."
+			" Not freeing resources\n");
+		return;
+	}
+
+	dma_free_coherent(&dummy_dma_dev, 4096, (void *)ioat_desc, 0);
+	iounmap(ioat_iomap);
+}
+
+/* End: I/O AT Helper routines */
+
+#define DIMM_THRTLOW 0x64
+#define DIMM_THRTCTL 0x67
+#define DIMM_THRTCTL_THRMHUNT (1UL << 0)
+#define DIMM_MC 0x40
+#define DIMM_GTW_MODE (1UL << 17)
+#define DIMM_GBLACT 0x60
+
+/*
+ * Keep track of an exponential-decaying average of recent idle durations.
+ * The latest duration gets DURATION_WEIGHT_PCT percentage weight
+ * in this average, with the old average getting the remaining weight.
+ *
+ * High weights emphasize recent history, low weights include long history.
+ */
+#define DURATION_WEIGHT_PCT 55
+
+/*
+ * When the decaying average of recent durations or the predicted duration
+ * of the next timer interrupt is shorter than duration_threshold, the
+ * driver will decline to throttle.
+ */
+#define DURATION_THRESHOLD_US 100
+
+
+/* Store DIMM thermal throttle configuration */
+static int i7300_idle_thrt_save(void)
+{
+	u32 new_mc_val;
+	u8 gblactlm;
+
+	pci_read_config_byte(fbd_dev, DIMM_THRTCTL, &i7300_idle_thrtctl_saved);
+	pci_read_config_byte(fbd_dev, DIMM_THRTLOW, &i7300_idle_thrtlow_saved);
+	pci_read_config_dword(fbd_dev, DIMM_MC, &i7300_idle_mc_saved);
+	/*
+	 * Make sure we have Global Throttling Window Mode set to have a
+	 * "short" window. This (mostly) works around an issue where
+	 * throttling persists until the end of the global throttling window
+	 * size. On the tested system, this was resulting in a maximum of
+	 * 64 ms to exit throttling (average 32 ms). The actual numbers
+	 * depends on system frequencies. Setting the short window reduces
+	 * this by a factor of 4096.
+	 *
+	 * We will only do this only if the system is set for
+	 * unlimited-activations while in open-loop throttling (i.e., when
+	 * Global Activation Throttle Limit is zero).
+	 */
+	pci_read_config_byte(fbd_dev, DIMM_GBLACT, &gblactlm);
+	dprintk("thrtctl_saved = 0x%02x, thrtlow_saved = 0x%02x\n",
+		i7300_idle_thrtctl_saved,
+		i7300_idle_thrtlow_saved);
+	dprintk("mc_saved = 0x%08x, gblactlm = 0x%02x\n",
+		i7300_idle_mc_saved,
+		gblactlm);
+	if (gblactlm == 0) {
+		new_mc_val = i7300_idle_mc_saved | DIMM_GTW_MODE;
+		pci_write_config_dword(fbd_dev, DIMM_MC, new_mc_val);
+		return 0;
+	} else {
+		dprintk("could not set GTW_MODE = 1 (OLTT enabled)\n");
+		return -ENODEV;
+	}
+}
+
+/* Restore DIMM thermal throttle configuration */
+static void i7300_idle_thrt_restore(void)
+{
+	pci_write_config_dword(fbd_dev, DIMM_MC, i7300_idle_mc_saved);
+	pci_write_config_byte(fbd_dev, DIMM_THRTLOW, i7300_idle_thrtlow_saved);
+	pci_write_config_byte(fbd_dev, DIMM_THRTCTL, i7300_idle_thrtctl_saved);
+}
+
+/* Enable DIMM thermal throttling */
+static void i7300_idle_start(void)
+{
+	u8 new_ctl;
+	u8 limit;
+
+	new_ctl = i7300_idle_thrtctl_saved & ~DIMM_THRTCTL_THRMHUNT;
+	pci_write_config_byte(fbd_dev, DIMM_THRTCTL, new_ctl);
+
+	limit = i7300_idle_thrtlowlm;
+	if (unlikely(limit > MAX_THRTLWLIMIT))
+		limit = MAX_THRTLWLIMIT;
+
+	pci_write_config_byte(fbd_dev, DIMM_THRTLOW, limit);
+
+	new_ctl = i7300_idle_thrtctl_saved | DIMM_THRTCTL_THRMHUNT;
+	pci_write_config_byte(fbd_dev, DIMM_THRTCTL, new_ctl);
+}
+
+/* Disable DIMM thermal throttling */
+static void i7300_idle_stop(void)
+{
+	u8 new_ctl;
+	u8 got_ctl;
+
+	new_ctl = i7300_idle_thrtctl_saved & ~DIMM_THRTCTL_THRMHUNT;
+	pci_write_config_byte(fbd_dev, DIMM_THRTCTL, new_ctl);
+
+	pci_write_config_byte(fbd_dev, DIMM_THRTLOW, i7300_idle_thrtlow_saved);
+	pci_write_config_byte(fbd_dev, DIMM_THRTCTL, i7300_idle_thrtctl_saved);
+	pci_read_config_byte(fbd_dev, DIMM_THRTCTL, &got_ctl);
+	WARN_ON_ONCE(got_ctl != i7300_idle_thrtctl_saved);
+}
+
+
+/*
+ * i7300_avg_duration_check()
+ * return 0 if the decaying average of recent idle durations is
+ * more than DURATION_THRESHOLD_US
+ */
+static int i7300_avg_duration_check(void)
+{
+	if (avg_idle_us >= DURATION_THRESHOLD_US)
+		return 0;
+
+#ifdef DEBUG
+	past_skip++;
+#endif
+	return 1;
+}
+
+/* Idle notifier to look at idle CPUs */
+static int i7300_idle_notifier(struct notifier_block *nb, unsigned long val,
+				void *data)
+{
+	unsigned long flags;
+	ktime_t now_ktime;
+	static ktime_t idle_begin_time;
+	static int time_init = 1;
+
+	if (!i7300_idle_thrtlowlm)
+		return 0;
+
+	if (unlikely(time_init)) {
+		time_init = 0;
+		idle_begin_time = ktime_get();
+	}
+
+	spin_lock_irqsave(&i7300_idle_lock, flags);
+	if (val == IDLE_START) {
+
+		cpu_set(smp_processor_id(), idle_cpumask);
+
+		if (cpus_weight(idle_cpumask) != num_online_cpus())
+			goto end;
+
+		now_ktime = ktime_get();
+		idle_begin_time = now_ktime;
+
+		if (i7300_avg_duration_check())
+			goto end;
+
+		i7300_idle_active = 1;
+		total_starts++;
+		start_ktime = now_ktime;
+
+		i7300_idle_start();
+		i7300_idle_ioat_start();
+
+	} else if (val == IDLE_END) {
+		cpu_clear(smp_processor_id(), idle_cpumask);
+		if (cpus_weight(idle_cpumask) == (num_online_cpus() - 1)) {
+			/* First CPU coming out of idle */
+			u64 idle_duration_us;
+
+			now_ktime = ktime_get();
+
+			idle_duration_us = ktime_to_us(ktime_sub
+						(now_ktime, idle_begin_time));
+
+			avg_idle_us =
+				((100 - DURATION_WEIGHT_PCT) * avg_idle_us +
+				 DURATION_WEIGHT_PCT * idle_duration_us) / 100;
+
+			if (i7300_idle_active) {
+				ktime_t idle_ktime;
+
+				idle_ktime = ktime_sub(now_ktime, start_ktime);
+				total_us += ktime_to_us(idle_ktime);
+
+				i7300_idle_ioat_stop();
+				i7300_idle_stop();
+				i7300_idle_active = 0;
+			}
+		}
+	}
+end:
+	spin_unlock_irqrestore(&i7300_idle_lock, flags);
+	return 0;
+}
+
+static struct notifier_block i7300_idle_nb = {
+	.notifier_call = i7300_idle_notifier,
+};
+
+/*
+ * I/O AT controls (PCI bus 0 device 8 function 0)
+ * DIMM controls (PCI bus 0 device 16 function 1)
+ */
+#define IOAT_BUS 0
+#define IOAT_DEVFN PCI_DEVFN(8, 0)
+#define MEMCTL_BUS 0
+#define MEMCTL_DEVFN PCI_DEVFN(16, 1)
+
+struct fbd_ioat {
+	unsigned int vendor;
+	unsigned int ioat_dev;
+};
+
+/*
+ * The i5000 chip-set has the same hooks as the i7300
+ * but support is disabled by default because this driver
+ * has not been validated on that platform.
+ */
+#define SUPPORT_I5000 0
+
+static const struct fbd_ioat fbd_ioat_list[] = {
+	{PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_CNB},
+#if SUPPORT_I5000
+	{PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT},
+#endif
+	{0, 0}
+};
+
+/* table of devices that work with this driver */
+static const struct pci_device_id pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_FBD_CNB) },
+#if SUPPORT_I5000
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_5000_ERR) },
+#endif
+	{ } /* Terminating entry */
+};
+
+MODULE_DEVICE_TABLE(pci, pci_tbl);
+
+/* Check for known platforms with I/O-AT */
+static int __init i7300_idle_platform_probe(void)
+{
+	int i;
+
+	fbd_dev = pci_get_bus_and_slot(MEMCTL_BUS, MEMCTL_DEVFN);
+	if (!fbd_dev)
+		return -ENODEV;
+
+	for (i = 0; pci_tbl[i].vendor != 0; i++) {
+		if (fbd_dev->vendor == pci_tbl[i].vendor &&
+		    fbd_dev->device == pci_tbl[i].device) {
+			break;
+		}
+	}
+	if (pci_tbl[i].vendor == 0)
+		return -ENODEV;
+
+	ioat_dev = pci_get_bus_and_slot(IOAT_BUS, IOAT_DEVFN);
+	if (!ioat_dev)
+		return -ENODEV;
+
+	for (i = 0; fbd_ioat_list[i].vendor != 0; i++) {
+		if (ioat_dev->vendor == fbd_ioat_list[i].vendor &&
+		    ioat_dev->device == fbd_ioat_list[i].ioat_dev) {
+			return 0;
+		}
+	}
+	return -ENODEV;
+}
+
+int stats_open_generic(struct inode *inode, struct file *fp)
+{
+	fp->private_data = inode->i_private;
+	return 0;
+}
+
+static ssize_t stats_read_ul(struct file *fp, char __user *ubuf, size_t count,
+				loff_t *off)
+{
+	unsigned long *p = fp->private_data;
+	char buf[32];
+	int len;
+
+	len = snprintf(buf, 32, "%lu\n", *p);
+	return simple_read_from_buffer(ubuf, count, off, buf, len);
+}
+
+static const struct file_operations idle_fops = {
+	.open	= stats_open_generic,
+	.read	= stats_read_ul,
+};
+
+struct debugfs_file_info {
+	void *ptr;
+	char name[32];
+	struct dentry *file;
+} debugfs_file_list[] = {
+				{&total_starts, "total_starts", NULL},
+				{&total_us, "total_us", NULL},
+#ifdef DEBUG
+				{&past_skip, "past_skip", NULL},
+#endif
+				{NULL, "", NULL}
+			};
+
+static int __init i7300_idle_init(void)
+{
+	spin_lock_init(&i7300_idle_lock);
+	cpus_clear(idle_cpumask);
+	total_us = 0;
+
+	if (i7300_idle_platform_probe())
+		return -ENODEV;
+
+	if (i7300_idle_thrt_save())
+		return -ENODEV;
+
+	if (i7300_idle_ioat_init())
+		return -ENODEV;
+
+	debugfs_dir = debugfs_create_dir("i7300_idle", NULL);
+	if (debugfs_dir) {
+		int i = 0;
+
+		while (debugfs_file_list[i].ptr != NULL) {
+			debugfs_file_list[i].file = debugfs_create_file(
+					debugfs_file_list[i].name,
+					S_IRUSR,
+					debugfs_dir,
+					debugfs_file_list[i].ptr,
+					&idle_fops);
+			i++;
+		}
+	}
+
+	idle_notifier_register(&i7300_idle_nb);
+
+	printk(KERN_INFO "i7300_idle: loaded v%s\n", I7300_IDLE_DRIVER_VERSION);
+	return 0;
+}
+
+static void __exit i7300_idle_exit(void)
+{
+	idle_notifier_unregister(&i7300_idle_nb);
+
+	if (debugfs_dir) {
+		int i = 0;
+
+		while (debugfs_file_list[i].file != NULL) {
+			debugfs_remove(debugfs_file_list[i].file);
+			i++;
+		}
+
+		debugfs_remove(debugfs_dir);
+	}
+	i7300_idle_thrt_restore();
+	i7300_idle_ioat_exit();
+}
+
+module_init(i7300_idle_init);
+module_exit(i7300_idle_exit);
+
+MODULE_AUTHOR("Andy Henroid <andrew.d.henroid@intel.com>");
+MODULE_DESCRIPTION("Intel Chipset DIMM Idle Power Saving Driver v"
+			I7300_IDLE_DRIVER_VERSION);
+MODULE_LICENSE("GPL");
diff --git a/include/asm-x86/idle.h b/include/asm-x86/idle.h
index cbb649123612..54ce018d4b6c 100644
--- a/include/asm-x86/idle.h
+++ b/include/asm-x86/idle.h
@@ -6,6 +6,7 @@
 
 struct notifier_block;
 void idle_notifier_register(struct notifier_block *n);
+void idle_notifier_unregister(struct notifier_block *n);
 
 void enter_idle(void);
 void exit_idle(void);
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index f1624b396754..efb786d11f2a 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2422,6 +2422,7 @@
 #define PCI_DEVICE_ID_INTEL_MCH_PC1	0x359a
 #define PCI_DEVICE_ID_INTEL_E7525_MCH	0x359e
 #define PCI_DEVICE_ID_INTEL_IOAT_CNB	0x360b
+#define PCI_DEVICE_ID_INTEL_FBD_CNB	0x360c
 #define PCI_DEVICE_ID_INTEL_ICH10_0	0x3a14
 #define PCI_DEVICE_ID_INTEL_ICH10_1	0x3a16
 #define PCI_DEVICE_ID_INTEL_ICH10_2	0x3a18
-- 
cgit v1.2.3


From 319edafef64406c971035c56bd68480e5a82b581 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Mon, 20 Oct 2008 18:15:30 +0100
Subject: smc911x: Add IRQ polarity configuration

Platforms like ARM Ltd's RealView require the IRQ polarity bit to be set
for the SMC9118 chip. This patch allows the dynamic configuration via
the smc911x_platdata structure.

This patch also changes the smc91x_platdata structure name to the
correct smc911x_platdata in the smc911x_drv_probe() function.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/net/smc911x.c   | 11 ++++++++---
 include/linux/smc911x.h |  1 +
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/net/smc911x.c b/drivers/net/smc911x.c
index ec32b5d89c92..2c78229ad04b 100644
--- a/drivers/net/smc911x.c
+++ b/drivers/net/smc911x.c
@@ -180,7 +180,7 @@ static void PRINT_PKT(u_char *buf, int length)
 static void smc911x_reset(struct net_device *dev)
 {
 	struct smc911x_local *lp = netdev_priv(dev);
-	unsigned int reg, timeout=0, resets=1;
+	unsigned int reg, timeout=0, resets=1, irq_cfg;
 	unsigned long flags;
 
 	DBG(SMC_DEBUG_FUNC, "%s: --> %s\n", dev->name, __func__);
@@ -252,7 +252,12 @@ static void smc911x_reset(struct net_device *dev)
 	 * Deassert IRQ for 1*10us for edge type interrupts
 	 * and drive IRQ pin push-pull
 	 */
-	SMC_SET_IRQ_CFG(lp, (1 << 24) | INT_CFG_IRQ_EN_ | INT_CFG_IRQ_TYPE_);
+	irq_cfg = (1 << 24) | INT_CFG_IRQ_EN_ | INT_CFG_IRQ_TYPE_;
+#ifdef SMC_DYNAMIC_BUS_CONFIG
+	if (lp->cfg.irq_polarity)
+		irq_cfg |= INT_CFG_IRQ_POL_;
+#endif
+	SMC_SET_IRQ_CFG(lp, irq_cfg);
 
 	/* clear anything saved */
 	if (lp->pending_tx_skb != NULL) {
@@ -2054,7 +2059,7 @@ err_out:
  */
 static int smc911x_drv_probe(struct platform_device *pdev)
 {
-	struct smc91x_platdata *pd = pdev->dev.platform_data;
+	struct smc911x_platdata *pd = pdev->dev.platform_data;
 	struct net_device *ndev;
 	struct resource *res;
 	struct smc911x_local *lp;
diff --git a/include/linux/smc911x.h b/include/linux/smc911x.h
index b58f54c24183..521f37143fae 100644
--- a/include/linux/smc911x.h
+++ b/include/linux/smc911x.h
@@ -7,6 +7,7 @@
 struct smc911x_platdata {
 	unsigned long flags;
 	unsigned long irq_flags; /* IRQF_... */
+	int irq_polarity;
 };
 
 #endif /* __SMC911X_H__ */
-- 
cgit v1.2.3


From 93fc9e1bb6507dde945c2eab68c93e1066ac3691 Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Wed, 22 Oct 2008 10:25:29 -0700
Subject: mlx4_core: Support multiple pre-reserved QP regions

For ethernet support, we need to reserve QPs for the ethernet and
fibre channel driver.  The QPs are reserved at the end of the QP
table.  (This way we assure that they are aligned to their size)

We need to consider these reserved ranges in bitmap creation, so we
extend the mlx4 bitmap utility functions to allow reserved ranges at
both the bottom and the top of the range.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/net/mlx4/alloc.c    | 29 +++++++++++++--------
 drivers/net/mlx4/cq.c       |  2 +-
 drivers/net/mlx4/eq.c       |  2 +-
 drivers/net/mlx4/fw.c       |  5 ++++
 drivers/net/mlx4/fw.h       |  2 ++
 drivers/net/mlx4/main.c     | 62 ++++++++++++++++++++++++++++++++++++++++-----
 drivers/net/mlx4/mcg.c      |  4 +--
 drivers/net/mlx4/mlx4.h     |  4 ++-
 drivers/net/mlx4/mr.c       |  2 +-
 drivers/net/mlx4/pd.c       |  4 +--
 drivers/net/mlx4/qp.c       | 36 ++++++++++++++++++++++++--
 drivers/net/mlx4/srq.c      |  2 +-
 include/linux/mlx4/device.h | 19 +++++++++++++-
 13 files changed, 144 insertions(+), 29 deletions(-)

(limited to 'include')

diff --git a/drivers/net/mlx4/alloc.c b/drivers/net/mlx4/alloc.c
index e6c0d5bb5dcb..e2bc7ecf162d 100644
--- a/drivers/net/mlx4/alloc.c
+++ b/drivers/net/mlx4/alloc.c
@@ -47,13 +47,16 @@ u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap)
 
 	obj = find_next_zero_bit(bitmap->table, bitmap->max, bitmap->last);
 	if (obj >= bitmap->max) {
-		bitmap->top = (bitmap->top + bitmap->max) & bitmap->mask;
+		bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
+				& bitmap->mask;
 		obj = find_first_zero_bit(bitmap->table, bitmap->max);
 	}
 
 	if (obj < bitmap->max) {
 		set_bit(obj, bitmap->table);
-		bitmap->last = (obj + 1) & (bitmap->max - 1);
+		bitmap->last = (obj + 1);
+		if (bitmap->last == bitmap->max)
+			bitmap->last = 0;
 		obj |= bitmap->top;
 	} else
 		obj = -1;
@@ -109,9 +112,9 @@ u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align)
 	obj = find_aligned_range(bitmap->table, bitmap->last,
 				 bitmap->max, cnt, align);
 	if (obj >= bitmap->max) {
-		bitmap->top = (bitmap->top + bitmap->max) & bitmap->mask;
-		obj = find_aligned_range(bitmap->table, 0,
-					 bitmap->max,
+		bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
+				& bitmap->mask;
+		obj = find_aligned_range(bitmap->table, 0, bitmap->max,
 					 cnt, align);
 	}
 
@@ -136,17 +139,19 @@ void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt)
 {
 	u32 i;
 
-	obj &= bitmap->max - 1;
+	obj &= bitmap->max + bitmap->reserved_top - 1;
 
 	spin_lock(&bitmap->lock);
 	for (i = 0; i < cnt; i++)
 		clear_bit(obj + i, bitmap->table);
 	bitmap->last = min(bitmap->last, obj);
-	bitmap->top = (bitmap->top + bitmap->max) & bitmap->mask;
+	bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
+			& bitmap->mask;
 	spin_unlock(&bitmap->lock);
 }
 
-int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask, u32 reserved)
+int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
+		     u32 reserved_bot, u32 reserved_top)
 {
 	int i;
 
@@ -156,14 +161,16 @@ int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask, u32 reserved
 
 	bitmap->last = 0;
 	bitmap->top  = 0;
-	bitmap->max  = num;
+	bitmap->max  = num - reserved_top;
 	bitmap->mask = mask;
+	bitmap->reserved_top = reserved_top;
 	spin_lock_init(&bitmap->lock);
-	bitmap->table = kzalloc(BITS_TO_LONGS(num) * sizeof (long), GFP_KERNEL);
+	bitmap->table = kzalloc(BITS_TO_LONGS(bitmap->max) *
+				sizeof (long), GFP_KERNEL);
 	if (!bitmap->table)
 		return -ENOMEM;
 
-	for (i = 0; i < reserved; ++i)
+	for (i = 0; i < reserved_bot; ++i)
 		set_bit(i, bitmap->table);
 
 	return 0;
diff --git a/drivers/net/mlx4/cq.c b/drivers/net/mlx4/cq.c
index 9bb50e3f8974..b7ad2829d67e 100644
--- a/drivers/net/mlx4/cq.c
+++ b/drivers/net/mlx4/cq.c
@@ -300,7 +300,7 @@ int mlx4_init_cq_table(struct mlx4_dev *dev)
 	INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
 
 	err = mlx4_bitmap_init(&cq_table->bitmap, dev->caps.num_cqs,
-			       dev->caps.num_cqs - 1, dev->caps.reserved_cqs);
+			       dev->caps.num_cqs - 1, dev->caps.reserved_cqs, 0);
 	if (err)
 		return err;
 
diff --git a/drivers/net/mlx4/eq.c b/drivers/net/mlx4/eq.c
index 8a8b56135a58..de169338cd90 100644
--- a/drivers/net/mlx4/eq.c
+++ b/drivers/net/mlx4/eq.c
@@ -558,7 +558,7 @@ int mlx4_init_eq_table(struct mlx4_dev *dev)
 	int i;
 
 	err = mlx4_bitmap_init(&priv->eq_table.bitmap, dev->caps.num_eqs,
-			       dev->caps.num_eqs - 1, dev->caps.reserved_eqs);
+			       dev->caps.num_eqs - 1, dev->caps.reserved_eqs, 0);
 	if (err)
 		return err;
 
diff --git a/drivers/net/mlx4/fw.c b/drivers/net/mlx4/fw.c
index 7e32955da982..40d8142c23b2 100644
--- a/drivers/net/mlx4/fw.c
+++ b/drivers/net/mlx4/fw.c
@@ -357,6 +357,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_PORT_MTU_OFFSET			0x01
 #define QUERY_PORT_WIDTH_OFFSET			0x06
 #define QUERY_PORT_MAX_GID_PKEY_OFFSET		0x07
+#define QUERY_PORT_MAX_MACVLAN_OFFSET		0x0a
 #define QUERY_PORT_MAX_VL_OFFSET		0x0b
 
 		for (i = 1; i <= dev_cap->num_ports; ++i) {
@@ -374,6 +375,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 			dev_cap->max_pkeys[i]	   = 1 << (field & 0xf);
 			MLX4_GET(field, outbox, QUERY_PORT_MAX_VL_OFFSET);
 			dev_cap->max_vl[i]	   = field & 0xf;
+			MLX4_GET(field, outbox, QUERY_PORT_MAX_MACVLAN_OFFSET);
+			dev_cap->log_max_macs[i]  = field & 0xf;
+			dev_cap->log_max_vlans[i] = field >> 4;
+
 		}
 	}
 
diff --git a/drivers/net/mlx4/fw.h b/drivers/net/mlx4/fw.h
index decbb5c2ad41..c34e726d66e4 100644
--- a/drivers/net/mlx4/fw.h
+++ b/drivers/net/mlx4/fw.h
@@ -102,6 +102,8 @@ struct mlx4_dev_cap {
 	u32 reserved_lkey;
 	u64 max_icm_sz;
 	int max_gso_sz;
+	u8  log_max_macs[MLX4_MAX_PORTS + 1];
+	u8  log_max_vlans[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_adapter {
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 1252a919de2e..560e1962212e 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -85,6 +85,19 @@ static struct mlx4_profile default_profile = {
 	.num_mtt	= 1 << 20,
 };
 
+static int log_num_mac = 2;
+module_param_named(log_num_mac, log_num_mac, int, 0444);
+MODULE_PARM_DESC(log_num_mac, "Log2 max number of MACs per ETH port (1-7)");
+
+static int log_num_vlan;
+module_param_named(log_num_vlan, log_num_vlan, int, 0444);
+MODULE_PARM_DESC(log_num_vlan, "Log2 max number of VLANs per ETH port (0-7)");
+
+static int use_prio;
+module_param_named(use_prio, use_prio, bool, 0444);
+MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports "
+		  "(0/1, default 0)");
+
 static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 {
 	int err;
@@ -134,7 +147,6 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_rq_sg	     = dev_cap->max_rq_sg;
 	dev->caps.max_wqes	     = dev_cap->max_qp_sz;
 	dev->caps.max_qp_init_rdma   = dev_cap->max_requester_per_qp;
-	dev->caps.reserved_qps	     = dev_cap->reserved_qps;
 	dev->caps.max_srq_wqes	     = dev_cap->max_srq_sz;
 	dev->caps.max_srq_sge	     = dev_cap->max_rq_sg - 1;
 	dev->caps.reserved_srqs	     = dev_cap->reserved_srqs;
@@ -163,6 +175,39 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.stat_rate_support  = dev_cap->stat_rate_support;
 	dev->caps.max_gso_sz	     = dev_cap->max_gso_sz;
 
+	dev->caps.log_num_macs  = log_num_mac;
+	dev->caps.log_num_vlans = log_num_vlan;
+	dev->caps.log_num_prios = use_prio ? 3 : 0;
+
+	for (i = 1; i <= dev->caps.num_ports; ++i) {
+		if (dev->caps.log_num_macs > dev_cap->log_max_macs[i]) {
+			dev->caps.log_num_macs = dev_cap->log_max_macs[i];
+			mlx4_warn(dev, "Requested number of MACs is too much "
+				  "for port %d, reducing to %d.\n",
+				  i, 1 << dev->caps.log_num_macs);
+		}
+		if (dev->caps.log_num_vlans > dev_cap->log_max_vlans[i]) {
+			dev->caps.log_num_vlans = dev_cap->log_max_vlans[i];
+			mlx4_warn(dev, "Requested number of VLANs is too much "
+				  "for port %d, reducing to %d.\n",
+				  i, 1 << dev->caps.log_num_vlans);
+		}
+	}
+
+	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] = dev_cap->reserved_qps;
+	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] =
+		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] =
+		(1 << dev->caps.log_num_macs) *
+		(1 << dev->caps.log_num_vlans) *
+		(1 << dev->caps.log_num_prios) *
+		dev->caps.num_ports;
+	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH] = MLX4_NUM_FEXCH;
+
+	dev->caps.reserved_qps = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] +
+		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] +
+		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] +
+		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH];
+
 	return 0;
 }
 
@@ -211,7 +256,8 @@ static int mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
 				  ((u64) (MLX4_CMPT_TYPE_QP *
 					  cmpt_entry_sz) << MLX4_CMPT_SHIFT),
 				  cmpt_entry_sz, dev->caps.num_qps,
-				  dev->caps.reserved_qps, 0, 0);
+				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+				  0, 0);
 	if (err)
 		goto err;
 
@@ -336,7 +382,8 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  init_hca->qpc_base,
 				  dev_cap->qpc_entry_sz,
 				  dev->caps.num_qps,
-				  dev->caps.reserved_qps, 0, 0);
+				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+				  0, 0);
 	if (err) {
 		mlx4_err(dev, "Failed to map QP context memory, aborting.\n");
 		goto err_unmap_dmpt;
@@ -346,7 +393,8 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  init_hca->auxc_base,
 				  dev_cap->aux_entry_sz,
 				  dev->caps.num_qps,
-				  dev->caps.reserved_qps, 0, 0);
+				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+				  0, 0);
 	if (err) {
 		mlx4_err(dev, "Failed to map AUXC context memory, aborting.\n");
 		goto err_unmap_qp;
@@ -356,7 +404,8 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  init_hca->altc_base,
 				  dev_cap->altc_entry_sz,
 				  dev->caps.num_qps,
-				  dev->caps.reserved_qps, 0, 0);
+				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+				  0, 0);
 	if (err) {
 		mlx4_err(dev, "Failed to map ALTC context memory, aborting.\n");
 		goto err_unmap_auxc;
@@ -366,7 +415,8 @@ static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
 				  init_hca->rdmarc_base,
 				  dev_cap->rdmarc_entry_sz << priv->qp_table.rdmarc_shift,
 				  dev->caps.num_qps,
-				  dev->caps.reserved_qps, 0, 0);
+				  dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+				  0, 0);
 	if (err) {
 		mlx4_err(dev, "Failed to map RDMARC context memory, aborting\n");
 		goto err_unmap_altc;
diff --git a/drivers/net/mlx4/mcg.c b/drivers/net/mlx4/mcg.c
index c83f88ce0736..592c01ae2c5d 100644
--- a/drivers/net/mlx4/mcg.c
+++ b/drivers/net/mlx4/mcg.c
@@ -368,8 +368,8 @@ int mlx4_init_mcg_table(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int err;
 
-	err = mlx4_bitmap_init(&priv->mcg_table.bitmap,
-			       dev->caps.num_amgms, dev->caps.num_amgms - 1, 0);
+	err = mlx4_bitmap_init(&priv->mcg_table.bitmap, dev->caps.num_amgms,
+			       dev->caps.num_amgms - 1, 0, 0);
 	if (err)
 		return err;
 
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index b55ddab73f66..9e2f44c31810 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -111,6 +111,7 @@ struct mlx4_bitmap {
 	u32			last;
 	u32			top;
 	u32			max;
+	u32                     reserved_top;
 	u32			mask;
 	spinlock_t		lock;
 	unsigned long	       *table;
@@ -290,7 +291,8 @@ u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap);
 void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj);
 u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align);
 void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt);
-int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask, u32 reserved);
+int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
+		     u32 reserved_bot, u32 resetrved_top);
 void mlx4_bitmap_cleanup(struct mlx4_bitmap *bitmap);
 
 int mlx4_reset(struct mlx4_dev *dev);
diff --git a/drivers/net/mlx4/mr.c b/drivers/net/mlx4/mr.c
index d1dd5b48dbd1..0caf74cae8bc 100644
--- a/drivers/net/mlx4/mr.c
+++ b/drivers/net/mlx4/mr.c
@@ -461,7 +461,7 @@ int mlx4_init_mr_table(struct mlx4_dev *dev)
 	int err;
 
 	err = mlx4_bitmap_init(&mr_table->mpt_bitmap, dev->caps.num_mpts,
-			       ~0, dev->caps.reserved_mrws);
+			       ~0, dev->caps.reserved_mrws, 0);
 	if (err)
 		return err;
 
diff --git a/drivers/net/mlx4/pd.c b/drivers/net/mlx4/pd.c
index aa616892d09c..26d1a7a9e375 100644
--- a/drivers/net/mlx4/pd.c
+++ b/drivers/net/mlx4/pd.c
@@ -62,7 +62,7 @@ int mlx4_init_pd_table(struct mlx4_dev *dev)
 	struct mlx4_priv *priv = mlx4_priv(dev);
 
 	return mlx4_bitmap_init(&priv->pd_bitmap, dev->caps.num_pds,
-				(1 << 24) - 1, dev->caps.reserved_pds);
+				(1 << 24) - 1, dev->caps.reserved_pds, 0);
 }
 
 void mlx4_cleanup_pd_table(struct mlx4_dev *dev)
@@ -100,7 +100,7 @@ int mlx4_init_uar_table(struct mlx4_dev *dev)
 
 	return mlx4_bitmap_init(&mlx4_priv(dev)->uar_table.bitmap,
 				dev->caps.num_uars, dev->caps.num_uars - 1,
-				max(128, dev->caps.reserved_uars));
+				max(128, dev->caps.reserved_uars), 0);
 }
 
 void mlx4_cleanup_uar_table(struct mlx4_dev *dev)
diff --git a/drivers/net/mlx4/qp.c b/drivers/net/mlx4/qp.c
index 98e0c40ba368..1c565ef8d179 100644
--- a/drivers/net/mlx4/qp.c
+++ b/drivers/net/mlx4/qp.c
@@ -272,6 +272,7 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 {
 	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
 	int err;
+	int reserved_from_top = 0;
 
 	spin_lock_init(&qp_table->lock);
 	INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC);
@@ -281,9 +282,40 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 	 * block of special QPs must be aligned to a multiple of 8, so
 	 * round up.
 	 */
-	dev->caps.sqp_start = ALIGN(dev->caps.reserved_qps, 8);
+	dev->caps.sqp_start =
+		ALIGN(dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 8);
+
+	{
+		int sort[MLX4_NUM_QP_REGION];
+		int i, j, tmp;
+		int last_base = dev->caps.num_qps;
+
+		for (i = 1; i < MLX4_NUM_QP_REGION; ++i)
+			sort[i] = i;
+
+		for (i = MLX4_NUM_QP_REGION; i > 0; --i) {
+			for (j = 2; j < i; ++j) {
+				if (dev->caps.reserved_qps_cnt[sort[j]] >
+				    dev->caps.reserved_qps_cnt[sort[j - 1]]) {
+					tmp             = sort[j];
+					sort[j]         = sort[j - 1];
+					sort[j - 1]     = tmp;
+				}
+			}
+		}
+
+		for (i = 1; i < MLX4_NUM_QP_REGION; ++i) {
+			last_base -= dev->caps.reserved_qps_cnt[sort[i]];
+			dev->caps.reserved_qps_base[sort[i]] = last_base;
+			reserved_from_top +=
+				dev->caps.reserved_qps_cnt[sort[i]];
+		}
+
+	}
+
 	err = mlx4_bitmap_init(&qp_table->bitmap, dev->caps.num_qps,
-			       (1 << 24) - 1, dev->caps.sqp_start + 8);
+			       (1 << 23) - 1, dev->caps.sqp_start + 8,
+			       reserved_from_top);
 	if (err)
 		return err;
 
diff --git a/drivers/net/mlx4/srq.c b/drivers/net/mlx4/srq.c
index 533eb6db24b3..fe9f218691f5 100644
--- a/drivers/net/mlx4/srq.c
+++ b/drivers/net/mlx4/srq.c
@@ -245,7 +245,7 @@ int mlx4_init_srq_table(struct mlx4_dev *dev)
 	INIT_RADIX_TREE(&srq_table->tree, GFP_ATOMIC);
 
 	err = mlx4_bitmap_init(&srq_table->bitmap, dev->caps.num_srqs,
-			       dev->caps.num_srqs - 1, dev->caps.reserved_srqs);
+			       dev->caps.num_srqs - 1, dev->caps.reserved_srqs, 0);
 	if (err)
 		return err;
 
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index d21e879f3c90..693f93cd29e1 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -145,6 +145,18 @@ enum {
 	MLX4_MTT_FLAG_PRESENT		= 1
 };
 
+enum mlx4_qp_region {
+	MLX4_QP_REGION_FW = 0,
+	MLX4_QP_REGION_ETH_ADDR,
+	MLX4_QP_REGION_FC_ADDR,
+	MLX4_QP_REGION_FC_EXCH,
+	MLX4_NUM_QP_REGION
+};
+
+enum {
+	MLX4_NUM_FEXCH          = 64 * 1024,
+};
+
 static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor)
 {
 	return (major << 32) | (minor << 16) | subminor;
@@ -169,7 +181,6 @@ struct mlx4_caps {
 	int			max_rq_desc_sz;
 	int			max_qp_init_rdma;
 	int			max_qp_dest_rdma;
-	int			reserved_qps;
 	int			sqp_start;
 	int			num_srqs;
 	int			max_srq_wqes;
@@ -201,6 +212,12 @@ struct mlx4_caps {
 	u16			stat_rate_support;
 	u8			port_width_cap[MLX4_MAX_PORTS + 1];
 	int			max_gso_sz;
+	int                     reserved_qps_cnt[MLX4_NUM_QP_REGION];
+	int			reserved_qps;
+	int                     reserved_qps_base[MLX4_NUM_QP_REGION];
+	int                     log_num_macs;
+	int                     log_num_vlans;
+	int                     log_num_prios;
 };
 
 struct mlx4_buf_list {
-- 
cgit v1.2.3


From b79acb49de6c2ab9ff0245f0f2b573d48b9a2d93 Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Wed, 22 Oct 2008 10:56:48 -0700
Subject: mlx4_core: Get ethernet MTU and default address from firmware

Get maximum ethernet MTU and default MAC address from the firmware
QUERY_DEV_CAP command.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/net/mlx4/fw.c       | 13 ++++++++-----
 drivers/net/mlx4/fw.h       |  4 +++-
 drivers/net/mlx4/main.c     |  4 +++-
 include/linux/mlx4/device.h |  4 +++-
 4 files changed, 17 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/drivers/net/mlx4/fw.c b/drivers/net/mlx4/fw.c
index 40d8142c23b2..8d402db9a03d 100644
--- a/drivers/net/mlx4/fw.c
+++ b/drivers/net/mlx4/fw.c
@@ -346,7 +346,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 			MLX4_GET(field, outbox, QUERY_DEV_CAP_VL_PORT_OFFSET);
 			dev_cap->max_vl[i]	   = field >> 4;
 			MLX4_GET(field, outbox, QUERY_DEV_CAP_MTU_WIDTH_OFFSET);
-			dev_cap->max_mtu[i]	   = field >> 4;
+			dev_cap->ib_mtu[i]	   = field >> 4;
 			dev_cap->max_port_width[i] = field & 0xf;
 			MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_GID_OFFSET);
 			dev_cap->max_gids[i]	   = 1 << (field & 0xf);
@@ -355,8 +355,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		}
 	} else {
 #define QUERY_PORT_MTU_OFFSET			0x01
+#define QUERY_PORT_ETH_MTU_OFFSET		0x02
 #define QUERY_PORT_WIDTH_OFFSET			0x06
 #define QUERY_PORT_MAX_GID_PKEY_OFFSET		0x07
+#define QUERY_PORT_MAC_OFFSET			0x08
 #define QUERY_PORT_MAX_MACVLAN_OFFSET		0x0a
 #define QUERY_PORT_MAX_VL_OFFSET		0x0b
 
@@ -367,7 +369,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 				goto out;
 
 			MLX4_GET(field, outbox, QUERY_PORT_MTU_OFFSET);
-			dev_cap->max_mtu[i]	   = field & 0xf;
+			dev_cap->ib_mtu[i]	   = field & 0xf;
 			MLX4_GET(field, outbox, QUERY_PORT_WIDTH_OFFSET);
 			dev_cap->max_port_width[i] = field & 0xf;
 			MLX4_GET(field, outbox, QUERY_PORT_MAX_GID_PKEY_OFFSET);
@@ -378,7 +380,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 			MLX4_GET(field, outbox, QUERY_PORT_MAX_MACVLAN_OFFSET);
 			dev_cap->log_max_macs[i]  = field & 0xf;
 			dev_cap->log_max_vlans[i] = field >> 4;
-
+			MLX4_GET(dev_cap->eth_mtu[i], outbox, QUERY_PORT_ETH_MTU_OFFSET);
+			MLX4_GET(dev_cap->def_mac[i], outbox, QUERY_PORT_MAC_OFFSET);
 		}
 	}
 
@@ -412,7 +415,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	mlx4_dbg(dev, "Max CQEs: %d, max WQEs: %d, max SRQ WQEs: %d\n",
 		 dev_cap->max_cq_sz, dev_cap->max_qp_sz, dev_cap->max_srq_sz);
 	mlx4_dbg(dev, "Local CA ACK delay: %d, max MTU: %d, port width cap: %d\n",
-		 dev_cap->local_ca_ack_delay, 128 << dev_cap->max_mtu[1],
+		 dev_cap->local_ca_ack_delay, 128 << dev_cap->ib_mtu[1],
 		 dev_cap->max_port_width[1]);
 	mlx4_dbg(dev, "Max SQ desc size: %d, max SQ S/G: %d\n",
 		 dev_cap->max_sq_desc_sz, dev_cap->max_sq_sg);
@@ -824,7 +827,7 @@ int mlx4_INIT_PORT(struct mlx4_dev *dev, int port)
 		flags |= (dev->caps.port_width_cap[port] & 0xf) << INIT_PORT_PORT_WIDTH_SHIFT;
 		MLX4_PUT(inbox, flags,		  INIT_PORT_FLAGS_OFFSET);
 
-		field = 128 << dev->caps.mtu_cap[port];
+		field = 128 << dev->caps.ib_mtu_cap[port];
 		MLX4_PUT(inbox, field, INIT_PORT_MTU_OFFSET);
 		field = dev->caps.gid_table_len[port];
 		MLX4_PUT(inbox, field, INIT_PORT_MAX_GID_OFFSET);
diff --git a/drivers/net/mlx4/fw.h b/drivers/net/mlx4/fw.h
index c34e726d66e4..d0913d4d262a 100644
--- a/drivers/net/mlx4/fw.h
+++ b/drivers/net/mlx4/fw.h
@@ -66,11 +66,13 @@ struct mlx4_dev_cap {
 	int local_ca_ack_delay;
 	int num_ports;
 	u32 max_msg_sz;
-	int max_mtu[MLX4_MAX_PORTS + 1];
+	int ib_mtu[MLX4_MAX_PORTS + 1];
 	int max_port_width[MLX4_MAX_PORTS + 1];
 	int max_vl[MLX4_MAX_PORTS + 1];
 	int max_gids[MLX4_MAX_PORTS + 1];
 	int max_pkeys[MLX4_MAX_PORTS + 1];
+	u64 def_mac[MLX4_MAX_PORTS + 1];
+	u16 eth_mtu[MLX4_MAX_PORTS + 1];
 	u16 stat_rate_support;
 	u32 flags;
 	int reserved_uars;
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 560e1962212e..28f36b88de38 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -133,10 +133,12 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.num_ports	     = dev_cap->num_ports;
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
 		dev->caps.vl_cap[i]	    = dev_cap->max_vl[i];
-		dev->caps.mtu_cap[i]	    = dev_cap->max_mtu[i];
+		dev->caps.ib_mtu_cap[i]	    = dev_cap->ib_mtu[i];
 		dev->caps.gid_table_len[i]  = dev_cap->max_gids[i];
 		dev->caps.pkey_table_len[i] = dev_cap->max_pkeys[i];
 		dev->caps.port_width_cap[i] = dev_cap->max_port_width[i];
+		dev->caps.eth_mtu_cap[i]    = dev_cap->eth_mtu[i];
+		dev->caps.def_mac[i]        = dev_cap->def_mac[i];
 	}
 
 	dev->caps.num_uars	     = dev_cap->uar_size / PAGE_SIZE;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 693f93cd29e1..f9e73cfc540b 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -166,7 +166,9 @@ struct mlx4_caps {
 	u64			fw_ver;
 	int			num_ports;
 	int			vl_cap[MLX4_MAX_PORTS + 1];
-	int			mtu_cap[MLX4_MAX_PORTS + 1];
+	int			ib_mtu_cap[MLX4_MAX_PORTS + 1];
+	u64			def_mac[MLX4_MAX_PORTS + 1];
+	int			eth_mtu_cap[MLX4_MAX_PORTS + 1];
 	int			gid_table_len[MLX4_MAX_PORTS + 1];
 	int			pkey_table_len[MLX4_MAX_PORTS + 1];
 	int			local_ca_ack_delay;
-- 
cgit v1.2.3


From 08e5338d119daeb3c7746fa80fa916b8d3d48e89 Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Wed, 22 Oct 2008 20:21:29 +0200
Subject: i2c-algo-pcf: Pass adapter data into ->waitforpin() method

Pass adapter data into ->waitforpin() method.

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jean Delvare <khali@linux-fr.org>
---
 drivers/i2c/algos/i2c-algo-pcf.c | 2 +-
 drivers/i2c/busses/i2c-elektor.c | 3 ++-
 include/linux/i2c-algo-pcf.h     | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include')

diff --git a/drivers/i2c/algos/i2c-algo-pcf.c b/drivers/i2c/algos/i2c-algo-pcf.c
index 1e328d19cd6d..a8a5b6d1dd88 100644
--- a/drivers/i2c/algos/i2c-algo-pcf.c
+++ b/drivers/i2c/algos/i2c-algo-pcf.c
@@ -135,7 +135,7 @@ static int wait_for_pin(struct i2c_algo_pcf_data *adap, int *status) {
 	*status = get_pcf(adap, 1);
 #ifndef STUB_I2C
 	while (timeout-- && (*status & I2C_PCF_PIN)) {
-		adap->waitforpin();
+		adap->waitforpin(adap->data);
 		*status = get_pcf(adap, 1);
 	}
 	if (*status & I2C_PCF_LAB) {
diff --git a/drivers/i2c/busses/i2c-elektor.c b/drivers/i2c/busses/i2c-elektor.c
index 7f38c01fb3a0..0ed3ccb81b63 100644
--- a/drivers/i2c/busses/i2c-elektor.c
+++ b/drivers/i2c/busses/i2c-elektor.c
@@ -104,7 +104,8 @@ static int pcf_isa_getclock(void *data)
 	return (clock);
 }
 
-static void pcf_isa_waitforpin(void) {
+static void pcf_isa_waitforpin(void *data)
+{
 	DEFINE_WAIT(wait);
 	int timeout = 2;
 	unsigned long flags;
diff --git a/include/linux/i2c-algo-pcf.h b/include/linux/i2c-algo-pcf.h
index 0177d280f733..5de8a319bf14 100644
--- a/include/linux/i2c-algo-pcf.h
+++ b/include/linux/i2c-algo-pcf.h
@@ -31,7 +31,7 @@ struct i2c_algo_pcf_data {
 	int  (*getpcf) (void *data, int ctl);
 	int  (*getown) (void *data);
 	int  (*getclock) (void *data);
-	void (*waitforpin) (void);
+	void (*waitforpin) (void *data);
 
 	/* Multi-master lost arbitration back-off delay (msecs)
 	 * This should be set by the bus adapter or knowledgable client
-- 
cgit v1.2.3


From 30091404af5a7cd515e7b565df76932e295d8f6f Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Wed, 22 Oct 2008 20:21:30 +0200
Subject: i2c-algo-pcf: Add adapter hooks around xfer begin and end

Some I2C bus implementations need to synchronize with external
entities, such as system firmware, which might also be programming the
same I2C bus.

In order to facilitate this add ->xfer_begin() and ->xfer_end() hooks
which are invoked around pcf_xfer().

[JD: Make these hooks optional.]

Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Jean Delvare <khali@linux-fr.org>
---
 drivers/i2c/algos/i2c-algo-pcf.c | 17 +++++++++++++----
 include/linux/i2c-algo-pcf.h     |  3 +++
 2 files changed, 16 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/i2c/algos/i2c-algo-pcf.c b/drivers/i2c/algos/i2c-algo-pcf.c
index a8a5b6d1dd88..b8a6f3bcbae3 100644
--- a/drivers/i2c/algos/i2c-algo-pcf.c
+++ b/drivers/i2c/algos/i2c-algo-pcf.c
@@ -331,13 +331,16 @@ static int pcf_xfer(struct i2c_adapter *i2c_adap,
 	int i;
 	int ret=0, timeout, status;
     
+	if (adap->xfer_begin)
+		adap->xfer_begin(adap->data);
 
 	/* Check for bus busy */
 	timeout = wait_for_bb(adap);
 	if (timeout) {
 		DEB2(printk(KERN_ERR "i2c-algo-pcf.o: "
 		            "Timeout waiting for BB in pcf_xfer\n");)
-		return -EIO;
+		i = -EIO;
+		goto out;
 	}
 	
 	for (i = 0;ret >= 0 && i < num; i++) {
@@ -359,12 +362,14 @@ static int pcf_xfer(struct i2c_adapter *i2c_adap,
 		if (timeout) {
 			if (timeout == -EINTR) {
 				/* arbitration lost */
-				return (-EINTR);
+				i = -EINTR;
+				goto out;
 			}
 			i2c_stop(adap);
 			DEB2(printk(KERN_ERR "i2c-algo-pcf.o: Timeout waiting "
 				    "for PIN(1) in pcf_xfer\n");)
-			return (-EREMOTEIO);
+			i = -EREMOTEIO;
+			goto out;
 		}
     
 #ifndef STUB_I2C
@@ -372,7 +377,8 @@ static int pcf_xfer(struct i2c_adapter *i2c_adap,
 		if (status & I2C_PCF_LRB) {
 			i2c_stop(adap);
 			DEB2(printk(KERN_ERR "i2c-algo-pcf.o: No LRB(1) in pcf_xfer\n");)
-			return (-EREMOTEIO);
+			i = -EREMOTEIO;
+			goto out;
 		}
 #endif
     
@@ -404,6 +410,9 @@ static int pcf_xfer(struct i2c_adapter *i2c_adap,
 		}
 	}
 
+out:
+	if (adap->xfer_end)
+		adap->xfer_end(adap->data);
 	return (i);
 }
 
diff --git a/include/linux/i2c-algo-pcf.h b/include/linux/i2c-algo-pcf.h
index 5de8a319bf14..0f91a957a690 100644
--- a/include/linux/i2c-algo-pcf.h
+++ b/include/linux/i2c-algo-pcf.h
@@ -33,6 +33,9 @@ struct i2c_algo_pcf_data {
 	int  (*getclock) (void *data);
 	void (*waitforpin) (void *data);
 
+	void (*xfer_begin) (void *data);
+	void (*xfer_end) (void *data);
+
 	/* Multi-master lost arbitration back-off delay (msecs)
 	 * This should be set by the bus adapter or knowledgable client
 	 * if bus is multi-mastered, else zero
-- 
cgit v1.2.3


From 14f55f7a033f86a4e8f0310dd4d54b5464322e6e Mon Sep 17 00:00:00 2001
From: Wolfram Sang <w.sang@pengutronix.de>
Date: Wed, 22 Oct 2008 20:21:30 +0200
Subject: i2c: Make clear what the class field of i2c_adapter is good for

Make clear what the class field of i2c_adapter is good for.

Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Signed-off-by: Jean Delvare <khali@linux-fr.org>
---
 include/linux/i2c.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 06115128047f..4ac8ec3c7927 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -345,7 +345,7 @@ struct i2c_algorithm {
 struct i2c_adapter {
 	struct module *owner;
 	unsigned int id;
-	unsigned int class;
+	unsigned int class;		  /* classes to allow probing for */
 	const struct i2c_algorithm *algo; /* the algorithm to access the bus */
 	void *algo_data;
 
-- 
cgit v1.2.3


From 7d1d8999b4bec0ba09f935e648a688bb25596d06 Mon Sep 17 00:00:00 2001
From: Jean Delvare <khali@linux-fr.org>
Date: Wed, 22 Oct 2008 20:21:31 +0200
Subject: i2c: Constify i2c_get_clientdata's parameter

i2c_get_clientdata doesn't change the i2c_client it is passed as a
parameter, so it can be constified. Same for i2c_get_adapdata.

Signed-off-by: Jean Delvare <khali@linux-fr.org>
---
 Documentation/i2c/writing-clients | 2 +-
 include/linux/device.h            | 2 +-
 include/linux/i2c.h               | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/Documentation/i2c/writing-clients b/Documentation/i2c/writing-clients
index d73ee117a8ca..3b01350c149c 100644
--- a/Documentation/i2c/writing-clients
+++ b/Documentation/i2c/writing-clients
@@ -83,7 +83,7 @@ be very useful.
 	void i2c_set_clientdata(struct i2c_client *client, void *data);
 
 	/* retrieve the value */
-	void *i2c_get_clientdata(struct i2c_client *client);
+	void *i2c_get_clientdata(const struct i2c_client *client);
 
 An example structure is below.
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 987f5912720a..1a3686d15f98 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -450,7 +450,7 @@ static inline void set_dev_node(struct device *dev, int node)
 }
 #endif
 
-static inline void *dev_get_drvdata(struct device *dev)
+static inline void *dev_get_drvdata(const struct device *dev)
 {
 	return dev->driver_data;
 }
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 4ac8ec3c7927..a411f0b70e8e 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -224,7 +224,7 @@ static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj)
 	return to_i2c_client(dev);
 }
 
-static inline void *i2c_get_clientdata (struct i2c_client *dev)
+static inline void *i2c_get_clientdata(const struct i2c_client *dev)
 {
 	return dev_get_drvdata (&dev->dev);
 }
@@ -369,7 +369,7 @@ struct i2c_adapter {
 };
 #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev)
 
-static inline void *i2c_get_adapdata (struct i2c_adapter *dev)
+static inline void *i2c_get_adapdata(const struct i2c_adapter *dev)
 {
 	return dev_get_drvdata (&dev->dev);
 }
-- 
cgit v1.2.3


From c0589d4bc19294a49934af1be736eb6e9ad11673 Mon Sep 17 00:00:00 2001
From: Jean Delvare <khali@linux-fr.org>
Date: Wed, 22 Oct 2008 20:21:31 +0200
Subject: i2c: Drop 2-byte address block transfer defines

We have no users and no implementers for these transfer types so it
makes little sense to define functionality bits for them.

Signed-off-by: Jean Delvare <khali@linux-fr.org>
---
 include/linux/i2c.h | 4 ----
 1 file changed, 4 deletions(-)

(limited to 'include')

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index a411f0b70e8e..7d21aba819ff 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -541,8 +541,6 @@ struct i2c_msg {
 #define I2C_FUNC_SMBUS_WRITE_BLOCK_DATA 0x02000000
 #define I2C_FUNC_SMBUS_READ_I2C_BLOCK	0x04000000 /* I2C-like block xfer  */
 #define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK	0x08000000 /* w/ 1-byte reg. addr. */
-#define I2C_FUNC_SMBUS_READ_I2C_BLOCK_2	 0x10000000 /* I2C-like block xfer  */
-#define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK_2 0x20000000 /* w/ 2-byte reg. addr. */
 
 #define I2C_FUNC_SMBUS_BYTE (I2C_FUNC_SMBUS_READ_BYTE | \
                              I2C_FUNC_SMBUS_WRITE_BYTE)
@@ -554,8 +552,6 @@ struct i2c_msg {
                                    I2C_FUNC_SMBUS_WRITE_BLOCK_DATA)
 #define I2C_FUNC_SMBUS_I2C_BLOCK (I2C_FUNC_SMBUS_READ_I2C_BLOCK | \
                                   I2C_FUNC_SMBUS_WRITE_I2C_BLOCK)
-#define I2C_FUNC_SMBUS_I2C_BLOCK_2 (I2C_FUNC_SMBUS_READ_I2C_BLOCK_2 | \
-                                    I2C_FUNC_SMBUS_WRITE_I2C_BLOCK_2)
 
 #define I2C_FUNC_SMBUS_EMUL (I2C_FUNC_SMBUS_QUICK | \
                              I2C_FUNC_SMBUS_BYTE | \
-- 
cgit v1.2.3


From 3ae70deef0a5cc34a96aa1972697d01606bc7933 Mon Sep 17 00:00:00 2001
From: Jean Delvare <khali@linux-fr.org>
Date: Wed, 22 Oct 2008 20:21:32 +0200
Subject: i2c: Clean up <linux/i2c.h>

Fix most checkpatch.pl errors and warnings. This includes replacing
spaces with tabs in many places, adding and removing spaces, and
folding long lines.

Also complete a couple prototypes to make it clearer what the
parameters represent.

Signed-off-by: Jean Delvare <khali@linux-fr.org>
---
 include/linux/i2c.h | 149 ++++++++++++++++++++++++++--------------------------
 1 file changed, 75 insertions(+), 74 deletions(-)

(limited to 'include')

diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 7d21aba819ff..12d7364ad3f3 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -53,45 +53,44 @@ struct i2c_board_info;
  * transmit one message at a time, a more complex version can be used to
  * transmit an arbitrary number of messages without interruption.
  */
-extern int i2c_master_send(struct i2c_client *,const char* ,int);
-extern int i2c_master_recv(struct i2c_client *,char* ,int);
+extern int i2c_master_send(struct i2c_client *client, const char *buf,
+			   int count);
+extern int i2c_master_recv(struct i2c_client *client, char *buf, int count);
 
 /* Transfer num messages.
  */
-extern int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num);
-
+extern int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
+			int num);
 
 /* This is the very generalized SMBus access routine. You probably do not
    want to use this, though; one of the functions below may be much easier,
    and probably just as fast.
    Note that we use i2c_adapter here, because you do not need a specific
    smbus adapter to call this function. */
-extern s32 i2c_smbus_xfer (struct i2c_adapter * adapter, u16 addr,
-                           unsigned short flags,
-                           char read_write, u8 command, int size,
-                           union i2c_smbus_data * data);
+extern s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
+			  unsigned short flags, char read_write, u8 command,
+			  int size, union i2c_smbus_data *data);
 
 /* Now follow the 'nice' access routines. These also document the calling
    conventions of i2c_smbus_xfer. */
 
-extern s32 i2c_smbus_read_byte(struct i2c_client * client);
-extern s32 i2c_smbus_write_byte(struct i2c_client * client, u8 value);
-extern s32 i2c_smbus_read_byte_data(struct i2c_client * client, u8 command);
-extern s32 i2c_smbus_write_byte_data(struct i2c_client * client,
-                                     u8 command, u8 value);
-extern s32 i2c_smbus_read_word_data(struct i2c_client * client, u8 command);
-extern s32 i2c_smbus_write_word_data(struct i2c_client * client,
-                                     u8 command, u16 value);
+extern s32 i2c_smbus_read_byte(struct i2c_client *client);
+extern s32 i2c_smbus_write_byte(struct i2c_client *client, u8 value);
+extern s32 i2c_smbus_read_byte_data(struct i2c_client *client, u8 command);
+extern s32 i2c_smbus_write_byte_data(struct i2c_client *client,
+				     u8 command, u8 value);
+extern s32 i2c_smbus_read_word_data(struct i2c_client *client, u8 command);
+extern s32 i2c_smbus_write_word_data(struct i2c_client *client,
+				     u8 command, u16 value);
 /* Returns the number of read bytes */
 extern s32 i2c_smbus_read_block_data(struct i2c_client *client,
 				     u8 command, u8 *values);
-extern s32 i2c_smbus_write_block_data(struct i2c_client * client,
-				      u8 command, u8 length,
-				      const u8 *values);
+extern s32 i2c_smbus_write_block_data(struct i2c_client *client,
+				      u8 command, u8 length, const u8 *values);
 /* Returns the number of read bytes */
-extern s32 i2c_smbus_read_i2c_block_data(struct i2c_client * client,
+extern s32 i2c_smbus_read_i2c_block_data(struct i2c_client *client,
 					 u8 command, u8 length, u8 *values);
-extern s32 i2c_smbus_write_i2c_block_data(struct i2c_client * client,
+extern s32 i2c_smbus_write_i2c_block_data(struct i2c_client *client,
 					  u8 command, u8 length,
 					  const u8 *values);
 
@@ -169,7 +168,7 @@ struct i2c_driver {
 	/* a ioctl like command that can be used to perform specific functions
 	 * with the device.
 	 */
-	int (*command)(struct i2c_client *client,unsigned int cmd, void *arg);
+	int (*command)(struct i2c_client *client, unsigned int cmd, void *arg);
 
 	struct device_driver driver;
 	const struct i2c_device_id *id_table;
@@ -226,12 +225,12 @@ static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj)
 
 static inline void *i2c_get_clientdata(const struct i2c_client *dev)
 {
-	return dev_get_drvdata (&dev->dev);
+	return dev_get_drvdata(&dev->dev);
 }
 
-static inline void i2c_set_clientdata (struct i2c_client *dev, void *data)
+static inline void i2c_set_clientdata(struct i2c_client *dev, void *data)
 {
-	dev_set_drvdata (&dev->dev, data);
+	dev_set_drvdata(&dev->dev, data);
 }
 
 /**
@@ -272,7 +271,7 @@ struct i2c_board_info {
  * fields (such as associated irq, or device-specific platform_data)
  * are provided using conventional syntax.
  */
-#define I2C_BOARD_INFO(dev_type,dev_addr) \
+#define I2C_BOARD_INFO(dev_type, dev_addr) \
 	.type = (dev_type), .addr = (dev_addr)
 
 
@@ -306,10 +305,12 @@ extern void i2c_unregister_device(struct i2c_client *);
  */
 #ifdef CONFIG_I2C_BOARDINFO
 extern int
-i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned n);
+i2c_register_board_info(int busnum, struct i2c_board_info const *info,
+			unsigned n);
 #else
 static inline int
-i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned n)
+i2c_register_board_info(int busnum, struct i2c_board_info const *info,
+			unsigned n)
 {
 	return 0;
 }
@@ -328,11 +329,11 @@ struct i2c_algorithm {
 	   using common I2C messages */
 	/* master_xfer should return the number of messages successfully
 	   processed, or a negative value on error */
-	int (*master_xfer)(struct i2c_adapter *adap,struct i2c_msg *msgs,
-	                   int num);
+	int (*master_xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs,
+			   int num);
 	int (*smbus_xfer) (struct i2c_adapter *adap, u16 addr,
-	                   unsigned short flags, char read_write,
-	                   u8 command, int size, union i2c_smbus_data * data);
+			   unsigned short flags, char read_write,
+			   u8 command, int size, union i2c_smbus_data *data);
 
 	/* To determine what the adapter supports */
 	u32 (*functionality) (struct i2c_adapter *);
@@ -371,12 +372,12 @@ struct i2c_adapter {
 
 static inline void *i2c_get_adapdata(const struct i2c_adapter *dev)
 {
-	return dev_get_drvdata (&dev->dev);
+	return dev_get_drvdata(&dev->dev);
 }
 
-static inline void i2c_set_adapdata (struct i2c_adapter *dev, void *data)
+static inline void i2c_set_adapdata(struct i2c_adapter *dev, void *data)
 {
-	dev_set_drvdata (&dev->dev, data);
+	dev_set_drvdata(&dev->dev, data);
 }
 
 /*flags for the client struct: */
@@ -449,7 +450,7 @@ extern int i2c_probe(struct i2c_adapter *adapter,
 		const struct i2c_client_address_data *address_data,
 		int (*found_proc) (struct i2c_adapter *, int, int));
 
-extern struct i2c_adapter* i2c_get_adapter(int id);
+extern struct i2c_adapter *i2c_get_adapter(int id);
 extern void i2c_put_adapter(struct i2c_adapter *adap);
 
 
@@ -465,7 +466,7 @@ static inline int i2c_check_functionality(struct i2c_adapter *adap, u32 func)
 	return (func & i2c_get_functionality(adap)) == func;
 }
 
-/* Return id number for a specific adapter */
+/* Return the adapter number for a specific adapter */
 static inline int i2c_adapter_id(struct i2c_adapter *adap)
 {
 	return adap->nr;
@@ -526,7 +527,7 @@ struct i2c_msg {
 
 #define I2C_FUNC_I2C			0x00000001
 #define I2C_FUNC_10BIT_ADDR		0x00000002
-#define I2C_FUNC_PROTOCOL_MANGLING	0x00000004 /* I2C_M_{REV_DIR_ADDR,NOSTART,..} */
+#define I2C_FUNC_PROTOCOL_MANGLING	0x00000004 /* I2C_M_NOSTART etc. */
 #define I2C_FUNC_SMBUS_PEC		0x00000008
 #define I2C_FUNC_SMBUS_BLOCK_PROC_CALL	0x00008000 /* SMBus 2.0 */
 #define I2C_FUNC_SMBUS_QUICK		0x00010000
@@ -542,25 +543,25 @@ struct i2c_msg {
 #define I2C_FUNC_SMBUS_READ_I2C_BLOCK	0x04000000 /* I2C-like block xfer  */
 #define I2C_FUNC_SMBUS_WRITE_I2C_BLOCK	0x08000000 /* w/ 1-byte reg. addr. */
 
-#define I2C_FUNC_SMBUS_BYTE (I2C_FUNC_SMBUS_READ_BYTE | \
-                             I2C_FUNC_SMBUS_WRITE_BYTE)
-#define I2C_FUNC_SMBUS_BYTE_DATA (I2C_FUNC_SMBUS_READ_BYTE_DATA | \
-                                  I2C_FUNC_SMBUS_WRITE_BYTE_DATA)
-#define I2C_FUNC_SMBUS_WORD_DATA (I2C_FUNC_SMBUS_READ_WORD_DATA | \
-                                  I2C_FUNC_SMBUS_WRITE_WORD_DATA)
-#define I2C_FUNC_SMBUS_BLOCK_DATA (I2C_FUNC_SMBUS_READ_BLOCK_DATA | \
-                                   I2C_FUNC_SMBUS_WRITE_BLOCK_DATA)
-#define I2C_FUNC_SMBUS_I2C_BLOCK (I2C_FUNC_SMBUS_READ_I2C_BLOCK | \
-                                  I2C_FUNC_SMBUS_WRITE_I2C_BLOCK)
-
-#define I2C_FUNC_SMBUS_EMUL (I2C_FUNC_SMBUS_QUICK | \
-                             I2C_FUNC_SMBUS_BYTE | \
-                             I2C_FUNC_SMBUS_BYTE_DATA | \
-                             I2C_FUNC_SMBUS_WORD_DATA | \
-                             I2C_FUNC_SMBUS_PROC_CALL | \
-                             I2C_FUNC_SMBUS_WRITE_BLOCK_DATA | \
-			     I2C_FUNC_SMBUS_I2C_BLOCK | \
-			     I2C_FUNC_SMBUS_PEC)
+#define I2C_FUNC_SMBUS_BYTE		(I2C_FUNC_SMBUS_READ_BYTE | \
+					 I2C_FUNC_SMBUS_WRITE_BYTE)
+#define I2C_FUNC_SMBUS_BYTE_DATA	(I2C_FUNC_SMBUS_READ_BYTE_DATA | \
+					 I2C_FUNC_SMBUS_WRITE_BYTE_DATA)
+#define I2C_FUNC_SMBUS_WORD_DATA	(I2C_FUNC_SMBUS_READ_WORD_DATA | \
+					 I2C_FUNC_SMBUS_WRITE_WORD_DATA)
+#define I2C_FUNC_SMBUS_BLOCK_DATA	(I2C_FUNC_SMBUS_READ_BLOCK_DATA | \
+					 I2C_FUNC_SMBUS_WRITE_BLOCK_DATA)
+#define I2C_FUNC_SMBUS_I2C_BLOCK	(I2C_FUNC_SMBUS_READ_I2C_BLOCK | \
+					 I2C_FUNC_SMBUS_WRITE_I2C_BLOCK)
+
+#define I2C_FUNC_SMBUS_EMUL		(I2C_FUNC_SMBUS_QUICK | \
+					 I2C_FUNC_SMBUS_BYTE | \
+					 I2C_FUNC_SMBUS_BYTE_DATA | \
+					 I2C_FUNC_SMBUS_WORD_DATA | \
+					 I2C_FUNC_SMBUS_PROC_CALL | \
+					 I2C_FUNC_SMBUS_WRITE_BLOCK_DATA | \
+					 I2C_FUNC_SMBUS_I2C_BLOCK | \
+					 I2C_FUNC_SMBUS_PEC)
 
 /*
  * Data for SMBus Messages
@@ -570,7 +571,7 @@ union i2c_smbus_data {
 	__u8 byte;
 	__u16 word;
 	__u8 block[I2C_SMBUS_BLOCK_MAX + 2]; /* block[0] is used for length */
-	                       /* and one more for user-space compatibility */
+			       /* and one more for user-space compatibility */
 };
 
 /* i2c_smbus_xfer read or write markers */
@@ -598,21 +599,21 @@ union i2c_smbus_data {
 
 /* Default fill of many variables */
 #define I2C_CLIENT_DEFAULTS {I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
-                          I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END}
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END, \
+			     I2C_CLIENT_END, I2C_CLIENT_END, I2C_CLIENT_END}
 
 /* I2C_CLIENT_MODULE_PARM creates a module parameter, and puts it in the
    module header */
@@ -621,7 +622,7 @@ union i2c_smbus_data {
   static unsigned short var[I2C_CLIENT_MAX_OPTS] = I2C_CLIENT_DEFAULTS; \
   static unsigned int var##_num; \
   module_param_array(var, short, &var##_num, 0); \
-  MODULE_PARM_DESC(var,desc)
+  MODULE_PARM_DESC(var, desc)
 
 #define I2C_CLIENT_MODULE_PARM_FORCE(name)				\
 I2C_CLIENT_MODULE_PARM(force_##name,					\
-- 
cgit v1.2.3


From 11f1f2afd6b07729b12aaba479344d7f12d88ff9 Mon Sep 17 00:00:00 2001
From: Anton Vorontsov <avorontsov@ru.mvista.com>
Date: Wed, 22 Oct 2008 20:21:33 +0200
Subject: i2c: Add info->archdata field

If present the info->archdata is copied into the dev->archdata.
Some (OpenFirmware) platforms need it.

Signed-off-by: Anton Vorontsov <avorontsov@ru.mvista.com>
Signed-off-by: Jean Delvare <khali@linux-fr.org>
---
 drivers/i2c/i2c-core.c | 3 +++
 include/linux/i2c.h    | 2 ++
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 42e852d79ffa..5a485c22660a 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -266,6 +266,9 @@ i2c_new_device(struct i2c_adapter *adap, struct i2c_board_info const *info)
 
 	client->dev.platform_data = info->platform_data;
 
+	if (info->archdata)
+		client->dev.archdata = *info->archdata;
+
 	client->flags = info->flags;
 	client->addr = info->addr;
 	client->irq = info->irq;
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 12d7364ad3f3..33a5992d4936 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -239,6 +239,7 @@ static inline void i2c_set_clientdata(struct i2c_client *dev, void *data)
  * @flags: to initialize i2c_client.flags
  * @addr: stored in i2c_client.addr
  * @platform_data: stored in i2c_client.dev.platform_data
+ * @archdata: copied into i2c_client.dev.archdata
  * @irq: stored in i2c_client.irq
  *
  * I2C doesn't actually support hardware probing, although controllers and
@@ -258,6 +259,7 @@ struct i2c_board_info {
 	unsigned short	flags;
 	unsigned short	addr;
 	void		*platform_data;
+	struct dev_archdata	*archdata;
 	int		irq;
 };
 
-- 
cgit v1.2.3


From 2a2336f8228292b8197f4187e54b0748903e6645 Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Wed, 22 Oct 2008 11:44:46 -0700
Subject: mlx4_core: Ethernet MAC/VLAN management

Add support for managing MAC and VLAN filters for each port.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Oren Duer <oren@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/net/mlx4/Makefile   |   2 +-
 drivers/net/mlx4/main.c     |  14 +++
 drivers/net/mlx4/mlx4.h     |  33 ++++++
 drivers/net/mlx4/port.c     | 259 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mlx4/cmd.h    |   9 ++
 include/linux/mlx4/device.h |  12 ++
 6 files changed, 328 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/mlx4/port.c

(limited to 'include')

diff --git a/drivers/net/mlx4/Makefile b/drivers/net/mlx4/Makefile
index 0952a6528f58..9f493666e27b 100644
--- a/drivers/net/mlx4/Makefile
+++ b/drivers/net/mlx4/Makefile
@@ -1,4 +1,4 @@
 obj-$(CONFIG_MLX4_CORE)		+= mlx4_core.o
 
 mlx4_core-y :=	alloc.o catas.o cmd.o cq.o eq.o fw.o icm.o intf.o main.o mcg.o \
-		mr.o pd.o profile.o qp.o reset.o srq.o
+		mr.o pd.o port.o profile.o qp.o reset.o srq.o
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 28f36b88de38..0a5c8bfb3f1f 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -780,11 +780,22 @@ no_msi:
 		priv->eq_table.eq[i].irq = dev->pdev->irq;
 }
 
+static void mlx4_init_port_info(struct mlx4_dev *dev, int port)
+{
+	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+
+	info->dev = dev;
+	info->port = port;
+	mlx4_init_mac_table(dev, &info->mac_table);
+	mlx4_init_vlan_table(dev, &info->vlan_table);
+}
+
 static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct mlx4_priv *priv;
 	struct mlx4_dev *dev;
 	int err;
+	int port;
 
 	printk(KERN_INFO PFX "Initializing %s\n",
 	       pci_name(pdev));
@@ -894,6 +905,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_close;
 
+	for (port = 1; port <= dev->caps.num_ports; port++)
+		mlx4_init_port_info(dev, port);
+
 	err = mlx4_register_device(dev);
 	if (err)
 		goto err_cleanup;
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index 9e2f44c31810..23309f381ee3 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -252,6 +252,35 @@ struct mlx4_catas_err {
 	struct list_head	list;
 };
 
+#define MLX4_MAX_MAC_NUM	128
+#define MLX4_MAC_TABLE_SIZE	(MLX4_MAX_MAC_NUM << 3)
+
+struct mlx4_mac_table {
+	__be64			entries[MLX4_MAX_MAC_NUM];
+	int			refs[MLX4_MAX_MAC_NUM];
+	struct mutex		mutex;
+	int			total;
+	int			max;
+};
+
+#define MLX4_MAX_VLAN_NUM	128
+#define MLX4_VLAN_TABLE_SIZE	(MLX4_MAX_VLAN_NUM << 2)
+
+struct mlx4_vlan_table {
+	__be32			entries[MLX4_MAX_VLAN_NUM];
+	int			refs[MLX4_MAX_VLAN_NUM];
+	struct mutex		mutex;
+	int			total;
+	int			max;
+};
+
+struct mlx4_port_info {
+	struct mlx4_dev	       *dev;
+	int			port;
+	struct mlx4_mac_table	mac_table;
+	struct mlx4_vlan_table	vlan_table;
+};
+
 struct mlx4_priv {
 	struct mlx4_dev		dev;
 
@@ -280,6 +309,7 @@ struct mlx4_priv {
 
 	struct mlx4_uar		driver_uar;
 	void __iomem	       *kar;
+	struct mlx4_port_info	port[MLX4_MAX_PORTS + 1];
 };
 
 static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
@@ -350,4 +380,7 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type);
 
 void mlx4_handle_catas_err(struct mlx4_dev *dev);
 
+void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table);
+void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table);
+
 #endif /* MLX4_H */
diff --git a/drivers/net/mlx4/port.c b/drivers/net/mlx4/port.c
new file mode 100644
index 000000000000..8644f3d978ee
--- /dev/null
+++ b/drivers/net/mlx4/port.c
@@ -0,0 +1,259 @@
+/*
+ * Copyright (c) 2007 Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/errno.h>
+#include <linux/if_ether.h>
+
+#include <linux/mlx4/cmd.h>
+
+#include "mlx4.h"
+
+#define MLX4_MAC_VALID		(1ull << 63)
+#define MLX4_MAC_MASK		0xffffffffffffULL
+
+#define MLX4_VLAN_VALID		(1u << 31)
+#define MLX4_VLAN_MASK		0xfff
+
+void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table)
+{
+	int i;
+
+	mutex_init(&table->mutex);
+	for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
+		table->entries[i] = 0;
+		table->refs[i]	 = 0;
+	}
+	table->max   = 1 << dev->caps.log_num_macs;
+	table->total = 0;
+}
+
+void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table)
+{
+	int i;
+
+	mutex_init(&table->mutex);
+	for (i = 0; i < MLX4_MAX_VLAN_NUM; i++) {
+		table->entries[i] = 0;
+		table->refs[i]	 = 0;
+	}
+	table->max   = 1 << dev->caps.log_num_vlans;
+	table->total = 0;
+}
+
+static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
+				   __be64 *entries)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	u32 in_mod;
+	int err;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	memcpy(mailbox->buf, entries, MLX4_MAC_TABLE_SIZE);
+
+	in_mod = MLX4_SET_PORT_MAC_TABLE << 8 | port;
+	err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
+		       MLX4_CMD_TIME_CLASS_B);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+
+int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *index)
+{
+	struct mlx4_mac_table *table = &mlx4_priv(dev)->port[port].mac_table;
+	int i, err = 0;
+	int free = -1;
+
+	mlx4_dbg(dev, "Registering MAC: 0x%llx\n", (unsigned long long) mac);
+	mutex_lock(&table->mutex);
+	for (i = 0; i < MLX4_MAX_MAC_NUM - 1; i++) {
+		if (free < 0 && !table->refs[i]) {
+			free = i;
+			continue;
+		}
+
+		if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
+			/* MAC already registered, increase refernce count */
+			*index = i;
+			++table->refs[i];
+			goto out;
+		}
+	}
+	mlx4_dbg(dev, "Free MAC index is %d\n", free);
+
+	if (table->total == table->max) {
+		/* No free mac entries */
+		err = -ENOSPC;
+		goto out;
+	}
+
+	/* Register new MAC */
+	table->refs[free] = 1;
+	table->entries[free] = cpu_to_be64(mac | MLX4_MAC_VALID);
+
+	err = mlx4_set_port_mac_table(dev, port, table->entries);
+	if (unlikely(err)) {
+		mlx4_err(dev, "Failed adding MAC: 0x%llx\n", (unsigned long long) mac);
+		table->refs[free] = 0;
+		table->entries[free] = 0;
+		goto out;
+	}
+
+	*index = free;
+	++table->total;
+out:
+	mutex_unlock(&table->mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_register_mac);
+
+void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int index)
+{
+	struct mlx4_mac_table *table = &mlx4_priv(dev)->port[port].mac_table;
+
+	mutex_lock(&table->mutex);
+	if (!table->refs[index]) {
+		mlx4_warn(dev, "No MAC entry for index %d\n", index);
+		goto out;
+	}
+	if (--table->refs[index]) {
+		mlx4_warn(dev, "Have more references for index %d,"
+			  "no need to modify MAC table\n", index);
+		goto out;
+	}
+	table->entries[index] = 0;
+	mlx4_set_port_mac_table(dev, port, table->entries);
+	--table->total;
+out:
+	mutex_unlock(&table->mutex);
+}
+EXPORT_SYMBOL_GPL(mlx4_unregister_mac);
+
+static int mlx4_set_port_vlan_table(struct mlx4_dev *dev, u8 port,
+				    __be32 *entries)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	u32 in_mod;
+	int err;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	memcpy(mailbox->buf, entries, MLX4_VLAN_TABLE_SIZE);
+	in_mod = MLX4_SET_PORT_VLAN_TABLE << 8 | port;
+	err = mlx4_cmd(dev, mailbox->dma, in_mod, 1, MLX4_CMD_SET_PORT,
+		       MLX4_CMD_TIME_CLASS_B);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+
+	return err;
+}
+
+int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index)
+{
+	struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table;
+	int i, err = 0;
+	int free = -1;
+
+	mutex_lock(&table->mutex);
+	for (i = MLX4_VLAN_REGULAR; i < MLX4_MAX_VLAN_NUM; i++) {
+		if (free < 0 && (table->refs[i] == 0)) {
+			free = i;
+			continue;
+		}
+
+		if (table->refs[i] &&
+		    (vlan == (MLX4_VLAN_MASK &
+			      be32_to_cpu(table->entries[i])))) {
+			/* Vlan already registered, increase refernce count */
+			*index = i;
+			++table->refs[i];
+			goto out;
+		}
+	}
+
+	if (table->total == table->max) {
+		/* No free vlan entries */
+		err = -ENOSPC;
+		goto out;
+	}
+
+	/* Register new MAC */
+	table->refs[free] = 1;
+	table->entries[free] = cpu_to_be32(vlan | MLX4_VLAN_VALID);
+
+	err = mlx4_set_port_vlan_table(dev, port, table->entries);
+	if (unlikely(err)) {
+		mlx4_warn(dev, "Failed adding vlan: %u\n", vlan);
+		table->refs[free] = 0;
+		table->entries[free] = 0;
+		goto out;
+	}
+
+	*index = free;
+	++table->total;
+out:
+	mutex_unlock(&table->mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_register_vlan);
+
+void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index)
+{
+	struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table;
+
+	if (index < MLX4_VLAN_REGULAR) {
+		mlx4_warn(dev, "Trying to free special vlan index %d\n", index);
+		return;
+	}
+
+	mutex_lock(&table->mutex);
+	if (!table->refs[index]) {
+		mlx4_warn(dev, "No vlan entry for index %d\n", index);
+		goto out;
+	}
+	if (--table->refs[index]) {
+		mlx4_dbg(dev, "Have more references for index %d,"
+			 "no need to modify vlan table\n", index);
+		goto out;
+	}
+	table->entries[index] = 0;
+	mlx4_set_port_vlan_table(dev, port, table->entries);
+	--table->total;
+out:
+	mutex_unlock(&table->mutex);
+}
+EXPORT_SYMBOL_GPL(mlx4_unregister_vlan);
diff --git a/include/linux/mlx4/cmd.h b/include/linux/mlx4/cmd.h
index 77323a72dd3c..cf9c679ab38b 100644
--- a/include/linux/mlx4/cmd.h
+++ b/include/linux/mlx4/cmd.h
@@ -132,6 +132,15 @@ enum {
 	MLX4_MAILBOX_SIZE	=  4096
 };
 
+enum {
+	/* set port opcode modifiers */
+	MLX4_SET_PORT_GENERAL   = 0x0,
+	MLX4_SET_PORT_RQP_CALC  = 0x1,
+	MLX4_SET_PORT_MAC_TABLE = 0x2,
+	MLX4_SET_PORT_VLAN_TABLE = 0x3,
+	MLX4_SET_PORT_PRIO_MAP  = 0x4,
+};
+
 struct mlx4_dev;
 
 struct mlx4_cmd_mailbox {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index f9e73cfc540b..1951fe70a251 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -153,6 +153,12 @@ enum mlx4_qp_region {
 	MLX4_NUM_QP_REGION
 };
 
+enum mlx4_special_vlan_idx {
+	MLX4_NO_VLAN_IDX        = 0,
+	MLX4_VLAN_MISS_IDX,
+	MLX4_VLAN_REGULAR
+};
+
 enum {
 	MLX4_NUM_FEXCH          = 64 * 1024,
 };
@@ -438,6 +444,12 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			  int block_mcast_loopback);
 int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]);
 
+int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *index);
+void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int index);
+
+int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
+void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, int index);
+
 int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list,
 		      int npages, u64 iova, u32 *lkey, u32 *rkey);
 int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
-- 
cgit v1.2.3


From f5adfaa372c76423b6e8e4727a9701330374f364 Mon Sep 17 00:00:00 2001
From: Zhao Yakui <yakui.zhao@intel.com>
Date: Mon, 11 Aug 2008 14:57:50 +0800
Subject: ACPI: Add "acpi.power_nocheck=1" to disable power state check in
 power transition

   Maybe the incorrect power state is returned on the bogus bios, which
is different with the real power state. For example: the bios returns D0
state and the real power state is D3. OS expects to set the device to D0
state. In  such case if OS uses the power state returned by the BIOS and
checks the device power state very strictly in power transition, the device
can't be transited to the correct power state.

   So the boot option of "acpi.power_nocheck=1" is added to avoid checking
the device power in the course of device power transition.

http://bugzilla.kernel.org/show_bug.cgi?id=8049
http://bugzilla.kernel.org/show_bug.cgi?id=11000

Signed-off-by: Zhao Yakui <yakui.zhao@intel.com>
Signed-off-by: Zhang Rui <rui.zhang@intel.com>
Signed-off-by: Li Shaohua <shaohua.li@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 Documentation/kernel-parameters.txt |  8 +++++++
 drivers/acpi/bus.c                  | 14 ++++++++++++-
 drivers/acpi/power.c                | 42 +++++++++++++++++++++++++++----------
 include/acpi/acpi_drivers.h         |  1 +
 4 files changed, 53 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 44d1bd142edf..99cf83fd6947 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -251,6 +251,14 @@ and is between 256 and 4096 characters. It is defined in the file
  			Warning: Many of these options can produce a lot of
  			output and make your system unusable. Be very careful.
 
+ 	acpi.power_nocheck=	[HW,ACPI]
+ 			Format: 1/0 enable/disable the check of power state.
+ 			On some bogus BIOS the _PSC object/_STA object of
+ 			power resource can't return the correct device power
+ 			state. In such case it is unneccessary to check its
+ 			power state again in power transition.
+ 			1 : disable the power state check
+
 	acpi_pm_good	[X86-32,X86-64]
 			Override the pmtimer bug detection: force the kernel
 			to assume that this machine's pmtimer latches its value
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index ccae305ee55d..91bdeb3b081e 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -223,7 +223,19 @@ int acpi_bus_set_power(acpi_handle handle, int state)
 	/*
 	 * Get device's current power state
 	 */
-	acpi_bus_get_power(device->handle, &device->power.state);
+	if (!acpi_power_nocheck) {
+		/*
+		 * Maybe the incorrect power state is returned on the bogus
+		 * bios, which is different with the real power state.
+		 * For example: the bios returns D0 state and the real power
+		 * state is D3. OS expects to set the device to D0 state. In
+		 * such case if OS uses the power state returned by the BIOS,
+		 * the device can't be transisted to the correct power state.
+		 * So if the acpi_power_nocheck is set, it is unnecessary to
+		 * get the power state by calling acpi_bus_get_power.
+		 */
+		acpi_bus_get_power(device->handle, &device->power.state);
+	}
 	if ((state == device->power.state) && !device->flags.force_power_state) {
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Device is already at D%d\n",
 				  state));
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index e7bab75075a9..7ff7349c0c52 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -54,6 +54,14 @@ ACPI_MODULE_NAME("power");
 #define ACPI_POWER_RESOURCE_STATE_OFF	0x00
 #define ACPI_POWER_RESOURCE_STATE_ON	0x01
 #define ACPI_POWER_RESOURCE_STATE_UNKNOWN 0xFF
+
+#ifdef MODULE_PARAM_PREFIX
+#undef MODULE_PARAM_PREFIX
+#endif
+#define MODULE_PARAM_PREFIX "acpi."
+int acpi_power_nocheck;
+module_param_named(power_nocheck, acpi_power_nocheck, bool, 000);
+
 static int acpi_power_add(struct acpi_device *device);
 static int acpi_power_remove(struct acpi_device *device, int type);
 static int acpi_power_resume(struct acpi_device *device);
@@ -228,12 +236,18 @@ static int acpi_power_on(acpi_handle handle, struct acpi_device *dev)
 	if (ACPI_FAILURE(status))
 		return -ENODEV;
 
-	result = acpi_power_get_state(resource->device->handle, &state);
-	if (result)
-		return result;
-	if (state != ACPI_POWER_RESOURCE_STATE_ON)
-		return -ENOEXEC;
-
+	if (!acpi_power_nocheck) {
+		/*
+		 * If acpi_power_nocheck is set, it is unnecessary to check
+		 * the power state after power transition.
+		 */
+		result = acpi_power_get_state(resource->device->handle,
+				&state);
+		if (result)
+			return result;
+		if (state != ACPI_POWER_RESOURCE_STATE_ON)
+			return -ENOEXEC;
+	}
 	/* Update the power resource's _device_ power state */
 	resource->device->power.state = ACPI_STATE_D0;
 
@@ -279,11 +293,17 @@ static int acpi_power_off_device(acpi_handle handle, struct acpi_device *dev)
 	if (ACPI_FAILURE(status))
 		return -ENODEV;
 
-	result = acpi_power_get_state(handle, &state);
-	if (result)
-		return result;
-	if (state != ACPI_POWER_RESOURCE_STATE_OFF)
-		return -ENOEXEC;
+	if (!acpi_power_nocheck) {
+		/*
+		 * If acpi_power_nocheck is set, it is unnecessary to check
+		 * the power state after power transition.
+		 */
+		result = acpi_power_get_state(handle, &state);
+		if (result)
+			return result;
+		if (state != ACPI_POWER_RESOURCE_STATE_OFF)
+			return -ENOEXEC;
+	}
 
 	/* Update the power resource's _device_ power state */
 	resource->device->power.state = ACPI_STATE_D3;
diff --git a/include/acpi/acpi_drivers.h b/include/acpi/acpi_drivers.h
index e5f38e5ce86f..efbaa271ee11 100644
--- a/include/acpi/acpi_drivers.h
+++ b/include/acpi/acpi_drivers.h
@@ -93,6 +93,7 @@ int acpi_enable_wakeup_device_power(struct acpi_device *dev, int sleep_state);
 int acpi_disable_wakeup_device_power(struct acpi_device *dev);
 int acpi_power_get_inferred_state(struct acpi_device *device);
 int acpi_power_transition(struct acpi_device *device, int state);
+extern int acpi_power_nocheck;
 #endif
 
 /* --------------------------------------------------------------------------
-- 
cgit v1.2.3


From 7ff93f8b7ecbc36e7ffc5c11a61643821c1bfee5 Mon Sep 17 00:00:00 2001
From: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Date: Wed, 22 Oct 2008 15:38:42 -0700
Subject: mlx4_core: Multiple port type support

Multi-protocol adapters support different port types.  Each consumer
of mlx4_core queries for supported port types; in particular mlx4_ib
can no longer assume that all physical ports belong to it.  Port type
is configured through a sysfs interface.  When the type of a port is
changed, all mlx4 interfaces are unregistered, and then registered
again with the new port types.

Signed-off-by: Yevgeny Petrilin <yevgenyp@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/hw/mlx4/mad.c     |   6 +-
 drivers/infiniband/hw/mlx4/main.c    |  11 +-
 drivers/infiniband/hw/mlx4/mlx4_ib.h |   1 +
 drivers/net/mlx4/fw.c                |   4 +
 drivers/net/mlx4/fw.h                |   1 +
 drivers/net/mlx4/main.c              | 211 ++++++++++++++++++++++++++++++++++-
 drivers/net/mlx4/mlx4.h              |   6 +
 drivers/net/mlx4/port.c              |  23 ++++
 include/linux/mlx4/device.h          |  14 +++
 9 files changed, 266 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index cdca3a511e1c..606f1e2ef284 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -298,7 +298,7 @@ int mlx4_ib_mad_init(struct mlx4_ib_dev *dev)
 	int p, q;
 	int ret;
 
-	for (p = 0; p < dev->dev->caps.num_ports; ++p)
+	for (p = 0; p < dev->num_ports; ++p)
 		for (q = 0; q <= 1; ++q) {
 			agent = ib_register_mad_agent(&dev->ib_dev, p + 1,
 						      q ? IB_QPT_GSI : IB_QPT_SMI,
@@ -314,7 +314,7 @@ int mlx4_ib_mad_init(struct mlx4_ib_dev *dev)
 	return 0;
 
 err:
-	for (p = 0; p < dev->dev->caps.num_ports; ++p)
+	for (p = 0; p < dev->num_ports; ++p)
 		for (q = 0; q <= 1; ++q)
 			if (dev->send_agent[p][q])
 				ib_unregister_mad_agent(dev->send_agent[p][q]);
@@ -327,7 +327,7 @@ void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev)
 	struct ib_mad_agent *agent;
 	int p, q;
 
-	for (p = 0; p < dev->dev->caps.num_ports; ++p) {
+	for (p = 0; p < dev->num_ports; ++p) {
 		for (q = 0; q <= 1; ++q) {
 			agent = dev->send_agent[p][q];
 			dev->send_agent[p][q] = NULL;
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index a3c2851c0545..2e80f8f47b02 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -574,7 +574,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.owner		= THIS_MODULE;
 	ibdev->ib_dev.node_type		= RDMA_NODE_IB_CA;
 	ibdev->ib_dev.local_dma_lkey	= dev->caps.reserved_lkey;
-	ibdev->ib_dev.phys_port_cnt	= dev->caps.num_ports;
+	ibdev->num_ports = 0;
+	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+		ibdev->num_ports++;
+	ibdev->ib_dev.phys_port_cnt     = ibdev->num_ports;
 	ibdev->ib_dev.num_comp_vectors	= 1;
 	ibdev->ib_dev.dma_device	= &dev->pdev->dev;
 
@@ -691,7 +694,7 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 	struct mlx4_ib_dev *ibdev = ibdev_ptr;
 	int p;
 
-	for (p = 1; p <= dev->caps.num_ports; ++p)
+	for (p = 1; p <= ibdev->num_ports; ++p)
 		mlx4_CLOSE_PORT(dev, p);
 
 	mlx4_ib_mad_cleanup(ibdev);
@@ -706,6 +709,10 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 			  enum mlx4_dev_event event, int port)
 {
 	struct ib_event ibev;
+	struct mlx4_ib_dev *ibdev = to_mdev((struct ib_device *) ibdev_ptr);
+
+	if (port > ibdev->num_ports)
+		return;
 
 	switch (event) {
 	case MLX4_DEV_EVENT_PORT_UP:
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 6e2b0dc21b61..9974e886b8de 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -162,6 +162,7 @@ struct mlx4_ib_ah {
 struct mlx4_ib_dev {
 	struct ib_device	ib_dev;
 	struct mlx4_dev	       *dev;
+	int			num_ports;
 	void __iomem	       *uar_map;
 
 	struct mlx4_uar		priv_uar;
diff --git a/drivers/net/mlx4/fw.c b/drivers/net/mlx4/fw.c
index 8d402db9a03d..be09fdb79cb8 100644
--- a/drivers/net/mlx4/fw.c
+++ b/drivers/net/mlx4/fw.c
@@ -88,6 +88,7 @@ static void dump_dev_cap_flags(struct mlx4_dev *dev, u32 flags)
 		[ 8] = "P_Key violation counter",
 		[ 9] = "Q_Key violation counter",
 		[10] = "VMM",
+		[12] = "DPDP",
 		[16] = "MW support",
 		[17] = "APM support",
 		[18] = "Atomic ops support",
@@ -354,6 +355,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 			dev_cap->max_pkeys[i]	   = 1 << (field & 0xf);
 		}
 	} else {
+#define QUERY_PORT_SUPPORTED_TYPE_OFFSET	0x00
 #define QUERY_PORT_MTU_OFFSET			0x01
 #define QUERY_PORT_ETH_MTU_OFFSET		0x02
 #define QUERY_PORT_WIDTH_OFFSET			0x06
@@ -368,6 +370,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 			if (err)
 				goto out;
 
+			MLX4_GET(field, outbox, QUERY_PORT_SUPPORTED_TYPE_OFFSET);
+			dev_cap->supported_port_types[i] = field & 3;
 			MLX4_GET(field, outbox, QUERY_PORT_MTU_OFFSET);
 			dev_cap->ib_mtu[i]	   = field & 0xf;
 			MLX4_GET(field, outbox, QUERY_PORT_WIDTH_OFFSET);
diff --git a/drivers/net/mlx4/fw.h b/drivers/net/mlx4/fw.h
index d0913d4d262a..526d7f30c041 100644
--- a/drivers/net/mlx4/fw.h
+++ b/drivers/net/mlx4/fw.h
@@ -104,6 +104,7 @@ struct mlx4_dev_cap {
 	u32 reserved_lkey;
 	u64 max_icm_sz;
 	int max_gso_sz;
+	u8  supported_port_types[MLX4_MAX_PORTS + 1];
 	u8  log_max_macs[MLX4_MAX_PORTS + 1];
 	u8  log_max_vlans[MLX4_MAX_PORTS + 1];
 };
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index 0a5c8bfb3f1f..c1d447873bf1 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -98,6 +98,44 @@ module_param_named(use_prio, use_prio, bool, 0444);
 MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports "
 		  "(0/1, default 0)");
 
+static int mlx4_check_port_params(struct mlx4_dev *dev,
+				  enum mlx4_port_type *port_type)
+{
+	int i;
+
+	for (i = 0; i < dev->caps.num_ports - 1; i++) {
+		if (port_type[i] != port_type[i+1] &&
+		    !(dev->caps.flags & MLX4_DEV_CAP_FLAG_DPDP)) {
+			mlx4_err(dev, "Only same port types supported "
+				 "on this HCA, aborting.\n");
+			return -EINVAL;
+		}
+	}
+	if ((port_type[0] == MLX4_PORT_TYPE_ETH) &&
+	    (port_type[1] == MLX4_PORT_TYPE_IB)) {
+		mlx4_err(dev, "eth-ib configuration is not supported.\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < dev->caps.num_ports; i++) {
+		if (!(port_type[i] & dev->caps.supported_type[i+1])) {
+			mlx4_err(dev, "Requested port type for port %d is not "
+				      "supported on this HCA\n", i + 1);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static void mlx4_set_port_mask(struct mlx4_dev *dev)
+{
+	int i;
+
+	dev->caps.port_mask = 0;
+	for (i = 1; i <= dev->caps.num_ports; ++i)
+		if (dev->caps.port_type[i] == MLX4_PORT_TYPE_IB)
+			dev->caps.port_mask |= 1 << (i - 1);
+}
 static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 {
 	int err;
@@ -139,6 +177,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev->caps.port_width_cap[i] = dev_cap->max_port_width[i];
 		dev->caps.eth_mtu_cap[i]    = dev_cap->eth_mtu[i];
 		dev->caps.def_mac[i]        = dev_cap->def_mac[i];
+		dev->caps.supported_type[i] = dev_cap->supported_port_types[i];
 	}
 
 	dev->caps.num_uars	     = dev_cap->uar_size / PAGE_SIZE;
@@ -182,6 +221,11 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.log_num_prios = use_prio ? 3 : 0;
 
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
+		if (dev->caps.supported_type[i] != MLX4_PORT_TYPE_ETH)
+			dev->caps.port_type[i] = MLX4_PORT_TYPE_IB;
+		else
+			dev->caps.port_type[i] = MLX4_PORT_TYPE_ETH;
+
 		if (dev->caps.log_num_macs > dev_cap->log_max_macs[i]) {
 			dev->caps.log_num_macs = dev_cap->log_max_macs[i];
 			mlx4_warn(dev, "Requested number of MACs is too much "
@@ -196,6 +240,8 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		}
 	}
 
+	mlx4_set_port_mask(dev);
+
 	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] = dev_cap->reserved_qps;
 	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] =
 		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] =
@@ -213,6 +259,95 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	return 0;
 }
 
+/*
+ * Change the port configuration of the device.
+ * Every user of this function must hold the port mutex.
+ */
+static int mlx4_change_port_types(struct mlx4_dev *dev,
+				  enum mlx4_port_type *port_types)
+{
+	int err = 0;
+	int change = 0;
+	int port;
+
+	for (port = 0; port <  dev->caps.num_ports; port++) {
+		if (port_types[port] != dev->caps.port_type[port + 1]) {
+			change = 1;
+			dev->caps.port_type[port + 1] = port_types[port];
+		}
+	}
+	if (change) {
+		mlx4_unregister_device(dev);
+		for (port = 1; port <= dev->caps.num_ports; port++) {
+			mlx4_CLOSE_PORT(dev, port);
+			err = mlx4_SET_PORT(dev, port);
+			if (err) {
+				mlx4_err(dev, "Failed to set port %d, "
+					      "aborting\n", port);
+				goto out;
+			}
+		}
+		mlx4_set_port_mask(dev);
+		err = mlx4_register_device(dev);
+	}
+
+out:
+	return err;
+}
+
+static ssize_t show_port_type(struct device *dev,
+			      struct device_attribute *attr,
+			      char *buf)
+{
+	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
+						   port_attr);
+	struct mlx4_dev *mdev = info->dev;
+
+	return sprintf(buf, "%s\n",
+		       mdev->caps.port_type[info->port] == MLX4_PORT_TYPE_IB ?
+		       "ib" : "eth");
+}
+
+static ssize_t set_port_type(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	struct mlx4_port_info *info = container_of(attr, struct mlx4_port_info,
+						   port_attr);
+	struct mlx4_dev *mdev = info->dev;
+	struct mlx4_priv *priv = mlx4_priv(mdev);
+	enum mlx4_port_type types[MLX4_MAX_PORTS];
+	int i;
+	int err = 0;
+
+	if (!strcmp(buf, "ib\n"))
+		info->tmp_type = MLX4_PORT_TYPE_IB;
+	else if (!strcmp(buf, "eth\n"))
+		info->tmp_type = MLX4_PORT_TYPE_ETH;
+	else {
+		mlx4_err(mdev, "%s is not supported port type\n", buf);
+		return -EINVAL;
+	}
+
+	mutex_lock(&priv->port_mutex);
+	for (i = 0; i < mdev->caps.num_ports; i++)
+		types[i] = priv->port[i+1].tmp_type ? priv->port[i+1].tmp_type :
+					mdev->caps.port_type[i+1];
+
+	err = mlx4_check_port_params(mdev, types);
+	if (err)
+		goto out;
+
+	for (i = 1; i <= mdev->caps.num_ports; i++)
+		priv->port[i].tmp_type = 0;
+
+	err = mlx4_change_port_types(mdev, types);
+
+out:
+	mutex_unlock(&priv->port_mutex);
+	return err ? err : count;
+}
+
 static int mlx4_load_fw(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
@@ -617,6 +752,7 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	int err;
+	int port;
 
 	err = mlx4_init_uar_table(dev);
 	if (err) {
@@ -715,8 +851,20 @@ static int mlx4_setup_hca(struct mlx4_dev *dev)
 		goto err_qp_table_free;
 	}
 
+	for (port = 1; port <= dev->caps.num_ports; port++) {
+		err = mlx4_SET_PORT(dev, port);
+		if (err) {
+			mlx4_err(dev, "Failed to set port %d, aborting\n",
+				port);
+			goto err_mcg_table_free;
+		}
+	}
+
 	return 0;
 
+err_mcg_table_free:
+	mlx4_cleanup_mcg_table(dev);
+
 err_qp_table_free:
 	mlx4_cleanup_qp_table(dev);
 
@@ -780,14 +928,37 @@ no_msi:
 		priv->eq_table.eq[i].irq = dev->pdev->irq;
 }
 
-static void mlx4_init_port_info(struct mlx4_dev *dev, int port)
+static int mlx4_init_port_info(struct mlx4_dev *dev, int port)
 {
 	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+	int err = 0;
 
 	info->dev = dev;
 	info->port = port;
 	mlx4_init_mac_table(dev, &info->mac_table);
 	mlx4_init_vlan_table(dev, &info->vlan_table);
+
+	sprintf(info->dev_name, "mlx4_port%d", port);
+	info->port_attr.attr.name = info->dev_name;
+	info->port_attr.attr.mode = S_IRUGO | S_IWUSR;
+	info->port_attr.show      = show_port_type;
+	info->port_attr.store     = set_port_type;
+
+	err = device_create_file(&dev->pdev->dev, &info->port_attr);
+	if (err) {
+		mlx4_err(dev, "Failed to create file for port %d\n", port);
+		info->port = -1;
+	}
+
+	return err;
+}
+
+static void mlx4_cleanup_port_info(struct mlx4_port_info *info)
+{
+	if (info->port < 0)
+		return;
+
+	device_remove_file(&info->dev->pdev->dev, &info->port_attr);
 }
 
 static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -870,6 +1041,8 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	INIT_LIST_HEAD(&priv->ctx_list);
 	spin_lock_init(&priv->ctx_lock);
 
+	mutex_init(&priv->port_mutex);
+
 	INIT_LIST_HEAD(&priv->pgdir_list);
 	mutex_init(&priv->pgdir_mutex);
 
@@ -905,18 +1078,24 @@ static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_close;
 
-	for (port = 1; port <= dev->caps.num_ports; port++)
-		mlx4_init_port_info(dev, port);
+	for (port = 1; port <= dev->caps.num_ports; port++) {
+		err = mlx4_init_port_info(dev, port);
+		if (err)
+			goto err_port;
+	}
 
 	err = mlx4_register_device(dev);
 	if (err)
-		goto err_cleanup;
+		goto err_port;
 
 	pci_set_drvdata(pdev, dev);
 
 	return 0;
 
-err_cleanup:
+err_port:
+	for (port = 1; port <= dev->caps.num_ports; port++)
+		mlx4_cleanup_port_info(&priv->port[port]);
+
 	mlx4_cleanup_mcg_table(dev);
 	mlx4_cleanup_qp_table(dev);
 	mlx4_cleanup_srq_table(dev);
@@ -973,8 +1152,10 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	if (dev) {
 		mlx4_unregister_device(dev);
 
-		for (p = 1; p <= dev->caps.num_ports; ++p)
+		for (p = 1; p <= dev->caps.num_ports; p++) {
+			mlx4_cleanup_port_info(&priv->port[p]);
 			mlx4_CLOSE_PORT(dev, p);
+		}
 
 		mlx4_cleanup_mcg_table(dev);
 		mlx4_cleanup_qp_table(dev);
@@ -1026,10 +1207,28 @@ static struct pci_driver mlx4_driver = {
 	.remove		= __devexit_p(mlx4_remove_one)
 };
 
+static int __init mlx4_verify_params(void)
+{
+	if ((log_num_mac < 0) || (log_num_mac > 7)) {
+		printk(KERN_WARNING "mlx4_core: bad num_mac: %d\n", log_num_mac);
+		return -1;
+	}
+
+	if ((log_num_vlan < 0) || (log_num_vlan > 7)) {
+		printk(KERN_WARNING "mlx4_core: bad num_vlan: %d\n", log_num_vlan);
+		return -1;
+	}
+
+	return 0;
+}
+
 static int __init mlx4_init(void)
 {
 	int ret;
 
+	if (mlx4_verify_params())
+		return -EINVAL;
+
 	ret = mlx4_catas_init();
 	if (ret)
 		return ret;
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index 23309f381ee3..fa431fad0eec 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -277,6 +277,9 @@ struct mlx4_vlan_table {
 struct mlx4_port_info {
 	struct mlx4_dev	       *dev;
 	int			port;
+	char			dev_name[16];
+	struct device_attribute port_attr;
+	enum mlx4_port_type	tmp_type;
 	struct mlx4_mac_table	mac_table;
 	struct mlx4_vlan_table	vlan_table;
 };
@@ -310,6 +313,7 @@ struct mlx4_priv {
 	struct mlx4_uar		driver_uar;
 	void __iomem	       *kar;
 	struct mlx4_port_info	port[MLX4_MAX_PORTS + 1];
+	struct mutex		port_mutex;
 };
 
 static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
@@ -383,4 +387,6 @@ void mlx4_handle_catas_err(struct mlx4_dev *dev);
 void mlx4_init_mac_table(struct mlx4_dev *dev, struct mlx4_mac_table *table);
 void mlx4_init_vlan_table(struct mlx4_dev *dev, struct mlx4_vlan_table *table);
 
+int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port);
+
 #endif /* MLX4_H */
diff --git a/drivers/net/mlx4/port.c b/drivers/net/mlx4/port.c
index 8644f3d978ee..e2fdab42c4ce 100644
--- a/drivers/net/mlx4/port.c
+++ b/drivers/net/mlx4/port.c
@@ -257,3 +257,26 @@ out:
 	mutex_unlock(&table->mutex);
 }
 EXPORT_SYMBOL_GPL(mlx4_unregister_vlan);
+
+int mlx4_SET_PORT(struct mlx4_dev *dev, u8 port)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	int err;
+	u8 is_eth = dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+
+	memset(mailbox->buf, 0, 256);
+	if (is_eth) {
+		((u8 *) mailbox->buf)[3] = 6;
+		((__be16 *) mailbox->buf)[4] = cpu_to_be16(1 << 15);
+		((__be16 *) mailbox->buf)[6] = cpu_to_be16(1 << 15);
+	}
+	err = mlx4_cmd(dev, mailbox->dma, port, is_eth, MLX4_CMD_SET_PORT,
+		       MLX4_CMD_TIME_CLASS_B);
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 1951fe70a251..bd9977b89490 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -60,6 +60,7 @@ enum {
 	MLX4_DEV_CAP_FLAG_IPOIB_CSUM	= 1 <<  7,
 	MLX4_DEV_CAP_FLAG_BAD_PKEY_CNTR	= 1 <<  8,
 	MLX4_DEV_CAP_FLAG_BAD_QKEY_CNTR	= 1 <<  9,
+	MLX4_DEV_CAP_FLAG_DPDP		= 1 << 12,
 	MLX4_DEV_CAP_FLAG_MEM_WINDOW	= 1 << 16,
 	MLX4_DEV_CAP_FLAG_APM		= 1 << 17,
 	MLX4_DEV_CAP_FLAG_ATOMIC	= 1 << 18,
@@ -153,6 +154,11 @@ enum mlx4_qp_region {
 	MLX4_NUM_QP_REGION
 };
 
+enum mlx4_port_type {
+	MLX4_PORT_TYPE_IB	= 1 << 0,
+	MLX4_PORT_TYPE_ETH	= 1 << 1,
+};
+
 enum mlx4_special_vlan_idx {
 	MLX4_NO_VLAN_IDX        = 0,
 	MLX4_VLAN_MISS_IDX,
@@ -226,6 +232,9 @@ struct mlx4_caps {
 	int                     log_num_macs;
 	int                     log_num_vlans;
 	int                     log_num_prios;
+	enum mlx4_port_type	port_type[MLX4_MAX_PORTS + 1];
+	u8			supported_type[MLX4_MAX_PORTS + 1];
+	u32			port_mask;
 };
 
 struct mlx4_buf_list {
@@ -380,6 +389,11 @@ struct mlx4_init_port_param {
 	u64			si_guid;
 };
 
+#define mlx4_foreach_port(port, dev, type)				\
+	for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++)	\
+		if (((type) == MLX4_PORT_TYPE_IB ? (dev)->caps.port_mask : \
+		     ~(dev)->caps.port_mask) & 1 << ((port) - 1))
+
 int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 		   struct mlx4_buf *buf);
 void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf);
-- 
cgit v1.2.3


From 8dd7f8036c123296fc4214f9d8810eb485570422 Mon Sep 17 00:00:00 2001
From: Sheng Yang <sheng@linux.intel.com>
Date: Tue, 21 Oct 2008 17:38:25 +0800
Subject: PCI: add support for function level reset

Sometimes, it's necessary to enable software's ability to quiesce and
reset endpoint hardware with function-level granularity, so provide
support for it.

The patch implement Function Level Reset(FLR) feature following PCI-e
spec. And this is the first step. We would add more generic method, like
D0/D3, to allow more devices support this function.

The patch contains two functions. pcie_reset_function() is the new
driver API, and, contains some action to quiesce a device.  The other
function is a helper:  pcie_execute_reset_function() just executes the
reset for a particular device function.

Current the usage model is in KVM. Function reset is necessary for
assigning device to a guest, or moving it between partitions.

For Function Level Reset(FLR), please refer to PCI Express spec chapter
6.6.2.

Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/pci/pci.c        | 98 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pci.h      |  2 +
 include/linux/pci_regs.h |  2 +
 3 files changed, 102 insertions(+)

(limited to 'include')

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index aee73cf251b6..533aeb5fcbe4 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -18,6 +18,7 @@
 #include <linux/log2.h>
 #include <linux/pci-aspm.h>
 #include <linux/pm_wakeup.h>
+#include <linux/interrupt.h>
 #include <asm/dma.h>	/* isa_dma_bridge_buggy */
 #include "pci.h"
 
@@ -1745,6 +1746,103 @@ int pci_set_dma_seg_boundary(struct pci_dev *dev, unsigned long mask)
 EXPORT_SYMBOL(pci_set_dma_seg_boundary);
 #endif
 
+/**
+ * pci_execute_reset_function() - Reset a PCI device function
+ * @dev: Device function to reset
+ *
+ * Some devices allow an individual function to be reset without affecting
+ * other functions in the same device.  The PCI device must be responsive
+ * to PCI config space in order to use this function.
+ *
+ * The device function is presumed to be unused when this function is called.
+ * Resetting the device will make the contents of PCI configuration space
+ * random, so any caller of this must be prepared to reinitialise the
+ * device including MSI, bus mastering, BARs, decoding IO and memory spaces,
+ * etc.
+ *
+ * Returns 0 if the device function was successfully reset or -ENOTTY if the
+ * device doesn't support resetting a single function.
+ */
+int pci_execute_reset_function(struct pci_dev *dev)
+{
+	u16 status;
+	u32 cap;
+	int exppos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+
+	if (!exppos)
+		return -ENOTTY;
+	pci_read_config_dword(dev, exppos + PCI_EXP_DEVCAP, &cap);
+	if (!(cap & PCI_EXP_DEVCAP_FLR))
+		return -ENOTTY;
+
+	pci_block_user_cfg_access(dev);
+
+	/* Wait for Transaction Pending bit clean */
+	msleep(100);
+	pci_read_config_word(dev, exppos + PCI_EXP_DEVSTA, &status);
+	if (status & PCI_EXP_DEVSTA_TRPND) {
+		dev_info(&dev->dev, "Busy after 100ms while trying to reset; "
+			"sleeping for 1 second\n");
+		ssleep(1);
+		pci_read_config_word(dev, exppos + PCI_EXP_DEVSTA, &status);
+		if (status & PCI_EXP_DEVSTA_TRPND)
+			dev_info(&dev->dev, "Still busy after 1s; "
+				"proceeding with reset anyway\n");
+	}
+
+	pci_write_config_word(dev, exppos + PCI_EXP_DEVCTL,
+				PCI_EXP_DEVCTL_BCR_FLR);
+	mdelay(100);
+
+	pci_unblock_user_cfg_access(dev);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_execute_reset_function);
+
+/**
+ * pci_reset_function() - quiesce and reset a PCI device function
+ * @dev: Device function to reset
+ *
+ * Some devices allow an individual function to be reset without affecting
+ * other functions in the same device.  The PCI device must be responsive
+ * to PCI config space in order to use this function.
+ *
+ * This function does not just reset the PCI portion of a device, but
+ * clears all the state associated with the device.  This function differs
+ * from pci_execute_reset_function in that it saves and restores device state
+ * over the reset.
+ *
+ * Returns 0 if the device function was successfully reset or -ENOTTY if the
+ * device doesn't support resetting a single function.
+ */
+int pci_reset_function(struct pci_dev *dev)
+{
+	u32 cap;
+	int exppos = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	int r;
+
+	if (!exppos)
+		return -ENOTTY;
+	pci_read_config_dword(dev, exppos + PCI_EXP_DEVCAP, &cap);
+	if (!(cap & PCI_EXP_DEVCAP_FLR))
+		return -ENOTTY;
+
+	if (!dev->msi_enabled && !dev->msix_enabled)
+		disable_irq(dev->irq);
+	pci_save_state(dev);
+
+	pci_write_config_word(dev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
+
+	r = pci_execute_reset_function(dev);
+
+	pci_restore_state(dev);
+	if (!dev->msi_enabled && !dev->msix_enabled)
+		enable_irq(dev->irq);
+
+	return r;
+}
+EXPORT_SYMBOL_GPL(pci_reset_function);
+
 /**
  * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count
  * @dev: PCI device to query
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 085187be29c7..f6f6810296e6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -626,6 +626,8 @@ int pcix_get_mmrbc(struct pci_dev *dev);
 int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc);
 int pcie_get_readrq(struct pci_dev *dev);
 int pcie_set_readrq(struct pci_dev *dev, int rq);
+int pci_reset_function(struct pci_dev *dev);
+int pci_execute_reset_function(struct pci_dev *dev);
 void pci_update_resource(struct pci_dev *dev, struct resource *res, int resno);
 int __must_check pci_assign_resource(struct pci_dev *dev, int i);
 int pci_select_bars(struct pci_dev *dev, unsigned long flags);
diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h
index eb6686b88f9a..e5effd47ed74 100644
--- a/include/linux/pci_regs.h
+++ b/include/linux/pci_regs.h
@@ -377,6 +377,7 @@
 #define  PCI_EXP_DEVCAP_RBER	0x8000	/* Role-Based Error Reporting */
 #define  PCI_EXP_DEVCAP_PWR_VAL	0x3fc0000 /* Slot Power Limit Value */
 #define  PCI_EXP_DEVCAP_PWR_SCL	0xc000000 /* Slot Power Limit Scale */
+#define  PCI_EXP_DEVCAP_FLR     0x10000000 /* Function Level Reset */
 #define PCI_EXP_DEVCTL		8	/* Device Control */
 #define  PCI_EXP_DEVCTL_CERE	0x0001	/* Correctable Error Reporting En. */
 #define  PCI_EXP_DEVCTL_NFERE	0x0002	/* Non-Fatal Error Reporting Enable */
@@ -389,6 +390,7 @@
 #define  PCI_EXP_DEVCTL_AUX_PME	0x0400	/* Auxiliary Power PM Enable */
 #define  PCI_EXP_DEVCTL_NOSNOOP_EN 0x0800  /* Enable No Snoop */
 #define  PCI_EXP_DEVCTL_READRQ	0x7000	/* Max_Read_Request_Size */
+#define  PCI_EXP_DEVCTL_BCR_FLR 0x8000  /* Bridge Configuration Retry / FLR */
 #define PCI_EXP_DEVSTA		10	/* Device Status */
 #define  PCI_EXP_DEVSTA_CED	0x01	/* Correctable Error Detected */
 #define  PCI_EXP_DEVSTA_NFED	0x02	/* Non-Fatal Error Detected */
-- 
cgit v1.2.3


From 64c7f63c1b5c26f057c26f7920f397fed2f590d9 Mon Sep 17 00:00:00 2001
From: Jesse Barnes <jbarnes@virtuousgeek.org>
Date: Tue, 21 Oct 2008 10:09:05 -0700
Subject: PCI: include io.h in pci.h so that ioremap_nocache is defined

Ingo pointed out that the m32r build was broken by pci_ioremap.  It looks like
some files include pci.h w/o including io.h.  The latter defines ioremap_* if
present, so it makes sense to include it in pci.h now that we have pci_ioremap
there.

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 include/linux/pci.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index f6f6810296e6..ee2fd6304e05 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -18,6 +18,7 @@
 #define LINUX_PCI_H
 
 #include <linux/pci_regs.h>	/* The pci register defines */
+#include <linux/io.h>
 
 /*
  * The PCI interface treats multi-function devices as independent
-- 
cgit v1.2.3


From 1359f2701b96abd9bb69c1273fb995a093b6409a Mon Sep 17 00:00:00 2001
From: Alex Chiang <achiang@hp.com>
Date: Mon, 20 Oct 2008 17:40:42 -0600
Subject: PCI Hotplug core: add 'name' param pci_hp_register interface

Update pci_hp_register() to take a const char *name parameter.

The motivation for this is to clean up the individual hotplug
drivers so that each one does not have to manage its own name.
The PCI core should be the place where we manage the name.

We update the interface and all callsites first, in a
"no functional change" manner, and clean up the drivers later.

Cc: kristen.c.accardi@intel.com
Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Reviewed-by: Matthew Wilcox <willy@linux.intel.com>
Signed-off-by: Alex Chiang <achiang@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/pci/hotplug/acpiphp_core.c      |  3 ++-
 drivers/pci/hotplug/cpci_hotplug_core.c |  3 ++-
 drivers/pci/hotplug/cpqphp_core.c       |  3 ++-
 drivers/pci/hotplug/fakephp.c           |  3 ++-
 drivers/pci/hotplug/ibmphp_ebda.c       |  3 ++-
 drivers/pci/hotplug/pci_hotplug_core.c  | 15 ++++++++-------
 drivers/pci/hotplug/pciehp_core.c       |  3 ++-
 drivers/pci/hotplug/rpaphp_slot.c       |  2 +-
 drivers/pci/hotplug/sgi_hotplug.c       |  3 ++-
 drivers/pci/hotplug/shpchp_core.c       |  3 ++-
 include/linux/pci_hotplug.h             |  3 ++-
 11 files changed, 27 insertions(+), 17 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c
index 0e496e866a84..e9841765339f 100644
--- a/drivers/pci/hotplug/acpiphp_core.c
+++ b/drivers/pci/hotplug/acpiphp_core.c
@@ -340,7 +340,8 @@ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot)
 
 	retval = pci_hp_register(slot->hotplug_slot,
 					acpiphp_slot->bridge->pci_bus,
-					acpiphp_slot->device);
+					acpiphp_slot->device,
+					slot->name);
 	if (retval == -EBUSY)
 		goto error_hpslot;
 	if (retval) {
diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c
index 935947991dc9..5e5dee85763c 100644
--- a/drivers/pci/hotplug/cpci_hotplug_core.c
+++ b/drivers/pci/hotplug/cpci_hotplug_core.c
@@ -285,7 +285,8 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last)
 		info->attention_status = cpci_get_attention_status(slot);
 
 		dbg("registering slot %s", slot->hotplug_slot->name);
-		status = pci_hp_register(slot->hotplug_slot, bus, i);
+		status = pci_hp_register(slot->hotplug_slot, bus, i,
+					 slot->hotplug_slot->name);
 		if (status) {
 			err("pci_hp_register failed with error %d", status);
 			goto error_name;
diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c
index 54defec51d08..a7fe4584f00b 100644
--- a/drivers/pci/hotplug/cpqphp_core.c
+++ b/drivers/pci/hotplug/cpqphp_core.c
@@ -436,7 +436,8 @@ static int ctrl_slot_setup(struct controller *ctrl,
 				slot_number);
 		result = pci_hp_register(hotplug_slot,
 					 ctrl->pci_dev->subordinate,
-					 slot->device);
+					 slot->device,
+					 hotplug_slot->name);
 		if (result) {
 			err("pci_hp_register failed with error %d\n", result);
 			goto error_name;
diff --git a/drivers/pci/hotplug/fakephp.c b/drivers/pci/hotplug/fakephp.c
index 146ca9cd1567..3069f2153832 100644
--- a/drivers/pci/hotplug/fakephp.c
+++ b/drivers/pci/hotplug/fakephp.c
@@ -126,7 +126,8 @@ static int add_slot(struct pci_dev *dev)
 	slot->release = &dummy_release;
 	slot->private = dslot;
 
-	retval = pci_hp_register(slot, dev->bus, PCI_SLOT(dev->devfn));
+	retval = pci_hp_register(slot, dev->bus, PCI_SLOT(dev->devfn),
+				 slot->name);
 	if (retval) {
 		err("pci_hp_register failed with error %d\n", retval);
 		goto error_dslot;
diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c
index 8cfd1c4926c8..342d3e8f77c8 100644
--- a/drivers/pci/hotplug/ibmphp_ebda.c
+++ b/drivers/pci/hotplug/ibmphp_ebda.c
@@ -966,7 +966,8 @@ static int __init ebda_rsrc_controller (void)
 	list_for_each_entry(tmp_slot, &ibmphp_slot_head, ibm_slot_list) {
 		snprintf (tmp_slot->hotplug_slot->name, 30, "%s", create_file_name (tmp_slot));
 		pci_hp_register(tmp_slot->hotplug_slot,
-			pci_find_bus(0, tmp_slot->bus), tmp_slot->device);
+			pci_find_bus(0, tmp_slot->bus), tmp_slot->device,
+			tmp_slot->hotplug_slot->name);
 	}
 
 	print_ebda_hpc ();
diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index 2e6c4474644e..02b1ae12a2e6 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -547,13 +547,15 @@ out:
  * @bus: bus this slot is on
  * @slot: pointer to the &struct hotplug_slot to register
  * @slot_nr: slot number
+ * @name: name registered with kobject core
  *
  * Registers a hotplug slot with the pci hotplug subsystem, which will allow
  * userspace interaction to the slot.
  *
  * Returns 0 if successful, anything else for an error.
  */
-int pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus, int slot_nr)
+int pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus, int slot_nr,
+			const char *name)
 {
 	int result;
 	struct pci_slot *pci_slot;
@@ -569,7 +571,7 @@ int pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus, int slot_nr)
 	}
 
 	/* Check if we have already registered a slot with the same name. */
-	if (get_slot_from_name(slot->name))
+	if (get_slot_from_name(name))
 		return -EEXIST;
 
 	/*
@@ -577,7 +579,7 @@ int pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus, int slot_nr)
 	 * driver and call it here again. If we've already created the
 	 * pci_slot, the interface will simply bump the refcount.
 	 */
-	pci_slot = pci_create_slot(bus, slot_nr, slot->name);
+	pci_slot = pci_create_slot(bus, slot_nr, name);
 	if (IS_ERR(pci_slot))
 		return PTR_ERR(pci_slot);
 
@@ -593,8 +595,8 @@ int pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus, int slot_nr)
 	/*
 	 * Allow pcihp drivers to override the ACPI_PCI_SLOT name.
 	 */
-	if (strcmp(kobject_name(&pci_slot->kobj), slot->name)) {
-		result = kobject_rename(&pci_slot->kobj, slot->name);
+	if (strcmp(kobject_name(&pci_slot->kobj), name)) {
+		result = kobject_rename(&pci_slot->kobj, name);
 		if (result) {
 			pci_destroy_slot(pci_slot);
 			return result;
@@ -607,8 +609,7 @@ int pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus, int slot_nr)
 
 	result = fs_add_slot(pci_slot);
 	kobject_uevent(&pci_slot->kobj, KOBJ_ADD);
-	dbg("Added slot %s to the list\n", slot->name);
-
+	dbg("Added slot %s to the list\n", name);
 
 	return result;
 }
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index c748a19db89d..3ace5e057601 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -226,7 +226,8 @@ static int init_slots(struct controller *ctrl)
 duplicate_name:
 		retval = pci_hp_register(hotplug_slot,
 					 ctrl->pci_dev->subordinate,
-					 slot->device);
+					 slot->device,
+					 slot->name);
 		if (retval) {
 			/*
 			 * If slot N already exists, we'll try to create
diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c
index 50884507b8be..736d3b43ed0b 100644
--- a/drivers/pci/hotplug/rpaphp_slot.c
+++ b/drivers/pci/hotplug/rpaphp_slot.c
@@ -137,7 +137,7 @@ int rpaphp_register_slot(struct slot *slot)
 		slotno = PCI_SLOT(PCI_DN(slot->dn->child)->devfn);
 	else
 		slotno = -1;
-	retval = pci_hp_register(php_slot, slot->bus, slotno);
+	retval = pci_hp_register(php_slot, slot->bus, slotno, slot->name);
 	if (retval) {
 		err("pci_hp_register failed with error %d\n", retval);
 		return retval;
diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c
index 410fe0394a8e..6d20bbd4359a 100644
--- a/drivers/pci/hotplug/sgi_hotplug.c
+++ b/drivers/pci/hotplug/sgi_hotplug.c
@@ -653,7 +653,8 @@ static int sn_hotplug_slot_register(struct pci_bus *pci_bus)
 		bss_hotplug_slot->ops = &sn_hotplug_slot_ops;
 		bss_hotplug_slot->release = &sn_release_slot;
 
-		rc = pci_hp_register(bss_hotplug_slot, pci_bus, device);
+		rc = pci_hp_register(bss_hotplug_slot, pci_bus, device,
+				     bss_hotplug_slot->name);
 		if (rc)
 			goto register_err;
 
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index cc38615395f1..bf5096612aab 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -146,7 +146,8 @@ static int init_slots(struct controller *ctrl)
 		    slot->hp_slot, slot->number, ctrl->slot_device_offset);
 duplicate_name:
 		retval = pci_hp_register(slot->hotplug_slot,
-				ctrl->pci_dev->subordinate, slot->device);
+				ctrl->pci_dev->subordinate, slot->device,
+				hotplug_slot->name);
 		if (retval) {
 			/*
 			 * If slot N already exists, we'll try to create
diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h
index a08cd06b541a..5efba6671865 100644
--- a/include/linux/pci_hotplug.h
+++ b/include/linux/pci_hotplug.h
@@ -165,7 +165,8 @@ struct hotplug_slot {
 };
 #define to_hotplug_slot(n) container_of(n, struct hotplug_slot, kobj)
 
-extern int pci_hp_register(struct hotplug_slot *, struct pci_bus *, int nr);
+extern int pci_hp_register(struct hotplug_slot *, struct pci_bus *, int nr,
+			   const char *name);
 extern int pci_hp_deregister(struct hotplug_slot *slot);
 extern int __must_check pci_hp_change_slot_info	(struct hotplug_slot *slot,
 						 struct hotplug_slot_info *info);
-- 
cgit v1.2.3


From d25b7c8d6ba2735602003d75a28894772fe8ad6a Mon Sep 17 00:00:00 2001
From: Alex Chiang <achiang@hp.com>
Date: Mon, 20 Oct 2008 17:40:47 -0600
Subject: PCI: rename pci_update_slot_number to pci_renumber_slot

The GPL exported symbol pci_update_slot_number has been renamed to
pci_renumber_slot. Some of the safety checks were unnecessary and
were removed.

Cc: kristen.c.accardi@intel.com
Cc: matthew@wil.cx
Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: Alex Chiang <achiang@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/pci/slot.c  | 15 +++++----------
 include/linux/pci.h |  2 +-
 2 files changed, 6 insertions(+), 11 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index 0c6db03698ea..b9b90ab6b861 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -175,7 +175,7 @@ placeholder:
 EXPORT_SYMBOL_GPL(pci_create_slot);
 
 /**
- * pci_update_slot_number - update %struct pci_slot -> number
+ * pci_renumber_slot - update %struct pci_slot -> number
  * @slot - %struct pci_slot to update
  * @slot_nr - new number for slot
  *
@@ -183,27 +183,22 @@ EXPORT_SYMBOL_GPL(pci_create_slot);
  * created a placeholder slot in pci_create_slot() by passing a -1 as
  * slot_nr, to update their %struct pci_slot with the correct @slot_nr.
  */
-
-void pci_update_slot_number(struct pci_slot *slot, int slot_nr)
+void pci_renumber_slot(struct pci_slot *slot, int slot_nr)
 {
-	int name_count = 0;
 	struct pci_slot *tmp;
 
 	down_write(&pci_bus_sem);
 
 	list_for_each_entry(tmp, &slot->bus->slots, list) {
 		WARN_ON(tmp->number == slot_nr);
-		if (!strcmp(kobject_name(&tmp->kobj), kobject_name(&slot->kobj)))
-			name_count++;
+		goto out;
 	}
 
-	if (name_count > 1)
-		printk(KERN_WARNING "pci_update_slot_number found %d slots with the same name: %s\n", name_count, kobject_name(&slot->kobj));
-
 	slot->number = slot_nr;
+out:
 	up_write(&pci_bus_sem);
 }
-EXPORT_SYMBOL_GPL(pci_update_slot_number);
+EXPORT_SYMBOL_GPL(pci_renumber_slot);
 
 /**
  * pci_destroy_slot - decrement refcount for physical PCI slot
diff --git a/include/linux/pci.h b/include/linux/pci.h
index ee2fd6304e05..41717ae9807e 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -512,7 +512,7 @@ struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev,
 struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
 				 const char *name);
 void pci_destroy_slot(struct pci_slot *slot);
-void pci_update_slot_number(struct pci_slot *slot, int slot_nr);
+void pci_renumber_slot(struct pci_slot *slot, int slot_nr);
 int pci_scan_slot(struct pci_bus *bus, int devfn);
 struct pci_dev *pci_scan_single_device(struct pci_bus *bus, int devfn);
 void pci_device_add(struct pci_dev *dev, struct pci_bus *bus);
-- 
cgit v1.2.3


From 828f37683e6d3ab5912989df0d04201db7ad798e Mon Sep 17 00:00:00 2001
From: Alex Chiang <achiang@hp.com>
Date: Mon, 20 Oct 2008 17:40:52 -0600
Subject: PCI: update pci_create_slot() to take a 'hotplug' param

Slot detection drivers can co-exist with hotplug drivers. The names
of the detected/claimed slots may be different depending on module
load order.

For legacy reasons, we need to allow hotplug drivers to override
the slot name if a detection driver is loaded first (and they find
the same slots).

Creating and overriding slot names should be an atomic operation,
otherwise you get a locking nightmare as various drivers race to
call pci_create_slot().

pci_create_slot() is already serialized by grabbing the pci_bus_sem.

We update the API and add a 'hotplug' param, which is:

	set if the caller is a hotplug driver
	NULL if the caller is a detection driver

pci_create_slot() does not actually use the 'hotplug' parameter in this
patch. A later patch will add the logic that uses it.

Cc: kristen.c.accardi@intel.com
Cc: matthew@wil.cx
Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: Alex Chiang <achiang@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/acpi/pci_slot.c                | 2 +-
 drivers/pci/hotplug/pci_hotplug_core.c | 2 +-
 drivers/pci/slot.c                     | 4 +++-
 include/linux/pci.h                    | 3 ++-
 4 files changed, 7 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/pci_slot.c b/drivers/acpi/pci_slot.c
index d5b4ef898879..8d4a568be1cc 100644
--- a/drivers/acpi/pci_slot.c
+++ b/drivers/acpi/pci_slot.c
@@ -150,7 +150,7 @@ register_slot(acpi_handle handle, u32 lvl, void *context, void **rv)
 	}
 
 	snprintf(name, sizeof(name), "%u", (u32)sun);
-	pci_slot = pci_create_slot(pci_bus, device, name);
+	pci_slot = pci_create_slot(pci_bus, device, name, NULL);
 	if (IS_ERR(pci_slot)) {
 		err("pci_create_slot returned %ld\n", PTR_ERR(pci_slot));
 		kfree(slot);
diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index 02b1ae12a2e6..1cdeb642fdcf 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -579,7 +579,7 @@ int pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus, int slot_nr,
 	 * driver and call it here again. If we've already created the
 	 * pci_slot, the interface will simply bump the refcount.
 	 */
-	pci_slot = pci_create_slot(bus, slot_nr, name);
+	pci_slot = pci_create_slot(bus, slot_nr, name, slot);
 	if (IS_ERR(pci_slot))
 		return PTR_ERR(pci_slot);
 
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index b9b90ab6b861..0e009c3ba5fd 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -83,6 +83,7 @@ static struct kobj_type pci_slot_ktype = {
  * @parent: struct pci_bus of parent bridge
  * @slot_nr: PCI_SLOT(pci_dev->devfn) or -1 for placeholder
  * @name: user visible string presented in /sys/bus/pci/slots/<name>
+ * @hotplug: set if caller is hotplug driver, NULL otherwise
  *
  * PCI slots have first class attributes such as address, speed, width,
  * and a &struct pci_slot is used to manage them. This interface will
@@ -111,7 +112,8 @@ static struct kobj_type pci_slot_ktype = {
  */
 
 struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
-				 const char *name)
+				 const char *name,
+				 struct hotplug_slot *hotplug)
 {
 	struct pci_dev *dev;
 	struct pci_slot *slot;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 41717ae9807e..9a8cee623301 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -510,7 +510,8 @@ struct pci_bus *pci_create_bus(struct device *parent, int bus,
 struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev,
 				int busnr);
 struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr,
-				 const char *name);
+				 const char *name,
+				 struct hotplug_slot *hotplug);
 void pci_destroy_slot(struct pci_slot *slot);
 void pci_renumber_slot(struct pci_slot *slot, int slot_nr);
 int pci_scan_slot(struct pci_bus *bus, int devfn);
-- 
cgit v1.2.3


From 0ad772ec464d3fcf9d210836b97e654f393606c4 Mon Sep 17 00:00:00 2001
From: Alex Chiang <achiang@hp.com>
Date: Mon, 20 Oct 2008 17:41:07 -0600
Subject: PCI, PCI Hotplug: introduce slot_name helpers

In preparation for cleaning up the various hotplug drivers
such that they don't have to manage their own 'name' parameters
anymore, we provide the following convenience functions:

	pci_slot_name()
	hotplug_slot_name()

These helpers will be used by individual hotplug drivers.

Cc: kristen.c.accardi@intel.com
Cc: matthew@wil.cx
Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: Alex Chiang <achiang@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/pci/slot.c          | 2 +-
 include/linux/pci.h         | 5 +++++
 include/linux/pci_hotplug.h | 5 +++++
 3 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index b6ee352ae459..4dd1c3e157ae 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -121,7 +121,7 @@ static int rename_slot(struct pci_slot *slot, const char *name)
 	int result = 0;
 	char *slot_name;
 
-	if (strcmp(kobject_name(&slot->kobj), name) == 0)
+	if (strcmp(pci_slot_name(slot), name) == 0)
 		return result;
 
 	slot_name = make_slot_name(name);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 9a8cee623301..955ab705c05e 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -65,6 +65,11 @@ struct pci_slot {
 	struct kobject kobj;
 };
 
+static inline const char *pci_slot_name(const struct pci_slot *slot)
+{
+	return kobject_name(&slot->kobj);
+}
+
 /* File state for mmap()s on /proc/bus/pci/X/Y */
 enum pci_mmap_state {
 	pci_mmap_io,
diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h
index 5efba6671865..a3a3245943b1 100644
--- a/include/linux/pci_hotplug.h
+++ b/include/linux/pci_hotplug.h
@@ -165,6 +165,11 @@ struct hotplug_slot {
 };
 #define to_hotplug_slot(n) container_of(n, struct hotplug_slot, kobj)
 
+static inline const char *hotplug_slot_name(const struct hotplug_slot *slot)
+{
+	return pci_slot_name(slot->pci_slot);
+}
+
 extern int pci_hp_register(struct hotplug_slot *, struct pci_bus *, int nr,
 			   const char *name);
 extern int pci_hp_deregister(struct hotplug_slot *slot);
-- 
cgit v1.2.3


From 58319b802a614f10f1b5238fbde7a4b2e9a60069 Mon Sep 17 00:00:00 2001
From: Alex Chiang <achiang@hp.com>
Date: Mon, 20 Oct 2008 17:41:58 -0600
Subject: PCI: Hotplug core: remove 'name'

Now that the PCI core manages the 'name' for each individual
hotplug driver, and all drivers (except rpaphp) have been converted
to use hotplug_slot_name(), there is no need for the PCI hotplug
core to drag around its own copy of name either.

Cc: kristen.c.accardi@intel.com
Cc: matthew@wil.cx
Acked-by: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
Signed-off-by: Alex Chiang <achiang@hp.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/pci/hotplug/pci_hotplug_core.c | 6 +++---
 include/linux/pci_hotplug.h            | 3 ---
 2 files changed, 3 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index a6f1f282b683..535fce0f07f9 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -533,7 +533,7 @@ static struct hotplug_slot *get_slot_from_name (const char *name)
 
 	list_for_each (tmp, &pci_hotplug_slot_list) {
 		slot = list_entry (tmp, struct hotplug_slot, slot_list);
-		if (strcmp(slot->name, name) == 0)
+		if (strcmp(hotplug_slot_name(slot), name) == 0)
 			return slot;
 	}
 	return NULL;
@@ -611,7 +611,7 @@ int pci_hp_deregister(struct hotplug_slot *hotplug)
 		return -ENODEV;
 
 	mutex_lock(&pci_hp_mutex);
-	temp = get_slot_from_name(hotplug->name);
+	temp = get_slot_from_name(hotplug_slot_name(hotplug));
 	if (temp != hotplug) {
 		mutex_unlock(&pci_hp_mutex);
 		return -ENODEV;
@@ -621,7 +621,7 @@ int pci_hp_deregister(struct hotplug_slot *hotplug)
 
 	slot = hotplug->pci_slot;
 	fs_remove_slot(slot);
-	dbg("Removed slot %s from the list\n", hotplug->name);
+	dbg("Removed slot %s from the list\n", hotplug_slot_name(hotplug));
 
 	hotplug->release(hotplug);
 	slot->hotplug = NULL;
diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h
index a3a3245943b1..a00bd1a0f156 100644
--- a/include/linux/pci_hotplug.h
+++ b/include/linux/pci_hotplug.h
@@ -142,8 +142,6 @@ struct hotplug_slot_info {
 
 /**
  * struct hotplug_slot - used to register a physical slot with the hotplug pci core
- * @name: the name of the slot being registered.  This string must
- * be unique amoung slots registered on this system.
  * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot
  * @info: pointer to the &struct hotplug_slot_info for the initial values for
  * this slot.
@@ -153,7 +151,6 @@ struct hotplug_slot_info {
  * needs.
  */
 struct hotplug_slot {
-	char				*name;
 	struct hotplug_slot_ops		*ops;
 	struct hotplug_slot_info	*info;
 	void (*release) (struct hotplug_slot *slot);
-- 
cgit v1.2.3


From 1388cc964e680c1086ca0edae35be094cb29d51e Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Wed, 22 Oct 2008 13:39:55 +1100
Subject: PCI: don't export linux/io.h from pci.h

Move the include of io.h down into the #ifdef __KERNEL__ protected
region.

Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 include/linux/pci.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 955ab705c05e..752def8a2ef4 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -18,7 +18,6 @@
 #define LINUX_PCI_H
 
 #include <linux/pci_regs.h>	/* The pci register defines */
-#include <linux/io.h>
 
 /*
  * The PCI interface treats multi-function devices as independent
@@ -52,6 +51,7 @@
 #include <linux/kobject.h>
 #include <asm/atomic.h>
 #include <linux/device.h>
+#include <linux/io.h>
 
 /* Include the ID list */
 #include <linux/pci_ids.h>
-- 
cgit v1.2.3


From 0b15a3a5285bac2a2caa4ef970410674b6dd2de5 Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Wed, 22 Oct 2008 18:47:40 -0500
Subject: 9p: fix debug build error

Fixes build problem with 9p when building with debug disabled.
Also contains some fixes for warnings which pop up when
CONFIG_NET_9P_DEBUG is disabled.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/9p.h | 2 +-
 net/9p/protocol.c   | 9 +++++++++
 net/9p/trans_fd.c   | 4 +---
 3 files changed, 11 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/net/9p/9p.h b/include/net/9p/9p.h
index d2c60c73619d..b77c1478c99f 100644
--- a/include/net/9p/9p.h
+++ b/include/net/9p/9p.h
@@ -56,9 +56,9 @@ enum p9_debug_flags {
 	P9_DEBUG_PKT =		(1<<10),
 };
 
+#ifdef CONFIG_NET_9P_DEBUG
 extern unsigned int p9_debug_level;
 
-#ifdef CONFIG_NET_9P_DEBUG
 #define P9_DPRINTK(level, format, arg...) \
 do {  \
 	if ((p9_debug_level & level) == level) {\
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 29be52439086..908e79faf48e 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -53,6 +53,7 @@
 static int
 p9pdu_writef(struct p9_fcall *pdu, int optional, const char *fmt, ...);
 
+#ifdef CONFIG_NET_9P_DEBUG
 void
 p9pdu_dump(int way, struct p9_fcall *pdu)
 {
@@ -81,6 +82,12 @@ p9pdu_dump(int way, struct p9_fcall *pdu)
 	else
 		P9_DPRINTK(P9_DEBUG_PKT, "]]](%d) %s\n", datalen, buf);
 }
+#else
+void
+p9pdu_dump(int way, struct p9_fcall *pdu)
+{
+}
+#endif
 EXPORT_SYMBOL(p9pdu_dump);
 
 void p9stat_free(struct p9_wstat *stbuf)
@@ -542,8 +549,10 @@ int p9pdu_finalize(struct p9_fcall *pdu)
 	err = p9pdu_writef(pdu, 0, "d", size);
 	pdu->size = size;
 
+#ifdef CONFIG_NET_9P_DEBUG
 	if ((p9_debug_level & P9_DEBUG_PKT) == P9_DEBUG_PKT)
 		p9pdu_dump(0, pdu);
+#endif
 
 	P9_DPRINTK(P9_DEBUG_9P, ">>> size=%d type: %d tag: %d\n", pdu->size,
 							pdu->id, pdu->tag);
diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c
index be65d8242fd2..1df0356f242b 100644
--- a/net/9p/trans_fd.c
+++ b/net/9p/trans_fd.c
@@ -678,11 +678,9 @@ static int p9_fd_request(struct p9_client *client, struct p9_req_t *req)
 
 static int p9_fd_cancel(struct p9_client *client, struct p9_req_t *req)
 {
-	struct p9_trans_fd *ts = client->trans;
-	struct p9_conn *m = ts->conn;
 	int ret = 1;
 
-	P9_DPRINTK(P9_DEBUG_TRANS, "mux %p req %p\n", m, req);
+	P9_DPRINTK(P9_DEBUG_TRANS, "client %p req %p\n", client, req);
 
 	spin_lock(&client->lock);
 	list_del(&req->req_list);
-- 
cgit v1.2.3


From fc79d4b104f0eb8c2a7242150eaf8756ced4c344 Mon Sep 17 00:00:00 2001
From: Tom Tucker <tom@opengridcomputing.com>
Date: Wed, 22 Oct 2008 18:47:39 -0500
Subject: 9p: rdma: RDMA Transport Support for 9P

This patch implements the RDMA transport provider for 9P. It allows
mounts to be performed over iWARP and IB capable network interfaces.

Signed-off-by: Tom Tucker <tom@opengridcomputing.com>
Signed-off-by: Latchesar Ionkov <lionkov@lanl.gov>
---
 include/net/9p/client.h |   1 +
 net/9p/Kconfig          |   6 +
 net/9p/Makefile         |   4 +
 net/9p/trans_rdma.c     | 712 ++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 723 insertions(+)
 create mode 100644 net/9p/trans_rdma.c

(limited to 'include')

diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index 1f17f3d93727..9fe45b32ce4a 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -206,6 +206,7 @@ int p9_client_wstat(struct p9_fid *fid, struct p9_wstat *wst);
 struct p9_req_t *p9_tag_lookup(struct p9_client *, u16);
 void p9_client_cb(struct p9_client *c, struct p9_req_t *req);
 
+int p9_parse_header(struct p9_fcall *, int32_t *, int8_t *, int16_t *, int);
 int p9stat_read(char *, int, struct p9_wstat *, int);
 void p9stat_free(struct p9_wstat *);
 
diff --git a/net/9p/Kconfig b/net/9p/Kconfig
index ff34c5acc130..c42c0c400bf9 100644
--- a/net/9p/Kconfig
+++ b/net/9p/Kconfig
@@ -20,6 +20,12 @@ config NET_9P_VIRTIO
 	  This builds support for a transports between
 	  guest partitions and a host partition.
 
+config NET_9P_RDMA
+	depends on NET_9P && INFINIBAND && EXPERIMENTAL
+	tristate "9P RDMA Transport (Experimental)"
+	help
+	  This builds support for a RDMA transport.
+
 config NET_9P_DEBUG
 	bool "Debug information"
 	depends on NET_9P
diff --git a/net/9p/Makefile b/net/9p/Makefile
index 1041b7bd12e2..198a640d53a6 100644
--- a/net/9p/Makefile
+++ b/net/9p/Makefile
@@ -1,5 +1,6 @@
 obj-$(CONFIG_NET_9P) := 9pnet.o
 obj-$(CONFIG_NET_9P_VIRTIO) += 9pnet_virtio.o
+obj-$(CONFIG_NET_9P_RDMA) += 9pnet_rdma.o
 
 9pnet-objs := \
 	mod.o \
@@ -11,3 +12,6 @@ obj-$(CONFIG_NET_9P_VIRTIO) += 9pnet_virtio.o
 
 9pnet_virtio-objs := \
 	trans_virtio.o \
+
+9pnet_rdma-objs := \
+	trans_rdma.o \
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
new file mode 100644
index 000000000000..8d6cc4777aae
--- /dev/null
+++ b/net/9p/trans_rdma.c
@@ -0,0 +1,712 @@
+/*
+ * linux/fs/9p/trans_rdma.c
+ *
+ * RDMA transport layer based on the trans_fd.c implementation.
+ *
+ *  Copyright (C) 2008 by Tom Tucker <tom@opengridcomputing.com>
+ *  Copyright (C) 2006 by Russ Cox <rsc@swtch.com>
+ *  Copyright (C) 2004-2005 by Latchesar Ionkov <lucho@ionkov.net>
+ *  Copyright (C) 2004-2008 by Eric Van Hensbergen <ericvh@gmail.com>
+ *  Copyright (C) 1997-2002 by Ron Minnich <rminnich@sarnoff.com>
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License version 2
+ *  as published by the Free Software Foundation.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to:
+ *  Free Software Foundation
+ *  51 Franklin Street, Fifth Floor
+ *  Boston, MA  02111-1301  USA
+ *
+ */
+
+#include <linux/in.h>
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/ipv6.h>
+#include <linux/kthread.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/un.h>
+#include <linux/uaccess.h>
+#include <linux/inet.h>
+#include <linux/idr.h>
+#include <linux/file.h>
+#include <linux/parser.h>
+#include <linux/semaphore.h>
+#include <net/9p/9p.h>
+#include <net/9p/client.h>
+#include <net/9p/transport.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/rdma_cm.h>
+#include <rdma/ib_verbs.h>
+
+#define P9_PORT			5640
+#define P9_RDMA_SQ_DEPTH	32
+#define P9_RDMA_RQ_DEPTH	32
+#define P9_RDMA_SEND_SGE	4
+#define P9_RDMA_RECV_SGE	4
+#define P9_RDMA_IRD		0
+#define P9_RDMA_ORD		0
+#define P9_RDMA_TIMEOUT		30000		/* 30 seconds */
+#define P9_RDMA_MAXSIZE		(4*4096)	/* Min SGE is 4, so we can
+						 * safely advertise a maxsize
+						 * of 64k */
+
+#define P9_RDMA_MAX_SGE (P9_RDMA_MAXSIZE >> PAGE_SHIFT)
+/**
+ * struct p9_trans_rdma - RDMA transport instance
+ *
+ * @state: tracks the transport state machine for connection setup and tear down
+ * @cm_id: The RDMA CM ID
+ * @pd: Protection Domain pointer
+ * @qp: Queue Pair pointer
+ * @cq: Completion Queue pointer
+ * @lkey: The local access only memory region key
+ * @timeout: Number of uSecs to wait for connection management events
+ * @sq_depth: The depth of the Send Queue
+ * @sq_sem: Semaphore for the SQ
+ * @rq_depth: The depth of the Receive Queue.
+ * @addr: The remote peer's address
+ * @req_lock: Protects the active request list
+ * @send_wait: Wait list when the SQ fills up
+ * @cm_done: Completion event for connection management tracking
+ */
+struct p9_trans_rdma {
+	enum {
+		P9_RDMA_INIT,
+		P9_RDMA_ADDR_RESOLVED,
+		P9_RDMA_ROUTE_RESOLVED,
+		P9_RDMA_CONNECTED,
+		P9_RDMA_FLUSHING,
+		P9_RDMA_CLOSING,
+		P9_RDMA_CLOSED,
+	} state;
+	struct rdma_cm_id *cm_id;
+	struct ib_pd *pd;
+	struct ib_qp *qp;
+	struct ib_cq *cq;
+	struct ib_mr *dma_mr;
+	u32 lkey;
+	long timeout;
+	int sq_depth;
+	struct semaphore sq_sem;
+	int rq_depth;
+	atomic_t rq_count;
+	struct sockaddr_in addr;
+	spinlock_t req_lock;
+
+	struct completion cm_done;
+};
+
+/**
+ * p9_rdma_context - Keeps track of in-process WR
+ *
+ * @wc_op: The original WR op for when the CQE completes in error.
+ * @busa: Bus address to unmap when the WR completes
+ * @req: Keeps track of requests (send)
+ * @rc: Keepts track of replies (receive)
+ */
+struct p9_rdma_req;
+struct p9_rdma_context {
+	enum ib_wc_opcode wc_op;
+	dma_addr_t busa;
+	union {
+		struct p9_req_t *req;
+		struct p9_fcall *rc;
+	};
+};
+
+/**
+ * p9_rdma_opts - Collection of mount options
+ * @port: port of connection
+ * @sq_depth: The requested depth of the SQ. This really doesn't need
+ * to be any deeper than the number of threads used in the client
+ * @rq_depth: The depth of the RQ. Should be greater than or equal to SQ depth
+ * @timeout: Time to wait in msecs for CM events
+ */
+struct p9_rdma_opts {
+	short port;
+	int sq_depth;
+	int rq_depth;
+	long timeout;
+};
+
+/*
+ * Option Parsing (code inspired by NFS code)
+ */
+enum {
+	/* Options that take integer arguments */
+	Opt_port, Opt_rq_depth, Opt_sq_depth, Opt_timeout, Opt_err,
+};
+
+static match_table_t tokens = {
+	{Opt_port, "port=%u"},
+	{Opt_sq_depth, "sq=%u"},
+	{Opt_rq_depth, "rq=%u"},
+	{Opt_timeout, "timeout=%u"},
+	{Opt_err, NULL},
+};
+
+/**
+ * parse_options - parse mount options into session structure
+ * @options: options string passed from mount
+ * @opts: transport-specific structure to parse options into
+ *
+ * Returns 0 upon success, -ERRNO upon failure
+ */
+static int parse_opts(char *params, struct p9_rdma_opts *opts)
+{
+	char *p;
+	substring_t args[MAX_OPT_ARGS];
+	int option;
+	char *options;
+	int ret;
+
+	opts->port = P9_PORT;
+	opts->sq_depth = P9_RDMA_SQ_DEPTH;
+	opts->rq_depth = P9_RDMA_RQ_DEPTH;
+	opts->timeout = P9_RDMA_TIMEOUT;
+
+	if (!params)
+		return 0;
+
+	options = kstrdup(params, GFP_KERNEL);
+	if (!options) {
+		P9_DPRINTK(P9_DEBUG_ERROR,
+			   "failed to allocate copy of option string\n");
+		return -ENOMEM;
+	}
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token;
+		int r;
+		if (!*p)
+			continue;
+		token = match_token(p, tokens, args);
+		r = match_int(&args[0], &option);
+		if (r < 0) {
+			P9_DPRINTK(P9_DEBUG_ERROR,
+				   "integer field, but no integer?\n");
+			ret = r;
+			continue;
+		}
+		switch (token) {
+		case Opt_port:
+			opts->port = option;
+			break;
+		case Opt_sq_depth:
+			opts->sq_depth = option;
+			break;
+		case Opt_rq_depth:
+			opts->rq_depth = option;
+			break;
+		case Opt_timeout:
+			opts->timeout = option;
+			break;
+		default:
+			continue;
+		}
+	}
+	/* RQ must be at least as large as the SQ */
+	opts->rq_depth = max(opts->rq_depth, opts->sq_depth);
+	kfree(options);
+	return 0;
+}
+
+static int
+p9_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event)
+{
+	struct p9_client *c = id->context;
+	struct p9_trans_rdma *rdma = c->trans;
+	switch (event->event) {
+	case RDMA_CM_EVENT_ADDR_RESOLVED:
+		BUG_ON(rdma->state != P9_RDMA_INIT);
+		rdma->state = P9_RDMA_ADDR_RESOLVED;
+		break;
+
+	case RDMA_CM_EVENT_ROUTE_RESOLVED:
+		BUG_ON(rdma->state != P9_RDMA_ADDR_RESOLVED);
+		rdma->state = P9_RDMA_ROUTE_RESOLVED;
+		break;
+
+	case RDMA_CM_EVENT_ESTABLISHED:
+		BUG_ON(rdma->state != P9_RDMA_ROUTE_RESOLVED);
+		rdma->state = P9_RDMA_CONNECTED;
+		break;
+
+	case RDMA_CM_EVENT_DISCONNECTED:
+		if (rdma)
+			rdma->state = P9_RDMA_CLOSED;
+		if (c)
+			c->status = Disconnected;
+		break;
+
+	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
+		break;
+
+	case RDMA_CM_EVENT_ADDR_CHANGE:
+	case RDMA_CM_EVENT_ROUTE_ERROR:
+	case RDMA_CM_EVENT_DEVICE_REMOVAL:
+	case RDMA_CM_EVENT_MULTICAST_JOIN:
+	case RDMA_CM_EVENT_MULTICAST_ERROR:
+	case RDMA_CM_EVENT_REJECTED:
+	case RDMA_CM_EVENT_CONNECT_REQUEST:
+	case RDMA_CM_EVENT_CONNECT_RESPONSE:
+	case RDMA_CM_EVENT_CONNECT_ERROR:
+	case RDMA_CM_EVENT_ADDR_ERROR:
+	case RDMA_CM_EVENT_UNREACHABLE:
+		c->status = Disconnected;
+		rdma_disconnect(rdma->cm_id);
+		break;
+	default:
+		BUG();
+	}
+	complete(&rdma->cm_done);
+	return 0;
+}
+
+static void
+handle_recv(struct p9_client *client, struct p9_trans_rdma *rdma,
+	    struct p9_rdma_context *c, enum ib_wc_status status, u32 byte_len)
+{
+	struct p9_req_t *req;
+	int err = 0;
+	int16_t tag;
+
+	req = NULL;
+	ib_dma_unmap_single(rdma->cm_id->device, c->busa, client->msize,
+							 DMA_FROM_DEVICE);
+
+	if (status != IB_WC_SUCCESS)
+		goto err_out;
+
+	err = p9_parse_header(c->rc, NULL, NULL, &tag, 1);
+	if (err)
+		goto err_out;
+
+	req = p9_tag_lookup(client, tag);
+	if (!req)
+		goto err_out;
+
+	req->rc = c->rc;
+	p9_client_cb(client, req);
+
+	return;
+
+ err_out:
+	P9_DPRINTK(P9_DEBUG_ERROR, "req %p err %d status %d\n",
+		   req, err, status);
+	rdma->state = P9_RDMA_FLUSHING;
+	client->status = Disconnected;
+	return;
+}
+
+static void
+handle_send(struct p9_client *client, struct p9_trans_rdma *rdma,
+	    struct p9_rdma_context *c, enum ib_wc_status status, u32 byte_len)
+{
+	ib_dma_unmap_single(rdma->cm_id->device,
+			    c->busa, c->req->tc->size,
+			    DMA_TO_DEVICE);
+}
+
+static void qp_event_handler(struct ib_event *event, void *context)
+{
+	P9_DPRINTK(P9_DEBUG_ERROR, "QP event %d context %p\n", event->event,
+								context);
+}
+
+static void cq_comp_handler(struct ib_cq *cq, void *cq_context)
+{
+	struct p9_client *client = cq_context;
+	struct p9_trans_rdma *rdma = client->trans;
+	int ret;
+	struct ib_wc wc;
+
+	ib_req_notify_cq(rdma->cq, IB_CQ_NEXT_COMP);
+	while ((ret = ib_poll_cq(cq, 1, &wc)) > 0) {
+		struct p9_rdma_context *c = (void *) (unsigned long) wc.wr_id;
+
+		switch (c->wc_op) {
+		case IB_WC_RECV:
+			atomic_dec(&rdma->rq_count);
+			handle_recv(client, rdma, c, wc.status, wc.byte_len);
+			break;
+
+		case IB_WC_SEND:
+			handle_send(client, rdma, c, wc.status, wc.byte_len);
+			up(&rdma->sq_sem);
+			break;
+
+		default:
+			printk(KERN_ERR "9prdma: unexpected completion type, "
+			       "c->wc_op=%d, wc.opcode=%d, status=%d\n",
+			       c->wc_op, wc.opcode, wc.status);
+			break;
+		}
+		kfree(c);
+	}
+}
+
+static void cq_event_handler(struct ib_event *e, void *v)
+{
+	P9_DPRINTK(P9_DEBUG_ERROR, "CQ event %d context %p\n", e->event, v);
+}
+
+static void rdma_destroy_trans(struct p9_trans_rdma *rdma)
+{
+	if (!rdma)
+		return;
+
+	if (rdma->dma_mr && !IS_ERR(rdma->dma_mr))
+		ib_dereg_mr(rdma->dma_mr);
+
+	if (rdma->qp && !IS_ERR(rdma->qp))
+		ib_destroy_qp(rdma->qp);
+
+	if (rdma->pd && !IS_ERR(rdma->pd))
+		ib_dealloc_pd(rdma->pd);
+
+	if (rdma->cq && !IS_ERR(rdma->cq))
+		ib_destroy_cq(rdma->cq);
+
+	if (rdma->cm_id && !IS_ERR(rdma->cm_id))
+		rdma_destroy_id(rdma->cm_id);
+
+	kfree(rdma);
+}
+
+static int
+post_recv(struct p9_client *client, struct p9_rdma_context *c)
+{
+	struct p9_trans_rdma *rdma = client->trans;
+	struct ib_recv_wr wr, *bad_wr;
+	struct ib_sge sge;
+
+	c->busa = ib_dma_map_single(rdma->cm_id->device,
+				    c->rc->sdata, client->msize,
+				    DMA_FROM_DEVICE);
+	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa))
+		goto error;
+
+	sge.addr = c->busa;
+	sge.length = client->msize;
+	sge.lkey = rdma->lkey;
+
+	wr.next = NULL;
+	c->wc_op = IB_WC_RECV;
+	wr.wr_id = (unsigned long) c;
+	wr.sg_list = &sge;
+	wr.num_sge = 1;
+	return ib_post_recv(rdma->qp, &wr, &bad_wr);
+
+ error:
+	P9_DPRINTK(P9_DEBUG_ERROR, "EIO\n");
+	return -EIO;
+}
+
+static int rdma_request(struct p9_client *client, struct p9_req_t *req)
+{
+	struct p9_trans_rdma *rdma = client->trans;
+	struct ib_send_wr wr, *bad_wr;
+	struct ib_sge sge;
+	int err = 0;
+	unsigned long flags;
+	struct p9_rdma_context *c = NULL;
+	struct p9_rdma_context *rpl_context = NULL;
+
+	/* Allocate an fcall for the reply */
+	rpl_context = kmalloc(sizeof *rpl_context, GFP_KERNEL);
+	if (!rpl_context)
+		goto err_close;
+
+	/*
+	 * If the request has a buffer, steal it, otherwise
+	 * allocate a new one.  Typically, requests should already
+	 * have receive buffers allocated and just swap them around
+	 */
+	if (!req->rc) {
+		req->rc = kmalloc(sizeof(struct p9_fcall)+client->msize,
+								GFP_KERNEL);
+		if (req->rc) {
+			req->rc->sdata = (char *) req->rc +
+						sizeof(struct p9_fcall);
+			req->rc->capacity = client->msize;
+		}
+	}
+	rpl_context->rc = req->rc;
+	if (!rpl_context->rc) {
+		kfree(rpl_context);
+		goto err_close;
+	}
+
+	/*
+	 * Post a receive buffer for this request. We need to ensure
+	 * there is a reply buffer available for every outstanding
+	 * request. A flushed request can result in no reply for an
+	 * outstanding request, so we must keep a count to avoid
+	 * overflowing the RQ.
+	 */
+	if (atomic_inc_return(&rdma->rq_count) <= rdma->rq_depth) {
+		err = post_recv(client, rpl_context);
+		if (err) {
+			kfree(rpl_context->rc);
+			kfree(rpl_context);
+			goto err_close;
+		}
+	} else
+		atomic_dec(&rdma->rq_count);
+
+	/* remove posted receive buffer from request structure */
+	req->rc = NULL;
+
+	/* Post the request */
+	c = kmalloc(sizeof *c, GFP_KERNEL);
+	if (!c)
+		goto err_close;
+	c->req = req;
+
+	c->busa = ib_dma_map_single(rdma->cm_id->device,
+				    c->req->tc->sdata, c->req->tc->size,
+				    DMA_TO_DEVICE);
+	if (ib_dma_mapping_error(rdma->cm_id->device, c->busa))
+		goto error;
+
+	sge.addr = c->busa;
+	sge.length = c->req->tc->size;
+	sge.lkey = rdma->lkey;
+
+	wr.next = NULL;
+	c->wc_op = IB_WC_SEND;
+	wr.wr_id = (unsigned long) c;
+	wr.opcode = IB_WR_SEND;
+	wr.send_flags = IB_SEND_SIGNALED;
+	wr.sg_list = &sge;
+	wr.num_sge = 1;
+
+	if (down_interruptible(&rdma->sq_sem))
+		goto error;
+
+	return ib_post_send(rdma->qp, &wr, &bad_wr);
+
+ error:
+	P9_DPRINTK(P9_DEBUG_ERROR, "EIO\n");
+	return -EIO;
+
+ err_close:
+	spin_lock_irqsave(&rdma->req_lock, flags);
+	if (rdma->state < P9_RDMA_CLOSING) {
+		rdma->state = P9_RDMA_CLOSING;
+		spin_unlock_irqrestore(&rdma->req_lock, flags);
+		rdma_disconnect(rdma->cm_id);
+	} else
+		spin_unlock_irqrestore(&rdma->req_lock, flags);
+	return err;
+}
+
+static void rdma_close(struct p9_client *client)
+{
+	struct p9_trans_rdma *rdma;
+
+	if (!client)
+		return;
+
+	rdma = client->trans;
+	if (!rdma)
+		return;
+
+	client->status = Disconnected;
+	rdma_disconnect(rdma->cm_id);
+	rdma_destroy_trans(rdma);
+}
+
+/**
+ * alloc_rdma - Allocate and initialize the rdma transport structure
+ * @msize: MTU
+ * @dotu: Extension attribute
+ * @opts: Mount options structure
+ */
+static struct p9_trans_rdma *alloc_rdma(struct p9_rdma_opts *opts)
+{
+	struct p9_trans_rdma *rdma;
+
+	rdma = kzalloc(sizeof(struct p9_trans_rdma), GFP_KERNEL);
+	if (!rdma)
+		return NULL;
+
+	rdma->sq_depth = opts->sq_depth;
+	rdma->rq_depth = opts->rq_depth;
+	rdma->timeout = opts->timeout;
+	spin_lock_init(&rdma->req_lock);
+	init_completion(&rdma->cm_done);
+	sema_init(&rdma->sq_sem, rdma->sq_depth);
+	atomic_set(&rdma->rq_count, 0);
+
+	return rdma;
+}
+
+/* its not clear to me we can do anything after send has been posted */
+static int rdma_cancel(struct p9_client *client, struct p9_req_t *req)
+{
+	return 1;
+}
+
+/**
+ * trans_create_rdma - Transport method for creating atransport instance
+ * @client: client instance
+ * @addr: IP address string
+ * @args: Mount options string
+ */
+static int
+rdma_create_trans(struct p9_client *client, const char *addr, char *args)
+{
+	int err;
+	struct p9_rdma_opts opts;
+	struct p9_trans_rdma *rdma;
+	struct rdma_conn_param conn_param;
+	struct ib_qp_init_attr qp_attr;
+	struct ib_device_attr devattr;
+
+	/* Parse the transport specific mount options */
+	err = parse_opts(args, &opts);
+	if (err < 0)
+		return err;
+
+	/* Create and initialize the RDMA transport structure */
+	rdma = alloc_rdma(&opts);
+	if (!rdma)
+		return -ENOMEM;
+
+	/* Create the RDMA CM ID */
+	rdma->cm_id = rdma_create_id(p9_cm_event_handler, client, RDMA_PS_TCP);
+	if (IS_ERR(rdma->cm_id))
+		goto error;
+
+	/* Resolve the server's address */
+	rdma->addr.sin_family = AF_INET;
+	rdma->addr.sin_addr.s_addr = in_aton(addr);
+	rdma->addr.sin_port = htons(opts.port);
+	err = rdma_resolve_addr(rdma->cm_id, NULL,
+				(struct sockaddr *)&rdma->addr,
+				rdma->timeout);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_ADDR_RESOLVED))
+		goto error;
+
+	/* Resolve the route to the server */
+	err = rdma_resolve_route(rdma->cm_id, rdma->timeout);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_ROUTE_RESOLVED))
+		goto error;
+
+	/* Query the device attributes */
+	err = ib_query_device(rdma->cm_id->device, &devattr);
+	if (err)
+		goto error;
+
+	/* Create the Completion Queue */
+	rdma->cq = ib_create_cq(rdma->cm_id->device, cq_comp_handler,
+				cq_event_handler, client,
+				opts.sq_depth + opts.rq_depth + 1, 0);
+	if (IS_ERR(rdma->cq))
+		goto error;
+	ib_req_notify_cq(rdma->cq, IB_CQ_NEXT_COMP);
+
+	/* Create the Protection Domain */
+	rdma->pd = ib_alloc_pd(rdma->cm_id->device);
+	if (IS_ERR(rdma->pd))
+		goto error;
+
+	/* Cache the DMA lkey in the transport */
+	rdma->dma_mr = NULL;
+	if (devattr.device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)
+		rdma->lkey = rdma->cm_id->device->local_dma_lkey;
+	else {
+		rdma->dma_mr = ib_get_dma_mr(rdma->pd, IB_ACCESS_LOCAL_WRITE);
+		if (IS_ERR(rdma->dma_mr))
+			goto error;
+		rdma->lkey = rdma->dma_mr->lkey;
+	}
+
+	/* Create the Queue Pair */
+	memset(&qp_attr, 0, sizeof qp_attr);
+	qp_attr.event_handler = qp_event_handler;
+	qp_attr.qp_context = client;
+	qp_attr.cap.max_send_wr = opts.sq_depth;
+	qp_attr.cap.max_recv_wr = opts.rq_depth;
+	qp_attr.cap.max_send_sge = P9_RDMA_SEND_SGE;
+	qp_attr.cap.max_recv_sge = P9_RDMA_RECV_SGE;
+	qp_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
+	qp_attr.qp_type = IB_QPT_RC;
+	qp_attr.send_cq = rdma->cq;
+	qp_attr.recv_cq = rdma->cq;
+	err = rdma_create_qp(rdma->cm_id, rdma->pd, &qp_attr);
+	if (err)
+		goto error;
+	rdma->qp = rdma->cm_id->qp;
+
+	/* Request a connection */
+	memset(&conn_param, 0, sizeof(conn_param));
+	conn_param.private_data = NULL;
+	conn_param.private_data_len = 0;
+	conn_param.responder_resources = P9_RDMA_IRD;
+	conn_param.initiator_depth = P9_RDMA_ORD;
+	err = rdma_connect(rdma->cm_id, &conn_param);
+	if (err)
+		goto error;
+	err = wait_for_completion_interruptible(&rdma->cm_done);
+	if (err || (rdma->state != P9_RDMA_CONNECTED))
+		goto error;
+
+	client->trans = rdma;
+	client->status = Connected;
+
+	return 0;
+
+error:
+	rdma_destroy_trans(rdma);
+	return -ENOTCONN;
+}
+
+static struct p9_trans_module p9_rdma_trans = {
+	.name = "rdma",
+	.maxsize = P9_RDMA_MAXSIZE,
+	.def = 0,
+	.owner = THIS_MODULE,
+	.create = rdma_create_trans,
+	.close = rdma_close,
+	.request = rdma_request,
+	.cancel = rdma_cancel,
+};
+
+/**
+ * p9_trans_rdma_init - Register the 9P RDMA transport driver
+ */
+static int __init p9_trans_rdma_init(void)
+{
+	v9fs_register_trans(&p9_rdma_trans);
+	return 0;
+}
+
+static void __exit p9_trans_rdma_exit(void)
+{
+	v9fs_unregister_trans(&p9_rdma_trans);
+}
+
+module_init(p9_trans_rdma_init);
+module_exit(p9_trans_rdma_exit);
+
+MODULE_AUTHOR("Tom Tucker <tom@opengridcomputing.com>");
+MODULE_DESCRIPTION("RDMA Transport for 9P");
+MODULE_LICENSE("Dual BSD/GPL");
-- 
cgit v1.2.3


From e45c5405e12c7cef93940cb7a541ab459ec0096a Mon Sep 17 00:00:00 2001
From: Eric Van Hensbergen <ericvh@gmail.com>
Date: Wed, 22 Oct 2008 18:54:47 -0500
Subject: 9p: fix sparse warnings

Several sparse warnings were introduced by patches accepted during the merge
window which weren't caught.  This patch fixes those warnings.

Signed-off-by: Eric Van Hensbergen <ericvh@gmail.com>
---
 include/net/9p/client.h |  1 +
 net/9p/client.c         |  1 +
 net/9p/protocol.c       | 24 ++++++++++++------------
 3 files changed, 14 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/include/net/9p/client.h b/include/net/9p/client.h
index 9fe45b32ce4a..4012e07162e5 100644
--- a/include/net/9p/client.h
+++ b/include/net/9p/client.h
@@ -182,6 +182,7 @@ struct p9_fid {
 	struct list_head dlist;	/* list of all fids attached to a dentry */
 };
 
+int p9_client_version(struct p9_client *);
 struct p9_client *p9_client_create(const char *dev_name, char *options);
 void p9_client_destroy(struct p9_client *clnt);
 void p9_client_disconnect(struct p9_client *clnt);
diff --git a/net/9p/client.c b/net/9p/client.c
index bbac2f72b4d2..67717f69412e 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -159,6 +159,7 @@ static struct p9_req_t *p9_tag_alloc(struct p9_client *c, u16 tag)
 
 			if (!c->reqs[row]) {
 				printk(KERN_ERR "Couldn't grow tag array\n");
+				spin_unlock_irqrestore(&c->lock, flags);
 				return ERR_PTR(-ENOMEM);
 			}
 			for (col = 0; col < P9_ROW_MAXTAG; col++) {
diff --git a/net/9p/protocol.c b/net/9p/protocol.c
index 908e79faf48e..dcd7666824ba 100644
--- a/net/9p/protocol.c
+++ b/net/9p/protocol.c
@@ -186,7 +186,7 @@ p9pdu_vreadf(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap)
 			}
 			break;
 		case 's':{
-				char **ptr = va_arg(ap, char **);
+				char **sptr = va_arg(ap, char **);
 				int16_t len;
 				int size;
 
@@ -196,17 +196,17 @@ p9pdu_vreadf(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap)
 
 				size = MAX(len, 0);
 
-				*ptr = kmalloc(size + 1, GFP_KERNEL);
-				if (*ptr == NULL) {
+				*sptr = kmalloc(size + 1, GFP_KERNEL);
+				if (*sptr == NULL) {
 					errcode = -EFAULT;
 					break;
 				}
-				if (pdu_read(pdu, *ptr, size)) {
+				if (pdu_read(pdu, *sptr, size)) {
 					errcode = -EFAULT;
-					kfree(*ptr);
-					*ptr = NULL;
+					kfree(*sptr);
+					*sptr = NULL;
 				} else
-					(*ptr)[size] = 0;
+					(*sptr)[size] = 0;
 			}
 			break;
 		case 'Q':{
@@ -380,13 +380,13 @@ p9pdu_vwritef(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap)
 			}
 			break;
 		case 's':{
-				const char *ptr = va_arg(ap, const char *);
+				const char *sptr = va_arg(ap, const char *);
 				int16_t len = 0;
-				if (ptr)
-					len = MIN(strlen(ptr), USHORT_MAX);
+				if (sptr)
+					len = MIN(strlen(sptr), USHORT_MAX);
 
 				errcode = p9pdu_writef(pdu, optional, "w", len);
-				if (!errcode && pdu_write(pdu, ptr, len))
+				if (!errcode && pdu_write(pdu, sptr, len))
 					errcode = -EFAULT;
 			}
 			break;
@@ -426,7 +426,7 @@ p9pdu_vwritef(struct p9_fcall *pdu, int optional, const char *fmt, va_list ap)
 		case 'U':{
 				int32_t count = va_arg(ap, int32_t);
 				const char __user *udata =
-						va_arg(ap, const void *);
+						va_arg(ap, const void __user *);
 				errcode =
 				    p9pdu_writef(pdu, optional, "d", count);
 				if (!errcode && pdu_write_u(pdu, udata, count))
-- 
cgit v1.2.3


From 848e4c68c4695beae563f9a3d59fce596b466a74 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 21 Oct 2008 14:26:39 +0900
Subject: libata: transfer EHI control flags to slave ehc.i

ATA_EHI_NO_AUTOPSY and ATA_EHI_QUIET are used to control the behavior
of EH.  As only the master link is visible outside EH, these flags are
set only for the master link although they should also apply to the
slave link, which causes spurious EH messages during probe and
suspend/resume.

This patch transfers those two flags to slave ehc.i before performing
slave autopsy and reporting.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jeff Garzik <jgarzik@redhat.com>
---
 drivers/ata/libata-eh.c | 5 +++++
 include/linux/libata.h  | 3 +++
 2 files changed, 8 insertions(+)

(limited to 'include')

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index a93247cc395a..d2409a8acece 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -2010,8 +2010,13 @@ void ata_eh_autopsy(struct ata_port *ap)
 		struct ata_eh_context *mehc = &ap->link.eh_context;
 		struct ata_eh_context *sehc = &ap->slave_link->eh_context;
 
+		/* transfer control flags from master to slave */
+		sehc->i.flags |= mehc->i.flags & ATA_EHI_TO_SLAVE_MASK;
+
+		/* perform autopsy on the slave link */
 		ata_eh_link_autopsy(ap->slave_link);
 
+		/* transfer actions from slave to master and clear slave */
 		ata_eh_about_to_do(ap->slave_link, NULL, ATA_EH_ALL_ACTIONS);
 		mehc->i.action		|= sehc->i.action;
 		mehc->i.dev_action[1]	|= sehc->i.dev_action[1];
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 947cf84e555d..c261aa0584b1 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -340,6 +340,9 @@ enum {
 
 	ATA_EHI_DID_RESET	= ATA_EHI_DID_SOFTRESET | ATA_EHI_DID_HARDRESET,
 
+	/* mask of flags to transfer *to* the slave link */
+	ATA_EHI_TO_SLAVE_MASK	= ATA_EHI_NO_AUTOPSY | ATA_EHI_QUIET,
+
 	/* max tries if error condition is still set after ->error_handler */
 	ATA_EH_MAX_TRIES	= 5,
 
-- 
cgit v1.2.3


From 9db4fcd99f7ef886ded97cd26a8642c70fbe34df Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Fri, 4 Jul 2008 10:56:13 +0800
Subject: ACPICA: Fix wrong resource descriptor length for 64-bit build

The "minimal" descriptors such as EndTag are calculated as 12
bytes long, but the actual length in the internal descriptor is
16 because of the round-up to 8 on 64-bit build.

http://www.acpica.org/bugzilla/show_bug.cgi?id=728

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 include/acpi/actypes.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 4ea4f40bf894..73d6b1cb07f3 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -1225,8 +1225,8 @@ struct acpi_resource {
 
 #pragma pack()
 
-#define ACPI_RS_SIZE_MIN                    12
 #define ACPI_RS_SIZE_NO_DATA                8	/* Id + Length fields */
+#define ACPI_RS_SIZE_MIN                    (u32) ACPI_ROUND_UP_TO_NATIVE_WORD (12)
 #define ACPI_RS_SIZE(type)                  (u32) (ACPI_RS_SIZE_NO_DATA + sizeof (type))
 
 #define ACPI_NEXT_RESOURCE(res)             (struct acpi_resource *)((u8 *) res + res->length)
-- 
cgit v1.2.3


From b417d40b9a850f12f69aa9d785d2af39c9463bb8 Mon Sep 17 00:00:00 2001
From: Yi Yang <yi.y.yang@intel.com>
Date: Mon, 4 Aug 2008 10:30:09 +0800
Subject: ACPICA: Return status from global init function

Return status from acpi_ut_init_globals. This is used by both
the kernel subsystem and the utilities such as iASL compiler.
The function could possibly fail when the caches are initialized.
Yang Yi.

Signed-off-by: Yi Yang <yi.y.yang@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/utilities/utglobal.c | 8 ++++----
 drivers/acpi/utilities/utxface.c  | 7 ++++++-
 include/acpi/acutils.h            | 2 +-
 3 files changed, 11 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/utilities/utglobal.c b/drivers/acpi/utilities/utglobal.c
index a6e71b801d2d..248eefc369f8 100644
--- a/drivers/acpi/utilities/utglobal.c
+++ b/drivers/acpi/utilities/utglobal.c
@@ -677,14 +677,14 @@ u8 acpi_ut_valid_object_type(acpi_object_type type)
  *
  * PARAMETERS:  None
  *
- * RETURN:      None
+ * RETURN:      Status
  *
  * DESCRIPTION: Init library globals.  All globals that require specific
  *              initialization should be initialized here!
  *
  ******************************************************************************/
 
-void acpi_ut_init_globals(void)
+acpi_status acpi_ut_init_globals(void)
 {
 	acpi_status status;
 	u32 i;
@@ -695,7 +695,7 @@ void acpi_ut_init_globals(void)
 
 	status = acpi_ut_create_caches();
 	if (ACPI_FAILURE(status)) {
-		return;
+		return_ACPI_STATUS(status);
 	}
 
 	/* Mutex locked flags */
@@ -772,7 +772,7 @@ void acpi_ut_init_globals(void)
 	acpi_gbl_display_final_mem_stats = FALSE;
 #endif
 
-	return_VOID;
+	return_ACPI_STATUS(AE_OK);
 }
 
 ACPI_EXPORT_SYMBOL(acpi_dbg_level)
diff --git a/drivers/acpi/utilities/utxface.c b/drivers/acpi/utilities/utxface.c
index f8bdadf3c32f..c198a4d40583 100644
--- a/drivers/acpi/utilities/utxface.c
+++ b/drivers/acpi/utilities/utxface.c
@@ -81,7 +81,12 @@ acpi_status __init acpi_initialize_subsystem(void)
 
 	/* Initialize all globals used by the subsystem */
 
-	acpi_ut_init_globals();
+	status = acpi_ut_init_globals();
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status,
+				"During initialization of globals"));
+		return_ACPI_STATUS(status);
+	}
 
 	/* Create the default mutex objects */
 
diff --git a/include/acpi/acutils.h b/include/acpi/acutils.h
index 69f8888771ff..10ce81406f9c 100644
--- a/include/acpi/acutils.h
+++ b/include/acpi/acutils.h
@@ -110,7 +110,7 @@ struct acpi_pkg_info {
 /*
  * utglobal - Global data structures and procedures
  */
-void acpi_ut_init_globals(void);
+acpi_status acpi_ut_init_globals(void);
 
 #if defined(ACPI_DEBUG_OUTPUT) || defined(ACPI_DEBUGGER)
 
-- 
cgit v1.2.3


From c9bdd8057d706a972d804d2d8614a283641a5660 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Mon, 4 Aug 2008 09:54:17 +0800
Subject: ACPICA: Cleanup macro definition file.

Removed unused macros. Ensure that multiple parameters always have a space
after a comma. Cleanup some comments.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 include/acpi/acmacros.h | 248 ++++++++++++++++++++++--------------------------
 1 file changed, 115 insertions(+), 133 deletions(-)

(limited to 'include')

diff --git a/include/acpi/acmacros.h b/include/acpi/acmacros.h
index 57ab9e9d7593..2106f9136cce 100644
--- a/include/acpi/acmacros.h
+++ b/include/acpi/acmacros.h
@@ -62,7 +62,7 @@
 #define ACPI_ARRAY_LENGTH(x)            (sizeof(x) / sizeof((x)[0]))
 
 /*
- * Extract data using a pointer.  Any more than a byte and we
+ * Extract data using a pointer. Any more than a byte and we
  * get into potential aligment issues -- see the STORE macros below.
  * Use with care.
  */
@@ -80,21 +80,21 @@
  */
 #define ACPI_CAST_PTR(t, p)             ((t *) (acpi_uintptr_t) (p))
 #define ACPI_CAST_INDIRECT_PTR(t, p)    ((t **) (acpi_uintptr_t) (p))
-#define ACPI_ADD_PTR(t, a, b)		ACPI_CAST_PTR (t, (ACPI_CAST_PTR (u8,(a)) + (acpi_size)(b)))
-#define ACPI_PTR_DIFF(a, b)		(acpi_size) (ACPI_CAST_PTR (u8,(a)) - ACPI_CAST_PTR (u8,(b)))
+#define ACPI_ADD_PTR(t, a, b)		ACPI_CAST_PTR (t, (ACPI_CAST_PTR (u8, (a)) + (acpi_size)(b)))
+#define ACPI_PTR_DIFF(a, b)		(acpi_size) (ACPI_CAST_PTR (u8, (a)) - ACPI_CAST_PTR (u8, (b)))
 
 /* Pointer/Integer type conversions */
 
 #define ACPI_TO_POINTER(i)		ACPI_ADD_PTR (void, (void *) NULL, (acpi_size) i)
-#define ACPI_TO_INTEGER(p)              ACPI_PTR_DIFF (p,(void *) NULL)
-#define ACPI_OFFSET(d,f)                (acpi_size) ACPI_PTR_DIFF (&(((d *)0)->f),(void *) NULL)
+#define ACPI_TO_INTEGER(p)              ACPI_PTR_DIFF (p, (void *) NULL)
+#define ACPI_OFFSET(d, f)               (acpi_size) ACPI_PTR_DIFF (&(((d *)0)->f), (void *) NULL)
 #define ACPI_PHYSADDR_TO_PTR(i)         ACPI_TO_POINTER(i)
 #define ACPI_PTR_TO_PHYSADDR(i)         ACPI_TO_INTEGER(i)
 
 #ifndef ACPI_MISALIGNMENT_NOT_SUPPORTED
-#define ACPI_COMPARE_NAME(a,b)          (*ACPI_CAST_PTR (u32,(a)) == *ACPI_CAST_PTR (u32,(b)))
+#define ACPI_COMPARE_NAME(a, b)         (*ACPI_CAST_PTR (u32, (a)) == *ACPI_CAST_PTR (u32, (b)))
 #else
-#define ACPI_COMPARE_NAME(a,b)          (!ACPI_STRNCMP (ACPI_CAST_PTR (char,(a)), ACPI_CAST_PTR (char,(b)), ACPI_NAME_SIZE))
+#define ACPI_COMPARE_NAME(a, b)         (!ACPI_STRNCMP (ACPI_CAST_PTR (char, (a)), ACPI_CAST_PTR (char, (b)), ACPI_NAME_SIZE))
 #endif
 
 /*
@@ -114,7 +114,7 @@ struct acpi_integer_overlay {
 
 /* Split 64-bit integer into two 32-bit values. Use with %8.8_x%8.8_x */
 
-#define ACPI_FORMAT_UINT64(i)           ACPI_HIDWORD(i),ACPI_LODWORD(i)
+#define ACPI_FORMAT_UINT64(i)           ACPI_HIDWORD(i), ACPI_LODWORD(i)
 
 #if ACPI_MACHINE_WIDTH == 64
 #define ACPI_FORMAT_NATIVE_UINT(i)      ACPI_FORMAT_UINT64(i)
@@ -132,37 +132,33 @@ struct acpi_integer_overlay {
  * Macros for big-endian machines
  */
 
-/* This macro sets a buffer index, starting from the end of the buffer */
-
-#define ACPI_BUFFER_INDEX(buf_len,buf_offset,byte_gran) ((buf_len) - (((buf_offset)+1) * (byte_gran)))
-
 /* These macros reverse the bytes during the move, converting little-endian to big endian */
 
 			  /* Big Endian      <==        Little Endian */
 			  /*  Hi...Lo                     Lo...Hi     */
 /* 16-bit source, 16/32/64 destination */
 
-#define ACPI_MOVE_16_TO_16(d,s)         {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[1];\
+#define ACPI_MOVE_16_TO_16(d, s)        {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[1];\
 					   ((  u8 *)(void *)(d))[1] = ((u8 *)(void *)(s))[0];}
 
-#define ACPI_MOVE_16_TO_32(d,s)         {(*(u32 *)(void *)(d))=0;\
+#define ACPI_MOVE_16_TO_32(d, s)        {(*(u32 *)(void *)(d))=0;\
 							   ((u8 *)(void *)(d))[2] = ((u8 *)(void *)(s))[1];\
 							   ((u8 *)(void *)(d))[3] = ((u8 *)(void *)(s))[0];}
 
-#define ACPI_MOVE_16_TO_64(d,s)         {(*(u64 *)(void *)(d))=0;\
+#define ACPI_MOVE_16_TO_64(d, s)        {(*(u64 *)(void *)(d))=0;\
 									 ((u8 *)(void *)(d))[6] = ((u8 *)(void *)(s))[1];\
 									 ((u8 *)(void *)(d))[7] = ((u8 *)(void *)(s))[0];}
 
 /* 32-bit source, 16/32/64 destination */
 
-#define ACPI_MOVE_32_TO_16(d,s)         ACPI_MOVE_16_TO_16(d,s)	/* Truncate to 16 */
+#define ACPI_MOVE_32_TO_16(d, s)        ACPI_MOVE_16_TO_16(d, s)	/* Truncate to 16 */
 
-#define ACPI_MOVE_32_TO_32(d,s)         {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[3];\
+#define ACPI_MOVE_32_TO_32(d, s)        {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[3];\
 										 ((  u8 *)(void *)(d))[1] = ((u8 *)(void *)(s))[2];\
 										 ((  u8 *)(void *)(d))[2] = ((u8 *)(void *)(s))[1];\
 										 ((  u8 *)(void *)(d))[3] = ((u8 *)(void *)(s))[0];}
 
-#define ACPI_MOVE_32_TO_64(d,s)         {(*(u64 *)(void *)(d))=0;\
+#define ACPI_MOVE_32_TO_64(d, s)        {(*(u64 *)(void *)(d))=0;\
 										   ((u8 *)(void *)(d))[4] = ((u8 *)(void *)(s))[3];\
 										   ((u8 *)(void *)(d))[5] = ((u8 *)(void *)(s))[2];\
 										   ((u8 *)(void *)(d))[6] = ((u8 *)(void *)(s))[1];\
@@ -170,11 +166,11 @@ struct acpi_integer_overlay {
 
 /* 64-bit source, 16/32/64 destination */
 
-#define ACPI_MOVE_64_TO_16(d,s)         ACPI_MOVE_16_TO_16(d,s)	/* Truncate to 16 */
+#define ACPI_MOVE_64_TO_16(d, s)        ACPI_MOVE_16_TO_16(d, s)	/* Truncate to 16 */
 
-#define ACPI_MOVE_64_TO_32(d,s)         ACPI_MOVE_32_TO_32(d,s)	/* Truncate to 32 */
+#define ACPI_MOVE_64_TO_32(d, s)        ACPI_MOVE_32_TO_32(d, s)	/* Truncate to 32 */
 
-#define ACPI_MOVE_64_TO_64(d,s)         {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[7];\
+#define ACPI_MOVE_64_TO_64(d, s)        {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[7];\
 										 ((  u8 *)(void *)(d))[1] = ((u8 *)(void *)(s))[6];\
 										 ((  u8 *)(void *)(d))[2] = ((u8 *)(void *)(s))[5];\
 										 ((  u8 *)(void *)(d))[3] = ((u8 *)(void *)(s))[4];\
@@ -187,63 +183,59 @@ struct acpi_integer_overlay {
  * Macros for little-endian machines
  */
 
-/* This macro sets a buffer index, starting from the beginning of the buffer */
-
-#define ACPI_BUFFER_INDEX(buf_len,buf_offset,byte_gran) (buf_offset)
-
 #ifndef ACPI_MISALIGNMENT_NOT_SUPPORTED
 
 /* The hardware supports unaligned transfers, just do the little-endian move */
 
 /* 16-bit source, 16/32/64 destination */
 
-#define ACPI_MOVE_16_TO_16(d,s)         *(u16 *)(void *)(d) = *(u16 *)(void *)(s)
-#define ACPI_MOVE_16_TO_32(d,s)         *(u32 *)(void *)(d) = *(u16 *)(void *)(s)
-#define ACPI_MOVE_16_TO_64(d,s)         *(u64 *)(void *)(d) = *(u16 *)(void *)(s)
+#define ACPI_MOVE_16_TO_16(d, s)        *(u16 *)(void *)(d) = *(u16 *)(void *)(s)
+#define ACPI_MOVE_16_TO_32(d, s)        *(u32 *)(void *)(d) = *(u16 *)(void *)(s)
+#define ACPI_MOVE_16_TO_64(d, s)        *(u64 *)(void *)(d) = *(u16 *)(void *)(s)
 
 /* 32-bit source, 16/32/64 destination */
 
-#define ACPI_MOVE_32_TO_16(d,s)         ACPI_MOVE_16_TO_16(d,s)	/* Truncate to 16 */
-#define ACPI_MOVE_32_TO_32(d,s)         *(u32 *)(void *)(d) = *(u32 *)(void *)(s)
-#define ACPI_MOVE_32_TO_64(d,s)         *(u64 *)(void *)(d) = *(u32 *)(void *)(s)
+#define ACPI_MOVE_32_TO_16(d, s)        ACPI_MOVE_16_TO_16(d, s)	/* Truncate to 16 */
+#define ACPI_MOVE_32_TO_32(d, s)        *(u32 *)(void *)(d) = *(u32 *)(void *)(s)
+#define ACPI_MOVE_32_TO_64(d, s)        *(u64 *)(void *)(d) = *(u32 *)(void *)(s)
 
 /* 64-bit source, 16/32/64 destination */
 
-#define ACPI_MOVE_64_TO_16(d,s)         ACPI_MOVE_16_TO_16(d,s)	/* Truncate to 16 */
-#define ACPI_MOVE_64_TO_32(d,s)         ACPI_MOVE_32_TO_32(d,s)	/* Truncate to 32 */
-#define ACPI_MOVE_64_TO_64(d,s)         *(u64 *)(void *)(d) = *(u64 *)(void *)(s)
+#define ACPI_MOVE_64_TO_16(d, s)        ACPI_MOVE_16_TO_16(d, s)	/* Truncate to 16 */
+#define ACPI_MOVE_64_TO_32(d, s)        ACPI_MOVE_32_TO_32(d, s)	/* Truncate to 32 */
+#define ACPI_MOVE_64_TO_64(d, s)        *(u64 *)(void *)(d) = *(u64 *)(void *)(s)
 
 #else
 /*
- * The hardware does not support unaligned transfers.  We must move the
- * data one byte at a time.  These macros work whether the source or
+ * The hardware does not support unaligned transfers. We must move the
+ * data one byte at a time. These macros work whether the source or
  * the destination (or both) is/are unaligned.  (Little-endian move)
  */
 
 /* 16-bit source, 16/32/64 destination */
 
-#define ACPI_MOVE_16_TO_16(d,s)         {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[0];\
+#define ACPI_MOVE_16_TO_16(d, s)        {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[0];\
 										 ((  u8 *)(void *)(d))[1] = ((u8 *)(void *)(s))[1];}
 
-#define ACPI_MOVE_16_TO_32(d,s)         {(*(u32 *)(void *)(d)) = 0; ACPI_MOVE_16_TO_16(d,s);}
-#define ACPI_MOVE_16_TO_64(d,s)         {(*(u64 *)(void *)(d)) = 0; ACPI_MOVE_16_TO_16(d,s);}
+#define ACPI_MOVE_16_TO_32(d, s)        {(*(u32 *)(void *)(d)) = 0; ACPI_MOVE_16_TO_16(d, s);}
+#define ACPI_MOVE_16_TO_64(d, s)        {(*(u64 *)(void *)(d)) = 0; ACPI_MOVE_16_TO_16(d, s);}
 
 /* 32-bit source, 16/32/64 destination */
 
-#define ACPI_MOVE_32_TO_16(d,s)         ACPI_MOVE_16_TO_16(d,s)	/* Truncate to 16 */
+#define ACPI_MOVE_32_TO_16(d, s)        ACPI_MOVE_16_TO_16(d, s)	/* Truncate to 16 */
 
-#define ACPI_MOVE_32_TO_32(d,s)         {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[0];\
+#define ACPI_MOVE_32_TO_32(d, s)        {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[0];\
 										 ((  u8 *)(void *)(d))[1] = ((u8 *)(void *)(s))[1];\
 										 ((  u8 *)(void *)(d))[2] = ((u8 *)(void *)(s))[2];\
 										 ((  u8 *)(void *)(d))[3] = ((u8 *)(void *)(s))[3];}
 
-#define ACPI_MOVE_32_TO_64(d,s)         {(*(u64 *)(void *)(d)) = 0; ACPI_MOVE_32_TO_32(d,s);}
+#define ACPI_MOVE_32_TO_64(d, s)        {(*(u64 *)(void *)(d)) = 0; ACPI_MOVE_32_TO_32(d, s);}
 
 /* 64-bit source, 16/32/64 destination */
 
-#define ACPI_MOVE_64_TO_16(d,s)         ACPI_MOVE_16_TO_16(d,s)	/* Truncate to 16 */
-#define ACPI_MOVE_64_TO_32(d,s)         ACPI_MOVE_32_TO_32(d,s)	/* Truncate to 32 */
-#define ACPI_MOVE_64_TO_64(d,s)         {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[0];\
+#define ACPI_MOVE_64_TO_16(d, s)        ACPI_MOVE_16_TO_16(d, s)	/* Truncate to 16 */
+#define ACPI_MOVE_64_TO_32(d, s)        ACPI_MOVE_32_TO_32(d, s)	/* Truncate to 32 */
+#define ACPI_MOVE_64_TO_64(d, s)        {((  u8 *)(void *)(d))[0] = ((u8 *)(void *)(s))[0];\
 										 ((  u8 *)(void *)(d))[1] = ((u8 *)(void *)(s))[1];\
 										 ((  u8 *)(void *)(d))[2] = ((u8 *)(void *)(s))[2];\
 										 ((  u8 *)(void *)(d))[3] = ((u8 *)(void *)(s))[3];\
@@ -257,10 +249,10 @@ struct acpi_integer_overlay {
 /* Macros based on machine integer width */
 
 #if ACPI_MACHINE_WIDTH == 32
-#define ACPI_MOVE_SIZE_TO_16(d,s)       ACPI_MOVE_32_TO_16(d,s)
+#define ACPI_MOVE_SIZE_TO_16(d, s)       ACPI_MOVE_32_TO_16(d, s)
 
 #elif ACPI_MACHINE_WIDTH == 64
-#define ACPI_MOVE_SIZE_TO_16(d,s)       ACPI_MOVE_64_TO_16(d,s)
+#define ACPI_MOVE_SIZE_TO_16(d, s)       ACPI_MOVE_64_TO_16(d, s)
 
 #else
 #error unknown ACPI_MACHINE_WIDTH
@@ -269,29 +261,29 @@ struct acpi_integer_overlay {
 /*
  * Fast power-of-two math macros for non-optimized compilers
  */
-#define _ACPI_DIV(value,power_of2)      ((u32) ((value) >> (power_of2)))
-#define _ACPI_MUL(value,power_of2)      ((u32) ((value) << (power_of2)))
-#define _ACPI_MOD(value,divisor)        ((u32) ((value) & ((divisor) -1)))
+#define _ACPI_DIV(value, power_of2)      ((u32) ((value) >> (power_of2)))
+#define _ACPI_MUL(value, power_of2)      ((u32) ((value) << (power_of2)))
+#define _ACPI_MOD(value, divisor)        ((u32) ((value) & ((divisor) -1)))
 
-#define ACPI_DIV_2(a)                   _ACPI_DIV(a,1)
-#define ACPI_MUL_2(a)                   _ACPI_MUL(a,1)
-#define ACPI_MOD_2(a)                   _ACPI_MOD(a,2)
+#define ACPI_DIV_2(a)                   _ACPI_DIV(a, 1)
+#define ACPI_MUL_2(a)                   _ACPI_MUL(a, 1)
+#define ACPI_MOD_2(a)                   _ACPI_MOD(a, 2)
 
-#define ACPI_DIV_4(a)                   _ACPI_DIV(a,2)
-#define ACPI_MUL_4(a)                   _ACPI_MUL(a,2)
-#define ACPI_MOD_4(a)                   _ACPI_MOD(a,4)
+#define ACPI_DIV_4(a)                   _ACPI_DIV(a, 2)
+#define ACPI_MUL_4(a)                   _ACPI_MUL(a, 2)
+#define ACPI_MOD_4(a)                   _ACPI_MOD(a, 4)
 
-#define ACPI_DIV_8(a)                   _ACPI_DIV(a,3)
-#define ACPI_MUL_8(a)                   _ACPI_MUL(a,3)
-#define ACPI_MOD_8(a)                   _ACPI_MOD(a,8)
+#define ACPI_DIV_8(a)                   _ACPI_DIV(a, 3)
+#define ACPI_MUL_8(a)                   _ACPI_MUL(a, 3)
+#define ACPI_MOD_8(a)                   _ACPI_MOD(a, 8)
 
-#define ACPI_DIV_16(a)                  _ACPI_DIV(a,4)
-#define ACPI_MUL_16(a)                  _ACPI_MUL(a,4)
-#define ACPI_MOD_16(a)                  _ACPI_MOD(a,16)
+#define ACPI_DIV_16(a)                  _ACPI_DIV(a, 4)
+#define ACPI_MUL_16(a)                  _ACPI_MUL(a, 4)
+#define ACPI_MOD_16(a)                  _ACPI_MOD(a, 16)
 
-#define ACPI_DIV_32(a)                  _ACPI_DIV(a,5)
-#define ACPI_MUL_32(a)                  _ACPI_MUL(a,5)
-#define ACPI_MOD_32(a)                  _ACPI_MOD(a,32)
+#define ACPI_DIV_32(a)                  _ACPI_DIV(a, 5)
+#define ACPI_MUL_32(a)                  _ACPI_MUL(a, 5)
+#define ACPI_MOD_32(a)                  _ACPI_MOD(a, 32)
 
 /*
  * Rounding macros (Power of two boundaries only)
@@ -305,13 +297,13 @@ struct acpi_integer_overlay {
 
 /* Note: sizeof(acpi_size) evaluates to either 4 or 8 (32- vs 64-bit mode) */
 
-#define ACPI_ROUND_DOWN_TO_32BIT(a)         ACPI_ROUND_DOWN(a,4)
-#define ACPI_ROUND_DOWN_TO_64BIT(a)         ACPI_ROUND_DOWN(a,8)
-#define ACPI_ROUND_DOWN_TO_NATIVE_WORD(a)   ACPI_ROUND_DOWN(a,sizeof(acpi_size))
+#define ACPI_ROUND_DOWN_TO_32BIT(a)         ACPI_ROUND_DOWN(a, 4)
+#define ACPI_ROUND_DOWN_TO_64BIT(a)         ACPI_ROUND_DOWN(a, 8)
+#define ACPI_ROUND_DOWN_TO_NATIVE_WORD(a)   ACPI_ROUND_DOWN(a, sizeof(acpi_size))
 
-#define ACPI_ROUND_UP_TO_32BIT(a)           ACPI_ROUND_UP(a,4)
-#define ACPI_ROUND_UP_TO_64BIT(a)           ACPI_ROUND_UP(a,8)
-#define ACPI_ROUND_UP_TO_NATIVE_WORD(a)     ACPI_ROUND_UP(a,sizeof(acpi_size))
+#define ACPI_ROUND_UP_TO_32BIT(a)           ACPI_ROUND_UP(a, 4)
+#define ACPI_ROUND_UP_TO_64BIT(a)           ACPI_ROUND_UP(a, 8)
+#define ACPI_ROUND_UP_TO_NATIVE_WORD(a)     ACPI_ROUND_UP(a, sizeof(acpi_size))
 
 #define ACPI_ROUND_BITS_UP_TO_BYTES(a)      ACPI_DIV_8((a) + 7)
 #define ACPI_ROUND_BITS_DOWN_TO_BYTES(a)    ACPI_DIV_8((a))
@@ -320,9 +312,9 @@ struct acpi_integer_overlay {
 
 /* Generic (non-power-of-two) rounding */
 
-#define ACPI_ROUND_UP_TO(value,boundary)    (((value) + ((boundary)-1)) / (boundary))
+#define ACPI_ROUND_UP_TO(value, boundary)   (((value) + ((boundary)-1)) / (boundary))
 
-#define ACPI_IS_MISALIGNED(value)	    (((acpi_size)value) & (sizeof(acpi_size)-1))
+#define ACPI_IS_MISALIGNED(value)	    (((acpi_size) value) & (sizeof(acpi_size)-1))
 
 /*
  * Bitmask creation
@@ -333,8 +325,6 @@ struct acpi_integer_overlay {
 #define ACPI_MASK_BITS_ABOVE(position)      (~((ACPI_INTEGER_MAX) << ((u32) (position))))
 #define ACPI_MASK_BITS_BELOW(position)      ((ACPI_INTEGER_MAX) << ((u32) (position)))
 
-#define ACPI_IS_OCTAL_DIGIT(d)              (((char)(d) >= '0') && ((char)(d) <= '7'))
-
 /* Bitfields within ACPI registers */
 
 #define ACPI_REGISTER_PREPARE_BITS(val, pos, mask)      ((val << pos) & mask)
@@ -342,39 +332,29 @@ struct acpi_integer_overlay {
 
 #define ACPI_INSERT_BITS(target, mask, source)          target = ((target & (~(mask))) | (source & mask))
 
-/* Generate a UUID */
-
-#define ACPI_INIT_UUID(a,b,c,d0,d1,d2,d3,d4,d5,d6,d7) \
-	(a) & 0xFF, ((a) >> 8) & 0xFF, ((a) >> 16) & 0xFF, ((a) >> 24) & 0xFF, \
-	(b) & 0xFF, ((b) >> 8) & 0xFF, \
-	(c) & 0xFF, ((c) >> 8) & 0xFF, \
-	(d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7)
-
 /*
- * An struct acpi_namespace_node * can appear in some contexts,
- * where a pointer to an union acpi_operand_object    can also
- * appear.  This macro is used to distinguish them.
+ * An struct acpi_namespace_node can appear in some contexts
+ * where a pointer to an union acpi_operand_object can also
+ * appear. This macro is used to distinguish them.
  *
  * The "Descriptor" field is the first field in both structures.
  */
 #define ACPI_GET_DESCRIPTOR_TYPE(d)     (((union acpi_descriptor *)(void *)(d))->common.descriptor_type)
-#define ACPI_SET_DESCRIPTOR_TYPE(d,t)   (((union acpi_descriptor *)(void *)(d))->common.descriptor_type = t)
+#define ACPI_SET_DESCRIPTOR_TYPE(d, t)  (((union acpi_descriptor *)(void *)(d))->common.descriptor_type = t)
 
 /* Macro to test the object type */
 
 #define ACPI_GET_OBJECT_TYPE(d)         (((union acpi_operand_object *)(void *)(d))->common.type)
 
-/* Macro to check the table flags for SINGLE or MULTIPLE tables are allowed */
-
-#define ACPI_IS_SINGLE_TABLE(x)         (((x) & 0x01) == ACPI_TABLE_SINGLE ? 1 : 0)
-
 /*
  * Macros for the master AML opcode table
  */
-#if defined(ACPI_DISASSEMBLER) || defined (ACPI_DEBUG_OUTPUT)
-#define ACPI_OP(name,Pargs,Iargs,obj_type,class,type,flags)    {name,(u32)(Pargs),(u32)(Iargs),(u32)(flags),obj_type,class,type}
+#if defined (ACPI_DISASSEMBLER) || defined (ACPI_DEBUG_OUTPUT)
+#define ACPI_OP(name, Pargs, Iargs, obj_type, class, type, flags) \
+	{name, (u32)(Pargs), (u32)(Iargs), (u32)(flags), obj_type, class, type}
 #else
-#define ACPI_OP(name,Pargs,Iargs,obj_type,class,type,flags)    {(u32)(Pargs),(u32)(Iargs),(u32)(flags),obj_type,class,type}
+#define ACPI_OP(name, Pargs, Iargs, obj_type, class, type, flags) \
+	{(u32)(Pargs), (u32)(Iargs), (u32)(flags), obj_type, class, type}
 #endif
 
 #ifdef ACPI_DISASSEMBLER
@@ -392,18 +372,18 @@ struct acpi_integer_overlay {
 #define ARG_6(x)                        ((u32)(x) << (5 * ARG_TYPE_WIDTH))
 
 #define ARGI_LIST1(a)                   (ARG_1(a))
-#define ARGI_LIST2(a,b)                 (ARG_1(b)|ARG_2(a))
-#define ARGI_LIST3(a,b,c)               (ARG_1(c)|ARG_2(b)|ARG_3(a))
-#define ARGI_LIST4(a,b,c,d)             (ARG_1(d)|ARG_2(c)|ARG_3(b)|ARG_4(a))
-#define ARGI_LIST5(a,b,c,d,e)           (ARG_1(e)|ARG_2(d)|ARG_3(c)|ARG_4(b)|ARG_5(a))
-#define ARGI_LIST6(a,b,c,d,e,f)         (ARG_1(f)|ARG_2(e)|ARG_3(d)|ARG_4(c)|ARG_5(b)|ARG_6(a))
+#define ARGI_LIST2(a, b)                (ARG_1(b)|ARG_2(a))
+#define ARGI_LIST3(a, b, c)             (ARG_1(c)|ARG_2(b)|ARG_3(a))
+#define ARGI_LIST4(a, b, c, d)          (ARG_1(d)|ARG_2(c)|ARG_3(b)|ARG_4(a))
+#define ARGI_LIST5(a, b, c, d, e)       (ARG_1(e)|ARG_2(d)|ARG_3(c)|ARG_4(b)|ARG_5(a))
+#define ARGI_LIST6(a, b, c, d, e, f)    (ARG_1(f)|ARG_2(e)|ARG_3(d)|ARG_4(c)|ARG_5(b)|ARG_6(a))
 
 #define ARGP_LIST1(a)                   (ARG_1(a))
-#define ARGP_LIST2(a,b)                 (ARG_1(a)|ARG_2(b))
-#define ARGP_LIST3(a,b,c)               (ARG_1(a)|ARG_2(b)|ARG_3(c))
-#define ARGP_LIST4(a,b,c,d)             (ARG_1(a)|ARG_2(b)|ARG_3(c)|ARG_4(d))
-#define ARGP_LIST5(a,b,c,d,e)           (ARG_1(a)|ARG_2(b)|ARG_3(c)|ARG_4(d)|ARG_5(e))
-#define ARGP_LIST6(a,b,c,d,e,f)         (ARG_1(a)|ARG_2(b)|ARG_3(c)|ARG_4(d)|ARG_5(e)|ARG_6(f))
+#define ARGP_LIST2(a, b)                (ARG_1(a)|ARG_2(b))
+#define ARGP_LIST3(a, b, c)             (ARG_1(a)|ARG_2(b)|ARG_3(c))
+#define ARGP_LIST4(a, b, c, d)          (ARG_1(a)|ARG_2(b)|ARG_3(c)|ARG_4(d))
+#define ARGP_LIST5(a, b, c, d, e)       (ARG_1(a)|ARG_2(b)|ARG_3(c)|ARG_4(d)|ARG_5(e))
+#define ARGP_LIST6(a, b, c, d, e, f)    (ARG_1(a)|ARG_2(b)|ARG_3(c)|ARG_4(d)|ARG_5(e)|ARG_6(f))
 
 #define GET_CURRENT_ARG_TYPE(list)      (list & ((u32) 0x1F))
 #define INCREMENT_ARG_LIST(list)        (list >>= ((u32) ARG_TYPE_WIDTH))
@@ -434,8 +414,8 @@ struct acpi_integer_overlay {
 #define ACPI_WARNING(plist)             acpi_ut_warning plist
 #define ACPI_EXCEPTION(plist)           acpi_ut_exception plist
 #define ACPI_ERROR(plist)               acpi_ut_error plist
-#define ACPI_ERROR_NAMESPACE(s,e)       acpi_ns_report_error (AE_INFO, s, e);
-#define ACPI_ERROR_METHOD(s,n,p,e)      acpi_ns_report_method_error (AE_INFO, s, n, p, e);
+#define ACPI_ERROR_NAMESPACE(s, e)      acpi_ns_report_error (AE_INFO, s, e);
+#define ACPI_ERROR_METHOD(s, n, p, e)   acpi_ns_report_method_error (AE_INFO, s, n, p, e);
 
 #else
 
@@ -445,8 +425,8 @@ struct acpi_integer_overlay {
 #define ACPI_WARNING(plist)
 #define ACPI_EXCEPTION(plist)
 #define ACPI_ERROR(plist)
-#define ACPI_ERROR_NAMESPACE(s,e)
-#define ACPI_ERROR_METHOD(s,n,p,e)
+#define ACPI_ERROR_NAMESPACE(s, e)
+#define ACPI_ERROR_METHOD(s, n, p, e)
 #endif
 
 /*
@@ -489,18 +469,18 @@ struct acpi_integer_overlay {
 
 #define ACPI_FUNCTION_TRACE(a)          ACPI_FUNCTION_NAME(a) \
 			  acpi_ut_trace(ACPI_DEBUG_PARAMETERS)
-#define ACPI_FUNCTION_TRACE_PTR(a,b)    ACPI_FUNCTION_NAME(a) \
-					   acpi_ut_trace_ptr(ACPI_DEBUG_PARAMETERS,(void *)b)
-#define ACPI_FUNCTION_TRACE_U32(a,b)    ACPI_FUNCTION_NAME(a) \
-							 acpi_ut_trace_u32(ACPI_DEBUG_PARAMETERS,(u32)b)
-#define ACPI_FUNCTION_TRACE_STR(a,b)    ACPI_FUNCTION_NAME(a) \
-									  acpi_ut_trace_str(ACPI_DEBUG_PARAMETERS,(char *)b)
+#define ACPI_FUNCTION_TRACE_PTR(a, b)   ACPI_FUNCTION_NAME(a) \
+					   acpi_ut_trace_ptr(ACPI_DEBUG_PARAMETERS, (void *)b)
+#define ACPI_FUNCTION_TRACE_U32(a, b)   ACPI_FUNCTION_NAME(a) \
+							 acpi_ut_trace_u32(ACPI_DEBUG_PARAMETERS, (u32)b)
+#define ACPI_FUNCTION_TRACE_STR(a, b)   ACPI_FUNCTION_NAME(a) \
+									  acpi_ut_trace_str(ACPI_DEBUG_PARAMETERS, (char *)b)
 
 #define ACPI_FUNCTION_ENTRY()           acpi_ut_track_stack_ptr()
 
 /*
  * Function exit tracing.
- * WARNING: These macros include a return statement.  This is usually considered
+ * WARNING: These macros include a return statement. This is usually considered
  * bad form, but having a separate exit macro is very ugly and difficult to maintain.
  * One of the FUNCTION_TRACE macros above must be used in conjunction with these macros
  * so that "_AcpiFunctionName" is defined.
@@ -596,13 +576,13 @@ struct acpi_integer_overlay {
 
 /* Stack and buffer dumping */
 
-#define ACPI_DUMP_STACK_ENTRY(a)        acpi_ex_dump_operand((a),0)
-#define ACPI_DUMP_OPERANDS(a,b,c)	acpi_ex_dump_operands(a,b,c)
+#define ACPI_DUMP_STACK_ENTRY(a)        acpi_ex_dump_operand((a), 0)
+#define ACPI_DUMP_OPERANDS(a, b, c)	acpi_ex_dump_operands(a, b, c)
 
-#define ACPI_DUMP_ENTRY(a,b)            acpi_ns_dump_entry (a,b)
-#define ACPI_DUMP_PATHNAME(a,b,c,d)     acpi_ns_dump_pathname(a,b,c,d)
+#define ACPI_DUMP_ENTRY(a, b)           acpi_ns_dump_entry (a, b)
+#define ACPI_DUMP_PATHNAME(a, b, c, d)  acpi_ns_dump_pathname(a, b, c, d)
 #define ACPI_DUMP_RESOURCE_LIST(a)      acpi_rs_dump_resource_list(a)
-#define ACPI_DUMP_BUFFER(a,b)           acpi_ut_dump_buffer((u8 *)a,b,DB_BYTE_DISPLAY,_COMPONENT)
+#define ACPI_DUMP_BUFFER(a, b)          acpi_ut_dump_buffer((u8 *) a, b, DB_BYTE_DISPLAY, _COMPONENT)
 
 /*
  * Master debug print macros
@@ -625,20 +605,20 @@ struct acpi_integer_overlay {
 #define ACPI_DEBUG_ONLY_MEMBERS(a)	do { } while(0)
 #define ACPI_FUNCTION_NAME(a)		do { } while(0)
 #define ACPI_FUNCTION_TRACE(a)		do { } while(0)
-#define ACPI_FUNCTION_TRACE_PTR(a,b)	do { } while(0)
-#define ACPI_FUNCTION_TRACE_U32(a,b)	do { } while(0)
-#define ACPI_FUNCTION_TRACE_STR(a,b)	do { } while(0)
+#define ACPI_FUNCTION_TRACE_PTR(a, b)	do { } while(0)
+#define ACPI_FUNCTION_TRACE_U32(a, b)	do { } while(0)
+#define ACPI_FUNCTION_TRACE_STR(a, b)	do { } while(0)
 #define ACPI_FUNCTION_EXIT		do { } while(0)
 #define ACPI_FUNCTION_STATUS_EXIT(s)	do { } while(0)
 #define ACPI_FUNCTION_VALUE_EXIT(s)	do { } while(0)
 #define ACPI_FUNCTION_ENTRY()		do { } while(0)
 #define ACPI_DUMP_STACK_ENTRY(a)	do { } while(0)
-#define ACPI_DUMP_OPERANDS(a,b,c)      do { } while(0)
-#define ACPI_DUMP_ENTRY(a,b)		do { } while(0)
-#define ACPI_DUMP_TABLES(a,b)		do { } while(0)
-#define ACPI_DUMP_PATHNAME(a,b,c,d)	do { } while(0)
+#define ACPI_DUMP_OPERANDS(a, b, c)     do { } while(0)
+#define ACPI_DUMP_ENTRY(a, b)		do { } while(0)
+#define ACPI_DUMP_TABLES(a, b)		do { } while(0)
+#define ACPI_DUMP_PATHNAME(a, b, c, d)	do { } while(0)
 #define ACPI_DUMP_RESOURCE_LIST(a)	do { } while(0)
-#define ACPI_DUMP_BUFFER(a,b)		do { } while(0)
+#define ACPI_DUMP_BUFFER(a, b)		do { } while(0)
 #define ACPI_DEBUG_PRINT(pl)		do { } while(0)
 #define ACPI_DEBUG_PRINT_RAW(pl)	do { } while(0)
 
@@ -677,15 +657,17 @@ struct acpi_integer_overlay {
 /*
  * Memory allocation tracking (DEBUG ONLY)
  */
+#define ACPI_MEM_PARAMETERS         _COMPONENT, _acpi_module_name, __LINE__
+
 #ifndef ACPI_DBG_TRACK_ALLOCATIONS
 
 /* Memory allocation */
 
 #ifndef ACPI_ALLOCATE
-#define ACPI_ALLOCATE(a)            acpi_ut_allocate((acpi_size)(a),_COMPONENT,_acpi_module_name,__LINE__)
+#define ACPI_ALLOCATE(a)            acpi_ut_allocate((acpi_size)(a), ACPI_MEM_PARAMETERS)
 #endif
 #ifndef ACPI_ALLOCATE_ZEROED
-#define ACPI_ALLOCATE_ZEROED(a)     acpi_ut_allocate_zeroed((acpi_size)(a), _COMPONENT,_acpi_module_name,__LINE__)
+#define ACPI_ALLOCATE_ZEROED(a)     acpi_ut_allocate_zeroed((acpi_size)(a), ACPI_MEM_PARAMETERS)
 #endif
 #ifndef ACPI_FREE
 #define ACPI_FREE(a)                acpio_os_free(a)
@@ -696,9 +678,9 @@ struct acpi_integer_overlay {
 
 /* Memory allocation */
 
-#define ACPI_ALLOCATE(a)            acpi_ut_allocate_and_track((acpi_size)(a),_COMPONENT,_acpi_module_name,__LINE__)
-#define ACPI_ALLOCATE_ZEROED(a)     acpi_ut_allocate_zeroed_and_track((acpi_size)(a), _COMPONENT,_acpi_module_name,__LINE__)
-#define ACPI_FREE(a)                acpi_ut_free_and_track(a,_COMPONENT,_acpi_module_name,__LINE__)
+#define ACPI_ALLOCATE(a)            acpi_ut_allocate_and_track((acpi_size)(a), ACPI_MEM_PARAMETERS)
+#define ACPI_ALLOCATE_ZEROED(a)     acpi_ut_allocate_zeroed_and_track((acpi_size)(a), ACPI_MEM_PARAMETERS)
+#define ACPI_FREE(a)                acpi_ut_free_and_track(a, ACPI_MEM_PARAMETERS)
 #define ACPI_MEM_TRACKING(a)        a
 
 #endif				/* ACPI_DBG_TRACK_ALLOCATIONS */
-- 
cgit v1.2.3


From 0a1fbf2db0d275f0f8160bb9c3e51c4df5bafdc2 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Fri, 4 Jul 2008 10:53:58 +0800
Subject: ACPICA: Return method arg count from acpi_get_object_info

Also update the debugger so that the correct number of arguments is
passed to the method. Prevents a warning message from the debugger.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/namespace/nsxfname.c | 4 ++++
 include/acpi/actypes.h            | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/namespace/nsxfname.c b/drivers/acpi/namespace/nsxfname.c
index 3cb910ded44a..5efa4e7ddb0b 100644
--- a/drivers/acpi/namespace/nsxfname.c
+++ b/drivers/acpi/namespace/nsxfname.c
@@ -265,6 +265,10 @@ acpi_get_object_info(acpi_handle handle, struct acpi_buffer * buffer)
 	info->name = node->name.integer;
 	info->valid = 0;
 
+	if (node->type == ACPI_TYPE_METHOD) {
+		info->param_count = node->object->method.param_count;
+	}
+
 	status = acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
 	if (ACPI_FAILURE(status)) {
 		goto cleanup;
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 73d6b1cb07f3..6bd08e83f31c 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -859,6 +859,7 @@ struct acpi_obj_info_header {
 struct acpi_device_info {
 	ACPI_COMMON_OBJ_INFO;
 
+	u32 param_count;	/* If a method, required parameter count */
 	u32 valid;		/* Indicates which fields below are valid */
 	u32 current_status;	/* _STA value */
 	acpi_integer address;	/* _ADR value if any */
-- 
cgit v1.2.3


From d00d23651d17a2848f6923f3b1ec4efe19f5f2f1 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Mon, 4 Aug 2008 10:12:31 +0800
Subject: ACPICA: Update version to 20080701

Update version to 20080701.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 include/acpi/acconfig.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h
index 4eb75a88795a..328caeee821e 100644
--- a/include/acpi/acconfig.h
+++ b/include/acpi/acconfig.h
@@ -63,7 +63,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION 		0x20080609
+#define ACPI_CA_VERSION 		0x20080701
 
 /*
  * OS name, used for the _OS object.  The _OS object is essentially obsolete,
-- 
cgit v1.2.3


From f02a99ac66748f8b62477c86f6df04d3ec6169fd Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Mon, 4 Aug 2008 10:40:09 +0800
Subject: ACPICA: Add function to decode reference obj types to strings

Created for improved error messages.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/utilities/utglobal.c | 36 ++++++++++++++++++++++++++++++++++++
 include/acpi/acutils.h            |  2 ++
 2 files changed, 38 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/utilities/utglobal.c b/drivers/acpi/utilities/utglobal.c
index 248eefc369f8..bcace577183b 100644
--- a/drivers/acpi/utilities/utglobal.c
+++ b/drivers/acpi/utilities/utglobal.c
@@ -45,6 +45,7 @@
 
 #include <acpi/acpi.h>
 #include <acpi/acnamesp.h>
+#include <acpi/amlcode.h>
 
 ACPI_EXPORT_SYMBOL(acpi_gbl_FADT)
 #define _COMPONENT          ACPI_UTILITIES
@@ -575,6 +576,41 @@ char *acpi_ut_get_descriptor_name(void *object)
 
 }
 
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ut_get_reference_name
+ *
+ * PARAMETERS:  Object               - An ACPI reference object
+ *
+ * RETURN:      Pointer to a string
+ *
+ * DESCRIPTION: Decode a reference object sub-type to a string.
+ *
+ ******************************************************************************/
+
+/* Printable names of reference object sub-types */
+
+const char *acpi_ut_get_reference_name(union acpi_operand_object *object)
+{
+
+	switch (object->reference.opcode) {
+	case AML_INT_NAMEPATH_OP:
+		return "Name";
+
+	case AML_LOAD_OP:
+		return "DDB-Handle";
+
+	case AML_REF_OF_OP:
+		return "RefOf";
+
+	case AML_INDEX_OP:
+		return "Index";
+
+	default:
+		return "Unknown";
+	}
+}
+
 #if defined(ACPI_DEBUG_OUTPUT) || defined(ACPI_DEBUGGER)
 /*
  * Strings and procedures used for debug only
diff --git a/include/acpi/acutils.h b/include/acpi/acutils.h
index 10ce81406f9c..d8307b2987e3 100644
--- a/include/acpi/acutils.h
+++ b/include/acpi/acutils.h
@@ -126,6 +126,8 @@ char *acpi_ut_get_node_name(void *object);
 
 char *acpi_ut_get_descriptor_name(void *object);
 
+const char *acpi_ut_get_reference_name(union acpi_operand_object *object);
+
 char *acpi_ut_get_object_type_name(union acpi_operand_object *obj_desc);
 
 char *acpi_ut_get_region_name(u8 space_id);
-- 
cgit v1.2.3


From 1d7cc03049f7c9c5cced9208a39316c5245ef314 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Mon, 4 Aug 2008 10:42:47 +0800
Subject: ACPICA: x2APIC support: changes for MADT and SRAT ACPI tables

Support for the x2APIC. There are 2 new subtables for the MADT and
one new subtable for the SRAT. Includes disassembler and acpisrc
support. Data from the Intel 64 Architecture x2APIC Specification,
June 2008.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 include/acpi/acdisasm.h |  4 ++++
 include/acpi/actbl1.h   | 51 +++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 49 insertions(+), 6 deletions(-)

(limited to 'include')

diff --git a/include/acpi/acdisasm.h b/include/acpi/acdisasm.h
index f53faca8ec80..0c1ed387073c 100644
--- a/include/acpi/acdisasm.h
+++ b/include/acpi/acdisasm.h
@@ -186,6 +186,8 @@ extern struct acpi_dmtable_info acpi_dm_table_info_madt5[];
 extern struct acpi_dmtable_info acpi_dm_table_info_madt6[];
 extern struct acpi_dmtable_info acpi_dm_table_info_madt7[];
 extern struct acpi_dmtable_info acpi_dm_table_info_madt8[];
+extern struct acpi_dmtable_info acpi_dm_table_info_madt9[];
+extern struct acpi_dmtable_info acpi_dm_table_info_madt10[];
 extern struct acpi_dmtable_info acpi_dm_table_info_madt_hdr[];
 extern struct acpi_dmtable_info acpi_dm_table_info_mcfg[];
 extern struct acpi_dmtable_info acpi_dm_table_info_mcfg0[];
@@ -197,8 +199,10 @@ extern struct acpi_dmtable_info acpi_dm_table_info_slit[];
 extern struct acpi_dmtable_info acpi_dm_table_info_spcr[];
 extern struct acpi_dmtable_info acpi_dm_table_info_spmi[];
 extern struct acpi_dmtable_info acpi_dm_table_info_srat[];
+extern struct acpi_dmtable_info acpi_dm_table_info_srat_hdr[];
 extern struct acpi_dmtable_info acpi_dm_table_info_srat0[];
 extern struct acpi_dmtable_info acpi_dm_table_info_srat1[];
+extern struct acpi_dmtable_info acpi_dm_table_info_srat2[];
 extern struct acpi_dmtable_info acpi_dm_table_info_tcpa[];
 extern struct acpi_dmtable_info acpi_dm_table_info_wdrt[];
 
diff --git a/include/acpi/actbl1.h b/include/acpi/actbl1.h
index d38f9be2f6ee..63f5b4cf4de1 100644
--- a/include/acpi/actbl1.h
+++ b/include/acpi/actbl1.h
@@ -908,7 +908,9 @@ enum acpi_madt_type {
 	ACPI_MADT_TYPE_IO_SAPIC = 6,
 	ACPI_MADT_TYPE_LOCAL_SAPIC = 7,
 	ACPI_MADT_TYPE_INTERRUPT_SOURCE = 8,
-	ACPI_MADT_TYPE_RESERVED = 9	/* 9 and greater are reserved */
+	ACPI_MADT_TYPE_LOCAL_X2APIC = 9,
+	ACPI_MADT_TYPE_LOCAL_X2APIC_NMI = 10,
+	ACPI_MADT_TYPE_RESERVED = 11	/* 11 and greater are reserved */
 };
 
 /*
@@ -1009,6 +1011,26 @@ struct acpi_madt_interrupt_source {
 
 #define ACPI_MADT_CPEI_OVERRIDE     (1)
 
+/* 9: Processor Local X2_APIC (07/2008) */
+
+struct acpi_madt_local_x2apic {
+	struct acpi_subtable_header header;
+	u16 reserved;		/* Reserved - must be zero */
+	u32 local_apic_id;	/* Processor X2_APIC ID  */
+	u32 lapic_flags;
+	u32 uid;		/* Extended X2_APIC processor ID */
+};
+
+/* 10: Local X2APIC NMI (07/2008) */
+
+struct acpi_madt_local_x2apic_nmi {
+	struct acpi_subtable_header header;
+	u16 inti_flags;
+	u32 uid;		/* Processor X2_APIC ID */
+	u8 lint;		/* LINTn to which NMI is connected */
+	u8 reserved[3];
+};
+
 /*
  * Common flags fields for MADT subtables
  */
@@ -1150,10 +1172,15 @@ struct acpi_table_srat {
 enum acpi_srat_type {
 	ACPI_SRAT_TYPE_CPU_AFFINITY = 0,
 	ACPI_SRAT_TYPE_MEMORY_AFFINITY = 1,
-	ACPI_SRAT_TYPE_RESERVED = 2
+	ACPI_SRAT_TYPE_X2APIC_CPU_AFFINITY = 2,
+	ACPI_SRAT_TYPE_RESERVED = 3	/* 3 and greater are reserved */
 };
 
-/* SRAT sub-tables */
+/*
+ * SRAT Sub-tables, correspond to Type in struct acpi_subtable_header
+ */
+
+/* 0: Processor Local APIC/SAPIC Affinity */
 
 struct acpi_srat_cpu_affinity {
 	struct acpi_subtable_header header;
@@ -1165,9 +1192,7 @@ struct acpi_srat_cpu_affinity {
 	u32 reserved;		/* Reserved, must be zero */
 };
 
-/* Flags */
-
-#define ACPI_SRAT_CPU_ENABLED       (1)	/* 00: Use affinity structure */
+/* 1: Memory Affinity */
 
 struct acpi_srat_mem_affinity {
 	struct acpi_subtable_header header;
@@ -1186,6 +1211,20 @@ struct acpi_srat_mem_affinity {
 #define ACPI_SRAT_MEM_HOT_PLUGGABLE (1<<1)	/* 01: Memory region is hot pluggable */
 #define ACPI_SRAT_MEM_NON_VOLATILE  (1<<2)	/* 02: Memory region is non-volatile */
 
+/* 2: Processor Local X2_APIC Affinity (07/2008) */
+
+struct acpi_srat_x2apic_cpu_affinity {
+	struct acpi_subtable_header header;
+	u16 reserved;		/* Reserved, must be zero */
+	u32 proximity_domain;
+	u32 apic_id;
+	u32 flags;
+};
+
+/* Flags for struct acpi_srat_cpu_affinity and struct acpi_srat_x2apic_cpu_affinity */
+
+#define ACPI_SRAT_CPU_ENABLED       (1)	/* 00: Use affinity structure */
+
 /*******************************************************************************
  *
  * TCPA - Trusted Computing Platform Alliance table
-- 
cgit v1.2.3


From eec935490172dbfa1a32647f9deb2b66a66f2741 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Mon, 4 Aug 2008 11:15:11 +0800
Subject: ACPICA: Update version to 20080729

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 include/acpi/acconfig.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h
index 328caeee821e..4da88b165b5c 100644
--- a/include/acpi/acconfig.h
+++ b/include/acpi/acconfig.h
@@ -63,7 +63,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION 		0x20080701
+#define ACPI_CA_VERSION 		0x20080729
 
 /*
  * OS name, used for the _OS object.  The _OS object is essentially obsolete,
-- 
cgit v1.2.3


From 8bd108d14604d9c95000751e6c6ecbd11ea6ed40 Mon Sep 17 00:00:00 2001
From: Alexey Starikovskiy <astarikovskiy@suse.de>
Date: Thu, 25 Sep 2008 21:40:30 +0400
Subject: ACPICA: add preemption point after each opcode parse

Reference: http://marc.info/?l=linux-acpi&m=122236382701062&w=2

Signed-off-by: Alexey Starikovskiy <astarikovskiy@suse.de>
Tested-by: Sitsofe Wheeler <sitsofe@yahoo.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/parser/psloop.c    | 2 ++
 include/acpi/acmacros.h         | 5 +++++
 include/acpi/platform/aclinux.h | 6 ++++++
 3 files changed, 13 insertions(+)

(limited to 'include')

diff --git a/drivers/acpi/parser/psloop.c b/drivers/acpi/parser/psloop.c
index c06238e55d98..4647039a0d8a 100644
--- a/drivers/acpi/parser/psloop.c
+++ b/drivers/acpi/parser/psloop.c
@@ -719,6 +719,8 @@ acpi_ps_complete_op(struct acpi_walk_state *walk_state,
 		*op = NULL;
 	}
 
+	ACPI_PREEMPTION_POINT();
+
 	return_ACPI_STATUS(AE_OK);
 }
 
diff --git a/include/acpi/acmacros.h b/include/acpi/acmacros.h
index 2106f9136cce..a1e3240bf460 100644
--- a/include/acpi/acmacros.h
+++ b/include/acpi/acmacros.h
@@ -685,4 +685,9 @@ struct acpi_integer_overlay {
 
 #endif				/* ACPI_DBG_TRACK_ALLOCATIONS */
 
+/* Preemption point */
+#ifndef ACPI_PREEMPTION_POINT
+#define ACPI_PREEMPTION_POINT() /* no preemption */
+#endif
+
 #endif				/* ACMACROS_H */
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 9af464598682..029c8c06c151 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -53,6 +53,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/ctype.h>
+#include <linux/sched.h>
 #include <asm/system.h>
 #include <asm/atomic.h>
 #include <asm/div64.h>
@@ -137,4 +138,9 @@ static inline void *acpi_os_acquire_object(acpi_cache_t * cache)
 #define ACPI_ALLOCATE_ZEROED(a)	acpi_os_allocate_zeroed(a)
 #define ACPI_FREE(a)		kfree(a)
 
+/*
+ * We need to show where it is safe to preempt execution of ACPICA
+ */
+#define ACPI_PREEMPTION_POINT()	cond_resched()
+
 #endif				/* __ACLINUX_H__ */
-- 
cgit v1.2.3


From 23d3e055beb12db2a3b91dfeee474c4d5ecc13b9 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Sun, 28 Sep 2008 15:00:47 +0800
Subject: ACPICA: Remove obsolete debug levels (WARN and ERROR)

Removed ACPI_DB_WARN and ACPI_DB_ERROR. These debug levels were
made obsolete by the ACPI_WARNING and ACPI_ERROR/ACPI_EXCEPTION
interfaces.  Also added ACPI_DB_EVENTS to correspond with the
existing ACPI_LV_EVENTS.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/debug.c              |  2 --
 drivers/acpi/executer/exstore.c   |  2 +-
 drivers/acpi/namespace/nssearch.c |  2 +-
 include/acpi/acoutput.h           | 32 +++++++++++++-------------------
 4 files changed, 15 insertions(+), 23 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/debug.c b/drivers/acpi/debug.c
index 6df564f4ca6e..abf36b4b1d1d 100644
--- a/drivers/acpi/debug.c
+++ b/drivers/acpi/debug.c
@@ -47,8 +47,6 @@ static const struct acpi_dlayer acpi_debug_layers[] = {
 };
 
 static const struct acpi_dlevel acpi_debug_levels[] = {
-	ACPI_DEBUG_INIT(ACPI_LV_ERROR),
-	ACPI_DEBUG_INIT(ACPI_LV_WARN),
 	ACPI_DEBUG_INIT(ACPI_LV_INIT),
 	ACPI_DEBUG_INIT(ACPI_LV_DEBUG_OBJECT),
 	ACPI_DEBUG_INIT(ACPI_LV_INFO),
diff --git a/drivers/acpi/executer/exstore.c b/drivers/acpi/executer/exstore.c
index 38b55e352495..09e96846d155 100644
--- a/drivers/acpi/executer/exstore.c
+++ b/drivers/acpi/executer/exstore.c
@@ -403,7 +403,7 @@ acpi_ex_store(union acpi_operand_object *source_desc,
 
 		ACPI_ERROR((AE_INFO, "Unknown Reference opcode %X",
 			    ref_desc->reference.opcode));
-		ACPI_DUMP_ENTRY(ref_desc, ACPI_LV_ERROR);
+		ACPI_DUMP_ENTRY(ref_desc, ACPI_LV_INFO);
 
 		status = AE_AML_INTERNAL;
 		break;
diff --git a/drivers/acpi/namespace/nssearch.c b/drivers/acpi/namespace/nssearch.c
index 8399276cba1e..a9a80bf811b3 100644
--- a/drivers/acpi/namespace/nssearch.c
+++ b/drivers/acpi/namespace/nssearch.c
@@ -331,7 +331,7 @@ acpi_ns_search_and_enter(u32 target_name,
 				      "Found bad character(s) in name, repaired: [%4.4s]\n",
 				      ACPI_CAST_PTR(char, &target_name)));
 		} else {
-			ACPI_DEBUG_PRINT((ACPI_DB_WARN,
+			ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 					  "Found bad character(s) in name, repaired: [%4.4s]\n",
 					  ACPI_CAST_PTR(char, &target_name)));
 		}
diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h
index e17873defcec..09d33c7740f0 100644
--- a/include/acpi/acoutput.h
+++ b/include/acpi/acoutput.h
@@ -80,12 +80,10 @@
 /*
  * Raw debug output levels, do not use these in the DEBUG_PRINT macros
  */
-#define ACPI_LV_ERROR               0x00000001
-#define ACPI_LV_WARN                0x00000002
-#define ACPI_LV_INIT                0x00000004
-#define ACPI_LV_DEBUG_OBJECT        0x00000008
-#define ACPI_LV_INFO                0x00000010
-#define ACPI_LV_ALL_EXCEPTIONS      0x0000001F
+#define ACPI_LV_INIT                0x00000001
+#define ACPI_LV_DEBUG_OBJECT        0x00000002
+#define ACPI_LV_INFO                0x00000004
+#define ACPI_LV_ALL_EXCEPTIONS      0x00000007
 
 /* Trace verbosity level 1 [Standard Trace Level] */
 
@@ -127,7 +125,6 @@
 #define ACPI_LV_VERBOSE_INFO        0x20000000
 #define ACPI_LV_FULL_TABLES         0x40000000
 #define ACPI_LV_EVENTS              0x80000000
-
 #define ACPI_LV_VERBOSE             0xF0000000
 
 /*
@@ -135,21 +132,17 @@
  */
 #define ACPI_DEBUG_LEVEL(dl)        (u32) dl,ACPI_DEBUG_PARAMETERS
 
-/* Exception level -- used in the global "DebugLevel" */
-
+/*
+ * Exception level -- used in the global "DebugLevel"
+ *
+ * Note: For errors, use the ACPI_ERROR or ACPI_EXCEPTION interfaces.
+ * For warnings, use ACPI_WARNING.
+ */
 #define ACPI_DB_INIT                ACPI_DEBUG_LEVEL (ACPI_LV_INIT)
 #define ACPI_DB_DEBUG_OBJECT        ACPI_DEBUG_LEVEL (ACPI_LV_DEBUG_OBJECT)
 #define ACPI_DB_INFO                ACPI_DEBUG_LEVEL (ACPI_LV_INFO)
 #define ACPI_DB_ALL_EXCEPTIONS      ACPI_DEBUG_LEVEL (ACPI_LV_ALL_EXCEPTIONS)
 
-/*
- * These two levels are essentially obsolete, all instances in the
- * ACPICA core code have been replaced by ACPI_ERROR and ACPI_WARNING
- * (Kept here because some drivers may still use them)
- */
-#define ACPI_DB_ERROR               ACPI_DEBUG_LEVEL (ACPI_LV_ERROR)
-#define ACPI_DB_WARN                ACPI_DEBUG_LEVEL (ACPI_LV_WARN)
-
 /* Trace level -- also used in the global "DebugLevel" */
 
 #define ACPI_DB_INIT_NAMES          ACPI_DEBUG_LEVEL (ACPI_LV_INIT_NAMES)
@@ -173,13 +166,14 @@
 #define ACPI_DB_USER_REQUESTS       ACPI_DEBUG_LEVEL (ACPI_LV_USER_REQUESTS)
 #define ACPI_DB_PACKAGE             ACPI_DEBUG_LEVEL (ACPI_LV_PACKAGE)
 #define ACPI_DB_MUTEX               ACPI_DEBUG_LEVEL (ACPI_LV_MUTEX)
+#define ACPI_DB_EVENTS              ACPI_DEBUG_LEVEL (ACPI_LV_EVENTS)
 
 #define ACPI_DB_ALL                 ACPI_DEBUG_LEVEL (ACPI_LV_ALL)
 
 /* Defaults for debug_level, debug and normal */
 
-#define ACPI_DEBUG_DEFAULT          (ACPI_LV_INIT | ACPI_LV_WARN | ACPI_LV_ERROR)
-#define ACPI_NORMAL_DEFAULT         (ACPI_LV_INIT | ACPI_LV_WARN | ACPI_LV_ERROR)
+#define ACPI_DEBUG_DEFAULT          (ACPI_LV_INIT | ACPI_LV_DEBUG_OBJECT)
+#define ACPI_NORMAL_DEFAULT         (ACPI_LV_INIT | ACPI_LV_DEBUG_OBJECT)
 #define ACPI_DEBUG_ALL              (ACPI_LV_AML_DISASSEMBLE | ACPI_LV_ALL_EXCEPTIONS | ACPI_LV_ALL)
 
 #endif				/* __ACOUTPUT_H__ */
-- 
cgit v1.2.3


From 8d5c54b65b20bf81fa9841a27143e2f71f3a7756 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Sat, 27 Sep 2008 10:22:09 +0800
Subject: ACPICA: Add namespace node to operand object union

Add ACPI_NAMESPACE_NODE to the ACPI_OPERAND_OBJECT in order to
simplify code that accepts both of these objects. A common type
field is used to differentiate them.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 include/acpi/acobject.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include')

diff --git a/include/acpi/acobject.h b/include/acpi/acobject.h
index e9657dac69b7..0ca39265bb0f 100644
--- a/include/acpi/acobject.h
+++ b/include/acpi/acobject.h
@@ -379,6 +379,13 @@ union acpi_operand_object {
 	struct acpi_object_extra extra;
 	struct acpi_object_data data;
 	struct acpi_object_cache_list cache;
+
+	/*
+	 * Add namespace node to union in order to simplify code that accepts both
+	 * ACPI_OPERAND_OBJECTs and ACPI_NAMESPACE_NODEs. The structures share
+	 * a common descriptor_type field in order to differentiate them.
+	 */
+	struct acpi_namespace_node node;
 };
 
 /******************************************************************************
-- 
cgit v1.2.3


From 65f4692c5220330e1ea044796c4cfa603e349c84 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Sat, 27 Sep 2008 10:28:07 +0800
Subject: ACPICA: Remove obsolete exception codes

Removed 10 exception codes (and corresponding name strings)
that were obsolete for various reasons.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 include/acpi/acexcep.h | 128 +++++++++++++++++++++----------------------------
 1 file changed, 55 insertions(+), 73 deletions(-)

(limited to 'include')

diff --git a/include/acpi/acexcep.h b/include/acpi/acexcep.h
index e5a890ffeb02..84f5cb242863 100644
--- a/include/acpi/acexcep.h
+++ b/include/acpi/acexcep.h
@@ -76,25 +76,21 @@
 #define AE_STACK_OVERFLOW               (acpi_status) (0x000C | AE_CODE_ENVIRONMENTAL)
 #define AE_STACK_UNDERFLOW              (acpi_status) (0x000D | AE_CODE_ENVIRONMENTAL)
 #define AE_NOT_IMPLEMENTED              (acpi_status) (0x000E | AE_CODE_ENVIRONMENTAL)
-#define AE_VERSION_MISMATCH             (acpi_status) (0x000F | AE_CODE_ENVIRONMENTAL)
-#define AE_SUPPORT                      (acpi_status) (0x0010 | AE_CODE_ENVIRONMENTAL)
-#define AE_SHARE                        (acpi_status) (0x0011 | AE_CODE_ENVIRONMENTAL)
-#define AE_LIMIT                        (acpi_status) (0x0012 | AE_CODE_ENVIRONMENTAL)
-#define AE_TIME                         (acpi_status) (0x0013 | AE_CODE_ENVIRONMENTAL)
-#define AE_UNKNOWN_STATUS               (acpi_status) (0x0014 | AE_CODE_ENVIRONMENTAL)
-#define AE_ACQUIRE_DEADLOCK             (acpi_status) (0x0015 | AE_CODE_ENVIRONMENTAL)
-#define AE_RELEASE_DEADLOCK             (acpi_status) (0x0016 | AE_CODE_ENVIRONMENTAL)
-#define AE_NOT_ACQUIRED                 (acpi_status) (0x0017 | AE_CODE_ENVIRONMENTAL)
-#define AE_ALREADY_ACQUIRED             (acpi_status) (0x0018 | AE_CODE_ENVIRONMENTAL)
-#define AE_NO_HARDWARE_RESPONSE         (acpi_status) (0x0019 | AE_CODE_ENVIRONMENTAL)
-#define AE_NO_GLOBAL_LOCK               (acpi_status) (0x001A | AE_CODE_ENVIRONMENTAL)
-#define AE_LOGICAL_ADDRESS              (acpi_status) (0x001B | AE_CODE_ENVIRONMENTAL)
-#define AE_ABORT_METHOD                 (acpi_status) (0x001C | AE_CODE_ENVIRONMENTAL)
-#define AE_SAME_HANDLER                 (acpi_status) (0x001D | AE_CODE_ENVIRONMENTAL)
-#define AE_WAKE_ONLY_GPE                (acpi_status) (0x001E | AE_CODE_ENVIRONMENTAL)
-#define AE_OWNER_ID_LIMIT               (acpi_status) (0x001F | AE_CODE_ENVIRONMENTAL)
+#define AE_SUPPORT                      (acpi_status) (0x000F | AE_CODE_ENVIRONMENTAL)
+#define AE_LIMIT                        (acpi_status) (0x0010 | AE_CODE_ENVIRONMENTAL)
+#define AE_TIME                         (acpi_status) (0x0011 | AE_CODE_ENVIRONMENTAL)
+#define AE_ACQUIRE_DEADLOCK             (acpi_status) (0x0012 | AE_CODE_ENVIRONMENTAL)
+#define AE_RELEASE_DEADLOCK             (acpi_status) (0x0013 | AE_CODE_ENVIRONMENTAL)
+#define AE_NOT_ACQUIRED                 (acpi_status) (0x0014 | AE_CODE_ENVIRONMENTAL)
+#define AE_ALREADY_ACQUIRED             (acpi_status) (0x0015 | AE_CODE_ENVIRONMENTAL)
+#define AE_NO_HARDWARE_RESPONSE         (acpi_status) (0x0016 | AE_CODE_ENVIRONMENTAL)
+#define AE_NO_GLOBAL_LOCK               (acpi_status) (0x0017 | AE_CODE_ENVIRONMENTAL)
+#define AE_ABORT_METHOD                 (acpi_status) (0x0018 | AE_CODE_ENVIRONMENTAL)
+#define AE_SAME_HANDLER                 (acpi_status) (0x0019 | AE_CODE_ENVIRONMENTAL)
+#define AE_WAKE_ONLY_GPE                (acpi_status) (0x001A | AE_CODE_ENVIRONMENTAL)
+#define AE_OWNER_ID_LIMIT               (acpi_status) (0x001B | AE_CODE_ENVIRONMENTAL)
 
-#define AE_CODE_ENV_MAX                 0x001F
+#define AE_CODE_ENV_MAX                 0x001B
 
 /*
  * Programmer exceptions
@@ -103,14 +99,12 @@
 #define AE_BAD_CHARACTER                (acpi_status) (0x0002 | AE_CODE_PROGRAMMER)
 #define AE_BAD_PATHNAME                 (acpi_status) (0x0003 | AE_CODE_PROGRAMMER)
 #define AE_BAD_DATA                     (acpi_status) (0x0004 | AE_CODE_PROGRAMMER)
-#define AE_BAD_ADDRESS                  (acpi_status) (0x0005 | AE_CODE_PROGRAMMER)
-#define AE_ALIGNMENT                    (acpi_status) (0x0006 | AE_CODE_PROGRAMMER)
-#define AE_BAD_HEX_CONSTANT             (acpi_status) (0x0007 | AE_CODE_PROGRAMMER)
-#define AE_BAD_OCTAL_CONSTANT           (acpi_status) (0x0008 | AE_CODE_PROGRAMMER)
-#define AE_BAD_DECIMAL_CONSTANT         (acpi_status) (0x0009 | AE_CODE_PROGRAMMER)
-#define AE_MISSING_ARGUMENTS		(acpi_status) (0x000A | AE_CODE_PROGRAMMER)
+#define AE_BAD_HEX_CONSTANT             (acpi_status) (0x0005 | AE_CODE_PROGRAMMER)
+#define AE_BAD_OCTAL_CONSTANT           (acpi_status) (0x0006 | AE_CODE_PROGRAMMER)
+#define AE_BAD_DECIMAL_CONSTANT         (acpi_status) (0x0007 | AE_CODE_PROGRAMMER)
+#define AE_MISSING_ARGUMENTS            (acpi_status) (0x0008 | AE_CODE_PROGRAMMER)
 
-#define AE_CODE_PGM_MAX 		0x000A
+#define AE_CODE_PGM_MAX                 0x0008
 
 /*
  * Acpi table exceptions
@@ -119,51 +113,48 @@
 #define AE_BAD_HEADER                   (acpi_status) (0x0002 | AE_CODE_ACPI_TABLES)
 #define AE_BAD_CHECKSUM                 (acpi_status) (0x0003 | AE_CODE_ACPI_TABLES)
 #define AE_BAD_VALUE                    (acpi_status) (0x0004 | AE_CODE_ACPI_TABLES)
-#define AE_TABLE_NOT_SUPPORTED          (acpi_status) (0x0005 | AE_CODE_ACPI_TABLES)
-#define AE_INVALID_TABLE_LENGTH         (acpi_status) (0x0006 | AE_CODE_ACPI_TABLES)
+#define AE_INVALID_TABLE_LENGTH         (acpi_status) (0x0005 | AE_CODE_ACPI_TABLES)
 
-#define AE_CODE_TBL_MAX                 0x0006
+#define AE_CODE_TBL_MAX                 0x0005
 
 /*
  * AML exceptions.  These are caused by problems with
  * the actual AML byte stream
  */
-#define AE_AML_ERROR                    (acpi_status) (0x0001 | AE_CODE_AML)
-#define AE_AML_PARSE                    (acpi_status) (0x0002 | AE_CODE_AML)
-#define AE_AML_BAD_OPCODE               (acpi_status) (0x0003 | AE_CODE_AML)
-#define AE_AML_NO_OPERAND               (acpi_status) (0x0004 | AE_CODE_AML)
-#define AE_AML_OPERAND_TYPE             (acpi_status) (0x0005 | AE_CODE_AML)
-#define AE_AML_OPERAND_VALUE            (acpi_status) (0x0006 | AE_CODE_AML)
-#define AE_AML_UNINITIALIZED_LOCAL      (acpi_status) (0x0007 | AE_CODE_AML)
-#define AE_AML_UNINITIALIZED_ARG        (acpi_status) (0x0008 | AE_CODE_AML)
-#define AE_AML_UNINITIALIZED_ELEMENT    (acpi_status) (0x0009 | AE_CODE_AML)
-#define AE_AML_NUMERIC_OVERFLOW         (acpi_status) (0x000A | AE_CODE_AML)
-#define AE_AML_REGION_LIMIT             (acpi_status) (0x000B | AE_CODE_AML)
-#define AE_AML_BUFFER_LIMIT             (acpi_status) (0x000C | AE_CODE_AML)
-#define AE_AML_PACKAGE_LIMIT            (acpi_status) (0x000D | AE_CODE_AML)
-#define AE_AML_DIVIDE_BY_ZERO           (acpi_status) (0x000E | AE_CODE_AML)
-#define AE_AML_BAD_NAME                 (acpi_status) (0x000F | AE_CODE_AML)
-#define AE_AML_NAME_NOT_FOUND           (acpi_status) (0x0010 | AE_CODE_AML)
-#define AE_AML_INTERNAL                 (acpi_status) (0x0011 | AE_CODE_AML)
-#define AE_AML_INVALID_SPACE_ID         (acpi_status) (0x0012 | AE_CODE_AML)
-#define AE_AML_STRING_LIMIT             (acpi_status) (0x0013 | AE_CODE_AML)
-#define AE_AML_NO_RETURN_VALUE          (acpi_status) (0x0014 | AE_CODE_AML)
-#define AE_AML_METHOD_LIMIT             (acpi_status) (0x0015 | AE_CODE_AML)
-#define AE_AML_NOT_OWNER                (acpi_status) (0x0016 | AE_CODE_AML)
-#define AE_AML_MUTEX_ORDER              (acpi_status) (0x0017 | AE_CODE_AML)
-#define AE_AML_MUTEX_NOT_ACQUIRED       (acpi_status) (0x0018 | AE_CODE_AML)
-#define AE_AML_INVALID_RESOURCE_TYPE    (acpi_status) (0x0019 | AE_CODE_AML)
-#define AE_AML_INVALID_INDEX            (acpi_status) (0x001A | AE_CODE_AML)
-#define AE_AML_REGISTER_LIMIT           (acpi_status) (0x001B | AE_CODE_AML)
-#define AE_AML_NO_WHILE                 (acpi_status) (0x001C | AE_CODE_AML)
-#define AE_AML_ALIGNMENT                (acpi_status) (0x001D | AE_CODE_AML)
-#define AE_AML_NO_RESOURCE_END_TAG      (acpi_status) (0x001E | AE_CODE_AML)
-#define AE_AML_BAD_RESOURCE_VALUE       (acpi_status) (0x001F | AE_CODE_AML)
-#define AE_AML_CIRCULAR_REFERENCE       (acpi_status) (0x0020 | AE_CODE_AML)
-#define AE_AML_BAD_RESOURCE_LENGTH      (acpi_status) (0x0021 | AE_CODE_AML)
-#define AE_AML_ILLEGAL_ADDRESS          (acpi_status) (0x0022 | AE_CODE_AML)
+#define AE_AML_BAD_OPCODE               (acpi_status) (0x0001 | AE_CODE_AML)
+#define AE_AML_NO_OPERAND               (acpi_status) (0x0002 | AE_CODE_AML)
+#define AE_AML_OPERAND_TYPE             (acpi_status) (0x0003 | AE_CODE_AML)
+#define AE_AML_OPERAND_VALUE            (acpi_status) (0x0004 | AE_CODE_AML)
+#define AE_AML_UNINITIALIZED_LOCAL      (acpi_status) (0x0005 | AE_CODE_AML)
+#define AE_AML_UNINITIALIZED_ARG        (acpi_status) (0x0006 | AE_CODE_AML)
+#define AE_AML_UNINITIALIZED_ELEMENT    (acpi_status) (0x0007 | AE_CODE_AML)
+#define AE_AML_NUMERIC_OVERFLOW         (acpi_status) (0x0008 | AE_CODE_AML)
+#define AE_AML_REGION_LIMIT             (acpi_status) (0x0009 | AE_CODE_AML)
+#define AE_AML_BUFFER_LIMIT             (acpi_status) (0x000A | AE_CODE_AML)
+#define AE_AML_PACKAGE_LIMIT            (acpi_status) (0x000B | AE_CODE_AML)
+#define AE_AML_DIVIDE_BY_ZERO           (acpi_status) (0x000C | AE_CODE_AML)
+#define AE_AML_BAD_NAME                 (acpi_status) (0x000D | AE_CODE_AML)
+#define AE_AML_NAME_NOT_FOUND           (acpi_status) (0x000E | AE_CODE_AML)
+#define AE_AML_INTERNAL                 (acpi_status) (0x000F | AE_CODE_AML)
+#define AE_AML_INVALID_SPACE_ID         (acpi_status) (0x0010 | AE_CODE_AML)
+#define AE_AML_STRING_LIMIT             (acpi_status) (0x0011 | AE_CODE_AML)
+#define AE_AML_NO_RETURN_VALUE          (acpi_status) (0x0012 | AE_CODE_AML)
+#define AE_AML_METHOD_LIMIT             (acpi_status) (0x0013 | AE_CODE_AML)
+#define AE_AML_NOT_OWNER                (acpi_status) (0x0014 | AE_CODE_AML)
+#define AE_AML_MUTEX_ORDER              (acpi_status) (0x0015 | AE_CODE_AML)
+#define AE_AML_MUTEX_NOT_ACQUIRED       (acpi_status) (0x0016 | AE_CODE_AML)
+#define AE_AML_INVALID_RESOURCE_TYPE    (acpi_status) (0x0017 | AE_CODE_AML)
+#define AE_AML_INVALID_INDEX            (acpi_status) (0x0018 | AE_CODE_AML)
+#define AE_AML_REGISTER_LIMIT           (acpi_status) (0x0019 | AE_CODE_AML)
+#define AE_AML_NO_WHILE                 (acpi_status) (0x001A | AE_CODE_AML)
+#define AE_AML_ALIGNMENT                (acpi_status) (0x001B | AE_CODE_AML)
+#define AE_AML_NO_RESOURCE_END_TAG      (acpi_status) (0x001C | AE_CODE_AML)
+#define AE_AML_BAD_RESOURCE_VALUE       (acpi_status) (0x001D | AE_CODE_AML)
+#define AE_AML_CIRCULAR_REFERENCE       (acpi_status) (0x001E | AE_CODE_AML)
+#define AE_AML_BAD_RESOURCE_LENGTH      (acpi_status) (0x001F | AE_CODE_AML)
+#define AE_AML_ILLEGAL_ADDRESS          (acpi_status) (0x0020 | AE_CODE_AML)
 
-#define AE_CODE_AML_MAX                 0x0022
+#define AE_CODE_AML_MAX                 0x0020
 
 /*
  * Internal exceptions used for control
@@ -206,19 +197,15 @@ char const *acpi_gbl_exception_names_env[] = {
 	"AE_STACK_OVERFLOW",
 	"AE_STACK_UNDERFLOW",
 	"AE_NOT_IMPLEMENTED",
-	"AE_VERSION_MISMATCH",
 	"AE_SUPPORT",
-	"AE_SHARE",
 	"AE_LIMIT",
 	"AE_TIME",
-	"AE_UNKNOWN_STATUS",
 	"AE_ACQUIRE_DEADLOCK",
 	"AE_RELEASE_DEADLOCK",
 	"AE_NOT_ACQUIRED",
 	"AE_ALREADY_ACQUIRED",
 	"AE_NO_HARDWARE_RESPONSE",
 	"AE_NO_GLOBAL_LOCK",
-	"AE_LOGICAL_ADDRESS",
 	"AE_ABORT_METHOD",
 	"AE_SAME_HANDLER",
 	"AE_WAKE_ONLY_GPE",
@@ -231,8 +218,6 @@ char const *acpi_gbl_exception_names_pgm[] = {
 	"AE_BAD_CHARACTER",
 	"AE_BAD_PATHNAME",
 	"AE_BAD_DATA",
-	"AE_BAD_ADDRESS",
-	"AE_ALIGNMENT",
 	"AE_BAD_HEX_CONSTANT",
 	"AE_BAD_OCTAL_CONSTANT",
 	"AE_BAD_DECIMAL_CONSTANT",
@@ -245,14 +230,11 @@ char const *acpi_gbl_exception_names_tbl[] = {
 	"AE_BAD_HEADER",
 	"AE_BAD_CHECKSUM",
 	"AE_BAD_VALUE",
-	"AE_TABLE_NOT_SUPPORTED",
 	"AE_INVALID_TABLE_LENGTH"
 };
 
 char const *acpi_gbl_exception_names_aml[] = {
 	NULL,
-	"AE_AML_ERROR",
-	"AE_AML_PARSE",
 	"AE_AML_BAD_OPCODE",
 	"AE_AML_NO_OPERAND",
 	"AE_AML_OPERAND_TYPE",
@@ -284,7 +266,7 @@ char const *acpi_gbl_exception_names_aml[] = {
 	"AE_AML_BAD_RESOURCE_VALUE",
 	"AE_AML_CIRCULAR_REFERENCE",
 	"AE_AML_BAD_RESOURCE_LENGTH",
-	"AE_AML_ILLEGAL_ADDRESS"
+	"AE_AML_ILLEGAL_ADDRESS",
 };
 
 char const *acpi_gbl_exception_names_ctrl[] = {
-- 
cgit v1.2.3


From 57e664cfd968ec8e4b0bfd80a5e8f903307e598b Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Sat, 27 Sep 2008 10:40:39 +0800
Subject: ACPICA: Update for Reference ACPI_OPERAND_OBJECT

1) Add new field for use by DdbHandle (Value)
2) Use ACPI_CAST_INDIRECT_PTR to eliminate strict type warnings
3) Cleanup debug output

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/dispatcher/dsobject.c | 16 ++++++++++------
 drivers/acpi/executer/exconfig.c   |  6 +++---
 drivers/acpi/executer/exdump.c     | 29 ++++++++++++++---------------
 drivers/acpi/executer/exstore.c    |  4 ++--
 include/acpi/acobject.h            |  1 +
 5 files changed, 30 insertions(+), 26 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/dispatcher/dsobject.c b/drivers/acpi/dispatcher/dsobject.c
index 0f2805899210..09af39fff1a3 100644
--- a/drivers/acpi/dispatcher/dsobject.c
+++ b/drivers/acpi/dispatcher/dsobject.c
@@ -741,10 +741,12 @@ acpi_ds_init_object_from_op(struct acpi_walk_state *walk_state,
 							      obj_desc->
 							      reference.offset,
 							      walk_state,
+							      ACPI_CAST_INDIRECT_PTR
 							      (struct
-							       acpi_namespace_node
-							       **)&obj_desc->
-							      reference.object);
+							       acpi_namespace_node,
+							       &obj_desc->
+							       reference.
+							       object));
 #endif
 			break;
 
@@ -760,10 +762,12 @@ acpi_ds_init_object_from_op(struct acpi_walk_state *walk_state,
 							      obj_desc->
 							      reference.offset,
 							      walk_state,
+							      ACPI_CAST_INDIRECT_PTR
 							      (struct
-							       acpi_namespace_node
-							       **)&obj_desc->
-							      reference.object);
+							       acpi_namespace_node,
+							       &obj_desc->
+							       reference.
+							       object));
 #endif
 			break;
 
diff --git a/drivers/acpi/executer/exconfig.c b/drivers/acpi/executer/exconfig.c
index 4c512c2990e5..5f2b1ebf70a3 100644
--- a/drivers/acpi/executer/exconfig.c
+++ b/drivers/acpi/executer/exconfig.c
@@ -96,7 +96,7 @@ acpi_ex_add_table(u32 table_index,
 
 	/* Install the new table into the local data structures */
 
-	obj_desc->reference.object = ACPI_TO_POINTER(table_index);
+	obj_desc->reference.value = table_index;
 
 	/* Add the table to the namespace */
 
@@ -505,9 +505,9 @@ acpi_status acpi_ex_unload_table(union acpi_operand_object *ddb_handle)
 		return_ACPI_STATUS(AE_BAD_PARAMETER);
 	}
 
-	/* Get the table index from the ddb_handle (acpi_size for 64-bit case) */
+	/* Get the table index from the ddb_handle */
 
-	table_index = (u32) (acpi_size) table_desc->reference.object;
+	table_index = table_desc->reference.value;
 
 	/* Invoke table handler if present */
 
diff --git a/drivers/acpi/executer/exdump.c b/drivers/acpi/executer/exdump.c
index 2be2e2bf95bf..7d4123256cf1 100644
--- a/drivers/acpi/executer/exdump.c
+++ b/drivers/acpi/executer/exdump.c
@@ -214,10 +214,11 @@ static struct acpi_exdump_info acpi_ex_dump_index_field[5] = {
 	{ACPI_EXD_POINTER, ACPI_EXD_OFFSET(index_field.data_obj), "Data Object"}
 };
 
-static struct acpi_exdump_info acpi_ex_dump_reference[7] = {
+static struct acpi_exdump_info acpi_ex_dump_reference[8] = {
 	{ACPI_EXD_INIT, ACPI_EXD_TABLE_SIZE(acpi_ex_dump_reference), NULL},
 	{ACPI_EXD_UINT8, ACPI_EXD_OFFSET(reference.target_type), "Target Type"},
 	{ACPI_EXD_UINT32, ACPI_EXD_OFFSET(reference.offset), "Offset"},
+	{ACPI_EXD_UINT32, ACPI_EXD_OFFSET(reference.value), "Value"},
 	{ACPI_EXD_POINTER, ACPI_EXD_OFFSET(reference.object), "Object Desc"},
 	{ACPI_EXD_POINTER, ACPI_EXD_OFFSET(reference.node), "Node"},
 	{ACPI_EXD_POINTER, ACPI_EXD_OFFSET(reference.where), "Where"},
@@ -497,24 +498,24 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth)
 		switch (obj_desc->reference.opcode) {
 		case AML_DEBUG_OP:
 
-			acpi_os_printf("Reference: Debug\n");
+			acpi_os_printf("Reference: [Debug]\n");
 			break;
 
 		case AML_INDEX_OP:
 
-			acpi_os_printf("Reference: Index %p\n",
+			acpi_os_printf("Reference: [Index] %p\n",
 				       obj_desc->reference.object);
 			break;
 
 		case AML_LOAD_OP:
 
-			acpi_os_printf("Reference: [DdbHandle] TableIndex %p\n",
-				       obj_desc->reference.object);
+			acpi_os_printf("Reference: [DdbHandle] TableIndex %X\n",
+				       obj_desc->reference.value);
 			break;
 
 		case AML_REF_OF_OP:
 
-			acpi_os_printf("Reference: (RefOf) %p [%s]\n",
+			acpi_os_printf("Reference: [RefOf] %p [%s]\n",
 				       obj_desc->reference.object,
 				       acpi_ut_get_type_name(((union
 							       acpi_operand_object
@@ -526,7 +527,7 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth)
 
 		case AML_ARG_OP:
 
-			acpi_os_printf("Reference: Arg%d",
+			acpi_os_printf("Reference: [Arg%d]",
 				       obj_desc->reference.offset);
 
 			if (ACPI_GET_OBJECT_TYPE(obj_desc) == ACPI_TYPE_INTEGER) {
@@ -544,7 +545,7 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth)
 
 		case AML_LOCAL_OP:
 
-			acpi_os_printf("Reference: Local%d",
+			acpi_os_printf("Reference: [Local%d]",
 				       obj_desc->reference.offset);
 
 			if (ACPI_GET_OBJECT_TYPE(obj_desc) == ACPI_TYPE_INTEGER) {
@@ -562,7 +563,7 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth)
 
 		case AML_INT_NAMEPATH_OP:
 
-			acpi_os_printf("Reference: Namepath %X [%4.4s]\n",
+			acpi_os_printf("Reference: [Namepath] %X [%4.4s]\n",
 				       obj_desc->reference.node->name.integer,
 				       obj_desc->reference.node->name.ascii);
 			break;
@@ -883,13 +884,11 @@ static void acpi_ex_dump_reference_obj(union acpi_operand_object *obj_desc)
 			acpi_os_printf(" Target: %p",
 				       obj_desc->reference.object);
 			if (obj_desc->reference.opcode == AML_LOAD_OP) {
-				/*
-				 * For DDBHandle reference,
-				 * obj_desc->Reference.Object is the table index
-				 */
-				acpi_os_printf(" [DDBHandle]\n");
+				acpi_os_printf(" [DDBHandle] Table Index: %X\n",
+					       obj_desc->reference.value);
 			} else {
-				acpi_os_printf(" [%s]\n",
+				acpi_os_printf(" Target: %p [%s]\n",
+					       obj_desc->reference.object,
 					       acpi_ut_get_type_name(((union
 								       acpi_operand_object
 								       *)
diff --git a/drivers/acpi/executer/exstore.c b/drivers/acpi/executer/exstore.c
index 09e96846d155..20b4893e06ed 100644
--- a/drivers/acpi/executer/exstore.c
+++ b/drivers/acpi/executer/exstore.c
@@ -193,8 +193,8 @@ acpi_ex_do_debug_object(union acpi_operand_object *source_desc,
 
 		if (source_desc->reference.opcode == AML_LOAD_OP) {	/* Load and load_table */
 			ACPI_DEBUG_PRINT_RAW((ACPI_DB_DEBUG_OBJECT,
-					      " Table OwnerId %p\n",
-					      source_desc->reference.object));
+					      " Table Index %X\n",
+					      source_desc->reference.value));
 			break;
 		}
 
diff --git a/include/acpi/acobject.h b/include/acpi/acobject.h
index 0ca39265bb0f..7a8a652ffb78 100644
--- a/include/acpi/acobject.h
+++ b/include/acpi/acobject.h
@@ -318,6 +318,7 @@ struct acpi_object_reference {
 	struct acpi_namespace_node *node;
 	union acpi_operand_object **where;
 	u32 offset;		/* Used for arg_op, local_op, and index_op */
+	u32 value;		/* Used for ddb_handle */
 };
 
 /*
-- 
cgit v1.2.3


From 1044f1f65b7df2aae979e397904c4985eeb99ba2 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Sat, 27 Sep 2008 11:08:41 +0800
Subject: ACPICA: Cleanup for internal Reference Object

Fix some sloppiness in the Reference object. No longer use AML
opcodes to differentiate the types, introduce new reference
Class. Cleanup the debug output code.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/dispatcher/dsmthdat.c | 83 ++++++++++++++++++++------------------
 drivers/acpi/dispatcher/dsobject.c | 56 +++++++++++++++----------
 drivers/acpi/dispatcher/dsopcode.c |  2 +-
 drivers/acpi/dispatcher/dswexec.c  |  8 ++--
 drivers/acpi/executer/exconfig.c   |  3 +-
 drivers/acpi/executer/exdump.c     | 74 ++++++++++++++++-----------------
 drivers/acpi/executer/exmisc.c     | 14 +++----
 drivers/acpi/executer/exoparg1.c   | 26 ++++++------
 drivers/acpi/executer/exoparg2.c   |  4 +-
 drivers/acpi/executer/exresnte.c   | 16 +++-----
 drivers/acpi/executer/exresolv.c   | 60 +++++++++++++--------------
 drivers/acpi/executer/exresop.c    | 50 ++++++++++-------------
 drivers/acpi/executer/exstore.c    | 57 +++++++++++++-------------
 drivers/acpi/executer/exstoren.c   |  3 +-
 drivers/acpi/namespace/nsdump.c    |  5 +--
 drivers/acpi/namespace/nsxfeval.c  |  7 ++--
 drivers/acpi/resources/rscalc.c    |  5 +--
 drivers/acpi/resources/rscreate.c  | 10 ++---
 drivers/acpi/utilities/utcopy.c    | 29 +++++++------
 drivers/acpi/utilities/utdelete.c  |  5 +--
 drivers/acpi/utilities/utglobal.c  | 35 +++++++++-------
 drivers/acpi/utilities/utobject.c  |  9 ++---
 include/acpi/acdebug.h             |  4 ++
 include/acpi/acdispat.h            |  6 +--
 include/acpi/acobject.h            | 31 ++++++++++----
 25 files changed, 310 insertions(+), 292 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/dispatcher/dsmthdat.c b/drivers/acpi/dispatcher/dsmthdat.c
index 13c43eac35db..d03f81bd1bcb 100644
--- a/drivers/acpi/dispatcher/dsmthdat.c
+++ b/drivers/acpi/dispatcher/dsmthdat.c
@@ -43,7 +43,6 @@
 
 #include <acpi/acpi.h>
 #include <acpi/acdispat.h>
-#include <acpi/amlcode.h>
 #include <acpi/acnamesp.h>
 #include <acpi/acinterp.h>
 
@@ -52,11 +51,11 @@ ACPI_MODULE_NAME("dsmthdat")
 
 /* Local prototypes */
 static void
-acpi_ds_method_data_delete_value(u16 opcode,
+acpi_ds_method_data_delete_value(u8 type,
 				 u32 index, struct acpi_walk_state *walk_state);
 
 static acpi_status
-acpi_ds_method_data_set_value(u16 opcode,
+acpi_ds_method_data_set_value(u8 type,
 			      u32 index,
 			      union acpi_operand_object *object,
 			      struct acpi_walk_state *walk_state);
@@ -216,7 +215,7 @@ acpi_ds_method_data_init_args(union acpi_operand_object **params,
 		 * Store the argument in the method/walk descriptor.
 		 * Do not copy the arg in order to implement call by reference
 		 */
-		status = acpi_ds_method_data_set_value(AML_ARG_OP, index,
+		status = acpi_ds_method_data_set_value(ACPI_REFCLASS_ARG, index,
 						       params[index],
 						       walk_state);
 		if (ACPI_FAILURE(status)) {
@@ -234,7 +233,8 @@ acpi_ds_method_data_init_args(union acpi_operand_object **params,
  *
  * FUNCTION:    acpi_ds_method_data_get_node
  *
- * PARAMETERS:  Opcode              - Either AML_LOCAL_OP or AML_ARG_OP
+ * PARAMETERS:  Type                - Either ACPI_REFCLASS_LOCAL or
+ *                                    ACPI_REFCLASS_ARG
  *              Index               - Which Local or Arg whose type to get
  *              walk_state          - Current walk state object
  *              Node                - Where the node is returned.
@@ -246,7 +246,7 @@ acpi_ds_method_data_init_args(union acpi_operand_object **params,
  ******************************************************************************/
 
 acpi_status
-acpi_ds_method_data_get_node(u16 opcode,
+acpi_ds_method_data_get_node(u8 type,
 			     u32 index,
 			     struct acpi_walk_state *walk_state,
 			     struct acpi_namespace_node **node)
@@ -256,8 +256,8 @@ acpi_ds_method_data_get_node(u16 opcode,
 	/*
 	 * Method Locals and Arguments are supported
 	 */
-	switch (opcode) {
-	case AML_LOCAL_OP:
+	switch (type) {
+	case ACPI_REFCLASS_LOCAL:
 
 		if (index > ACPI_METHOD_MAX_LOCAL) {
 			ACPI_ERROR((AE_INFO,
@@ -271,7 +271,7 @@ acpi_ds_method_data_get_node(u16 opcode,
 		*node = &walk_state->local_variables[index];
 		break;
 
-	case AML_ARG_OP:
+	case ACPI_REFCLASS_ARG:
 
 		if (index > ACPI_METHOD_MAX_ARG) {
 			ACPI_ERROR((AE_INFO,
@@ -286,8 +286,8 @@ acpi_ds_method_data_get_node(u16 opcode,
 		break;
 
 	default:
-		ACPI_ERROR((AE_INFO, "Opcode %d is invalid", opcode));
-		return_ACPI_STATUS(AE_AML_BAD_OPCODE);
+		ACPI_ERROR((AE_INFO, "Type %d is invalid", type));
+		return_ACPI_STATUS(AE_TYPE);
 	}
 
 	return_ACPI_STATUS(AE_OK);
@@ -297,7 +297,8 @@ acpi_ds_method_data_get_node(u16 opcode,
  *
  * FUNCTION:    acpi_ds_method_data_set_value
  *
- * PARAMETERS:  Opcode              - Either AML_LOCAL_OP or AML_ARG_OP
+ * PARAMETERS:  Type                - Either ACPI_REFCLASS_LOCAL or
+ *                                    ACPI_REFCLASS_ARG
  *              Index               - Which Local or Arg to get
  *              Object              - Object to be inserted into the stack entry
  *              walk_state          - Current walk state object
@@ -310,7 +311,7 @@ acpi_ds_method_data_get_node(u16 opcode,
  ******************************************************************************/
 
 static acpi_status
-acpi_ds_method_data_set_value(u16 opcode,
+acpi_ds_method_data_set_value(u8 type,
 			      u32 index,
 			      union acpi_operand_object *object,
 			      struct acpi_walk_state *walk_state)
@@ -321,13 +322,13 @@ acpi_ds_method_data_set_value(u16 opcode,
 	ACPI_FUNCTION_TRACE(ds_method_data_set_value);
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
-			  "NewObj %p Opcode %X, Refs=%d [%s]\n", object,
-			  opcode, object->common.reference_count,
+			  "NewObj %p Type %2.2X, Refs=%d [%s]\n", object,
+			  type, object->common.reference_count,
 			  acpi_ut_get_type_name(object->common.type)));
 
 	/* Get the namespace node for the arg/local */
 
-	status = acpi_ds_method_data_get_node(opcode, index, walk_state, &node);
+	status = acpi_ds_method_data_get_node(type, index, walk_state, &node);
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
 	}
@@ -350,7 +351,8 @@ acpi_ds_method_data_set_value(u16 opcode,
  *
  * FUNCTION:    acpi_ds_method_data_get_value
  *
- * PARAMETERS:  Opcode              - Either AML_LOCAL_OP or AML_ARG_OP
+ * PARAMETERS:  Type                - Either ACPI_REFCLASS_LOCAL or
+ *                                    ACPI_REFCLASS_ARG
  *              Index               - Which local_var or argument to get
  *              walk_state          - Current walk state object
  *              dest_desc           - Where Arg or Local value is returned
@@ -363,7 +365,7 @@ acpi_ds_method_data_set_value(u16 opcode,
  ******************************************************************************/
 
 acpi_status
-acpi_ds_method_data_get_value(u16 opcode,
+acpi_ds_method_data_get_value(u8 type,
 			      u32 index,
 			      struct acpi_walk_state *walk_state,
 			      union acpi_operand_object **dest_desc)
@@ -383,7 +385,7 @@ acpi_ds_method_data_get_value(u16 opcode,
 
 	/* Get the namespace node for the arg/local */
 
-	status = acpi_ds_method_data_get_node(opcode, index, walk_state, &node);
+	status = acpi_ds_method_data_get_node(type, index, walk_state, &node);
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
 	}
@@ -419,8 +421,8 @@ acpi_ds_method_data_get_value(u16 opcode,
 		/* Otherwise, return the error */
 
 		else
-			switch (opcode) {
-			case AML_ARG_OP:
+			switch (type) {
+			case ACPI_REFCLASS_ARG:
 
 				ACPI_ERROR((AE_INFO,
 					    "Uninitialized Arg[%d] at node %p",
@@ -428,7 +430,7 @@ acpi_ds_method_data_get_value(u16 opcode,
 
 				return_ACPI_STATUS(AE_AML_UNINITIALIZED_ARG);
 
-			case AML_LOCAL_OP:
+			case ACPI_REFCLASS_LOCAL:
 
 				ACPI_ERROR((AE_INFO,
 					    "Uninitialized Local[%d] at node %p",
@@ -437,9 +439,10 @@ acpi_ds_method_data_get_value(u16 opcode,
 				return_ACPI_STATUS(AE_AML_UNINITIALIZED_LOCAL);
 
 			default:
+
 				ACPI_ERROR((AE_INFO,
 					    "Not a Arg/Local opcode: %X",
-					    opcode));
+					    type));
 				return_ACPI_STATUS(AE_AML_INTERNAL);
 			}
 	}
@@ -458,7 +461,8 @@ acpi_ds_method_data_get_value(u16 opcode,
  *
  * FUNCTION:    acpi_ds_method_data_delete_value
  *
- * PARAMETERS:  Opcode              - Either AML_LOCAL_OP or AML_ARG_OP
+ * PARAMETERS:  Type                - Either ACPI_REFCLASS_LOCAL or
+ *                                    ACPI_REFCLASS_ARG
  *              Index               - Which local_var or argument to delete
  *              walk_state          - Current walk state object
  *
@@ -470,7 +474,7 @@ acpi_ds_method_data_get_value(u16 opcode,
  ******************************************************************************/
 
 static void
-acpi_ds_method_data_delete_value(u16 opcode,
+acpi_ds_method_data_delete_value(u8 type,
 				 u32 index, struct acpi_walk_state *walk_state)
 {
 	acpi_status status;
@@ -481,7 +485,7 @@ acpi_ds_method_data_delete_value(u16 opcode,
 
 	/* Get the namespace node for the arg/local */
 
-	status = acpi_ds_method_data_get_node(opcode, index, walk_state, &node);
+	status = acpi_ds_method_data_get_node(type, index, walk_state, &node);
 	if (ACPI_FAILURE(status)) {
 		return_VOID;
 	}
@@ -514,7 +518,8 @@ acpi_ds_method_data_delete_value(u16 opcode,
  *
  * FUNCTION:    acpi_ds_store_object_to_local
  *
- * PARAMETERS:  Opcode              - Either AML_LOCAL_OP or AML_ARG_OP
+ * PARAMETERS:  Type                - Either ACPI_REFCLASS_LOCAL or
+ *                                    ACPI_REFCLASS_ARG
  *              Index               - Which Local or Arg to set
  *              obj_desc            - Value to be stored
  *              walk_state          - Current walk state
@@ -528,7 +533,7 @@ acpi_ds_method_data_delete_value(u16 opcode,
  ******************************************************************************/
 
 acpi_status
-acpi_ds_store_object_to_local(u16 opcode,
+acpi_ds_store_object_to_local(u8 type,
 			      u32 index,
 			      union acpi_operand_object *obj_desc,
 			      struct acpi_walk_state *walk_state)
@@ -539,8 +544,8 @@ acpi_ds_store_object_to_local(u16 opcode,
 	union acpi_operand_object *new_obj_desc;
 
 	ACPI_FUNCTION_TRACE(ds_store_object_to_local);
-	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Opcode=%X Index=%d Obj=%p\n",
-			  opcode, index, obj_desc));
+	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "Type=%2.2X Index=%d Obj=%p\n",
+			  type, index, obj_desc));
 
 	/* Parameter validation */
 
@@ -550,7 +555,7 @@ acpi_ds_store_object_to_local(u16 opcode,
 
 	/* Get the namespace node for the arg/local */
 
-	status = acpi_ds_method_data_get_node(opcode, index, walk_state, &node);
+	status = acpi_ds_method_data_get_node(type, index, walk_state, &node);
 	if (ACPI_FAILURE(status)) {
 		return_ACPI_STATUS(status);
 	}
@@ -602,7 +607,7 @@ acpi_ds_store_object_to_local(u16 opcode,
 		 *
 		 * Weird, but true.
 		 */
-		if (opcode == AML_ARG_OP) {
+		if (type == ACPI_REFCLASS_ARG) {
 			/*
 			 * If we have a valid reference object that came from ref_of(),
 			 * do the indirect store
@@ -611,8 +616,8 @@ acpi_ds_store_object_to_local(u16 opcode,
 			     ACPI_DESC_TYPE_OPERAND)
 			    && (current_obj_desc->common.type ==
 				ACPI_TYPE_LOCAL_REFERENCE)
-			    && (current_obj_desc->reference.opcode ==
-				AML_REF_OF_OP)) {
+			    && (current_obj_desc->reference.class ==
+				ACPI_REFCLASS_REFOF)) {
 				ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
 						  "Arg (%p) is an ObjRef(Node), storing in node %p\n",
 						  new_obj_desc,
@@ -640,11 +645,9 @@ acpi_ds_store_object_to_local(u16 opcode,
 			}
 		}
 
-		/*
-		 * Delete the existing object
-		 * before storing the new one
-		 */
-		acpi_ds_method_data_delete_value(opcode, index, walk_state);
+		/* Delete the existing object before storing the new one */
+
+		acpi_ds_method_data_delete_value(type, index, walk_state);
 	}
 
 	/*
@@ -653,7 +656,7 @@ acpi_ds_store_object_to_local(u16 opcode,
 	 * (increments the object reference count by one)
 	 */
 	status =
-	    acpi_ds_method_data_set_value(opcode, index, new_obj_desc,
+	    acpi_ds_method_data_set_value(type, index, new_obj_desc,
 					  walk_state);
 
 	/* Remove local reference if we copied the object above */
diff --git a/drivers/acpi/dispatcher/dsobject.c b/drivers/acpi/dispatcher/dsobject.c
index 09af39fff1a3..4f08e599d07e 100644
--- a/drivers/acpi/dispatcher/dsobject.c
+++ b/drivers/acpi/dispatcher/dsobject.c
@@ -731,36 +731,35 @@ acpi_ds_init_object_from_op(struct acpi_walk_state *walk_state,
 		switch (op_info->type) {
 		case AML_TYPE_LOCAL_VARIABLE:
 
-			/* Split the opcode into a base opcode + offset */
+			/* Local ID (0-7) is (AML opcode - base AML_LOCAL_OP) */
 
-			obj_desc->reference.opcode = AML_LOCAL_OP;
-			obj_desc->reference.offset = opcode - AML_LOCAL_OP;
+			obj_desc->reference.value = opcode - AML_LOCAL_OP;
+			obj_desc->reference.class = ACPI_REFCLASS_LOCAL;
 
 #ifndef ACPI_NO_METHOD_EXECUTION
-			status = acpi_ds_method_data_get_node(AML_LOCAL_OP,
-							      obj_desc->
-							      reference.offset,
-							      walk_state,
-							      ACPI_CAST_INDIRECT_PTR
-							      (struct
-							       acpi_namespace_node,
-							       &obj_desc->
-							       reference.
-							       object));
+			status =
+			    acpi_ds_method_data_get_node(ACPI_REFCLASS_LOCAL,
+							 obj_desc->reference.
+							 value, walk_state,
+							 ACPI_CAST_INDIRECT_PTR
+							 (struct
+							  acpi_namespace_node,
+							  &obj_desc->reference.
+							  object));
 #endif
 			break;
 
 		case AML_TYPE_METHOD_ARGUMENT:
 
-			/* Split the opcode into a base opcode + offset */
+			/* Arg ID (0-6) is (AML opcode - base AML_ARG_OP) */
 
-			obj_desc->reference.opcode = AML_ARG_OP;
-			obj_desc->reference.offset = opcode - AML_ARG_OP;
+			obj_desc->reference.value = opcode - AML_ARG_OP;
+			obj_desc->reference.class = ACPI_REFCLASS_ARG;
 
 #ifndef ACPI_NO_METHOD_EXECUTION
-			status = acpi_ds_method_data_get_node(AML_ARG_OP,
+			status = acpi_ds_method_data_get_node(ACPI_REFCLASS_ARG,
 							      obj_desc->
-							      reference.offset,
+							      reference.value,
 							      walk_state,
 							      ACPI_CAST_INDIRECT_PTR
 							      (struct
@@ -771,18 +770,31 @@ acpi_ds_init_object_from_op(struct acpi_walk_state *walk_state,
 #endif
 			break;
 
-		default:	/* Other literals, etc.. */
+		default:	/* Object name or Debug object */
 
-			if (op->common.aml_opcode == AML_INT_NAMEPATH_OP) {
+			switch (op->common.aml_opcode) {
+			case AML_INT_NAMEPATH_OP:
 
 				/* Node was saved in Op */
 
 				obj_desc->reference.node = op->common.node;
 				obj_desc->reference.object =
 				    op->common.node->object;
-			}
+				obj_desc->reference.class = ACPI_REFCLASS_NAME;
+				break;
+
+			case AML_DEBUG_OP:
 
-			obj_desc->reference.opcode = opcode;
+				obj_desc->reference.class = ACPI_REFCLASS_DEBUG;
+				break;
+
+			default:
+
+				ACPI_ERROR((AE_INFO,
+					    "Unimplemented reference type for AML opcode: %4.4X",
+					    opcode));
+				return_ACPI_STATUS(AE_AML_OPERAND_TYPE);
+			}
 			break;
 		}
 		break;
diff --git a/drivers/acpi/dispatcher/dsopcode.c b/drivers/acpi/dispatcher/dsopcode.c
index 6a81c4400edf..69fae5905bb8 100644
--- a/drivers/acpi/dispatcher/dsopcode.c
+++ b/drivers/acpi/dispatcher/dsopcode.c
@@ -1330,7 +1330,7 @@ acpi_ds_exec_end_control_op(struct acpi_walk_state * walk_state,
 			     (walk_state->results->results.obj_desc[0]) ==
 			     ACPI_TYPE_LOCAL_REFERENCE)
 			    && ((walk_state->results->results.obj_desc[0])->
-				reference.opcode != AML_INDEX_OP)) {
+				reference.class != ACPI_REFCLASS_INDEX)) {
 				status =
 				    acpi_ex_resolve_to_value(&walk_state->
 							     results->results.
diff --git a/drivers/acpi/dispatcher/dswexec.c b/drivers/acpi/dispatcher/dswexec.c
index b5072fa9c920..5b2419197b9b 100644
--- a/drivers/acpi/dispatcher/dswexec.c
+++ b/drivers/acpi/dispatcher/dswexec.c
@@ -429,10 +429,10 @@ acpi_status acpi_ds_exec_end_op(struct acpi_walk_state *walk_state)
 			     ACPI_TYPE_LOCAL_REFERENCE)
 			    && (walk_state->operands[1]->common.type ==
 				ACPI_TYPE_LOCAL_REFERENCE)
-			    && (walk_state->operands[0]->reference.opcode ==
-				walk_state->operands[1]->reference.opcode)
-			    && (walk_state->operands[0]->reference.offset ==
-				walk_state->operands[1]->reference.offset)) {
+			    && (walk_state->operands[0]->reference.class ==
+				walk_state->operands[1]->reference.class)
+			    && (walk_state->operands[0]->reference.value ==
+				walk_state->operands[1]->reference.value)) {
 				status = AE_OK;
 			} else {
 				ACPI_EXCEPTION((AE_INFO, status,
diff --git a/drivers/acpi/executer/exconfig.c b/drivers/acpi/executer/exconfig.c
index 5f2b1ebf70a3..74da6fa52ef1 100644
--- a/drivers/acpi/executer/exconfig.c
+++ b/drivers/acpi/executer/exconfig.c
@@ -43,7 +43,6 @@
 
 #include <acpi/acpi.h>
 #include <acpi/acinterp.h>
-#include <acpi/amlcode.h>
 #include <acpi/acnamesp.h>
 #include <acpi/actables.h>
 #include <acpi/acdispat.h>
@@ -91,7 +90,7 @@ acpi_ex_add_table(u32 table_index,
 
 	/* Init the table handle */
 
-	obj_desc->reference.opcode = AML_LOAD_OP;
+	obj_desc->reference.class = ACPI_REFCLASS_TABLE;
 	*ddb_handle = obj_desc;
 
 	/* Install the new table into the local data structures */
diff --git a/drivers/acpi/executer/exdump.c b/drivers/acpi/executer/exdump.c
index 7d4123256cf1..d087a7d28aa5 100644
--- a/drivers/acpi/executer/exdump.c
+++ b/drivers/acpi/executer/exdump.c
@@ -45,7 +45,6 @@
 #include <acpi/acinterp.h>
 #include <acpi/amlcode.h>
 #include <acpi/acnamesp.h>
-#include <acpi/acparser.h>
 
 #define _COMPONENT          ACPI_EXECUTER
 ACPI_MODULE_NAME("exdump")
@@ -216,8 +215,8 @@ static struct acpi_exdump_info acpi_ex_dump_index_field[5] = {
 
 static struct acpi_exdump_info acpi_ex_dump_reference[8] = {
 	{ACPI_EXD_INIT, ACPI_EXD_TABLE_SIZE(acpi_ex_dump_reference), NULL},
+	{ACPI_EXD_UINT8, ACPI_EXD_OFFSET(reference.class), "Class"},
 	{ACPI_EXD_UINT8, ACPI_EXD_OFFSET(reference.target_type), "Target Type"},
-	{ACPI_EXD_UINT32, ACPI_EXD_OFFSET(reference.offset), "Offset"},
 	{ACPI_EXD_UINT32, ACPI_EXD_OFFSET(reference.value), "Value"},
 	{ACPI_EXD_POINTER, ACPI_EXD_OFFSET(reference.object), "Object Desc"},
 	{ACPI_EXD_POINTER, ACPI_EXD_OFFSET(reference.node), "Node"},
@@ -414,10 +413,10 @@ acpi_ex_dump_object(union acpi_operand_object *obj_desc,
 
 		case ACPI_EXD_REFERENCE:
 
-			acpi_ex_out_string("Opcode",
-					   (acpi_ps_get_opcode_info
-					    (obj_desc->reference.opcode))->
-					   name);
+			acpi_ex_out_string("Class Name",
+					   (char *)
+					   acpi_ut_get_reference_name
+					   (obj_desc));
 			acpi_ex_dump_reference_obj(obj_desc);
 			break;
 
@@ -495,40 +494,41 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth)
 	switch (ACPI_GET_OBJECT_TYPE(obj_desc)) {
 	case ACPI_TYPE_LOCAL_REFERENCE:
 
-		switch (obj_desc->reference.opcode) {
-		case AML_DEBUG_OP:
+		acpi_os_printf("Reference: [%s] ",
+			       acpi_ut_get_reference_name(obj_desc));
+
+		switch (obj_desc->reference.class) {
+		case ACPI_REFCLASS_DEBUG:
 
-			acpi_os_printf("Reference: [Debug]\n");
+			acpi_os_printf("\n");
 			break;
 
-		case AML_INDEX_OP:
+		case ACPI_REFCLASS_INDEX:
 
-			acpi_os_printf("Reference: [Index] %p\n",
-				       obj_desc->reference.object);
+			acpi_os_printf("%p\n", obj_desc->reference.object);
 			break;
 
-		case AML_LOAD_OP:
+		case ACPI_REFCLASS_TABLE:
 
-			acpi_os_printf("Reference: [DdbHandle] TableIndex %X\n",
+			acpi_os_printf("Table Index %X\n",
 				       obj_desc->reference.value);
 			break;
 
-		case AML_REF_OF_OP:
+		case ACPI_REFCLASS_REFOF:
 
-			acpi_os_printf("Reference: [RefOf] %p [%s]\n",
-				       obj_desc->reference.object,
+			acpi_os_printf("%p [%s]\n", obj_desc->reference.object,
 				       acpi_ut_get_type_name(((union
 							       acpi_operand_object
-							       *)obj_desc->
+							       *)
+							      obj_desc->
 							      reference.
 							      object)->common.
 							     type));
 			break;
 
-		case AML_ARG_OP:
+		case ACPI_REFCLASS_ARG:
 
-			acpi_os_printf("Reference: [Arg%d]",
-				       obj_desc->reference.offset);
+			acpi_os_printf("%X", obj_desc->reference.value);
 
 			if (ACPI_GET_OBJECT_TYPE(obj_desc) == ACPI_TYPE_INTEGER) {
 
@@ -543,10 +543,9 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth)
 			acpi_os_printf("\n");
 			break;
 
-		case AML_LOCAL_OP:
+		case ACPI_REFCLASS_LOCAL:
 
-			acpi_os_printf("Reference: [Local%d]",
-				       obj_desc->reference.offset);
+			acpi_os_printf("%X", obj_desc->reference.value);
 
 			if (ACPI_GET_OBJECT_TYPE(obj_desc) == ACPI_TYPE_INTEGER) {
 
@@ -561,21 +560,16 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth)
 			acpi_os_printf("\n");
 			break;
 
-		case AML_INT_NAMEPATH_OP:
+		case ACPI_REFCLASS_NAME:
 
-			acpi_os_printf("Reference: [Namepath] %X [%4.4s]\n",
-				       obj_desc->reference.node->name.integer,
+			acpi_os_printf("- [%4.4s]\n",
 				       obj_desc->reference.node->name.ascii);
 			break;
 
-		default:
-
-			/* Unknown opcode */
+		default:	/* Unknown reference class */
 
-			acpi_os_printf("Unknown Reference opcode=%X\n",
-				       obj_desc->reference.opcode);
+			acpi_os_printf("%2.2X\n", obj_desc->reference.class);
 			break;
-
 		}
 		break;
 
@@ -866,8 +860,8 @@ static void acpi_ex_dump_reference_obj(union acpi_operand_object *obj_desc)
 
 	ret_buf.length = ACPI_ALLOCATE_LOCAL_BUFFER;
 
-	if (obj_desc->reference.opcode == AML_INT_NAMEPATH_OP) {
-		acpi_os_printf(" Named Object %p ", obj_desc->reference.node);
+	if (obj_desc->reference.class == ACPI_REFCLASS_NAME) {
+		acpi_os_printf(" %p ", obj_desc->reference.node);
 
 		status =
 		    acpi_ns_handle_to_pathname(obj_desc->reference.node,
@@ -883,8 +877,8 @@ static void acpi_ex_dump_reference_obj(union acpi_operand_object *obj_desc)
 		    ACPI_DESC_TYPE_OPERAND) {
 			acpi_os_printf(" Target: %p",
 				       obj_desc->reference.object);
-			if (obj_desc->reference.opcode == AML_LOAD_OP) {
-				acpi_os_printf(" [DDBHandle] Table Index: %X\n",
+			if (obj_desc->reference.class == ACPI_REFCLASS_TABLE) {
+				acpi_os_printf(" Table Index: %X\n",
 					       obj_desc->reference.value);
 			} else {
 				acpi_os_printf(" Target: %p [%s]\n",
@@ -987,9 +981,9 @@ acpi_ex_dump_package_obj(union acpi_operand_object *obj_desc,
 
 	case ACPI_TYPE_LOCAL_REFERENCE:
 
-		acpi_os_printf("[Object Reference] %s",
-			       (acpi_ps_get_opcode_info
-				(obj_desc->reference.opcode))->name);
+		acpi_os_printf("[Object Reference] Type [%s] %2.2X",
+			       acpi_ut_get_reference_name(obj_desc),
+			       obj_desc->reference.class);
 		acpi_ex_dump_reference_obj(obj_desc);
 		break;
 
diff --git a/drivers/acpi/executer/exmisc.c b/drivers/acpi/executer/exmisc.c
index 731414a581a6..efb191340059 100644
--- a/drivers/acpi/executer/exmisc.c
+++ b/drivers/acpi/executer/exmisc.c
@@ -86,10 +86,10 @@ acpi_ex_get_object_reference(union acpi_operand_object *obj_desc,
 		/*
 		 * Must be a reference to a Local or Arg
 		 */
-		switch (obj_desc->reference.opcode) {
-		case AML_LOCAL_OP:
-		case AML_ARG_OP:
-		case AML_DEBUG_OP:
+		switch (obj_desc->reference.class) {
+		case ACPI_REFCLASS_LOCAL:
+		case ACPI_REFCLASS_ARG:
+		case ACPI_REFCLASS_DEBUG:
 
 			/* The referenced object is the pseudo-node for the local/arg */
 
@@ -98,8 +98,8 @@ acpi_ex_get_object_reference(union acpi_operand_object *obj_desc,
 
 		default:
 
-			ACPI_ERROR((AE_INFO, "Unknown Reference opcode %X",
-				    obj_desc->reference.opcode));
+			ACPI_ERROR((AE_INFO, "Unknown Reference Class %2.2X",
+				    obj_desc->reference.class));
 			return_ACPI_STATUS(AE_AML_INTERNAL);
 		}
 		break;
@@ -127,7 +127,7 @@ acpi_ex_get_object_reference(union acpi_operand_object *obj_desc,
 		return_ACPI_STATUS(AE_NO_MEMORY);
 	}
 
-	reference_obj->reference.opcode = AML_REF_OF_OP;
+	reference_obj->reference.class = ACPI_REFCLASS_REFOF;
 	reference_obj->reference.object = referenced_obj;
 	*return_desc = reference_obj;
 
diff --git a/drivers/acpi/executer/exoparg1.c b/drivers/acpi/executer/exoparg1.c
index 7c3bea575e02..f622f9eac8a1 100644
--- a/drivers/acpi/executer/exoparg1.c
+++ b/drivers/acpi/executer/exoparg1.c
@@ -825,16 +825,16 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 				 *
 				 * Must resolve/dereference the local/arg reference first
 				 */
-				switch (operand[0]->reference.opcode) {
-				case AML_LOCAL_OP:
-				case AML_ARG_OP:
+				switch (operand[0]->reference.class) {
+				case ACPI_REFCLASS_LOCAL:
+				case ACPI_REFCLASS_ARG:
 
 					/* Set Operand[0] to the value of the local/arg */
 
 					status =
 					    acpi_ds_method_data_get_value
-					    (operand[0]->reference.opcode,
-					     operand[0]->reference.offset,
+					    (operand[0]->reference.class,
+					     operand[0]->reference.value,
 					     walk_state, &temp_desc);
 					if (ACPI_FAILURE(status)) {
 						goto cleanup;
@@ -848,7 +848,7 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 					operand[0] = temp_desc;
 					break;
 
-				case AML_REF_OF_OP:
+				case ACPI_REFCLASS_REFOF:
 
 					/* Get the object to which the reference refers */
 
@@ -928,8 +928,8 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 			 * This must be a reference object produced by either the
 			 * Index() or ref_of() operator
 			 */
-			switch (operand[0]->reference.opcode) {
-			case AML_INDEX_OP:
+			switch (operand[0]->reference.class) {
+			case ACPI_REFCLASS_INDEX:
 
 				/*
 				 * The target type for the Index operator must be
@@ -965,7 +965,7 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 					return_desc->integer.value =
 					    temp_desc->buffer.
 					    pointer[operand[0]->reference.
-						    offset];
+						    value];
 					break;
 
 				case ACPI_TYPE_PACKAGE:
@@ -985,7 +985,7 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 				default:
 
 					ACPI_ERROR((AE_INFO,
-						    "Unknown Index TargetType %X in obj %p",
+						    "Unknown Index TargetType %X in reference object %p",
 						    operand[0]->reference.
 						    target_type, operand[0]));
 					status = AE_AML_OPERAND_TYPE;
@@ -993,7 +993,7 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 				}
 				break;
 
-			case AML_REF_OF_OP:
+			case ACPI_REFCLASS_REFOF:
 
 				return_desc = operand[0]->reference.object;
 
@@ -1013,9 +1013,9 @@ acpi_status acpi_ex_opcode_1A_0T_1R(struct acpi_walk_state *walk_state)
 
 			default:
 				ACPI_ERROR((AE_INFO,
-					    "Unknown opcode in reference(%p) - %X",
+					    "Unknown class in reference(%p) - %2.2X",
 					    operand[0],
-					    operand[0]->reference.opcode));
+					    operand[0]->reference.class));
 
 				status = AE_TYPE;
 				goto cleanup;
diff --git a/drivers/acpi/executer/exoparg2.c b/drivers/acpi/executer/exoparg2.c
index 8e8bbb6ccebd..368def5dffce 100644
--- a/drivers/acpi/executer/exoparg2.c
+++ b/drivers/acpi/executer/exoparg2.c
@@ -391,8 +391,8 @@ acpi_status acpi_ex_opcode_2A_1T_1R(struct acpi_walk_state *walk_state)
 		/* Initialize the Index reference object */
 
 		index = operand[1]->integer.value;
-		return_desc->reference.offset = (u32) index;
-		return_desc->reference.opcode = AML_INDEX_OP;
+		return_desc->reference.value = (u32) index;
+		return_desc->reference.class = ACPI_REFCLASS_INDEX;
 
 		/*
 		 * At this point, the Source operand is a String, Buffer, or Package.
diff --git a/drivers/acpi/executer/exresnte.c b/drivers/acpi/executer/exresnte.c
index 5596f42c9676..423ad3635f3d 100644
--- a/drivers/acpi/executer/exresnte.c
+++ b/drivers/acpi/executer/exresnte.c
@@ -46,8 +46,6 @@
 #include <acpi/acdispat.h>
 #include <acpi/acinterp.h>
 #include <acpi/acnamesp.h>
-#include <acpi/acparser.h>
-#include <acpi/amlcode.h>
 
 #define _COMPONENT          ACPI_EXECUTER
 ACPI_MODULE_NAME("exresnte")
@@ -238,10 +236,10 @@ acpi_ex_resolve_node_to_value(struct acpi_namespace_node **object_ptr,
 
 	case ACPI_TYPE_LOCAL_REFERENCE:
 
-		switch (source_desc->reference.opcode) {
-		case AML_LOAD_OP:	/* This is a ddb_handle */
-		case AML_REF_OF_OP:
-		case AML_INDEX_OP:
+		switch (source_desc->reference.class) {
+		case ACPI_REFCLASS_TABLE:	/* This is a ddb_handle */
+		case ACPI_REFCLASS_REFOF:
+		case ACPI_REFCLASS_INDEX:
 
 			/* Return an additional reference to the object */
 
@@ -253,10 +251,8 @@ acpi_ex_resolve_node_to_value(struct acpi_namespace_node **object_ptr,
 			/* No named references are allowed here */
 
 			ACPI_ERROR((AE_INFO,
-				    "Unsupported Reference opcode %X (%s)",
-				    source_desc->reference.opcode,
-				    acpi_ps_get_opcode_name(source_desc->
-							    reference.opcode)));
+				    "Unsupported Reference type %X",
+				    source_desc->reference.class));
 
 			return_ACPI_STATUS(AE_AML_OPERAND_TYPE);
 		}
diff --git a/drivers/acpi/executer/exresolv.c b/drivers/acpi/executer/exresolv.c
index b35f7c817acf..89571b92a522 100644
--- a/drivers/acpi/executer/exresolv.c
+++ b/drivers/acpi/executer/exresolv.c
@@ -47,7 +47,6 @@
 #include <acpi/acdispat.h>
 #include <acpi/acinterp.h>
 #include <acpi/acnamesp.h>
-#include <acpi/acparser.h>
 
 #define _COMPONENT          ACPI_EXECUTER
 ACPI_MODULE_NAME("exresolv")
@@ -141,7 +140,7 @@ acpi_ex_resolve_object_to_value(union acpi_operand_object **stack_ptr,
 	acpi_status status = AE_OK;
 	union acpi_operand_object *stack_desc;
 	union acpi_operand_object *obj_desc = NULL;
-	u16 opcode;
+	u8 ref_type;
 
 	ACPI_FUNCTION_TRACE(ex_resolve_object_to_value);
 
@@ -152,19 +151,19 @@ acpi_ex_resolve_object_to_value(union acpi_operand_object **stack_ptr,
 	switch (ACPI_GET_OBJECT_TYPE(stack_desc)) {
 	case ACPI_TYPE_LOCAL_REFERENCE:
 
-		opcode = stack_desc->reference.opcode;
+		ref_type = stack_desc->reference.class;
 
-		switch (opcode) {
-		case AML_LOCAL_OP:
-		case AML_ARG_OP:
+		switch (ref_type) {
+		case ACPI_REFCLASS_LOCAL:
+		case ACPI_REFCLASS_ARG:
 
 			/*
 			 * Get the local from the method's state info
 			 * Note: this increments the local's object reference count
 			 */
-			status = acpi_ds_method_data_get_value(opcode,
+			status = acpi_ds_method_data_get_value(ref_type,
 							       stack_desc->
-							       reference.offset,
+							       reference.value,
 							       walk_state,
 							       &obj_desc);
 			if (ACPI_FAILURE(status)) {
@@ -173,7 +172,7 @@ acpi_ex_resolve_object_to_value(union acpi_operand_object **stack_ptr,
 
 			ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
 					  "[Arg/Local %X] ValueObj is %p\n",
-					  stack_desc->reference.offset,
+					  stack_desc->reference.value,
 					  obj_desc));
 
 			/*
@@ -184,7 +183,7 @@ acpi_ex_resolve_object_to_value(union acpi_operand_object **stack_ptr,
 			*stack_ptr = obj_desc;
 			break;
 
-		case AML_INDEX_OP:
+		case ACPI_REFCLASS_INDEX:
 
 			switch (stack_desc->reference.target_type) {
 			case ACPI_TYPE_BUFFER_FIELD:
@@ -239,15 +238,15 @@ acpi_ex_resolve_object_to_value(union acpi_operand_object **stack_ptr,
 			}
 			break;
 
-		case AML_REF_OF_OP:
-		case AML_DEBUG_OP:
-		case AML_LOAD_OP:
+		case ACPI_REFCLASS_REFOF:
+		case ACPI_REFCLASS_DEBUG:
+		case ACPI_REFCLASS_TABLE:
 
 			/* Just leave the object as-is, do not dereference */
 
 			break;
 
-		case AML_INT_NAMEPATH_OP:	/* Reference to a named object */
+		case ACPI_REFCLASS_NAME:	/* Reference to a named object */
 
 			/* Dereference the name */
 
@@ -273,8 +272,7 @@ acpi_ex_resolve_object_to_value(union acpi_operand_object **stack_ptr,
 		default:
 
 			ACPI_ERROR((AE_INFO,
-				    "Unknown Reference opcode %X (%s) in %p",
-				    opcode, acpi_ps_get_opcode_name(opcode),
+				    "Unknown Reference type %X in %p", ref_type,
 				    stack_desc));
 			status = AE_AML_INTERNAL;
 			break;
@@ -388,13 +386,13 @@ acpi_ex_resolve_multiple(struct acpi_walk_state *walk_state,
 	 * traversing the list of possibly many nested references.
 	 */
 	while (ACPI_GET_OBJECT_TYPE(obj_desc) == ACPI_TYPE_LOCAL_REFERENCE) {
-		switch (obj_desc->reference.opcode) {
-		case AML_REF_OF_OP:
-		case AML_INT_NAMEPATH_OP:
+		switch (obj_desc->reference.class) {
+		case ACPI_REFCLASS_REFOF:
+		case ACPI_REFCLASS_NAME:
 
 			/* Dereference the reference pointer */
 
-			if (obj_desc->reference.opcode == AML_REF_OF_OP) {
+			if (obj_desc->reference.class == ACPI_REFCLASS_REFOF) {
 				node = obj_desc->reference.object;
 			} else {	/* AML_INT_NAMEPATH_OP */
 
@@ -429,7 +427,7 @@ acpi_ex_resolve_multiple(struct acpi_walk_state *walk_state,
 			}
 			break;
 
-		case AML_INDEX_OP:
+		case ACPI_REFCLASS_INDEX:
 
 			/* Get the type of this reference (index into another object) */
 
@@ -455,22 +453,22 @@ acpi_ex_resolve_multiple(struct acpi_walk_state *walk_state,
 			}
 			break;
 
-		case AML_LOAD_OP:
+		case ACPI_REFCLASS_TABLE:
 
 			type = ACPI_TYPE_DDB_HANDLE;
 			goto exit;
 
-		case AML_LOCAL_OP:
-		case AML_ARG_OP:
+		case ACPI_REFCLASS_LOCAL:
+		case ACPI_REFCLASS_ARG:
 
 			if (return_desc) {
 				status =
 				    acpi_ds_method_data_get_value(obj_desc->
 								  reference.
-								  opcode,
+								  class,
 								  obj_desc->
 								  reference.
-								  offset,
+								  value,
 								  walk_state,
 								  &obj_desc);
 				if (ACPI_FAILURE(status)) {
@@ -481,10 +479,10 @@ acpi_ex_resolve_multiple(struct acpi_walk_state *walk_state,
 				status =
 				    acpi_ds_method_data_get_node(obj_desc->
 								 reference.
-								 opcode,
+								 class,
 								 obj_desc->
 								 reference.
-								 offset,
+								 value,
 								 walk_state,
 								 &node);
 				if (ACPI_FAILURE(status)) {
@@ -499,7 +497,7 @@ acpi_ex_resolve_multiple(struct acpi_walk_state *walk_state,
 			}
 			break;
 
-		case AML_DEBUG_OP:
+		case ACPI_REFCLASS_DEBUG:
 
 			/* The Debug Object is of type "DebugObject" */
 
@@ -509,8 +507,8 @@ acpi_ex_resolve_multiple(struct acpi_walk_state *walk_state,
 		default:
 
 			ACPI_ERROR((AE_INFO,
-				    "Unknown Reference subtype %X",
-				    obj_desc->reference.opcode));
+				    "Unknown Reference Class %2.2X",
+				    obj_desc->reference.class));
 			return_ACPI_STATUS(AE_AML_INTERNAL);
 		}
 	}
diff --git a/drivers/acpi/executer/exresop.c b/drivers/acpi/executer/exresop.c
index 54085f16ec28..0bb82593da72 100644
--- a/drivers/acpi/executer/exresop.c
+++ b/drivers/acpi/executer/exresop.c
@@ -225,41 +225,36 @@ acpi_ex_resolve_operands(u16 opcode,
 
 			if (object_type == (u8) ACPI_TYPE_LOCAL_REFERENCE) {
 
-				/* Decode the Reference */
+				/* Validate the Reference */
 
-				op_info = acpi_ps_get_opcode_info(opcode);
-				if (op_info->class == AML_CLASS_UNKNOWN) {
-					return_ACPI_STATUS(AE_AML_BAD_OPCODE);
-				}
+				switch (obj_desc->reference.class) {
+				case ACPI_REFCLASS_DEBUG:
 
-				switch (obj_desc->reference.opcode) {
-				case AML_DEBUG_OP:
 					target_op = AML_DEBUG_OP;
 
 					/*lint -fallthrough */
 
-				case AML_INDEX_OP:
-				case AML_REF_OF_OP:
-				case AML_ARG_OP:
-				case AML_LOCAL_OP:
-				case AML_LOAD_OP:	/* ddb_handle from LOAD_OP or LOAD_TABLE_OP */
-				case AML_INT_NAMEPATH_OP:	/* Reference to a named object */
-
-					ACPI_DEBUG_ONLY_MEMBERS(ACPI_DEBUG_PRINT
-								((ACPI_DB_EXEC,
-								  "Operand is a Reference, RefOpcode [%s]\n",
-								  (acpi_ps_get_opcode_info
-								   (obj_desc->
-								    reference.
-								    opcode))->
-								  name)));
+				case ACPI_REFCLASS_ARG:
+				case ACPI_REFCLASS_LOCAL:
+				case ACPI_REFCLASS_INDEX:
+				case ACPI_REFCLASS_REFOF:
+				case ACPI_REFCLASS_TABLE:	/* ddb_handle from LOAD_OP or LOAD_TABLE_OP */
+				case ACPI_REFCLASS_NAME:	/* Reference to a named object */
+
+					ACPI_DEBUG_PRINT((ACPI_DB_EXEC,
+							  "Operand is a Reference, Class [%s] %2.2X\n",
+							  acpi_ut_get_reference_name
+							  (obj_desc),
+							  obj_desc->reference.
+							  class));
 					break;
 
 				default:
+
 					ACPI_ERROR((AE_INFO,
-						    "Operand is a Reference, Unknown Reference Opcode: %X",
-						    obj_desc->reference.
-						    opcode));
+						    "Unknown Reference Class %2.2X in %p",
+						    obj_desc->reference.class,
+						    obj_desc));
 
 					return_ACPI_STATUS(AE_AML_OPERAND_TYPE);
 				}
@@ -270,8 +265,7 @@ acpi_ex_resolve_operands(u16 opcode,
 
 			/* Invalid descriptor */
 
-			ACPI_ERROR((AE_INFO,
-				    "Invalid descriptor %p [%s]",
+			ACPI_ERROR((AE_INFO, "Invalid descriptor %p [%s]",
 				    obj_desc,
 				    acpi_ut_get_descriptor_name(obj_desc)));
 
@@ -343,7 +337,7 @@ acpi_ex_resolve_operands(u16 opcode,
 			if ((opcode == AML_STORE_OP) &&
 			    (ACPI_GET_OBJECT_TYPE(*stack_ptr) ==
 			     ACPI_TYPE_LOCAL_REFERENCE)
-			    && ((*stack_ptr)->reference.opcode == AML_INDEX_OP)) {
+			    && ((*stack_ptr)->reference.class == ACPI_REFCLASS_INDEX)) {
 				goto next_operand;
 			}
 			break;
diff --git a/drivers/acpi/executer/exstore.c b/drivers/acpi/executer/exstore.c
index 20b4893e06ed..3318df4cbd98 100644
--- a/drivers/acpi/executer/exstore.c
+++ b/drivers/acpi/executer/exstore.c
@@ -47,7 +47,6 @@
 #include <acpi/acinterp.h>
 #include <acpi/amlcode.h>
 #include <acpi/acnamesp.h>
-#include <acpi/acparser.h>
 
 #define _COMPONENT          ACPI_EXECUTER
 ACPI_MODULE_NAME("exstore")
@@ -179,23 +178,27 @@ acpi_ex_do_debug_object(union acpi_operand_object *source_desc,
 
 	case ACPI_TYPE_LOCAL_REFERENCE:
 
-		if (source_desc->reference.opcode == AML_INDEX_OP) {
-			ACPI_DEBUG_PRINT_RAW((ACPI_DB_DEBUG_OBJECT,
-					      "[%s, 0x%X]\n",
-					      acpi_ps_get_opcode_name
-					      (source_desc->reference.opcode),
-					      source_desc->reference.offset));
-		} else {
-			ACPI_DEBUG_PRINT_RAW((ACPI_DB_DEBUG_OBJECT, "[%s]",
-					      acpi_ps_get_opcode_name
-					      (source_desc->reference.opcode)));
-		}
+		ACPI_DEBUG_PRINT_RAW((ACPI_DB_DEBUG_OBJECT, "[%s] ",
+				      acpi_ut_get_reference_name(source_desc)));
+
+		/* Decode the reference */
+
+		switch (source_desc->reference.class) {
+		case ACPI_REFCLASS_INDEX:
+
+			ACPI_DEBUG_PRINT_RAW((ACPI_DB_DEBUG_OBJECT, "0x%X\n",
+					      source_desc->reference.value));
+			break;
+
+		case ACPI_REFCLASS_TABLE:
 
-		if (source_desc->reference.opcode == AML_LOAD_OP) {	/* Load and load_table */
 			ACPI_DEBUG_PRINT_RAW((ACPI_DB_DEBUG_OBJECT,
-					      " Table Index %X\n",
+					      "Table Index 0x%X\n",
 					      source_desc->reference.value));
 			break;
+
+		default:
+			break;
 		}
 
 		ACPI_DEBUG_PRINT_RAW((ACPI_DB_DEBUG_OBJECT, "  "));
@@ -347,15 +350,15 @@ acpi_ex_store(union acpi_operand_object *source_desc,
 	}
 
 	/*
-	 * Examine the Reference opcode.  These cases are handled:
+	 * Examine the Reference class. These cases are handled:
 	 *
 	 * 1) Store to Name (Change the object associated with a name)
 	 * 2) Store to an indexed area of a Buffer or Package
 	 * 3) Store to a Method Local or Arg
 	 * 4) Store to the debug object
 	 */
-	switch (ref_desc->reference.opcode) {
-	case AML_REF_OF_OP:
+	switch (ref_desc->reference.class) {
+	case ACPI_REFCLASS_REFOF:
 
 		/* Storing an object into a Name "container" */
 
@@ -365,7 +368,7 @@ acpi_ex_store(union acpi_operand_object *source_desc,
 						      ACPI_IMPLICIT_CONVERSION);
 		break;
 
-	case AML_INDEX_OP:
+	case ACPI_REFCLASS_INDEX:
 
 		/* Storing to an Index (pointer into a packager or buffer) */
 
@@ -374,18 +377,18 @@ acpi_ex_store(union acpi_operand_object *source_desc,
 						  walk_state);
 		break;
 
-	case AML_LOCAL_OP:
-	case AML_ARG_OP:
+	case ACPI_REFCLASS_LOCAL:
+	case ACPI_REFCLASS_ARG:
 
 		/* Store to a method local/arg  */
 
 		status =
-		    acpi_ds_store_object_to_local(ref_desc->reference.opcode,
-						  ref_desc->reference.offset,
+		    acpi_ds_store_object_to_local(ref_desc->reference.class,
+						  ref_desc->reference.value,
 						  source_desc, walk_state);
 		break;
 
-	case AML_DEBUG_OP:
+	case ACPI_REFCLASS_DEBUG:
 
 		/*
 		 * Storing to the Debug object causes the value stored to be
@@ -401,8 +404,8 @@ acpi_ex_store(union acpi_operand_object *source_desc,
 
 	default:
 
-		ACPI_ERROR((AE_INFO, "Unknown Reference opcode %X",
-			    ref_desc->reference.opcode));
+		ACPI_ERROR((AE_INFO, "Unknown Reference Class %2.2X",
+			    ref_desc->reference.class));
 		ACPI_DUMP_ENTRY(ref_desc, ACPI_LV_INFO);
 
 		status = AE_AML_INTERNAL;
@@ -458,7 +461,7 @@ acpi_ex_store_object_to_index(union acpi_operand_object *source_desc,
 
 		if (ACPI_GET_OBJECT_TYPE(source_desc) ==
 		    ACPI_TYPE_LOCAL_REFERENCE
-		    && source_desc->reference.opcode == AML_LOAD_OP) {
+		    && source_desc->reference.class == ACPI_REFCLASS_TABLE) {
 
 			/* This is a DDBHandle, just add a reference to it */
 
@@ -553,7 +556,7 @@ acpi_ex_store_object_to_index(union acpi_operand_object *source_desc,
 
 		/* Store the source value into the target buffer byte */
 
-		obj_desc->buffer.pointer[index_desc->reference.offset] = value;
+		obj_desc->buffer.pointer[index_desc->reference.value] = value;
 		break;
 
 	default:
diff --git a/drivers/acpi/executer/exstoren.c b/drivers/acpi/executer/exstoren.c
index a6d2168b81f9..eef61a00803e 100644
--- a/drivers/acpi/executer/exstoren.c
+++ b/drivers/acpi/executer/exstoren.c
@@ -121,7 +121,8 @@ acpi_ex_resolve_object(union acpi_operand_object **source_desc_ptr,
 		    (ACPI_GET_OBJECT_TYPE(source_desc) != ACPI_TYPE_STRING) &&
 		    !((ACPI_GET_OBJECT_TYPE(source_desc) ==
 		       ACPI_TYPE_LOCAL_REFERENCE)
-		      && (source_desc->reference.opcode == AML_LOAD_OP))) {
+		      && (source_desc->reference.class ==
+			  ACPI_REFCLASS_TABLE))) {
 
 			/* Conversion successful but still not a valid type */
 
diff --git a/drivers/acpi/namespace/nsdump.c b/drivers/acpi/namespace/nsdump.c
index 0ab22004728a..cc0ae39440e4 100644
--- a/drivers/acpi/namespace/nsdump.c
+++ b/drivers/acpi/namespace/nsdump.c
@@ -43,7 +43,6 @@
 
 #include <acpi/acpi.h>
 #include <acpi/acnamesp.h>
-#include <acpi/acparser.h>
 
 #define _COMPONENT          ACPI_NAMESPACE
 ACPI_MODULE_NAME("nsdump")
@@ -334,9 +333,7 @@ acpi_ns_dump_one_object(acpi_handle obj_handle,
 		case ACPI_TYPE_LOCAL_REFERENCE:
 
 			acpi_os_printf("[%s]\n",
-				       acpi_ps_get_opcode_name(obj_desc->
-							       reference.
-							       opcode));
+				       acpi_ut_get_reference_name(obj_desc));
 			break;
 
 		case ACPI_TYPE_BUFFER_FIELD:
diff --git a/drivers/acpi/namespace/nsxfeval.c b/drivers/acpi/namespace/nsxfeval.c
index f3cc37624537..a085cc39c055 100644
--- a/drivers/acpi/namespace/nsxfeval.c
+++ b/drivers/acpi/namespace/nsxfeval.c
@@ -45,7 +45,6 @@
 #include <acpi/acpi.h>
 #include <acpi/acnamesp.h>
 #include <acpi/acinterp.h>
-#include <acpi/amlcode.h>
 
 #define _COMPONENT          ACPI_NAMESPACE
 ACPI_MODULE_NAME("nsxfeval")
@@ -399,13 +398,13 @@ static void acpi_ns_resolve_references(struct acpi_evaluate_info *info)
 	 * (AML_LOAD_OP) cannot be dereferenced, nor can it be converted to
 	 * an union acpi_object.
 	 */
-	switch (info->return_object->reference.opcode) {
-	case AML_INDEX_OP:
+	switch (info->return_object->reference.class) {
+	case ACPI_REFCLASS_INDEX:
 
 		obj_desc = *(info->return_object->reference.where);
 		break;
 
-	case AML_REF_OF_OP:
+	case ACPI_REFCLASS_REFOF:
 
 		node = info->return_object->reference.object;
 		if (node) {
diff --git a/drivers/acpi/resources/rscalc.c b/drivers/acpi/resources/rscalc.c
index d9063ea414e3..8eaaecf92009 100644
--- a/drivers/acpi/resources/rscalc.c
+++ b/drivers/acpi/resources/rscalc.c
@@ -43,7 +43,6 @@
 
 #include <acpi/acpi.h>
 #include <acpi/acresrc.h>
-#include <acpi/amlcode.h>
 #include <acpi/acnamesp.h>
 
 #define _COMPONENT          ACPI_RESOURCES
@@ -560,8 +559,8 @@ acpi_rs_get_pci_routing_table_length(union acpi_operand_object *package_object,
 			      ACPI_GET_OBJECT_TYPE(*sub_object_list)) ||
 			     ((ACPI_TYPE_LOCAL_REFERENCE ==
 			       ACPI_GET_OBJECT_TYPE(*sub_object_list)) &&
-			      ((*sub_object_list)->reference.opcode ==
-			       AML_INT_NAMEPATH_OP)))) {
+			      ((*sub_object_list)->reference.class ==
+			       ACPI_REFCLASS_NAME)))) {
 				name_found = TRUE;
 			} else {
 				/* Look at the next element */
diff --git a/drivers/acpi/resources/rscreate.c b/drivers/acpi/resources/rscreate.c
index 7804a8c40e7a..c0bbfa2c4193 100644
--- a/drivers/acpi/resources/rscreate.c
+++ b/drivers/acpi/resources/rscreate.c
@@ -43,7 +43,6 @@
 
 #include <acpi/acpi.h>
 #include <acpi/acresrc.h>
-#include <acpi/amlcode.h>
 #include <acpi/acnamesp.h>
 
 #define _COMPONENT          ACPI_RESOURCES
@@ -310,13 +309,12 @@ acpi_rs_create_pci_routing_table(union acpi_operand_object *package_object,
 			switch (ACPI_GET_OBJECT_TYPE(obj_desc)) {
 			case ACPI_TYPE_LOCAL_REFERENCE:
 
-				if (obj_desc->reference.opcode !=
-				    AML_INT_NAMEPATH_OP) {
+				if (obj_desc->reference.class !=
+				    ACPI_REFCLASS_NAME) {
 					ACPI_ERROR((AE_INFO,
-						    "(PRT[%X].Source) Need name, found reference op %X",
+						    "(PRT[%X].Source) Need name, found Reference Class %X",
 						    index,
-						    obj_desc->reference.
-						    opcode));
+						    obj_desc->reference.class));
 					return_ACPI_STATUS(AE_BAD_DATA);
 				}
 
diff --git a/drivers/acpi/utilities/utcopy.c b/drivers/acpi/utilities/utcopy.c
index 53499ac90988..5b2f7c27b705 100644
--- a/drivers/acpi/utilities/utcopy.c
+++ b/drivers/acpi/utilities/utcopy.c
@@ -42,7 +42,6 @@
  */
 
 #include <acpi/acpi.h>
-#include <acpi/amlcode.h>
 #include <acpi/acnamesp.h>
 
 
@@ -176,20 +175,24 @@ acpi_ut_copy_isimple_to_esimple(union acpi_operand_object *internal_object,
 
 		/* This is an object reference. */
 
-		switch (internal_object->reference.opcode) {
-		case AML_INT_NAMEPATH_OP:
-
-			/* For namepath, return the object handle ("reference") */
-
-		default:
-
-			/* We are referring to the namespace node */
+		switch (internal_object->reference.class) {
+		case ACPI_REFCLASS_NAME:
 
+			/*
+			 * For namepath, return the object handle ("reference")
+			 * We are referring to the namespace node
+			 */
 			external_object->reference.handle =
 			    internal_object->reference.node;
 			external_object->reference.actual_type =
 			    acpi_ns_get_type(internal_object->reference.node);
 			break;
+
+		default:
+
+			/* All other reference types are unsupported */
+
+			return_ACPI_STATUS(AE_TYPE);
 		}
 		break;
 
@@ -533,7 +536,7 @@ acpi_ut_copy_esimple_to_isimple(union acpi_object *external_object,
 
 		/* TBD: should validate incoming handle */
 
-		internal_object->reference.opcode = AML_INT_NAMEPATH_OP;
+		internal_object->reference.class = ACPI_REFCLASS_NAME;
 		internal_object->reference.node =
 		    external_object->reference.handle;
 		break;
@@ -743,11 +746,11 @@ acpi_ut_copy_simple_object(union acpi_operand_object *source_desc,
 		 * We copied the reference object, so we now must add a reference
 		 * to the object pointed to by the reference
 		 *
-		 * DDBHandle reference (from Load/load_table is a special reference,
-		 * it's Reference.Object is the table index, so does not need to
+		 * DDBHandle reference (from Load/load_table) is a special reference,
+		 * it does not have a Reference.Object, so does not need to
 		 * increase the reference count
 		 */
-		if (source_desc->reference.opcode == AML_LOAD_OP) {
+		if (source_desc->reference.class == ACPI_REFCLASS_TABLE) {
 			break;
 		}
 
diff --git a/drivers/acpi/utilities/utdelete.c b/drivers/acpi/utilities/utdelete.c
index 42609d3a8aa9..5c219758c226 100644
--- a/drivers/acpi/utilities/utdelete.c
+++ b/drivers/acpi/utilities/utdelete.c
@@ -45,7 +45,6 @@
 #include <acpi/acinterp.h>
 #include <acpi/acnamesp.h>
 #include <acpi/acevents.h>
-#include <acpi/amlcode.h>
 
 #define _COMPONENT          ACPI_UTILITIES
 ACPI_MODULE_NAME("utdelete")
@@ -548,8 +547,8 @@ acpi_ut_update_object_reference(union acpi_operand_object *object, u16 action)
 			 * reference must track changes to the ref count of the index or
 			 * target object.
 			 */
-			if ((object->reference.opcode == AML_INDEX_OP) ||
-			    (object->reference.opcode == AML_INT_NAMEPATH_OP)) {
+			if ((object->reference.class == ACPI_REFCLASS_INDEX) ||
+			    (object->reference.class == ACPI_REFCLASS_NAME)) {
 				next_object = object->reference.object;
 			}
 			break;
diff --git a/drivers/acpi/utilities/utglobal.c b/drivers/acpi/utilities/utglobal.c
index bcace577183b..0b1e493a8374 100644
--- a/drivers/acpi/utilities/utglobal.c
+++ b/drivers/acpi/utilities/utglobal.c
@@ -45,7 +45,6 @@
 
 #include <acpi/acpi.h>
 #include <acpi/acnamesp.h>
-#include <acpi/amlcode.h>
 
 ACPI_EXPORT_SYMBOL(acpi_gbl_FADT)
 #define _COMPONENT          ACPI_UTILITIES
@@ -590,25 +589,31 @@ char *acpi_ut_get_descriptor_name(void *object)
 
 /* Printable names of reference object sub-types */
 
+static const char *acpi_gbl_ref_class_names[] = {
+	/* 00 */ "Local",
+	/* 01 */ "Argument",
+	/* 02 */ "RefOf",
+	/* 03 */ "Index",
+	/* 04 */ "DdbHandle",
+	/* 05 */ "Named Object",
+	/* 06 */ "Debug"
+};
+
 const char *acpi_ut_get_reference_name(union acpi_operand_object *object)
 {
+	if (!object)
+		return "NULL Object";
 
-	switch (object->reference.opcode) {
-	case AML_INT_NAMEPATH_OP:
-		return "Name";
+	if (ACPI_GET_DESCRIPTOR_TYPE(object) != ACPI_DESC_TYPE_OPERAND)
+		return "Not an Operand object";
 
-	case AML_LOAD_OP:
-		return "DDB-Handle";
+	if (object->common.type != ACPI_TYPE_LOCAL_REFERENCE)
+		return "Not a Reference object";
 
-	case AML_REF_OF_OP:
-		return "RefOf";
+	if (object->reference.class > ACPI_REFCLASS_MAX)
+		return "Unknown Reference class";
 
-	case AML_INDEX_OP:
-		return "Index";
-
-	default:
-		return "Unknown";
-	}
+	return acpi_gbl_ref_class_names[object->reference.class];
 }
 
 #if defined(ACPI_DEBUG_OUTPUT) || defined(ACPI_DEBUGGER)
@@ -812,4 +817,4 @@ acpi_status acpi_ut_init_globals(void)
 }
 
 ACPI_EXPORT_SYMBOL(acpi_dbg_level)
-    ACPI_EXPORT_SYMBOL(acpi_dbg_layer)
+ACPI_EXPORT_SYMBOL(acpi_dbg_layer)
diff --git a/drivers/acpi/utilities/utobject.c b/drivers/acpi/utilities/utobject.c
index 924d05af94d2..c354e7a42bcd 100644
--- a/drivers/acpi/utilities/utobject.c
+++ b/drivers/acpi/utilities/utobject.c
@@ -43,7 +43,6 @@
 
 #include <acpi/acpi.h>
 #include <acpi/acnamesp.h>
-#include <acpi/amlcode.h>
 
 #define _COMPONENT          ACPI_UTILITIES
 ACPI_MODULE_NAME("utobject")
@@ -478,8 +477,8 @@ acpi_ut_get_simple_object_size(union acpi_operand_object *internal_object,
 
 	case ACPI_TYPE_LOCAL_REFERENCE:
 
-		switch (internal_object->reference.opcode) {
-		case AML_INT_NAMEPATH_OP:
+		switch (internal_object->reference.class) {
+		case ACPI_REFCLASS_NAME:
 
 			/*
 			 * Get the actual length of the full pathname to this object.
@@ -504,9 +503,9 @@ acpi_ut_get_simple_object_size(union acpi_operand_object *internal_object,
 			 */
 			ACPI_ERROR((AE_INFO,
 				    "Cannot convert to external object - "
-				    "unsupported Reference type [%s] %X in object %p",
+				    "unsupported Reference Class [%s] %X in object %p",
 				    acpi_ut_get_reference_name(internal_object),
-				    internal_object->reference.opcode,
+				    internal_object->reference.class,
 				    internal_object));
 			status = AE_TYPE;
 			break;
diff --git a/include/acpi/acdebug.h b/include/acpi/acdebug.h
index c5a1b50d8d94..a4fb001d96f1 100644
--- a/include/acpi/acdebug.h
+++ b/include/acpi/acdebug.h
@@ -123,6 +123,10 @@ void acpi_db_check_integrity(void);
 
 void acpi_db_generate_gpe(char *gpe_arg, char *block_arg);
 
+void acpi_db_check_predefined_names(void);
+
+void acpi_db_batch_execute(void);
+
 /*
  * dbdisply - debug display commands
  */
diff --git a/include/acpi/acdispat.h b/include/acpi/acdispat.h
index 21a73a105d0a..6291904be01e 100644
--- a/include/acpi/acdispat.h
+++ b/include/acpi/acdispat.h
@@ -157,7 +157,7 @@ acpi_ds_init_callbacks(struct acpi_walk_state *walk_state, u32 pass_number);
  * dsmthdat - method data (locals/args)
  */
 acpi_status
-acpi_ds_store_object_to_local(u16 opcode,
+acpi_ds_store_object_to_local(u8 type,
 			      u32 index,
 			      union acpi_operand_object *src_desc,
 			      struct acpi_walk_state *walk_state);
@@ -173,7 +173,7 @@ void acpi_ds_method_data_delete_all(struct acpi_walk_state *walk_state);
 u8 acpi_ds_is_method_value(union acpi_operand_object *obj_desc);
 
 acpi_status
-acpi_ds_method_data_get_value(u16 opcode,
+acpi_ds_method_data_get_value(u8 type,
 			      u32 index,
 			      struct acpi_walk_state *walk_state,
 			      union acpi_operand_object **dest_desc);
@@ -184,7 +184,7 @@ acpi_ds_method_data_init_args(union acpi_operand_object **params,
 			      struct acpi_walk_state *walk_state);
 
 acpi_status
-acpi_ds_method_data_get_node(u16 opcode,
+acpi_ds_method_data_get_node(u8 type,
 			     u32 index,
 			     struct acpi_walk_state *walk_state,
 			     struct acpi_namespace_node **node);
diff --git a/include/acpi/acobject.h b/include/acpi/acobject.h
index 7a8a652ffb78..eb6f038b03d9 100644
--- a/include/acpi/acobject.h
+++ b/include/acpi/acobject.h
@@ -308,19 +308,34 @@ struct acpi_object_addr_handler {
  *****************************************************************************/
 
 /*
- * The Reference object type is used for these opcodes:
- * Arg[0-6], Local[0-7], index_op, name_op, zero_op, one_op, ones_op, debug_op
+ * The Reference object is used for these opcodes:
+ * Arg[0-6], Local[0-7], index_op, name_op, ref_of_op, load_op, load_table_op, debug_op
+ * The Reference.Class differentiates these types.
  */
 struct acpi_object_reference {
-	ACPI_OBJECT_COMMON_HEADER u8 target_type;	/* Used for index_op */
-	u16 opcode;
+	ACPI_OBJECT_COMMON_HEADER u8 class;	/* Reference Class */
+	u8 target_type;		/* Used for Index Op */
+	u8 reserved;
 	void *object;		/* name_op=>HANDLE to obj, index_op=>union acpi_operand_object */
-	struct acpi_namespace_node *node;
-	union acpi_operand_object **where;
-	u32 offset;		/* Used for arg_op, local_op, and index_op */
-	u32 value;		/* Used for ddb_handle */
+	struct acpi_namespace_node *node;	/* ref_of or Namepath */
+	union acpi_operand_object **where;	/* Target of Index */
+	u32 value;		/* Used for Local/Arg/Index/ddb_handle */
 };
 
+/* Values for Reference.Class above */
+
+typedef enum {
+	ACPI_REFCLASS_LOCAL = 0,	/* Method local */
+	ACPI_REFCLASS_ARG = 1,	/* Method argument */
+	ACPI_REFCLASS_REFOF = 2,	/* Result of ref_of() TBD: Split to Ref/Node and Ref/operand_obj? */
+	ACPI_REFCLASS_INDEX = 3,	/* Result of Index() */
+	ACPI_REFCLASS_TABLE = 4,	/* ddb_handle - Load(), load_table() */
+	ACPI_REFCLASS_NAME = 5,	/* Reference to a named object */
+	ACPI_REFCLASS_DEBUG = 6,	/* Debug object */
+
+	ACPI_REFCLASS_MAX = 6
+} ACPI_REFERENCE_CLASSES;
+
 /*
  * Extra object is used as additional storage for types that
  * have AML code in their declarations (term_args) that must be
-- 
cgit v1.2.3


From 51f52819bd02112a1f61f0741231f14bdb0cae7b Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Sat, 27 Sep 2008 11:14:04 +0800
Subject: ACPICA: Update version to 20080829

Update version to 20080829.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 include/acpi/acconfig.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h
index 4da88b165b5c..2b737e510b15 100644
--- a/include/acpi/acconfig.h
+++ b/include/acpi/acconfig.h
@@ -63,7 +63,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION 		0x20080729
+#define ACPI_CA_VERSION                 0x20080829
 
 /*
  * OS name, used for the _OS object.  The _OS object is essentially obsolete,
-- 
cgit v1.2.3


From bbbbeb8e31af97f11b84294b2e7e5607125829d2 Mon Sep 17 00:00:00 2001
From: Lin Ming <ming.m.lin@intel.com>
Date: Sat, 27 Sep 2008 11:26:59 +0800
Subject: ACPICA: Remove unused ACPI register bit definition

Removed the ACPI_BITREG_WAKE_ENABLE definition and entry in the
global register table. This bit does not exist and is unused.

http://www.acpica.org/bugzilla/show_bug.cgi?id=442

Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/utilities/utglobal.c |  1 -
 include/acpi/actypes.h            | 34 +++++++++++++++++++++++-----------
 2 files changed, 23 insertions(+), 12 deletions(-)

(limited to 'include')

diff --git a/drivers/acpi/utilities/utglobal.c b/drivers/acpi/utilities/utglobal.c
index 0b1e493a8374..670551b95e56 100644
--- a/drivers/acpi/utilities/utglobal.c
+++ b/drivers/acpi/utilities/utglobal.c
@@ -281,7 +281,6 @@ struct acpi_bit_register_info acpi_gbl_bit_register_info[ACPI_NUM_BITREG] = {
 	/* ACPI_BITREG_RT_CLOCK_ENABLE      */ {ACPI_REGISTER_PM1_ENABLE,
 						ACPI_BITPOSITION_RT_CLOCK_ENABLE,
 						ACPI_BITMASK_RT_CLOCK_ENABLE},
-	/* ACPI_BITREG_WAKE_ENABLE          */ {ACPI_REGISTER_PM1_ENABLE, 0, 0},
 	/* ACPI_BITREG_PCIEXP_WAKE_DISABLE  */ {ACPI_REGISTER_PM1_ENABLE,
 						ACPI_BITPOSITION_PCIEXP_WAKE_DISABLE,
 						ACPI_BITMASK_PCIEXP_WAKE_DISABLE},
diff --git a/include/acpi/actypes.h b/include/acpi/actypes.h
index 6bd08e83f31c..e8936ab59627 100644
--- a/include/acpi/actypes.h
+++ b/include/acpi/actypes.h
@@ -607,8 +607,15 @@ typedef u8 acpi_adr_space_type;
 
 /*
  * bit_register IDs
- * These are bitfields defined within the full ACPI registers
+ *
+ * These values are intended to be used by the hardware interfaces
+ * and are mapped to individual bitfields defined within the ACPI
+ * registers. See the acpi_gbl_bit_register_info global table in utglobal.c
+ * for this mapping.
  */
+
+/* PM1 Status register */
+
 #define ACPI_BITREG_TIMER_STATUS                0x00
 #define ACPI_BITREG_BUS_MASTER_STATUS           0x01
 #define ACPI_BITREG_GLOBAL_LOCK_STATUS          0x02
@@ -618,24 +625,29 @@ typedef u8 acpi_adr_space_type;
 #define ACPI_BITREG_WAKE_STATUS                 0x06
 #define ACPI_BITREG_PCIEXP_WAKE_STATUS          0x07
 
+/* PM1 Enable register */
+
 #define ACPI_BITREG_TIMER_ENABLE                0x08
 #define ACPI_BITREG_GLOBAL_LOCK_ENABLE          0x09
 #define ACPI_BITREG_POWER_BUTTON_ENABLE         0x0A
 #define ACPI_BITREG_SLEEP_BUTTON_ENABLE         0x0B
 #define ACPI_BITREG_RT_CLOCK_ENABLE             0x0C
-#define ACPI_BITREG_WAKE_ENABLE                 0x0D
-#define ACPI_BITREG_PCIEXP_WAKE_DISABLE         0x0E
+#define ACPI_BITREG_PCIEXP_WAKE_DISABLE         0x0D
+
+/* PM1 Control register */
+
+#define ACPI_BITREG_SCI_ENABLE                  0x0E
+#define ACPI_BITREG_BUS_MASTER_RLD              0x0F
+#define ACPI_BITREG_GLOBAL_LOCK_RELEASE         0x10
+#define ACPI_BITREG_SLEEP_TYPE_A                0x11
+#define ACPI_BITREG_SLEEP_TYPE_B                0x12
+#define ACPI_BITREG_SLEEP_ENABLE                0x13
 
-#define ACPI_BITREG_SCI_ENABLE                  0x0F
-#define ACPI_BITREG_BUS_MASTER_RLD              0x10
-#define ACPI_BITREG_GLOBAL_LOCK_RELEASE         0x11
-#define ACPI_BITREG_SLEEP_TYPE_A                0x12
-#define ACPI_BITREG_SLEEP_TYPE_B                0x13
-#define ACPI_BITREG_SLEEP_ENABLE                0x14
+/* PM2 Control register */
 
-#define ACPI_BITREG_ARB_DISABLE                 0x15
+#define ACPI_BITREG_ARB_DISABLE                 0x14
 
-#define ACPI_BITREG_MAX                         0x15
+#define ACPI_BITREG_MAX                         0x14
 #define ACPI_NUM_BITREG                         ACPI_BITREG_MAX + 1
 
 /*
-- 
cgit v1.2.3


From e8707b340fb5b6313cde784b944a568dfd770ddd Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Sun, 28 Sep 2008 15:26:17 +0800
Subject: ACPICA: New: Validation for predefined ACPI methods/objects

Validates predefined ACPI objects that appear in the namespace,
at the time they are evaluated. The argument count and the type of
the returned object are validated. The purpose of this validation
is to detect problems with the BIOS-exposed predefined ACPI objects
before the results are returned to the ACPI-related drivers.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 drivers/acpi/namespace/Makefile   |   2 +-
 drivers/acpi/namespace/nseval.c   |  35 +-
 drivers/acpi/namespace/nsnames.c  |   2 -
 drivers/acpi/namespace/nspredef.c | 900 ++++++++++++++++++++++++++++++++++++++
 include/acpi/acdebug.h            |   4 +
 include/acpi/aclocal.h            |  77 ++++
 include/acpi/acnamesp.h           |  16 +
 include/acpi/acpredef.h           | 371 ++++++++++++++++
 8 files changed, 1401 insertions(+), 6 deletions(-)
 create mode 100644 drivers/acpi/namespace/nspredef.c
 create mode 100644 include/acpi/acpredef.h

(limited to 'include')

diff --git a/drivers/acpi/namespace/Makefile b/drivers/acpi/namespace/Makefile
index 3f63d3640696..371a2daf837f 100644
--- a/drivers/acpi/namespace/Makefile
+++ b/drivers/acpi/namespace/Makefile
@@ -5,7 +5,7 @@
 obj-y := nsaccess.o  nsload.o    nssearch.o  nsxfeval.o \
 	 nsalloc.o   nseval.o    nsnames.o   nsutils.o   nsxfname.o \
 	 nsdump.o    nsinit.o    nsobject.o  nswalk.o    nsxfobj.o  \
-	 nsparse.o
+	 nsparse.o   nspredef.o
 
 obj-$(ACPI_FUTURE_USAGE) += nsdumpdv.o
 
diff --git a/drivers/acpi/namespace/nseval.c b/drivers/acpi/namespace/nseval.c
index 42dae12f2ef8..4cdf03ac2b46 100644
--- a/drivers/acpi/namespace/nseval.c
+++ b/drivers/acpi/namespace/nseval.c
@@ -78,6 +78,7 @@ ACPI_MODULE_NAME("nseval")
 acpi_status acpi_ns_evaluate(struct acpi_evaluate_info * info)
 {
 	acpi_status status;
+	struct acpi_namespace_node *node;
 
 	ACPI_FUNCTION_TRACE(ns_evaluate);
 
@@ -117,6 +118,8 @@ acpi_status acpi_ns_evaluate(struct acpi_evaluate_info * info)
 			  info->resolved_node,
 			  acpi_ns_get_attached_object(info->resolved_node)));
 
+	node = info->resolved_node;
+
 	/*
 	 * Two major cases here:
 	 *
@@ -261,9 +264,35 @@ acpi_status acpi_ns_evaluate(struct acpi_evaluate_info * info)
 		}
 	}
 
-	/*
-	 * Check if there is a return value that must be dealt with
-	 */
+	/* Validation of return values for ACPI-predefined methods and objects */
+
+	if ((status == AE_OK) || (status == AE_CTRL_RETURN_VALUE)) {
+		/*
+		 * If this is the first evaluation, check the return value. This
+		 * ensures that any warnings will only be emitted during the very
+		 * first evaluation of the object.
+		 */
+		if (!(node->flags & ANOBJ_EVALUATED)) {
+			/*
+			 * Check for a predefined ACPI name. If found, validate the
+			 * returned object.
+			 *
+			 * Note: Ignore return status for now, emit warnings if there are
+			 * problems with the returned object. May change later to abort
+			 * the method on invalid return object.
+			 */
+			(void)acpi_ns_check_predefined_names(node,
+							     info->
+							     return_object);
+		}
+
+		/* Mark the node as having been evaluated */
+
+		node->flags |= ANOBJ_EVALUATED;
+	}
+
+	/* Check if there is a return value that must be dealt with */
+
 	if (status == AE_CTRL_RETURN_VALUE) {
 
 		/* If caller does not want the return value, delete it */
diff --git a/drivers/acpi/namespace/nsnames.c b/drivers/acpi/namespace/nsnames.c
index 9c587bdfe3f3..42a39a7c96e9 100644
--- a/drivers/acpi/namespace/nsnames.c
+++ b/drivers/acpi/namespace/nsnames.c
@@ -115,7 +115,6 @@ acpi_ns_build_external_path(struct acpi_namespace_node *node,
 	return (AE_OK);
 }
 
-#ifdef ACPI_DEBUG_OUTPUT
 /*******************************************************************************
  *
  * FUNCTION:    acpi_ns_get_external_pathname
@@ -163,7 +162,6 @@ char *acpi_ns_get_external_pathname(struct acpi_namespace_node *node)
 
 	return_PTR(name_buffer);
 }
-#endif
 
 /*******************************************************************************
  *
diff --git a/drivers/acpi/namespace/nspredef.c b/drivers/acpi/namespace/nspredef.c
new file mode 100644
index 000000000000..0f17cf0898c9
--- /dev/null
+++ b/drivers/acpi/namespace/nspredef.c
@@ -0,0 +1,900 @@
+/******************************************************************************
+ *
+ * Module Name: nspredef - Validation of ACPI predefined methods and objects
+ *              $Revision: 1.1 $
+ *
+ *****************************************************************************/
+
+/*
+ * Copyright (C) 2000 - 2008, Intel Corp.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. Redistributions in binary form must reproduce at minimum a disclaimer
+ *    substantially similar to the "NO WARRANTY" disclaimer below
+ *    ("Disclaimer") and any redistribution must be conditioned upon
+ *    including a substantially similar Disclaimer requirement for further
+ *    binary redistribution.
+ * 3. Neither the names of the above-listed copyright holders nor the names
+ *    of any contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * NO WARRANTY
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGES.
+ */
+
+#include <acpi/acpi.h>
+#include <acpi/acnamesp.h>
+#include <acpi/acpredef.h>
+
+#define _COMPONENT          ACPI_NAMESPACE
+ACPI_MODULE_NAME("nspredef")
+
+/*******************************************************************************
+ *
+ * This module validates predefined ACPI objects that appear in the namespace,
+ * at the time they are evaluated (via acpi_evaluate_object). The purpose of this
+ * validation is to detect problems with BIOS-exposed predefined ACPI objects
+ * before the results are returned to the ACPI-related drivers.
+ *
+ * There are several areas that are validated:
+ *
+ *  1) The number of input arguments as defined by the method/object in the
+ *      ASL is validated against the ACPI specification.
+ *  2) The type of the return object (if any) is validated against the ACPI
+ *      specification.
+ *  3) For returned package objects, the count of package elements is
+ *      validated, as well as the type of each package element. Nested
+ *      packages are supported.
+ *
+ * For any problems found, a warning message is issued.
+ *
+ ******************************************************************************/
+/* Local prototypes */
+static acpi_status
+acpi_ns_check_package(char *pathname,
+		      union acpi_operand_object *return_object,
+		      const union acpi_predefined_info *predefined);
+
+static acpi_status
+acpi_ns_check_package_elements(char *pathname,
+			       union acpi_operand_object **elements,
+			       u8 type1, u32 count1, u8 type2, u32 count2);
+
+static acpi_status
+acpi_ns_check_object_type(char *pathname,
+			  union acpi_operand_object *return_object,
+			  u32 expected_btypes, u32 package_index);
+
+static acpi_status
+acpi_ns_check_reference(char *pathname,
+			union acpi_operand_object *return_object);
+
+/*
+ * Names for the types that can be returned by the predefined objects.
+ * Used for warning messages. Must be in the same order as the ACPI_RTYPEs
+ */
+static const char *acpi_rtype_names[] = {
+	"/Integer",
+	"/String",
+	"/Buffer",
+	"/Package",
+	"/Reference",
+};
+
+#define ACPI_NOT_PACKAGE    ACPI_UINT32_MAX
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_check_predefined_names
+ *
+ * PARAMETERS:  Node            - Namespace node for the method/object
+ *              return_object   - Object returned from the evaluation of this
+ *                                method/object
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Check an ACPI name for a match in the predefined name list.
+ *
+ ******************************************************************************/
+
+acpi_status
+acpi_ns_check_predefined_names(struct acpi_namespace_node *node,
+			       union acpi_operand_object *return_object)
+{
+	acpi_status status = AE_OK;
+	const union acpi_predefined_info *predefined;
+	char *pathname;
+
+	/* Match the name for this method/object against the predefined list */
+
+	predefined = acpi_ns_check_for_predefined_name(node);
+	if (!predefined) {
+
+		/* Name was not one of the predefined names */
+
+		return (AE_OK);
+	}
+
+	/* Get the full pathname to the object, for use in error messages */
+
+	pathname = acpi_ns_get_external_pathname(node);
+	if (!pathname) {
+		pathname = ACPI_CAST_PTR(char, predefined->info.name);
+	}
+
+	/*
+	 * Check that the parameter count for this method is in accordance
+	 * with the ACPI specification.
+	 */
+	acpi_ns_check_parameter_count(pathname, node, predefined);
+
+	/*
+	 * If there is no return value, check if we require a return value for
+	 * this predefined name. Either one return value is expected, or none,
+	 * for both methods and other objects.
+	 *
+	 * Exit now if there is no return object. Warning if one was expected.
+	 */
+	if (!return_object) {
+		if ((predefined->info.expected_btypes) &&
+		    (!(predefined->info.expected_btypes & ACPI_RTYPE_NONE))) {
+			ACPI_ERROR((AE_INFO,
+				    "%s: Missing expected return value",
+				    pathname));
+
+			status = AE_AML_NO_RETURN_VALUE;
+		}
+		goto exit;
+	}
+
+	/*
+	 * We have a return value, but if one wasn't expected, just exit, this is
+	 * not a problem
+	 *
+	 * For example, if "Implicit return value" is enabled, methods will
+	 * always return a value
+	 */
+	if (!predefined->info.expected_btypes) {
+		goto exit;
+	}
+
+	/*
+	 * Check that the type of the return object is what is expected for
+	 * this predefined name
+	 */
+	status = acpi_ns_check_object_type(pathname, return_object,
+					   predefined->info.expected_btypes,
+					   ACPI_NOT_PACKAGE);
+	if (ACPI_FAILURE(status)) {
+		goto exit;
+	}
+
+	/* For returned Package objects, check the type of all sub-objects */
+
+	if (ACPI_GET_OBJECT_TYPE(return_object) == ACPI_TYPE_PACKAGE) {
+		status =
+		    acpi_ns_check_package(pathname, return_object, predefined);
+	}
+
+      exit:
+	if (pathname) {
+		ACPI_FREE(pathname);
+	}
+
+	return (status);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_check_parameter_count
+ *
+ * PARAMETERS:  Pathname        - Full pathname to the node (for error msgs)
+ *              Node            - Namespace node for the method/object
+ *              Predefined      - Pointer to entry in predefined name table
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Check that the declared (in ASL/AML) parameter count for a
+ *              predefined name is what is expected (i.e., what is defined in
+ *              the ACPI specification for this predefined name.)
+ *
+ ******************************************************************************/
+
+void
+acpi_ns_check_parameter_count(char *pathname,
+			      struct acpi_namespace_node *node,
+			      const union acpi_predefined_info *predefined)
+{
+	u32 param_count;
+	u32 required_params_current;
+	u32 required_params_old;
+
+	/*
+	 * Check that the ASL-defined parameter count is what is expected for
+	 * this predefined name.
+	 *
+	 * Methods have 0-7 parameters. All other types have zero.
+	 */
+	param_count = 0;
+	if (node->type == ACPI_TYPE_METHOD) {
+		param_count = node->object->method.param_count;
+	}
+
+	/* Validate parameter count - allow two different legal counts (_SCP) */
+
+	required_params_current = predefined->info.param_count & 0x0F;
+	required_params_old = predefined->info.param_count >> 4;
+
+	if ((param_count != required_params_current) &&
+	    (param_count != required_params_old)) {
+		ACPI_WARNING((AE_INFO,
+			      "%s: Parameter count mismatch - ASL declared %d, expected %d",
+			      pathname, param_count, required_params_current));
+	}
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_check_for_predefined_name
+ *
+ * PARAMETERS:  Node            - Namespace node for the method/object
+ *
+ * RETURN:      Pointer to entry in predefined table. NULL indicates not found.
+ *
+ * DESCRIPTION: Check an object name against the predefined object list.
+ *
+ ******************************************************************************/
+
+const union acpi_predefined_info *acpi_ns_check_for_predefined_name(struct
+								    acpi_namespace_node
+								    *node)
+{
+	const union acpi_predefined_info *this_name;
+
+	/* Quick check for a predefined name, first character must be underscore */
+
+	if (node->name.ascii[0] != '_') {
+		return (NULL);
+	}
+
+	/* Search info table for a predefined method/object name */
+
+	this_name = predefined_names;
+	while (this_name->info.name[0]) {
+		if (ACPI_COMPARE_NAME(node->name.ascii, this_name->info.name)) {
+
+			/* Return pointer to this table entry */
+
+			return (this_name);
+		}
+
+		/*
+		 * Skip next entry in the table if this name returns a Package
+		 * (next entry contains the package info)
+		 */
+		if (this_name->info.expected_btypes & ACPI_RTYPE_PACKAGE) {
+			this_name++;
+		}
+
+		this_name++;
+	}
+
+	return (NULL);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_check_package
+ *
+ * PARAMETERS:  Pathname        - Full pathname to the node (for error msgs)
+ *              return_object   - Object returned from the evaluation of a
+ *                                method or object
+ *              Predefined      - Pointer to entry in predefined name table
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Check a returned package object for the correct count and
+ *              correct type of all sub-objects.
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_ns_check_package(char *pathname,
+		      union acpi_operand_object *return_object,
+		      const union acpi_predefined_info *predefined)
+{
+	const union acpi_predefined_info *package;
+	union acpi_operand_object *sub_package;
+	union acpi_operand_object **elements;
+	union acpi_operand_object **sub_elements;
+	acpi_status status;
+	u32 expected_count;
+	u32 count;
+	u32 i;
+	u32 j;
+
+	ACPI_FUNCTION_NAME(ns_check_package);
+
+	/* The package info for this name is in the next table entry */
+
+	package = predefined + 1;
+
+	ACPI_DEBUG_PRINT((ACPI_DB_NAMES,
+			  "%s Validating return Package of Type %X, Count %X\n",
+			  pathname, package->ret_info.type,
+			  return_object->package.count));
+
+	/* Extract package count and elements array */
+
+	elements = return_object->package.elements;
+	count = return_object->package.count;
+
+	/* The package must have at least one element, else invalid */
+
+	if (!count) {
+		ACPI_WARNING((AE_INFO,
+			      "%s: Return Package has no elements (empty)",
+			      pathname));
+
+		return (AE_AML_OPERAND_VALUE);
+	}
+
+	/*
+	 * Decode the type of the expected package contents
+	 *
+	 * PTYPE1 packages contain no subpackages
+	 * PTYPE2 packages contain sub-packages
+	 */
+	switch (package->ret_info.type) {
+	case ACPI_PTYPE1_FIXED:
+
+		/*
+		 * The package count is fixed and there are no sub-packages
+		 *
+		 * If package is too small, exit.
+		 * If package is larger than expected, issue warning but continue
+		 */
+		expected_count =
+		    package->ret_info.count1 + package->ret_info.count2;
+		if (count < expected_count) {
+			goto package_too_small;
+		} else if (count > expected_count) {
+			ACPI_WARNING((AE_INFO,
+				      "%s: Return Package is larger than needed - "
+				      "found %u, expected %u", pathname, count,
+				      expected_count));
+		}
+
+		/* Validate all elements of the returned package */
+
+		status = acpi_ns_check_package_elements(pathname, elements,
+							package->ret_info.
+							object_type1,
+							package->ret_info.
+							count1,
+							package->ret_info.
+							object_type2,
+							package->ret_info.
+							count2);
+		if (ACPI_FAILURE(status)) {
+			return (status);
+		}
+		break;
+
+	case ACPI_PTYPE1_VAR:
+
+		/*
+		 * The package count is variable, there are no sub-packages, and all
+		 * elements must be of the same type
+		 */
+		for (i = 0; i < count; i++) {
+			status = acpi_ns_check_object_type(pathname, *elements,
+							   package->ret_info.
+							   object_type1, i);
+			if (ACPI_FAILURE(status)) {
+				return (status);
+			}
+			elements++;
+		}
+		break;
+
+	case ACPI_PTYPE1_OPTION:
+
+		/*
+		 * The package count is variable, there are no sub-packages. There are
+		 * a fixed number of required elements, and a variable number of
+		 * optional elements.
+		 *
+		 * Check if package is at least as large as the minimum required
+		 */
+		expected_count = package->ret_info3.count;
+		if (count < expected_count) {
+			goto package_too_small;
+		}
+
+		/* Variable number of sub-objects */
+
+		for (i = 0; i < count; i++) {
+			if (i < package->ret_info3.count) {
+
+				/* These are the required package elements (0, 1, or 2) */
+
+				status =
+				    acpi_ns_check_object_type(pathname,
+							      *elements,
+							      package->
+							      ret_info3.
+							      object_type[i],
+							      i);
+				if (ACPI_FAILURE(status)) {
+					return (status);
+				}
+			} else {
+				/* These are the optional package elements */
+
+				status =
+				    acpi_ns_check_object_type(pathname,
+							      *elements,
+							      package->
+							      ret_info3.
+							      tail_object_type,
+							      i);
+				if (ACPI_FAILURE(status)) {
+					return (status);
+				}
+			}
+			elements++;
+		}
+		break;
+
+	case ACPI_PTYPE2_PKG_COUNT:
+
+		/* First element is the (Integer) count of sub-packages to follow */
+
+		status = acpi_ns_check_object_type(pathname, *elements,
+						   ACPI_RTYPE_INTEGER, 0);
+		if (ACPI_FAILURE(status)) {
+			return (status);
+		}
+
+		/*
+		 * Count cannot be larger than the parent package length, but allow it
+		 * to be smaller. The >= accounts for the Integer above.
+		 */
+		expected_count = (u32) (*elements)->integer.value;
+		if (expected_count >= count) {
+			goto package_too_small;
+		}
+
+		count = expected_count;
+		elements++;
+
+		/* Now we can walk the sub-packages */
+
+		/*lint -fallthrough */
+
+	case ACPI_PTYPE2:
+	case ACPI_PTYPE2_FIXED:
+	case ACPI_PTYPE2_MIN:
+	case ACPI_PTYPE2_COUNT:
+
+		/*
+		 * These types all return a single package that consists of a variable
+		 * number of sub-packages
+		 */
+		for (i = 0; i < count; i++) {
+			sub_package = *elements;
+			sub_elements = sub_package->package.elements;
+
+			/* Each sub-object must be of type Package */
+
+			status =
+			    acpi_ns_check_object_type(pathname, sub_package,
+						      ACPI_RTYPE_PACKAGE, i);
+			if (ACPI_FAILURE(status)) {
+				return (status);
+			}
+
+			/* Examine the different types of sub-packages */
+
+			switch (package->ret_info.type) {
+			case ACPI_PTYPE2:
+			case ACPI_PTYPE2_PKG_COUNT:
+
+				/* Each subpackage has a fixed number of elements */
+
+				expected_count =
+				    package->ret_info.count1 +
+				    package->ret_info.count2;
+				if (sub_package->package.count !=
+				    expected_count) {
+					count = sub_package->package.count;
+					goto package_too_small;
+				}
+
+				status =
+				    acpi_ns_check_package_elements(pathname,
+								   sub_elements,
+								   package->
+								   ret_info.
+								   object_type1,
+								   package->
+								   ret_info.
+								   count1,
+								   package->
+								   ret_info.
+								   object_type2,
+								   package->
+								   ret_info.
+								   count2);
+				if (ACPI_FAILURE(status)) {
+					return (status);
+				}
+				break;
+
+			case ACPI_PTYPE2_FIXED:
+
+				/* Each sub-package has a fixed length */
+
+				expected_count = package->ret_info2.count;
+				if (sub_package->package.count < expected_count) {
+					count = sub_package->package.count;
+					goto package_too_small;
+				}
+
+				/* Check the type of each sub-package element */
+
+				for (j = 0; j < expected_count; j++) {
+					status =
+					    acpi_ns_check_object_type(pathname,
+								      sub_elements
+								      [j],
+								      package->
+								      ret_info2.
+								      object_type
+								      [j], j);
+					if (ACPI_FAILURE(status)) {
+						return (status);
+					}
+				}
+				break;
+
+			case ACPI_PTYPE2_MIN:
+
+				/* Each sub-package has a variable but minimum length */
+
+				expected_count = package->ret_info.count1;
+				if (sub_package->package.count < expected_count) {
+					count = sub_package->package.count;
+					goto package_too_small;
+				}
+
+				/* Check the type of each sub-package element */
+
+				status =
+				    acpi_ns_check_package_elements(pathname,
+								   sub_elements,
+								   package->
+								   ret_info.
+								   object_type1,
+								   sub_package->
+								   package.
+								   count, 0, 0);
+				if (ACPI_FAILURE(status)) {
+					return (status);
+				}
+				break;
+
+			case ACPI_PTYPE2_COUNT:
+
+				/* First element is the (Integer) count of elements to follow */
+
+				status =
+				    acpi_ns_check_object_type(pathname,
+							      *sub_elements,
+							      ACPI_RTYPE_INTEGER,
+							      0);
+				if (ACPI_FAILURE(status)) {
+					return (status);
+				}
+
+				/* Make sure package is large enough for the Count */
+
+				expected_count =
+				    (u32) (*sub_elements)->integer.value;
+				if (sub_package->package.count < expected_count) {
+					count = sub_package->package.count;
+					goto package_too_small;
+				}
+
+				/* Check the type of each sub-package element */
+
+				status =
+				    acpi_ns_check_package_elements(pathname,
+								   (sub_elements
+								    + 1),
+								   package->
+								   ret_info.
+								   object_type1,
+								   (expected_count
+								    - 1), 0, 0);
+				if (ACPI_FAILURE(status)) {
+					return (status);
+				}
+				break;
+
+			default:
+				break;
+			}
+
+			elements++;
+		}
+		break;
+
+	default:
+
+		/* Should not get here if predefined info table is correct */
+
+		ACPI_WARNING((AE_INFO,
+			      "%s: Invalid internal return type in table entry: %X",
+			      pathname, package->ret_info.type));
+
+		return (AE_AML_INTERNAL);
+	}
+
+	return (AE_OK);
+
+      package_too_small:
+
+	/* Error exit for the case with an incorrect package count */
+
+	ACPI_WARNING((AE_INFO, "%s: Return Package is too small - "
+		      "found %u, expected %u", pathname, count,
+		      expected_count));
+
+	return (AE_AML_OPERAND_VALUE);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_check_package_elements
+ *
+ * PARAMETERS:  Pathname        - Full pathname to the node (for error msgs)
+ *              Elements        - Pointer to the package elements array
+ *              Type1           - Object type for first group
+ *              Count1          - Count for first group
+ *              Type2           - Object type for second group
+ *              Count2          - Count for second group
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Check that all elements of a package are of the correct object
+ *              type. Supports up to two groups of different object types.
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_ns_check_package_elements(char *pathname,
+			       union acpi_operand_object **elements,
+			       u8 type1, u32 count1, u8 type2, u32 count2)
+{
+	union acpi_operand_object **this_element = elements;
+	acpi_status status;
+	u32 i;
+
+	/*
+	 * Up to two groups of package elements are supported by the data
+	 * structure. All elements in each group must be of the same type.
+	 * The second group can have a count of zero.
+	 */
+	for (i = 0; i < count1; i++) {
+		status = acpi_ns_check_object_type(pathname, *this_element,
+						   type1, i);
+		if (ACPI_FAILURE(status)) {
+			return (status);
+		}
+		this_element++;
+	}
+
+	for (i = 0; i < count2; i++) {
+		status = acpi_ns_check_object_type(pathname, *this_element,
+						   type2, (i + count1));
+		if (ACPI_FAILURE(status)) {
+			return (status);
+		}
+		this_element++;
+	}
+
+	return (AE_OK);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_check_object_type
+ *
+ * PARAMETERS:  Pathname        - Full pathname to the node (for error msgs)
+ *              return_object   - Object return from the execution of this
+ *                                method/object
+ *              expected_btypes - Bitmap of expected return type(s)
+ *              package_index   - Index of object within parent package (if
+ *                                applicable - ACPI_NOT_PACKAGE otherwise)
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Check the type of the return object against the expected object
+ *              type(s). Use of Btype allows multiple expected object types.
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_ns_check_object_type(char *pathname,
+			  union acpi_operand_object *return_object,
+			  u32 expected_btypes, u32 package_index)
+{
+	acpi_status status = AE_OK;
+	u32 return_btype;
+	char type_buffer[48];	/* Room for 5 types */
+	u32 this_rtype;
+	u32 i;
+	u32 j;
+
+	/*
+	 * If we get a NULL return_object here, it is a NULL package element,
+	 * and this is always an error.
+	 */
+	if (!return_object) {
+		goto type_error_exit;
+	}
+
+	/* A Namespace node should not get here, but make sure */
+
+	if (ACPI_GET_DESCRIPTOR_TYPE(return_object) == ACPI_DESC_TYPE_NAMED) {
+		ACPI_WARNING((AE_INFO,
+			      "%s: Invalid return type - Found a Namespace node [%4.4s] type %s",
+			      pathname, return_object->node.name.ascii,
+			      acpi_ut_get_type_name(return_object->node.type)));
+		return (AE_AML_OPERAND_TYPE);
+	}
+
+	/*
+	 * Convert the object type (ACPI_TYPE_xxx) to a bitmapped object type.
+	 * The bitmapped type allows multiple possible return types.
+	 *
+	 * Note, the cases below must handle all of the possible types returned
+	 * from all of the predefined names (including elements of returned
+	 * packages)
+	 */
+	switch (ACPI_GET_OBJECT_TYPE(return_object)) {
+	case ACPI_TYPE_INTEGER:
+		return_btype = ACPI_RTYPE_INTEGER;
+		break;
+
+	case ACPI_TYPE_BUFFER:
+		return_btype = ACPI_RTYPE_BUFFER;
+		break;
+
+	case ACPI_TYPE_STRING:
+		return_btype = ACPI_RTYPE_STRING;
+		break;
+
+	case ACPI_TYPE_PACKAGE:
+		return_btype = ACPI_RTYPE_PACKAGE;
+		break;
+
+	case ACPI_TYPE_LOCAL_REFERENCE:
+		return_btype = ACPI_RTYPE_REFERENCE;
+		break;
+
+	default:
+		/* Not one of the supported objects, must be incorrect */
+
+		goto type_error_exit;
+	}
+
+	/* Is the object one of the expected types? */
+
+	if (!(return_btype & expected_btypes)) {
+		goto type_error_exit;
+	}
+
+	/* For reference objects, check that the reference type is correct */
+
+	if (ACPI_GET_OBJECT_TYPE(return_object) == ACPI_TYPE_LOCAL_REFERENCE) {
+		status = acpi_ns_check_reference(pathname, return_object);
+	}
+
+	return (status);
+
+      type_error_exit:
+
+	/* Create a string with all expected types for this predefined object */
+
+	j = 1;
+	type_buffer[0] = 0;
+	this_rtype = ACPI_RTYPE_INTEGER;
+
+	for (i = 0; i < ACPI_NUM_RTYPES; i++) {
+
+		/* If one of the expected types, concatenate the name of this type */
+
+		if (expected_btypes & this_rtype) {
+			ACPI_STRCAT(type_buffer, &acpi_rtype_names[i][j]);
+			j = 0;	/* Use name separator from now on */
+		}
+		this_rtype <<= 1;	/* Next Rtype */
+	}
+
+	if (package_index == ACPI_NOT_PACKAGE) {
+		ACPI_WARNING((AE_INFO,
+			      "%s: Return type mismatch - found %s, expected %s",
+			      pathname,
+			      acpi_ut_get_object_type_name(return_object),
+			      type_buffer));
+	} else {
+		ACPI_WARNING((AE_INFO,
+			      "%s: Return Package type mismatch at index %u - "
+			      "found %s, expected %s", pathname, package_index,
+			      acpi_ut_get_object_type_name(return_object),
+			      type_buffer));
+	}
+
+	return (AE_AML_OPERAND_TYPE);
+}
+
+/*******************************************************************************
+ *
+ * FUNCTION:    acpi_ns_check_reference
+ *
+ * PARAMETERS:  Pathname        - Full pathname to the node (for error msgs)
+ *              return_object   - Object returned from the evaluation of a
+ *                                method or object
+ *
+ * RETURN:      Status
+ *
+ * DESCRIPTION: Check a returned reference object for the correct reference
+ *              type. The only reference type that can be returned from a
+ *              predefined method is a named reference. All others are invalid.
+ *
+ ******************************************************************************/
+
+static acpi_status
+acpi_ns_check_reference(char *pathname,
+			union acpi_operand_object *return_object)
+{
+
+	/*
+	 * Check the reference object for the correct reference type (opcode).
+	 * The only type of reference that can be converted to an union acpi_object is
+	 * a reference to a named object (reference class: NAME)
+	 */
+	if (return_object->reference.class == ACPI_REFCLASS_NAME) {
+		return (AE_OK);
+	}
+
+	ACPI_WARNING((AE_INFO,
+		      "%s: Return type mismatch - unexpected reference object type [%s] %2.2X",
+		      pathname, acpi_ut_get_reference_name(return_object),
+		      return_object->reference.class));
+
+	return (AE_AML_OPERAND_TYPE);
+}
diff --git a/include/acpi/acdebug.h b/include/acpi/acdebug.h
index a4fb001d96f1..62c59df3b86c 100644
--- a/include/acpi/acdebug.h
+++ b/include/acpi/acdebug.h
@@ -154,6 +154,10 @@ void
 acpi_db_display_argument_object(union acpi_operand_object *obj_desc,
 				struct acpi_walk_state *walk_state);
 
+void acpi_db_check_predefined_names(void);
+
+void acpi_db_batch_execute(void);
+
 /*
  * dbexec - debugger control method execution
  */
diff --git a/include/acpi/aclocal.h b/include/acpi/aclocal.h
index b221c8583ddd..ecab527cf78e 100644
--- a/include/acpi/aclocal.h
+++ b/include/acpi/aclocal.h
@@ -208,6 +208,7 @@ struct acpi_namespace_node {
 #define ANOBJ_METHOD_ARG                0x04	/* Node is a method argument */
 #define ANOBJ_METHOD_LOCAL              0x08	/* Node is a method local */
 #define ANOBJ_SUBTREE_HAS_INI           0x10	/* Used to optimize device initialization */
+#define ANOBJ_EVALUATED                 0x20	/* Set on first evaluation of node */
 
 #define ANOBJ_IS_EXTERNAL               0x08	/* i_aSL only: This object created via External() */
 #define ANOBJ_METHOD_NO_RETVAL          0x10	/* i_aSL only: Method has no return value */
@@ -340,6 +341,82 @@ acpi_status(*ACPI_INTERNAL_METHOD) (struct acpi_walk_state * walk_state);
 #define ACPI_BTYPE_OBJECTS_AND_REFS     0x0001FFFF	/* ARG or LOCAL */
 #define ACPI_BTYPE_ALL_OBJECTS          0x0000FFFF
 
+/*
+ * Information structure for ACPI predefined names.
+ * Each entry in the table contains the following items:
+ *
+ * Name                 - The ACPI reserved name
+ * param_count          - Number of arguments to the method
+ * expected_return_btypes - Allowed type(s) for the return value
+ */
+struct acpi_name_info {
+	char name[ACPI_NAME_SIZE];
+	u8 param_count;
+	u8 expected_btypes;
+};
+
+/*
+ * Secondary information structures for ACPI predefined objects that return
+ * package objects. This structure appears as the next entry in the table
+ * after the NAME_INFO structure above.
+ *
+ * The reason for this is to minimize the size of the predefined name table.
+ */
+
+/*
+ * Used for ACPI_PTYPE1_FIXED, ACPI_PTYPE1_VAR, ACPI_PTYPE2,
+ * ACPI_PTYPE2_MIN, ACPI_PTYPE2_PKG_COUNT, ACPI_PTYPE2_COUNT
+ */
+struct acpi_package_info {
+	u8 type;
+	u8 object_type1;
+	u8 count1;
+	u8 object_type2;
+	u8 count2;
+	u8 reserved;
+};
+
+/* Used for ACPI_PTYPE2_FIXED */
+
+struct acpi_package_info2 {
+	u8 type;
+	u8 count;
+	u8 object_type[4];
+};
+
+/* Used for ACPI_PTYPE1_OPTION */
+
+struct acpi_package_info3 {
+	u8 type;
+	u8 count;
+	u8 object_type[2];
+	u8 tail_object_type;
+	u8 reserved;
+};
+
+union acpi_predefined_info {
+	struct acpi_name_info info;
+	struct acpi_package_info ret_info;
+	struct acpi_package_info2 ret_info2;
+	struct acpi_package_info3 ret_info3;
+};
+
+/*
+ * Bitmapped return value types
+ * Note: the actual data types must be contiguous, a loop in nspredef.c
+ * depends on this.
+ */
+#define ACPI_RTYPE_ANY                  0x00
+#define ACPI_RTYPE_NONE                 0x01
+#define ACPI_RTYPE_INTEGER              0x02
+#define ACPI_RTYPE_STRING               0x04
+#define ACPI_RTYPE_BUFFER               0x08
+#define ACPI_RTYPE_PACKAGE              0x10
+#define ACPI_RTYPE_REFERENCE            0x20
+#define ACPI_RTYPE_ALL                  0x3F
+
+#define ACPI_NUM_RTYPES                 5	/* Number of actual object types */
+
 /*****************************************************************************
  *
  * Event typedefs and structs
diff --git a/include/acpi/acnamesp.h b/include/acpi/acnamesp.h
index c34008507b69..db4e6f677855 100644
--- a/include/acpi/acnamesp.h
+++ b/include/acpi/acnamesp.h
@@ -177,6 +177,22 @@ acpi_ns_dump_objects(acpi_object_type type,
  */
 acpi_status acpi_ns_evaluate(struct acpi_evaluate_info *info);
 
+/*
+ * nspredef - Support for predefined/reserved names
+ */
+acpi_status
+acpi_ns_check_predefined_names(struct acpi_namespace_node *node,
+			       union acpi_operand_object *return_object);
+
+const union acpi_predefined_info *acpi_ns_check_for_predefined_name(struct
+								    acpi_namespace_node
+								    *node);
+
+void
+acpi_ns_check_parameter_count(char *pathname,
+			      struct acpi_namespace_node *node,
+			      const union acpi_predefined_info *info);
+
 /*
  * nsnames - Name and Scope manipulation
  */
diff --git a/include/acpi/acpredef.h b/include/acpi/acpredef.h
new file mode 100644
index 000000000000..619fb75f8861
--- /dev/null
+++ b/include/acpi/acpredef.h
@@ -0,0 +1,371 @@
+/******************************************************************************
+ *
+ * Name: acpredef - Information table for ACPI predefined methods and objects
+ *              $Revision: 1.1 $
+ *
+ *****************************************************************************/
+
+/*
+ * Copyright (C) 2000 - 2008, Intel Corp.
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions, and the following disclaimer,
+ *    without modification.
+ * 2. Redistributions in binary form must reproduce at minimum a disclaimer
+ *    substantially similar to the "NO WARRANTY" disclaimer below
+ *    ("Disclaimer") and any redistribution must be conditioned upon
+ *    including a substantially similar Disclaimer requirement for further
+ *    binary redistribution.
+ * 3. Neither the names of the above-listed copyright holders nor the names
+ *    of any contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * NO WARRANTY
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * HOLDERS OR CONTRIBUTORS BE LIABLE FOR SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
+ * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING
+ * IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGES.
+ */
+
+#ifndef __ACPREDEF_H__
+#define __ACPREDEF_H__
+
+/******************************************************************************
+ *
+ * Return Package types
+ *
+ * 1) PTYPE1 packages do not contain sub-packages.
+ *
+ * ACPI_PTYPE1_FIXED: Fixed length, 1 or 2 object types:
+ *     object type
+ *     count
+ *     object type
+ *     count
+ *
+ * ACPI_PTYPE1_VAR: Variable length:
+ *    object type (Int/Buf/Ref)
+ *
+ * ACPI_PTYPE1_OPTION: Package has some required and some optional elements:
+ *      Used for _PRW
+ *
+ *
+ * 2) PTYPE2 packages contain a variable number of sub-packages. Each of the
+ *    different types describe the contents of each of the sub-packages.
+ *
+ * ACPI_PTYPE2: Each subpackage contains 1 or 2 object types:
+ *     object type
+ *     count
+ *     object type
+ *     count
+ *
+ * ACPI_PTYPE2_COUNT: Each subpackage has a count as first element:
+ *     object type
+ *
+ * ACPI_PTYPE2_PKG_COUNT: Count of subpackages at start, 1 or 2 object types:
+ *     object type
+ *     count
+ *     object type
+ *     count
+ *
+ * ACPI_PTYPE2_FIXED: Each subpackage is of fixed length:
+ *      Used for _PRT
+ *
+ * ACPI_PTYPE2_MIN: Each subpackage has a variable but minimum length
+ *      Used for _HPX
+ *
+ *****************************************************************************/
+
+enum acpi_return_package_types {
+	ACPI_PTYPE1_FIXED = 1,
+	ACPI_PTYPE1_VAR = 2,
+	ACPI_PTYPE1_OPTION = 3,
+	ACPI_PTYPE2 = 4,
+	ACPI_PTYPE2_COUNT = 5,
+	ACPI_PTYPE2_PKG_COUNT = 6,
+	ACPI_PTYPE2_FIXED = 7,
+	ACPI_PTYPE2_MIN = 8
+};
+
+/*
+ * Predefined method/object information table.
+ *
+ * These are the names that can actually be evaluated via acpi_evaluate_object.
+ * Not present in this table are the following:
+ *
+ *      1) Predefined/Reserved names that are never evaluated via acpi_evaluate_object:
+ *          _Lxx and _Exx GPE methods
+ *          _Qxx EC methods
+ *          _T_x compiler temporary variables
+ *
+ *      2) Predefined names that never actually exist within the AML code:
+ *          Predefined resource descriptor field names
+ *
+ *      3) Predefined names that are implemented within ACPICA:
+ *          _OSI
+ *
+ *      4) Some predefined names that are not documented within the ACPI spec.
+ *          _WDG, _WED
+ *
+ * The main entries in the table each contain the following items:
+ *
+ * Name                 - The ACPI reserved name
+ * param_count          - Number of arguments to the method
+ * expected_btypes      - Allowed type(s) for the return value.
+ *                        0 means that no return value is expected.
+ *
+ * For methods that return packages, the next entry in the table contains
+ * information about the expected structure of the package. This information
+ * is saved here (rather than in a separate table) in order to minimize the
+ * overall size of the stored data.
+ */
+static const union acpi_predefined_info predefined_names[] = {
+	{.info = {"_AC0", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_AC1", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_AC2", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_AC3", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_AC4", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_AC5", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_AC6", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_AC7", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_AC8", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_AC9", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_ADR", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_AL0", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_AL1", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_AL2", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_AL3", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_AL4", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_AL5", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_AL6", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_AL7", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_AL8", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_AL9", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_ALC", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_ALI", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_ALP", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_ALR", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE2, ACPI_RTYPE_INTEGER, 2, 0, 0, 0}},	/* variable (Pkgs) each 2 (Ints) */
+	{.info = {"_ALT", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_BBN", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_BCL", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER, 0, 0, 0, 0}},	/* variable (Ints) */
+	{.info = {"_BCM", 1, 0}},
+	{.info = {"_BDN", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_BFS", 1, 0}},
+	{.info = {"_BIF", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER,
+					  9,
+					  ACPI_RTYPE_STRING, 4, 0}},	/* fixed (9 Int),(4 Str) */
+	{.info = {"_BLT", 3, 0}},
+	{.info = {"_BMC", 1, 0}},
+	{.info = {"_BMD", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 5, 0, 0, 0}},	/* fixed (5 Int) */
+	{.info = {"_BQC", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_BST", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 4, 0, 0, 0}},	/* fixed (4 Int) */
+	{.info = {"_BTM", 1, ACPI_RTYPE_INTEGER}},
+	{.info = {"_BTP", 1, 0}},
+	{.info = {"_CBA", 0, ACPI_RTYPE_INTEGER}},	/* see PCI firmware spec 3.0 */
+	{.info = {"_CID", 0,
+	 ACPI_RTYPE_INTEGER | ACPI_RTYPE_STRING | ACPI_RTYPE_PACKAGE}},
+	{.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER | ACPI_RTYPE_STRING, 0, 0, 0, 0}},	/* variable (Ints/Strs) */
+	{.info = {"_CRS", 0, ACPI_RTYPE_BUFFER}},
+	{.info = {"_CRT", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_CSD", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE2_COUNT, ACPI_RTYPE_INTEGER, 0, 0, 0, 0}},	/* variable (1 Int(n), n-1 Int) */
+	{.info = {"_CST", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE2_PKG_COUNT,
+					  ACPI_RTYPE_BUFFER, 1,
+					  ACPI_RTYPE_INTEGER, 3, 0}},	/* variable (1 Int(n), n Pkg (1 Buf/3 Int) */
+	{.info = {"_DCK", 1, ACPI_RTYPE_INTEGER}},
+	{.info = {"_DCS", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_DDC", 1, ACPI_RTYPE_INTEGER | ACPI_RTYPE_BUFFER}},
+	{.info = {"_DDN", 0, ACPI_RTYPE_STRING}},
+	{.info = {"_DGS", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_DIS", 0, 0}},
+	{.info = {"_DMA", 0, ACPI_RTYPE_BUFFER}},
+	{.info = {"_DOD", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER, 0, 0, 0, 0}},	/* variable (Ints) */
+	{.info = {"_DOS", 1, 0}},
+	{.info = {"_DSM", 4, ACPI_RTYPE_ALL}},	/* Must return a type, but it can be of any type */
+	{.info = {"_DSS", 1, 0}},
+	{.info = {"_DSW", 3, 0}},
+	{.info = {"_EC_", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_EDL", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_EJ0", 1, 0}},
+	{.info = {"_EJ1", 1, 0}},
+	{.info = {"_EJ2", 1, 0}},
+	{.info = {"_EJ3", 1, 0}},
+	{.info = {"_EJ4", 1, 0}},
+	{.info = {"_EJD", 0, ACPI_RTYPE_STRING}},
+	{.info = {"_FDE", 0, ACPI_RTYPE_BUFFER}},
+	{.info = {"_FDI", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 16, 0, 0, 0}},	/* fixed (16 Int) */
+	{.info = {"_FDM", 1, 0}},
+	{.info = {"_FIX", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER, 0, 0, 0, 0}},	/* variable (Ints) */
+	{.info = {"_GLK", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_GPD", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_GPE", 0, ACPI_RTYPE_INTEGER}},	/* _GPE method, not _GPE scope */
+	{.info = {"_GSB", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_GTF", 0, ACPI_RTYPE_BUFFER}},
+	{.info = {"_GTM", 0, ACPI_RTYPE_BUFFER}},
+	{.info = {"_GTS", 1, 0}},
+	{.info = {"_HID", 0, ACPI_RTYPE_INTEGER | ACPI_RTYPE_STRING}},
+	{.info = {"_HOT", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_HPP", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 4, 0, 0, 0}},	/* fixed (4 Int) */
+
+	/*
+	 * For _HPX, a single package is returned, containing a variable number of sub-packages.
+	 * Each sub-package contains a PCI record setting. There are several different type of
+	 * record settings, of different lengths, but all elements of all settings are Integers.
+	 */
+	{.info = {"_HPX", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE2_MIN, ACPI_RTYPE_INTEGER, 5, 0, 0, 0}},	/* variable (Pkgs) each (var Ints) */
+	{.info = {"_IFT", 0, ACPI_RTYPE_INTEGER}},	/* see IPMI spec */
+	{.info = {"_INI", 0, 0}},
+	{.info = {"_IRC", 0, 0}},
+	{.info = {"_LCK", 1, 0}},
+	{.info = {"_LID", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_MAT", 0, ACPI_RTYPE_BUFFER}},
+	{.info = {"_MLS", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE2, ACPI_RTYPE_STRING, 2, 0, 0, 0}},	/* variable (Pkgs) each (2 Str) */
+	{.info = {"_MSG", 1, 0}},
+	{.info = {"_OFF", 0, 0}},
+	{.info = {"_ON_", 0, 0}},
+	{.info = {"_OS_", 0, ACPI_RTYPE_STRING}},
+	{.info = {"_OSC", 4, ACPI_RTYPE_BUFFER}},
+	{.info = {"_OST", 3, 0}},
+	{.info = {"_PCL", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_PCT", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_FIXED, ACPI_RTYPE_BUFFER, 2, 0, 0, 0}},	/* fixed (2 Buf) */
+	{.info = {"_PDC", 1, 0}},
+	{.info = {"_PIC", 1, 0}},
+	{.info = {"_PLD", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_BUFFER, 0, 0, 0, 0}},	/* variable (Bufs) */
+	{.info = {"_PPC", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_PPE", 0, ACPI_RTYPE_INTEGER}},	/* see dig64 spec */
+	{.info = {"_PR0", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_PR1", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_PR2", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_PRS", 0, ACPI_RTYPE_BUFFER}},
+
+	/*
+	 * For _PRT, many BIOSs reverse the 2nd and 3rd Package elements. This bug is so prevalent that there
+	 * is code in the ACPICA Resource Manager to detect this and switch them back. For now, do not allow
+	 * and issue a warning. To allow this and eliminate the warning, add the ACPI_RTYPE_REFERENCE
+	 * type to the 2nd element (index 1) in the statement below.
+	 */
+	{.info = {"_PRT", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE2_FIXED, 4,
+					  ACPI_RTYPE_INTEGER,
+					  ACPI_RTYPE_INTEGER,
+					  ACPI_RTYPE_INTEGER | ACPI_RTYPE_REFERENCE, ACPI_RTYPE_INTEGER}},	/* variable (Pkgs) each (4): Int,Int,Int/Ref,Int */
+
+	{.info = {"_PRW", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_OPTION, 2,
+					  ACPI_RTYPE_INTEGER |
+					  ACPI_RTYPE_PACKAGE,
+					  ACPI_RTYPE_INTEGER, ACPI_RTYPE_REFERENCE, 0}},	/* variable (Pkgs) each: Pkg/Int,Int,[variable Refs] (Pkg is Ref/Int) */
+
+	{.info = {"_PS0", 0, 0}},
+	{.info = {"_PS1", 0, 0}},
+	{.info = {"_PS2", 0, 0}},
+	{.info = {"_PS3", 0, 0}},
+	{.info = {"_PSC", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_PSD", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE2_COUNT, ACPI_RTYPE_INTEGER, 0, 0, 0, 0}},	/* variable (Pkgs) each (5 Int) with count */
+	{.info = {"_PSL", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_PSR", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_PSS", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE2, ACPI_RTYPE_INTEGER, 6, 0, 0, 0}},	/* variable (Pkgs) each (6 Int) */
+	{.info = {"_PSV", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_PSW", 1, 0}},
+	{.info = {"_PTC", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_FIXED, ACPI_RTYPE_BUFFER, 2, 0, 0, 0}},	/* fixed (2 Buf) */
+	{.info = {"_PTS", 1, 0}},
+	{.info = {"_PXM", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_REG", 2, 0}},
+	{.info = {"_REV", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_RMV", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_ROM", 2, ACPI_RTYPE_BUFFER}},
+	{.info = {"_RTV", 0, ACPI_RTYPE_INTEGER}},
+
+	/*
+	 * For _S0_ through _S5_, the ACPI spec defines a return Package containing 1 Integer,
+	 * but most DSDTs have it wrong - 2,3, or 4 integers. Allow this by making the objects "variable length",
+	 * but all elements must be Integers.
+	 */
+	{.info = {"_S0_", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER, 1, 0, 0, 0}},	/* fixed (1 Int) */
+	{.info = {"_S1_", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER, 1, 0, 0, 0}},	/* fixed (1 Int) */
+	{.info = {"_S2_", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER, 1, 0, 0, 0}},	/* fixed (1 Int) */
+	{.info = {"_S3_", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER, 1, 0, 0, 0}},	/* fixed (1 Int) */
+	{.info = {"_S4_", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER, 1, 0, 0, 0}},	/* fixed (1 Int) */
+	{.info = {"_S5_", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_INTEGER, 1, 0, 0, 0}},	/* fixed (1 Int) */
+
+	{.info = {"_S1D", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_S2D", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_S3D", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_S4D", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_S0W", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_S1W", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_S2W", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_S3W", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_S4W", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_SBS", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_SCP", 0x13, 0}},	/* Acpi 1.0 allowed 1 arg. Acpi 3.0 expanded to 3 args. Allow both. */
+	/* Note: the 3-arg definition may be removed for ACPI 4.0 */
+	{.info = {"_SDD", 1, 0}},
+	{.info = {"_SEG", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_SLI", 0, ACPI_RTYPE_BUFFER}},
+	{.info = {"_SPD", 1, ACPI_RTYPE_INTEGER}},
+	{.info = {"_SRS", 1, 0}},
+	{.info = {"_SRV", 0, ACPI_RTYPE_INTEGER}},	/* see IPMI spec */
+	{.info = {"_SST", 1, 0}},
+	{.info = {"_STA", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_STM", 3, 0}},
+	{.info = {"_STR", 0, ACPI_RTYPE_BUFFER}},
+	{.info = {"_SUN", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_SWS", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_TC1", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_TC2", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_TMP", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_TPC", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_TPT", 1, 0}},
+	{.info = {"_TRT", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE2, ACPI_RTYPE_REFERENCE, 2,
+					  ACPI_RTYPE_INTEGER, 6, 0}},	/* variable (Pkgs) each 2_ref/6_int */
+	{.info = {"_TSD", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE2_COUNT, ACPI_RTYPE_INTEGER, 5, 0, 0, 0}},	/* variable (Pkgs) each 5_int with count */
+	{.info = {"_TSP", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_TSS", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE2, ACPI_RTYPE_INTEGER, 5, 0, 0, 0}},	/* variable (Pkgs) each 5_int */
+	{.info = {"_TST", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_TTS", 1, 0}},
+	{.info = {"_TZD", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_VAR, ACPI_RTYPE_REFERENCE, 0, 0, 0, 0}},	/* variable (Refs) */
+	{.info = {"_TZM", 0, ACPI_RTYPE_REFERENCE}},
+	{.info = {"_TZP", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_UID", 0, ACPI_RTYPE_INTEGER | ACPI_RTYPE_STRING}},
+	{.info = {"_UPC", 0, ACPI_RTYPE_PACKAGE}}, {.ret_info = {ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 4, 0, 0, 0}},	/* fixed (4 Int) */
+	{.info = {"_UPD", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_UPP", 0, ACPI_RTYPE_INTEGER}},
+	{.info = {"_VPO", 0, ACPI_RTYPE_INTEGER}},
+
+	/* Acpi 1.0 defined _WAK with no return value. Later, it was changed to return a package */
+
+	{.info = {"_WAK", 1, ACPI_RTYPE_NONE | ACPI_RTYPE_PACKAGE}},
+	{.ret_info = {ACPI_PTYPE1_FIXED, ACPI_RTYPE_INTEGER, 2, 0, 0, 0}},	/* fixed (2 Int), but is optional */
+	{.ret_info = {0, 0, 0, 0, 0, 0}}	/* Table terminator */
+};
+
+#if 0
+	/* Not implemented */
+
+{
+"_WDG", 0, ACPI_RTYPE_BUFFER},	/* MS Extension */
+
+{
+"_WED", 1, ACPI_RTYPE_PACKAGE},	/* MS Extension */
+
+    /* This is an internally implemented control method, no need to check */
+{
+"_OSI", 1, ACPI_RTYPE_INTEGER},
+
+    /* TBD: */
+    _PRT - currently ignore reversed entries.attempt to fix here ?
+    think about code that attempts to fix package elements like _BIF, etc.
+#endif
+#endif
-- 
cgit v1.2.3


From ed37a71eac8ba375d85ab10ed5f5e8bdf1cd72e0 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Sat, 27 Sep 2008 13:39:20 +0800
Subject: ACPICA: Update version to 20080926

Update version to 20080926.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Signed-off-by: Len Brown <len.brown@intel.com>
---
 include/acpi/acconfig.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/acpi/acconfig.h b/include/acpi/acconfig.h
index 2b737e510b15..29feee27f0ea 100644
--- a/include/acpi/acconfig.h
+++ b/include/acpi/acconfig.h
@@ -63,7 +63,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20080829
+#define ACPI_CA_VERSION                 0x20080926
 
 /*
  * OS name, used for the _OS object.  The _OS object is essentially obsolete,
-- 
cgit v1.2.3


From 930cc144a043ff95e56b6888fa51c618b33f89e7 Mon Sep 17 00:00:00 2001
From: Kumar Gala <galak@kernel.crashing.org>
Date: Tue, 21 Oct 2008 22:19:00 -0700
Subject: math-emu: Fix signalling of underflow and inexact while packing
 result.

I'm trying to move the powerpc math-emu code to use the include/math-emu bits.

In doing so I've been using TestFloat to see how good or bad we are
doing.  For the most part the current math-emu code that PPC uses has
a number of issues that the code in include/math-emu seems to solve
(plus bugs we've had for ever that no one every realized).

Anyways, I've come across a case that we are flagging underflow and
inexact because we think we have a denormalized result from a double
precision divide:

000.FFFFFFFFFFFFF / 3FE.FFFFFFFFFFFFE
	soft: 001.0000000000000 .....  syst: 001.0000000000000 ...ux

What it looks like is the results out of FP_DIV_D are:

D:
sign:	  0
mantissa: 01000000 00000000
exp:	 -1023 (0)

The problem seems like we aren't normalizing the result and bumping the exp.

Now that I'm digging into this a bit I'm thinking my issue has to do with
the fix DaveM put in place from back in Aug 2007 (commit
405849610fd96b4f34cd1875c4c033228fea6c0f):

[MATH-EMU]: Fix underflow exception reporting.

    2) we ended up rounding back up to normal (this is the case where
       we set the exponent to 1 and set the fraction to zero), this
       should set inexact too
...

    Another example, "0x0.0000000000001p-1022 / 16.0", should signal both
    inexact and underflow.  The cpu implementations and ieee1754
    literature is very clear about this.  This is case #2 above.

Here is the distilled glibc test case from Jakub Jelinek which prompted that
commit:

--------------------
#include <float.h>
#include <fenv.h>
#include <stdio.h>

volatile double d = DBL_MIN;
volatile double e = 0x0.0000000000001p-1022;
volatile double f = 16.0;
int
main (void)
{
  printf ("%x\n", fetestexcept (FE_UNDERFLOW));
  d /= f;
  printf ("%x\n", fetestexcept (FE_UNDERFLOW));
  e /= f;
  printf ("%x\n", fetestexcept (FE_UNDERFLOW));
  return 0;
}
--------------------

It looks like the case I have we are exact before rounding, but think it
looks like the rounding case since it appears as if "overflow is set".

000.FFFFFFFFFFFFF / 3FE.FFFFFFFFFFFFE = 001.0000000000000

I think the following adds the check for my case and still works for the
issue your commit was trying to resolve.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/math-emu/op-common.h | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

(limited to 'include')

diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h
index cc1ec396f8d6..bc50aa0d6d73 100644
--- a/include/math-emu/op-common.h
+++ b/include/math-emu/op-common.h
@@ -139,18 +139,27 @@ do {								\
 	if (X##_e <= _FP_WFRACBITS_##fs)			\
 	  {							\
 	    _FP_FRAC_SRS_##wc(X, X##_e, _FP_WFRACBITS_##fs);	\
-	    _FP_ROUND(wc, X);					\
 	    if (_FP_FRAC_HIGH_##fs(X)				\
 		& (_FP_OVERFLOW_##fs >> 1))			\
 	      {							\
 	        X##_e = 1;					\
 	        _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);	\
-	        FP_SET_EXCEPTION(FP_EX_INEXACT);		\
 	      }							\
 	    else						\
 	      {							\
-		X##_e = 0;					\
-		_FP_FRAC_SRL_##wc(X, _FP_WORKBITS);		\
+		_FP_ROUND(wc, X);				\
+		if (_FP_FRAC_HIGH_##fs(X)			\
+		   & (_FP_OVERFLOW_##fs >> 1))			\
+		  {						\
+		    X##_e = 1;					\
+		    _FP_FRAC_SET_##wc(X, _FP_ZEROFRAC_##wc);	\
+		    FP_SET_EXCEPTION(FP_EX_INEXACT);		\
+		  }						\
+		else						\
+		  {						\
+		    X##_e = 0;					\
+		    _FP_FRAC_SRL_##wc(X, _FP_WORKBITS);		\
+		  }						\
 	      }							\
 	    if ((FP_CUR_EXCEPTIONS & FP_EX_INEXACT) ||		\
 		(FP_TRAPPING_EXCEPTIONS & FP_EX_UNDERFLOW))	\
-- 
cgit v1.2.3


From 60b8267338aafde5315fc65ff385f3d4d75eccfe Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 22 Oct 2008 22:09:59 -0700
Subject: math-emu: Fix thinko in _FP_DIV

In commit 48d6c64311ddb6417b901639530ccbc47bdc7635 ("math-emu: Add
support for reporting exact invalid exception") code was added to
set the new FP_EX_INVALID_{IDI,ZDZ} exception flag bits.

However there is a missing break statement for the
_FP_CLS_COMBINE(FP_CLS_INF,FP_CLS_INF) switch case, the
code just falls into _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_ZERO)
which then proceeds to overwrite all of the settings.

Fix by adding the missing break.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/math-emu/op-common.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include')

diff --git a/include/math-emu/op-common.h b/include/math-emu/op-common.h
index bc50aa0d6d73..f456534dcaf9 100644
--- a/include/math-emu/op-common.h
+++ b/include/math-emu/op-common.h
@@ -503,6 +503,8 @@ do {							\
     R##_c = FP_CLS_NAN;					\
     _FP_FRAC_SET_##wc(R, _FP_NANFRAC_##fs);		\
     FP_SET_EXCEPTION(FP_EX_INVALID | FP_EX_INVALID_IDI);\
+    break;						\
+							\
   case _FP_CLS_COMBINE(FP_CLS_ZERO,FP_CLS_ZERO):	\
     R##_s = _FP_NANSIGN_##fs;				\
     R##_c = FP_CLS_NAN;					\
-- 
cgit v1.2.3


From 8ede0bdb63305d3353efd97e9af6210afb05734e Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 17 Aug 2008 19:13:17 -0400
Subject: x86, um: initial part of asm-um move

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/um/Makefile                         |  17 +-
 arch/um/include/asm/a.out-core.h         |  27 +++
 arch/um/include/asm/a.out.h              |  11 +
 arch/um/include/asm/alternative-asm.h    |   6 +
 arch/um/include/asm/alternative.h        |   6 +
 arch/um/include/asm/apic.h               |   4 +
 arch/um/include/asm/archparam-i386.h     |  26 +++
 arch/um/include/asm/archparam-ppc.h      |   8 +
 arch/um/include/asm/archparam-x86_64.h   |  26 +++
 arch/um/include/asm/asm.h                |   6 +
 arch/um/include/asm/atomic.h             |  11 +
 arch/um/include/asm/auxvec.h             |   4 +
 arch/um/include/asm/bitops.h             |  10 +
 arch/um/include/asm/boot.h               |   6 +
 arch/um/include/asm/bug.h                |   6 +
 arch/um/include/asm/bugs.h               |   6 +
 arch/um/include/asm/byteorder.h          |   6 +
 arch/um/include/asm/cache.h              |  17 ++
 arch/um/include/asm/cacheflush.h         |   6 +
 arch/um/include/asm/calling.h            |   9 +
 arch/um/include/asm/checksum.h           |   6 +
 arch/um/include/asm/cmpxchg.h            |   6 +
 arch/um/include/asm/cobalt.h             |   6 +
 arch/um/include/asm/common.lds.S         | 130 +++++++++++
 arch/um/include/asm/cpufeature.h         |   6 +
 arch/um/include/asm/cputime.h            |   6 +
 arch/um/include/asm/current.h            |  13 ++
 arch/um/include/asm/delay.h              |  20 ++
 arch/um/include/asm/desc.h               |  16 ++
 arch/um/include/asm/device.h             |   7 +
 arch/um/include/asm/div64.h              |   6 +
 arch/um/include/asm/dma-mapping.h        | 128 +++++++++++
 arch/um/include/asm/dma.h                |  10 +
 arch/um/include/asm/dwarf2.h             |  11 +
 arch/um/include/asm/elf-i386.h           | 163 ++++++++++++++
 arch/um/include/asm/elf-ppc.h            |  53 +++++
 arch/um/include/asm/elf-x86_64.h         | 119 ++++++++++
 arch/um/include/asm/emergency-restart.h  |   6 +
 arch/um/include/asm/errno.h              |   6 +
 arch/um/include/asm/fcntl.h              |   6 +
 arch/um/include/asm/fixmap.h             |  98 +++++++++
 arch/um/include/asm/floppy.h             |   6 +
 arch/um/include/asm/frame.h              |   6 +
 arch/um/include/asm/futex.h              |   6 +
 arch/um/include/asm/hardirq.h            |  25 +++
 arch/um/include/asm/highmem.h            |  12 ++
 arch/um/include/asm/host_ldt-i386.h      |  34 +++
 arch/um/include/asm/host_ldt-x86_64.h    |  38 ++++
 arch/um/include/asm/hw_irq.h             |   7 +
 arch/um/include/asm/ide.h                |   6 +
 arch/um/include/asm/io.h                 |  57 +++++
 arch/um/include/asm/ioctl.h              |   6 +
 arch/um/include/asm/ioctls.h             |   6 +
 arch/um/include/asm/ipcbuf.h             |   6 +
 arch/um/include/asm/irq.h                |  23 ++
 arch/um/include/asm/irq_regs.h           |   1 +
 arch/um/include/asm/irq_vectors.h        |  20 ++
 arch/um/include/asm/irqflags.h           |   6 +
 arch/um/include/asm/kdebug.h             |   1 +
 arch/um/include/asm/kmap_types.h         |  29 +++
 arch/um/include/asm/ldt.h                |  37 ++++
 arch/um/include/asm/linkage.h            |   6 +
 arch/um/include/asm/local.h              |   6 +
 arch/um/include/asm/locks.h              |   6 +
 arch/um/include/asm/mca_dma.h            |   6 +
 arch/um/include/asm/mman.h               |   6 +
 arch/um/include/asm/mmu.h                |  22 ++
 arch/um/include/asm/mmu_context.h        |  54 +++++
 arch/um/include/asm/module-generic.h     |   6 +
 arch/um/include/asm/module-i386.h        |  13 ++
 arch/um/include/asm/module-x86_64.h      |  30 +++
 arch/um/include/asm/msgbuf.h             |   6 +
 arch/um/include/asm/mtrr.h               |   6 +
 arch/um/include/asm/mutex.h              |   9 +
 arch/um/include/asm/nops.h               |   6 +
 arch/um/include/asm/page.h               | 122 +++++++++++
 arch/um/include/asm/page_offset.h        |   1 +
 arch/um/include/asm/param.h              |  20 ++
 arch/um/include/asm/paravirt.h           |   6 +
 arch/um/include/asm/pci.h                |   7 +
 arch/um/include/asm/pda.h                |  31 +++
 arch/um/include/asm/percpu.h             |   6 +
 arch/um/include/asm/pgalloc.h            |  72 +++++++
 arch/um/include/asm/pgtable-2level.h     |  53 +++++
 arch/um/include/asm/pgtable-3level.h     | 146 +++++++++++++
 arch/um/include/asm/pgtable.h            | 358 +++++++++++++++++++++++++++++++
 arch/um/include/asm/poll.h               |   6 +
 arch/um/include/asm/posix_types.h        |   6 +
 arch/um/include/asm/prctl.h              |   6 +
 arch/um/include/asm/processor-generic.h  | 136 ++++++++++++
 arch/um/include/asm/processor-i386.h     |  78 +++++++
 arch/um/include/asm/processor-ppc.h      |  15 ++
 arch/um/include/asm/processor-x86_64.h   |  56 +++++
 arch/um/include/asm/ptrace-generic.h     |  55 +++++
 arch/um/include/asm/ptrace-i386.h        |  60 ++++++
 arch/um/include/asm/ptrace-x86_64.h      |  81 +++++++
 arch/um/include/asm/required-features.h  |   9 +
 arch/um/include/asm/resource.h           |   6 +
 arch/um/include/asm/rwlock.h             |   6 +
 arch/um/include/asm/rwsem.h              |   6 +
 arch/um/include/asm/scatterlist.h        |   6 +
 arch/um/include/asm/sections.h           |   7 +
 arch/um/include/asm/segment.h            |  10 +
 arch/um/include/asm/sembuf.h             |   6 +
 arch/um/include/asm/serial.h             |   6 +
 arch/um/include/asm/setup.h              |  10 +
 arch/um/include/asm/shmbuf.h             |   6 +
 arch/um/include/asm/shmparam.h           |   6 +
 arch/um/include/asm/sigcontext-generic.h |   6 +
 arch/um/include/asm/sigcontext-i386.h    |   6 +
 arch/um/include/asm/sigcontext-ppc.h     |  10 +
 arch/um/include/asm/sigcontext-x86_64.h  |  22 ++
 arch/um/include/asm/siginfo.h            |   6 +
 arch/um/include/asm/signal.h             |  29 +++
 arch/um/include/asm/smp.h                |  33 +++
 arch/um/include/asm/socket.h             |   6 +
 arch/um/include/asm/sockios.h            |   6 +
 arch/um/include/asm/spinlock.h           |   6 +
 arch/um/include/asm/spinlock_types.h     |   6 +
 arch/um/include/asm/stat.h               |   6 +
 arch/um/include/asm/statfs.h             |   6 +
 arch/um/include/asm/string.h             |   7 +
 arch/um/include/asm/suspend.h            |   4 +
 arch/um/include/asm/system-generic.h     |  47 ++++
 arch/um/include/asm/system-i386.h        |   6 +
 arch/um/include/asm/system-ppc.h         |  12 ++
 arch/um/include/asm/system-x86_64.h      |  23 ++
 arch/um/include/asm/termbits.h           |   6 +
 arch/um/include/asm/termios.h            |   6 +
 arch/um/include/asm/thread_info.h        |  83 +++++++
 arch/um/include/asm/timex.h              |  13 ++
 arch/um/include/asm/tlb.h                | 127 +++++++++++
 arch/um/include/asm/tlbflush.h           |  31 +++
 arch/um/include/asm/topology.h           |   6 +
 arch/um/include/asm/types.h              |   6 +
 arch/um/include/asm/uaccess.h            |  99 +++++++++
 arch/um/include/asm/ucontext.h           |   6 +
 arch/um/include/asm/unaligned.h          |   6 +
 arch/um/include/asm/unistd.h             |  41 ++++
 arch/um/include/asm/user.h               |   6 +
 arch/um/include/asm/vga.h                |   6 +
 arch/um/include/asm/vm-flags-i386.h      |  14 ++
 arch/um/include/asm/vm-flags-x86_64.h    |  33 +++
 arch/um/include/asm/vm86.h               |   6 +
 arch/um/include/asm/xor.h                |   6 +
 include/asm-um/a.out-core.h              |  27 ---
 include/asm-um/a.out.h                   |  11 -
 include/asm-um/alternative-asm.h         |   6 -
 include/asm-um/alternative.h             |   6 -
 include/asm-um/apic.h                    |   4 -
 include/asm-um/archparam-i386.h          |  26 ---
 include/asm-um/archparam-ppc.h           |   8 -
 include/asm-um/archparam-x86_64.h        |  26 ---
 include/asm-um/asm.h                     |   6 -
 include/asm-um/atomic.h                  |  11 -
 include/asm-um/auxvec.h                  |   4 -
 include/asm-um/bitops.h                  |  10 -
 include/asm-um/boot.h                    |   6 -
 include/asm-um/bug.h                     |   6 -
 include/asm-um/bugs.h                    |   6 -
 include/asm-um/byteorder.h               |   6 -
 include/asm-um/cache.h                   |  17 --
 include/asm-um/cacheflush.h              |   6 -
 include/asm-um/calling.h                 |   9 -
 include/asm-um/checksum.h                |   6 -
 include/asm-um/cmpxchg.h                 |   6 -
 include/asm-um/cobalt.h                  |   6 -
 include/asm-um/common.lds.S              | 130 -----------
 include/asm-um/cpufeature.h              |   6 -
 include/asm-um/cputime.h                 |   6 -
 include/asm-um/current.h                 |  13 --
 include/asm-um/delay.h                   |  20 --
 include/asm-um/desc.h                    |  16 --
 include/asm-um/device.h                  |   7 -
 include/asm-um/div64.h                   |   6 -
 include/asm-um/dma-mapping.h             | 128 -----------
 include/asm-um/dma.h                     |  10 -
 include/asm-um/dwarf2.h                  |  11 -
 include/asm-um/elf-i386.h                | 163 --------------
 include/asm-um/elf-ppc.h                 |  53 -----
 include/asm-um/elf-x86_64.h              | 119 ----------
 include/asm-um/emergency-restart.h       |   6 -
 include/asm-um/errno.h                   |   6 -
 include/asm-um/fcntl.h                   |   6 -
 include/asm-um/fixmap.h                  |  98 ---------
 include/asm-um/floppy.h                  |   6 -
 include/asm-um/frame.h                   |   6 -
 include/asm-um/futex.h                   |   6 -
 include/asm-um/hardirq.h                 |  25 ---
 include/asm-um/highmem.h                 |  12 --
 include/asm-um/host_ldt-i386.h           |  34 ---
 include/asm-um/host_ldt-x86_64.h         |  38 ----
 include/asm-um/hw_irq.h                  |   7 -
 include/asm-um/ide.h                     |   6 -
 include/asm-um/io.h                      |  57 -----
 include/asm-um/ioctl.h                   |   6 -
 include/asm-um/ioctls.h                  |   6 -
 include/asm-um/ipcbuf.h                  |   6 -
 include/asm-um/irq.h                     |  23 --
 include/asm-um/irq_regs.h                |   1 -
 include/asm-um/irq_vectors.h             |  20 --
 include/asm-um/irqflags.h                |   6 -
 include/asm-um/kdebug.h                  |   1 -
 include/asm-um/kmap_types.h              |  29 ---
 include/asm-um/ldt.h                     |  37 ----
 include/asm-um/linkage.h                 |   6 -
 include/asm-um/local.h                   |   6 -
 include/asm-um/locks.h                   |   6 -
 include/asm-um/mca_dma.h                 |   6 -
 include/asm-um/mman.h                    |   6 -
 include/asm-um/mmu.h                     |  22 --
 include/asm-um/mmu_context.h             |  54 -----
 include/asm-um/module-generic.h          |   6 -
 include/asm-um/module-i386.h             |  13 --
 include/asm-um/module-x86_64.h           |  30 ---
 include/asm-um/msgbuf.h                  |   6 -
 include/asm-um/mtrr.h                    |   6 -
 include/asm-um/mutex.h                   |   9 -
 include/asm-um/nops.h                    |   6 -
 include/asm-um/page.h                    | 122 -----------
 include/asm-um/page_offset.h             |   1 -
 include/asm-um/param.h                   |  20 --
 include/asm-um/paravirt.h                |   6 -
 include/asm-um/pci.h                     |   7 -
 include/asm-um/pda.h                     |  31 ---
 include/asm-um/percpu.h                  |   6 -
 include/asm-um/pgalloc.h                 |  72 -------
 include/asm-um/pgtable-2level.h          |  53 -----
 include/asm-um/pgtable-3level.h          | 146 -------------
 include/asm-um/pgtable.h                 | 358 -------------------------------
 include/asm-um/poll.h                    |   6 -
 include/asm-um/posix_types.h             |   6 -
 include/asm-um/prctl.h                   |   6 -
 include/asm-um/processor-generic.h       | 136 ------------
 include/asm-um/processor-i386.h          |  78 -------
 include/asm-um/processor-ppc.h           |  15 --
 include/asm-um/processor-x86_64.h        |  56 -----
 include/asm-um/ptrace-generic.h          |  55 -----
 include/asm-um/ptrace-i386.h             |  60 ------
 include/asm-um/ptrace-x86_64.h           |  81 -------
 include/asm-um/required-features.h       |   9 -
 include/asm-um/resource.h                |   6 -
 include/asm-um/rwlock.h                  |   6 -
 include/asm-um/rwsem.h                   |   6 -
 include/asm-um/scatterlist.h             |   6 -
 include/asm-um/sections.h                |   7 -
 include/asm-um/segment.h                 |  10 -
 include/asm-um/sembuf.h                  |   6 -
 include/asm-um/serial.h                  |   6 -
 include/asm-um/setup.h                   |  10 -
 include/asm-um/shmbuf.h                  |   6 -
 include/asm-um/shmparam.h                |   6 -
 include/asm-um/sigcontext-generic.h      |   6 -
 include/asm-um/sigcontext-i386.h         |   6 -
 include/asm-um/sigcontext-ppc.h          |  10 -
 include/asm-um/sigcontext-x86_64.h       |  22 --
 include/asm-um/siginfo.h                 |   6 -
 include/asm-um/signal.h                  |  29 ---
 include/asm-um/smp.h                     |  33 ---
 include/asm-um/socket.h                  |   6 -
 include/asm-um/sockios.h                 |   6 -
 include/asm-um/spinlock.h                |   6 -
 include/asm-um/spinlock_types.h          |   6 -
 include/asm-um/stat.h                    |   6 -
 include/asm-um/statfs.h                  |   6 -
 include/asm-um/string.h                  |   7 -
 include/asm-um/suspend.h                 |   4 -
 include/asm-um/system-generic.h          |  47 ----
 include/asm-um/system-i386.h             |   6 -
 include/asm-um/system-ppc.h              |  12 --
 include/asm-um/system-x86_64.h           |  23 --
 include/asm-um/termbits.h                |   6 -
 include/asm-um/termios.h                 |   6 -
 include/asm-um/thread_info.h             |  83 -------
 include/asm-um/timex.h                   |  13 --
 include/asm-um/tlb.h                     | 127 -----------
 include/asm-um/tlbflush.h                |  31 ---
 include/asm-um/topology.h                |   6 -
 include/asm-um/types.h                   |   6 -
 include/asm-um/uaccess.h                 |  99 ---------
 include/asm-um/ucontext.h                |   6 -
 include/asm-um/unaligned.h               |   6 -
 include/asm-um/unistd.h                  |  41 ----
 include/asm-um/user.h                    |   6 -
 include/asm-um/vga.h                     |   6 -
 include/asm-um/vm-flags-i386.h           |  14 --
 include/asm-um/vm-flags-x86_64.h         |  33 ---
 include/asm-um/vm86.h                    |   6 -
 include/asm-um/xor.h                     |   6 -
 289 files changed, 3699 insertions(+), 3698 deletions(-)
 create mode 100644 arch/um/include/asm/a.out-core.h
 create mode 100644 arch/um/include/asm/a.out.h
 create mode 100644 arch/um/include/asm/alternative-asm.h
 create mode 100644 arch/um/include/asm/alternative.h
 create mode 100644 arch/um/include/asm/apic.h
 create mode 100644 arch/um/include/asm/archparam-i386.h
 create mode 100644 arch/um/include/asm/archparam-ppc.h
 create mode 100644 arch/um/include/asm/archparam-x86_64.h
 create mode 100644 arch/um/include/asm/asm.h
 create mode 100644 arch/um/include/asm/atomic.h
 create mode 100644 arch/um/include/asm/auxvec.h
 create mode 100644 arch/um/include/asm/bitops.h
 create mode 100644 arch/um/include/asm/boot.h
 create mode 100644 arch/um/include/asm/bug.h
 create mode 100644 arch/um/include/asm/bugs.h
 create mode 100644 arch/um/include/asm/byteorder.h
 create mode 100644 arch/um/include/asm/cache.h
 create mode 100644 arch/um/include/asm/cacheflush.h
 create mode 100644 arch/um/include/asm/calling.h
 create mode 100644 arch/um/include/asm/checksum.h
 create mode 100644 arch/um/include/asm/cmpxchg.h
 create mode 100644 arch/um/include/asm/cobalt.h
 create mode 100644 arch/um/include/asm/common.lds.S
 create mode 100644 arch/um/include/asm/cpufeature.h
 create mode 100644 arch/um/include/asm/cputime.h
 create mode 100644 arch/um/include/asm/current.h
 create mode 100644 arch/um/include/asm/delay.h
 create mode 100644 arch/um/include/asm/desc.h
 create mode 100644 arch/um/include/asm/device.h
 create mode 100644 arch/um/include/asm/div64.h
 create mode 100644 arch/um/include/asm/dma-mapping.h
 create mode 100644 arch/um/include/asm/dma.h
 create mode 100644 arch/um/include/asm/dwarf2.h
 create mode 100644 arch/um/include/asm/elf-i386.h
 create mode 100644 arch/um/include/asm/elf-ppc.h
 create mode 100644 arch/um/include/asm/elf-x86_64.h
 create mode 100644 arch/um/include/asm/emergency-restart.h
 create mode 100644 arch/um/include/asm/errno.h
 create mode 100644 arch/um/include/asm/fcntl.h
 create mode 100644 arch/um/include/asm/fixmap.h
 create mode 100644 arch/um/include/asm/floppy.h
 create mode 100644 arch/um/include/asm/frame.h
 create mode 100644 arch/um/include/asm/futex.h
 create mode 100644 arch/um/include/asm/hardirq.h
 create mode 100644 arch/um/include/asm/highmem.h
 create mode 100644 arch/um/include/asm/host_ldt-i386.h
 create mode 100644 arch/um/include/asm/host_ldt-x86_64.h
 create mode 100644 arch/um/include/asm/hw_irq.h
 create mode 100644 arch/um/include/asm/ide.h
 create mode 100644 arch/um/include/asm/io.h
 create mode 100644 arch/um/include/asm/ioctl.h
 create mode 100644 arch/um/include/asm/ioctls.h
 create mode 100644 arch/um/include/asm/ipcbuf.h
 create mode 100644 arch/um/include/asm/irq.h
 create mode 100644 arch/um/include/asm/irq_regs.h
 create mode 100644 arch/um/include/asm/irq_vectors.h
 create mode 100644 arch/um/include/asm/irqflags.h
 create mode 100644 arch/um/include/asm/kdebug.h
 create mode 100644 arch/um/include/asm/kmap_types.h
 create mode 100644 arch/um/include/asm/ldt.h
 create mode 100644 arch/um/include/asm/linkage.h
 create mode 100644 arch/um/include/asm/local.h
 create mode 100644 arch/um/include/asm/locks.h
 create mode 100644 arch/um/include/asm/mca_dma.h
 create mode 100644 arch/um/include/asm/mman.h
 create mode 100644 arch/um/include/asm/mmu.h
 create mode 100644 arch/um/include/asm/mmu_context.h
 create mode 100644 arch/um/include/asm/module-generic.h
 create mode 100644 arch/um/include/asm/module-i386.h
 create mode 100644 arch/um/include/asm/module-x86_64.h
 create mode 100644 arch/um/include/asm/msgbuf.h
 create mode 100644 arch/um/include/asm/mtrr.h
 create mode 100644 arch/um/include/asm/mutex.h
 create mode 100644 arch/um/include/asm/nops.h
 create mode 100644 arch/um/include/asm/page.h
 create mode 100644 arch/um/include/asm/page_offset.h
 create mode 100644 arch/um/include/asm/param.h
 create mode 100644 arch/um/include/asm/paravirt.h
 create mode 100644 arch/um/include/asm/pci.h
 create mode 100644 arch/um/include/asm/pda.h
 create mode 100644 arch/um/include/asm/percpu.h
 create mode 100644 arch/um/include/asm/pgalloc.h
 create mode 100644 arch/um/include/asm/pgtable-2level.h
 create mode 100644 arch/um/include/asm/pgtable-3level.h
 create mode 100644 arch/um/include/asm/pgtable.h
 create mode 100644 arch/um/include/asm/poll.h
 create mode 100644 arch/um/include/asm/posix_types.h
 create mode 100644 arch/um/include/asm/prctl.h
 create mode 100644 arch/um/include/asm/processor-generic.h
 create mode 100644 arch/um/include/asm/processor-i386.h
 create mode 100644 arch/um/include/asm/processor-ppc.h
 create mode 100644 arch/um/include/asm/processor-x86_64.h
 create mode 100644 arch/um/include/asm/ptrace-generic.h
 create mode 100644 arch/um/include/asm/ptrace-i386.h
 create mode 100644 arch/um/include/asm/ptrace-x86_64.h
 create mode 100644 arch/um/include/asm/required-features.h
 create mode 100644 arch/um/include/asm/resource.h
 create mode 100644 arch/um/include/asm/rwlock.h
 create mode 100644 arch/um/include/asm/rwsem.h
 create mode 100644 arch/um/include/asm/scatterlist.h
 create mode 100644 arch/um/include/asm/sections.h
 create mode 100644 arch/um/include/asm/segment.h
 create mode 100644 arch/um/include/asm/sembuf.h
 create mode 100644 arch/um/include/asm/serial.h
 create mode 100644 arch/um/include/asm/setup.h
 create mode 100644 arch/um/include/asm/shmbuf.h
 create mode 100644 arch/um/include/asm/shmparam.h
 create mode 100644 arch/um/include/asm/sigcontext-generic.h
 create mode 100644 arch/um/include/asm/sigcontext-i386.h
 create mode 100644 arch/um/include/asm/sigcontext-ppc.h
 create mode 100644 arch/um/include/asm/sigcontext-x86_64.h
 create mode 100644 arch/um/include/asm/siginfo.h
 create mode 100644 arch/um/include/asm/signal.h
 create mode 100644 arch/um/include/asm/smp.h
 create mode 100644 arch/um/include/asm/socket.h
 create mode 100644 arch/um/include/asm/sockios.h
 create mode 100644 arch/um/include/asm/spinlock.h
 create mode 100644 arch/um/include/asm/spinlock_types.h
 create mode 100644 arch/um/include/asm/stat.h
 create mode 100644 arch/um/include/asm/statfs.h
 create mode 100644 arch/um/include/asm/string.h
 create mode 100644 arch/um/include/asm/suspend.h
 create mode 100644 arch/um/include/asm/system-generic.h
 create mode 100644 arch/um/include/asm/system-i386.h
 create mode 100644 arch/um/include/asm/system-ppc.h
 create mode 100644 arch/um/include/asm/system-x86_64.h
 create mode 100644 arch/um/include/asm/termbits.h
 create mode 100644 arch/um/include/asm/termios.h
 create mode 100644 arch/um/include/asm/thread_info.h
 create mode 100644 arch/um/include/asm/timex.h
 create mode 100644 arch/um/include/asm/tlb.h
 create mode 100644 arch/um/include/asm/tlbflush.h
 create mode 100644 arch/um/include/asm/topology.h
 create mode 100644 arch/um/include/asm/types.h
 create mode 100644 arch/um/include/asm/uaccess.h
 create mode 100644 arch/um/include/asm/ucontext.h
 create mode 100644 arch/um/include/asm/unaligned.h
 create mode 100644 arch/um/include/asm/unistd.h
 create mode 100644 arch/um/include/asm/user.h
 create mode 100644 arch/um/include/asm/vga.h
 create mode 100644 arch/um/include/asm/vm-flags-i386.h
 create mode 100644 arch/um/include/asm/vm-flags-x86_64.h
 create mode 100644 arch/um/include/asm/vm86.h
 create mode 100644 arch/um/include/asm/xor.h
 delete mode 100644 include/asm-um/a.out-core.h
 delete mode 100644 include/asm-um/a.out.h
 delete mode 100644 include/asm-um/alternative-asm.h
 delete mode 100644 include/asm-um/alternative.h
 delete mode 100644 include/asm-um/apic.h
 delete mode 100644 include/asm-um/archparam-i386.h
 delete mode 100644 include/asm-um/archparam-ppc.h
 delete mode 100644 include/asm-um/archparam-x86_64.h
 delete mode 100644 include/asm-um/asm.h
 delete mode 100644 include/asm-um/atomic.h
 delete mode 100644 include/asm-um/auxvec.h
 delete mode 100644 include/asm-um/bitops.h
 delete mode 100644 include/asm-um/boot.h
 delete mode 100644 include/asm-um/bug.h
 delete mode 100644 include/asm-um/bugs.h
 delete mode 100644 include/asm-um/byteorder.h
 delete mode 100644 include/asm-um/cache.h
 delete mode 100644 include/asm-um/cacheflush.h
 delete mode 100644 include/asm-um/calling.h
 delete mode 100644 include/asm-um/checksum.h
 delete mode 100644 include/asm-um/cmpxchg.h
 delete mode 100644 include/asm-um/cobalt.h
 delete mode 100644 include/asm-um/common.lds.S
 delete mode 100644 include/asm-um/cpufeature.h
 delete mode 100644 include/asm-um/cputime.h
 delete mode 100644 include/asm-um/current.h
 delete mode 100644 include/asm-um/delay.h
 delete mode 100644 include/asm-um/desc.h
 delete mode 100644 include/asm-um/device.h
 delete mode 100644 include/asm-um/div64.h
 delete mode 100644 include/asm-um/dma-mapping.h
 delete mode 100644 include/asm-um/dma.h
 delete mode 100644 include/asm-um/dwarf2.h
 delete mode 100644 include/asm-um/elf-i386.h
 delete mode 100644 include/asm-um/elf-ppc.h
 delete mode 100644 include/asm-um/elf-x86_64.h
 delete mode 100644 include/asm-um/emergency-restart.h
 delete mode 100644 include/asm-um/errno.h
 delete mode 100644 include/asm-um/fcntl.h
 delete mode 100644 include/asm-um/fixmap.h
 delete mode 100644 include/asm-um/floppy.h
 delete mode 100644 include/asm-um/frame.h
 delete mode 100644 include/asm-um/futex.h
 delete mode 100644 include/asm-um/hardirq.h
 delete mode 100644 include/asm-um/highmem.h
 delete mode 100644 include/asm-um/host_ldt-i386.h
 delete mode 100644 include/asm-um/host_ldt-x86_64.h
 delete mode 100644 include/asm-um/hw_irq.h
 delete mode 100644 include/asm-um/ide.h
 delete mode 100644 include/asm-um/io.h
 delete mode 100644 include/asm-um/ioctl.h
 delete mode 100644 include/asm-um/ioctls.h
 delete mode 100644 include/asm-um/ipcbuf.h
 delete mode 100644 include/asm-um/irq.h
 delete mode 100644 include/asm-um/irq_regs.h
 delete mode 100644 include/asm-um/irq_vectors.h
 delete mode 100644 include/asm-um/irqflags.h
 delete mode 100644 include/asm-um/kdebug.h
 delete mode 100644 include/asm-um/kmap_types.h
 delete mode 100644 include/asm-um/ldt.h
 delete mode 100644 include/asm-um/linkage.h
 delete mode 100644 include/asm-um/local.h
 delete mode 100644 include/asm-um/locks.h
 delete mode 100644 include/asm-um/mca_dma.h
 delete mode 100644 include/asm-um/mman.h
 delete mode 100644 include/asm-um/mmu.h
 delete mode 100644 include/asm-um/mmu_context.h
 delete mode 100644 include/asm-um/module-generic.h
 delete mode 100644 include/asm-um/module-i386.h
 delete mode 100644 include/asm-um/module-x86_64.h
 delete mode 100644 include/asm-um/msgbuf.h
 delete mode 100644 include/asm-um/mtrr.h
 delete mode 100644 include/asm-um/mutex.h
 delete mode 100644 include/asm-um/nops.h
 delete mode 100644 include/asm-um/page.h
 delete mode 100644 include/asm-um/page_offset.h
 delete mode 100644 include/asm-um/param.h
 delete mode 100644 include/asm-um/paravirt.h
 delete mode 100644 include/asm-um/pci.h
 delete mode 100644 include/asm-um/pda.h
 delete mode 100644 include/asm-um/percpu.h
 delete mode 100644 include/asm-um/pgalloc.h
 delete mode 100644 include/asm-um/pgtable-2level.h
 delete mode 100644 include/asm-um/pgtable-3level.h
 delete mode 100644 include/asm-um/pgtable.h
 delete mode 100644 include/asm-um/poll.h
 delete mode 100644 include/asm-um/posix_types.h
 delete mode 100644 include/asm-um/prctl.h
 delete mode 100644 include/asm-um/processor-generic.h
 delete mode 100644 include/asm-um/processor-i386.h
 delete mode 100644 include/asm-um/processor-ppc.h
 delete mode 100644 include/asm-um/processor-x86_64.h
 delete mode 100644 include/asm-um/ptrace-generic.h
 delete mode 100644 include/asm-um/ptrace-i386.h
 delete mode 100644 include/asm-um/ptrace-x86_64.h
 delete mode 100644 include/asm-um/required-features.h
 delete mode 100644 include/asm-um/resource.h
 delete mode 100644 include/asm-um/rwlock.h
 delete mode 100644 include/asm-um/rwsem.h
 delete mode 100644 include/asm-um/scatterlist.h
 delete mode 100644 include/asm-um/sections.h
 delete mode 100644 include/asm-um/segment.h
 delete mode 100644 include/asm-um/sembuf.h
 delete mode 100644 include/asm-um/serial.h
 delete mode 100644 include/asm-um/setup.h
 delete mode 100644 include/asm-um/shmbuf.h
 delete mode 100644 include/asm-um/shmparam.h
 delete mode 100644 include/asm-um/sigcontext-generic.h
 delete mode 100644 include/asm-um/sigcontext-i386.h
 delete mode 100644 include/asm-um/sigcontext-ppc.h
 delete mode 100644 include/asm-um/sigcontext-x86_64.h
 delete mode 100644 include/asm-um/siginfo.h
 delete mode 100644 include/asm-um/signal.h
 delete mode 100644 include/asm-um/smp.h
 delete mode 100644 include/asm-um/socket.h
 delete mode 100644 include/asm-um/sockios.h
 delete mode 100644 include/asm-um/spinlock.h
 delete mode 100644 include/asm-um/spinlock_types.h
 delete mode 100644 include/asm-um/stat.h
 delete mode 100644 include/asm-um/statfs.h
 delete mode 100644 include/asm-um/string.h
 delete mode 100644 include/asm-um/suspend.h
 delete mode 100644 include/asm-um/system-generic.h
 delete mode 100644 include/asm-um/system-i386.h
 delete mode 100644 include/asm-um/system-ppc.h
 delete mode 100644 include/asm-um/system-x86_64.h
 delete mode 100644 include/asm-um/termbits.h
 delete mode 100644 include/asm-um/termios.h
 delete mode 100644 include/asm-um/thread_info.h
 delete mode 100644 include/asm-um/timex.h
 delete mode 100644 include/asm-um/tlb.h
 delete mode 100644 include/asm-um/tlbflush.h
 delete mode 100644 include/asm-um/topology.h
 delete mode 100644 include/asm-um/types.h
 delete mode 100644 include/asm-um/uaccess.h
 delete mode 100644 include/asm-um/ucontext.h
 delete mode 100644 include/asm-um/unaligned.h
 delete mode 100644 include/asm-um/unistd.h
 delete mode 100644 include/asm-um/user.h
 delete mode 100644 include/asm-um/vga.h
 delete mode 100644 include/asm-um/vm-flags-i386.h
 delete mode 100644 include/asm-um/vm-flags-x86_64.h
 delete mode 100644 include/asm-um/vm86.h
 delete mode 100644 include/asm-um/xor.h

(limited to 'include')

diff --git a/arch/um/Makefile b/arch/um/Makefile
index 88c5b0a52777..94fb24ea5afa 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -21,14 +21,14 @@ core-y			+= $(ARCH_DIR)/kernel/		\
 # Have to precede the include because the included Makefiles reference them.
 SYMLINK_HEADERS := archparam.h system.h sigcontext.h processor.h ptrace.h \
 	module.h vm-flags.h elf.h host_ldt.h
-SYMLINK_HEADERS := $(foreach header,$(SYMLINK_HEADERS),include/asm-um/$(header))
+SYMLINK_HEADERS := $(foreach header,$(SYMLINK_HEADERS),$(ARCH_DIR)/include/asm/$(header))
 
 # XXX: The "os" symlink is only used by arch/um/include/os.h, which includes
 # ../os/include/file.h
 #
 # These are cleaned up during mrproper. Please DO NOT fix it again, this is
 # the Correct Thing(tm) to do!
-ARCH_SYMLINKS = include/asm-um/arch $(ARCH_DIR)/include/shared/sysdep $(ARCH_DIR)/os \
+ARCH_SYMLINKS = $(ARCH_DIR)/include/asm/arch $(ARCH_DIR)/include/shared/sysdep $(ARCH_DIR)/os \
 	$(SYMLINK_HEADERS) $(ARCH_DIR)/include/shared/uml-config.h
 
 MODE_INCLUDE	+= -I$(srctree)/$(ARCH_DIR)/include/shared/skas
@@ -38,6 +38,7 @@ include $(srctree)/$(ARCH_DIR)/Makefile-skas
 ARCH_INCLUDE	:= -I$(ARCH_DIR)/include/shared
 ifneq ($(KBUILD_SRC),)
 ARCH_INCLUDE	+= -I$(srctree)/$(ARCH_DIR)/include/shared
+KBUILD_CPPFLAGS += -I$(ARCH_DIR)/include # for arch symlink
 endif
 SYS_DIR		:= $(ARCH_DIR)/include/shared/sysdep-$(SUBARCH)
 
@@ -145,19 +146,19 @@ archclean:
 $(SYMLINK_HEADERS):
 	@echo '  SYMLINK $@'
 ifneq ($(KBUILD_SRC),)
-	$(Q)mkdir -p $(objtree)/include/asm-um
-	$(Q)ln -fsn $(srctree)/include/asm-um/$(basename $(notdir $@))-$(SUBARCH)$(suffix $@) $@
+	$(Q)mkdir -p $(objtree)/$(ARCH_DIR)/include/asm
+	$(Q)ln -fsn $(srctree)/$(ARCH_DIR)/include/asm/$(basename $(notdir $@))-$(SUBARCH)$(suffix $@) $@
 else
 	$(Q)ln -sf $(basename $(notdir $@))-$(SUBARCH)$(suffix $@) $@
 endif
 
-include/asm-um/arch:
+$(ARCH_DIR)/include/asm/arch:
 	@echo '  SYMLINK $@'
 ifneq ($(KBUILD_SRC),)
-	$(Q)mkdir -p $(objtree)/include/asm-um
+	$(Q)mkdir -p $(objtree)/$(ARCH_DIR)/include/asm
 	$(Q)ln -fsn $(srctree)/include/asm-$(HEADER_ARCH) $@
 else
-	$(Q)ln -fsn ../asm-$(HEADER_ARCH) $@
+	$(Q)ln -fsn ../../../../include/asm-$(HEADER_ARCH) $@
 endif
 
 $(objtree)/$(ARCH_DIR)/include/shared:
@@ -209,6 +210,6 @@ $(ARCH_DIR)/include/shared/user_constants.h: $(ARCH_DIR)/sys-$(SUBARCH)/user-off
 
 $(ARCH_DIR)/include/shared/kern_constants.h: $(objtree)/$(ARCH_DIR)/include/shared
 	@echo '  SYMLINK $@'
-	$(Q)ln -sf ../../../../include/asm-um/asm-offsets.h $@
+	$(Q)ln -sf ../../../../include/asm/asm-offsets.h $@
 
 export SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING OS HEADER_ARCH
diff --git a/arch/um/include/asm/a.out-core.h b/arch/um/include/asm/a.out-core.h
new file mode 100644
index 000000000000..995643b18309
--- /dev/null
+++ b/arch/um/include/asm/a.out-core.h
@@ -0,0 +1,27 @@
+/* a.out coredump register dumper
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef __UM_A_OUT_CORE_H
+#define __UM_A_OUT_CORE_H
+
+#ifdef __KERNEL__
+
+#include <linux/user.h>
+
+/*
+ * fill in the user structure for an a.out core dump
+ */
+static inline void aout_dump_thread(struct pt_regs *regs, struct user *u)
+{
+}
+
+#endif /* __KERNEL__ */
+#endif /* __UM_A_OUT_CORE_H */
diff --git a/arch/um/include/asm/a.out.h b/arch/um/include/asm/a.out.h
new file mode 100644
index 000000000000..754181ee8683
--- /dev/null
+++ b/arch/um/include/asm/a.out.h
@@ -0,0 +1,11 @@
+/*
+ * Copyright (C) 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_A_OUT_H
+#define __UM_A_OUT_H
+
+#include "asm/arch/a.out.h"
+
+#endif
diff --git a/arch/um/include/asm/alternative-asm.h b/arch/um/include/asm/alternative-asm.h
new file mode 100644
index 000000000000..9aa9fa2402a4
--- /dev/null
+++ b/arch/um/include/asm/alternative-asm.h
@@ -0,0 +1,6 @@
+#ifndef __UM_ALTERNATIVE_ASM_I
+#define __UM_ALTERNATIVE_ASM_I
+
+#include "asm/arch/alternative-asm.h"
+
+#endif
diff --git a/arch/um/include/asm/alternative.h b/arch/um/include/asm/alternative.h
new file mode 100644
index 000000000000..b6434396bd42
--- /dev/null
+++ b/arch/um/include/asm/alternative.h
@@ -0,0 +1,6 @@
+#ifndef __UM_ALTERNATIVE_H
+#define __UM_ALTERNATIVE_H
+
+#include "asm/arch/alternative.h"
+
+#endif
diff --git a/arch/um/include/asm/apic.h b/arch/um/include/asm/apic.h
new file mode 100644
index 000000000000..876dee84ab11
--- /dev/null
+++ b/arch/um/include/asm/apic.h
@@ -0,0 +1,4 @@
+#ifndef __UM_APIC_H
+#define __UM_APIC_H
+
+#endif
diff --git a/arch/um/include/asm/archparam-i386.h b/arch/um/include/asm/archparam-i386.h
new file mode 100644
index 000000000000..49e89b8d7e58
--- /dev/null
+++ b/arch/um/include/asm/archparam-i386.h
@@ -0,0 +1,26 @@
+/* 
+ * Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_ARCHPARAM_I386_H
+#define __UM_ARCHPARAM_I386_H
+
+/********* Nothing for asm-um/hardirq.h **********/
+
+/********* Nothing for asm-um/hw_irq.h **********/
+
+/********* Nothing for asm-um/string.h **********/
+
+#endif
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
diff --git a/arch/um/include/asm/archparam-ppc.h b/arch/um/include/asm/archparam-ppc.h
new file mode 100644
index 000000000000..4269d8a37b4f
--- /dev/null
+++ b/arch/um/include/asm/archparam-ppc.h
@@ -0,0 +1,8 @@
+#ifndef __UM_ARCHPARAM_PPC_H
+#define __UM_ARCHPARAM_PPC_H
+
+/********* Bits for asm-um/string.h **********/
+
+#define __HAVE_ARCH_STRRCHR
+
+#endif
diff --git a/arch/um/include/asm/archparam-x86_64.h b/arch/um/include/asm/archparam-x86_64.h
new file mode 100644
index 000000000000..270ed9586b68
--- /dev/null
+++ b/arch/um/include/asm/archparam-x86_64.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright 2003 PathScale, Inc.
+ *
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_ARCHPARAM_X86_64_H
+#define __UM_ARCHPARAM_X86_64_H
+
+
+/* No user-accessible fixmap addresses, i.e. vsyscall */
+#define FIXADDR_USER_START	0
+#define FIXADDR_USER_END	0
+
+#endif
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
diff --git a/arch/um/include/asm/asm.h b/arch/um/include/asm/asm.h
new file mode 100644
index 000000000000..af1269a1e9eb
--- /dev/null
+++ b/arch/um/include/asm/asm.h
@@ -0,0 +1,6 @@
+#ifndef __UM_ASM_H
+#define __UM_ASM_H
+
+#include "asm/arch/asm.h"
+
+#endif
diff --git a/arch/um/include/asm/atomic.h b/arch/um/include/asm/atomic.h
new file mode 100644
index 000000000000..b683f1034d1e
--- /dev/null
+++ b/arch/um/include/asm/atomic.h
@@ -0,0 +1,11 @@
+#ifndef __UM_ATOMIC_H
+#define __UM_ATOMIC_H
+
+/* The i386 atomic.h calls printk, but doesn't include kernel.h, so we
+ * include it here.
+ */
+#include "linux/kernel.h"
+
+#include "asm/arch/atomic.h"
+
+#endif
diff --git a/arch/um/include/asm/auxvec.h b/arch/um/include/asm/auxvec.h
new file mode 100644
index 000000000000..1e5e1c2fc9b1
--- /dev/null
+++ b/arch/um/include/asm/auxvec.h
@@ -0,0 +1,4 @@
+#ifndef __UM_AUXVEC_H
+#define __UM_AUXVEC_H
+
+#endif
diff --git a/arch/um/include/asm/bitops.h b/arch/um/include/asm/bitops.h
new file mode 100644
index 000000000000..e4d38d437b97
--- /dev/null
+++ b/arch/um/include/asm/bitops.h
@@ -0,0 +1,10 @@
+#ifndef __UM_BITOPS_H
+#define __UM_BITOPS_H
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include "asm/arch/bitops.h"
+
+#endif
diff --git a/arch/um/include/asm/boot.h b/arch/um/include/asm/boot.h
new file mode 100644
index 000000000000..09548c3e784e
--- /dev/null
+++ b/arch/um/include/asm/boot.h
@@ -0,0 +1,6 @@
+#ifndef __UM_BOOT_H
+#define __UM_BOOT_H
+
+#include "asm/arch/boot.h"
+
+#endif
diff --git a/arch/um/include/asm/bug.h b/arch/um/include/asm/bug.h
new file mode 100644
index 000000000000..9e33b864c359
--- /dev/null
+++ b/arch/um/include/asm/bug.h
@@ -0,0 +1,6 @@
+#ifndef __UM_BUG_H
+#define __UM_BUG_H
+
+#include <asm-generic/bug.h>
+
+#endif
diff --git a/arch/um/include/asm/bugs.h b/arch/um/include/asm/bugs.h
new file mode 100644
index 000000000000..6a72e240d5fc
--- /dev/null
+++ b/arch/um/include/asm/bugs.h
@@ -0,0 +1,6 @@
+#ifndef __UM_BUGS_H
+#define __UM_BUGS_H
+
+void check_bugs(void);
+
+#endif
diff --git a/arch/um/include/asm/byteorder.h b/arch/um/include/asm/byteorder.h
new file mode 100644
index 000000000000..eee0a834f447
--- /dev/null
+++ b/arch/um/include/asm/byteorder.h
@@ -0,0 +1,6 @@
+#ifndef __UM_BYTEORDER_H
+#define __UM_BYTEORDER_H
+
+#include "asm/arch/byteorder.h"
+
+#endif
diff --git a/arch/um/include/asm/cache.h b/arch/um/include/asm/cache.h
new file mode 100644
index 000000000000..19e1bdd67416
--- /dev/null
+++ b/arch/um/include/asm/cache.h
@@ -0,0 +1,17 @@
+#ifndef __UM_CACHE_H
+#define __UM_CACHE_H
+
+
+#if defined(CONFIG_UML_X86) && !defined(CONFIG_64BIT)
+# define L1_CACHE_SHIFT		(CONFIG_X86_L1_CACHE_SHIFT)
+#elif defined(CONFIG_UML_X86) /* 64-bit */
+# define L1_CACHE_SHIFT		6 /* Should be 7 on Intel */
+#else
+/* XXX: this was taken from x86, now it's completely random. Luckily only
+ * affects SMP padding. */
+# define L1_CACHE_SHIFT		5
+#endif
+
+#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
+
+#endif
diff --git a/arch/um/include/asm/cacheflush.h b/arch/um/include/asm/cacheflush.h
new file mode 100644
index 000000000000..12e9d4b74c8f
--- /dev/null
+++ b/arch/um/include/asm/cacheflush.h
@@ -0,0 +1,6 @@
+#ifndef __UM_CACHEFLUSH_H
+#define __UM_CACHEFLUSH_H
+
+#include "asm/arch/cacheflush.h"
+
+#endif
diff --git a/arch/um/include/asm/calling.h b/arch/um/include/asm/calling.h
new file mode 100644
index 000000000000..0b2384cc99fd
--- /dev/null
+++ b/arch/um/include/asm/calling.h
@@ -0,0 +1,9 @@
+# Copyright 2003 - 2004 Pathscale, Inc
+# Released under the GPL
+
+#ifndef __UM_CALLING_H /* XXX x86_64 */
+#define __UM_CALLING_H
+
+#include "asm/arch/calling.h"
+
+#endif
diff --git a/arch/um/include/asm/checksum.h b/arch/um/include/asm/checksum.h
new file mode 100644
index 000000000000..5b501361e361
--- /dev/null
+++ b/arch/um/include/asm/checksum.h
@@ -0,0 +1,6 @@
+#ifndef __UM_CHECKSUM_H
+#define __UM_CHECKSUM_H
+
+#include "sysdep/checksum.h"
+
+#endif
diff --git a/arch/um/include/asm/cmpxchg.h b/arch/um/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..529376a99885
--- /dev/null
+++ b/arch/um/include/asm/cmpxchg.h
@@ -0,0 +1,6 @@
+#ifndef __UM_CMPXCHG_H
+#define __UM_CMPXCHG_H
+
+#include "asm/arch/cmpxchg.h"
+
+#endif
diff --git a/arch/um/include/asm/cobalt.h b/arch/um/include/asm/cobalt.h
new file mode 100644
index 000000000000..f813a684be98
--- /dev/null
+++ b/arch/um/include/asm/cobalt.h
@@ -0,0 +1,6 @@
+#ifndef __UM_COBALT_H
+#define __UM_COBALT_H
+
+#include "asm/arch/cobalt.h"
+
+#endif
diff --git a/arch/um/include/asm/common.lds.S b/arch/um/include/asm/common.lds.S
new file mode 100644
index 000000000000..cb0248616d49
--- /dev/null
+++ b/arch/um/include/asm/common.lds.S
@@ -0,0 +1,130 @@
+#include <asm-generic/vmlinux.lds.h>
+
+  .fini      : { *(.fini)    } =0x9090
+  _etext = .;
+  PROVIDE (etext = .);
+
+  . = ALIGN(4096);
+  _sdata = .;
+  PROVIDE (sdata = .);
+
+  RODATA
+
+  .unprotected : { *(.unprotected) }
+  . = ALIGN(4096);
+  PROVIDE (_unprotected_end = .);
+
+  . = ALIGN(4096);
+  .note : { *(.note.*) }
+  __ex_table : {
+	__start___ex_table = .;
+	*(__ex_table)
+	__stop___ex_table = .;
+  }
+
+  BUG_TABLE
+
+  .uml.setup.init : {
+	__uml_setup_start = .;
+	*(.uml.setup.init)
+	__uml_setup_end = .;
+  }
+	
+  .uml.help.init : {
+	__uml_help_start = .;
+	*(.uml.help.init)
+	__uml_help_end = .;
+  }
+	
+  .uml.postsetup.init : {
+	__uml_postsetup_start = .;
+	*(.uml.postsetup.init)
+	__uml_postsetup_end = .;
+  }
+	
+  .init.setup : {
+	__setup_start = .;
+	*(.init.setup)
+	__setup_end = .;
+  }
+
+  . = ALIGN(32);
+  .data.percpu : {
+	__per_cpu_start = . ;
+	*(.data.percpu)
+	__per_cpu_end = . ;
+  }
+	
+  .initcall.init : {
+	__initcall_start = .;
+	INITCALLS
+	__initcall_end = .;
+  }
+
+  .con_initcall.init : {
+	__con_initcall_start = .;
+	*(.con_initcall.init)
+	__con_initcall_end = .;
+  }
+
+  .uml.initcall.init : {
+	__uml_initcall_start = .;
+	*(.uml.initcall.init)
+	__uml_initcall_end = .;
+  }
+  __init_end = .;
+
+  SECURITY_INIT
+
+  .exitcall : {
+	__exitcall_begin = .;
+	*(.exitcall.exit)
+	__exitcall_end = .;
+  }
+
+  .uml.exitcall : {
+	__uml_exitcall_begin = .;
+	*(.uml.exitcall.exit)
+	__uml_exitcall_end = .;
+  }
+
+  . = ALIGN(4);
+  .altinstructions : {
+	__alt_instructions = .;
+	*(.altinstructions)
+	__alt_instructions_end = .;
+  }
+  .altinstr_replacement : { *(.altinstr_replacement) }
+  /* .exit.text is discard at runtime, not link time, to deal with references
+     from .altinstructions and .eh_frame */
+  .exit.text : { *(.exit.text) }
+  .exit.data : { *(.exit.data) }
+
+  .preinit_array : {
+	__preinit_array_start = .;
+	*(.preinit_array)
+	__preinit_array_end = .;
+  }
+  .init_array : {
+	__init_array_start = .;
+	*(.init_array)
+	__init_array_end = .;
+  }
+  .fini_array : {
+	__fini_array_start = .;
+	*(.fini_array)
+	__fini_array_end = .;
+  }
+
+   . = ALIGN(4096);
+  .init.ramfs : {
+	__initramfs_start = .;
+	*(.init.ramfs)
+	__initramfs_end = .;
+  }
+
+  /* Sections to be discarded */
+  /DISCARD/ : {
+ 	*(.exitcall.exit)
+  }
+
diff --git a/arch/um/include/asm/cpufeature.h b/arch/um/include/asm/cpufeature.h
new file mode 100644
index 000000000000..fb7bd42a4d96
--- /dev/null
+++ b/arch/um/include/asm/cpufeature.h
@@ -0,0 +1,6 @@
+#ifndef __UM_CPUFEATURE_H
+#define __UM_CPUFEATURE_H
+
+#include "asm/arch/cpufeature.h"
+
+#endif
diff --git a/arch/um/include/asm/cputime.h b/arch/um/include/asm/cputime.h
new file mode 100644
index 000000000000..c84acbadfa2f
--- /dev/null
+++ b/arch/um/include/asm/cputime.h
@@ -0,0 +1,6 @@
+#ifndef __UM_CPUTIME_H
+#define __UM_CPUTIME_H
+
+#include <asm-generic/cputime.h>
+
+#endif /* __UM_CPUTIME_H */
diff --git a/arch/um/include/asm/current.h b/arch/um/include/asm/current.h
new file mode 100644
index 000000000000..c2191d9aa03d
--- /dev/null
+++ b/arch/um/include/asm/current.h
@@ -0,0 +1,13 @@
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_CURRENT_H
+#define __UM_CURRENT_H
+
+#include "linux/thread_info.h"
+
+#define current (current_thread_info()->task)
+
+#endif
diff --git a/arch/um/include/asm/delay.h b/arch/um/include/asm/delay.h
new file mode 100644
index 000000000000..c71e32b6741e
--- /dev/null
+++ b/arch/um/include/asm/delay.h
@@ -0,0 +1,20 @@
+#ifndef __UM_DELAY_H
+#define __UM_DELAY_H
+
+#define MILLION 1000000
+
+/* Undefined on purpose */
+extern void __bad_udelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __delay(unsigned long loops);
+
+#define udelay(n) ((__builtin_constant_p(n) && (n) > 20000) ? \
+	__bad_udelay() : __udelay(n))
+
+/* It appears that ndelay is not used at all for UML, and has never been
+ * implemented. */
+extern void __unimplemented_ndelay(void);
+#define ndelay(n) __unimplemented_ndelay()
+
+#endif
diff --git a/arch/um/include/asm/desc.h b/arch/um/include/asm/desc.h
new file mode 100644
index 000000000000..4ec34a51b62c
--- /dev/null
+++ b/arch/um/include/asm/desc.h
@@ -0,0 +1,16 @@
+#ifndef __UM_DESC_H
+#define __UM_DESC_H
+
+/* Taken from asm-i386/desc.h, it's the only thing we need. The rest wouldn't
+ * compile, and has never been used. */
+#define LDT_empty(info) (\
+	(info)->base_addr	== 0	&& \
+	(info)->limit		== 0	&& \
+	(info)->contents	== 0	&& \
+	(info)->read_exec_only	== 1	&& \
+	(info)->seg_32bit	== 0	&& \
+	(info)->limit_in_pages	== 0	&& \
+	(info)->seg_not_present	== 1	&& \
+	(info)->useable		== 0	)
+
+#endif
diff --git a/arch/um/include/asm/device.h b/arch/um/include/asm/device.h
new file mode 100644
index 000000000000..d8f9872b0e2d
--- /dev/null
+++ b/arch/um/include/asm/device.h
@@ -0,0 +1,7 @@
+/*
+ * Arch specific extensions to struct device
+ *
+ * This file is released under the GPLv2
+ */
+#include <asm-generic/device.h>
+
diff --git a/arch/um/include/asm/div64.h b/arch/um/include/asm/div64.h
new file mode 100644
index 000000000000..1e17f7409cab
--- /dev/null
+++ b/arch/um/include/asm/div64.h
@@ -0,0 +1,6 @@
+#ifndef _UM_DIV64_H
+#define _UM_DIV64_H
+
+#include "asm/arch/div64.h"
+
+#endif
diff --git a/arch/um/include/asm/dma-mapping.h b/arch/um/include/asm/dma-mapping.h
new file mode 100644
index 000000000000..90fc708b320e
--- /dev/null
+++ b/arch/um/include/asm/dma-mapping.h
@@ -0,0 +1,128 @@
+#ifndef _ASM_DMA_MAPPING_H
+#define _ASM_DMA_MAPPING_H
+
+#include <asm/scatterlist.h>
+
+static inline int
+dma_supported(struct device *dev, u64 mask)
+{
+	BUG();
+	return(0);
+}
+
+static inline int
+dma_set_mask(struct device *dev, u64 dma_mask)
+{
+	BUG();
+	return(0);
+}
+
+static inline void *
+dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		   gfp_t flag)
+{
+	BUG();
+	return((void *) 0);
+}
+
+static inline void
+dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
+		  dma_addr_t dma_handle)
+{
+	BUG();
+}
+
+static inline dma_addr_t
+dma_map_single(struct device *dev, void *cpu_addr, size_t size,
+	       enum dma_data_direction direction)
+{
+	BUG();
+	return(0);
+}
+
+static inline void
+dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
+		 enum dma_data_direction direction)
+{
+	BUG();
+}
+
+static inline dma_addr_t
+dma_map_page(struct device *dev, struct page *page,
+	     unsigned long offset, size_t size,
+	     enum dma_data_direction direction)
+{
+	BUG();
+	return(0);
+}
+
+static inline void
+dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
+	       enum dma_data_direction direction)
+{
+	BUG();
+}
+
+static inline int
+dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+	   enum dma_data_direction direction)
+{
+	BUG();
+	return(0);
+}
+
+static inline void
+dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
+	     enum dma_data_direction direction)
+{
+	BUG();
+}
+
+static inline void
+dma_sync_single(struct device *dev, dma_addr_t dma_handle, size_t size,
+		enum dma_data_direction direction)
+{
+	BUG();
+}
+
+static inline void
+dma_sync_sg(struct device *dev, struct scatterlist *sg, int nelems,
+	    enum dma_data_direction direction)
+{
+	BUG();
+}
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+#define dma_is_consistent(d, h) (1)
+
+static inline int
+dma_get_cache_alignment(void)
+{
+	BUG();
+	return(0);
+}
+
+static inline void
+dma_sync_single_range(struct device *dev, dma_addr_t dma_handle,
+		      unsigned long offset, size_t size,
+		      enum dma_data_direction direction)
+{
+	BUG();
+}
+
+static inline void
+dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+	       enum dma_data_direction direction)
+{
+	BUG();
+}
+
+static inline int
+dma_mapping_error(struct device *dev, dma_addr_t dma_handle)
+{
+	BUG();
+	return 0;
+}
+
+#endif
diff --git a/arch/um/include/asm/dma.h b/arch/um/include/asm/dma.h
new file mode 100644
index 000000000000..9f6139a8a525
--- /dev/null
+++ b/arch/um/include/asm/dma.h
@@ -0,0 +1,10 @@
+#ifndef __UM_DMA_H
+#define __UM_DMA_H
+
+#include "asm/io.h"
+
+extern unsigned long uml_physmem;
+
+#define MAX_DMA_ADDRESS (uml_physmem)
+
+#endif
diff --git a/arch/um/include/asm/dwarf2.h b/arch/um/include/asm/dwarf2.h
new file mode 100644
index 000000000000..d1a02e762931
--- /dev/null
+++ b/arch/um/include/asm/dwarf2.h
@@ -0,0 +1,11 @@
+/* Copyright 2003 - 2004 Pathscale, Inc
+ * Released under the GPL
+ */
+
+/* Needed on x86_64 by thunk.S */
+#ifndef __UM_DWARF2_H
+#define __UM_DWARF2_H
+
+#include "asm/arch/dwarf2.h"
+
+#endif
diff --git a/arch/um/include/asm/elf-i386.h b/arch/um/include/asm/elf-i386.h
new file mode 100644
index 000000000000..d0da9d7c5371
--- /dev/null
+++ b/arch/um/include/asm/elf-i386.h
@@ -0,0 +1,163 @@
+/*
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+#ifndef __UM_ELF_I386_H
+#define __UM_ELF_I386_H
+
+#include <asm/user.h>
+#include "skas.h"
+
+#define R_386_NONE	0
+#define R_386_32	1
+#define R_386_PC32	2
+#define R_386_GOT32	3
+#define R_386_PLT32	4
+#define R_386_COPY	5
+#define R_386_GLOB_DAT	6
+#define R_386_JMP_SLOT	7
+#define R_386_RELATIVE	8
+#define R_386_GOTOFF	9
+#define R_386_GOTPC	10
+#define R_386_NUM	11
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_i387_struct elf_fpregset_t;
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) \
+	(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
+
+#define ELF_CLASS	ELFCLASS32
+#define ELF_DATA        ELFDATA2LSB
+#define ELF_ARCH        EM_386
+
+#define ELF_PLAT_INIT(regs, load_addr) do { \
+	PT_REGS_EBX(regs) = 0; \
+	PT_REGS_ECX(regs) = 0; \
+	PT_REGS_EDX(regs) = 0; \
+	PT_REGS_ESI(regs) = 0; \
+	PT_REGS_EDI(regs) = 0; \
+	PT_REGS_EBP(regs) = 0; \
+	PT_REGS_EAX(regs) = 0; \
+} while (0)
+
+#define USE_ELF_CORE_DUMP
+#define ELF_EXEC_PAGESIZE 4096
+
+#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3)
+
+/* Shamelessly stolen from include/asm-i386/elf.h */
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs) do {	\
+	pr_reg[0] = PT_REGS_EBX(regs);		\
+	pr_reg[1] = PT_REGS_ECX(regs);		\
+	pr_reg[2] = PT_REGS_EDX(regs);		\
+	pr_reg[3] = PT_REGS_ESI(regs);		\
+	pr_reg[4] = PT_REGS_EDI(regs);		\
+	pr_reg[5] = PT_REGS_EBP(regs);		\
+	pr_reg[6] = PT_REGS_EAX(regs);		\
+	pr_reg[7] = PT_REGS_DS(regs);		\
+	pr_reg[8] = PT_REGS_ES(regs);		\
+	/* fake once used fs and gs selectors? */	\
+	pr_reg[9] = PT_REGS_DS(regs);		\
+	pr_reg[10] = PT_REGS_DS(regs);		\
+	pr_reg[11] = PT_REGS_SYSCALL_NR(regs);	\
+	pr_reg[12] = PT_REGS_IP(regs);		\
+	pr_reg[13] = PT_REGS_CS(regs);		\
+	pr_reg[14] = PT_REGS_EFLAGS(regs);	\
+	pr_reg[15] = PT_REGS_SP(regs);		\
+	pr_reg[16] = PT_REGS_SS(regs);		\
+} while (0);
+
+extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
+
+#define ELF_CORE_COPY_FPREGS(t, fpu) elf_core_copy_fpregs(t, fpu)
+
+extern long elf_aux_hwcap;
+#define ELF_HWCAP (elf_aux_hwcap)
+
+extern char * elf_aux_platform;
+#define ELF_PLATFORM (elf_aux_platform)
+
+#define SET_PERSONALITY(ex) do { } while (0)
+
+extern unsigned long vsyscall_ehdr;
+extern unsigned long vsyscall_end;
+extern unsigned long __kernel_vsyscall;
+
+#define VSYSCALL_BASE vsyscall_ehdr
+#define VSYSCALL_END vsyscall_end
+
+/*
+ * This is the range that is readable by user mode, and things
+ * acting like user mode such as get_user_pages.
+ */
+#define FIXADDR_USER_START      VSYSCALL_BASE
+#define FIXADDR_USER_END        VSYSCALL_END
+
+/*
+ * Architecture-neutral AT_ values in 0-17, leave some room
+ * for more of them, start the x86-specific ones at 32.
+ */
+#define AT_SYSINFO		32
+#define AT_SYSINFO_EHDR		33
+
+#define ARCH_DLINFO						\
+do {								\
+	if ( vsyscall_ehdr ) {					\
+		NEW_AUX_ENT(AT_SYSINFO,	__kernel_vsyscall);	\
+		NEW_AUX_ENT(AT_SYSINFO_EHDR, vsyscall_ehdr);	\
+	}							\
+} while (0)
+
+/*
+ * These macros parameterize elf_core_dump in fs/binfmt_elf.c to write out
+ * extra segments containing the vsyscall DSO contents.  Dumping its
+ * contents makes post-mortem fully interpretable later without matching up
+ * the same kernel and hardware config to see what PC values meant.
+ * Dumping its extra ELF program headers includes all the other information
+ * a debugger needs to easily find how the vsyscall DSO was being used.
+ */
+#define ELF_CORE_EXTRA_PHDRS						      \
+	(vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0 )
+
+#define ELF_CORE_WRITE_EXTRA_PHDRS					      \
+if ( vsyscall_ehdr ) {							      \
+	const struct elfhdr *const ehdrp = (struct elfhdr *)vsyscall_ehdr;    \
+	const struct elf_phdr *const phdrp =				      \
+		(const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff);   \
+	int i;								      \
+	Elf32_Off ofs = 0;						      \
+	for (i = 0; i < ehdrp->e_phnum; ++i) {				      \
+		struct elf_phdr phdr = phdrp[i];			      \
+		if (phdr.p_type == PT_LOAD) {				      \
+			ofs = phdr.p_offset = offset;			      \
+			offset += phdr.p_filesz;			      \
+		}							      \
+		else							      \
+			phdr.p_offset += ofs;				      \
+		phdr.p_paddr = 0; /* match other core phdrs */		      \
+		DUMP_WRITE(&phdr, sizeof(phdr));			      \
+	}								      \
+}
+#define ELF_CORE_WRITE_EXTRA_DATA					      \
+if ( vsyscall_ehdr ) {							      \
+	const struct elfhdr *const ehdrp = (struct elfhdr *)vsyscall_ehdr;    \
+	const struct elf_phdr *const phdrp =				      \
+		(const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff);   \
+	int i;								      \
+	for (i = 0; i < ehdrp->e_phnum; ++i) {				      \
+		if (phdrp[i].p_type == PT_LOAD)				      \
+			DUMP_WRITE((void *) phdrp[i].p_vaddr,		      \
+				   phdrp[i].p_filesz);			      \
+	}								      \
+}
+
+#endif
diff --git a/arch/um/include/asm/elf-ppc.h b/arch/um/include/asm/elf-ppc.h
new file mode 100644
index 000000000000..af9463cd8ce5
--- /dev/null
+++ b/arch/um/include/asm/elf-ppc.h
@@ -0,0 +1,53 @@
+#ifndef __UM_ELF_PPC_H
+#define __UM_ELF_PPC_H
+
+
+extern long elf_aux_hwcap;
+#define ELF_HWCAP (elf_aux_hwcap)
+
+#define SET_PERSONALITY(ex) do ; while(0)
+
+#define ELF_EXEC_PAGESIZE 4096
+
+#define elf_check_arch(x) (1)
+
+#ifdef CONFIG_64BIT
+#define ELF_CLASS ELFCLASS64
+#else
+#define ELF_CLASS ELFCLASS32
+#endif
+
+#define USE_ELF_CORE_DUMP
+
+#define R_386_NONE	0
+#define R_386_32	1
+#define R_386_PC32	2
+#define R_386_GOT32	3
+#define R_386_PLT32	4
+#define R_386_COPY	5
+#define R_386_GLOB_DAT	6
+#define R_386_JMP_SLOT	7
+#define R_386_RELATIVE	8
+#define R_386_GOTOFF	9
+#define R_386_GOTPC	10
+#define R_386_NUM	11
+
+#define ELF_PLATFORM (0)
+
+#define ELF_ET_DYN_BASE (0x08000000)
+
+/* the following stolen from asm-ppc/elf.h */
+#define ELF_NGREG	48	/* includes nip, msr, lr, etc. */
+#define ELF_NFPREG	33	/* includes fpscr */
+/* General registers */
+typedef unsigned long elf_greg_t;
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+/* Floating point registers */
+typedef double elf_fpreg_t;
+typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
+
+#define ELF_DATA        ELFDATA2MSB
+#define ELF_ARCH	EM_PPC
+
+#endif
diff --git a/arch/um/include/asm/elf-x86_64.h b/arch/um/include/asm/elf-x86_64.h
new file mode 100644
index 000000000000..6e8a9195e952
--- /dev/null
+++ b/arch/um/include/asm/elf-x86_64.h
@@ -0,0 +1,119 @@
+/*
+ * Copyright 2003 PathScale, Inc.
+ * Copyright (C) 2003 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ *
+ * Licensed under the GPL
+ */
+#ifndef __UM_ELF_X86_64_H
+#define __UM_ELF_X86_64_H
+
+#include <asm/user.h>
+#include "skas.h"
+
+/* x86-64 relocation types, taken from asm-x86_64/elf.h */
+#define R_X86_64_NONE		0	/* No reloc */
+#define R_X86_64_64		1	/* Direct 64 bit  */
+#define R_X86_64_PC32		2	/* PC relative 32 bit signed */
+#define R_X86_64_GOT32		3	/* 32 bit GOT entry */
+#define R_X86_64_PLT32		4	/* 32 bit PLT address */
+#define R_X86_64_COPY		5	/* Copy symbol at runtime */
+#define R_X86_64_GLOB_DAT	6	/* Create GOT entry */
+#define R_X86_64_JUMP_SLOT	7	/* Create PLT entry */
+#define R_X86_64_RELATIVE	8	/* Adjust by program base */
+#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative
+					   offset to GOT */
+#define R_X86_64_32		10	/* Direct 32 bit zero extended */
+#define R_X86_64_32S		11	/* Direct 32 bit sign extended */
+#define R_X86_64_16		12	/* Direct 16 bit zero extended */
+#define R_X86_64_PC16		13	/* 16 bit sign extended pc relative */
+#define R_X86_64_8		14	/* Direct 8 bit sign extended  */
+#define R_X86_64_PC8		15	/* 8 bit sign extended pc relative */
+
+#define R_X86_64_NUM		16
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_i387_struct elf_fpregset_t;
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) \
+	((x)->e_machine == EM_X86_64)
+
+#define ELF_CLASS	ELFCLASS64
+#define ELF_DATA        ELFDATA2LSB
+#define ELF_ARCH        EM_X86_64
+
+#define ELF_PLAT_INIT(regs, load_addr)    do { \
+	PT_REGS_RBX(regs) = 0; \
+	PT_REGS_RCX(regs) = 0; \
+	PT_REGS_RDX(regs) = 0; \
+	PT_REGS_RSI(regs) = 0; \
+	PT_REGS_RDI(regs) = 0; \
+	PT_REGS_RBP(regs) = 0; \
+	PT_REGS_RAX(regs) = 0; \
+	PT_REGS_R8(regs) = 0; \
+	PT_REGS_R9(regs) = 0; \
+	PT_REGS_R10(regs) = 0; \
+	PT_REGS_R11(regs) = 0; \
+	PT_REGS_R12(regs) = 0; \
+	PT_REGS_R13(regs) = 0; \
+	PT_REGS_R14(regs) = 0; \
+	PT_REGS_R15(regs) = 0; \
+} while (0)
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs)		\
+	(pr_reg)[0] = (regs)->regs.gp[0];			\
+	(pr_reg)[1] = (regs)->regs.gp[1];			\
+	(pr_reg)[2] = (regs)->regs.gp[2];			\
+	(pr_reg)[3] = (regs)->regs.gp[3];			\
+	(pr_reg)[4] = (regs)->regs.gp[4];			\
+	(pr_reg)[5] = (regs)->regs.gp[5];			\
+	(pr_reg)[6] = (regs)->regs.gp[6];			\
+	(pr_reg)[7] = (regs)->regs.gp[7];			\
+	(pr_reg)[8] = (regs)->regs.gp[8];			\
+	(pr_reg)[9] = (regs)->regs.gp[9];			\
+	(pr_reg)[10] = (regs)->regs.gp[10];			\
+	(pr_reg)[11] = (regs)->regs.gp[11];			\
+	(pr_reg)[12] = (regs)->regs.gp[12];			\
+	(pr_reg)[13] = (regs)->regs.gp[13];			\
+	(pr_reg)[14] = (regs)->regs.gp[14];			\
+	(pr_reg)[15] = (regs)->regs.gp[15];			\
+	(pr_reg)[16] = (regs)->regs.gp[16];			\
+	(pr_reg)[17] = (regs)->regs.gp[17];			\
+	(pr_reg)[18] = (regs)->regs.gp[18];			\
+	(pr_reg)[19] = (regs)->regs.gp[19];			\
+	(pr_reg)[20] = (regs)->regs.gp[20];			\
+	(pr_reg)[21] = current->thread.arch.fs;			\
+	(pr_reg)[22] = 0;					\
+	(pr_reg)[23] = 0;					\
+	(pr_reg)[24] = 0;					\
+	(pr_reg)[25] = 0;					\
+	(pr_reg)[26] = 0;
+
+extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
+
+#define ELF_CORE_COPY_FPREGS(t, fpu) elf_core_copy_fpregs(t, fpu)
+
+#ifdef TIF_IA32 /* XXX */
+#error XXX, indeed
+        clear_thread_flag(TIF_IA32);
+#endif
+
+#define USE_ELF_CORE_DUMP
+#define ELF_EXEC_PAGESIZE 4096
+
+#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3)
+
+extern long elf_aux_hwcap;
+#define ELF_HWCAP (elf_aux_hwcap)
+
+#define ELF_PLATFORM "x86_64"
+
+#define SET_PERSONALITY(ex) do ; while(0)
+
+#endif
diff --git a/arch/um/include/asm/emergency-restart.h b/arch/um/include/asm/emergency-restart.h
new file mode 100644
index 000000000000..108d8c48e42e
--- /dev/null
+++ b/arch/um/include/asm/emergency-restart.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_EMERGENCY_RESTART_H
+#define _ASM_EMERGENCY_RESTART_H
+
+#include <asm-generic/emergency-restart.h>
+
+#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/arch/um/include/asm/errno.h b/arch/um/include/asm/errno.h
new file mode 100644
index 000000000000..b7a9e37fd8d8
--- /dev/null
+++ b/arch/um/include/asm/errno.h
@@ -0,0 +1,6 @@
+#ifndef __UM_ERRNO_H
+#define __UM_ERRNO_H
+
+#include "asm/arch/errno.h"
+
+#endif
diff --git a/arch/um/include/asm/fcntl.h b/arch/um/include/asm/fcntl.h
new file mode 100644
index 000000000000..812a65446d92
--- /dev/null
+++ b/arch/um/include/asm/fcntl.h
@@ -0,0 +1,6 @@
+#ifndef __UM_FCNTL_H
+#define __UM_FCNTL_H
+
+#include "asm/arch/fcntl.h"
+
+#endif
diff --git a/arch/um/include/asm/fixmap.h b/arch/um/include/asm/fixmap.h
new file mode 100644
index 000000000000..9d2be52b8655
--- /dev/null
+++ b/arch/um/include/asm/fixmap.h
@@ -0,0 +1,98 @@
+#ifndef __UM_FIXMAP_H
+#define __UM_FIXMAP_H
+
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/kmap_types.h>
+#include <asm/archparam.h>
+#include <asm/page.h>
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process. We allocate these special  addresses
+ * from the end of virtual memory (0xfffff000) backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * these 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages. (or larger if used with an increment
+ * highger than 1) use fixmap_set(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+
+/*
+ * on UP currently we will have no trace of the fixmap mechanizm,
+ * no page table allocations, etc. This might change in the
+ * future, say framebuffers for the console driver(s) could be
+ * fix-mapped?
+ */
+enum fixed_addresses {
+#ifdef CONFIG_HIGHMEM
+	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
+	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
+#endif
+	__end_of_fixed_addresses
+};
+
+extern void __set_fixmap (enum fixed_addresses idx,
+			  unsigned long phys, pgprot_t flags);
+
+#define set_fixmap(idx, phys) \
+		__set_fixmap(idx, phys, PAGE_KERNEL)
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys) \
+		__set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
+/*
+ * used by vmalloc.c.
+ *
+ * Leave one empty page between vmalloc'ed areas and
+ * the start of the fixmap, and leave one page empty
+ * at the top of mem..
+ */
+
+#define FIXADDR_TOP	(TASK_SIZE - 2 * PAGE_SIZE)
+#define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
+
+#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x)      ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
+
+extern void __this_fixmap_does_not_exist(void);
+
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without tranlation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static inline unsigned long fix_to_virt(const unsigned int idx)
+{
+	/*
+	 * this branch gets completely eliminated after inlining,
+	 * except when someone tries to use fixaddr indices in an
+	 * illegal way. (such as mixing up address types or using
+	 * out-of-range indices).
+	 *
+	 * If it doesn't get removed, the linker will complain
+	 * loudly with a reasonably clear error message..
+	 */
+	if (idx >= __end_of_fixed_addresses)
+		__this_fixmap_does_not_exist();
+
+        return __fix_to_virt(idx);
+}
+
+static inline unsigned long virt_to_fix(const unsigned long vaddr)
+{
+      BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
+      return __virt_to_fix(vaddr);
+}
+
+#endif
diff --git a/arch/um/include/asm/floppy.h b/arch/um/include/asm/floppy.h
new file mode 100644
index 000000000000..453e7415fb6f
--- /dev/null
+++ b/arch/um/include/asm/floppy.h
@@ -0,0 +1,6 @@
+#ifndef __UM_FLOPPY_H
+#define __UM_FLOPPY_H
+
+#include "asm/arch/floppy.h"
+
+#endif
diff --git a/arch/um/include/asm/frame.h b/arch/um/include/asm/frame.h
new file mode 100644
index 000000000000..8a8c1cb415b4
--- /dev/null
+++ b/arch/um/include/asm/frame.h
@@ -0,0 +1,6 @@
+#ifndef __UM_FRAME_I
+#define __UM_FRAME_I
+
+#include "asm/arch/frame.h"
+
+#endif
diff --git a/arch/um/include/asm/futex.h b/arch/um/include/asm/futex.h
new file mode 100644
index 000000000000..6a332a9f099c
--- /dev/null
+++ b/arch/um/include/asm/futex.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_FUTEX_H
+#define _ASM_FUTEX_H
+
+#include <asm-generic/futex.h>
+
+#endif
diff --git a/arch/um/include/asm/hardirq.h b/arch/um/include/asm/hardirq.h
new file mode 100644
index 000000000000..313ebb8a2566
--- /dev/null
+++ b/arch/um/include/asm/hardirq.h
@@ -0,0 +1,25 @@
+/* (c) 2004 cw@f00f.org, GPLv2 blah blah */
+
+#ifndef __ASM_UM_HARDIRQ_H
+#define __ASM_UM_HARDIRQ_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+/* NOTE: When SMP works again we might want to make this
+ * ____cacheline_aligned or maybe use per_cpu state? --cw */
+typedef struct {
+	unsigned int __softirq_pending;
+} irq_cpustat_t;
+
+#include <linux/irq_cpustat.h>
+
+/* As this would be very strange for UML to get we BUG() after the
+ * printk. */
+static inline void ack_bad_irq(unsigned int irq)
+{
+	printk(KERN_ERR "unexpected IRQ %02x\n", irq);
+	BUG();
+}
+
+#endif /* __ASM_UM_HARDIRQ_H */
diff --git a/arch/um/include/asm/highmem.h b/arch/um/include/asm/highmem.h
new file mode 100644
index 000000000000..36974cb8abc7
--- /dev/null
+++ b/arch/um/include/asm/highmem.h
@@ -0,0 +1,12 @@
+#ifndef __UM_HIGHMEM_H
+#define __UM_HIGHMEM_H
+
+#include "asm/page.h"
+#include "asm/fixmap.h"
+#include "asm/arch/highmem.h"
+
+#undef PKMAP_BASE
+
+#define PKMAP_BASE ((FIXADDR_START - LAST_PKMAP * PAGE_SIZE) & PMD_MASK)
+
+#endif
diff --git a/arch/um/include/asm/host_ldt-i386.h b/arch/um/include/asm/host_ldt-i386.h
new file mode 100644
index 000000000000..b27cb0a9dd30
--- /dev/null
+++ b/arch/um/include/asm/host_ldt-i386.h
@@ -0,0 +1,34 @@
+#ifndef __ASM_HOST_LDT_I386_H
+#define __ASM_HOST_LDT_I386_H
+
+#include "asm/arch/ldt.h"
+
+/*
+ * macros stolen from include/asm-i386/desc.h
+ */
+#define LDT_entry_a(info) \
+	((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
+
+#define LDT_entry_b(info) \
+	(((info)->base_addr & 0xff000000) | \
+	(((info)->base_addr & 0x00ff0000) >> 16) | \
+	((info)->limit & 0xf0000) | \
+	(((info)->read_exec_only ^ 1) << 9) | \
+	((info)->contents << 10) | \
+	(((info)->seg_not_present ^ 1) << 15) | \
+	((info)->seg_32bit << 22) | \
+	((info)->limit_in_pages << 23) | \
+	((info)->useable << 20) | \
+	0x7000)
+
+#define LDT_empty(info) (\
+	(info)->base_addr	== 0	&& \
+	(info)->limit		== 0	&& \
+	(info)->contents	== 0	&& \
+	(info)->read_exec_only	== 1	&& \
+	(info)->seg_32bit	== 0	&& \
+	(info)->limit_in_pages	== 0	&& \
+	(info)->seg_not_present	== 1	&& \
+	(info)->useable		== 0	)
+
+#endif
diff --git a/arch/um/include/asm/host_ldt-x86_64.h b/arch/um/include/asm/host_ldt-x86_64.h
new file mode 100644
index 000000000000..74a63f7d9a90
--- /dev/null
+++ b/arch/um/include/asm/host_ldt-x86_64.h
@@ -0,0 +1,38 @@
+#ifndef __ASM_HOST_LDT_X86_64_H
+#define __ASM_HOST_LDT_X86_64_H
+
+#include "asm/arch/ldt.h"
+
+/*
+ * macros stolen from include/asm-x86_64/desc.h
+ */
+#define LDT_entry_a(info) \
+	((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
+
+/* Don't allow setting of the lm bit. It is useless anyways because
+ * 64bit system calls require __USER_CS. */
+#define LDT_entry_b(info) \
+	(((info)->base_addr & 0xff000000) | \
+	(((info)->base_addr & 0x00ff0000) >> 16) | \
+	((info)->limit & 0xf0000) | \
+	(((info)->read_exec_only ^ 1) << 9) | \
+	((info)->contents << 10) | \
+	(((info)->seg_not_present ^ 1) << 15) | \
+	((info)->seg_32bit << 22) | \
+	((info)->limit_in_pages << 23) | \
+	((info)->useable << 20) | \
+	/* ((info)->lm << 21) | */ \
+	0x7000)
+
+#define LDT_empty(info) (\
+	(info)->base_addr	== 0	&& \
+	(info)->limit		== 0	&& \
+	(info)->contents	== 0	&& \
+	(info)->read_exec_only	== 1	&& \
+	(info)->seg_32bit	== 0	&& \
+	(info)->limit_in_pages	== 0	&& \
+	(info)->seg_not_present	== 1	&& \
+	(info)->useable		== 0	&& \
+	(info)->lm              == 0)
+
+#endif
diff --git a/arch/um/include/asm/hw_irq.h b/arch/um/include/asm/hw_irq.h
new file mode 100644
index 000000000000..1cf84cf5f21a
--- /dev/null
+++ b/arch/um/include/asm/hw_irq.h
@@ -0,0 +1,7 @@
+#ifndef _ASM_UM_HW_IRQ_H
+#define _ASM_UM_HW_IRQ_H
+
+#include "asm/irq.h"
+#include "asm/archparam.h"
+
+#endif
diff --git a/arch/um/include/asm/ide.h b/arch/um/include/asm/ide.h
new file mode 100644
index 000000000000..3d1ccebcfbaf
--- /dev/null
+++ b/arch/um/include/asm/ide.h
@@ -0,0 +1,6 @@
+#ifndef __UM_IDE_H
+#define __UM_IDE_H
+
+#include "asm/arch/ide.h"
+
+#endif
diff --git a/arch/um/include/asm/io.h b/arch/um/include/asm/io.h
new file mode 100644
index 000000000000..44e8b8c772ae
--- /dev/null
+++ b/arch/um/include/asm/io.h
@@ -0,0 +1,57 @@
+#ifndef __UM_IO_H
+#define __UM_IO_H
+
+#include "asm/page.h"
+
+#define IO_SPACE_LIMIT 0xdeadbeef /* Sure hope nothing uses this */
+
+static inline int inb(unsigned long i) { return(0); }
+static inline void outb(char c, unsigned long i) { }
+
+/*
+ * Change virtual addresses to physical addresses and vv.
+ * These are pretty trivial
+ */
+static inline unsigned long virt_to_phys(volatile void * address)
+{
+	return __pa((void *) address);
+}
+
+static inline void * phys_to_virt(unsigned long address)
+{
+	return __va(address);
+}
+
+/*
+ * Convert a physical pointer to a virtual kernel pointer for /dev/mem
+ * access
+ */
+#define xlate_dev_mem_ptr(p)	__va(p)
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p)	p
+
+static inline void writeb(unsigned char b, volatile void __iomem *addr)
+{
+	*(volatile unsigned char __force *) addr = b;
+}
+static inline void writew(unsigned short b, volatile void __iomem *addr)
+{
+	*(volatile unsigned short __force *) addr = b;
+}
+static inline void writel(unsigned int b, volatile void __iomem *addr)
+{
+	*(volatile unsigned int __force *) addr = b;
+}
+static inline void writeq(unsigned int b, volatile void __iomem *addr)
+{
+	*(volatile unsigned long long __force *) addr = b;
+}
+#define __raw_writeb writeb
+#define __raw_writew writew
+#define __raw_writel writel
+#define __raw_writeq writeq
+
+#endif
diff --git a/arch/um/include/asm/ioctl.h b/arch/um/include/asm/ioctl.h
new file mode 100644
index 000000000000..cc22157346db
--- /dev/null
+++ b/arch/um/include/asm/ioctl.h
@@ -0,0 +1,6 @@
+#ifndef __UM_IOCTL_H
+#define __UM_IOCTL_H
+
+#include "asm/arch/ioctl.h"
+
+#endif
diff --git a/arch/um/include/asm/ioctls.h b/arch/um/include/asm/ioctls.h
new file mode 100644
index 000000000000..9a1a017de6a7
--- /dev/null
+++ b/arch/um/include/asm/ioctls.h
@@ -0,0 +1,6 @@
+#ifndef __UM_IOCTLS_H
+#define __UM_IOCTLS_H
+
+#include "asm/arch/ioctls.h"
+
+#endif
diff --git a/arch/um/include/asm/ipcbuf.h b/arch/um/include/asm/ipcbuf.h
new file mode 100644
index 000000000000..bb2ad31dc434
--- /dev/null
+++ b/arch/um/include/asm/ipcbuf.h
@@ -0,0 +1,6 @@
+#ifndef __UM_IPCBUF_H
+#define __UM_IPCBUF_H
+
+#include "asm/arch/ipcbuf.h"
+
+#endif
diff --git a/arch/um/include/asm/irq.h b/arch/um/include/asm/irq.h
new file mode 100644
index 000000000000..4a2037f8204b
--- /dev/null
+++ b/arch/um/include/asm/irq.h
@@ -0,0 +1,23 @@
+#ifndef __UM_IRQ_H
+#define __UM_IRQ_H
+
+#define TIMER_IRQ		0
+#define UMN_IRQ			1
+#define CONSOLE_IRQ		2
+#define CONSOLE_WRITE_IRQ	3
+#define UBD_IRQ			4
+#define UM_ETH_IRQ		5
+#define SSL_IRQ			6
+#define SSL_WRITE_IRQ		7
+#define ACCEPT_IRQ		8
+#define MCONSOLE_IRQ		9
+#define WINCH_IRQ		10
+#define SIGIO_WRITE_IRQ 	11
+#define TELNETD_IRQ 		12
+#define XTERM_IRQ 		13
+#define RANDOM_IRQ 		14
+
+#define LAST_IRQ RANDOM_IRQ
+#define NR_IRQS (LAST_IRQ + 1)
+
+#endif
diff --git a/arch/um/include/asm/irq_regs.h b/arch/um/include/asm/irq_regs.h
new file mode 100644
index 000000000000..3dd9c0b70270
--- /dev/null
+++ b/arch/um/include/asm/irq_regs.h
@@ -0,0 +1 @@
+#include <asm-generic/irq_regs.h>
diff --git a/arch/um/include/asm/irq_vectors.h b/arch/um/include/asm/irq_vectors.h
new file mode 100644
index 000000000000..62ddba6fc733
--- /dev/null
+++ b/arch/um/include/asm/irq_vectors.h
@@ -0,0 +1,20 @@
+/* 
+ * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_IRQ_VECTORS_H
+#define __UM_IRQ_VECTORS_H
+
+#endif
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
diff --git a/arch/um/include/asm/irqflags.h b/arch/um/include/asm/irqflags.h
new file mode 100644
index 000000000000..659b9abdfdba
--- /dev/null
+++ b/arch/um/include/asm/irqflags.h
@@ -0,0 +1,6 @@
+#ifndef __UM_IRQFLAGS_H
+#define __UM_IRQFLAGS_H
+
+/* Empty for now */
+
+#endif
diff --git a/arch/um/include/asm/kdebug.h b/arch/um/include/asm/kdebug.h
new file mode 100644
index 000000000000..6ece1b037665
--- /dev/null
+++ b/arch/um/include/asm/kdebug.h
@@ -0,0 +1 @@
+#include <asm-generic/kdebug.h>
diff --git a/arch/um/include/asm/kmap_types.h b/arch/um/include/asm/kmap_types.h
new file mode 100644
index 000000000000..6c03acdb4405
--- /dev/null
+++ b/arch/um/include/asm/kmap_types.h
@@ -0,0 +1,29 @@
+/* 
+ * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_KMAP_TYPES_H
+#define __UM_KMAP_TYPES_H
+
+/* No more #include "asm/arch/kmap_types.h" ! */
+
+enum km_type {
+	KM_BOUNCE_READ,
+	KM_SKB_SUNRPC_DATA,
+	KM_SKB_DATA_SOFTIRQ,
+	KM_USER0,
+	KM_USER1,
+	KM_UML_USERCOPY,	/* UML specific, for copy_*_user - used in do_op_one_page */
+	KM_BIO_SRC_IRQ,
+	KM_BIO_DST_IRQ,
+	KM_PTE0,
+	KM_PTE1,
+	KM_IRQ0,
+	KM_IRQ1,
+	KM_SOFTIRQ0,
+	KM_SOFTIRQ1,
+	KM_TYPE_NR
+};
+
+#endif
diff --git a/arch/um/include/asm/ldt.h b/arch/um/include/asm/ldt.h
new file mode 100644
index 000000000000..52af512f5e7d
--- /dev/null
+++ b/arch/um/include/asm/ldt.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (C) 2004 Fujitsu Siemens Computers GmbH
+ * Licensed under the GPL
+ *
+ * Author: Bodo Stroesser <bstroesser@fujitsu-siemens.com>
+ */
+
+#ifndef __ASM_LDT_H
+#define __ASM_LDT_H
+
+#include <linux/mutex.h>
+#include "asm/host_ldt.h"
+
+extern void ldt_host_info(void);
+
+#define LDT_PAGES_MAX \
+	((LDT_ENTRIES * LDT_ENTRY_SIZE)/PAGE_SIZE)
+#define LDT_ENTRIES_PER_PAGE \
+	(PAGE_SIZE/LDT_ENTRY_SIZE)
+#define LDT_DIRECT_ENTRIES \
+	((LDT_PAGES_MAX*sizeof(void *))/LDT_ENTRY_SIZE)
+
+struct ldt_entry {
+	__u32 a;
+	__u32 b;
+};
+
+typedef struct uml_ldt {
+	int entry_count;
+	struct mutex lock;
+	union {
+		struct ldt_entry * pages[LDT_PAGES_MAX];
+		struct ldt_entry entries[LDT_DIRECT_ENTRIES];
+	} u;
+} uml_ldt_t;
+
+#endif
diff --git a/arch/um/include/asm/linkage.h b/arch/um/include/asm/linkage.h
new file mode 100644
index 000000000000..7dfce37adc8b
--- /dev/null
+++ b/arch/um/include/asm/linkage.h
@@ -0,0 +1,6 @@
+#ifndef __ASM_UM_LINKAGE_H
+#define __ASM_UM_LINKAGE_H
+
+#include "asm/arch/linkage.h"
+
+#endif
diff --git a/arch/um/include/asm/local.h b/arch/um/include/asm/local.h
new file mode 100644
index 000000000000..9a280c5bb609
--- /dev/null
+++ b/arch/um/include/asm/local.h
@@ -0,0 +1,6 @@
+#ifndef __UM_LOCAL_H
+#define __UM_LOCAL_H
+
+#include "asm/arch/local.h"
+
+#endif
diff --git a/arch/um/include/asm/locks.h b/arch/um/include/asm/locks.h
new file mode 100644
index 000000000000..f80030a3ef5a
--- /dev/null
+++ b/arch/um/include/asm/locks.h
@@ -0,0 +1,6 @@
+#ifndef __UM_LOCKS_H
+#define __UM_LOCKS_H
+
+#include "asm/arch/locks.h"
+
+#endif
diff --git a/arch/um/include/asm/mca_dma.h b/arch/um/include/asm/mca_dma.h
new file mode 100644
index 000000000000..e492e4ec1392
--- /dev/null
+++ b/arch/um/include/asm/mca_dma.h
@@ -0,0 +1,6 @@
+#ifndef mca___UM_DMA_H
+#define mca___UM_DMA_H
+
+#include "asm/arch/mca_dma.h"
+
+#endif
diff --git a/arch/um/include/asm/mman.h b/arch/um/include/asm/mman.h
new file mode 100644
index 000000000000..b09ed523019b
--- /dev/null
+++ b/arch/um/include/asm/mman.h
@@ -0,0 +1,6 @@
+#ifndef __UM_MMAN_H
+#define __UM_MMAN_H
+
+#include "asm/arch/mman.h"
+
+#endif
diff --git a/arch/um/include/asm/mmu.h b/arch/um/include/asm/mmu.h
new file mode 100644
index 000000000000..2cf35c21d694
--- /dev/null
+++ b/arch/um/include/asm/mmu.h
@@ -0,0 +1,22 @@
+/* 
+ * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __MMU_H
+#define __MMU_H
+
+#include "um_mmu.h"
+
+#endif
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
diff --git a/arch/um/include/asm/mmu_context.h b/arch/um/include/asm/mmu_context.h
new file mode 100644
index 000000000000..54f42e8b0105
--- /dev/null
+++ b/arch/um/include/asm/mmu_context.h
@@ -0,0 +1,54 @@
+/* 
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_MMU_CONTEXT_H
+#define __UM_MMU_CONTEXT_H
+
+#include "linux/sched.h"
+#include "um_mmu.h"
+
+extern void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm);
+extern void arch_exit_mmap(struct mm_struct *mm);
+
+#define get_mmu_context(task) do ; while(0)
+#define activate_context(tsk) do ; while(0)
+
+#define deactivate_mm(tsk,mm)	do { } while (0)
+
+extern void force_flush_all(void);
+
+static inline void activate_mm(struct mm_struct *old, struct mm_struct *new)
+{
+	/*
+	 * This is called by fs/exec.c and sys_unshare()
+	 * when the new ->mm is used for the first time.
+	 */
+	__switch_mm(&new->context.id);
+	arch_dup_mmap(old, new);
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, 
+			     struct task_struct *tsk)
+{
+	unsigned cpu = smp_processor_id();
+
+	if(prev != next){
+		cpu_clear(cpu, prev->cpu_vm_mask);
+		cpu_set(cpu, next->cpu_vm_mask);
+		if(next != &init_mm)
+			__switch_mm(&next->context.id);
+	}
+}
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, 
+				  struct task_struct *tsk)
+{
+}
+
+extern int init_new_context(struct task_struct *task, struct mm_struct *mm);
+
+extern void destroy_context(struct mm_struct *mm);
+
+#endif
diff --git a/arch/um/include/asm/module-generic.h b/arch/um/include/asm/module-generic.h
new file mode 100644
index 000000000000..5a265f56b174
--- /dev/null
+++ b/arch/um/include/asm/module-generic.h
@@ -0,0 +1,6 @@
+#ifndef __UM_MODULE_GENERIC_H
+#define __UM_MODULE_GENERIC_H
+
+#include "asm/arch/module.h"
+
+#endif
diff --git a/arch/um/include/asm/module-i386.h b/arch/um/include/asm/module-i386.h
new file mode 100644
index 000000000000..5ead4a0b2e35
--- /dev/null
+++ b/arch/um/include/asm/module-i386.h
@@ -0,0 +1,13 @@
+#ifndef __UM_MODULE_I386_H
+#define __UM_MODULE_I386_H
+
+/* UML is simple */
+struct mod_arch_specific
+{
+};
+
+#define Elf_Shdr Elf32_Shdr
+#define Elf_Sym Elf32_Sym
+#define Elf_Ehdr Elf32_Ehdr
+
+#endif
diff --git a/arch/um/include/asm/module-x86_64.h b/arch/um/include/asm/module-x86_64.h
new file mode 100644
index 000000000000..35b5491d3e96
--- /dev/null
+++ b/arch/um/include/asm/module-x86_64.h
@@ -0,0 +1,30 @@
+/*
+ * Copyright 2003 PathScale, Inc.
+ *
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_MODULE_X86_64_H
+#define __UM_MODULE_X86_64_H
+
+/* UML is simple */
+struct mod_arch_specific
+{
+};
+
+#define Elf_Shdr Elf64_Shdr
+#define Elf_Sym Elf64_Sym
+#define Elf_Ehdr Elf64_Ehdr
+
+#endif
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
diff --git a/arch/um/include/asm/msgbuf.h b/arch/um/include/asm/msgbuf.h
new file mode 100644
index 000000000000..8ce8c30d5377
--- /dev/null
+++ b/arch/um/include/asm/msgbuf.h
@@ -0,0 +1,6 @@
+#ifndef __UM_MSGBUF_H
+#define __UM_MSGBUF_H
+
+#include "asm/arch/msgbuf.h"
+
+#endif
diff --git a/arch/um/include/asm/mtrr.h b/arch/um/include/asm/mtrr.h
new file mode 100644
index 000000000000..5e9cd12c578d
--- /dev/null
+++ b/arch/um/include/asm/mtrr.h
@@ -0,0 +1,6 @@
+#ifndef __UM_MTRR_H
+#define __UM_MTRR_H
+
+#include "asm/arch/mtrr.h"
+
+#endif
diff --git a/arch/um/include/asm/mutex.h b/arch/um/include/asm/mutex.h
new file mode 100644
index 000000000000..458c1f7fbc18
--- /dev/null
+++ b/arch/um/include/asm/mutex.h
@@ -0,0 +1,9 @@
+/*
+ * Pull in the generic implementation for the mutex fastpath.
+ *
+ * TODO: implement optimized primitives instead, or leave the generic
+ * implementation in place, or pick the atomic_xchg() based generic
+ * implementation. (see asm-generic/mutex-xchg.h for details)
+ */
+
+#include <asm-generic/mutex-dec.h>
diff --git a/arch/um/include/asm/nops.h b/arch/um/include/asm/nops.h
new file mode 100644
index 000000000000..814e9bf5dea6
--- /dev/null
+++ b/arch/um/include/asm/nops.h
@@ -0,0 +1,6 @@
+#ifndef __UM_NOPS_H
+#define __UM_NOPS_H
+
+#include "asm/arch/nops.h"
+
+#endif
diff --git a/arch/um/include/asm/page.h b/arch/um/include/asm/page.h
new file mode 100644
index 000000000000..a6df1f13d732
--- /dev/null
+++ b/arch/um/include/asm/page.h
@@ -0,0 +1,122 @@
+/*
+ * Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com)
+ * Copyright 2003 PathScale, Inc.
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PAGE_H
+#define __UM_PAGE_H
+
+#include <linux/const.h>
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT	12
+#define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
+#define PAGE_MASK	(~(PAGE_SIZE-1))
+
+#ifndef __ASSEMBLY__
+
+struct page;
+
+#include <linux/types.h>
+#include <asm/vm-flags.h>
+
+/*
+ * These are used to make use of C type-checking..
+ */
+
+#define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
+#define copy_page(to,from)	memcpy((void *)(to), (void *)(from), PAGE_SIZE)
+
+#define clear_user_page(page, vaddr, pg)	clear_page(page)
+#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
+
+#if defined(CONFIG_3_LEVEL_PGTABLES) && !defined(CONFIG_64BIT)
+
+typedef struct { unsigned long pte_low, pte_high; } pte_t;
+typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pgd; } pgd_t;
+#define pte_val(x) ((x).pte_low | ((unsigned long long) (x).pte_high << 32))
+
+#define pte_get_bits(pte, bits) ((pte).pte_low & (bits))
+#define pte_set_bits(pte, bits) ((pte).pte_low |= (bits))
+#define pte_clear_bits(pte, bits) ((pte).pte_low &= ~(bits))
+#define pte_copy(to, from) ({ (to).pte_high = (from).pte_high; \
+			      smp_wmb(); \
+			      (to).pte_low = (from).pte_low; })
+#define pte_is_zero(pte) (!((pte).pte_low & ~_PAGE_NEWPAGE) && !(pte).pte_high)
+#define pte_set_val(pte, phys, prot) \
+	({ (pte).pte_high = (phys) >> 32; \
+	   (pte).pte_low = (phys) | pgprot_val(prot); })
+
+#define pmd_val(x)	((x).pmd)
+#define __pmd(x) ((pmd_t) { (x) } )
+
+typedef unsigned long long pfn_t;
+typedef unsigned long long phys_t;
+
+#else
+
+typedef struct { unsigned long pte; } pte_t;
+typedef struct { unsigned long pgd; } pgd_t;
+
+#ifdef CONFIG_3_LEVEL_PGTABLES
+typedef struct { unsigned long pmd; } pmd_t;
+#define pmd_val(x)	((x).pmd)
+#define __pmd(x) ((pmd_t) { (x) } )
+#endif
+
+#define pte_val(x)	((x).pte)
+
+
+#define pte_get_bits(p, bits) ((p).pte & (bits))
+#define pte_set_bits(p, bits) ((p).pte |= (bits))
+#define pte_clear_bits(p, bits) ((p).pte &= ~(bits))
+#define pte_copy(to, from) ((to).pte = (from).pte)
+#define pte_is_zero(p) (!((p).pte & ~_PAGE_NEWPAGE))
+#define pte_set_val(p, phys, prot) (p).pte = (phys | pgprot_val(prot))
+
+typedef unsigned long pfn_t;
+typedef unsigned long phys_t;
+
+#endif
+
+typedef struct { unsigned long pgprot; } pgprot_t;
+
+typedef struct page *pgtable_t;
+
+#define pgd_val(x)	((x).pgd)
+#define pgprot_val(x)	((x).pgprot)
+
+#define __pte(x) ((pte_t) { (x) } )
+#define __pgd(x) ((pgd_t) { (x) } )
+#define __pgprot(x)	((pgprot_t) { (x) } )
+
+extern unsigned long uml_physmem;
+
+#define PAGE_OFFSET (uml_physmem)
+#define KERNELBASE PAGE_OFFSET
+
+#define __va_space (8*1024*1024)
+
+#include "mem.h"
+
+/* Cast to unsigned long before casting to void * to avoid a warning from
+ * mmap_kmem about cutting a long long down to a void *.  Not sure that
+ * casting is the right thing, but 32-bit UML can't have 64-bit virtual
+ * addresses
+ */
+#define __pa(virt) to_phys((void *) (unsigned long) (virt))
+#define __va(phys) to_virt((unsigned long) (phys))
+
+#define phys_to_pfn(p) ((pfn_t) ((p) >> PAGE_SHIFT))
+#define pfn_to_phys(pfn) ((phys_t) ((pfn) << PAGE_SHIFT))
+
+#define pfn_valid(pfn) ((pfn) < max_mapnr)
+#define virt_addr_valid(v) pfn_valid(phys_to_pfn(__pa(v)))
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/page.h>
+
+#endif	/* __ASSEMBLY__ */
+#endif	/* __UM_PAGE_H */
diff --git a/arch/um/include/asm/page_offset.h b/arch/um/include/asm/page_offset.h
new file mode 100644
index 000000000000..1c168dfbf359
--- /dev/null
+++ b/arch/um/include/asm/page_offset.h
@@ -0,0 +1 @@
+#define PAGE_OFFSET_RAW (uml_physmem)
diff --git a/arch/um/include/asm/param.h b/arch/um/include/asm/param.h
new file mode 100644
index 000000000000..e44f4e60d16d
--- /dev/null
+++ b/arch/um/include/asm/param.h
@@ -0,0 +1,20 @@
+#ifndef _UM_PARAM_H
+#define _UM_PARAM_H
+
+#define EXEC_PAGESIZE   4096
+
+#ifndef NOGROUP
+#define NOGROUP         (-1)
+#endif
+
+#define MAXHOSTNAMELEN  64      /* max length of hostname */
+
+#ifdef __KERNEL__
+#define HZ CONFIG_HZ
+#define USER_HZ	100	   /* .. some user interfaces are in "ticks" */
+#define CLOCKS_PER_SEC (USER_HZ)  /* frequency at which times() counts */
+#else
+#define HZ 100
+#endif
+
+#endif
diff --git a/arch/um/include/asm/paravirt.h b/arch/um/include/asm/paravirt.h
new file mode 100644
index 000000000000..9d6aaad80b5f
--- /dev/null
+++ b/arch/um/include/asm/paravirt.h
@@ -0,0 +1,6 @@
+#ifndef __UM_PARAVIRT_H
+#define __UM_PARAVIRT_H
+
+#include "asm/arch/paravirt.h"
+
+#endif
diff --git a/arch/um/include/asm/pci.h b/arch/um/include/asm/pci.h
new file mode 100644
index 000000000000..59923199cdc3
--- /dev/null
+++ b/arch/um/include/asm/pci.h
@@ -0,0 +1,7 @@
+#ifndef __UM_PCI_H
+#define __UM_PCI_H
+
+#define PCI_DMA_BUS_IS_PHYS     (1)
+#define pcibios_scan_all_fns(a, b)	0
+
+#endif
diff --git a/arch/um/include/asm/pda.h b/arch/um/include/asm/pda.h
new file mode 100644
index 000000000000..0d8bf33ffd42
--- /dev/null
+++ b/arch/um/include/asm/pda.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright 2003 PathScale, Inc.
+ *
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PDA_X86_64_H
+#define __UM_PDA_X86_64_H
+
+/* XXX */
+struct foo {
+	unsigned int __softirq_pending;
+	unsigned int __nmi_count;
+};
+
+extern struct foo me;
+
+#define read_pda(me) (&me)
+
+#endif
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
diff --git a/arch/um/include/asm/percpu.h b/arch/um/include/asm/percpu.h
new file mode 100644
index 000000000000..5723e2aab8e7
--- /dev/null
+++ b/arch/um/include/asm/percpu.h
@@ -0,0 +1,6 @@
+#ifndef __UM_PERCPU_H
+#define __UM_PERCPU_H
+
+#include "asm/arch/percpu.h"
+
+#endif
diff --git a/arch/um/include/asm/pgalloc.h b/arch/um/include/asm/pgalloc.h
new file mode 100644
index 000000000000..9062a6e72241
--- /dev/null
+++ b/arch/um/include/asm/pgalloc.h
@@ -0,0 +1,72 @@
+/* 
+ * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com)
+ * Copyright 2003 PathScale, Inc.
+ * Derived from include/asm-i386/pgalloc.h and include/asm-i386/pgtable.h
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PGALLOC_H
+#define __UM_PGALLOC_H
+
+#include "linux/mm.h"
+#include "asm/fixmap.h"
+
+#define pmd_populate_kernel(mm, pmd, pte) \
+	set_pmd(pmd, __pmd(_PAGE_TABLE + (unsigned long) __pa(pte)))
+
+#define pmd_populate(mm, pmd, pte) 				\
+	set_pmd(pmd, __pmd(_PAGE_TABLE +			\
+		((unsigned long long)page_to_pfn(pte) <<	\
+			(unsigned long long) PAGE_SHIFT)))
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
+/*
+ * Allocate and free page tables.
+ */
+extern pgd_t *pgd_alloc(struct mm_struct *);
+extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
+
+extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
+extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long);
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	free_page((unsigned long) pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
+{
+	pgtable_page_dtor(pte);
+	__free_page(pte);
+}
+
+#define __pte_free_tlb(tlb,pte)				\
+do {							\
+	pgtable_page_dtor(pte);				\
+	tlb_remove_page((tlb),(pte));			\
+} while (0)
+
+#ifdef CONFIG_3_LEVEL_PGTABLES
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	free_page((unsigned long)pmd);
+}
+
+#define __pmd_free_tlb(tlb,x)   tlb_remove_page((tlb),virt_to_page(x))
+#endif
+
+#define check_pgt_cache()	do { } while (0)
+
+#endif
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
diff --git a/arch/um/include/asm/pgtable-2level.h b/arch/um/include/asm/pgtable-2level.h
new file mode 100644
index 000000000000..f534b73e753e
--- /dev/null
+++ b/arch/um/include/asm/pgtable-2level.h
@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com)
+ * Copyright 2003 PathScale, Inc.
+ * Derived from include/asm-i386/pgtable.h
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PGTABLE_2LEVEL_H
+#define __UM_PGTABLE_2LEVEL_H
+
+#include <asm-generic/pgtable-nopmd.h>
+
+/* PGDIR_SHIFT determines what a third-level page table entry can map */
+
+#define PGDIR_SHIFT	22
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+/*
+ * entries per page directory level: the i386 is two-level, so
+ * we don't really have any PMD directory physically.
+ */
+#define PTRS_PER_PTE	1024
+#define USER_PTRS_PER_PGD ((TASK_SIZE + (PGDIR_SIZE - 1)) / PGDIR_SIZE)
+#define PTRS_PER_PGD	1024
+#define FIRST_USER_ADDRESS	0
+
+#define pte_ERROR(e) \
+        printk("%s:%d: bad pte %p(%08lx).\n", __FILE__, __LINE__, &(e), \
+	       pte_val(e))
+#define pgd_ERROR(e) \
+        printk("%s:%d: bad pgd %p(%08lx).\n", __FILE__, __LINE__, &(e), \
+	       pgd_val(e))
+
+static inline int pgd_newpage(pgd_t pgd)	{ return 0; }
+static inline void pgd_mkuptodate(pgd_t pgd)	{ }
+
+#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval))
+
+#define pte_pfn(x) phys_to_pfn(pte_val(x))
+#define pfn_pte(pfn, prot) __pte(pfn_to_phys(pfn) | pgprot_val(prot))
+#define pfn_pmd(pfn, prot) __pmd(pfn_to_phys(pfn) | pgprot_val(prot))
+
+/*
+ * Bits 0 through 4 are taken
+ */
+#define PTE_FILE_MAX_BITS	27
+
+#define pte_to_pgoff(pte) (pte_val(pte) >> 5)
+
+#define pgoff_to_pte(off) ((pte_t) { ((off) << 5) + _PAGE_FILE })
+
+#endif
diff --git a/arch/um/include/asm/pgtable-3level.h b/arch/um/include/asm/pgtable-3level.h
new file mode 100644
index 000000000000..0446f456b428
--- /dev/null
+++ b/arch/um/include/asm/pgtable-3level.h
@@ -0,0 +1,146 @@
+/*
+ * Copyright 2003 PathScale Inc
+ * Derived from include/asm-i386/pgtable.h
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PGTABLE_3LEVEL_H
+#define __UM_PGTABLE_3LEVEL_H
+
+#include <asm-generic/pgtable-nopud.h>
+
+/* PGDIR_SHIFT determines what a third-level page table entry can map */
+
+#ifdef CONFIG_64BIT
+#define PGDIR_SHIFT	30
+#else
+#define PGDIR_SHIFT	31
+#endif
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE-1))
+
+/* PMD_SHIFT determines the size of the area a second-level page table can
+ * map
+ */
+
+#define PMD_SHIFT	21
+#define PMD_SIZE	(1UL << PMD_SHIFT)
+#define PMD_MASK	(~(PMD_SIZE-1))
+
+/*
+ * entries per page directory level
+ */
+
+#define PTRS_PER_PTE 512
+#ifdef CONFIG_64BIT
+#define PTRS_PER_PMD 512
+#define PTRS_PER_PGD 512
+#else
+#define PTRS_PER_PMD 1024
+#define PTRS_PER_PGD 1024
+#endif
+
+#define USER_PTRS_PER_PGD ((TASK_SIZE + (PGDIR_SIZE - 1)) / PGDIR_SIZE)
+#define FIRST_USER_ADDRESS	0
+
+#define pte_ERROR(e) \
+        printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), \
+	       pte_val(e))
+#define pmd_ERROR(e) \
+        printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e), \
+	       pmd_val(e))
+#define pgd_ERROR(e) \
+        printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e), \
+	       pgd_val(e))
+
+#define pud_none(x)	(!(pud_val(x) & ~_PAGE_NEWPAGE))
+#define	pud_bad(x)	((pud_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
+#define pud_present(x)	(pud_val(x) & _PAGE_PRESENT)
+#define pud_populate(mm, pud, pmd) \
+	set_pud(pud, __pud(_PAGE_TABLE + __pa(pmd)))
+
+#ifdef CONFIG_64BIT
+#define set_pud(pudptr, pudval) set_64bit((phys_t *) (pudptr), pud_val(pudval))
+#else
+#define set_pud(pudptr, pudval) (*(pudptr) = (pudval))
+#endif
+
+static inline int pgd_newpage(pgd_t pgd)
+{
+	return(pgd_val(pgd) & _PAGE_NEWPAGE);
+}
+
+static inline void pgd_mkuptodate(pgd_t pgd) { pgd_val(pgd) &= ~_PAGE_NEWPAGE; }
+
+#ifdef CONFIG_64BIT
+#define set_pmd(pmdptr, pmdval) set_64bit((phys_t *) (pmdptr), pmd_val(pmdval))
+#else
+#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval))
+#endif
+
+struct mm_struct;
+extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address);
+
+static inline void pud_clear (pud_t *pud)
+{
+	set_pud(pud, __pud(_PAGE_NEWPAGE));
+}
+
+#define pud_page(pud) phys_to_page(pud_val(pud) & PAGE_MASK)
+#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PAGE_MASK))
+
+/* Find an entry in the second-level page table.. */
+#define pmd_offset(pud, address) ((pmd_t *) pud_page_vaddr(*(pud)) + \
+			pmd_index(address))
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+	return phys_to_pfn(pte_val(pte));
+}
+
+static inline pte_t pfn_pte(pfn_t page_nr, pgprot_t pgprot)
+{
+	pte_t pte;
+	phys_t phys = pfn_to_phys(page_nr);
+
+	pte_set_val(pte, phys, pgprot);
+	return pte;
+}
+
+static inline pmd_t pfn_pmd(pfn_t page_nr, pgprot_t pgprot)
+{
+	return __pmd((page_nr << PAGE_SHIFT) | pgprot_val(pgprot));
+}
+
+/*
+ * Bits 0 through 3 are taken in the low part of the pte,
+ * put the 32 bits of offset into the high part.
+ */
+#define PTE_FILE_MAX_BITS	32
+
+#ifdef CONFIG_64BIT
+
+#define pte_to_pgoff(p) ((p).pte >> 32)
+
+#define pgoff_to_pte(off) ((pte_t) { ((off) << 32) | _PAGE_FILE })
+
+#else
+
+#define pte_to_pgoff(pte) ((pte).pte_high)
+
+#define pgoff_to_pte(off) ((pte_t) { _PAGE_FILE, (off) })
+
+#endif
+
+#endif
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
diff --git a/arch/um/include/asm/pgtable.h b/arch/um/include/asm/pgtable.h
new file mode 100644
index 000000000000..02db81b7b86e
--- /dev/null
+++ b/arch/um/include/asm/pgtable.h
@@ -0,0 +1,358 @@
+/* 
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Copyright 2003 PathScale, Inc.
+ * Derived from include/asm-i386/pgtable.h
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PGTABLE_H
+#define __UM_PGTABLE_H
+
+#include <asm/fixmap.h>
+
+#define _PAGE_PRESENT	0x001
+#define _PAGE_NEWPAGE	0x002
+#define _PAGE_NEWPROT	0x004
+#define _PAGE_RW	0x020
+#define _PAGE_USER	0x040
+#define _PAGE_ACCESSED	0x080
+#define _PAGE_DIRTY	0x100
+/* If _PAGE_PRESENT is clear, we use these: */
+#define _PAGE_FILE	0x008	/* nonlinear file mapping, saved PTE; unset:swap */
+#define _PAGE_PROTNONE	0x010	/* if the user mapped it with PROT_NONE;
+				   pte_present gives true */
+
+#ifdef CONFIG_3_LEVEL_PGTABLES
+#include "asm/pgtable-3level.h"
+#else
+#include "asm/pgtable-2level.h"
+#endif
+
+extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+
+/* zero page used for uninitialized stuff */
+extern unsigned long *empty_zero_page;
+
+#define pgtable_cache_init() do ; while (0)
+
+/* Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 8MB value just means that there will be a 8MB "hole" after the
+ * physical memory until the kernel virtual memory starts.  That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ */
+
+extern unsigned long end_iomem;
+
+#define VMALLOC_OFFSET	(__va_space)
+#define VMALLOC_START ((end_iomem + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
+#ifdef CONFIG_HIGHMEM
+# define VMALLOC_END	(PKMAP_BASE-2*PAGE_SIZE)
+#else
+# define VMALLOC_END	(FIXADDR_START-2*PAGE_SIZE)
+#endif
+
+#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#define PAGE_NONE	__pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
+
+/*
+ * The i386 can't do page protection for execute, and considers that the same
+ * are read.
+ * Also, write permissions imply read permissions. This is the closest we can
+ * get..
+ */
+#define __P000	PAGE_NONE
+#define __P001	PAGE_READONLY
+#define __P010	PAGE_COPY
+#define __P011	PAGE_COPY
+#define __P100	PAGE_READONLY
+#define __P101	PAGE_READONLY
+#define __P110	PAGE_COPY
+#define __P111	PAGE_COPY
+
+#define __S000	PAGE_NONE
+#define __S001	PAGE_READONLY
+#define __S010	PAGE_SHARED
+#define __S011	PAGE_SHARED
+#define __S100	PAGE_READONLY
+#define __S101	PAGE_READONLY
+#define __S110	PAGE_SHARED
+#define __S111	PAGE_SHARED
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+#define ZERO_PAGE(vaddr) virt_to_page(empty_zero_page)
+
+#define pte_clear(mm,addr,xp) pte_set_val(*(xp), (phys_t) 0, __pgprot(_PAGE_NEWPAGE))
+
+#define pmd_none(x)	(!((unsigned long)pmd_val(x) & ~_PAGE_NEWPAGE))
+#define	pmd_bad(x)	((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
+
+#define pmd_present(x)	(pmd_val(x) & _PAGE_PRESENT)
+#define pmd_clear(xp)	do { pmd_val(*(xp)) = _PAGE_NEWPAGE; } while (0)
+
+#define pmd_newpage(x)  (pmd_val(x) & _PAGE_NEWPAGE)
+#define pmd_mkuptodate(x) (pmd_val(x) &= ~_PAGE_NEWPAGE)
+
+#define pud_newpage(x)  (pud_val(x) & _PAGE_NEWPAGE)
+#define pud_mkuptodate(x) (pud_val(x) &= ~_PAGE_NEWPAGE)
+
+#define pmd_page(pmd) phys_to_page(pmd_val(pmd) & PAGE_MASK)
+
+#define pte_page(x) pfn_to_page(pte_pfn(x))
+
+#define pte_present(x)	pte_get_bits(x, (_PAGE_PRESENT | _PAGE_PROTNONE))
+
+/*
+ * =================================
+ * Flags checking section.
+ * =================================
+ */
+
+static inline int pte_none(pte_t pte)
+{
+	return pte_is_zero(pte);
+}
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_read(pte_t pte)
+{ 
+	return((pte_get_bits(pte, _PAGE_USER)) &&
+	       !(pte_get_bits(pte, _PAGE_PROTNONE)));
+}
+
+static inline int pte_exec(pte_t pte){
+	return((pte_get_bits(pte, _PAGE_USER)) &&
+	       !(pte_get_bits(pte, _PAGE_PROTNONE)));
+}
+
+static inline int pte_write(pte_t pte)
+{
+	return((pte_get_bits(pte, _PAGE_RW)) &&
+	       !(pte_get_bits(pte, _PAGE_PROTNONE)));
+}
+
+/*
+ * The following only works if pte_present() is not true.
+ */
+static inline int pte_file(pte_t pte)
+{
+	return pte_get_bits(pte, _PAGE_FILE);
+}
+
+static inline int pte_dirty(pte_t pte)
+{
+	return pte_get_bits(pte, _PAGE_DIRTY);
+}
+
+static inline int pte_young(pte_t pte)
+{
+	return pte_get_bits(pte, _PAGE_ACCESSED);
+}
+
+static inline int pte_newpage(pte_t pte)
+{
+	return pte_get_bits(pte, _PAGE_NEWPAGE);
+}
+
+static inline int pte_newprot(pte_t pte)
+{ 
+	return(pte_present(pte) && (pte_get_bits(pte, _PAGE_NEWPROT)));
+}
+
+static inline int pte_special(pte_t pte)
+{
+	return 0;
+}
+
+/*
+ * =================================
+ * Flags setting section.
+ * =================================
+ */
+
+static inline pte_t pte_mknewprot(pte_t pte)
+{
+	pte_set_bits(pte, _PAGE_NEWPROT);
+	return(pte);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	pte_clear_bits(pte, _PAGE_DIRTY);
+	return(pte);
+}
+
+static inline pte_t pte_mkold(pte_t pte)	
+{ 
+	pte_clear_bits(pte, _PAGE_ACCESSED);
+	return(pte);
+}
+
+static inline pte_t pte_wrprotect(pte_t pte)
+{ 
+	pte_clear_bits(pte, _PAGE_RW);
+	return(pte_mknewprot(pte)); 
+}
+
+static inline pte_t pte_mkread(pte_t pte)
+{ 
+	pte_set_bits(pte, _PAGE_USER);
+	return(pte_mknewprot(pte)); 
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{ 
+	pte_set_bits(pte, _PAGE_DIRTY);
+	return(pte);
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	pte_set_bits(pte, _PAGE_ACCESSED);
+	return(pte);
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)	
+{
+	pte_set_bits(pte, _PAGE_RW);
+	return(pte_mknewprot(pte)); 
+}
+
+static inline pte_t pte_mkuptodate(pte_t pte)	
+{
+	pte_clear_bits(pte, _PAGE_NEWPAGE);
+	if(pte_present(pte))
+		pte_clear_bits(pte, _PAGE_NEWPROT);
+	return(pte); 
+}
+
+static inline pte_t pte_mknewpage(pte_t pte)
+{
+	pte_set_bits(pte, _PAGE_NEWPAGE);
+	return(pte);
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return(pte);
+}
+
+static inline void set_pte(pte_t *pteptr, pte_t pteval)
+{
+	pte_copy(*pteptr, pteval);
+
+	/* If it's a swap entry, it needs to be marked _PAGE_NEWPAGE so
+	 * fix_range knows to unmap it.  _PAGE_NEWPROT is specific to
+	 * mapped pages.
+	 */
+
+	*pteptr = pte_mknewpage(*pteptr);
+	if(pte_present(*pteptr)) *pteptr = pte_mknewprot(*pteptr);
+}
+#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+
+#define phys_to_page(phys) pfn_to_page(phys_to_pfn(phys))
+#define __virt_to_page(virt) phys_to_page(__pa(virt))
+#define page_to_phys(page) pfn_to_phys((pfn_t) page_to_pfn(page))
+#define virt_to_page(addr) __virt_to_page((const unsigned long) addr)
+
+#define mk_pte(page, pgprot) \
+	({ pte_t pte;					\
+							\
+	pte_set_val(pte, page_to_phys(page), (pgprot));	\
+	if (pte_present(pte))				\
+		pte_mknewprot(pte_mknewpage(pte));	\
+	pte;})
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	pte_set_val(pte, (pte_val(pte) & _PAGE_CHG_MASK), newprot);
+	return pte; 
+}
+
+/*
+ * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
+ *
+ * this macro returns the index of the entry in the pgd page which would
+ * control the given virtual address
+ */
+#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
+
+/*
+ * pgd_offset() returns a (pgd_t *)
+ * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
+ */
+#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
+
+/*
+ * a shortcut which implies the use of the kernel's pgd, instead
+ * of a process's
+ */
+#define pgd_offset_k(address) pgd_offset(&init_mm, address)
+
+/*
+ * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
+ *
+ * this macro returns the index of the entry in the pmd page which would
+ * control the given virtual address
+ */
+#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
+
+#define pmd_page_vaddr(pmd) \
+	((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
+
+/*
+ * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
+ *
+ * this macro returns the index of the entry in the pte page which would
+ * control the given virtual address
+ */
+#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, address) \
+	((pte_t *) pmd_page_vaddr(*(dir)) +  pte_index(address))
+#define pte_offset_map(dir, address) \
+	((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address))
+#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address)
+#define pte_unmap(pte) do { } while (0)
+#define pte_unmap_nested(pte) do { } while (0)
+
+struct mm_struct;
+extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr);
+
+#define update_mmu_cache(vma,address,pte) do ; while (0)
+
+/* Encode and de-code a swap entry */
+#define __swp_type(x)			(((x).val >> 4) & 0x3f)
+#define __swp_offset(x)			((x).val >> 11)
+
+#define __swp_entry(type, offset) \
+	((swp_entry_t) { ((type) << 4) | ((offset) << 11) })
+#define __pte_to_swp_entry(pte) \
+	((swp_entry_t) { pte_val(pte_mkuptodate(pte)) })
+#define __swp_entry_to_pte(x)		((pte_t) { (x).val })
+
+#define kern_addr_valid(addr) (1)
+
+#include <asm-generic/pgtable.h>
+
+#endif
diff --git a/arch/um/include/asm/poll.h b/arch/um/include/asm/poll.h
new file mode 100644
index 000000000000..1eb4e1bc6383
--- /dev/null
+++ b/arch/um/include/asm/poll.h
@@ -0,0 +1,6 @@
+#ifndef __UM_POLL_H
+#define __UM_POLL_H
+
+#include "asm/arch/poll.h"
+
+#endif
diff --git a/arch/um/include/asm/posix_types.h b/arch/um/include/asm/posix_types.h
new file mode 100644
index 000000000000..32fb4198f644
--- /dev/null
+++ b/arch/um/include/asm/posix_types.h
@@ -0,0 +1,6 @@
+#ifndef __UM_POSIX_TYPES_H
+#define __UM_POSIX_TYPES_H
+
+#include "asm/arch/posix_types.h"
+
+#endif
diff --git a/arch/um/include/asm/prctl.h b/arch/um/include/asm/prctl.h
new file mode 100644
index 000000000000..64b6d099bdd5
--- /dev/null
+++ b/arch/um/include/asm/prctl.h
@@ -0,0 +1,6 @@
+#ifndef __UM_PRCTL_H
+#define __UM_PRCTL_H
+
+#include "asm/arch/prctl.h"
+
+#endif
diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
new file mode 100644
index 000000000000..bed668824b5f
--- /dev/null
+++ b/arch/um/include/asm/processor-generic.h
@@ -0,0 +1,136 @@
+/* 
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PROCESSOR_GENERIC_H
+#define __UM_PROCESSOR_GENERIC_H
+
+struct pt_regs;
+
+struct task_struct;
+
+#include "asm/ptrace.h"
+#include "registers.h"
+#include "sysdep/archsetjmp.h"
+
+struct mm_struct;
+
+struct thread_struct {
+	struct task_struct *saved_task;
+	/*
+	 * This flag is set to 1 before calling do_fork (and analyzed in
+	 * copy_thread) to mark that we are begin called from userspace (fork /
+	 * vfork / clone), and reset to 0 after. It is left to 0 when called
+	 * from kernelspace (i.e. kernel_thread() or fork_idle(),
+	 * as of 2.6.11).
+	 */
+	int forking;
+	struct pt_regs regs;
+	int singlestep_syscall;
+	void *fault_addr;
+	jmp_buf *fault_catcher;
+	struct task_struct *prev_sched;
+	unsigned long temp_stack;
+	jmp_buf *exec_buf;
+	struct arch_thread arch;
+	jmp_buf switch_buf;
+	int mm_count;
+	struct {
+		int op;
+		union {
+			struct {
+				int pid;
+			} fork, exec;
+			struct {
+				int (*proc)(void *);
+				void *arg;
+			} thread;
+			struct {
+				void (*proc)(void *);
+				void *arg;
+			} cb;
+		} u;
+	} request;
+};
+
+#define INIT_THREAD \
+{ \
+	.forking		= 0, \
+	.regs		   	= EMPTY_REGS,	\
+	.fault_addr		= NULL, \
+	.prev_sched		= NULL, \
+	.temp_stack		= 0, \
+	.exec_buf		= NULL, \
+	.arch			= INIT_ARCH_THREAD, \
+	.request		= { 0 } \
+}
+
+extern struct task_struct *alloc_task_struct(void);
+
+static inline void release_thread(struct task_struct *task)
+{
+}
+
+extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
+
+static inline void prepare_to_copy(struct task_struct *tsk)
+{
+}
+
+
+extern unsigned long thread_saved_pc(struct task_struct *t);
+
+static inline void mm_copy_segments(struct mm_struct *from_mm,
+				    struct mm_struct *new_mm)
+{
+}
+
+#define init_stack	(init_thread_union.stack)
+
+/*
+ * User space process size: 3GB (default).
+ */
+extern unsigned long task_size;
+
+#define TASK_SIZE (task_size)
+
+#undef STACK_TOP
+#undef STACK_TOP_MAX
+
+extern unsigned long stacksizelim;
+
+#define STACK_ROOM	(stacksizelim)
+#define STACK_TOP	(TASK_SIZE - 2 * PAGE_SIZE)
+#define STACK_TOP_MAX	STACK_TOP
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE	(0x40000000)
+
+extern void start_thread(struct pt_regs *regs, unsigned long entry, 
+			 unsigned long stack);
+
+struct cpuinfo_um {
+	unsigned long loops_per_jiffy;
+	int ipi_pipe[2];
+};
+
+extern struct cpuinfo_um boot_cpu_data;
+
+#define my_cpu_data		cpu_data[smp_processor_id()]
+
+#ifdef CONFIG_SMP
+extern struct cpuinfo_um cpu_data[];
+#define current_cpu_data cpu_data[smp_processor_id()]
+#else
+#define cpu_data (&boot_cpu_data)
+#define current_cpu_data boot_cpu_data
+#endif
+
+
+#define KSTK_REG(tsk, reg) get_thread_reg(reg, &tsk->thread.switch_buf)
+extern unsigned long get_wchan(struct task_struct *p);
+
+#endif
diff --git a/arch/um/include/asm/processor-i386.h b/arch/um/include/asm/processor-i386.h
new file mode 100644
index 000000000000..a2b7fe13fe1e
--- /dev/null
+++ b/arch/um/include/asm/processor-i386.h
@@ -0,0 +1,78 @@
+/*
+ * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PROCESSOR_I386_H
+#define __UM_PROCESSOR_I386_H
+
+#include "linux/string.h"
+#include "asm/host_ldt.h"
+#include "asm/segment.h"
+
+extern int host_has_cmov;
+
+/* include faultinfo structure */
+#include "sysdep/faultinfo.h"
+
+struct uml_tls_struct {
+	struct user_desc tls;
+	unsigned flushed:1;
+	unsigned present:1;
+};
+
+struct arch_thread {
+	struct uml_tls_struct tls_array[GDT_ENTRY_TLS_ENTRIES];
+	unsigned long debugregs[8];
+	int debugregs_seq;
+	struct faultinfo faultinfo;
+};
+
+#define INIT_ARCH_THREAD { \
+	.tls_array  		= { [ 0 ... GDT_ENTRY_TLS_ENTRIES - 1 ] = \
+				    { .present = 0, .flushed = 0 } }, \
+	.debugregs  		= { [ 0 ... 7 ] = 0 }, \
+	.debugregs_seq		= 0, \
+	.faultinfo		= { 0, 0, 0 } \
+}
+
+static inline void arch_flush_thread(struct arch_thread *thread)
+{
+	/* Clear any TLS still hanging */
+	memset(&thread->tls_array, 0, sizeof(thread->tls_array));
+}
+
+static inline void arch_copy_thread(struct arch_thread *from,
+                                    struct arch_thread *to)
+{
+        memcpy(&to->tls_array, &from->tls_array, sizeof(from->tls_array));
+}
+
+#include "asm/arch/user.h"
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+	__asm__ __volatile__("rep;nop": : :"memory");
+}
+
+#define cpu_relax()	rep_nop()
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter"). Stolen
+ * from asm-i386/processor.h
+ */
+#define current_text_addr() \
+	({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; })
+
+#define ARCH_IS_STACKGROW(address) \
+       (address + 32 >= UPT_SP(&current->thread.regs.regs))
+
+#define KSTK_EIP(tsk) KSTK_REG(tsk, EIP)
+#define KSTK_ESP(tsk) KSTK_REG(tsk, UESP)
+#define KSTK_EBP(tsk) KSTK_REG(tsk, EBP)
+
+#include "asm/processor-generic.h"
+
+#endif
diff --git a/arch/um/include/asm/processor-ppc.h b/arch/um/include/asm/processor-ppc.h
new file mode 100644
index 000000000000..959323151229
--- /dev/null
+++ b/arch/um/include/asm/processor-ppc.h
@@ -0,0 +1,15 @@
+#ifndef __UM_PROCESSOR_PPC_H
+#define __UM_PROCESSOR_PPC_H
+
+#if defined(__ASSEMBLY__)
+
+#define CONFIG_PPC_MULTIPLATFORM
+#include "arch/processor.h"
+
+#else
+
+#include "asm/processor-generic.h"
+
+#endif
+
+#endif
diff --git a/arch/um/include/asm/processor-x86_64.h b/arch/um/include/asm/processor-x86_64.h
new file mode 100644
index 000000000000..e50933175e91
--- /dev/null
+++ b/arch/um/include/asm/processor-x86_64.h
@@ -0,0 +1,56 @@
+/*
+ * Copyright 2003 PathScale, Inc.
+ *
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PROCESSOR_X86_64_H
+#define __UM_PROCESSOR_X86_64_H
+
+/* include faultinfo structure */
+#include "sysdep/faultinfo.h"
+
+struct arch_thread {
+        unsigned long debugregs[8];
+        int debugregs_seq;
+        unsigned long fs;
+        struct faultinfo faultinfo;
+};
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+	__asm__ __volatile__("rep;nop": : :"memory");
+}
+
+#define cpu_relax()   rep_nop()
+
+#define INIT_ARCH_THREAD { .debugregs  		= { [ 0 ... 7 ] = 0 }, \
+			   .debugregs_seq	= 0, \
+			   .fs			= 0, \
+			   .faultinfo		= { 0, 0, 0 } }
+
+static inline void arch_flush_thread(struct arch_thread *thread)
+{
+}
+
+static inline void arch_copy_thread(struct arch_thread *from,
+                                    struct arch_thread *to)
+{
+	to->fs = from->fs;
+}
+
+#include "asm/arch/user.h"
+
+#define current_text_addr() \
+	({ void *pc; __asm__("movq $1f,%0\n1:":"=g" (pc)); pc; })
+
+#define ARCH_IS_STACKGROW(address) \
+        (address + 128 >= UPT_SP(&current->thread.regs.regs))
+
+#define KSTK_EIP(tsk) KSTK_REG(tsk, RIP)
+#define KSTK_ESP(tsk) KSTK_REG(tsk, RSP)
+
+#include "asm/processor-generic.h"
+
+#endif
diff --git a/arch/um/include/asm/ptrace-generic.h b/arch/um/include/asm/ptrace-generic.h
new file mode 100644
index 000000000000..315749705ea1
--- /dev/null
+++ b/arch/um/include/asm/ptrace-generic.h
@@ -0,0 +1,55 @@
+/* 
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PTRACE_GENERIC_H
+#define __UM_PTRACE_GENERIC_H
+
+#ifndef __ASSEMBLY__
+
+#include "asm/arch/ptrace-abi.h"
+#include <asm/user.h>
+#include "sysdep/ptrace.h"
+
+struct pt_regs {
+	struct uml_pt_regs regs;
+};
+
+#define EMPTY_REGS { .regs = EMPTY_UML_PT_REGS }
+
+#define PT_REGS_IP(r) UPT_IP(&(r)->regs)
+#define PT_REGS_SP(r) UPT_SP(&(r)->regs)
+
+#define PT_REG(r, reg) UPT_REG(&(r)->regs, reg)
+#define PT_REGS_SET(r, reg, val) UPT_SET(&(r)->regs, reg, val)
+
+#define PT_REGS_SET_SYSCALL_RETURN(r, res) \
+	UPT_SET_SYSCALL_RETURN(&(r)->regs, res)
+#define PT_REGS_RESTART_SYSCALL(r) UPT_RESTART_SYSCALL(&(r)->regs)
+
+#define PT_REGS_SYSCALL_NR(r) UPT_SYSCALL_NR(&(r)->regs)
+
+#define PT_REGS_SC(r) UPT_SC(&(r)->regs)
+
+#define instruction_pointer(regs) PT_REGS_IP(regs)
+
+struct task_struct;
+
+extern long subarch_ptrace(struct task_struct *child, long request, long addr,
+			   long data);
+extern unsigned long getreg(struct task_struct *child, int regno);
+extern int putreg(struct task_struct *child, int regno, unsigned long value);
+extern int get_fpregs(struct user_i387_struct __user *buf,
+		      struct task_struct *child);
+extern int set_fpregs(struct user_i387_struct __user *buf,
+		      struct task_struct *child);
+
+extern void show_regs(struct pt_regs *regs);
+
+extern int arch_copy_tls(struct task_struct *new);
+extern void clear_flushed_tls(struct task_struct *task);
+
+#endif
+
+#endif
diff --git a/arch/um/include/asm/ptrace-i386.h b/arch/um/include/asm/ptrace-i386.h
new file mode 100644
index 000000000000..b2d24c5ea2c3
--- /dev/null
+++ b/arch/um/include/asm/ptrace-i386.h
@@ -0,0 +1,60 @@
+/* 
+ * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PTRACE_I386_H
+#define __UM_PTRACE_I386_H
+
+#define HOST_AUDIT_ARCH AUDIT_ARCH_I386
+
+#include "linux/compiler.h"
+#include "asm/ptrace-generic.h"
+#include <asm/user.h>
+#include "sysdep/ptrace.h"
+
+#define PT_REGS_EAX(r) UPT_EAX(&(r)->regs)
+#define PT_REGS_EBX(r) UPT_EBX(&(r)->regs)
+#define PT_REGS_ECX(r) UPT_ECX(&(r)->regs)
+#define PT_REGS_EDX(r) UPT_EDX(&(r)->regs)
+#define PT_REGS_ESI(r) UPT_ESI(&(r)->regs)
+#define PT_REGS_EDI(r) UPT_EDI(&(r)->regs)
+#define PT_REGS_EBP(r) UPT_EBP(&(r)->regs)
+
+#define PT_REGS_CS(r) UPT_CS(&(r)->regs)
+#define PT_REGS_SS(r) UPT_SS(&(r)->regs)
+#define PT_REGS_DS(r) UPT_DS(&(r)->regs)
+#define PT_REGS_ES(r) UPT_ES(&(r)->regs)
+#define PT_REGS_FS(r) UPT_FS(&(r)->regs)
+#define PT_REGS_GS(r) UPT_GS(&(r)->regs)
+
+#define PT_REGS_EFLAGS(r) UPT_EFLAGS(&(r)->regs)
+
+#define PT_REGS_ORIG_SYSCALL(r) PT_REGS_EAX(r)
+#define PT_REGS_SYSCALL_RET(r) PT_REGS_EAX(r)
+#define PT_FIX_EXEC_STACK(sp) do ; while(0)
+
+/* Cope with a conditional i386 definition. */
+#undef profile_pc
+#define profile_pc(regs) PT_REGS_IP(regs)
+
+#define user_mode(r) UPT_IS_USER(&(r)->regs)
+
+/*
+ * Forward declaration to avoid including sysdep/tls.h, which causes a
+ * circular include, and compilation failures.
+ */
+struct user_desc;
+
+extern int get_fpxregs(struct user_fxsr_struct __user *buf,
+		       struct task_struct *child);
+extern int set_fpxregs(struct user_fxsr_struct __user *buf,
+		       struct task_struct *tsk);
+
+extern int ptrace_get_thread_area(struct task_struct *child, int idx,
+                                  struct user_desc __user *user_desc);
+
+extern int ptrace_set_thread_area(struct task_struct *child, int idx,
+                                  struct user_desc __user *user_desc);
+
+#endif
diff --git a/arch/um/include/asm/ptrace-x86_64.h b/arch/um/include/asm/ptrace-x86_64.h
new file mode 100644
index 000000000000..4c475350dcf0
--- /dev/null
+++ b/arch/um/include/asm/ptrace-x86_64.h
@@ -0,0 +1,81 @@
+/*
+ * Copyright 2003 PathScale, Inc.
+ *
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_PTRACE_X86_64_H
+#define __UM_PTRACE_X86_64_H
+
+#include "linux/compiler.h"
+#include "asm/errno.h"
+#include "asm/host_ldt.h"
+
+#define __FRAME_OFFSETS /* Needed to get the R* macros */
+#include "asm/ptrace-generic.h"
+
+#define HOST_AUDIT_ARCH AUDIT_ARCH_X86_64
+
+/* Also defined in sysdep/ptrace.h, so may already be defined. */
+#ifndef FS_BASE
+#define FS_BASE (21 * sizeof(unsigned long))
+#define GS_BASE (22 * sizeof(unsigned long))
+#define DS (23 * sizeof(unsigned long))
+#define ES (24 * sizeof(unsigned long))
+#define FS (25 * sizeof(unsigned long))
+#define GS (26 * sizeof(unsigned long))
+#endif
+
+#define PT_REGS_RBX(r) UPT_RBX(&(r)->regs)
+#define PT_REGS_RCX(r) UPT_RCX(&(r)->regs)
+#define PT_REGS_RDX(r) UPT_RDX(&(r)->regs)
+#define PT_REGS_RSI(r) UPT_RSI(&(r)->regs)
+#define PT_REGS_RDI(r) UPT_RDI(&(r)->regs)
+#define PT_REGS_RBP(r) UPT_RBP(&(r)->regs)
+#define PT_REGS_RAX(r) UPT_RAX(&(r)->regs)
+#define PT_REGS_R8(r) UPT_R8(&(r)->regs)
+#define PT_REGS_R9(r) UPT_R9(&(r)->regs)
+#define PT_REGS_R10(r) UPT_R10(&(r)->regs)
+#define PT_REGS_R11(r) UPT_R11(&(r)->regs)
+#define PT_REGS_R12(r) UPT_R12(&(r)->regs)
+#define PT_REGS_R13(r) UPT_R13(&(r)->regs)
+#define PT_REGS_R14(r) UPT_R14(&(r)->regs)
+#define PT_REGS_R15(r) UPT_R15(&(r)->regs)
+
+#define PT_REGS_FS(r) UPT_FS(&(r)->regs)
+#define PT_REGS_GS(r) UPT_GS(&(r)->regs)
+#define PT_REGS_DS(r) UPT_DS(&(r)->regs)
+#define PT_REGS_ES(r) UPT_ES(&(r)->regs)
+#define PT_REGS_SS(r) UPT_SS(&(r)->regs)
+#define PT_REGS_CS(r) UPT_CS(&(r)->regs)
+
+#define PT_REGS_ORIG_RAX(r) UPT_ORIG_RAX(&(r)->regs)
+#define PT_REGS_RIP(r) UPT_IP(&(r)->regs)
+#define PT_REGS_RSP(r) UPT_SP(&(r)->regs)
+
+#define PT_REGS_EFLAGS(r) UPT_EFLAGS(&(r)->regs)
+
+/* XXX */
+#define user_mode(r) UPT_IS_USER(&(r)->regs)
+#define PT_REGS_ORIG_SYSCALL(r) PT_REGS_RAX(r)
+#define PT_REGS_SYSCALL_RET(r) PT_REGS_RAX(r)
+
+#define PT_FIX_EXEC_STACK(sp) do ; while(0)
+
+#define profile_pc(regs) PT_REGS_IP(regs)
+
+static inline int ptrace_get_thread_area(struct task_struct *child, int idx,
+                                         struct user_desc __user *user_desc)
+{
+        return -ENOSYS;
+}
+
+static inline int ptrace_set_thread_area(struct task_struct *child, int idx,
+                                         struct user_desc __user *user_desc)
+{
+        return -ENOSYS;
+}
+
+extern long arch_prctl(struct task_struct *task, int code,
+		       unsigned long __user *addr);
+#endif
diff --git a/arch/um/include/asm/required-features.h b/arch/um/include/asm/required-features.h
new file mode 100644
index 000000000000..dfb967b2d2f3
--- /dev/null
+++ b/arch/um/include/asm/required-features.h
@@ -0,0 +1,9 @@
+#ifndef __UM_REQUIRED_FEATURES_H
+#define __UM_REQUIRED_FEATURES_H
+
+/*
+ * Nothing to see, just need something for the i386 and x86_64 asm
+ * headers to include.
+ */
+
+#endif
diff --git a/arch/um/include/asm/resource.h b/arch/um/include/asm/resource.h
new file mode 100644
index 000000000000..c9b074001252
--- /dev/null
+++ b/arch/um/include/asm/resource.h
@@ -0,0 +1,6 @@
+#ifndef __UM_RESOURCE_H
+#define __UM_RESOURCE_H
+
+#include "asm/arch/resource.h"
+
+#endif
diff --git a/arch/um/include/asm/rwlock.h b/arch/um/include/asm/rwlock.h
new file mode 100644
index 000000000000..ff383aafc9fe
--- /dev/null
+++ b/arch/um/include/asm/rwlock.h
@@ -0,0 +1,6 @@
+#ifndef __UM_RWLOCK_H
+#define __UM_RWLOCK_H
+
+#include "asm/arch/rwlock.h"
+
+#endif
diff --git a/arch/um/include/asm/rwsem.h b/arch/um/include/asm/rwsem.h
new file mode 100644
index 000000000000..b5fc449dc86b
--- /dev/null
+++ b/arch/um/include/asm/rwsem.h
@@ -0,0 +1,6 @@
+#ifndef __UM_RWSEM_H__
+#define __UM_RWSEM_H__
+
+#include "asm/arch/rwsem.h"
+
+#endif
diff --git a/arch/um/include/asm/scatterlist.h b/arch/um/include/asm/scatterlist.h
new file mode 100644
index 000000000000..e92016aa2079
--- /dev/null
+++ b/arch/um/include/asm/scatterlist.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SCATTERLIST_H
+#define __UM_SCATTERLIST_H
+
+#include "asm/arch/scatterlist.h"
+
+#endif
diff --git a/arch/um/include/asm/sections.h b/arch/um/include/asm/sections.h
new file mode 100644
index 000000000000..6b0231eefea8
--- /dev/null
+++ b/arch/um/include/asm/sections.h
@@ -0,0 +1,7 @@
+#ifndef _UM_SECTIONS_H
+#define _UM_SECTIONS_H
+
+/* nothing to see, move along */
+#include <asm-generic/sections.h>
+
+#endif
diff --git a/arch/um/include/asm/segment.h b/arch/um/include/asm/segment.h
new file mode 100644
index 000000000000..45183fcd10b6
--- /dev/null
+++ b/arch/um/include/asm/segment.h
@@ -0,0 +1,10 @@
+#ifndef __UM_SEGMENT_H
+#define __UM_SEGMENT_H
+
+extern int host_gdt_entry_tls_min;
+
+#define GDT_ENTRY_TLS_ENTRIES 3
+#define GDT_ENTRY_TLS_MIN host_gdt_entry_tls_min
+#define GDT_ENTRY_TLS_MAX (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1)
+
+#endif
diff --git a/arch/um/include/asm/sembuf.h b/arch/um/include/asm/sembuf.h
new file mode 100644
index 000000000000..1ae82c14ff86
--- /dev/null
+++ b/arch/um/include/asm/sembuf.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SEMBUF_H
+#define __UM_SEMBUF_H
+
+#include "asm/arch/sembuf.h"
+
+#endif
diff --git a/arch/um/include/asm/serial.h b/arch/um/include/asm/serial.h
new file mode 100644
index 000000000000..61ad07cfd2d5
--- /dev/null
+++ b/arch/um/include/asm/serial.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SERIAL_H
+#define __UM_SERIAL_H
+
+#include "asm/arch/serial.h"
+
+#endif
diff --git a/arch/um/include/asm/setup.h b/arch/um/include/asm/setup.h
new file mode 100644
index 000000000000..99f086301f4c
--- /dev/null
+++ b/arch/um/include/asm/setup.h
@@ -0,0 +1,10 @@
+#ifndef SETUP_H_INCLUDED
+#define SETUP_H_INCLUDED
+
+/* POSIX mandated with _POSIX_ARG_MAX that we can rely on 4096 chars in the
+ * command line, so this choice is ok.
+ */
+
+#define COMMAND_LINE_SIZE 4096
+
+#endif		/* SETUP_H_INCLUDED */
diff --git a/arch/um/include/asm/shmbuf.h b/arch/um/include/asm/shmbuf.h
new file mode 100644
index 000000000000..9684d4a284a6
--- /dev/null
+++ b/arch/um/include/asm/shmbuf.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SHMBUF_H
+#define __UM_SHMBUF_H
+
+#include "asm/arch/shmbuf.h"
+
+#endif
diff --git a/arch/um/include/asm/shmparam.h b/arch/um/include/asm/shmparam.h
new file mode 100644
index 000000000000..124c00174f6a
--- /dev/null
+++ b/arch/um/include/asm/shmparam.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SHMPARAM_H
+#define __UM_SHMPARAM_H
+
+#include "asm/arch/shmparam.h"
+
+#endif
diff --git a/arch/um/include/asm/sigcontext-generic.h b/arch/um/include/asm/sigcontext-generic.h
new file mode 100644
index 000000000000..164587014c61
--- /dev/null
+++ b/arch/um/include/asm/sigcontext-generic.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SIGCONTEXT_GENERIC_H
+#define __UM_SIGCONTEXT_GENERIC_H
+
+#include "asm/arch/sigcontext.h"
+
+#endif
diff --git a/arch/um/include/asm/sigcontext-i386.h b/arch/um/include/asm/sigcontext-i386.h
new file mode 100644
index 000000000000..b88333f488bb
--- /dev/null
+++ b/arch/um/include/asm/sigcontext-i386.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SIGCONTEXT_I386_H
+#define __UM_SIGCONTEXT_I386_H
+
+#include "asm/sigcontext-generic.h"
+
+#endif
diff --git a/arch/um/include/asm/sigcontext-ppc.h b/arch/um/include/asm/sigcontext-ppc.h
new file mode 100644
index 000000000000..2467f20eda99
--- /dev/null
+++ b/arch/um/include/asm/sigcontext-ppc.h
@@ -0,0 +1,10 @@
+#ifndef __UM_SIGCONTEXT_PPC_H
+#define __UM_SIGCONTEXT_PPC_H
+
+#define pt_regs sys_pt_regs
+
+#include "asm/sigcontext-generic.h"
+
+#undef pt_regs
+
+#endif
diff --git a/arch/um/include/asm/sigcontext-x86_64.h b/arch/um/include/asm/sigcontext-x86_64.h
new file mode 100644
index 000000000000..b600e0b01e48
--- /dev/null
+++ b/arch/um/include/asm/sigcontext-x86_64.h
@@ -0,0 +1,22 @@
+/* Copyright 2003 PathScale, Inc.
+ *
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_SIGCONTEXT_X86_64_H
+#define __UM_SIGCONTEXT_X86_64_H
+
+#include "asm/sigcontext-generic.h"
+
+#endif
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
diff --git a/arch/um/include/asm/siginfo.h b/arch/um/include/asm/siginfo.h
new file mode 100644
index 000000000000..bec6124c36d0
--- /dev/null
+++ b/arch/um/include/asm/siginfo.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SIGINFO_H
+#define __UM_SIGINFO_H
+
+#include "asm/arch/siginfo.h"
+
+#endif
diff --git a/arch/um/include/asm/signal.h b/arch/um/include/asm/signal.h
new file mode 100644
index 000000000000..52ed92cbce4c
--- /dev/null
+++ b/arch/um/include/asm/signal.h
@@ -0,0 +1,29 @@
+/* 
+ * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_SIGNAL_H
+#define __UM_SIGNAL_H
+
+/* Need to kill the do_signal() declaration in the i386 signal.h */
+
+#define do_signal do_signal_renamed
+#include "asm/arch/signal.h"
+#undef do_signal
+#undef ptrace_signal_deliver
+
+#define ptrace_signal_deliver(regs, cookie) do {} while(0)
+
+#endif
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
diff --git a/arch/um/include/asm/smp.h b/arch/um/include/asm/smp.h
new file mode 100644
index 000000000000..f27a96313174
--- /dev/null
+++ b/arch/um/include/asm/smp.h
@@ -0,0 +1,33 @@
+#ifndef __UM_SMP_H
+#define __UM_SMP_H
+
+#ifdef CONFIG_SMP
+
+#include "linux/bitops.h"
+#include "asm/current.h"
+#include "linux/cpumask.h"
+
+#define raw_smp_processor_id() (current_thread->cpu)
+
+#define cpu_logical_map(n) (n)
+#define cpu_number_map(n) (n)
+#define PROC_CHANGE_PENALTY	15 /* Pick a number, any number */
+extern int hard_smp_processor_id(void);
+#define NO_PROC_ID -1
+
+extern int ncpus;
+
+
+static inline void smp_cpus_done(unsigned int maxcpus)
+{
+}
+
+extern struct task_struct *idle_threads[NR_CPUS];
+
+#else
+
+#define hard_smp_processor_id()		0
+
+#endif
+
+#endif
diff --git a/arch/um/include/asm/socket.h b/arch/um/include/asm/socket.h
new file mode 100644
index 000000000000..67886e42ef04
--- /dev/null
+++ b/arch/um/include/asm/socket.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SOCKET_H
+#define __UM_SOCKET_H
+
+#include "asm/arch/socket.h"
+
+#endif
diff --git a/arch/um/include/asm/sockios.h b/arch/um/include/asm/sockios.h
new file mode 100644
index 000000000000..93ee1c55c4d6
--- /dev/null
+++ b/arch/um/include/asm/sockios.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SOCKIOS_H
+#define __UM_SOCKIOS_H
+
+#include "asm/arch/sockios.h"
+
+#endif
diff --git a/arch/um/include/asm/spinlock.h b/arch/um/include/asm/spinlock.h
new file mode 100644
index 000000000000..f18c82886992
--- /dev/null
+++ b/arch/um/include/asm/spinlock.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SPINLOCK_H
+#define __UM_SPINLOCK_H
+
+#include "asm/arch/spinlock.h"
+
+#endif
diff --git a/arch/um/include/asm/spinlock_types.h b/arch/um/include/asm/spinlock_types.h
new file mode 100644
index 000000000000..e5a94294bf82
--- /dev/null
+++ b/arch/um/include/asm/spinlock_types.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SPINLOCK_TYPES_H
+#define __UM_SPINLOCK_TYPES_H
+
+#include "asm/arch/spinlock_types.h"
+
+#endif
diff --git a/arch/um/include/asm/stat.h b/arch/um/include/asm/stat.h
new file mode 100644
index 000000000000..83ed85ad2539
--- /dev/null
+++ b/arch/um/include/asm/stat.h
@@ -0,0 +1,6 @@
+#ifndef __UM_STAT_H
+#define __UM_STAT_H
+
+#include "asm/arch/stat.h"
+
+#endif
diff --git a/arch/um/include/asm/statfs.h b/arch/um/include/asm/statfs.h
new file mode 100644
index 000000000000..ba6fb53e7f87
--- /dev/null
+++ b/arch/um/include/asm/statfs.h
@@ -0,0 +1,6 @@
+#ifndef _UM_STATFS_H
+#define _UM_STATFS_H
+
+#include "asm/arch/statfs.h"
+
+#endif
diff --git a/arch/um/include/asm/string.h b/arch/um/include/asm/string.h
new file mode 100644
index 000000000000..9a0571f6dd61
--- /dev/null
+++ b/arch/um/include/asm/string.h
@@ -0,0 +1,7 @@
+#ifndef __UM_STRING_H
+#define __UM_STRING_H
+
+#include "asm/arch/string.h"
+#include "asm/archparam.h"
+
+#endif
diff --git a/arch/um/include/asm/suspend.h b/arch/um/include/asm/suspend.h
new file mode 100644
index 000000000000..f4e8e007f468
--- /dev/null
+++ b/arch/um/include/asm/suspend.h
@@ -0,0 +1,4 @@
+#ifndef __UM_SUSPEND_H
+#define __UM_SUSPEND_H
+
+#endif
diff --git a/arch/um/include/asm/system-generic.h b/arch/um/include/asm/system-generic.h
new file mode 100644
index 000000000000..5bcfa35e7a22
--- /dev/null
+++ b/arch/um/include/asm/system-generic.h
@@ -0,0 +1,47 @@
+#ifndef __UM_SYSTEM_GENERIC_H
+#define __UM_SYSTEM_GENERIC_H
+
+#include "asm/arch/system.h"
+
+#undef switch_to
+#undef local_irq_save
+#undef local_irq_restore
+#undef local_irq_disable
+#undef local_irq_enable
+#undef local_save_flags
+#undef local_irq_restore
+#undef local_irq_enable
+#undef local_irq_disable
+#undef local_irq_save
+#undef irqs_disabled
+
+extern void *switch_to(void *prev, void *next, void *last);
+
+extern int get_signals(void);
+extern int set_signals(int enable);
+extern int get_signals(void);
+extern void block_signals(void);
+extern void unblock_signals(void);
+
+#define local_save_flags(flags) do { typecheck(unsigned long, flags); \
+				     (flags) = get_signals(); } while(0)
+#define local_irq_restore(flags) do { typecheck(unsigned long, flags); \
+				      set_signals(flags); } while(0)
+
+#define local_irq_save(flags) do { local_save_flags(flags); \
+                                   local_irq_disable(); } while(0)
+
+#define local_irq_enable() unblock_signals()
+#define local_irq_disable() block_signals()
+
+#define irqs_disabled()                 \
+({                                      \
+        unsigned long flags;            \
+        local_save_flags(flags);        \
+        (flags == 0);                   \
+})
+
+extern void *_switch_to(void *prev, void *next, void *last);
+#define switch_to(prev, next, last) prev = _switch_to(prev, next, last)
+
+#endif
diff --git a/arch/um/include/asm/system-i386.h b/arch/um/include/asm/system-i386.h
new file mode 100644
index 000000000000..c436263e67ba
--- /dev/null
+++ b/arch/um/include/asm/system-i386.h
@@ -0,0 +1,6 @@
+#ifndef __UM_SYSTEM_I386_H
+#define __UM_SYSTEM_I386_H
+
+#include "asm/system-generic.h"
+    
+#endif
diff --git a/arch/um/include/asm/system-ppc.h b/arch/um/include/asm/system-ppc.h
new file mode 100644
index 000000000000..17cde6640bf5
--- /dev/null
+++ b/arch/um/include/asm/system-ppc.h
@@ -0,0 +1,12 @@
+#ifndef __UM_SYSTEM_PPC_H
+#define __UM_SYSTEM_PPC_H
+
+#define _switch_to _ppc_switch_to
+
+#include "asm/arch/system.h"
+
+#undef _switch_to
+ 
+#include "asm/system-generic.h"
+
+#endif
diff --git a/arch/um/include/asm/system-x86_64.h b/arch/um/include/asm/system-x86_64.h
new file mode 100644
index 000000000000..e1b61b580734
--- /dev/null
+++ b/arch/um/include/asm/system-x86_64.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright 2003 PathScale, Inc.
+ *
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_SYSTEM_X86_64_H
+#define __UM_SYSTEM_X86_64_H
+
+#include "asm/system-generic.h"
+
+#endif
+
+/*
+ * Overrides for Emacs so that we follow Linus's tabbing style.
+ * Emacs will notice this stuff at the end of the file and automatically
+ * adjust the settings for this buffer only.  This must remain at the end
+ * of the file.
+ * ---------------------------------------------------------------------------
+ * Local variables:
+ * c-file-style: "linux"
+ * End:
+ */
diff --git a/arch/um/include/asm/termbits.h b/arch/um/include/asm/termbits.h
new file mode 100644
index 000000000000..5739c608a2cb
--- /dev/null
+++ b/arch/um/include/asm/termbits.h
@@ -0,0 +1,6 @@
+#ifndef __UM_TERMBITS_H
+#define __UM_TERMBITS_H
+
+#include "asm/arch/termbits.h"
+
+#endif
diff --git a/arch/um/include/asm/termios.h b/arch/um/include/asm/termios.h
new file mode 100644
index 000000000000..d9f97b303311
--- /dev/null
+++ b/arch/um/include/asm/termios.h
@@ -0,0 +1,6 @@
+#ifndef __UM_TERMIOS_H
+#define __UM_TERMIOS_H
+
+#include "asm/arch/termios.h"
+
+#endif
diff --git a/arch/um/include/asm/thread_info.h b/arch/um/include/asm/thread_info.h
new file mode 100644
index 000000000000..62274ab9471f
--- /dev/null
+++ b/arch/um/include/asm/thread_info.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_THREAD_INFO_H
+#define __UM_THREAD_INFO_H
+
+#ifndef __ASSEMBLY__
+
+#include <asm/types.h>
+#include <asm/page.h>
+#include <asm/uaccess.h>
+
+struct thread_info {
+	struct task_struct	*task;		/* main task structure */
+	struct exec_domain	*exec_domain;	/* execution domain */
+	unsigned long		flags;		/* low level flags */
+	__u32			cpu;		/* current CPU */
+	int			preempt_count;  /* 0 => preemptable,
+						   <0 => BUG */
+	mm_segment_t		addr_limit;	/* thread address space:
+					 	   0-0xBFFFFFFF for user
+						   0-0xFFFFFFFF for kernel */
+	struct restart_block    restart_block;
+	struct thread_info	*real_thread;    /* Points to non-IRQ stack */
+};
+
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.task =		&tsk,			\
+	.exec_domain =	&default_exec_domain,	\
+	.flags =		0,		\
+	.cpu =		0,			\
+	.preempt_count =	1,		\
+	.addr_limit =	KERNEL_DS,		\
+	.restart_block =  {			\
+		.fn =  do_no_restart_syscall,	\
+	},					\
+	.real_thread = NULL,			\
+}
+
+#define init_thread_info	(init_thread_union.thread_info)
+#define init_stack		(init_thread_union.stack)
+
+#define THREAD_SIZE ((1 << CONFIG_KERNEL_STACK_ORDER) * PAGE_SIZE)
+/* how to get the thread information struct from C */
+static inline struct thread_info *current_thread_info(void)
+{
+	struct thread_info *ti;
+	unsigned long mask = THREAD_SIZE - 1;
+	ti = (struct thread_info *) (((unsigned long) &ti) & ~mask);
+	return ti;
+}
+
+#define THREAD_SIZE_ORDER CONFIG_KERNEL_STACK_ORDER
+
+#endif
+
+#define PREEMPT_ACTIVE		0x10000000
+
+#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
+#define TIF_SIGPENDING		1	/* signal pending */
+#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
+#define TIF_POLLING_NRFLAG      3       /* true if poll_idle() is polling
+					 * TIF_NEED_RESCHED
+					 */
+#define TIF_RESTART_BLOCK 	4
+#define TIF_MEMDIE	 	5
+#define TIF_SYSCALL_AUDIT	6
+#define TIF_RESTORE_SIGMASK	7
+#define TIF_FREEZE		16	/* is freezing for suspend */
+
+#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
+#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_POLLING_NRFLAG     (1 << TIF_POLLING_NRFLAG)
+#define _TIF_MEMDIE		(1 << TIF_MEMDIE)
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
+#define _TIF_FREEZE		(1 << TIF_FREEZE)
+
+#endif
diff --git a/arch/um/include/asm/timex.h b/arch/um/include/asm/timex.h
new file mode 100644
index 000000000000..0f4ada08f748
--- /dev/null
+++ b/arch/um/include/asm/timex.h
@@ -0,0 +1,13 @@
+#ifndef __UM_TIMEX_H
+#define __UM_TIMEX_H
+
+typedef unsigned long cycles_t;
+
+static inline cycles_t get_cycles (void)
+{
+	return 0;
+}
+
+#define CLOCK_TICK_RATE (HZ)
+
+#endif
diff --git a/arch/um/include/asm/tlb.h b/arch/um/include/asm/tlb.h
new file mode 100644
index 000000000000..5240fa1c5e08
--- /dev/null
+++ b/arch/um/include/asm/tlb.h
@@ -0,0 +1,127 @@
+#ifndef __UM_TLB_H
+#define __UM_TLB_H
+
+#include <linux/pagemap.h>
+#include <linux/swap.h>
+#include <asm/percpu.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+
+#define tlb_start_vma(tlb, vma) do { } while (0)
+#define tlb_end_vma(tlb, vma) do { } while (0)
+#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+
+/* struct mmu_gather is an opaque type used by the mm code for passing around
+ * any data needed by arch specific code for tlb_remove_page.
+ */
+struct mmu_gather {
+	struct mm_struct	*mm;
+	unsigned int		need_flush; /* Really unmapped some ptes? */
+	unsigned long		start;
+	unsigned long		end;
+	unsigned int		fullmm; /* non-zero means full mm flush */
+};
+
+/* Users of the generic TLB shootdown code must declare this storage space. */
+DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
+
+static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
+					  unsigned long address)
+{
+	if (tlb->start > address)
+		tlb->start = address;
+	if (tlb->end < address + PAGE_SIZE)
+		tlb->end = address + PAGE_SIZE;
+}
+
+static inline void init_tlb_gather(struct mmu_gather *tlb)
+{
+	tlb->need_flush = 0;
+
+	tlb->start = TASK_SIZE;
+	tlb->end = 0;
+
+	if (tlb->fullmm) {
+		tlb->start = 0;
+		tlb->end = TASK_SIZE;
+	}
+}
+
+/* tlb_gather_mmu
+ *	Return a pointer to an initialized struct mmu_gather.
+ */
+static inline struct mmu_gather *
+tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
+{
+	struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
+
+	tlb->mm = mm;
+	tlb->fullmm = full_mm_flush;
+
+	init_tlb_gather(tlb);
+
+	return tlb;
+}
+
+extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+			       unsigned long end);
+
+static inline void
+tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+{
+	if (!tlb->need_flush)
+		return;
+
+	flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end);
+	init_tlb_gather(tlb);
+}
+
+/* tlb_finish_mmu
+ *	Called at the end of the shootdown operation to free up any resources
+ *	that were required.
+ */
+static inline void
+tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
+{
+	tlb_flush_mmu(tlb, start, end);
+
+	/* keep the page table cache within bounds */
+	check_pgt_cache();
+
+	put_cpu_var(mmu_gathers);
+}
+
+/* tlb_remove_page
+ *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)),
+ *	while handling the additional races in SMP caused by other CPUs
+ *	caching valid mappings in their TLBs.
+ */
+static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
+{
+	tlb->need_flush = 1;
+	free_page_and_swap_cache(page);
+	return;
+}
+
+/**
+ * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
+ *
+ * Record the fact that pte's were really umapped in ->need_flush, so we can
+ * later optimise away the tlb invalidate.   This helps when userspace is
+ * unmapping already-unmapped pages, which happens quite a lot.
+ */
+#define tlb_remove_tlb_entry(tlb, ptep, address)		\
+	do {							\
+		tlb->need_flush = 1;				\
+		__tlb_remove_tlb_entry(tlb, ptep, address);	\
+	} while (0)
+
+#define pte_free_tlb(tlb, ptep) __pte_free_tlb(tlb, ptep)
+
+#define pud_free_tlb(tlb, pudp) __pud_free_tlb(tlb, pudp)
+
+#define pmd_free_tlb(tlb, pmdp) __pmd_free_tlb(tlb, pmdp)
+
+#define tlb_migrate_finish(mm) do {} while (0)
+
+#endif
diff --git a/arch/um/include/asm/tlbflush.h b/arch/um/include/asm/tlbflush.h
new file mode 100644
index 000000000000..614f2c091178
--- /dev/null
+++ b/arch/um/include/asm/tlbflush.h
@@ -0,0 +1,31 @@
+/*
+ * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_TLBFLUSH_H
+#define __UM_TLBFLUSH_H
+
+#include <linux/mm.h>
+
+/*
+ * TLB flushing:
+ *
+ *  - flush_tlb() flushes the current mm struct TLBs
+ *  - flush_tlb_all() flushes all processes TLBs
+ *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - flush_tlb_kernel_vm() flushes the kernel vm area
+ *  - flush_tlb_range(vma, start, end) flushes a range of pages
+ */
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_mm(struct mm_struct *mm);
+extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, 
+			    unsigned long end);
+extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long address);
+extern void flush_tlb_kernel_vm(void);
+extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
+extern void __flush_tlb_one(unsigned long addr);
+
+#endif
diff --git a/arch/um/include/asm/topology.h b/arch/um/include/asm/topology.h
new file mode 100644
index 000000000000..0905e4f21d42
--- /dev/null
+++ b/arch/um/include/asm/topology.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_UM_TOPOLOGY_H
+#define _ASM_UM_TOPOLOGY_H
+
+#include <asm-generic/topology.h>
+
+#endif
diff --git a/arch/um/include/asm/types.h b/arch/um/include/asm/types.h
new file mode 100644
index 000000000000..816e9590fc73
--- /dev/null
+++ b/arch/um/include/asm/types.h
@@ -0,0 +1,6 @@
+#ifndef __UM_TYPES_H
+#define __UM_TYPES_H
+
+#include "asm/arch/types.h"
+
+#endif
diff --git a/arch/um/include/asm/uaccess.h b/arch/um/include/asm/uaccess.h
new file mode 100644
index 000000000000..b9a895d6fa1d
--- /dev/null
+++ b/arch/um/include/asm/uaccess.h
@@ -0,0 +1,99 @@
+/* 
+ * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __UM_UACCESS_H
+#define __UM_UACCESS_H
+
+#include <asm/errno.h>
+#include <asm/processor.h>
+
+/* thread_info has a mm_segment_t in it, so put the definition up here */
+typedef struct {
+	unsigned long seg;
+} mm_segment_t;
+
+#include "linux/thread_info.h"
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+/*
+ * The fs value determines whether argument validity checking should be
+ * performed or not.  If get_fs() == USER_DS, checking is performed, with
+ * get_fs() == KERNEL_DS, checking is bypassed.
+ *
+ * For historical reasons, these macros are grossly misnamed.
+ */
+
+#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
+
+#define KERNEL_DS	MAKE_MM_SEG(0xFFFFFFFF)
+#define USER_DS		MAKE_MM_SEG(TASK_SIZE)
+
+#define get_ds()	(KERNEL_DS)
+#define get_fs()	(current_thread_info()->addr_limit)
+#define set_fs(x)	(current_thread_info()->addr_limit = (x))
+
+#define segment_eq(a, b) ((a).seg == (b).seg)
+
+#include "um_uaccess.h"
+
+#define __copy_from_user(to, from, n) copy_from_user(to, from, n)
+
+#define __copy_to_user(to, from, n) copy_to_user(to, from, n)
+
+#define __copy_to_user_inatomic __copy_to_user
+#define __copy_from_user_inatomic __copy_from_user
+
+#define __get_user(x, ptr) \
+({ \
+	const __typeof__(*(ptr)) __user *__private_ptr = (ptr);	\
+	__typeof__(x) __private_val;			\
+	int __private_ret = -EFAULT;			\
+	(x) = (__typeof__(*(__private_ptr)))0;				\
+	if (__copy_from_user((__force void *)&__private_val, (__private_ptr),\
+			     sizeof(*(__private_ptr))) == 0) {		\
+		(x) = (__typeof__(*(__private_ptr))) __private_val;	\
+		__private_ret = 0;					\
+	}								\
+	__private_ret;							\
+}) 
+
+#define get_user(x, ptr) \
+({ \
+        const __typeof__((*(ptr))) __user *private_ptr = (ptr); \
+        (access_ok(VERIFY_READ, private_ptr, sizeof(*private_ptr)) ? \
+	 __get_user(x, private_ptr) : ((x) = (__typeof__(*ptr))0, -EFAULT)); \
+})
+
+#define __put_user(x, ptr) \
+({ \
+        __typeof__(*(ptr)) __user *__private_ptr = ptr; \
+        __typeof__(*(__private_ptr)) __private_val; \
+        int __private_ret = -EFAULT; \
+        __private_val = (__typeof__(*(__private_ptr))) (x); \
+        if (__copy_to_user((__private_ptr), &__private_val, \
+			   sizeof(*(__private_ptr))) == 0) { \
+		__private_ret = 0; \
+	} \
+        __private_ret; \
+})
+
+#define put_user(x, ptr) \
+({ \
+        __typeof__(*(ptr)) __user *private_ptr = (ptr); \
+        (access_ok(VERIFY_WRITE, private_ptr, sizeof(*private_ptr)) ? \
+	 __put_user(x, private_ptr) : -EFAULT); \
+})
+
+#define strlen_user(str) strnlen_user(str, ~0U >> 1)
+
+struct exception_table_entry
+{
+        unsigned long insn;
+	unsigned long fixup;
+};
+
+#endif
diff --git a/arch/um/include/asm/ucontext.h b/arch/um/include/asm/ucontext.h
new file mode 100644
index 000000000000..5c96c0e607f0
--- /dev/null
+++ b/arch/um/include/asm/ucontext.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_UM_UCONTEXT_H
+#define _ASM_UM_UCONTEXT_H
+
+#include "asm/arch/ucontext.h"
+
+#endif
diff --git a/arch/um/include/asm/unaligned.h b/arch/um/include/asm/unaligned.h
new file mode 100644
index 000000000000..a47196974e39
--- /dev/null
+++ b/arch/um/include/asm/unaligned.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_UM_UNALIGNED_H
+#define _ASM_UM_UNALIGNED_H
+
+#include "asm/arch/unaligned.h"
+
+#endif /* _ASM_UM_UNALIGNED_H */
diff --git a/arch/um/include/asm/unistd.h b/arch/um/include/asm/unistd.h
new file mode 100644
index 000000000000..38bd9d94ee46
--- /dev/null
+++ b/arch/um/include/asm/unistd.h
@@ -0,0 +1,41 @@
+/* 
+ * Copyright (C) 2000 - 2004  Jeff Dike (jdike@karaya.com)
+ * Licensed under the GPL
+ */
+
+#ifndef _UM_UNISTD_H_
+#define _UM_UNISTD_H_
+
+#include <linux/syscalls.h>
+#include "linux/resource.h"
+#include "asm/uaccess.h"
+
+extern int um_execve(const char *file, char *const argv[], char *const env[]);
+
+#ifdef __KERNEL__
+/* We get __ARCH_WANT_OLD_STAT and __ARCH_WANT_STAT64 from the base arch */
+#define __ARCH_WANT_OLD_READDIR
+#define __ARCH_WANT_SYS_ALARM
+#define __ARCH_WANT_SYS_GETHOSTNAME
+#define __ARCH_WANT_SYS_PAUSE
+#define __ARCH_WANT_SYS_SGETMASK
+#define __ARCH_WANT_SYS_SIGNAL
+#define __ARCH_WANT_SYS_TIME
+#define __ARCH_WANT_SYS_UTIME
+#define __ARCH_WANT_SYS_WAITPID
+#define __ARCH_WANT_SYS_SOCKETCALL
+#define __ARCH_WANT_SYS_FADVISE64
+#define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
+#define __ARCH_WANT_SYS_NICE
+#define __ARCH_WANT_SYS_OLD_GETRLIMIT
+#define __ARCH_WANT_SYS_OLDUMOUNT
+#define __ARCH_WANT_SYS_SIGPENDING
+#define __ARCH_WANT_SYS_SIGPROCMASK
+#define __ARCH_WANT_SYS_RT_SIGACTION
+#define __ARCH_WANT_SYS_RT_SIGSUSPEND
+#endif
+
+#include "asm/arch/unistd.h"
+
+#endif /* _UM_UNISTD_H_*/
diff --git a/arch/um/include/asm/user.h b/arch/um/include/asm/user.h
new file mode 100644
index 000000000000..aae414ee1f5e
--- /dev/null
+++ b/arch/um/include/asm/user.h
@@ -0,0 +1,6 @@
+#ifndef __UM_USER_H
+#define __UM_USER_H
+
+#include "asm/arch/user.h"
+
+#endif
diff --git a/arch/um/include/asm/vga.h b/arch/um/include/asm/vga.h
new file mode 100644
index 000000000000..903a592b00d0
--- /dev/null
+++ b/arch/um/include/asm/vga.h
@@ -0,0 +1,6 @@
+#ifndef __UM_VGA_H
+#define __UM_VGA_H
+
+#include "asm/arch/vga.h"
+
+#endif
diff --git a/arch/um/include/asm/vm-flags-i386.h b/arch/um/include/asm/vm-flags-i386.h
new file mode 100644
index 000000000000..e0d24c568dbc
--- /dev/null
+++ b/arch/um/include/asm/vm-flags-i386.h
@@ -0,0 +1,14 @@
+/*
+ * Copyright (C) 2004 Jeff Dike (jdike@addtoit.com)
+ * Licensed under the GPL
+ */
+
+#ifndef __VM_FLAGS_I386_H
+#define __VM_FLAGS_I386_H
+
+#define VM_DATA_DEFAULT_FLAGS \
+	(VM_READ | VM_WRITE | \
+	((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
+		 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+#endif
diff --git a/arch/um/include/asm/vm-flags-x86_64.h b/arch/um/include/asm/vm-flags-x86_64.h
new file mode 100644
index 000000000000..3213edfa7888
--- /dev/null
+++ b/arch/um/include/asm/vm-flags-x86_64.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (C) 2004 Jeff Dike (jdike@addtoit.com)
+ * Copyright 2003 PathScale, Inc.
+ * Licensed under the GPL
+ */
+
+#ifndef __VM_FLAGS_X86_64_H
+#define __VM_FLAGS_X86_64_H
+
+#define __VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
+				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+#define __VM_STACK_FLAGS 	(VM_GROWSDOWN | VM_READ | VM_WRITE | \
+				 VM_EXEC | VM_MAYREAD | VM_MAYWRITE | \
+				 VM_MAYEXEC)
+
+extern unsigned long vm_stack_flags, vm_stack_flags32;
+extern unsigned long vm_data_default_flags, vm_data_default_flags32;
+extern unsigned long vm_force_exec32;
+
+#ifdef TIF_IA32
+#define VM_DATA_DEFAULT_FLAGS \
+	(test_thread_flag(TIF_IA32) ? vm_data_default_flags32 : \
+	  vm_data_default_flags)
+
+#define VM_STACK_DEFAULT_FLAGS \
+	(test_thread_flag(TIF_IA32) ? vm_stack_flags32 : vm_stack_flags)
+#endif
+
+#define VM_DATA_DEFAULT_FLAGS vm_data_default_flags
+
+#define VM_STACK_DEFAULT_FLAGS vm_stack_flags
+
+#endif
diff --git a/arch/um/include/asm/vm86.h b/arch/um/include/asm/vm86.h
new file mode 100644
index 000000000000..7801f82de1f4
--- /dev/null
+++ b/arch/um/include/asm/vm86.h
@@ -0,0 +1,6 @@
+#ifndef __UM_VM86_H
+#define __UM_VM86_H
+
+#include "asm/arch/vm86.h"
+
+#endif
diff --git a/arch/um/include/asm/xor.h b/arch/um/include/asm/xor.h
new file mode 100644
index 000000000000..a19db3e17241
--- /dev/null
+++ b/arch/um/include/asm/xor.h
@@ -0,0 +1,6 @@
+#ifndef __UM_XOR_H
+#define __UM_XOR_H
+
+#include "asm-generic/xor.h"
+
+#endif
diff --git a/include/asm-um/a.out-core.h b/include/asm-um/a.out-core.h
deleted file mode 100644
index 995643b18309..000000000000
--- a/include/asm-um/a.out-core.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* a.out coredump register dumper
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#ifndef __UM_A_OUT_CORE_H
-#define __UM_A_OUT_CORE_H
-
-#ifdef __KERNEL__
-
-#include <linux/user.h>
-
-/*
- * fill in the user structure for an a.out core dump
- */
-static inline void aout_dump_thread(struct pt_regs *regs, struct user *u)
-{
-}
-
-#endif /* __KERNEL__ */
-#endif /* __UM_A_OUT_CORE_H */
diff --git a/include/asm-um/a.out.h b/include/asm-um/a.out.h
deleted file mode 100644
index 754181ee8683..000000000000
--- a/include/asm-um/a.out.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/*
- * Copyright (C) 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_A_OUT_H
-#define __UM_A_OUT_H
-
-#include "asm/arch/a.out.h"
-
-#endif
diff --git a/include/asm-um/alternative-asm.h b/include/asm-um/alternative-asm.h
deleted file mode 100644
index 9aa9fa2402a4..000000000000
--- a/include/asm-um/alternative-asm.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_ALTERNATIVE_ASM_I
-#define __UM_ALTERNATIVE_ASM_I
-
-#include "asm/arch/alternative-asm.h"
-
-#endif
diff --git a/include/asm-um/alternative.h b/include/asm-um/alternative.h
deleted file mode 100644
index b6434396bd42..000000000000
--- a/include/asm-um/alternative.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_ALTERNATIVE_H
-#define __UM_ALTERNATIVE_H
-
-#include "asm/arch/alternative.h"
-
-#endif
diff --git a/include/asm-um/apic.h b/include/asm-um/apic.h
deleted file mode 100644
index 876dee84ab11..000000000000
--- a/include/asm-um/apic.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef __UM_APIC_H
-#define __UM_APIC_H
-
-#endif
diff --git a/include/asm-um/archparam-i386.h b/include/asm-um/archparam-i386.h
deleted file mode 100644
index 49e89b8d7e58..000000000000
--- a/include/asm-um/archparam-i386.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* 
- * Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_ARCHPARAM_I386_H
-#define __UM_ARCHPARAM_I386_H
-
-/********* Nothing for asm-um/hardirq.h **********/
-
-/********* Nothing for asm-um/hw_irq.h **********/
-
-/********* Nothing for asm-um/string.h **********/
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/include/asm-um/archparam-ppc.h b/include/asm-um/archparam-ppc.h
deleted file mode 100644
index 4269d8a37b4f..000000000000
--- a/include/asm-um/archparam-ppc.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef __UM_ARCHPARAM_PPC_H
-#define __UM_ARCHPARAM_PPC_H
-
-/********* Bits for asm-um/string.h **********/
-
-#define __HAVE_ARCH_STRRCHR
-
-#endif
diff --git a/include/asm-um/archparam-x86_64.h b/include/asm-um/archparam-x86_64.h
deleted file mode 100644
index 270ed9586b68..000000000000
--- a/include/asm-um/archparam-x86_64.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_ARCHPARAM_X86_64_H
-#define __UM_ARCHPARAM_X86_64_H
-
-
-/* No user-accessible fixmap addresses, i.e. vsyscall */
-#define FIXADDR_USER_START	0
-#define FIXADDR_USER_END	0
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/include/asm-um/asm.h b/include/asm-um/asm.h
deleted file mode 100644
index af1269a1e9eb..000000000000
--- a/include/asm-um/asm.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_ASM_H
-#define __UM_ASM_H
-
-#include "asm/arch/asm.h"
-
-#endif
diff --git a/include/asm-um/atomic.h b/include/asm-um/atomic.h
deleted file mode 100644
index b683f1034d1e..000000000000
--- a/include/asm-um/atomic.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef __UM_ATOMIC_H
-#define __UM_ATOMIC_H
-
-/* The i386 atomic.h calls printk, but doesn't include kernel.h, so we
- * include it here.
- */
-#include "linux/kernel.h"
-
-#include "asm/arch/atomic.h"
-
-#endif
diff --git a/include/asm-um/auxvec.h b/include/asm-um/auxvec.h
deleted file mode 100644
index 1e5e1c2fc9b1..000000000000
--- a/include/asm-um/auxvec.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef __UM_AUXVEC_H
-#define __UM_AUXVEC_H
-
-#endif
diff --git a/include/asm-um/bitops.h b/include/asm-um/bitops.h
deleted file mode 100644
index e4d38d437b97..000000000000
--- a/include/asm-um/bitops.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __UM_BITOPS_H
-#define __UM_BITOPS_H
-
-#ifndef _LINUX_BITOPS_H
-#error only <linux/bitops.h> can be included directly
-#endif
-
-#include "asm/arch/bitops.h"
-
-#endif
diff --git a/include/asm-um/boot.h b/include/asm-um/boot.h
deleted file mode 100644
index 09548c3e784e..000000000000
--- a/include/asm-um/boot.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_BOOT_H
-#define __UM_BOOT_H
-
-#include "asm/arch/boot.h"
-
-#endif
diff --git a/include/asm-um/bug.h b/include/asm-um/bug.h
deleted file mode 100644
index 9e33b864c359..000000000000
--- a/include/asm-um/bug.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_BUG_H
-#define __UM_BUG_H
-
-#include <asm-generic/bug.h>
-
-#endif
diff --git a/include/asm-um/bugs.h b/include/asm-um/bugs.h
deleted file mode 100644
index 6a72e240d5fc..000000000000
--- a/include/asm-um/bugs.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_BUGS_H
-#define __UM_BUGS_H
-
-void check_bugs(void);
-
-#endif
diff --git a/include/asm-um/byteorder.h b/include/asm-um/byteorder.h
deleted file mode 100644
index eee0a834f447..000000000000
--- a/include/asm-um/byteorder.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_BYTEORDER_H
-#define __UM_BYTEORDER_H
-
-#include "asm/arch/byteorder.h"
-
-#endif
diff --git a/include/asm-um/cache.h b/include/asm-um/cache.h
deleted file mode 100644
index 19e1bdd67416..000000000000
--- a/include/asm-um/cache.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef __UM_CACHE_H
-#define __UM_CACHE_H
-
-
-#if defined(CONFIG_UML_X86) && !defined(CONFIG_64BIT)
-# define L1_CACHE_SHIFT		(CONFIG_X86_L1_CACHE_SHIFT)
-#elif defined(CONFIG_UML_X86) /* 64-bit */
-# define L1_CACHE_SHIFT		6 /* Should be 7 on Intel */
-#else
-/* XXX: this was taken from x86, now it's completely random. Luckily only
- * affects SMP padding. */
-# define L1_CACHE_SHIFT		5
-#endif
-
-#define L1_CACHE_BYTES		(1 << L1_CACHE_SHIFT)
-
-#endif
diff --git a/include/asm-um/cacheflush.h b/include/asm-um/cacheflush.h
deleted file mode 100644
index 12e9d4b74c8f..000000000000
--- a/include/asm-um/cacheflush.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_CACHEFLUSH_H
-#define __UM_CACHEFLUSH_H
-
-#include "asm/arch/cacheflush.h"
-
-#endif
diff --git a/include/asm-um/calling.h b/include/asm-um/calling.h
deleted file mode 100644
index 0b2384cc99fd..000000000000
--- a/include/asm-um/calling.h
+++ /dev/null
@@ -1,9 +0,0 @@
-# Copyright 2003 - 2004 Pathscale, Inc
-# Released under the GPL
-
-#ifndef __UM_CALLING_H /* XXX x86_64 */
-#define __UM_CALLING_H
-
-#include "asm/arch/calling.h"
-
-#endif
diff --git a/include/asm-um/checksum.h b/include/asm-um/checksum.h
deleted file mode 100644
index 5b501361e361..000000000000
--- a/include/asm-um/checksum.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_CHECKSUM_H
-#define __UM_CHECKSUM_H
-
-#include "sysdep/checksum.h"
-
-#endif
diff --git a/include/asm-um/cmpxchg.h b/include/asm-um/cmpxchg.h
deleted file mode 100644
index 529376a99885..000000000000
--- a/include/asm-um/cmpxchg.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_CMPXCHG_H
-#define __UM_CMPXCHG_H
-
-#include "asm/arch/cmpxchg.h"
-
-#endif
diff --git a/include/asm-um/cobalt.h b/include/asm-um/cobalt.h
deleted file mode 100644
index f813a684be98..000000000000
--- a/include/asm-um/cobalt.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_COBALT_H
-#define __UM_COBALT_H
-
-#include "asm/arch/cobalt.h"
-
-#endif
diff --git a/include/asm-um/common.lds.S b/include/asm-um/common.lds.S
deleted file mode 100644
index cb0248616d49..000000000000
--- a/include/asm-um/common.lds.S
+++ /dev/null
@@ -1,130 +0,0 @@
-#include <asm-generic/vmlinux.lds.h>
-
-  .fini      : { *(.fini)    } =0x9090
-  _etext = .;
-  PROVIDE (etext = .);
-
-  . = ALIGN(4096);
-  _sdata = .;
-  PROVIDE (sdata = .);
-
-  RODATA
-
-  .unprotected : { *(.unprotected) }
-  . = ALIGN(4096);
-  PROVIDE (_unprotected_end = .);
-
-  . = ALIGN(4096);
-  .note : { *(.note.*) }
-  __ex_table : {
-	__start___ex_table = .;
-	*(__ex_table)
-	__stop___ex_table = .;
-  }
-
-  BUG_TABLE
-
-  .uml.setup.init : {
-	__uml_setup_start = .;
-	*(.uml.setup.init)
-	__uml_setup_end = .;
-  }
-	
-  .uml.help.init : {
-	__uml_help_start = .;
-	*(.uml.help.init)
-	__uml_help_end = .;
-  }
-	
-  .uml.postsetup.init : {
-	__uml_postsetup_start = .;
-	*(.uml.postsetup.init)
-	__uml_postsetup_end = .;
-  }
-	
-  .init.setup : {
-	__setup_start = .;
-	*(.init.setup)
-	__setup_end = .;
-  }
-
-  . = ALIGN(32);
-  .data.percpu : {
-	__per_cpu_start = . ;
-	*(.data.percpu)
-	__per_cpu_end = . ;
-  }
-	
-  .initcall.init : {
-	__initcall_start = .;
-	INITCALLS
-	__initcall_end = .;
-  }
-
-  .con_initcall.init : {
-	__con_initcall_start = .;
-	*(.con_initcall.init)
-	__con_initcall_end = .;
-  }
-
-  .uml.initcall.init : {
-	__uml_initcall_start = .;
-	*(.uml.initcall.init)
-	__uml_initcall_end = .;
-  }
-  __init_end = .;
-
-  SECURITY_INIT
-
-  .exitcall : {
-	__exitcall_begin = .;
-	*(.exitcall.exit)
-	__exitcall_end = .;
-  }
-
-  .uml.exitcall : {
-	__uml_exitcall_begin = .;
-	*(.uml.exitcall.exit)
-	__uml_exitcall_end = .;
-  }
-
-  . = ALIGN(4);
-  .altinstructions : {
-	__alt_instructions = .;
-	*(.altinstructions)
-	__alt_instructions_end = .;
-  }
-  .altinstr_replacement : { *(.altinstr_replacement) }
-  /* .exit.text is discard at runtime, not link time, to deal with references
-     from .altinstructions and .eh_frame */
-  .exit.text : { *(.exit.text) }
-  .exit.data : { *(.exit.data) }
-
-  .preinit_array : {
-	__preinit_array_start = .;
-	*(.preinit_array)
-	__preinit_array_end = .;
-  }
-  .init_array : {
-	__init_array_start = .;
-	*(.init_array)
-	__init_array_end = .;
-  }
-  .fini_array : {
-	__fini_array_start = .;
-	*(.fini_array)
-	__fini_array_end = .;
-  }
-
-   . = ALIGN(4096);
-  .init.ramfs : {
-	__initramfs_start = .;
-	*(.init.ramfs)
-	__initramfs_end = .;
-  }
-
-  /* Sections to be discarded */
-  /DISCARD/ : {
- 	*(.exitcall.exit)
-  }
-
diff --git a/include/asm-um/cpufeature.h b/include/asm-um/cpufeature.h
deleted file mode 100644
index fb7bd42a4d96..000000000000
--- a/include/asm-um/cpufeature.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_CPUFEATURE_H
-#define __UM_CPUFEATURE_H
-
-#include "asm/arch/cpufeature.h"
-
-#endif
diff --git a/include/asm-um/cputime.h b/include/asm-um/cputime.h
deleted file mode 100644
index c84acbadfa2f..000000000000
--- a/include/asm-um/cputime.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_CPUTIME_H
-#define __UM_CPUTIME_H
-
-#include <asm-generic/cputime.h>
-
-#endif /* __UM_CPUTIME_H */
diff --git a/include/asm-um/current.h b/include/asm-um/current.h
deleted file mode 100644
index c2191d9aa03d..000000000000
--- a/include/asm-um/current.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/*
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_CURRENT_H
-#define __UM_CURRENT_H
-
-#include "linux/thread_info.h"
-
-#define current (current_thread_info()->task)
-
-#endif
diff --git a/include/asm-um/delay.h b/include/asm-um/delay.h
deleted file mode 100644
index c71e32b6741e..000000000000
--- a/include/asm-um/delay.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef __UM_DELAY_H
-#define __UM_DELAY_H
-
-#define MILLION 1000000
-
-/* Undefined on purpose */
-extern void __bad_udelay(void);
-
-extern void __udelay(unsigned long usecs);
-extern void __delay(unsigned long loops);
-
-#define udelay(n) ((__builtin_constant_p(n) && (n) > 20000) ? \
-	__bad_udelay() : __udelay(n))
-
-/* It appears that ndelay is not used at all for UML, and has never been
- * implemented. */
-extern void __unimplemented_ndelay(void);
-#define ndelay(n) __unimplemented_ndelay()
-
-#endif
diff --git a/include/asm-um/desc.h b/include/asm-um/desc.h
deleted file mode 100644
index 4ec34a51b62c..000000000000
--- a/include/asm-um/desc.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __UM_DESC_H
-#define __UM_DESC_H
-
-/* Taken from asm-i386/desc.h, it's the only thing we need. The rest wouldn't
- * compile, and has never been used. */
-#define LDT_empty(info) (\
-	(info)->base_addr	== 0	&& \
-	(info)->limit		== 0	&& \
-	(info)->contents	== 0	&& \
-	(info)->read_exec_only	== 1	&& \
-	(info)->seg_32bit	== 0	&& \
-	(info)->limit_in_pages	== 0	&& \
-	(info)->seg_not_present	== 1	&& \
-	(info)->useable		== 0	)
-
-#endif
diff --git a/include/asm-um/device.h b/include/asm-um/device.h
deleted file mode 100644
index d8f9872b0e2d..000000000000
--- a/include/asm-um/device.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/*
- * Arch specific extensions to struct device
- *
- * This file is released under the GPLv2
- */
-#include <asm-generic/device.h>
-
diff --git a/include/asm-um/div64.h b/include/asm-um/div64.h
deleted file mode 100644
index 1e17f7409cab..000000000000
--- a/include/asm-um/div64.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _UM_DIV64_H
-#define _UM_DIV64_H
-
-#include "asm/arch/div64.h"
-
-#endif
diff --git a/include/asm-um/dma-mapping.h b/include/asm-um/dma-mapping.h
deleted file mode 100644
index 90fc708b320e..000000000000
--- a/include/asm-um/dma-mapping.h
+++ /dev/null
@@ -1,128 +0,0 @@
-#ifndef _ASM_DMA_MAPPING_H
-#define _ASM_DMA_MAPPING_H
-
-#include <asm/scatterlist.h>
-
-static inline int
-dma_supported(struct device *dev, u64 mask)
-{
-	BUG();
-	return(0);
-}
-
-static inline int
-dma_set_mask(struct device *dev, u64 dma_mask)
-{
-	BUG();
-	return(0);
-}
-
-static inline void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		   gfp_t flag)
-{
-	BUG();
-	return((void *) 0);
-}
-
-static inline void
-dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
-		  dma_addr_t dma_handle)
-{
-	BUG();
-}
-
-static inline dma_addr_t
-dma_map_single(struct device *dev, void *cpu_addr, size_t size,
-	       enum dma_data_direction direction)
-{
-	BUG();
-	return(0);
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		 enum dma_data_direction direction)
-{
-	BUG();
-}
-
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size,
-	     enum dma_data_direction direction)
-{
-	BUG();
-	return(0);
-}
-
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t dma_address, size_t size,
-	       enum dma_data_direction direction)
-{
-	BUG();
-}
-
-static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-	   enum dma_data_direction direction)
-{
-	BUG();
-	return(0);
-}
-
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
-	     enum dma_data_direction direction)
-{
-	BUG();
-}
-
-static inline void
-dma_sync_single(struct device *dev, dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	BUG();
-}
-
-static inline void
-dma_sync_sg(struct device *dev, struct scatterlist *sg, int nelems,
-	    enum dma_data_direction direction)
-{
-	BUG();
-}
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-#define dma_is_consistent(d, h) (1)
-
-static inline int
-dma_get_cache_alignment(void)
-{
-	BUG();
-	return(0);
-}
-
-static inline void
-dma_sync_single_range(struct device *dev, dma_addr_t dma_handle,
-		      unsigned long offset, size_t size,
-		      enum dma_data_direction direction)
-{
-	BUG();
-}
-
-static inline void
-dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	       enum dma_data_direction direction)
-{
-	BUG();
-}
-
-static inline int
-dma_mapping_error(struct device *dev, dma_addr_t dma_handle)
-{
-	BUG();
-	return 0;
-}
-
-#endif
diff --git a/include/asm-um/dma.h b/include/asm-um/dma.h
deleted file mode 100644
index 9f6139a8a525..000000000000
--- a/include/asm-um/dma.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __UM_DMA_H
-#define __UM_DMA_H
-
-#include "asm/io.h"
-
-extern unsigned long uml_physmem;
-
-#define MAX_DMA_ADDRESS (uml_physmem)
-
-#endif
diff --git a/include/asm-um/dwarf2.h b/include/asm-um/dwarf2.h
deleted file mode 100644
index d1a02e762931..000000000000
--- a/include/asm-um/dwarf2.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* Copyright 2003 - 2004 Pathscale, Inc
- * Released under the GPL
- */
-
-/* Needed on x86_64 by thunk.S */
-#ifndef __UM_DWARF2_H
-#define __UM_DWARF2_H
-
-#include "asm/arch/dwarf2.h"
-
-#endif
diff --git a/include/asm-um/elf-i386.h b/include/asm-um/elf-i386.h
deleted file mode 100644
index d0da9d7c5371..000000000000
--- a/include/asm-um/elf-i386.h
+++ /dev/null
@@ -1,163 +0,0 @@
-/*
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-#ifndef __UM_ELF_I386_H
-#define __UM_ELF_I386_H
-
-#include <asm/user.h>
-#include "skas.h"
-
-#define R_386_NONE	0
-#define R_386_32	1
-#define R_386_PC32	2
-#define R_386_GOT32	3
-#define R_386_PLT32	4
-#define R_386_COPY	5
-#define R_386_GLOB_DAT	6
-#define R_386_JMP_SLOT	7
-#define R_386_RELATIVE	8
-#define R_386_GOTOFF	9
-#define R_386_GOTPC	10
-#define R_386_NUM	11
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_i387_struct elf_fpregset_t;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) \
-	(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
-
-#define ELF_CLASS	ELFCLASS32
-#define ELF_DATA        ELFDATA2LSB
-#define ELF_ARCH        EM_386
-
-#define ELF_PLAT_INIT(regs, load_addr) do { \
-	PT_REGS_EBX(regs) = 0; \
-	PT_REGS_ECX(regs) = 0; \
-	PT_REGS_EDX(regs) = 0; \
-	PT_REGS_ESI(regs) = 0; \
-	PT_REGS_EDI(regs) = 0; \
-	PT_REGS_EBP(regs) = 0; \
-	PT_REGS_EAX(regs) = 0; \
-} while (0)
-
-#define USE_ELF_CORE_DUMP
-#define ELF_EXEC_PAGESIZE 4096
-
-#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3)
-
-/* Shamelessly stolen from include/asm-i386/elf.h */
-
-#define ELF_CORE_COPY_REGS(pr_reg, regs) do {	\
-	pr_reg[0] = PT_REGS_EBX(regs);		\
-	pr_reg[1] = PT_REGS_ECX(regs);		\
-	pr_reg[2] = PT_REGS_EDX(regs);		\
-	pr_reg[3] = PT_REGS_ESI(regs);		\
-	pr_reg[4] = PT_REGS_EDI(regs);		\
-	pr_reg[5] = PT_REGS_EBP(regs);		\
-	pr_reg[6] = PT_REGS_EAX(regs);		\
-	pr_reg[7] = PT_REGS_DS(regs);		\
-	pr_reg[8] = PT_REGS_ES(regs);		\
-	/* fake once used fs and gs selectors? */	\
-	pr_reg[9] = PT_REGS_DS(regs);		\
-	pr_reg[10] = PT_REGS_DS(regs);		\
-	pr_reg[11] = PT_REGS_SYSCALL_NR(regs);	\
-	pr_reg[12] = PT_REGS_IP(regs);		\
-	pr_reg[13] = PT_REGS_CS(regs);		\
-	pr_reg[14] = PT_REGS_EFLAGS(regs);	\
-	pr_reg[15] = PT_REGS_SP(regs);		\
-	pr_reg[16] = PT_REGS_SS(regs);		\
-} while (0);
-
-extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
-
-#define ELF_CORE_COPY_FPREGS(t, fpu) elf_core_copy_fpregs(t, fpu)
-
-extern long elf_aux_hwcap;
-#define ELF_HWCAP (elf_aux_hwcap)
-
-extern char * elf_aux_platform;
-#define ELF_PLATFORM (elf_aux_platform)
-
-#define SET_PERSONALITY(ex) do { } while (0)
-
-extern unsigned long vsyscall_ehdr;
-extern unsigned long vsyscall_end;
-extern unsigned long __kernel_vsyscall;
-
-#define VSYSCALL_BASE vsyscall_ehdr
-#define VSYSCALL_END vsyscall_end
-
-/*
- * This is the range that is readable by user mode, and things
- * acting like user mode such as get_user_pages.
- */
-#define FIXADDR_USER_START      VSYSCALL_BASE
-#define FIXADDR_USER_END        VSYSCALL_END
-
-/*
- * Architecture-neutral AT_ values in 0-17, leave some room
- * for more of them, start the x86-specific ones at 32.
- */
-#define AT_SYSINFO		32
-#define AT_SYSINFO_EHDR		33
-
-#define ARCH_DLINFO						\
-do {								\
-	if ( vsyscall_ehdr ) {					\
-		NEW_AUX_ENT(AT_SYSINFO,	__kernel_vsyscall);	\
-		NEW_AUX_ENT(AT_SYSINFO_EHDR, vsyscall_ehdr);	\
-	}							\
-} while (0)
-
-/*
- * These macros parameterize elf_core_dump in fs/binfmt_elf.c to write out
- * extra segments containing the vsyscall DSO contents.  Dumping its
- * contents makes post-mortem fully interpretable later without matching up
- * the same kernel and hardware config to see what PC values meant.
- * Dumping its extra ELF program headers includes all the other information
- * a debugger needs to easily find how the vsyscall DSO was being used.
- */
-#define ELF_CORE_EXTRA_PHDRS						      \
-	(vsyscall_ehdr ? (((struct elfhdr *)vsyscall_ehdr)->e_phnum) : 0 )
-
-#define ELF_CORE_WRITE_EXTRA_PHDRS					      \
-if ( vsyscall_ehdr ) {							      \
-	const struct elfhdr *const ehdrp = (struct elfhdr *)vsyscall_ehdr;    \
-	const struct elf_phdr *const phdrp =				      \
-		(const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff);   \
-	int i;								      \
-	Elf32_Off ofs = 0;						      \
-	for (i = 0; i < ehdrp->e_phnum; ++i) {				      \
-		struct elf_phdr phdr = phdrp[i];			      \
-		if (phdr.p_type == PT_LOAD) {				      \
-			ofs = phdr.p_offset = offset;			      \
-			offset += phdr.p_filesz;			      \
-		}							      \
-		else							      \
-			phdr.p_offset += ofs;				      \
-		phdr.p_paddr = 0; /* match other core phdrs */		      \
-		DUMP_WRITE(&phdr, sizeof(phdr));			      \
-	}								      \
-}
-#define ELF_CORE_WRITE_EXTRA_DATA					      \
-if ( vsyscall_ehdr ) {							      \
-	const struct elfhdr *const ehdrp = (struct elfhdr *)vsyscall_ehdr;    \
-	const struct elf_phdr *const phdrp =				      \
-		(const struct elf_phdr *) (vsyscall_ehdr + ehdrp->e_phoff);   \
-	int i;								      \
-	for (i = 0; i < ehdrp->e_phnum; ++i) {				      \
-		if (phdrp[i].p_type == PT_LOAD)				      \
-			DUMP_WRITE((void *) phdrp[i].p_vaddr,		      \
-				   phdrp[i].p_filesz);			      \
-	}								      \
-}
-
-#endif
diff --git a/include/asm-um/elf-ppc.h b/include/asm-um/elf-ppc.h
deleted file mode 100644
index af9463cd8ce5..000000000000
--- a/include/asm-um/elf-ppc.h
+++ /dev/null
@@ -1,53 +0,0 @@
-#ifndef __UM_ELF_PPC_H
-#define __UM_ELF_PPC_H
-
-
-extern long elf_aux_hwcap;
-#define ELF_HWCAP (elf_aux_hwcap)
-
-#define SET_PERSONALITY(ex) do ; while(0)
-
-#define ELF_EXEC_PAGESIZE 4096
-
-#define elf_check_arch(x) (1)
-
-#ifdef CONFIG_64BIT
-#define ELF_CLASS ELFCLASS64
-#else
-#define ELF_CLASS ELFCLASS32
-#endif
-
-#define USE_ELF_CORE_DUMP
-
-#define R_386_NONE	0
-#define R_386_32	1
-#define R_386_PC32	2
-#define R_386_GOT32	3
-#define R_386_PLT32	4
-#define R_386_COPY	5
-#define R_386_GLOB_DAT	6
-#define R_386_JMP_SLOT	7
-#define R_386_RELATIVE	8
-#define R_386_GOTOFF	9
-#define R_386_GOTPC	10
-#define R_386_NUM	11
-
-#define ELF_PLATFORM (0)
-
-#define ELF_ET_DYN_BASE (0x08000000)
-
-/* the following stolen from asm-ppc/elf.h */
-#define ELF_NGREG	48	/* includes nip, msr, lr, etc. */
-#define ELF_NFPREG	33	/* includes fpscr */
-/* General registers */
-typedef unsigned long elf_greg_t;
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-/* Floating point registers */
-typedef double elf_fpreg_t;
-typedef elf_fpreg_t elf_fpregset_t[ELF_NFPREG];
-
-#define ELF_DATA        ELFDATA2MSB
-#define ELF_ARCH	EM_PPC
-
-#endif
diff --git a/include/asm-um/elf-x86_64.h b/include/asm-um/elf-x86_64.h
deleted file mode 100644
index 6e8a9195e952..000000000000
--- a/include/asm-um/elf-x86_64.h
+++ /dev/null
@@ -1,119 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- * Copyright (C) 2003 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- *
- * Licensed under the GPL
- */
-#ifndef __UM_ELF_X86_64_H
-#define __UM_ELF_X86_64_H
-
-#include <asm/user.h>
-#include "skas.h"
-
-/* x86-64 relocation types, taken from asm-x86_64/elf.h */
-#define R_X86_64_NONE		0	/* No reloc */
-#define R_X86_64_64		1	/* Direct 64 bit  */
-#define R_X86_64_PC32		2	/* PC relative 32 bit signed */
-#define R_X86_64_GOT32		3	/* 32 bit GOT entry */
-#define R_X86_64_PLT32		4	/* 32 bit PLT address */
-#define R_X86_64_COPY		5	/* Copy symbol at runtime */
-#define R_X86_64_GLOB_DAT	6	/* Create GOT entry */
-#define R_X86_64_JUMP_SLOT	7	/* Create PLT entry */
-#define R_X86_64_RELATIVE	8	/* Adjust by program base */
-#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative
-					   offset to GOT */
-#define R_X86_64_32		10	/* Direct 32 bit zero extended */
-#define R_X86_64_32S		11	/* Direct 32 bit sign extended */
-#define R_X86_64_16		12	/* Direct 16 bit zero extended */
-#define R_X86_64_PC16		13	/* 16 bit sign extended pc relative */
-#define R_X86_64_8		14	/* Direct 8 bit sign extended  */
-#define R_X86_64_PC8		15	/* 8 bit sign extended pc relative */
-
-#define R_X86_64_NUM		16
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof (struct user_regs_struct) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_i387_struct elf_fpregset_t;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) \
-	((x)->e_machine == EM_X86_64)
-
-#define ELF_CLASS	ELFCLASS64
-#define ELF_DATA        ELFDATA2LSB
-#define ELF_ARCH        EM_X86_64
-
-#define ELF_PLAT_INIT(regs, load_addr)    do { \
-	PT_REGS_RBX(regs) = 0; \
-	PT_REGS_RCX(regs) = 0; \
-	PT_REGS_RDX(regs) = 0; \
-	PT_REGS_RSI(regs) = 0; \
-	PT_REGS_RDI(regs) = 0; \
-	PT_REGS_RBP(regs) = 0; \
-	PT_REGS_RAX(regs) = 0; \
-	PT_REGS_R8(regs) = 0; \
-	PT_REGS_R9(regs) = 0; \
-	PT_REGS_R10(regs) = 0; \
-	PT_REGS_R11(regs) = 0; \
-	PT_REGS_R12(regs) = 0; \
-	PT_REGS_R13(regs) = 0; \
-	PT_REGS_R14(regs) = 0; \
-	PT_REGS_R15(regs) = 0; \
-} while (0)
-
-#define ELF_CORE_COPY_REGS(pr_reg, regs)		\
-	(pr_reg)[0] = (regs)->regs.gp[0];			\
-	(pr_reg)[1] = (regs)->regs.gp[1];			\
-	(pr_reg)[2] = (regs)->regs.gp[2];			\
-	(pr_reg)[3] = (regs)->regs.gp[3];			\
-	(pr_reg)[4] = (regs)->regs.gp[4];			\
-	(pr_reg)[5] = (regs)->regs.gp[5];			\
-	(pr_reg)[6] = (regs)->regs.gp[6];			\
-	(pr_reg)[7] = (regs)->regs.gp[7];			\
-	(pr_reg)[8] = (regs)->regs.gp[8];			\
-	(pr_reg)[9] = (regs)->regs.gp[9];			\
-	(pr_reg)[10] = (regs)->regs.gp[10];			\
-	(pr_reg)[11] = (regs)->regs.gp[11];			\
-	(pr_reg)[12] = (regs)->regs.gp[12];			\
-	(pr_reg)[13] = (regs)->regs.gp[13];			\
-	(pr_reg)[14] = (regs)->regs.gp[14];			\
-	(pr_reg)[15] = (regs)->regs.gp[15];			\
-	(pr_reg)[16] = (regs)->regs.gp[16];			\
-	(pr_reg)[17] = (regs)->regs.gp[17];			\
-	(pr_reg)[18] = (regs)->regs.gp[18];			\
-	(pr_reg)[19] = (regs)->regs.gp[19];			\
-	(pr_reg)[20] = (regs)->regs.gp[20];			\
-	(pr_reg)[21] = current->thread.arch.fs;			\
-	(pr_reg)[22] = 0;					\
-	(pr_reg)[23] = 0;					\
-	(pr_reg)[24] = 0;					\
-	(pr_reg)[25] = 0;					\
-	(pr_reg)[26] = 0;
-
-extern int elf_core_copy_fpregs(struct task_struct *t, elf_fpregset_t *fpu);
-
-#define ELF_CORE_COPY_FPREGS(t, fpu) elf_core_copy_fpregs(t, fpu)
-
-#ifdef TIF_IA32 /* XXX */
-#error XXX, indeed
-        clear_thread_flag(TIF_IA32);
-#endif
-
-#define USE_ELF_CORE_DUMP
-#define ELF_EXEC_PAGESIZE 4096
-
-#define ELF_ET_DYN_BASE (2 * TASK_SIZE / 3)
-
-extern long elf_aux_hwcap;
-#define ELF_HWCAP (elf_aux_hwcap)
-
-#define ELF_PLATFORM "x86_64"
-
-#define SET_PERSONALITY(ex) do ; while(0)
-
-#endif
diff --git a/include/asm-um/emergency-restart.h b/include/asm-um/emergency-restart.h
deleted file mode 100644
index 108d8c48e42e..000000000000
--- a/include/asm-um/emergency-restart.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_EMERGENCY_RESTART_H
-#define _ASM_EMERGENCY_RESTART_H
-
-#include <asm-generic/emergency-restart.h>
-
-#endif /* _ASM_EMERGENCY_RESTART_H */
diff --git a/include/asm-um/errno.h b/include/asm-um/errno.h
deleted file mode 100644
index b7a9e37fd8d8..000000000000
--- a/include/asm-um/errno.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_ERRNO_H
-#define __UM_ERRNO_H
-
-#include "asm/arch/errno.h"
-
-#endif
diff --git a/include/asm-um/fcntl.h b/include/asm-um/fcntl.h
deleted file mode 100644
index 812a65446d92..000000000000
--- a/include/asm-um/fcntl.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_FCNTL_H
-#define __UM_FCNTL_H
-
-#include "asm/arch/fcntl.h"
-
-#endif
diff --git a/include/asm-um/fixmap.h b/include/asm-um/fixmap.h
deleted file mode 100644
index 9d2be52b8655..000000000000
--- a/include/asm-um/fixmap.h
+++ /dev/null
@@ -1,98 +0,0 @@
-#ifndef __UM_FIXMAP_H
-#define __UM_FIXMAP_H
-
-#include <asm/processor.h>
-#include <asm/system.h>
-#include <asm/kmap_types.h>
-#include <asm/archparam.h>
-#include <asm/page.h>
-
-/*
- * Here we define all the compile-time 'special' virtual
- * addresses. The point is to have a constant address at
- * compile time, but to set the physical address only
- * in the boot process. We allocate these special  addresses
- * from the end of virtual memory (0xfffff000) backwards.
- * Also this lets us do fail-safe vmalloc(), we
- * can guarantee that these special addresses and
- * vmalloc()-ed addresses never overlap.
- *
- * these 'compile-time allocated' memory buffers are
- * fixed-size 4k pages. (or larger if used with an increment
- * highger than 1) use fixmap_set(idx,phys) to associate
- * physical memory with fixmap indices.
- *
- * TLB entries of such buffers will not be flushed across
- * task switches.
- */
-
-/*
- * on UP currently we will have no trace of the fixmap mechanizm,
- * no page table allocations, etc. This might change in the
- * future, say framebuffers for the console driver(s) could be
- * fix-mapped?
- */
-enum fixed_addresses {
-#ifdef CONFIG_HIGHMEM
-	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
-	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
-#endif
-	__end_of_fixed_addresses
-};
-
-extern void __set_fixmap (enum fixed_addresses idx,
-			  unsigned long phys, pgprot_t flags);
-
-#define set_fixmap(idx, phys) \
-		__set_fixmap(idx, phys, PAGE_KERNEL)
-/*
- * Some hardware wants to get fixmapped without caching.
- */
-#define set_fixmap_nocache(idx, phys) \
-		__set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
-/*
- * used by vmalloc.c.
- *
- * Leave one empty page between vmalloc'ed areas and
- * the start of the fixmap, and leave one page empty
- * at the top of mem..
- */
-
-#define FIXADDR_TOP	(TASK_SIZE - 2 * PAGE_SIZE)
-#define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
-
-#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
-#define __virt_to_fix(x)      ((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
-
-extern void __this_fixmap_does_not_exist(void);
-
-/*
- * 'index to address' translation. If anyone tries to use the idx
- * directly without tranlation, we catch the bug with a NULL-deference
- * kernel oops. Illegal ranges of incoming indices are caught too.
- */
-static inline unsigned long fix_to_virt(const unsigned int idx)
-{
-	/*
-	 * this branch gets completely eliminated after inlining,
-	 * except when someone tries to use fixaddr indices in an
-	 * illegal way. (such as mixing up address types or using
-	 * out-of-range indices).
-	 *
-	 * If it doesn't get removed, the linker will complain
-	 * loudly with a reasonably clear error message..
-	 */
-	if (idx >= __end_of_fixed_addresses)
-		__this_fixmap_does_not_exist();
-
-        return __fix_to_virt(idx);
-}
-
-static inline unsigned long virt_to_fix(const unsigned long vaddr)
-{
-      BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
-      return __virt_to_fix(vaddr);
-}
-
-#endif
diff --git a/include/asm-um/floppy.h b/include/asm-um/floppy.h
deleted file mode 100644
index 453e7415fb6f..000000000000
--- a/include/asm-um/floppy.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_FLOPPY_H
-#define __UM_FLOPPY_H
-
-#include "asm/arch/floppy.h"
-
-#endif
diff --git a/include/asm-um/frame.h b/include/asm-um/frame.h
deleted file mode 100644
index 8a8c1cb415b4..000000000000
--- a/include/asm-um/frame.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_FRAME_I
-#define __UM_FRAME_I
-
-#include "asm/arch/frame.h"
-
-#endif
diff --git a/include/asm-um/futex.h b/include/asm-um/futex.h
deleted file mode 100644
index 6a332a9f099c..000000000000
--- a/include/asm-um/futex.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_FUTEX_H
-#define _ASM_FUTEX_H
-
-#include <asm-generic/futex.h>
-
-#endif
diff --git a/include/asm-um/hardirq.h b/include/asm-um/hardirq.h
deleted file mode 100644
index 313ebb8a2566..000000000000
--- a/include/asm-um/hardirq.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* (c) 2004 cw@f00f.org, GPLv2 blah blah */
-
-#ifndef __ASM_UM_HARDIRQ_H
-#define __ASM_UM_HARDIRQ_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-/* NOTE: When SMP works again we might want to make this
- * ____cacheline_aligned or maybe use per_cpu state? --cw */
-typedef struct {
-	unsigned int __softirq_pending;
-} irq_cpustat_t;
-
-#include <linux/irq_cpustat.h>
-
-/* As this would be very strange for UML to get we BUG() after the
- * printk. */
-static inline void ack_bad_irq(unsigned int irq)
-{
-	printk(KERN_ERR "unexpected IRQ %02x\n", irq);
-	BUG();
-}
-
-#endif /* __ASM_UM_HARDIRQ_H */
diff --git a/include/asm-um/highmem.h b/include/asm-um/highmem.h
deleted file mode 100644
index 36974cb8abc7..000000000000
--- a/include/asm-um/highmem.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __UM_HIGHMEM_H
-#define __UM_HIGHMEM_H
-
-#include "asm/page.h"
-#include "asm/fixmap.h"
-#include "asm/arch/highmem.h"
-
-#undef PKMAP_BASE
-
-#define PKMAP_BASE ((FIXADDR_START - LAST_PKMAP * PAGE_SIZE) & PMD_MASK)
-
-#endif
diff --git a/include/asm-um/host_ldt-i386.h b/include/asm-um/host_ldt-i386.h
deleted file mode 100644
index b27cb0a9dd30..000000000000
--- a/include/asm-um/host_ldt-i386.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef __ASM_HOST_LDT_I386_H
-#define __ASM_HOST_LDT_I386_H
-
-#include "asm/arch/ldt.h"
-
-/*
- * macros stolen from include/asm-i386/desc.h
- */
-#define LDT_entry_a(info) \
-	((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
-
-#define LDT_entry_b(info) \
-	(((info)->base_addr & 0xff000000) | \
-	(((info)->base_addr & 0x00ff0000) >> 16) | \
-	((info)->limit & 0xf0000) | \
-	(((info)->read_exec_only ^ 1) << 9) | \
-	((info)->contents << 10) | \
-	(((info)->seg_not_present ^ 1) << 15) | \
-	((info)->seg_32bit << 22) | \
-	((info)->limit_in_pages << 23) | \
-	((info)->useable << 20) | \
-	0x7000)
-
-#define LDT_empty(info) (\
-	(info)->base_addr	== 0	&& \
-	(info)->limit		== 0	&& \
-	(info)->contents	== 0	&& \
-	(info)->read_exec_only	== 1	&& \
-	(info)->seg_32bit	== 0	&& \
-	(info)->limit_in_pages	== 0	&& \
-	(info)->seg_not_present	== 1	&& \
-	(info)->useable		== 0	)
-
-#endif
diff --git a/include/asm-um/host_ldt-x86_64.h b/include/asm-um/host_ldt-x86_64.h
deleted file mode 100644
index 74a63f7d9a90..000000000000
--- a/include/asm-um/host_ldt-x86_64.h
+++ /dev/null
@@ -1,38 +0,0 @@
-#ifndef __ASM_HOST_LDT_X86_64_H
-#define __ASM_HOST_LDT_X86_64_H
-
-#include "asm/arch/ldt.h"
-
-/*
- * macros stolen from include/asm-x86_64/desc.h
- */
-#define LDT_entry_a(info) \
-	((((info)->base_addr & 0x0000ffff) << 16) | ((info)->limit & 0x0ffff))
-
-/* Don't allow setting of the lm bit. It is useless anyways because
- * 64bit system calls require __USER_CS. */
-#define LDT_entry_b(info) \
-	(((info)->base_addr & 0xff000000) | \
-	(((info)->base_addr & 0x00ff0000) >> 16) | \
-	((info)->limit & 0xf0000) | \
-	(((info)->read_exec_only ^ 1) << 9) | \
-	((info)->contents << 10) | \
-	(((info)->seg_not_present ^ 1) << 15) | \
-	((info)->seg_32bit << 22) | \
-	((info)->limit_in_pages << 23) | \
-	((info)->useable << 20) | \
-	/* ((info)->lm << 21) | */ \
-	0x7000)
-
-#define LDT_empty(info) (\
-	(info)->base_addr	== 0	&& \
-	(info)->limit		== 0	&& \
-	(info)->contents	== 0	&& \
-	(info)->read_exec_only	== 1	&& \
-	(info)->seg_32bit	== 0	&& \
-	(info)->limit_in_pages	== 0	&& \
-	(info)->seg_not_present	== 1	&& \
-	(info)->useable		== 0	&& \
-	(info)->lm              == 0)
-
-#endif
diff --git a/include/asm-um/hw_irq.h b/include/asm-um/hw_irq.h
deleted file mode 100644
index 1cf84cf5f21a..000000000000
--- a/include/asm-um/hw_irq.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _ASM_UM_HW_IRQ_H
-#define _ASM_UM_HW_IRQ_H
-
-#include "asm/irq.h"
-#include "asm/archparam.h"
-
-#endif
diff --git a/include/asm-um/ide.h b/include/asm-um/ide.h
deleted file mode 100644
index 3d1ccebcfbaf..000000000000
--- a/include/asm-um/ide.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_IDE_H
-#define __UM_IDE_H
-
-#include "asm/arch/ide.h"
-
-#endif
diff --git a/include/asm-um/io.h b/include/asm-um/io.h
deleted file mode 100644
index 44e8b8c772ae..000000000000
--- a/include/asm-um/io.h
+++ /dev/null
@@ -1,57 +0,0 @@
-#ifndef __UM_IO_H
-#define __UM_IO_H
-
-#include "asm/page.h"
-
-#define IO_SPACE_LIMIT 0xdeadbeef /* Sure hope nothing uses this */
-
-static inline int inb(unsigned long i) { return(0); }
-static inline void outb(char c, unsigned long i) { }
-
-/*
- * Change virtual addresses to physical addresses and vv.
- * These are pretty trivial
- */
-static inline unsigned long virt_to_phys(volatile void * address)
-{
-	return __pa((void *) address);
-}
-
-static inline void * phys_to_virt(unsigned long address)
-{
-	return __va(address);
-}
-
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
-
-static inline void writeb(unsigned char b, volatile void __iomem *addr)
-{
-	*(volatile unsigned char __force *) addr = b;
-}
-static inline void writew(unsigned short b, volatile void __iomem *addr)
-{
-	*(volatile unsigned short __force *) addr = b;
-}
-static inline void writel(unsigned int b, volatile void __iomem *addr)
-{
-	*(volatile unsigned int __force *) addr = b;
-}
-static inline void writeq(unsigned int b, volatile void __iomem *addr)
-{
-	*(volatile unsigned long long __force *) addr = b;
-}
-#define __raw_writeb writeb
-#define __raw_writew writew
-#define __raw_writel writel
-#define __raw_writeq writeq
-
-#endif
diff --git a/include/asm-um/ioctl.h b/include/asm-um/ioctl.h
deleted file mode 100644
index cc22157346db..000000000000
--- a/include/asm-um/ioctl.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_IOCTL_H
-#define __UM_IOCTL_H
-
-#include "asm/arch/ioctl.h"
-
-#endif
diff --git a/include/asm-um/ioctls.h b/include/asm-um/ioctls.h
deleted file mode 100644
index 9a1a017de6a7..000000000000
--- a/include/asm-um/ioctls.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_IOCTLS_H
-#define __UM_IOCTLS_H
-
-#include "asm/arch/ioctls.h"
-
-#endif
diff --git a/include/asm-um/ipcbuf.h b/include/asm-um/ipcbuf.h
deleted file mode 100644
index bb2ad31dc434..000000000000
--- a/include/asm-um/ipcbuf.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_IPCBUF_H
-#define __UM_IPCBUF_H
-
-#include "asm/arch/ipcbuf.h"
-
-#endif
diff --git a/include/asm-um/irq.h b/include/asm-um/irq.h
deleted file mode 100644
index 4a2037f8204b..000000000000
--- a/include/asm-um/irq.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef __UM_IRQ_H
-#define __UM_IRQ_H
-
-#define TIMER_IRQ		0
-#define UMN_IRQ			1
-#define CONSOLE_IRQ		2
-#define CONSOLE_WRITE_IRQ	3
-#define UBD_IRQ			4
-#define UM_ETH_IRQ		5
-#define SSL_IRQ			6
-#define SSL_WRITE_IRQ		7
-#define ACCEPT_IRQ		8
-#define MCONSOLE_IRQ		9
-#define WINCH_IRQ		10
-#define SIGIO_WRITE_IRQ 	11
-#define TELNETD_IRQ 		12
-#define XTERM_IRQ 		13
-#define RANDOM_IRQ 		14
-
-#define LAST_IRQ RANDOM_IRQ
-#define NR_IRQS (LAST_IRQ + 1)
-
-#endif
diff --git a/include/asm-um/irq_regs.h b/include/asm-um/irq_regs.h
deleted file mode 100644
index 3dd9c0b70270..000000000000
--- a/include/asm-um/irq_regs.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/include/asm-um/irq_vectors.h b/include/asm-um/irq_vectors.h
deleted file mode 100644
index 62ddba6fc733..000000000000
--- a/include/asm-um/irq_vectors.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/* 
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_IRQ_VECTORS_H
-#define __UM_IRQ_VECTORS_H
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/include/asm-um/irqflags.h b/include/asm-um/irqflags.h
deleted file mode 100644
index 659b9abdfdba..000000000000
--- a/include/asm-um/irqflags.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_IRQFLAGS_H
-#define __UM_IRQFLAGS_H
-
-/* Empty for now */
-
-#endif
diff --git a/include/asm-um/kdebug.h b/include/asm-um/kdebug.h
deleted file mode 100644
index 6ece1b037665..000000000000
--- a/include/asm-um/kdebug.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/kdebug.h>
diff --git a/include/asm-um/kmap_types.h b/include/asm-um/kmap_types.h
deleted file mode 100644
index 6c03acdb4405..000000000000
--- a/include/asm-um/kmap_types.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* 
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_KMAP_TYPES_H
-#define __UM_KMAP_TYPES_H
-
-/* No more #include "asm/arch/kmap_types.h" ! */
-
-enum km_type {
-	KM_BOUNCE_READ,
-	KM_SKB_SUNRPC_DATA,
-	KM_SKB_DATA_SOFTIRQ,
-	KM_USER0,
-	KM_USER1,
-	KM_UML_USERCOPY,	/* UML specific, for copy_*_user - used in do_op_one_page */
-	KM_BIO_SRC_IRQ,
-	KM_BIO_DST_IRQ,
-	KM_PTE0,
-	KM_PTE1,
-	KM_IRQ0,
-	KM_IRQ1,
-	KM_SOFTIRQ0,
-	KM_SOFTIRQ1,
-	KM_TYPE_NR
-};
-
-#endif
diff --git a/include/asm-um/ldt.h b/include/asm-um/ldt.h
deleted file mode 100644
index 52af512f5e7d..000000000000
--- a/include/asm-um/ldt.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Copyright (C) 2004 Fujitsu Siemens Computers GmbH
- * Licensed under the GPL
- *
- * Author: Bodo Stroesser <bstroesser@fujitsu-siemens.com>
- */
-
-#ifndef __ASM_LDT_H
-#define __ASM_LDT_H
-
-#include <linux/mutex.h>
-#include "asm/host_ldt.h"
-
-extern void ldt_host_info(void);
-
-#define LDT_PAGES_MAX \
-	((LDT_ENTRIES * LDT_ENTRY_SIZE)/PAGE_SIZE)
-#define LDT_ENTRIES_PER_PAGE \
-	(PAGE_SIZE/LDT_ENTRY_SIZE)
-#define LDT_DIRECT_ENTRIES \
-	((LDT_PAGES_MAX*sizeof(void *))/LDT_ENTRY_SIZE)
-
-struct ldt_entry {
-	__u32 a;
-	__u32 b;
-};
-
-typedef struct uml_ldt {
-	int entry_count;
-	struct mutex lock;
-	union {
-		struct ldt_entry * pages[LDT_PAGES_MAX];
-		struct ldt_entry entries[LDT_DIRECT_ENTRIES];
-	} u;
-} uml_ldt_t;
-
-#endif
diff --git a/include/asm-um/linkage.h b/include/asm-um/linkage.h
deleted file mode 100644
index 7dfce37adc8b..000000000000
--- a/include/asm-um/linkage.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_UM_LINKAGE_H
-#define __ASM_UM_LINKAGE_H
-
-#include "asm/arch/linkage.h"
-
-#endif
diff --git a/include/asm-um/local.h b/include/asm-um/local.h
deleted file mode 100644
index 9a280c5bb609..000000000000
--- a/include/asm-um/local.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_LOCAL_H
-#define __UM_LOCAL_H
-
-#include "asm/arch/local.h"
-
-#endif
diff --git a/include/asm-um/locks.h b/include/asm-um/locks.h
deleted file mode 100644
index f80030a3ef5a..000000000000
--- a/include/asm-um/locks.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_LOCKS_H
-#define __UM_LOCKS_H
-
-#include "asm/arch/locks.h"
-
-#endif
diff --git a/include/asm-um/mca_dma.h b/include/asm-um/mca_dma.h
deleted file mode 100644
index e492e4ec1392..000000000000
--- a/include/asm-um/mca_dma.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef mca___UM_DMA_H
-#define mca___UM_DMA_H
-
-#include "asm/arch/mca_dma.h"
-
-#endif
diff --git a/include/asm-um/mman.h b/include/asm-um/mman.h
deleted file mode 100644
index b09ed523019b..000000000000
--- a/include/asm-um/mman.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_MMAN_H
-#define __UM_MMAN_H
-
-#include "asm/arch/mman.h"
-
-#endif
diff --git a/include/asm-um/mmu.h b/include/asm-um/mmu.h
deleted file mode 100644
index 2cf35c21d694..000000000000
--- a/include/asm-um/mmu.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* 
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __MMU_H
-#define __MMU_H
-
-#include "um_mmu.h"
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/include/asm-um/mmu_context.h b/include/asm-um/mmu_context.h
deleted file mode 100644
index 54f42e8b0105..000000000000
--- a/include/asm-um/mmu_context.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/* 
- * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_MMU_CONTEXT_H
-#define __UM_MMU_CONTEXT_H
-
-#include "linux/sched.h"
-#include "um_mmu.h"
-
-extern void arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm);
-extern void arch_exit_mmap(struct mm_struct *mm);
-
-#define get_mmu_context(task) do ; while(0)
-#define activate_context(tsk) do ; while(0)
-
-#define deactivate_mm(tsk,mm)	do { } while (0)
-
-extern void force_flush_all(void);
-
-static inline void activate_mm(struct mm_struct *old, struct mm_struct *new)
-{
-	/*
-	 * This is called by fs/exec.c and sys_unshare()
-	 * when the new ->mm is used for the first time.
-	 */
-	__switch_mm(&new->context.id);
-	arch_dup_mmap(old, new);
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, 
-			     struct task_struct *tsk)
-{
-	unsigned cpu = smp_processor_id();
-
-	if(prev != next){
-		cpu_clear(cpu, prev->cpu_vm_mask);
-		cpu_set(cpu, next->cpu_vm_mask);
-		if(next != &init_mm)
-			__switch_mm(&next->context.id);
-	}
-}
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, 
-				  struct task_struct *tsk)
-{
-}
-
-extern int init_new_context(struct task_struct *task, struct mm_struct *mm);
-
-extern void destroy_context(struct mm_struct *mm);
-
-#endif
diff --git a/include/asm-um/module-generic.h b/include/asm-um/module-generic.h
deleted file mode 100644
index 5a265f56b174..000000000000
--- a/include/asm-um/module-generic.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_MODULE_GENERIC_H
-#define __UM_MODULE_GENERIC_H
-
-#include "asm/arch/module.h"
-
-#endif
diff --git a/include/asm-um/module-i386.h b/include/asm-um/module-i386.h
deleted file mode 100644
index 5ead4a0b2e35..000000000000
--- a/include/asm-um/module-i386.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __UM_MODULE_I386_H
-#define __UM_MODULE_I386_H
-
-/* UML is simple */
-struct mod_arch_specific
-{
-};
-
-#define Elf_Shdr Elf32_Shdr
-#define Elf_Sym Elf32_Sym
-#define Elf_Ehdr Elf32_Ehdr
-
-#endif
diff --git a/include/asm-um/module-x86_64.h b/include/asm-um/module-x86_64.h
deleted file mode 100644
index 35b5491d3e96..000000000000
--- a/include/asm-um/module-x86_64.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_MODULE_X86_64_H
-#define __UM_MODULE_X86_64_H
-
-/* UML is simple */
-struct mod_arch_specific
-{
-};
-
-#define Elf_Shdr Elf64_Shdr
-#define Elf_Sym Elf64_Sym
-#define Elf_Ehdr Elf64_Ehdr
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/include/asm-um/msgbuf.h b/include/asm-um/msgbuf.h
deleted file mode 100644
index 8ce8c30d5377..000000000000
--- a/include/asm-um/msgbuf.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_MSGBUF_H
-#define __UM_MSGBUF_H
-
-#include "asm/arch/msgbuf.h"
-
-#endif
diff --git a/include/asm-um/mtrr.h b/include/asm-um/mtrr.h
deleted file mode 100644
index 5e9cd12c578d..000000000000
--- a/include/asm-um/mtrr.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_MTRR_H
-#define __UM_MTRR_H
-
-#include "asm/arch/mtrr.h"
-
-#endif
diff --git a/include/asm-um/mutex.h b/include/asm-um/mutex.h
deleted file mode 100644
index 458c1f7fbc18..000000000000
--- a/include/asm-um/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>
diff --git a/include/asm-um/nops.h b/include/asm-um/nops.h
deleted file mode 100644
index 814e9bf5dea6..000000000000
--- a/include/asm-um/nops.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_NOPS_H
-#define __UM_NOPS_H
-
-#include "asm/arch/nops.h"
-
-#endif
diff --git a/include/asm-um/page.h b/include/asm-um/page.h
deleted file mode 100644
index a6df1f13d732..000000000000
--- a/include/asm-um/page.h
+++ /dev/null
@@ -1,122 +0,0 @@
-/*
- * Copyright (C) 2000 - 2003 Jeff Dike (jdike@addtoit.com)
- * Copyright 2003 PathScale, Inc.
- * Licensed under the GPL
- */
-
-#ifndef __UM_PAGE_H
-#define __UM_PAGE_H
-
-#include <linux/const.h>
-
-/* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT	12
-#define PAGE_SIZE	(_AC(1, UL) << PAGE_SHIFT)
-#define PAGE_MASK	(~(PAGE_SIZE-1))
-
-#ifndef __ASSEMBLY__
-
-struct page;
-
-#include <linux/types.h>
-#include <asm/vm-flags.h>
-
-/*
- * These are used to make use of C type-checking..
- */
-
-#define clear_page(page)	memset((void *)(page), 0, PAGE_SIZE)
-#define copy_page(to,from)	memcpy((void *)(to), (void *)(from), PAGE_SIZE)
-
-#define clear_user_page(page, vaddr, pg)	clear_page(page)
-#define copy_user_page(to, from, vaddr, pg)	copy_page(to, from)
-
-#if defined(CONFIG_3_LEVEL_PGTABLES) && !defined(CONFIG_64BIT)
-
-typedef struct { unsigned long pte_low, pte_high; } pte_t;
-typedef struct { unsigned long pmd; } pmd_t;
-typedef struct { unsigned long pgd; } pgd_t;
-#define pte_val(x) ((x).pte_low | ((unsigned long long) (x).pte_high << 32))
-
-#define pte_get_bits(pte, bits) ((pte).pte_low & (bits))
-#define pte_set_bits(pte, bits) ((pte).pte_low |= (bits))
-#define pte_clear_bits(pte, bits) ((pte).pte_low &= ~(bits))
-#define pte_copy(to, from) ({ (to).pte_high = (from).pte_high; \
-			      smp_wmb(); \
-			      (to).pte_low = (from).pte_low; })
-#define pte_is_zero(pte) (!((pte).pte_low & ~_PAGE_NEWPAGE) && !(pte).pte_high)
-#define pte_set_val(pte, phys, prot) \
-	({ (pte).pte_high = (phys) >> 32; \
-	   (pte).pte_low = (phys) | pgprot_val(prot); })
-
-#define pmd_val(x)	((x).pmd)
-#define __pmd(x) ((pmd_t) { (x) } )
-
-typedef unsigned long long pfn_t;
-typedef unsigned long long phys_t;
-
-#else
-
-typedef struct { unsigned long pte; } pte_t;
-typedef struct { unsigned long pgd; } pgd_t;
-
-#ifdef CONFIG_3_LEVEL_PGTABLES
-typedef struct { unsigned long pmd; } pmd_t;
-#define pmd_val(x)	((x).pmd)
-#define __pmd(x) ((pmd_t) { (x) } )
-#endif
-
-#define pte_val(x)	((x).pte)
-
-
-#define pte_get_bits(p, bits) ((p).pte & (bits))
-#define pte_set_bits(p, bits) ((p).pte |= (bits))
-#define pte_clear_bits(p, bits) ((p).pte &= ~(bits))
-#define pte_copy(to, from) ((to).pte = (from).pte)
-#define pte_is_zero(p) (!((p).pte & ~_PAGE_NEWPAGE))
-#define pte_set_val(p, phys, prot) (p).pte = (phys | pgprot_val(prot))
-
-typedef unsigned long pfn_t;
-typedef unsigned long phys_t;
-
-#endif
-
-typedef struct { unsigned long pgprot; } pgprot_t;
-
-typedef struct page *pgtable_t;
-
-#define pgd_val(x)	((x).pgd)
-#define pgprot_val(x)	((x).pgprot)
-
-#define __pte(x) ((pte_t) { (x) } )
-#define __pgd(x) ((pgd_t) { (x) } )
-#define __pgprot(x)	((pgprot_t) { (x) } )
-
-extern unsigned long uml_physmem;
-
-#define PAGE_OFFSET (uml_physmem)
-#define KERNELBASE PAGE_OFFSET
-
-#define __va_space (8*1024*1024)
-
-#include "mem.h"
-
-/* Cast to unsigned long before casting to void * to avoid a warning from
- * mmap_kmem about cutting a long long down to a void *.  Not sure that
- * casting is the right thing, but 32-bit UML can't have 64-bit virtual
- * addresses
- */
-#define __pa(virt) to_phys((void *) (unsigned long) (virt))
-#define __va(phys) to_virt((unsigned long) (phys))
-
-#define phys_to_pfn(p) ((pfn_t) ((p) >> PAGE_SHIFT))
-#define pfn_to_phys(pfn) ((phys_t) ((pfn) << PAGE_SHIFT))
-
-#define pfn_valid(pfn) ((pfn) < max_mapnr)
-#define virt_addr_valid(v) pfn_valid(phys_to_pfn(__pa(v)))
-
-#include <asm-generic/memory_model.h>
-#include <asm-generic/page.h>
-
-#endif	/* __ASSEMBLY__ */
-#endif	/* __UM_PAGE_H */
diff --git a/include/asm-um/page_offset.h b/include/asm-um/page_offset.h
deleted file mode 100644
index 1c168dfbf359..000000000000
--- a/include/asm-um/page_offset.h
+++ /dev/null
@@ -1 +0,0 @@
-#define PAGE_OFFSET_RAW (uml_physmem)
diff --git a/include/asm-um/param.h b/include/asm-um/param.h
deleted file mode 100644
index e44f4e60d16d..000000000000
--- a/include/asm-um/param.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef _UM_PARAM_H
-#define _UM_PARAM_H
-
-#define EXEC_PAGESIZE   4096
-
-#ifndef NOGROUP
-#define NOGROUP         (-1)
-#endif
-
-#define MAXHOSTNAMELEN  64      /* max length of hostname */
-
-#ifdef __KERNEL__
-#define HZ CONFIG_HZ
-#define USER_HZ	100	   /* .. some user interfaces are in "ticks" */
-#define CLOCKS_PER_SEC (USER_HZ)  /* frequency at which times() counts */
-#else
-#define HZ 100
-#endif
-
-#endif
diff --git a/include/asm-um/paravirt.h b/include/asm-um/paravirt.h
deleted file mode 100644
index 9d6aaad80b5f..000000000000
--- a/include/asm-um/paravirt.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_PARAVIRT_H
-#define __UM_PARAVIRT_H
-
-#include "asm/arch/paravirt.h"
-
-#endif
diff --git a/include/asm-um/pci.h b/include/asm-um/pci.h
deleted file mode 100644
index 59923199cdc3..000000000000
--- a/include/asm-um/pci.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __UM_PCI_H
-#define __UM_PCI_H
-
-#define PCI_DMA_BUS_IS_PHYS     (1)
-#define pcibios_scan_all_fns(a, b)	0
-
-#endif
diff --git a/include/asm-um/pda.h b/include/asm-um/pda.h
deleted file mode 100644
index 0d8bf33ffd42..000000000000
--- a/include/asm-um/pda.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_PDA_X86_64_H
-#define __UM_PDA_X86_64_H
-
-/* XXX */
-struct foo {
-	unsigned int __softirq_pending;
-	unsigned int __nmi_count;
-};
-
-extern struct foo me;
-
-#define read_pda(me) (&me)
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/include/asm-um/percpu.h b/include/asm-um/percpu.h
deleted file mode 100644
index 5723e2aab8e7..000000000000
--- a/include/asm-um/percpu.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_PERCPU_H
-#define __UM_PERCPU_H
-
-#include "asm/arch/percpu.h"
-
-#endif
diff --git a/include/asm-um/pgalloc.h b/include/asm-um/pgalloc.h
deleted file mode 100644
index 9062a6e72241..000000000000
--- a/include/asm-um/pgalloc.h
+++ /dev/null
@@ -1,72 +0,0 @@
-/* 
- * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com)
- * Copyright 2003 PathScale, Inc.
- * Derived from include/asm-i386/pgalloc.h and include/asm-i386/pgtable.h
- * Licensed under the GPL
- */
-
-#ifndef __UM_PGALLOC_H
-#define __UM_PGALLOC_H
-
-#include "linux/mm.h"
-#include "asm/fixmap.h"
-
-#define pmd_populate_kernel(mm, pmd, pte) \
-	set_pmd(pmd, __pmd(_PAGE_TABLE + (unsigned long) __pa(pte)))
-
-#define pmd_populate(mm, pmd, pte) 				\
-	set_pmd(pmd, __pmd(_PAGE_TABLE +			\
-		((unsigned long long)page_to_pfn(pte) <<	\
-			(unsigned long long) PAGE_SHIFT)))
-#define pmd_pgtable(pmd) pmd_page(pmd)
-
-/*
- * Allocate and free page tables.
- */
-extern pgd_t *pgd_alloc(struct mm_struct *);
-extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
-
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
-extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long);
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	free_page((unsigned long) pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
-{
-	pgtable_page_dtor(pte);
-	__free_page(pte);
-}
-
-#define __pte_free_tlb(tlb,pte)				\
-do {							\
-	pgtable_page_dtor(pte);				\
-	tlb_remove_page((tlb),(pte));			\
-} while (0)
-
-#ifdef CONFIG_3_LEVEL_PGTABLES
-
-static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
-{
-	free_page((unsigned long)pmd);
-}
-
-#define __pmd_free_tlb(tlb,x)   tlb_remove_page((tlb),virt_to_page(x))
-#endif
-
-#define check_pgt_cache()	do { } while (0)
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/include/asm-um/pgtable-2level.h b/include/asm-um/pgtable-2level.h
deleted file mode 100644
index f534b73e753e..000000000000
--- a/include/asm-um/pgtable-2level.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/*
- * Copyright (C) 2000, 2001, 2002 Jeff Dike (jdike@karaya.com)
- * Copyright 2003 PathScale, Inc.
- * Derived from include/asm-i386/pgtable.h
- * Licensed under the GPL
- */
-
-#ifndef __UM_PGTABLE_2LEVEL_H
-#define __UM_PGTABLE_2LEVEL_H
-
-#include <asm-generic/pgtable-nopmd.h>
-
-/* PGDIR_SHIFT determines what a third-level page table entry can map */
-
-#define PGDIR_SHIFT	22
-#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
-#define PGDIR_MASK	(~(PGDIR_SIZE-1))
-
-/*
- * entries per page directory level: the i386 is two-level, so
- * we don't really have any PMD directory physically.
- */
-#define PTRS_PER_PTE	1024
-#define USER_PTRS_PER_PGD ((TASK_SIZE + (PGDIR_SIZE - 1)) / PGDIR_SIZE)
-#define PTRS_PER_PGD	1024
-#define FIRST_USER_ADDRESS	0
-
-#define pte_ERROR(e) \
-        printk("%s:%d: bad pte %p(%08lx).\n", __FILE__, __LINE__, &(e), \
-	       pte_val(e))
-#define pgd_ERROR(e) \
-        printk("%s:%d: bad pgd %p(%08lx).\n", __FILE__, __LINE__, &(e), \
-	       pgd_val(e))
-
-static inline int pgd_newpage(pgd_t pgd)	{ return 0; }
-static inline void pgd_mkuptodate(pgd_t pgd)	{ }
-
-#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval))
-
-#define pte_pfn(x) phys_to_pfn(pte_val(x))
-#define pfn_pte(pfn, prot) __pte(pfn_to_phys(pfn) | pgprot_val(prot))
-#define pfn_pmd(pfn, prot) __pmd(pfn_to_phys(pfn) | pgprot_val(prot))
-
-/*
- * Bits 0 through 4 are taken
- */
-#define PTE_FILE_MAX_BITS	27
-
-#define pte_to_pgoff(pte) (pte_val(pte) >> 5)
-
-#define pgoff_to_pte(off) ((pte_t) { ((off) << 5) + _PAGE_FILE })
-
-#endif
diff --git a/include/asm-um/pgtable-3level.h b/include/asm-um/pgtable-3level.h
deleted file mode 100644
index 0446f456b428..000000000000
--- a/include/asm-um/pgtable-3level.h
+++ /dev/null
@@ -1,146 +0,0 @@
-/*
- * Copyright 2003 PathScale Inc
- * Derived from include/asm-i386/pgtable.h
- * Licensed under the GPL
- */
-
-#ifndef __UM_PGTABLE_3LEVEL_H
-#define __UM_PGTABLE_3LEVEL_H
-
-#include <asm-generic/pgtable-nopud.h>
-
-/* PGDIR_SHIFT determines what a third-level page table entry can map */
-
-#ifdef CONFIG_64BIT
-#define PGDIR_SHIFT	30
-#else
-#define PGDIR_SHIFT	31
-#endif
-#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
-#define PGDIR_MASK	(~(PGDIR_SIZE-1))
-
-/* PMD_SHIFT determines the size of the area a second-level page table can
- * map
- */
-
-#define PMD_SHIFT	21
-#define PMD_SIZE	(1UL << PMD_SHIFT)
-#define PMD_MASK	(~(PMD_SIZE-1))
-
-/*
- * entries per page directory level
- */
-
-#define PTRS_PER_PTE 512
-#ifdef CONFIG_64BIT
-#define PTRS_PER_PMD 512
-#define PTRS_PER_PGD 512
-#else
-#define PTRS_PER_PMD 1024
-#define PTRS_PER_PGD 1024
-#endif
-
-#define USER_PTRS_PER_PGD ((TASK_SIZE + (PGDIR_SIZE - 1)) / PGDIR_SIZE)
-#define FIRST_USER_ADDRESS	0
-
-#define pte_ERROR(e) \
-        printk("%s:%d: bad pte %p(%016lx).\n", __FILE__, __LINE__, &(e), \
-	       pte_val(e))
-#define pmd_ERROR(e) \
-        printk("%s:%d: bad pmd %p(%016lx).\n", __FILE__, __LINE__, &(e), \
-	       pmd_val(e))
-#define pgd_ERROR(e) \
-        printk("%s:%d: bad pgd %p(%016lx).\n", __FILE__, __LINE__, &(e), \
-	       pgd_val(e))
-
-#define pud_none(x)	(!(pud_val(x) & ~_PAGE_NEWPAGE))
-#define	pud_bad(x)	((pud_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
-#define pud_present(x)	(pud_val(x) & _PAGE_PRESENT)
-#define pud_populate(mm, pud, pmd) \
-	set_pud(pud, __pud(_PAGE_TABLE + __pa(pmd)))
-
-#ifdef CONFIG_64BIT
-#define set_pud(pudptr, pudval) set_64bit((phys_t *) (pudptr), pud_val(pudval))
-#else
-#define set_pud(pudptr, pudval) (*(pudptr) = (pudval))
-#endif
-
-static inline int pgd_newpage(pgd_t pgd)
-{
-	return(pgd_val(pgd) & _PAGE_NEWPAGE);
-}
-
-static inline void pgd_mkuptodate(pgd_t pgd) { pgd_val(pgd) &= ~_PAGE_NEWPAGE; }
-
-#ifdef CONFIG_64BIT
-#define set_pmd(pmdptr, pmdval) set_64bit((phys_t *) (pmdptr), pmd_val(pmdval))
-#else
-#define set_pmd(pmdptr, pmdval) (*(pmdptr) = (pmdval))
-#endif
-
-struct mm_struct;
-extern pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address);
-
-static inline void pud_clear (pud_t *pud)
-{
-	set_pud(pud, __pud(_PAGE_NEWPAGE));
-}
-
-#define pud_page(pud) phys_to_page(pud_val(pud) & PAGE_MASK)
-#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PAGE_MASK))
-
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(pud, address) ((pmd_t *) pud_page_vaddr(*(pud)) + \
-			pmd_index(address))
-
-static inline unsigned long pte_pfn(pte_t pte)
-{
-	return phys_to_pfn(pte_val(pte));
-}
-
-static inline pte_t pfn_pte(pfn_t page_nr, pgprot_t pgprot)
-{
-	pte_t pte;
-	phys_t phys = pfn_to_phys(page_nr);
-
-	pte_set_val(pte, phys, pgprot);
-	return pte;
-}
-
-static inline pmd_t pfn_pmd(pfn_t page_nr, pgprot_t pgprot)
-{
-	return __pmd((page_nr << PAGE_SHIFT) | pgprot_val(pgprot));
-}
-
-/*
- * Bits 0 through 3 are taken in the low part of the pte,
- * put the 32 bits of offset into the high part.
- */
-#define PTE_FILE_MAX_BITS	32
-
-#ifdef CONFIG_64BIT
-
-#define pte_to_pgoff(p) ((p).pte >> 32)
-
-#define pgoff_to_pte(off) ((pte_t) { ((off) << 32) | _PAGE_FILE })
-
-#else
-
-#define pte_to_pgoff(pte) ((pte).pte_high)
-
-#define pgoff_to_pte(off) ((pte_t) { _PAGE_FILE, (off) })
-
-#endif
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/include/asm-um/pgtable.h b/include/asm-um/pgtable.h
deleted file mode 100644
index 02db81b7b86e..000000000000
--- a/include/asm-um/pgtable.h
+++ /dev/null
@@ -1,358 +0,0 @@
-/* 
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Copyright 2003 PathScale, Inc.
- * Derived from include/asm-i386/pgtable.h
- * Licensed under the GPL
- */
-
-#ifndef __UM_PGTABLE_H
-#define __UM_PGTABLE_H
-
-#include <asm/fixmap.h>
-
-#define _PAGE_PRESENT	0x001
-#define _PAGE_NEWPAGE	0x002
-#define _PAGE_NEWPROT	0x004
-#define _PAGE_RW	0x020
-#define _PAGE_USER	0x040
-#define _PAGE_ACCESSED	0x080
-#define _PAGE_DIRTY	0x100
-/* If _PAGE_PRESENT is clear, we use these: */
-#define _PAGE_FILE	0x008	/* nonlinear file mapping, saved PTE; unset:swap */
-#define _PAGE_PROTNONE	0x010	/* if the user mapped it with PROT_NONE;
-				   pte_present gives true */
-
-#ifdef CONFIG_3_LEVEL_PGTABLES
-#include "asm/pgtable-3level.h"
-#else
-#include "asm/pgtable-2level.h"
-#endif
-
-extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
-
-/* zero page used for uninitialized stuff */
-extern unsigned long *empty_zero_page;
-
-#define pgtable_cache_init() do ; while (0)
-
-/* Just any arbitrary offset to the start of the vmalloc VM area: the
- * current 8MB value just means that there will be a 8MB "hole" after the
- * physical memory until the kernel virtual memory starts.  That means that
- * any out-of-bounds memory accesses will hopefully be caught.
- * The vmalloc() routines leaves a hole of 4kB between each vmalloced
- * area for the same reason. ;)
- */
-
-extern unsigned long end_iomem;
-
-#define VMALLOC_OFFSET	(__va_space)
-#define VMALLOC_START ((end_iomem + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
-#ifdef CONFIG_HIGHMEM
-# define VMALLOC_END	(PKMAP_BASE-2*PAGE_SIZE)
-#else
-# define VMALLOC_END	(FIXADDR_START-2*PAGE_SIZE)
-#endif
-
-#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _PAGE_CHG_MASK	(PAGE_MASK | _PAGE_ACCESSED | _PAGE_DIRTY)
-
-#define PAGE_NONE	__pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
-#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_COPY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_READONLY	__pgprot(_PAGE_PRESENT | _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_KERNEL	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
-
-/*
- * The i386 can't do page protection for execute, and considers that the same
- * are read.
- * Also, write permissions imply read permissions. This is the closest we can
- * get..
- */
-#define __P000	PAGE_NONE
-#define __P001	PAGE_READONLY
-#define __P010	PAGE_COPY
-#define __P011	PAGE_COPY
-#define __P100	PAGE_READONLY
-#define __P101	PAGE_READONLY
-#define __P110	PAGE_COPY
-#define __P111	PAGE_COPY
-
-#define __S000	PAGE_NONE
-#define __S001	PAGE_READONLY
-#define __S010	PAGE_SHARED
-#define __S011	PAGE_SHARED
-#define __S100	PAGE_READONLY
-#define __S101	PAGE_READONLY
-#define __S110	PAGE_SHARED
-#define __S111	PAGE_SHARED
-
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-#define ZERO_PAGE(vaddr) virt_to_page(empty_zero_page)
-
-#define pte_clear(mm,addr,xp) pte_set_val(*(xp), (phys_t) 0, __pgprot(_PAGE_NEWPAGE))
-
-#define pmd_none(x)	(!((unsigned long)pmd_val(x) & ~_PAGE_NEWPAGE))
-#define	pmd_bad(x)	((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
-
-#define pmd_present(x)	(pmd_val(x) & _PAGE_PRESENT)
-#define pmd_clear(xp)	do { pmd_val(*(xp)) = _PAGE_NEWPAGE; } while (0)
-
-#define pmd_newpage(x)  (pmd_val(x) & _PAGE_NEWPAGE)
-#define pmd_mkuptodate(x) (pmd_val(x) &= ~_PAGE_NEWPAGE)
-
-#define pud_newpage(x)  (pud_val(x) & _PAGE_NEWPAGE)
-#define pud_mkuptodate(x) (pud_val(x) &= ~_PAGE_NEWPAGE)
-
-#define pmd_page(pmd) phys_to_page(pmd_val(pmd) & PAGE_MASK)
-
-#define pte_page(x) pfn_to_page(pte_pfn(x))
-
-#define pte_present(x)	pte_get_bits(x, (_PAGE_PRESENT | _PAGE_PROTNONE))
-
-/*
- * =================================
- * Flags checking section.
- * =================================
- */
-
-static inline int pte_none(pte_t pte)
-{
-	return pte_is_zero(pte);
-}
-
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
-static inline int pte_read(pte_t pte)
-{ 
-	return((pte_get_bits(pte, _PAGE_USER)) &&
-	       !(pte_get_bits(pte, _PAGE_PROTNONE)));
-}
-
-static inline int pte_exec(pte_t pte){
-	return((pte_get_bits(pte, _PAGE_USER)) &&
-	       !(pte_get_bits(pte, _PAGE_PROTNONE)));
-}
-
-static inline int pte_write(pte_t pte)
-{
-	return((pte_get_bits(pte, _PAGE_RW)) &&
-	       !(pte_get_bits(pte, _PAGE_PROTNONE)));
-}
-
-/*
- * The following only works if pte_present() is not true.
- */
-static inline int pte_file(pte_t pte)
-{
-	return pte_get_bits(pte, _PAGE_FILE);
-}
-
-static inline int pte_dirty(pte_t pte)
-{
-	return pte_get_bits(pte, _PAGE_DIRTY);
-}
-
-static inline int pte_young(pte_t pte)
-{
-	return pte_get_bits(pte, _PAGE_ACCESSED);
-}
-
-static inline int pte_newpage(pte_t pte)
-{
-	return pte_get_bits(pte, _PAGE_NEWPAGE);
-}
-
-static inline int pte_newprot(pte_t pte)
-{ 
-	return(pte_present(pte) && (pte_get_bits(pte, _PAGE_NEWPROT)));
-}
-
-static inline int pte_special(pte_t pte)
-{
-	return 0;
-}
-
-/*
- * =================================
- * Flags setting section.
- * =================================
- */
-
-static inline pte_t pte_mknewprot(pte_t pte)
-{
-	pte_set_bits(pte, _PAGE_NEWPROT);
-	return(pte);
-}
-
-static inline pte_t pte_mkclean(pte_t pte)
-{
-	pte_clear_bits(pte, _PAGE_DIRTY);
-	return(pte);
-}
-
-static inline pte_t pte_mkold(pte_t pte)	
-{ 
-	pte_clear_bits(pte, _PAGE_ACCESSED);
-	return(pte);
-}
-
-static inline pte_t pte_wrprotect(pte_t pte)
-{ 
-	pte_clear_bits(pte, _PAGE_RW);
-	return(pte_mknewprot(pte)); 
-}
-
-static inline pte_t pte_mkread(pte_t pte)
-{ 
-	pte_set_bits(pte, _PAGE_USER);
-	return(pte_mknewprot(pte)); 
-}
-
-static inline pte_t pte_mkdirty(pte_t pte)
-{ 
-	pte_set_bits(pte, _PAGE_DIRTY);
-	return(pte);
-}
-
-static inline pte_t pte_mkyoung(pte_t pte)
-{
-	pte_set_bits(pte, _PAGE_ACCESSED);
-	return(pte);
-}
-
-static inline pte_t pte_mkwrite(pte_t pte)	
-{
-	pte_set_bits(pte, _PAGE_RW);
-	return(pte_mknewprot(pte)); 
-}
-
-static inline pte_t pte_mkuptodate(pte_t pte)	
-{
-	pte_clear_bits(pte, _PAGE_NEWPAGE);
-	if(pte_present(pte))
-		pte_clear_bits(pte, _PAGE_NEWPROT);
-	return(pte); 
-}
-
-static inline pte_t pte_mknewpage(pte_t pte)
-{
-	pte_set_bits(pte, _PAGE_NEWPAGE);
-	return(pte);
-}
-
-static inline pte_t pte_mkspecial(pte_t pte)
-{
-	return(pte);
-}
-
-static inline void set_pte(pte_t *pteptr, pte_t pteval)
-{
-	pte_copy(*pteptr, pteval);
-
-	/* If it's a swap entry, it needs to be marked _PAGE_NEWPAGE so
-	 * fix_range knows to unmap it.  _PAGE_NEWPROT is specific to
-	 * mapped pages.
-	 */
-
-	*pteptr = pte_mknewpage(*pteptr);
-	if(pte_present(*pteptr)) *pteptr = pte_mknewprot(*pteptr);
-}
-#define set_pte_at(mm,addr,ptep,pteval) set_pte(ptep,pteval)
-
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-
-#define phys_to_page(phys) pfn_to_page(phys_to_pfn(phys))
-#define __virt_to_page(virt) phys_to_page(__pa(virt))
-#define page_to_phys(page) pfn_to_phys((pfn_t) page_to_pfn(page))
-#define virt_to_page(addr) __virt_to_page((const unsigned long) addr)
-
-#define mk_pte(page, pgprot) \
-	({ pte_t pte;					\
-							\
-	pte_set_val(pte, page_to_phys(page), (pgprot));	\
-	if (pte_present(pte))				\
-		pte_mknewprot(pte_mknewpage(pte));	\
-	pte;})
-
-static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
-{
-	pte_set_val(pte, (pte_val(pte) & _PAGE_CHG_MASK), newprot);
-	return pte; 
-}
-
-/*
- * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
- *
- * this macro returns the index of the entry in the pgd page which would
- * control the given virtual address
- */
-#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD-1))
-
-/*
- * pgd_offset() returns a (pgd_t *)
- * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
- */
-#define pgd_offset(mm, address) ((mm)->pgd+pgd_index(address))
-
-/*
- * a shortcut which implies the use of the kernel's pgd, instead
- * of a process's
- */
-#define pgd_offset_k(address) pgd_offset(&init_mm, address)
-
-/*
- * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
- *
- * this macro returns the index of the entry in the pmd page which would
- * control the given virtual address
- */
-#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
-#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD-1))
-
-#define pmd_page_vaddr(pmd) \
-	((unsigned long) __va(pmd_val(pmd) & PAGE_MASK))
-
-/*
- * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
- *
- * this macro returns the index of the entry in the pte page which would
- * control the given virtual address
- */
-#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_kernel(dir, address) \
-	((pte_t *) pmd_page_vaddr(*(dir)) +  pte_index(address))
-#define pte_offset_map(dir, address) \
-	((pte_t *)page_address(pmd_page(*(dir))) + pte_index(address))
-#define pte_offset_map_nested(dir, address) pte_offset_map(dir, address)
-#define pte_unmap(pte) do { } while (0)
-#define pte_unmap_nested(pte) do { } while (0)
-
-struct mm_struct;
-extern pte_t *virt_to_pte(struct mm_struct *mm, unsigned long addr);
-
-#define update_mmu_cache(vma,address,pte) do ; while (0)
-
-/* Encode and de-code a swap entry */
-#define __swp_type(x)			(((x).val >> 4) & 0x3f)
-#define __swp_offset(x)			((x).val >> 11)
-
-#define __swp_entry(type, offset) \
-	((swp_entry_t) { ((type) << 4) | ((offset) << 11) })
-#define __pte_to_swp_entry(pte) \
-	((swp_entry_t) { pte_val(pte_mkuptodate(pte)) })
-#define __swp_entry_to_pte(x)		((pte_t) { (x).val })
-
-#define kern_addr_valid(addr) (1)
-
-#include <asm-generic/pgtable.h>
-
-#endif
diff --git a/include/asm-um/poll.h b/include/asm-um/poll.h
deleted file mode 100644
index 1eb4e1bc6383..000000000000
--- a/include/asm-um/poll.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_POLL_H
-#define __UM_POLL_H
-
-#include "asm/arch/poll.h"
-
-#endif
diff --git a/include/asm-um/posix_types.h b/include/asm-um/posix_types.h
deleted file mode 100644
index 32fb4198f644..000000000000
--- a/include/asm-um/posix_types.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_POSIX_TYPES_H
-#define __UM_POSIX_TYPES_H
-
-#include "asm/arch/posix_types.h"
-
-#endif
diff --git a/include/asm-um/prctl.h b/include/asm-um/prctl.h
deleted file mode 100644
index 64b6d099bdd5..000000000000
--- a/include/asm-um/prctl.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_PRCTL_H
-#define __UM_PRCTL_H
-
-#include "asm/arch/prctl.h"
-
-#endif
diff --git a/include/asm-um/processor-generic.h b/include/asm-um/processor-generic.h
deleted file mode 100644
index bed668824b5f..000000000000
--- a/include/asm-um/processor-generic.h
+++ /dev/null
@@ -1,136 +0,0 @@
-/* 
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_PROCESSOR_GENERIC_H
-#define __UM_PROCESSOR_GENERIC_H
-
-struct pt_regs;
-
-struct task_struct;
-
-#include "asm/ptrace.h"
-#include "registers.h"
-#include "sysdep/archsetjmp.h"
-
-struct mm_struct;
-
-struct thread_struct {
-	struct task_struct *saved_task;
-	/*
-	 * This flag is set to 1 before calling do_fork (and analyzed in
-	 * copy_thread) to mark that we are begin called from userspace (fork /
-	 * vfork / clone), and reset to 0 after. It is left to 0 when called
-	 * from kernelspace (i.e. kernel_thread() or fork_idle(),
-	 * as of 2.6.11).
-	 */
-	int forking;
-	struct pt_regs regs;
-	int singlestep_syscall;
-	void *fault_addr;
-	jmp_buf *fault_catcher;
-	struct task_struct *prev_sched;
-	unsigned long temp_stack;
-	jmp_buf *exec_buf;
-	struct arch_thread arch;
-	jmp_buf switch_buf;
-	int mm_count;
-	struct {
-		int op;
-		union {
-			struct {
-				int pid;
-			} fork, exec;
-			struct {
-				int (*proc)(void *);
-				void *arg;
-			} thread;
-			struct {
-				void (*proc)(void *);
-				void *arg;
-			} cb;
-		} u;
-	} request;
-};
-
-#define INIT_THREAD \
-{ \
-	.forking		= 0, \
-	.regs		   	= EMPTY_REGS,	\
-	.fault_addr		= NULL, \
-	.prev_sched		= NULL, \
-	.temp_stack		= 0, \
-	.exec_buf		= NULL, \
-	.arch			= INIT_ARCH_THREAD, \
-	.request		= { 0 } \
-}
-
-extern struct task_struct *alloc_task_struct(void);
-
-static inline void release_thread(struct task_struct *task)
-{
-}
-
-extern int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags);
-
-static inline void prepare_to_copy(struct task_struct *tsk)
-{
-}
-
-
-extern unsigned long thread_saved_pc(struct task_struct *t);
-
-static inline void mm_copy_segments(struct mm_struct *from_mm,
-				    struct mm_struct *new_mm)
-{
-}
-
-#define init_stack	(init_thread_union.stack)
-
-/*
- * User space process size: 3GB (default).
- */
-extern unsigned long task_size;
-
-#define TASK_SIZE (task_size)
-
-#undef STACK_TOP
-#undef STACK_TOP_MAX
-
-extern unsigned long stacksizelim;
-
-#define STACK_ROOM	(stacksizelim)
-#define STACK_TOP	(TASK_SIZE - 2 * PAGE_SIZE)
-#define STACK_TOP_MAX	STACK_TOP
-
-/* This decides where the kernel will search for a free chunk of vm
- * space during mmap's.
- */
-#define TASK_UNMAPPED_BASE	(0x40000000)
-
-extern void start_thread(struct pt_regs *regs, unsigned long entry, 
-			 unsigned long stack);
-
-struct cpuinfo_um {
-	unsigned long loops_per_jiffy;
-	int ipi_pipe[2];
-};
-
-extern struct cpuinfo_um boot_cpu_data;
-
-#define my_cpu_data		cpu_data[smp_processor_id()]
-
-#ifdef CONFIG_SMP
-extern struct cpuinfo_um cpu_data[];
-#define current_cpu_data cpu_data[smp_processor_id()]
-#else
-#define cpu_data (&boot_cpu_data)
-#define current_cpu_data boot_cpu_data
-#endif
-
-
-#define KSTK_REG(tsk, reg) get_thread_reg(reg, &tsk->thread.switch_buf)
-extern unsigned long get_wchan(struct task_struct *p);
-
-#endif
diff --git a/include/asm-um/processor-i386.h b/include/asm-um/processor-i386.h
deleted file mode 100644
index a2b7fe13fe1e..000000000000
--- a/include/asm-um/processor-i386.h
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_PROCESSOR_I386_H
-#define __UM_PROCESSOR_I386_H
-
-#include "linux/string.h"
-#include "asm/host_ldt.h"
-#include "asm/segment.h"
-
-extern int host_has_cmov;
-
-/* include faultinfo structure */
-#include "sysdep/faultinfo.h"
-
-struct uml_tls_struct {
-	struct user_desc tls;
-	unsigned flushed:1;
-	unsigned present:1;
-};
-
-struct arch_thread {
-	struct uml_tls_struct tls_array[GDT_ENTRY_TLS_ENTRIES];
-	unsigned long debugregs[8];
-	int debugregs_seq;
-	struct faultinfo faultinfo;
-};
-
-#define INIT_ARCH_THREAD { \
-	.tls_array  		= { [ 0 ... GDT_ENTRY_TLS_ENTRIES - 1 ] = \
-				    { .present = 0, .flushed = 0 } }, \
-	.debugregs  		= { [ 0 ... 7 ] = 0 }, \
-	.debugregs_seq		= 0, \
-	.faultinfo		= { 0, 0, 0 } \
-}
-
-static inline void arch_flush_thread(struct arch_thread *thread)
-{
-	/* Clear any TLS still hanging */
-	memset(&thread->tls_array, 0, sizeof(thread->tls_array));
-}
-
-static inline void arch_copy_thread(struct arch_thread *from,
-                                    struct arch_thread *to)
-{
-        memcpy(&to->tls_array, &from->tls_array, sizeof(from->tls_array));
-}
-
-#include "asm/arch/user.h"
-
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static inline void rep_nop(void)
-{
-	__asm__ __volatile__("rep;nop": : :"memory");
-}
-
-#define cpu_relax()	rep_nop()
-
-/*
- * Default implementation of macro that returns current
- * instruction pointer ("program counter"). Stolen
- * from asm-i386/processor.h
- */
-#define current_text_addr() \
-	({ void *pc; __asm__("movl $1f,%0\n1:":"=g" (pc)); pc; })
-
-#define ARCH_IS_STACKGROW(address) \
-       (address + 32 >= UPT_SP(&current->thread.regs.regs))
-
-#define KSTK_EIP(tsk) KSTK_REG(tsk, EIP)
-#define KSTK_ESP(tsk) KSTK_REG(tsk, UESP)
-#define KSTK_EBP(tsk) KSTK_REG(tsk, EBP)
-
-#include "asm/processor-generic.h"
-
-#endif
diff --git a/include/asm-um/processor-ppc.h b/include/asm-um/processor-ppc.h
deleted file mode 100644
index 959323151229..000000000000
--- a/include/asm-um/processor-ppc.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef __UM_PROCESSOR_PPC_H
-#define __UM_PROCESSOR_PPC_H
-
-#if defined(__ASSEMBLY__)
-
-#define CONFIG_PPC_MULTIPLATFORM
-#include "arch/processor.h"
-
-#else
-
-#include "asm/processor-generic.h"
-
-#endif
-
-#endif
diff --git a/include/asm-um/processor-x86_64.h b/include/asm-um/processor-x86_64.h
deleted file mode 100644
index e50933175e91..000000000000
--- a/include/asm-um/processor-x86_64.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_PROCESSOR_X86_64_H
-#define __UM_PROCESSOR_X86_64_H
-
-/* include faultinfo structure */
-#include "sysdep/faultinfo.h"
-
-struct arch_thread {
-        unsigned long debugregs[8];
-        int debugregs_seq;
-        unsigned long fs;
-        struct faultinfo faultinfo;
-};
-
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static inline void rep_nop(void)
-{
-	__asm__ __volatile__("rep;nop": : :"memory");
-}
-
-#define cpu_relax()   rep_nop()
-
-#define INIT_ARCH_THREAD { .debugregs  		= { [ 0 ... 7 ] = 0 }, \
-			   .debugregs_seq	= 0, \
-			   .fs			= 0, \
-			   .faultinfo		= { 0, 0, 0 } }
-
-static inline void arch_flush_thread(struct arch_thread *thread)
-{
-}
-
-static inline void arch_copy_thread(struct arch_thread *from,
-                                    struct arch_thread *to)
-{
-	to->fs = from->fs;
-}
-
-#include "asm/arch/user.h"
-
-#define current_text_addr() \
-	({ void *pc; __asm__("movq $1f,%0\n1:":"=g" (pc)); pc; })
-
-#define ARCH_IS_STACKGROW(address) \
-        (address + 128 >= UPT_SP(&current->thread.regs.regs))
-
-#define KSTK_EIP(tsk) KSTK_REG(tsk, RIP)
-#define KSTK_ESP(tsk) KSTK_REG(tsk, RSP)
-
-#include "asm/processor-generic.h"
-
-#endif
diff --git a/include/asm-um/ptrace-generic.h b/include/asm-um/ptrace-generic.h
deleted file mode 100644
index 315749705ea1..000000000000
--- a/include/asm-um/ptrace-generic.h
+++ /dev/null
@@ -1,55 +0,0 @@
-/* 
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_PTRACE_GENERIC_H
-#define __UM_PTRACE_GENERIC_H
-
-#ifndef __ASSEMBLY__
-
-#include "asm/arch/ptrace-abi.h"
-#include <asm/user.h>
-#include "sysdep/ptrace.h"
-
-struct pt_regs {
-	struct uml_pt_regs regs;
-};
-
-#define EMPTY_REGS { .regs = EMPTY_UML_PT_REGS }
-
-#define PT_REGS_IP(r) UPT_IP(&(r)->regs)
-#define PT_REGS_SP(r) UPT_SP(&(r)->regs)
-
-#define PT_REG(r, reg) UPT_REG(&(r)->regs, reg)
-#define PT_REGS_SET(r, reg, val) UPT_SET(&(r)->regs, reg, val)
-
-#define PT_REGS_SET_SYSCALL_RETURN(r, res) \
-	UPT_SET_SYSCALL_RETURN(&(r)->regs, res)
-#define PT_REGS_RESTART_SYSCALL(r) UPT_RESTART_SYSCALL(&(r)->regs)
-
-#define PT_REGS_SYSCALL_NR(r) UPT_SYSCALL_NR(&(r)->regs)
-
-#define PT_REGS_SC(r) UPT_SC(&(r)->regs)
-
-#define instruction_pointer(regs) PT_REGS_IP(regs)
-
-struct task_struct;
-
-extern long subarch_ptrace(struct task_struct *child, long request, long addr,
-			   long data);
-extern unsigned long getreg(struct task_struct *child, int regno);
-extern int putreg(struct task_struct *child, int regno, unsigned long value);
-extern int get_fpregs(struct user_i387_struct __user *buf,
-		      struct task_struct *child);
-extern int set_fpregs(struct user_i387_struct __user *buf,
-		      struct task_struct *child);
-
-extern void show_regs(struct pt_regs *regs);
-
-extern int arch_copy_tls(struct task_struct *new);
-extern void clear_flushed_tls(struct task_struct *task);
-
-#endif
-
-#endif
diff --git a/include/asm-um/ptrace-i386.h b/include/asm-um/ptrace-i386.h
deleted file mode 100644
index b2d24c5ea2c3..000000000000
--- a/include/asm-um/ptrace-i386.h
+++ /dev/null
@@ -1,60 +0,0 @@
-/* 
- * Copyright (C) 2000 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_PTRACE_I386_H
-#define __UM_PTRACE_I386_H
-
-#define HOST_AUDIT_ARCH AUDIT_ARCH_I386
-
-#include "linux/compiler.h"
-#include "asm/ptrace-generic.h"
-#include <asm/user.h>
-#include "sysdep/ptrace.h"
-
-#define PT_REGS_EAX(r) UPT_EAX(&(r)->regs)
-#define PT_REGS_EBX(r) UPT_EBX(&(r)->regs)
-#define PT_REGS_ECX(r) UPT_ECX(&(r)->regs)
-#define PT_REGS_EDX(r) UPT_EDX(&(r)->regs)
-#define PT_REGS_ESI(r) UPT_ESI(&(r)->regs)
-#define PT_REGS_EDI(r) UPT_EDI(&(r)->regs)
-#define PT_REGS_EBP(r) UPT_EBP(&(r)->regs)
-
-#define PT_REGS_CS(r) UPT_CS(&(r)->regs)
-#define PT_REGS_SS(r) UPT_SS(&(r)->regs)
-#define PT_REGS_DS(r) UPT_DS(&(r)->regs)
-#define PT_REGS_ES(r) UPT_ES(&(r)->regs)
-#define PT_REGS_FS(r) UPT_FS(&(r)->regs)
-#define PT_REGS_GS(r) UPT_GS(&(r)->regs)
-
-#define PT_REGS_EFLAGS(r) UPT_EFLAGS(&(r)->regs)
-
-#define PT_REGS_ORIG_SYSCALL(r) PT_REGS_EAX(r)
-#define PT_REGS_SYSCALL_RET(r) PT_REGS_EAX(r)
-#define PT_FIX_EXEC_STACK(sp) do ; while(0)
-
-/* Cope with a conditional i386 definition. */
-#undef profile_pc
-#define profile_pc(regs) PT_REGS_IP(regs)
-
-#define user_mode(r) UPT_IS_USER(&(r)->regs)
-
-/*
- * Forward declaration to avoid including sysdep/tls.h, which causes a
- * circular include, and compilation failures.
- */
-struct user_desc;
-
-extern int get_fpxregs(struct user_fxsr_struct __user *buf,
-		       struct task_struct *child);
-extern int set_fpxregs(struct user_fxsr_struct __user *buf,
-		       struct task_struct *tsk);
-
-extern int ptrace_get_thread_area(struct task_struct *child, int idx,
-                                  struct user_desc __user *user_desc);
-
-extern int ptrace_set_thread_area(struct task_struct *child, int idx,
-                                  struct user_desc __user *user_desc);
-
-#endif
diff --git a/include/asm-um/ptrace-x86_64.h b/include/asm-um/ptrace-x86_64.h
deleted file mode 100644
index 4c475350dcf0..000000000000
--- a/include/asm-um/ptrace-x86_64.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_PTRACE_X86_64_H
-#define __UM_PTRACE_X86_64_H
-
-#include "linux/compiler.h"
-#include "asm/errno.h"
-#include "asm/host_ldt.h"
-
-#define __FRAME_OFFSETS /* Needed to get the R* macros */
-#include "asm/ptrace-generic.h"
-
-#define HOST_AUDIT_ARCH AUDIT_ARCH_X86_64
-
-/* Also defined in sysdep/ptrace.h, so may already be defined. */
-#ifndef FS_BASE
-#define FS_BASE (21 * sizeof(unsigned long))
-#define GS_BASE (22 * sizeof(unsigned long))
-#define DS (23 * sizeof(unsigned long))
-#define ES (24 * sizeof(unsigned long))
-#define FS (25 * sizeof(unsigned long))
-#define GS (26 * sizeof(unsigned long))
-#endif
-
-#define PT_REGS_RBX(r) UPT_RBX(&(r)->regs)
-#define PT_REGS_RCX(r) UPT_RCX(&(r)->regs)
-#define PT_REGS_RDX(r) UPT_RDX(&(r)->regs)
-#define PT_REGS_RSI(r) UPT_RSI(&(r)->regs)
-#define PT_REGS_RDI(r) UPT_RDI(&(r)->regs)
-#define PT_REGS_RBP(r) UPT_RBP(&(r)->regs)
-#define PT_REGS_RAX(r) UPT_RAX(&(r)->regs)
-#define PT_REGS_R8(r) UPT_R8(&(r)->regs)
-#define PT_REGS_R9(r) UPT_R9(&(r)->regs)
-#define PT_REGS_R10(r) UPT_R10(&(r)->regs)
-#define PT_REGS_R11(r) UPT_R11(&(r)->regs)
-#define PT_REGS_R12(r) UPT_R12(&(r)->regs)
-#define PT_REGS_R13(r) UPT_R13(&(r)->regs)
-#define PT_REGS_R14(r) UPT_R14(&(r)->regs)
-#define PT_REGS_R15(r) UPT_R15(&(r)->regs)
-
-#define PT_REGS_FS(r) UPT_FS(&(r)->regs)
-#define PT_REGS_GS(r) UPT_GS(&(r)->regs)
-#define PT_REGS_DS(r) UPT_DS(&(r)->regs)
-#define PT_REGS_ES(r) UPT_ES(&(r)->regs)
-#define PT_REGS_SS(r) UPT_SS(&(r)->regs)
-#define PT_REGS_CS(r) UPT_CS(&(r)->regs)
-
-#define PT_REGS_ORIG_RAX(r) UPT_ORIG_RAX(&(r)->regs)
-#define PT_REGS_RIP(r) UPT_IP(&(r)->regs)
-#define PT_REGS_RSP(r) UPT_SP(&(r)->regs)
-
-#define PT_REGS_EFLAGS(r) UPT_EFLAGS(&(r)->regs)
-
-/* XXX */
-#define user_mode(r) UPT_IS_USER(&(r)->regs)
-#define PT_REGS_ORIG_SYSCALL(r) PT_REGS_RAX(r)
-#define PT_REGS_SYSCALL_RET(r) PT_REGS_RAX(r)
-
-#define PT_FIX_EXEC_STACK(sp) do ; while(0)
-
-#define profile_pc(regs) PT_REGS_IP(regs)
-
-static inline int ptrace_get_thread_area(struct task_struct *child, int idx,
-                                         struct user_desc __user *user_desc)
-{
-        return -ENOSYS;
-}
-
-static inline int ptrace_set_thread_area(struct task_struct *child, int idx,
-                                         struct user_desc __user *user_desc)
-{
-        return -ENOSYS;
-}
-
-extern long arch_prctl(struct task_struct *task, int code,
-		       unsigned long __user *addr);
-#endif
diff --git a/include/asm-um/required-features.h b/include/asm-um/required-features.h
deleted file mode 100644
index dfb967b2d2f3..000000000000
--- a/include/asm-um/required-features.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef __UM_REQUIRED_FEATURES_H
-#define __UM_REQUIRED_FEATURES_H
-
-/*
- * Nothing to see, just need something for the i386 and x86_64 asm
- * headers to include.
- */
-
-#endif
diff --git a/include/asm-um/resource.h b/include/asm-um/resource.h
deleted file mode 100644
index c9b074001252..000000000000
--- a/include/asm-um/resource.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_RESOURCE_H
-#define __UM_RESOURCE_H
-
-#include "asm/arch/resource.h"
-
-#endif
diff --git a/include/asm-um/rwlock.h b/include/asm-um/rwlock.h
deleted file mode 100644
index ff383aafc9fe..000000000000
--- a/include/asm-um/rwlock.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_RWLOCK_H
-#define __UM_RWLOCK_H
-
-#include "asm/arch/rwlock.h"
-
-#endif
diff --git a/include/asm-um/rwsem.h b/include/asm-um/rwsem.h
deleted file mode 100644
index b5fc449dc86b..000000000000
--- a/include/asm-um/rwsem.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_RWSEM_H__
-#define __UM_RWSEM_H__
-
-#include "asm/arch/rwsem.h"
-
-#endif
diff --git a/include/asm-um/scatterlist.h b/include/asm-um/scatterlist.h
deleted file mode 100644
index e92016aa2079..000000000000
--- a/include/asm-um/scatterlist.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SCATTERLIST_H
-#define __UM_SCATTERLIST_H
-
-#include "asm/arch/scatterlist.h"
-
-#endif
diff --git a/include/asm-um/sections.h b/include/asm-um/sections.h
deleted file mode 100644
index 6b0231eefea8..000000000000
--- a/include/asm-um/sections.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _UM_SECTIONS_H
-#define _UM_SECTIONS_H
-
-/* nothing to see, move along */
-#include <asm-generic/sections.h>
-
-#endif
diff --git a/include/asm-um/segment.h b/include/asm-um/segment.h
deleted file mode 100644
index 45183fcd10b6..000000000000
--- a/include/asm-um/segment.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __UM_SEGMENT_H
-#define __UM_SEGMENT_H
-
-extern int host_gdt_entry_tls_min;
-
-#define GDT_ENTRY_TLS_ENTRIES 3
-#define GDT_ENTRY_TLS_MIN host_gdt_entry_tls_min
-#define GDT_ENTRY_TLS_MAX (GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1)
-
-#endif
diff --git a/include/asm-um/sembuf.h b/include/asm-um/sembuf.h
deleted file mode 100644
index 1ae82c14ff86..000000000000
--- a/include/asm-um/sembuf.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SEMBUF_H
-#define __UM_SEMBUF_H
-
-#include "asm/arch/sembuf.h"
-
-#endif
diff --git a/include/asm-um/serial.h b/include/asm-um/serial.h
deleted file mode 100644
index 61ad07cfd2d5..000000000000
--- a/include/asm-um/serial.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SERIAL_H
-#define __UM_SERIAL_H
-
-#include "asm/arch/serial.h"
-
-#endif
diff --git a/include/asm-um/setup.h b/include/asm-um/setup.h
deleted file mode 100644
index 99f086301f4c..000000000000
--- a/include/asm-um/setup.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef SETUP_H_INCLUDED
-#define SETUP_H_INCLUDED
-
-/* POSIX mandated with _POSIX_ARG_MAX that we can rely on 4096 chars in the
- * command line, so this choice is ok.
- */
-
-#define COMMAND_LINE_SIZE 4096
-
-#endif		/* SETUP_H_INCLUDED */
diff --git a/include/asm-um/shmbuf.h b/include/asm-um/shmbuf.h
deleted file mode 100644
index 9684d4a284a6..000000000000
--- a/include/asm-um/shmbuf.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SHMBUF_H
-#define __UM_SHMBUF_H
-
-#include "asm/arch/shmbuf.h"
-
-#endif
diff --git a/include/asm-um/shmparam.h b/include/asm-um/shmparam.h
deleted file mode 100644
index 124c00174f6a..000000000000
--- a/include/asm-um/shmparam.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SHMPARAM_H
-#define __UM_SHMPARAM_H
-
-#include "asm/arch/shmparam.h"
-
-#endif
diff --git a/include/asm-um/sigcontext-generic.h b/include/asm-um/sigcontext-generic.h
deleted file mode 100644
index 164587014c61..000000000000
--- a/include/asm-um/sigcontext-generic.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SIGCONTEXT_GENERIC_H
-#define __UM_SIGCONTEXT_GENERIC_H
-
-#include "asm/arch/sigcontext.h"
-
-#endif
diff --git a/include/asm-um/sigcontext-i386.h b/include/asm-um/sigcontext-i386.h
deleted file mode 100644
index b88333f488bb..000000000000
--- a/include/asm-um/sigcontext-i386.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SIGCONTEXT_I386_H
-#define __UM_SIGCONTEXT_I386_H
-
-#include "asm/sigcontext-generic.h"
-
-#endif
diff --git a/include/asm-um/sigcontext-ppc.h b/include/asm-um/sigcontext-ppc.h
deleted file mode 100644
index 2467f20eda99..000000000000
--- a/include/asm-um/sigcontext-ppc.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __UM_SIGCONTEXT_PPC_H
-#define __UM_SIGCONTEXT_PPC_H
-
-#define pt_regs sys_pt_regs
-
-#include "asm/sigcontext-generic.h"
-
-#undef pt_regs
-
-#endif
diff --git a/include/asm-um/sigcontext-x86_64.h b/include/asm-um/sigcontext-x86_64.h
deleted file mode 100644
index b600e0b01e48..000000000000
--- a/include/asm-um/sigcontext-x86_64.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_SIGCONTEXT_X86_64_H
-#define __UM_SIGCONTEXT_X86_64_H
-
-#include "asm/sigcontext-generic.h"
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/include/asm-um/siginfo.h b/include/asm-um/siginfo.h
deleted file mode 100644
index bec6124c36d0..000000000000
--- a/include/asm-um/siginfo.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SIGINFO_H
-#define __UM_SIGINFO_H
-
-#include "asm/arch/siginfo.h"
-
-#endif
diff --git a/include/asm-um/signal.h b/include/asm-um/signal.h
deleted file mode 100644
index 52ed92cbce4c..000000000000
--- a/include/asm-um/signal.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* 
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_SIGNAL_H
-#define __UM_SIGNAL_H
-
-/* Need to kill the do_signal() declaration in the i386 signal.h */
-
-#define do_signal do_signal_renamed
-#include "asm/arch/signal.h"
-#undef do_signal
-#undef ptrace_signal_deliver
-
-#define ptrace_signal_deliver(regs, cookie) do {} while(0)
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/include/asm-um/smp.h b/include/asm-um/smp.h
deleted file mode 100644
index f27a96313174..000000000000
--- a/include/asm-um/smp.h
+++ /dev/null
@@ -1,33 +0,0 @@
-#ifndef __UM_SMP_H
-#define __UM_SMP_H
-
-#ifdef CONFIG_SMP
-
-#include "linux/bitops.h"
-#include "asm/current.h"
-#include "linux/cpumask.h"
-
-#define raw_smp_processor_id() (current_thread->cpu)
-
-#define cpu_logical_map(n) (n)
-#define cpu_number_map(n) (n)
-#define PROC_CHANGE_PENALTY	15 /* Pick a number, any number */
-extern int hard_smp_processor_id(void);
-#define NO_PROC_ID -1
-
-extern int ncpus;
-
-
-static inline void smp_cpus_done(unsigned int maxcpus)
-{
-}
-
-extern struct task_struct *idle_threads[NR_CPUS];
-
-#else
-
-#define hard_smp_processor_id()		0
-
-#endif
-
-#endif
diff --git a/include/asm-um/socket.h b/include/asm-um/socket.h
deleted file mode 100644
index 67886e42ef04..000000000000
--- a/include/asm-um/socket.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SOCKET_H
-#define __UM_SOCKET_H
-
-#include "asm/arch/socket.h"
-
-#endif
diff --git a/include/asm-um/sockios.h b/include/asm-um/sockios.h
deleted file mode 100644
index 93ee1c55c4d6..000000000000
--- a/include/asm-um/sockios.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SOCKIOS_H
-#define __UM_SOCKIOS_H
-
-#include "asm/arch/sockios.h"
-
-#endif
diff --git a/include/asm-um/spinlock.h b/include/asm-um/spinlock.h
deleted file mode 100644
index f18c82886992..000000000000
--- a/include/asm-um/spinlock.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SPINLOCK_H
-#define __UM_SPINLOCK_H
-
-#include "asm/arch/spinlock.h"
-
-#endif
diff --git a/include/asm-um/spinlock_types.h b/include/asm-um/spinlock_types.h
deleted file mode 100644
index e5a94294bf82..000000000000
--- a/include/asm-um/spinlock_types.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SPINLOCK_TYPES_H
-#define __UM_SPINLOCK_TYPES_H
-
-#include "asm/arch/spinlock_types.h"
-
-#endif
diff --git a/include/asm-um/stat.h b/include/asm-um/stat.h
deleted file mode 100644
index 83ed85ad2539..000000000000
--- a/include/asm-um/stat.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_STAT_H
-#define __UM_STAT_H
-
-#include "asm/arch/stat.h"
-
-#endif
diff --git a/include/asm-um/statfs.h b/include/asm-um/statfs.h
deleted file mode 100644
index ba6fb53e7f87..000000000000
--- a/include/asm-um/statfs.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _UM_STATFS_H
-#define _UM_STATFS_H
-
-#include "asm/arch/statfs.h"
-
-#endif
diff --git a/include/asm-um/string.h b/include/asm-um/string.h
deleted file mode 100644
index 9a0571f6dd61..000000000000
--- a/include/asm-um/string.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __UM_STRING_H
-#define __UM_STRING_H
-
-#include "asm/arch/string.h"
-#include "asm/archparam.h"
-
-#endif
diff --git a/include/asm-um/suspend.h b/include/asm-um/suspend.h
deleted file mode 100644
index f4e8e007f468..000000000000
--- a/include/asm-um/suspend.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef __UM_SUSPEND_H
-#define __UM_SUSPEND_H
-
-#endif
diff --git a/include/asm-um/system-generic.h b/include/asm-um/system-generic.h
deleted file mode 100644
index 5bcfa35e7a22..000000000000
--- a/include/asm-um/system-generic.h
+++ /dev/null
@@ -1,47 +0,0 @@
-#ifndef __UM_SYSTEM_GENERIC_H
-#define __UM_SYSTEM_GENERIC_H
-
-#include "asm/arch/system.h"
-
-#undef switch_to
-#undef local_irq_save
-#undef local_irq_restore
-#undef local_irq_disable
-#undef local_irq_enable
-#undef local_save_flags
-#undef local_irq_restore
-#undef local_irq_enable
-#undef local_irq_disable
-#undef local_irq_save
-#undef irqs_disabled
-
-extern void *switch_to(void *prev, void *next, void *last);
-
-extern int get_signals(void);
-extern int set_signals(int enable);
-extern int get_signals(void);
-extern void block_signals(void);
-extern void unblock_signals(void);
-
-#define local_save_flags(flags) do { typecheck(unsigned long, flags); \
-				     (flags) = get_signals(); } while(0)
-#define local_irq_restore(flags) do { typecheck(unsigned long, flags); \
-				      set_signals(flags); } while(0)
-
-#define local_irq_save(flags) do { local_save_flags(flags); \
-                                   local_irq_disable(); } while(0)
-
-#define local_irq_enable() unblock_signals()
-#define local_irq_disable() block_signals()
-
-#define irqs_disabled()                 \
-({                                      \
-        unsigned long flags;            \
-        local_save_flags(flags);        \
-        (flags == 0);                   \
-})
-
-extern void *_switch_to(void *prev, void *next, void *last);
-#define switch_to(prev, next, last) prev = _switch_to(prev, next, last)
-
-#endif
diff --git a/include/asm-um/system-i386.h b/include/asm-um/system-i386.h
deleted file mode 100644
index c436263e67ba..000000000000
--- a/include/asm-um/system-i386.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_SYSTEM_I386_H
-#define __UM_SYSTEM_I386_H
-
-#include "asm/system-generic.h"
-    
-#endif
diff --git a/include/asm-um/system-ppc.h b/include/asm-um/system-ppc.h
deleted file mode 100644
index 17cde6640bf5..000000000000
--- a/include/asm-um/system-ppc.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __UM_SYSTEM_PPC_H
-#define __UM_SYSTEM_PPC_H
-
-#define _switch_to _ppc_switch_to
-
-#include "asm/arch/system.h"
-
-#undef _switch_to
- 
-#include "asm/system-generic.h"
-
-#endif
diff --git a/include/asm-um/system-x86_64.h b/include/asm-um/system-x86_64.h
deleted file mode 100644
index e1b61b580734..000000000000
--- a/include/asm-um/system-x86_64.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __UM_SYSTEM_X86_64_H
-#define __UM_SYSTEM_X86_64_H
-
-#include "asm/system-generic.h"
-
-#endif
-
-/*
- * Overrides for Emacs so that we follow Linus's tabbing style.
- * Emacs will notice this stuff at the end of the file and automatically
- * adjust the settings for this buffer only.  This must remain at the end
- * of the file.
- * ---------------------------------------------------------------------------
- * Local variables:
- * c-file-style: "linux"
- * End:
- */
diff --git a/include/asm-um/termbits.h b/include/asm-um/termbits.h
deleted file mode 100644
index 5739c608a2cb..000000000000
--- a/include/asm-um/termbits.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_TERMBITS_H
-#define __UM_TERMBITS_H
-
-#include "asm/arch/termbits.h"
-
-#endif
diff --git a/include/asm-um/termios.h b/include/asm-um/termios.h
deleted file mode 100644
index d9f97b303311..000000000000
--- a/include/asm-um/termios.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_TERMIOS_H
-#define __UM_TERMIOS_H
-
-#include "asm/arch/termios.h"
-
-#endif
diff --git a/include/asm-um/thread_info.h b/include/asm-um/thread_info.h
deleted file mode 100644
index 62274ab9471f..000000000000
--- a/include/asm-um/thread_info.h
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_THREAD_INFO_H
-#define __UM_THREAD_INFO_H
-
-#ifndef __ASSEMBLY__
-
-#include <asm/types.h>
-#include <asm/page.h>
-#include <asm/uaccess.h>
-
-struct thread_info {
-	struct task_struct	*task;		/* main task structure */
-	struct exec_domain	*exec_domain;	/* execution domain */
-	unsigned long		flags;		/* low level flags */
-	__u32			cpu;		/* current CPU */
-	int			preempt_count;  /* 0 => preemptable,
-						   <0 => BUG */
-	mm_segment_t		addr_limit;	/* thread address space:
-					 	   0-0xBFFFFFFF for user
-						   0-0xFFFFFFFF for kernel */
-	struct restart_block    restart_block;
-	struct thread_info	*real_thread;    /* Points to non-IRQ stack */
-};
-
-#define INIT_THREAD_INFO(tsk)			\
-{						\
-	.task =		&tsk,			\
-	.exec_domain =	&default_exec_domain,	\
-	.flags =		0,		\
-	.cpu =		0,			\
-	.preempt_count =	1,		\
-	.addr_limit =	KERNEL_DS,		\
-	.restart_block =  {			\
-		.fn =  do_no_restart_syscall,	\
-	},					\
-	.real_thread = NULL,			\
-}
-
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
-#define THREAD_SIZE ((1 << CONFIG_KERNEL_STACK_ORDER) * PAGE_SIZE)
-/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-	struct thread_info *ti;
-	unsigned long mask = THREAD_SIZE - 1;
-	ti = (struct thread_info *) (((unsigned long) &ti) & ~mask);
-	return ti;
-}
-
-#define THREAD_SIZE_ORDER CONFIG_KERNEL_STACK_ORDER
-
-#endif
-
-#define PREEMPT_ACTIVE		0x10000000
-
-#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
-#define TIF_SIGPENDING		1	/* signal pending */
-#define TIF_NEED_RESCHED	2	/* rescheduling necessary */
-#define TIF_POLLING_NRFLAG      3       /* true if poll_idle() is polling
-					 * TIF_NEED_RESCHED
-					 */
-#define TIF_RESTART_BLOCK 	4
-#define TIF_MEMDIE	 	5
-#define TIF_SYSCALL_AUDIT	6
-#define TIF_RESTORE_SIGMASK	7
-#define TIF_FREEZE		16	/* is freezing for suspend */
-
-#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
-#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
-#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
-#define _TIF_POLLING_NRFLAG     (1 << TIF_POLLING_NRFLAG)
-#define _TIF_MEMDIE		(1 << TIF_MEMDIE)
-#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
-#define _TIF_RESTORE_SIGMASK	(1 << TIF_RESTORE_SIGMASK)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
-
-#endif
diff --git a/include/asm-um/timex.h b/include/asm-um/timex.h
deleted file mode 100644
index 0f4ada08f748..000000000000
--- a/include/asm-um/timex.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __UM_TIMEX_H
-#define __UM_TIMEX_H
-
-typedef unsigned long cycles_t;
-
-static inline cycles_t get_cycles (void)
-{
-	return 0;
-}
-
-#define CLOCK_TICK_RATE (HZ)
-
-#endif
diff --git a/include/asm-um/tlb.h b/include/asm-um/tlb.h
deleted file mode 100644
index 5240fa1c5e08..000000000000
--- a/include/asm-um/tlb.h
+++ /dev/null
@@ -1,127 +0,0 @@
-#ifndef __UM_TLB_H
-#define __UM_TLB_H
-
-#include <linux/pagemap.h>
-#include <linux/swap.h>
-#include <asm/percpu.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
-/* struct mmu_gather is an opaque type used by the mm code for passing around
- * any data needed by arch specific code for tlb_remove_page.
- */
-struct mmu_gather {
-	struct mm_struct	*mm;
-	unsigned int		need_flush; /* Really unmapped some ptes? */
-	unsigned long		start;
-	unsigned long		end;
-	unsigned int		fullmm; /* non-zero means full mm flush */
-};
-
-/* Users of the generic TLB shootdown code must declare this storage space. */
-DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
-
-static inline void __tlb_remove_tlb_entry(struct mmu_gather *tlb, pte_t *ptep,
-					  unsigned long address)
-{
-	if (tlb->start > address)
-		tlb->start = address;
-	if (tlb->end < address + PAGE_SIZE)
-		tlb->end = address + PAGE_SIZE;
-}
-
-static inline void init_tlb_gather(struct mmu_gather *tlb)
-{
-	tlb->need_flush = 0;
-
-	tlb->start = TASK_SIZE;
-	tlb->end = 0;
-
-	if (tlb->fullmm) {
-		tlb->start = 0;
-		tlb->end = TASK_SIZE;
-	}
-}
-
-/* tlb_gather_mmu
- *	Return a pointer to an initialized struct mmu_gather.
- */
-static inline struct mmu_gather *
-tlb_gather_mmu(struct mm_struct *mm, unsigned int full_mm_flush)
-{
-	struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
-
-	tlb->mm = mm;
-	tlb->fullmm = full_mm_flush;
-
-	init_tlb_gather(tlb);
-
-	return tlb;
-}
-
-extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
-			       unsigned long end);
-
-static inline void
-tlb_flush_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-	if (!tlb->need_flush)
-		return;
-
-	flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end);
-	init_tlb_gather(tlb);
-}
-
-/* tlb_finish_mmu
- *	Called at the end of the shootdown operation to free up any resources
- *	that were required.
- */
-static inline void
-tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end)
-{
-	tlb_flush_mmu(tlb, start, end);
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	put_cpu_var(mmu_gathers);
-}
-
-/* tlb_remove_page
- *	Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)),
- *	while handling the additional races in SMP caused by other CPUs
- *	caching valid mappings in their TLBs.
- */
-static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
-{
-	tlb->need_flush = 1;
-	free_page_and_swap_cache(page);
-	return;
-}
-
-/**
- * tlb_remove_tlb_entry - remember a pte unmapping for later tlb invalidation.
- *
- * Record the fact that pte's were really umapped in ->need_flush, so we can
- * later optimise away the tlb invalidate.   This helps when userspace is
- * unmapping already-unmapped pages, which happens quite a lot.
- */
-#define tlb_remove_tlb_entry(tlb, ptep, address)		\
-	do {							\
-		tlb->need_flush = 1;				\
-		__tlb_remove_tlb_entry(tlb, ptep, address);	\
-	} while (0)
-
-#define pte_free_tlb(tlb, ptep) __pte_free_tlb(tlb, ptep)
-
-#define pud_free_tlb(tlb, pudp) __pud_free_tlb(tlb, pudp)
-
-#define pmd_free_tlb(tlb, pmdp) __pmd_free_tlb(tlb, pmdp)
-
-#define tlb_migrate_finish(mm) do {} while (0)
-
-#endif
diff --git a/include/asm-um/tlbflush.h b/include/asm-um/tlbflush.h
deleted file mode 100644
index 614f2c091178..000000000000
--- a/include/asm-um/tlbflush.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Copyright (C) 2002 - 2007 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_TLBFLUSH_H
-#define __UM_TLBFLUSH_H
-
-#include <linux/mm.h>
-
-/*
- * TLB flushing:
- *
- *  - flush_tlb() flushes the current mm struct TLBs
- *  - flush_tlb_all() flushes all processes TLBs
- *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
- *  - flush_tlb_page(vma, vmaddr) flushes one page
- *  - flush_tlb_kernel_vm() flushes the kernel vm area
- *  - flush_tlb_range(vma, start, end) flushes a range of pages
- */
-
-extern void flush_tlb_all(void);
-extern void flush_tlb_mm(struct mm_struct *mm);
-extern void flush_tlb_range(struct vm_area_struct *vma, unsigned long start, 
-			    unsigned long end);
-extern void flush_tlb_page(struct vm_area_struct *vma, unsigned long address);
-extern void flush_tlb_kernel_vm(void);
-extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
-extern void __flush_tlb_one(unsigned long addr);
-
-#endif
diff --git a/include/asm-um/topology.h b/include/asm-um/topology.h
deleted file mode 100644
index 0905e4f21d42..000000000000
--- a/include/asm-um/topology.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_UM_TOPOLOGY_H
-#define _ASM_UM_TOPOLOGY_H
-
-#include <asm-generic/topology.h>
-
-#endif
diff --git a/include/asm-um/types.h b/include/asm-um/types.h
deleted file mode 100644
index 816e9590fc73..000000000000
--- a/include/asm-um/types.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_TYPES_H
-#define __UM_TYPES_H
-
-#include "asm/arch/types.h"
-
-#endif
diff --git a/include/asm-um/uaccess.h b/include/asm-um/uaccess.h
deleted file mode 100644
index b9a895d6fa1d..000000000000
--- a/include/asm-um/uaccess.h
+++ /dev/null
@@ -1,99 +0,0 @@
-/* 
- * Copyright (C) 2002 Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef __UM_UACCESS_H
-#define __UM_UACCESS_H
-
-#include <asm/errno.h>
-#include <asm/processor.h>
-
-/* thread_info has a mm_segment_t in it, so put the definition up here */
-typedef struct {
-	unsigned long seg;
-} mm_segment_t;
-
-#include "linux/thread_info.h"
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not.  If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons, these macros are grossly misnamed.
- */
-
-#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
-
-#define KERNEL_DS	MAKE_MM_SEG(0xFFFFFFFF)
-#define USER_DS		MAKE_MM_SEG(TASK_SIZE)
-
-#define get_ds()	(KERNEL_DS)
-#define get_fs()	(current_thread_info()->addr_limit)
-#define set_fs(x)	(current_thread_info()->addr_limit = (x))
-
-#define segment_eq(a, b) ((a).seg == (b).seg)
-
-#include "um_uaccess.h"
-
-#define __copy_from_user(to, from, n) copy_from_user(to, from, n)
-
-#define __copy_to_user(to, from, n) copy_to_user(to, from, n)
-
-#define __copy_to_user_inatomic __copy_to_user
-#define __copy_from_user_inatomic __copy_from_user
-
-#define __get_user(x, ptr) \
-({ \
-	const __typeof__(*(ptr)) __user *__private_ptr = (ptr);	\
-	__typeof__(x) __private_val;			\
-	int __private_ret = -EFAULT;			\
-	(x) = (__typeof__(*(__private_ptr)))0;				\
-	if (__copy_from_user((__force void *)&__private_val, (__private_ptr),\
-			     sizeof(*(__private_ptr))) == 0) {		\
-		(x) = (__typeof__(*(__private_ptr))) __private_val;	\
-		__private_ret = 0;					\
-	}								\
-	__private_ret;							\
-}) 
-
-#define get_user(x, ptr) \
-({ \
-        const __typeof__((*(ptr))) __user *private_ptr = (ptr); \
-        (access_ok(VERIFY_READ, private_ptr, sizeof(*private_ptr)) ? \
-	 __get_user(x, private_ptr) : ((x) = (__typeof__(*ptr))0, -EFAULT)); \
-})
-
-#define __put_user(x, ptr) \
-({ \
-        __typeof__(*(ptr)) __user *__private_ptr = ptr; \
-        __typeof__(*(__private_ptr)) __private_val; \
-        int __private_ret = -EFAULT; \
-        __private_val = (__typeof__(*(__private_ptr))) (x); \
-        if (__copy_to_user((__private_ptr), &__private_val, \
-			   sizeof(*(__private_ptr))) == 0) { \
-		__private_ret = 0; \
-	} \
-        __private_ret; \
-})
-
-#define put_user(x, ptr) \
-({ \
-        __typeof__(*(ptr)) __user *private_ptr = (ptr); \
-        (access_ok(VERIFY_WRITE, private_ptr, sizeof(*private_ptr)) ? \
-	 __put_user(x, private_ptr) : -EFAULT); \
-})
-
-#define strlen_user(str) strnlen_user(str, ~0U >> 1)
-
-struct exception_table_entry
-{
-        unsigned long insn;
-	unsigned long fixup;
-};
-
-#endif
diff --git a/include/asm-um/ucontext.h b/include/asm-um/ucontext.h
deleted file mode 100644
index 5c96c0e607f0..000000000000
--- a/include/asm-um/ucontext.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_UM_UCONTEXT_H
-#define _ASM_UM_UCONTEXT_H
-
-#include "asm/arch/ucontext.h"
-
-#endif
diff --git a/include/asm-um/unaligned.h b/include/asm-um/unaligned.h
deleted file mode 100644
index a47196974e39..000000000000
--- a/include/asm-um/unaligned.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_UM_UNALIGNED_H
-#define _ASM_UM_UNALIGNED_H
-
-#include "asm/arch/unaligned.h"
-
-#endif /* _ASM_UM_UNALIGNED_H */
diff --git a/include/asm-um/unistd.h b/include/asm-um/unistd.h
deleted file mode 100644
index 38bd9d94ee46..000000000000
--- a/include/asm-um/unistd.h
+++ /dev/null
@@ -1,41 +0,0 @@
-/* 
- * Copyright (C) 2000 - 2004  Jeff Dike (jdike@karaya.com)
- * Licensed under the GPL
- */
-
-#ifndef _UM_UNISTD_H_
-#define _UM_UNISTD_H_
-
-#include <linux/syscalls.h>
-#include "linux/resource.h"
-#include "asm/uaccess.h"
-
-extern int um_execve(const char *file, char *const argv[], char *const env[]);
-
-#ifdef __KERNEL__
-/* We get __ARCH_WANT_OLD_STAT and __ARCH_WANT_STAT64 from the base arch */
-#define __ARCH_WANT_OLD_READDIR
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_SGETMASK
-#define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_SOCKETCALL
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_NICE
-#define __ARCH_WANT_SYS_OLD_GETRLIMIT
-#define __ARCH_WANT_SYS_OLDUMOUNT
-#define __ARCH_WANT_SYS_SIGPENDING
-#define __ARCH_WANT_SYS_SIGPROCMASK
-#define __ARCH_WANT_SYS_RT_SIGACTION
-#define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#endif
-
-#include "asm/arch/unistd.h"
-
-#endif /* _UM_UNISTD_H_*/
diff --git a/include/asm-um/user.h b/include/asm-um/user.h
deleted file mode 100644
index aae414ee1f5e..000000000000
--- a/include/asm-um/user.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_USER_H
-#define __UM_USER_H
-
-#include "asm/arch/user.h"
-
-#endif
diff --git a/include/asm-um/vga.h b/include/asm-um/vga.h
deleted file mode 100644
index 903a592b00d0..000000000000
--- a/include/asm-um/vga.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_VGA_H
-#define __UM_VGA_H
-
-#include "asm/arch/vga.h"
-
-#endif
diff --git a/include/asm-um/vm-flags-i386.h b/include/asm-um/vm-flags-i386.h
deleted file mode 100644
index e0d24c568dbc..000000000000
--- a/include/asm-um/vm-flags-i386.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * Copyright (C) 2004 Jeff Dike (jdike@addtoit.com)
- * Licensed under the GPL
- */
-
-#ifndef __VM_FLAGS_I386_H
-#define __VM_FLAGS_I386_H
-
-#define VM_DATA_DEFAULT_FLAGS \
-	(VM_READ | VM_WRITE | \
-	((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
-		 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
-#endif
diff --git a/include/asm-um/vm-flags-x86_64.h b/include/asm-um/vm-flags-x86_64.h
deleted file mode 100644
index 3213edfa7888..000000000000
--- a/include/asm-um/vm-flags-x86_64.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- * Copyright (C) 2004 Jeff Dike (jdike@addtoit.com)
- * Copyright 2003 PathScale, Inc.
- * Licensed under the GPL
- */
-
-#ifndef __VM_FLAGS_X86_64_H
-#define __VM_FLAGS_X86_64_H
-
-#define __VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
-				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-#define __VM_STACK_FLAGS 	(VM_GROWSDOWN | VM_READ | VM_WRITE | \
-				 VM_EXEC | VM_MAYREAD | VM_MAYWRITE | \
-				 VM_MAYEXEC)
-
-extern unsigned long vm_stack_flags, vm_stack_flags32;
-extern unsigned long vm_data_default_flags, vm_data_default_flags32;
-extern unsigned long vm_force_exec32;
-
-#ifdef TIF_IA32
-#define VM_DATA_DEFAULT_FLAGS \
-	(test_thread_flag(TIF_IA32) ? vm_data_default_flags32 : \
-	  vm_data_default_flags)
-
-#define VM_STACK_DEFAULT_FLAGS \
-	(test_thread_flag(TIF_IA32) ? vm_stack_flags32 : vm_stack_flags)
-#endif
-
-#define VM_DATA_DEFAULT_FLAGS vm_data_default_flags
-
-#define VM_STACK_DEFAULT_FLAGS vm_stack_flags
-
-#endif
diff --git a/include/asm-um/vm86.h b/include/asm-um/vm86.h
deleted file mode 100644
index 7801f82de1f4..000000000000
--- a/include/asm-um/vm86.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_VM86_H
-#define __UM_VM86_H
-
-#include "asm/arch/vm86.h"
-
-#endif
diff --git a/include/asm-um/xor.h b/include/asm-um/xor.h
deleted file mode 100644
index a19db3e17241..000000000000
--- a/include/asm-um/xor.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __UM_XOR_H
-#define __UM_XOR_H
-
-#include "asm-generic/xor.h"
-
-#endif
-- 
cgit v1.2.3


From bb8985586b7a906e116db835c64773b7a7d51663 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 17 Aug 2008 21:05:42 -0400
Subject: x86, um: ... and asm-x86 move

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
---
 arch/ia64/ia32/audit.c                            |    2 +-
 arch/um/Makefile                                  |    4 +-
 arch/um/sys-x86_64/syscall_table.c                |    4 +-
 arch/x86/Makefile                                 |    6 +-
 arch/x86/include/asm/Kbuild                       |   24 +
 arch/x86/include/asm/a.out-core.h                 |   73 +
 arch/x86/include/asm/a.out.h                      |   20 +
 arch/x86/include/asm/acpi.h                       |  178 +++
 arch/x86/include/asm/agp.h                        |   35 +
 arch/x86/include/asm/alternative-asm.h            |   22 +
 arch/x86/include/asm/alternative.h                |  183 +++
 arch/x86/include/asm/amd_iommu.h                  |   35 +
 arch/x86/include/asm/amd_iommu_types.h            |  404 +++++
 arch/x86/include/asm/apic.h                       |  199 +++
 arch/x86/include/asm/apicdef.h                    |  417 ++++++
 arch/x86/include/asm/arch_hooks.h                 |   26 +
 arch/x86/include/asm/asm.h                        |   47 +
 arch/x86/include/asm/atomic.h                     |    5 +
 arch/x86/include/asm/atomic_32.h                  |  259 ++++
 arch/x86/include/asm/atomic_64.h                  |  473 ++++++
 arch/x86/include/asm/auxvec.h                     |   12 +
 arch/x86/include/asm/bigsmp/apic.h                |  139 ++
 arch/x86/include/asm/bigsmp/apicdef.h             |   13 +
 arch/x86/include/asm/bigsmp/ipi.h                 |   25 +
 arch/x86/include/asm/bios_ebda.h                  |   36 +
 arch/x86/include/asm/bitops.h                     |  451 ++++++
 arch/x86/include/asm/boot.h                       |   26 +
 arch/x86/include/asm/bootparam.h                  |  111 ++
 arch/x86/include/asm/bug.h                        |   39 +
 arch/x86/include/asm/bugs.h                       |   12 +
 arch/x86/include/asm/byteorder.h                  |   81 +
 arch/x86/include/asm/cache.h                      |   20 +
 arch/x86/include/asm/cacheflush.h                 |  118 ++
 arch/x86/include/asm/calgary.h                    |   72 +
 arch/x86/include/asm/calling.h                    |  170 +++
 arch/x86/include/asm/checksum.h                   |    5 +
 arch/x86/include/asm/checksum_32.h                |  189 +++
 arch/x86/include/asm/checksum_64.h                |  191 +++
 arch/x86/include/asm/cmpxchg.h                    |    5 +
 arch/x86/include/asm/cmpxchg_32.h                 |  344 +++++
 arch/x86/include/asm/cmpxchg_64.h                 |  185 +++
 arch/x86/include/asm/compat.h                     |  218 +++
 arch/x86/include/asm/cpu.h                        |   20 +
 arch/x86/include/asm/cpufeature.h                 |  271 ++++
 arch/x86/include/asm/cputime.h                    |    1 +
 arch/x86/include/asm/current.h                    |   39 +
 arch/x86/include/asm/debugreg.h                   |   70 +
 arch/x86/include/asm/delay.h                      |   31 +
 arch/x86/include/asm/desc.h                       |  409 +++++
 arch/x86/include/asm/desc_defs.h                  |   95 ++
 arch/x86/include/asm/device.h                     |   16 +
 arch/x86/include/asm/div64.h                      |   60 +
 arch/x86/include/asm/dma-mapping.h                |  308 ++++
 arch/x86/include/asm/dma.h                        |  318 ++++
 arch/x86/include/asm/dmi.h                        |   26 +
 arch/x86/include/asm/ds.h                         |  238 +++
 arch/x86/include/asm/dwarf2.h                     |   61 +
 arch/x86/include/asm/e820.h                       |  146 ++
 arch/x86/include/asm/edac.h                       |   18 +
 arch/x86/include/asm/efi.h                        |  110 ++
 arch/x86/include/asm/elf.h                        |  336 +++++
 arch/x86/include/asm/emergency-restart.h          |   18 +
 arch/x86/include/asm/errno.h                      |    1 +
 arch/x86/include/asm/es7000/apic.h                |  193 +++
 arch/x86/include/asm/es7000/apicdef.h             |   13 +
 arch/x86/include/asm/es7000/ipi.h                 |   24 +
 arch/x86/include/asm/es7000/mpparse.h             |   30 +
 arch/x86/include/asm/es7000/wakecpu.h             |   59 +
 arch/x86/include/asm/fb.h                         |   21 +
 arch/x86/include/asm/fcntl.h                      |    1 +
 arch/x86/include/asm/fixmap.h                     |   68 +
 arch/x86/include/asm/fixmap_32.h                  |  123 ++
 arch/x86/include/asm/fixmap_64.h                  |   83 ++
 arch/x86/include/asm/floppy.h                     |  281 ++++
 arch/x86/include/asm/frame.h                      |   27 +
 arch/x86/include/asm/ftrace.h                     |   24 +
 arch/x86/include/asm/futex.h                      |  140 ++
 arch/x86/include/asm/gart.h                       |   73 +
 arch/x86/include/asm/genapic.h                    |    5 +
 arch/x86/include/asm/genapic_32.h                 |  126 ++
 arch/x86/include/asm/genapic_64.h                 |   58 +
 arch/x86/include/asm/geode.h                      |  253 ++++
 arch/x86/include/asm/gpio.h                       |   56 +
 arch/x86/include/asm/hardirq.h                    |   11 +
 arch/x86/include/asm/hardirq_32.h                 |   28 +
 arch/x86/include/asm/hardirq_64.h                 |   23 +
 arch/x86/include/asm/highmem.h                    |   82 +
 arch/x86/include/asm/hpet.h                       |  114 ++
 arch/x86/include/asm/hugetlb.h                    |   93 ++
 arch/x86/include/asm/hw_irq.h                     |  131 ++
 arch/x86/include/asm/hypertransport.h             |   45 +
 arch/x86/include/asm/i387.h                       |  400 +++++
 arch/x86/include/asm/i8253.h                      |   18 +
 arch/x86/include/asm/i8259.h                      |   63 +
 arch/x86/include/asm/ia32.h                       |  170 +++
 arch/x86/include/asm/ia32_unistd.h                |   18 +
 arch/x86/include/asm/idle.h                       |   15 +
 arch/x86/include/asm/intel_arch_perfmon.h         |   31 +
 arch/x86/include/asm/io.h                         |   91 ++
 arch/x86/include/asm/io_32.h                      |  284 ++++
 arch/x86/include/asm/io_64.h                      |  244 +++
 arch/x86/include/asm/io_apic.h                    |  204 +++
 arch/x86/include/asm/ioctl.h                      |    1 +
 arch/x86/include/asm/ioctls.h                     |   94 ++
 arch/x86/include/asm/iommu.h                      |   46 +
 arch/x86/include/asm/ipcbuf.h                     |   28 +
 arch/x86/include/asm/ipi.h                        |  138 ++
 arch/x86/include/asm/irq.h                        |   50 +
 arch/x86/include/asm/irq_regs.h                   |    5 +
 arch/x86/include/asm/irq_regs_32.h                |   29 +
 arch/x86/include/asm/irq_regs_64.h                |    1 +
 arch/x86/include/asm/irq_remapping.h              |    8 +
 arch/x86/include/asm/irq_vectors.h                |  164 ++
 arch/x86/include/asm/irqflags.h                   |  211 +++
 arch/x86/include/asm/ist.h                        |   34 +
 arch/x86/include/asm/k8.h                         |   15 +
 arch/x86/include/asm/kdebug.h                     |   37 +
 arch/x86/include/asm/kexec.h                      |  175 +++
 arch/x86/include/asm/kgdb.h                       |   79 +
 arch/x86/include/asm/kmap_types.h                 |   29 +
 arch/x86/include/asm/kprobes.h                    |   88 ++
 arch/x86/include/asm/kvm.h                        |  211 +++
 arch/x86/include/asm/kvm_host.h                   |  752 ++++++++++
 arch/x86/include/asm/kvm_para.h                   |  147 ++
 arch/x86/include/asm/kvm_x86_emulate.h            |  184 +++
 arch/x86/include/asm/ldt.h                        |   40 +
 arch/x86/include/asm/lguest.h                     |   94 ++
 arch/x86/include/asm/lguest_hcall.h               |   71 +
 arch/x86/include/asm/linkage.h                    |   61 +
 arch/x86/include/asm/local.h                      |  235 +++
 arch/x86/include/asm/mach-default/apm.h           |   73 +
 arch/x86/include/asm/mach-default/do_timer.h      |   16 +
 arch/x86/include/asm/mach-default/entry_arch.h    |   36 +
 arch/x86/include/asm/mach-default/mach_apic.h     |  156 ++
 arch/x86/include/asm/mach-default/mach_apicdef.h  |   24 +
 arch/x86/include/asm/mach-default/mach_ipi.h      |   64 +
 arch/x86/include/asm/mach-default/mach_mpparse.h  |   17 +
 arch/x86/include/asm/mach-default/mach_mpspec.h   |   12 +
 arch/x86/include/asm/mach-default/mach_timer.h    |   48 +
 arch/x86/include/asm/mach-default/mach_traps.h    |   33 +
 arch/x86/include/asm/mach-default/mach_wakecpu.h  |   42 +
 arch/x86/include/asm/mach-default/pci-functions.h |   19 +
 arch/x86/include/asm/mach-default/setup_arch.h    |    3 +
 arch/x86/include/asm/mach-default/smpboot_hooks.h |   59 +
 arch/x86/include/asm/mach-generic/gpio.h          |   15 +
 arch/x86/include/asm/mach-generic/mach_apic.h     |   33 +
 arch/x86/include/asm/mach-generic/mach_apicdef.h  |   11 +
 arch/x86/include/asm/mach-generic/mach_ipi.h      |   10 +
 arch/x86/include/asm/mach-generic/mach_mpparse.h  |   10 +
 arch/x86/include/asm/mach-generic/mach_mpspec.h   |   12 +
 arch/x86/include/asm/mach-rdc321x/gpio.h          |   60 +
 arch/x86/include/asm/mach-rdc321x/rdc321x_defs.h  |   12 +
 arch/x86/include/asm/mach-voyager/do_timer.h      |   17 +
 arch/x86/include/asm/mach-voyager/entry_arch.h    |   26 +
 arch/x86/include/asm/mach-voyager/setup_arch.h    |   12 +
 arch/x86/include/asm/math_emu.h                   |   31 +
 arch/x86/include/asm/mc146818rtc.h                |  104 ++
 arch/x86/include/asm/mca.h                        |   43 +
 arch/x86/include/asm/mca_dma.h                    |  201 +++
 arch/x86/include/asm/mce.h                        |  130 ++
 arch/x86/include/asm/microcode.h                  |   47 +
 arch/x86/include/asm/mman.h                       |   20 +
 arch/x86/include/asm/mmconfig.h                   |   12 +
 arch/x86/include/asm/mmu.h                        |   26 +
 arch/x86/include/asm/mmu_context.h                |   37 +
 arch/x86/include/asm/mmu_context_32.h             |   56 +
 arch/x86/include/asm/mmu_context_64.h             |   54 +
 arch/x86/include/asm/mmx.h                        |   14 +
 arch/x86/include/asm/mmzone.h                     |    5 +
 arch/x86/include/asm/mmzone_32.h                  |  134 ++
 arch/x86/include/asm/mmzone_64.h                  |   51 +
 arch/x86/include/asm/module.h                     |   80 +
 arch/x86/include/asm/mpspec.h                     |  145 ++
 arch/x86/include/asm/mpspec_def.h                 |  180 +++
 arch/x86/include/asm/msgbuf.h                     |   39 +
 arch/x86/include/asm/msidef.h                     |   55 +
 arch/x86/include/asm/msr-index.h                  |  332 +++++
 arch/x86/include/asm/msr.h                        |  247 +++
 arch/x86/include/asm/mtrr.h                       |  173 +++
 arch/x86/include/asm/mutex.h                      |    5 +
 arch/x86/include/asm/mutex_32.h                   |  125 ++
 arch/x86/include/asm/mutex_64.h                   |  100 ++
 arch/x86/include/asm/nmi.h                        |   81 +
 arch/x86/include/asm/nops.h                       |  118 ++
 arch/x86/include/asm/numa.h                       |    5 +
 arch/x86/include/asm/numa_32.h                    |   11 +
 arch/x86/include/asm/numa_64.h                    |   43 +
 arch/x86/include/asm/numaq.h                      |  169 +++
 arch/x86/include/asm/numaq/apic.h                 |  136 ++
 arch/x86/include/asm/numaq/apicdef.h              |   14 +
 arch/x86/include/asm/numaq/ipi.h                  |   25 +
 arch/x86/include/asm/numaq/mpparse.h              |    7 +
 arch/x86/include/asm/numaq/wakecpu.h              |   43 +
 arch/x86/include/asm/olpc.h                       |  132 ++
 arch/x86/include/asm/page.h                       |  209 +++
 arch/x86/include/asm/page_32.h                    |  136 ++
 arch/x86/include/asm/page_64.h                    |  105 ++
 arch/x86/include/asm/param.h                      |   22 +
 arch/x86/include/asm/paravirt.h                   | 1650 +++++++++++++++++++++
 arch/x86/include/asm/parport.h                    |   10 +
 arch/x86/include/asm/pat.h                        |   22 +
 arch/x86/include/asm/pci-direct.h                 |   21 +
 arch/x86/include/asm/pci.h                        |  114 ++
 arch/x86/include/asm/pci_32.h                     |   34 +
 arch/x86/include/asm/pci_64.h                     |   66 +
 arch/x86/include/asm/pda.h                        |  137 ++
 arch/x86/include/asm/percpu.h                     |  218 +++
 arch/x86/include/asm/pgalloc.h                    |  114 ++
 arch/x86/include/asm/pgtable-2level-defs.h        |   20 +
 arch/x86/include/asm/pgtable-2level.h             |   79 +
 arch/x86/include/asm/pgtable-3level-defs.h        |   28 +
 arch/x86/include/asm/pgtable-3level.h             |  175 +++
 arch/x86/include/asm/pgtable.h                    |  561 +++++++
 arch/x86/include/asm/pgtable_32.h                 |  191 +++
 arch/x86/include/asm/pgtable_64.h                 |  285 ++++
 arch/x86/include/asm/poll.h                       |    1 +
 arch/x86/include/asm/posix_types.h                |   13 +
 arch/x86/include/asm/posix_types_32.h             |   85 ++
 arch/x86/include/asm/posix_types_64.h             |  119 ++
 arch/x86/include/asm/prctl.h                      |   10 +
 arch/x86/include/asm/processor-cyrix.h            |   38 +
 arch/x86/include/asm/processor-flags.h            |  100 ++
 arch/x86/include/asm/processor.h                  |  936 ++++++++++++
 arch/x86/include/asm/proto.h                      |   32 +
 arch/x86/include/asm/ptrace-abi.h                 |  145 ++
 arch/x86/include/asm/ptrace.h                     |  280 ++++
 arch/x86/include/asm/pvclock-abi.h                |   42 +
 arch/x86/include/asm/pvclock.h                    |   14 +
 arch/x86/include/asm/reboot.h                     |   21 +
 arch/x86/include/asm/reboot_fixups.h              |    6 +
 arch/x86/include/asm/required-features.h          |   82 +
 arch/x86/include/asm/resource.h                   |    1 +
 arch/x86/include/asm/resume-trace.h               |   21 +
 arch/x86/include/asm/rio.h                        |   63 +
 arch/x86/include/asm/rtc.h                        |    1 +
 arch/x86/include/asm/rwlock.h                     |    8 +
 arch/x86/include/asm/rwsem.h                      |  265 ++++
 arch/x86/include/asm/scatterlist.h                |   33 +
 arch/x86/include/asm/seccomp.h                    |    5 +
 arch/x86/include/asm/seccomp_32.h                 |   17 +
 arch/x86/include/asm/seccomp_64.h                 |   25 +
 arch/x86/include/asm/sections.h                   |    1 +
 arch/x86/include/asm/segment.h                    |  209 +++
 arch/x86/include/asm/sembuf.h                     |   24 +
 arch/x86/include/asm/serial.h                     |   29 +
 arch/x86/include/asm/setup.h                      |  105 ++
 arch/x86/include/asm/shmbuf.h                     |   51 +
 arch/x86/include/asm/shmparam.h                   |    6 +
 arch/x86/include/asm/sigcontext.h                 |  284 ++++
 arch/x86/include/asm/sigcontext32.h               |   75 +
 arch/x86/include/asm/siginfo.h                    |   10 +
 arch/x86/include/asm/signal.h                     |  262 ++++
 arch/x86/include/asm/smp.h                        |  229 +++
 arch/x86/include/asm/socket.h                     |   57 +
 arch/x86/include/asm/sockios.h                    |   13 +
 arch/x86/include/asm/sparsemem.h                  |   34 +
 arch/x86/include/asm/spinlock.h                   |  364 +++++
 arch/x86/include/asm/spinlock_types.h             |   20 +
 arch/x86/include/asm/srat.h                       |   39 +
 arch/x86/include/asm/stacktrace.h                 |   21 +
 arch/x86/include/asm/stat.h                       |  114 ++
 arch/x86/include/asm/statfs.h                     |   12 +
 arch/x86/include/asm/string.h                     |    5 +
 arch/x86/include/asm/string_32.h                  |  326 ++++
 arch/x86/include/asm/string_64.h                  |   60 +
 arch/x86/include/asm/summit/apic.h                |  184 +++
 arch/x86/include/asm/summit/apicdef.h             |   13 +
 arch/x86/include/asm/summit/ipi.h                 |   25 +
 arch/x86/include/asm/summit/mpparse.h             |  109 ++
 arch/x86/include/asm/suspend.h                    |    5 +
 arch/x86/include/asm/suspend_32.h                 |   51 +
 arch/x86/include/asm/suspend_64.h                 |   52 +
 arch/x86/include/asm/swiotlb.h                    |   58 +
 arch/x86/include/asm/sync_bitops.h                |  130 ++
 arch/x86/include/asm/syscall.h                    |  211 +++
 arch/x86/include/asm/syscalls.h                   |   93 ++
 arch/x86/include/asm/system.h                     |  425 ++++++
 arch/x86/include/asm/system_64.h                  |   22 +
 arch/x86/include/asm/tce.h                        |   48 +
 arch/x86/include/asm/termbits.h                   |  198 +++
 arch/x86/include/asm/termios.h                    |  113 ++
 arch/x86/include/asm/therm_throt.h                |    9 +
 arch/x86/include/asm/thread_info.h                |  264 ++++
 arch/x86/include/asm/time.h                       |   63 +
 arch/x86/include/asm/timer.h                      |   66 +
 arch/x86/include/asm/timex.h                      |   19 +
 arch/x86/include/asm/tlb.h                        |   11 +
 arch/x86/include/asm/tlbflush.h                   |  178 +++
 arch/x86/include/asm/topology.h                   |  258 ++++
 arch/x86/include/asm/trampoline.h                 |   21 +
 arch/x86/include/asm/traps.h                      |   81 +
 arch/x86/include/asm/tsc.h                        |   62 +
 arch/x86/include/asm/types.h                      |   36 +
 arch/x86/include/asm/uaccess.h                    |  454 ++++++
 arch/x86/include/asm/uaccess_32.h                 |  218 +++
 arch/x86/include/asm/uaccess_64.h                 |  202 +++
 arch/x86/include/asm/ucontext.h                   |   18 +
 arch/x86/include/asm/unaligned.h                  |   14 +
 arch/x86/include/asm/unistd.h                     |   13 +
 arch/x86/include/asm/unistd_32.h                  |  379 +++++
 arch/x86/include/asm/unistd_64.h                  |  693 +++++++++
 arch/x86/include/asm/unwind.h                     |   13 +
 arch/x86/include/asm/user.h                       |    5 +
 arch/x86/include/asm/user32.h                     |   70 +
 arch/x86/include/asm/user_32.h                    |  131 ++
 arch/x86/include/asm/user_64.h                    |  137 ++
 arch/x86/include/asm/uv/bios.h                    |   94 ++
 arch/x86/include/asm/uv/uv_bau.h                  |  332 +++++
 arch/x86/include/asm/uv/uv_hub.h                  |  354 +++++
 arch/x86/include/asm/uv/uv_irq.h                  |   36 +
 arch/x86/include/asm/uv/uv_mmrs.h                 | 1295 ++++++++++++++++
 arch/x86/include/asm/vdso.h                       |   47 +
 arch/x86/include/asm/vga.h                        |   20 +
 arch/x86/include/asm/vgtod.h                      |   29 +
 arch/x86/include/asm/vic.h                        |   61 +
 arch/x86/include/asm/visws/cobalt.h               |  125 ++
 arch/x86/include/asm/visws/lithium.h              |   53 +
 arch/x86/include/asm/visws/piix4.h                |  107 ++
 arch/x86/include/asm/visws/sgivw.h                |    5 +
 arch/x86/include/asm/vm86.h                       |  208 +++
 arch/x86/include/asm/vmi.h                        |  263 ++++
 arch/x86/include/asm/vmi_time.h                   |   98 ++
 arch/x86/include/asm/voyager.h                    |  528 +++++++
 arch/x86/include/asm/vsyscall.h                   |   44 +
 arch/x86/include/asm/xcr.h                        |   49 +
 arch/x86/include/asm/xen/events.h                 |   24 +
 arch/x86/include/asm/xen/grant_table.h            |    7 +
 arch/x86/include/asm/xen/hypercall.h              |  527 +++++++
 arch/x86/include/asm/xen/hypervisor.h             |   82 +
 arch/x86/include/asm/xen/interface.h              |  175 +++
 arch/x86/include/asm/xen/interface_32.h           |   97 ++
 arch/x86/include/asm/xen/interface_64.h           |  159 ++
 arch/x86/include/asm/xen/page.h                   |  165 +++
 arch/x86/include/asm/xor.h                        |    5 +
 arch/x86/include/asm/xor_32.h                     |  888 +++++++++++
 arch/x86/include/asm/xor_64.h                     |  361 +++++
 arch/x86/include/asm/xsave.h                      |  118 ++
 arch/x86/kernel/cpu/Makefile                      |    2 +-
 drivers/xen/cpu_hotplug.c                         |    2 +-
 include/asm-x86/Kbuild                            |   24 -
 include/asm-x86/a.out-core.h                      |   73 -
 include/asm-x86/a.out.h                           |   20 -
 include/asm-x86/acpi.h                            |  178 ---
 include/asm-x86/agp.h                             |   35 -
 include/asm-x86/alternative-asm.h                 |   22 -
 include/asm-x86/alternative.h                     |  183 ---
 include/asm-x86/amd_iommu.h                       |   35 -
 include/asm-x86/amd_iommu_types.h                 |  404 -----
 include/asm-x86/apic.h                            |  199 ---
 include/asm-x86/apicdef.h                         |  417 ------
 include/asm-x86/arch_hooks.h                      |   26 -
 include/asm-x86/asm.h                             |   47 -
 include/asm-x86/atomic.h                          |    5 -
 include/asm-x86/atomic_32.h                       |  259 ----
 include/asm-x86/atomic_64.h                       |  473 ------
 include/asm-x86/auxvec.h                          |   12 -
 include/asm-x86/bigsmp/apic.h                     |  139 --
 include/asm-x86/bigsmp/apicdef.h                  |   13 -
 include/asm-x86/bigsmp/ipi.h                      |   25 -
 include/asm-x86/bios_ebda.h                       |   36 -
 include/asm-x86/bitops.h                          |  451 ------
 include/asm-x86/boot.h                            |   26 -
 include/asm-x86/bootparam.h                       |  111 --
 include/asm-x86/bug.h                             |   39 -
 include/asm-x86/bugs.h                            |   12 -
 include/asm-x86/byteorder.h                       |   81 -
 include/asm-x86/cache.h                           |   20 -
 include/asm-x86/cacheflush.h                      |  118 --
 include/asm-x86/calgary.h                         |   72 -
 include/asm-x86/calling.h                         |  170 ---
 include/asm-x86/checksum.h                        |    5 -
 include/asm-x86/checksum_32.h                     |  189 ---
 include/asm-x86/checksum_64.h                     |  191 ---
 include/asm-x86/cmpxchg.h                         |    5 -
 include/asm-x86/cmpxchg_32.h                      |  344 -----
 include/asm-x86/cmpxchg_64.h                      |  185 ---
 include/asm-x86/compat.h                          |  218 ---
 include/asm-x86/cpu.h                             |   20 -
 include/asm-x86/cpufeature.h                      |  271 ----
 include/asm-x86/cputime.h                         |    1 -
 include/asm-x86/current.h                         |   39 -
 include/asm-x86/debugreg.h                        |   70 -
 include/asm-x86/delay.h                           |   31 -
 include/asm-x86/desc.h                            |  409 -----
 include/asm-x86/desc_defs.h                       |   95 --
 include/asm-x86/device.h                          |   16 -
 include/asm-x86/div64.h                           |   60 -
 include/asm-x86/dma-mapping.h                     |  308 ----
 include/asm-x86/dma.h                             |  318 ----
 include/asm-x86/dmi.h                             |   26 -
 include/asm-x86/ds.h                              |  238 ---
 include/asm-x86/dwarf2.h                          |   61 -
 include/asm-x86/e820.h                            |  146 --
 include/asm-x86/edac.h                            |   18 -
 include/asm-x86/efi.h                             |  110 --
 include/asm-x86/elf.h                             |  336 -----
 include/asm-x86/emergency-restart.h               |   18 -
 include/asm-x86/errno.h                           |    1 -
 include/asm-x86/es7000/apic.h                     |  193 ---
 include/asm-x86/es7000/apicdef.h                  |   13 -
 include/asm-x86/es7000/ipi.h                      |   24 -
 include/asm-x86/es7000/mpparse.h                  |   30 -
 include/asm-x86/es7000/wakecpu.h                  |   59 -
 include/asm-x86/fb.h                              |   21 -
 include/asm-x86/fcntl.h                           |    1 -
 include/asm-x86/fixmap.h                          |   68 -
 include/asm-x86/fixmap_32.h                       |  123 --
 include/asm-x86/fixmap_64.h                       |   83 --
 include/asm-x86/floppy.h                          |  281 ----
 include/asm-x86/frame.h                           |   27 -
 include/asm-x86/ftrace.h                          |   24 -
 include/asm-x86/futex.h                           |  140 --
 include/asm-x86/gart.h                            |   73 -
 include/asm-x86/genapic.h                         |    5 -
 include/asm-x86/genapic_32.h                      |  126 --
 include/asm-x86/genapic_64.h                      |   58 -
 include/asm-x86/geode.h                           |  253 ----
 include/asm-x86/gpio.h                            |   56 -
 include/asm-x86/hardirq.h                         |   11 -
 include/asm-x86/hardirq_32.h                      |   28 -
 include/asm-x86/hardirq_64.h                      |   23 -
 include/asm-x86/highmem.h                         |   82 -
 include/asm-x86/hpet.h                            |  114 --
 include/asm-x86/hugetlb.h                         |   93 --
 include/asm-x86/hw_irq.h                          |  131 --
 include/asm-x86/hypertransport.h                  |   45 -
 include/asm-x86/i387.h                            |  400 -----
 include/asm-x86/i8253.h                           |   18 -
 include/asm-x86/i8259.h                           |   63 -
 include/asm-x86/ia32.h                            |  170 ---
 include/asm-x86/ia32_unistd.h                     |   18 -
 include/asm-x86/idle.h                            |   15 -
 include/asm-x86/intel_arch_perfmon.h              |   31 -
 include/asm-x86/io.h                              |   91 --
 include/asm-x86/io_32.h                           |  284 ----
 include/asm-x86/io_64.h                           |  244 ---
 include/asm-x86/io_apic.h                         |  204 ---
 include/asm-x86/ioctl.h                           |    1 -
 include/asm-x86/ioctls.h                          |   94 --
 include/asm-x86/iommu.h                           |   46 -
 include/asm-x86/ipcbuf.h                          |   28 -
 include/asm-x86/ipi.h                             |  138 --
 include/asm-x86/irq.h                             |   50 -
 include/asm-x86/irq_regs.h                        |    5 -
 include/asm-x86/irq_regs_32.h                     |   29 -
 include/asm-x86/irq_regs_64.h                     |    1 -
 include/asm-x86/irq_remapping.h                   |    8 -
 include/asm-x86/irq_vectors.h                     |  164 --
 include/asm-x86/irqflags.h                        |  211 ---
 include/asm-x86/ist.h                             |   34 -
 include/asm-x86/k8.h                              |   15 -
 include/asm-x86/kdebug.h                          |   37 -
 include/asm-x86/kexec.h                           |  175 ---
 include/asm-x86/kgdb.h                            |   79 -
 include/asm-x86/kmap_types.h                      |   29 -
 include/asm-x86/kprobes.h                         |   88 --
 include/asm-x86/kvm.h                             |  211 ---
 include/asm-x86/kvm_host.h                        |  752 ----------
 include/asm-x86/kvm_para.h                        |  147 --
 include/asm-x86/kvm_x86_emulate.h                 |  184 ---
 include/asm-x86/ldt.h                             |   40 -
 include/asm-x86/lguest.h                          |   94 --
 include/asm-x86/lguest_hcall.h                    |   71 -
 include/asm-x86/linkage.h                         |   61 -
 include/asm-x86/local.h                           |  235 ---
 include/asm-x86/mach-default/apm.h                |   73 -
 include/asm-x86/mach-default/do_timer.h           |   16 -
 include/asm-x86/mach-default/entry_arch.h         |   36 -
 include/asm-x86/mach-default/mach_apic.h          |  156 --
 include/asm-x86/mach-default/mach_apicdef.h       |   24 -
 include/asm-x86/mach-default/mach_ipi.h           |   64 -
 include/asm-x86/mach-default/mach_mpparse.h       |   17 -
 include/asm-x86/mach-default/mach_mpspec.h        |   12 -
 include/asm-x86/mach-default/mach_timer.h         |   48 -
 include/asm-x86/mach-default/mach_traps.h         |   33 -
 include/asm-x86/mach-default/mach_wakecpu.h       |   42 -
 include/asm-x86/mach-default/pci-functions.h      |   19 -
 include/asm-x86/mach-default/setup_arch.h         |    3 -
 include/asm-x86/mach-default/smpboot_hooks.h      |   59 -
 include/asm-x86/mach-generic/gpio.h               |   15 -
 include/asm-x86/mach-generic/mach_apic.h          |   33 -
 include/asm-x86/mach-generic/mach_apicdef.h       |   11 -
 include/asm-x86/mach-generic/mach_ipi.h           |   10 -
 include/asm-x86/mach-generic/mach_mpparse.h       |   10 -
 include/asm-x86/mach-generic/mach_mpspec.h        |   12 -
 include/asm-x86/mach-rdc321x/gpio.h               |   60 -
 include/asm-x86/mach-rdc321x/rdc321x_defs.h       |   12 -
 include/asm-x86/mach-voyager/do_timer.h           |   17 -
 include/asm-x86/mach-voyager/entry_arch.h         |   26 -
 include/asm-x86/mach-voyager/setup_arch.h         |   12 -
 include/asm-x86/math_emu.h                        |   31 -
 include/asm-x86/mc146818rtc.h                     |  104 --
 include/asm-x86/mca.h                             |   43 -
 include/asm-x86/mca_dma.h                         |  201 ---
 include/asm-x86/mce.h                             |  130 --
 include/asm-x86/microcode.h                       |   47 -
 include/asm-x86/mman.h                            |   20 -
 include/asm-x86/mmconfig.h                        |   12 -
 include/asm-x86/mmu.h                             |   26 -
 include/asm-x86/mmu_context.h                     |   37 -
 include/asm-x86/mmu_context_32.h                  |   56 -
 include/asm-x86/mmu_context_64.h                  |   54 -
 include/asm-x86/mmx.h                             |   14 -
 include/asm-x86/mmzone.h                          |    5 -
 include/asm-x86/mmzone_32.h                       |  134 --
 include/asm-x86/mmzone_64.h                       |   51 -
 include/asm-x86/module.h                          |   80 -
 include/asm-x86/mpspec.h                          |  145 --
 include/asm-x86/mpspec_def.h                      |  180 ---
 include/asm-x86/msgbuf.h                          |   39 -
 include/asm-x86/msidef.h                          |   55 -
 include/asm-x86/msr-index.h                       |  332 -----
 include/asm-x86/msr.h                             |  247 ---
 include/asm-x86/mtrr.h                            |  173 ---
 include/asm-x86/mutex.h                           |    5 -
 include/asm-x86/mutex_32.h                        |  125 --
 include/asm-x86/mutex_64.h                        |  100 --
 include/asm-x86/nmi.h                             |   81 -
 include/asm-x86/nops.h                            |  118 --
 include/asm-x86/numa.h                            |    5 -
 include/asm-x86/numa_32.h                         |   11 -
 include/asm-x86/numa_64.h                         |   43 -
 include/asm-x86/numaq.h                           |  169 ---
 include/asm-x86/numaq/apic.h                      |  136 --
 include/asm-x86/numaq/apicdef.h                   |   14 -
 include/asm-x86/numaq/ipi.h                       |   25 -
 include/asm-x86/numaq/mpparse.h                   |    7 -
 include/asm-x86/numaq/wakecpu.h                   |   43 -
 include/asm-x86/olpc.h                            |  132 --
 include/asm-x86/page.h                            |  209 ---
 include/asm-x86/page_32.h                         |  136 --
 include/asm-x86/page_64.h                         |  105 --
 include/asm-x86/param.h                           |   22 -
 include/asm-x86/paravirt.h                        | 1650 ---------------------
 include/asm-x86/parport.h                         |   10 -
 include/asm-x86/pat.h                             |   22 -
 include/asm-x86/pci-direct.h                      |   21 -
 include/asm-x86/pci.h                             |  114 --
 include/asm-x86/pci_32.h                          |   34 -
 include/asm-x86/pci_64.h                          |   66 -
 include/asm-x86/pda.h                             |  137 --
 include/asm-x86/percpu.h                          |  218 ---
 include/asm-x86/pgalloc.h                         |  114 --
 include/asm-x86/pgtable-2level-defs.h             |   20 -
 include/asm-x86/pgtable-2level.h                  |   79 -
 include/asm-x86/pgtable-3level-defs.h             |   28 -
 include/asm-x86/pgtable-3level.h                  |  175 ---
 include/asm-x86/pgtable.h                         |  561 -------
 include/asm-x86/pgtable_32.h                      |  191 ---
 include/asm-x86/pgtable_64.h                      |  285 ----
 include/asm-x86/poll.h                            |    1 -
 include/asm-x86/posix_types.h                     |   13 -
 include/asm-x86/posix_types_32.h                  |   85 --
 include/asm-x86/posix_types_64.h                  |  119 --
 include/asm-x86/prctl.h                           |   10 -
 include/asm-x86/processor-cyrix.h                 |   38 -
 include/asm-x86/processor-flags.h                 |  100 --
 include/asm-x86/processor.h                       |  936 ------------
 include/asm-x86/proto.h                           |   32 -
 include/asm-x86/ptrace-abi.h                      |  145 --
 include/asm-x86/ptrace.h                          |  280 ----
 include/asm-x86/pvclock-abi.h                     |   42 -
 include/asm-x86/pvclock.h                         |   14 -
 include/asm-x86/reboot.h                          |   21 -
 include/asm-x86/reboot_fixups.h                   |    6 -
 include/asm-x86/required-features.h               |   82 -
 include/asm-x86/resource.h                        |    1 -
 include/asm-x86/resume-trace.h                    |   21 -
 include/asm-x86/rio.h                             |   63 -
 include/asm-x86/rtc.h                             |    1 -
 include/asm-x86/rwlock.h                          |    8 -
 include/asm-x86/rwsem.h                           |  265 ----
 include/asm-x86/scatterlist.h                     |   33 -
 include/asm-x86/seccomp.h                         |    5 -
 include/asm-x86/seccomp_32.h                      |   17 -
 include/asm-x86/seccomp_64.h                      |   25 -
 include/asm-x86/sections.h                        |    1 -
 include/asm-x86/segment.h                         |  209 ---
 include/asm-x86/sembuf.h                          |   24 -
 include/asm-x86/serial.h                          |   29 -
 include/asm-x86/setup.h                           |  105 --
 include/asm-x86/shmbuf.h                          |   51 -
 include/asm-x86/shmparam.h                        |    6 -
 include/asm-x86/sigcontext.h                      |  284 ----
 include/asm-x86/sigcontext32.h                    |   75 -
 include/asm-x86/siginfo.h                         |   10 -
 include/asm-x86/signal.h                          |  262 ----
 include/asm-x86/smp.h                             |  229 ---
 include/asm-x86/socket.h                          |   57 -
 include/asm-x86/sockios.h                         |   13 -
 include/asm-x86/sparsemem.h                       |   34 -
 include/asm-x86/spinlock.h                        |  364 -----
 include/asm-x86/spinlock_types.h                  |   20 -
 include/asm-x86/srat.h                            |   39 -
 include/asm-x86/stacktrace.h                      |   21 -
 include/asm-x86/stat.h                            |  114 --
 include/asm-x86/statfs.h                          |   12 -
 include/asm-x86/string.h                          |    5 -
 include/asm-x86/string_32.h                       |  326 ----
 include/asm-x86/string_64.h                       |   60 -
 include/asm-x86/summit/apic.h                     |  184 ---
 include/asm-x86/summit/apicdef.h                  |   13 -
 include/asm-x86/summit/ipi.h                      |   25 -
 include/asm-x86/summit/mpparse.h                  |  109 --
 include/asm-x86/suspend.h                         |    5 -
 include/asm-x86/suspend_32.h                      |   51 -
 include/asm-x86/suspend_64.h                      |   52 -
 include/asm-x86/swiotlb.h                         |   58 -
 include/asm-x86/sync_bitops.h                     |  130 --
 include/asm-x86/syscall.h                         |  211 ---
 include/asm-x86/syscalls.h                        |   93 --
 include/asm-x86/system.h                          |  425 ------
 include/asm-x86/system_64.h                       |   22 -
 include/asm-x86/tce.h                             |   48 -
 include/asm-x86/termbits.h                        |  198 ---
 include/asm-x86/termios.h                         |  113 --
 include/asm-x86/therm_throt.h                     |    9 -
 include/asm-x86/thread_info.h                     |  264 ----
 include/asm-x86/time.h                            |   63 -
 include/asm-x86/timer.h                           |   66 -
 include/asm-x86/timex.h                           |   19 -
 include/asm-x86/tlb.h                             |   11 -
 include/asm-x86/tlbflush.h                        |  178 ---
 include/asm-x86/topology.h                        |  258 ----
 include/asm-x86/trampoline.h                      |   21 -
 include/asm-x86/traps.h                           |   81 -
 include/asm-x86/tsc.h                             |   62 -
 include/asm-x86/types.h                           |   36 -
 include/asm-x86/uaccess.h                         |  454 ------
 include/asm-x86/uaccess_32.h                      |  218 ---
 include/asm-x86/uaccess_64.h                      |  202 ---
 include/asm-x86/ucontext.h                        |   18 -
 include/asm-x86/unaligned.h                       |   14 -
 include/asm-x86/unistd.h                          |   13 -
 include/asm-x86/unistd_32.h                       |  379 -----
 include/asm-x86/unistd_64.h                       |  693 ---------
 include/asm-x86/unwind.h                          |   13 -
 include/asm-x86/user.h                            |    5 -
 include/asm-x86/user32.h                          |   70 -
 include/asm-x86/user_32.h                         |  131 --
 include/asm-x86/user_64.h                         |  137 --
 include/asm-x86/uv/bios.h                         |   94 --
 include/asm-x86/uv/uv_bau.h                       |  332 -----
 include/asm-x86/uv/uv_hub.h                       |  354 -----
 include/asm-x86/uv/uv_irq.h                       |   36 -
 include/asm-x86/uv/uv_mmrs.h                      | 1295 ----------------
 include/asm-x86/vdso.h                            |   47 -
 include/asm-x86/vga.h                             |   20 -
 include/asm-x86/vgtod.h                           |   29 -
 include/asm-x86/vic.h                             |   61 -
 include/asm-x86/visws/cobalt.h                    |  125 --
 include/asm-x86/visws/lithium.h                   |   53 -
 include/asm-x86/visws/piix4.h                     |  107 --
 include/asm-x86/visws/sgivw.h                     |    5 -
 include/asm-x86/vm86.h                            |  208 ---
 include/asm-x86/vmi.h                             |  263 ----
 include/asm-x86/vmi_time.h                        |   98 --
 include/asm-x86/voyager.h                         |  528 -------
 include/asm-x86/vsyscall.h                        |   44 -
 include/asm-x86/xcr.h                             |   49 -
 include/asm-x86/xen/events.h                      |   24 -
 include/asm-x86/xen/grant_table.h                 |    7 -
 include/asm-x86/xen/hypercall.h                   |  527 -------
 include/asm-x86/xen/hypervisor.h                  |   82 -
 include/asm-x86/xen/interface.h                   |  175 ---
 include/asm-x86/xen/interface_32.h                |   97 --
 include/asm-x86/xen/interface_64.h                |  159 --
 include/asm-x86/xen/page.h                        |  165 ---
 include/asm-x86/xor.h                             |    5 -
 include/asm-x86/xor_32.h                          |  888 -----------
 include/asm-x86/xor_64.h                          |  361 -----
 include/asm-x86/xsave.h                           |  118 --
 scripts/checksyscalls.sh                          |    2 +-
 673 files changed, 38683 insertions(+), 38683 deletions(-)
 create mode 100644 arch/x86/include/asm/Kbuild
 create mode 100644 arch/x86/include/asm/a.out-core.h
 create mode 100644 arch/x86/include/asm/a.out.h
 create mode 100644 arch/x86/include/asm/acpi.h
 create mode 100644 arch/x86/include/asm/agp.h
 create mode 100644 arch/x86/include/asm/alternative-asm.h
 create mode 100644 arch/x86/include/asm/alternative.h
 create mode 100644 arch/x86/include/asm/amd_iommu.h
 create mode 100644 arch/x86/include/asm/amd_iommu_types.h
 create mode 100644 arch/x86/include/asm/apic.h
 create mode 100644 arch/x86/include/asm/apicdef.h
 create mode 100644 arch/x86/include/asm/arch_hooks.h
 create mode 100644 arch/x86/include/asm/asm.h
 create mode 100644 arch/x86/include/asm/atomic.h
 create mode 100644 arch/x86/include/asm/atomic_32.h
 create mode 100644 arch/x86/include/asm/atomic_64.h
 create mode 100644 arch/x86/include/asm/auxvec.h
 create mode 100644 arch/x86/include/asm/bigsmp/apic.h
 create mode 100644 arch/x86/include/asm/bigsmp/apicdef.h
 create mode 100644 arch/x86/include/asm/bigsmp/ipi.h
 create mode 100644 arch/x86/include/asm/bios_ebda.h
 create mode 100644 arch/x86/include/asm/bitops.h
 create mode 100644 arch/x86/include/asm/boot.h
 create mode 100644 arch/x86/include/asm/bootparam.h
 create mode 100644 arch/x86/include/asm/bug.h
 create mode 100644 arch/x86/include/asm/bugs.h
 create mode 100644 arch/x86/include/asm/byteorder.h
 create mode 100644 arch/x86/include/asm/cache.h
 create mode 100644 arch/x86/include/asm/cacheflush.h
 create mode 100644 arch/x86/include/asm/calgary.h
 create mode 100644 arch/x86/include/asm/calling.h
 create mode 100644 arch/x86/include/asm/checksum.h
 create mode 100644 arch/x86/include/asm/checksum_32.h
 create mode 100644 arch/x86/include/asm/checksum_64.h
 create mode 100644 arch/x86/include/asm/cmpxchg.h
 create mode 100644 arch/x86/include/asm/cmpxchg_32.h
 create mode 100644 arch/x86/include/asm/cmpxchg_64.h
 create mode 100644 arch/x86/include/asm/compat.h
 create mode 100644 arch/x86/include/asm/cpu.h
 create mode 100644 arch/x86/include/asm/cpufeature.h
 create mode 100644 arch/x86/include/asm/cputime.h
 create mode 100644 arch/x86/include/asm/current.h
 create mode 100644 arch/x86/include/asm/debugreg.h
 create mode 100644 arch/x86/include/asm/delay.h
 create mode 100644 arch/x86/include/asm/desc.h
 create mode 100644 arch/x86/include/asm/desc_defs.h
 create mode 100644 arch/x86/include/asm/device.h
 create mode 100644 arch/x86/include/asm/div64.h
 create mode 100644 arch/x86/include/asm/dma-mapping.h
 create mode 100644 arch/x86/include/asm/dma.h
 create mode 100644 arch/x86/include/asm/dmi.h
 create mode 100644 arch/x86/include/asm/ds.h
 create mode 100644 arch/x86/include/asm/dwarf2.h
 create mode 100644 arch/x86/include/asm/e820.h
 create mode 100644 arch/x86/include/asm/edac.h
 create mode 100644 arch/x86/include/asm/efi.h
 create mode 100644 arch/x86/include/asm/elf.h
 create mode 100644 arch/x86/include/asm/emergency-restart.h
 create mode 100644 arch/x86/include/asm/errno.h
 create mode 100644 arch/x86/include/asm/es7000/apic.h
 create mode 100644 arch/x86/include/asm/es7000/apicdef.h
 create mode 100644 arch/x86/include/asm/es7000/ipi.h
 create mode 100644 arch/x86/include/asm/es7000/mpparse.h
 create mode 100644 arch/x86/include/asm/es7000/wakecpu.h
 create mode 100644 arch/x86/include/asm/fb.h
 create mode 100644 arch/x86/include/asm/fcntl.h
 create mode 100644 arch/x86/include/asm/fixmap.h
 create mode 100644 arch/x86/include/asm/fixmap_32.h
 create mode 100644 arch/x86/include/asm/fixmap_64.h
 create mode 100644 arch/x86/include/asm/floppy.h
 create mode 100644 arch/x86/include/asm/frame.h
 create mode 100644 arch/x86/include/asm/ftrace.h
 create mode 100644 arch/x86/include/asm/futex.h
 create mode 100644 arch/x86/include/asm/gart.h
 create mode 100644 arch/x86/include/asm/genapic.h
 create mode 100644 arch/x86/include/asm/genapic_32.h
 create mode 100644 arch/x86/include/asm/genapic_64.h
 create mode 100644 arch/x86/include/asm/geode.h
 create mode 100644 arch/x86/include/asm/gpio.h
 create mode 100644 arch/x86/include/asm/hardirq.h
 create mode 100644 arch/x86/include/asm/hardirq_32.h
 create mode 100644 arch/x86/include/asm/hardirq_64.h
 create mode 100644 arch/x86/include/asm/highmem.h
 create mode 100644 arch/x86/include/asm/hpet.h
 create mode 100644 arch/x86/include/asm/hugetlb.h
 create mode 100644 arch/x86/include/asm/hw_irq.h
 create mode 100644 arch/x86/include/asm/hypertransport.h
 create mode 100644 arch/x86/include/asm/i387.h
 create mode 100644 arch/x86/include/asm/i8253.h
 create mode 100644 arch/x86/include/asm/i8259.h
 create mode 100644 arch/x86/include/asm/ia32.h
 create mode 100644 arch/x86/include/asm/ia32_unistd.h
 create mode 100644 arch/x86/include/asm/idle.h
 create mode 100644 arch/x86/include/asm/intel_arch_perfmon.h
 create mode 100644 arch/x86/include/asm/io.h
 create mode 100644 arch/x86/include/asm/io_32.h
 create mode 100644 arch/x86/include/asm/io_64.h
 create mode 100644 arch/x86/include/asm/io_apic.h
 create mode 100644 arch/x86/include/asm/ioctl.h
 create mode 100644 arch/x86/include/asm/ioctls.h
 create mode 100644 arch/x86/include/asm/iommu.h
 create mode 100644 arch/x86/include/asm/ipcbuf.h
 create mode 100644 arch/x86/include/asm/ipi.h
 create mode 100644 arch/x86/include/asm/irq.h
 create mode 100644 arch/x86/include/asm/irq_regs.h
 create mode 100644 arch/x86/include/asm/irq_regs_32.h
 create mode 100644 arch/x86/include/asm/irq_regs_64.h
 create mode 100644 arch/x86/include/asm/irq_remapping.h
 create mode 100644 arch/x86/include/asm/irq_vectors.h
 create mode 100644 arch/x86/include/asm/irqflags.h
 create mode 100644 arch/x86/include/asm/ist.h
 create mode 100644 arch/x86/include/asm/k8.h
 create mode 100644 arch/x86/include/asm/kdebug.h
 create mode 100644 arch/x86/include/asm/kexec.h
 create mode 100644 arch/x86/include/asm/kgdb.h
 create mode 100644 arch/x86/include/asm/kmap_types.h
 create mode 100644 arch/x86/include/asm/kprobes.h
 create mode 100644 arch/x86/include/asm/kvm.h
 create mode 100644 arch/x86/include/asm/kvm_host.h
 create mode 100644 arch/x86/include/asm/kvm_para.h
 create mode 100644 arch/x86/include/asm/kvm_x86_emulate.h
 create mode 100644 arch/x86/include/asm/ldt.h
 create mode 100644 arch/x86/include/asm/lguest.h
 create mode 100644 arch/x86/include/asm/lguest_hcall.h
 create mode 100644 arch/x86/include/asm/linkage.h
 create mode 100644 arch/x86/include/asm/local.h
 create mode 100644 arch/x86/include/asm/mach-default/apm.h
 create mode 100644 arch/x86/include/asm/mach-default/do_timer.h
 create mode 100644 arch/x86/include/asm/mach-default/entry_arch.h
 create mode 100644 arch/x86/include/asm/mach-default/mach_apic.h
 create mode 100644 arch/x86/include/asm/mach-default/mach_apicdef.h
 create mode 100644 arch/x86/include/asm/mach-default/mach_ipi.h
 create mode 100644 arch/x86/include/asm/mach-default/mach_mpparse.h
 create mode 100644 arch/x86/include/asm/mach-default/mach_mpspec.h
 create mode 100644 arch/x86/include/asm/mach-default/mach_timer.h
 create mode 100644 arch/x86/include/asm/mach-default/mach_traps.h
 create mode 100644 arch/x86/include/asm/mach-default/mach_wakecpu.h
 create mode 100644 arch/x86/include/asm/mach-default/pci-functions.h
 create mode 100644 arch/x86/include/asm/mach-default/setup_arch.h
 create mode 100644 arch/x86/include/asm/mach-default/smpboot_hooks.h
 create mode 100644 arch/x86/include/asm/mach-generic/gpio.h
 create mode 100644 arch/x86/include/asm/mach-generic/mach_apic.h
 create mode 100644 arch/x86/include/asm/mach-generic/mach_apicdef.h
 create mode 100644 arch/x86/include/asm/mach-generic/mach_ipi.h
 create mode 100644 arch/x86/include/asm/mach-generic/mach_mpparse.h
 create mode 100644 arch/x86/include/asm/mach-generic/mach_mpspec.h
 create mode 100644 arch/x86/include/asm/mach-rdc321x/gpio.h
 create mode 100644 arch/x86/include/asm/mach-rdc321x/rdc321x_defs.h
 create mode 100644 arch/x86/include/asm/mach-voyager/do_timer.h
 create mode 100644 arch/x86/include/asm/mach-voyager/entry_arch.h
 create mode 100644 arch/x86/include/asm/mach-voyager/setup_arch.h
 create mode 100644 arch/x86/include/asm/math_emu.h
 create mode 100644 arch/x86/include/asm/mc146818rtc.h
 create mode 100644 arch/x86/include/asm/mca.h
 create mode 100644 arch/x86/include/asm/mca_dma.h
 create mode 100644 arch/x86/include/asm/mce.h
 create mode 100644 arch/x86/include/asm/microcode.h
 create mode 100644 arch/x86/include/asm/mman.h
 create mode 100644 arch/x86/include/asm/mmconfig.h
 create mode 100644 arch/x86/include/asm/mmu.h
 create mode 100644 arch/x86/include/asm/mmu_context.h
 create mode 100644 arch/x86/include/asm/mmu_context_32.h
 create mode 100644 arch/x86/include/asm/mmu_context_64.h
 create mode 100644 arch/x86/include/asm/mmx.h
 create mode 100644 arch/x86/include/asm/mmzone.h
 create mode 100644 arch/x86/include/asm/mmzone_32.h
 create mode 100644 arch/x86/include/asm/mmzone_64.h
 create mode 100644 arch/x86/include/asm/module.h
 create mode 100644 arch/x86/include/asm/mpspec.h
 create mode 100644 arch/x86/include/asm/mpspec_def.h
 create mode 100644 arch/x86/include/asm/msgbuf.h
 create mode 100644 arch/x86/include/asm/msidef.h
 create mode 100644 arch/x86/include/asm/msr-index.h
 create mode 100644 arch/x86/include/asm/msr.h
 create mode 100644 arch/x86/include/asm/mtrr.h
 create mode 100644 arch/x86/include/asm/mutex.h
 create mode 100644 arch/x86/include/asm/mutex_32.h
 create mode 100644 arch/x86/include/asm/mutex_64.h
 create mode 100644 arch/x86/include/asm/nmi.h
 create mode 100644 arch/x86/include/asm/nops.h
 create mode 100644 arch/x86/include/asm/numa.h
 create mode 100644 arch/x86/include/asm/numa_32.h
 create mode 100644 arch/x86/include/asm/numa_64.h
 create mode 100644 arch/x86/include/asm/numaq.h
 create mode 100644 arch/x86/include/asm/numaq/apic.h
 create mode 100644 arch/x86/include/asm/numaq/apicdef.h
 create mode 100644 arch/x86/include/asm/numaq/ipi.h
 create mode 100644 arch/x86/include/asm/numaq/mpparse.h
 create mode 100644 arch/x86/include/asm/numaq/wakecpu.h
 create mode 100644 arch/x86/include/asm/olpc.h
 create mode 100644 arch/x86/include/asm/page.h
 create mode 100644 arch/x86/include/asm/page_32.h
 create mode 100644 arch/x86/include/asm/page_64.h
 create mode 100644 arch/x86/include/asm/param.h
 create mode 100644 arch/x86/include/asm/paravirt.h
 create mode 100644 arch/x86/include/asm/parport.h
 create mode 100644 arch/x86/include/asm/pat.h
 create mode 100644 arch/x86/include/asm/pci-direct.h
 create mode 100644 arch/x86/include/asm/pci.h
 create mode 100644 arch/x86/include/asm/pci_32.h
 create mode 100644 arch/x86/include/asm/pci_64.h
 create mode 100644 arch/x86/include/asm/pda.h
 create mode 100644 arch/x86/include/asm/percpu.h
 create mode 100644 arch/x86/include/asm/pgalloc.h
 create mode 100644 arch/x86/include/asm/pgtable-2level-defs.h
 create mode 100644 arch/x86/include/asm/pgtable-2level.h
 create mode 100644 arch/x86/include/asm/pgtable-3level-defs.h
 create mode 100644 arch/x86/include/asm/pgtable-3level.h
 create mode 100644 arch/x86/include/asm/pgtable.h
 create mode 100644 arch/x86/include/asm/pgtable_32.h
 create mode 100644 arch/x86/include/asm/pgtable_64.h
 create mode 100644 arch/x86/include/asm/poll.h
 create mode 100644 arch/x86/include/asm/posix_types.h
 create mode 100644 arch/x86/include/asm/posix_types_32.h
 create mode 100644 arch/x86/include/asm/posix_types_64.h
 create mode 100644 arch/x86/include/asm/prctl.h
 create mode 100644 arch/x86/include/asm/processor-cyrix.h
 create mode 100644 arch/x86/include/asm/processor-flags.h
 create mode 100644 arch/x86/include/asm/processor.h
 create mode 100644 arch/x86/include/asm/proto.h
 create mode 100644 arch/x86/include/asm/ptrace-abi.h
 create mode 100644 arch/x86/include/asm/ptrace.h
 create mode 100644 arch/x86/include/asm/pvclock-abi.h
 create mode 100644 arch/x86/include/asm/pvclock.h
 create mode 100644 arch/x86/include/asm/reboot.h
 create mode 100644 arch/x86/include/asm/reboot_fixups.h
 create mode 100644 arch/x86/include/asm/required-features.h
 create mode 100644 arch/x86/include/asm/resource.h
 create mode 100644 arch/x86/include/asm/resume-trace.h
 create mode 100644 arch/x86/include/asm/rio.h
 create mode 100644 arch/x86/include/asm/rtc.h
 create mode 100644 arch/x86/include/asm/rwlock.h
 create mode 100644 arch/x86/include/asm/rwsem.h
 create mode 100644 arch/x86/include/asm/scatterlist.h
 create mode 100644 arch/x86/include/asm/seccomp.h
 create mode 100644 arch/x86/include/asm/seccomp_32.h
 create mode 100644 arch/x86/include/asm/seccomp_64.h
 create mode 100644 arch/x86/include/asm/sections.h
 create mode 100644 arch/x86/include/asm/segment.h
 create mode 100644 arch/x86/include/asm/sembuf.h
 create mode 100644 arch/x86/include/asm/serial.h
 create mode 100644 arch/x86/include/asm/setup.h
 create mode 100644 arch/x86/include/asm/shmbuf.h
 create mode 100644 arch/x86/include/asm/shmparam.h
 create mode 100644 arch/x86/include/asm/sigcontext.h
 create mode 100644 arch/x86/include/asm/sigcontext32.h
 create mode 100644 arch/x86/include/asm/siginfo.h
 create mode 100644 arch/x86/include/asm/signal.h
 create mode 100644 arch/x86/include/asm/smp.h
 create mode 100644 arch/x86/include/asm/socket.h
 create mode 100644 arch/x86/include/asm/sockios.h
 create mode 100644 arch/x86/include/asm/sparsemem.h
 create mode 100644 arch/x86/include/asm/spinlock.h
 create mode 100644 arch/x86/include/asm/spinlock_types.h
 create mode 100644 arch/x86/include/asm/srat.h
 create mode 100644 arch/x86/include/asm/stacktrace.h
 create mode 100644 arch/x86/include/asm/stat.h
 create mode 100644 arch/x86/include/asm/statfs.h
 create mode 100644 arch/x86/include/asm/string.h
 create mode 100644 arch/x86/include/asm/string_32.h
 create mode 100644 arch/x86/include/asm/string_64.h
 create mode 100644 arch/x86/include/asm/summit/apic.h
 create mode 100644 arch/x86/include/asm/summit/apicdef.h
 create mode 100644 arch/x86/include/asm/summit/ipi.h
 create mode 100644 arch/x86/include/asm/summit/mpparse.h
 create mode 100644 arch/x86/include/asm/suspend.h
 create mode 100644 arch/x86/include/asm/suspend_32.h
 create mode 100644 arch/x86/include/asm/suspend_64.h
 create mode 100644 arch/x86/include/asm/swiotlb.h
 create mode 100644 arch/x86/include/asm/sync_bitops.h
 create mode 100644 arch/x86/include/asm/syscall.h
 create mode 100644 arch/x86/include/asm/syscalls.h
 create mode 100644 arch/x86/include/asm/system.h
 create mode 100644 arch/x86/include/asm/system_64.h
 create mode 100644 arch/x86/include/asm/tce.h
 create mode 100644 arch/x86/include/asm/termbits.h
 create mode 100644 arch/x86/include/asm/termios.h
 create mode 100644 arch/x86/include/asm/therm_throt.h
 create mode 100644 arch/x86/include/asm/thread_info.h
 create mode 100644 arch/x86/include/asm/time.h
 create mode 100644 arch/x86/include/asm/timer.h
 create mode 100644 arch/x86/include/asm/timex.h
 create mode 100644 arch/x86/include/asm/tlb.h
 create mode 100644 arch/x86/include/asm/tlbflush.h
 create mode 100644 arch/x86/include/asm/topology.h
 create mode 100644 arch/x86/include/asm/trampoline.h
 create mode 100644 arch/x86/include/asm/traps.h
 create mode 100644 arch/x86/include/asm/tsc.h
 create mode 100644 arch/x86/include/asm/types.h
 create mode 100644 arch/x86/include/asm/uaccess.h
 create mode 100644 arch/x86/include/asm/uaccess_32.h
 create mode 100644 arch/x86/include/asm/uaccess_64.h
 create mode 100644 arch/x86/include/asm/ucontext.h
 create mode 100644 arch/x86/include/asm/unaligned.h
 create mode 100644 arch/x86/include/asm/unistd.h
 create mode 100644 arch/x86/include/asm/unistd_32.h
 create mode 100644 arch/x86/include/asm/unistd_64.h
 create mode 100644 arch/x86/include/asm/unwind.h
 create mode 100644 arch/x86/include/asm/user.h
 create mode 100644 arch/x86/include/asm/user32.h
 create mode 100644 arch/x86/include/asm/user_32.h
 create mode 100644 arch/x86/include/asm/user_64.h
 create mode 100644 arch/x86/include/asm/uv/bios.h
 create mode 100644 arch/x86/include/asm/uv/uv_bau.h
 create mode 100644 arch/x86/include/asm/uv/uv_hub.h
 create mode 100644 arch/x86/include/asm/uv/uv_irq.h
 create mode 100644 arch/x86/include/asm/uv/uv_mmrs.h
 create mode 100644 arch/x86/include/asm/vdso.h
 create mode 100644 arch/x86/include/asm/vga.h
 create mode 100644 arch/x86/include/asm/vgtod.h
 create mode 100644 arch/x86/include/asm/vic.h
 create mode 100644 arch/x86/include/asm/visws/cobalt.h
 create mode 100644 arch/x86/include/asm/visws/lithium.h
 create mode 100644 arch/x86/include/asm/visws/piix4.h
 create mode 100644 arch/x86/include/asm/visws/sgivw.h
 create mode 100644 arch/x86/include/asm/vm86.h
 create mode 100644 arch/x86/include/asm/vmi.h
 create mode 100644 arch/x86/include/asm/vmi_time.h
 create mode 100644 arch/x86/include/asm/voyager.h
 create mode 100644 arch/x86/include/asm/vsyscall.h
 create mode 100644 arch/x86/include/asm/xcr.h
 create mode 100644 arch/x86/include/asm/xen/events.h
 create mode 100644 arch/x86/include/asm/xen/grant_table.h
 create mode 100644 arch/x86/include/asm/xen/hypercall.h
 create mode 100644 arch/x86/include/asm/xen/hypervisor.h
 create mode 100644 arch/x86/include/asm/xen/interface.h
 create mode 100644 arch/x86/include/asm/xen/interface_32.h
 create mode 100644 arch/x86/include/asm/xen/interface_64.h
 create mode 100644 arch/x86/include/asm/xen/page.h
 create mode 100644 arch/x86/include/asm/xor.h
 create mode 100644 arch/x86/include/asm/xor_32.h
 create mode 100644 arch/x86/include/asm/xor_64.h
 create mode 100644 arch/x86/include/asm/xsave.h
 delete mode 100644 include/asm-x86/Kbuild
 delete mode 100644 include/asm-x86/a.out-core.h
 delete mode 100644 include/asm-x86/a.out.h
 delete mode 100644 include/asm-x86/acpi.h
 delete mode 100644 include/asm-x86/agp.h
 delete mode 100644 include/asm-x86/alternative-asm.h
 delete mode 100644 include/asm-x86/alternative.h
 delete mode 100644 include/asm-x86/amd_iommu.h
 delete mode 100644 include/asm-x86/amd_iommu_types.h
 delete mode 100644 include/asm-x86/apic.h
 delete mode 100644 include/asm-x86/apicdef.h
 delete mode 100644 include/asm-x86/arch_hooks.h
 delete mode 100644 include/asm-x86/asm.h
 delete mode 100644 include/asm-x86/atomic.h
 delete mode 100644 include/asm-x86/atomic_32.h
 delete mode 100644 include/asm-x86/atomic_64.h
 delete mode 100644 include/asm-x86/auxvec.h
 delete mode 100644 include/asm-x86/bigsmp/apic.h
 delete mode 100644 include/asm-x86/bigsmp/apicdef.h
 delete mode 100644 include/asm-x86/bigsmp/ipi.h
 delete mode 100644 include/asm-x86/bios_ebda.h
 delete mode 100644 include/asm-x86/bitops.h
 delete mode 100644 include/asm-x86/boot.h
 delete mode 100644 include/asm-x86/bootparam.h
 delete mode 100644 include/asm-x86/bug.h
 delete mode 100644 include/asm-x86/bugs.h
 delete mode 100644 include/asm-x86/byteorder.h
 delete mode 100644 include/asm-x86/cache.h
 delete mode 100644 include/asm-x86/cacheflush.h
 delete mode 100644 include/asm-x86/calgary.h
 delete mode 100644 include/asm-x86/calling.h
 delete mode 100644 include/asm-x86/checksum.h
 delete mode 100644 include/asm-x86/checksum_32.h
 delete mode 100644 include/asm-x86/checksum_64.h
 delete mode 100644 include/asm-x86/cmpxchg.h
 delete mode 100644 include/asm-x86/cmpxchg_32.h
 delete mode 100644 include/asm-x86/cmpxchg_64.h
 delete mode 100644 include/asm-x86/compat.h
 delete mode 100644 include/asm-x86/cpu.h
 delete mode 100644 include/asm-x86/cpufeature.h
 delete mode 100644 include/asm-x86/cputime.h
 delete mode 100644 include/asm-x86/current.h
 delete mode 100644 include/asm-x86/debugreg.h
 delete mode 100644 include/asm-x86/delay.h
 delete mode 100644 include/asm-x86/desc.h
 delete mode 100644 include/asm-x86/desc_defs.h
 delete mode 100644 include/asm-x86/device.h
 delete mode 100644 include/asm-x86/div64.h
 delete mode 100644 include/asm-x86/dma-mapping.h
 delete mode 100644 include/asm-x86/dma.h
 delete mode 100644 include/asm-x86/dmi.h
 delete mode 100644 include/asm-x86/ds.h
 delete mode 100644 include/asm-x86/dwarf2.h
 delete mode 100644 include/asm-x86/e820.h
 delete mode 100644 include/asm-x86/edac.h
 delete mode 100644 include/asm-x86/efi.h
 delete mode 100644 include/asm-x86/elf.h
 delete mode 100644 include/asm-x86/emergency-restart.h
 delete mode 100644 include/asm-x86/errno.h
 delete mode 100644 include/asm-x86/es7000/apic.h
 delete mode 100644 include/asm-x86/es7000/apicdef.h
 delete mode 100644 include/asm-x86/es7000/ipi.h
 delete mode 100644 include/asm-x86/es7000/mpparse.h
 delete mode 100644 include/asm-x86/es7000/wakecpu.h
 delete mode 100644 include/asm-x86/fb.h
 delete mode 100644 include/asm-x86/fcntl.h
 delete mode 100644 include/asm-x86/fixmap.h
 delete mode 100644 include/asm-x86/fixmap_32.h
 delete mode 100644 include/asm-x86/fixmap_64.h
 delete mode 100644 include/asm-x86/floppy.h
 delete mode 100644 include/asm-x86/frame.h
 delete mode 100644 include/asm-x86/ftrace.h
 delete mode 100644 include/asm-x86/futex.h
 delete mode 100644 include/asm-x86/gart.h
 delete mode 100644 include/asm-x86/genapic.h
 delete mode 100644 include/asm-x86/genapic_32.h
 delete mode 100644 include/asm-x86/genapic_64.h
 delete mode 100644 include/asm-x86/geode.h
 delete mode 100644 include/asm-x86/gpio.h
 delete mode 100644 include/asm-x86/hardirq.h
 delete mode 100644 include/asm-x86/hardirq_32.h
 delete mode 100644 include/asm-x86/hardirq_64.h
 delete mode 100644 include/asm-x86/highmem.h
 delete mode 100644 include/asm-x86/hpet.h
 delete mode 100644 include/asm-x86/hugetlb.h
 delete mode 100644 include/asm-x86/hw_irq.h
 delete mode 100644 include/asm-x86/hypertransport.h
 delete mode 100644 include/asm-x86/i387.h
 delete mode 100644 include/asm-x86/i8253.h
 delete mode 100644 include/asm-x86/i8259.h
 delete mode 100644 include/asm-x86/ia32.h
 delete mode 100644 include/asm-x86/ia32_unistd.h
 delete mode 100644 include/asm-x86/idle.h
 delete mode 100644 include/asm-x86/intel_arch_perfmon.h
 delete mode 100644 include/asm-x86/io.h
 delete mode 100644 include/asm-x86/io_32.h
 delete mode 100644 include/asm-x86/io_64.h
 delete mode 100644 include/asm-x86/io_apic.h
 delete mode 100644 include/asm-x86/ioctl.h
 delete mode 100644 include/asm-x86/ioctls.h
 delete mode 100644 include/asm-x86/iommu.h
 delete mode 100644 include/asm-x86/ipcbuf.h
 delete mode 100644 include/asm-x86/ipi.h
 delete mode 100644 include/asm-x86/irq.h
 delete mode 100644 include/asm-x86/irq_regs.h
 delete mode 100644 include/asm-x86/irq_regs_32.h
 delete mode 100644 include/asm-x86/irq_regs_64.h
 delete mode 100644 include/asm-x86/irq_remapping.h
 delete mode 100644 include/asm-x86/irq_vectors.h
 delete mode 100644 include/asm-x86/irqflags.h
 delete mode 100644 include/asm-x86/ist.h
 delete mode 100644 include/asm-x86/k8.h
 delete mode 100644 include/asm-x86/kdebug.h
 delete mode 100644 include/asm-x86/kexec.h
 delete mode 100644 include/asm-x86/kgdb.h
 delete mode 100644 include/asm-x86/kmap_types.h
 delete mode 100644 include/asm-x86/kprobes.h
 delete mode 100644 include/asm-x86/kvm.h
 delete mode 100644 include/asm-x86/kvm_host.h
 delete mode 100644 include/asm-x86/kvm_para.h
 delete mode 100644 include/asm-x86/kvm_x86_emulate.h
 delete mode 100644 include/asm-x86/ldt.h
 delete mode 100644 include/asm-x86/lguest.h
 delete mode 100644 include/asm-x86/lguest_hcall.h
 delete mode 100644 include/asm-x86/linkage.h
 delete mode 100644 include/asm-x86/local.h
 delete mode 100644 include/asm-x86/mach-default/apm.h
 delete mode 100644 include/asm-x86/mach-default/do_timer.h
 delete mode 100644 include/asm-x86/mach-default/entry_arch.h
 delete mode 100644 include/asm-x86/mach-default/mach_apic.h
 delete mode 100644 include/asm-x86/mach-default/mach_apicdef.h
 delete mode 100644 include/asm-x86/mach-default/mach_ipi.h
 delete mode 100644 include/asm-x86/mach-default/mach_mpparse.h
 delete mode 100644 include/asm-x86/mach-default/mach_mpspec.h
 delete mode 100644 include/asm-x86/mach-default/mach_timer.h
 delete mode 100644 include/asm-x86/mach-default/mach_traps.h
 delete mode 100644 include/asm-x86/mach-default/mach_wakecpu.h
 delete mode 100644 include/asm-x86/mach-default/pci-functions.h
 delete mode 100644 include/asm-x86/mach-default/setup_arch.h
 delete mode 100644 include/asm-x86/mach-default/smpboot_hooks.h
 delete mode 100644 include/asm-x86/mach-generic/gpio.h
 delete mode 100644 include/asm-x86/mach-generic/mach_apic.h
 delete mode 100644 include/asm-x86/mach-generic/mach_apicdef.h
 delete mode 100644 include/asm-x86/mach-generic/mach_ipi.h
 delete mode 100644 include/asm-x86/mach-generic/mach_mpparse.h
 delete mode 100644 include/asm-x86/mach-generic/mach_mpspec.h
 delete mode 100644 include/asm-x86/mach-rdc321x/gpio.h
 delete mode 100644 include/asm-x86/mach-rdc321x/rdc321x_defs.h
 delete mode 100644 include/asm-x86/mach-voyager/do_timer.h
 delete mode 100644 include/asm-x86/mach-voyager/entry_arch.h
 delete mode 100644 include/asm-x86/mach-voyager/setup_arch.h
 delete mode 100644 include/asm-x86/math_emu.h
 delete mode 100644 include/asm-x86/mc146818rtc.h
 delete mode 100644 include/asm-x86/mca.h
 delete mode 100644 include/asm-x86/mca_dma.h
 delete mode 100644 include/asm-x86/mce.h
 delete mode 100644 include/asm-x86/microcode.h
 delete mode 100644 include/asm-x86/mman.h
 delete mode 100644 include/asm-x86/mmconfig.h
 delete mode 100644 include/asm-x86/mmu.h
 delete mode 100644 include/asm-x86/mmu_context.h
 delete mode 100644 include/asm-x86/mmu_context_32.h
 delete mode 100644 include/asm-x86/mmu_context_64.h
 delete mode 100644 include/asm-x86/mmx.h
 delete mode 100644 include/asm-x86/mmzone.h
 delete mode 100644 include/asm-x86/mmzone_32.h
 delete mode 100644 include/asm-x86/mmzone_64.h
 delete mode 100644 include/asm-x86/module.h
 delete mode 100644 include/asm-x86/mpspec.h
 delete mode 100644 include/asm-x86/mpspec_def.h
 delete mode 100644 include/asm-x86/msgbuf.h
 delete mode 100644 include/asm-x86/msidef.h
 delete mode 100644 include/asm-x86/msr-index.h
 delete mode 100644 include/asm-x86/msr.h
 delete mode 100644 include/asm-x86/mtrr.h
 delete mode 100644 include/asm-x86/mutex.h
 delete mode 100644 include/asm-x86/mutex_32.h
 delete mode 100644 include/asm-x86/mutex_64.h
 delete mode 100644 include/asm-x86/nmi.h
 delete mode 100644 include/asm-x86/nops.h
 delete mode 100644 include/asm-x86/numa.h
 delete mode 100644 include/asm-x86/numa_32.h
 delete mode 100644 include/asm-x86/numa_64.h
 delete mode 100644 include/asm-x86/numaq.h
 delete mode 100644 include/asm-x86/numaq/apic.h
 delete mode 100644 include/asm-x86/numaq/apicdef.h
 delete mode 100644 include/asm-x86/numaq/ipi.h
 delete mode 100644 include/asm-x86/numaq/mpparse.h
 delete mode 100644 include/asm-x86/numaq/wakecpu.h
 delete mode 100644 include/asm-x86/olpc.h
 delete mode 100644 include/asm-x86/page.h
 delete mode 100644 include/asm-x86/page_32.h
 delete mode 100644 include/asm-x86/page_64.h
 delete mode 100644 include/asm-x86/param.h
 delete mode 100644 include/asm-x86/paravirt.h
 delete mode 100644 include/asm-x86/parport.h
 delete mode 100644 include/asm-x86/pat.h
 delete mode 100644 include/asm-x86/pci-direct.h
 delete mode 100644 include/asm-x86/pci.h
 delete mode 100644 include/asm-x86/pci_32.h
 delete mode 100644 include/asm-x86/pci_64.h
 delete mode 100644 include/asm-x86/pda.h
 delete mode 100644 include/asm-x86/percpu.h
 delete mode 100644 include/asm-x86/pgalloc.h
 delete mode 100644 include/asm-x86/pgtable-2level-defs.h
 delete mode 100644 include/asm-x86/pgtable-2level.h
 delete mode 100644 include/asm-x86/pgtable-3level-defs.h
 delete mode 100644 include/asm-x86/pgtable-3level.h
 delete mode 100644 include/asm-x86/pgtable.h
 delete mode 100644 include/asm-x86/pgtable_32.h
 delete mode 100644 include/asm-x86/pgtable_64.h
 delete mode 100644 include/asm-x86/poll.h
 delete mode 100644 include/asm-x86/posix_types.h
 delete mode 100644 include/asm-x86/posix_types_32.h
 delete mode 100644 include/asm-x86/posix_types_64.h
 delete mode 100644 include/asm-x86/prctl.h
 delete mode 100644 include/asm-x86/processor-cyrix.h
 delete mode 100644 include/asm-x86/processor-flags.h
 delete mode 100644 include/asm-x86/processor.h
 delete mode 100644 include/asm-x86/proto.h
 delete mode 100644 include/asm-x86/ptrace-abi.h
 delete mode 100644 include/asm-x86/ptrace.h
 delete mode 100644 include/asm-x86/pvclock-abi.h
 delete mode 100644 include/asm-x86/pvclock.h
 delete mode 100644 include/asm-x86/reboot.h
 delete mode 100644 include/asm-x86/reboot_fixups.h
 delete mode 100644 include/asm-x86/required-features.h
 delete mode 100644 include/asm-x86/resource.h
 delete mode 100644 include/asm-x86/resume-trace.h
 delete mode 100644 include/asm-x86/rio.h
 delete mode 100644 include/asm-x86/rtc.h
 delete mode 100644 include/asm-x86/rwlock.h
 delete mode 100644 include/asm-x86/rwsem.h
 delete mode 100644 include/asm-x86/scatterlist.h
 delete mode 100644 include/asm-x86/seccomp.h
 delete mode 100644 include/asm-x86/seccomp_32.h
 delete mode 100644 include/asm-x86/seccomp_64.h
 delete mode 100644 include/asm-x86/sections.h
 delete mode 100644 include/asm-x86/segment.h
 delete mode 100644 include/asm-x86/sembuf.h
 delete mode 100644 include/asm-x86/serial.h
 delete mode 100644 include/asm-x86/setup.h
 delete mode 100644 include/asm-x86/shmbuf.h
 delete mode 100644 include/asm-x86/shmparam.h
 delete mode 100644 include/asm-x86/sigcontext.h
 delete mode 100644 include/asm-x86/sigcontext32.h
 delete mode 100644 include/asm-x86/siginfo.h
 delete mode 100644 include/asm-x86/signal.h
 delete mode 100644 include/asm-x86/smp.h
 delete mode 100644 include/asm-x86/socket.h
 delete mode 100644 include/asm-x86/sockios.h
 delete mode 100644 include/asm-x86/sparsemem.h
 delete mode 100644 include/asm-x86/spinlock.h
 delete mode 100644 include/asm-x86/spinlock_types.h
 delete mode 100644 include/asm-x86/srat.h
 delete mode 100644 include/asm-x86/stacktrace.h
 delete mode 100644 include/asm-x86/stat.h
 delete mode 100644 include/asm-x86/statfs.h
 delete mode 100644 include/asm-x86/string.h
 delete mode 100644 include/asm-x86/string_32.h
 delete mode 100644 include/asm-x86/string_64.h
 delete mode 100644 include/asm-x86/summit/apic.h
 delete mode 100644 include/asm-x86/summit/apicdef.h
 delete mode 100644 include/asm-x86/summit/ipi.h
 delete mode 100644 include/asm-x86/summit/mpparse.h
 delete mode 100644 include/asm-x86/suspend.h
 delete mode 100644 include/asm-x86/suspend_32.h
 delete mode 100644 include/asm-x86/suspend_64.h
 delete mode 100644 include/asm-x86/swiotlb.h
 delete mode 100644 include/asm-x86/sync_bitops.h
 delete mode 100644 include/asm-x86/syscall.h
 delete mode 100644 include/asm-x86/syscalls.h
 delete mode 100644 include/asm-x86/system.h
 delete mode 100644 include/asm-x86/system_64.h
 delete mode 100644 include/asm-x86/tce.h
 delete mode 100644 include/asm-x86/termbits.h
 delete mode 100644 include/asm-x86/termios.h
 delete mode 100644 include/asm-x86/therm_throt.h
 delete mode 100644 include/asm-x86/thread_info.h
 delete mode 100644 include/asm-x86/time.h
 delete mode 100644 include/asm-x86/timer.h
 delete mode 100644 include/asm-x86/timex.h
 delete mode 100644 include/asm-x86/tlb.h
 delete mode 100644 include/asm-x86/tlbflush.h
 delete mode 100644 include/asm-x86/topology.h
 delete mode 100644 include/asm-x86/trampoline.h
 delete mode 100644 include/asm-x86/traps.h
 delete mode 100644 include/asm-x86/tsc.h
 delete mode 100644 include/asm-x86/types.h
 delete mode 100644 include/asm-x86/uaccess.h
 delete mode 100644 include/asm-x86/uaccess_32.h
 delete mode 100644 include/asm-x86/uaccess_64.h
 delete mode 100644 include/asm-x86/ucontext.h
 delete mode 100644 include/asm-x86/unaligned.h
 delete mode 100644 include/asm-x86/unistd.h
 delete mode 100644 include/asm-x86/unistd_32.h
 delete mode 100644 include/asm-x86/unistd_64.h
 delete mode 100644 include/asm-x86/unwind.h
 delete mode 100644 include/asm-x86/user.h
 delete mode 100644 include/asm-x86/user32.h
 delete mode 100644 include/asm-x86/user_32.h
 delete mode 100644 include/asm-x86/user_64.h
 delete mode 100644 include/asm-x86/uv/bios.h
 delete mode 100644 include/asm-x86/uv/uv_bau.h
 delete mode 100644 include/asm-x86/uv/uv_hub.h
 delete mode 100644 include/asm-x86/uv/uv_irq.h
 delete mode 100644 include/asm-x86/uv/uv_mmrs.h
 delete mode 100644 include/asm-x86/vdso.h
 delete mode 100644 include/asm-x86/vga.h
 delete mode 100644 include/asm-x86/vgtod.h
 delete mode 100644 include/asm-x86/vic.h
 delete mode 100644 include/asm-x86/visws/cobalt.h
 delete mode 100644 include/asm-x86/visws/lithium.h
 delete mode 100644 include/asm-x86/visws/piix4.h
 delete mode 100644 include/asm-x86/visws/sgivw.h
 delete mode 100644 include/asm-x86/vm86.h
 delete mode 100644 include/asm-x86/vmi.h
 delete mode 100644 include/asm-x86/vmi_time.h
 delete mode 100644 include/asm-x86/voyager.h
 delete mode 100644 include/asm-x86/vsyscall.h
 delete mode 100644 include/asm-x86/xcr.h
 delete mode 100644 include/asm-x86/xen/events.h
 delete mode 100644 include/asm-x86/xen/grant_table.h
 delete mode 100644 include/asm-x86/xen/hypercall.h
 delete mode 100644 include/asm-x86/xen/hypervisor.h
 delete mode 100644 include/asm-x86/xen/interface.h
 delete mode 100644 include/asm-x86/xen/interface_32.h
 delete mode 100644 include/asm-x86/xen/interface_64.h
 delete mode 100644 include/asm-x86/xen/page.h
 delete mode 100644 include/asm-x86/xor.h
 delete mode 100644 include/asm-x86/xor_32.h
 delete mode 100644 include/asm-x86/xor_64.h
 delete mode 100644 include/asm-x86/xsave.h

(limited to 'include')

diff --git a/arch/ia64/ia32/audit.c b/arch/ia64/ia32/audit.c
index 5e901c75df1b..5c93ddd1e42d 100644
--- a/arch/ia64/ia32/audit.c
+++ b/arch/ia64/ia32/audit.c
@@ -1,4 +1,4 @@
-#include <asm-x86/unistd_32.h>
+#include "../../x86/include/asm/unistd_32.h"
 
 unsigned ia32_dir_class[] = {
 #include <asm-generic/audit_dir_write.h>
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 94fb24ea5afa..4fc79f3030e4 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -156,9 +156,9 @@ $(ARCH_DIR)/include/asm/arch:
 	@echo '  SYMLINK $@'
 ifneq ($(KBUILD_SRC),)
 	$(Q)mkdir -p $(objtree)/$(ARCH_DIR)/include/asm
-	$(Q)ln -fsn $(srctree)/include/asm-$(HEADER_ARCH) $@
+	$(Q)ln -fsn $(srctree)/arch/$(HEADER_ARCH)/include/asm $@
 else
-	$(Q)ln -fsn ../../../../include/asm-$(HEADER_ARCH) $@
+	$(Q)ln -fsn ../../../$(HEADER_ARCH)/include/asm $@
 endif
 
 $(objtree)/$(ARCH_DIR)/include/shared:
diff --git a/arch/um/sys-x86_64/syscall_table.c b/arch/um/sys-x86_64/syscall_table.c
index 32f5fbe2d0d2..ef42ec01eaff 100644
--- a/arch/um/sys-x86_64/syscall_table.c
+++ b/arch/um/sys-x86_64/syscall_table.c
@@ -42,7 +42,7 @@
 
 #define __SYSCALL(nr, sym) extern asmlinkage void sym(void) ;
 #undef ASM_X86__UNISTD_64_H
-#include <asm-x86/unistd_64.h>
+#include "../../x86/include/asm/unistd_64.h"
 
 #undef __SYSCALL
 #define __SYSCALL(nr, sym) [ nr ] = sym,
@@ -64,7 +64,7 @@ extern void sys_ni_syscall(void);
  */
 
 sys_call_ptr_t sys_call_table[] __cacheline_aligned = {
-#include <asm-x86/unistd_64.h>
+#include "../../x86/include/asm/unistd_64.h"
 };
 
 int syscall_table_size = sizeof(sys_call_table);
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index f5631da585b6..d1a47adb5aec 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -110,16 +110,16 @@ KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
 mcore-y  := arch/x86/mach-default/
 
 # Voyager subarch support
-mflags-$(CONFIG_X86_VOYAGER)	:= -Iinclude/asm-x86/mach-voyager
+mflags-$(CONFIG_X86_VOYAGER)	:= -Iarch/x86/include/asm/mach-voyager
 mcore-$(CONFIG_X86_VOYAGER)	:= arch/x86/mach-voyager/
 
 # generic subarchitecture
-mflags-$(CONFIG_X86_GENERICARCH):= -Iinclude/asm-x86/mach-generic
+mflags-$(CONFIG_X86_GENERICARCH):= -Iarch/x86/include/asm/mach-generic
 fcore-$(CONFIG_X86_GENERICARCH)	+= arch/x86/mach-generic/
 mcore-$(CONFIG_X86_GENERICARCH)	:= arch/x86/mach-default/
 
 # default subarch .h files
-mflags-y += -Iinclude/asm-x86/mach-default
+mflags-y += -Iarch/x86/include/asm/mach-default
 
 # 64 bit does not support subarch support - clear sub arch variables
 fcore-$(CONFIG_X86_64)  :=
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
new file mode 100644
index 000000000000..4a8e80cdcfa5
--- /dev/null
+++ b/arch/x86/include/asm/Kbuild
@@ -0,0 +1,24 @@
+include include/asm-generic/Kbuild.asm
+
+header-y += boot.h
+header-y += bootparam.h
+header-y += debugreg.h
+header-y += ldt.h
+header-y += msr-index.h
+header-y += prctl.h
+header-y += ptrace-abi.h
+header-y += sigcontext32.h
+header-y += ucontext.h
+header-y += processor-flags.h
+
+unifdef-y += e820.h
+unifdef-y += ist.h
+unifdef-y += mce.h
+unifdef-y += msr.h
+unifdef-y += mtrr.h
+unifdef-y += posix_types_32.h
+unifdef-y += posix_types_64.h
+unifdef-y += unistd_32.h
+unifdef-y += unistd_64.h
+unifdef-y += vm86.h
+unifdef-y += vsyscall.h
diff --git a/arch/x86/include/asm/a.out-core.h b/arch/x86/include/asm/a.out-core.h
new file mode 100644
index 000000000000..f5705761a37b
--- /dev/null
+++ b/arch/x86/include/asm/a.out-core.h
@@ -0,0 +1,73 @@
+/* a.out coredump register dumper
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef ASM_X86__A_OUT_CORE_H
+#define ASM_X86__A_OUT_CORE_H
+
+#ifdef __KERNEL__
+#ifdef CONFIG_X86_32
+
+#include <linux/user.h>
+#include <linux/elfcore.h>
+
+/*
+ * fill in the user structure for an a.out core dump
+ */
+static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
+{
+	u16 gs;
+
+/* changed the size calculations - should hopefully work better. lbt */
+	dump->magic = CMAGIC;
+	dump->start_code = 0;
+	dump->start_stack = regs->sp & ~(PAGE_SIZE - 1);
+	dump->u_tsize = ((unsigned long)current->mm->end_code) >> PAGE_SHIFT;
+	dump->u_dsize = ((unsigned long)(current->mm->brk + (PAGE_SIZE - 1)))
+			>> PAGE_SHIFT;
+	dump->u_dsize -= dump->u_tsize;
+	dump->u_ssize = 0;
+	dump->u_debugreg[0] = current->thread.debugreg0;
+	dump->u_debugreg[1] = current->thread.debugreg1;
+	dump->u_debugreg[2] = current->thread.debugreg2;
+	dump->u_debugreg[3] = current->thread.debugreg3;
+	dump->u_debugreg[4] = 0;
+	dump->u_debugreg[5] = 0;
+	dump->u_debugreg[6] = current->thread.debugreg6;
+	dump->u_debugreg[7] = current->thread.debugreg7;
+
+	if (dump->start_stack < TASK_SIZE)
+		dump->u_ssize = ((unsigned long)(TASK_SIZE - dump->start_stack))
+				>> PAGE_SHIFT;
+
+	dump->regs.bx = regs->bx;
+	dump->regs.cx = regs->cx;
+	dump->regs.dx = regs->dx;
+	dump->regs.si = regs->si;
+	dump->regs.di = regs->di;
+	dump->regs.bp = regs->bp;
+	dump->regs.ax = regs->ax;
+	dump->regs.ds = (u16)regs->ds;
+	dump->regs.es = (u16)regs->es;
+	dump->regs.fs = (u16)regs->fs;
+	savesegment(gs, gs);
+	dump->regs.orig_ax = regs->orig_ax;
+	dump->regs.ip = regs->ip;
+	dump->regs.cs = (u16)regs->cs;
+	dump->regs.flags = regs->flags;
+	dump->regs.sp = regs->sp;
+	dump->regs.ss = (u16)regs->ss;
+
+	dump->u_fpvalid = dump_fpu(regs, &dump->i387);
+}
+
+#endif /* CONFIG_X86_32 */
+#endif /* __KERNEL__ */
+#endif /* ASM_X86__A_OUT_CORE_H */
diff --git a/arch/x86/include/asm/a.out.h b/arch/x86/include/asm/a.out.h
new file mode 100644
index 000000000000..0948748bc69c
--- /dev/null
+++ b/arch/x86/include/asm/a.out.h
@@ -0,0 +1,20 @@
+#ifndef ASM_X86__A_OUT_H
+#define ASM_X86__A_OUT_H
+
+struct exec
+{
+	unsigned int a_info;	/* Use macros N_MAGIC, etc for access */
+	unsigned a_text;	/* length of text, in bytes */
+	unsigned a_data;	/* length of data, in bytes */
+	unsigned a_bss;		/* length of uninitialized data area for file, in bytes */
+	unsigned a_syms;	/* length of symbol table data in file, in bytes */
+	unsigned a_entry;	/* start address */
+	unsigned a_trsize;	/* length of relocation info for text, in bytes */
+	unsigned a_drsize;	/* length of relocation info for data, in bytes */
+};
+
+#define N_TRSIZE(a)	((a).a_trsize)
+#define N_DRSIZE(a)	((a).a_drsize)
+#define N_SYMSIZE(a)	((a).a_syms)
+
+#endif /* ASM_X86__A_OUT_H */
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
new file mode 100644
index 000000000000..392e17336be1
--- /dev/null
+++ b/arch/x86/include/asm/acpi.h
@@ -0,0 +1,178 @@
+#ifndef ASM_X86__ACPI_H
+#define ASM_X86__ACPI_H
+
+/*
+ *  Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *  Copyright (C) 2001 Patrick Mochel <mochel@osdl.org>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+#include <acpi/pdc_intel.h>
+
+#include <asm/numa.h>
+#include <asm/processor.h>
+#include <asm/mmu.h>
+#include <asm/mpspec.h>
+
+#define COMPILER_DEPENDENT_INT64   long long
+#define COMPILER_DEPENDENT_UINT64  unsigned long long
+
+/*
+ * Calling conventions:
+ *
+ * ACPI_SYSTEM_XFACE        - Interfaces to host OS (handlers, threads)
+ * ACPI_EXTERNAL_XFACE      - External ACPI interfaces
+ * ACPI_INTERNAL_XFACE      - Internal ACPI interfaces
+ * ACPI_INTERNAL_VAR_XFACE  - Internal variable-parameter list interfaces
+ */
+#define ACPI_SYSTEM_XFACE
+#define ACPI_EXTERNAL_XFACE
+#define ACPI_INTERNAL_XFACE
+#define ACPI_INTERNAL_VAR_XFACE
+
+/* Asm macros */
+
+#define ACPI_ASM_MACROS
+#define BREAKPOINT3
+#define ACPI_DISABLE_IRQS() local_irq_disable()
+#define ACPI_ENABLE_IRQS()  local_irq_enable()
+#define ACPI_FLUSH_CPU_CACHE()	wbinvd()
+
+int __acpi_acquire_global_lock(unsigned int *lock);
+int __acpi_release_global_lock(unsigned int *lock);
+
+#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \
+	((Acq) = __acpi_acquire_global_lock(&facs->global_lock))
+
+#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \
+	((Acq) = __acpi_release_global_lock(&facs->global_lock))
+
+/*
+ * Math helper asm macros
+ */
+#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \
+	asm("divl %2;"				     \
+	    : "=a"(q32), "=d"(r32)		     \
+	    : "r"(d32),				     \
+	     "0"(n_lo), "1"(n_hi))
+
+
+#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \
+	asm("shrl   $1,%2	;"	\
+	    "rcrl   $1,%3;"		\
+	    : "=r"(n_hi), "=r"(n_lo)	\
+	    : "0"(n_hi), "1"(n_lo))
+
+#ifdef CONFIG_ACPI
+extern int acpi_lapic;
+extern int acpi_ioapic;
+extern int acpi_noirq;
+extern int acpi_strict;
+extern int acpi_disabled;
+extern int acpi_ht;
+extern int acpi_pci_disabled;
+extern int acpi_skip_timer_override;
+extern int acpi_use_timer_override;
+
+extern u8 acpi_sci_flags;
+extern int acpi_sci_override_gsi;
+void acpi_pic_sci_set_trigger(unsigned int, u16);
+
+static inline void disable_acpi(void)
+{
+	acpi_disabled = 1;
+	acpi_ht = 0;
+	acpi_pci_disabled = 1;
+	acpi_noirq = 1;
+}
+
+/* Fixmap pages to reserve for ACPI boot-time tables (see fixmap.h) */
+#define FIX_ACPI_PAGES 4
+
+extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
+
+static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
+static inline void acpi_disable_pci(void)
+{
+	acpi_pci_disabled = 1;
+	acpi_noirq_set();
+}
+extern int acpi_irq_balance_set(char *str);
+
+/* routines for saving/restoring kernel state */
+extern int acpi_save_state_mem(void);
+extern void acpi_restore_state_mem(void);
+
+extern unsigned long acpi_wakeup_address;
+
+/* early initialization routine */
+extern void acpi_reserve_bootmem(void);
+
+/*
+ * Check if the CPU can handle C2 and deeper
+ */
+static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
+{
+	/*
+	 * Early models (<=5) of AMD Opterons are not supposed to go into
+	 * C2 state.
+	 *
+	 * Steppings 0x0A and later are good
+	 */
+	if (boot_cpu_data.x86 == 0x0F &&
+	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
+	    boot_cpu_data.x86_model <= 0x05 &&
+	    boot_cpu_data.x86_mask < 0x0A)
+		return 1;
+	else if (boot_cpu_has(X86_FEATURE_AMDC1E))
+		return 1;
+	else
+		return max_cstate;
+}
+
+#else /* !CONFIG_ACPI */
+
+#define acpi_lapic 0
+#define acpi_ioapic 0
+static inline void acpi_noirq_set(void) { }
+static inline void acpi_disable_pci(void) { }
+static inline void disable_acpi(void) { }
+
+#endif /* !CONFIG_ACPI */
+
+#define ARCH_HAS_POWER_INIT	1
+
+struct bootnode;
+
+#ifdef CONFIG_ACPI_NUMA
+extern int acpi_numa;
+extern int acpi_scan_nodes(unsigned long start, unsigned long end);
+#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
+extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
+				   int num_nodes);
+#else
+static inline void acpi_fake_nodes(const struct bootnode *fake_nodes,
+				   int num_nodes)
+{
+}
+#endif
+
+#define acpi_unlazy_tlb(x)	leave_mm(x)
+
+#endif /* ASM_X86__ACPI_H */
diff --git a/arch/x86/include/asm/agp.h b/arch/x86/include/asm/agp.h
new file mode 100644
index 000000000000..3617fd4fcdf9
--- /dev/null
+++ b/arch/x86/include/asm/agp.h
@@ -0,0 +1,35 @@
+#ifndef ASM_X86__AGP_H
+#define ASM_X86__AGP_H
+
+#include <asm/pgtable.h>
+#include <asm/cacheflush.h>
+
+/*
+ * Functions to keep the agpgart mappings coherent with the MMU. The
+ * GART gives the CPU a physical alias of pages in memory. The alias
+ * region is mapped uncacheable. Make sure there are no conflicting
+ * mappings with different cachability attributes for the same
+ * page. This avoids data corruption on some CPUs.
+ */
+
+#define map_page_into_agp(page) set_pages_uc(page, 1)
+#define unmap_page_from_agp(page) set_pages_wb(page, 1)
+
+/*
+ * Could use CLFLUSH here if the cpu supports it. But then it would
+ * need to be called for each cacheline of the whole page so it may
+ * not be worth it. Would need a page for it.
+ */
+#define flush_agp_cache() wbinvd()
+
+/* Convert a physical address to an address suitable for the GART. */
+#define phys_to_gart(x) (x)
+#define gart_to_phys(x) (x)
+
+/* GATT allocation. Returns/accepts GATT kernel virtual address. */
+#define alloc_gatt_pages(order)		\
+	((char *)__get_free_pages(GFP_KERNEL, (order)))
+#define free_gatt_pages(table, order)	\
+	free_pages((unsigned long)(table), (order))
+
+#endif /* ASM_X86__AGP_H */
diff --git a/arch/x86/include/asm/alternative-asm.h b/arch/x86/include/asm/alternative-asm.h
new file mode 100644
index 000000000000..e2077d343c33
--- /dev/null
+++ b/arch/x86/include/asm/alternative-asm.h
@@ -0,0 +1,22 @@
+#ifdef __ASSEMBLY__
+
+#ifdef CONFIG_X86_32
+# define X86_ALIGN .long
+#else
+# define X86_ALIGN .quad
+#endif
+
+#ifdef CONFIG_SMP
+	.macro LOCK_PREFIX
+1:	lock
+	.section .smp_locks,"a"
+	.align 4
+	X86_ALIGN 1b
+	.previous
+	.endm
+#else
+	.macro LOCK_PREFIX
+	.endm
+#endif
+
+#endif  /*  __ASSEMBLY__  */
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
new file mode 100644
index 000000000000..22d3c9862bf3
--- /dev/null
+++ b/arch/x86/include/asm/alternative.h
@@ -0,0 +1,183 @@
+#ifndef ASM_X86__ALTERNATIVE_H
+#define ASM_X86__ALTERNATIVE_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <asm/asm.h>
+
+/*
+ * Alternative inline assembly for SMP.
+ *
+ * The LOCK_PREFIX macro defined here replaces the LOCK and
+ * LOCK_PREFIX macros used everywhere in the source tree.
+ *
+ * SMP alternatives use the same data structures as the other
+ * alternatives and the X86_FEATURE_UP flag to indicate the case of a
+ * UP system running a SMP kernel.  The existing apply_alternatives()
+ * works fine for patching a SMP kernel for UP.
+ *
+ * The SMP alternative tables can be kept after boot and contain both
+ * UP and SMP versions of the instructions to allow switching back to
+ * SMP at runtime, when hotplugging in a new CPU, which is especially
+ * useful in virtualized environments.
+ *
+ * The very common lock prefix is handled as special case in a
+ * separate table which is a pure address list without replacement ptr
+ * and size information.  That keeps the table sizes small.
+ */
+
+#ifdef CONFIG_SMP
+#define LOCK_PREFIX \
+		".section .smp_locks,\"a\"\n"	\
+		_ASM_ALIGN "\n"			\
+		_ASM_PTR "661f\n" /* address */	\
+		".previous\n"			\
+		"661:\n\tlock; "
+
+#else /* ! CONFIG_SMP */
+#define LOCK_PREFIX ""
+#endif
+
+/* This must be included *after* the definition of LOCK_PREFIX */
+#include <asm/cpufeature.h>
+
+struct alt_instr {
+	u8 *instr;		/* original instruction */
+	u8 *replacement;
+	u8  cpuid;		/* cpuid bit set for replacement */
+	u8  instrlen;		/* length of original instruction */
+	u8  replacementlen;	/* length of new instruction, <= instrlen */
+	u8  pad1;
+#ifdef CONFIG_X86_64
+	u32 pad2;
+#endif
+};
+
+extern void alternative_instructions(void);
+extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
+
+struct module;
+
+#ifdef CONFIG_SMP
+extern void alternatives_smp_module_add(struct module *mod, char *name,
+					void *locks, void *locks_end,
+					void *text, void *text_end);
+extern void alternatives_smp_module_del(struct module *mod);
+extern void alternatives_smp_switch(int smp);
+#else
+static inline void alternatives_smp_module_add(struct module *mod, char *name,
+					       void *locks, void *locks_end,
+					       void *text, void *text_end) {}
+static inline void alternatives_smp_module_del(struct module *mod) {}
+static inline void alternatives_smp_switch(int smp) {}
+#endif	/* CONFIG_SMP */
+
+const unsigned char *const *find_nop_table(void);
+
+/*
+ * Alternative instructions for different CPU types or capabilities.
+ *
+ * This allows to use optimized instructions even on generic binary
+ * kernels.
+ *
+ * length of oldinstr must be longer or equal the length of newinstr
+ * It can be padded with nops as needed.
+ *
+ * For non barrier like inlines please define new variants
+ * without volatile and memory clobber.
+ */
+#define alternative(oldinstr, newinstr, feature)			\
+	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
+		      ".section .altinstructions,\"a\"\n"		\
+		      _ASM_ALIGN "\n"					\
+		      _ASM_PTR "661b\n"		/* label */		\
+		      _ASM_PTR "663f\n"		/* new instruction */	\
+		      "	 .byte %c0\n"		/* feature bit */	\
+		      "	 .byte 662b-661b\n"	/* sourcelen */		\
+		      "	 .byte 664f-663f\n"	/* replacementlen */	\
+		      ".previous\n"					\
+		      ".section .altinstr_replacement,\"ax\"\n"		\
+		      "663:\n\t" newinstr "\n664:\n"  /* replacement */	\
+		      ".previous" :: "i" (feature) : "memory")
+
+/*
+ * Alternative inline assembly with input.
+ *
+ * Pecularities:
+ * No memory clobber here.
+ * Argument numbers start with 1.
+ * Best is to use constraints that are fixed size (like (%1) ... "r")
+ * If you use variable sized constraints like "m" or "g" in the
+ * replacement make sure to pad to the worst case length.
+ */
+#define alternative_input(oldinstr, newinstr, feature, input...)	\
+	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
+		      ".section .altinstructions,\"a\"\n"		\
+		      _ASM_ALIGN "\n"					\
+		      _ASM_PTR "661b\n"		/* label */		\
+		      _ASM_PTR "663f\n"		/* new instruction */	\
+		      "	 .byte %c0\n"		/* feature bit */	\
+		      "	 .byte 662b-661b\n"	/* sourcelen */		\
+		      "	 .byte 664f-663f\n"	/* replacementlen */	\
+		      ".previous\n"					\
+		      ".section .altinstr_replacement,\"ax\"\n"		\
+		      "663:\n\t" newinstr "\n664:\n"  /* replacement */	\
+		      ".previous" :: "i" (feature), ##input)
+
+/* Like alternative_input, but with a single output argument */
+#define alternative_io(oldinstr, newinstr, feature, output, input...)	\
+	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
+		      ".section .altinstructions,\"a\"\n"		\
+		      _ASM_ALIGN "\n"					\
+		      _ASM_PTR "661b\n"		/* label */		\
+		      _ASM_PTR "663f\n"		/* new instruction */	\
+		      "	 .byte %c[feat]\n"	/* feature bit */	\
+		      "	 .byte 662b-661b\n"	/* sourcelen */		\
+		      "	 .byte 664f-663f\n"	/* replacementlen */	\
+		      ".previous\n"					\
+		      ".section .altinstr_replacement,\"ax\"\n"		\
+		      "663:\n\t" newinstr "\n664:\n"  /* replacement */ \
+		      ".previous" : output : [feat] "i" (feature), ##input)
+
+/*
+ * use this macro(s) if you need more than one output parameter
+ * in alternative_io
+ */
+#define ASM_OUTPUT2(a, b) a, b
+
+struct paravirt_patch_site;
+#ifdef CONFIG_PARAVIRT
+void apply_paravirt(struct paravirt_patch_site *start,
+		    struct paravirt_patch_site *end);
+#else
+static inline void apply_paravirt(struct paravirt_patch_site *start,
+				  struct paravirt_patch_site *end)
+{}
+#define __parainstructions	NULL
+#define __parainstructions_end	NULL
+#endif
+
+extern void add_nops(void *insns, unsigned int len);
+
+/*
+ * Clear and restore the kernel write-protection flag on the local CPU.
+ * Allows the kernel to edit read-only pages.
+ * Side-effect: any interrupt handler running between save and restore will have
+ * the ability to write to read-only pages.
+ *
+ * Warning:
+ * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and
+ * no thread can be preempted in the instructions being modified (no iret to an
+ * invalid instruction possible) or if the instructions are changed from a
+ * consistent state to another consistent state atomically.
+ * More care must be taken when modifying code in the SMP case because of
+ * Intel's errata.
+ * On the local CPU you need to be protected again NMI or MCE handlers seeing an
+ * inconsistent instruction while you patch.
+ * The _early version expects the memory to already be RW.
+ */
+
+extern void *text_poke(void *addr, const void *opcode, size_t len);
+extern void *text_poke_early(void *addr, const void *opcode, size_t len);
+
+#endif /* ASM_X86__ALTERNATIVE_H */
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
new file mode 100644
index 000000000000..041d0db7da27
--- /dev/null
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -0,0 +1,35 @@
+/*
+ * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *         Leo Duran <leo.duran@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#ifndef ASM_X86__AMD_IOMMU_H
+#define ASM_X86__AMD_IOMMU_H
+
+#include <linux/irqreturn.h>
+
+#ifdef CONFIG_AMD_IOMMU
+extern int amd_iommu_init(void);
+extern int amd_iommu_init_dma_ops(void);
+extern void amd_iommu_detect(void);
+extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
+#else
+static inline int amd_iommu_init(void) { return -ENODEV; }
+static inline void amd_iommu_detect(void) { }
+#endif
+
+#endif /* ASM_X86__AMD_IOMMU_H */
diff --git a/arch/x86/include/asm/amd_iommu_types.h b/arch/x86/include/asm/amd_iommu_types.h
new file mode 100644
index 000000000000..b3085869a17b
--- /dev/null
+++ b/arch/x86/include/asm/amd_iommu_types.h
@@ -0,0 +1,404 @@
+/*
+ * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *         Leo Duran <leo.duran@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#ifndef ASM_X86__AMD_IOMMU_TYPES_H
+#define ASM_X86__AMD_IOMMU_TYPES_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+/*
+ * some size calculation constants
+ */
+#define DEV_TABLE_ENTRY_SIZE		32
+#define ALIAS_TABLE_ENTRY_SIZE		2
+#define RLOOKUP_TABLE_ENTRY_SIZE	(sizeof(void *))
+
+/* Length of the MMIO region for the AMD IOMMU */
+#define MMIO_REGION_LENGTH       0x4000
+
+/* Capability offsets used by the driver */
+#define MMIO_CAP_HDR_OFFSET	0x00
+#define MMIO_RANGE_OFFSET	0x0c
+#define MMIO_MISC_OFFSET	0x10
+
+/* Masks, shifts and macros to parse the device range capability */
+#define MMIO_RANGE_LD_MASK	0xff000000
+#define MMIO_RANGE_FD_MASK	0x00ff0000
+#define MMIO_RANGE_BUS_MASK	0x0000ff00
+#define MMIO_RANGE_LD_SHIFT	24
+#define MMIO_RANGE_FD_SHIFT	16
+#define MMIO_RANGE_BUS_SHIFT	8
+#define MMIO_GET_LD(x)  (((x) & MMIO_RANGE_LD_MASK) >> MMIO_RANGE_LD_SHIFT)
+#define MMIO_GET_FD(x)  (((x) & MMIO_RANGE_FD_MASK) >> MMIO_RANGE_FD_SHIFT)
+#define MMIO_GET_BUS(x) (((x) & MMIO_RANGE_BUS_MASK) >> MMIO_RANGE_BUS_SHIFT)
+#define MMIO_MSI_NUM(x)	((x) & 0x1f)
+
+/* Flag masks for the AMD IOMMU exclusion range */
+#define MMIO_EXCL_ENABLE_MASK 0x01ULL
+#define MMIO_EXCL_ALLOW_MASK  0x02ULL
+
+/* Used offsets into the MMIO space */
+#define MMIO_DEV_TABLE_OFFSET   0x0000
+#define MMIO_CMD_BUF_OFFSET     0x0008
+#define MMIO_EVT_BUF_OFFSET     0x0010
+#define MMIO_CONTROL_OFFSET     0x0018
+#define MMIO_EXCL_BASE_OFFSET   0x0020
+#define MMIO_EXCL_LIMIT_OFFSET  0x0028
+#define MMIO_CMD_HEAD_OFFSET	0x2000
+#define MMIO_CMD_TAIL_OFFSET	0x2008
+#define MMIO_EVT_HEAD_OFFSET	0x2010
+#define MMIO_EVT_TAIL_OFFSET	0x2018
+#define MMIO_STATUS_OFFSET	0x2020
+
+/* MMIO status bits */
+#define MMIO_STATUS_COM_WAIT_INT_MASK	0x04
+
+/* event logging constants */
+#define EVENT_ENTRY_SIZE	0x10
+#define EVENT_TYPE_SHIFT	28
+#define EVENT_TYPE_MASK		0xf
+#define EVENT_TYPE_ILL_DEV	0x1
+#define EVENT_TYPE_IO_FAULT	0x2
+#define EVENT_TYPE_DEV_TAB_ERR	0x3
+#define EVENT_TYPE_PAGE_TAB_ERR	0x4
+#define EVENT_TYPE_ILL_CMD	0x5
+#define EVENT_TYPE_CMD_HARD_ERR	0x6
+#define EVENT_TYPE_IOTLB_INV_TO	0x7
+#define EVENT_TYPE_INV_DEV_REQ	0x8
+#define EVENT_DEVID_MASK	0xffff
+#define EVENT_DEVID_SHIFT	0
+#define EVENT_DOMID_MASK	0xffff
+#define EVENT_DOMID_SHIFT	0
+#define EVENT_FLAGS_MASK	0xfff
+#define EVENT_FLAGS_SHIFT	0x10
+
+/* feature control bits */
+#define CONTROL_IOMMU_EN        0x00ULL
+#define CONTROL_HT_TUN_EN       0x01ULL
+#define CONTROL_EVT_LOG_EN      0x02ULL
+#define CONTROL_EVT_INT_EN      0x03ULL
+#define CONTROL_COMWAIT_EN      0x04ULL
+#define CONTROL_PASSPW_EN       0x08ULL
+#define CONTROL_RESPASSPW_EN    0x09ULL
+#define CONTROL_COHERENT_EN     0x0aULL
+#define CONTROL_ISOC_EN         0x0bULL
+#define CONTROL_CMDBUF_EN       0x0cULL
+#define CONTROL_PPFLOG_EN       0x0dULL
+#define CONTROL_PPFINT_EN       0x0eULL
+
+/* command specific defines */
+#define CMD_COMPL_WAIT          0x01
+#define CMD_INV_DEV_ENTRY       0x02
+#define CMD_INV_IOMMU_PAGES     0x03
+
+#define CMD_COMPL_WAIT_STORE_MASK	0x01
+#define CMD_COMPL_WAIT_INT_MASK		0x02
+#define CMD_INV_IOMMU_PAGES_SIZE_MASK	0x01
+#define CMD_INV_IOMMU_PAGES_PDE_MASK	0x02
+
+#define CMD_INV_IOMMU_ALL_PAGES_ADDRESS	0x7fffffffffffffffULL
+
+/* macros and definitions for device table entries */
+#define DEV_ENTRY_VALID         0x00
+#define DEV_ENTRY_TRANSLATION   0x01
+#define DEV_ENTRY_IR            0x3d
+#define DEV_ENTRY_IW            0x3e
+#define DEV_ENTRY_NO_PAGE_FAULT	0x62
+#define DEV_ENTRY_EX            0x67
+#define DEV_ENTRY_SYSMGT1       0x68
+#define DEV_ENTRY_SYSMGT2       0x69
+#define DEV_ENTRY_INIT_PASS     0xb8
+#define DEV_ENTRY_EINT_PASS     0xb9
+#define DEV_ENTRY_NMI_PASS      0xba
+#define DEV_ENTRY_LINT0_PASS    0xbe
+#define DEV_ENTRY_LINT1_PASS    0xbf
+#define DEV_ENTRY_MODE_MASK	0x07
+#define DEV_ENTRY_MODE_SHIFT	0x09
+
+/* constants to configure the command buffer */
+#define CMD_BUFFER_SIZE    8192
+#define CMD_BUFFER_ENTRIES 512
+#define MMIO_CMD_SIZE_SHIFT 56
+#define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT)
+
+/* constants for event buffer handling */
+#define EVT_BUFFER_SIZE		8192 /* 512 entries */
+#define EVT_LEN_MASK		(0x9ULL << 56)
+
+#define PAGE_MODE_1_LEVEL 0x01
+#define PAGE_MODE_2_LEVEL 0x02
+#define PAGE_MODE_3_LEVEL 0x03
+
+#define IOMMU_PDE_NL_0   0x000ULL
+#define IOMMU_PDE_NL_1   0x200ULL
+#define IOMMU_PDE_NL_2   0x400ULL
+#define IOMMU_PDE_NL_3   0x600ULL
+
+#define IOMMU_PTE_L2_INDEX(address) (((address) >> 30) & 0x1ffULL)
+#define IOMMU_PTE_L1_INDEX(address) (((address) >> 21) & 0x1ffULL)
+#define IOMMU_PTE_L0_INDEX(address) (((address) >> 12) & 0x1ffULL)
+
+#define IOMMU_MAP_SIZE_L1 (1ULL << 21)
+#define IOMMU_MAP_SIZE_L2 (1ULL << 30)
+#define IOMMU_MAP_SIZE_L3 (1ULL << 39)
+
+#define IOMMU_PTE_P  (1ULL << 0)
+#define IOMMU_PTE_TV (1ULL << 1)
+#define IOMMU_PTE_U  (1ULL << 59)
+#define IOMMU_PTE_FC (1ULL << 60)
+#define IOMMU_PTE_IR (1ULL << 61)
+#define IOMMU_PTE_IW (1ULL << 62)
+
+#define IOMMU_L1_PDE(address) \
+	((address) | IOMMU_PDE_NL_1 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
+#define IOMMU_L2_PDE(address) \
+	((address) | IOMMU_PDE_NL_2 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
+
+#define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
+#define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
+#define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))
+#define IOMMU_PTE_MODE(pte) (((pte) >> 9) & 0x07)
+
+#define IOMMU_PROT_MASK 0x03
+#define IOMMU_PROT_IR 0x01
+#define IOMMU_PROT_IW 0x02
+
+/* IOMMU capabilities */
+#define IOMMU_CAP_IOTLB   24
+#define IOMMU_CAP_NPCACHE 26
+
+#define MAX_DOMAIN_ID 65536
+
+/* FIXME: move this macro to <linux/pci.h> */
+#define PCI_BUS(x) (((x) >> 8) & 0xff)
+
+/*
+ * This structure contains generic data for  IOMMU protection domains
+ * independent of their use.
+ */
+struct protection_domain {
+	spinlock_t lock; /* mostly used to lock the page table*/
+	u16 id;		 /* the domain id written to the device table */
+	int mode;	 /* paging mode (0-6 levels) */
+	u64 *pt_root;	 /* page table root pointer */
+	void *priv;	 /* private data */
+};
+
+/*
+ * Data container for a dma_ops specific protection domain
+ */
+struct dma_ops_domain {
+	struct list_head list;
+
+	/* generic protection domain information */
+	struct protection_domain domain;
+
+	/* size of the aperture for the mappings */
+	unsigned long aperture_size;
+
+	/* address we start to search for free addresses */
+	unsigned long next_bit;
+
+	/* address allocation bitmap */
+	unsigned long *bitmap;
+
+	/*
+	 * Array of PTE pages for the aperture. In this array we save all the
+	 * leaf pages of the domain page table used for the aperture. This way
+	 * we don't need to walk the page table to find a specific PTE. We can
+	 * just calculate its address in constant time.
+	 */
+	u64 **pte_pages;
+
+	/* This will be set to true when TLB needs to be flushed */
+	bool need_flush;
+
+	/*
+	 * if this is a preallocated domain, keep the device for which it was
+	 * preallocated in this variable
+	 */
+	u16 target_dev;
+};
+
+/*
+ * Structure where we save information about one hardware AMD IOMMU in the
+ * system.
+ */
+struct amd_iommu {
+	struct list_head list;
+
+	/* locks the accesses to the hardware */
+	spinlock_t lock;
+
+	/* Pointer to PCI device of this IOMMU */
+	struct pci_dev *dev;
+
+	/*
+	 * Capability pointer. There could be more than one IOMMU per PCI
+	 * device function if there are more than one AMD IOMMU capability
+	 * pointers.
+	 */
+	u16 cap_ptr;
+
+	/* physical address of MMIO space */
+	u64 mmio_phys;
+	/* virtual address of MMIO space */
+	u8 *mmio_base;
+
+	/* capabilities of that IOMMU read from ACPI */
+	u32 cap;
+
+	/* pci domain of this IOMMU */
+	u16 pci_seg;
+
+	/* first device this IOMMU handles. read from PCI */
+	u16 first_device;
+	/* last device this IOMMU handles. read from PCI */
+	u16 last_device;
+
+	/* start of exclusion range of that IOMMU */
+	u64 exclusion_start;
+	/* length of exclusion range of that IOMMU */
+	u64 exclusion_length;
+
+	/* command buffer virtual address */
+	u8 *cmd_buf;
+	/* size of command buffer */
+	u32 cmd_buf_size;
+
+	/* event buffer virtual address */
+	u8 *evt_buf;
+	/* size of event buffer */
+	u32 evt_buf_size;
+	/* MSI number for event interrupt */
+	u16 evt_msi_num;
+
+	/* if one, we need to send a completion wait command */
+	int need_sync;
+
+	/* true if interrupts for this IOMMU are already enabled */
+	bool int_enabled;
+
+	/* default dma_ops domain for that IOMMU */
+	struct dma_ops_domain *default_dom;
+};
+
+/*
+ * List with all IOMMUs in the system. This list is not locked because it is
+ * only written and read at driver initialization or suspend time
+ */
+extern struct list_head amd_iommu_list;
+
+/*
+ * Structure defining one entry in the device table
+ */
+struct dev_table_entry {
+	u32 data[8];
+};
+
+/*
+ * One entry for unity mappings parsed out of the ACPI table.
+ */
+struct unity_map_entry {
+	struct list_head list;
+
+	/* starting device id this entry is used for (including) */
+	u16 devid_start;
+	/* end device id this entry is used for (including) */
+	u16 devid_end;
+
+	/* start address to unity map (including) */
+	u64 address_start;
+	/* end address to unity map (including) */
+	u64 address_end;
+
+	/* required protection */
+	int prot;
+};
+
+/*
+ * List of all unity mappings. It is not locked because as runtime it is only
+ * read. It is created at ACPI table parsing time.
+ */
+extern struct list_head amd_iommu_unity_map;
+
+/*
+ * Data structures for device handling
+ */
+
+/*
+ * Device table used by hardware. Read and write accesses by software are
+ * locked with the amd_iommu_pd_table lock.
+ */
+extern struct dev_table_entry *amd_iommu_dev_table;
+
+/*
+ * Alias table to find requestor ids to device ids. Not locked because only
+ * read on runtime.
+ */
+extern u16 *amd_iommu_alias_table;
+
+/*
+ * Reverse lookup table to find the IOMMU which translates a specific device.
+ */
+extern struct amd_iommu **amd_iommu_rlookup_table;
+
+/* size of the dma_ops aperture as power of 2 */
+extern unsigned amd_iommu_aperture_order;
+
+/* largest PCI device id we expect translation requests for */
+extern u16 amd_iommu_last_bdf;
+
+/* data structures for protection domain handling */
+extern struct protection_domain **amd_iommu_pd_table;
+
+/* allocation bitmap for domain ids */
+extern unsigned long *amd_iommu_pd_alloc_bitmap;
+
+/* will be 1 if device isolation is enabled */
+extern int amd_iommu_isolate;
+
+/*
+ * If true, the addresses will be flushed on unmap time, not when
+ * they are reused
+ */
+extern bool amd_iommu_unmap_flush;
+
+/* takes a PCI device id and prints it out in a readable form */
+static inline void print_devid(u16 devid, int nl)
+{
+	int bus = devid >> 8;
+	int dev = devid >> 3 & 0x1f;
+	int fn  = devid & 0x07;
+
+	printk("%02x:%02x.%x", bus, dev, fn);
+	if (nl)
+		printk("\n");
+}
+
+/* takes bus and device/function and returns the device id
+ * FIXME: should that be in generic PCI code? */
+static inline u16 calc_devid(u8 bus, u8 devfn)
+{
+	return (((u16)bus) << 8) | devfn;
+}
+
+#endif /* ASM_X86__AMD_IOMMU_TYPES_H */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
new file mode 100644
index 000000000000..ef1d72dbdfe0
--- /dev/null
+++ b/arch/x86/include/asm/apic.h
@@ -0,0 +1,199 @@
+#ifndef ASM_X86__APIC_H
+#define ASM_X86__APIC_H
+
+#include <linux/pm.h>
+#include <linux/delay.h>
+
+#include <asm/alternative.h>
+#include <asm/fixmap.h>
+#include <asm/apicdef.h>
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/cpufeature.h>
+#include <asm/msr.h>
+
+#define ARCH_APICTIMER_STOPS_ON_C3	1
+
+/*
+ * Debugging macros
+ */
+#define APIC_QUIET   0
+#define APIC_VERBOSE 1
+#define APIC_DEBUG   2
+
+/*
+ * Define the default level of output to be very little
+ * This can be turned up by using apic=verbose for more
+ * information and apic=debug for _lots_ of information.
+ * apic_verbosity is defined in apic.c
+ */
+#define apic_printk(v, s, a...) do {       \
+		if ((v) <= apic_verbosity) \
+			printk(s, ##a);    \
+	} while (0)
+
+
+extern void generic_apic_probe(void);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+extern unsigned int apic_verbosity;
+extern int local_apic_timer_c2_ok;
+
+extern int disable_apic;
+/*
+ * Basic functions accessing APICs.
+ */
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define setup_boot_clock setup_boot_APIC_clock
+#define setup_secondary_clock setup_secondary_APIC_clock
+#endif
+
+extern int is_vsmp_box(void);
+extern void xapic_wait_icr_idle(void);
+extern u32 safe_xapic_wait_icr_idle(void);
+extern u64 xapic_icr_read(void);
+extern void xapic_icr_write(u32, u32);
+extern int setup_profiling_timer(unsigned int);
+
+static inline void native_apic_mem_write(u32 reg, u32 v)
+{
+	volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
+
+	alternative_io("movl %0, %1", "xchgl %0, %1", X86_FEATURE_11AP,
+		       ASM_OUTPUT2("=r" (v), "=m" (*addr)),
+		       ASM_OUTPUT2("0" (v), "m" (*addr)));
+}
+
+static inline u32 native_apic_mem_read(u32 reg)
+{
+	return *((volatile u32 *)(APIC_BASE + reg));
+}
+
+static inline void native_apic_msr_write(u32 reg, u32 v)
+{
+	if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR ||
+	    reg == APIC_LVR)
+		return;
+
+	wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0);
+}
+
+static inline u32 native_apic_msr_read(u32 reg)
+{
+	u32 low, high;
+
+	if (reg == APIC_DFR)
+		return -1;
+
+	rdmsr(APIC_BASE_MSR + (reg >> 4), low, high);
+	return low;
+}
+
+#ifndef CONFIG_X86_32
+extern int x2apic, x2apic_preenabled;
+extern void check_x2apic(void);
+extern void enable_x2apic(void);
+extern void enable_IR_x2apic(void);
+extern void x2apic_icr_write(u32 low, u32 id);
+static inline int x2apic_enabled(void)
+{
+	int msr, msr2;
+
+	if (!cpu_has_x2apic)
+		return 0;
+
+	rdmsr(MSR_IA32_APICBASE, msr, msr2);
+	if (msr & X2APIC_ENABLE)
+		return 1;
+	return 0;
+}
+#else
+#define x2apic_enabled()	0
+#endif
+
+struct apic_ops {
+	u32 (*read)(u32 reg);
+	void (*write)(u32 reg, u32 v);
+	u64 (*icr_read)(void);
+	void (*icr_write)(u32 low, u32 high);
+	void (*wait_icr_idle)(void);
+	u32 (*safe_wait_icr_idle)(void);
+};
+
+extern struct apic_ops *apic_ops;
+
+#define apic_read (apic_ops->read)
+#define apic_write (apic_ops->write)
+#define apic_icr_read (apic_ops->icr_read)
+#define apic_icr_write (apic_ops->icr_write)
+#define apic_wait_icr_idle (apic_ops->wait_icr_idle)
+#define safe_apic_wait_icr_idle (apic_ops->safe_wait_icr_idle)
+
+extern int get_physical_broadcast(void);
+
+#ifdef CONFIG_X86_64
+static inline void ack_x2APIC_irq(void)
+{
+	/* Docs say use 0 for future compatibility */
+	native_apic_msr_write(APIC_EOI, 0);
+}
+#endif
+
+
+static inline void ack_APIC_irq(void)
+{
+	/*
+	 * ack_APIC_irq() actually gets compiled as a single instruction
+	 * ... yummie.
+	 */
+
+	/* Docs say use 0 for future compatibility */
+	apic_write(APIC_EOI, 0);
+}
+
+extern int lapic_get_maxlvt(void);
+extern void clear_local_APIC(void);
+extern void connect_bsp_APIC(void);
+extern void disconnect_bsp_APIC(int virt_wire_setup);
+extern void disable_local_APIC(void);
+extern void lapic_shutdown(void);
+extern int verify_local_APIC(void);
+extern void cache_APIC_registers(void);
+extern void sync_Arb_IDs(void);
+extern void init_bsp_APIC(void);
+extern void setup_local_APIC(void);
+extern void end_local_APIC_setup(void);
+extern void init_apic_mappings(void);
+extern void setup_boot_APIC_clock(void);
+extern void setup_secondary_APIC_clock(void);
+extern int APIC_init_uniprocessor(void);
+extern void enable_NMI_through_LVT0(void);
+
+/*
+ * On 32bit this is mach-xxx local
+ */
+#ifdef CONFIG_X86_64
+extern void early_init_lapic_mapping(void);
+extern int apic_is_clustered_box(void);
+#else
+static inline int apic_is_clustered_box(void)
+{
+	return 0;
+}
+#endif
+
+extern u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask);
+extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
+
+
+#else /* !CONFIG_X86_LOCAL_APIC */
+static inline void lapic_shutdown(void) { }
+#define local_apic_timer_c2_ok		1
+static inline void init_apic_mappings(void) { }
+
+#endif /* !CONFIG_X86_LOCAL_APIC */
+
+#endif /* ASM_X86__APIC_H */
diff --git a/arch/x86/include/asm/apicdef.h b/arch/x86/include/asm/apicdef.h
new file mode 100644
index 000000000000..b922c85ac91d
--- /dev/null
+++ b/arch/x86/include/asm/apicdef.h
@@ -0,0 +1,417 @@
+#ifndef ASM_X86__APICDEF_H
+#define ASM_X86__APICDEF_H
+
+/*
+ * Constants for various Intel APICs. (local APIC, IOAPIC, etc.)
+ *
+ * Alan Cox <Alan.Cox@linux.org>, 1995.
+ * Ingo Molnar <mingo@redhat.com>, 1999, 2000
+ */
+
+#define	APIC_DEFAULT_PHYS_BASE	0xfee00000
+
+#define	APIC_ID		0x20
+
+#define	APIC_LVR	0x30
+#define		APIC_LVR_MASK		0xFF00FF
+#define		GET_APIC_VERSION(x)	((x) & 0xFFu)
+#define		GET_APIC_MAXLVT(x)	(((x) >> 16) & 0xFFu)
+#ifdef CONFIG_X86_32
+#  define	APIC_INTEGRATED(x)	((x) & 0xF0u)
+#else
+#  define	APIC_INTEGRATED(x)	(1)
+#endif
+#define		APIC_XAPIC(x)		((x) >= 0x14)
+#define	APIC_TASKPRI	0x80
+#define		APIC_TPRI_MASK		0xFFu
+#define	APIC_ARBPRI	0x90
+#define		APIC_ARBPRI_MASK	0xFFu
+#define	APIC_PROCPRI	0xA0
+#define	APIC_EOI	0xB0
+#define		APIC_EIO_ACK		0x0
+#define	APIC_RRR	0xC0
+#define	APIC_LDR	0xD0
+#define		APIC_LDR_MASK		(0xFFu << 24)
+#define		GET_APIC_LOGICAL_ID(x)	(((x) >> 24) & 0xFFu)
+#define		SET_APIC_LOGICAL_ID(x)	(((x) << 24))
+#define		APIC_ALL_CPUS		0xFFu
+#define	APIC_DFR	0xE0
+#define		APIC_DFR_CLUSTER		0x0FFFFFFFul
+#define		APIC_DFR_FLAT			0xFFFFFFFFul
+#define	APIC_SPIV	0xF0
+#define		APIC_SPIV_FOCUS_DISABLED	(1 << 9)
+#define		APIC_SPIV_APIC_ENABLED		(1 << 8)
+#define	APIC_ISR	0x100
+#define	APIC_ISR_NR     0x8     /* Number of 32 bit ISR registers. */
+#define	APIC_TMR	0x180
+#define	APIC_IRR	0x200
+#define	APIC_ESR	0x280
+#define		APIC_ESR_SEND_CS	0x00001
+#define		APIC_ESR_RECV_CS	0x00002
+#define		APIC_ESR_SEND_ACC	0x00004
+#define		APIC_ESR_RECV_ACC	0x00008
+#define		APIC_ESR_SENDILL	0x00020
+#define		APIC_ESR_RECVILL	0x00040
+#define		APIC_ESR_ILLREGA	0x00080
+#define	APIC_ICR	0x300
+#define		APIC_DEST_SELF		0x40000
+#define		APIC_DEST_ALLINC	0x80000
+#define		APIC_DEST_ALLBUT	0xC0000
+#define		APIC_ICR_RR_MASK	0x30000
+#define		APIC_ICR_RR_INVALID	0x00000
+#define		APIC_ICR_RR_INPROG	0x10000
+#define		APIC_ICR_RR_VALID	0x20000
+#define		APIC_INT_LEVELTRIG	0x08000
+#define		APIC_INT_ASSERT		0x04000
+#define		APIC_ICR_BUSY		0x01000
+#define		APIC_DEST_LOGICAL	0x00800
+#define		APIC_DEST_PHYSICAL	0x00000
+#define		APIC_DM_FIXED		0x00000
+#define		APIC_DM_LOWEST		0x00100
+#define		APIC_DM_SMI		0x00200
+#define		APIC_DM_REMRD		0x00300
+#define		APIC_DM_NMI		0x00400
+#define		APIC_DM_INIT		0x00500
+#define		APIC_DM_STARTUP		0x00600
+#define		APIC_DM_EXTINT		0x00700
+#define		APIC_VECTOR_MASK	0x000FF
+#define	APIC_ICR2	0x310
+#define		GET_APIC_DEST_FIELD(x)	(((x) >> 24) & 0xFF)
+#define		SET_APIC_DEST_FIELD(x)	((x) << 24)
+#define	APIC_LVTT	0x320
+#define	APIC_LVTTHMR	0x330
+#define	APIC_LVTPC	0x340
+#define	APIC_LVT0	0x350
+#define		APIC_LVT_TIMER_BASE_MASK	(0x3 << 18)
+#define		GET_APIC_TIMER_BASE(x)		(((x) >> 18) & 0x3)
+#define		SET_APIC_TIMER_BASE(x)		(((x) << 18))
+#define		APIC_TIMER_BASE_CLKIN		0x0
+#define		APIC_TIMER_BASE_TMBASE		0x1
+#define		APIC_TIMER_BASE_DIV		0x2
+#define		APIC_LVT_TIMER_PERIODIC		(1 << 17)
+#define		APIC_LVT_MASKED			(1 << 16)
+#define		APIC_LVT_LEVEL_TRIGGER		(1 << 15)
+#define		APIC_LVT_REMOTE_IRR		(1 << 14)
+#define		APIC_INPUT_POLARITY		(1 << 13)
+#define		APIC_SEND_PENDING		(1 << 12)
+#define		APIC_MODE_MASK			0x700
+#define		GET_APIC_DELIVERY_MODE(x)	(((x) >> 8) & 0x7)
+#define		SET_APIC_DELIVERY_MODE(x, y)	(((x) & ~0x700) | ((y) << 8))
+#define			APIC_MODE_FIXED		0x0
+#define			APIC_MODE_NMI		0x4
+#define			APIC_MODE_EXTINT	0x7
+#define	APIC_LVT1	0x360
+#define	APIC_LVTERR	0x370
+#define	APIC_TMICT	0x380
+#define	APIC_TMCCT	0x390
+#define	APIC_TDCR	0x3E0
+#define APIC_SELF_IPI	0x3F0
+#define		APIC_TDR_DIV_TMBASE	(1 << 2)
+#define		APIC_TDR_DIV_1		0xB
+#define		APIC_TDR_DIV_2		0x0
+#define		APIC_TDR_DIV_4		0x1
+#define		APIC_TDR_DIV_8		0x2
+#define		APIC_TDR_DIV_16		0x3
+#define		APIC_TDR_DIV_32		0x8
+#define		APIC_TDR_DIV_64		0x9
+#define		APIC_TDR_DIV_128	0xA
+#define	APIC_EILVT0     0x500
+#define		APIC_EILVT_NR_AMD_K8	1	/* # of extended interrupts */
+#define		APIC_EILVT_NR_AMD_10H	4
+#define		APIC_EILVT_LVTOFF(x)	(((x) >> 4) & 0xF)
+#define		APIC_EILVT_MSG_FIX	0x0
+#define		APIC_EILVT_MSG_SMI	0x2
+#define		APIC_EILVT_MSG_NMI	0x4
+#define		APIC_EILVT_MSG_EXT	0x7
+#define		APIC_EILVT_MASKED	(1 << 16)
+#define	APIC_EILVT1     0x510
+#define	APIC_EILVT2     0x520
+#define	APIC_EILVT3     0x530
+
+#define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
+#define APIC_BASE_MSR	0x800
+#define X2APIC_ENABLE	(1UL << 10)
+
+#ifdef CONFIG_X86_32
+# define MAX_IO_APICS 64
+#else
+# define MAX_IO_APICS 128
+# define MAX_LOCAL_APIC 32768
+#endif
+
+/*
+ * All x86-64 systems are xAPIC compatible.
+ * In the following, "apicid" is a physical APIC ID.
+ */
+#define XAPIC_DEST_CPUS_SHIFT	4
+#define XAPIC_DEST_CPUS_MASK	((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
+#define XAPIC_DEST_CLUSTER_MASK	(XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
+#define APIC_CLUSTER(apicid)	((apicid) & XAPIC_DEST_CLUSTER_MASK)
+#define APIC_CLUSTERID(apicid)	(APIC_CLUSTER(apicid) >> XAPIC_DEST_CPUS_SHIFT)
+#define APIC_CPUID(apicid)	((apicid) & XAPIC_DEST_CPUS_MASK)
+#define NUM_APIC_CLUSTERS	((BAD_APICID + 1) >> XAPIC_DEST_CPUS_SHIFT)
+
+/*
+ * the local APIC register structure, memory mapped. Not terribly well
+ * tested, but we might eventually use this one in the future - the
+ * problem why we cannot use it right now is the P5 APIC, it has an
+ * errata which cannot take 8-bit reads and writes, only 32-bit ones ...
+ */
+#define u32 unsigned int
+
+struct local_apic {
+
+/*000*/	struct { u32 __reserved[4]; } __reserved_01;
+
+/*010*/	struct { u32 __reserved[4]; } __reserved_02;
+
+/*020*/	struct { /* APIC ID Register */
+		u32   __reserved_1	: 24,
+			phys_apic_id	:  4,
+			__reserved_2	:  4;
+		u32 __reserved[3];
+	} id;
+
+/*030*/	const
+	struct { /* APIC Version Register */
+		u32   version		:  8,
+			__reserved_1	:  8,
+			max_lvt		:  8,
+			__reserved_2	:  8;
+		u32 __reserved[3];
+	} version;
+
+/*040*/	struct { u32 __reserved[4]; } __reserved_03;
+
+/*050*/	struct { u32 __reserved[4]; } __reserved_04;
+
+/*060*/	struct { u32 __reserved[4]; } __reserved_05;
+
+/*070*/	struct { u32 __reserved[4]; } __reserved_06;
+
+/*080*/	struct { /* Task Priority Register */
+		u32   priority	:  8,
+			__reserved_1	: 24;
+		u32 __reserved_2[3];
+	} tpr;
+
+/*090*/	const
+	struct { /* Arbitration Priority Register */
+		u32   priority	:  8,
+			__reserved_1	: 24;
+		u32 __reserved_2[3];
+	} apr;
+
+/*0A0*/	const
+	struct { /* Processor Priority Register */
+		u32   priority	:  8,
+			__reserved_1	: 24;
+		u32 __reserved_2[3];
+	} ppr;
+
+/*0B0*/	struct { /* End Of Interrupt Register */
+		u32   eoi;
+		u32 __reserved[3];
+	} eoi;
+
+/*0C0*/	struct { u32 __reserved[4]; } __reserved_07;
+
+/*0D0*/	struct { /* Logical Destination Register */
+		u32   __reserved_1	: 24,
+			logical_dest	:  8;
+		u32 __reserved_2[3];
+	} ldr;
+
+/*0E0*/	struct { /* Destination Format Register */
+		u32   __reserved_1	: 28,
+			model		:  4;
+		u32 __reserved_2[3];
+	} dfr;
+
+/*0F0*/	struct { /* Spurious Interrupt Vector Register */
+		u32	spurious_vector	:  8,
+			apic_enabled	:  1,
+			focus_cpu	:  1,
+			__reserved_2	: 22;
+		u32 __reserved_3[3];
+	} svr;
+
+/*100*/	struct { /* In Service Register */
+/*170*/		u32 bitfield;
+		u32 __reserved[3];
+	} isr [8];
+
+/*180*/	struct { /* Trigger Mode Register */
+/*1F0*/		u32 bitfield;
+		u32 __reserved[3];
+	} tmr [8];
+
+/*200*/	struct { /* Interrupt Request Register */
+/*270*/		u32 bitfield;
+		u32 __reserved[3];
+	} irr [8];
+
+/*280*/	union { /* Error Status Register */
+		struct {
+			u32   send_cs_error			:  1,
+				receive_cs_error		:  1,
+				send_accept_error		:  1,
+				receive_accept_error		:  1,
+				__reserved_1			:  1,
+				send_illegal_vector		:  1,
+				receive_illegal_vector		:  1,
+				illegal_register_address	:  1,
+				__reserved_2			: 24;
+			u32 __reserved_3[3];
+		} error_bits;
+		struct {
+			u32 errors;
+			u32 __reserved_3[3];
+		} all_errors;
+	} esr;
+
+/*290*/	struct { u32 __reserved[4]; } __reserved_08;
+
+/*2A0*/	struct { u32 __reserved[4]; } __reserved_09;
+
+/*2B0*/	struct { u32 __reserved[4]; } __reserved_10;
+
+/*2C0*/	struct { u32 __reserved[4]; } __reserved_11;
+
+/*2D0*/	struct { u32 __reserved[4]; } __reserved_12;
+
+/*2E0*/	struct { u32 __reserved[4]; } __reserved_13;
+
+/*2F0*/	struct { u32 __reserved[4]; } __reserved_14;
+
+/*300*/	struct { /* Interrupt Command Register 1 */
+		u32   vector			:  8,
+			delivery_mode		:  3,
+			destination_mode	:  1,
+			delivery_status		:  1,
+			__reserved_1		:  1,
+			level			:  1,
+			trigger			:  1,
+			__reserved_2		:  2,
+			shorthand		:  2,
+			__reserved_3		:  12;
+		u32 __reserved_4[3];
+	} icr1;
+
+/*310*/	struct { /* Interrupt Command Register 2 */
+		union {
+			u32   __reserved_1	: 24,
+				phys_dest	:  4,
+				__reserved_2	:  4;
+			u32   __reserved_3	: 24,
+				logical_dest	:  8;
+		} dest;
+		u32 __reserved_4[3];
+	} icr2;
+
+/*320*/	struct { /* LVT - Timer */
+		u32   vector		:  8,
+			__reserved_1	:  4,
+			delivery_status	:  1,
+			__reserved_2	:  3,
+			mask		:  1,
+			timer_mode	:  1,
+			__reserved_3	: 14;
+		u32 __reserved_4[3];
+	} lvt_timer;
+
+/*330*/	struct { /* LVT - Thermal Sensor */
+		u32  vector		:  8,
+			delivery_mode	:  3,
+			__reserved_1	:  1,
+			delivery_status	:  1,
+			__reserved_2	:  3,
+			mask		:  1,
+			__reserved_3	: 15;
+		u32 __reserved_4[3];
+	} lvt_thermal;
+
+/*340*/	struct { /* LVT - Performance Counter */
+		u32   vector		:  8,
+			delivery_mode	:  3,
+			__reserved_1	:  1,
+			delivery_status	:  1,
+			__reserved_2	:  3,
+			mask		:  1,
+			__reserved_3	: 15;
+		u32 __reserved_4[3];
+	} lvt_pc;
+
+/*350*/	struct { /* LVT - LINT0 */
+		u32   vector		:  8,
+			delivery_mode	:  3,
+			__reserved_1	:  1,
+			delivery_status	:  1,
+			polarity	:  1,
+			remote_irr	:  1,
+			trigger		:  1,
+			mask		:  1,
+			__reserved_2	: 15;
+		u32 __reserved_3[3];
+	} lvt_lint0;
+
+/*360*/	struct { /* LVT - LINT1 */
+		u32   vector		:  8,
+			delivery_mode	:  3,
+			__reserved_1	:  1,
+			delivery_status	:  1,
+			polarity	:  1,
+			remote_irr	:  1,
+			trigger		:  1,
+			mask		:  1,
+			__reserved_2	: 15;
+		u32 __reserved_3[3];
+	} lvt_lint1;
+
+/*370*/	struct { /* LVT - Error */
+		u32   vector		:  8,
+			__reserved_1	:  4,
+			delivery_status	:  1,
+			__reserved_2	:  3,
+			mask		:  1,
+			__reserved_3	: 15;
+		u32 __reserved_4[3];
+	} lvt_error;
+
+/*380*/	struct { /* Timer Initial Count Register */
+		u32   initial_count;
+		u32 __reserved_2[3];
+	} timer_icr;
+
+/*390*/	const
+	struct { /* Timer Current Count Register */
+		u32   curr_count;
+		u32 __reserved_2[3];
+	} timer_ccr;
+
+/*3A0*/	struct { u32 __reserved[4]; } __reserved_16;
+
+/*3B0*/	struct { u32 __reserved[4]; } __reserved_17;
+
+/*3C0*/	struct { u32 __reserved[4]; } __reserved_18;
+
+/*3D0*/	struct { u32 __reserved[4]; } __reserved_19;
+
+/*3E0*/	struct { /* Timer Divide Configuration Register */
+		u32   divisor		:  4,
+			__reserved_1	: 28;
+		u32 __reserved_2[3];
+	} timer_dcr;
+
+/*3F0*/	struct { u32 __reserved[4]; } __reserved_20;
+
+} __attribute__ ((packed));
+
+#undef u32
+
+#ifdef CONFIG_X86_32
+ #define BAD_APICID 0xFFu
+#else
+ #define BAD_APICID 0xFFFFu
+#endif
+#endif /* ASM_X86__APICDEF_H */
diff --git a/arch/x86/include/asm/arch_hooks.h b/arch/x86/include/asm/arch_hooks.h
new file mode 100644
index 000000000000..de4596b24c23
--- /dev/null
+++ b/arch/x86/include/asm/arch_hooks.h
@@ -0,0 +1,26 @@
+#ifndef ASM_X86__ARCH_HOOKS_H
+#define ASM_X86__ARCH_HOOKS_H
+
+#include <linux/interrupt.h>
+
+/*
+ *	linux/include/asm/arch_hooks.h
+ *
+ *	define the architecture specific hooks
+ */
+
+/* these aren't arch hooks, they are generic routines
+ * that can be used by the hooks */
+extern void init_ISA_irqs(void);
+extern irqreturn_t timer_interrupt(int irq, void *dev_id);
+
+/* these are the defined hooks */
+extern void intr_init_hook(void);
+extern void pre_intr_init_hook(void);
+extern void pre_setup_arch_hook(void);
+extern void trap_init_hook(void);
+extern void pre_time_init_hook(void);
+extern void time_init_hook(void);
+extern void mca_nmi_hook(void);
+
+#endif /* ASM_X86__ARCH_HOOKS_H */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
new file mode 100644
index 000000000000..e1355f44d7c3
--- /dev/null
+++ b/arch/x86/include/asm/asm.h
@@ -0,0 +1,47 @@
+#ifndef ASM_X86__ASM_H
+#define ASM_X86__ASM_H
+
+#ifdef __ASSEMBLY__
+# define __ASM_FORM(x)	x
+# define __ASM_EX_SEC	.section __ex_table
+#else
+# define __ASM_FORM(x)	" " #x " "
+# define __ASM_EX_SEC	" .section __ex_table,\"a\"\n"
+#endif
+
+#ifdef CONFIG_X86_32
+# define __ASM_SEL(a,b) __ASM_FORM(a)
+#else
+# define __ASM_SEL(a,b) __ASM_FORM(b)
+#endif
+
+#define __ASM_SIZE(inst)	__ASM_SEL(inst##l, inst##q)
+#define __ASM_REG(reg)		__ASM_SEL(e##reg, r##reg)
+
+#define _ASM_PTR	__ASM_SEL(.long, .quad)
+#define _ASM_ALIGN	__ASM_SEL(.balign 4, .balign 8)
+
+#define _ASM_MOV	__ASM_SIZE(mov)
+#define _ASM_INC	__ASM_SIZE(inc)
+#define _ASM_DEC	__ASM_SIZE(dec)
+#define _ASM_ADD	__ASM_SIZE(add)
+#define _ASM_SUB	__ASM_SIZE(sub)
+#define _ASM_XADD	__ASM_SIZE(xadd)
+
+#define _ASM_AX		__ASM_REG(ax)
+#define _ASM_BX		__ASM_REG(bx)
+#define _ASM_CX		__ASM_REG(cx)
+#define _ASM_DX		__ASM_REG(dx)
+#define _ASM_SP		__ASM_REG(sp)
+#define _ASM_BP		__ASM_REG(bp)
+#define _ASM_SI		__ASM_REG(si)
+#define _ASM_DI		__ASM_REG(di)
+
+/* Exception table entry */
+# define _ASM_EXTABLE(from,to) \
+	__ASM_EX_SEC	\
+	_ASM_ALIGN "\n" \
+	_ASM_PTR #from "," #to "\n" \
+	" .previous\n"
+
+#endif /* ASM_X86__ASM_H */
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
new file mode 100644
index 000000000000..4e1b8873c474
--- /dev/null
+++ b/arch/x86/include/asm/atomic.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "atomic_32.h"
+#else
+# include "atomic_64.h"
+#endif
diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h
new file mode 100644
index 000000000000..14d3f0beb889
--- /dev/null
+++ b/arch/x86/include/asm/atomic_32.h
@@ -0,0 +1,259 @@
+#ifndef ASM_X86__ATOMIC_32_H
+#define ASM_X86__ATOMIC_32_H
+
+#include <linux/compiler.h>
+#include <asm/processor.h>
+#include <asm/cmpxchg.h>
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ */
+
+/*
+ * Make sure gcc doesn't try to be clever and move things around
+ * on us. We need to use _exactly_ the address the user gave us,
+ * not some alias that contains the same information.
+ */
+typedef struct {
+	int counter;
+} atomic_t;
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+#define atomic_read(v)		((v)->counter)
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+#define atomic_set(v, i)	(((v)->counter) = (i))
+
+/**
+ * atomic_add - add integer to atomic variable
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v.
+ */
+static inline void atomic_add(int i, atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "addl %1,%0"
+		     : "+m" (v->counter)
+		     : "ir" (i));
+}
+
+/**
+ * atomic_sub - subtract integer from atomic variable
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v.
+ */
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "subl %1,%0"
+		     : "+m" (v->counter)
+		     : "ir" (i));
+}
+
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic_sub_and_test(int i, atomic_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
+		     : "+m" (v->counter), "=qm" (c)
+		     : "ir" (i) : "memory");
+	return c;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "incl %0"
+		     : "+m" (v->counter));
+}
+
+/**
+ * atomic_dec - decrement atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1.
+ */
+static inline void atomic_dec(atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "decl %0"
+		     : "+m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "decl %0; sete %1"
+		     : "+m" (v->counter), "=qm" (c)
+		     : : "memory");
+	return c != 0;
+}
+
+/**
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic_inc_and_test(atomic_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "incl %0; sete %1"
+		     : "+m" (v->counter), "=qm" (c)
+		     : : "memory");
+	return c != 0;
+}
+
+/**
+ * atomic_add_negative - add and test if negative
+ * @v: pointer of type atomic_t
+ * @i: integer value to add
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static inline int atomic_add_negative(int i, atomic_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
+		     : "+m" (v->counter), "=qm" (c)
+		     : "ir" (i) : "memory");
+	return c;
+}
+
+/**
+ * atomic_add_return - add integer and return
+ * @v: pointer of type atomic_t
+ * @i: integer value to add
+ *
+ * Atomically adds @i to @v and returns @i + @v
+ */
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	int __i;
+#ifdef CONFIG_M386
+	unsigned long flags;
+	if (unlikely(boot_cpu_data.x86 <= 3))
+		goto no_xadd;
+#endif
+	/* Modern 486+ processor */
+	__i = i;
+	asm volatile(LOCK_PREFIX "xaddl %0, %1"
+		     : "+r" (i), "+m" (v->counter)
+		     : : "memory");
+	return i + __i;
+
+#ifdef CONFIG_M386
+no_xadd: /* Legacy 386 processor */
+	local_irq_save(flags);
+	__i = atomic_read(v);
+	atomic_set(v, i + __i);
+	local_irq_restore(flags);
+	return i + __i;
+#endif
+}
+
+/**
+ * atomic_sub_return - subtract integer and return
+ * @v: pointer of type atomic_t
+ * @i: integer value to subtract
+ *
+ * Atomically subtracts @i from @v and returns @v - @i
+ */
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	return atomic_add_return(-i, v);
+}
+
+#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
+#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
+
+/**
+ * atomic_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as @v was not already @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static inline int atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int c, old;
+	c = atomic_read(v);
+	for (;;) {
+		if (unlikely(c == (u)))
+			break;
+		old = atomic_cmpxchg((v), c, c + (a));
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+	return c != (u);
+}
+
+#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+
+#define atomic_inc_return(v)  (atomic_add_return(1, v))
+#define atomic_dec_return(v)  (atomic_sub_return(1, v))
+
+/* These are x86-specific, used by some header files */
+#define atomic_clear_mask(mask, addr)				\
+	asm volatile(LOCK_PREFIX "andl %0,%1"			\
+		     : : "r" (~(mask)), "m" (*(addr)) : "memory")
+
+#define atomic_set_mask(mask, addr)				\
+	asm volatile(LOCK_PREFIX "orl %0,%1"				\
+		     : : "r" (mask), "m" (*(addr)) : "memory")
+
+/* Atomic operations are already serializing on x86 */
+#define smp_mb__before_atomic_dec()	barrier()
+#define smp_mb__after_atomic_dec()	barrier()
+#define smp_mb__before_atomic_inc()	barrier()
+#define smp_mb__after_atomic_inc()	barrier()
+
+#include <asm-generic/atomic.h>
+#endif /* ASM_X86__ATOMIC_32_H */
diff --git a/arch/x86/include/asm/atomic_64.h b/arch/x86/include/asm/atomic_64.h
new file mode 100644
index 000000000000..2cb218c4a356
--- /dev/null
+++ b/arch/x86/include/asm/atomic_64.h
@@ -0,0 +1,473 @@
+#ifndef ASM_X86__ATOMIC_64_H
+#define ASM_X86__ATOMIC_64_H
+
+#include <asm/alternative.h>
+#include <asm/cmpxchg.h>
+
+/* atomic_t should be 32 bit signed type */
+
+/*
+ * Atomic operations that C can't guarantee us.  Useful for
+ * resource counting etc..
+ */
+
+/*
+ * Make sure gcc doesn't try to be clever and move things around
+ * on us. We need to use _exactly_ the address the user gave us,
+ * not some alias that contains the same information.
+ */
+typedef struct {
+	int counter;
+} atomic_t;
+
+#define ATOMIC_INIT(i)	{ (i) }
+
+/**
+ * atomic_read - read atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically reads the value of @v.
+ */
+#define atomic_read(v)		((v)->counter)
+
+/**
+ * atomic_set - set atomic variable
+ * @v: pointer of type atomic_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+#define atomic_set(v, i)		(((v)->counter) = (i))
+
+/**
+ * atomic_add - add integer to atomic variable
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v.
+ */
+static inline void atomic_add(int i, atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "addl %1,%0"
+		     : "=m" (v->counter)
+		     : "ir" (i), "m" (v->counter));
+}
+
+/**
+ * atomic_sub - subtract the atomic variable
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v.
+ */
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "subl %1,%0"
+		     : "=m" (v->counter)
+		     : "ir" (i), "m" (v->counter));
+}
+
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic_sub_and_test(int i, atomic_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
+		     : "=m" (v->counter), "=qm" (c)
+		     : "ir" (i), "m" (v->counter) : "memory");
+	return c;
+}
+
+/**
+ * atomic_inc - increment atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic_inc(atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "incl %0"
+		     : "=m" (v->counter)
+		     : "m" (v->counter));
+}
+
+/**
+ * atomic_dec - decrement atomic variable
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1.
+ */
+static inline void atomic_dec(atomic_t *v)
+{
+	asm volatile(LOCK_PREFIX "decl %0"
+		     : "=m" (v->counter)
+		     : "m" (v->counter));
+}
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic_dec_and_test(atomic_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "decl %0; sete %1"
+		     : "=m" (v->counter), "=qm" (c)
+		     : "m" (v->counter) : "memory");
+	return c != 0;
+}
+
+/**
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic_inc_and_test(atomic_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "incl %0; sete %1"
+		     : "=m" (v->counter), "=qm" (c)
+		     : "m" (v->counter) : "memory");
+	return c != 0;
+}
+
+/**
+ * atomic_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static inline int atomic_add_negative(int i, atomic_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
+		     : "=m" (v->counter), "=qm" (c)
+		     : "ir" (i), "m" (v->counter) : "memory");
+	return c;
+}
+
+/**
+ * atomic_add_return - add and return
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v and returns @i + @v
+ */
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	int __i = i;
+	asm volatile(LOCK_PREFIX "xaddl %0, %1"
+		     : "+r" (i), "+m" (v->counter)
+		     : : "memory");
+	return i + __i;
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	return atomic_add_return(-i, v);
+}
+
+#define atomic_inc_return(v)  (atomic_add_return(1, v))
+#define atomic_dec_return(v)  (atomic_sub_return(1, v))
+
+/* An 64bit atomic type */
+
+typedef struct {
+	long counter;
+} atomic64_t;
+
+#define ATOMIC64_INIT(i)	{ (i) }
+
+/**
+ * atomic64_read - read atomic64 variable
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically reads the value of @v.
+ * Doesn't imply a read memory barrier.
+ */
+#define atomic64_read(v)		((v)->counter)
+
+/**
+ * atomic64_set - set atomic64 variable
+ * @v: pointer to type atomic64_t
+ * @i: required value
+ *
+ * Atomically sets the value of @v to @i.
+ */
+#define atomic64_set(v, i)		(((v)->counter) = (i))
+
+/**
+ * atomic64_add - add integer to atomic64 variable
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v.
+ */
+static inline void atomic64_add(long i, atomic64_t *v)
+{
+	asm volatile(LOCK_PREFIX "addq %1,%0"
+		     : "=m" (v->counter)
+		     : "er" (i), "m" (v->counter));
+}
+
+/**
+ * atomic64_sub - subtract the atomic64 variable
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically subtracts @i from @v.
+ */
+static inline void atomic64_sub(long i, atomic64_t *v)
+{
+	asm volatile(LOCK_PREFIX "subq %1,%0"
+		     : "=m" (v->counter)
+		     : "er" (i), "m" (v->counter));
+}
+
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic64_sub_and_test(long i, atomic64_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
+		     : "=m" (v->counter), "=qm" (c)
+		     : "er" (i), "m" (v->counter) : "memory");
+	return c;
+}
+
+/**
+ * atomic64_inc - increment atomic64 variable
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically increments @v by 1.
+ */
+static inline void atomic64_inc(atomic64_t *v)
+{
+	asm volatile(LOCK_PREFIX "incq %0"
+		     : "=m" (v->counter)
+		     : "m" (v->counter));
+}
+
+/**
+ * atomic64_dec - decrement atomic64 variable
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically decrements @v by 1.
+ */
+static inline void atomic64_dec(atomic64_t *v)
+{
+	asm volatile(LOCK_PREFIX "decq %0"
+		     : "=m" (v->counter)
+		     : "m" (v->counter));
+}
+
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int atomic64_dec_and_test(atomic64_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "decq %0; sete %1"
+		     : "=m" (v->counter), "=qm" (c)
+		     : "m" (v->counter) : "memory");
+	return c != 0;
+}
+
+/**
+ * atomic64_inc_and_test - increment and test
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int atomic64_inc_and_test(atomic64_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "incq %0; sete %1"
+		     : "=m" (v->counter), "=qm" (c)
+		     : "m" (v->counter) : "memory");
+	return c != 0;
+}
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static inline int atomic64_add_negative(long i, atomic64_t *v)
+{
+	unsigned char c;
+
+	asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
+		     : "=m" (v->counter), "=qm" (c)
+		     : "er" (i), "m" (v->counter) : "memory");
+	return c;
+}
+
+/**
+ * atomic64_add_return - add and return
+ * @i: integer value to add
+ * @v: pointer to type atomic64_t
+ *
+ * Atomically adds @i to @v and returns @i + @v
+ */
+static inline long atomic64_add_return(long i, atomic64_t *v)
+{
+	long __i = i;
+	asm volatile(LOCK_PREFIX "xaddq %0, %1;"
+		     : "+r" (i), "+m" (v->counter)
+		     : : "memory");
+	return i + __i;
+}
+
+static inline long atomic64_sub_return(long i, atomic64_t *v)
+{
+	return atomic64_add_return(-i, v);
+}
+
+#define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
+#define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
+
+#define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
+#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
+
+#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
+#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
+
+/**
+ * atomic_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static inline int atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int c, old;
+	c = atomic_read(v);
+	for (;;) {
+		if (unlikely(c == (u)))
+			break;
+		old = atomic_cmpxchg((v), c, c + (a));
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+	return c != (u);
+}
+
+#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
+
+/**
+ * atomic64_add_unless - add unless the number is a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, so long as it was not @u.
+ * Returns non-zero if @v was not @u, and zero otherwise.
+ */
+static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
+{
+	long c, old;
+	c = atomic64_read(v);
+	for (;;) {
+		if (unlikely(c == (u)))
+			break;
+		old = atomic64_cmpxchg((v), c, c + (a));
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+	return c != (u);
+}
+
+/**
+ * atomic_inc_short - increment of a short integer
+ * @v: pointer to type int
+ *
+ * Atomically adds 1 to @v
+ * Returns the new value of @u
+ */
+static inline short int atomic_inc_short(short int *v)
+{
+	asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
+	return *v;
+}
+
+/**
+ * atomic_or_long - OR of two long integers
+ * @v1: pointer to type unsigned long
+ * @v2: pointer to type unsigned long
+ *
+ * Atomically ORs @v1 and @v2
+ * Returns the result of the OR
+ */
+static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
+{
+	asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
+}
+
+#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
+
+/* These are x86-specific, used by some header files */
+#define atomic_clear_mask(mask, addr)					\
+	asm volatile(LOCK_PREFIX "andl %0,%1"				\
+		     : : "r" (~(mask)), "m" (*(addr)) : "memory")
+
+#define atomic_set_mask(mask, addr)					\
+	asm volatile(LOCK_PREFIX "orl %0,%1"				\
+		     : : "r" ((unsigned)(mask)), "m" (*(addr))		\
+		     : "memory")
+
+/* Atomic operations are already serializing on x86 */
+#define smp_mb__before_atomic_dec()	barrier()
+#define smp_mb__after_atomic_dec()	barrier()
+#define smp_mb__before_atomic_inc()	barrier()
+#define smp_mb__after_atomic_inc()	barrier()
+
+#include <asm-generic/atomic.h>
+#endif /* ASM_X86__ATOMIC_64_H */
diff --git a/arch/x86/include/asm/auxvec.h b/arch/x86/include/asm/auxvec.h
new file mode 100644
index 000000000000..12c7cac74202
--- /dev/null
+++ b/arch/x86/include/asm/auxvec.h
@@ -0,0 +1,12 @@
+#ifndef ASM_X86__AUXVEC_H
+#define ASM_X86__AUXVEC_H
+/*
+ * Architecture-neutral AT_ values in 0-17, leave some room
+ * for more of them, start the x86-specific ones at 32.
+ */
+#ifdef __i386__
+#define AT_SYSINFO		32
+#endif
+#define AT_SYSINFO_EHDR		33
+
+#endif /* ASM_X86__AUXVEC_H */
diff --git a/arch/x86/include/asm/bigsmp/apic.h b/arch/x86/include/asm/bigsmp/apic.h
new file mode 100644
index 000000000000..1d9543b9d358
--- /dev/null
+++ b/arch/x86/include/asm/bigsmp/apic.h
@@ -0,0 +1,139 @@
+#ifndef __ASM_MACH_APIC_H
+#define __ASM_MACH_APIC_H
+
+#define xapic_phys_to_log_apicid(cpu) (per_cpu(x86_bios_cpu_apicid, cpu))
+#define esr_disable (1)
+
+static inline int apic_id_registered(void)
+{
+	return (1);
+}
+
+static inline cpumask_t target_cpus(void)
+{
+#ifdef CONFIG_SMP
+        return cpu_online_map;
+#else
+        return cpumask_of_cpu(0);
+#endif
+}
+
+#undef APIC_DEST_LOGICAL
+#define APIC_DEST_LOGICAL	0
+#define APIC_DFR_VALUE		(APIC_DFR_FLAT)
+#define INT_DELIVERY_MODE	(dest_Fixed)
+#define INT_DEST_MODE		(0)    /* phys delivery to target proc */
+#define NO_BALANCE_IRQ		(0)
+#define WAKE_SECONDARY_VIA_INIT
+
+
+static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+	return (0);
+}
+
+static inline unsigned long check_apicid_present(int bit)
+{
+	return (1);
+}
+
+static inline unsigned long calculate_ldr(int cpu)
+{
+	unsigned long val, id;
+	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+	id = xapic_phys_to_log_apicid(cpu);
+	val |= SET_APIC_LOGICAL_ID(id);
+	return val;
+}
+
+/*
+ * Set up the logical destination ID.
+ *
+ * Intel recommends to set DFR, LDR and TPR before enabling
+ * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
+ * document number 292116).  So here it goes...
+ */
+static inline void init_apic_ldr(void)
+{
+	unsigned long val;
+	int cpu = smp_processor_id();
+
+	apic_write(APIC_DFR, APIC_DFR_VALUE);
+	val = calculate_ldr(cpu);
+	apic_write(APIC_LDR, val);
+}
+
+static inline void setup_apic_routing(void)
+{
+	printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
+		"Physflat", nr_ioapics);
+}
+
+static inline int multi_timer_check(int apic, int irq)
+{
+	return (0);
+}
+
+static inline int apicid_to_node(int logical_apicid)
+{
+	return apicid_2_node[hard_smp_processor_id()];
+}
+
+static inline int cpu_present_to_apicid(int mps_cpu)
+{
+	if (mps_cpu < NR_CPUS)
+		return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
+
+	return BAD_APICID;
+}
+
+static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
+{
+	return physid_mask_of_physid(phys_apicid);
+}
+
+extern u8 cpu_2_logical_apicid[];
+/* Mapping from cpu number to logical apicid */
+static inline int cpu_to_logical_apicid(int cpu)
+{
+	if (cpu >= NR_CPUS)
+		return BAD_APICID;
+	return cpu_physical_id(cpu);
+}
+
+static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
+{
+	/* For clustered we don't have a good way to do this yet - hack */
+	return physids_promote(0xFFL);
+}
+
+static inline void setup_portio_remap(void)
+{
+}
+
+static inline void enable_apic_mode(void)
+{
+}
+
+static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+	return (1);
+}
+
+/* As we are using single CPU as destination, pick only one CPU here */
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+	int cpu;
+	int apicid;	
+
+	cpu = first_cpu(cpumask);
+	apicid = cpu_to_logical_apicid(cpu);
+	return apicid;
+}
+
+static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
+{
+	return cpuid_apic >> index_msb;
+}
+
+#endif /* __ASM_MACH_APIC_H */
diff --git a/arch/x86/include/asm/bigsmp/apicdef.h b/arch/x86/include/asm/bigsmp/apicdef.h
new file mode 100644
index 000000000000..392c3f5ef2fe
--- /dev/null
+++ b/arch/x86/include/asm/bigsmp/apicdef.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_MACH_APICDEF_H
+#define __ASM_MACH_APICDEF_H
+
+#define		APIC_ID_MASK		(0xFF<<24)
+
+static inline unsigned get_apic_id(unsigned long x)
+{
+	return (((x)>>24)&0xFF);
+}
+
+#define		GET_APIC_ID(x)	get_apic_id(x)
+
+#endif
diff --git a/arch/x86/include/asm/bigsmp/ipi.h b/arch/x86/include/asm/bigsmp/ipi.h
new file mode 100644
index 000000000000..9404c535b7ec
--- /dev/null
+++ b/arch/x86/include/asm/bigsmp/ipi.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_MACH_IPI_H
+#define __ASM_MACH_IPI_H
+
+void send_IPI_mask_sequence(cpumask_t mask, int vector);
+
+static inline void send_IPI_mask(cpumask_t mask, int vector)
+{
+	send_IPI_mask_sequence(mask, vector);
+}
+
+static inline void send_IPI_allbutself(int vector)
+{
+	cpumask_t mask = cpu_online_map;
+	cpu_clear(smp_processor_id(), mask);
+
+	if (!cpus_empty(mask))
+		send_IPI_mask(mask, vector);
+}
+
+static inline void send_IPI_all(int vector)
+{
+	send_IPI_mask(cpu_online_map, vector);
+}
+
+#endif /* __ASM_MACH_IPI_H */
diff --git a/arch/x86/include/asm/bios_ebda.h b/arch/x86/include/asm/bios_ebda.h
new file mode 100644
index 000000000000..79b4b88505d7
--- /dev/null
+++ b/arch/x86/include/asm/bios_ebda.h
@@ -0,0 +1,36 @@
+#ifndef ASM_X86__BIOS_EBDA_H
+#define ASM_X86__BIOS_EBDA_H
+
+#include <asm/io.h>
+
+/*
+ * there is a real-mode segmented pointer pointing to the
+ * 4K EBDA area at 0x40E.
+ */
+static inline unsigned int get_bios_ebda(void)
+{
+	unsigned int address = *(unsigned short *)phys_to_virt(0x40E);
+	address <<= 4;
+	return address;	/* 0 means none */
+}
+
+void reserve_ebda_region(void);
+
+#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
+/*
+ * This is obviously not a great place for this, but we want to be
+ * able to scatter it around anywhere in the kernel.
+ */
+void check_for_bios_corruption(void);
+void start_periodic_check_for_corruption(void);
+#else
+static inline void check_for_bios_corruption(void)
+{
+}
+
+static inline void start_periodic_check_for_corruption(void)
+{
+}
+#endif
+
+#endif /* ASM_X86__BIOS_EBDA_H */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
new file mode 100644
index 000000000000..451a74762bd4
--- /dev/null
+++ b/arch/x86/include/asm/bitops.h
@@ -0,0 +1,451 @@
+#ifndef ASM_X86__BITOPS_H
+#define ASM_X86__BITOPS_H
+
+/*
+ * Copyright 1992, Linus Torvalds.
+ */
+
+#ifndef _LINUX_BITOPS_H
+#error only <linux/bitops.h> can be included directly
+#endif
+
+#include <linux/compiler.h>
+#include <asm/alternative.h>
+
+/*
+ * These have to be done with inline assembly: that way the bit-setting
+ * is guaranteed to be atomic. All bit operations return 0 if the bit
+ * was cleared before the operation and != 0 if it was not.
+ *
+ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
+ */
+
+#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1)
+/* Technically wrong, but this avoids compilation errors on some gcc
+   versions. */
+#define BITOP_ADDR(x) "=m" (*(volatile long *) (x))
+#else
+#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
+#endif
+
+#define ADDR				BITOP_ADDR(addr)
+
+/*
+ * We do the locked ops that don't return the old value as
+ * a mask operation on a byte.
+ */
+#define IS_IMMEDIATE(nr)		(__builtin_constant_p(nr))
+#define CONST_MASK_ADDR(nr, addr)	BITOP_ADDR((void *)(addr) + ((nr)>>3))
+#define CONST_MASK(nr)			(1 << ((nr) & 7))
+
+/**
+ * set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered.  See __set_bit()
+ * if you do not require the atomic guarantees.
+ *
+ * Note: there are no guarantees that this function will not be reordered
+ * on non x86 architectures, so if you are writing portable code,
+ * make sure not to rely on its reordering guarantees.
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void set_bit(unsigned int nr, volatile unsigned long *addr)
+{
+	if (IS_IMMEDIATE(nr)) {
+		asm volatile(LOCK_PREFIX "orb %1,%0"
+			: CONST_MASK_ADDR(nr, addr)
+			: "iq" ((u8)CONST_MASK(nr))
+			: "memory");
+	} else {
+		asm volatile(LOCK_PREFIX "bts %1,%0"
+			: BITOP_ADDR(addr) : "Ir" (nr) : "memory");
+	}
+}
+
+/**
+ * __set_bit - Set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * Unlike set_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __set_bit(int nr, volatile unsigned long *addr)
+{
+	asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
+}
+
+/**
+ * clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and may not be reordered.  However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * in order to ensure changes are visible on other processors.
+ */
+static inline void clear_bit(int nr, volatile unsigned long *addr)
+{
+	if (IS_IMMEDIATE(nr)) {
+		asm volatile(LOCK_PREFIX "andb %1,%0"
+			: CONST_MASK_ADDR(nr, addr)
+			: "iq" ((u8)~CONST_MASK(nr)));
+	} else {
+		asm volatile(LOCK_PREFIX "btr %1,%0"
+			: BITOP_ADDR(addr)
+			: "Ir" (nr));
+	}
+}
+
+/*
+ * clear_bit_unlock - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * clear_bit() is atomic and implies release semantics before the memory
+ * operation. It can be used for an unlock.
+ */
+static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+{
+	barrier();
+	clear_bit(nr, addr);
+}
+
+static inline void __clear_bit(int nr, volatile unsigned long *addr)
+{
+	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
+}
+
+/*
+ * __clear_bit_unlock - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * __clear_bit() is non-atomic and implies release semantics before the memory
+ * operation. It can be used for an unlock if no other CPUs can concurrently
+ * modify other bits in the word.
+ *
+ * No memory barrier is required here, because x86 cannot reorder stores past
+ * older loads. Same principle as spin_unlock.
+ */
+static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
+{
+	barrier();
+	__clear_bit(nr, addr);
+}
+
+#define smp_mb__before_clear_bit()	barrier()
+#define smp_mb__after_clear_bit()	barrier()
+
+/**
+ * __change_bit - Toggle a bit in memory
+ * @nr: the bit to change
+ * @addr: the address to start counting from
+ *
+ * Unlike change_bit(), this function is non-atomic and may be reordered.
+ * If it's called on the same region of memory simultaneously, the effect
+ * may be that only one operation succeeds.
+ */
+static inline void __change_bit(int nr, volatile unsigned long *addr)
+{
+	asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
+}
+
+/**
+ * change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * change_bit() is atomic and may not be reordered.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void change_bit(int nr, volatile unsigned long *addr)
+{
+	asm volatile(LOCK_PREFIX "btc %1,%0" : ADDR : "Ir" (nr));
+}
+
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile(LOCK_PREFIX "bts %2,%1\n\t"
+		     "sbb %0,%0" : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
+
+	return oldbit;
+}
+
+/**
+ * test_and_set_bit_lock - Set a bit and return its old value for lock
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This is the same as test_and_set_bit on x86.
+ */
+static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr)
+{
+	return test_and_set_bit(nr, addr);
+}
+
+/**
+ * __test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm("bts %2,%1\n\t"
+	    "sbb %0,%0"
+	    : "=r" (oldbit), ADDR
+	    : "Ir" (nr));
+	return oldbit;
+}
+
+/**
+ * test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile(LOCK_PREFIX "btr %2,%1\n\t"
+		     "sbb %0,%0"
+		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
+
+	return oldbit;
+}
+
+/**
+ * __test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is non-atomic and can be reordered.
+ * If two examples of this operation race, one can appear to succeed
+ * but actually fail.  You must protect multiple accesses with a lock.
+ */
+static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile("btr %2,%1\n\t"
+		     "sbb %0,%0"
+		     : "=r" (oldbit), ADDR
+		     : "Ir" (nr));
+	return oldbit;
+}
+
+/* WARNING: non atomic and it can be reordered! */
+static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile("btc %2,%1\n\t"
+		     "sbb %0,%0"
+		     : "=r" (oldbit), ADDR
+		     : "Ir" (nr) : "memory");
+
+	return oldbit;
+}
+
+/**
+ * test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile(LOCK_PREFIX "btc %2,%1\n\t"
+		     "sbb %0,%0"
+		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
+
+	return oldbit;
+}
+
+static inline int constant_test_bit(int nr, const volatile unsigned long *addr)
+{
+	return ((1UL << (nr % BITS_PER_LONG)) &
+		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
+}
+
+static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile("bt %2,%1\n\t"
+		     "sbb %0,%0"
+		     : "=r" (oldbit)
+		     : "m" (*(unsigned long *)addr), "Ir" (nr));
+
+	return oldbit;
+}
+
+#if 0 /* Fool kernel-doc since it doesn't do macros yet */
+/**
+ * test_bit - Determine whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static int test_bit(int nr, const volatile unsigned long *addr);
+#endif
+
+#define test_bit(nr, addr)			\
+	(__builtin_constant_p((nr))		\
+	 ? constant_test_bit((nr), (addr))	\
+	 : variable_test_bit((nr), (addr)))
+
+/**
+ * __ffs - find first set bit in word
+ * @word: The word to search
+ *
+ * Undefined if no bit exists, so code should check against 0 first.
+ */
+static inline unsigned long __ffs(unsigned long word)
+{
+	asm("bsf %1,%0"
+		: "=r" (word)
+		: "rm" (word));
+	return word;
+}
+
+/**
+ * ffz - find first zero bit in word
+ * @word: The word to search
+ *
+ * Undefined if no zero exists, so code should check against ~0UL first.
+ */
+static inline unsigned long ffz(unsigned long word)
+{
+	asm("bsf %1,%0"
+		: "=r" (word)
+		: "r" (~word));
+	return word;
+}
+
+/*
+ * __fls: find last set bit in word
+ * @word: The word to search
+ *
+ * Undefined if no set bit exists, so code should check against 0 first.
+ */
+static inline unsigned long __fls(unsigned long word)
+{
+	asm("bsr %1,%0"
+	    : "=r" (word)
+	    : "rm" (word));
+	return word;
+}
+
+#ifdef __KERNEL__
+/**
+ * ffs - find first set bit in word
+ * @x: the word to search
+ *
+ * This is defined the same way as the libc and compiler builtin ffs
+ * routines, therefore differs in spirit from the other bitops.
+ *
+ * ffs(value) returns 0 if value is 0 or the position of the first
+ * set bit if value is nonzero. The first (least significant) bit
+ * is at position 1.
+ */
+static inline int ffs(int x)
+{
+	int r;
+#ifdef CONFIG_X86_CMOV
+	asm("bsfl %1,%0\n\t"
+	    "cmovzl %2,%0"
+	    : "=r" (r) : "rm" (x), "r" (-1));
+#else
+	asm("bsfl %1,%0\n\t"
+	    "jnz 1f\n\t"
+	    "movl $-1,%0\n"
+	    "1:" : "=r" (r) : "rm" (x));
+#endif
+	return r + 1;
+}
+
+/**
+ * fls - find last set bit in word
+ * @x: the word to search
+ *
+ * This is defined in a similar way as the libc and compiler builtin
+ * ffs, but returns the position of the most significant set bit.
+ *
+ * fls(value) returns 0 if value is 0 or the position of the last
+ * set bit if value is nonzero. The last (most significant) bit is
+ * at position 32.
+ */
+static inline int fls(int x)
+{
+	int r;
+#ifdef CONFIG_X86_CMOV
+	asm("bsrl %1,%0\n\t"
+	    "cmovzl %2,%0"
+	    : "=&r" (r) : "rm" (x), "rm" (-1));
+#else
+	asm("bsrl %1,%0\n\t"
+	    "jnz 1f\n\t"
+	    "movl $-1,%0\n"
+	    "1:" : "=r" (r) : "rm" (x));
+#endif
+	return r + 1;
+}
+#endif /* __KERNEL__ */
+
+#undef ADDR
+
+#ifdef __KERNEL__
+
+#include <asm-generic/bitops/sched.h>
+
+#define ARCH_HAS_FAST_MULTIPLIER 1
+
+#include <asm-generic/bitops/hweight.h>
+
+#endif /* __KERNEL__ */
+
+#include <asm-generic/bitops/fls64.h>
+
+#ifdef __KERNEL__
+
+#include <asm-generic/bitops/ext2-non-atomic.h>
+
+#define ext2_set_bit_atomic(lock, nr, addr)			\
+	test_and_set_bit((nr), (unsigned long *)(addr))
+#define ext2_clear_bit_atomic(lock, nr, addr)			\
+	test_and_clear_bit((nr), (unsigned long *)(addr))
+
+#include <asm-generic/bitops/minix.h>
+
+#endif /* __KERNEL__ */
+#endif /* ASM_X86__BITOPS_H */
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
new file mode 100644
index 000000000000..1d63bd5d5946
--- /dev/null
+++ b/arch/x86/include/asm/boot.h
@@ -0,0 +1,26 @@
+#ifndef ASM_X86__BOOT_H
+#define ASM_X86__BOOT_H
+
+/* Don't touch these, unless you really know what you're doing. */
+#define DEF_SYSSEG	0x1000
+#define DEF_SYSSIZE	0x7F00
+
+/* Internal svga startup constants */
+#define NORMAL_VGA	0xffff		/* 80x25 mode */
+#define EXTENDED_VGA	0xfffe		/* 80x50 mode */
+#define ASK_VGA		0xfffd		/* ask for it at bootup */
+
+/* Physical address where kernel should be loaded. */
+#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
+				+ (CONFIG_PHYSICAL_ALIGN - 1)) \
+				& ~(CONFIG_PHYSICAL_ALIGN - 1))
+
+#ifdef CONFIG_X86_64
+#define BOOT_HEAP_SIZE	0x7000
+#define BOOT_STACK_SIZE	0x4000
+#else
+#define BOOT_HEAP_SIZE	0x4000
+#define BOOT_STACK_SIZE	0x1000
+#endif
+
+#endif /* ASM_X86__BOOT_H */
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
new file mode 100644
index 000000000000..ccf027e2d97d
--- /dev/null
+++ b/arch/x86/include/asm/bootparam.h
@@ -0,0 +1,111 @@
+#ifndef ASM_X86__BOOTPARAM_H
+#define ASM_X86__BOOTPARAM_H
+
+#include <linux/types.h>
+#include <linux/screen_info.h>
+#include <linux/apm_bios.h>
+#include <linux/edd.h>
+#include <asm/e820.h>
+#include <asm/ist.h>
+#include <video/edid.h>
+
+/* setup data types */
+#define SETUP_NONE			0
+#define SETUP_E820_EXT			1
+
+/* extensible setup data list node */
+struct setup_data {
+	__u64 next;
+	__u32 type;
+	__u32 len;
+	__u8 data[0];
+};
+
+struct setup_header {
+	__u8	setup_sects;
+	__u16	root_flags;
+	__u32	syssize;
+	__u16	ram_size;
+#define RAMDISK_IMAGE_START_MASK	0x07FF
+#define RAMDISK_PROMPT_FLAG		0x8000
+#define RAMDISK_LOAD_FLAG		0x4000
+	__u16	vid_mode;
+	__u16	root_dev;
+	__u16	boot_flag;
+	__u16	jump;
+	__u32	header;
+	__u16	version;
+	__u32	realmode_swtch;
+	__u16	start_sys;
+	__u16	kernel_version;
+	__u8	type_of_loader;
+	__u8	loadflags;
+#define LOADED_HIGH	(1<<0)
+#define QUIET_FLAG	(1<<5)
+#define KEEP_SEGMENTS	(1<<6)
+#define CAN_USE_HEAP	(1<<7)
+	__u16	setup_move_size;
+	__u32	code32_start;
+	__u32	ramdisk_image;
+	__u32	ramdisk_size;
+	__u32	bootsect_kludge;
+	__u16	heap_end_ptr;
+	__u16	_pad1;
+	__u32	cmd_line_ptr;
+	__u32	initrd_addr_max;
+	__u32	kernel_alignment;
+	__u8	relocatable_kernel;
+	__u8	_pad2[3];
+	__u32	cmdline_size;
+	__u32	hardware_subarch;
+	__u64	hardware_subarch_data;
+	__u32	payload_offset;
+	__u32	payload_length;
+	__u64	setup_data;
+} __attribute__((packed));
+
+struct sys_desc_table {
+	__u16 length;
+	__u8  table[14];
+};
+
+struct efi_info {
+	__u32 efi_loader_signature;
+	__u32 efi_systab;
+	__u32 efi_memdesc_size;
+	__u32 efi_memdesc_version;
+	__u32 efi_memmap;
+	__u32 efi_memmap_size;
+	__u32 efi_systab_hi;
+	__u32 efi_memmap_hi;
+};
+
+/* The so-called "zeropage" */
+struct boot_params {
+	struct screen_info screen_info;			/* 0x000 */
+	struct apm_bios_info apm_bios_info;		/* 0x040 */
+	__u8  _pad2[12];				/* 0x054 */
+	struct ist_info ist_info;			/* 0x060 */
+	__u8  _pad3[16];				/* 0x070 */
+	__u8  hd0_info[16];	/* obsolete! */		/* 0x080 */
+	__u8  hd1_info[16];	/* obsolete! */		/* 0x090 */
+	struct sys_desc_table sys_desc_table;		/* 0x0a0 */
+	__u8  _pad4[144];				/* 0x0b0 */
+	struct edid_info edid_info;			/* 0x140 */
+	struct efi_info efi_info;			/* 0x1c0 */
+	__u32 alt_mem_k;				/* 0x1e0 */
+	__u32 scratch;		/* Scratch field! */	/* 0x1e4 */
+	__u8  e820_entries;				/* 0x1e8 */
+	__u8  eddbuf_entries;				/* 0x1e9 */
+	__u8  edd_mbr_sig_buf_entries;			/* 0x1ea */
+	__u8  _pad6[6];					/* 0x1eb */
+	struct setup_header hdr;    /* setup header */	/* 0x1f1 */
+	__u8  _pad7[0x290-0x1f1-sizeof(struct setup_header)];
+	__u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX];	/* 0x290 */
+	struct e820entry e820_map[E820MAX];		/* 0x2d0 */
+	__u8  _pad8[48];				/* 0xcd0 */
+	struct edd_info eddbuf[EDDMAXNR];		/* 0xd00 */
+	__u8  _pad9[276];				/* 0xeec */
+} __attribute__((packed));
+
+#endif /* ASM_X86__BOOTPARAM_H */
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
new file mode 100644
index 000000000000..91ad43a54c47
--- /dev/null
+++ b/arch/x86/include/asm/bug.h
@@ -0,0 +1,39 @@
+#ifndef ASM_X86__BUG_H
+#define ASM_X86__BUG_H
+
+#ifdef CONFIG_BUG
+#define HAVE_ARCH_BUG
+
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+
+#ifdef CONFIG_X86_32
+# define __BUG_C0	"2:\t.long 1b, %c0\n"
+#else
+# define __BUG_C0	"2:\t.quad 1b, %c0\n"
+#endif
+
+#define BUG()							\
+do {								\
+	asm volatile("1:\tud2\n"				\
+		     ".pushsection __bug_table,\"a\"\n"		\
+		     __BUG_C0					\
+		     "\t.word %c1, 0\n"				\
+		     "\t.org 2b+%c2\n"				\
+		     ".popsection"				\
+		     : : "i" (__FILE__), "i" (__LINE__),	\
+		     "i" (sizeof(struct bug_entry)));		\
+	for (;;) ;						\
+} while (0)
+
+#else
+#define BUG()							\
+do {								\
+	asm volatile("ud2");					\
+	for (;;) ;						\
+} while (0)
+#endif
+
+#endif /* !CONFIG_BUG */
+
+#include <asm-generic/bug.h>
+#endif /* ASM_X86__BUG_H */
diff --git a/arch/x86/include/asm/bugs.h b/arch/x86/include/asm/bugs.h
new file mode 100644
index 000000000000..dc604985f2ad
--- /dev/null
+++ b/arch/x86/include/asm/bugs.h
@@ -0,0 +1,12 @@
+#ifndef ASM_X86__BUGS_H
+#define ASM_X86__BUGS_H
+
+extern void check_bugs(void);
+
+#if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32)
+int ppro_with_ram_bug(void);
+#else
+static inline int ppro_with_ram_bug(void) { return 0; }
+#endif
+
+#endif /* ASM_X86__BUGS_H */
diff --git a/arch/x86/include/asm/byteorder.h b/arch/x86/include/asm/byteorder.h
new file mode 100644
index 000000000000..722f27d68105
--- /dev/null
+++ b/arch/x86/include/asm/byteorder.h
@@ -0,0 +1,81 @@
+#ifndef ASM_X86__BYTEORDER_H
+#define ASM_X86__BYTEORDER_H
+
+#include <asm/types.h>
+#include <linux/compiler.h>
+
+#ifdef __GNUC__
+
+#ifdef __i386__
+
+static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
+{
+#ifdef CONFIG_X86_BSWAP
+	asm("bswap %0" : "=r" (x) : "0" (x));
+#else
+	asm("xchgb %b0,%h0\n\t"	/* swap lower bytes	*/
+	    "rorl $16,%0\n\t"	/* swap words		*/
+	    "xchgb %b0,%h0"	/* swap higher bytes	*/
+	    : "=q" (x)
+	    : "0" (x));
+#endif
+	return x;
+}
+
+static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
+{
+	union {
+		struct {
+			__u32 a;
+			__u32 b;
+		} s;
+		__u64 u;
+	} v;
+	v.u = val;
+#ifdef CONFIG_X86_BSWAP
+	asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1"
+	    : "=r" (v.s.a), "=r" (v.s.b)
+	    : "0" (v.s.a), "1" (v.s.b));
+#else
+	v.s.a = ___arch__swab32(v.s.a);
+	v.s.b = ___arch__swab32(v.s.b);
+	asm("xchgl %0,%1"
+	    : "=r" (v.s.a), "=r" (v.s.b)
+	    : "0" (v.s.a), "1" (v.s.b));
+#endif
+	return v.u;
+}
+
+#else /* __i386__ */
+
+static inline __attribute_const__ __u64 ___arch__swab64(__u64 x)
+{
+	asm("bswapq %0"
+	    : "=r" (x)
+	    : "0" (x));
+	return x;
+}
+
+static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
+{
+	asm("bswapl %0"
+	    : "=r" (x)
+	    : "0" (x));
+	return x;
+}
+
+#endif
+
+/* Do not define swab16.  Gcc is smart enough to recognize "C" version and
+   convert it into rotation or exhange.  */
+
+#define __arch__swab64(x) ___arch__swab64(x)
+#define __arch__swab32(x) ___arch__swab32(x)
+
+#define __BYTEORDER_HAS_U64__
+
+#endif /* __GNUC__ */
+
+#include <linux/byteorder/little_endian.h>
+
+#endif /* ASM_X86__BYTEORDER_H */
diff --git a/arch/x86/include/asm/cache.h b/arch/x86/include/asm/cache.h
new file mode 100644
index 000000000000..ea3f1cc06a97
--- /dev/null
+++ b/arch/x86/include/asm/cache.h
@@ -0,0 +1,20 @@
+#ifndef ASM_X86__CACHE_H
+#define ASM_X86__CACHE_H
+
+/* L1 cache line size */
+#define L1_CACHE_SHIFT	(CONFIG_X86_L1_CACHE_SHIFT)
+#define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
+
+#define __read_mostly __attribute__((__section__(".data.read_mostly")))
+
+#ifdef CONFIG_X86_VSMP
+/* vSMP Internode cacheline shift */
+#define INTERNODE_CACHE_SHIFT (12)
+#ifdef CONFIG_SMP
+#define __cacheline_aligned_in_smp					\
+	__attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT))))	\
+	__attribute__((__section__(".data.page_aligned")))
+#endif
+#endif
+
+#endif /* ASM_X86__CACHE_H */
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
new file mode 100644
index 000000000000..68840ef1b35a
--- /dev/null
+++ b/arch/x86/include/asm/cacheflush.h
@@ -0,0 +1,118 @@
+#ifndef ASM_X86__CACHEFLUSH_H
+#define ASM_X86__CACHEFLUSH_H
+
+/* Keep includes the same across arches.  */
+#include <linux/mm.h>
+
+/* Caches aren't brain-dead on the intel. */
+#define flush_cache_all()			do { } while (0)
+#define flush_cache_mm(mm)			do { } while (0)
+#define flush_cache_dup_mm(mm)			do { } while (0)
+#define flush_cache_range(vma, start, end)	do { } while (0)
+#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
+#define flush_dcache_page(page)			do { } while (0)
+#define flush_dcache_mmap_lock(mapping)		do { } while (0)
+#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
+#define flush_icache_range(start, end)		do { } while (0)
+#define flush_icache_page(vma, pg)		do { } while (0)
+#define flush_icache_user_range(vma, pg, adr, len)	do { } while (0)
+#define flush_cache_vmap(start, end)		do { } while (0)
+#define flush_cache_vunmap(start, end)		do { } while (0)
+
+#define copy_to_user_page(vma, page, vaddr, dst, src, len)	\
+	memcpy((dst), (src), (len))
+#define copy_from_user_page(vma, page, vaddr, dst, src, len)	\
+	memcpy((dst), (src), (len))
+
+#define PG_non_WB				PG_arch_1
+PAGEFLAG(NonWB, non_WB)
+
+/*
+ * The set_memory_* API can be used to change various attributes of a virtual
+ * address range. The attributes include:
+ * Cachability   : UnCached, WriteCombining, WriteBack
+ * Executability : eXeutable, NoteXecutable
+ * Read/Write    : ReadOnly, ReadWrite
+ * Presence      : NotPresent
+ *
+ * Within a catagory, the attributes are mutually exclusive.
+ *
+ * The implementation of this API will take care of various aspects that
+ * are associated with changing such attributes, such as:
+ * - Flushing TLBs
+ * - Flushing CPU caches
+ * - Making sure aliases of the memory behind the mapping don't violate
+ *   coherency rules as defined by the CPU in the system.
+ *
+ * What this API does not do:
+ * - Provide exclusion between various callers - including callers that
+ *   operation on other mappings of the same physical page
+ * - Restore default attributes when a page is freed
+ * - Guarantee that mappings other than the requested one are
+ *   in any state, other than that these do not violate rules for
+ *   the CPU you have. Do not depend on any effects on other mappings,
+ *   CPUs other than the one you have may have more relaxed rules.
+ * The caller is required to take care of these.
+ */
+
+int _set_memory_uc(unsigned long addr, int numpages);
+int _set_memory_wc(unsigned long addr, int numpages);
+int _set_memory_wb(unsigned long addr, int numpages);
+int set_memory_uc(unsigned long addr, int numpages);
+int set_memory_wc(unsigned long addr, int numpages);
+int set_memory_wb(unsigned long addr, int numpages);
+int set_memory_x(unsigned long addr, int numpages);
+int set_memory_nx(unsigned long addr, int numpages);
+int set_memory_ro(unsigned long addr, int numpages);
+int set_memory_rw(unsigned long addr, int numpages);
+int set_memory_np(unsigned long addr, int numpages);
+int set_memory_4k(unsigned long addr, int numpages);
+
+int set_memory_array_uc(unsigned long *addr, int addrinarray);
+int set_memory_array_wb(unsigned long *addr, int addrinarray);
+
+/*
+ * For legacy compatibility with the old APIs, a few functions
+ * are provided that work on a "struct page".
+ * These functions operate ONLY on the 1:1 kernel mapping of the
+ * memory that the struct page represents, and internally just
+ * call the set_memory_* function. See the description of the
+ * set_memory_* function for more details on conventions.
+ *
+ * These APIs should be considered *deprecated* and are likely going to
+ * be removed in the future.
+ * The reason for this is the implicit operation on the 1:1 mapping only,
+ * making this not a generally useful API.
+ *
+ * Specifically, many users of the old APIs had a virtual address,
+ * called virt_to_page() or vmalloc_to_page() on that address to
+ * get a struct page* that the old API required.
+ * To convert these cases, use set_memory_*() on the original
+ * virtual address, do not use these functions.
+ */
+
+int set_pages_uc(struct page *page, int numpages);
+int set_pages_wb(struct page *page, int numpages);
+int set_pages_x(struct page *page, int numpages);
+int set_pages_nx(struct page *page, int numpages);
+int set_pages_ro(struct page *page, int numpages);
+int set_pages_rw(struct page *page, int numpages);
+
+
+void clflush_cache_range(void *addr, unsigned int size);
+
+#ifdef CONFIG_DEBUG_RODATA
+void mark_rodata_ro(void);
+extern const int rodata_test_data;
+#endif
+
+#ifdef CONFIG_DEBUG_RODATA_TEST
+int rodata_test(void);
+#else
+static inline int rodata_test(void)
+{
+	return 0;
+}
+#endif
+
+#endif /* ASM_X86__CACHEFLUSH_H */
diff --git a/arch/x86/include/asm/calgary.h b/arch/x86/include/asm/calgary.h
new file mode 100644
index 000000000000..933fd272f826
--- /dev/null
+++ b/arch/x86/include/asm/calgary.h
@@ -0,0 +1,72 @@
+/*
+ * Derived from include/asm-powerpc/iommu.h
+ *
+ * Copyright IBM Corporation, 2006-2007
+ *
+ * Author: Jon Mason <jdmason@us.ibm.com>
+ * Author: Muli Ben-Yehuda <muli@il.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#ifndef ASM_X86__CALGARY_H
+#define ASM_X86__CALGARY_H
+
+#include <linux/spinlock.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/timer.h>
+#include <asm/types.h>
+
+struct iommu_table {
+	struct cal_chipset_ops *chip_ops; /* chipset specific funcs */
+	unsigned long  it_base;      /* mapped address of tce table */
+	unsigned long  it_hint;      /* Hint for next alloc */
+	unsigned long *it_map;       /* A simple allocation bitmap for now */
+	void __iomem  *bbar;         /* Bridge BAR */
+	u64	       tar_val;      /* Table Address Register */
+	struct timer_list watchdog_timer;
+	spinlock_t     it_lock;      /* Protects it_map */
+	unsigned int   it_size;      /* Size of iommu table in entries */
+	unsigned char  it_busno;     /* Bus number this table belongs to */
+};
+
+struct cal_chipset_ops {
+	void (*handle_quirks)(struct iommu_table *tbl, struct pci_dev *dev);
+	void (*tce_cache_blast)(struct iommu_table *tbl);
+	void (*dump_error_regs)(struct iommu_table *tbl);
+};
+
+#define TCE_TABLE_SIZE_UNSPECIFIED	~0
+#define TCE_TABLE_SIZE_64K		0
+#define TCE_TABLE_SIZE_128K		1
+#define TCE_TABLE_SIZE_256K		2
+#define TCE_TABLE_SIZE_512K		3
+#define TCE_TABLE_SIZE_1M		4
+#define TCE_TABLE_SIZE_2M		5
+#define TCE_TABLE_SIZE_4M		6
+#define TCE_TABLE_SIZE_8M		7
+
+extern int use_calgary;
+
+#ifdef CONFIG_CALGARY_IOMMU
+extern int calgary_iommu_init(void);
+extern void detect_calgary(void);
+#else
+static inline int calgary_iommu_init(void) { return 1; }
+static inline void detect_calgary(void) { return; }
+#endif
+
+#endif /* ASM_X86__CALGARY_H */
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
new file mode 100644
index 000000000000..2bc162e0ec6e
--- /dev/null
+++ b/arch/x86/include/asm/calling.h
@@ -0,0 +1,170 @@
+/*
+ * Some macros to handle stack frames in assembly.
+ */
+
+#define R15		  0
+#define R14		  8
+#define R13		 16
+#define R12		 24
+#define RBP		 32
+#define RBX		 40
+
+/* arguments: interrupts/non tracing syscalls only save upto here*/
+#define R11		 48
+#define R10		 56
+#define R9		 64
+#define R8		 72
+#define RAX		 80
+#define RCX		 88
+#define RDX		 96
+#define RSI		104
+#define RDI		112
+#define ORIG_RAX	120       /* + error_code */
+/* end of arguments */
+
+/* cpu exception frame or undefined in case of fast syscall. */
+#define RIP		128
+#define CS		136
+#define EFLAGS		144
+#define RSP		152
+#define SS		160
+
+#define ARGOFFSET	R11
+#define SWFRAME		ORIG_RAX
+
+	.macro SAVE_ARGS addskip=0, norcx=0, nor891011=0
+	subq  $9*8+\addskip, %rsp
+	CFI_ADJUST_CFA_OFFSET	9*8+\addskip
+	movq  %rdi, 8*8(%rsp)
+	CFI_REL_OFFSET	rdi, 8*8
+	movq  %rsi, 7*8(%rsp)
+	CFI_REL_OFFSET	rsi, 7*8
+	movq  %rdx, 6*8(%rsp)
+	CFI_REL_OFFSET	rdx, 6*8
+	.if \norcx
+	.else
+	movq  %rcx, 5*8(%rsp)
+	CFI_REL_OFFSET	rcx, 5*8
+	.endif
+	movq  %rax, 4*8(%rsp)
+	CFI_REL_OFFSET	rax, 4*8
+	.if \nor891011
+	.else
+	movq  %r8, 3*8(%rsp)
+	CFI_REL_OFFSET	r8,  3*8
+	movq  %r9, 2*8(%rsp)
+	CFI_REL_OFFSET	r9,  2*8
+	movq  %r10, 1*8(%rsp)
+	CFI_REL_OFFSET	r10, 1*8
+	movq  %r11, (%rsp)
+	CFI_REL_OFFSET	r11, 0*8
+	.endif
+	.endm
+
+#define ARG_SKIP	9*8
+
+	.macro RESTORE_ARGS skiprax=0, addskip=0, skiprcx=0, skipr11=0, \
+			    skipr8910=0, skiprdx=0
+	.if \skipr11
+	.else
+	movq (%rsp), %r11
+	CFI_RESTORE r11
+	.endif
+	.if \skipr8910
+	.else
+	movq 1*8(%rsp), %r10
+	CFI_RESTORE r10
+	movq 2*8(%rsp), %r9
+	CFI_RESTORE r9
+	movq 3*8(%rsp), %r8
+	CFI_RESTORE r8
+	.endif
+	.if \skiprax
+	.else
+	movq 4*8(%rsp), %rax
+	CFI_RESTORE rax
+	.endif
+	.if \skiprcx
+	.else
+	movq 5*8(%rsp), %rcx
+	CFI_RESTORE rcx
+	.endif
+	.if \skiprdx
+	.else
+	movq 6*8(%rsp), %rdx
+	CFI_RESTORE rdx
+	.endif
+	movq 7*8(%rsp), %rsi
+	CFI_RESTORE rsi
+	movq 8*8(%rsp), %rdi
+	CFI_RESTORE rdi
+	.if ARG_SKIP+\addskip > 0
+	addq $ARG_SKIP+\addskip, %rsp
+	CFI_ADJUST_CFA_OFFSET	-(ARG_SKIP+\addskip)
+	.endif
+	.endm
+
+	.macro LOAD_ARGS offset, skiprax=0
+	movq \offset(%rsp),    %r11
+	movq \offset+8(%rsp),  %r10
+	movq \offset+16(%rsp), %r9
+	movq \offset+24(%rsp), %r8
+	movq \offset+40(%rsp), %rcx
+	movq \offset+48(%rsp), %rdx
+	movq \offset+56(%rsp), %rsi
+	movq \offset+64(%rsp), %rdi
+	.if \skiprax
+	.else
+	movq \offset+72(%rsp), %rax
+	.endif
+	.endm
+
+#define REST_SKIP	6*8
+
+	.macro SAVE_REST
+	subq $REST_SKIP, %rsp
+	CFI_ADJUST_CFA_OFFSET	REST_SKIP
+	movq %rbx, 5*8(%rsp)
+	CFI_REL_OFFSET	rbx, 5*8
+	movq %rbp, 4*8(%rsp)
+	CFI_REL_OFFSET	rbp, 4*8
+	movq %r12, 3*8(%rsp)
+	CFI_REL_OFFSET	r12, 3*8
+	movq %r13, 2*8(%rsp)
+	CFI_REL_OFFSET	r13, 2*8
+	movq %r14, 1*8(%rsp)
+	CFI_REL_OFFSET	r14, 1*8
+	movq %r15, (%rsp)
+	CFI_REL_OFFSET	r15, 0*8
+	.endm
+
+	.macro RESTORE_REST
+	movq (%rsp),     %r15
+	CFI_RESTORE r15
+	movq 1*8(%rsp),  %r14
+	CFI_RESTORE r14
+	movq 2*8(%rsp),  %r13
+	CFI_RESTORE r13
+	movq 3*8(%rsp),  %r12
+	CFI_RESTORE r12
+	movq 4*8(%rsp),  %rbp
+	CFI_RESTORE rbp
+	movq 5*8(%rsp),  %rbx
+	CFI_RESTORE rbx
+	addq $REST_SKIP, %rsp
+	CFI_ADJUST_CFA_OFFSET	-(REST_SKIP)
+	.endm
+
+	.macro SAVE_ALL
+	SAVE_ARGS
+	SAVE_REST
+	.endm
+
+	.macro RESTORE_ALL addskip=0
+	RESTORE_REST
+	RESTORE_ARGS 0, \addskip
+	.endm
+
+	.macro icebp
+	.byte 0xf1
+	.endm
diff --git a/arch/x86/include/asm/checksum.h b/arch/x86/include/asm/checksum.h
new file mode 100644
index 000000000000..848850fd7d62
--- /dev/null
+++ b/arch/x86/include/asm/checksum.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "checksum_32.h"
+#else
+# include "checksum_64.h"
+#endif
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
new file mode 100644
index 000000000000..d041e8cda227
--- /dev/null
+++ b/arch/x86/include/asm/checksum_32.h
@@ -0,0 +1,189 @@
+#ifndef ASM_X86__CHECKSUM_32_H
+#define ASM_X86__CHECKSUM_32_H
+
+#include <linux/in6.h>
+
+#include <asm/uaccess.h>
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+asmlinkage __wsum csum_partial(const void *buff, int len, __wsum sum);
+
+/*
+ * the same as csum_partial, but copies from src while it
+ * checksums, and handles user-space pointer exceptions correctly, when needed.
+ *
+ * here even more important to align src and dst on a 32-bit (or even
+ * better 64-bit) boundary
+ */
+
+asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
+					    int len, __wsum sum,
+					    int *src_err_ptr, int *dst_err_ptr);
+
+/*
+ *	Note: when you get a NULL pointer exception here this means someone
+ *	passed in an incorrect kernel address to one of these functions.
+ *
+ *	If you use these functions directly please don't forget the
+ *	access_ok().
+ */
+static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst,
+					       int len, __wsum sum)
+{
+	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
+}
+
+static inline __wsum csum_partial_copy_from_user(const void __user *src,
+						 void *dst,
+						 int len, __wsum sum,
+						 int *err_ptr)
+{
+	might_sleep();
+	return csum_partial_copy_generic((__force void *)src, dst,
+					 len, sum, err_ptr, NULL);
+}
+
+/*
+ *	This is a version of ip_compute_csum() optimized for IP headers,
+ *	which always checksum on 4 octet boundaries.
+ *
+ *	By Jorge Cwik <jorge@laser.satlink.net>, adapted for linux by
+ *	Arnt Gulbrandsen.
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	unsigned int sum;
+
+	asm volatile("movl (%1), %0	;\n"
+		     "subl $4, %2	;\n"
+		     "jbe 2f		;\n"
+		     "addl 4(%1), %0	;\n"
+		     "adcl 8(%1), %0	;\n"
+		     "adcl 12(%1), %0;\n"
+		     "1:	adcl 16(%1), %0	;\n"
+		     "lea 4(%1), %1	;\n"
+		     "decl %2	;\n"
+		     "jne 1b		;\n"
+		     "adcl $0, %0	;\n"
+		     "movl %0, %2	;\n"
+		     "shrl $16, %0	;\n"
+		     "addw %w2, %w0	;\n"
+		     "adcl $0, %0	;\n"
+		     "notl %0	;\n"
+		     "2:		;\n"
+	/* Since the input registers which are loaded with iph and ihl
+	   are modified, we must also specify them as outputs, or gcc
+	   will assume they contain their original values. */
+		     : "=r" (sum), "=r" (iph), "=r" (ihl)
+		     : "1" (iph), "2" (ihl)
+		     : "memory");
+	return (__force __sum16)sum;
+}
+
+/*
+ *	Fold a partial checksum
+ */
+
+static inline __sum16 csum_fold(__wsum sum)
+{
+	asm("addl %1, %0		;\n"
+	    "adcl $0xffff, %0	;\n"
+	    : "=r" (sum)
+	    : "r" ((__force u32)sum << 16),
+	      "0" ((__force u32)sum & 0xffff0000));
+	return (__force __sum16)(~(__force u32)sum >> 16);
+}
+
+static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+					unsigned short len,
+					unsigned short proto,
+					__wsum sum)
+{
+	asm("addl %1, %0	;\n"
+	    "adcl %2, %0	;\n"
+	    "adcl %3, %0	;\n"
+	    "adcl $0, %0	;\n"
+	    : "=r" (sum)
+	    : "g" (daddr), "g"(saddr),
+	      "g" ((len + proto) << 8), "0" (sum));
+	return sum;
+}
+
+/*
+ * computes the checksum of the TCP/UDP pseudo-header
+ * returns a 16-bit checksum, already complemented
+ */
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+					unsigned short len,
+					unsigned short proto,
+					__wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+
+static inline __sum16 ip_compute_csum(const void *buff, int len)
+{
+    return csum_fold(csum_partial(buff, len, 0));
+}
+
+#define _HAVE_ARCH_IPV6_CSUM
+static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
+				      const struct in6_addr *daddr,
+				      __u32 len, unsigned short proto,
+				      __wsum sum)
+{
+	asm("addl 0(%1), %0	;\n"
+	    "adcl 4(%1), %0	;\n"
+	    "adcl 8(%1), %0	;\n"
+	    "adcl 12(%1), %0	;\n"
+	    "adcl 0(%2), %0	;\n"
+	    "adcl 4(%2), %0	;\n"
+	    "adcl 8(%2), %0	;\n"
+	    "adcl 12(%2), %0	;\n"
+	    "adcl %3, %0	;\n"
+	    "adcl %4, %0	;\n"
+	    "adcl $0, %0	;\n"
+	    : "=&r" (sum)
+	    : "r" (saddr), "r" (daddr),
+	      "r" (htonl(len)), "r" (htonl(proto)), "0" (sum));
+
+	return csum_fold(sum);
+}
+
+/*
+ *	Copy and checksum to user
+ */
+#define HAVE_CSUM_COPY_USER
+static inline __wsum csum_and_copy_to_user(const void *src,
+					   void __user *dst,
+					   int len, __wsum sum,
+					   int *err_ptr)
+{
+	might_sleep();
+	if (access_ok(VERIFY_WRITE, dst, len))
+		return csum_partial_copy_generic(src, (__force void *)dst,
+						 len, sum, NULL, err_ptr);
+
+	if (len)
+		*err_ptr = -EFAULT;
+
+	return (__force __wsum)-1; /* invalid checksum */
+}
+
+#endif /* ASM_X86__CHECKSUM_32_H */
diff --git a/arch/x86/include/asm/checksum_64.h b/arch/x86/include/asm/checksum_64.h
new file mode 100644
index 000000000000..110f403beb89
--- /dev/null
+++ b/arch/x86/include/asm/checksum_64.h
@@ -0,0 +1,191 @@
+#ifndef ASM_X86__CHECKSUM_64_H
+#define ASM_X86__CHECKSUM_64_H
+
+/*
+ * Checksums for x86-64
+ * Copyright 2002 by Andi Kleen, SuSE Labs
+ * with some code from asm-x86/checksum.h
+ */
+
+#include <linux/compiler.h>
+#include <asm/uaccess.h>
+#include <asm/byteorder.h>
+
+/**
+ * csum_fold - Fold and invert a 32bit checksum.
+ * sum: 32bit unfolded sum
+ *
+ * Fold a 32bit running checksum to 16bit and invert it. This is usually
+ * the last step before putting a checksum into a packet.
+ * Make sure not to mix with 64bit checksums.
+ */
+static inline __sum16 csum_fold(__wsum sum)
+{
+	asm("  addl %1,%0\n"
+	    "  adcl $0xffff,%0"
+	    : "=r" (sum)
+	    : "r" ((__force u32)sum << 16),
+	      "0" ((__force u32)sum & 0xffff0000));
+	return (__force __sum16)(~(__force u32)sum >> 16);
+}
+
+/*
+ *	This is a version of ip_compute_csum() optimized for IP headers,
+ *	which always checksum on 4 octet boundaries.
+ *
+ *	By Jorge Cwik <jorge@laser.satlink.net>, adapted for linux by
+ *	Arnt Gulbrandsen.
+ */
+
+/**
+ * ip_fast_csum - Compute the IPv4 header checksum efficiently.
+ * iph: ipv4 header
+ * ihl: length of header / 4
+ */
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+	unsigned int sum;
+
+	asm("  movl (%1), %0\n"
+	    "  subl $4, %2\n"
+	    "  jbe 2f\n"
+	    "  addl 4(%1), %0\n"
+	    "  adcl 8(%1), %0\n"
+	    "  adcl 12(%1), %0\n"
+	    "1: adcl 16(%1), %0\n"
+	    "  lea 4(%1), %1\n"
+	    "  decl %2\n"
+	    "  jne	1b\n"
+	    "  adcl $0, %0\n"
+	    "  movl %0, %2\n"
+	    "  shrl $16, %0\n"
+	    "  addw %w2, %w0\n"
+	    "  adcl $0, %0\n"
+	    "  notl %0\n"
+	    "2:"
+	/* Since the input registers which are loaded with iph and ihl
+	   are modified, we must also specify them as outputs, or gcc
+	   will assume they contain their original values. */
+	    : "=r" (sum), "=r" (iph), "=r" (ihl)
+	    : "1" (iph), "2" (ihl)
+	    : "memory");
+	return (__force __sum16)sum;
+}
+
+/**
+ * csum_tcpup_nofold - Compute an IPv4 pseudo header checksum.
+ * @saddr: source address
+ * @daddr: destination address
+ * @len: length of packet
+ * @proto: ip protocol of packet
+ * @sum: initial sum to be added in (32bit unfolded)
+ *
+ * Returns the pseudo header checksum the input data. Result is
+ * 32bit unfolded.
+ */
+static inline __wsum
+csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
+		   unsigned short proto, __wsum sum)
+{
+	asm("  addl %1, %0\n"
+	    "  adcl %2, %0\n"
+	    "  adcl %3, %0\n"
+	    "  adcl $0, %0\n"
+	    : "=r" (sum)
+	    : "g" (daddr), "g" (saddr),
+	      "g" ((len + proto)<<8), "0" (sum));
+	return sum;
+}
+
+
+/**
+ * csum_tcpup_magic - Compute an IPv4 pseudo header checksum.
+ * @saddr: source address
+ * @daddr: destination address
+ * @len: length of packet
+ * @proto: ip protocol of packet
+ * @sum: initial sum to be added in (32bit unfolded)
+ *
+ * Returns the 16bit pseudo header checksum the input data already
+ * complemented and ready to be filled in.
+ */
+static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
+					unsigned short len,
+					unsigned short proto, __wsum sum)
+{
+	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
+}
+
+/**
+ * csum_partial - Compute an internet checksum.
+ * @buff: buffer to be checksummed
+ * @len: length of buffer.
+ * @sum: initial sum to be added in (32bit unfolded)
+ *
+ * Returns the 32bit unfolded internet checksum of the buffer.
+ * Before filling it in it needs to be csum_fold()'ed.
+ * buff should be aligned to a 64bit boundary if possible.
+ */
+extern __wsum csum_partial(const void *buff, int len, __wsum sum);
+
+#define  _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1
+#define HAVE_CSUM_COPY_USER 1
+
+
+/* Do not call this directly. Use the wrappers below */
+extern __wsum csum_partial_copy_generic(const void *src, const void *dst,
+					int len, __wsum sum,
+					int *src_err_ptr, int *dst_err_ptr);
+
+
+extern __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
+					  int len, __wsum isum, int *errp);
+extern __wsum csum_partial_copy_to_user(const void *src, void __user *dst,
+					int len, __wsum isum, int *errp);
+extern __wsum csum_partial_copy_nocheck(const void *src, void *dst,
+					int len, __wsum sum);
+
+/* Old names. To be removed. */
+#define csum_and_copy_to_user csum_partial_copy_to_user
+#define csum_and_copy_from_user csum_partial_copy_from_user
+
+/**
+ * ip_compute_csum - Compute an 16bit IP checksum.
+ * @buff: buffer address.
+ * @len: length of buffer.
+ *
+ * Returns the 16bit folded/inverted checksum of the passed buffer.
+ * Ready to fill in.
+ */
+extern __sum16 ip_compute_csum(const void *buff, int len);
+
+/**
+ * csum_ipv6_magic - Compute checksum of an IPv6 pseudo header.
+ * @saddr: source address
+ * @daddr: destination address
+ * @len: length of packet
+ * @proto: protocol of packet
+ * @sum: initial sum (32bit unfolded) to be added in
+ *
+ * Computes an IPv6 pseudo header checksum. This sum is added the checksum
+ * into UDP/TCP packets and contains some link layer information.
+ * Returns the unfolded 32bit checksum.
+ */
+
+struct in6_addr;
+
+#define _HAVE_ARCH_IPV6_CSUM 1
+extern __sum16
+csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr,
+		__u32 len, unsigned short proto, __wsum sum);
+
+static inline unsigned add32_with_carry(unsigned a, unsigned b)
+{
+	asm("addl %2,%0\n\t"
+	    "adcl $0,%0"
+	    : "=r" (a)
+	    : "0" (a), "r" (b));
+	return a;
+}
+
+#endif /* ASM_X86__CHECKSUM_64_H */
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
new file mode 100644
index 000000000000..a460fa088d4c
--- /dev/null
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "cmpxchg_32.h"
+#else
+# include "cmpxchg_64.h"
+#endif
diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
new file mode 100644
index 000000000000..0622e45cdf7c
--- /dev/null
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -0,0 +1,344 @@
+#ifndef ASM_X86__CMPXCHG_32_H
+#define ASM_X86__CMPXCHG_32_H
+
+#include <linux/bitops.h> /* for LOCK_PREFIX */
+
+/*
+ * Note: if you use set64_bit(), __cmpxchg64(), or their variants, you
+ *       you need to test for the feature in boot_cpu_data.
+ */
+
+#define xchg(ptr, v)							\
+	((__typeof__(*(ptr)))__xchg((unsigned long)(v), (ptr), sizeof(*(ptr))))
+
+struct __xchg_dummy {
+	unsigned long a[100];
+};
+#define __xg(x) ((struct __xchg_dummy *)(x))
+
+/*
+ * The semantics of XCHGCMP8B are a bit strange, this is why
+ * there is a loop and the loading of %%eax and %%edx has to
+ * be inside. This inlines well in most cases, the cached
+ * cost is around ~38 cycles. (in the future we might want
+ * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
+ * might have an implicit FPU-save as a cost, so it's not
+ * clear which path to go.)
+ *
+ * cmpxchg8b must be used with the lock prefix here to allow
+ * the instruction to be executed atomically, see page 3-102
+ * of the instruction set reference 24319102.pdf. We need
+ * the reader side to see the coherent 64bit value.
+ */
+static inline void __set_64bit(unsigned long long *ptr,
+			       unsigned int low, unsigned int high)
+{
+	asm volatile("\n1:\t"
+		     "movl (%0), %%eax\n\t"
+		     "movl 4(%0), %%edx\n\t"
+		     LOCK_PREFIX "cmpxchg8b (%0)\n\t"
+		     "jnz 1b"
+		     : /* no outputs */
+		     : "D"(ptr),
+		       "b"(low),
+		       "c"(high)
+		     : "ax", "dx", "memory");
+}
+
+static inline void __set_64bit_constant(unsigned long long *ptr,
+					unsigned long long value)
+{
+	__set_64bit(ptr, (unsigned int)value, (unsigned int)(value >> 32));
+}
+
+#define ll_low(x)	*(((unsigned int *)&(x)) + 0)
+#define ll_high(x)	*(((unsigned int *)&(x)) + 1)
+
+static inline void __set_64bit_var(unsigned long long *ptr,
+				   unsigned long long value)
+{
+	__set_64bit(ptr, ll_low(value), ll_high(value));
+}
+
+#define set_64bit(ptr, value)			\
+	(__builtin_constant_p((value))		\
+	 ? __set_64bit_constant((ptr), (value))	\
+	 : __set_64bit_var((ptr), (value)))
+
+#define _set_64bit(ptr, value)						\
+	(__builtin_constant_p(value)					\
+	 ? __set_64bit(ptr, (unsigned int)(value),			\
+		       (unsigned int)((value) >> 32))			\
+	 : __set_64bit(ptr, ll_low((value)), ll_high((value))))
+
+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
+ * Note 2: xchg has side effect, so that attribute volatile is necessary,
+ *	  but generally the primitive is invalid, *ptr is output argument. --ANK
+ */
+static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
+				   int size)
+{
+	switch (size) {
+	case 1:
+		asm volatile("xchgb %b0,%1"
+			     : "=q" (x)
+			     : "m" (*__xg(ptr)), "0" (x)
+			     : "memory");
+		break;
+	case 2:
+		asm volatile("xchgw %w0,%1"
+			     : "=r" (x)
+			     : "m" (*__xg(ptr)), "0" (x)
+			     : "memory");
+		break;
+	case 4:
+		asm volatile("xchgl %0,%1"
+			     : "=r" (x)
+			     : "m" (*__xg(ptr)), "0" (x)
+			     : "memory");
+		break;
+	}
+	return x;
+}
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#ifdef CONFIG_X86_CMPXCHG
+#define __HAVE_ARCH_CMPXCHG 1
+#define cmpxchg(ptr, o, n)						\
+	((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),	\
+				       (unsigned long)(n),		\
+				       sizeof(*(ptr))))
+#define sync_cmpxchg(ptr, o, n)						\
+	((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o),	\
+					    (unsigned long)(n),		\
+					    sizeof(*(ptr))))
+#define cmpxchg_local(ptr, o, n)					\
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
+					     (unsigned long)(n),	\
+					     sizeof(*(ptr))))
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+#define cmpxchg64(ptr, o, n)						\
+	((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
+					 (unsigned long long)(n)))
+#define cmpxchg64_local(ptr, o, n)					\
+	((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \
+					       (unsigned long long)(n)))
+#endif
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+				      unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		asm volatile(LOCK_PREFIX "cmpxchgb %b1,%2"
+			     : "=a"(prev)
+			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 2:
+		asm volatile(LOCK_PREFIX "cmpxchgw %w1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 4:
+		asm volatile(LOCK_PREFIX "cmpxchgl %1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	}
+	return old;
+}
+
+/*
+ * Always use locked operations when touching memory shared with a
+ * hypervisor, since the system may be SMP even if the guest kernel
+ * isn't.
+ */
+static inline unsigned long __sync_cmpxchg(volatile void *ptr,
+					   unsigned long old,
+					   unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		asm volatile("lock; cmpxchgb %b1,%2"
+			     : "=a"(prev)
+			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 2:
+		asm volatile("lock; cmpxchgw %w1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 4:
+		asm volatile("lock; cmpxchgl %1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	}
+	return old;
+}
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+					    unsigned long old,
+					    unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		asm volatile("cmpxchgb %b1,%2"
+			     : "=a"(prev)
+			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 2:
+		asm volatile("cmpxchgw %w1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 4:
+		asm volatile("cmpxchgl %1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	}
+	return old;
+}
+
+static inline unsigned long long __cmpxchg64(volatile void *ptr,
+					     unsigned long long old,
+					     unsigned long long new)
+{
+	unsigned long long prev;
+	asm volatile(LOCK_PREFIX "cmpxchg8b %3"
+		     : "=A"(prev)
+		     : "b"((unsigned long)new),
+		       "c"((unsigned long)(new >> 32)),
+		       "m"(*__xg(ptr)),
+		       "0"(old)
+		     : "memory");
+	return prev;
+}
+
+static inline unsigned long long __cmpxchg64_local(volatile void *ptr,
+						   unsigned long long old,
+						   unsigned long long new)
+{
+	unsigned long long prev;
+	asm volatile("cmpxchg8b %3"
+		     : "=A"(prev)
+		     : "b"((unsigned long)new),
+		       "c"((unsigned long)(new >> 32)),
+		       "m"(*__xg(ptr)),
+		       "0"(old)
+		     : "memory");
+	return prev;
+}
+
+#ifndef CONFIG_X86_CMPXCHG
+/*
+ * Building a kernel capable running on 80386. It may be necessary to
+ * simulate the cmpxchg on the 80386 CPU. For that purpose we define
+ * a function for each of the sizes we support.
+ */
+
+extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
+extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
+extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
+
+static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
+					unsigned long new, int size)
+{
+	switch (size) {
+	case 1:
+		return cmpxchg_386_u8(ptr, old, new);
+	case 2:
+		return cmpxchg_386_u16(ptr, old, new);
+	case 4:
+		return cmpxchg_386_u32(ptr, old, new);
+	}
+	return old;
+}
+
+#define cmpxchg(ptr, o, n)						\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	if (likely(boot_cpu_data.x86 > 3))				\
+		__ret = (__typeof__(*(ptr)))__cmpxchg((ptr),		\
+				(unsigned long)(o), (unsigned long)(n),	\
+				sizeof(*(ptr)));			\
+	else								\
+		__ret = (__typeof__(*(ptr)))cmpxchg_386((ptr),		\
+				(unsigned long)(o), (unsigned long)(n),	\
+				sizeof(*(ptr)));			\
+	__ret;								\
+})
+#define cmpxchg_local(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	if (likely(boot_cpu_data.x86 > 3))				\
+		__ret = (__typeof__(*(ptr)))__cmpxchg_local((ptr),	\
+				(unsigned long)(o), (unsigned long)(n),	\
+				sizeof(*(ptr)));			\
+	else								\
+		__ret = (__typeof__(*(ptr)))cmpxchg_386((ptr),		\
+				(unsigned long)(o), (unsigned long)(n),	\
+				sizeof(*(ptr)));			\
+	__ret;								\
+})
+#endif
+
+#ifndef CONFIG_X86_CMPXCHG64
+/*
+ * Building a kernel capable running on 80386 and 80486. It may be necessary
+ * to simulate the cmpxchg8b on the 80386 and 80486 CPU.
+ */
+
+extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64);
+
+#define cmpxchg64(ptr, o, n)						\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	if (likely(boot_cpu_data.x86 > 4))				\
+		__ret = (__typeof__(*(ptr)))__cmpxchg64((ptr),		\
+				(unsigned long long)(o),		\
+				(unsigned long long)(n));		\
+	else								\
+		__ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr),	\
+				(unsigned long long)(o),		\
+				(unsigned long long)(n));		\
+	__ret;								\
+})
+#define cmpxchg64_local(ptr, o, n)					\
+({									\
+	__typeof__(*(ptr)) __ret;					\
+	if (likely(boot_cpu_data.x86 > 4))				\
+		__ret = (__typeof__(*(ptr)))__cmpxchg64_local((ptr),	\
+				(unsigned long long)(o),		\
+				(unsigned long long)(n));		\
+	else								\
+		__ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr),	\
+				(unsigned long long)(o),		\
+				(unsigned long long)(n));		\
+	__ret;								\
+})
+
+#endif
+
+#endif /* ASM_X86__CMPXCHG_32_H */
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
new file mode 100644
index 000000000000..63c1a5e61b99
--- /dev/null
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -0,0 +1,185 @@
+#ifndef ASM_X86__CMPXCHG_64_H
+#define ASM_X86__CMPXCHG_64_H
+
+#include <asm/alternative.h> /* Provides LOCK_PREFIX */
+
+#define xchg(ptr, v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v), \
+						 (ptr), sizeof(*(ptr))))
+
+#define __xg(x) ((volatile long *)(x))
+
+static inline void set_64bit(volatile unsigned long *ptr, unsigned long val)
+{
+	*ptr = val;
+}
+
+#define _set_64bit set_64bit
+
+/*
+ * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
+ * Note 2: xchg has side effect, so that attribute volatile is necessary,
+ *	  but generally the primitive is invalid, *ptr is output argument. --ANK
+ */
+static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
+				   int size)
+{
+	switch (size) {
+	case 1:
+		asm volatile("xchgb %b0,%1"
+			     : "=q" (x)
+			     : "m" (*__xg(ptr)), "0" (x)
+			     : "memory");
+		break;
+	case 2:
+		asm volatile("xchgw %w0,%1"
+			     : "=r" (x)
+			     : "m" (*__xg(ptr)), "0" (x)
+			     : "memory");
+		break;
+	case 4:
+		asm volatile("xchgl %k0,%1"
+			     : "=r" (x)
+			     : "m" (*__xg(ptr)), "0" (x)
+			     : "memory");
+		break;
+	case 8:
+		asm volatile("xchgq %0,%1"
+			     : "=r" (x)
+			     : "m" (*__xg(ptr)), "0" (x)
+			     : "memory");
+		break;
+	}
+	return x;
+}
+
+/*
+ * Atomic compare and exchange.  Compare OLD with MEM, if identical,
+ * store NEW in MEM.  Return the initial value in MEM.  Success is
+ * indicated by comparing RETURN with OLD.
+ */
+
+#define __HAVE_ARCH_CMPXCHG 1
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+				      unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		asm volatile(LOCK_PREFIX "cmpxchgb %b1,%2"
+			     : "=a"(prev)
+			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 2:
+		asm volatile(LOCK_PREFIX "cmpxchgw %w1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 4:
+		asm volatile(LOCK_PREFIX "cmpxchgl %k1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 8:
+		asm volatile(LOCK_PREFIX "cmpxchgq %1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	}
+	return old;
+}
+
+/*
+ * Always use locked operations when touching memory shared with a
+ * hypervisor, since the system may be SMP even if the guest kernel
+ * isn't.
+ */
+static inline unsigned long __sync_cmpxchg(volatile void *ptr,
+					   unsigned long old,
+					   unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		asm volatile("lock; cmpxchgb %b1,%2"
+			     : "=a"(prev)
+			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 2:
+		asm volatile("lock; cmpxchgw %w1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 4:
+		asm volatile("lock; cmpxchgl %1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	}
+	return old;
+}
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+					    unsigned long old,
+					    unsigned long new, int size)
+{
+	unsigned long prev;
+	switch (size) {
+	case 1:
+		asm volatile("cmpxchgb %b1,%2"
+			     : "=a"(prev)
+			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 2:
+		asm volatile("cmpxchgw %w1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 4:
+		asm volatile("cmpxchgl %k1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	case 8:
+		asm volatile("cmpxchgq %1,%2"
+			     : "=a"(prev)
+			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
+			     : "memory");
+		return prev;
+	}
+	return old;
+}
+
+#define cmpxchg(ptr, o, n)						\
+	((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),	\
+				       (unsigned long)(n), sizeof(*(ptr))))
+#define cmpxchg64(ptr, o, n)						\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg((ptr), (o), (n));					\
+})
+#define cmpxchg_local(ptr, o, n)					\
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
+					     (unsigned long)(n),	\
+					     sizeof(*(ptr))))
+#define sync_cmpxchg(ptr, o, n)						\
+	((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o),	\
+					    (unsigned long)(n),		\
+					    sizeof(*(ptr))))
+#define cmpxchg64_local(ptr, o, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	cmpxchg_local((ptr), (o), (n));					\
+})
+
+#endif /* ASM_X86__CMPXCHG_64_H */
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
new file mode 100644
index 000000000000..6732b150949e
--- /dev/null
+++ b/arch/x86/include/asm/compat.h
@@ -0,0 +1,218 @@
+#ifndef ASM_X86__COMPAT_H
+#define ASM_X86__COMPAT_H
+
+/*
+ * Architecture specific compatibility types
+ */
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <asm/user32.h>
+
+#define COMPAT_USER_HZ	100
+
+typedef u32		compat_size_t;
+typedef s32		compat_ssize_t;
+typedef s32		compat_time_t;
+typedef s32		compat_clock_t;
+typedef s32		compat_pid_t;
+typedef u16		__compat_uid_t;
+typedef u16		__compat_gid_t;
+typedef u32		__compat_uid32_t;
+typedef u32		__compat_gid32_t;
+typedef u16		compat_mode_t;
+typedef u32		compat_ino_t;
+typedef u16		compat_dev_t;
+typedef s32		compat_off_t;
+typedef s64		compat_loff_t;
+typedef u16		compat_nlink_t;
+typedef u16		compat_ipc_pid_t;
+typedef s32		compat_daddr_t;
+typedef u32		compat_caddr_t;
+typedef __kernel_fsid_t	compat_fsid_t;
+typedef s32		compat_timer_t;
+typedef s32		compat_key_t;
+
+typedef s32		compat_int_t;
+typedef s32		compat_long_t;
+typedef s64 __attribute__((aligned(4))) compat_s64;
+typedef u32		compat_uint_t;
+typedef u32		compat_ulong_t;
+typedef u64 __attribute__((aligned(4))) compat_u64;
+
+struct compat_timespec {
+	compat_time_t	tv_sec;
+	s32		tv_nsec;
+};
+
+struct compat_timeval {
+	compat_time_t	tv_sec;
+	s32		tv_usec;
+};
+
+struct compat_stat {
+	compat_dev_t	st_dev;
+	u16		__pad1;
+	compat_ino_t	st_ino;
+	compat_mode_t	st_mode;
+	compat_nlink_t	st_nlink;
+	__compat_uid_t	st_uid;
+	__compat_gid_t	st_gid;
+	compat_dev_t	st_rdev;
+	u16		__pad2;
+	u32		st_size;
+	u32		st_blksize;
+	u32		st_blocks;
+	u32		st_atime;
+	u32		st_atime_nsec;
+	u32		st_mtime;
+	u32		st_mtime_nsec;
+	u32		st_ctime;
+	u32		st_ctime_nsec;
+	u32		__unused4;
+	u32		__unused5;
+};
+
+struct compat_flock {
+	short		l_type;
+	short		l_whence;
+	compat_off_t	l_start;
+	compat_off_t	l_len;
+	compat_pid_t	l_pid;
+};
+
+#define F_GETLK64	12	/*  using 'struct flock64' */
+#define F_SETLK64	13
+#define F_SETLKW64	14
+
+/*
+ * IA32 uses 4 byte alignment for 64 bit quantities,
+ * so we need to pack this structure.
+ */
+struct compat_flock64 {
+	short		l_type;
+	short		l_whence;
+	compat_loff_t	l_start;
+	compat_loff_t	l_len;
+	compat_pid_t	l_pid;
+} __attribute__((packed));
+
+struct compat_statfs {
+	int		f_type;
+	int		f_bsize;
+	int		f_blocks;
+	int		f_bfree;
+	int		f_bavail;
+	int		f_files;
+	int		f_ffree;
+	compat_fsid_t	f_fsid;
+	int		f_namelen;	/* SunOS ignores this field. */
+	int		f_frsize;
+	int		f_spare[5];
+};
+
+#define COMPAT_RLIM_OLD_INFINITY	0x7fffffff
+#define COMPAT_RLIM_INFINITY		0xffffffff
+
+typedef u32		compat_old_sigset_t;	/* at least 32 bits */
+
+#define _COMPAT_NSIG		64
+#define _COMPAT_NSIG_BPW	32
+
+typedef u32               compat_sigset_word;
+
+#define COMPAT_OFF_T_MAX	0x7fffffff
+#define COMPAT_LOFF_T_MAX	0x7fffffffffffffffL
+
+struct compat_ipc64_perm {
+	compat_key_t key;
+	__compat_uid32_t uid;
+	__compat_gid32_t gid;
+	__compat_uid32_t cuid;
+	__compat_gid32_t cgid;
+	unsigned short mode;
+	unsigned short __pad1;
+	unsigned short seq;
+	unsigned short __pad2;
+	compat_ulong_t unused1;
+	compat_ulong_t unused2;
+};
+
+struct compat_semid64_ds {
+	struct compat_ipc64_perm sem_perm;
+	compat_time_t  sem_otime;
+	compat_ulong_t __unused1;
+	compat_time_t  sem_ctime;
+	compat_ulong_t __unused2;
+	compat_ulong_t sem_nsems;
+	compat_ulong_t __unused3;
+	compat_ulong_t __unused4;
+};
+
+struct compat_msqid64_ds {
+	struct compat_ipc64_perm msg_perm;
+	compat_time_t  msg_stime;
+	compat_ulong_t __unused1;
+	compat_time_t  msg_rtime;
+	compat_ulong_t __unused2;
+	compat_time_t  msg_ctime;
+	compat_ulong_t __unused3;
+	compat_ulong_t msg_cbytes;
+	compat_ulong_t msg_qnum;
+	compat_ulong_t msg_qbytes;
+	compat_pid_t   msg_lspid;
+	compat_pid_t   msg_lrpid;
+	compat_ulong_t __unused4;
+	compat_ulong_t __unused5;
+};
+
+struct compat_shmid64_ds {
+	struct compat_ipc64_perm shm_perm;
+	compat_size_t  shm_segsz;
+	compat_time_t  shm_atime;
+	compat_ulong_t __unused1;
+	compat_time_t  shm_dtime;
+	compat_ulong_t __unused2;
+	compat_time_t  shm_ctime;
+	compat_ulong_t __unused3;
+	compat_pid_t   shm_cpid;
+	compat_pid_t   shm_lpid;
+	compat_ulong_t shm_nattch;
+	compat_ulong_t __unused4;
+	compat_ulong_t __unused5;
+};
+
+/*
+ * The type of struct elf_prstatus.pr_reg in compatible core dumps.
+ */
+typedef struct user_regs_struct32 compat_elf_gregset_t;
+
+/*
+ * A pointer passed in from user mode. This should not
+ * be used for syscall parameters, just declare them
+ * as pointers because the syscall entry code will have
+ * appropriately converted them already.
+ */
+typedef	u32		compat_uptr_t;
+
+static inline void __user *compat_ptr(compat_uptr_t uptr)
+{
+	return (void __user *)(unsigned long)uptr;
+}
+
+static inline compat_uptr_t ptr_to_compat(void __user *uptr)
+{
+	return (u32)(unsigned long)uptr;
+}
+
+static inline void __user *compat_alloc_user_space(long len)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+	return (void __user *)regs->sp - len;
+}
+
+static inline int is_compat_task(void)
+{
+	return current_thread_info()->status & TS_COMPAT;
+}
+
+#endif /* ASM_X86__COMPAT_H */
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
new file mode 100644
index 000000000000..83a115083f0d
--- /dev/null
+++ b/arch/x86/include/asm/cpu.h
@@ -0,0 +1,20 @@
+#ifndef ASM_X86__CPU_H
+#define ASM_X86__CPU_H
+
+#include <linux/device.h>
+#include <linux/cpu.h>
+#include <linux/topology.h>
+#include <linux/nodemask.h>
+#include <linux/percpu.h>
+
+struct x86_cpu {
+	struct cpu cpu;
+};
+
+#ifdef CONFIG_HOTPLUG_CPU
+extern int arch_register_cpu(int num);
+extern void arch_unregister_cpu(int);
+#endif
+
+DECLARE_PER_CPU(int, cpu_state);
+#endif /* ASM_X86__CPU_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
new file mode 100644
index 000000000000..adfeae6586e1
--- /dev/null
+++ b/arch/x86/include/asm/cpufeature.h
@@ -0,0 +1,271 @@
+/*
+ * Defines x86 CPU feature bits
+ */
+#ifndef ASM_X86__CPUFEATURE_H
+#define ASM_X86__CPUFEATURE_H
+
+#include <asm/required-features.h>
+
+#define NCAPINTS	9	/* N 32-bit words worth of info */
+
+/*
+ * Note: If the comment begins with a quoted string, that string is used
+ * in /proc/cpuinfo instead of the macro name.  If the string is "",
+ * this feature bit is not displayed in /proc/cpuinfo at all.
+ */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
+#define X86_FEATURE_FPU		(0*32+ 0) /* Onboard FPU */
+#define X86_FEATURE_VME		(0*32+ 1) /* Virtual Mode Extensions */
+#define X86_FEATURE_DE		(0*32+ 2) /* Debugging Extensions */
+#define X86_FEATURE_PSE		(0*32+ 3) /* Page Size Extensions */
+#define X86_FEATURE_TSC		(0*32+ 4) /* Time Stamp Counter */
+#define X86_FEATURE_MSR		(0*32+ 5) /* Model-Specific Registers */
+#define X86_FEATURE_PAE		(0*32+ 6) /* Physical Address Extensions */
+#define X86_FEATURE_MCE		(0*32+ 7) /* Machine Check Architecture */
+#define X86_FEATURE_CX8		(0*32+ 8) /* CMPXCHG8 instruction */
+#define X86_FEATURE_APIC	(0*32+ 9) /* Onboard APIC */
+#define X86_FEATURE_SEP		(0*32+11) /* SYSENTER/SYSEXIT */
+#define X86_FEATURE_MTRR	(0*32+12) /* Memory Type Range Registers */
+#define X86_FEATURE_PGE		(0*32+13) /* Page Global Enable */
+#define X86_FEATURE_MCA		(0*32+14) /* Machine Check Architecture */
+#define X86_FEATURE_CMOV	(0*32+15) /* CMOV instructions */
+					  /* (plus FCMOVcc, FCOMI with FPU) */
+#define X86_FEATURE_PAT		(0*32+16) /* Page Attribute Table */
+#define X86_FEATURE_PSE36	(0*32+17) /* 36-bit PSEs */
+#define X86_FEATURE_PN		(0*32+18) /* Processor serial number */
+#define X86_FEATURE_CLFLSH	(0*32+19) /* "clflush" CLFLUSH instruction */
+#define X86_FEATURE_DS		(0*32+21) /* "dts" Debug Store */
+#define X86_FEATURE_ACPI	(0*32+22) /* ACPI via MSR */
+#define X86_FEATURE_MMX		(0*32+23) /* Multimedia Extensions */
+#define X86_FEATURE_FXSR	(0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM		(0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2	(0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP	(0*32+27) /* "ss" CPU self snoop */
+#define X86_FEATURE_HT		(0*32+28) /* Hyper-Threading */
+#define X86_FEATURE_ACC		(0*32+29) /* "tm" Automatic clock control */
+#define X86_FEATURE_IA64	(0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE		(0*32+31) /* Pending Break Enable */
+
+/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
+/* Don't duplicate feature flags which are redundant with Intel! */
+#define X86_FEATURE_SYSCALL	(1*32+11) /* SYSCALL/SYSRET */
+#define X86_FEATURE_MP		(1*32+19) /* MP Capable. */
+#define X86_FEATURE_NX		(1*32+20) /* Execute Disable */
+#define X86_FEATURE_MMXEXT	(1*32+22) /* AMD MMX extensions */
+#define X86_FEATURE_FXSR_OPT	(1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES	(1*32+26) /* "pdpe1gb" GB pages */
+#define X86_FEATURE_RDTSCP	(1*32+27) /* RDTSCP */
+#define X86_FEATURE_LM		(1*32+29) /* Long Mode (x86-64) */
+#define X86_FEATURE_3DNOWEXT	(1*32+30) /* AMD 3DNow! extensions */
+#define X86_FEATURE_3DNOW	(1*32+31) /* 3DNow! */
+
+/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
+#define X86_FEATURE_RECOVERY	(2*32+ 0) /* CPU in recovery mode */
+#define X86_FEATURE_LONGRUN	(2*32+ 1) /* Longrun power control */
+#define X86_FEATURE_LRTI	(2*32+ 3) /* LongRun table interface */
+
+/* Other features, Linux-defined mapping, word 3 */
+/* This range is used for feature bits which conflict or are synthesized */
+#define X86_FEATURE_CXMMX	(3*32+ 0) /* Cyrix MMX extensions */
+#define X86_FEATURE_K6_MTRR	(3*32+ 1) /* AMD K6 nonstandard MTRRs */
+#define X86_FEATURE_CYRIX_ARR	(3*32+ 2) /* Cyrix ARRs (= MTRRs) */
+#define X86_FEATURE_CENTAUR_MCR	(3*32+ 3) /* Centaur MCRs (= MTRRs) */
+/* cpu types for specific tunings: */
+#define X86_FEATURE_K8		(3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7		(3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3		(3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4		(3*32+ 7) /* "" P4 */
+#define X86_FEATURE_CONSTANT_TSC (3*32+ 8) /* TSC ticks at a constant rate */
+#define X86_FEATURE_UP		(3*32+ 9) /* smp kernel running on up */
+#define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
+#define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_PEBS	(3*32+12) /* Precise-Event Based Sampling */
+#define X86_FEATURE_BTS		(3*32+13) /* Branch Trace Store */
+#define X86_FEATURE_SYSCALL32	(3*32+14) /* "" syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32	(3*32+15) /* "" sysenter in ia32 userspace */
+#define X86_FEATURE_REP_GOOD	(3*32+16) /* rep microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* "" Mfence synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
+#define X86_FEATURE_11AP	(3*32+19) /* "" Bad local APIC aka 11AP */
+#define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
+#define X86_FEATURE_AMDC1E	(3*32+21) /* AMD C1E detected */
+#define X86_FEATURE_XTOPOLOGY	(3*32+21) /* cpu topology enum extensions */
+
+/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
+#define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ	(4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64	(4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT	(4*32+ 3) /* "monitor" Monitor/Mwait support */
+#define X86_FEATURE_DSCPL	(4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+#define X86_FEATURE_VMX		(4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX		(4*32+ 6) /* Safer mode */
+#define X86_FEATURE_EST		(4*32+ 7) /* Enhanced SpeedStep */
+#define X86_FEATURE_TM2		(4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3	(4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_CID		(4*32+10) /* Context ID */
+#define X86_FEATURE_FMA		(4*32+12) /* Fused multiply-add */
+#define X86_FEATURE_CX16	(4*32+13) /* CMPXCHG16B */
+#define X86_FEATURE_XTPR	(4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM	(4*32+15) /* Performance Capabilities */
+#define X86_FEATURE_DCA		(4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1	(4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2	(4*32+20) /* "sse4_2" SSE-4.2 */
+#define X86_FEATURE_X2APIC	(4*32+21) /* x2APIC */
+#define X86_FEATURE_AES		(4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE	(4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+#define X86_FEATURE_OSXSAVE	(4*32+27) /* "" XSAVE enabled in the OS */
+#define X86_FEATURE_AVX		(4*32+28) /* Advanced Vector Extensions */
+
+/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
+#define X86_FEATURE_XSTORE	(5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN	(5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT	(5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN	(5*32+ 7) /* "ace_en" on-CPU crypto enabled */
+#define X86_FEATURE_ACE2	(5*32+ 8) /* Advanced Cryptography Engine v2 */
+#define X86_FEATURE_ACE2_EN	(5*32+ 9) /* ACE v2 enabled */
+#define X86_FEATURE_PHE		(5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN	(5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM		(5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN	(5*32+13) /* PMM enabled */
+
+/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
+#define X86_FEATURE_LAHF_LM	(6*32+ 0) /* LAHF/SAHF in long mode */
+#define X86_FEATURE_CMP_LEGACY	(6*32+ 1) /* If yes HyperThreading not valid */
+#define X86_FEATURE_SVM		(6*32+ 2) /* Secure virtual machine */
+#define X86_FEATURE_EXTAPIC	(6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY	(6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM		(6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A	(6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE (6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW	(6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS		(6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_SSE5	(6*32+11) /* SSE-5 */
+#define X86_FEATURE_SKINIT	(6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
+
+/*
+ * Auxiliary flags: Linux defined - For features scattered in various
+ * CPUID levels like 0x6, 0xA etc
+ */
+#define X86_FEATURE_IDA		(7*32+ 0) /* Intel Dynamic Acceleration */
+
+/* Virtualization flags: Linux defined */
+#define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI        (8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT         (8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID        (8*32+ 4) /* Intel Virtual Processor ID */
+
+#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
+
+#include <linux/bitops.h>
+
+extern const char * const x86_cap_flags[NCAPINTS*32];
+extern const char * const x86_power_flags[32];
+
+#define test_cpu_cap(c, bit)						\
+	 test_bit(bit, (unsigned long *)((c)->x86_capability))
+
+#define cpu_has(c, bit)							\
+	(__builtin_constant_p(bit) &&					\
+	 ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) ||	\
+	   (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) ||	\
+	   (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) ||	\
+	   (((bit)>>5)==3 && (1UL<<((bit)&31) & REQUIRED_MASK3)) ||	\
+	   (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) ||	\
+	   (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) ||	\
+	   (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||	\
+	   (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) )	\
+	  ? 1 :								\
+	 test_cpu_cap(c, bit))
+
+#define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
+
+#define set_cpu_cap(c, bit)	set_bit(bit, (unsigned long *)((c)->x86_capability))
+#define clear_cpu_cap(c, bit)	clear_bit(bit, (unsigned long *)((c)->x86_capability))
+#define setup_clear_cpu_cap(bit) do { \
+	clear_cpu_cap(&boot_cpu_data, bit);	\
+	set_bit(bit, (unsigned long *)cleared_cpu_caps); \
+} while (0)
+#define setup_force_cpu_cap(bit) do { \
+	set_cpu_cap(&boot_cpu_data, bit);	\
+	clear_bit(bit, (unsigned long *)cleared_cpu_caps);	\
+} while (0)
+
+#define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
+#define cpu_has_vme		boot_cpu_has(X86_FEATURE_VME)
+#define cpu_has_de		boot_cpu_has(X86_FEATURE_DE)
+#define cpu_has_pse		boot_cpu_has(X86_FEATURE_PSE)
+#define cpu_has_tsc		boot_cpu_has(X86_FEATURE_TSC)
+#define cpu_has_pae		boot_cpu_has(X86_FEATURE_PAE)
+#define cpu_has_pge		boot_cpu_has(X86_FEATURE_PGE)
+#define cpu_has_apic		boot_cpu_has(X86_FEATURE_APIC)
+#define cpu_has_sep		boot_cpu_has(X86_FEATURE_SEP)
+#define cpu_has_mtrr		boot_cpu_has(X86_FEATURE_MTRR)
+#define cpu_has_mmx		boot_cpu_has(X86_FEATURE_MMX)
+#define cpu_has_fxsr		boot_cpu_has(X86_FEATURE_FXSR)
+#define cpu_has_xmm		boot_cpu_has(X86_FEATURE_XMM)
+#define cpu_has_xmm2		boot_cpu_has(X86_FEATURE_XMM2)
+#define cpu_has_xmm3		boot_cpu_has(X86_FEATURE_XMM3)
+#define cpu_has_ht		boot_cpu_has(X86_FEATURE_HT)
+#define cpu_has_mp		boot_cpu_has(X86_FEATURE_MP)
+#define cpu_has_nx		boot_cpu_has(X86_FEATURE_NX)
+#define cpu_has_k6_mtrr		boot_cpu_has(X86_FEATURE_K6_MTRR)
+#define cpu_has_cyrix_arr	boot_cpu_has(X86_FEATURE_CYRIX_ARR)
+#define cpu_has_centaur_mcr	boot_cpu_has(X86_FEATURE_CENTAUR_MCR)
+#define cpu_has_xstore		boot_cpu_has(X86_FEATURE_XSTORE)
+#define cpu_has_xstore_enabled	boot_cpu_has(X86_FEATURE_XSTORE_EN)
+#define cpu_has_xcrypt		boot_cpu_has(X86_FEATURE_XCRYPT)
+#define cpu_has_xcrypt_enabled	boot_cpu_has(X86_FEATURE_XCRYPT_EN)
+#define cpu_has_ace2		boot_cpu_has(X86_FEATURE_ACE2)
+#define cpu_has_ace2_enabled	boot_cpu_has(X86_FEATURE_ACE2_EN)
+#define cpu_has_phe		boot_cpu_has(X86_FEATURE_PHE)
+#define cpu_has_phe_enabled	boot_cpu_has(X86_FEATURE_PHE_EN)
+#define cpu_has_pmm		boot_cpu_has(X86_FEATURE_PMM)
+#define cpu_has_pmm_enabled	boot_cpu_has(X86_FEATURE_PMM_EN)
+#define cpu_has_ds		boot_cpu_has(X86_FEATURE_DS)
+#define cpu_has_pebs		boot_cpu_has(X86_FEATURE_PEBS)
+#define cpu_has_clflush		boot_cpu_has(X86_FEATURE_CLFLSH)
+#define cpu_has_bts		boot_cpu_has(X86_FEATURE_BTS)
+#define cpu_has_gbpages		boot_cpu_has(X86_FEATURE_GBPAGES)
+#define cpu_has_arch_perfmon	boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
+#define cpu_has_pat		boot_cpu_has(X86_FEATURE_PAT)
+#define cpu_has_xmm4_1		boot_cpu_has(X86_FEATURE_XMM4_1)
+#define cpu_has_xmm4_2		boot_cpu_has(X86_FEATURE_XMM4_2)
+#define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
+#define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
+
+#if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
+# define cpu_has_invlpg		1
+#else
+# define cpu_has_invlpg		(boot_cpu_data.x86 > 3)
+#endif
+
+#ifdef CONFIG_X86_64
+
+#undef  cpu_has_vme
+#define cpu_has_vme		0
+
+#undef  cpu_has_pae
+#define cpu_has_pae		___BUG___
+
+#undef  cpu_has_mp
+#define cpu_has_mp		1
+
+#undef  cpu_has_k6_mtrr
+#define cpu_has_k6_mtrr		0
+
+#undef  cpu_has_cyrix_arr
+#define cpu_has_cyrix_arr	0
+
+#undef  cpu_has_centaur_mcr
+#define cpu_has_centaur_mcr	0
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
+
+#endif /* ASM_X86__CPUFEATURE_H */
diff --git a/arch/x86/include/asm/cputime.h b/arch/x86/include/asm/cputime.h
new file mode 100644
index 000000000000..6d68ad7e0ea3
--- /dev/null
+++ b/arch/x86/include/asm/cputime.h
@@ -0,0 +1 @@
+#include <asm-generic/cputime.h>
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
new file mode 100644
index 000000000000..a863ead856f3
--- /dev/null
+++ b/arch/x86/include/asm/current.h
@@ -0,0 +1,39 @@
+#ifndef ASM_X86__CURRENT_H
+#define ASM_X86__CURRENT_H
+
+#ifdef CONFIG_X86_32
+#include <linux/compiler.h>
+#include <asm/percpu.h>
+
+struct task_struct;
+
+DECLARE_PER_CPU(struct task_struct *, current_task);
+static __always_inline struct task_struct *get_current(void)
+{
+	return x86_read_percpu(current_task);
+}
+
+#else /* X86_32 */
+
+#ifndef __ASSEMBLY__
+#include <asm/pda.h>
+
+struct task_struct;
+
+static __always_inline struct task_struct *get_current(void)
+{
+	return read_pda(pcurrent);
+}
+
+#else /* __ASSEMBLY__ */
+
+#include <asm/asm-offsets.h>
+#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* X86_32 */
+
+#define current get_current()
+
+#endif /* ASM_X86__CURRENT_H */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
new file mode 100644
index 000000000000..ecb6907c3ea4
--- /dev/null
+++ b/arch/x86/include/asm/debugreg.h
@@ -0,0 +1,70 @@
+#ifndef ASM_X86__DEBUGREG_H
+#define ASM_X86__DEBUGREG_H
+
+
+/* Indicate the register numbers for a number of the specific
+   debug registers.  Registers 0-3 contain the addresses we wish to trap on */
+#define DR_FIRSTADDR 0        /* u_debugreg[DR_FIRSTADDR] */
+#define DR_LASTADDR 3         /* u_debugreg[DR_LASTADDR]  */
+
+#define DR_STATUS 6           /* u_debugreg[DR_STATUS]     */
+#define DR_CONTROL 7          /* u_debugreg[DR_CONTROL] */
+
+/* Define a few things for the status register.  We can use this to determine
+   which debugging register was responsible for the trap.  The other bits
+   are either reserved or not of interest to us. */
+
+#define DR_TRAP0	(0x1)		/* db0 */
+#define DR_TRAP1	(0x2)		/* db1 */
+#define DR_TRAP2	(0x4)		/* db2 */
+#define DR_TRAP3	(0x8)		/* db3 */
+
+#define DR_STEP		(0x4000)	/* single-step */
+#define DR_SWITCH	(0x8000)	/* task switch */
+
+/* Now define a bunch of things for manipulating the control register.
+   The top two bytes of the control register consist of 4 fields of 4
+   bits - each field corresponds to one of the four debug registers,
+   and indicates what types of access we trap on, and how large the data
+   field is that we are looking at */
+
+#define DR_CONTROL_SHIFT 16 /* Skip this many bits in ctl register */
+#define DR_CONTROL_SIZE 4   /* 4 control bits per register */
+
+#define DR_RW_EXECUTE (0x0)   /* Settings for the access types to trap on */
+#define DR_RW_WRITE (0x1)
+#define DR_RW_READ (0x3)
+
+#define DR_LEN_1 (0x0) /* Settings for data length to trap on */
+#define DR_LEN_2 (0x4)
+#define DR_LEN_4 (0xC)
+#define DR_LEN_8 (0x8)
+
+/* The low byte to the control register determine which registers are
+   enabled.  There are 4 fields of two bits.  One bit is "local", meaning
+   that the processor will reset the bit after a task switch and the other
+   is global meaning that we have to explicitly reset the bit.  With linux,
+   you can use either one, since we explicitly zero the register when we enter
+   kernel mode. */
+
+#define DR_LOCAL_ENABLE_SHIFT 0    /* Extra shift to the local enable bit */
+#define DR_GLOBAL_ENABLE_SHIFT 1   /* Extra shift to the global enable bit */
+#define DR_ENABLE_SIZE 2           /* 2 enable bits per register */
+
+#define DR_LOCAL_ENABLE_MASK (0x55)  /* Set  local bits for all 4 regs */
+#define DR_GLOBAL_ENABLE_MASK (0xAA) /* Set global bits for all 4 regs */
+
+/* The second byte to the control register has a few special things.
+   We can slow the instruction pipeline for instructions coming via the
+   gdt or the ldt if we want to.  I am not sure why this is an advantage */
+
+#ifdef __i386__
+#define DR_CONTROL_RESERVED (0xFC00) /* Reserved by Intel */
+#else
+#define DR_CONTROL_RESERVED (0xFFFFFFFF0000FC00UL) /* Reserved */
+#endif
+
+#define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
+#define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
+
+#endif /* ASM_X86__DEBUGREG_H */
diff --git a/arch/x86/include/asm/delay.h b/arch/x86/include/asm/delay.h
new file mode 100644
index 000000000000..8a0da95b4fc5
--- /dev/null
+++ b/arch/x86/include/asm/delay.h
@@ -0,0 +1,31 @@
+#ifndef ASM_X86__DELAY_H
+#define ASM_X86__DELAY_H
+
+/*
+ * Copyright (C) 1993 Linus Torvalds
+ *
+ * Delay routines calling functions in arch/x86/lib/delay.c
+ */
+
+/* Undefined functions to get compile-time errors */
+extern void __bad_udelay(void);
+extern void __bad_ndelay(void);
+
+extern void __udelay(unsigned long usecs);
+extern void __ndelay(unsigned long nsecs);
+extern void __const_udelay(unsigned long xloops);
+extern void __delay(unsigned long loops);
+
+/* 0x10c7 is 2**32 / 1000000 (rounded up) */
+#define udelay(n) (__builtin_constant_p(n) ? \
+	((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c7ul)) : \
+	__udelay(n))
+
+/* 0x5 is 2**32 / 1000000000 (rounded up) */
+#define ndelay(n) (__builtin_constant_p(n) ? \
+	((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \
+	__ndelay(n))
+
+void use_tsc_delay(void);
+
+#endif /* ASM_X86__DELAY_H */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
new file mode 100644
index 000000000000..f06adac7938c
--- /dev/null
+++ b/arch/x86/include/asm/desc.h
@@ -0,0 +1,409 @@
+#ifndef ASM_X86__DESC_H
+#define ASM_X86__DESC_H
+
+#ifndef __ASSEMBLY__
+#include <asm/desc_defs.h>
+#include <asm/ldt.h>
+#include <asm/mmu.h>
+#include <linux/smp.h>
+
+static inline void fill_ldt(struct desc_struct *desc,
+			    const struct user_desc *info)
+{
+	desc->limit0 = info->limit & 0x0ffff;
+	desc->base0 = info->base_addr & 0x0000ffff;
+
+	desc->base1 = (info->base_addr & 0x00ff0000) >> 16;
+	desc->type = (info->read_exec_only ^ 1) << 1;
+	desc->type |= info->contents << 2;
+	desc->s = 1;
+	desc->dpl = 0x3;
+	desc->p = info->seg_not_present ^ 1;
+	desc->limit = (info->limit & 0xf0000) >> 16;
+	desc->avl = info->useable;
+	desc->d = info->seg_32bit;
+	desc->g = info->limit_in_pages;
+	desc->base2 = (info->base_addr & 0xff000000) >> 24;
+	/*
+	 * Don't allow setting of the lm bit. It is useless anyway
+	 * because 64bit system calls require __USER_CS:
+	 */
+	desc->l = 0;
+}
+
+extern struct desc_ptr idt_descr;
+extern gate_desc idt_table[];
+
+struct gdt_page {
+	struct desc_struct gdt[GDT_ENTRIES];
+} __attribute__((aligned(PAGE_SIZE)));
+DECLARE_PER_CPU(struct gdt_page, gdt_page);
+
+static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
+{
+	return per_cpu(gdt_page, cpu).gdt;
+}
+
+#ifdef CONFIG_X86_64
+
+static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
+			     unsigned dpl, unsigned ist, unsigned seg)
+{
+	gate->offset_low = PTR_LOW(func);
+	gate->segment = __KERNEL_CS;
+	gate->ist = ist;
+	gate->p = 1;
+	gate->dpl = dpl;
+	gate->zero0 = 0;
+	gate->zero1 = 0;
+	gate->type = type;
+	gate->offset_middle = PTR_MIDDLE(func);
+	gate->offset_high = PTR_HIGH(func);
+}
+
+#else
+static inline void pack_gate(gate_desc *gate, unsigned char type,
+			     unsigned long base, unsigned dpl, unsigned flags,
+			     unsigned short seg)
+{
+	gate->a = (seg << 16) | (base & 0xffff);
+	gate->b = (base & 0xffff0000) |
+		  (((0x80 | type | (dpl << 5)) & 0xff) << 8);
+}
+
+#endif
+
+static inline int desc_empty(const void *ptr)
+{
+	const u32 *desc = ptr;
+	return !(desc[0] | desc[1]);
+}
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define load_TR_desc() native_load_tr_desc()
+#define load_gdt(dtr) native_load_gdt(dtr)
+#define load_idt(dtr) native_load_idt(dtr)
+#define load_tr(tr) asm volatile("ltr %0"::"m" (tr))
+#define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt))
+
+#define store_gdt(dtr) native_store_gdt(dtr)
+#define store_idt(dtr) native_store_idt(dtr)
+#define store_tr(tr) (tr = native_store_tr())
+#define store_ldt(ldt) asm("sldt %0":"=m" (ldt))
+
+#define load_TLS(t, cpu) native_load_tls(t, cpu)
+#define set_ldt native_set_ldt
+
+#define write_ldt_entry(dt, entry, desc)	\
+	native_write_ldt_entry(dt, entry, desc)
+#define write_gdt_entry(dt, entry, desc, type)		\
+	native_write_gdt_entry(dt, entry, desc, type)
+#define write_idt_entry(dt, entry, g)		\
+	native_write_idt_entry(dt, entry, g)
+
+static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
+{
+}
+
+static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
+{
+}
+#endif	/* CONFIG_PARAVIRT */
+
+static inline void native_write_idt_entry(gate_desc *idt, int entry,
+					  const gate_desc *gate)
+{
+	memcpy(&idt[entry], gate, sizeof(*gate));
+}
+
+static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry,
+					  const void *desc)
+{
+	memcpy(&ldt[entry], desc, 8);
+}
+
+static inline void native_write_gdt_entry(struct desc_struct *gdt, int entry,
+					  const void *desc, int type)
+{
+	unsigned int size;
+	switch (type) {
+	case DESC_TSS:
+		size = sizeof(tss_desc);
+		break;
+	case DESC_LDT:
+		size = sizeof(ldt_desc);
+		break;
+	default:
+		size = sizeof(struct desc_struct);
+		break;
+	}
+	memcpy(&gdt[entry], desc, size);
+}
+
+static inline void pack_descriptor(struct desc_struct *desc, unsigned long base,
+				   unsigned long limit, unsigned char type,
+				   unsigned char flags)
+{
+	desc->a = ((base & 0xffff) << 16) | (limit & 0xffff);
+	desc->b = (base & 0xff000000) | ((base & 0xff0000) >> 16) |
+		(limit & 0x000f0000) | ((type & 0xff) << 8) |
+		((flags & 0xf) << 20);
+	desc->p = 1;
+}
+
+
+static inline void set_tssldt_descriptor(void *d, unsigned long addr,
+					 unsigned type, unsigned size)
+{
+#ifdef CONFIG_X86_64
+	struct ldttss_desc64 *desc = d;
+	memset(desc, 0, sizeof(*desc));
+	desc->limit0 = size & 0xFFFF;
+	desc->base0 = PTR_LOW(addr);
+	desc->base1 = PTR_MIDDLE(addr) & 0xFF;
+	desc->type = type;
+	desc->p = 1;
+	desc->limit1 = (size >> 16) & 0xF;
+	desc->base2 = (PTR_MIDDLE(addr) >> 8) & 0xFF;
+	desc->base3 = PTR_HIGH(addr);
+#else
+	pack_descriptor((struct desc_struct *)d, addr, size, 0x80 | type, 0);
+#endif
+}
+
+static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr)
+{
+	struct desc_struct *d = get_cpu_gdt_table(cpu);
+	tss_desc tss;
+
+	/*
+	 * sizeof(unsigned long) coming from an extra "long" at the end
+	 * of the iobitmap. See tss_struct definition in processor.h
+	 *
+	 * -1? seg base+limit should be pointing to the address of the
+	 * last valid byte
+	 */
+	set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS,
+			      IO_BITMAP_OFFSET + IO_BITMAP_BYTES +
+			      sizeof(unsigned long) - 1);
+	write_gdt_entry(d, entry, &tss, DESC_TSS);
+}
+
+#define set_tss_desc(cpu, addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr)
+
+static inline void native_set_ldt(const void *addr, unsigned int entries)
+{
+	if (likely(entries == 0))
+		asm volatile("lldt %w0"::"q" (0));
+	else {
+		unsigned cpu = smp_processor_id();
+		ldt_desc ldt;
+
+		set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT,
+				      entries * LDT_ENTRY_SIZE - 1);
+		write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT,
+				&ldt, DESC_LDT);
+		asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8));
+	}
+}
+
+static inline void native_load_tr_desc(void)
+{
+	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
+}
+
+static inline void native_load_gdt(const struct desc_ptr *dtr)
+{
+	asm volatile("lgdt %0"::"m" (*dtr));
+}
+
+static inline void native_load_idt(const struct desc_ptr *dtr)
+{
+	asm volatile("lidt %0"::"m" (*dtr));
+}
+
+static inline void native_store_gdt(struct desc_ptr *dtr)
+{
+	asm volatile("sgdt %0":"=m" (*dtr));
+}
+
+static inline void native_store_idt(struct desc_ptr *dtr)
+{
+	asm volatile("sidt %0":"=m" (*dtr));
+}
+
+static inline unsigned long native_store_tr(void)
+{
+	unsigned long tr;
+	asm volatile("str %0":"=r" (tr));
+	return tr;
+}
+
+static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
+{
+	unsigned int i;
+	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+
+	for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
+		gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
+}
+
+#define _LDT_empty(info)				\
+	((info)->base_addr		== 0	&&	\
+	 (info)->limit			== 0	&&	\
+	 (info)->contents		== 0	&&	\
+	 (info)->read_exec_only		== 1	&&	\
+	 (info)->seg_32bit		== 0	&&	\
+	 (info)->limit_in_pages		== 0	&&	\
+	 (info)->seg_not_present	== 1	&&	\
+	 (info)->useable		== 0)
+
+#ifdef CONFIG_X86_64
+#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0))
+#else
+#define LDT_empty(info) (_LDT_empty(info))
+#endif
+
+static inline void clear_LDT(void)
+{
+	set_ldt(NULL, 0);
+}
+
+/*
+ * load one particular LDT into the current CPU
+ */
+static inline void load_LDT_nolock(mm_context_t *pc)
+{
+	set_ldt(pc->ldt, pc->size);
+}
+
+static inline void load_LDT(mm_context_t *pc)
+{
+	preempt_disable();
+	load_LDT_nolock(pc);
+	preempt_enable();
+}
+
+static inline unsigned long get_desc_base(const struct desc_struct *desc)
+{
+	return desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24);
+}
+
+static inline unsigned long get_desc_limit(const struct desc_struct *desc)
+{
+	return desc->limit0 | (desc->limit << 16);
+}
+
+static inline void _set_gate(int gate, unsigned type, void *addr,
+			     unsigned dpl, unsigned ist, unsigned seg)
+{
+	gate_desc s;
+	pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg);
+	/*
+	 * does not need to be atomic because it is only done once at
+	 * setup time
+	 */
+	write_idt_entry(idt_table, gate, &s);
+}
+
+/*
+ * This needs to use 'idt_table' rather than 'idt', and
+ * thus use the _nonmapped_ version of the IDT, as the
+ * Pentium F0 0F bugfix can have resulted in the mapped
+ * IDT being write-protected.
+ */
+static inline void set_intr_gate(unsigned int n, void *addr)
+{
+	BUG_ON((unsigned)n > 0xFF);
+	_set_gate(n, GATE_INTERRUPT, addr, 0, 0, __KERNEL_CS);
+}
+
+#define SYS_VECTOR_FREE		0
+#define SYS_VECTOR_ALLOCED	1
+
+extern int first_system_vector;
+extern char system_vectors[];
+
+static inline void alloc_system_vector(int vector)
+{
+	if (system_vectors[vector] == SYS_VECTOR_FREE) {
+		system_vectors[vector] = SYS_VECTOR_ALLOCED;
+		if (first_system_vector > vector)
+			first_system_vector = vector;
+	} else
+		BUG();
+}
+
+static inline void alloc_intr_gate(unsigned int n, void *addr)
+{
+	alloc_system_vector(n);
+	set_intr_gate(n, addr);
+}
+
+/*
+ * This routine sets up an interrupt gate at directory privilege level 3.
+ */
+static inline void set_system_intr_gate(unsigned int n, void *addr)
+{
+	BUG_ON((unsigned)n > 0xFF);
+	_set_gate(n, GATE_INTERRUPT, addr, 0x3, 0, __KERNEL_CS);
+}
+
+static inline void set_system_trap_gate(unsigned int n, void *addr)
+{
+	BUG_ON((unsigned)n > 0xFF);
+	_set_gate(n, GATE_TRAP, addr, 0x3, 0, __KERNEL_CS);
+}
+
+static inline void set_trap_gate(unsigned int n, void *addr)
+{
+	BUG_ON((unsigned)n > 0xFF);
+	_set_gate(n, GATE_TRAP, addr, 0, 0, __KERNEL_CS);
+}
+
+static inline void set_task_gate(unsigned int n, unsigned int gdt_entry)
+{
+	BUG_ON((unsigned)n > 0xFF);
+	_set_gate(n, GATE_TASK, (void *)0, 0, 0, (gdt_entry<<3));
+}
+
+static inline void set_intr_gate_ist(int n, void *addr, unsigned ist)
+{
+	BUG_ON((unsigned)n > 0xFF);
+	_set_gate(n, GATE_INTERRUPT, addr, 0, ist, __KERNEL_CS);
+}
+
+static inline void set_system_intr_gate_ist(int n, void *addr, unsigned ist)
+{
+	BUG_ON((unsigned)n > 0xFF);
+	_set_gate(n, GATE_INTERRUPT, addr, 0x3, ist, __KERNEL_CS);
+}
+
+#else
+/*
+ * GET_DESC_BASE reads the descriptor base of the specified segment.
+ *
+ * Args:
+ *    idx - descriptor index
+ *    gdt - GDT pointer
+ *    base - 32bit register to which the base will be written
+ *    lo_w - lo word of the "base" register
+ *    lo_b - lo byte of the "base" register
+ *    hi_b - hi byte of the low word of the "base" register
+ *
+ * Example:
+ *    GET_DESC_BASE(GDT_ENTRY_ESPFIX_SS, %ebx, %eax, %ax, %al, %ah)
+ *    Will read the base address of GDT_ENTRY_ESPFIX_SS and put it into %eax.
+ */
+#define GET_DESC_BASE(idx, gdt, base, lo_w, lo_b, hi_b) \
+	movb idx * 8 + 4(gdt), lo_b;			\
+	movb idx * 8 + 7(gdt), hi_b;			\
+	shll $16, base;					\
+	movw idx * 8 + 2(gdt), lo_w;
+
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* ASM_X86__DESC_H */
diff --git a/arch/x86/include/asm/desc_defs.h b/arch/x86/include/asm/desc_defs.h
new file mode 100644
index 000000000000..b881db664b46
--- /dev/null
+++ b/arch/x86/include/asm/desc_defs.h
@@ -0,0 +1,95 @@
+/* Written 2000 by Andi Kleen */
+#ifndef ASM_X86__DESC_DEFS_H
+#define ASM_X86__DESC_DEFS_H
+
+/*
+ * Segment descriptor structure definitions, usable from both x86_64 and i386
+ * archs.
+ */
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+/*
+ * FIXME: Acessing the desc_struct through its fields is more elegant,
+ * and should be the one valid thing to do. However, a lot of open code
+ * still touches the a and b acessors, and doing this allow us to do it
+ * incrementally. We keep the signature as a struct, rather than an union,
+ * so we can get rid of it transparently in the future -- glommer
+ */
+/* 8 byte segment descriptor */
+struct desc_struct {
+	union {
+		struct {
+			unsigned int a;
+			unsigned int b;
+		};
+		struct {
+			u16 limit0;
+			u16 base0;
+			unsigned base1: 8, type: 4, s: 1, dpl: 2, p: 1;
+			unsigned limit: 4, avl: 1, l: 1, d: 1, g: 1, base2: 8;
+		};
+	};
+} __attribute__((packed));
+
+enum {
+	GATE_INTERRUPT = 0xE,
+	GATE_TRAP = 0xF,
+	GATE_CALL = 0xC,
+	GATE_TASK = 0x5,
+};
+
+/* 16byte gate */
+struct gate_struct64 {
+	u16 offset_low;
+	u16 segment;
+	unsigned ist : 3, zero0 : 5, type : 5, dpl : 2, p : 1;
+	u16 offset_middle;
+	u32 offset_high;
+	u32 zero1;
+} __attribute__((packed));
+
+#define PTR_LOW(x) ((unsigned long long)(x) & 0xFFFF)
+#define PTR_MIDDLE(x) (((unsigned long long)(x) >> 16) & 0xFFFF)
+#define PTR_HIGH(x) ((unsigned long long)(x) >> 32)
+
+enum {
+	DESC_TSS = 0x9,
+	DESC_LDT = 0x2,
+	DESCTYPE_S = 0x10,	/* !system */
+};
+
+/* LDT or TSS descriptor in the GDT. 16 bytes. */
+struct ldttss_desc64 {
+	u16 limit0;
+	u16 base0;
+	unsigned base1 : 8, type : 5, dpl : 2, p : 1;
+	unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8;
+	u32 base3;
+	u32 zero1;
+} __attribute__((packed));
+
+#ifdef CONFIG_X86_64
+typedef struct gate_struct64 gate_desc;
+typedef struct ldttss_desc64 ldt_desc;
+typedef struct ldttss_desc64 tss_desc;
+#define gate_offset(g) ((g).offset_low | ((unsigned long)(g).offset_middle << 16) | ((unsigned long)(g).offset_high << 32))
+#define gate_segment(g) ((g).segment)
+#else
+typedef struct desc_struct gate_desc;
+typedef struct desc_struct ldt_desc;
+typedef struct desc_struct tss_desc;
+#define gate_offset(g)		(((g).b & 0xffff0000) | ((g).a & 0x0000ffff))
+#define gate_segment(g)		((g).a >> 16)
+#endif
+
+struct desc_ptr {
+	unsigned short size;
+	unsigned long address;
+} __attribute__((packed)) ;
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* ASM_X86__DESC_DEFS_H */
diff --git a/arch/x86/include/asm/device.h b/arch/x86/include/asm/device.h
new file mode 100644
index 000000000000..1bece04c7d9d
--- /dev/null
+++ b/arch/x86/include/asm/device.h
@@ -0,0 +1,16 @@
+#ifndef ASM_X86__DEVICE_H
+#define ASM_X86__DEVICE_H
+
+struct dev_archdata {
+#ifdef CONFIG_ACPI
+	void	*acpi_handle;
+#endif
+#ifdef CONFIG_X86_64
+struct dma_mapping_ops *dma_ops;
+#endif
+#ifdef CONFIG_DMAR
+	void *iommu; /* hook for IOMMU specific extension */
+#endif
+};
+
+#endif /* ASM_X86__DEVICE_H */
diff --git a/arch/x86/include/asm/div64.h b/arch/x86/include/asm/div64.h
new file mode 100644
index 000000000000..f9530f23f1d6
--- /dev/null
+++ b/arch/x86/include/asm/div64.h
@@ -0,0 +1,60 @@
+#ifndef ASM_X86__DIV64_H
+#define ASM_X86__DIV64_H
+
+#ifdef CONFIG_X86_32
+
+#include <linux/types.h>
+
+/*
+ * do_div() is NOT a C function. It wants to return
+ * two values (the quotient and the remainder), but
+ * since that doesn't work very well in C, what it
+ * does is:
+ *
+ * - modifies the 64-bit dividend _in_place_
+ * - returns the 32-bit remainder
+ *
+ * This ends up being the most efficient "calling
+ * convention" on x86.
+ */
+#define do_div(n, base)						\
+({								\
+	unsigned long __upper, __low, __high, __mod, __base;	\
+	__base = (base);					\
+	asm("":"=a" (__low), "=d" (__high) : "A" (n));		\
+	__upper = __high;					\
+	if (__high) {						\
+		__upper = __high % (__base);			\
+		__high = __high / (__base);			\
+	}							\
+	asm("divl %2":"=a" (__low), "=d" (__mod)		\
+	    : "rm" (__base), "0" (__low), "1" (__upper));	\
+	asm("":"=A" (n) : "a" (__low), "d" (__high));		\
+	__mod;							\
+})
+
+static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
+{
+	union {
+		u64 v64;
+		u32 v32[2];
+	} d = { dividend };
+	u32 upper;
+
+	upper = d.v32[1];
+	d.v32[1] = 0;
+	if (upper >= divisor) {
+		d.v32[1] = upper / divisor;
+		upper %= divisor;
+	}
+	asm ("divl %2" : "=a" (d.v32[0]), "=d" (*remainder) :
+		"rm" (divisor), "0" (d.v32[0]), "1" (upper));
+	return d.v64;
+}
+#define div_u64_rem	div_u64_rem
+
+#else
+# include <asm-generic/div64.h>
+#endif /* CONFIG_X86_32 */
+
+#endif /* ASM_X86__DIV64_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
new file mode 100644
index 000000000000..219c33d6361c
--- /dev/null
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -0,0 +1,308 @@
+#ifndef ASM_X86__DMA_MAPPING_H
+#define ASM_X86__DMA_MAPPING_H
+
+/*
+ * IOMMU interface. See Documentation/DMA-mapping.txt and DMA-API.txt for
+ * documentation.
+ */
+
+#include <linux/scatterlist.h>
+#include <asm/io.h>
+#include <asm/swiotlb.h>
+#include <asm-generic/dma-coherent.h>
+
+extern dma_addr_t bad_dma_address;
+extern int iommu_merge;
+extern struct device x86_dma_fallback_dev;
+extern int panic_on_overflow;
+
+struct dma_mapping_ops {
+	int             (*mapping_error)(struct device *dev,
+					 dma_addr_t dma_addr);
+	void*           (*alloc_coherent)(struct device *dev, size_t size,
+				dma_addr_t *dma_handle, gfp_t gfp);
+	void            (*free_coherent)(struct device *dev, size_t size,
+				void *vaddr, dma_addr_t dma_handle);
+	dma_addr_t      (*map_single)(struct device *hwdev, phys_addr_t ptr,
+				size_t size, int direction);
+	void            (*unmap_single)(struct device *dev, dma_addr_t addr,
+				size_t size, int direction);
+	void            (*sync_single_for_cpu)(struct device *hwdev,
+				dma_addr_t dma_handle, size_t size,
+				int direction);
+	void            (*sync_single_for_device)(struct device *hwdev,
+				dma_addr_t dma_handle, size_t size,
+				int direction);
+	void            (*sync_single_range_for_cpu)(struct device *hwdev,
+				dma_addr_t dma_handle, unsigned long offset,
+				size_t size, int direction);
+	void            (*sync_single_range_for_device)(struct device *hwdev,
+				dma_addr_t dma_handle, unsigned long offset,
+				size_t size, int direction);
+	void            (*sync_sg_for_cpu)(struct device *hwdev,
+				struct scatterlist *sg, int nelems,
+				int direction);
+	void            (*sync_sg_for_device)(struct device *hwdev,
+				struct scatterlist *sg, int nelems,
+				int direction);
+	int             (*map_sg)(struct device *hwdev, struct scatterlist *sg,
+				int nents, int direction);
+	void            (*unmap_sg)(struct device *hwdev,
+				struct scatterlist *sg, int nents,
+				int direction);
+	int             (*dma_supported)(struct device *hwdev, u64 mask);
+	int		is_phys;
+};
+
+extern struct dma_mapping_ops *dma_ops;
+
+static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
+{
+#ifdef CONFIG_X86_32
+	return dma_ops;
+#else
+	if (unlikely(!dev) || !dev->archdata.dma_ops)
+		return dma_ops;
+	else
+		return dev->archdata.dma_ops;
+#endif /* ASM_X86__DMA_MAPPING_H */
+}
+
+/* Make sure we keep the same behaviour */
+static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+#ifdef CONFIG_X86_32
+	return 0;
+#else
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
+	if (ops->mapping_error)
+		return ops->mapping_error(dev, dma_addr);
+
+	return (dma_addr == bad_dma_address);
+#endif
+}
+
+#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
+#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
+#define dma_is_consistent(d, h)	(1)
+
+extern int dma_supported(struct device *hwdev, u64 mask);
+extern int dma_set_mask(struct device *dev, u64 mask);
+
+extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
+					dma_addr_t *dma_addr, gfp_t flag);
+
+static inline dma_addr_t
+dma_map_single(struct device *hwdev, void *ptr, size_t size,
+	       int direction)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
+	BUG_ON(!valid_dma_direction(direction));
+	return ops->map_single(hwdev, virt_to_phys(ptr), size, direction);
+}
+
+static inline void
+dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size,
+		 int direction)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(direction));
+	if (ops->unmap_single)
+		ops->unmap_single(dev, addr, size, direction);
+}
+
+static inline int
+dma_map_sg(struct device *hwdev, struct scatterlist *sg,
+	   int nents, int direction)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
+	BUG_ON(!valid_dma_direction(direction));
+	return ops->map_sg(hwdev, sg, nents, direction);
+}
+
+static inline void
+dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
+	     int direction)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
+	BUG_ON(!valid_dma_direction(direction));
+	if (ops->unmap_sg)
+		ops->unmap_sg(hwdev, sg, nents, direction);
+}
+
+static inline void
+dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
+			size_t size, int direction)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
+	BUG_ON(!valid_dma_direction(direction));
+	if (ops->sync_single_for_cpu)
+		ops->sync_single_for_cpu(hwdev, dma_handle, size, direction);
+	flush_write_buffers();
+}
+
+static inline void
+dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle,
+			   size_t size, int direction)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
+	BUG_ON(!valid_dma_direction(direction));
+	if (ops->sync_single_for_device)
+		ops->sync_single_for_device(hwdev, dma_handle, size, direction);
+	flush_write_buffers();
+}
+
+static inline void
+dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
+			      unsigned long offset, size_t size, int direction)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
+	BUG_ON(!valid_dma_direction(direction));
+	if (ops->sync_single_range_for_cpu)
+		ops->sync_single_range_for_cpu(hwdev, dma_handle, offset,
+					       size, direction);
+	flush_write_buffers();
+}
+
+static inline void
+dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle,
+				 unsigned long offset, size_t size,
+				 int direction)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
+	BUG_ON(!valid_dma_direction(direction));
+	if (ops->sync_single_range_for_device)
+		ops->sync_single_range_for_device(hwdev, dma_handle,
+						  offset, size, direction);
+	flush_write_buffers();
+}
+
+static inline void
+dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+		    int nelems, int direction)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
+	BUG_ON(!valid_dma_direction(direction));
+	if (ops->sync_sg_for_cpu)
+		ops->sync_sg_for_cpu(hwdev, sg, nelems, direction);
+	flush_write_buffers();
+}
+
+static inline void
+dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+		       int nelems, int direction)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
+
+	BUG_ON(!valid_dma_direction(direction));
+	if (ops->sync_sg_for_device)
+		ops->sync_sg_for_device(hwdev, sg, nelems, direction);
+
+	flush_write_buffers();
+}
+
+static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
+				      size_t offset, size_t size,
+				      int direction)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
+
+	BUG_ON(!valid_dma_direction(direction));
+	return ops->map_single(dev, page_to_phys(page) + offset,
+			       size, direction);
+}
+
+static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
+				  size_t size, int direction)
+{
+	dma_unmap_single(dev, addr, size, direction);
+}
+
+static inline void
+dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+	enum dma_data_direction dir)
+{
+	flush_write_buffers();
+}
+
+static inline int dma_get_cache_alignment(void)
+{
+	/* no easy way to get cache size on all x86, so return the
+	 * maximum possible, to be safe */
+	return boot_cpu_data.x86_clflush_size;
+}
+
+static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
+						    gfp_t gfp)
+{
+	unsigned long dma_mask = 0;
+
+	dma_mask = dev->coherent_dma_mask;
+	if (!dma_mask)
+		dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK;
+
+	return dma_mask;
+}
+
+static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
+{
+#ifdef CONFIG_X86_64
+	unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp);
+
+	if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
+		gfp |= GFP_DMA32;
+#endif
+       return gfp;
+}
+
+static inline void *
+dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
+	void *memory;
+
+	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+
+	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
+		return memory;
+
+	if (!dev) {
+		dev = &x86_dma_fallback_dev;
+		gfp |= GFP_DMA;
+	}
+
+	if (!is_device_dma_capable(dev))
+		return NULL;
+
+	if (!ops->alloc_coherent)
+		return NULL;
+
+	return ops->alloc_coherent(dev, size, dma_handle,
+				   dma_alloc_coherent_gfp_flags(dev, gfp));
+}
+
+static inline void dma_free_coherent(struct device *dev, size_t size,
+				     void *vaddr, dma_addr_t bus)
+{
+	struct dma_mapping_ops *ops = get_dma_ops(dev);
+
+	WARN_ON(irqs_disabled());       /* for portability */
+
+	if (dma_release_from_coherent(dev, get_order(size), vaddr))
+		return;
+
+	if (ops->free_coherent)
+		ops->free_coherent(dev, size, vaddr, bus);
+}
+
+#endif
diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h
new file mode 100644
index 000000000000..c9f7a4eec555
--- /dev/null
+++ b/arch/x86/include/asm/dma.h
@@ -0,0 +1,318 @@
+/*
+ * linux/include/asm/dma.h: Defines for using and allocating dma channels.
+ * Written by Hennus Bergman, 1992.
+ * High DMA channel support & info by Hannu Savolainen
+ * and John Boyd, Nov. 1992.
+ */
+
+#ifndef ASM_X86__DMA_H
+#define ASM_X86__DMA_H
+
+#include <linux/spinlock.h>	/* And spinlocks */
+#include <asm/io.h>		/* need byte IO */
+#include <linux/delay.h>
+
+#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
+#define dma_outb	outb_p
+#else
+#define dma_outb	outb
+#endif
+
+#define dma_inb		inb
+
+/*
+ * NOTES about DMA transfers:
+ *
+ *  controller 1: channels 0-3, byte operations, ports 00-1F
+ *  controller 2: channels 4-7, word operations, ports C0-DF
+ *
+ *  - ALL registers are 8 bits only, regardless of transfer size
+ *  - channel 4 is not used - cascades 1 into 2.
+ *  - channels 0-3 are byte - addresses/counts are for physical bytes
+ *  - channels 5-7 are word - addresses/counts are for physical words
+ *  - transfers must not cross physical 64K (0-3) or 128K (5-7) boundaries
+ *  - transfer count loaded to registers is 1 less than actual count
+ *  - controller 2 offsets are all even (2x offsets for controller 1)
+ *  - page registers for 5-7 don't use data bit 0, represent 128K pages
+ *  - page registers for 0-3 use bit 0, represent 64K pages
+ *
+ * DMA transfers are limited to the lower 16MB of _physical_ memory.
+ * Note that addresses loaded into registers must be _physical_ addresses,
+ * not logical addresses (which may differ if paging is active).
+ *
+ *  Address mapping for channels 0-3:
+ *
+ *   A23 ... A16 A15 ... A8  A7 ... A0    (Physical addresses)
+ *    |  ...  |   |  ... |   |  ... |
+ *    |  ...  |   |  ... |   |  ... |
+ *    |  ...  |   |  ... |   |  ... |
+ *   P7  ...  P0  A7 ... A0  A7 ... A0
+ * |    Page    | Addr MSB | Addr LSB |   (DMA registers)
+ *
+ *  Address mapping for channels 5-7:
+ *
+ *   A23 ... A17 A16 A15 ... A9 A8 A7 ... A1 A0    (Physical addresses)
+ *    |  ...  |   \   \   ... \  \  \  ... \  \
+ *    |  ...  |    \   \   ... \  \  \  ... \  (not used)
+ *    |  ...  |     \   \   ... \  \  \  ... \
+ *   P7  ...  P1 (0) A7 A6  ... A0 A7 A6 ... A0
+ * |      Page      |  Addr MSB   |  Addr LSB  |   (DMA registers)
+ *
+ * Again, channels 5-7 transfer _physical_ words (16 bits), so addresses
+ * and counts _must_ be word-aligned (the lowest address bit is _ignored_ at
+ * the hardware level, so odd-byte transfers aren't possible).
+ *
+ * Transfer count (_not # bytes_) is limited to 64K, represented as actual
+ * count - 1 : 64K => 0xFFFF, 1 => 0x0000.  Thus, count is always 1 or more,
+ * and up to 128K bytes may be transferred on channels 5-7 in one operation.
+ *
+ */
+
+#define MAX_DMA_CHANNELS	8
+
+#ifdef CONFIG_X86_32
+
+/* The maximum address that we can perform a DMA transfer to on this platform */
+#define MAX_DMA_ADDRESS      (PAGE_OFFSET + 0x1000000)
+
+#else
+
+/* 16MB ISA DMA zone */
+#define MAX_DMA_PFN   ((16 * 1024 * 1024) >> PAGE_SHIFT)
+
+/* 4GB broken PCI/AGP hardware bus master zone */
+#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
+
+/* Compat define for old dma zone */
+#define MAX_DMA_ADDRESS ((unsigned long)__va(MAX_DMA_PFN << PAGE_SHIFT))
+
+#endif
+
+/* 8237 DMA controllers */
+#define IO_DMA1_BASE	0x00	/* 8 bit slave DMA, channels 0..3 */
+#define IO_DMA2_BASE	0xC0	/* 16 bit master DMA, ch 4(=slave input)..7 */
+
+/* DMA controller registers */
+#define DMA1_CMD_REG		0x08	/* command register (w) */
+#define DMA1_STAT_REG		0x08	/* status register (r) */
+#define DMA1_REQ_REG		0x09    /* request register (w) */
+#define DMA1_MASK_REG		0x0A	/* single-channel mask (w) */
+#define DMA1_MODE_REG		0x0B	/* mode register (w) */
+#define DMA1_CLEAR_FF_REG	0x0C	/* clear pointer flip-flop (w) */
+#define DMA1_TEMP_REG		0x0D    /* Temporary Register (r) */
+#define DMA1_RESET_REG		0x0D	/* Master Clear (w) */
+#define DMA1_CLR_MASK_REG       0x0E    /* Clear Mask */
+#define DMA1_MASK_ALL_REG       0x0F    /* all-channels mask (w) */
+
+#define DMA2_CMD_REG		0xD0	/* command register (w) */
+#define DMA2_STAT_REG		0xD0	/* status register (r) */
+#define DMA2_REQ_REG		0xD2    /* request register (w) */
+#define DMA2_MASK_REG		0xD4	/* single-channel mask (w) */
+#define DMA2_MODE_REG		0xD6	/* mode register (w) */
+#define DMA2_CLEAR_FF_REG	0xD8	/* clear pointer flip-flop (w) */
+#define DMA2_TEMP_REG		0xDA    /* Temporary Register (r) */
+#define DMA2_RESET_REG		0xDA	/* Master Clear (w) */
+#define DMA2_CLR_MASK_REG       0xDC    /* Clear Mask */
+#define DMA2_MASK_ALL_REG       0xDE    /* all-channels mask (w) */
+
+#define DMA_ADDR_0		0x00    /* DMA address registers */
+#define DMA_ADDR_1		0x02
+#define DMA_ADDR_2		0x04
+#define DMA_ADDR_3		0x06
+#define DMA_ADDR_4		0xC0
+#define DMA_ADDR_5		0xC4
+#define DMA_ADDR_6		0xC8
+#define DMA_ADDR_7		0xCC
+
+#define DMA_CNT_0		0x01    /* DMA count registers */
+#define DMA_CNT_1		0x03
+#define DMA_CNT_2		0x05
+#define DMA_CNT_3		0x07
+#define DMA_CNT_4		0xC2
+#define DMA_CNT_5		0xC6
+#define DMA_CNT_6		0xCA
+#define DMA_CNT_7		0xCE
+
+#define DMA_PAGE_0		0x87    /* DMA page registers */
+#define DMA_PAGE_1		0x83
+#define DMA_PAGE_2		0x81
+#define DMA_PAGE_3		0x82
+#define DMA_PAGE_5		0x8B
+#define DMA_PAGE_6		0x89
+#define DMA_PAGE_7		0x8A
+
+/* I/O to memory, no autoinit, increment, single mode */
+#define DMA_MODE_READ		0x44
+/* memory to I/O, no autoinit, increment, single mode */
+#define DMA_MODE_WRITE		0x48
+/* pass thru DREQ->HRQ, DACK<-HLDA only */
+#define DMA_MODE_CASCADE	0xC0
+
+#define DMA_AUTOINIT		0x10
+
+
+extern spinlock_t  dma_spin_lock;
+
+static inline unsigned long claim_dma_lock(void)
+{
+	unsigned long flags;
+	spin_lock_irqsave(&dma_spin_lock, flags);
+	return flags;
+}
+
+static inline void release_dma_lock(unsigned long flags)
+{
+	spin_unlock_irqrestore(&dma_spin_lock, flags);
+}
+
+/* enable/disable a specific DMA channel */
+static inline void enable_dma(unsigned int dmanr)
+{
+	if (dmanr <= 3)
+		dma_outb(dmanr, DMA1_MASK_REG);
+	else
+		dma_outb(dmanr & 3, DMA2_MASK_REG);
+}
+
+static inline void disable_dma(unsigned int dmanr)
+{
+	if (dmanr <= 3)
+		dma_outb(dmanr | 4, DMA1_MASK_REG);
+	else
+		dma_outb((dmanr & 3) | 4, DMA2_MASK_REG);
+}
+
+/* Clear the 'DMA Pointer Flip Flop'.
+ * Write 0 for LSB/MSB, 1 for MSB/LSB access.
+ * Use this once to initialize the FF to a known state.
+ * After that, keep track of it. :-)
+ * --- In order to do that, the DMA routines below should ---
+ * --- only be used while holding the DMA lock ! ---
+ */
+static inline void clear_dma_ff(unsigned int dmanr)
+{
+	if (dmanr <= 3)
+		dma_outb(0, DMA1_CLEAR_FF_REG);
+	else
+		dma_outb(0, DMA2_CLEAR_FF_REG);
+}
+
+/* set mode (above) for a specific DMA channel */
+static inline void set_dma_mode(unsigned int dmanr, char mode)
+{
+	if (dmanr <= 3)
+		dma_outb(mode | dmanr, DMA1_MODE_REG);
+	else
+		dma_outb(mode | (dmanr & 3), DMA2_MODE_REG);
+}
+
+/* Set only the page register bits of the transfer address.
+ * This is used for successive transfers when we know the contents of
+ * the lower 16 bits of the DMA current address register, but a 64k boundary
+ * may have been crossed.
+ */
+static inline void set_dma_page(unsigned int dmanr, char pagenr)
+{
+	switch (dmanr) {
+	case 0:
+		dma_outb(pagenr, DMA_PAGE_0);
+		break;
+	case 1:
+		dma_outb(pagenr, DMA_PAGE_1);
+		break;
+	case 2:
+		dma_outb(pagenr, DMA_PAGE_2);
+		break;
+	case 3:
+		dma_outb(pagenr, DMA_PAGE_3);
+		break;
+	case 5:
+		dma_outb(pagenr & 0xfe, DMA_PAGE_5);
+		break;
+	case 6:
+		dma_outb(pagenr & 0xfe, DMA_PAGE_6);
+		break;
+	case 7:
+		dma_outb(pagenr & 0xfe, DMA_PAGE_7);
+		break;
+	}
+}
+
+
+/* Set transfer address & page bits for specific DMA channel.
+ * Assumes dma flipflop is clear.
+ */
+static inline void set_dma_addr(unsigned int dmanr, unsigned int a)
+{
+	set_dma_page(dmanr, a>>16);
+	if (dmanr <= 3)  {
+		dma_outb(a & 0xff, ((dmanr & 3) << 1) + IO_DMA1_BASE);
+		dma_outb((a >> 8) & 0xff, ((dmanr & 3) << 1) + IO_DMA1_BASE);
+	}  else  {
+		dma_outb((a >> 1) & 0xff, ((dmanr & 3) << 2) + IO_DMA2_BASE);
+		dma_outb((a >> 9) & 0xff, ((dmanr & 3) << 2) + IO_DMA2_BASE);
+	}
+}
+
+
+/* Set transfer size (max 64k for DMA0..3, 128k for DMA5..7) for
+ * a specific DMA channel.
+ * You must ensure the parameters are valid.
+ * NOTE: from a manual: "the number of transfers is one more
+ * than the initial word count"! This is taken into account.
+ * Assumes dma flip-flop is clear.
+ * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7.
+ */
+static inline void set_dma_count(unsigned int dmanr, unsigned int count)
+{
+	count--;
+	if (dmanr <= 3)  {
+		dma_outb(count & 0xff, ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE);
+		dma_outb((count >> 8) & 0xff,
+			 ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE);
+	} else {
+		dma_outb((count >> 1) & 0xff,
+			 ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE);
+		dma_outb((count >> 9) & 0xff,
+			 ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE);
+	}
+}
+
+
+/* Get DMA residue count. After a DMA transfer, this
+ * should return zero. Reading this while a DMA transfer is
+ * still in progress will return unpredictable results.
+ * If called before the channel has been used, it may return 1.
+ * Otherwise, it returns the number of _bytes_ left to transfer.
+ *
+ * Assumes DMA flip-flop is clear.
+ */
+static inline int get_dma_residue(unsigned int dmanr)
+{
+	unsigned int io_port;
+	/* using short to get 16-bit wrap around */
+	unsigned short count;
+
+	io_port = (dmanr <= 3) ? ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE
+		: ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE;
+
+	count = 1 + dma_inb(io_port);
+	count += dma_inb(io_port) << 8;
+
+	return (dmanr <= 3) ? count : (count << 1);
+}
+
+
+/* These are in kernel/dma.c: */
+extern int request_dma(unsigned int dmanr, const char *device_id);
+extern void free_dma(unsigned int dmanr);
+
+/* From PCI */
+
+#ifdef CONFIG_PCI
+extern int isa_dma_bridge_buggy;
+#else
+#define isa_dma_bridge_buggy	(0)
+#endif
+
+#endif /* ASM_X86__DMA_H */
diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h
new file mode 100644
index 000000000000..1cff6fe81fa5
--- /dev/null
+++ b/arch/x86/include/asm/dmi.h
@@ -0,0 +1,26 @@
+#ifndef ASM_X86__DMI_H
+#define ASM_X86__DMI_H
+
+#include <asm/io.h>
+
+#define DMI_MAX_DATA 2048
+
+extern int dmi_alloc_index;
+extern char dmi_alloc_data[DMI_MAX_DATA];
+
+/* This is so early that there is no good way to allocate dynamic memory.
+   Allocate data in an BSS array. */
+static inline void *dmi_alloc(unsigned len)
+{
+	int idx = dmi_alloc_index;
+	if ((dmi_alloc_index + len) > DMI_MAX_DATA)
+		return NULL;
+	dmi_alloc_index += len;
+	return dmi_alloc_data + idx;
+}
+
+/* Use early IO mappings for DMI because it's initialized early */
+#define dmi_ioremap early_ioremap
+#define dmi_iounmap early_iounmap
+
+#endif /* ASM_X86__DMI_H */
diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h
new file mode 100644
index 000000000000..c3c953a45b21
--- /dev/null
+++ b/arch/x86/include/asm/ds.h
@@ -0,0 +1,238 @@
+/*
+ * Debug Store (DS) support
+ *
+ * This provides a low-level interface to the hardware's Debug Store
+ * feature that is used for branch trace store (BTS) and
+ * precise-event based sampling (PEBS).
+ *
+ * It manages:
+ * - per-thread and per-cpu allocation of BTS and PEBS
+ * - buffer memory allocation (optional)
+ * - buffer overflow handling
+ * - buffer access
+ *
+ * It assumes:
+ * - get_task_struct on all parameter tasks
+ * - current is allowed to trace parameter tasks
+ *
+ *
+ * Copyright (C) 2007-2008 Intel Corporation.
+ * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
+ */
+
+#ifndef ASM_X86__DS_H
+#define ASM_X86__DS_H
+
+#ifdef CONFIG_X86_DS
+
+#include <linux/types.h>
+#include <linux/init.h>
+
+
+struct task_struct;
+
+/*
+ * Request BTS or PEBS
+ *
+ * Due to alignement constraints, the actual buffer may be slightly
+ * smaller than the requested or provided buffer.
+ *
+ * Returns 0 on success; -Eerrno otherwise
+ *
+ * task: the task to request recording for;
+ *       NULL for per-cpu recording on the current cpu
+ * base: the base pointer for the (non-pageable) buffer;
+ *       NULL if buffer allocation requested
+ * size: the size of the requested or provided buffer
+ * ovfl: pointer to a function to be called on buffer overflow;
+ *       NULL if cyclic buffer requested
+ */
+typedef void (*ds_ovfl_callback_t)(struct task_struct *);
+extern int ds_request_bts(struct task_struct *task, void *base, size_t size,
+			  ds_ovfl_callback_t ovfl);
+extern int ds_request_pebs(struct task_struct *task, void *base, size_t size,
+			   ds_ovfl_callback_t ovfl);
+
+/*
+ * Release BTS or PEBS resources
+ *
+ * Frees buffers allocated on ds_request.
+ *
+ * Returns 0 on success; -Eerrno otherwise
+ *
+ * task: the task to release resources for;
+ *       NULL to release resources for the current cpu
+ */
+extern int ds_release_bts(struct task_struct *task);
+extern int ds_release_pebs(struct task_struct *task);
+
+/*
+ * Return the (array) index of the write pointer.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * Returns -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * pos (out): if not NULL, will hold the result
+ */
+extern int ds_get_bts_index(struct task_struct *task, size_t *pos);
+extern int ds_get_pebs_index(struct task_struct *task, size_t *pos);
+
+/*
+ * Return the (array) index one record beyond the end of the array.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * Returns -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * pos (out): if not NULL, will hold the result
+ */
+extern int ds_get_bts_end(struct task_struct *task, size_t *pos);
+extern int ds_get_pebs_end(struct task_struct *task, size_t *pos);
+
+/*
+ * Provide a pointer to the BTS/PEBS record at parameter index.
+ * (assuming an array of BTS/PEBS records)
+ *
+ * The pointer points directly into the buffer. The user is
+ * responsible for copying the record.
+ *
+ * Returns the size of a single record on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * index: the index of the requested record
+ * record (out): pointer to the requested record
+ */
+extern int ds_access_bts(struct task_struct *task,
+			 size_t index, const void **record);
+extern int ds_access_pebs(struct task_struct *task,
+			  size_t index, const void **record);
+
+/*
+ * Write one or more BTS/PEBS records at the write pointer index and
+ * advance the write pointer.
+ *
+ * If size is not a multiple of the record size, trailing bytes are
+ * zeroed out.
+ *
+ * May result in one or more overflow notifications.
+ *
+ * If called during overflow handling, that is, with index >=
+ * interrupt threshold, the write will wrap around.
+ *
+ * An overflow notification is given if and when the interrupt
+ * threshold is reached during or after the write.
+ *
+ * Returns the number of bytes written or -Eerrno.
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * buffer: the buffer to write
+ * size: the size of the buffer
+ */
+extern int ds_write_bts(struct task_struct *task,
+			const void *buffer, size_t size);
+extern int ds_write_pebs(struct task_struct *task,
+			 const void *buffer, size_t size);
+
+/*
+ * Same as ds_write_bts/pebs, but omit ownership checks.
+ *
+ * This is needed to have some other task than the owner of the
+ * BTS/PEBS buffer or the parameter task itself write into the
+ * respective buffer.
+ */
+extern int ds_unchecked_write_bts(struct task_struct *task,
+				  const void *buffer, size_t size);
+extern int ds_unchecked_write_pebs(struct task_struct *task,
+				   const void *buffer, size_t size);
+
+/*
+ * Reset the write pointer of the BTS/PEBS buffer.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ */
+extern int ds_reset_bts(struct task_struct *task);
+extern int ds_reset_pebs(struct task_struct *task);
+
+/*
+ * Clear the BTS/PEBS buffer and reset the write pointer.
+ * The entire buffer will be zeroed out.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ */
+extern int ds_clear_bts(struct task_struct *task);
+extern int ds_clear_pebs(struct task_struct *task);
+
+/*
+ * Provide the PEBS counter reset value.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * value (out): the counter reset value
+ */
+extern int ds_get_pebs_reset(struct task_struct *task, u64 *value);
+
+/*
+ * Set the PEBS counter reset value.
+ *
+ * Returns 0 on success; -Eerrno on error
+ *
+ * task: the task to access;
+ *       NULL to access the current cpu
+ * value: the new counter reset value
+ */
+extern int ds_set_pebs_reset(struct task_struct *task, u64 value);
+
+/*
+ * Initialization
+ */
+struct cpuinfo_x86;
+extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
+
+
+
+/*
+ * The DS context - part of struct thread_struct.
+ */
+struct ds_context {
+	/* pointer to the DS configuration; goes into MSR_IA32_DS_AREA */
+	unsigned char *ds;
+	/* the owner of the BTS and PEBS configuration, respectively */
+	struct task_struct *owner[2];
+	/* buffer overflow notification function for BTS and PEBS */
+	ds_ovfl_callback_t callback[2];
+	/* the original buffer address */
+	void *buffer[2];
+	/* the number of allocated pages for on-request allocated buffers */
+	unsigned int pages[2];
+	/* use count */
+	unsigned long count;
+	/* a pointer to the context location inside the thread_struct
+	 * or the per_cpu context array */
+	struct ds_context **this;
+	/* a pointer to the task owning this context, or NULL, if the
+	 * context is owned by a cpu */
+	struct task_struct *task;
+};
+
+/* called by exit_thread() to free leftover contexts */
+extern void ds_free(struct ds_context *context);
+
+#else /* CONFIG_X86_DS */
+
+#define ds_init_intel(config) do {} while (0)
+
+#endif /* CONFIG_X86_DS */
+#endif /* ASM_X86__DS_H */
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
new file mode 100644
index 000000000000..21d1bc32ad7c
--- /dev/null
+++ b/arch/x86/include/asm/dwarf2.h
@@ -0,0 +1,61 @@
+#ifndef ASM_X86__DWARF2_H
+#define ASM_X86__DWARF2_H
+
+#ifndef __ASSEMBLY__
+#warning "asm/dwarf2.h should be only included in pure assembly files"
+#endif
+
+/*
+   Macros for dwarf2 CFI unwind table entries.
+   See "as.info" for details on these pseudo ops. Unfortunately
+   they are only supported in very new binutils, so define them
+   away for older version.
+ */
+
+#ifdef CONFIG_AS_CFI
+
+#define CFI_STARTPROC .cfi_startproc
+#define CFI_ENDPROC .cfi_endproc
+#define CFI_DEF_CFA .cfi_def_cfa
+#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
+#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
+#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
+#define CFI_OFFSET .cfi_offset
+#define CFI_REL_OFFSET .cfi_rel_offset
+#define CFI_REGISTER .cfi_register
+#define CFI_RESTORE .cfi_restore
+#define CFI_REMEMBER_STATE .cfi_remember_state
+#define CFI_RESTORE_STATE .cfi_restore_state
+#define CFI_UNDEFINED .cfi_undefined
+
+#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
+#define CFI_SIGNAL_FRAME .cfi_signal_frame
+#else
+#define CFI_SIGNAL_FRAME
+#endif
+
+#else
+
+/* Due to the structure of pre-exisiting code, don't use assembler line
+   comment character # to ignore the arguments. Instead, use a dummy macro. */
+.macro cfi_ignore a=0, b=0, c=0, d=0
+.endm
+
+#define CFI_STARTPROC	cfi_ignore
+#define CFI_ENDPROC	cfi_ignore
+#define CFI_DEF_CFA	cfi_ignore
+#define CFI_DEF_CFA_REGISTER	cfi_ignore
+#define CFI_DEF_CFA_OFFSET	cfi_ignore
+#define CFI_ADJUST_CFA_OFFSET	cfi_ignore
+#define CFI_OFFSET	cfi_ignore
+#define CFI_REL_OFFSET	cfi_ignore
+#define CFI_REGISTER	cfi_ignore
+#define CFI_RESTORE	cfi_ignore
+#define CFI_REMEMBER_STATE cfi_ignore
+#define CFI_RESTORE_STATE cfi_ignore
+#define CFI_UNDEFINED cfi_ignore
+#define CFI_SIGNAL_FRAME cfi_ignore
+
+#endif
+
+#endif /* ASM_X86__DWARF2_H */
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
new file mode 100644
index 000000000000..5abbdec06bd2
--- /dev/null
+++ b/arch/x86/include/asm/e820.h
@@ -0,0 +1,146 @@
+#ifndef ASM_X86__E820_H
+#define ASM_X86__E820_H
+#define E820MAP	0x2d0		/* our map */
+#define E820MAX	128		/* number of entries in E820MAP */
+
+/*
+ * Legacy E820 BIOS limits us to 128 (E820MAX) nodes due to the
+ * constrained space in the zeropage.  If we have more nodes than
+ * that, and if we've booted off EFI firmware, then the EFI tables
+ * passed us from the EFI firmware can list more nodes.  Size our
+ * internal memory map tables to have room for these additional
+ * nodes, based on up to three entries per node for which the
+ * kernel was built: MAX_NUMNODES == (1 << CONFIG_NODES_SHIFT),
+ * plus E820MAX, allowing space for the possible duplicate E820
+ * entries that might need room in the same arrays, prior to the
+ * call to sanitize_e820_map() to remove duplicates.  The allowance
+ * of three memory map entries per node is "enough" entries for
+ * the initial hardware platform motivating this mechanism to make
+ * use of additional EFI map entries.  Future platforms may want
+ * to allow more than three entries per node or otherwise refine
+ * this size.
+ */
+
+/*
+ * Odd: 'make headers_check' complains about numa.h if I try
+ * to collapse the next two #ifdef lines to a single line:
+ *	#if defined(__KERNEL__) && defined(CONFIG_EFI)
+ */
+#ifdef __KERNEL__
+#ifdef CONFIG_EFI
+#include <linux/numa.h>
+#define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES)
+#else	/* ! CONFIG_EFI */
+#define E820_X_MAX E820MAX
+#endif
+#else	/* ! __KERNEL__ */
+#define E820_X_MAX E820MAX
+#endif
+
+#define E820NR	0x1e8		/* # entries in E820MAP */
+
+#define E820_RAM	1
+#define E820_RESERVED	2
+#define E820_ACPI	3
+#define E820_NVS	4
+#define E820_UNUSABLE	5
+
+/* reserved RAM used by kernel itself */
+#define E820_RESERVED_KERN        128
+
+#ifndef __ASSEMBLY__
+struct e820entry {
+	__u64 addr;	/* start of memory segment */
+	__u64 size;	/* size of memory segment */
+	__u32 type;	/* type of memory segment */
+} __attribute__((packed));
+
+struct e820map {
+	__u32 nr_map;
+	struct e820entry map[E820_X_MAX];
+};
+
+#ifdef __KERNEL__
+/* see comment in arch/x86/kernel/e820.c */
+extern struct e820map e820;
+extern struct e820map e820_saved;
+
+extern unsigned long pci_mem_start;
+extern int e820_any_mapped(u64 start, u64 end, unsigned type);
+extern int e820_all_mapped(u64 start, u64 end, unsigned type);
+extern void e820_add_region(u64 start, u64 size, int type);
+extern void e820_print_map(char *who);
+extern int
+sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, int *pnr_map);
+extern u64 e820_update_range(u64 start, u64 size, unsigned old_type,
+			       unsigned new_type);
+extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
+			     int checktype);
+extern void update_e820(void);
+extern void e820_setup_gap(void);
+extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
+			unsigned long start_addr, unsigned long long end_addr);
+struct setup_data;
+extern void parse_e820_ext(struct setup_data *data, unsigned long pa_data);
+
+#if defined(CONFIG_X86_64) || \
+	(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
+extern void e820_mark_nosave_regions(unsigned long limit_pfn);
+#else
+static inline void e820_mark_nosave_regions(unsigned long limit_pfn)
+{
+}
+#endif
+
+#ifdef CONFIG_MEMTEST
+extern void early_memtest(unsigned long start, unsigned long end);
+#else
+static inline void early_memtest(unsigned long start, unsigned long end)
+{
+}
+#endif
+
+extern unsigned long end_user_pfn;
+
+extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
+extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
+extern void reserve_early(u64 start, u64 end, char *name);
+extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
+extern void free_early(u64 start, u64 end);
+extern void early_res_to_bootmem(u64 start, u64 end);
+extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
+
+extern unsigned long e820_end_of_ram_pfn(void);
+extern unsigned long e820_end_of_low_ram_pfn(void);
+extern int e820_find_active_region(const struct e820entry *ei,
+				  unsigned long start_pfn,
+				  unsigned long last_pfn,
+				  unsigned long *ei_startpfn,
+				  unsigned long *ei_endpfn);
+extern void e820_register_active_regions(int nid, unsigned long start_pfn,
+					 unsigned long end_pfn);
+extern u64 e820_hole_size(u64 start, u64 end);
+extern void finish_e820_parsing(void);
+extern void e820_reserve_resources(void);
+extern void e820_reserve_resources_late(void);
+extern void setup_memory_map(void);
+extern char *default_machine_specific_memory_setup(void);
+extern char *machine_specific_memory_setup(void);
+extern char *memory_setup(void);
+#endif /* __KERNEL__ */
+#endif /* __ASSEMBLY__ */
+
+#define ISA_START_ADDRESS	0xa0000
+#define ISA_END_ADDRESS		0x100000
+#define is_ISA_range(s, e) ((s) >= ISA_START_ADDRESS && (e) < ISA_END_ADDRESS)
+
+#define BIOS_BEGIN		0x000a0000
+#define BIOS_END		0x00100000
+
+#ifdef __KERNEL__
+#include <linux/ioport.h>
+
+#define HIGH_MEMORY	(1024*1024)
+#endif /* __KERNEL__ */
+
+#endif /* ASM_X86__E820_H */
diff --git a/arch/x86/include/asm/edac.h b/arch/x86/include/asm/edac.h
new file mode 100644
index 000000000000..9493c5b27bbd
--- /dev/null
+++ b/arch/x86/include/asm/edac.h
@@ -0,0 +1,18 @@
+#ifndef ASM_X86__EDAC_H
+#define ASM_X86__EDAC_H
+
+/* ECC atomic, DMA, SMP and interrupt safe scrub function */
+
+static inline void atomic_scrub(void *va, u32 size)
+{
+	u32 i, *virt_addr = va;
+
+	/*
+	 * Very carefully read and write to memory atomically so we
+	 * are interrupt, DMA and SMP safe.
+	 */
+	for (i = 0; i < size / 4; i++, virt_addr++)
+		asm volatile("lock; addl $0, %0"::"m" (*virt_addr));
+}
+
+#endif /* ASM_X86__EDAC_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
new file mode 100644
index 000000000000..313438e63348
--- /dev/null
+++ b/arch/x86/include/asm/efi.h
@@ -0,0 +1,110 @@
+#ifndef ASM_X86__EFI_H
+#define ASM_X86__EFI_H
+
+#ifdef CONFIG_X86_32
+
+extern unsigned long asmlinkage efi_call_phys(void *, ...);
+
+#define efi_call_phys0(f)		efi_call_phys(f)
+#define efi_call_phys1(f, a1)		efi_call_phys(f, a1)
+#define efi_call_phys2(f, a1, a2)	efi_call_phys(f, a1, a2)
+#define efi_call_phys3(f, a1, a2, a3)	efi_call_phys(f, a1, a2, a3)
+#define efi_call_phys4(f, a1, a2, a3, a4)	\
+	efi_call_phys(f, a1, a2, a3, a4)
+#define efi_call_phys5(f, a1, a2, a3, a4, a5)	\
+	efi_call_phys(f, a1, a2, a3, a4, a5)
+#define efi_call_phys6(f, a1, a2, a3, a4, a5, a6)	\
+	efi_call_phys(f, a1, a2, a3, a4, a5, a6)
+/*
+ * Wrap all the virtual calls in a way that forces the parameters on the stack.
+ */
+
+#define efi_call_virt(f, args...) \
+	((efi_##f##_t __attribute__((regparm(0)))*)efi.systab->runtime->f)(args)
+
+#define efi_call_virt0(f)		efi_call_virt(f)
+#define efi_call_virt1(f, a1)		efi_call_virt(f, a1)
+#define efi_call_virt2(f, a1, a2)	efi_call_virt(f, a1, a2)
+#define efi_call_virt3(f, a1, a2, a3)	efi_call_virt(f, a1, a2, a3)
+#define efi_call_virt4(f, a1, a2, a3, a4)	\
+	efi_call_virt(f, a1, a2, a3, a4)
+#define efi_call_virt5(f, a1, a2, a3, a4, a5)	\
+	efi_call_virt(f, a1, a2, a3, a4, a5)
+#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)	\
+	efi_call_virt(f, a1, a2, a3, a4, a5, a6)
+
+#define efi_ioremap(addr, size)			ioremap_cache(addr, size)
+
+#else /* !CONFIG_X86_32 */
+
+#define MAX_EFI_IO_PAGES	100
+
+extern u64 efi_call0(void *fp);
+extern u64 efi_call1(void *fp, u64 arg1);
+extern u64 efi_call2(void *fp, u64 arg1, u64 arg2);
+extern u64 efi_call3(void *fp, u64 arg1, u64 arg2, u64 arg3);
+extern u64 efi_call4(void *fp, u64 arg1, u64 arg2, u64 arg3, u64 arg4);
+extern u64 efi_call5(void *fp, u64 arg1, u64 arg2, u64 arg3,
+		     u64 arg4, u64 arg5);
+extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
+		     u64 arg4, u64 arg5, u64 arg6);
+
+#define efi_call_phys0(f)			\
+	efi_call0((void *)(f))
+#define efi_call_phys1(f, a1)			\
+	efi_call1((void *)(f), (u64)(a1))
+#define efi_call_phys2(f, a1, a2)			\
+	efi_call2((void *)(f), (u64)(a1), (u64)(a2))
+#define efi_call_phys3(f, a1, a2, a3)				\
+	efi_call3((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3))
+#define efi_call_phys4(f, a1, a2, a3, a4)				\
+	efi_call4((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3),		\
+		  (u64)(a4))
+#define efi_call_phys5(f, a1, a2, a3, a4, a5)				\
+	efi_call5((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3),		\
+		  (u64)(a4), (u64)(a5))
+#define efi_call_phys6(f, a1, a2, a3, a4, a5, a6)			\
+	efi_call6((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3),		\
+		  (u64)(a4), (u64)(a5), (u64)(a6))
+
+#define efi_call_virt0(f)				\
+	efi_call0((void *)(efi.systab->runtime->f))
+#define efi_call_virt1(f, a1)					\
+	efi_call1((void *)(efi.systab->runtime->f), (u64)(a1))
+#define efi_call_virt2(f, a1, a2)					\
+	efi_call2((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2))
+#define efi_call_virt3(f, a1, a2, a3)					\
+	efi_call3((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+		  (u64)(a3))
+#define efi_call_virt4(f, a1, a2, a3, a4)				\
+	efi_call4((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+		  (u64)(a3), (u64)(a4))
+#define efi_call_virt5(f, a1, a2, a3, a4, a5)				\
+	efi_call5((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+		  (u64)(a3), (u64)(a4), (u64)(a5))
+#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)			\
+	efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
+		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
+
+extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size);
+
+#endif /* CONFIG_X86_32 */
+
+extern void efi_reserve_early(void);
+extern void efi_call_phys_prelog(void);
+extern void efi_call_phys_epilog(void);
+
+#ifndef CONFIG_EFI
+/*
+ * IF EFI is not configured, have the EFI calls return -ENOSYS.
+ */
+#define efi_call0(_f)					(-ENOSYS)
+#define efi_call1(_f, _a1)				(-ENOSYS)
+#define efi_call2(_f, _a1, _a2)				(-ENOSYS)
+#define efi_call3(_f, _a1, _a2, _a3)			(-ENOSYS)
+#define efi_call4(_f, _a1, _a2, _a3, _a4)		(-ENOSYS)
+#define efi_call5(_f, _a1, _a2, _a3, _a4, _a5)		(-ENOSYS)
+#define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6)	(-ENOSYS)
+#endif /* CONFIG_EFI */
+
+#endif /* ASM_X86__EFI_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
new file mode 100644
index 000000000000..26bc15f01e78
--- /dev/null
+++ b/arch/x86/include/asm/elf.h
@@ -0,0 +1,336 @@
+#ifndef ASM_X86__ELF_H
+#define ASM_X86__ELF_H
+
+/*
+ * ELF register definitions..
+ */
+
+#include <asm/ptrace.h>
+#include <asm/user.h>
+#include <asm/auxvec.h>
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof(struct user_regs_struct) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_i387_struct elf_fpregset_t;
+
+#ifdef __i386__
+
+typedef struct user_fxsr_struct elf_fpxregset_t;
+
+#define R_386_NONE	0
+#define R_386_32	1
+#define R_386_PC32	2
+#define R_386_GOT32	3
+#define R_386_PLT32	4
+#define R_386_COPY	5
+#define R_386_GLOB_DAT	6
+#define R_386_JMP_SLOT	7
+#define R_386_RELATIVE	8
+#define R_386_GOTOFF	9
+#define R_386_GOTPC	10
+#define R_386_NUM	11
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS	ELFCLASS32
+#define ELF_DATA	ELFDATA2LSB
+#define ELF_ARCH	EM_386
+
+#else
+
+/* x86-64 relocation types */
+#define R_X86_64_NONE		0	/* No reloc */
+#define R_X86_64_64		1	/* Direct 64 bit  */
+#define R_X86_64_PC32		2	/* PC relative 32 bit signed */
+#define R_X86_64_GOT32		3	/* 32 bit GOT entry */
+#define R_X86_64_PLT32		4	/* 32 bit PLT address */
+#define R_X86_64_COPY		5	/* Copy symbol at runtime */
+#define R_X86_64_GLOB_DAT	6	/* Create GOT entry */
+#define R_X86_64_JUMP_SLOT	7	/* Create PLT entry */
+#define R_X86_64_RELATIVE	8	/* Adjust by program base */
+#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative
+					   offset to GOT */
+#define R_X86_64_32		10	/* Direct 32 bit zero extended */
+#define R_X86_64_32S		11	/* Direct 32 bit sign extended */
+#define R_X86_64_16		12	/* Direct 16 bit zero extended */
+#define R_X86_64_PC16		13	/* 16 bit sign extended pc relative */
+#define R_X86_64_8		14	/* Direct 8 bit sign extended  */
+#define R_X86_64_PC8		15	/* 8 bit sign extended pc relative */
+
+#define R_X86_64_NUM		16
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS	ELFCLASS64
+#define ELF_DATA	ELFDATA2LSB
+#define ELF_ARCH	EM_X86_64
+
+#endif
+
+#include <asm/vdso.h>
+
+extern unsigned int vdso_enabled;
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch_ia32(x) \
+	(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
+
+#include <asm/processor.h>
+#include <asm/system.h>
+
+#ifdef CONFIG_X86_32
+#include <asm/desc.h>
+
+#define elf_check_arch(x)	elf_check_arch_ia32(x)
+
+/* SVR4/i386 ABI (pages 3-31, 3-32) says that when the program starts %edx
+   contains a pointer to a function which might be registered using `atexit'.
+   This provides a mean for the dynamic linker to call DT_FINI functions for
+   shared libraries that have been loaded before the code runs.
+
+   A value of 0 tells we have no such handler.
+
+   We might as well make sure everything else is cleared too (except for %esp),
+   just to make things more deterministic.
+ */
+#define ELF_PLAT_INIT(_r, load_addr)		\
+	do {					\
+	_r->bx = 0; _r->cx = 0; _r->dx = 0;	\
+	_r->si = 0; _r->di = 0; _r->bp = 0;	\
+	_r->ax = 0;				\
+} while (0)
+
+/*
+ * regs is struct pt_regs, pr_reg is elf_gregset_t (which is
+ * now struct_user_regs, they are different)
+ */
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs)	\
+do {						\
+	pr_reg[0] = regs->bx;			\
+	pr_reg[1] = regs->cx;			\
+	pr_reg[2] = regs->dx;			\
+	pr_reg[3] = regs->si;			\
+	pr_reg[4] = regs->di;			\
+	pr_reg[5] = regs->bp;			\
+	pr_reg[6] = regs->ax;			\
+	pr_reg[7] = regs->ds & 0xffff;		\
+	pr_reg[8] = regs->es & 0xffff;		\
+	pr_reg[9] = regs->fs & 0xffff;		\
+	savesegment(gs, pr_reg[10]);		\
+	pr_reg[11] = regs->orig_ax;		\
+	pr_reg[12] = regs->ip;			\
+	pr_reg[13] = regs->cs & 0xffff;		\
+	pr_reg[14] = regs->flags;		\
+	pr_reg[15] = regs->sp;			\
+	pr_reg[16] = regs->ss & 0xffff;		\
+} while (0);
+
+#define ELF_PLATFORM	(utsname()->machine)
+#define set_personality_64bit()	do { } while (0)
+
+#else /* CONFIG_X86_32 */
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x)			\
+	((x)->e_machine == EM_X86_64)
+
+#define compat_elf_check_arch(x)	elf_check_arch_ia32(x)
+
+static inline void start_ia32_thread(struct pt_regs *regs, u32 ip, u32 sp)
+{
+	loadsegment(fs, 0);
+	loadsegment(ds, __USER32_DS);
+	loadsegment(es, __USER32_DS);
+	load_gs_index(0);
+	regs->ip = ip;
+	regs->sp = sp;
+	regs->flags = X86_EFLAGS_IF;
+	regs->cs = __USER32_CS;
+	regs->ss = __USER32_DS;
+}
+
+static inline void elf_common_init(struct thread_struct *t,
+				   struct pt_regs *regs, const u16 ds)
+{
+	regs->ax = regs->bx = regs->cx = regs->dx = 0;
+	regs->si = regs->di = regs->bp = 0;
+	regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0;
+	regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
+	t->fs = t->gs = 0;
+	t->fsindex = t->gsindex = 0;
+	t->ds = t->es = ds;
+}
+
+#define ELF_PLAT_INIT(_r, load_addr)			\
+do {							\
+	elf_common_init(&current->thread, _r, 0);	\
+	clear_thread_flag(TIF_IA32);			\
+} while (0)
+
+#define	COMPAT_ELF_PLAT_INIT(regs, load_addr)		\
+	elf_common_init(&current->thread, regs, __USER_DS)
+
+#define	compat_start_thread(regs, ip, sp)		\
+do {							\
+	start_ia32_thread(regs, ip, sp);		\
+	set_fs(USER_DS);				\
+} while (0)
+
+#define COMPAT_SET_PERSONALITY(ex)			\
+do {							\
+	if (test_thread_flag(TIF_IA32))			\
+		clear_thread_flag(TIF_ABI_PENDING);	\
+	else						\
+		set_thread_flag(TIF_ABI_PENDING);	\
+	current->personality |= force_personality32;	\
+} while (0)
+
+#define COMPAT_ELF_PLATFORM			("i686")
+
+/*
+ * regs is struct pt_regs, pr_reg is elf_gregset_t (which is
+ * now struct_user_regs, they are different). Assumes current is the process
+ * getting dumped.
+ */
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs)			\
+do {								\
+	unsigned v;						\
+	(pr_reg)[0] = (regs)->r15;				\
+	(pr_reg)[1] = (regs)->r14;				\
+	(pr_reg)[2] = (regs)->r13;				\
+	(pr_reg)[3] = (regs)->r12;				\
+	(pr_reg)[4] = (regs)->bp;				\
+	(pr_reg)[5] = (regs)->bx;				\
+	(pr_reg)[6] = (regs)->r11;				\
+	(pr_reg)[7] = (regs)->r10;				\
+	(pr_reg)[8] = (regs)->r9;				\
+	(pr_reg)[9] = (regs)->r8;				\
+	(pr_reg)[10] = (regs)->ax;				\
+	(pr_reg)[11] = (regs)->cx;				\
+	(pr_reg)[12] = (regs)->dx;				\
+	(pr_reg)[13] = (regs)->si;				\
+	(pr_reg)[14] = (regs)->di;				\
+	(pr_reg)[15] = (regs)->orig_ax;				\
+	(pr_reg)[16] = (regs)->ip;				\
+	(pr_reg)[17] = (regs)->cs;				\
+	(pr_reg)[18] = (regs)->flags;				\
+	(pr_reg)[19] = (regs)->sp;				\
+	(pr_reg)[20] = (regs)->ss;				\
+	(pr_reg)[21] = current->thread.fs;			\
+	(pr_reg)[22] = current->thread.gs;			\
+	asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v;	\
+	asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v;	\
+	asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v;	\
+	asm("movl %%gs,%0" : "=r" (v)); (pr_reg)[26] = v;	\
+} while (0);
+
+/* I'm not sure if we can use '-' here */
+#define ELF_PLATFORM       ("x86_64")
+extern void set_personality_64bit(void);
+extern unsigned int sysctl_vsyscall32;
+extern int force_personality32;
+
+#endif /* !CONFIG_X86_32 */
+
+#define CORE_DUMP_USE_REGSET
+#define USE_ELF_CORE_DUMP
+#define ELF_EXEC_PAGESIZE	4096
+
+/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
+   use of this is to invoke "./ld.so someprog" to test out a new version of
+   the loader.  We need to make sure that it is out of the way of the program
+   that it will "exec", and that there is sufficient room for the brk.  */
+
+#define ELF_ET_DYN_BASE		(TASK_SIZE / 3 * 2)
+
+/* This yields a mask that user programs can use to figure out what
+   instruction set this CPU supports.  This could be done in user space,
+   but it's not easy, and we've already done it here.  */
+
+#define ELF_HWCAP		(boot_cpu_data.x86_capability[0])
+
+/* This yields a string that ld.so will use to load implementation
+   specific libraries for optimization.  This is more specific in
+   intent than poking at uname or /proc/cpuinfo.
+
+   For the moment, we have only optimizations for the Intel generations,
+   but that could change... */
+
+#define SET_PERSONALITY(ex) set_personality_64bit()
+
+/*
+ * An executable for which elf_read_implies_exec() returns TRUE will
+ * have the READ_IMPLIES_EXEC personality flag set automatically.
+ */
+#define elf_read_implies_exec(ex, executable_stack)	\
+	(executable_stack != EXSTACK_DISABLE_X)
+
+struct task_struct;
+
+#define	ARCH_DLINFO_IA32(vdso_enabled)					\
+do {									\
+	if (vdso_enabled) {						\
+		NEW_AUX_ENT(AT_SYSINFO,	VDSO_ENTRY);			\
+		NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE);	\
+	}								\
+} while (0)
+
+#ifdef CONFIG_X86_32
+
+#define VDSO_HIGH_BASE		(__fix_to_virt(FIX_VDSO))
+
+#define ARCH_DLINFO		ARCH_DLINFO_IA32(vdso_enabled)
+
+/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
+
+#else /* CONFIG_X86_32 */
+
+#define VDSO_HIGH_BASE		0xffffe000U /* CONFIG_COMPAT_VDSO address */
+
+/* 1GB for 64bit, 8MB for 32bit */
+#define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff)
+
+#define ARCH_DLINFO							\
+do {									\
+	if (vdso_enabled)						\
+		NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
+			    (unsigned long)current->mm->context.vdso);	\
+} while (0)
+
+#define AT_SYSINFO		32
+
+#define COMPAT_ARCH_DLINFO	ARCH_DLINFO_IA32(sysctl_vsyscall32)
+
+#define COMPAT_ELF_ET_DYN_BASE	(TASK_UNMAPPED_BASE + 0x1000000)
+
+#endif /* !CONFIG_X86_32 */
+
+#define VDSO_CURRENT_BASE	((unsigned long)current->mm->context.vdso)
+
+#define VDSO_ENTRY							\
+	((unsigned long)VDSO32_SYMBOL(VDSO_CURRENT_BASE, vsyscall))
+
+struct linux_binprm;
+
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+extern int arch_setup_additional_pages(struct linux_binprm *bprm,
+				       int executable_stack);
+
+extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
+#define compat_arch_setup_additional_pages	syscall32_setup_pages
+
+extern unsigned long arch_randomize_brk(struct mm_struct *mm);
+#define arch_randomize_brk arch_randomize_brk
+
+#endif /* ASM_X86__ELF_H */
diff --git a/arch/x86/include/asm/emergency-restart.h b/arch/x86/include/asm/emergency-restart.h
new file mode 100644
index 000000000000..190d0d8b71e3
--- /dev/null
+++ b/arch/x86/include/asm/emergency-restart.h
@@ -0,0 +1,18 @@
+#ifndef ASM_X86__EMERGENCY_RESTART_H
+#define ASM_X86__EMERGENCY_RESTART_H
+
+enum reboot_type {
+	BOOT_TRIPLE = 't',
+	BOOT_KBD = 'k',
+#ifdef CONFIG_X86_32
+	BOOT_BIOS = 'b',
+#endif
+	BOOT_ACPI = 'a',
+	BOOT_EFI = 'e'
+};
+
+extern enum reboot_type reboot_type;
+
+extern void machine_emergency_restart(void);
+
+#endif /* ASM_X86__EMERGENCY_RESTART_H */
diff --git a/arch/x86/include/asm/errno.h b/arch/x86/include/asm/errno.h
new file mode 100644
index 000000000000..4c82b503d92f
--- /dev/null
+++ b/arch/x86/include/asm/errno.h
@@ -0,0 +1 @@
+#include <asm-generic/errno.h>
diff --git a/arch/x86/include/asm/es7000/apic.h b/arch/x86/include/asm/es7000/apic.h
new file mode 100644
index 000000000000..380f0b4f17ed
--- /dev/null
+++ b/arch/x86/include/asm/es7000/apic.h
@@ -0,0 +1,193 @@
+#ifndef __ASM_ES7000_APIC_H
+#define __ASM_ES7000_APIC_H
+
+#define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu)
+#define esr_disable (1)
+
+static inline int apic_id_registered(void)
+{
+	        return (1);
+}
+
+static inline cpumask_t target_cpus(void)
+{
+#if defined CONFIG_ES7000_CLUSTERED_APIC
+	return CPU_MASK_ALL;
+#else
+	return cpumask_of_cpu(smp_processor_id());
+#endif
+}
+
+#if defined CONFIG_ES7000_CLUSTERED_APIC
+#define APIC_DFR_VALUE		(APIC_DFR_CLUSTER)
+#define INT_DELIVERY_MODE	(dest_LowestPrio)
+#define INT_DEST_MODE		(1)    /* logical delivery broadcast to all procs */
+#define NO_BALANCE_IRQ		(1)
+#undef  WAKE_SECONDARY_VIA_INIT
+#define WAKE_SECONDARY_VIA_MIP
+#else
+#define APIC_DFR_VALUE		(APIC_DFR_FLAT)
+#define INT_DELIVERY_MODE	(dest_Fixed)
+#define INT_DEST_MODE		(0)    /* phys delivery to target procs */
+#define NO_BALANCE_IRQ		(0)
+#undef  APIC_DEST_LOGICAL
+#define APIC_DEST_LOGICAL	0x0
+#define WAKE_SECONDARY_VIA_INIT
+#endif
+
+static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+	return 0;
+}
+static inline unsigned long check_apicid_present(int bit)
+{
+	return physid_isset(bit, phys_cpu_present_map);
+}
+
+#define apicid_cluster(apicid) (apicid & 0xF0)
+
+static inline unsigned long calculate_ldr(int cpu)
+{
+	unsigned long id;
+	id = xapic_phys_to_log_apicid(cpu);
+	return (SET_APIC_LOGICAL_ID(id));
+}
+
+/*
+ * Set up the logical destination ID.
+ *
+ * Intel recommends to set DFR, LdR and TPR before enabling
+ * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
+ * document number 292116).  So here it goes...
+ */
+static inline void init_apic_ldr(void)
+{
+	unsigned long val;
+	int cpu = smp_processor_id();
+
+	apic_write(APIC_DFR, APIC_DFR_VALUE);
+	val = calculate_ldr(cpu);
+	apic_write(APIC_LDR, val);
+}
+
+#ifndef CONFIG_X86_GENERICARCH
+extern void enable_apic_mode(void);
+#endif
+
+extern int apic_version [MAX_APICS];
+static inline void setup_apic_routing(void)
+{
+	int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id());
+	printk("Enabling APIC mode:  %s.  Using %d I/O APICs, target cpus %lx\n",
+		(apic_version[apic] == 0x14) ?
+		"Physical Cluster" : "Logical Cluster", nr_ioapics, cpus_addr(target_cpus())[0]);
+}
+
+static inline int multi_timer_check(int apic, int irq)
+{
+	return 0;
+}
+
+static inline int apicid_to_node(int logical_apicid)
+{
+	return 0;
+}
+
+
+static inline int cpu_present_to_apicid(int mps_cpu)
+{
+	if (!mps_cpu)
+		return boot_cpu_physical_apicid;
+	else if (mps_cpu < NR_CPUS)
+		return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
+	else
+		return BAD_APICID;
+}
+
+static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
+{
+	static int id = 0;
+	physid_mask_t mask;
+	mask = physid_mask_of_physid(id);
+	++id;
+	return mask;
+}
+
+extern u8 cpu_2_logical_apicid[];
+/* Mapping from cpu number to logical apicid */
+static inline int cpu_to_logical_apicid(int cpu)
+{
+#ifdef CONFIG_SMP
+       if (cpu >= NR_CPUS)
+	       return BAD_APICID;
+       return (int)cpu_2_logical_apicid[cpu];
+#else
+	return logical_smp_processor_id();
+#endif
+}
+
+static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
+{
+	/* For clustered we don't have a good way to do this yet - hack */
+	return physids_promote(0xff);
+}
+
+
+static inline void setup_portio_remap(void)
+{
+}
+
+extern unsigned int boot_cpu_physical_apicid;
+static inline int check_phys_apicid_present(int cpu_physical_apicid)
+{
+	boot_cpu_physical_apicid = read_apic_id();
+	return (1);
+}
+
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+	int num_bits_set;
+	int cpus_found = 0;
+	int cpu;
+	int apicid;
+
+	num_bits_set = cpus_weight(cpumask);
+	/* Return id to all */
+	if (num_bits_set == NR_CPUS)
+#if defined CONFIG_ES7000_CLUSTERED_APIC
+		return 0xFF;
+#else
+		return cpu_to_logical_apicid(0);
+#endif
+	/*
+	 * The cpus in the mask must all be on the apic cluster.  If are not
+	 * on the same apicid cluster return default value of TARGET_CPUS.
+	 */
+	cpu = first_cpu(cpumask);
+	apicid = cpu_to_logical_apicid(cpu);
+	while (cpus_found < num_bits_set) {
+		if (cpu_isset(cpu, cpumask)) {
+			int new_apicid = cpu_to_logical_apicid(cpu);
+			if (apicid_cluster(apicid) !=
+					apicid_cluster(new_apicid)){
+				printk ("%s: Not a valid mask!\n", __func__);
+#if defined CONFIG_ES7000_CLUSTERED_APIC
+				return 0xFF;
+#else
+				return cpu_to_logical_apicid(0);
+#endif
+			}
+			apicid = new_apicid;
+			cpus_found++;
+		}
+		cpu++;
+	}
+	return apicid;
+}
+
+static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
+{
+	return cpuid_apic >> index_msb;
+}
+
+#endif /* __ASM_ES7000_APIC_H */
diff --git a/arch/x86/include/asm/es7000/apicdef.h b/arch/x86/include/asm/es7000/apicdef.h
new file mode 100644
index 000000000000..8b234a3cb851
--- /dev/null
+++ b/arch/x86/include/asm/es7000/apicdef.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_ES7000_APICDEF_H
+#define __ASM_ES7000_APICDEF_H
+
+#define		APIC_ID_MASK		(0xFF<<24)
+
+static inline unsigned get_apic_id(unsigned long x)
+{
+	return (((x)>>24)&0xFF);
+}
+
+#define		GET_APIC_ID(x)	get_apic_id(x)
+
+#endif
diff --git a/arch/x86/include/asm/es7000/ipi.h b/arch/x86/include/asm/es7000/ipi.h
new file mode 100644
index 000000000000..632a955fcc0a
--- /dev/null
+++ b/arch/x86/include/asm/es7000/ipi.h
@@ -0,0 +1,24 @@
+#ifndef __ASM_ES7000_IPI_H
+#define __ASM_ES7000_IPI_H
+
+void send_IPI_mask_sequence(cpumask_t mask, int vector);
+
+static inline void send_IPI_mask(cpumask_t mask, int vector)
+{
+	send_IPI_mask_sequence(mask, vector);
+}
+
+static inline void send_IPI_allbutself(int vector)
+{
+	cpumask_t mask = cpu_online_map;
+	cpu_clear(smp_processor_id(), mask);
+	if (!cpus_empty(mask))
+		send_IPI_mask(mask, vector);
+}
+
+static inline void send_IPI_all(int vector)
+{
+	send_IPI_mask(cpu_online_map, vector);
+}
+
+#endif /* __ASM_ES7000_IPI_H */
diff --git a/arch/x86/include/asm/es7000/mpparse.h b/arch/x86/include/asm/es7000/mpparse.h
new file mode 100644
index 000000000000..ed5a3caae141
--- /dev/null
+++ b/arch/x86/include/asm/es7000/mpparse.h
@@ -0,0 +1,30 @@
+#ifndef __ASM_ES7000_MPPARSE_H
+#define __ASM_ES7000_MPPARSE_H
+
+#include <linux/acpi.h>
+
+extern int parse_unisys_oem (char *oemptr);
+extern int find_unisys_acpi_oem_table(unsigned long *oem_addr);
+extern void unmap_unisys_acpi_oem_table(unsigned long oem_addr);
+extern void setup_unisys(void);
+
+#ifndef CONFIG_X86_GENERICARCH
+extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id);
+extern int mps_oem_check(struct mp_config_table *mpc, char *oem,
+				char *productid);
+#endif
+
+#ifdef CONFIG_ACPI
+
+static inline int es7000_check_dsdt(void)
+{
+	struct acpi_table_header header;
+
+	if (ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_DSDT, 0, &header)) &&
+	    !strncmp(header.oem_id, "UNISYS", 6))
+		return 1;
+	return 0;
+}
+#endif
+
+#endif /* __ASM_MACH_MPPARSE_H */
diff --git a/arch/x86/include/asm/es7000/wakecpu.h b/arch/x86/include/asm/es7000/wakecpu.h
new file mode 100644
index 000000000000..3ffc5a7bf667
--- /dev/null
+++ b/arch/x86/include/asm/es7000/wakecpu.h
@@ -0,0 +1,59 @@
+#ifndef __ASM_ES7000_WAKECPU_H
+#define __ASM_ES7000_WAKECPU_H
+
+/*
+ * This file copes with machines that wakeup secondary CPUs by the
+ * INIT, INIT, STARTUP sequence.
+ */
+
+#ifdef CONFIG_ES7000_CLUSTERED_APIC
+#define WAKE_SECONDARY_VIA_MIP
+#else
+#define WAKE_SECONDARY_VIA_INIT
+#endif
+
+#ifdef WAKE_SECONDARY_VIA_MIP
+extern int es7000_start_cpu(int cpu, unsigned long eip);
+static inline int
+wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
+{
+	int boot_error = 0;
+	boot_error = es7000_start_cpu(phys_apicid, start_eip);
+	return boot_error;
+}
+#endif
+
+#define TRAMPOLINE_LOW phys_to_virt(0x467)
+#define TRAMPOLINE_HIGH phys_to_virt(0x469)
+
+#define boot_cpu_apicid boot_cpu_physical_apicid
+
+static inline void wait_for_init_deassert(atomic_t *deassert)
+{
+#ifdef WAKE_SECONDARY_VIA_INIT
+	while (!atomic_read(deassert))
+		cpu_relax();
+#endif
+	return;
+}
+
+/* Nothing to do for most platforms, since cleared by the INIT cycle */
+static inline void smp_callin_clear_local_apic(void)
+{
+}
+
+static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
+{
+}
+
+static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
+{
+}
+
+#if APIC_DEBUG
+ #define inquire_remote_apic(apicid) __inquire_remote_apic(apicid)
+#else
+ #define inquire_remote_apic(apicid) {}
+#endif
+
+#endif /* __ASM_MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/fb.h b/arch/x86/include/asm/fb.h
new file mode 100644
index 000000000000..aca38dbd9a64
--- /dev/null
+++ b/arch/x86/include/asm/fb.h
@@ -0,0 +1,21 @@
+#ifndef ASM_X86__FB_H
+#define ASM_X86__FB_H
+
+#include <linux/fb.h>
+#include <linux/fs.h>
+#include <asm/page.h>
+
+static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
+				unsigned long off)
+{
+	if (boot_cpu_data.x86 > 3)
+		pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
+}
+
+#ifdef CONFIG_X86_32
+extern int fb_is_primary_device(struct fb_info *info);
+#else
+static inline int fb_is_primary_device(struct fb_info *info) { return 0; }
+#endif
+
+#endif /* ASM_X86__FB_H */
diff --git a/arch/x86/include/asm/fcntl.h b/arch/x86/include/asm/fcntl.h
new file mode 100644
index 000000000000..46ab12db5739
--- /dev/null
+++ b/arch/x86/include/asm/fcntl.h
@@ -0,0 +1 @@
+#include <asm-generic/fcntl.h>
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
new file mode 100644
index 000000000000..78e33a1bc591
--- /dev/null
+++ b/arch/x86/include/asm/fixmap.h
@@ -0,0 +1,68 @@
+#ifndef ASM_X86__FIXMAP_H
+#define ASM_X86__FIXMAP_H
+
+#ifdef CONFIG_X86_32
+# include "fixmap_32.h"
+#else
+# include "fixmap_64.h"
+#endif
+
+extern int fixmaps_set;
+
+void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
+void native_set_fixmap(enum fixed_addresses idx,
+		       unsigned long phys, pgprot_t flags);
+
+#ifndef CONFIG_PARAVIRT
+static inline void __set_fixmap(enum fixed_addresses idx,
+				unsigned long phys, pgprot_t flags)
+{
+	native_set_fixmap(idx, phys, flags);
+}
+#endif
+
+#define set_fixmap(idx, phys)				\
+	__set_fixmap(idx, phys, PAGE_KERNEL)
+
+/*
+ * Some hardware wants to get fixmapped without caching.
+ */
+#define set_fixmap_nocache(idx, phys)			\
+	__set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
+
+#define clear_fixmap(idx)			\
+	__set_fixmap(idx, 0, __pgprot(0))
+
+#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
+#define __virt_to_fix(x)	((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
+
+extern void __this_fixmap_does_not_exist(void);
+
+/*
+ * 'index to address' translation. If anyone tries to use the idx
+ * directly without translation, we catch the bug with a NULL-deference
+ * kernel oops. Illegal ranges of incoming indices are caught too.
+ */
+static __always_inline unsigned long fix_to_virt(const unsigned int idx)
+{
+	/*
+	 * this branch gets completely eliminated after inlining,
+	 * except when someone tries to use fixaddr indices in an
+	 * illegal way. (such as mixing up address types or using
+	 * out-of-range indices).
+	 *
+	 * If it doesn't get removed, the linker will complain
+	 * loudly with a reasonably clear error message..
+	 */
+	if (idx >= __end_of_fixed_addresses)
+		__this_fixmap_does_not_exist();
+
+	return __fix_to_virt(idx);
+}
+
+static inline unsigned long virt_to_fix(const unsigned long vaddr)
+{
+	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
+	return __virt_to_fix(vaddr);
+}
+#endif /* ASM_X86__FIXMAP_H */
diff --git a/arch/x86/include/asm/fixmap_32.h b/arch/x86/include/asm/fixmap_32.h
new file mode 100644
index 000000000000..8844002da0e0
--- /dev/null
+++ b/arch/x86/include/asm/fixmap_32.h
@@ -0,0 +1,123 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ *
+ * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
+ */
+
+#ifndef ASM_X86__FIXMAP_32_H
+#define ASM_X86__FIXMAP_32_H
+
+
+/* used by vmalloc.c, vsyscall.lds.S.
+ *
+ * Leave one empty page between vmalloc'ed areas and
+ * the start of the fixmap.
+ */
+extern unsigned long __FIXADDR_TOP;
+#define FIXADDR_USER_START     __fix_to_virt(FIX_VDSO)
+#define FIXADDR_USER_END       __fix_to_virt(FIX_VDSO - 1)
+
+#ifndef __ASSEMBLY__
+#include <linux/kernel.h>
+#include <asm/acpi.h>
+#include <asm/apicdef.h>
+#include <asm/page.h>
+#ifdef CONFIG_HIGHMEM
+#include <linux/threads.h>
+#include <asm/kmap_types.h>
+#endif
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process. We allocate these special addresses
+ * from the end of virtual memory (0xfffff000) backwards.
+ * Also this lets us do fail-safe vmalloc(), we
+ * can guarantee that these special addresses and
+ * vmalloc()-ed addresses never overlap.
+ *
+ * these 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages. (or larger if used with an increment
+ * highger than 1) use fixmap_set(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+enum fixed_addresses {
+	FIX_HOLE,
+	FIX_VDSO,
+	FIX_DBGP_BASE,
+	FIX_EARLYCON_MEM_BASE,
+#ifdef CONFIG_X86_LOCAL_APIC
+	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
+#endif
+#ifdef CONFIG_X86_IO_APIC
+	FIX_IO_APIC_BASE_0,
+	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1,
+#endif
+#ifdef CONFIG_X86_VISWS_APIC
+	FIX_CO_CPU,	/* Cobalt timer */
+	FIX_CO_APIC,	/* Cobalt APIC Redirection Table */
+	FIX_LI_PCIA,	/* Lithium PCI Bridge A */
+	FIX_LI_PCIB,	/* Lithium PCI Bridge B */
+#endif
+#ifdef CONFIG_X86_F00F_BUG
+	FIX_F00F_IDT,	/* Virtual mapping for IDT */
+#endif
+#ifdef CONFIG_X86_CYCLONE_TIMER
+	FIX_CYCLONE_TIMER, /*cyclone timer register*/
+#endif
+#ifdef CONFIG_HIGHMEM
+	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
+	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
+#endif
+#ifdef CONFIG_PCI_MMCONFIG
+	FIX_PCIE_MCFG,
+#endif
+#ifdef CONFIG_PARAVIRT
+	FIX_PARAVIRT_BOOTMAP,
+#endif
+	__end_of_permanent_fixed_addresses,
+	/*
+	 * 256 temporary boot-time mappings, used by early_ioremap(),
+	 * before ioremap() is functional.
+	 *
+	 * We round it up to the next 256 pages boundary so that we
+	 * can have a single pgd entry and a single pte table:
+	 */
+#define NR_FIX_BTMAPS		64
+#define FIX_BTMAPS_SLOTS	4
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
+			(__end_of_permanent_fixed_addresses & 255),
+	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
+	FIX_WP_TEST,
+#ifdef CONFIG_ACPI
+	FIX_ACPI_BEGIN,
+	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
+#endif
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+	FIX_OHCI1394_BASE,
+#endif
+	__end_of_fixed_addresses
+};
+
+extern void reserve_top_address(unsigned long reserve);
+
+
+#define FIXADDR_TOP	((unsigned long)__FIXADDR_TOP)
+
+#define __FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
+#define __FIXADDR_BOOT_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START		(FIXADDR_TOP - __FIXADDR_SIZE)
+#define FIXADDR_BOOT_START	(FIXADDR_TOP - __FIXADDR_BOOT_SIZE)
+
+#endif /* !__ASSEMBLY__ */
+#endif /* ASM_X86__FIXMAP_32_H */
diff --git a/arch/x86/include/asm/fixmap_64.h b/arch/x86/include/asm/fixmap_64.h
new file mode 100644
index 000000000000..dab4751d1307
--- /dev/null
+++ b/arch/x86/include/asm/fixmap_64.h
@@ -0,0 +1,83 @@
+/*
+ * fixmap.h: compile-time virtual memory allocation
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1998 Ingo Molnar
+ */
+
+#ifndef ASM_X86__FIXMAP_64_H
+#define ASM_X86__FIXMAP_64_H
+
+#include <linux/kernel.h>
+#include <asm/acpi.h>
+#include <asm/apicdef.h>
+#include <asm/page.h>
+#include <asm/vsyscall.h>
+#include <asm/efi.h>
+
+/*
+ * Here we define all the compile-time 'special' virtual
+ * addresses. The point is to have a constant address at
+ * compile time, but to set the physical address only
+ * in the boot process.
+ *
+ * These 'compile-time allocated' memory buffers are
+ * fixed-size 4k pages (or larger if used with an increment
+ * higher than 1). Use set_fixmap(idx,phys) to associate
+ * physical memory with fixmap indices.
+ *
+ * TLB entries of such buffers will not be flushed across
+ * task switches.
+ */
+
+enum fixed_addresses {
+	VSYSCALL_LAST_PAGE,
+	VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
+			    + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
+	VSYSCALL_HPET,
+	FIX_DBGP_BASE,
+	FIX_EARLYCON_MEM_BASE,
+	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
+	FIX_IO_APIC_BASE_0,
+	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
+	FIX_EFI_IO_MAP_LAST_PAGE,
+	FIX_EFI_IO_MAP_FIRST_PAGE = FIX_EFI_IO_MAP_LAST_PAGE
+				  + MAX_EFI_IO_PAGES - 1,
+#ifdef CONFIG_PARAVIRT
+	FIX_PARAVIRT_BOOTMAP,
+#endif
+	__end_of_permanent_fixed_addresses,
+#ifdef CONFIG_ACPI
+	FIX_ACPI_BEGIN,
+	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
+#endif
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+	FIX_OHCI1394_BASE,
+#endif
+	/*
+	 * 256 temporary boot-time mappings, used by early_ioremap(),
+	 * before ioremap() is functional.
+	 *
+	 * We round it up to the next 256 pages boundary so that we
+	 * can have a single pgd entry and a single pte table:
+	 */
+#define NR_FIX_BTMAPS		64
+#define FIX_BTMAPS_SLOTS	4
+	FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
+			(__end_of_permanent_fixed_addresses & 255),
+	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
+	__end_of_fixed_addresses
+};
+
+#define FIXADDR_TOP	(VSYSCALL_END-PAGE_SIZE)
+#define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
+#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
+
+/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */
+#define FIXADDR_USER_START	((unsigned long)VSYSCALL32_VSYSCALL)
+#define FIXADDR_USER_END	(FIXADDR_USER_START + PAGE_SIZE)
+
+#endif /* ASM_X86__FIXMAP_64_H */
diff --git a/arch/x86/include/asm/floppy.h b/arch/x86/include/asm/floppy.h
new file mode 100644
index 000000000000..7d83a3a83e37
--- /dev/null
+++ b/arch/x86/include/asm/floppy.h
@@ -0,0 +1,281 @@
+/*
+ * Architecture specific parts of the Floppy driver
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1995
+ */
+#ifndef ASM_X86__FLOPPY_H
+#define ASM_X86__FLOPPY_H
+
+#include <linux/vmalloc.h>
+
+/*
+ * The DMA channel used by the floppy controller cannot access data at
+ * addresses >= 16MB
+ *
+ * Went back to the 1MB limit, as some people had problems with the floppy
+ * driver otherwise. It doesn't matter much for performance anyway, as most
+ * floppy accesses go through the track buffer.
+ */
+#define _CROSS_64KB(a, s, vdma)						\
+	(!(vdma) &&							\
+	 ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
+
+#define CROSS_64KB(a, s) _CROSS_64KB(a, s, use_virtual_dma & 1)
+
+
+#define SW fd_routine[use_virtual_dma & 1]
+#define CSW fd_routine[can_use_virtual_dma & 1]
+
+
+#define fd_inb(port)		inb_p(port)
+#define fd_outb(value, port)	outb_p(value, port)
+
+#define fd_request_dma()	CSW._request_dma(FLOPPY_DMA, "floppy")
+#define fd_free_dma()		CSW._free_dma(FLOPPY_DMA)
+#define fd_enable_irq()		enable_irq(FLOPPY_IRQ)
+#define fd_disable_irq()	disable_irq(FLOPPY_IRQ)
+#define fd_free_irq()		free_irq(FLOPPY_IRQ, NULL)
+#define fd_get_dma_residue()	SW._get_dma_residue(FLOPPY_DMA)
+#define fd_dma_mem_alloc(size)	SW._dma_mem_alloc(size)
+#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
+
+#define FLOPPY_CAN_FALLBACK_ON_NODMA
+
+static int virtual_dma_count;
+static int virtual_dma_residue;
+static char *virtual_dma_addr;
+static int virtual_dma_mode;
+static int doing_pdma;
+
+static irqreturn_t floppy_hardint(int irq, void *dev_id)
+{
+	unsigned char st;
+
+#undef TRACE_FLPY_INT
+
+#ifdef TRACE_FLPY_INT
+	static int calls;
+	static int bytes;
+	static int dma_wait;
+#endif
+	if (!doing_pdma)
+		return floppy_interrupt(irq, dev_id);
+
+#ifdef TRACE_FLPY_INT
+	if (!calls)
+		bytes = virtual_dma_count;
+#endif
+
+	{
+		int lcount;
+		char *lptr;
+
+		st = 1;
+		for (lcount = virtual_dma_count, lptr = virtual_dma_addr;
+		     lcount; lcount--, lptr++) {
+			st = inb(virtual_dma_port + 4) & 0xa0;
+			if (st != 0xa0)
+				break;
+			if (virtual_dma_mode)
+				outb_p(*lptr, virtual_dma_port + 5);
+			else
+				*lptr = inb_p(virtual_dma_port + 5);
+		}
+		virtual_dma_count = lcount;
+		virtual_dma_addr = lptr;
+		st = inb(virtual_dma_port + 4);
+	}
+
+#ifdef TRACE_FLPY_INT
+	calls++;
+#endif
+	if (st == 0x20)
+		return IRQ_HANDLED;
+	if (!(st & 0x20)) {
+		virtual_dma_residue += virtual_dma_count;
+		virtual_dma_count = 0;
+#ifdef TRACE_FLPY_INT
+		printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
+		       virtual_dma_count, virtual_dma_residue, calls, bytes,
+		       dma_wait);
+		calls = 0;
+		dma_wait = 0;
+#endif
+		doing_pdma = 0;
+		floppy_interrupt(irq, dev_id);
+		return IRQ_HANDLED;
+	}
+#ifdef TRACE_FLPY_INT
+	if (!virtual_dma_count)
+		dma_wait++;
+#endif
+	return IRQ_HANDLED;
+}
+
+static void fd_disable_dma(void)
+{
+	if (!(can_use_virtual_dma & 1))
+		disable_dma(FLOPPY_DMA);
+	doing_pdma = 0;
+	virtual_dma_residue += virtual_dma_count;
+	virtual_dma_count = 0;
+}
+
+static int vdma_request_dma(unsigned int dmanr, const char *device_id)
+{
+	return 0;
+}
+
+static void vdma_nop(unsigned int dummy)
+{
+}
+
+
+static int vdma_get_dma_residue(unsigned int dummy)
+{
+	return virtual_dma_count + virtual_dma_residue;
+}
+
+
+static int fd_request_irq(void)
+{
+	if (can_use_virtual_dma)
+		return request_irq(FLOPPY_IRQ, floppy_hardint,
+				   IRQF_DISABLED, "floppy", NULL);
+	else
+		return request_irq(FLOPPY_IRQ, floppy_interrupt,
+				   IRQF_DISABLED, "floppy", NULL);
+}
+
+static unsigned long dma_mem_alloc(unsigned long size)
+{
+	return __get_dma_pages(GFP_KERNEL|__GFP_NORETRY, get_order(size));
+}
+
+
+static unsigned long vdma_mem_alloc(unsigned long size)
+{
+	return (unsigned long)vmalloc(size);
+
+}
+
+#define nodma_mem_alloc(size) vdma_mem_alloc(size)
+
+static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
+{
+	if ((unsigned long)addr >= (unsigned long)high_memory)
+		vfree((void *)addr);
+	else
+		free_pages(addr, get_order(size));
+}
+
+#define fd_dma_mem_free(addr, size)  _fd_dma_mem_free(addr, size)
+
+static void _fd_chose_dma_mode(char *addr, unsigned long size)
+{
+	if (can_use_virtual_dma == 2) {
+		if ((unsigned long)addr >= (unsigned long)high_memory ||
+		    isa_virt_to_bus(addr) >= 0x1000000 ||
+		    _CROSS_64KB(addr, size, 0))
+			use_virtual_dma = 1;
+		else
+			use_virtual_dma = 0;
+	} else {
+		use_virtual_dma = can_use_virtual_dma & 1;
+	}
+}
+
+#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
+
+
+static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+	doing_pdma = 1;
+	virtual_dma_port = io;
+	virtual_dma_mode = (mode == DMA_MODE_WRITE);
+	virtual_dma_addr = addr;
+	virtual_dma_count = size;
+	virtual_dma_residue = 0;
+	return 0;
+}
+
+static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
+{
+#ifdef FLOPPY_SANITY_CHECK
+	if (CROSS_64KB(addr, size)) {
+		printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
+		return -1;
+	}
+#endif
+	/* actual, physical DMA */
+	doing_pdma = 0;
+	clear_dma_ff(FLOPPY_DMA);
+	set_dma_mode(FLOPPY_DMA, mode);
+	set_dma_addr(FLOPPY_DMA, isa_virt_to_bus(addr));
+	set_dma_count(FLOPPY_DMA, size);
+	enable_dma(FLOPPY_DMA);
+	return 0;
+}
+
+static struct fd_routine_l {
+	int (*_request_dma)(unsigned int dmanr, const char *device_id);
+	void (*_free_dma)(unsigned int dmanr);
+	int (*_get_dma_residue)(unsigned int dummy);
+	unsigned long (*_dma_mem_alloc)(unsigned long size);
+	int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
+} fd_routine[] = {
+	{
+		request_dma,
+		free_dma,
+		get_dma_residue,
+		dma_mem_alloc,
+		hard_dma_setup
+	},
+	{
+		vdma_request_dma,
+		vdma_nop,
+		vdma_get_dma_residue,
+		vdma_mem_alloc,
+		vdma_dma_setup
+	}
+};
+
+
+static int FDC1 = 0x3f0;
+static int FDC2 = -1;
+
+/*
+ * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
+ * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
+ * coincides with another rtc CMOS user.		Paul G.
+ */
+#define FLOPPY0_TYPE					\
+({							\
+	unsigned long flags;				\
+	unsigned char val;				\
+	spin_lock_irqsave(&rtc_lock, flags);		\
+	val = (CMOS_READ(0x10) >> 4) & 15;		\
+	spin_unlock_irqrestore(&rtc_lock, flags);	\
+	val;						\
+})
+
+#define FLOPPY1_TYPE					\
+({							\
+	unsigned long flags;				\
+	unsigned char val;				\
+	spin_lock_irqsave(&rtc_lock, flags);		\
+	val = CMOS_READ(0x10) & 15;			\
+	spin_unlock_irqrestore(&rtc_lock, flags);	\
+	val;						\
+})
+
+#define N_FDC 2
+#define N_DRIVE 8
+
+#define EXTRA_FLOPPY_PARAMS
+
+#endif /* ASM_X86__FLOPPY_H */
diff --git a/arch/x86/include/asm/frame.h b/arch/x86/include/asm/frame.h
new file mode 100644
index 000000000000..06850a7194e1
--- /dev/null
+++ b/arch/x86/include/asm/frame.h
@@ -0,0 +1,27 @@
+#ifdef __ASSEMBLY__
+
+#include <asm/dwarf2.h>
+
+/* The annotation hides the frame from the unwinder and makes it look
+   like a ordinary ebp save/restore. This avoids some special cases for
+   frame pointer later */
+#ifdef CONFIG_FRAME_POINTER
+	.macro FRAME
+	pushl %ebp
+	CFI_ADJUST_CFA_OFFSET 4
+	CFI_REL_OFFSET ebp,0
+	movl %esp,%ebp
+	.endm
+	.macro ENDFRAME
+	popl %ebp
+	CFI_ADJUST_CFA_OFFSET -4
+	CFI_RESTORE ebp
+	.endm
+#else
+	.macro FRAME
+	.endm
+	.macro ENDFRAME
+	.endm
+#endif
+
+#endif  /*  __ASSEMBLY__  */
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
new file mode 100644
index 000000000000..1bb6f9bbe1ab
--- /dev/null
+++ b/arch/x86/include/asm/ftrace.h
@@ -0,0 +1,24 @@
+#ifndef ASM_X86__FTRACE_H
+#define ASM_X86__FTRACE_H
+
+#ifdef CONFIG_FTRACE
+#define MCOUNT_ADDR		((long)(mcount))
+#define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */
+
+#ifndef __ASSEMBLY__
+extern void mcount(void);
+
+static inline unsigned long ftrace_call_adjust(unsigned long addr)
+{
+	/*
+	 * call mcount is "e8 <4 byte offset>"
+	 * The addr points to the 4 byte offset and the caller of this
+	 * function wants the pointer to e8. Simply subtract one.
+	 */
+	return addr - 1;
+}
+#endif
+
+#endif /* CONFIG_FTRACE */
+
+#endif /* ASM_X86__FTRACE_H */
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
new file mode 100644
index 000000000000..06b924ef6fa5
--- /dev/null
+++ b/arch/x86/include/asm/futex.h
@@ -0,0 +1,140 @@
+#ifndef ASM_X86__FUTEX_H
+#define ASM_X86__FUTEX_H
+
+#ifdef __KERNEL__
+
+#include <linux/futex.h>
+#include <linux/uaccess.h>
+
+#include <asm/asm.h>
+#include <asm/errno.h>
+#include <asm/processor.h>
+#include <asm/system.h>
+
+#define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg)	\
+	asm volatile("1:\t" insn "\n"				\
+		     "2:\t.section .fixup,\"ax\"\n"		\
+		     "3:\tmov\t%3, %1\n"			\
+		     "\tjmp\t2b\n"				\
+		     "\t.previous\n"				\
+		     _ASM_EXTABLE(1b, 3b)			\
+		     : "=r" (oldval), "=r" (ret), "+m" (*uaddr)	\
+		     : "i" (-EFAULT), "0" (oparg), "1" (0))
+
+#define __futex_atomic_op2(insn, ret, oldval, uaddr, oparg)	\
+	asm volatile("1:\tmovl	%2, %0\n"			\
+		     "\tmovl\t%0, %3\n"				\
+		     "\t" insn "\n"				\
+		     "2:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"	\
+		     "\tjnz\t1b\n"				\
+		     "3:\t.section .fixup,\"ax\"\n"		\
+		     "4:\tmov\t%5, %1\n"			\
+		     "\tjmp\t3b\n"				\
+		     "\t.previous\n"				\
+		     _ASM_EXTABLE(1b, 4b)			\
+		     _ASM_EXTABLE(2b, 4b)			\
+		     : "=&a" (oldval), "=&r" (ret),		\
+		       "+m" (*uaddr), "=&r" (tem)		\
+		     : "r" (oparg), "i" (-EFAULT), "1" (0))
+
+static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
+{
+	int op = (encoded_op >> 28) & 7;
+	int cmp = (encoded_op >> 24) & 15;
+	int oparg = (encoded_op << 8) >> 20;
+	int cmparg = (encoded_op << 20) >> 20;
+	int oldval = 0, ret, tem;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+		return -EFAULT;
+
+#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
+	/* Real i386 machines can only support FUTEX_OP_SET */
+	if (op != FUTEX_OP_SET && boot_cpu_data.x86 == 3)
+		return -ENOSYS;
+#endif
+
+	pagefault_disable();
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op1("xchgl %0, %2", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op1(LOCK_PREFIX "xaddl %0, %2", ret, oldval,
+				   uaddr, oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op2("orl %4, %3", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op2("andl %4, %3", ret, oldval, uaddr, ~oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op2("xorl %4, %3", ret, oldval, uaddr, oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	pagefault_enable();
+
+	if (!ret) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ:
+			ret = (oldval == cmparg);
+			break;
+		case FUTEX_OP_CMP_NE:
+			ret = (oldval != cmparg);
+			break;
+		case FUTEX_OP_CMP_LT:
+			ret = (oldval < cmparg);
+			break;
+		case FUTEX_OP_CMP_GE:
+			ret = (oldval >= cmparg);
+			break;
+		case FUTEX_OP_CMP_LE:
+			ret = (oldval <= cmparg);
+			break;
+		case FUTEX_OP_CMP_GT:
+			ret = (oldval > cmparg);
+			break;
+		default:
+			ret = -ENOSYS;
+		}
+	}
+	return ret;
+}
+
+static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
+						int newval)
+{
+
+#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
+	/* Real i386 machines have no cmpxchg instruction */
+	if (boot_cpu_data.x86 == 3)
+		return -ENOSYS;
+#endif
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+		return -EFAULT;
+
+	asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %3, %1\n"
+		     "2:\t.section .fixup, \"ax\"\n"
+		     "3:\tmov     %2, %0\n"
+		     "\tjmp     2b\n"
+		     "\t.previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : "=a" (oldval), "+m" (*uaddr)
+		     : "i" (-EFAULT), "r" (newval), "0" (oldval)
+		     : "memory"
+	);
+
+	return oldval;
+}
+
+#endif
+#endif /* ASM_X86__FUTEX_H */
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
new file mode 100644
index 000000000000..605edb39ef9e
--- /dev/null
+++ b/arch/x86/include/asm/gart.h
@@ -0,0 +1,73 @@
+#ifndef ASM_X86__GART_H
+#define ASM_X86__GART_H
+
+#include <asm/e820.h>
+
+extern void set_up_gart_resume(u32, u32);
+
+extern int fallback_aper_order;
+extern int fallback_aper_force;
+extern int fix_aperture;
+
+/* PTE bits. */
+#define GPTE_VALID	1
+#define GPTE_COHERENT	2
+
+/* Aperture control register bits. */
+#define GARTEN		(1<<0)
+#define DISGARTCPU	(1<<4)
+#define DISGARTIO	(1<<5)
+
+/* GART cache control register bits. */
+#define INVGART		(1<<0)
+#define GARTPTEERR	(1<<1)
+
+/* K8 On-cpu GART registers */
+#define AMD64_GARTAPERTURECTL	0x90
+#define AMD64_GARTAPERTUREBASE	0x94
+#define AMD64_GARTTABLEBASE	0x98
+#define AMD64_GARTCACHECTL	0x9c
+#define AMD64_GARTEN		(1<<0)
+
+extern int agp_amd64_init(void);
+
+static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
+{
+	u32 tmp, ctl;
+
+        /* address of the mappings table */
+        addr >>= 12;
+        tmp = (u32) addr<<4;
+        tmp &= ~0xf;
+        pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
+
+        /* Enable GART translation for this hammer. */
+        pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
+        ctl |= GARTEN;
+        ctl &= ~(DISGARTCPU | DISGARTIO);
+        pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
+}
+
+static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
+{
+	if (!aper_base)
+		return 0;
+
+	if (aper_base + aper_size > 0x100000000ULL) {
+		printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n");
+		return 0;
+	}
+	if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
+		printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n");
+		return 0;
+	}
+	if (aper_size < min_size) {
+		printk(KERN_INFO "Aperture too small (%d MB) than (%d MB)\n",
+				 aper_size>>20, min_size>>20);
+		return 0;
+	}
+
+	return 1;
+}
+
+#endif /* ASM_X86__GART_H */
diff --git a/arch/x86/include/asm/genapic.h b/arch/x86/include/asm/genapic.h
new file mode 100644
index 000000000000..d48bee663a6f
--- /dev/null
+++ b/arch/x86/include/asm/genapic.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "genapic_32.h"
+#else
+# include "genapic_64.h"
+#endif
diff --git a/arch/x86/include/asm/genapic_32.h b/arch/x86/include/asm/genapic_32.h
new file mode 100644
index 000000000000..6fe4f81bfcf9
--- /dev/null
+++ b/arch/x86/include/asm/genapic_32.h
@@ -0,0 +1,126 @@
+#ifndef ASM_X86__GENAPIC_32_H
+#define ASM_X86__GENAPIC_32_H
+
+#include <asm/mpspec.h>
+
+/*
+ * Generic APIC driver interface.
+ *
+ * An straight forward mapping of the APIC related parts of the
+ * x86 subarchitecture interface to a dynamic object.
+ *
+ * This is used by the "generic" x86 subarchitecture.
+ *
+ * Copyright 2003 Andi Kleen, SuSE Labs.
+ */
+
+struct mpc_config_bus;
+struct mp_config_table;
+struct mpc_config_processor;
+
+struct genapic {
+	char *name;
+	int (*probe)(void);
+
+	int (*apic_id_registered)(void);
+	cpumask_t (*target_cpus)(void);
+	int int_delivery_mode;
+	int int_dest_mode;
+	int ESR_DISABLE;
+	int apic_destination_logical;
+	unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid);
+	unsigned long (*check_apicid_present)(int apicid);
+	int no_balance_irq;
+	int no_ioapic_check;
+	void (*init_apic_ldr)(void);
+	physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map);
+
+	void (*setup_apic_routing)(void);
+	int (*multi_timer_check)(int apic, int irq);
+	int (*apicid_to_node)(int logical_apicid);
+	int (*cpu_to_logical_apicid)(int cpu);
+	int (*cpu_present_to_apicid)(int mps_cpu);
+	physid_mask_t (*apicid_to_cpu_present)(int phys_apicid);
+	void (*setup_portio_remap)(void);
+	int (*check_phys_apicid_present)(int boot_cpu_physical_apicid);
+	void (*enable_apic_mode)(void);
+	u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb);
+
+	/* mpparse */
+	/* When one of the next two hooks returns 1 the genapic
+	   is switched to this. Essentially they are additional probe
+	   functions. */
+	int (*mps_oem_check)(struct mp_config_table *mpc, char *oem,
+			     char *productid);
+	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
+
+	unsigned (*get_apic_id)(unsigned long x);
+	unsigned long apic_id_mask;
+	unsigned int (*cpu_mask_to_apicid)(cpumask_t cpumask);
+	cpumask_t (*vector_allocation_domain)(int cpu);
+
+#ifdef CONFIG_SMP
+	/* ipi */
+	void (*send_IPI_mask)(cpumask_t mask, int vector);
+	void (*send_IPI_allbutself)(int vector);
+	void (*send_IPI_all)(int vector);
+#endif
+};
+
+#define APICFUNC(x) .x = x,
+
+/* More functions could be probably marked IPIFUNC and save some space
+   in UP GENERICARCH kernels, but I don't have the nerve right now
+   to untangle this mess. -AK  */
+#ifdef CONFIG_SMP
+#define IPIFUNC(x) APICFUNC(x)
+#else
+#define IPIFUNC(x)
+#endif
+
+#define APIC_INIT(aname, aprobe)			\
+{							\
+	.name = aname,					\
+	.probe = aprobe,				\
+	.int_delivery_mode = INT_DELIVERY_MODE,		\
+	.int_dest_mode = INT_DEST_MODE,			\
+	.no_balance_irq = NO_BALANCE_IRQ,		\
+	.ESR_DISABLE = esr_disable,			\
+	.apic_destination_logical = APIC_DEST_LOGICAL,	\
+	APICFUNC(apic_id_registered)			\
+	APICFUNC(target_cpus)				\
+	APICFUNC(check_apicid_used)			\
+	APICFUNC(check_apicid_present)			\
+	APICFUNC(init_apic_ldr)				\
+	APICFUNC(ioapic_phys_id_map)			\
+	APICFUNC(setup_apic_routing)			\
+	APICFUNC(multi_timer_check)			\
+	APICFUNC(apicid_to_node)			\
+	APICFUNC(cpu_to_logical_apicid)			\
+	APICFUNC(cpu_present_to_apicid)			\
+	APICFUNC(apicid_to_cpu_present)			\
+	APICFUNC(setup_portio_remap)			\
+	APICFUNC(check_phys_apicid_present)		\
+	APICFUNC(mps_oem_check)				\
+	APICFUNC(get_apic_id)				\
+	.apic_id_mask = APIC_ID_MASK,			\
+	APICFUNC(cpu_mask_to_apicid)			\
+	APICFUNC(vector_allocation_domain)			\
+	APICFUNC(acpi_madt_oem_check)			\
+	IPIFUNC(send_IPI_mask)				\
+	IPIFUNC(send_IPI_allbutself)			\
+	IPIFUNC(send_IPI_all)				\
+	APICFUNC(enable_apic_mode)			\
+	APICFUNC(phys_pkg_id)				\
+}
+
+extern struct genapic *genapic;
+
+enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
+#define get_uv_system_type()		UV_NONE
+#define is_uv_system()			0
+#define uv_wakeup_secondary(a, b)	1
+#define uv_system_init()		do {} while (0)
+
+
+#endif /* ASM_X86__GENAPIC_32_H */
diff --git a/arch/x86/include/asm/genapic_64.h b/arch/x86/include/asm/genapic_64.h
new file mode 100644
index 000000000000..ed6a4886c082
--- /dev/null
+++ b/arch/x86/include/asm/genapic_64.h
@@ -0,0 +1,58 @@
+#ifndef ASM_X86__GENAPIC_64_H
+#define ASM_X86__GENAPIC_64_H
+
+/*
+ * Copyright 2004 James Cleverdon, IBM.
+ * Subject to the GNU Public License, v.2
+ *
+ * Generic APIC sub-arch data struct.
+ *
+ * Hacked for x86-64 by James Cleverdon from i386 architecture code by
+ * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
+ * James Cleverdon.
+ */
+
+struct genapic {
+	char *name;
+	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
+	u32 int_delivery_mode;
+	u32 int_dest_mode;
+	int (*apic_id_registered)(void);
+	cpumask_t (*target_cpus)(void);
+	cpumask_t (*vector_allocation_domain)(int cpu);
+	void (*init_apic_ldr)(void);
+	/* ipi */
+	void (*send_IPI_mask)(cpumask_t mask, int vector);
+	void (*send_IPI_allbutself)(int vector);
+	void (*send_IPI_all)(int vector);
+	void (*send_IPI_self)(int vector);
+	/* */
+	unsigned int (*cpu_mask_to_apicid)(cpumask_t cpumask);
+	unsigned int (*phys_pkg_id)(int index_msb);
+	unsigned int (*get_apic_id)(unsigned long x);
+	unsigned long (*set_apic_id)(unsigned int id);
+	unsigned long apic_id_mask;
+};
+
+extern struct genapic *genapic;
+
+extern struct genapic apic_flat;
+extern struct genapic apic_physflat;
+extern struct genapic apic_x2apic_cluster;
+extern struct genapic apic_x2apic_phys;
+extern int acpi_madt_oem_check(char *, char *);
+
+extern void apic_send_IPI_self(int vector);
+enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
+extern enum uv_system_type get_uv_system_type(void);
+extern int is_uv_system(void);
+
+extern struct genapic apic_x2apic_uv_x;
+DECLARE_PER_CPU(int, x2apic_extra_bits);
+extern void uv_cpu_init(void);
+extern void uv_system_init(void);
+extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
+
+extern void setup_apic_routing(void);
+
+#endif /* ASM_X86__GENAPIC_64_H */
diff --git a/arch/x86/include/asm/geode.h b/arch/x86/include/asm/geode.h
new file mode 100644
index 000000000000..3f3444be2638
--- /dev/null
+++ b/arch/x86/include/asm/geode.h
@@ -0,0 +1,253 @@
+/*
+ * AMD Geode definitions
+ * Copyright (C) 2006, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ */
+
+#ifndef ASM_X86__GEODE_H
+#define ASM_X86__GEODE_H
+
+#include <asm/processor.h>
+#include <linux/io.h>
+
+/* Generic southbridge functions */
+
+#define GEODE_DEV_PMS 0
+#define GEODE_DEV_ACPI 1
+#define GEODE_DEV_GPIO 2
+#define GEODE_DEV_MFGPT 3
+
+extern int geode_get_dev_base(unsigned int dev);
+
+/* Useful macros */
+#define geode_pms_base()	geode_get_dev_base(GEODE_DEV_PMS)
+#define geode_acpi_base()	geode_get_dev_base(GEODE_DEV_ACPI)
+#define geode_gpio_base()	geode_get_dev_base(GEODE_DEV_GPIO)
+#define geode_mfgpt_base()	geode_get_dev_base(GEODE_DEV_MFGPT)
+
+/* MSRS */
+
+#define MSR_GLIU_P2D_RO0	0x10000029
+
+#define MSR_LX_GLD_MSR_CONFIG	0x48002001
+#define MSR_LX_MSR_PADSEL	0x48002011	/* NOT 0x48000011; the data
+						 * sheet has the wrong value */
+#define MSR_GLCP_SYS_RSTPLL	0x4C000014
+#define MSR_GLCP_DOTPLL		0x4C000015
+
+#define MSR_LBAR_SMB		0x5140000B
+#define MSR_LBAR_GPIO		0x5140000C
+#define MSR_LBAR_MFGPT		0x5140000D
+#define MSR_LBAR_ACPI		0x5140000E
+#define MSR_LBAR_PMS		0x5140000F
+
+#define MSR_DIVIL_SOFT_RESET	0x51400017
+
+#define MSR_PIC_YSEL_LOW	0x51400020
+#define MSR_PIC_YSEL_HIGH	0x51400021
+#define MSR_PIC_ZSEL_LOW	0x51400022
+#define MSR_PIC_ZSEL_HIGH	0x51400023
+#define MSR_PIC_IRQM_LPC	0x51400025
+
+#define MSR_MFGPT_IRQ		0x51400028
+#define MSR_MFGPT_NR		0x51400029
+#define MSR_MFGPT_SETUP		0x5140002B
+
+#define MSR_LX_SPARE_MSR	0x80000011	/* DC-specific */
+
+#define MSR_GX_GLD_MSR_CONFIG	0xC0002001
+#define MSR_GX_MSR_PADSEL	0xC0002011
+
+/* Resource Sizes */
+
+#define LBAR_GPIO_SIZE		0xFF
+#define LBAR_MFGPT_SIZE		0x40
+#define LBAR_ACPI_SIZE		0x40
+#define LBAR_PMS_SIZE		0x80
+
+/* ACPI registers (PMS block) */
+
+/*
+ * PM1_EN is only valid when VSA is enabled for 16 bit reads.
+ * When VSA is not enabled, *always* read both PM1_STS and PM1_EN
+ * with a 32 bit read at offset 0x0
+ */
+
+#define PM1_STS			0x00
+#define PM1_EN			0x02
+#define PM1_CNT			0x08
+#define PM2_CNT			0x0C
+#define PM_TMR			0x10
+#define PM_GPE0_STS		0x18
+#define PM_GPE0_EN		0x1C
+
+/* PMC registers (PMS block) */
+
+#define PM_SSD			0x00
+#define PM_SCXA			0x04
+#define PM_SCYA			0x08
+#define PM_OUT_SLPCTL		0x0C
+#define PM_SCLK			0x10
+#define PM_SED			0x1
+#define PM_SCXD			0x18
+#define PM_SCYD			0x1C
+#define PM_IN_SLPCTL		0x20
+#define PM_WKD			0x30
+#define PM_WKXD			0x34
+#define PM_RD			0x38
+#define PM_WKXA			0x3C
+#define PM_FSD			0x40
+#define PM_TSD			0x44
+#define PM_PSD			0x48
+#define PM_NWKD			0x4C
+#define PM_AWKD			0x50
+#define PM_SSC			0x54
+
+/* VSA2 magic values */
+
+#define VSA_VRC_INDEX		0xAC1C
+#define VSA_VRC_DATA		0xAC1E
+#define VSA_VR_UNLOCK		0xFC53	/* unlock virtual register */
+#define VSA_VR_SIGNATURE	0x0003
+#define VSA_VR_MEM_SIZE		0x0200
+#define AMD_VSA_SIG		0x4132	/* signature is ascii 'VSA2' */
+#define GSW_VSA_SIG		0x534d  /* General Software signature */
+/* GPIO */
+
+#define GPIO_OUTPUT_VAL		0x00
+#define GPIO_OUTPUT_ENABLE	0x04
+#define GPIO_OUTPUT_OPEN_DRAIN	0x08
+#define GPIO_OUTPUT_INVERT	0x0C
+#define GPIO_OUTPUT_AUX1	0x10
+#define GPIO_OUTPUT_AUX2	0x14
+#define GPIO_PULL_UP		0x18
+#define GPIO_PULL_DOWN		0x1C
+#define GPIO_INPUT_ENABLE	0x20
+#define GPIO_INPUT_INVERT	0x24
+#define GPIO_INPUT_FILTER	0x28
+#define GPIO_INPUT_EVENT_COUNT	0x2C
+#define GPIO_READ_BACK		0x30
+#define GPIO_INPUT_AUX1		0x34
+#define GPIO_EVENTS_ENABLE	0x38
+#define GPIO_LOCK_ENABLE	0x3C
+#define GPIO_POSITIVE_EDGE_EN	0x40
+#define GPIO_NEGATIVE_EDGE_EN	0x44
+#define GPIO_POSITIVE_EDGE_STS	0x48
+#define GPIO_NEGATIVE_EDGE_STS	0x4C
+
+#define GPIO_MAP_X		0xE0
+#define GPIO_MAP_Y		0xE4
+#define GPIO_MAP_Z		0xE8
+#define GPIO_MAP_W		0xEC
+
+static inline u32 geode_gpio(unsigned int nr)
+{
+	BUG_ON(nr > 28);
+	return 1 << nr;
+}
+
+extern void geode_gpio_set(u32, unsigned int);
+extern void geode_gpio_clear(u32, unsigned int);
+extern int geode_gpio_isset(u32, unsigned int);
+extern void geode_gpio_setup_event(unsigned int, int, int);
+extern void geode_gpio_set_irq(unsigned int, unsigned int);
+
+static inline void geode_gpio_event_irq(unsigned int gpio, int pair)
+{
+	geode_gpio_setup_event(gpio, pair, 0);
+}
+
+static inline void geode_gpio_event_pme(unsigned int gpio, int pair)
+{
+	geode_gpio_setup_event(gpio, pair, 1);
+}
+
+/* Specific geode tests */
+
+static inline int is_geode_gx(void)
+{
+	return ((boot_cpu_data.x86_vendor == X86_VENDOR_NSC) &&
+		(boot_cpu_data.x86 == 5) &&
+		(boot_cpu_data.x86_model == 5));
+}
+
+static inline int is_geode_lx(void)
+{
+	return ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) &&
+		(boot_cpu_data.x86 == 5) &&
+		(boot_cpu_data.x86_model == 10));
+}
+
+static inline int is_geode(void)
+{
+	return (is_geode_gx() || is_geode_lx());
+}
+
+#ifdef CONFIG_MGEODE_LX
+extern int geode_has_vsa2(void);
+#else
+static inline int geode_has_vsa2(void)
+{
+	return 0;
+}
+#endif
+
+/* MFGPTs */
+
+#define MFGPT_MAX_TIMERS	8
+#define MFGPT_TIMER_ANY		(-1)
+
+#define MFGPT_DOMAIN_WORKING	1
+#define MFGPT_DOMAIN_STANDBY	2
+#define MFGPT_DOMAIN_ANY	(MFGPT_DOMAIN_WORKING | MFGPT_DOMAIN_STANDBY)
+
+#define MFGPT_CMP1		0
+#define MFGPT_CMP2		1
+
+#define MFGPT_EVENT_IRQ		0
+#define MFGPT_EVENT_NMI		1
+#define MFGPT_EVENT_RESET	3
+
+#define MFGPT_REG_CMP1		0
+#define MFGPT_REG_CMP2		2
+#define MFGPT_REG_COUNTER	4
+#define MFGPT_REG_SETUP		6
+
+#define MFGPT_SETUP_CNTEN	(1 << 15)
+#define MFGPT_SETUP_CMP2	(1 << 14)
+#define MFGPT_SETUP_CMP1	(1 << 13)
+#define MFGPT_SETUP_SETUP	(1 << 12)
+#define MFGPT_SETUP_STOPEN	(1 << 11)
+#define MFGPT_SETUP_EXTEN	(1 << 10)
+#define MFGPT_SETUP_REVEN	(1 << 5)
+#define MFGPT_SETUP_CLKSEL	(1 << 4)
+
+static inline void geode_mfgpt_write(int timer, u16 reg, u16 value)
+{
+	u32 base = geode_get_dev_base(GEODE_DEV_MFGPT);
+	outw(value, base + reg + (timer * 8));
+}
+
+static inline u16 geode_mfgpt_read(int timer, u16 reg)
+{
+	u32 base = geode_get_dev_base(GEODE_DEV_MFGPT);
+	return inw(base + reg + (timer * 8));
+}
+
+extern int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable);
+extern int geode_mfgpt_set_irq(int timer, int cmp, int *irq, int enable);
+extern int geode_mfgpt_alloc_timer(int timer, int domain);
+
+#define geode_mfgpt_setup_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 1)
+#define geode_mfgpt_release_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 0)
+
+#ifdef CONFIG_GEODE_MFGPT_TIMER
+extern int __init mfgpt_timer_setup(void);
+#else
+static inline int mfgpt_timer_setup(void) { return 0; }
+#endif
+
+#endif /* ASM_X86__GEODE_H */
diff --git a/arch/x86/include/asm/gpio.h b/arch/x86/include/asm/gpio.h
new file mode 100644
index 000000000000..497fb980d962
--- /dev/null
+++ b/arch/x86/include/asm/gpio.h
@@ -0,0 +1,56 @@
+/*
+ * Generic GPIO API implementation for x86.
+ *
+ * Derived from the generic GPIO API for powerpc:
+ *
+ * Copyright (c) 2007-2008  MontaVista Software, Inc.
+ *
+ * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _ASM_I386_GPIO_H
+#define _ASM_I386_GPIO_H
+
+#include <asm-generic/gpio.h>
+
+#ifdef CONFIG_GPIOLIB
+
+/*
+ * Just call gpiolib.
+ */
+static inline int gpio_get_value(unsigned int gpio)
+{
+	return __gpio_get_value(gpio);
+}
+
+static inline void gpio_set_value(unsigned int gpio, int value)
+{
+	__gpio_set_value(gpio, value);
+}
+
+static inline int gpio_cansleep(unsigned int gpio)
+{
+	return __gpio_cansleep(gpio);
+}
+
+/*
+ * Not implemented, yet.
+ */
+static inline int gpio_to_irq(unsigned int gpio)
+{
+	return -ENOSYS;
+}
+
+static inline int irq_to_gpio(unsigned int irq)
+{
+	return -EINVAL;
+}
+
+#endif /* CONFIG_GPIOLIB */
+
+#endif /* ASM_X86__GPIO_H */
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
new file mode 100644
index 000000000000..000787df66e6
--- /dev/null
+++ b/arch/x86/include/asm/hardirq.h
@@ -0,0 +1,11 @@
+#ifdef CONFIG_X86_32
+# include "hardirq_32.h"
+#else
+# include "hardirq_64.h"
+#endif
+
+extern u64 arch_irq_stat_cpu(unsigned int cpu);
+#define arch_irq_stat_cpu	arch_irq_stat_cpu
+
+extern u64 arch_irq_stat(void);
+#define arch_irq_stat		arch_irq_stat
diff --git a/arch/x86/include/asm/hardirq_32.h b/arch/x86/include/asm/hardirq_32.h
new file mode 100644
index 000000000000..700fe230d919
--- /dev/null
+++ b/arch/x86/include/asm/hardirq_32.h
@@ -0,0 +1,28 @@
+#ifndef ASM_X86__HARDIRQ_32_H
+#define ASM_X86__HARDIRQ_32_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+
+typedef struct {
+	unsigned int __softirq_pending;
+	unsigned long idle_timestamp;
+	unsigned int __nmi_count;	/* arch dependent */
+	unsigned int apic_timer_irqs;	/* arch dependent */
+	unsigned int irq0_irqs;
+	unsigned int irq_resched_count;
+	unsigned int irq_call_count;
+	unsigned int irq_tlb_count;
+	unsigned int irq_thermal_count;
+	unsigned int irq_spurious_count;
+} ____cacheline_aligned irq_cpustat_t;
+
+DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
+
+#define __ARCH_IRQ_STAT
+#define __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member)
+
+void ack_bad_irq(unsigned int irq);
+#include <linux/irq_cpustat.h>
+
+#endif /* ASM_X86__HARDIRQ_32_H */
diff --git a/arch/x86/include/asm/hardirq_64.h b/arch/x86/include/asm/hardirq_64.h
new file mode 100644
index 000000000000..f8bd2919a8ce
--- /dev/null
+++ b/arch/x86/include/asm/hardirq_64.h
@@ -0,0 +1,23 @@
+#ifndef ASM_X86__HARDIRQ_64_H
+#define ASM_X86__HARDIRQ_64_H
+
+#include <linux/threads.h>
+#include <linux/irq.h>
+#include <asm/pda.h>
+#include <asm/apic.h>
+
+/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
+#define MAX_HARDIRQS_PER_CPU NR_VECTORS
+
+#define __ARCH_IRQ_STAT 1
+
+#define local_softirq_pending() read_pda(__softirq_pending)
+
+#define __ARCH_SET_SOFTIRQ_PENDING 1
+
+#define set_softirq_pending(x) write_pda(__softirq_pending, (x))
+#define or_softirq_pending(x)  or_pda(__softirq_pending, (x))
+
+extern void ack_bad_irq(unsigned int irq);
+
+#endif /* ASM_X86__HARDIRQ_64_H */
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
new file mode 100644
index 000000000000..bc3f6a280316
--- /dev/null
+++ b/arch/x86/include/asm/highmem.h
@@ -0,0 +1,82 @@
+/*
+ * highmem.h: virtual kernel memory mappings for high memory
+ *
+ * Used in CONFIG_HIGHMEM systems for memory pages which
+ * are not addressable by direct kernel virtual addresses.
+ *
+ * Copyright (C) 1999 Gerhard Wichert, Siemens AG
+ *		      Gerhard.Wichert@pdb.siemens.de
+ *
+ *
+ * Redesigned the x86 32-bit VM architecture to deal with
+ * up to 16 Terabyte physical memory. With current x86 CPUs
+ * we now support up to 64 Gigabytes physical RAM.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ */
+
+#ifndef ASM_X86__HIGHMEM_H
+#define ASM_X86__HIGHMEM_H
+
+#ifdef __KERNEL__
+
+#include <linux/interrupt.h>
+#include <linux/threads.h>
+#include <asm/kmap_types.h>
+#include <asm/tlbflush.h>
+#include <asm/paravirt.h>
+
+/* declarations for highmem.c */
+extern unsigned long highstart_pfn, highend_pfn;
+
+extern pte_t *kmap_pte;
+extern pgprot_t kmap_prot;
+extern pte_t *pkmap_page_table;
+
+/*
+ * Right now we initialize only a single pte table. It can be extended
+ * easily, subsequent pte tables have to be allocated in one physical
+ * chunk of RAM.
+ */
+/*
+ * Ordering is:
+ *
+ * FIXADDR_TOP
+ * 			fixed_addresses
+ * FIXADDR_START
+ * 			temp fixed addresses
+ * FIXADDR_BOOT_START
+ * 			Persistent kmap area
+ * PKMAP_BASE
+ * VMALLOC_END
+ * 			Vmalloc area
+ * VMALLOC_START
+ * high_memory
+ */
+#define LAST_PKMAP_MASK (LAST_PKMAP-1)
+#define PKMAP_NR(virt)  ((virt-PKMAP_BASE) >> PAGE_SHIFT)
+#define PKMAP_ADDR(nr)  (PKMAP_BASE + ((nr) << PAGE_SHIFT))
+
+extern void *kmap_high(struct page *page);
+extern void kunmap_high(struct page *page);
+
+void *kmap(struct page *page);
+void kunmap(struct page *page);
+void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot);
+void *kmap_atomic(struct page *page, enum km_type type);
+void kunmap_atomic(void *kvaddr, enum km_type type);
+void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
+struct page *kmap_atomic_to_page(void *ptr);
+
+#ifndef CONFIG_PARAVIRT
+#define kmap_atomic_pte(page, type)	kmap_atomic(page, type)
+#endif
+
+#define flush_cache_kmaps()	do { } while (0)
+
+extern void add_highpages_with_active_regions(int nid, unsigned long start_pfn,
+					unsigned long end_pfn);
+
+#endif /* __KERNEL__ */
+
+#endif /* ASM_X86__HIGHMEM_H */
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
new file mode 100644
index 000000000000..58b273f6ef07
--- /dev/null
+++ b/arch/x86/include/asm/hpet.h
@@ -0,0 +1,114 @@
+#ifndef ASM_X86__HPET_H
+#define ASM_X86__HPET_H
+
+#include <linux/msi.h>
+
+#ifdef CONFIG_HPET_TIMER
+
+#define HPET_MMAP_SIZE		1024
+
+#define HPET_ID			0x000
+#define HPET_PERIOD		0x004
+#define HPET_CFG		0x010
+#define HPET_STATUS		0x020
+#define HPET_COUNTER		0x0f0
+
+#define HPET_Tn_CFG(n)		(0x100 + 0x20 * n)
+#define HPET_Tn_CMP(n)		(0x108 + 0x20 * n)
+#define HPET_Tn_ROUTE(n)	(0x110 + 0x20 * n)
+
+#define HPET_T0_CFG		0x100
+#define HPET_T0_CMP		0x108
+#define HPET_T0_ROUTE		0x110
+#define HPET_T1_CFG		0x120
+#define HPET_T1_CMP		0x128
+#define HPET_T1_ROUTE		0x130
+#define HPET_T2_CFG		0x140
+#define HPET_T2_CMP		0x148
+#define HPET_T2_ROUTE		0x150
+
+#define HPET_ID_REV		0x000000ff
+#define HPET_ID_NUMBER		0x00001f00
+#define HPET_ID_64BIT		0x00002000
+#define HPET_ID_LEGSUP		0x00008000
+#define HPET_ID_VENDOR		0xffff0000
+#define	HPET_ID_NUMBER_SHIFT	8
+#define HPET_ID_VENDOR_SHIFT	16
+
+#define HPET_ID_VENDOR_8086	0x8086
+
+#define HPET_CFG_ENABLE		0x001
+#define HPET_CFG_LEGACY		0x002
+#define	HPET_LEGACY_8254	2
+#define	HPET_LEGACY_RTC		8
+
+#define HPET_TN_LEVEL		0x0002
+#define HPET_TN_ENABLE		0x0004
+#define HPET_TN_PERIODIC	0x0008
+#define HPET_TN_PERIODIC_CAP	0x0010
+#define HPET_TN_64BIT_CAP	0x0020
+#define HPET_TN_SETVAL		0x0040
+#define HPET_TN_32BIT		0x0100
+#define HPET_TN_ROUTE		0x3e00
+#define HPET_TN_FSB		0x4000
+#define HPET_TN_FSB_CAP		0x8000
+#define HPET_TN_ROUTE_SHIFT	9
+
+/* Max HPET Period is 10^8 femto sec as in HPET spec */
+#define HPET_MAX_PERIOD		100000000UL
+/*
+ * Min HPET period is 10^5 femto sec just for safety. If it is less than this,
+ * then 32 bit HPET counter wrapsaround in less than 0.5 sec.
+ */
+#define HPET_MIN_PERIOD		100000UL
+
+/* hpet memory map physical address */
+extern unsigned long hpet_address;
+extern unsigned long force_hpet_address;
+extern int hpet_force_user;
+extern int is_hpet_enabled(void);
+extern int hpet_enable(void);
+extern void hpet_disable(void);
+extern unsigned long hpet_readl(unsigned long a);
+extern void force_hpet_resume(void);
+
+extern void hpet_msi_unmask(unsigned int irq);
+extern void hpet_msi_mask(unsigned int irq);
+extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg);
+extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg);
+
+#ifdef CONFIG_PCI_MSI
+extern int arch_setup_hpet_msi(unsigned int irq);
+#else
+static inline int arch_setup_hpet_msi(unsigned int irq)
+{
+	return -EINVAL;
+}
+#endif
+
+#ifdef CONFIG_HPET_EMULATE_RTC
+
+#include <linux/interrupt.h>
+
+typedef irqreturn_t (*rtc_irq_handler)(int interrupt, void *cookie);
+extern int hpet_mask_rtc_irq_bit(unsigned long bit_mask);
+extern int hpet_set_rtc_irq_bit(unsigned long bit_mask);
+extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min,
+			       unsigned char sec);
+extern int hpet_set_periodic_freq(unsigned long freq);
+extern int hpet_rtc_dropped_irq(void);
+extern int hpet_rtc_timer_init(void);
+extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id);
+extern int hpet_register_irq_handler(rtc_irq_handler handler);
+extern void hpet_unregister_irq_handler(rtc_irq_handler handler);
+
+#endif /* CONFIG_HPET_EMULATE_RTC */
+
+#else /* CONFIG_HPET_TIMER */
+
+static inline int hpet_enable(void) { return 0; }
+static inline int is_hpet_enabled(void) { return 0; }
+#define hpet_readl(a) 0
+
+#endif
+#endif /* ASM_X86__HPET_H */
diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
new file mode 100644
index 000000000000..0b7ec5dc0884
--- /dev/null
+++ b/arch/x86/include/asm/hugetlb.h
@@ -0,0 +1,93 @@
+#ifndef ASM_X86__HUGETLB_H
+#define ASM_X86__HUGETLB_H
+
+#include <asm/page.h>
+
+
+static inline int is_hugepage_only_range(struct mm_struct *mm,
+					 unsigned long addr,
+					 unsigned long len) {
+	return 0;
+}
+
+/*
+ * If the arch doesn't supply something else, assume that hugepage
+ * size aligned regions are ok without further preparation.
+ */
+static inline int prepare_hugepage_range(struct file *file,
+			unsigned long addr, unsigned long len)
+{
+	struct hstate *h = hstate_file(file);
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (addr & ~huge_page_mask(h))
+		return -EINVAL;
+	return 0;
+}
+
+static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) {
+}
+
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+					  unsigned long addr, unsigned long end,
+					  unsigned long floor,
+					  unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep)
+{
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep)
+{
+}
+
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+					   unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+					     unsigned long addr, pte_t *ptep,
+					     pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+
+static inline int arch_prepare_hugepage(struct page *page)
+{
+	return 0;
+}
+
+static inline void arch_release_hugepage(struct page *page)
+{
+}
+
+#endif /* ASM_X86__HUGETLB_H */
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
new file mode 100644
index 000000000000..749d042f0556
--- /dev/null
+++ b/arch/x86/include/asm/hw_irq.h
@@ -0,0 +1,131 @@
+#ifndef ASM_X86__HW_IRQ_H
+#define ASM_X86__HW_IRQ_H
+
+/*
+ * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ * moved some of the old arch/i386/kernel/irq.h to here. VY
+ *
+ * IRQ/IPI changes taken from work by Thomas Radke
+ * <tomsoft@informatik.tu-chemnitz.de>
+ *
+ * hacked by Andi Kleen for x86-64.
+ * unified by tglx
+ */
+
+#include <asm/irq_vectors.h>
+
+#ifndef __ASSEMBLY__
+
+#include <linux/percpu.h>
+#include <linux/profile.h>
+#include <linux/smp.h>
+
+#include <asm/atomic.h>
+#include <asm/irq.h>
+#include <asm/sections.h>
+
+#define platform_legacy_irq(irq)	((irq) < 16)
+
+/* Interrupt handlers registered during init_IRQ */
+extern void apic_timer_interrupt(void);
+extern void error_interrupt(void);
+extern void spurious_interrupt(void);
+extern void thermal_interrupt(void);
+extern void reschedule_interrupt(void);
+
+extern void invalidate_interrupt(void);
+extern void invalidate_interrupt0(void);
+extern void invalidate_interrupt1(void);
+extern void invalidate_interrupt2(void);
+extern void invalidate_interrupt3(void);
+extern void invalidate_interrupt4(void);
+extern void invalidate_interrupt5(void);
+extern void invalidate_interrupt6(void);
+extern void invalidate_interrupt7(void);
+
+extern void irq_move_cleanup_interrupt(void);
+extern void threshold_interrupt(void);
+
+extern void call_function_interrupt(void);
+extern void call_function_single_interrupt(void);
+
+/* PIC specific functions */
+extern void disable_8259A_irq(unsigned int irq);
+extern void enable_8259A_irq(unsigned int irq);
+extern int i8259A_irq_pending(unsigned int irq);
+extern void make_8259A_irq(unsigned int irq);
+extern void init_8259A(int aeoi);
+
+/* IOAPIC */
+#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
+extern unsigned long io_apic_irqs;
+
+extern void init_VISWS_APIC_irqs(void);
+extern void setup_IO_APIC(void);
+extern void disable_IO_APIC(void);
+extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
+extern void setup_ioapic_dest(void);
+
+#ifdef CONFIG_X86_64
+extern void enable_IO_APIC(void);
+#endif
+
+/* IPI functions */
+#ifdef CONFIG_X86_32
+extern void send_IPI_self(int vector);
+#endif
+extern void send_IPI(int dest, int vector);
+
+/* Statistics */
+extern atomic_t irq_err_count;
+extern atomic_t irq_mis_count;
+
+/* EISA */
+extern void eisa_set_level_irq(unsigned int irq);
+
+/* Voyager functions */
+extern asmlinkage void vic_cpi_interrupt(void);
+extern asmlinkage void vic_sys_interrupt(void);
+extern asmlinkage void vic_cmn_interrupt(void);
+extern asmlinkage void qic_timer_interrupt(void);
+extern asmlinkage void qic_invalidate_interrupt(void);
+extern asmlinkage void qic_reschedule_interrupt(void);
+extern asmlinkage void qic_enable_irq_interrupt(void);
+extern asmlinkage void qic_call_function_interrupt(void);
+
+/* SMP */
+extern void smp_apic_timer_interrupt(struct pt_regs *);
+extern void smp_spurious_interrupt(struct pt_regs *);
+extern void smp_error_interrupt(struct pt_regs *);
+#ifdef CONFIG_X86_SMP
+extern void smp_reschedule_interrupt(struct pt_regs *);
+extern void smp_call_function_interrupt(struct pt_regs *);
+extern void smp_call_function_single_interrupt(struct pt_regs *);
+#ifdef CONFIG_X86_32
+extern void smp_invalidate_interrupt(struct pt_regs *);
+#else
+extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
+#endif
+#endif
+
+#ifdef CONFIG_X86_32
+extern void (*const interrupt[NR_VECTORS])(void);
+#endif
+
+typedef int vector_irq_t[NR_VECTORS];
+DECLARE_PER_CPU(vector_irq_t, vector_irq);
+
+#ifdef CONFIG_X86_IO_APIC
+extern void lock_vector_lock(void);
+extern void unlock_vector_lock(void);
+extern void __setup_vector_irq(int cpu);
+#else
+static inline void lock_vector_lock(void) {}
+static inline void unlock_vector_lock(void) {}
+static inline void __setup_vector_irq(int cpu) {}
+#endif
+
+#endif /* !ASSEMBLY_ */
+
+#endif /* ASM_X86__HW_IRQ_H */
diff --git a/arch/x86/include/asm/hypertransport.h b/arch/x86/include/asm/hypertransport.h
new file mode 100644
index 000000000000..cc011a3bc1c2
--- /dev/null
+++ b/arch/x86/include/asm/hypertransport.h
@@ -0,0 +1,45 @@
+#ifndef ASM_X86__HYPERTRANSPORT_H
+#define ASM_X86__HYPERTRANSPORT_H
+
+/*
+ * Constants for x86 Hypertransport Interrupts.
+ */
+
+#define HT_IRQ_LOW_BASE			0xf8000000
+
+#define HT_IRQ_LOW_VECTOR_SHIFT		16
+#define HT_IRQ_LOW_VECTOR_MASK		0x00ff0000
+#define HT_IRQ_LOW_VECTOR(v)						\
+	(((v) << HT_IRQ_LOW_VECTOR_SHIFT) & HT_IRQ_LOW_VECTOR_MASK)
+
+#define HT_IRQ_LOW_DEST_ID_SHIFT	8
+#define HT_IRQ_LOW_DEST_ID_MASK		0x0000ff00
+#define HT_IRQ_LOW_DEST_ID(v)						\
+	(((v) << HT_IRQ_LOW_DEST_ID_SHIFT) & HT_IRQ_LOW_DEST_ID_MASK)
+
+#define HT_IRQ_LOW_DM_PHYSICAL		0x0000000
+#define HT_IRQ_LOW_DM_LOGICAL		0x0000040
+
+#define HT_IRQ_LOW_RQEOI_EDGE		0x0000000
+#define HT_IRQ_LOW_RQEOI_LEVEL		0x0000020
+
+
+#define HT_IRQ_LOW_MT_FIXED		0x0000000
+#define HT_IRQ_LOW_MT_ARBITRATED	0x0000004
+#define HT_IRQ_LOW_MT_SMI		0x0000008
+#define HT_IRQ_LOW_MT_NMI		0x000000c
+#define HT_IRQ_LOW_MT_INIT		0x0000010
+#define HT_IRQ_LOW_MT_STARTUP		0x0000014
+#define HT_IRQ_LOW_MT_EXTINT		0x0000018
+#define HT_IRQ_LOW_MT_LINT1		0x000008c
+#define HT_IRQ_LOW_MT_LINT0		0x0000098
+
+#define HT_IRQ_LOW_IRQ_MASKED		0x0000001
+
+
+#define HT_IRQ_HIGH_DEST_ID_SHIFT	0
+#define HT_IRQ_HIGH_DEST_ID_MASK	0x00ffffff
+#define HT_IRQ_HIGH_DEST_ID(v)						\
+	((((v) >> 8) << HT_IRQ_HIGH_DEST_ID_SHIFT) & HT_IRQ_HIGH_DEST_ID_MASK)
+
+#endif /* ASM_X86__HYPERTRANSPORT_H */
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
new file mode 100644
index 000000000000..9ba862a4eac0
--- /dev/null
+++ b/arch/x86/include/asm/i387.h
@@ -0,0 +1,400 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef ASM_X86__I387_H
+#define ASM_X86__I387_H
+
+#include <linux/sched.h>
+#include <linux/kernel_stat.h>
+#include <linux/regset.h>
+#include <linux/hardirq.h>
+#include <asm/asm.h>
+#include <asm/processor.h>
+#include <asm/sigcontext.h>
+#include <asm/user.h>
+#include <asm/uaccess.h>
+#include <asm/xsave.h>
+
+extern unsigned int sig_xstate_size;
+extern void fpu_init(void);
+extern void mxcsr_feature_mask_init(void);
+extern int init_fpu(struct task_struct *child);
+extern asmlinkage void math_state_restore(void);
+extern void init_thread_xstate(void);
+extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
+
+extern user_regset_active_fn fpregs_active, xfpregs_active;
+extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get;
+extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set;
+
+extern struct _fpx_sw_bytes fx_sw_reserved;
+#ifdef CONFIG_IA32_EMULATION
+extern unsigned int sig_xstate_ia32_size;
+extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
+struct _fpstate_ia32;
+struct _xstate_ia32;
+extern int save_i387_xstate_ia32(void __user *buf);
+extern int restore_i387_xstate_ia32(void __user *buf);
+#endif
+
+#define X87_FSW_ES (1 << 7)	/* Exception Summary */
+
+#ifdef CONFIG_X86_64
+
+/* Ignore delayed exceptions from user space */
+static inline void tolerant_fwait(void)
+{
+	asm volatile("1: fwait\n"
+		     "2:\n"
+		     _ASM_EXTABLE(1b, 2b));
+}
+
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
+{
+	int err;
+
+	asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
+		     "2:\n"
+		     ".section .fixup,\"ax\"\n"
+		     "3:  movl $-1,%[err]\n"
+		     "    jmp  2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err)
+#if 0 /* See comment in __save_init_fpu() below. */
+		     : [fx] "r" (fx), "m" (*fx), "0" (0));
+#else
+		     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
+#endif
+	return err;
+}
+
+static inline int restore_fpu_checking(struct task_struct *tsk)
+{
+	if (task_thread_info(tsk)->status & TS_XSAVE)
+		return xrstor_checking(&tsk->thread.xstate->xsave);
+	else
+		return fxrstor_checking(&tsk->thread.xstate->fxsave);
+}
+
+/* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
+   is pending. Clear the x87 state here by setting it to fixed
+   values. The kernel data segment can be sometimes 0 and sometimes
+   new user value. Both should be ok.
+   Use the PDA as safe address because it should be already in L1. */
+static inline void clear_fpu_state(struct task_struct *tsk)
+{
+	struct xsave_struct *xstate = &tsk->thread.xstate->xsave;
+	struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
+
+	/*
+	 * xsave header may indicate the init state of the FP.
+	 */
+	if ((task_thread_info(tsk)->status & TS_XSAVE) &&
+	    !(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
+		return;
+
+	if (unlikely(fx->swd & X87_FSW_ES))
+		asm volatile("fnclex");
+	alternative_input(ASM_NOP8 ASM_NOP2,
+			  "    emms\n"		/* clear stack tags */
+			  "    fildl %%gs:0",	/* load to clear state */
+			  X86_FEATURE_FXSAVE_LEAK);
+}
+
+static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
+{
+	int err;
+
+	asm volatile("1:  rex64/fxsave (%[fx])\n\t"
+		     "2:\n"
+		     ".section .fixup,\"ax\"\n"
+		     "3:  movl $-1,%[err]\n"
+		     "    jmp  2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err), "=m" (*fx)
+#if 0 /* See comment in __fxsave_clear() below. */
+		     : [fx] "r" (fx), "0" (0));
+#else
+		     : [fx] "cdaSDb" (fx), "0" (0));
+#endif
+	if (unlikely(err) &&
+	    __clear_user(fx, sizeof(struct i387_fxsave_struct)))
+		err = -EFAULT;
+	/* No need to clear here because the caller clears USED_MATH */
+	return err;
+}
+
+static inline void fxsave(struct task_struct *tsk)
+{
+	/* Using "rex64; fxsave %0" is broken because, if the memory operand
+	   uses any extended registers for addressing, a second REX prefix
+	   will be generated (to the assembler, rex64 followed by semicolon
+	   is a separate instruction), and hence the 64-bitness is lost. */
+#if 0
+	/* Using "fxsaveq %0" would be the ideal choice, but is only supported
+	   starting with gas 2.16. */
+	__asm__ __volatile__("fxsaveq %0"
+			     : "=m" (tsk->thread.xstate->fxsave));
+#elif 0
+	/* Using, as a workaround, the properly prefixed form below isn't
+	   accepted by any binutils version so far released, complaining that
+	   the same type of prefix is used twice if an extended register is
+	   needed for addressing (fix submitted to mainline 2005-11-21). */
+	__asm__ __volatile__("rex64/fxsave %0"
+			     : "=m" (tsk->thread.xstate->fxsave));
+#else
+	/* This, however, we can work around by forcing the compiler to select
+	   an addressing mode that doesn't require extended registers. */
+	__asm__ __volatile__("rex64/fxsave (%1)"
+			     : "=m" (tsk->thread.xstate->fxsave)
+			     : "cdaSDb" (&tsk->thread.xstate->fxsave));
+#endif
+}
+
+static inline void __save_init_fpu(struct task_struct *tsk)
+{
+	if (task_thread_info(tsk)->status & TS_XSAVE)
+		xsave(tsk);
+	else
+		fxsave(tsk);
+
+	clear_fpu_state(tsk);
+	task_thread_info(tsk)->status &= ~TS_USEDFPU;
+}
+
+#else  /* CONFIG_X86_32 */
+
+extern void finit(void);
+
+static inline void tolerant_fwait(void)
+{
+	asm volatile("fnclex ; fwait");
+}
+
+static inline void restore_fpu(struct task_struct *tsk)
+{
+	if (task_thread_info(tsk)->status & TS_XSAVE) {
+		xrstor_checking(&tsk->thread.xstate->xsave);
+		return;
+	}
+	/*
+	 * The "nop" is needed to make the instructions the same
+	 * length.
+	 */
+	alternative_input(
+		"nop ; frstor %1",
+		"fxrstor %1",
+		X86_FEATURE_FXSR,
+		"m" (tsk->thread.xstate->fxsave));
+}
+
+/* We need a safe address that is cheap to find and that is already
+   in L1 during context switch. The best choices are unfortunately
+   different for UP and SMP */
+#ifdef CONFIG_SMP
+#define safe_address (__per_cpu_offset[0])
+#else
+#define safe_address (kstat_cpu(0).cpustat.user)
+#endif
+
+/*
+ * These must be called with preempt disabled
+ */
+static inline void __save_init_fpu(struct task_struct *tsk)
+{
+	if (task_thread_info(tsk)->status & TS_XSAVE) {
+		struct xsave_struct *xstate = &tsk->thread.xstate->xsave;
+		struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
+
+		xsave(tsk);
+
+		/*
+		 * xsave header may indicate the init state of the FP.
+		 */
+		if (!(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
+			goto end;
+
+		if (unlikely(fx->swd & X87_FSW_ES))
+			asm volatile("fnclex");
+
+		/*
+		 * we can do a simple return here or be paranoid :)
+		 */
+		goto clear_state;
+	}
+
+	/* Use more nops than strictly needed in case the compiler
+	   varies code */
+	alternative_input(
+		"fnsave %[fx] ;fwait;" GENERIC_NOP8 GENERIC_NOP4,
+		"fxsave %[fx]\n"
+		"bt $7,%[fsw] ; jnc 1f ; fnclex\n1:",
+		X86_FEATURE_FXSR,
+		[fx] "m" (tsk->thread.xstate->fxsave),
+		[fsw] "m" (tsk->thread.xstate->fxsave.swd) : "memory");
+clear_state:
+	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+	   is pending.  Clear the x87 state here by setting it to fixed
+	   values. safe_address is a random variable that should be in L1 */
+	alternative_input(
+		GENERIC_NOP8 GENERIC_NOP2,
+		"emms\n\t"	  	/* clear stack tags */
+		"fildl %[addr]", 	/* set F?P to defined value */
+		X86_FEATURE_FXSAVE_LEAK,
+		[addr] "m" (safe_address));
+end:
+	task_thread_info(tsk)->status &= ~TS_USEDFPU;
+}
+
+#endif	/* CONFIG_X86_64 */
+
+/*
+ * Signal frame handlers...
+ */
+extern int save_i387_xstate(void __user *buf);
+extern int restore_i387_xstate(void __user *buf);
+
+static inline void __unlazy_fpu(struct task_struct *tsk)
+{
+	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+		__save_init_fpu(tsk);
+		stts();
+	} else
+		tsk->fpu_counter = 0;
+}
+
+static inline void __clear_fpu(struct task_struct *tsk)
+{
+	if (task_thread_info(tsk)->status & TS_USEDFPU) {
+		tolerant_fwait();
+		task_thread_info(tsk)->status &= ~TS_USEDFPU;
+		stts();
+	}
+}
+
+static inline void kernel_fpu_begin(void)
+{
+	struct thread_info *me = current_thread_info();
+	preempt_disable();
+	if (me->status & TS_USEDFPU)
+		__save_init_fpu(me->task);
+	else
+		clts();
+}
+
+static inline void kernel_fpu_end(void)
+{
+	stts();
+	preempt_enable();
+}
+
+/*
+ * Some instructions like VIA's padlock instructions generate a spurious
+ * DNA fault but don't modify SSE registers. And these instructions
+ * get used from interrupt context aswell. To prevent these kernel instructions
+ * in interrupt context interact wrongly with other user/kernel fpu usage, we
+ * should use them only in the context of irq_ts_save/restore()
+ */
+static inline int irq_ts_save(void)
+{
+	/*
+	 * If we are in process context, we are ok to take a spurious DNA fault.
+	 * Otherwise, doing clts() in process context require pre-emption to
+	 * be disabled or some heavy lifting like kernel_fpu_begin()
+	 */
+	if (!in_interrupt())
+		return 0;
+
+	if (read_cr0() & X86_CR0_TS) {
+		clts();
+		return 1;
+	}
+
+	return 0;
+}
+
+static inline void irq_ts_restore(int TS_state)
+{
+	if (TS_state)
+		stts();
+}
+
+#ifdef CONFIG_X86_64
+
+static inline void save_init_fpu(struct task_struct *tsk)
+{
+	__save_init_fpu(tsk);
+	stts();
+}
+
+#define unlazy_fpu	__unlazy_fpu
+#define clear_fpu	__clear_fpu
+
+#else  /* CONFIG_X86_32 */
+
+/*
+ * These disable preemption on their own and are safe
+ */
+static inline void save_init_fpu(struct task_struct *tsk)
+{
+	preempt_disable();
+	__save_init_fpu(tsk);
+	stts();
+	preempt_enable();
+}
+
+static inline void unlazy_fpu(struct task_struct *tsk)
+{
+	preempt_disable();
+	__unlazy_fpu(tsk);
+	preempt_enable();
+}
+
+static inline void clear_fpu(struct task_struct *tsk)
+{
+	preempt_disable();
+	__clear_fpu(tsk);
+	preempt_enable();
+}
+
+#endif	/* CONFIG_X86_64 */
+
+/*
+ * i387 state interaction
+ */
+static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
+{
+	if (cpu_has_fxsr) {
+		return tsk->thread.xstate->fxsave.cwd;
+	} else {
+		return (unsigned short)tsk->thread.xstate->fsave.cwd;
+	}
+}
+
+static inline unsigned short get_fpu_swd(struct task_struct *tsk)
+{
+	if (cpu_has_fxsr) {
+		return tsk->thread.xstate->fxsave.swd;
+	} else {
+		return (unsigned short)tsk->thread.xstate->fsave.swd;
+	}
+}
+
+static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
+{
+	if (cpu_has_xmm) {
+		return tsk->thread.xstate->fxsave.mxcsr;
+	} else {
+		return MXCSR_DEFAULT;
+	}
+}
+
+#endif /* ASM_X86__I387_H */
diff --git a/arch/x86/include/asm/i8253.h b/arch/x86/include/asm/i8253.h
new file mode 100644
index 000000000000..15a5b530044e
--- /dev/null
+++ b/arch/x86/include/asm/i8253.h
@@ -0,0 +1,18 @@
+#ifndef ASM_X86__I8253_H
+#define ASM_X86__I8253_H
+
+/* i8253A PIT registers */
+#define PIT_MODE		0x43
+#define PIT_CH0			0x40
+#define PIT_CH2			0x42
+
+extern spinlock_t i8253_lock;
+
+extern struct clock_event_device *global_clock_event;
+
+extern void setup_pit_timer(void);
+
+#define inb_pit		inb_p
+#define outb_pit	outb_p
+
+#endif /* ASM_X86__I8253_H */
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
new file mode 100644
index 000000000000..23c1b3baaecd
--- /dev/null
+++ b/arch/x86/include/asm/i8259.h
@@ -0,0 +1,63 @@
+#ifndef ASM_X86__I8259_H
+#define ASM_X86__I8259_H
+
+#include <linux/delay.h>
+
+extern unsigned int cached_irq_mask;
+
+#define __byte(x, y)		(((unsigned char *)&(y))[x])
+#define cached_master_mask	(__byte(0, cached_irq_mask))
+#define cached_slave_mask	(__byte(1, cached_irq_mask))
+
+/* i8259A PIC registers */
+#define PIC_MASTER_CMD		0x20
+#define PIC_MASTER_IMR		0x21
+#define PIC_MASTER_ISR		PIC_MASTER_CMD
+#define PIC_MASTER_POLL		PIC_MASTER_ISR
+#define PIC_MASTER_OCW3		PIC_MASTER_ISR
+#define PIC_SLAVE_CMD		0xa0
+#define PIC_SLAVE_IMR		0xa1
+
+/* i8259A PIC related value */
+#define PIC_CASCADE_IR		2
+#define MASTER_ICW4_DEFAULT	0x01
+#define SLAVE_ICW4_DEFAULT	0x01
+#define PIC_ICW4_AEOI		2
+
+extern spinlock_t i8259A_lock;
+
+extern void init_8259A(int auto_eoi);
+extern void enable_8259A_irq(unsigned int irq);
+extern void disable_8259A_irq(unsigned int irq);
+extern unsigned int startup_8259A_irq(unsigned int irq);
+
+/* the PIC may need a careful delay on some platforms, hence specific calls */
+static inline unsigned char inb_pic(unsigned int port)
+{
+	unsigned char value = inb(port);
+
+	/*
+	 * delay for some accesses to PIC on motherboard or in chipset
+	 * must be at least one microsecond, so be safe here:
+	 */
+	udelay(2);
+
+	return value;
+}
+
+static inline void outb_pic(unsigned char value, unsigned int port)
+{
+	outb(value, port);
+	/*
+	 * delay for some accesses to PIC on motherboard or in chipset
+	 * must be at least one microsecond, so be safe here:
+	 */
+	udelay(2);
+}
+
+extern struct irq_chip i8259A_chip;
+
+extern void mask_8259A(void);
+extern void unmask_8259A(void);
+
+#endif /* ASM_X86__I8259_H */
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
new file mode 100644
index 000000000000..f932f7ad51dd
--- /dev/null
+++ b/arch/x86/include/asm/ia32.h
@@ -0,0 +1,170 @@
+#ifndef ASM_X86__IA32_H
+#define ASM_X86__IA32_H
+
+
+#ifdef CONFIG_IA32_EMULATION
+
+#include <linux/compat.h>
+
+/*
+ * 32 bit structures for IA32 support.
+ */
+
+#include <asm/sigcontext32.h>
+
+/* signal.h */
+struct sigaction32 {
+	unsigned int  sa_handler;	/* Really a pointer, but need to deal
+					   with 32 bits */
+	unsigned int sa_flags;
+	unsigned int sa_restorer;	/* Another 32 bit pointer */
+	compat_sigset_t sa_mask;	/* A 32 bit mask */
+};
+
+struct old_sigaction32 {
+	unsigned int  sa_handler;	/* Really a pointer, but need to deal
+					   with 32 bits */
+	compat_old_sigset_t sa_mask;	/* A 32 bit mask */
+	unsigned int sa_flags;
+	unsigned int sa_restorer;	/* Another 32 bit pointer */
+};
+
+typedef struct sigaltstack_ia32 {
+	unsigned int	ss_sp;
+	int		ss_flags;
+	unsigned int	ss_size;
+} stack_ia32_t;
+
+struct ucontext_ia32 {
+	unsigned int	  uc_flags;
+	unsigned int 	  uc_link;
+	stack_ia32_t	  uc_stack;
+	struct sigcontext_ia32 uc_mcontext;
+	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
+};
+
+/* This matches struct stat64 in glibc2.2, hence the absolutely
+ * insane amounts of padding around dev_t's.
+ */
+struct stat64 {
+	unsigned long long	st_dev;
+	unsigned char		__pad0[4];
+
+#define STAT64_HAS_BROKEN_ST_INO	1
+	unsigned int		__st_ino;
+
+	unsigned int		st_mode;
+	unsigned int		st_nlink;
+
+	unsigned int		st_uid;
+	unsigned int		st_gid;
+
+	unsigned long long	st_rdev;
+	unsigned char		__pad3[4];
+
+	long long		st_size;
+	unsigned int		st_blksize;
+
+	long long		st_blocks;/* Number 512-byte blocks allocated */
+
+	unsigned 		st_atime;
+	unsigned 		st_atime_nsec;
+	unsigned 		st_mtime;
+	unsigned 		st_mtime_nsec;
+	unsigned 		st_ctime;
+	unsigned 		st_ctime_nsec;
+
+	unsigned long long	st_ino;
+} __attribute__((packed));
+
+typedef struct compat_siginfo {
+	int si_signo;
+	int si_errno;
+	int si_code;
+
+	union {
+		int _pad[((128 / sizeof(int)) - 3)];
+
+		/* kill() */
+		struct {
+			unsigned int _pid;	/* sender's pid */
+			unsigned int _uid;	/* sender's uid */
+		} _kill;
+
+		/* POSIX.1b timers */
+		struct {
+			compat_timer_t _tid;	/* timer id */
+			int _overrun;		/* overrun count */
+			compat_sigval_t _sigval;	/* same as below */
+			int _sys_private;	/* not to be passed to user */
+			int _overrun_incr;	/* amount to add to overrun */
+		} _timer;
+
+		/* POSIX.1b signals */
+		struct {
+			unsigned int _pid;	/* sender's pid */
+			unsigned int _uid;	/* sender's uid */
+			compat_sigval_t _sigval;
+		} _rt;
+
+		/* SIGCHLD */
+		struct {
+			unsigned int _pid;	/* which child */
+			unsigned int _uid;	/* sender's uid */
+			int _status;		/* exit code */
+			compat_clock_t _utime;
+			compat_clock_t _stime;
+		} _sigchld;
+
+		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
+		struct {
+			unsigned int _addr;	/* faulting insn/memory ref. */
+		} _sigfault;
+
+		/* SIGPOLL */
+		struct {
+			int _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
+			int _fd;
+		} _sigpoll;
+	} _sifields;
+} compat_siginfo_t;
+
+struct sigframe32 {
+	u32 pretcode;
+	int sig;
+	struct sigcontext_ia32 sc;
+	struct _fpstate_ia32 fpstate;
+	unsigned int extramask[_COMPAT_NSIG_WORDS-1];
+};
+
+struct rt_sigframe32 {
+	u32 pretcode;
+	int sig;
+	u32 pinfo;
+	u32 puc;
+	compat_siginfo_t info;
+	struct ucontext_ia32 uc;
+	struct _fpstate_ia32 fpstate;
+};
+
+struct ustat32 {
+	__u32			f_tfree;
+	compat_ino_t		f_tinode;
+	char			f_fname[6];
+	char			f_fpack[6];
+};
+
+#define IA32_STACK_TOP IA32_PAGE_OFFSET
+
+#ifdef __KERNEL__
+struct linux_binprm;
+extern int ia32_setup_arg_pages(struct linux_binprm *bprm,
+				unsigned long stack_top, int exec_stack);
+struct mm_struct;
+extern void ia32_pick_mmap_layout(struct mm_struct *mm);
+
+#endif
+
+#endif /* !CONFIG_IA32_SUPPORT */
+
+#endif /* ASM_X86__IA32_H */
diff --git a/arch/x86/include/asm/ia32_unistd.h b/arch/x86/include/asm/ia32_unistd.h
new file mode 100644
index 000000000000..dbd887d8a5a5
--- /dev/null
+++ b/arch/x86/include/asm/ia32_unistd.h
@@ -0,0 +1,18 @@
+#ifndef ASM_X86__IA32_UNISTD_H
+#define ASM_X86__IA32_UNISTD_H
+
+/*
+ * This file contains the system call numbers of the ia32 port,
+ * this is for the kernel only.
+ * Only add syscalls here where some part of the kernel needs to know
+ * the number. This should be otherwise in sync with asm-x86/unistd_32.h. -AK
+ */
+
+#define __NR_ia32_restart_syscall 0
+#define __NR_ia32_exit		  1
+#define __NR_ia32_read		  3
+#define __NR_ia32_write		  4
+#define __NR_ia32_sigreturn	119
+#define __NR_ia32_rt_sigreturn	173
+
+#endif /* ASM_X86__IA32_UNISTD_H */
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
new file mode 100644
index 000000000000..baa3f783d27d
--- /dev/null
+++ b/arch/x86/include/asm/idle.h
@@ -0,0 +1,15 @@
+#ifndef ASM_X86__IDLE_H
+#define ASM_X86__IDLE_H
+
+#define IDLE_START 1
+#define IDLE_END 2
+
+struct notifier_block;
+void idle_notifier_register(struct notifier_block *n);
+
+void enter_idle(void);
+void exit_idle(void);
+
+void c1e_remove_cpu(int cpu);
+
+#endif /* ASM_X86__IDLE_H */
diff --git a/arch/x86/include/asm/intel_arch_perfmon.h b/arch/x86/include/asm/intel_arch_perfmon.h
new file mode 100644
index 000000000000..07c03c6c9a16
--- /dev/null
+++ b/arch/x86/include/asm/intel_arch_perfmon.h
@@ -0,0 +1,31 @@
+#ifndef ASM_X86__INTEL_ARCH_PERFMON_H
+#define ASM_X86__INTEL_ARCH_PERFMON_H
+
+#define MSR_ARCH_PERFMON_PERFCTR0		0xc1
+#define MSR_ARCH_PERFMON_PERFCTR1		0xc2
+
+#define MSR_ARCH_PERFMON_EVENTSEL0		0x186
+#define MSR_ARCH_PERFMON_EVENTSEL1		0x187
+
+#define ARCH_PERFMON_EVENTSEL0_ENABLE	(1 << 22)
+#define ARCH_PERFMON_EVENTSEL_INT	(1 << 20)
+#define ARCH_PERFMON_EVENTSEL_OS	(1 << 17)
+#define ARCH_PERFMON_EVENTSEL_USR	(1 << 16)
+
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL	(0x3c)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK	(0x00 << 8)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX (0)
+#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
+	(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
+
+union cpuid10_eax {
+	struct {
+		unsigned int version_id:8;
+		unsigned int num_counters:8;
+		unsigned int bit_width:8;
+		unsigned int mask_length:8;
+	} split;
+	unsigned int full;
+};
+
+#endif /* ASM_X86__INTEL_ARCH_PERFMON_H */
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
new file mode 100644
index 000000000000..a233f835e0b5
--- /dev/null
+++ b/arch/x86/include/asm/io.h
@@ -0,0 +1,91 @@
+#ifndef ASM_X86__IO_H
+#define ASM_X86__IO_H
+
+#define ARCH_HAS_IOREMAP_WC
+
+#include <linux/compiler.h>
+
+#define build_mmio_read(name, size, type, reg, barrier) \
+static inline type name(const volatile void __iomem *addr) \
+{ type ret; asm volatile("mov" size " %1,%0":reg (ret) \
+:"m" (*(volatile type __force *)addr) barrier); return ret; }
+
+#define build_mmio_write(name, size, type, reg, barrier) \
+static inline void name(type val, volatile void __iomem *addr) \
+{ asm volatile("mov" size " %0,%1": :reg (val), \
+"m" (*(volatile type __force *)addr) barrier); }
+
+build_mmio_read(readb, "b", unsigned char, "=q", :"memory")
+build_mmio_read(readw, "w", unsigned short, "=r", :"memory")
+build_mmio_read(readl, "l", unsigned int, "=r", :"memory")
+
+build_mmio_read(__readb, "b", unsigned char, "=q", )
+build_mmio_read(__readw, "w", unsigned short, "=r", )
+build_mmio_read(__readl, "l", unsigned int, "=r", )
+
+build_mmio_write(writeb, "b", unsigned char, "q", :"memory")
+build_mmio_write(writew, "w", unsigned short, "r", :"memory")
+build_mmio_write(writel, "l", unsigned int, "r", :"memory")
+
+build_mmio_write(__writeb, "b", unsigned char, "q", )
+build_mmio_write(__writew, "w", unsigned short, "r", )
+build_mmio_write(__writel, "l", unsigned int, "r", )
+
+#define readb_relaxed(a) __readb(a)
+#define readw_relaxed(a) __readw(a)
+#define readl_relaxed(a) __readl(a)
+#define __raw_readb __readb
+#define __raw_readw __readw
+#define __raw_readl __readl
+
+#define __raw_writeb __writeb
+#define __raw_writew __writew
+#define __raw_writel __writel
+
+#define mmiowb() barrier()
+
+#ifdef CONFIG_X86_64
+build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
+build_mmio_read(__readq, "q", unsigned long, "=r", )
+build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
+build_mmio_write(__writeq, "q", unsigned long, "r", )
+
+#define readq_relaxed(a) __readq(a)
+#define __raw_readq __readq
+#define __raw_writeq writeq
+
+/* Let people know we have them */
+#define readq readq
+#define writeq writeq
+#endif
+
+extern int iommu_bio_merge;
+
+#ifdef CONFIG_X86_32
+# include "io_32.h"
+#else
+# include "io_64.h"
+#endif
+
+extern void *xlate_dev_mem_ptr(unsigned long phys);
+extern void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
+
+extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
+				unsigned long prot_val);
+extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size);
+
+/*
+ * early_ioremap() and early_iounmap() are for temporary early boot-time
+ * mappings, before the real ioremap() is functional.
+ * A boot-time mapping is currently limited to at most 16 pages.
+ */
+extern void early_ioremap_init(void);
+extern void early_ioremap_clear(void);
+extern void early_ioremap_reset(void);
+extern void *early_ioremap(unsigned long offset, unsigned long size);
+extern void *early_memremap(unsigned long offset, unsigned long size);
+extern void early_iounmap(void *addr, unsigned long size);
+extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
+
+
+#endif /* ASM_X86__IO_H */
diff --git a/arch/x86/include/asm/io_32.h b/arch/x86/include/asm/io_32.h
new file mode 100644
index 000000000000..4f7d878bda18
--- /dev/null
+++ b/arch/x86/include/asm/io_32.h
@@ -0,0 +1,284 @@
+#ifndef ASM_X86__IO_32_H
+#define ASM_X86__IO_32_H
+
+#include <linux/string.h>
+#include <linux/compiler.h>
+
+/*
+ * This file contains the definitions for the x86 IO instructions
+ * inb/inw/inl/outb/outw/outl and the "string versions" of the same
+ * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
+ * versions of the single-IO instructions (inb_p/inw_p/..).
+ *
+ * This file is not meant to be obfuscating: it's just complicated
+ * to (a) handle it all in a way that makes gcc able to optimize it
+ * as well as possible and (b) trying to avoid writing the same thing
+ * over and over again with slight variations and possibly making a
+ * mistake somewhere.
+ */
+
+/*
+ * Thanks to James van Artsdalen for a better timing-fix than
+ * the two short jumps: using outb's to a nonexistent port seems
+ * to guarantee better timings even on fast machines.
+ *
+ * On the other hand, I'd like to be sure of a non-existent port:
+ * I feel a bit unsafe about using 0x80 (should be safe, though)
+ *
+ *		Linus
+ */
+
+ /*
+  *  Bit simplified and optimized by Jan Hubicka
+  *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
+  *
+  *  isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
+  *  isa_read[wl] and isa_write[wl] fixed
+  *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+  */
+
+#define IO_SPACE_LIMIT 0xffff
+
+#define XQUAD_PORTIO_BASE 0xfe400000
+#define XQUAD_PORTIO_QUAD 0x40000  /* 256k per quad. */
+
+#ifdef __KERNEL__
+
+#include <asm-generic/iomap.h>
+
+#include <linux/vmalloc.h>
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p)	p
+
+/**
+ *	virt_to_phys	-	map virtual addresses to physical
+ *	@address: address to remap
+ *
+ *	The returned physical address is the physical (CPU) mapping for
+ *	the memory address given. It is only valid to use this function on
+ *	addresses directly mapped or allocated via kmalloc.
+ *
+ *	This function does not give bus mappings for DMA transfers. In
+ *	almost all conceivable cases a device driver should not be using
+ *	this function
+ */
+
+static inline unsigned long virt_to_phys(volatile void *address)
+{
+	return __pa(address);
+}
+
+/**
+ *	phys_to_virt	-	map physical address to virtual
+ *	@address: address to remap
+ *
+ *	The returned virtual address is a current CPU mapping for
+ *	the memory address given. It is only valid to use this function on
+ *	addresses that have a kernel mapping
+ *
+ *	This function does not handle bus mappings for DMA transfers. In
+ *	almost all conceivable cases a device driver should not be using
+ *	this function
+ */
+
+static inline void *phys_to_virt(unsigned long address)
+{
+	return __va(address);
+}
+
+/*
+ * Change "struct page" to physical address.
+ */
+#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+
+/**
+ * ioremap     -   map bus memory into CPU space
+ * @offset:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * If the area you are trying to map is a PCI BAR you should have a
+ * look at pci_iomap().
+ */
+extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
+				unsigned long prot_val);
+
+/*
+ * The default ioremap() behavior is non-cached:
+ */
+static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
+{
+	return ioremap_nocache(offset, size);
+}
+
+extern void iounmap(volatile void __iomem *addr);
+
+/*
+ * ISA I/O bus memory addresses are 1:1 with the physical address.
+ */
+#define isa_virt_to_bus virt_to_phys
+#define isa_page_to_bus page_to_phys
+#define isa_bus_to_virt phys_to_virt
+
+/*
+ * However PCI ones are not necessarily 1:1 and therefore these interfaces
+ * are forbidden in portable PCI drivers.
+ *
+ * Allow them on x86 for legacy drivers, though.
+ */
+#define virt_to_bus virt_to_phys
+#define bus_to_virt phys_to_virt
+
+static inline void
+memset_io(volatile void __iomem *addr, unsigned char val, int count)
+{
+	memset((void __force *)addr, val, count);
+}
+
+static inline void
+memcpy_fromio(void *dst, const volatile void __iomem *src, int count)
+{
+	__memcpy(dst, (const void __force *)src, count);
+}
+
+static inline void
+memcpy_toio(volatile void __iomem *dst, const void *src, int count)
+{
+	__memcpy((void __force *)dst, src, count);
+}
+
+/*
+ * ISA space is 'always mapped' on a typical x86 system, no need to
+ * explicitly ioremap() it. The fact that the ISA IO space is mapped
+ * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
+ * are physical addresses. The following constant pointer can be
+ * used as the IO-area pointer (it can be iounmapped as well, so the
+ * analogy with PCI is quite large):
+ */
+#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
+
+/*
+ *	Cache management
+ *
+ *	This needed for two cases
+ *	1. Out of order aware processors
+ *	2. Accidentally out of order processors (PPro errata #51)
+ */
+
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+
+static inline void flush_write_buffers(void)
+{
+	asm volatile("lock; addl $0,0(%%esp)": : :"memory");
+}
+
+#else
+
+#define flush_write_buffers() do { } while (0)
+
+#endif
+
+#endif /* __KERNEL__ */
+
+extern void native_io_delay(void);
+
+extern int io_delay_type;
+extern void io_delay_init(void);
+
+#if defined(CONFIG_PARAVIRT)
+#include <asm/paravirt.h>
+#else
+
+static inline void slow_down_io(void)
+{
+	native_io_delay();
+#ifdef REALLY_SLOW_IO
+	native_io_delay();
+	native_io_delay();
+	native_io_delay();
+#endif
+}
+
+#endif
+
+#define __BUILDIO(bwl, bw, type)				\
+static inline void out##bwl(unsigned type value, int port)	\
+{								\
+	out##bwl##_local(value, port);				\
+}								\
+								\
+static inline unsigned type in##bwl(int port)			\
+{								\
+	return in##bwl##_local(port);				\
+}
+
+#define BUILDIO(bwl, bw, type)						\
+static inline void out##bwl##_local(unsigned type value, int port)	\
+{									\
+	asm volatile("out" #bwl " %" #bw "0, %w1"		\
+		     : : "a"(value), "Nd"(port));			\
+}									\
+									\
+static inline unsigned type in##bwl##_local(int port)			\
+{									\
+	unsigned type value;						\
+	asm volatile("in" #bwl " %w1, %" #bw "0"		\
+		     : "=a"(value) : "Nd"(port));			\
+	return value;							\
+}									\
+									\
+static inline void out##bwl##_local_p(unsigned type value, int port)	\
+{									\
+	out##bwl##_local(value, port);					\
+	slow_down_io();							\
+}									\
+									\
+static inline unsigned type in##bwl##_local_p(int port)			\
+{									\
+	unsigned type value = in##bwl##_local(port);			\
+	slow_down_io();							\
+	return value;							\
+}									\
+									\
+__BUILDIO(bwl, bw, type)						\
+									\
+static inline void out##bwl##_p(unsigned type value, int port)		\
+{									\
+	out##bwl(value, port);						\
+	slow_down_io();							\
+}									\
+									\
+static inline unsigned type in##bwl##_p(int port)			\
+{									\
+	unsigned type value = in##bwl(port);				\
+	slow_down_io();							\
+	return value;							\
+}									\
+									\
+static inline void outs##bwl(int port, const void *addr, unsigned long count) \
+{									\
+	asm volatile("rep; outs" #bwl					\
+		     : "+S"(addr), "+c"(count) : "d"(port));		\
+}									\
+									\
+static inline void ins##bwl(int port, void *addr, unsigned long count)	\
+{									\
+	asm volatile("rep; ins" #bwl					\
+		     : "+D"(addr), "+c"(count) : "d"(port));		\
+}
+
+BUILDIO(b, b, char)
+BUILDIO(w, w, short)
+BUILDIO(l, , int)
+
+#endif /* ASM_X86__IO_32_H */
diff --git a/arch/x86/include/asm/io_64.h b/arch/x86/include/asm/io_64.h
new file mode 100644
index 000000000000..ee6e086b7dfe
--- /dev/null
+++ b/arch/x86/include/asm/io_64.h
@@ -0,0 +1,244 @@
+#ifndef ASM_X86__IO_64_H
+#define ASM_X86__IO_64_H
+
+
+/*
+ * This file contains the definitions for the x86 IO instructions
+ * inb/inw/inl/outb/outw/outl and the "string versions" of the same
+ * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
+ * versions of the single-IO instructions (inb_p/inw_p/..).
+ *
+ * This file is not meant to be obfuscating: it's just complicated
+ * to (a) handle it all in a way that makes gcc able to optimize it
+ * as well as possible and (b) trying to avoid writing the same thing
+ * over and over again with slight variations and possibly making a
+ * mistake somewhere.
+ */
+
+/*
+ * Thanks to James van Artsdalen for a better timing-fix than
+ * the two short jumps: using outb's to a nonexistent port seems
+ * to guarantee better timings even on fast machines.
+ *
+ * On the other hand, I'd like to be sure of a non-existent port:
+ * I feel a bit unsafe about using 0x80 (should be safe, though)
+ *
+ *		Linus
+ */
+
+ /*
+  *  Bit simplified and optimized by Jan Hubicka
+  *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
+  *
+  *  isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
+  *  isa_read[wl] and isa_write[wl] fixed
+  *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+  */
+
+extern void native_io_delay(void);
+
+extern int io_delay_type;
+extern void io_delay_init(void);
+
+#if defined(CONFIG_PARAVIRT)
+#include <asm/paravirt.h>
+#else
+
+static inline void slow_down_io(void)
+{
+	native_io_delay();
+#ifdef REALLY_SLOW_IO
+	native_io_delay();
+	native_io_delay();
+	native_io_delay();
+#endif
+}
+#endif
+
+/*
+ * Talk about misusing macros..
+ */
+#define __OUT1(s, x)							\
+static inline void out##s(unsigned x value, unsigned short port) {
+
+#define __OUT2(s, s1, s2)				\
+asm volatile ("out" #s " %" s1 "0,%" s2 "1"
+
+#ifndef REALLY_SLOW_IO
+#define REALLY_SLOW_IO
+#define UNSET_REALLY_SLOW_IO
+#endif
+
+#define __OUT(s, s1, x)							\
+	__OUT1(s, x) __OUT2(s, s1, "w") : : "a" (value), "Nd" (port));	\
+	}								\
+	__OUT1(s##_p, x) __OUT2(s, s1, "w") : : "a" (value), "Nd" (port)); \
+	slow_down_io();							\
+}
+
+#define __IN1(s)							\
+static inline RETURN_TYPE in##s(unsigned short port)			\
+{									\
+	RETURN_TYPE _v;
+
+#define __IN2(s, s1, s2)						\
+	asm volatile ("in" #s " %" s2 "1,%" s1 "0"
+
+#define __IN(s, s1, i...)						\
+	__IN1(s) __IN2(s, s1, "w") : "=a" (_v) : "Nd" (port), ##i);	\
+	return _v;							\
+	}								\
+	__IN1(s##_p) __IN2(s, s1, "w") : "=a" (_v) : "Nd" (port), ##i);	\
+	slow_down_io(); \
+	return _v; }
+
+#ifdef UNSET_REALLY_SLOW_IO
+#undef REALLY_SLOW_IO
+#endif
+
+#define __INS(s)							\
+static inline void ins##s(unsigned short port, void *addr,		\
+			  unsigned long count)				\
+{									\
+	asm volatile ("rep ; ins" #s					\
+		      : "=D" (addr), "=c" (count)			\
+		      : "d" (port), "0" (addr), "1" (count));		\
+}
+
+#define __OUTS(s)							\
+static inline void outs##s(unsigned short port, const void *addr,	\
+			   unsigned long count)				\
+{									\
+	asm volatile ("rep ; outs" #s					\
+		      : "=S" (addr), "=c" (count)			\
+		      : "d" (port), "0" (addr), "1" (count));		\
+}
+
+#define RETURN_TYPE unsigned char
+__IN(b, "")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned short
+__IN(w, "")
+#undef RETURN_TYPE
+#define RETURN_TYPE unsigned int
+__IN(l, "")
+#undef RETURN_TYPE
+
+__OUT(b, "b", char)
+__OUT(w, "w", short)
+__OUT(l, , int)
+
+__INS(b)
+__INS(w)
+__INS(l)
+
+__OUTS(b)
+__OUTS(w)
+__OUTS(l)
+
+#define IO_SPACE_LIMIT 0xffff
+
+#if defined(__KERNEL__) && defined(__x86_64__)
+
+#include <linux/vmalloc.h>
+
+#ifndef __i386__
+/*
+ * Change virtual addresses to physical addresses and vv.
+ * These are pretty trivial
+ */
+static inline unsigned long virt_to_phys(volatile void *address)
+{
+	return __pa(address);
+}
+
+static inline void *phys_to_virt(unsigned long address)
+{
+	return __va(address);
+}
+#endif
+
+/*
+ * Change "struct page" to physical address.
+ */
+#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
+
+#include <asm-generic/iomap.h>
+
+/*
+ * This one maps high address device memory and turns off caching for that area.
+ * it's useful if some control registers are in such an area and write combining
+ * or read caching is not desirable:
+ */
+extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
+extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
+				unsigned long prot_val);
+
+/*
+ * The default ioremap() behavior is non-cached:
+ */
+static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
+{
+	return ioremap_nocache(offset, size);
+}
+
+extern void iounmap(volatile void __iomem *addr);
+
+extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
+
+/*
+ * ISA I/O bus memory addresses are 1:1 with the physical address.
+ */
+#define isa_virt_to_bus virt_to_phys
+#define isa_page_to_bus page_to_phys
+#define isa_bus_to_virt phys_to_virt
+
+/*
+ * However PCI ones are not necessarily 1:1 and therefore these interfaces
+ * are forbidden in portable PCI drivers.
+ *
+ * Allow them on x86 for legacy drivers, though.
+ */
+#define virt_to_bus virt_to_phys
+#define bus_to_virt phys_to_virt
+
+void __memcpy_fromio(void *, unsigned long, unsigned);
+void __memcpy_toio(unsigned long, const void *, unsigned);
+
+static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
+				 unsigned len)
+{
+	__memcpy_fromio(to, (unsigned long)from, len);
+}
+
+static inline void memcpy_toio(volatile void __iomem *to, const void *from,
+			       unsigned len)
+{
+	__memcpy_toio((unsigned long)to, from, len);
+}
+
+void memset_io(volatile void __iomem *a, int b, size_t c);
+
+/*
+ * ISA space is 'always mapped' on a typical x86 system, no need to
+ * explicitly ioremap() it. The fact that the ISA IO space is mapped
+ * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
+ * are physical addresses. The following constant pointer can be
+ * used as the IO-area pointer (it can be iounmapped as well, so the
+ * analogy with PCI is quite large):
+ */
+#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
+
+#define flush_write_buffers()
+
+#define BIO_VMERGE_BOUNDARY iommu_bio_merge
+
+/*
+ * Convert a virtual cached pointer to an uncached pointer
+ */
+#define xlate_dev_kmem_ptr(p)	p
+
+#endif /* __KERNEL__ */
+
+#endif /* ASM_X86__IO_64_H */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
new file mode 100644
index 000000000000..d35cbd7aa587
--- /dev/null
+++ b/arch/x86/include/asm/io_apic.h
@@ -0,0 +1,204 @@
+#ifndef ASM_X86__IO_APIC_H
+#define ASM_X86__IO_APIC_H
+
+#include <linux/types.h>
+#include <asm/mpspec.h>
+#include <asm/apicdef.h>
+#include <asm/irq_vectors.h>
+
+/*
+ * Intel IO-APIC support for SMP and UP systems.
+ *
+ * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar
+ */
+
+/* I/O Unit Redirection Table */
+#define IO_APIC_REDIR_VECTOR_MASK	0x000FF
+#define IO_APIC_REDIR_DEST_LOGICAL	0x00800
+#define IO_APIC_REDIR_DEST_PHYSICAL	0x00000
+#define IO_APIC_REDIR_SEND_PENDING	(1 << 12)
+#define IO_APIC_REDIR_REMOTE_IRR	(1 << 14)
+#define IO_APIC_REDIR_LEVEL_TRIGGER	(1 << 15)
+#define IO_APIC_REDIR_MASKED		(1 << 16)
+
+/*
+ * The structure of the IO-APIC:
+ */
+union IO_APIC_reg_00 {
+	u32	raw;
+	struct {
+		u32	__reserved_2	: 14,
+			LTS		:  1,
+			delivery_type	:  1,
+			__reserved_1	:  8,
+			ID		:  8;
+	} __attribute__ ((packed)) bits;
+};
+
+union IO_APIC_reg_01 {
+	u32	raw;
+	struct {
+		u32	version		:  8,
+			__reserved_2	:  7,
+			PRQ		:  1,
+			entries		:  8,
+			__reserved_1	:  8;
+	} __attribute__ ((packed)) bits;
+};
+
+union IO_APIC_reg_02 {
+	u32	raw;
+	struct {
+		u32	__reserved_2	: 24,
+			arbitration	:  4,
+			__reserved_1	:  4;
+	} __attribute__ ((packed)) bits;
+};
+
+union IO_APIC_reg_03 {
+	u32	raw;
+	struct {
+		u32	boot_DT		:  1,
+			__reserved_1	: 31;
+	} __attribute__ ((packed)) bits;
+};
+
+enum ioapic_irq_destination_types {
+	dest_Fixed = 0,
+	dest_LowestPrio = 1,
+	dest_SMI = 2,
+	dest__reserved_1 = 3,
+	dest_NMI = 4,
+	dest_INIT = 5,
+	dest__reserved_2 = 6,
+	dest_ExtINT = 7
+};
+
+struct IO_APIC_route_entry {
+	__u32	vector		:  8,
+		delivery_mode	:  3,	/* 000: FIXED
+					 * 001: lowest prio
+					 * 111: ExtINT
+					 */
+		dest_mode	:  1,	/* 0: physical, 1: logical */
+		delivery_status	:  1,
+		polarity	:  1,
+		irr		:  1,
+		trigger		:  1,	/* 0: edge, 1: level */
+		mask		:  1,	/* 0: enabled, 1: disabled */
+		__reserved_2	: 15;
+
+	__u32	__reserved_3	: 24,
+		dest		:  8;
+} __attribute__ ((packed));
+
+struct IR_IO_APIC_route_entry {
+	__u64	vector		: 8,
+		zero		: 3,
+		index2		: 1,
+		delivery_status : 1,
+		polarity	: 1,
+		irr		: 1,
+		trigger		: 1,
+		mask		: 1,
+		reserved	: 31,
+		format		: 1,
+		index		: 15;
+} __attribute__ ((packed));
+
+#ifdef CONFIG_X86_IO_APIC
+
+/*
+ * # of IO-APICs and # of IRQ routing registers
+ */
+extern int nr_ioapics;
+extern int nr_ioapic_registers[MAX_IO_APICS];
+
+/*
+ * MP-BIOS irq configuration table structures:
+ */
+
+#define MP_MAX_IOAPIC_PIN 127
+
+struct mp_config_ioapic {
+	unsigned long mp_apicaddr;
+	unsigned int mp_apicid;
+	unsigned char mp_type;
+	unsigned char mp_apicver;
+	unsigned char mp_flags;
+};
+
+struct mp_config_intsrc {
+	unsigned int mp_dstapic;
+	unsigned char mp_type;
+	unsigned char mp_irqtype;
+	unsigned short mp_irqflag;
+	unsigned char mp_srcbus;
+	unsigned char mp_srcbusirq;
+	unsigned char mp_dstirq;
+};
+
+/* I/O APIC entries */
+extern struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
+
+/* # of MP IRQ source entries */
+extern int mp_irq_entries;
+
+/* MP IRQ source entries */
+extern struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
+
+/* non-0 if default (table-less) MP configuration */
+extern int mpc_default_type;
+
+/* Older SiS APIC requires we rewrite the index register */
+extern int sis_apic_bug;
+
+/* 1 if "noapic" boot option passed */
+extern int skip_ioapic_setup;
+
+/* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
+extern int timer_through_8259;
+
+static inline void disable_ioapic_setup(void)
+{
+	skip_ioapic_setup = 1;
+}
+
+/*
+ * If we use the IO-APIC for IRQ routing, disable automatic
+ * assignment of PCI IRQ's.
+ */
+#define io_apic_assign_pci_irqs \
+	(mp_irq_entries && !skip_ioapic_setup && io_apic_irqs)
+
+#ifdef CONFIG_ACPI
+extern int io_apic_get_unique_id(int ioapic, int apic_id);
+extern int io_apic_get_version(int ioapic);
+extern int io_apic_get_redir_entries(int ioapic);
+extern int io_apic_set_pci_routing(int ioapic, int pin, int irq,
+				   int edge_level, int active_high_low);
+#endif /* CONFIG_ACPI */
+
+extern int (*ioapic_renumber_irq)(int ioapic, int irq);
+extern void ioapic_init_mappings(void);
+
+#ifdef CONFIG_X86_64
+extern int save_mask_IO_APIC_setup(void);
+extern void restore_IO_APIC_setup(void);
+extern void reinit_intr_remapped_IO_APIC(int);
+#endif
+
+extern int probe_nr_irqs(void);
+
+#else  /* !CONFIG_X86_IO_APIC */
+#define io_apic_assign_pci_irqs 0
+static const int timer_through_8259 = 0;
+static inline void ioapic_init_mappings(void) { }
+
+static inline int probe_nr_irqs(void)
+{
+	return NR_IRQS;
+}
+#endif
+
+#endif /* ASM_X86__IO_APIC_H */
diff --git a/arch/x86/include/asm/ioctl.h b/arch/x86/include/asm/ioctl.h
new file mode 100644
index 000000000000..b279fe06dfe5
--- /dev/null
+++ b/arch/x86/include/asm/ioctl.h
@@ -0,0 +1 @@
+#include <asm-generic/ioctl.h>
diff --git a/arch/x86/include/asm/ioctls.h b/arch/x86/include/asm/ioctls.h
new file mode 100644
index 000000000000..06752a649044
--- /dev/null
+++ b/arch/x86/include/asm/ioctls.h
@@ -0,0 +1,94 @@
+#ifndef ASM_X86__IOCTLS_H
+#define ASM_X86__IOCTLS_H
+
+#include <asm/ioctl.h>
+
+/* 0x54 is just a magic number to make these relatively unique ('T') */
+
+#define TCGETS		0x5401
+#define TCSETS		0x5402 /* Clashes with SNDCTL_TMR_START sound ioctl */
+#define TCSETSW		0x5403
+#define TCSETSF		0x5404
+#define TCGETA		0x5405
+#define TCSETA		0x5406
+#define TCSETAW		0x5407
+#define TCSETAF		0x5408
+#define TCSBRK		0x5409
+#define TCXONC		0x540A
+#define TCFLSH		0x540B
+#define TIOCEXCL	0x540C
+#define TIOCNXCL	0x540D
+#define TIOCSCTTY	0x540E
+#define TIOCGPGRP	0x540F
+#define TIOCSPGRP	0x5410
+#define TIOCOUTQ	0x5411
+#define TIOCSTI		0x5412
+#define TIOCGWINSZ	0x5413
+#define TIOCSWINSZ	0x5414
+#define TIOCMGET	0x5415
+#define TIOCMBIS	0x5416
+#define TIOCMBIC	0x5417
+#define TIOCMSET	0x5418
+#define TIOCGSOFTCAR	0x5419
+#define TIOCSSOFTCAR	0x541A
+#define FIONREAD	0x541B
+#define TIOCINQ		FIONREAD
+#define TIOCLINUX	0x541C
+#define TIOCCONS	0x541D
+#define TIOCGSERIAL	0x541E
+#define TIOCSSERIAL	0x541F
+#define TIOCPKT		0x5420
+#define FIONBIO		0x5421
+#define TIOCNOTTY	0x5422
+#define TIOCSETD	0x5423
+#define TIOCGETD	0x5424
+#define TCSBRKP		0x5425	/* Needed for POSIX tcsendbreak() */
+/* #define TIOCTTYGSTRUCT 0x5426 - Former debugging-only ioctl */
+#define TIOCSBRK	0x5427  /* BSD compatibility */
+#define TIOCCBRK	0x5428  /* BSD compatibility */
+#define TIOCGSID	0x5429  /* Return the session ID of FD */
+#define TCGETS2		_IOR('T', 0x2A, struct termios2)
+#define TCSETS2		_IOW('T', 0x2B, struct termios2)
+#define TCSETSW2	_IOW('T', 0x2C, struct termios2)
+#define TCSETSF2	_IOW('T', 0x2D, struct termios2)
+#define TIOCGRS485	0x542E
+#define TIOCSRS485	0x542F
+#define TIOCGPTN	_IOR('T', 0x30, unsigned int)
+				/* Get Pty Number (of pty-mux device) */
+#define TIOCSPTLCK	_IOW('T', 0x31, int)  /* Lock/unlock Pty */
+#define TCGETX		0x5432 /* SYS5 TCGETX compatibility */
+#define TCSETX		0x5433
+#define TCSETXF		0x5434
+#define TCSETXW		0x5435
+
+#define FIONCLEX	0x5450
+#define FIOCLEX		0x5451
+#define FIOASYNC	0x5452
+#define TIOCSERCONFIG	0x5453
+#define TIOCSERGWILD	0x5454
+#define TIOCSERSWILD	0x5455
+#define TIOCGLCKTRMIOS	0x5456
+#define TIOCSLCKTRMIOS	0x5457
+#define TIOCSERGSTRUCT	0x5458 /* For debugging only */
+#define TIOCSERGETLSR   0x5459 /* Get line status register */
+#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
+#define TIOCSERSETMULTI 0x545B /* Set multiport config */
+
+#define TIOCMIWAIT	0x545C	/* wait for a change on serial input line(s) */
+#define TIOCGICOUNT	0x545D	/* read serial port inline interrupt counts */
+#define TIOCGHAYESESP   0x545E  /* Get Hayes ESP configuration */
+#define TIOCSHAYESESP   0x545F  /* Set Hayes ESP configuration */
+#define FIOQSIZE	0x5460
+
+/* Used for packet mode */
+#define TIOCPKT_DATA		 0
+#define TIOCPKT_FLUSHREAD	 1
+#define TIOCPKT_FLUSHWRITE	 2
+#define TIOCPKT_STOP		 4
+#define TIOCPKT_START		 8
+#define TIOCPKT_NOSTOP		16
+#define TIOCPKT_DOSTOP		32
+
+#define TIOCSER_TEMT    0x01	/* Transmitter physically empty */
+
+#endif /* ASM_X86__IOCTLS_H */
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
new file mode 100644
index 000000000000..961e746da977
--- /dev/null
+++ b/arch/x86/include/asm/iommu.h
@@ -0,0 +1,46 @@
+#ifndef ASM_X86__IOMMU_H
+#define ASM_X86__IOMMU_H
+
+extern void pci_iommu_shutdown(void);
+extern void no_iommu_init(void);
+extern struct dma_mapping_ops nommu_dma_ops;
+extern int force_iommu, no_iommu;
+extern int iommu_detected;
+extern int dmar_disabled;
+
+extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len);
+
+#ifdef CONFIG_GART_IOMMU
+extern int gart_iommu_aperture;
+extern int gart_iommu_aperture_allowed;
+extern int gart_iommu_aperture_disabled;
+
+extern void early_gart_iommu_check(void);
+extern void gart_iommu_init(void);
+extern void gart_iommu_shutdown(void);
+extern void __init gart_parse_options(char *);
+extern void gart_iommu_hole_init(void);
+
+#else
+#define gart_iommu_aperture            0
+#define gart_iommu_aperture_allowed    0
+#define gart_iommu_aperture_disabled   1
+
+static inline void early_gart_iommu_check(void)
+{
+}
+static inline void gart_iommu_init(void)
+{
+}
+static inline void gart_iommu_shutdown(void)
+{
+}
+static inline void gart_parse_options(char *options)
+{
+}
+static inline void gart_iommu_hole_init(void)
+{
+}
+#endif
+
+#endif /* ASM_X86__IOMMU_H */
diff --git a/arch/x86/include/asm/ipcbuf.h b/arch/x86/include/asm/ipcbuf.h
new file mode 100644
index 000000000000..910304fbdc8f
--- /dev/null
+++ b/arch/x86/include/asm/ipcbuf.h
@@ -0,0 +1,28 @@
+#ifndef ASM_X86__IPCBUF_H
+#define ASM_X86__IPCBUF_H
+
+/*
+ * The ipc64_perm structure for x86 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 32-bit mode_t and seq
+ * - 2 miscellaneous 32-bit values
+ */
+
+struct ipc64_perm {
+	__kernel_key_t		key;
+	__kernel_uid32_t	uid;
+	__kernel_gid32_t	gid;
+	__kernel_uid32_t	cuid;
+	__kernel_gid32_t	cgid;
+	__kernel_mode_t		mode;
+	unsigned short		__pad1;
+	unsigned short		seq;
+	unsigned short		__pad2;
+	unsigned long		__unused1;
+	unsigned long		__unused2;
+};
+
+#endif /* ASM_X86__IPCBUF_H */
diff --git a/arch/x86/include/asm/ipi.h b/arch/x86/include/asm/ipi.h
new file mode 100644
index 000000000000..30a692cfaff8
--- /dev/null
+++ b/arch/x86/include/asm/ipi.h
@@ -0,0 +1,138 @@
+#ifndef ASM_X86__IPI_H
+#define ASM_X86__IPI_H
+
+/*
+ * Copyright 2004 James Cleverdon, IBM.
+ * Subject to the GNU Public License, v.2
+ *
+ * Generic APIC InterProcessor Interrupt code.
+ *
+ * Moved to include file by James Cleverdon from
+ * arch/x86-64/kernel/smp.c
+ *
+ * Copyrights from kernel/smp.c:
+ *
+ * (c) 1995 Alan Cox, Building #3 <alan@redhat.com>
+ * (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com>
+ * (c) 2002,2003 Andi Kleen, SuSE Labs.
+ * Subject to the GNU Public License, v.2
+ */
+
+#include <asm/hw_irq.h>
+#include <asm/apic.h>
+#include <asm/smp.h>
+
+/*
+ * the following functions deal with sending IPIs between CPUs.
+ *
+ * We use 'broadcast', CPU->CPU IPIs and self-IPIs too.
+ */
+
+static inline unsigned int __prepare_ICR(unsigned int shortcut, int vector,
+					 unsigned int dest)
+{
+	unsigned int icr = shortcut | dest;
+
+	switch (vector) {
+	default:
+		icr |= APIC_DM_FIXED | vector;
+		break;
+	case NMI_VECTOR:
+		icr |= APIC_DM_NMI;
+		break;
+	}
+	return icr;
+}
+
+static inline int __prepare_ICR2(unsigned int mask)
+{
+	return SET_APIC_DEST_FIELD(mask);
+}
+
+static inline void __xapic_wait_icr_idle(void)
+{
+	while (native_apic_mem_read(APIC_ICR) & APIC_ICR_BUSY)
+		cpu_relax();
+}
+
+static inline void __send_IPI_shortcut(unsigned int shortcut, int vector,
+				       unsigned int dest)
+{
+	/*
+	 * Subtle. In the case of the 'never do double writes' workaround
+	 * we have to lock out interrupts to be safe.  As we don't care
+	 * of the value read we use an atomic rmw access to avoid costly
+	 * cli/sti.  Otherwise we use an even cheaper single atomic write
+	 * to the APIC.
+	 */
+	unsigned int cfg;
+
+	/*
+	 * Wait for idle.
+	 */
+	__xapic_wait_icr_idle();
+
+	/*
+	 * No need to touch the target chip field
+	 */
+	cfg = __prepare_ICR(shortcut, vector, dest);
+
+	/*
+	 * Send the IPI. The write to APIC_ICR fires this off.
+	 */
+	native_apic_mem_write(APIC_ICR, cfg);
+}
+
+/*
+ * This is used to send an IPI with no shorthand notation (the destination is
+ * specified in bits 56 to 63 of the ICR).
+ */
+static inline void __send_IPI_dest_field(unsigned int mask, int vector,
+					 unsigned int dest)
+{
+	unsigned long cfg;
+
+	/*
+	 * Wait for idle.
+	 */
+	if (unlikely(vector == NMI_VECTOR))
+		safe_apic_wait_icr_idle();
+	else
+		__xapic_wait_icr_idle();
+
+	/*
+	 * prepare target chip field
+	 */
+	cfg = __prepare_ICR2(mask);
+	native_apic_mem_write(APIC_ICR2, cfg);
+
+	/*
+	 * program the ICR
+	 */
+	cfg = __prepare_ICR(0, vector, dest);
+
+	/*
+	 * Send the IPI. The write to APIC_ICR fires this off.
+	 */
+	native_apic_mem_write(APIC_ICR, cfg);
+}
+
+static inline void send_IPI_mask_sequence(cpumask_t mask, int vector)
+{
+	unsigned long flags;
+	unsigned long query_cpu;
+
+	/*
+	 * Hack. The clustered APIC addressing mode doesn't allow us to send
+	 * to an arbitrary mask, so I do a unicast to each CPU instead.
+	 * - mbligh
+	 */
+	local_irq_save(flags);
+	for_each_cpu_mask_nr(query_cpu, mask) {
+		__send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, query_cpu),
+				      vector, APIC_DEST_PHYSICAL);
+	}
+	local_irq_restore(flags);
+}
+
+#endif /* ASM_X86__IPI_H */
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
new file mode 100644
index 000000000000..1e5f2909c1db
--- /dev/null
+++ b/arch/x86/include/asm/irq.h
@@ -0,0 +1,50 @@
+#ifndef ASM_X86__IRQ_H
+#define ASM_X86__IRQ_H
+/*
+ *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
+ *
+ *	IRQ/IPI changes taken from work by Thomas Radke
+ *	<tomsoft@informatik.tu-chemnitz.de>
+ */
+
+#include <asm/apicdef.h>
+#include <asm/irq_vectors.h>
+
+static inline int irq_canonicalize(int irq)
+{
+	return ((irq == 2) ? 9 : irq);
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+# define ARCH_HAS_NMI_WATCHDOG
+#endif
+
+#ifdef CONFIG_4KSTACKS
+  extern void irq_ctx_init(int cpu);
+  extern void irq_ctx_exit(int cpu);
+# define __ARCH_HAS_DO_SOFTIRQ
+#else
+# define irq_ctx_init(cpu) do { } while (0)
+# define irq_ctx_exit(cpu) do { } while (0)
+# ifdef CONFIG_X86_64
+#  define __ARCH_HAS_DO_SOFTIRQ
+# endif
+#endif
+
+#ifdef CONFIG_IRQBALANCE
+extern int irqbalance_disable(char *str);
+#endif
+
+#ifdef CONFIG_HOTPLUG_CPU
+#include <linux/cpumask.h>
+extern void fixup_irqs(cpumask_t map);
+#endif
+
+extern unsigned int do_IRQ(struct pt_regs *regs);
+extern void init_IRQ(void);
+extern void native_init_IRQ(void);
+
+/* Interrupt vector management */
+extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
+
+#endif /* ASM_X86__IRQ_H */
diff --git a/arch/x86/include/asm/irq_regs.h b/arch/x86/include/asm/irq_regs.h
new file mode 100644
index 000000000000..89c898ab298b
--- /dev/null
+++ b/arch/x86/include/asm/irq_regs.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "irq_regs_32.h"
+#else
+# include "irq_regs_64.h"
+#endif
diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h
new file mode 100644
index 000000000000..316a3b258871
--- /dev/null
+++ b/arch/x86/include/asm/irq_regs_32.h
@@ -0,0 +1,29 @@
+/*
+ * Per-cpu current frame pointer - the location of the last exception frame on
+ * the stack, stored in the per-cpu area.
+ *
+ * Jeremy Fitzhardinge <jeremy@goop.org>
+ */
+#ifndef ASM_X86__IRQ_REGS_32_H
+#define ASM_X86__IRQ_REGS_32_H
+
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU(struct pt_regs *, irq_regs);
+
+static inline struct pt_regs *get_irq_regs(void)
+{
+	return x86_read_percpu(irq_regs);
+}
+
+static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
+{
+	struct pt_regs *old_regs;
+
+	old_regs = get_irq_regs();
+	x86_write_percpu(irq_regs, new_regs);
+
+	return old_regs;
+}
+
+#endif /* ASM_X86__IRQ_REGS_32_H */
diff --git a/arch/x86/include/asm/irq_regs_64.h b/arch/x86/include/asm/irq_regs_64.h
new file mode 100644
index 000000000000..3dd9c0b70270
--- /dev/null
+++ b/arch/x86/include/asm/irq_regs_64.h
@@ -0,0 +1 @@
+#include <asm-generic/irq_regs.h>
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
new file mode 100644
index 000000000000..78242c6ffa58
--- /dev/null
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -0,0 +1,8 @@
+#ifndef _ASM_IRQ_REMAPPING_H
+#define _ASM_IRQ_REMAPPING_H
+
+extern int x2apic;
+
+#define IRTE_DEST(dest) ((x2apic) ? dest : dest << 8)
+
+#endif
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
new file mode 100644
index 000000000000..a8d065d85f57
--- /dev/null
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -0,0 +1,164 @@
+#ifndef ASM_X86__IRQ_VECTORS_H
+#define ASM_X86__IRQ_VECTORS_H
+
+#include <linux/threads.h>
+
+#define NMI_VECTOR		0x02
+
+/*
+ * IDT vectors usable for external interrupt sources start
+ * at 0x20:
+ */
+#define FIRST_EXTERNAL_VECTOR	0x20
+
+#ifdef CONFIG_X86_32
+# define SYSCALL_VECTOR		0x80
+#else
+# define IA32_SYSCALL_VECTOR	0x80
+#endif
+
+/*
+ * Reserve the lowest usable priority level 0x20 - 0x2f for triggering
+ * cleanup after irq migration.
+ */
+#define IRQ_MOVE_CLEANUP_VECTOR	FIRST_EXTERNAL_VECTOR
+
+/*
+ * Vectors 0x30-0x3f are used for ISA interrupts.
+ */
+#define IRQ0_VECTOR		(FIRST_EXTERNAL_VECTOR + 0x10)
+#define IRQ1_VECTOR		(IRQ0_VECTOR + 1)
+#define IRQ2_VECTOR		(IRQ0_VECTOR + 2)
+#define IRQ3_VECTOR		(IRQ0_VECTOR + 3)
+#define IRQ4_VECTOR		(IRQ0_VECTOR + 4)
+#define IRQ5_VECTOR		(IRQ0_VECTOR + 5)
+#define IRQ6_VECTOR		(IRQ0_VECTOR + 6)
+#define IRQ7_VECTOR		(IRQ0_VECTOR + 7)
+#define IRQ8_VECTOR		(IRQ0_VECTOR + 8)
+#define IRQ9_VECTOR		(IRQ0_VECTOR + 9)
+#define IRQ10_VECTOR		(IRQ0_VECTOR + 10)
+#define IRQ11_VECTOR		(IRQ0_VECTOR + 11)
+#define IRQ12_VECTOR		(IRQ0_VECTOR + 12)
+#define IRQ13_VECTOR		(IRQ0_VECTOR + 13)
+#define IRQ14_VECTOR		(IRQ0_VECTOR + 14)
+#define IRQ15_VECTOR		(IRQ0_VECTOR + 15)
+
+/*
+ * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
+ *
+ *  some of the following vectors are 'rare', they are merged
+ *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
+ *  TLB, reschedule and local APIC vectors are performance-critical.
+ *
+ *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
+ */
+#ifdef CONFIG_X86_32
+
+# define SPURIOUS_APIC_VECTOR		0xff
+# define ERROR_APIC_VECTOR		0xfe
+# define INVALIDATE_TLB_VECTOR		0xfd
+# define RESCHEDULE_VECTOR		0xfc
+# define CALL_FUNCTION_VECTOR		0xfb
+# define CALL_FUNCTION_SINGLE_VECTOR	0xfa
+# define THERMAL_APIC_VECTOR		0xf0
+
+#else
+
+#define SPURIOUS_APIC_VECTOR		0xff
+#define ERROR_APIC_VECTOR		0xfe
+#define RESCHEDULE_VECTOR		0xfd
+#define CALL_FUNCTION_VECTOR		0xfc
+#define CALL_FUNCTION_SINGLE_VECTOR	0xfb
+#define THERMAL_APIC_VECTOR		0xfa
+#define THRESHOLD_APIC_VECTOR		0xf9
+#define UV_BAU_MESSAGE			0xf8
+#define INVALIDATE_TLB_VECTOR_END	0xf7
+#define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
+
+#define NUM_INVALIDATE_TLB_VECTORS	8
+
+#endif
+
+/*
+ * Local APIC timer IRQ vector is on a different priority level,
+ * to work around the 'lost local interrupt if more than 2 IRQ
+ * sources per level' errata.
+ */
+#define LOCAL_TIMER_VECTOR	0xef
+
+/*
+ * First APIC vector available to drivers: (vectors 0x30-0xee) we
+ * start at 0x31(0x41) to spread out vectors evenly between priority
+ * levels. (0x80 is the syscall vector)
+ */
+#define FIRST_DEVICE_VECTOR	(IRQ15_VECTOR + 2)
+
+#define NR_VECTORS		256
+
+#define FPU_IRQ			13
+
+#define	FIRST_VM86_IRQ		3
+#define LAST_VM86_IRQ		15
+#define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
+
+#ifdef CONFIG_X86_64
+# if NR_CPUS < MAX_IO_APICS
+#  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
+# else
+#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
+# endif
+
+#elif !defined(CONFIG_X86_VOYAGER)
+
+# if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS)
+
+#  define NR_IRQS		224
+
+# else /* IO_APIC || PARAVIRT */
+
+#  define NR_IRQS		16
+
+# endif
+
+#else /* !VISWS && !VOYAGER */
+
+# define NR_IRQS		224
+
+#endif /* VISWS */
+
+/* Voyager specific defines */
+/* These define the CPIs we use in linux */
+#define VIC_CPI_LEVEL0			0
+#define VIC_CPI_LEVEL1			1
+/* now the fake CPIs */
+#define VIC_TIMER_CPI			2
+#define VIC_INVALIDATE_CPI		3
+#define VIC_RESCHEDULE_CPI		4
+#define VIC_ENABLE_IRQ_CPI		5
+#define VIC_CALL_FUNCTION_CPI		6
+#define VIC_CALL_FUNCTION_SINGLE_CPI	7
+
+/* Now the QIC CPIs:  Since we don't need the two initial levels,
+ * these are 2 less than the VIC CPIs */
+#define QIC_CPI_OFFSET			1
+#define QIC_TIMER_CPI			(VIC_TIMER_CPI - QIC_CPI_OFFSET)
+#define QIC_INVALIDATE_CPI		(VIC_INVALIDATE_CPI - QIC_CPI_OFFSET)
+#define QIC_RESCHEDULE_CPI		(VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET)
+#define QIC_ENABLE_IRQ_CPI		(VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET)
+#define QIC_CALL_FUNCTION_CPI		(VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET)
+#define QIC_CALL_FUNCTION_SINGLE_CPI	(VIC_CALL_FUNCTION_SINGLE_CPI - QIC_CPI_OFFSET)
+
+#define VIC_START_FAKE_CPI		VIC_TIMER_CPI
+#define VIC_END_FAKE_CPI		VIC_CALL_FUNCTION_SINGLE_CPI
+
+/* this is the SYS_INT CPI. */
+#define VIC_SYS_INT			8
+#define VIC_CMN_INT			15
+
+/* This is the boot CPI for alternate processors.  It gets overwritten
+ * by the above once the system has activated all available processors */
+#define VIC_CPU_BOOT_CPI		VIC_CPI_LEVEL0
+#define VIC_CPU_BOOT_ERRATA_CPI		(VIC_CPI_LEVEL0 + 8)
+
+
+#endif /* ASM_X86__IRQ_VECTORS_H */
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
new file mode 100644
index 000000000000..2bdab21f0898
--- /dev/null
+++ b/arch/x86/include/asm/irqflags.h
@@ -0,0 +1,211 @@
+#ifndef _X86_IRQFLAGS_H_
+#define _X86_IRQFLAGS_H_
+
+#include <asm/processor-flags.h>
+
+#ifndef __ASSEMBLY__
+/*
+ * Interrupt control:
+ */
+
+static inline unsigned long native_save_fl(void)
+{
+	unsigned long flags;
+
+	asm volatile("# __raw_save_flags\n\t"
+		     "pushf ; pop %0"
+		     : "=g" (flags)
+		     : /* no input */
+		     : "memory");
+
+	return flags;
+}
+
+static inline void native_restore_fl(unsigned long flags)
+{
+	asm volatile("push %0 ; popf"
+		     : /* no output */
+		     :"g" (flags)
+		     :"memory", "cc");
+}
+
+static inline void native_irq_disable(void)
+{
+	asm volatile("cli": : :"memory");
+}
+
+static inline void native_irq_enable(void)
+{
+	asm volatile("sti": : :"memory");
+}
+
+static inline void native_safe_halt(void)
+{
+	asm volatile("sti; hlt": : :"memory");
+}
+
+static inline void native_halt(void)
+{
+	asm volatile("hlt": : :"memory");
+}
+
+#endif
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#ifndef __ASSEMBLY__
+
+static inline unsigned long __raw_local_save_flags(void)
+{
+	return native_save_fl();
+}
+
+static inline void raw_local_irq_restore(unsigned long flags)
+{
+	native_restore_fl(flags);
+}
+
+static inline void raw_local_irq_disable(void)
+{
+	native_irq_disable();
+}
+
+static inline void raw_local_irq_enable(void)
+{
+	native_irq_enable();
+}
+
+/*
+ * Used in the idle loop; sti takes one instruction cycle
+ * to complete:
+ */
+static inline void raw_safe_halt(void)
+{
+	native_safe_halt();
+}
+
+/*
+ * Used when interrupts are already enabled or to
+ * shutdown the processor:
+ */
+static inline void halt(void)
+{
+	native_halt();
+}
+
+/*
+ * For spinlocks, etc:
+ */
+static inline unsigned long __raw_local_irq_save(void)
+{
+	unsigned long flags = __raw_local_save_flags();
+
+	raw_local_irq_disable();
+
+	return flags;
+}
+#else
+
+#define ENABLE_INTERRUPTS(x)	sti
+#define DISABLE_INTERRUPTS(x)	cli
+
+#ifdef CONFIG_X86_64
+#define SWAPGS	swapgs
+/*
+ * Currently paravirt can't handle swapgs nicely when we
+ * don't have a stack we can rely on (such as a user space
+ * stack).  So we either find a way around these or just fault
+ * and emulate if a guest tries to call swapgs directly.
+ *
+ * Either way, this is a good way to document that we don't
+ * have a reliable stack. x86_64 only.
+ */
+#define SWAPGS_UNSAFE_STACK	swapgs
+
+#define PARAVIRT_ADJUST_EXCEPTION_FRAME	/*  */
+
+#define INTERRUPT_RETURN	iretq
+#define USERGS_SYSRET64				\
+	swapgs;					\
+	sysretq;
+#define USERGS_SYSRET32				\
+	swapgs;					\
+	sysretl
+#define ENABLE_INTERRUPTS_SYSEXIT32		\
+	swapgs;					\
+	sti;					\
+	sysexit
+
+#else
+#define INTERRUPT_RETURN		iret
+#define ENABLE_INTERRUPTS_SYSEXIT	sti; sysexit
+#define GET_CR0_INTO_EAX		movl %cr0, %eax
+#endif
+
+
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_PARAVIRT */
+
+#ifndef __ASSEMBLY__
+#define raw_local_save_flags(flags)				\
+	do { (flags) = __raw_local_save_flags(); } while (0)
+
+#define raw_local_irq_save(flags)				\
+	do { (flags) = __raw_local_irq_save(); } while (0)
+
+static inline int raw_irqs_disabled_flags(unsigned long flags)
+{
+	return !(flags & X86_EFLAGS_IF);
+}
+
+static inline int raw_irqs_disabled(void)
+{
+	unsigned long flags = __raw_local_save_flags();
+
+	return raw_irqs_disabled_flags(flags);
+}
+
+#else
+
+#ifdef CONFIG_X86_64
+#define ARCH_LOCKDEP_SYS_EXIT		call lockdep_sys_exit_thunk
+#define ARCH_LOCKDEP_SYS_EXIT_IRQ	\
+	TRACE_IRQS_ON; \
+	sti; \
+	SAVE_REST; \
+	LOCKDEP_SYS_EXIT; \
+	RESTORE_REST; \
+	cli; \
+	TRACE_IRQS_OFF;
+
+#else
+#define ARCH_LOCKDEP_SYS_EXIT			\
+	pushl %eax;				\
+	pushl %ecx;				\
+	pushl %edx;				\
+	call lockdep_sys_exit;			\
+	popl %edx;				\
+	popl %ecx;				\
+	popl %eax;
+
+#define ARCH_LOCKDEP_SYS_EXIT_IRQ
+#endif
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+#  define TRACE_IRQS_ON		call trace_hardirqs_on_thunk;
+#  define TRACE_IRQS_OFF	call trace_hardirqs_off_thunk;
+#else
+#  define TRACE_IRQS_ON
+#  define TRACE_IRQS_OFF
+#endif
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+#  define LOCKDEP_SYS_EXIT	ARCH_LOCKDEP_SYS_EXIT
+#  define LOCKDEP_SYS_EXIT_IRQ	ARCH_LOCKDEP_SYS_EXIT_IRQ
+# else
+#  define LOCKDEP_SYS_EXIT
+#  define LOCKDEP_SYS_EXIT_IRQ
+# endif
+
+#endif /* __ASSEMBLY__ */
+#endif
diff --git a/arch/x86/include/asm/ist.h b/arch/x86/include/asm/ist.h
new file mode 100644
index 000000000000..35a2fe9bc921
--- /dev/null
+++ b/arch/x86/include/asm/ist.h
@@ -0,0 +1,34 @@
+#ifndef ASM_X86__IST_H
+#define ASM_X86__IST_H
+
+/*
+ * Include file for the interface to IST BIOS
+ * Copyright 2002 Andy Grover <andrew.grover@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the
+ * Free Software Foundation; either version 2, or (at your option) any
+ * later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+
+#include <linux/types.h>
+
+struct ist_info {
+	__u32 signature;
+	__u32 command;
+	__u32 event;
+	__u32 perf_level;
+};
+
+#ifdef __KERNEL__
+
+extern struct ist_info ist_info;
+
+#endif	/* __KERNEL__ */
+#endif /* ASM_X86__IST_H */
diff --git a/arch/x86/include/asm/k8.h b/arch/x86/include/asm/k8.h
new file mode 100644
index 000000000000..2bbaf4370a55
--- /dev/null
+++ b/arch/x86/include/asm/k8.h
@@ -0,0 +1,15 @@
+#ifndef ASM_X86__K8_H
+#define ASM_X86__K8_H
+
+#include <linux/pci.h>
+
+extern struct pci_device_id k8_nb_ids[];
+
+extern int early_is_k8_nb(u32 value);
+extern struct pci_dev **k8_northbridges;
+extern int num_k8_northbridges;
+extern int cache_k8_northbridges(void);
+extern void k8_flush_garts(void);
+extern int k8_scan_nodes(unsigned long start, unsigned long end);
+
+#endif /* ASM_X86__K8_H */
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
new file mode 100644
index 000000000000..fbbab66ee9df
--- /dev/null
+++ b/arch/x86/include/asm/kdebug.h
@@ -0,0 +1,37 @@
+#ifndef ASM_X86__KDEBUG_H
+#define ASM_X86__KDEBUG_H
+
+#include <linux/notifier.h>
+
+struct pt_regs;
+
+/* Grossly misnamed. */
+enum die_val {
+	DIE_OOPS = 1,
+	DIE_INT3,
+	DIE_DEBUG,
+	DIE_PANIC,
+	DIE_NMI,
+	DIE_DIE,
+	DIE_NMIWATCHDOG,
+	DIE_KERNELDEBUG,
+	DIE_TRAP,
+	DIE_GPF,
+	DIE_CALL,
+	DIE_NMI_IPI,
+	DIE_PAGE_FAULT,
+	DIE_NMIUNKNOWN,
+};
+
+extern void printk_address(unsigned long address, int reliable);
+extern void die(const char *, struct pt_regs *,long);
+extern int __must_check __die(const char *, struct pt_regs *, long);
+extern void show_registers(struct pt_regs *regs);
+extern void show_trace(struct task_struct *t, struct pt_regs *regs,
+		       unsigned long *sp, unsigned long bp);
+extern void __show_regs(struct pt_regs *regs, int all);
+extern void show_regs(struct pt_regs *regs);
+extern unsigned long oops_begin(void);
+extern void oops_end(unsigned long, struct pt_regs *, int signr);
+
+#endif /* ASM_X86__KDEBUG_H */
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
new file mode 100644
index 000000000000..ea09600d6129
--- /dev/null
+++ b/arch/x86/include/asm/kexec.h
@@ -0,0 +1,175 @@
+#ifndef ASM_X86__KEXEC_H
+#define ASM_X86__KEXEC_H
+
+#ifdef CONFIG_X86_32
+# define PA_CONTROL_PAGE	0
+# define VA_CONTROL_PAGE	1
+# define PA_PGD			2
+# define VA_PGD			3
+# define PA_PTE_0		4
+# define VA_PTE_0		5
+# define PA_PTE_1		6
+# define VA_PTE_1		7
+# define PA_SWAP_PAGE		8
+# ifdef CONFIG_X86_PAE
+#  define PA_PMD_0		9
+#  define VA_PMD_0		10
+#  define PA_PMD_1		11
+#  define VA_PMD_1		12
+#  define PAGES_NR		13
+# else
+#  define PAGES_NR		9
+# endif
+#else
+# define PA_CONTROL_PAGE	0
+# define VA_CONTROL_PAGE	1
+# define PA_PGD			2
+# define VA_PGD			3
+# define PA_PUD_0		4
+# define VA_PUD_0		5
+# define PA_PMD_0		6
+# define VA_PMD_0		7
+# define PA_PTE_0		8
+# define VA_PTE_0		9
+# define PA_PUD_1		10
+# define VA_PUD_1		11
+# define PA_PMD_1		12
+# define VA_PMD_1		13
+# define PA_PTE_1		14
+# define VA_PTE_1		15
+# define PA_TABLE_PAGE		16
+# define PAGES_NR		17
+#endif
+
+#ifdef CONFIG_X86_32
+# define KEXEC_CONTROL_CODE_MAX_SIZE	2048
+#endif
+
+#ifndef __ASSEMBLY__
+
+#include <linux/string.h>
+
+#include <asm/page.h>
+#include <asm/ptrace.h>
+
+/*
+ * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return.
+ * I.e. Maximum page that is mapped directly into kernel memory,
+ * and kmap is not required.
+ *
+ * So far x86_64 is limited to 40 physical address bits.
+ */
+#ifdef CONFIG_X86_32
+/* Maximum physical address we can use pages from */
+# define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
+/* Maximum address we can reach in physical address mode */
+# define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
+/* Maximum address we can use for the control code buffer */
+# define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE
+
+# define KEXEC_CONTROL_PAGE_SIZE	4096
+
+/* The native architecture */
+# define KEXEC_ARCH KEXEC_ARCH_386
+
+/* We can also handle crash dumps from 64 bit kernel. */
+# define vmcore_elf_check_arch_cross(x) ((x)->e_machine == EM_X86_64)
+#else
+/* Maximum physical address we can use pages from */
+# define KEXEC_SOURCE_MEMORY_LIMIT      (0xFFFFFFFFFFUL)
+/* Maximum address we can reach in physical address mode */
+# define KEXEC_DESTINATION_MEMORY_LIMIT (0xFFFFFFFFFFUL)
+/* Maximum address we can use for the control pages */
+# define KEXEC_CONTROL_MEMORY_LIMIT     (0xFFFFFFFFFFUL)
+
+/* Allocate one page for the pdp and the second for the code */
+# define KEXEC_CONTROL_PAGE_SIZE  (4096UL + 4096UL)
+
+/* The native architecture */
+# define KEXEC_ARCH KEXEC_ARCH_X86_64
+#endif
+
+/*
+ * CPU does not save ss and sp on stack if execution is already
+ * running in kernel mode at the time of NMI occurrence. This code
+ * fixes it.
+ */
+static inline void crash_fixup_ss_esp(struct pt_regs *newregs,
+				      struct pt_regs *oldregs)
+{
+#ifdef CONFIG_X86_32
+	newregs->sp = (unsigned long)&(oldregs->sp);
+	asm volatile("xorl %%eax, %%eax\n\t"
+		     "movw %%ss, %%ax\n\t"
+		     :"=a"(newregs->ss));
+#endif
+}
+
+/*
+ * This function is responsible for capturing register states if coming
+ * via panic otherwise just fix up the ss and sp if coming via kernel
+ * mode exception.
+ */
+static inline void crash_setup_regs(struct pt_regs *newregs,
+				    struct pt_regs *oldregs)
+{
+	if (oldregs) {
+		memcpy(newregs, oldregs, sizeof(*newregs));
+		crash_fixup_ss_esp(newregs, oldregs);
+	} else {
+#ifdef CONFIG_X86_32
+		asm volatile("movl %%ebx,%0" : "=m"(newregs->bx));
+		asm volatile("movl %%ecx,%0" : "=m"(newregs->cx));
+		asm volatile("movl %%edx,%0" : "=m"(newregs->dx));
+		asm volatile("movl %%esi,%0" : "=m"(newregs->si));
+		asm volatile("movl %%edi,%0" : "=m"(newregs->di));
+		asm volatile("movl %%ebp,%0" : "=m"(newregs->bp));
+		asm volatile("movl %%eax,%0" : "=m"(newregs->ax));
+		asm volatile("movl %%esp,%0" : "=m"(newregs->sp));
+		asm volatile("movl %%ss, %%eax;" :"=a"(newregs->ss));
+		asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs));
+		asm volatile("movl %%ds, %%eax;" :"=a"(newregs->ds));
+		asm volatile("movl %%es, %%eax;" :"=a"(newregs->es));
+		asm volatile("pushfl; popl %0" :"=m"(newregs->flags));
+#else
+		asm volatile("movq %%rbx,%0" : "=m"(newregs->bx));
+		asm volatile("movq %%rcx,%0" : "=m"(newregs->cx));
+		asm volatile("movq %%rdx,%0" : "=m"(newregs->dx));
+		asm volatile("movq %%rsi,%0" : "=m"(newregs->si));
+		asm volatile("movq %%rdi,%0" : "=m"(newregs->di));
+		asm volatile("movq %%rbp,%0" : "=m"(newregs->bp));
+		asm volatile("movq %%rax,%0" : "=m"(newregs->ax));
+		asm volatile("movq %%rsp,%0" : "=m"(newregs->sp));
+		asm volatile("movq %%r8,%0" : "=m"(newregs->r8));
+		asm volatile("movq %%r9,%0" : "=m"(newregs->r9));
+		asm volatile("movq %%r10,%0" : "=m"(newregs->r10));
+		asm volatile("movq %%r11,%0" : "=m"(newregs->r11));
+		asm volatile("movq %%r12,%0" : "=m"(newregs->r12));
+		asm volatile("movq %%r13,%0" : "=m"(newregs->r13));
+		asm volatile("movq %%r14,%0" : "=m"(newregs->r14));
+		asm volatile("movq %%r15,%0" : "=m"(newregs->r15));
+		asm volatile("movl %%ss, %%eax;" :"=a"(newregs->ss));
+		asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs));
+		asm volatile("pushfq; popq %0" :"=m"(newregs->flags));
+#endif
+		newregs->ip = (unsigned long)current_text_addr();
+	}
+}
+
+#ifdef CONFIG_X86_32
+asmlinkage unsigned long
+relocate_kernel(unsigned long indirection_page,
+		unsigned long control_page,
+		unsigned long start_address,
+		unsigned int has_pae,
+		unsigned int preserve_context);
+#else
+NORET_TYPE void
+relocate_kernel(unsigned long indirection_page,
+		unsigned long page_list,
+		unsigned long start_address) ATTRIB_NORET;
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* ASM_X86__KEXEC_H */
diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h
new file mode 100644
index 000000000000..d283863354de
--- /dev/null
+++ b/arch/x86/include/asm/kgdb.h
@@ -0,0 +1,79 @@
+#ifndef ASM_X86__KGDB_H
+#define ASM_X86__KGDB_H
+
+/*
+ * Copyright (C) 2001-2004 Amit S. Kale
+ * Copyright (C) 2008 Wind River Systems, Inc.
+ */
+
+/*
+ * BUFMAX defines the maximum number of characters in inbound/outbound
+ * buffers at least NUMREGBYTES*2 are needed for register packets
+ * Longer buffer is needed to list all threads
+ */
+#define BUFMAX			1024
+
+/*
+ *  Note that this register image is in a different order than
+ *  the register image that Linux produces at interrupt time.
+ *
+ *  Linux's register image is defined by struct pt_regs in ptrace.h.
+ *  Just why GDB uses a different order is a historical mystery.
+ */
+#ifdef CONFIG_X86_32
+enum regnames {
+	GDB_AX,			/* 0 */
+	GDB_CX,			/* 1 */
+	GDB_DX,			/* 2 */
+	GDB_BX,			/* 3 */
+	GDB_SP,			/* 4 */
+	GDB_BP,			/* 5 */
+	GDB_SI,			/* 6 */
+	GDB_DI,			/* 7 */
+	GDB_PC,			/* 8 also known as eip */
+	GDB_PS,			/* 9 also known as eflags */
+	GDB_CS,			/* 10 */
+	GDB_SS,			/* 11 */
+	GDB_DS,			/* 12 */
+	GDB_ES,			/* 13 */
+	GDB_FS,			/* 14 */
+	GDB_GS,			/* 15 */
+};
+#define NUMREGBYTES		((GDB_GS+1)*4)
+#else /* ! CONFIG_X86_32 */
+enum regnames64 {
+	GDB_AX,			/* 0 */
+	GDB_BX,			/* 1 */
+	GDB_CX,			/* 2 */
+	GDB_DX,			/* 3 */
+	GDB_SI,			/* 4 */
+	GDB_DI,			/* 5 */
+	GDB_BP,			/* 6 */
+	GDB_SP,			/* 7 */
+	GDB_R8,			/* 8 */
+	GDB_R9,			/* 9 */
+	GDB_R10,		/* 10 */
+	GDB_R11,		/* 11 */
+	GDB_R12,		/* 12 */
+	GDB_R13,		/* 13 */
+	GDB_R14,		/* 14 */
+	GDB_R15,		/* 15 */
+	GDB_PC,			/* 16 */
+};
+
+enum regnames32 {
+	GDB_PS = 34,
+	GDB_CS,
+	GDB_SS,
+};
+#define NUMREGBYTES		((GDB_SS+1)*4)
+#endif /* CONFIG_X86_32 */
+
+static inline void arch_kgdb_breakpoint(void)
+{
+	asm("   int $3");
+}
+#define BREAK_INSTR_SIZE	1
+#define CACHE_FLUSH_IS_SAFE	1
+
+#endif /* ASM_X86__KGDB_H */
diff --git a/arch/x86/include/asm/kmap_types.h b/arch/x86/include/asm/kmap_types.h
new file mode 100644
index 000000000000..89f44493e643
--- /dev/null
+++ b/arch/x86/include/asm/kmap_types.h
@@ -0,0 +1,29 @@
+#ifndef ASM_X86__KMAP_TYPES_H
+#define ASM_X86__KMAP_TYPES_H
+
+#if defined(CONFIG_X86_32) && defined(CONFIG_DEBUG_HIGHMEM)
+# define D(n) __KM_FENCE_##n ,
+#else
+# define D(n)
+#endif
+
+enum km_type {
+D(0)	KM_BOUNCE_READ,
+D(1)	KM_SKB_SUNRPC_DATA,
+D(2)	KM_SKB_DATA_SOFTIRQ,
+D(3)	KM_USER0,
+D(4)	KM_USER1,
+D(5)	KM_BIO_SRC_IRQ,
+D(6)	KM_BIO_DST_IRQ,
+D(7)	KM_PTE0,
+D(8)	KM_PTE1,
+D(9)	KM_IRQ0,
+D(10)	KM_IRQ1,
+D(11)	KM_SOFTIRQ0,
+D(12)	KM_SOFTIRQ1,
+D(13)	KM_TYPE_NR
+};
+
+#undef D
+
+#endif /* ASM_X86__KMAP_TYPES_H */
diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
new file mode 100644
index 000000000000..8a0748d01036
--- /dev/null
+++ b/arch/x86/include/asm/kprobes.h
@@ -0,0 +1,88 @@
+#ifndef ASM_X86__KPROBES_H
+#define ASM_X86__KPROBES_H
+/*
+ *  Kernel Probes (KProbes)
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
+ *
+ * Copyright (C) IBM Corporation, 2002, 2004
+ *
+ * See arch/x86/kernel/kprobes.c for x86 kprobes history.
+ */
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/percpu.h>
+
+#define  __ARCH_WANT_KPROBES_INSN_SLOT
+
+struct pt_regs;
+struct kprobe;
+
+typedef u8 kprobe_opcode_t;
+#define BREAKPOINT_INSTRUCTION	0xcc
+#define RELATIVEJUMP_INSTRUCTION 0xe9
+#define MAX_INSN_SIZE 16
+#define MAX_STACK_SIZE 64
+#define MIN_STACK_SIZE(ADDR)					       \
+	(((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \
+			      THREAD_SIZE - (unsigned long)(ADDR)))    \
+	 ? (MAX_STACK_SIZE)					       \
+	 : (((unsigned long)current_thread_info()) +		       \
+	    THREAD_SIZE - (unsigned long)(ADDR)))
+
+#define flush_insn_slot(p)	do { } while (0)
+
+extern const int kretprobe_blacklist_size;
+
+void arch_remove_kprobe(struct kprobe *p);
+void kretprobe_trampoline(void);
+
+/* Architecture specific copy of original instruction*/
+struct arch_specific_insn {
+	/* copy of the original instruction */
+	kprobe_opcode_t *insn;
+	/*
+	 * boostable = -1: This instruction type is not boostable.
+	 * boostable = 0: This instruction type is boostable.
+	 * boostable = 1: This instruction has been boosted: we have
+	 * added a relative jump after the instruction copy in insn,
+	 * so no single-step and fixup are needed (unless there's
+	 * a post_handler or break_handler).
+	 */
+	int boostable;
+};
+
+struct prev_kprobe {
+	struct kprobe *kp;
+	unsigned long status;
+	unsigned long old_flags;
+	unsigned long saved_flags;
+};
+
+/* per-cpu kprobe control block */
+struct kprobe_ctlblk {
+	unsigned long kprobe_status;
+	unsigned long kprobe_old_flags;
+	unsigned long kprobe_saved_flags;
+	unsigned long *jprobe_saved_sp;
+	struct pt_regs jprobe_saved_regs;
+	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
+	struct prev_kprobe prev_kprobe;
+};
+
+extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
+extern int kprobe_exceptions_notify(struct notifier_block *self,
+				    unsigned long val, void *data);
+#endif /* ASM_X86__KPROBES_H */
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
new file mode 100644
index 000000000000..ba0dd791fadf
--- /dev/null
+++ b/arch/x86/include/asm/kvm.h
@@ -0,0 +1,211 @@
+#ifndef ASM_X86__KVM_H
+#define ASM_X86__KVM_H
+
+/*
+ * KVM x86 specific structures and definitions
+ *
+ */
+
+#include <asm/types.h>
+#include <linux/ioctl.h>
+
+/* Architectural interrupt line count. */
+#define KVM_NR_INTERRUPTS 256
+
+struct kvm_memory_alias {
+	__u32 slot;  /* this has a different namespace than memory slots */
+	__u32 flags;
+	__u64 guest_phys_addr;
+	__u64 memory_size;
+	__u64 target_phys_addr;
+};
+
+/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */
+struct kvm_pic_state {
+	__u8 last_irr;	/* edge detection */
+	__u8 irr;		/* interrupt request register */
+	__u8 imr;		/* interrupt mask register */
+	__u8 isr;		/* interrupt service register */
+	__u8 priority_add;	/* highest irq priority */
+	__u8 irq_base;
+	__u8 read_reg_select;
+	__u8 poll;
+	__u8 special_mask;
+	__u8 init_state;
+	__u8 auto_eoi;
+	__u8 rotate_on_auto_eoi;
+	__u8 special_fully_nested_mode;
+	__u8 init4;		/* true if 4 byte init */
+	__u8 elcr;		/* PIIX edge/trigger selection */
+	__u8 elcr_mask;
+};
+
+#define KVM_IOAPIC_NUM_PINS  24
+struct kvm_ioapic_state {
+	__u64 base_address;
+	__u32 ioregsel;
+	__u32 id;
+	__u32 irr;
+	__u32 pad;
+	union {
+		__u64 bits;
+		struct {
+			__u8 vector;
+			__u8 delivery_mode:3;
+			__u8 dest_mode:1;
+			__u8 delivery_status:1;
+			__u8 polarity:1;
+			__u8 remote_irr:1;
+			__u8 trig_mode:1;
+			__u8 mask:1;
+			__u8 reserve:7;
+			__u8 reserved[4];
+			__u8 dest_id;
+		} fields;
+	} redirtbl[KVM_IOAPIC_NUM_PINS];
+};
+
+#define KVM_IRQCHIP_PIC_MASTER   0
+#define KVM_IRQCHIP_PIC_SLAVE    1
+#define KVM_IRQCHIP_IOAPIC       2
+
+/* for KVM_GET_REGS and KVM_SET_REGS */
+struct kvm_regs {
+	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
+	__u64 rax, rbx, rcx, rdx;
+	__u64 rsi, rdi, rsp, rbp;
+	__u64 r8,  r9,  r10, r11;
+	__u64 r12, r13, r14, r15;
+	__u64 rip, rflags;
+};
+
+/* for KVM_GET_LAPIC and KVM_SET_LAPIC */
+#define KVM_APIC_REG_SIZE 0x400
+struct kvm_lapic_state {
+	char regs[KVM_APIC_REG_SIZE];
+};
+
+struct kvm_segment {
+	__u64 base;
+	__u32 limit;
+	__u16 selector;
+	__u8  type;
+	__u8  present, dpl, db, s, l, g, avl;
+	__u8  unusable;
+	__u8  padding;
+};
+
+struct kvm_dtable {
+	__u64 base;
+	__u16 limit;
+	__u16 padding[3];
+};
+
+
+/* for KVM_GET_SREGS and KVM_SET_SREGS */
+struct kvm_sregs {
+	/* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */
+	struct kvm_segment cs, ds, es, fs, gs, ss;
+	struct kvm_segment tr, ldt;
+	struct kvm_dtable gdt, idt;
+	__u64 cr0, cr2, cr3, cr4, cr8;
+	__u64 efer;
+	__u64 apic_base;
+	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
+};
+
+/* for KVM_GET_FPU and KVM_SET_FPU */
+struct kvm_fpu {
+	__u8  fpr[8][16];
+	__u16 fcw;
+	__u16 fsw;
+	__u8  ftwx;  /* in fxsave format */
+	__u8  pad1;
+	__u16 last_opcode;
+	__u64 last_ip;
+	__u64 last_dp;
+	__u8  xmm[16][16];
+	__u32 mxcsr;
+	__u32 pad2;
+};
+
+struct kvm_msr_entry {
+	__u32 index;
+	__u32 reserved;
+	__u64 data;
+};
+
+/* for KVM_GET_MSRS and KVM_SET_MSRS */
+struct kvm_msrs {
+	__u32 nmsrs; /* number of msrs in entries */
+	__u32 pad;
+
+	struct kvm_msr_entry entries[0];
+};
+
+/* for KVM_GET_MSR_INDEX_LIST */
+struct kvm_msr_list {
+	__u32 nmsrs; /* number of msrs in entries */
+	__u32 indices[0];
+};
+
+
+struct kvm_cpuid_entry {
+	__u32 function;
+	__u32 eax;
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 padding;
+};
+
+/* for KVM_SET_CPUID */
+struct kvm_cpuid {
+	__u32 nent;
+	__u32 padding;
+	struct kvm_cpuid_entry entries[0];
+};
+
+struct kvm_cpuid_entry2 {
+	__u32 function;
+	__u32 index;
+	__u32 flags;
+	__u32 eax;
+	__u32 ebx;
+	__u32 ecx;
+	__u32 edx;
+	__u32 padding[3];
+};
+
+#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
+#define KVM_CPUID_FLAG_STATEFUL_FUNC    2
+#define KVM_CPUID_FLAG_STATE_READ_NEXT  4
+
+/* for KVM_SET_CPUID2 */
+struct kvm_cpuid2 {
+	__u32 nent;
+	__u32 padding;
+	struct kvm_cpuid_entry2 entries[0];
+};
+
+/* for KVM_GET_PIT and KVM_SET_PIT */
+struct kvm_pit_channel_state {
+	__u32 count; /* can be 65536 */
+	__u16 latched_count;
+	__u8 count_latched;
+	__u8 status_latched;
+	__u8 status;
+	__u8 read_state;
+	__u8 write_state;
+	__u8 write_latch;
+	__u8 rw_mode;
+	__u8 mode;
+	__u8 bcd;
+	__u8 gate;
+	__s64 count_load_time;
+};
+
+struct kvm_pit_state {
+	struct kvm_pit_channel_state channels[3];
+};
+#endif /* ASM_X86__KVM_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
new file mode 100644
index 000000000000..411fb8cfb24e
--- /dev/null
+++ b/arch/x86/include/asm/kvm_host.h
@@ -0,0 +1,752 @@
+/*
+ * Kernel-based Virtual Machine driver for Linux
+ *
+ * This header defines architecture specific interfaces, x86 version
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#ifndef ASM_X86__KVM_HOST_H
+#define ASM_X86__KVM_HOST_H
+
+#include <linux/types.h>
+#include <linux/mm.h>
+#include <linux/mmu_notifier.h>
+
+#include <linux/kvm.h>
+#include <linux/kvm_para.h>
+#include <linux/kvm_types.h>
+
+#include <asm/pvclock-abi.h>
+#include <asm/desc.h>
+
+#define KVM_MAX_VCPUS 16
+#define KVM_MEMORY_SLOTS 32
+/* memory slots that does not exposed to userspace */
+#define KVM_PRIVATE_MEM_SLOTS 4
+
+#define KVM_PIO_PAGE_OFFSET 1
+#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
+
+#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
+#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
+#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |	\
+				  0xFFFFFF0000000000ULL)
+
+#define KVM_GUEST_CR0_MASK				   \
+	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \
+	 | X86_CR0_NW | X86_CR0_CD)
+#define KVM_VM_CR0_ALWAYS_ON						\
+	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
+	 | X86_CR0_MP)
+#define KVM_GUEST_CR4_MASK						\
+	(X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
+#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
+#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
+
+#define INVALID_PAGE (~(hpa_t)0)
+#define UNMAPPED_GVA (~(gpa_t)0)
+
+/* shadow tables are PAE even on non-PAE hosts */
+#define KVM_HPAGE_SHIFT 21
+#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT)
+#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1))
+
+#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE)
+
+#define DE_VECTOR 0
+#define DB_VECTOR 1
+#define BP_VECTOR 3
+#define OF_VECTOR 4
+#define BR_VECTOR 5
+#define UD_VECTOR 6
+#define NM_VECTOR 7
+#define DF_VECTOR 8
+#define TS_VECTOR 10
+#define NP_VECTOR 11
+#define SS_VECTOR 12
+#define GP_VECTOR 13
+#define PF_VECTOR 14
+#define MF_VECTOR 16
+#define MC_VECTOR 18
+
+#define SELECTOR_TI_MASK (1 << 2)
+#define SELECTOR_RPL_MASK 0x03
+
+#define IOPL_SHIFT 12
+
+#define KVM_ALIAS_SLOTS 4
+
+#define KVM_PERMILLE_MMU_PAGES 20
+#define KVM_MIN_ALLOC_MMU_PAGES 64
+#define KVM_MMU_HASH_SHIFT 10
+#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
+#define KVM_MIN_FREE_MMU_PAGES 5
+#define KVM_REFILL_PAGES 25
+#define KVM_MAX_CPUID_ENTRIES 40
+#define KVM_NR_VAR_MTRR 8
+
+extern spinlock_t kvm_lock;
+extern struct list_head vm_list;
+
+struct kvm_vcpu;
+struct kvm;
+
+enum kvm_reg {
+	VCPU_REGS_RAX = 0,
+	VCPU_REGS_RCX = 1,
+	VCPU_REGS_RDX = 2,
+	VCPU_REGS_RBX = 3,
+	VCPU_REGS_RSP = 4,
+	VCPU_REGS_RBP = 5,
+	VCPU_REGS_RSI = 6,
+	VCPU_REGS_RDI = 7,
+#ifdef CONFIG_X86_64
+	VCPU_REGS_R8 = 8,
+	VCPU_REGS_R9 = 9,
+	VCPU_REGS_R10 = 10,
+	VCPU_REGS_R11 = 11,
+	VCPU_REGS_R12 = 12,
+	VCPU_REGS_R13 = 13,
+	VCPU_REGS_R14 = 14,
+	VCPU_REGS_R15 = 15,
+#endif
+	VCPU_REGS_RIP,
+	NR_VCPU_REGS
+};
+
+enum {
+	VCPU_SREG_ES,
+	VCPU_SREG_CS,
+	VCPU_SREG_SS,
+	VCPU_SREG_DS,
+	VCPU_SREG_FS,
+	VCPU_SREG_GS,
+	VCPU_SREG_TR,
+	VCPU_SREG_LDTR,
+};
+
+#include <asm/kvm_x86_emulate.h>
+
+#define KVM_NR_MEM_OBJS 40
+
+struct kvm_guest_debug {
+	int enabled;
+	unsigned long bp[4];
+	int singlestep;
+};
+
+/*
+ * We don't want allocation failures within the mmu code, so we preallocate
+ * enough memory for a single page fault in a cache.
+ */
+struct kvm_mmu_memory_cache {
+	int nobjs;
+	void *objects[KVM_NR_MEM_OBJS];
+};
+
+#define NR_PTE_CHAIN_ENTRIES 5
+
+struct kvm_pte_chain {
+	u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES];
+	struct hlist_node link;
+};
+
+/*
+ * kvm_mmu_page_role, below, is defined as:
+ *
+ *   bits 0:3 - total guest paging levels (2-4, or zero for real mode)
+ *   bits 4:7 - page table level for this shadow (1-4)
+ *   bits 8:9 - page table quadrant for 2-level guests
+ *   bit   16 - "metaphysical" - gfn is not a real page (huge page/real mode)
+ *   bits 17:19 - common access permissions for all ptes in this shadow page
+ */
+union kvm_mmu_page_role {
+	unsigned word;
+	struct {
+		unsigned glevels:4;
+		unsigned level:4;
+		unsigned quadrant:2;
+		unsigned pad_for_nice_hex_output:6;
+		unsigned metaphysical:1;
+		unsigned access:3;
+		unsigned invalid:1;
+	};
+};
+
+struct kvm_mmu_page {
+	struct list_head link;
+	struct hlist_node hash_link;
+
+	/*
+	 * The following two entries are used to key the shadow page in the
+	 * hash table.
+	 */
+	gfn_t gfn;
+	union kvm_mmu_page_role role;
+
+	u64 *spt;
+	/* hold the gfn of each spte inside spt */
+	gfn_t *gfns;
+	unsigned long slot_bitmap; /* One bit set per slot which has memory
+				    * in this shadow page.
+				    */
+	int multimapped;         /* More than one parent_pte? */
+	int root_count;          /* Currently serving as active root */
+	bool unsync;
+	bool unsync_children;
+	union {
+		u64 *parent_pte;               /* !multimapped */
+		struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */
+	};
+	DECLARE_BITMAP(unsync_child_bitmap, 512);
+};
+
+struct kvm_pv_mmu_op_buffer {
+	void *ptr;
+	unsigned len;
+	unsigned processed;
+	char buf[512] __aligned(sizeof(long));
+};
+
+/*
+ * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
+ * 32-bit).  The kvm_mmu structure abstracts the details of the current mmu
+ * mode.
+ */
+struct kvm_mmu {
+	void (*new_cr3)(struct kvm_vcpu *vcpu);
+	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
+	void (*free)(struct kvm_vcpu *vcpu);
+	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
+	void (*prefetch_page)(struct kvm_vcpu *vcpu,
+			      struct kvm_mmu_page *page);
+	int (*sync_page)(struct kvm_vcpu *vcpu,
+			 struct kvm_mmu_page *sp);
+	void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
+	hpa_t root_hpa;
+	int root_level;
+	int shadow_root_level;
+
+	u64 *pae_root;
+};
+
+struct kvm_vcpu_arch {
+	u64 host_tsc;
+	int interrupt_window_open;
+	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
+	DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS);
+	/*
+	 * rip and regs accesses must go through
+	 * kvm_{register,rip}_{read,write} functions.
+	 */
+	unsigned long regs[NR_VCPU_REGS];
+	u32 regs_avail;
+	u32 regs_dirty;
+
+	unsigned long cr0;
+	unsigned long cr2;
+	unsigned long cr3;
+	unsigned long cr4;
+	unsigned long cr8;
+	u64 pdptrs[4]; /* pae */
+	u64 shadow_efer;
+	u64 apic_base;
+	struct kvm_lapic *apic;    /* kernel irqchip context */
+	int mp_state;
+	int sipi_vector;
+	u64 ia32_misc_enable_msr;
+	bool tpr_access_reporting;
+
+	struct kvm_mmu mmu;
+	/* only needed in kvm_pv_mmu_op() path, but it's hot so
+	 * put it here to avoid allocation */
+	struct kvm_pv_mmu_op_buffer mmu_op_buffer;
+
+	struct kvm_mmu_memory_cache mmu_pte_chain_cache;
+	struct kvm_mmu_memory_cache mmu_rmap_desc_cache;
+	struct kvm_mmu_memory_cache mmu_page_cache;
+	struct kvm_mmu_memory_cache mmu_page_header_cache;
+
+	gfn_t last_pt_write_gfn;
+	int   last_pt_write_count;
+	u64  *last_pte_updated;
+	gfn_t last_pte_gfn;
+
+	struct {
+		gfn_t gfn;	/* presumed gfn during guest pte update */
+		pfn_t pfn;	/* pfn corresponding to that gfn */
+		int largepage;
+		unsigned long mmu_seq;
+	} update_pte;
+
+	struct i387_fxsave_struct host_fx_image;
+	struct i387_fxsave_struct guest_fx_image;
+
+	gva_t mmio_fault_cr2;
+	struct kvm_pio_request pio;
+	void *pio_data;
+
+	struct kvm_queued_exception {
+		bool pending;
+		bool has_error_code;
+		u8 nr;
+		u32 error_code;
+	} exception;
+
+	struct kvm_queued_interrupt {
+		bool pending;
+		u8 nr;
+	} interrupt;
+
+	struct {
+		int active;
+		u8 save_iopl;
+		struct kvm_save_segment {
+			u16 selector;
+			unsigned long base;
+			u32 limit;
+			u32 ar;
+		} tr, es, ds, fs, gs;
+	} rmode;
+	int halt_request; /* real mode on Intel only */
+
+	int cpuid_nent;
+	struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES];
+	/* emulate context */
+
+	struct x86_emulate_ctxt emulate_ctxt;
+
+	gpa_t time;
+	struct pvclock_vcpu_time_info hv_clock;
+	unsigned int hv_clock_tsc_khz;
+	unsigned int time_offset;
+	struct page *time_page;
+
+	bool nmi_pending;
+	bool nmi_injected;
+
+	u64 mtrr[0x100];
+};
+
+struct kvm_mem_alias {
+	gfn_t base_gfn;
+	unsigned long npages;
+	gfn_t target_gfn;
+};
+
+struct kvm_arch{
+	int naliases;
+	struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS];
+
+	unsigned int n_free_mmu_pages;
+	unsigned int n_requested_mmu_pages;
+	unsigned int n_alloc_mmu_pages;
+	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
+	/*
+	 * Hash table of struct kvm_mmu_page.
+	 */
+	struct list_head active_mmu_pages;
+	struct list_head assigned_dev_head;
+	struct dmar_domain *intel_iommu_domain;
+	struct kvm_pic *vpic;
+	struct kvm_ioapic *vioapic;
+	struct kvm_pit *vpit;
+	struct hlist_head irq_ack_notifier_list;
+
+	int round_robin_prev_vcpu;
+	unsigned int tss_addr;
+	struct page *apic_access_page;
+
+	gpa_t wall_clock;
+
+	struct page *ept_identity_pagetable;
+	bool ept_identity_pagetable_done;
+};
+
+struct kvm_vm_stat {
+	u32 mmu_shadow_zapped;
+	u32 mmu_pte_write;
+	u32 mmu_pte_updated;
+	u32 mmu_pde_zapped;
+	u32 mmu_flooded;
+	u32 mmu_recycled;
+	u32 mmu_cache_miss;
+	u32 mmu_unsync;
+	u32 remote_tlb_flush;
+	u32 lpages;
+};
+
+struct kvm_vcpu_stat {
+	u32 pf_fixed;
+	u32 pf_guest;
+	u32 tlb_flush;
+	u32 invlpg;
+
+	u32 exits;
+	u32 io_exits;
+	u32 mmio_exits;
+	u32 signal_exits;
+	u32 irq_window_exits;
+	u32 nmi_window_exits;
+	u32 halt_exits;
+	u32 halt_wakeup;
+	u32 request_irq_exits;
+	u32 irq_exits;
+	u32 host_state_reload;
+	u32 efer_reload;
+	u32 fpu_reload;
+	u32 insn_emulation;
+	u32 insn_emulation_fail;
+	u32 hypercalls;
+	u32 irq_injections;
+};
+
+struct descriptor_table {
+	u16 limit;
+	unsigned long base;
+} __attribute__((packed));
+
+struct kvm_x86_ops {
+	int (*cpu_has_kvm_support)(void);          /* __init */
+	int (*disabled_by_bios)(void);             /* __init */
+	void (*hardware_enable)(void *dummy);      /* __init */
+	void (*hardware_disable)(void *dummy);
+	void (*check_processor_compatibility)(void *rtn);
+	int (*hardware_setup)(void);               /* __init */
+	void (*hardware_unsetup)(void);            /* __exit */
+	bool (*cpu_has_accelerated_tpr)(void);
+
+	/* Create, but do not attach this VCPU */
+	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
+	void (*vcpu_free)(struct kvm_vcpu *vcpu);
+	int (*vcpu_reset)(struct kvm_vcpu *vcpu);
+
+	void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
+	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
+	void (*vcpu_put)(struct kvm_vcpu *vcpu);
+
+	int (*set_guest_debug)(struct kvm_vcpu *vcpu,
+			       struct kvm_debug_guest *dbg);
+	void (*guest_debug_pre)(struct kvm_vcpu *vcpu);
+	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
+	int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
+	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
+	void (*get_segment)(struct kvm_vcpu *vcpu,
+			    struct kvm_segment *var, int seg);
+	int (*get_cpl)(struct kvm_vcpu *vcpu);
+	void (*set_segment)(struct kvm_vcpu *vcpu,
+			    struct kvm_segment *var, int seg);
+	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
+	void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
+	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
+	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
+	void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
+	void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
+	void (*get_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
+	void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
+	void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
+	void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
+	unsigned long (*get_dr)(struct kvm_vcpu *vcpu, int dr);
+	void (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value,
+		       int *exception);
+	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
+	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
+	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+
+	void (*tlb_flush)(struct kvm_vcpu *vcpu);
+
+	void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
+	int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu);
+	void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
+	void (*patch_hypercall)(struct kvm_vcpu *vcpu,
+				unsigned char *hypercall_addr);
+	int (*get_irq)(struct kvm_vcpu *vcpu);
+	void (*set_irq)(struct kvm_vcpu *vcpu, int vec);
+	void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr,
+				bool has_error_code, u32 error_code);
+	bool (*exception_injected)(struct kvm_vcpu *vcpu);
+	void (*inject_pending_irq)(struct kvm_vcpu *vcpu);
+	void (*inject_pending_vectors)(struct kvm_vcpu *vcpu,
+				       struct kvm_run *run);
+
+	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
+	int (*get_tdp_level)(void);
+};
+
+extern struct kvm_x86_ops *kvm_x86_ops;
+
+int kvm_mmu_module_init(void);
+void kvm_mmu_module_exit(void);
+
+void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
+int kvm_mmu_create(struct kvm_vcpu *vcpu);
+int kvm_mmu_setup(struct kvm_vcpu *vcpu);
+void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
+void kvm_mmu_set_base_ptes(u64 base_pte);
+void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
+		u64 dirty_mask, u64 nx_mask, u64 x_mask);
+
+int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
+void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
+void kvm_mmu_zap_all(struct kvm *kvm);
+unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
+void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
+
+int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
+
+int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
+			  const void *val, int bytes);
+int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
+		  gpa_t addr, unsigned long *ret);
+
+extern bool tdp_enabled;
+
+enum emulation_result {
+	EMULATE_DONE,       /* no further processing */
+	EMULATE_DO_MMIO,      /* kvm_run filled with mmio request */
+	EMULATE_FAIL,         /* can't emulate this instruction */
+};
+
+#define EMULTYPE_NO_DECODE	    (1 << 0)
+#define EMULTYPE_TRAP_UD	    (1 << 1)
+int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run,
+			unsigned long cr2, u16 error_code, int emulation_type);
+void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
+void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
+void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
+void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
+		   unsigned long *rflags);
+
+unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr);
+void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value,
+		     unsigned long *rflags);
+void kvm_enable_efer_bits(u64);
+int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
+int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
+
+struct x86_emulate_ctxt;
+
+int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+		     int size, unsigned port);
+int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+			   int size, unsigned long count, int down,
+			    gva_t address, int rep, unsigned port);
+void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
+int kvm_emulate_halt(struct kvm_vcpu *vcpu);
+int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address);
+int emulate_clts(struct kvm_vcpu *vcpu);
+int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr,
+		    unsigned long *dest);
+int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
+		    unsigned long value);
+
+void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
+int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
+				int type_bits, int seg);
+
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);
+
+void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
+void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
+void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
+void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
+unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
+void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
+void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
+
+int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
+int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);
+
+void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
+void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
+			   u32 error_code);
+
+void kvm_pic_set_irq(void *opaque, int irq, int level);
+
+void kvm_inject_nmi(struct kvm_vcpu *vcpu);
+
+void fx_init(struct kvm_vcpu *vcpu);
+
+int emulator_read_std(unsigned long addr,
+		      void *val,
+		      unsigned int bytes,
+		      struct kvm_vcpu *vcpu);
+int emulator_write_emulated(unsigned long addr,
+			    const void *val,
+			    unsigned int bytes,
+			    struct kvm_vcpu *vcpu);
+
+unsigned long segment_base(u16 selector);
+
+void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
+void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
+		       const u8 *new, int bytes);
+int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
+void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
+int kvm_mmu_load(struct kvm_vcpu *vcpu);
+void kvm_mmu_unload(struct kvm_vcpu *vcpu);
+void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
+
+int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
+
+int kvm_fix_hypercall(struct kvm_vcpu *vcpu);
+
+int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code);
+void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
+
+void kvm_enable_tdp(void);
+void kvm_disable_tdp(void);
+
+int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
+int complete_pio(struct kvm_vcpu *vcpu);
+
+static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
+{
+	struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
+
+	return (struct kvm_mmu_page *)page_private(page);
+}
+
+static inline u16 kvm_read_fs(void)
+{
+	u16 seg;
+	asm("mov %%fs, %0" : "=g"(seg));
+	return seg;
+}
+
+static inline u16 kvm_read_gs(void)
+{
+	u16 seg;
+	asm("mov %%gs, %0" : "=g"(seg));
+	return seg;
+}
+
+static inline u16 kvm_read_ldt(void)
+{
+	u16 ldt;
+	asm("sldt %0" : "=g"(ldt));
+	return ldt;
+}
+
+static inline void kvm_load_fs(u16 sel)
+{
+	asm("mov %0, %%fs" : : "rm"(sel));
+}
+
+static inline void kvm_load_gs(u16 sel)
+{
+	asm("mov %0, %%gs" : : "rm"(sel));
+}
+
+static inline void kvm_load_ldt(u16 sel)
+{
+	asm("lldt %0" : : "rm"(sel));
+}
+
+static inline void kvm_get_idt(struct descriptor_table *table)
+{
+	asm("sidt %0" : "=m"(*table));
+}
+
+static inline void kvm_get_gdt(struct descriptor_table *table)
+{
+	asm("sgdt %0" : "=m"(*table));
+}
+
+static inline unsigned long kvm_read_tr_base(void)
+{
+	u16 tr;
+	asm("str %0" : "=g"(tr));
+	return segment_base(tr);
+}
+
+#ifdef CONFIG_X86_64
+static inline unsigned long read_msr(unsigned long msr)
+{
+	u64 value;
+
+	rdmsrl(msr, value);
+	return value;
+}
+#endif
+
+static inline void kvm_fx_save(struct i387_fxsave_struct *image)
+{
+	asm("fxsave (%0)":: "r" (image));
+}
+
+static inline void kvm_fx_restore(struct i387_fxsave_struct *image)
+{
+	asm("fxrstor (%0)":: "r" (image));
+}
+
+static inline void kvm_fx_finit(void)
+{
+	asm("finit");
+}
+
+static inline u32 get_rdx_init_val(void)
+{
+	return 0x600; /* P6 family */
+}
+
+static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
+{
+	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
+}
+
+#define ASM_VMX_VMCLEAR_RAX       ".byte 0x66, 0x0f, 0xc7, 0x30"
+#define ASM_VMX_VMLAUNCH          ".byte 0x0f, 0x01, 0xc2"
+#define ASM_VMX_VMRESUME          ".byte 0x0f, 0x01, 0xc3"
+#define ASM_VMX_VMPTRLD_RAX       ".byte 0x0f, 0xc7, 0x30"
+#define ASM_VMX_VMREAD_RDX_RAX    ".byte 0x0f, 0x78, 0xd0"
+#define ASM_VMX_VMWRITE_RAX_RDX   ".byte 0x0f, 0x79, 0xd0"
+#define ASM_VMX_VMWRITE_RSP_RDX   ".byte 0x0f, 0x79, 0xd4"
+#define ASM_VMX_VMXOFF            ".byte 0x0f, 0x01, 0xc4"
+#define ASM_VMX_VMXON_RAX         ".byte 0xf3, 0x0f, 0xc7, 0x30"
+#define ASM_VMX_INVEPT		  ".byte 0x66, 0x0f, 0x38, 0x80, 0x08"
+#define ASM_VMX_INVVPID		  ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
+
+#define MSR_IA32_TIME_STAMP_COUNTER		0x010
+
+#define TSS_IOPB_BASE_OFFSET 0x66
+#define TSS_BASE_SIZE 0x68
+#define TSS_IOPB_SIZE (65536 / 8)
+#define TSS_REDIRECTION_SIZE (256 / 8)
+#define RMODE_TSS_SIZE							\
+	(TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
+
+enum {
+	TASK_SWITCH_CALL = 0,
+	TASK_SWITCH_IRET = 1,
+	TASK_SWITCH_JMP = 2,
+	TASK_SWITCH_GATE = 3,
+};
+
+/*
+ * Hardware virtualization extension instructions may fault if a
+ * reboot turns off virtualization while processes are running.
+ * Trap the fault and ignore the instruction if that happens.
+ */
+asmlinkage void kvm_handle_fault_on_reboot(void);
+
+#define __kvm_handle_fault_on_reboot(insn) \
+	"666: " insn "\n\t" \
+	".pushsection .fixup, \"ax\" \n" \
+	"667: \n\t" \
+	__ASM_SIZE(push) " $666b \n\t"	      \
+	"jmp kvm_handle_fault_on_reboot \n\t" \
+	".popsection \n\t" \
+	".pushsection __ex_table, \"a\" \n\t" \
+	_ASM_PTR " 666b, 667b \n\t" \
+	".popsection"
+
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
+int kvm_age_hva(struct kvm *kvm, unsigned long hva);
+
+#endif /* ASM_X86__KVM_HOST_H */
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
new file mode 100644
index 000000000000..30054fded4fb
--- /dev/null
+++ b/arch/x86/include/asm/kvm_para.h
@@ -0,0 +1,147 @@
+#ifndef ASM_X86__KVM_PARA_H
+#define ASM_X86__KVM_PARA_H
+
+/* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx.  It
+ * should be used to determine that a VM is running under KVM.
+ */
+#define KVM_CPUID_SIGNATURE	0x40000000
+
+/* This CPUID returns a feature bitmap in eax.  Before enabling a particular
+ * paravirtualization, the appropriate feature bit should be checked.
+ */
+#define KVM_CPUID_FEATURES	0x40000001
+#define KVM_FEATURE_CLOCKSOURCE		0
+#define KVM_FEATURE_NOP_IO_DELAY	1
+#define KVM_FEATURE_MMU_OP		2
+
+#define MSR_KVM_WALL_CLOCK  0x11
+#define MSR_KVM_SYSTEM_TIME 0x12
+
+#define KVM_MAX_MMU_OP_BATCH           32
+
+/* Operations for KVM_HC_MMU_OP */
+#define KVM_MMU_OP_WRITE_PTE            1
+#define KVM_MMU_OP_FLUSH_TLB	        2
+#define KVM_MMU_OP_RELEASE_PT	        3
+
+/* Payload for KVM_HC_MMU_OP */
+struct kvm_mmu_op_header {
+	__u32 op;
+	__u32 pad;
+};
+
+struct kvm_mmu_op_write_pte {
+	struct kvm_mmu_op_header header;
+	__u64 pte_phys;
+	__u64 pte_val;
+};
+
+struct kvm_mmu_op_flush_tlb {
+	struct kvm_mmu_op_header header;
+};
+
+struct kvm_mmu_op_release_pt {
+	struct kvm_mmu_op_header header;
+	__u64 pt_phys;
+};
+
+#ifdef __KERNEL__
+#include <asm/processor.h>
+
+extern void kvmclock_init(void);
+
+
+/* This instruction is vmcall.  On non-VT architectures, it will generate a
+ * trap that we will then rewrite to the appropriate instruction.
+ */
+#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
+
+/* For KVM hypercalls, a three-byte sequence of either the vmrun or the vmmrun
+ * instruction.  The hypervisor may replace it with something else but only the
+ * instructions are guaranteed to be supported.
+ *
+ * Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively.
+ * The hypercall number should be placed in rax and the return value will be
+ * placed in rax.  No other registers will be clobbered unless explicited
+ * noted by the particular hypercall.
+ */
+
+static inline long kvm_hypercall0(unsigned int nr)
+{
+	long ret;
+	asm volatile(KVM_HYPERCALL
+		     : "=a"(ret)
+		     : "a"(nr)
+		     : "memory");
+	return ret;
+}
+
+static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
+{
+	long ret;
+	asm volatile(KVM_HYPERCALL
+		     : "=a"(ret)
+		     : "a"(nr), "b"(p1)
+		     : "memory");
+	return ret;
+}
+
+static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
+				  unsigned long p2)
+{
+	long ret;
+	asm volatile(KVM_HYPERCALL
+		     : "=a"(ret)
+		     : "a"(nr), "b"(p1), "c"(p2)
+		     : "memory");
+	return ret;
+}
+
+static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
+				  unsigned long p2, unsigned long p3)
+{
+	long ret;
+	asm volatile(KVM_HYPERCALL
+		     : "=a"(ret)
+		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3)
+		     : "memory");
+	return ret;
+}
+
+static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
+				  unsigned long p2, unsigned long p3,
+				  unsigned long p4)
+{
+	long ret;
+	asm volatile(KVM_HYPERCALL
+		     : "=a"(ret)
+		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4)
+		     : "memory");
+	return ret;
+}
+
+static inline int kvm_para_available(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	char signature[13];
+
+	cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
+	memcpy(signature + 0, &ebx, 4);
+	memcpy(signature + 4, &ecx, 4);
+	memcpy(signature + 8, &edx, 4);
+	signature[12] = 0;
+
+	if (strcmp(signature, "KVMKVMKVM") == 0)
+		return 1;
+
+	return 0;
+}
+
+static inline unsigned int kvm_arch_para_features(void)
+{
+	return cpuid_eax(KVM_CPUID_FEATURES);
+}
+
+#endif
+
+#endif /* ASM_X86__KVM_PARA_H */
diff --git a/arch/x86/include/asm/kvm_x86_emulate.h b/arch/x86/include/asm/kvm_x86_emulate.h
new file mode 100644
index 000000000000..e2d9b030c1ac
--- /dev/null
+++ b/arch/x86/include/asm/kvm_x86_emulate.h
@@ -0,0 +1,184 @@
+/******************************************************************************
+ * x86_emulate.h
+ *
+ * Generic x86 (32-bit and 64-bit) instruction decoder and emulator.
+ *
+ * Copyright (c) 2005 Keir Fraser
+ *
+ * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4
+ */
+
+#ifndef ASM_X86__KVM_X86_EMULATE_H
+#define ASM_X86__KVM_X86_EMULATE_H
+
+struct x86_emulate_ctxt;
+
+/*
+ * x86_emulate_ops:
+ *
+ * These operations represent the instruction emulator's interface to memory.
+ * There are two categories of operation: those that act on ordinary memory
+ * regions (*_std), and those that act on memory regions known to require
+ * special treatment or emulation (*_emulated).
+ *
+ * The emulator assumes that an instruction accesses only one 'emulated memory'
+ * location, that this location is the given linear faulting address (cr2), and
+ * that this is one of the instruction's data operands. Instruction fetches and
+ * stack operations are assumed never to access emulated memory. The emulator
+ * automatically deduces which operand of a string-move operation is accessing
+ * emulated memory, and assumes that the other operand accesses normal memory.
+ *
+ * NOTES:
+ *  1. The emulator isn't very smart about emulated vs. standard memory.
+ *     'Emulated memory' access addresses should be checked for sanity.
+ *     'Normal memory' accesses may fault, and the caller must arrange to
+ *     detect and handle reentrancy into the emulator via recursive faults.
+ *     Accesses may be unaligned and may cross page boundaries.
+ *  2. If the access fails (cannot emulate, or a standard access faults) then
+ *     it is up to the memop to propagate the fault to the guest VM via
+ *     some out-of-band mechanism, unknown to the emulator. The memop signals
+ *     failure by returning X86EMUL_PROPAGATE_FAULT to the emulator, which will
+ *     then immediately bail.
+ *  3. Valid access sizes are 1, 2, 4 and 8 bytes. On x86/32 systems only
+ *     cmpxchg8b_emulated need support 8-byte accesses.
+ *  4. The emulator cannot handle 64-bit mode emulation on an x86/32 system.
+ */
+/* Access completed successfully: continue emulation as normal. */
+#define X86EMUL_CONTINUE        0
+/* Access is unhandleable: bail from emulation and return error to caller. */
+#define X86EMUL_UNHANDLEABLE    1
+/* Terminate emulation but return success to the caller. */
+#define X86EMUL_PROPAGATE_FAULT 2 /* propagate a generated fault to guest */
+#define X86EMUL_RETRY_INSTR     2 /* retry the instruction for some reason */
+#define X86EMUL_CMPXCHG_FAILED  2 /* cmpxchg did not see expected value */
+struct x86_emulate_ops {
+	/*
+	 * read_std: Read bytes of standard (non-emulated/special) memory.
+	 *           Used for instruction fetch, stack operations, and others.
+	 *  @addr:  [IN ] Linear address from which to read.
+	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
+	 *  @bytes: [IN ] Number of bytes to read from memory.
+	 */
+	int (*read_std)(unsigned long addr, void *val,
+			unsigned int bytes, struct kvm_vcpu *vcpu);
+
+	/*
+	 * read_emulated: Read bytes from emulated/special memory area.
+	 *  @addr:  [IN ] Linear address from which to read.
+	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
+	 *  @bytes: [IN ] Number of bytes to read from memory.
+	 */
+	int (*read_emulated)(unsigned long addr,
+			     void *val,
+			     unsigned int bytes,
+			     struct kvm_vcpu *vcpu);
+
+	/*
+	 * write_emulated: Read bytes from emulated/special memory area.
+	 *  @addr:  [IN ] Linear address to which to write.
+	 *  @val:   [IN ] Value to write to memory (low-order bytes used as
+	 *                required).
+	 *  @bytes: [IN ] Number of bytes to write to memory.
+	 */
+	int (*write_emulated)(unsigned long addr,
+			      const void *val,
+			      unsigned int bytes,
+			      struct kvm_vcpu *vcpu);
+
+	/*
+	 * cmpxchg_emulated: Emulate an atomic (LOCKed) CMPXCHG operation on an
+	 *                   emulated/special memory area.
+	 *  @addr:  [IN ] Linear address to access.
+	 *  @old:   [IN ] Value expected to be current at @addr.
+	 *  @new:   [IN ] Value to write to @addr.
+	 *  @bytes: [IN ] Number of bytes to access using CMPXCHG.
+	 */
+	int (*cmpxchg_emulated)(unsigned long addr,
+				const void *old,
+				const void *new,
+				unsigned int bytes,
+				struct kvm_vcpu *vcpu);
+
+};
+
+/* Type, address-of, and value of an instruction's operand. */
+struct operand {
+	enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type;
+	unsigned int bytes;
+	unsigned long val, orig_val, *ptr;
+};
+
+struct fetch_cache {
+	u8 data[15];
+	unsigned long start;
+	unsigned long end;
+};
+
+struct decode_cache {
+	u8 twobyte;
+	u8 b;
+	u8 lock_prefix;
+	u8 rep_prefix;
+	u8 op_bytes;
+	u8 ad_bytes;
+	u8 rex_prefix;
+	struct operand src;
+	struct operand dst;
+	bool has_seg_override;
+	u8 seg_override;
+	unsigned int d;
+	unsigned long regs[NR_VCPU_REGS];
+	unsigned long eip;
+	/* modrm */
+	u8 modrm;
+	u8 modrm_mod;
+	u8 modrm_reg;
+	u8 modrm_rm;
+	u8 use_modrm_ea;
+	bool rip_relative;
+	unsigned long modrm_ea;
+	void *modrm_ptr;
+	unsigned long modrm_val;
+	struct fetch_cache fetch;
+};
+
+struct x86_emulate_ctxt {
+	/* Register state before/after emulation. */
+	struct kvm_vcpu *vcpu;
+
+	/* Linear faulting address (if emulating a page-faulting instruction) */
+	unsigned long eflags;
+
+	/* Emulated execution mode, represented by an X86EMUL_MODE value. */
+	int mode;
+
+	u32 cs_base;
+
+	/* decode cache */
+
+	struct decode_cache decode;
+};
+
+/* Repeat String Operation Prefix */
+#define REPE_PREFIX  1
+#define REPNE_PREFIX    2
+
+/* Execution mode, passed to the emulator. */
+#define X86EMUL_MODE_REAL     0	/* Real mode.             */
+#define X86EMUL_MODE_PROT16   2	/* 16-bit protected mode. */
+#define X86EMUL_MODE_PROT32   4	/* 32-bit protected mode. */
+#define X86EMUL_MODE_PROT64   8	/* 64-bit (long) mode.    */
+
+/* Host execution mode. */
+#if defined(__i386__)
+#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT32
+#elif defined(CONFIG_X86_64)
+#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64
+#endif
+
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt,
+		    struct x86_emulate_ops *ops);
+int x86_emulate_insn(struct x86_emulate_ctxt *ctxt,
+		     struct x86_emulate_ops *ops);
+
+#endif /* ASM_X86__KVM_X86_EMULATE_H */
diff --git a/arch/x86/include/asm/ldt.h b/arch/x86/include/asm/ldt.h
new file mode 100644
index 000000000000..a5228504d867
--- /dev/null
+++ b/arch/x86/include/asm/ldt.h
@@ -0,0 +1,40 @@
+/*
+ * ldt.h
+ *
+ * Definitions of structures used with the modify_ldt system call.
+ */
+#ifndef ASM_X86__LDT_H
+#define ASM_X86__LDT_H
+
+/* Maximum number of LDT entries supported. */
+#define LDT_ENTRIES	8192
+/* The size of each LDT entry. */
+#define LDT_ENTRY_SIZE	8
+
+#ifndef __ASSEMBLY__
+/*
+ * Note on 64bit base and limit is ignored and you cannot set DS/ES/CS
+ * not to the default values if you still want to do syscalls. This
+ * call is more for 32bit mode therefore.
+ */
+struct user_desc {
+	unsigned int  entry_number;
+	unsigned int  base_addr;
+	unsigned int  limit;
+	unsigned int  seg_32bit:1;
+	unsigned int  contents:2;
+	unsigned int  read_exec_only:1;
+	unsigned int  limit_in_pages:1;
+	unsigned int  seg_not_present:1;
+	unsigned int  useable:1;
+#ifdef __x86_64__
+	unsigned int  lm:1;
+#endif
+};
+
+#define MODIFY_LDT_CONTENTS_DATA	0
+#define MODIFY_LDT_CONTENTS_STACK	1
+#define MODIFY_LDT_CONTENTS_CODE	2
+
+#endif /* !__ASSEMBLY__ */
+#endif /* ASM_X86__LDT_H */
diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h
new file mode 100644
index 000000000000..7505e947ed27
--- /dev/null
+++ b/arch/x86/include/asm/lguest.h
@@ -0,0 +1,94 @@
+#ifndef ASM_X86__LGUEST_H
+#define ASM_X86__LGUEST_H
+
+#define GDT_ENTRY_LGUEST_CS	10
+#define GDT_ENTRY_LGUEST_DS	11
+#define LGUEST_CS		(GDT_ENTRY_LGUEST_CS * 8)
+#define LGUEST_DS		(GDT_ENTRY_LGUEST_DS * 8)
+
+#ifndef __ASSEMBLY__
+#include <asm/desc.h>
+
+#define GUEST_PL 1
+
+/* Every guest maps the core switcher code. */
+#define SHARED_SWITCHER_PAGES \
+	DIV_ROUND_UP(end_switcher_text - start_switcher_text, PAGE_SIZE)
+/* Pages for switcher itself, then two pages per cpu */
+#define TOTAL_SWITCHER_PAGES (SHARED_SWITCHER_PAGES + 2 * NR_CPUS)
+
+/* We map at -4M for ease of mapping into the guest (one PTE page). */
+#define SWITCHER_ADDR 0xFFC00000
+
+/* Found in switcher.S */
+extern unsigned long default_idt_entries[];
+
+/* Declarations for definitions in lguest_guest.S */
+extern char lguest_noirq_start[], lguest_noirq_end[];
+extern const char lgstart_cli[], lgend_cli[];
+extern const char lgstart_sti[], lgend_sti[];
+extern const char lgstart_popf[], lgend_popf[];
+extern const char lgstart_pushf[], lgend_pushf[];
+extern const char lgstart_iret[], lgend_iret[];
+
+extern void lguest_iret(void);
+extern void lguest_init(void);
+
+struct lguest_regs {
+	/* Manually saved part. */
+	unsigned long eax, ebx, ecx, edx;
+	unsigned long esi, edi, ebp;
+	unsigned long gs;
+	unsigned long fs, ds, es;
+	unsigned long trapnum, errcode;
+	/* Trap pushed part */
+	unsigned long eip;
+	unsigned long cs;
+	unsigned long eflags;
+	unsigned long esp;
+	unsigned long ss;
+};
+
+/* This is a guest-specific page (mapped ro) into the guest. */
+struct lguest_ro_state {
+	/* Host information we need to restore when we switch back. */
+	u32 host_cr3;
+	struct desc_ptr host_idt_desc;
+	struct desc_ptr host_gdt_desc;
+	u32 host_sp;
+
+	/* Fields which are used when guest is running. */
+	struct desc_ptr guest_idt_desc;
+	struct desc_ptr guest_gdt_desc;
+	struct x86_hw_tss guest_tss;
+	struct desc_struct guest_idt[IDT_ENTRIES];
+	struct desc_struct guest_gdt[GDT_ENTRIES];
+};
+
+struct lg_cpu_arch {
+	/* The GDT entries copied into lguest_ro_state when running. */
+	struct desc_struct gdt[GDT_ENTRIES];
+
+	/* The IDT entries: some copied into lguest_ro_state when running. */
+	struct desc_struct idt[IDT_ENTRIES];
+
+	/* The address of the last guest-visible pagefault (ie. cr2). */
+	unsigned long last_pagefault;
+};
+
+static inline void lguest_set_ts(void)
+{
+	u32 cr0;
+
+	cr0 = read_cr0();
+	if (!(cr0 & 8))
+		write_cr0(cr0 | 8);
+}
+
+/* Full 4G segment descriptors, suitable for CS and DS. */
+#define FULL_EXEC_SEGMENT ((struct desc_struct){ { {0x0000ffff, 0x00cf9b00} } })
+#define FULL_SEGMENT ((struct desc_struct){ { {0x0000ffff, 0x00cf9300} } })
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* ASM_X86__LGUEST_H */
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
new file mode 100644
index 000000000000..8f034ba4b53e
--- /dev/null
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -0,0 +1,71 @@
+/* Architecture specific portion of the lguest hypercalls */
+#ifndef ASM_X86__LGUEST_HCALL_H
+#define ASM_X86__LGUEST_HCALL_H
+
+#define LHCALL_FLUSH_ASYNC	0
+#define LHCALL_LGUEST_INIT	1
+#define LHCALL_SHUTDOWN		2
+#define LHCALL_LOAD_GDT		3
+#define LHCALL_NEW_PGTABLE	4
+#define LHCALL_FLUSH_TLB	5
+#define LHCALL_LOAD_IDT_ENTRY	6
+#define LHCALL_SET_STACK	7
+#define LHCALL_TS		8
+#define LHCALL_SET_CLOCKEVENT	9
+#define LHCALL_HALT		10
+#define LHCALL_SET_PTE		14
+#define LHCALL_SET_PMD		15
+#define LHCALL_LOAD_TLS		16
+#define LHCALL_NOTIFY		17
+
+#define LGUEST_TRAP_ENTRY 0x1F
+
+/* Argument number 3 to LHCALL_LGUEST_SHUTDOWN */
+#define LGUEST_SHUTDOWN_POWEROFF	1
+#define LGUEST_SHUTDOWN_RESTART		2
+
+#ifndef __ASSEMBLY__
+#include <asm/hw_irq.h>
+
+/*G:031 But first, how does our Guest contact the Host to ask for privileged
+ * operations?  There are two ways: the direct way is to make a "hypercall",
+ * to make requests of the Host Itself.
+ *
+ * Our hypercall mechanism uses the highest unused trap code (traps 32 and
+ * above are used by real hardware interrupts).  Fifteen hypercalls are
+ * available: the hypercall number is put in the %eax register, and the
+ * arguments (when required) are placed in %edx, %ebx and %ecx.  If a return
+ * value makes sense, it's returned in %eax.
+ *
+ * Grossly invalid calls result in Sudden Death at the hands of the vengeful
+ * Host, rather than returning failure.  This reflects Winston Churchill's
+ * definition of a gentleman: "someone who is only rude intentionally". */
+static inline unsigned long
+hcall(unsigned long call,
+      unsigned long arg1, unsigned long arg2, unsigned long arg3)
+{
+	/* "int" is the Intel instruction to trigger a trap. */
+	asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY)
+		     /* The call in %eax (aka "a") might be overwritten */
+		     : "=a"(call)
+		       /* The arguments are in %eax, %edx, %ebx & %ecx */
+		     : "a"(call), "d"(arg1), "b"(arg2), "c"(arg3)
+		       /* "memory" means this might write somewhere in memory.
+			* This isn't true for all calls, but it's safe to tell
+			* gcc that it might happen so it doesn't get clever. */
+		     : "memory");
+	return call;
+}
+/*:*/
+
+/* Can't use our min() macro here: needs to be a constant */
+#define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32)
+
+#define LHCALL_RING_SIZE 64
+struct hcall_args {
+	/* These map directly onto eax, ebx, ecx, edx in struct lguest_regs */
+	unsigned long arg0, arg2, arg3, arg1;
+};
+
+#endif /* !__ASSEMBLY__ */
+#endif /* ASM_X86__LGUEST_HCALL_H */
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
new file mode 100644
index 000000000000..42d8b62ee8ab
--- /dev/null
+++ b/arch/x86/include/asm/linkage.h
@@ -0,0 +1,61 @@
+#ifndef ASM_X86__LINKAGE_H
+#define ASM_X86__LINKAGE_H
+
+#undef notrace
+#define notrace __attribute__((no_instrument_function))
+
+#ifdef CONFIG_X86_64
+#define __ALIGN .p2align 4,,15
+#define __ALIGN_STR ".p2align 4,,15"
+#endif
+
+#ifdef CONFIG_X86_32
+#define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
+/*
+ * For 32-bit UML - mark functions implemented in assembly that use
+ * regparm input parameters:
+ */
+#define asmregparm __attribute__((regparm(3)))
+
+/*
+ * Make sure the compiler doesn't do anything stupid with the
+ * arguments on the stack - they are owned by the *caller*, not
+ * the callee. This just fools gcc into not spilling into them,
+ * and keeps it from doing tailcall recursion and/or using the
+ * stack slots for temporaries, since they are live and "used"
+ * all the way to the end of the function.
+ *
+ * NOTE! On x86-64, all the arguments are in registers, so this
+ * only matters on a 32-bit kernel.
+ */
+#define asmlinkage_protect(n, ret, args...) \
+	__asmlinkage_protect##n(ret, ##args)
+#define __asmlinkage_protect_n(ret, args...) \
+	__asm__ __volatile__ ("" : "=r" (ret) : "0" (ret), ##args)
+#define __asmlinkage_protect0(ret) \
+	__asmlinkage_protect_n(ret)
+#define __asmlinkage_protect1(ret, arg1) \
+	__asmlinkage_protect_n(ret, "g" (arg1))
+#define __asmlinkage_protect2(ret, arg1, arg2) \
+	__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2))
+#define __asmlinkage_protect3(ret, arg1, arg2, arg3) \
+	__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3))
+#define __asmlinkage_protect4(ret, arg1, arg2, arg3, arg4) \
+	__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \
+			      "g" (arg4))
+#define __asmlinkage_protect5(ret, arg1, arg2, arg3, arg4, arg5) \
+	__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \
+			      "g" (arg4), "g" (arg5))
+#define __asmlinkage_protect6(ret, arg1, arg2, arg3, arg4, arg5, arg6) \
+	__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \
+			      "g" (arg4), "g" (arg5), "g" (arg6))
+
+#endif
+
+#ifdef CONFIG_X86_ALIGNMENT_16
+#define __ALIGN .align 16,0x90
+#define __ALIGN_STR ".align 16,0x90"
+#endif
+
+#endif /* ASM_X86__LINKAGE_H */
+
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
new file mode 100644
index 000000000000..ae91994fd6c9
--- /dev/null
+++ b/arch/x86/include/asm/local.h
@@ -0,0 +1,235 @@
+#ifndef ASM_X86__LOCAL_H
+#define ASM_X86__LOCAL_H
+
+#include <linux/percpu.h>
+
+#include <asm/system.h>
+#include <asm/atomic.h>
+#include <asm/asm.h>
+
+typedef struct {
+	atomic_long_t a;
+} local_t;
+
+#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
+
+#define local_read(l)	atomic_long_read(&(l)->a)
+#define local_set(l, i)	atomic_long_set(&(l)->a, (i))
+
+static inline void local_inc(local_t *l)
+{
+	asm volatile(_ASM_INC "%0"
+		     : "+m" (l->a.counter));
+}
+
+static inline void local_dec(local_t *l)
+{
+	asm volatile(_ASM_DEC "%0"
+		     : "+m" (l->a.counter));
+}
+
+static inline void local_add(long i, local_t *l)
+{
+	asm volatile(_ASM_ADD "%1,%0"
+		     : "+m" (l->a.counter)
+		     : "ir" (i));
+}
+
+static inline void local_sub(long i, local_t *l)
+{
+	asm volatile(_ASM_SUB "%1,%0"
+		     : "+m" (l->a.counter)
+		     : "ir" (i));
+}
+
+/**
+ * local_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @l: pointer to type local_t
+ *
+ * Atomically subtracts @i from @l and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int local_sub_and_test(long i, local_t *l)
+{
+	unsigned char c;
+
+	asm volatile(_ASM_SUB "%2,%0; sete %1"
+		     : "+m" (l->a.counter), "=qm" (c)
+		     : "ir" (i) : "memory");
+	return c;
+}
+
+/**
+ * local_dec_and_test - decrement and test
+ * @l: pointer to type local_t
+ *
+ * Atomically decrements @l by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+static inline int local_dec_and_test(local_t *l)
+{
+	unsigned char c;
+
+	asm volatile(_ASM_DEC "%0; sete %1"
+		     : "+m" (l->a.counter), "=qm" (c)
+		     : : "memory");
+	return c != 0;
+}
+
+/**
+ * local_inc_and_test - increment and test
+ * @l: pointer to type local_t
+ *
+ * Atomically increments @l by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+static inline int local_inc_and_test(local_t *l)
+{
+	unsigned char c;
+
+	asm volatile(_ASM_INC "%0; sete %1"
+		     : "+m" (l->a.counter), "=qm" (c)
+		     : : "memory");
+	return c != 0;
+}
+
+/**
+ * local_add_negative - add and test if negative
+ * @i: integer value to add
+ * @l: pointer to type local_t
+ *
+ * Atomically adds @i to @l and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+static inline int local_add_negative(long i, local_t *l)
+{
+	unsigned char c;
+
+	asm volatile(_ASM_ADD "%2,%0; sets %1"
+		     : "+m" (l->a.counter), "=qm" (c)
+		     : "ir" (i) : "memory");
+	return c;
+}
+
+/**
+ * local_add_return - add and return
+ * @i: integer value to add
+ * @l: pointer to type local_t
+ *
+ * Atomically adds @i to @l and returns @i + @l
+ */
+static inline long local_add_return(long i, local_t *l)
+{
+	long __i;
+#ifdef CONFIG_M386
+	unsigned long flags;
+	if (unlikely(boot_cpu_data.x86 <= 3))
+		goto no_xadd;
+#endif
+	/* Modern 486+ processor */
+	__i = i;
+	asm volatile(_ASM_XADD "%0, %1;"
+		     : "+r" (i), "+m" (l->a.counter)
+		     : : "memory");
+	return i + __i;
+
+#ifdef CONFIG_M386
+no_xadd: /* Legacy 386 processor */
+	local_irq_save(flags);
+	__i = local_read(l);
+	local_set(l, i + __i);
+	local_irq_restore(flags);
+	return i + __i;
+#endif
+}
+
+static inline long local_sub_return(long i, local_t *l)
+{
+	return local_add_return(-i, l);
+}
+
+#define local_inc_return(l)  (local_add_return(1, l))
+#define local_dec_return(l)  (local_sub_return(1, l))
+
+#define local_cmpxchg(l, o, n) \
+	(cmpxchg_local(&((l)->a.counter), (o), (n)))
+/* Always has a lock prefix */
+#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
+
+/**
+ * local_add_unless - add unless the number is a given value
+ * @l: pointer of type local_t
+ * @a: the amount to add to l...
+ * @u: ...unless l is equal to u.
+ *
+ * Atomically adds @a to @l, so long as it was not @u.
+ * Returns non-zero if @l was not @u, and zero otherwise.
+ */
+#define local_add_unless(l, a, u)				\
+({								\
+	long c, old;						\
+	c = local_read((l));					\
+	for (;;) {						\
+		if (unlikely(c == (u)))				\
+			break;					\
+		old = local_cmpxchg((l), c, c + (a));		\
+		if (likely(old == c))				\
+			break;					\
+		c = old;					\
+	}							\
+	c != (u);						\
+})
+#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
+
+/* On x86_32, these are no better than the atomic variants.
+ * On x86-64 these are better than the atomic variants on SMP kernels
+ * because they dont use a lock prefix.
+ */
+#define __local_inc(l)		local_inc(l)
+#define __local_dec(l)		local_dec(l)
+#define __local_add(i, l)	local_add((i), (l))
+#define __local_sub(i, l)	local_sub((i), (l))
+
+/* Use these for per-cpu local_t variables: on some archs they are
+ * much more efficient than these naive implementations.  Note they take
+ * a variable, not an address.
+ *
+ * X86_64: This could be done better if we moved the per cpu data directly
+ * after GS.
+ */
+
+/* Need to disable preemption for the cpu local counters otherwise we could
+   still access a variable of a previous CPU in a non atomic way. */
+#define cpu_local_wrap_v(l)		\
+({					\
+	local_t res__;			\
+	preempt_disable(); 		\
+	res__ = (l);			\
+	preempt_enable();		\
+	res__;				\
+})
+#define cpu_local_wrap(l)		\
+({					\
+	preempt_disable();		\
+	(l);				\
+	preempt_enable();		\
+})					\
+
+#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var((l))))
+#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var((l)), (i)))
+#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var((l))))
+#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var((l))))
+#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var((l))))
+#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var((l))))
+
+#define __cpu_local_inc(l)	cpu_local_inc((l))
+#define __cpu_local_dec(l)	cpu_local_dec((l))
+#define __cpu_local_add(i, l)	cpu_local_add((i), (l))
+#define __cpu_local_sub(i, l)	cpu_local_sub((i), (l))
+
+#endif /* ASM_X86__LOCAL_H */
diff --git a/arch/x86/include/asm/mach-default/apm.h b/arch/x86/include/asm/mach-default/apm.h
new file mode 100644
index 000000000000..2aa61b54fbd5
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/apm.h
@@ -0,0 +1,73 @@
+/*
+ *  Machine specific APM BIOS functions for generic.
+ *  Split out from apm.c by Osamu Tomita <tomita@cinet.co.jp>
+ */
+
+#ifndef ASM_X86__MACH_DEFAULT__APM_H
+#define ASM_X86__MACH_DEFAULT__APM_H
+
+#ifdef APM_ZERO_SEGS
+#	define APM_DO_ZERO_SEGS \
+		"pushl %%ds\n\t" \
+		"pushl %%es\n\t" \
+		"xorl %%edx, %%edx\n\t" \
+		"mov %%dx, %%ds\n\t" \
+		"mov %%dx, %%es\n\t" \
+		"mov %%dx, %%fs\n\t" \
+		"mov %%dx, %%gs\n\t"
+#	define APM_DO_POP_SEGS \
+		"popl %%es\n\t" \
+		"popl %%ds\n\t"
+#else
+#	define APM_DO_ZERO_SEGS
+#	define APM_DO_POP_SEGS
+#endif
+
+static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
+					u32 *eax, u32 *ebx, u32 *ecx,
+					u32 *edx, u32 *esi)
+{
+	/*
+	 * N.B. We do NOT need a cld after the BIOS call
+	 * because we always save and restore the flags.
+	 */
+	__asm__ __volatile__(APM_DO_ZERO_SEGS
+		"pushl %%edi\n\t"
+		"pushl %%ebp\n\t"
+		"lcall *%%cs:apm_bios_entry\n\t"
+		"setc %%al\n\t"
+		"popl %%ebp\n\t"
+		"popl %%edi\n\t"
+		APM_DO_POP_SEGS
+		: "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx),
+		  "=S" (*esi)
+		: "a" (func), "b" (ebx_in), "c" (ecx_in)
+		: "memory", "cc");
+}
+
+static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
+						u32 ecx_in, u32 *eax)
+{
+	int	cx, dx, si;
+	u8	error;
+
+	/*
+	 * N.B. We do NOT need a cld after the BIOS call
+	 * because we always save and restore the flags.
+	 */
+	__asm__ __volatile__(APM_DO_ZERO_SEGS
+		"pushl %%edi\n\t"
+		"pushl %%ebp\n\t"
+		"lcall *%%cs:apm_bios_entry\n\t"
+		"setc %%bl\n\t"
+		"popl %%ebp\n\t"
+		"popl %%edi\n\t"
+		APM_DO_POP_SEGS
+		: "=a" (*eax), "=b" (error), "=c" (cx), "=d" (dx),
+		  "=S" (si)
+		: "a" (func), "b" (ebx_in), "c" (ecx_in)
+		: "memory", "cc");
+	return error;
+}
+
+#endif /* ASM_X86__MACH_DEFAULT__APM_H */
diff --git a/arch/x86/include/asm/mach-default/do_timer.h b/arch/x86/include/asm/mach-default/do_timer.h
new file mode 100644
index 000000000000..23ecda0b28a0
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/do_timer.h
@@ -0,0 +1,16 @@
+/* defines for inline arch setup functions */
+#include <linux/clockchips.h>
+
+#include <asm/i8259.h>
+#include <asm/i8253.h>
+
+/**
+ * do_timer_interrupt_hook - hook into timer tick
+ *
+ * Call the pit clock event handler. see asm/i8253.h
+ **/
+
+static inline void do_timer_interrupt_hook(void)
+{
+	global_clock_event->event_handler(global_clock_event);
+}
diff --git a/arch/x86/include/asm/mach-default/entry_arch.h b/arch/x86/include/asm/mach-default/entry_arch.h
new file mode 100644
index 000000000000..6b1add8e31dd
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/entry_arch.h
@@ -0,0 +1,36 @@
+/*
+ * This file is designed to contain the BUILD_INTERRUPT specifications for
+ * all of the extra named interrupt vectors used by the architecture.
+ * Usually this is the Inter Process Interrupts (IPIs)
+ */
+
+/*
+ * The following vectors are part of the Linux architecture, there
+ * is no hardware IRQ pin equivalent for them, they are triggered
+ * through the ICC by us (IPIs)
+ */
+#ifdef CONFIG_X86_SMP
+BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
+BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
+BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
+BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
+BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
+#endif
+
+/*
+ * every pentium local APIC has two 'local interrupts', with a
+ * soft-definable vector attached to both interrupts, one of
+ * which is a timer interrupt, the other one is error counter
+ * overflow. Linux uses the local APIC timer interrupt to get
+ * a much simpler SMP time architecture:
+ */
+#ifdef CONFIG_X86_LOCAL_APIC
+BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
+BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
+BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
+
+#ifdef CONFIG_X86_MCE_P4THERMAL
+BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
+#endif
+
+#endif
diff --git a/arch/x86/include/asm/mach-default/mach_apic.h b/arch/x86/include/asm/mach-default/mach_apic.h
new file mode 100644
index 000000000000..3c66f2cdaec1
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/mach_apic.h
@@ -0,0 +1,156 @@
+#ifndef ASM_X86__MACH_DEFAULT__MACH_APIC_H
+#define ASM_X86__MACH_DEFAULT__MACH_APIC_H
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+#include <mach_apicdef.h>
+#include <asm/smp.h>
+
+#define APIC_DFR_VALUE	(APIC_DFR_FLAT)
+
+static inline cpumask_t target_cpus(void)
+{ 
+#ifdef CONFIG_SMP
+	return cpu_online_map;
+#else
+	return cpumask_of_cpu(0);
+#endif
+} 
+
+#define NO_BALANCE_IRQ (0)
+#define esr_disable (0)
+
+#ifdef CONFIG_X86_64
+#include <asm/genapic.h>
+#define INT_DELIVERY_MODE (genapic->int_delivery_mode)
+#define INT_DEST_MODE (genapic->int_dest_mode)
+#define TARGET_CPUS	  (genapic->target_cpus())
+#define apic_id_registered (genapic->apic_id_registered)
+#define init_apic_ldr (genapic->init_apic_ldr)
+#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
+#define phys_pkg_id	(genapic->phys_pkg_id)
+#define vector_allocation_domain    (genapic->vector_allocation_domain)
+#define read_apic_id()  (GET_APIC_ID(apic_read(APIC_ID)))
+#define send_IPI_self (genapic->send_IPI_self)
+extern void setup_apic_routing(void);
+#else
+#define INT_DELIVERY_MODE dest_LowestPrio
+#define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
+#define TARGET_CPUS (target_cpus())
+/*
+ * Set up the logical destination ID.
+ *
+ * Intel recommends to set DFR, LDR and TPR before enabling
+ * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
+ * document number 292116).  So here it goes...
+ */
+static inline void init_apic_ldr(void)
+{
+	unsigned long val;
+
+	apic_write(APIC_DFR, APIC_DFR_VALUE);
+	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+	val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
+	apic_write(APIC_LDR, val);
+}
+
+static inline int apic_id_registered(void)
+{
+	return physid_isset(read_apic_id(), phys_cpu_present_map);
+}
+
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+	return cpus_addr(cpumask)[0];
+}
+
+static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
+{
+	return cpuid_apic >> index_msb;
+}
+
+static inline void setup_apic_routing(void)
+{
+#ifdef CONFIG_X86_IO_APIC
+	printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
+					"Flat", nr_ioapics);
+#endif
+}
+
+static inline int apicid_to_node(int logical_apicid)
+{
+#ifdef CONFIG_SMP
+	return apicid_2_node[hard_smp_processor_id()];
+#else
+	return 0;
+#endif
+}
+
+static inline cpumask_t vector_allocation_domain(int cpu)
+{
+        /* Careful. Some cpus do not strictly honor the set of cpus
+         * specified in the interrupt destination when using lowest
+         * priority interrupt delivery mode.
+         *
+         * In particular there was a hyperthreading cpu observed to
+         * deliver interrupts to the wrong hyperthread when only one
+         * hyperthread was specified in the interrupt desitination.
+         */
+        cpumask_t domain = { { [0] = APIC_ALL_CPUS, } };
+        return domain;
+}
+#endif
+
+static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+	return physid_isset(apicid, bitmap);
+}
+
+static inline unsigned long check_apicid_present(int bit)
+{
+	return physid_isset(bit, phys_cpu_present_map);
+}
+
+static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
+{
+	return phys_map;
+}
+
+static inline int multi_timer_check(int apic, int irq)
+{
+	return 0;
+}
+
+/* Mapping from cpu number to logical apicid */
+static inline int cpu_to_logical_apicid(int cpu)
+{
+	return 1 << cpu;
+}
+
+static inline int cpu_present_to_apicid(int mps_cpu)
+{
+	if (mps_cpu < NR_CPUS && cpu_present(mps_cpu))
+		return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
+	else
+		return BAD_APICID;
+}
+
+static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
+{
+	return physid_mask_of_physid(phys_apicid);
+}
+
+static inline void setup_portio_remap(void)
+{
+}
+
+static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+	return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map);
+}
+
+static inline void enable_apic_mode(void)
+{
+}
+#endif /* CONFIG_X86_LOCAL_APIC */
+#endif /* ASM_X86__MACH_DEFAULT__MACH_APIC_H */
diff --git a/arch/x86/include/asm/mach-default/mach_apicdef.h b/arch/x86/include/asm/mach-default/mach_apicdef.h
new file mode 100644
index 000000000000..0c2d41c41b20
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/mach_apicdef.h
@@ -0,0 +1,24 @@
+#ifndef ASM_X86__MACH_DEFAULT__MACH_APICDEF_H
+#define ASM_X86__MACH_DEFAULT__MACH_APICDEF_H
+
+#include <asm/apic.h>
+
+#ifdef CONFIG_X86_64
+#define	APIC_ID_MASK		(genapic->apic_id_mask)
+#define GET_APIC_ID(x)		(genapic->get_apic_id(x))
+#define	SET_APIC_ID(x)		(genapic->set_apic_id(x))
+#else
+#define		APIC_ID_MASK		(0xF<<24)
+static inline unsigned get_apic_id(unsigned long x) 
+{
+	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
+	if (APIC_XAPIC(ver))
+		return (((x)>>24)&0xFF);
+	else
+		return (((x)>>24)&0xF);
+} 
+
+#define		GET_APIC_ID(x)	get_apic_id(x)
+#endif
+
+#endif /* ASM_X86__MACH_DEFAULT__MACH_APICDEF_H */
diff --git a/arch/x86/include/asm/mach-default/mach_ipi.h b/arch/x86/include/asm/mach-default/mach_ipi.h
new file mode 100644
index 000000000000..674bc7e50c35
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/mach_ipi.h
@@ -0,0 +1,64 @@
+#ifndef ASM_X86__MACH_DEFAULT__MACH_IPI_H
+#define ASM_X86__MACH_DEFAULT__MACH_IPI_H
+
+/* Avoid include hell */
+#define NMI_VECTOR 0x02
+
+void send_IPI_mask_bitmask(cpumask_t mask, int vector);
+void __send_IPI_shortcut(unsigned int shortcut, int vector);
+
+extern int no_broadcast;
+
+#ifdef CONFIG_X86_64
+#include <asm/genapic.h>
+#define send_IPI_mask (genapic->send_IPI_mask)
+#else
+static inline void send_IPI_mask(cpumask_t mask, int vector)
+{
+	send_IPI_mask_bitmask(mask, vector);
+}
+#endif
+
+static inline void __local_send_IPI_allbutself(int vector)
+{
+	if (no_broadcast || vector == NMI_VECTOR) {
+		cpumask_t mask = cpu_online_map;
+
+		cpu_clear(smp_processor_id(), mask);
+		send_IPI_mask(mask, vector);
+	} else
+		__send_IPI_shortcut(APIC_DEST_ALLBUT, vector);
+}
+
+static inline void __local_send_IPI_all(int vector)
+{
+	if (no_broadcast || vector == NMI_VECTOR)
+		send_IPI_mask(cpu_online_map, vector);
+	else
+		__send_IPI_shortcut(APIC_DEST_ALLINC, vector);
+}
+
+#ifdef CONFIG_X86_64
+#define send_IPI_allbutself (genapic->send_IPI_allbutself)
+#define send_IPI_all (genapic->send_IPI_all)
+#else
+static inline void send_IPI_allbutself(int vector)
+{
+	/*
+	 * if there are no other CPUs in the system then we get an APIC send 
+	 * error if we try to broadcast, thus avoid sending IPIs in this case.
+	 */
+	if (!(num_online_cpus() > 1))
+		return;
+
+	__local_send_IPI_allbutself(vector);
+	return;
+}
+
+static inline void send_IPI_all(int vector)
+{
+	__local_send_IPI_all(vector);
+}
+#endif
+
+#endif /* ASM_X86__MACH_DEFAULT__MACH_IPI_H */
diff --git a/arch/x86/include/asm/mach-default/mach_mpparse.h b/arch/x86/include/asm/mach-default/mach_mpparse.h
new file mode 100644
index 000000000000..9c381f2815ac
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/mach_mpparse.h
@@ -0,0 +1,17 @@
+#ifndef ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H
+#define ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H
+
+static inline int mps_oem_check(struct mp_config_table *mpc, char *oem, 
+		char *productid)
+{
+	return 0;
+}
+
+/* Hook from generic ACPI tables.c */
+static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	return 0;
+}
+
+
+#endif /* ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H */
diff --git a/arch/x86/include/asm/mach-default/mach_mpspec.h b/arch/x86/include/asm/mach-default/mach_mpspec.h
new file mode 100644
index 000000000000..d77646f011f1
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/mach_mpspec.h
@@ -0,0 +1,12 @@
+#ifndef ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H
+#define ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H
+
+#define MAX_IRQ_SOURCES 256
+
+#if CONFIG_BASE_SMALL == 0
+#define MAX_MP_BUSSES 256
+#else
+#define MAX_MP_BUSSES 32
+#endif
+
+#endif /* ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H */
diff --git a/arch/x86/include/asm/mach-default/mach_timer.h b/arch/x86/include/asm/mach-default/mach_timer.h
new file mode 100644
index 000000000000..990b15833834
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/mach_timer.h
@@ -0,0 +1,48 @@
+/*
+ *  Machine specific calibrate_tsc() for generic.
+ *  Split out from timer_tsc.c by Osamu Tomita <tomita@cinet.co.jp>
+ */
+/* ------ Calibrate the TSC ------- 
+ * Return 2^32 * (1 / (TSC clocks per usec)) for do_fast_gettimeoffset().
+ * Too much 64-bit arithmetic here to do this cleanly in C, and for
+ * accuracy's sake we want to keep the overhead on the CTC speaker (channel 2)
+ * output busy loop as low as possible. We avoid reading the CTC registers
+ * directly because of the awkward 8-bit access mechanism of the 82C54
+ * device.
+ */
+#ifndef ASM_X86__MACH_DEFAULT__MACH_TIMER_H
+#define ASM_X86__MACH_DEFAULT__MACH_TIMER_H
+
+#define CALIBRATE_TIME_MSEC 30 /* 30 msecs */
+#define CALIBRATE_LATCH	\
+	((CLOCK_TICK_RATE * CALIBRATE_TIME_MSEC + 1000/2)/1000)
+
+static inline void mach_prepare_counter(void)
+{
+       /* Set the Gate high, disable speaker */
+	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
+
+	/*
+	 * Now let's take care of CTC channel 2
+	 *
+	 * Set the Gate high, program CTC channel 2 for mode 0,
+	 * (interrupt on terminal count mode), binary count,
+	 * load 5 * LATCH count, (LSB and MSB) to begin countdown.
+	 *
+	 * Some devices need a delay here.
+	 */
+	outb(0xb0, 0x43);			/* binary, mode 0, LSB/MSB, Ch 2 */
+	outb_p(CALIBRATE_LATCH & 0xff, 0x42);	/* LSB of count */
+	outb_p(CALIBRATE_LATCH >> 8, 0x42);       /* MSB of count */
+}
+
+static inline void mach_countup(unsigned long *count_p)
+{
+	unsigned long count = 0;
+	do {
+		count++;
+	} while ((inb_p(0x61) & 0x20) == 0);
+	*count_p = count;
+}
+
+#endif /* ASM_X86__MACH_DEFAULT__MACH_TIMER_H */
diff --git a/arch/x86/include/asm/mach-default/mach_traps.h b/arch/x86/include/asm/mach-default/mach_traps.h
new file mode 100644
index 000000000000..ff8778f26b84
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/mach_traps.h
@@ -0,0 +1,33 @@
+/*
+ *  Machine specific NMI handling for generic.
+ *  Split out from traps.c by Osamu Tomita <tomita@cinet.co.jp>
+ */
+#ifndef ASM_X86__MACH_DEFAULT__MACH_TRAPS_H
+#define ASM_X86__MACH_DEFAULT__MACH_TRAPS_H
+
+#include <asm/mc146818rtc.h>
+
+static inline unsigned char get_nmi_reason(void)
+{
+	return inb(0x61);
+}
+
+static inline void reassert_nmi(void)
+{
+	int old_reg = -1;
+
+	if (do_i_have_lock_cmos())
+		old_reg = current_lock_cmos_reg();
+	else
+		lock_cmos(0); /* register doesn't matter here */
+	outb(0x8f, 0x70);
+	inb(0x71);		/* dummy */
+	outb(0x0f, 0x70);
+	inb(0x71);		/* dummy */
+	if (old_reg >= 0)
+		outb(old_reg, 0x70);
+	else
+		unlock_cmos();
+}
+
+#endif /* ASM_X86__MACH_DEFAULT__MACH_TRAPS_H */
diff --git a/arch/x86/include/asm/mach-default/mach_wakecpu.h b/arch/x86/include/asm/mach-default/mach_wakecpu.h
new file mode 100644
index 000000000000..361b810f5160
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/mach_wakecpu.h
@@ -0,0 +1,42 @@
+#ifndef ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H
+#define ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H
+
+/* 
+ * This file copes with machines that wakeup secondary CPUs by the
+ * INIT, INIT, STARTUP sequence.
+ */
+
+#define WAKE_SECONDARY_VIA_INIT
+
+#define TRAMPOLINE_LOW phys_to_virt(0x467)
+#define TRAMPOLINE_HIGH phys_to_virt(0x469)
+
+#define boot_cpu_apicid boot_cpu_physical_apicid
+
+static inline void wait_for_init_deassert(atomic_t *deassert)
+{
+	while (!atomic_read(deassert))
+		cpu_relax();
+	return;
+}
+
+/* Nothing to do for most platforms, since cleared by the INIT cycle */
+static inline void smp_callin_clear_local_apic(void)
+{
+}
+
+static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
+{
+}
+
+static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
+{
+}
+
+#if APIC_DEBUG
+ #define inquire_remote_apic(apicid) __inquire_remote_apic(apicid)
+#else
+ #define inquire_remote_apic(apicid) {}
+#endif
+
+#endif /* ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H */
diff --git a/arch/x86/include/asm/mach-default/pci-functions.h b/arch/x86/include/asm/mach-default/pci-functions.h
new file mode 100644
index 000000000000..ed0bab427354
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/pci-functions.h
@@ -0,0 +1,19 @@
+/*
+ *	PCI BIOS function numbering for conventional PCI BIOS 
+ *	systems
+ */
+
+#define PCIBIOS_PCI_FUNCTION_ID 	0xb1XX
+#define PCIBIOS_PCI_BIOS_PRESENT 	0xb101
+#define PCIBIOS_FIND_PCI_DEVICE		0xb102
+#define PCIBIOS_FIND_PCI_CLASS_CODE	0xb103
+#define PCIBIOS_GENERATE_SPECIAL_CYCLE	0xb106
+#define PCIBIOS_READ_CONFIG_BYTE	0xb108
+#define PCIBIOS_READ_CONFIG_WORD	0xb109
+#define PCIBIOS_READ_CONFIG_DWORD	0xb10a
+#define PCIBIOS_WRITE_CONFIG_BYTE	0xb10b
+#define PCIBIOS_WRITE_CONFIG_WORD	0xb10c
+#define PCIBIOS_WRITE_CONFIG_DWORD	0xb10d
+#define PCIBIOS_GET_ROUTING_OPTIONS	0xb10e
+#define PCIBIOS_SET_PCI_HW_INT		0xb10f
+
diff --git a/arch/x86/include/asm/mach-default/setup_arch.h b/arch/x86/include/asm/mach-default/setup_arch.h
new file mode 100644
index 000000000000..38846208b548
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/setup_arch.h
@@ -0,0 +1,3 @@
+/* Hook to call BIOS initialisation function */
+
+/* no action for generic */
diff --git a/arch/x86/include/asm/mach-default/smpboot_hooks.h b/arch/x86/include/asm/mach-default/smpboot_hooks.h
new file mode 100644
index 000000000000..dbab36d64d48
--- /dev/null
+++ b/arch/x86/include/asm/mach-default/smpboot_hooks.h
@@ -0,0 +1,59 @@
+/* two abstractions specific to kernel/smpboot.c, mainly to cater to visws
+ * which needs to alter them. */
+
+static inline void smpboot_clear_io_apic_irqs(void)
+{
+#ifdef CONFIG_X86_IO_APIC
+	io_apic_irqs = 0;
+#endif
+}
+
+static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
+{
+	CMOS_WRITE(0xa, 0xf);
+	local_flush_tlb();
+	pr_debug("1.\n");
+	*((volatile unsigned short *) TRAMPOLINE_HIGH) = start_eip >> 4;
+	pr_debug("2.\n");
+	*((volatile unsigned short *) TRAMPOLINE_LOW) = start_eip & 0xf;
+	pr_debug("3.\n");
+}
+
+static inline void smpboot_restore_warm_reset_vector(void)
+{
+	/*
+	 * Install writable page 0 entry to set BIOS data area.
+	 */
+	local_flush_tlb();
+
+	/*
+	 * Paranoid:  Set warm reset code and vector here back
+	 * to default values.
+	 */
+	CMOS_WRITE(0, 0xf);
+
+	*((volatile long *) phys_to_virt(0x467)) = 0;
+}
+
+static inline void __init smpboot_setup_io_apic(void)
+{
+#ifdef CONFIG_X86_IO_APIC
+	/*
+	 * Here we can be sure that there is an IO-APIC in the system. Let's
+	 * go and set it up:
+	 */
+	if (!skip_ioapic_setup && nr_ioapics)
+		setup_IO_APIC();
+	else {
+		nr_ioapics = 0;
+		localise_nmi_watchdog();
+	}
+#endif
+}
+
+static inline void smpboot_clear_io_apic(void)
+{
+#ifdef CONFIG_X86_IO_APIC
+	nr_ioapics = 0;
+#endif
+}
diff --git a/arch/x86/include/asm/mach-generic/gpio.h b/arch/x86/include/asm/mach-generic/gpio.h
new file mode 100644
index 000000000000..6ce0f7786ef8
--- /dev/null
+++ b/arch/x86/include/asm/mach-generic/gpio.h
@@ -0,0 +1,15 @@
+#ifndef ASM_X86__MACH_GENERIC__GPIO_H
+#define ASM_X86__MACH_GENERIC__GPIO_H
+
+int gpio_request(unsigned gpio, const char *label);
+void gpio_free(unsigned gpio);
+int gpio_direction_input(unsigned gpio);
+int gpio_direction_output(unsigned gpio, int value);
+int gpio_get_value(unsigned gpio);
+void gpio_set_value(unsigned gpio, int value);
+int gpio_to_irq(unsigned gpio);
+int irq_to_gpio(unsigned irq);
+
+#include <asm-generic/gpio.h>           /* cansleep wrappers */
+
+#endif /* ASM_X86__MACH_GENERIC__GPIO_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_apic.h b/arch/x86/include/asm/mach-generic/mach_apic.h
new file mode 100644
index 000000000000..5085b52da301
--- /dev/null
+++ b/arch/x86/include/asm/mach-generic/mach_apic.h
@@ -0,0 +1,33 @@
+#ifndef ASM_X86__MACH_GENERIC__MACH_APIC_H
+#define ASM_X86__MACH_GENERIC__MACH_APIC_H
+
+#include <asm/genapic.h>
+
+#define esr_disable (genapic->ESR_DISABLE)
+#define NO_BALANCE_IRQ (genapic->no_balance_irq)
+#define INT_DELIVERY_MODE (genapic->int_delivery_mode)
+#define INT_DEST_MODE (genapic->int_dest_mode)
+#undef APIC_DEST_LOGICAL
+#define APIC_DEST_LOGICAL (genapic->apic_destination_logical)
+#define TARGET_CPUS	  (genapic->target_cpus())
+#define apic_id_registered (genapic->apic_id_registered)
+#define init_apic_ldr (genapic->init_apic_ldr)
+#define ioapic_phys_id_map (genapic->ioapic_phys_id_map)
+#define setup_apic_routing (genapic->setup_apic_routing)
+#define multi_timer_check (genapic->multi_timer_check)
+#define apicid_to_node (genapic->apicid_to_node)
+#define cpu_to_logical_apicid (genapic->cpu_to_logical_apicid) 
+#define cpu_present_to_apicid (genapic->cpu_present_to_apicid)
+#define apicid_to_cpu_present (genapic->apicid_to_cpu_present)
+#define setup_portio_remap (genapic->setup_portio_remap)
+#define check_apicid_present (genapic->check_apicid_present)
+#define check_phys_apicid_present (genapic->check_phys_apicid_present)
+#define check_apicid_used (genapic->check_apicid_used)
+#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
+#define vector_allocation_domain (genapic->vector_allocation_domain)
+#define enable_apic_mode (genapic->enable_apic_mode)
+#define phys_pkg_id (genapic->phys_pkg_id)
+
+extern void generic_bigsmp_probe(void);
+
+#endif /* ASM_X86__MACH_GENERIC__MACH_APIC_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_apicdef.h b/arch/x86/include/asm/mach-generic/mach_apicdef.h
new file mode 100644
index 000000000000..1657f38b8f27
--- /dev/null
+++ b/arch/x86/include/asm/mach-generic/mach_apicdef.h
@@ -0,0 +1,11 @@
+#ifndef ASM_X86__MACH_GENERIC__MACH_APICDEF_H
+#define ASM_X86__MACH_GENERIC__MACH_APICDEF_H
+
+#ifndef APIC_DEFINITION
+#include <asm/genapic.h>
+
+#define GET_APIC_ID (genapic->get_apic_id)
+#define APIC_ID_MASK (genapic->apic_id_mask)
+#endif
+
+#endif /* ASM_X86__MACH_GENERIC__MACH_APICDEF_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_ipi.h b/arch/x86/include/asm/mach-generic/mach_ipi.h
new file mode 100644
index 000000000000..f67433dbd65f
--- /dev/null
+++ b/arch/x86/include/asm/mach-generic/mach_ipi.h
@@ -0,0 +1,10 @@
+#ifndef ASM_X86__MACH_GENERIC__MACH_IPI_H
+#define ASM_X86__MACH_GENERIC__MACH_IPI_H
+
+#include <asm/genapic.h>
+
+#define send_IPI_mask (genapic->send_IPI_mask)
+#define send_IPI_allbutself (genapic->send_IPI_allbutself)
+#define send_IPI_all (genapic->send_IPI_all)
+
+#endif /* ASM_X86__MACH_GENERIC__MACH_IPI_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_mpparse.h b/arch/x86/include/asm/mach-generic/mach_mpparse.h
new file mode 100644
index 000000000000..3115564e557c
--- /dev/null
+++ b/arch/x86/include/asm/mach-generic/mach_mpparse.h
@@ -0,0 +1,10 @@
+#ifndef ASM_X86__MACH_GENERIC__MACH_MPPARSE_H
+#define ASM_X86__MACH_GENERIC__MACH_MPPARSE_H
+
+
+extern int mps_oem_check(struct mp_config_table *mpc, char *oem,
+			 char *productid);
+
+extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id);
+
+#endif /* ASM_X86__MACH_GENERIC__MACH_MPPARSE_H */
diff --git a/arch/x86/include/asm/mach-generic/mach_mpspec.h b/arch/x86/include/asm/mach-generic/mach_mpspec.h
new file mode 100644
index 000000000000..6061b153613e
--- /dev/null
+++ b/arch/x86/include/asm/mach-generic/mach_mpspec.h
@@ -0,0 +1,12 @@
+#ifndef ASM_X86__MACH_GENERIC__MACH_MPSPEC_H
+#define ASM_X86__MACH_GENERIC__MACH_MPSPEC_H
+
+#define MAX_IRQ_SOURCES 256
+
+/* Summit or generic (i.e. installer) kernels need lots of bus entries. */
+/* Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. */
+#define MAX_MP_BUSSES 260
+
+extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
+				char *productid);
+#endif /* ASM_X86__MACH_GENERIC__MACH_MPSPEC_H */
diff --git a/arch/x86/include/asm/mach-rdc321x/gpio.h b/arch/x86/include/asm/mach-rdc321x/gpio.h
new file mode 100644
index 000000000000..94b6cdf532e2
--- /dev/null
+++ b/arch/x86/include/asm/mach-rdc321x/gpio.h
@@ -0,0 +1,60 @@
+#ifndef ASM_X86__MACH_RDC321X__GPIO_H
+#define ASM_X86__MACH_RDC321X__GPIO_H
+
+#include <linux/kernel.h>
+
+extern int rdc_gpio_get_value(unsigned gpio);
+extern void rdc_gpio_set_value(unsigned gpio, int value);
+extern int rdc_gpio_direction_input(unsigned gpio);
+extern int rdc_gpio_direction_output(unsigned gpio, int value);
+extern int rdc_gpio_request(unsigned gpio, const char *label);
+extern void rdc_gpio_free(unsigned gpio);
+extern void __init rdc321x_gpio_setup(void);
+
+/* Wrappers for the arch-neutral GPIO API */
+
+static inline int gpio_request(unsigned gpio, const char *label)
+{
+	return rdc_gpio_request(gpio, label);
+}
+
+static inline void gpio_free(unsigned gpio)
+{
+	might_sleep();
+	rdc_gpio_free(gpio);
+}
+
+static inline int gpio_direction_input(unsigned gpio)
+{
+	return rdc_gpio_direction_input(gpio);
+}
+
+static inline int gpio_direction_output(unsigned gpio, int value)
+{
+	return rdc_gpio_direction_output(gpio, value);
+}
+
+static inline int gpio_get_value(unsigned gpio)
+{
+	return rdc_gpio_get_value(gpio);
+}
+
+static inline void gpio_set_value(unsigned gpio, int value)
+{
+	rdc_gpio_set_value(gpio, value);
+}
+
+static inline int gpio_to_irq(unsigned gpio)
+{
+	return gpio;
+}
+
+static inline int irq_to_gpio(unsigned irq)
+{
+	return irq;
+}
+
+/* For cansleep */
+#include <asm-generic/gpio.h>
+
+#endif /* ASM_X86__MACH_RDC321X__GPIO_H */
diff --git a/arch/x86/include/asm/mach-rdc321x/rdc321x_defs.h b/arch/x86/include/asm/mach-rdc321x/rdc321x_defs.h
new file mode 100644
index 000000000000..c8e9c8bed3d0
--- /dev/null
+++ b/arch/x86/include/asm/mach-rdc321x/rdc321x_defs.h
@@ -0,0 +1,12 @@
+#define PFX	"rdc321x: "
+
+/* General purpose configuration and data registers */
+#define RDC3210_CFGREG_ADDR     0x0CF8
+#define RDC3210_CFGREG_DATA     0x0CFC
+
+#define RDC321X_GPIO_CTRL_REG1	0x48
+#define RDC321X_GPIO_CTRL_REG2	0x84
+#define RDC321X_GPIO_DATA_REG1	0x4c
+#define RDC321X_GPIO_DATA_REG2	0x88
+
+#define RDC321X_MAX_GPIO	58
diff --git a/arch/x86/include/asm/mach-voyager/do_timer.h b/arch/x86/include/asm/mach-voyager/do_timer.h
new file mode 100644
index 000000000000..9e5a459fd15b
--- /dev/null
+++ b/arch/x86/include/asm/mach-voyager/do_timer.h
@@ -0,0 +1,17 @@
+/* defines for inline arch setup functions */
+#include <linux/clockchips.h>
+
+#include <asm/voyager.h>
+#include <asm/i8253.h>
+
+/**
+ * do_timer_interrupt_hook - hook into timer tick
+ *
+ * Call the pit clock event handler. see asm/i8253.h
+ **/
+static inline void do_timer_interrupt_hook(void)
+{
+	global_clock_event->event_handler(global_clock_event);
+	voyager_timer_interrupt();
+}
+
diff --git a/arch/x86/include/asm/mach-voyager/entry_arch.h b/arch/x86/include/asm/mach-voyager/entry_arch.h
new file mode 100644
index 000000000000..ae52624b5937
--- /dev/null
+++ b/arch/x86/include/asm/mach-voyager/entry_arch.h
@@ -0,0 +1,26 @@
+/* -*- mode: c; c-basic-offset: 8 -*- */
+
+/* Copyright (C) 2002
+ *
+ * Author: James.Bottomley@HansenPartnership.com
+ *
+ * linux/arch/i386/voyager/entry_arch.h
+ *
+ * This file builds the VIC and QIC CPI gates
+ */
+
+/* initialise the voyager interrupt gates 
+ *
+ * This uses the macros in irq.h to set up assembly jump gates.  The
+ * calls are then redirected to the same routine with smp_ prefixed */
+BUILD_INTERRUPT(vic_sys_interrupt, VIC_SYS_INT)
+BUILD_INTERRUPT(vic_cmn_interrupt, VIC_CMN_INT)
+BUILD_INTERRUPT(vic_cpi_interrupt, VIC_CPI_LEVEL0);
+
+/* do all the QIC interrupts */
+BUILD_INTERRUPT(qic_timer_interrupt, QIC_TIMER_CPI);
+BUILD_INTERRUPT(qic_invalidate_interrupt, QIC_INVALIDATE_CPI);
+BUILD_INTERRUPT(qic_reschedule_interrupt, QIC_RESCHEDULE_CPI);
+BUILD_INTERRUPT(qic_enable_irq_interrupt, QIC_ENABLE_IRQ_CPI);
+BUILD_INTERRUPT(qic_call_function_interrupt, QIC_CALL_FUNCTION_CPI);
+BUILD_INTERRUPT(qic_call_function_single_interrupt, QIC_CALL_FUNCTION_SINGLE_CPI);
diff --git a/arch/x86/include/asm/mach-voyager/setup_arch.h b/arch/x86/include/asm/mach-voyager/setup_arch.h
new file mode 100644
index 000000000000..71729ca05cd7
--- /dev/null
+++ b/arch/x86/include/asm/mach-voyager/setup_arch.h
@@ -0,0 +1,12 @@
+#include <asm/voyager.h>
+#include <asm/setup.h>
+#define VOYAGER_BIOS_INFO ((struct voyager_bios_info *) \
+			(&boot_params.apm_bios_info))
+
+/* Hook to call BIOS initialisation function */
+
+/* for voyager, pass the voyager BIOS/SUS info area to the detection
+ * routines */
+
+#define ARCH_SETUP	voyager_detect(VOYAGER_BIOS_INFO);
+
diff --git a/arch/x86/include/asm/math_emu.h b/arch/x86/include/asm/math_emu.h
new file mode 100644
index 000000000000..5768d8e95c8c
--- /dev/null
+++ b/arch/x86/include/asm/math_emu.h
@@ -0,0 +1,31 @@
+#ifndef ASM_X86__MATH_EMU_H
+#define ASM_X86__MATH_EMU_H
+
+/* This structure matches the layout of the data saved to the stack
+   following a device-not-present interrupt, part of it saved
+   automatically by the 80386/80486.
+   */
+struct info {
+	long ___orig_eip;
+	long ___ebx;
+	long ___ecx;
+	long ___edx;
+	long ___esi;
+	long ___edi;
+	long ___ebp;
+	long ___eax;
+	long ___ds;
+	long ___es;
+	long ___fs;
+	long ___orig_eax;
+	long ___eip;
+	long ___cs;
+	long ___eflags;
+	long ___esp;
+	long ___ss;
+	long ___vm86_es; /* This and the following only in vm86 mode */
+	long ___vm86_ds;
+	long ___vm86_fs;
+	long ___vm86_gs;
+};
+#endif /* ASM_X86__MATH_EMU_H */
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
new file mode 100644
index 000000000000..a995f33176cd
--- /dev/null
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -0,0 +1,104 @@
+/*
+ * Machine dependent access functions for RTC registers.
+ */
+#ifndef ASM_X86__MC146818RTC_H
+#define ASM_X86__MC146818RTC_H
+
+#include <asm/io.h>
+#include <asm/system.h>
+#include <asm/processor.h>
+#include <linux/mc146818rtc.h>
+
+#ifndef RTC_PORT
+#define RTC_PORT(x)	(0x70 + (x))
+#define RTC_ALWAYS_BCD	1	/* RTC operates in binary mode */
+#endif
+
+#if defined(CONFIG_X86_32) && defined(__HAVE_ARCH_CMPXCHG)
+/*
+ * This lock provides nmi access to the CMOS/RTC registers.  It has some
+ * special properties.  It is owned by a CPU and stores the index register
+ * currently being accessed (if owned).  The idea here is that it works
+ * like a normal lock (normally).  However, in an NMI, the NMI code will
+ * first check to see if its CPU owns the lock, meaning that the NMI
+ * interrupted during the read/write of the device.  If it does, it goes ahead
+ * and performs the access and then restores the index register.  If it does
+ * not, it locks normally.
+ *
+ * Note that since we are working with NMIs, we need this lock even in
+ * a non-SMP machine just to mark that the lock is owned.
+ *
+ * This only works with compare-and-swap.  There is no other way to
+ * atomically claim the lock and set the owner.
+ */
+#include <linux/smp.h>
+extern volatile unsigned long cmos_lock;
+
+/*
+ * All of these below must be called with interrupts off, preempt
+ * disabled, etc.
+ */
+
+static inline void lock_cmos(unsigned char reg)
+{
+	unsigned long new;
+	new = ((smp_processor_id() + 1) << 8) | reg;
+	for (;;) {
+		if (cmos_lock) {
+			cpu_relax();
+			continue;
+		}
+		if (__cmpxchg(&cmos_lock, 0, new, sizeof(cmos_lock)) == 0)
+			return;
+	}
+}
+
+static inline void unlock_cmos(void)
+{
+	cmos_lock = 0;
+}
+
+static inline int do_i_have_lock_cmos(void)
+{
+	return (cmos_lock >> 8) == (smp_processor_id() + 1);
+}
+
+static inline unsigned char current_lock_cmos_reg(void)
+{
+	return cmos_lock & 0xff;
+}
+
+#define lock_cmos_prefix(reg)			\
+	do {					\
+		unsigned long cmos_flags;	\
+		local_irq_save(cmos_flags);	\
+		lock_cmos(reg)
+
+#define lock_cmos_suffix(reg)			\
+	unlock_cmos();				\
+	local_irq_restore(cmos_flags);		\
+	} while (0)
+#else
+#define lock_cmos_prefix(reg) do {} while (0)
+#define lock_cmos_suffix(reg) do {} while (0)
+#define lock_cmos(reg)
+#define unlock_cmos()
+#define do_i_have_lock_cmos() 0
+#define current_lock_cmos_reg() 0
+#endif
+
+/*
+ * The yet supported machines all access the RTC index register via
+ * an ISA port access but the way to access the date register differs ...
+ */
+#define CMOS_READ(addr) rtc_cmos_read(addr)
+#define CMOS_WRITE(val, addr) rtc_cmos_write(val, addr)
+unsigned char rtc_cmos_read(unsigned char addr);
+void rtc_cmos_write(unsigned char val, unsigned char addr);
+
+extern int mach_set_rtc_mmss(unsigned long nowtime);
+extern unsigned long mach_get_cmos_time(void);
+
+#define RTC_IRQ 8
+
+#endif /* ASM_X86__MC146818RTC_H */
diff --git a/arch/x86/include/asm/mca.h b/arch/x86/include/asm/mca.h
new file mode 100644
index 000000000000..60d1ed287b13
--- /dev/null
+++ b/arch/x86/include/asm/mca.h
@@ -0,0 +1,43 @@
+/* -*- mode: c; c-basic-offset: 8 -*- */
+
+/* Platform specific MCA defines */
+#ifndef ASM_X86__MCA_H
+#define ASM_X86__MCA_H
+
+/* Maximal number of MCA slots - actually, some machines have less, but
+ * they all have sufficient number of POS registers to cover 8.
+ */
+#define MCA_MAX_SLOT_NR  8
+
+/* Most machines have only one MCA bus.  The only multiple bus machines
+ * I know have at most two */
+#define MAX_MCA_BUSSES 2
+
+#define MCA_PRIMARY_BUS		0
+#define MCA_SECONDARY_BUS	1
+
+/* Dummy slot numbers on primary MCA for integrated functions */
+#define MCA_INTEGSCSI	(MCA_MAX_SLOT_NR)
+#define MCA_INTEGVIDEO	(MCA_MAX_SLOT_NR+1)
+#define MCA_MOTHERBOARD (MCA_MAX_SLOT_NR+2)
+
+/* Dummy POS values for integrated functions */
+#define MCA_DUMMY_POS_START	0x10000
+#define MCA_INTEGSCSI_POS	(MCA_DUMMY_POS_START+1)
+#define MCA_INTEGVIDEO_POS	(MCA_DUMMY_POS_START+2)
+#define MCA_MOTHERBOARD_POS	(MCA_DUMMY_POS_START+3)
+
+/* MCA registers */
+
+#define MCA_MOTHERBOARD_SETUP_REG	0x94
+#define MCA_ADAPTER_SETUP_REG		0x96
+#define MCA_POS_REG(n)			(0x100+(n))
+
+#define MCA_ENABLED	0x01	/* POS 2, set if adapter enabled */
+
+/* Max number of adapters, including both slots and various integrated
+ * things.
+ */
+#define MCA_NUMADAPTERS (MCA_MAX_SLOT_NR+3)
+
+#endif /* ASM_X86__MCA_H */
diff --git a/arch/x86/include/asm/mca_dma.h b/arch/x86/include/asm/mca_dma.h
new file mode 100644
index 000000000000..49f22be237d2
--- /dev/null
+++ b/arch/x86/include/asm/mca_dma.h
@@ -0,0 +1,201 @@
+#ifndef ASM_X86__MCA_DMA_H
+#define ASM_X86__MCA_DMA_H
+
+#include <asm/io.h>
+#include <linux/ioport.h>
+
+/*
+ * Microchannel specific DMA stuff.  DMA on an MCA machine is fairly similar to
+ *   standard PC dma, but it certainly has its quirks.  DMA register addresses
+ *   are in a different place and there are some added functions.  Most of this
+ *   should be pretty obvious on inspection.  Note that the user must divide
+ *   count by 2 when using 16-bit dma; that is not handled by these functions.
+ *
+ * Ramen Noodles are yummy.
+ *
+ *  1998 Tymm Twillman <tymm@computer.org>
+ */
+
+/*
+ * Registers that are used by the DMA controller; FN is the function register
+ *   (tell the controller what to do) and EXE is the execution register (how
+ *   to do it)
+ */
+
+#define MCA_DMA_REG_FN  0x18
+#define MCA_DMA_REG_EXE 0x1A
+
+/*
+ * Functions that the DMA controller can do
+ */
+
+#define MCA_DMA_FN_SET_IO       0x00
+#define MCA_DMA_FN_SET_ADDR     0x20
+#define MCA_DMA_FN_GET_ADDR     0x30
+#define MCA_DMA_FN_SET_COUNT    0x40
+#define MCA_DMA_FN_GET_COUNT    0x50
+#define MCA_DMA_FN_GET_STATUS   0x60
+#define MCA_DMA_FN_SET_MODE     0x70
+#define MCA_DMA_FN_SET_ARBUS    0x80
+#define MCA_DMA_FN_MASK         0x90
+#define MCA_DMA_FN_RESET_MASK   0xA0
+#define MCA_DMA_FN_MASTER_CLEAR 0xD0
+
+/*
+ * Modes (used by setting MCA_DMA_FN_MODE in the function register)
+ *
+ * Note that the MODE_READ is read from memory (write to device), and
+ *   MODE_WRITE is vice-versa.
+ */
+
+#define MCA_DMA_MODE_XFER  0x04  /* read by default */
+#define MCA_DMA_MODE_READ  0x04  /* same as XFER */
+#define MCA_DMA_MODE_WRITE 0x08  /* OR with MODE_XFER to use */
+#define MCA_DMA_MODE_IO    0x01  /* DMA from IO register */
+#define MCA_DMA_MODE_16    0x40  /* 16 bit xfers */
+
+
+/**
+ *	mca_enable_dma	-	channel to enable DMA on
+ *	@dmanr: DMA channel
+ *
+ *	Enable the MCA bus DMA on a channel. This can be called from
+ *	IRQ context.
+ */
+
+static inline void mca_enable_dma(unsigned int dmanr)
+{
+	outb(MCA_DMA_FN_RESET_MASK | dmanr, MCA_DMA_REG_FN);
+}
+
+/**
+ *	mca_disble_dma	-	channel to disable DMA on
+ *	@dmanr: DMA channel
+ *
+ *	Enable the MCA bus DMA on a channel. This can be called from
+ *	IRQ context.
+ */
+
+static inline void mca_disable_dma(unsigned int dmanr)
+{
+	outb(MCA_DMA_FN_MASK | dmanr, MCA_DMA_REG_FN);
+}
+
+/**
+ *	mca_set_dma_addr -	load a 24bit DMA address
+ *	@dmanr: DMA channel
+ *	@a: 24bit bus address
+ *
+ *	Load the address register in the DMA controller. This has a 24bit
+ *	limitation (16Mb).
+ */
+
+static inline void mca_set_dma_addr(unsigned int dmanr, unsigned int a)
+{
+	outb(MCA_DMA_FN_SET_ADDR | dmanr, MCA_DMA_REG_FN);
+	outb(a & 0xff, MCA_DMA_REG_EXE);
+	outb((a >> 8) & 0xff, MCA_DMA_REG_EXE);
+	outb((a >> 16) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ *	mca_get_dma_addr -	load a 24bit DMA address
+ *	@dmanr: DMA channel
+ *
+ *	Read the address register in the DMA controller. This has a 24bit
+ *	limitation (16Mb). The return is a bus address.
+ */
+
+static inline unsigned int mca_get_dma_addr(unsigned int dmanr)
+{
+	unsigned int addr;
+
+	outb(MCA_DMA_FN_GET_ADDR | dmanr, MCA_DMA_REG_FN);
+	addr = inb(MCA_DMA_REG_EXE);
+	addr |= inb(MCA_DMA_REG_EXE) << 8;
+	addr |= inb(MCA_DMA_REG_EXE) << 16;
+
+	return addr;
+}
+
+/**
+ *	mca_set_dma_count -	load a 16bit transfer count
+ *	@dmanr: DMA channel
+ *	@count: count
+ *
+ *	Set the DMA count for this channel. This can be up to 64Kbytes.
+ *	Setting a count of zero will not do what you expect.
+ */
+
+static inline void mca_set_dma_count(unsigned int dmanr, unsigned int count)
+{
+	count--;  /* transfers one more than count -- correct for this */
+
+	outb(MCA_DMA_FN_SET_COUNT | dmanr, MCA_DMA_REG_FN);
+	outb(count & 0xff, MCA_DMA_REG_EXE);
+	outb((count >> 8) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ *	mca_get_dma_residue -	get the remaining bytes to transfer
+ *	@dmanr: DMA channel
+ *
+ *	This function returns the number of bytes left to transfer
+ *	on this DMA channel.
+ */
+
+static inline unsigned int mca_get_dma_residue(unsigned int dmanr)
+{
+	unsigned short count;
+
+	outb(MCA_DMA_FN_GET_COUNT | dmanr, MCA_DMA_REG_FN);
+	count = 1 + inb(MCA_DMA_REG_EXE);
+	count += inb(MCA_DMA_REG_EXE) << 8;
+
+	return count;
+}
+
+/**
+ *	mca_set_dma_io -	set the port for an I/O transfer
+ *	@dmanr: DMA channel
+ *	@io_addr: an I/O port number
+ *
+ *	Unlike the ISA bus DMA controllers the DMA on MCA bus can transfer
+ *	with an I/O port target.
+ */
+
+static inline void mca_set_dma_io(unsigned int dmanr, unsigned int io_addr)
+{
+	/*
+	 * DMA from a port address -- set the io address
+	 */
+
+	outb(MCA_DMA_FN_SET_IO | dmanr, MCA_DMA_REG_FN);
+	outb(io_addr & 0xff, MCA_DMA_REG_EXE);
+	outb((io_addr >>  8) & 0xff, MCA_DMA_REG_EXE);
+}
+
+/**
+ *	mca_set_dma_mode -	set the DMA mode
+ *	@dmanr: DMA channel
+ *	@mode: mode to set
+ *
+ *	The DMA controller supports several modes. The mode values you can
+ *	set are-
+ *
+ *	%MCA_DMA_MODE_READ when reading from the DMA device.
+ *
+ *	%MCA_DMA_MODE_WRITE to writing to the DMA device.
+ *
+ *	%MCA_DMA_MODE_IO to do DMA to or from an I/O port.
+ *
+ *	%MCA_DMA_MODE_16 to do 16bit transfers.
+ */
+
+static inline void mca_set_dma_mode(unsigned int dmanr, unsigned int mode)
+{
+	outb(MCA_DMA_FN_SET_MODE | dmanr, MCA_DMA_REG_FN);
+	outb(mode, MCA_DMA_REG_EXE);
+}
+
+#endif /* ASM_X86__MCA_DMA_H */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
new file mode 100644
index 000000000000..036133eaf744
--- /dev/null
+++ b/arch/x86/include/asm/mce.h
@@ -0,0 +1,130 @@
+#ifndef ASM_X86__MCE_H
+#define ASM_X86__MCE_H
+
+#ifdef __x86_64__
+
+#include <asm/ioctls.h>
+#include <asm/types.h>
+
+/*
+ * Machine Check support for x86
+ */
+
+#define MCG_CTL_P	 (1UL<<8)   /* MCG_CAP register available */
+
+#define MCG_STATUS_RIPV  (1UL<<0)   /* restart ip valid */
+#define MCG_STATUS_EIPV  (1UL<<1)   /* ip points to correct instruction */
+#define MCG_STATUS_MCIP  (1UL<<2)   /* machine check in progress */
+
+#define MCI_STATUS_VAL   (1UL<<63)  /* valid error */
+#define MCI_STATUS_OVER  (1UL<<62)  /* previous errors lost */
+#define MCI_STATUS_UC    (1UL<<61)  /* uncorrected error */
+#define MCI_STATUS_EN    (1UL<<60)  /* error enabled */
+#define MCI_STATUS_MISCV (1UL<<59)  /* misc error reg. valid */
+#define MCI_STATUS_ADDRV (1UL<<58)  /* addr reg. valid */
+#define MCI_STATUS_PCC   (1UL<<57)  /* processor context corrupt */
+
+/* Fields are zero when not available */
+struct mce {
+	__u64 status;
+	__u64 misc;
+	__u64 addr;
+	__u64 mcgstatus;
+	__u64 ip;
+	__u64 tsc;	/* cpu time stamp counter */
+	__u64 res1;	/* for future extension */
+	__u64 res2;	/* dito. */
+	__u8  cs;		/* code segment */
+	__u8  bank;	/* machine check bank */
+	__u8  cpu;	/* cpu that raised the error */
+	__u8  finished;   /* entry is valid */
+	__u32 pad;
+};
+
+/*
+ * This structure contains all data related to the MCE log.  Also
+ * carries a signature to make it easier to find from external
+ * debugging tools.  Each entry is only valid when its finished flag
+ * is set.
+ */
+
+#define MCE_LOG_LEN 32
+
+struct mce_log {
+	char signature[12]; /* "MACHINECHECK" */
+	unsigned len;	    /* = MCE_LOG_LEN */
+	unsigned next;
+	unsigned flags;
+	unsigned pad0;
+	struct mce entry[MCE_LOG_LEN];
+};
+
+#define MCE_OVERFLOW 0		/* bit 0 in flags means overflow */
+
+#define MCE_LOG_SIGNATURE	"MACHINECHECK"
+
+#define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
+#define MCE_GET_LOG_LEN      _IOR('M', 2, int)
+#define MCE_GETCLEAR_FLAGS   _IOR('M', 3, int)
+
+/* Software defined banks */
+#define MCE_EXTENDED_BANK	128
+#define MCE_THERMAL_BANK	MCE_EXTENDED_BANK + 0
+
+#define K8_MCE_THRESHOLD_BASE      (MCE_EXTENDED_BANK + 1)      /* MCE_AMD */
+#define K8_MCE_THRESHOLD_BANK_0    (MCE_THRESHOLD_BASE + 0 * 9)
+#define K8_MCE_THRESHOLD_BANK_1    (MCE_THRESHOLD_BASE + 1 * 9)
+#define K8_MCE_THRESHOLD_BANK_2    (MCE_THRESHOLD_BASE + 2 * 9)
+#define K8_MCE_THRESHOLD_BANK_3    (MCE_THRESHOLD_BASE + 3 * 9)
+#define K8_MCE_THRESHOLD_BANK_4    (MCE_THRESHOLD_BASE + 4 * 9)
+#define K8_MCE_THRESHOLD_BANK_5    (MCE_THRESHOLD_BASE + 5 * 9)
+#define K8_MCE_THRESHOLD_DRAM_ECC  (MCE_THRESHOLD_BANK_4 + 0)
+
+#endif /* __x86_64__ */
+
+#ifdef __KERNEL__
+
+#ifdef CONFIG_X86_32
+extern int mce_disabled;
+#else /* CONFIG_X86_32 */
+
+#include <asm/atomic.h>
+
+void mce_log(struct mce *m);
+DECLARE_PER_CPU(struct sys_device, device_mce);
+extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
+
+#ifdef CONFIG_X86_MCE_INTEL
+void mce_intel_feature_init(struct cpuinfo_x86 *c);
+#else
+static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
+#endif
+
+#ifdef CONFIG_X86_MCE_AMD
+void mce_amd_feature_init(struct cpuinfo_x86 *c);
+#else
+static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
+#endif
+
+void mce_log_therm_throt_event(unsigned int cpu, __u64 status);
+
+extern atomic_t mce_entry;
+
+extern void do_machine_check(struct pt_regs *, long);
+extern int mce_notify_user(void);
+
+#endif /* !CONFIG_X86_32 */
+
+
+
+#ifdef CONFIG_X86_MCE
+extern void mcheck_init(struct cpuinfo_x86 *c);
+#else
+#define mcheck_init(c) do { } while (0)
+#endif
+extern void stop_mce(void);
+extern void restart_mce(void);
+
+#endif /* __KERNEL__ */
+
+#endif /* ASM_X86__MCE_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
new file mode 100644
index 000000000000..62c793bb70ca
--- /dev/null
+++ b/arch/x86/include/asm/microcode.h
@@ -0,0 +1,47 @@
+#ifndef ASM_X86__MICROCODE_H
+#define ASM_X86__MICROCODE_H
+
+struct cpu_signature {
+	unsigned int sig;
+	unsigned int pf;
+	unsigned int rev;
+};
+
+struct device;
+
+struct microcode_ops {
+	int  (*request_microcode_user) (int cpu, const void __user *buf, size_t size);
+	int  (*request_microcode_fw) (int cpu, struct device *device);
+
+	void (*apply_microcode) (int cpu);
+
+	int  (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
+	void (*microcode_fini_cpu) (int cpu);
+};
+
+struct ucode_cpu_info {
+	struct cpu_signature cpu_sig;
+	int valid;
+	void *mc;
+};
+extern struct ucode_cpu_info ucode_cpu_info[];
+
+#ifdef CONFIG_MICROCODE_INTEL
+extern struct microcode_ops * __init init_intel_microcode(void);
+#else
+static inline struct microcode_ops * __init init_intel_microcode(void)
+{
+	return NULL;
+}
+#endif /* CONFIG_MICROCODE_INTEL */
+
+#ifdef CONFIG_MICROCODE_AMD
+extern struct microcode_ops * __init init_amd_microcode(void);
+#else
+static inline struct microcode_ops * __init init_amd_microcode(void)
+{
+	return NULL;
+}
+#endif
+
+#endif /* ASM_X86__MICROCODE_H */
diff --git a/arch/x86/include/asm/mman.h b/arch/x86/include/asm/mman.h
new file mode 100644
index 000000000000..4ef28e6de383
--- /dev/null
+++ b/arch/x86/include/asm/mman.h
@@ -0,0 +1,20 @@
+#ifndef ASM_X86__MMAN_H
+#define ASM_X86__MMAN_H
+
+#include <asm-generic/mman.h>
+
+#define MAP_32BIT	0x40		/* only give out 32bit addresses */
+
+#define MAP_GROWSDOWN	0x0100		/* stack-like segment */
+#define MAP_DENYWRITE	0x0800		/* ETXTBSY */
+#define MAP_EXECUTABLE	0x1000		/* mark it as an executable */
+#define MAP_LOCKED	0x2000		/* pages are locked */
+#define MAP_NORESERVE	0x4000		/* don't check for reservations */
+#define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
+#define MAP_NONBLOCK	0x10000		/* do not block on IO */
+#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
+
+#define MCL_CURRENT	1		/* lock all current mappings */
+#define MCL_FUTURE	2		/* lock all future mappings */
+
+#endif /* ASM_X86__MMAN_H */
diff --git a/arch/x86/include/asm/mmconfig.h b/arch/x86/include/asm/mmconfig.h
new file mode 100644
index 000000000000..fb79b1cf5d07
--- /dev/null
+++ b/arch/x86/include/asm/mmconfig.h
@@ -0,0 +1,12 @@
+#ifndef ASM_X86__MMCONFIG_H
+#define ASM_X86__MMCONFIG_H
+
+#ifdef CONFIG_PCI_MMCONFIG
+extern void __cpuinit fam10h_check_enable_mmcfg(void);
+extern void __cpuinit check_enable_amd_mmconf_dmi(void);
+#else
+static inline void fam10h_check_enable_mmcfg(void) { }
+static inline void check_enable_amd_mmconf_dmi(void) { }
+#endif
+
+#endif /* ASM_X86__MMCONFIG_H */
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
new file mode 100644
index 000000000000..9d5aff14334a
--- /dev/null
+++ b/arch/x86/include/asm/mmu.h
@@ -0,0 +1,26 @@
+#ifndef ASM_X86__MMU_H
+#define ASM_X86__MMU_H
+
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+
+/*
+ * The x86 doesn't have a mmu context, but
+ * we put the segment information here.
+ */
+typedef struct {
+	void *ldt;
+	int size;
+	struct mutex lock;
+	void *vdso;
+} mm_context_t;
+
+#ifdef CONFIG_SMP
+void leave_mm(int cpu);
+#else
+static inline void leave_mm(int cpu)
+{
+}
+#endif
+
+#endif /* ASM_X86__MMU_H */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
new file mode 100644
index 000000000000..8ec940bfd079
--- /dev/null
+++ b/arch/x86/include/asm/mmu_context.h
@@ -0,0 +1,37 @@
+#ifndef ASM_X86__MMU_CONTEXT_H
+#define ASM_X86__MMU_CONTEXT_H
+
+#include <asm/desc.h>
+#include <asm/atomic.h>
+#include <asm/pgalloc.h>
+#include <asm/tlbflush.h>
+#include <asm/paravirt.h>
+#ifndef CONFIG_PARAVIRT
+#include <asm-generic/mm_hooks.h>
+
+static inline void paravirt_activate_mm(struct mm_struct *prev,
+					struct mm_struct *next)
+{
+}
+#endif	/* !CONFIG_PARAVIRT */
+
+/*
+ * Used for LDT copy/destruction.
+ */
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
+void destroy_context(struct mm_struct *mm);
+
+#ifdef CONFIG_X86_32
+# include "mmu_context_32.h"
+#else
+# include "mmu_context_64.h"
+#endif
+
+#define activate_mm(prev, next)			\
+do {						\
+	paravirt_activate_mm((prev), (next));	\
+	switch_mm((prev), (next), NULL);	\
+} while (0);
+
+
+#endif /* ASM_X86__MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/mmu_context_32.h b/arch/x86/include/asm/mmu_context_32.h
new file mode 100644
index 000000000000..cce6f6e4afd6
--- /dev/null
+++ b/arch/x86/include/asm/mmu_context_32.h
@@ -0,0 +1,56 @@
+#ifndef ASM_X86__MMU_CONTEXT_32_H
+#define ASM_X86__MMU_CONTEXT_32_H
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+#ifdef CONFIG_SMP
+	unsigned cpu = smp_processor_id();
+	if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
+		per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_LAZY;
+#endif
+}
+
+static inline void switch_mm(struct mm_struct *prev,
+			     struct mm_struct *next,
+			     struct task_struct *tsk)
+{
+	int cpu = smp_processor_id();
+
+	if (likely(prev != next)) {
+		/* stop flush ipis for the previous mm */
+		cpu_clear(cpu, prev->cpu_vm_mask);
+#ifdef CONFIG_SMP
+		per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
+		per_cpu(cpu_tlbstate, cpu).active_mm = next;
+#endif
+		cpu_set(cpu, next->cpu_vm_mask);
+
+		/* Re-load page tables */
+		load_cr3(next->pgd);
+
+		/*
+		 * load the LDT, if the LDT is different:
+		 */
+		if (unlikely(prev->context.ldt != next->context.ldt))
+			load_LDT_nolock(&next->context);
+	}
+#ifdef CONFIG_SMP
+	else {
+		per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
+		BUG_ON(per_cpu(cpu_tlbstate, cpu).active_mm != next);
+
+		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+			/* We were in lazy tlb mode and leave_mm disabled
+			 * tlb flush IPI delivery. We must reload %cr3.
+			 */
+			load_cr3(next->pgd);
+			load_LDT_nolock(&next->context);
+		}
+	}
+#endif
+}
+
+#define deactivate_mm(tsk, mm)			\
+	asm("movl %0,%%gs": :"r" (0));
+
+#endif /* ASM_X86__MMU_CONTEXT_32_H */
diff --git a/arch/x86/include/asm/mmu_context_64.h b/arch/x86/include/asm/mmu_context_64.h
new file mode 100644
index 000000000000..26758673c828
--- /dev/null
+++ b/arch/x86/include/asm/mmu_context_64.h
@@ -0,0 +1,54 @@
+#ifndef ASM_X86__MMU_CONTEXT_64_H
+#define ASM_X86__MMU_CONTEXT_64_H
+
+#include <asm/pda.h>
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+#ifdef CONFIG_SMP
+	if (read_pda(mmu_state) == TLBSTATE_OK)
+		write_pda(mmu_state, TLBSTATE_LAZY);
+#endif
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+			     struct task_struct *tsk)
+{
+	unsigned cpu = smp_processor_id();
+	if (likely(prev != next)) {
+		/* stop flush ipis for the previous mm */
+		cpu_clear(cpu, prev->cpu_vm_mask);
+#ifdef CONFIG_SMP
+		write_pda(mmu_state, TLBSTATE_OK);
+		write_pda(active_mm, next);
+#endif
+		cpu_set(cpu, next->cpu_vm_mask);
+		load_cr3(next->pgd);
+
+		if (unlikely(next->context.ldt != prev->context.ldt))
+			load_LDT_nolock(&next->context);
+	}
+#ifdef CONFIG_SMP
+	else {
+		write_pda(mmu_state, TLBSTATE_OK);
+		if (read_pda(active_mm) != next)
+			BUG();
+		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
+			/* We were in lazy tlb mode and leave_mm disabled
+			 * tlb flush IPI delivery. We must reload CR3
+			 * to make sure to use no freed page tables.
+			 */
+			load_cr3(next->pgd);
+			load_LDT_nolock(&next->context);
+		}
+	}
+#endif
+}
+
+#define deactivate_mm(tsk, mm)			\
+do {						\
+	load_gs_index(0);			\
+	asm volatile("movl %0,%%fs"::"r"(0));	\
+} while (0)
+
+#endif /* ASM_X86__MMU_CONTEXT_64_H */
diff --git a/arch/x86/include/asm/mmx.h b/arch/x86/include/asm/mmx.h
new file mode 100644
index 000000000000..2e7299bb3653
--- /dev/null
+++ b/arch/x86/include/asm/mmx.h
@@ -0,0 +1,14 @@
+#ifndef ASM_X86__MMX_H
+#define ASM_X86__MMX_H
+
+/*
+ *	MMX 3Dnow! helper operations
+ */
+
+#include <linux/types.h>
+
+extern void *_mmx_memcpy(void *to, const void *from, size_t size);
+extern void mmx_clear_page(void *page);
+extern void mmx_copy_page(void *to, void *from);
+
+#endif /* ASM_X86__MMX_H */
diff --git a/arch/x86/include/asm/mmzone.h b/arch/x86/include/asm/mmzone.h
new file mode 100644
index 000000000000..64217ea16a36
--- /dev/null
+++ b/arch/x86/include/asm/mmzone.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "mmzone_32.h"
+#else
+# include "mmzone_64.h"
+#endif
diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h
new file mode 100644
index 000000000000..121b65d61d86
--- /dev/null
+++ b/arch/x86/include/asm/mmzone_32.h
@@ -0,0 +1,134 @@
+/*
+ * Written by Pat Gaughen (gone@us.ibm.com) Mar 2002
+ *
+ */
+
+#ifndef ASM_X86__MMZONE_32_H
+#define ASM_X86__MMZONE_32_H
+
+#include <asm/smp.h>
+
+#ifdef CONFIG_NUMA
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid)	(node_data[nid])
+
+#include <asm/numaq.h>
+/* summit or generic arch */
+#include <asm/srat.h>
+
+extern int get_memcfg_numa_flat(void);
+/*
+ * This allows any one NUMA architecture to be compiled
+ * for, and still fall back to the flat function if it
+ * fails.
+ */
+static inline void get_memcfg_numa(void)
+{
+
+	if (get_memcfg_numaq())
+		return;
+	if (get_memcfg_from_srat())
+		return;
+	get_memcfg_numa_flat();
+}
+
+extern int early_pfn_to_nid(unsigned long pfn);
+
+#else /* !CONFIG_NUMA */
+
+#define get_memcfg_numa get_memcfg_numa_flat
+
+#endif /* CONFIG_NUMA */
+
+#ifdef CONFIG_DISCONTIGMEM
+
+/*
+ * generic node memory support, the following assumptions apply:
+ *
+ * 1) memory comes in 64Mb contigious chunks which are either present or not
+ * 2) we will not have more than 64Gb in total
+ *
+ * for now assume that 64Gb is max amount of RAM for whole system
+ *    64Gb / 4096bytes/page = 16777216 pages
+ */
+#define MAX_NR_PAGES 16777216
+#define MAX_ELEMENTS 1024
+#define PAGES_PER_ELEMENT (MAX_NR_PAGES/MAX_ELEMENTS)
+
+extern s8 physnode_map[];
+
+static inline int pfn_to_nid(unsigned long pfn)
+{
+#ifdef CONFIG_NUMA
+	return((int) physnode_map[(pfn) / PAGES_PER_ELEMENT]);
+#else
+	return 0;
+#endif
+}
+
+/*
+ * Following are macros that each numa implmentation must define.
+ */
+
+#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
+#define node_end_pfn(nid)						\
+({									\
+	pg_data_t *__pgdat = NODE_DATA(nid);				\
+	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
+})
+
+static inline int pfn_valid(int pfn)
+{
+	int nid = pfn_to_nid(pfn);
+
+	if (nid >= 0)
+		return (pfn < node_end_pfn(nid));
+	return 0;
+}
+
+#endif /* CONFIG_DISCONTIGMEM */
+
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+
+/*
+ * Following are macros that are specific to this numa platform.
+ */
+#define reserve_bootmem(addr, size, flags) \
+	reserve_bootmem_node(NODE_DATA(0), (addr), (size), (flags))
+#define alloc_bootmem(x) \
+	__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_nopanic(x) \
+	__alloc_bootmem_node_nopanic(NODE_DATA(0), (x), SMP_CACHE_BYTES, \
+				__pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_low(x) \
+	__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0)
+#define alloc_bootmem_pages(x) \
+	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_pages_nopanic(x) \
+	__alloc_bootmem_node_nopanic(NODE_DATA(0), (x), PAGE_SIZE, \
+				__pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_low_pages(x) \
+	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0)
+#define alloc_bootmem_node(pgdat, x)					\
+({									\
+	struct pglist_data  __maybe_unused			\
+				*__alloc_bootmem_node__pgdat = (pgdat);	\
+	__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES,	\
+						__pa(MAX_DMA_ADDRESS));	\
+})
+#define alloc_bootmem_pages_node(pgdat, x)				\
+({									\
+	struct pglist_data  __maybe_unused			\
+				*__alloc_bootmem_node__pgdat = (pgdat);	\
+	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE,		\
+						__pa(MAX_DMA_ADDRESS));	\
+})
+#define alloc_bootmem_low_pages_node(pgdat, x)				\
+({									\
+	struct pglist_data  __maybe_unused			\
+				*__alloc_bootmem_node__pgdat = (pgdat);	\
+	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0);		\
+})
+#endif /* CONFIG_NEED_MULTIPLE_NODES */
+
+#endif /* ASM_X86__MMZONE_32_H */
diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h
new file mode 100644
index 000000000000..6480f3333b2a
--- /dev/null
+++ b/arch/x86/include/asm/mmzone_64.h
@@ -0,0 +1,51 @@
+/* K8 NUMA support */
+/* Copyright 2002,2003 by Andi Kleen, SuSE Labs */
+/* 2.5 Version loosely based on the NUMAQ Code by Pat Gaughen. */
+#ifndef ASM_X86__MMZONE_64_H
+#define ASM_X86__MMZONE_64_H
+
+
+#ifdef CONFIG_NUMA
+
+#include <linux/mmdebug.h>
+
+#include <asm/smp.h>
+
+/* Simple perfect hash to map physical addresses to node numbers */
+struct memnode {
+	int shift;
+	unsigned int mapsize;
+	s16 *map;
+	s16 embedded_map[64 - 8];
+} ____cacheline_aligned; /* total size = 128 bytes */
+extern struct memnode memnode;
+#define memnode_shift memnode.shift
+#define memnodemap memnode.map
+#define memnodemapsize memnode.mapsize
+
+extern struct pglist_data *node_data[];
+
+static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
+{
+	unsigned nid;
+	VIRTUAL_BUG_ON(!memnodemap);
+	nid = memnodemap[addr >> memnode_shift];
+	VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]);
+	return nid;
+}
+
+#define NODE_DATA(nid)		(node_data[nid])
+
+#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
+#define node_end_pfn(nid)       (NODE_DATA(nid)->node_start_pfn +	\
+				 NODE_DATA(nid)->node_spanned_pages)
+
+extern int early_pfn_to_nid(unsigned long pfn);
+
+#ifdef CONFIG_NUMA_EMU
+#define FAKE_NODE_MIN_SIZE	(64 * 1024 * 1024)
+#define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
+#endif
+
+#endif
+#endif /* ASM_X86__MMZONE_64_H */
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
new file mode 100644
index 000000000000..864f2005fc1d
--- /dev/null
+++ b/arch/x86/include/asm/module.h
@@ -0,0 +1,80 @@
+#ifndef ASM_X86__MODULE_H
+#define ASM_X86__MODULE_H
+
+/* x86_32/64 are simple */
+struct mod_arch_specific {};
+
+#ifdef CONFIG_X86_32
+# define Elf_Shdr Elf32_Shdr
+# define Elf_Sym Elf32_Sym
+# define Elf_Ehdr Elf32_Ehdr
+#else
+# define Elf_Shdr Elf64_Shdr
+# define Elf_Sym Elf64_Sym
+# define Elf_Ehdr Elf64_Ehdr
+#endif
+
+#ifdef CONFIG_X86_64
+/* X86_64 does not define MODULE_PROC_FAMILY */
+#elif defined CONFIG_M386
+#define MODULE_PROC_FAMILY "386 "
+#elif defined CONFIG_M486
+#define MODULE_PROC_FAMILY "486 "
+#elif defined CONFIG_M586
+#define MODULE_PROC_FAMILY "586 "
+#elif defined CONFIG_M586TSC
+#define MODULE_PROC_FAMILY "586TSC "
+#elif defined CONFIG_M586MMX
+#define MODULE_PROC_FAMILY "586MMX "
+#elif defined CONFIG_MCORE2
+#define MODULE_PROC_FAMILY "CORE2 "
+#elif defined CONFIG_M686
+#define MODULE_PROC_FAMILY "686 "
+#elif defined CONFIG_MPENTIUMII
+#define MODULE_PROC_FAMILY "PENTIUMII "
+#elif defined CONFIG_MPENTIUMIII
+#define MODULE_PROC_FAMILY "PENTIUMIII "
+#elif defined CONFIG_MPENTIUMM
+#define MODULE_PROC_FAMILY "PENTIUMM "
+#elif defined CONFIG_MPENTIUM4
+#define MODULE_PROC_FAMILY "PENTIUM4 "
+#elif defined CONFIG_MK6
+#define MODULE_PROC_FAMILY "K6 "
+#elif defined CONFIG_MK7
+#define MODULE_PROC_FAMILY "K7 "
+#elif defined CONFIG_MK8
+#define MODULE_PROC_FAMILY "K8 "
+#elif defined CONFIG_X86_ELAN
+#define MODULE_PROC_FAMILY "ELAN "
+#elif defined CONFIG_MCRUSOE
+#define MODULE_PROC_FAMILY "CRUSOE "
+#elif defined CONFIG_MEFFICEON
+#define MODULE_PROC_FAMILY "EFFICEON "
+#elif defined CONFIG_MWINCHIPC6
+#define MODULE_PROC_FAMILY "WINCHIPC6 "
+#elif defined CONFIG_MWINCHIP3D
+#define MODULE_PROC_FAMILY "WINCHIP3D "
+#elif defined CONFIG_MCYRIXIII
+#define MODULE_PROC_FAMILY "CYRIXIII "
+#elif defined CONFIG_MVIAC3_2
+#define MODULE_PROC_FAMILY "VIAC3-2 "
+#elif defined CONFIG_MVIAC7
+#define MODULE_PROC_FAMILY "VIAC7 "
+#elif defined CONFIG_MGEODEGX1
+#define MODULE_PROC_FAMILY "GEODEGX1 "
+#elif defined CONFIG_MGEODE_LX
+#define MODULE_PROC_FAMILY "GEODE "
+#else
+#error unknown processor family
+#endif
+
+#ifdef CONFIG_X86_32
+# ifdef CONFIG_4KSTACKS
+#  define MODULE_STACKSIZE "4KSTACKS "
+# else
+#  define MODULE_STACKSIZE ""
+# endif
+# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY MODULE_STACKSIZE
+#endif
+
+#endif /* ASM_X86__MODULE_H */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
new file mode 100644
index 000000000000..be2241a818f1
--- /dev/null
+++ b/arch/x86/include/asm/mpspec.h
@@ -0,0 +1,145 @@
+#ifndef ASM_X86__MPSPEC_H
+#define ASM_X86__MPSPEC_H
+
+#include <linux/init.h>
+
+#include <asm/mpspec_def.h>
+
+extern int apic_version[MAX_APICS];
+
+#ifdef CONFIG_X86_32
+#include <mach_mpspec.h>
+
+extern unsigned int def_to_bigsmp;
+extern u8 apicid_2_node[];
+extern int pic_mode;
+
+#ifdef CONFIG_X86_NUMAQ
+extern int mp_bus_id_to_node[MAX_MP_BUSSES];
+extern int mp_bus_id_to_local[MAX_MP_BUSSES];
+extern int quad_local_to_mp_bus_id [NR_CPUS/4][4];
+#endif
+
+#define MAX_APICID 256
+
+#else
+
+#define MAX_MP_BUSSES 256
+/* Each PCI slot may be a combo card with its own bus.  4 IRQ pins per slot. */
+#define MAX_IRQ_SOURCES (MAX_MP_BUSSES * 4)
+
+#endif
+
+extern void early_find_smp_config(void);
+extern void early_get_smp_config(void);
+
+#if defined(CONFIG_MCA) || defined(CONFIG_EISA)
+extern int mp_bus_id_to_type[MAX_MP_BUSSES];
+#endif
+
+extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
+
+extern unsigned int boot_cpu_physical_apicid;
+extern unsigned int max_physical_apicid;
+extern int smp_found_config;
+extern int mpc_default_type;
+extern unsigned long mp_lapic_addr;
+
+extern void find_smp_config(void);
+extern void get_smp_config(void);
+#ifdef CONFIG_X86_MPPARSE
+extern void early_reserve_e820_mpc_new(void);
+#else
+static inline void early_reserve_e820_mpc_new(void) { }
+#endif
+
+void __cpuinit generic_processor_info(int apicid, int version);
+#ifdef CONFIG_ACPI
+extern void mp_register_ioapic(int id, u32 address, u32 gsi_base);
+extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
+				   u32 gsi);
+extern void mp_config_acpi_legacy_irqs(void);
+extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
+#ifdef CONFIG_X86_IO_APIC
+extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
+				u32 gsi, int triggering, int polarity);
+#else
+static inline int
+mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
+		   u32 gsi, int triggering, int polarity)
+{
+	return 0;
+}
+#endif
+#endif /* CONFIG_ACPI */
+
+#define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_APICS)
+
+struct physid_mask {
+	unsigned long mask[PHYSID_ARRAY_SIZE];
+};
+
+typedef struct physid_mask physid_mask_t;
+
+#define physid_set(physid, map)			set_bit(physid, (map).mask)
+#define physid_clear(physid, map)		clear_bit(physid, (map).mask)
+#define physid_isset(physid, map)		test_bit(physid, (map).mask)
+#define physid_test_and_set(physid, map)			\
+	test_and_set_bit(physid, (map).mask)
+
+#define physids_and(dst, src1, src2)					\
+	bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+
+#define physids_or(dst, src1, src2)					\
+	bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
+
+#define physids_clear(map)					\
+	bitmap_zero((map).mask, MAX_APICS)
+
+#define physids_complement(dst, src)				\
+	bitmap_complement((dst).mask, (src).mask, MAX_APICS)
+
+#define physids_empty(map)					\
+	bitmap_empty((map).mask, MAX_APICS)
+
+#define physids_equal(map1, map2)				\
+	bitmap_equal((map1).mask, (map2).mask, MAX_APICS)
+
+#define physids_weight(map)					\
+	bitmap_weight((map).mask, MAX_APICS)
+
+#define physids_shift_right(d, s, n)				\
+	bitmap_shift_right((d).mask, (s).mask, n, MAX_APICS)
+
+#define physids_shift_left(d, s, n)				\
+	bitmap_shift_left((d).mask, (s).mask, n, MAX_APICS)
+
+#define physids_coerce(map)			((map).mask[0])
+
+#define physids_promote(physids)					\
+	({								\
+		physid_mask_t __physid_mask = PHYSID_MASK_NONE;		\
+		__physid_mask.mask[0] = physids;			\
+		__physid_mask;						\
+	})
+
+/* Note: will create very large stack frames if physid_mask_t is big */
+#define physid_mask_of_physid(physid)					\
+	({								\
+		physid_mask_t __physid_mask = PHYSID_MASK_NONE;		\
+		physid_set(physid, __physid_mask);			\
+		__physid_mask;						\
+	})
+
+static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
+{
+	physids_clear(*map);
+	physid_set(physid, *map);
+}
+
+#define PHYSID_MASK_ALL		{ {[0 ... PHYSID_ARRAY_SIZE-1] = ~0UL} }
+#define PHYSID_MASK_NONE	{ {[0 ... PHYSID_ARRAY_SIZE-1] = 0UL} }
+
+extern physid_mask_t phys_cpu_present_map;
+
+#endif /* ASM_X86__MPSPEC_H */
diff --git a/arch/x86/include/asm/mpspec_def.h b/arch/x86/include/asm/mpspec_def.h
new file mode 100644
index 000000000000..79166b048012
--- /dev/null
+++ b/arch/x86/include/asm/mpspec_def.h
@@ -0,0 +1,180 @@
+#ifndef ASM_X86__MPSPEC_DEF_H
+#define ASM_X86__MPSPEC_DEF_H
+
+/*
+ * Structure definitions for SMP machines following the
+ * Intel Multiprocessing Specification 1.1 and 1.4.
+ */
+
+/*
+ * This tag identifies where the SMP configuration
+ * information is.
+ */
+
+#define SMP_MAGIC_IDENT	(('_'<<24) | ('P'<<16) | ('M'<<8) | '_')
+
+#ifdef CONFIG_X86_32
+# define MAX_MPC_ENTRY 1024
+# define MAX_APICS      256
+#else
+# if NR_CPUS <= 255
+#  define MAX_APICS     255
+# else
+#  define MAX_APICS   32768
+# endif
+#endif
+
+struct intel_mp_floating {
+	char mpf_signature[4];		/* "_MP_"			*/
+	unsigned int mpf_physptr;	/* Configuration table address	*/
+	unsigned char mpf_length;	/* Our length (paragraphs)	*/
+	unsigned char mpf_specification;/* Specification version	*/
+	unsigned char mpf_checksum;	/* Checksum (makes sum 0)	*/
+	unsigned char mpf_feature1;	/* Standard or configuration ?	*/
+	unsigned char mpf_feature2;	/* Bit7 set for IMCR|PIC	*/
+	unsigned char mpf_feature3;	/* Unused (0)			*/
+	unsigned char mpf_feature4;	/* Unused (0)			*/
+	unsigned char mpf_feature5;	/* Unused (0)			*/
+};
+
+#define MPC_SIGNATURE "PCMP"
+
+struct mp_config_table {
+	char mpc_signature[4];
+	unsigned short mpc_length;	/* Size of table */
+	char mpc_spec;			/* 0x01 */
+	char mpc_checksum;
+	char mpc_oem[8];
+	char mpc_productid[12];
+	unsigned int mpc_oemptr;	/* 0 if not present */
+	unsigned short mpc_oemsize;	/* 0 if not present */
+	unsigned short mpc_oemcount;
+	unsigned int mpc_lapic;	/* APIC address */
+	unsigned int reserved;
+};
+
+/* Followed by entries */
+
+#define	MP_PROCESSOR		0
+#define	MP_BUS			1
+#define	MP_IOAPIC		2
+#define	MP_INTSRC		3
+#define	MP_LINTSRC		4
+/* Used by IBM NUMA-Q to describe node locality */
+#define	MP_TRANSLATION		192
+
+#define CPU_ENABLED		1	/* Processor is available */
+#define CPU_BOOTPROCESSOR	2	/* Processor is the BP */
+
+#define CPU_STEPPING_MASK	0x000F
+#define CPU_MODEL_MASK		0x00F0
+#define CPU_FAMILY_MASK		0x0F00
+
+struct mpc_config_processor {
+	unsigned char mpc_type;
+	unsigned char mpc_apicid;	/* Local APIC number */
+	unsigned char mpc_apicver;	/* Its versions */
+	unsigned char mpc_cpuflag;
+	unsigned int mpc_cpufeature;
+	unsigned int mpc_featureflag;	/* CPUID feature value */
+	unsigned int mpc_reserved[2];
+};
+
+struct mpc_config_bus {
+	unsigned char mpc_type;
+	unsigned char mpc_busid;
+	unsigned char mpc_bustype[6];
+};
+
+/* List of Bus Type string values, Intel MP Spec. */
+#define BUSTYPE_EISA	"EISA"
+#define BUSTYPE_ISA	"ISA"
+#define BUSTYPE_INTERN	"INTERN"	/* Internal BUS */
+#define BUSTYPE_MCA	"MCA"
+#define BUSTYPE_VL	"VL"		/* Local bus */
+#define BUSTYPE_PCI	"PCI"
+#define BUSTYPE_PCMCIA	"PCMCIA"
+#define BUSTYPE_CBUS	"CBUS"
+#define BUSTYPE_CBUSII	"CBUSII"
+#define BUSTYPE_FUTURE	"FUTURE"
+#define BUSTYPE_MBI	"MBI"
+#define BUSTYPE_MBII	"MBII"
+#define BUSTYPE_MPI	"MPI"
+#define BUSTYPE_MPSA	"MPSA"
+#define BUSTYPE_NUBUS	"NUBUS"
+#define BUSTYPE_TC	"TC"
+#define BUSTYPE_VME	"VME"
+#define BUSTYPE_XPRESS	"XPRESS"
+
+#define MPC_APIC_USABLE		0x01
+
+struct mpc_config_ioapic {
+	unsigned char mpc_type;
+	unsigned char mpc_apicid;
+	unsigned char mpc_apicver;
+	unsigned char mpc_flags;
+	unsigned int mpc_apicaddr;
+};
+
+struct mpc_config_intsrc {
+	unsigned char mpc_type;
+	unsigned char mpc_irqtype;
+	unsigned short mpc_irqflag;
+	unsigned char mpc_srcbus;
+	unsigned char mpc_srcbusirq;
+	unsigned char mpc_dstapic;
+	unsigned char mpc_dstirq;
+};
+
+enum mp_irq_source_types {
+	mp_INT = 0,
+	mp_NMI = 1,
+	mp_SMI = 2,
+	mp_ExtINT = 3
+};
+
+#define MP_IRQDIR_DEFAULT	0
+#define MP_IRQDIR_HIGH		1
+#define MP_IRQDIR_LOW		3
+
+#define MP_APIC_ALL	0xFF
+
+struct mpc_config_lintsrc {
+	unsigned char mpc_type;
+	unsigned char mpc_irqtype;
+	unsigned short mpc_irqflag;
+	unsigned char mpc_srcbusid;
+	unsigned char mpc_srcbusirq;
+	unsigned char mpc_destapic;
+	unsigned char mpc_destapiclint;
+};
+
+#define MPC_OEM_SIGNATURE "_OEM"
+
+struct mp_config_oemtable {
+	char oem_signature[4];
+	unsigned short oem_length;	/* Size of table */
+	char  oem_rev;			/* 0x01 */
+	char  oem_checksum;
+	char  mpc_oem[8];
+};
+
+/*
+ *	Default configurations
+ *
+ *	1	2 CPU ISA 82489DX
+ *	2	2 CPU EISA 82489DX neither IRQ 0 timer nor IRQ 13 DMA chaining
+ *	3	2 CPU EISA 82489DX
+ *	4	2 CPU MCA 82489DX
+ *	5	2 CPU ISA+PCI
+ *	6	2 CPU EISA+PCI
+ *	7	2 CPU MCA+PCI
+ */
+
+enum mp_bustype {
+	MP_BUS_ISA = 1,
+	MP_BUS_EISA,
+	MP_BUS_PCI,
+	MP_BUS_MCA,
+};
+#endif /* ASM_X86__MPSPEC_DEF_H */
diff --git a/arch/x86/include/asm/msgbuf.h b/arch/x86/include/asm/msgbuf.h
new file mode 100644
index 000000000000..1b538c907a3d
--- /dev/null
+++ b/arch/x86/include/asm/msgbuf.h
@@ -0,0 +1,39 @@
+#ifndef ASM_X86__MSGBUF_H
+#define ASM_X86__MSGBUF_H
+
+/*
+ * The msqid64_ds structure for i386 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space on i386 is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ *
+ * Pad space on x8664 is left for:
+ * - 2 miscellaneous 64-bit values
+ */
+struct msqid64_ds {
+	struct ipc64_perm msg_perm;
+	__kernel_time_t msg_stime;	/* last msgsnd time */
+#ifdef __i386__
+	unsigned long	__unused1;
+#endif
+	__kernel_time_t msg_rtime;	/* last msgrcv time */
+#ifdef __i386__
+	unsigned long	__unused2;
+#endif
+	__kernel_time_t msg_ctime;	/* last change time */
+#ifdef __i386__
+	unsigned long	__unused3;
+#endif
+	unsigned long  msg_cbytes;	/* current number of bytes on queue */
+	unsigned long  msg_qnum;	/* number of messages in queue */
+	unsigned long  msg_qbytes;	/* max number of bytes on queue */
+	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
+	__kernel_pid_t msg_lrpid;	/* last receive pid */
+	unsigned long  __unused4;
+	unsigned long  __unused5;
+};
+
+#endif /* ASM_X86__MSGBUF_H */
diff --git a/arch/x86/include/asm/msidef.h b/arch/x86/include/asm/msidef.h
new file mode 100644
index 000000000000..ed9190246876
--- /dev/null
+++ b/arch/x86/include/asm/msidef.h
@@ -0,0 +1,55 @@
+#ifndef ASM_X86__MSIDEF_H
+#define ASM_X86__MSIDEF_H
+
+/*
+ * Constants for Intel APIC based MSI messages.
+ */
+
+/*
+ * Shifts for MSI data
+ */
+
+#define MSI_DATA_VECTOR_SHIFT		0
+#define  MSI_DATA_VECTOR_MASK		0x000000ff
+#define	 MSI_DATA_VECTOR(v)		(((v) << MSI_DATA_VECTOR_SHIFT) & \
+					 MSI_DATA_VECTOR_MASK)
+
+#define MSI_DATA_DELIVERY_MODE_SHIFT	8
+#define  MSI_DATA_DELIVERY_FIXED	(0 << MSI_DATA_DELIVERY_MODE_SHIFT)
+#define  MSI_DATA_DELIVERY_LOWPRI	(1 << MSI_DATA_DELIVERY_MODE_SHIFT)
+
+#define MSI_DATA_LEVEL_SHIFT		14
+#define	 MSI_DATA_LEVEL_DEASSERT	(0 << MSI_DATA_LEVEL_SHIFT)
+#define	 MSI_DATA_LEVEL_ASSERT		(1 << MSI_DATA_LEVEL_SHIFT)
+
+#define MSI_DATA_TRIGGER_SHIFT		15
+#define  MSI_DATA_TRIGGER_EDGE		(0 << MSI_DATA_TRIGGER_SHIFT)
+#define  MSI_DATA_TRIGGER_LEVEL		(1 << MSI_DATA_TRIGGER_SHIFT)
+
+/*
+ * Shift/mask fields for msi address
+ */
+
+#define MSI_ADDR_BASE_HI		0
+#define MSI_ADDR_BASE_LO		0xfee00000
+
+#define MSI_ADDR_DEST_MODE_SHIFT	2
+#define  MSI_ADDR_DEST_MODE_PHYSICAL	(0 << MSI_ADDR_DEST_MODE_SHIFT)
+#define	 MSI_ADDR_DEST_MODE_LOGICAL	(1 << MSI_ADDR_DEST_MODE_SHIFT)
+
+#define MSI_ADDR_REDIRECTION_SHIFT	3
+#define  MSI_ADDR_REDIRECTION_CPU	(0 << MSI_ADDR_REDIRECTION_SHIFT)
+					/* dedicated cpu */
+#define  MSI_ADDR_REDIRECTION_LOWPRI	(1 << MSI_ADDR_REDIRECTION_SHIFT)
+					/* lowest priority */
+
+#define MSI_ADDR_DEST_ID_SHIFT		12
+#define	 MSI_ADDR_DEST_ID_MASK		0x00ffff0
+#define  MSI_ADDR_DEST_ID(dest)		(((dest) << MSI_ADDR_DEST_ID_SHIFT) & \
+					 MSI_ADDR_DEST_ID_MASK)
+
+#define MSI_ADDR_IR_EXT_INT		(1 << 4)
+#define MSI_ADDR_IR_SHV			(1 << 3)
+#define MSI_ADDR_IR_INDEX1(index)	((index & 0x8000) >> 13)
+#define MSI_ADDR_IR_INDEX2(index)	((index & 0x7fff) << 5)
+#endif /* ASM_X86__MSIDEF_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
new file mode 100644
index 000000000000..dabd10f0bbee
--- /dev/null
+++ b/arch/x86/include/asm/msr-index.h
@@ -0,0 +1,332 @@
+#ifndef ASM_X86__MSR_INDEX_H
+#define ASM_X86__MSR_INDEX_H
+
+/* CPU model specific register (MSR) numbers */
+
+/* x86-64 specific MSRs */
+#define MSR_EFER		0xc0000080 /* extended feature register */
+#define MSR_STAR		0xc0000081 /* legacy mode SYSCALL target */
+#define MSR_LSTAR		0xc0000082 /* long mode SYSCALL target */
+#define MSR_CSTAR		0xc0000083 /* compat mode SYSCALL target */
+#define MSR_SYSCALL_MASK	0xc0000084 /* EFLAGS mask for syscall */
+#define MSR_FS_BASE		0xc0000100 /* 64bit FS base */
+#define MSR_GS_BASE		0xc0000101 /* 64bit GS base */
+#define MSR_KERNEL_GS_BASE	0xc0000102 /* SwapGS GS shadow */
+
+/* EFER bits: */
+#define _EFER_SCE		0  /* SYSCALL/SYSRET */
+#define _EFER_LME		8  /* Long mode enable */
+#define _EFER_LMA		10 /* Long mode active (read-only) */
+#define _EFER_NX		11 /* No execute enable */
+
+#define EFER_SCE		(1<<_EFER_SCE)
+#define EFER_LME		(1<<_EFER_LME)
+#define EFER_LMA		(1<<_EFER_LMA)
+#define EFER_NX			(1<<_EFER_NX)
+
+/* Intel MSRs. Some also available on other CPUs */
+#define MSR_IA32_PERFCTR0		0x000000c1
+#define MSR_IA32_PERFCTR1		0x000000c2
+#define MSR_FSB_FREQ			0x000000cd
+
+#define MSR_MTRRcap			0x000000fe
+#define MSR_IA32_BBL_CR_CTL		0x00000119
+
+#define MSR_IA32_SYSENTER_CS		0x00000174
+#define MSR_IA32_SYSENTER_ESP		0x00000175
+#define MSR_IA32_SYSENTER_EIP		0x00000176
+
+#define MSR_IA32_MCG_CAP		0x00000179
+#define MSR_IA32_MCG_STATUS		0x0000017a
+#define MSR_IA32_MCG_CTL		0x0000017b
+
+#define MSR_IA32_PEBS_ENABLE		0x000003f1
+#define MSR_IA32_DS_AREA		0x00000600
+#define MSR_IA32_PERF_CAPABILITIES	0x00000345
+
+#define MSR_MTRRfix64K_00000		0x00000250
+#define MSR_MTRRfix16K_80000		0x00000258
+#define MSR_MTRRfix16K_A0000		0x00000259
+#define MSR_MTRRfix4K_C0000		0x00000268
+#define MSR_MTRRfix4K_C8000		0x00000269
+#define MSR_MTRRfix4K_D0000		0x0000026a
+#define MSR_MTRRfix4K_D8000		0x0000026b
+#define MSR_MTRRfix4K_E0000		0x0000026c
+#define MSR_MTRRfix4K_E8000		0x0000026d
+#define MSR_MTRRfix4K_F0000		0x0000026e
+#define MSR_MTRRfix4K_F8000		0x0000026f
+#define MSR_MTRRdefType			0x000002ff
+
+#define MSR_IA32_CR_PAT			0x00000277
+
+#define MSR_IA32_DEBUGCTLMSR		0x000001d9
+#define MSR_IA32_LASTBRANCHFROMIP	0x000001db
+#define MSR_IA32_LASTBRANCHTOIP		0x000001dc
+#define MSR_IA32_LASTINTFROMIP		0x000001dd
+#define MSR_IA32_LASTINTTOIP		0x000001de
+
+/* DEBUGCTLMSR bits (others vary by model): */
+#define _DEBUGCTLMSR_LBR	0 /* last branch recording */
+#define _DEBUGCTLMSR_BTF	1 /* single-step on branches */
+
+#define DEBUGCTLMSR_LBR		(1UL << _DEBUGCTLMSR_LBR)
+#define DEBUGCTLMSR_BTF		(1UL << _DEBUGCTLMSR_BTF)
+
+#define MSR_IA32_MC0_CTL		0x00000400
+#define MSR_IA32_MC0_STATUS		0x00000401
+#define MSR_IA32_MC0_ADDR		0x00000402
+#define MSR_IA32_MC0_MISC		0x00000403
+
+#define MSR_P6_PERFCTR0			0x000000c1
+#define MSR_P6_PERFCTR1			0x000000c2
+#define MSR_P6_EVNTSEL0			0x00000186
+#define MSR_P6_EVNTSEL1			0x00000187
+
+/* AMD64 MSRs. Not complete. See the architecture manual for a more
+   complete list. */
+
+#define MSR_AMD64_NB_CFG		0xc001001f
+#define MSR_AMD64_IBSFETCHCTL		0xc0011030
+#define MSR_AMD64_IBSFETCHLINAD		0xc0011031
+#define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
+#define MSR_AMD64_IBSOPCTL		0xc0011033
+#define MSR_AMD64_IBSOPRIP		0xc0011034
+#define MSR_AMD64_IBSOPDATA		0xc0011035
+#define MSR_AMD64_IBSOPDATA2		0xc0011036
+#define MSR_AMD64_IBSOPDATA3		0xc0011037
+#define MSR_AMD64_IBSDCLINAD		0xc0011038
+#define MSR_AMD64_IBSDCPHYSAD		0xc0011039
+#define MSR_AMD64_IBSCTL		0xc001103a
+
+/* Fam 10h MSRs */
+#define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
+#define FAM10H_MMIO_CONF_ENABLE		(1<<0)
+#define FAM10H_MMIO_CONF_BUSRANGE_MASK	0xf
+#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
+#define FAM10H_MMIO_CONF_BASE_MASK	0xfffffff
+#define FAM10H_MMIO_CONF_BASE_SHIFT	20
+
+/* K8 MSRs */
+#define MSR_K8_TOP_MEM1			0xc001001a
+#define MSR_K8_TOP_MEM2			0xc001001d
+#define MSR_K8_SYSCFG			0xc0010010
+#define MSR_K8_HWCR			0xc0010015
+#define MSR_K8_INT_PENDING_MSG		0xc0010055
+/* C1E active bits in int pending message */
+#define K8_INTP_C1E_ACTIVE_MASK		0x18000000
+#define MSR_K8_TSEG_ADDR		0xc0010112
+#define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
+#define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
+#define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
+
+/* K7 MSRs */
+#define MSR_K7_EVNTSEL0			0xc0010000
+#define MSR_K7_PERFCTR0			0xc0010004
+#define MSR_K7_EVNTSEL1			0xc0010001
+#define MSR_K7_PERFCTR1			0xc0010005
+#define MSR_K7_EVNTSEL2			0xc0010002
+#define MSR_K7_PERFCTR2			0xc0010006
+#define MSR_K7_EVNTSEL3			0xc0010003
+#define MSR_K7_PERFCTR3			0xc0010007
+#define MSR_K7_CLK_CTL			0xc001001b
+#define MSR_K7_HWCR			0xc0010015
+#define MSR_K7_FID_VID_CTL		0xc0010041
+#define MSR_K7_FID_VID_STATUS		0xc0010042
+
+/* K6 MSRs */
+#define MSR_K6_EFER			0xc0000080
+#define MSR_K6_STAR			0xc0000081
+#define MSR_K6_WHCR			0xc0000082
+#define MSR_K6_UWCCR			0xc0000085
+#define MSR_K6_EPMR			0xc0000086
+#define MSR_K6_PSOR			0xc0000087
+#define MSR_K6_PFIR			0xc0000088
+
+/* Centaur-Hauls/IDT defined MSRs. */
+#define MSR_IDT_FCR1			0x00000107
+#define MSR_IDT_FCR2			0x00000108
+#define MSR_IDT_FCR3			0x00000109
+#define MSR_IDT_FCR4			0x0000010a
+
+#define MSR_IDT_MCR0			0x00000110
+#define MSR_IDT_MCR1			0x00000111
+#define MSR_IDT_MCR2			0x00000112
+#define MSR_IDT_MCR3			0x00000113
+#define MSR_IDT_MCR4			0x00000114
+#define MSR_IDT_MCR5			0x00000115
+#define MSR_IDT_MCR6			0x00000116
+#define MSR_IDT_MCR7			0x00000117
+#define MSR_IDT_MCR_CTRL		0x00000120
+
+/* VIA Cyrix defined MSRs*/
+#define MSR_VIA_FCR			0x00001107
+#define MSR_VIA_LONGHAUL		0x0000110a
+#define MSR_VIA_RNG			0x0000110b
+#define MSR_VIA_BCR2			0x00001147
+
+/* Transmeta defined MSRs */
+#define MSR_TMTA_LONGRUN_CTRL		0x80868010
+#define MSR_TMTA_LONGRUN_FLAGS		0x80868011
+#define MSR_TMTA_LRTI_READOUT		0x80868018
+#define MSR_TMTA_LRTI_VOLT_MHZ		0x8086801a
+
+/* Intel defined MSRs. */
+#define MSR_IA32_P5_MC_ADDR		0x00000000
+#define MSR_IA32_P5_MC_TYPE		0x00000001
+#define MSR_IA32_TSC			0x00000010
+#define MSR_IA32_PLATFORM_ID		0x00000017
+#define MSR_IA32_EBL_CR_POWERON		0x0000002a
+#define MSR_IA32_FEATURE_CONTROL        0x0000003a
+
+#define FEATURE_CONTROL_LOCKED		(1<<0)
+#define FEATURE_CONTROL_VMXON_ENABLED	(1<<2)
+
+#define MSR_IA32_APICBASE		0x0000001b
+#define MSR_IA32_APICBASE_BSP		(1<<8)
+#define MSR_IA32_APICBASE_ENABLE	(1<<11)
+#define MSR_IA32_APICBASE_BASE		(0xfffff<<12)
+
+#define MSR_IA32_UCODE_WRITE		0x00000079
+#define MSR_IA32_UCODE_REV		0x0000008b
+
+#define MSR_IA32_PERF_STATUS		0x00000198
+#define MSR_IA32_PERF_CTL		0x00000199
+
+#define MSR_IA32_MPERF			0x000000e7
+#define MSR_IA32_APERF			0x000000e8
+
+#define MSR_IA32_THERM_CONTROL		0x0000019a
+#define MSR_IA32_THERM_INTERRUPT	0x0000019b
+#define MSR_IA32_THERM_STATUS		0x0000019c
+#define MSR_IA32_MISC_ENABLE		0x000001a0
+
+/* Intel Model 6 */
+#define MSR_P6_EVNTSEL0			0x00000186
+#define MSR_P6_EVNTSEL1			0x00000187
+
+/* P4/Xeon+ specific */
+#define MSR_IA32_MCG_EAX		0x00000180
+#define MSR_IA32_MCG_EBX		0x00000181
+#define MSR_IA32_MCG_ECX		0x00000182
+#define MSR_IA32_MCG_EDX		0x00000183
+#define MSR_IA32_MCG_ESI		0x00000184
+#define MSR_IA32_MCG_EDI		0x00000185
+#define MSR_IA32_MCG_EBP		0x00000186
+#define MSR_IA32_MCG_ESP		0x00000187
+#define MSR_IA32_MCG_EFLAGS		0x00000188
+#define MSR_IA32_MCG_EIP		0x00000189
+#define MSR_IA32_MCG_RESERVED		0x0000018a
+
+/* Pentium IV performance counter MSRs */
+#define MSR_P4_BPU_PERFCTR0		0x00000300
+#define MSR_P4_BPU_PERFCTR1		0x00000301
+#define MSR_P4_BPU_PERFCTR2		0x00000302
+#define MSR_P4_BPU_PERFCTR3		0x00000303
+#define MSR_P4_MS_PERFCTR0		0x00000304
+#define MSR_P4_MS_PERFCTR1		0x00000305
+#define MSR_P4_MS_PERFCTR2		0x00000306
+#define MSR_P4_MS_PERFCTR3		0x00000307
+#define MSR_P4_FLAME_PERFCTR0		0x00000308
+#define MSR_P4_FLAME_PERFCTR1		0x00000309
+#define MSR_P4_FLAME_PERFCTR2		0x0000030a
+#define MSR_P4_FLAME_PERFCTR3		0x0000030b
+#define MSR_P4_IQ_PERFCTR0		0x0000030c
+#define MSR_P4_IQ_PERFCTR1		0x0000030d
+#define MSR_P4_IQ_PERFCTR2		0x0000030e
+#define MSR_P4_IQ_PERFCTR3		0x0000030f
+#define MSR_P4_IQ_PERFCTR4		0x00000310
+#define MSR_P4_IQ_PERFCTR5		0x00000311
+#define MSR_P4_BPU_CCCR0		0x00000360
+#define MSR_P4_BPU_CCCR1		0x00000361
+#define MSR_P4_BPU_CCCR2		0x00000362
+#define MSR_P4_BPU_CCCR3		0x00000363
+#define MSR_P4_MS_CCCR0			0x00000364
+#define MSR_P4_MS_CCCR1			0x00000365
+#define MSR_P4_MS_CCCR2			0x00000366
+#define MSR_P4_MS_CCCR3			0x00000367
+#define MSR_P4_FLAME_CCCR0		0x00000368
+#define MSR_P4_FLAME_CCCR1		0x00000369
+#define MSR_P4_FLAME_CCCR2		0x0000036a
+#define MSR_P4_FLAME_CCCR3		0x0000036b
+#define MSR_P4_IQ_CCCR0			0x0000036c
+#define MSR_P4_IQ_CCCR1			0x0000036d
+#define MSR_P4_IQ_CCCR2			0x0000036e
+#define MSR_P4_IQ_CCCR3			0x0000036f
+#define MSR_P4_IQ_CCCR4			0x00000370
+#define MSR_P4_IQ_CCCR5			0x00000371
+#define MSR_P4_ALF_ESCR0		0x000003ca
+#define MSR_P4_ALF_ESCR1		0x000003cb
+#define MSR_P4_BPU_ESCR0		0x000003b2
+#define MSR_P4_BPU_ESCR1		0x000003b3
+#define MSR_P4_BSU_ESCR0		0x000003a0
+#define MSR_P4_BSU_ESCR1		0x000003a1
+#define MSR_P4_CRU_ESCR0		0x000003b8
+#define MSR_P4_CRU_ESCR1		0x000003b9
+#define MSR_P4_CRU_ESCR2		0x000003cc
+#define MSR_P4_CRU_ESCR3		0x000003cd
+#define MSR_P4_CRU_ESCR4		0x000003e0
+#define MSR_P4_CRU_ESCR5		0x000003e1
+#define MSR_P4_DAC_ESCR0		0x000003a8
+#define MSR_P4_DAC_ESCR1		0x000003a9
+#define MSR_P4_FIRM_ESCR0		0x000003a4
+#define MSR_P4_FIRM_ESCR1		0x000003a5
+#define MSR_P4_FLAME_ESCR0		0x000003a6
+#define MSR_P4_FLAME_ESCR1		0x000003a7
+#define MSR_P4_FSB_ESCR0		0x000003a2
+#define MSR_P4_FSB_ESCR1		0x000003a3
+#define MSR_P4_IQ_ESCR0			0x000003ba
+#define MSR_P4_IQ_ESCR1			0x000003bb
+#define MSR_P4_IS_ESCR0			0x000003b4
+#define MSR_P4_IS_ESCR1			0x000003b5
+#define MSR_P4_ITLB_ESCR0		0x000003b6
+#define MSR_P4_ITLB_ESCR1		0x000003b7
+#define MSR_P4_IX_ESCR0			0x000003c8
+#define MSR_P4_IX_ESCR1			0x000003c9
+#define MSR_P4_MOB_ESCR0		0x000003aa
+#define MSR_P4_MOB_ESCR1		0x000003ab
+#define MSR_P4_MS_ESCR0			0x000003c0
+#define MSR_P4_MS_ESCR1			0x000003c1
+#define MSR_P4_PMH_ESCR0		0x000003ac
+#define MSR_P4_PMH_ESCR1		0x000003ad
+#define MSR_P4_RAT_ESCR0		0x000003bc
+#define MSR_P4_RAT_ESCR1		0x000003bd
+#define MSR_P4_SAAT_ESCR0		0x000003ae
+#define MSR_P4_SAAT_ESCR1		0x000003af
+#define MSR_P4_SSU_ESCR0		0x000003be
+#define MSR_P4_SSU_ESCR1		0x000003bf /* guess: not in manual */
+
+#define MSR_P4_TBPU_ESCR0		0x000003c2
+#define MSR_P4_TBPU_ESCR1		0x000003c3
+#define MSR_P4_TC_ESCR0			0x000003c4
+#define MSR_P4_TC_ESCR1			0x000003c5
+#define MSR_P4_U2L_ESCR0		0x000003b0
+#define MSR_P4_U2L_ESCR1		0x000003b1
+
+/* Intel Core-based CPU performance counters */
+#define MSR_CORE_PERF_FIXED_CTR0	0x00000309
+#define MSR_CORE_PERF_FIXED_CTR1	0x0000030a
+#define MSR_CORE_PERF_FIXED_CTR2	0x0000030b
+#define MSR_CORE_PERF_FIXED_CTR_CTRL	0x0000038d
+#define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
+#define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
+#define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
+
+/* Geode defined MSRs */
+#define MSR_GEODE_BUSCONT_CONF0		0x00001900
+
+/* Intel VT MSRs */
+#define MSR_IA32_VMX_BASIC              0x00000480
+#define MSR_IA32_VMX_PINBASED_CTLS      0x00000481
+#define MSR_IA32_VMX_PROCBASED_CTLS     0x00000482
+#define MSR_IA32_VMX_EXIT_CTLS          0x00000483
+#define MSR_IA32_VMX_ENTRY_CTLS         0x00000484
+#define MSR_IA32_VMX_MISC               0x00000485
+#define MSR_IA32_VMX_CR0_FIXED0         0x00000486
+#define MSR_IA32_VMX_CR0_FIXED1         0x00000487
+#define MSR_IA32_VMX_CR4_FIXED0         0x00000488
+#define MSR_IA32_VMX_CR4_FIXED1         0x00000489
+#define MSR_IA32_VMX_VMCS_ENUM          0x0000048a
+#define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
+#define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
+
+#endif /* ASM_X86__MSR_INDEX_H */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
new file mode 100644
index 000000000000..530af1f6389e
--- /dev/null
+++ b/arch/x86/include/asm/msr.h
@@ -0,0 +1,247 @@
+#ifndef ASM_X86__MSR_H
+#define ASM_X86__MSR_H
+
+#include <asm/msr-index.h>
+
+#ifndef __ASSEMBLY__
+# include <linux/types.h>
+#endif
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+
+#include <asm/asm.h>
+#include <asm/errno.h>
+
+static inline unsigned long long native_read_tscp(unsigned int *aux)
+{
+	unsigned long low, high;
+	asm volatile(".byte 0x0f,0x01,0xf9"
+		     : "=a" (low), "=d" (high), "=c" (*aux));
+	return low | ((u64)high << 32);
+}
+
+/*
+ * i386 calling convention returns 64-bit value in edx:eax, while
+ * x86_64 returns at rax. Also, the "A" constraint does not really
+ * mean rdx:rax in x86_64, so we need specialized behaviour for each
+ * architecture
+ */
+#ifdef CONFIG_X86_64
+#define DECLARE_ARGS(val, low, high)	unsigned low, high
+#define EAX_EDX_VAL(val, low, high)	((low) | ((u64)(high) << 32))
+#define EAX_EDX_ARGS(val, low, high)	"a" (low), "d" (high)
+#define EAX_EDX_RET(val, low, high)	"=a" (low), "=d" (high)
+#else
+#define DECLARE_ARGS(val, low, high)	unsigned long long val
+#define EAX_EDX_VAL(val, low, high)	(val)
+#define EAX_EDX_ARGS(val, low, high)	"A" (val)
+#define EAX_EDX_RET(val, low, high)	"=A" (val)
+#endif
+
+static inline unsigned long long native_read_msr(unsigned int msr)
+{
+	DECLARE_ARGS(val, low, high);
+
+	asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr));
+	return EAX_EDX_VAL(val, low, high);
+}
+
+static inline unsigned long long native_read_msr_safe(unsigned int msr,
+						      int *err)
+{
+	DECLARE_ARGS(val, low, high);
+
+	asm volatile("2: rdmsr ; xor %[err],%[err]\n"
+		     "1:\n\t"
+		     ".section .fixup,\"ax\"\n\t"
+		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
+		     ".previous\n\t"
+		     _ASM_EXTABLE(2b, 3b)
+		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
+		     : "c" (msr), [fault] "i" (-EFAULT));
+	return EAX_EDX_VAL(val, low, high);
+}
+
+static inline unsigned long long native_read_msr_amd_safe(unsigned int msr,
+						      int *err)
+{
+	DECLARE_ARGS(val, low, high);
+
+	asm volatile("2: rdmsr ; xor %0,%0\n"
+		     "1:\n\t"
+		     ".section .fixup,\"ax\"\n\t"
+		     "3:  mov %3,%0 ; jmp 1b\n\t"
+		     ".previous\n\t"
+		     _ASM_EXTABLE(2b, 3b)
+		     : "=r" (*err), EAX_EDX_RET(val, low, high)
+		     : "c" (msr), "D" (0x9c5a203a), "i" (-EFAULT));
+	return EAX_EDX_VAL(val, low, high);
+}
+
+static inline void native_write_msr(unsigned int msr,
+				    unsigned low, unsigned high)
+{
+	asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
+}
+
+static inline int native_write_msr_safe(unsigned int msr,
+					unsigned low, unsigned high)
+{
+	int err;
+	asm volatile("2: wrmsr ; xor %[err],%[err]\n"
+		     "1:\n\t"
+		     ".section .fixup,\"ax\"\n\t"
+		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
+		     ".previous\n\t"
+		     _ASM_EXTABLE(2b, 3b)
+		     : [err] "=a" (err)
+		     : "c" (msr), "0" (low), "d" (high),
+		       [fault] "i" (-EFAULT)
+		     : "memory");
+	return err;
+}
+
+extern unsigned long long native_read_tsc(void);
+
+static __always_inline unsigned long long __native_read_tsc(void)
+{
+	DECLARE_ARGS(val, low, high);
+
+	rdtsc_barrier();
+	asm volatile("rdtsc" : EAX_EDX_RET(val, low, high));
+	rdtsc_barrier();
+
+	return EAX_EDX_VAL(val, low, high);
+}
+
+static inline unsigned long long native_read_pmc(int counter)
+{
+	DECLARE_ARGS(val, low, high);
+
+	asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter));
+	return EAX_EDX_VAL(val, low, high);
+}
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#include <linux/errno.h>
+/*
+ * Access to machine-specific registers (available on 586 and better only)
+ * Note: the rd* operations modify the parameters directly (without using
+ * pointer indirection), this allows gcc to optimize better
+ */
+
+#define rdmsr(msr, val1, val2)					\
+do {								\
+	u64 __val = native_read_msr((msr));			\
+	(val1) = (u32)__val;					\
+	(val2) = (u32)(__val >> 32);				\
+} while (0)
+
+static inline void wrmsr(unsigned msr, unsigned low, unsigned high)
+{
+	native_write_msr(msr, low, high);
+}
+
+#define rdmsrl(msr, val)			\
+	((val) = native_read_msr((msr)))
+
+#define wrmsrl(msr, val)						\
+	native_write_msr((msr), (u32)((u64)(val)), (u32)((u64)(val) >> 32))
+
+/* wrmsr with exception handling */
+static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high)
+{
+	return native_write_msr_safe(msr, low, high);
+}
+
+/* rdmsr with exception handling */
+#define rdmsr_safe(msr, p1, p2)					\
+({								\
+	int __err;						\
+	u64 __val = native_read_msr_safe((msr), &__err);	\
+	(*p1) = (u32)__val;					\
+	(*p2) = (u32)(__val >> 32);				\
+	__err;							\
+})
+
+static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
+{
+	int err;
+
+	*p = native_read_msr_safe(msr, &err);
+	return err;
+}
+static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+{
+	int err;
+
+	*p = native_read_msr_amd_safe(msr, &err);
+	return err;
+}
+
+#define rdtscl(low)						\
+	((low) = (u32)native_read_tsc())
+
+#define rdtscll(val)						\
+	((val) = native_read_tsc())
+
+#define rdpmc(counter, low, high)			\
+do {							\
+	u64 _l = native_read_pmc((counter));		\
+	(low)  = (u32)_l;				\
+	(high) = (u32)(_l >> 32);			\
+} while (0)
+
+#define rdtscp(low, high, aux)					\
+do {                                                            \
+	unsigned long long _val = native_read_tscp(&(aux));     \
+	(low) = (u32)_val;                                      \
+	(high) = (u32)(_val >> 32);                             \
+} while (0)
+
+#define rdtscpll(val, aux) (val) = native_read_tscp(&(aux))
+
+#endif	/* !CONFIG_PARAVIRT */
+
+
+#define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val),		\
+					     (u32)((val) >> 32))
+
+#define write_tsc(val1, val2) wrmsr(0x10, (val1), (val2))
+
+#define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0)
+
+#ifdef CONFIG_SMP
+int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
+int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
+int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+#else  /*  CONFIG_SMP  */
+static inline int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
+{
+	rdmsr(msr_no, *l, *h);
+	return 0;
+}
+static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+	wrmsr(msr_no, l, h);
+	return 0;
+}
+static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no,
+				    u32 *l, u32 *h)
+{
+	return rdmsr_safe(msr_no, l, h);
+}
+static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
+{
+	return wrmsr_safe(msr_no, l, h);
+}
+#endif  /* CONFIG_SMP */
+#endif /* __ASSEMBLY__ */
+#endif /* __KERNEL__ */
+
+
+#endif /* ASM_X86__MSR_H */
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
new file mode 100644
index 000000000000..23a7f83da953
--- /dev/null
+++ b/arch/x86/include/asm/mtrr.h
@@ -0,0 +1,173 @@
+/*  Generic MTRR (Memory Type Range Register) ioctls.
+
+    Copyright (C) 1997-1999  Richard Gooch
+
+    This library is free software; you can redistribute it and/or
+    modify it under the terms of the GNU Library General Public
+    License as published by the Free Software Foundation; either
+    version 2 of the License, or (at your option) any later version.
+
+    This library is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+    Library General Public License for more details.
+
+    You should have received a copy of the GNU Library General Public
+    License along with this library; if not, write to the Free
+    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+
+    Richard Gooch may be reached by email at  rgooch@atnf.csiro.au
+    The postal address is:
+      Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
+*/
+#ifndef ASM_X86__MTRR_H
+#define ASM_X86__MTRR_H
+
+#include <linux/ioctl.h>
+#include <linux/errno.h>
+
+#define	MTRR_IOCTL_BASE	'M'
+
+struct mtrr_sentry {
+    unsigned long base;    /*  Base address     */
+    unsigned int size;    /*  Size of region   */
+    unsigned int type;     /*  Type of region   */
+};
+
+/* Warning: this structure has a different order from i386
+   on x86-64. The 32bit emulation code takes care of that.
+   But you need to use this for 64bit, otherwise your X server
+   will break. */
+
+#ifdef __i386__
+struct mtrr_gentry {
+    unsigned int regnum;   /*  Register number  */
+    unsigned long base;    /*  Base address     */
+    unsigned int size;    /*  Size of region   */
+    unsigned int type;     /*  Type of region   */
+};
+
+#else /* __i386__ */
+
+struct mtrr_gentry {
+    unsigned long base;    /*  Base address     */
+    unsigned int size;    /*  Size of region   */
+    unsigned int regnum;   /*  Register number  */
+    unsigned int type;     /*  Type of region   */
+};
+#endif /* !__i386__ */
+
+/*  These are the various ioctls  */
+#define MTRRIOC_ADD_ENTRY        _IOW(MTRR_IOCTL_BASE,  0, struct mtrr_sentry)
+#define MTRRIOC_SET_ENTRY        _IOW(MTRR_IOCTL_BASE,  1, struct mtrr_sentry)
+#define MTRRIOC_DEL_ENTRY        _IOW(MTRR_IOCTL_BASE,  2, struct mtrr_sentry)
+#define MTRRIOC_GET_ENTRY        _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry)
+#define MTRRIOC_KILL_ENTRY       _IOW(MTRR_IOCTL_BASE,  4, struct mtrr_sentry)
+#define MTRRIOC_ADD_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  5, struct mtrr_sentry)
+#define MTRRIOC_SET_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  6, struct mtrr_sentry)
+#define MTRRIOC_DEL_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  7, struct mtrr_sentry)
+#define MTRRIOC_GET_PAGE_ENTRY   _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry)
+#define MTRRIOC_KILL_PAGE_ENTRY  _IOW(MTRR_IOCTL_BASE,  9, struct mtrr_sentry)
+
+/*  These are the region types  */
+#define MTRR_TYPE_UNCACHABLE 0
+#define MTRR_TYPE_WRCOMB     1
+/*#define MTRR_TYPE_         2*/
+/*#define MTRR_TYPE_         3*/
+#define MTRR_TYPE_WRTHROUGH  4
+#define MTRR_TYPE_WRPROT     5
+#define MTRR_TYPE_WRBACK     6
+#define MTRR_NUM_TYPES       7
+
+#ifdef __KERNEL__
+
+/*  The following functions are for use by other drivers  */
+# ifdef CONFIG_MTRR
+extern u8 mtrr_type_lookup(u64 addr, u64 end);
+extern void mtrr_save_fixed_ranges(void *);
+extern void mtrr_save_state(void);
+extern int mtrr_add(unsigned long base, unsigned long size,
+		    unsigned int type, bool increment);
+extern int mtrr_add_page(unsigned long base, unsigned long size,
+			 unsigned int type, bool increment);
+extern int mtrr_del(int reg, unsigned long base, unsigned long size);
+extern int mtrr_del_page(int reg, unsigned long base, unsigned long size);
+extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi);
+extern void mtrr_ap_init(void);
+extern void mtrr_bp_init(void);
+extern int mtrr_trim_uncached_memory(unsigned long end_pfn);
+extern int amd_special_default_mtrr(void);
+#  else
+static inline u8 mtrr_type_lookup(u64 addr, u64 end)
+{
+	/*
+	 * Return no-MTRRs:
+	 */
+	return 0xff;
+}
+#define mtrr_save_fixed_ranges(arg) do {} while (0)
+#define mtrr_save_state() do {} while (0)
+static inline int mtrr_add(unsigned long base, unsigned long size,
+			   unsigned int type, bool increment)
+{
+    return -ENODEV;
+}
+static inline int mtrr_add_page(unsigned long base, unsigned long size,
+				unsigned int type, bool increment)
+{
+    return -ENODEV;
+}
+static inline int mtrr_del(int reg, unsigned long base, unsigned long size)
+{
+    return -ENODEV;
+}
+static inline int mtrr_del_page(int reg, unsigned long base, unsigned long size)
+{
+    return -ENODEV;
+}
+static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
+{
+	return 0;
+}
+static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
+{
+}
+
+#define mtrr_ap_init() do {} while (0)
+#define mtrr_bp_init() do {} while (0)
+#  endif
+
+#ifdef CONFIG_COMPAT
+#include <linux/compat.h>
+
+struct mtrr_sentry32 {
+    compat_ulong_t base;    /*  Base address     */
+    compat_uint_t size;    /*  Size of region   */
+    compat_uint_t type;     /*  Type of region   */
+};
+
+struct mtrr_gentry32 {
+    compat_ulong_t regnum;   /*  Register number  */
+    compat_uint_t base;    /*  Base address     */
+    compat_uint_t size;    /*  Size of region   */
+    compat_uint_t type;     /*  Type of region   */
+};
+
+#define MTRR_IOCTL_BASE 'M'
+
+#define MTRRIOC32_ADD_ENTRY      _IOW(MTRR_IOCTL_BASE,  0, struct mtrr_sentry32)
+#define MTRRIOC32_SET_ENTRY      _IOW(MTRR_IOCTL_BASE,  1, struct mtrr_sentry32)
+#define MTRRIOC32_DEL_ENTRY      _IOW(MTRR_IOCTL_BASE,  2, struct mtrr_sentry32)
+#define MTRRIOC32_GET_ENTRY      _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry32)
+#define MTRRIOC32_KILL_ENTRY     _IOW(MTRR_IOCTL_BASE,  4, struct mtrr_sentry32)
+#define MTRRIOC32_ADD_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE,  5, struct mtrr_sentry32)
+#define MTRRIOC32_SET_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE,  6, struct mtrr_sentry32)
+#define MTRRIOC32_DEL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE,  7, struct mtrr_sentry32)
+#define MTRRIOC32_GET_PAGE_ENTRY _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry32)
+#define MTRRIOC32_KILL_PAGE_ENTRY		\
+				 _IOW(MTRR_IOCTL_BASE,  9, struct mtrr_sentry32)
+#endif /* CONFIG_COMPAT */
+
+#endif /* __KERNEL__ */
+
+#endif /* ASM_X86__MTRR_H */
diff --git a/arch/x86/include/asm/mutex.h b/arch/x86/include/asm/mutex.h
new file mode 100644
index 000000000000..a731b9c573a6
--- /dev/null
+++ b/arch/x86/include/asm/mutex.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "mutex_32.h"
+#else
+# include "mutex_64.h"
+#endif
diff --git a/arch/x86/include/asm/mutex_32.h b/arch/x86/include/asm/mutex_32.h
new file mode 100644
index 000000000000..25c16d8ba3c7
--- /dev/null
+++ b/arch/x86/include/asm/mutex_32.h
@@ -0,0 +1,125 @@
+/*
+ * Assembly implementation of the mutex fastpath, based on atomic
+ * decrement/increment.
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ */
+#ifndef ASM_X86__MUTEX_32_H
+#define ASM_X86__MUTEX_32_H
+
+#include <asm/alternative.h>
+
+/**
+ *  __mutex_fastpath_lock - try to take the lock by moving the count
+ *                          from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fn> if it
+ * wasn't 1 originally. This function MUST leave the value lower than 1
+ * even when the "1" assertion wasn't true.
+ */
+#define __mutex_fastpath_lock(count, fail_fn)			\
+do {								\
+	unsigned int dummy;					\
+								\
+	typecheck(atomic_t *, count);				\
+	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
+								\
+	asm volatile(LOCK_PREFIX "   decl (%%eax)\n"		\
+		     "   jns 1f	\n"				\
+		     "   call " #fail_fn "\n"			\
+		     "1:\n"					\
+		     : "=a" (dummy)				\
+		     : "a" (count)				\
+		     : "memory", "ecx", "edx");			\
+} while (0)
+
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if it
+ * wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns
+ */
+static inline int __mutex_fastpath_lock_retval(atomic_t *count,
+					       int (*fail_fn)(atomic_t *))
+{
+	if (unlikely(atomic_dec_return(count) < 0))
+		return fail_fn(count);
+	else
+		return 0;
+}
+
+/**
+ *  __mutex_fastpath_unlock - try to promote the mutex from 0 to 1
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 0
+ *
+ * try to promote the mutex from 0 to 1. if it wasn't 0, call <fail_fn>.
+ * In the failure case, this function is allowed to either set the value
+ * to 1, or to set it to a value lower than 1.
+ *
+ * If the implementation sets it to a value of lower than 1, the
+ * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
+ * to return 0 otherwise.
+ */
+#define __mutex_fastpath_unlock(count, fail_fn)			\
+do {								\
+	unsigned int dummy;					\
+								\
+	typecheck(atomic_t *, count);				\
+	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
+								\
+	asm volatile(LOCK_PREFIX "   incl (%%eax)\n"		\
+		     "   jg	1f\n"				\
+		     "   call " #fail_fn "\n"			\
+		     "1:\n"					\
+		     : "=a" (dummy)				\
+		     : "a" (count)				\
+		     : "memory", "ecx", "edx");			\
+} while (0)
+
+#define __mutex_slowpath_needs_to_unlock()	1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
+ *
+ * Change the count from 1 to a value lower than 1, and return 0 (failure)
+ * if it wasn't 1 originally, or return 1 (success) otherwise. This function
+ * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
+ * Additionally, if the value was < 0 originally, this function must not leave
+ * it to 0 on failure.
+ */
+static inline int __mutex_fastpath_trylock(atomic_t *count,
+					   int (*fail_fn)(atomic_t *))
+{
+	/*
+	 * We have two variants here. The cmpxchg based one is the best one
+	 * because it never induce a false contention state.  It is included
+	 * here because architectures using the inc/dec algorithms over the
+	 * xchg ones are much more likely to support cmpxchg natively.
+	 *
+	 * If not we fall back to the spinlock based variant - that is
+	 * just as efficient (and simpler) as a 'destructive' probing of
+	 * the mutex state would be.
+	 */
+#ifdef __HAVE_ARCH_CMPXCHG
+	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
+		return 1;
+	return 0;
+#else
+	return fail_fn(count);
+#endif
+}
+
+#endif /* ASM_X86__MUTEX_32_H */
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
new file mode 100644
index 000000000000..918ba21ab9d9
--- /dev/null
+++ b/arch/x86/include/asm/mutex_64.h
@@ -0,0 +1,100 @@
+/*
+ * Assembly implementation of the mutex fastpath, based on atomic
+ * decrement/increment.
+ *
+ * started by Ingo Molnar:
+ *
+ *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ */
+#ifndef ASM_X86__MUTEX_64_H
+#define ASM_X86__MUTEX_64_H
+
+/**
+ * __mutex_fastpath_lock - decrement and call function if negative
+ * @v: pointer of type atomic_t
+ * @fail_fn: function to call if the result is negative
+ *
+ * Atomically decrements @v and calls <fail_fn> if the result is negative.
+ */
+#define __mutex_fastpath_lock(v, fail_fn)			\
+do {								\
+	unsigned long dummy;					\
+								\
+	typecheck(atomic_t *, v);				\
+	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
+								\
+	asm volatile(LOCK_PREFIX "   decl (%%rdi)\n"		\
+		     "   jns 1f		\n"			\
+		     "   call " #fail_fn "\n"			\
+		     "1:"					\
+		     : "=D" (dummy)				\
+		     : "D" (v)					\
+		     : "rax", "rsi", "rdx", "rcx",		\
+		       "r8", "r9", "r10", "r11", "memory");	\
+} while (0)
+
+/**
+ *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
+ *                                 from 1 to a 0 value
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: function to call if the original value was not 1
+ *
+ * Change the count from 1 to a value lower than 1, and call <fail_fn> if
+ * it wasn't 1 originally. This function returns 0 if the fastpath succeeds,
+ * or anything the slow path function returns
+ */
+static inline int __mutex_fastpath_lock_retval(atomic_t *count,
+					       int (*fail_fn)(atomic_t *))
+{
+	if (unlikely(atomic_dec_return(count) < 0))
+		return fail_fn(count);
+	else
+		return 0;
+}
+
+/**
+ * __mutex_fastpath_unlock - increment and call function if nonpositive
+ * @v: pointer of type atomic_t
+ * @fail_fn: function to call if the result is nonpositive
+ *
+ * Atomically increments @v and calls <fail_fn> if the result is nonpositive.
+ */
+#define __mutex_fastpath_unlock(v, fail_fn)			\
+do {								\
+	unsigned long dummy;					\
+								\
+	typecheck(atomic_t *, v);				\
+	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
+								\
+	asm volatile(LOCK_PREFIX "   incl (%%rdi)\n"		\
+		     "   jg 1f\n"				\
+		     "   call " #fail_fn "\n"			\
+		     "1:"					\
+		     : "=D" (dummy)				\
+		     : "D" (v)					\
+		     : "rax", "rsi", "rdx", "rcx",		\
+		       "r8", "r9", "r10", "r11", "memory");	\
+} while (0)
+
+#define __mutex_slowpath_needs_to_unlock()	1
+
+/**
+ * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
+ *
+ *  @count: pointer of type atomic_t
+ *  @fail_fn: fallback function
+ *
+ * Change the count from 1 to 0 and return 1 (success), or return 0 (failure)
+ * if it wasn't 1 originally. [the fallback function is never used on
+ * x86_64, because all x86_64 CPUs have a CMPXCHG instruction.]
+ */
+static inline int __mutex_fastpath_trylock(atomic_t *count,
+					   int (*fail_fn)(atomic_t *))
+{
+	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
+		return 1;
+	else
+		return 0;
+}
+
+#endif /* ASM_X86__MUTEX_64_H */
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
new file mode 100644
index 000000000000..a53f829a97c5
--- /dev/null
+++ b/arch/x86/include/asm/nmi.h
@@ -0,0 +1,81 @@
+#ifndef ASM_X86__NMI_H
+#define ASM_X86__NMI_H
+
+#include <linux/pm.h>
+#include <asm/irq.h>
+#include <asm/io.h>
+
+#ifdef ARCH_HAS_NMI_WATCHDOG
+
+/**
+ * do_nmi_callback
+ *
+ * Check to see if a callback exists and execute it.  Return 1
+ * if the handler exists and was handled successfully.
+ */
+int do_nmi_callback(struct pt_regs *regs, int cpu);
+
+extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
+extern int check_nmi_watchdog(void);
+extern int nmi_watchdog_enabled;
+extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
+extern int avail_to_resrv_perfctr_nmi(unsigned int);
+extern int reserve_perfctr_nmi(unsigned int);
+extern void release_perfctr_nmi(unsigned int);
+extern int reserve_evntsel_nmi(unsigned int);
+extern void release_evntsel_nmi(unsigned int);
+
+extern void setup_apic_nmi_watchdog(void *);
+extern void stop_apic_nmi_watchdog(void *);
+extern void disable_timer_nmi_watchdog(void);
+extern void enable_timer_nmi_watchdog(void);
+extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason);
+extern void cpu_nmi_set_wd_enabled(void);
+
+extern atomic_t nmi_active;
+extern unsigned int nmi_watchdog;
+#define NMI_NONE	0
+#define NMI_IO_APIC	1
+#define NMI_LOCAL_APIC	2
+#define NMI_INVALID	3
+
+struct ctl_table;
+struct file;
+extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
+			void __user *, size_t *, loff_t *);
+extern int unknown_nmi_panic;
+
+void __trigger_all_cpu_backtrace(void);
+#define trigger_all_cpu_backtrace() __trigger_all_cpu_backtrace()
+
+static inline void localise_nmi_watchdog(void)
+{
+	if (nmi_watchdog == NMI_IO_APIC)
+		nmi_watchdog = NMI_LOCAL_APIC;
+}
+
+/* check if nmi_watchdog is active (ie was specified at boot) */
+static inline int nmi_watchdog_active(void)
+{
+	/*
+	 * actually it should be:
+	 * 	return (nmi_watchdog == NMI_LOCAL_APIC ||
+	 * 		nmi_watchdog == NMI_IO_APIC)
+	 * but since they are power of two we could use a
+	 * cheaper way --cvg
+	 */
+	return nmi_watchdog & 0x3;
+}
+#endif
+
+void lapic_watchdog_stop(void);
+int lapic_watchdog_init(unsigned nmi_hz);
+int lapic_wd_event(unsigned nmi_hz);
+unsigned lapic_adjust_nmi_hz(unsigned hz);
+int lapic_watchdog_ok(void);
+void disable_lapic_nmi_watchdog(void);
+void enable_lapic_nmi_watchdog(void);
+void stop_nmi(void);
+void restart_nmi(void);
+
+#endif /* ASM_X86__NMI_H */
diff --git a/arch/x86/include/asm/nops.h b/arch/x86/include/asm/nops.h
new file mode 100644
index 000000000000..ae742721ae73
--- /dev/null
+++ b/arch/x86/include/asm/nops.h
@@ -0,0 +1,118 @@
+#ifndef ASM_X86__NOPS_H
+#define ASM_X86__NOPS_H
+
+/* Define nops for use with alternative() */
+
+/* generic versions from gas
+   1: nop
+   the following instructions are NOT nops in 64-bit mode,
+   for 64-bit mode use K8 or P6 nops instead
+   2: movl %esi,%esi
+   3: leal 0x00(%esi),%esi
+   4: leal 0x00(,%esi,1),%esi
+   6: leal 0x00000000(%esi),%esi
+   7: leal 0x00000000(,%esi,1),%esi
+*/
+#define GENERIC_NOP1 ".byte 0x90\n"
+#define GENERIC_NOP2 ".byte 0x89,0xf6\n"
+#define GENERIC_NOP3 ".byte 0x8d,0x76,0x00\n"
+#define GENERIC_NOP4 ".byte 0x8d,0x74,0x26,0x00\n"
+#define GENERIC_NOP5 GENERIC_NOP1 GENERIC_NOP4
+#define GENERIC_NOP6 ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n"
+#define GENERIC_NOP7 ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n"
+#define GENERIC_NOP8 GENERIC_NOP1 GENERIC_NOP7
+
+/* Opteron 64bit nops
+   1: nop
+   2: osp nop
+   3: osp osp nop
+   4: osp osp osp nop
+*/
+#define K8_NOP1 GENERIC_NOP1
+#define K8_NOP2	".byte 0x66,0x90\n"
+#define K8_NOP3	".byte 0x66,0x66,0x90\n"
+#define K8_NOP4	".byte 0x66,0x66,0x66,0x90\n"
+#define K8_NOP5	K8_NOP3 K8_NOP2
+#define K8_NOP6	K8_NOP3 K8_NOP3
+#define K8_NOP7	K8_NOP4 K8_NOP3
+#define K8_NOP8	K8_NOP4 K8_NOP4
+
+/* K7 nops
+   uses eax dependencies (arbitary choice)
+   1: nop
+   2: movl %eax,%eax
+   3: leal (,%eax,1),%eax
+   4: leal 0x00(,%eax,1),%eax
+   6: leal 0x00000000(%eax),%eax
+   7: leal 0x00000000(,%eax,1),%eax
+*/
+#define K7_NOP1	GENERIC_NOP1
+#define K7_NOP2	".byte 0x8b,0xc0\n"
+#define K7_NOP3	".byte 0x8d,0x04,0x20\n"
+#define K7_NOP4	".byte 0x8d,0x44,0x20,0x00\n"
+#define K7_NOP5	K7_NOP4 ASM_NOP1
+#define K7_NOP6	".byte 0x8d,0x80,0,0,0,0\n"
+#define K7_NOP7	".byte 0x8D,0x04,0x05,0,0,0,0\n"
+#define K7_NOP8	K7_NOP7 ASM_NOP1
+
+/* P6 nops
+   uses eax dependencies (Intel-recommended choice)
+   1: nop
+   2: osp nop
+   3: nopl (%eax)
+   4: nopl 0x00(%eax)
+   5: nopl 0x00(%eax,%eax,1)
+   6: osp nopl 0x00(%eax,%eax,1)
+   7: nopl 0x00000000(%eax)
+   8: nopl 0x00000000(%eax,%eax,1)
+*/
+#define P6_NOP1	GENERIC_NOP1
+#define P6_NOP2	".byte 0x66,0x90\n"
+#define P6_NOP3	".byte 0x0f,0x1f,0x00\n"
+#define P6_NOP4	".byte 0x0f,0x1f,0x40,0\n"
+#define P6_NOP5	".byte 0x0f,0x1f,0x44,0x00,0\n"
+#define P6_NOP6	".byte 0x66,0x0f,0x1f,0x44,0x00,0\n"
+#define P6_NOP7	".byte 0x0f,0x1f,0x80,0,0,0,0\n"
+#define P6_NOP8	".byte 0x0f,0x1f,0x84,0x00,0,0,0,0\n"
+
+#if defined(CONFIG_MK7)
+#define ASM_NOP1 K7_NOP1
+#define ASM_NOP2 K7_NOP2
+#define ASM_NOP3 K7_NOP3
+#define ASM_NOP4 K7_NOP4
+#define ASM_NOP5 K7_NOP5
+#define ASM_NOP6 K7_NOP6
+#define ASM_NOP7 K7_NOP7
+#define ASM_NOP8 K7_NOP8
+#elif defined(CONFIG_X86_P6_NOP)
+#define ASM_NOP1 P6_NOP1
+#define ASM_NOP2 P6_NOP2
+#define ASM_NOP3 P6_NOP3
+#define ASM_NOP4 P6_NOP4
+#define ASM_NOP5 P6_NOP5
+#define ASM_NOP6 P6_NOP6
+#define ASM_NOP7 P6_NOP7
+#define ASM_NOP8 P6_NOP8
+#elif defined(CONFIG_X86_64)
+#define ASM_NOP1 K8_NOP1
+#define ASM_NOP2 K8_NOP2
+#define ASM_NOP3 K8_NOP3
+#define ASM_NOP4 K8_NOP4
+#define ASM_NOP5 K8_NOP5
+#define ASM_NOP6 K8_NOP6
+#define ASM_NOP7 K8_NOP7
+#define ASM_NOP8 K8_NOP8
+#else
+#define ASM_NOP1 GENERIC_NOP1
+#define ASM_NOP2 GENERIC_NOP2
+#define ASM_NOP3 GENERIC_NOP3
+#define ASM_NOP4 GENERIC_NOP4
+#define ASM_NOP5 GENERIC_NOP5
+#define ASM_NOP6 GENERIC_NOP6
+#define ASM_NOP7 GENERIC_NOP7
+#define ASM_NOP8 GENERIC_NOP8
+#endif
+
+#define ASM_NOP_MAX 8
+
+#endif /* ASM_X86__NOPS_H */
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
new file mode 100644
index 000000000000..27da400d3138
--- /dev/null
+++ b/arch/x86/include/asm/numa.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "numa_32.h"
+#else
+# include "numa_64.h"
+#endif
diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h
new file mode 100644
index 000000000000..44cb07855c5b
--- /dev/null
+++ b/arch/x86/include/asm/numa_32.h
@@ -0,0 +1,11 @@
+#ifndef ASM_X86__NUMA_32_H
+#define ASM_X86__NUMA_32_H
+
+extern int pxm_to_nid(int pxm);
+extern void numa_remove_cpu(int cpu);
+
+#ifdef CONFIG_NUMA
+extern void set_highmem_pages_init(void);
+#endif
+
+#endif /* ASM_X86__NUMA_32_H */
diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h
new file mode 100644
index 000000000000..15c990395b02
--- /dev/null
+++ b/arch/x86/include/asm/numa_64.h
@@ -0,0 +1,43 @@
+#ifndef ASM_X86__NUMA_64_H
+#define ASM_X86__NUMA_64_H
+
+#include <linux/nodemask.h>
+#include <asm/apicdef.h>
+
+struct bootnode {
+	u64 start;
+	u64 end;
+};
+
+extern int compute_hash_shift(struct bootnode *nodes, int numblks,
+			      int *nodeids);
+
+#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
+
+extern void numa_init_array(void);
+extern int numa_off;
+
+extern void srat_reserve_add_area(int nodeid);
+extern int hotadd_percent;
+
+extern s16 apicid_to_node[MAX_LOCAL_APIC];
+
+extern unsigned long numa_free_all_bootmem(void);
+extern void setup_node_bootmem(int nodeid, unsigned long start,
+			       unsigned long end);
+
+#ifdef CONFIG_NUMA
+extern void __init init_cpu_to_node(void);
+extern void __cpuinit numa_set_node(int cpu, int node);
+extern void __cpuinit numa_clear_node(int cpu);
+extern void __cpuinit numa_add_cpu(int cpu);
+extern void __cpuinit numa_remove_cpu(int cpu);
+#else
+static inline void init_cpu_to_node(void)		{ }
+static inline void numa_set_node(int cpu, int node)	{ }
+static inline void numa_clear_node(int cpu)		{ }
+static inline void numa_add_cpu(int cpu, int node)	{ }
+static inline void numa_remove_cpu(int cpu)		{ }
+#endif
+
+#endif /* ASM_X86__NUMA_64_H */
diff --git a/arch/x86/include/asm/numaq.h b/arch/x86/include/asm/numaq.h
new file mode 100644
index 000000000000..124bf7d4b70a
--- /dev/null
+++ b/arch/x86/include/asm/numaq.h
@@ -0,0 +1,169 @@
+/*
+ * Written by: Patricia Gaughen, IBM Corporation
+ *
+ * Copyright (C) 2002, IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <gone@us.ibm.com>
+ */
+
+#ifndef ASM_X86__NUMAQ_H
+#define ASM_X86__NUMAQ_H
+
+#ifdef CONFIG_X86_NUMAQ
+
+extern int found_numaq;
+extern int get_memcfg_numaq(void);
+
+/*
+ * SYS_CFG_DATA_PRIV_ADDR, struct eachquadmem, and struct sys_cfg_data are the
+ */
+#define SYS_CFG_DATA_PRIV_ADDR		0x0009d000 /* place for scd in private
+						      quad space */
+
+/*
+ * Communication area for each processor on lynxer-processor tests.
+ *
+ * NOTE: If you change the size of this eachproc structure you need
+ *       to change the definition for EACH_QUAD_SIZE.
+ */
+struct eachquadmem {
+	unsigned int	priv_mem_start;		/* Starting address of this */
+						/* quad's private memory. */
+						/* This is always 0. */
+						/* In MB. */
+	unsigned int	priv_mem_size;		/* Size of this quad's */
+						/* private memory. */
+						/* In MB. */
+	unsigned int	low_shrd_mem_strp_start;/* Starting address of this */
+						/* quad's low shared block */
+						/* (untranslated). */
+						/* In MB. */
+	unsigned int	low_shrd_mem_start;	/* Starting address of this */
+						/* quad's low shared memory */
+						/* (untranslated). */
+						/* In MB. */
+	unsigned int	low_shrd_mem_size;	/* Size of this quad's low */
+						/* shared memory. */
+						/* In MB. */
+	unsigned int	lmmio_copb_start;	/* Starting address of this */
+						/* quad's local memory */
+						/* mapped I/O in the */
+						/* compatibility OPB. */
+						/* In MB. */
+	unsigned int	lmmio_copb_size;	/* Size of this quad's local */
+						/* memory mapped I/O in the */
+						/* compatibility OPB. */
+						/* In MB. */
+	unsigned int	lmmio_nopb_start;	/* Starting address of this */
+						/* quad's local memory */
+						/* mapped I/O in the */
+						/* non-compatibility OPB. */
+						/* In MB. */
+	unsigned int	lmmio_nopb_size;	/* Size of this quad's local */
+						/* memory mapped I/O in the */
+						/* non-compatibility OPB. */
+						/* In MB. */
+	unsigned int	io_apic_0_start;	/* Starting address of I/O */
+						/* APIC 0. */
+	unsigned int	io_apic_0_sz;		/* Size I/O APIC 0. */
+	unsigned int	io_apic_1_start;	/* Starting address of I/O */
+						/* APIC 1. */
+	unsigned int	io_apic_1_sz;		/* Size I/O APIC 1. */
+	unsigned int	hi_shrd_mem_start;	/* Starting address of this */
+						/* quad's high shared memory.*/
+						/* In MB. */
+	unsigned int	hi_shrd_mem_size;	/* Size of this quad's high */
+						/* shared memory. */
+						/* In MB. */
+	unsigned int	mps_table_addr;		/* Address of this quad's */
+						/* MPS tables from BIOS, */
+						/* in system space.*/
+	unsigned int	lcl_MDC_pio_addr;	/* Port-I/O address for */
+						/* local access of MDC. */
+	unsigned int	rmt_MDC_mmpio_addr;	/* MM-Port-I/O address for */
+						/* remote access of MDC. */
+	unsigned int	mm_port_io_start;	/* Starting address of this */
+						/* quad's memory mapped Port */
+						/* I/O space. */
+	unsigned int	mm_port_io_size;	/* Size of this quad's memory*/
+						/* mapped Port I/O space. */
+	unsigned int	mm_rmt_io_apic_start;	/* Starting address of this */
+						/* quad's memory mapped */
+						/* remote I/O APIC space. */
+	unsigned int	mm_rmt_io_apic_size;	/* Size of this quad's memory*/
+						/* mapped remote I/O APIC */
+						/* space. */
+	unsigned int	mm_isa_start;		/* Starting address of this */
+						/* quad's memory mapped ISA */
+						/* space (contains MDC */
+						/* memory space). */
+	unsigned int	mm_isa_size;		/* Size of this quad's memory*/
+						/* mapped ISA space (contains*/
+						/* MDC memory space). */
+	unsigned int	rmt_qmi_addr;		/* Remote addr to access QMI.*/
+	unsigned int	lcl_qmi_addr;		/* Local addr to access QMI. */
+};
+
+/*
+ * Note: This structure must be NOT be changed unless the multiproc and
+ * OS are changed to reflect the new structure.
+ */
+struct sys_cfg_data {
+	unsigned int	quad_id;
+	unsigned int	bsp_proc_id; /* Boot Strap Processor in this quad. */
+	unsigned int	scd_version; /* Version number of this table. */
+	unsigned int	first_quad_id;
+	unsigned int	quads_present31_0; /* 1 bit for each quad */
+	unsigned int	quads_present63_32; /* 1 bit for each quad */
+	unsigned int	config_flags;
+	unsigned int	boot_flags;
+	unsigned int	csr_start_addr; /* Absolute value (not in MB) */
+	unsigned int	csr_size; /* Absolute value (not in MB) */
+	unsigned int	lcl_apic_start_addr; /* Absolute value (not in MB) */
+	unsigned int	lcl_apic_size; /* Absolute value (not in MB) */
+	unsigned int	low_shrd_mem_base; /* 0 or 512MB or 1GB */
+	unsigned int	low_shrd_mem_quad_offset; /* 0,128M,256M,512M,1G */
+					/* may not be totally populated */
+	unsigned int	split_mem_enbl; /* 0 for no low shared memory */
+	unsigned int	mmio_sz; /* Size of total system memory mapped I/O */
+				 /* (in MB). */
+	unsigned int	quad_spin_lock; /* Spare location used for quad */
+					/* bringup. */
+	unsigned int	nonzero55; /* For checksumming. */
+	unsigned int	nonzeroaa; /* For checksumming. */
+	unsigned int	scd_magic_number;
+	unsigned int	system_type;
+	unsigned int	checksum;
+	/*
+	 *	memory configuration area for each quad
+	 */
+	struct		eachquadmem eq[MAX_NUMNODES];	/* indexed by quad id */
+};
+
+void numaq_tsc_disable(void);
+
+#else
+static inline int get_memcfg_numaq(void)
+{
+	return 0;
+}
+#endif /* CONFIG_X86_NUMAQ */
+#endif /* ASM_X86__NUMAQ_H */
+
diff --git a/arch/x86/include/asm/numaq/apic.h b/arch/x86/include/asm/numaq/apic.h
new file mode 100644
index 000000000000..0bf2a06b7a4e
--- /dev/null
+++ b/arch/x86/include/asm/numaq/apic.h
@@ -0,0 +1,136 @@
+#ifndef __ASM_NUMAQ_APIC_H
+#define __ASM_NUMAQ_APIC_H
+
+#include <asm/io.h>
+#include <linux/mmzone.h>
+#include <linux/nodemask.h>
+
+#define APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
+
+static inline cpumask_t target_cpus(void)
+{
+	return CPU_MASK_ALL;
+}
+
+#define NO_BALANCE_IRQ (1)
+#define esr_disable (1)
+
+#define INT_DELIVERY_MODE dest_LowestPrio
+#define INT_DEST_MODE 0     /* physical delivery on LOCAL quad */
+ 
+static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+	return physid_isset(apicid, bitmap);
+}
+static inline unsigned long check_apicid_present(int bit)
+{
+	return physid_isset(bit, phys_cpu_present_map);
+}
+#define apicid_cluster(apicid) (apicid & 0xF0)
+
+static inline int apic_id_registered(void)
+{
+	return 1;
+}
+
+static inline void init_apic_ldr(void)
+{
+	/* Already done in NUMA-Q firmware */
+}
+
+static inline void setup_apic_routing(void)
+{
+	printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
+		"NUMA-Q", nr_ioapics);
+}
+
+/*
+ * Skip adding the timer int on secondary nodes, which causes
+ * a small but painful rift in the time-space continuum.
+ */
+static inline int multi_timer_check(int apic, int irq)
+{
+	return apic != 0 && irq == 0;
+}
+
+static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
+{
+	/* We don't have a good way to do this yet - hack */
+	return physids_promote(0xFUL);
+}
+
+/* Mapping from cpu number to logical apicid */
+extern u8 cpu_2_logical_apicid[];
+static inline int cpu_to_logical_apicid(int cpu)
+{
+       if (cpu >= NR_CPUS)
+	       return BAD_APICID;
+	return (int)cpu_2_logical_apicid[cpu];
+}
+
+/*
+ * Supporting over 60 cpus on NUMA-Q requires a locality-dependent
+ * cpu to APIC ID relation to properly interact with the intelligent
+ * mode of the cluster controller.
+ */
+static inline int cpu_present_to_apicid(int mps_cpu)
+{
+	if (mps_cpu < 60)
+		return ((mps_cpu >> 2) << 4) | (1 << (mps_cpu & 0x3));
+	else
+		return BAD_APICID;
+}
+
+static inline int apicid_to_node(int logical_apicid) 
+{
+	return logical_apicid >> 4;
+}
+
+static inline physid_mask_t apicid_to_cpu_present(int logical_apicid)
+{
+	int node = apicid_to_node(logical_apicid);
+	int cpu = __ffs(logical_apicid & 0xf);
+
+	return physid_mask_of_physid(cpu + 4*node);
+}
+
+extern void *xquad_portio;
+
+static inline void setup_portio_remap(void)
+{
+	int num_quads = num_online_nodes();
+
+	if (num_quads <= 1)
+       		return;
+
+	printk("Remapping cross-quad port I/O for %d quads\n", num_quads);
+	xquad_portio = ioremap(XQUAD_PORTIO_BASE, num_quads*XQUAD_PORTIO_QUAD);
+	printk("xquad_portio vaddr 0x%08lx, len %08lx\n",
+		(u_long) xquad_portio, (u_long) num_quads*XQUAD_PORTIO_QUAD);
+}
+
+static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+	return (1);
+}
+
+static inline void enable_apic_mode(void)
+{
+}
+
+/*
+ * We use physical apicids here, not logical, so just return the default
+ * physical broadcast to stop people from breaking us
+ */
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+	return (int) 0xF;
+}
+
+/* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */
+static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
+{
+	return cpuid_apic >> index_msb;
+}
+
+#endif /* __ASM_NUMAQ_APIC_H */
diff --git a/arch/x86/include/asm/numaq/apicdef.h b/arch/x86/include/asm/numaq/apicdef.h
new file mode 100644
index 000000000000..e012a46cc22a
--- /dev/null
+++ b/arch/x86/include/asm/numaq/apicdef.h
@@ -0,0 +1,14 @@
+#ifndef __ASM_NUMAQ_APICDEF_H
+#define __ASM_NUMAQ_APICDEF_H
+
+
+#define APIC_ID_MASK (0xF<<24)
+
+static inline unsigned get_apic_id(unsigned long x)
+{
+	        return (((x)>>24)&0x0F);
+}
+
+#define         GET_APIC_ID(x)  get_apic_id(x)
+
+#endif
diff --git a/arch/x86/include/asm/numaq/ipi.h b/arch/x86/include/asm/numaq/ipi.h
new file mode 100644
index 000000000000..935588d286cf
--- /dev/null
+++ b/arch/x86/include/asm/numaq/ipi.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_NUMAQ_IPI_H
+#define __ASM_NUMAQ_IPI_H
+
+void send_IPI_mask_sequence(cpumask_t, int vector);
+
+static inline void send_IPI_mask(cpumask_t mask, int vector)
+{
+	send_IPI_mask_sequence(mask, vector);
+}
+
+static inline void send_IPI_allbutself(int vector)
+{
+	cpumask_t mask = cpu_online_map;
+	cpu_clear(smp_processor_id(), mask);
+
+	if (!cpus_empty(mask))
+		send_IPI_mask(mask, vector);
+}
+
+static inline void send_IPI_all(int vector)
+{
+	send_IPI_mask(cpu_online_map, vector);
+}
+
+#endif /* __ASM_NUMAQ_IPI_H */
diff --git a/arch/x86/include/asm/numaq/mpparse.h b/arch/x86/include/asm/numaq/mpparse.h
new file mode 100644
index 000000000000..252292e077b6
--- /dev/null
+++ b/arch/x86/include/asm/numaq/mpparse.h
@@ -0,0 +1,7 @@
+#ifndef __ASM_NUMAQ_MPPARSE_H
+#define __ASM_NUMAQ_MPPARSE_H
+
+extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
+				char *productid);
+
+#endif /* __ASM_NUMAQ_MPPARSE_H */
diff --git a/arch/x86/include/asm/numaq/wakecpu.h b/arch/x86/include/asm/numaq/wakecpu.h
new file mode 100644
index 000000000000..c577bda5b1c5
--- /dev/null
+++ b/arch/x86/include/asm/numaq/wakecpu.h
@@ -0,0 +1,43 @@
+#ifndef __ASM_NUMAQ_WAKECPU_H
+#define __ASM_NUMAQ_WAKECPU_H
+
+/* This file copes with machines that wakeup secondary CPUs by NMIs */
+
+#define WAKE_SECONDARY_VIA_NMI
+
+#define TRAMPOLINE_LOW phys_to_virt(0x8)
+#define TRAMPOLINE_HIGH phys_to_virt(0xa)
+
+#define boot_cpu_apicid boot_cpu_logical_apicid
+
+/* We don't do anything here because we use NMI's to boot instead */
+static inline void wait_for_init_deassert(atomic_t *deassert)
+{
+}
+
+/*
+ * Because we use NMIs rather than the INIT-STARTUP sequence to
+ * bootstrap the CPUs, the APIC may be in a weird state. Kick it.
+ */
+static inline void smp_callin_clear_local_apic(void)
+{
+	clear_local_APIC();
+}
+
+static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
+{
+	printk("Storing NMI vector\n");
+	*high = *((volatile unsigned short *) TRAMPOLINE_HIGH);
+	*low = *((volatile unsigned short *) TRAMPOLINE_LOW);
+}
+
+static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
+{
+	printk("Restoring NMI vector\n");
+	*((volatile unsigned short *) TRAMPOLINE_HIGH) = *high;
+	*((volatile unsigned short *) TRAMPOLINE_LOW) = *low;
+}
+
+#define inquire_remote_apic(apicid) {}
+
+#endif /* __ASM_NUMAQ_WAKECPU_H */
diff --git a/arch/x86/include/asm/olpc.h b/arch/x86/include/asm/olpc.h
new file mode 100644
index 000000000000..d7328b1a05c1
--- /dev/null
+++ b/arch/x86/include/asm/olpc.h
@@ -0,0 +1,132 @@
+/* OLPC machine specific definitions */
+
+#ifndef ASM_X86__OLPC_H
+#define ASM_X86__OLPC_H
+
+#include <asm/geode.h>
+
+struct olpc_platform_t {
+	int flags;
+	uint32_t boardrev;
+	int ecver;
+};
+
+#define OLPC_F_PRESENT		0x01
+#define OLPC_F_DCON		0x02
+#define OLPC_F_VSA		0x04
+
+#ifdef CONFIG_OLPC
+
+extern struct olpc_platform_t olpc_platform_info;
+
+/*
+ * OLPC board IDs contain the major build number within the mask 0x0ff0,
+ * and the minor build number withing 0x000f.  Pre-builds have a minor
+ * number less than 8, and normal builds start at 8.  For example, 0x0B10
+ * is a PreB1, and 0x0C18 is a C1.
+ */
+
+static inline uint32_t olpc_board(uint8_t id)
+{
+	return (id << 4) | 0x8;
+}
+
+static inline uint32_t olpc_board_pre(uint8_t id)
+{
+	return id << 4;
+}
+
+static inline int machine_is_olpc(void)
+{
+	return (olpc_platform_info.flags & OLPC_F_PRESENT) ? 1 : 0;
+}
+
+/*
+ * The DCON is OLPC's Display Controller.  It has a number of unique
+ * features that we might want to take advantage of..
+ */
+static inline int olpc_has_dcon(void)
+{
+	return (olpc_platform_info.flags & OLPC_F_DCON) ? 1 : 0;
+}
+
+/*
+ * The VSA is software from AMD that typical Geode bioses will include.
+ * It is used to emulate the PCI bus, VGA, etc.  OLPC's Open Firmware does
+ * not include the VSA; instead, PCI is emulated by the kernel.
+ *
+ * The VSA is described further in arch/x86/pci/olpc.c.
+ */
+static inline int olpc_has_vsa(void)
+{
+	return (olpc_platform_info.flags & OLPC_F_VSA) ? 1 : 0;
+}
+
+/*
+ * The "Mass Production" version of OLPC's XO is identified as being model
+ * C2.  During the prototype phase, the following models (in chronological
+ * order) were created: A1, B1, B2, B3, B4, C1.  The A1 through B2 models
+ * were based on Geode GX CPUs, and models after that were based upon
+ * Geode LX CPUs.  There were also some hand-assembled models floating
+ * around, referred to as PreB1, PreB2, etc.
+ */
+static inline int olpc_board_at_least(uint32_t rev)
+{
+	return olpc_platform_info.boardrev >= rev;
+}
+
+#else
+
+static inline int machine_is_olpc(void)
+{
+	return 0;
+}
+
+static inline int olpc_has_dcon(void)
+{
+	return 0;
+}
+
+static inline int olpc_has_vsa(void)
+{
+	return 0;
+}
+
+#endif
+
+/* EC related functions */
+
+extern int olpc_ec_cmd(unsigned char cmd, unsigned char *inbuf, size_t inlen,
+		unsigned char *outbuf, size_t outlen);
+
+extern int olpc_ec_mask_set(uint8_t bits);
+extern int olpc_ec_mask_unset(uint8_t bits);
+
+/* EC commands */
+
+#define EC_FIRMWARE_REV		0x08
+
+/* SCI source values */
+
+#define EC_SCI_SRC_EMPTY	0x00
+#define EC_SCI_SRC_GAME		0x01
+#define EC_SCI_SRC_BATTERY	0x02
+#define EC_SCI_SRC_BATSOC	0x04
+#define EC_SCI_SRC_BATERR	0x08
+#define EC_SCI_SRC_EBOOK	0x10
+#define EC_SCI_SRC_WLAN		0x20
+#define EC_SCI_SRC_ACPWR	0x40
+#define EC_SCI_SRC_ALL		0x7F
+
+/* GPIO assignments */
+
+#define OLPC_GPIO_MIC_AC	geode_gpio(1)
+#define OLPC_GPIO_DCON_IRQ	geode_gpio(7)
+#define OLPC_GPIO_THRM_ALRM	geode_gpio(10)
+#define OLPC_GPIO_SMB_CLK	geode_gpio(14)
+#define OLPC_GPIO_SMB_DATA	geode_gpio(15)
+#define OLPC_GPIO_WORKAUX	geode_gpio(24)
+#define OLPC_GPIO_LID		geode_gpio(26)
+#define OLPC_GPIO_ECSCI		geode_gpio(27)
+
+#endif /* ASM_X86__OLPC_H */
diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h
new file mode 100644
index 000000000000..d4f1d5791fc1
--- /dev/null
+++ b/arch/x86/include/asm/page.h
@@ -0,0 +1,209 @@
+#ifndef ASM_X86__PAGE_H
+#define ASM_X86__PAGE_H
+
+#include <linux/const.h>
+
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT	12
+#define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
+#define PAGE_MASK	(~(PAGE_SIZE-1))
+
+#ifdef __KERNEL__
+
+#define __PHYSICAL_MASK		((phys_addr_t)(1ULL << __PHYSICAL_MASK_SHIFT) - 1)
+#define __VIRTUAL_MASK		((1UL << __VIRTUAL_MASK_SHIFT) - 1)
+
+/* Cast PAGE_MASK to a signed type so that it is sign-extended if
+   virtual addresses are 32-bits but physical addresses are larger
+   (ie, 32-bit PAE). */
+#define PHYSICAL_PAGE_MASK	(((signed long)PAGE_MASK) & __PHYSICAL_MASK)
+
+/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
+#define PTE_PFN_MASK		((pteval_t)PHYSICAL_PAGE_MASK)
+
+/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */
+#define PTE_FLAGS_MASK		(~PTE_PFN_MASK)
+
+#define PMD_PAGE_SIZE		(_AC(1, UL) << PMD_SHIFT)
+#define PMD_PAGE_MASK		(~(PMD_PAGE_SIZE-1))
+
+#define HPAGE_SHIFT		PMD_SHIFT
+#define HPAGE_SIZE		(_AC(1,UL) << HPAGE_SHIFT)
+#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
+#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
+
+#define HUGE_MAX_HSTATE 2
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+#endif
+
+#ifdef CONFIG_X86_64
+#include <asm/page_64.h>
+#else
+#include <asm/page_32.h>
+#endif	/* CONFIG_X86_64 */
+
+#define PAGE_OFFSET		((unsigned long)__PAGE_OFFSET)
+
+#define VM_DATA_DEFAULT_FLAGS \
+	(((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
+	 VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+
+
+#ifndef __ASSEMBLY__
+
+typedef struct { pgdval_t pgd; } pgd_t;
+typedef struct { pgprotval_t pgprot; } pgprot_t;
+
+extern int page_is_ram(unsigned long pagenr);
+extern int pagerange_is_ram(unsigned long start, unsigned long end);
+extern int devmem_is_allowed(unsigned long pagenr);
+extern void map_devmem(unsigned long pfn, unsigned long size,
+		       pgprot_t vma_prot);
+extern void unmap_devmem(unsigned long pfn, unsigned long size,
+			 pgprot_t vma_prot);
+
+extern unsigned long max_low_pfn_mapped;
+extern unsigned long max_pfn_mapped;
+
+struct page;
+
+static inline void clear_user_page(void *page, unsigned long vaddr,
+				struct page *pg)
+{
+	clear_page(page);
+}
+
+static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
+				struct page *topage)
+{
+	copy_page(to, from);
+}
+
+#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
+	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
+#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
+
+static inline pgd_t native_make_pgd(pgdval_t val)
+{
+	return (pgd_t) { val };
+}
+
+static inline pgdval_t native_pgd_val(pgd_t pgd)
+{
+	return pgd.pgd;
+}
+
+#if PAGETABLE_LEVELS >= 3
+#if PAGETABLE_LEVELS == 4
+typedef struct { pudval_t pud; } pud_t;
+
+static inline pud_t native_make_pud(pmdval_t val)
+{
+	return (pud_t) { val };
+}
+
+static inline pudval_t native_pud_val(pud_t pud)
+{
+	return pud.pud;
+}
+#else	/* PAGETABLE_LEVELS == 3 */
+#include <asm-generic/pgtable-nopud.h>
+
+static inline pudval_t native_pud_val(pud_t pud)
+{
+	return native_pgd_val(pud.pgd);
+}
+#endif	/* PAGETABLE_LEVELS == 4 */
+
+typedef struct { pmdval_t pmd; } pmd_t;
+
+static inline pmd_t native_make_pmd(pmdval_t val)
+{
+	return (pmd_t) { val };
+}
+
+static inline pmdval_t native_pmd_val(pmd_t pmd)
+{
+	return pmd.pmd;
+}
+#else  /* PAGETABLE_LEVELS == 2 */
+#include <asm-generic/pgtable-nopmd.h>
+
+static inline pmdval_t native_pmd_val(pmd_t pmd)
+{
+	return native_pgd_val(pmd.pud.pgd);
+}
+#endif	/* PAGETABLE_LEVELS >= 3 */
+
+static inline pte_t native_make_pte(pteval_t val)
+{
+	return (pte_t) { .pte = val };
+}
+
+static inline pteval_t native_pte_val(pte_t pte)
+{
+	return pte.pte;
+}
+
+static inline pteval_t native_pte_flags(pte_t pte)
+{
+	return native_pte_val(pte) & PTE_FLAGS_MASK;
+}
+
+#define pgprot_val(x)	((x).pgprot)
+#define __pgprot(x)	((pgprot_t) { (x) } )
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else  /* !CONFIG_PARAVIRT */
+
+#define pgd_val(x)	native_pgd_val(x)
+#define __pgd(x)	native_make_pgd(x)
+
+#ifndef __PAGETABLE_PUD_FOLDED
+#define pud_val(x)	native_pud_val(x)
+#define __pud(x)	native_make_pud(x)
+#endif
+
+#ifndef __PAGETABLE_PMD_FOLDED
+#define pmd_val(x)	native_pmd_val(x)
+#define __pmd(x)	native_make_pmd(x)
+#endif
+
+#define pte_val(x)	native_pte_val(x)
+#define pte_flags(x)	native_pte_flags(x)
+#define __pte(x)	native_make_pte(x)
+
+#endif	/* CONFIG_PARAVIRT */
+
+#define __pa(x)		__phys_addr((unsigned long)(x))
+#define __pa_nodebug(x)	__phys_addr_nodebug((unsigned long)(x))
+/* __pa_symbol should be used for C visible symbols.
+   This seems to be the official gcc blessed way to do such arithmetic. */
+#define __pa_symbol(x)	__pa(__phys_reloc_hide((unsigned long)(x)))
+
+#define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
+
+#define __boot_va(x)		__va(x)
+#define __boot_pa(x)		__pa(x)
+
+/*
+ * virt_to_page(kaddr) returns a valid pointer if and only if
+ * virt_addr_valid(kaddr) returns true.
+ */
+#define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+#define pfn_to_kaddr(pfn)      __va((pfn) << PAGE_SHIFT)
+extern bool __virt_addr_valid(unsigned long kaddr);
+#define virt_addr_valid(kaddr)	__virt_addr_valid((unsigned long) (kaddr))
+
+#endif	/* __ASSEMBLY__ */
+
+#include <asm-generic/memory_model.h>
+#include <asm-generic/page.h>
+
+#define __HAVE_ARCH_GATE_AREA 1
+
+#endif	/* __KERNEL__ */
+#endif /* ASM_X86__PAGE_H */
diff --git a/arch/x86/include/asm/page_32.h b/arch/x86/include/asm/page_32.h
new file mode 100644
index 000000000000..bdf5dba4cfb0
--- /dev/null
+++ b/arch/x86/include/asm/page_32.h
@@ -0,0 +1,136 @@
+#ifndef ASM_X86__PAGE_32_H
+#define ASM_X86__PAGE_32_H
+
+/*
+ * This handles the memory map.
+ *
+ * A __PAGE_OFFSET of 0xC0000000 means that the kernel has
+ * a virtual address space of one gigabyte, which limits the
+ * amount of physical memory you can use to about 950MB.
+ *
+ * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
+ * and CONFIG_HIGHMEM64G options in the kernel configuration.
+ */
+#define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
+
+#ifdef CONFIG_4KSTACKS
+#define THREAD_ORDER	0
+#else
+#define THREAD_ORDER	1
+#endif
+#define THREAD_SIZE 	(PAGE_SIZE << THREAD_ORDER)
+
+#define STACKFAULT_STACK 0
+#define DOUBLEFAULT_STACK 1
+#define NMI_STACK 0
+#define DEBUG_STACK 0
+#define MCE_STACK 0
+#define N_EXCEPTION_STACKS 1
+
+#ifdef CONFIG_X86_PAE
+/* 44=32+12, the limit we can fit into an unsigned long pfn */
+#define __PHYSICAL_MASK_SHIFT	44
+#define __VIRTUAL_MASK_SHIFT	32
+#define PAGETABLE_LEVELS	3
+
+#ifndef __ASSEMBLY__
+typedef u64	pteval_t;
+typedef u64	pmdval_t;
+typedef u64	pudval_t;
+typedef u64	pgdval_t;
+typedef u64	pgprotval_t;
+
+typedef union {
+	struct {
+		unsigned long pte_low, pte_high;
+	};
+	pteval_t pte;
+} pte_t;
+#endif	/* __ASSEMBLY__
+ */
+#else  /* !CONFIG_X86_PAE */
+#define __PHYSICAL_MASK_SHIFT	32
+#define __VIRTUAL_MASK_SHIFT	32
+#define PAGETABLE_LEVELS	2
+
+#ifndef __ASSEMBLY__
+typedef unsigned long	pteval_t;
+typedef unsigned long	pmdval_t;
+typedef unsigned long	pudval_t;
+typedef unsigned long	pgdval_t;
+typedef unsigned long	pgprotval_t;
+
+typedef union {
+	pteval_t pte;
+	pteval_t pte_low;
+} pte_t;
+
+#endif	/* __ASSEMBLY__ */
+#endif	/* CONFIG_X86_PAE */
+
+#ifndef __ASSEMBLY__
+typedef struct page *pgtable_t;
+#endif
+
+#ifdef CONFIG_HUGETLB_PAGE
+#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#endif
+
+#ifndef __ASSEMBLY__
+#define __phys_addr_nodebug(x)	((x) - PAGE_OFFSET)
+#ifdef CONFIG_DEBUG_VIRTUAL
+extern unsigned long __phys_addr(unsigned long);
+#else
+#define __phys_addr(x)		__phys_addr_nodebug(x)
+#endif
+#define __phys_reloc_hide(x)	RELOC_HIDE((x), 0)
+
+#ifdef CONFIG_FLATMEM
+#define pfn_valid(pfn)		((pfn) < max_mapnr)
+#endif /* CONFIG_FLATMEM */
+
+extern int nx_enabled;
+
+/*
+ * This much address space is reserved for vmalloc() and iomap()
+ * as well as fixmap mappings.
+ */
+extern unsigned int __VMALLOC_RESERVE;
+extern int sysctl_legacy_va_layout;
+
+extern void find_low_pfn_range(void);
+extern unsigned long init_memory_mapping(unsigned long start,
+					 unsigned long end);
+extern void initmem_init(unsigned long, unsigned long);
+extern void free_initmem(void);
+extern void setup_bootmem_allocator(void);
+
+
+#ifdef CONFIG_X86_USE_3DNOW
+#include <asm/mmx.h>
+
+static inline void clear_page(void *page)
+{
+	mmx_clear_page(page);
+}
+
+static inline void copy_page(void *to, void *from)
+{
+	mmx_copy_page(to, from);
+}
+#else  /* !CONFIG_X86_USE_3DNOW */
+#include <linux/string.h>
+
+static inline void clear_page(void *page)
+{
+	memset(page, 0, PAGE_SIZE);
+}
+
+static inline void copy_page(void *to, void *from)
+{
+	memcpy(to, from, PAGE_SIZE);
+}
+#endif	/* CONFIG_X86_3DNOW */
+#endif	/* !__ASSEMBLY__ */
+
+#endif /* ASM_X86__PAGE_32_H */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
new file mode 100644
index 000000000000..49380b8c7e25
--- /dev/null
+++ b/arch/x86/include/asm/page_64.h
@@ -0,0 +1,105 @@
+#ifndef ASM_X86__PAGE_64_H
+#define ASM_X86__PAGE_64_H
+
+#define PAGETABLE_LEVELS	4
+
+#define THREAD_ORDER	1
+#define THREAD_SIZE  (PAGE_SIZE << THREAD_ORDER)
+#define CURRENT_MASK (~(THREAD_SIZE - 1))
+
+#define EXCEPTION_STACK_ORDER 0
+#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
+
+#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
+#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
+
+#define IRQSTACK_ORDER 2
+#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER)
+
+#define STACKFAULT_STACK 1
+#define DOUBLEFAULT_STACK 2
+#define NMI_STACK 3
+#define DEBUG_STACK 4
+#define MCE_STACK 5
+#define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
+
+#define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
+#define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
+
+/*
+ * Set __PAGE_OFFSET to the most negative possible address +
+ * PGDIR_SIZE*16 (pgd slot 272).  The gap is to allow a space for a
+ * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
+ * what Xen requires.
+ */
+#define __PAGE_OFFSET           _AC(0xffff880000000000, UL)
+
+#define __PHYSICAL_START	CONFIG_PHYSICAL_START
+#define __KERNEL_ALIGN		0x200000
+
+/*
+ * Make sure kernel is aligned to 2MB address. Catching it at compile
+ * time is better. Change your config file and compile the kernel
+ * for a 2MB aligned address (CONFIG_PHYSICAL_START)
+ */
+#if (CONFIG_PHYSICAL_START % __KERNEL_ALIGN) != 0
+#error "CONFIG_PHYSICAL_START must be a multiple of 2MB"
+#endif
+
+#define __START_KERNEL		(__START_KERNEL_map + __PHYSICAL_START)
+#define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
+
+/* See Documentation/x86_64/mm.txt for a description of the memory map. */
+#define __PHYSICAL_MASK_SHIFT	46
+#define __VIRTUAL_MASK_SHIFT	48
+
+/*
+ * Kernel image size is limited to 512 MB (see level2_kernel_pgt in
+ * arch/x86/kernel/head_64.S), and it is mapped here:
+ */
+#define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
+#define KERNEL_IMAGE_START	_AC(0xffffffff80000000, UL)
+
+#ifndef __ASSEMBLY__
+void clear_page(void *page);
+void copy_page(void *to, void *from);
+
+/* duplicated to the one in bootmem.h */
+extern unsigned long max_pfn;
+extern unsigned long phys_base;
+
+extern unsigned long __phys_addr(unsigned long);
+#define __phys_reloc_hide(x)	(x)
+
+/*
+ * These are used to make use of C type-checking..
+ */
+typedef unsigned long	pteval_t;
+typedef unsigned long	pmdval_t;
+typedef unsigned long	pudval_t;
+typedef unsigned long	pgdval_t;
+typedef unsigned long	pgprotval_t;
+
+typedef struct page *pgtable_t;
+
+typedef struct { pteval_t pte; } pte_t;
+
+#define vmemmap ((struct page *)VMEMMAP_START)
+
+extern unsigned long init_memory_mapping(unsigned long start,
+					 unsigned long end);
+
+extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
+extern void free_initmem(void);
+
+extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
+extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
+
+#endif	/* !__ASSEMBLY__ */
+
+#ifdef CONFIG_FLATMEM
+#define pfn_valid(pfn)          ((pfn) < max_pfn)
+#endif
+
+
+#endif /* ASM_X86__PAGE_64_H */
diff --git a/arch/x86/include/asm/param.h b/arch/x86/include/asm/param.h
new file mode 100644
index 000000000000..0009cfb11a5f
--- /dev/null
+++ b/arch/x86/include/asm/param.h
@@ -0,0 +1,22 @@
+#ifndef ASM_X86__PARAM_H
+#define ASM_X86__PARAM_H
+
+#ifdef __KERNEL__
+# define HZ		CONFIG_HZ	/* Internal kernel timer frequency */
+# define USER_HZ	100		/* some user interfaces are */
+# define CLOCKS_PER_SEC	(USER_HZ)       /* in "ticks" like times() */
+#endif
+
+#ifndef HZ
+#define HZ 100
+#endif
+
+#define EXEC_PAGESIZE	4096
+
+#ifndef NOGROUP
+#define NOGROUP		(-1)
+#endif
+
+#define MAXHOSTNAMELEN	64	/* max length of hostname */
+
+#endif /* ASM_X86__PARAM_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
new file mode 100644
index 000000000000..8d6ae2f760d0
--- /dev/null
+++ b/arch/x86/include/asm/paravirt.h
@@ -0,0 +1,1650 @@
+#ifndef ASM_X86__PARAVIRT_H
+#define ASM_X86__PARAVIRT_H
+/* Various instructions on x86 need to be replaced for
+ * para-virtualization: those hooks are defined here. */
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/page.h>
+#include <asm/asm.h>
+
+/* Bitmask of what can be clobbered: usually at least eax. */
+#define CLBR_NONE 0
+#define CLBR_EAX  (1 << 0)
+#define CLBR_ECX  (1 << 1)
+#define CLBR_EDX  (1 << 2)
+
+#ifdef CONFIG_X86_64
+#define CLBR_RSI  (1 << 3)
+#define CLBR_RDI  (1 << 4)
+#define CLBR_R8   (1 << 5)
+#define CLBR_R9   (1 << 6)
+#define CLBR_R10  (1 << 7)
+#define CLBR_R11  (1 << 8)
+#define CLBR_ANY  ((1 << 9) - 1)
+#include <asm/desc_defs.h>
+#else
+/* CLBR_ANY should match all regs platform has. For i386, that's just it */
+#define CLBR_ANY  ((1 << 3) - 1)
+#endif /* X86_64 */
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+#include <linux/cpumask.h>
+#include <asm/kmap_types.h>
+#include <asm/desc_defs.h>
+
+struct page;
+struct thread_struct;
+struct desc_ptr;
+struct tss_struct;
+struct mm_struct;
+struct desc_struct;
+
+/* general info */
+struct pv_info {
+	unsigned int kernel_rpl;
+	int shared_kernel_pmd;
+	int paravirt_enabled;
+	const char *name;
+};
+
+struct pv_init_ops {
+	/*
+	 * Patch may replace one of the defined code sequences with
+	 * arbitrary code, subject to the same register constraints.
+	 * This generally means the code is not free to clobber any
+	 * registers other than EAX.  The patch function should return
+	 * the number of bytes of code generated, as we nop pad the
+	 * rest in generic code.
+	 */
+	unsigned (*patch)(u8 type, u16 clobber, void *insnbuf,
+			  unsigned long addr, unsigned len);
+
+	/* Basic arch-specific setup */
+	void (*arch_setup)(void);
+	char *(*memory_setup)(void);
+	void (*post_allocator_init)(void);
+
+	/* Print a banner to identify the environment */
+	void (*banner)(void);
+};
+
+
+struct pv_lazy_ops {
+	/* Set deferred update mode, used for batching operations. */
+	void (*enter)(void);
+	void (*leave)(void);
+};
+
+struct pv_time_ops {
+	void (*time_init)(void);
+
+	/* Set and set time of day */
+	unsigned long (*get_wallclock)(void);
+	int (*set_wallclock)(unsigned long);
+
+	unsigned long long (*sched_clock)(void);
+	unsigned long (*get_tsc_khz)(void);
+};
+
+struct pv_cpu_ops {
+	/* hooks for various privileged instructions */
+	unsigned long (*get_debugreg)(int regno);
+	void (*set_debugreg)(int regno, unsigned long value);
+
+	void (*clts)(void);
+
+	unsigned long (*read_cr0)(void);
+	void (*write_cr0)(unsigned long);
+
+	unsigned long (*read_cr4_safe)(void);
+	unsigned long (*read_cr4)(void);
+	void (*write_cr4)(unsigned long);
+
+#ifdef CONFIG_X86_64
+	unsigned long (*read_cr8)(void);
+	void (*write_cr8)(unsigned long);
+#endif
+
+	/* Segment descriptor handling */
+	void (*load_tr_desc)(void);
+	void (*load_gdt)(const struct desc_ptr *);
+	void (*load_idt)(const struct desc_ptr *);
+	void (*store_gdt)(struct desc_ptr *);
+	void (*store_idt)(struct desc_ptr *);
+	void (*set_ldt)(const void *desc, unsigned entries);
+	unsigned long (*store_tr)(void);
+	void (*load_tls)(struct thread_struct *t, unsigned int cpu);
+#ifdef CONFIG_X86_64
+	void (*load_gs_index)(unsigned int idx);
+#endif
+	void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum,
+				const void *desc);
+	void (*write_gdt_entry)(struct desc_struct *,
+				int entrynum, const void *desc, int size);
+	void (*write_idt_entry)(gate_desc *,
+				int entrynum, const gate_desc *gate);
+	void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries);
+	void (*free_ldt)(struct desc_struct *ldt, unsigned entries);
+
+	void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t);
+
+	void (*set_iopl_mask)(unsigned mask);
+
+	void (*wbinvd)(void);
+	void (*io_delay)(void);
+
+	/* cpuid emulation, mostly so that caps bits can be disabled */
+	void (*cpuid)(unsigned int *eax, unsigned int *ebx,
+		      unsigned int *ecx, unsigned int *edx);
+
+	/* MSR, PMC and TSR operations.
+	   err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
+	u64 (*read_msr_amd)(unsigned int msr, int *err);
+	u64 (*read_msr)(unsigned int msr, int *err);
+	int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
+
+	u64 (*read_tsc)(void);
+	u64 (*read_pmc)(int counter);
+	unsigned long long (*read_tscp)(unsigned int *aux);
+
+	/*
+	 * Atomically enable interrupts and return to userspace.  This
+	 * is only ever used to return to 32-bit processes; in a
+	 * 64-bit kernel, it's used for 32-on-64 compat processes, but
+	 * never native 64-bit processes.  (Jump, not call.)
+	 */
+	void (*irq_enable_sysexit)(void);
+
+	/*
+	 * Switch to usermode gs and return to 64-bit usermode using
+	 * sysret.  Only used in 64-bit kernels to return to 64-bit
+	 * processes.  Usermode register state, including %rsp, must
+	 * already be restored.
+	 */
+	void (*usergs_sysret64)(void);
+
+	/*
+	 * Switch to usermode gs and return to 32-bit usermode using
+	 * sysret.  Used to return to 32-on-64 compat processes.
+	 * Other usermode register state, including %esp, must already
+	 * be restored.
+	 */
+	void (*usergs_sysret32)(void);
+
+	/* Normal iret.  Jump to this with the standard iret stack
+	   frame set up. */
+	void (*iret)(void);
+
+	void (*swapgs)(void);
+
+	struct pv_lazy_ops lazy_mode;
+};
+
+struct pv_irq_ops {
+	void (*init_IRQ)(void);
+
+	/*
+	 * Get/set interrupt state.  save_fl and restore_fl are only
+	 * expected to use X86_EFLAGS_IF; all other bits
+	 * returned from save_fl are undefined, and may be ignored by
+	 * restore_fl.
+	 */
+	unsigned long (*save_fl)(void);
+	void (*restore_fl)(unsigned long);
+	void (*irq_disable)(void);
+	void (*irq_enable)(void);
+	void (*safe_halt)(void);
+	void (*halt)(void);
+
+#ifdef CONFIG_X86_64
+	void (*adjust_exception_frame)(void);
+#endif
+};
+
+struct pv_apic_ops {
+#ifdef CONFIG_X86_LOCAL_APIC
+	void (*setup_boot_clock)(void);
+	void (*setup_secondary_clock)(void);
+
+	void (*startup_ipi_hook)(int phys_apicid,
+				 unsigned long start_eip,
+				 unsigned long start_esp);
+#endif
+};
+
+struct pv_mmu_ops {
+	/*
+	 * Called before/after init_mm pagetable setup. setup_start
+	 * may reset %cr3, and may pre-install parts of the pagetable;
+	 * pagetable setup is expected to preserve any existing
+	 * mapping.
+	 */
+	void (*pagetable_setup_start)(pgd_t *pgd_base);
+	void (*pagetable_setup_done)(pgd_t *pgd_base);
+
+	unsigned long (*read_cr2)(void);
+	void (*write_cr2)(unsigned long);
+
+	unsigned long (*read_cr3)(void);
+	void (*write_cr3)(unsigned long);
+
+	/*
+	 * Hooks for intercepting the creation/use/destruction of an
+	 * mm_struct.
+	 */
+	void (*activate_mm)(struct mm_struct *prev,
+			    struct mm_struct *next);
+	void (*dup_mmap)(struct mm_struct *oldmm,
+			 struct mm_struct *mm);
+	void (*exit_mmap)(struct mm_struct *mm);
+
+
+	/* TLB operations */
+	void (*flush_tlb_user)(void);
+	void (*flush_tlb_kernel)(void);
+	void (*flush_tlb_single)(unsigned long addr);
+	void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
+				 unsigned long va);
+
+	/* Hooks for allocating and freeing a pagetable top-level */
+	int  (*pgd_alloc)(struct mm_struct *mm);
+	void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd);
+
+	/*
+	 * Hooks for allocating/releasing pagetable pages when they're
+	 * attached to a pagetable
+	 */
+	void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
+	void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
+	void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count);
+	void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
+	void (*release_pte)(unsigned long pfn);
+	void (*release_pmd)(unsigned long pfn);
+	void (*release_pud)(unsigned long pfn);
+
+	/* Pagetable manipulation functions */
+	void (*set_pte)(pte_t *ptep, pte_t pteval);
+	void (*set_pte_at)(struct mm_struct *mm, unsigned long addr,
+			   pte_t *ptep, pte_t pteval);
+	void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
+	void (*pte_update)(struct mm_struct *mm, unsigned long addr,
+			   pte_t *ptep);
+	void (*pte_update_defer)(struct mm_struct *mm,
+				 unsigned long addr, pte_t *ptep);
+
+	pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
+					pte_t *ptep);
+	void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
+					pte_t *ptep, pte_t pte);
+
+	pteval_t (*pte_val)(pte_t);
+	pteval_t (*pte_flags)(pte_t);
+	pte_t (*make_pte)(pteval_t pte);
+
+	pgdval_t (*pgd_val)(pgd_t);
+	pgd_t (*make_pgd)(pgdval_t pgd);
+
+#if PAGETABLE_LEVELS >= 3
+#ifdef CONFIG_X86_PAE
+	void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
+	void (*set_pte_present)(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep, pte_t pte);
+	void (*pte_clear)(struct mm_struct *mm, unsigned long addr,
+			  pte_t *ptep);
+	void (*pmd_clear)(pmd_t *pmdp);
+
+#endif	/* CONFIG_X86_PAE */
+
+	void (*set_pud)(pud_t *pudp, pud_t pudval);
+
+	pmdval_t (*pmd_val)(pmd_t);
+	pmd_t (*make_pmd)(pmdval_t pmd);
+
+#if PAGETABLE_LEVELS == 4
+	pudval_t (*pud_val)(pud_t);
+	pud_t (*make_pud)(pudval_t pud);
+
+	void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
+#endif	/* PAGETABLE_LEVELS == 4 */
+#endif	/* PAGETABLE_LEVELS >= 3 */
+
+#ifdef CONFIG_HIGHPTE
+	void *(*kmap_atomic_pte)(struct page *page, enum km_type type);
+#endif
+
+	struct pv_lazy_ops lazy_mode;
+
+	/* dom0 ops */
+
+	/* Sometimes the physical address is a pfn, and sometimes its
+	   an mfn.  We can tell which is which from the index. */
+	void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx,
+			   unsigned long phys, pgprot_t flags);
+};
+
+struct raw_spinlock;
+struct pv_lock_ops {
+	int (*spin_is_locked)(struct raw_spinlock *lock);
+	int (*spin_is_contended)(struct raw_spinlock *lock);
+	void (*spin_lock)(struct raw_spinlock *lock);
+	void (*spin_lock_flags)(struct raw_spinlock *lock, unsigned long flags);
+	int (*spin_trylock)(struct raw_spinlock *lock);
+	void (*spin_unlock)(struct raw_spinlock *lock);
+};
+
+/* This contains all the paravirt structures: we get a convenient
+ * number for each function using the offset which we use to indicate
+ * what to patch. */
+struct paravirt_patch_template {
+	struct pv_init_ops pv_init_ops;
+	struct pv_time_ops pv_time_ops;
+	struct pv_cpu_ops pv_cpu_ops;
+	struct pv_irq_ops pv_irq_ops;
+	struct pv_apic_ops pv_apic_ops;
+	struct pv_mmu_ops pv_mmu_ops;
+	struct pv_lock_ops pv_lock_ops;
+};
+
+extern struct pv_info pv_info;
+extern struct pv_init_ops pv_init_ops;
+extern struct pv_time_ops pv_time_ops;
+extern struct pv_cpu_ops pv_cpu_ops;
+extern struct pv_irq_ops pv_irq_ops;
+extern struct pv_apic_ops pv_apic_ops;
+extern struct pv_mmu_ops pv_mmu_ops;
+extern struct pv_lock_ops pv_lock_ops;
+
+#define PARAVIRT_PATCH(x)					\
+	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
+
+#define paravirt_type(op)				\
+	[paravirt_typenum] "i" (PARAVIRT_PATCH(op)),	\
+	[paravirt_opptr] "m" (op)
+#define paravirt_clobber(clobber)		\
+	[paravirt_clobber] "i" (clobber)
+
+/*
+ * Generate some code, and mark it as patchable by the
+ * apply_paravirt() alternate instruction patcher.
+ */
+#define _paravirt_alt(insn_string, type, clobber)	\
+	"771:\n\t" insn_string "\n" "772:\n"		\
+	".pushsection .parainstructions,\"a\"\n"	\
+	_ASM_ALIGN "\n"					\
+	_ASM_PTR " 771b\n"				\
+	"  .byte " type "\n"				\
+	"  .byte 772b-771b\n"				\
+	"  .short " clobber "\n"			\
+	".popsection\n"
+
+/* Generate patchable code, with the default asm parameters. */
+#define paravirt_alt(insn_string)					\
+	_paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]")
+
+/* Simple instruction patching code. */
+#define DEF_NATIVE(ops, name, code) 					\
+	extern const char start_##ops##_##name[], end_##ops##_##name[];	\
+	asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
+
+unsigned paravirt_patch_nop(void);
+unsigned paravirt_patch_ignore(unsigned len);
+unsigned paravirt_patch_call(void *insnbuf,
+			     const void *target, u16 tgt_clobbers,
+			     unsigned long addr, u16 site_clobbers,
+			     unsigned len);
+unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
+			    unsigned long addr, unsigned len);
+unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
+				unsigned long addr, unsigned len);
+
+unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
+			      const char *start, const char *end);
+
+unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
+		      unsigned long addr, unsigned len);
+
+int paravirt_disable_iospace(void);
+
+/*
+ * This generates an indirect call based on the operation type number.
+ * The type number, computed in PARAVIRT_PATCH, is derived from the
+ * offset into the paravirt_patch_template structure, and can therefore be
+ * freely converted back into a structure offset.
+ */
+#define PARAVIRT_CALL	"call *%[paravirt_opptr];"
+
+/*
+ * These macros are intended to wrap calls through one of the paravirt
+ * ops structs, so that they can be later identified and patched at
+ * runtime.
+ *
+ * Normally, a call to a pv_op function is a simple indirect call:
+ * (pv_op_struct.operations)(args...).
+ *
+ * Unfortunately, this is a relatively slow operation for modern CPUs,
+ * because it cannot necessarily determine what the destination
+ * address is.  In this case, the address is a runtime constant, so at
+ * the very least we can patch the call to e a simple direct call, or
+ * ideally, patch an inline implementation into the callsite.  (Direct
+ * calls are essentially free, because the call and return addresses
+ * are completely predictable.)
+ *
+ * For i386, these macros rely on the standard gcc "regparm(3)" calling
+ * convention, in which the first three arguments are placed in %eax,
+ * %edx, %ecx (in that order), and the remaining arguments are placed
+ * on the stack.  All caller-save registers (eax,edx,ecx) are expected
+ * to be modified (either clobbered or used for return values).
+ * X86_64, on the other hand, already specifies a register-based calling
+ * conventions, returning at %rax, with parameteres going on %rdi, %rsi,
+ * %rdx, and %rcx. Note that for this reason, x86_64 does not need any
+ * special handling for dealing with 4 arguments, unlike i386.
+ * However, x86_64 also have to clobber all caller saved registers, which
+ * unfortunately, are quite a bit (r8 - r11)
+ *
+ * The call instruction itself is marked by placing its start address
+ * and size into the .parainstructions section, so that
+ * apply_paravirt() in arch/i386/kernel/alternative.c can do the
+ * appropriate patching under the control of the backend pv_init_ops
+ * implementation.
+ *
+ * Unfortunately there's no way to get gcc to generate the args setup
+ * for the call, and then allow the call itself to be generated by an
+ * inline asm.  Because of this, we must do the complete arg setup and
+ * return value handling from within these macros.  This is fairly
+ * cumbersome.
+ *
+ * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments.
+ * It could be extended to more arguments, but there would be little
+ * to be gained from that.  For each number of arguments, there are
+ * the two VCALL and CALL variants for void and non-void functions.
+ *
+ * When there is a return value, the invoker of the macro must specify
+ * the return type.  The macro then uses sizeof() on that type to
+ * determine whether its a 32 or 64 bit value, and places the return
+ * in the right register(s) (just %eax for 32-bit, and %edx:%eax for
+ * 64-bit). For x86_64 machines, it just returns at %rax regardless of
+ * the return value size.
+ *
+ * 64-bit arguments are passed as a pair of adjacent 32-bit arguments
+ * i386 also passes 64-bit arguments as a pair of adjacent 32-bit arguments
+ * in low,high order
+ *
+ * Small structures are passed and returned in registers.  The macro
+ * calling convention can't directly deal with this, so the wrapper
+ * functions must do this.
+ *
+ * These PVOP_* macros are only defined within this header.  This
+ * means that all uses must be wrapped in inline functions.  This also
+ * makes sure the incoming and outgoing types are always correct.
+ */
+#ifdef CONFIG_X86_32
+#define PVOP_VCALL_ARGS			unsigned long __eax, __edx, __ecx
+#define PVOP_CALL_ARGS			PVOP_VCALL_ARGS
+#define PVOP_VCALL_CLOBBERS		"=a" (__eax), "=d" (__edx),	\
+					"=c" (__ecx)
+#define PVOP_CALL_CLOBBERS		PVOP_VCALL_CLOBBERS
+#define EXTRA_CLOBBERS
+#define VEXTRA_CLOBBERS
+#else
+#define PVOP_VCALL_ARGS		unsigned long __edi, __esi, __edx, __ecx
+#define PVOP_CALL_ARGS		PVOP_VCALL_ARGS, __eax
+#define PVOP_VCALL_CLOBBERS	"=D" (__edi),				\
+				"=S" (__esi), "=d" (__edx),		\
+				"=c" (__ecx)
+
+#define PVOP_CALL_CLOBBERS	PVOP_VCALL_CLOBBERS, "=a" (__eax)
+
+#define EXTRA_CLOBBERS	 , "r8", "r9", "r10", "r11"
+#define VEXTRA_CLOBBERS	 , "rax", "r8", "r9", "r10", "r11"
+#endif
+
+#ifdef CONFIG_PARAVIRT_DEBUG
+#define PVOP_TEST_NULL(op)	BUG_ON(op == NULL)
+#else
+#define PVOP_TEST_NULL(op)	((void)op)
+#endif
+
+#define __PVOP_CALL(rettype, op, pre, post, ...)			\
+	({								\
+		rettype __ret;						\
+		PVOP_CALL_ARGS;					\
+		PVOP_TEST_NULL(op);					\
+		/* This is 32-bit specific, but is okay in 64-bit */	\
+		/* since this condition will never hold */		\
+		if (sizeof(rettype) > sizeof(unsigned long)) {		\
+			asm volatile(pre				\
+				     paravirt_alt(PARAVIRT_CALL)	\
+				     post				\
+				     : PVOP_CALL_CLOBBERS		\
+				     : paravirt_type(op),		\
+				       paravirt_clobber(CLBR_ANY),	\
+				       ##__VA_ARGS__			\
+				     : "memory", "cc" EXTRA_CLOBBERS);	\
+			__ret = (rettype)((((u64)__edx) << 32) | __eax); \
+		} else {						\
+			asm volatile(pre				\
+				     paravirt_alt(PARAVIRT_CALL)	\
+				     post				\
+				     : PVOP_CALL_CLOBBERS		\
+				     : paravirt_type(op),		\
+				       paravirt_clobber(CLBR_ANY),	\
+				       ##__VA_ARGS__			\
+				     : "memory", "cc" EXTRA_CLOBBERS);	\
+			__ret = (rettype)__eax;				\
+		}							\
+		__ret;							\
+	})
+#define __PVOP_VCALL(op, pre, post, ...)				\
+	({								\
+		PVOP_VCALL_ARGS;					\
+		PVOP_TEST_NULL(op);					\
+		asm volatile(pre					\
+			     paravirt_alt(PARAVIRT_CALL)		\
+			     post					\
+			     : PVOP_VCALL_CLOBBERS			\
+			     : paravirt_type(op),			\
+			       paravirt_clobber(CLBR_ANY),		\
+			       ##__VA_ARGS__				\
+			     : "memory", "cc" VEXTRA_CLOBBERS);		\
+	})
+
+#define PVOP_CALL0(rettype, op)						\
+	__PVOP_CALL(rettype, op, "", "")
+#define PVOP_VCALL0(op)							\
+	__PVOP_VCALL(op, "", "")
+
+#define PVOP_CALL1(rettype, op, arg1)					\
+	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)))
+#define PVOP_VCALL1(op, arg1)						\
+	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)))
+
+#define PVOP_CALL2(rettype, op, arg1, arg2)				\
+	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)), 	\
+	"1" ((unsigned long)(arg2)))
+#define PVOP_VCALL2(op, arg1, arg2)					\
+	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)), 		\
+	"1" ((unsigned long)(arg2)))
+
+#define PVOP_CALL3(rettype, op, arg1, arg2, arg3)			\
+	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)),	\
+	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)))
+#define PVOP_VCALL3(op, arg1, arg2, arg3)				\
+	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)),		\
+	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)))
+
+/* This is the only difference in x86_64. We can make it much simpler */
+#ifdef CONFIG_X86_32
+#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
+	__PVOP_CALL(rettype, op,					\
+		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
+		    "0" ((u32)(arg1)), "1" ((u32)(arg2)),		\
+		    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
+#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
+	__PVOP_VCALL(op,						\
+		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
+		    "0" ((u32)(arg1)), "1" ((u32)(arg2)),		\
+		    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
+#else
+#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
+	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)),	\
+	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)),		\
+	"3"((unsigned long)(arg4)))
+#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
+	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)),		\
+	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)),		\
+	"3"((unsigned long)(arg4)))
+#endif
+
+static inline int paravirt_enabled(void)
+{
+	return pv_info.paravirt_enabled;
+}
+
+static inline void load_sp0(struct tss_struct *tss,
+			     struct thread_struct *thread)
+{
+	PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread);
+}
+
+#define ARCH_SETUP			pv_init_ops.arch_setup();
+static inline unsigned long get_wallclock(void)
+{
+	return PVOP_CALL0(unsigned long, pv_time_ops.get_wallclock);
+}
+
+static inline int set_wallclock(unsigned long nowtime)
+{
+	return PVOP_CALL1(int, pv_time_ops.set_wallclock, nowtime);
+}
+
+static inline void (*choose_time_init(void))(void)
+{
+	return pv_time_ops.time_init;
+}
+
+/* The paravirtualized CPUID instruction. */
+static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
+			   unsigned int *ecx, unsigned int *edx)
+{
+	PVOP_VCALL4(pv_cpu_ops.cpuid, eax, ebx, ecx, edx);
+}
+
+/*
+ * These special macros can be used to get or set a debugging register
+ */
+static inline unsigned long paravirt_get_debugreg(int reg)
+{
+	return PVOP_CALL1(unsigned long, pv_cpu_ops.get_debugreg, reg);
+}
+#define get_debugreg(var, reg) var = paravirt_get_debugreg(reg)
+static inline void set_debugreg(unsigned long val, int reg)
+{
+	PVOP_VCALL2(pv_cpu_ops.set_debugreg, reg, val);
+}
+
+static inline void clts(void)
+{
+	PVOP_VCALL0(pv_cpu_ops.clts);
+}
+
+static inline unsigned long read_cr0(void)
+{
+	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr0);
+}
+
+static inline void write_cr0(unsigned long x)
+{
+	PVOP_VCALL1(pv_cpu_ops.write_cr0, x);
+}
+
+static inline unsigned long read_cr2(void)
+{
+	return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr2);
+}
+
+static inline void write_cr2(unsigned long x)
+{
+	PVOP_VCALL1(pv_mmu_ops.write_cr2, x);
+}
+
+static inline unsigned long read_cr3(void)
+{
+	return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3);
+}
+
+static inline void write_cr3(unsigned long x)
+{
+	PVOP_VCALL1(pv_mmu_ops.write_cr3, x);
+}
+
+static inline unsigned long read_cr4(void)
+{
+	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4);
+}
+static inline unsigned long read_cr4_safe(void)
+{
+	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe);
+}
+
+static inline void write_cr4(unsigned long x)
+{
+	PVOP_VCALL1(pv_cpu_ops.write_cr4, x);
+}
+
+#ifdef CONFIG_X86_64
+static inline unsigned long read_cr8(void)
+{
+	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr8);
+}
+
+static inline void write_cr8(unsigned long x)
+{
+	PVOP_VCALL1(pv_cpu_ops.write_cr8, x);
+}
+#endif
+
+static inline void raw_safe_halt(void)
+{
+	PVOP_VCALL0(pv_irq_ops.safe_halt);
+}
+
+static inline void halt(void)
+{
+	PVOP_VCALL0(pv_irq_ops.safe_halt);
+}
+
+static inline void wbinvd(void)
+{
+	PVOP_VCALL0(pv_cpu_ops.wbinvd);
+}
+
+#define get_kernel_rpl()  (pv_info.kernel_rpl)
+
+static inline u64 paravirt_read_msr(unsigned msr, int *err)
+{
+	return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
+}
+static inline u64 paravirt_read_msr_amd(unsigned msr, int *err)
+{
+	return PVOP_CALL2(u64, pv_cpu_ops.read_msr_amd, msr, err);
+}
+static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
+{
+	return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
+}
+
+/* These should all do BUG_ON(_err), but our headers are too tangled. */
+#define rdmsr(msr, val1, val2)			\
+do {						\
+	int _err;				\
+	u64 _l = paravirt_read_msr(msr, &_err);	\
+	val1 = (u32)_l;				\
+	val2 = _l >> 32;			\
+} while (0)
+
+#define wrmsr(msr, val1, val2)			\
+do {						\
+	paravirt_write_msr(msr, val1, val2);	\
+} while (0)
+
+#define rdmsrl(msr, val)			\
+do {						\
+	int _err;				\
+	val = paravirt_read_msr(msr, &_err);	\
+} while (0)
+
+#define wrmsrl(msr, val)	wrmsr(msr, (u32)((u64)(val)), ((u64)(val))>>32)
+#define wrmsr_safe(msr, a, b)	paravirt_write_msr(msr, a, b)
+
+/* rdmsr with exception handling */
+#define rdmsr_safe(msr, a, b)			\
+({						\
+	int _err;				\
+	u64 _l = paravirt_read_msr(msr, &_err);	\
+	(*a) = (u32)_l;				\
+	(*b) = _l >> 32;			\
+	_err;					\
+})
+
+static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
+{
+	int err;
+
+	*p = paravirt_read_msr(msr, &err);
+	return err;
+}
+static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+{
+	int err;
+
+	*p = paravirt_read_msr_amd(msr, &err);
+	return err;
+}
+
+static inline u64 paravirt_read_tsc(void)
+{
+	return PVOP_CALL0(u64, pv_cpu_ops.read_tsc);
+}
+
+#define rdtscl(low)				\
+do {						\
+	u64 _l = paravirt_read_tsc();		\
+	low = (int)_l;				\
+} while (0)
+
+#define rdtscll(val) (val = paravirt_read_tsc())
+
+static inline unsigned long long paravirt_sched_clock(void)
+{
+	return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
+}
+#define calibrate_tsc() (pv_time_ops.get_tsc_khz())
+
+static inline unsigned long long paravirt_read_pmc(int counter)
+{
+	return PVOP_CALL1(u64, pv_cpu_ops.read_pmc, counter);
+}
+
+#define rdpmc(counter, low, high)		\
+do {						\
+	u64 _l = paravirt_read_pmc(counter);	\
+	low = (u32)_l;				\
+	high = _l >> 32;			\
+} while (0)
+
+static inline unsigned long long paravirt_rdtscp(unsigned int *aux)
+{
+	return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux);
+}
+
+#define rdtscp(low, high, aux)				\
+do {							\
+	int __aux;					\
+	unsigned long __val = paravirt_rdtscp(&__aux);	\
+	(low) = (u32)__val;				\
+	(high) = (u32)(__val >> 32);			\
+	(aux) = __aux;					\
+} while (0)
+
+#define rdtscpll(val, aux)				\
+do {							\
+	unsigned long __aux; 				\
+	val = paravirt_rdtscp(&__aux);			\
+	(aux) = __aux;					\
+} while (0)
+
+static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
+{
+	PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
+}
+
+static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
+{
+	PVOP_VCALL2(pv_cpu_ops.free_ldt, ldt, entries);
+}
+
+static inline void load_TR_desc(void)
+{
+	PVOP_VCALL0(pv_cpu_ops.load_tr_desc);
+}
+static inline void load_gdt(const struct desc_ptr *dtr)
+{
+	PVOP_VCALL1(pv_cpu_ops.load_gdt, dtr);
+}
+static inline void load_idt(const struct desc_ptr *dtr)
+{
+	PVOP_VCALL1(pv_cpu_ops.load_idt, dtr);
+}
+static inline void set_ldt(const void *addr, unsigned entries)
+{
+	PVOP_VCALL2(pv_cpu_ops.set_ldt, addr, entries);
+}
+static inline void store_gdt(struct desc_ptr *dtr)
+{
+	PVOP_VCALL1(pv_cpu_ops.store_gdt, dtr);
+}
+static inline void store_idt(struct desc_ptr *dtr)
+{
+	PVOP_VCALL1(pv_cpu_ops.store_idt, dtr);
+}
+static inline unsigned long paravirt_store_tr(void)
+{
+	return PVOP_CALL0(unsigned long, pv_cpu_ops.store_tr);
+}
+#define store_tr(tr)	((tr) = paravirt_store_tr())
+static inline void load_TLS(struct thread_struct *t, unsigned cpu)
+{
+	PVOP_VCALL2(pv_cpu_ops.load_tls, t, cpu);
+}
+
+#ifdef CONFIG_X86_64
+static inline void load_gs_index(unsigned int gs)
+{
+	PVOP_VCALL1(pv_cpu_ops.load_gs_index, gs);
+}
+#endif
+
+static inline void write_ldt_entry(struct desc_struct *dt, int entry,
+				   const void *desc)
+{
+	PVOP_VCALL3(pv_cpu_ops.write_ldt_entry, dt, entry, desc);
+}
+
+static inline void write_gdt_entry(struct desc_struct *dt, int entry,
+				   void *desc, int type)
+{
+	PVOP_VCALL4(pv_cpu_ops.write_gdt_entry, dt, entry, desc, type);
+}
+
+static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
+{
+	PVOP_VCALL3(pv_cpu_ops.write_idt_entry, dt, entry, g);
+}
+static inline void set_iopl_mask(unsigned mask)
+{
+	PVOP_VCALL1(pv_cpu_ops.set_iopl_mask, mask);
+}
+
+/* The paravirtualized I/O functions */
+static inline void slow_down_io(void)
+{
+	pv_cpu_ops.io_delay();
+#ifdef REALLY_SLOW_IO
+	pv_cpu_ops.io_delay();
+	pv_cpu_ops.io_delay();
+	pv_cpu_ops.io_delay();
+#endif
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+static inline void setup_boot_clock(void)
+{
+	PVOP_VCALL0(pv_apic_ops.setup_boot_clock);
+}
+
+static inline void setup_secondary_clock(void)
+{
+	PVOP_VCALL0(pv_apic_ops.setup_secondary_clock);
+}
+#endif
+
+static inline void paravirt_post_allocator_init(void)
+{
+	if (pv_init_ops.post_allocator_init)
+		(*pv_init_ops.post_allocator_init)();
+}
+
+static inline void paravirt_pagetable_setup_start(pgd_t *base)
+{
+	(*pv_mmu_ops.pagetable_setup_start)(base);
+}
+
+static inline void paravirt_pagetable_setup_done(pgd_t *base)
+{
+	(*pv_mmu_ops.pagetable_setup_done)(base);
+}
+
+#ifdef CONFIG_SMP
+static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip,
+				    unsigned long start_esp)
+{
+	PVOP_VCALL3(pv_apic_ops.startup_ipi_hook,
+		    phys_apicid, start_eip, start_esp);
+}
+#endif
+
+static inline void paravirt_activate_mm(struct mm_struct *prev,
+					struct mm_struct *next)
+{
+	PVOP_VCALL2(pv_mmu_ops.activate_mm, prev, next);
+}
+
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+	PVOP_VCALL2(pv_mmu_ops.dup_mmap, oldmm, mm);
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+	PVOP_VCALL1(pv_mmu_ops.exit_mmap, mm);
+}
+
+static inline void __flush_tlb(void)
+{
+	PVOP_VCALL0(pv_mmu_ops.flush_tlb_user);
+}
+static inline void __flush_tlb_global(void)
+{
+	PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel);
+}
+static inline void __flush_tlb_single(unsigned long addr)
+{
+	PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
+}
+
+static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
+				    unsigned long va)
+{
+	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
+}
+
+static inline int paravirt_pgd_alloc(struct mm_struct *mm)
+{
+	return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm);
+}
+
+static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+	PVOP_VCALL2(pv_mmu_ops.pgd_free, mm, pgd);
+}
+
+static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)
+{
+	PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn);
+}
+static inline void paravirt_release_pte(unsigned long pfn)
+{
+	PVOP_VCALL1(pv_mmu_ops.release_pte, pfn);
+}
+
+static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
+{
+	PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
+}
+
+static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
+					    unsigned long start, unsigned long count)
+{
+	PVOP_VCALL4(pv_mmu_ops.alloc_pmd_clone, pfn, clonepfn, start, count);
+}
+static inline void paravirt_release_pmd(unsigned long pfn)
+{
+	PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
+}
+
+static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)
+{
+	PVOP_VCALL2(pv_mmu_ops.alloc_pud, mm, pfn);
+}
+static inline void paravirt_release_pud(unsigned long pfn)
+{
+	PVOP_VCALL1(pv_mmu_ops.release_pud, pfn);
+}
+
+#ifdef CONFIG_HIGHPTE
+static inline void *kmap_atomic_pte(struct page *page, enum km_type type)
+{
+	unsigned long ret;
+	ret = PVOP_CALL2(unsigned long, pv_mmu_ops.kmap_atomic_pte, page, type);
+	return (void *)ret;
+}
+#endif
+
+static inline void pte_update(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep)
+{
+	PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep);
+}
+
+static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
+				    pte_t *ptep)
+{
+	PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep);
+}
+
+static inline pte_t __pte(pteval_t val)
+{
+	pteval_t ret;
+
+	if (sizeof(pteval_t) > sizeof(long))
+		ret = PVOP_CALL2(pteval_t,
+				 pv_mmu_ops.make_pte,
+				 val, (u64)val >> 32);
+	else
+		ret = PVOP_CALL1(pteval_t,
+				 pv_mmu_ops.make_pte,
+				 val);
+
+	return (pte_t) { .pte = ret };
+}
+
+static inline pteval_t pte_val(pte_t pte)
+{
+	pteval_t ret;
+
+	if (sizeof(pteval_t) > sizeof(long))
+		ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_val,
+				 pte.pte, (u64)pte.pte >> 32);
+	else
+		ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_val,
+				 pte.pte);
+
+	return ret;
+}
+
+static inline pteval_t pte_flags(pte_t pte)
+{
+	pteval_t ret;
+
+	if (sizeof(pteval_t) > sizeof(long))
+		ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_flags,
+				 pte.pte, (u64)pte.pte >> 32);
+	else
+		ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags,
+				 pte.pte);
+
+#ifdef CONFIG_PARAVIRT_DEBUG
+	BUG_ON(ret & PTE_PFN_MASK);
+#endif
+	return ret;
+}
+
+static inline pgd_t __pgd(pgdval_t val)
+{
+	pgdval_t ret;
+
+	if (sizeof(pgdval_t) > sizeof(long))
+		ret = PVOP_CALL2(pgdval_t, pv_mmu_ops.make_pgd,
+				 val, (u64)val >> 32);
+	else
+		ret = PVOP_CALL1(pgdval_t, pv_mmu_ops.make_pgd,
+				 val);
+
+	return (pgd_t) { ret };
+}
+
+static inline pgdval_t pgd_val(pgd_t pgd)
+{
+	pgdval_t ret;
+
+	if (sizeof(pgdval_t) > sizeof(long))
+		ret =  PVOP_CALL2(pgdval_t, pv_mmu_ops.pgd_val,
+				  pgd.pgd, (u64)pgd.pgd >> 32);
+	else
+		ret =  PVOP_CALL1(pgdval_t, pv_mmu_ops.pgd_val,
+				  pgd.pgd);
+
+	return ret;
+}
+
+#define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
+					   pte_t *ptep)
+{
+	pteval_t ret;
+
+	ret = PVOP_CALL3(pteval_t, pv_mmu_ops.ptep_modify_prot_start,
+			 mm, addr, ptep);
+
+	return (pte_t) { .pte = ret };
+}
+
+static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
+					   pte_t *ptep, pte_t pte)
+{
+	if (sizeof(pteval_t) > sizeof(long))
+		/* 5 arg words */
+		pv_mmu_ops.ptep_modify_prot_commit(mm, addr, ptep, pte);
+	else
+		PVOP_VCALL4(pv_mmu_ops.ptep_modify_prot_commit,
+			    mm, addr, ptep, pte.pte);
+}
+
+static inline void set_pte(pte_t *ptep, pte_t pte)
+{
+	if (sizeof(pteval_t) > sizeof(long))
+		PVOP_VCALL3(pv_mmu_ops.set_pte, ptep,
+			    pte.pte, (u64)pte.pte >> 32);
+	else
+		PVOP_VCALL2(pv_mmu_ops.set_pte, ptep,
+			    pte.pte);
+}
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pte)
+{
+	if (sizeof(pteval_t) > sizeof(long))
+		/* 5 arg words */
+		pv_mmu_ops.set_pte_at(mm, addr, ptep, pte);
+	else
+		PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pte.pte);
+}
+
+static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+	pmdval_t val = native_pmd_val(pmd);
+
+	if (sizeof(pmdval_t) > sizeof(long))
+		PVOP_VCALL3(pv_mmu_ops.set_pmd, pmdp, val, (u64)val >> 32);
+	else
+		PVOP_VCALL2(pv_mmu_ops.set_pmd, pmdp, val);
+}
+
+#if PAGETABLE_LEVELS >= 3
+static inline pmd_t __pmd(pmdval_t val)
+{
+	pmdval_t ret;
+
+	if (sizeof(pmdval_t) > sizeof(long))
+		ret = PVOP_CALL2(pmdval_t, pv_mmu_ops.make_pmd,
+				 val, (u64)val >> 32);
+	else
+		ret = PVOP_CALL1(pmdval_t, pv_mmu_ops.make_pmd,
+				 val);
+
+	return (pmd_t) { ret };
+}
+
+static inline pmdval_t pmd_val(pmd_t pmd)
+{
+	pmdval_t ret;
+
+	if (sizeof(pmdval_t) > sizeof(long))
+		ret =  PVOP_CALL2(pmdval_t, pv_mmu_ops.pmd_val,
+				  pmd.pmd, (u64)pmd.pmd >> 32);
+	else
+		ret =  PVOP_CALL1(pmdval_t, pv_mmu_ops.pmd_val,
+				  pmd.pmd);
+
+	return ret;
+}
+
+static inline void set_pud(pud_t *pudp, pud_t pud)
+{
+	pudval_t val = native_pud_val(pud);
+
+	if (sizeof(pudval_t) > sizeof(long))
+		PVOP_VCALL3(pv_mmu_ops.set_pud, pudp,
+			    val, (u64)val >> 32);
+	else
+		PVOP_VCALL2(pv_mmu_ops.set_pud, pudp,
+			    val);
+}
+#if PAGETABLE_LEVELS == 4
+static inline pud_t __pud(pudval_t val)
+{
+	pudval_t ret;
+
+	if (sizeof(pudval_t) > sizeof(long))
+		ret = PVOP_CALL2(pudval_t, pv_mmu_ops.make_pud,
+				 val, (u64)val >> 32);
+	else
+		ret = PVOP_CALL1(pudval_t, pv_mmu_ops.make_pud,
+				 val);
+
+	return (pud_t) { ret };
+}
+
+static inline pudval_t pud_val(pud_t pud)
+{
+	pudval_t ret;
+
+	if (sizeof(pudval_t) > sizeof(long))
+		ret =  PVOP_CALL2(pudval_t, pv_mmu_ops.pud_val,
+				  pud.pud, (u64)pud.pud >> 32);
+	else
+		ret =  PVOP_CALL1(pudval_t, pv_mmu_ops.pud_val,
+				  pud.pud);
+
+	return ret;
+}
+
+static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	pgdval_t val = native_pgd_val(pgd);
+
+	if (sizeof(pgdval_t) > sizeof(long))
+		PVOP_VCALL3(pv_mmu_ops.set_pgd, pgdp,
+			    val, (u64)val >> 32);
+	else
+		PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp,
+			    val);
+}
+
+static inline void pgd_clear(pgd_t *pgdp)
+{
+	set_pgd(pgdp, __pgd(0));
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+	set_pud(pudp, __pud(0));
+}
+
+#endif	/* PAGETABLE_LEVELS == 4 */
+
+#endif	/* PAGETABLE_LEVELS >= 3 */
+
+#ifdef CONFIG_X86_PAE
+/* Special-case pte-setting operations for PAE, which can't update a
+   64-bit pte atomically */
+static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
+{
+	PVOP_VCALL3(pv_mmu_ops.set_pte_atomic, ptep,
+		    pte.pte, pte.pte >> 32);
+}
+
+static inline void set_pte_present(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	/* 5 arg words */
+	pv_mmu_ops.set_pte_present(mm, addr, ptep, pte);
+}
+
+static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
+			     pte_t *ptep)
+{
+	PVOP_VCALL3(pv_mmu_ops.pte_clear, mm, addr, ptep);
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	PVOP_VCALL1(pv_mmu_ops.pmd_clear, pmdp);
+}
+#else  /* !CONFIG_X86_PAE */
+static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
+{
+	set_pte(ptep, pte);
+}
+
+static inline void set_pte_present(struct mm_struct *mm, unsigned long addr,
+				   pte_t *ptep, pte_t pte)
+{
+	set_pte(ptep, pte);
+}
+
+static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
+			     pte_t *ptep)
+{
+	set_pte_at(mm, addr, ptep, __pte(0));
+}
+
+static inline void pmd_clear(pmd_t *pmdp)
+{
+	set_pmd(pmdp, __pmd(0));
+}
+#endif	/* CONFIG_X86_PAE */
+
+/* Lazy mode for batching updates / context switch */
+enum paravirt_lazy_mode {
+	PARAVIRT_LAZY_NONE,
+	PARAVIRT_LAZY_MMU,
+	PARAVIRT_LAZY_CPU,
+};
+
+enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
+void paravirt_enter_lazy_cpu(void);
+void paravirt_leave_lazy_cpu(void);
+void paravirt_enter_lazy_mmu(void);
+void paravirt_leave_lazy_mmu(void);
+void paravirt_leave_lazy(enum paravirt_lazy_mode mode);
+
+#define  __HAVE_ARCH_ENTER_LAZY_CPU_MODE
+static inline void arch_enter_lazy_cpu_mode(void)
+{
+	PVOP_VCALL0(pv_cpu_ops.lazy_mode.enter);
+}
+
+static inline void arch_leave_lazy_cpu_mode(void)
+{
+	PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
+}
+
+static inline void arch_flush_lazy_cpu_mode(void)
+{
+	if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)) {
+		arch_leave_lazy_cpu_mode();
+		arch_enter_lazy_cpu_mode();
+	}
+}
+
+
+#define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
+static inline void arch_enter_lazy_mmu_mode(void)
+{
+	PVOP_VCALL0(pv_mmu_ops.lazy_mode.enter);
+}
+
+static inline void arch_leave_lazy_mmu_mode(void)
+{
+	PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
+}
+
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+	if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU)) {
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+}
+
+static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
+				unsigned long phys, pgprot_t flags)
+{
+	pv_mmu_ops.set_fixmap(idx, phys, flags);
+}
+
+void _paravirt_nop(void);
+#define paravirt_nop	((void *)_paravirt_nop)
+
+void paravirt_use_bytelocks(void);
+
+#ifdef CONFIG_SMP
+
+static inline int __raw_spin_is_locked(struct raw_spinlock *lock)
+{
+	return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock);
+}
+
+static inline int __raw_spin_is_contended(struct raw_spinlock *lock)
+{
+	return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
+}
+
+static __always_inline void __raw_spin_lock(struct raw_spinlock *lock)
+{
+	PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
+}
+
+static __always_inline void __raw_spin_lock_flags(struct raw_spinlock *lock,
+						  unsigned long flags)
+{
+	PVOP_VCALL2(pv_lock_ops.spin_lock_flags, lock, flags);
+}
+
+static __always_inline int __raw_spin_trylock(struct raw_spinlock *lock)
+{
+	return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
+}
+
+static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
+{
+	PVOP_VCALL1(pv_lock_ops.spin_unlock, lock);
+}
+
+#endif
+
+/* These all sit in the .parainstructions section to tell us what to patch. */
+struct paravirt_patch_site {
+	u8 *instr; 		/* original instructions */
+	u8 instrtype;		/* type of this instruction */
+	u8 len;			/* length of original instruction */
+	u16 clobbers;		/* what registers you may clobber */
+};
+
+extern struct paravirt_patch_site __parainstructions[],
+	__parainstructions_end[];
+
+#ifdef CONFIG_X86_32
+#define PV_SAVE_REGS "pushl %%ecx; pushl %%edx;"
+#define PV_RESTORE_REGS "popl %%edx; popl %%ecx"
+#define PV_FLAGS_ARG "0"
+#define PV_EXTRA_CLOBBERS
+#define PV_VEXTRA_CLOBBERS
+#else
+/* We save some registers, but all of them, that's too much. We clobber all
+ * caller saved registers but the argument parameter */
+#define PV_SAVE_REGS "pushq %%rdi;"
+#define PV_RESTORE_REGS "popq %%rdi;"
+#define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx", "rsi"
+#define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx", "rsi"
+#define PV_FLAGS_ARG "D"
+#endif
+
+static inline unsigned long __raw_local_save_flags(void)
+{
+	unsigned long f;
+
+	asm volatile(paravirt_alt(PV_SAVE_REGS
+				  PARAVIRT_CALL
+				  PV_RESTORE_REGS)
+		     : "=a"(f)
+		     : paravirt_type(pv_irq_ops.save_fl),
+		       paravirt_clobber(CLBR_EAX)
+		     : "memory", "cc" PV_VEXTRA_CLOBBERS);
+	return f;
+}
+
+static inline void raw_local_irq_restore(unsigned long f)
+{
+	asm volatile(paravirt_alt(PV_SAVE_REGS
+				  PARAVIRT_CALL
+				  PV_RESTORE_REGS)
+		     : "=a"(f)
+		     : PV_FLAGS_ARG(f),
+		       paravirt_type(pv_irq_ops.restore_fl),
+		       paravirt_clobber(CLBR_EAX)
+		     : "memory", "cc" PV_EXTRA_CLOBBERS);
+}
+
+static inline void raw_local_irq_disable(void)
+{
+	asm volatile(paravirt_alt(PV_SAVE_REGS
+				  PARAVIRT_CALL
+				  PV_RESTORE_REGS)
+		     :
+		     : paravirt_type(pv_irq_ops.irq_disable),
+		       paravirt_clobber(CLBR_EAX)
+		     : "memory", "eax", "cc" PV_EXTRA_CLOBBERS);
+}
+
+static inline void raw_local_irq_enable(void)
+{
+	asm volatile(paravirt_alt(PV_SAVE_REGS
+				  PARAVIRT_CALL
+				  PV_RESTORE_REGS)
+		     :
+		     : paravirt_type(pv_irq_ops.irq_enable),
+		       paravirt_clobber(CLBR_EAX)
+		     : "memory", "eax", "cc" PV_EXTRA_CLOBBERS);
+}
+
+static inline unsigned long __raw_local_irq_save(void)
+{
+	unsigned long f;
+
+	f = __raw_local_save_flags();
+	raw_local_irq_disable();
+	return f;
+}
+
+
+/* Make sure as little as possible of this mess escapes. */
+#undef PARAVIRT_CALL
+#undef __PVOP_CALL
+#undef __PVOP_VCALL
+#undef PVOP_VCALL0
+#undef PVOP_CALL0
+#undef PVOP_VCALL1
+#undef PVOP_CALL1
+#undef PVOP_VCALL2
+#undef PVOP_CALL2
+#undef PVOP_VCALL3
+#undef PVOP_CALL3
+#undef PVOP_VCALL4
+#undef PVOP_CALL4
+
+#else  /* __ASSEMBLY__ */
+
+#define _PVSITE(ptype, clobbers, ops, word, algn)	\
+771:;						\
+	ops;					\
+772:;						\
+	.pushsection .parainstructions,"a";	\
+	 .align	algn;				\
+	 word 771b;				\
+	 .byte ptype;				\
+	 .byte 772b-771b;			\
+	 .short clobbers;			\
+	.popsection
+
+
+#ifdef CONFIG_X86_64
+#define PV_SAVE_REGS				\
+	push %rax;				\
+	push %rcx;				\
+	push %rdx;				\
+	push %rsi;				\
+	push %rdi;				\
+	push %r8;				\
+	push %r9;				\
+	push %r10;				\
+	push %r11
+#define PV_RESTORE_REGS				\
+	pop %r11;				\
+	pop %r10;				\
+	pop %r9;				\
+	pop %r8;				\
+	pop %rdi;				\
+	pop %rsi;				\
+	pop %rdx;				\
+	pop %rcx;				\
+	pop %rax
+#define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 8)
+#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
+#define PARA_INDIRECT(addr)	*addr(%rip)
+#else
+#define PV_SAVE_REGS   pushl %eax; pushl %edi; pushl %ecx; pushl %edx
+#define PV_RESTORE_REGS popl %edx; popl %ecx; popl %edi; popl %eax
+#define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 4)
+#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4)
+#define PARA_INDIRECT(addr)	*%cs:addr
+#endif
+
+#define INTERRUPT_RETURN						\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE,	\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret))
+
+#define DISABLE_INTERRUPTS(clobbers)					\
+	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
+		  PV_SAVE_REGS;						\
+		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable);	\
+		  PV_RESTORE_REGS;)			\
+
+#define ENABLE_INTERRUPTS(clobbers)					\
+	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,	\
+		  PV_SAVE_REGS;						\
+		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);	\
+		  PV_RESTORE_REGS;)
+
+#define USERGS_SYSRET32							\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32),	\
+		  CLBR_NONE,						\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32))
+
+#ifdef CONFIG_X86_32
+#define GET_CR0_INTO_EAX				\
+	push %ecx; push %edx;				\
+	call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0);	\
+	pop %edx; pop %ecx
+
+#define ENABLE_INTERRUPTS_SYSEXIT					\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),	\
+		  CLBR_NONE,						\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
+
+
+#else	/* !CONFIG_X86_32 */
+
+/*
+ * If swapgs is used while the userspace stack is still current,
+ * there's no way to call a pvop.  The PV replacement *must* be
+ * inlined, or the swapgs instruction must be trapped and emulated.
+ */
+#define SWAPGS_UNSAFE_STACK						\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
+		  swapgs)
+
+#define SWAPGS								\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
+		  PV_SAVE_REGS;						\
+		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs);		\
+		  PV_RESTORE_REGS					\
+		 )
+
+#define GET_CR2_INTO_RCX				\
+	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2);	\
+	movq %rax, %rcx;				\
+	xorq %rax, %rax;
+
+#define PARAVIRT_ADJUST_EXCEPTION_FRAME					\
+	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_adjust_exception_frame), \
+		  CLBR_NONE,						\
+		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_adjust_exception_frame))
+
+#define USERGS_SYSRET64							\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),	\
+		  CLBR_NONE,						\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+
+#define ENABLE_INTERRUPTS_SYSEXIT32					\
+	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),	\
+		  CLBR_NONE,						\
+		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
+#endif	/* CONFIG_X86_32 */
+
+#endif /* __ASSEMBLY__ */
+#endif /* CONFIG_PARAVIRT */
+#endif /* ASM_X86__PARAVIRT_H */
diff --git a/arch/x86/include/asm/parport.h b/arch/x86/include/asm/parport.h
new file mode 100644
index 000000000000..2e3dda4dc3d9
--- /dev/null
+++ b/arch/x86/include/asm/parport.h
@@ -0,0 +1,10 @@
+#ifndef ASM_X86__PARPORT_H
+#define ASM_X86__PARPORT_H
+
+static int __devinit parport_pc_find_isa_ports(int autoirq, int autodma);
+static int __devinit parport_pc_find_nonpci_ports(int autoirq, int autodma)
+{
+	return parport_pc_find_isa_ports(autoirq, autodma);
+}
+
+#endif /* ASM_X86__PARPORT_H */
diff --git a/arch/x86/include/asm/pat.h b/arch/x86/include/asm/pat.h
new file mode 100644
index 000000000000..482c3e3f9879
--- /dev/null
+++ b/arch/x86/include/asm/pat.h
@@ -0,0 +1,22 @@
+#ifndef ASM_X86__PAT_H
+#define ASM_X86__PAT_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_X86_PAT
+extern int pat_enabled;
+extern void validate_pat_support(struct cpuinfo_x86 *c);
+#else
+static const int pat_enabled;
+static inline void validate_pat_support(struct cpuinfo_x86 *c) { }
+#endif
+
+extern void pat_init(void);
+
+extern int reserve_memtype(u64 start, u64 end,
+		unsigned long req_type, unsigned long *ret_type);
+extern int free_memtype(u64 start, u64 end);
+
+extern void pat_disable(char *reason);
+
+#endif /* ASM_X86__PAT_H */
diff --git a/arch/x86/include/asm/pci-direct.h b/arch/x86/include/asm/pci-direct.h
new file mode 100644
index 000000000000..da42be07b690
--- /dev/null
+++ b/arch/x86/include/asm/pci-direct.h
@@ -0,0 +1,21 @@
+#ifndef ASM_X86__PCI_DIRECT_H
+#define ASM_X86__PCI_DIRECT_H
+
+#include <linux/types.h>
+
+/* Direct PCI access. This is used for PCI accesses in early boot before
+   the PCI subsystem works. */
+
+extern u32 read_pci_config(u8 bus, u8 slot, u8 func, u8 offset);
+extern u8 read_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset);
+extern u16 read_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset);
+extern void write_pci_config(u8 bus, u8 slot, u8 func, u8 offset, u32 val);
+extern void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val);
+extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val);
+
+extern int early_pci_allowed(void);
+
+extern unsigned int pci_early_dump_regs;
+extern void early_dump_pci_device(u8 bus, u8 slot, u8 func);
+extern void early_dump_pci_devices(void);
+#endif /* ASM_X86__PCI_DIRECT_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
new file mode 100644
index 000000000000..602583192991
--- /dev/null
+++ b/arch/x86/include/asm/pci.h
@@ -0,0 +1,114 @@
+#ifndef ASM_X86__PCI_H
+#define ASM_X86__PCI_H
+
+#include <linux/mm.h> /* for struct page */
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <asm/scatterlist.h>
+#include <asm/io.h>
+
+#ifdef __KERNEL__
+
+struct pci_sysdata {
+	int		domain;		/* PCI domain */
+	int		node;		/* NUMA node */
+#ifdef CONFIG_X86_64
+	void		*iommu;		/* IOMMU private data */
+#endif
+};
+
+extern int pci_routeirq;
+
+/* scan a bus after allocating a pci_sysdata for it */
+extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops,
+					    int node);
+extern struct pci_bus *pci_scan_bus_with_sysdata(int busno);
+
+static inline int pci_domain_nr(struct pci_bus *bus)
+{
+	struct pci_sysdata *sd = bus->sysdata;
+	return sd->domain;
+}
+
+static inline int pci_proc_domain(struct pci_bus *bus)
+{
+	return pci_domain_nr(bus);
+}
+
+
+/* Can be used to override the logic in pci_scan_bus for skipping
+   already-configured bus numbers - to be used for buggy BIOSes
+   or architectures with incomplete PCI setup by the loader */
+
+#ifdef CONFIG_PCI
+extern unsigned int pcibios_assign_all_busses(void);
+#else
+#define pcibios_assign_all_busses()	0
+#endif
+#define pcibios_scan_all_fns(a, b)	0
+
+extern unsigned long pci_mem_start;
+#define PCIBIOS_MIN_IO		0x1000
+#define PCIBIOS_MIN_MEM		(pci_mem_start)
+
+#define PCIBIOS_MIN_CARDBUS_IO	0x4000
+
+void pcibios_config_init(void);
+struct pci_bus *pcibios_scan_root(int bus);
+
+void pcibios_set_master(struct pci_dev *dev);
+void pcibios_penalize_isa_irq(int irq, int active);
+struct irq_routing_table *pcibios_get_irq_routing_table(void);
+int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
+
+
+#define HAVE_PCI_MMAP
+extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+			       enum pci_mmap_state mmap_state,
+			       int write_combine);
+
+
+#ifdef CONFIG_PCI
+extern void early_quirks(void);
+static inline void pci_dma_burst_advice(struct pci_dev *pdev,
+					enum pci_dma_burst_strategy *strat,
+					unsigned long *strategy_parameter)
+{
+	*strat = PCI_DMA_BURST_INFINITY;
+	*strategy_parameter = ~0UL;
+}
+#else
+static inline void early_quirks(void) { }
+#endif
+
+#endif  /* __KERNEL__ */
+
+#ifdef CONFIG_X86_32
+# include "pci_32.h"
+#else
+# include "pci_64.h"
+#endif
+
+/* implement the pci_ DMA API in terms of the generic device dma_ one */
+#include <asm-generic/pci-dma-compat.h>
+
+/* generic pci stuff */
+#include <asm-generic/pci.h>
+
+#ifdef CONFIG_NUMA
+/* Returns the node based on pci bus */
+static inline int __pcibus_to_node(struct pci_bus *bus)
+{
+	struct pci_sysdata *sd = bus->sysdata;
+
+	return sd->node;
+}
+
+static inline cpumask_t __pcibus_to_cpumask(struct pci_bus *bus)
+{
+	return node_to_cpumask(__pcibus_to_node(bus));
+}
+#endif
+
+#endif /* ASM_X86__PCI_H */
diff --git a/arch/x86/include/asm/pci_32.h b/arch/x86/include/asm/pci_32.h
new file mode 100644
index 000000000000..3f2288207c0c
--- /dev/null
+++ b/arch/x86/include/asm/pci_32.h
@@ -0,0 +1,34 @@
+#ifndef ASM_X86__PCI_32_H
+#define ASM_X86__PCI_32_H
+
+
+#ifdef __KERNEL__
+
+
+/* Dynamic DMA mapping stuff.
+ * i386 has everything mapped statically.
+ */
+
+struct pci_dev;
+
+/* The PCI address space does equal the physical memory
+ * address space.  The networking and block device layers use
+ * this boolean for bounce buffer decisions.
+ */
+#define PCI_DMA_BUS_IS_PHYS	(1)
+
+/* pci_unmap_{page,single} is a nop so... */
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	dma_addr_t ADDR_NAME[0];
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)	unsigned LEN_NAME[0];
+#define pci_unmap_addr(PTR, ADDR_NAME)	sizeof((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
+	do { break; } while (pci_unmap_addr(PTR, ADDR_NAME))
+#define pci_unmap_len(PTR, LEN_NAME)		sizeof((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
+	do { break; } while (pci_unmap_len(PTR, LEN_NAME))
+
+
+#endif /* __KERNEL__ */
+
+
+#endif /* ASM_X86__PCI_32_H */
diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h
new file mode 100644
index 000000000000..f72e12d5770e
--- /dev/null
+++ b/arch/x86/include/asm/pci_64.h
@@ -0,0 +1,66 @@
+#ifndef ASM_X86__PCI_64_H
+#define ASM_X86__PCI_64_H
+
+#ifdef __KERNEL__
+
+#ifdef CONFIG_CALGARY_IOMMU
+static inline void *pci_iommu(struct pci_bus *bus)
+{
+	struct pci_sysdata *sd = bus->sysdata;
+	return sd->iommu;
+}
+
+static inline void set_pci_iommu(struct pci_bus *bus, void *val)
+{
+	struct pci_sysdata *sd = bus->sysdata;
+	sd->iommu = val;
+}
+#endif /* CONFIG_CALGARY_IOMMU */
+
+extern int (*pci_config_read)(int seg, int bus, int dev, int fn,
+			      int reg, int len, u32 *value);
+extern int (*pci_config_write)(int seg, int bus, int dev, int fn,
+			       int reg, int len, u32 value);
+
+extern void dma32_reserve_bootmem(void);
+extern void pci_iommu_alloc(void);
+
+/* The PCI address space does equal the physical memory
+ * address space.  The networking and block device layers use
+ * this boolean for bounce buffer decisions
+ *
+ * On AMD64 it mostly equals, but we set it to zero if a hardware
+ * IOMMU (gart) of sotware IOMMU (swiotlb) is available.
+ */
+#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
+
+#if defined(CONFIG_GART_IOMMU) || defined(CONFIG_CALGARY_IOMMU)
+
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	\
+	dma_addr_t ADDR_NAME;
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)		\
+	__u32 LEN_NAME;
+#define pci_unmap_addr(PTR, ADDR_NAME)			\
+	((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)		\
+	(((PTR)->ADDR_NAME) = (VAL))
+#define pci_unmap_len(PTR, LEN_NAME)			\
+	((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL)		\
+	(((PTR)->LEN_NAME) = (VAL))
+
+#else
+/* No IOMMU */
+
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
+#define pci_unmap_addr(PTR, ADDR_NAME)		(0)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)	do { } while (0)
+#define pci_unmap_len(PTR, LEN_NAME)		(0)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL)	do { } while (0)
+
+#endif
+
+#endif /* __KERNEL__ */
+
+#endif /* ASM_X86__PCI_64_H */
diff --git a/arch/x86/include/asm/pda.h b/arch/x86/include/asm/pda.h
new file mode 100644
index 000000000000..80860afffbdb
--- /dev/null
+++ b/arch/x86/include/asm/pda.h
@@ -0,0 +1,137 @@
+#ifndef ASM_X86__PDA_H
+#define ASM_X86__PDA_H
+
+#ifndef __ASSEMBLY__
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/cache.h>
+#include <asm/page.h>
+
+/* Per processor datastructure. %gs points to it while the kernel runs */
+struct x8664_pda {
+	struct task_struct *pcurrent;	/* 0  Current process */
+	unsigned long data_offset;	/* 8 Per cpu data offset from linker
+					   address */
+	unsigned long kernelstack;	/* 16 top of kernel stack for current */
+	unsigned long oldrsp;		/* 24 user rsp for system call */
+	int irqcount;			/* 32 Irq nesting counter. Starts -1 */
+	unsigned int cpunumber;		/* 36 Logical CPU number */
+#ifdef CONFIG_CC_STACKPROTECTOR
+	unsigned long stack_canary;	/* 40 stack canary value */
+					/* gcc-ABI: this canary MUST be at
+					   offset 40!!! */
+#endif
+	char *irqstackptr;
+	short nodenumber;		/* number of current node (32k max) */
+	short in_bootmem;		/* pda lives in bootmem */
+	unsigned int __softirq_pending;
+	unsigned int __nmi_count;	/* number of NMI on this CPUs */
+	short mmu_state;
+	short isidle;
+	struct mm_struct *active_mm;
+	unsigned apic_timer_irqs;
+	unsigned irq0_irqs;
+	unsigned irq_resched_count;
+	unsigned irq_call_count;
+	unsigned irq_tlb_count;
+	unsigned irq_thermal_count;
+	unsigned irq_threshold_count;
+	unsigned irq_spurious_count;
+} ____cacheline_aligned_in_smp;
+
+extern struct x8664_pda **_cpu_pda;
+extern void pda_init(int);
+
+#define cpu_pda(i) (_cpu_pda[i])
+
+/*
+ * There is no fast way to get the base address of the PDA, all the accesses
+ * have to mention %fs/%gs.  So it needs to be done this Torvaldian way.
+ */
+extern void __bad_pda_field(void) __attribute__((noreturn));
+
+/*
+ * proxy_pda doesn't actually exist, but tell gcc it is accessed for
+ * all PDA accesses so it gets read/write dependencies right.
+ */
+extern struct x8664_pda _proxy_pda;
+
+#define pda_offset(field) offsetof(struct x8664_pda, field)
+
+#define pda_to_op(op, field, val)					\
+do {									\
+	typedef typeof(_proxy_pda.field) T__;				\
+	if (0) { T__ tmp__; tmp__ = (val); }	/* type checking */	\
+	switch (sizeof(_proxy_pda.field)) {				\
+	case 2:								\
+		asm(op "w %1,%%gs:%c2" :				\
+		    "+m" (_proxy_pda.field) :				\
+		    "ri" ((T__)val),					\
+		    "i"(pda_offset(field)));				\
+		break;							\
+	case 4:								\
+		asm(op "l %1,%%gs:%c2" :				\
+		    "+m" (_proxy_pda.field) :				\
+		    "ri" ((T__)val),					\
+		    "i" (pda_offset(field)));				\
+		break;							\
+	case 8:								\
+		asm(op "q %1,%%gs:%c2":					\
+		    "+m" (_proxy_pda.field) :				\
+		    "ri" ((T__)val),					\
+		    "i"(pda_offset(field)));				\
+		break;							\
+	default:							\
+		__bad_pda_field();					\
+	}								\
+} while (0)
+
+#define pda_from_op(op, field)			\
+({						\
+	typeof(_proxy_pda.field) ret__;		\
+	switch (sizeof(_proxy_pda.field)) {	\
+	case 2:					\
+		asm(op "w %%gs:%c1,%0" :	\
+		    "=r" (ret__) :		\
+		    "i" (pda_offset(field)),	\
+		    "m" (_proxy_pda.field));	\
+		break;				\
+	case 4:					\
+		asm(op "l %%gs:%c1,%0":		\
+		    "=r" (ret__):		\
+		    "i" (pda_offset(field)),	\
+		    "m" (_proxy_pda.field));	\
+		break;				\
+	case 8:					\
+		asm(op "q %%gs:%c1,%0":		\
+		    "=r" (ret__) :		\
+		    "i" (pda_offset(field)),	\
+		    "m" (_proxy_pda.field));	\
+		break;				\
+	default:				\
+		__bad_pda_field();		\
+	}					\
+	ret__;					\
+})
+
+#define read_pda(field)		pda_from_op("mov", field)
+#define write_pda(field, val)	pda_to_op("mov", field, val)
+#define add_pda(field, val)	pda_to_op("add", field, val)
+#define sub_pda(field, val)	pda_to_op("sub", field, val)
+#define or_pda(field, val)	pda_to_op("or", field, val)
+
+/* This is not atomic against other CPUs -- CPU preemption needs to be off */
+#define test_and_clear_bit_pda(bit, field)				\
+({									\
+	int old__;							\
+	asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0"			\
+		     : "=r" (old__), "+m" (_proxy_pda.field)		\
+		     : "dIr" (bit), "i" (pda_offset(field)) : "memory");\
+	old__;								\
+})
+
+#endif
+
+#define PDA_STACKOFFSET (5*8)
+
+#endif /* ASM_X86__PDA_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
new file mode 100644
index 000000000000..e10a1d0678cf
--- /dev/null
+++ b/arch/x86/include/asm/percpu.h
@@ -0,0 +1,218 @@
+#ifndef ASM_X86__PERCPU_H
+#define ASM_X86__PERCPU_H
+
+#ifdef CONFIG_X86_64
+#include <linux/compiler.h>
+
+/* Same as asm-generic/percpu.h, except that we store the per cpu offset
+   in the PDA. Longer term the PDA and every per cpu variable
+   should be just put into a single section and referenced directly
+   from %gs */
+
+#ifdef CONFIG_SMP
+#include <asm/pda.h>
+
+#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
+#define __my_cpu_offset read_pda(data_offset)
+
+#define per_cpu_offset(x) (__per_cpu_offset(x))
+
+#endif
+#include <asm-generic/percpu.h>
+
+DECLARE_PER_CPU(struct x8664_pda, pda);
+
+/*
+ * These are supposed to be implemented as a single instruction which
+ * operates on the per-cpu data base segment.  x86-64 doesn't have
+ * that yet, so this is a fairly inefficient workaround for the
+ * meantime.  The single instruction is atomic with respect to
+ * preemption and interrupts, so we need to explicitly disable
+ * interrupts here to achieve the same effect.  However, because it
+ * can be used from within interrupt-disable/enable, we can't actually
+ * disable interrupts; disabling preemption is enough.
+ */
+#define x86_read_percpu(var)						\
+	({								\
+		typeof(per_cpu_var(var)) __tmp;				\
+		preempt_disable();					\
+		__tmp = __get_cpu_var(var);				\
+		preempt_enable();					\
+		__tmp;							\
+	})
+
+#define x86_write_percpu(var, val)					\
+	do {								\
+		preempt_disable();					\
+		__get_cpu_var(var) = (val);				\
+		preempt_enable();					\
+	} while(0)
+
+#else /* CONFIG_X86_64 */
+
+#ifdef __ASSEMBLY__
+
+/*
+ * PER_CPU finds an address of a per-cpu variable.
+ *
+ * Args:
+ *    var - variable name
+ *    reg - 32bit register
+ *
+ * The resulting address is stored in the "reg" argument.
+ *
+ * Example:
+ *    PER_CPU(cpu_gdt_descr, %ebx)
+ */
+#ifdef CONFIG_SMP
+#define PER_CPU(var, reg)				\
+	movl %fs:per_cpu__##this_cpu_off, reg;		\
+	lea per_cpu__##var(reg), reg
+#define PER_CPU_VAR(var)	%fs:per_cpu__##var
+#else /* ! SMP */
+#define PER_CPU(var, reg)			\
+	movl $per_cpu__##var, reg
+#define PER_CPU_VAR(var)	per_cpu__##var
+#endif	/* SMP */
+
+#else /* ...!ASSEMBLY */
+
+/*
+ * PER_CPU finds an address of a per-cpu variable.
+ *
+ * Args:
+ *    var - variable name
+ *    cpu - 32bit register containing the current CPU number
+ *
+ * The resulting address is stored in the "cpu" argument.
+ *
+ * Example:
+ *    PER_CPU(cpu_gdt_descr, %ebx)
+ */
+#ifdef CONFIG_SMP
+
+#define __my_cpu_offset x86_read_percpu(this_cpu_off)
+
+/* fs segment starts at (positive) offset == __per_cpu_offset[cpu] */
+#define __percpu_seg "%%fs:"
+
+#else  /* !SMP */
+
+#define __percpu_seg ""
+
+#endif	/* SMP */
+
+#include <asm-generic/percpu.h>
+
+/* We can use this directly for local CPU (faster). */
+DECLARE_PER_CPU(unsigned long, this_cpu_off);
+
+/* For arch-specific code, we can use direct single-insn ops (they
+ * don't give an lvalue though). */
+extern void __bad_percpu_size(void);
+
+#define percpu_to_op(op, var, val)			\
+do {							\
+	typedef typeof(var) T__;			\
+	if (0) {					\
+		T__ tmp__;				\
+		tmp__ = (val);				\
+	}						\
+	switch (sizeof(var)) {				\
+	case 1:						\
+		asm(op "b %1,"__percpu_seg"%0"		\
+		    : "+m" (var)			\
+		    : "ri" ((T__)val));			\
+		break;					\
+	case 2:						\
+		asm(op "w %1,"__percpu_seg"%0"		\
+		    : "+m" (var)			\
+		    : "ri" ((T__)val));			\
+		break;					\
+	case 4:						\
+		asm(op "l %1,"__percpu_seg"%0"		\
+		    : "+m" (var)			\
+		    : "ri" ((T__)val));			\
+		break;					\
+	default: __bad_percpu_size();			\
+	}						\
+} while (0)
+
+#define percpu_from_op(op, var)				\
+({							\
+	typeof(var) ret__;				\
+	switch (sizeof(var)) {				\
+	case 1:						\
+		asm(op "b "__percpu_seg"%1,%0"		\
+		    : "=r" (ret__)			\
+		    : "m" (var));			\
+		break;					\
+	case 2:						\
+		asm(op "w "__percpu_seg"%1,%0"		\
+		    : "=r" (ret__)			\
+		    : "m" (var));			\
+		break;					\
+	case 4:						\
+		asm(op "l "__percpu_seg"%1,%0"		\
+		    : "=r" (ret__)			\
+		    : "m" (var));			\
+		break;					\
+	default: __bad_percpu_size();			\
+	}						\
+	ret__;						\
+})
+
+#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
+#define x86_write_percpu(var, val) percpu_to_op("mov", per_cpu__##var, val)
+#define x86_add_percpu(var, val) percpu_to_op("add", per_cpu__##var, val)
+#define x86_sub_percpu(var, val) percpu_to_op("sub", per_cpu__##var, val)
+#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
+#endif /* !__ASSEMBLY__ */
+#endif /* !CONFIG_X86_64 */
+
+#ifdef CONFIG_SMP
+
+/*
+ * Define the "EARLY_PER_CPU" macros.  These are used for some per_cpu
+ * variables that are initialized and accessed before there are per_cpu
+ * areas allocated.
+ */
+
+#define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)			\
+	DEFINE_PER_CPU(_type, _name) = _initvalue;			\
+	__typeof__(_type) _name##_early_map[NR_CPUS] __initdata =	\
+				{ [0 ... NR_CPUS-1] = _initvalue };	\
+	__typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map
+
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
+	EXPORT_PER_CPU_SYMBOL(_name)
+
+#define DECLARE_EARLY_PER_CPU(_type, _name)			\
+	DECLARE_PER_CPU(_type, _name);				\
+	extern __typeof__(_type) *_name##_early_ptr;		\
+	extern __typeof__(_type)  _name##_early_map[]
+
+#define	early_per_cpu_ptr(_name) (_name##_early_ptr)
+#define	early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
+#define	early_per_cpu(_name, _cpu) 				\
+	(early_per_cpu_ptr(_name) ?				\
+		early_per_cpu_ptr(_name)[_cpu] :		\
+		per_cpu(_name, _cpu))
+
+#else	/* !CONFIG_SMP */
+#define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)		\
+	DEFINE_PER_CPU(_type, _name) = _initvalue
+
+#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
+	EXPORT_PER_CPU_SYMBOL(_name)
+
+#define DECLARE_EARLY_PER_CPU(_type, _name)			\
+	DECLARE_PER_CPU(_type, _name)
+
+#define	early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
+#define	early_per_cpu_ptr(_name) NULL
+/* no early_per_cpu_map() */
+
+#endif	/* !CONFIG_SMP */
+
+#endif /* ASM_X86__PERCPU_H */
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
new file mode 100644
index 000000000000..3cd23adedae8
--- /dev/null
+++ b/arch/x86/include/asm/pgalloc.h
@@ -0,0 +1,114 @@
+#ifndef ASM_X86__PGALLOC_H
+#define ASM_X86__PGALLOC_H
+
+#include <linux/threads.h>
+#include <linux/mm.h>		/* for struct page */
+#include <linux/pagemap.h>
+
+static inline int  __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; }
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define paravirt_pgd_alloc(mm)	__paravirt_pgd_alloc(mm)
+static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {}
+static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)	{}
+static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)	{}
+static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
+					    unsigned long start, unsigned long count) {}
+static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)	{}
+static inline void paravirt_release_pte(unsigned long pfn) {}
+static inline void paravirt_release_pmd(unsigned long pfn) {}
+static inline void paravirt_release_pud(unsigned long pfn) {}
+#endif
+
+/*
+ * Allocate and free page tables.
+ */
+extern pgd_t *pgd_alloc(struct mm_struct *);
+extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
+
+extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
+extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long);
+
+/* Should really implement gc for free page table pages. This could be
+   done with a reference count in struct page. */
+
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	BUG_ON((unsigned long)pte & (PAGE_SIZE-1));
+	free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, struct page *pte)
+{
+	__free_page(pte);
+}
+
+extern void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
+
+static inline void pmd_populate_kernel(struct mm_struct *mm,
+				       pmd_t *pmd, pte_t *pte)
+{
+	paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT);
+	set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
+}
+
+static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
+				struct page *pte)
+{
+	unsigned long pfn = page_to_pfn(pte);
+
+	paravirt_alloc_pte(mm, pfn);
+	set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE));
+}
+
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
+#if PAGETABLE_LEVELS > 2
+static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
+{
+	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+	free_page((unsigned long)pmd);
+}
+
+extern void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
+
+#ifdef CONFIG_X86_PAE
+extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
+#else	/* !CONFIG_X86_PAE */
+static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
+{
+	paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
+	set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd)));
+}
+#endif	/* CONFIG_X86_PAE */
+
+#if PAGETABLE_LEVELS > 3
+static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
+{
+	paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT);
+	set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud)));
+}
+
+static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+}
+
+static inline void pud_free(struct mm_struct *mm, pud_t *pud)
+{
+	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
+	free_page((unsigned long)pud);
+}
+
+extern void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud);
+#endif	/* PAGETABLE_LEVELS > 3 */
+#endif	/* PAGETABLE_LEVELS > 2 */
+
+#endif /* ASM_X86__PGALLOC_H */
diff --git a/arch/x86/include/asm/pgtable-2level-defs.h b/arch/x86/include/asm/pgtable-2level-defs.h
new file mode 100644
index 000000000000..7ec48f4e5347
--- /dev/null
+++ b/arch/x86/include/asm/pgtable-2level-defs.h
@@ -0,0 +1,20 @@
+#ifndef ASM_X86__PGTABLE_2LEVEL_DEFS_H
+#define ASM_X86__PGTABLE_2LEVEL_DEFS_H
+
+#define SHARED_KERNEL_PMD	0
+
+/*
+ * traditional i386 two-level paging structure:
+ */
+
+#define PGDIR_SHIFT	22
+#define PTRS_PER_PGD	1024
+
+/*
+ * the i386 is two-level, so we don't really have any
+ * PMD directory physically.
+ */
+
+#define PTRS_PER_PTE	1024
+
+#endif /* ASM_X86__PGTABLE_2LEVEL_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
new file mode 100644
index 000000000000..81762081dcd8
--- /dev/null
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -0,0 +1,79 @@
+#ifndef ASM_X86__PGTABLE_2LEVEL_H
+#define ASM_X86__PGTABLE_2LEVEL_H
+
+#define pte_ERROR(e) \
+	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
+#define pgd_ERROR(e) \
+	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+
+/*
+ * Certain architectures need to do special things when PTEs
+ * within a page table are directly modified.  Thus, the following
+ * hook is made available.
+ */
+static inline void native_set_pte(pte_t *ptep , pte_t pte)
+{
+	*ptep = pte;
+}
+
+static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+	*pmdp = pmd;
+}
+
+static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
+{
+	native_set_pte(ptep, pte);
+}
+
+static inline void native_set_pte_present(struct mm_struct *mm,
+					  unsigned long addr,
+					  pte_t *ptep, pte_t pte)
+{
+	native_set_pte(ptep, pte);
+}
+
+static inline void native_pmd_clear(pmd_t *pmdp)
+{
+	native_set_pmd(pmdp, __pmd(0));
+}
+
+static inline void native_pte_clear(struct mm_struct *mm,
+				    unsigned long addr, pte_t *xp)
+{
+	*xp = native_make_pte(0);
+}
+
+#ifdef CONFIG_SMP
+static inline pte_t native_ptep_get_and_clear(pte_t *xp)
+{
+	return __pte(xchg(&xp->pte_low, 0));
+}
+#else
+#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
+#endif
+
+#define pte_none(x)		(!(x).pte_low)
+
+/*
+ * Bits 0, 6 and 7 are taken, split up the 29 bits of offset
+ * into this range:
+ */
+#define PTE_FILE_MAX_BITS	29
+
+#define pte_to_pgoff(pte)						\
+	((((pte).pte_low >> 1) & 0x1f) + (((pte).pte_low >> 8) << 5))
+
+#define pgoff_to_pte(off)						\
+	((pte_t) { .pte_low = (((off) & 0x1f) << 1) +			\
+			(((off) >> 5) << 8) + _PAGE_FILE })
+
+/* Encode and de-code a swap entry */
+#define __swp_type(x)			(((x).val >> 1) & 0x1f)
+#define __swp_offset(x)			((x).val >> 8)
+#define __swp_entry(type, offset)				\
+	((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { (pte).pte_low })
+#define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
+
+#endif /* ASM_X86__PGTABLE_2LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable-3level-defs.h b/arch/x86/include/asm/pgtable-3level-defs.h
new file mode 100644
index 000000000000..c05fe6ff3720
--- /dev/null
+++ b/arch/x86/include/asm/pgtable-3level-defs.h
@@ -0,0 +1,28 @@
+#ifndef ASM_X86__PGTABLE_3LEVEL_DEFS_H
+#define ASM_X86__PGTABLE_3LEVEL_DEFS_H
+
+#ifdef CONFIG_PARAVIRT
+#define SHARED_KERNEL_PMD	(pv_info.shared_kernel_pmd)
+#else
+#define SHARED_KERNEL_PMD	1
+#endif
+
+/*
+ * PGDIR_SHIFT determines what a top-level page table entry can map
+ */
+#define PGDIR_SHIFT	30
+#define PTRS_PER_PGD	4
+
+/*
+ * PMD_SHIFT determines the size of the area a middle-level
+ * page table can map
+ */
+#define PMD_SHIFT	21
+#define PTRS_PER_PMD	512
+
+/*
+ * entries per page directory level
+ */
+#define PTRS_PER_PTE	512
+
+#endif /* ASM_X86__PGTABLE_3LEVEL_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
new file mode 100644
index 000000000000..75f4276b5ddb
--- /dev/null
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -0,0 +1,175 @@
+#ifndef ASM_X86__PGTABLE_3LEVEL_H
+#define ASM_X86__PGTABLE_3LEVEL_H
+
+/*
+ * Intel Physical Address Extension (PAE) Mode - three-level page
+ * tables on PPro+ CPUs.
+ *
+ * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
+ */
+
+#define pte_ERROR(e)							\
+	printk("%s:%d: bad pte %p(%08lx%08lx).\n",			\
+	       __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
+#define pmd_ERROR(e)							\
+	printk("%s:%d: bad pmd %p(%016Lx).\n",				\
+	       __FILE__, __LINE__, &(e), pmd_val(e))
+#define pgd_ERROR(e)							\
+	printk("%s:%d: bad pgd %p(%016Lx).\n",				\
+	       __FILE__, __LINE__, &(e), pgd_val(e))
+
+static inline int pud_none(pud_t pud)
+{
+	return pud_val(pud) == 0;
+}
+
+static inline int pud_bad(pud_t pud)
+{
+	return (pud_val(pud) & ~(PTE_PFN_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0;
+}
+
+static inline int pud_present(pud_t pud)
+{
+	return pud_val(pud) & _PAGE_PRESENT;
+}
+
+/* Rules for using set_pte: the pte being assigned *must* be
+ * either not present or in a state where the hardware will
+ * not attempt to update the pte.  In places where this is
+ * not possible, use pte_get_and_clear to obtain the old pte
+ * value and then use set_pte to update it.  -ben
+ */
+static inline void native_set_pte(pte_t *ptep, pte_t pte)
+{
+	ptep->pte_high = pte.pte_high;
+	smp_wmb();
+	ptep->pte_low = pte.pte_low;
+}
+
+/*
+ * Since this is only called on user PTEs, and the page fault handler
+ * must handle the already racy situation of simultaneous page faults,
+ * we are justified in merely clearing the PTE present bit, followed
+ * by a set.  The ordering here is important.
+ */
+static inline void native_set_pte_present(struct mm_struct *mm,
+					  unsigned long addr,
+					  pte_t *ptep, pte_t pte)
+{
+	ptep->pte_low = 0;
+	smp_wmb();
+	ptep->pte_high = pte.pte_high;
+	smp_wmb();
+	ptep->pte_low = pte.pte_low;
+}
+
+static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
+{
+	set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
+}
+
+static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+	set_64bit((unsigned long long *)(pmdp), native_pmd_val(pmd));
+}
+
+static inline void native_set_pud(pud_t *pudp, pud_t pud)
+{
+	set_64bit((unsigned long long *)(pudp), native_pud_val(pud));
+}
+
+/*
+ * For PTEs and PDEs, we must clear the P-bit first when clearing a page table
+ * entry, so clear the bottom half first and enforce ordering with a compiler
+ * barrier.
+ */
+static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
+				    pte_t *ptep)
+{
+	ptep->pte_low = 0;
+	smp_wmb();
+	ptep->pte_high = 0;
+}
+
+static inline void native_pmd_clear(pmd_t *pmd)
+{
+	u32 *tmp = (u32 *)pmd;
+	*tmp = 0;
+	smp_wmb();
+	*(tmp + 1) = 0;
+}
+
+static inline void pud_clear(pud_t *pudp)
+{
+	unsigned long pgd;
+
+	set_pud(pudp, __pud(0));
+
+	/*
+	 * According to Intel App note "TLBs, Paging-Structure Caches,
+	 * and Their Invalidation", April 2007, document 317080-001,
+	 * section 8.1: in PAE mode we explicitly have to flush the
+	 * TLB via cr3 if the top-level pgd is changed...
+	 *
+	 * Make sure the pud entry we're updating is within the
+	 * current pgd to avoid unnecessary TLB flushes.
+	 */
+	pgd = read_cr3();
+	if (__pa(pudp) >= pgd && __pa(pudp) <
+	    (pgd + sizeof(pgd_t)*PTRS_PER_PGD))
+		write_cr3(pgd);
+}
+
+#define pud_page(pud) ((struct page *) __va(pud_val(pud) & PTE_PFN_MASK))
+
+#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PTE_PFN_MASK))
+
+
+/* Find an entry in the second-level page table.. */
+#define pmd_offset(pud, address) ((pmd_t *)pud_page(*(pud)) +	\
+				  pmd_index(address))
+
+#ifdef CONFIG_SMP
+static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
+{
+	pte_t res;
+
+	/* xchg acts as a barrier before the setting of the high bits */
+	res.pte_low = xchg(&ptep->pte_low, 0);
+	res.pte_high = ptep->pte_high;
+	ptep->pte_high = 0;
+
+	return res;
+}
+#else
+#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
+#endif
+
+#define __HAVE_ARCH_PTE_SAME
+static inline int pte_same(pte_t a, pte_t b)
+{
+	return a.pte_low == b.pte_low && a.pte_high == b.pte_high;
+}
+
+static inline int pte_none(pte_t pte)
+{
+	return !pte.pte_low && !pte.pte_high;
+}
+
+/*
+ * Bits 0, 6 and 7 are taken in the low part of the pte,
+ * put the 32 bits of offset into the high part.
+ */
+#define pte_to_pgoff(pte) ((pte).pte_high)
+#define pgoff_to_pte(off)						\
+	((pte_t) { { .pte_low = _PAGE_FILE, .pte_high = (off) } })
+#define PTE_FILE_MAX_BITS       32
+
+/* Encode and de-code a swap entry */
+#define __swp_type(x)			(((x).val) & 0x1f)
+#define __swp_offset(x)			((x).val >> 5)
+#define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) << 5})
+#define __pte_to_swp_entry(pte)		((swp_entry_t){ (pte).pte_high })
+#define __swp_entry_to_pte(x)		((pte_t){ { .pte_high = (x).val } })
+
+#endif /* ASM_X86__PGTABLE_3LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
new file mode 100644
index 000000000000..88a53b1a17f0
--- /dev/null
+++ b/arch/x86/include/asm/pgtable.h
@@ -0,0 +1,561 @@
+#ifndef ASM_X86__PGTABLE_H
+#define ASM_X86__PGTABLE_H
+
+#define FIRST_USER_ADDRESS	0
+
+#define _PAGE_BIT_PRESENT	0	/* is present */
+#define _PAGE_BIT_RW		1	/* writeable */
+#define _PAGE_BIT_USER		2	/* userspace addressable */
+#define _PAGE_BIT_PWT		3	/* page write through */
+#define _PAGE_BIT_PCD		4	/* page cache disabled */
+#define _PAGE_BIT_ACCESSED	5	/* was accessed (raised by CPU) */
+#define _PAGE_BIT_DIRTY		6	/* was written to (raised by CPU) */
+#define _PAGE_BIT_FILE		6
+#define _PAGE_BIT_PSE		7	/* 4 MB (or 2MB) page */
+#define _PAGE_BIT_PAT		7	/* on 4KB pages */
+#define _PAGE_BIT_GLOBAL	8	/* Global TLB entry PPro+ */
+#define _PAGE_BIT_UNUSED1	9	/* available for programmer */
+#define _PAGE_BIT_IOMAP		10	/* flag used to indicate IO mapping */
+#define _PAGE_BIT_UNUSED3	11
+#define _PAGE_BIT_PAT_LARGE	12	/* On 2MB or 1GB pages */
+#define _PAGE_BIT_SPECIAL	_PAGE_BIT_UNUSED1
+#define _PAGE_BIT_CPA_TEST	_PAGE_BIT_UNUSED1
+#define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
+
+#define _PAGE_PRESENT	(_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
+#define _PAGE_RW	(_AT(pteval_t, 1) << _PAGE_BIT_RW)
+#define _PAGE_USER	(_AT(pteval_t, 1) << _PAGE_BIT_USER)
+#define _PAGE_PWT	(_AT(pteval_t, 1) << _PAGE_BIT_PWT)
+#define _PAGE_PCD	(_AT(pteval_t, 1) << _PAGE_BIT_PCD)
+#define _PAGE_ACCESSED	(_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
+#define _PAGE_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
+#define _PAGE_PSE	(_AT(pteval_t, 1) << _PAGE_BIT_PSE)
+#define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
+#define _PAGE_UNUSED1	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
+#define _PAGE_IOMAP	(_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
+#define _PAGE_UNUSED3	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
+#define _PAGE_PAT	(_AT(pteval_t, 1) << _PAGE_BIT_PAT)
+#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
+#define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
+#define _PAGE_CPA_TEST	(_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
+#define __HAVE_ARCH_PTE_SPECIAL
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+#define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
+#else
+#define _PAGE_NX	(_AT(pteval_t, 0))
+#endif
+
+/* If _PAGE_PRESENT is clear, we use these: */
+#define _PAGE_FILE	_PAGE_DIRTY	/* nonlinear file mapping,
+					 * saved PTE; unset:swap */
+#define _PAGE_PROTNONE	_PAGE_PSE	/* if the user mapped it with PROT_NONE;
+					   pte_present gives true */
+
+#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |	\
+			 _PAGE_ACCESSED | _PAGE_DIRTY)
+#define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |	\
+			 _PAGE_DIRTY)
+
+/* Set of bits not changed in pte_modify */
+#define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
+			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)
+
+#define _PAGE_CACHE_MASK	(_PAGE_PCD | _PAGE_PWT)
+#define _PAGE_CACHE_WB		(0)
+#define _PAGE_CACHE_WC		(_PAGE_PWT)
+#define _PAGE_CACHE_UC_MINUS	(_PAGE_PCD)
+#define _PAGE_CACHE_UC		(_PAGE_PCD | _PAGE_PWT)
+
+#define PAGE_NONE	__pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
+#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
+				 _PAGE_ACCESSED | _PAGE_NX)
+
+#define PAGE_SHARED_EXEC	__pgprot(_PAGE_PRESENT | _PAGE_RW |	\
+					 _PAGE_USER | _PAGE_ACCESSED)
+#define PAGE_COPY_NOEXEC	__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
+					 _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_COPY_EXEC		__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
+					 _PAGE_ACCESSED)
+#define PAGE_COPY		PAGE_COPY_NOEXEC
+#define PAGE_READONLY		__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
+					 _PAGE_ACCESSED | _PAGE_NX)
+#define PAGE_READONLY_EXEC	__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
+					 _PAGE_ACCESSED)
+
+#define __PAGE_KERNEL_EXEC						\
+	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
+#define __PAGE_KERNEL		(__PAGE_KERNEL_EXEC | _PAGE_NX)
+
+#define __PAGE_KERNEL_RO		(__PAGE_KERNEL & ~_PAGE_RW)
+#define __PAGE_KERNEL_RX		(__PAGE_KERNEL_EXEC & ~_PAGE_RW)
+#define __PAGE_KERNEL_EXEC_NOCACHE	(__PAGE_KERNEL_EXEC | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_KERNEL_WC		(__PAGE_KERNEL | _PAGE_CACHE_WC)
+#define __PAGE_KERNEL_NOCACHE		(__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_KERNEL_UC_MINUS		(__PAGE_KERNEL | _PAGE_PCD)
+#define __PAGE_KERNEL_VSYSCALL		(__PAGE_KERNEL_RX | _PAGE_USER)
+#define __PAGE_KERNEL_VSYSCALL_NOCACHE	(__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
+#define __PAGE_KERNEL_LARGE		(__PAGE_KERNEL | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_NOCACHE	(__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
+#define __PAGE_KERNEL_LARGE_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)
+
+#define __PAGE_KERNEL_IO		(__PAGE_KERNEL | _PAGE_IOMAP)
+#define __PAGE_KERNEL_IO_NOCACHE	(__PAGE_KERNEL_NOCACHE | _PAGE_IOMAP)
+#define __PAGE_KERNEL_IO_UC_MINUS	(__PAGE_KERNEL_UC_MINUS | _PAGE_IOMAP)
+#define __PAGE_KERNEL_IO_WC		(__PAGE_KERNEL_WC | _PAGE_IOMAP)
+
+#define PAGE_KERNEL			__pgprot(__PAGE_KERNEL)
+#define PAGE_KERNEL_RO			__pgprot(__PAGE_KERNEL_RO)
+#define PAGE_KERNEL_EXEC		__pgprot(__PAGE_KERNEL_EXEC)
+#define PAGE_KERNEL_RX			__pgprot(__PAGE_KERNEL_RX)
+#define PAGE_KERNEL_WC			__pgprot(__PAGE_KERNEL_WC)
+#define PAGE_KERNEL_NOCACHE		__pgprot(__PAGE_KERNEL_NOCACHE)
+#define PAGE_KERNEL_UC_MINUS		__pgprot(__PAGE_KERNEL_UC_MINUS)
+#define PAGE_KERNEL_EXEC_NOCACHE	__pgprot(__PAGE_KERNEL_EXEC_NOCACHE)
+#define PAGE_KERNEL_LARGE		__pgprot(__PAGE_KERNEL_LARGE)
+#define PAGE_KERNEL_LARGE_NOCACHE	__pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
+#define PAGE_KERNEL_LARGE_EXEC		__pgprot(__PAGE_KERNEL_LARGE_EXEC)
+#define PAGE_KERNEL_VSYSCALL		__pgprot(__PAGE_KERNEL_VSYSCALL)
+#define PAGE_KERNEL_VSYSCALL_NOCACHE	__pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
+
+#define PAGE_KERNEL_IO			__pgprot(__PAGE_KERNEL_IO)
+#define PAGE_KERNEL_IO_NOCACHE		__pgprot(__PAGE_KERNEL_IO_NOCACHE)
+#define PAGE_KERNEL_IO_UC_MINUS		__pgprot(__PAGE_KERNEL_IO_UC_MINUS)
+#define PAGE_KERNEL_IO_WC		__pgprot(__PAGE_KERNEL_IO_WC)
+
+/*         xwr */
+#define __P000	PAGE_NONE
+#define __P001	PAGE_READONLY
+#define __P010	PAGE_COPY
+#define __P011	PAGE_COPY
+#define __P100	PAGE_READONLY_EXEC
+#define __P101	PAGE_READONLY_EXEC
+#define __P110	PAGE_COPY_EXEC
+#define __P111	PAGE_COPY_EXEC
+
+#define __S000	PAGE_NONE
+#define __S001	PAGE_READONLY
+#define __S010	PAGE_SHARED
+#define __S011	PAGE_SHARED
+#define __S100	PAGE_READONLY_EXEC
+#define __S101	PAGE_READONLY_EXEC
+#define __S110	PAGE_SHARED_EXEC
+#define __S111	PAGE_SHARED_EXEC
+
+/*
+ * early identity mapping  pte attrib macros.
+ */
+#ifdef CONFIG_X86_64
+#define __PAGE_KERNEL_IDENT_LARGE_EXEC	__PAGE_KERNEL_LARGE_EXEC
+#else
+/*
+ * For PDE_IDENT_ATTR include USER bit. As the PDE and PTE protection
+ * bits are combined, this will alow user to access the high address mapped
+ * VDSO in the presence of CONFIG_COMPAT_VDSO
+ */
+#define PTE_IDENT_ATTR	 0x003		/* PRESENT+RW */
+#define PDE_IDENT_ATTR	 0x067		/* PRESENT+RW+USER+DIRTY+ACCESSED */
+#define PGD_IDENT_ATTR	 0x001		/* PRESENT (no other attributes) */
+#endif
+
+#ifndef __ASSEMBLY__
+
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
+#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
+
+extern spinlock_t pgd_lock;
+extern struct list_head pgd_list;
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+static inline int pte_dirty(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_DIRTY;
+}
+
+static inline int pte_young(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_ACCESSED;
+}
+
+static inline int pte_write(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_RW;
+}
+
+static inline int pte_file(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_FILE;
+}
+
+static inline int pte_huge(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_PSE;
+}
+
+static inline int pte_global(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_GLOBAL;
+}
+
+static inline int pte_exec(pte_t pte)
+{
+	return !(pte_flags(pte) & _PAGE_NX);
+}
+
+static inline int pte_special(pte_t pte)
+{
+	return pte_flags(pte) & _PAGE_SPECIAL;
+}
+
+static inline unsigned long pte_pfn(pte_t pte)
+{
+	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
+}
+
+#define pte_page(pte)	pfn_to_page(pte_pfn(pte))
+
+static inline int pmd_large(pmd_t pte)
+{
+	return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
+		(_PAGE_PSE | _PAGE_PRESENT);
+}
+
+static inline pte_t pte_mkclean(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkold(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
+}
+
+static inline pte_t pte_wrprotect(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_RW);
+}
+
+static inline pte_t pte_mkexec(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_NX);
+}
+
+static inline pte_t pte_mkdirty(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_DIRTY);
+}
+
+static inline pte_t pte_mkyoung(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_ACCESSED);
+}
+
+static inline pte_t pte_mkwrite(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_RW);
+}
+
+static inline pte_t pte_mkhuge(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_PSE);
+}
+
+static inline pte_t pte_clrhuge(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_PSE);
+}
+
+static inline pte_t pte_mkglobal(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_GLOBAL);
+}
+
+static inline pte_t pte_clrglobal(pte_t pte)
+{
+	return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
+}
+
+static inline pte_t pte_mkspecial(pte_t pte)
+{
+	return __pte(pte_val(pte) | _PAGE_SPECIAL);
+}
+
+extern pteval_t __supported_pte_mask;
+
+static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
+{
+	return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) |
+		      pgprot_val(pgprot)) & __supported_pte_mask);
+}
+
+static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
+{
+	return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) |
+		      pgprot_val(pgprot)) & __supported_pte_mask);
+}
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	pteval_t val = pte_val(pte);
+
+	/*
+	 * Chop off the NX bit (if present), and add the NX portion of
+	 * the newprot (if present):
+	 */
+	val &= _PAGE_CHG_MASK;
+	val |= pgprot_val(newprot) & (~_PAGE_CHG_MASK) & __supported_pte_mask;
+
+	return __pte(val);
+}
+
+/* mprotect needs to preserve PAT bits when updating vm_page_prot */
+#define pgprot_modify pgprot_modify
+static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
+{
+	pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK;
+	pgprotval_t addbits = pgprot_val(newprot);
+	return __pgprot(preservebits | addbits);
+}
+
+#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)
+
+#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
+
+#ifndef __ASSEMBLY__
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+struct file;
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+                              unsigned long size, pgprot_t vma_prot);
+int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
+                              unsigned long size, pgprot_t *vma_prot);
+#endif
+
+/* Install a pte for a particular vaddr in kernel space. */
+void set_pte_vaddr(unsigned long vaddr, pte_t pte);
+
+#ifdef CONFIG_X86_32
+extern void native_pagetable_setup_start(pgd_t *base);
+extern void native_pagetable_setup_done(pgd_t *base);
+#else
+static inline void native_pagetable_setup_start(pgd_t *base) {}
+static inline void native_pagetable_setup_done(pgd_t *base) {}
+#endif
+
+extern int arch_report_meminfo(char *page);
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else  /* !CONFIG_PARAVIRT */
+#define set_pte(ptep, pte)		native_set_pte(ptep, pte)
+#define set_pte_at(mm, addr, ptep, pte)	native_set_pte_at(mm, addr, ptep, pte)
+
+#define set_pte_present(mm, addr, ptep, pte)				\
+	native_set_pte_present(mm, addr, ptep, pte)
+#define set_pte_atomic(ptep, pte)					\
+	native_set_pte_atomic(ptep, pte)
+
+#define set_pmd(pmdp, pmd)		native_set_pmd(pmdp, pmd)
+
+#ifndef __PAGETABLE_PUD_FOLDED
+#define set_pgd(pgdp, pgd)		native_set_pgd(pgdp, pgd)
+#define pgd_clear(pgd)			native_pgd_clear(pgd)
+#endif
+
+#ifndef set_pud
+# define set_pud(pudp, pud)		native_set_pud(pudp, pud)
+#endif
+
+#ifndef __PAGETABLE_PMD_FOLDED
+#define pud_clear(pud)			native_pud_clear(pud)
+#endif
+
+#define pte_clear(mm, addr, ptep)	native_pte_clear(mm, addr, ptep)
+#define pmd_clear(pmd)			native_pmd_clear(pmd)
+
+#define pte_update(mm, addr, ptep)              do { } while (0)
+#define pte_update_defer(mm, addr, ptep)        do { } while (0)
+
+static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
+{
+	native_pagetable_setup_start(base);
+}
+
+static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
+{
+	native_pagetable_setup_done(base);
+}
+#endif	/* CONFIG_PARAVIRT */
+
+#endif	/* __ASSEMBLY__ */
+
+#ifdef CONFIG_X86_32
+# include "pgtable_32.h"
+#else
+# include "pgtable_64.h"
+#endif
+
+/*
+ * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
+ *
+ * this macro returns the index of the entry in the pgd page which would
+ * control the given virtual address
+ */
+#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
+
+/*
+ * pgd_offset() returns a (pgd_t *)
+ * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
+ */
+#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
+/*
+ * a shortcut which implies the use of the kernel's pgd, instead
+ * of a process's
+ */
+#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
+
+
+#define KERNEL_PGD_BOUNDARY	pgd_index(PAGE_OFFSET)
+#define KERNEL_PGD_PTRS		(PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
+
+#ifndef __ASSEMBLY__
+
+enum {
+	PG_LEVEL_NONE,
+	PG_LEVEL_4K,
+	PG_LEVEL_2M,
+	PG_LEVEL_1G,
+	PG_LEVEL_NUM
+};
+
+#ifdef CONFIG_PROC_FS
+extern void update_page_count(int level, unsigned long pages);
+#else
+static inline void update_page_count(int level, unsigned long pages) { }
+#endif
+
+/*
+ * Helper function that returns the kernel pagetable entry controlling
+ * the virtual address 'address'. NULL means no pagetable entry present.
+ * NOTE: the return type is pte_t but if the pmd is PSE then we return it
+ * as a pte too.
+ */
+extern pte_t *lookup_address(unsigned long address, unsigned int *level);
+
+/* local pte updates need not use xchg for locking */
+static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
+{
+	pte_t res = *ptep;
+
+	/* Pure native function needs no input for mm, addr */
+	native_pte_clear(NULL, 0, ptep);
+	return res;
+}
+
+static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
+				     pte_t *ptep , pte_t pte)
+{
+	native_set_pte(ptep, pte);
+}
+
+#ifndef CONFIG_PARAVIRT
+/*
+ * Rules for using pte_update - it must be called after any PTE update which
+ * has not been done using the set_pte / clear_pte interfaces.  It is used by
+ * shadow mode hypervisors to resynchronize the shadow page tables.  Kernel PTE
+ * updates should either be sets, clears, or set_pte_atomic for P->P
+ * transitions, which means this hook should only be called for user PTEs.
+ * This hook implies a P->P protection or access change has taken place, which
+ * requires a subsequent TLB flush.  The notification can optionally be delayed
+ * until the TLB flush event by using the pte_update_defer form of the
+ * interface, but care must be taken to assure that the flush happens while
+ * still holding the same page table lock so that the shadow and primary pages
+ * do not become out of sync on SMP.
+ */
+#define pte_update(mm, addr, ptep)		do { } while (0)
+#define pte_update_defer(mm, addr, ptep)	do { } while (0)
+#endif
+
+/*
+ * We only update the dirty/accessed state if we set
+ * the dirty bit by hand in the kernel, since the hardware
+ * will do the accessed bit for us, and we don't want to
+ * race with other CPU's that might be updating the dirty
+ * bit at the same time.
+ */
+struct vm_area_struct;
+
+#define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+extern int ptep_set_access_flags(struct vm_area_struct *vma,
+				 unsigned long address, pte_t *ptep,
+				 pte_t entry, int dirty);
+
+#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
+extern int ptep_test_and_clear_young(struct vm_area_struct *vma,
+				     unsigned long addr, pte_t *ptep);
+
+#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+extern int ptep_clear_flush_young(struct vm_area_struct *vma,
+				  unsigned long address, pte_t *ptep);
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
+static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				       pte_t *ptep)
+{
+	pte_t pte = native_ptep_get_and_clear(ptep);
+	pte_update(mm, addr, ptep);
+	return pte;
+}
+
+#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
+static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep,
+					    int full)
+{
+	pte_t pte;
+	if (full) {
+		/*
+		 * Full address destruction in progress; paravirt does not
+		 * care about updates and native needs no locking
+		 */
+		pte = native_local_ptep_get_and_clear(ptep);
+	} else {
+		pte = ptep_get_and_clear(mm, addr, ptep);
+	}
+	return pte;
+}
+
+#define __HAVE_ARCH_PTEP_SET_WRPROTECT
+static inline void ptep_set_wrprotect(struct mm_struct *mm,
+				      unsigned long addr, pte_t *ptep)
+{
+	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
+	pte_update(mm, addr, ptep);
+}
+
+/*
+ * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
+ *
+ *  dst - pointer to pgd range anwhere on a pgd page
+ *  src - ""
+ *  count - the number of pgds to copy.
+ *
+ * dst and src can be on the same page, but the range must not overlap,
+ * and must not cross a page boundary.
+ */
+static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
+{
+       memcpy(dst, src, count * sizeof(pgd_t));
+}
+
+
+#include <asm-generic/pgtable.h>
+#endif	/* __ASSEMBLY__ */
+
+#endif /* ASM_X86__PGTABLE_H */
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
new file mode 100644
index 000000000000..8de702dc7d62
--- /dev/null
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -0,0 +1,191 @@
+#ifndef ASM_X86__PGTABLE_32_H
+#define ASM_X86__PGTABLE_32_H
+
+
+/*
+ * The Linux memory management assumes a three-level page table setup. On
+ * the i386, we use that, but "fold" the mid level into the top-level page
+ * table, so that we physically have the same two-level page table as the
+ * i386 mmu expects.
+ *
+ * This file contains the functions and defines necessary to modify and use
+ * the i386 page table tree.
+ */
+#ifndef __ASSEMBLY__
+#include <asm/processor.h>
+#include <asm/fixmap.h>
+#include <linux/threads.h>
+#include <asm/paravirt.h>
+
+#include <linux/bitops.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/spinlock.h>
+
+struct mm_struct;
+struct vm_area_struct;
+
+extern pgd_t swapper_pg_dir[1024];
+
+static inline void pgtable_cache_init(void) { }
+static inline void check_pgt_cache(void) { }
+void paging_init(void);
+
+extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
+
+/*
+ * The Linux x86 paging architecture is 'compile-time dual-mode', it
+ * implements both the traditional 2-level x86 page tables and the
+ * newer 3-level PAE-mode page tables.
+ */
+#ifdef CONFIG_X86_PAE
+# include <asm/pgtable-3level-defs.h>
+# define PMD_SIZE	(1UL << PMD_SHIFT)
+# define PMD_MASK	(~(PMD_SIZE - 1))
+#else
+# include <asm/pgtable-2level-defs.h>
+#endif
+
+#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE - 1))
+
+/* Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 8MB value just means that there will be a 8MB "hole" after the
+ * physical memory until the kernel virtual memory starts.  That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ */
+#define VMALLOC_OFFSET	(8 * 1024 * 1024)
+#define VMALLOC_START	((unsigned long)high_memory + VMALLOC_OFFSET)
+#ifdef CONFIG_X86_PAE
+#define LAST_PKMAP 512
+#else
+#define LAST_PKMAP 1024
+#endif
+
+#define PKMAP_BASE ((FIXADDR_BOOT_START - PAGE_SIZE * (LAST_PKMAP + 1))	\
+		    & PMD_MASK)
+
+#ifdef CONFIG_HIGHMEM
+# define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
+#else
+# define VMALLOC_END	(FIXADDR_START - 2 * PAGE_SIZE)
+#endif
+
+#define MAXMEM	(VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE)
+
+/*
+ * Define this if things work differently on an i386 and an i486:
+ * it will (on an i486) warn about kernel memory accesses that are
+ * done without a 'access_ok(VERIFY_WRITE,..)'
+ */
+#undef TEST_ACCESS_OK
+
+/* The boot page tables (all created as a single array) */
+extern unsigned long pg0[];
+
+#define pte_present(x)	((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
+
+/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
+#define pmd_none(x)	(!(unsigned long)pmd_val((x)))
+#define pmd_present(x)	(pmd_val((x)) & _PAGE_PRESENT)
+#define pmd_bad(x) ((pmd_val(x) & (PTE_FLAGS_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
+
+#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
+
+#ifdef CONFIG_X86_PAE
+# include <asm/pgtable-3level.h>
+#else
+# include <asm/pgtable-2level.h>
+#endif
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ * On processors which do not support it, this is a no-op.
+ */
+#define pgprot_noncached(prot)					\
+	((boot_cpu_data.x86 > 3)				\
+	 ? (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT))	\
+	 : (prot))
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
+
+
+static inline int pud_large(pud_t pud) { return 0; }
+
+/*
+ * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
+ *
+ * this macro returns the index of the entry in the pmd page which would
+ * control the given virtual address
+ */
+#define pmd_index(address)				\
+	(((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+
+/*
+ * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
+ *
+ * this macro returns the index of the entry in the pte page which would
+ * control the given virtual address
+ */
+#define pte_index(address)					\
+	(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, address)				\
+	((pte_t *)pmd_page_vaddr(*(dir)) +  pte_index((address)))
+
+#define pmd_page(pmd) (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
+
+#define pmd_page_vaddr(pmd)					\
+	((unsigned long)__va(pmd_val((pmd)) & PTE_PFN_MASK))
+
+#if defined(CONFIG_HIGHPTE)
+#define pte_offset_map(dir, address)					\
+	((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE0) +		\
+	 pte_index((address)))
+#define pte_offset_map_nested(dir, address)				\
+	((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE1) +		\
+	 pte_index((address)))
+#define pte_unmap(pte) kunmap_atomic((pte), KM_PTE0)
+#define pte_unmap_nested(pte) kunmap_atomic((pte), KM_PTE1)
+#else
+#define pte_offset_map(dir, address)					\
+	((pte_t *)page_address(pmd_page(*(dir))) + pte_index((address)))
+#define pte_offset_map_nested(dir, address) pte_offset_map((dir), (address))
+#define pte_unmap(pte) do { } while (0)
+#define pte_unmap_nested(pte) do { } while (0)
+#endif
+
+/* Clear a kernel PTE and flush it from the TLB */
+#define kpte_clear_flush(ptep, vaddr)		\
+do {						\
+	pte_clear(&init_mm, (vaddr), (ptep));	\
+	__flush_tlb_one((vaddr));		\
+} while (0)
+
+/*
+ * The i386 doesn't have any external MMU info: the kernel page
+ * tables contain all the necessary information.
+ */
+#define update_mmu_cache(vma, address, pte) do { } while (0)
+
+#endif /* !__ASSEMBLY__ */
+
+/*
+ * kern_addr_valid() is (1) for FLATMEM and (0) for
+ * SPARSEMEM and DISCONTIGMEM
+ */
+#ifdef CONFIG_FLATMEM
+#define kern_addr_valid(addr)	(1)
+#else
+#define kern_addr_valid(kaddr)	(0)
+#endif
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)	\
+	remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+#endif /* ASM_X86__PGTABLE_32_H */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
new file mode 100644
index 000000000000..fde9770e53d1
--- /dev/null
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -0,0 +1,285 @@
+#ifndef ASM_X86__PGTABLE_64_H
+#define ASM_X86__PGTABLE_64_H
+
+#include <linux/const.h>
+#ifndef __ASSEMBLY__
+
+/*
+ * This file contains the functions and defines necessary to modify and use
+ * the x86-64 page table tree.
+ */
+#include <asm/processor.h>
+#include <linux/bitops.h>
+#include <linux/threads.h>
+#include <asm/pda.h>
+
+extern pud_t level3_kernel_pgt[512];
+extern pud_t level3_ident_pgt[512];
+extern pmd_t level2_kernel_pgt[512];
+extern pmd_t level2_fixmap_pgt[512];
+extern pmd_t level2_ident_pgt[512];
+extern pgd_t init_level4_pgt[];
+
+#define swapper_pg_dir init_level4_pgt
+
+extern void paging_init(void);
+
+#endif /* !__ASSEMBLY__ */
+
+#define SHARED_KERNEL_PMD	0
+
+/*
+ * PGDIR_SHIFT determines what a top-level page table entry can map
+ */
+#define PGDIR_SHIFT	39
+#define PTRS_PER_PGD	512
+
+/*
+ * 3rd level page
+ */
+#define PUD_SHIFT	30
+#define PTRS_PER_PUD	512
+
+/*
+ * PMD_SHIFT determines the size of the area a middle-level
+ * page table can map
+ */
+#define PMD_SHIFT	21
+#define PTRS_PER_PMD	512
+
+/*
+ * entries per page directory level
+ */
+#define PTRS_PER_PTE	512
+
+#ifndef __ASSEMBLY__
+
+#define pte_ERROR(e)					\
+	printk("%s:%d: bad pte %p(%016lx).\n",		\
+	       __FILE__, __LINE__, &(e), pte_val(e))
+#define pmd_ERROR(e)					\
+	printk("%s:%d: bad pmd %p(%016lx).\n",		\
+	       __FILE__, __LINE__, &(e), pmd_val(e))
+#define pud_ERROR(e)					\
+	printk("%s:%d: bad pud %p(%016lx).\n",		\
+	       __FILE__, __LINE__, &(e), pud_val(e))
+#define pgd_ERROR(e)					\
+	printk("%s:%d: bad pgd %p(%016lx).\n",		\
+	       __FILE__, __LINE__, &(e), pgd_val(e))
+
+#define pgd_none(x)	(!pgd_val(x))
+#define pud_none(x)	(!pud_val(x))
+
+struct mm_struct;
+
+void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
+
+
+static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
+				    pte_t *ptep)
+{
+	*ptep = native_make_pte(0);
+}
+
+static inline void native_set_pte(pte_t *ptep, pte_t pte)
+{
+	*ptep = pte;
+}
+
+static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
+{
+	native_set_pte(ptep, pte);
+}
+
+static inline pte_t native_ptep_get_and_clear(pte_t *xp)
+{
+#ifdef CONFIG_SMP
+	return native_make_pte(xchg(&xp->pte, 0));
+#else
+	/* native_local_ptep_get_and_clear,
+	   but duplicated because of cyclic dependency */
+	pte_t ret = *xp;
+	native_pte_clear(NULL, 0, xp);
+	return ret;
+#endif
+}
+
+static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
+{
+	*pmdp = pmd;
+}
+
+static inline void native_pmd_clear(pmd_t *pmd)
+{
+	native_set_pmd(pmd, native_make_pmd(0));
+}
+
+static inline void native_set_pud(pud_t *pudp, pud_t pud)
+{
+	*pudp = pud;
+}
+
+static inline void native_pud_clear(pud_t *pud)
+{
+	native_set_pud(pud, native_make_pud(0));
+}
+
+static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
+{
+	*pgdp = pgd;
+}
+
+static inline void native_pgd_clear(pgd_t *pgd)
+{
+	native_set_pgd(pgd, native_make_pgd(0));
+}
+
+#define pte_same(a, b)		((a).pte == (b).pte)
+
+#endif /* !__ASSEMBLY__ */
+
+#define PMD_SIZE	(_AC(1, UL) << PMD_SHIFT)
+#define PMD_MASK	(~(PMD_SIZE - 1))
+#define PUD_SIZE	(_AC(1, UL) << PUD_SHIFT)
+#define PUD_MASK	(~(PUD_SIZE - 1))
+#define PGDIR_SIZE	(_AC(1, UL) << PGDIR_SHIFT)
+#define PGDIR_MASK	(~(PGDIR_SIZE - 1))
+
+
+#define MAXMEM		 _AC(0x00003fffffffffff, UL)
+#define VMALLOC_START    _AC(0xffffc20000000000, UL)
+#define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
+#define VMEMMAP_START	 _AC(0xffffe20000000000, UL)
+#define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
+#define MODULES_END      _AC(0xffffffffff000000, UL)
+#define MODULES_LEN   (MODULES_END - MODULES_VADDR)
+
+#ifndef __ASSEMBLY__
+
+static inline int pgd_bad(pgd_t pgd)
+{
+	return (pgd_val(pgd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
+}
+
+static inline int pud_bad(pud_t pud)
+{
+	return (pud_val(pud) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
+}
+
+static inline int pmd_bad(pmd_t pmd)
+{
+	return (pmd_val(pmd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
+}
+
+#define pte_none(x)	(!pte_val((x)))
+#define pte_present(x)	(pte_val((x)) & (_PAGE_PRESENT | _PAGE_PROTNONE))
+
+#define pages_to_mb(x)	((x) >> (20 - PAGE_SHIFT))   /* FIXME: is this right? */
+
+/*
+ * Macro to mark a page protection value as "uncacheable".
+ */
+#define pgprot_noncached(prot)					\
+	(__pgprot(pgprot_val((prot)) | _PAGE_PCD | _PAGE_PWT))
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+
+/*
+ * Level 4 access.
+ */
+#define pgd_page_vaddr(pgd)						\
+	((unsigned long)__va((unsigned long)pgd_val((pgd)) & PTE_PFN_MASK))
+#define pgd_page(pgd)		(pfn_to_page(pgd_val((pgd)) >> PAGE_SHIFT))
+#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
+static inline int pgd_large(pgd_t pgd) { return 0; }
+#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
+
+/* PUD - Level3 access */
+/* to find an entry in a page-table-directory. */
+#define pud_page_vaddr(pud)						\
+	((unsigned long)__va(pud_val((pud)) & PHYSICAL_PAGE_MASK))
+#define pud_page(pud)	(pfn_to_page(pud_val((pud)) >> PAGE_SHIFT))
+#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
+#define pud_offset(pgd, address)					\
+	((pud_t *)pgd_page_vaddr(*(pgd)) + pud_index((address)))
+#define pud_present(pud) (pud_val((pud)) & _PAGE_PRESENT)
+
+static inline int pud_large(pud_t pte)
+{
+	return (pud_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
+		(_PAGE_PSE | _PAGE_PRESENT);
+}
+
+/* PMD  - Level 2 access */
+#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val((pmd)) & PTE_PFN_MASK))
+#define pmd_page(pmd)		(pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
+
+#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
+#define pmd_offset(dir, address) ((pmd_t *)pud_page_vaddr(*(dir)) + \
+				  pmd_index(address))
+#define pmd_none(x)	(!pmd_val((x)))
+#define pmd_present(x)	(pmd_val((x)) & _PAGE_PRESENT)
+#define pfn_pmd(nr, prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val((prot))))
+#define pmd_pfn(x)  ((pmd_val((x)) & __PHYSICAL_MASK) >> PAGE_SHIFT)
+
+#define pte_to_pgoff(pte) ((pte_val((pte)) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
+#define pgoff_to_pte(off) ((pte_t) { .pte = ((off) << PAGE_SHIFT) |	\
+					    _PAGE_FILE })
+#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT
+
+/* PTE - Level 1 access. */
+
+/* page, protection -> pte */
+#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn((page)), (pgprot))
+
+#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_vaddr(*(dir)) + \
+					 pte_index((address)))
+
+/* x86-64 always has all page tables mapped. */
+#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
+#define pte_offset_map_nested(dir, address) pte_offset_kernel((dir), (address))
+#define pte_unmap(pte) /* NOP */
+#define pte_unmap_nested(pte) /* NOP */
+
+#define update_mmu_cache(vma, address, pte) do { } while (0)
+
+extern int direct_gbpages;
+
+/* Encode and de-code a swap entry */
+#define __swp_type(x)			(((x).val >> 1) & 0x3f)
+#define __swp_offset(x)			((x).val >> 8)
+#define __swp_entry(type, offset)	((swp_entry_t) { ((type) << 1) | \
+							 ((offset) << 8) })
+#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
+#define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
+
+extern int kern_addr_valid(unsigned long addr);
+extern void cleanup_highmap(void);
+
+#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)	\
+	remap_pfn_range(vma, vaddr, pfn, size, prot)
+
+#define HAVE_ARCH_UNMAPPED_AREA
+#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
+
+#define pgtable_cache_init()   do { } while (0)
+#define check_pgt_cache()      do { } while (0)
+
+#define PAGE_AGP    PAGE_KERNEL_NOCACHE
+#define HAVE_PAGE_AGP 1
+
+/* fs/proc/kcore.c */
+#define	kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK)
+#define	kc_offset_to_vaddr(o)				\
+	(((o) & (1UL << (__VIRTUAL_MASK_SHIFT - 1)))	\
+	 ? ((o) | ~__VIRTUAL_MASK)			\
+	 : (o))
+
+#define __HAVE_ARCH_PTE_SAME
+#endif /* !__ASSEMBLY__ */
+
+#endif /* ASM_X86__PGTABLE_64_H */
diff --git a/arch/x86/include/asm/poll.h b/arch/x86/include/asm/poll.h
new file mode 100644
index 000000000000..c98509d3149e
--- /dev/null
+++ b/arch/x86/include/asm/poll.h
@@ -0,0 +1 @@
+#include <asm-generic/poll.h>
diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h
new file mode 100644
index 000000000000..bb7133dc155d
--- /dev/null
+++ b/arch/x86/include/asm/posix_types.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "posix_types_32.h"
+# else
+#  include "posix_types_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "posix_types_32.h"
+# else
+#  include "posix_types_64.h"
+# endif
+#endif
diff --git a/arch/x86/include/asm/posix_types_32.h b/arch/x86/include/asm/posix_types_32.h
new file mode 100644
index 000000000000..70cf2bb05939
--- /dev/null
+++ b/arch/x86/include/asm/posix_types_32.h
@@ -0,0 +1,85 @@
+#ifndef ASM_X86__POSIX_TYPES_32_H
+#define ASM_X86__POSIX_TYPES_32_H
+
+/*
+ * This file is generally used by user-level software, so you need to
+ * be a little careful about namespace pollution etc.  Also, we cannot
+ * assume GCC is being used.
+ */
+
+typedef unsigned long	__kernel_ino_t;
+typedef unsigned short	__kernel_mode_t;
+typedef unsigned short	__kernel_nlink_t;
+typedef long		__kernel_off_t;
+typedef int		__kernel_pid_t;
+typedef unsigned short	__kernel_ipc_pid_t;
+typedef unsigned short	__kernel_uid_t;
+typedef unsigned short	__kernel_gid_t;
+typedef unsigned int	__kernel_size_t;
+typedef int		__kernel_ssize_t;
+typedef int		__kernel_ptrdiff_t;
+typedef long		__kernel_time_t;
+typedef long		__kernel_suseconds_t;
+typedef long		__kernel_clock_t;
+typedef int		__kernel_timer_t;
+typedef int		__kernel_clockid_t;
+typedef int		__kernel_daddr_t;
+typedef char *		__kernel_caddr_t;
+typedef unsigned short	__kernel_uid16_t;
+typedef unsigned short	__kernel_gid16_t;
+typedef unsigned int	__kernel_uid32_t;
+typedef unsigned int	__kernel_gid32_t;
+
+typedef unsigned short	__kernel_old_uid_t;
+typedef unsigned short	__kernel_old_gid_t;
+typedef unsigned short	__kernel_old_dev_t;
+
+#ifdef __GNUC__
+typedef long long	__kernel_loff_t;
+#endif
+
+typedef struct {
+	int	val[2];
+} __kernel_fsid_t;
+
+#if defined(__KERNEL__)
+
+#undef	__FD_SET
+#define __FD_SET(fd,fdsetp)					\
+	asm volatile("btsl %1,%0":				\
+		     "+m" (*(__kernel_fd_set *)(fdsetp))	\
+		     : "r" ((int)(fd)))
+
+#undef	__FD_CLR
+#define __FD_CLR(fd,fdsetp)					\
+	asm volatile("btrl %1,%0":				\
+		     "+m" (*(__kernel_fd_set *)(fdsetp))	\
+		     : "r" ((int) (fd)))
+
+#undef	__FD_ISSET
+#define __FD_ISSET(fd,fdsetp)					\
+	(__extension__						\
+	 ({							\
+	 unsigned char __result;				\
+	 asm volatile("btl %1,%2 ; setb %0"			\
+		      : "=q" (__result)				\
+		      : "r" ((int)(fd)),			\
+			"m" (*(__kernel_fd_set *)(fdsetp)));	\
+	 __result;						\
+}))
+
+#undef	__FD_ZERO
+#define __FD_ZERO(fdsetp)					\
+do {								\
+	int __d0, __d1;						\
+	asm volatile("cld ; rep ; stosl"			\
+		     : "=m" (*(__kernel_fd_set *)(fdsetp)),	\
+		       "=&c" (__d0), "=&D" (__d1)		\
+		     : "a" (0), "1" (__FDSET_LONGS),		\
+		       "2" ((__kernel_fd_set *)(fdsetp))	\
+		     : "memory");				\
+} while (0)
+
+#endif /* defined(__KERNEL__) */
+
+#endif /* ASM_X86__POSIX_TYPES_32_H */
diff --git a/arch/x86/include/asm/posix_types_64.h b/arch/x86/include/asm/posix_types_64.h
new file mode 100644
index 000000000000..388b4e7f4a44
--- /dev/null
+++ b/arch/x86/include/asm/posix_types_64.h
@@ -0,0 +1,119 @@
+#ifndef ASM_X86__POSIX_TYPES_64_H
+#define ASM_X86__POSIX_TYPES_64_H
+
+/*
+ * This file is generally used by user-level software, so you need to
+ * be a little careful about namespace pollution etc.  Also, we cannot
+ * assume GCC is being used.
+ */
+
+typedef unsigned long	__kernel_ino_t;
+typedef unsigned int	__kernel_mode_t;
+typedef unsigned long	__kernel_nlink_t;
+typedef long		__kernel_off_t;
+typedef int		__kernel_pid_t;
+typedef int		__kernel_ipc_pid_t;
+typedef unsigned int	__kernel_uid_t;
+typedef unsigned int	__kernel_gid_t;
+typedef unsigned long	__kernel_size_t;
+typedef long		__kernel_ssize_t;
+typedef long		__kernel_ptrdiff_t;
+typedef long		__kernel_time_t;
+typedef long		__kernel_suseconds_t;
+typedef long		__kernel_clock_t;
+typedef int		__kernel_timer_t;
+typedef int		__kernel_clockid_t;
+typedef int		__kernel_daddr_t;
+typedef char *		__kernel_caddr_t;
+typedef unsigned short	__kernel_uid16_t;
+typedef unsigned short	__kernel_gid16_t;
+
+#ifdef __GNUC__
+typedef long long	__kernel_loff_t;
+#endif
+
+typedef struct {
+	int	val[2];
+} __kernel_fsid_t;
+
+typedef unsigned short __kernel_old_uid_t;
+typedef unsigned short __kernel_old_gid_t;
+typedef __kernel_uid_t __kernel_uid32_t;
+typedef __kernel_gid_t __kernel_gid32_t;
+
+typedef unsigned long	__kernel_old_dev_t;
+
+#ifdef __KERNEL__
+
+#undef __FD_SET
+static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
+{
+	unsigned long _tmp = fd / __NFDBITS;
+	unsigned long _rem = fd % __NFDBITS;
+	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
+}
+
+#undef __FD_CLR
+static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
+{
+	unsigned long _tmp = fd / __NFDBITS;
+	unsigned long _rem = fd % __NFDBITS;
+	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
+}
+
+#undef __FD_ISSET
+static inline int __FD_ISSET(unsigned long fd, __const__ __kernel_fd_set *p)
+{
+	unsigned long _tmp = fd / __NFDBITS;
+	unsigned long _rem = fd % __NFDBITS;
+	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
+}
+
+/*
+ * This will unroll the loop for the normal constant cases (8 or 32 longs,
+ * for 256 and 1024-bit fd_sets respectively)
+ */
+#undef __FD_ZERO
+static inline void __FD_ZERO(__kernel_fd_set *p)
+{
+	unsigned long *tmp = p->fds_bits;
+	int i;
+
+	if (__builtin_constant_p(__FDSET_LONGS)) {
+		switch (__FDSET_LONGS) {
+		case 32:
+			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
+			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
+			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
+			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
+			tmp[16] = 0; tmp[17] = 0; tmp[18] = 0; tmp[19] = 0;
+			tmp[20] = 0; tmp[21] = 0; tmp[22] = 0; tmp[23] = 0;
+			tmp[24] = 0; tmp[25] = 0; tmp[26] = 0; tmp[27] = 0;
+			tmp[28] = 0; tmp[29] = 0; tmp[30] = 0; tmp[31] = 0;
+			return;
+		case 16:
+			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
+			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
+			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
+			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
+			return;
+		case 8:
+			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
+			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
+			return;
+		case 4:
+			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
+			return;
+		}
+	}
+	i = __FDSET_LONGS;
+	while (i) {
+		i--;
+		*tmp = 0;
+		tmp++;
+	}
+}
+
+#endif /* defined(__KERNEL__) */
+
+#endif /* ASM_X86__POSIX_TYPES_64_H */
diff --git a/arch/x86/include/asm/prctl.h b/arch/x86/include/asm/prctl.h
new file mode 100644
index 000000000000..e7ae34eb4103
--- /dev/null
+++ b/arch/x86/include/asm/prctl.h
@@ -0,0 +1,10 @@
+#ifndef ASM_X86__PRCTL_H
+#define ASM_X86__PRCTL_H
+
+#define ARCH_SET_GS 0x1001
+#define ARCH_SET_FS 0x1002
+#define ARCH_GET_FS 0x1003
+#define ARCH_GET_GS 0x1004
+
+
+#endif /* ASM_X86__PRCTL_H */
diff --git a/arch/x86/include/asm/processor-cyrix.h b/arch/x86/include/asm/processor-cyrix.h
new file mode 100644
index 000000000000..1198f2a0e42c
--- /dev/null
+++ b/arch/x86/include/asm/processor-cyrix.h
@@ -0,0 +1,38 @@
+/*
+ * NSC/Cyrix CPU indexed register access. Must be inlined instead of
+ * macros to ensure correct access ordering
+ * Access order is always 0x22 (=offset), 0x23 (=value)
+ *
+ * When using the old macros a line like
+ *   setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
+ * gets expanded to:
+ *  do {
+ *    outb((CX86_CCR2), 0x22);
+ *    outb((({
+ *        outb((CX86_CCR2), 0x22);
+ *        inb(0x23);
+ *    }) | 0x88), 0x23);
+ *  } while (0);
+ *
+ * which in fact violates the access order (= 0x22, 0x22, 0x23, 0x23).
+ */
+
+static inline u8 getCx86(u8 reg)
+{
+	outb(reg, 0x22);
+	return inb(0x23);
+}
+
+static inline void setCx86(u8 reg, u8 data)
+{
+	outb(reg, 0x22);
+	outb(data, 0x23);
+}
+
+#define getCx86_old(reg) ({ outb((reg), 0x22); inb(0x23); })
+
+#define setCx86_old(reg, data) do { \
+	outb((reg), 0x22); \
+	outb((data), 0x23); \
+} while (0)
+
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
new file mode 100644
index 000000000000..dc5f0712f9fa
--- /dev/null
+++ b/arch/x86/include/asm/processor-flags.h
@@ -0,0 +1,100 @@
+#ifndef ASM_X86__PROCESSOR_FLAGS_H
+#define ASM_X86__PROCESSOR_FLAGS_H
+/* Various flags defined: can be included from assembler. */
+
+/*
+ * EFLAGS bits
+ */
+#define X86_EFLAGS_CF	0x00000001 /* Carry Flag */
+#define X86_EFLAGS_PF	0x00000004 /* Parity Flag */
+#define X86_EFLAGS_AF	0x00000010 /* Auxillary carry Flag */
+#define X86_EFLAGS_ZF	0x00000040 /* Zero Flag */
+#define X86_EFLAGS_SF	0x00000080 /* Sign Flag */
+#define X86_EFLAGS_TF	0x00000100 /* Trap Flag */
+#define X86_EFLAGS_IF	0x00000200 /* Interrupt Flag */
+#define X86_EFLAGS_DF	0x00000400 /* Direction Flag */
+#define X86_EFLAGS_OF	0x00000800 /* Overflow Flag */
+#define X86_EFLAGS_IOPL	0x00003000 /* IOPL mask */
+#define X86_EFLAGS_NT	0x00004000 /* Nested Task */
+#define X86_EFLAGS_RF	0x00010000 /* Resume Flag */
+#define X86_EFLAGS_VM	0x00020000 /* Virtual Mode */
+#define X86_EFLAGS_AC	0x00040000 /* Alignment Check */
+#define X86_EFLAGS_VIF	0x00080000 /* Virtual Interrupt Flag */
+#define X86_EFLAGS_VIP	0x00100000 /* Virtual Interrupt Pending */
+#define X86_EFLAGS_ID	0x00200000 /* CPUID detection flag */
+
+/*
+ * Basic CPU control in CR0
+ */
+#define X86_CR0_PE	0x00000001 /* Protection Enable */
+#define X86_CR0_MP	0x00000002 /* Monitor Coprocessor */
+#define X86_CR0_EM	0x00000004 /* Emulation */
+#define X86_CR0_TS	0x00000008 /* Task Switched */
+#define X86_CR0_ET	0x00000010 /* Extension Type */
+#define X86_CR0_NE	0x00000020 /* Numeric Error */
+#define X86_CR0_WP	0x00010000 /* Write Protect */
+#define X86_CR0_AM	0x00040000 /* Alignment Mask */
+#define X86_CR0_NW	0x20000000 /* Not Write-through */
+#define X86_CR0_CD	0x40000000 /* Cache Disable */
+#define X86_CR0_PG	0x80000000 /* Paging */
+
+/*
+ * Paging options in CR3
+ */
+#define X86_CR3_PWT	0x00000008 /* Page Write Through */
+#define X86_CR3_PCD	0x00000010 /* Page Cache Disable */
+
+/*
+ * Intel CPU features in CR4
+ */
+#define X86_CR4_VME	0x00000001 /* enable vm86 extensions */
+#define X86_CR4_PVI	0x00000002 /* virtual interrupts flag enable */
+#define X86_CR4_TSD	0x00000004 /* disable time stamp at ipl 3 */
+#define X86_CR4_DE	0x00000008 /* enable debugging extensions */
+#define X86_CR4_PSE	0x00000010 /* enable page size extensions */
+#define X86_CR4_PAE	0x00000020 /* enable physical address extensions */
+#define X86_CR4_MCE	0x00000040 /* Machine check enable */
+#define X86_CR4_PGE	0x00000080 /* enable global pages */
+#define X86_CR4_PCE	0x00000100 /* enable performance counters at ipl 3 */
+#define X86_CR4_OSFXSR	0x00000200 /* enable fast FPU save and restore */
+#define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */
+#define X86_CR4_VMXE	0x00002000 /* enable VMX virtualization */
+#define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
+
+/*
+ * x86-64 Task Priority Register, CR8
+ */
+#define X86_CR8_TPR	0x0000000F /* task priority register */
+
+/*
+ * AMD and Transmeta use MSRs for configuration; see <asm/msr-index.h>
+ */
+
+/*
+ *      NSC/Cyrix CPU configuration register indexes
+ */
+#define CX86_PCR0	0x20
+#define CX86_GCR	0xb8
+#define CX86_CCR0	0xc0
+#define CX86_CCR1	0xc1
+#define CX86_CCR2	0xc2
+#define CX86_CCR3	0xc3
+#define CX86_CCR4	0xe8
+#define CX86_CCR5	0xe9
+#define CX86_CCR6	0xea
+#define CX86_CCR7	0xeb
+#define CX86_PCR1	0xf0
+#define CX86_DIR0	0xfe
+#define CX86_DIR1	0xff
+#define CX86_ARR_BASE	0xc4
+#define CX86_RCR_BASE	0xdc
+
+#ifdef __KERNEL__
+#ifdef CONFIG_VM86
+#define X86_VM_MASK	X86_EFLAGS_VM
+#else
+#define X86_VM_MASK	0 /* No VM86 support */
+#endif
+#endif
+
+#endif /* ASM_X86__PROCESSOR_FLAGS_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
new file mode 100644
index 000000000000..ee7cbb30773a
--- /dev/null
+++ b/arch/x86/include/asm/processor.h
@@ -0,0 +1,936 @@
+#ifndef ASM_X86__PROCESSOR_H
+#define ASM_X86__PROCESSOR_H
+
+#include <asm/processor-flags.h>
+
+/* Forward declaration, a strange C thing */
+struct task_struct;
+struct mm_struct;
+
+#include <asm/vm86.h>
+#include <asm/math_emu.h>
+#include <asm/segment.h>
+#include <asm/types.h>
+#include <asm/sigcontext.h>
+#include <asm/current.h>
+#include <asm/cpufeature.h>
+#include <asm/system.h>
+#include <asm/page.h>
+#include <asm/percpu.h>
+#include <asm/msr.h>
+#include <asm/desc_defs.h>
+#include <asm/nops.h>
+#include <asm/ds.h>
+
+#include <linux/personality.h>
+#include <linux/cpumask.h>
+#include <linux/cache.h>
+#include <linux/threads.h>
+#include <linux/init.h>
+
+/*
+ * Default implementation of macro that returns current
+ * instruction pointer ("program counter").
+ */
+static inline void *current_text_addr(void)
+{
+	void *pc;
+
+	asm volatile("mov $1f, %0; 1:":"=r" (pc));
+
+	return pc;
+}
+
+#ifdef CONFIG_X86_VSMP
+# define ARCH_MIN_TASKALIGN		(1 << INTERNODE_CACHE_SHIFT)
+# define ARCH_MIN_MMSTRUCT_ALIGN	(1 << INTERNODE_CACHE_SHIFT)
+#else
+# define ARCH_MIN_TASKALIGN		16
+# define ARCH_MIN_MMSTRUCT_ALIGN	0
+#endif
+
+/*
+ *  CPU type and hardware bug flags. Kept separately for each CPU.
+ *  Members of this structure are referenced in head.S, so think twice
+ *  before touching them. [mj]
+ */
+
+struct cpuinfo_x86 {
+	__u8			x86;		/* CPU family */
+	__u8			x86_vendor;	/* CPU vendor */
+	__u8			x86_model;
+	__u8			x86_mask;
+#ifdef CONFIG_X86_32
+	char			wp_works_ok;	/* It doesn't on 386's */
+
+	/* Problems on some 486Dx4's and old 386's: */
+	char			hlt_works_ok;
+	char			hard_math;
+	char			rfu;
+	char			fdiv_bug;
+	char			f00f_bug;
+	char			coma_bug;
+	char			pad0;
+#else
+	/* Number of 4K pages in DTLB/ITLB combined(in pages): */
+	int			 x86_tlbsize;
+	__u8			x86_virt_bits;
+	__u8			x86_phys_bits;
+#endif
+	/* CPUID returned core id bits: */
+	__u8			x86_coreid_bits;
+	/* Max extended CPUID function supported: */
+	__u32			extended_cpuid_level;
+	/* Maximum supported CPUID level, -1=no CPUID: */
+	int			cpuid_level;
+	__u32			x86_capability[NCAPINTS];
+	char			x86_vendor_id[16];
+	char			x86_model_id[64];
+	/* in KB - valid for CPUS which support this call: */
+	int			x86_cache_size;
+	int			x86_cache_alignment;	/* In bytes */
+	int			x86_power;
+	unsigned long		loops_per_jiffy;
+#ifdef CONFIG_SMP
+	/* cpus sharing the last level cache: */
+	cpumask_t		llc_shared_map;
+#endif
+	/* cpuid returned max cores value: */
+	u16			 x86_max_cores;
+	u16			apicid;
+	u16			initial_apicid;
+	u16			x86_clflush_size;
+#ifdef CONFIG_SMP
+	/* number of cores as seen by the OS: */
+	u16			booted_cores;
+	/* Physical processor id: */
+	u16			phys_proc_id;
+	/* Core id: */
+	u16			cpu_core_id;
+	/* Index into per_cpu list: */
+	u16			cpu_index;
+#endif
+} __attribute__((__aligned__(SMP_CACHE_BYTES)));
+
+#define X86_VENDOR_INTEL	0
+#define X86_VENDOR_CYRIX	1
+#define X86_VENDOR_AMD		2
+#define X86_VENDOR_UMC		3
+#define X86_VENDOR_CENTAUR	5
+#define X86_VENDOR_TRANSMETA	7
+#define X86_VENDOR_NSC		8
+#define X86_VENDOR_NUM		9
+
+#define X86_VENDOR_UNKNOWN	0xff
+
+/*
+ * capabilities of CPUs
+ */
+extern struct cpuinfo_x86	boot_cpu_data;
+extern struct cpuinfo_x86	new_cpu_data;
+
+extern struct tss_struct	doublefault_tss;
+extern __u32			cleared_cpu_caps[NCAPINTS];
+
+#ifdef CONFIG_SMP
+DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info);
+#define cpu_data(cpu)		per_cpu(cpu_info, cpu)
+#define current_cpu_data	__get_cpu_var(cpu_info)
+#else
+#define cpu_data(cpu)		boot_cpu_data
+#define current_cpu_data	boot_cpu_data
+#endif
+
+extern const struct seq_operations cpuinfo_op;
+
+static inline int hlt_works(int cpu)
+{
+#ifdef CONFIG_X86_32
+	return cpu_data(cpu).hlt_works_ok;
+#else
+	return 1;
+#endif
+}
+
+#define cache_line_size()	(boot_cpu_data.x86_cache_alignment)
+
+extern void cpu_detect(struct cpuinfo_x86 *c);
+
+extern struct pt_regs *idle_regs(struct pt_regs *);
+
+extern void early_cpu_init(void);
+extern void identify_boot_cpu(void);
+extern void identify_secondary_cpu(struct cpuinfo_x86 *);
+extern void print_cpu_info(struct cpuinfo_x86 *);
+extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
+extern unsigned short num_cache_leaves;
+
+extern void detect_extended_topology(struct cpuinfo_x86 *c);
+extern void detect_ht(struct cpuinfo_x86 *c);
+
+static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
+				unsigned int *ecx, unsigned int *edx)
+{
+	/* ecx is often an input as well as an output. */
+	asm("cpuid"
+	    : "=a" (*eax),
+	      "=b" (*ebx),
+	      "=c" (*ecx),
+	      "=d" (*edx)
+	    : "0" (*eax), "2" (*ecx));
+}
+
+static inline void load_cr3(pgd_t *pgdir)
+{
+	write_cr3(__pa(pgdir));
+}
+
+#ifdef CONFIG_X86_32
+/* This is the TSS defined by the hardware. */
+struct x86_hw_tss {
+	unsigned short		back_link, __blh;
+	unsigned long		sp0;
+	unsigned short		ss0, __ss0h;
+	unsigned long		sp1;
+	/* ss1 caches MSR_IA32_SYSENTER_CS: */
+	unsigned short		ss1, __ss1h;
+	unsigned long		sp2;
+	unsigned short		ss2, __ss2h;
+	unsigned long		__cr3;
+	unsigned long		ip;
+	unsigned long		flags;
+	unsigned long		ax;
+	unsigned long		cx;
+	unsigned long		dx;
+	unsigned long		bx;
+	unsigned long		sp;
+	unsigned long		bp;
+	unsigned long		si;
+	unsigned long		di;
+	unsigned short		es, __esh;
+	unsigned short		cs, __csh;
+	unsigned short		ss, __ssh;
+	unsigned short		ds, __dsh;
+	unsigned short		fs, __fsh;
+	unsigned short		gs, __gsh;
+	unsigned short		ldt, __ldth;
+	unsigned short		trace;
+	unsigned short		io_bitmap_base;
+
+} __attribute__((packed));
+#else
+struct x86_hw_tss {
+	u32			reserved1;
+	u64			sp0;
+	u64			sp1;
+	u64			sp2;
+	u64			reserved2;
+	u64			ist[7];
+	u32			reserved3;
+	u32			reserved4;
+	u16			reserved5;
+	u16			io_bitmap_base;
+
+} __attribute__((packed)) ____cacheline_aligned;
+#endif
+
+/*
+ * IO-bitmap sizes:
+ */
+#define IO_BITMAP_BITS			65536
+#define IO_BITMAP_BYTES			(IO_BITMAP_BITS/8)
+#define IO_BITMAP_LONGS			(IO_BITMAP_BYTES/sizeof(long))
+#define IO_BITMAP_OFFSET		offsetof(struct tss_struct, io_bitmap)
+#define INVALID_IO_BITMAP_OFFSET	0x8000
+#define INVALID_IO_BITMAP_OFFSET_LAZY	0x9000
+
+struct tss_struct {
+	/*
+	 * The hardware state:
+	 */
+	struct x86_hw_tss	x86_tss;
+
+	/*
+	 * The extra 1 is there because the CPU will access an
+	 * additional byte beyond the end of the IO permission
+	 * bitmap. The extra byte must be all 1 bits, and must
+	 * be within the limit.
+	 */
+	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
+	/*
+	 * Cache the current maximum and the last task that used the bitmap:
+	 */
+	unsigned long		io_bitmap_max;
+	struct thread_struct	*io_bitmap_owner;
+
+	/*
+	 * .. and then another 0x100 bytes for the emergency kernel stack:
+	 */
+	unsigned long		stack[64];
+
+} ____cacheline_aligned;
+
+DECLARE_PER_CPU(struct tss_struct, init_tss);
+
+/*
+ * Save the original ist values for checking stack pointers during debugging
+ */
+struct orig_ist {
+	unsigned long		ist[7];
+};
+
+#define	MXCSR_DEFAULT		0x1f80
+
+struct i387_fsave_struct {
+	u32			cwd;	/* FPU Control Word		*/
+	u32			swd;	/* FPU Status Word		*/
+	u32			twd;	/* FPU Tag Word			*/
+	u32			fip;	/* FPU IP Offset		*/
+	u32			fcs;	/* FPU IP Selector		*/
+	u32			foo;	/* FPU Operand Pointer Offset	*/
+	u32			fos;	/* FPU Operand Pointer Selector	*/
+
+	/* 8*10 bytes for each FP-reg = 80 bytes:			*/
+	u32			st_space[20];
+
+	/* Software status information [not touched by FSAVE ]:		*/
+	u32			status;
+};
+
+struct i387_fxsave_struct {
+	u16			cwd; /* Control Word			*/
+	u16			swd; /* Status Word			*/
+	u16			twd; /* Tag Word			*/
+	u16			fop; /* Last Instruction Opcode		*/
+	union {
+		struct {
+			u64	rip; /* Instruction Pointer		*/
+			u64	rdp; /* Data Pointer			*/
+		};
+		struct {
+			u32	fip; /* FPU IP Offset			*/
+			u32	fcs; /* FPU IP Selector			*/
+			u32	foo; /* FPU Operand Offset		*/
+			u32	fos; /* FPU Operand Selector		*/
+		};
+	};
+	u32			mxcsr;		/* MXCSR Register State */
+	u32			mxcsr_mask;	/* MXCSR Mask		*/
+
+	/* 8*16 bytes for each FP-reg = 128 bytes:			*/
+	u32			st_space[32];
+
+	/* 16*16 bytes for each XMM-reg = 256 bytes:			*/
+	u32			xmm_space[64];
+
+	u32			padding[12];
+
+	union {
+		u32		padding1[12];
+		u32		sw_reserved[12];
+	};
+
+} __attribute__((aligned(16)));
+
+struct i387_soft_struct {
+	u32			cwd;
+	u32			swd;
+	u32			twd;
+	u32			fip;
+	u32			fcs;
+	u32			foo;
+	u32			fos;
+	/* 8*10 bytes for each FP-reg = 80 bytes: */
+	u32			st_space[20];
+	u8			ftop;
+	u8			changed;
+	u8			lookahead;
+	u8			no_update;
+	u8			rm;
+	u8			alimit;
+	struct info		*info;
+	u32			entry_eip;
+};
+
+struct xsave_hdr_struct {
+	u64 xstate_bv;
+	u64 reserved1[2];
+	u64 reserved2[5];
+} __attribute__((packed));
+
+struct xsave_struct {
+	struct i387_fxsave_struct i387;
+	struct xsave_hdr_struct xsave_hdr;
+	/* new processor state extensions will go here */
+} __attribute__ ((packed, aligned (64)));
+
+union thread_xstate {
+	struct i387_fsave_struct	fsave;
+	struct i387_fxsave_struct	fxsave;
+	struct i387_soft_struct		soft;
+	struct xsave_struct		xsave;
+};
+
+#ifdef CONFIG_X86_64
+DECLARE_PER_CPU(struct orig_ist, orig_ist);
+#endif
+
+extern void print_cpu_info(struct cpuinfo_x86 *);
+extern unsigned int xstate_size;
+extern void free_thread_xstate(struct task_struct *);
+extern struct kmem_cache *task_xstate_cachep;
+extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
+extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
+extern unsigned short num_cache_leaves;
+
+struct thread_struct {
+	/* Cached TLS descriptors: */
+	struct desc_struct	tls_array[GDT_ENTRY_TLS_ENTRIES];
+	unsigned long		sp0;
+	unsigned long		sp;
+#ifdef CONFIG_X86_32
+	unsigned long		sysenter_cs;
+#else
+	unsigned long		usersp;	/* Copy from PDA */
+	unsigned short		es;
+	unsigned short		ds;
+	unsigned short		fsindex;
+	unsigned short		gsindex;
+#endif
+	unsigned long		ip;
+	unsigned long		fs;
+	unsigned long		gs;
+	/* Hardware debugging registers: */
+	unsigned long		debugreg0;
+	unsigned long		debugreg1;
+	unsigned long		debugreg2;
+	unsigned long		debugreg3;
+	unsigned long		debugreg6;
+	unsigned long		debugreg7;
+	/* Fault info: */
+	unsigned long		cr2;
+	unsigned long		trap_no;
+	unsigned long		error_code;
+	/* floating point and extended processor state */
+	union thread_xstate	*xstate;
+#ifdef CONFIG_X86_32
+	/* Virtual 86 mode info */
+	struct vm86_struct __user *vm86_info;
+	unsigned long		screen_bitmap;
+	unsigned long		v86flags;
+	unsigned long		v86mask;
+	unsigned long		saved_sp0;
+	unsigned int		saved_fs;
+	unsigned int		saved_gs;
+#endif
+	/* IO permissions: */
+	unsigned long		*io_bitmap_ptr;
+	unsigned long		iopl;
+	/* Max allowed port in the bitmap, in bytes: */
+	unsigned		io_bitmap_max;
+/* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
+	unsigned long	debugctlmsr;
+#ifdef CONFIG_X86_DS
+/* Debug Store context; see include/asm-x86/ds.h; goes into MSR_IA32_DS_AREA */
+	struct ds_context	*ds_ctx;
+#endif /* CONFIG_X86_DS */
+#ifdef CONFIG_X86_PTRACE_BTS
+/* the signal to send on a bts buffer overflow */
+	unsigned int	bts_ovfl_signal;
+#endif /* CONFIG_X86_PTRACE_BTS */
+};
+
+static inline unsigned long native_get_debugreg(int regno)
+{
+	unsigned long val = 0;	/* Damn you, gcc! */
+
+	switch (regno) {
+	case 0:
+		asm("mov %%db0, %0" :"=r" (val));
+		break;
+	case 1:
+		asm("mov %%db1, %0" :"=r" (val));
+		break;
+	case 2:
+		asm("mov %%db2, %0" :"=r" (val));
+		break;
+	case 3:
+		asm("mov %%db3, %0" :"=r" (val));
+		break;
+	case 6:
+		asm("mov %%db6, %0" :"=r" (val));
+		break;
+	case 7:
+		asm("mov %%db7, %0" :"=r" (val));
+		break;
+	default:
+		BUG();
+	}
+	return val;
+}
+
+static inline void native_set_debugreg(int regno, unsigned long value)
+{
+	switch (regno) {
+	case 0:
+		asm("mov %0, %%db0"	::"r" (value));
+		break;
+	case 1:
+		asm("mov %0, %%db1"	::"r" (value));
+		break;
+	case 2:
+		asm("mov %0, %%db2"	::"r" (value));
+		break;
+	case 3:
+		asm("mov %0, %%db3"	::"r" (value));
+		break;
+	case 6:
+		asm("mov %0, %%db6"	::"r" (value));
+		break;
+	case 7:
+		asm("mov %0, %%db7"	::"r" (value));
+		break;
+	default:
+		BUG();
+	}
+}
+
+/*
+ * Set IOPL bits in EFLAGS from given mask
+ */
+static inline void native_set_iopl_mask(unsigned mask)
+{
+#ifdef CONFIG_X86_32
+	unsigned int reg;
+
+	asm volatile ("pushfl;"
+		      "popl %0;"
+		      "andl %1, %0;"
+		      "orl %2, %0;"
+		      "pushl %0;"
+		      "popfl"
+		      : "=&r" (reg)
+		      : "i" (~X86_EFLAGS_IOPL), "r" (mask));
+#endif
+}
+
+static inline void
+native_load_sp0(struct tss_struct *tss, struct thread_struct *thread)
+{
+	tss->x86_tss.sp0 = thread->sp0;
+#ifdef CONFIG_X86_32
+	/* Only happens when SEP is enabled, no need to test "SEP"arately: */
+	if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
+		tss->x86_tss.ss1 = thread->sysenter_cs;
+		wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
+	}
+#endif
+}
+
+static inline void native_swapgs(void)
+{
+#ifdef CONFIG_X86_64
+	asm volatile("swapgs" ::: "memory");
+#endif
+}
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define __cpuid			native_cpuid
+#define paravirt_enabled()	0
+
+/*
+ * These special macros can be used to get or set a debugging register
+ */
+#define get_debugreg(var, register)				\
+	(var) = native_get_debugreg(register)
+#define set_debugreg(value, register)				\
+	native_set_debugreg(register, value)
+
+static inline void load_sp0(struct tss_struct *tss,
+			    struct thread_struct *thread)
+{
+	native_load_sp0(tss, thread);
+}
+
+#define set_iopl_mask native_set_iopl_mask
+#endif /* CONFIG_PARAVIRT */
+
+/*
+ * Save the cr4 feature set we're using (ie
+ * Pentium 4MB enable and PPro Global page
+ * enable), so that any CPU's that boot up
+ * after us can get the correct flags.
+ */
+extern unsigned long		mmu_cr4_features;
+
+static inline void set_in_cr4(unsigned long mask)
+{
+	unsigned cr4;
+
+	mmu_cr4_features |= mask;
+	cr4 = read_cr4();
+	cr4 |= mask;
+	write_cr4(cr4);
+}
+
+static inline void clear_in_cr4(unsigned long mask)
+{
+	unsigned cr4;
+
+	mmu_cr4_features &= ~mask;
+	cr4 = read_cr4();
+	cr4 &= ~mask;
+	write_cr4(cr4);
+}
+
+typedef struct {
+	unsigned long		seg;
+} mm_segment_t;
+
+
+/*
+ * create a kernel thread without removing it from tasklists
+ */
+extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
+
+/* Free all resources held by a thread. */
+extern void release_thread(struct task_struct *);
+
+/* Prepare to copy thread state - unlazy all lazy state */
+extern void prepare_to_copy(struct task_struct *tsk);
+
+unsigned long get_wchan(struct task_struct *p);
+
+/*
+ * Generic CPUID function
+ * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
+ * resulting in stale register contents being returned.
+ */
+static inline void cpuid(unsigned int op,
+			 unsigned int *eax, unsigned int *ebx,
+			 unsigned int *ecx, unsigned int *edx)
+{
+	*eax = op;
+	*ecx = 0;
+	__cpuid(eax, ebx, ecx, edx);
+}
+
+/* Some CPUID calls want 'count' to be placed in ecx */
+static inline void cpuid_count(unsigned int op, int count,
+			       unsigned int *eax, unsigned int *ebx,
+			       unsigned int *ecx, unsigned int *edx)
+{
+	*eax = op;
+	*ecx = count;
+	__cpuid(eax, ebx, ecx, edx);
+}
+
+/*
+ * CPUID functions returning a single datum
+ */
+static inline unsigned int cpuid_eax(unsigned int op)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return eax;
+}
+
+static inline unsigned int cpuid_ebx(unsigned int op)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return ebx;
+}
+
+static inline unsigned int cpuid_ecx(unsigned int op)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return ecx;
+}
+
+static inline unsigned int cpuid_edx(unsigned int op)
+{
+	unsigned int eax, ebx, ecx, edx;
+
+	cpuid(op, &eax, &ebx, &ecx, &edx);
+
+	return edx;
+}
+
+/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
+static inline void rep_nop(void)
+{
+	asm volatile("rep; nop" ::: "memory");
+}
+
+static inline void cpu_relax(void)
+{
+	rep_nop();
+}
+
+/* Stop speculative execution: */
+static inline void sync_core(void)
+{
+	int tmp;
+
+	asm volatile("cpuid" : "=a" (tmp) : "0" (1)
+		     : "ebx", "ecx", "edx", "memory");
+}
+
+static inline void __monitor(const void *eax, unsigned long ecx,
+			     unsigned long edx)
+{
+	/* "monitor %eax, %ecx, %edx;" */
+	asm volatile(".byte 0x0f, 0x01, 0xc8;"
+		     :: "a" (eax), "c" (ecx), "d"(edx));
+}
+
+static inline void __mwait(unsigned long eax, unsigned long ecx)
+{
+	/* "mwait %eax, %ecx;" */
+	asm volatile(".byte 0x0f, 0x01, 0xc9;"
+		     :: "a" (eax), "c" (ecx));
+}
+
+static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
+{
+	trace_hardirqs_on();
+	/* "mwait %eax, %ecx;" */
+	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
+		     :: "a" (eax), "c" (ecx));
+}
+
+extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
+
+extern void select_idle_routine(const struct cpuinfo_x86 *c);
+
+extern unsigned long		boot_option_idle_override;
+extern unsigned long		idle_halt;
+extern unsigned long		idle_nomwait;
+
+/*
+ * on systems with caches, caches must be flashed as the absolute
+ * last instruction before going into a suspended halt.  Otherwise,
+ * dirty data can linger in the cache and become stale on resume,
+ * leading to strange errors.
+ *
+ * perform a variety of operations to guarantee that the compiler
+ * will not reorder instructions.  wbinvd itself is serializing
+ * so the processor will not reorder.
+ *
+ * Systems without cache can just go into halt.
+ */
+static inline void wbinvd_halt(void)
+{
+	mb();
+	/* check for clflush to determine if wbinvd is legal */
+	if (cpu_has_clflush)
+		asm volatile("cli; wbinvd; 1: hlt; jmp 1b" : : : "memory");
+	else
+		while (1)
+			halt();
+}
+
+extern void enable_sep_cpu(void);
+extern int sysenter_setup(void);
+
+/* Defined in head.S */
+extern struct desc_ptr		early_gdt_descr;
+
+extern void cpu_set_gdt(int);
+extern void switch_to_new_gdt(void);
+extern void cpu_init(void);
+extern void init_gdt(int cpu);
+
+static inline void update_debugctlmsr(unsigned long debugctlmsr)
+{
+#ifndef CONFIG_X86_DEBUGCTLMSR
+	if (boot_cpu_data.x86 < 6)
+		return;
+#endif
+	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+}
+
+/*
+ * from system description table in BIOS. Mostly for MCA use, but
+ * others may find it useful:
+ */
+extern unsigned int		machine_id;
+extern unsigned int		machine_submodel_id;
+extern unsigned int		BIOS_revision;
+
+/* Boot loader type from the setup header: */
+extern int			bootloader_type;
+
+extern char			ignore_fpu_irq;
+
+#define HAVE_ARCH_PICK_MMAP_LAYOUT 1
+#define ARCH_HAS_PREFETCHW
+#define ARCH_HAS_SPINLOCK_PREFETCH
+
+#ifdef CONFIG_X86_32
+# define BASE_PREFETCH		ASM_NOP4
+# define ARCH_HAS_PREFETCH
+#else
+# define BASE_PREFETCH		"prefetcht0 (%1)"
+#endif
+
+/*
+ * Prefetch instructions for Pentium III (+) and AMD Athlon (+)
+ *
+ * It's not worth to care about 3dnow prefetches for the K6
+ * because they are microcoded there and very slow.
+ */
+static inline void prefetch(const void *x)
+{
+	alternative_input(BASE_PREFETCH,
+			  "prefetchnta (%1)",
+			  X86_FEATURE_XMM,
+			  "r" (x));
+}
+
+/*
+ * 3dnow prefetch to get an exclusive cache line.
+ * Useful for spinlocks to avoid one state transition in the
+ * cache coherency protocol:
+ */
+static inline void prefetchw(const void *x)
+{
+	alternative_input(BASE_PREFETCH,
+			  "prefetchw (%1)",
+			  X86_FEATURE_3DNOW,
+			  "r" (x));
+}
+
+static inline void spin_lock_prefetch(const void *x)
+{
+	prefetchw(x);
+}
+
+#ifdef CONFIG_X86_32
+/*
+ * User space process size: 3GB (default).
+ */
+#define TASK_SIZE		PAGE_OFFSET
+#define STACK_TOP		TASK_SIZE
+#define STACK_TOP_MAX		STACK_TOP
+
+#define INIT_THREAD  {							  \
+	.sp0			= sizeof(init_stack) + (long)&init_stack, \
+	.vm86_info		= NULL,					  \
+	.sysenter_cs		= __KERNEL_CS,				  \
+	.io_bitmap_ptr		= NULL,					  \
+	.fs			= __KERNEL_PERCPU,			  \
+}
+
+/*
+ * Note that the .io_bitmap member must be extra-big. This is because
+ * the CPU will access an additional byte beyond the end of the IO
+ * permission bitmap. The extra byte must be all 1 bits, and must
+ * be within the limit.
+ */
+#define INIT_TSS  {							  \
+	.x86_tss = {							  \
+		.sp0		= sizeof(init_stack) + (long)&init_stack, \
+		.ss0		= __KERNEL_DS,				  \
+		.ss1		= __KERNEL_CS,				  \
+		.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,		  \
+	 },								  \
+	.io_bitmap		= { [0 ... IO_BITMAP_LONGS] = ~0 },	  \
+}
+
+extern unsigned long thread_saved_pc(struct task_struct *tsk);
+
+#define THREAD_SIZE_LONGS      (THREAD_SIZE/sizeof(unsigned long))
+#define KSTK_TOP(info)                                                 \
+({                                                                     \
+       unsigned long *__ptr = (unsigned long *)(info);                 \
+       (unsigned long)(&__ptr[THREAD_SIZE_LONGS]);                     \
+})
+
+/*
+ * The below -8 is to reserve 8 bytes on top of the ring0 stack.
+ * This is necessary to guarantee that the entire "struct pt_regs"
+ * is accessable even if the CPU haven't stored the SS/ESP registers
+ * on the stack (interrupt gate does not save these registers
+ * when switching to the same priv ring).
+ * Therefore beware: accessing the ss/esp fields of the
+ * "struct pt_regs" is possible, but they may contain the
+ * completely wrong values.
+ */
+#define task_pt_regs(task)                                             \
+({                                                                     \
+       struct pt_regs *__regs__;                                       \
+       __regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task))-8); \
+       __regs__ - 1;                                                   \
+})
+
+#define KSTK_ESP(task)		(task_pt_regs(task)->sp)
+
+#else
+/*
+ * User space process size. 47bits minus one guard page.
+ */
+#define TASK_SIZE64	((1UL << 47) - PAGE_SIZE)
+
+/* This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define IA32_PAGE_OFFSET	((current->personality & ADDR_LIMIT_3GB) ? \
+					0xc0000000 : 0xFFFFe000)
+
+#define TASK_SIZE		(test_thread_flag(TIF_IA32) ? \
+					IA32_PAGE_OFFSET : TASK_SIZE64)
+#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_IA32)) ? \
+					IA32_PAGE_OFFSET : TASK_SIZE64)
+
+#define STACK_TOP		TASK_SIZE
+#define STACK_TOP_MAX		TASK_SIZE64
+
+#define INIT_THREAD  { \
+	.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
+}
+
+#define INIT_TSS  { \
+	.x86_tss.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
+}
+
+/*
+ * Return saved PC of a blocked thread.
+ * What is this good for? it will be always the scheduler or ret_from_fork.
+ */
+#define thread_saved_pc(t)	(*(unsigned long *)((t)->thread.sp - 8))
+
+#define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
+#define KSTK_ESP(tsk)		-1 /* sorry. doesn't work for syscall. */
+#endif /* CONFIG_X86_64 */
+
+extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
+					       unsigned long new_sp);
+
+/*
+ * This decides where the kernel will search for a free chunk of vm
+ * space during mmap's.
+ */
+#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 3))
+
+#define KSTK_EIP(task)		(task_pt_regs(task)->ip)
+
+/* Get/set a process' ability to use the timestamp counter instruction */
+#define GET_TSC_CTL(adr)	get_tsc_mode((adr))
+#define SET_TSC_CTL(val)	set_tsc_mode((val))
+
+extern int get_tsc_mode(unsigned long adr);
+extern int set_tsc_mode(unsigned int val);
+
+#endif /* ASM_X86__PROCESSOR_H */
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
new file mode 100644
index 000000000000..6e89e8b4de0e
--- /dev/null
+++ b/arch/x86/include/asm/proto.h
@@ -0,0 +1,32 @@
+#ifndef ASM_X86__PROTO_H
+#define ASM_X86__PROTO_H
+
+#include <asm/ldt.h>
+
+/* misc architecture specific prototypes */
+
+extern void early_idt_handler(void);
+
+extern void system_call(void);
+extern void syscall_init(void);
+
+extern void ia32_syscall(void);
+extern void ia32_cstar_target(void);
+extern void ia32_sysenter_target(void);
+
+extern void syscall32_cpu_init(void);
+
+extern void check_efer(void);
+
+#ifdef CONFIG_X86_BIOS_REBOOT
+extern int reboot_force;
+#else
+static const int reboot_force = 0;
+#endif
+
+long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
+
+#define round_up(x, y) (((x) + (y) - 1) & ~((y) - 1))
+#define round_down(x, y) ((x) & ~((y) - 1))
+
+#endif /* ASM_X86__PROTO_H */
diff --git a/arch/x86/include/asm/ptrace-abi.h b/arch/x86/include/asm/ptrace-abi.h
new file mode 100644
index 000000000000..4298b8882a78
--- /dev/null
+++ b/arch/x86/include/asm/ptrace-abi.h
@@ -0,0 +1,145 @@
+#ifndef ASM_X86__PTRACE_ABI_H
+#define ASM_X86__PTRACE_ABI_H
+
+#ifdef __i386__
+
+#define EBX 0
+#define ECX 1
+#define EDX 2
+#define ESI 3
+#define EDI 4
+#define EBP 5
+#define EAX 6
+#define DS 7
+#define ES 8
+#define FS 9
+#define GS 10
+#define ORIG_EAX 11
+#define EIP 12
+#define CS  13
+#define EFL 14
+#define UESP 15
+#define SS   16
+#define FRAME_SIZE 17
+
+#else /* __i386__ */
+
+#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS)
+#define R15 0
+#define R14 8
+#define R13 16
+#define R12 24
+#define RBP 32
+#define RBX 40
+/* arguments: interrupts/non tracing syscalls only save upto here*/
+#define R11 48
+#define R10 56
+#define R9 64
+#define R8 72
+#define RAX 80
+#define RCX 88
+#define RDX 96
+#define RSI 104
+#define RDI 112
+#define ORIG_RAX 120       /* = ERROR */
+/* end of arguments */
+/* cpu exception frame or undefined in case of fast syscall. */
+#define RIP 128
+#define CS 136
+#define EFLAGS 144
+#define RSP 152
+#define SS 160
+#define ARGOFFSET R11
+#endif /* __ASSEMBLY__ */
+
+/* top of stack page */
+#define FRAME_SIZE 168
+
+#endif /* !__i386__ */
+
+/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
+#define PTRACE_GETREGS            12
+#define PTRACE_SETREGS            13
+#define PTRACE_GETFPREGS          14
+#define PTRACE_SETFPREGS          15
+#define PTRACE_GETFPXREGS         18
+#define PTRACE_SETFPXREGS         19
+
+#define PTRACE_OLDSETOPTIONS      21
+
+/* only useful for access 32bit programs / kernels */
+#define PTRACE_GET_THREAD_AREA    25
+#define PTRACE_SET_THREAD_AREA    26
+
+#ifdef __x86_64__
+# define PTRACE_ARCH_PRCTL	  30
+#endif
+
+#define PTRACE_SYSEMU		  31
+#define PTRACE_SYSEMU_SINGLESTEP  32
+
+#define PTRACE_SINGLEBLOCK	33	/* resume execution until next branch */
+
+#ifdef CONFIG_X86_PTRACE_BTS
+
+#ifndef __ASSEMBLY__
+#include <asm/types.h>
+
+/* configuration/status structure used in PTRACE_BTS_CONFIG and
+   PTRACE_BTS_STATUS commands.
+*/
+struct ptrace_bts_config {
+	/* requested or actual size of BTS buffer in bytes */
+	__u32 size;
+	/* bitmask of below flags */
+	__u32 flags;
+	/* buffer overflow signal */
+	__u32 signal;
+	/* actual size of bts_struct in bytes */
+	__u32 bts_size;
+};
+#endif /* __ASSEMBLY__ */
+
+#define PTRACE_BTS_O_TRACE	0x1 /* branch trace */
+#define PTRACE_BTS_O_SCHED	0x2 /* scheduling events w/ jiffies */
+#define PTRACE_BTS_O_SIGNAL     0x4 /* send SIG<signal> on buffer overflow
+				       instead of wrapping around */
+#define PTRACE_BTS_O_ALLOC	0x8 /* (re)allocate buffer */
+
+#define PTRACE_BTS_CONFIG	40
+/* Configure branch trace recording.
+   ADDR points to a struct ptrace_bts_config.
+   DATA gives the size of that buffer.
+   A new buffer is allocated, if requested in the flags.
+   An overflow signal may only be requested for new buffers.
+   Returns the number of bytes read.
+*/
+#define PTRACE_BTS_STATUS	41
+/* Return the current configuration in a struct ptrace_bts_config
+   pointed to by ADDR; DATA gives the size of that buffer.
+   Returns the number of bytes written.
+*/
+#define PTRACE_BTS_SIZE		42
+/* Return the number of available BTS records for draining.
+   DATA and ADDR are ignored.
+*/
+#define PTRACE_BTS_GET		43
+/* Get a single BTS record.
+   DATA defines the index into the BTS array, where 0 is the newest
+   entry, and higher indices refer to older entries.
+   ADDR is pointing to struct bts_struct (see asm/ds.h).
+*/
+#define PTRACE_BTS_CLEAR	44
+/* Clear the BTS buffer.
+   DATA and ADDR are ignored.
+*/
+#define PTRACE_BTS_DRAIN	45
+/* Read all available BTS records and clear the buffer.
+   ADDR points to an array of struct bts_struct.
+   DATA gives the size of that buffer.
+   BTS records are read from oldest to newest.
+   Returns number of BTS records drained.
+*/
+#endif /* CONFIG_X86_PTRACE_BTS */
+
+#endif /* ASM_X86__PTRACE_ABI_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
new file mode 100644
index 000000000000..a2025525a15a
--- /dev/null
+++ b/arch/x86/include/asm/ptrace.h
@@ -0,0 +1,280 @@
+#ifndef ASM_X86__PTRACE_H
+#define ASM_X86__PTRACE_H
+
+#include <linux/compiler.h>	/* For __user */
+#include <asm/ptrace-abi.h>
+#include <asm/processor-flags.h>
+
+#ifdef __KERNEL__
+#include <asm/ds.h>		/* the DS BTS struct is used for ptrace too */
+#include <asm/segment.h>
+#endif
+
+#ifndef __ASSEMBLY__
+
+#ifdef __i386__
+/* this struct defines the way the registers are stored on the
+   stack during a system call. */
+
+#ifndef __KERNEL__
+
+struct pt_regs {
+	long ebx;
+	long ecx;
+	long edx;
+	long esi;
+	long edi;
+	long ebp;
+	long eax;
+	int  xds;
+	int  xes;
+	int  xfs;
+	/* int  gs; */
+	long orig_eax;
+	long eip;
+	int  xcs;
+	long eflags;
+	long esp;
+	int  xss;
+};
+
+#else /* __KERNEL__ */
+
+struct pt_regs {
+	unsigned long bx;
+	unsigned long cx;
+	unsigned long dx;
+	unsigned long si;
+	unsigned long di;
+	unsigned long bp;
+	unsigned long ax;
+	unsigned long ds;
+	unsigned long es;
+	unsigned long fs;
+	/* int  gs; */
+	unsigned long orig_ax;
+	unsigned long ip;
+	unsigned long cs;
+	unsigned long flags;
+	unsigned long sp;
+	unsigned long ss;
+};
+
+#endif /* __KERNEL__ */
+
+#else /* __i386__ */
+
+#ifndef __KERNEL__
+
+struct pt_regs {
+	unsigned long r15;
+	unsigned long r14;
+	unsigned long r13;
+	unsigned long r12;
+	unsigned long rbp;
+	unsigned long rbx;
+/* arguments: non interrupts/non tracing syscalls only save upto here*/
+	unsigned long r11;
+	unsigned long r10;
+	unsigned long r9;
+	unsigned long r8;
+	unsigned long rax;
+	unsigned long rcx;
+	unsigned long rdx;
+	unsigned long rsi;
+	unsigned long rdi;
+	unsigned long orig_rax;
+/* end of arguments */
+/* cpu exception frame or undefined */
+	unsigned long rip;
+	unsigned long cs;
+	unsigned long eflags;
+	unsigned long rsp;
+	unsigned long ss;
+/* top of stack page */
+};
+
+#else /* __KERNEL__ */
+
+struct pt_regs {
+	unsigned long r15;
+	unsigned long r14;
+	unsigned long r13;
+	unsigned long r12;
+	unsigned long bp;
+	unsigned long bx;
+/* arguments: non interrupts/non tracing syscalls only save upto here*/
+	unsigned long r11;
+	unsigned long r10;
+	unsigned long r9;
+	unsigned long r8;
+	unsigned long ax;
+	unsigned long cx;
+	unsigned long dx;
+	unsigned long si;
+	unsigned long di;
+	unsigned long orig_ax;
+/* end of arguments */
+/* cpu exception frame or undefined */
+	unsigned long ip;
+	unsigned long cs;
+	unsigned long flags;
+	unsigned long sp;
+	unsigned long ss;
+/* top of stack page */
+};
+
+#endif /* __KERNEL__ */
+#endif /* !__i386__ */
+
+
+#ifdef CONFIG_X86_PTRACE_BTS
+/* a branch trace record entry
+ *
+ * In order to unify the interface between various processor versions,
+ * we use the below data structure for all processors.
+ */
+enum bts_qualifier {
+	BTS_INVALID = 0,
+	BTS_BRANCH,
+	BTS_TASK_ARRIVES,
+	BTS_TASK_DEPARTS
+};
+
+struct bts_struct {
+	__u64 qualifier;
+	union {
+		/* BTS_BRANCH */
+		struct {
+			__u64 from_ip;
+			__u64 to_ip;
+		} lbr;
+		/* BTS_TASK_ARRIVES or
+		   BTS_TASK_DEPARTS */
+		__u64 jiffies;
+	} variant;
+};
+#endif /* CONFIG_X86_PTRACE_BTS */
+
+#ifdef __KERNEL__
+
+#include <linux/init.h>
+
+struct cpuinfo_x86;
+struct task_struct;
+
+#ifdef CONFIG_X86_PTRACE_BTS
+extern void __cpuinit ptrace_bts_init_intel(struct cpuinfo_x86 *);
+extern void ptrace_bts_take_timestamp(struct task_struct *, enum bts_qualifier);
+#else
+#define ptrace_bts_init_intel(config) do {} while (0)
+#endif /* CONFIG_X86_PTRACE_BTS */
+
+extern unsigned long profile_pc(struct pt_regs *regs);
+
+extern unsigned long
+convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
+extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
+			 int error_code, int si_code);
+void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+
+extern long syscall_trace_enter(struct pt_regs *);
+extern void syscall_trace_leave(struct pt_regs *);
+
+static inline unsigned long regs_return_value(struct pt_regs *regs)
+{
+	return regs->ax;
+}
+
+/*
+ * user_mode_vm(regs) determines whether a register set came from user mode.
+ * This is true if V8086 mode was enabled OR if the register set was from
+ * protected mode with RPL-3 CS value.  This tricky test checks that with
+ * one comparison.  Many places in the kernel can bypass this full check
+ * if they have already ruled out V8086 mode, so user_mode(regs) can be used.
+ */
+static inline int user_mode(struct pt_regs *regs)
+{
+#ifdef CONFIG_X86_32
+	return (regs->cs & SEGMENT_RPL_MASK) == USER_RPL;
+#else
+	return !!(regs->cs & 3);
+#endif
+}
+
+static inline int user_mode_vm(struct pt_regs *regs)
+{
+#ifdef CONFIG_X86_32
+	return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >=
+		USER_RPL;
+#else
+	return user_mode(regs);
+#endif
+}
+
+static inline int v8086_mode(struct pt_regs *regs)
+{
+#ifdef CONFIG_X86_32
+	return (regs->flags & X86_VM_MASK);
+#else
+	return 0;	/* No V86 mode support in long mode */
+#endif
+}
+
+/*
+ * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
+ * when it traps.  So regs will be the current sp.
+ *
+ * This is valid only for kernel mode traps.
+ */
+static inline unsigned long kernel_trap_sp(struct pt_regs *regs)
+{
+#ifdef CONFIG_X86_32
+	return (unsigned long)regs;
+#else
+	return regs->sp;
+#endif
+}
+
+static inline unsigned long instruction_pointer(struct pt_regs *regs)
+{
+	return regs->ip;
+}
+
+static inline unsigned long frame_pointer(struct pt_regs *regs)
+{
+	return regs->bp;
+}
+
+static inline unsigned long user_stack_pointer(struct pt_regs *regs)
+{
+	return regs->sp;
+}
+
+/*
+ * These are defined as per linux/ptrace.h, which see.
+ */
+#define arch_has_single_step()	(1)
+extern void user_enable_single_step(struct task_struct *);
+extern void user_disable_single_step(struct task_struct *);
+
+extern void user_enable_block_step(struct task_struct *);
+#ifdef CONFIG_X86_DEBUGCTLMSR
+#define arch_has_block_step()	(1)
+#else
+#define arch_has_block_step()	(boot_cpu_data.x86 >= 6)
+#endif
+
+struct user_desc;
+extern int do_get_thread_area(struct task_struct *p, int idx,
+			      struct user_desc __user *info);
+extern int do_set_thread_area(struct task_struct *p, int idx,
+			      struct user_desc __user *info, int can_allocate);
+
+#define __ARCH_WANT_COMPAT_SYS_PTRACE
+
+#endif /* __KERNEL__ */
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* ASM_X86__PTRACE_H */
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
new file mode 100644
index 000000000000..edb3b4ecfc81
--- /dev/null
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -0,0 +1,42 @@
+#ifndef ASM_X86__PVCLOCK_ABI_H
+#define ASM_X86__PVCLOCK_ABI_H
+#ifndef __ASSEMBLY__
+
+/*
+ * These structs MUST NOT be changed.
+ * They are the ABI between hypervisor and guest OS.
+ * Both Xen and KVM are using this.
+ *
+ * pvclock_vcpu_time_info holds the system time and the tsc timestamp
+ * of the last update. So the guest can use the tsc delta to get a
+ * more precise system time.  There is one per virtual cpu.
+ *
+ * pvclock_wall_clock references the point in time when the system
+ * time was zero (usually boot time), thus the guest calculates the
+ * current wall clock by adding the system time.
+ *
+ * Protocol for the "version" fields is: hypervisor raises it (making
+ * it uneven) before it starts updating the fields and raises it again
+ * (making it even) when it is done.  Thus the guest can make sure the
+ * time values it got are consistent by checking the version before
+ * and after reading them.
+ */
+
+struct pvclock_vcpu_time_info {
+	u32   version;
+	u32   pad0;
+	u64   tsc_timestamp;
+	u64   system_time;
+	u32   tsc_to_system_mul;
+	s8    tsc_shift;
+	u8    pad[3];
+} __attribute__((__packed__)); /* 32 bytes */
+
+struct pvclock_wall_clock {
+	u32   version;
+	u32   sec;
+	u32   nsec;
+} __attribute__((__packed__));
+
+#endif /* __ASSEMBLY__ */
+#endif /* ASM_X86__PVCLOCK_ABI_H */
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
new file mode 100644
index 000000000000..ad29e277fd6d
--- /dev/null
+++ b/arch/x86/include/asm/pvclock.h
@@ -0,0 +1,14 @@
+#ifndef ASM_X86__PVCLOCK_H
+#define ASM_X86__PVCLOCK_H
+
+#include <linux/clocksource.h>
+#include <asm/pvclock-abi.h>
+
+/* some helper functions for xen and kvm pv clock sources */
+cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
+unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
+void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
+			    struct pvclock_vcpu_time_info *vcpu,
+			    struct timespec *ts);
+
+#endif /* ASM_X86__PVCLOCK_H */
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
new file mode 100644
index 000000000000..1c2f0ce9e31e
--- /dev/null
+++ b/arch/x86/include/asm/reboot.h
@@ -0,0 +1,21 @@
+#ifndef ASM_X86__REBOOT_H
+#define ASM_X86__REBOOT_H
+
+struct pt_regs;
+
+struct machine_ops {
+	void (*restart)(char *cmd);
+	void (*halt)(void);
+	void (*power_off)(void);
+	void (*shutdown)(void);
+	void (*crash_shutdown)(struct pt_regs *);
+	void (*emergency_restart)(void);
+};
+
+extern struct machine_ops machine_ops;
+
+void native_machine_crash_shutdown(struct pt_regs *regs);
+void native_machine_shutdown(void);
+void machine_real_restart(const unsigned char *code, int length);
+
+#endif /* ASM_X86__REBOOT_H */
diff --git a/arch/x86/include/asm/reboot_fixups.h b/arch/x86/include/asm/reboot_fixups.h
new file mode 100644
index 000000000000..2c2987d97570
--- /dev/null
+++ b/arch/x86/include/asm/reboot_fixups.h
@@ -0,0 +1,6 @@
+#ifndef ASM_X86__REBOOT_FIXUPS_H
+#define ASM_X86__REBOOT_FIXUPS_H
+
+extern void mach_reboot_fixups(void);
+
+#endif /* ASM_X86__REBOOT_FIXUPS_H */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
new file mode 100644
index 000000000000..a01c4e376331
--- /dev/null
+++ b/arch/x86/include/asm/required-features.h
@@ -0,0 +1,82 @@
+#ifndef ASM_X86__REQUIRED_FEATURES_H
+#define ASM_X86__REQUIRED_FEATURES_H
+
+/* Define minimum CPUID feature set for kernel These bits are checked
+   really early to actually display a visible error message before the
+   kernel dies.  Make sure to assign features to the proper mask!
+
+   Some requirements that are not in CPUID yet are also in the
+   CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
+
+   The real information is in arch/x86/Kconfig.cpu, this just converts
+   the CONFIGs into a bitmask */
+
+#ifndef CONFIG_MATH_EMULATION
+# define NEED_FPU	(1<<(X86_FEATURE_FPU & 31))
+#else
+# define NEED_FPU	0
+#endif
+
+#if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
+# define NEED_PAE	(1<<(X86_FEATURE_PAE & 31))
+#else
+# define NEED_PAE	0
+#endif
+
+#ifdef CONFIG_X86_CMPXCHG64
+# define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
+#else
+# define NEED_CX8	0
+#endif
+
+#if defined(CONFIG_X86_CMOV) || defined(CONFIG_X86_64)
+# define NEED_CMOV	(1<<(X86_FEATURE_CMOV & 31))
+#else
+# define NEED_CMOV	0
+#endif
+
+#ifdef CONFIG_X86_USE_3DNOW
+# define NEED_3DNOW	(1<<(X86_FEATURE_3DNOW & 31))
+#else
+# define NEED_3DNOW	0
+#endif
+
+#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
+# define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
+#else
+# define NEED_NOPL	0
+#endif
+
+#ifdef CONFIG_X86_64
+#define NEED_PSE	0
+#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
+#define NEED_PGE	(1<<(X86_FEATURE_PGE & 31))
+#define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
+#define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
+#define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
+#define NEED_LM		(1<<(X86_FEATURE_LM & 31))
+#else
+#define NEED_PSE	0
+#define NEED_MSR	0
+#define NEED_PGE	0
+#define NEED_FXSR	0
+#define NEED_XMM	0
+#define NEED_XMM2	0
+#define NEED_LM		0
+#endif
+
+#define REQUIRED_MASK0	(NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
+			 NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
+			 NEED_XMM|NEED_XMM2)
+#define SSE_MASK	(NEED_XMM|NEED_XMM2)
+
+#define REQUIRED_MASK1	(NEED_LM|NEED_3DNOW)
+
+#define REQUIRED_MASK2	0
+#define REQUIRED_MASK3	(NEED_NOPL)
+#define REQUIRED_MASK4	0
+#define REQUIRED_MASK5	0
+#define REQUIRED_MASK6	0
+#define REQUIRED_MASK7	0
+
+#endif /* ASM_X86__REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/resource.h b/arch/x86/include/asm/resource.h
new file mode 100644
index 000000000000..04bc4db8921b
--- /dev/null
+++ b/arch/x86/include/asm/resource.h
@@ -0,0 +1 @@
+#include <asm-generic/resource.h>
diff --git a/arch/x86/include/asm/resume-trace.h b/arch/x86/include/asm/resume-trace.h
new file mode 100644
index 000000000000..e39376d7de50
--- /dev/null
+++ b/arch/x86/include/asm/resume-trace.h
@@ -0,0 +1,21 @@
+#ifndef ASM_X86__RESUME_TRACE_H
+#define ASM_X86__RESUME_TRACE_H
+
+#include <asm/asm.h>
+
+#define TRACE_RESUME(user)					\
+do {								\
+	if (pm_trace_enabled) {					\
+		const void *tracedata;				\
+		asm volatile(_ASM_MOV " $1f,%0\n"		\
+			     ".section .tracedata,\"a\"\n"	\
+			     "1:\t.word %c1\n\t"		\
+			     _ASM_PTR " %c2\n"			\
+			     ".previous"			\
+			     :"=r" (tracedata)			\
+			     : "i" (__LINE__), "i" (__FILE__));	\
+		generate_resume_trace(tracedata, user);		\
+	}							\
+} while (0)
+
+#endif /* ASM_X86__RESUME_TRACE_H */
diff --git a/arch/x86/include/asm/rio.h b/arch/x86/include/asm/rio.h
new file mode 100644
index 000000000000..5e1256bdee83
--- /dev/null
+++ b/arch/x86/include/asm/rio.h
@@ -0,0 +1,63 @@
+/*
+ * Derived from include/asm-x86/mach-summit/mach_mpparse.h
+ *          and include/asm-x86/mach-default/bios_ebda.h
+ *
+ * Author: Laurent Vivier <Laurent.Vivier@bull.net>
+ */
+
+#ifndef ASM_X86__RIO_H
+#define ASM_X86__RIO_H
+
+#define RIO_TABLE_VERSION	3
+
+struct rio_table_hdr {
+	u8 version;		/* Version number of this data structure  */
+	u8 num_scal_dev;	/* # of Scalability devices               */
+	u8 num_rio_dev;		/* # of RIO I/O devices                   */
+} __attribute__((packed));
+
+struct scal_detail {
+	u8 node_id;		/* Scalability Node ID                    */
+	u32 CBAR;		/* Address of 1MB register space          */
+	u8 port0node;		/* Node ID port connected to: 0xFF=None   */
+	u8 port0port;		/* Port num port connected to: 0,1,2, or  */
+				/* 0xFF=None                              */
+	u8 port1node;		/* Node ID port connected to: 0xFF = None */
+	u8 port1port;		/* Port num port connected to: 0,1,2, or  */
+				/* 0xFF=None                              */
+	u8 port2node;		/* Node ID port connected to: 0xFF = None */
+	u8 port2port;		/* Port num port connected to: 0,1,2, or  */
+				/* 0xFF=None                              */
+	u8 chassis_num;		/* 1 based Chassis number (1 = boot node) */
+} __attribute__((packed));
+
+struct rio_detail {
+	u8 node_id;		/* RIO Node ID                            */
+	u32 BBAR;		/* Address of 1MB register space          */
+	u8 type;		/* Type of device                         */
+	u8 owner_id;		/* Node ID of Hurricane that owns this    */
+				/* node                                   */
+	u8 port0node;		/* Node ID port connected to: 0xFF=None   */
+	u8 port0port;		/* Port num port connected to: 0,1,2, or  */
+				/* 0xFF=None                              */
+	u8 port1node;		/* Node ID port connected to: 0xFF=None   */
+	u8 port1port;		/* Port num port connected to: 0,1,2, or  */
+				/* 0xFF=None                              */
+	u8 first_slot;		/* Lowest slot number below this Calgary  */
+	u8 status;		/* Bit 0 = 1 : the XAPIC is used          */
+				/*       = 0 : the XAPIC is not used, ie: */
+				/*            ints fwded to another XAPIC */
+				/*           Bits1:7 Reserved             */
+	u8 WP_index;		/* instance index - lower ones have       */
+				/*     lower slot numbers/PCI bus numbers */
+	u8 chassis_num;		/* 1 based Chassis number                 */
+} __attribute__((packed));
+
+enum {
+	HURR_SCALABILTY	= 0,	/* Hurricane Scalability info */
+	HURR_RIOIB	= 2,	/* Hurricane RIOIB info       */
+	COMPAT_CALGARY	= 4,	/* Compatibility Calgary      */
+	ALT_CALGARY	= 5,	/* Second Planar Calgary      */
+};
+
+#endif /* ASM_X86__RIO_H */
diff --git a/arch/x86/include/asm/rtc.h b/arch/x86/include/asm/rtc.h
new file mode 100644
index 000000000000..f71c3b0ed360
--- /dev/null
+++ b/arch/x86/include/asm/rtc.h
@@ -0,0 +1 @@
+#include <asm-generic/rtc.h>
diff --git a/arch/x86/include/asm/rwlock.h b/arch/x86/include/asm/rwlock.h
new file mode 100644
index 000000000000..48a3109e1a7d
--- /dev/null
+++ b/arch/x86/include/asm/rwlock.h
@@ -0,0 +1,8 @@
+#ifndef ASM_X86__RWLOCK_H
+#define ASM_X86__RWLOCK_H
+
+#define RW_LOCK_BIAS		 0x01000000
+
+/* Actual code is in asm/spinlock.h or in arch/x86/lib/rwlock.S */
+
+#endif /* ASM_X86__RWLOCK_H */
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
new file mode 100644
index 000000000000..3ff3015b71a8
--- /dev/null
+++ b/arch/x86/include/asm/rwsem.h
@@ -0,0 +1,265 @@
+/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+
+ *
+ * Written by David Howells (dhowells@redhat.com).
+ *
+ * Derived from asm-x86/semaphore.h
+ *
+ *
+ * The MSW of the count is the negated number of active writers and waiting
+ * lockers, and the LSW is the total number of active locks
+ *
+ * The lock count is initialized to 0 (no active and no waiting lockers).
+ *
+ * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an
+ * uncontended lock. This can be determined because XADD returns the old value.
+ * Readers increment by 1 and see a positive value when uncontended, negative
+ * if there are writers (and maybe) readers waiting (in which case it goes to
+ * sleep).
+ *
+ * The value of WAITING_BIAS supports up to 32766 waiting processes. This can
+ * be extended to 65534 by manually checking the whole MSW rather than relying
+ * on the S flag.
+ *
+ * The value of ACTIVE_BIAS supports up to 65535 active processes.
+ *
+ * This should be totally fair - if anything is waiting, a process that wants a
+ * lock will go to the back of the queue. When the currently active lock is
+ * released, if there's a writer at the front of the queue, then that and only
+ * that will be woken up; if there's a bunch of consequtive readers at the
+ * front, then they'll all be woken up, but no other readers will be.
+ */
+
+#ifndef ASM_X86__RWSEM_H
+#define ASM_X86__RWSEM_H
+
+#ifndef _LINUX_RWSEM_H
+#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
+#endif
+
+#ifdef __KERNEL__
+
+#include <linux/list.h>
+#include <linux/spinlock.h>
+#include <linux/lockdep.h>
+
+struct rwsem_waiter;
+
+extern asmregparm struct rw_semaphore *
+ rwsem_down_read_failed(struct rw_semaphore *sem);
+extern asmregparm struct rw_semaphore *
+ rwsem_down_write_failed(struct rw_semaphore *sem);
+extern asmregparm struct rw_semaphore *
+ rwsem_wake(struct rw_semaphore *);
+extern asmregparm struct rw_semaphore *
+ rwsem_downgrade_wake(struct rw_semaphore *sem);
+
+/*
+ * the semaphore definition
+ */
+
+#define RWSEM_UNLOCKED_VALUE		0x00000000
+#define RWSEM_ACTIVE_BIAS		0x00000001
+#define RWSEM_ACTIVE_MASK		0x0000ffff
+#define RWSEM_WAITING_BIAS		(-0x00010000)
+#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
+#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
+
+struct rw_semaphore {
+	signed long		count;
+	spinlock_t		wait_lock;
+	struct list_head	wait_list;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif
+};
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
+#else
+# define __RWSEM_DEP_MAP_INIT(lockname)
+#endif
+
+
+#define __RWSEM_INITIALIZER(name)				\
+{								\
+	RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
+	LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) \
+}
+
+#define DECLARE_RWSEM(name)					\
+	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
+
+extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
+			 struct lock_class_key *key);
+
+#define init_rwsem(sem)						\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	__init_rwsem((sem), #sem, &__key);			\
+} while (0)
+
+/*
+ * lock for reading
+ */
+static inline void __down_read(struct rw_semaphore *sem)
+{
+	asm volatile("# beginning down_read\n\t"
+		     LOCK_PREFIX "  incl      (%%eax)\n\t"
+		     /* adds 0x00000001, returns the old value */
+		     "  jns        1f\n"
+		     "  call call_rwsem_down_read_failed\n"
+		     "1:\n\t"
+		     "# ending down_read\n\t"
+		     : "+m" (sem->count)
+		     : "a" (sem)
+		     : "memory", "cc");
+}
+
+/*
+ * trylock for reading -- returns 1 if successful, 0 if contention
+ */
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+	__s32 result, tmp;
+	asm volatile("# beginning __down_read_trylock\n\t"
+		     "  movl      %0,%1\n\t"
+		     "1:\n\t"
+		     "  movl	     %1,%2\n\t"
+		     "  addl      %3,%2\n\t"
+		     "  jle	     2f\n\t"
+		     LOCK_PREFIX "  cmpxchgl  %2,%0\n\t"
+		     "  jnz	     1b\n\t"
+		     "2:\n\t"
+		     "# ending __down_read_trylock\n\t"
+		     : "+m" (sem->count), "=&a" (result), "=&r" (tmp)
+		     : "i" (RWSEM_ACTIVE_READ_BIAS)
+		     : "memory", "cc");
+	return result >= 0 ? 1 : 0;
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
+{
+	int tmp;
+
+	tmp = RWSEM_ACTIVE_WRITE_BIAS;
+	asm volatile("# beginning down_write\n\t"
+		     LOCK_PREFIX "  xadd      %%edx,(%%eax)\n\t"
+		     /* subtract 0x0000ffff, returns the old value */
+		     "  testl     %%edx,%%edx\n\t"
+		     /* was the count 0 before? */
+		     "  jz        1f\n"
+		     "  call call_rwsem_down_write_failed\n"
+		     "1:\n"
+		     "# ending down_write"
+		     : "+m" (sem->count), "=d" (tmp)
+		     : "a" (sem), "1" (tmp)
+		     : "memory", "cc");
+}
+
+static inline void __down_write(struct rw_semaphore *sem)
+{
+	__down_write_nested(sem, 0);
+}
+
+/*
+ * trylock for writing -- returns 1 if successful, 0 if contention
+ */
+static inline int __down_write_trylock(struct rw_semaphore *sem)
+{
+	signed long ret = cmpxchg(&sem->count,
+				  RWSEM_UNLOCKED_VALUE,
+				  RWSEM_ACTIVE_WRITE_BIAS);
+	if (ret == RWSEM_UNLOCKED_VALUE)
+		return 1;
+	return 0;
+}
+
+/*
+ * unlock after reading
+ */
+static inline void __up_read(struct rw_semaphore *sem)
+{
+	__s32 tmp = -RWSEM_ACTIVE_READ_BIAS;
+	asm volatile("# beginning __up_read\n\t"
+		     LOCK_PREFIX "  xadd      %%edx,(%%eax)\n\t"
+		     /* subtracts 1, returns the old value */
+		     "  jns        1f\n\t"
+		     "  call call_rwsem_wake\n"
+		     "1:\n"
+		     "# ending __up_read\n"
+		     : "+m" (sem->count), "=d" (tmp)
+		     : "a" (sem), "1" (tmp)
+		     : "memory", "cc");
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+	asm volatile("# beginning __up_write\n\t"
+		     "  movl      %2,%%edx\n\t"
+		     LOCK_PREFIX "  xaddl     %%edx,(%%eax)\n\t"
+		     /* tries to transition
+			0xffff0001 -> 0x00000000 */
+		     "  jz       1f\n"
+		     "  call call_rwsem_wake\n"
+		     "1:\n\t"
+		     "# ending __up_write\n"
+		     : "+m" (sem->count)
+		     : "a" (sem), "i" (-RWSEM_ACTIVE_WRITE_BIAS)
+		     : "memory", "cc", "edx");
+}
+
+/*
+ * downgrade write lock to read lock
+ */
+static inline void __downgrade_write(struct rw_semaphore *sem)
+{
+	asm volatile("# beginning __downgrade_write\n\t"
+		     LOCK_PREFIX "  addl      %2,(%%eax)\n\t"
+		     /* transitions 0xZZZZ0001 -> 0xYYYY0001 */
+		     "  jns       1f\n\t"
+		     "  call call_rwsem_downgrade_wake\n"
+		     "1:\n\t"
+		     "# ending __downgrade_write\n"
+		     : "+m" (sem->count)
+		     : "a" (sem), "i" (-RWSEM_WAITING_BIAS)
+		     : "memory", "cc");
+}
+
+/*
+ * implement atomic add functionality
+ */
+static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
+{
+	asm volatile(LOCK_PREFIX "addl %1,%0"
+		     : "+m" (sem->count)
+		     : "ir" (delta));
+}
+
+/*
+ * implement exchange and add functionality
+ */
+static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
+{
+	int tmp = delta;
+
+	asm volatile(LOCK_PREFIX "xadd %0,%1"
+		     : "+r" (tmp), "+m" (sem->count)
+		     : : "memory");
+
+	return tmp + delta;
+}
+
+static inline int rwsem_is_locked(struct rw_semaphore *sem)
+{
+	return (sem->count != 0);
+}
+
+#endif /* __KERNEL__ */
+#endif /* ASM_X86__RWSEM_H */
diff --git a/arch/x86/include/asm/scatterlist.h b/arch/x86/include/asm/scatterlist.h
new file mode 100644
index 000000000000..ee48f880005d
--- /dev/null
+++ b/arch/x86/include/asm/scatterlist.h
@@ -0,0 +1,33 @@
+#ifndef ASM_X86__SCATTERLIST_H
+#define ASM_X86__SCATTERLIST_H
+
+#include <asm/types.h>
+
+struct scatterlist {
+#ifdef CONFIG_DEBUG_SG
+	unsigned long	sg_magic;
+#endif
+	unsigned long	page_link;
+	unsigned int	offset;
+	unsigned int	length;
+	dma_addr_t	dma_address;
+	unsigned int	dma_length;
+};
+
+#define ARCH_HAS_SG_CHAIN
+#define ISA_DMA_THRESHOLD (0x00ffffff)
+
+/*
+ * These macros should be used after a pci_map_sg call has been done
+ * to get bus addresses of each of the SG entries and their lengths.
+ * You should only work with the number of sg entries pci_map_sg
+ * returns.
+ */
+#define sg_dma_address(sg)	((sg)->dma_address)
+#ifdef CONFIG_X86_32
+# define sg_dma_len(sg)		((sg)->length)
+#else
+# define sg_dma_len(sg)		((sg)->dma_length)
+#endif
+
+#endif /* ASM_X86__SCATTERLIST_H */
diff --git a/arch/x86/include/asm/seccomp.h b/arch/x86/include/asm/seccomp.h
new file mode 100644
index 000000000000..c62e58a5a90d
--- /dev/null
+++ b/arch/x86/include/asm/seccomp.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "seccomp_32.h"
+#else
+# include "seccomp_64.h"
+#endif
diff --git a/arch/x86/include/asm/seccomp_32.h b/arch/x86/include/asm/seccomp_32.h
new file mode 100644
index 000000000000..cf9ab2dbcef1
--- /dev/null
+++ b/arch/x86/include/asm/seccomp_32.h
@@ -0,0 +1,17 @@
+#ifndef ASM_X86__SECCOMP_32_H
+#define ASM_X86__SECCOMP_32_H
+
+#include <linux/thread_info.h>
+
+#ifdef TIF_32BIT
+#error "unexpected TIF_32BIT on i386"
+#endif
+
+#include <linux/unistd.h>
+
+#define __NR_seccomp_read __NR_read
+#define __NR_seccomp_write __NR_write
+#define __NR_seccomp_exit __NR_exit
+#define __NR_seccomp_sigreturn __NR_sigreturn
+
+#endif /* ASM_X86__SECCOMP_32_H */
diff --git a/arch/x86/include/asm/seccomp_64.h b/arch/x86/include/asm/seccomp_64.h
new file mode 100644
index 000000000000..03274cea751f
--- /dev/null
+++ b/arch/x86/include/asm/seccomp_64.h
@@ -0,0 +1,25 @@
+#ifndef ASM_X86__SECCOMP_64_H
+#define ASM_X86__SECCOMP_64_H
+
+#include <linux/thread_info.h>
+
+#ifdef TIF_32BIT
+#error "unexpected TIF_32BIT on x86_64"
+#else
+#define TIF_32BIT TIF_IA32
+#endif
+
+#include <linux/unistd.h>
+#include <asm/ia32_unistd.h>
+
+#define __NR_seccomp_read __NR_read
+#define __NR_seccomp_write __NR_write
+#define __NR_seccomp_exit __NR_exit
+#define __NR_seccomp_sigreturn __NR_rt_sigreturn
+
+#define __NR_seccomp_read_32 __NR_ia32_read
+#define __NR_seccomp_write_32 __NR_ia32_write
+#define __NR_seccomp_exit_32 __NR_ia32_exit
+#define __NR_seccomp_sigreturn_32 __NR_ia32_sigreturn
+
+#endif /* ASM_X86__SECCOMP_64_H */
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
new file mode 100644
index 000000000000..2b8c5160388f
--- /dev/null
+++ b/arch/x86/include/asm/sections.h
@@ -0,0 +1 @@
+#include <asm-generic/sections.h>
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
new file mode 100644
index 000000000000..5d6e69454891
--- /dev/null
+++ b/arch/x86/include/asm/segment.h
@@ -0,0 +1,209 @@
+#ifndef ASM_X86__SEGMENT_H
+#define ASM_X86__SEGMENT_H
+
+/* Constructor for a conventional segment GDT (or LDT) entry */
+/* This is a macro so it can be used in initializers */
+#define GDT_ENTRY(flags, base, limit)			\
+	((((base)  & 0xff000000ULL) << (56-24)) |	\
+	 (((flags) & 0x0000f0ffULL) << 40) |		\
+	 (((limit) & 0x000f0000ULL) << (48-16)) |	\
+	 (((base)  & 0x00ffffffULL) << 16) |		\
+	 (((limit) & 0x0000ffffULL)))
+
+/* Simple and small GDT entries for booting only */
+
+#define GDT_ENTRY_BOOT_CS	2
+#define __BOOT_CS		(GDT_ENTRY_BOOT_CS * 8)
+
+#define GDT_ENTRY_BOOT_DS	(GDT_ENTRY_BOOT_CS + 1)
+#define __BOOT_DS		(GDT_ENTRY_BOOT_DS * 8)
+
+#define GDT_ENTRY_BOOT_TSS	(GDT_ENTRY_BOOT_CS + 2)
+#define __BOOT_TSS		(GDT_ENTRY_BOOT_TSS * 8)
+
+#ifdef CONFIG_X86_32
+/*
+ * The layout of the per-CPU GDT under Linux:
+ *
+ *   0 - null
+ *   1 - reserved
+ *   2 - reserved
+ *   3 - reserved
+ *
+ *   4 - unused			<==== new cacheline
+ *   5 - unused
+ *
+ *  ------- start of TLS (Thread-Local Storage) segments:
+ *
+ *   6 - TLS segment #1			[ glibc's TLS segment ]
+ *   7 - TLS segment #2			[ Wine's %fs Win32 segment ]
+ *   8 - TLS segment #3
+ *   9 - reserved
+ *  10 - reserved
+ *  11 - reserved
+ *
+ *  ------- start of kernel segments:
+ *
+ *  12 - kernel code segment		<==== new cacheline
+ *  13 - kernel data segment
+ *  14 - default user CS
+ *  15 - default user DS
+ *  16 - TSS
+ *  17 - LDT
+ *  18 - PNPBIOS support (16->32 gate)
+ *  19 - PNPBIOS support
+ *  20 - PNPBIOS support
+ *  21 - PNPBIOS support
+ *  22 - PNPBIOS support
+ *  23 - APM BIOS support
+ *  24 - APM BIOS support
+ *  25 - APM BIOS support
+ *
+ *  26 - ESPFIX small SS
+ *  27 - per-cpu			[ offset to per-cpu data area ]
+ *  28 - unused
+ *  29 - unused
+ *  30 - unused
+ *  31 - TSS for double fault handler
+ */
+#define GDT_ENTRY_TLS_MIN	6
+#define GDT_ENTRY_TLS_MAX 	(GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1)
+
+#define GDT_ENTRY_DEFAULT_USER_CS	14
+
+#define GDT_ENTRY_DEFAULT_USER_DS	15
+
+#define GDT_ENTRY_KERNEL_BASE	12
+
+#define GDT_ENTRY_KERNEL_CS		(GDT_ENTRY_KERNEL_BASE + 0)
+
+#define GDT_ENTRY_KERNEL_DS		(GDT_ENTRY_KERNEL_BASE + 1)
+
+#define GDT_ENTRY_TSS			(GDT_ENTRY_KERNEL_BASE + 4)
+#define GDT_ENTRY_LDT			(GDT_ENTRY_KERNEL_BASE + 5)
+
+#define GDT_ENTRY_PNPBIOS_BASE		(GDT_ENTRY_KERNEL_BASE + 6)
+#define GDT_ENTRY_APMBIOS_BASE		(GDT_ENTRY_KERNEL_BASE + 11)
+
+#define GDT_ENTRY_ESPFIX_SS		(GDT_ENTRY_KERNEL_BASE + 14)
+#define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS * 8)
+
+#define GDT_ENTRY_PERCPU			(GDT_ENTRY_KERNEL_BASE + 15)
+#ifdef CONFIG_SMP
+#define __KERNEL_PERCPU (GDT_ENTRY_PERCPU * 8)
+#else
+#define __KERNEL_PERCPU 0
+#endif
+
+#define GDT_ENTRY_DOUBLEFAULT_TSS	31
+
+/*
+ * The GDT has 32 entries
+ */
+#define GDT_ENTRIES 32
+
+/* The PnP BIOS entries in the GDT */
+#define GDT_ENTRY_PNPBIOS_CS32		(GDT_ENTRY_PNPBIOS_BASE + 0)
+#define GDT_ENTRY_PNPBIOS_CS16		(GDT_ENTRY_PNPBIOS_BASE + 1)
+#define GDT_ENTRY_PNPBIOS_DS		(GDT_ENTRY_PNPBIOS_BASE + 2)
+#define GDT_ENTRY_PNPBIOS_TS1		(GDT_ENTRY_PNPBIOS_BASE + 3)
+#define GDT_ENTRY_PNPBIOS_TS2		(GDT_ENTRY_PNPBIOS_BASE + 4)
+
+/* The PnP BIOS selectors */
+#define PNP_CS32   (GDT_ENTRY_PNPBIOS_CS32 * 8)	/* segment for calling fn */
+#define PNP_CS16   (GDT_ENTRY_PNPBIOS_CS16 * 8)	/* code segment for BIOS */
+#define PNP_DS     (GDT_ENTRY_PNPBIOS_DS * 8)	/* data segment for BIOS */
+#define PNP_TS1    (GDT_ENTRY_PNPBIOS_TS1 * 8)	/* transfer data segment */
+#define PNP_TS2    (GDT_ENTRY_PNPBIOS_TS2 * 8)	/* another data segment */
+
+/* Bottom two bits of selector give the ring privilege level */
+#define SEGMENT_RPL_MASK	0x3
+/* Bit 2 is table indicator (LDT/GDT) */
+#define SEGMENT_TI_MASK		0x4
+
+/* User mode is privilege level 3 */
+#define USER_RPL		0x3
+/* LDT segment has TI set, GDT has it cleared */
+#define SEGMENT_LDT		0x4
+#define SEGMENT_GDT		0x0
+
+/*
+ * Matching rules for certain types of segments.
+ */
+
+/* Matches PNP_CS32 and PNP_CS16 (they must be consecutive) */
+#define SEGMENT_IS_PNP_CODE(x)   (((x) & 0xf4) == GDT_ENTRY_PNPBIOS_BASE * 8)
+
+
+#else
+#include <asm/cache.h>
+
+#define GDT_ENTRY_KERNEL32_CS 1
+#define GDT_ENTRY_KERNEL_CS 2
+#define GDT_ENTRY_KERNEL_DS 3
+
+#define __KERNEL32_CS   (GDT_ENTRY_KERNEL32_CS * 8)
+
+/*
+ * we cannot use the same code segment descriptor for user and kernel
+ * -- not even in the long flat mode, because of different DPL /kkeil
+ * The segment offset needs to contain a RPL. Grr. -AK
+ * GDT layout to get 64bit syscall right (sysret hardcodes gdt offsets)
+ */
+#define GDT_ENTRY_DEFAULT_USER32_CS 4
+#define GDT_ENTRY_DEFAULT_USER_DS 5
+#define GDT_ENTRY_DEFAULT_USER_CS 6
+#define __USER32_CS   (GDT_ENTRY_DEFAULT_USER32_CS * 8 + 3)
+#define __USER32_DS	__USER_DS
+
+#define GDT_ENTRY_TSS 8	/* needs two entries */
+#define GDT_ENTRY_LDT 10 /* needs two entries */
+#define GDT_ENTRY_TLS_MIN 12
+#define GDT_ENTRY_TLS_MAX 14
+
+#define GDT_ENTRY_PER_CPU 15	/* Abused to load per CPU data from limit */
+#define __PER_CPU_SEG	(GDT_ENTRY_PER_CPU * 8 + 3)
+
+/* TLS indexes for 64bit - hardcoded in arch_prctl */
+#define FS_TLS 0
+#define GS_TLS 1
+
+#define GS_TLS_SEL ((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3)
+#define FS_TLS_SEL ((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3)
+
+#define GDT_ENTRIES 16
+
+#endif
+
+#define __KERNEL_CS	(GDT_ENTRY_KERNEL_CS * 8)
+#define __KERNEL_DS	(GDT_ENTRY_KERNEL_DS * 8)
+#define __USER_DS     (GDT_ENTRY_DEFAULT_USER_DS* 8 + 3)
+#define __USER_CS     (GDT_ENTRY_DEFAULT_USER_CS* 8 + 3)
+#ifndef CONFIG_PARAVIRT
+#define get_kernel_rpl()  0
+#endif
+
+/* User mode is privilege level 3 */
+#define USER_RPL		0x3
+/* LDT segment has TI set, GDT has it cleared */
+#define SEGMENT_LDT		0x4
+#define SEGMENT_GDT		0x0
+
+/* Bottom two bits of selector give the ring privilege level */
+#define SEGMENT_RPL_MASK	0x3
+/* Bit 2 is table indicator (LDT/GDT) */
+#define SEGMENT_TI_MASK		0x4
+
+#define IDT_ENTRIES 256
+#define NUM_EXCEPTION_VECTORS 32
+#define GDT_SIZE (GDT_ENTRIES * 8)
+#define GDT_ENTRY_TLS_ENTRIES 3
+#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8)
+
+#ifdef __KERNEL__
+#ifndef __ASSEMBLY__
+extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10];
+#endif
+#endif
+
+#endif /* ASM_X86__SEGMENT_H */
diff --git a/arch/x86/include/asm/sembuf.h b/arch/x86/include/asm/sembuf.h
new file mode 100644
index 000000000000..81f06b7e5a3f
--- /dev/null
+++ b/arch/x86/include/asm/sembuf.h
@@ -0,0 +1,24 @@
+#ifndef ASM_X86__SEMBUF_H
+#define ASM_X86__SEMBUF_H
+
+/*
+ * The semid64_ds structure for x86 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ */
+struct semid64_ds {
+	struct ipc64_perm sem_perm;	/* permissions .. see ipc.h */
+	__kernel_time_t	sem_otime;	/* last semop time */
+	unsigned long	__unused1;
+	__kernel_time_t	sem_ctime;	/* last change time */
+	unsigned long	__unused2;
+	unsigned long	sem_nsems;	/* no. of semaphores in array */
+	unsigned long	__unused3;
+	unsigned long	__unused4;
+};
+
+#endif /* ASM_X86__SEMBUF_H */
diff --git a/arch/x86/include/asm/serial.h b/arch/x86/include/asm/serial.h
new file mode 100644
index 000000000000..303660b671e5
--- /dev/null
+++ b/arch/x86/include/asm/serial.h
@@ -0,0 +1,29 @@
+#ifndef ASM_X86__SERIAL_H
+#define ASM_X86__SERIAL_H
+
+/*
+ * This assumes you have a 1.8432 MHz clock for your UART.
+ *
+ * It'd be nice if someone built a serial card with a 24.576 MHz
+ * clock, since the 16550A is capable of handling a top speed of 1.5
+ * megabits/second; but this requires the faster clock.
+ */
+#define BASE_BAUD ( 1843200 / 16 )
+
+/* Standard COM flags (except for COM4, because of the 8514 problem) */
+#ifdef CONFIG_SERIAL_DETECT_IRQ
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
+#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
+#else
+#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
+#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
+#endif
+
+#define SERIAL_PORT_DFNS			\
+	/* UART CLK   PORT IRQ     FLAGS        */			\
+	{ 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS },	/* ttyS0 */	\
+	{ 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS },	/* ttyS1 */	\
+	{ 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS },	/* ttyS2 */	\
+	{ 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS },	/* ttyS3 */
+
+#endif /* ASM_X86__SERIAL_H */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
new file mode 100644
index 000000000000..11b6cc14b289
--- /dev/null
+++ b/arch/x86/include/asm/setup.h
@@ -0,0 +1,105 @@
+#ifndef ASM_X86__SETUP_H
+#define ASM_X86__SETUP_H
+
+#define COMMAND_LINE_SIZE 2048
+
+#ifndef __ASSEMBLY__
+
+/* Interrupt control for vSMPowered x86_64 systems */
+void vsmp_init(void);
+
+#ifdef CONFIG_X86_VISWS
+extern void visws_early_detect(void);
+extern int is_visws_box(void);
+#else
+static inline void visws_early_detect(void) { }
+static inline int is_visws_box(void) { return 0; }
+#endif
+
+/*
+ * Any setup quirks to be performed?
+ */
+struct mpc_config_processor;
+struct mpc_config_bus;
+struct mp_config_oemtable;
+struct x86_quirks {
+	int (*arch_pre_time_init)(void);
+	int (*arch_time_init)(void);
+	int (*arch_pre_intr_init)(void);
+	int (*arch_intr_init)(void);
+	int (*arch_trap_init)(void);
+	char * (*arch_memory_setup)(void);
+	int (*mach_get_smp_config)(unsigned int early);
+	int (*mach_find_smp_config)(unsigned int reserve);
+
+	int *mpc_record;
+	int (*mpc_apic_id)(struct mpc_config_processor *m);
+	void (*mpc_oem_bus_info)(struct mpc_config_bus *m, char *name);
+	void (*mpc_oem_pci_bus)(struct mpc_config_bus *m);
+	void (*smp_read_mpc_oem)(struct mp_config_oemtable *oemtable,
+                                    unsigned short oemsize);
+	int (*setup_ioapic_ids)(void);
+};
+
+extern struct x86_quirks *x86_quirks;
+extern unsigned long saved_video_mode;
+
+#ifndef CONFIG_PARAVIRT
+#define paravirt_post_allocator_init()	do {} while (0)
+#endif
+#endif /* __ASSEMBLY__ */
+
+#ifdef __KERNEL__
+
+#ifdef __i386__
+
+#include <linux/pfn.h>
+/*
+ * Reserved space for vmalloc and iomap - defined in asm/page.h
+ */
+#define MAXMEM_PFN	PFN_DOWN(MAXMEM)
+#define MAX_NONPAE_PFN	(1 << 20)
+
+#endif /* __i386__ */
+
+#define PARAM_SIZE 4096		/* sizeof(struct boot_params) */
+
+#define OLD_CL_MAGIC		0xA33F
+#define OLD_CL_ADDRESS		0x020	/* Relative to real mode data */
+#define NEW_CL_POINTER		0x228	/* Relative to real mode data */
+
+#ifndef __ASSEMBLY__
+#include <asm/bootparam.h>
+
+#ifndef _SETUP
+
+/*
+ * This is set up by the setup-routine at boot-time
+ */
+extern struct boot_params boot_params;
+
+/*
+ * Do NOT EVER look at the BIOS memory size location.
+ * It does not work on many machines.
+ */
+#define LOWMEMSIZE()	(0x9f000)
+
+#ifdef __i386__
+
+void __init i386_start_kernel(void);
+extern void probe_roms(void);
+
+extern unsigned long init_pg_tables_start;
+extern unsigned long init_pg_tables_end;
+
+#else
+void __init x86_64_init_pda(void);
+void __init x86_64_start_kernel(char *real_mode);
+void __init x86_64_start_reservations(char *real_mode_data);
+
+#endif /* __i386__ */
+#endif /* _SETUP */
+#endif /* __ASSEMBLY__ */
+#endif  /*  __KERNEL__  */
+
+#endif /* ASM_X86__SETUP_H */
diff --git a/arch/x86/include/asm/shmbuf.h b/arch/x86/include/asm/shmbuf.h
new file mode 100644
index 000000000000..f51aec2298e9
--- /dev/null
+++ b/arch/x86/include/asm/shmbuf.h
@@ -0,0 +1,51 @@
+#ifndef ASM_X86__SHMBUF_H
+#define ASM_X86__SHMBUF_H
+
+/*
+ * The shmid64_ds structure for x86 architecture.
+ * Note extra padding because this structure is passed back and forth
+ * between kernel and user space.
+ *
+ * Pad space on 32 bit is left for:
+ * - 64-bit time_t to solve y2038 problem
+ * - 2 miscellaneous 32-bit values
+ *
+ * Pad space on 64 bit is left for:
+ * - 2 miscellaneous 64-bit values
+ */
+
+struct shmid64_ds {
+	struct ipc64_perm	shm_perm;	/* operation perms */
+	size_t			shm_segsz;	/* size of segment (bytes) */
+	__kernel_time_t		shm_atime;	/* last attach time */
+#ifdef __i386__
+	unsigned long		__unused1;
+#endif
+	__kernel_time_t		shm_dtime;	/* last detach time */
+#ifdef __i386__
+	unsigned long		__unused2;
+#endif
+	__kernel_time_t		shm_ctime;	/* last change time */
+#ifdef __i386__
+	unsigned long		__unused3;
+#endif
+	__kernel_pid_t		shm_cpid;	/* pid of creator */
+	__kernel_pid_t		shm_lpid;	/* pid of last operator */
+	unsigned long		shm_nattch;	/* no. of current attaches */
+	unsigned long		__unused4;
+	unsigned long		__unused5;
+};
+
+struct shminfo64 {
+	unsigned long	shmmax;
+	unsigned long	shmmin;
+	unsigned long	shmmni;
+	unsigned long	shmseg;
+	unsigned long	shmall;
+	unsigned long	__unused1;
+	unsigned long	__unused2;
+	unsigned long	__unused3;
+	unsigned long	__unused4;
+};
+
+#endif /* ASM_X86__SHMBUF_H */
diff --git a/arch/x86/include/asm/shmparam.h b/arch/x86/include/asm/shmparam.h
new file mode 100644
index 000000000000..a83a1fd96a0e
--- /dev/null
+++ b/arch/x86/include/asm/shmparam.h
@@ -0,0 +1,6 @@
+#ifndef ASM_X86__SHMPARAM_H
+#define ASM_X86__SHMPARAM_H
+
+#define SHMLBA PAGE_SIZE	 /* attach addr a multiple of this */
+
+#endif /* ASM_X86__SHMPARAM_H */
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
new file mode 100644
index 000000000000..ee813f4fe5d5
--- /dev/null
+++ b/arch/x86/include/asm/sigcontext.h
@@ -0,0 +1,284 @@
+#ifndef ASM_X86__SIGCONTEXT_H
+#define ASM_X86__SIGCONTEXT_H
+
+#include <linux/compiler.h>
+#include <asm/types.h>
+
+#define FP_XSTATE_MAGIC1	0x46505853U
+#define FP_XSTATE_MAGIC2	0x46505845U
+#define FP_XSTATE_MAGIC2_SIZE	sizeof(FP_XSTATE_MAGIC2)
+
+/*
+ * bytes 464..511 in the current 512byte layout of fxsave/fxrstor frame
+ * are reserved for SW usage. On cpu's supporting xsave/xrstor, these bytes
+ * are used to extended the fpstate pointer in the sigcontext, which now
+ * includes the extended state information along with fpstate information.
+ *
+ * Presence of FP_XSTATE_MAGIC1 at the beginning of this SW reserved
+ * area and FP_XSTATE_MAGIC2 at the end of memory layout
+ * (extended_size - FP_XSTATE_MAGIC2_SIZE) indicates the presence of the
+ * extended state information in the memory layout pointed by the fpstate
+ * pointer in sigcontext.
+ */
+struct _fpx_sw_bytes {
+	__u32 magic1;		/* FP_XSTATE_MAGIC1 */
+	__u32 extended_size;	/* total size of the layout referred by
+				 * fpstate pointer in the sigcontext.
+				 */
+	__u64 xstate_bv;
+				/* feature bit mask (including fp/sse/extended
+				 * state) that is present in the memory
+				 * layout.
+				 */
+	__u32 xstate_size;	/* actual xsave state size, based on the
+				 * features saved in the layout.
+				 * 'extended_size' will be greater than
+				 * 'xstate_size'.
+				 */
+	__u32 padding[7];	/*  for future use. */
+};
+
+#ifdef __i386__
+/*
+ * As documented in the iBCS2 standard..
+ *
+ * The first part of "struct _fpstate" is just the normal i387
+ * hardware setup, the extra "status" word is used to save the
+ * coprocessor status word before entering the handler.
+ *
+ * Pentium III FXSR, SSE support
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ *
+ * The FPU state data structure has had to grow to accommodate the
+ * extended FPU state required by the Streaming SIMD Extensions.
+ * There is no documented standard to accomplish this at the moment.
+ */
+struct _fpreg {
+	unsigned short significand[4];
+	unsigned short exponent;
+};
+
+struct _fpxreg {
+	unsigned short significand[4];
+	unsigned short exponent;
+	unsigned short padding[3];
+};
+
+struct _xmmreg {
+	unsigned long element[4];
+};
+
+struct _fpstate {
+	/* Regular FPU environment */
+	unsigned long	cw;
+	unsigned long	sw;
+	unsigned long	tag;
+	unsigned long	ipoff;
+	unsigned long	cssel;
+	unsigned long	dataoff;
+	unsigned long	datasel;
+	struct _fpreg	_st[8];
+	unsigned short	status;
+	unsigned short	magic;		/* 0xffff = regular FPU data only */
+
+	/* FXSR FPU environment */
+	unsigned long	_fxsr_env[6];	/* FXSR FPU env is ignored */
+	unsigned long	mxcsr;
+	unsigned long	reserved;
+	struct _fpxreg	_fxsr_st[8];	/* FXSR FPU reg data is ignored */
+	struct _xmmreg	_xmm[8];
+	unsigned long	padding1[44];
+
+	union {
+		unsigned long	padding2[12];
+		struct _fpx_sw_bytes sw_reserved; /* represents the extended
+						   * state info */
+	};
+};
+
+#define X86_FXSR_MAGIC		0x0000
+
+#ifdef __KERNEL__
+struct sigcontext {
+	unsigned short gs, __gsh;
+	unsigned short fs, __fsh;
+	unsigned short es, __esh;
+	unsigned short ds, __dsh;
+	unsigned long di;
+	unsigned long si;
+	unsigned long bp;
+	unsigned long sp;
+	unsigned long bx;
+	unsigned long dx;
+	unsigned long cx;
+	unsigned long ax;
+	unsigned long trapno;
+	unsigned long err;
+	unsigned long ip;
+	unsigned short cs, __csh;
+	unsigned long flags;
+	unsigned long sp_at_signal;
+	unsigned short ss, __ssh;
+
+	/*
+	 * fpstate is really (struct _fpstate *) or (struct _xstate *)
+	 * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
+	 * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
+	 * of extended memory layout. See comments at the defintion of
+	 * (struct _fpx_sw_bytes)
+	 */
+	void __user *fpstate;		/* zero when no FPU/extended context */
+	unsigned long oldmask;
+	unsigned long cr2;
+};
+#else /* __KERNEL__ */
+/*
+ * User-space might still rely on the old definition:
+ */
+struct sigcontext {
+	unsigned short gs, __gsh;
+	unsigned short fs, __fsh;
+	unsigned short es, __esh;
+	unsigned short ds, __dsh;
+	unsigned long edi;
+	unsigned long esi;
+	unsigned long ebp;
+	unsigned long esp;
+	unsigned long ebx;
+	unsigned long edx;
+	unsigned long ecx;
+	unsigned long eax;
+	unsigned long trapno;
+	unsigned long err;
+	unsigned long eip;
+	unsigned short cs, __csh;
+	unsigned long eflags;
+	unsigned long esp_at_signal;
+	unsigned short ss, __ssh;
+	struct _fpstate __user *fpstate;
+	unsigned long oldmask;
+	unsigned long cr2;
+};
+#endif /* !__KERNEL__ */
+
+#else /* __i386__ */
+
+/* FXSAVE frame */
+/* Note: reserved1/2 may someday contain valuable data. Always save/restore
+   them when you change signal frames. */
+struct _fpstate {
+	__u16	cwd;
+	__u16	swd;
+	__u16	twd;		/* Note this is not the same as the
+				   32bit/x87/FSAVE twd */
+	__u16	fop;
+	__u64	rip;
+	__u64	rdp;
+	__u32	mxcsr;
+	__u32	mxcsr_mask;
+	__u32	st_space[32];	/* 8*16 bytes for each FP-reg */
+	__u32	xmm_space[64];	/* 16*16 bytes for each XMM-reg  */
+	__u32	reserved2[12];
+	union {
+		__u32	reserved3[12];
+		struct _fpx_sw_bytes sw_reserved; /* represents the extended
+						   * state information */
+	};
+};
+
+#ifdef __KERNEL__
+struct sigcontext {
+	unsigned long r8;
+	unsigned long r9;
+	unsigned long r10;
+	unsigned long r11;
+	unsigned long r12;
+	unsigned long r13;
+	unsigned long r14;
+	unsigned long r15;
+	unsigned long di;
+	unsigned long si;
+	unsigned long bp;
+	unsigned long bx;
+	unsigned long dx;
+	unsigned long ax;
+	unsigned long cx;
+	unsigned long sp;
+	unsigned long ip;
+	unsigned long flags;
+	unsigned short cs;
+	unsigned short gs;
+	unsigned short fs;
+	unsigned short __pad0;
+	unsigned long err;
+	unsigned long trapno;
+	unsigned long oldmask;
+	unsigned long cr2;
+
+	/*
+	 * fpstate is really (struct _fpstate *) or (struct _xstate *)
+	 * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
+	 * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
+	 * of extended memory layout. See comments at the defintion of
+	 * (struct _fpx_sw_bytes)
+	 */
+	void __user *fpstate;		/* zero when no FPU/extended context */
+	unsigned long reserved1[8];
+};
+#else /* __KERNEL__ */
+/*
+ * User-space might still rely on the old definition:
+ */
+struct sigcontext {
+	unsigned long r8;
+	unsigned long r9;
+	unsigned long r10;
+	unsigned long r11;
+	unsigned long r12;
+	unsigned long r13;
+	unsigned long r14;
+	unsigned long r15;
+	unsigned long rdi;
+	unsigned long rsi;
+	unsigned long rbp;
+	unsigned long rbx;
+	unsigned long rdx;
+	unsigned long rax;
+	unsigned long rcx;
+	unsigned long rsp;
+	unsigned long rip;
+	unsigned long eflags;		/* RFLAGS */
+	unsigned short cs;
+	unsigned short gs;
+	unsigned short fs;
+	unsigned short __pad0;
+	unsigned long err;
+	unsigned long trapno;
+	unsigned long oldmask;
+	unsigned long cr2;
+	struct _fpstate __user *fpstate;	/* zero when no FPU context */
+	unsigned long reserved1[8];
+};
+#endif /* !__KERNEL__ */
+
+#endif /* !__i386__ */
+
+struct _xsave_hdr {
+	__u64 xstate_bv;
+	__u64 reserved1[2];
+	__u64 reserved2[5];
+};
+
+/*
+ * Extended state pointed by the fpstate pointer in the sigcontext.
+ * In addition to the fpstate, information encoded in the xstate_hdr
+ * indicates the presence of other extended state information
+ * supported by the processor and OS.
+ */
+struct _xstate {
+	struct _fpstate fpstate;
+	struct _xsave_hdr xstate_hdr;
+	/* new processor state extensions go here */
+};
+
+#endif /* ASM_X86__SIGCONTEXT_H */
diff --git a/arch/x86/include/asm/sigcontext32.h b/arch/x86/include/asm/sigcontext32.h
new file mode 100644
index 000000000000..8c347032c2f2
--- /dev/null
+++ b/arch/x86/include/asm/sigcontext32.h
@@ -0,0 +1,75 @@
+#ifndef ASM_X86__SIGCONTEXT32_H
+#define ASM_X86__SIGCONTEXT32_H
+
+/* signal context for 32bit programs. */
+
+#define X86_FXSR_MAGIC		0x0000
+
+struct _fpreg {
+	unsigned short significand[4];
+	unsigned short exponent;
+};
+
+struct _fpxreg {
+	unsigned short significand[4];
+	unsigned short exponent;
+	unsigned short padding[3];
+};
+
+struct _xmmreg {
+	__u32	element[4];
+};
+
+/* FSAVE frame with extensions */
+struct _fpstate_ia32 {
+	/* Regular FPU environment */
+	__u32 	cw;
+	__u32	sw;
+	__u32	tag;	/* not compatible to 64bit twd */
+	__u32	ipoff;
+	__u32	cssel;
+	__u32	dataoff;
+	__u32	datasel;
+	struct _fpreg	_st[8];
+	unsigned short	status;
+	unsigned short	magic;		/* 0xffff = regular FPU data only */
+
+	/* FXSR FPU environment */
+	__u32	_fxsr_env[6];
+	__u32	mxcsr;
+	__u32	reserved;
+	struct _fpxreg	_fxsr_st[8];
+	struct _xmmreg	_xmm[8];	/* It's actually 16 */
+	__u32	padding[44];
+	union {
+		__u32 padding2[12];
+		struct _fpx_sw_bytes sw_reserved;
+	};
+};
+
+struct sigcontext_ia32 {
+       unsigned short gs, __gsh;
+       unsigned short fs, __fsh;
+       unsigned short es, __esh;
+       unsigned short ds, __dsh;
+       unsigned int di;
+       unsigned int si;
+       unsigned int bp;
+       unsigned int sp;
+       unsigned int bx;
+       unsigned int dx;
+       unsigned int cx;
+       unsigned int ax;
+       unsigned int trapno;
+       unsigned int err;
+       unsigned int ip;
+       unsigned short cs, __csh;
+       unsigned int flags;
+       unsigned int sp_at_signal;
+       unsigned short ss, __ssh;
+       unsigned int fpstate;		/* really (struct _fpstate_ia32 *) */
+       unsigned int oldmask;
+       unsigned int cr2;
+};
+
+#endif /* ASM_X86__SIGCONTEXT32_H */
diff --git a/arch/x86/include/asm/siginfo.h b/arch/x86/include/asm/siginfo.h
new file mode 100644
index 000000000000..808bdfb2958c
--- /dev/null
+++ b/arch/x86/include/asm/siginfo.h
@@ -0,0 +1,10 @@
+#ifndef ASM_X86__SIGINFO_H
+#define ASM_X86__SIGINFO_H
+
+#ifdef __x86_64__
+# define __ARCH_SI_PREAMBLE_SIZE	(4 * sizeof(int))
+#endif
+
+#include <asm-generic/siginfo.h>
+
+#endif /* ASM_X86__SIGINFO_H */
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
new file mode 100644
index 000000000000..65acc82d267a
--- /dev/null
+++ b/arch/x86/include/asm/signal.h
@@ -0,0 +1,262 @@
+#ifndef ASM_X86__SIGNAL_H
+#define ASM_X86__SIGNAL_H
+
+#ifndef __ASSEMBLY__
+#include <linux/types.h>
+#include <linux/time.h>
+#include <linux/compiler.h>
+
+/* Avoid too many header ordering problems.  */
+struct siginfo;
+
+#ifdef __KERNEL__
+#include <linux/linkage.h>
+
+/* Most things should be clean enough to redefine this at will, if care
+   is taken to make libc match.  */
+
+#define _NSIG		64
+
+#ifdef __i386__
+# define _NSIG_BPW	32
+#else
+# define _NSIG_BPW	64
+#endif
+
+#define _NSIG_WORDS	(_NSIG / _NSIG_BPW)
+
+typedef unsigned long old_sigset_t;		/* at least 32 bits */
+
+typedef struct {
+	unsigned long sig[_NSIG_WORDS];
+} sigset_t;
+
+#else
+/* Here we must cater to libcs that poke about in kernel headers.  */
+
+#define NSIG		32
+typedef unsigned long sigset_t;
+
+#endif /* __KERNEL__ */
+#endif /* __ASSEMBLY__ */
+
+#define SIGHUP		 1
+#define SIGINT		 2
+#define SIGQUIT		 3
+#define SIGILL		 4
+#define SIGTRAP		 5
+#define SIGABRT		 6
+#define SIGIOT		 6
+#define SIGBUS		 7
+#define SIGFPE		 8
+#define SIGKILL		 9
+#define SIGUSR1		10
+#define SIGSEGV		11
+#define SIGUSR2		12
+#define SIGPIPE		13
+#define SIGALRM		14
+#define SIGTERM		15
+#define SIGSTKFLT	16
+#define SIGCHLD		17
+#define SIGCONT		18
+#define SIGSTOP		19
+#define SIGTSTP		20
+#define SIGTTIN		21
+#define SIGTTOU		22
+#define SIGURG		23
+#define SIGXCPU		24
+#define SIGXFSZ		25
+#define SIGVTALRM	26
+#define SIGPROF		27
+#define SIGWINCH	28
+#define SIGIO		29
+#define SIGPOLL		SIGIO
+/*
+#define SIGLOST		29
+*/
+#define SIGPWR		30
+#define SIGSYS		31
+#define	SIGUNUSED	31
+
+/* These should not be considered constants from userland.  */
+#define SIGRTMIN	32
+#define SIGRTMAX	_NSIG
+
+/*
+ * SA_FLAGS values:
+ *
+ * SA_ONSTACK indicates that a registered stack_t will be used.
+ * SA_RESTART flag to get restarting signals (which were the default long ago)
+ * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
+ * SA_RESETHAND clears the handler when the signal is delivered.
+ * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
+ * SA_NODEFER prevents the current signal from being masked in the handler.
+ *
+ * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
+ * Unix names RESETHAND and NODEFER respectively.
+ */
+#define SA_NOCLDSTOP	0x00000001u
+#define SA_NOCLDWAIT	0x00000002u
+#define SA_SIGINFO	0x00000004u
+#define SA_ONSTACK	0x08000000u
+#define SA_RESTART	0x10000000u
+#define SA_NODEFER	0x40000000u
+#define SA_RESETHAND	0x80000000u
+
+#define SA_NOMASK	SA_NODEFER
+#define SA_ONESHOT	SA_RESETHAND
+
+#define SA_RESTORER	0x04000000
+
+/*
+ * sigaltstack controls
+ */
+#define SS_ONSTACK	1
+#define SS_DISABLE	2
+
+#define MINSIGSTKSZ	2048
+#define SIGSTKSZ	8192
+
+#include <asm-generic/signal.h>
+
+#ifndef __ASSEMBLY__
+
+#ifdef __i386__
+# ifdef __KERNEL__
+struct old_sigaction {
+	__sighandler_t sa_handler;
+	old_sigset_t sa_mask;
+	unsigned long sa_flags;
+	__sigrestore_t sa_restorer;
+};
+
+struct sigaction {
+	__sighandler_t sa_handler;
+	unsigned long sa_flags;
+	__sigrestore_t sa_restorer;
+	sigset_t sa_mask;		/* mask last for extensibility */
+};
+
+struct k_sigaction {
+	struct sigaction sa;
+};
+
+extern void do_notify_resume(struct pt_regs *, void *, __u32);
+
+# else /* __KERNEL__ */
+/* Here we must cater to libcs that poke about in kernel headers.  */
+
+struct sigaction {
+	union {
+	  __sighandler_t _sa_handler;
+	  void (*_sa_sigaction)(int, struct siginfo *, void *);
+	} _u;
+	sigset_t sa_mask;
+	unsigned long sa_flags;
+	void (*sa_restorer)(void);
+};
+
+#define sa_handler	_u._sa_handler
+#define sa_sigaction	_u._sa_sigaction
+
+# endif /* ! __KERNEL__ */
+#else /* __i386__ */
+
+struct sigaction {
+	__sighandler_t sa_handler;
+	unsigned long sa_flags;
+	__sigrestore_t sa_restorer;
+	sigset_t sa_mask;		/* mask last for extensibility */
+};
+
+struct k_sigaction {
+	struct sigaction sa;
+};
+
+#endif /* !__i386__ */
+
+typedef struct sigaltstack {
+	void __user *ss_sp;
+	int ss_flags;
+	size_t ss_size;
+} stack_t;
+
+#ifdef __KERNEL__
+#include <asm/sigcontext.h>
+
+#ifdef __i386__
+
+#define __HAVE_ARCH_SIG_BITOPS
+
+#define sigaddset(set,sig)		    \
+	(__builtin_constant_p(sig)	    \
+	 ? __const_sigaddset((set), (sig))  \
+	 : __gen_sigaddset((set), (sig)))
+
+static inline void __gen_sigaddset(sigset_t *set, int _sig)
+{
+	asm("btsl %1,%0" : "+m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+static inline void __const_sigaddset(sigset_t *set, int _sig)
+{
+	unsigned long sig = _sig - 1;
+	set->sig[sig / _NSIG_BPW] |= 1 << (sig % _NSIG_BPW);
+}
+
+#define sigdelset(set, sig)		    \
+	(__builtin_constant_p(sig)	    \
+	 ? __const_sigdelset((set), (sig))  \
+	 : __gen_sigdelset((set), (sig)))
+
+
+static inline void __gen_sigdelset(sigset_t *set, int _sig)
+{
+	asm("btrl %1,%0" : "+m"(*set) : "Ir"(_sig - 1) : "cc");
+}
+
+static inline void __const_sigdelset(sigset_t *set, int _sig)
+{
+	unsigned long sig = _sig - 1;
+	set->sig[sig / _NSIG_BPW] &= ~(1 << (sig % _NSIG_BPW));
+}
+
+static inline int __const_sigismember(sigset_t *set, int _sig)
+{
+	unsigned long sig = _sig - 1;
+	return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW));
+}
+
+static inline int __gen_sigismember(sigset_t *set, int _sig)
+{
+	int ret;
+	asm("btl %2,%1\n\tsbbl %0,%0"
+	    : "=r"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
+	return ret;
+}
+
+#define sigismember(set, sig)			\
+	(__builtin_constant_p(sig)		\
+	 ? __const_sigismember((set), (sig))	\
+	 : __gen_sigismember((set), (sig)))
+
+static inline int sigfindinword(unsigned long word)
+{
+	asm("bsfl %1,%0" : "=r"(word) : "rm"(word) : "cc");
+	return word;
+}
+
+struct pt_regs;
+
+#else /* __i386__ */
+
+#undef __HAVE_ARCH_SIG_BITOPS
+
+#endif /* !__i386__ */
+
+#define ptrace_signal_deliver(regs, cookie) do { } while (0)
+
+#endif /* __KERNEL__ */
+#endif /* __ASSEMBLY__ */
+
+#endif /* ASM_X86__SIGNAL_H */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
new file mode 100644
index 000000000000..a6afc29f2dd9
--- /dev/null
+++ b/arch/x86/include/asm/smp.h
@@ -0,0 +1,229 @@
+#ifndef ASM_X86__SMP_H
+#define ASM_X86__SMP_H
+#ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
+#include <linux/init.h>
+#include <asm/percpu.h>
+
+/*
+ * We need the APIC definitions automatically as part of 'smp.h'
+ */
+#ifdef CONFIG_X86_LOCAL_APIC
+# include <asm/mpspec.h>
+# include <asm/apic.h>
+# ifdef CONFIG_X86_IO_APIC
+#  include <asm/io_apic.h>
+# endif
+#endif
+#include <asm/pda.h>
+#include <asm/thread_info.h>
+
+extern cpumask_t cpu_callout_map;
+extern cpumask_t cpu_initialized;
+extern cpumask_t cpu_callin_map;
+
+extern void (*mtrr_hook)(void);
+extern void zap_low_mappings(void);
+
+extern int __cpuinit get_local_pda(int cpu);
+
+extern int smp_num_siblings;
+extern unsigned int num_processors;
+extern cpumask_t cpu_initialized;
+
+DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
+DECLARE_PER_CPU(cpumask_t, cpu_core_map);
+DECLARE_PER_CPU(u16, cpu_llc_id);
+#ifdef CONFIG_X86_32
+DECLARE_PER_CPU(int, cpu_number);
+#endif
+
+DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
+DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+
+/* Static state in head.S used to set up a CPU */
+extern struct {
+	void *sp;
+	unsigned short ss;
+} stack_start;
+
+struct smp_ops {
+	void (*smp_prepare_boot_cpu)(void);
+	void (*smp_prepare_cpus)(unsigned max_cpus);
+	void (*smp_cpus_done)(unsigned max_cpus);
+
+	void (*smp_send_stop)(void);
+	void (*smp_send_reschedule)(int cpu);
+
+	int (*cpu_up)(unsigned cpu);
+	int (*cpu_disable)(void);
+	void (*cpu_die)(unsigned int cpu);
+	void (*play_dead)(void);
+
+	void (*send_call_func_ipi)(cpumask_t mask);
+	void (*send_call_func_single_ipi)(int cpu);
+};
+
+/* Globals due to paravirt */
+extern void set_cpu_sibling_map(int cpu);
+
+#ifdef CONFIG_SMP
+#ifndef CONFIG_PARAVIRT
+#define startup_ipi_hook(phys_apicid, start_eip, start_esp) do { } while (0)
+#endif
+extern struct smp_ops smp_ops;
+
+static inline void smp_send_stop(void)
+{
+	smp_ops.smp_send_stop();
+}
+
+static inline void smp_prepare_boot_cpu(void)
+{
+	smp_ops.smp_prepare_boot_cpu();
+}
+
+static inline void smp_prepare_cpus(unsigned int max_cpus)
+{
+	smp_ops.smp_prepare_cpus(max_cpus);
+}
+
+static inline void smp_cpus_done(unsigned int max_cpus)
+{
+	smp_ops.smp_cpus_done(max_cpus);
+}
+
+static inline int __cpu_up(unsigned int cpu)
+{
+	return smp_ops.cpu_up(cpu);
+}
+
+static inline int __cpu_disable(void)
+{
+	return smp_ops.cpu_disable();
+}
+
+static inline void __cpu_die(unsigned int cpu)
+{
+	smp_ops.cpu_die(cpu);
+}
+
+static inline void play_dead(void)
+{
+	smp_ops.play_dead();
+}
+
+static inline void smp_send_reschedule(int cpu)
+{
+	smp_ops.smp_send_reschedule(cpu);
+}
+
+static inline void arch_send_call_function_single_ipi(int cpu)
+{
+	smp_ops.send_call_func_single_ipi(cpu);
+}
+
+static inline void arch_send_call_function_ipi(cpumask_t mask)
+{
+	smp_ops.send_call_func_ipi(mask);
+}
+
+void cpu_disable_common(void);
+void native_smp_prepare_boot_cpu(void);
+void native_smp_prepare_cpus(unsigned int max_cpus);
+void native_smp_cpus_done(unsigned int max_cpus);
+int native_cpu_up(unsigned int cpunum);
+int native_cpu_disable(void);
+void native_cpu_die(unsigned int cpu);
+void native_play_dead(void);
+void play_dead_common(void);
+
+void native_send_call_func_ipi(cpumask_t mask);
+void native_send_call_func_single_ipi(int cpu);
+
+extern void prefill_possible_map(void);
+
+void smp_store_cpu_info(int id);
+#define cpu_physical_id(cpu)	per_cpu(x86_cpu_to_apicid, cpu)
+
+/* We don't mark CPUs online until __cpu_up(), so we need another measure */
+static inline int num_booting_cpus(void)
+{
+	return cpus_weight(cpu_callout_map);
+}
+#else
+static inline void prefill_possible_map(void)
+{
+}
+#endif /* CONFIG_SMP */
+
+extern unsigned disabled_cpus __cpuinitdata;
+
+#ifdef CONFIG_X86_32_SMP
+/*
+ * This function is needed by all SMP systems. It must _always_ be valid
+ * from the initial startup. We map APIC_BASE very early in page_setup(),
+ * so this is correct in the x86 case.
+ */
+#define raw_smp_processor_id() (x86_read_percpu(cpu_number))
+extern int safe_smp_processor_id(void);
+
+#elif defined(CONFIG_X86_64_SMP)
+#define raw_smp_processor_id()	read_pda(cpunumber)
+
+#define stack_smp_processor_id()					\
+({								\
+	struct thread_info *ti;						\
+	__asm__("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK));	\
+	ti->cpu;							\
+})
+#define safe_smp_processor_id()		smp_processor_id()
+
+#else /* !CONFIG_X86_32_SMP && !CONFIG_X86_64_SMP */
+#define cpu_physical_id(cpu)		boot_cpu_physical_apicid
+#define safe_smp_processor_id()		0
+#define stack_smp_processor_id() 	0
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+#ifndef CONFIG_X86_64
+static inline int logical_smp_processor_id(void)
+{
+	/* we don't want to mark this access volatile - bad code generation */
+	return GET_APIC_LOGICAL_ID(*(u32 *)(APIC_BASE + APIC_LDR));
+}
+
+#include <mach_apicdef.h>
+static inline unsigned int read_apic_id(void)
+{
+	unsigned int reg;
+
+	reg = *(u32 *)(APIC_BASE + APIC_ID);
+
+	return GET_APIC_ID(reg);
+}
+#endif
+
+
+# if defined(APIC_DEFINITION) || defined(CONFIG_X86_64)
+extern int hard_smp_processor_id(void);
+# else
+#include <mach_apicdef.h>
+static inline int hard_smp_processor_id(void)
+{
+	/* we don't want to mark this access volatile - bad code generation */
+	return read_apic_id();
+}
+# endif /* APIC_DEFINITION */
+
+#else /* CONFIG_X86_LOCAL_APIC */
+
+# ifndef CONFIG_SMP
+#  define hard_smp_processor_id()	0
+# endif
+
+#endif /* CONFIG_X86_LOCAL_APIC */
+
+#endif /* __ASSEMBLY__ */
+#endif /* ASM_X86__SMP_H */
diff --git a/arch/x86/include/asm/socket.h b/arch/x86/include/asm/socket.h
new file mode 100644
index 000000000000..db73274c83c3
--- /dev/null
+++ b/arch/x86/include/asm/socket.h
@@ -0,0 +1,57 @@
+#ifndef ASM_X86__SOCKET_H
+#define ASM_X86__SOCKET_H
+
+#include <asm/sockios.h>
+
+/* For setsockopt(2) */
+#define SOL_SOCKET	1
+
+#define SO_DEBUG	1
+#define SO_REUSEADDR	2
+#define SO_TYPE		3
+#define SO_ERROR	4
+#define SO_DONTROUTE	5
+#define SO_BROADCAST	6
+#define SO_SNDBUF	7
+#define SO_RCVBUF	8
+#define SO_SNDBUFFORCE	32
+#define SO_RCVBUFFORCE	33
+#define SO_KEEPALIVE	9
+#define SO_OOBINLINE	10
+#define SO_NO_CHECK	11
+#define SO_PRIORITY	12
+#define SO_LINGER	13
+#define SO_BSDCOMPAT	14
+/* To add :#define SO_REUSEPORT 15 */
+#define SO_PASSCRED	16
+#define SO_PEERCRED	17
+#define SO_RCVLOWAT	18
+#define SO_SNDLOWAT	19
+#define SO_RCVTIMEO	20
+#define SO_SNDTIMEO	21
+
+/* Security levels - as per NRL IPv6 - don't actually do anything */
+#define SO_SECURITY_AUTHENTICATION		22
+#define SO_SECURITY_ENCRYPTION_TRANSPORT	23
+#define SO_SECURITY_ENCRYPTION_NETWORK		24
+
+#define SO_BINDTODEVICE	25
+
+/* Socket filtering */
+#define SO_ATTACH_FILTER        26
+#define SO_DETACH_FILTER        27
+
+#define SO_PEERNAME		28
+#define SO_TIMESTAMP		29
+#define SCM_TIMESTAMP		SO_TIMESTAMP
+
+#define SO_ACCEPTCONN		30
+
+#define SO_PEERSEC		31
+#define SO_PASSSEC		34
+#define SO_TIMESTAMPNS		35
+#define SCM_TIMESTAMPNS		SO_TIMESTAMPNS
+
+#define SO_MARK			36
+
+#endif /* ASM_X86__SOCKET_H */
diff --git a/arch/x86/include/asm/sockios.h b/arch/x86/include/asm/sockios.h
new file mode 100644
index 000000000000..a006704fdc84
--- /dev/null
+++ b/arch/x86/include/asm/sockios.h
@@ -0,0 +1,13 @@
+#ifndef ASM_X86__SOCKIOS_H
+#define ASM_X86__SOCKIOS_H
+
+/* Socket-level I/O control calls. */
+#define FIOSETOWN	0x8901
+#define SIOCSPGRP	0x8902
+#define FIOGETOWN	0x8903
+#define SIOCGPGRP	0x8904
+#define SIOCATMARK	0x8905
+#define SIOCGSTAMP	0x8906		/* Get stamp (timeval) */
+#define SIOCGSTAMPNS	0x8907		/* Get stamp (timespec) */
+
+#endif /* ASM_X86__SOCKIOS_H */
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
new file mode 100644
index 000000000000..38f8e6bc3186
--- /dev/null
+++ b/arch/x86/include/asm/sparsemem.h
@@ -0,0 +1,34 @@
+#ifndef ASM_X86__SPARSEMEM_H
+#define ASM_X86__SPARSEMEM_H
+
+#ifdef CONFIG_SPARSEMEM
+/*
+ * generic non-linear memory support:
+ *
+ * 1) we will not split memory into more chunks than will fit into the flags
+ *    field of the struct page
+ *
+ * SECTION_SIZE_BITS		2^n: size of each section
+ * MAX_PHYSADDR_BITS		2^n: max size of physical address space
+ * MAX_PHYSMEM_BITS		2^n: how much memory we can have in that space
+ *
+ */
+
+#ifdef CONFIG_X86_32
+# ifdef CONFIG_X86_PAE
+#  define SECTION_SIZE_BITS	29
+#  define MAX_PHYSADDR_BITS	36
+#  define MAX_PHYSMEM_BITS	36
+# else
+#  define SECTION_SIZE_BITS	26
+#  define MAX_PHYSADDR_BITS	32
+#  define MAX_PHYSMEM_BITS	32
+# endif
+#else /* CONFIG_X86_32 */
+# define SECTION_SIZE_BITS	27 /* matt - 128 is convenient right now */
+# define MAX_PHYSADDR_BITS	44
+# define MAX_PHYSMEM_BITS	44
+#endif
+
+#endif /* CONFIG_SPARSEMEM */
+#endif /* ASM_X86__SPARSEMEM_H */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
new file mode 100644
index 000000000000..157ff7fab97a
--- /dev/null
+++ b/arch/x86/include/asm/spinlock.h
@@ -0,0 +1,364 @@
+#ifndef ASM_X86__SPINLOCK_H
+#define ASM_X86__SPINLOCK_H
+
+#include <asm/atomic.h>
+#include <asm/rwlock.h>
+#include <asm/page.h>
+#include <asm/processor.h>
+#include <linux/compiler.h>
+#include <asm/paravirt.h>
+/*
+ * Your basic SMP spinlocks, allowing only a single CPU anywhere
+ *
+ * Simple spin lock operations.  There are two variants, one clears IRQ's
+ * on the local processor, one does not.
+ *
+ * These are fair FIFO ticket locks, which are currently limited to 256
+ * CPUs.
+ *
+ * (the type definitions are in asm/spinlock_types.h)
+ */
+
+#ifdef CONFIG_X86_32
+# define LOCK_PTR_REG "a"
+# define REG_PTR_MODE "k"
+#else
+# define LOCK_PTR_REG "D"
+# define REG_PTR_MODE "q"
+#endif
+
+#if defined(CONFIG_X86_32) && \
+	(defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
+/*
+ * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
+ * (PPro errata 66, 92)
+ */
+# define UNLOCK_LOCK_PREFIX LOCK_PREFIX
+#else
+# define UNLOCK_LOCK_PREFIX
+#endif
+
+/*
+ * Ticket locks are conceptually two parts, one indicating the current head of
+ * the queue, and the other indicating the current tail. The lock is acquired
+ * by atomically noting the tail and incrementing it by one (thus adding
+ * ourself to the queue and noting our position), then waiting until the head
+ * becomes equal to the the initial value of the tail.
+ *
+ * We use an xadd covering *both* parts of the lock, to increment the tail and
+ * also load the position of the head, which takes care of memory ordering
+ * issues and should be optimal for the uncontended case. Note the tail must be
+ * in the high part, because a wide xadd increment of the low part would carry
+ * up and contaminate the high part.
+ *
+ * With fewer than 2^8 possible CPUs, we can use x86's partial registers to
+ * save some instructions and make the code more elegant. There really isn't
+ * much between them in performance though, especially as locks are out of line.
+ */
+#if (NR_CPUS < 256)
+#define TICKET_SHIFT 8
+
+static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
+{
+	short inc = 0x0100;
+
+	asm volatile (
+		LOCK_PREFIX "xaddw %w0, %1\n"
+		"1:\t"
+		"cmpb %h0, %b0\n\t"
+		"je 2f\n\t"
+		"rep ; nop\n\t"
+		"movb %1, %b0\n\t"
+		/* don't need lfence here, because loads are in-order */
+		"jmp 1b\n"
+		"2:"
+		: "+Q" (inc), "+m" (lock->slock)
+		:
+		: "memory", "cc");
+}
+
+static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
+{
+	int tmp, new;
+
+	asm volatile("movzwl %2, %0\n\t"
+		     "cmpb %h0,%b0\n\t"
+		     "leal 0x100(%" REG_PTR_MODE "0), %1\n\t"
+		     "jne 1f\n\t"
+		     LOCK_PREFIX "cmpxchgw %w1,%2\n\t"
+		     "1:"
+		     "sete %b1\n\t"
+		     "movzbl %b1,%0\n\t"
+		     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
+		     :
+		     : "memory", "cc");
+
+	return tmp;
+}
+
+static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
+{
+	asm volatile(UNLOCK_LOCK_PREFIX "incb %0"
+		     : "+m" (lock->slock)
+		     :
+		     : "memory", "cc");
+}
+#else
+#define TICKET_SHIFT 16
+
+static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
+{
+	int inc = 0x00010000;
+	int tmp;
+
+	asm volatile(LOCK_PREFIX "xaddl %0, %1\n"
+		     "movzwl %w0, %2\n\t"
+		     "shrl $16, %0\n\t"
+		     "1:\t"
+		     "cmpl %0, %2\n\t"
+		     "je 2f\n\t"
+		     "rep ; nop\n\t"
+		     "movzwl %1, %2\n\t"
+		     /* don't need lfence here, because loads are in-order */
+		     "jmp 1b\n"
+		     "2:"
+		     : "+r" (inc), "+m" (lock->slock), "=&r" (tmp)
+		     :
+		     : "memory", "cc");
+}
+
+static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
+{
+	int tmp;
+	int new;
+
+	asm volatile("movl %2,%0\n\t"
+		     "movl %0,%1\n\t"
+		     "roll $16, %0\n\t"
+		     "cmpl %0,%1\n\t"
+		     "leal 0x00010000(%" REG_PTR_MODE "0), %1\n\t"
+		     "jne 1f\n\t"
+		     LOCK_PREFIX "cmpxchgl %1,%2\n\t"
+		     "1:"
+		     "sete %b1\n\t"
+		     "movzbl %b1,%0\n\t"
+		     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
+		     :
+		     : "memory", "cc");
+
+	return tmp;
+}
+
+static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
+{
+	asm volatile(UNLOCK_LOCK_PREFIX "incw %0"
+		     : "+m" (lock->slock)
+		     :
+		     : "memory", "cc");
+}
+#endif
+
+static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
+{
+	int tmp = ACCESS_ONCE(lock->slock);
+
+	return !!(((tmp >> TICKET_SHIFT) ^ tmp) & ((1 << TICKET_SHIFT) - 1));
+}
+
+static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
+{
+	int tmp = ACCESS_ONCE(lock->slock);
+
+	return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1;
+}
+
+#ifdef CONFIG_PARAVIRT
+/*
+ * Define virtualization-friendly old-style lock byte lock, for use in
+ * pv_lock_ops if desired.
+ *
+ * This differs from the pre-2.6.24 spinlock by always using xchgb
+ * rather than decb to take the lock; this allows it to use a
+ * zero-initialized lock structure.  It also maintains a 1-byte
+ * contention counter, so that we can implement
+ * __byte_spin_is_contended.
+ */
+struct __byte_spinlock {
+	s8 lock;
+	s8 spinners;
+};
+
+static inline int __byte_spin_is_locked(raw_spinlock_t *lock)
+{
+	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+	return bl->lock != 0;
+}
+
+static inline int __byte_spin_is_contended(raw_spinlock_t *lock)
+{
+	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+	return bl->spinners != 0;
+}
+
+static inline void __byte_spin_lock(raw_spinlock_t *lock)
+{
+	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+	s8 val = 1;
+
+	asm("1: xchgb %1, %0\n"
+	    "   test %1,%1\n"
+	    "   jz 3f\n"
+	    "   " LOCK_PREFIX "incb %2\n"
+	    "2: rep;nop\n"
+	    "   cmpb $1, %0\n"
+	    "   je 2b\n"
+	    "   " LOCK_PREFIX "decb %2\n"
+	    "   jmp 1b\n"
+	    "3:"
+	    : "+m" (bl->lock), "+q" (val), "+m" (bl->spinners): : "memory");
+}
+
+static inline int __byte_spin_trylock(raw_spinlock_t *lock)
+{
+	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+	u8 old = 1;
+
+	asm("xchgb %1,%0"
+	    : "+m" (bl->lock), "+q" (old) : : "memory");
+
+	return old == 0;
+}
+
+static inline void __byte_spin_unlock(raw_spinlock_t *lock)
+{
+	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
+	smp_wmb();
+	bl->lock = 0;
+}
+#else  /* !CONFIG_PARAVIRT */
+static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
+{
+	return __ticket_spin_is_locked(lock);
+}
+
+static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
+{
+	return __ticket_spin_is_contended(lock);
+}
+
+static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
+{
+	__ticket_spin_lock(lock);
+}
+
+static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
+{
+	return __ticket_spin_trylock(lock);
+}
+
+static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
+{
+	__ticket_spin_unlock(lock);
+}
+
+static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
+						  unsigned long flags)
+{
+	__raw_spin_lock(lock);
+}
+
+#endif	/* CONFIG_PARAVIRT */
+
+static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
+{
+	while (__raw_spin_is_locked(lock))
+		cpu_relax();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers
+ * but only one writer.
+ *
+ * NOTE! it is quite common to have readers in interrupts
+ * but no interrupt writers. For those circumstances we
+ * can "mix" irq-safe locks - any writer needs to get a
+ * irq-safe write-lock, but readers can get non-irqsafe
+ * read-locks.
+ *
+ * On x86, we implement read-write locks as a 32-bit counter
+ * with the high bit (sign) being the "contended" bit.
+ */
+
+/**
+ * read_can_lock - would read_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+static inline int __raw_read_can_lock(raw_rwlock_t *lock)
+{
+	return (int)(lock)->lock > 0;
+}
+
+/**
+ * write_can_lock - would write_trylock() succeed?
+ * @lock: the rwlock in question.
+ */
+static inline int __raw_write_can_lock(raw_rwlock_t *lock)
+{
+	return (lock)->lock == RW_LOCK_BIAS;
+}
+
+static inline void __raw_read_lock(raw_rwlock_t *rw)
+{
+	asm volatile(LOCK_PREFIX " subl $1,(%0)\n\t"
+		     "jns 1f\n"
+		     "call __read_lock_failed\n\t"
+		     "1:\n"
+		     ::LOCK_PTR_REG (rw) : "memory");
+}
+
+static inline void __raw_write_lock(raw_rwlock_t *rw)
+{
+	asm volatile(LOCK_PREFIX " subl %1,(%0)\n\t"
+		     "jz 1f\n"
+		     "call __write_lock_failed\n\t"
+		     "1:\n"
+		     ::LOCK_PTR_REG (rw), "i" (RW_LOCK_BIAS) : "memory");
+}
+
+static inline int __raw_read_trylock(raw_rwlock_t *lock)
+{
+	atomic_t *count = (atomic_t *)lock;
+
+	atomic_dec(count);
+	if (atomic_read(count) >= 0)
+		return 1;
+	atomic_inc(count);
+	return 0;
+}
+
+static inline int __raw_write_trylock(raw_rwlock_t *lock)
+{
+	atomic_t *count = (atomic_t *)lock;
+
+	if (atomic_sub_and_test(RW_LOCK_BIAS, count))
+		return 1;
+	atomic_add(RW_LOCK_BIAS, count);
+	return 0;
+}
+
+static inline void __raw_read_unlock(raw_rwlock_t *rw)
+{
+	asm volatile(LOCK_PREFIX "incl %0" :"+m" (rw->lock) : : "memory");
+}
+
+static inline void __raw_write_unlock(raw_rwlock_t *rw)
+{
+	asm volatile(LOCK_PREFIX "addl %1, %0"
+		     : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory");
+}
+
+#define _raw_spin_relax(lock)	cpu_relax()
+#define _raw_read_relax(lock)	cpu_relax()
+#define _raw_write_relax(lock)	cpu_relax()
+
+#endif /* ASM_X86__SPINLOCK_H */
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
new file mode 100644
index 000000000000..6aa9b562c508
--- /dev/null
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -0,0 +1,20 @@
+#ifndef ASM_X86__SPINLOCK_TYPES_H
+#define ASM_X86__SPINLOCK_TYPES_H
+
+#ifndef __LINUX_SPINLOCK_TYPES_H
+# error "please don't include this file directly"
+#endif
+
+typedef struct raw_spinlock {
+	unsigned int slock;
+} raw_spinlock_t;
+
+#define __RAW_SPIN_LOCK_UNLOCKED	{ 0 }
+
+typedef struct {
+	unsigned int lock;
+} raw_rwlock_t;
+
+#define __RAW_RW_LOCK_UNLOCKED		{ RW_LOCK_BIAS }
+
+#endif /* ASM_X86__SPINLOCK_TYPES_H */
diff --git a/arch/x86/include/asm/srat.h b/arch/x86/include/asm/srat.h
new file mode 100644
index 000000000000..5363e4f7e1cd
--- /dev/null
+++ b/arch/x86/include/asm/srat.h
@@ -0,0 +1,39 @@
+/*
+ * Some of the code in this file has been gleaned from the 64 bit
+ * discontigmem support code base.
+ *
+ * Copyright (C) 2002, IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to Pat Gaughen <gone@us.ibm.com>
+ */
+
+#ifndef ASM_X86__SRAT_H
+#define ASM_X86__SRAT_H
+
+#ifdef CONFIG_ACPI_NUMA
+extern int get_memcfg_from_srat(void);
+#else
+static inline int get_memcfg_from_srat(void)
+{
+	return 0;
+}
+#endif
+
+#endif /* ASM_X86__SRAT_H */
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
new file mode 100644
index 000000000000..f43517e28532
--- /dev/null
+++ b/arch/x86/include/asm/stacktrace.h
@@ -0,0 +1,21 @@
+#ifndef ASM_X86__STACKTRACE_H
+#define ASM_X86__STACKTRACE_H
+
+extern int kstack_depth_to_print;
+
+/* Generic stack tracer with callbacks */
+
+struct stacktrace_ops {
+	void (*warning)(void *data, char *msg);
+	/* msg must contain %s for the symbol */
+	void (*warning_symbol)(void *data, char *msg, unsigned long symbol);
+	void (*address)(void *data, unsigned long address, int reliable);
+	/* On negative return stop dumping */
+	int (*stack)(void *data, char *name);
+};
+
+void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
+		unsigned long *stack, unsigned long bp,
+		const struct stacktrace_ops *ops, void *data);
+
+#endif /* ASM_X86__STACKTRACE_H */
diff --git a/arch/x86/include/asm/stat.h b/arch/x86/include/asm/stat.h
new file mode 100644
index 000000000000..1e120f628905
--- /dev/null
+++ b/arch/x86/include/asm/stat.h
@@ -0,0 +1,114 @@
+#ifndef ASM_X86__STAT_H
+#define ASM_X86__STAT_H
+
+#define STAT_HAVE_NSEC 1
+
+#ifdef __i386__
+struct stat {
+	unsigned long  st_dev;
+	unsigned long  st_ino;
+	unsigned short st_mode;
+	unsigned short st_nlink;
+	unsigned short st_uid;
+	unsigned short st_gid;
+	unsigned long  st_rdev;
+	unsigned long  st_size;
+	unsigned long  st_blksize;
+	unsigned long  st_blocks;
+	unsigned long  st_atime;
+	unsigned long  st_atime_nsec;
+	unsigned long  st_mtime;
+	unsigned long  st_mtime_nsec;
+	unsigned long  st_ctime;
+	unsigned long  st_ctime_nsec;
+	unsigned long  __unused4;
+	unsigned long  __unused5;
+};
+
+#define STAT64_HAS_BROKEN_ST_INO	1
+
+/* This matches struct stat64 in glibc2.1, hence the absolutely
+ * insane amounts of padding around dev_t's.
+ */
+struct stat64 {
+	unsigned long long	st_dev;
+	unsigned char	__pad0[4];
+
+	unsigned long	__st_ino;
+
+	unsigned int	st_mode;
+	unsigned int	st_nlink;
+
+	unsigned long	st_uid;
+	unsigned long	st_gid;
+
+	unsigned long long	st_rdev;
+	unsigned char	__pad3[4];
+
+	long long	st_size;
+	unsigned long	st_blksize;
+
+	/* Number 512-byte blocks allocated. */
+	unsigned long long	st_blocks;
+
+	unsigned long	st_atime;
+	unsigned long	st_atime_nsec;
+
+	unsigned long	st_mtime;
+	unsigned int	st_mtime_nsec;
+
+	unsigned long	st_ctime;
+	unsigned long	st_ctime_nsec;
+
+	unsigned long long	st_ino;
+};
+
+#else /* __i386__ */
+
+struct stat {
+	unsigned long	st_dev;
+	unsigned long	st_ino;
+	unsigned long	st_nlink;
+
+	unsigned int	st_mode;
+	unsigned int	st_uid;
+	unsigned int	st_gid;
+	unsigned int	__pad0;
+	unsigned long	st_rdev;
+	long		st_size;
+	long		st_blksize;
+	long		st_blocks;	/* Number 512-byte blocks allocated. */
+
+	unsigned long	st_atime;
+	unsigned long	st_atime_nsec;
+	unsigned long	st_mtime;
+	unsigned long	st_mtime_nsec;
+	unsigned long	st_ctime;
+	unsigned long   st_ctime_nsec;
+	long		__unused[3];
+};
+#endif
+
+/* for 32bit emulation and 32 bit kernels */
+struct __old_kernel_stat {
+	unsigned short st_dev;
+	unsigned short st_ino;
+	unsigned short st_mode;
+	unsigned short st_nlink;
+	unsigned short st_uid;
+	unsigned short st_gid;
+	unsigned short st_rdev;
+#ifdef __i386__
+	unsigned long  st_size;
+	unsigned long  st_atime;
+	unsigned long  st_mtime;
+	unsigned long  st_ctime;
+#else
+	unsigned int  st_size;
+	unsigned int  st_atime;
+	unsigned int  st_mtime;
+	unsigned int  st_ctime;
+#endif
+};
+
+#endif /* ASM_X86__STAT_H */
diff --git a/arch/x86/include/asm/statfs.h b/arch/x86/include/asm/statfs.h
new file mode 100644
index 000000000000..ca5dc19dd461
--- /dev/null
+++ b/arch/x86/include/asm/statfs.h
@@ -0,0 +1,12 @@
+#ifndef ASM_X86__STATFS_H
+#define ASM_X86__STATFS_H
+
+/*
+ * We need compat_statfs64 to be packed, because the i386 ABI won't
+ * add padding at the end to bring it to a multiple of 8 bytes, but
+ * the x86_64 ABI will.
+ */
+#define ARCH_PACK_COMPAT_STATFS64 __attribute__((packed,aligned(4)))
+
+#include <asm-generic/statfs.h>
+#endif /* ASM_X86__STATFS_H */
diff --git a/arch/x86/include/asm/string.h b/arch/x86/include/asm/string.h
new file mode 100644
index 000000000000..6dfd6d9373a0
--- /dev/null
+++ b/arch/x86/include/asm/string.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "string_32.h"
+#else
+# include "string_64.h"
+#endif
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
new file mode 100644
index 000000000000..487843ed245a
--- /dev/null
+++ b/arch/x86/include/asm/string_32.h
@@ -0,0 +1,326 @@
+#ifndef ASM_X86__STRING_32_H
+#define ASM_X86__STRING_32_H
+
+#ifdef __KERNEL__
+
+/* Let gcc decide whether to inline or use the out of line functions */
+
+#define __HAVE_ARCH_STRCPY
+extern char *strcpy(char *dest, const char *src);
+
+#define __HAVE_ARCH_STRNCPY
+extern char *strncpy(char *dest, const char *src, size_t count);
+
+#define __HAVE_ARCH_STRCAT
+extern char *strcat(char *dest, const char *src);
+
+#define __HAVE_ARCH_STRNCAT
+extern char *strncat(char *dest, const char *src, size_t count);
+
+#define __HAVE_ARCH_STRCMP
+extern int strcmp(const char *cs, const char *ct);
+
+#define __HAVE_ARCH_STRNCMP
+extern int strncmp(const char *cs, const char *ct, size_t count);
+
+#define __HAVE_ARCH_STRCHR
+extern char *strchr(const char *s, int c);
+
+#define __HAVE_ARCH_STRLEN
+extern size_t strlen(const char *s);
+
+static __always_inline void *__memcpy(void *to, const void *from, size_t n)
+{
+	int d0, d1, d2;
+	asm volatile("rep ; movsl\n\t"
+		     "movl %4,%%ecx\n\t"
+		     "andl $3,%%ecx\n\t"
+		     "jz 1f\n\t"
+		     "rep ; movsb\n\t"
+		     "1:"
+		     : "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		     : "0" (n / 4), "g" (n), "1" ((long)to), "2" ((long)from)
+		     : "memory");
+	return to;
+}
+
+/*
+ * This looks ugly, but the compiler can optimize it totally,
+ * as the count is constant.
+ */
+static __always_inline void *__constant_memcpy(void *to, const void *from,
+					       size_t n)
+{
+	long esi, edi;
+	if (!n)
+		return to;
+
+	switch (n) {
+	case 1:
+		*(char *)to = *(char *)from;
+		return to;
+	case 2:
+		*(short *)to = *(short *)from;
+		return to;
+	case 4:
+		*(int *)to = *(int *)from;
+		return to;
+
+	case 3:
+		*(short *)to = *(short *)from;
+		*((char *)to + 2) = *((char *)from + 2);
+		return to;
+	case 5:
+		*(int *)to = *(int *)from;
+		*((char *)to + 4) = *((char *)from + 4);
+		return to;
+	case 6:
+		*(int *)to = *(int *)from;
+		*((short *)to + 2) = *((short *)from + 2);
+		return to;
+	case 8:
+		*(int *)to = *(int *)from;
+		*((int *)to + 1) = *((int *)from + 1);
+		return to;
+	}
+
+	esi = (long)from;
+	edi = (long)to;
+	if (n >= 5 * 4) {
+		/* large block: use rep prefix */
+		int ecx;
+		asm volatile("rep ; movsl"
+			     : "=&c" (ecx), "=&D" (edi), "=&S" (esi)
+			     : "0" (n / 4), "1" (edi), "2" (esi)
+			     : "memory"
+		);
+	} else {
+		/* small block: don't clobber ecx + smaller code */
+		if (n >= 4 * 4)
+			asm volatile("movsl"
+				     : "=&D"(edi), "=&S"(esi)
+				     : "0"(edi), "1"(esi)
+				     : "memory");
+		if (n >= 3 * 4)
+			asm volatile("movsl"
+				     : "=&D"(edi), "=&S"(esi)
+				     : "0"(edi), "1"(esi)
+				     : "memory");
+		if (n >= 2 * 4)
+			asm volatile("movsl"
+				     : "=&D"(edi), "=&S"(esi)
+				     : "0"(edi), "1"(esi)
+				     : "memory");
+		if (n >= 1 * 4)
+			asm volatile("movsl"
+				     : "=&D"(edi), "=&S"(esi)
+				     : "0"(edi), "1"(esi)
+				     : "memory");
+	}
+	switch (n % 4) {
+		/* tail */
+	case 0:
+		return to;
+	case 1:
+		asm volatile("movsb"
+			     : "=&D"(edi), "=&S"(esi)
+			     : "0"(edi), "1"(esi)
+			     : "memory");
+		return to;
+	case 2:
+		asm volatile("movsw"
+			     : "=&D"(edi), "=&S"(esi)
+			     : "0"(edi), "1"(esi)
+			     : "memory");
+		return to;
+	default:
+		asm volatile("movsw\n\tmovsb"
+			     : "=&D"(edi), "=&S"(esi)
+			     : "0"(edi), "1"(esi)
+			     : "memory");
+		return to;
+	}
+}
+
+#define __HAVE_ARCH_MEMCPY
+
+#ifdef CONFIG_X86_USE_3DNOW
+
+#include <asm/mmx.h>
+
+/*
+ *	This CPU favours 3DNow strongly (eg AMD Athlon)
+ */
+
+static inline void *__constant_memcpy3d(void *to, const void *from, size_t len)
+{
+	if (len < 512)
+		return __constant_memcpy(to, from, len);
+	return _mmx_memcpy(to, from, len);
+}
+
+static inline void *__memcpy3d(void *to, const void *from, size_t len)
+{
+	if (len < 512)
+		return __memcpy(to, from, len);
+	return _mmx_memcpy(to, from, len);
+}
+
+#define memcpy(t, f, n)				\
+	(__builtin_constant_p((n))		\
+	 ? __constant_memcpy3d((t), (f), (n))	\
+	 : __memcpy3d((t), (f), (n)))
+
+#else
+
+/*
+ *	No 3D Now!
+ */
+
+#define memcpy(t, f, n)				\
+	(__builtin_constant_p((n))		\
+	 ? __constant_memcpy((t), (f), (n))	\
+	 : __memcpy((t), (f), (n)))
+
+#endif
+
+#define __HAVE_ARCH_MEMMOVE
+void *memmove(void *dest, const void *src, size_t n);
+
+#define memcmp __builtin_memcmp
+
+#define __HAVE_ARCH_MEMCHR
+extern void *memchr(const void *cs, int c, size_t count);
+
+static inline void *__memset_generic(void *s, char c, size_t count)
+{
+	int d0, d1;
+	asm volatile("rep\n\t"
+		     "stosb"
+		     : "=&c" (d0), "=&D" (d1)
+		     : "a" (c), "1" (s), "0" (count)
+		     : "memory");
+	return s;
+}
+
+/* we might want to write optimized versions of these later */
+#define __constant_count_memset(s, c, count) __memset_generic((s), (c), (count))
+
+/*
+ * memset(x, 0, y) is a reasonably common thing to do, so we want to fill
+ * things 32 bits at a time even when we don't know the size of the
+ * area at compile-time..
+ */
+static __always_inline
+void *__constant_c_memset(void *s, unsigned long c, size_t count)
+{
+	int d0, d1;
+	asm volatile("rep ; stosl\n\t"
+		     "testb $2,%b3\n\t"
+		     "je 1f\n\t"
+		     "stosw\n"
+		     "1:\ttestb $1,%b3\n\t"
+		     "je 2f\n\t"
+		     "stosb\n"
+		     "2:"
+		     : "=&c" (d0), "=&D" (d1)
+		     : "a" (c), "q" (count), "0" (count/4), "1" ((long)s)
+		     : "memory");
+	return s;
+}
+
+/* Added by Gertjan van Wingerde to make minix and sysv module work */
+#define __HAVE_ARCH_STRNLEN
+extern size_t strnlen(const char *s, size_t count);
+/* end of additional stuff */
+
+#define __HAVE_ARCH_STRSTR
+extern char *strstr(const char *cs, const char *ct);
+
+/*
+ * This looks horribly ugly, but the compiler can optimize it totally,
+ * as we by now know that both pattern and count is constant..
+ */
+static __always_inline
+void *__constant_c_and_count_memset(void *s, unsigned long pattern,
+				    size_t count)
+{
+	switch (count) {
+	case 0:
+		return s;
+	case 1:
+		*(unsigned char *)s = pattern & 0xff;
+		return s;
+	case 2:
+		*(unsigned short *)s = pattern & 0xffff;
+		return s;
+	case 3:
+		*(unsigned short *)s = pattern & 0xffff;
+		*((unsigned char *)s + 2) = pattern & 0xff;
+		return s;
+	case 4:
+		*(unsigned long *)s = pattern;
+		return s;
+	}
+
+#define COMMON(x)							\
+	asm volatile("rep ; stosl"					\
+		     x							\
+		     : "=&c" (d0), "=&D" (d1)				\
+		     : "a" (eax), "0" (count/4), "1" ((long)s)	\
+		     : "memory")
+
+	{
+		int d0, d1;
+#if __GNUC__ == 4 && __GNUC_MINOR__ == 0
+		/* Workaround for broken gcc 4.0 */
+		register unsigned long eax asm("%eax") = pattern;
+#else
+		unsigned long eax = pattern;
+#endif
+
+		switch (count % 4) {
+		case 0:
+			COMMON("");
+			return s;
+		case 1:
+			COMMON("\n\tstosb");
+			return s;
+		case 2:
+			COMMON("\n\tstosw");
+			return s;
+		default:
+			COMMON("\n\tstosw\n\tstosb");
+			return s;
+		}
+	}
+
+#undef COMMON
+}
+
+#define __constant_c_x_memset(s, c, count)			\
+	(__builtin_constant_p(count)				\
+	 ? __constant_c_and_count_memset((s), (c), (count))	\
+	 : __constant_c_memset((s), (c), (count)))
+
+#define __memset(s, c, count)				\
+	(__builtin_constant_p(count)			\
+	 ? __constant_count_memset((s), (c), (count))	\
+	 : __memset_generic((s), (c), (count)))
+
+#define __HAVE_ARCH_MEMSET
+#define memset(s, c, count)						\
+	(__builtin_constant_p(c)					\
+	 ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \
+				 (count))				\
+	 : __memset((s), (c), (count)))
+
+/*
+ * find the first occurrence of byte 'c', or 1 past the area if none
+ */
+#define __HAVE_ARCH_MEMSCAN
+extern void *memscan(void *addr, int c, size_t size);
+
+#endif /* __KERNEL__ */
+
+#endif /* ASM_X86__STRING_32_H */
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
new file mode 100644
index 000000000000..a2add11d3b66
--- /dev/null
+++ b/arch/x86/include/asm/string_64.h
@@ -0,0 +1,60 @@
+#ifndef ASM_X86__STRING_64_H
+#define ASM_X86__STRING_64_H
+
+#ifdef __KERNEL__
+
+/* Written 2002 by Andi Kleen */
+
+/* Only used for special circumstances. Stolen from i386/string.h */
+static __always_inline void *__inline_memcpy(void *to, const void *from, size_t n)
+{
+	unsigned long d0, d1, d2;
+	asm volatile("rep ; movsl\n\t"
+		     "testb $2,%b4\n\t"
+		     "je 1f\n\t"
+		     "movsw\n"
+		     "1:\ttestb $1,%b4\n\t"
+		     "je 2f\n\t"
+		     "movsb\n"
+		     "2:"
+		     : "=&c" (d0), "=&D" (d1), "=&S" (d2)
+		     : "0" (n / 4), "q" (n), "1" ((long)to), "2" ((long)from)
+		     : "memory");
+	return to;
+}
+
+/* Even with __builtin_ the compiler may decide to use the out of line
+   function. */
+
+#define __HAVE_ARCH_MEMCPY 1
+#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4
+extern void *memcpy(void *to, const void *from, size_t len);
+#else
+extern void *__memcpy(void *to, const void *from, size_t len);
+#define memcpy(dst, src, len)					\
+({								\
+	size_t __len = (len);					\
+	void *__ret;						\
+	if (__builtin_constant_p(len) && __len >= 64)		\
+		__ret = __memcpy((dst), (src), __len);		\
+	else							\
+		__ret = __builtin_memcpy((dst), (src), __len);	\
+	__ret;							\
+})
+#endif
+
+#define __HAVE_ARCH_MEMSET
+void *memset(void *s, int c, size_t n);
+
+#define __HAVE_ARCH_MEMMOVE
+void *memmove(void *dest, const void *src, size_t count);
+
+int memcmp(const void *cs, const void *ct, size_t count);
+size_t strlen(const char *s);
+char *strcpy(char *dest, const char *src);
+char *strcat(char *dest, const char *src);
+int strcmp(const char *cs, const char *ct);
+
+#endif /* __KERNEL__ */
+
+#endif /* ASM_X86__STRING_64_H */
diff --git a/arch/x86/include/asm/summit/apic.h b/arch/x86/include/asm/summit/apic.h
new file mode 100644
index 000000000000..9b3070f1c2ac
--- /dev/null
+++ b/arch/x86/include/asm/summit/apic.h
@@ -0,0 +1,184 @@
+#ifndef __ASM_SUMMIT_APIC_H
+#define __ASM_SUMMIT_APIC_H
+
+#include <asm/smp.h>
+
+#define esr_disable (1)
+#define NO_BALANCE_IRQ (0)
+
+/* In clustered mode, the high nibble of APIC ID is a cluster number.
+ * The low nibble is a 4-bit bitmap. */
+#define XAPIC_DEST_CPUS_SHIFT	4
+#define XAPIC_DEST_CPUS_MASK	((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
+#define XAPIC_DEST_CLUSTER_MASK	(XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
+
+#define APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
+
+static inline cpumask_t target_cpus(void)
+{
+	/* CPU_MASK_ALL (0xff) has undefined behaviour with
+	 * dest_LowestPrio mode logical clustered apic interrupt routing
+	 * Just start on cpu 0.  IRQ balancing will spread load
+	 */
+	return cpumask_of_cpu(0);
+}
+
+#define INT_DELIVERY_MODE (dest_LowestPrio)
+#define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
+
+static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
+{
+	return 0;
+}
+
+/* we don't use the phys_cpu_present_map to indicate apicid presence */
+static inline unsigned long check_apicid_present(int bit)
+{
+	return 1;
+}
+
+#define apicid_cluster(apicid) ((apicid) & XAPIC_DEST_CLUSTER_MASK)
+
+extern u8 cpu_2_logical_apicid[];
+
+static inline void init_apic_ldr(void)
+{
+	unsigned long val, id;
+	int count = 0;
+	u8 my_id = (u8)hard_smp_processor_id();
+	u8 my_cluster = (u8)apicid_cluster(my_id);
+#ifdef CONFIG_SMP
+	u8 lid;
+	int i;
+
+	/* Create logical APIC IDs by counting CPUs already in cluster. */
+	for (count = 0, i = NR_CPUS; --i >= 0; ) {
+		lid = cpu_2_logical_apicid[i];
+		if (lid != BAD_APICID && apicid_cluster(lid) == my_cluster)
+			++count;
+	}
+#endif
+	/* We only have a 4 wide bitmap in cluster mode.  If a deranged
+	 * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
+	BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
+	id = my_cluster | (1UL << count);
+	apic_write(APIC_DFR, APIC_DFR_VALUE);
+	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
+	val |= SET_APIC_LOGICAL_ID(id);
+	apic_write(APIC_LDR, val);
+}
+
+static inline int multi_timer_check(int apic, int irq)
+{
+	return 0;
+}
+
+static inline int apic_id_registered(void)
+{
+	return 1;
+}
+
+static inline void setup_apic_routing(void)
+{
+	printk("Enabling APIC mode:  Summit.  Using %d I/O APICs\n",
+						nr_ioapics);
+}
+
+static inline int apicid_to_node(int logical_apicid)
+{
+#ifdef CONFIG_SMP
+	return apicid_2_node[hard_smp_processor_id()];
+#else
+	return 0;
+#endif
+}
+
+/* Mapping from cpu number to logical apicid */
+static inline int cpu_to_logical_apicid(int cpu)
+{
+#ifdef CONFIG_SMP
+       if (cpu >= NR_CPUS)
+	       return BAD_APICID;
+	return (int)cpu_2_logical_apicid[cpu];
+#else
+	return logical_smp_processor_id();
+#endif
+}
+
+static inline int cpu_present_to_apicid(int mps_cpu)
+{
+	if (mps_cpu < NR_CPUS)
+		return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
+	else
+		return BAD_APICID;
+}
+
+static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_id_map)
+{
+	/* For clustered we don't have a good way to do this yet - hack */
+	return physids_promote(0x0F);
+}
+
+static inline physid_mask_t apicid_to_cpu_present(int apicid)
+{
+	return physid_mask_of_physid(0);
+}
+
+static inline void setup_portio_remap(void)
+{
+}
+
+static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
+{
+	return 1;
+}
+
+static inline void enable_apic_mode(void)
+{
+}
+
+static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
+{
+	int num_bits_set;
+	int cpus_found = 0;
+	int cpu;
+	int apicid;
+
+	num_bits_set = cpus_weight(cpumask);
+	/* Return id to all */
+	if (num_bits_set == NR_CPUS)
+		return (int) 0xFF;
+	/*
+	 * The cpus in the mask must all be on the apic cluster.  If are not
+	 * on the same apicid cluster return default value of TARGET_CPUS.
+	 */
+	cpu = first_cpu(cpumask);
+	apicid = cpu_to_logical_apicid(cpu);
+	while (cpus_found < num_bits_set) {
+		if (cpu_isset(cpu, cpumask)) {
+			int new_apicid = cpu_to_logical_apicid(cpu);
+			if (apicid_cluster(apicid) !=
+					apicid_cluster(new_apicid)){
+				printk ("%s: Not a valid mask!\n", __func__);
+				return 0xFF;
+			}
+			apicid = apicid | new_apicid;
+			cpus_found++;
+		}
+		cpu++;
+	}
+	return apicid;
+}
+
+/* cpuid returns the value latched in the HW at reset, not the APIC ID
+ * register's value.  For any box whose BIOS changes APIC IDs, like
+ * clustered APIC systems, we must use hard_smp_processor_id.
+ *
+ * See Intel's IA-32 SW Dev's Manual Vol2 under CPUID.
+ */
+static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
+{
+	return hard_smp_processor_id() >> index_msb;
+}
+
+#endif /* __ASM_SUMMIT_APIC_H */
diff --git a/arch/x86/include/asm/summit/apicdef.h b/arch/x86/include/asm/summit/apicdef.h
new file mode 100644
index 000000000000..f3fbca1f61c1
--- /dev/null
+++ b/arch/x86/include/asm/summit/apicdef.h
@@ -0,0 +1,13 @@
+#ifndef __ASM_SUMMIT_APICDEF_H
+#define __ASM_SUMMIT_APICDEF_H
+
+#define		APIC_ID_MASK		(0xFF<<24)
+
+static inline unsigned get_apic_id(unsigned long x)
+{
+	return (x>>24)&0xFF;
+}
+
+#define		GET_APIC_ID(x)	get_apic_id(x)
+
+#endif
diff --git a/arch/x86/include/asm/summit/ipi.h b/arch/x86/include/asm/summit/ipi.h
new file mode 100644
index 000000000000..53bd1e7bd7b4
--- /dev/null
+++ b/arch/x86/include/asm/summit/ipi.h
@@ -0,0 +1,25 @@
+#ifndef __ASM_SUMMIT_IPI_H
+#define __ASM_SUMMIT_IPI_H
+
+void send_IPI_mask_sequence(cpumask_t mask, int vector);
+
+static inline void send_IPI_mask(cpumask_t mask, int vector)
+{
+	send_IPI_mask_sequence(mask, vector);
+}
+
+static inline void send_IPI_allbutself(int vector)
+{
+	cpumask_t mask = cpu_online_map;
+	cpu_clear(smp_processor_id(), mask);
+
+	if (!cpus_empty(mask))
+		send_IPI_mask(mask, vector);
+}
+
+static inline void send_IPI_all(int vector)
+{
+	send_IPI_mask(cpu_online_map, vector);
+}
+
+#endif /* __ASM_SUMMIT_IPI_H */
diff --git a/arch/x86/include/asm/summit/mpparse.h b/arch/x86/include/asm/summit/mpparse.h
new file mode 100644
index 000000000000..013ce6fab2d5
--- /dev/null
+++ b/arch/x86/include/asm/summit/mpparse.h
@@ -0,0 +1,109 @@
+#ifndef __ASM_SUMMIT_MPPARSE_H
+#define __ASM_SUMMIT_MPPARSE_H
+
+#include <asm/tsc.h>
+
+extern int use_cyclone;
+
+#ifdef CONFIG_X86_SUMMIT_NUMA
+extern void setup_summit(void);
+#else
+#define setup_summit()	{}
+#endif
+
+static inline int mps_oem_check(struct mp_config_table *mpc, char *oem,
+		char *productid)
+{
+	if (!strncmp(oem, "IBM ENSW", 8) &&
+			(!strncmp(productid, "VIGIL SMP", 9)
+			 || !strncmp(productid, "EXA", 3)
+			 || !strncmp(productid, "RUTHLESS SMP", 12))){
+		mark_tsc_unstable("Summit based system");
+		use_cyclone = 1; /*enable cyclone-timer*/
+		setup_summit();
+		return 1;
+	}
+	return 0;
+}
+
+/* Hook from generic ACPI tables.c */
+static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
+{
+	if (!strncmp(oem_id, "IBM", 3) &&
+	    (!strncmp(oem_table_id, "SERVIGIL", 8)
+	     || !strncmp(oem_table_id, "EXA", 3))){
+		mark_tsc_unstable("Summit based system");
+		use_cyclone = 1; /*enable cyclone-timer*/
+		setup_summit();
+		return 1;
+	}
+	return 0;
+}
+
+struct rio_table_hdr {
+	unsigned char version;      /* Version number of this data structure           */
+	                            /* Version 3 adds chassis_num & WP_index           */
+	unsigned char num_scal_dev; /* # of Scalability devices (Twisters for Vigil)   */
+	unsigned char num_rio_dev;  /* # of RIO I/O devices (Cyclones and Winnipegs)   */
+} __attribute__((packed));
+
+struct scal_detail {
+	unsigned char node_id;      /* Scalability Node ID                             */
+	unsigned long CBAR;         /* Address of 1MB register space                   */
+	unsigned char port0node;    /* Node ID port connected to: 0xFF=None            */
+	unsigned char port0port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
+	unsigned char port1node;    /* Node ID port connected to: 0xFF = None          */
+	unsigned char port1port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
+	unsigned char port2node;    /* Node ID port connected to: 0xFF = None          */
+	unsigned char port2port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
+	unsigned char chassis_num;  /* 1 based Chassis number (1 = boot node)          */
+} __attribute__((packed));
+
+struct rio_detail {
+	unsigned char node_id;      /* RIO Node ID                                     */
+	unsigned long BBAR;         /* Address of 1MB register space                   */
+	unsigned char type;         /* Type of device                                  */
+	unsigned char owner_id;     /* For WPEG: Node ID of Cyclone that owns this WPEG*/
+	                            /* For CYC:  Node ID of Twister that owns this CYC */
+	unsigned char port0node;    /* Node ID port connected to: 0xFF=None            */
+	unsigned char port0port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
+	unsigned char port1node;    /* Node ID port connected to: 0xFF=None            */
+	unsigned char port1port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
+	unsigned char first_slot;   /* For WPEG: Lowest slot number below this WPEG    */
+	                            /* For CYC:  0                                     */
+	unsigned char status;       /* For WPEG: Bit 0 = 1 : the XAPIC is used         */
+	                            /*                 = 0 : the XAPIC is not used, ie:*/
+	                            /*                     ints fwded to another XAPIC */
+	                            /*           Bits1:7 Reserved                      */
+	                            /* For CYC:  Bits0:7 Reserved                      */
+	unsigned char WP_index;     /* For WPEG: WPEG instance index - lower ones have */
+	                            /*           lower slot numbers/PCI bus numbers    */
+	                            /* For CYC:  No meaning                            */
+	unsigned char chassis_num;  /* 1 based Chassis number                          */
+	                            /* For LookOut WPEGs this field indicates the      */
+	                            /* Expansion Chassis #, enumerated from Boot       */
+	                            /* Node WPEG external port, then Boot Node CYC     */
+	                            /* external port, then Next Vigil chassis WPEG     */
+	                            /* external port, etc.                             */
+	                            /* Shared Lookouts have only 1 chassis number (the */
+	                            /* first one assigned)                             */
+} __attribute__((packed));
+
+
+typedef enum {
+	CompatTwister = 0,  /* Compatibility Twister               */
+	AltTwister    = 1,  /* Alternate Twister of internal 8-way */
+	CompatCyclone = 2,  /* Compatibility Cyclone               */
+	AltCyclone    = 3,  /* Alternate Cyclone of internal 8-way */
+	CompatWPEG    = 4,  /* Compatibility WPEG                  */
+	AltWPEG       = 5,  /* Second Planar WPEG                  */
+	LookOutAWPEG  = 6,  /* LookOut WPEG                        */
+	LookOutBWPEG  = 7,  /* LookOut WPEG                        */
+} node_type;
+
+static inline int is_WPEG(struct rio_detail *rio){
+	return (rio->type == CompatWPEG || rio->type == AltWPEG ||
+		rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
+}
+
+#endif /* __ASM_SUMMIT_MPPARSE_H */
diff --git a/arch/x86/include/asm/suspend.h b/arch/x86/include/asm/suspend.h
new file mode 100644
index 000000000000..9bd521fe4570
--- /dev/null
+++ b/arch/x86/include/asm/suspend.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "suspend_32.h"
+#else
+# include "suspend_64.h"
+#endif
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
new file mode 100644
index 000000000000..acb6d4d491f4
--- /dev/null
+++ b/arch/x86/include/asm/suspend_32.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright 2001-2002 Pavel Machek <pavel@suse.cz>
+ * Based on code
+ * Copyright 2001 Patrick Mochel <mochel@osdl.org>
+ */
+#ifndef ASM_X86__SUSPEND_32_H
+#define ASM_X86__SUSPEND_32_H
+
+#include <asm/desc.h>
+#include <asm/i387.h>
+
+static inline int arch_prepare_suspend(void) { return 0; }
+
+/* image of the saved processor state */
+struct saved_context {
+	u16 es, fs, gs, ss;
+	unsigned long cr0, cr2, cr3, cr4;
+	struct desc_ptr gdt;
+	struct desc_ptr idt;
+	u16 ldt;
+	u16 tss;
+	unsigned long tr;
+	unsigned long safety;
+	unsigned long return_address;
+} __attribute__((packed));
+
+#ifdef CONFIG_ACPI
+extern unsigned long saved_eip;
+extern unsigned long saved_esp;
+extern unsigned long saved_ebp;
+extern unsigned long saved_ebx;
+extern unsigned long saved_esi;
+extern unsigned long saved_edi;
+
+static inline void acpi_save_register_state(unsigned long return_point)
+{
+	saved_eip = return_point;
+	asm volatile("movl %%esp,%0" : "=m" (saved_esp));
+	asm volatile("movl %%ebp,%0" : "=m" (saved_ebp));
+	asm volatile("movl %%ebx,%0" : "=m" (saved_ebx));
+	asm volatile("movl %%edi,%0" : "=m" (saved_edi));
+	asm volatile("movl %%esi,%0" : "=m" (saved_esi));
+}
+
+#define acpi_restore_register_state()  do {} while (0)
+
+/* routines for saving/restoring kernel state */
+extern int acpi_save_state_mem(void);
+#endif
+
+#endif /* ASM_X86__SUSPEND_32_H */
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
new file mode 100644
index 000000000000..cf821dd310e8
--- /dev/null
+++ b/arch/x86/include/asm/suspend_64.h
@@ -0,0 +1,52 @@
+/*
+ * Copyright 2001-2003 Pavel Machek <pavel@suse.cz>
+ * Based on code
+ * Copyright 2001 Patrick Mochel <mochel@osdl.org>
+ */
+#ifndef ASM_X86__SUSPEND_64_H
+#define ASM_X86__SUSPEND_64_H
+
+#include <asm/desc.h>
+#include <asm/i387.h>
+
+static inline int arch_prepare_suspend(void)
+{
+	return 0;
+}
+
+/*
+ * Image of the saved processor state, used by the low level ACPI suspend to
+ * RAM code and by the low level hibernation code.
+ *
+ * If you modify it, fix arch/x86/kernel/acpi/wakeup_64.S and make sure that
+ * __save/__restore_processor_state(), defined in arch/x86/kernel/suspend_64.c,
+ * still work as required.
+ */
+struct saved_context {
+	struct pt_regs regs;
+	u16 ds, es, fs, gs, ss;
+	unsigned long gs_base, gs_kernel_base, fs_base;
+	unsigned long cr0, cr2, cr3, cr4, cr8;
+	unsigned long efer;
+	u16 gdt_pad;
+	u16 gdt_limit;
+	unsigned long gdt_base;
+	u16 idt_pad;
+	u16 idt_limit;
+	unsigned long idt_base;
+	u16 ldt;
+	u16 tss;
+	unsigned long tr;
+	unsigned long safety;
+	unsigned long return_address;
+} __attribute__((packed));
+
+#define loaddebug(thread,register) \
+	set_debugreg((thread)->debugreg##register, register)
+
+/* routines for saving/restoring kernel state */
+extern int acpi_save_state_mem(void);
+extern char core_restore_code;
+extern char restore_registers;
+
+#endif /* ASM_X86__SUSPEND_64_H */
diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h
new file mode 100644
index 000000000000..1e20adbcad4b
--- /dev/null
+++ b/arch/x86/include/asm/swiotlb.h
@@ -0,0 +1,58 @@
+#ifndef ASM_X86__SWIOTLB_H
+#define ASM_X86__SWIOTLB_H
+
+#include <asm/dma-mapping.h>
+
+/* SWIOTLB interface */
+
+extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr,
+				     size_t size, int dir);
+extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+				    dma_addr_t *dma_handle, gfp_t flags);
+extern void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+				 size_t size, int dir);
+extern void swiotlb_sync_single_for_cpu(struct device *hwdev,
+					dma_addr_t dev_addr,
+					size_t size, int dir);
+extern void swiotlb_sync_single_for_device(struct device *hwdev,
+					   dma_addr_t dev_addr,
+					   size_t size, int dir);
+extern void swiotlb_sync_single_range_for_cpu(struct device *hwdev,
+					      dma_addr_t dev_addr,
+					      unsigned long offset,
+					      size_t size, int dir);
+extern void swiotlb_sync_single_range_for_device(struct device *hwdev,
+						 dma_addr_t dev_addr,
+						 unsigned long offset,
+						 size_t size, int dir);
+extern void swiotlb_sync_sg_for_cpu(struct device *hwdev,
+				    struct scatterlist *sg, int nelems,
+				    int dir);
+extern void swiotlb_sync_sg_for_device(struct device *hwdev,
+				       struct scatterlist *sg, int nelems,
+				       int dir);
+extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg,
+			  int nents, int direction);
+extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg,
+			     int nents, int direction);
+extern int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr);
+extern void swiotlb_free_coherent(struct device *hwdev, size_t size,
+				  void *vaddr, dma_addr_t dma_handle);
+extern int swiotlb_dma_supported(struct device *hwdev, u64 mask);
+extern void swiotlb_init(void);
+
+extern int swiotlb_force;
+
+#ifdef CONFIG_SWIOTLB
+extern int swiotlb;
+extern void pci_swiotlb_init(void);
+#else
+#define swiotlb 0
+static inline void pci_swiotlb_init(void)
+{
+}
+#endif
+
+static inline void dma_mark_clean(void *addr, size_t size) {}
+
+#endif /* ASM_X86__SWIOTLB_H */
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
new file mode 100644
index 000000000000..b689bee71104
--- /dev/null
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -0,0 +1,130 @@
+#ifndef ASM_X86__SYNC_BITOPS_H
+#define ASM_X86__SYNC_BITOPS_H
+
+/*
+ * Copyright 1992, Linus Torvalds.
+ */
+
+/*
+ * These have to be done with inline assembly: that way the bit-setting
+ * is guaranteed to be atomic. All bit operations return 0 if the bit
+ * was cleared before the operation and != 0 if it was not.
+ *
+ * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
+ */
+
+#define ADDR (*(volatile long *)addr)
+
+/**
+ * sync_set_bit - Atomically set a bit in memory
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ *
+ * This function is atomic and may not be reordered.  See __set_bit()
+ * if you do not require the atomic guarantees.
+ *
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void sync_set_bit(int nr, volatile unsigned long *addr)
+{
+	asm volatile("lock; btsl %1,%0"
+		     : "+m" (ADDR)
+		     : "Ir" (nr)
+		     : "memory");
+}
+
+/**
+ * sync_clear_bit - Clears a bit in memory
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ *
+ * sync_clear_bit() is atomic and may not be reordered.  However, it does
+ * not contain a memory barrier, so if it is used for locking purposes,
+ * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * in order to ensure changes are visible on other processors.
+ */
+static inline void sync_clear_bit(int nr, volatile unsigned long *addr)
+{
+	asm volatile("lock; btrl %1,%0"
+		     : "+m" (ADDR)
+		     : "Ir" (nr)
+		     : "memory");
+}
+
+/**
+ * sync_change_bit - Toggle a bit in memory
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ *
+ * sync_change_bit() is atomic and may not be reordered.
+ * Note that @nr may be almost arbitrarily large; this function is not
+ * restricted to acting on a single-word quantity.
+ */
+static inline void sync_change_bit(int nr, volatile unsigned long *addr)
+{
+	asm volatile("lock; btcl %1,%0"
+		     : "+m" (ADDR)
+		     : "Ir" (nr)
+		     : "memory");
+}
+
+/**
+ * sync_test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile("lock; btsl %2,%1\n\tsbbl %0,%0"
+		     : "=r" (oldbit), "+m" (ADDR)
+		     : "Ir" (nr) : "memory");
+	return oldbit;
+}
+
+/**
+ * sync_test_and_clear_bit - Clear a bit and return its old value
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile("lock; btrl %2,%1\n\tsbbl %0,%0"
+		     : "=r" (oldbit), "+m" (ADDR)
+		     : "Ir" (nr) : "memory");
+	return oldbit;
+}
+
+/**
+ * sync_test_and_change_bit - Change a bit and return its old value
+ * @nr: Bit to change
+ * @addr: Address to count from
+ *
+ * This operation is atomic and cannot be reordered.
+ * It also implies a memory barrier.
+ */
+static inline int sync_test_and_change_bit(int nr, volatile unsigned long *addr)
+{
+	int oldbit;
+
+	asm volatile("lock; btcl %2,%1\n\tsbbl %0,%0"
+		     : "=r" (oldbit), "+m" (ADDR)
+		     : "Ir" (nr) : "memory");
+	return oldbit;
+}
+
+#define sync_test_bit(nr, addr) test_bit(nr, addr)
+
+#undef ADDR
+
+#endif /* ASM_X86__SYNC_BITOPS_H */
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
new file mode 100644
index 000000000000..04c47dc5597c
--- /dev/null
+++ b/arch/x86/include/asm/syscall.h
@@ -0,0 +1,211 @@
+/*
+ * Access to user system call parameters and results
+ *
+ * Copyright (C) 2008 Red Hat, Inc.  All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License v.2.
+ *
+ * See asm-generic/syscall.h for descriptions of what we must do here.
+ */
+
+#ifndef _ASM_SYSCALL_H
+#define _ASM_SYSCALL_H	1
+
+#include <linux/sched.h>
+#include <linux/err.h>
+
+static inline long syscall_get_nr(struct task_struct *task,
+				  struct pt_regs *regs)
+{
+	/*
+	 * We always sign-extend a -1 value being set here,
+	 * so this is always either -1L or a syscall number.
+	 */
+	return regs->orig_ax;
+}
+
+static inline void syscall_rollback(struct task_struct *task,
+				    struct pt_regs *regs)
+{
+	regs->ax = regs->orig_ax;
+}
+
+static inline long syscall_get_error(struct task_struct *task,
+				     struct pt_regs *regs)
+{
+	unsigned long error = regs->ax;
+#ifdef CONFIG_IA32_EMULATION
+	/*
+	 * TS_COMPAT is set for 32-bit syscall entries and then
+	 * remains set until we return to user mode.
+	 */
+	if (task_thread_info(task)->status & TS_COMPAT)
+		/*
+		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
+		 * and will match correctly in comparisons.
+		 */
+		error = (long) (int) error;
+#endif
+	return IS_ERR_VALUE(error) ? error : 0;
+}
+
+static inline long syscall_get_return_value(struct task_struct *task,
+					    struct pt_regs *regs)
+{
+	return regs->ax;
+}
+
+static inline void syscall_set_return_value(struct task_struct *task,
+					    struct pt_regs *regs,
+					    int error, long val)
+{
+	regs->ax = (long) error ?: val;
+}
+
+#ifdef CONFIG_X86_32
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+	BUG_ON(i + n > 6);
+	memcpy(args, &regs->bx + i, n * sizeof(args[0]));
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+	BUG_ON(i + n > 6);
+	memcpy(&regs->bx + i, args, n * sizeof(args[0]));
+}
+
+#else	 /* CONFIG_X86_64 */
+
+static inline void syscall_get_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 unsigned long *args)
+{
+# ifdef CONFIG_IA32_EMULATION
+	if (task_thread_info(task)->status & TS_COMPAT)
+		switch (i + n) {
+		case 6:
+			if (!n--) break;
+			*args++ = regs->bp;
+		case 5:
+			if (!n--) break;
+			*args++ = regs->di;
+		case 4:
+			if (!n--) break;
+			*args++ = regs->si;
+		case 3:
+			if (!n--) break;
+			*args++ = regs->dx;
+		case 2:
+			if (!n--) break;
+			*args++ = regs->cx;
+		case 1:
+			if (!n--) break;
+			*args++ = regs->bx;
+		case 0:
+			if (!n--) break;
+		default:
+			BUG();
+			break;
+		}
+	else
+# endif
+		switch (i + n) {
+		case 6:
+			if (!n--) break;
+			*args++ = regs->r9;
+		case 5:
+			if (!n--) break;
+			*args++ = regs->r8;
+		case 4:
+			if (!n--) break;
+			*args++ = regs->r10;
+		case 3:
+			if (!n--) break;
+			*args++ = regs->dx;
+		case 2:
+			if (!n--) break;
+			*args++ = regs->si;
+		case 1:
+			if (!n--) break;
+			*args++ = regs->di;
+		case 0:
+			if (!n--) break;
+		default:
+			BUG();
+			break;
+		}
+}
+
+static inline void syscall_set_arguments(struct task_struct *task,
+					 struct pt_regs *regs,
+					 unsigned int i, unsigned int n,
+					 const unsigned long *args)
+{
+# ifdef CONFIG_IA32_EMULATION
+	if (task_thread_info(task)->status & TS_COMPAT)
+		switch (i + n) {
+		case 6:
+			if (!n--) break;
+			regs->bp = *args++;
+		case 5:
+			if (!n--) break;
+			regs->di = *args++;
+		case 4:
+			if (!n--) break;
+			regs->si = *args++;
+		case 3:
+			if (!n--) break;
+			regs->dx = *args++;
+		case 2:
+			if (!n--) break;
+			regs->cx = *args++;
+		case 1:
+			if (!n--) break;
+			regs->bx = *args++;
+		case 0:
+			if (!n--) break;
+		default:
+			BUG();
+		}
+	else
+# endif
+		switch (i + n) {
+		case 6:
+			if (!n--) break;
+			regs->r9 = *args++;
+		case 5:
+			if (!n--) break;
+			regs->r8 = *args++;
+		case 4:
+			if (!n--) break;
+			regs->r10 = *args++;
+		case 3:
+			if (!n--) break;
+			regs->dx = *args++;
+		case 2:
+			if (!n--) break;
+			regs->si = *args++;
+		case 1:
+			if (!n--) break;
+			regs->di = *args++;
+		case 0:
+			if (!n--) break;
+		default:
+			BUG();
+		}
+}
+
+#endif	/* CONFIG_X86_32 */
+
+#endif	/* _ASM_SYSCALL_H */
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
new file mode 100644
index 000000000000..87803da44010
--- /dev/null
+++ b/arch/x86/include/asm/syscalls.h
@@ -0,0 +1,93 @@
+/*
+ * syscalls.h - Linux syscall interfaces (arch-specific)
+ *
+ * Copyright (c) 2008 Jaswinder Singh
+ *
+ * This file is released under the GPLv2.
+ * See the file COPYING for more details.
+ */
+
+#ifndef _ASM_X86_SYSCALLS_H
+#define _ASM_X86_SYSCALLS_H
+
+#include <linux/compiler.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <linux/signal.h>
+
+/* Common in X86_32 and X86_64 */
+/* kernel/ioport.c */
+asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
+
+/* X86_32 only */
+#ifdef CONFIG_X86_32
+/* kernel/process_32.c */
+asmlinkage int sys_fork(struct pt_regs);
+asmlinkage int sys_clone(struct pt_regs);
+asmlinkage int sys_vfork(struct pt_regs);
+asmlinkage int sys_execve(struct pt_regs);
+
+/* kernel/signal_32.c */
+asmlinkage int sys_sigsuspend(int, int, old_sigset_t);
+asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
+			     struct old_sigaction __user *);
+asmlinkage int sys_sigaltstack(unsigned long);
+asmlinkage unsigned long sys_sigreturn(unsigned long);
+asmlinkage int sys_rt_sigreturn(unsigned long);
+
+/* kernel/ioport.c */
+asmlinkage long sys_iopl(unsigned long);
+
+/* kernel/ldt.c */
+asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
+
+/* kernel/sys_i386_32.c */
+asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
+			  unsigned long, unsigned long, unsigned long);
+struct mmap_arg_struct;
+asmlinkage int old_mmap(struct mmap_arg_struct __user *);
+struct sel_arg_struct;
+asmlinkage int old_select(struct sel_arg_struct __user *);
+asmlinkage int sys_ipc(uint, int, int, int, void __user *, long);
+struct old_utsname;
+asmlinkage int sys_uname(struct old_utsname __user *);
+struct oldold_utsname;
+asmlinkage int sys_olduname(struct oldold_utsname __user *);
+
+/* kernel/tls.c */
+asmlinkage int sys_set_thread_area(struct user_desc __user *);
+asmlinkage int sys_get_thread_area(struct user_desc __user *);
+
+/* kernel/vm86_32.c */
+asmlinkage int sys_vm86old(struct pt_regs);
+asmlinkage int sys_vm86(struct pt_regs);
+
+#else /* CONFIG_X86_32 */
+
+/* X86_64 only */
+/* kernel/process_64.c */
+asmlinkage long sys_fork(struct pt_regs *);
+asmlinkage long sys_clone(unsigned long, unsigned long,
+			  void __user *, void __user *,
+			  struct pt_regs *);
+asmlinkage long sys_vfork(struct pt_regs *);
+asmlinkage long sys_execve(char __user *, char __user * __user *,
+			   char __user * __user *,
+			   struct pt_regs *);
+
+/* kernel/ioport.c */
+asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
+
+/* kernel/signal_64.c */
+asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
+				struct pt_regs *);
+asmlinkage long sys_rt_sigreturn(struct pt_regs *);
+
+/* kernel/sys_x86_64.c */
+asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
+			 unsigned long, unsigned long, unsigned long);
+struct new_utsname;
+asmlinkage long sys_uname(struct new_utsname __user *);
+
+#endif /* CONFIG_X86_32 */
+#endif /* _ASM_X86_SYSCALLS_H */
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
new file mode 100644
index 000000000000..b20c894660f9
--- /dev/null
+++ b/arch/x86/include/asm/system.h
@@ -0,0 +1,425 @@
+#ifndef ASM_X86__SYSTEM_H
+#define ASM_X86__SYSTEM_H
+
+#include <asm/asm.h>
+#include <asm/segment.h>
+#include <asm/cpufeature.h>
+#include <asm/cmpxchg.h>
+#include <asm/nops.h>
+
+#include <linux/kernel.h>
+#include <linux/irqflags.h>
+
+/* entries in ARCH_DLINFO: */
+#ifdef CONFIG_IA32_EMULATION
+# define AT_VECTOR_SIZE_ARCH 2
+#else
+# define AT_VECTOR_SIZE_ARCH 1
+#endif
+
+#ifdef CONFIG_X86_32
+
+struct task_struct; /* one of the stranger aspects of C forward declarations */
+struct task_struct *__switch_to(struct task_struct *prev,
+				struct task_struct *next);
+
+/*
+ * Saving eflags is important. It switches not only IOPL between tasks,
+ * it also protects other tasks from NT leaking through sysenter etc.
+ */
+#define switch_to(prev, next, last)					\
+do {									\
+	/*								\
+	 * Context-switching clobbers all registers, so we clobber	\
+	 * them explicitly, via unused output variables.		\
+	 * (EAX and EBP is not listed because EBP is saved/restored	\
+	 * explicitly for wchan access and EAX is the return value of	\
+	 * __switch_to())						\
+	 */								\
+	unsigned long ebx, ecx, edx, esi, edi;				\
+									\
+	asm volatile("pushfl\n\t"		/* save    flags */	\
+		     "pushl %%ebp\n\t"		/* save    EBP   */	\
+		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
+		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
+		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
+		     "pushl %[next_ip]\n\t"	/* restore EIP   */	\
+		     "jmp __switch_to\n"	/* regparm call  */	\
+		     "1:\t"						\
+		     "popl %%ebp\n\t"		/* restore EBP   */	\
+		     "popfl\n"			/* restore flags */	\
+									\
+		     /* output parameters */				\
+		     : [prev_sp] "=m" (prev->thread.sp),		\
+		       [prev_ip] "=m" (prev->thread.ip),		\
+		       "=a" (last),					\
+									\
+		       /* clobbered output registers: */		\
+		       "=b" (ebx), "=c" (ecx), "=d" (edx),		\
+		       "=S" (esi), "=D" (edi)				\
+		       							\
+		       /* input parameters: */				\
+		     : [next_sp]  "m" (next->thread.sp),		\
+		       [next_ip]  "m" (next->thread.ip),		\
+		       							\
+		       /* regparm parameters for __switch_to(): */	\
+		       [prev]     "a" (prev),				\
+		       [next]     "d" (next)				\
+									\
+		     : /* reloaded segment registers */			\
+			"memory");					\
+} while (0)
+
+/*
+ * disable hlt during certain critical i/o operations
+ */
+#define HAVE_DISABLE_HLT
+#else
+#define __SAVE(reg, offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t"
+#define __RESTORE(reg, offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t"
+
+/* frame pointer must be last for get_wchan */
+#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
+
+#define __EXTRA_CLOBBER  \
+	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
+	  "r12", "r13", "r14", "r15"
+
+/* Save restore flags to clear handle leaking NT */
+#define switch_to(prev, next, last) \
+	asm volatile(SAVE_CONTEXT						    \
+	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
+	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
+	     "call __switch_to\n\t"					  \
+	     ".globl thread_return\n"					  \
+	     "thread_return:\n\t"					  \
+	     "movq %%gs:%P[pda_pcurrent],%%rsi\n\t"			  \
+	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
+	     LOCK_PREFIX "btr  %[tif_fork],%P[ti_flags](%%r8)\n\t"	  \
+	     "movq %%rax,%%rdi\n\t" 					  \
+	     "jc   ret_from_fork\n\t"					  \
+	     RESTORE_CONTEXT						  \
+	     : "=a" (last)					  	  \
+	     : [next] "S" (next), [prev] "D" (prev),			  \
+	       [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
+	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
+	       [tif_fork] "i" (TIF_FORK),			  	  \
+	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
+	       [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent))  \
+	     : "memory", "cc" __EXTRA_CLOBBER)
+#endif
+
+#ifdef __KERNEL__
+#define _set_base(addr, base) do { unsigned long __pr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+	"rorl $16,%%edx\n\t" \
+	"movb %%dl,%2\n\t" \
+	"movb %%dh,%3" \
+	:"=&d" (__pr) \
+	:"m" (*((addr)+2)), \
+	 "m" (*((addr)+4)), \
+	 "m" (*((addr)+7)), \
+	 "0" (base) \
+	); } while (0)
+
+#define _set_limit(addr, limit) do { unsigned long __lr; \
+__asm__ __volatile__ ("movw %%dx,%1\n\t" \
+	"rorl $16,%%edx\n\t" \
+	"movb %2,%%dh\n\t" \
+	"andb $0xf0,%%dh\n\t" \
+	"orb %%dh,%%dl\n\t" \
+	"movb %%dl,%2" \
+	:"=&d" (__lr) \
+	:"m" (*(addr)), \
+	 "m" (*((addr)+6)), \
+	 "0" (limit) \
+	); } while (0)
+
+#define set_base(ldt, base) _set_base(((char *)&(ldt)) , (base))
+#define set_limit(ldt, limit) _set_limit(((char *)&(ldt)) , ((limit)-1))
+
+extern void native_load_gs_index(unsigned);
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg, value)			\
+	asm volatile("\n"			\
+		     "1:\t"			\
+		     "movl %k0,%%" #seg "\n"	\
+		     "2:\n"			\
+		     ".section .fixup,\"ax\"\n"	\
+		     "3:\t"			\
+		     "movl %k1, %%" #seg "\n\t"	\
+		     "jmp 2b\n"			\
+		     ".previous\n"		\
+		     _ASM_EXTABLE(1b,3b)	\
+		     : :"r" (value), "r" (0) : "memory")
+
+
+/*
+ * Save a segment register away
+ */
+#define savesegment(seg, value)				\
+	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
+
+static inline unsigned long get_limit(unsigned long segment)
+{
+	unsigned long __limit;
+	asm("lsll %1,%0" : "=r" (__limit) : "r" (segment));
+	return __limit + 1;
+}
+
+static inline void native_clts(void)
+{
+	asm volatile("clts");
+}
+
+/*
+ * Volatile isn't enough to prevent the compiler from reordering the
+ * read/write functions for the control registers and messing everything up.
+ * A memory clobber would solve the problem, but would prevent reordering of
+ * all loads stores around it, which can hurt performance. Solution is to
+ * use a variable and mimic reads and writes to it to enforce serialization
+ */
+static unsigned long __force_order;
+
+static inline unsigned long native_read_cr0(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr0(unsigned long val)
+{
+	asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr2(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr2(unsigned long val)
+{
+	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr3(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr3(unsigned long val)
+{
+	asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr4(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline unsigned long native_read_cr4_safe(void)
+{
+	unsigned long val;
+	/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
+	 * exists, so it will never fail. */
+#ifdef CONFIG_X86_32
+	asm volatile("1: mov %%cr4, %0\n"
+		     "2:\n"
+		     _ASM_EXTABLE(1b, 2b)
+		     : "=r" (val), "=m" (__force_order) : "0" (0));
+#else
+	val = native_read_cr4();
+#endif
+	return val;
+}
+
+static inline void native_write_cr4(unsigned long val)
+{
+	asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
+}
+
+#ifdef CONFIG_X86_64
+static inline unsigned long native_read_cr8(void)
+{
+	unsigned long cr8;
+	asm volatile("movq %%cr8,%0" : "=r" (cr8));
+	return cr8;
+}
+
+static inline void native_write_cr8(unsigned long val)
+{
+	asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
+}
+#endif
+
+static inline void native_wbinvd(void)
+{
+	asm volatile("wbinvd": : :"memory");
+}
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define read_cr0()	(native_read_cr0())
+#define write_cr0(x)	(native_write_cr0(x))
+#define read_cr2()	(native_read_cr2())
+#define write_cr2(x)	(native_write_cr2(x))
+#define read_cr3()	(native_read_cr3())
+#define write_cr3(x)	(native_write_cr3(x))
+#define read_cr4()	(native_read_cr4())
+#define read_cr4_safe()	(native_read_cr4_safe())
+#define write_cr4(x)	(native_write_cr4(x))
+#define wbinvd()	(native_wbinvd())
+#ifdef CONFIG_X86_64
+#define read_cr8()	(native_read_cr8())
+#define write_cr8(x)	(native_write_cr8(x))
+#define load_gs_index   native_load_gs_index
+#endif
+
+/* Clear the 'TS' bit */
+#define clts()		(native_clts())
+
+#endif/* CONFIG_PARAVIRT */
+
+#define stts() write_cr0(read_cr0() | X86_CR0_TS)
+
+#endif /* __KERNEL__ */
+
+static inline void clflush(volatile void *__p)
+{
+	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
+}
+
+#define nop() asm volatile ("nop")
+
+void disable_hlt(void);
+void enable_hlt(void);
+
+void cpu_idle_wait(void);
+
+extern unsigned long arch_align_stack(unsigned long sp);
+extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+
+void default_idle(void);
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+#ifdef CONFIG_X86_32
+/*
+ * Some non-Intel clones support out of order store. wmb() ceases to be a
+ * nop for these.
+ */
+#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#else
+#define mb() 	asm volatile("mfence":::"memory")
+#define rmb()	asm volatile("lfence":::"memory")
+#define wmb()	asm volatile("sfence" ::: "memory")
+#endif
+
+/**
+ * read_barrier_depends - Flush all pending reads that subsequents reads
+ * depend on.
+ *
+ * No data-dependent reads from memory-like regions are ever reordered
+ * over this barrier.  All reads preceding this primitive are guaranteed
+ * to access memory (but not necessarily other CPUs' caches) before any
+ * reads following this primitive that depend on the data return by
+ * any of the preceding reads.  This primitive is much lighter weight than
+ * rmb() on most CPUs, and is never heavier weight than is
+ * rmb().
+ *
+ * These ordering constraints are respected by both the local CPU
+ * and the compiler.
+ *
+ * Ordering is not guaranteed by anything other than these primitives,
+ * not even by data dependencies.  See the documentation for
+ * memory_barrier() for examples and URLs to more information.
+ *
+ * For example, the following code would force ordering (the initial
+ * value of "a" is zero, "b" is one, and "p" is "&a"):
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	b = 2;
+ *	memory_barrier();
+ *	p = &b;				q = p;
+ *					read_barrier_depends();
+ *					d = *q;
+ * </programlisting>
+ *
+ * because the read of "*q" depends on the read of "p" and these
+ * two reads are separated by a read_barrier_depends().  However,
+ * the following code, with the same initial values for "a" and "b":
+ *
+ * <programlisting>
+ *	CPU 0				CPU 1
+ *
+ *	a = 2;
+ *	memory_barrier();
+ *	b = 3;				y = b;
+ *					read_barrier_depends();
+ *					x = a;
+ * </programlisting>
+ *
+ * does not enforce ordering, since there is no data dependency between
+ * the read of "a" and the read of "b".  Therefore, on some CPUs, such
+ * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
+ * in cases like this where there are no data dependencies.
+ **/
+
+#define read_barrier_depends()	do { } while (0)
+
+#ifdef CONFIG_SMP
+#define smp_mb()	mb()
+#ifdef CONFIG_X86_PPRO_FENCE
+# define smp_rmb()	rmb()
+#else
+# define smp_rmb()	barrier()
+#endif
+#ifdef CONFIG_X86_OOSTORE
+# define smp_wmb() 	wmb()
+#else
+# define smp_wmb()	barrier()
+#endif
+#define smp_read_barrier_depends()	read_barrier_depends()
+#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#else
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while (0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif
+
+/*
+ * Stop RDTSC speculation. This is needed when you need to use RDTSC
+ * (or get_cycles or vread that possibly accesses the TSC) in a defined
+ * code region.
+ *
+ * (Could use an alternative three way for this if there was one.)
+ */
+static inline void rdtsc_barrier(void)
+{
+	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
+	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+}
+
+#endif /* ASM_X86__SYSTEM_H */
diff --git a/arch/x86/include/asm/system_64.h b/arch/x86/include/asm/system_64.h
new file mode 100644
index 000000000000..5aedb8bffc5a
--- /dev/null
+++ b/arch/x86/include/asm/system_64.h
@@ -0,0 +1,22 @@
+#ifndef ASM_X86__SYSTEM_64_H
+#define ASM_X86__SYSTEM_64_H
+
+#include <asm/segment.h>
+#include <asm/cmpxchg.h>
+
+
+static inline unsigned long read_cr8(void)
+{
+	unsigned long cr8;
+	asm volatile("movq %%cr8,%0" : "=r" (cr8));
+	return cr8;
+}
+
+static inline void write_cr8(unsigned long val)
+{
+	asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
+}
+
+#include <linux/irqflags.h>
+
+#endif /* ASM_X86__SYSTEM_64_H */
diff --git a/arch/x86/include/asm/tce.h b/arch/x86/include/asm/tce.h
new file mode 100644
index 000000000000..e7932d7fbbab
--- /dev/null
+++ b/arch/x86/include/asm/tce.h
@@ -0,0 +1,48 @@
+/*
+ * This file is derived from asm-powerpc/tce.h.
+ *
+ * Copyright (C) IBM Corporation, 2006
+ *
+ * Author: Muli Ben-Yehuda <muli@il.ibm.com>
+ * Author: Jon Mason <jdmason@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#ifndef ASM_X86__TCE_H
+#define ASM_X86__TCE_H
+
+extern unsigned int specified_table_size;
+struct iommu_table;
+
+#define TCE_ENTRY_SIZE   8   /* in bytes */
+
+#define TCE_READ_SHIFT   0
+#define TCE_WRITE_SHIFT  1
+#define TCE_HUBID_SHIFT  2   /* unused */
+#define TCE_RSVD_SHIFT   8   /* unused */
+#define TCE_RPN_SHIFT    12
+#define TCE_UNUSED_SHIFT 48  /* unused */
+
+#define TCE_RPN_MASK     0x0000fffffffff000ULL
+
+extern void tce_build(struct iommu_table *tbl, unsigned long index,
+		      unsigned int npages, unsigned long uaddr, int direction);
+extern void tce_free(struct iommu_table *tbl, long index, unsigned int npages);
+extern void * __init alloc_tce_table(void);
+extern void __init free_tce_table(void *tbl);
+extern int __init build_tce_table(struct pci_dev *dev, void __iomem *bbar);
+
+#endif /* ASM_X86__TCE_H */
diff --git a/arch/x86/include/asm/termbits.h b/arch/x86/include/asm/termbits.h
new file mode 100644
index 000000000000..3d00dc5e0c71
--- /dev/null
+++ b/arch/x86/include/asm/termbits.h
@@ -0,0 +1,198 @@
+#ifndef ASM_X86__TERMBITS_H
+#define ASM_X86__TERMBITS_H
+
+#include <linux/posix_types.h>
+
+typedef unsigned char	cc_t;
+typedef unsigned int	speed_t;
+typedef unsigned int	tcflag_t;
+
+#define NCCS 19
+struct termios {
+	tcflag_t c_iflag;		/* input mode flags */
+	tcflag_t c_oflag;		/* output mode flags */
+	tcflag_t c_cflag;		/* control mode flags */
+	tcflag_t c_lflag;		/* local mode flags */
+	cc_t c_line;			/* line discipline */
+	cc_t c_cc[NCCS];		/* control characters */
+};
+
+struct termios2 {
+	tcflag_t c_iflag;		/* input mode flags */
+	tcflag_t c_oflag;		/* output mode flags */
+	tcflag_t c_cflag;		/* control mode flags */
+	tcflag_t c_lflag;		/* local mode flags */
+	cc_t c_line;			/* line discipline */
+	cc_t c_cc[NCCS];		/* control characters */
+	speed_t c_ispeed;		/* input speed */
+	speed_t c_ospeed;		/* output speed */
+};
+
+struct ktermios {
+	tcflag_t c_iflag;		/* input mode flags */
+	tcflag_t c_oflag;		/* output mode flags */
+	tcflag_t c_cflag;		/* control mode flags */
+	tcflag_t c_lflag;		/* local mode flags */
+	cc_t c_line;			/* line discipline */
+	cc_t c_cc[NCCS];		/* control characters */
+	speed_t c_ispeed;		/* input speed */
+	speed_t c_ospeed;		/* output speed */
+};
+
+/* c_cc characters */
+#define VINTR 0
+#define VQUIT 1
+#define VERASE 2
+#define VKILL 3
+#define VEOF 4
+#define VTIME 5
+#define VMIN 6
+#define VSWTC 7
+#define VSTART 8
+#define VSTOP 9
+#define VSUSP 10
+#define VEOL 11
+#define VREPRINT 12
+#define VDISCARD 13
+#define VWERASE 14
+#define VLNEXT 15
+#define VEOL2 16
+
+/* c_iflag bits */
+#define IGNBRK	0000001
+#define BRKINT	0000002
+#define IGNPAR	0000004
+#define PARMRK	0000010
+#define INPCK	0000020
+#define ISTRIP	0000040
+#define INLCR	0000100
+#define IGNCR	0000200
+#define ICRNL	0000400
+#define IUCLC	0001000
+#define IXON	0002000
+#define IXANY	0004000
+#define IXOFF	0010000
+#define IMAXBEL	0020000
+#define IUTF8	0040000
+
+/* c_oflag bits */
+#define OPOST	0000001
+#define OLCUC	0000002
+#define ONLCR	0000004
+#define OCRNL	0000010
+#define ONOCR	0000020
+#define ONLRET	0000040
+#define OFILL	0000100
+#define OFDEL	0000200
+#define NLDLY	0000400
+#define   NL0	0000000
+#define   NL1	0000400
+#define CRDLY	0003000
+#define   CR0	0000000
+#define   CR1	0001000
+#define   CR2	0002000
+#define   CR3	0003000
+#define TABDLY	0014000
+#define   TAB0	0000000
+#define   TAB1	0004000
+#define   TAB2	0010000
+#define   TAB3	0014000
+#define   XTABS	0014000
+#define BSDLY	0020000
+#define   BS0	0000000
+#define   BS1	0020000
+#define VTDLY	0040000
+#define   VT0	0000000
+#define   VT1	0040000
+#define FFDLY	0100000
+#define   FF0	0000000
+#define   FF1	0100000
+
+/* c_cflag bit meaning */
+#define CBAUD	0010017
+#define  B0	0000000		/* hang up */
+#define  B50	0000001
+#define  B75	0000002
+#define  B110	0000003
+#define  B134	0000004
+#define  B150	0000005
+#define  B200	0000006
+#define  B300	0000007
+#define  B600	0000010
+#define  B1200	0000011
+#define  B1800	0000012
+#define  B2400	0000013
+#define  B4800	0000014
+#define  B9600	0000015
+#define  B19200	0000016
+#define  B38400	0000017
+#define EXTA B19200
+#define EXTB B38400
+#define CSIZE	0000060
+#define   CS5	0000000
+#define   CS6	0000020
+#define   CS7	0000040
+#define   CS8	0000060
+#define CSTOPB	0000100
+#define CREAD	0000200
+#define PARENB	0000400
+#define PARODD	0001000
+#define HUPCL	0002000
+#define CLOCAL	0004000
+#define CBAUDEX 0010000
+#define	   BOTHER 0010000		/* non standard rate */
+#define    B57600 0010001
+#define   B115200 0010002
+#define   B230400 0010003
+#define   B460800 0010004
+#define   B500000 0010005
+#define   B576000 0010006
+#define   B921600 0010007
+#define  B1000000 0010010
+#define  B1152000 0010011
+#define  B1500000 0010012
+#define  B2000000 0010013
+#define  B2500000 0010014
+#define  B3000000 0010015
+#define  B3500000 0010016
+#define  B4000000 0010017
+#define CIBAUD	  002003600000	/* input baud rate */
+#define CMSPAR	  010000000000	/* mark or space (stick) parity */
+#define CRTSCTS	  020000000000	/* flow control */
+
+#define IBSHIFT	  16		/* Shift from CBAUD to CIBAUD */
+
+/* c_lflag bits */
+#define ISIG	0000001
+#define ICANON	0000002
+#define XCASE	0000004
+#define ECHO	0000010
+#define ECHOE	0000020
+#define ECHOK	0000040
+#define ECHONL	0000100
+#define NOFLSH	0000200
+#define TOSTOP	0000400
+#define ECHOCTL	0001000
+#define ECHOPRT	0002000
+#define ECHOKE	0004000
+#define FLUSHO	0010000
+#define PENDIN	0040000
+#define IEXTEN	0100000
+
+/* tcflow() and TCXONC use these */
+#define	TCOOFF		0
+#define	TCOON		1
+#define	TCIOFF		2
+#define	TCION		3
+
+/* tcflush() and TCFLSH use these */
+#define	TCIFLUSH	0
+#define	TCOFLUSH	1
+#define	TCIOFLUSH	2
+
+/* tcsetattr uses these */
+#define	TCSANOW		0
+#define	TCSADRAIN	1
+#define	TCSAFLUSH	2
+
+#endif /* ASM_X86__TERMBITS_H */
diff --git a/arch/x86/include/asm/termios.h b/arch/x86/include/asm/termios.h
new file mode 100644
index 000000000000..e235db248071
--- /dev/null
+++ b/arch/x86/include/asm/termios.h
@@ -0,0 +1,113 @@
+#ifndef ASM_X86__TERMIOS_H
+#define ASM_X86__TERMIOS_H
+
+#include <asm/termbits.h>
+#include <asm/ioctls.h>
+
+struct winsize {
+	unsigned short ws_row;
+	unsigned short ws_col;
+	unsigned short ws_xpixel;
+	unsigned short ws_ypixel;
+};
+
+#define NCC 8
+struct termio {
+	unsigned short c_iflag;		/* input mode flags */
+	unsigned short c_oflag;		/* output mode flags */
+	unsigned short c_cflag;		/* control mode flags */
+	unsigned short c_lflag;		/* local mode flags */
+	unsigned char c_line;		/* line discipline */
+	unsigned char c_cc[NCC];	/* control characters */
+};
+
+/* modem lines */
+#define TIOCM_LE	0x001
+#define TIOCM_DTR	0x002
+#define TIOCM_RTS	0x004
+#define TIOCM_ST	0x008
+#define TIOCM_SR	0x010
+#define TIOCM_CTS	0x020
+#define TIOCM_CAR	0x040
+#define TIOCM_RNG	0x080
+#define TIOCM_DSR	0x100
+#define TIOCM_CD	TIOCM_CAR
+#define TIOCM_RI	TIOCM_RNG
+#define TIOCM_OUT1	0x2000
+#define TIOCM_OUT2	0x4000
+#define TIOCM_LOOP	0x8000
+
+/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
+
+#ifdef __KERNEL__
+
+#include <asm/uaccess.h>
+
+/*	intr=^C		quit=^\		erase=del	kill=^U
+	eof=^D		vtime=\0	vmin=\1		sxtc=\0
+	start=^Q	stop=^S		susp=^Z		eol=\0
+	reprint=^R	discard=^U	werase=^W	lnext=^V
+	eol2=\0
+*/
+#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
+
+/*
+ * Translate a "termio" structure into a "termios". Ugh.
+ */
+#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
+	unsigned short __tmp; \
+	get_user(__tmp,&(termio)->x); \
+	*(unsigned short *) &(termios)->x = __tmp; \
+}
+
+static inline int user_termio_to_kernel_termios(struct ktermios *termios,
+						struct termio __user *termio)
+{
+	SET_LOW_TERMIOS_BITS(termios, termio, c_iflag);
+	SET_LOW_TERMIOS_BITS(termios, termio, c_oflag);
+	SET_LOW_TERMIOS_BITS(termios, termio, c_cflag);
+	SET_LOW_TERMIOS_BITS(termios, termio, c_lflag);
+	return copy_from_user(termios->c_cc, termio->c_cc, NCC);
+}
+
+/*
+ * Translate a "termios" structure into a "termio". Ugh.
+ */
+static inline int kernel_termios_to_user_termio(struct termio __user *termio,
+					    struct ktermios *termios)
+{
+	put_user((termios)->c_iflag, &(termio)->c_iflag);
+	put_user((termios)->c_oflag, &(termio)->c_oflag);
+	put_user((termios)->c_cflag, &(termio)->c_cflag);
+	put_user((termios)->c_lflag, &(termio)->c_lflag);
+	put_user((termios)->c_line,  &(termio)->c_line);
+	return copy_to_user((termio)->c_cc, (termios)->c_cc, NCC);
+}
+
+static inline int user_termios_to_kernel_termios(struct ktermios *k,
+						 struct termios2 __user *u)
+{
+	return copy_from_user(k, u, sizeof(struct termios2));
+}
+
+static inline int kernel_termios_to_user_termios(struct termios2 __user *u,
+						 struct ktermios *k)
+{
+	return copy_to_user(u, k, sizeof(struct termios2));
+}
+
+static inline int user_termios_to_kernel_termios_1(struct ktermios *k,
+						   struct termios __user *u)
+{
+	return copy_from_user(k, u, sizeof(struct termios));
+}
+
+static inline int kernel_termios_to_user_termios_1(struct termios __user *u,
+						   struct ktermios *k)
+{
+	return copy_to_user(u, k, sizeof(struct termios));
+}
+
+#endif	/* __KERNEL__ */
+
+#endif /* ASM_X86__TERMIOS_H */
diff --git a/arch/x86/include/asm/therm_throt.h b/arch/x86/include/asm/therm_throt.h
new file mode 100644
index 000000000000..1c7f57b6b66e
--- /dev/null
+++ b/arch/x86/include/asm/therm_throt.h
@@ -0,0 +1,9 @@
+#ifndef ASM_X86__THERM_THROT_H
+#define ASM_X86__THERM_THROT_H
+
+#include <asm/atomic.h>
+
+extern atomic_t therm_throt_en;
+int therm_throt_process(int curr);
+
+#endif /* ASM_X86__THERM_THROT_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
new file mode 100644
index 000000000000..3f4e52bb77f5
--- /dev/null
+++ b/arch/x86/include/asm/thread_info.h
@@ -0,0 +1,264 @@
+/* thread_info.h: low-level thread information
+ *
+ * Copyright (C) 2002  David Howells (dhowells@redhat.com)
+ * - Incorporating suggestions made by Linus Torvalds and Dave Miller
+ */
+
+#ifndef ASM_X86__THREAD_INFO_H
+#define ASM_X86__THREAD_INFO_H
+
+#include <linux/compiler.h>
+#include <asm/page.h>
+#include <asm/types.h>
+
+/*
+ * low level task data that entry.S needs immediate access to
+ * - this struct should fit entirely inside of one cache line
+ * - this struct shares the supervisor stack pages
+ */
+#ifndef __ASSEMBLY__
+struct task_struct;
+struct exec_domain;
+#include <asm/processor.h>
+
+struct thread_info {
+	struct task_struct	*task;		/* main task structure */
+	struct exec_domain	*exec_domain;	/* execution domain */
+	unsigned long		flags;		/* low level flags */
+	__u32			status;		/* thread synchronous flags */
+	__u32			cpu;		/* current CPU */
+	int			preempt_count;	/* 0 => preemptable,
+						   <0 => BUG */
+	mm_segment_t		addr_limit;
+	struct restart_block    restart_block;
+	void __user		*sysenter_return;
+#ifdef CONFIG_X86_32
+	unsigned long           previous_esp;   /* ESP of the previous stack in
+						   case of nested (IRQ) stacks
+						*/
+	__u8			supervisor_stack[0];
+#endif
+};
+
+#define INIT_THREAD_INFO(tsk)			\
+{						\
+	.task		= &tsk,			\
+	.exec_domain	= &default_exec_domain,	\
+	.flags		= 0,			\
+	.cpu		= 0,			\
+	.preempt_count	= 1,			\
+	.addr_limit	= KERNEL_DS,		\
+	.restart_block = {			\
+		.fn = do_no_restart_syscall,	\
+	},					\
+}
+
+#define init_thread_info	(init_thread_union.thread_info)
+#define init_stack		(init_thread_union.stack)
+
+#else /* !__ASSEMBLY__ */
+
+#include <asm/asm-offsets.h>
+
+#endif
+
+/*
+ * thread information flags
+ * - these are process state flags that various assembly files
+ *   may need to access
+ * - pending work-to-be-done flags are in LSW
+ * - other flags in MSW
+ * Warning: layout of LSW is hardcoded in entry.S
+ */
+#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
+#define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
+#define TIF_SIGPENDING		2	/* signal pending */
+#define TIF_NEED_RESCHED	3	/* rescheduling necessary */
+#define TIF_SINGLESTEP		4	/* reenable singlestep on user return*/
+#define TIF_IRET		5	/* force IRET */
+#define TIF_SYSCALL_EMU		6	/* syscall emulation active */
+#define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
+#define TIF_SECCOMP		8	/* secure computing */
+#define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
+#define TIF_NOTSC		16	/* TSC is not accessible in userland */
+#define TIF_IA32		17	/* 32bit process */
+#define TIF_FORK		18	/* ret_from_fork */
+#define TIF_ABI_PENDING		19
+#define TIF_MEMDIE		20
+#define TIF_DEBUG		21	/* uses debug registers */
+#define TIF_IO_BITMAP		22	/* uses I/O bitmap */
+#define TIF_FREEZE		23	/* is freezing for suspend */
+#define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
+#define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
+#define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
+#define TIF_BTS_TRACE_TS	27      /* record scheduling event timestamps */
+
+#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
+#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
+#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
+#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
+#define _TIF_IRET		(1 << TIF_IRET)
+#define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
+#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
+#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
+#define _TIF_NOTSC		(1 << TIF_NOTSC)
+#define _TIF_IA32		(1 << TIF_IA32)
+#define _TIF_FORK		(1 << TIF_FORK)
+#define _TIF_ABI_PENDING	(1 << TIF_ABI_PENDING)
+#define _TIF_DEBUG		(1 << TIF_DEBUG)
+#define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
+#define _TIF_FREEZE		(1 << TIF_FREEZE)
+#define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
+#define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
+#define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
+#define _TIF_BTS_TRACE_TS	(1 << TIF_BTS_TRACE_TS)
+
+/* work to do in syscall_trace_enter() */
+#define _TIF_WORK_SYSCALL_ENTRY	\
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \
+	 _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP)
+
+/* work to do in syscall_trace_leave() */
+#define _TIF_WORK_SYSCALL_EXIT	\
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP)
+
+/* work to do on interrupt/exception return */
+#define _TIF_WORK_MASK							\
+	(0x0000FFFF &							\
+	 ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|			\
+	   _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU))
+
+/* work to do on any return to user space */
+#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
+
+/* Only used for 64 bit */
+#define _TIF_DO_NOTIFY_MASK						\
+	(_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME)
+
+/* flags to check in __switch_to() */
+#define _TIF_WORK_CTXSW							\
+	(_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_BTS_TRACE_TS| \
+								_TIF_NOTSC)
+
+#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
+#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
+
+#define PREEMPT_ACTIVE		0x10000000
+
+/* thread information allocation */
+#ifdef CONFIG_DEBUG_STACK_USAGE
+#define THREAD_FLAGS (GFP_KERNEL | __GFP_ZERO)
+#else
+#define THREAD_FLAGS GFP_KERNEL
+#endif
+
+#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
+
+#define alloc_thread_info(tsk)						\
+	((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER))
+
+#ifdef CONFIG_X86_32
+
+#define STACK_WARN	(THREAD_SIZE/8)
+/*
+ * macros/functions for gaining access to the thread information structure
+ *
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#ifndef __ASSEMBLY__
+
+
+/* how to get the current stack pointer from C */
+register unsigned long current_stack_pointer asm("esp") __used;
+
+/* how to get the thread information struct from C */
+static inline struct thread_info *current_thread_info(void)
+{
+	return (struct thread_info *)
+		(current_stack_pointer & ~(THREAD_SIZE - 1));
+}
+
+#else /* !__ASSEMBLY__ */
+
+/* how to get the thread information struct from ASM */
+#define GET_THREAD_INFO(reg)	 \
+	movl $-THREAD_SIZE, reg; \
+	andl %esp, reg
+
+/* use this one if reg already contains %esp */
+#define GET_THREAD_INFO_WITH_ESP(reg) \
+	andl $-THREAD_SIZE, reg
+
+#endif
+
+#else /* X86_32 */
+
+#include <asm/pda.h>
+
+/*
+ * macros/functions for gaining access to the thread information structure
+ * preempt_count needs to be 1 initially, until the scheduler is functional.
+ */
+#ifndef __ASSEMBLY__
+static inline struct thread_info *current_thread_info(void)
+{
+	struct thread_info *ti;
+	ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
+	return ti;
+}
+
+/* do not use in interrupt context */
+static inline struct thread_info *stack_thread_info(void)
+{
+	struct thread_info *ti;
+	asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
+	return ti;
+}
+
+#else /* !__ASSEMBLY__ */
+
+/* how to get the thread information struct from ASM */
+#define GET_THREAD_INFO(reg) \
+	movq %gs:pda_kernelstack,reg ; \
+	subq $(THREAD_SIZE-PDA_STACKOFFSET),reg
+
+#endif
+
+#endif /* !X86_32 */
+
+/*
+ * Thread-synchronous status.
+ *
+ * This is different from the flags in that nobody else
+ * ever touches our thread-synchronous status, so we don't
+ * have to worry about atomic accesses.
+ */
+#define TS_USEDFPU		0x0001	/* FPU was used by this task
+					   this quantum (SMP) */
+#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
+#define TS_POLLING		0x0004	/* true if in idle loop
+					   and not sleeping */
+#define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal() */
+#define TS_XSAVE		0x0010	/* Use xsave/xrstor */
+
+#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
+
+#ifndef __ASSEMBLY__
+#define HAVE_SET_RESTORE_SIGMASK	1
+static inline void set_restore_sigmask(void)
+{
+	struct thread_info *ti = current_thread_info();
+	ti->status |= TS_RESTORE_SIGMASK;
+	set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags);
+}
+#endif	/* !__ASSEMBLY__ */
+
+#ifndef __ASSEMBLY__
+extern void arch_task_cache_init(void);
+extern void free_thread_info(struct thread_info *ti);
+extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
+#define arch_task_cache_init arch_task_cache_init
+#endif
+#endif /* ASM_X86__THREAD_INFO_H */
diff --git a/arch/x86/include/asm/time.h b/arch/x86/include/asm/time.h
new file mode 100644
index 000000000000..3e724eef7ac4
--- /dev/null
+++ b/arch/x86/include/asm/time.h
@@ -0,0 +1,63 @@
+#ifndef ASM_X86__TIME_H
+#define ASM_X86__TIME_H
+
+extern void hpet_time_init(void);
+
+#include <asm/mc146818rtc.h>
+#ifdef CONFIG_X86_32
+#include <linux/efi.h>
+
+static inline unsigned long native_get_wallclock(void)
+{
+	unsigned long retval;
+
+	if (efi_enabled)
+		retval = efi_get_time();
+	else
+		retval = mach_get_cmos_time();
+
+	return retval;
+}
+
+static inline int native_set_wallclock(unsigned long nowtime)
+{
+	int retval;
+
+	if (efi_enabled)
+		retval = efi_set_rtc_mmss(nowtime);
+	else
+		retval = mach_set_rtc_mmss(nowtime);
+
+	return retval;
+}
+
+#else
+extern void native_time_init_hook(void);
+
+static inline unsigned long native_get_wallclock(void)
+{
+	return mach_get_cmos_time();
+}
+
+static inline int native_set_wallclock(unsigned long nowtime)
+{
+	return mach_set_rtc_mmss(nowtime);
+}
+
+#endif
+
+extern void time_init(void);
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else /* !CONFIG_PARAVIRT */
+
+#define get_wallclock() native_get_wallclock()
+#define set_wallclock(x) native_set_wallclock(x)
+#define choose_time_init() hpet_time_init
+
+#endif /* CONFIG_PARAVIRT */
+
+extern unsigned long __init calibrate_cpu(void);
+
+#endif /* ASM_X86__TIME_H */
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
new file mode 100644
index 000000000000..d0babce4b47a
--- /dev/null
+++ b/arch/x86/include/asm/timer.h
@@ -0,0 +1,66 @@
+#ifndef ASM_X86__TIMER_H
+#define ASM_X86__TIMER_H
+#include <linux/init.h>
+#include <linux/pm.h>
+#include <linux/percpu.h>
+
+#define TICK_SIZE (tick_nsec / 1000)
+
+unsigned long long native_sched_clock(void);
+unsigned long native_calibrate_tsc(void);
+
+#ifdef CONFIG_X86_32
+extern int timer_ack;
+extern int recalibrate_cpu_khz(void);
+#endif /* CONFIG_X86_32 */
+
+extern int no_timer_check;
+
+#ifndef CONFIG_PARAVIRT
+#define calibrate_tsc() native_calibrate_tsc()
+#endif
+
+/* Accelerators for sched_clock()
+ * convert from cycles(64bits) => nanoseconds (64bits)
+ *  basic equation:
+ *		ns = cycles / (freq / ns_per_sec)
+ *		ns = cycles * (ns_per_sec / freq)
+ *		ns = cycles * (10^9 / (cpu_khz * 10^3))
+ *		ns = cycles * (10^6 / cpu_khz)
+ *
+ *	Then we use scaling math (suggested by george@mvista.com) to get:
+ *		ns = cycles * (10^6 * SC / cpu_khz) / SC
+ *		ns = cycles * cyc2ns_scale / SC
+ *
+ *	And since SC is a constant power of two, we can convert the div
+ *  into a shift.
+ *
+ *  We can use khz divisor instead of mhz to keep a better precision, since
+ *  cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
+ *  (mathieu.desnoyers@polymtl.ca)
+ *
+ *			-johnstul@us.ibm.com "math is hard, lets go shopping!"
+ */
+
+DECLARE_PER_CPU(unsigned long, cyc2ns);
+
+#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
+
+static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
+{
+	return cyc * per_cpu(cyc2ns, smp_processor_id()) >> CYC2NS_SCALE_FACTOR;
+}
+
+static inline unsigned long long cycles_2_ns(unsigned long long cyc)
+{
+	unsigned long long ns;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	ns = __cycles_2_ns(cyc);
+	local_irq_restore(flags);
+
+	return ns;
+}
+
+#endif /* ASM_X86__TIMER_H */
diff --git a/arch/x86/include/asm/timex.h b/arch/x86/include/asm/timex.h
new file mode 100644
index 000000000000..d1ce2416a5da
--- /dev/null
+++ b/arch/x86/include/asm/timex.h
@@ -0,0 +1,19 @@
+/* x86 architecture timex specifications */
+#ifndef ASM_X86__TIMEX_H
+#define ASM_X86__TIMEX_H
+
+#include <asm/processor.h>
+#include <asm/tsc.h>
+
+#ifdef CONFIG_X86_ELAN
+#  define PIT_TICK_RATE 1189200 /* AMD Elan has different frequency! */
+#elif defined(CONFIG_X86_RDC321X)
+#  define PIT_TICK_RATE 1041667 /* Underlying HZ for R8610 */
+#else
+#  define PIT_TICK_RATE 1193182 /* Underlying HZ */
+#endif
+#define CLOCK_TICK_RATE	PIT_TICK_RATE
+
+#define ARCH_HAS_READ_CURRENT_TIMER
+
+#endif /* ASM_X86__TIMEX_H */
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
new file mode 100644
index 000000000000..db36e9e89e87
--- /dev/null
+++ b/arch/x86/include/asm/tlb.h
@@ -0,0 +1,11 @@
+#ifndef ASM_X86__TLB_H
+#define ASM_X86__TLB_H
+
+#define tlb_start_vma(tlb, vma) do { } while (0)
+#define tlb_end_vma(tlb, vma) do { } while (0)
+#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
+#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+
+#include <asm-generic/tlb.h>
+
+#endif /* ASM_X86__TLB_H */
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
new file mode 100644
index 000000000000..3cdd08b5bdb7
--- /dev/null
+++ b/arch/x86/include/asm/tlbflush.h
@@ -0,0 +1,178 @@
+#ifndef ASM_X86__TLBFLUSH_H
+#define ASM_X86__TLBFLUSH_H
+
+#include <linux/mm.h>
+#include <linux/sched.h>
+
+#include <asm/processor.h>
+#include <asm/system.h>
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+#define __flush_tlb() __native_flush_tlb()
+#define __flush_tlb_global() __native_flush_tlb_global()
+#define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
+#endif
+
+static inline void __native_flush_tlb(void)
+{
+	write_cr3(read_cr3());
+}
+
+static inline void __native_flush_tlb_global(void)
+{
+	unsigned long flags;
+	unsigned long cr4;
+
+	/*
+	 * Read-modify-write to CR4 - protect it from preemption and
+	 * from interrupts. (Use the raw variant because this code can
+	 * be called from deep inside debugging code.)
+	 */
+	raw_local_irq_save(flags);
+
+	cr4 = read_cr4();
+	/* clear PGE */
+	write_cr4(cr4 & ~X86_CR4_PGE);
+	/* write old PGE again and flush TLBs */
+	write_cr4(cr4);
+
+	raw_local_irq_restore(flags);
+}
+
+static inline void __native_flush_tlb_single(unsigned long addr)
+{
+	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
+}
+
+static inline void __flush_tlb_all(void)
+{
+	if (cpu_has_pge)
+		__flush_tlb_global();
+	else
+		__flush_tlb();
+}
+
+static inline void __flush_tlb_one(unsigned long addr)
+{
+	if (cpu_has_invlpg)
+		__flush_tlb_single(addr);
+	else
+		__flush_tlb();
+}
+
+#ifdef CONFIG_X86_32
+# define TLB_FLUSH_ALL	0xffffffff
+#else
+# define TLB_FLUSH_ALL	-1ULL
+#endif
+
+/*
+ * TLB flushing:
+ *
+ *  - flush_tlb() flushes the current mm struct TLBs
+ *  - flush_tlb_all() flushes all processes TLBs
+ *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
+ *  - flush_tlb_page(vma, vmaddr) flushes one page
+ *  - flush_tlb_range(vma, start, end) flushes a range of pages
+ *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
+ *  - flush_tlb_others(cpumask, mm, va) flushes TLBs on other cpus
+ *
+ * ..but the i386 has somewhat limited tlb flushing capabilities,
+ * and page-granular flushes are available only on i486 and up.
+ *
+ * x86-64 can only flush individual pages or full VMs. For a range flush
+ * we always do the full VM. Might be worth trying if for a small
+ * range a few INVLPGs in a row are a win.
+ */
+
+#ifndef CONFIG_SMP
+
+#define flush_tlb() __flush_tlb()
+#define flush_tlb_all() __flush_tlb_all()
+#define local_flush_tlb() __flush_tlb()
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+	if (mm == current->active_mm)
+		__flush_tlb();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma,
+				  unsigned long addr)
+{
+	if (vma->vm_mm == current->active_mm)
+		__flush_tlb_one(addr);
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+	if (vma->vm_mm == current->active_mm)
+		__flush_tlb();
+}
+
+static inline void native_flush_tlb_others(const cpumask_t *cpumask,
+					   struct mm_struct *mm,
+					   unsigned long va)
+{
+}
+
+static inline void reset_lazy_tlbstate(void)
+{
+}
+
+#else  /* SMP */
+
+#include <asm/smp.h>
+
+#define local_flush_tlb() __flush_tlb()
+
+extern void flush_tlb_all(void);
+extern void flush_tlb_current_task(void);
+extern void flush_tlb_mm(struct mm_struct *);
+extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
+
+#define flush_tlb()	flush_tlb_current_task()
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+	flush_tlb_mm(vma->vm_mm);
+}
+
+void native_flush_tlb_others(const cpumask_t *cpumask, struct mm_struct *mm,
+			     unsigned long va);
+
+#define TLBSTATE_OK	1
+#define TLBSTATE_LAZY	2
+
+#ifdef CONFIG_X86_32
+struct tlb_state {
+	struct mm_struct *active_mm;
+	int state;
+	char __cacheline_padding[L1_CACHE_BYTES-8];
+};
+DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
+
+void reset_lazy_tlbstate(void);
+#else
+static inline void reset_lazy_tlbstate(void)
+{
+}
+#endif
+
+#endif	/* SMP */
+
+#ifndef CONFIG_PARAVIRT
+#define flush_tlb_others(mask, mm, va)	native_flush_tlb_others(&mask, mm, va)
+#endif
+
+static inline void flush_tlb_kernel_range(unsigned long start,
+					  unsigned long end)
+{
+	flush_tlb_all();
+}
+
+#endif /* ASM_X86__TLBFLUSH_H */
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
new file mode 100644
index 000000000000..7eca9bc022b2
--- /dev/null
+++ b/arch/x86/include/asm/topology.h
@@ -0,0 +1,258 @@
+/*
+ * Written by: Matthew Dobson, IBM Corporation
+ *
+ * Copyright (C) 2002, IBM Corp.
+ *
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to <colpatch@us.ibm.com>
+ */
+#ifndef ASM_X86__TOPOLOGY_H
+#define ASM_X86__TOPOLOGY_H
+
+#ifdef CONFIG_X86_32
+# ifdef CONFIG_X86_HT
+#  define ENABLE_TOPO_DEFINES
+# endif
+#else
+# ifdef CONFIG_SMP
+#  define ENABLE_TOPO_DEFINES
+# endif
+#endif
+
+/* Node not present */
+#define NUMA_NO_NODE	(-1)
+
+#ifdef CONFIG_NUMA
+#include <linux/cpumask.h>
+#include <asm/mpspec.h>
+
+#ifdef CONFIG_X86_32
+
+/* Mappings between node number and cpus on that node. */
+extern cpumask_t node_to_cpumask_map[];
+
+/* Mappings between logical cpu number and node number */
+extern int cpu_to_node_map[];
+
+/* Returns the number of the node containing CPU 'cpu' */
+static inline int cpu_to_node(int cpu)
+{
+	return cpu_to_node_map[cpu];
+}
+#define early_cpu_to_node(cpu)	cpu_to_node(cpu)
+
+/* Returns a bitmask of CPUs on Node 'node'.
+ *
+ * Side note: this function creates the returned cpumask on the stack
+ * so with a high NR_CPUS count, excessive stack space is used.  The
+ * node_to_cpumask_ptr function should be used whenever possible.
+ */
+static inline cpumask_t node_to_cpumask(int node)
+{
+	return node_to_cpumask_map[node];
+}
+
+#else /* CONFIG_X86_64 */
+
+/* Mappings between node number and cpus on that node. */
+extern cpumask_t *node_to_cpumask_map;
+
+/* Mappings between logical cpu number and node number */
+DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
+
+/* Returns the number of the current Node. */
+#define numa_node_id()		read_pda(nodenumber)
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+extern int cpu_to_node(int cpu);
+extern int early_cpu_to_node(int cpu);
+extern const cpumask_t *_node_to_cpumask_ptr(int node);
+extern cpumask_t node_to_cpumask(int node);
+
+#else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+/* Returns the number of the node containing CPU 'cpu' */
+static inline int cpu_to_node(int cpu)
+{
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
+
+/* Same function but used if called before per_cpu areas are setup */
+static inline int early_cpu_to_node(int cpu)
+{
+	if (early_per_cpu_ptr(x86_cpu_to_node_map))
+		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
+
+/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline const cpumask_t *_node_to_cpumask_ptr(int node)
+{
+	return &node_to_cpumask_map[node];
+}
+
+/* Returns a bitmask of CPUs on Node 'node'. */
+static inline cpumask_t node_to_cpumask(int node)
+{
+	return node_to_cpumask_map[node];
+}
+
+#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+/* Replace default node_to_cpumask_ptr with optimized version */
+#define node_to_cpumask_ptr(v, node)		\
+		const cpumask_t *v = _node_to_cpumask_ptr(node)
+
+#define node_to_cpumask_ptr_next(v, node)	\
+			   v = _node_to_cpumask_ptr(node)
+
+#endif /* CONFIG_X86_64 */
+
+/*
+ * Returns the number of the node containing Node 'node'. This
+ * architecture is flat, so it is a pretty simple function!
+ */
+#define parent_node(node) (node)
+
+#define pcibus_to_node(bus) __pcibus_to_node(bus)
+#define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus)
+
+#ifdef CONFIG_X86_32
+extern unsigned long node_start_pfn[];
+extern unsigned long node_end_pfn[];
+extern unsigned long node_remap_size[];
+#define node_has_online_mem(nid) (node_start_pfn[nid] != node_end_pfn[nid])
+
+# define SD_CACHE_NICE_TRIES	1
+# define SD_IDLE_IDX		1
+# define SD_NEWIDLE_IDX		2
+# define SD_FORKEXEC_IDX	0
+
+#else
+
+# define SD_CACHE_NICE_TRIES	2
+# define SD_IDLE_IDX		2
+# define SD_NEWIDLE_IDX		2
+# define SD_FORKEXEC_IDX	1
+
+#endif
+
+/* sched_domains SD_NODE_INIT for NUMAQ machines */
+#define SD_NODE_INIT (struct sched_domain) {		\
+	.min_interval		= 8,			\
+	.max_interval		= 32,			\
+	.busy_factor		= 32,			\
+	.imbalance_pct		= 125,			\
+	.cache_nice_tries	= SD_CACHE_NICE_TRIES,	\
+	.busy_idx		= 3,			\
+	.idle_idx		= SD_IDLE_IDX,		\
+	.newidle_idx		= SD_NEWIDLE_IDX,	\
+	.wake_idx		= 1,			\
+	.forkexec_idx		= SD_FORKEXEC_IDX,	\
+	.flags			= SD_LOAD_BALANCE	\
+				| SD_BALANCE_EXEC	\
+				| SD_BALANCE_FORK	\
+				| SD_SERIALIZE		\
+				| SD_WAKE_BALANCE,	\
+	.last_balance		= jiffies,		\
+	.balance_interval	= 1,			\
+}
+
+#ifdef CONFIG_X86_64_ACPI_NUMA
+extern int __node_distance(int, int);
+#define node_distance(a, b) __node_distance(a, b)
+#endif
+
+#else /* !CONFIG_NUMA */
+
+#define numa_node_id()		0
+#define	cpu_to_node(cpu)	0
+#define	early_cpu_to_node(cpu)	0
+
+static inline const cpumask_t *_node_to_cpumask_ptr(int node)
+{
+	return &cpu_online_map;
+}
+static inline cpumask_t node_to_cpumask(int node)
+{
+	return cpu_online_map;
+}
+static inline int node_to_first_cpu(int node)
+{
+	return first_cpu(cpu_online_map);
+}
+
+/* Replace default node_to_cpumask_ptr with optimized version */
+#define node_to_cpumask_ptr(v, node)		\
+		const cpumask_t *v = _node_to_cpumask_ptr(node)
+
+#define node_to_cpumask_ptr_next(v, node)	\
+			   v = _node_to_cpumask_ptr(node)
+#endif
+
+#include <asm-generic/topology.h>
+
+#ifdef CONFIG_NUMA
+/* Returns the number of the first CPU on Node 'node'. */
+static inline int node_to_first_cpu(int node)
+{
+	node_to_cpumask_ptr(mask, node);
+	return first_cpu(*mask);
+}
+#endif
+
+extern cpumask_t cpu_coregroup_map(int cpu);
+
+#ifdef ENABLE_TOPO_DEFINES
+#define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
+#define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
+#define topology_core_siblings(cpu)		(per_cpu(cpu_core_map, cpu))
+#define topology_thread_siblings(cpu)		(per_cpu(cpu_sibling_map, cpu))
+
+/* indicates that pointers to the topology cpumask_t maps are valid */
+#define arch_provides_topology_pointers		yes
+#endif
+
+static inline void arch_fix_phys_package_id(int num, u32 slot)
+{
+}
+
+struct pci_bus;
+void set_pci_bus_resources_arch_default(struct pci_bus *b);
+
+#ifdef CONFIG_SMP
+#define mc_capable()			(boot_cpu_data.x86_max_cores > 1)
+#define smt_capable()			(smp_num_siblings > 1)
+#endif
+
+#ifdef CONFIG_NUMA
+extern int get_mp_bus_to_node(int busnum);
+extern void set_mp_bus_to_node(int busnum, int node);
+#else
+static inline int get_mp_bus_to_node(int busnum)
+{
+	return 0;
+}
+static inline void set_mp_bus_to_node(int busnum, int node)
+{
+}
+#endif
+
+#endif /* ASM_X86__TOPOLOGY_H */
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
new file mode 100644
index 000000000000..0406bbd898a9
--- /dev/null
+++ b/arch/x86/include/asm/trampoline.h
@@ -0,0 +1,21 @@
+#ifndef ASM_X86__TRAMPOLINE_H
+#define ASM_X86__TRAMPOLINE_H
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Trampoline 80x86 program as an array.
+ */
+extern const unsigned char trampoline_data [];
+extern const unsigned char trampoline_end  [];
+extern unsigned char *trampoline_base;
+
+extern unsigned long init_rsp;
+extern unsigned long initial_code;
+
+#define TRAMPOLINE_BASE 0x6000
+extern unsigned long setup_trampoline(void);
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* ASM_X86__TRAMPOLINE_H */
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
new file mode 100644
index 000000000000..6c3dc2c65751
--- /dev/null
+++ b/arch/x86/include/asm/traps.h
@@ -0,0 +1,81 @@
+#ifndef ASM_X86__TRAPS_H
+#define ASM_X86__TRAPS_H
+
+#include <asm/debugreg.h>
+
+#ifdef CONFIG_X86_32
+#define dotraplinkage
+#else
+#define dotraplinkage asmlinkage
+#endif
+
+asmlinkage void divide_error(void);
+asmlinkage void debug(void);
+asmlinkage void nmi(void);
+asmlinkage void int3(void);
+asmlinkage void overflow(void);
+asmlinkage void bounds(void);
+asmlinkage void invalid_op(void);
+asmlinkage void device_not_available(void);
+#ifdef CONFIG_X86_64
+asmlinkage void double_fault(void);
+#endif
+asmlinkage void coprocessor_segment_overrun(void);
+asmlinkage void invalid_TSS(void);
+asmlinkage void segment_not_present(void);
+asmlinkage void stack_segment(void);
+asmlinkage void general_protection(void);
+asmlinkage void page_fault(void);
+asmlinkage void spurious_interrupt_bug(void);
+asmlinkage void coprocessor_error(void);
+asmlinkage void alignment_check(void);
+#ifdef CONFIG_X86_MCE
+asmlinkage void machine_check(void);
+#endif /* CONFIG_X86_MCE */
+asmlinkage void simd_coprocessor_error(void);
+
+dotraplinkage void do_divide_error(struct pt_regs *, long);
+dotraplinkage void do_debug(struct pt_regs *, long);
+dotraplinkage void do_nmi(struct pt_regs *, long);
+dotraplinkage void do_int3(struct pt_regs *, long);
+dotraplinkage void do_overflow(struct pt_regs *, long);
+dotraplinkage void do_bounds(struct pt_regs *, long);
+dotraplinkage void do_invalid_op(struct pt_regs *, long);
+dotraplinkage void do_device_not_available(struct pt_regs *, long);
+dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long);
+dotraplinkage void do_invalid_TSS(struct pt_regs *, long);
+dotraplinkage void do_segment_not_present(struct pt_regs *, long);
+dotraplinkage void do_stack_segment(struct pt_regs *, long);
+dotraplinkage void do_general_protection(struct pt_regs *, long);
+dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
+dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long);
+dotraplinkage void do_coprocessor_error(struct pt_regs *, long);
+dotraplinkage void do_alignment_check(struct pt_regs *, long);
+#ifdef CONFIG_X86_MCE
+dotraplinkage void do_machine_check(struct pt_regs *, long);
+#endif
+dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
+#ifdef CONFIG_X86_32
+dotraplinkage void do_iret_error(struct pt_regs *, long);
+#endif
+
+static inline int get_si_code(unsigned long condition)
+{
+	if (condition & DR_STEP)
+		return TRAP_TRACE;
+	else if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3))
+		return TRAP_HWBKPT;
+	else
+		return TRAP_BRKPT;
+}
+
+extern int panic_on_unrecovered_nmi;
+extern int kstack_depth_to_print;
+
+#ifdef CONFIG_X86_32
+void math_error(void __user *);
+unsigned long patch_espfix_desc(unsigned long, unsigned long);
+asmlinkage void math_emulate(long);
+#endif
+
+#endif /* ASM_X86__TRAPS_H */
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
new file mode 100644
index 000000000000..ad0f5c41e78c
--- /dev/null
+++ b/arch/x86/include/asm/tsc.h
@@ -0,0 +1,62 @@
+/*
+ * x86 TSC related functions
+ */
+#ifndef ASM_X86__TSC_H
+#define ASM_X86__TSC_H
+
+#include <asm/processor.h>
+
+#define NS_SCALE	10 /* 2^10, carefully chosen */
+#define US_SCALE	32 /* 2^32, arbitralrily chosen */
+
+/*
+ * Standard way to access the cycle counter.
+ */
+typedef unsigned long long cycles_t;
+
+extern unsigned int cpu_khz;
+extern unsigned int tsc_khz;
+
+extern void disable_TSC(void);
+
+static inline cycles_t get_cycles(void)
+{
+	unsigned long long ret = 0;
+
+#ifndef CONFIG_X86_TSC
+	if (!cpu_has_tsc)
+		return 0;
+#endif
+	rdtscll(ret);
+
+	return ret;
+}
+
+static __always_inline cycles_t vget_cycles(void)
+{
+	/*
+	 * We only do VDSOs on TSC capable CPUs, so this shouldnt
+	 * access boot_cpu_data (which is not VDSO-safe):
+	 */
+#ifndef CONFIG_X86_TSC
+	if (!cpu_has_tsc)
+		return 0;
+#endif
+	return (cycles_t)__native_read_tsc();
+}
+
+extern void tsc_init(void);
+extern void mark_tsc_unstable(char *reason);
+extern int unsynchronized_tsc(void);
+int check_tsc_unstable(void);
+
+/*
+ * Boot-time check whether the TSCs are synchronized across
+ * all CPUs/cores:
+ */
+extern void check_tsc_sync_source(int cpu);
+extern void check_tsc_sync_target(void);
+
+extern int notsc_setup(char *);
+
+#endif /* ASM_X86__TSC_H */
diff --git a/arch/x86/include/asm/types.h b/arch/x86/include/asm/types.h
new file mode 100644
index 000000000000..e78b52e17444
--- /dev/null
+++ b/arch/x86/include/asm/types.h
@@ -0,0 +1,36 @@
+#ifndef ASM_X86__TYPES_H
+#define ASM_X86__TYPES_H
+
+#include <asm-generic/int-ll64.h>
+
+#ifndef __ASSEMBLY__
+
+typedef unsigned short umode_t;
+
+#endif /* __ASSEMBLY__ */
+
+/*
+ * These aren't exported outside the kernel to avoid name space clashes
+ */
+#ifdef __KERNEL__
+
+#ifdef CONFIG_X86_32
+# define BITS_PER_LONG 32
+#else
+# define BITS_PER_LONG 64
+#endif
+
+#ifndef __ASSEMBLY__
+
+typedef u64 dma64_addr_t;
+#if defined(CONFIG_X86_64) || defined(CONFIG_HIGHMEM64G)
+/* DMA addresses come in 32-bit and 64-bit flavours. */
+typedef u64 dma_addr_t;
+#else
+typedef u32 dma_addr_t;
+#endif
+
+#endif /* __ASSEMBLY__ */
+#endif /* __KERNEL__ */
+
+#endif /* ASM_X86__TYPES_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
new file mode 100644
index 000000000000..48ebc0ad40ec
--- /dev/null
+++ b/arch/x86/include/asm/uaccess.h
@@ -0,0 +1,454 @@
+#ifndef ASM_X86__UACCESS_H
+#define ASM_X86__UACCESS_H
+/*
+ * User space memory access functions
+ */
+#include <linux/errno.h>
+#include <linux/compiler.h>
+#include <linux/thread_info.h>
+#include <linux/prefetch.h>
+#include <linux/string.h>
+#include <asm/asm.h>
+#include <asm/page.h>
+
+#define VERIFY_READ 0
+#define VERIFY_WRITE 1
+
+/*
+ * The fs value determines whether argument validity checking should be
+ * performed or not.  If get_fs() == USER_DS, checking is performed, with
+ * get_fs() == KERNEL_DS, checking is bypassed.
+ *
+ * For historical reasons, these macros are grossly misnamed.
+ */
+
+#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
+
+#define KERNEL_DS	MAKE_MM_SEG(-1UL)
+#define USER_DS		MAKE_MM_SEG(PAGE_OFFSET)
+
+#define get_ds()	(KERNEL_DS)
+#define get_fs()	(current_thread_info()->addr_limit)
+#define set_fs(x)	(current_thread_info()->addr_limit = (x))
+
+#define segment_eq(a, b)	((a).seg == (b).seg)
+
+#define __addr_ok(addr)					\
+	((unsigned long __force)(addr) <		\
+	 (current_thread_info()->addr_limit.seg))
+
+/*
+ * Test whether a block of memory is a valid user space address.
+ * Returns 0 if the range is valid, nonzero otherwise.
+ *
+ * This is equivalent to the following test:
+ * (u33)addr + (u33)size >= (u33)current->addr_limit.seg (u65 for x86_64)
+ *
+ * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
+ */
+
+#define __range_not_ok(addr, size)					\
+({									\
+	unsigned long flag, roksum;					\
+	__chk_user_ptr(addr);						\
+	asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"		\
+	    : "=&r" (flag), "=r" (roksum)				\
+	    : "1" (addr), "g" ((long)(size)),				\
+	      "rm" (current_thread_info()->addr_limit.seg));		\
+	flag;								\
+})
+
+/**
+ * access_ok: - Checks if a user space pointer is valid
+ * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE.  Note that
+ *        %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe
+ *        to write to a block, it is always safe to read from it.
+ * @addr: User space pointer to start of block to check
+ * @size: Size of block to check
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Checks if a pointer to a block of memory in user space is valid.
+ *
+ * Returns true (nonzero) if the memory block may be valid, false (zero)
+ * if it is definitely invalid.
+ *
+ * Note that, depending on architecture, this function probably just
+ * checks that the pointer is in the user space range - after calling
+ * this function, memory access functions may still return -EFAULT.
+ */
+#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
+
+/*
+ * The exception table consists of pairs of addresses: the first is the
+ * address of an instruction that is allowed to fault, and the second is
+ * the address at which the program should continue.  No registers are
+ * modified, so it is entirely up to the continuation code to figure out
+ * what to do.
+ *
+ * All the routines below use bits of fixup code that are out of line
+ * with the main instruction path.  This means when everything is well,
+ * we don't even have to jump over them.  Further, they do not intrude
+ * on our cache or tlb entries.
+ */
+
+struct exception_table_entry {
+	unsigned long insn, fixup;
+};
+
+extern int fixup_exception(struct pt_regs *regs);
+
+/*
+ * These are the main single-value transfer routines.  They automatically
+ * use the right size if we just have the right pointer type.
+ *
+ * This gets kind of ugly. We want to return _two_ values in "get_user()"
+ * and yet we don't want to do any pointers, because that is too much
+ * of a performance impact. Thus we have a few rather ugly macros here,
+ * and hide all the ugliness from the user.
+ *
+ * The "__xxx" versions of the user access functions are versions that
+ * do not verify the address space, that must have been done previously
+ * with a separate "access_ok()" call (this is used when we do multiple
+ * accesses to the same area of user memory).
+ */
+
+extern int __get_user_1(void);
+extern int __get_user_2(void);
+extern int __get_user_4(void);
+extern int __get_user_8(void);
+extern int __get_user_bad(void);
+
+#define __get_user_x(size, ret, x, ptr)		      \
+	asm volatile("call __get_user_" #size	      \
+		     : "=a" (ret),"=d" (x)	      \
+		     : "0" (ptr))		      \
+
+/* Careful: we have to cast the result to the type of the pointer
+ * for sign reasons */
+
+/**
+ * get_user: - Get a simple variable from user space.
+ * @x:   Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+#ifdef CONFIG_X86_32
+#define __get_user_8(__ret_gu, __val_gu, ptr)				\
+		__get_user_x(X, __ret_gu, __val_gu, ptr)
+#else
+#define __get_user_8(__ret_gu, __val_gu, ptr)				\
+		__get_user_x(8, __ret_gu, __val_gu, ptr)
+#endif
+
+#define get_user(x, ptr)						\
+({									\
+	int __ret_gu;							\
+	unsigned long __val_gu;						\
+	__chk_user_ptr(ptr);						\
+	switch (sizeof(*(ptr))) {					\
+	case 1:								\
+		__get_user_x(1, __ret_gu, __val_gu, ptr);		\
+		break;							\
+	case 2:								\
+		__get_user_x(2, __ret_gu, __val_gu, ptr);		\
+		break;							\
+	case 4:								\
+		__get_user_x(4, __ret_gu, __val_gu, ptr);		\
+		break;							\
+	case 8:								\
+		__get_user_8(__ret_gu, __val_gu, ptr);			\
+		break;							\
+	default:							\
+		__get_user_x(X, __ret_gu, __val_gu, ptr);		\
+		break;							\
+	}								\
+	(x) = (__typeof__(*(ptr)))__val_gu;				\
+	__ret_gu;							\
+})
+
+#define __put_user_x(size, x, ptr, __ret_pu)			\
+	asm volatile("call __put_user_" #size : "=a" (__ret_pu)	\
+		     :"0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
+
+
+
+#ifdef CONFIG_X86_32
+#define __put_user_u64(x, addr, err)					\
+	asm volatile("1:	movl %%eax,0(%2)\n"			\
+		     "2:	movl %%edx,4(%2)\n"			\
+		     "3:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "4:	movl %3,%0\n"				\
+		     "	jmp 3b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 4b)				\
+		     _ASM_EXTABLE(2b, 4b)				\
+		     : "=r" (err)					\
+		     : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err))
+
+#define __put_user_x8(x, ptr, __ret_pu)				\
+	asm volatile("call __put_user_8" : "=a" (__ret_pu)	\
+		     : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
+#else
+#define __put_user_u64(x, ptr, retval) \
+	__put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT)
+#define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu)
+#endif
+
+extern void __put_user_bad(void);
+
+/*
+ * Strange magic calling convention: pointer in %ecx,
+ * value in %eax(:%edx), return value in %eax. clobbers %rbx
+ */
+extern void __put_user_1(void);
+extern void __put_user_2(void);
+extern void __put_user_4(void);
+extern void __put_user_8(void);
+
+#ifdef CONFIG_X86_WP_WORKS_OK
+
+/**
+ * put_user: - Write a simple value into user space.
+ * @x:   Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+#define put_user(x, ptr)					\
+({								\
+	int __ret_pu;						\
+	__typeof__(*(ptr)) __pu_val;				\
+	__chk_user_ptr(ptr);					\
+	__pu_val = x;						\
+	switch (sizeof(*(ptr))) {				\
+	case 1:							\
+		__put_user_x(1, __pu_val, ptr, __ret_pu);	\
+		break;						\
+	case 2:							\
+		__put_user_x(2, __pu_val, ptr, __ret_pu);	\
+		break;						\
+	case 4:							\
+		__put_user_x(4, __pu_val, ptr, __ret_pu);	\
+		break;						\
+	case 8:							\
+		__put_user_x8(__pu_val, ptr, __ret_pu);		\
+		break;						\
+	default:						\
+		__put_user_x(X, __pu_val, ptr, __ret_pu);	\
+		break;						\
+	}							\
+	__ret_pu;						\
+})
+
+#define __put_user_size(x, ptr, size, retval, errret)			\
+do {									\
+	retval = 0;							\
+	__chk_user_ptr(ptr);						\
+	switch (size) {							\
+	case 1:								\
+		__put_user_asm(x, ptr, retval, "b", "b", "iq", errret);	\
+		break;							\
+	case 2:								\
+		__put_user_asm(x, ptr, retval, "w", "w", "ir", errret);	\
+		break;							\
+	case 4:								\
+		__put_user_asm(x, ptr, retval, "l", "k",  "ir", errret);\
+		break;							\
+	case 8:								\
+		__put_user_u64((__typeof__(*ptr))(x), ptr, retval);	\
+		break;							\
+	default:							\
+		__put_user_bad();					\
+	}								\
+} while (0)
+
+#else
+
+#define __put_user_size(x, ptr, size, retval, errret)			\
+do {									\
+	__typeof__(*(ptr))__pus_tmp = x;				\
+	retval = 0;							\
+									\
+	if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, size) != 0))	\
+		retval = errret;					\
+} while (0)
+
+#define put_user(x, ptr)					\
+({								\
+	int __ret_pu;						\
+	__typeof__(*(ptr))__pus_tmp = x;			\
+	__ret_pu = 0;						\
+	if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp,		\
+				       sizeof(*(ptr))) != 0))	\
+		__ret_pu = -EFAULT;				\
+	__ret_pu;						\
+})
+#endif
+
+#ifdef CONFIG_X86_32
+#define __get_user_asm_u64(x, ptr, retval, errret)	(x) = __get_user_bad()
+#else
+#define __get_user_asm_u64(x, ptr, retval, errret) \
+	 __get_user_asm(x, ptr, retval, "q", "", "=r", errret)
+#endif
+
+#define __get_user_size(x, ptr, size, retval, errret)			\
+do {									\
+	retval = 0;							\
+	__chk_user_ptr(ptr);						\
+	switch (size) {							\
+	case 1:								\
+		__get_user_asm(x, ptr, retval, "b", "b", "=q", errret);	\
+		break;							\
+	case 2:								\
+		__get_user_asm(x, ptr, retval, "w", "w", "=r", errret);	\
+		break;							\
+	case 4:								\
+		__get_user_asm(x, ptr, retval, "l", "k", "=r", errret);	\
+		break;							\
+	case 8:								\
+		__get_user_asm_u64(x, ptr, retval, errret);		\
+		break;							\
+	default:							\
+		(x) = __get_user_bad();					\
+	}								\
+} while (0)
+
+#define __get_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
+	asm volatile("1:	mov"itype" %2,%"rtype"1\n"		\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:	mov %3,%0\n"				\
+		     "	xor"itype" %"rtype"1,%"rtype"1\n"		\
+		     "	jmp 2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : "=r" (err), ltype(x)				\
+		     : "m" (__m(addr)), "i" (errret), "0" (err))
+
+#define __put_user_nocheck(x, ptr, size)			\
+({								\
+	long __pu_err;						\
+	__put_user_size((x), (ptr), (size), __pu_err, -EFAULT);	\
+	__pu_err;						\
+})
+
+#define __get_user_nocheck(x, ptr, size)				\
+({									\
+	long __gu_err;							\
+	unsigned long __gu_val;						\
+	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
+	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+	__gu_err;							\
+})
+
+/* FIXME: this hack is definitely wrong -AK */
+struct __large_struct { unsigned long buf[100]; };
+#define __m(x) (*(struct __large_struct __user *)(x))
+
+/*
+ * Tell gcc we read from memory instead of writing: this is because
+ * we do not write to any memory gcc knows about, so there are no
+ * aliasing issues.
+ */
+#define __put_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
+	asm volatile("1:	mov"itype" %"rtype"1,%2\n"		\
+		     "2:\n"						\
+		     ".section .fixup,\"ax\"\n"				\
+		     "3:	mov %3,%0\n"				\
+		     "	jmp 2b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 3b)				\
+		     : "=r"(err)					\
+		     : ltype(x), "m" (__m(addr)), "i" (errret), "0" (err))
+/**
+ * __get_user: - Get a simple variable from user space, with less checking.
+ * @x:   Variable to store result.
+ * @ptr: Source address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple variable from user space to kernel
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and the result of
+ * dereferencing @ptr must be assignable to @x without a cast.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ * On error, the variable @x is set to zero.
+ */
+
+#define __get_user(x, ptr)						\
+	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+/**
+ * __put_user: - Write a simple value into user space, with less checking.
+ * @x:   Value to copy to user space.
+ * @ptr: Destination address, in user space.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * This macro copies a single simple value from kernel space to user
+ * space.  It supports simple types like char and int, but not larger
+ * data types like structures or arrays.
+ *
+ * @ptr must have pointer-to-simple-variable type, and @x must be assignable
+ * to the result of dereferencing @ptr.
+ *
+ * Caller must check the pointer with access_ok() before calling this
+ * function.
+ *
+ * Returns zero on success, or -EFAULT on error.
+ */
+
+#define __put_user(x, ptr)						\
+	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+
+#define __get_user_unaligned __get_user
+#define __put_user_unaligned __put_user
+
+/*
+ * movsl can be slow when source and dest are not both 8-byte aligned
+ */
+#ifdef CONFIG_X86_INTEL_USERCOPY
+extern struct movsl_mask {
+	int mask;
+} ____cacheline_aligned_in_smp movsl_mask;
+#endif
+
+#define ARCH_HAS_NOCACHE_UACCESS 1
+
+#ifdef CONFIG_X86_32
+# include "uaccess_32.h"
+#else
+# define ARCH_HAS_SEARCH_EXTABLE
+# include "uaccess_64.h"
+#endif
+
+#endif /* ASM_X86__UACCESS_H */
+
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
new file mode 100644
index 000000000000..6b5b57d9c6d1
--- /dev/null
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -0,0 +1,218 @@
+#ifndef ASM_X86__UACCESS_32_H
+#define ASM_X86__UACCESS_32_H
+
+/*
+ * User space memory access functions
+ */
+#include <linux/errno.h>
+#include <linux/thread_info.h>
+#include <linux/prefetch.h>
+#include <linux/string.h>
+#include <asm/asm.h>
+#include <asm/page.h>
+
+unsigned long __must_check __copy_to_user_ll
+		(void __user *to, const void *from, unsigned long n);
+unsigned long __must_check __copy_from_user_ll
+		(void *to, const void __user *from, unsigned long n);
+unsigned long __must_check __copy_from_user_ll_nozero
+		(void *to, const void __user *from, unsigned long n);
+unsigned long __must_check __copy_from_user_ll_nocache
+		(void *to, const void __user *from, unsigned long n);
+unsigned long __must_check __copy_from_user_ll_nocache_nozero
+		(void *to, const void __user *from, unsigned long n);
+
+/**
+ * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.
+ *
+ * Copy data from kernel space to user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ * The caller should also make sure he pins the user space address
+ * so that the we don't result in page fault and sleep.
+ *
+ * Here we special-case 1, 2 and 4-byte copy_*_user invocations.  On a fault
+ * we return the initial request size (1, 2 or 4), as copy_*_user should do.
+ * If a store crosses a page boundary and gets a fault, the x86 will not write
+ * anything, so this is accurate.
+ */
+
+static __always_inline unsigned long __must_check
+__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
+{
+	if (__builtin_constant_p(n)) {
+		unsigned long ret;
+
+		switch (n) {
+		case 1:
+			__put_user_size(*(u8 *)from, (u8 __user *)to,
+					1, ret, 1);
+			return ret;
+		case 2:
+			__put_user_size(*(u16 *)from, (u16 __user *)to,
+					2, ret, 2);
+			return ret;
+		case 4:
+			__put_user_size(*(u32 *)from, (u32 __user *)to,
+					4, ret, 4);
+			return ret;
+		}
+	}
+	return __copy_to_user_ll(to, from, n);
+}
+
+/**
+ * __copy_to_user: - Copy a block of data into user space, with less checking.
+ * @to:   Destination address, in user space.
+ * @from: Source address, in kernel space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Copy data from kernel space to user space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ */
+static __always_inline unsigned long __must_check
+__copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+       might_sleep();
+       return __copy_to_user_inatomic(to, from, n);
+}
+
+static __always_inline unsigned long
+__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
+{
+	/* Avoid zeroing the tail if the copy fails..
+	 * If 'n' is constant and 1, 2, or 4, we do still zero on a failure,
+	 * but as the zeroing behaviour is only significant when n is not
+	 * constant, that shouldn't be a problem.
+	 */
+	if (__builtin_constant_p(n)) {
+		unsigned long ret;
+
+		switch (n) {
+		case 1:
+			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			return ret;
+		case 2:
+			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			return ret;
+		case 4:
+			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			return ret;
+		}
+	}
+	return __copy_from_user_ll_nozero(to, from, n);
+}
+
+/**
+ * __copy_from_user: - Copy a block of data from user space, with less checking.
+ * @to:   Destination address, in kernel space.
+ * @from: Source address, in user space.
+ * @n:    Number of bytes to copy.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Copy data from user space to kernel space.  Caller must check
+ * the specified block with access_ok() before calling this function.
+ *
+ * Returns number of bytes that could not be copied.
+ * On success, this will be zero.
+ *
+ * If some data could not be copied, this function will pad the copied
+ * data to the requested size using zero bytes.
+ *
+ * An alternate version - __copy_from_user_inatomic() - may be called from
+ * atomic context and will fail rather than sleep.  In this case the
+ * uncopied bytes will *NOT* be padded with zeros.  See fs/filemap.h
+ * for explanation of why this is needed.
+ */
+static __always_inline unsigned long
+__copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	might_sleep();
+	if (__builtin_constant_p(n)) {
+		unsigned long ret;
+
+		switch (n) {
+		case 1:
+			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			return ret;
+		case 2:
+			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			return ret;
+		case 4:
+			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			return ret;
+		}
+	}
+	return __copy_from_user_ll(to, from, n);
+}
+
+static __always_inline unsigned long __copy_from_user_nocache(void *to,
+				const void __user *from, unsigned long n)
+{
+	might_sleep();
+	if (__builtin_constant_p(n)) {
+		unsigned long ret;
+
+		switch (n) {
+		case 1:
+			__get_user_size(*(u8 *)to, from, 1, ret, 1);
+			return ret;
+		case 2:
+			__get_user_size(*(u16 *)to, from, 2, ret, 2);
+			return ret;
+		case 4:
+			__get_user_size(*(u32 *)to, from, 4, ret, 4);
+			return ret;
+		}
+	}
+	return __copy_from_user_ll_nocache(to, from, n);
+}
+
+static __always_inline unsigned long
+__copy_from_user_inatomic_nocache(void *to, const void __user *from,
+				  unsigned long n)
+{
+       return __copy_from_user_ll_nocache_nozero(to, from, n);
+}
+
+unsigned long __must_check copy_to_user(void __user *to,
+					const void *from, unsigned long n);
+unsigned long __must_check copy_from_user(void *to,
+					  const void __user *from,
+					  unsigned long n);
+long __must_check strncpy_from_user(char *dst, const char __user *src,
+				    long count);
+long __must_check __strncpy_from_user(char *dst,
+				      const char __user *src, long count);
+
+/**
+ * strlen_user: - Get the size of a string in user space.
+ * @str: The string to measure.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Get the size of a NUL-terminated string in user space.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ * On exception, returns 0.
+ *
+ * If there is a limit on the length of a valid string, you may wish to
+ * consider using strnlen_user() instead.
+ */
+#define strlen_user(str) strnlen_user(str, LONG_MAX)
+
+long strnlen_user(const char __user *str, long n);
+unsigned long __must_check clear_user(void __user *mem, unsigned long len);
+unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
+
+#endif /* ASM_X86__UACCESS_32_H */
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
new file mode 100644
index 000000000000..c96c1f5d07a2
--- /dev/null
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -0,0 +1,202 @@
+#ifndef ASM_X86__UACCESS_64_H
+#define ASM_X86__UACCESS_64_H
+
+/*
+ * User space memory access functions
+ */
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/prefetch.h>
+#include <linux/lockdep.h>
+#include <asm/page.h>
+
+/*
+ * Copy To/From Userspace
+ */
+
+/* Handles exceptions in both to and from, but doesn't do access_ok */
+__must_check unsigned long
+copy_user_generic(void *to, const void *from, unsigned len);
+
+__must_check unsigned long
+copy_to_user(void __user *to, const void *from, unsigned len);
+__must_check unsigned long
+copy_from_user(void *to, const void __user *from, unsigned len);
+__must_check unsigned long
+copy_in_user(void __user *to, const void __user *from, unsigned len);
+
+static __always_inline __must_check
+int __copy_from_user(void *dst, const void __user *src, unsigned size)
+{
+	int ret = 0;
+	if (!__builtin_constant_p(size))
+		return copy_user_generic(dst, (__force void *)src, size);
+	switch (size) {
+	case 1:__get_user_asm(*(u8 *)dst, (u8 __user *)src,
+			      ret, "b", "b", "=q", 1);
+		return ret;
+	case 2:__get_user_asm(*(u16 *)dst, (u16 __user *)src,
+			      ret, "w", "w", "=r", 2);
+		return ret;
+	case 4:__get_user_asm(*(u32 *)dst, (u32 __user *)src,
+			      ret, "l", "k", "=r", 4);
+		return ret;
+	case 8:__get_user_asm(*(u64 *)dst, (u64 __user *)src,
+			      ret, "q", "", "=r", 8);
+		return ret;
+	case 10:
+		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
+			       ret, "q", "", "=r", 16);
+		if (unlikely(ret))
+			return ret;
+		__get_user_asm(*(u16 *)(8 + (char *)dst),
+			       (u16 __user *)(8 + (char __user *)src),
+			       ret, "w", "w", "=r", 2);
+		return ret;
+	case 16:
+		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
+			       ret, "q", "", "=r", 16);
+		if (unlikely(ret))
+			return ret;
+		__get_user_asm(*(u64 *)(8 + (char *)dst),
+			       (u64 __user *)(8 + (char __user *)src),
+			       ret, "q", "", "=r", 8);
+		return ret;
+	default:
+		return copy_user_generic(dst, (__force void *)src, size);
+	}
+}
+
+static __always_inline __must_check
+int __copy_to_user(void __user *dst, const void *src, unsigned size)
+{
+	int ret = 0;
+	if (!__builtin_constant_p(size))
+		return copy_user_generic((__force void *)dst, src, size);
+	switch (size) {
+	case 1:__put_user_asm(*(u8 *)src, (u8 __user *)dst,
+			      ret, "b", "b", "iq", 1);
+		return ret;
+	case 2:__put_user_asm(*(u16 *)src, (u16 __user *)dst,
+			      ret, "w", "w", "ir", 2);
+		return ret;
+	case 4:__put_user_asm(*(u32 *)src, (u32 __user *)dst,
+			      ret, "l", "k", "ir", 4);
+		return ret;
+	case 8:__put_user_asm(*(u64 *)src, (u64 __user *)dst,
+			      ret, "q", "", "ir", 8);
+		return ret;
+	case 10:
+		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
+			       ret, "q", "", "ir", 10);
+		if (unlikely(ret))
+			return ret;
+		asm("":::"memory");
+		__put_user_asm(4[(u16 *)src], 4 + (u16 __user *)dst,
+			       ret, "w", "w", "ir", 2);
+		return ret;
+	case 16:
+		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
+			       ret, "q", "", "ir", 16);
+		if (unlikely(ret))
+			return ret;
+		asm("":::"memory");
+		__put_user_asm(1[(u64 *)src], 1 + (u64 __user *)dst,
+			       ret, "q", "", "ir", 8);
+		return ret;
+	default:
+		return copy_user_generic((__force void *)dst, src, size);
+	}
+}
+
+static __always_inline __must_check
+int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
+{
+	int ret = 0;
+	if (!__builtin_constant_p(size))
+		return copy_user_generic((__force void *)dst,
+					 (__force void *)src, size);
+	switch (size) {
+	case 1: {
+		u8 tmp;
+		__get_user_asm(tmp, (u8 __user *)src,
+			       ret, "b", "b", "=q", 1);
+		if (likely(!ret))
+			__put_user_asm(tmp, (u8 __user *)dst,
+				       ret, "b", "b", "iq", 1);
+		return ret;
+	}
+	case 2: {
+		u16 tmp;
+		__get_user_asm(tmp, (u16 __user *)src,
+			       ret, "w", "w", "=r", 2);
+		if (likely(!ret))
+			__put_user_asm(tmp, (u16 __user *)dst,
+				       ret, "w", "w", "ir", 2);
+		return ret;
+	}
+
+	case 4: {
+		u32 tmp;
+		__get_user_asm(tmp, (u32 __user *)src,
+			       ret, "l", "k", "=r", 4);
+		if (likely(!ret))
+			__put_user_asm(tmp, (u32 __user *)dst,
+				       ret, "l", "k", "ir", 4);
+		return ret;
+	}
+	case 8: {
+		u64 tmp;
+		__get_user_asm(tmp, (u64 __user *)src,
+			       ret, "q", "", "=r", 8);
+		if (likely(!ret))
+			__put_user_asm(tmp, (u64 __user *)dst,
+				       ret, "q", "", "ir", 8);
+		return ret;
+	}
+	default:
+		return copy_user_generic((__force void *)dst,
+					 (__force void *)src, size);
+	}
+}
+
+__must_check long
+strncpy_from_user(char *dst, const char __user *src, long count);
+__must_check long
+__strncpy_from_user(char *dst, const char __user *src, long count);
+__must_check long strnlen_user(const char __user *str, long n);
+__must_check long __strnlen_user(const char __user *str, long n);
+__must_check long strlen_user(const char __user *str);
+__must_check unsigned long clear_user(void __user *mem, unsigned long len);
+__must_check unsigned long __clear_user(void __user *mem, unsigned long len);
+
+__must_check long __copy_from_user_inatomic(void *dst, const void __user *src,
+					    unsigned size);
+
+static __must_check __always_inline int
+__copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
+{
+	return copy_user_generic((__force void *)dst, src, size);
+}
+
+extern long __copy_user_nocache(void *dst, const void __user *src,
+				unsigned size, int zerorest);
+
+static inline int __copy_from_user_nocache(void *dst, const void __user *src,
+					   unsigned size)
+{
+	might_sleep();
+	return __copy_user_nocache(dst, src, size, 1);
+}
+
+static inline int __copy_from_user_inatomic_nocache(void *dst,
+						    const void __user *src,
+						    unsigned size)
+{
+	return __copy_user_nocache(dst, src, size, 0);
+}
+
+unsigned long
+copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest);
+
+#endif /* ASM_X86__UACCESS_64_H */
diff --git a/arch/x86/include/asm/ucontext.h b/arch/x86/include/asm/ucontext.h
new file mode 100644
index 000000000000..89eaa5456a7e
--- /dev/null
+++ b/arch/x86/include/asm/ucontext.h
@@ -0,0 +1,18 @@
+#ifndef ASM_X86__UCONTEXT_H
+#define ASM_X86__UCONTEXT_H
+
+#define UC_FP_XSTATE	0x1	/* indicates the presence of extended state
+				 * information in the memory layout pointed
+				 * by the fpstate pointer in the ucontext's
+				 * sigcontext struct (uc_mcontext).
+				 */
+
+struct ucontext {
+	unsigned long	  uc_flags;
+	struct ucontext  *uc_link;
+	stack_t		  uc_stack;
+	struct sigcontext uc_mcontext;
+	sigset_t	  uc_sigmask;	/* mask last for extensibility */
+};
+
+#endif /* ASM_X86__UCONTEXT_H */
diff --git a/arch/x86/include/asm/unaligned.h b/arch/x86/include/asm/unaligned.h
new file mode 100644
index 000000000000..59dcdec37160
--- /dev/null
+++ b/arch/x86/include/asm/unaligned.h
@@ -0,0 +1,14 @@
+#ifndef ASM_X86__UNALIGNED_H
+#define ASM_X86__UNALIGNED_H
+
+/*
+ * The x86 can do unaligned accesses itself.
+ */
+
+#include <linux/unaligned/access_ok.h>
+#include <linux/unaligned/generic.h>
+
+#define get_unaligned __get_unaligned_le
+#define put_unaligned __put_unaligned_le
+
+#endif /* ASM_X86__UNALIGNED_H */
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
new file mode 100644
index 000000000000..2a58ed3e51d8
--- /dev/null
+++ b/arch/x86/include/asm/unistd.h
@@ -0,0 +1,13 @@
+#ifdef __KERNEL__
+# ifdef CONFIG_X86_32
+#  include "unistd_32.h"
+# else
+#  include "unistd_64.h"
+# endif
+#else
+# ifdef __i386__
+#  include "unistd_32.h"
+# else
+#  include "unistd_64.h"
+# endif
+#endif
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
new file mode 100644
index 000000000000..017f4a87c913
--- /dev/null
+++ b/arch/x86/include/asm/unistd_32.h
@@ -0,0 +1,379 @@
+#ifndef ASM_X86__UNISTD_32_H
+#define ASM_X86__UNISTD_32_H
+
+/*
+ * This file contains the system call numbers.
+ */
+
+#define __NR_restart_syscall      0
+#define __NR_exit		  1
+#define __NR_fork		  2
+#define __NR_read		  3
+#define __NR_write		  4
+#define __NR_open		  5
+#define __NR_close		  6
+#define __NR_waitpid		  7
+#define __NR_creat		  8
+#define __NR_link		  9
+#define __NR_unlink		 10
+#define __NR_execve		 11
+#define __NR_chdir		 12
+#define __NR_time		 13
+#define __NR_mknod		 14
+#define __NR_chmod		 15
+#define __NR_lchown		 16
+#define __NR_break		 17
+#define __NR_oldstat		 18
+#define __NR_lseek		 19
+#define __NR_getpid		 20
+#define __NR_mount		 21
+#define __NR_umount		 22
+#define __NR_setuid		 23
+#define __NR_getuid		 24
+#define __NR_stime		 25
+#define __NR_ptrace		 26
+#define __NR_alarm		 27
+#define __NR_oldfstat		 28
+#define __NR_pause		 29
+#define __NR_utime		 30
+#define __NR_stty		 31
+#define __NR_gtty		 32
+#define __NR_access		 33
+#define __NR_nice		 34
+#define __NR_ftime		 35
+#define __NR_sync		 36
+#define __NR_kill		 37
+#define __NR_rename		 38
+#define __NR_mkdir		 39
+#define __NR_rmdir		 40
+#define __NR_dup		 41
+#define __NR_pipe		 42
+#define __NR_times		 43
+#define __NR_prof		 44
+#define __NR_brk		 45
+#define __NR_setgid		 46
+#define __NR_getgid		 47
+#define __NR_signal		 48
+#define __NR_geteuid		 49
+#define __NR_getegid		 50
+#define __NR_acct		 51
+#define __NR_umount2		 52
+#define __NR_lock		 53
+#define __NR_ioctl		 54
+#define __NR_fcntl		 55
+#define __NR_mpx		 56
+#define __NR_setpgid		 57
+#define __NR_ulimit		 58
+#define __NR_oldolduname	 59
+#define __NR_umask		 60
+#define __NR_chroot		 61
+#define __NR_ustat		 62
+#define __NR_dup2		 63
+#define __NR_getppid		 64
+#define __NR_getpgrp		 65
+#define __NR_setsid		 66
+#define __NR_sigaction		 67
+#define __NR_sgetmask		 68
+#define __NR_ssetmask		 69
+#define __NR_setreuid		 70
+#define __NR_setregid		 71
+#define __NR_sigsuspend		 72
+#define __NR_sigpending		 73
+#define __NR_sethostname	 74
+#define __NR_setrlimit		 75
+#define __NR_getrlimit		 76   /* Back compatible 2Gig limited rlimit */
+#define __NR_getrusage		 77
+#define __NR_gettimeofday	 78
+#define __NR_settimeofday	 79
+#define __NR_getgroups		 80
+#define __NR_setgroups		 81
+#define __NR_select		 82
+#define __NR_symlink		 83
+#define __NR_oldlstat		 84
+#define __NR_readlink		 85
+#define __NR_uselib		 86
+#define __NR_swapon		 87
+#define __NR_reboot		 88
+#define __NR_readdir		 89
+#define __NR_mmap		 90
+#define __NR_munmap		 91
+#define __NR_truncate		 92
+#define __NR_ftruncate		 93
+#define __NR_fchmod		 94
+#define __NR_fchown		 95
+#define __NR_getpriority	 96
+#define __NR_setpriority	 97
+#define __NR_profil		 98
+#define __NR_statfs		 99
+#define __NR_fstatfs		100
+#define __NR_ioperm		101
+#define __NR_socketcall		102
+#define __NR_syslog		103
+#define __NR_setitimer		104
+#define __NR_getitimer		105
+#define __NR_stat		106
+#define __NR_lstat		107
+#define __NR_fstat		108
+#define __NR_olduname		109
+#define __NR_iopl		110
+#define __NR_vhangup		111
+#define __NR_idle		112
+#define __NR_vm86old		113
+#define __NR_wait4		114
+#define __NR_swapoff		115
+#define __NR_sysinfo		116
+#define __NR_ipc		117
+#define __NR_fsync		118
+#define __NR_sigreturn		119
+#define __NR_clone		120
+#define __NR_setdomainname	121
+#define __NR_uname		122
+#define __NR_modify_ldt		123
+#define __NR_adjtimex		124
+#define __NR_mprotect		125
+#define __NR_sigprocmask	126
+#define __NR_create_module	127
+#define __NR_init_module	128
+#define __NR_delete_module	129
+#define __NR_get_kernel_syms	130
+#define __NR_quotactl		131
+#define __NR_getpgid		132
+#define __NR_fchdir		133
+#define __NR_bdflush		134
+#define __NR_sysfs		135
+#define __NR_personality	136
+#define __NR_afs_syscall	137 /* Syscall for Andrew File System */
+#define __NR_setfsuid		138
+#define __NR_setfsgid		139
+#define __NR__llseek		140
+#define __NR_getdents		141
+#define __NR__newselect		142
+#define __NR_flock		143
+#define __NR_msync		144
+#define __NR_readv		145
+#define __NR_writev		146
+#define __NR_getsid		147
+#define __NR_fdatasync		148
+#define __NR__sysctl		149
+#define __NR_mlock		150
+#define __NR_munlock		151
+#define __NR_mlockall		152
+#define __NR_munlockall		153
+#define __NR_sched_setparam		154
+#define __NR_sched_getparam		155
+#define __NR_sched_setscheduler		156
+#define __NR_sched_getscheduler		157
+#define __NR_sched_yield		158
+#define __NR_sched_get_priority_max	159
+#define __NR_sched_get_priority_min	160
+#define __NR_sched_rr_get_interval	161
+#define __NR_nanosleep		162
+#define __NR_mremap		163
+#define __NR_setresuid		164
+#define __NR_getresuid		165
+#define __NR_vm86		166
+#define __NR_query_module	167
+#define __NR_poll		168
+#define __NR_nfsservctl		169
+#define __NR_setresgid		170
+#define __NR_getresgid		171
+#define __NR_prctl              172
+#define __NR_rt_sigreturn	173
+#define __NR_rt_sigaction	174
+#define __NR_rt_sigprocmask	175
+#define __NR_rt_sigpending	176
+#define __NR_rt_sigtimedwait	177
+#define __NR_rt_sigqueueinfo	178
+#define __NR_rt_sigsuspend	179
+#define __NR_pread64		180
+#define __NR_pwrite64		181
+#define __NR_chown		182
+#define __NR_getcwd		183
+#define __NR_capget		184
+#define __NR_capset		185
+#define __NR_sigaltstack	186
+#define __NR_sendfile		187
+#define __NR_getpmsg		188	/* some people actually want streams */
+#define __NR_putpmsg		189	/* some people actually want streams */
+#define __NR_vfork		190
+#define __NR_ugetrlimit		191	/* SuS compliant getrlimit */
+#define __NR_mmap2		192
+#define __NR_truncate64		193
+#define __NR_ftruncate64	194
+#define __NR_stat64		195
+#define __NR_lstat64		196
+#define __NR_fstat64		197
+#define __NR_lchown32		198
+#define __NR_getuid32		199
+#define __NR_getgid32		200
+#define __NR_geteuid32		201
+#define __NR_getegid32		202
+#define __NR_setreuid32		203
+#define __NR_setregid32		204
+#define __NR_getgroups32	205
+#define __NR_setgroups32	206
+#define __NR_fchown32		207
+#define __NR_setresuid32	208
+#define __NR_getresuid32	209
+#define __NR_setresgid32	210
+#define __NR_getresgid32	211
+#define __NR_chown32		212
+#define __NR_setuid32		213
+#define __NR_setgid32		214
+#define __NR_setfsuid32		215
+#define __NR_setfsgid32		216
+#define __NR_pivot_root		217
+#define __NR_mincore		218
+#define __NR_madvise		219
+#define __NR_madvise1		219	/* delete when C lib stub is removed */
+#define __NR_getdents64		220
+#define __NR_fcntl64		221
+/* 223 is unused */
+#define __NR_gettid		224
+#define __NR_readahead		225
+#define __NR_setxattr		226
+#define __NR_lsetxattr		227
+#define __NR_fsetxattr		228
+#define __NR_getxattr		229
+#define __NR_lgetxattr		230
+#define __NR_fgetxattr		231
+#define __NR_listxattr		232
+#define __NR_llistxattr		233
+#define __NR_flistxattr		234
+#define __NR_removexattr	235
+#define __NR_lremovexattr	236
+#define __NR_fremovexattr	237
+#define __NR_tkill		238
+#define __NR_sendfile64		239
+#define __NR_futex		240
+#define __NR_sched_setaffinity	241
+#define __NR_sched_getaffinity	242
+#define __NR_set_thread_area	243
+#define __NR_get_thread_area	244
+#define __NR_io_setup		245
+#define __NR_io_destroy		246
+#define __NR_io_getevents	247
+#define __NR_io_submit		248
+#define __NR_io_cancel		249
+#define __NR_fadvise64		250
+/* 251 is available for reuse (was briefly sys_set_zone_reclaim) */
+#define __NR_exit_group		252
+#define __NR_lookup_dcookie	253
+#define __NR_epoll_create	254
+#define __NR_epoll_ctl		255
+#define __NR_epoll_wait		256
+#define __NR_remap_file_pages	257
+#define __NR_set_tid_address	258
+#define __NR_timer_create	259
+#define __NR_timer_settime	(__NR_timer_create+1)
+#define __NR_timer_gettime	(__NR_timer_create+2)
+#define __NR_timer_getoverrun	(__NR_timer_create+3)
+#define __NR_timer_delete	(__NR_timer_create+4)
+#define __NR_clock_settime	(__NR_timer_create+5)
+#define __NR_clock_gettime	(__NR_timer_create+6)
+#define __NR_clock_getres	(__NR_timer_create+7)
+#define __NR_clock_nanosleep	(__NR_timer_create+8)
+#define __NR_statfs64		268
+#define __NR_fstatfs64		269
+#define __NR_tgkill		270
+#define __NR_utimes		271
+#define __NR_fadvise64_64	272
+#define __NR_vserver		273
+#define __NR_mbind		274
+#define __NR_get_mempolicy	275
+#define __NR_set_mempolicy	276
+#define __NR_mq_open 		277
+#define __NR_mq_unlink		(__NR_mq_open+1)
+#define __NR_mq_timedsend	(__NR_mq_open+2)
+#define __NR_mq_timedreceive	(__NR_mq_open+3)
+#define __NR_mq_notify		(__NR_mq_open+4)
+#define __NR_mq_getsetattr	(__NR_mq_open+5)
+#define __NR_kexec_load		283
+#define __NR_waitid		284
+/* #define __NR_sys_setaltroot	285 */
+#define __NR_add_key		286
+#define __NR_request_key	287
+#define __NR_keyctl		288
+#define __NR_ioprio_set		289
+#define __NR_ioprio_get		290
+#define __NR_inotify_init	291
+#define __NR_inotify_add_watch	292
+#define __NR_inotify_rm_watch	293
+#define __NR_migrate_pages	294
+#define __NR_openat		295
+#define __NR_mkdirat		296
+#define __NR_mknodat		297
+#define __NR_fchownat		298
+#define __NR_futimesat		299
+#define __NR_fstatat64		300
+#define __NR_unlinkat		301
+#define __NR_renameat		302
+#define __NR_linkat		303
+#define __NR_symlinkat		304
+#define __NR_readlinkat		305
+#define __NR_fchmodat		306
+#define __NR_faccessat		307
+#define __NR_pselect6		308
+#define __NR_ppoll		309
+#define __NR_unshare		310
+#define __NR_set_robust_list	311
+#define __NR_get_robust_list	312
+#define __NR_splice		313
+#define __NR_sync_file_range	314
+#define __NR_tee		315
+#define __NR_vmsplice		316
+#define __NR_move_pages		317
+#define __NR_getcpu		318
+#define __NR_epoll_pwait	319
+#define __NR_utimensat		320
+#define __NR_signalfd		321
+#define __NR_timerfd_create	322
+#define __NR_eventfd		323
+#define __NR_fallocate		324
+#define __NR_timerfd_settime	325
+#define __NR_timerfd_gettime	326
+#define __NR_signalfd4		327
+#define __NR_eventfd2		328
+#define __NR_epoll_create1	329
+#define __NR_dup3		330
+#define __NR_pipe2		331
+#define __NR_inotify_init1	332
+
+#ifdef __KERNEL__
+
+#define __ARCH_WANT_IPC_PARSE_VERSION
+#define __ARCH_WANT_OLD_READDIR
+#define __ARCH_WANT_OLD_STAT
+#define __ARCH_WANT_STAT64
+#define __ARCH_WANT_SYS_ALARM
+#define __ARCH_WANT_SYS_GETHOSTNAME
+#define __ARCH_WANT_SYS_PAUSE
+#define __ARCH_WANT_SYS_SGETMASK
+#define __ARCH_WANT_SYS_SIGNAL
+#define __ARCH_WANT_SYS_TIME
+#define __ARCH_WANT_SYS_UTIME
+#define __ARCH_WANT_SYS_WAITPID
+#define __ARCH_WANT_SYS_SOCKETCALL
+#define __ARCH_WANT_SYS_FADVISE64
+#define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
+#define __ARCH_WANT_SYS_NICE
+#define __ARCH_WANT_SYS_OLD_GETRLIMIT
+#define __ARCH_WANT_SYS_OLDUMOUNT
+#define __ARCH_WANT_SYS_SIGPENDING
+#define __ARCH_WANT_SYS_SIGPROCMASK
+#define __ARCH_WANT_SYS_RT_SIGACTION
+#define __ARCH_WANT_SYS_RT_SIGSUSPEND
+
+/*
+ * "Conditional" syscalls
+ *
+ * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
+ * but it doesn't work on all toolchains, so we just do it by hand
+ */
+#ifndef cond_syscall
+#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* ASM_X86__UNISTD_32_H */
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
new file mode 100644
index 000000000000..ace83f1f6787
--- /dev/null
+++ b/arch/x86/include/asm/unistd_64.h
@@ -0,0 +1,693 @@
+#ifndef ASM_X86__UNISTD_64_H
+#define ASM_X86__UNISTD_64_H
+
+#ifndef __SYSCALL
+#define __SYSCALL(a, b)
+#endif
+
+/*
+ * This file contains the system call numbers.
+ *
+ * Note: holes are not allowed.
+ */
+
+/* at least 8 syscall per cacheline */
+#define __NR_read				0
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write				1
+__SYSCALL(__NR_write, sys_write)
+#define __NR_open				2
+__SYSCALL(__NR_open, sys_open)
+#define __NR_close				3
+__SYSCALL(__NR_close, sys_close)
+#define __NR_stat				4
+__SYSCALL(__NR_stat, sys_newstat)
+#define __NR_fstat				5
+__SYSCALL(__NR_fstat, sys_newfstat)
+#define __NR_lstat				6
+__SYSCALL(__NR_lstat, sys_newlstat)
+#define __NR_poll				7
+__SYSCALL(__NR_poll, sys_poll)
+
+#define __NR_lseek				8
+__SYSCALL(__NR_lseek, sys_lseek)
+#define __NR_mmap				9
+__SYSCALL(__NR_mmap, sys_mmap)
+#define __NR_mprotect				10
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_munmap				11
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_brk				12
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_rt_sigaction			13
+__SYSCALL(__NR_rt_sigaction, sys_rt_sigaction)
+#define __NR_rt_sigprocmask			14
+__SYSCALL(__NR_rt_sigprocmask, sys_rt_sigprocmask)
+#define __NR_rt_sigreturn			15
+__SYSCALL(__NR_rt_sigreturn, stub_rt_sigreturn)
+
+#define __NR_ioctl				16
+__SYSCALL(__NR_ioctl, sys_ioctl)
+#define __NR_pread64				17
+__SYSCALL(__NR_pread64, sys_pread64)
+#define __NR_pwrite64				18
+__SYSCALL(__NR_pwrite64, sys_pwrite64)
+#define __NR_readv				19
+__SYSCALL(__NR_readv, sys_readv)
+#define __NR_writev				20
+__SYSCALL(__NR_writev, sys_writev)
+#define __NR_access				21
+__SYSCALL(__NR_access, sys_access)
+#define __NR_pipe				22
+__SYSCALL(__NR_pipe, sys_pipe)
+#define __NR_select				23
+__SYSCALL(__NR_select, sys_select)
+
+#define __NR_sched_yield			24
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_mremap				25
+__SYSCALL(__NR_mremap, sys_mremap)
+#define __NR_msync				26
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_mincore				27
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise				28
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_shmget				29
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmat				30
+__SYSCALL(__NR_shmat, sys_shmat)
+#define __NR_shmctl				31
+__SYSCALL(__NR_shmctl, sys_shmctl)
+
+#define __NR_dup				32
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_dup2				33
+__SYSCALL(__NR_dup2, sys_dup2)
+#define __NR_pause				34
+__SYSCALL(__NR_pause, sys_pause)
+#define __NR_nanosleep				35
+__SYSCALL(__NR_nanosleep, sys_nanosleep)
+#define __NR_getitimer				36
+__SYSCALL(__NR_getitimer, sys_getitimer)
+#define __NR_alarm				37
+__SYSCALL(__NR_alarm, sys_alarm)
+#define __NR_setitimer				38
+__SYSCALL(__NR_setitimer, sys_setitimer)
+#define __NR_getpid				39
+__SYSCALL(__NR_getpid, sys_getpid)
+
+#define __NR_sendfile				40
+__SYSCALL(__NR_sendfile, sys_sendfile64)
+#define __NR_socket				41
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_connect				42
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_accept				43
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_sendto				44
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recvfrom				45
+__SYSCALL(__NR_recvfrom, sys_recvfrom)
+#define __NR_sendmsg				46
+__SYSCALL(__NR_sendmsg, sys_sendmsg)
+#define __NR_recvmsg				47
+__SYSCALL(__NR_recvmsg, sys_recvmsg)
+
+#define __NR_shutdown				48
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_bind				49
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_listen				50
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_getsockname			51
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername			52
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_socketpair				53
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_setsockopt				54
+__SYSCALL(__NR_setsockopt, sys_setsockopt)
+#define __NR_getsockopt				55
+__SYSCALL(__NR_getsockopt, sys_getsockopt)
+
+#define __NR_clone				56
+__SYSCALL(__NR_clone, stub_clone)
+#define __NR_fork				57
+__SYSCALL(__NR_fork, stub_fork)
+#define __NR_vfork				58
+__SYSCALL(__NR_vfork, stub_vfork)
+#define __NR_execve				59
+__SYSCALL(__NR_execve, stub_execve)
+#define __NR_exit				60
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_wait4				61
+__SYSCALL(__NR_wait4, sys_wait4)
+#define __NR_kill				62
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_uname				63
+__SYSCALL(__NR_uname, sys_uname)
+
+#define __NR_semget				64
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semop				65
+__SYSCALL(__NR_semop, sys_semop)
+#define __NR_semctl				66
+__SYSCALL(__NR_semctl, sys_semctl)
+#define __NR_shmdt				67
+__SYSCALL(__NR_shmdt, sys_shmdt)
+#define __NR_msgget				68
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgsnd				69
+__SYSCALL(__NR_msgsnd, sys_msgsnd)
+#define __NR_msgrcv				70
+__SYSCALL(__NR_msgrcv, sys_msgrcv)
+#define __NR_msgctl				71
+__SYSCALL(__NR_msgctl, sys_msgctl)
+
+#define __NR_fcntl				72
+__SYSCALL(__NR_fcntl, sys_fcntl)
+#define __NR_flock				73
+__SYSCALL(__NR_flock, sys_flock)
+#define __NR_fsync				74
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_fdatasync				75
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+#define __NR_truncate				76
+__SYSCALL(__NR_truncate, sys_truncate)
+#define __NR_ftruncate				77
+__SYSCALL(__NR_ftruncate, sys_ftruncate)
+#define __NR_getdents				78
+__SYSCALL(__NR_getdents, sys_getdents)
+#define __NR_getcwd				79
+__SYSCALL(__NR_getcwd, sys_getcwd)
+
+#define __NR_chdir				80
+__SYSCALL(__NR_chdir, sys_chdir)
+#define __NR_fchdir				81
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_rename				82
+__SYSCALL(__NR_rename, sys_rename)
+#define __NR_mkdir				83
+__SYSCALL(__NR_mkdir, sys_mkdir)
+#define __NR_rmdir				84
+__SYSCALL(__NR_rmdir, sys_rmdir)
+#define __NR_creat				85
+__SYSCALL(__NR_creat, sys_creat)
+#define __NR_link				86
+__SYSCALL(__NR_link, sys_link)
+#define __NR_unlink				87
+__SYSCALL(__NR_unlink, sys_unlink)
+
+#define __NR_symlink				88
+__SYSCALL(__NR_symlink, sys_symlink)
+#define __NR_readlink				89
+__SYSCALL(__NR_readlink, sys_readlink)
+#define __NR_chmod				90
+__SYSCALL(__NR_chmod, sys_chmod)
+#define __NR_fchmod				91
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_chown				92
+__SYSCALL(__NR_chown, sys_chown)
+#define __NR_fchown				93
+__SYSCALL(__NR_fchown, sys_fchown)
+#define __NR_lchown				94
+__SYSCALL(__NR_lchown, sys_lchown)
+#define __NR_umask				95
+__SYSCALL(__NR_umask, sys_umask)
+
+#define __NR_gettimeofday			96
+__SYSCALL(__NR_gettimeofday, sys_gettimeofday)
+#define __NR_getrlimit				97
+__SYSCALL(__NR_getrlimit, sys_getrlimit)
+#define __NR_getrusage				98
+__SYSCALL(__NR_getrusage, sys_getrusage)
+#define __NR_sysinfo				99
+__SYSCALL(__NR_sysinfo, sys_sysinfo)
+#define __NR_times				100
+__SYSCALL(__NR_times, sys_times)
+#define __NR_ptrace				101
+__SYSCALL(__NR_ptrace, sys_ptrace)
+#define __NR_getuid				102
+__SYSCALL(__NR_getuid, sys_getuid)
+#define __NR_syslog				103
+__SYSCALL(__NR_syslog, sys_syslog)
+
+/* at the very end the stuff that never runs during the benchmarks */
+#define __NR_getgid				104
+__SYSCALL(__NR_getgid, sys_getgid)
+#define __NR_setuid				105
+__SYSCALL(__NR_setuid, sys_setuid)
+#define __NR_setgid				106
+__SYSCALL(__NR_setgid, sys_setgid)
+#define __NR_geteuid				107
+__SYSCALL(__NR_geteuid, sys_geteuid)
+#define __NR_getegid				108
+__SYSCALL(__NR_getegid, sys_getegid)
+#define __NR_setpgid				109
+__SYSCALL(__NR_setpgid, sys_setpgid)
+#define __NR_getppid				110
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getpgrp				111
+__SYSCALL(__NR_getpgrp, sys_getpgrp)
+
+#define __NR_setsid				112
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_setreuid				113
+__SYSCALL(__NR_setreuid, sys_setreuid)
+#define __NR_setregid				114
+__SYSCALL(__NR_setregid, sys_setregid)
+#define __NR_getgroups				115
+__SYSCALL(__NR_getgroups, sys_getgroups)
+#define __NR_setgroups				116
+__SYSCALL(__NR_setgroups, sys_setgroups)
+#define __NR_setresuid				117
+__SYSCALL(__NR_setresuid, sys_setresuid)
+#define __NR_getresuid				118
+__SYSCALL(__NR_getresuid, sys_getresuid)
+#define __NR_setresgid				119
+__SYSCALL(__NR_setresgid, sys_setresgid)
+
+#define __NR_getresgid				120
+__SYSCALL(__NR_getresgid, sys_getresgid)
+#define __NR_getpgid				121
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_setfsuid				122
+__SYSCALL(__NR_setfsuid, sys_setfsuid)
+#define __NR_setfsgid				123
+__SYSCALL(__NR_setfsgid, sys_setfsgid)
+#define __NR_getsid				124
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_capget				125
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset				126
+__SYSCALL(__NR_capset, sys_capset)
+
+#define __NR_rt_sigpending			127
+__SYSCALL(__NR_rt_sigpending, sys_rt_sigpending)
+#define __NR_rt_sigtimedwait			128
+__SYSCALL(__NR_rt_sigtimedwait, sys_rt_sigtimedwait)
+#define __NR_rt_sigqueueinfo			129
+__SYSCALL(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo)
+#define __NR_rt_sigsuspend			130
+__SYSCALL(__NR_rt_sigsuspend, sys_rt_sigsuspend)
+#define __NR_sigaltstack			131
+__SYSCALL(__NR_sigaltstack, stub_sigaltstack)
+#define __NR_utime				132
+__SYSCALL(__NR_utime, sys_utime)
+#define __NR_mknod				133
+__SYSCALL(__NR_mknod, sys_mknod)
+
+/* Only needed for a.out */
+#define __NR_uselib				134
+__SYSCALL(__NR_uselib, sys_ni_syscall)
+#define __NR_personality			135
+__SYSCALL(__NR_personality, sys_personality)
+
+#define __NR_ustat				136
+__SYSCALL(__NR_ustat, sys_ustat)
+#define __NR_statfs				137
+__SYSCALL(__NR_statfs, sys_statfs)
+#define __NR_fstatfs				138
+__SYSCALL(__NR_fstatfs, sys_fstatfs)
+#define __NR_sysfs				139
+__SYSCALL(__NR_sysfs, sys_sysfs)
+
+#define __NR_getpriority			140
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_setpriority			141
+__SYSCALL(__NR_setpriority, sys_setpriority)
+#define __NR_sched_setparam			142
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_getparam			143
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setscheduler			144
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler			145
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_get_priority_max		146
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min		147
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#define __NR_sched_rr_get_interval		148
+__SYSCALL(__NR_sched_rr_get_interval, sys_sched_rr_get_interval)
+
+#define __NR_mlock				149
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock				150
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall				151
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall				152
+__SYSCALL(__NR_munlockall, sys_munlockall)
+
+#define __NR_vhangup				153
+__SYSCALL(__NR_vhangup, sys_vhangup)
+
+#define __NR_modify_ldt				154
+__SYSCALL(__NR_modify_ldt, sys_modify_ldt)
+
+#define __NR_pivot_root				155
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+
+#define __NR__sysctl				156
+__SYSCALL(__NR__sysctl, sys_sysctl)
+
+#define __NR_prctl				157
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_arch_prctl				158
+__SYSCALL(__NR_arch_prctl, sys_arch_prctl)
+
+#define __NR_adjtimex				159
+__SYSCALL(__NR_adjtimex, sys_adjtimex)
+
+#define __NR_setrlimit				160
+__SYSCALL(__NR_setrlimit, sys_setrlimit)
+
+#define __NR_chroot				161
+__SYSCALL(__NR_chroot, sys_chroot)
+
+#define __NR_sync				162
+__SYSCALL(__NR_sync, sys_sync)
+
+#define __NR_acct				163
+__SYSCALL(__NR_acct, sys_acct)
+
+#define __NR_settimeofday			164
+__SYSCALL(__NR_settimeofday, sys_settimeofday)
+
+#define __NR_mount				165
+__SYSCALL(__NR_mount, sys_mount)
+#define __NR_umount2				166
+__SYSCALL(__NR_umount2, sys_umount)
+
+#define __NR_swapon				167
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_swapoff				168
+__SYSCALL(__NR_swapoff, sys_swapoff)
+
+#define __NR_reboot				169
+__SYSCALL(__NR_reboot, sys_reboot)
+
+#define __NR_sethostname			170
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setdomainname			171
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+
+#define __NR_iopl				172
+__SYSCALL(__NR_iopl, stub_iopl)
+#define __NR_ioperm				173
+__SYSCALL(__NR_ioperm, sys_ioperm)
+
+#define __NR_create_module			174
+__SYSCALL(__NR_create_module, sys_ni_syscall)
+#define __NR_init_module			175
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module			176
+__SYSCALL(__NR_delete_module, sys_delete_module)
+#define __NR_get_kernel_syms			177
+__SYSCALL(__NR_get_kernel_syms, sys_ni_syscall)
+#define __NR_query_module			178
+__SYSCALL(__NR_query_module, sys_ni_syscall)
+
+#define __NR_quotactl				179
+__SYSCALL(__NR_quotactl, sys_quotactl)
+
+#define __NR_nfsservctl				180
+__SYSCALL(__NR_nfsservctl, sys_nfsservctl)
+
+/* reserved for LiS/STREAMS */
+#define __NR_getpmsg				181
+__SYSCALL(__NR_getpmsg, sys_ni_syscall)
+#define __NR_putpmsg				182
+__SYSCALL(__NR_putpmsg, sys_ni_syscall)
+
+/* reserved for AFS */
+#define __NR_afs_syscall			183
+__SYSCALL(__NR_afs_syscall, sys_ni_syscall)
+
+/* reserved for tux */
+#define __NR_tuxcall				184
+__SYSCALL(__NR_tuxcall, sys_ni_syscall)
+
+#define __NR_security				185
+__SYSCALL(__NR_security, sys_ni_syscall)
+
+#define __NR_gettid				186
+__SYSCALL(__NR_gettid, sys_gettid)
+
+#define __NR_readahead				187
+__SYSCALL(__NR_readahead, sys_readahead)
+#define __NR_setxattr				188
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr				189
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr				190
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr				191
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr				192
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr				193
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr				194
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr				195
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr				196
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr			197
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr			198
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr			199
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+#define __NR_tkill				200
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_time				201
+__SYSCALL(__NR_time, sys_time)
+#define __NR_futex				202
+__SYSCALL(__NR_futex, sys_futex)
+#define __NR_sched_setaffinity			203
+__SYSCALL(__NR_sched_setaffinity, sys_sched_setaffinity)
+#define __NR_sched_getaffinity			204
+__SYSCALL(__NR_sched_getaffinity, sys_sched_getaffinity)
+#define __NR_set_thread_area			205
+__SYSCALL(__NR_set_thread_area, sys_ni_syscall)	/* use arch_prctl */
+#define __NR_io_setup				206
+__SYSCALL(__NR_io_setup, sys_io_setup)
+#define __NR_io_destroy				207
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_getevents			208
+__SYSCALL(__NR_io_getevents, sys_io_getevents)
+#define __NR_io_submit				209
+__SYSCALL(__NR_io_submit, sys_io_submit)
+#define __NR_io_cancel				210
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#define __NR_get_thread_area			211
+__SYSCALL(__NR_get_thread_area, sys_ni_syscall)	/* use arch_prctl */
+#define __NR_lookup_dcookie			212
+__SYSCALL(__NR_lookup_dcookie, sys_lookup_dcookie)
+#define __NR_epoll_create			213
+__SYSCALL(__NR_epoll_create, sys_epoll_create)
+#define __NR_epoll_ctl_old			214
+__SYSCALL(__NR_epoll_ctl_old, sys_ni_syscall)
+#define __NR_epoll_wait_old			215
+__SYSCALL(__NR_epoll_wait_old, sys_ni_syscall)
+#define __NR_remap_file_pages			216
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+#define __NR_getdents64				217
+__SYSCALL(__NR_getdents64, sys_getdents64)
+#define __NR_set_tid_address			218
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_restart_syscall			219
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_semtimedop				220
+__SYSCALL(__NR_semtimedop, sys_semtimedop)
+#define __NR_fadvise64				221
+__SYSCALL(__NR_fadvise64, sys_fadvise64)
+#define __NR_timer_create			222
+__SYSCALL(__NR_timer_create, sys_timer_create)
+#define __NR_timer_settime			223
+__SYSCALL(__NR_timer_settime, sys_timer_settime)
+#define __NR_timer_gettime			224
+__SYSCALL(__NR_timer_gettime, sys_timer_gettime)
+#define __NR_timer_getoverrun			225
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#define __NR_timer_delete			226
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#define __NR_clock_settime			227
+__SYSCALL(__NR_clock_settime, sys_clock_settime)
+#define __NR_clock_gettime			228
+__SYSCALL(__NR_clock_gettime, sys_clock_gettime)
+#define __NR_clock_getres			229
+__SYSCALL(__NR_clock_getres, sys_clock_getres)
+#define __NR_clock_nanosleep			230
+__SYSCALL(__NR_clock_nanosleep, sys_clock_nanosleep)
+#define __NR_exit_group				231
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_epoll_wait				232
+__SYSCALL(__NR_epoll_wait, sys_epoll_wait)
+#define __NR_epoll_ctl				233
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_tgkill				234
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_utimes				235
+__SYSCALL(__NR_utimes, sys_utimes)
+#define __NR_vserver				236
+__SYSCALL(__NR_vserver, sys_ni_syscall)
+#define __NR_mbind				237
+__SYSCALL(__NR_mbind, sys_mbind)
+#define __NR_set_mempolicy			238
+__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy)
+#define __NR_get_mempolicy			239
+__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy)
+#define __NR_mq_open				240
+__SYSCALL(__NR_mq_open, sys_mq_open)
+#define __NR_mq_unlink				241
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#define __NR_mq_timedsend			242
+__SYSCALL(__NR_mq_timedsend, sys_mq_timedsend)
+#define __NR_mq_timedreceive			243
+__SYSCALL(__NR_mq_timedreceive, sys_mq_timedreceive)
+#define __NR_mq_notify				244
+__SYSCALL(__NR_mq_notify, sys_mq_notify)
+#define __NR_mq_getsetattr			245
+__SYSCALL(__NR_mq_getsetattr, sys_mq_getsetattr)
+#define __NR_kexec_load				246
+__SYSCALL(__NR_kexec_load, sys_kexec_load)
+#define __NR_waitid				247
+__SYSCALL(__NR_waitid, sys_waitid)
+#define __NR_add_key				248
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key			249
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl				250
+__SYSCALL(__NR_keyctl, sys_keyctl)
+#define __NR_ioprio_set				251
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get				252
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+#define __NR_inotify_init			253
+__SYSCALL(__NR_inotify_init, sys_inotify_init)
+#define __NR_inotify_add_watch			254
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch			255
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+#define __NR_migrate_pages			256
+__SYSCALL(__NR_migrate_pages, sys_migrate_pages)
+#define __NR_openat				257
+__SYSCALL(__NR_openat, sys_openat)
+#define __NR_mkdirat				258
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_mknodat				259
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_fchownat				260
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_futimesat				261
+__SYSCALL(__NR_futimesat, sys_futimesat)
+#define __NR_newfstatat				262
+__SYSCALL(__NR_newfstatat, sys_newfstatat)
+#define __NR_unlinkat				263
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_renameat				264
+__SYSCALL(__NR_renameat, sys_renameat)
+#define __NR_linkat				265
+__SYSCALL(__NR_linkat, sys_linkat)
+#define __NR_symlinkat				266
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_readlinkat				267
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR_fchmodat				268
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_faccessat				269
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_pselect6				270
+__SYSCALL(__NR_pselect6, sys_pselect6)
+#define __NR_ppoll				271
+__SYSCALL(__NR_ppoll,	sys_ppoll)
+#define __NR_unshare				272
+__SYSCALL(__NR_unshare,	sys_unshare)
+#define __NR_set_robust_list			273
+__SYSCALL(__NR_set_robust_list, sys_set_robust_list)
+#define __NR_get_robust_list			274
+__SYSCALL(__NR_get_robust_list, sys_get_robust_list)
+#define __NR_splice				275
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_tee				276
+__SYSCALL(__NR_tee, sys_tee)
+#define __NR_sync_file_range			277
+__SYSCALL(__NR_sync_file_range, sys_sync_file_range)
+#define __NR_vmsplice				278
+__SYSCALL(__NR_vmsplice, sys_vmsplice)
+#define __NR_move_pages				279
+__SYSCALL(__NR_move_pages, sys_move_pages)
+#define __NR_utimensat				280
+__SYSCALL(__NR_utimensat, sys_utimensat)
+#define __IGNORE_getcpu		/* implemented as a vsyscall */
+#define __NR_epoll_pwait			281
+__SYSCALL(__NR_epoll_pwait, sys_epoll_pwait)
+#define __NR_signalfd				282
+__SYSCALL(__NR_signalfd, sys_signalfd)
+#define __NR_timerfd_create			283
+__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#define __NR_eventfd				284
+__SYSCALL(__NR_eventfd, sys_eventfd)
+#define __NR_fallocate				285
+__SYSCALL(__NR_fallocate, sys_fallocate)
+#define __NR_timerfd_settime			286
+__SYSCALL(__NR_timerfd_settime, sys_timerfd_settime)
+#define __NR_timerfd_gettime			287
+__SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime)
+#define __NR_paccept				288
+__SYSCALL(__NR_paccept, sys_paccept)
+#define __NR_signalfd4				289
+__SYSCALL(__NR_signalfd4, sys_signalfd4)
+#define __NR_eventfd2				290
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+#define __NR_epoll_create1			291
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_dup3				292
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR_pipe2				293
+__SYSCALL(__NR_pipe2, sys_pipe2)
+#define __NR_inotify_init1			294
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+
+
+#ifndef __NO_STUBS
+#define __ARCH_WANT_OLD_READDIR
+#define __ARCH_WANT_OLD_STAT
+#define __ARCH_WANT_SYS_ALARM
+#define __ARCH_WANT_SYS_GETHOSTNAME
+#define __ARCH_WANT_SYS_PAUSE
+#define __ARCH_WANT_SYS_SGETMASK
+#define __ARCH_WANT_SYS_SIGNAL
+#define __ARCH_WANT_SYS_UTIME
+#define __ARCH_WANT_SYS_WAITPID
+#define __ARCH_WANT_SYS_SOCKETCALL
+#define __ARCH_WANT_SYS_FADVISE64
+#define __ARCH_WANT_SYS_GETPGRP
+#define __ARCH_WANT_SYS_LLSEEK
+#define __ARCH_WANT_SYS_NICE
+#define __ARCH_WANT_SYS_OLD_GETRLIMIT
+#define __ARCH_WANT_SYS_OLDUMOUNT
+#define __ARCH_WANT_SYS_SIGPENDING
+#define __ARCH_WANT_SYS_SIGPROCMASK
+#define __ARCH_WANT_SYS_RT_SIGACTION
+#define __ARCH_WANT_SYS_RT_SIGSUSPEND
+#define __ARCH_WANT_SYS_TIME
+#define __ARCH_WANT_COMPAT_SYS_TIME
+#endif	/* __NO_STUBS */
+
+#ifdef __KERNEL__
+/*
+ * "Conditional" syscalls
+ *
+ * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
+ * but it doesn't work on all toolchains, so we just do it by hand
+ */
+#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
+#endif	/* __KERNEL__ */
+
+#endif /* ASM_X86__UNISTD_64_H */
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
new file mode 100644
index 000000000000..a2151567db44
--- /dev/null
+++ b/arch/x86/include/asm/unwind.h
@@ -0,0 +1,13 @@
+#ifndef ASM_X86__UNWIND_H
+#define ASM_X86__UNWIND_H
+
+#define UNW_PC(frame) ((void)(frame), 0UL)
+#define UNW_SP(frame) ((void)(frame), 0UL)
+#define UNW_FP(frame) ((void)(frame), 0UL)
+
+static inline int arch_unw_user_mode(const void *info)
+{
+	return 0;
+}
+
+#endif /* ASM_X86__UNWIND_H */
diff --git a/arch/x86/include/asm/user.h b/arch/x86/include/asm/user.h
new file mode 100644
index 000000000000..999873b22e7f
--- /dev/null
+++ b/arch/x86/include/asm/user.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "user_32.h"
+#else
+# include "user_64.h"
+#endif
diff --git a/arch/x86/include/asm/user32.h b/arch/x86/include/asm/user32.h
new file mode 100644
index 000000000000..aa66c1857f06
--- /dev/null
+++ b/arch/x86/include/asm/user32.h
@@ -0,0 +1,70 @@
+#ifndef ASM_X86__USER32_H
+#define ASM_X86__USER32_H
+
+/* IA32 compatible user structures for ptrace.
+ * These should be used for 32bit coredumps too. */
+
+struct user_i387_ia32_struct {
+	u32	cwd;
+	u32	swd;
+	u32	twd;
+	u32	fip;
+	u32	fcs;
+	u32	foo;
+	u32	fos;
+	u32	st_space[20];   /* 8*10 bytes for each FP-reg = 80 bytes */
+};
+
+/* FSAVE frame with extensions */
+struct user32_fxsr_struct {
+	unsigned short	cwd;
+	unsigned short	swd;
+	unsigned short	twd;	/* not compatible to 64bit twd */
+	unsigned short	fop;
+	int	fip;
+	int	fcs;
+	int	foo;
+	int	fos;
+	int	mxcsr;
+	int	reserved;
+	int	st_space[32];	/* 8*16 bytes for each FP-reg = 128 bytes */
+	int	xmm_space[32];	/* 8*16 bytes for each XMM-reg = 128 bytes */
+	int	padding[56];
+};
+
+struct user_regs_struct32 {
+	__u32 ebx, ecx, edx, esi, edi, ebp, eax;
+	unsigned short ds, __ds, es, __es;
+	unsigned short fs, __fs, gs, __gs;
+	__u32 orig_eax, eip;
+	unsigned short cs, __cs;
+	__u32 eflags, esp;
+	unsigned short ss, __ss;
+};
+
+struct user32 {
+  struct user_regs_struct32 regs; /* Where the registers are actually stored */
+  int u_fpvalid;		/* True if math co-processor being used. */
+				/* for this mess. Not yet used. */
+  struct user_i387_ia32_struct i387;	/* Math Co-processor registers. */
+/* The rest of this junk is to help gdb figure out what goes where */
+  __u32 u_tsize;	/* Text segment size (pages). */
+  __u32 u_dsize;	/* Data segment size (pages). */
+  __u32 u_ssize;	/* Stack segment size (pages). */
+  __u32 start_code;     /* Starting virtual address of text. */
+  __u32 start_stack;	/* Starting virtual address of stack area.
+				   This is actually the bottom of the stack,
+				   the top of the stack is always found in the
+				   esp register.  */
+  __u32 signal;     		/* Signal that caused the core dump. */
+  int reserved;			/* No __u32er used */
+  __u32 u_ar0;	/* Used by gdb to help find the values for */
+				/* the registers. */
+  __u32 u_fpstate;	/* Math Co-processor pointer. */
+  __u32 magic;		/* To uniquely identify a core file */
+  char u_comm[32];		/* User command that was responsible */
+  int u_debugreg[8];
+};
+
+
+#endif /* ASM_X86__USER32_H */
diff --git a/arch/x86/include/asm/user_32.h b/arch/x86/include/asm/user_32.h
new file mode 100644
index 000000000000..e0fe2f55f1a6
--- /dev/null
+++ b/arch/x86/include/asm/user_32.h
@@ -0,0 +1,131 @@
+#ifndef ASM_X86__USER_32_H
+#define ASM_X86__USER_32_H
+
+#include <asm/page.h>
+/* Core file format: The core file is written in such a way that gdb
+   can understand it and provide useful information to the user (under
+   linux we use the 'trad-core' bfd).  There are quite a number of
+   obstacles to being able to view the contents of the floating point
+   registers, and until these are solved you will not be able to view the
+   contents of them.  Actually, you can read in the core file and look at
+   the contents of the user struct to find out what the floating point
+   registers contain.
+   The actual file contents are as follows:
+   UPAGE: 1 page consisting of a user struct that tells gdb what is present
+   in the file.  Directly after this is a copy of the task_struct, which
+   is currently not used by gdb, but it may come in useful at some point.
+   All of the registers are stored as part of the upage.  The upage should
+   always be only one page.
+   DATA: The data area is stored.  We use current->end_text to
+   current->brk to pick up all of the user variables, plus any memory
+   that may have been malloced.  No attempt is made to determine if a page
+   is demand-zero or if a page is totally unused, we just cover the entire
+   range.  All of the addresses are rounded in such a way that an integral
+   number of pages is written.
+   STACK: We need the stack information in order to get a meaningful
+   backtrace.  We need to write the data from (esp) to
+   current->start_stack, so we round each of these off in order to be able
+   to write an integer number of pages.
+   The minimum core file size is 3 pages, or 12288 bytes.
+*/
+
+/*
+ * Pentium III FXSR, SSE support
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ *
+ * Provide support for the GDB 5.0+ PTRACE_{GET|SET}FPXREGS requests for
+ * interacting with the FXSR-format floating point environment.  Floating
+ * point data can be accessed in the regular format in the usual manner,
+ * and both the standard and SIMD floating point data can be accessed via
+ * the new ptrace requests.  In either case, changes to the FPU environment
+ * will be reflected in the task's state as expected.
+ */
+
+struct user_i387_struct {
+	long	cwd;
+	long	swd;
+	long	twd;
+	long	fip;
+	long	fcs;
+	long	foo;
+	long	fos;
+	long	st_space[20];	/* 8*10 bytes for each FP-reg = 80 bytes */
+};
+
+struct user_fxsr_struct {
+	unsigned short	cwd;
+	unsigned short	swd;
+	unsigned short	twd;
+	unsigned short	fop;
+	long	fip;
+	long	fcs;
+	long	foo;
+	long	fos;
+	long	mxcsr;
+	long	reserved;
+	long	st_space[32];	/* 8*16 bytes for each FP-reg = 128 bytes */
+	long	xmm_space[32];	/* 8*16 bytes for each XMM-reg = 128 bytes */
+	long	padding[56];
+};
+
+/*
+ * This is the old layout of "struct pt_regs", and
+ * is still the layout used by user mode (the new
+ * pt_regs doesn't have all registers as the kernel
+ * doesn't use the extra segment registers)
+ */
+struct user_regs_struct {
+	unsigned long	bx;
+	unsigned long	cx;
+	unsigned long	dx;
+	unsigned long	si;
+	unsigned long	di;
+	unsigned long	bp;
+	unsigned long	ax;
+	unsigned long	ds;
+	unsigned long	es;
+	unsigned long	fs;
+	unsigned long	gs;
+	unsigned long	orig_ax;
+	unsigned long	ip;
+	unsigned long	cs;
+	unsigned long	flags;
+	unsigned long	sp;
+	unsigned long	ss;
+};
+
+/* When the kernel dumps core, it starts by dumping the user struct -
+   this will be used by gdb to figure out where the data and stack segments
+   are within the file, and what virtual addresses to use. */
+struct user{
+/* We start with the registers, to mimic the way that "memory" is returned
+   from the ptrace(3,...) function.  */
+  struct user_regs_struct regs;	/* Where the registers are actually stored */
+/* ptrace does not yet supply these.  Someday.... */
+  int u_fpvalid;		/* True if math co-processor being used. */
+				/* for this mess. Not yet used. */
+  struct user_i387_struct i387;	/* Math Co-processor registers. */
+/* The rest of this junk is to help gdb figure out what goes where */
+  unsigned long int u_tsize;	/* Text segment size (pages). */
+  unsigned long int u_dsize;	/* Data segment size (pages). */
+  unsigned long int u_ssize;	/* Stack segment size (pages). */
+  unsigned long start_code;     /* Starting virtual address of text. */
+  unsigned long start_stack;	/* Starting virtual address of stack area.
+				   This is actually the bottom of the stack,
+				   the top of the stack is always found in the
+				   esp register.  */
+  long int signal;     		/* Signal that caused the core dump. */
+  int reserved;			/* No longer used */
+  unsigned long u_ar0;		/* Used by gdb to help find the values for */
+				/* the registers. */
+  struct user_i387_struct *u_fpstate;	/* Math Co-processor pointer. */
+  unsigned long magic;		/* To uniquely identify a core file */
+  char u_comm[32];		/* User command that was responsible */
+  int u_debugreg[8];
+};
+#define NBPG PAGE_SIZE
+#define UPAGES 1
+#define HOST_TEXT_START_ADDR (u.start_code)
+#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
+
+#endif /* ASM_X86__USER_32_H */
diff --git a/arch/x86/include/asm/user_64.h b/arch/x86/include/asm/user_64.h
new file mode 100644
index 000000000000..38b5799863b4
--- /dev/null
+++ b/arch/x86/include/asm/user_64.h
@@ -0,0 +1,137 @@
+#ifndef ASM_X86__USER_64_H
+#define ASM_X86__USER_64_H
+
+#include <asm/types.h>
+#include <asm/page.h>
+/* Core file format: The core file is written in such a way that gdb
+   can understand it and provide useful information to the user.
+   There are quite a number of obstacles to being able to view the
+   contents of the floating point registers, and until these are
+   solved you will not be able to view the contents of them.
+   Actually, you can read in the core file and look at the contents of
+   the user struct to find out what the floating point registers
+   contain.
+
+   The actual file contents are as follows:
+   UPAGE: 1 page consisting of a user struct that tells gdb what is present
+   in the file.  Directly after this is a copy of the task_struct, which
+   is currently not used by gdb, but it may come in useful at some point.
+   All of the registers are stored as part of the upage.  The upage should
+   always be only one page.
+   DATA: The data area is stored.  We use current->end_text to
+   current->brk to pick up all of the user variables, plus any memory
+   that may have been malloced.  No attempt is made to determine if a page
+   is demand-zero or if a page is totally unused, we just cover the entire
+   range.  All of the addresses are rounded in such a way that an integral
+   number of pages is written.
+   STACK: We need the stack information in order to get a meaningful
+   backtrace.  We need to write the data from (esp) to
+   current->start_stack, so we round each of these off in order to be able
+   to write an integer number of pages.
+   The minimum core file size is 3 pages, or 12288 bytes.  */
+
+/*
+ * Pentium III FXSR, SSE support
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ *
+ * Provide support for the GDB 5.0+ PTRACE_{GET|SET}FPXREGS requests for
+ * interacting with the FXSR-format floating point environment.  Floating
+ * point data can be accessed in the regular format in the usual manner,
+ * and both the standard and SIMD floating point data can be accessed via
+ * the new ptrace requests.  In either case, changes to the FPU environment
+ * will be reflected in the task's state as expected.
+ *
+ * x86-64 support by Andi Kleen.
+ */
+
+/* This matches the 64bit FXSAVE format as defined by AMD. It is the same
+   as the 32bit format defined by Intel, except that the selector:offset pairs
+   for data and eip are replaced with flat 64bit pointers. */
+struct user_i387_struct {
+	unsigned short	cwd;
+	unsigned short	swd;
+	unsigned short	twd;	/* Note this is not the same as
+				   the 32bit/x87/FSAVE twd */
+	unsigned short	fop;
+	__u64	rip;
+	__u64	rdp;
+	__u32	mxcsr;
+	__u32	mxcsr_mask;
+	__u32	st_space[32];	/* 8*16 bytes for each FP-reg = 128 bytes */
+	__u32	xmm_space[64];	/* 16*16 bytes for each XMM-reg = 256 bytes */
+	__u32	padding[24];
+};
+
+/*
+ * Segment register layout in coredumps.
+ */
+struct user_regs_struct {
+	unsigned long	r15;
+	unsigned long	r14;
+	unsigned long	r13;
+	unsigned long	r12;
+	unsigned long	bp;
+	unsigned long	bx;
+	unsigned long	r11;
+	unsigned long	r10;
+	unsigned long	r9;
+	unsigned long	r8;
+	unsigned long	ax;
+	unsigned long	cx;
+	unsigned long	dx;
+	unsigned long	si;
+	unsigned long	di;
+	unsigned long	orig_ax;
+	unsigned long	ip;
+	unsigned long	cs;
+	unsigned long	flags;
+	unsigned long	sp;
+	unsigned long	ss;
+	unsigned long	fs_base;
+	unsigned long	gs_base;
+	unsigned long	ds;
+	unsigned long	es;
+	unsigned long	fs;
+	unsigned long	gs;
+};
+
+/* When the kernel dumps core, it starts by dumping the user struct -
+   this will be used by gdb to figure out where the data and stack segments
+   are within the file, and what virtual addresses to use. */
+
+struct user {
+/* We start with the registers, to mimic the way that "memory" is returned
+   from the ptrace(3,...) function.  */
+  struct user_regs_struct regs;	/* Where the registers are actually stored */
+/* ptrace does not yet supply these.  Someday.... */
+  int u_fpvalid;		/* True if math co-processor being used. */
+				/* for this mess. Not yet used. */
+  int pad0;
+  struct user_i387_struct i387;	/* Math Co-processor registers. */
+/* The rest of this junk is to help gdb figure out what goes where */
+  unsigned long int u_tsize;	/* Text segment size (pages). */
+  unsigned long int u_dsize;	/* Data segment size (pages). */
+  unsigned long int u_ssize;	/* Stack segment size (pages). */
+  unsigned long start_code;     /* Starting virtual address of text. */
+  unsigned long start_stack;	/* Starting virtual address of stack area.
+				   This is actually the bottom of the stack,
+				   the top of the stack is always found in the
+				   esp register.  */
+  long int signal;		/* Signal that caused the core dump. */
+  int reserved;			/* No longer used */
+  int pad1;
+  unsigned long u_ar0;		/* Used by gdb to help find the values for */
+				/* the registers. */
+  struct user_i387_struct *u_fpstate;	/* Math Co-processor pointer. */
+  unsigned long magic;		/* To uniquely identify a core file */
+  char u_comm[32];		/* User command that was responsible */
+  unsigned long u_debugreg[8];
+  unsigned long error_code; /* CPU error code or 0 */
+  unsigned long fault_address; /* CR3 or 0 */
+};
+#define NBPG PAGE_SIZE
+#define UPAGES 1
+#define HOST_TEXT_START_ADDR (u.start_code)
+#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
+
+#endif /* ASM_X86__USER_64_H */
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
new file mode 100644
index 000000000000..215f1969c266
--- /dev/null
+++ b/arch/x86/include/asm/uv/bios.h
@@ -0,0 +1,94 @@
+#ifndef ASM_X86__UV__BIOS_H
+#define ASM_X86__UV__BIOS_H
+
+/*
+ * UV BIOS layer definitions.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
+ *  Copyright (c) Russ Anderson
+ */
+
+#include <linux/rtc.h>
+
+/*
+ * Values for the BIOS calls.  It is passed as the first * argument in the
+ * BIOS call.  Passing any other value in the first argument will result
+ * in a BIOS_STATUS_UNIMPLEMENTED return status.
+ */
+enum uv_bios_cmd {
+	UV_BIOS_COMMON,
+	UV_BIOS_GET_SN_INFO,
+	UV_BIOS_FREQ_BASE
+};
+
+/*
+ * Status values returned from a BIOS call.
+ */
+enum {
+	BIOS_STATUS_SUCCESS		=  0,
+	BIOS_STATUS_UNIMPLEMENTED	= -ENOSYS,
+	BIOS_STATUS_EINVAL		= -EINVAL,
+	BIOS_STATUS_UNAVAIL		= -EBUSY
+};
+
+/*
+ * The UV system table describes specific firmware
+ * capabilities available to the Linux kernel at runtime.
+ */
+struct uv_systab {
+	char signature[4];	/* must be "UVST" */
+	u32 revision;		/* distinguish different firmware revs */
+	u64 function;		/* BIOS runtime callback function ptr */
+};
+
+enum {
+	BIOS_FREQ_BASE_PLATFORM = 0,
+	BIOS_FREQ_BASE_INTERVAL_TIMER = 1,
+	BIOS_FREQ_BASE_REALTIME_CLOCK = 2
+};
+
+union partition_info_u {
+	u64	val;
+	struct {
+		u64	hub_version	:  8,
+			partition_id	: 16,
+			coherence_id	: 16,
+			region_size	: 24;
+	};
+};
+
+/*
+ * bios calls have 6 parameters
+ */
+extern s64 uv_bios_call(enum uv_bios_cmd, u64, u64, u64, u64, u64);
+extern s64 uv_bios_call_irqsave(enum uv_bios_cmd, u64, u64, u64, u64, u64);
+extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64);
+
+extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *);
+extern s64 uv_bios_freq_base(u64, u64 *);
+
+extern void uv_bios_init(void);
+
+extern int uv_type;
+extern long sn_partition_id;
+extern long uv_coherency_id;
+extern long uv_region_size;
+#define partition_coherence_id()	(uv_coherency_id)
+
+extern struct kobject *sgi_uv_kobj;	/* /sys/firmware/sgi_uv */
+
+#endif /* ASM_X86__UV__BIOS_H */
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
new file mode 100644
index 000000000000..77153fb18f5e
--- /dev/null
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -0,0 +1,332 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * SGI UV Broadcast Assist Unit definitions
+ *
+ * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
+ */
+
+#ifndef ASM_X86__UV__UV_BAU_H
+#define ASM_X86__UV__UV_BAU_H
+
+#include <linux/bitmap.h>
+#define BITSPERBYTE 8
+
+/*
+ * Broadcast Assist Unit messaging structures
+ *
+ * Selective Broadcast activations are induced by software action
+ * specifying a particular 8-descriptor "set" via a 6-bit index written
+ * to an MMR.
+ * Thus there are 64 unique 512-byte sets of SB descriptors - one set for
+ * each 6-bit index value. These descriptor sets are mapped in sequence
+ * starting with set 0 located at the address specified in the
+ * BAU_SB_DESCRIPTOR_BASE register, set 1 is located at BASE + 512,
+ * set 2 is at BASE + 2*512, set 3 at BASE + 3*512, and so on.
+ *
+ * We will use 31 sets, one for sending BAU messages from each of the 32
+ * cpu's on the node.
+ *
+ * TLB shootdown will use the first of the 8 descriptors of each set.
+ * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set).
+ */
+
+#define UV_ITEMS_PER_DESCRIPTOR		8
+#define UV_CPUS_PER_ACT_STATUS		32
+#define UV_ACT_STATUS_MASK		0x3
+#define UV_ACT_STATUS_SIZE		2
+#define UV_ACTIVATION_DESCRIPTOR_SIZE	32
+#define UV_DISTRIBUTION_SIZE		256
+#define UV_SW_ACK_NPENDING		8
+#define UV_NET_ENDPOINT_INTD		0x38
+#define UV_DESC_BASE_PNODE_SHIFT	49
+#define UV_PAYLOADQ_PNODE_SHIFT		49
+#define UV_PTC_BASENAME			"sgi_uv/ptc_statistics"
+#define uv_physnodeaddr(x)		((__pa((unsigned long)(x)) & uv_mmask))
+
+/*
+ * bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1
+ */
+#define DESC_STATUS_IDLE		0
+#define DESC_STATUS_ACTIVE		1
+#define DESC_STATUS_DESTINATION_TIMEOUT	2
+#define DESC_STATUS_SOURCE_TIMEOUT	3
+
+/*
+ * source side threshholds at which message retries print a warning
+ */
+#define SOURCE_TIMEOUT_LIMIT		20
+#define DESTINATION_TIMEOUT_LIMIT	20
+
+/*
+ * number of entries in the destination side payload queue
+ */
+#define DEST_Q_SIZE			17
+/*
+ * number of destination side software ack resources
+ */
+#define DEST_NUM_RESOURCES		8
+#define MAX_CPUS_PER_NODE		32
+/*
+ * completion statuses for sending a TLB flush message
+ */
+#define	FLUSH_RETRY			1
+#define	FLUSH_GIVEUP			2
+#define	FLUSH_COMPLETE			3
+
+/*
+ * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor)
+ * If the 'multilevel' flag in the header portion of the descriptor
+ * has been set to 0, then endpoint multi-unicast mode is selected.
+ * The distribution specification (32 bytes) is interpreted as a 256-bit
+ * distribution vector. Adjacent bits correspond to consecutive even numbered
+ * nodeIDs. The result of adding the index of a given bit to the 15-bit
+ * 'base_dest_nodeid' field of the header corresponds to the
+ * destination nodeID associated with that specified bit.
+ */
+struct bau_target_nodemask {
+	unsigned long bits[BITS_TO_LONGS(256)];
+};
+
+/*
+ * mask of cpu's on a node
+ * (during initialization we need to check that unsigned long has
+ *  enough bits for max. cpu's per node)
+ */
+struct bau_local_cpumask {
+	unsigned long bits;
+};
+
+/*
+ * Payload: 16 bytes (128 bits) (bytes 0x20-0x2f of descriptor)
+ * only 12 bytes (96 bits) of the payload area are usable.
+ * An additional 3 bytes (bits 27:4) of the header address are carried
+ * to the next bytes of the destination payload queue.
+ * And an additional 2 bytes of the header Suppl_A field are also
+ * carried to the destination payload queue.
+ * But the first byte of the Suppl_A becomes bits 127:120 (the 16th byte)
+ * of the destination payload queue, which is written by the hardware
+ * with the s/w ack resource bit vector.
+ * [ effective message contents (16 bytes (128 bits) maximum), not counting
+ *   the s/w ack bit vector  ]
+ */
+
+/*
+ * The payload is software-defined for INTD transactions
+ */
+struct bau_msg_payload {
+	unsigned long address;		/* signifies a page or all TLB's
+						of the cpu */
+	/* 64 bits */
+	unsigned short sending_cpu;	/* filled in by sender */
+	/* 16 bits */
+	unsigned short acknowledge_count;/* filled in by destination */
+	/* 16 bits */
+	unsigned int reserved1:32;	/* not usable */
+};
+
+
+/*
+ * Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
+ * see table 4.2.3.0.1 in broacast_assist spec.
+ */
+struct bau_msg_header {
+	int dest_subnodeid:6;	/* must be zero */
+	/* bits 5:0 */
+	int base_dest_nodeid:15; /* nasid>>1 (pnode) of first bit in node_map */
+	/* bits 20:6 */
+	int command:8;		/* message type */
+	/* bits 28:21 */
+				/* 0x38: SN3net EndPoint Message */
+	int rsvd_1:3;		/* must be zero */
+	/* bits 31:29 */
+				/* int will align on 32 bits */
+	int rsvd_2:9;		/* must be zero */
+	/* bits 40:32 */
+				/* Suppl_A is 56-41 */
+	int payload_2a:8;	/* becomes byte 16 of msg */
+	/* bits 48:41 */	/* not currently using */
+	int payload_2b:8;	/* becomes byte 17 of msg */
+	/* bits 56:49 */	/* not currently using */
+				/* Address field (96:57) is never used as an
+				   address (these are address bits 42:3) */
+	int rsvd_3:1;		/* must be zero */
+	/* bit 57 */
+				/* address bits 27:4 are payload */
+				/* these 24 bits become bytes 12-14 of msg */
+	int replied_to:1;	/* sent as 0 by the source to byte 12 */
+	/* bit 58 */
+
+	int payload_1a:5;	/* not currently used */
+	/* bits 63:59 */
+	int payload_1b:8;	/* not currently used */
+	/* bits 71:64 */
+	int payload_1c:8;	/* not currently used */
+	/* bits 79:72 */
+	int payload_1d:2;	/* not currently used */
+	/* bits 81:80 */
+
+	int rsvd_4:7;		/* must be zero */
+	/* bits 88:82 */
+	int sw_ack_flag:1;	/* software acknowledge flag */
+	/* bit 89 */
+				/* INTD trasactions at destination are to
+				   wait for software acknowledge */
+	int rsvd_5:6;		/* must be zero */
+	/* bits 95:90 */
+	int rsvd_6:5;		/* must be zero */
+	/* bits 100:96 */
+	int int_both:1;		/* if 1, interrupt both sockets on the blade */
+	/* bit 101*/
+	int fairness:3;		/* usually zero */
+	/* bits 104:102 */
+	int multilevel:1;	/* multi-level multicast format */
+	/* bit 105 */
+				/* 0 for TLB: endpoint multi-unicast messages */
+	int chaining:1;		/* next descriptor is part of this activation*/
+	/* bit 106 */
+	int rsvd_7:21;		/* must be zero */
+	/* bits 127:107 */
+};
+
+/*
+ * The activation descriptor:
+ * The format of the message to send, plus all accompanying control
+ * Should be 64 bytes
+ */
+struct bau_desc {
+	struct bau_target_nodemask distribution;
+	/*
+	 * message template, consisting of header and payload:
+	 */
+	struct bau_msg_header header;
+	struct bau_msg_payload payload;
+};
+/*
+ *   -payload--    ---------header------
+ *   bytes 0-11    bits 41-56  bits 58-81
+ *       A           B  (2)      C (3)
+ *
+ *            A/B/C are moved to:
+ *       A            C          B
+ *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
+ *   ------------payload queue-----------
+ */
+
+/*
+ * The payload queue on the destination side is an array of these.
+ * With BAU_MISC_CONTROL set for software acknowledge mode, the messages
+ * are 32 bytes (2 micropackets) (256 bits) in length, but contain only 17
+ * bytes of usable data, including the sw ack vector in byte 15 (bits 127:120)
+ * (12 bytes come from bau_msg_payload, 3 from payload_1, 2 from
+ *  sw_ack_vector and payload_2)
+ * "Enabling Software Acknowledgment mode (see Section 4.3.3 Software
+ *  Acknowledge Processing) also selects 32 byte (17 bytes usable) payload
+ *  operation."
+ */
+struct bau_payload_queue_entry {
+	unsigned long address;		/* signifies a page or all TLB's
+						of the cpu */
+	/* 64 bits, bytes 0-7 */
+
+	unsigned short sending_cpu;	/* cpu that sent the message */
+	/* 16 bits, bytes 8-9 */
+
+	unsigned short acknowledge_count; /* filled in by destination */
+	/* 16 bits, bytes 10-11 */
+
+	unsigned short replied_to:1;	/* sent as 0 by the source */
+	/* 1 bit */
+	unsigned short unused1:7;       /* not currently using */
+	/* 7 bits: byte 12) */
+
+	unsigned char unused2[2];	/* not currently using */
+	/* bytes 13-14 */
+
+	unsigned char sw_ack_vector;	/* filled in by the hardware */
+	/* byte 15 (bits 127:120) */
+
+	unsigned char unused4[3];	/* not currently using bytes 17-19 */
+	/* bytes 17-19 */
+
+	int number_of_cpus;		/* filled in at destination */
+	/* 32 bits, bytes 20-23 (aligned) */
+
+	unsigned char unused5[8];       /* not using */
+	/* bytes 24-31 */
+};
+
+/*
+ * one for every slot in the destination payload queue
+ */
+struct bau_msg_status {
+	struct bau_local_cpumask seen_by;	/* map of cpu's */
+};
+
+/*
+ * one for every slot in the destination software ack resources
+ */
+struct bau_sw_ack_status {
+	struct bau_payload_queue_entry *msg;	/* associated message */
+	int watcher;				/* cpu monitoring, or -1 */
+};
+
+/*
+ * one on every node and per-cpu; to locate the software tables
+ */
+struct bau_control {
+	struct bau_desc *descriptor_base;
+	struct bau_payload_queue_entry *bau_msg_head;
+	struct bau_payload_queue_entry *va_queue_first;
+	struct bau_payload_queue_entry *va_queue_last;
+	struct bau_msg_status *msg_statuses;
+	int *watching; /* pointer to array */
+};
+
+/*
+ * This structure is allocated per_cpu for UV TLB shootdown statistics.
+ */
+struct ptc_stats {
+	unsigned long ptc_i;	/* number of IPI-style flushes */
+	unsigned long requestor;	/* number of nodes this cpu sent to */
+	unsigned long requestee;	/* times cpu was remotely requested */
+	unsigned long alltlb;	/* times all tlb's on this cpu were flushed */
+	unsigned long onetlb;	/* times just one tlb on this cpu was flushed */
+	unsigned long s_retry;	/* retries on source side timeouts */
+	unsigned long d_retry;	/* retries on destination side timeouts */
+	unsigned long sflush;	/* cycles spent in uv_flush_tlb_others */
+	unsigned long dflush;	/* cycles spent on destination side */
+	unsigned long retriesok; /* successes on retries */
+	unsigned long nomsg;	/* interrupts with no message */
+	unsigned long multmsg;	/* interrupts with multiple messages */
+	unsigned long ntargeted;/* nodes targeted */
+};
+
+static inline int bau_node_isset(int node, struct bau_target_nodemask *dstp)
+{
+	return constant_test_bit(node, &dstp->bits[0]);
+}
+static inline void bau_node_set(int node, struct bau_target_nodemask *dstp)
+{
+	__set_bit(node, &dstp->bits[0]);
+}
+static inline void bau_nodes_clear(struct bau_target_nodemask *dstp, int nbits)
+{
+	bitmap_zero(&dstp->bits[0], nbits);
+}
+
+static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits)
+{
+	bitmap_zero(&dstp->bits, nbits);
+}
+
+#define cpubit_isset(cpu, bau_local_cpumask) \
+	test_bit((cpu), (bau_local_cpumask).bits)
+
+extern int uv_flush_tlb_others(cpumask_t *, struct mm_struct *, unsigned long);
+extern void uv_bau_message_intr1(void);
+extern void uv_bau_timeout_intr1(void);
+
+#endif /* ASM_X86__UV__UV_BAU_H */
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
new file mode 100644
index 000000000000..bdb5b01afbf5
--- /dev/null
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -0,0 +1,354 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * SGI UV architectural definitions
+ *
+ * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
+ */
+
+#ifndef ASM_X86__UV__UV_HUB_H
+#define ASM_X86__UV__UV_HUB_H
+
+#include <linux/numa.h>
+#include <linux/percpu.h>
+#include <asm/types.h>
+#include <asm/percpu.h>
+
+
+/*
+ * Addressing Terminology
+ *
+ *	M       - The low M bits of a physical address represent the offset
+ *		  into the blade local memory. RAM memory on a blade is physically
+ *		  contiguous (although various IO spaces may punch holes in
+ *		  it)..
+ *
+ * 	N	- Number of bits in the node portion of a socket physical
+ * 		  address.
+ *
+ * 	NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
+ * 	 	  routers always have low bit of 1, C/MBricks have low bit
+ * 		  equal to 0. Most addressing macros that target UV hub chips
+ * 		  right shift the NASID by 1 to exclude the always-zero bit.
+ * 		  NASIDs contain up to 15 bits.
+ *
+ *	GNODE   - NASID right shifted by 1 bit. Most mmrs contain gnodes instead
+ *		  of nasids.
+ *
+ * 	PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
+ * 		  of the nasid for socket usage.
+ *
+ *
+ *  NumaLink Global Physical Address Format:
+ *  +--------------------------------+---------------------+
+ *  |00..000|      GNODE             |      NodeOffset     |
+ *  +--------------------------------+---------------------+
+ *          |<-------53 - M bits --->|<--------M bits ----->
+ *
+ *	M - number of node offset bits (35 .. 40)
+ *
+ *
+ *  Memory/UV-HUB Processor Socket Address Format:
+ *  +----------------+---------------+---------------------+
+ *  |00..000000000000|   PNODE       |      NodeOffset     |
+ *  +----------------+---------------+---------------------+
+ *                   <--- N bits --->|<--------M bits ----->
+ *
+ *	M - number of node offset bits (35 .. 40)
+ *	N - number of PNODE bits (0 .. 10)
+ *
+ *		Note: M + N cannot currently exceed 44 (x86_64) or 46 (IA64).
+ *		The actual values are configuration dependent and are set at
+ *		boot time. M & N values are set by the hardware/BIOS at boot.
+ *
+ *
+ * APICID format
+ * 	NOTE!!!!!! This is the current format of the APICID. However, code
+ * 	should assume that this will change in the future. Use functions
+ * 	in this file for all APICID bit manipulations and conversion.
+ *
+ * 		1111110000000000
+ * 		5432109876543210
+ *		pppppppppplc0cch
+ *		sssssssssss
+ *
+ *			p  = pnode bits
+ *			l =  socket number on board
+ *			c  = core
+ *			h  = hyperthread
+ *			s  = bits that are in the SOCKET_ID CSR
+ *
+ *	Note: Processor only supports 12 bits in the APICID register. The ACPI
+ *	      tables hold all 16 bits. Software needs to be aware of this.
+ *
+ * 	      Unless otherwise specified, all references to APICID refer to
+ * 	      the FULL value contained in ACPI tables, not the subset in the
+ * 	      processor APICID register.
+ */
+
+
+/*
+ * Maximum number of bricks in all partitions and in all coherency domains.
+ * This is the total number of bricks accessible in the numalink fabric. It
+ * includes all C & M bricks. Routers are NOT included.
+ *
+ * This value is also the value of the maximum number of non-router NASIDs
+ * in the numalink fabric.
+ *
+ * NOTE: a brick may contain 1 or 2 OS nodes. Don't get these confused.
+ */
+#define UV_MAX_NUMALINK_BLADES	16384
+
+/*
+ * Maximum number of C/Mbricks within a software SSI (hardware may support
+ * more).
+ */
+#define UV_MAX_SSI_BLADES	256
+
+/*
+ * The largest possible NASID of a C or M brick (+ 2)
+ */
+#define UV_MAX_NASID_VALUE	(UV_MAX_NUMALINK_NODES * 2)
+
+/*
+ * The following defines attributes of the HUB chip. These attributes are
+ * frequently referenced and are kept in the per-cpu data areas of each cpu.
+ * They are kept together in a struct to minimize cache misses.
+ */
+struct uv_hub_info_s {
+	unsigned long	global_mmr_base;
+	unsigned long	gpa_mask;
+	unsigned long	gnode_upper;
+	unsigned long	lowmem_remap_top;
+	unsigned long	lowmem_remap_base;
+	unsigned short	pnode;
+	unsigned short	pnode_mask;
+	unsigned short	coherency_domain_number;
+	unsigned short	numa_blade_id;
+	unsigned char	blade_processor_id;
+	unsigned char	m_val;
+	unsigned char	n_val;
+};
+DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
+#define uv_hub_info 		(&__get_cpu_var(__uv_hub_info))
+#define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
+
+/*
+ * Local & Global MMR space macros.
+ * 	Note: macros are intended to be used ONLY by inline functions
+ * 	in this file - not by other kernel code.
+ * 		n -  NASID (full 15-bit global nasid)
+ * 		g -  GNODE (full 15-bit global nasid, right shifted 1)
+ * 		p -  PNODE (local part of nsids, right shifted 1)
+ */
+#define UV_NASID_TO_PNODE(n)		(((n) >> 1) & uv_hub_info->pnode_mask)
+#define UV_PNODE_TO_NASID(p)		(((p) << 1) | uv_hub_info->gnode_upper)
+
+#define UV_LOCAL_MMR_BASE		0xf4000000UL
+#define UV_GLOBAL_MMR32_BASE		0xf8000000UL
+#define UV_GLOBAL_MMR64_BASE		(uv_hub_info->global_mmr_base)
+#define UV_LOCAL_MMR_SIZE		(64UL * 1024 * 1024)
+#define UV_GLOBAL_MMR32_SIZE		(64UL * 1024 * 1024)
+
+#define UV_GLOBAL_MMR32_PNODE_SHIFT	15
+#define UV_GLOBAL_MMR64_PNODE_SHIFT	26
+
+#define UV_GLOBAL_MMR32_PNODE_BITS(p)	((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
+
+#define UV_GLOBAL_MMR64_PNODE_BITS(p)					\
+	((unsigned long)(p) << UV_GLOBAL_MMR64_PNODE_SHIFT)
+
+#define UV_APIC_PNODE_SHIFT	6
+
+/*
+ * Macros for converting between kernel virtual addresses, socket local physical
+ * addresses, and UV global physical addresses.
+ * 	Note: use the standard __pa() & __va() macros for converting
+ * 	      between socket virtual and socket physical addresses.
+ */
+
+/* socket phys RAM --> UV global physical address */
+static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
+{
+	if (paddr < uv_hub_info->lowmem_remap_top)
+		paddr += uv_hub_info->lowmem_remap_base;
+	return paddr | uv_hub_info->gnode_upper;
+}
+
+
+/* socket virtual --> UV global physical address */
+static inline unsigned long uv_gpa(void *v)
+{
+	return __pa(v) | uv_hub_info->gnode_upper;
+}
+
+/* socket virtual --> UV global physical address */
+static inline void *uv_vgpa(void *v)
+{
+	return (void *)uv_gpa(v);
+}
+
+/* UV global physical address --> socket virtual */
+static inline void *uv_va(unsigned long gpa)
+{
+	return __va(gpa & uv_hub_info->gpa_mask);
+}
+
+/* pnode, offset --> socket virtual */
+static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
+{
+	return __va(((unsigned long)pnode << uv_hub_info->m_val) | offset);
+}
+
+
+/*
+ * Extract a PNODE from an APICID (full apicid, not processor subset)
+ */
+static inline int uv_apicid_to_pnode(int apicid)
+{
+	return (apicid >> UV_APIC_PNODE_SHIFT);
+}
+
+/*
+ * Access global MMRs using the low memory MMR32 space. This region supports
+ * faster MMR access but not all MMRs are accessible in this space.
+ */
+static inline unsigned long *uv_global_mmr32_address(int pnode,
+				unsigned long offset)
+{
+	return __va(UV_GLOBAL_MMR32_BASE |
+		       UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset);
+}
+
+static inline void uv_write_global_mmr32(int pnode, unsigned long offset,
+				 unsigned long val)
+{
+	*uv_global_mmr32_address(pnode, offset) = val;
+}
+
+static inline unsigned long uv_read_global_mmr32(int pnode,
+						 unsigned long offset)
+{
+	return *uv_global_mmr32_address(pnode, offset);
+}
+
+/*
+ * Access Global MMR space using the MMR space located at the top of physical
+ * memory.
+ */
+static inline unsigned long *uv_global_mmr64_address(int pnode,
+				unsigned long offset)
+{
+	return __va(UV_GLOBAL_MMR64_BASE |
+		    UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset);
+}
+
+static inline void uv_write_global_mmr64(int pnode, unsigned long offset,
+				unsigned long val)
+{
+	*uv_global_mmr64_address(pnode, offset) = val;
+}
+
+static inline unsigned long uv_read_global_mmr64(int pnode,
+						 unsigned long offset)
+{
+	return *uv_global_mmr64_address(pnode, offset);
+}
+
+/*
+ * Access hub local MMRs. Faster than using global space but only local MMRs
+ * are accessible.
+ */
+static inline unsigned long *uv_local_mmr_address(unsigned long offset)
+{
+	return __va(UV_LOCAL_MMR_BASE | offset);
+}
+
+static inline unsigned long uv_read_local_mmr(unsigned long offset)
+{
+	return *uv_local_mmr_address(offset);
+}
+
+static inline void uv_write_local_mmr(unsigned long offset, unsigned long val)
+{
+	*uv_local_mmr_address(offset) = val;
+}
+
+/*
+ * Structures and definitions for converting between cpu, node, pnode, and blade
+ * numbers.
+ */
+struct uv_blade_info {
+	unsigned short	nr_possible_cpus;
+	unsigned short	nr_online_cpus;
+	unsigned short	pnode;
+};
+extern struct uv_blade_info *uv_blade_info;
+extern short *uv_node_to_blade;
+extern short *uv_cpu_to_blade;
+extern short uv_possible_blades;
+
+/* Blade-local cpu number of current cpu. Numbered 0 .. <# cpus on the blade> */
+static inline int uv_blade_processor_id(void)
+{
+	return uv_hub_info->blade_processor_id;
+}
+
+/* Blade number of current cpu. Numnbered 0 .. <#blades -1> */
+static inline int uv_numa_blade_id(void)
+{
+	return uv_hub_info->numa_blade_id;
+}
+
+/* Convert a cpu number to the the UV blade number */
+static inline int uv_cpu_to_blade_id(int cpu)
+{
+	return uv_cpu_to_blade[cpu];
+}
+
+/* Convert linux node number to the UV blade number */
+static inline int uv_node_to_blade_id(int nid)
+{
+	return uv_node_to_blade[nid];
+}
+
+/* Convert a blade id to the PNODE of the blade */
+static inline int uv_blade_to_pnode(int bid)
+{
+	return uv_blade_info[bid].pnode;
+}
+
+/* Determine the number of possible cpus on a blade */
+static inline int uv_blade_nr_possible_cpus(int bid)
+{
+	return uv_blade_info[bid].nr_possible_cpus;
+}
+
+/* Determine the number of online cpus on a blade */
+static inline int uv_blade_nr_online_cpus(int bid)
+{
+	return uv_blade_info[bid].nr_online_cpus;
+}
+
+/* Convert a cpu id to the PNODE of the blade containing the cpu */
+static inline int uv_cpu_to_pnode(int cpu)
+{
+	return uv_blade_info[uv_cpu_to_blade_id(cpu)].pnode;
+}
+
+/* Convert a linux node number to the PNODE of the blade */
+static inline int uv_node_to_pnode(int nid)
+{
+	return uv_blade_info[uv_node_to_blade_id(nid)].pnode;
+}
+
+/* Maximum possible number of blades */
+static inline int uv_num_possible_blades(void)
+{
+	return uv_possible_blades;
+}
+
+#endif /* ASM_X86__UV__UV_HUB_H */
+
diff --git a/arch/x86/include/asm/uv/uv_irq.h b/arch/x86/include/asm/uv/uv_irq.h
new file mode 100644
index 000000000000..8bf5f32da9c6
--- /dev/null
+++ b/arch/x86/include/asm/uv/uv_irq.h
@@ -0,0 +1,36 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * SGI UV IRQ definitions
+ *
+ * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
+ */
+
+#ifndef ASM_X86__UV__UV_IRQ_H
+#define ASM_X86__UV__UV_IRQ_H
+
+/* If a generic version of this structure gets defined, eliminate this one. */
+struct uv_IO_APIC_route_entry {
+	__u64	vector		:  8,
+		delivery_mode	:  3,
+		dest_mode	:  1,
+		delivery_status	:  1,
+		polarity	:  1,
+		__reserved_1	:  1,
+		trigger		:  1,
+		mask		:  1,
+		__reserved_2	: 15,
+		dest		: 32;
+};
+
+extern struct irq_chip uv_irq_chip;
+
+extern int arch_enable_uv_irq(char *, unsigned int, int, int, unsigned long);
+extern void arch_disable_uv_irq(int, unsigned long);
+
+extern int uv_setup_irq(char *, int, int, unsigned long);
+extern void uv_teardown_irq(unsigned int, int, unsigned long);
+
+#endif /* ASM_X86__UV__UV_IRQ_H */
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
new file mode 100644
index 000000000000..8b03d89d2459
--- /dev/null
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -0,0 +1,1295 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * SGI UV MMR definitions
+ *
+ * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
+ */
+
+#ifndef ASM_X86__UV__UV_MMRS_H
+#define ASM_X86__UV__UV_MMRS_H
+
+#define UV_MMR_ENABLE		(1UL << 63)
+
+/* ========================================================================= */
+/*                           UVH_BAU_DATA_CONFIG                             */
+/* ========================================================================= */
+#define UVH_BAU_DATA_CONFIG 0x61680UL
+#define UVH_BAU_DATA_CONFIG_32 0x0438
+
+#define UVH_BAU_DATA_CONFIG_VECTOR_SHFT 0
+#define UVH_BAU_DATA_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_BAU_DATA_CONFIG_DM_SHFT 8
+#define UVH_BAU_DATA_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_BAU_DATA_CONFIG_DESTMODE_SHFT 11
+#define UVH_BAU_DATA_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_BAU_DATA_CONFIG_STATUS_SHFT 12
+#define UVH_BAU_DATA_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_BAU_DATA_CONFIG_P_SHFT 13
+#define UVH_BAU_DATA_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_BAU_DATA_CONFIG_T_SHFT 15
+#define UVH_BAU_DATA_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_BAU_DATA_CONFIG_M_SHFT 16
+#define UVH_BAU_DATA_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_BAU_DATA_CONFIG_APIC_ID_SHFT 32
+#define UVH_BAU_DATA_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_bau_data_config_u {
+    unsigned long	v;
+    struct uvh_bau_data_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                           UVH_EVENT_OCCURRED0                             */
+/* ========================================================================= */
+#define UVH_EVENT_OCCURRED0 0x70000UL
+#define UVH_EVENT_OCCURRED0_32 0x005e8
+
+#define UVH_EVENT_OCCURRED0_LB_HCERR_SHFT 0
+#define UVH_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
+#define UVH_EVENT_OCCURRED0_GR0_HCERR_SHFT 1
+#define UVH_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL
+#define UVH_EVENT_OCCURRED0_GR1_HCERR_SHFT 2
+#define UVH_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL
+#define UVH_EVENT_OCCURRED0_LH_HCERR_SHFT 3
+#define UVH_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL
+#define UVH_EVENT_OCCURRED0_RH_HCERR_SHFT 4
+#define UVH_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL
+#define UVH_EVENT_OCCURRED0_XN_HCERR_SHFT 5
+#define UVH_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL
+#define UVH_EVENT_OCCURRED0_SI_HCERR_SHFT 6
+#define UVH_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL
+#define UVH_EVENT_OCCURRED0_LB_AOERR0_SHFT 7
+#define UVH_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL
+#define UVH_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8
+#define UVH_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL
+#define UVH_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9
+#define UVH_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL
+#define UVH_EVENT_OCCURRED0_LH_AOERR0_SHFT 10
+#define UVH_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL
+#define UVH_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
+#define UVH_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
+#define UVH_EVENT_OCCURRED0_XN_AOERR0_SHFT 12
+#define UVH_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL
+#define UVH_EVENT_OCCURRED0_SI_AOERR0_SHFT 13
+#define UVH_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL
+#define UVH_EVENT_OCCURRED0_LB_AOERR1_SHFT 14
+#define UVH_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL
+#define UVH_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15
+#define UVH_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL
+#define UVH_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16
+#define UVH_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL
+#define UVH_EVENT_OCCURRED0_LH_AOERR1_SHFT 17
+#define UVH_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL
+#define UVH_EVENT_OCCURRED0_RH_AOERR1_SHFT 18
+#define UVH_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL
+#define UVH_EVENT_OCCURRED0_XN_AOERR1_SHFT 19
+#define UVH_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL
+#define UVH_EVENT_OCCURRED0_SI_AOERR1_SHFT 20
+#define UVH_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL
+#define UVH_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21
+#define UVH_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL
+#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22
+#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38
+#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL
+#define UVH_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39
+#define UVH_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL
+#define UVH_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40
+#define UVH_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL
+#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41
+#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL
+#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42
+#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL
+#define UVH_EVENT_OCCURRED0_LTC_INT_SHFT 43
+#define UVH_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL
+#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44
+#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
+#define UVH_EVENT_OCCURRED0_IPI_INT_SHFT 45
+#define UVH_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46
+#define UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47
+#define UVH_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48
+#define UVH_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL
+#define UVH_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49
+#define UVH_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL
+#define UVH_EVENT_OCCURRED0_PROFILE_INT_SHFT 50
+#define UVH_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC0_SHFT 51
+#define UVH_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC1_SHFT 52
+#define UVH_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC2_SHFT 53
+#define UVH_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL
+#define UVH_EVENT_OCCURRED0_RTC3_SHFT 54
+#define UVH_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL
+#define UVH_EVENT_OCCURRED0_BAU_DATA_SHFT 55
+#define UVH_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL
+#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56
+#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL
+union uvh_event_occurred0_u {
+    unsigned long	v;
+    struct uvh_event_occurred0_s {
+	unsigned long	lb_hcerr             :  1;  /* RW, W1C */
+	unsigned long	gr0_hcerr            :  1;  /* RW, W1C */
+	unsigned long	gr1_hcerr            :  1;  /* RW, W1C */
+	unsigned long	lh_hcerr             :  1;  /* RW, W1C */
+	unsigned long	rh_hcerr             :  1;  /* RW, W1C */
+	unsigned long	xn_hcerr             :  1;  /* RW, W1C */
+	unsigned long	si_hcerr             :  1;  /* RW, W1C */
+	unsigned long	lb_aoerr0            :  1;  /* RW, W1C */
+	unsigned long	gr0_aoerr0           :  1;  /* RW, W1C */
+	unsigned long	gr1_aoerr0           :  1;  /* RW, W1C */
+	unsigned long	lh_aoerr0            :  1;  /* RW, W1C */
+	unsigned long	rh_aoerr0            :  1;  /* RW, W1C */
+	unsigned long	xn_aoerr0            :  1;  /* RW, W1C */
+	unsigned long	si_aoerr0            :  1;  /* RW, W1C */
+	unsigned long	lb_aoerr1            :  1;  /* RW, W1C */
+	unsigned long	gr0_aoerr1           :  1;  /* RW, W1C */
+	unsigned long	gr1_aoerr1           :  1;  /* RW, W1C */
+	unsigned long	lh_aoerr1            :  1;  /* RW, W1C */
+	unsigned long	rh_aoerr1            :  1;  /* RW, W1C */
+	unsigned long	xn_aoerr1            :  1;  /* RW, W1C */
+	unsigned long	si_aoerr1            :  1;  /* RW, W1C */
+	unsigned long	rh_vpi_int           :  1;  /* RW, W1C */
+	unsigned long	system_shutdown_int  :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_0         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_1         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_2         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_3         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_4         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_5         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_6         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_7         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_8         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_9         :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_10        :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_11        :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_12        :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_13        :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_14        :  1;  /* RW, W1C */
+	unsigned long	lb_irq_int_15        :  1;  /* RW, W1C */
+	unsigned long	l1_nmi_int           :  1;  /* RW, W1C */
+	unsigned long	stop_clock           :  1;  /* RW, W1C */
+	unsigned long	asic_to_l1           :  1;  /* RW, W1C */
+	unsigned long	l1_to_asic           :  1;  /* RW, W1C */
+	unsigned long	ltc_int              :  1;  /* RW, W1C */
+	unsigned long	la_seq_trigger       :  1;  /* RW, W1C */
+	unsigned long	ipi_int              :  1;  /* RW, W1C */
+	unsigned long	extio_int0           :  1;  /* RW, W1C */
+	unsigned long	extio_int1           :  1;  /* RW, W1C */
+	unsigned long	extio_int2           :  1;  /* RW, W1C */
+	unsigned long	extio_int3           :  1;  /* RW, W1C */
+	unsigned long	profile_int          :  1;  /* RW, W1C */
+	unsigned long	rtc0                 :  1;  /* RW, W1C */
+	unsigned long	rtc1                 :  1;  /* RW, W1C */
+	unsigned long	rtc2                 :  1;  /* RW, W1C */
+	unsigned long	rtc3                 :  1;  /* RW, W1C */
+	unsigned long	bau_data             :  1;  /* RW, W1C */
+	unsigned long	power_management_req :  1;  /* RW, W1C */
+	unsigned long	rsvd_57_63           :  7;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                        UVH_EVENT_OCCURRED0_ALIAS                          */
+/* ========================================================================= */
+#define UVH_EVENT_OCCURRED0_ALIAS 0x0000000000070008UL
+#define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0
+
+/* ========================================================================= */
+/*                               UVH_INT_CMPB                                */
+/* ========================================================================= */
+#define UVH_INT_CMPB 0x22080UL
+
+#define UVH_INT_CMPB_REAL_TIME_CMPB_SHFT 0
+#define UVH_INT_CMPB_REAL_TIME_CMPB_MASK 0x00ffffffffffffffUL
+
+union uvh_int_cmpb_u {
+    unsigned long	v;
+    struct uvh_int_cmpb_s {
+	unsigned long	real_time_cmpb : 56;  /* RW */
+	unsigned long	rsvd_56_63     :  8;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                               UVH_INT_CMPC                                */
+/* ========================================================================= */
+#define UVH_INT_CMPC 0x22100UL
+
+#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT 0
+#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK 0x00ffffffffffffffUL
+
+union uvh_int_cmpc_u {
+    unsigned long	v;
+    struct uvh_int_cmpc_s {
+	unsigned long	real_time_cmpc : 56;  /* RW */
+	unsigned long	rsvd_56_63     :  8;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                               UVH_INT_CMPD                                */
+/* ========================================================================= */
+#define UVH_INT_CMPD 0x22180UL
+
+#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT 0
+#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK 0x00ffffffffffffffUL
+
+union uvh_int_cmpd_u {
+    unsigned long	v;
+    struct uvh_int_cmpd_s {
+	unsigned long	real_time_cmpd : 56;  /* RW */
+	unsigned long	rsvd_56_63     :  8;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                               UVH_IPI_INT                                 */
+/* ========================================================================= */
+#define UVH_IPI_INT 0x60500UL
+#define UVH_IPI_INT_32 0x0348
+
+#define UVH_IPI_INT_VECTOR_SHFT 0
+#define UVH_IPI_INT_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_IPI_INT_DELIVERY_MODE_SHFT 8
+#define UVH_IPI_INT_DELIVERY_MODE_MASK 0x0000000000000700UL
+#define UVH_IPI_INT_DESTMODE_SHFT 11
+#define UVH_IPI_INT_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_IPI_INT_APIC_ID_SHFT 16
+#define UVH_IPI_INT_APIC_ID_MASK 0x0000ffffffff0000UL
+#define UVH_IPI_INT_SEND_SHFT 63
+#define UVH_IPI_INT_SEND_MASK 0x8000000000000000UL
+
+union uvh_ipi_int_u {
+    unsigned long	v;
+    struct uvh_ipi_int_s {
+	unsigned long	vector_       :  8;  /* RW */
+	unsigned long	delivery_mode :  3;  /* RW */
+	unsigned long	destmode      :  1;  /* RW */
+	unsigned long	rsvd_12_15    :  4;  /*    */
+	unsigned long	apic_id       : 32;  /* RW */
+	unsigned long	rsvd_48_62    : 15;  /*    */
+	unsigned long	send          :  1;  /* WP */
+    } s;
+};
+
+/* ========================================================================= */
+/*                   UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST                     */
+/* ========================================================================= */
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x009c0
+
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_SHFT 49
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_MASK 0x7ffe000000000000UL
+
+union uvh_lb_bau_intd_payload_queue_first_u {
+    unsigned long	v;
+    struct uvh_lb_bau_intd_payload_queue_first_s {
+	unsigned long	rsvd_0_3:  4;  /*    */
+	unsigned long	address : 39;  /* RW */
+	unsigned long	rsvd_43_48:  6;  /*    */
+	unsigned long	node_id : 14;  /* RW */
+	unsigned long	rsvd_63 :  1;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST                     */
+/* ========================================================================= */
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x009c8
+
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL
+
+union uvh_lb_bau_intd_payload_queue_last_u {
+    unsigned long	v;
+    struct uvh_lb_bau_intd_payload_queue_last_s {
+	unsigned long	rsvd_0_3:  4;  /*    */
+	unsigned long	address : 39;  /* RW */
+	unsigned long	rsvd_43_63: 21;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL                     */
+/* ========================================================================= */
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x009d0
+
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4
+#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL
+
+union uvh_lb_bau_intd_payload_queue_tail_u {
+    unsigned long	v;
+    struct uvh_lb_bau_intd_payload_queue_tail_s {
+	unsigned long	rsvd_0_3:  4;  /*    */
+	unsigned long	address : 39;  /* RW */
+	unsigned long	rsvd_43_63: 21;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                   UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE                    */
+/* ========================================================================= */
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0x0a68
+
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_SHFT 1
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_MASK 0x0000000000000002UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_SHFT 2
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_MASK 0x0000000000000004UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_SHFT 3
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_MASK 0x0000000000000008UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_SHFT 4
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_MASK 0x0000000000000010UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_SHFT 5
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_MASK 0x0000000000000020UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_SHFT 6
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_MASK 0x0000000000000040UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_SHFT 7
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_MASK 0x0000000000000080UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_SHFT 8
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_MASK 0x0000000000000100UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_SHFT 9
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_MASK 0x0000000000000200UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_SHFT 10
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_MASK 0x0000000000000400UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_SHFT 11
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_MASK 0x0000000000000800UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_SHFT 12
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_MASK 0x0000000000001000UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_SHFT 13
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_MASK 0x0000000000002000UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_SHFT 14
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_MASK 0x0000000000004000UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_SHFT 15
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_MASK 0x0000000000008000UL
+union uvh_lb_bau_intd_software_acknowledge_u {
+    unsigned long	v;
+    struct uvh_lb_bau_intd_software_acknowledge_s {
+	unsigned long	pending_0 :  1;  /* RW, W1C */
+	unsigned long	pending_1 :  1;  /* RW, W1C */
+	unsigned long	pending_2 :  1;  /* RW, W1C */
+	unsigned long	pending_3 :  1;  /* RW, W1C */
+	unsigned long	pending_4 :  1;  /* RW, W1C */
+	unsigned long	pending_5 :  1;  /* RW, W1C */
+	unsigned long	pending_6 :  1;  /* RW, W1C */
+	unsigned long	pending_7 :  1;  /* RW, W1C */
+	unsigned long	timeout_0 :  1;  /* RW, W1C */
+	unsigned long	timeout_1 :  1;  /* RW, W1C */
+	unsigned long	timeout_2 :  1;  /* RW, W1C */
+	unsigned long	timeout_3 :  1;  /* RW, W1C */
+	unsigned long	timeout_4 :  1;  /* RW, W1C */
+	unsigned long	timeout_5 :  1;  /* RW, W1C */
+	unsigned long	timeout_6 :  1;  /* RW, W1C */
+	unsigned long	timeout_7 :  1;  /* RW, W1C */
+	unsigned long	rsvd_16_63: 48;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS                 */
+/* ========================================================================= */
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x0000000000320088UL
+#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0x0a70
+
+/* ========================================================================= */
+/*                     UVH_LB_BAU_SB_ACTIVATION_CONTROL                      */
+/* ========================================================================= */
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x009a8
+
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_SHFT 0
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_MASK 0x000000000000003fUL
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT 62
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_MASK 0x4000000000000000UL
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INIT_SHFT 63
+#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INIT_MASK 0x8000000000000000UL
+
+union uvh_lb_bau_sb_activation_control_u {
+    unsigned long	v;
+    struct uvh_lb_bau_sb_activation_control_s {
+	unsigned long	index :  6;  /* RW */
+	unsigned long	rsvd_6_61: 56;  /*    */
+	unsigned long	push  :  1;  /* WP */
+	unsigned long	init  :  1;  /* WP */
+    } s;
+};
+
+/* ========================================================================= */
+/*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_0                      */
+/* ========================================================================= */
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x009b0
+
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_SHFT 0
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_MASK 0xffffffffffffffffUL
+
+union uvh_lb_bau_sb_activation_status_0_u {
+    unsigned long	v;
+    struct uvh_lb_bau_sb_activation_status_0_s {
+	unsigned long	status : 64;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_1                      */
+/* ========================================================================= */
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x009b8
+
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_SHFT 0
+#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_MASK 0xffffffffffffffffUL
+
+union uvh_lb_bau_sb_activation_status_1_u {
+    unsigned long	v;
+    struct uvh_lb_bau_sb_activation_status_1_s {
+	unsigned long	status : 64;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                      UVH_LB_BAU_SB_DESCRIPTOR_BASE                        */
+/* ========================================================================= */
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x009a0
+
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT 12
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT 49
+#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK 0x7ffe000000000000UL
+
+union uvh_lb_bau_sb_descriptor_base_u {
+    unsigned long	v;
+    struct uvh_lb_bau_sb_descriptor_base_s {
+	unsigned long	rsvd_0_11    : 12;  /*    */
+	unsigned long	page_address : 31;  /* RW */
+	unsigned long	rsvd_43_48   :  6;  /*    */
+	unsigned long	node_id      : 14;  /* RW */
+	unsigned long	rsvd_63      :  1;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                      UVH_LB_MCAST_AOERR0_RPT_ENABLE                       */
+/* ========================================================================= */
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE 0x50b20UL
+
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_SHFT 0
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_MASK 0x0000000000000001UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_SHFT 1
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_MASK 0x0000000000000002UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_SHFT 2
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_MASK 0x0000000000000004UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_SHFT 3
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_MASK 0x0000000000000008UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_SHFT 4
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_MASK 0x0000000000000010UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_SHFT 5
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_MASK 0x0000000000000020UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_SHFT 6
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_MASK 0x0000000000000040UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_SHFT 7
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_MASK 0x0000000000000080UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_SHFT 8
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_MASK 0x0000000000000100UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_SHFT 9
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_MASK 0x0000000000000200UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_SHFT 10
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_MASK 0x0000000000000400UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_SHFT 11
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_MASK 0x0000000000000800UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_SHFT 12
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_MASK 0x0000000000001000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_SHFT 13
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_MASK 0x0000000000002000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_SHFT 14
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_MASK 0x0000000000004000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_SHFT 15
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_MASK 0x0000000000008000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_SHFT 16
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_MASK 0x0000000000010000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_SHFT 17
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_MASK 0x0000000000020000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_SHFT 18
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_MASK 0x0000000000040000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_SHFT 19
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_MASK 0x0000000000080000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_SHFT 20
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_MASK 0x0000000000100000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_SHFT 21
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_MASK 0x0000000000200000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_SHFT 22
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_MASK 0x0000000000400000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_SHFT 23
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_MASK 0x0000000000800000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_SHFT 24
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_MASK 0x0000000001000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_SHFT 25
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_MASK 0x0000000002000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_SHFT 26
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_MASK 0x0000000004000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_SHFT 27
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_MASK 0x0000000008000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_SHFT 28
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_MASK 0x0000000010000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_SHFT 29
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_MASK 0x0000000020000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_SHFT 30
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_MASK 0x0000000040000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_SHFT 31
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_MASK 0x0000000080000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_SHFT 32
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_MASK 0x0000000100000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_SHFT 33
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_MASK 0x0000000200000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_SHFT 34
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_MASK 0x0000000400000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_SHFT 35
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_MASK 0x0000000800000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_SHFT 36
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_MASK 0x0000001000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_SHFT 37
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_MASK 0x0000002000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_SHFT 38
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_MASK 0x0000004000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_SHFT 39
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_MASK 0x0000008000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_SHFT 40
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_MASK 0x0000010000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_SHFT 41
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_MASK 0x0000020000000000UL
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_SHFT 42
+#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_MASK 0x0000040000000000UL
+
+union uvh_lb_mcast_aoerr0_rpt_enable_u {
+    unsigned long	v;
+    struct uvh_lb_mcast_aoerr0_rpt_enable_s {
+	unsigned long	mcast_obese_msg                         :  1;  /* RW */
+	unsigned long	mcast_data_sb_err                       :  1;  /* RW */
+	unsigned long	mcast_nack_buff_parity                  :  1;  /* RW */
+	unsigned long	mcast_timeout                           :  1;  /* RW */
+	unsigned long	mcast_inactive_reply                    :  1;  /* RW */
+	unsigned long	mcast_upgrade_error                     :  1;  /* RW */
+	unsigned long	mcast_reg_count_underflow               :  1;  /* RW */
+	unsigned long	mcast_rep_obese_msg                     :  1;  /* RW */
+	unsigned long	ucache_req_runt_msg                     :  1;  /* RW */
+	unsigned long	ucache_req_obese_msg                    :  1;  /* RW */
+	unsigned long	ucache_req_data_sb_err                  :  1;  /* RW */
+	unsigned long	ucache_rep_runt_msg                     :  1;  /* RW */
+	unsigned long	ucache_rep_obese_msg                    :  1;  /* RW */
+	unsigned long	ucache_rep_data_sb_err                  :  1;  /* RW */
+	unsigned long	ucache_rep_command_err                  :  1;  /* RW */
+	unsigned long	ucache_pend_timeout                     :  1;  /* RW */
+	unsigned long	macc_req_runt_msg                       :  1;  /* RW */
+	unsigned long	macc_req_obese_msg                      :  1;  /* RW */
+	unsigned long	macc_req_data_sb_err                    :  1;  /* RW */
+	unsigned long	macc_rep_runt_msg                       :  1;  /* RW */
+	unsigned long	macc_rep_obese_msg                      :  1;  /* RW */
+	unsigned long	macc_rep_data_sb_err                    :  1;  /* RW */
+	unsigned long	macc_amo_timeout                        :  1;  /* RW */
+	unsigned long	macc_put_timeout                        :  1;  /* RW */
+	unsigned long	macc_spurious_event                     :  1;  /* RW */
+	unsigned long	ioh_destination_table_parity            :  1;  /* RW */
+	unsigned long	get_had_error_reply                     :  1;  /* RW */
+	unsigned long	get_timeout                             :  1;  /* RW */
+	unsigned long	lock_manager_had_error_reply            :  1;  /* RW */
+	unsigned long	put_had_error_reply                     :  1;  /* RW */
+	unsigned long	put_timeout                             :  1;  /* RW */
+	unsigned long	sb_activation_overrun                   :  1;  /* RW */
+	unsigned long	completed_gb_activation_had_error_reply :  1;  /* RW */
+	unsigned long	completed_gb_activation_timeout         :  1;  /* RW */
+	unsigned long	descriptor_buffer_0_parity              :  1;  /* RW */
+	unsigned long	descriptor_buffer_1_parity              :  1;  /* RW */
+	unsigned long	socket_destination_table_parity         :  1;  /* RW */
+	unsigned long	bau_reply_payload_corruption            :  1;  /* RW */
+	unsigned long	io_port_destination_table_parity        :  1;  /* RW */
+	unsigned long	intd_soft_ack_timeout                   :  1;  /* RW */
+	unsigned long	int_rep_obese_msg                       :  1;  /* RW */
+	unsigned long	int_rep_command_err                     :  1;  /* RW */
+	unsigned long	int_timeout                             :  1;  /* RW */
+	unsigned long	rsvd_43_63                              : 21;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                          UVH_LOCAL_INT0_CONFIG                            */
+/* ========================================================================= */
+#define UVH_LOCAL_INT0_CONFIG 0x61000UL
+
+#define UVH_LOCAL_INT0_CONFIG_VECTOR_SHFT 0
+#define UVH_LOCAL_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_LOCAL_INT0_CONFIG_DM_SHFT 8
+#define UVH_LOCAL_INT0_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_LOCAL_INT0_CONFIG_DESTMODE_SHFT 11
+#define UVH_LOCAL_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_LOCAL_INT0_CONFIG_STATUS_SHFT 12
+#define UVH_LOCAL_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_LOCAL_INT0_CONFIG_P_SHFT 13
+#define UVH_LOCAL_INT0_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_LOCAL_INT0_CONFIG_T_SHFT 15
+#define UVH_LOCAL_INT0_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_LOCAL_INT0_CONFIG_M_SHFT 16
+#define UVH_LOCAL_INT0_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_LOCAL_INT0_CONFIG_APIC_ID_SHFT 32
+#define UVH_LOCAL_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_local_int0_config_u {
+    unsigned long	v;
+    struct uvh_local_int0_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                          UVH_LOCAL_INT0_ENABLE                            */
+/* ========================================================================= */
+#define UVH_LOCAL_INT0_ENABLE 0x65000UL
+
+#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_SHFT 0
+#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_MASK 0x0000000000000001UL
+#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_SHFT 1
+#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_MASK 0x0000000000000002UL
+#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_SHFT 2
+#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_MASK 0x0000000000000004UL
+#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_SHFT 3
+#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_MASK 0x0000000000000008UL
+#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_SHFT 4
+#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_MASK 0x0000000000000010UL
+#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_SHFT 5
+#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_MASK 0x0000000000000020UL
+#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_SHFT 6
+#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_MASK 0x0000000000000040UL
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_SHFT 7
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_MASK 0x0000000000000080UL
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_SHFT 8
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_MASK 0x0000000000000100UL
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_SHFT 9
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_MASK 0x0000000000000200UL
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_SHFT 10
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_MASK 0x0000000000000400UL
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_SHFT 11
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_MASK 0x0000000000000800UL
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_SHFT 12
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_MASK 0x0000000000001000UL
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_SHFT 13
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_MASK 0x0000000000002000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_SHFT 14
+#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_MASK 0x0000000000004000UL
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_SHFT 15
+#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_MASK 0x0000000000008000UL
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_SHFT 16
+#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_MASK 0x0000000000010000UL
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_SHFT 17
+#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_MASK 0x0000000000020000UL
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_SHFT 18
+#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_MASK 0x0000000000040000UL
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_SHFT 19
+#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_MASK 0x0000000000080000UL
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_SHFT 20
+#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_MASK 0x0000000000100000UL
+#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_SHFT 21
+#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_MASK 0x0000000000200000UL
+#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_SHFT 22
+#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_SHFT 23
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_MASK 0x0000000000800000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_SHFT 24
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_MASK 0x0000000001000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_SHFT 25
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_MASK 0x0000000002000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_SHFT 26
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_MASK 0x0000000004000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_SHFT 27
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_MASK 0x0000000008000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_SHFT 28
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_MASK 0x0000000010000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_SHFT 29
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_MASK 0x0000000020000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_SHFT 30
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_MASK 0x0000000040000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_SHFT 31
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_MASK 0x0000000080000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_SHFT 32
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_MASK 0x0000000100000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_SHFT 33
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_MASK 0x0000000200000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_SHFT 34
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_MASK 0x0000000400000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_SHFT 35
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_MASK 0x0000000800000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_SHFT 36
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_MASK 0x0000001000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_SHFT 37
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_MASK 0x0000002000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_SHFT 38
+#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_MASK 0x0000004000000000UL
+#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_SHFT 39
+#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_MASK 0x0000008000000000UL
+#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_SHFT 40
+#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_MASK 0x0000010000000000UL
+#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_SHFT 41
+#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_MASK 0x0000020000000000UL
+#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_SHFT 42
+#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_MASK 0x0000040000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LTC_INT_SHFT 43
+#define UVH_LOCAL_INT0_ENABLE_LTC_INT_MASK 0x0000080000000000UL
+#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_SHFT 44
+#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
+
+union uvh_local_int0_enable_u {
+    unsigned long	v;
+    struct uvh_local_int0_enable_s {
+	unsigned long	lb_hcerr            :  1;  /* RW */
+	unsigned long	gr0_hcerr           :  1;  /* RW */
+	unsigned long	gr1_hcerr           :  1;  /* RW */
+	unsigned long	lh_hcerr            :  1;  /* RW */
+	unsigned long	rh_hcerr            :  1;  /* RW */
+	unsigned long	xn_hcerr            :  1;  /* RW */
+	unsigned long	si_hcerr            :  1;  /* RW */
+	unsigned long	lb_aoerr0           :  1;  /* RW */
+	unsigned long	gr0_aoerr0          :  1;  /* RW */
+	unsigned long	gr1_aoerr0          :  1;  /* RW */
+	unsigned long	lh_aoerr0           :  1;  /* RW */
+	unsigned long	rh_aoerr0           :  1;  /* RW */
+	unsigned long	xn_aoerr0           :  1;  /* RW */
+	unsigned long	si_aoerr0           :  1;  /* RW */
+	unsigned long	lb_aoerr1           :  1;  /* RW */
+	unsigned long	gr0_aoerr1          :  1;  /* RW */
+	unsigned long	gr1_aoerr1          :  1;  /* RW */
+	unsigned long	lh_aoerr1           :  1;  /* RW */
+	unsigned long	rh_aoerr1           :  1;  /* RW */
+	unsigned long	xn_aoerr1           :  1;  /* RW */
+	unsigned long	si_aoerr1           :  1;  /* RW */
+	unsigned long	rh_vpi_int          :  1;  /* RW */
+	unsigned long	system_shutdown_int :  1;  /* RW */
+	unsigned long	lb_irq_int_0        :  1;  /* RW */
+	unsigned long	lb_irq_int_1        :  1;  /* RW */
+	unsigned long	lb_irq_int_2        :  1;  /* RW */
+	unsigned long	lb_irq_int_3        :  1;  /* RW */
+	unsigned long	lb_irq_int_4        :  1;  /* RW */
+	unsigned long	lb_irq_int_5        :  1;  /* RW */
+	unsigned long	lb_irq_int_6        :  1;  /* RW */
+	unsigned long	lb_irq_int_7        :  1;  /* RW */
+	unsigned long	lb_irq_int_8        :  1;  /* RW */
+	unsigned long	lb_irq_int_9        :  1;  /* RW */
+	unsigned long	lb_irq_int_10       :  1;  /* RW */
+	unsigned long	lb_irq_int_11       :  1;  /* RW */
+	unsigned long	lb_irq_int_12       :  1;  /* RW */
+	unsigned long	lb_irq_int_13       :  1;  /* RW */
+	unsigned long	lb_irq_int_14       :  1;  /* RW */
+	unsigned long	lb_irq_int_15       :  1;  /* RW */
+	unsigned long	l1_nmi_int          :  1;  /* RW */
+	unsigned long	stop_clock          :  1;  /* RW */
+	unsigned long	asic_to_l1          :  1;  /* RW */
+	unsigned long	l1_to_asic          :  1;  /* RW */
+	unsigned long	ltc_int             :  1;  /* RW */
+	unsigned long	la_seq_trigger      :  1;  /* RW */
+	unsigned long	rsvd_45_63          : 19;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                               UVH_NODE_ID                                 */
+/* ========================================================================= */
+#define UVH_NODE_ID 0x0UL
+
+#define UVH_NODE_ID_FORCE1_SHFT 0
+#define UVH_NODE_ID_FORCE1_MASK 0x0000000000000001UL
+#define UVH_NODE_ID_MANUFACTURER_SHFT 1
+#define UVH_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL
+#define UVH_NODE_ID_PART_NUMBER_SHFT 12
+#define UVH_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL
+#define UVH_NODE_ID_REVISION_SHFT 28
+#define UVH_NODE_ID_REVISION_MASK 0x00000000f0000000UL
+#define UVH_NODE_ID_NODE_ID_SHFT 32
+#define UVH_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL
+#define UVH_NODE_ID_NODES_PER_BIT_SHFT 48
+#define UVH_NODE_ID_NODES_PER_BIT_MASK 0x007f000000000000UL
+#define UVH_NODE_ID_NI_PORT_SHFT 56
+#define UVH_NODE_ID_NI_PORT_MASK 0x0f00000000000000UL
+
+union uvh_node_id_u {
+    unsigned long	v;
+    struct uvh_node_id_s {
+	unsigned long	force1        :  1;  /* RO */
+	unsigned long	manufacturer  : 11;  /* RO */
+	unsigned long	part_number   : 16;  /* RO */
+	unsigned long	revision      :  4;  /* RO */
+	unsigned long	node_id       : 15;  /* RW */
+	unsigned long	rsvd_47       :  1;  /*    */
+	unsigned long	nodes_per_bit :  7;  /* RW */
+	unsigned long	rsvd_55       :  1;  /*    */
+	unsigned long	ni_port       :  4;  /* RO */
+	unsigned long	rsvd_60_63    :  4;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                          UVH_NODE_PRESENT_TABLE                           */
+/* ========================================================================= */
+#define UVH_NODE_PRESENT_TABLE 0x1400UL
+#define UVH_NODE_PRESENT_TABLE_DEPTH 16
+
+#define UVH_NODE_PRESENT_TABLE_NODES_SHFT 0
+#define UVH_NODE_PRESENT_TABLE_NODES_MASK 0xffffffffffffffffUL
+
+union uvh_node_present_table_u {
+    unsigned long	v;
+    struct uvh_node_present_table_s {
+	unsigned long	nodes : 64;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL
+
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_alias210_redirect_config_0_mmr_s {
+	unsigned long	rsvd_0_23 : 24;  /*    */
+	unsigned long	dest_base : 22;  /* RW */
+	unsigned long	rsvd_46_63: 18;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR 0x16000e0UL
+
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_alias210_redirect_config_1_mmr_s {
+	unsigned long	rsvd_0_23 : 24;  /*    */
+	unsigned long	dest_base : 22;  /* RW */
+	unsigned long	rsvd_46_63: 18;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR 0x16000f0UL
+
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
+
+union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_alias210_redirect_config_2_mmr_s {
+	unsigned long	rsvd_0_23 : 24;  /*    */
+	unsigned long	dest_base : 22;  /* RW */
+	unsigned long	rsvd_46_63: 18;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                    UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR                      */
+/* ========================================================================= */
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR 0x1600020UL
+
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT 26
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_cfg_overlay_config_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_cfg_overlay_config_mmr_s {
+	unsigned long	rsvd_0_25: 26;  /*    */
+	unsigned long	base   : 20;  /* RW */
+	unsigned long	rsvd_46_62: 17;  /*    */
+	unsigned long	enable :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                    UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR                      */
+/* ========================================================================= */
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL
+
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_gru_overlay_config_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_gru_overlay_config_mmr_s {
+	unsigned long	rsvd_0_27: 28;  /*    */
+	unsigned long	base   : 18;  /* RW */
+	unsigned long	rsvd_46_47:  2;  /*    */
+	unsigned long	gr4    :  1;  /* RW */
+	unsigned long	rsvd_49_51:  3;  /*    */
+	unsigned long	n_gru  :  4;  /* RW */
+	unsigned long	rsvd_56_62:  7;  /*    */
+	unsigned long	enable :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                   UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR                     */
+/* ========================================================================= */
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
+
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_mmioh_overlay_config_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_mmioh_overlay_config_mmr_s {
+	unsigned long	rsvd_0_29: 30;  /*    */
+	unsigned long	base   : 16;  /* RW */
+	unsigned long	m_io   :  6;  /* RW */
+	unsigned long	n_io   :  4;  /* RW */
+	unsigned long	rsvd_56_62:  7;  /*    */
+	unsigned long	enable :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                    UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR                      */
+/* ========================================================================= */
+#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL
+
+#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26
+#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
+#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_SHFT 46
+#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_MASK 0x0000400000000000UL
+#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_mmr_overlay_config_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_mmr_overlay_config_mmr_s {
+	unsigned long	rsvd_0_25: 26;  /*    */
+	unsigned long	base     : 20;  /* RW */
+	unsigned long	dual_hub :  1;  /* RW */
+	unsigned long	rsvd_47_62: 16;  /*    */
+	unsigned long	enable   :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                                 UVH_RTC                                   */
+/* ========================================================================= */
+#define UVH_RTC 0x340000UL
+
+#define UVH_RTC_REAL_TIME_CLOCK_SHFT 0
+#define UVH_RTC_REAL_TIME_CLOCK_MASK 0x00ffffffffffffffUL
+
+union uvh_rtc_u {
+    unsigned long	v;
+    struct uvh_rtc_s {
+	unsigned long	real_time_clock : 56;  /* RW */
+	unsigned long	rsvd_56_63      :  8;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                           UVH_RTC1_INT_CONFIG                             */
+/* ========================================================================= */
+#define UVH_RTC1_INT_CONFIG 0x615c0UL
+
+#define UVH_RTC1_INT_CONFIG_VECTOR_SHFT 0
+#define UVH_RTC1_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_RTC1_INT_CONFIG_DM_SHFT 8
+#define UVH_RTC1_INT_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_RTC1_INT_CONFIG_DESTMODE_SHFT 11
+#define UVH_RTC1_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_RTC1_INT_CONFIG_STATUS_SHFT 12
+#define UVH_RTC1_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_RTC1_INT_CONFIG_P_SHFT 13
+#define UVH_RTC1_INT_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_RTC1_INT_CONFIG_T_SHFT 15
+#define UVH_RTC1_INT_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_RTC1_INT_CONFIG_M_SHFT 16
+#define UVH_RTC1_INT_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_RTC1_INT_CONFIG_APIC_ID_SHFT 32
+#define UVH_RTC1_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_rtc1_int_config_u {
+    unsigned long	v;
+    struct uvh_rtc1_int_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                           UVH_RTC2_INT_CONFIG                             */
+/* ========================================================================= */
+#define UVH_RTC2_INT_CONFIG 0x61600UL
+
+#define UVH_RTC2_INT_CONFIG_VECTOR_SHFT 0
+#define UVH_RTC2_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_RTC2_INT_CONFIG_DM_SHFT 8
+#define UVH_RTC2_INT_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_RTC2_INT_CONFIG_DESTMODE_SHFT 11
+#define UVH_RTC2_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_RTC2_INT_CONFIG_STATUS_SHFT 12
+#define UVH_RTC2_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_RTC2_INT_CONFIG_P_SHFT 13
+#define UVH_RTC2_INT_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_RTC2_INT_CONFIG_T_SHFT 15
+#define UVH_RTC2_INT_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_RTC2_INT_CONFIG_M_SHFT 16
+#define UVH_RTC2_INT_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_RTC2_INT_CONFIG_APIC_ID_SHFT 32
+#define UVH_RTC2_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_rtc2_int_config_u {
+    unsigned long	v;
+    struct uvh_rtc2_int_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                           UVH_RTC3_INT_CONFIG                             */
+/* ========================================================================= */
+#define UVH_RTC3_INT_CONFIG 0x61640UL
+
+#define UVH_RTC3_INT_CONFIG_VECTOR_SHFT 0
+#define UVH_RTC3_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_RTC3_INT_CONFIG_DM_SHFT 8
+#define UVH_RTC3_INT_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_RTC3_INT_CONFIG_DESTMODE_SHFT 11
+#define UVH_RTC3_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_RTC3_INT_CONFIG_STATUS_SHFT 12
+#define UVH_RTC3_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_RTC3_INT_CONFIG_P_SHFT 13
+#define UVH_RTC3_INT_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_RTC3_INT_CONFIG_T_SHFT 15
+#define UVH_RTC3_INT_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_RTC3_INT_CONFIG_M_SHFT 16
+#define UVH_RTC3_INT_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_RTC3_INT_CONFIG_APIC_ID_SHFT 32
+#define UVH_RTC3_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_rtc3_int_config_u {
+    unsigned long	v;
+    struct uvh_rtc3_int_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                            UVH_RTC_INC_RATIO                              */
+/* ========================================================================= */
+#define UVH_RTC_INC_RATIO 0x350000UL
+
+#define UVH_RTC_INC_RATIO_FRACTION_SHFT 0
+#define UVH_RTC_INC_RATIO_FRACTION_MASK 0x00000000000fffffUL
+#define UVH_RTC_INC_RATIO_RATIO_SHFT 20
+#define UVH_RTC_INC_RATIO_RATIO_MASK 0x0000000000700000UL
+
+union uvh_rtc_inc_ratio_u {
+    unsigned long	v;
+    struct uvh_rtc_inc_ratio_s {
+	unsigned long	fraction : 20;  /* RW */
+	unsigned long	ratio    :  3;  /* RW */
+	unsigned long	rsvd_23_63: 41;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                          UVH_SI_ADDR_MAP_CONFIG                           */
+/* ========================================================================= */
+#define UVH_SI_ADDR_MAP_CONFIG 0xc80000UL
+
+#define UVH_SI_ADDR_MAP_CONFIG_M_SKT_SHFT 0
+#define UVH_SI_ADDR_MAP_CONFIG_M_SKT_MASK 0x000000000000003fUL
+#define UVH_SI_ADDR_MAP_CONFIG_N_SKT_SHFT 8
+#define UVH_SI_ADDR_MAP_CONFIG_N_SKT_MASK 0x0000000000000f00UL
+
+union uvh_si_addr_map_config_u {
+    unsigned long	v;
+    struct uvh_si_addr_map_config_s {
+	unsigned long	m_skt :  6;  /* RW */
+	unsigned long	rsvd_6_7:  2;  /*    */
+	unsigned long	n_skt :  4;  /* RW */
+	unsigned long	rsvd_12_63: 52;  /*    */
+    } s;
+};
+
+/* ========================================================================= */
+/*                       UVH_SI_ALIAS0_OVERLAY_CONFIG                        */
+/* ========================================================================= */
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG 0xc80008UL
+
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_SHFT 24
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_SHFT 48
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_SHFT 63
+#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_si_alias0_overlay_config_u {
+    unsigned long	v;
+    struct uvh_si_alias0_overlay_config_s {
+	unsigned long	rsvd_0_23: 24;  /*    */
+	unsigned long	base    :  8;  /* RW */
+	unsigned long	rsvd_32_47: 16;  /*    */
+	unsigned long	m_alias :  5;  /* RW */
+	unsigned long	rsvd_53_62: 10;  /*    */
+	unsigned long	enable  :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                       UVH_SI_ALIAS1_OVERLAY_CONFIG                        */
+/* ========================================================================= */
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG 0xc80010UL
+
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_SHFT 24
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_SHFT 48
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_SHFT 63
+#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_si_alias1_overlay_config_u {
+    unsigned long	v;
+    struct uvh_si_alias1_overlay_config_s {
+	unsigned long	rsvd_0_23: 24;  /*    */
+	unsigned long	base    :  8;  /* RW */
+	unsigned long	rsvd_32_47: 16;  /*    */
+	unsigned long	m_alias :  5;  /* RW */
+	unsigned long	rsvd_53_62: 10;  /*    */
+	unsigned long	enable  :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                       UVH_SI_ALIAS2_OVERLAY_CONFIG                        */
+/* ========================================================================= */
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG 0xc80018UL
+
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_SHFT 24
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_SHFT 48
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_SHFT 63
+#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_si_alias2_overlay_config_u {
+    unsigned long	v;
+    struct uvh_si_alias2_overlay_config_s {
+	unsigned long	rsvd_0_23: 24;  /*    */
+	unsigned long	base    :  8;  /* RW */
+	unsigned long	rsvd_32_47: 16;  /*    */
+	unsigned long	m_alias :  5;  /* RW */
+	unsigned long	rsvd_53_62: 10;  /*    */
+	unsigned long	enable  :  1;  /* RW */
+    } s;
+};
+
+
+#endif /* ASM_X86__UV__UV_MMRS_H */
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
new file mode 100644
index 000000000000..4ab320913ea3
--- /dev/null
+++ b/arch/x86/include/asm/vdso.h
@@ -0,0 +1,47 @@
+#ifndef ASM_X86__VDSO_H
+#define ASM_X86__VDSO_H
+
+#ifdef CONFIG_X86_64
+extern const char VDSO64_PRELINK[];
+
+/*
+ * Given a pointer to the vDSO image, find the pointer to VDSO64_name
+ * as that symbol is defined in the vDSO sources or linker script.
+ */
+#define VDSO64_SYMBOL(base, name)					\
+({									\
+	extern const char VDSO64_##name[];				\
+	(void *)(VDSO64_##name - VDSO64_PRELINK + (unsigned long)(base)); \
+})
+#endif
+
+#if defined CONFIG_X86_32 || defined CONFIG_COMPAT
+extern const char VDSO32_PRELINK[];
+
+/*
+ * Given a pointer to the vDSO image, find the pointer to VDSO32_name
+ * as that symbol is defined in the vDSO sources or linker script.
+ */
+#define VDSO32_SYMBOL(base, name)					\
+({									\
+	extern const char VDSO32_##name[];				\
+	(void *)(VDSO32_##name - VDSO32_PRELINK + (unsigned long)(base)); \
+})
+#endif
+
+/*
+ * These symbols are defined with the addresses in the vsyscall page.
+ * See vsyscall-sigreturn.S.
+ */
+extern void __user __kernel_sigreturn;
+extern void __user __kernel_rt_sigreturn;
+
+/*
+ * These symbols are defined by vdso32.S to mark the bounds
+ * of the ELF DSO images included therein.
+ */
+extern const char vdso32_int80_start, vdso32_int80_end;
+extern const char vdso32_syscall_start, vdso32_syscall_end;
+extern const char vdso32_sysenter_start, vdso32_sysenter_end;
+
+#endif /* ASM_X86__VDSO_H */
diff --git a/arch/x86/include/asm/vga.h b/arch/x86/include/asm/vga.h
new file mode 100644
index 000000000000..b9e493d07d07
--- /dev/null
+++ b/arch/x86/include/asm/vga.h
@@ -0,0 +1,20 @@
+/*
+ *	Access to VGA videoram
+ *
+ *	(c) 1998 Martin Mares <mj@ucw.cz>
+ */
+
+#ifndef ASM_X86__VGA_H
+#define ASM_X86__VGA_H
+
+/*
+ *	On the PC, we can just recalculate addresses and then
+ *	access the videoram directly without any black magic.
+ */
+
+#define VGA_MAP_MEM(x, s) (unsigned long)phys_to_virt(x)
+
+#define vga_readb(x) (*(x))
+#define vga_writeb(x, y) (*(y) = (x))
+
+#endif /* ASM_X86__VGA_H */
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
new file mode 100644
index 000000000000..38fd13364021
--- /dev/null
+++ b/arch/x86/include/asm/vgtod.h
@@ -0,0 +1,29 @@
+#ifndef ASM_X86__VGTOD_H
+#define ASM_X86__VGTOD_H
+
+#include <asm/vsyscall.h>
+#include <linux/clocksource.h>
+
+struct vsyscall_gtod_data {
+	seqlock_t	lock;
+
+	/* open coded 'struct timespec' */
+	time_t		wall_time_sec;
+	u32		wall_time_nsec;
+
+	int		sysctl_enabled;
+	struct timezone sys_tz;
+	struct { /* extract of a clocksource struct */
+		cycle_t (*vread)(void);
+		cycle_t	cycle_last;
+		cycle_t	mask;
+		u32	mult;
+		u32	shift;
+	} clock;
+	struct timespec wall_to_monotonic;
+};
+extern struct vsyscall_gtod_data __vsyscall_gtod_data
+__section_vsyscall_gtod_data;
+extern struct vsyscall_gtod_data vsyscall_gtod_data;
+
+#endif /* ASM_X86__VGTOD_H */
diff --git a/arch/x86/include/asm/vic.h b/arch/x86/include/asm/vic.h
new file mode 100644
index 000000000000..53100f353612
--- /dev/null
+++ b/arch/x86/include/asm/vic.h
@@ -0,0 +1,61 @@
+/* Copyright (C) 1999,2001
+ *
+ * Author: J.E.J.Bottomley@HansenPartnership.com
+ *
+ * Standard include definitions for the NCR Voyager Interrupt Controller */
+
+/* The eight CPI vectors.  To activate a CPI, you write a bit mask
+ * corresponding to the processor set to be interrupted into the
+ * relevant register.  That set of CPUs will then be interrupted with
+ * the CPI */
+static const int VIC_CPI_Registers[] =
+	{0xFC00, 0xFC01, 0xFC08, 0xFC09,
+	 0xFC10, 0xFC11, 0xFC18, 0xFC19 };
+
+#define VIC_PROC_WHO_AM_I		0xfc29
+#	define	QUAD_IDENTIFIER		0xC0
+#	define  EIGHT_SLOT_IDENTIFIER	0xE0
+#define QIC_EXTENDED_PROCESSOR_SELECT	0xFC72
+#define VIC_CPI_BASE_REGISTER		0xFC41
+#define VIC_PROCESSOR_ID		0xFC21
+#	define VIC_CPU_MASQUERADE_ENABLE 0x8
+
+#define VIC_CLAIM_REGISTER_0		0xFC38
+#define VIC_CLAIM_REGISTER_1		0xFC39
+#define VIC_REDIRECT_REGISTER_0		0xFC60
+#define VIC_REDIRECT_REGISTER_1		0xFC61
+#define VIC_PRIORITY_REGISTER		0xFC20
+
+#define VIC_PRIMARY_MC_BASE		0xFC48
+#define VIC_SECONDARY_MC_BASE		0xFC49
+
+#define QIC_PROCESSOR_ID		0xFC71
+#	define	QIC_CPUID_ENABLE	0x08
+
+#define QIC_VIC_CPI_BASE_REGISTER	0xFC79
+#define QIC_CPI_BASE_REGISTER		0xFC7A
+
+#define QIC_MASK_REGISTER0		0xFC80
+/* NOTE: these are masked high, enabled low */
+#	define QIC_PERF_TIMER		0x01
+#	define QIC_LPE			0x02
+#	define QIC_SYS_INT		0x04
+#	define QIC_CMN_INT		0x08
+/* at the moment, just enable CMN_INT, disable SYS_INT */
+#	define QIC_DEFAULT_MASK0	(~(QIC_CMN_INT /* | VIC_SYS_INT */))
+#define QIC_MASK_REGISTER1		0xFC81
+#	define QIC_BOOT_CPI_MASK	0xFE
+/* Enable CPI's 1-6 inclusive */
+#	define QIC_CPI_ENABLE		0x81
+
+#define QIC_INTERRUPT_CLEAR0		0xFC8A
+#define QIC_INTERRUPT_CLEAR1		0xFC8B
+
+/* this is where we place the CPI vectors */
+#define VIC_DEFAULT_CPI_BASE		0xC0
+/* this is where we place the QIC CPI vectors */
+#define QIC_DEFAULT_CPI_BASE		0xD0
+
+#define VIC_BOOT_INTERRUPT_MASK		0xfe
+
+extern void smp_vic_timer_interrupt(void);
diff --git a/arch/x86/include/asm/visws/cobalt.h b/arch/x86/include/asm/visws/cobalt.h
new file mode 100644
index 000000000000..9627a8fe84e9
--- /dev/null
+++ b/arch/x86/include/asm/visws/cobalt.h
@@ -0,0 +1,125 @@
+#ifndef ASM_X86__VISWS__COBALT_H
+#define ASM_X86__VISWS__COBALT_H
+
+#include <asm/fixmap.h>
+
+/*
+ * Cobalt SGI Visual Workstation system ASIC
+ */ 
+
+#define CO_CPU_NUM_PHYS 0x1e00
+#define CO_CPU_TAB_PHYS (CO_CPU_NUM_PHYS + 2)
+
+#define CO_CPU_MAX 4
+
+#define	CO_CPU_PHYS		0xc2000000
+#define	CO_APIC_PHYS		0xc4000000
+
+/* see set_fixmap() and asm/fixmap.h */
+#define	CO_CPU_VADDR		(fix_to_virt(FIX_CO_CPU))
+#define	CO_APIC_VADDR		(fix_to_virt(FIX_CO_APIC))
+
+/* Cobalt CPU registers -- relative to CO_CPU_VADDR, use co_cpu_*() */
+#define	CO_CPU_REV		0x08
+#define	CO_CPU_CTRL		0x10
+#define	CO_CPU_STAT		0x20
+#define	CO_CPU_TIMEVAL		0x30
+
+/* CO_CPU_CTRL bits */
+#define	CO_CTRL_TIMERUN		0x04		/* 0 == disabled */
+#define	CO_CTRL_TIMEMASK	0x08		/* 0 == unmasked */
+
+/* CO_CPU_STATUS bits */
+#define	CO_STAT_TIMEINTR	0x02	/* (r) 1 == int pend, (w) 0 == clear */
+
+/* CO_CPU_TIMEVAL value */
+#define	CO_TIME_HZ		100000000	/* Cobalt core rate */
+
+/* Cobalt APIC registers -- relative to CO_APIC_VADDR, use co_apic_*() */
+#define	CO_APIC_HI(n)		(((n) * 0x10) + 4)
+#define	CO_APIC_LO(n)		((n) * 0x10)
+#define	CO_APIC_ID		0x0ffc
+
+/* CO_APIC_ID bits */
+#define	CO_APIC_ENABLE		0x00000100
+
+/* CO_APIC_LO bits */
+#define	CO_APIC_MASK		0x00010000	/* 0 = enabled */
+#define	CO_APIC_LEVEL		0x00008000	/* 0 = edge */
+
+/*
+ * Where things are physically wired to Cobalt
+ * #defines with no board _<type>_<rev>_ are common to all (thus far)
+ */
+#define	CO_APIC_IDE0		4
+#define CO_APIC_IDE1		2		/* Only on 320 */
+
+#define	CO_APIC_8259		12		/* serial, floppy, par-l-l */
+
+/* Lithium PCI Bridge A -- "the one with 82557 Ethernet" */
+#define	CO_APIC_PCIA_BASE0	0 /* and 1 */	/* slot 0, line 0 */
+#define	CO_APIC_PCIA_BASE123	5 /* and 6 */	/* slot 0, line 1 */
+
+#define	CO_APIC_PIIX4_USB	7		/* this one is weird */
+
+/* Lithium PCI Bridge B -- "the one with PIIX4" */
+#define	CO_APIC_PCIB_BASE0	8 /* and 9-12 *//* slot 0, line 0 */
+#define	CO_APIC_PCIB_BASE123	13 /* 14.15 */	/* slot 0, line 1 */
+
+#define	CO_APIC_VIDOUT0		16
+#define	CO_APIC_VIDOUT1		17
+#define	CO_APIC_VIDIN0		18
+#define	CO_APIC_VIDIN1		19
+
+#define	CO_APIC_LI_AUDIO	22
+
+#define	CO_APIC_AS		24
+#define	CO_APIC_RE		25
+
+#define CO_APIC_CPU		28		/* Timer and Cache interrupt */
+#define	CO_APIC_NMI		29
+#define	CO_APIC_LAST		CO_APIC_NMI
+
+/*
+ * This is how irqs are assigned on the Visual Workstation.
+ * Legacy devices get irq's 1-15 (system clock is 0 and is CO_APIC_CPU).
+ * All other devices (including PCI) go to Cobalt and are irq's 16 on up.
+ */
+#define	CO_IRQ_APIC0	16			/* irq of apic entry 0 */
+#define	IS_CO_APIC(irq)	((irq) >= CO_IRQ_APIC0)
+#define	CO_IRQ(apic)	(CO_IRQ_APIC0 + (apic))	/* apic ent to irq */
+#define	CO_APIC(irq)	((irq) - CO_IRQ_APIC0)	/* irq to apic ent */
+#define CO_IRQ_IDE0	14			/* knowledge of... */
+#define CO_IRQ_IDE1	15			/* ... ide driver defaults! */
+#define	CO_IRQ_8259	CO_IRQ(CO_APIC_8259)
+
+#ifdef CONFIG_X86_VISWS_APIC
+static inline void co_cpu_write(unsigned long reg, unsigned long v)
+{
+	*((volatile unsigned long *)(CO_CPU_VADDR+reg))=v;
+}
+
+static inline unsigned long co_cpu_read(unsigned long reg)
+{
+	return *((volatile unsigned long *)(CO_CPU_VADDR+reg));
+}            
+             
+static inline void co_apic_write(unsigned long reg, unsigned long v)
+{
+	*((volatile unsigned long *)(CO_APIC_VADDR+reg))=v;
+}            
+             
+static inline unsigned long co_apic_read(unsigned long reg)
+{
+	return *((volatile unsigned long *)(CO_APIC_VADDR+reg));
+}
+#endif
+
+extern char visws_board_type;
+
+#define	VISWS_320	0
+#define	VISWS_540	1
+
+extern char visws_board_rev;
+
+#endif /* ASM_X86__VISWS__COBALT_H */
diff --git a/arch/x86/include/asm/visws/lithium.h b/arch/x86/include/asm/visws/lithium.h
new file mode 100644
index 000000000000..b36d3b378c63
--- /dev/null
+++ b/arch/x86/include/asm/visws/lithium.h
@@ -0,0 +1,53 @@
+#ifndef ASM_X86__VISWS__LITHIUM_H
+#define ASM_X86__VISWS__LITHIUM_H
+
+#include <asm/fixmap.h>
+
+/*
+ * Lithium is the SGI Visual Workstation I/O ASIC
+ */
+
+#define	LI_PCI_A_PHYS		0xfc000000	/* Enet is dev 3 */
+#define	LI_PCI_B_PHYS		0xfd000000	/* PIIX4 is here */
+
+/* see set_fixmap() and asm/fixmap.h */
+#define LI_PCIA_VADDR   (fix_to_virt(FIX_LI_PCIA))
+#define LI_PCIB_VADDR   (fix_to_virt(FIX_LI_PCIB))
+
+/* Not a standard PCI? (not in linux/pci.h) */
+#define	LI_PCI_BUSNUM	0x44			/* lo8: primary, hi8: sub */
+#define LI_PCI_INTEN    0x46
+
+/* LI_PCI_INTENT bits */
+#define	LI_INTA_0	0x0001
+#define	LI_INTA_1	0x0002
+#define	LI_INTA_2	0x0004
+#define	LI_INTA_3	0x0008
+#define	LI_INTA_4	0x0010
+#define	LI_INTB		0x0020
+#define	LI_INTC		0x0040
+#define	LI_INTD		0x0080
+
+/* More special purpose macros... */
+static inline void li_pcia_write16(unsigned long reg, unsigned short v)
+{
+	*((volatile unsigned short *)(LI_PCIA_VADDR+reg))=v;
+}
+
+static inline unsigned short li_pcia_read16(unsigned long reg)
+{
+	 return *((volatile unsigned short *)(LI_PCIA_VADDR+reg));
+}
+
+static inline void li_pcib_write16(unsigned long reg, unsigned short v)
+{
+	*((volatile unsigned short *)(LI_PCIB_VADDR+reg))=v;
+}
+
+static inline unsigned short li_pcib_read16(unsigned long reg)
+{
+	return *((volatile unsigned short *)(LI_PCIB_VADDR+reg));
+}
+
+#endif /* ASM_X86__VISWS__LITHIUM_H */
+
diff --git a/arch/x86/include/asm/visws/piix4.h b/arch/x86/include/asm/visws/piix4.h
new file mode 100644
index 000000000000..61c938045ec9
--- /dev/null
+++ b/arch/x86/include/asm/visws/piix4.h
@@ -0,0 +1,107 @@
+#ifndef ASM_X86__VISWS__PIIX4_H
+#define ASM_X86__VISWS__PIIX4_H
+
+/*
+ * PIIX4 as used on SGI Visual Workstations
+ */
+
+#define	PIIX_PM_START		0x0F80
+
+#define	SIO_GPIO_START		0x0FC0
+
+#define	SIO_PM_START		0x0FC8
+
+#define	PMBASE			PIIX_PM_START
+#define	GPIREG0			(PMBASE+0x30)
+#define	GPIREG(x)		(GPIREG0+((x)/8))
+#define	GPIBIT(x)		(1 << ((x)%8))
+
+#define	PIIX_GPI_BD_ID1		18
+#define	PIIX_GPI_BD_ID2		19
+#define	PIIX_GPI_BD_ID3		20
+#define	PIIX_GPI_BD_ID4		21
+#define	PIIX_GPI_BD_REG		GPIREG(PIIX_GPI_BD_ID1)
+#define	PIIX_GPI_BD_MASK	(GPIBIT(PIIX_GPI_BD_ID1) | \
+				GPIBIT(PIIX_GPI_BD_ID2) | \
+				GPIBIT(PIIX_GPI_BD_ID3) | \
+				GPIBIT(PIIX_GPI_BD_ID4) )
+
+#define	PIIX_GPI_BD_SHIFT	(PIIX_GPI_BD_ID1 % 8)
+
+#define	SIO_INDEX		0x2e
+#define	SIO_DATA		0x2f
+
+#define	SIO_DEV_SEL		0x7
+#define	SIO_DEV_ENB		0x30
+#define	SIO_DEV_MSB		0x60
+#define	SIO_DEV_LSB		0x61
+
+#define	SIO_GP_DEV		0x7
+
+#define	SIO_GP_BASE		SIO_GPIO_START
+#define	SIO_GP_MSB		(SIO_GP_BASE>>8)
+#define	SIO_GP_LSB		(SIO_GP_BASE&0xff)
+
+#define	SIO_GP_DATA1		(SIO_GP_BASE+0)
+
+#define	SIO_PM_DEV		0x8
+
+#define	SIO_PM_BASE		SIO_PM_START
+#define	SIO_PM_MSB		(SIO_PM_BASE>>8)
+#define	SIO_PM_LSB		(SIO_PM_BASE&0xff)
+#define	SIO_PM_INDEX		(SIO_PM_BASE+0)
+#define	SIO_PM_DATA		(SIO_PM_BASE+1)
+
+#define	SIO_PM_FER2		0x1
+
+#define	SIO_PM_GP_EN		0x80
+
+
+
+/*
+ * This is the dev/reg where generating a config cycle will
+ * result in a PCI special cycle.
+ */
+#define SPECIAL_DEV		0xff
+#define SPECIAL_REG		0x00
+
+/*
+ * PIIX4 needs to see a special cycle with the following data
+ * to be convinced the processor has gone into the stop grant
+ * state.  PIIX4 insists on seeing this before it will power
+ * down a system.
+ */
+#define PIIX_SPECIAL_STOP		0x00120002
+
+#define PIIX4_RESET_PORT	0xcf9
+#define PIIX4_RESET_VAL		0x6
+
+#define PMSTS_PORT		0xf80	// 2 bytes	PM Status
+#define PMEN_PORT		0xf82	// 2 bytes	PM Enable
+#define	PMCNTRL_PORT		0xf84	// 2 bytes	PM Control
+
+#define PM_SUSPEND_ENABLE	0x2000	// start sequence to suspend state
+
+/*
+ * PMSTS and PMEN I/O bit definitions.
+ * (Bits are the same in both registers)
+ */
+#define PM_STS_RSM		(1<<15)	// Resume Status
+#define PM_STS_PWRBTNOR		(1<<11)	// Power Button Override
+#define PM_STS_RTC		(1<<10)	// RTC status
+#define PM_STS_PWRBTN		(1<<8)	// Power Button Pressed?
+#define PM_STS_GBL		(1<<5)	// Global Status
+#define PM_STS_BM		(1<<4)	// Bus Master Status
+#define PM_STS_TMROF		(1<<0)	// Timer Overflow Status.
+
+/*
+ * Stop clock GPI register
+ */
+#define PIIX_GPIREG0			(0xf80 + 0x30)
+
+/*
+ * Stop clock GPI bit in GPIREG0
+ */
+#define	PIIX_GPI_STPCLK		0x4	// STPCLK signal routed back in
+
+#endif /* ASM_X86__VISWS__PIIX4_H */
diff --git a/arch/x86/include/asm/visws/sgivw.h b/arch/x86/include/asm/visws/sgivw.h
new file mode 100644
index 000000000000..5fbf63e1003c
--- /dev/null
+++ b/arch/x86/include/asm/visws/sgivw.h
@@ -0,0 +1,5 @@
+/*
+ * Frame buffer position and size:
+ */
+extern unsigned long sgivwfb_mem_phys;
+extern unsigned long sgivwfb_mem_size;
diff --git a/arch/x86/include/asm/vm86.h b/arch/x86/include/asm/vm86.h
new file mode 100644
index 000000000000..998bd18eb737
--- /dev/null
+++ b/arch/x86/include/asm/vm86.h
@@ -0,0 +1,208 @@
+#ifndef ASM_X86__VM86_H
+#define ASM_X86__VM86_H
+
+/*
+ * I'm guessing at the VIF/VIP flag usage, but hope that this is how
+ * the Pentium uses them. Linux will return from vm86 mode when both
+ * VIF and VIP is set.
+ *
+ * On a Pentium, we could probably optimize the virtual flags directly
+ * in the eflags register instead of doing it "by hand" in vflags...
+ *
+ * Linus
+ */
+
+#include <asm/processor-flags.h>
+
+#define BIOSSEG		0x0f000
+
+#define CPU_086		0
+#define CPU_186		1
+#define CPU_286		2
+#define CPU_386		3
+#define CPU_486		4
+#define CPU_586		5
+
+/*
+ * Return values for the 'vm86()' system call
+ */
+#define VM86_TYPE(retval)	((retval) & 0xff)
+#define VM86_ARG(retval)	((retval) >> 8)
+
+#define VM86_SIGNAL	0	/* return due to signal */
+#define VM86_UNKNOWN	1	/* unhandled GP fault
+				   - IO-instruction or similar */
+#define VM86_INTx	2	/* int3/int x instruction (ARG = x) */
+#define VM86_STI	3	/* sti/popf/iret instruction enabled
+				   virtual interrupts */
+
+/*
+ * Additional return values when invoking new vm86()
+ */
+#define VM86_PICRETURN	4	/* return due to pending PIC request */
+#define VM86_TRAP	6	/* return due to DOS-debugger request */
+
+/*
+ * function codes when invoking new vm86()
+ */
+#define VM86_PLUS_INSTALL_CHECK	0
+#define VM86_ENTER		1
+#define VM86_ENTER_NO_BYPASS	2
+#define	VM86_REQUEST_IRQ	3
+#define VM86_FREE_IRQ		4
+#define VM86_GET_IRQ_BITS	5
+#define VM86_GET_AND_RESET_IRQ	6
+
+/*
+ * This is the stack-layout seen by the user space program when we have
+ * done a translation of "SAVE_ALL" from vm86 mode. The real kernel layout
+ * is 'kernel_vm86_regs' (see below).
+ */
+
+struct vm86_regs {
+/*
+ * normal regs, with special meaning for the segment descriptors..
+ */
+	long ebx;
+	long ecx;
+	long edx;
+	long esi;
+	long edi;
+	long ebp;
+	long eax;
+	long __null_ds;
+	long __null_es;
+	long __null_fs;
+	long __null_gs;
+	long orig_eax;
+	long eip;
+	unsigned short cs, __csh;
+	long eflags;
+	long esp;
+	unsigned short ss, __ssh;
+/*
+ * these are specific to v86 mode:
+ */
+	unsigned short es, __esh;
+	unsigned short ds, __dsh;
+	unsigned short fs, __fsh;
+	unsigned short gs, __gsh;
+};
+
+struct revectored_struct {
+	unsigned long __map[8];			/* 256 bits */
+};
+
+struct vm86_struct {
+	struct vm86_regs regs;
+	unsigned long flags;
+	unsigned long screen_bitmap;
+	unsigned long cpu_type;
+	struct revectored_struct int_revectored;
+	struct revectored_struct int21_revectored;
+};
+
+/*
+ * flags masks
+ */
+#define VM86_SCREEN_BITMAP	0x0001
+
+struct vm86plus_info_struct {
+	unsigned long force_return_for_pic:1;
+	unsigned long vm86dbg_active:1;       /* for debugger */
+	unsigned long vm86dbg_TFpendig:1;     /* for debugger */
+	unsigned long unused:28;
+	unsigned long is_vm86pus:1;	      /* for vm86 internal use */
+	unsigned char vm86dbg_intxxtab[32];   /* for debugger */
+};
+struct vm86plus_struct {
+	struct vm86_regs regs;
+	unsigned long flags;
+	unsigned long screen_bitmap;
+	unsigned long cpu_type;
+	struct revectored_struct int_revectored;
+	struct revectored_struct int21_revectored;
+	struct vm86plus_info_struct vm86plus;
+};
+
+#ifdef __KERNEL__
+
+#include <asm/ptrace.h>
+
+/*
+ * This is the (kernel) stack-layout when we have done a "SAVE_ALL" from vm86
+ * mode - the main change is that the old segment descriptors aren't
+ * useful any more and are forced to be zero by the kernel (and the
+ * hardware when a trap occurs), and the real segment descriptors are
+ * at the end of the structure. Look at ptrace.h to see the "normal"
+ * setup. For user space layout see 'struct vm86_regs' above.
+ */
+
+struct kernel_vm86_regs {
+/*
+ * normal regs, with special meaning for the segment descriptors..
+ */
+	struct pt_regs pt;
+/*
+ * these are specific to v86 mode:
+ */
+	unsigned short es, __esh;
+	unsigned short ds, __dsh;
+	unsigned short fs, __fsh;
+	unsigned short gs, __gsh;
+};
+
+struct kernel_vm86_struct {
+	struct kernel_vm86_regs regs;
+/*
+ * the below part remains on the kernel stack while we are in VM86 mode.
+ * 'tss.esp0' then contains the address of VM86_TSS_ESP0 below, and when we
+ * get forced back from VM86, the CPU and "SAVE_ALL" will restore the above
+ * 'struct kernel_vm86_regs' with the then actual values.
+ * Therefore, pt_regs in fact points to a complete 'kernel_vm86_struct'
+ * in kernelspace, hence we need not reget the data from userspace.
+ */
+#define VM86_TSS_ESP0 flags
+	unsigned long flags;
+	unsigned long screen_bitmap;
+	unsigned long cpu_type;
+	struct revectored_struct int_revectored;
+	struct revectored_struct int21_revectored;
+	struct vm86plus_info_struct vm86plus;
+	struct pt_regs *regs32;   /* here we save the pointer to the old regs */
+/*
+ * The below is not part of the structure, but the stack layout continues
+ * this way. In front of 'return-eip' may be some data, depending on
+ * compilation, so we don't rely on this and save the pointer to 'oldregs'
+ * in 'regs32' above.
+ * However, with GCC-2.7.2 and the current CFLAGS you see exactly this:
+
+	long return-eip;        from call to vm86()
+	struct pt_regs oldregs;  user space registers as saved by syscall
+ */
+};
+
+#ifdef CONFIG_VM86
+
+void handle_vm86_fault(struct kernel_vm86_regs *, long);
+int handle_vm86_trap(struct kernel_vm86_regs *, long, int);
+struct pt_regs *save_v86_state(struct kernel_vm86_regs *);
+
+struct task_struct;
+void release_vm86_irqs(struct task_struct *);
+
+#else
+
+#define handle_vm86_fault(a, b)
+#define release_vm86_irqs(a)
+
+static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c)
+{
+	return 0;
+}
+
+#endif /* CONFIG_VM86 */
+
+#endif /* __KERNEL__ */
+
+#endif /* ASM_X86__VM86_H */
diff --git a/arch/x86/include/asm/vmi.h b/arch/x86/include/asm/vmi.h
new file mode 100644
index 000000000000..b7c0dea119fe
--- /dev/null
+++ b/arch/x86/include/asm/vmi.h
@@ -0,0 +1,263 @@
+/*
+ * VMI interface definition
+ *
+ * Copyright (C) 2005, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Maintained by: Zachary Amsden zach@vmware.com
+ *
+ */
+#include <linux/types.h>
+
+/*
+ *---------------------------------------------------------------------
+ *
+ *  VMI Option ROM API
+ *
+ *---------------------------------------------------------------------
+ */
+#define VMI_SIGNATURE 0x696d5663   /* "cVmi" */
+
+#define PCI_VENDOR_ID_VMWARE            0x15AD
+#define PCI_DEVICE_ID_VMWARE_VMI        0x0801
+
+/*
+ * We use two version numbers for compatibility, with the major
+ * number signifying interface breakages, and the minor number
+ * interface extensions.
+ */
+#define VMI_API_REV_MAJOR       3
+#define VMI_API_REV_MINOR       0
+
+#define VMI_CALL_CPUID			0
+#define VMI_CALL_WRMSR			1
+#define VMI_CALL_RDMSR			2
+#define VMI_CALL_SetGDT			3
+#define VMI_CALL_SetLDT			4
+#define VMI_CALL_SetIDT			5
+#define VMI_CALL_SetTR			6
+#define VMI_CALL_GetGDT			7
+#define VMI_CALL_GetLDT			8
+#define VMI_CALL_GetIDT			9
+#define VMI_CALL_GetTR			10
+#define VMI_CALL_WriteGDTEntry		11
+#define VMI_CALL_WriteLDTEntry		12
+#define VMI_CALL_WriteIDTEntry		13
+#define VMI_CALL_UpdateKernelStack	14
+#define VMI_CALL_SetCR0			15
+#define VMI_CALL_SetCR2			16
+#define VMI_CALL_SetCR3			17
+#define VMI_CALL_SetCR4			18
+#define VMI_CALL_GetCR0			19
+#define VMI_CALL_GetCR2			20
+#define VMI_CALL_GetCR3			21
+#define VMI_CALL_GetCR4			22
+#define VMI_CALL_WBINVD			23
+#define VMI_CALL_SetDR			24
+#define VMI_CALL_GetDR			25
+#define VMI_CALL_RDPMC			26
+#define VMI_CALL_RDTSC			27
+#define VMI_CALL_CLTS			28
+#define VMI_CALL_EnableInterrupts	29
+#define VMI_CALL_DisableInterrupts	30
+#define VMI_CALL_GetInterruptMask	31
+#define VMI_CALL_SetInterruptMask	32
+#define VMI_CALL_IRET			33
+#define VMI_CALL_SYSEXIT		34
+#define VMI_CALL_Halt			35
+#define VMI_CALL_Reboot			36
+#define VMI_CALL_Shutdown		37
+#define VMI_CALL_SetPxE			38
+#define VMI_CALL_SetPxELong		39
+#define VMI_CALL_UpdatePxE		40
+#define VMI_CALL_UpdatePxELong		41
+#define VMI_CALL_MachineToPhysical	42
+#define VMI_CALL_PhysicalToMachine	43
+#define VMI_CALL_AllocatePage		44
+#define VMI_CALL_ReleasePage		45
+#define VMI_CALL_InvalPage		46
+#define VMI_CALL_FlushTLB		47
+#define VMI_CALL_SetLinearMapping	48
+
+#define VMI_CALL_SetIOPLMask		61
+#define VMI_CALL_SetInitialAPState	62
+#define VMI_CALL_APICWrite		63
+#define VMI_CALL_APICRead		64
+#define VMI_CALL_IODelay		65
+#define VMI_CALL_SetLazyMode		73
+
+/*
+ *---------------------------------------------------------------------
+ *
+ * MMU operation flags
+ *
+ *---------------------------------------------------------------------
+ */
+
+/* Flags used by VMI_{Allocate|Release}Page call */
+#define VMI_PAGE_PAE             0x10  /* Allocate PAE shadow */
+#define VMI_PAGE_CLONE           0x20  /* Clone from another shadow */
+#define VMI_PAGE_ZEROED          0x40  /* Page is pre-zeroed */
+
+
+/* Flags shared by Allocate|Release Page and PTE updates */
+#define VMI_PAGE_PT              0x01
+#define VMI_PAGE_PD              0x02
+#define VMI_PAGE_PDP             0x04
+#define VMI_PAGE_PML4            0x08
+
+#define VMI_PAGE_NORMAL          0x00 /* for debugging */
+
+/* Flags used by PTE updates */
+#define VMI_PAGE_CURRENT_AS      0x10 /* implies VMI_PAGE_VA_MASK is valid */
+#define VMI_PAGE_DEFER           0x20 /* may queue update until TLB inval */
+#define VMI_PAGE_VA_MASK         0xfffff000
+
+#ifdef CONFIG_X86_PAE
+#define VMI_PAGE_L1		(VMI_PAGE_PT | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
+#define VMI_PAGE_L2		(VMI_PAGE_PD | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
+#else
+#define VMI_PAGE_L1		(VMI_PAGE_PT | VMI_PAGE_ZEROED)
+#define VMI_PAGE_L2		(VMI_PAGE_PD | VMI_PAGE_ZEROED)
+#endif
+
+/* Flags used by VMI_FlushTLB call */
+#define VMI_FLUSH_TLB            0x01
+#define VMI_FLUSH_GLOBAL         0x02
+
+/*
+ *---------------------------------------------------------------------
+ *
+ *  VMI relocation definitions for ROM call get_reloc
+ *
+ *---------------------------------------------------------------------
+ */
+
+/* VMI Relocation types */
+#define VMI_RELOCATION_NONE     0
+#define VMI_RELOCATION_CALL_REL 1
+#define VMI_RELOCATION_JUMP_REL 2
+#define VMI_RELOCATION_NOP	3
+
+#ifndef __ASSEMBLY__
+struct vmi_relocation_info {
+	unsigned char           *eip;
+	unsigned char           type;
+	unsigned char           reserved[3];
+};
+#endif
+
+
+/*
+ *---------------------------------------------------------------------
+ *
+ *  Generic ROM structures and definitions
+ *
+ *---------------------------------------------------------------------
+ */
+
+#ifndef __ASSEMBLY__
+
+struct vrom_header {
+	u16     rom_signature;  /* option ROM signature */
+	u8      rom_length;     /* ROM length in 512 byte chunks */
+	u8      rom_entry[4];   /* 16-bit code entry point */
+	u8      rom_pad0;       /* 4-byte align pad */
+	u32     vrom_signature; /* VROM identification signature */
+	u8      api_version_min;/* Minor version of API */
+	u8      api_version_maj;/* Major version of API */
+	u8      jump_slots;     /* Number of jump slots */
+	u8      reserved1;      /* Reserved for expansion */
+	u32     virtual_top;    /* Hypervisor virtual address start */
+	u16     reserved2;      /* Reserved for expansion */
+	u16	license_offs;	/* Offset to License string */
+	u16     pci_header_offs;/* Offset to PCI OPROM header */
+	u16     pnp_header_offs;/* Offset to PnP OPROM header */
+	u32     rom_pad3;       /* PnP reserverd / VMI reserved */
+	u8      reserved[96];   /* Reserved for headers */
+	char    vmi_init[8];    /* VMI_Init jump point */
+	char    get_reloc[8];   /* VMI_GetRelocationInfo jump point */
+} __attribute__((packed));
+
+struct pnp_header {
+	char sig[4];
+	char rev;
+	char size;
+	short next;
+	short res;
+	long devID;
+	unsigned short manufacturer_offset;
+	unsigned short product_offset;
+} __attribute__((packed));
+
+struct pci_header {
+	char sig[4];
+	short vendorID;
+	short deviceID;
+	short vpdData;
+	short size;
+	char rev;
+	char class;
+	char subclass;
+	char interface;
+	short chunks;
+	char rom_version_min;
+	char rom_version_maj;
+	char codetype;
+	char lastRom;
+	short reserved;
+} __attribute__((packed));
+
+/* Function prototypes for bootstrapping */
+extern void vmi_init(void);
+extern void vmi_bringup(void);
+extern void vmi_apply_boot_page_allocations(void);
+
+/* State needed to start an application processor in an SMP system. */
+struct vmi_ap_state {
+	u32 cr0;
+	u32 cr2;
+	u32 cr3;
+	u32 cr4;
+
+	u64 efer;
+
+	u32 eip;
+	u32 eflags;
+	u32 eax;
+	u32 ebx;
+	u32 ecx;
+	u32 edx;
+	u32 esp;
+	u32 ebp;
+	u32 esi;
+	u32 edi;
+	u16 cs;
+	u16 ss;
+	u16 ds;
+	u16 es;
+	u16 fs;
+	u16 gs;
+	u16 ldtr;
+
+	u16 gdtr_limit;
+	u32 gdtr_base;
+	u32 idtr_base;
+	u16 idtr_limit;
+};
+
+#endif
diff --git a/arch/x86/include/asm/vmi_time.h b/arch/x86/include/asm/vmi_time.h
new file mode 100644
index 000000000000..b2d39e6a08b7
--- /dev/null
+++ b/arch/x86/include/asm/vmi_time.h
@@ -0,0 +1,98 @@
+/*
+ * VMI Time wrappers
+ *
+ * Copyright (C) 2006, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to dhecht@vmware.com
+ *
+ */
+
+#ifndef ASM_X86__VMI_TIME_H
+#define ASM_X86__VMI_TIME_H
+
+/*
+ * Raw VMI call indices for timer functions
+ */
+#define VMI_CALL_GetCycleFrequency	66
+#define VMI_CALL_GetCycleCounter	67
+#define VMI_CALL_SetAlarm		68
+#define VMI_CALL_CancelAlarm		69
+#define VMI_CALL_GetWallclockTime	70
+#define VMI_CALL_WallclockUpdated	71
+
+/* Cached VMI timer operations */
+extern struct vmi_timer_ops {
+	u64 (*get_cycle_frequency)(void);
+	u64 (*get_cycle_counter)(int);
+	u64 (*get_wallclock)(void);
+	int (*wallclock_updated)(void);
+	void (*set_alarm)(u32 flags, u64 expiry, u64 period);
+	void (*cancel_alarm)(u32 flags);
+} vmi_timer_ops;
+
+/* Prototypes */
+extern void __init vmi_time_init(void);
+extern unsigned long vmi_get_wallclock(void);
+extern int vmi_set_wallclock(unsigned long now);
+extern unsigned long long vmi_sched_clock(void);
+extern unsigned long vmi_tsc_khz(void);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+extern void __devinit vmi_time_bsp_init(void);
+extern void __devinit vmi_time_ap_init(void);
+#endif
+
+/*
+ * When run under a hypervisor, a vcpu is always in one of three states:
+ * running, halted, or ready.  The vcpu is in the 'running' state if it
+ * is executing.  When the vcpu executes the halt interface, the vcpu
+ * enters the 'halted' state and remains halted until there is some work
+ * pending for the vcpu (e.g. an alarm expires, host I/O completes on
+ * behalf of virtual I/O).  At this point, the vcpu enters the 'ready'
+ * state (waiting for the hypervisor to reschedule it).  Finally, at any
+ * time when the vcpu is not in the 'running' state nor the 'halted'
+ * state, it is in the 'ready' state.
+ *
+ * Real time is advances while the vcpu is 'running', 'ready', or
+ * 'halted'.  Stolen time is the time in which the vcpu is in the
+ * 'ready' state.  Available time is the remaining time -- the vcpu is
+ * either 'running' or 'halted'.
+ *
+ * All three views of time are accessible through the VMI cycle
+ * counters.
+ */
+
+/* The cycle counters. */
+#define VMI_CYCLES_REAL         0
+#define VMI_CYCLES_AVAILABLE    1
+#define VMI_CYCLES_STOLEN       2
+
+/* The alarm interface 'flags' bits */
+#define VMI_ALARM_COUNTERS      2
+
+#define VMI_ALARM_COUNTER_MASK  0x000000ff
+
+#define VMI_ALARM_WIRED_IRQ0    0x00000000
+#define VMI_ALARM_WIRED_LVTT    0x00010000
+
+#define VMI_ALARM_IS_ONESHOT    0x00000000
+#define VMI_ALARM_IS_PERIODIC   0x00000100
+
+#define CONFIG_VMI_ALARM_HZ	100
+
+#endif /* ASM_X86__VMI_TIME_H */
diff --git a/arch/x86/include/asm/voyager.h b/arch/x86/include/asm/voyager.h
new file mode 100644
index 000000000000..9c811d2e6f91
--- /dev/null
+++ b/arch/x86/include/asm/voyager.h
@@ -0,0 +1,528 @@
+/* Copyright (C) 1999,2001
+ *
+ * Author: J.E.J.Bottomley@HansenPartnership.com
+ *
+ * Standard include definitions for the NCR Voyager system */
+
+#undef	VOYAGER_DEBUG
+#undef	VOYAGER_CAT_DEBUG
+
+#ifdef VOYAGER_DEBUG
+#define VDEBUG(x)	printk x
+#else
+#define VDEBUG(x)
+#endif
+
+/* There are three levels of voyager machine: 3,4 and 5. The rule is
+ * if it's less than 3435 it's a Level 3 except for a 3360 which is
+ * a level 4.  A 3435 or above is a Level 5 */
+#define VOYAGER_LEVEL5_AND_ABOVE	0x3435
+#define VOYAGER_LEVEL4			0x3360
+
+/* The L4 DINO ASIC */
+#define VOYAGER_DINO			0x43
+
+/* voyager ports in standard I/O space */
+#define VOYAGER_MC_SETUP	0x96
+
+
+#define	VOYAGER_CAT_CONFIG_PORT			0x97
+#	define VOYAGER_CAT_DESELECT		0xff
+#define VOYAGER_SSPB_RELOCATION_PORT		0x98
+
+/* Valid CAT controller commands */
+/* start instruction register cycle */
+#define VOYAGER_CAT_IRCYC			0x01
+/* start data register cycle */
+#define VOYAGER_CAT_DRCYC			0x02
+/* move to execute state */
+#define VOYAGER_CAT_RUN				0x0F
+/* end operation */
+#define VOYAGER_CAT_END				0x80
+/* hold in idle state */
+#define VOYAGER_CAT_HOLD			0x90
+/* single step an "intest" vector */
+#define VOYAGER_CAT_STEP			0xE0
+/* return cat controller to CLEMSON mode */
+#define VOYAGER_CAT_CLEMSON			0xFF
+
+/* the default cat command header */
+#define VOYAGER_CAT_HEADER			0x7F
+
+/* the range of possible CAT module ids in the system */
+#define VOYAGER_MIN_MODULE			0x10
+#define VOYAGER_MAX_MODULE			0x1f
+
+/* The voyager registers per asic */
+#define VOYAGER_ASIC_ID_REG			0x00
+#define VOYAGER_ASIC_TYPE_REG			0x01
+/* the sub address registers can be made auto incrementing on reads */
+#define VOYAGER_AUTO_INC_REG			0x02
+#	define VOYAGER_AUTO_INC			0x04
+#	define VOYAGER_NO_AUTO_INC		0xfb
+#define VOYAGER_SUBADDRDATA			0x03
+#define VOYAGER_SCANPATH			0x05
+#	define VOYAGER_CONNECT_ASIC		0x01
+#	define VOYAGER_DISCONNECT_ASIC		0xfe
+#define VOYAGER_SUBADDRLO			0x06
+#define VOYAGER_SUBADDRHI			0x07
+#define VOYAGER_SUBMODSELECT			0x08
+#define VOYAGER_SUBMODPRESENT			0x09
+
+#define VOYAGER_SUBADDR_LO			0xff
+#define VOYAGER_SUBADDR_HI			0xffff
+
+/* the maximum size of a scan path -- used to form instructions */
+#define VOYAGER_MAX_SCAN_PATH			0x100
+/* the biggest possible register size (in bytes) */
+#define VOYAGER_MAX_REG_SIZE			4
+
+/* Total number of possible modules (including submodules) */
+#define VOYAGER_MAX_MODULES			16
+/* Largest number of asics per module */
+#define VOYAGER_MAX_ASICS_PER_MODULE		7
+
+/* the CAT asic of each module is always the first one */
+#define VOYAGER_CAT_ID				0
+#define VOYAGER_PSI				0x1a
+
+/* voyager instruction operations and registers */
+#define VOYAGER_READ_CONFIG			0x1
+#define VOYAGER_WRITE_CONFIG			0x2
+#define VOYAGER_BYPASS				0xff
+
+typedef struct voyager_asic {
+	__u8	asic_addr;	/* ASIC address; Level 4 */
+	__u8	asic_type;      /* ASIC type */
+	__u8	asic_id;	/* ASIC id */
+	__u8	jtag_id[4];	/* JTAG id */
+	__u8	asic_location;	/* Location within scan path; start w/ 0 */
+	__u8	bit_location;	/* Location within bit stream; start w/ 0 */
+	__u8	ireg_length;	/* Instruction register length */
+	__u16	subaddr;	/* Amount of sub address space */
+	struct voyager_asic *next;	/* Next asic in linked list */
+} voyager_asic_t;
+
+typedef struct voyager_module {
+	__u8	module_addr;		/* Module address */
+	__u8	scan_path_connected;	/* Scan path connected */
+	__u16   ee_size;		/* Size of the EEPROM */
+	__u16   num_asics;		/* Number of Asics */
+	__u16   inst_bits;		/* Instruction bits in the scan path */
+	__u16   largest_reg;		/* Largest register in the scan path */
+	__u16   smallest_reg;		/* Smallest register in the scan path */
+	voyager_asic_t   *asic;		/* First ASIC in scan path (CAT_I) */
+	struct   voyager_module *submodule;	/* Submodule pointer */
+	struct   voyager_module *next;		/* Next module in linked list */
+} voyager_module_t;
+
+typedef struct voyager_eeprom_hdr {
+	 __u8  module_id[4];
+	 __u8  version_id;
+	 __u8  config_id;
+	 __u16 boundry_id;	/* boundary scan id */
+	 __u16 ee_size;		/* size of EEPROM */
+	 __u8  assembly[11];	/* assembly # */
+	 __u8  assembly_rev;	/* assembly rev */
+	 __u8  tracer[4];	/* tracer number */
+	 __u16 assembly_cksum;	/* asm checksum */
+	 __u16 power_consump;	/* pwr requirements */
+	 __u16 num_asics;	/* number of asics */
+	 __u16 bist_time;	/* min. bist time */
+	 __u16 err_log_offset;	/* error log offset */
+	 __u16 scan_path_offset;/* scan path offset */
+	 __u16 cct_offset;
+	 __u16 log_length;	/* length of err log */
+	 __u16 xsum_end;	/* offset to end of
+				   checksum */
+	 __u8  reserved[4];
+	 __u8  sflag;		/* starting sentinal */
+	 __u8  part_number[13];	/* prom part number */
+	 __u8  version[10];	/* version number */
+	 __u8  signature[8];
+	 __u16 eeprom_chksum;
+	 __u32  data_stamp_offset;
+	 __u8  eflag ;		 /* ending sentinal */
+} __attribute__((packed)) voyager_eprom_hdr_t;
+
+
+
+#define VOYAGER_EPROM_SIZE_OFFSET				\
+	((__u16)(&(((voyager_eprom_hdr_t *)0)->ee_size)))
+#define VOYAGER_XSUM_END_OFFSET		0x2a
+
+/* the following three definitions are for internal table layouts
+ * in the module EPROMs.  We really only care about the IDs and
+ * offsets */
+typedef struct voyager_sp_table {
+	__u8 asic_id;
+	__u8 bypass_flag;
+	__u16 asic_data_offset;
+	__u16 config_data_offset;
+} __attribute__((packed)) voyager_sp_table_t;
+
+typedef struct voyager_jtag_table {
+	__u8 icode[4];
+	__u8 runbist[4];
+	__u8 intest[4];
+	__u8 samp_preld[4];
+	__u8 ireg_len;
+} __attribute__((packed)) voyager_jtt_t;
+
+typedef struct voyager_asic_data_table {
+	__u8 jtag_id[4];
+	__u16 length_bsr;
+	__u16 length_bist_reg;
+	__u32 bist_clk;
+	__u16 subaddr_bits;
+	__u16 seed_bits;
+	__u16 sig_bits;
+	__u16 jtag_offset;
+} __attribute__((packed)) voyager_at_t;
+
+/* Voyager Interrupt Controller (VIC) registers */
+
+/* Base to add to Cross Processor Interrupts (CPIs) when triggering
+ * the CPU IRQ line */
+/* register defines for the WCBICs (one per processor) */
+#define VOYAGER_WCBIC0	0x41		/* bus A node P1 processor 0 */
+#define VOYAGER_WCBIC1	0x49		/* bus A node P1 processor 1 */
+#define VOYAGER_WCBIC2	0x51		/* bus A node P2 processor 0 */
+#define VOYAGER_WCBIC3	0x59		/* bus A node P2 processor 1 */
+#define VOYAGER_WCBIC4	0x61		/* bus B node P1 processor 0 */
+#define VOYAGER_WCBIC5	0x69		/* bus B node P1 processor 1 */
+#define VOYAGER_WCBIC6	0x71		/* bus B node P2 processor 0 */
+#define VOYAGER_WCBIC7	0x79		/* bus B node P2 processor 1 */
+
+
+/* top of memory registers */
+#define VOYAGER_WCBIC_TOM_L	0x4
+#define VOYAGER_WCBIC_TOM_H	0x5
+
+/* register defines for Voyager Memory Contol (VMC)
+ * these are present on L4 machines only */
+#define	VOYAGER_VMC1		0x81
+#define VOYAGER_VMC2		0x91
+#define VOYAGER_VMC3		0xa1
+#define VOYAGER_VMC4		0xb1
+
+/* VMC Ports */
+#define VOYAGER_VMC_MEMORY_SETUP	0x9
+#	define VMC_Interleaving		0x01
+#	define VMC_4Way			0x02
+#	define VMC_EvenCacheLines	0x04
+#	define VMC_HighLine		0x08
+#	define VMC_Start0_Enable	0x20
+#	define VMC_Start1_Enable	0x40
+#	define VMC_Vremap		0x80
+#define VOYAGER_VMC_BANK_DENSITY	0xa
+#	define	VMC_BANK_EMPTY		0
+#	define	VMC_BANK_4MB		1
+#	define	VMC_BANK_16MB		2
+#	define	VMC_BANK_64MB		3
+#	define	VMC_BANK0_MASK		0x03
+#	define	VMC_BANK1_MASK		0x0C
+#	define	VMC_BANK2_MASK		0x30
+#	define	VMC_BANK3_MASK		0xC0
+
+/* Magellan Memory Controller (MMC) defines - present on L5 */
+#define VOYAGER_MMC_ASIC_ID		1
+/* the two memory modules corresponding to memory cards in the system */
+#define VOYAGER_MMC_MEMORY0_MODULE	0x14
+#define VOYAGER_MMC_MEMORY1_MODULE	0x15
+/* the Magellan Memory Address (MMA) defines */
+#define VOYAGER_MMA_ASIC_ID		2
+
+/* Submodule number for the Quad Baseboard */
+#define VOYAGER_QUAD_BASEBOARD		1
+
+/* ASIC defines for the Quad Baseboard */
+#define VOYAGER_QUAD_QDATA0		1
+#define VOYAGER_QUAD_QDATA1		2
+#define VOYAGER_QUAD_QABC		3
+
+/* Useful areas in extended CMOS */
+#define VOYAGER_PROCESSOR_PRESENT_MASK	0x88a
+#define VOYAGER_MEMORY_CLICKMAP		0xa23
+#define VOYAGER_DUMP_LOCATION		0xb1a
+
+/* SUS In Control bit - used to tell SUS that we don't need to be
+ * babysat anymore */
+#define VOYAGER_SUS_IN_CONTROL_PORT	0x3ff
+#	define VOYAGER_IN_CONTROL_FLAG	0x80
+
+/* Voyager PSI defines */
+#define VOYAGER_PSI_STATUS_REG		0x08
+#	define PSI_DC_FAIL		0x01
+#	define PSI_MON			0x02
+#	define PSI_FAULT		0x04
+#	define PSI_ALARM		0x08
+#	define PSI_CURRENT		0x10
+#	define PSI_DVM			0x20
+#	define PSI_PSCFAULT		0x40
+#	define PSI_STAT_CHG		0x80
+
+#define VOYAGER_PSI_SUPPLY_REG		0x8000
+	/* read */
+#	define PSI_FAIL_DC		0x01
+#	define PSI_FAIL_AC		0x02
+#	define PSI_MON_INT		0x04
+#	define PSI_SWITCH_OFF		0x08
+#	define PSI_HX_OFF		0x10
+#	define PSI_SECURITY		0x20
+#	define PSI_CMOS_BATT_LOW	0x40
+#	define PSI_CMOS_BATT_FAIL	0x80
+	/* write */
+#	define PSI_CLR_SWITCH_OFF	0x13
+#	define PSI_CLR_HX_OFF		0x14
+#	define PSI_CLR_CMOS_BATT_FAIL	0x17
+
+#define VOYAGER_PSI_MASK		0x8001
+#	define PSI_MASK_MASK		0x10
+
+#define VOYAGER_PSI_AC_FAIL_REG		0x8004
+#define	AC_FAIL_STAT_CHANGE		0x80
+
+#define VOYAGER_PSI_GENERAL_REG		0x8007
+	/* read */
+#	define PSI_SWITCH_ON		0x01
+#	define PSI_SWITCH_ENABLED	0x02
+#	define PSI_ALARM_ENABLED	0x08
+#	define PSI_SECURE_ENABLED	0x10
+#	define PSI_COLD_RESET		0x20
+#	define PSI_COLD_START		0x80
+	/* write */
+#	define PSI_POWER_DOWN		0x10
+#	define PSI_SWITCH_DISABLE	0x01
+#	define PSI_SWITCH_ENABLE	0x11
+#	define PSI_CLEAR		0x12
+#	define PSI_ALARM_DISABLE	0x03
+#	define PSI_ALARM_ENABLE		0x13
+#	define PSI_CLEAR_COLD_RESET	0x05
+#	define PSI_SET_COLD_RESET	0x15
+#	define PSI_CLEAR_COLD_START	0x07
+#	define PSI_SET_COLD_START	0x17
+
+
+
+struct voyager_bios_info {
+	__u8	len;
+	__u8	major;
+	__u8	minor;
+	__u8	debug;
+	__u8	num_classes;
+	__u8	class_1;
+	__u8	class_2;
+};
+
+/* The following structures and definitions are for the Kernel/SUS
+ * interface these are needed to find out how SUS initialised any Quad
+ * boards in the system */
+
+#define	NUMBER_OF_MC_BUSSES	2
+#define SLOTS_PER_MC_BUS	8
+#define MAX_CPUS                16      /* 16 way CPU system */
+#define MAX_PROCESSOR_BOARDS	4	/* 4 processor slot system */
+#define MAX_CACHE_LEVELS	4	/* # of cache levels supported */
+#define MAX_SHARED_CPUS		4	/* # of CPUs that can share a LARC */
+#define NUMBER_OF_POS_REGS	8
+
+typedef struct {
+	__u8	MC_Slot;
+	__u8	POS_Values[NUMBER_OF_POS_REGS];
+} __attribute__((packed)) MC_SlotInformation_t;
+
+struct QuadDescription {
+	__u8  Type;	/* for type 0 (DYADIC or MONADIC) all fields
+			 * will be zero except for slot */
+	__u8 StructureVersion;
+	__u32 CPI_BaseAddress;
+	__u32  LARC_BankSize;
+	__u32 LocalMemoryStateBits;
+	__u8  Slot; /* Processor slots 1 - 4 */
+} __attribute__((packed));
+
+struct ProcBoardInfo {
+	__u8 Type;
+	__u8 StructureVersion;
+	__u8 NumberOfBoards;
+	struct QuadDescription QuadData[MAX_PROCESSOR_BOARDS];
+} __attribute__((packed));
+
+struct CacheDescription {
+	__u8 Level;
+	__u32 TotalSize;
+	__u16 LineSize;
+	__u8  Associativity;
+	__u8  CacheType;
+	__u8  WriteType;
+	__u8  Number_CPUs_SharedBy;
+	__u8  Shared_CPUs_Hardware_IDs[MAX_SHARED_CPUS];
+
+} __attribute__((packed));
+
+struct CPU_Description {
+	__u8 CPU_HardwareId;
+	char *FRU_String;
+	__u8 NumberOfCacheLevels;
+	struct CacheDescription CacheLevelData[MAX_CACHE_LEVELS];
+} __attribute__((packed));
+
+struct CPU_Info {
+	__u8 Type;
+	__u8 StructureVersion;
+	__u8 NumberOf_CPUs;
+	struct CPU_Description CPU_Data[MAX_CPUS];
+} __attribute__((packed));
+
+
+/*
+ * This structure will be used by SUS and the OS.
+ * The assumption about this structure is that no blank space is
+ * packed in it by our friend the compiler.
+ */
+typedef struct {
+	__u8	Mailbox_SUS;		/* Written to by SUS to give
+					   commands/response to the OS */
+	__u8	Mailbox_OS;		/* Written to by the OS to give
+					   commands/response to SUS */
+	__u8	SUS_MailboxVersion;	/* Tells the OS which iteration of the
+					   interface SUS supports */
+	__u8	OS_MailboxVersion;	/* Tells SUS which iteration of the
+					   interface the OS supports */
+	__u32	OS_Flags;		/* Flags set by the OS as info for
+					   SUS */
+	__u32	SUS_Flags;		/* Flags set by SUS as info
+					   for the OS */
+	__u32	WatchDogPeriod;		/* Watchdog period (in seconds) which
+					   the DP uses to see if the OS
+					   is dead */
+	__u32	WatchDogCount;		/* Updated by the OS on every tic. */
+	__u32	MemoryFor_SUS_ErrorLog;	/* Flat 32 bit address which tells SUS
+					   where to stuff the SUS error log
+					   on a dump */
+	MC_SlotInformation_t MC_SlotInfo[NUMBER_OF_MC_BUSSES*SLOTS_PER_MC_BUS];
+					/* Storage for MCA POS data */
+	/* All new SECOND_PASS_INTERFACE fields added from this point */
+	struct ProcBoardInfo    *BoardData;
+	struct CPU_Info         *CPU_Data;
+	/* All new fields must be added from this point */
+} Voyager_KernelSUS_Mbox_t;
+
+/* structure for finding the right memory address to send a QIC CPI to */
+struct voyager_qic_cpi {
+	/* Each cache line (32 bytes) can trigger a cpi.  The cpi
+	 * read/write may occur anywhere in the cache line---pick the
+	 * middle to be safe */
+	struct  {
+		__u32 pad1[3];
+		__u32 cpi;
+		__u32 pad2[4];
+	} qic_cpi[8];
+};
+
+struct voyager_status {
+	__u32	power_fail:1;
+	__u32	switch_off:1;
+	__u32	request_from_kernel:1;
+};
+
+struct voyager_psi_regs {
+	__u8 cat_id;
+	__u8 cat_dev;
+	__u8 cat_control;
+	__u8 subaddr;
+	__u8 dummy4;
+	__u8 checkbit;
+	__u8 subaddr_low;
+	__u8 subaddr_high;
+	__u8 intstatus;
+	__u8 stat1;
+	__u8 stat3;
+	__u8 fault;
+	__u8 tms;
+	__u8 gen;
+	__u8 sysconf;
+	__u8 dummy15;
+};
+
+struct voyager_psi_subregs {
+	__u8 supply;
+	__u8 mask;
+	__u8 present;
+	__u8 DCfail;
+	__u8 ACfail;
+	__u8 fail;
+	__u8 UPSfail;
+	__u8 genstatus;
+};
+
+struct voyager_psi {
+	struct voyager_psi_regs regs;
+	struct voyager_psi_subregs subregs;
+};
+
+struct voyager_SUS {
+#define	VOYAGER_DUMP_BUTTON_NMI		0x1
+#define VOYAGER_SUS_VALID		0x2
+#define VOYAGER_SYSINT_COMPLETE		0x3
+	__u8	SUS_mbox;
+#define VOYAGER_NO_COMMAND		0x0
+#define VOYAGER_IGNORE_DUMP		0x1
+#define VOYAGER_DO_DUMP			0x2
+#define VOYAGER_SYSINT_HANDSHAKE	0x3
+#define VOYAGER_DO_MEM_DUMP		0x4
+#define VOYAGER_SYSINT_WAS_RECOVERED	0x5
+	__u8	kernel_mbox;
+#define	VOYAGER_MAILBOX_VERSION		0x10
+	__u8	SUS_version;
+	__u8	kernel_version;
+#define VOYAGER_OS_HAS_SYSINT		0x1
+#define VOYAGER_OS_IN_PROGRESS		0x2
+#define VOYAGER_UPDATING_WDPERIOD	0x4
+	__u32	kernel_flags;
+#define VOYAGER_SUS_BOOTING		0x1
+#define VOYAGER_SUS_IN_PROGRESS		0x2
+	__u32	SUS_flags;
+	__u32	watchdog_period;
+	__u32	watchdog_count;
+	__u32	SUS_errorlog;
+	/* lots of system configuration stuff under here */
+};
+
+/* Variables exported by voyager_smp */
+extern __u32 voyager_extended_vic_processors;
+extern __u32 voyager_allowed_boot_processors;
+extern __u32 voyager_quad_processors;
+extern struct voyager_qic_cpi *voyager_quad_cpi_addr[NR_CPUS];
+extern struct voyager_SUS *voyager_SUS;
+
+/* variables exported always */
+extern struct task_struct *voyager_thread;
+extern int voyager_level;
+extern struct voyager_status voyager_status;
+
+/* functions exported by the voyager and voyager_smp modules */
+extern int voyager_cat_readb(__u8 module, __u8 asic, int reg);
+extern void voyager_cat_init(void);
+extern void voyager_detect(struct voyager_bios_info *);
+extern void voyager_trap_init(void);
+extern void voyager_setup_irqs(void);
+extern int voyager_memory_detect(int region, __u32 *addr, __u32 *length);
+extern void voyager_smp_intr_init(void);
+extern __u8 voyager_extended_cmos_read(__u16 cmos_address);
+extern void voyager_smp_dump(void);
+extern void voyager_timer_interrupt(void);
+extern void smp_local_timer_interrupt(void);
+extern void voyager_power_off(void);
+extern void smp_voyager_power_off(void *dummy);
+extern void voyager_restart(void);
+extern void voyager_cat_power_off(void);
+extern void voyager_cat_do_common_interrupt(void);
+extern void voyager_handle_nmi(void);
+/* Commands for the following are */
+#define	VOYAGER_PSI_READ	0
+#define VOYAGER_PSI_WRITE	1
+#define VOYAGER_PSI_SUBREAD	2
+#define VOYAGER_PSI_SUBWRITE	3
+extern void voyager_cat_psi(__u8, __u16, __u8 *);
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
new file mode 100644
index 000000000000..dcd4682413de
--- /dev/null
+++ b/arch/x86/include/asm/vsyscall.h
@@ -0,0 +1,44 @@
+#ifndef ASM_X86__VSYSCALL_H
+#define ASM_X86__VSYSCALL_H
+
+enum vsyscall_num {
+	__NR_vgettimeofday,
+	__NR_vtime,
+	__NR_vgetcpu,
+};
+
+#define VSYSCALL_START (-10UL << 20)
+#define VSYSCALL_SIZE 1024
+#define VSYSCALL_END (-2UL << 20)
+#define VSYSCALL_MAPPED_PAGES 1
+#define VSYSCALL_ADDR(vsyscall_nr) (VSYSCALL_START+VSYSCALL_SIZE*(vsyscall_nr))
+
+#ifdef __KERNEL__
+#include <linux/seqlock.h>
+
+#define __section_vgetcpu_mode __attribute__ ((unused, __section__ (".vgetcpu_mode"), aligned(16)))
+#define __section_jiffies __attribute__ ((unused, __section__ (".jiffies"), aligned(16)))
+
+/* Definitions for CONFIG_GENERIC_TIME definitions */
+#define __section_vsyscall_gtod_data __attribute__ \
+	((unused, __section__ (".vsyscall_gtod_data"),aligned(16)))
+#define __section_vsyscall_clock __attribute__ \
+	((unused, __section__ (".vsyscall_clock"),aligned(16)))
+#define __vsyscall_fn \
+	__attribute__ ((unused, __section__(".vsyscall_fn"))) notrace
+
+#define VGETCPU_RDTSCP	1
+#define VGETCPU_LSL	2
+
+extern int __vgetcpu_mode;
+extern volatile unsigned long __jiffies;
+
+/* kernel space (writeable) */
+extern int vgetcpu_mode;
+extern struct timezone sys_tz;
+
+extern void map_vsyscall(void);
+
+#endif /* __KERNEL__ */
+
+#endif /* ASM_X86__VSYSCALL_H */
diff --git a/arch/x86/include/asm/xcr.h b/arch/x86/include/asm/xcr.h
new file mode 100644
index 000000000000..f2cba4e79a23
--- /dev/null
+++ b/arch/x86/include/asm/xcr.h
@@ -0,0 +1,49 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright 2008 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2 or (at your
+ *   option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * asm-x86/xcr.h
+ *
+ * Definitions for the eXtended Control Register instructions
+ */
+
+#ifndef _ASM_X86_XCR_H
+#define _ASM_X86_XCR_H
+
+#define XCR_XFEATURE_ENABLED_MASK	0x00000000
+
+#ifdef __KERNEL__
+# ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+static inline u64 xgetbv(u32 index)
+{
+	u32 eax, edx;
+
+	asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
+		     : "=a" (eax), "=d" (edx)
+		     : "c" (index));
+	return eax + ((u64)edx << 32);
+}
+
+static inline void xsetbv(u32 index, u64 value)
+{
+	u32 eax = value;
+	u32 edx = value >> 32;
+
+	asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
+		     : : "a" (eax), "d" (edx), "c" (index));
+}
+
+# endif /* __ASSEMBLY__ */
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_XCR_H */
diff --git a/arch/x86/include/asm/xen/events.h b/arch/x86/include/asm/xen/events.h
new file mode 100644
index 000000000000..8151f5b8b6cb
--- /dev/null
+++ b/arch/x86/include/asm/xen/events.h
@@ -0,0 +1,24 @@
+#ifndef ASM_X86__XEN__EVENTS_H
+#define ASM_X86__XEN__EVENTS_H
+
+enum ipi_vector {
+	XEN_RESCHEDULE_VECTOR,
+	XEN_CALL_FUNCTION_VECTOR,
+	XEN_CALL_FUNCTION_SINGLE_VECTOR,
+	XEN_SPIN_UNLOCK_VECTOR,
+
+	XEN_NR_IPIS,
+};
+
+static inline int xen_irqs_disabled(struct pt_regs *regs)
+{
+	return raw_irqs_disabled_flags(regs->flags);
+}
+
+static inline void xen_do_IRQ(int irq, struct pt_regs *regs)
+{
+	regs->orig_ax = ~irq;
+	do_IRQ(regs);
+}
+
+#endif /* ASM_X86__XEN__EVENTS_H */
diff --git a/arch/x86/include/asm/xen/grant_table.h b/arch/x86/include/asm/xen/grant_table.h
new file mode 100644
index 000000000000..c4baab4d2b68
--- /dev/null
+++ b/arch/x86/include/asm/xen/grant_table.h
@@ -0,0 +1,7 @@
+#ifndef ASM_X86__XEN__GRANT_TABLE_H
+#define ASM_X86__XEN__GRANT_TABLE_H
+
+#define xen_alloc_vm_area(size)	alloc_vm_area(size)
+#define xen_free_vm_area(area)	free_vm_area(area)
+
+#endif /* ASM_X86__XEN__GRANT_TABLE_H */
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
new file mode 100644
index 000000000000..44f4259bee3f
--- /dev/null
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -0,0 +1,527 @@
+/******************************************************************************
+ * hypercall.h
+ *
+ * Linux-specific hypervisor handling.
+ *
+ * Copyright (c) 2002-2004, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef ASM_X86__XEN__HYPERCALL_H
+#define ASM_X86__XEN__HYPERCALL_H
+
+#include <linux/errno.h>
+#include <linux/string.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/sched.h>
+#include <xen/interface/physdev.h>
+
+/*
+ * The hypercall asms have to meet several constraints:
+ * - Work on 32- and 64-bit.
+ *    The two architectures put their arguments in different sets of
+ *    registers.
+ *
+ * - Work around asm syntax quirks
+ *    It isn't possible to specify one of the rNN registers in a
+ *    constraint, so we use explicit register variables to get the
+ *    args into the right place.
+ *
+ * - Mark all registers as potentially clobbered
+ *    Even unused parameters can be clobbered by the hypervisor, so we
+ *    need to make sure gcc knows it.
+ *
+ * - Avoid compiler bugs.
+ *    This is the tricky part.  Because x86_32 has such a constrained
+ *    register set, gcc versions below 4.3 have trouble generating
+ *    code when all the arg registers and memory are trashed by the
+ *    asm.  There are syntactically simpler ways of achieving the
+ *    semantics below, but they cause the compiler to crash.
+ *
+ *    The only combination I found which works is:
+ *     - assign the __argX variables first
+ *     - list all actually used parameters as "+r" (__argX)
+ *     - clobber the rest
+ *
+ * The result certainly isn't pretty, and it really shows up cpp's
+ * weakness as as macro language.  Sorry.  (But let's just give thanks
+ * there aren't more than 5 arguments...)
+ */
+
+extern struct { char _entry[32]; } hypercall_page[];
+
+#define __HYPERCALL		"call hypercall_page+%c[offset]"
+#define __HYPERCALL_ENTRY(x)						\
+	[offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0]))
+
+#ifdef CONFIG_X86_32
+#define __HYPERCALL_RETREG	"eax"
+#define __HYPERCALL_ARG1REG	"ebx"
+#define __HYPERCALL_ARG2REG	"ecx"
+#define __HYPERCALL_ARG3REG	"edx"
+#define __HYPERCALL_ARG4REG	"esi"
+#define __HYPERCALL_ARG5REG	"edi"
+#else
+#define __HYPERCALL_RETREG	"rax"
+#define __HYPERCALL_ARG1REG	"rdi"
+#define __HYPERCALL_ARG2REG	"rsi"
+#define __HYPERCALL_ARG3REG	"rdx"
+#define __HYPERCALL_ARG4REG	"r10"
+#define __HYPERCALL_ARG5REG	"r8"
+#endif
+
+#define __HYPERCALL_DECLS						\
+	register unsigned long __res  asm(__HYPERCALL_RETREG);		\
+	register unsigned long __arg1 asm(__HYPERCALL_ARG1REG) = __arg1; \
+	register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \
+	register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \
+	register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \
+	register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5;
+
+#define __HYPERCALL_0PARAM	"=r" (__res)
+#define __HYPERCALL_1PARAM	__HYPERCALL_0PARAM, "+r" (__arg1)
+#define __HYPERCALL_2PARAM	__HYPERCALL_1PARAM, "+r" (__arg2)
+#define __HYPERCALL_3PARAM	__HYPERCALL_2PARAM, "+r" (__arg3)
+#define __HYPERCALL_4PARAM	__HYPERCALL_3PARAM, "+r" (__arg4)
+#define __HYPERCALL_5PARAM	__HYPERCALL_4PARAM, "+r" (__arg5)
+
+#define __HYPERCALL_0ARG()
+#define __HYPERCALL_1ARG(a1)						\
+	__HYPERCALL_0ARG()		__arg1 = (unsigned long)(a1);
+#define __HYPERCALL_2ARG(a1,a2)						\
+	__HYPERCALL_1ARG(a1)		__arg2 = (unsigned long)(a2);
+#define __HYPERCALL_3ARG(a1,a2,a3)					\
+	__HYPERCALL_2ARG(a1,a2)		__arg3 = (unsigned long)(a3);
+#define __HYPERCALL_4ARG(a1,a2,a3,a4)					\
+	__HYPERCALL_3ARG(a1,a2,a3)	__arg4 = (unsigned long)(a4);
+#define __HYPERCALL_5ARG(a1,a2,a3,a4,a5)				\
+	__HYPERCALL_4ARG(a1,a2,a3,a4)	__arg5 = (unsigned long)(a5);
+
+#define __HYPERCALL_CLOBBER5	"memory"
+#define __HYPERCALL_CLOBBER4	__HYPERCALL_CLOBBER5, __HYPERCALL_ARG5REG
+#define __HYPERCALL_CLOBBER3	__HYPERCALL_CLOBBER4, __HYPERCALL_ARG4REG
+#define __HYPERCALL_CLOBBER2	__HYPERCALL_CLOBBER3, __HYPERCALL_ARG3REG
+#define __HYPERCALL_CLOBBER1	__HYPERCALL_CLOBBER2, __HYPERCALL_ARG2REG
+#define __HYPERCALL_CLOBBER0	__HYPERCALL_CLOBBER1, __HYPERCALL_ARG1REG
+
+#define _hypercall0(type, name)						\
+({									\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_0ARG();						\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_0PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER0);				\
+	(type)__res;							\
+})
+
+#define _hypercall1(type, name, a1)					\
+({									\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_1ARG(a1);						\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_1PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER1);				\
+	(type)__res;							\
+})
+
+#define _hypercall2(type, name, a1, a2)					\
+({									\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_2ARG(a1, a2);					\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_2PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER2);				\
+	(type)__res;							\
+})
+
+#define _hypercall3(type, name, a1, a2, a3)				\
+({									\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_3ARG(a1, a2, a3);					\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_3PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER3);				\
+	(type)__res;							\
+})
+
+#define _hypercall4(type, name, a1, a2, a3, a4)				\
+({									\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_4ARG(a1, a2, a3, a4);				\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_4PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER4);				\
+	(type)__res;							\
+})
+
+#define _hypercall5(type, name, a1, a2, a3, a4, a5)			\
+({									\
+	__HYPERCALL_DECLS;						\
+	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);				\
+	asm volatile (__HYPERCALL					\
+		      : __HYPERCALL_5PARAM				\
+		      : __HYPERCALL_ENTRY(name)				\
+		      : __HYPERCALL_CLOBBER5);				\
+	(type)__res;							\
+})
+
+static inline int
+HYPERVISOR_set_trap_table(struct trap_info *table)
+{
+	return _hypercall1(int, set_trap_table, table);
+}
+
+static inline int
+HYPERVISOR_mmu_update(struct mmu_update *req, int count,
+		      int *success_count, domid_t domid)
+{
+	return _hypercall4(int, mmu_update, req, count, success_count, domid);
+}
+
+static inline int
+HYPERVISOR_mmuext_op(struct mmuext_op *op, int count,
+		     int *success_count, domid_t domid)
+{
+	return _hypercall4(int, mmuext_op, op, count, success_count, domid);
+}
+
+static inline int
+HYPERVISOR_set_gdt(unsigned long *frame_list, int entries)
+{
+	return _hypercall2(int, set_gdt, frame_list, entries);
+}
+
+static inline int
+HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp)
+{
+	return _hypercall2(int, stack_switch, ss, esp);
+}
+
+#ifdef CONFIG_X86_32
+static inline int
+HYPERVISOR_set_callbacks(unsigned long event_selector,
+			 unsigned long event_address,
+			 unsigned long failsafe_selector,
+			 unsigned long failsafe_address)
+{
+	return _hypercall4(int, set_callbacks,
+			   event_selector, event_address,
+			   failsafe_selector, failsafe_address);
+}
+#else  /* CONFIG_X86_64 */
+static inline int
+HYPERVISOR_set_callbacks(unsigned long event_address,
+			unsigned long failsafe_address,
+			unsigned long syscall_address)
+{
+	return _hypercall3(int, set_callbacks,
+			   event_address, failsafe_address,
+			   syscall_address);
+}
+#endif  /* CONFIG_X86_{32,64} */
+
+static inline int
+HYPERVISOR_callback_op(int cmd, void *arg)
+{
+	return _hypercall2(int, callback_op, cmd, arg);
+}
+
+static inline int
+HYPERVISOR_fpu_taskswitch(int set)
+{
+	return _hypercall1(int, fpu_taskswitch, set);
+}
+
+static inline int
+HYPERVISOR_sched_op(int cmd, void *arg)
+{
+	return _hypercall2(int, sched_op_new, cmd, arg);
+}
+
+static inline long
+HYPERVISOR_set_timer_op(u64 timeout)
+{
+	unsigned long timeout_hi = (unsigned long)(timeout>>32);
+	unsigned long timeout_lo = (unsigned long)timeout;
+	return _hypercall2(long, set_timer_op, timeout_lo, timeout_hi);
+}
+
+static inline int
+HYPERVISOR_set_debugreg(int reg, unsigned long value)
+{
+	return _hypercall2(int, set_debugreg, reg, value);
+}
+
+static inline unsigned long
+HYPERVISOR_get_debugreg(int reg)
+{
+	return _hypercall1(unsigned long, get_debugreg, reg);
+}
+
+static inline int
+HYPERVISOR_update_descriptor(u64 ma, u64 desc)
+{
+	return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32);
+}
+
+static inline int
+HYPERVISOR_memory_op(unsigned int cmd, void *arg)
+{
+	return _hypercall2(int, memory_op, cmd, arg);
+}
+
+static inline int
+HYPERVISOR_multicall(void *call_list, int nr_calls)
+{
+	return _hypercall2(int, multicall, call_list, nr_calls);
+}
+
+static inline int
+HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
+			     unsigned long flags)
+{
+	if (sizeof(new_val) == sizeof(long))
+		return _hypercall3(int, update_va_mapping, va,
+				   new_val.pte, flags);
+	else
+		return _hypercall4(int, update_va_mapping, va,
+				   new_val.pte, new_val.pte >> 32, flags);
+}
+
+static inline int
+HYPERVISOR_event_channel_op(int cmd, void *arg)
+{
+	int rc = _hypercall2(int, event_channel_op, cmd, arg);
+	if (unlikely(rc == -ENOSYS)) {
+		struct evtchn_op op;
+		op.cmd = cmd;
+		memcpy(&op.u, arg, sizeof(op.u));
+		rc = _hypercall1(int, event_channel_op_compat, &op);
+		memcpy(arg, &op.u, sizeof(op.u));
+	}
+	return rc;
+}
+
+static inline int
+HYPERVISOR_xen_version(int cmd, void *arg)
+{
+	return _hypercall2(int, xen_version, cmd, arg);
+}
+
+static inline int
+HYPERVISOR_console_io(int cmd, int count, char *str)
+{
+	return _hypercall3(int, console_io, cmd, count, str);
+}
+
+static inline int
+HYPERVISOR_physdev_op(int cmd, void *arg)
+{
+	int rc = _hypercall2(int, physdev_op, cmd, arg);
+	if (unlikely(rc == -ENOSYS)) {
+		struct physdev_op op;
+		op.cmd = cmd;
+		memcpy(&op.u, arg, sizeof(op.u));
+		rc = _hypercall1(int, physdev_op_compat, &op);
+		memcpy(arg, &op.u, sizeof(op.u));
+	}
+	return rc;
+}
+
+static inline int
+HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count)
+{
+	return _hypercall3(int, grant_table_op, cmd, uop, count);
+}
+
+static inline int
+HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, pte_t new_val,
+					 unsigned long flags, domid_t domid)
+{
+	if (sizeof(new_val) == sizeof(long))
+		return _hypercall4(int, update_va_mapping_otherdomain, va,
+				   new_val.pte, flags, domid);
+	else
+		return _hypercall5(int, update_va_mapping_otherdomain, va,
+				   new_val.pte, new_val.pte >> 32,
+				   flags, domid);
+}
+
+static inline int
+HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type)
+{
+	return _hypercall2(int, vm_assist, cmd, type);
+}
+
+static inline int
+HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args)
+{
+	return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args);
+}
+
+#ifdef CONFIG_X86_64
+static inline int
+HYPERVISOR_set_segment_base(int reg, unsigned long value)
+{
+	return _hypercall2(int, set_segment_base, reg, value);
+}
+#endif
+
+static inline int
+HYPERVISOR_suspend(unsigned long srec)
+{
+	return _hypercall3(int, sched_op, SCHEDOP_shutdown,
+			   SHUTDOWN_suspend, srec);
+}
+
+static inline int
+HYPERVISOR_nmi_op(unsigned long op, unsigned long arg)
+{
+	return _hypercall2(int, nmi_op, op, arg);
+}
+
+static inline void
+MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
+{
+	mcl->op = __HYPERVISOR_fpu_taskswitch;
+	mcl->args[0] = set;
+}
+
+static inline void
+MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
+			pte_t new_val, unsigned long flags)
+{
+	mcl->op = __HYPERVISOR_update_va_mapping;
+	mcl->args[0] = va;
+	if (sizeof(new_val) == sizeof(long)) {
+		mcl->args[1] = new_val.pte;
+		mcl->args[2] = flags;
+	} else {
+		mcl->args[1] = new_val.pte;
+		mcl->args[2] = new_val.pte >> 32;
+		mcl->args[3] = flags;
+	}
+}
+
+static inline void
+MULTI_grant_table_op(struct multicall_entry *mcl, unsigned int cmd,
+		     void *uop, unsigned int count)
+{
+	mcl->op = __HYPERVISOR_grant_table_op;
+	mcl->args[0] = cmd;
+	mcl->args[1] = (unsigned long)uop;
+	mcl->args[2] = count;
+}
+
+static inline void
+MULTI_update_va_mapping_otherdomain(struct multicall_entry *mcl, unsigned long va,
+				    pte_t new_val, unsigned long flags,
+				    domid_t domid)
+{
+	mcl->op = __HYPERVISOR_update_va_mapping_otherdomain;
+	mcl->args[0] = va;
+	if (sizeof(new_val) == sizeof(long)) {
+		mcl->args[1] = new_val.pte;
+		mcl->args[2] = flags;
+		mcl->args[3] = domid;
+	} else {
+		mcl->args[1] = new_val.pte;
+		mcl->args[2] = new_val.pte >> 32;
+		mcl->args[3] = flags;
+		mcl->args[4] = domid;
+	}
+}
+
+static inline void
+MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
+			struct desc_struct desc)
+{
+	mcl->op = __HYPERVISOR_update_descriptor;
+	if (sizeof(maddr) == sizeof(long)) {
+		mcl->args[0] = maddr;
+		mcl->args[1] = *(unsigned long *)&desc;
+	} else {
+		mcl->args[0] = maddr;
+		mcl->args[1] = maddr >> 32;
+		mcl->args[2] = desc.a;
+		mcl->args[3] = desc.b;
+	}
+}
+
+static inline void
+MULTI_memory_op(struct multicall_entry *mcl, unsigned int cmd, void *arg)
+{
+	mcl->op = __HYPERVISOR_memory_op;
+	mcl->args[0] = cmd;
+	mcl->args[1] = (unsigned long)arg;
+}
+
+static inline void
+MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
+		 int count, int *success_count, domid_t domid)
+{
+	mcl->op = __HYPERVISOR_mmu_update;
+	mcl->args[0] = (unsigned long)req;
+	mcl->args[1] = count;
+	mcl->args[2] = (unsigned long)success_count;
+	mcl->args[3] = domid;
+}
+
+static inline void
+MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count,
+		int *success_count, domid_t domid)
+{
+	mcl->op = __HYPERVISOR_mmuext_op;
+	mcl->args[0] = (unsigned long)op;
+	mcl->args[1] = count;
+	mcl->args[2] = (unsigned long)success_count;
+	mcl->args[3] = domid;
+}
+
+static inline void
+MULTI_set_gdt(struct multicall_entry *mcl, unsigned long *frames, int entries)
+{
+	mcl->op = __HYPERVISOR_set_gdt;
+	mcl->args[0] = (unsigned long)frames;
+	mcl->args[1] = entries;
+}
+
+static inline void
+MULTI_stack_switch(struct multicall_entry *mcl,
+		   unsigned long ss, unsigned long esp)
+{
+	mcl->op = __HYPERVISOR_stack_switch;
+	mcl->args[0] = ss;
+	mcl->args[1] = esp;
+}
+
+#endif /* ASM_X86__XEN__HYPERCALL_H */
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
new file mode 100644
index 000000000000..445a24759560
--- /dev/null
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -0,0 +1,82 @@
+/******************************************************************************
+ * hypervisor.h
+ *
+ * Linux-specific hypervisor handling.
+ *
+ * Copyright (c) 2002-2004, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef ASM_X86__XEN__HYPERVISOR_H
+#define ASM_X86__XEN__HYPERVISOR_H
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+
+#include <xen/interface/xen.h>
+#include <xen/interface/version.h>
+
+#include <asm/ptrace.h>
+#include <asm/page.h>
+#include <asm/desc.h>
+#if defined(__i386__)
+#  ifdef CONFIG_X86_PAE
+#   include <asm-generic/pgtable-nopud.h>
+#  else
+#   include <asm-generic/pgtable-nopmd.h>
+#  endif
+#endif
+#include <asm/xen/hypercall.h>
+
+/* arch/i386/kernel/setup.c */
+extern struct shared_info *HYPERVISOR_shared_info;
+extern struct start_info *xen_start_info;
+
+/* arch/i386/mach-xen/evtchn.c */
+/* Force a proper event-channel callback from Xen. */
+extern void force_evtchn_callback(void);
+
+/* Turn jiffies into Xen system time. */
+u64 jiffies_to_st(unsigned long jiffies);
+
+
+#define MULTI_UVMFLAGS_INDEX 3
+#define MULTI_UVMDOMID_INDEX 4
+
+enum xen_domain_type {
+	XEN_NATIVE,
+	XEN_PV_DOMAIN,
+	XEN_HVM_DOMAIN,
+};
+
+extern enum xen_domain_type xen_domain_type;
+
+#define xen_domain()		(xen_domain_type != XEN_NATIVE)
+#define xen_pv_domain()		(xen_domain_type == XEN_PV_DOMAIN)
+#define xen_initial_domain()	(xen_pv_domain() && xen_start_info->flags & SIF_INITDOMAIN)
+#define xen_hvm_domain()	(xen_domain_type == XEN_HVM_DOMAIN)
+
+#endif /* ASM_X86__XEN__HYPERVISOR_H */
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
new file mode 100644
index 000000000000..d077bba96da9
--- /dev/null
+++ b/arch/x86/include/asm/xen/interface.h
@@ -0,0 +1,175 @@
+/******************************************************************************
+ * arch-x86_32.h
+ *
+ * Guest OS interface to x86 Xen.
+ *
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#ifndef ASM_X86__XEN__INTERFACE_H
+#define ASM_X86__XEN__INTERFACE_H
+
+#ifdef __XEN__
+#define __DEFINE_GUEST_HANDLE(name, type) \
+    typedef struct { type *p; } __guest_handle_ ## name
+#else
+#define __DEFINE_GUEST_HANDLE(name, type) \
+    typedef type * __guest_handle_ ## name
+#endif
+
+#define DEFINE_GUEST_HANDLE_STRUCT(name) \
+	__DEFINE_GUEST_HANDLE(name, struct name)
+#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name)
+#define GUEST_HANDLE(name)        __guest_handle_ ## name
+
+#ifdef __XEN__
+#if defined(__i386__)
+#define set_xen_guest_handle(hnd, val)			\
+	do {						\
+		if (sizeof(hnd) == 8)			\
+			*(uint64_t *)&(hnd) = 0;	\
+		(hnd).p = val;				\
+	} while (0)
+#elif defined(__x86_64__)
+#define set_xen_guest_handle(hnd, val)	do { (hnd).p = val; } while (0)
+#endif
+#else
+#if defined(__i386__)
+#define set_xen_guest_handle(hnd, val)			\
+	do {						\
+		if (sizeof(hnd) == 8)			\
+			*(uint64_t *)&(hnd) = 0;	\
+		(hnd) = val;				\
+	} while (0)
+#elif defined(__x86_64__)
+#define set_xen_guest_handle(hnd, val)	do { (hnd) = val; } while (0)
+#endif
+#endif
+
+#ifndef __ASSEMBLY__
+/* Guest handles for primitive C types. */
+__DEFINE_GUEST_HANDLE(uchar, unsigned char);
+__DEFINE_GUEST_HANDLE(uint,  unsigned int);
+__DEFINE_GUEST_HANDLE(ulong, unsigned long);
+DEFINE_GUEST_HANDLE(char);
+DEFINE_GUEST_HANDLE(int);
+DEFINE_GUEST_HANDLE(long);
+DEFINE_GUEST_HANDLE(void);
+#endif
+
+#ifndef HYPERVISOR_VIRT_START
+#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
+#endif
+
+#ifndef machine_to_phys_mapping
+#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
+#endif
+
+/* Maximum number of virtual CPUs in multi-processor guests. */
+#define MAX_VIRT_CPUS 32
+
+/*
+ * SEGMENT DESCRIPTOR TABLES
+ */
+/*
+ * A number of GDT entries are reserved by Xen. These are not situated at the
+ * start of the GDT because some stupid OSes export hard-coded selector values
+ * in their ABI. These hard-coded values are always near the start of the GDT,
+ * so Xen places itself out of the way, at the far end of the GDT.
+ */
+#define FIRST_RESERVED_GDT_PAGE  14
+#define FIRST_RESERVED_GDT_BYTE  (FIRST_RESERVED_GDT_PAGE * 4096)
+#define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8)
+
+/*
+ * Send an array of these to HYPERVISOR_set_trap_table()
+ * The privilege level specifies which modes may enter a trap via a software
+ * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
+ * privilege levels as follows:
+ *  Level == 0: Noone may enter
+ *  Level == 1: Kernel may enter
+ *  Level == 2: Kernel may enter
+ *  Level == 3: Everyone may enter
+ */
+#define TI_GET_DPL(_ti)		((_ti)->flags & 3)
+#define TI_GET_IF(_ti)		((_ti)->flags & 4)
+#define TI_SET_DPL(_ti, _dpl)	((_ti)->flags |= (_dpl))
+#define TI_SET_IF(_ti, _if)	((_ti)->flags |= ((!!(_if))<<2))
+
+#ifndef __ASSEMBLY__
+struct trap_info {
+    uint8_t       vector;  /* exception vector                              */
+    uint8_t       flags;   /* 0-3: privilege level; 4: clear event enable?  */
+    uint16_t      cs;      /* code selector                                 */
+    unsigned long address; /* code offset                                   */
+};
+DEFINE_GUEST_HANDLE_STRUCT(trap_info);
+
+struct arch_shared_info {
+    unsigned long max_pfn;                  /* max pfn that appears in table */
+    /* Frame containing list of mfns containing list of mfns containing p2m. */
+    unsigned long pfn_to_mfn_frame_list_list;
+    unsigned long nmi_reason;
+};
+#endif	/* !__ASSEMBLY__ */
+
+#ifdef CONFIG_X86_32
+#include "interface_32.h"
+#else
+#include "interface_64.h"
+#endif
+
+#ifndef __ASSEMBLY__
+/*
+ * The following is all CPU context. Note that the fpu_ctxt block is filled
+ * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
+ */
+struct vcpu_guest_context {
+    /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */
+    struct { char x[512]; } fpu_ctxt;       /* User-level FPU registers     */
+#define VGCF_I387_VALID (1<<0)
+#define VGCF_HVM_GUEST  (1<<1)
+#define VGCF_IN_KERNEL  (1<<2)
+    unsigned long flags;                    /* VGCF_* flags                 */
+    struct cpu_user_regs user_regs;         /* User-level CPU registers     */
+    struct trap_info trap_ctxt[256];        /* Virtual IDT                  */
+    unsigned long ldt_base, ldt_ents;       /* LDT (linear address, # ents) */
+    unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */
+    unsigned long kernel_ss, kernel_sp;     /* Virtual TSS (only SS1/SP1)   */
+    /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */
+    unsigned long ctrlreg[8];               /* CR0-CR7 (control registers)  */
+    unsigned long debugreg[8];              /* DB0-DB7 (debug registers)    */
+#ifdef __i386__
+    unsigned long event_callback_cs;        /* CS:EIP of event callback     */
+    unsigned long event_callback_eip;
+    unsigned long failsafe_callback_cs;     /* CS:EIP of failsafe callback  */
+    unsigned long failsafe_callback_eip;
+#else
+    unsigned long event_callback_eip;
+    unsigned long failsafe_callback_eip;
+    unsigned long syscall_callback_eip;
+#endif
+    unsigned long vm_assist;                /* VMASST_TYPE_* bitmap */
+#ifdef __x86_64__
+    /* Segment base addresses. */
+    uint64_t      fs_base;
+    uint64_t      gs_base_kernel;
+    uint64_t      gs_base_user;
+#endif
+};
+DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context);
+#endif	/* !__ASSEMBLY__ */
+
+/*
+ * Prefix forces emulation of some non-trapping instructions.
+ * Currently only CPUID.
+ */
+#ifdef __ASSEMBLY__
+#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ;
+#define XEN_CPUID          XEN_EMULATE_PREFIX cpuid
+#else
+#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; "
+#define XEN_CPUID          XEN_EMULATE_PREFIX "cpuid"
+#endif
+
+#endif /* ASM_X86__XEN__INTERFACE_H */
diff --git a/arch/x86/include/asm/xen/interface_32.h b/arch/x86/include/asm/xen/interface_32.h
new file mode 100644
index 000000000000..08167e19fc66
--- /dev/null
+++ b/arch/x86/include/asm/xen/interface_32.h
@@ -0,0 +1,97 @@
+/******************************************************************************
+ * arch-x86_32.h
+ *
+ * Guest OS interface to x86 32-bit Xen.
+ *
+ * Copyright (c) 2004, K A Fraser
+ */
+
+#ifndef ASM_X86__XEN__INTERFACE_32_H
+#define ASM_X86__XEN__INTERFACE_32_H
+
+
+/*
+ * These flat segments are in the Xen-private section of every GDT. Since these
+ * are also present in the initial GDT, many OSes will be able to avoid
+ * installing their own GDT.
+ */
+#define FLAT_RING1_CS 0xe019    /* GDT index 259 */
+#define FLAT_RING1_DS 0xe021    /* GDT index 260 */
+#define FLAT_RING1_SS 0xe021    /* GDT index 260 */
+#define FLAT_RING3_CS 0xe02b    /* GDT index 261 */
+#define FLAT_RING3_DS 0xe033    /* GDT index 262 */
+#define FLAT_RING3_SS 0xe033    /* GDT index 262 */
+
+#define FLAT_KERNEL_CS FLAT_RING1_CS
+#define FLAT_KERNEL_DS FLAT_RING1_DS
+#define FLAT_KERNEL_SS FLAT_RING1_SS
+#define FLAT_USER_CS    FLAT_RING3_CS
+#define FLAT_USER_DS    FLAT_RING3_DS
+#define FLAT_USER_SS    FLAT_RING3_SS
+
+/* And the trap vector is... */
+#define TRAP_INSTR "int $0x82"
+
+/*
+ * Virtual addresses beyond this are not modifiable by guest OSes. The
+ * machine->physical mapping table starts at this address, read-only.
+ */
+#define __HYPERVISOR_VIRT_START 0xF5800000
+
+#ifndef __ASSEMBLY__
+
+struct cpu_user_regs {
+    uint32_t ebx;
+    uint32_t ecx;
+    uint32_t edx;
+    uint32_t esi;
+    uint32_t edi;
+    uint32_t ebp;
+    uint32_t eax;
+    uint16_t error_code;    /* private */
+    uint16_t entry_vector;  /* private */
+    uint32_t eip;
+    uint16_t cs;
+    uint8_t  saved_upcall_mask;
+    uint8_t  _pad0;
+    uint32_t eflags;        /* eflags.IF == !saved_upcall_mask */
+    uint32_t esp;
+    uint16_t ss, _pad1;
+    uint16_t es, _pad2;
+    uint16_t ds, _pad3;
+    uint16_t fs, _pad4;
+    uint16_t gs, _pad5;
+};
+DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
+
+typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */
+
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */
+};
+
+struct xen_callback {
+	unsigned long cs;
+	unsigned long eip;
+};
+typedef struct xen_callback xen_callback_t;
+
+#define XEN_CALLBACK(__cs, __eip)				\
+	((struct xen_callback){ .cs = (__cs), .eip = (unsigned long)(__eip) })
+#endif /* !__ASSEMBLY__ */
+
+
+/*
+ * Page-directory addresses above 4GB do not fit into architectural %cr3.
+ * When accessing %cr3, or equivalent field in vcpu_guest_context, guests
+ * must use the following accessor macros to pack/unpack valid MFNs.
+ *
+ * Note that Xen is using the fact that the pagetable base is always
+ * page-aligned, and putting the 12 MSB of the address into the 12 LSB
+ * of cr3.
+ */
+#define xen_pfn_to_cr3(pfn) (((unsigned)(pfn) << 12) | ((unsigned)(pfn) >> 20))
+#define xen_cr3_to_pfn(cr3) (((unsigned)(cr3) >> 12) | ((unsigned)(cr3) << 20))
+
+#endif /* ASM_X86__XEN__INTERFACE_32_H */
diff --git a/arch/x86/include/asm/xen/interface_64.h b/arch/x86/include/asm/xen/interface_64.h
new file mode 100644
index 000000000000..046c0f1e01d4
--- /dev/null
+++ b/arch/x86/include/asm/xen/interface_64.h
@@ -0,0 +1,159 @@
+#ifndef ASM_X86__XEN__INTERFACE_64_H
+#define ASM_X86__XEN__INTERFACE_64_H
+
+/*
+ * 64-bit segment selectors
+ * These flat segments are in the Xen-private section of every GDT. Since these
+ * are also present in the initial GDT, many OSes will be able to avoid
+ * installing their own GDT.
+ */
+
+#define FLAT_RING3_CS32 0xe023  /* GDT index 260 */
+#define FLAT_RING3_CS64 0xe033  /* GDT index 261 */
+#define FLAT_RING3_DS32 0xe02b  /* GDT index 262 */
+#define FLAT_RING3_DS64 0x0000  /* NULL selector */
+#define FLAT_RING3_SS32 0xe02b  /* GDT index 262 */
+#define FLAT_RING3_SS64 0xe02b  /* GDT index 262 */
+
+#define FLAT_KERNEL_DS64 FLAT_RING3_DS64
+#define FLAT_KERNEL_DS32 FLAT_RING3_DS32
+#define FLAT_KERNEL_DS   FLAT_KERNEL_DS64
+#define FLAT_KERNEL_CS64 FLAT_RING3_CS64
+#define FLAT_KERNEL_CS32 FLAT_RING3_CS32
+#define FLAT_KERNEL_CS   FLAT_KERNEL_CS64
+#define FLAT_KERNEL_SS64 FLAT_RING3_SS64
+#define FLAT_KERNEL_SS32 FLAT_RING3_SS32
+#define FLAT_KERNEL_SS   FLAT_KERNEL_SS64
+
+#define FLAT_USER_DS64 FLAT_RING3_DS64
+#define FLAT_USER_DS32 FLAT_RING3_DS32
+#define FLAT_USER_DS   FLAT_USER_DS64
+#define FLAT_USER_CS64 FLAT_RING3_CS64
+#define FLAT_USER_CS32 FLAT_RING3_CS32
+#define FLAT_USER_CS   FLAT_USER_CS64
+#define FLAT_USER_SS64 FLAT_RING3_SS64
+#define FLAT_USER_SS32 FLAT_RING3_SS32
+#define FLAT_USER_SS   FLAT_USER_SS64
+
+#define __HYPERVISOR_VIRT_START 0xFFFF800000000000
+#define __HYPERVISOR_VIRT_END   0xFFFF880000000000
+#define __MACH2PHYS_VIRT_START  0xFFFF800000000000
+#define __MACH2PHYS_VIRT_END    0xFFFF804000000000
+
+#ifndef HYPERVISOR_VIRT_START
+#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
+#define HYPERVISOR_VIRT_END   mk_unsigned_long(__HYPERVISOR_VIRT_END)
+#endif
+
+#define MACH2PHYS_VIRT_START  mk_unsigned_long(__MACH2PHYS_VIRT_START)
+#define MACH2PHYS_VIRT_END    mk_unsigned_long(__MACH2PHYS_VIRT_END)
+#define MACH2PHYS_NR_ENTRIES  ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3)
+#ifndef machine_to_phys_mapping
+#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
+#endif
+
+/*
+ * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base)
+ *  @which == SEGBASE_*  ;  @base == 64-bit base address
+ * Returns 0 on success.
+ */
+#define SEGBASE_FS          0
+#define SEGBASE_GS_USER     1
+#define SEGBASE_GS_KERNEL   2
+#define SEGBASE_GS_USER_SEL 3 /* Set user %gs specified in base[15:0] */
+
+/*
+ * int HYPERVISOR_iret(void)
+ * All arguments are on the kernel stack, in the following format.
+ * Never returns if successful. Current kernel context is lost.
+ * The saved CS is mapped as follows:
+ *   RING0 -> RING3 kernel mode.
+ *   RING1 -> RING3 kernel mode.
+ *   RING2 -> RING3 kernel mode.
+ *   RING3 -> RING3 user mode.
+ * However RING0 indicates that the guest kernel should return to iteself
+ * directly with
+ *      orb   $3,1*8(%rsp)
+ *      iretq
+ * If flags contains VGCF_in_syscall:
+ *   Restore RAX, RIP, RFLAGS, RSP.
+ *   Discard R11, RCX, CS, SS.
+ * Otherwise:
+ *   Restore RAX, R11, RCX, CS:RIP, RFLAGS, SS:RSP.
+ * All other registers are saved on hypercall entry and restored to user.
+ */
+/* Guest exited in SYSCALL context? Return to guest with SYSRET? */
+#define _VGCF_in_syscall 8
+#define VGCF_in_syscall  (1<<_VGCF_in_syscall)
+#define VGCF_IN_SYSCALL  VGCF_in_syscall
+
+#ifndef __ASSEMBLY__
+
+struct iret_context {
+    /* Top of stack (%rsp at point of hypercall). */
+    uint64_t rax, r11, rcx, flags, rip, cs, rflags, rsp, ss;
+    /* Bottom of iret stack frame. */
+};
+
+#if defined(__GNUC__) && !defined(__STRICT_ANSI__)
+/* Anonymous union includes both 32- and 64-bit names (e.g., eax/rax). */
+#define __DECL_REG(name) union { \
+    uint64_t r ## name, e ## name; \
+    uint32_t _e ## name; \
+}
+#else
+/* Non-gcc sources must always use the proper 64-bit name (e.g., rax). */
+#define __DECL_REG(name) uint64_t r ## name
+#endif
+
+struct cpu_user_regs {
+    uint64_t r15;
+    uint64_t r14;
+    uint64_t r13;
+    uint64_t r12;
+    __DECL_REG(bp);
+    __DECL_REG(bx);
+    uint64_t r11;
+    uint64_t r10;
+    uint64_t r9;
+    uint64_t r8;
+    __DECL_REG(ax);
+    __DECL_REG(cx);
+    __DECL_REG(dx);
+    __DECL_REG(si);
+    __DECL_REG(di);
+    uint32_t error_code;    /* private */
+    uint32_t entry_vector;  /* private */
+    __DECL_REG(ip);
+    uint16_t cs, _pad0[1];
+    uint8_t  saved_upcall_mask;
+    uint8_t  _pad1[3];
+    __DECL_REG(flags);      /* rflags.IF == !saved_upcall_mask */
+    __DECL_REG(sp);
+    uint16_t ss, _pad2[3];
+    uint16_t es, _pad3[3];
+    uint16_t ds, _pad4[3];
+    uint16_t fs, _pad5[3]; /* Non-zero => takes precedence over fs_base.     */
+    uint16_t gs, _pad6[3]; /* Non-zero => takes precedence over gs_base_usr. */
+};
+DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
+
+#undef __DECL_REG
+
+#define xen_pfn_to_cr3(pfn) ((unsigned long)(pfn) << 12)
+#define xen_cr3_to_pfn(cr3) ((unsigned long)(cr3) >> 12)
+
+struct arch_vcpu_info {
+    unsigned long cr2;
+    unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
+};
+
+typedef unsigned long xen_callback_t;
+
+#define XEN_CALLBACK(__cs, __rip)				\
+	((unsigned long)(__rip))
+
+#endif /* !__ASSEMBLY__ */
+
+
+#endif /* ASM_X86__XEN__INTERFACE_64_H */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
new file mode 100644
index 000000000000..d5eada0a48d9
--- /dev/null
+++ b/arch/x86/include/asm/xen/page.h
@@ -0,0 +1,165 @@
+#ifndef ASM_X86__XEN__PAGE_H
+#define ASM_X86__XEN__PAGE_H
+
+#include <linux/pfn.h>
+
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+
+#include <xen/features.h>
+
+/* Xen machine address */
+typedef struct xmaddr {
+	phys_addr_t maddr;
+} xmaddr_t;
+
+/* Xen pseudo-physical address */
+typedef struct xpaddr {
+	phys_addr_t paddr;
+} xpaddr_t;
+
+#define XMADDR(x)	((xmaddr_t) { .maddr = (x) })
+#define XPADDR(x)	((xpaddr_t) { .paddr = (x) })
+
+/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
+#define INVALID_P2M_ENTRY	(~0UL)
+#define FOREIGN_FRAME_BIT	(1UL<<31)
+#define FOREIGN_FRAME(m)	((m) | FOREIGN_FRAME_BIT)
+
+/* Maximum amount of memory we can handle in a domain in pages */
+#define MAX_DOMAIN_PAGES						\
+    ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
+
+
+extern unsigned long get_phys_to_machine(unsigned long pfn);
+extern void set_phys_to_machine(unsigned long pfn, unsigned long mfn);
+
+static inline unsigned long pfn_to_mfn(unsigned long pfn)
+{
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return pfn;
+
+	return get_phys_to_machine(pfn) & ~FOREIGN_FRAME_BIT;
+}
+
+static inline int phys_to_machine_mapping_valid(unsigned long pfn)
+{
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return 1;
+
+	return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+	unsigned long pfn;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return mfn;
+
+#if 0
+	if (unlikely((mfn >> machine_to_phys_order) != 0))
+		return max_mapnr;
+#endif
+
+	pfn = 0;
+	/*
+	 * The array access can fail (e.g., device space beyond end of RAM).
+	 * In such cases it doesn't matter what we return (we return garbage),
+	 * but we must handle the fault without crashing!
+	 */
+	__get_user(pfn, &machine_to_phys_mapping[mfn]);
+
+	return pfn;
+}
+
+static inline xmaddr_t phys_to_machine(xpaddr_t phys)
+{
+	unsigned offset = phys.paddr & ~PAGE_MASK;
+	return XMADDR(PFN_PHYS(pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset);
+}
+
+static inline xpaddr_t machine_to_phys(xmaddr_t machine)
+{
+	unsigned offset = machine.maddr & ~PAGE_MASK;
+	return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset);
+}
+
+/*
+ * We detect special mappings in one of two ways:
+ *  1. If the MFN is an I/O page then Xen will set the m2p entry
+ *     to be outside our maximum possible pseudophys range.
+ *  2. If the MFN belongs to a different domain then we will certainly
+ *     not have MFN in our p2m table. Conversely, if the page is ours,
+ *     then we'll have p2m(m2p(MFN))==MFN.
+ * If we detect a special mapping then it doesn't have a 'struct page'.
+ * We force !pfn_valid() by returning an out-of-range pointer.
+ *
+ * NB. These checks require that, for any MFN that is not in our reservation,
+ * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if
+ * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN.
+ * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety.
+ *
+ * NB2. When deliberately mapping foreign pages into the p2m table, you *must*
+ *      use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we
+ *      require. In all the cases we care about, the FOREIGN_FRAME bit is
+ *      masked (e.g., pfn_to_mfn()) so behaviour there is correct.
+ */
+static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
+{
+	extern unsigned long max_mapnr;
+	unsigned long pfn = mfn_to_pfn(mfn);
+	if ((pfn < max_mapnr)
+	    && !xen_feature(XENFEAT_auto_translated_physmap)
+	    && (get_phys_to_machine(pfn) != mfn))
+		return max_mapnr; /* force !pfn_valid() */
+	/* XXX fixme; not true with sparsemem */
+	return pfn;
+}
+
+/* VIRT <-> MACHINE conversion */
+#define virt_to_machine(v)	(phys_to_machine(XPADDR(__pa(v))))
+#define virt_to_mfn(v)		(pfn_to_mfn(PFN_DOWN(__pa(v))))
+#define mfn_to_virt(m)		(__va(mfn_to_pfn(m) << PAGE_SHIFT))
+
+static inline unsigned long pte_mfn(pte_t pte)
+{
+	return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT;
+}
+
+static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)
+{
+	pte_t pte;
+
+	pte.pte = ((phys_addr_t)page_nr << PAGE_SHIFT) |
+		(pgprot_val(pgprot) & __supported_pte_mask);
+
+	return pte;
+}
+
+static inline pteval_t pte_val_ma(pte_t pte)
+{
+	return pte.pte;
+}
+
+static inline pte_t __pte_ma(pteval_t x)
+{
+	return (pte_t) { .pte = x };
+}
+
+#define pmd_val_ma(v) ((v).pmd)
+#ifdef __PAGETABLE_PUD_FOLDED
+#define pud_val_ma(v) ((v).pgd.pgd)
+#else
+#define pud_val_ma(v) ((v).pud)
+#endif
+#define __pmd_ma(x)	((pmd_t) { (x) } )
+
+#define pgd_val_ma(x)	((x).pgd)
+
+
+xmaddr_t arbitrary_virt_to_machine(void *address);
+void make_lowmem_page_readonly(void *vaddr);
+void make_lowmem_page_readwrite(void *vaddr);
+
+#endif /* ASM_X86__XEN__PAGE_H */
diff --git a/arch/x86/include/asm/xor.h b/arch/x86/include/asm/xor.h
new file mode 100644
index 000000000000..11b3bb86e17b
--- /dev/null
+++ b/arch/x86/include/asm/xor.h
@@ -0,0 +1,5 @@
+#ifdef CONFIG_X86_32
+# include "xor_32.h"
+#else
+# include "xor_64.h"
+#endif
diff --git a/arch/x86/include/asm/xor_32.h b/arch/x86/include/asm/xor_32.h
new file mode 100644
index 000000000000..921b45840449
--- /dev/null
+++ b/arch/x86/include/asm/xor_32.h
@@ -0,0 +1,888 @@
+#ifndef ASM_X86__XOR_32_H
+#define ASM_X86__XOR_32_H
+
+/*
+ * Optimized RAID-5 checksumming functions for MMX and SSE.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * You should have received a copy of the GNU General Public License
+ * (for example /usr/src/linux/COPYING); if not, write to the Free
+ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+/*
+ * High-speed RAID5 checksumming functions utilizing MMX instructions.
+ * Copyright (C) 1998 Ingo Molnar.
+ */
+
+#define LD(x, y)	"       movq   8*("#x")(%1), %%mm"#y"   ;\n"
+#define ST(x, y)	"       movq %%mm"#y",   8*("#x")(%1)   ;\n"
+#define XO1(x, y)	"       pxor   8*("#x")(%2), %%mm"#y"   ;\n"
+#define XO2(x, y)	"       pxor   8*("#x")(%3), %%mm"#y"   ;\n"
+#define XO3(x, y)	"       pxor   8*("#x")(%4), %%mm"#y"   ;\n"
+#define XO4(x, y)	"       pxor   8*("#x")(%5), %%mm"#y"   ;\n"
+
+#include <asm/i387.h>
+
+static void
+xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	unsigned long lines = bytes >> 7;
+
+	kernel_fpu_begin();
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)				\
+	LD(i, 0)				\
+		LD(i + 1, 1)			\
+			LD(i + 2, 2)		\
+				LD(i + 3, 3)	\
+	XO1(i, 0)				\
+	ST(i, 0)				\
+		XO1(i+1, 1)			\
+		ST(i+1, 1)			\
+			XO1(i + 2, 2)		\
+			ST(i + 2, 2)		\
+				XO1(i + 3, 3)	\
+				ST(i + 3, 3)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+	BLOCK(0)
+	BLOCK(4)
+	BLOCK(8)
+	BLOCK(12)
+
+	"       addl $128, %1         ;\n"
+	"       addl $128, %2         ;\n"
+	"       decl %0               ;\n"
+	"       jnz 1b                ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2)
+	:
+	: "memory");
+
+	kernel_fpu_end();
+}
+
+static void
+xor_pII_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	      unsigned long *p3)
+{
+	unsigned long lines = bytes >> 7;
+
+	kernel_fpu_begin();
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)				\
+	LD(i, 0)				\
+		LD(i + 1, 1)			\
+			LD(i + 2, 2)		\
+				LD(i + 3, 3)	\
+	XO1(i, 0)				\
+		XO1(i + 1, 1)			\
+			XO1(i + 2, 2)		\
+				XO1(i + 3, 3)	\
+	XO2(i, 0)				\
+	ST(i, 0)				\
+		XO2(i + 1, 1)			\
+		ST(i + 1, 1)			\
+			XO2(i + 2, 2)		\
+			ST(i + 2, 2)		\
+				XO2(i + 3, 3)	\
+				ST(i + 3, 3)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+	BLOCK(0)
+	BLOCK(4)
+	BLOCK(8)
+	BLOCK(12)
+
+	"       addl $128, %1         ;\n"
+	"       addl $128, %2         ;\n"
+	"       addl $128, %3         ;\n"
+	"       decl %0               ;\n"
+	"       jnz 1b                ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3)
+	:
+	: "memory");
+
+	kernel_fpu_end();
+}
+
+static void
+xor_pII_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	      unsigned long *p3, unsigned long *p4)
+{
+	unsigned long lines = bytes >> 7;
+
+	kernel_fpu_begin();
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)				\
+	LD(i, 0)				\
+		LD(i + 1, 1)			\
+			LD(i + 2, 2)		\
+				LD(i + 3, 3)	\
+	XO1(i, 0)				\
+		XO1(i + 1, 1)			\
+			XO1(i + 2, 2)		\
+				XO1(i + 3, 3)	\
+	XO2(i, 0)				\
+		XO2(i + 1, 1)			\
+			XO2(i + 2, 2)		\
+				XO2(i + 3, 3)	\
+	XO3(i, 0)				\
+	ST(i, 0)				\
+		XO3(i + 1, 1)			\
+		ST(i + 1, 1)			\
+			XO3(i + 2, 2)		\
+			ST(i + 2, 2)		\
+				XO3(i + 3, 3)	\
+				ST(i + 3, 3)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+	BLOCK(0)
+	BLOCK(4)
+	BLOCK(8)
+	BLOCK(12)
+
+	"       addl $128, %1         ;\n"
+	"       addl $128, %2         ;\n"
+	"       addl $128, %3         ;\n"
+	"       addl $128, %4         ;\n"
+	"       decl %0               ;\n"
+	"       jnz 1b                ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+	:
+	: "memory");
+
+	kernel_fpu_end();
+}
+
+
+static void
+xor_pII_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	      unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	unsigned long lines = bytes >> 7;
+
+	kernel_fpu_begin();
+
+	/* Make sure GCC forgets anything it knows about p4 or p5,
+	   such that it won't pass to the asm volatile below a
+	   register that is shared with any other variable.  That's
+	   because we modify p4 and p5 there, but we can't mark them
+	   as read/write, otherwise we'd overflow the 10-asm-operands
+	   limit of GCC < 3.1.  */
+	asm("" : "+r" (p4), "+r" (p5));
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)				\
+	LD(i, 0)				\
+		LD(i + 1, 1)			\
+			LD(i + 2, 2)		\
+				LD(i + 3, 3)	\
+	XO1(i, 0)				\
+		XO1(i + 1, 1)			\
+			XO1(i + 2, 2)		\
+				XO1(i + 3, 3)	\
+	XO2(i, 0)				\
+		XO2(i + 1, 1)			\
+			XO2(i + 2, 2)		\
+				XO2(i + 3, 3)	\
+	XO3(i, 0)				\
+		XO3(i + 1, 1)			\
+			XO3(i + 2, 2)		\
+				XO3(i + 3, 3)	\
+	XO4(i, 0)				\
+	ST(i, 0)				\
+		XO4(i + 1, 1)			\
+		ST(i + 1, 1)			\
+			XO4(i + 2, 2)		\
+			ST(i + 2, 2)		\
+				XO4(i + 3, 3)	\
+				ST(i + 3, 3)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+	BLOCK(0)
+	BLOCK(4)
+	BLOCK(8)
+	BLOCK(12)
+
+	"       addl $128, %1         ;\n"
+	"       addl $128, %2         ;\n"
+	"       addl $128, %3         ;\n"
+	"       addl $128, %4         ;\n"
+	"       addl $128, %5         ;\n"
+	"       decl %0               ;\n"
+	"       jnz 1b                ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3)
+	: "r" (p4), "r" (p5)
+	: "memory");
+
+	/* p4 and p5 were modified, and now the variables are dead.
+	   Clobber them just to be sure nobody does something stupid
+	   like assuming they have some legal value.  */
+	asm("" : "=r" (p4), "=r" (p5));
+
+	kernel_fpu_end();
+}
+
+#undef LD
+#undef XO1
+#undef XO2
+#undef XO3
+#undef XO4
+#undef ST
+#undef BLOCK
+
+static void
+xor_p5_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	unsigned long lines = bytes >> 6;
+
+	kernel_fpu_begin();
+
+	asm volatile(
+	" .align 32	             ;\n"
+	" 1:                         ;\n"
+	"       movq   (%1), %%mm0   ;\n"
+	"       movq  8(%1), %%mm1   ;\n"
+	"       pxor   (%2), %%mm0   ;\n"
+	"       movq 16(%1), %%mm2   ;\n"
+	"       movq %%mm0,   (%1)   ;\n"
+	"       pxor  8(%2), %%mm1   ;\n"
+	"       movq 24(%1), %%mm3   ;\n"
+	"       movq %%mm1,  8(%1)   ;\n"
+	"       pxor 16(%2), %%mm2   ;\n"
+	"       movq 32(%1), %%mm4   ;\n"
+	"       movq %%mm2, 16(%1)   ;\n"
+	"       pxor 24(%2), %%mm3   ;\n"
+	"       movq 40(%1), %%mm5   ;\n"
+	"       movq %%mm3, 24(%1)   ;\n"
+	"       pxor 32(%2), %%mm4   ;\n"
+	"       movq 48(%1), %%mm6   ;\n"
+	"       movq %%mm4, 32(%1)   ;\n"
+	"       pxor 40(%2), %%mm5   ;\n"
+	"       movq 56(%1), %%mm7   ;\n"
+	"       movq %%mm5, 40(%1)   ;\n"
+	"       pxor 48(%2), %%mm6   ;\n"
+	"       pxor 56(%2), %%mm7   ;\n"
+	"       movq %%mm6, 48(%1)   ;\n"
+	"       movq %%mm7, 56(%1)   ;\n"
+
+	"       addl $64, %1         ;\n"
+	"       addl $64, %2         ;\n"
+	"       decl %0              ;\n"
+	"       jnz 1b               ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2)
+	:
+	: "memory");
+
+	kernel_fpu_end();
+}
+
+static void
+xor_p5_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	     unsigned long *p3)
+{
+	unsigned long lines = bytes >> 6;
+
+	kernel_fpu_begin();
+
+	asm volatile(
+	" .align 32,0x90             ;\n"
+	" 1:                         ;\n"
+	"       movq   (%1), %%mm0   ;\n"
+	"       movq  8(%1), %%mm1   ;\n"
+	"       pxor   (%2), %%mm0   ;\n"
+	"       movq 16(%1), %%mm2   ;\n"
+	"       pxor  8(%2), %%mm1   ;\n"
+	"       pxor   (%3), %%mm0   ;\n"
+	"       pxor 16(%2), %%mm2   ;\n"
+	"       movq %%mm0,   (%1)   ;\n"
+	"       pxor  8(%3), %%mm1   ;\n"
+	"       pxor 16(%3), %%mm2   ;\n"
+	"       movq 24(%1), %%mm3   ;\n"
+	"       movq %%mm1,  8(%1)   ;\n"
+	"       movq 32(%1), %%mm4   ;\n"
+	"       movq 40(%1), %%mm5   ;\n"
+	"       pxor 24(%2), %%mm3   ;\n"
+	"       movq %%mm2, 16(%1)   ;\n"
+	"       pxor 32(%2), %%mm4   ;\n"
+	"       pxor 24(%3), %%mm3   ;\n"
+	"       pxor 40(%2), %%mm5   ;\n"
+	"       movq %%mm3, 24(%1)   ;\n"
+	"       pxor 32(%3), %%mm4   ;\n"
+	"       pxor 40(%3), %%mm5   ;\n"
+	"       movq 48(%1), %%mm6   ;\n"
+	"       movq %%mm4, 32(%1)   ;\n"
+	"       movq 56(%1), %%mm7   ;\n"
+	"       pxor 48(%2), %%mm6   ;\n"
+	"       movq %%mm5, 40(%1)   ;\n"
+	"       pxor 56(%2), %%mm7   ;\n"
+	"       pxor 48(%3), %%mm6   ;\n"
+	"       pxor 56(%3), %%mm7   ;\n"
+	"       movq %%mm6, 48(%1)   ;\n"
+	"       movq %%mm7, 56(%1)   ;\n"
+
+	"       addl $64, %1         ;\n"
+	"       addl $64, %2         ;\n"
+	"       addl $64, %3         ;\n"
+	"       decl %0              ;\n"
+	"       jnz 1b               ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3)
+	:
+	: "memory" );
+
+	kernel_fpu_end();
+}
+
+static void
+xor_p5_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	     unsigned long *p3, unsigned long *p4)
+{
+	unsigned long lines = bytes >> 6;
+
+	kernel_fpu_begin();
+
+	asm volatile(
+	" .align 32,0x90             ;\n"
+	" 1:                         ;\n"
+	"       movq   (%1), %%mm0   ;\n"
+	"       movq  8(%1), %%mm1   ;\n"
+	"       pxor   (%2), %%mm0   ;\n"
+	"       movq 16(%1), %%mm2   ;\n"
+	"       pxor  8(%2), %%mm1   ;\n"
+	"       pxor   (%3), %%mm0   ;\n"
+	"       pxor 16(%2), %%mm2   ;\n"
+	"       pxor  8(%3), %%mm1   ;\n"
+	"       pxor   (%4), %%mm0   ;\n"
+	"       movq 24(%1), %%mm3   ;\n"
+	"       pxor 16(%3), %%mm2   ;\n"
+	"       pxor  8(%4), %%mm1   ;\n"
+	"       movq %%mm0,   (%1)   ;\n"
+	"       movq 32(%1), %%mm4   ;\n"
+	"       pxor 24(%2), %%mm3   ;\n"
+	"       pxor 16(%4), %%mm2   ;\n"
+	"       movq %%mm1,  8(%1)   ;\n"
+	"       movq 40(%1), %%mm5   ;\n"
+	"       pxor 32(%2), %%mm4   ;\n"
+	"       pxor 24(%3), %%mm3   ;\n"
+	"       movq %%mm2, 16(%1)   ;\n"
+	"       pxor 40(%2), %%mm5   ;\n"
+	"       pxor 32(%3), %%mm4   ;\n"
+	"       pxor 24(%4), %%mm3   ;\n"
+	"       movq %%mm3, 24(%1)   ;\n"
+	"       movq 56(%1), %%mm7   ;\n"
+	"       movq 48(%1), %%mm6   ;\n"
+	"       pxor 40(%3), %%mm5   ;\n"
+	"       pxor 32(%4), %%mm4   ;\n"
+	"       pxor 48(%2), %%mm6   ;\n"
+	"       movq %%mm4, 32(%1)   ;\n"
+	"       pxor 56(%2), %%mm7   ;\n"
+	"       pxor 40(%4), %%mm5   ;\n"
+	"       pxor 48(%3), %%mm6   ;\n"
+	"       pxor 56(%3), %%mm7   ;\n"
+	"       movq %%mm5, 40(%1)   ;\n"
+	"       pxor 48(%4), %%mm6   ;\n"
+	"       pxor 56(%4), %%mm7   ;\n"
+	"       movq %%mm6, 48(%1)   ;\n"
+	"       movq %%mm7, 56(%1)   ;\n"
+
+	"       addl $64, %1         ;\n"
+	"       addl $64, %2         ;\n"
+	"       addl $64, %3         ;\n"
+	"       addl $64, %4         ;\n"
+	"       decl %0              ;\n"
+	"       jnz 1b               ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+	:
+	: "memory");
+
+	kernel_fpu_end();
+}
+
+static void
+xor_p5_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	     unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	unsigned long lines = bytes >> 6;
+
+	kernel_fpu_begin();
+
+	/* Make sure GCC forgets anything it knows about p4 or p5,
+	   such that it won't pass to the asm volatile below a
+	   register that is shared with any other variable.  That's
+	   because we modify p4 and p5 there, but we can't mark them
+	   as read/write, otherwise we'd overflow the 10-asm-operands
+	   limit of GCC < 3.1.  */
+	asm("" : "+r" (p4), "+r" (p5));
+
+	asm volatile(
+	" .align 32,0x90             ;\n"
+	" 1:                         ;\n"
+	"       movq   (%1), %%mm0   ;\n"
+	"       movq  8(%1), %%mm1   ;\n"
+	"       pxor   (%2), %%mm0   ;\n"
+	"       pxor  8(%2), %%mm1   ;\n"
+	"       movq 16(%1), %%mm2   ;\n"
+	"       pxor   (%3), %%mm0   ;\n"
+	"       pxor  8(%3), %%mm1   ;\n"
+	"       pxor 16(%2), %%mm2   ;\n"
+	"       pxor   (%4), %%mm0   ;\n"
+	"       pxor  8(%4), %%mm1   ;\n"
+	"       pxor 16(%3), %%mm2   ;\n"
+	"       movq 24(%1), %%mm3   ;\n"
+	"       pxor   (%5), %%mm0   ;\n"
+	"       pxor  8(%5), %%mm1   ;\n"
+	"       movq %%mm0,   (%1)   ;\n"
+	"       pxor 16(%4), %%mm2   ;\n"
+	"       pxor 24(%2), %%mm3   ;\n"
+	"       movq %%mm1,  8(%1)   ;\n"
+	"       pxor 16(%5), %%mm2   ;\n"
+	"       pxor 24(%3), %%mm3   ;\n"
+	"       movq 32(%1), %%mm4   ;\n"
+	"       movq %%mm2, 16(%1)   ;\n"
+	"       pxor 24(%4), %%mm3   ;\n"
+	"       pxor 32(%2), %%mm4   ;\n"
+	"       movq 40(%1), %%mm5   ;\n"
+	"       pxor 24(%5), %%mm3   ;\n"
+	"       pxor 32(%3), %%mm4   ;\n"
+	"       pxor 40(%2), %%mm5   ;\n"
+	"       movq %%mm3, 24(%1)   ;\n"
+	"       pxor 32(%4), %%mm4   ;\n"
+	"       pxor 40(%3), %%mm5   ;\n"
+	"       movq 48(%1), %%mm6   ;\n"
+	"       movq 56(%1), %%mm7   ;\n"
+	"       pxor 32(%5), %%mm4   ;\n"
+	"       pxor 40(%4), %%mm5   ;\n"
+	"       pxor 48(%2), %%mm6   ;\n"
+	"       pxor 56(%2), %%mm7   ;\n"
+	"       movq %%mm4, 32(%1)   ;\n"
+	"       pxor 48(%3), %%mm6   ;\n"
+	"       pxor 56(%3), %%mm7   ;\n"
+	"       pxor 40(%5), %%mm5   ;\n"
+	"       pxor 48(%4), %%mm6   ;\n"
+	"       pxor 56(%4), %%mm7   ;\n"
+	"       movq %%mm5, 40(%1)   ;\n"
+	"       pxor 48(%5), %%mm6   ;\n"
+	"       pxor 56(%5), %%mm7   ;\n"
+	"       movq %%mm6, 48(%1)   ;\n"
+	"       movq %%mm7, 56(%1)   ;\n"
+
+	"       addl $64, %1         ;\n"
+	"       addl $64, %2         ;\n"
+	"       addl $64, %3         ;\n"
+	"       addl $64, %4         ;\n"
+	"       addl $64, %5         ;\n"
+	"       decl %0              ;\n"
+	"       jnz 1b               ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3)
+	: "r" (p4), "r" (p5)
+	: "memory");
+
+	/* p4 and p5 were modified, and now the variables are dead.
+	   Clobber them just to be sure nobody does something stupid
+	   like assuming they have some legal value.  */
+	asm("" : "=r" (p4), "=r" (p5));
+
+	kernel_fpu_end();
+}
+
+static struct xor_block_template xor_block_pII_mmx = {
+	.name = "pII_mmx",
+	.do_2 = xor_pII_mmx_2,
+	.do_3 = xor_pII_mmx_3,
+	.do_4 = xor_pII_mmx_4,
+	.do_5 = xor_pII_mmx_5,
+};
+
+static struct xor_block_template xor_block_p5_mmx = {
+	.name = "p5_mmx",
+	.do_2 = xor_p5_mmx_2,
+	.do_3 = xor_p5_mmx_3,
+	.do_4 = xor_p5_mmx_4,
+	.do_5 = xor_p5_mmx_5,
+};
+
+/*
+ * Cache avoiding checksumming functions utilizing KNI instructions
+ * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
+ */
+
+#define XMMS_SAVE				\
+do {						\
+	preempt_disable();			\
+	cr0 = read_cr0();			\
+	clts();					\
+	asm volatile(				\
+		"movups %%xmm0,(%0)	;\n\t"	\
+		"movups %%xmm1,0x10(%0)	;\n\t"	\
+		"movups %%xmm2,0x20(%0)	;\n\t"	\
+		"movups %%xmm3,0x30(%0)	;\n\t"	\
+		:				\
+		: "r" (xmm_save) 		\
+		: "memory");			\
+} while (0)
+
+#define XMMS_RESTORE				\
+do {						\
+	asm volatile(				\
+		"sfence			;\n\t"	\
+		"movups (%0),%%xmm0	;\n\t"	\
+		"movups 0x10(%0),%%xmm1	;\n\t"	\
+		"movups 0x20(%0),%%xmm2	;\n\t"	\
+		"movups 0x30(%0),%%xmm3	;\n\t"	\
+		:				\
+		: "r" (xmm_save)		\
+		: "memory");			\
+	write_cr0(cr0);				\
+	preempt_enable();			\
+} while (0)
+
+#define ALIGN16 __attribute__((aligned(16)))
+
+#define OFFS(x)		"16*("#x")"
+#define PF_OFFS(x)	"256+16*("#x")"
+#define	PF0(x)		"	prefetchnta "PF_OFFS(x)"(%1)		;\n"
+#define LD(x, y)	"       movaps   "OFFS(x)"(%1), %%xmm"#y"	;\n"
+#define ST(x, y)	"       movaps %%xmm"#y",   "OFFS(x)"(%1)	;\n"
+#define PF1(x)		"	prefetchnta "PF_OFFS(x)"(%2)		;\n"
+#define PF2(x)		"	prefetchnta "PF_OFFS(x)"(%3)		;\n"
+#define PF3(x)		"	prefetchnta "PF_OFFS(x)"(%4)		;\n"
+#define PF4(x)		"	prefetchnta "PF_OFFS(x)"(%5)		;\n"
+#define PF5(x)		"	prefetchnta "PF_OFFS(x)"(%6)		;\n"
+#define XO1(x, y)	"       xorps   "OFFS(x)"(%2), %%xmm"#y"	;\n"
+#define XO2(x, y)	"       xorps   "OFFS(x)"(%3), %%xmm"#y"	;\n"
+#define XO3(x, y)	"       xorps   "OFFS(x)"(%4), %%xmm"#y"	;\n"
+#define XO4(x, y)	"       xorps   "OFFS(x)"(%5), %%xmm"#y"	;\n"
+#define XO5(x, y)	"       xorps   "OFFS(x)"(%6), %%xmm"#y"	;\n"
+
+
+static void
+xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	unsigned long lines = bytes >> 8;
+	char xmm_save[16*4] ALIGN16;
+	int cr0;
+
+	XMMS_SAVE;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i)					\
+		LD(i, 0)				\
+			LD(i + 1, 1)			\
+		PF1(i)					\
+				PF1(i + 2)		\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO1(i, 0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		ST(i, 0)				\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       addl $256, %1           ;\n"
+	"       addl $256, %2           ;\n"
+	"       decl %0                 ;\n"
+	"       jnz 1b                  ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2)
+	:
+	: "memory");
+
+	XMMS_RESTORE;
+}
+
+static void
+xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	  unsigned long *p3)
+{
+	unsigned long lines = bytes >> 8;
+	char xmm_save[16*4] ALIGN16;
+	int cr0;
+
+	XMMS_SAVE;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i) \
+		PF1(i)					\
+				PF1(i + 2)		\
+		LD(i,0)					\
+			LD(i + 1, 1)			\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF2(i)					\
+				PF2(i + 2)		\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO1(i,0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		XO2(i,0)				\
+			XO2(i + 1, 1)			\
+				XO2(i + 2, 2)		\
+					XO2(i + 3, 3)	\
+		ST(i,0)					\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       addl $256, %1           ;\n"
+	"       addl $256, %2           ;\n"
+	"       addl $256, %3           ;\n"
+	"       decl %0                 ;\n"
+	"       jnz 1b                  ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r"(p2), "+r"(p3)
+	:
+	: "memory" );
+
+	XMMS_RESTORE;
+}
+
+static void
+xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	  unsigned long *p3, unsigned long *p4)
+{
+	unsigned long lines = bytes >> 8;
+	char xmm_save[16*4] ALIGN16;
+	int cr0;
+
+	XMMS_SAVE;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i) \
+		PF1(i)					\
+				PF1(i + 2)		\
+		LD(i,0)					\
+			LD(i + 1, 1)			\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF2(i)					\
+				PF2(i + 2)		\
+		XO1(i,0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		PF3(i)					\
+				PF3(i + 2)		\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO2(i,0)				\
+			XO2(i + 1, 1)			\
+				XO2(i + 2, 2)		\
+					XO2(i + 3, 3)	\
+		XO3(i,0)				\
+			XO3(i + 1, 1)			\
+				XO3(i + 2, 2)		\
+					XO3(i + 3, 3)	\
+		ST(i,0)					\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       addl $256, %1           ;\n"
+	"       addl $256, %2           ;\n"
+	"       addl $256, %3           ;\n"
+	"       addl $256, %4           ;\n"
+	"       decl %0                 ;\n"
+	"       jnz 1b                  ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
+	:
+	: "memory" );
+
+	XMMS_RESTORE;
+}
+
+static void
+xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	  unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	unsigned long lines = bytes >> 8;
+	char xmm_save[16*4] ALIGN16;
+	int cr0;
+
+	XMMS_SAVE;
+
+	/* Make sure GCC forgets anything it knows about p4 or p5,
+	   such that it won't pass to the asm volatile below a
+	   register that is shared with any other variable.  That's
+	   because we modify p4 and p5 there, but we can't mark them
+	   as read/write, otherwise we'd overflow the 10-asm-operands
+	   limit of GCC < 3.1.  */
+	asm("" : "+r" (p4), "+r" (p5));
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i) \
+		PF1(i)					\
+				PF1(i + 2)		\
+		LD(i,0)					\
+			LD(i + 1, 1)			\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF2(i)					\
+				PF2(i + 2)		\
+		XO1(i,0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		PF3(i)					\
+				PF3(i + 2)		\
+		XO2(i,0)				\
+			XO2(i + 1, 1)			\
+				XO2(i + 2, 2)		\
+					XO2(i + 3, 3)	\
+		PF4(i)					\
+				PF4(i + 2)		\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO3(i,0)				\
+			XO3(i + 1, 1)			\
+				XO3(i + 2, 2)		\
+					XO3(i + 3, 3)	\
+		XO4(i,0)				\
+			XO4(i + 1, 1)			\
+				XO4(i + 2, 2)		\
+					XO4(i + 3, 3)	\
+		ST(i,0)					\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       addl $256, %1           ;\n"
+	"       addl $256, %2           ;\n"
+	"       addl $256, %3           ;\n"
+	"       addl $256, %4           ;\n"
+	"       addl $256, %5           ;\n"
+	"       decl %0                 ;\n"
+	"       jnz 1b                  ;\n"
+	: "+r" (lines),
+	  "+r" (p1), "+r" (p2), "+r" (p3)
+	: "r" (p4), "r" (p5)
+	: "memory");
+
+	/* p4 and p5 were modified, and now the variables are dead.
+	   Clobber them just to be sure nobody does something stupid
+	   like assuming they have some legal value.  */
+	asm("" : "=r" (p4), "=r" (p5));
+
+	XMMS_RESTORE;
+}
+
+static struct xor_block_template xor_block_pIII_sse = {
+	.name = "pIII_sse",
+	.do_2 = xor_sse_2,
+	.do_3 = xor_sse_3,
+	.do_4 = xor_sse_4,
+	.do_5 = xor_sse_5,
+};
+
+/* Also try the generic routines.  */
+#include <asm-generic/xor.h>
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES				\
+do {							\
+	xor_speed(&xor_block_8regs);			\
+	xor_speed(&xor_block_8regs_p);			\
+	xor_speed(&xor_block_32regs);			\
+	xor_speed(&xor_block_32regs_p);			\
+	if (cpu_has_xmm)				\
+		xor_speed(&xor_block_pIII_sse);		\
+	if (cpu_has_mmx) {				\
+		xor_speed(&xor_block_pII_mmx);		\
+		xor_speed(&xor_block_p5_mmx);		\
+	}						\
+} while (0)
+
+/* We force the use of the SSE xor block because it can write around L2.
+   We may also be able to load into the L1 only depending on how the cpu
+   deals with a load to a line that is being prefetched.  */
+#define XOR_SELECT_TEMPLATE(FASTEST)			\
+	(cpu_has_xmm ? &xor_block_pIII_sse : FASTEST)
+
+#endif /* ASM_X86__XOR_32_H */
diff --git a/arch/x86/include/asm/xor_64.h b/arch/x86/include/asm/xor_64.h
new file mode 100644
index 000000000000..2d3a18de295b
--- /dev/null
+++ b/arch/x86/include/asm/xor_64.h
@@ -0,0 +1,361 @@
+#ifndef ASM_X86__XOR_64_H
+#define ASM_X86__XOR_64_H
+
+/*
+ * Optimized RAID-5 checksumming functions for MMX and SSE.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2, or (at your option)
+ * any later version.
+ *
+ * You should have received a copy of the GNU General Public License
+ * (for example /usr/src/linux/COPYING); if not, write to the Free
+ * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+
+
+/*
+ * Cache avoiding checksumming functions utilizing KNI instructions
+ * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
+ */
+
+/*
+ * Based on
+ * High-speed RAID5 checksumming functions utilizing SSE instructions.
+ * Copyright (C) 1998 Ingo Molnar.
+ */
+
+/*
+ * x86-64 changes / gcc fixes from Andi Kleen.
+ * Copyright 2002 Andi Kleen, SuSE Labs.
+ *
+ * This hasn't been optimized for the hammer yet, but there are likely
+ * no advantages to be gotten from x86-64 here anyways.
+ */
+
+typedef struct {
+	unsigned long a, b;
+} __attribute__((aligned(16))) xmm_store_t;
+
+/* Doesn't use gcc to save the XMM registers, because there is no easy way to
+   tell it to do a clts before the register saving. */
+#define XMMS_SAVE				\
+do {						\
+	preempt_disable();			\
+	asm volatile(				\
+		"movq %%cr0,%0		;\n\t"	\
+		"clts			;\n\t"	\
+		"movups %%xmm0,(%1)	;\n\t"	\
+		"movups %%xmm1,0x10(%1)	;\n\t"	\
+		"movups %%xmm2,0x20(%1)	;\n\t"	\
+		"movups %%xmm3,0x30(%1)	;\n\t"	\
+		: "=&r" (cr0)			\
+		: "r" (xmm_save) 		\
+		: "memory");			\
+} while (0)
+
+#define XMMS_RESTORE				\
+do {						\
+	asm volatile(				\
+		"sfence			;\n\t"	\
+		"movups (%1),%%xmm0	;\n\t"	\
+		"movups 0x10(%1),%%xmm1	;\n\t"	\
+		"movups 0x20(%1),%%xmm2	;\n\t"	\
+		"movups 0x30(%1),%%xmm3	;\n\t"	\
+		"movq 	%0,%%cr0	;\n\t"	\
+		:				\
+		: "r" (cr0), "r" (xmm_save)	\
+		: "memory");			\
+	preempt_enable();			\
+} while (0)
+
+#define OFFS(x)		"16*("#x")"
+#define PF_OFFS(x)	"256+16*("#x")"
+#define	PF0(x)		"	prefetchnta "PF_OFFS(x)"(%[p1])		;\n"
+#define LD(x, y)	"       movaps   "OFFS(x)"(%[p1]), %%xmm"#y"	;\n"
+#define ST(x, y)	"       movaps %%xmm"#y",   "OFFS(x)"(%[p1])	;\n"
+#define PF1(x)		"	prefetchnta "PF_OFFS(x)"(%[p2])		;\n"
+#define PF2(x)		"	prefetchnta "PF_OFFS(x)"(%[p3])		;\n"
+#define PF3(x)		"	prefetchnta "PF_OFFS(x)"(%[p4])		;\n"
+#define PF4(x)		"	prefetchnta "PF_OFFS(x)"(%[p5])		;\n"
+#define PF5(x)		"	prefetchnta "PF_OFFS(x)"(%[p6])		;\n"
+#define XO1(x, y)	"       xorps   "OFFS(x)"(%[p2]), %%xmm"#y"	;\n"
+#define XO2(x, y)	"       xorps   "OFFS(x)"(%[p3]), %%xmm"#y"	;\n"
+#define XO3(x, y)	"       xorps   "OFFS(x)"(%[p4]), %%xmm"#y"	;\n"
+#define XO4(x, y)	"       xorps   "OFFS(x)"(%[p5]), %%xmm"#y"	;\n"
+#define XO5(x, y)	"       xorps   "OFFS(x)"(%[p6]), %%xmm"#y"	;\n"
+
+
+static void
+xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
+{
+	unsigned int lines = bytes >> 8;
+	unsigned long cr0;
+	xmm_store_t xmm_save[4];
+
+	XMMS_SAVE;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i) \
+		LD(i, 0)				\
+			LD(i + 1, 1)			\
+		PF1(i)					\
+				PF1(i + 2)		\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO1(i, 0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		ST(i, 0)				\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       addq %[inc], %[p1]           ;\n"
+	"       addq %[inc], %[p2]           ;\n"
+		"		decl %[cnt] ; jnz 1b"
+	: [p1] "+r" (p1), [p2] "+r" (p2), [cnt] "+r" (lines)
+	: [inc] "r" (256UL)
+	: "memory");
+
+	XMMS_RESTORE;
+}
+
+static void
+xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	  unsigned long *p3)
+{
+	unsigned int lines = bytes >> 8;
+	xmm_store_t xmm_save[4];
+	unsigned long cr0;
+
+	XMMS_SAVE;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i) \
+		PF1(i)					\
+				PF1(i + 2)		\
+		LD(i, 0)					\
+			LD(i + 1, 1)			\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF2(i)					\
+				PF2(i + 2)		\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO1(i, 0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		XO2(i, 0)				\
+			XO2(i + 1, 1)			\
+				XO2(i + 2, 2)		\
+					XO2(i + 3, 3)	\
+		ST(i, 0)				\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       addq %[inc], %[p1]           ;\n"
+	"       addq %[inc], %[p2]          ;\n"
+	"       addq %[inc], %[p3]           ;\n"
+		"		decl %[cnt] ; jnz 1b"
+	: [cnt] "+r" (lines),
+	  [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
+	: [inc] "r" (256UL)
+	: "memory");
+	XMMS_RESTORE;
+}
+
+static void
+xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	  unsigned long *p3, unsigned long *p4)
+{
+	unsigned int lines = bytes >> 8;
+	xmm_store_t xmm_save[4];
+	unsigned long cr0;
+
+	XMMS_SAVE;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i) \
+		PF1(i)					\
+				PF1(i + 2)		\
+		LD(i, 0)				\
+			LD(i + 1, 1)			\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF2(i)					\
+				PF2(i + 2)		\
+		XO1(i, 0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		PF3(i)					\
+				PF3(i + 2)		\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO2(i, 0)				\
+			XO2(i + 1, 1)			\
+				XO2(i + 2, 2)		\
+					XO2(i + 3, 3)	\
+		XO3(i, 0)				\
+			XO3(i + 1, 1)			\
+				XO3(i + 2, 2)		\
+					XO3(i + 3, 3)	\
+		ST(i, 0)				\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       addq %[inc], %[p1]           ;\n"
+	"       addq %[inc], %[p2]           ;\n"
+	"       addq %[inc], %[p3]           ;\n"
+	"       addq %[inc], %[p4]           ;\n"
+	"	decl %[cnt] ; jnz 1b"
+	: [cnt] "+c" (lines),
+	  [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4)
+	: [inc] "r" (256UL)
+	: "memory" );
+
+	XMMS_RESTORE;
+}
+
+static void
+xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
+	  unsigned long *p3, unsigned long *p4, unsigned long *p5)
+{
+	unsigned int lines = bytes >> 8;
+	xmm_store_t xmm_save[4];
+	unsigned long cr0;
+
+	XMMS_SAVE;
+
+	asm volatile(
+#undef BLOCK
+#define BLOCK(i) \
+		PF1(i)					\
+				PF1(i + 2)		\
+		LD(i, 0)				\
+			LD(i + 1, 1)			\
+				LD(i + 2, 2)		\
+					LD(i + 3, 3)	\
+		PF2(i)					\
+				PF2(i + 2)		\
+		XO1(i, 0)				\
+			XO1(i + 1, 1)			\
+				XO1(i + 2, 2)		\
+					XO1(i + 3, 3)	\
+		PF3(i)					\
+				PF3(i + 2)		\
+		XO2(i, 0)				\
+			XO2(i + 1, 1)			\
+				XO2(i + 2, 2)		\
+					XO2(i + 3, 3)	\
+		PF4(i)					\
+				PF4(i + 2)		\
+		PF0(i + 4)				\
+				PF0(i + 6)		\
+		XO3(i, 0)				\
+			XO3(i + 1, 1)			\
+				XO3(i + 2, 2)		\
+					XO3(i + 3, 3)	\
+		XO4(i, 0)				\
+			XO4(i + 1, 1)			\
+				XO4(i + 2, 2)		\
+					XO4(i + 3, 3)	\
+		ST(i, 0)				\
+			ST(i + 1, 1)			\
+				ST(i + 2, 2)		\
+					ST(i + 3, 3)	\
+
+
+		PF0(0)
+				PF0(2)
+
+	" .align 32			;\n"
+	" 1:                            ;\n"
+
+		BLOCK(0)
+		BLOCK(4)
+		BLOCK(8)
+		BLOCK(12)
+
+	"       addq %[inc], %[p1]           ;\n"
+	"       addq %[inc], %[p2]           ;\n"
+	"       addq %[inc], %[p3]           ;\n"
+	"       addq %[inc], %[p4]           ;\n"
+	"       addq %[inc], %[p5]           ;\n"
+	"	decl %[cnt] ; jnz 1b"
+	: [cnt] "+c" (lines),
+	  [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4),
+	  [p5] "+r" (p5)
+	: [inc] "r" (256UL)
+	: "memory");
+
+	XMMS_RESTORE;
+}
+
+static struct xor_block_template xor_block_sse = {
+	.name = "generic_sse",
+	.do_2 = xor_sse_2,
+	.do_3 = xor_sse_3,
+	.do_4 = xor_sse_4,
+	.do_5 = xor_sse_5,
+};
+
+#undef XOR_TRY_TEMPLATES
+#define XOR_TRY_TEMPLATES			\
+do {						\
+	xor_speed(&xor_block_sse);		\
+} while (0)
+
+/* We force the use of the SSE xor block because it can write around L2.
+   We may also be able to load into the L1 only depending on how the cpu
+   deals with a load to a line that is being prefetched.  */
+#define XOR_SELECT_TEMPLATE(FASTEST) (&xor_block_sse)
+
+#endif /* ASM_X86__XOR_64_H */
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
new file mode 100644
index 000000000000..08e9a1ac07a9
--- /dev/null
+++ b/arch/x86/include/asm/xsave.h
@@ -0,0 +1,118 @@
+#ifndef __ASM_X86_XSAVE_H
+#define __ASM_X86_XSAVE_H
+
+#include <linux/types.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+
+#define XSTATE_FP	0x1
+#define XSTATE_SSE	0x2
+
+#define XSTATE_FPSSE	(XSTATE_FP | XSTATE_SSE)
+
+#define FXSAVE_SIZE	512
+
+/*
+ * These are the features that the OS can handle currently.
+ */
+#define XCNTXT_MASK	(XSTATE_FP | XSTATE_SSE)
+
+#ifdef CONFIG_X86_64
+#define REX_PREFIX	"0x48, "
+#else
+#define REX_PREFIX
+#endif
+
+extern unsigned int xstate_size;
+extern u64 pcntxt_mask;
+extern struct xsave_struct *init_xstate_buf;
+
+extern void xsave_cntxt_init(void);
+extern void xsave_init(void);
+extern int init_fpu(struct task_struct *child);
+extern int check_for_xstate(struct i387_fxsave_struct __user *buf,
+			    void __user *fpstate,
+			    struct _fpx_sw_bytes *sw);
+
+static inline int xrstor_checking(struct xsave_struct *fx)
+{
+	int err;
+
+	asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
+		     "2:\n"
+		     ".section .fixup,\"ax\"\n"
+		     "3:  movl $-1,%[err]\n"
+		     "    jmp  2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err)
+		     : "D" (fx), "m" (*fx), "a" (-1), "d" (-1), "0" (0)
+		     : "memory");
+
+	return err;
+}
+
+static inline int xsave_user(struct xsave_struct __user *buf)
+{
+	int err;
+	__asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x27\n"
+			     "2:\n"
+			     ".section .fixup,\"ax\"\n"
+			     "3:  movl $-1,%[err]\n"
+			     "    jmp  2b\n"
+			     ".previous\n"
+			     ".section __ex_table,\"a\"\n"
+			     _ASM_ALIGN "\n"
+			     _ASM_PTR "1b,3b\n"
+			     ".previous"
+			     : [err] "=r" (err)
+			     : "D" (buf), "a" (-1), "d" (-1), "0" (0)
+			     : "memory");
+	if (unlikely(err) && __clear_user(buf, xstate_size))
+		err = -EFAULT;
+	/* No need to clear here because the caller clears USED_MATH */
+	return err;
+}
+
+static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
+{
+	int err;
+	struct xsave_struct *xstate = ((__force struct xsave_struct *)buf);
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+
+	__asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n"
+			     "2:\n"
+			     ".section .fixup,\"ax\"\n"
+			     "3:  movl $-1,%[err]\n"
+			     "    jmp  2b\n"
+			     ".previous\n"
+			     ".section __ex_table,\"a\"\n"
+			     _ASM_ALIGN "\n"
+			     _ASM_PTR "1b,3b\n"
+			     ".previous"
+			     : [err] "=r" (err)
+			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
+			     : "memory");	/* memory required? */
+	return err;
+}
+
+static inline void xrstor_state(struct xsave_struct *fx, u64 mask)
+{
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+
+	asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
+		     : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+		     :   "memory");
+}
+
+static inline void xsave(struct task_struct *tsk)
+{
+	/* This, however, we can work around by forcing the compiler to select
+	   an addressing mode that doesn't require extended registers. */
+	__asm__ __volatile__(".byte " REX_PREFIX "0x0f,0xae,0x27"
+			     : : "D" (&(tsk->thread.xstate->xsave)),
+				 "a" (-1), "d"(-1) : "memory");
+}
+#endif
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 7f0b45a5d788..82ec6075c057 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -25,7 +25,7 @@ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
 quiet_cmd_mkcapflags = MKCAP   $@
       cmd_mkcapflags = $(PERL) $(srctree)/$(src)/mkcapflags.pl $< $@
 
-cpufeature = $(src)/../../../../include/asm-x86/cpufeature.h
+cpufeature = $(src)/../../include/asm/cpufeature.h
 
 targets += capflags.c
 $(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.pl FORCE
diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c
index 565280ec1c6a..974f56d1ebe1 100644
--- a/drivers/xen/cpu_hotplug.c
+++ b/drivers/xen/cpu_hotplug.c
@@ -2,7 +2,7 @@
 
 #include <xen/xenbus.h>
 
-#include <asm-x86/xen/hypervisor.h>
+#include <asm/xen/hypervisor.h>
 #include <asm/cpu.h>
 
 static void enable_hotplug_cpu(int cpu)
diff --git a/include/asm-x86/Kbuild b/include/asm-x86/Kbuild
deleted file mode 100644
index 4a8e80cdcfa5..000000000000
--- a/include/asm-x86/Kbuild
+++ /dev/null
@@ -1,24 +0,0 @@
-include include/asm-generic/Kbuild.asm
-
-header-y += boot.h
-header-y += bootparam.h
-header-y += debugreg.h
-header-y += ldt.h
-header-y += msr-index.h
-header-y += prctl.h
-header-y += ptrace-abi.h
-header-y += sigcontext32.h
-header-y += ucontext.h
-header-y += processor-flags.h
-
-unifdef-y += e820.h
-unifdef-y += ist.h
-unifdef-y += mce.h
-unifdef-y += msr.h
-unifdef-y += mtrr.h
-unifdef-y += posix_types_32.h
-unifdef-y += posix_types_64.h
-unifdef-y += unistd_32.h
-unifdef-y += unistd_64.h
-unifdef-y += vm86.h
-unifdef-y += vsyscall.h
diff --git a/include/asm-x86/a.out-core.h b/include/asm-x86/a.out-core.h
deleted file mode 100644
index f5705761a37b..000000000000
--- a/include/asm-x86/a.out-core.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/* a.out coredump register dumper
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-
-#ifndef ASM_X86__A_OUT_CORE_H
-#define ASM_X86__A_OUT_CORE_H
-
-#ifdef __KERNEL__
-#ifdef CONFIG_X86_32
-
-#include <linux/user.h>
-#include <linux/elfcore.h>
-
-/*
- * fill in the user structure for an a.out core dump
- */
-static inline void aout_dump_thread(struct pt_regs *regs, struct user *dump)
-{
-	u16 gs;
-
-/* changed the size calculations - should hopefully work better. lbt */
-	dump->magic = CMAGIC;
-	dump->start_code = 0;
-	dump->start_stack = regs->sp & ~(PAGE_SIZE - 1);
-	dump->u_tsize = ((unsigned long)current->mm->end_code) >> PAGE_SHIFT;
-	dump->u_dsize = ((unsigned long)(current->mm->brk + (PAGE_SIZE - 1)))
-			>> PAGE_SHIFT;
-	dump->u_dsize -= dump->u_tsize;
-	dump->u_ssize = 0;
-	dump->u_debugreg[0] = current->thread.debugreg0;
-	dump->u_debugreg[1] = current->thread.debugreg1;
-	dump->u_debugreg[2] = current->thread.debugreg2;
-	dump->u_debugreg[3] = current->thread.debugreg3;
-	dump->u_debugreg[4] = 0;
-	dump->u_debugreg[5] = 0;
-	dump->u_debugreg[6] = current->thread.debugreg6;
-	dump->u_debugreg[7] = current->thread.debugreg7;
-
-	if (dump->start_stack < TASK_SIZE)
-		dump->u_ssize = ((unsigned long)(TASK_SIZE - dump->start_stack))
-				>> PAGE_SHIFT;
-
-	dump->regs.bx = regs->bx;
-	dump->regs.cx = regs->cx;
-	dump->regs.dx = regs->dx;
-	dump->regs.si = regs->si;
-	dump->regs.di = regs->di;
-	dump->regs.bp = regs->bp;
-	dump->regs.ax = regs->ax;
-	dump->regs.ds = (u16)regs->ds;
-	dump->regs.es = (u16)regs->es;
-	dump->regs.fs = (u16)regs->fs;
-	savesegment(gs, gs);
-	dump->regs.orig_ax = regs->orig_ax;
-	dump->regs.ip = regs->ip;
-	dump->regs.cs = (u16)regs->cs;
-	dump->regs.flags = regs->flags;
-	dump->regs.sp = regs->sp;
-	dump->regs.ss = (u16)regs->ss;
-
-	dump->u_fpvalid = dump_fpu(regs, &dump->i387);
-}
-
-#endif /* CONFIG_X86_32 */
-#endif /* __KERNEL__ */
-#endif /* ASM_X86__A_OUT_CORE_H */
diff --git a/include/asm-x86/a.out.h b/include/asm-x86/a.out.h
deleted file mode 100644
index 0948748bc69c..000000000000
--- a/include/asm-x86/a.out.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef ASM_X86__A_OUT_H
-#define ASM_X86__A_OUT_H
-
-struct exec
-{
-	unsigned int a_info;	/* Use macros N_MAGIC, etc for access */
-	unsigned a_text;	/* length of text, in bytes */
-	unsigned a_data;	/* length of data, in bytes */
-	unsigned a_bss;		/* length of uninitialized data area for file, in bytes */
-	unsigned a_syms;	/* length of symbol table data in file, in bytes */
-	unsigned a_entry;	/* start address */
-	unsigned a_trsize;	/* length of relocation info for text, in bytes */
-	unsigned a_drsize;	/* length of relocation info for data, in bytes */
-};
-
-#define N_TRSIZE(a)	((a).a_trsize)
-#define N_DRSIZE(a)	((a).a_drsize)
-#define N_SYMSIZE(a)	((a).a_syms)
-
-#endif /* ASM_X86__A_OUT_H */
diff --git a/include/asm-x86/acpi.h b/include/asm-x86/acpi.h
deleted file mode 100644
index 392e17336be1..000000000000
--- a/include/asm-x86/acpi.h
+++ /dev/null
@@ -1,178 +0,0 @@
-#ifndef ASM_X86__ACPI_H
-#define ASM_X86__ACPI_H
-
-/*
- *  Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
- *  Copyright (C) 2001 Patrick Mochel <mochel@osdl.org>
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- */
-#include <acpi/pdc_intel.h>
-
-#include <asm/numa.h>
-#include <asm/processor.h>
-#include <asm/mmu.h>
-#include <asm/mpspec.h>
-
-#define COMPILER_DEPENDENT_INT64   long long
-#define COMPILER_DEPENDENT_UINT64  unsigned long long
-
-/*
- * Calling conventions:
- *
- * ACPI_SYSTEM_XFACE        - Interfaces to host OS (handlers, threads)
- * ACPI_EXTERNAL_XFACE      - External ACPI interfaces
- * ACPI_INTERNAL_XFACE      - Internal ACPI interfaces
- * ACPI_INTERNAL_VAR_XFACE  - Internal variable-parameter list interfaces
- */
-#define ACPI_SYSTEM_XFACE
-#define ACPI_EXTERNAL_XFACE
-#define ACPI_INTERNAL_XFACE
-#define ACPI_INTERNAL_VAR_XFACE
-
-/* Asm macros */
-
-#define ACPI_ASM_MACROS
-#define BREAKPOINT3
-#define ACPI_DISABLE_IRQS() local_irq_disable()
-#define ACPI_ENABLE_IRQS()  local_irq_enable()
-#define ACPI_FLUSH_CPU_CACHE()	wbinvd()
-
-int __acpi_acquire_global_lock(unsigned int *lock);
-int __acpi_release_global_lock(unsigned int *lock);
-
-#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \
-	((Acq) = __acpi_acquire_global_lock(&facs->global_lock))
-
-#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \
-	((Acq) = __acpi_release_global_lock(&facs->global_lock))
-
-/*
- * Math helper asm macros
- */
-#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \
-	asm("divl %2;"				     \
-	    : "=a"(q32), "=d"(r32)		     \
-	    : "r"(d32),				     \
-	     "0"(n_lo), "1"(n_hi))
-
-
-#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \
-	asm("shrl   $1,%2	;"	\
-	    "rcrl   $1,%3;"		\
-	    : "=r"(n_hi), "=r"(n_lo)	\
-	    : "0"(n_hi), "1"(n_lo))
-
-#ifdef CONFIG_ACPI
-extern int acpi_lapic;
-extern int acpi_ioapic;
-extern int acpi_noirq;
-extern int acpi_strict;
-extern int acpi_disabled;
-extern int acpi_ht;
-extern int acpi_pci_disabled;
-extern int acpi_skip_timer_override;
-extern int acpi_use_timer_override;
-
-extern u8 acpi_sci_flags;
-extern int acpi_sci_override_gsi;
-void acpi_pic_sci_set_trigger(unsigned int, u16);
-
-static inline void disable_acpi(void)
-{
-	acpi_disabled = 1;
-	acpi_ht = 0;
-	acpi_pci_disabled = 1;
-	acpi_noirq = 1;
-}
-
-/* Fixmap pages to reserve for ACPI boot-time tables (see fixmap.h) */
-#define FIX_ACPI_PAGES 4
-
-extern int acpi_gsi_to_irq(u32 gsi, unsigned int *irq);
-
-static inline void acpi_noirq_set(void) { acpi_noirq = 1; }
-static inline void acpi_disable_pci(void)
-{
-	acpi_pci_disabled = 1;
-	acpi_noirq_set();
-}
-extern int acpi_irq_balance_set(char *str);
-
-/* routines for saving/restoring kernel state */
-extern int acpi_save_state_mem(void);
-extern void acpi_restore_state_mem(void);
-
-extern unsigned long acpi_wakeup_address;
-
-/* early initialization routine */
-extern void acpi_reserve_bootmem(void);
-
-/*
- * Check if the CPU can handle C2 and deeper
- */
-static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
-{
-	/*
-	 * Early models (<=5) of AMD Opterons are not supposed to go into
-	 * C2 state.
-	 *
-	 * Steppings 0x0A and later are good
-	 */
-	if (boot_cpu_data.x86 == 0x0F &&
-	    boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
-	    boot_cpu_data.x86_model <= 0x05 &&
-	    boot_cpu_data.x86_mask < 0x0A)
-		return 1;
-	else if (boot_cpu_has(X86_FEATURE_AMDC1E))
-		return 1;
-	else
-		return max_cstate;
-}
-
-#else /* !CONFIG_ACPI */
-
-#define acpi_lapic 0
-#define acpi_ioapic 0
-static inline void acpi_noirq_set(void) { }
-static inline void acpi_disable_pci(void) { }
-static inline void disable_acpi(void) { }
-
-#endif /* !CONFIG_ACPI */
-
-#define ARCH_HAS_POWER_INIT	1
-
-struct bootnode;
-
-#ifdef CONFIG_ACPI_NUMA
-extern int acpi_numa;
-extern int acpi_scan_nodes(unsigned long start, unsigned long end);
-#define NR_NODE_MEMBLKS (MAX_NUMNODES*2)
-extern void acpi_fake_nodes(const struct bootnode *fake_nodes,
-				   int num_nodes);
-#else
-static inline void acpi_fake_nodes(const struct bootnode *fake_nodes,
-				   int num_nodes)
-{
-}
-#endif
-
-#define acpi_unlazy_tlb(x)	leave_mm(x)
-
-#endif /* ASM_X86__ACPI_H */
diff --git a/include/asm-x86/agp.h b/include/asm-x86/agp.h
deleted file mode 100644
index 3617fd4fcdf9..000000000000
--- a/include/asm-x86/agp.h
+++ /dev/null
@@ -1,35 +0,0 @@
-#ifndef ASM_X86__AGP_H
-#define ASM_X86__AGP_H
-
-#include <asm/pgtable.h>
-#include <asm/cacheflush.h>
-
-/*
- * Functions to keep the agpgart mappings coherent with the MMU. The
- * GART gives the CPU a physical alias of pages in memory. The alias
- * region is mapped uncacheable. Make sure there are no conflicting
- * mappings with different cachability attributes for the same
- * page. This avoids data corruption on some CPUs.
- */
-
-#define map_page_into_agp(page) set_pages_uc(page, 1)
-#define unmap_page_from_agp(page) set_pages_wb(page, 1)
-
-/*
- * Could use CLFLUSH here if the cpu supports it. But then it would
- * need to be called for each cacheline of the whole page so it may
- * not be worth it. Would need a page for it.
- */
-#define flush_agp_cache() wbinvd()
-
-/* Convert a physical address to an address suitable for the GART. */
-#define phys_to_gart(x) (x)
-#define gart_to_phys(x) (x)
-
-/* GATT allocation. Returns/accepts GATT kernel virtual address. */
-#define alloc_gatt_pages(order)		\
-	((char *)__get_free_pages(GFP_KERNEL, (order)))
-#define free_gatt_pages(table, order)	\
-	free_pages((unsigned long)(table), (order))
-
-#endif /* ASM_X86__AGP_H */
diff --git a/include/asm-x86/alternative-asm.h b/include/asm-x86/alternative-asm.h
deleted file mode 100644
index e2077d343c33..000000000000
--- a/include/asm-x86/alternative-asm.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifdef __ASSEMBLY__
-
-#ifdef CONFIG_X86_32
-# define X86_ALIGN .long
-#else
-# define X86_ALIGN .quad
-#endif
-
-#ifdef CONFIG_SMP
-	.macro LOCK_PREFIX
-1:	lock
-	.section .smp_locks,"a"
-	.align 4
-	X86_ALIGN 1b
-	.previous
-	.endm
-#else
-	.macro LOCK_PREFIX
-	.endm
-#endif
-
-#endif  /*  __ASSEMBLY__  */
diff --git a/include/asm-x86/alternative.h b/include/asm-x86/alternative.h
deleted file mode 100644
index 22d3c9862bf3..000000000000
--- a/include/asm-x86/alternative.h
+++ /dev/null
@@ -1,183 +0,0 @@
-#ifndef ASM_X86__ALTERNATIVE_H
-#define ASM_X86__ALTERNATIVE_H
-
-#include <linux/types.h>
-#include <linux/stddef.h>
-#include <asm/asm.h>
-
-/*
- * Alternative inline assembly for SMP.
- *
- * The LOCK_PREFIX macro defined here replaces the LOCK and
- * LOCK_PREFIX macros used everywhere in the source tree.
- *
- * SMP alternatives use the same data structures as the other
- * alternatives and the X86_FEATURE_UP flag to indicate the case of a
- * UP system running a SMP kernel.  The existing apply_alternatives()
- * works fine for patching a SMP kernel for UP.
- *
- * The SMP alternative tables can be kept after boot and contain both
- * UP and SMP versions of the instructions to allow switching back to
- * SMP at runtime, when hotplugging in a new CPU, which is especially
- * useful in virtualized environments.
- *
- * The very common lock prefix is handled as special case in a
- * separate table which is a pure address list without replacement ptr
- * and size information.  That keeps the table sizes small.
- */
-
-#ifdef CONFIG_SMP
-#define LOCK_PREFIX \
-		".section .smp_locks,\"a\"\n"	\
-		_ASM_ALIGN "\n"			\
-		_ASM_PTR "661f\n" /* address */	\
-		".previous\n"			\
-		"661:\n\tlock; "
-
-#else /* ! CONFIG_SMP */
-#define LOCK_PREFIX ""
-#endif
-
-/* This must be included *after* the definition of LOCK_PREFIX */
-#include <asm/cpufeature.h>
-
-struct alt_instr {
-	u8 *instr;		/* original instruction */
-	u8 *replacement;
-	u8  cpuid;		/* cpuid bit set for replacement */
-	u8  instrlen;		/* length of original instruction */
-	u8  replacementlen;	/* length of new instruction, <= instrlen */
-	u8  pad1;
-#ifdef CONFIG_X86_64
-	u32 pad2;
-#endif
-};
-
-extern void alternative_instructions(void);
-extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end);
-
-struct module;
-
-#ifdef CONFIG_SMP
-extern void alternatives_smp_module_add(struct module *mod, char *name,
-					void *locks, void *locks_end,
-					void *text, void *text_end);
-extern void alternatives_smp_module_del(struct module *mod);
-extern void alternatives_smp_switch(int smp);
-#else
-static inline void alternatives_smp_module_add(struct module *mod, char *name,
-					       void *locks, void *locks_end,
-					       void *text, void *text_end) {}
-static inline void alternatives_smp_module_del(struct module *mod) {}
-static inline void alternatives_smp_switch(int smp) {}
-#endif	/* CONFIG_SMP */
-
-const unsigned char *const *find_nop_table(void);
-
-/*
- * Alternative instructions for different CPU types or capabilities.
- *
- * This allows to use optimized instructions even on generic binary
- * kernels.
- *
- * length of oldinstr must be longer or equal the length of newinstr
- * It can be padded with nops as needed.
- *
- * For non barrier like inlines please define new variants
- * without volatile and memory clobber.
- */
-#define alternative(oldinstr, newinstr, feature)			\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c0\n"		/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */	\
-		      ".previous" :: "i" (feature) : "memory")
-
-/*
- * Alternative inline assembly with input.
- *
- * Pecularities:
- * No memory clobber here.
- * Argument numbers start with 1.
- * Best is to use constraints that are fixed size (like (%1) ... "r")
- * If you use variable sized constraints like "m" or "g" in the
- * replacement make sure to pad to the worst case length.
- */
-#define alternative_input(oldinstr, newinstr, feature, input...)	\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c0\n"		/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */	\
-		      ".previous" :: "i" (feature), ##input)
-
-/* Like alternative_input, but with a single output argument */
-#define alternative_io(oldinstr, newinstr, feature, output, input...)	\
-	asm volatile ("661:\n\t" oldinstr "\n662:\n"			\
-		      ".section .altinstructions,\"a\"\n"		\
-		      _ASM_ALIGN "\n"					\
-		      _ASM_PTR "661b\n"		/* label */		\
-		      _ASM_PTR "663f\n"		/* new instruction */	\
-		      "	 .byte %c[feat]\n"	/* feature bit */	\
-		      "	 .byte 662b-661b\n"	/* sourcelen */		\
-		      "	 .byte 664f-663f\n"	/* replacementlen */	\
-		      ".previous\n"					\
-		      ".section .altinstr_replacement,\"ax\"\n"		\
-		      "663:\n\t" newinstr "\n664:\n"  /* replacement */ \
-		      ".previous" : output : [feat] "i" (feature), ##input)
-
-/*
- * use this macro(s) if you need more than one output parameter
- * in alternative_io
- */
-#define ASM_OUTPUT2(a, b) a, b
-
-struct paravirt_patch_site;
-#ifdef CONFIG_PARAVIRT
-void apply_paravirt(struct paravirt_patch_site *start,
-		    struct paravirt_patch_site *end);
-#else
-static inline void apply_paravirt(struct paravirt_patch_site *start,
-				  struct paravirt_patch_site *end)
-{}
-#define __parainstructions	NULL
-#define __parainstructions_end	NULL
-#endif
-
-extern void add_nops(void *insns, unsigned int len);
-
-/*
- * Clear and restore the kernel write-protection flag on the local CPU.
- * Allows the kernel to edit read-only pages.
- * Side-effect: any interrupt handler running between save and restore will have
- * the ability to write to read-only pages.
- *
- * Warning:
- * Code patching in the UP case is safe if NMIs and MCE handlers are stopped and
- * no thread can be preempted in the instructions being modified (no iret to an
- * invalid instruction possible) or if the instructions are changed from a
- * consistent state to another consistent state atomically.
- * More care must be taken when modifying code in the SMP case because of
- * Intel's errata.
- * On the local CPU you need to be protected again NMI or MCE handlers seeing an
- * inconsistent instruction while you patch.
- * The _early version expects the memory to already be RW.
- */
-
-extern void *text_poke(void *addr, const void *opcode, size_t len);
-extern void *text_poke_early(void *addr, const void *opcode, size_t len);
-
-#endif /* ASM_X86__ALTERNATIVE_H */
diff --git a/include/asm-x86/amd_iommu.h b/include/asm-x86/amd_iommu.h
deleted file mode 100644
index 041d0db7da27..000000000000
--- a/include/asm-x86/amd_iommu.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
- *         Leo Duran <leo.duran@amd.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#ifndef ASM_X86__AMD_IOMMU_H
-#define ASM_X86__AMD_IOMMU_H
-
-#include <linux/irqreturn.h>
-
-#ifdef CONFIG_AMD_IOMMU
-extern int amd_iommu_init(void);
-extern int amd_iommu_init_dma_ops(void);
-extern void amd_iommu_detect(void);
-extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
-#else
-static inline int amd_iommu_init(void) { return -ENODEV; }
-static inline void amd_iommu_detect(void) { }
-#endif
-
-#endif /* ASM_X86__AMD_IOMMU_H */
diff --git a/include/asm-x86/amd_iommu_types.h b/include/asm-x86/amd_iommu_types.h
deleted file mode 100644
index b3085869a17b..000000000000
--- a/include/asm-x86/amd_iommu_types.h
+++ /dev/null
@@ -1,404 +0,0 @@
-/*
- * Copyright (C) 2007-2008 Advanced Micro Devices, Inc.
- * Author: Joerg Roedel <joerg.roedel@amd.com>
- *         Leo Duran <leo.duran@amd.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License version 2 as published
- * by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#ifndef ASM_X86__AMD_IOMMU_TYPES_H
-#define ASM_X86__AMD_IOMMU_TYPES_H
-
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-/*
- * some size calculation constants
- */
-#define DEV_TABLE_ENTRY_SIZE		32
-#define ALIAS_TABLE_ENTRY_SIZE		2
-#define RLOOKUP_TABLE_ENTRY_SIZE	(sizeof(void *))
-
-/* Length of the MMIO region for the AMD IOMMU */
-#define MMIO_REGION_LENGTH       0x4000
-
-/* Capability offsets used by the driver */
-#define MMIO_CAP_HDR_OFFSET	0x00
-#define MMIO_RANGE_OFFSET	0x0c
-#define MMIO_MISC_OFFSET	0x10
-
-/* Masks, shifts and macros to parse the device range capability */
-#define MMIO_RANGE_LD_MASK	0xff000000
-#define MMIO_RANGE_FD_MASK	0x00ff0000
-#define MMIO_RANGE_BUS_MASK	0x0000ff00
-#define MMIO_RANGE_LD_SHIFT	24
-#define MMIO_RANGE_FD_SHIFT	16
-#define MMIO_RANGE_BUS_SHIFT	8
-#define MMIO_GET_LD(x)  (((x) & MMIO_RANGE_LD_MASK) >> MMIO_RANGE_LD_SHIFT)
-#define MMIO_GET_FD(x)  (((x) & MMIO_RANGE_FD_MASK) >> MMIO_RANGE_FD_SHIFT)
-#define MMIO_GET_BUS(x) (((x) & MMIO_RANGE_BUS_MASK) >> MMIO_RANGE_BUS_SHIFT)
-#define MMIO_MSI_NUM(x)	((x) & 0x1f)
-
-/* Flag masks for the AMD IOMMU exclusion range */
-#define MMIO_EXCL_ENABLE_MASK 0x01ULL
-#define MMIO_EXCL_ALLOW_MASK  0x02ULL
-
-/* Used offsets into the MMIO space */
-#define MMIO_DEV_TABLE_OFFSET   0x0000
-#define MMIO_CMD_BUF_OFFSET     0x0008
-#define MMIO_EVT_BUF_OFFSET     0x0010
-#define MMIO_CONTROL_OFFSET     0x0018
-#define MMIO_EXCL_BASE_OFFSET   0x0020
-#define MMIO_EXCL_LIMIT_OFFSET  0x0028
-#define MMIO_CMD_HEAD_OFFSET	0x2000
-#define MMIO_CMD_TAIL_OFFSET	0x2008
-#define MMIO_EVT_HEAD_OFFSET	0x2010
-#define MMIO_EVT_TAIL_OFFSET	0x2018
-#define MMIO_STATUS_OFFSET	0x2020
-
-/* MMIO status bits */
-#define MMIO_STATUS_COM_WAIT_INT_MASK	0x04
-
-/* event logging constants */
-#define EVENT_ENTRY_SIZE	0x10
-#define EVENT_TYPE_SHIFT	28
-#define EVENT_TYPE_MASK		0xf
-#define EVENT_TYPE_ILL_DEV	0x1
-#define EVENT_TYPE_IO_FAULT	0x2
-#define EVENT_TYPE_DEV_TAB_ERR	0x3
-#define EVENT_TYPE_PAGE_TAB_ERR	0x4
-#define EVENT_TYPE_ILL_CMD	0x5
-#define EVENT_TYPE_CMD_HARD_ERR	0x6
-#define EVENT_TYPE_IOTLB_INV_TO	0x7
-#define EVENT_TYPE_INV_DEV_REQ	0x8
-#define EVENT_DEVID_MASK	0xffff
-#define EVENT_DEVID_SHIFT	0
-#define EVENT_DOMID_MASK	0xffff
-#define EVENT_DOMID_SHIFT	0
-#define EVENT_FLAGS_MASK	0xfff
-#define EVENT_FLAGS_SHIFT	0x10
-
-/* feature control bits */
-#define CONTROL_IOMMU_EN        0x00ULL
-#define CONTROL_HT_TUN_EN       0x01ULL
-#define CONTROL_EVT_LOG_EN      0x02ULL
-#define CONTROL_EVT_INT_EN      0x03ULL
-#define CONTROL_COMWAIT_EN      0x04ULL
-#define CONTROL_PASSPW_EN       0x08ULL
-#define CONTROL_RESPASSPW_EN    0x09ULL
-#define CONTROL_COHERENT_EN     0x0aULL
-#define CONTROL_ISOC_EN         0x0bULL
-#define CONTROL_CMDBUF_EN       0x0cULL
-#define CONTROL_PPFLOG_EN       0x0dULL
-#define CONTROL_PPFINT_EN       0x0eULL
-
-/* command specific defines */
-#define CMD_COMPL_WAIT          0x01
-#define CMD_INV_DEV_ENTRY       0x02
-#define CMD_INV_IOMMU_PAGES     0x03
-
-#define CMD_COMPL_WAIT_STORE_MASK	0x01
-#define CMD_COMPL_WAIT_INT_MASK		0x02
-#define CMD_INV_IOMMU_PAGES_SIZE_MASK	0x01
-#define CMD_INV_IOMMU_PAGES_PDE_MASK	0x02
-
-#define CMD_INV_IOMMU_ALL_PAGES_ADDRESS	0x7fffffffffffffffULL
-
-/* macros and definitions for device table entries */
-#define DEV_ENTRY_VALID         0x00
-#define DEV_ENTRY_TRANSLATION   0x01
-#define DEV_ENTRY_IR            0x3d
-#define DEV_ENTRY_IW            0x3e
-#define DEV_ENTRY_NO_PAGE_FAULT	0x62
-#define DEV_ENTRY_EX            0x67
-#define DEV_ENTRY_SYSMGT1       0x68
-#define DEV_ENTRY_SYSMGT2       0x69
-#define DEV_ENTRY_INIT_PASS     0xb8
-#define DEV_ENTRY_EINT_PASS     0xb9
-#define DEV_ENTRY_NMI_PASS      0xba
-#define DEV_ENTRY_LINT0_PASS    0xbe
-#define DEV_ENTRY_LINT1_PASS    0xbf
-#define DEV_ENTRY_MODE_MASK	0x07
-#define DEV_ENTRY_MODE_SHIFT	0x09
-
-/* constants to configure the command buffer */
-#define CMD_BUFFER_SIZE    8192
-#define CMD_BUFFER_ENTRIES 512
-#define MMIO_CMD_SIZE_SHIFT 56
-#define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT)
-
-/* constants for event buffer handling */
-#define EVT_BUFFER_SIZE		8192 /* 512 entries */
-#define EVT_LEN_MASK		(0x9ULL << 56)
-
-#define PAGE_MODE_1_LEVEL 0x01
-#define PAGE_MODE_2_LEVEL 0x02
-#define PAGE_MODE_3_LEVEL 0x03
-
-#define IOMMU_PDE_NL_0   0x000ULL
-#define IOMMU_PDE_NL_1   0x200ULL
-#define IOMMU_PDE_NL_2   0x400ULL
-#define IOMMU_PDE_NL_3   0x600ULL
-
-#define IOMMU_PTE_L2_INDEX(address) (((address) >> 30) & 0x1ffULL)
-#define IOMMU_PTE_L1_INDEX(address) (((address) >> 21) & 0x1ffULL)
-#define IOMMU_PTE_L0_INDEX(address) (((address) >> 12) & 0x1ffULL)
-
-#define IOMMU_MAP_SIZE_L1 (1ULL << 21)
-#define IOMMU_MAP_SIZE_L2 (1ULL << 30)
-#define IOMMU_MAP_SIZE_L3 (1ULL << 39)
-
-#define IOMMU_PTE_P  (1ULL << 0)
-#define IOMMU_PTE_TV (1ULL << 1)
-#define IOMMU_PTE_U  (1ULL << 59)
-#define IOMMU_PTE_FC (1ULL << 60)
-#define IOMMU_PTE_IR (1ULL << 61)
-#define IOMMU_PTE_IW (1ULL << 62)
-
-#define IOMMU_L1_PDE(address) \
-	((address) | IOMMU_PDE_NL_1 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
-#define IOMMU_L2_PDE(address) \
-	((address) | IOMMU_PDE_NL_2 | IOMMU_PTE_P | IOMMU_PTE_IR | IOMMU_PTE_IW)
-
-#define IOMMU_PAGE_MASK (((1ULL << 52) - 1) & ~0xfffULL)
-#define IOMMU_PTE_PRESENT(pte) ((pte) & IOMMU_PTE_P)
-#define IOMMU_PTE_PAGE(pte) (phys_to_virt((pte) & IOMMU_PAGE_MASK))
-#define IOMMU_PTE_MODE(pte) (((pte) >> 9) & 0x07)
-
-#define IOMMU_PROT_MASK 0x03
-#define IOMMU_PROT_IR 0x01
-#define IOMMU_PROT_IW 0x02
-
-/* IOMMU capabilities */
-#define IOMMU_CAP_IOTLB   24
-#define IOMMU_CAP_NPCACHE 26
-
-#define MAX_DOMAIN_ID 65536
-
-/* FIXME: move this macro to <linux/pci.h> */
-#define PCI_BUS(x) (((x) >> 8) & 0xff)
-
-/*
- * This structure contains generic data for  IOMMU protection domains
- * independent of their use.
- */
-struct protection_domain {
-	spinlock_t lock; /* mostly used to lock the page table*/
-	u16 id;		 /* the domain id written to the device table */
-	int mode;	 /* paging mode (0-6 levels) */
-	u64 *pt_root;	 /* page table root pointer */
-	void *priv;	 /* private data */
-};
-
-/*
- * Data container for a dma_ops specific protection domain
- */
-struct dma_ops_domain {
-	struct list_head list;
-
-	/* generic protection domain information */
-	struct protection_domain domain;
-
-	/* size of the aperture for the mappings */
-	unsigned long aperture_size;
-
-	/* address we start to search for free addresses */
-	unsigned long next_bit;
-
-	/* address allocation bitmap */
-	unsigned long *bitmap;
-
-	/*
-	 * Array of PTE pages for the aperture. In this array we save all the
-	 * leaf pages of the domain page table used for the aperture. This way
-	 * we don't need to walk the page table to find a specific PTE. We can
-	 * just calculate its address in constant time.
-	 */
-	u64 **pte_pages;
-
-	/* This will be set to true when TLB needs to be flushed */
-	bool need_flush;
-
-	/*
-	 * if this is a preallocated domain, keep the device for which it was
-	 * preallocated in this variable
-	 */
-	u16 target_dev;
-};
-
-/*
- * Structure where we save information about one hardware AMD IOMMU in the
- * system.
- */
-struct amd_iommu {
-	struct list_head list;
-
-	/* locks the accesses to the hardware */
-	spinlock_t lock;
-
-	/* Pointer to PCI device of this IOMMU */
-	struct pci_dev *dev;
-
-	/*
-	 * Capability pointer. There could be more than one IOMMU per PCI
-	 * device function if there are more than one AMD IOMMU capability
-	 * pointers.
-	 */
-	u16 cap_ptr;
-
-	/* physical address of MMIO space */
-	u64 mmio_phys;
-	/* virtual address of MMIO space */
-	u8 *mmio_base;
-
-	/* capabilities of that IOMMU read from ACPI */
-	u32 cap;
-
-	/* pci domain of this IOMMU */
-	u16 pci_seg;
-
-	/* first device this IOMMU handles. read from PCI */
-	u16 first_device;
-	/* last device this IOMMU handles. read from PCI */
-	u16 last_device;
-
-	/* start of exclusion range of that IOMMU */
-	u64 exclusion_start;
-	/* length of exclusion range of that IOMMU */
-	u64 exclusion_length;
-
-	/* command buffer virtual address */
-	u8 *cmd_buf;
-	/* size of command buffer */
-	u32 cmd_buf_size;
-
-	/* event buffer virtual address */
-	u8 *evt_buf;
-	/* size of event buffer */
-	u32 evt_buf_size;
-	/* MSI number for event interrupt */
-	u16 evt_msi_num;
-
-	/* if one, we need to send a completion wait command */
-	int need_sync;
-
-	/* true if interrupts for this IOMMU are already enabled */
-	bool int_enabled;
-
-	/* default dma_ops domain for that IOMMU */
-	struct dma_ops_domain *default_dom;
-};
-
-/*
- * List with all IOMMUs in the system. This list is not locked because it is
- * only written and read at driver initialization or suspend time
- */
-extern struct list_head amd_iommu_list;
-
-/*
- * Structure defining one entry in the device table
- */
-struct dev_table_entry {
-	u32 data[8];
-};
-
-/*
- * One entry for unity mappings parsed out of the ACPI table.
- */
-struct unity_map_entry {
-	struct list_head list;
-
-	/* starting device id this entry is used for (including) */
-	u16 devid_start;
-	/* end device id this entry is used for (including) */
-	u16 devid_end;
-
-	/* start address to unity map (including) */
-	u64 address_start;
-	/* end address to unity map (including) */
-	u64 address_end;
-
-	/* required protection */
-	int prot;
-};
-
-/*
- * List of all unity mappings. It is not locked because as runtime it is only
- * read. It is created at ACPI table parsing time.
- */
-extern struct list_head amd_iommu_unity_map;
-
-/*
- * Data structures for device handling
- */
-
-/*
- * Device table used by hardware. Read and write accesses by software are
- * locked with the amd_iommu_pd_table lock.
- */
-extern struct dev_table_entry *amd_iommu_dev_table;
-
-/*
- * Alias table to find requestor ids to device ids. Not locked because only
- * read on runtime.
- */
-extern u16 *amd_iommu_alias_table;
-
-/*
- * Reverse lookup table to find the IOMMU which translates a specific device.
- */
-extern struct amd_iommu **amd_iommu_rlookup_table;
-
-/* size of the dma_ops aperture as power of 2 */
-extern unsigned amd_iommu_aperture_order;
-
-/* largest PCI device id we expect translation requests for */
-extern u16 amd_iommu_last_bdf;
-
-/* data structures for protection domain handling */
-extern struct protection_domain **amd_iommu_pd_table;
-
-/* allocation bitmap for domain ids */
-extern unsigned long *amd_iommu_pd_alloc_bitmap;
-
-/* will be 1 if device isolation is enabled */
-extern int amd_iommu_isolate;
-
-/*
- * If true, the addresses will be flushed on unmap time, not when
- * they are reused
- */
-extern bool amd_iommu_unmap_flush;
-
-/* takes a PCI device id and prints it out in a readable form */
-static inline void print_devid(u16 devid, int nl)
-{
-	int bus = devid >> 8;
-	int dev = devid >> 3 & 0x1f;
-	int fn  = devid & 0x07;
-
-	printk("%02x:%02x.%x", bus, dev, fn);
-	if (nl)
-		printk("\n");
-}
-
-/* takes bus and device/function and returns the device id
- * FIXME: should that be in generic PCI code? */
-static inline u16 calc_devid(u8 bus, u8 devfn)
-{
-	return (((u16)bus) << 8) | devfn;
-}
-
-#endif /* ASM_X86__AMD_IOMMU_TYPES_H */
diff --git a/include/asm-x86/apic.h b/include/asm-x86/apic.h
deleted file mode 100644
index ef1d72dbdfe0..000000000000
--- a/include/asm-x86/apic.h
+++ /dev/null
@@ -1,199 +0,0 @@
-#ifndef ASM_X86__APIC_H
-#define ASM_X86__APIC_H
-
-#include <linux/pm.h>
-#include <linux/delay.h>
-
-#include <asm/alternative.h>
-#include <asm/fixmap.h>
-#include <asm/apicdef.h>
-#include <asm/processor.h>
-#include <asm/system.h>
-#include <asm/cpufeature.h>
-#include <asm/msr.h>
-
-#define ARCH_APICTIMER_STOPS_ON_C3	1
-
-/*
- * Debugging macros
- */
-#define APIC_QUIET   0
-#define APIC_VERBOSE 1
-#define APIC_DEBUG   2
-
-/*
- * Define the default level of output to be very little
- * This can be turned up by using apic=verbose for more
- * information and apic=debug for _lots_ of information.
- * apic_verbosity is defined in apic.c
- */
-#define apic_printk(v, s, a...) do {       \
-		if ((v) <= apic_verbosity) \
-			printk(s, ##a);    \
-	} while (0)
-
-
-extern void generic_apic_probe(void);
-
-#ifdef CONFIG_X86_LOCAL_APIC
-
-extern unsigned int apic_verbosity;
-extern int local_apic_timer_c2_ok;
-
-extern int disable_apic;
-/*
- * Basic functions accessing APICs.
- */
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-#define setup_boot_clock setup_boot_APIC_clock
-#define setup_secondary_clock setup_secondary_APIC_clock
-#endif
-
-extern int is_vsmp_box(void);
-extern void xapic_wait_icr_idle(void);
-extern u32 safe_xapic_wait_icr_idle(void);
-extern u64 xapic_icr_read(void);
-extern void xapic_icr_write(u32, u32);
-extern int setup_profiling_timer(unsigned int);
-
-static inline void native_apic_mem_write(u32 reg, u32 v)
-{
-	volatile u32 *addr = (volatile u32 *)(APIC_BASE + reg);
-
-	alternative_io("movl %0, %1", "xchgl %0, %1", X86_FEATURE_11AP,
-		       ASM_OUTPUT2("=r" (v), "=m" (*addr)),
-		       ASM_OUTPUT2("0" (v), "m" (*addr)));
-}
-
-static inline u32 native_apic_mem_read(u32 reg)
-{
-	return *((volatile u32 *)(APIC_BASE + reg));
-}
-
-static inline void native_apic_msr_write(u32 reg, u32 v)
-{
-	if (reg == APIC_DFR || reg == APIC_ID || reg == APIC_LDR ||
-	    reg == APIC_LVR)
-		return;
-
-	wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0);
-}
-
-static inline u32 native_apic_msr_read(u32 reg)
-{
-	u32 low, high;
-
-	if (reg == APIC_DFR)
-		return -1;
-
-	rdmsr(APIC_BASE_MSR + (reg >> 4), low, high);
-	return low;
-}
-
-#ifndef CONFIG_X86_32
-extern int x2apic, x2apic_preenabled;
-extern void check_x2apic(void);
-extern void enable_x2apic(void);
-extern void enable_IR_x2apic(void);
-extern void x2apic_icr_write(u32 low, u32 id);
-static inline int x2apic_enabled(void)
-{
-	int msr, msr2;
-
-	if (!cpu_has_x2apic)
-		return 0;
-
-	rdmsr(MSR_IA32_APICBASE, msr, msr2);
-	if (msr & X2APIC_ENABLE)
-		return 1;
-	return 0;
-}
-#else
-#define x2apic_enabled()	0
-#endif
-
-struct apic_ops {
-	u32 (*read)(u32 reg);
-	void (*write)(u32 reg, u32 v);
-	u64 (*icr_read)(void);
-	void (*icr_write)(u32 low, u32 high);
-	void (*wait_icr_idle)(void);
-	u32 (*safe_wait_icr_idle)(void);
-};
-
-extern struct apic_ops *apic_ops;
-
-#define apic_read (apic_ops->read)
-#define apic_write (apic_ops->write)
-#define apic_icr_read (apic_ops->icr_read)
-#define apic_icr_write (apic_ops->icr_write)
-#define apic_wait_icr_idle (apic_ops->wait_icr_idle)
-#define safe_apic_wait_icr_idle (apic_ops->safe_wait_icr_idle)
-
-extern int get_physical_broadcast(void);
-
-#ifdef CONFIG_X86_64
-static inline void ack_x2APIC_irq(void)
-{
-	/* Docs say use 0 for future compatibility */
-	native_apic_msr_write(APIC_EOI, 0);
-}
-#endif
-
-
-static inline void ack_APIC_irq(void)
-{
-	/*
-	 * ack_APIC_irq() actually gets compiled as a single instruction
-	 * ... yummie.
-	 */
-
-	/* Docs say use 0 for future compatibility */
-	apic_write(APIC_EOI, 0);
-}
-
-extern int lapic_get_maxlvt(void);
-extern void clear_local_APIC(void);
-extern void connect_bsp_APIC(void);
-extern void disconnect_bsp_APIC(int virt_wire_setup);
-extern void disable_local_APIC(void);
-extern void lapic_shutdown(void);
-extern int verify_local_APIC(void);
-extern void cache_APIC_registers(void);
-extern void sync_Arb_IDs(void);
-extern void init_bsp_APIC(void);
-extern void setup_local_APIC(void);
-extern void end_local_APIC_setup(void);
-extern void init_apic_mappings(void);
-extern void setup_boot_APIC_clock(void);
-extern void setup_secondary_APIC_clock(void);
-extern int APIC_init_uniprocessor(void);
-extern void enable_NMI_through_LVT0(void);
-
-/*
- * On 32bit this is mach-xxx local
- */
-#ifdef CONFIG_X86_64
-extern void early_init_lapic_mapping(void);
-extern int apic_is_clustered_box(void);
-#else
-static inline int apic_is_clustered_box(void)
-{
-	return 0;
-}
-#endif
-
-extern u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask);
-extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
-
-
-#else /* !CONFIG_X86_LOCAL_APIC */
-static inline void lapic_shutdown(void) { }
-#define local_apic_timer_c2_ok		1
-static inline void init_apic_mappings(void) { }
-
-#endif /* !CONFIG_X86_LOCAL_APIC */
-
-#endif /* ASM_X86__APIC_H */
diff --git a/include/asm-x86/apicdef.h b/include/asm-x86/apicdef.h
deleted file mode 100644
index b922c85ac91d..000000000000
--- a/include/asm-x86/apicdef.h
+++ /dev/null
@@ -1,417 +0,0 @@
-#ifndef ASM_X86__APICDEF_H
-#define ASM_X86__APICDEF_H
-
-/*
- * Constants for various Intel APICs. (local APIC, IOAPIC, etc.)
- *
- * Alan Cox <Alan.Cox@linux.org>, 1995.
- * Ingo Molnar <mingo@redhat.com>, 1999, 2000
- */
-
-#define	APIC_DEFAULT_PHYS_BASE	0xfee00000
-
-#define	APIC_ID		0x20
-
-#define	APIC_LVR	0x30
-#define		APIC_LVR_MASK		0xFF00FF
-#define		GET_APIC_VERSION(x)	((x) & 0xFFu)
-#define		GET_APIC_MAXLVT(x)	(((x) >> 16) & 0xFFu)
-#ifdef CONFIG_X86_32
-#  define	APIC_INTEGRATED(x)	((x) & 0xF0u)
-#else
-#  define	APIC_INTEGRATED(x)	(1)
-#endif
-#define		APIC_XAPIC(x)		((x) >= 0x14)
-#define	APIC_TASKPRI	0x80
-#define		APIC_TPRI_MASK		0xFFu
-#define	APIC_ARBPRI	0x90
-#define		APIC_ARBPRI_MASK	0xFFu
-#define	APIC_PROCPRI	0xA0
-#define	APIC_EOI	0xB0
-#define		APIC_EIO_ACK		0x0
-#define	APIC_RRR	0xC0
-#define	APIC_LDR	0xD0
-#define		APIC_LDR_MASK		(0xFFu << 24)
-#define		GET_APIC_LOGICAL_ID(x)	(((x) >> 24) & 0xFFu)
-#define		SET_APIC_LOGICAL_ID(x)	(((x) << 24))
-#define		APIC_ALL_CPUS		0xFFu
-#define	APIC_DFR	0xE0
-#define		APIC_DFR_CLUSTER		0x0FFFFFFFul
-#define		APIC_DFR_FLAT			0xFFFFFFFFul
-#define	APIC_SPIV	0xF0
-#define		APIC_SPIV_FOCUS_DISABLED	(1 << 9)
-#define		APIC_SPIV_APIC_ENABLED		(1 << 8)
-#define	APIC_ISR	0x100
-#define	APIC_ISR_NR     0x8     /* Number of 32 bit ISR registers. */
-#define	APIC_TMR	0x180
-#define	APIC_IRR	0x200
-#define	APIC_ESR	0x280
-#define		APIC_ESR_SEND_CS	0x00001
-#define		APIC_ESR_RECV_CS	0x00002
-#define		APIC_ESR_SEND_ACC	0x00004
-#define		APIC_ESR_RECV_ACC	0x00008
-#define		APIC_ESR_SENDILL	0x00020
-#define		APIC_ESR_RECVILL	0x00040
-#define		APIC_ESR_ILLREGA	0x00080
-#define	APIC_ICR	0x300
-#define		APIC_DEST_SELF		0x40000
-#define		APIC_DEST_ALLINC	0x80000
-#define		APIC_DEST_ALLBUT	0xC0000
-#define		APIC_ICR_RR_MASK	0x30000
-#define		APIC_ICR_RR_INVALID	0x00000
-#define		APIC_ICR_RR_INPROG	0x10000
-#define		APIC_ICR_RR_VALID	0x20000
-#define		APIC_INT_LEVELTRIG	0x08000
-#define		APIC_INT_ASSERT		0x04000
-#define		APIC_ICR_BUSY		0x01000
-#define		APIC_DEST_LOGICAL	0x00800
-#define		APIC_DEST_PHYSICAL	0x00000
-#define		APIC_DM_FIXED		0x00000
-#define		APIC_DM_LOWEST		0x00100
-#define		APIC_DM_SMI		0x00200
-#define		APIC_DM_REMRD		0x00300
-#define		APIC_DM_NMI		0x00400
-#define		APIC_DM_INIT		0x00500
-#define		APIC_DM_STARTUP		0x00600
-#define		APIC_DM_EXTINT		0x00700
-#define		APIC_VECTOR_MASK	0x000FF
-#define	APIC_ICR2	0x310
-#define		GET_APIC_DEST_FIELD(x)	(((x) >> 24) & 0xFF)
-#define		SET_APIC_DEST_FIELD(x)	((x) << 24)
-#define	APIC_LVTT	0x320
-#define	APIC_LVTTHMR	0x330
-#define	APIC_LVTPC	0x340
-#define	APIC_LVT0	0x350
-#define		APIC_LVT_TIMER_BASE_MASK	(0x3 << 18)
-#define		GET_APIC_TIMER_BASE(x)		(((x) >> 18) & 0x3)
-#define		SET_APIC_TIMER_BASE(x)		(((x) << 18))
-#define		APIC_TIMER_BASE_CLKIN		0x0
-#define		APIC_TIMER_BASE_TMBASE		0x1
-#define		APIC_TIMER_BASE_DIV		0x2
-#define		APIC_LVT_TIMER_PERIODIC		(1 << 17)
-#define		APIC_LVT_MASKED			(1 << 16)
-#define		APIC_LVT_LEVEL_TRIGGER		(1 << 15)
-#define		APIC_LVT_REMOTE_IRR		(1 << 14)
-#define		APIC_INPUT_POLARITY		(1 << 13)
-#define		APIC_SEND_PENDING		(1 << 12)
-#define		APIC_MODE_MASK			0x700
-#define		GET_APIC_DELIVERY_MODE(x)	(((x) >> 8) & 0x7)
-#define		SET_APIC_DELIVERY_MODE(x, y)	(((x) & ~0x700) | ((y) << 8))
-#define			APIC_MODE_FIXED		0x0
-#define			APIC_MODE_NMI		0x4
-#define			APIC_MODE_EXTINT	0x7
-#define	APIC_LVT1	0x360
-#define	APIC_LVTERR	0x370
-#define	APIC_TMICT	0x380
-#define	APIC_TMCCT	0x390
-#define	APIC_TDCR	0x3E0
-#define APIC_SELF_IPI	0x3F0
-#define		APIC_TDR_DIV_TMBASE	(1 << 2)
-#define		APIC_TDR_DIV_1		0xB
-#define		APIC_TDR_DIV_2		0x0
-#define		APIC_TDR_DIV_4		0x1
-#define		APIC_TDR_DIV_8		0x2
-#define		APIC_TDR_DIV_16		0x3
-#define		APIC_TDR_DIV_32		0x8
-#define		APIC_TDR_DIV_64		0x9
-#define		APIC_TDR_DIV_128	0xA
-#define	APIC_EILVT0     0x500
-#define		APIC_EILVT_NR_AMD_K8	1	/* # of extended interrupts */
-#define		APIC_EILVT_NR_AMD_10H	4
-#define		APIC_EILVT_LVTOFF(x)	(((x) >> 4) & 0xF)
-#define		APIC_EILVT_MSG_FIX	0x0
-#define		APIC_EILVT_MSG_SMI	0x2
-#define		APIC_EILVT_MSG_NMI	0x4
-#define		APIC_EILVT_MSG_EXT	0x7
-#define		APIC_EILVT_MASKED	(1 << 16)
-#define	APIC_EILVT1     0x510
-#define	APIC_EILVT2     0x520
-#define	APIC_EILVT3     0x530
-
-#define APIC_BASE (fix_to_virt(FIX_APIC_BASE))
-#define APIC_BASE_MSR	0x800
-#define X2APIC_ENABLE	(1UL << 10)
-
-#ifdef CONFIG_X86_32
-# define MAX_IO_APICS 64
-#else
-# define MAX_IO_APICS 128
-# define MAX_LOCAL_APIC 32768
-#endif
-
-/*
- * All x86-64 systems are xAPIC compatible.
- * In the following, "apicid" is a physical APIC ID.
- */
-#define XAPIC_DEST_CPUS_SHIFT	4
-#define XAPIC_DEST_CPUS_MASK	((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
-#define XAPIC_DEST_CLUSTER_MASK	(XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
-#define APIC_CLUSTER(apicid)	((apicid) & XAPIC_DEST_CLUSTER_MASK)
-#define APIC_CLUSTERID(apicid)	(APIC_CLUSTER(apicid) >> XAPIC_DEST_CPUS_SHIFT)
-#define APIC_CPUID(apicid)	((apicid) & XAPIC_DEST_CPUS_MASK)
-#define NUM_APIC_CLUSTERS	((BAD_APICID + 1) >> XAPIC_DEST_CPUS_SHIFT)
-
-/*
- * the local APIC register structure, memory mapped. Not terribly well
- * tested, but we might eventually use this one in the future - the
- * problem why we cannot use it right now is the P5 APIC, it has an
- * errata which cannot take 8-bit reads and writes, only 32-bit ones ...
- */
-#define u32 unsigned int
-
-struct local_apic {
-
-/*000*/	struct { u32 __reserved[4]; } __reserved_01;
-
-/*010*/	struct { u32 __reserved[4]; } __reserved_02;
-
-/*020*/	struct { /* APIC ID Register */
-		u32   __reserved_1	: 24,
-			phys_apic_id	:  4,
-			__reserved_2	:  4;
-		u32 __reserved[3];
-	} id;
-
-/*030*/	const
-	struct { /* APIC Version Register */
-		u32   version		:  8,
-			__reserved_1	:  8,
-			max_lvt		:  8,
-			__reserved_2	:  8;
-		u32 __reserved[3];
-	} version;
-
-/*040*/	struct { u32 __reserved[4]; } __reserved_03;
-
-/*050*/	struct { u32 __reserved[4]; } __reserved_04;
-
-/*060*/	struct { u32 __reserved[4]; } __reserved_05;
-
-/*070*/	struct { u32 __reserved[4]; } __reserved_06;
-
-/*080*/	struct { /* Task Priority Register */
-		u32   priority	:  8,
-			__reserved_1	: 24;
-		u32 __reserved_2[3];
-	} tpr;
-
-/*090*/	const
-	struct { /* Arbitration Priority Register */
-		u32   priority	:  8,
-			__reserved_1	: 24;
-		u32 __reserved_2[3];
-	} apr;
-
-/*0A0*/	const
-	struct { /* Processor Priority Register */
-		u32   priority	:  8,
-			__reserved_1	: 24;
-		u32 __reserved_2[3];
-	} ppr;
-
-/*0B0*/	struct { /* End Of Interrupt Register */
-		u32   eoi;
-		u32 __reserved[3];
-	} eoi;
-
-/*0C0*/	struct { u32 __reserved[4]; } __reserved_07;
-
-/*0D0*/	struct { /* Logical Destination Register */
-		u32   __reserved_1	: 24,
-			logical_dest	:  8;
-		u32 __reserved_2[3];
-	} ldr;
-
-/*0E0*/	struct { /* Destination Format Register */
-		u32   __reserved_1	: 28,
-			model		:  4;
-		u32 __reserved_2[3];
-	} dfr;
-
-/*0F0*/	struct { /* Spurious Interrupt Vector Register */
-		u32	spurious_vector	:  8,
-			apic_enabled	:  1,
-			focus_cpu	:  1,
-			__reserved_2	: 22;
-		u32 __reserved_3[3];
-	} svr;
-
-/*100*/	struct { /* In Service Register */
-/*170*/		u32 bitfield;
-		u32 __reserved[3];
-	} isr [8];
-
-/*180*/	struct { /* Trigger Mode Register */
-/*1F0*/		u32 bitfield;
-		u32 __reserved[3];
-	} tmr [8];
-
-/*200*/	struct { /* Interrupt Request Register */
-/*270*/		u32 bitfield;
-		u32 __reserved[3];
-	} irr [8];
-
-/*280*/	union { /* Error Status Register */
-		struct {
-			u32   send_cs_error			:  1,
-				receive_cs_error		:  1,
-				send_accept_error		:  1,
-				receive_accept_error		:  1,
-				__reserved_1			:  1,
-				send_illegal_vector		:  1,
-				receive_illegal_vector		:  1,
-				illegal_register_address	:  1,
-				__reserved_2			: 24;
-			u32 __reserved_3[3];
-		} error_bits;
-		struct {
-			u32 errors;
-			u32 __reserved_3[3];
-		} all_errors;
-	} esr;
-
-/*290*/	struct { u32 __reserved[4]; } __reserved_08;
-
-/*2A0*/	struct { u32 __reserved[4]; } __reserved_09;
-
-/*2B0*/	struct { u32 __reserved[4]; } __reserved_10;
-
-/*2C0*/	struct { u32 __reserved[4]; } __reserved_11;
-
-/*2D0*/	struct { u32 __reserved[4]; } __reserved_12;
-
-/*2E0*/	struct { u32 __reserved[4]; } __reserved_13;
-
-/*2F0*/	struct { u32 __reserved[4]; } __reserved_14;
-
-/*300*/	struct { /* Interrupt Command Register 1 */
-		u32   vector			:  8,
-			delivery_mode		:  3,
-			destination_mode	:  1,
-			delivery_status		:  1,
-			__reserved_1		:  1,
-			level			:  1,
-			trigger			:  1,
-			__reserved_2		:  2,
-			shorthand		:  2,
-			__reserved_3		:  12;
-		u32 __reserved_4[3];
-	} icr1;
-
-/*310*/	struct { /* Interrupt Command Register 2 */
-		union {
-			u32   __reserved_1	: 24,
-				phys_dest	:  4,
-				__reserved_2	:  4;
-			u32   __reserved_3	: 24,
-				logical_dest	:  8;
-		} dest;
-		u32 __reserved_4[3];
-	} icr2;
-
-/*320*/	struct { /* LVT - Timer */
-		u32   vector		:  8,
-			__reserved_1	:  4,
-			delivery_status	:  1,
-			__reserved_2	:  3,
-			mask		:  1,
-			timer_mode	:  1,
-			__reserved_3	: 14;
-		u32 __reserved_4[3];
-	} lvt_timer;
-
-/*330*/	struct { /* LVT - Thermal Sensor */
-		u32  vector		:  8,
-			delivery_mode	:  3,
-			__reserved_1	:  1,
-			delivery_status	:  1,
-			__reserved_2	:  3,
-			mask		:  1,
-			__reserved_3	: 15;
-		u32 __reserved_4[3];
-	} lvt_thermal;
-
-/*340*/	struct { /* LVT - Performance Counter */
-		u32   vector		:  8,
-			delivery_mode	:  3,
-			__reserved_1	:  1,
-			delivery_status	:  1,
-			__reserved_2	:  3,
-			mask		:  1,
-			__reserved_3	: 15;
-		u32 __reserved_4[3];
-	} lvt_pc;
-
-/*350*/	struct { /* LVT - LINT0 */
-		u32   vector		:  8,
-			delivery_mode	:  3,
-			__reserved_1	:  1,
-			delivery_status	:  1,
-			polarity	:  1,
-			remote_irr	:  1,
-			trigger		:  1,
-			mask		:  1,
-			__reserved_2	: 15;
-		u32 __reserved_3[3];
-	} lvt_lint0;
-
-/*360*/	struct { /* LVT - LINT1 */
-		u32   vector		:  8,
-			delivery_mode	:  3,
-			__reserved_1	:  1,
-			delivery_status	:  1,
-			polarity	:  1,
-			remote_irr	:  1,
-			trigger		:  1,
-			mask		:  1,
-			__reserved_2	: 15;
-		u32 __reserved_3[3];
-	} lvt_lint1;
-
-/*370*/	struct { /* LVT - Error */
-		u32   vector		:  8,
-			__reserved_1	:  4,
-			delivery_status	:  1,
-			__reserved_2	:  3,
-			mask		:  1,
-			__reserved_3	: 15;
-		u32 __reserved_4[3];
-	} lvt_error;
-
-/*380*/	struct { /* Timer Initial Count Register */
-		u32   initial_count;
-		u32 __reserved_2[3];
-	} timer_icr;
-
-/*390*/	const
-	struct { /* Timer Current Count Register */
-		u32   curr_count;
-		u32 __reserved_2[3];
-	} timer_ccr;
-
-/*3A0*/	struct { u32 __reserved[4]; } __reserved_16;
-
-/*3B0*/	struct { u32 __reserved[4]; } __reserved_17;
-
-/*3C0*/	struct { u32 __reserved[4]; } __reserved_18;
-
-/*3D0*/	struct { u32 __reserved[4]; } __reserved_19;
-
-/*3E0*/	struct { /* Timer Divide Configuration Register */
-		u32   divisor		:  4,
-			__reserved_1	: 28;
-		u32 __reserved_2[3];
-	} timer_dcr;
-
-/*3F0*/	struct { u32 __reserved[4]; } __reserved_20;
-
-} __attribute__ ((packed));
-
-#undef u32
-
-#ifdef CONFIG_X86_32
- #define BAD_APICID 0xFFu
-#else
- #define BAD_APICID 0xFFFFu
-#endif
-#endif /* ASM_X86__APICDEF_H */
diff --git a/include/asm-x86/arch_hooks.h b/include/asm-x86/arch_hooks.h
deleted file mode 100644
index de4596b24c23..000000000000
--- a/include/asm-x86/arch_hooks.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef ASM_X86__ARCH_HOOKS_H
-#define ASM_X86__ARCH_HOOKS_H
-
-#include <linux/interrupt.h>
-
-/*
- *	linux/include/asm/arch_hooks.h
- *
- *	define the architecture specific hooks
- */
-
-/* these aren't arch hooks, they are generic routines
- * that can be used by the hooks */
-extern void init_ISA_irqs(void);
-extern irqreturn_t timer_interrupt(int irq, void *dev_id);
-
-/* these are the defined hooks */
-extern void intr_init_hook(void);
-extern void pre_intr_init_hook(void);
-extern void pre_setup_arch_hook(void);
-extern void trap_init_hook(void);
-extern void pre_time_init_hook(void);
-extern void time_init_hook(void);
-extern void mca_nmi_hook(void);
-
-#endif /* ASM_X86__ARCH_HOOKS_H */
diff --git a/include/asm-x86/asm.h b/include/asm-x86/asm.h
deleted file mode 100644
index e1355f44d7c3..000000000000
--- a/include/asm-x86/asm.h
+++ /dev/null
@@ -1,47 +0,0 @@
-#ifndef ASM_X86__ASM_H
-#define ASM_X86__ASM_H
-
-#ifdef __ASSEMBLY__
-# define __ASM_FORM(x)	x
-# define __ASM_EX_SEC	.section __ex_table
-#else
-# define __ASM_FORM(x)	" " #x " "
-# define __ASM_EX_SEC	" .section __ex_table,\"a\"\n"
-#endif
-
-#ifdef CONFIG_X86_32
-# define __ASM_SEL(a,b) __ASM_FORM(a)
-#else
-# define __ASM_SEL(a,b) __ASM_FORM(b)
-#endif
-
-#define __ASM_SIZE(inst)	__ASM_SEL(inst##l, inst##q)
-#define __ASM_REG(reg)		__ASM_SEL(e##reg, r##reg)
-
-#define _ASM_PTR	__ASM_SEL(.long, .quad)
-#define _ASM_ALIGN	__ASM_SEL(.balign 4, .balign 8)
-
-#define _ASM_MOV	__ASM_SIZE(mov)
-#define _ASM_INC	__ASM_SIZE(inc)
-#define _ASM_DEC	__ASM_SIZE(dec)
-#define _ASM_ADD	__ASM_SIZE(add)
-#define _ASM_SUB	__ASM_SIZE(sub)
-#define _ASM_XADD	__ASM_SIZE(xadd)
-
-#define _ASM_AX		__ASM_REG(ax)
-#define _ASM_BX		__ASM_REG(bx)
-#define _ASM_CX		__ASM_REG(cx)
-#define _ASM_DX		__ASM_REG(dx)
-#define _ASM_SP		__ASM_REG(sp)
-#define _ASM_BP		__ASM_REG(bp)
-#define _ASM_SI		__ASM_REG(si)
-#define _ASM_DI		__ASM_REG(di)
-
-/* Exception table entry */
-# define _ASM_EXTABLE(from,to) \
-	__ASM_EX_SEC	\
-	_ASM_ALIGN "\n" \
-	_ASM_PTR #from "," #to "\n" \
-	" .previous\n"
-
-#endif /* ASM_X86__ASM_H */
diff --git a/include/asm-x86/atomic.h b/include/asm-x86/atomic.h
deleted file mode 100644
index 4e1b8873c474..000000000000
--- a/include/asm-x86/atomic.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "atomic_32.h"
-#else
-# include "atomic_64.h"
-#endif
diff --git a/include/asm-x86/atomic_32.h b/include/asm-x86/atomic_32.h
deleted file mode 100644
index 14d3f0beb889..000000000000
--- a/include/asm-x86/atomic_32.h
+++ /dev/null
@@ -1,259 +0,0 @@
-#ifndef ASM_X86__ATOMIC_32_H
-#define ASM_X86__ATOMIC_32_H
-
-#include <linux/compiler.h>
-#include <asm/processor.h>
-#include <asm/cmpxchg.h>
-
-/*
- * Atomic operations that C can't guarantee us.  Useful for
- * resource counting etc..
- */
-
-/*
- * Make sure gcc doesn't try to be clever and move things around
- * on us. We need to use _exactly_ the address the user gave us,
- * not some alias that contains the same information.
- */
-typedef struct {
-	int counter;
-} atomic_t;
-
-#define ATOMIC_INIT(i)	{ (i) }
-
-/**
- * atomic_read - read atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically reads the value of @v.
- */
-#define atomic_read(v)		((v)->counter)
-
-/**
- * atomic_set - set atomic variable
- * @v: pointer of type atomic_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
-#define atomic_set(v, i)	(((v)->counter) = (i))
-
-/**
- * atomic_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v.
- */
-static inline void atomic_add(int i, atomic_t *v)
-{
-	asm volatile(LOCK_PREFIX "addl %1,%0"
-		     : "+m" (v->counter)
-		     : "ir" (i));
-}
-
-/**
- * atomic_sub - subtract integer from atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v.
- */
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	asm volatile(LOCK_PREFIX "subl %1,%0"
-		     : "+m" (v->counter)
-		     : "ir" (i));
-}
-
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_sub_and_test(int i, atomic_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
-}
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-static inline void atomic_inc(atomic_t *v)
-{
-	asm volatile(LOCK_PREFIX "incl %0"
-		     : "+m" (v->counter));
-}
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-static inline void atomic_dec(atomic_t *v)
-{
-	asm volatile(LOCK_PREFIX "decl %0"
-		     : "+m" (v->counter));
-}
-
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int atomic_dec_and_test(atomic_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "decl %0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
-}
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_inc_and_test(atomic_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "incl %0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
-}
-
-/**
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int atomic_add_negative(int i, atomic_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
-}
-
-/**
- * atomic_add_return - add integer and return
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns @i + @v
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	int __i;
-#ifdef CONFIG_M386
-	unsigned long flags;
-	if (unlikely(boot_cpu_data.x86 <= 3))
-		goto no_xadd;
-#endif
-	/* Modern 486+ processor */
-	__i = i;
-	asm volatile(LOCK_PREFIX "xaddl %0, %1"
-		     : "+r" (i), "+m" (v->counter)
-		     : : "memory");
-	return i + __i;
-
-#ifdef CONFIG_M386
-no_xadd: /* Legacy 386 processor */
-	local_irq_save(flags);
-	__i = atomic_read(v);
-	atomic_set(v, i + __i);
-	local_irq_restore(flags);
-	return i + __i;
-#endif
-}
-
-/**
- * atomic_sub_return - subtract integer and return
- * @v: pointer of type atomic_t
- * @i: integer value to subtract
- *
- * Atomically subtracts @i from @v and returns @v - @i
- */
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	return atomic_add_return(-i, v);
-}
-
-#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
-#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
-
-/**
- * atomic_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-#define atomic_inc_return(v)  (atomic_add_return(1, v))
-#define atomic_dec_return(v)  (atomic_sub_return(1, v))
-
-/* These are x86-specific, used by some header files */
-#define atomic_clear_mask(mask, addr)				\
-	asm volatile(LOCK_PREFIX "andl %0,%1"			\
-		     : : "r" (~(mask)), "m" (*(addr)) : "memory")
-
-#define atomic_set_mask(mask, addr)				\
-	asm volatile(LOCK_PREFIX "orl %0,%1"				\
-		     : : "r" (mask), "m" (*(addr)) : "memory")
-
-/* Atomic operations are already serializing on x86 */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
-#include <asm-generic/atomic.h>
-#endif /* ASM_X86__ATOMIC_32_H */
diff --git a/include/asm-x86/atomic_64.h b/include/asm-x86/atomic_64.h
deleted file mode 100644
index 2cb218c4a356..000000000000
--- a/include/asm-x86/atomic_64.h
+++ /dev/null
@@ -1,473 +0,0 @@
-#ifndef ASM_X86__ATOMIC_64_H
-#define ASM_X86__ATOMIC_64_H
-
-#include <asm/alternative.h>
-#include <asm/cmpxchg.h>
-
-/* atomic_t should be 32 bit signed type */
-
-/*
- * Atomic operations that C can't guarantee us.  Useful for
- * resource counting etc..
- */
-
-/*
- * Make sure gcc doesn't try to be clever and move things around
- * on us. We need to use _exactly_ the address the user gave us,
- * not some alias that contains the same information.
- */
-typedef struct {
-	int counter;
-} atomic_t;
-
-#define ATOMIC_INIT(i)	{ (i) }
-
-/**
- * atomic_read - read atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically reads the value of @v.
- */
-#define atomic_read(v)		((v)->counter)
-
-/**
- * atomic_set - set atomic variable
- * @v: pointer of type atomic_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
-#define atomic_set(v, i)		(((v)->counter) = (i))
-
-/**
- * atomic_add - add integer to atomic variable
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v.
- */
-static inline void atomic_add(int i, atomic_t *v)
-{
-	asm volatile(LOCK_PREFIX "addl %1,%0"
-		     : "=m" (v->counter)
-		     : "ir" (i), "m" (v->counter));
-}
-
-/**
- * atomic_sub - subtract the atomic variable
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v.
- */
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	asm volatile(LOCK_PREFIX "subl %1,%0"
-		     : "=m" (v->counter)
-		     : "ir" (i), "m" (v->counter));
-}
-
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_sub_and_test(int i, atomic_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "ir" (i), "m" (v->counter) : "memory");
-	return c;
-}
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-static inline void atomic_inc(atomic_t *v)
-{
-	asm volatile(LOCK_PREFIX "incl %0"
-		     : "=m" (v->counter)
-		     : "m" (v->counter));
-}
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-static inline void atomic_dec(atomic_t *v)
-{
-	asm volatile(LOCK_PREFIX "decl %0"
-		     : "=m" (v->counter)
-		     : "m" (v->counter));
-}
-
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int atomic_dec_and_test(atomic_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "decl %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
-}
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic_inc_and_test(atomic_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "incl %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
-}
-
-/**
- * atomic_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int atomic_add_negative(int i, atomic_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "ir" (i), "m" (v->counter) : "memory");
-	return c;
-}
-
-/**
- * atomic_add_return - add and return
- * @i: integer value to add
- * @v: pointer of type atomic_t
- *
- * Atomically adds @i to @v and returns @i + @v
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	int __i = i;
-	asm volatile(LOCK_PREFIX "xaddl %0, %1"
-		     : "+r" (i), "+m" (v->counter)
-		     : : "memory");
-	return i + __i;
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	return atomic_add_return(-i, v);
-}
-
-#define atomic_inc_return(v)  (atomic_add_return(1, v))
-#define atomic_dec_return(v)  (atomic_sub_return(1, v))
-
-/* An 64bit atomic type */
-
-typedef struct {
-	long counter;
-} atomic64_t;
-
-#define ATOMIC64_INIT(i)	{ (i) }
-
-/**
- * atomic64_read - read atomic64 variable
- * @v: pointer of type atomic64_t
- *
- * Atomically reads the value of @v.
- * Doesn't imply a read memory barrier.
- */
-#define atomic64_read(v)		((v)->counter)
-
-/**
- * atomic64_set - set atomic64 variable
- * @v: pointer to type atomic64_t
- * @i: required value
- *
- * Atomically sets the value of @v to @i.
- */
-#define atomic64_set(v, i)		(((v)->counter) = (i))
-
-/**
- * atomic64_add - add integer to atomic64 variable
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v.
- */
-static inline void atomic64_add(long i, atomic64_t *v)
-{
-	asm volatile(LOCK_PREFIX "addq %1,%0"
-		     : "=m" (v->counter)
-		     : "er" (i), "m" (v->counter));
-}
-
-/**
- * atomic64_sub - subtract the atomic64 variable
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v.
- */
-static inline void atomic64_sub(long i, atomic64_t *v)
-{
-	asm volatile(LOCK_PREFIX "subq %1,%0"
-		     : "=m" (v->counter)
-		     : "er" (i), "m" (v->counter));
-}
-
-/**
- * atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic64_sub_and_test(long i, atomic64_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "er" (i), "m" (v->counter) : "memory");
-	return c;
-}
-
-/**
- * atomic64_inc - increment atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1.
- */
-static inline void atomic64_inc(atomic64_t *v)
-{
-	asm volatile(LOCK_PREFIX "incq %0"
-		     : "=m" (v->counter)
-		     : "m" (v->counter));
-}
-
-/**
- * atomic64_dec - decrement atomic64 variable
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
-static inline void atomic64_dec(atomic64_t *v)
-{
-	asm volatile(LOCK_PREFIX "decq %0"
-		     : "=m" (v->counter)
-		     : "m" (v->counter));
-}
-
-/**
- * atomic64_dec_and_test - decrement and test
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int atomic64_dec_and_test(atomic64_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "decq %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
-}
-
-/**
- * atomic64_inc_and_test - increment and test
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int atomic64_inc_and_test(atomic64_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "incq %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
-}
-
-/**
- * atomic64_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int atomic64_add_negative(long i, atomic64_t *v)
-{
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "er" (i), "m" (v->counter) : "memory");
-	return c;
-}
-
-/**
- * atomic64_add_return - add and return
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns @i + @v
- */
-static inline long atomic64_add_return(long i, atomic64_t *v)
-{
-	long __i = i;
-	asm volatile(LOCK_PREFIX "xaddq %0, %1;"
-		     : "+r" (i), "+m" (v->counter)
-		     : : "memory");
-	return i + __i;
-}
-
-static inline long atomic64_sub_return(long i, atomic64_t *v)
-{
-	return atomic64_add_return(-i, v);
-}
-
-#define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
-#define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
-
-#define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
-#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
-
-#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
-#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
-
-/**
- * atomic_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
- */
-static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
-/**
- * atomic_inc_short - increment of a short integer
- * @v: pointer to type int
- *
- * Atomically adds 1 to @v
- * Returns the new value of @u
- */
-static inline short int atomic_inc_short(short int *v)
-{
-	asm(LOCK_PREFIX "addw $1, %0" : "+m" (*v));
-	return *v;
-}
-
-/**
- * atomic_or_long - OR of two long integers
- * @v1: pointer to type unsigned long
- * @v2: pointer to type unsigned long
- *
- * Atomically ORs @v1 and @v2
- * Returns the result of the OR
- */
-static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
-{
-	asm(LOCK_PREFIX "orq %1, %0" : "+m" (*v1) : "r" (v2));
-}
-
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
-/* These are x86-specific, used by some header files */
-#define atomic_clear_mask(mask, addr)					\
-	asm volatile(LOCK_PREFIX "andl %0,%1"				\
-		     : : "r" (~(mask)), "m" (*(addr)) : "memory")
-
-#define atomic_set_mask(mask, addr)					\
-	asm volatile(LOCK_PREFIX "orl %0,%1"				\
-		     : : "r" ((unsigned)(mask)), "m" (*(addr))		\
-		     : "memory")
-
-/* Atomic operations are already serializing on x86 */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
-#include <asm-generic/atomic.h>
-#endif /* ASM_X86__ATOMIC_64_H */
diff --git a/include/asm-x86/auxvec.h b/include/asm-x86/auxvec.h
deleted file mode 100644
index 12c7cac74202..000000000000
--- a/include/asm-x86/auxvec.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef ASM_X86__AUXVEC_H
-#define ASM_X86__AUXVEC_H
-/*
- * Architecture-neutral AT_ values in 0-17, leave some room
- * for more of them, start the x86-specific ones at 32.
- */
-#ifdef __i386__
-#define AT_SYSINFO		32
-#endif
-#define AT_SYSINFO_EHDR		33
-
-#endif /* ASM_X86__AUXVEC_H */
diff --git a/include/asm-x86/bigsmp/apic.h b/include/asm-x86/bigsmp/apic.h
deleted file mode 100644
index 1d9543b9d358..000000000000
--- a/include/asm-x86/bigsmp/apic.h
+++ /dev/null
@@ -1,139 +0,0 @@
-#ifndef __ASM_MACH_APIC_H
-#define __ASM_MACH_APIC_H
-
-#define xapic_phys_to_log_apicid(cpu) (per_cpu(x86_bios_cpu_apicid, cpu))
-#define esr_disable (1)
-
-static inline int apic_id_registered(void)
-{
-	return (1);
-}
-
-static inline cpumask_t target_cpus(void)
-{
-#ifdef CONFIG_SMP
-        return cpu_online_map;
-#else
-        return cpumask_of_cpu(0);
-#endif
-}
-
-#undef APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL	0
-#define APIC_DFR_VALUE		(APIC_DFR_FLAT)
-#define INT_DELIVERY_MODE	(dest_Fixed)
-#define INT_DEST_MODE		(0)    /* phys delivery to target proc */
-#define NO_BALANCE_IRQ		(0)
-#define WAKE_SECONDARY_VIA_INIT
-
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return (0);
-}
-
-static inline unsigned long check_apicid_present(int bit)
-{
-	return (1);
-}
-
-static inline unsigned long calculate_ldr(int cpu)
-{
-	unsigned long val, id;
-	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-	id = xapic_phys_to_log_apicid(cpu);
-	val |= SET_APIC_LOGICAL_ID(id);
-	return val;
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr(void)
-{
-	unsigned long val;
-	int cpu = smp_processor_id();
-
-	apic_write(APIC_DFR, APIC_DFR_VALUE);
-	val = calculate_ldr(cpu);
-	apic_write(APIC_LDR, val);
-}
-
-static inline void setup_apic_routing(void)
-{
-	printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
-		"Physflat", nr_ioapics);
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-	return (0);
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-	return apicid_2_node[hard_smp_processor_id()];
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (mps_cpu < NR_CPUS)
-		return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
-
-	return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
-{
-	return physid_mask_of_physid(phys_apicid);
-}
-
-extern u8 cpu_2_logical_apicid[];
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-	if (cpu >= NR_CPUS)
-		return BAD_APICID;
-	return cpu_physical_id(cpu);
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-	/* For clustered we don't have a good way to do this yet - hack */
-	return physids_promote(0xFFL);
-}
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-	return (1);
-}
-
-/* As we are using single CPU as destination, pick only one CPU here */
-static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
-{
-	int cpu;
-	int apicid;	
-
-	cpu = first_cpu(cpumask);
-	apicid = cpu_to_logical_apicid(cpu);
-	return apicid;
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_MACH_APIC_H */
diff --git a/include/asm-x86/bigsmp/apicdef.h b/include/asm-x86/bigsmp/apicdef.h
deleted file mode 100644
index 392c3f5ef2fe..000000000000
--- a/include/asm-x86/bigsmp/apicdef.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_MACH_APICDEF_H
-#define __ASM_MACH_APICDEF_H
-
-#define		APIC_ID_MASK		(0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-	return (((x)>>24)&0xFF);
-}
-
-#define		GET_APIC_ID(x)	get_apic_id(x)
-
-#endif
diff --git a/include/asm-x86/bigsmp/ipi.h b/include/asm-x86/bigsmp/ipi.h
deleted file mode 100644
index 9404c535b7ec..000000000000
--- a/include/asm-x86/bigsmp/ipi.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __ASM_MACH_IPI_H
-#define __ASM_MACH_IPI_H
-
-void send_IPI_mask_sequence(cpumask_t mask, int vector);
-
-static inline void send_IPI_mask(cpumask_t mask, int vector)
-{
-	send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
-
-	if (!cpus_empty(mask))
-		send_IPI_mask(mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-	send_IPI_mask(cpu_online_map, vector);
-}
-
-#endif /* __ASM_MACH_IPI_H */
diff --git a/include/asm-x86/bios_ebda.h b/include/asm-x86/bios_ebda.h
deleted file mode 100644
index 79b4b88505d7..000000000000
--- a/include/asm-x86/bios_ebda.h
+++ /dev/null
@@ -1,36 +0,0 @@
-#ifndef ASM_X86__BIOS_EBDA_H
-#define ASM_X86__BIOS_EBDA_H
-
-#include <asm/io.h>
-
-/*
- * there is a real-mode segmented pointer pointing to the
- * 4K EBDA area at 0x40E.
- */
-static inline unsigned int get_bios_ebda(void)
-{
-	unsigned int address = *(unsigned short *)phys_to_virt(0x40E);
-	address <<= 4;
-	return address;	/* 0 means none */
-}
-
-void reserve_ebda_region(void);
-
-#ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
-/*
- * This is obviously not a great place for this, but we want to be
- * able to scatter it around anywhere in the kernel.
- */
-void check_for_bios_corruption(void);
-void start_periodic_check_for_corruption(void);
-#else
-static inline void check_for_bios_corruption(void)
-{
-}
-
-static inline void start_periodic_check_for_corruption(void)
-{
-}
-#endif
-
-#endif /* ASM_X86__BIOS_EBDA_H */
diff --git a/include/asm-x86/bitops.h b/include/asm-x86/bitops.h
deleted file mode 100644
index 451a74762bd4..000000000000
--- a/include/asm-x86/bitops.h
+++ /dev/null
@@ -1,451 +0,0 @@
-#ifndef ASM_X86__BITOPS_H
-#define ASM_X86__BITOPS_H
-
-/*
- * Copyright 1992, Linus Torvalds.
- */
-
-#ifndef _LINUX_BITOPS_H
-#error only <linux/bitops.h> can be included directly
-#endif
-
-#include <linux/compiler.h>
-#include <asm/alternative.h>
-
-/*
- * These have to be done with inline assembly: that way the bit-setting
- * is guaranteed to be atomic. All bit operations return 0 if the bit
- * was cleared before the operation and != 0 if it was not.
- *
- * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
- */
-
-#if __GNUC__ < 4 || (__GNUC__ == 4 && __GNUC_MINOR__ < 1)
-/* Technically wrong, but this avoids compilation errors on some gcc
-   versions. */
-#define BITOP_ADDR(x) "=m" (*(volatile long *) (x))
-#else
-#define BITOP_ADDR(x) "+m" (*(volatile long *) (x))
-#endif
-
-#define ADDR				BITOP_ADDR(addr)
-
-/*
- * We do the locked ops that don't return the old value as
- * a mask operation on a byte.
- */
-#define IS_IMMEDIATE(nr)		(__builtin_constant_p(nr))
-#define CONST_MASK_ADDR(nr, addr)	BITOP_ADDR((void *)(addr) + ((nr)>>3))
-#define CONST_MASK(nr)			(1 << ((nr) & 7))
-
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered.  See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note: there are no guarantees that this function will not be reordered
- * on non x86 architectures, so if you are writing portable code,
- * make sure not to rely on its reordering guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void set_bit(unsigned int nr, volatile unsigned long *addr)
-{
-	if (IS_IMMEDIATE(nr)) {
-		asm volatile(LOCK_PREFIX "orb %1,%0"
-			: CONST_MASK_ADDR(nr, addr)
-			: "iq" ((u8)CONST_MASK(nr))
-			: "memory");
-	} else {
-		asm volatile(LOCK_PREFIX "bts %1,%0"
-			: BITOP_ADDR(addr) : "Ir" (nr) : "memory");
-	}
-}
-
-/**
- * __set_bit - Set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * Unlike set_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static inline void __set_bit(int nr, volatile unsigned long *addr)
-{
-	asm volatile("bts %1,%0" : ADDR : "Ir" (nr) : "memory");
-}
-
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered.  However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
- * in order to ensure changes are visible on other processors.
- */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
-{
-	if (IS_IMMEDIATE(nr)) {
-		asm volatile(LOCK_PREFIX "andb %1,%0"
-			: CONST_MASK_ADDR(nr, addr)
-			: "iq" ((u8)~CONST_MASK(nr)));
-	} else {
-		asm volatile(LOCK_PREFIX "btr %1,%0"
-			: BITOP_ADDR(addr)
-			: "Ir" (nr));
-	}
-}
-
-/*
- * clear_bit_unlock - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and implies release semantics before the memory
- * operation. It can be used for an unlock.
- */
-static inline void clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
-{
-	barrier();
-	clear_bit(nr, addr);
-}
-
-static inline void __clear_bit(int nr, volatile unsigned long *addr)
-{
-	asm volatile("btr %1,%0" : ADDR : "Ir" (nr));
-}
-
-/*
- * __clear_bit_unlock - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * __clear_bit() is non-atomic and implies release semantics before the memory
- * operation. It can be used for an unlock if no other CPUs can concurrently
- * modify other bits in the word.
- *
- * No memory barrier is required here, because x86 cannot reorder stores past
- * older loads. Same principle as spin_unlock.
- */
-static inline void __clear_bit_unlock(unsigned nr, volatile unsigned long *addr)
-{
-	barrier();
-	__clear_bit(nr, addr);
-}
-
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
-/**
- * __change_bit - Toggle a bit in memory
- * @nr: the bit to change
- * @addr: the address to start counting from
- *
- * Unlike change_bit(), this function is non-atomic and may be reordered.
- * If it's called on the same region of memory simultaneously, the effect
- * may be that only one operation succeeds.
- */
-static inline void __change_bit(int nr, volatile unsigned long *addr)
-{
-	asm volatile("btc %1,%0" : ADDR : "Ir" (nr));
-}
-
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void change_bit(int nr, volatile unsigned long *addr)
-{
-	asm volatile(LOCK_PREFIX "btc %1,%0" : ADDR : "Ir" (nr));
-}
-
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "bts %2,%1\n\t"
-		     "sbb %0,%0" : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
-}
-
-/**
- * test_and_set_bit_lock - Set a bit and return its old value for lock
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This is the same as test_and_set_bit on x86.
- */
-static inline int test_and_set_bit_lock(int nr, volatile unsigned long *addr)
-{
-	return test_and_set_bit(nr, addr);
-}
-
-/**
- * __test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static inline int __test_and_set_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	asm("bts %2,%1\n\t"
-	    "sbb %0,%0"
-	    : "=r" (oldbit), ADDR
-	    : "Ir" (nr));
-	return oldbit;
-}
-
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "btr %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
-}
-
-/**
- * __test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is non-atomic and can be reordered.
- * If two examples of this operation race, one can appear to succeed
- * but actually fail.  You must protect multiple accesses with a lock.
- */
-static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	asm volatile("btr %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR
-		     : "Ir" (nr));
-	return oldbit;
-}
-
-/* WARNING: non atomic and it can be reordered! */
-static inline int __test_and_change_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	asm volatile("btc %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR
-		     : "Ir" (nr) : "memory");
-
-	return oldbit;
-}
-
-/**
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "btc %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
-}
-
-static inline int constant_test_bit(int nr, const volatile unsigned long *addr)
-{
-	return ((1UL << (nr % BITS_PER_LONG)) &
-		(((unsigned long *)addr)[nr / BITS_PER_LONG])) != 0;
-}
-
-static inline int variable_test_bit(int nr, volatile const unsigned long *addr)
-{
-	int oldbit;
-
-	asm volatile("bt %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit)
-		     : "m" (*(unsigned long *)addr), "Ir" (nr));
-
-	return oldbit;
-}
-
-#if 0 /* Fool kernel-doc since it doesn't do macros yet */
-/**
- * test_bit - Determine whether a bit is set
- * @nr: bit number to test
- * @addr: Address to start counting from
- */
-static int test_bit(int nr, const volatile unsigned long *addr);
-#endif
-
-#define test_bit(nr, addr)			\
-	(__builtin_constant_p((nr))		\
-	 ? constant_test_bit((nr), (addr))	\
-	 : variable_test_bit((nr), (addr)))
-
-/**
- * __ffs - find first set bit in word
- * @word: The word to search
- *
- * Undefined if no bit exists, so code should check against 0 first.
- */
-static inline unsigned long __ffs(unsigned long word)
-{
-	asm("bsf %1,%0"
-		: "=r" (word)
-		: "rm" (word));
-	return word;
-}
-
-/**
- * ffz - find first zero bit in word
- * @word: The word to search
- *
- * Undefined if no zero exists, so code should check against ~0UL first.
- */
-static inline unsigned long ffz(unsigned long word)
-{
-	asm("bsf %1,%0"
-		: "=r" (word)
-		: "r" (~word));
-	return word;
-}
-
-/*
- * __fls: find last set bit in word
- * @word: The word to search
- *
- * Undefined if no set bit exists, so code should check against 0 first.
- */
-static inline unsigned long __fls(unsigned long word)
-{
-	asm("bsr %1,%0"
-	    : "=r" (word)
-	    : "rm" (word));
-	return word;
-}
-
-#ifdef __KERNEL__
-/**
- * ffs - find first set bit in word
- * @x: the word to search
- *
- * This is defined the same way as the libc and compiler builtin ffs
- * routines, therefore differs in spirit from the other bitops.
- *
- * ffs(value) returns 0 if value is 0 or the position of the first
- * set bit if value is nonzero. The first (least significant) bit
- * is at position 1.
- */
-static inline int ffs(int x)
-{
-	int r;
-#ifdef CONFIG_X86_CMOV
-	asm("bsfl %1,%0\n\t"
-	    "cmovzl %2,%0"
-	    : "=r" (r) : "rm" (x), "r" (-1));
-#else
-	asm("bsfl %1,%0\n\t"
-	    "jnz 1f\n\t"
-	    "movl $-1,%0\n"
-	    "1:" : "=r" (r) : "rm" (x));
-#endif
-	return r + 1;
-}
-
-/**
- * fls - find last set bit in word
- * @x: the word to search
- *
- * This is defined in a similar way as the libc and compiler builtin
- * ffs, but returns the position of the most significant set bit.
- *
- * fls(value) returns 0 if value is 0 or the position of the last
- * set bit if value is nonzero. The last (most significant) bit is
- * at position 32.
- */
-static inline int fls(int x)
-{
-	int r;
-#ifdef CONFIG_X86_CMOV
-	asm("bsrl %1,%0\n\t"
-	    "cmovzl %2,%0"
-	    : "=&r" (r) : "rm" (x), "rm" (-1));
-#else
-	asm("bsrl %1,%0\n\t"
-	    "jnz 1f\n\t"
-	    "movl $-1,%0\n"
-	    "1:" : "=r" (r) : "rm" (x));
-#endif
-	return r + 1;
-}
-#endif /* __KERNEL__ */
-
-#undef ADDR
-
-#ifdef __KERNEL__
-
-#include <asm-generic/bitops/sched.h>
-
-#define ARCH_HAS_FAST_MULTIPLIER 1
-
-#include <asm-generic/bitops/hweight.h>
-
-#endif /* __KERNEL__ */
-
-#include <asm-generic/bitops/fls64.h>
-
-#ifdef __KERNEL__
-
-#include <asm-generic/bitops/ext2-non-atomic.h>
-
-#define ext2_set_bit_atomic(lock, nr, addr)			\
-	test_and_set_bit((nr), (unsigned long *)(addr))
-#define ext2_clear_bit_atomic(lock, nr, addr)			\
-	test_and_clear_bit((nr), (unsigned long *)(addr))
-
-#include <asm-generic/bitops/minix.h>
-
-#endif /* __KERNEL__ */
-#endif /* ASM_X86__BITOPS_H */
diff --git a/include/asm-x86/boot.h b/include/asm-x86/boot.h
deleted file mode 100644
index 1d63bd5d5946..000000000000
--- a/include/asm-x86/boot.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef ASM_X86__BOOT_H
-#define ASM_X86__BOOT_H
-
-/* Don't touch these, unless you really know what you're doing. */
-#define DEF_SYSSEG	0x1000
-#define DEF_SYSSIZE	0x7F00
-
-/* Internal svga startup constants */
-#define NORMAL_VGA	0xffff		/* 80x25 mode */
-#define EXTENDED_VGA	0xfffe		/* 80x50 mode */
-#define ASK_VGA		0xfffd		/* ask for it at bootup */
-
-/* Physical address where kernel should be loaded. */
-#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
-				+ (CONFIG_PHYSICAL_ALIGN - 1)) \
-				& ~(CONFIG_PHYSICAL_ALIGN - 1))
-
-#ifdef CONFIG_X86_64
-#define BOOT_HEAP_SIZE	0x7000
-#define BOOT_STACK_SIZE	0x4000
-#else
-#define BOOT_HEAP_SIZE	0x4000
-#define BOOT_STACK_SIZE	0x1000
-#endif
-
-#endif /* ASM_X86__BOOT_H */
diff --git a/include/asm-x86/bootparam.h b/include/asm-x86/bootparam.h
deleted file mode 100644
index ccf027e2d97d..000000000000
--- a/include/asm-x86/bootparam.h
+++ /dev/null
@@ -1,111 +0,0 @@
-#ifndef ASM_X86__BOOTPARAM_H
-#define ASM_X86__BOOTPARAM_H
-
-#include <linux/types.h>
-#include <linux/screen_info.h>
-#include <linux/apm_bios.h>
-#include <linux/edd.h>
-#include <asm/e820.h>
-#include <asm/ist.h>
-#include <video/edid.h>
-
-/* setup data types */
-#define SETUP_NONE			0
-#define SETUP_E820_EXT			1
-
-/* extensible setup data list node */
-struct setup_data {
-	__u64 next;
-	__u32 type;
-	__u32 len;
-	__u8 data[0];
-};
-
-struct setup_header {
-	__u8	setup_sects;
-	__u16	root_flags;
-	__u32	syssize;
-	__u16	ram_size;
-#define RAMDISK_IMAGE_START_MASK	0x07FF
-#define RAMDISK_PROMPT_FLAG		0x8000
-#define RAMDISK_LOAD_FLAG		0x4000
-	__u16	vid_mode;
-	__u16	root_dev;
-	__u16	boot_flag;
-	__u16	jump;
-	__u32	header;
-	__u16	version;
-	__u32	realmode_swtch;
-	__u16	start_sys;
-	__u16	kernel_version;
-	__u8	type_of_loader;
-	__u8	loadflags;
-#define LOADED_HIGH	(1<<0)
-#define QUIET_FLAG	(1<<5)
-#define KEEP_SEGMENTS	(1<<6)
-#define CAN_USE_HEAP	(1<<7)
-	__u16	setup_move_size;
-	__u32	code32_start;
-	__u32	ramdisk_image;
-	__u32	ramdisk_size;
-	__u32	bootsect_kludge;
-	__u16	heap_end_ptr;
-	__u16	_pad1;
-	__u32	cmd_line_ptr;
-	__u32	initrd_addr_max;
-	__u32	kernel_alignment;
-	__u8	relocatable_kernel;
-	__u8	_pad2[3];
-	__u32	cmdline_size;
-	__u32	hardware_subarch;
-	__u64	hardware_subarch_data;
-	__u32	payload_offset;
-	__u32	payload_length;
-	__u64	setup_data;
-} __attribute__((packed));
-
-struct sys_desc_table {
-	__u16 length;
-	__u8  table[14];
-};
-
-struct efi_info {
-	__u32 efi_loader_signature;
-	__u32 efi_systab;
-	__u32 efi_memdesc_size;
-	__u32 efi_memdesc_version;
-	__u32 efi_memmap;
-	__u32 efi_memmap_size;
-	__u32 efi_systab_hi;
-	__u32 efi_memmap_hi;
-};
-
-/* The so-called "zeropage" */
-struct boot_params {
-	struct screen_info screen_info;			/* 0x000 */
-	struct apm_bios_info apm_bios_info;		/* 0x040 */
-	__u8  _pad2[12];				/* 0x054 */
-	struct ist_info ist_info;			/* 0x060 */
-	__u8  _pad3[16];				/* 0x070 */
-	__u8  hd0_info[16];	/* obsolete! */		/* 0x080 */
-	__u8  hd1_info[16];	/* obsolete! */		/* 0x090 */
-	struct sys_desc_table sys_desc_table;		/* 0x0a0 */
-	__u8  _pad4[144];				/* 0x0b0 */
-	struct edid_info edid_info;			/* 0x140 */
-	struct efi_info efi_info;			/* 0x1c0 */
-	__u32 alt_mem_k;				/* 0x1e0 */
-	__u32 scratch;		/* Scratch field! */	/* 0x1e4 */
-	__u8  e820_entries;				/* 0x1e8 */
-	__u8  eddbuf_entries;				/* 0x1e9 */
-	__u8  edd_mbr_sig_buf_entries;			/* 0x1ea */
-	__u8  _pad6[6];					/* 0x1eb */
-	struct setup_header hdr;    /* setup header */	/* 0x1f1 */
-	__u8  _pad7[0x290-0x1f1-sizeof(struct setup_header)];
-	__u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX];	/* 0x290 */
-	struct e820entry e820_map[E820MAX];		/* 0x2d0 */
-	__u8  _pad8[48];				/* 0xcd0 */
-	struct edd_info eddbuf[EDDMAXNR];		/* 0xd00 */
-	__u8  _pad9[276];				/* 0xeec */
-} __attribute__((packed));
-
-#endif /* ASM_X86__BOOTPARAM_H */
diff --git a/include/asm-x86/bug.h b/include/asm-x86/bug.h
deleted file mode 100644
index 91ad43a54c47..000000000000
--- a/include/asm-x86/bug.h
+++ /dev/null
@@ -1,39 +0,0 @@
-#ifndef ASM_X86__BUG_H
-#define ASM_X86__BUG_H
-
-#ifdef CONFIG_BUG
-#define HAVE_ARCH_BUG
-
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-
-#ifdef CONFIG_X86_32
-# define __BUG_C0	"2:\t.long 1b, %c0\n"
-#else
-# define __BUG_C0	"2:\t.quad 1b, %c0\n"
-#endif
-
-#define BUG()							\
-do {								\
-	asm volatile("1:\tud2\n"				\
-		     ".pushsection __bug_table,\"a\"\n"		\
-		     __BUG_C0					\
-		     "\t.word %c1, 0\n"				\
-		     "\t.org 2b+%c2\n"				\
-		     ".popsection"				\
-		     : : "i" (__FILE__), "i" (__LINE__),	\
-		     "i" (sizeof(struct bug_entry)));		\
-	for (;;) ;						\
-} while (0)
-
-#else
-#define BUG()							\
-do {								\
-	asm volatile("ud2");					\
-	for (;;) ;						\
-} while (0)
-#endif
-
-#endif /* !CONFIG_BUG */
-
-#include <asm-generic/bug.h>
-#endif /* ASM_X86__BUG_H */
diff --git a/include/asm-x86/bugs.h b/include/asm-x86/bugs.h
deleted file mode 100644
index dc604985f2ad..000000000000
--- a/include/asm-x86/bugs.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef ASM_X86__BUGS_H
-#define ASM_X86__BUGS_H
-
-extern void check_bugs(void);
-
-#if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32)
-int ppro_with_ram_bug(void);
-#else
-static inline int ppro_with_ram_bug(void) { return 0; }
-#endif
-
-#endif /* ASM_X86__BUGS_H */
diff --git a/include/asm-x86/byteorder.h b/include/asm-x86/byteorder.h
deleted file mode 100644
index 722f27d68105..000000000000
--- a/include/asm-x86/byteorder.h
+++ /dev/null
@@ -1,81 +0,0 @@
-#ifndef ASM_X86__BYTEORDER_H
-#define ASM_X86__BYTEORDER_H
-
-#include <asm/types.h>
-#include <linux/compiler.h>
-
-#ifdef __GNUC__
-
-#ifdef __i386__
-
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
-{
-#ifdef CONFIG_X86_BSWAP
-	asm("bswap %0" : "=r" (x) : "0" (x));
-#else
-	asm("xchgb %b0,%h0\n\t"	/* swap lower bytes	*/
-	    "rorl $16,%0\n\t"	/* swap words		*/
-	    "xchgb %b0,%h0"	/* swap higher bytes	*/
-	    : "=q" (x)
-	    : "0" (x));
-#endif
-	return x;
-}
-
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
-{
-	union {
-		struct {
-			__u32 a;
-			__u32 b;
-		} s;
-		__u64 u;
-	} v;
-	v.u = val;
-#ifdef CONFIG_X86_BSWAP
-	asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1"
-	    : "=r" (v.s.a), "=r" (v.s.b)
-	    : "0" (v.s.a), "1" (v.s.b));
-#else
-	v.s.a = ___arch__swab32(v.s.a);
-	v.s.b = ___arch__swab32(v.s.b);
-	asm("xchgl %0,%1"
-	    : "=r" (v.s.a), "=r" (v.s.b)
-	    : "0" (v.s.a), "1" (v.s.b));
-#endif
-	return v.u;
-}
-
-#else /* __i386__ */
-
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 x)
-{
-	asm("bswapq %0"
-	    : "=r" (x)
-	    : "0" (x));
-	return x;
-}
-
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
-{
-	asm("bswapl %0"
-	    : "=r" (x)
-	    : "0" (x));
-	return x;
-}
-
-#endif
-
-/* Do not define swab16.  Gcc is smart enough to recognize "C" version and
-   convert it into rotation or exhange.  */
-
-#define __arch__swab64(x) ___arch__swab64(x)
-#define __arch__swab32(x) ___arch__swab32(x)
-
-#define __BYTEORDER_HAS_U64__
-
-#endif /* __GNUC__ */
-
-#include <linux/byteorder/little_endian.h>
-
-#endif /* ASM_X86__BYTEORDER_H */
diff --git a/include/asm-x86/cache.h b/include/asm-x86/cache.h
deleted file mode 100644
index ea3f1cc06a97..000000000000
--- a/include/asm-x86/cache.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef ASM_X86__CACHE_H
-#define ASM_X86__CACHE_H
-
-/* L1 cache line size */
-#define L1_CACHE_SHIFT	(CONFIG_X86_L1_CACHE_SHIFT)
-#define L1_CACHE_BYTES	(1 << L1_CACHE_SHIFT)
-
-#define __read_mostly __attribute__((__section__(".data.read_mostly")))
-
-#ifdef CONFIG_X86_VSMP
-/* vSMP Internode cacheline shift */
-#define INTERNODE_CACHE_SHIFT (12)
-#ifdef CONFIG_SMP
-#define __cacheline_aligned_in_smp					\
-	__attribute__((__aligned__(1 << (INTERNODE_CACHE_SHIFT))))	\
-	__attribute__((__section__(".data.page_aligned")))
-#endif
-#endif
-
-#endif /* ASM_X86__CACHE_H */
diff --git a/include/asm-x86/cacheflush.h b/include/asm-x86/cacheflush.h
deleted file mode 100644
index 68840ef1b35a..000000000000
--- a/include/asm-x86/cacheflush.h
+++ /dev/null
@@ -1,118 +0,0 @@
-#ifndef ASM_X86__CACHEFLUSH_H
-#define ASM_X86__CACHEFLUSH_H
-
-/* Keep includes the same across arches.  */
-#include <linux/mm.h>
-
-/* Caches aren't brain-dead on the intel. */
-#define flush_cache_all()			do { } while (0)
-#define flush_cache_mm(mm)			do { } while (0)
-#define flush_cache_dup_mm(mm)			do { } while (0)
-#define flush_cache_range(vma, start, end)	do { } while (0)
-#define flush_cache_page(vma, vmaddr, pfn)	do { } while (0)
-#define flush_dcache_page(page)			do { } while (0)
-#define flush_dcache_mmap_lock(mapping)		do { } while (0)
-#define flush_dcache_mmap_unlock(mapping)	do { } while (0)
-#define flush_icache_range(start, end)		do { } while (0)
-#define flush_icache_page(vma, pg)		do { } while (0)
-#define flush_icache_user_range(vma, pg, adr, len)	do { } while (0)
-#define flush_cache_vmap(start, end)		do { } while (0)
-#define flush_cache_vunmap(start, end)		do { } while (0)
-
-#define copy_to_user_page(vma, page, vaddr, dst, src, len)	\
-	memcpy((dst), (src), (len))
-#define copy_from_user_page(vma, page, vaddr, dst, src, len)	\
-	memcpy((dst), (src), (len))
-
-#define PG_non_WB				PG_arch_1
-PAGEFLAG(NonWB, non_WB)
-
-/*
- * The set_memory_* API can be used to change various attributes of a virtual
- * address range. The attributes include:
- * Cachability   : UnCached, WriteCombining, WriteBack
- * Executability : eXeutable, NoteXecutable
- * Read/Write    : ReadOnly, ReadWrite
- * Presence      : NotPresent
- *
- * Within a catagory, the attributes are mutually exclusive.
- *
- * The implementation of this API will take care of various aspects that
- * are associated with changing such attributes, such as:
- * - Flushing TLBs
- * - Flushing CPU caches
- * - Making sure aliases of the memory behind the mapping don't violate
- *   coherency rules as defined by the CPU in the system.
- *
- * What this API does not do:
- * - Provide exclusion between various callers - including callers that
- *   operation on other mappings of the same physical page
- * - Restore default attributes when a page is freed
- * - Guarantee that mappings other than the requested one are
- *   in any state, other than that these do not violate rules for
- *   the CPU you have. Do not depend on any effects on other mappings,
- *   CPUs other than the one you have may have more relaxed rules.
- * The caller is required to take care of these.
- */
-
-int _set_memory_uc(unsigned long addr, int numpages);
-int _set_memory_wc(unsigned long addr, int numpages);
-int _set_memory_wb(unsigned long addr, int numpages);
-int set_memory_uc(unsigned long addr, int numpages);
-int set_memory_wc(unsigned long addr, int numpages);
-int set_memory_wb(unsigned long addr, int numpages);
-int set_memory_x(unsigned long addr, int numpages);
-int set_memory_nx(unsigned long addr, int numpages);
-int set_memory_ro(unsigned long addr, int numpages);
-int set_memory_rw(unsigned long addr, int numpages);
-int set_memory_np(unsigned long addr, int numpages);
-int set_memory_4k(unsigned long addr, int numpages);
-
-int set_memory_array_uc(unsigned long *addr, int addrinarray);
-int set_memory_array_wb(unsigned long *addr, int addrinarray);
-
-/*
- * For legacy compatibility with the old APIs, a few functions
- * are provided that work on a "struct page".
- * These functions operate ONLY on the 1:1 kernel mapping of the
- * memory that the struct page represents, and internally just
- * call the set_memory_* function. See the description of the
- * set_memory_* function for more details on conventions.
- *
- * These APIs should be considered *deprecated* and are likely going to
- * be removed in the future.
- * The reason for this is the implicit operation on the 1:1 mapping only,
- * making this not a generally useful API.
- *
- * Specifically, many users of the old APIs had a virtual address,
- * called virt_to_page() or vmalloc_to_page() on that address to
- * get a struct page* that the old API required.
- * To convert these cases, use set_memory_*() on the original
- * virtual address, do not use these functions.
- */
-
-int set_pages_uc(struct page *page, int numpages);
-int set_pages_wb(struct page *page, int numpages);
-int set_pages_x(struct page *page, int numpages);
-int set_pages_nx(struct page *page, int numpages);
-int set_pages_ro(struct page *page, int numpages);
-int set_pages_rw(struct page *page, int numpages);
-
-
-void clflush_cache_range(void *addr, unsigned int size);
-
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
-extern const int rodata_test_data;
-#endif
-
-#ifdef CONFIG_DEBUG_RODATA_TEST
-int rodata_test(void);
-#else
-static inline int rodata_test(void)
-{
-	return 0;
-}
-#endif
-
-#endif /* ASM_X86__CACHEFLUSH_H */
diff --git a/include/asm-x86/calgary.h b/include/asm-x86/calgary.h
deleted file mode 100644
index 933fd272f826..000000000000
--- a/include/asm-x86/calgary.h
+++ /dev/null
@@ -1,72 +0,0 @@
-/*
- * Derived from include/asm-powerpc/iommu.h
- *
- * Copyright IBM Corporation, 2006-2007
- *
- * Author: Jon Mason <jdmason@us.ibm.com>
- * Author: Muli Ben-Yehuda <muli@il.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#ifndef ASM_X86__CALGARY_H
-#define ASM_X86__CALGARY_H
-
-#include <linux/spinlock.h>
-#include <linux/device.h>
-#include <linux/dma-mapping.h>
-#include <linux/timer.h>
-#include <asm/types.h>
-
-struct iommu_table {
-	struct cal_chipset_ops *chip_ops; /* chipset specific funcs */
-	unsigned long  it_base;      /* mapped address of tce table */
-	unsigned long  it_hint;      /* Hint for next alloc */
-	unsigned long *it_map;       /* A simple allocation bitmap for now */
-	void __iomem  *bbar;         /* Bridge BAR */
-	u64	       tar_val;      /* Table Address Register */
-	struct timer_list watchdog_timer;
-	spinlock_t     it_lock;      /* Protects it_map */
-	unsigned int   it_size;      /* Size of iommu table in entries */
-	unsigned char  it_busno;     /* Bus number this table belongs to */
-};
-
-struct cal_chipset_ops {
-	void (*handle_quirks)(struct iommu_table *tbl, struct pci_dev *dev);
-	void (*tce_cache_blast)(struct iommu_table *tbl);
-	void (*dump_error_regs)(struct iommu_table *tbl);
-};
-
-#define TCE_TABLE_SIZE_UNSPECIFIED	~0
-#define TCE_TABLE_SIZE_64K		0
-#define TCE_TABLE_SIZE_128K		1
-#define TCE_TABLE_SIZE_256K		2
-#define TCE_TABLE_SIZE_512K		3
-#define TCE_TABLE_SIZE_1M		4
-#define TCE_TABLE_SIZE_2M		5
-#define TCE_TABLE_SIZE_4M		6
-#define TCE_TABLE_SIZE_8M		7
-
-extern int use_calgary;
-
-#ifdef CONFIG_CALGARY_IOMMU
-extern int calgary_iommu_init(void);
-extern void detect_calgary(void);
-#else
-static inline int calgary_iommu_init(void) { return 1; }
-static inline void detect_calgary(void) { return; }
-#endif
-
-#endif /* ASM_X86__CALGARY_H */
diff --git a/include/asm-x86/calling.h b/include/asm-x86/calling.h
deleted file mode 100644
index 2bc162e0ec6e..000000000000
--- a/include/asm-x86/calling.h
+++ /dev/null
@@ -1,170 +0,0 @@
-/*
- * Some macros to handle stack frames in assembly.
- */
-
-#define R15		  0
-#define R14		  8
-#define R13		 16
-#define R12		 24
-#define RBP		 32
-#define RBX		 40
-
-/* arguments: interrupts/non tracing syscalls only save upto here*/
-#define R11		 48
-#define R10		 56
-#define R9		 64
-#define R8		 72
-#define RAX		 80
-#define RCX		 88
-#define RDX		 96
-#define RSI		104
-#define RDI		112
-#define ORIG_RAX	120       /* + error_code */
-/* end of arguments */
-
-/* cpu exception frame or undefined in case of fast syscall. */
-#define RIP		128
-#define CS		136
-#define EFLAGS		144
-#define RSP		152
-#define SS		160
-
-#define ARGOFFSET	R11
-#define SWFRAME		ORIG_RAX
-
-	.macro SAVE_ARGS addskip=0, norcx=0, nor891011=0
-	subq  $9*8+\addskip, %rsp
-	CFI_ADJUST_CFA_OFFSET	9*8+\addskip
-	movq  %rdi, 8*8(%rsp)
-	CFI_REL_OFFSET	rdi, 8*8
-	movq  %rsi, 7*8(%rsp)
-	CFI_REL_OFFSET	rsi, 7*8
-	movq  %rdx, 6*8(%rsp)
-	CFI_REL_OFFSET	rdx, 6*8
-	.if \norcx
-	.else
-	movq  %rcx, 5*8(%rsp)
-	CFI_REL_OFFSET	rcx, 5*8
-	.endif
-	movq  %rax, 4*8(%rsp)
-	CFI_REL_OFFSET	rax, 4*8
-	.if \nor891011
-	.else
-	movq  %r8, 3*8(%rsp)
-	CFI_REL_OFFSET	r8,  3*8
-	movq  %r9, 2*8(%rsp)
-	CFI_REL_OFFSET	r9,  2*8
-	movq  %r10, 1*8(%rsp)
-	CFI_REL_OFFSET	r10, 1*8
-	movq  %r11, (%rsp)
-	CFI_REL_OFFSET	r11, 0*8
-	.endif
-	.endm
-
-#define ARG_SKIP	9*8
-
-	.macro RESTORE_ARGS skiprax=0, addskip=0, skiprcx=0, skipr11=0, \
-			    skipr8910=0, skiprdx=0
-	.if \skipr11
-	.else
-	movq (%rsp), %r11
-	CFI_RESTORE r11
-	.endif
-	.if \skipr8910
-	.else
-	movq 1*8(%rsp), %r10
-	CFI_RESTORE r10
-	movq 2*8(%rsp), %r9
-	CFI_RESTORE r9
-	movq 3*8(%rsp), %r8
-	CFI_RESTORE r8
-	.endif
-	.if \skiprax
-	.else
-	movq 4*8(%rsp), %rax
-	CFI_RESTORE rax
-	.endif
-	.if \skiprcx
-	.else
-	movq 5*8(%rsp), %rcx
-	CFI_RESTORE rcx
-	.endif
-	.if \skiprdx
-	.else
-	movq 6*8(%rsp), %rdx
-	CFI_RESTORE rdx
-	.endif
-	movq 7*8(%rsp), %rsi
-	CFI_RESTORE rsi
-	movq 8*8(%rsp), %rdi
-	CFI_RESTORE rdi
-	.if ARG_SKIP+\addskip > 0
-	addq $ARG_SKIP+\addskip, %rsp
-	CFI_ADJUST_CFA_OFFSET	-(ARG_SKIP+\addskip)
-	.endif
-	.endm
-
-	.macro LOAD_ARGS offset, skiprax=0
-	movq \offset(%rsp),    %r11
-	movq \offset+8(%rsp),  %r10
-	movq \offset+16(%rsp), %r9
-	movq \offset+24(%rsp), %r8
-	movq \offset+40(%rsp), %rcx
-	movq \offset+48(%rsp), %rdx
-	movq \offset+56(%rsp), %rsi
-	movq \offset+64(%rsp), %rdi
-	.if \skiprax
-	.else
-	movq \offset+72(%rsp), %rax
-	.endif
-	.endm
-
-#define REST_SKIP	6*8
-
-	.macro SAVE_REST
-	subq $REST_SKIP, %rsp
-	CFI_ADJUST_CFA_OFFSET	REST_SKIP
-	movq %rbx, 5*8(%rsp)
-	CFI_REL_OFFSET	rbx, 5*8
-	movq %rbp, 4*8(%rsp)
-	CFI_REL_OFFSET	rbp, 4*8
-	movq %r12, 3*8(%rsp)
-	CFI_REL_OFFSET	r12, 3*8
-	movq %r13, 2*8(%rsp)
-	CFI_REL_OFFSET	r13, 2*8
-	movq %r14, 1*8(%rsp)
-	CFI_REL_OFFSET	r14, 1*8
-	movq %r15, (%rsp)
-	CFI_REL_OFFSET	r15, 0*8
-	.endm
-
-	.macro RESTORE_REST
-	movq (%rsp),     %r15
-	CFI_RESTORE r15
-	movq 1*8(%rsp),  %r14
-	CFI_RESTORE r14
-	movq 2*8(%rsp),  %r13
-	CFI_RESTORE r13
-	movq 3*8(%rsp),  %r12
-	CFI_RESTORE r12
-	movq 4*8(%rsp),  %rbp
-	CFI_RESTORE rbp
-	movq 5*8(%rsp),  %rbx
-	CFI_RESTORE rbx
-	addq $REST_SKIP, %rsp
-	CFI_ADJUST_CFA_OFFSET	-(REST_SKIP)
-	.endm
-
-	.macro SAVE_ALL
-	SAVE_ARGS
-	SAVE_REST
-	.endm
-
-	.macro RESTORE_ALL addskip=0
-	RESTORE_REST
-	RESTORE_ARGS 0, \addskip
-	.endm
-
-	.macro icebp
-	.byte 0xf1
-	.endm
diff --git a/include/asm-x86/checksum.h b/include/asm-x86/checksum.h
deleted file mode 100644
index 848850fd7d62..000000000000
--- a/include/asm-x86/checksum.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "checksum_32.h"
-#else
-# include "checksum_64.h"
-#endif
diff --git a/include/asm-x86/checksum_32.h b/include/asm-x86/checksum_32.h
deleted file mode 100644
index d041e8cda227..000000000000
--- a/include/asm-x86/checksum_32.h
+++ /dev/null
@@ -1,189 +0,0 @@
-#ifndef ASM_X86__CHECKSUM_32_H
-#define ASM_X86__CHECKSUM_32_H
-
-#include <linux/in6.h>
-
-#include <asm/uaccess.h>
-
-/*
- * computes the checksum of a memory block at buff, length len,
- * and adds in "sum" (32-bit)
- *
- * returns a 32-bit number suitable for feeding into itself
- * or csum_tcpudp_magic
- *
- * this function must be called with even lengths, except
- * for the last fragment, which may be odd
- *
- * it's best to have buff aligned on a 32-bit boundary
- */
-asmlinkage __wsum csum_partial(const void *buff, int len, __wsum sum);
-
-/*
- * the same as csum_partial, but copies from src while it
- * checksums, and handles user-space pointer exceptions correctly, when needed.
- *
- * here even more important to align src and dst on a 32-bit (or even
- * better 64-bit) boundary
- */
-
-asmlinkage __wsum csum_partial_copy_generic(const void *src, void *dst,
-					    int len, __wsum sum,
-					    int *src_err_ptr, int *dst_err_ptr);
-
-/*
- *	Note: when you get a NULL pointer exception here this means someone
- *	passed in an incorrect kernel address to one of these functions.
- *
- *	If you use these functions directly please don't forget the
- *	access_ok().
- */
-static inline __wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					       int len, __wsum sum)
-{
-	return csum_partial_copy_generic(src, dst, len, sum, NULL, NULL);
-}
-
-static inline __wsum csum_partial_copy_from_user(const void __user *src,
-						 void *dst,
-						 int len, __wsum sum,
-						 int *err_ptr)
-{
-	might_sleep();
-	return csum_partial_copy_generic((__force void *)src, dst,
-					 len, sum, err_ptr, NULL);
-}
-
-/*
- *	This is a version of ip_compute_csum() optimized for IP headers,
- *	which always checksum on 4 octet boundaries.
- *
- *	By Jorge Cwik <jorge@laser.satlink.net>, adapted for linux by
- *	Arnt Gulbrandsen.
- */
-static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
-{
-	unsigned int sum;
-
-	asm volatile("movl (%1), %0	;\n"
-		     "subl $4, %2	;\n"
-		     "jbe 2f		;\n"
-		     "addl 4(%1), %0	;\n"
-		     "adcl 8(%1), %0	;\n"
-		     "adcl 12(%1), %0;\n"
-		     "1:	adcl 16(%1), %0	;\n"
-		     "lea 4(%1), %1	;\n"
-		     "decl %2	;\n"
-		     "jne 1b		;\n"
-		     "adcl $0, %0	;\n"
-		     "movl %0, %2	;\n"
-		     "shrl $16, %0	;\n"
-		     "addw %w2, %w0	;\n"
-		     "adcl $0, %0	;\n"
-		     "notl %0	;\n"
-		     "2:		;\n"
-	/* Since the input registers which are loaded with iph and ihl
-	   are modified, we must also specify them as outputs, or gcc
-	   will assume they contain their original values. */
-		     : "=r" (sum), "=r" (iph), "=r" (ihl)
-		     : "1" (iph), "2" (ihl)
-		     : "memory");
-	return (__force __sum16)sum;
-}
-
-/*
- *	Fold a partial checksum
- */
-
-static inline __sum16 csum_fold(__wsum sum)
-{
-	asm("addl %1, %0		;\n"
-	    "adcl $0xffff, %0	;\n"
-	    : "=r" (sum)
-	    : "r" ((__force u32)sum << 16),
-	      "0" ((__force u32)sum & 0xffff0000));
-	return (__force __sum16)(~(__force u32)sum >> 16);
-}
-
-static inline __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
-					__wsum sum)
-{
-	asm("addl %1, %0	;\n"
-	    "adcl %2, %0	;\n"
-	    "adcl %3, %0	;\n"
-	    "adcl $0, %0	;\n"
-	    : "=r" (sum)
-	    : "g" (daddr), "g"(saddr),
-	      "g" ((len + proto) << 8), "0" (sum));
-	return sum;
-}
-
-/*
- * computes the checksum of the TCP/UDP pseudo-header
- * returns a 16-bit checksum, already complemented
- */
-static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto,
-					__wsum sum)
-{
-	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
-}
-
-/*
- * this routine is used for miscellaneous IP-like checksums, mainly
- * in icmp.c
- */
-
-static inline __sum16 ip_compute_csum(const void *buff, int len)
-{
-    return csum_fold(csum_partial(buff, len, 0));
-}
-
-#define _HAVE_ARCH_IPV6_CSUM
-static inline __sum16 csum_ipv6_magic(const struct in6_addr *saddr,
-				      const struct in6_addr *daddr,
-				      __u32 len, unsigned short proto,
-				      __wsum sum)
-{
-	asm("addl 0(%1), %0	;\n"
-	    "adcl 4(%1), %0	;\n"
-	    "adcl 8(%1), %0	;\n"
-	    "adcl 12(%1), %0	;\n"
-	    "adcl 0(%2), %0	;\n"
-	    "adcl 4(%2), %0	;\n"
-	    "adcl 8(%2), %0	;\n"
-	    "adcl 12(%2), %0	;\n"
-	    "adcl %3, %0	;\n"
-	    "adcl %4, %0	;\n"
-	    "adcl $0, %0	;\n"
-	    : "=&r" (sum)
-	    : "r" (saddr), "r" (daddr),
-	      "r" (htonl(len)), "r" (htonl(proto)), "0" (sum));
-
-	return csum_fold(sum);
-}
-
-/*
- *	Copy and checksum to user
- */
-#define HAVE_CSUM_COPY_USER
-static inline __wsum csum_and_copy_to_user(const void *src,
-					   void __user *dst,
-					   int len, __wsum sum,
-					   int *err_ptr)
-{
-	might_sleep();
-	if (access_ok(VERIFY_WRITE, dst, len))
-		return csum_partial_copy_generic(src, (__force void *)dst,
-						 len, sum, NULL, err_ptr);
-
-	if (len)
-		*err_ptr = -EFAULT;
-
-	return (__force __wsum)-1; /* invalid checksum */
-}
-
-#endif /* ASM_X86__CHECKSUM_32_H */
diff --git a/include/asm-x86/checksum_64.h b/include/asm-x86/checksum_64.h
deleted file mode 100644
index 110f403beb89..000000000000
--- a/include/asm-x86/checksum_64.h
+++ /dev/null
@@ -1,191 +0,0 @@
-#ifndef ASM_X86__CHECKSUM_64_H
-#define ASM_X86__CHECKSUM_64_H
-
-/*
- * Checksums for x86-64
- * Copyright 2002 by Andi Kleen, SuSE Labs
- * with some code from asm-x86/checksum.h
- */
-
-#include <linux/compiler.h>
-#include <asm/uaccess.h>
-#include <asm/byteorder.h>
-
-/**
- * csum_fold - Fold and invert a 32bit checksum.
- * sum: 32bit unfolded sum
- *
- * Fold a 32bit running checksum to 16bit and invert it. This is usually
- * the last step before putting a checksum into a packet.
- * Make sure not to mix with 64bit checksums.
- */
-static inline __sum16 csum_fold(__wsum sum)
-{
-	asm("  addl %1,%0\n"
-	    "  adcl $0xffff,%0"
-	    : "=r" (sum)
-	    : "r" ((__force u32)sum << 16),
-	      "0" ((__force u32)sum & 0xffff0000));
-	return (__force __sum16)(~(__force u32)sum >> 16);
-}
-
-/*
- *	This is a version of ip_compute_csum() optimized for IP headers,
- *	which always checksum on 4 octet boundaries.
- *
- *	By Jorge Cwik <jorge@laser.satlink.net>, adapted for linux by
- *	Arnt Gulbrandsen.
- */
-
-/**
- * ip_fast_csum - Compute the IPv4 header checksum efficiently.
- * iph: ipv4 header
- * ihl: length of header / 4
- */
-static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
-{
-	unsigned int sum;
-
-	asm("  movl (%1), %0\n"
-	    "  subl $4, %2\n"
-	    "  jbe 2f\n"
-	    "  addl 4(%1), %0\n"
-	    "  adcl 8(%1), %0\n"
-	    "  adcl 12(%1), %0\n"
-	    "1: adcl 16(%1), %0\n"
-	    "  lea 4(%1), %1\n"
-	    "  decl %2\n"
-	    "  jne	1b\n"
-	    "  adcl $0, %0\n"
-	    "  movl %0, %2\n"
-	    "  shrl $16, %0\n"
-	    "  addw %w2, %w0\n"
-	    "  adcl $0, %0\n"
-	    "  notl %0\n"
-	    "2:"
-	/* Since the input registers which are loaded with iph and ihl
-	   are modified, we must also specify them as outputs, or gcc
-	   will assume they contain their original values. */
-	    : "=r" (sum), "=r" (iph), "=r" (ihl)
-	    : "1" (iph), "2" (ihl)
-	    : "memory");
-	return (__force __sum16)sum;
-}
-
-/**
- * csum_tcpup_nofold - Compute an IPv4 pseudo header checksum.
- * @saddr: source address
- * @daddr: destination address
- * @len: length of packet
- * @proto: ip protocol of packet
- * @sum: initial sum to be added in (32bit unfolded)
- *
- * Returns the pseudo header checksum the input data. Result is
- * 32bit unfolded.
- */
-static inline __wsum
-csum_tcpudp_nofold(__be32 saddr, __be32 daddr, unsigned short len,
-		   unsigned short proto, __wsum sum)
-{
-	asm("  addl %1, %0\n"
-	    "  adcl %2, %0\n"
-	    "  adcl %3, %0\n"
-	    "  adcl $0, %0\n"
-	    : "=r" (sum)
-	    : "g" (daddr), "g" (saddr),
-	      "g" ((len + proto)<<8), "0" (sum));
-	return sum;
-}
-
-
-/**
- * csum_tcpup_magic - Compute an IPv4 pseudo header checksum.
- * @saddr: source address
- * @daddr: destination address
- * @len: length of packet
- * @proto: ip protocol of packet
- * @sum: initial sum to be added in (32bit unfolded)
- *
- * Returns the 16bit pseudo header checksum the input data already
- * complemented and ready to be filled in.
- */
-static inline __sum16 csum_tcpudp_magic(__be32 saddr, __be32 daddr,
-					unsigned short len,
-					unsigned short proto, __wsum sum)
-{
-	return csum_fold(csum_tcpudp_nofold(saddr, daddr, len, proto, sum));
-}
-
-/**
- * csum_partial - Compute an internet checksum.
- * @buff: buffer to be checksummed
- * @len: length of buffer.
- * @sum: initial sum to be added in (32bit unfolded)
- *
- * Returns the 32bit unfolded internet checksum of the buffer.
- * Before filling it in it needs to be csum_fold()'ed.
- * buff should be aligned to a 64bit boundary if possible.
- */
-extern __wsum csum_partial(const void *buff, int len, __wsum sum);
-
-#define  _HAVE_ARCH_COPY_AND_CSUM_FROM_USER 1
-#define HAVE_CSUM_COPY_USER 1
-
-
-/* Do not call this directly. Use the wrappers below */
-extern __wsum csum_partial_copy_generic(const void *src, const void *dst,
-					int len, __wsum sum,
-					int *src_err_ptr, int *dst_err_ptr);
-
-
-extern __wsum csum_partial_copy_from_user(const void __user *src, void *dst,
-					  int len, __wsum isum, int *errp);
-extern __wsum csum_partial_copy_to_user(const void *src, void __user *dst,
-					int len, __wsum isum, int *errp);
-extern __wsum csum_partial_copy_nocheck(const void *src, void *dst,
-					int len, __wsum sum);
-
-/* Old names. To be removed. */
-#define csum_and_copy_to_user csum_partial_copy_to_user
-#define csum_and_copy_from_user csum_partial_copy_from_user
-
-/**
- * ip_compute_csum - Compute an 16bit IP checksum.
- * @buff: buffer address.
- * @len: length of buffer.
- *
- * Returns the 16bit folded/inverted checksum of the passed buffer.
- * Ready to fill in.
- */
-extern __sum16 ip_compute_csum(const void *buff, int len);
-
-/**
- * csum_ipv6_magic - Compute checksum of an IPv6 pseudo header.
- * @saddr: source address
- * @daddr: destination address
- * @len: length of packet
- * @proto: protocol of packet
- * @sum: initial sum (32bit unfolded) to be added in
- *
- * Computes an IPv6 pseudo header checksum. This sum is added the checksum
- * into UDP/TCP packets and contains some link layer information.
- * Returns the unfolded 32bit checksum.
- */
-
-struct in6_addr;
-
-#define _HAVE_ARCH_IPV6_CSUM 1
-extern __sum16
-csum_ipv6_magic(const struct in6_addr *saddr, const struct in6_addr *daddr,
-		__u32 len, unsigned short proto, __wsum sum);
-
-static inline unsigned add32_with_carry(unsigned a, unsigned b)
-{
-	asm("addl %2,%0\n\t"
-	    "adcl $0,%0"
-	    : "=r" (a)
-	    : "0" (a), "r" (b));
-	return a;
-}
-
-#endif /* ASM_X86__CHECKSUM_64_H */
diff --git a/include/asm-x86/cmpxchg.h b/include/asm-x86/cmpxchg.h
deleted file mode 100644
index a460fa088d4c..000000000000
--- a/include/asm-x86/cmpxchg.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "cmpxchg_32.h"
-#else
-# include "cmpxchg_64.h"
-#endif
diff --git a/include/asm-x86/cmpxchg_32.h b/include/asm-x86/cmpxchg_32.h
deleted file mode 100644
index 0622e45cdf7c..000000000000
--- a/include/asm-x86/cmpxchg_32.h
+++ /dev/null
@@ -1,344 +0,0 @@
-#ifndef ASM_X86__CMPXCHG_32_H
-#define ASM_X86__CMPXCHG_32_H
-
-#include <linux/bitops.h> /* for LOCK_PREFIX */
-
-/*
- * Note: if you use set64_bit(), __cmpxchg64(), or their variants, you
- *       you need to test for the feature in boot_cpu_data.
- */
-
-#define xchg(ptr, v)							\
-	((__typeof__(*(ptr)))__xchg((unsigned long)(v), (ptr), sizeof(*(ptr))))
-
-struct __xchg_dummy {
-	unsigned long a[100];
-};
-#define __xg(x) ((struct __xchg_dummy *)(x))
-
-/*
- * The semantics of XCHGCMP8B are a bit strange, this is why
- * there is a loop and the loading of %%eax and %%edx has to
- * be inside. This inlines well in most cases, the cached
- * cost is around ~38 cycles. (in the future we might want
- * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
- * might have an implicit FPU-save as a cost, so it's not
- * clear which path to go.)
- *
- * cmpxchg8b must be used with the lock prefix here to allow
- * the instruction to be executed atomically, see page 3-102
- * of the instruction set reference 24319102.pdf. We need
- * the reader side to see the coherent 64bit value.
- */
-static inline void __set_64bit(unsigned long long *ptr,
-			       unsigned int low, unsigned int high)
-{
-	asm volatile("\n1:\t"
-		     "movl (%0), %%eax\n\t"
-		     "movl 4(%0), %%edx\n\t"
-		     LOCK_PREFIX "cmpxchg8b (%0)\n\t"
-		     "jnz 1b"
-		     : /* no outputs */
-		     : "D"(ptr),
-		       "b"(low),
-		       "c"(high)
-		     : "ax", "dx", "memory");
-}
-
-static inline void __set_64bit_constant(unsigned long long *ptr,
-					unsigned long long value)
-{
-	__set_64bit(ptr, (unsigned int)value, (unsigned int)(value >> 32));
-}
-
-#define ll_low(x)	*(((unsigned int *)&(x)) + 0)
-#define ll_high(x)	*(((unsigned int *)&(x)) + 1)
-
-static inline void __set_64bit_var(unsigned long long *ptr,
-				   unsigned long long value)
-{
-	__set_64bit(ptr, ll_low(value), ll_high(value));
-}
-
-#define set_64bit(ptr, value)			\
-	(__builtin_constant_p((value))		\
-	 ? __set_64bit_constant((ptr), (value))	\
-	 : __set_64bit_var((ptr), (value)))
-
-#define _set_64bit(ptr, value)						\
-	(__builtin_constant_p(value)					\
-	 ? __set_64bit(ptr, (unsigned int)(value),			\
-		       (unsigned int)((value) >> 32))			\
-	 : __set_64bit(ptr, ll_low((value)), ll_high((value))))
-
-/*
- * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
- * Note 2: xchg has side effect, so that attribute volatile is necessary,
- *	  but generally the primitive is invalid, *ptr is output argument. --ANK
- */
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
-				   int size)
-{
-	switch (size) {
-	case 1:
-		asm volatile("xchgb %b0,%1"
-			     : "=q" (x)
-			     : "m" (*__xg(ptr)), "0" (x)
-			     : "memory");
-		break;
-	case 2:
-		asm volatile("xchgw %w0,%1"
-			     : "=r" (x)
-			     : "m" (*__xg(ptr)), "0" (x)
-			     : "memory");
-		break;
-	case 4:
-		asm volatile("xchgl %0,%1"
-			     : "=r" (x)
-			     : "m" (*__xg(ptr)), "0" (x)
-			     : "memory");
-		break;
-	}
-	return x;
-}
-
-/*
- * Atomic compare and exchange.  Compare OLD with MEM, if identical,
- * store NEW in MEM.  Return the initial value in MEM.  Success is
- * indicated by comparing RETURN with OLD.
- */
-
-#ifdef CONFIG_X86_CMPXCHG
-#define __HAVE_ARCH_CMPXCHG 1
-#define cmpxchg(ptr, o, n)						\
-	((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),	\
-				       (unsigned long)(n),		\
-				       sizeof(*(ptr))))
-#define sync_cmpxchg(ptr, o, n)						\
-	((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o),	\
-					    (unsigned long)(n),		\
-					    sizeof(*(ptr))))
-#define cmpxchg_local(ptr, o, n)					\
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
-					     (unsigned long)(n),	\
-					     sizeof(*(ptr))))
-#endif
-
-#ifdef CONFIG_X86_CMPXCHG64
-#define cmpxchg64(ptr, o, n)						\
-	((__typeof__(*(ptr)))__cmpxchg64((ptr), (unsigned long long)(o), \
-					 (unsigned long long)(n)))
-#define cmpxchg64_local(ptr, o, n)					\
-	((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \
-					       (unsigned long long)(n)))
-#endif
-
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
-				      unsigned long new, int size)
-{
-	unsigned long prev;
-	switch (size) {
-	case 1:
-		asm volatile(LOCK_PREFIX "cmpxchgb %b1,%2"
-			     : "=a"(prev)
-			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 2:
-		asm volatile(LOCK_PREFIX "cmpxchgw %w1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 4:
-		asm volatile(LOCK_PREFIX "cmpxchgl %1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	}
-	return old;
-}
-
-/*
- * Always use locked operations when touching memory shared with a
- * hypervisor, since the system may be SMP even if the guest kernel
- * isn't.
- */
-static inline unsigned long __sync_cmpxchg(volatile void *ptr,
-					   unsigned long old,
-					   unsigned long new, int size)
-{
-	unsigned long prev;
-	switch (size) {
-	case 1:
-		asm volatile("lock; cmpxchgb %b1,%2"
-			     : "=a"(prev)
-			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 2:
-		asm volatile("lock; cmpxchgw %w1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 4:
-		asm volatile("lock; cmpxchgl %1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	}
-	return old;
-}
-
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
-					    unsigned long old,
-					    unsigned long new, int size)
-{
-	unsigned long prev;
-	switch (size) {
-	case 1:
-		asm volatile("cmpxchgb %b1,%2"
-			     : "=a"(prev)
-			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 2:
-		asm volatile("cmpxchgw %w1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 4:
-		asm volatile("cmpxchgl %1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	}
-	return old;
-}
-
-static inline unsigned long long __cmpxchg64(volatile void *ptr,
-					     unsigned long long old,
-					     unsigned long long new)
-{
-	unsigned long long prev;
-	asm volatile(LOCK_PREFIX "cmpxchg8b %3"
-		     : "=A"(prev)
-		     : "b"((unsigned long)new),
-		       "c"((unsigned long)(new >> 32)),
-		       "m"(*__xg(ptr)),
-		       "0"(old)
-		     : "memory");
-	return prev;
-}
-
-static inline unsigned long long __cmpxchg64_local(volatile void *ptr,
-						   unsigned long long old,
-						   unsigned long long new)
-{
-	unsigned long long prev;
-	asm volatile("cmpxchg8b %3"
-		     : "=A"(prev)
-		     : "b"((unsigned long)new),
-		       "c"((unsigned long)(new >> 32)),
-		       "m"(*__xg(ptr)),
-		       "0"(old)
-		     : "memory");
-	return prev;
-}
-
-#ifndef CONFIG_X86_CMPXCHG
-/*
- * Building a kernel capable running on 80386. It may be necessary to
- * simulate the cmpxchg on the 80386 CPU. For that purpose we define
- * a function for each of the sizes we support.
- */
-
-extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
-extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
-extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);
-
-static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
-					unsigned long new, int size)
-{
-	switch (size) {
-	case 1:
-		return cmpxchg_386_u8(ptr, old, new);
-	case 2:
-		return cmpxchg_386_u16(ptr, old, new);
-	case 4:
-		return cmpxchg_386_u32(ptr, old, new);
-	}
-	return old;
-}
-
-#define cmpxchg(ptr, o, n)						\
-({									\
-	__typeof__(*(ptr)) __ret;					\
-	if (likely(boot_cpu_data.x86 > 3))				\
-		__ret = (__typeof__(*(ptr)))__cmpxchg((ptr),		\
-				(unsigned long)(o), (unsigned long)(n),	\
-				sizeof(*(ptr)));			\
-	else								\
-		__ret = (__typeof__(*(ptr)))cmpxchg_386((ptr),		\
-				(unsigned long)(o), (unsigned long)(n),	\
-				sizeof(*(ptr)));			\
-	__ret;								\
-})
-#define cmpxchg_local(ptr, o, n)					\
-({									\
-	__typeof__(*(ptr)) __ret;					\
-	if (likely(boot_cpu_data.x86 > 3))				\
-		__ret = (__typeof__(*(ptr)))__cmpxchg_local((ptr),	\
-				(unsigned long)(o), (unsigned long)(n),	\
-				sizeof(*(ptr)));			\
-	else								\
-		__ret = (__typeof__(*(ptr)))cmpxchg_386((ptr),		\
-				(unsigned long)(o), (unsigned long)(n),	\
-				sizeof(*(ptr)));			\
-	__ret;								\
-})
-#endif
-
-#ifndef CONFIG_X86_CMPXCHG64
-/*
- * Building a kernel capable running on 80386 and 80486. It may be necessary
- * to simulate the cmpxchg8b on the 80386 and 80486 CPU.
- */
-
-extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64);
-
-#define cmpxchg64(ptr, o, n)						\
-({									\
-	__typeof__(*(ptr)) __ret;					\
-	if (likely(boot_cpu_data.x86 > 4))				\
-		__ret = (__typeof__(*(ptr)))__cmpxchg64((ptr),		\
-				(unsigned long long)(o),		\
-				(unsigned long long)(n));		\
-	else								\
-		__ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr),	\
-				(unsigned long long)(o),		\
-				(unsigned long long)(n));		\
-	__ret;								\
-})
-#define cmpxchg64_local(ptr, o, n)					\
-({									\
-	__typeof__(*(ptr)) __ret;					\
-	if (likely(boot_cpu_data.x86 > 4))				\
-		__ret = (__typeof__(*(ptr)))__cmpxchg64_local((ptr),	\
-				(unsigned long long)(o),		\
-				(unsigned long long)(n));		\
-	else								\
-		__ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr),	\
-				(unsigned long long)(o),		\
-				(unsigned long long)(n));		\
-	__ret;								\
-})
-
-#endif
-
-#endif /* ASM_X86__CMPXCHG_32_H */
diff --git a/include/asm-x86/cmpxchg_64.h b/include/asm-x86/cmpxchg_64.h
deleted file mode 100644
index 63c1a5e61b99..000000000000
--- a/include/asm-x86/cmpxchg_64.h
+++ /dev/null
@@ -1,185 +0,0 @@
-#ifndef ASM_X86__CMPXCHG_64_H
-#define ASM_X86__CMPXCHG_64_H
-
-#include <asm/alternative.h> /* Provides LOCK_PREFIX */
-
-#define xchg(ptr, v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v), \
-						 (ptr), sizeof(*(ptr))))
-
-#define __xg(x) ((volatile long *)(x))
-
-static inline void set_64bit(volatile unsigned long *ptr, unsigned long val)
-{
-	*ptr = val;
-}
-
-#define _set_64bit set_64bit
-
-/*
- * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
- * Note 2: xchg has side effect, so that attribute volatile is necessary,
- *	  but generally the primitive is invalid, *ptr is output argument. --ANK
- */
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
-				   int size)
-{
-	switch (size) {
-	case 1:
-		asm volatile("xchgb %b0,%1"
-			     : "=q" (x)
-			     : "m" (*__xg(ptr)), "0" (x)
-			     : "memory");
-		break;
-	case 2:
-		asm volatile("xchgw %w0,%1"
-			     : "=r" (x)
-			     : "m" (*__xg(ptr)), "0" (x)
-			     : "memory");
-		break;
-	case 4:
-		asm volatile("xchgl %k0,%1"
-			     : "=r" (x)
-			     : "m" (*__xg(ptr)), "0" (x)
-			     : "memory");
-		break;
-	case 8:
-		asm volatile("xchgq %0,%1"
-			     : "=r" (x)
-			     : "m" (*__xg(ptr)), "0" (x)
-			     : "memory");
-		break;
-	}
-	return x;
-}
-
-/*
- * Atomic compare and exchange.  Compare OLD with MEM, if identical,
- * store NEW in MEM.  Return the initial value in MEM.  Success is
- * indicated by comparing RETURN with OLD.
- */
-
-#define __HAVE_ARCH_CMPXCHG 1
-
-static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
-				      unsigned long new, int size)
-{
-	unsigned long prev;
-	switch (size) {
-	case 1:
-		asm volatile(LOCK_PREFIX "cmpxchgb %b1,%2"
-			     : "=a"(prev)
-			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 2:
-		asm volatile(LOCK_PREFIX "cmpxchgw %w1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 4:
-		asm volatile(LOCK_PREFIX "cmpxchgl %k1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 8:
-		asm volatile(LOCK_PREFIX "cmpxchgq %1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	}
-	return old;
-}
-
-/*
- * Always use locked operations when touching memory shared with a
- * hypervisor, since the system may be SMP even if the guest kernel
- * isn't.
- */
-static inline unsigned long __sync_cmpxchg(volatile void *ptr,
-					   unsigned long old,
-					   unsigned long new, int size)
-{
-	unsigned long prev;
-	switch (size) {
-	case 1:
-		asm volatile("lock; cmpxchgb %b1,%2"
-			     : "=a"(prev)
-			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 2:
-		asm volatile("lock; cmpxchgw %w1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 4:
-		asm volatile("lock; cmpxchgl %1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	}
-	return old;
-}
-
-static inline unsigned long __cmpxchg_local(volatile void *ptr,
-					    unsigned long old,
-					    unsigned long new, int size)
-{
-	unsigned long prev;
-	switch (size) {
-	case 1:
-		asm volatile("cmpxchgb %b1,%2"
-			     : "=a"(prev)
-			     : "q"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 2:
-		asm volatile("cmpxchgw %w1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 4:
-		asm volatile("cmpxchgl %k1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	case 8:
-		asm volatile("cmpxchgq %1,%2"
-			     : "=a"(prev)
-			     : "r"(new), "m"(*__xg(ptr)), "0"(old)
-			     : "memory");
-		return prev;
-	}
-	return old;
-}
-
-#define cmpxchg(ptr, o, n)						\
-	((__typeof__(*(ptr)))__cmpxchg((ptr), (unsigned long)(o),	\
-				       (unsigned long)(n), sizeof(*(ptr))))
-#define cmpxchg64(ptr, o, n)						\
-({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg((ptr), (o), (n));					\
-})
-#define cmpxchg_local(ptr, o, n)					\
-	((__typeof__(*(ptr)))__cmpxchg_local((ptr), (unsigned long)(o),	\
-					     (unsigned long)(n),	\
-					     sizeof(*(ptr))))
-#define sync_cmpxchg(ptr, o, n)						\
-	((__typeof__(*(ptr)))__sync_cmpxchg((ptr), (unsigned long)(o),	\
-					    (unsigned long)(n),		\
-					    sizeof(*(ptr))))
-#define cmpxchg64_local(ptr, o, n)					\
-({									\
-	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
-})
-
-#endif /* ASM_X86__CMPXCHG_64_H */
diff --git a/include/asm-x86/compat.h b/include/asm-x86/compat.h
deleted file mode 100644
index 6732b150949e..000000000000
--- a/include/asm-x86/compat.h
+++ /dev/null
@@ -1,218 +0,0 @@
-#ifndef ASM_X86__COMPAT_H
-#define ASM_X86__COMPAT_H
-
-/*
- * Architecture specific compatibility types
- */
-#include <linux/types.h>
-#include <linux/sched.h>
-#include <asm/user32.h>
-
-#define COMPAT_USER_HZ	100
-
-typedef u32		compat_size_t;
-typedef s32		compat_ssize_t;
-typedef s32		compat_time_t;
-typedef s32		compat_clock_t;
-typedef s32		compat_pid_t;
-typedef u16		__compat_uid_t;
-typedef u16		__compat_gid_t;
-typedef u32		__compat_uid32_t;
-typedef u32		__compat_gid32_t;
-typedef u16		compat_mode_t;
-typedef u32		compat_ino_t;
-typedef u16		compat_dev_t;
-typedef s32		compat_off_t;
-typedef s64		compat_loff_t;
-typedef u16		compat_nlink_t;
-typedef u16		compat_ipc_pid_t;
-typedef s32		compat_daddr_t;
-typedef u32		compat_caddr_t;
-typedef __kernel_fsid_t	compat_fsid_t;
-typedef s32		compat_timer_t;
-typedef s32		compat_key_t;
-
-typedef s32		compat_int_t;
-typedef s32		compat_long_t;
-typedef s64 __attribute__((aligned(4))) compat_s64;
-typedef u32		compat_uint_t;
-typedef u32		compat_ulong_t;
-typedef u64 __attribute__((aligned(4))) compat_u64;
-
-struct compat_timespec {
-	compat_time_t	tv_sec;
-	s32		tv_nsec;
-};
-
-struct compat_timeval {
-	compat_time_t	tv_sec;
-	s32		tv_usec;
-};
-
-struct compat_stat {
-	compat_dev_t	st_dev;
-	u16		__pad1;
-	compat_ino_t	st_ino;
-	compat_mode_t	st_mode;
-	compat_nlink_t	st_nlink;
-	__compat_uid_t	st_uid;
-	__compat_gid_t	st_gid;
-	compat_dev_t	st_rdev;
-	u16		__pad2;
-	u32		st_size;
-	u32		st_blksize;
-	u32		st_blocks;
-	u32		st_atime;
-	u32		st_atime_nsec;
-	u32		st_mtime;
-	u32		st_mtime_nsec;
-	u32		st_ctime;
-	u32		st_ctime_nsec;
-	u32		__unused4;
-	u32		__unused5;
-};
-
-struct compat_flock {
-	short		l_type;
-	short		l_whence;
-	compat_off_t	l_start;
-	compat_off_t	l_len;
-	compat_pid_t	l_pid;
-};
-
-#define F_GETLK64	12	/*  using 'struct flock64' */
-#define F_SETLK64	13
-#define F_SETLKW64	14
-
-/*
- * IA32 uses 4 byte alignment for 64 bit quantities,
- * so we need to pack this structure.
- */
-struct compat_flock64 {
-	short		l_type;
-	short		l_whence;
-	compat_loff_t	l_start;
-	compat_loff_t	l_len;
-	compat_pid_t	l_pid;
-} __attribute__((packed));
-
-struct compat_statfs {
-	int		f_type;
-	int		f_bsize;
-	int		f_blocks;
-	int		f_bfree;
-	int		f_bavail;
-	int		f_files;
-	int		f_ffree;
-	compat_fsid_t	f_fsid;
-	int		f_namelen;	/* SunOS ignores this field. */
-	int		f_frsize;
-	int		f_spare[5];
-};
-
-#define COMPAT_RLIM_OLD_INFINITY	0x7fffffff
-#define COMPAT_RLIM_INFINITY		0xffffffff
-
-typedef u32		compat_old_sigset_t;	/* at least 32 bits */
-
-#define _COMPAT_NSIG		64
-#define _COMPAT_NSIG_BPW	32
-
-typedef u32               compat_sigset_word;
-
-#define COMPAT_OFF_T_MAX	0x7fffffff
-#define COMPAT_LOFF_T_MAX	0x7fffffffffffffffL
-
-struct compat_ipc64_perm {
-	compat_key_t key;
-	__compat_uid32_t uid;
-	__compat_gid32_t gid;
-	__compat_uid32_t cuid;
-	__compat_gid32_t cgid;
-	unsigned short mode;
-	unsigned short __pad1;
-	unsigned short seq;
-	unsigned short __pad2;
-	compat_ulong_t unused1;
-	compat_ulong_t unused2;
-};
-
-struct compat_semid64_ds {
-	struct compat_ipc64_perm sem_perm;
-	compat_time_t  sem_otime;
-	compat_ulong_t __unused1;
-	compat_time_t  sem_ctime;
-	compat_ulong_t __unused2;
-	compat_ulong_t sem_nsems;
-	compat_ulong_t __unused3;
-	compat_ulong_t __unused4;
-};
-
-struct compat_msqid64_ds {
-	struct compat_ipc64_perm msg_perm;
-	compat_time_t  msg_stime;
-	compat_ulong_t __unused1;
-	compat_time_t  msg_rtime;
-	compat_ulong_t __unused2;
-	compat_time_t  msg_ctime;
-	compat_ulong_t __unused3;
-	compat_ulong_t msg_cbytes;
-	compat_ulong_t msg_qnum;
-	compat_ulong_t msg_qbytes;
-	compat_pid_t   msg_lspid;
-	compat_pid_t   msg_lrpid;
-	compat_ulong_t __unused4;
-	compat_ulong_t __unused5;
-};
-
-struct compat_shmid64_ds {
-	struct compat_ipc64_perm shm_perm;
-	compat_size_t  shm_segsz;
-	compat_time_t  shm_atime;
-	compat_ulong_t __unused1;
-	compat_time_t  shm_dtime;
-	compat_ulong_t __unused2;
-	compat_time_t  shm_ctime;
-	compat_ulong_t __unused3;
-	compat_pid_t   shm_cpid;
-	compat_pid_t   shm_lpid;
-	compat_ulong_t shm_nattch;
-	compat_ulong_t __unused4;
-	compat_ulong_t __unused5;
-};
-
-/*
- * The type of struct elf_prstatus.pr_reg in compatible core dumps.
- */
-typedef struct user_regs_struct32 compat_elf_gregset_t;
-
-/*
- * A pointer passed in from user mode. This should not
- * be used for syscall parameters, just declare them
- * as pointers because the syscall entry code will have
- * appropriately converted them already.
- */
-typedef	u32		compat_uptr_t;
-
-static inline void __user *compat_ptr(compat_uptr_t uptr)
-{
-	return (void __user *)(unsigned long)uptr;
-}
-
-static inline compat_uptr_t ptr_to_compat(void __user *uptr)
-{
-	return (u32)(unsigned long)uptr;
-}
-
-static inline void __user *compat_alloc_user_space(long len)
-{
-	struct pt_regs *regs = task_pt_regs(current);
-	return (void __user *)regs->sp - len;
-}
-
-static inline int is_compat_task(void)
-{
-	return current_thread_info()->status & TS_COMPAT;
-}
-
-#endif /* ASM_X86__COMPAT_H */
diff --git a/include/asm-x86/cpu.h b/include/asm-x86/cpu.h
deleted file mode 100644
index 83a115083f0d..000000000000
--- a/include/asm-x86/cpu.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef ASM_X86__CPU_H
-#define ASM_X86__CPU_H
-
-#include <linux/device.h>
-#include <linux/cpu.h>
-#include <linux/topology.h>
-#include <linux/nodemask.h>
-#include <linux/percpu.h>
-
-struct x86_cpu {
-	struct cpu cpu;
-};
-
-#ifdef CONFIG_HOTPLUG_CPU
-extern int arch_register_cpu(int num);
-extern void arch_unregister_cpu(int);
-#endif
-
-DECLARE_PER_CPU(int, cpu_state);
-#endif /* ASM_X86__CPU_H */
diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h
deleted file mode 100644
index adfeae6586e1..000000000000
--- a/include/asm-x86/cpufeature.h
+++ /dev/null
@@ -1,271 +0,0 @@
-/*
- * Defines x86 CPU feature bits
- */
-#ifndef ASM_X86__CPUFEATURE_H
-#define ASM_X86__CPUFEATURE_H
-
-#include <asm/required-features.h>
-
-#define NCAPINTS	9	/* N 32-bit words worth of info */
-
-/*
- * Note: If the comment begins with a quoted string, that string is used
- * in /proc/cpuinfo instead of the macro name.  If the string is "",
- * this feature bit is not displayed in /proc/cpuinfo at all.
- */
-
-/* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
-#define X86_FEATURE_FPU		(0*32+ 0) /* Onboard FPU */
-#define X86_FEATURE_VME		(0*32+ 1) /* Virtual Mode Extensions */
-#define X86_FEATURE_DE		(0*32+ 2) /* Debugging Extensions */
-#define X86_FEATURE_PSE		(0*32+ 3) /* Page Size Extensions */
-#define X86_FEATURE_TSC		(0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR		(0*32+ 5) /* Model-Specific Registers */
-#define X86_FEATURE_PAE		(0*32+ 6) /* Physical Address Extensions */
-#define X86_FEATURE_MCE		(0*32+ 7) /* Machine Check Architecture */
-#define X86_FEATURE_CX8		(0*32+ 8) /* CMPXCHG8 instruction */
-#define X86_FEATURE_APIC	(0*32+ 9) /* Onboard APIC */
-#define X86_FEATURE_SEP		(0*32+11) /* SYSENTER/SYSEXIT */
-#define X86_FEATURE_MTRR	(0*32+12) /* Memory Type Range Registers */
-#define X86_FEATURE_PGE		(0*32+13) /* Page Global Enable */
-#define X86_FEATURE_MCA		(0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV	(0*32+15) /* CMOV instructions */
-					  /* (plus FCMOVcc, FCOMI with FPU) */
-#define X86_FEATURE_PAT		(0*32+16) /* Page Attribute Table */
-#define X86_FEATURE_PSE36	(0*32+17) /* 36-bit PSEs */
-#define X86_FEATURE_PN		(0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLSH	(0*32+19) /* "clflush" CLFLUSH instruction */
-#define X86_FEATURE_DS		(0*32+21) /* "dts" Debug Store */
-#define X86_FEATURE_ACPI	(0*32+22) /* ACPI via MSR */
-#define X86_FEATURE_MMX		(0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR	(0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
-#define X86_FEATURE_XMM		(0*32+25) /* "sse" */
-#define X86_FEATURE_XMM2	(0*32+26) /* "sse2" */
-#define X86_FEATURE_SELFSNOOP	(0*32+27) /* "ss" CPU self snoop */
-#define X86_FEATURE_HT		(0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC		(0*32+29) /* "tm" Automatic clock control */
-#define X86_FEATURE_IA64	(0*32+30) /* IA-64 processor */
-#define X86_FEATURE_PBE		(0*32+31) /* Pending Break Enable */
-
-/* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
-/* Don't duplicate feature flags which are redundant with Intel! */
-#define X86_FEATURE_SYSCALL	(1*32+11) /* SYSCALL/SYSRET */
-#define X86_FEATURE_MP		(1*32+19) /* MP Capable. */
-#define X86_FEATURE_NX		(1*32+20) /* Execute Disable */
-#define X86_FEATURE_MMXEXT	(1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_FXSR_OPT	(1*32+25) /* FXSAVE/FXRSTOR optimizations */
-#define X86_FEATURE_GBPAGES	(1*32+26) /* "pdpe1gb" GB pages */
-#define X86_FEATURE_RDTSCP	(1*32+27) /* RDTSCP */
-#define X86_FEATURE_LM		(1*32+29) /* Long Mode (x86-64) */
-#define X86_FEATURE_3DNOWEXT	(1*32+30) /* AMD 3DNow! extensions */
-#define X86_FEATURE_3DNOW	(1*32+31) /* 3DNow! */
-
-/* Transmeta-defined CPU features, CPUID level 0x80860001, word 2 */
-#define X86_FEATURE_RECOVERY	(2*32+ 0) /* CPU in recovery mode */
-#define X86_FEATURE_LONGRUN	(2*32+ 1) /* Longrun power control */
-#define X86_FEATURE_LRTI	(2*32+ 3) /* LongRun table interface */
-
-/* Other features, Linux-defined mapping, word 3 */
-/* This range is used for feature bits which conflict or are synthesized */
-#define X86_FEATURE_CXMMX	(3*32+ 0) /* Cyrix MMX extensions */
-#define X86_FEATURE_K6_MTRR	(3*32+ 1) /* AMD K6 nonstandard MTRRs */
-#define X86_FEATURE_CYRIX_ARR	(3*32+ 2) /* Cyrix ARRs (= MTRRs) */
-#define X86_FEATURE_CENTAUR_MCR	(3*32+ 3) /* Centaur MCRs (= MTRRs) */
-/* cpu types for specific tunings: */
-#define X86_FEATURE_K8		(3*32+ 4) /* "" Opteron, Athlon64 */
-#define X86_FEATURE_K7		(3*32+ 5) /* "" Athlon */
-#define X86_FEATURE_P3		(3*32+ 6) /* "" P3 */
-#define X86_FEATURE_P4		(3*32+ 7) /* "" P4 */
-#define X86_FEATURE_CONSTANT_TSC (3*32+ 8) /* TSC ticks at a constant rate */
-#define X86_FEATURE_UP		(3*32+ 9) /* smp kernel running on up */
-#define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
-#define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_PEBS	(3*32+12) /* Precise-Event Based Sampling */
-#define X86_FEATURE_BTS		(3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	(3*32+14) /* "" syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	(3*32+15) /* "" sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD	(3*32+16) /* rep microcode works well */
-#define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* "" Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
-#define X86_FEATURE_11AP	(3*32+19) /* "" Bad local APIC aka 11AP */
-#define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
-#define X86_FEATURE_AMDC1E	(3*32+21) /* AMD C1E detected */
-#define X86_FEATURE_XTOPOLOGY	(3*32+21) /* cpu topology enum extensions */
-
-/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
-#define X86_FEATURE_PCLMULQDQ	(4*32+ 1) /* PCLMULQDQ instruction */
-#define X86_FEATURE_DTES64	(4*32+ 2) /* 64-bit Debug Store */
-#define X86_FEATURE_MWAIT	(4*32+ 3) /* "monitor" Monitor/Mwait support */
-#define X86_FEATURE_DSCPL	(4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
-#define X86_FEATURE_VMX		(4*32+ 5) /* Hardware virtualization */
-#define X86_FEATURE_SMX		(4*32+ 6) /* Safer mode */
-#define X86_FEATURE_EST		(4*32+ 7) /* Enhanced SpeedStep */
-#define X86_FEATURE_TM2		(4*32+ 8) /* Thermal Monitor 2 */
-#define X86_FEATURE_SSSE3	(4*32+ 9) /* Supplemental SSE-3 */
-#define X86_FEATURE_CID		(4*32+10) /* Context ID */
-#define X86_FEATURE_FMA		(4*32+12) /* Fused multiply-add */
-#define X86_FEATURE_CX16	(4*32+13) /* CMPXCHG16B */
-#define X86_FEATURE_XTPR	(4*32+14) /* Send Task Priority Messages */
-#define X86_FEATURE_PDCM	(4*32+15) /* Performance Capabilities */
-#define X86_FEATURE_DCA		(4*32+18) /* Direct Cache Access */
-#define X86_FEATURE_XMM4_1	(4*32+19) /* "sse4_1" SSE-4.1 */
-#define X86_FEATURE_XMM4_2	(4*32+20) /* "sse4_2" SSE-4.2 */
-#define X86_FEATURE_X2APIC	(4*32+21) /* x2APIC */
-#define X86_FEATURE_AES		(4*32+25) /* AES instructions */
-#define X86_FEATURE_XSAVE	(4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
-#define X86_FEATURE_OSXSAVE	(4*32+27) /* "" XSAVE enabled in the OS */
-#define X86_FEATURE_AVX		(4*32+28) /* Advanced Vector Extensions */
-
-/* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE	(5*32+ 2) /* "rng" RNG present (xstore) */
-#define X86_FEATURE_XSTORE_EN	(5*32+ 3) /* "rng_en" RNG enabled */
-#define X86_FEATURE_XCRYPT	(5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
-#define X86_FEATURE_XCRYPT_EN	(5*32+ 7) /* "ace_en" on-CPU crypto enabled */
-#define X86_FEATURE_ACE2	(5*32+ 8) /* Advanced Cryptography Engine v2 */
-#define X86_FEATURE_ACE2_EN	(5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE		(5*32+10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN	(5*32+11) /* PHE enabled */
-#define X86_FEATURE_PMM		(5*32+12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN	(5*32+13) /* PMM enabled */
-
-/* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
-#define X86_FEATURE_LAHF_LM	(6*32+ 0) /* LAHF/SAHF in long mode */
-#define X86_FEATURE_CMP_LEGACY	(6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_SVM		(6*32+ 2) /* Secure virtual machine */
-#define X86_FEATURE_EXTAPIC	(6*32+ 3) /* Extended APIC space */
-#define X86_FEATURE_CR8_LEGACY	(6*32+ 4) /* CR8 in 32-bit mode */
-#define X86_FEATURE_ABM		(6*32+ 5) /* Advanced bit manipulation */
-#define X86_FEATURE_SSE4A	(6*32+ 6) /* SSE-4A */
-#define X86_FEATURE_MISALIGNSSE (6*32+ 7) /* Misaligned SSE mode */
-#define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
-#define X86_FEATURE_OSVW	(6*32+ 9) /* OS Visible Workaround */
-#define X86_FEATURE_IBS		(6*32+10) /* Instruction Based Sampling */
-#define X86_FEATURE_SSE5	(6*32+11) /* SSE-5 */
-#define X86_FEATURE_SKINIT	(6*32+12) /* SKINIT/STGI instructions */
-#define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
-
-/*
- * Auxiliary flags: Linux defined - For features scattered in various
- * CPUID levels like 0x6, 0xA etc
- */
-#define X86_FEATURE_IDA		(7*32+ 0) /* Intel Dynamic Acceleration */
-
-/* Virtualization flags: Linux defined */
-#define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
-#define X86_FEATURE_VNMI        (8*32+ 1) /* Intel Virtual NMI */
-#define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */
-#define X86_FEATURE_EPT         (8*32+ 3) /* Intel Extended Page Table */
-#define X86_FEATURE_VPID        (8*32+ 4) /* Intel Virtual Processor ID */
-
-#if defined(__KERNEL__) && !defined(__ASSEMBLY__)
-
-#include <linux/bitops.h>
-
-extern const char * const x86_cap_flags[NCAPINTS*32];
-extern const char * const x86_power_flags[32];
-
-#define test_cpu_cap(c, bit)						\
-	 test_bit(bit, (unsigned long *)((c)->x86_capability))
-
-#define cpu_has(c, bit)							\
-	(__builtin_constant_p(bit) &&					\
-	 ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) ||	\
-	   (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) ||	\
-	   (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) ||	\
-	   (((bit)>>5)==3 && (1UL<<((bit)&31) & REQUIRED_MASK3)) ||	\
-	   (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) ||	\
-	   (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) ||	\
-	   (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) ||	\
-	   (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) )	\
-	  ? 1 :								\
-	 test_cpu_cap(c, bit))
-
-#define boot_cpu_has(bit)	cpu_has(&boot_cpu_data, bit)
-
-#define set_cpu_cap(c, bit)	set_bit(bit, (unsigned long *)((c)->x86_capability))
-#define clear_cpu_cap(c, bit)	clear_bit(bit, (unsigned long *)((c)->x86_capability))
-#define setup_clear_cpu_cap(bit) do { \
-	clear_cpu_cap(&boot_cpu_data, bit);	\
-	set_bit(bit, (unsigned long *)cleared_cpu_caps); \
-} while (0)
-#define setup_force_cpu_cap(bit) do { \
-	set_cpu_cap(&boot_cpu_data, bit);	\
-	clear_bit(bit, (unsigned long *)cleared_cpu_caps);	\
-} while (0)
-
-#define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
-#define cpu_has_vme		boot_cpu_has(X86_FEATURE_VME)
-#define cpu_has_de		boot_cpu_has(X86_FEATURE_DE)
-#define cpu_has_pse		boot_cpu_has(X86_FEATURE_PSE)
-#define cpu_has_tsc		boot_cpu_has(X86_FEATURE_TSC)
-#define cpu_has_pae		boot_cpu_has(X86_FEATURE_PAE)
-#define cpu_has_pge		boot_cpu_has(X86_FEATURE_PGE)
-#define cpu_has_apic		boot_cpu_has(X86_FEATURE_APIC)
-#define cpu_has_sep		boot_cpu_has(X86_FEATURE_SEP)
-#define cpu_has_mtrr		boot_cpu_has(X86_FEATURE_MTRR)
-#define cpu_has_mmx		boot_cpu_has(X86_FEATURE_MMX)
-#define cpu_has_fxsr		boot_cpu_has(X86_FEATURE_FXSR)
-#define cpu_has_xmm		boot_cpu_has(X86_FEATURE_XMM)
-#define cpu_has_xmm2		boot_cpu_has(X86_FEATURE_XMM2)
-#define cpu_has_xmm3		boot_cpu_has(X86_FEATURE_XMM3)
-#define cpu_has_ht		boot_cpu_has(X86_FEATURE_HT)
-#define cpu_has_mp		boot_cpu_has(X86_FEATURE_MP)
-#define cpu_has_nx		boot_cpu_has(X86_FEATURE_NX)
-#define cpu_has_k6_mtrr		boot_cpu_has(X86_FEATURE_K6_MTRR)
-#define cpu_has_cyrix_arr	boot_cpu_has(X86_FEATURE_CYRIX_ARR)
-#define cpu_has_centaur_mcr	boot_cpu_has(X86_FEATURE_CENTAUR_MCR)
-#define cpu_has_xstore		boot_cpu_has(X86_FEATURE_XSTORE)
-#define cpu_has_xstore_enabled	boot_cpu_has(X86_FEATURE_XSTORE_EN)
-#define cpu_has_xcrypt		boot_cpu_has(X86_FEATURE_XCRYPT)
-#define cpu_has_xcrypt_enabled	boot_cpu_has(X86_FEATURE_XCRYPT_EN)
-#define cpu_has_ace2		boot_cpu_has(X86_FEATURE_ACE2)
-#define cpu_has_ace2_enabled	boot_cpu_has(X86_FEATURE_ACE2_EN)
-#define cpu_has_phe		boot_cpu_has(X86_FEATURE_PHE)
-#define cpu_has_phe_enabled	boot_cpu_has(X86_FEATURE_PHE_EN)
-#define cpu_has_pmm		boot_cpu_has(X86_FEATURE_PMM)
-#define cpu_has_pmm_enabled	boot_cpu_has(X86_FEATURE_PMM_EN)
-#define cpu_has_ds		boot_cpu_has(X86_FEATURE_DS)
-#define cpu_has_pebs		boot_cpu_has(X86_FEATURE_PEBS)
-#define cpu_has_clflush		boot_cpu_has(X86_FEATURE_CLFLSH)
-#define cpu_has_bts		boot_cpu_has(X86_FEATURE_BTS)
-#define cpu_has_gbpages		boot_cpu_has(X86_FEATURE_GBPAGES)
-#define cpu_has_arch_perfmon	boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
-#define cpu_has_pat		boot_cpu_has(X86_FEATURE_PAT)
-#define cpu_has_xmm4_1		boot_cpu_has(X86_FEATURE_XMM4_1)
-#define cpu_has_xmm4_2		boot_cpu_has(X86_FEATURE_XMM4_2)
-#define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
-#define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
-
-#if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
-# define cpu_has_invlpg		1
-#else
-# define cpu_has_invlpg		(boot_cpu_data.x86 > 3)
-#endif
-
-#ifdef CONFIG_X86_64
-
-#undef  cpu_has_vme
-#define cpu_has_vme		0
-
-#undef  cpu_has_pae
-#define cpu_has_pae		___BUG___
-
-#undef  cpu_has_mp
-#define cpu_has_mp		1
-
-#undef  cpu_has_k6_mtrr
-#define cpu_has_k6_mtrr		0
-
-#undef  cpu_has_cyrix_arr
-#define cpu_has_cyrix_arr	0
-
-#undef  cpu_has_centaur_mcr
-#define cpu_has_centaur_mcr	0
-
-#endif /* CONFIG_X86_64 */
-
-#endif /* defined(__KERNEL__) && !defined(__ASSEMBLY__) */
-
-#endif /* ASM_X86__CPUFEATURE_H */
diff --git a/include/asm-x86/cputime.h b/include/asm-x86/cputime.h
deleted file mode 100644
index 6d68ad7e0ea3..000000000000
--- a/include/asm-x86/cputime.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/cputime.h>
diff --git a/include/asm-x86/current.h b/include/asm-x86/current.h
deleted file mode 100644
index a863ead856f3..000000000000
--- a/include/asm-x86/current.h
+++ /dev/null
@@ -1,39 +0,0 @@
-#ifndef ASM_X86__CURRENT_H
-#define ASM_X86__CURRENT_H
-
-#ifdef CONFIG_X86_32
-#include <linux/compiler.h>
-#include <asm/percpu.h>
-
-struct task_struct;
-
-DECLARE_PER_CPU(struct task_struct *, current_task);
-static __always_inline struct task_struct *get_current(void)
-{
-	return x86_read_percpu(current_task);
-}
-
-#else /* X86_32 */
-
-#ifndef __ASSEMBLY__
-#include <asm/pda.h>
-
-struct task_struct;
-
-static __always_inline struct task_struct *get_current(void)
-{
-	return read_pda(pcurrent);
-}
-
-#else /* __ASSEMBLY__ */
-
-#include <asm/asm-offsets.h>
-#define GET_CURRENT(reg) movq %gs:(pda_pcurrent),reg
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* X86_32 */
-
-#define current get_current()
-
-#endif /* ASM_X86__CURRENT_H */
diff --git a/include/asm-x86/debugreg.h b/include/asm-x86/debugreg.h
deleted file mode 100644
index ecb6907c3ea4..000000000000
--- a/include/asm-x86/debugreg.h
+++ /dev/null
@@ -1,70 +0,0 @@
-#ifndef ASM_X86__DEBUGREG_H
-#define ASM_X86__DEBUGREG_H
-
-
-/* Indicate the register numbers for a number of the specific
-   debug registers.  Registers 0-3 contain the addresses we wish to trap on */
-#define DR_FIRSTADDR 0        /* u_debugreg[DR_FIRSTADDR] */
-#define DR_LASTADDR 3         /* u_debugreg[DR_LASTADDR]  */
-
-#define DR_STATUS 6           /* u_debugreg[DR_STATUS]     */
-#define DR_CONTROL 7          /* u_debugreg[DR_CONTROL] */
-
-/* Define a few things for the status register.  We can use this to determine
-   which debugging register was responsible for the trap.  The other bits
-   are either reserved or not of interest to us. */
-
-#define DR_TRAP0	(0x1)		/* db0 */
-#define DR_TRAP1	(0x2)		/* db1 */
-#define DR_TRAP2	(0x4)		/* db2 */
-#define DR_TRAP3	(0x8)		/* db3 */
-
-#define DR_STEP		(0x4000)	/* single-step */
-#define DR_SWITCH	(0x8000)	/* task switch */
-
-/* Now define a bunch of things for manipulating the control register.
-   The top two bytes of the control register consist of 4 fields of 4
-   bits - each field corresponds to one of the four debug registers,
-   and indicates what types of access we trap on, and how large the data
-   field is that we are looking at */
-
-#define DR_CONTROL_SHIFT 16 /* Skip this many bits in ctl register */
-#define DR_CONTROL_SIZE 4   /* 4 control bits per register */
-
-#define DR_RW_EXECUTE (0x0)   /* Settings for the access types to trap on */
-#define DR_RW_WRITE (0x1)
-#define DR_RW_READ (0x3)
-
-#define DR_LEN_1 (0x0) /* Settings for data length to trap on */
-#define DR_LEN_2 (0x4)
-#define DR_LEN_4 (0xC)
-#define DR_LEN_8 (0x8)
-
-/* The low byte to the control register determine which registers are
-   enabled.  There are 4 fields of two bits.  One bit is "local", meaning
-   that the processor will reset the bit after a task switch and the other
-   is global meaning that we have to explicitly reset the bit.  With linux,
-   you can use either one, since we explicitly zero the register when we enter
-   kernel mode. */
-
-#define DR_LOCAL_ENABLE_SHIFT 0    /* Extra shift to the local enable bit */
-#define DR_GLOBAL_ENABLE_SHIFT 1   /* Extra shift to the global enable bit */
-#define DR_ENABLE_SIZE 2           /* 2 enable bits per register */
-
-#define DR_LOCAL_ENABLE_MASK (0x55)  /* Set  local bits for all 4 regs */
-#define DR_GLOBAL_ENABLE_MASK (0xAA) /* Set global bits for all 4 regs */
-
-/* The second byte to the control register has a few special things.
-   We can slow the instruction pipeline for instructions coming via the
-   gdt or the ldt if we want to.  I am not sure why this is an advantage */
-
-#ifdef __i386__
-#define DR_CONTROL_RESERVED (0xFC00) /* Reserved by Intel */
-#else
-#define DR_CONTROL_RESERVED (0xFFFFFFFF0000FC00UL) /* Reserved */
-#endif
-
-#define DR_LOCAL_SLOWDOWN (0x100)   /* Local slow the pipeline */
-#define DR_GLOBAL_SLOWDOWN (0x200)  /* Global slow the pipeline */
-
-#endif /* ASM_X86__DEBUGREG_H */
diff --git a/include/asm-x86/delay.h b/include/asm-x86/delay.h
deleted file mode 100644
index 8a0da95b4fc5..000000000000
--- a/include/asm-x86/delay.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef ASM_X86__DELAY_H
-#define ASM_X86__DELAY_H
-
-/*
- * Copyright (C) 1993 Linus Torvalds
- *
- * Delay routines calling functions in arch/x86/lib/delay.c
- */
-
-/* Undefined functions to get compile-time errors */
-extern void __bad_udelay(void);
-extern void __bad_ndelay(void);
-
-extern void __udelay(unsigned long usecs);
-extern void __ndelay(unsigned long nsecs);
-extern void __const_udelay(unsigned long xloops);
-extern void __delay(unsigned long loops);
-
-/* 0x10c7 is 2**32 / 1000000 (rounded up) */
-#define udelay(n) (__builtin_constant_p(n) ? \
-	((n) > 20000 ? __bad_udelay() : __const_udelay((n) * 0x10c7ul)) : \
-	__udelay(n))
-
-/* 0x5 is 2**32 / 1000000000 (rounded up) */
-#define ndelay(n) (__builtin_constant_p(n) ? \
-	((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \
-	__ndelay(n))
-
-void use_tsc_delay(void);
-
-#endif /* ASM_X86__DELAY_H */
diff --git a/include/asm-x86/desc.h b/include/asm-x86/desc.h
deleted file mode 100644
index f06adac7938c..000000000000
--- a/include/asm-x86/desc.h
+++ /dev/null
@@ -1,409 +0,0 @@
-#ifndef ASM_X86__DESC_H
-#define ASM_X86__DESC_H
-
-#ifndef __ASSEMBLY__
-#include <asm/desc_defs.h>
-#include <asm/ldt.h>
-#include <asm/mmu.h>
-#include <linux/smp.h>
-
-static inline void fill_ldt(struct desc_struct *desc,
-			    const struct user_desc *info)
-{
-	desc->limit0 = info->limit & 0x0ffff;
-	desc->base0 = info->base_addr & 0x0000ffff;
-
-	desc->base1 = (info->base_addr & 0x00ff0000) >> 16;
-	desc->type = (info->read_exec_only ^ 1) << 1;
-	desc->type |= info->contents << 2;
-	desc->s = 1;
-	desc->dpl = 0x3;
-	desc->p = info->seg_not_present ^ 1;
-	desc->limit = (info->limit & 0xf0000) >> 16;
-	desc->avl = info->useable;
-	desc->d = info->seg_32bit;
-	desc->g = info->limit_in_pages;
-	desc->base2 = (info->base_addr & 0xff000000) >> 24;
-	/*
-	 * Don't allow setting of the lm bit. It is useless anyway
-	 * because 64bit system calls require __USER_CS:
-	 */
-	desc->l = 0;
-}
-
-extern struct desc_ptr idt_descr;
-extern gate_desc idt_table[];
-
-struct gdt_page {
-	struct desc_struct gdt[GDT_ENTRIES];
-} __attribute__((aligned(PAGE_SIZE)));
-DECLARE_PER_CPU(struct gdt_page, gdt_page);
-
-static inline struct desc_struct *get_cpu_gdt_table(unsigned int cpu)
-{
-	return per_cpu(gdt_page, cpu).gdt;
-}
-
-#ifdef CONFIG_X86_64
-
-static inline void pack_gate(gate_desc *gate, unsigned type, unsigned long func,
-			     unsigned dpl, unsigned ist, unsigned seg)
-{
-	gate->offset_low = PTR_LOW(func);
-	gate->segment = __KERNEL_CS;
-	gate->ist = ist;
-	gate->p = 1;
-	gate->dpl = dpl;
-	gate->zero0 = 0;
-	gate->zero1 = 0;
-	gate->type = type;
-	gate->offset_middle = PTR_MIDDLE(func);
-	gate->offset_high = PTR_HIGH(func);
-}
-
-#else
-static inline void pack_gate(gate_desc *gate, unsigned char type,
-			     unsigned long base, unsigned dpl, unsigned flags,
-			     unsigned short seg)
-{
-	gate->a = (seg << 16) | (base & 0xffff);
-	gate->b = (base & 0xffff0000) |
-		  (((0x80 | type | (dpl << 5)) & 0xff) << 8);
-}
-
-#endif
-
-static inline int desc_empty(const void *ptr)
-{
-	const u32 *desc = ptr;
-	return !(desc[0] | desc[1]);
-}
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-#define load_TR_desc() native_load_tr_desc()
-#define load_gdt(dtr) native_load_gdt(dtr)
-#define load_idt(dtr) native_load_idt(dtr)
-#define load_tr(tr) asm volatile("ltr %0"::"m" (tr))
-#define load_ldt(ldt) asm volatile("lldt %0"::"m" (ldt))
-
-#define store_gdt(dtr) native_store_gdt(dtr)
-#define store_idt(dtr) native_store_idt(dtr)
-#define store_tr(tr) (tr = native_store_tr())
-#define store_ldt(ldt) asm("sldt %0":"=m" (ldt))
-
-#define load_TLS(t, cpu) native_load_tls(t, cpu)
-#define set_ldt native_set_ldt
-
-#define write_ldt_entry(dt, entry, desc)	\
-	native_write_ldt_entry(dt, entry, desc)
-#define write_gdt_entry(dt, entry, desc, type)		\
-	native_write_gdt_entry(dt, entry, desc, type)
-#define write_idt_entry(dt, entry, g)		\
-	native_write_idt_entry(dt, entry, g)
-
-static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
-{
-}
-
-static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
-{
-}
-#endif	/* CONFIG_PARAVIRT */
-
-static inline void native_write_idt_entry(gate_desc *idt, int entry,
-					  const gate_desc *gate)
-{
-	memcpy(&idt[entry], gate, sizeof(*gate));
-}
-
-static inline void native_write_ldt_entry(struct desc_struct *ldt, int entry,
-					  const void *desc)
-{
-	memcpy(&ldt[entry], desc, 8);
-}
-
-static inline void native_write_gdt_entry(struct desc_struct *gdt, int entry,
-					  const void *desc, int type)
-{
-	unsigned int size;
-	switch (type) {
-	case DESC_TSS:
-		size = sizeof(tss_desc);
-		break;
-	case DESC_LDT:
-		size = sizeof(ldt_desc);
-		break;
-	default:
-		size = sizeof(struct desc_struct);
-		break;
-	}
-	memcpy(&gdt[entry], desc, size);
-}
-
-static inline void pack_descriptor(struct desc_struct *desc, unsigned long base,
-				   unsigned long limit, unsigned char type,
-				   unsigned char flags)
-{
-	desc->a = ((base & 0xffff) << 16) | (limit & 0xffff);
-	desc->b = (base & 0xff000000) | ((base & 0xff0000) >> 16) |
-		(limit & 0x000f0000) | ((type & 0xff) << 8) |
-		((flags & 0xf) << 20);
-	desc->p = 1;
-}
-
-
-static inline void set_tssldt_descriptor(void *d, unsigned long addr,
-					 unsigned type, unsigned size)
-{
-#ifdef CONFIG_X86_64
-	struct ldttss_desc64 *desc = d;
-	memset(desc, 0, sizeof(*desc));
-	desc->limit0 = size & 0xFFFF;
-	desc->base0 = PTR_LOW(addr);
-	desc->base1 = PTR_MIDDLE(addr) & 0xFF;
-	desc->type = type;
-	desc->p = 1;
-	desc->limit1 = (size >> 16) & 0xF;
-	desc->base2 = (PTR_MIDDLE(addr) >> 8) & 0xFF;
-	desc->base3 = PTR_HIGH(addr);
-#else
-	pack_descriptor((struct desc_struct *)d, addr, size, 0x80 | type, 0);
-#endif
-}
-
-static inline void __set_tss_desc(unsigned cpu, unsigned int entry, void *addr)
-{
-	struct desc_struct *d = get_cpu_gdt_table(cpu);
-	tss_desc tss;
-
-	/*
-	 * sizeof(unsigned long) coming from an extra "long" at the end
-	 * of the iobitmap. See tss_struct definition in processor.h
-	 *
-	 * -1? seg base+limit should be pointing to the address of the
-	 * last valid byte
-	 */
-	set_tssldt_descriptor(&tss, (unsigned long)addr, DESC_TSS,
-			      IO_BITMAP_OFFSET + IO_BITMAP_BYTES +
-			      sizeof(unsigned long) - 1);
-	write_gdt_entry(d, entry, &tss, DESC_TSS);
-}
-
-#define set_tss_desc(cpu, addr) __set_tss_desc(cpu, GDT_ENTRY_TSS, addr)
-
-static inline void native_set_ldt(const void *addr, unsigned int entries)
-{
-	if (likely(entries == 0))
-		asm volatile("lldt %w0"::"q" (0));
-	else {
-		unsigned cpu = smp_processor_id();
-		ldt_desc ldt;
-
-		set_tssldt_descriptor(&ldt, (unsigned long)addr, DESC_LDT,
-				      entries * LDT_ENTRY_SIZE - 1);
-		write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT,
-				&ldt, DESC_LDT);
-		asm volatile("lldt %w0"::"q" (GDT_ENTRY_LDT*8));
-	}
-}
-
-static inline void native_load_tr_desc(void)
-{
-	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
-}
-
-static inline void native_load_gdt(const struct desc_ptr *dtr)
-{
-	asm volatile("lgdt %0"::"m" (*dtr));
-}
-
-static inline void native_load_idt(const struct desc_ptr *dtr)
-{
-	asm volatile("lidt %0"::"m" (*dtr));
-}
-
-static inline void native_store_gdt(struct desc_ptr *dtr)
-{
-	asm volatile("sgdt %0":"=m" (*dtr));
-}
-
-static inline void native_store_idt(struct desc_ptr *dtr)
-{
-	asm volatile("sidt %0":"=m" (*dtr));
-}
-
-static inline unsigned long native_store_tr(void)
-{
-	unsigned long tr;
-	asm volatile("str %0":"=r" (tr));
-	return tr;
-}
-
-static inline void native_load_tls(struct thread_struct *t, unsigned int cpu)
-{
-	unsigned int i;
-	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
-
-	for (i = 0; i < GDT_ENTRY_TLS_ENTRIES; i++)
-		gdt[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i];
-}
-
-#define _LDT_empty(info)				\
-	((info)->base_addr		== 0	&&	\
-	 (info)->limit			== 0	&&	\
-	 (info)->contents		== 0	&&	\
-	 (info)->read_exec_only		== 1	&&	\
-	 (info)->seg_32bit		== 0	&&	\
-	 (info)->limit_in_pages		== 0	&&	\
-	 (info)->seg_not_present	== 1	&&	\
-	 (info)->useable		== 0)
-
-#ifdef CONFIG_X86_64
-#define LDT_empty(info) (_LDT_empty(info) && ((info)->lm == 0))
-#else
-#define LDT_empty(info) (_LDT_empty(info))
-#endif
-
-static inline void clear_LDT(void)
-{
-	set_ldt(NULL, 0);
-}
-
-/*
- * load one particular LDT into the current CPU
- */
-static inline void load_LDT_nolock(mm_context_t *pc)
-{
-	set_ldt(pc->ldt, pc->size);
-}
-
-static inline void load_LDT(mm_context_t *pc)
-{
-	preempt_disable();
-	load_LDT_nolock(pc);
-	preempt_enable();
-}
-
-static inline unsigned long get_desc_base(const struct desc_struct *desc)
-{
-	return desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24);
-}
-
-static inline unsigned long get_desc_limit(const struct desc_struct *desc)
-{
-	return desc->limit0 | (desc->limit << 16);
-}
-
-static inline void _set_gate(int gate, unsigned type, void *addr,
-			     unsigned dpl, unsigned ist, unsigned seg)
-{
-	gate_desc s;
-	pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg);
-	/*
-	 * does not need to be atomic because it is only done once at
-	 * setup time
-	 */
-	write_idt_entry(idt_table, gate, &s);
-}
-
-/*
- * This needs to use 'idt_table' rather than 'idt', and
- * thus use the _nonmapped_ version of the IDT, as the
- * Pentium F0 0F bugfix can have resulted in the mapped
- * IDT being write-protected.
- */
-static inline void set_intr_gate(unsigned int n, void *addr)
-{
-	BUG_ON((unsigned)n > 0xFF);
-	_set_gate(n, GATE_INTERRUPT, addr, 0, 0, __KERNEL_CS);
-}
-
-#define SYS_VECTOR_FREE		0
-#define SYS_VECTOR_ALLOCED	1
-
-extern int first_system_vector;
-extern char system_vectors[];
-
-static inline void alloc_system_vector(int vector)
-{
-	if (system_vectors[vector] == SYS_VECTOR_FREE) {
-		system_vectors[vector] = SYS_VECTOR_ALLOCED;
-		if (first_system_vector > vector)
-			first_system_vector = vector;
-	} else
-		BUG();
-}
-
-static inline void alloc_intr_gate(unsigned int n, void *addr)
-{
-	alloc_system_vector(n);
-	set_intr_gate(n, addr);
-}
-
-/*
- * This routine sets up an interrupt gate at directory privilege level 3.
- */
-static inline void set_system_intr_gate(unsigned int n, void *addr)
-{
-	BUG_ON((unsigned)n > 0xFF);
-	_set_gate(n, GATE_INTERRUPT, addr, 0x3, 0, __KERNEL_CS);
-}
-
-static inline void set_system_trap_gate(unsigned int n, void *addr)
-{
-	BUG_ON((unsigned)n > 0xFF);
-	_set_gate(n, GATE_TRAP, addr, 0x3, 0, __KERNEL_CS);
-}
-
-static inline void set_trap_gate(unsigned int n, void *addr)
-{
-	BUG_ON((unsigned)n > 0xFF);
-	_set_gate(n, GATE_TRAP, addr, 0, 0, __KERNEL_CS);
-}
-
-static inline void set_task_gate(unsigned int n, unsigned int gdt_entry)
-{
-	BUG_ON((unsigned)n > 0xFF);
-	_set_gate(n, GATE_TASK, (void *)0, 0, 0, (gdt_entry<<3));
-}
-
-static inline void set_intr_gate_ist(int n, void *addr, unsigned ist)
-{
-	BUG_ON((unsigned)n > 0xFF);
-	_set_gate(n, GATE_INTERRUPT, addr, 0, ist, __KERNEL_CS);
-}
-
-static inline void set_system_intr_gate_ist(int n, void *addr, unsigned ist)
-{
-	BUG_ON((unsigned)n > 0xFF);
-	_set_gate(n, GATE_INTERRUPT, addr, 0x3, ist, __KERNEL_CS);
-}
-
-#else
-/*
- * GET_DESC_BASE reads the descriptor base of the specified segment.
- *
- * Args:
- *    idx - descriptor index
- *    gdt - GDT pointer
- *    base - 32bit register to which the base will be written
- *    lo_w - lo word of the "base" register
- *    lo_b - lo byte of the "base" register
- *    hi_b - hi byte of the low word of the "base" register
- *
- * Example:
- *    GET_DESC_BASE(GDT_ENTRY_ESPFIX_SS, %ebx, %eax, %ax, %al, %ah)
- *    Will read the base address of GDT_ENTRY_ESPFIX_SS and put it into %eax.
- */
-#define GET_DESC_BASE(idx, gdt, base, lo_w, lo_b, hi_b) \
-	movb idx * 8 + 4(gdt), lo_b;			\
-	movb idx * 8 + 7(gdt), hi_b;			\
-	shll $16, base;					\
-	movw idx * 8 + 2(gdt), lo_w;
-
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* ASM_X86__DESC_H */
diff --git a/include/asm-x86/desc_defs.h b/include/asm-x86/desc_defs.h
deleted file mode 100644
index b881db664b46..000000000000
--- a/include/asm-x86/desc_defs.h
+++ /dev/null
@@ -1,95 +0,0 @@
-/* Written 2000 by Andi Kleen */
-#ifndef ASM_X86__DESC_DEFS_H
-#define ASM_X86__DESC_DEFS_H
-
-/*
- * Segment descriptor structure definitions, usable from both x86_64 and i386
- * archs.
- */
-
-#ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-
-/*
- * FIXME: Acessing the desc_struct through its fields is more elegant,
- * and should be the one valid thing to do. However, a lot of open code
- * still touches the a and b acessors, and doing this allow us to do it
- * incrementally. We keep the signature as a struct, rather than an union,
- * so we can get rid of it transparently in the future -- glommer
- */
-/* 8 byte segment descriptor */
-struct desc_struct {
-	union {
-		struct {
-			unsigned int a;
-			unsigned int b;
-		};
-		struct {
-			u16 limit0;
-			u16 base0;
-			unsigned base1: 8, type: 4, s: 1, dpl: 2, p: 1;
-			unsigned limit: 4, avl: 1, l: 1, d: 1, g: 1, base2: 8;
-		};
-	};
-} __attribute__((packed));
-
-enum {
-	GATE_INTERRUPT = 0xE,
-	GATE_TRAP = 0xF,
-	GATE_CALL = 0xC,
-	GATE_TASK = 0x5,
-};
-
-/* 16byte gate */
-struct gate_struct64 {
-	u16 offset_low;
-	u16 segment;
-	unsigned ist : 3, zero0 : 5, type : 5, dpl : 2, p : 1;
-	u16 offset_middle;
-	u32 offset_high;
-	u32 zero1;
-} __attribute__((packed));
-
-#define PTR_LOW(x) ((unsigned long long)(x) & 0xFFFF)
-#define PTR_MIDDLE(x) (((unsigned long long)(x) >> 16) & 0xFFFF)
-#define PTR_HIGH(x) ((unsigned long long)(x) >> 32)
-
-enum {
-	DESC_TSS = 0x9,
-	DESC_LDT = 0x2,
-	DESCTYPE_S = 0x10,	/* !system */
-};
-
-/* LDT or TSS descriptor in the GDT. 16 bytes. */
-struct ldttss_desc64 {
-	u16 limit0;
-	u16 base0;
-	unsigned base1 : 8, type : 5, dpl : 2, p : 1;
-	unsigned limit1 : 4, zero0 : 3, g : 1, base2 : 8;
-	u32 base3;
-	u32 zero1;
-} __attribute__((packed));
-
-#ifdef CONFIG_X86_64
-typedef struct gate_struct64 gate_desc;
-typedef struct ldttss_desc64 ldt_desc;
-typedef struct ldttss_desc64 tss_desc;
-#define gate_offset(g) ((g).offset_low | ((unsigned long)(g).offset_middle << 16) | ((unsigned long)(g).offset_high << 32))
-#define gate_segment(g) ((g).segment)
-#else
-typedef struct desc_struct gate_desc;
-typedef struct desc_struct ldt_desc;
-typedef struct desc_struct tss_desc;
-#define gate_offset(g)		(((g).b & 0xffff0000) | ((g).a & 0x0000ffff))
-#define gate_segment(g)		((g).a >> 16)
-#endif
-
-struct desc_ptr {
-	unsigned short size;
-	unsigned long address;
-} __attribute__((packed)) ;
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* ASM_X86__DESC_DEFS_H */
diff --git a/include/asm-x86/device.h b/include/asm-x86/device.h
deleted file mode 100644
index 1bece04c7d9d..000000000000
--- a/include/asm-x86/device.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef ASM_X86__DEVICE_H
-#define ASM_X86__DEVICE_H
-
-struct dev_archdata {
-#ifdef CONFIG_ACPI
-	void	*acpi_handle;
-#endif
-#ifdef CONFIG_X86_64
-struct dma_mapping_ops *dma_ops;
-#endif
-#ifdef CONFIG_DMAR
-	void *iommu; /* hook for IOMMU specific extension */
-#endif
-};
-
-#endif /* ASM_X86__DEVICE_H */
diff --git a/include/asm-x86/div64.h b/include/asm-x86/div64.h
deleted file mode 100644
index f9530f23f1d6..000000000000
--- a/include/asm-x86/div64.h
+++ /dev/null
@@ -1,60 +0,0 @@
-#ifndef ASM_X86__DIV64_H
-#define ASM_X86__DIV64_H
-
-#ifdef CONFIG_X86_32
-
-#include <linux/types.h>
-
-/*
- * do_div() is NOT a C function. It wants to return
- * two values (the quotient and the remainder), but
- * since that doesn't work very well in C, what it
- * does is:
- *
- * - modifies the 64-bit dividend _in_place_
- * - returns the 32-bit remainder
- *
- * This ends up being the most efficient "calling
- * convention" on x86.
- */
-#define do_div(n, base)						\
-({								\
-	unsigned long __upper, __low, __high, __mod, __base;	\
-	__base = (base);					\
-	asm("":"=a" (__low), "=d" (__high) : "A" (n));		\
-	__upper = __high;					\
-	if (__high) {						\
-		__upper = __high % (__base);			\
-		__high = __high / (__base);			\
-	}							\
-	asm("divl %2":"=a" (__low), "=d" (__mod)		\
-	    : "rm" (__base), "0" (__low), "1" (__upper));	\
-	asm("":"=A" (n) : "a" (__low), "d" (__high));		\
-	__mod;							\
-})
-
-static inline u64 div_u64_rem(u64 dividend, u32 divisor, u32 *remainder)
-{
-	union {
-		u64 v64;
-		u32 v32[2];
-	} d = { dividend };
-	u32 upper;
-
-	upper = d.v32[1];
-	d.v32[1] = 0;
-	if (upper >= divisor) {
-		d.v32[1] = upper / divisor;
-		upper %= divisor;
-	}
-	asm ("divl %2" : "=a" (d.v32[0]), "=d" (*remainder) :
-		"rm" (divisor), "0" (d.v32[0]), "1" (upper));
-	return d.v64;
-}
-#define div_u64_rem	div_u64_rem
-
-#else
-# include <asm-generic/div64.h>
-#endif /* CONFIG_X86_32 */
-
-#endif /* ASM_X86__DIV64_H */
diff --git a/include/asm-x86/dma-mapping.h b/include/asm-x86/dma-mapping.h
deleted file mode 100644
index 219c33d6361c..000000000000
--- a/include/asm-x86/dma-mapping.h
+++ /dev/null
@@ -1,308 +0,0 @@
-#ifndef ASM_X86__DMA_MAPPING_H
-#define ASM_X86__DMA_MAPPING_H
-
-/*
- * IOMMU interface. See Documentation/DMA-mapping.txt and DMA-API.txt for
- * documentation.
- */
-
-#include <linux/scatterlist.h>
-#include <asm/io.h>
-#include <asm/swiotlb.h>
-#include <asm-generic/dma-coherent.h>
-
-extern dma_addr_t bad_dma_address;
-extern int iommu_merge;
-extern struct device x86_dma_fallback_dev;
-extern int panic_on_overflow;
-
-struct dma_mapping_ops {
-	int             (*mapping_error)(struct device *dev,
-					 dma_addr_t dma_addr);
-	void*           (*alloc_coherent)(struct device *dev, size_t size,
-				dma_addr_t *dma_handle, gfp_t gfp);
-	void            (*free_coherent)(struct device *dev, size_t size,
-				void *vaddr, dma_addr_t dma_handle);
-	dma_addr_t      (*map_single)(struct device *hwdev, phys_addr_t ptr,
-				size_t size, int direction);
-	void            (*unmap_single)(struct device *dev, dma_addr_t addr,
-				size_t size, int direction);
-	void            (*sync_single_for_cpu)(struct device *hwdev,
-				dma_addr_t dma_handle, size_t size,
-				int direction);
-	void            (*sync_single_for_device)(struct device *hwdev,
-				dma_addr_t dma_handle, size_t size,
-				int direction);
-	void            (*sync_single_range_for_cpu)(struct device *hwdev,
-				dma_addr_t dma_handle, unsigned long offset,
-				size_t size, int direction);
-	void            (*sync_single_range_for_device)(struct device *hwdev,
-				dma_addr_t dma_handle, unsigned long offset,
-				size_t size, int direction);
-	void            (*sync_sg_for_cpu)(struct device *hwdev,
-				struct scatterlist *sg, int nelems,
-				int direction);
-	void            (*sync_sg_for_device)(struct device *hwdev,
-				struct scatterlist *sg, int nelems,
-				int direction);
-	int             (*map_sg)(struct device *hwdev, struct scatterlist *sg,
-				int nents, int direction);
-	void            (*unmap_sg)(struct device *hwdev,
-				struct scatterlist *sg, int nents,
-				int direction);
-	int             (*dma_supported)(struct device *hwdev, u64 mask);
-	int		is_phys;
-};
-
-extern struct dma_mapping_ops *dma_ops;
-
-static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
-{
-#ifdef CONFIG_X86_32
-	return dma_ops;
-#else
-	if (unlikely(!dev) || !dev->archdata.dma_ops)
-		return dma_ops;
-	else
-		return dev->archdata.dma_ops;
-#endif /* ASM_X86__DMA_MAPPING_H */
-}
-
-/* Make sure we keep the same behaviour */
-static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
-{
-#ifdef CONFIG_X86_32
-	return 0;
-#else
-	struct dma_mapping_ops *ops = get_dma_ops(dev);
-	if (ops->mapping_error)
-		return ops->mapping_error(dev, dma_addr);
-
-	return (dma_addr == bad_dma_address);
-#endif
-}
-
-#define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
-#define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
-#define dma_is_consistent(d, h)	(1)
-
-extern int dma_supported(struct device *hwdev, u64 mask);
-extern int dma_set_mask(struct device *dev, u64 mask);
-
-extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-					dma_addr_t *dma_addr, gfp_t flag);
-
-static inline dma_addr_t
-dma_map_single(struct device *hwdev, void *ptr, size_t size,
-	       int direction)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(direction));
-	return ops->map_single(hwdev, virt_to_phys(ptr), size, direction);
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size,
-		 int direction)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(direction));
-	if (ops->unmap_single)
-		ops->unmap_single(dev, addr, size, direction);
-}
-
-static inline int
-dma_map_sg(struct device *hwdev, struct scatterlist *sg,
-	   int nents, int direction)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(direction));
-	return ops->map_sg(hwdev, sg, nents, direction);
-}
-
-static inline void
-dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
-	     int direction)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(direction));
-	if (ops->unmap_sg)
-		ops->unmap_sg(hwdev, sg, nents, direction);
-}
-
-static inline void
-dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
-			size_t size, int direction)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(direction));
-	if (ops->sync_single_for_cpu)
-		ops->sync_single_for_cpu(hwdev, dma_handle, size, direction);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle,
-			   size_t size, int direction)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(direction));
-	if (ops->sync_single_for_device)
-		ops->sync_single_for_device(hwdev, dma_handle, size, direction);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
-			      unsigned long offset, size_t size, int direction)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(direction));
-	if (ops->sync_single_range_for_cpu)
-		ops->sync_single_range_for_cpu(hwdev, dma_handle, offset,
-					       size, direction);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle,
-				 unsigned long offset, size_t size,
-				 int direction)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(direction));
-	if (ops->sync_single_range_for_device)
-		ops->sync_single_range_for_device(hwdev, dma_handle,
-						  offset, size, direction);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-		    int nelems, int direction)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(direction));
-	if (ops->sync_sg_for_cpu)
-		ops->sync_sg_for_cpu(hwdev, sg, nelems, direction);
-	flush_write_buffers();
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
-		       int nelems, int direction)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(hwdev);
-
-	BUG_ON(!valid_dma_direction(direction));
-	if (ops->sync_sg_for_device)
-		ops->sync_sg_for_device(hwdev, sg, nelems, direction);
-
-	flush_write_buffers();
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-				      size_t offset, size_t size,
-				      int direction)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(dev);
-
-	BUG_ON(!valid_dma_direction(direction));
-	return ops->map_single(dev, page_to_phys(page) + offset,
-			       size, direction);
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
-				  size_t size, int direction)
-{
-	dma_unmap_single(dev, addr, size, direction);
-}
-
-static inline void
-dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-	enum dma_data_direction dir)
-{
-	flush_write_buffers();
-}
-
-static inline int dma_get_cache_alignment(void)
-{
-	/* no easy way to get cache size on all x86, so return the
-	 * maximum possible, to be safe */
-	return boot_cpu_data.x86_clflush_size;
-}
-
-static inline unsigned long dma_alloc_coherent_mask(struct device *dev,
-						    gfp_t gfp)
-{
-	unsigned long dma_mask = 0;
-
-	dma_mask = dev->coherent_dma_mask;
-	if (!dma_mask)
-		dma_mask = (gfp & GFP_DMA) ? DMA_24BIT_MASK : DMA_32BIT_MASK;
-
-	return dma_mask;
-}
-
-static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
-{
-#ifdef CONFIG_X86_64
-	unsigned long dma_mask = dma_alloc_coherent_mask(dev, gfp);
-
-	if (dma_mask <= DMA_32BIT_MASK && !(gfp & GFP_DMA))
-		gfp |= GFP_DMA32;
-#endif
-       return gfp;
-}
-
-static inline void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(dev);
-	void *memory;
-
-	gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
-
-	if (dma_alloc_from_coherent(dev, size, dma_handle, &memory))
-		return memory;
-
-	if (!dev) {
-		dev = &x86_dma_fallback_dev;
-		gfp |= GFP_DMA;
-	}
-
-	if (!is_device_dma_capable(dev))
-		return NULL;
-
-	if (!ops->alloc_coherent)
-		return NULL;
-
-	return ops->alloc_coherent(dev, size, dma_handle,
-				   dma_alloc_coherent_gfp_flags(dev, gfp));
-}
-
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t bus)
-{
-	struct dma_mapping_ops *ops = get_dma_ops(dev);
-
-	WARN_ON(irqs_disabled());       /* for portability */
-
-	if (dma_release_from_coherent(dev, get_order(size), vaddr))
-		return;
-
-	if (ops->free_coherent)
-		ops->free_coherent(dev, size, vaddr, bus);
-}
-
-#endif
diff --git a/include/asm-x86/dma.h b/include/asm-x86/dma.h
deleted file mode 100644
index c9f7a4eec555..000000000000
--- a/include/asm-x86/dma.h
+++ /dev/null
@@ -1,318 +0,0 @@
-/*
- * linux/include/asm/dma.h: Defines for using and allocating dma channels.
- * Written by Hennus Bergman, 1992.
- * High DMA channel support & info by Hannu Savolainen
- * and John Boyd, Nov. 1992.
- */
-
-#ifndef ASM_X86__DMA_H
-#define ASM_X86__DMA_H
-
-#include <linux/spinlock.h>	/* And spinlocks */
-#include <asm/io.h>		/* need byte IO */
-#include <linux/delay.h>
-
-#ifdef HAVE_REALLY_SLOW_DMA_CONTROLLER
-#define dma_outb	outb_p
-#else
-#define dma_outb	outb
-#endif
-
-#define dma_inb		inb
-
-/*
- * NOTES about DMA transfers:
- *
- *  controller 1: channels 0-3, byte operations, ports 00-1F
- *  controller 2: channels 4-7, word operations, ports C0-DF
- *
- *  - ALL registers are 8 bits only, regardless of transfer size
- *  - channel 4 is not used - cascades 1 into 2.
- *  - channels 0-3 are byte - addresses/counts are for physical bytes
- *  - channels 5-7 are word - addresses/counts are for physical words
- *  - transfers must not cross physical 64K (0-3) or 128K (5-7) boundaries
- *  - transfer count loaded to registers is 1 less than actual count
- *  - controller 2 offsets are all even (2x offsets for controller 1)
- *  - page registers for 5-7 don't use data bit 0, represent 128K pages
- *  - page registers for 0-3 use bit 0, represent 64K pages
- *
- * DMA transfers are limited to the lower 16MB of _physical_ memory.
- * Note that addresses loaded into registers must be _physical_ addresses,
- * not logical addresses (which may differ if paging is active).
- *
- *  Address mapping for channels 0-3:
- *
- *   A23 ... A16 A15 ... A8  A7 ... A0    (Physical addresses)
- *    |  ...  |   |  ... |   |  ... |
- *    |  ...  |   |  ... |   |  ... |
- *    |  ...  |   |  ... |   |  ... |
- *   P7  ...  P0  A7 ... A0  A7 ... A0
- * |    Page    | Addr MSB | Addr LSB |   (DMA registers)
- *
- *  Address mapping for channels 5-7:
- *
- *   A23 ... A17 A16 A15 ... A9 A8 A7 ... A1 A0    (Physical addresses)
- *    |  ...  |   \   \   ... \  \  \  ... \  \
- *    |  ...  |    \   \   ... \  \  \  ... \  (not used)
- *    |  ...  |     \   \   ... \  \  \  ... \
- *   P7  ...  P1 (0) A7 A6  ... A0 A7 A6 ... A0
- * |      Page      |  Addr MSB   |  Addr LSB  |   (DMA registers)
- *
- * Again, channels 5-7 transfer _physical_ words (16 bits), so addresses
- * and counts _must_ be word-aligned (the lowest address bit is _ignored_ at
- * the hardware level, so odd-byte transfers aren't possible).
- *
- * Transfer count (_not # bytes_) is limited to 64K, represented as actual
- * count - 1 : 64K => 0xFFFF, 1 => 0x0000.  Thus, count is always 1 or more,
- * and up to 128K bytes may be transferred on channels 5-7 in one operation.
- *
- */
-
-#define MAX_DMA_CHANNELS	8
-
-#ifdef CONFIG_X86_32
-
-/* The maximum address that we can perform a DMA transfer to on this platform */
-#define MAX_DMA_ADDRESS      (PAGE_OFFSET + 0x1000000)
-
-#else
-
-/* 16MB ISA DMA zone */
-#define MAX_DMA_PFN   ((16 * 1024 * 1024) >> PAGE_SHIFT)
-
-/* 4GB broken PCI/AGP hardware bus master zone */
-#define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT)
-
-/* Compat define for old dma zone */
-#define MAX_DMA_ADDRESS ((unsigned long)__va(MAX_DMA_PFN << PAGE_SHIFT))
-
-#endif
-
-/* 8237 DMA controllers */
-#define IO_DMA1_BASE	0x00	/* 8 bit slave DMA, channels 0..3 */
-#define IO_DMA2_BASE	0xC0	/* 16 bit master DMA, ch 4(=slave input)..7 */
-
-/* DMA controller registers */
-#define DMA1_CMD_REG		0x08	/* command register (w) */
-#define DMA1_STAT_REG		0x08	/* status register (r) */
-#define DMA1_REQ_REG		0x09    /* request register (w) */
-#define DMA1_MASK_REG		0x0A	/* single-channel mask (w) */
-#define DMA1_MODE_REG		0x0B	/* mode register (w) */
-#define DMA1_CLEAR_FF_REG	0x0C	/* clear pointer flip-flop (w) */
-#define DMA1_TEMP_REG		0x0D    /* Temporary Register (r) */
-#define DMA1_RESET_REG		0x0D	/* Master Clear (w) */
-#define DMA1_CLR_MASK_REG       0x0E    /* Clear Mask */
-#define DMA1_MASK_ALL_REG       0x0F    /* all-channels mask (w) */
-
-#define DMA2_CMD_REG		0xD0	/* command register (w) */
-#define DMA2_STAT_REG		0xD0	/* status register (r) */
-#define DMA2_REQ_REG		0xD2    /* request register (w) */
-#define DMA2_MASK_REG		0xD4	/* single-channel mask (w) */
-#define DMA2_MODE_REG		0xD6	/* mode register (w) */
-#define DMA2_CLEAR_FF_REG	0xD8	/* clear pointer flip-flop (w) */
-#define DMA2_TEMP_REG		0xDA    /* Temporary Register (r) */
-#define DMA2_RESET_REG		0xDA	/* Master Clear (w) */
-#define DMA2_CLR_MASK_REG       0xDC    /* Clear Mask */
-#define DMA2_MASK_ALL_REG       0xDE    /* all-channels mask (w) */
-
-#define DMA_ADDR_0		0x00    /* DMA address registers */
-#define DMA_ADDR_1		0x02
-#define DMA_ADDR_2		0x04
-#define DMA_ADDR_3		0x06
-#define DMA_ADDR_4		0xC0
-#define DMA_ADDR_5		0xC4
-#define DMA_ADDR_6		0xC8
-#define DMA_ADDR_7		0xCC
-
-#define DMA_CNT_0		0x01    /* DMA count registers */
-#define DMA_CNT_1		0x03
-#define DMA_CNT_2		0x05
-#define DMA_CNT_3		0x07
-#define DMA_CNT_4		0xC2
-#define DMA_CNT_5		0xC6
-#define DMA_CNT_6		0xCA
-#define DMA_CNT_7		0xCE
-
-#define DMA_PAGE_0		0x87    /* DMA page registers */
-#define DMA_PAGE_1		0x83
-#define DMA_PAGE_2		0x81
-#define DMA_PAGE_3		0x82
-#define DMA_PAGE_5		0x8B
-#define DMA_PAGE_6		0x89
-#define DMA_PAGE_7		0x8A
-
-/* I/O to memory, no autoinit, increment, single mode */
-#define DMA_MODE_READ		0x44
-/* memory to I/O, no autoinit, increment, single mode */
-#define DMA_MODE_WRITE		0x48
-/* pass thru DREQ->HRQ, DACK<-HLDA only */
-#define DMA_MODE_CASCADE	0xC0
-
-#define DMA_AUTOINIT		0x10
-
-
-extern spinlock_t  dma_spin_lock;
-
-static inline unsigned long claim_dma_lock(void)
-{
-	unsigned long flags;
-	spin_lock_irqsave(&dma_spin_lock, flags);
-	return flags;
-}
-
-static inline void release_dma_lock(unsigned long flags)
-{
-	spin_unlock_irqrestore(&dma_spin_lock, flags);
-}
-
-/* enable/disable a specific DMA channel */
-static inline void enable_dma(unsigned int dmanr)
-{
-	if (dmanr <= 3)
-		dma_outb(dmanr, DMA1_MASK_REG);
-	else
-		dma_outb(dmanr & 3, DMA2_MASK_REG);
-}
-
-static inline void disable_dma(unsigned int dmanr)
-{
-	if (dmanr <= 3)
-		dma_outb(dmanr | 4, DMA1_MASK_REG);
-	else
-		dma_outb((dmanr & 3) | 4, DMA2_MASK_REG);
-}
-
-/* Clear the 'DMA Pointer Flip Flop'.
- * Write 0 for LSB/MSB, 1 for MSB/LSB access.
- * Use this once to initialize the FF to a known state.
- * After that, keep track of it. :-)
- * --- In order to do that, the DMA routines below should ---
- * --- only be used while holding the DMA lock ! ---
- */
-static inline void clear_dma_ff(unsigned int dmanr)
-{
-	if (dmanr <= 3)
-		dma_outb(0, DMA1_CLEAR_FF_REG);
-	else
-		dma_outb(0, DMA2_CLEAR_FF_REG);
-}
-
-/* set mode (above) for a specific DMA channel */
-static inline void set_dma_mode(unsigned int dmanr, char mode)
-{
-	if (dmanr <= 3)
-		dma_outb(mode | dmanr, DMA1_MODE_REG);
-	else
-		dma_outb(mode | (dmanr & 3), DMA2_MODE_REG);
-}
-
-/* Set only the page register bits of the transfer address.
- * This is used for successive transfers when we know the contents of
- * the lower 16 bits of the DMA current address register, but a 64k boundary
- * may have been crossed.
- */
-static inline void set_dma_page(unsigned int dmanr, char pagenr)
-{
-	switch (dmanr) {
-	case 0:
-		dma_outb(pagenr, DMA_PAGE_0);
-		break;
-	case 1:
-		dma_outb(pagenr, DMA_PAGE_1);
-		break;
-	case 2:
-		dma_outb(pagenr, DMA_PAGE_2);
-		break;
-	case 3:
-		dma_outb(pagenr, DMA_PAGE_3);
-		break;
-	case 5:
-		dma_outb(pagenr & 0xfe, DMA_PAGE_5);
-		break;
-	case 6:
-		dma_outb(pagenr & 0xfe, DMA_PAGE_6);
-		break;
-	case 7:
-		dma_outb(pagenr & 0xfe, DMA_PAGE_7);
-		break;
-	}
-}
-
-
-/* Set transfer address & page bits for specific DMA channel.
- * Assumes dma flipflop is clear.
- */
-static inline void set_dma_addr(unsigned int dmanr, unsigned int a)
-{
-	set_dma_page(dmanr, a>>16);
-	if (dmanr <= 3)  {
-		dma_outb(a & 0xff, ((dmanr & 3) << 1) + IO_DMA1_BASE);
-		dma_outb((a >> 8) & 0xff, ((dmanr & 3) << 1) + IO_DMA1_BASE);
-	}  else  {
-		dma_outb((a >> 1) & 0xff, ((dmanr & 3) << 2) + IO_DMA2_BASE);
-		dma_outb((a >> 9) & 0xff, ((dmanr & 3) << 2) + IO_DMA2_BASE);
-	}
-}
-
-
-/* Set transfer size (max 64k for DMA0..3, 128k for DMA5..7) for
- * a specific DMA channel.
- * You must ensure the parameters are valid.
- * NOTE: from a manual: "the number of transfers is one more
- * than the initial word count"! This is taken into account.
- * Assumes dma flip-flop is clear.
- * NOTE 2: "count" represents _bytes_ and must be even for channels 5-7.
- */
-static inline void set_dma_count(unsigned int dmanr, unsigned int count)
-{
-	count--;
-	if (dmanr <= 3)  {
-		dma_outb(count & 0xff, ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE);
-		dma_outb((count >> 8) & 0xff,
-			 ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE);
-	} else {
-		dma_outb((count >> 1) & 0xff,
-			 ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE);
-		dma_outb((count >> 9) & 0xff,
-			 ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE);
-	}
-}
-
-
-/* Get DMA residue count. After a DMA transfer, this
- * should return zero. Reading this while a DMA transfer is
- * still in progress will return unpredictable results.
- * If called before the channel has been used, it may return 1.
- * Otherwise, it returns the number of _bytes_ left to transfer.
- *
- * Assumes DMA flip-flop is clear.
- */
-static inline int get_dma_residue(unsigned int dmanr)
-{
-	unsigned int io_port;
-	/* using short to get 16-bit wrap around */
-	unsigned short count;
-
-	io_port = (dmanr <= 3) ? ((dmanr & 3) << 1) + 1 + IO_DMA1_BASE
-		: ((dmanr & 3) << 2) + 2 + IO_DMA2_BASE;
-
-	count = 1 + dma_inb(io_port);
-	count += dma_inb(io_port) << 8;
-
-	return (dmanr <= 3) ? count : (count << 1);
-}
-
-
-/* These are in kernel/dma.c: */
-extern int request_dma(unsigned int dmanr, const char *device_id);
-extern void free_dma(unsigned int dmanr);
-
-/* From PCI */
-
-#ifdef CONFIG_PCI
-extern int isa_dma_bridge_buggy;
-#else
-#define isa_dma_bridge_buggy	(0)
-#endif
-
-#endif /* ASM_X86__DMA_H */
diff --git a/include/asm-x86/dmi.h b/include/asm-x86/dmi.h
deleted file mode 100644
index 1cff6fe81fa5..000000000000
--- a/include/asm-x86/dmi.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef ASM_X86__DMI_H
-#define ASM_X86__DMI_H
-
-#include <asm/io.h>
-
-#define DMI_MAX_DATA 2048
-
-extern int dmi_alloc_index;
-extern char dmi_alloc_data[DMI_MAX_DATA];
-
-/* This is so early that there is no good way to allocate dynamic memory.
-   Allocate data in an BSS array. */
-static inline void *dmi_alloc(unsigned len)
-{
-	int idx = dmi_alloc_index;
-	if ((dmi_alloc_index + len) > DMI_MAX_DATA)
-		return NULL;
-	dmi_alloc_index += len;
-	return dmi_alloc_data + idx;
-}
-
-/* Use early IO mappings for DMI because it's initialized early */
-#define dmi_ioremap early_ioremap
-#define dmi_iounmap early_iounmap
-
-#endif /* ASM_X86__DMI_H */
diff --git a/include/asm-x86/ds.h b/include/asm-x86/ds.h
deleted file mode 100644
index c3c953a45b21..000000000000
--- a/include/asm-x86/ds.h
+++ /dev/null
@@ -1,238 +0,0 @@
-/*
- * Debug Store (DS) support
- *
- * This provides a low-level interface to the hardware's Debug Store
- * feature that is used for branch trace store (BTS) and
- * precise-event based sampling (PEBS).
- *
- * It manages:
- * - per-thread and per-cpu allocation of BTS and PEBS
- * - buffer memory allocation (optional)
- * - buffer overflow handling
- * - buffer access
- *
- * It assumes:
- * - get_task_struct on all parameter tasks
- * - current is allowed to trace parameter tasks
- *
- *
- * Copyright (C) 2007-2008 Intel Corporation.
- * Markus Metzger <markus.t.metzger@intel.com>, 2007-2008
- */
-
-#ifndef ASM_X86__DS_H
-#define ASM_X86__DS_H
-
-#ifdef CONFIG_X86_DS
-
-#include <linux/types.h>
-#include <linux/init.h>
-
-
-struct task_struct;
-
-/*
- * Request BTS or PEBS
- *
- * Due to alignement constraints, the actual buffer may be slightly
- * smaller than the requested or provided buffer.
- *
- * Returns 0 on success; -Eerrno otherwise
- *
- * task: the task to request recording for;
- *       NULL for per-cpu recording on the current cpu
- * base: the base pointer for the (non-pageable) buffer;
- *       NULL if buffer allocation requested
- * size: the size of the requested or provided buffer
- * ovfl: pointer to a function to be called on buffer overflow;
- *       NULL if cyclic buffer requested
- */
-typedef void (*ds_ovfl_callback_t)(struct task_struct *);
-extern int ds_request_bts(struct task_struct *task, void *base, size_t size,
-			  ds_ovfl_callback_t ovfl);
-extern int ds_request_pebs(struct task_struct *task, void *base, size_t size,
-			   ds_ovfl_callback_t ovfl);
-
-/*
- * Release BTS or PEBS resources
- *
- * Frees buffers allocated on ds_request.
- *
- * Returns 0 on success; -Eerrno otherwise
- *
- * task: the task to release resources for;
- *       NULL to release resources for the current cpu
- */
-extern int ds_release_bts(struct task_struct *task);
-extern int ds_release_pebs(struct task_struct *task);
-
-/*
- * Return the (array) index of the write pointer.
- * (assuming an array of BTS/PEBS records)
- *
- * Returns -Eerrno on error
- *
- * task: the task to access;
- *       NULL to access the current cpu
- * pos (out): if not NULL, will hold the result
- */
-extern int ds_get_bts_index(struct task_struct *task, size_t *pos);
-extern int ds_get_pebs_index(struct task_struct *task, size_t *pos);
-
-/*
- * Return the (array) index one record beyond the end of the array.
- * (assuming an array of BTS/PEBS records)
- *
- * Returns -Eerrno on error
- *
- * task: the task to access;
- *       NULL to access the current cpu
- * pos (out): if not NULL, will hold the result
- */
-extern int ds_get_bts_end(struct task_struct *task, size_t *pos);
-extern int ds_get_pebs_end(struct task_struct *task, size_t *pos);
-
-/*
- * Provide a pointer to the BTS/PEBS record at parameter index.
- * (assuming an array of BTS/PEBS records)
- *
- * The pointer points directly into the buffer. The user is
- * responsible for copying the record.
- *
- * Returns the size of a single record on success; -Eerrno on error
- *
- * task: the task to access;
- *       NULL to access the current cpu
- * index: the index of the requested record
- * record (out): pointer to the requested record
- */
-extern int ds_access_bts(struct task_struct *task,
-			 size_t index, const void **record);
-extern int ds_access_pebs(struct task_struct *task,
-			  size_t index, const void **record);
-
-/*
- * Write one or more BTS/PEBS records at the write pointer index and
- * advance the write pointer.
- *
- * If size is not a multiple of the record size, trailing bytes are
- * zeroed out.
- *
- * May result in one or more overflow notifications.
- *
- * If called during overflow handling, that is, with index >=
- * interrupt threshold, the write will wrap around.
- *
- * An overflow notification is given if and when the interrupt
- * threshold is reached during or after the write.
- *
- * Returns the number of bytes written or -Eerrno.
- *
- * task: the task to access;
- *       NULL to access the current cpu
- * buffer: the buffer to write
- * size: the size of the buffer
- */
-extern int ds_write_bts(struct task_struct *task,
-			const void *buffer, size_t size);
-extern int ds_write_pebs(struct task_struct *task,
-			 const void *buffer, size_t size);
-
-/*
- * Same as ds_write_bts/pebs, but omit ownership checks.
- *
- * This is needed to have some other task than the owner of the
- * BTS/PEBS buffer or the parameter task itself write into the
- * respective buffer.
- */
-extern int ds_unchecked_write_bts(struct task_struct *task,
-				  const void *buffer, size_t size);
-extern int ds_unchecked_write_pebs(struct task_struct *task,
-				   const void *buffer, size_t size);
-
-/*
- * Reset the write pointer of the BTS/PEBS buffer.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * task: the task to access;
- *       NULL to access the current cpu
- */
-extern int ds_reset_bts(struct task_struct *task);
-extern int ds_reset_pebs(struct task_struct *task);
-
-/*
- * Clear the BTS/PEBS buffer and reset the write pointer.
- * The entire buffer will be zeroed out.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * task: the task to access;
- *       NULL to access the current cpu
- */
-extern int ds_clear_bts(struct task_struct *task);
-extern int ds_clear_pebs(struct task_struct *task);
-
-/*
- * Provide the PEBS counter reset value.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * task: the task to access;
- *       NULL to access the current cpu
- * value (out): the counter reset value
- */
-extern int ds_get_pebs_reset(struct task_struct *task, u64 *value);
-
-/*
- * Set the PEBS counter reset value.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * task: the task to access;
- *       NULL to access the current cpu
- * value: the new counter reset value
- */
-extern int ds_set_pebs_reset(struct task_struct *task, u64 value);
-
-/*
- * Initialization
- */
-struct cpuinfo_x86;
-extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
-
-
-
-/*
- * The DS context - part of struct thread_struct.
- */
-struct ds_context {
-	/* pointer to the DS configuration; goes into MSR_IA32_DS_AREA */
-	unsigned char *ds;
-	/* the owner of the BTS and PEBS configuration, respectively */
-	struct task_struct *owner[2];
-	/* buffer overflow notification function for BTS and PEBS */
-	ds_ovfl_callback_t callback[2];
-	/* the original buffer address */
-	void *buffer[2];
-	/* the number of allocated pages for on-request allocated buffers */
-	unsigned int pages[2];
-	/* use count */
-	unsigned long count;
-	/* a pointer to the context location inside the thread_struct
-	 * or the per_cpu context array */
-	struct ds_context **this;
-	/* a pointer to the task owning this context, or NULL, if the
-	 * context is owned by a cpu */
-	struct task_struct *task;
-};
-
-/* called by exit_thread() to free leftover contexts */
-extern void ds_free(struct ds_context *context);
-
-#else /* CONFIG_X86_DS */
-
-#define ds_init_intel(config) do {} while (0)
-
-#endif /* CONFIG_X86_DS */
-#endif /* ASM_X86__DS_H */
diff --git a/include/asm-x86/dwarf2.h b/include/asm-x86/dwarf2.h
deleted file mode 100644
index 21d1bc32ad7c..000000000000
--- a/include/asm-x86/dwarf2.h
+++ /dev/null
@@ -1,61 +0,0 @@
-#ifndef ASM_X86__DWARF2_H
-#define ASM_X86__DWARF2_H
-
-#ifndef __ASSEMBLY__
-#warning "asm/dwarf2.h should be only included in pure assembly files"
-#endif
-
-/*
-   Macros for dwarf2 CFI unwind table entries.
-   See "as.info" for details on these pseudo ops. Unfortunately
-   they are only supported in very new binutils, so define them
-   away for older version.
- */
-
-#ifdef CONFIG_AS_CFI
-
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
-
-#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
-#else
-#define CFI_SIGNAL_FRAME
-#endif
-
-#else
-
-/* Due to the structure of pre-exisiting code, don't use assembler line
-   comment character # to ignore the arguments. Instead, use a dummy macro. */
-.macro cfi_ignore a=0, b=0, c=0, d=0
-.endm
-
-#define CFI_STARTPROC	cfi_ignore
-#define CFI_ENDPROC	cfi_ignore
-#define CFI_DEF_CFA	cfi_ignore
-#define CFI_DEF_CFA_REGISTER	cfi_ignore
-#define CFI_DEF_CFA_OFFSET	cfi_ignore
-#define CFI_ADJUST_CFA_OFFSET	cfi_ignore
-#define CFI_OFFSET	cfi_ignore
-#define CFI_REL_OFFSET	cfi_ignore
-#define CFI_REGISTER	cfi_ignore
-#define CFI_RESTORE	cfi_ignore
-#define CFI_REMEMBER_STATE cfi_ignore
-#define CFI_RESTORE_STATE cfi_ignore
-#define CFI_UNDEFINED cfi_ignore
-#define CFI_SIGNAL_FRAME cfi_ignore
-
-#endif
-
-#endif /* ASM_X86__DWARF2_H */
diff --git a/include/asm-x86/e820.h b/include/asm-x86/e820.h
deleted file mode 100644
index 5abbdec06bd2..000000000000
--- a/include/asm-x86/e820.h
+++ /dev/null
@@ -1,146 +0,0 @@
-#ifndef ASM_X86__E820_H
-#define ASM_X86__E820_H
-#define E820MAP	0x2d0		/* our map */
-#define E820MAX	128		/* number of entries in E820MAP */
-
-/*
- * Legacy E820 BIOS limits us to 128 (E820MAX) nodes due to the
- * constrained space in the zeropage.  If we have more nodes than
- * that, and if we've booted off EFI firmware, then the EFI tables
- * passed us from the EFI firmware can list more nodes.  Size our
- * internal memory map tables to have room for these additional
- * nodes, based on up to three entries per node for which the
- * kernel was built: MAX_NUMNODES == (1 << CONFIG_NODES_SHIFT),
- * plus E820MAX, allowing space for the possible duplicate E820
- * entries that might need room in the same arrays, prior to the
- * call to sanitize_e820_map() to remove duplicates.  The allowance
- * of three memory map entries per node is "enough" entries for
- * the initial hardware platform motivating this mechanism to make
- * use of additional EFI map entries.  Future platforms may want
- * to allow more than three entries per node or otherwise refine
- * this size.
- */
-
-/*
- * Odd: 'make headers_check' complains about numa.h if I try
- * to collapse the next two #ifdef lines to a single line:
- *	#if defined(__KERNEL__) && defined(CONFIG_EFI)
- */
-#ifdef __KERNEL__
-#ifdef CONFIG_EFI
-#include <linux/numa.h>
-#define E820_X_MAX (E820MAX + 3 * MAX_NUMNODES)
-#else	/* ! CONFIG_EFI */
-#define E820_X_MAX E820MAX
-#endif
-#else	/* ! __KERNEL__ */
-#define E820_X_MAX E820MAX
-#endif
-
-#define E820NR	0x1e8		/* # entries in E820MAP */
-
-#define E820_RAM	1
-#define E820_RESERVED	2
-#define E820_ACPI	3
-#define E820_NVS	4
-#define E820_UNUSABLE	5
-
-/* reserved RAM used by kernel itself */
-#define E820_RESERVED_KERN        128
-
-#ifndef __ASSEMBLY__
-struct e820entry {
-	__u64 addr;	/* start of memory segment */
-	__u64 size;	/* size of memory segment */
-	__u32 type;	/* type of memory segment */
-} __attribute__((packed));
-
-struct e820map {
-	__u32 nr_map;
-	struct e820entry map[E820_X_MAX];
-};
-
-#ifdef __KERNEL__
-/* see comment in arch/x86/kernel/e820.c */
-extern struct e820map e820;
-extern struct e820map e820_saved;
-
-extern unsigned long pci_mem_start;
-extern int e820_any_mapped(u64 start, u64 end, unsigned type);
-extern int e820_all_mapped(u64 start, u64 end, unsigned type);
-extern void e820_add_region(u64 start, u64 size, int type);
-extern void e820_print_map(char *who);
-extern int
-sanitize_e820_map(struct e820entry *biosmap, int max_nr_map, int *pnr_map);
-extern u64 e820_update_range(u64 start, u64 size, unsigned old_type,
-			       unsigned new_type);
-extern u64 e820_remove_range(u64 start, u64 size, unsigned old_type,
-			     int checktype);
-extern void update_e820(void);
-extern void e820_setup_gap(void);
-extern int e820_search_gap(unsigned long *gapstart, unsigned long *gapsize,
-			unsigned long start_addr, unsigned long long end_addr);
-struct setup_data;
-extern void parse_e820_ext(struct setup_data *data, unsigned long pa_data);
-
-#if defined(CONFIG_X86_64) || \
-	(defined(CONFIG_X86_32) && defined(CONFIG_HIBERNATION))
-extern void e820_mark_nosave_regions(unsigned long limit_pfn);
-#else
-static inline void e820_mark_nosave_regions(unsigned long limit_pfn)
-{
-}
-#endif
-
-#ifdef CONFIG_MEMTEST
-extern void early_memtest(unsigned long start, unsigned long end);
-#else
-static inline void early_memtest(unsigned long start, unsigned long end)
-{
-}
-#endif
-
-extern unsigned long end_user_pfn;
-
-extern u64 find_e820_area(u64 start, u64 end, u64 size, u64 align);
-extern u64 find_e820_area_size(u64 start, u64 *sizep, u64 align);
-extern void reserve_early(u64 start, u64 end, char *name);
-extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
-extern void free_early(u64 start, u64 end);
-extern void early_res_to_bootmem(u64 start, u64 end);
-extern u64 early_reserve_e820(u64 startt, u64 sizet, u64 align);
-
-extern unsigned long e820_end_of_ram_pfn(void);
-extern unsigned long e820_end_of_low_ram_pfn(void);
-extern int e820_find_active_region(const struct e820entry *ei,
-				  unsigned long start_pfn,
-				  unsigned long last_pfn,
-				  unsigned long *ei_startpfn,
-				  unsigned long *ei_endpfn);
-extern void e820_register_active_regions(int nid, unsigned long start_pfn,
-					 unsigned long end_pfn);
-extern u64 e820_hole_size(u64 start, u64 end);
-extern void finish_e820_parsing(void);
-extern void e820_reserve_resources(void);
-extern void e820_reserve_resources_late(void);
-extern void setup_memory_map(void);
-extern char *default_machine_specific_memory_setup(void);
-extern char *machine_specific_memory_setup(void);
-extern char *memory_setup(void);
-#endif /* __KERNEL__ */
-#endif /* __ASSEMBLY__ */
-
-#define ISA_START_ADDRESS	0xa0000
-#define ISA_END_ADDRESS		0x100000
-#define is_ISA_range(s, e) ((s) >= ISA_START_ADDRESS && (e) < ISA_END_ADDRESS)
-
-#define BIOS_BEGIN		0x000a0000
-#define BIOS_END		0x00100000
-
-#ifdef __KERNEL__
-#include <linux/ioport.h>
-
-#define HIGH_MEMORY	(1024*1024)
-#endif /* __KERNEL__ */
-
-#endif /* ASM_X86__E820_H */
diff --git a/include/asm-x86/edac.h b/include/asm-x86/edac.h
deleted file mode 100644
index 9493c5b27bbd..000000000000
--- a/include/asm-x86/edac.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef ASM_X86__EDAC_H
-#define ASM_X86__EDAC_H
-
-/* ECC atomic, DMA, SMP and interrupt safe scrub function */
-
-static inline void atomic_scrub(void *va, u32 size)
-{
-	u32 i, *virt_addr = va;
-
-	/*
-	 * Very carefully read and write to memory atomically so we
-	 * are interrupt, DMA and SMP safe.
-	 */
-	for (i = 0; i < size / 4; i++, virt_addr++)
-		asm volatile("lock; addl $0, %0"::"m" (*virt_addr));
-}
-
-#endif /* ASM_X86__EDAC_H */
diff --git a/include/asm-x86/efi.h b/include/asm-x86/efi.h
deleted file mode 100644
index 313438e63348..000000000000
--- a/include/asm-x86/efi.h
+++ /dev/null
@@ -1,110 +0,0 @@
-#ifndef ASM_X86__EFI_H
-#define ASM_X86__EFI_H
-
-#ifdef CONFIG_X86_32
-
-extern unsigned long asmlinkage efi_call_phys(void *, ...);
-
-#define efi_call_phys0(f)		efi_call_phys(f)
-#define efi_call_phys1(f, a1)		efi_call_phys(f, a1)
-#define efi_call_phys2(f, a1, a2)	efi_call_phys(f, a1, a2)
-#define efi_call_phys3(f, a1, a2, a3)	efi_call_phys(f, a1, a2, a3)
-#define efi_call_phys4(f, a1, a2, a3, a4)	\
-	efi_call_phys(f, a1, a2, a3, a4)
-#define efi_call_phys5(f, a1, a2, a3, a4, a5)	\
-	efi_call_phys(f, a1, a2, a3, a4, a5)
-#define efi_call_phys6(f, a1, a2, a3, a4, a5, a6)	\
-	efi_call_phys(f, a1, a2, a3, a4, a5, a6)
-/*
- * Wrap all the virtual calls in a way that forces the parameters on the stack.
- */
-
-#define efi_call_virt(f, args...) \
-	((efi_##f##_t __attribute__((regparm(0)))*)efi.systab->runtime->f)(args)
-
-#define efi_call_virt0(f)		efi_call_virt(f)
-#define efi_call_virt1(f, a1)		efi_call_virt(f, a1)
-#define efi_call_virt2(f, a1, a2)	efi_call_virt(f, a1, a2)
-#define efi_call_virt3(f, a1, a2, a3)	efi_call_virt(f, a1, a2, a3)
-#define efi_call_virt4(f, a1, a2, a3, a4)	\
-	efi_call_virt(f, a1, a2, a3, a4)
-#define efi_call_virt5(f, a1, a2, a3, a4, a5)	\
-	efi_call_virt(f, a1, a2, a3, a4, a5)
-#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)	\
-	efi_call_virt(f, a1, a2, a3, a4, a5, a6)
-
-#define efi_ioremap(addr, size)			ioremap_cache(addr, size)
-
-#else /* !CONFIG_X86_32 */
-
-#define MAX_EFI_IO_PAGES	100
-
-extern u64 efi_call0(void *fp);
-extern u64 efi_call1(void *fp, u64 arg1);
-extern u64 efi_call2(void *fp, u64 arg1, u64 arg2);
-extern u64 efi_call3(void *fp, u64 arg1, u64 arg2, u64 arg3);
-extern u64 efi_call4(void *fp, u64 arg1, u64 arg2, u64 arg3, u64 arg4);
-extern u64 efi_call5(void *fp, u64 arg1, u64 arg2, u64 arg3,
-		     u64 arg4, u64 arg5);
-extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
-		     u64 arg4, u64 arg5, u64 arg6);
-
-#define efi_call_phys0(f)			\
-	efi_call0((void *)(f))
-#define efi_call_phys1(f, a1)			\
-	efi_call1((void *)(f), (u64)(a1))
-#define efi_call_phys2(f, a1, a2)			\
-	efi_call2((void *)(f), (u64)(a1), (u64)(a2))
-#define efi_call_phys3(f, a1, a2, a3)				\
-	efi_call3((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3))
-#define efi_call_phys4(f, a1, a2, a3, a4)				\
-	efi_call4((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3),		\
-		  (u64)(a4))
-#define efi_call_phys5(f, a1, a2, a3, a4, a5)				\
-	efi_call5((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3),		\
-		  (u64)(a4), (u64)(a5))
-#define efi_call_phys6(f, a1, a2, a3, a4, a5, a6)			\
-	efi_call6((void *)(f), (u64)(a1), (u64)(a2), (u64)(a3),		\
-		  (u64)(a4), (u64)(a5), (u64)(a6))
-
-#define efi_call_virt0(f)				\
-	efi_call0((void *)(efi.systab->runtime->f))
-#define efi_call_virt1(f, a1)					\
-	efi_call1((void *)(efi.systab->runtime->f), (u64)(a1))
-#define efi_call_virt2(f, a1, a2)					\
-	efi_call2((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2))
-#define efi_call_virt3(f, a1, a2, a3)					\
-	efi_call3((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3))
-#define efi_call_virt4(f, a1, a2, a3, a4)				\
-	efi_call4((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4))
-#define efi_call_virt5(f, a1, a2, a3, a4, a5)				\
-	efi_call5((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4), (u64)(a5))
-#define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)			\
-	efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
-		  (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
-
-extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size);
-
-#endif /* CONFIG_X86_32 */
-
-extern void efi_reserve_early(void);
-extern void efi_call_phys_prelog(void);
-extern void efi_call_phys_epilog(void);
-
-#ifndef CONFIG_EFI
-/*
- * IF EFI is not configured, have the EFI calls return -ENOSYS.
- */
-#define efi_call0(_f)					(-ENOSYS)
-#define efi_call1(_f, _a1)				(-ENOSYS)
-#define efi_call2(_f, _a1, _a2)				(-ENOSYS)
-#define efi_call3(_f, _a1, _a2, _a3)			(-ENOSYS)
-#define efi_call4(_f, _a1, _a2, _a3, _a4)		(-ENOSYS)
-#define efi_call5(_f, _a1, _a2, _a3, _a4, _a5)		(-ENOSYS)
-#define efi_call6(_f, _a1, _a2, _a3, _a4, _a5, _a6)	(-ENOSYS)
-#endif /* CONFIG_EFI */
-
-#endif /* ASM_X86__EFI_H */
diff --git a/include/asm-x86/elf.h b/include/asm-x86/elf.h
deleted file mode 100644
index 26bc15f01e78..000000000000
--- a/include/asm-x86/elf.h
+++ /dev/null
@@ -1,336 +0,0 @@
-#ifndef ASM_X86__ELF_H
-#define ASM_X86__ELF_H
-
-/*
- * ELF register definitions..
- */
-
-#include <asm/ptrace.h>
-#include <asm/user.h>
-#include <asm/auxvec.h>
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof(struct user_regs_struct) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_i387_struct elf_fpregset_t;
-
-#ifdef __i386__
-
-typedef struct user_fxsr_struct elf_fpxregset_t;
-
-#define R_386_NONE	0
-#define R_386_32	1
-#define R_386_PC32	2
-#define R_386_GOT32	3
-#define R_386_PLT32	4
-#define R_386_COPY	5
-#define R_386_GLOB_DAT	6
-#define R_386_JMP_SLOT	7
-#define R_386_RELATIVE	8
-#define R_386_GOTOFF	9
-#define R_386_GOTPC	10
-#define R_386_NUM	11
-
-/*
- * These are used to set parameters in the core dumps.
- */
-#define ELF_CLASS	ELFCLASS32
-#define ELF_DATA	ELFDATA2LSB
-#define ELF_ARCH	EM_386
-
-#else
-
-/* x86-64 relocation types */
-#define R_X86_64_NONE		0	/* No reloc */
-#define R_X86_64_64		1	/* Direct 64 bit  */
-#define R_X86_64_PC32		2	/* PC relative 32 bit signed */
-#define R_X86_64_GOT32		3	/* 32 bit GOT entry */
-#define R_X86_64_PLT32		4	/* 32 bit PLT address */
-#define R_X86_64_COPY		5	/* Copy symbol at runtime */
-#define R_X86_64_GLOB_DAT	6	/* Create GOT entry */
-#define R_X86_64_JUMP_SLOT	7	/* Create PLT entry */
-#define R_X86_64_RELATIVE	8	/* Adjust by program base */
-#define R_X86_64_GOTPCREL	9	/* 32 bit signed pc relative
-					   offset to GOT */
-#define R_X86_64_32		10	/* Direct 32 bit zero extended */
-#define R_X86_64_32S		11	/* Direct 32 bit sign extended */
-#define R_X86_64_16		12	/* Direct 16 bit zero extended */
-#define R_X86_64_PC16		13	/* 16 bit sign extended pc relative */
-#define R_X86_64_8		14	/* Direct 8 bit sign extended  */
-#define R_X86_64_PC8		15	/* 8 bit sign extended pc relative */
-
-#define R_X86_64_NUM		16
-
-/*
- * These are used to set parameters in the core dumps.
- */
-#define ELF_CLASS	ELFCLASS64
-#define ELF_DATA	ELFDATA2LSB
-#define ELF_ARCH	EM_X86_64
-
-#endif
-
-#include <asm/vdso.h>
-
-extern unsigned int vdso_enabled;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch_ia32(x) \
-	(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
-
-#include <asm/processor.h>
-#include <asm/system.h>
-
-#ifdef CONFIG_X86_32
-#include <asm/desc.h>
-
-#define elf_check_arch(x)	elf_check_arch_ia32(x)
-
-/* SVR4/i386 ABI (pages 3-31, 3-32) says that when the program starts %edx
-   contains a pointer to a function which might be registered using `atexit'.
-   This provides a mean for the dynamic linker to call DT_FINI functions for
-   shared libraries that have been loaded before the code runs.
-
-   A value of 0 tells we have no such handler.
-
-   We might as well make sure everything else is cleared too (except for %esp),
-   just to make things more deterministic.
- */
-#define ELF_PLAT_INIT(_r, load_addr)		\
-	do {					\
-	_r->bx = 0; _r->cx = 0; _r->dx = 0;	\
-	_r->si = 0; _r->di = 0; _r->bp = 0;	\
-	_r->ax = 0;				\
-} while (0)
-
-/*
- * regs is struct pt_regs, pr_reg is elf_gregset_t (which is
- * now struct_user_regs, they are different)
- */
-
-#define ELF_CORE_COPY_REGS(pr_reg, regs)	\
-do {						\
-	pr_reg[0] = regs->bx;			\
-	pr_reg[1] = regs->cx;			\
-	pr_reg[2] = regs->dx;			\
-	pr_reg[3] = regs->si;			\
-	pr_reg[4] = regs->di;			\
-	pr_reg[5] = regs->bp;			\
-	pr_reg[6] = regs->ax;			\
-	pr_reg[7] = regs->ds & 0xffff;		\
-	pr_reg[8] = regs->es & 0xffff;		\
-	pr_reg[9] = regs->fs & 0xffff;		\
-	savesegment(gs, pr_reg[10]);		\
-	pr_reg[11] = regs->orig_ax;		\
-	pr_reg[12] = regs->ip;			\
-	pr_reg[13] = regs->cs & 0xffff;		\
-	pr_reg[14] = regs->flags;		\
-	pr_reg[15] = regs->sp;			\
-	pr_reg[16] = regs->ss & 0xffff;		\
-} while (0);
-
-#define ELF_PLATFORM	(utsname()->machine)
-#define set_personality_64bit()	do { } while (0)
-
-#else /* CONFIG_X86_32 */
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x)			\
-	((x)->e_machine == EM_X86_64)
-
-#define compat_elf_check_arch(x)	elf_check_arch_ia32(x)
-
-static inline void start_ia32_thread(struct pt_regs *regs, u32 ip, u32 sp)
-{
-	loadsegment(fs, 0);
-	loadsegment(ds, __USER32_DS);
-	loadsegment(es, __USER32_DS);
-	load_gs_index(0);
-	regs->ip = ip;
-	regs->sp = sp;
-	regs->flags = X86_EFLAGS_IF;
-	regs->cs = __USER32_CS;
-	regs->ss = __USER32_DS;
-}
-
-static inline void elf_common_init(struct thread_struct *t,
-				   struct pt_regs *regs, const u16 ds)
-{
-	regs->ax = regs->bx = regs->cx = regs->dx = 0;
-	regs->si = regs->di = regs->bp = 0;
-	regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0;
-	regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
-	t->fs = t->gs = 0;
-	t->fsindex = t->gsindex = 0;
-	t->ds = t->es = ds;
-}
-
-#define ELF_PLAT_INIT(_r, load_addr)			\
-do {							\
-	elf_common_init(&current->thread, _r, 0);	\
-	clear_thread_flag(TIF_IA32);			\
-} while (0)
-
-#define	COMPAT_ELF_PLAT_INIT(regs, load_addr)		\
-	elf_common_init(&current->thread, regs, __USER_DS)
-
-#define	compat_start_thread(regs, ip, sp)		\
-do {							\
-	start_ia32_thread(regs, ip, sp);		\
-	set_fs(USER_DS);				\
-} while (0)
-
-#define COMPAT_SET_PERSONALITY(ex)			\
-do {							\
-	if (test_thread_flag(TIF_IA32))			\
-		clear_thread_flag(TIF_ABI_PENDING);	\
-	else						\
-		set_thread_flag(TIF_ABI_PENDING);	\
-	current->personality |= force_personality32;	\
-} while (0)
-
-#define COMPAT_ELF_PLATFORM			("i686")
-
-/*
- * regs is struct pt_regs, pr_reg is elf_gregset_t (which is
- * now struct_user_regs, they are different). Assumes current is the process
- * getting dumped.
- */
-
-#define ELF_CORE_COPY_REGS(pr_reg, regs)			\
-do {								\
-	unsigned v;						\
-	(pr_reg)[0] = (regs)->r15;				\
-	(pr_reg)[1] = (regs)->r14;				\
-	(pr_reg)[2] = (regs)->r13;				\
-	(pr_reg)[3] = (regs)->r12;				\
-	(pr_reg)[4] = (regs)->bp;				\
-	(pr_reg)[5] = (regs)->bx;				\
-	(pr_reg)[6] = (regs)->r11;				\
-	(pr_reg)[7] = (regs)->r10;				\
-	(pr_reg)[8] = (regs)->r9;				\
-	(pr_reg)[9] = (regs)->r8;				\
-	(pr_reg)[10] = (regs)->ax;				\
-	(pr_reg)[11] = (regs)->cx;				\
-	(pr_reg)[12] = (regs)->dx;				\
-	(pr_reg)[13] = (regs)->si;				\
-	(pr_reg)[14] = (regs)->di;				\
-	(pr_reg)[15] = (regs)->orig_ax;				\
-	(pr_reg)[16] = (regs)->ip;				\
-	(pr_reg)[17] = (regs)->cs;				\
-	(pr_reg)[18] = (regs)->flags;				\
-	(pr_reg)[19] = (regs)->sp;				\
-	(pr_reg)[20] = (regs)->ss;				\
-	(pr_reg)[21] = current->thread.fs;			\
-	(pr_reg)[22] = current->thread.gs;			\
-	asm("movl %%ds,%0" : "=r" (v)); (pr_reg)[23] = v;	\
-	asm("movl %%es,%0" : "=r" (v)); (pr_reg)[24] = v;	\
-	asm("movl %%fs,%0" : "=r" (v)); (pr_reg)[25] = v;	\
-	asm("movl %%gs,%0" : "=r" (v)); (pr_reg)[26] = v;	\
-} while (0);
-
-/* I'm not sure if we can use '-' here */
-#define ELF_PLATFORM       ("x86_64")
-extern void set_personality_64bit(void);
-extern unsigned int sysctl_vsyscall32;
-extern int force_personality32;
-
-#endif /* !CONFIG_X86_32 */
-
-#define CORE_DUMP_USE_REGSET
-#define USE_ELF_CORE_DUMP
-#define ELF_EXEC_PAGESIZE	4096
-
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE		(TASK_SIZE / 3 * 2)
-
-/* This yields a mask that user programs can use to figure out what
-   instruction set this CPU supports.  This could be done in user space,
-   but it's not easy, and we've already done it here.  */
-
-#define ELF_HWCAP		(boot_cpu_data.x86_capability[0])
-
-/* This yields a string that ld.so will use to load implementation
-   specific libraries for optimization.  This is more specific in
-   intent than poking at uname or /proc/cpuinfo.
-
-   For the moment, we have only optimizations for the Intel generations,
-   but that could change... */
-
-#define SET_PERSONALITY(ex) set_personality_64bit()
-
-/*
- * An executable for which elf_read_implies_exec() returns TRUE will
- * have the READ_IMPLIES_EXEC personality flag set automatically.
- */
-#define elf_read_implies_exec(ex, executable_stack)	\
-	(executable_stack != EXSTACK_DISABLE_X)
-
-struct task_struct;
-
-#define	ARCH_DLINFO_IA32(vdso_enabled)					\
-do {									\
-	if (vdso_enabled) {						\
-		NEW_AUX_ENT(AT_SYSINFO,	VDSO_ENTRY);			\
-		NEW_AUX_ENT(AT_SYSINFO_EHDR, VDSO_CURRENT_BASE);	\
-	}								\
-} while (0)
-
-#ifdef CONFIG_X86_32
-
-#define VDSO_HIGH_BASE		(__fix_to_virt(FIX_VDSO))
-
-#define ARCH_DLINFO		ARCH_DLINFO_IA32(vdso_enabled)
-
-/* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
-
-#else /* CONFIG_X86_32 */
-
-#define VDSO_HIGH_BASE		0xffffe000U /* CONFIG_COMPAT_VDSO address */
-
-/* 1GB for 64bit, 8MB for 32bit */
-#define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff)
-
-#define ARCH_DLINFO							\
-do {									\
-	if (vdso_enabled)						\
-		NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
-			    (unsigned long)current->mm->context.vdso);	\
-} while (0)
-
-#define AT_SYSINFO		32
-
-#define COMPAT_ARCH_DLINFO	ARCH_DLINFO_IA32(sysctl_vsyscall32)
-
-#define COMPAT_ELF_ET_DYN_BASE	(TASK_UNMAPPED_BASE + 0x1000000)
-
-#endif /* !CONFIG_X86_32 */
-
-#define VDSO_CURRENT_BASE	((unsigned long)current->mm->context.vdso)
-
-#define VDSO_ENTRY							\
-	((unsigned long)VDSO32_SYMBOL(VDSO_CURRENT_BASE, vsyscall))
-
-struct linux_binprm;
-
-#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
-extern int arch_setup_additional_pages(struct linux_binprm *bprm,
-				       int executable_stack);
-
-extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
-#define compat_arch_setup_additional_pages	syscall32_setup_pages
-
-extern unsigned long arch_randomize_brk(struct mm_struct *mm);
-#define arch_randomize_brk arch_randomize_brk
-
-#endif /* ASM_X86__ELF_H */
diff --git a/include/asm-x86/emergency-restart.h b/include/asm-x86/emergency-restart.h
deleted file mode 100644
index 190d0d8b71e3..000000000000
--- a/include/asm-x86/emergency-restart.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef ASM_X86__EMERGENCY_RESTART_H
-#define ASM_X86__EMERGENCY_RESTART_H
-
-enum reboot_type {
-	BOOT_TRIPLE = 't',
-	BOOT_KBD = 'k',
-#ifdef CONFIG_X86_32
-	BOOT_BIOS = 'b',
-#endif
-	BOOT_ACPI = 'a',
-	BOOT_EFI = 'e'
-};
-
-extern enum reboot_type reboot_type;
-
-extern void machine_emergency_restart(void);
-
-#endif /* ASM_X86__EMERGENCY_RESTART_H */
diff --git a/include/asm-x86/errno.h b/include/asm-x86/errno.h
deleted file mode 100644
index 4c82b503d92f..000000000000
--- a/include/asm-x86/errno.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/errno.h>
diff --git a/include/asm-x86/es7000/apic.h b/include/asm-x86/es7000/apic.h
deleted file mode 100644
index 380f0b4f17ed..000000000000
--- a/include/asm-x86/es7000/apic.h
+++ /dev/null
@@ -1,193 +0,0 @@
-#ifndef __ASM_ES7000_APIC_H
-#define __ASM_ES7000_APIC_H
-
-#define xapic_phys_to_log_apicid(cpu) per_cpu(x86_bios_cpu_apicid, cpu)
-#define esr_disable (1)
-
-static inline int apic_id_registered(void)
-{
-	        return (1);
-}
-
-static inline cpumask_t target_cpus(void)
-{
-#if defined CONFIG_ES7000_CLUSTERED_APIC
-	return CPU_MASK_ALL;
-#else
-	return cpumask_of_cpu(smp_processor_id());
-#endif
-}
-
-#if defined CONFIG_ES7000_CLUSTERED_APIC
-#define APIC_DFR_VALUE		(APIC_DFR_CLUSTER)
-#define INT_DELIVERY_MODE	(dest_LowestPrio)
-#define INT_DEST_MODE		(1)    /* logical delivery broadcast to all procs */
-#define NO_BALANCE_IRQ		(1)
-#undef  WAKE_SECONDARY_VIA_INIT
-#define WAKE_SECONDARY_VIA_MIP
-#else
-#define APIC_DFR_VALUE		(APIC_DFR_FLAT)
-#define INT_DELIVERY_MODE	(dest_Fixed)
-#define INT_DEST_MODE		(0)    /* phys delivery to target procs */
-#define NO_BALANCE_IRQ		(0)
-#undef  APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL	0x0
-#define WAKE_SECONDARY_VIA_INIT
-#endif
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return 0;
-}
-static inline unsigned long check_apicid_present(int bit)
-{
-	return physid_isset(bit, phys_cpu_present_map);
-}
-
-#define apicid_cluster(apicid) (apicid & 0xF0)
-
-static inline unsigned long calculate_ldr(int cpu)
-{
-	unsigned long id;
-	id = xapic_phys_to_log_apicid(cpu);
-	return (SET_APIC_LOGICAL_ID(id));
-}
-
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LdR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr(void)
-{
-	unsigned long val;
-	int cpu = smp_processor_id();
-
-	apic_write(APIC_DFR, APIC_DFR_VALUE);
-	val = calculate_ldr(cpu);
-	apic_write(APIC_LDR, val);
-}
-
-#ifndef CONFIG_X86_GENERICARCH
-extern void enable_apic_mode(void);
-#endif
-
-extern int apic_version [MAX_APICS];
-static inline void setup_apic_routing(void)
-{
-	int apic = per_cpu(x86_bios_cpu_apicid, smp_processor_id());
-	printk("Enabling APIC mode:  %s.  Using %d I/O APICs, target cpus %lx\n",
-		(apic_version[apic] == 0x14) ?
-		"Physical Cluster" : "Logical Cluster", nr_ioapics, cpus_addr(target_cpus())[0]);
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-	return 0;
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-	return 0;
-}
-
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (!mps_cpu)
-		return boot_cpu_physical_apicid;
-	else if (mps_cpu < NR_CPUS)
-		return (int) per_cpu(x86_bios_cpu_apicid, mps_cpu);
-	else
-		return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
-{
-	static int id = 0;
-	physid_mask_t mask;
-	mask = physid_mask_of_physid(id);
-	++id;
-	return mask;
-}
-
-extern u8 cpu_2_logical_apicid[];
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
-       if (cpu >= NR_CPUS)
-	       return BAD_APICID;
-       return (int)cpu_2_logical_apicid[cpu];
-#else
-	return logical_smp_processor_id();
-#endif
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-	/* For clustered we don't have a good way to do this yet - hack */
-	return physids_promote(0xff);
-}
-
-
-static inline void setup_portio_remap(void)
-{
-}
-
-extern unsigned int boot_cpu_physical_apicid;
-static inline int check_phys_apicid_present(int cpu_physical_apicid)
-{
-	boot_cpu_physical_apicid = read_apic_id();
-	return (1);
-}
-
-static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
-{
-	int num_bits_set;
-	int cpus_found = 0;
-	int cpu;
-	int apicid;
-
-	num_bits_set = cpus_weight(cpumask);
-	/* Return id to all */
-	if (num_bits_set == NR_CPUS)
-#if defined CONFIG_ES7000_CLUSTERED_APIC
-		return 0xFF;
-#else
-		return cpu_to_logical_apicid(0);
-#endif
-	/*
-	 * The cpus in the mask must all be on the apic cluster.  If are not
-	 * on the same apicid cluster return default value of TARGET_CPUS.
-	 */
-	cpu = first_cpu(cpumask);
-	apicid = cpu_to_logical_apicid(cpu);
-	while (cpus_found < num_bits_set) {
-		if (cpu_isset(cpu, cpumask)) {
-			int new_apicid = cpu_to_logical_apicid(cpu);
-			if (apicid_cluster(apicid) !=
-					apicid_cluster(new_apicid)){
-				printk ("%s: Not a valid mask!\n", __func__);
-#if defined CONFIG_ES7000_CLUSTERED_APIC
-				return 0xFF;
-#else
-				return cpu_to_logical_apicid(0);
-#endif
-			}
-			apicid = new_apicid;
-			cpus_found++;
-		}
-		cpu++;
-	}
-	return apicid;
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_ES7000_APIC_H */
diff --git a/include/asm-x86/es7000/apicdef.h b/include/asm-x86/es7000/apicdef.h
deleted file mode 100644
index 8b234a3cb851..000000000000
--- a/include/asm-x86/es7000/apicdef.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_ES7000_APICDEF_H
-#define __ASM_ES7000_APICDEF_H
-
-#define		APIC_ID_MASK		(0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-	return (((x)>>24)&0xFF);
-}
-
-#define		GET_APIC_ID(x)	get_apic_id(x)
-
-#endif
diff --git a/include/asm-x86/es7000/ipi.h b/include/asm-x86/es7000/ipi.h
deleted file mode 100644
index 632a955fcc0a..000000000000
--- a/include/asm-x86/es7000/ipi.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef __ASM_ES7000_IPI_H
-#define __ASM_ES7000_IPI_H
-
-void send_IPI_mask_sequence(cpumask_t mask, int vector);
-
-static inline void send_IPI_mask(cpumask_t mask, int vector)
-{
-	send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
-	if (!cpus_empty(mask))
-		send_IPI_mask(mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-	send_IPI_mask(cpu_online_map, vector);
-}
-
-#endif /* __ASM_ES7000_IPI_H */
diff --git a/include/asm-x86/es7000/mpparse.h b/include/asm-x86/es7000/mpparse.h
deleted file mode 100644
index ed5a3caae141..000000000000
--- a/include/asm-x86/es7000/mpparse.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef __ASM_ES7000_MPPARSE_H
-#define __ASM_ES7000_MPPARSE_H
-
-#include <linux/acpi.h>
-
-extern int parse_unisys_oem (char *oemptr);
-extern int find_unisys_acpi_oem_table(unsigned long *oem_addr);
-extern void unmap_unisys_acpi_oem_table(unsigned long oem_addr);
-extern void setup_unisys(void);
-
-#ifndef CONFIG_X86_GENERICARCH
-extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id);
-extern int mps_oem_check(struct mp_config_table *mpc, char *oem,
-				char *productid);
-#endif
-
-#ifdef CONFIG_ACPI
-
-static inline int es7000_check_dsdt(void)
-{
-	struct acpi_table_header header;
-
-	if (ACPI_SUCCESS(acpi_get_table_header(ACPI_SIG_DSDT, 0, &header)) &&
-	    !strncmp(header.oem_id, "UNISYS", 6))
-		return 1;
-	return 0;
-}
-#endif
-
-#endif /* __ASM_MACH_MPPARSE_H */
diff --git a/include/asm-x86/es7000/wakecpu.h b/include/asm-x86/es7000/wakecpu.h
deleted file mode 100644
index 3ffc5a7bf667..000000000000
--- a/include/asm-x86/es7000/wakecpu.h
+++ /dev/null
@@ -1,59 +0,0 @@
-#ifndef __ASM_ES7000_WAKECPU_H
-#define __ASM_ES7000_WAKECPU_H
-
-/*
- * This file copes with machines that wakeup secondary CPUs by the
- * INIT, INIT, STARTUP sequence.
- */
-
-#ifdef CONFIG_ES7000_CLUSTERED_APIC
-#define WAKE_SECONDARY_VIA_MIP
-#else
-#define WAKE_SECONDARY_VIA_INIT
-#endif
-
-#ifdef WAKE_SECONDARY_VIA_MIP
-extern int es7000_start_cpu(int cpu, unsigned long eip);
-static inline int
-wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
-{
-	int boot_error = 0;
-	boot_error = es7000_start_cpu(phys_apicid, start_eip);
-	return boot_error;
-}
-#endif
-
-#define TRAMPOLINE_LOW phys_to_virt(0x467)
-#define TRAMPOLINE_HIGH phys_to_virt(0x469)
-
-#define boot_cpu_apicid boot_cpu_physical_apicid
-
-static inline void wait_for_init_deassert(atomic_t *deassert)
-{
-#ifdef WAKE_SECONDARY_VIA_INIT
-	while (!atomic_read(deassert))
-		cpu_relax();
-#endif
-	return;
-}
-
-/* Nothing to do for most platforms, since cleared by the INIT cycle */
-static inline void smp_callin_clear_local_apic(void)
-{
-}
-
-static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-#if APIC_DEBUG
- #define inquire_remote_apic(apicid) __inquire_remote_apic(apicid)
-#else
- #define inquire_remote_apic(apicid) {}
-#endif
-
-#endif /* __ASM_MACH_WAKECPU_H */
diff --git a/include/asm-x86/fb.h b/include/asm-x86/fb.h
deleted file mode 100644
index aca38dbd9a64..000000000000
--- a/include/asm-x86/fb.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef ASM_X86__FB_H
-#define ASM_X86__FB_H
-
-#include <linux/fb.h>
-#include <linux/fs.h>
-#include <asm/page.h>
-
-static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
-				unsigned long off)
-{
-	if (boot_cpu_data.x86 > 3)
-		pgprot_val(vma->vm_page_prot) |= _PAGE_PCD;
-}
-
-#ifdef CONFIG_X86_32
-extern int fb_is_primary_device(struct fb_info *info);
-#else
-static inline int fb_is_primary_device(struct fb_info *info) { return 0; }
-#endif
-
-#endif /* ASM_X86__FB_H */
diff --git a/include/asm-x86/fcntl.h b/include/asm-x86/fcntl.h
deleted file mode 100644
index 46ab12db5739..000000000000
--- a/include/asm-x86/fcntl.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/fcntl.h>
diff --git a/include/asm-x86/fixmap.h b/include/asm-x86/fixmap.h
deleted file mode 100644
index 78e33a1bc591..000000000000
--- a/include/asm-x86/fixmap.h
+++ /dev/null
@@ -1,68 +0,0 @@
-#ifndef ASM_X86__FIXMAP_H
-#define ASM_X86__FIXMAP_H
-
-#ifdef CONFIG_X86_32
-# include "fixmap_32.h"
-#else
-# include "fixmap_64.h"
-#endif
-
-extern int fixmaps_set;
-
-void __native_set_fixmap(enum fixed_addresses idx, pte_t pte);
-void native_set_fixmap(enum fixed_addresses idx,
-		       unsigned long phys, pgprot_t flags);
-
-#ifndef CONFIG_PARAVIRT
-static inline void __set_fixmap(enum fixed_addresses idx,
-				unsigned long phys, pgprot_t flags)
-{
-	native_set_fixmap(idx, phys, flags);
-}
-#endif
-
-#define set_fixmap(idx, phys)				\
-	__set_fixmap(idx, phys, PAGE_KERNEL)
-
-/*
- * Some hardware wants to get fixmapped without caching.
- */
-#define set_fixmap_nocache(idx, phys)			\
-	__set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
-
-#define clear_fixmap(idx)			\
-	__set_fixmap(idx, 0, __pgprot(0))
-
-#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
-#define __virt_to_fix(x)	((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
-
-extern void __this_fixmap_does_not_exist(void);
-
-/*
- * 'index to address' translation. If anyone tries to use the idx
- * directly without translation, we catch the bug with a NULL-deference
- * kernel oops. Illegal ranges of incoming indices are caught too.
- */
-static __always_inline unsigned long fix_to_virt(const unsigned int idx)
-{
-	/*
-	 * this branch gets completely eliminated after inlining,
-	 * except when someone tries to use fixaddr indices in an
-	 * illegal way. (such as mixing up address types or using
-	 * out-of-range indices).
-	 *
-	 * If it doesn't get removed, the linker will complain
-	 * loudly with a reasonably clear error message..
-	 */
-	if (idx >= __end_of_fixed_addresses)
-		__this_fixmap_does_not_exist();
-
-	return __fix_to_virt(idx);
-}
-
-static inline unsigned long virt_to_fix(const unsigned long vaddr)
-{
-	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
-	return __virt_to_fix(vaddr);
-}
-#endif /* ASM_X86__FIXMAP_H */
diff --git a/include/asm-x86/fixmap_32.h b/include/asm-x86/fixmap_32.h
deleted file mode 100644
index 8844002da0e0..000000000000
--- a/include/asm-x86/fixmap_32.h
+++ /dev/null
@@ -1,123 +0,0 @@
-/*
- * fixmap.h: compile-time virtual memory allocation
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1998 Ingo Molnar
- *
- * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
- */
-
-#ifndef ASM_X86__FIXMAP_32_H
-#define ASM_X86__FIXMAP_32_H
-
-
-/* used by vmalloc.c, vsyscall.lds.S.
- *
- * Leave one empty page between vmalloc'ed areas and
- * the start of the fixmap.
- */
-extern unsigned long __FIXADDR_TOP;
-#define FIXADDR_USER_START     __fix_to_virt(FIX_VDSO)
-#define FIXADDR_USER_END       __fix_to_virt(FIX_VDSO - 1)
-
-#ifndef __ASSEMBLY__
-#include <linux/kernel.h>
-#include <asm/acpi.h>
-#include <asm/apicdef.h>
-#include <asm/page.h>
-#ifdef CONFIG_HIGHMEM
-#include <linux/threads.h>
-#include <asm/kmap_types.h>
-#endif
-
-/*
- * Here we define all the compile-time 'special' virtual
- * addresses. The point is to have a constant address at
- * compile time, but to set the physical address only
- * in the boot process. We allocate these special addresses
- * from the end of virtual memory (0xfffff000) backwards.
- * Also this lets us do fail-safe vmalloc(), we
- * can guarantee that these special addresses and
- * vmalloc()-ed addresses never overlap.
- *
- * these 'compile-time allocated' memory buffers are
- * fixed-size 4k pages. (or larger if used with an increment
- * highger than 1) use fixmap_set(idx,phys) to associate
- * physical memory with fixmap indices.
- *
- * TLB entries of such buffers will not be flushed across
- * task switches.
- */
-enum fixed_addresses {
-	FIX_HOLE,
-	FIX_VDSO,
-	FIX_DBGP_BASE,
-	FIX_EARLYCON_MEM_BASE,
-#ifdef CONFIG_X86_LOCAL_APIC
-	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
-#endif
-#ifdef CONFIG_X86_IO_APIC
-	FIX_IO_APIC_BASE_0,
-	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS-1,
-#endif
-#ifdef CONFIG_X86_VISWS_APIC
-	FIX_CO_CPU,	/* Cobalt timer */
-	FIX_CO_APIC,	/* Cobalt APIC Redirection Table */
-	FIX_LI_PCIA,	/* Lithium PCI Bridge A */
-	FIX_LI_PCIB,	/* Lithium PCI Bridge B */
-#endif
-#ifdef CONFIG_X86_F00F_BUG
-	FIX_F00F_IDT,	/* Virtual mapping for IDT */
-#endif
-#ifdef CONFIG_X86_CYCLONE_TIMER
-	FIX_CYCLONE_TIMER, /*cyclone timer register*/
-#endif
-#ifdef CONFIG_HIGHMEM
-	FIX_KMAP_BEGIN,	/* reserved pte's for temporary kernel mappings */
-	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
-#endif
-#ifdef CONFIG_PCI_MMCONFIG
-	FIX_PCIE_MCFG,
-#endif
-#ifdef CONFIG_PARAVIRT
-	FIX_PARAVIRT_BOOTMAP,
-#endif
-	__end_of_permanent_fixed_addresses,
-	/*
-	 * 256 temporary boot-time mappings, used by early_ioremap(),
-	 * before ioremap() is functional.
-	 *
-	 * We round it up to the next 256 pages boundary so that we
-	 * can have a single pgd entry and a single pte table:
-	 */
-#define NR_FIX_BTMAPS		64
-#define FIX_BTMAPS_SLOTS	4
-	FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
-			(__end_of_permanent_fixed_addresses & 255),
-	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
-	FIX_WP_TEST,
-#ifdef CONFIG_ACPI
-	FIX_ACPI_BEGIN,
-	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-	FIX_OHCI1394_BASE,
-#endif
-	__end_of_fixed_addresses
-};
-
-extern void reserve_top_address(unsigned long reserve);
-
-
-#define FIXADDR_TOP	((unsigned long)__FIXADDR_TOP)
-
-#define __FIXADDR_SIZE	(__end_of_permanent_fixed_addresses << PAGE_SHIFT)
-#define __FIXADDR_BOOT_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START		(FIXADDR_TOP - __FIXADDR_SIZE)
-#define FIXADDR_BOOT_START	(FIXADDR_TOP - __FIXADDR_BOOT_SIZE)
-
-#endif /* !__ASSEMBLY__ */
-#endif /* ASM_X86__FIXMAP_32_H */
diff --git a/include/asm-x86/fixmap_64.h b/include/asm-x86/fixmap_64.h
deleted file mode 100644
index dab4751d1307..000000000000
--- a/include/asm-x86/fixmap_64.h
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- * fixmap.h: compile-time virtual memory allocation
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1998 Ingo Molnar
- */
-
-#ifndef ASM_X86__FIXMAP_64_H
-#define ASM_X86__FIXMAP_64_H
-
-#include <linux/kernel.h>
-#include <asm/acpi.h>
-#include <asm/apicdef.h>
-#include <asm/page.h>
-#include <asm/vsyscall.h>
-#include <asm/efi.h>
-
-/*
- * Here we define all the compile-time 'special' virtual
- * addresses. The point is to have a constant address at
- * compile time, but to set the physical address only
- * in the boot process.
- *
- * These 'compile-time allocated' memory buffers are
- * fixed-size 4k pages (or larger if used with an increment
- * higher than 1). Use set_fixmap(idx,phys) to associate
- * physical memory with fixmap indices.
- *
- * TLB entries of such buffers will not be flushed across
- * task switches.
- */
-
-enum fixed_addresses {
-	VSYSCALL_LAST_PAGE,
-	VSYSCALL_FIRST_PAGE = VSYSCALL_LAST_PAGE
-			    + ((VSYSCALL_END-VSYSCALL_START) >> PAGE_SHIFT) - 1,
-	VSYSCALL_HPET,
-	FIX_DBGP_BASE,
-	FIX_EARLYCON_MEM_BASE,
-	FIX_APIC_BASE,	/* local (CPU) APIC) -- required for SMP or not */
-	FIX_IO_APIC_BASE_0,
-	FIX_IO_APIC_BASE_END = FIX_IO_APIC_BASE_0 + MAX_IO_APICS - 1,
-	FIX_EFI_IO_MAP_LAST_PAGE,
-	FIX_EFI_IO_MAP_FIRST_PAGE = FIX_EFI_IO_MAP_LAST_PAGE
-				  + MAX_EFI_IO_PAGES - 1,
-#ifdef CONFIG_PARAVIRT
-	FIX_PARAVIRT_BOOTMAP,
-#endif
-	__end_of_permanent_fixed_addresses,
-#ifdef CONFIG_ACPI
-	FIX_ACPI_BEGIN,
-	FIX_ACPI_END = FIX_ACPI_BEGIN + FIX_ACPI_PAGES - 1,
-#endif
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-	FIX_OHCI1394_BASE,
-#endif
-	/*
-	 * 256 temporary boot-time mappings, used by early_ioremap(),
-	 * before ioremap() is functional.
-	 *
-	 * We round it up to the next 256 pages boundary so that we
-	 * can have a single pgd entry and a single pte table:
-	 */
-#define NR_FIX_BTMAPS		64
-#define FIX_BTMAPS_SLOTS	4
-	FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
-			(__end_of_permanent_fixed_addresses & 255),
-	FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
-	__end_of_fixed_addresses
-};
-
-#define FIXADDR_TOP	(VSYSCALL_END-PAGE_SIZE)
-#define FIXADDR_SIZE	(__end_of_fixed_addresses << PAGE_SHIFT)
-#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
-
-/* Only covers 32bit vsyscalls currently. Need another set for 64bit. */
-#define FIXADDR_USER_START	((unsigned long)VSYSCALL32_VSYSCALL)
-#define FIXADDR_USER_END	(FIXADDR_USER_START + PAGE_SIZE)
-
-#endif /* ASM_X86__FIXMAP_64_H */
diff --git a/include/asm-x86/floppy.h b/include/asm-x86/floppy.h
deleted file mode 100644
index 7d83a3a83e37..000000000000
--- a/include/asm-x86/floppy.h
+++ /dev/null
@@ -1,281 +0,0 @@
-/*
- * Architecture specific parts of the Floppy driver
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1995
- */
-#ifndef ASM_X86__FLOPPY_H
-#define ASM_X86__FLOPPY_H
-
-#include <linux/vmalloc.h>
-
-/*
- * The DMA channel used by the floppy controller cannot access data at
- * addresses >= 16MB
- *
- * Went back to the 1MB limit, as some people had problems with the floppy
- * driver otherwise. It doesn't matter much for performance anyway, as most
- * floppy accesses go through the track buffer.
- */
-#define _CROSS_64KB(a, s, vdma)						\
-	(!(vdma) &&							\
-	 ((unsigned long)(a)/K_64 != ((unsigned long)(a) + (s) - 1) / K_64))
-
-#define CROSS_64KB(a, s) _CROSS_64KB(a, s, use_virtual_dma & 1)
-
-
-#define SW fd_routine[use_virtual_dma & 1]
-#define CSW fd_routine[can_use_virtual_dma & 1]
-
-
-#define fd_inb(port)		inb_p(port)
-#define fd_outb(value, port)	outb_p(value, port)
-
-#define fd_request_dma()	CSW._request_dma(FLOPPY_DMA, "floppy")
-#define fd_free_dma()		CSW._free_dma(FLOPPY_DMA)
-#define fd_enable_irq()		enable_irq(FLOPPY_IRQ)
-#define fd_disable_irq()	disable_irq(FLOPPY_IRQ)
-#define fd_free_irq()		free_irq(FLOPPY_IRQ, NULL)
-#define fd_get_dma_residue()	SW._get_dma_residue(FLOPPY_DMA)
-#define fd_dma_mem_alloc(size)	SW._dma_mem_alloc(size)
-#define fd_dma_setup(addr, size, mode, io) SW._dma_setup(addr, size, mode, io)
-
-#define FLOPPY_CAN_FALLBACK_ON_NODMA
-
-static int virtual_dma_count;
-static int virtual_dma_residue;
-static char *virtual_dma_addr;
-static int virtual_dma_mode;
-static int doing_pdma;
-
-static irqreturn_t floppy_hardint(int irq, void *dev_id)
-{
-	unsigned char st;
-
-#undef TRACE_FLPY_INT
-
-#ifdef TRACE_FLPY_INT
-	static int calls;
-	static int bytes;
-	static int dma_wait;
-#endif
-	if (!doing_pdma)
-		return floppy_interrupt(irq, dev_id);
-
-#ifdef TRACE_FLPY_INT
-	if (!calls)
-		bytes = virtual_dma_count;
-#endif
-
-	{
-		int lcount;
-		char *lptr;
-
-		st = 1;
-		for (lcount = virtual_dma_count, lptr = virtual_dma_addr;
-		     lcount; lcount--, lptr++) {
-			st = inb(virtual_dma_port + 4) & 0xa0;
-			if (st != 0xa0)
-				break;
-			if (virtual_dma_mode)
-				outb_p(*lptr, virtual_dma_port + 5);
-			else
-				*lptr = inb_p(virtual_dma_port + 5);
-		}
-		virtual_dma_count = lcount;
-		virtual_dma_addr = lptr;
-		st = inb(virtual_dma_port + 4);
-	}
-
-#ifdef TRACE_FLPY_INT
-	calls++;
-#endif
-	if (st == 0x20)
-		return IRQ_HANDLED;
-	if (!(st & 0x20)) {
-		virtual_dma_residue += virtual_dma_count;
-		virtual_dma_count = 0;
-#ifdef TRACE_FLPY_INT
-		printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
-		       virtual_dma_count, virtual_dma_residue, calls, bytes,
-		       dma_wait);
-		calls = 0;
-		dma_wait = 0;
-#endif
-		doing_pdma = 0;
-		floppy_interrupt(irq, dev_id);
-		return IRQ_HANDLED;
-	}
-#ifdef TRACE_FLPY_INT
-	if (!virtual_dma_count)
-		dma_wait++;
-#endif
-	return IRQ_HANDLED;
-}
-
-static void fd_disable_dma(void)
-{
-	if (!(can_use_virtual_dma & 1))
-		disable_dma(FLOPPY_DMA);
-	doing_pdma = 0;
-	virtual_dma_residue += virtual_dma_count;
-	virtual_dma_count = 0;
-}
-
-static int vdma_request_dma(unsigned int dmanr, const char *device_id)
-{
-	return 0;
-}
-
-static void vdma_nop(unsigned int dummy)
-{
-}
-
-
-static int vdma_get_dma_residue(unsigned int dummy)
-{
-	return virtual_dma_count + virtual_dma_residue;
-}
-
-
-static int fd_request_irq(void)
-{
-	if (can_use_virtual_dma)
-		return request_irq(FLOPPY_IRQ, floppy_hardint,
-				   IRQF_DISABLED, "floppy", NULL);
-	else
-		return request_irq(FLOPPY_IRQ, floppy_interrupt,
-				   IRQF_DISABLED, "floppy", NULL);
-}
-
-static unsigned long dma_mem_alloc(unsigned long size)
-{
-	return __get_dma_pages(GFP_KERNEL|__GFP_NORETRY, get_order(size));
-}
-
-
-static unsigned long vdma_mem_alloc(unsigned long size)
-{
-	return (unsigned long)vmalloc(size);
-
-}
-
-#define nodma_mem_alloc(size) vdma_mem_alloc(size)
-
-static void _fd_dma_mem_free(unsigned long addr, unsigned long size)
-{
-	if ((unsigned long)addr >= (unsigned long)high_memory)
-		vfree((void *)addr);
-	else
-		free_pages(addr, get_order(size));
-}
-
-#define fd_dma_mem_free(addr, size)  _fd_dma_mem_free(addr, size)
-
-static void _fd_chose_dma_mode(char *addr, unsigned long size)
-{
-	if (can_use_virtual_dma == 2) {
-		if ((unsigned long)addr >= (unsigned long)high_memory ||
-		    isa_virt_to_bus(addr) >= 0x1000000 ||
-		    _CROSS_64KB(addr, size, 0))
-			use_virtual_dma = 1;
-		else
-			use_virtual_dma = 0;
-	} else {
-		use_virtual_dma = can_use_virtual_dma & 1;
-	}
-}
-
-#define fd_chose_dma_mode(addr, size) _fd_chose_dma_mode(addr, size)
-
-
-static int vdma_dma_setup(char *addr, unsigned long size, int mode, int io)
-{
-	doing_pdma = 1;
-	virtual_dma_port = io;
-	virtual_dma_mode = (mode == DMA_MODE_WRITE);
-	virtual_dma_addr = addr;
-	virtual_dma_count = size;
-	virtual_dma_residue = 0;
-	return 0;
-}
-
-static int hard_dma_setup(char *addr, unsigned long size, int mode, int io)
-{
-#ifdef FLOPPY_SANITY_CHECK
-	if (CROSS_64KB(addr, size)) {
-		printk("DMA crossing 64-K boundary %p-%p\n", addr, addr+size);
-		return -1;
-	}
-#endif
-	/* actual, physical DMA */
-	doing_pdma = 0;
-	clear_dma_ff(FLOPPY_DMA);
-	set_dma_mode(FLOPPY_DMA, mode);
-	set_dma_addr(FLOPPY_DMA, isa_virt_to_bus(addr));
-	set_dma_count(FLOPPY_DMA, size);
-	enable_dma(FLOPPY_DMA);
-	return 0;
-}
-
-static struct fd_routine_l {
-	int (*_request_dma)(unsigned int dmanr, const char *device_id);
-	void (*_free_dma)(unsigned int dmanr);
-	int (*_get_dma_residue)(unsigned int dummy);
-	unsigned long (*_dma_mem_alloc)(unsigned long size);
-	int (*_dma_setup)(char *addr, unsigned long size, int mode, int io);
-} fd_routine[] = {
-	{
-		request_dma,
-		free_dma,
-		get_dma_residue,
-		dma_mem_alloc,
-		hard_dma_setup
-	},
-	{
-		vdma_request_dma,
-		vdma_nop,
-		vdma_get_dma_residue,
-		vdma_mem_alloc,
-		vdma_dma_setup
-	}
-};
-
-
-static int FDC1 = 0x3f0;
-static int FDC2 = -1;
-
-/*
- * Floppy types are stored in the rtc's CMOS RAM and so rtc_lock
- * is needed to prevent corrupted CMOS RAM in case "insmod floppy"
- * coincides with another rtc CMOS user.		Paul G.
- */
-#define FLOPPY0_TYPE					\
-({							\
-	unsigned long flags;				\
-	unsigned char val;				\
-	spin_lock_irqsave(&rtc_lock, flags);		\
-	val = (CMOS_READ(0x10) >> 4) & 15;		\
-	spin_unlock_irqrestore(&rtc_lock, flags);	\
-	val;						\
-})
-
-#define FLOPPY1_TYPE					\
-({							\
-	unsigned long flags;				\
-	unsigned char val;				\
-	spin_lock_irqsave(&rtc_lock, flags);		\
-	val = CMOS_READ(0x10) & 15;			\
-	spin_unlock_irqrestore(&rtc_lock, flags);	\
-	val;						\
-})
-
-#define N_FDC 2
-#define N_DRIVE 8
-
-#define EXTRA_FLOPPY_PARAMS
-
-#endif /* ASM_X86__FLOPPY_H */
diff --git a/include/asm-x86/frame.h b/include/asm-x86/frame.h
deleted file mode 100644
index 06850a7194e1..000000000000
--- a/include/asm-x86/frame.h
+++ /dev/null
@@ -1,27 +0,0 @@
-#ifdef __ASSEMBLY__
-
-#include <asm/dwarf2.h>
-
-/* The annotation hides the frame from the unwinder and makes it look
-   like a ordinary ebp save/restore. This avoids some special cases for
-   frame pointer later */
-#ifdef CONFIG_FRAME_POINTER
-	.macro FRAME
-	pushl %ebp
-	CFI_ADJUST_CFA_OFFSET 4
-	CFI_REL_OFFSET ebp,0
-	movl %esp,%ebp
-	.endm
-	.macro ENDFRAME
-	popl %ebp
-	CFI_ADJUST_CFA_OFFSET -4
-	CFI_RESTORE ebp
-	.endm
-#else
-	.macro FRAME
-	.endm
-	.macro ENDFRAME
-	.endm
-#endif
-
-#endif  /*  __ASSEMBLY__  */
diff --git a/include/asm-x86/ftrace.h b/include/asm-x86/ftrace.h
deleted file mode 100644
index 1bb6f9bbe1ab..000000000000
--- a/include/asm-x86/ftrace.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef ASM_X86__FTRACE_H
-#define ASM_X86__FTRACE_H
-
-#ifdef CONFIG_FTRACE
-#define MCOUNT_ADDR		((long)(mcount))
-#define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */
-
-#ifndef __ASSEMBLY__
-extern void mcount(void);
-
-static inline unsigned long ftrace_call_adjust(unsigned long addr)
-{
-	/*
-	 * call mcount is "e8 <4 byte offset>"
-	 * The addr points to the 4 byte offset and the caller of this
-	 * function wants the pointer to e8. Simply subtract one.
-	 */
-	return addr - 1;
-}
-#endif
-
-#endif /* CONFIG_FTRACE */
-
-#endif /* ASM_X86__FTRACE_H */
diff --git a/include/asm-x86/futex.h b/include/asm-x86/futex.h
deleted file mode 100644
index 06b924ef6fa5..000000000000
--- a/include/asm-x86/futex.h
+++ /dev/null
@@ -1,140 +0,0 @@
-#ifndef ASM_X86__FUTEX_H
-#define ASM_X86__FUTEX_H
-
-#ifdef __KERNEL__
-
-#include <linux/futex.h>
-#include <linux/uaccess.h>
-
-#include <asm/asm.h>
-#include <asm/errno.h>
-#include <asm/processor.h>
-#include <asm/system.h>
-
-#define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg)	\
-	asm volatile("1:\t" insn "\n"				\
-		     "2:\t.section .fixup,\"ax\"\n"		\
-		     "3:\tmov\t%3, %1\n"			\
-		     "\tjmp\t2b\n"				\
-		     "\t.previous\n"				\
-		     _ASM_EXTABLE(1b, 3b)			\
-		     : "=r" (oldval), "=r" (ret), "+m" (*uaddr)	\
-		     : "i" (-EFAULT), "0" (oparg), "1" (0))
-
-#define __futex_atomic_op2(insn, ret, oldval, uaddr, oparg)	\
-	asm volatile("1:\tmovl	%2, %0\n"			\
-		     "\tmovl\t%0, %3\n"				\
-		     "\t" insn "\n"				\
-		     "2:\t" LOCK_PREFIX "cmpxchgl %3, %2\n"	\
-		     "\tjnz\t1b\n"				\
-		     "3:\t.section .fixup,\"ax\"\n"		\
-		     "4:\tmov\t%5, %1\n"			\
-		     "\tjmp\t3b\n"				\
-		     "\t.previous\n"				\
-		     _ASM_EXTABLE(1b, 4b)			\
-		     _ASM_EXTABLE(2b, 4b)			\
-		     : "=&a" (oldval), "=&r" (ret),		\
-		       "+m" (*uaddr), "=&r" (tem)		\
-		     : "r" (oparg), "i" (-EFAULT), "1" (0))
-
-static inline int futex_atomic_op_inuser(int encoded_op, int __user *uaddr)
-{
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
-	int oldval = 0, ret, tem;
-
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
-
-#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
-	/* Real i386 machines can only support FUTEX_OP_SET */
-	if (op != FUTEX_OP_SET && boot_cpu_data.x86 == 3)
-		return -ENOSYS;
-#endif
-
-	pagefault_disable();
-
-	switch (op) {
-	case FUTEX_OP_SET:
-		__futex_atomic_op1("xchgl %0, %2", ret, oldval, uaddr, oparg);
-		break;
-	case FUTEX_OP_ADD:
-		__futex_atomic_op1(LOCK_PREFIX "xaddl %0, %2", ret, oldval,
-				   uaddr, oparg);
-		break;
-	case FUTEX_OP_OR:
-		__futex_atomic_op2("orl %4, %3", ret, oldval, uaddr, oparg);
-		break;
-	case FUTEX_OP_ANDN:
-		__futex_atomic_op2("andl %4, %3", ret, oldval, uaddr, ~oparg);
-		break;
-	case FUTEX_OP_XOR:
-		__futex_atomic_op2("xorl %4, %3", ret, oldval, uaddr, oparg);
-		break;
-	default:
-		ret = -ENOSYS;
-	}
-
-	pagefault_enable();
-
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ:
-			ret = (oldval == cmparg);
-			break;
-		case FUTEX_OP_CMP_NE:
-			ret = (oldval != cmparg);
-			break;
-		case FUTEX_OP_CMP_LT:
-			ret = (oldval < cmparg);
-			break;
-		case FUTEX_OP_CMP_GE:
-			ret = (oldval >= cmparg);
-			break;
-		case FUTEX_OP_CMP_LE:
-			ret = (oldval <= cmparg);
-			break;
-		case FUTEX_OP_CMP_GT:
-			ret = (oldval > cmparg);
-			break;
-		default:
-			ret = -ENOSYS;
-		}
-	}
-	return ret;
-}
-
-static inline int futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval,
-						int newval)
-{
-
-#if defined(CONFIG_X86_32) && !defined(CONFIG_X86_BSWAP)
-	/* Real i386 machines have no cmpxchg instruction */
-	if (boot_cpu_data.x86 == 3)
-		return -ENOSYS;
-#endif
-
-	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
-		return -EFAULT;
-
-	asm volatile("1:\t" LOCK_PREFIX "cmpxchgl %3, %1\n"
-		     "2:\t.section .fixup, \"ax\"\n"
-		     "3:\tmov     %2, %0\n"
-		     "\tjmp     2b\n"
-		     "\t.previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : "=a" (oldval), "+m" (*uaddr)
-		     : "i" (-EFAULT), "r" (newval), "0" (oldval)
-		     : "memory"
-	);
-
-	return oldval;
-}
-
-#endif
-#endif /* ASM_X86__FUTEX_H */
diff --git a/include/asm-x86/gart.h b/include/asm-x86/gart.h
deleted file mode 100644
index 605edb39ef9e..000000000000
--- a/include/asm-x86/gart.h
+++ /dev/null
@@ -1,73 +0,0 @@
-#ifndef ASM_X86__GART_H
-#define ASM_X86__GART_H
-
-#include <asm/e820.h>
-
-extern void set_up_gart_resume(u32, u32);
-
-extern int fallback_aper_order;
-extern int fallback_aper_force;
-extern int fix_aperture;
-
-/* PTE bits. */
-#define GPTE_VALID	1
-#define GPTE_COHERENT	2
-
-/* Aperture control register bits. */
-#define GARTEN		(1<<0)
-#define DISGARTCPU	(1<<4)
-#define DISGARTIO	(1<<5)
-
-/* GART cache control register bits. */
-#define INVGART		(1<<0)
-#define GARTPTEERR	(1<<1)
-
-/* K8 On-cpu GART registers */
-#define AMD64_GARTAPERTURECTL	0x90
-#define AMD64_GARTAPERTUREBASE	0x94
-#define AMD64_GARTTABLEBASE	0x98
-#define AMD64_GARTCACHECTL	0x9c
-#define AMD64_GARTEN		(1<<0)
-
-extern int agp_amd64_init(void);
-
-static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
-{
-	u32 tmp, ctl;
-
-        /* address of the mappings table */
-        addr >>= 12;
-        tmp = (u32) addr<<4;
-        tmp &= ~0xf;
-        pci_write_config_dword(dev, AMD64_GARTTABLEBASE, tmp);
-
-        /* Enable GART translation for this hammer. */
-        pci_read_config_dword(dev, AMD64_GARTAPERTURECTL, &ctl);
-        ctl |= GARTEN;
-        ctl &= ~(DISGARTCPU | DISGARTIO);
-        pci_write_config_dword(dev, AMD64_GARTAPERTURECTL, ctl);
-}
-
-static inline int aperture_valid(u64 aper_base, u32 aper_size, u32 min_size)
-{
-	if (!aper_base)
-		return 0;
-
-	if (aper_base + aper_size > 0x100000000ULL) {
-		printk(KERN_INFO "Aperture beyond 4GB. Ignoring.\n");
-		return 0;
-	}
-	if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) {
-		printk(KERN_INFO "Aperture pointing to e820 RAM. Ignoring.\n");
-		return 0;
-	}
-	if (aper_size < min_size) {
-		printk(KERN_INFO "Aperture too small (%d MB) than (%d MB)\n",
-				 aper_size>>20, min_size>>20);
-		return 0;
-	}
-
-	return 1;
-}
-
-#endif /* ASM_X86__GART_H */
diff --git a/include/asm-x86/genapic.h b/include/asm-x86/genapic.h
deleted file mode 100644
index d48bee663a6f..000000000000
--- a/include/asm-x86/genapic.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "genapic_32.h"
-#else
-# include "genapic_64.h"
-#endif
diff --git a/include/asm-x86/genapic_32.h b/include/asm-x86/genapic_32.h
deleted file mode 100644
index 6fe4f81bfcf9..000000000000
--- a/include/asm-x86/genapic_32.h
+++ /dev/null
@@ -1,126 +0,0 @@
-#ifndef ASM_X86__GENAPIC_32_H
-#define ASM_X86__GENAPIC_32_H
-
-#include <asm/mpspec.h>
-
-/*
- * Generic APIC driver interface.
- *
- * An straight forward mapping of the APIC related parts of the
- * x86 subarchitecture interface to a dynamic object.
- *
- * This is used by the "generic" x86 subarchitecture.
- *
- * Copyright 2003 Andi Kleen, SuSE Labs.
- */
-
-struct mpc_config_bus;
-struct mp_config_table;
-struct mpc_config_processor;
-
-struct genapic {
-	char *name;
-	int (*probe)(void);
-
-	int (*apic_id_registered)(void);
-	cpumask_t (*target_cpus)(void);
-	int int_delivery_mode;
-	int int_dest_mode;
-	int ESR_DISABLE;
-	int apic_destination_logical;
-	unsigned long (*check_apicid_used)(physid_mask_t bitmap, int apicid);
-	unsigned long (*check_apicid_present)(int apicid);
-	int no_balance_irq;
-	int no_ioapic_check;
-	void (*init_apic_ldr)(void);
-	physid_mask_t (*ioapic_phys_id_map)(physid_mask_t map);
-
-	void (*setup_apic_routing)(void);
-	int (*multi_timer_check)(int apic, int irq);
-	int (*apicid_to_node)(int logical_apicid);
-	int (*cpu_to_logical_apicid)(int cpu);
-	int (*cpu_present_to_apicid)(int mps_cpu);
-	physid_mask_t (*apicid_to_cpu_present)(int phys_apicid);
-	void (*setup_portio_remap)(void);
-	int (*check_phys_apicid_present)(int boot_cpu_physical_apicid);
-	void (*enable_apic_mode)(void);
-	u32 (*phys_pkg_id)(u32 cpuid_apic, int index_msb);
-
-	/* mpparse */
-	/* When one of the next two hooks returns 1 the genapic
-	   is switched to this. Essentially they are additional probe
-	   functions. */
-	int (*mps_oem_check)(struct mp_config_table *mpc, char *oem,
-			     char *productid);
-	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-
-	unsigned (*get_apic_id)(unsigned long x);
-	unsigned long apic_id_mask;
-	unsigned int (*cpu_mask_to_apicid)(cpumask_t cpumask);
-	cpumask_t (*vector_allocation_domain)(int cpu);
-
-#ifdef CONFIG_SMP
-	/* ipi */
-	void (*send_IPI_mask)(cpumask_t mask, int vector);
-	void (*send_IPI_allbutself)(int vector);
-	void (*send_IPI_all)(int vector);
-#endif
-};
-
-#define APICFUNC(x) .x = x,
-
-/* More functions could be probably marked IPIFUNC and save some space
-   in UP GENERICARCH kernels, but I don't have the nerve right now
-   to untangle this mess. -AK  */
-#ifdef CONFIG_SMP
-#define IPIFUNC(x) APICFUNC(x)
-#else
-#define IPIFUNC(x)
-#endif
-
-#define APIC_INIT(aname, aprobe)			\
-{							\
-	.name = aname,					\
-	.probe = aprobe,				\
-	.int_delivery_mode = INT_DELIVERY_MODE,		\
-	.int_dest_mode = INT_DEST_MODE,			\
-	.no_balance_irq = NO_BALANCE_IRQ,		\
-	.ESR_DISABLE = esr_disable,			\
-	.apic_destination_logical = APIC_DEST_LOGICAL,	\
-	APICFUNC(apic_id_registered)			\
-	APICFUNC(target_cpus)				\
-	APICFUNC(check_apicid_used)			\
-	APICFUNC(check_apicid_present)			\
-	APICFUNC(init_apic_ldr)				\
-	APICFUNC(ioapic_phys_id_map)			\
-	APICFUNC(setup_apic_routing)			\
-	APICFUNC(multi_timer_check)			\
-	APICFUNC(apicid_to_node)			\
-	APICFUNC(cpu_to_logical_apicid)			\
-	APICFUNC(cpu_present_to_apicid)			\
-	APICFUNC(apicid_to_cpu_present)			\
-	APICFUNC(setup_portio_remap)			\
-	APICFUNC(check_phys_apicid_present)		\
-	APICFUNC(mps_oem_check)				\
-	APICFUNC(get_apic_id)				\
-	.apic_id_mask = APIC_ID_MASK,			\
-	APICFUNC(cpu_mask_to_apicid)			\
-	APICFUNC(vector_allocation_domain)			\
-	APICFUNC(acpi_madt_oem_check)			\
-	IPIFUNC(send_IPI_mask)				\
-	IPIFUNC(send_IPI_allbutself)			\
-	IPIFUNC(send_IPI_all)				\
-	APICFUNC(enable_apic_mode)			\
-	APICFUNC(phys_pkg_id)				\
-}
-
-extern struct genapic *genapic;
-
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-#define get_uv_system_type()		UV_NONE
-#define is_uv_system()			0
-#define uv_wakeup_secondary(a, b)	1
-#define uv_system_init()		do {} while (0)
-
-
-#endif /* ASM_X86__GENAPIC_32_H */
diff --git a/include/asm-x86/genapic_64.h b/include/asm-x86/genapic_64.h
deleted file mode 100644
index ed6a4886c082..000000000000
--- a/include/asm-x86/genapic_64.h
+++ /dev/null
@@ -1,58 +0,0 @@
-#ifndef ASM_X86__GENAPIC_64_H
-#define ASM_X86__GENAPIC_64_H
-
-/*
- * Copyright 2004 James Cleverdon, IBM.
- * Subject to the GNU Public License, v.2
- *
- * Generic APIC sub-arch data struct.
- *
- * Hacked for x86-64 by James Cleverdon from i386 architecture code by
- * Martin Bligh, Andi Kleen, James Bottomley, John Stultz, and
- * James Cleverdon.
- */
-
-struct genapic {
-	char *name;
-	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
-	u32 int_delivery_mode;
-	u32 int_dest_mode;
-	int (*apic_id_registered)(void);
-	cpumask_t (*target_cpus)(void);
-	cpumask_t (*vector_allocation_domain)(int cpu);
-	void (*init_apic_ldr)(void);
-	/* ipi */
-	void (*send_IPI_mask)(cpumask_t mask, int vector);
-	void (*send_IPI_allbutself)(int vector);
-	void (*send_IPI_all)(int vector);
-	void (*send_IPI_self)(int vector);
-	/* */
-	unsigned int (*cpu_mask_to_apicid)(cpumask_t cpumask);
-	unsigned int (*phys_pkg_id)(int index_msb);
-	unsigned int (*get_apic_id)(unsigned long x);
-	unsigned long (*set_apic_id)(unsigned int id);
-	unsigned long apic_id_mask;
-};
-
-extern struct genapic *genapic;
-
-extern struct genapic apic_flat;
-extern struct genapic apic_physflat;
-extern struct genapic apic_x2apic_cluster;
-extern struct genapic apic_x2apic_phys;
-extern int acpi_madt_oem_check(char *, char *);
-
-extern void apic_send_IPI_self(int vector);
-enum uv_system_type {UV_NONE, UV_LEGACY_APIC, UV_X2APIC, UV_NON_UNIQUE_APIC};
-extern enum uv_system_type get_uv_system_type(void);
-extern int is_uv_system(void);
-
-extern struct genapic apic_x2apic_uv_x;
-DECLARE_PER_CPU(int, x2apic_extra_bits);
-extern void uv_cpu_init(void);
-extern void uv_system_init(void);
-extern int uv_wakeup_secondary(int phys_apicid, unsigned int start_rip);
-
-extern void setup_apic_routing(void);
-
-#endif /* ASM_X86__GENAPIC_64_H */
diff --git a/include/asm-x86/geode.h b/include/asm-x86/geode.h
deleted file mode 100644
index 3f3444be2638..000000000000
--- a/include/asm-x86/geode.h
+++ /dev/null
@@ -1,253 +0,0 @@
-/*
- * AMD Geode definitions
- * Copyright (C) 2006, Advanced Micro Devices, Inc.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of version 2 of the GNU General Public License
- * as published by the Free Software Foundation.
- */
-
-#ifndef ASM_X86__GEODE_H
-#define ASM_X86__GEODE_H
-
-#include <asm/processor.h>
-#include <linux/io.h>
-
-/* Generic southbridge functions */
-
-#define GEODE_DEV_PMS 0
-#define GEODE_DEV_ACPI 1
-#define GEODE_DEV_GPIO 2
-#define GEODE_DEV_MFGPT 3
-
-extern int geode_get_dev_base(unsigned int dev);
-
-/* Useful macros */
-#define geode_pms_base()	geode_get_dev_base(GEODE_DEV_PMS)
-#define geode_acpi_base()	geode_get_dev_base(GEODE_DEV_ACPI)
-#define geode_gpio_base()	geode_get_dev_base(GEODE_DEV_GPIO)
-#define geode_mfgpt_base()	geode_get_dev_base(GEODE_DEV_MFGPT)
-
-/* MSRS */
-
-#define MSR_GLIU_P2D_RO0	0x10000029
-
-#define MSR_LX_GLD_MSR_CONFIG	0x48002001
-#define MSR_LX_MSR_PADSEL	0x48002011	/* NOT 0x48000011; the data
-						 * sheet has the wrong value */
-#define MSR_GLCP_SYS_RSTPLL	0x4C000014
-#define MSR_GLCP_DOTPLL		0x4C000015
-
-#define MSR_LBAR_SMB		0x5140000B
-#define MSR_LBAR_GPIO		0x5140000C
-#define MSR_LBAR_MFGPT		0x5140000D
-#define MSR_LBAR_ACPI		0x5140000E
-#define MSR_LBAR_PMS		0x5140000F
-
-#define MSR_DIVIL_SOFT_RESET	0x51400017
-
-#define MSR_PIC_YSEL_LOW	0x51400020
-#define MSR_PIC_YSEL_HIGH	0x51400021
-#define MSR_PIC_ZSEL_LOW	0x51400022
-#define MSR_PIC_ZSEL_HIGH	0x51400023
-#define MSR_PIC_IRQM_LPC	0x51400025
-
-#define MSR_MFGPT_IRQ		0x51400028
-#define MSR_MFGPT_NR		0x51400029
-#define MSR_MFGPT_SETUP		0x5140002B
-
-#define MSR_LX_SPARE_MSR	0x80000011	/* DC-specific */
-
-#define MSR_GX_GLD_MSR_CONFIG	0xC0002001
-#define MSR_GX_MSR_PADSEL	0xC0002011
-
-/* Resource Sizes */
-
-#define LBAR_GPIO_SIZE		0xFF
-#define LBAR_MFGPT_SIZE		0x40
-#define LBAR_ACPI_SIZE		0x40
-#define LBAR_PMS_SIZE		0x80
-
-/* ACPI registers (PMS block) */
-
-/*
- * PM1_EN is only valid when VSA is enabled for 16 bit reads.
- * When VSA is not enabled, *always* read both PM1_STS and PM1_EN
- * with a 32 bit read at offset 0x0
- */
-
-#define PM1_STS			0x00
-#define PM1_EN			0x02
-#define PM1_CNT			0x08
-#define PM2_CNT			0x0C
-#define PM_TMR			0x10
-#define PM_GPE0_STS		0x18
-#define PM_GPE0_EN		0x1C
-
-/* PMC registers (PMS block) */
-
-#define PM_SSD			0x00
-#define PM_SCXA			0x04
-#define PM_SCYA			0x08
-#define PM_OUT_SLPCTL		0x0C
-#define PM_SCLK			0x10
-#define PM_SED			0x1
-#define PM_SCXD			0x18
-#define PM_SCYD			0x1C
-#define PM_IN_SLPCTL		0x20
-#define PM_WKD			0x30
-#define PM_WKXD			0x34
-#define PM_RD			0x38
-#define PM_WKXA			0x3C
-#define PM_FSD			0x40
-#define PM_TSD			0x44
-#define PM_PSD			0x48
-#define PM_NWKD			0x4C
-#define PM_AWKD			0x50
-#define PM_SSC			0x54
-
-/* VSA2 magic values */
-
-#define VSA_VRC_INDEX		0xAC1C
-#define VSA_VRC_DATA		0xAC1E
-#define VSA_VR_UNLOCK		0xFC53	/* unlock virtual register */
-#define VSA_VR_SIGNATURE	0x0003
-#define VSA_VR_MEM_SIZE		0x0200
-#define AMD_VSA_SIG		0x4132	/* signature is ascii 'VSA2' */
-#define GSW_VSA_SIG		0x534d  /* General Software signature */
-/* GPIO */
-
-#define GPIO_OUTPUT_VAL		0x00
-#define GPIO_OUTPUT_ENABLE	0x04
-#define GPIO_OUTPUT_OPEN_DRAIN	0x08
-#define GPIO_OUTPUT_INVERT	0x0C
-#define GPIO_OUTPUT_AUX1	0x10
-#define GPIO_OUTPUT_AUX2	0x14
-#define GPIO_PULL_UP		0x18
-#define GPIO_PULL_DOWN		0x1C
-#define GPIO_INPUT_ENABLE	0x20
-#define GPIO_INPUT_INVERT	0x24
-#define GPIO_INPUT_FILTER	0x28
-#define GPIO_INPUT_EVENT_COUNT	0x2C
-#define GPIO_READ_BACK		0x30
-#define GPIO_INPUT_AUX1		0x34
-#define GPIO_EVENTS_ENABLE	0x38
-#define GPIO_LOCK_ENABLE	0x3C
-#define GPIO_POSITIVE_EDGE_EN	0x40
-#define GPIO_NEGATIVE_EDGE_EN	0x44
-#define GPIO_POSITIVE_EDGE_STS	0x48
-#define GPIO_NEGATIVE_EDGE_STS	0x4C
-
-#define GPIO_MAP_X		0xE0
-#define GPIO_MAP_Y		0xE4
-#define GPIO_MAP_Z		0xE8
-#define GPIO_MAP_W		0xEC
-
-static inline u32 geode_gpio(unsigned int nr)
-{
-	BUG_ON(nr > 28);
-	return 1 << nr;
-}
-
-extern void geode_gpio_set(u32, unsigned int);
-extern void geode_gpio_clear(u32, unsigned int);
-extern int geode_gpio_isset(u32, unsigned int);
-extern void geode_gpio_setup_event(unsigned int, int, int);
-extern void geode_gpio_set_irq(unsigned int, unsigned int);
-
-static inline void geode_gpio_event_irq(unsigned int gpio, int pair)
-{
-	geode_gpio_setup_event(gpio, pair, 0);
-}
-
-static inline void geode_gpio_event_pme(unsigned int gpio, int pair)
-{
-	geode_gpio_setup_event(gpio, pair, 1);
-}
-
-/* Specific geode tests */
-
-static inline int is_geode_gx(void)
-{
-	return ((boot_cpu_data.x86_vendor == X86_VENDOR_NSC) &&
-		(boot_cpu_data.x86 == 5) &&
-		(boot_cpu_data.x86_model == 5));
-}
-
-static inline int is_geode_lx(void)
-{
-	return ((boot_cpu_data.x86_vendor == X86_VENDOR_AMD) &&
-		(boot_cpu_data.x86 == 5) &&
-		(boot_cpu_data.x86_model == 10));
-}
-
-static inline int is_geode(void)
-{
-	return (is_geode_gx() || is_geode_lx());
-}
-
-#ifdef CONFIG_MGEODE_LX
-extern int geode_has_vsa2(void);
-#else
-static inline int geode_has_vsa2(void)
-{
-	return 0;
-}
-#endif
-
-/* MFGPTs */
-
-#define MFGPT_MAX_TIMERS	8
-#define MFGPT_TIMER_ANY		(-1)
-
-#define MFGPT_DOMAIN_WORKING	1
-#define MFGPT_DOMAIN_STANDBY	2
-#define MFGPT_DOMAIN_ANY	(MFGPT_DOMAIN_WORKING | MFGPT_DOMAIN_STANDBY)
-
-#define MFGPT_CMP1		0
-#define MFGPT_CMP2		1
-
-#define MFGPT_EVENT_IRQ		0
-#define MFGPT_EVENT_NMI		1
-#define MFGPT_EVENT_RESET	3
-
-#define MFGPT_REG_CMP1		0
-#define MFGPT_REG_CMP2		2
-#define MFGPT_REG_COUNTER	4
-#define MFGPT_REG_SETUP		6
-
-#define MFGPT_SETUP_CNTEN	(1 << 15)
-#define MFGPT_SETUP_CMP2	(1 << 14)
-#define MFGPT_SETUP_CMP1	(1 << 13)
-#define MFGPT_SETUP_SETUP	(1 << 12)
-#define MFGPT_SETUP_STOPEN	(1 << 11)
-#define MFGPT_SETUP_EXTEN	(1 << 10)
-#define MFGPT_SETUP_REVEN	(1 << 5)
-#define MFGPT_SETUP_CLKSEL	(1 << 4)
-
-static inline void geode_mfgpt_write(int timer, u16 reg, u16 value)
-{
-	u32 base = geode_get_dev_base(GEODE_DEV_MFGPT);
-	outw(value, base + reg + (timer * 8));
-}
-
-static inline u16 geode_mfgpt_read(int timer, u16 reg)
-{
-	u32 base = geode_get_dev_base(GEODE_DEV_MFGPT);
-	return inw(base + reg + (timer * 8));
-}
-
-extern int geode_mfgpt_toggle_event(int timer, int cmp, int event, int enable);
-extern int geode_mfgpt_set_irq(int timer, int cmp, int *irq, int enable);
-extern int geode_mfgpt_alloc_timer(int timer, int domain);
-
-#define geode_mfgpt_setup_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 1)
-#define geode_mfgpt_release_irq(t, c, i) geode_mfgpt_set_irq((t), (c), (i), 0)
-
-#ifdef CONFIG_GEODE_MFGPT_TIMER
-extern int __init mfgpt_timer_setup(void);
-#else
-static inline int mfgpt_timer_setup(void) { return 0; }
-#endif
-
-#endif /* ASM_X86__GEODE_H */
diff --git a/include/asm-x86/gpio.h b/include/asm-x86/gpio.h
deleted file mode 100644
index 497fb980d962..000000000000
--- a/include/asm-x86/gpio.h
+++ /dev/null
@@ -1,56 +0,0 @@
-/*
- * Generic GPIO API implementation for x86.
- *
- * Derived from the generic GPIO API for powerpc:
- *
- * Copyright (c) 2007-2008  MontaVista Software, Inc.
- *
- * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef _ASM_I386_GPIO_H
-#define _ASM_I386_GPIO_H
-
-#include <asm-generic/gpio.h>
-
-#ifdef CONFIG_GPIOLIB
-
-/*
- * Just call gpiolib.
- */
-static inline int gpio_get_value(unsigned int gpio)
-{
-	return __gpio_get_value(gpio);
-}
-
-static inline void gpio_set_value(unsigned int gpio, int value)
-{
-	__gpio_set_value(gpio, value);
-}
-
-static inline int gpio_cansleep(unsigned int gpio)
-{
-	return __gpio_cansleep(gpio);
-}
-
-/*
- * Not implemented, yet.
- */
-static inline int gpio_to_irq(unsigned int gpio)
-{
-	return -ENOSYS;
-}
-
-static inline int irq_to_gpio(unsigned int irq)
-{
-	return -EINVAL;
-}
-
-#endif /* CONFIG_GPIOLIB */
-
-#endif /* ASM_X86__GPIO_H */
diff --git a/include/asm-x86/hardirq.h b/include/asm-x86/hardirq.h
deleted file mode 100644
index 000787df66e6..000000000000
--- a/include/asm-x86/hardirq.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "hardirq_32.h"
-#else
-# include "hardirq_64.h"
-#endif
-
-extern u64 arch_irq_stat_cpu(unsigned int cpu);
-#define arch_irq_stat_cpu	arch_irq_stat_cpu
-
-extern u64 arch_irq_stat(void);
-#define arch_irq_stat		arch_irq_stat
diff --git a/include/asm-x86/hardirq_32.h b/include/asm-x86/hardirq_32.h
deleted file mode 100644
index 700fe230d919..000000000000
--- a/include/asm-x86/hardirq_32.h
+++ /dev/null
@@ -1,28 +0,0 @@
-#ifndef ASM_X86__HARDIRQ_32_H
-#define ASM_X86__HARDIRQ_32_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-
-typedef struct {
-	unsigned int __softirq_pending;
-	unsigned long idle_timestamp;
-	unsigned int __nmi_count;	/* arch dependent */
-	unsigned int apic_timer_irqs;	/* arch dependent */
-	unsigned int irq0_irqs;
-	unsigned int irq_resched_count;
-	unsigned int irq_call_count;
-	unsigned int irq_tlb_count;
-	unsigned int irq_thermal_count;
-	unsigned int irq_spurious_count;
-} ____cacheline_aligned irq_cpustat_t;
-
-DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
-
-#define __ARCH_IRQ_STAT
-#define __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member)
-
-void ack_bad_irq(unsigned int irq);
-#include <linux/irq_cpustat.h>
-
-#endif /* ASM_X86__HARDIRQ_32_H */
diff --git a/include/asm-x86/hardirq_64.h b/include/asm-x86/hardirq_64.h
deleted file mode 100644
index f8bd2919a8ce..000000000000
--- a/include/asm-x86/hardirq_64.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef ASM_X86__HARDIRQ_64_H
-#define ASM_X86__HARDIRQ_64_H
-
-#include <linux/threads.h>
-#include <linux/irq.h>
-#include <asm/pda.h>
-#include <asm/apic.h>
-
-/* We can have at most NR_VECTORS irqs routed to a cpu at a time */
-#define MAX_HARDIRQS_PER_CPU NR_VECTORS
-
-#define __ARCH_IRQ_STAT 1
-
-#define local_softirq_pending() read_pda(__softirq_pending)
-
-#define __ARCH_SET_SOFTIRQ_PENDING 1
-
-#define set_softirq_pending(x) write_pda(__softirq_pending, (x))
-#define or_softirq_pending(x)  or_pda(__softirq_pending, (x))
-
-extern void ack_bad_irq(unsigned int irq);
-
-#endif /* ASM_X86__HARDIRQ_64_H */
diff --git a/include/asm-x86/highmem.h b/include/asm-x86/highmem.h
deleted file mode 100644
index bc3f6a280316..000000000000
--- a/include/asm-x86/highmem.h
+++ /dev/null
@@ -1,82 +0,0 @@
-/*
- * highmem.h: virtual kernel memory mappings for high memory
- *
- * Used in CONFIG_HIGHMEM systems for memory pages which
- * are not addressable by direct kernel virtual addresses.
- *
- * Copyright (C) 1999 Gerhard Wichert, Siemens AG
- *		      Gerhard.Wichert@pdb.siemens.de
- *
- *
- * Redesigned the x86 32-bit VM architecture to deal with
- * up to 16 Terabyte physical memory. With current x86 CPUs
- * we now support up to 64 Gigabytes physical RAM.
- *
- * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
- */
-
-#ifndef ASM_X86__HIGHMEM_H
-#define ASM_X86__HIGHMEM_H
-
-#ifdef __KERNEL__
-
-#include <linux/interrupt.h>
-#include <linux/threads.h>
-#include <asm/kmap_types.h>
-#include <asm/tlbflush.h>
-#include <asm/paravirt.h>
-
-/* declarations for highmem.c */
-extern unsigned long highstart_pfn, highend_pfn;
-
-extern pte_t *kmap_pte;
-extern pgprot_t kmap_prot;
-extern pte_t *pkmap_page_table;
-
-/*
- * Right now we initialize only a single pte table. It can be extended
- * easily, subsequent pte tables have to be allocated in one physical
- * chunk of RAM.
- */
-/*
- * Ordering is:
- *
- * FIXADDR_TOP
- * 			fixed_addresses
- * FIXADDR_START
- * 			temp fixed addresses
- * FIXADDR_BOOT_START
- * 			Persistent kmap area
- * PKMAP_BASE
- * VMALLOC_END
- * 			Vmalloc area
- * VMALLOC_START
- * high_memory
- */
-#define LAST_PKMAP_MASK (LAST_PKMAP-1)
-#define PKMAP_NR(virt)  ((virt-PKMAP_BASE) >> PAGE_SHIFT)
-#define PKMAP_ADDR(nr)  (PKMAP_BASE + ((nr) << PAGE_SHIFT))
-
-extern void *kmap_high(struct page *page);
-extern void kunmap_high(struct page *page);
-
-void *kmap(struct page *page);
-void kunmap(struct page *page);
-void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot);
-void *kmap_atomic(struct page *page, enum km_type type);
-void kunmap_atomic(void *kvaddr, enum km_type type);
-void *kmap_atomic_pfn(unsigned long pfn, enum km_type type);
-struct page *kmap_atomic_to_page(void *ptr);
-
-#ifndef CONFIG_PARAVIRT
-#define kmap_atomic_pte(page, type)	kmap_atomic(page, type)
-#endif
-
-#define flush_cache_kmaps()	do { } while (0)
-
-extern void add_highpages_with_active_regions(int nid, unsigned long start_pfn,
-					unsigned long end_pfn);
-
-#endif /* __KERNEL__ */
-
-#endif /* ASM_X86__HIGHMEM_H */
diff --git a/include/asm-x86/hpet.h b/include/asm-x86/hpet.h
deleted file mode 100644
index 58b273f6ef07..000000000000
--- a/include/asm-x86/hpet.h
+++ /dev/null
@@ -1,114 +0,0 @@
-#ifndef ASM_X86__HPET_H
-#define ASM_X86__HPET_H
-
-#include <linux/msi.h>
-
-#ifdef CONFIG_HPET_TIMER
-
-#define HPET_MMAP_SIZE		1024
-
-#define HPET_ID			0x000
-#define HPET_PERIOD		0x004
-#define HPET_CFG		0x010
-#define HPET_STATUS		0x020
-#define HPET_COUNTER		0x0f0
-
-#define HPET_Tn_CFG(n)		(0x100 + 0x20 * n)
-#define HPET_Tn_CMP(n)		(0x108 + 0x20 * n)
-#define HPET_Tn_ROUTE(n)	(0x110 + 0x20 * n)
-
-#define HPET_T0_CFG		0x100
-#define HPET_T0_CMP		0x108
-#define HPET_T0_ROUTE		0x110
-#define HPET_T1_CFG		0x120
-#define HPET_T1_CMP		0x128
-#define HPET_T1_ROUTE		0x130
-#define HPET_T2_CFG		0x140
-#define HPET_T2_CMP		0x148
-#define HPET_T2_ROUTE		0x150
-
-#define HPET_ID_REV		0x000000ff
-#define HPET_ID_NUMBER		0x00001f00
-#define HPET_ID_64BIT		0x00002000
-#define HPET_ID_LEGSUP		0x00008000
-#define HPET_ID_VENDOR		0xffff0000
-#define	HPET_ID_NUMBER_SHIFT	8
-#define HPET_ID_VENDOR_SHIFT	16
-
-#define HPET_ID_VENDOR_8086	0x8086
-
-#define HPET_CFG_ENABLE		0x001
-#define HPET_CFG_LEGACY		0x002
-#define	HPET_LEGACY_8254	2
-#define	HPET_LEGACY_RTC		8
-
-#define HPET_TN_LEVEL		0x0002
-#define HPET_TN_ENABLE		0x0004
-#define HPET_TN_PERIODIC	0x0008
-#define HPET_TN_PERIODIC_CAP	0x0010
-#define HPET_TN_64BIT_CAP	0x0020
-#define HPET_TN_SETVAL		0x0040
-#define HPET_TN_32BIT		0x0100
-#define HPET_TN_ROUTE		0x3e00
-#define HPET_TN_FSB		0x4000
-#define HPET_TN_FSB_CAP		0x8000
-#define HPET_TN_ROUTE_SHIFT	9
-
-/* Max HPET Period is 10^8 femto sec as in HPET spec */
-#define HPET_MAX_PERIOD		100000000UL
-/*
- * Min HPET period is 10^5 femto sec just for safety. If it is less than this,
- * then 32 bit HPET counter wrapsaround in less than 0.5 sec.
- */
-#define HPET_MIN_PERIOD		100000UL
-
-/* hpet memory map physical address */
-extern unsigned long hpet_address;
-extern unsigned long force_hpet_address;
-extern int hpet_force_user;
-extern int is_hpet_enabled(void);
-extern int hpet_enable(void);
-extern void hpet_disable(void);
-extern unsigned long hpet_readl(unsigned long a);
-extern void force_hpet_resume(void);
-
-extern void hpet_msi_unmask(unsigned int irq);
-extern void hpet_msi_mask(unsigned int irq);
-extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg);
-extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg);
-
-#ifdef CONFIG_PCI_MSI
-extern int arch_setup_hpet_msi(unsigned int irq);
-#else
-static inline int arch_setup_hpet_msi(unsigned int irq)
-{
-	return -EINVAL;
-}
-#endif
-
-#ifdef CONFIG_HPET_EMULATE_RTC
-
-#include <linux/interrupt.h>
-
-typedef irqreturn_t (*rtc_irq_handler)(int interrupt, void *cookie);
-extern int hpet_mask_rtc_irq_bit(unsigned long bit_mask);
-extern int hpet_set_rtc_irq_bit(unsigned long bit_mask);
-extern int hpet_set_alarm_time(unsigned char hrs, unsigned char min,
-			       unsigned char sec);
-extern int hpet_set_periodic_freq(unsigned long freq);
-extern int hpet_rtc_dropped_irq(void);
-extern int hpet_rtc_timer_init(void);
-extern irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id);
-extern int hpet_register_irq_handler(rtc_irq_handler handler);
-extern void hpet_unregister_irq_handler(rtc_irq_handler handler);
-
-#endif /* CONFIG_HPET_EMULATE_RTC */
-
-#else /* CONFIG_HPET_TIMER */
-
-static inline int hpet_enable(void) { return 0; }
-static inline int is_hpet_enabled(void) { return 0; }
-#define hpet_readl(a) 0
-
-#endif
-#endif /* ASM_X86__HPET_H */
diff --git a/include/asm-x86/hugetlb.h b/include/asm-x86/hugetlb.h
deleted file mode 100644
index 0b7ec5dc0884..000000000000
--- a/include/asm-x86/hugetlb.h
+++ /dev/null
@@ -1,93 +0,0 @@
-#ifndef ASM_X86__HUGETLB_H
-#define ASM_X86__HUGETLB_H
-
-#include <asm/page.h>
-
-
-static inline int is_hugepage_only_range(struct mm_struct *mm,
-					 unsigned long addr,
-					 unsigned long len) {
-	return 0;
-}
-
-/*
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
-static inline void hugetlb_prefault_arch_hook(struct mm_struct *mm) {
-}
-
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
-{
-}
-
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
-
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
-static inline int arch_prepare_hugepage(struct page *page)
-{
-	return 0;
-}
-
-static inline void arch_release_hugepage(struct page *page)
-{
-}
-
-#endif /* ASM_X86__HUGETLB_H */
diff --git a/include/asm-x86/hw_irq.h b/include/asm-x86/hw_irq.h
deleted file mode 100644
index 749d042f0556..000000000000
--- a/include/asm-x86/hw_irq.h
+++ /dev/null
@@ -1,131 +0,0 @@
-#ifndef ASM_X86__HW_IRQ_H
-#define ASM_X86__HW_IRQ_H
-
-/*
- * (C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- * moved some of the old arch/i386/kernel/irq.h to here. VY
- *
- * IRQ/IPI changes taken from work by Thomas Radke
- * <tomsoft@informatik.tu-chemnitz.de>
- *
- * hacked by Andi Kleen for x86-64.
- * unified by tglx
- */
-
-#include <asm/irq_vectors.h>
-
-#ifndef __ASSEMBLY__
-
-#include <linux/percpu.h>
-#include <linux/profile.h>
-#include <linux/smp.h>
-
-#include <asm/atomic.h>
-#include <asm/irq.h>
-#include <asm/sections.h>
-
-#define platform_legacy_irq(irq)	((irq) < 16)
-
-/* Interrupt handlers registered during init_IRQ */
-extern void apic_timer_interrupt(void);
-extern void error_interrupt(void);
-extern void spurious_interrupt(void);
-extern void thermal_interrupt(void);
-extern void reschedule_interrupt(void);
-
-extern void invalidate_interrupt(void);
-extern void invalidate_interrupt0(void);
-extern void invalidate_interrupt1(void);
-extern void invalidate_interrupt2(void);
-extern void invalidate_interrupt3(void);
-extern void invalidate_interrupt4(void);
-extern void invalidate_interrupt5(void);
-extern void invalidate_interrupt6(void);
-extern void invalidate_interrupt7(void);
-
-extern void irq_move_cleanup_interrupt(void);
-extern void threshold_interrupt(void);
-
-extern void call_function_interrupt(void);
-extern void call_function_single_interrupt(void);
-
-/* PIC specific functions */
-extern void disable_8259A_irq(unsigned int irq);
-extern void enable_8259A_irq(unsigned int irq);
-extern int i8259A_irq_pending(unsigned int irq);
-extern void make_8259A_irq(unsigned int irq);
-extern void init_8259A(int aeoi);
-
-/* IOAPIC */
-#define IO_APIC_IRQ(x) (((x) >= 16) || ((1<<(x)) & io_apic_irqs))
-extern unsigned long io_apic_irqs;
-
-extern void init_VISWS_APIC_irqs(void);
-extern void setup_IO_APIC(void);
-extern void disable_IO_APIC(void);
-extern int IO_APIC_get_PCI_irq_vector(int bus, int slot, int fn);
-extern void setup_ioapic_dest(void);
-
-#ifdef CONFIG_X86_64
-extern void enable_IO_APIC(void);
-#endif
-
-/* IPI functions */
-#ifdef CONFIG_X86_32
-extern void send_IPI_self(int vector);
-#endif
-extern void send_IPI(int dest, int vector);
-
-/* Statistics */
-extern atomic_t irq_err_count;
-extern atomic_t irq_mis_count;
-
-/* EISA */
-extern void eisa_set_level_irq(unsigned int irq);
-
-/* Voyager functions */
-extern asmlinkage void vic_cpi_interrupt(void);
-extern asmlinkage void vic_sys_interrupt(void);
-extern asmlinkage void vic_cmn_interrupt(void);
-extern asmlinkage void qic_timer_interrupt(void);
-extern asmlinkage void qic_invalidate_interrupt(void);
-extern asmlinkage void qic_reschedule_interrupt(void);
-extern asmlinkage void qic_enable_irq_interrupt(void);
-extern asmlinkage void qic_call_function_interrupt(void);
-
-/* SMP */
-extern void smp_apic_timer_interrupt(struct pt_regs *);
-extern void smp_spurious_interrupt(struct pt_regs *);
-extern void smp_error_interrupt(struct pt_regs *);
-#ifdef CONFIG_X86_SMP
-extern void smp_reschedule_interrupt(struct pt_regs *);
-extern void smp_call_function_interrupt(struct pt_regs *);
-extern void smp_call_function_single_interrupt(struct pt_regs *);
-#ifdef CONFIG_X86_32
-extern void smp_invalidate_interrupt(struct pt_regs *);
-#else
-extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
-#endif
-#endif
-
-#ifdef CONFIG_X86_32
-extern void (*const interrupt[NR_VECTORS])(void);
-#endif
-
-typedef int vector_irq_t[NR_VECTORS];
-DECLARE_PER_CPU(vector_irq_t, vector_irq);
-
-#ifdef CONFIG_X86_IO_APIC
-extern void lock_vector_lock(void);
-extern void unlock_vector_lock(void);
-extern void __setup_vector_irq(int cpu);
-#else
-static inline void lock_vector_lock(void) {}
-static inline void unlock_vector_lock(void) {}
-static inline void __setup_vector_irq(int cpu) {}
-#endif
-
-#endif /* !ASSEMBLY_ */
-
-#endif /* ASM_X86__HW_IRQ_H */
diff --git a/include/asm-x86/hypertransport.h b/include/asm-x86/hypertransport.h
deleted file mode 100644
index cc011a3bc1c2..000000000000
--- a/include/asm-x86/hypertransport.h
+++ /dev/null
@@ -1,45 +0,0 @@
-#ifndef ASM_X86__HYPERTRANSPORT_H
-#define ASM_X86__HYPERTRANSPORT_H
-
-/*
- * Constants for x86 Hypertransport Interrupts.
- */
-
-#define HT_IRQ_LOW_BASE			0xf8000000
-
-#define HT_IRQ_LOW_VECTOR_SHIFT		16
-#define HT_IRQ_LOW_VECTOR_MASK		0x00ff0000
-#define HT_IRQ_LOW_VECTOR(v)						\
-	(((v) << HT_IRQ_LOW_VECTOR_SHIFT) & HT_IRQ_LOW_VECTOR_MASK)
-
-#define HT_IRQ_LOW_DEST_ID_SHIFT	8
-#define HT_IRQ_LOW_DEST_ID_MASK		0x0000ff00
-#define HT_IRQ_LOW_DEST_ID(v)						\
-	(((v) << HT_IRQ_LOW_DEST_ID_SHIFT) & HT_IRQ_LOW_DEST_ID_MASK)
-
-#define HT_IRQ_LOW_DM_PHYSICAL		0x0000000
-#define HT_IRQ_LOW_DM_LOGICAL		0x0000040
-
-#define HT_IRQ_LOW_RQEOI_EDGE		0x0000000
-#define HT_IRQ_LOW_RQEOI_LEVEL		0x0000020
-
-
-#define HT_IRQ_LOW_MT_FIXED		0x0000000
-#define HT_IRQ_LOW_MT_ARBITRATED	0x0000004
-#define HT_IRQ_LOW_MT_SMI		0x0000008
-#define HT_IRQ_LOW_MT_NMI		0x000000c
-#define HT_IRQ_LOW_MT_INIT		0x0000010
-#define HT_IRQ_LOW_MT_STARTUP		0x0000014
-#define HT_IRQ_LOW_MT_EXTINT		0x0000018
-#define HT_IRQ_LOW_MT_LINT1		0x000008c
-#define HT_IRQ_LOW_MT_LINT0		0x0000098
-
-#define HT_IRQ_LOW_IRQ_MASKED		0x0000001
-
-
-#define HT_IRQ_HIGH_DEST_ID_SHIFT	0
-#define HT_IRQ_HIGH_DEST_ID_MASK	0x00ffffff
-#define HT_IRQ_HIGH_DEST_ID(v)						\
-	((((v) >> 8) << HT_IRQ_HIGH_DEST_ID_SHIFT) & HT_IRQ_HIGH_DEST_ID_MASK)
-
-#endif /* ASM_X86__HYPERTRANSPORT_H */
diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h
deleted file mode 100644
index 9ba862a4eac0..000000000000
--- a/include/asm-x86/i387.h
+++ /dev/null
@@ -1,400 +0,0 @@
-/*
- * Copyright (C) 1994 Linus Torvalds
- *
- * Pentium III FXSR, SSE support
- * General FPU state handling cleanups
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- * x86-64 work by Andi Kleen 2002
- */
-
-#ifndef ASM_X86__I387_H
-#define ASM_X86__I387_H
-
-#include <linux/sched.h>
-#include <linux/kernel_stat.h>
-#include <linux/regset.h>
-#include <linux/hardirq.h>
-#include <asm/asm.h>
-#include <asm/processor.h>
-#include <asm/sigcontext.h>
-#include <asm/user.h>
-#include <asm/uaccess.h>
-#include <asm/xsave.h>
-
-extern unsigned int sig_xstate_size;
-extern void fpu_init(void);
-extern void mxcsr_feature_mask_init(void);
-extern int init_fpu(struct task_struct *child);
-extern asmlinkage void math_state_restore(void);
-extern void init_thread_xstate(void);
-extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
-
-extern user_regset_active_fn fpregs_active, xfpregs_active;
-extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get;
-extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set;
-
-extern struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-extern unsigned int sig_xstate_ia32_size;
-extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
-struct _fpstate_ia32;
-struct _xstate_ia32;
-extern int save_i387_xstate_ia32(void __user *buf);
-extern int restore_i387_xstate_ia32(void __user *buf);
-#endif
-
-#define X87_FSW_ES (1 << 7)	/* Exception Summary */
-
-#ifdef CONFIG_X86_64
-
-/* Ignore delayed exceptions from user space */
-static inline void tolerant_fwait(void)
-{
-	asm volatile("1: fwait\n"
-		     "2:\n"
-		     _ASM_EXTABLE(1b, 2b));
-}
-
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
-	int err;
-
-	asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err)
-#if 0 /* See comment in __save_init_fpu() below. */
-		     : [fx] "r" (fx), "m" (*fx), "0" (0));
-#else
-		     : [fx] "cdaSDb" (fx), "m" (*fx), "0" (0));
-#endif
-	return err;
-}
-
-static inline int restore_fpu_checking(struct task_struct *tsk)
-{
-	if (task_thread_info(tsk)->status & TS_XSAVE)
-		return xrstor_checking(&tsk->thread.xstate->xsave);
-	else
-		return fxrstor_checking(&tsk->thread.xstate->fxsave);
-}
-
-/* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
-   is pending. Clear the x87 state here by setting it to fixed
-   values. The kernel data segment can be sometimes 0 and sometimes
-   new user value. Both should be ok.
-   Use the PDA as safe address because it should be already in L1. */
-static inline void clear_fpu_state(struct task_struct *tsk)
-{
-	struct xsave_struct *xstate = &tsk->thread.xstate->xsave;
-	struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
-
-	/*
-	 * xsave header may indicate the init state of the FP.
-	 */
-	if ((task_thread_info(tsk)->status & TS_XSAVE) &&
-	    !(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
-		return;
-
-	if (unlikely(fx->swd & X87_FSW_ES))
-		asm volatile("fnclex");
-	alternative_input(ASM_NOP8 ASM_NOP2,
-			  "    emms\n"		/* clear stack tags */
-			  "    fildl %%gs:0",	/* load to clear state */
-			  X86_FEATURE_FXSAVE_LEAK);
-}
-
-static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
-{
-	int err;
-
-	asm volatile("1:  rex64/fxsave (%[fx])\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err), "=m" (*fx)
-#if 0 /* See comment in __fxsave_clear() below. */
-		     : [fx] "r" (fx), "0" (0));
-#else
-		     : [fx] "cdaSDb" (fx), "0" (0));
-#endif
-	if (unlikely(err) &&
-	    __clear_user(fx, sizeof(struct i387_fxsave_struct)))
-		err = -EFAULT;
-	/* No need to clear here because the caller clears USED_MATH */
-	return err;
-}
-
-static inline void fxsave(struct task_struct *tsk)
-{
-	/* Using "rex64; fxsave %0" is broken because, if the memory operand
-	   uses any extended registers for addressing, a second REX prefix
-	   will be generated (to the assembler, rex64 followed by semicolon
-	   is a separate instruction), and hence the 64-bitness is lost. */
-#if 0
-	/* Using "fxsaveq %0" would be the ideal choice, but is only supported
-	   starting with gas 2.16. */
-	__asm__ __volatile__("fxsaveq %0"
-			     : "=m" (tsk->thread.xstate->fxsave));
-#elif 0
-	/* Using, as a workaround, the properly prefixed form below isn't
-	   accepted by any binutils version so far released, complaining that
-	   the same type of prefix is used twice if an extended register is
-	   needed for addressing (fix submitted to mainline 2005-11-21). */
-	__asm__ __volatile__("rex64/fxsave %0"
-			     : "=m" (tsk->thread.xstate->fxsave));
-#else
-	/* This, however, we can work around by forcing the compiler to select
-	   an addressing mode that doesn't require extended registers. */
-	__asm__ __volatile__("rex64/fxsave (%1)"
-			     : "=m" (tsk->thread.xstate->fxsave)
-			     : "cdaSDb" (&tsk->thread.xstate->fxsave));
-#endif
-}
-
-static inline void __save_init_fpu(struct task_struct *tsk)
-{
-	if (task_thread_info(tsk)->status & TS_XSAVE)
-		xsave(tsk);
-	else
-		fxsave(tsk);
-
-	clear_fpu_state(tsk);
-	task_thread_info(tsk)->status &= ~TS_USEDFPU;
-}
-
-#else  /* CONFIG_X86_32 */
-
-extern void finit(void);
-
-static inline void tolerant_fwait(void)
-{
-	asm volatile("fnclex ; fwait");
-}
-
-static inline void restore_fpu(struct task_struct *tsk)
-{
-	if (task_thread_info(tsk)->status & TS_XSAVE) {
-		xrstor_checking(&tsk->thread.xstate->xsave);
-		return;
-	}
-	/*
-	 * The "nop" is needed to make the instructions the same
-	 * length.
-	 */
-	alternative_input(
-		"nop ; frstor %1",
-		"fxrstor %1",
-		X86_FEATURE_FXSR,
-		"m" (tsk->thread.xstate->fxsave));
-}
-
-/* We need a safe address that is cheap to find and that is already
-   in L1 during context switch. The best choices are unfortunately
-   different for UP and SMP */
-#ifdef CONFIG_SMP
-#define safe_address (__per_cpu_offset[0])
-#else
-#define safe_address (kstat_cpu(0).cpustat.user)
-#endif
-
-/*
- * These must be called with preempt disabled
- */
-static inline void __save_init_fpu(struct task_struct *tsk)
-{
-	if (task_thread_info(tsk)->status & TS_XSAVE) {
-		struct xsave_struct *xstate = &tsk->thread.xstate->xsave;
-		struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
-
-		xsave(tsk);
-
-		/*
-		 * xsave header may indicate the init state of the FP.
-		 */
-		if (!(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
-			goto end;
-
-		if (unlikely(fx->swd & X87_FSW_ES))
-			asm volatile("fnclex");
-
-		/*
-		 * we can do a simple return here or be paranoid :)
-		 */
-		goto clear_state;
-	}
-
-	/* Use more nops than strictly needed in case the compiler
-	   varies code */
-	alternative_input(
-		"fnsave %[fx] ;fwait;" GENERIC_NOP8 GENERIC_NOP4,
-		"fxsave %[fx]\n"
-		"bt $7,%[fsw] ; jnc 1f ; fnclex\n1:",
-		X86_FEATURE_FXSR,
-		[fx] "m" (tsk->thread.xstate->fxsave),
-		[fsw] "m" (tsk->thread.xstate->fxsave.swd) : "memory");
-clear_state:
-	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
-	   is pending.  Clear the x87 state here by setting it to fixed
-	   values. safe_address is a random variable that should be in L1 */
-	alternative_input(
-		GENERIC_NOP8 GENERIC_NOP2,
-		"emms\n\t"	  	/* clear stack tags */
-		"fildl %[addr]", 	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (safe_address));
-end:
-	task_thread_info(tsk)->status &= ~TS_USEDFPU;
-}
-
-#endif	/* CONFIG_X86_64 */
-
-/*
- * Signal frame handlers...
- */
-extern int save_i387_xstate(void __user *buf);
-extern int restore_i387_xstate(void __user *buf);
-
-static inline void __unlazy_fpu(struct task_struct *tsk)
-{
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
-		__save_init_fpu(tsk);
-		stts();
-	} else
-		tsk->fpu_counter = 0;
-}
-
-static inline void __clear_fpu(struct task_struct *tsk)
-{
-	if (task_thread_info(tsk)->status & TS_USEDFPU) {
-		tolerant_fwait();
-		task_thread_info(tsk)->status &= ~TS_USEDFPU;
-		stts();
-	}
-}
-
-static inline void kernel_fpu_begin(void)
-{
-	struct thread_info *me = current_thread_info();
-	preempt_disable();
-	if (me->status & TS_USEDFPU)
-		__save_init_fpu(me->task);
-	else
-		clts();
-}
-
-static inline void kernel_fpu_end(void)
-{
-	stts();
-	preempt_enable();
-}
-
-/*
- * Some instructions like VIA's padlock instructions generate a spurious
- * DNA fault but don't modify SSE registers. And these instructions
- * get used from interrupt context aswell. To prevent these kernel instructions
- * in interrupt context interact wrongly with other user/kernel fpu usage, we
- * should use them only in the context of irq_ts_save/restore()
- */
-static inline int irq_ts_save(void)
-{
-	/*
-	 * If we are in process context, we are ok to take a spurious DNA fault.
-	 * Otherwise, doing clts() in process context require pre-emption to
-	 * be disabled or some heavy lifting like kernel_fpu_begin()
-	 */
-	if (!in_interrupt())
-		return 0;
-
-	if (read_cr0() & X86_CR0_TS) {
-		clts();
-		return 1;
-	}
-
-	return 0;
-}
-
-static inline void irq_ts_restore(int TS_state)
-{
-	if (TS_state)
-		stts();
-}
-
-#ifdef CONFIG_X86_64
-
-static inline void save_init_fpu(struct task_struct *tsk)
-{
-	__save_init_fpu(tsk);
-	stts();
-}
-
-#define unlazy_fpu	__unlazy_fpu
-#define clear_fpu	__clear_fpu
-
-#else  /* CONFIG_X86_32 */
-
-/*
- * These disable preemption on their own and are safe
- */
-static inline void save_init_fpu(struct task_struct *tsk)
-{
-	preempt_disable();
-	__save_init_fpu(tsk);
-	stts();
-	preempt_enable();
-}
-
-static inline void unlazy_fpu(struct task_struct *tsk)
-{
-	preempt_disable();
-	__unlazy_fpu(tsk);
-	preempt_enable();
-}
-
-static inline void clear_fpu(struct task_struct *tsk)
-{
-	preempt_disable();
-	__clear_fpu(tsk);
-	preempt_enable();
-}
-
-#endif	/* CONFIG_X86_64 */
-
-/*
- * i387 state interaction
- */
-static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
-{
-	if (cpu_has_fxsr) {
-		return tsk->thread.xstate->fxsave.cwd;
-	} else {
-		return (unsigned short)tsk->thread.xstate->fsave.cwd;
-	}
-}
-
-static inline unsigned short get_fpu_swd(struct task_struct *tsk)
-{
-	if (cpu_has_fxsr) {
-		return tsk->thread.xstate->fxsave.swd;
-	} else {
-		return (unsigned short)tsk->thread.xstate->fsave.swd;
-	}
-}
-
-static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
-{
-	if (cpu_has_xmm) {
-		return tsk->thread.xstate->fxsave.mxcsr;
-	} else {
-		return MXCSR_DEFAULT;
-	}
-}
-
-#endif /* ASM_X86__I387_H */
diff --git a/include/asm-x86/i8253.h b/include/asm-x86/i8253.h
deleted file mode 100644
index 15a5b530044e..000000000000
--- a/include/asm-x86/i8253.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef ASM_X86__I8253_H
-#define ASM_X86__I8253_H
-
-/* i8253A PIT registers */
-#define PIT_MODE		0x43
-#define PIT_CH0			0x40
-#define PIT_CH2			0x42
-
-extern spinlock_t i8253_lock;
-
-extern struct clock_event_device *global_clock_event;
-
-extern void setup_pit_timer(void);
-
-#define inb_pit		inb_p
-#define outb_pit	outb_p
-
-#endif /* ASM_X86__I8253_H */
diff --git a/include/asm-x86/i8259.h b/include/asm-x86/i8259.h
deleted file mode 100644
index 23c1b3baaecd..000000000000
--- a/include/asm-x86/i8259.h
+++ /dev/null
@@ -1,63 +0,0 @@
-#ifndef ASM_X86__I8259_H
-#define ASM_X86__I8259_H
-
-#include <linux/delay.h>
-
-extern unsigned int cached_irq_mask;
-
-#define __byte(x, y)		(((unsigned char *)&(y))[x])
-#define cached_master_mask	(__byte(0, cached_irq_mask))
-#define cached_slave_mask	(__byte(1, cached_irq_mask))
-
-/* i8259A PIC registers */
-#define PIC_MASTER_CMD		0x20
-#define PIC_MASTER_IMR		0x21
-#define PIC_MASTER_ISR		PIC_MASTER_CMD
-#define PIC_MASTER_POLL		PIC_MASTER_ISR
-#define PIC_MASTER_OCW3		PIC_MASTER_ISR
-#define PIC_SLAVE_CMD		0xa0
-#define PIC_SLAVE_IMR		0xa1
-
-/* i8259A PIC related value */
-#define PIC_CASCADE_IR		2
-#define MASTER_ICW4_DEFAULT	0x01
-#define SLAVE_ICW4_DEFAULT	0x01
-#define PIC_ICW4_AEOI		2
-
-extern spinlock_t i8259A_lock;
-
-extern void init_8259A(int auto_eoi);
-extern void enable_8259A_irq(unsigned int irq);
-extern void disable_8259A_irq(unsigned int irq);
-extern unsigned int startup_8259A_irq(unsigned int irq);
-
-/* the PIC may need a careful delay on some platforms, hence specific calls */
-static inline unsigned char inb_pic(unsigned int port)
-{
-	unsigned char value = inb(port);
-
-	/*
-	 * delay for some accesses to PIC on motherboard or in chipset
-	 * must be at least one microsecond, so be safe here:
-	 */
-	udelay(2);
-
-	return value;
-}
-
-static inline void outb_pic(unsigned char value, unsigned int port)
-{
-	outb(value, port);
-	/*
-	 * delay for some accesses to PIC on motherboard or in chipset
-	 * must be at least one microsecond, so be safe here:
-	 */
-	udelay(2);
-}
-
-extern struct irq_chip i8259A_chip;
-
-extern void mask_8259A(void);
-extern void unmask_8259A(void);
-
-#endif /* ASM_X86__I8259_H */
diff --git a/include/asm-x86/ia32.h b/include/asm-x86/ia32.h
deleted file mode 100644
index f932f7ad51dd..000000000000
--- a/include/asm-x86/ia32.h
+++ /dev/null
@@ -1,170 +0,0 @@
-#ifndef ASM_X86__IA32_H
-#define ASM_X86__IA32_H
-
-
-#ifdef CONFIG_IA32_EMULATION
-
-#include <linux/compat.h>
-
-/*
- * 32 bit structures for IA32 support.
- */
-
-#include <asm/sigcontext32.h>
-
-/* signal.h */
-struct sigaction32 {
-	unsigned int  sa_handler;	/* Really a pointer, but need to deal
-					   with 32 bits */
-	unsigned int sa_flags;
-	unsigned int sa_restorer;	/* Another 32 bit pointer */
-	compat_sigset_t sa_mask;	/* A 32 bit mask */
-};
-
-struct old_sigaction32 {
-	unsigned int  sa_handler;	/* Really a pointer, but need to deal
-					   with 32 bits */
-	compat_old_sigset_t sa_mask;	/* A 32 bit mask */
-	unsigned int sa_flags;
-	unsigned int sa_restorer;	/* Another 32 bit pointer */
-};
-
-typedef struct sigaltstack_ia32 {
-	unsigned int	ss_sp;
-	int		ss_flags;
-	unsigned int	ss_size;
-} stack_ia32_t;
-
-struct ucontext_ia32 {
-	unsigned int	  uc_flags;
-	unsigned int 	  uc_link;
-	stack_ia32_t	  uc_stack;
-	struct sigcontext_ia32 uc_mcontext;
-	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
-};
-
-/* This matches struct stat64 in glibc2.2, hence the absolutely
- * insane amounts of padding around dev_t's.
- */
-struct stat64 {
-	unsigned long long	st_dev;
-	unsigned char		__pad0[4];
-
-#define STAT64_HAS_BROKEN_ST_INO	1
-	unsigned int		__st_ino;
-
-	unsigned int		st_mode;
-	unsigned int		st_nlink;
-
-	unsigned int		st_uid;
-	unsigned int		st_gid;
-
-	unsigned long long	st_rdev;
-	unsigned char		__pad3[4];
-
-	long long		st_size;
-	unsigned int		st_blksize;
-
-	long long		st_blocks;/* Number 512-byte blocks allocated */
-
-	unsigned 		st_atime;
-	unsigned 		st_atime_nsec;
-	unsigned 		st_mtime;
-	unsigned 		st_mtime_nsec;
-	unsigned 		st_ctime;
-	unsigned 		st_ctime_nsec;
-
-	unsigned long long	st_ino;
-} __attribute__((packed));
-
-typedef struct compat_siginfo {
-	int si_signo;
-	int si_errno;
-	int si_code;
-
-	union {
-		int _pad[((128 / sizeof(int)) - 3)];
-
-		/* kill() */
-		struct {
-			unsigned int _pid;	/* sender's pid */
-			unsigned int _uid;	/* sender's uid */
-		} _kill;
-
-		/* POSIX.1b timers */
-		struct {
-			compat_timer_t _tid;	/* timer id */
-			int _overrun;		/* overrun count */
-			compat_sigval_t _sigval;	/* same as below */
-			int _sys_private;	/* not to be passed to user */
-			int _overrun_incr;	/* amount to add to overrun */
-		} _timer;
-
-		/* POSIX.1b signals */
-		struct {
-			unsigned int _pid;	/* sender's pid */
-			unsigned int _uid;	/* sender's uid */
-			compat_sigval_t _sigval;
-		} _rt;
-
-		/* SIGCHLD */
-		struct {
-			unsigned int _pid;	/* which child */
-			unsigned int _uid;	/* sender's uid */
-			int _status;		/* exit code */
-			compat_clock_t _utime;
-			compat_clock_t _stime;
-		} _sigchld;
-
-		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
-		struct {
-			unsigned int _addr;	/* faulting insn/memory ref. */
-		} _sigfault;
-
-		/* SIGPOLL */
-		struct {
-			int _band;	/* POLL_IN, POLL_OUT, POLL_MSG */
-			int _fd;
-		} _sigpoll;
-	} _sifields;
-} compat_siginfo_t;
-
-struct sigframe32 {
-	u32 pretcode;
-	int sig;
-	struct sigcontext_ia32 sc;
-	struct _fpstate_ia32 fpstate;
-	unsigned int extramask[_COMPAT_NSIG_WORDS-1];
-};
-
-struct rt_sigframe32 {
-	u32 pretcode;
-	int sig;
-	u32 pinfo;
-	u32 puc;
-	compat_siginfo_t info;
-	struct ucontext_ia32 uc;
-	struct _fpstate_ia32 fpstate;
-};
-
-struct ustat32 {
-	__u32			f_tfree;
-	compat_ino_t		f_tinode;
-	char			f_fname[6];
-	char			f_fpack[6];
-};
-
-#define IA32_STACK_TOP IA32_PAGE_OFFSET
-
-#ifdef __KERNEL__
-struct linux_binprm;
-extern int ia32_setup_arg_pages(struct linux_binprm *bprm,
-				unsigned long stack_top, int exec_stack);
-struct mm_struct;
-extern void ia32_pick_mmap_layout(struct mm_struct *mm);
-
-#endif
-
-#endif /* !CONFIG_IA32_SUPPORT */
-
-#endif /* ASM_X86__IA32_H */
diff --git a/include/asm-x86/ia32_unistd.h b/include/asm-x86/ia32_unistd.h
deleted file mode 100644
index dbd887d8a5a5..000000000000
--- a/include/asm-x86/ia32_unistd.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef ASM_X86__IA32_UNISTD_H
-#define ASM_X86__IA32_UNISTD_H
-
-/*
- * This file contains the system call numbers of the ia32 port,
- * this is for the kernel only.
- * Only add syscalls here where some part of the kernel needs to know
- * the number. This should be otherwise in sync with asm-x86/unistd_32.h. -AK
- */
-
-#define __NR_ia32_restart_syscall 0
-#define __NR_ia32_exit		  1
-#define __NR_ia32_read		  3
-#define __NR_ia32_write		  4
-#define __NR_ia32_sigreturn	119
-#define __NR_ia32_rt_sigreturn	173
-
-#endif /* ASM_X86__IA32_UNISTD_H */
diff --git a/include/asm-x86/idle.h b/include/asm-x86/idle.h
deleted file mode 100644
index baa3f783d27d..000000000000
--- a/include/asm-x86/idle.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef ASM_X86__IDLE_H
-#define ASM_X86__IDLE_H
-
-#define IDLE_START 1
-#define IDLE_END 2
-
-struct notifier_block;
-void idle_notifier_register(struct notifier_block *n);
-
-void enter_idle(void);
-void exit_idle(void);
-
-void c1e_remove_cpu(int cpu);
-
-#endif /* ASM_X86__IDLE_H */
diff --git a/include/asm-x86/intel_arch_perfmon.h b/include/asm-x86/intel_arch_perfmon.h
deleted file mode 100644
index 07c03c6c9a16..000000000000
--- a/include/asm-x86/intel_arch_perfmon.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef ASM_X86__INTEL_ARCH_PERFMON_H
-#define ASM_X86__INTEL_ARCH_PERFMON_H
-
-#define MSR_ARCH_PERFMON_PERFCTR0		0xc1
-#define MSR_ARCH_PERFMON_PERFCTR1		0xc2
-
-#define MSR_ARCH_PERFMON_EVENTSEL0		0x186
-#define MSR_ARCH_PERFMON_EVENTSEL1		0x187
-
-#define ARCH_PERFMON_EVENTSEL0_ENABLE	(1 << 22)
-#define ARCH_PERFMON_EVENTSEL_INT	(1 << 20)
-#define ARCH_PERFMON_EVENTSEL_OS	(1 << 17)
-#define ARCH_PERFMON_EVENTSEL_USR	(1 << 16)
-
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL	(0x3c)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK	(0x00 << 8)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX (0)
-#define ARCH_PERFMON_UNHALTED_CORE_CYCLES_PRESENT \
-	(1 << (ARCH_PERFMON_UNHALTED_CORE_CYCLES_INDEX))
-
-union cpuid10_eax {
-	struct {
-		unsigned int version_id:8;
-		unsigned int num_counters:8;
-		unsigned int bit_width:8;
-		unsigned int mask_length:8;
-	} split;
-	unsigned int full;
-};
-
-#endif /* ASM_X86__INTEL_ARCH_PERFMON_H */
diff --git a/include/asm-x86/io.h b/include/asm-x86/io.h
deleted file mode 100644
index a233f835e0b5..000000000000
--- a/include/asm-x86/io.h
+++ /dev/null
@@ -1,91 +0,0 @@
-#ifndef ASM_X86__IO_H
-#define ASM_X86__IO_H
-
-#define ARCH_HAS_IOREMAP_WC
-
-#include <linux/compiler.h>
-
-#define build_mmio_read(name, size, type, reg, barrier) \
-static inline type name(const volatile void __iomem *addr) \
-{ type ret; asm volatile("mov" size " %1,%0":reg (ret) \
-:"m" (*(volatile type __force *)addr) barrier); return ret; }
-
-#define build_mmio_write(name, size, type, reg, barrier) \
-static inline void name(type val, volatile void __iomem *addr) \
-{ asm volatile("mov" size " %0,%1": :reg (val), \
-"m" (*(volatile type __force *)addr) barrier); }
-
-build_mmio_read(readb, "b", unsigned char, "=q", :"memory")
-build_mmio_read(readw, "w", unsigned short, "=r", :"memory")
-build_mmio_read(readl, "l", unsigned int, "=r", :"memory")
-
-build_mmio_read(__readb, "b", unsigned char, "=q", )
-build_mmio_read(__readw, "w", unsigned short, "=r", )
-build_mmio_read(__readl, "l", unsigned int, "=r", )
-
-build_mmio_write(writeb, "b", unsigned char, "q", :"memory")
-build_mmio_write(writew, "w", unsigned short, "r", :"memory")
-build_mmio_write(writel, "l", unsigned int, "r", :"memory")
-
-build_mmio_write(__writeb, "b", unsigned char, "q", )
-build_mmio_write(__writew, "w", unsigned short, "r", )
-build_mmio_write(__writel, "l", unsigned int, "r", )
-
-#define readb_relaxed(a) __readb(a)
-#define readw_relaxed(a) __readw(a)
-#define readl_relaxed(a) __readl(a)
-#define __raw_readb __readb
-#define __raw_readw __readw
-#define __raw_readl __readl
-
-#define __raw_writeb __writeb
-#define __raw_writew __writew
-#define __raw_writel __writel
-
-#define mmiowb() barrier()
-
-#ifdef CONFIG_X86_64
-build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
-build_mmio_read(__readq, "q", unsigned long, "=r", )
-build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
-build_mmio_write(__writeq, "q", unsigned long, "r", )
-
-#define readq_relaxed(a) __readq(a)
-#define __raw_readq __readq
-#define __raw_writeq writeq
-
-/* Let people know we have them */
-#define readq readq
-#define writeq writeq
-#endif
-
-extern int iommu_bio_merge;
-
-#ifdef CONFIG_X86_32
-# include "io_32.h"
-#else
-# include "io_64.h"
-#endif
-
-extern void *xlate_dev_mem_ptr(unsigned long phys);
-extern void unxlate_dev_mem_ptr(unsigned long phys, void *addr);
-
-extern int ioremap_change_attr(unsigned long vaddr, unsigned long size,
-				unsigned long prot_val);
-extern void __iomem *ioremap_wc(unsigned long offset, unsigned long size);
-
-/*
- * early_ioremap() and early_iounmap() are for temporary early boot-time
- * mappings, before the real ioremap() is functional.
- * A boot-time mapping is currently limited to at most 16 pages.
- */
-extern void early_ioremap_init(void);
-extern void early_ioremap_clear(void);
-extern void early_ioremap_reset(void);
-extern void *early_ioremap(unsigned long offset, unsigned long size);
-extern void *early_memremap(unsigned long offset, unsigned long size);
-extern void early_iounmap(void *addr, unsigned long size);
-extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
-
-
-#endif /* ASM_X86__IO_H */
diff --git a/include/asm-x86/io_32.h b/include/asm-x86/io_32.h
deleted file mode 100644
index 4f7d878bda18..000000000000
--- a/include/asm-x86/io_32.h
+++ /dev/null
@@ -1,284 +0,0 @@
-#ifndef ASM_X86__IO_32_H
-#define ASM_X86__IO_32_H
-
-#include <linux/string.h>
-#include <linux/compiler.h>
-
-/*
- * This file contains the definitions for the x86 IO instructions
- * inb/inw/inl/outb/outw/outl and the "string versions" of the same
- * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
- * versions of the single-IO instructions (inb_p/inw_p/..).
- *
- * This file is not meant to be obfuscating: it's just complicated
- * to (a) handle it all in a way that makes gcc able to optimize it
- * as well as possible and (b) trying to avoid writing the same thing
- * over and over again with slight variations and possibly making a
- * mistake somewhere.
- */
-
-/*
- * Thanks to James van Artsdalen for a better timing-fix than
- * the two short jumps: using outb's to a nonexistent port seems
- * to guarantee better timings even on fast machines.
- *
- * On the other hand, I'd like to be sure of a non-existent port:
- * I feel a bit unsafe about using 0x80 (should be safe, though)
- *
- *		Linus
- */
-
- /*
-  *  Bit simplified and optimized by Jan Hubicka
-  *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
-  *
-  *  isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
-  *  isa_read[wl] and isa_write[wl] fixed
-  *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-  */
-
-#define IO_SPACE_LIMIT 0xffff
-
-#define XQUAD_PORTIO_BASE 0xfe400000
-#define XQUAD_PORTIO_QUAD 0x40000  /* 256k per quad. */
-
-#ifdef __KERNEL__
-
-#include <asm-generic/iomap.h>
-
-#include <linux/vmalloc.h>
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
-
-/**
- *	virt_to_phys	-	map virtual addresses to physical
- *	@address: address to remap
- *
- *	The returned physical address is the physical (CPU) mapping for
- *	the memory address given. It is only valid to use this function on
- *	addresses directly mapped or allocated via kmalloc.
- *
- *	This function does not give bus mappings for DMA transfers. In
- *	almost all conceivable cases a device driver should not be using
- *	this function
- */
-
-static inline unsigned long virt_to_phys(volatile void *address)
-{
-	return __pa(address);
-}
-
-/**
- *	phys_to_virt	-	map physical address to virtual
- *	@address: address to remap
- *
- *	The returned virtual address is a current CPU mapping for
- *	the memory address given. It is only valid to use this function on
- *	addresses that have a kernel mapping
- *
- *	This function does not handle bus mappings for DMA transfers. In
- *	almost all conceivable cases a device driver should not be using
- *	this function
- */
-
-static inline void *phys_to_virt(unsigned long address)
-{
-	return __va(address);
-}
-
-/*
- * Change "struct page" to physical address.
- */
-#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
-
-/**
- * ioremap     -   map bus memory into CPU space
- * @offset:    bus address of the memory
- * @size:      size of the resource to map
- *
- * ioremap performs a platform specific sequence of operations to
- * make bus memory CPU accessible via the readb/readw/readl/writeb/
- * writew/writel functions and the other mmio helpers. The returned
- * address is not guaranteed to be usable directly as a virtual
- * address.
- *
- * If the area you are trying to map is a PCI BAR you should have a
- * look at pci_iomap().
- */
-extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
-				unsigned long prot_val);
-
-/*
- * The default ioremap() behavior is non-cached:
- */
-static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
-{
-	return ioremap_nocache(offset, size);
-}
-
-extern void iounmap(volatile void __iomem *addr);
-
-/*
- * ISA I/O bus memory addresses are 1:1 with the physical address.
- */
-#define isa_virt_to_bus virt_to_phys
-#define isa_page_to_bus page_to_phys
-#define isa_bus_to_virt phys_to_virt
-
-/*
- * However PCI ones are not necessarily 1:1 and therefore these interfaces
- * are forbidden in portable PCI drivers.
- *
- * Allow them on x86 for legacy drivers, though.
- */
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-
-static inline void
-memset_io(volatile void __iomem *addr, unsigned char val, int count)
-{
-	memset((void __force *)addr, val, count);
-}
-
-static inline void
-memcpy_fromio(void *dst, const volatile void __iomem *src, int count)
-{
-	__memcpy(dst, (const void __force *)src, count);
-}
-
-static inline void
-memcpy_toio(volatile void __iomem *dst, const void *src, int count)
-{
-	__memcpy((void __force *)dst, src, count);
-}
-
-/*
- * ISA space is 'always mapped' on a typical x86 system, no need to
- * explicitly ioremap() it. The fact that the ISA IO space is mapped
- * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
- * are physical addresses. The following constant pointer can be
- * used as the IO-area pointer (it can be iounmapped as well, so the
- * analogy with PCI is quite large):
- */
-#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
-
-/*
- *	Cache management
- *
- *	This needed for two cases
- *	1. Out of order aware processors
- *	2. Accidentally out of order processors (PPro errata #51)
- */
-
-#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
-
-static inline void flush_write_buffers(void)
-{
-	asm volatile("lock; addl $0,0(%%esp)": : :"memory");
-}
-
-#else
-
-#define flush_write_buffers() do { } while (0)
-
-#endif
-
-#endif /* __KERNEL__ */
-
-extern void native_io_delay(void);
-
-extern int io_delay_type;
-extern void io_delay_init(void);
-
-#if defined(CONFIG_PARAVIRT)
-#include <asm/paravirt.h>
-#else
-
-static inline void slow_down_io(void)
-{
-	native_io_delay();
-#ifdef REALLY_SLOW_IO
-	native_io_delay();
-	native_io_delay();
-	native_io_delay();
-#endif
-}
-
-#endif
-
-#define __BUILDIO(bwl, bw, type)				\
-static inline void out##bwl(unsigned type value, int port)	\
-{								\
-	out##bwl##_local(value, port);				\
-}								\
-								\
-static inline unsigned type in##bwl(int port)			\
-{								\
-	return in##bwl##_local(port);				\
-}
-
-#define BUILDIO(bwl, bw, type)						\
-static inline void out##bwl##_local(unsigned type value, int port)	\
-{									\
-	asm volatile("out" #bwl " %" #bw "0, %w1"		\
-		     : : "a"(value), "Nd"(port));			\
-}									\
-									\
-static inline unsigned type in##bwl##_local(int port)			\
-{									\
-	unsigned type value;						\
-	asm volatile("in" #bwl " %w1, %" #bw "0"		\
-		     : "=a"(value) : "Nd"(port));			\
-	return value;							\
-}									\
-									\
-static inline void out##bwl##_local_p(unsigned type value, int port)	\
-{									\
-	out##bwl##_local(value, port);					\
-	slow_down_io();							\
-}									\
-									\
-static inline unsigned type in##bwl##_local_p(int port)			\
-{									\
-	unsigned type value = in##bwl##_local(port);			\
-	slow_down_io();							\
-	return value;							\
-}									\
-									\
-__BUILDIO(bwl, bw, type)						\
-									\
-static inline void out##bwl##_p(unsigned type value, int port)		\
-{									\
-	out##bwl(value, port);						\
-	slow_down_io();							\
-}									\
-									\
-static inline unsigned type in##bwl##_p(int port)			\
-{									\
-	unsigned type value = in##bwl(port);				\
-	slow_down_io();							\
-	return value;							\
-}									\
-									\
-static inline void outs##bwl(int port, const void *addr, unsigned long count) \
-{									\
-	asm volatile("rep; outs" #bwl					\
-		     : "+S"(addr), "+c"(count) : "d"(port));		\
-}									\
-									\
-static inline void ins##bwl(int port, void *addr, unsigned long count)	\
-{									\
-	asm volatile("rep; ins" #bwl					\
-		     : "+D"(addr), "+c"(count) : "d"(port));		\
-}
-
-BUILDIO(b, b, char)
-BUILDIO(w, w, short)
-BUILDIO(l, , int)
-
-#endif /* ASM_X86__IO_32_H */
diff --git a/include/asm-x86/io_64.h b/include/asm-x86/io_64.h
deleted file mode 100644
index ee6e086b7dfe..000000000000
--- a/include/asm-x86/io_64.h
+++ /dev/null
@@ -1,244 +0,0 @@
-#ifndef ASM_X86__IO_64_H
-#define ASM_X86__IO_64_H
-
-
-/*
- * This file contains the definitions for the x86 IO instructions
- * inb/inw/inl/outb/outw/outl and the "string versions" of the same
- * (insb/insw/insl/outsb/outsw/outsl). You can also use "pausing"
- * versions of the single-IO instructions (inb_p/inw_p/..).
- *
- * This file is not meant to be obfuscating: it's just complicated
- * to (a) handle it all in a way that makes gcc able to optimize it
- * as well as possible and (b) trying to avoid writing the same thing
- * over and over again with slight variations and possibly making a
- * mistake somewhere.
- */
-
-/*
- * Thanks to James van Artsdalen for a better timing-fix than
- * the two short jumps: using outb's to a nonexistent port seems
- * to guarantee better timings even on fast machines.
- *
- * On the other hand, I'd like to be sure of a non-existent port:
- * I feel a bit unsafe about using 0x80 (should be safe, though)
- *
- *		Linus
- */
-
- /*
-  *  Bit simplified and optimized by Jan Hubicka
-  *  Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999.
-  *
-  *  isa_memset_io, isa_memcpy_fromio, isa_memcpy_toio added,
-  *  isa_read[wl] and isa_write[wl] fixed
-  *  - Arnaldo Carvalho de Melo <acme@conectiva.com.br>
-  */
-
-extern void native_io_delay(void);
-
-extern int io_delay_type;
-extern void io_delay_init(void);
-
-#if defined(CONFIG_PARAVIRT)
-#include <asm/paravirt.h>
-#else
-
-static inline void slow_down_io(void)
-{
-	native_io_delay();
-#ifdef REALLY_SLOW_IO
-	native_io_delay();
-	native_io_delay();
-	native_io_delay();
-#endif
-}
-#endif
-
-/*
- * Talk about misusing macros..
- */
-#define __OUT1(s, x)							\
-static inline void out##s(unsigned x value, unsigned short port) {
-
-#define __OUT2(s, s1, s2)				\
-asm volatile ("out" #s " %" s1 "0,%" s2 "1"
-
-#ifndef REALLY_SLOW_IO
-#define REALLY_SLOW_IO
-#define UNSET_REALLY_SLOW_IO
-#endif
-
-#define __OUT(s, s1, x)							\
-	__OUT1(s, x) __OUT2(s, s1, "w") : : "a" (value), "Nd" (port));	\
-	}								\
-	__OUT1(s##_p, x) __OUT2(s, s1, "w") : : "a" (value), "Nd" (port)); \
-	slow_down_io();							\
-}
-
-#define __IN1(s)							\
-static inline RETURN_TYPE in##s(unsigned short port)			\
-{									\
-	RETURN_TYPE _v;
-
-#define __IN2(s, s1, s2)						\
-	asm volatile ("in" #s " %" s2 "1,%" s1 "0"
-
-#define __IN(s, s1, i...)						\
-	__IN1(s) __IN2(s, s1, "w") : "=a" (_v) : "Nd" (port), ##i);	\
-	return _v;							\
-	}								\
-	__IN1(s##_p) __IN2(s, s1, "w") : "=a" (_v) : "Nd" (port), ##i);	\
-	slow_down_io(); \
-	return _v; }
-
-#ifdef UNSET_REALLY_SLOW_IO
-#undef REALLY_SLOW_IO
-#endif
-
-#define __INS(s)							\
-static inline void ins##s(unsigned short port, void *addr,		\
-			  unsigned long count)				\
-{									\
-	asm volatile ("rep ; ins" #s					\
-		      : "=D" (addr), "=c" (count)			\
-		      : "d" (port), "0" (addr), "1" (count));		\
-}
-
-#define __OUTS(s)							\
-static inline void outs##s(unsigned short port, const void *addr,	\
-			   unsigned long count)				\
-{									\
-	asm volatile ("rep ; outs" #s					\
-		      : "=S" (addr), "=c" (count)			\
-		      : "d" (port), "0" (addr), "1" (count));		\
-}
-
-#define RETURN_TYPE unsigned char
-__IN(b, "")
-#undef RETURN_TYPE
-#define RETURN_TYPE unsigned short
-__IN(w, "")
-#undef RETURN_TYPE
-#define RETURN_TYPE unsigned int
-__IN(l, "")
-#undef RETURN_TYPE
-
-__OUT(b, "b", char)
-__OUT(w, "w", short)
-__OUT(l, , int)
-
-__INS(b)
-__INS(w)
-__INS(l)
-
-__OUTS(b)
-__OUTS(w)
-__OUTS(l)
-
-#define IO_SPACE_LIMIT 0xffff
-
-#if defined(__KERNEL__) && defined(__x86_64__)
-
-#include <linux/vmalloc.h>
-
-#ifndef __i386__
-/*
- * Change virtual addresses to physical addresses and vv.
- * These are pretty trivial
- */
-static inline unsigned long virt_to_phys(volatile void *address)
-{
-	return __pa(address);
-}
-
-static inline void *phys_to_virt(unsigned long address)
-{
-	return __va(address);
-}
-#endif
-
-/*
- * Change "struct page" to physical address.
- */
-#define page_to_phys(page)    ((dma_addr_t)page_to_pfn(page) << PAGE_SHIFT)
-
-#include <asm-generic/iomap.h>
-
-/*
- * This one maps high address device memory and turns off caching for that area.
- * it's useful if some control registers are in such an area and write combining
- * or read caching is not desirable:
- */
-extern void __iomem *ioremap_nocache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_cache(resource_size_t offset, unsigned long size);
-extern void __iomem *ioremap_prot(resource_size_t offset, unsigned long size,
-				unsigned long prot_val);
-
-/*
- * The default ioremap() behavior is non-cached:
- */
-static inline void __iomem *ioremap(resource_size_t offset, unsigned long size)
-{
-	return ioremap_nocache(offset, size);
-}
-
-extern void iounmap(volatile void __iomem *addr);
-
-extern void __iomem *fix_ioremap(unsigned idx, unsigned long phys);
-
-/*
- * ISA I/O bus memory addresses are 1:1 with the physical address.
- */
-#define isa_virt_to_bus virt_to_phys
-#define isa_page_to_bus page_to_phys
-#define isa_bus_to_virt phys_to_virt
-
-/*
- * However PCI ones are not necessarily 1:1 and therefore these interfaces
- * are forbidden in portable PCI drivers.
- *
- * Allow them on x86 for legacy drivers, though.
- */
-#define virt_to_bus virt_to_phys
-#define bus_to_virt phys_to_virt
-
-void __memcpy_fromio(void *, unsigned long, unsigned);
-void __memcpy_toio(unsigned long, const void *, unsigned);
-
-static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
-				 unsigned len)
-{
-	__memcpy_fromio(to, (unsigned long)from, len);
-}
-
-static inline void memcpy_toio(volatile void __iomem *to, const void *from,
-			       unsigned len)
-{
-	__memcpy_toio((unsigned long)to, from, len);
-}
-
-void memset_io(volatile void __iomem *a, int b, size_t c);
-
-/*
- * ISA space is 'always mapped' on a typical x86 system, no need to
- * explicitly ioremap() it. The fact that the ISA IO space is mapped
- * to PAGE_OFFSET is pure coincidence - it does not mean ISA values
- * are physical addresses. The following constant pointer can be
- * used as the IO-area pointer (it can be iounmapped as well, so the
- * analogy with PCI is quite large):
- */
-#define __ISA_IO_base ((char __iomem *)(PAGE_OFFSET))
-
-#define flush_write_buffers()
-
-#define BIO_VMERGE_BOUNDARY iommu_bio_merge
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
-
-#endif /* __KERNEL__ */
-
-#endif /* ASM_X86__IO_64_H */
diff --git a/include/asm-x86/io_apic.h b/include/asm-x86/io_apic.h
deleted file mode 100644
index d35cbd7aa587..000000000000
--- a/include/asm-x86/io_apic.h
+++ /dev/null
@@ -1,204 +0,0 @@
-#ifndef ASM_X86__IO_APIC_H
-#define ASM_X86__IO_APIC_H
-
-#include <linux/types.h>
-#include <asm/mpspec.h>
-#include <asm/apicdef.h>
-#include <asm/irq_vectors.h>
-
-/*
- * Intel IO-APIC support for SMP and UP systems.
- *
- * Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar
- */
-
-/* I/O Unit Redirection Table */
-#define IO_APIC_REDIR_VECTOR_MASK	0x000FF
-#define IO_APIC_REDIR_DEST_LOGICAL	0x00800
-#define IO_APIC_REDIR_DEST_PHYSICAL	0x00000
-#define IO_APIC_REDIR_SEND_PENDING	(1 << 12)
-#define IO_APIC_REDIR_REMOTE_IRR	(1 << 14)
-#define IO_APIC_REDIR_LEVEL_TRIGGER	(1 << 15)
-#define IO_APIC_REDIR_MASKED		(1 << 16)
-
-/*
- * The structure of the IO-APIC:
- */
-union IO_APIC_reg_00 {
-	u32	raw;
-	struct {
-		u32	__reserved_2	: 14,
-			LTS		:  1,
-			delivery_type	:  1,
-			__reserved_1	:  8,
-			ID		:  8;
-	} __attribute__ ((packed)) bits;
-};
-
-union IO_APIC_reg_01 {
-	u32	raw;
-	struct {
-		u32	version		:  8,
-			__reserved_2	:  7,
-			PRQ		:  1,
-			entries		:  8,
-			__reserved_1	:  8;
-	} __attribute__ ((packed)) bits;
-};
-
-union IO_APIC_reg_02 {
-	u32	raw;
-	struct {
-		u32	__reserved_2	: 24,
-			arbitration	:  4,
-			__reserved_1	:  4;
-	} __attribute__ ((packed)) bits;
-};
-
-union IO_APIC_reg_03 {
-	u32	raw;
-	struct {
-		u32	boot_DT		:  1,
-			__reserved_1	: 31;
-	} __attribute__ ((packed)) bits;
-};
-
-enum ioapic_irq_destination_types {
-	dest_Fixed = 0,
-	dest_LowestPrio = 1,
-	dest_SMI = 2,
-	dest__reserved_1 = 3,
-	dest_NMI = 4,
-	dest_INIT = 5,
-	dest__reserved_2 = 6,
-	dest_ExtINT = 7
-};
-
-struct IO_APIC_route_entry {
-	__u32	vector		:  8,
-		delivery_mode	:  3,	/* 000: FIXED
-					 * 001: lowest prio
-					 * 111: ExtINT
-					 */
-		dest_mode	:  1,	/* 0: physical, 1: logical */
-		delivery_status	:  1,
-		polarity	:  1,
-		irr		:  1,
-		trigger		:  1,	/* 0: edge, 1: level */
-		mask		:  1,	/* 0: enabled, 1: disabled */
-		__reserved_2	: 15;
-
-	__u32	__reserved_3	: 24,
-		dest		:  8;
-} __attribute__ ((packed));
-
-struct IR_IO_APIC_route_entry {
-	__u64	vector		: 8,
-		zero		: 3,
-		index2		: 1,
-		delivery_status : 1,
-		polarity	: 1,
-		irr		: 1,
-		trigger		: 1,
-		mask		: 1,
-		reserved	: 31,
-		format		: 1,
-		index		: 15;
-} __attribute__ ((packed));
-
-#ifdef CONFIG_X86_IO_APIC
-
-/*
- * # of IO-APICs and # of IRQ routing registers
- */
-extern int nr_ioapics;
-extern int nr_ioapic_registers[MAX_IO_APICS];
-
-/*
- * MP-BIOS irq configuration table structures:
- */
-
-#define MP_MAX_IOAPIC_PIN 127
-
-struct mp_config_ioapic {
-	unsigned long mp_apicaddr;
-	unsigned int mp_apicid;
-	unsigned char mp_type;
-	unsigned char mp_apicver;
-	unsigned char mp_flags;
-};
-
-struct mp_config_intsrc {
-	unsigned int mp_dstapic;
-	unsigned char mp_type;
-	unsigned char mp_irqtype;
-	unsigned short mp_irqflag;
-	unsigned char mp_srcbus;
-	unsigned char mp_srcbusirq;
-	unsigned char mp_dstirq;
-};
-
-/* I/O APIC entries */
-extern struct mp_config_ioapic mp_ioapics[MAX_IO_APICS];
-
-/* # of MP IRQ source entries */
-extern int mp_irq_entries;
-
-/* MP IRQ source entries */
-extern struct mp_config_intsrc mp_irqs[MAX_IRQ_SOURCES];
-
-/* non-0 if default (table-less) MP configuration */
-extern int mpc_default_type;
-
-/* Older SiS APIC requires we rewrite the index register */
-extern int sis_apic_bug;
-
-/* 1 if "noapic" boot option passed */
-extern int skip_ioapic_setup;
-
-/* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
-extern int timer_through_8259;
-
-static inline void disable_ioapic_setup(void)
-{
-	skip_ioapic_setup = 1;
-}
-
-/*
- * If we use the IO-APIC for IRQ routing, disable automatic
- * assignment of PCI IRQ's.
- */
-#define io_apic_assign_pci_irqs \
-	(mp_irq_entries && !skip_ioapic_setup && io_apic_irqs)
-
-#ifdef CONFIG_ACPI
-extern int io_apic_get_unique_id(int ioapic, int apic_id);
-extern int io_apic_get_version(int ioapic);
-extern int io_apic_get_redir_entries(int ioapic);
-extern int io_apic_set_pci_routing(int ioapic, int pin, int irq,
-				   int edge_level, int active_high_low);
-#endif /* CONFIG_ACPI */
-
-extern int (*ioapic_renumber_irq)(int ioapic, int irq);
-extern void ioapic_init_mappings(void);
-
-#ifdef CONFIG_X86_64
-extern int save_mask_IO_APIC_setup(void);
-extern void restore_IO_APIC_setup(void);
-extern void reinit_intr_remapped_IO_APIC(int);
-#endif
-
-extern int probe_nr_irqs(void);
-
-#else  /* !CONFIG_X86_IO_APIC */
-#define io_apic_assign_pci_irqs 0
-static const int timer_through_8259 = 0;
-static inline void ioapic_init_mappings(void) { }
-
-static inline int probe_nr_irqs(void)
-{
-	return NR_IRQS;
-}
-#endif
-
-#endif /* ASM_X86__IO_APIC_H */
diff --git a/include/asm-x86/ioctl.h b/include/asm-x86/ioctl.h
deleted file mode 100644
index b279fe06dfe5..000000000000
--- a/include/asm-x86/ioctl.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ioctl.h>
diff --git a/include/asm-x86/ioctls.h b/include/asm-x86/ioctls.h
deleted file mode 100644
index 06752a649044..000000000000
--- a/include/asm-x86/ioctls.h
+++ /dev/null
@@ -1,94 +0,0 @@
-#ifndef ASM_X86__IOCTLS_H
-#define ASM_X86__IOCTLS_H
-
-#include <asm/ioctl.h>
-
-/* 0x54 is just a magic number to make these relatively unique ('T') */
-
-#define TCGETS		0x5401
-#define TCSETS		0x5402 /* Clashes with SNDCTL_TMR_START sound ioctl */
-#define TCSETSW		0x5403
-#define TCSETSF		0x5404
-#define TCGETA		0x5405
-#define TCSETA		0x5406
-#define TCSETAW		0x5407
-#define TCSETAF		0x5408
-#define TCSBRK		0x5409
-#define TCXONC		0x540A
-#define TCFLSH		0x540B
-#define TIOCEXCL	0x540C
-#define TIOCNXCL	0x540D
-#define TIOCSCTTY	0x540E
-#define TIOCGPGRP	0x540F
-#define TIOCSPGRP	0x5410
-#define TIOCOUTQ	0x5411
-#define TIOCSTI		0x5412
-#define TIOCGWINSZ	0x5413
-#define TIOCSWINSZ	0x5414
-#define TIOCMGET	0x5415
-#define TIOCMBIS	0x5416
-#define TIOCMBIC	0x5417
-#define TIOCMSET	0x5418
-#define TIOCGSOFTCAR	0x5419
-#define TIOCSSOFTCAR	0x541A
-#define FIONREAD	0x541B
-#define TIOCINQ		FIONREAD
-#define TIOCLINUX	0x541C
-#define TIOCCONS	0x541D
-#define TIOCGSERIAL	0x541E
-#define TIOCSSERIAL	0x541F
-#define TIOCPKT		0x5420
-#define FIONBIO		0x5421
-#define TIOCNOTTY	0x5422
-#define TIOCSETD	0x5423
-#define TIOCGETD	0x5424
-#define TCSBRKP		0x5425	/* Needed for POSIX tcsendbreak() */
-/* #define TIOCTTYGSTRUCT 0x5426 - Former debugging-only ioctl */
-#define TIOCSBRK	0x5427  /* BSD compatibility */
-#define TIOCCBRK	0x5428  /* BSD compatibility */
-#define TIOCGSID	0x5429  /* Return the session ID of FD */
-#define TCGETS2		_IOR('T', 0x2A, struct termios2)
-#define TCSETS2		_IOW('T', 0x2B, struct termios2)
-#define TCSETSW2	_IOW('T', 0x2C, struct termios2)
-#define TCSETSF2	_IOW('T', 0x2D, struct termios2)
-#define TIOCGRS485	0x542E
-#define TIOCSRS485	0x542F
-#define TIOCGPTN	_IOR('T', 0x30, unsigned int)
-				/* Get Pty Number (of pty-mux device) */
-#define TIOCSPTLCK	_IOW('T', 0x31, int)  /* Lock/unlock Pty */
-#define TCGETX		0x5432 /* SYS5 TCGETX compatibility */
-#define TCSETX		0x5433
-#define TCSETXF		0x5434
-#define TCSETXW		0x5435
-
-#define FIONCLEX	0x5450
-#define FIOCLEX		0x5451
-#define FIOASYNC	0x5452
-#define TIOCSERCONFIG	0x5453
-#define TIOCSERGWILD	0x5454
-#define TIOCSERSWILD	0x5455
-#define TIOCGLCKTRMIOS	0x5456
-#define TIOCSLCKTRMIOS	0x5457
-#define TIOCSERGSTRUCT	0x5458 /* For debugging only */
-#define TIOCSERGETLSR   0x5459 /* Get line status register */
-#define TIOCSERGETMULTI 0x545A /* Get multiport config  */
-#define TIOCSERSETMULTI 0x545B /* Set multiport config */
-
-#define TIOCMIWAIT	0x545C	/* wait for a change on serial input line(s) */
-#define TIOCGICOUNT	0x545D	/* read serial port inline interrupt counts */
-#define TIOCGHAYESESP   0x545E  /* Get Hayes ESP configuration */
-#define TIOCSHAYESESP   0x545F  /* Set Hayes ESP configuration */
-#define FIOQSIZE	0x5460
-
-/* Used for packet mode */
-#define TIOCPKT_DATA		 0
-#define TIOCPKT_FLUSHREAD	 1
-#define TIOCPKT_FLUSHWRITE	 2
-#define TIOCPKT_STOP		 4
-#define TIOCPKT_START		 8
-#define TIOCPKT_NOSTOP		16
-#define TIOCPKT_DOSTOP		32
-
-#define TIOCSER_TEMT    0x01	/* Transmitter physically empty */
-
-#endif /* ASM_X86__IOCTLS_H */
diff --git a/include/asm-x86/iommu.h b/include/asm-x86/iommu.h
deleted file mode 100644
index 961e746da977..000000000000
--- a/include/asm-x86/iommu.h
+++ /dev/null
@@ -1,46 +0,0 @@
-#ifndef ASM_X86__IOMMU_H
-#define ASM_X86__IOMMU_H
-
-extern void pci_iommu_shutdown(void);
-extern void no_iommu_init(void);
-extern struct dma_mapping_ops nommu_dma_ops;
-extern int force_iommu, no_iommu;
-extern int iommu_detected;
-extern int dmar_disabled;
-
-extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len);
-
-#ifdef CONFIG_GART_IOMMU
-extern int gart_iommu_aperture;
-extern int gart_iommu_aperture_allowed;
-extern int gart_iommu_aperture_disabled;
-
-extern void early_gart_iommu_check(void);
-extern void gart_iommu_init(void);
-extern void gart_iommu_shutdown(void);
-extern void __init gart_parse_options(char *);
-extern void gart_iommu_hole_init(void);
-
-#else
-#define gart_iommu_aperture            0
-#define gart_iommu_aperture_allowed    0
-#define gart_iommu_aperture_disabled   1
-
-static inline void early_gart_iommu_check(void)
-{
-}
-static inline void gart_iommu_init(void)
-{
-}
-static inline void gart_iommu_shutdown(void)
-{
-}
-static inline void gart_parse_options(char *options)
-{
-}
-static inline void gart_iommu_hole_init(void)
-{
-}
-#endif
-
-#endif /* ASM_X86__IOMMU_H */
diff --git a/include/asm-x86/ipcbuf.h b/include/asm-x86/ipcbuf.h
deleted file mode 100644
index 910304fbdc8f..000000000000
--- a/include/asm-x86/ipcbuf.h
+++ /dev/null
@@ -1,28 +0,0 @@
-#ifndef ASM_X86__IPCBUF_H
-#define ASM_X86__IPCBUF_H
-
-/*
- * The ipc64_perm structure for x86 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 32-bit mode_t and seq
- * - 2 miscellaneous 32-bit values
- */
-
-struct ipc64_perm {
-	__kernel_key_t		key;
-	__kernel_uid32_t	uid;
-	__kernel_gid32_t	gid;
-	__kernel_uid32_t	cuid;
-	__kernel_gid32_t	cgid;
-	__kernel_mode_t		mode;
-	unsigned short		__pad1;
-	unsigned short		seq;
-	unsigned short		__pad2;
-	unsigned long		__unused1;
-	unsigned long		__unused2;
-};
-
-#endif /* ASM_X86__IPCBUF_H */
diff --git a/include/asm-x86/ipi.h b/include/asm-x86/ipi.h
deleted file mode 100644
index 30a692cfaff8..000000000000
--- a/include/asm-x86/ipi.h
+++ /dev/null
@@ -1,138 +0,0 @@
-#ifndef ASM_X86__IPI_H
-#define ASM_X86__IPI_H
-
-/*
- * Copyright 2004 James Cleverdon, IBM.
- * Subject to the GNU Public License, v.2
- *
- * Generic APIC InterProcessor Interrupt code.
- *
- * Moved to include file by James Cleverdon from
- * arch/x86-64/kernel/smp.c
- *
- * Copyrights from kernel/smp.c:
- *
- * (c) 1995 Alan Cox, Building #3 <alan@redhat.com>
- * (c) 1998-99, 2000 Ingo Molnar <mingo@redhat.com>
- * (c) 2002,2003 Andi Kleen, SuSE Labs.
- * Subject to the GNU Public License, v.2
- */
-
-#include <asm/hw_irq.h>
-#include <asm/apic.h>
-#include <asm/smp.h>
-
-/*
- * the following functions deal with sending IPIs between CPUs.
- *
- * We use 'broadcast', CPU->CPU IPIs and self-IPIs too.
- */
-
-static inline unsigned int __prepare_ICR(unsigned int shortcut, int vector,
-					 unsigned int dest)
-{
-	unsigned int icr = shortcut | dest;
-
-	switch (vector) {
-	default:
-		icr |= APIC_DM_FIXED | vector;
-		break;
-	case NMI_VECTOR:
-		icr |= APIC_DM_NMI;
-		break;
-	}
-	return icr;
-}
-
-static inline int __prepare_ICR2(unsigned int mask)
-{
-	return SET_APIC_DEST_FIELD(mask);
-}
-
-static inline void __xapic_wait_icr_idle(void)
-{
-	while (native_apic_mem_read(APIC_ICR) & APIC_ICR_BUSY)
-		cpu_relax();
-}
-
-static inline void __send_IPI_shortcut(unsigned int shortcut, int vector,
-				       unsigned int dest)
-{
-	/*
-	 * Subtle. In the case of the 'never do double writes' workaround
-	 * we have to lock out interrupts to be safe.  As we don't care
-	 * of the value read we use an atomic rmw access to avoid costly
-	 * cli/sti.  Otherwise we use an even cheaper single atomic write
-	 * to the APIC.
-	 */
-	unsigned int cfg;
-
-	/*
-	 * Wait for idle.
-	 */
-	__xapic_wait_icr_idle();
-
-	/*
-	 * No need to touch the target chip field
-	 */
-	cfg = __prepare_ICR(shortcut, vector, dest);
-
-	/*
-	 * Send the IPI. The write to APIC_ICR fires this off.
-	 */
-	native_apic_mem_write(APIC_ICR, cfg);
-}
-
-/*
- * This is used to send an IPI with no shorthand notation (the destination is
- * specified in bits 56 to 63 of the ICR).
- */
-static inline void __send_IPI_dest_field(unsigned int mask, int vector,
-					 unsigned int dest)
-{
-	unsigned long cfg;
-
-	/*
-	 * Wait for idle.
-	 */
-	if (unlikely(vector == NMI_VECTOR))
-		safe_apic_wait_icr_idle();
-	else
-		__xapic_wait_icr_idle();
-
-	/*
-	 * prepare target chip field
-	 */
-	cfg = __prepare_ICR2(mask);
-	native_apic_mem_write(APIC_ICR2, cfg);
-
-	/*
-	 * program the ICR
-	 */
-	cfg = __prepare_ICR(0, vector, dest);
-
-	/*
-	 * Send the IPI. The write to APIC_ICR fires this off.
-	 */
-	native_apic_mem_write(APIC_ICR, cfg);
-}
-
-static inline void send_IPI_mask_sequence(cpumask_t mask, int vector)
-{
-	unsigned long flags;
-	unsigned long query_cpu;
-
-	/*
-	 * Hack. The clustered APIC addressing mode doesn't allow us to send
-	 * to an arbitrary mask, so I do a unicast to each CPU instead.
-	 * - mbligh
-	 */
-	local_irq_save(flags);
-	for_each_cpu_mask_nr(query_cpu, mask) {
-		__send_IPI_dest_field(per_cpu(x86_cpu_to_apicid, query_cpu),
-				      vector, APIC_DEST_PHYSICAL);
-	}
-	local_irq_restore(flags);
-}
-
-#endif /* ASM_X86__IPI_H */
diff --git a/include/asm-x86/irq.h b/include/asm-x86/irq.h
deleted file mode 100644
index 1e5f2909c1db..000000000000
--- a/include/asm-x86/irq.h
+++ /dev/null
@@ -1,50 +0,0 @@
-#ifndef ASM_X86__IRQ_H
-#define ASM_X86__IRQ_H
-/*
- *	(C) 1992, 1993 Linus Torvalds, (C) 1997 Ingo Molnar
- *
- *	IRQ/IPI changes taken from work by Thomas Radke
- *	<tomsoft@informatik.tu-chemnitz.de>
- */
-
-#include <asm/apicdef.h>
-#include <asm/irq_vectors.h>
-
-static inline int irq_canonicalize(int irq)
-{
-	return ((irq == 2) ? 9 : irq);
-}
-
-#ifdef CONFIG_X86_LOCAL_APIC
-# define ARCH_HAS_NMI_WATCHDOG
-#endif
-
-#ifdef CONFIG_4KSTACKS
-  extern void irq_ctx_init(int cpu);
-  extern void irq_ctx_exit(int cpu);
-# define __ARCH_HAS_DO_SOFTIRQ
-#else
-# define irq_ctx_init(cpu) do { } while (0)
-# define irq_ctx_exit(cpu) do { } while (0)
-# ifdef CONFIG_X86_64
-#  define __ARCH_HAS_DO_SOFTIRQ
-# endif
-#endif
-
-#ifdef CONFIG_IRQBALANCE
-extern int irqbalance_disable(char *str);
-#endif
-
-#ifdef CONFIG_HOTPLUG_CPU
-#include <linux/cpumask.h>
-extern void fixup_irqs(cpumask_t map);
-#endif
-
-extern unsigned int do_IRQ(struct pt_regs *regs);
-extern void init_IRQ(void);
-extern void native_init_IRQ(void);
-
-/* Interrupt vector management */
-extern DECLARE_BITMAP(used_vectors, NR_VECTORS);
-
-#endif /* ASM_X86__IRQ_H */
diff --git a/include/asm-x86/irq_regs.h b/include/asm-x86/irq_regs.h
deleted file mode 100644
index 89c898ab298b..000000000000
--- a/include/asm-x86/irq_regs.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "irq_regs_32.h"
-#else
-# include "irq_regs_64.h"
-#endif
diff --git a/include/asm-x86/irq_regs_32.h b/include/asm-x86/irq_regs_32.h
deleted file mode 100644
index 316a3b258871..000000000000
--- a/include/asm-x86/irq_regs_32.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/*
- * Per-cpu current frame pointer - the location of the last exception frame on
- * the stack, stored in the per-cpu area.
- *
- * Jeremy Fitzhardinge <jeremy@goop.org>
- */
-#ifndef ASM_X86__IRQ_REGS_32_H
-#define ASM_X86__IRQ_REGS_32_H
-
-#include <asm/percpu.h>
-
-DECLARE_PER_CPU(struct pt_regs *, irq_regs);
-
-static inline struct pt_regs *get_irq_regs(void)
-{
-	return x86_read_percpu(irq_regs);
-}
-
-static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
-{
-	struct pt_regs *old_regs;
-
-	old_regs = get_irq_regs();
-	x86_write_percpu(irq_regs, new_regs);
-
-	return old_regs;
-}
-
-#endif /* ASM_X86__IRQ_REGS_32_H */
diff --git a/include/asm-x86/irq_regs_64.h b/include/asm-x86/irq_regs_64.h
deleted file mode 100644
index 3dd9c0b70270..000000000000
--- a/include/asm-x86/irq_regs_64.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/irq_regs.h>
diff --git a/include/asm-x86/irq_remapping.h b/include/asm-x86/irq_remapping.h
deleted file mode 100644
index 78242c6ffa58..000000000000
--- a/include/asm-x86/irq_remapping.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _ASM_IRQ_REMAPPING_H
-#define _ASM_IRQ_REMAPPING_H
-
-extern int x2apic;
-
-#define IRTE_DEST(dest) ((x2apic) ? dest : dest << 8)
-
-#endif
diff --git a/include/asm-x86/irq_vectors.h b/include/asm-x86/irq_vectors.h
deleted file mode 100644
index a8d065d85f57..000000000000
--- a/include/asm-x86/irq_vectors.h
+++ /dev/null
@@ -1,164 +0,0 @@
-#ifndef ASM_X86__IRQ_VECTORS_H
-#define ASM_X86__IRQ_VECTORS_H
-
-#include <linux/threads.h>
-
-#define NMI_VECTOR		0x02
-
-/*
- * IDT vectors usable for external interrupt sources start
- * at 0x20:
- */
-#define FIRST_EXTERNAL_VECTOR	0x20
-
-#ifdef CONFIG_X86_32
-# define SYSCALL_VECTOR		0x80
-#else
-# define IA32_SYSCALL_VECTOR	0x80
-#endif
-
-/*
- * Reserve the lowest usable priority level 0x20 - 0x2f for triggering
- * cleanup after irq migration.
- */
-#define IRQ_MOVE_CLEANUP_VECTOR	FIRST_EXTERNAL_VECTOR
-
-/*
- * Vectors 0x30-0x3f are used for ISA interrupts.
- */
-#define IRQ0_VECTOR		(FIRST_EXTERNAL_VECTOR + 0x10)
-#define IRQ1_VECTOR		(IRQ0_VECTOR + 1)
-#define IRQ2_VECTOR		(IRQ0_VECTOR + 2)
-#define IRQ3_VECTOR		(IRQ0_VECTOR + 3)
-#define IRQ4_VECTOR		(IRQ0_VECTOR + 4)
-#define IRQ5_VECTOR		(IRQ0_VECTOR + 5)
-#define IRQ6_VECTOR		(IRQ0_VECTOR + 6)
-#define IRQ7_VECTOR		(IRQ0_VECTOR + 7)
-#define IRQ8_VECTOR		(IRQ0_VECTOR + 8)
-#define IRQ9_VECTOR		(IRQ0_VECTOR + 9)
-#define IRQ10_VECTOR		(IRQ0_VECTOR + 10)
-#define IRQ11_VECTOR		(IRQ0_VECTOR + 11)
-#define IRQ12_VECTOR		(IRQ0_VECTOR + 12)
-#define IRQ13_VECTOR		(IRQ0_VECTOR + 13)
-#define IRQ14_VECTOR		(IRQ0_VECTOR + 14)
-#define IRQ15_VECTOR		(IRQ0_VECTOR + 15)
-
-/*
- * Special IRQ vectors used by the SMP architecture, 0xf0-0xff
- *
- *  some of the following vectors are 'rare', they are merged
- *  into a single vector (CALL_FUNCTION_VECTOR) to save vector space.
- *  TLB, reschedule and local APIC vectors are performance-critical.
- *
- *  Vectors 0xf0-0xfa are free (reserved for future Linux use).
- */
-#ifdef CONFIG_X86_32
-
-# define SPURIOUS_APIC_VECTOR		0xff
-# define ERROR_APIC_VECTOR		0xfe
-# define INVALIDATE_TLB_VECTOR		0xfd
-# define RESCHEDULE_VECTOR		0xfc
-# define CALL_FUNCTION_VECTOR		0xfb
-# define CALL_FUNCTION_SINGLE_VECTOR	0xfa
-# define THERMAL_APIC_VECTOR		0xf0
-
-#else
-
-#define SPURIOUS_APIC_VECTOR		0xff
-#define ERROR_APIC_VECTOR		0xfe
-#define RESCHEDULE_VECTOR		0xfd
-#define CALL_FUNCTION_VECTOR		0xfc
-#define CALL_FUNCTION_SINGLE_VECTOR	0xfb
-#define THERMAL_APIC_VECTOR		0xfa
-#define THRESHOLD_APIC_VECTOR		0xf9
-#define UV_BAU_MESSAGE			0xf8
-#define INVALIDATE_TLB_VECTOR_END	0xf7
-#define INVALIDATE_TLB_VECTOR_START	0xf0	/* f0-f7 used for TLB flush */
-
-#define NUM_INVALIDATE_TLB_VECTORS	8
-
-#endif
-
-/*
- * Local APIC timer IRQ vector is on a different priority level,
- * to work around the 'lost local interrupt if more than 2 IRQ
- * sources per level' errata.
- */
-#define LOCAL_TIMER_VECTOR	0xef
-
-/*
- * First APIC vector available to drivers: (vectors 0x30-0xee) we
- * start at 0x31(0x41) to spread out vectors evenly between priority
- * levels. (0x80 is the syscall vector)
- */
-#define FIRST_DEVICE_VECTOR	(IRQ15_VECTOR + 2)
-
-#define NR_VECTORS		256
-
-#define FPU_IRQ			13
-
-#define	FIRST_VM86_IRQ		3
-#define LAST_VM86_IRQ		15
-#define invalid_vm86_irq(irq)	((irq) < 3 || (irq) > 15)
-
-#ifdef CONFIG_X86_64
-# if NR_CPUS < MAX_IO_APICS
-#  define NR_IRQS (NR_VECTORS + (32 * NR_CPUS))
-# else
-#  define NR_IRQS (NR_VECTORS + (32 * MAX_IO_APICS))
-# endif
-
-#elif !defined(CONFIG_X86_VOYAGER)
-
-# if defined(CONFIG_X86_IO_APIC) || defined(CONFIG_PARAVIRT) || defined(CONFIG_X86_VISWS)
-
-#  define NR_IRQS		224
-
-# else /* IO_APIC || PARAVIRT */
-
-#  define NR_IRQS		16
-
-# endif
-
-#else /* !VISWS && !VOYAGER */
-
-# define NR_IRQS		224
-
-#endif /* VISWS */
-
-/* Voyager specific defines */
-/* These define the CPIs we use in linux */
-#define VIC_CPI_LEVEL0			0
-#define VIC_CPI_LEVEL1			1
-/* now the fake CPIs */
-#define VIC_TIMER_CPI			2
-#define VIC_INVALIDATE_CPI		3
-#define VIC_RESCHEDULE_CPI		4
-#define VIC_ENABLE_IRQ_CPI		5
-#define VIC_CALL_FUNCTION_CPI		6
-#define VIC_CALL_FUNCTION_SINGLE_CPI	7
-
-/* Now the QIC CPIs:  Since we don't need the two initial levels,
- * these are 2 less than the VIC CPIs */
-#define QIC_CPI_OFFSET			1
-#define QIC_TIMER_CPI			(VIC_TIMER_CPI - QIC_CPI_OFFSET)
-#define QIC_INVALIDATE_CPI		(VIC_INVALIDATE_CPI - QIC_CPI_OFFSET)
-#define QIC_RESCHEDULE_CPI		(VIC_RESCHEDULE_CPI - QIC_CPI_OFFSET)
-#define QIC_ENABLE_IRQ_CPI		(VIC_ENABLE_IRQ_CPI - QIC_CPI_OFFSET)
-#define QIC_CALL_FUNCTION_CPI		(VIC_CALL_FUNCTION_CPI - QIC_CPI_OFFSET)
-#define QIC_CALL_FUNCTION_SINGLE_CPI	(VIC_CALL_FUNCTION_SINGLE_CPI - QIC_CPI_OFFSET)
-
-#define VIC_START_FAKE_CPI		VIC_TIMER_CPI
-#define VIC_END_FAKE_CPI		VIC_CALL_FUNCTION_SINGLE_CPI
-
-/* this is the SYS_INT CPI. */
-#define VIC_SYS_INT			8
-#define VIC_CMN_INT			15
-
-/* This is the boot CPI for alternate processors.  It gets overwritten
- * by the above once the system has activated all available processors */
-#define VIC_CPU_BOOT_CPI		VIC_CPI_LEVEL0
-#define VIC_CPU_BOOT_ERRATA_CPI		(VIC_CPI_LEVEL0 + 8)
-
-
-#endif /* ASM_X86__IRQ_VECTORS_H */
diff --git a/include/asm-x86/irqflags.h b/include/asm-x86/irqflags.h
deleted file mode 100644
index 2bdab21f0898..000000000000
--- a/include/asm-x86/irqflags.h
+++ /dev/null
@@ -1,211 +0,0 @@
-#ifndef _X86_IRQFLAGS_H_
-#define _X86_IRQFLAGS_H_
-
-#include <asm/processor-flags.h>
-
-#ifndef __ASSEMBLY__
-/*
- * Interrupt control:
- */
-
-static inline unsigned long native_save_fl(void)
-{
-	unsigned long flags;
-
-	asm volatile("# __raw_save_flags\n\t"
-		     "pushf ; pop %0"
-		     : "=g" (flags)
-		     : /* no input */
-		     : "memory");
-
-	return flags;
-}
-
-static inline void native_restore_fl(unsigned long flags)
-{
-	asm volatile("push %0 ; popf"
-		     : /* no output */
-		     :"g" (flags)
-		     :"memory", "cc");
-}
-
-static inline void native_irq_disable(void)
-{
-	asm volatile("cli": : :"memory");
-}
-
-static inline void native_irq_enable(void)
-{
-	asm volatile("sti": : :"memory");
-}
-
-static inline void native_safe_halt(void)
-{
-	asm volatile("sti; hlt": : :"memory");
-}
-
-static inline void native_halt(void)
-{
-	asm volatile("hlt": : :"memory");
-}
-
-#endif
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-#ifndef __ASSEMBLY__
-
-static inline unsigned long __raw_local_save_flags(void)
-{
-	return native_save_fl();
-}
-
-static inline void raw_local_irq_restore(unsigned long flags)
-{
-	native_restore_fl(flags);
-}
-
-static inline void raw_local_irq_disable(void)
-{
-	native_irq_disable();
-}
-
-static inline void raw_local_irq_enable(void)
-{
-	native_irq_enable();
-}
-
-/*
- * Used in the idle loop; sti takes one instruction cycle
- * to complete:
- */
-static inline void raw_safe_halt(void)
-{
-	native_safe_halt();
-}
-
-/*
- * Used when interrupts are already enabled or to
- * shutdown the processor:
- */
-static inline void halt(void)
-{
-	native_halt();
-}
-
-/*
- * For spinlocks, etc:
- */
-static inline unsigned long __raw_local_irq_save(void)
-{
-	unsigned long flags = __raw_local_save_flags();
-
-	raw_local_irq_disable();
-
-	return flags;
-}
-#else
-
-#define ENABLE_INTERRUPTS(x)	sti
-#define DISABLE_INTERRUPTS(x)	cli
-
-#ifdef CONFIG_X86_64
-#define SWAPGS	swapgs
-/*
- * Currently paravirt can't handle swapgs nicely when we
- * don't have a stack we can rely on (such as a user space
- * stack).  So we either find a way around these or just fault
- * and emulate if a guest tries to call swapgs directly.
- *
- * Either way, this is a good way to document that we don't
- * have a reliable stack. x86_64 only.
- */
-#define SWAPGS_UNSAFE_STACK	swapgs
-
-#define PARAVIRT_ADJUST_EXCEPTION_FRAME	/*  */
-
-#define INTERRUPT_RETURN	iretq
-#define USERGS_SYSRET64				\
-	swapgs;					\
-	sysretq;
-#define USERGS_SYSRET32				\
-	swapgs;					\
-	sysretl
-#define ENABLE_INTERRUPTS_SYSEXIT32		\
-	swapgs;					\
-	sti;					\
-	sysexit
-
-#else
-#define INTERRUPT_RETURN		iret
-#define ENABLE_INTERRUPTS_SYSEXIT	sti; sysexit
-#define GET_CR0_INTO_EAX		movl %cr0, %eax
-#endif
-
-
-#endif /* __ASSEMBLY__ */
-#endif /* CONFIG_PARAVIRT */
-
-#ifndef __ASSEMBLY__
-#define raw_local_save_flags(flags)				\
-	do { (flags) = __raw_local_save_flags(); } while (0)
-
-#define raw_local_irq_save(flags)				\
-	do { (flags) = __raw_local_irq_save(); } while (0)
-
-static inline int raw_irqs_disabled_flags(unsigned long flags)
-{
-	return !(flags & X86_EFLAGS_IF);
-}
-
-static inline int raw_irqs_disabled(void)
-{
-	unsigned long flags = __raw_local_save_flags();
-
-	return raw_irqs_disabled_flags(flags);
-}
-
-#else
-
-#ifdef CONFIG_X86_64
-#define ARCH_LOCKDEP_SYS_EXIT		call lockdep_sys_exit_thunk
-#define ARCH_LOCKDEP_SYS_EXIT_IRQ	\
-	TRACE_IRQS_ON; \
-	sti; \
-	SAVE_REST; \
-	LOCKDEP_SYS_EXIT; \
-	RESTORE_REST; \
-	cli; \
-	TRACE_IRQS_OFF;
-
-#else
-#define ARCH_LOCKDEP_SYS_EXIT			\
-	pushl %eax;				\
-	pushl %ecx;				\
-	pushl %edx;				\
-	call lockdep_sys_exit;			\
-	popl %edx;				\
-	popl %ecx;				\
-	popl %eax;
-
-#define ARCH_LOCKDEP_SYS_EXIT_IRQ
-#endif
-
-#ifdef CONFIG_TRACE_IRQFLAGS
-#  define TRACE_IRQS_ON		call trace_hardirqs_on_thunk;
-#  define TRACE_IRQS_OFF	call trace_hardirqs_off_thunk;
-#else
-#  define TRACE_IRQS_ON
-#  define TRACE_IRQS_OFF
-#endif
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-#  define LOCKDEP_SYS_EXIT	ARCH_LOCKDEP_SYS_EXIT
-#  define LOCKDEP_SYS_EXIT_IRQ	ARCH_LOCKDEP_SYS_EXIT_IRQ
-# else
-#  define LOCKDEP_SYS_EXIT
-#  define LOCKDEP_SYS_EXIT_IRQ
-# endif
-
-#endif /* __ASSEMBLY__ */
-#endif
diff --git a/include/asm-x86/ist.h b/include/asm-x86/ist.h
deleted file mode 100644
index 35a2fe9bc921..000000000000
--- a/include/asm-x86/ist.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef ASM_X86__IST_H
-#define ASM_X86__IST_H
-
-/*
- * Include file for the interface to IST BIOS
- * Copyright 2002 Andy Grover <andrew.grover@intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2, or (at your option) any
- * later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- */
-
-
-#include <linux/types.h>
-
-struct ist_info {
-	__u32 signature;
-	__u32 command;
-	__u32 event;
-	__u32 perf_level;
-};
-
-#ifdef __KERNEL__
-
-extern struct ist_info ist_info;
-
-#endif	/* __KERNEL__ */
-#endif /* ASM_X86__IST_H */
diff --git a/include/asm-x86/k8.h b/include/asm-x86/k8.h
deleted file mode 100644
index 2bbaf4370a55..000000000000
--- a/include/asm-x86/k8.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef ASM_X86__K8_H
-#define ASM_X86__K8_H
-
-#include <linux/pci.h>
-
-extern struct pci_device_id k8_nb_ids[];
-
-extern int early_is_k8_nb(u32 value);
-extern struct pci_dev **k8_northbridges;
-extern int num_k8_northbridges;
-extern int cache_k8_northbridges(void);
-extern void k8_flush_garts(void);
-extern int k8_scan_nodes(unsigned long start, unsigned long end);
-
-#endif /* ASM_X86__K8_H */
diff --git a/include/asm-x86/kdebug.h b/include/asm-x86/kdebug.h
deleted file mode 100644
index fbbab66ee9df..000000000000
--- a/include/asm-x86/kdebug.h
+++ /dev/null
@@ -1,37 +0,0 @@
-#ifndef ASM_X86__KDEBUG_H
-#define ASM_X86__KDEBUG_H
-
-#include <linux/notifier.h>
-
-struct pt_regs;
-
-/* Grossly misnamed. */
-enum die_val {
-	DIE_OOPS = 1,
-	DIE_INT3,
-	DIE_DEBUG,
-	DIE_PANIC,
-	DIE_NMI,
-	DIE_DIE,
-	DIE_NMIWATCHDOG,
-	DIE_KERNELDEBUG,
-	DIE_TRAP,
-	DIE_GPF,
-	DIE_CALL,
-	DIE_NMI_IPI,
-	DIE_PAGE_FAULT,
-	DIE_NMIUNKNOWN,
-};
-
-extern void printk_address(unsigned long address, int reliable);
-extern void die(const char *, struct pt_regs *,long);
-extern int __must_check __die(const char *, struct pt_regs *, long);
-extern void show_registers(struct pt_regs *regs);
-extern void show_trace(struct task_struct *t, struct pt_regs *regs,
-		       unsigned long *sp, unsigned long bp);
-extern void __show_regs(struct pt_regs *regs, int all);
-extern void show_regs(struct pt_regs *regs);
-extern unsigned long oops_begin(void);
-extern void oops_end(unsigned long, struct pt_regs *, int signr);
-
-#endif /* ASM_X86__KDEBUG_H */
diff --git a/include/asm-x86/kexec.h b/include/asm-x86/kexec.h
deleted file mode 100644
index ea09600d6129..000000000000
--- a/include/asm-x86/kexec.h
+++ /dev/null
@@ -1,175 +0,0 @@
-#ifndef ASM_X86__KEXEC_H
-#define ASM_X86__KEXEC_H
-
-#ifdef CONFIG_X86_32
-# define PA_CONTROL_PAGE	0
-# define VA_CONTROL_PAGE	1
-# define PA_PGD			2
-# define VA_PGD			3
-# define PA_PTE_0		4
-# define VA_PTE_0		5
-# define PA_PTE_1		6
-# define VA_PTE_1		7
-# define PA_SWAP_PAGE		8
-# ifdef CONFIG_X86_PAE
-#  define PA_PMD_0		9
-#  define VA_PMD_0		10
-#  define PA_PMD_1		11
-#  define VA_PMD_1		12
-#  define PAGES_NR		13
-# else
-#  define PAGES_NR		9
-# endif
-#else
-# define PA_CONTROL_PAGE	0
-# define VA_CONTROL_PAGE	1
-# define PA_PGD			2
-# define VA_PGD			3
-# define PA_PUD_0		4
-# define VA_PUD_0		5
-# define PA_PMD_0		6
-# define VA_PMD_0		7
-# define PA_PTE_0		8
-# define VA_PTE_0		9
-# define PA_PUD_1		10
-# define VA_PUD_1		11
-# define PA_PMD_1		12
-# define VA_PMD_1		13
-# define PA_PTE_1		14
-# define VA_PTE_1		15
-# define PA_TABLE_PAGE		16
-# define PAGES_NR		17
-#endif
-
-#ifdef CONFIG_X86_32
-# define KEXEC_CONTROL_CODE_MAX_SIZE	2048
-#endif
-
-#ifndef __ASSEMBLY__
-
-#include <linux/string.h>
-
-#include <asm/page.h>
-#include <asm/ptrace.h>
-
-/*
- * KEXEC_SOURCE_MEMORY_LIMIT maximum page get_free_page can return.
- * I.e. Maximum page that is mapped directly into kernel memory,
- * and kmap is not required.
- *
- * So far x86_64 is limited to 40 physical address bits.
- */
-#ifdef CONFIG_X86_32
-/* Maximum physical address we can use pages from */
-# define KEXEC_SOURCE_MEMORY_LIMIT (-1UL)
-/* Maximum address we can reach in physical address mode */
-# define KEXEC_DESTINATION_MEMORY_LIMIT (-1UL)
-/* Maximum address we can use for the control code buffer */
-# define KEXEC_CONTROL_MEMORY_LIMIT TASK_SIZE
-
-# define KEXEC_CONTROL_PAGE_SIZE	4096
-
-/* The native architecture */
-# define KEXEC_ARCH KEXEC_ARCH_386
-
-/* We can also handle crash dumps from 64 bit kernel. */
-# define vmcore_elf_check_arch_cross(x) ((x)->e_machine == EM_X86_64)
-#else
-/* Maximum physical address we can use pages from */
-# define KEXEC_SOURCE_MEMORY_LIMIT      (0xFFFFFFFFFFUL)
-/* Maximum address we can reach in physical address mode */
-# define KEXEC_DESTINATION_MEMORY_LIMIT (0xFFFFFFFFFFUL)
-/* Maximum address we can use for the control pages */
-# define KEXEC_CONTROL_MEMORY_LIMIT     (0xFFFFFFFFFFUL)
-
-/* Allocate one page for the pdp and the second for the code */
-# define KEXEC_CONTROL_PAGE_SIZE  (4096UL + 4096UL)
-
-/* The native architecture */
-# define KEXEC_ARCH KEXEC_ARCH_X86_64
-#endif
-
-/*
- * CPU does not save ss and sp on stack if execution is already
- * running in kernel mode at the time of NMI occurrence. This code
- * fixes it.
- */
-static inline void crash_fixup_ss_esp(struct pt_regs *newregs,
-				      struct pt_regs *oldregs)
-{
-#ifdef CONFIG_X86_32
-	newregs->sp = (unsigned long)&(oldregs->sp);
-	asm volatile("xorl %%eax, %%eax\n\t"
-		     "movw %%ss, %%ax\n\t"
-		     :"=a"(newregs->ss));
-#endif
-}
-
-/*
- * This function is responsible for capturing register states if coming
- * via panic otherwise just fix up the ss and sp if coming via kernel
- * mode exception.
- */
-static inline void crash_setup_regs(struct pt_regs *newregs,
-				    struct pt_regs *oldregs)
-{
-	if (oldregs) {
-		memcpy(newregs, oldregs, sizeof(*newregs));
-		crash_fixup_ss_esp(newregs, oldregs);
-	} else {
-#ifdef CONFIG_X86_32
-		asm volatile("movl %%ebx,%0" : "=m"(newregs->bx));
-		asm volatile("movl %%ecx,%0" : "=m"(newregs->cx));
-		asm volatile("movl %%edx,%0" : "=m"(newregs->dx));
-		asm volatile("movl %%esi,%0" : "=m"(newregs->si));
-		asm volatile("movl %%edi,%0" : "=m"(newregs->di));
-		asm volatile("movl %%ebp,%0" : "=m"(newregs->bp));
-		asm volatile("movl %%eax,%0" : "=m"(newregs->ax));
-		asm volatile("movl %%esp,%0" : "=m"(newregs->sp));
-		asm volatile("movl %%ss, %%eax;" :"=a"(newregs->ss));
-		asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs));
-		asm volatile("movl %%ds, %%eax;" :"=a"(newregs->ds));
-		asm volatile("movl %%es, %%eax;" :"=a"(newregs->es));
-		asm volatile("pushfl; popl %0" :"=m"(newregs->flags));
-#else
-		asm volatile("movq %%rbx,%0" : "=m"(newregs->bx));
-		asm volatile("movq %%rcx,%0" : "=m"(newregs->cx));
-		asm volatile("movq %%rdx,%0" : "=m"(newregs->dx));
-		asm volatile("movq %%rsi,%0" : "=m"(newregs->si));
-		asm volatile("movq %%rdi,%0" : "=m"(newregs->di));
-		asm volatile("movq %%rbp,%0" : "=m"(newregs->bp));
-		asm volatile("movq %%rax,%0" : "=m"(newregs->ax));
-		asm volatile("movq %%rsp,%0" : "=m"(newregs->sp));
-		asm volatile("movq %%r8,%0" : "=m"(newregs->r8));
-		asm volatile("movq %%r9,%0" : "=m"(newregs->r9));
-		asm volatile("movq %%r10,%0" : "=m"(newregs->r10));
-		asm volatile("movq %%r11,%0" : "=m"(newregs->r11));
-		asm volatile("movq %%r12,%0" : "=m"(newregs->r12));
-		asm volatile("movq %%r13,%0" : "=m"(newregs->r13));
-		asm volatile("movq %%r14,%0" : "=m"(newregs->r14));
-		asm volatile("movq %%r15,%0" : "=m"(newregs->r15));
-		asm volatile("movl %%ss, %%eax;" :"=a"(newregs->ss));
-		asm volatile("movl %%cs, %%eax;" :"=a"(newregs->cs));
-		asm volatile("pushfq; popq %0" :"=m"(newregs->flags));
-#endif
-		newregs->ip = (unsigned long)current_text_addr();
-	}
-}
-
-#ifdef CONFIG_X86_32
-asmlinkage unsigned long
-relocate_kernel(unsigned long indirection_page,
-		unsigned long control_page,
-		unsigned long start_address,
-		unsigned int has_pae,
-		unsigned int preserve_context);
-#else
-NORET_TYPE void
-relocate_kernel(unsigned long indirection_page,
-		unsigned long page_list,
-		unsigned long start_address) ATTRIB_NORET;
-#endif
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* ASM_X86__KEXEC_H */
diff --git a/include/asm-x86/kgdb.h b/include/asm-x86/kgdb.h
deleted file mode 100644
index d283863354de..000000000000
--- a/include/asm-x86/kgdb.h
+++ /dev/null
@@ -1,79 +0,0 @@
-#ifndef ASM_X86__KGDB_H
-#define ASM_X86__KGDB_H
-
-/*
- * Copyright (C) 2001-2004 Amit S. Kale
- * Copyright (C) 2008 Wind River Systems, Inc.
- */
-
-/*
- * BUFMAX defines the maximum number of characters in inbound/outbound
- * buffers at least NUMREGBYTES*2 are needed for register packets
- * Longer buffer is needed to list all threads
- */
-#define BUFMAX			1024
-
-/*
- *  Note that this register image is in a different order than
- *  the register image that Linux produces at interrupt time.
- *
- *  Linux's register image is defined by struct pt_regs in ptrace.h.
- *  Just why GDB uses a different order is a historical mystery.
- */
-#ifdef CONFIG_X86_32
-enum regnames {
-	GDB_AX,			/* 0 */
-	GDB_CX,			/* 1 */
-	GDB_DX,			/* 2 */
-	GDB_BX,			/* 3 */
-	GDB_SP,			/* 4 */
-	GDB_BP,			/* 5 */
-	GDB_SI,			/* 6 */
-	GDB_DI,			/* 7 */
-	GDB_PC,			/* 8 also known as eip */
-	GDB_PS,			/* 9 also known as eflags */
-	GDB_CS,			/* 10 */
-	GDB_SS,			/* 11 */
-	GDB_DS,			/* 12 */
-	GDB_ES,			/* 13 */
-	GDB_FS,			/* 14 */
-	GDB_GS,			/* 15 */
-};
-#define NUMREGBYTES		((GDB_GS+1)*4)
-#else /* ! CONFIG_X86_32 */
-enum regnames64 {
-	GDB_AX,			/* 0 */
-	GDB_BX,			/* 1 */
-	GDB_CX,			/* 2 */
-	GDB_DX,			/* 3 */
-	GDB_SI,			/* 4 */
-	GDB_DI,			/* 5 */
-	GDB_BP,			/* 6 */
-	GDB_SP,			/* 7 */
-	GDB_R8,			/* 8 */
-	GDB_R9,			/* 9 */
-	GDB_R10,		/* 10 */
-	GDB_R11,		/* 11 */
-	GDB_R12,		/* 12 */
-	GDB_R13,		/* 13 */
-	GDB_R14,		/* 14 */
-	GDB_R15,		/* 15 */
-	GDB_PC,			/* 16 */
-};
-
-enum regnames32 {
-	GDB_PS = 34,
-	GDB_CS,
-	GDB_SS,
-};
-#define NUMREGBYTES		((GDB_SS+1)*4)
-#endif /* CONFIG_X86_32 */
-
-static inline void arch_kgdb_breakpoint(void)
-{
-	asm("   int $3");
-}
-#define BREAK_INSTR_SIZE	1
-#define CACHE_FLUSH_IS_SAFE	1
-
-#endif /* ASM_X86__KGDB_H */
diff --git a/include/asm-x86/kmap_types.h b/include/asm-x86/kmap_types.h
deleted file mode 100644
index 89f44493e643..000000000000
--- a/include/asm-x86/kmap_types.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef ASM_X86__KMAP_TYPES_H
-#define ASM_X86__KMAP_TYPES_H
-
-#if defined(CONFIG_X86_32) && defined(CONFIG_DEBUG_HIGHMEM)
-# define D(n) __KM_FENCE_##n ,
-#else
-# define D(n)
-#endif
-
-enum km_type {
-D(0)	KM_BOUNCE_READ,
-D(1)	KM_SKB_SUNRPC_DATA,
-D(2)	KM_SKB_DATA_SOFTIRQ,
-D(3)	KM_USER0,
-D(4)	KM_USER1,
-D(5)	KM_BIO_SRC_IRQ,
-D(6)	KM_BIO_DST_IRQ,
-D(7)	KM_PTE0,
-D(8)	KM_PTE1,
-D(9)	KM_IRQ0,
-D(10)	KM_IRQ1,
-D(11)	KM_SOFTIRQ0,
-D(12)	KM_SOFTIRQ1,
-D(13)	KM_TYPE_NR
-};
-
-#undef D
-
-#endif /* ASM_X86__KMAP_TYPES_H */
diff --git a/include/asm-x86/kprobes.h b/include/asm-x86/kprobes.h
deleted file mode 100644
index 8a0748d01036..000000000000
--- a/include/asm-x86/kprobes.h
+++ /dev/null
@@ -1,88 +0,0 @@
-#ifndef ASM_X86__KPROBES_H
-#define ASM_X86__KPROBES_H
-/*
- *  Kernel Probes (KProbes)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) IBM Corporation, 2002, 2004
- *
- * See arch/x86/kernel/kprobes.c for x86 kprobes history.
- */
-#include <linux/types.h>
-#include <linux/ptrace.h>
-#include <linux/percpu.h>
-
-#define  __ARCH_WANT_KPROBES_INSN_SLOT
-
-struct pt_regs;
-struct kprobe;
-
-typedef u8 kprobe_opcode_t;
-#define BREAKPOINT_INSTRUCTION	0xcc
-#define RELATIVEJUMP_INSTRUCTION 0xe9
-#define MAX_INSN_SIZE 16
-#define MAX_STACK_SIZE 64
-#define MIN_STACK_SIZE(ADDR)					       \
-	(((MAX_STACK_SIZE) < (((unsigned long)current_thread_info()) + \
-			      THREAD_SIZE - (unsigned long)(ADDR)))    \
-	 ? (MAX_STACK_SIZE)					       \
-	 : (((unsigned long)current_thread_info()) +		       \
-	    THREAD_SIZE - (unsigned long)(ADDR)))
-
-#define flush_insn_slot(p)	do { } while (0)
-
-extern const int kretprobe_blacklist_size;
-
-void arch_remove_kprobe(struct kprobe *p);
-void kretprobe_trampoline(void);
-
-/* Architecture specific copy of original instruction*/
-struct arch_specific_insn {
-	/* copy of the original instruction */
-	kprobe_opcode_t *insn;
-	/*
-	 * boostable = -1: This instruction type is not boostable.
-	 * boostable = 0: This instruction type is boostable.
-	 * boostable = 1: This instruction has been boosted: we have
-	 * added a relative jump after the instruction copy in insn,
-	 * so no single-step and fixup are needed (unless there's
-	 * a post_handler or break_handler).
-	 */
-	int boostable;
-};
-
-struct prev_kprobe {
-	struct kprobe *kp;
-	unsigned long status;
-	unsigned long old_flags;
-	unsigned long saved_flags;
-};
-
-/* per-cpu kprobe control block */
-struct kprobe_ctlblk {
-	unsigned long kprobe_status;
-	unsigned long kprobe_old_flags;
-	unsigned long kprobe_saved_flags;
-	unsigned long *jprobe_saved_sp;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
-	struct prev_kprobe prev_kprobe;
-};
-
-extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
-extern int kprobe_exceptions_notify(struct notifier_block *self,
-				    unsigned long val, void *data);
-#endif /* ASM_X86__KPROBES_H */
diff --git a/include/asm-x86/kvm.h b/include/asm-x86/kvm.h
deleted file mode 100644
index ba0dd791fadf..000000000000
--- a/include/asm-x86/kvm.h
+++ /dev/null
@@ -1,211 +0,0 @@
-#ifndef ASM_X86__KVM_H
-#define ASM_X86__KVM_H
-
-/*
- * KVM x86 specific structures and definitions
- *
- */
-
-#include <asm/types.h>
-#include <linux/ioctl.h>
-
-/* Architectural interrupt line count. */
-#define KVM_NR_INTERRUPTS 256
-
-struct kvm_memory_alias {
-	__u32 slot;  /* this has a different namespace than memory slots */
-	__u32 flags;
-	__u64 guest_phys_addr;
-	__u64 memory_size;
-	__u64 target_phys_addr;
-};
-
-/* for KVM_GET_IRQCHIP and KVM_SET_IRQCHIP */
-struct kvm_pic_state {
-	__u8 last_irr;	/* edge detection */
-	__u8 irr;		/* interrupt request register */
-	__u8 imr;		/* interrupt mask register */
-	__u8 isr;		/* interrupt service register */
-	__u8 priority_add;	/* highest irq priority */
-	__u8 irq_base;
-	__u8 read_reg_select;
-	__u8 poll;
-	__u8 special_mask;
-	__u8 init_state;
-	__u8 auto_eoi;
-	__u8 rotate_on_auto_eoi;
-	__u8 special_fully_nested_mode;
-	__u8 init4;		/* true if 4 byte init */
-	__u8 elcr;		/* PIIX edge/trigger selection */
-	__u8 elcr_mask;
-};
-
-#define KVM_IOAPIC_NUM_PINS  24
-struct kvm_ioapic_state {
-	__u64 base_address;
-	__u32 ioregsel;
-	__u32 id;
-	__u32 irr;
-	__u32 pad;
-	union {
-		__u64 bits;
-		struct {
-			__u8 vector;
-			__u8 delivery_mode:3;
-			__u8 dest_mode:1;
-			__u8 delivery_status:1;
-			__u8 polarity:1;
-			__u8 remote_irr:1;
-			__u8 trig_mode:1;
-			__u8 mask:1;
-			__u8 reserve:7;
-			__u8 reserved[4];
-			__u8 dest_id;
-		} fields;
-	} redirtbl[KVM_IOAPIC_NUM_PINS];
-};
-
-#define KVM_IRQCHIP_PIC_MASTER   0
-#define KVM_IRQCHIP_PIC_SLAVE    1
-#define KVM_IRQCHIP_IOAPIC       2
-
-/* for KVM_GET_REGS and KVM_SET_REGS */
-struct kvm_regs {
-	/* out (KVM_GET_REGS) / in (KVM_SET_REGS) */
-	__u64 rax, rbx, rcx, rdx;
-	__u64 rsi, rdi, rsp, rbp;
-	__u64 r8,  r9,  r10, r11;
-	__u64 r12, r13, r14, r15;
-	__u64 rip, rflags;
-};
-
-/* for KVM_GET_LAPIC and KVM_SET_LAPIC */
-#define KVM_APIC_REG_SIZE 0x400
-struct kvm_lapic_state {
-	char regs[KVM_APIC_REG_SIZE];
-};
-
-struct kvm_segment {
-	__u64 base;
-	__u32 limit;
-	__u16 selector;
-	__u8  type;
-	__u8  present, dpl, db, s, l, g, avl;
-	__u8  unusable;
-	__u8  padding;
-};
-
-struct kvm_dtable {
-	__u64 base;
-	__u16 limit;
-	__u16 padding[3];
-};
-
-
-/* for KVM_GET_SREGS and KVM_SET_SREGS */
-struct kvm_sregs {
-	/* out (KVM_GET_SREGS) / in (KVM_SET_SREGS) */
-	struct kvm_segment cs, ds, es, fs, gs, ss;
-	struct kvm_segment tr, ldt;
-	struct kvm_dtable gdt, idt;
-	__u64 cr0, cr2, cr3, cr4, cr8;
-	__u64 efer;
-	__u64 apic_base;
-	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
-};
-
-/* for KVM_GET_FPU and KVM_SET_FPU */
-struct kvm_fpu {
-	__u8  fpr[8][16];
-	__u16 fcw;
-	__u16 fsw;
-	__u8  ftwx;  /* in fxsave format */
-	__u8  pad1;
-	__u16 last_opcode;
-	__u64 last_ip;
-	__u64 last_dp;
-	__u8  xmm[16][16];
-	__u32 mxcsr;
-	__u32 pad2;
-};
-
-struct kvm_msr_entry {
-	__u32 index;
-	__u32 reserved;
-	__u64 data;
-};
-
-/* for KVM_GET_MSRS and KVM_SET_MSRS */
-struct kvm_msrs {
-	__u32 nmsrs; /* number of msrs in entries */
-	__u32 pad;
-
-	struct kvm_msr_entry entries[0];
-};
-
-/* for KVM_GET_MSR_INDEX_LIST */
-struct kvm_msr_list {
-	__u32 nmsrs; /* number of msrs in entries */
-	__u32 indices[0];
-};
-
-
-struct kvm_cpuid_entry {
-	__u32 function;
-	__u32 eax;
-	__u32 ebx;
-	__u32 ecx;
-	__u32 edx;
-	__u32 padding;
-};
-
-/* for KVM_SET_CPUID */
-struct kvm_cpuid {
-	__u32 nent;
-	__u32 padding;
-	struct kvm_cpuid_entry entries[0];
-};
-
-struct kvm_cpuid_entry2 {
-	__u32 function;
-	__u32 index;
-	__u32 flags;
-	__u32 eax;
-	__u32 ebx;
-	__u32 ecx;
-	__u32 edx;
-	__u32 padding[3];
-};
-
-#define KVM_CPUID_FLAG_SIGNIFCANT_INDEX 1
-#define KVM_CPUID_FLAG_STATEFUL_FUNC    2
-#define KVM_CPUID_FLAG_STATE_READ_NEXT  4
-
-/* for KVM_SET_CPUID2 */
-struct kvm_cpuid2 {
-	__u32 nent;
-	__u32 padding;
-	struct kvm_cpuid_entry2 entries[0];
-};
-
-/* for KVM_GET_PIT and KVM_SET_PIT */
-struct kvm_pit_channel_state {
-	__u32 count; /* can be 65536 */
-	__u16 latched_count;
-	__u8 count_latched;
-	__u8 status_latched;
-	__u8 status;
-	__u8 read_state;
-	__u8 write_state;
-	__u8 write_latch;
-	__u8 rw_mode;
-	__u8 mode;
-	__u8 bcd;
-	__u8 gate;
-	__s64 count_load_time;
-};
-
-struct kvm_pit_state {
-	struct kvm_pit_channel_state channels[3];
-};
-#endif /* ASM_X86__KVM_H */
diff --git a/include/asm-x86/kvm_host.h b/include/asm-x86/kvm_host.h
deleted file mode 100644
index 411fb8cfb24e..000000000000
--- a/include/asm-x86/kvm_host.h
+++ /dev/null
@@ -1,752 +0,0 @@
-/*
- * Kernel-based Virtual Machine driver for Linux
- *
- * This header defines architecture specific interfaces, x86 version
- *
- * This work is licensed under the terms of the GNU GPL, version 2.  See
- * the COPYING file in the top-level directory.
- *
- */
-
-#ifndef ASM_X86__KVM_HOST_H
-#define ASM_X86__KVM_HOST_H
-
-#include <linux/types.h>
-#include <linux/mm.h>
-#include <linux/mmu_notifier.h>
-
-#include <linux/kvm.h>
-#include <linux/kvm_para.h>
-#include <linux/kvm_types.h>
-
-#include <asm/pvclock-abi.h>
-#include <asm/desc.h>
-
-#define KVM_MAX_VCPUS 16
-#define KVM_MEMORY_SLOTS 32
-/* memory slots that does not exposed to userspace */
-#define KVM_PRIVATE_MEM_SLOTS 4
-
-#define KVM_PIO_PAGE_OFFSET 1
-#define KVM_COALESCED_MMIO_PAGE_OFFSET 2
-
-#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
-#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
-#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |	\
-				  0xFFFFFF0000000000ULL)
-
-#define KVM_GUEST_CR0_MASK				   \
-	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \
-	 | X86_CR0_NW | X86_CR0_CD)
-#define KVM_VM_CR0_ALWAYS_ON						\
-	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
-	 | X86_CR0_MP)
-#define KVM_GUEST_CR4_MASK						\
-	(X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
-#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
-#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
-
-#define INVALID_PAGE (~(hpa_t)0)
-#define UNMAPPED_GVA (~(gpa_t)0)
-
-/* shadow tables are PAE even on non-PAE hosts */
-#define KVM_HPAGE_SHIFT 21
-#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT)
-#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1))
-
-#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE)
-
-#define DE_VECTOR 0
-#define DB_VECTOR 1
-#define BP_VECTOR 3
-#define OF_VECTOR 4
-#define BR_VECTOR 5
-#define UD_VECTOR 6
-#define NM_VECTOR 7
-#define DF_VECTOR 8
-#define TS_VECTOR 10
-#define NP_VECTOR 11
-#define SS_VECTOR 12
-#define GP_VECTOR 13
-#define PF_VECTOR 14
-#define MF_VECTOR 16
-#define MC_VECTOR 18
-
-#define SELECTOR_TI_MASK (1 << 2)
-#define SELECTOR_RPL_MASK 0x03
-
-#define IOPL_SHIFT 12
-
-#define KVM_ALIAS_SLOTS 4
-
-#define KVM_PERMILLE_MMU_PAGES 20
-#define KVM_MIN_ALLOC_MMU_PAGES 64
-#define KVM_MMU_HASH_SHIFT 10
-#define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
-#define KVM_MIN_FREE_MMU_PAGES 5
-#define KVM_REFILL_PAGES 25
-#define KVM_MAX_CPUID_ENTRIES 40
-#define KVM_NR_VAR_MTRR 8
-
-extern spinlock_t kvm_lock;
-extern struct list_head vm_list;
-
-struct kvm_vcpu;
-struct kvm;
-
-enum kvm_reg {
-	VCPU_REGS_RAX = 0,
-	VCPU_REGS_RCX = 1,
-	VCPU_REGS_RDX = 2,
-	VCPU_REGS_RBX = 3,
-	VCPU_REGS_RSP = 4,
-	VCPU_REGS_RBP = 5,
-	VCPU_REGS_RSI = 6,
-	VCPU_REGS_RDI = 7,
-#ifdef CONFIG_X86_64
-	VCPU_REGS_R8 = 8,
-	VCPU_REGS_R9 = 9,
-	VCPU_REGS_R10 = 10,
-	VCPU_REGS_R11 = 11,
-	VCPU_REGS_R12 = 12,
-	VCPU_REGS_R13 = 13,
-	VCPU_REGS_R14 = 14,
-	VCPU_REGS_R15 = 15,
-#endif
-	VCPU_REGS_RIP,
-	NR_VCPU_REGS
-};
-
-enum {
-	VCPU_SREG_ES,
-	VCPU_SREG_CS,
-	VCPU_SREG_SS,
-	VCPU_SREG_DS,
-	VCPU_SREG_FS,
-	VCPU_SREG_GS,
-	VCPU_SREG_TR,
-	VCPU_SREG_LDTR,
-};
-
-#include <asm/kvm_x86_emulate.h>
-
-#define KVM_NR_MEM_OBJS 40
-
-struct kvm_guest_debug {
-	int enabled;
-	unsigned long bp[4];
-	int singlestep;
-};
-
-/*
- * We don't want allocation failures within the mmu code, so we preallocate
- * enough memory for a single page fault in a cache.
- */
-struct kvm_mmu_memory_cache {
-	int nobjs;
-	void *objects[KVM_NR_MEM_OBJS];
-};
-
-#define NR_PTE_CHAIN_ENTRIES 5
-
-struct kvm_pte_chain {
-	u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES];
-	struct hlist_node link;
-};
-
-/*
- * kvm_mmu_page_role, below, is defined as:
- *
- *   bits 0:3 - total guest paging levels (2-4, or zero for real mode)
- *   bits 4:7 - page table level for this shadow (1-4)
- *   bits 8:9 - page table quadrant for 2-level guests
- *   bit   16 - "metaphysical" - gfn is not a real page (huge page/real mode)
- *   bits 17:19 - common access permissions for all ptes in this shadow page
- */
-union kvm_mmu_page_role {
-	unsigned word;
-	struct {
-		unsigned glevels:4;
-		unsigned level:4;
-		unsigned quadrant:2;
-		unsigned pad_for_nice_hex_output:6;
-		unsigned metaphysical:1;
-		unsigned access:3;
-		unsigned invalid:1;
-	};
-};
-
-struct kvm_mmu_page {
-	struct list_head link;
-	struct hlist_node hash_link;
-
-	/*
-	 * The following two entries are used to key the shadow page in the
-	 * hash table.
-	 */
-	gfn_t gfn;
-	union kvm_mmu_page_role role;
-
-	u64 *spt;
-	/* hold the gfn of each spte inside spt */
-	gfn_t *gfns;
-	unsigned long slot_bitmap; /* One bit set per slot which has memory
-				    * in this shadow page.
-				    */
-	int multimapped;         /* More than one parent_pte? */
-	int root_count;          /* Currently serving as active root */
-	bool unsync;
-	bool unsync_children;
-	union {
-		u64 *parent_pte;               /* !multimapped */
-		struct hlist_head parent_ptes; /* multimapped, kvm_pte_chain */
-	};
-	DECLARE_BITMAP(unsync_child_bitmap, 512);
-};
-
-struct kvm_pv_mmu_op_buffer {
-	void *ptr;
-	unsigned len;
-	unsigned processed;
-	char buf[512] __aligned(sizeof(long));
-};
-
-/*
- * x86 supports 3 paging modes (4-level 64-bit, 3-level 64-bit, and 2-level
- * 32-bit).  The kvm_mmu structure abstracts the details of the current mmu
- * mode.
- */
-struct kvm_mmu {
-	void (*new_cr3)(struct kvm_vcpu *vcpu);
-	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
-	void (*free)(struct kvm_vcpu *vcpu);
-	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
-	void (*prefetch_page)(struct kvm_vcpu *vcpu,
-			      struct kvm_mmu_page *page);
-	int (*sync_page)(struct kvm_vcpu *vcpu,
-			 struct kvm_mmu_page *sp);
-	void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
-	hpa_t root_hpa;
-	int root_level;
-	int shadow_root_level;
-
-	u64 *pae_root;
-};
-
-struct kvm_vcpu_arch {
-	u64 host_tsc;
-	int interrupt_window_open;
-	unsigned long irq_summary; /* bit vector: 1 per word in irq_pending */
-	DECLARE_BITMAP(irq_pending, KVM_NR_INTERRUPTS);
-	/*
-	 * rip and regs accesses must go through
-	 * kvm_{register,rip}_{read,write} functions.
-	 */
-	unsigned long regs[NR_VCPU_REGS];
-	u32 regs_avail;
-	u32 regs_dirty;
-
-	unsigned long cr0;
-	unsigned long cr2;
-	unsigned long cr3;
-	unsigned long cr4;
-	unsigned long cr8;
-	u64 pdptrs[4]; /* pae */
-	u64 shadow_efer;
-	u64 apic_base;
-	struct kvm_lapic *apic;    /* kernel irqchip context */
-	int mp_state;
-	int sipi_vector;
-	u64 ia32_misc_enable_msr;
-	bool tpr_access_reporting;
-
-	struct kvm_mmu mmu;
-	/* only needed in kvm_pv_mmu_op() path, but it's hot so
-	 * put it here to avoid allocation */
-	struct kvm_pv_mmu_op_buffer mmu_op_buffer;
-
-	struct kvm_mmu_memory_cache mmu_pte_chain_cache;
-	struct kvm_mmu_memory_cache mmu_rmap_desc_cache;
-	struct kvm_mmu_memory_cache mmu_page_cache;
-	struct kvm_mmu_memory_cache mmu_page_header_cache;
-
-	gfn_t last_pt_write_gfn;
-	int   last_pt_write_count;
-	u64  *last_pte_updated;
-	gfn_t last_pte_gfn;
-
-	struct {
-		gfn_t gfn;	/* presumed gfn during guest pte update */
-		pfn_t pfn;	/* pfn corresponding to that gfn */
-		int largepage;
-		unsigned long mmu_seq;
-	} update_pte;
-
-	struct i387_fxsave_struct host_fx_image;
-	struct i387_fxsave_struct guest_fx_image;
-
-	gva_t mmio_fault_cr2;
-	struct kvm_pio_request pio;
-	void *pio_data;
-
-	struct kvm_queued_exception {
-		bool pending;
-		bool has_error_code;
-		u8 nr;
-		u32 error_code;
-	} exception;
-
-	struct kvm_queued_interrupt {
-		bool pending;
-		u8 nr;
-	} interrupt;
-
-	struct {
-		int active;
-		u8 save_iopl;
-		struct kvm_save_segment {
-			u16 selector;
-			unsigned long base;
-			u32 limit;
-			u32 ar;
-		} tr, es, ds, fs, gs;
-	} rmode;
-	int halt_request; /* real mode on Intel only */
-
-	int cpuid_nent;
-	struct kvm_cpuid_entry2 cpuid_entries[KVM_MAX_CPUID_ENTRIES];
-	/* emulate context */
-
-	struct x86_emulate_ctxt emulate_ctxt;
-
-	gpa_t time;
-	struct pvclock_vcpu_time_info hv_clock;
-	unsigned int hv_clock_tsc_khz;
-	unsigned int time_offset;
-	struct page *time_page;
-
-	bool nmi_pending;
-	bool nmi_injected;
-
-	u64 mtrr[0x100];
-};
-
-struct kvm_mem_alias {
-	gfn_t base_gfn;
-	unsigned long npages;
-	gfn_t target_gfn;
-};
-
-struct kvm_arch{
-	int naliases;
-	struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS];
-
-	unsigned int n_free_mmu_pages;
-	unsigned int n_requested_mmu_pages;
-	unsigned int n_alloc_mmu_pages;
-	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
-	/*
-	 * Hash table of struct kvm_mmu_page.
-	 */
-	struct list_head active_mmu_pages;
-	struct list_head assigned_dev_head;
-	struct dmar_domain *intel_iommu_domain;
-	struct kvm_pic *vpic;
-	struct kvm_ioapic *vioapic;
-	struct kvm_pit *vpit;
-	struct hlist_head irq_ack_notifier_list;
-
-	int round_robin_prev_vcpu;
-	unsigned int tss_addr;
-	struct page *apic_access_page;
-
-	gpa_t wall_clock;
-
-	struct page *ept_identity_pagetable;
-	bool ept_identity_pagetable_done;
-};
-
-struct kvm_vm_stat {
-	u32 mmu_shadow_zapped;
-	u32 mmu_pte_write;
-	u32 mmu_pte_updated;
-	u32 mmu_pde_zapped;
-	u32 mmu_flooded;
-	u32 mmu_recycled;
-	u32 mmu_cache_miss;
-	u32 mmu_unsync;
-	u32 remote_tlb_flush;
-	u32 lpages;
-};
-
-struct kvm_vcpu_stat {
-	u32 pf_fixed;
-	u32 pf_guest;
-	u32 tlb_flush;
-	u32 invlpg;
-
-	u32 exits;
-	u32 io_exits;
-	u32 mmio_exits;
-	u32 signal_exits;
-	u32 irq_window_exits;
-	u32 nmi_window_exits;
-	u32 halt_exits;
-	u32 halt_wakeup;
-	u32 request_irq_exits;
-	u32 irq_exits;
-	u32 host_state_reload;
-	u32 efer_reload;
-	u32 fpu_reload;
-	u32 insn_emulation;
-	u32 insn_emulation_fail;
-	u32 hypercalls;
-	u32 irq_injections;
-};
-
-struct descriptor_table {
-	u16 limit;
-	unsigned long base;
-} __attribute__((packed));
-
-struct kvm_x86_ops {
-	int (*cpu_has_kvm_support)(void);          /* __init */
-	int (*disabled_by_bios)(void);             /* __init */
-	void (*hardware_enable)(void *dummy);      /* __init */
-	void (*hardware_disable)(void *dummy);
-	void (*check_processor_compatibility)(void *rtn);
-	int (*hardware_setup)(void);               /* __init */
-	void (*hardware_unsetup)(void);            /* __exit */
-	bool (*cpu_has_accelerated_tpr)(void);
-
-	/* Create, but do not attach this VCPU */
-	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
-	void (*vcpu_free)(struct kvm_vcpu *vcpu);
-	int (*vcpu_reset)(struct kvm_vcpu *vcpu);
-
-	void (*prepare_guest_switch)(struct kvm_vcpu *vcpu);
-	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
-	void (*vcpu_put)(struct kvm_vcpu *vcpu);
-
-	int (*set_guest_debug)(struct kvm_vcpu *vcpu,
-			       struct kvm_debug_guest *dbg);
-	void (*guest_debug_pre)(struct kvm_vcpu *vcpu);
-	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
-	int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
-	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
-	void (*get_segment)(struct kvm_vcpu *vcpu,
-			    struct kvm_segment *var, int seg);
-	int (*get_cpl)(struct kvm_vcpu *vcpu);
-	void (*set_segment)(struct kvm_vcpu *vcpu,
-			    struct kvm_segment *var, int seg);
-	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
-	void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
-	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
-	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
-	void (*set_cr4)(struct kvm_vcpu *vcpu, unsigned long cr4);
-	void (*set_efer)(struct kvm_vcpu *vcpu, u64 efer);
-	void (*get_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
-	void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
-	void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
-	void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
-	unsigned long (*get_dr)(struct kvm_vcpu *vcpu, int dr);
-	void (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value,
-		       int *exception);
-	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
-	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
-	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
-
-	void (*tlb_flush)(struct kvm_vcpu *vcpu);
-
-	void (*run)(struct kvm_vcpu *vcpu, struct kvm_run *run);
-	int (*handle_exit)(struct kvm_run *run, struct kvm_vcpu *vcpu);
-	void (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
-	void (*patch_hypercall)(struct kvm_vcpu *vcpu,
-				unsigned char *hypercall_addr);
-	int (*get_irq)(struct kvm_vcpu *vcpu);
-	void (*set_irq)(struct kvm_vcpu *vcpu, int vec);
-	void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr,
-				bool has_error_code, u32 error_code);
-	bool (*exception_injected)(struct kvm_vcpu *vcpu);
-	void (*inject_pending_irq)(struct kvm_vcpu *vcpu);
-	void (*inject_pending_vectors)(struct kvm_vcpu *vcpu,
-				       struct kvm_run *run);
-
-	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
-	int (*get_tdp_level)(void);
-};
-
-extern struct kvm_x86_ops *kvm_x86_ops;
-
-int kvm_mmu_module_init(void);
-void kvm_mmu_module_exit(void);
-
-void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
-int kvm_mmu_create(struct kvm_vcpu *vcpu);
-int kvm_mmu_setup(struct kvm_vcpu *vcpu);
-void kvm_mmu_set_nonpresent_ptes(u64 trap_pte, u64 notrap_pte);
-void kvm_mmu_set_base_ptes(u64 base_pte);
-void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask);
-
-int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
-void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
-void kvm_mmu_zap_all(struct kvm *kvm);
-unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
-void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
-
-int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
-
-int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
-			  const void *val, int bytes);
-int kvm_pv_mmu_op(struct kvm_vcpu *vcpu, unsigned long bytes,
-		  gpa_t addr, unsigned long *ret);
-
-extern bool tdp_enabled;
-
-enum emulation_result {
-	EMULATE_DONE,       /* no further processing */
-	EMULATE_DO_MMIO,      /* kvm_run filled with mmio request */
-	EMULATE_FAIL,         /* can't emulate this instruction */
-};
-
-#define EMULTYPE_NO_DECODE	    (1 << 0)
-#define EMULTYPE_TRAP_UD	    (1 << 1)
-int emulate_instruction(struct kvm_vcpu *vcpu, struct kvm_run *run,
-			unsigned long cr2, u16 error_code, int emulation_type);
-void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
-void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
-void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
-void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
-		   unsigned long *rflags);
-
-unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr);
-void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long value,
-		     unsigned long *rflags);
-void kvm_enable_efer_bits(u64);
-int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
-int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
-
-struct x86_emulate_ctxt;
-
-int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
-		     int size, unsigned port);
-int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
-			   int size, unsigned long count, int down,
-			    gva_t address, int rep, unsigned port);
-void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
-int kvm_emulate_halt(struct kvm_vcpu *vcpu);
-int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address);
-int emulate_clts(struct kvm_vcpu *vcpu);
-int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr,
-		    unsigned long *dest);
-int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
-		    unsigned long value);
-
-void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
-int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
-				int type_bits, int seg);
-
-int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);
-
-void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
-void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
-void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
-void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
-unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
-void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
-void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
-
-int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
-int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);
-
-void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
-void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
-void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
-			   u32 error_code);
-
-void kvm_pic_set_irq(void *opaque, int irq, int level);
-
-void kvm_inject_nmi(struct kvm_vcpu *vcpu);
-
-void fx_init(struct kvm_vcpu *vcpu);
-
-int emulator_read_std(unsigned long addr,
-		      void *val,
-		      unsigned int bytes,
-		      struct kvm_vcpu *vcpu);
-int emulator_write_emulated(unsigned long addr,
-			    const void *val,
-			    unsigned int bytes,
-			    struct kvm_vcpu *vcpu);
-
-unsigned long segment_base(u16 selector);
-
-void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
-void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
-		       const u8 *new, int bytes);
-int kvm_mmu_unprotect_page_virt(struct kvm_vcpu *vcpu, gva_t gva);
-void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
-int kvm_mmu_load(struct kvm_vcpu *vcpu);
-void kvm_mmu_unload(struct kvm_vcpu *vcpu);
-void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
-
-int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
-
-int kvm_fix_hypercall(struct kvm_vcpu *vcpu);
-
-int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code);
-void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
-
-void kvm_enable_tdp(void);
-void kvm_disable_tdp(void);
-
-int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
-int complete_pio(struct kvm_vcpu *vcpu);
-
-static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
-{
-	struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
-
-	return (struct kvm_mmu_page *)page_private(page);
-}
-
-static inline u16 kvm_read_fs(void)
-{
-	u16 seg;
-	asm("mov %%fs, %0" : "=g"(seg));
-	return seg;
-}
-
-static inline u16 kvm_read_gs(void)
-{
-	u16 seg;
-	asm("mov %%gs, %0" : "=g"(seg));
-	return seg;
-}
-
-static inline u16 kvm_read_ldt(void)
-{
-	u16 ldt;
-	asm("sldt %0" : "=g"(ldt));
-	return ldt;
-}
-
-static inline void kvm_load_fs(u16 sel)
-{
-	asm("mov %0, %%fs" : : "rm"(sel));
-}
-
-static inline void kvm_load_gs(u16 sel)
-{
-	asm("mov %0, %%gs" : : "rm"(sel));
-}
-
-static inline void kvm_load_ldt(u16 sel)
-{
-	asm("lldt %0" : : "rm"(sel));
-}
-
-static inline void kvm_get_idt(struct descriptor_table *table)
-{
-	asm("sidt %0" : "=m"(*table));
-}
-
-static inline void kvm_get_gdt(struct descriptor_table *table)
-{
-	asm("sgdt %0" : "=m"(*table));
-}
-
-static inline unsigned long kvm_read_tr_base(void)
-{
-	u16 tr;
-	asm("str %0" : "=g"(tr));
-	return segment_base(tr);
-}
-
-#ifdef CONFIG_X86_64
-static inline unsigned long read_msr(unsigned long msr)
-{
-	u64 value;
-
-	rdmsrl(msr, value);
-	return value;
-}
-#endif
-
-static inline void kvm_fx_save(struct i387_fxsave_struct *image)
-{
-	asm("fxsave (%0)":: "r" (image));
-}
-
-static inline void kvm_fx_restore(struct i387_fxsave_struct *image)
-{
-	asm("fxrstor (%0)":: "r" (image));
-}
-
-static inline void kvm_fx_finit(void)
-{
-	asm("finit");
-}
-
-static inline u32 get_rdx_init_val(void)
-{
-	return 0x600; /* P6 family */
-}
-
-static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
-{
-	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
-}
-
-#define ASM_VMX_VMCLEAR_RAX       ".byte 0x66, 0x0f, 0xc7, 0x30"
-#define ASM_VMX_VMLAUNCH          ".byte 0x0f, 0x01, 0xc2"
-#define ASM_VMX_VMRESUME          ".byte 0x0f, 0x01, 0xc3"
-#define ASM_VMX_VMPTRLD_RAX       ".byte 0x0f, 0xc7, 0x30"
-#define ASM_VMX_VMREAD_RDX_RAX    ".byte 0x0f, 0x78, 0xd0"
-#define ASM_VMX_VMWRITE_RAX_RDX   ".byte 0x0f, 0x79, 0xd0"
-#define ASM_VMX_VMWRITE_RSP_RDX   ".byte 0x0f, 0x79, 0xd4"
-#define ASM_VMX_VMXOFF            ".byte 0x0f, 0x01, 0xc4"
-#define ASM_VMX_VMXON_RAX         ".byte 0xf3, 0x0f, 0xc7, 0x30"
-#define ASM_VMX_INVEPT		  ".byte 0x66, 0x0f, 0x38, 0x80, 0x08"
-#define ASM_VMX_INVVPID		  ".byte 0x66, 0x0f, 0x38, 0x81, 0x08"
-
-#define MSR_IA32_TIME_STAMP_COUNTER		0x010
-
-#define TSS_IOPB_BASE_OFFSET 0x66
-#define TSS_BASE_SIZE 0x68
-#define TSS_IOPB_SIZE (65536 / 8)
-#define TSS_REDIRECTION_SIZE (256 / 8)
-#define RMODE_TSS_SIZE							\
-	(TSS_BASE_SIZE + TSS_REDIRECTION_SIZE + TSS_IOPB_SIZE + 1)
-
-enum {
-	TASK_SWITCH_CALL = 0,
-	TASK_SWITCH_IRET = 1,
-	TASK_SWITCH_JMP = 2,
-	TASK_SWITCH_GATE = 3,
-};
-
-/*
- * Hardware virtualization extension instructions may fault if a
- * reboot turns off virtualization while processes are running.
- * Trap the fault and ignore the instruction if that happens.
- */
-asmlinkage void kvm_handle_fault_on_reboot(void);
-
-#define __kvm_handle_fault_on_reboot(insn) \
-	"666: " insn "\n\t" \
-	".pushsection .fixup, \"ax\" \n" \
-	"667: \n\t" \
-	__ASM_SIZE(push) " $666b \n\t"	      \
-	"jmp kvm_handle_fault_on_reboot \n\t" \
-	".popsection \n\t" \
-	".pushsection __ex_table, \"a\" \n\t" \
-	_ASM_PTR " 666b, 667b \n\t" \
-	".popsection"
-
-#define KVM_ARCH_WANT_MMU_NOTIFIER
-int kvm_unmap_hva(struct kvm *kvm, unsigned long hva);
-int kvm_age_hva(struct kvm *kvm, unsigned long hva);
-
-#endif /* ASM_X86__KVM_HOST_H */
diff --git a/include/asm-x86/kvm_para.h b/include/asm-x86/kvm_para.h
deleted file mode 100644
index 30054fded4fb..000000000000
--- a/include/asm-x86/kvm_para.h
+++ /dev/null
@@ -1,147 +0,0 @@
-#ifndef ASM_X86__KVM_PARA_H
-#define ASM_X86__KVM_PARA_H
-
-/* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx.  It
- * should be used to determine that a VM is running under KVM.
- */
-#define KVM_CPUID_SIGNATURE	0x40000000
-
-/* This CPUID returns a feature bitmap in eax.  Before enabling a particular
- * paravirtualization, the appropriate feature bit should be checked.
- */
-#define KVM_CPUID_FEATURES	0x40000001
-#define KVM_FEATURE_CLOCKSOURCE		0
-#define KVM_FEATURE_NOP_IO_DELAY	1
-#define KVM_FEATURE_MMU_OP		2
-
-#define MSR_KVM_WALL_CLOCK  0x11
-#define MSR_KVM_SYSTEM_TIME 0x12
-
-#define KVM_MAX_MMU_OP_BATCH           32
-
-/* Operations for KVM_HC_MMU_OP */
-#define KVM_MMU_OP_WRITE_PTE            1
-#define KVM_MMU_OP_FLUSH_TLB	        2
-#define KVM_MMU_OP_RELEASE_PT	        3
-
-/* Payload for KVM_HC_MMU_OP */
-struct kvm_mmu_op_header {
-	__u32 op;
-	__u32 pad;
-};
-
-struct kvm_mmu_op_write_pte {
-	struct kvm_mmu_op_header header;
-	__u64 pte_phys;
-	__u64 pte_val;
-};
-
-struct kvm_mmu_op_flush_tlb {
-	struct kvm_mmu_op_header header;
-};
-
-struct kvm_mmu_op_release_pt {
-	struct kvm_mmu_op_header header;
-	__u64 pt_phys;
-};
-
-#ifdef __KERNEL__
-#include <asm/processor.h>
-
-extern void kvmclock_init(void);
-
-
-/* This instruction is vmcall.  On non-VT architectures, it will generate a
- * trap that we will then rewrite to the appropriate instruction.
- */
-#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
-
-/* For KVM hypercalls, a three-byte sequence of either the vmrun or the vmmrun
- * instruction.  The hypervisor may replace it with something else but only the
- * instructions are guaranteed to be supported.
- *
- * Up to four arguments may be passed in rbx, rcx, rdx, and rsi respectively.
- * The hypercall number should be placed in rax and the return value will be
- * placed in rax.  No other registers will be clobbered unless explicited
- * noted by the particular hypercall.
- */
-
-static inline long kvm_hypercall0(unsigned int nr)
-{
-	long ret;
-	asm volatile(KVM_HYPERCALL
-		     : "=a"(ret)
-		     : "a"(nr)
-		     : "memory");
-	return ret;
-}
-
-static inline long kvm_hypercall1(unsigned int nr, unsigned long p1)
-{
-	long ret;
-	asm volatile(KVM_HYPERCALL
-		     : "=a"(ret)
-		     : "a"(nr), "b"(p1)
-		     : "memory");
-	return ret;
-}
-
-static inline long kvm_hypercall2(unsigned int nr, unsigned long p1,
-				  unsigned long p2)
-{
-	long ret;
-	asm volatile(KVM_HYPERCALL
-		     : "=a"(ret)
-		     : "a"(nr), "b"(p1), "c"(p2)
-		     : "memory");
-	return ret;
-}
-
-static inline long kvm_hypercall3(unsigned int nr, unsigned long p1,
-				  unsigned long p2, unsigned long p3)
-{
-	long ret;
-	asm volatile(KVM_HYPERCALL
-		     : "=a"(ret)
-		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3)
-		     : "memory");
-	return ret;
-}
-
-static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
-				  unsigned long p2, unsigned long p3,
-				  unsigned long p4)
-{
-	long ret;
-	asm volatile(KVM_HYPERCALL
-		     : "=a"(ret)
-		     : "a"(nr), "b"(p1), "c"(p2), "d"(p3), "S"(p4)
-		     : "memory");
-	return ret;
-}
-
-static inline int kvm_para_available(void)
-{
-	unsigned int eax, ebx, ecx, edx;
-	char signature[13];
-
-	cpuid(KVM_CPUID_SIGNATURE, &eax, &ebx, &ecx, &edx);
-	memcpy(signature + 0, &ebx, 4);
-	memcpy(signature + 4, &ecx, 4);
-	memcpy(signature + 8, &edx, 4);
-	signature[12] = 0;
-
-	if (strcmp(signature, "KVMKVMKVM") == 0)
-		return 1;
-
-	return 0;
-}
-
-static inline unsigned int kvm_arch_para_features(void)
-{
-	return cpuid_eax(KVM_CPUID_FEATURES);
-}
-
-#endif
-
-#endif /* ASM_X86__KVM_PARA_H */
diff --git a/include/asm-x86/kvm_x86_emulate.h b/include/asm-x86/kvm_x86_emulate.h
deleted file mode 100644
index e2d9b030c1ac..000000000000
--- a/include/asm-x86/kvm_x86_emulate.h
+++ /dev/null
@@ -1,184 +0,0 @@
-/******************************************************************************
- * x86_emulate.h
- *
- * Generic x86 (32-bit and 64-bit) instruction decoder and emulator.
- *
- * Copyright (c) 2005 Keir Fraser
- *
- * From: xen-unstable 10676:af9809f51f81a3c43f276f00c81a52ef558afda4
- */
-
-#ifndef ASM_X86__KVM_X86_EMULATE_H
-#define ASM_X86__KVM_X86_EMULATE_H
-
-struct x86_emulate_ctxt;
-
-/*
- * x86_emulate_ops:
- *
- * These operations represent the instruction emulator's interface to memory.
- * There are two categories of operation: those that act on ordinary memory
- * regions (*_std), and those that act on memory regions known to require
- * special treatment or emulation (*_emulated).
- *
- * The emulator assumes that an instruction accesses only one 'emulated memory'
- * location, that this location is the given linear faulting address (cr2), and
- * that this is one of the instruction's data operands. Instruction fetches and
- * stack operations are assumed never to access emulated memory. The emulator
- * automatically deduces which operand of a string-move operation is accessing
- * emulated memory, and assumes that the other operand accesses normal memory.
- *
- * NOTES:
- *  1. The emulator isn't very smart about emulated vs. standard memory.
- *     'Emulated memory' access addresses should be checked for sanity.
- *     'Normal memory' accesses may fault, and the caller must arrange to
- *     detect and handle reentrancy into the emulator via recursive faults.
- *     Accesses may be unaligned and may cross page boundaries.
- *  2. If the access fails (cannot emulate, or a standard access faults) then
- *     it is up to the memop to propagate the fault to the guest VM via
- *     some out-of-band mechanism, unknown to the emulator. The memop signals
- *     failure by returning X86EMUL_PROPAGATE_FAULT to the emulator, which will
- *     then immediately bail.
- *  3. Valid access sizes are 1, 2, 4 and 8 bytes. On x86/32 systems only
- *     cmpxchg8b_emulated need support 8-byte accesses.
- *  4. The emulator cannot handle 64-bit mode emulation on an x86/32 system.
- */
-/* Access completed successfully: continue emulation as normal. */
-#define X86EMUL_CONTINUE        0
-/* Access is unhandleable: bail from emulation and return error to caller. */
-#define X86EMUL_UNHANDLEABLE    1
-/* Terminate emulation but return success to the caller. */
-#define X86EMUL_PROPAGATE_FAULT 2 /* propagate a generated fault to guest */
-#define X86EMUL_RETRY_INSTR     2 /* retry the instruction for some reason */
-#define X86EMUL_CMPXCHG_FAILED  2 /* cmpxchg did not see expected value */
-struct x86_emulate_ops {
-	/*
-	 * read_std: Read bytes of standard (non-emulated/special) memory.
-	 *           Used for instruction fetch, stack operations, and others.
-	 *  @addr:  [IN ] Linear address from which to read.
-	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
-	 *  @bytes: [IN ] Number of bytes to read from memory.
-	 */
-	int (*read_std)(unsigned long addr, void *val,
-			unsigned int bytes, struct kvm_vcpu *vcpu);
-
-	/*
-	 * read_emulated: Read bytes from emulated/special memory area.
-	 *  @addr:  [IN ] Linear address from which to read.
-	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
-	 *  @bytes: [IN ] Number of bytes to read from memory.
-	 */
-	int (*read_emulated)(unsigned long addr,
-			     void *val,
-			     unsigned int bytes,
-			     struct kvm_vcpu *vcpu);
-
-	/*
-	 * write_emulated: Read bytes from emulated/special memory area.
-	 *  @addr:  [IN ] Linear address to which to write.
-	 *  @val:   [IN ] Value to write to memory (low-order bytes used as
-	 *                required).
-	 *  @bytes: [IN ] Number of bytes to write to memory.
-	 */
-	int (*write_emulated)(unsigned long addr,
-			      const void *val,
-			      unsigned int bytes,
-			      struct kvm_vcpu *vcpu);
-
-	/*
-	 * cmpxchg_emulated: Emulate an atomic (LOCKed) CMPXCHG operation on an
-	 *                   emulated/special memory area.
-	 *  @addr:  [IN ] Linear address to access.
-	 *  @old:   [IN ] Value expected to be current at @addr.
-	 *  @new:   [IN ] Value to write to @addr.
-	 *  @bytes: [IN ] Number of bytes to access using CMPXCHG.
-	 */
-	int (*cmpxchg_emulated)(unsigned long addr,
-				const void *old,
-				const void *new,
-				unsigned int bytes,
-				struct kvm_vcpu *vcpu);
-
-};
-
-/* Type, address-of, and value of an instruction's operand. */
-struct operand {
-	enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type;
-	unsigned int bytes;
-	unsigned long val, orig_val, *ptr;
-};
-
-struct fetch_cache {
-	u8 data[15];
-	unsigned long start;
-	unsigned long end;
-};
-
-struct decode_cache {
-	u8 twobyte;
-	u8 b;
-	u8 lock_prefix;
-	u8 rep_prefix;
-	u8 op_bytes;
-	u8 ad_bytes;
-	u8 rex_prefix;
-	struct operand src;
-	struct operand dst;
-	bool has_seg_override;
-	u8 seg_override;
-	unsigned int d;
-	unsigned long regs[NR_VCPU_REGS];
-	unsigned long eip;
-	/* modrm */
-	u8 modrm;
-	u8 modrm_mod;
-	u8 modrm_reg;
-	u8 modrm_rm;
-	u8 use_modrm_ea;
-	bool rip_relative;
-	unsigned long modrm_ea;
-	void *modrm_ptr;
-	unsigned long modrm_val;
-	struct fetch_cache fetch;
-};
-
-struct x86_emulate_ctxt {
-	/* Register state before/after emulation. */
-	struct kvm_vcpu *vcpu;
-
-	/* Linear faulting address (if emulating a page-faulting instruction) */
-	unsigned long eflags;
-
-	/* Emulated execution mode, represented by an X86EMUL_MODE value. */
-	int mode;
-
-	u32 cs_base;
-
-	/* decode cache */
-
-	struct decode_cache decode;
-};
-
-/* Repeat String Operation Prefix */
-#define REPE_PREFIX  1
-#define REPNE_PREFIX    2
-
-/* Execution mode, passed to the emulator. */
-#define X86EMUL_MODE_REAL     0	/* Real mode.             */
-#define X86EMUL_MODE_PROT16   2	/* 16-bit protected mode. */
-#define X86EMUL_MODE_PROT32   4	/* 32-bit protected mode. */
-#define X86EMUL_MODE_PROT64   8	/* 64-bit (long) mode.    */
-
-/* Host execution mode. */
-#if defined(__i386__)
-#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT32
-#elif defined(CONFIG_X86_64)
-#define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64
-#endif
-
-int x86_decode_insn(struct x86_emulate_ctxt *ctxt,
-		    struct x86_emulate_ops *ops);
-int x86_emulate_insn(struct x86_emulate_ctxt *ctxt,
-		     struct x86_emulate_ops *ops);
-
-#endif /* ASM_X86__KVM_X86_EMULATE_H */
diff --git a/include/asm-x86/ldt.h b/include/asm-x86/ldt.h
deleted file mode 100644
index a5228504d867..000000000000
--- a/include/asm-x86/ldt.h
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- * ldt.h
- *
- * Definitions of structures used with the modify_ldt system call.
- */
-#ifndef ASM_X86__LDT_H
-#define ASM_X86__LDT_H
-
-/* Maximum number of LDT entries supported. */
-#define LDT_ENTRIES	8192
-/* The size of each LDT entry. */
-#define LDT_ENTRY_SIZE	8
-
-#ifndef __ASSEMBLY__
-/*
- * Note on 64bit base and limit is ignored and you cannot set DS/ES/CS
- * not to the default values if you still want to do syscalls. This
- * call is more for 32bit mode therefore.
- */
-struct user_desc {
-	unsigned int  entry_number;
-	unsigned int  base_addr;
-	unsigned int  limit;
-	unsigned int  seg_32bit:1;
-	unsigned int  contents:2;
-	unsigned int  read_exec_only:1;
-	unsigned int  limit_in_pages:1;
-	unsigned int  seg_not_present:1;
-	unsigned int  useable:1;
-#ifdef __x86_64__
-	unsigned int  lm:1;
-#endif
-};
-
-#define MODIFY_LDT_CONTENTS_DATA	0
-#define MODIFY_LDT_CONTENTS_STACK	1
-#define MODIFY_LDT_CONTENTS_CODE	2
-
-#endif /* !__ASSEMBLY__ */
-#endif /* ASM_X86__LDT_H */
diff --git a/include/asm-x86/lguest.h b/include/asm-x86/lguest.h
deleted file mode 100644
index 7505e947ed27..000000000000
--- a/include/asm-x86/lguest.h
+++ /dev/null
@@ -1,94 +0,0 @@
-#ifndef ASM_X86__LGUEST_H
-#define ASM_X86__LGUEST_H
-
-#define GDT_ENTRY_LGUEST_CS	10
-#define GDT_ENTRY_LGUEST_DS	11
-#define LGUEST_CS		(GDT_ENTRY_LGUEST_CS * 8)
-#define LGUEST_DS		(GDT_ENTRY_LGUEST_DS * 8)
-
-#ifndef __ASSEMBLY__
-#include <asm/desc.h>
-
-#define GUEST_PL 1
-
-/* Every guest maps the core switcher code. */
-#define SHARED_SWITCHER_PAGES \
-	DIV_ROUND_UP(end_switcher_text - start_switcher_text, PAGE_SIZE)
-/* Pages for switcher itself, then two pages per cpu */
-#define TOTAL_SWITCHER_PAGES (SHARED_SWITCHER_PAGES + 2 * NR_CPUS)
-
-/* We map at -4M for ease of mapping into the guest (one PTE page). */
-#define SWITCHER_ADDR 0xFFC00000
-
-/* Found in switcher.S */
-extern unsigned long default_idt_entries[];
-
-/* Declarations for definitions in lguest_guest.S */
-extern char lguest_noirq_start[], lguest_noirq_end[];
-extern const char lgstart_cli[], lgend_cli[];
-extern const char lgstart_sti[], lgend_sti[];
-extern const char lgstart_popf[], lgend_popf[];
-extern const char lgstart_pushf[], lgend_pushf[];
-extern const char lgstart_iret[], lgend_iret[];
-
-extern void lguest_iret(void);
-extern void lguest_init(void);
-
-struct lguest_regs {
-	/* Manually saved part. */
-	unsigned long eax, ebx, ecx, edx;
-	unsigned long esi, edi, ebp;
-	unsigned long gs;
-	unsigned long fs, ds, es;
-	unsigned long trapnum, errcode;
-	/* Trap pushed part */
-	unsigned long eip;
-	unsigned long cs;
-	unsigned long eflags;
-	unsigned long esp;
-	unsigned long ss;
-};
-
-/* This is a guest-specific page (mapped ro) into the guest. */
-struct lguest_ro_state {
-	/* Host information we need to restore when we switch back. */
-	u32 host_cr3;
-	struct desc_ptr host_idt_desc;
-	struct desc_ptr host_gdt_desc;
-	u32 host_sp;
-
-	/* Fields which are used when guest is running. */
-	struct desc_ptr guest_idt_desc;
-	struct desc_ptr guest_gdt_desc;
-	struct x86_hw_tss guest_tss;
-	struct desc_struct guest_idt[IDT_ENTRIES];
-	struct desc_struct guest_gdt[GDT_ENTRIES];
-};
-
-struct lg_cpu_arch {
-	/* The GDT entries copied into lguest_ro_state when running. */
-	struct desc_struct gdt[GDT_ENTRIES];
-
-	/* The IDT entries: some copied into lguest_ro_state when running. */
-	struct desc_struct idt[IDT_ENTRIES];
-
-	/* The address of the last guest-visible pagefault (ie. cr2). */
-	unsigned long last_pagefault;
-};
-
-static inline void lguest_set_ts(void)
-{
-	u32 cr0;
-
-	cr0 = read_cr0();
-	if (!(cr0 & 8))
-		write_cr0(cr0 | 8);
-}
-
-/* Full 4G segment descriptors, suitable for CS and DS. */
-#define FULL_EXEC_SEGMENT ((struct desc_struct){ { {0x0000ffff, 0x00cf9b00} } })
-#define FULL_SEGMENT ((struct desc_struct){ { {0x0000ffff, 0x00cf9300} } })
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* ASM_X86__LGUEST_H */
diff --git a/include/asm-x86/lguest_hcall.h b/include/asm-x86/lguest_hcall.h
deleted file mode 100644
index 8f034ba4b53e..000000000000
--- a/include/asm-x86/lguest_hcall.h
+++ /dev/null
@@ -1,71 +0,0 @@
-/* Architecture specific portion of the lguest hypercalls */
-#ifndef ASM_X86__LGUEST_HCALL_H
-#define ASM_X86__LGUEST_HCALL_H
-
-#define LHCALL_FLUSH_ASYNC	0
-#define LHCALL_LGUEST_INIT	1
-#define LHCALL_SHUTDOWN		2
-#define LHCALL_LOAD_GDT		3
-#define LHCALL_NEW_PGTABLE	4
-#define LHCALL_FLUSH_TLB	5
-#define LHCALL_LOAD_IDT_ENTRY	6
-#define LHCALL_SET_STACK	7
-#define LHCALL_TS		8
-#define LHCALL_SET_CLOCKEVENT	9
-#define LHCALL_HALT		10
-#define LHCALL_SET_PTE		14
-#define LHCALL_SET_PMD		15
-#define LHCALL_LOAD_TLS		16
-#define LHCALL_NOTIFY		17
-
-#define LGUEST_TRAP_ENTRY 0x1F
-
-/* Argument number 3 to LHCALL_LGUEST_SHUTDOWN */
-#define LGUEST_SHUTDOWN_POWEROFF	1
-#define LGUEST_SHUTDOWN_RESTART		2
-
-#ifndef __ASSEMBLY__
-#include <asm/hw_irq.h>
-
-/*G:031 But first, how does our Guest contact the Host to ask for privileged
- * operations?  There are two ways: the direct way is to make a "hypercall",
- * to make requests of the Host Itself.
- *
- * Our hypercall mechanism uses the highest unused trap code (traps 32 and
- * above are used by real hardware interrupts).  Fifteen hypercalls are
- * available: the hypercall number is put in the %eax register, and the
- * arguments (when required) are placed in %edx, %ebx and %ecx.  If a return
- * value makes sense, it's returned in %eax.
- *
- * Grossly invalid calls result in Sudden Death at the hands of the vengeful
- * Host, rather than returning failure.  This reflects Winston Churchill's
- * definition of a gentleman: "someone who is only rude intentionally". */
-static inline unsigned long
-hcall(unsigned long call,
-      unsigned long arg1, unsigned long arg2, unsigned long arg3)
-{
-	/* "int" is the Intel instruction to trigger a trap. */
-	asm volatile("int $" __stringify(LGUEST_TRAP_ENTRY)
-		     /* The call in %eax (aka "a") might be overwritten */
-		     : "=a"(call)
-		       /* The arguments are in %eax, %edx, %ebx & %ecx */
-		     : "a"(call), "d"(arg1), "b"(arg2), "c"(arg3)
-		       /* "memory" means this might write somewhere in memory.
-			* This isn't true for all calls, but it's safe to tell
-			* gcc that it might happen so it doesn't get clever. */
-		     : "memory");
-	return call;
-}
-/*:*/
-
-/* Can't use our min() macro here: needs to be a constant */
-#define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32)
-
-#define LHCALL_RING_SIZE 64
-struct hcall_args {
-	/* These map directly onto eax, ebx, ecx, edx in struct lguest_regs */
-	unsigned long arg0, arg2, arg3, arg1;
-};
-
-#endif /* !__ASSEMBLY__ */
-#endif /* ASM_X86__LGUEST_HCALL_H */
diff --git a/include/asm-x86/linkage.h b/include/asm-x86/linkage.h
deleted file mode 100644
index 42d8b62ee8ab..000000000000
--- a/include/asm-x86/linkage.h
+++ /dev/null
@@ -1,61 +0,0 @@
-#ifndef ASM_X86__LINKAGE_H
-#define ASM_X86__LINKAGE_H
-
-#undef notrace
-#define notrace __attribute__((no_instrument_function))
-
-#ifdef CONFIG_X86_64
-#define __ALIGN .p2align 4,,15
-#define __ALIGN_STR ".p2align 4,,15"
-#endif
-
-#ifdef CONFIG_X86_32
-#define asmlinkage CPP_ASMLINKAGE __attribute__((regparm(0)))
-/*
- * For 32-bit UML - mark functions implemented in assembly that use
- * regparm input parameters:
- */
-#define asmregparm __attribute__((regparm(3)))
-
-/*
- * Make sure the compiler doesn't do anything stupid with the
- * arguments on the stack - they are owned by the *caller*, not
- * the callee. This just fools gcc into not spilling into them,
- * and keeps it from doing tailcall recursion and/or using the
- * stack slots for temporaries, since they are live and "used"
- * all the way to the end of the function.
- *
- * NOTE! On x86-64, all the arguments are in registers, so this
- * only matters on a 32-bit kernel.
- */
-#define asmlinkage_protect(n, ret, args...) \
-	__asmlinkage_protect##n(ret, ##args)
-#define __asmlinkage_protect_n(ret, args...) \
-	__asm__ __volatile__ ("" : "=r" (ret) : "0" (ret), ##args)
-#define __asmlinkage_protect0(ret) \
-	__asmlinkage_protect_n(ret)
-#define __asmlinkage_protect1(ret, arg1) \
-	__asmlinkage_protect_n(ret, "g" (arg1))
-#define __asmlinkage_protect2(ret, arg1, arg2) \
-	__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2))
-#define __asmlinkage_protect3(ret, arg1, arg2, arg3) \
-	__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3))
-#define __asmlinkage_protect4(ret, arg1, arg2, arg3, arg4) \
-	__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \
-			      "g" (arg4))
-#define __asmlinkage_protect5(ret, arg1, arg2, arg3, arg4, arg5) \
-	__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \
-			      "g" (arg4), "g" (arg5))
-#define __asmlinkage_protect6(ret, arg1, arg2, arg3, arg4, arg5, arg6) \
-	__asmlinkage_protect_n(ret, "g" (arg1), "g" (arg2), "g" (arg3), \
-			      "g" (arg4), "g" (arg5), "g" (arg6))
-
-#endif
-
-#ifdef CONFIG_X86_ALIGNMENT_16
-#define __ALIGN .align 16,0x90
-#define __ALIGN_STR ".align 16,0x90"
-#endif
-
-#endif /* ASM_X86__LINKAGE_H */
-
diff --git a/include/asm-x86/local.h b/include/asm-x86/local.h
deleted file mode 100644
index ae91994fd6c9..000000000000
--- a/include/asm-x86/local.h
+++ /dev/null
@@ -1,235 +0,0 @@
-#ifndef ASM_X86__LOCAL_H
-#define ASM_X86__LOCAL_H
-
-#include <linux/percpu.h>
-
-#include <asm/system.h>
-#include <asm/atomic.h>
-#include <asm/asm.h>
-
-typedef struct {
-	atomic_long_t a;
-} local_t;
-
-#define LOCAL_INIT(i)	{ ATOMIC_LONG_INIT(i) }
-
-#define local_read(l)	atomic_long_read(&(l)->a)
-#define local_set(l, i)	atomic_long_set(&(l)->a, (i))
-
-static inline void local_inc(local_t *l)
-{
-	asm volatile(_ASM_INC "%0"
-		     : "+m" (l->a.counter));
-}
-
-static inline void local_dec(local_t *l)
-{
-	asm volatile(_ASM_DEC "%0"
-		     : "+m" (l->a.counter));
-}
-
-static inline void local_add(long i, local_t *l)
-{
-	asm volatile(_ASM_ADD "%1,%0"
-		     : "+m" (l->a.counter)
-		     : "ir" (i));
-}
-
-static inline void local_sub(long i, local_t *l)
-{
-	asm volatile(_ASM_SUB "%1,%0"
-		     : "+m" (l->a.counter)
-		     : "ir" (i));
-}
-
-/**
- * local_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @l: pointer to type local_t
- *
- * Atomically subtracts @i from @l and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int local_sub_and_test(long i, local_t *l)
-{
-	unsigned char c;
-
-	asm volatile(_ASM_SUB "%2,%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
-}
-
-/**
- * local_dec_and_test - decrement and test
- * @l: pointer to type local_t
- *
- * Atomically decrements @l by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int local_dec_and_test(local_t *l)
-{
-	unsigned char c;
-
-	asm volatile(_ASM_DEC "%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
-}
-
-/**
- * local_inc_and_test - increment and test
- * @l: pointer to type local_t
- *
- * Atomically increments @l by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int local_inc_and_test(local_t *l)
-{
-	unsigned char c;
-
-	asm volatile(_ASM_INC "%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
-}
-
-/**
- * local_add_negative - add and test if negative
- * @i: integer value to add
- * @l: pointer to type local_t
- *
- * Atomically adds @i to @l and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int local_add_negative(long i, local_t *l)
-{
-	unsigned char c;
-
-	asm volatile(_ASM_ADD "%2,%0; sets %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
-}
-
-/**
- * local_add_return - add and return
- * @i: integer value to add
- * @l: pointer to type local_t
- *
- * Atomically adds @i to @l and returns @i + @l
- */
-static inline long local_add_return(long i, local_t *l)
-{
-	long __i;
-#ifdef CONFIG_M386
-	unsigned long flags;
-	if (unlikely(boot_cpu_data.x86 <= 3))
-		goto no_xadd;
-#endif
-	/* Modern 486+ processor */
-	__i = i;
-	asm volatile(_ASM_XADD "%0, %1;"
-		     : "+r" (i), "+m" (l->a.counter)
-		     : : "memory");
-	return i + __i;
-
-#ifdef CONFIG_M386
-no_xadd: /* Legacy 386 processor */
-	local_irq_save(flags);
-	__i = local_read(l);
-	local_set(l, i + __i);
-	local_irq_restore(flags);
-	return i + __i;
-#endif
-}
-
-static inline long local_sub_return(long i, local_t *l)
-{
-	return local_add_return(-i, l);
-}
-
-#define local_inc_return(l)  (local_add_return(1, l))
-#define local_dec_return(l)  (local_sub_return(1, l))
-
-#define local_cmpxchg(l, o, n) \
-	(cmpxchg_local(&((l)->a.counter), (o), (n)))
-/* Always has a lock prefix */
-#define local_xchg(l, n) (xchg(&((l)->a.counter), (n)))
-
-/**
- * local_add_unless - add unless the number is a given value
- * @l: pointer of type local_t
- * @a: the amount to add to l...
- * @u: ...unless l is equal to u.
- *
- * Atomically adds @a to @l, so long as it was not @u.
- * Returns non-zero if @l was not @u, and zero otherwise.
- */
-#define local_add_unless(l, a, u)				\
-({								\
-	long c, old;						\
-	c = local_read((l));					\
-	for (;;) {						\
-		if (unlikely(c == (u)))				\
-			break;					\
-		old = local_cmpxchg((l), c, c + (a));		\
-		if (likely(old == c))				\
-			break;					\
-		c = old;					\
-	}							\
-	c != (u);						\
-})
-#define local_inc_not_zero(l) local_add_unless((l), 1, 0)
-
-/* On x86_32, these are no better than the atomic variants.
- * On x86-64 these are better than the atomic variants on SMP kernels
- * because they dont use a lock prefix.
- */
-#define __local_inc(l)		local_inc(l)
-#define __local_dec(l)		local_dec(l)
-#define __local_add(i, l)	local_add((i), (l))
-#define __local_sub(i, l)	local_sub((i), (l))
-
-/* Use these for per-cpu local_t variables: on some archs they are
- * much more efficient than these naive implementations.  Note they take
- * a variable, not an address.
- *
- * X86_64: This could be done better if we moved the per cpu data directly
- * after GS.
- */
-
-/* Need to disable preemption for the cpu local counters otherwise we could
-   still access a variable of a previous CPU in a non atomic way. */
-#define cpu_local_wrap_v(l)		\
-({					\
-	local_t res__;			\
-	preempt_disable(); 		\
-	res__ = (l);			\
-	preempt_enable();		\
-	res__;				\
-})
-#define cpu_local_wrap(l)		\
-({					\
-	preempt_disable();		\
-	(l);				\
-	preempt_enable();		\
-})					\
-
-#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var((l))))
-#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var((l)), (i)))
-#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var((l))))
-#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var((l))))
-#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var((l))))
-#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var((l))))
-
-#define __cpu_local_inc(l)	cpu_local_inc((l))
-#define __cpu_local_dec(l)	cpu_local_dec((l))
-#define __cpu_local_add(i, l)	cpu_local_add((i), (l))
-#define __cpu_local_sub(i, l)	cpu_local_sub((i), (l))
-
-#endif /* ASM_X86__LOCAL_H */
diff --git a/include/asm-x86/mach-default/apm.h b/include/asm-x86/mach-default/apm.h
deleted file mode 100644
index 2aa61b54fbd5..000000000000
--- a/include/asm-x86/mach-default/apm.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- *  Machine specific APM BIOS functions for generic.
- *  Split out from apm.c by Osamu Tomita <tomita@cinet.co.jp>
- */
-
-#ifndef ASM_X86__MACH_DEFAULT__APM_H
-#define ASM_X86__MACH_DEFAULT__APM_H
-
-#ifdef APM_ZERO_SEGS
-#	define APM_DO_ZERO_SEGS \
-		"pushl %%ds\n\t" \
-		"pushl %%es\n\t" \
-		"xorl %%edx, %%edx\n\t" \
-		"mov %%dx, %%ds\n\t" \
-		"mov %%dx, %%es\n\t" \
-		"mov %%dx, %%fs\n\t" \
-		"mov %%dx, %%gs\n\t"
-#	define APM_DO_POP_SEGS \
-		"popl %%es\n\t" \
-		"popl %%ds\n\t"
-#else
-#	define APM_DO_ZERO_SEGS
-#	define APM_DO_POP_SEGS
-#endif
-
-static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
-					u32 *eax, u32 *ebx, u32 *ecx,
-					u32 *edx, u32 *esi)
-{
-	/*
-	 * N.B. We do NOT need a cld after the BIOS call
-	 * because we always save and restore the flags.
-	 */
-	__asm__ __volatile__(APM_DO_ZERO_SEGS
-		"pushl %%edi\n\t"
-		"pushl %%ebp\n\t"
-		"lcall *%%cs:apm_bios_entry\n\t"
-		"setc %%al\n\t"
-		"popl %%ebp\n\t"
-		"popl %%edi\n\t"
-		APM_DO_POP_SEGS
-		: "=a" (*eax), "=b" (*ebx), "=c" (*ecx), "=d" (*edx),
-		  "=S" (*esi)
-		: "a" (func), "b" (ebx_in), "c" (ecx_in)
-		: "memory", "cc");
-}
-
-static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
-						u32 ecx_in, u32 *eax)
-{
-	int	cx, dx, si;
-	u8	error;
-
-	/*
-	 * N.B. We do NOT need a cld after the BIOS call
-	 * because we always save and restore the flags.
-	 */
-	__asm__ __volatile__(APM_DO_ZERO_SEGS
-		"pushl %%edi\n\t"
-		"pushl %%ebp\n\t"
-		"lcall *%%cs:apm_bios_entry\n\t"
-		"setc %%bl\n\t"
-		"popl %%ebp\n\t"
-		"popl %%edi\n\t"
-		APM_DO_POP_SEGS
-		: "=a" (*eax), "=b" (error), "=c" (cx), "=d" (dx),
-		  "=S" (si)
-		: "a" (func), "b" (ebx_in), "c" (ecx_in)
-		: "memory", "cc");
-	return error;
-}
-
-#endif /* ASM_X86__MACH_DEFAULT__APM_H */
diff --git a/include/asm-x86/mach-default/do_timer.h b/include/asm-x86/mach-default/do_timer.h
deleted file mode 100644
index 23ecda0b28a0..000000000000
--- a/include/asm-x86/mach-default/do_timer.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* defines for inline arch setup functions */
-#include <linux/clockchips.h>
-
-#include <asm/i8259.h>
-#include <asm/i8253.h>
-
-/**
- * do_timer_interrupt_hook - hook into timer tick
- *
- * Call the pit clock event handler. see asm/i8253.h
- **/
-
-static inline void do_timer_interrupt_hook(void)
-{
-	global_clock_event->event_handler(global_clock_event);
-}
diff --git a/include/asm-x86/mach-default/entry_arch.h b/include/asm-x86/mach-default/entry_arch.h
deleted file mode 100644
index 6b1add8e31dd..000000000000
--- a/include/asm-x86/mach-default/entry_arch.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * This file is designed to contain the BUILD_INTERRUPT specifications for
- * all of the extra named interrupt vectors used by the architecture.
- * Usually this is the Inter Process Interrupts (IPIs)
- */
-
-/*
- * The following vectors are part of the Linux architecture, there
- * is no hardware IRQ pin equivalent for them, they are triggered
- * through the ICC by us (IPIs)
- */
-#ifdef CONFIG_X86_SMP
-BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
-BUILD_INTERRUPT(invalidate_interrupt,INVALIDATE_TLB_VECTOR)
-BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
-BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
-BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
-#endif
-
-/*
- * every pentium local APIC has two 'local interrupts', with a
- * soft-definable vector attached to both interrupts, one of
- * which is a timer interrupt, the other one is error counter
- * overflow. Linux uses the local APIC timer interrupt to get
- * a much simpler SMP time architecture:
- */
-#ifdef CONFIG_X86_LOCAL_APIC
-BUILD_INTERRUPT(apic_timer_interrupt,LOCAL_TIMER_VECTOR)
-BUILD_INTERRUPT(error_interrupt,ERROR_APIC_VECTOR)
-BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
-
-#ifdef CONFIG_X86_MCE_P4THERMAL
-BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
-#endif
-
-#endif
diff --git a/include/asm-x86/mach-default/mach_apic.h b/include/asm-x86/mach-default/mach_apic.h
deleted file mode 100644
index 3c66f2cdaec1..000000000000
--- a/include/asm-x86/mach-default/mach_apic.h
+++ /dev/null
@@ -1,156 +0,0 @@
-#ifndef ASM_X86__MACH_DEFAULT__MACH_APIC_H
-#define ASM_X86__MACH_DEFAULT__MACH_APIC_H
-
-#ifdef CONFIG_X86_LOCAL_APIC
-
-#include <mach_apicdef.h>
-#include <asm/smp.h>
-
-#define APIC_DFR_VALUE	(APIC_DFR_FLAT)
-
-static inline cpumask_t target_cpus(void)
-{ 
-#ifdef CONFIG_SMP
-	return cpu_online_map;
-#else
-	return cpumask_of_cpu(0);
-#endif
-} 
-
-#define NO_BALANCE_IRQ (0)
-#define esr_disable (0)
-
-#ifdef CONFIG_X86_64
-#include <asm/genapic.h>
-#define INT_DELIVERY_MODE (genapic->int_delivery_mode)
-#define INT_DEST_MODE (genapic->int_dest_mode)
-#define TARGET_CPUS	  (genapic->target_cpus())
-#define apic_id_registered (genapic->apic_id_registered)
-#define init_apic_ldr (genapic->init_apic_ldr)
-#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
-#define phys_pkg_id	(genapic->phys_pkg_id)
-#define vector_allocation_domain    (genapic->vector_allocation_domain)
-#define read_apic_id()  (GET_APIC_ID(apic_read(APIC_ID)))
-#define send_IPI_self (genapic->send_IPI_self)
-extern void setup_apic_routing(void);
-#else
-#define INT_DELIVERY_MODE dest_LowestPrio
-#define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
-#define TARGET_CPUS (target_cpus())
-/*
- * Set up the logical destination ID.
- *
- * Intel recommends to set DFR, LDR and TPR before enabling
- * an APIC.  See e.g. "AP-388 82489DX User's Manual" (Intel
- * document number 292116).  So here it goes...
- */
-static inline void init_apic_ldr(void)
-{
-	unsigned long val;
-
-	apic_write(APIC_DFR, APIC_DFR_VALUE);
-	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-	val |= SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
-	apic_write(APIC_LDR, val);
-}
-
-static inline int apic_id_registered(void)
-{
-	return physid_isset(read_apic_id(), phys_cpu_present_map);
-}
-
-static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
-{
-	return cpus_addr(cpumask)[0];
-}
-
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-static inline void setup_apic_routing(void)
-{
-#ifdef CONFIG_X86_IO_APIC
-	printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
-					"Flat", nr_ioapics);
-#endif
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-#ifdef CONFIG_SMP
-	return apicid_2_node[hard_smp_processor_id()];
-#else
-	return 0;
-#endif
-}
-
-static inline cpumask_t vector_allocation_domain(int cpu)
-{
-        /* Careful. Some cpus do not strictly honor the set of cpus
-         * specified in the interrupt destination when using lowest
-         * priority interrupt delivery mode.
-         *
-         * In particular there was a hyperthreading cpu observed to
-         * deliver interrupts to the wrong hyperthread when only one
-         * hyperthread was specified in the interrupt desitination.
-         */
-        cpumask_t domain = { { [0] = APIC_ALL_CPUS, } };
-        return domain;
-}
-#endif
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return physid_isset(apicid, bitmap);
-}
-
-static inline unsigned long check_apicid_present(int bit)
-{
-	return physid_isset(bit, phys_cpu_present_map);
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-	return phys_map;
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-	return 0;
-}
-
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-	return 1 << cpu;
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (mps_cpu < NR_CPUS && cpu_present(mps_cpu))
-		return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
-	else
-		return BAD_APICID;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int phys_apicid)
-{
-	return physid_mask_of_physid(phys_apicid);
-}
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-	return physid_isset(boot_cpu_physical_apicid, phys_cpu_present_map);
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-#endif /* CONFIG_X86_LOCAL_APIC */
-#endif /* ASM_X86__MACH_DEFAULT__MACH_APIC_H */
diff --git a/include/asm-x86/mach-default/mach_apicdef.h b/include/asm-x86/mach-default/mach_apicdef.h
deleted file mode 100644
index 0c2d41c41b20..000000000000
--- a/include/asm-x86/mach-default/mach_apicdef.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef ASM_X86__MACH_DEFAULT__MACH_APICDEF_H
-#define ASM_X86__MACH_DEFAULT__MACH_APICDEF_H
-
-#include <asm/apic.h>
-
-#ifdef CONFIG_X86_64
-#define	APIC_ID_MASK		(genapic->apic_id_mask)
-#define GET_APIC_ID(x)		(genapic->get_apic_id(x))
-#define	SET_APIC_ID(x)		(genapic->set_apic_id(x))
-#else
-#define		APIC_ID_MASK		(0xF<<24)
-static inline unsigned get_apic_id(unsigned long x) 
-{
-	unsigned int ver = GET_APIC_VERSION(apic_read(APIC_LVR));
-	if (APIC_XAPIC(ver))
-		return (((x)>>24)&0xFF);
-	else
-		return (((x)>>24)&0xF);
-} 
-
-#define		GET_APIC_ID(x)	get_apic_id(x)
-#endif
-
-#endif /* ASM_X86__MACH_DEFAULT__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-default/mach_ipi.h b/include/asm-x86/mach-default/mach_ipi.h
deleted file mode 100644
index 674bc7e50c35..000000000000
--- a/include/asm-x86/mach-default/mach_ipi.h
+++ /dev/null
@@ -1,64 +0,0 @@
-#ifndef ASM_X86__MACH_DEFAULT__MACH_IPI_H
-#define ASM_X86__MACH_DEFAULT__MACH_IPI_H
-
-/* Avoid include hell */
-#define NMI_VECTOR 0x02
-
-void send_IPI_mask_bitmask(cpumask_t mask, int vector);
-void __send_IPI_shortcut(unsigned int shortcut, int vector);
-
-extern int no_broadcast;
-
-#ifdef CONFIG_X86_64
-#include <asm/genapic.h>
-#define send_IPI_mask (genapic->send_IPI_mask)
-#else
-static inline void send_IPI_mask(cpumask_t mask, int vector)
-{
-	send_IPI_mask_bitmask(mask, vector);
-}
-#endif
-
-static inline void __local_send_IPI_allbutself(int vector)
-{
-	if (no_broadcast || vector == NMI_VECTOR) {
-		cpumask_t mask = cpu_online_map;
-
-		cpu_clear(smp_processor_id(), mask);
-		send_IPI_mask(mask, vector);
-	} else
-		__send_IPI_shortcut(APIC_DEST_ALLBUT, vector);
-}
-
-static inline void __local_send_IPI_all(int vector)
-{
-	if (no_broadcast || vector == NMI_VECTOR)
-		send_IPI_mask(cpu_online_map, vector);
-	else
-		__send_IPI_shortcut(APIC_DEST_ALLINC, vector);
-}
-
-#ifdef CONFIG_X86_64
-#define send_IPI_allbutself (genapic->send_IPI_allbutself)
-#define send_IPI_all (genapic->send_IPI_all)
-#else
-static inline void send_IPI_allbutself(int vector)
-{
-	/*
-	 * if there are no other CPUs in the system then we get an APIC send 
-	 * error if we try to broadcast, thus avoid sending IPIs in this case.
-	 */
-	if (!(num_online_cpus() > 1))
-		return;
-
-	__local_send_IPI_allbutself(vector);
-	return;
-}
-
-static inline void send_IPI_all(int vector)
-{
-	__local_send_IPI_all(vector);
-}
-#endif
-
-#endif /* ASM_X86__MACH_DEFAULT__MACH_IPI_H */
diff --git a/include/asm-x86/mach-default/mach_mpparse.h b/include/asm-x86/mach-default/mach_mpparse.h
deleted file mode 100644
index 9c381f2815ac..000000000000
--- a/include/asm-x86/mach-default/mach_mpparse.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H
-#define ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H
-
-static inline int mps_oem_check(struct mp_config_table *mpc, char *oem, 
-		char *productid)
-{
-	return 0;
-}
-
-/* Hook from generic ACPI tables.c */
-static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-	return 0;
-}
-
-
-#endif /* ASM_X86__MACH_DEFAULT__MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-default/mach_mpspec.h b/include/asm-x86/mach-default/mach_mpspec.h
deleted file mode 100644
index d77646f011f1..000000000000
--- a/include/asm-x86/mach-default/mach_mpspec.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H
-#define ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-#if CONFIG_BASE_SMALL == 0
-#define MAX_MP_BUSSES 256
-#else
-#define MAX_MP_BUSSES 32
-#endif
-
-#endif /* ASM_X86__MACH_DEFAULT__MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-default/mach_timer.h b/include/asm-x86/mach-default/mach_timer.h
deleted file mode 100644
index 990b15833834..000000000000
--- a/include/asm-x86/mach-default/mach_timer.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
- *  Machine specific calibrate_tsc() for generic.
- *  Split out from timer_tsc.c by Osamu Tomita <tomita@cinet.co.jp>
- */
-/* ------ Calibrate the TSC ------- 
- * Return 2^32 * (1 / (TSC clocks per usec)) for do_fast_gettimeoffset().
- * Too much 64-bit arithmetic here to do this cleanly in C, and for
- * accuracy's sake we want to keep the overhead on the CTC speaker (channel 2)
- * output busy loop as low as possible. We avoid reading the CTC registers
- * directly because of the awkward 8-bit access mechanism of the 82C54
- * device.
- */
-#ifndef ASM_X86__MACH_DEFAULT__MACH_TIMER_H
-#define ASM_X86__MACH_DEFAULT__MACH_TIMER_H
-
-#define CALIBRATE_TIME_MSEC 30 /* 30 msecs */
-#define CALIBRATE_LATCH	\
-	((CLOCK_TICK_RATE * CALIBRATE_TIME_MSEC + 1000/2)/1000)
-
-static inline void mach_prepare_counter(void)
-{
-       /* Set the Gate high, disable speaker */
-	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
-
-	/*
-	 * Now let's take care of CTC channel 2
-	 *
-	 * Set the Gate high, program CTC channel 2 for mode 0,
-	 * (interrupt on terminal count mode), binary count,
-	 * load 5 * LATCH count, (LSB and MSB) to begin countdown.
-	 *
-	 * Some devices need a delay here.
-	 */
-	outb(0xb0, 0x43);			/* binary, mode 0, LSB/MSB, Ch 2 */
-	outb_p(CALIBRATE_LATCH & 0xff, 0x42);	/* LSB of count */
-	outb_p(CALIBRATE_LATCH >> 8, 0x42);       /* MSB of count */
-}
-
-static inline void mach_countup(unsigned long *count_p)
-{
-	unsigned long count = 0;
-	do {
-		count++;
-	} while ((inb_p(0x61) & 0x20) == 0);
-	*count_p = count;
-}
-
-#endif /* ASM_X86__MACH_DEFAULT__MACH_TIMER_H */
diff --git a/include/asm-x86/mach-default/mach_traps.h b/include/asm-x86/mach-default/mach_traps.h
deleted file mode 100644
index ff8778f26b84..000000000000
--- a/include/asm-x86/mach-default/mach_traps.h
+++ /dev/null
@@ -1,33 +0,0 @@
-/*
- *  Machine specific NMI handling for generic.
- *  Split out from traps.c by Osamu Tomita <tomita@cinet.co.jp>
- */
-#ifndef ASM_X86__MACH_DEFAULT__MACH_TRAPS_H
-#define ASM_X86__MACH_DEFAULT__MACH_TRAPS_H
-
-#include <asm/mc146818rtc.h>
-
-static inline unsigned char get_nmi_reason(void)
-{
-	return inb(0x61);
-}
-
-static inline void reassert_nmi(void)
-{
-	int old_reg = -1;
-
-	if (do_i_have_lock_cmos())
-		old_reg = current_lock_cmos_reg();
-	else
-		lock_cmos(0); /* register doesn't matter here */
-	outb(0x8f, 0x70);
-	inb(0x71);		/* dummy */
-	outb(0x0f, 0x70);
-	inb(0x71);		/* dummy */
-	if (old_reg >= 0)
-		outb(old_reg, 0x70);
-	else
-		unlock_cmos();
-}
-
-#endif /* ASM_X86__MACH_DEFAULT__MACH_TRAPS_H */
diff --git a/include/asm-x86/mach-default/mach_wakecpu.h b/include/asm-x86/mach-default/mach_wakecpu.h
deleted file mode 100644
index 361b810f5160..000000000000
--- a/include/asm-x86/mach-default/mach_wakecpu.h
+++ /dev/null
@@ -1,42 +0,0 @@
-#ifndef ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H
-#define ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H
-
-/* 
- * This file copes with machines that wakeup secondary CPUs by the
- * INIT, INIT, STARTUP sequence.
- */
-
-#define WAKE_SECONDARY_VIA_INIT
-
-#define TRAMPOLINE_LOW phys_to_virt(0x467)
-#define TRAMPOLINE_HIGH phys_to_virt(0x469)
-
-#define boot_cpu_apicid boot_cpu_physical_apicid
-
-static inline void wait_for_init_deassert(atomic_t *deassert)
-{
-	while (!atomic_read(deassert))
-		cpu_relax();
-	return;
-}
-
-/* Nothing to do for most platforms, since cleared by the INIT cycle */
-static inline void smp_callin_clear_local_apic(void)
-{
-}
-
-static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
-{
-}
-
-#if APIC_DEBUG
- #define inquire_remote_apic(apicid) __inquire_remote_apic(apicid)
-#else
- #define inquire_remote_apic(apicid) {}
-#endif
-
-#endif /* ASM_X86__MACH_DEFAULT__MACH_WAKECPU_H */
diff --git a/include/asm-x86/mach-default/pci-functions.h b/include/asm-x86/mach-default/pci-functions.h
deleted file mode 100644
index ed0bab427354..000000000000
--- a/include/asm-x86/mach-default/pci-functions.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- *	PCI BIOS function numbering for conventional PCI BIOS 
- *	systems
- */
-
-#define PCIBIOS_PCI_FUNCTION_ID 	0xb1XX
-#define PCIBIOS_PCI_BIOS_PRESENT 	0xb101
-#define PCIBIOS_FIND_PCI_DEVICE		0xb102
-#define PCIBIOS_FIND_PCI_CLASS_CODE	0xb103
-#define PCIBIOS_GENERATE_SPECIAL_CYCLE	0xb106
-#define PCIBIOS_READ_CONFIG_BYTE	0xb108
-#define PCIBIOS_READ_CONFIG_WORD	0xb109
-#define PCIBIOS_READ_CONFIG_DWORD	0xb10a
-#define PCIBIOS_WRITE_CONFIG_BYTE	0xb10b
-#define PCIBIOS_WRITE_CONFIG_WORD	0xb10c
-#define PCIBIOS_WRITE_CONFIG_DWORD	0xb10d
-#define PCIBIOS_GET_ROUTING_OPTIONS	0xb10e
-#define PCIBIOS_SET_PCI_HW_INT		0xb10f
-
diff --git a/include/asm-x86/mach-default/setup_arch.h b/include/asm-x86/mach-default/setup_arch.h
deleted file mode 100644
index 38846208b548..000000000000
--- a/include/asm-x86/mach-default/setup_arch.h
+++ /dev/null
@@ -1,3 +0,0 @@
-/* Hook to call BIOS initialisation function */
-
-/* no action for generic */
diff --git a/include/asm-x86/mach-default/smpboot_hooks.h b/include/asm-x86/mach-default/smpboot_hooks.h
deleted file mode 100644
index dbab36d64d48..000000000000
--- a/include/asm-x86/mach-default/smpboot_hooks.h
+++ /dev/null
@@ -1,59 +0,0 @@
-/* two abstractions specific to kernel/smpboot.c, mainly to cater to visws
- * which needs to alter them. */
-
-static inline void smpboot_clear_io_apic_irqs(void)
-{
-#ifdef CONFIG_X86_IO_APIC
-	io_apic_irqs = 0;
-#endif
-}
-
-static inline void smpboot_setup_warm_reset_vector(unsigned long start_eip)
-{
-	CMOS_WRITE(0xa, 0xf);
-	local_flush_tlb();
-	pr_debug("1.\n");
-	*((volatile unsigned short *) TRAMPOLINE_HIGH) = start_eip >> 4;
-	pr_debug("2.\n");
-	*((volatile unsigned short *) TRAMPOLINE_LOW) = start_eip & 0xf;
-	pr_debug("3.\n");
-}
-
-static inline void smpboot_restore_warm_reset_vector(void)
-{
-	/*
-	 * Install writable page 0 entry to set BIOS data area.
-	 */
-	local_flush_tlb();
-
-	/*
-	 * Paranoid:  Set warm reset code and vector here back
-	 * to default values.
-	 */
-	CMOS_WRITE(0, 0xf);
-
-	*((volatile long *) phys_to_virt(0x467)) = 0;
-}
-
-static inline void __init smpboot_setup_io_apic(void)
-{
-#ifdef CONFIG_X86_IO_APIC
-	/*
-	 * Here we can be sure that there is an IO-APIC in the system. Let's
-	 * go and set it up:
-	 */
-	if (!skip_ioapic_setup && nr_ioapics)
-		setup_IO_APIC();
-	else {
-		nr_ioapics = 0;
-		localise_nmi_watchdog();
-	}
-#endif
-}
-
-static inline void smpboot_clear_io_apic(void)
-{
-#ifdef CONFIG_X86_IO_APIC
-	nr_ioapics = 0;
-#endif
-}
diff --git a/include/asm-x86/mach-generic/gpio.h b/include/asm-x86/mach-generic/gpio.h
deleted file mode 100644
index 6ce0f7786ef8..000000000000
--- a/include/asm-x86/mach-generic/gpio.h
+++ /dev/null
@@ -1,15 +0,0 @@
-#ifndef ASM_X86__MACH_GENERIC__GPIO_H
-#define ASM_X86__MACH_GENERIC__GPIO_H
-
-int gpio_request(unsigned gpio, const char *label);
-void gpio_free(unsigned gpio);
-int gpio_direction_input(unsigned gpio);
-int gpio_direction_output(unsigned gpio, int value);
-int gpio_get_value(unsigned gpio);
-void gpio_set_value(unsigned gpio, int value);
-int gpio_to_irq(unsigned gpio);
-int irq_to_gpio(unsigned irq);
-
-#include <asm-generic/gpio.h>           /* cansleep wrappers */
-
-#endif /* ASM_X86__MACH_GENERIC__GPIO_H */
diff --git a/include/asm-x86/mach-generic/mach_apic.h b/include/asm-x86/mach-generic/mach_apic.h
deleted file mode 100644
index 5085b52da301..000000000000
--- a/include/asm-x86/mach-generic/mach_apic.h
+++ /dev/null
@@ -1,33 +0,0 @@
-#ifndef ASM_X86__MACH_GENERIC__MACH_APIC_H
-#define ASM_X86__MACH_GENERIC__MACH_APIC_H
-
-#include <asm/genapic.h>
-
-#define esr_disable (genapic->ESR_DISABLE)
-#define NO_BALANCE_IRQ (genapic->no_balance_irq)
-#define INT_DELIVERY_MODE (genapic->int_delivery_mode)
-#define INT_DEST_MODE (genapic->int_dest_mode)
-#undef APIC_DEST_LOGICAL
-#define APIC_DEST_LOGICAL (genapic->apic_destination_logical)
-#define TARGET_CPUS	  (genapic->target_cpus())
-#define apic_id_registered (genapic->apic_id_registered)
-#define init_apic_ldr (genapic->init_apic_ldr)
-#define ioapic_phys_id_map (genapic->ioapic_phys_id_map)
-#define setup_apic_routing (genapic->setup_apic_routing)
-#define multi_timer_check (genapic->multi_timer_check)
-#define apicid_to_node (genapic->apicid_to_node)
-#define cpu_to_logical_apicid (genapic->cpu_to_logical_apicid) 
-#define cpu_present_to_apicid (genapic->cpu_present_to_apicid)
-#define apicid_to_cpu_present (genapic->apicid_to_cpu_present)
-#define setup_portio_remap (genapic->setup_portio_remap)
-#define check_apicid_present (genapic->check_apicid_present)
-#define check_phys_apicid_present (genapic->check_phys_apicid_present)
-#define check_apicid_used (genapic->check_apicid_used)
-#define cpu_mask_to_apicid (genapic->cpu_mask_to_apicid)
-#define vector_allocation_domain (genapic->vector_allocation_domain)
-#define enable_apic_mode (genapic->enable_apic_mode)
-#define phys_pkg_id (genapic->phys_pkg_id)
-
-extern void generic_bigsmp_probe(void);
-
-#endif /* ASM_X86__MACH_GENERIC__MACH_APIC_H */
diff --git a/include/asm-x86/mach-generic/mach_apicdef.h b/include/asm-x86/mach-generic/mach_apicdef.h
deleted file mode 100644
index 1657f38b8f27..000000000000
--- a/include/asm-x86/mach-generic/mach_apicdef.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef ASM_X86__MACH_GENERIC__MACH_APICDEF_H
-#define ASM_X86__MACH_GENERIC__MACH_APICDEF_H
-
-#ifndef APIC_DEFINITION
-#include <asm/genapic.h>
-
-#define GET_APIC_ID (genapic->get_apic_id)
-#define APIC_ID_MASK (genapic->apic_id_mask)
-#endif
-
-#endif /* ASM_X86__MACH_GENERIC__MACH_APICDEF_H */
diff --git a/include/asm-x86/mach-generic/mach_ipi.h b/include/asm-x86/mach-generic/mach_ipi.h
deleted file mode 100644
index f67433dbd65f..000000000000
--- a/include/asm-x86/mach-generic/mach_ipi.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef ASM_X86__MACH_GENERIC__MACH_IPI_H
-#define ASM_X86__MACH_GENERIC__MACH_IPI_H
-
-#include <asm/genapic.h>
-
-#define send_IPI_mask (genapic->send_IPI_mask)
-#define send_IPI_allbutself (genapic->send_IPI_allbutself)
-#define send_IPI_all (genapic->send_IPI_all)
-
-#endif /* ASM_X86__MACH_GENERIC__MACH_IPI_H */
diff --git a/include/asm-x86/mach-generic/mach_mpparse.h b/include/asm-x86/mach-generic/mach_mpparse.h
deleted file mode 100644
index 3115564e557c..000000000000
--- a/include/asm-x86/mach-generic/mach_mpparse.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef ASM_X86__MACH_GENERIC__MACH_MPPARSE_H
-#define ASM_X86__MACH_GENERIC__MACH_MPPARSE_H
-
-
-extern int mps_oem_check(struct mp_config_table *mpc, char *oem,
-			 char *productid);
-
-extern int acpi_madt_oem_check(char *oem_id, char *oem_table_id);
-
-#endif /* ASM_X86__MACH_GENERIC__MACH_MPPARSE_H */
diff --git a/include/asm-x86/mach-generic/mach_mpspec.h b/include/asm-x86/mach-generic/mach_mpspec.h
deleted file mode 100644
index 6061b153613e..000000000000
--- a/include/asm-x86/mach-generic/mach_mpspec.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef ASM_X86__MACH_GENERIC__MACH_MPSPEC_H
-#define ASM_X86__MACH_GENERIC__MACH_MPSPEC_H
-
-#define MAX_IRQ_SOURCES 256
-
-/* Summit or generic (i.e. installer) kernels need lots of bus entries. */
-/* Maximum 256 PCI busses, plus 1 ISA bus in each of 4 cabinets. */
-#define MAX_MP_BUSSES 260
-
-extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
-				char *productid);
-#endif /* ASM_X86__MACH_GENERIC__MACH_MPSPEC_H */
diff --git a/include/asm-x86/mach-rdc321x/gpio.h b/include/asm-x86/mach-rdc321x/gpio.h
deleted file mode 100644
index 94b6cdf532e2..000000000000
--- a/include/asm-x86/mach-rdc321x/gpio.h
+++ /dev/null
@@ -1,60 +0,0 @@
-#ifndef ASM_X86__MACH_RDC321X__GPIO_H
-#define ASM_X86__MACH_RDC321X__GPIO_H
-
-#include <linux/kernel.h>
-
-extern int rdc_gpio_get_value(unsigned gpio);
-extern void rdc_gpio_set_value(unsigned gpio, int value);
-extern int rdc_gpio_direction_input(unsigned gpio);
-extern int rdc_gpio_direction_output(unsigned gpio, int value);
-extern int rdc_gpio_request(unsigned gpio, const char *label);
-extern void rdc_gpio_free(unsigned gpio);
-extern void __init rdc321x_gpio_setup(void);
-
-/* Wrappers for the arch-neutral GPIO API */
-
-static inline int gpio_request(unsigned gpio, const char *label)
-{
-	return rdc_gpio_request(gpio, label);
-}
-
-static inline void gpio_free(unsigned gpio)
-{
-	might_sleep();
-	rdc_gpio_free(gpio);
-}
-
-static inline int gpio_direction_input(unsigned gpio)
-{
-	return rdc_gpio_direction_input(gpio);
-}
-
-static inline int gpio_direction_output(unsigned gpio, int value)
-{
-	return rdc_gpio_direction_output(gpio, value);
-}
-
-static inline int gpio_get_value(unsigned gpio)
-{
-	return rdc_gpio_get_value(gpio);
-}
-
-static inline void gpio_set_value(unsigned gpio, int value)
-{
-	rdc_gpio_set_value(gpio, value);
-}
-
-static inline int gpio_to_irq(unsigned gpio)
-{
-	return gpio;
-}
-
-static inline int irq_to_gpio(unsigned irq)
-{
-	return irq;
-}
-
-/* For cansleep */
-#include <asm-generic/gpio.h>
-
-#endif /* ASM_X86__MACH_RDC321X__GPIO_H */
diff --git a/include/asm-x86/mach-rdc321x/rdc321x_defs.h b/include/asm-x86/mach-rdc321x/rdc321x_defs.h
deleted file mode 100644
index c8e9c8bed3d0..000000000000
--- a/include/asm-x86/mach-rdc321x/rdc321x_defs.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#define PFX	"rdc321x: "
-
-/* General purpose configuration and data registers */
-#define RDC3210_CFGREG_ADDR     0x0CF8
-#define RDC3210_CFGREG_DATA     0x0CFC
-
-#define RDC321X_GPIO_CTRL_REG1	0x48
-#define RDC321X_GPIO_CTRL_REG2	0x84
-#define RDC321X_GPIO_DATA_REG1	0x4c
-#define RDC321X_GPIO_DATA_REG2	0x88
-
-#define RDC321X_MAX_GPIO	58
diff --git a/include/asm-x86/mach-voyager/do_timer.h b/include/asm-x86/mach-voyager/do_timer.h
deleted file mode 100644
index 9e5a459fd15b..000000000000
--- a/include/asm-x86/mach-voyager/do_timer.h
+++ /dev/null
@@ -1,17 +0,0 @@
-/* defines for inline arch setup functions */
-#include <linux/clockchips.h>
-
-#include <asm/voyager.h>
-#include <asm/i8253.h>
-
-/**
- * do_timer_interrupt_hook - hook into timer tick
- *
- * Call the pit clock event handler. see asm/i8253.h
- **/
-static inline void do_timer_interrupt_hook(void)
-{
-	global_clock_event->event_handler(global_clock_event);
-	voyager_timer_interrupt();
-}
-
diff --git a/include/asm-x86/mach-voyager/entry_arch.h b/include/asm-x86/mach-voyager/entry_arch.h
deleted file mode 100644
index ae52624b5937..000000000000
--- a/include/asm-x86/mach-voyager/entry_arch.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* Copyright (C) 2002
- *
- * Author: James.Bottomley@HansenPartnership.com
- *
- * linux/arch/i386/voyager/entry_arch.h
- *
- * This file builds the VIC and QIC CPI gates
- */
-
-/* initialise the voyager interrupt gates 
- *
- * This uses the macros in irq.h to set up assembly jump gates.  The
- * calls are then redirected to the same routine with smp_ prefixed */
-BUILD_INTERRUPT(vic_sys_interrupt, VIC_SYS_INT)
-BUILD_INTERRUPT(vic_cmn_interrupt, VIC_CMN_INT)
-BUILD_INTERRUPT(vic_cpi_interrupt, VIC_CPI_LEVEL0);
-
-/* do all the QIC interrupts */
-BUILD_INTERRUPT(qic_timer_interrupt, QIC_TIMER_CPI);
-BUILD_INTERRUPT(qic_invalidate_interrupt, QIC_INVALIDATE_CPI);
-BUILD_INTERRUPT(qic_reschedule_interrupt, QIC_RESCHEDULE_CPI);
-BUILD_INTERRUPT(qic_enable_irq_interrupt, QIC_ENABLE_IRQ_CPI);
-BUILD_INTERRUPT(qic_call_function_interrupt, QIC_CALL_FUNCTION_CPI);
-BUILD_INTERRUPT(qic_call_function_single_interrupt, QIC_CALL_FUNCTION_SINGLE_CPI);
diff --git a/include/asm-x86/mach-voyager/setup_arch.h b/include/asm-x86/mach-voyager/setup_arch.h
deleted file mode 100644
index 71729ca05cd7..000000000000
--- a/include/asm-x86/mach-voyager/setup_arch.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#include <asm/voyager.h>
-#include <asm/setup.h>
-#define VOYAGER_BIOS_INFO ((struct voyager_bios_info *) \
-			(&boot_params.apm_bios_info))
-
-/* Hook to call BIOS initialisation function */
-
-/* for voyager, pass the voyager BIOS/SUS info area to the detection
- * routines */
-
-#define ARCH_SETUP	voyager_detect(VOYAGER_BIOS_INFO);
-
diff --git a/include/asm-x86/math_emu.h b/include/asm-x86/math_emu.h
deleted file mode 100644
index 5768d8e95c8c..000000000000
--- a/include/asm-x86/math_emu.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef ASM_X86__MATH_EMU_H
-#define ASM_X86__MATH_EMU_H
-
-/* This structure matches the layout of the data saved to the stack
-   following a device-not-present interrupt, part of it saved
-   automatically by the 80386/80486.
-   */
-struct info {
-	long ___orig_eip;
-	long ___ebx;
-	long ___ecx;
-	long ___edx;
-	long ___esi;
-	long ___edi;
-	long ___ebp;
-	long ___eax;
-	long ___ds;
-	long ___es;
-	long ___fs;
-	long ___orig_eax;
-	long ___eip;
-	long ___cs;
-	long ___eflags;
-	long ___esp;
-	long ___ss;
-	long ___vm86_es; /* This and the following only in vm86 mode */
-	long ___vm86_ds;
-	long ___vm86_fs;
-	long ___vm86_gs;
-};
-#endif /* ASM_X86__MATH_EMU_H */
diff --git a/include/asm-x86/mc146818rtc.h b/include/asm-x86/mc146818rtc.h
deleted file mode 100644
index a995f33176cd..000000000000
--- a/include/asm-x86/mc146818rtc.h
+++ /dev/null
@@ -1,104 +0,0 @@
-/*
- * Machine dependent access functions for RTC registers.
- */
-#ifndef ASM_X86__MC146818RTC_H
-#define ASM_X86__MC146818RTC_H
-
-#include <asm/io.h>
-#include <asm/system.h>
-#include <asm/processor.h>
-#include <linux/mc146818rtc.h>
-
-#ifndef RTC_PORT
-#define RTC_PORT(x)	(0x70 + (x))
-#define RTC_ALWAYS_BCD	1	/* RTC operates in binary mode */
-#endif
-
-#if defined(CONFIG_X86_32) && defined(__HAVE_ARCH_CMPXCHG)
-/*
- * This lock provides nmi access to the CMOS/RTC registers.  It has some
- * special properties.  It is owned by a CPU and stores the index register
- * currently being accessed (if owned).  The idea here is that it works
- * like a normal lock (normally).  However, in an NMI, the NMI code will
- * first check to see if its CPU owns the lock, meaning that the NMI
- * interrupted during the read/write of the device.  If it does, it goes ahead
- * and performs the access and then restores the index register.  If it does
- * not, it locks normally.
- *
- * Note that since we are working with NMIs, we need this lock even in
- * a non-SMP machine just to mark that the lock is owned.
- *
- * This only works with compare-and-swap.  There is no other way to
- * atomically claim the lock and set the owner.
- */
-#include <linux/smp.h>
-extern volatile unsigned long cmos_lock;
-
-/*
- * All of these below must be called with interrupts off, preempt
- * disabled, etc.
- */
-
-static inline void lock_cmos(unsigned char reg)
-{
-	unsigned long new;
-	new = ((smp_processor_id() + 1) << 8) | reg;
-	for (;;) {
-		if (cmos_lock) {
-			cpu_relax();
-			continue;
-		}
-		if (__cmpxchg(&cmos_lock, 0, new, sizeof(cmos_lock)) == 0)
-			return;
-	}
-}
-
-static inline void unlock_cmos(void)
-{
-	cmos_lock = 0;
-}
-
-static inline int do_i_have_lock_cmos(void)
-{
-	return (cmos_lock >> 8) == (smp_processor_id() + 1);
-}
-
-static inline unsigned char current_lock_cmos_reg(void)
-{
-	return cmos_lock & 0xff;
-}
-
-#define lock_cmos_prefix(reg)			\
-	do {					\
-		unsigned long cmos_flags;	\
-		local_irq_save(cmos_flags);	\
-		lock_cmos(reg)
-
-#define lock_cmos_suffix(reg)			\
-	unlock_cmos();				\
-	local_irq_restore(cmos_flags);		\
-	} while (0)
-#else
-#define lock_cmos_prefix(reg) do {} while (0)
-#define lock_cmos_suffix(reg) do {} while (0)
-#define lock_cmos(reg)
-#define unlock_cmos()
-#define do_i_have_lock_cmos() 0
-#define current_lock_cmos_reg() 0
-#endif
-
-/*
- * The yet supported machines all access the RTC index register via
- * an ISA port access but the way to access the date register differs ...
- */
-#define CMOS_READ(addr) rtc_cmos_read(addr)
-#define CMOS_WRITE(val, addr) rtc_cmos_write(val, addr)
-unsigned char rtc_cmos_read(unsigned char addr);
-void rtc_cmos_write(unsigned char val, unsigned char addr);
-
-extern int mach_set_rtc_mmss(unsigned long nowtime);
-extern unsigned long mach_get_cmos_time(void);
-
-#define RTC_IRQ 8
-
-#endif /* ASM_X86__MC146818RTC_H */
diff --git a/include/asm-x86/mca.h b/include/asm-x86/mca.h
deleted file mode 100644
index 60d1ed287b13..000000000000
--- a/include/asm-x86/mca.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* Platform specific MCA defines */
-#ifndef ASM_X86__MCA_H
-#define ASM_X86__MCA_H
-
-/* Maximal number of MCA slots - actually, some machines have less, but
- * they all have sufficient number of POS registers to cover 8.
- */
-#define MCA_MAX_SLOT_NR  8
-
-/* Most machines have only one MCA bus.  The only multiple bus machines
- * I know have at most two */
-#define MAX_MCA_BUSSES 2
-
-#define MCA_PRIMARY_BUS		0
-#define MCA_SECONDARY_BUS	1
-
-/* Dummy slot numbers on primary MCA for integrated functions */
-#define MCA_INTEGSCSI	(MCA_MAX_SLOT_NR)
-#define MCA_INTEGVIDEO	(MCA_MAX_SLOT_NR+1)
-#define MCA_MOTHERBOARD (MCA_MAX_SLOT_NR+2)
-
-/* Dummy POS values for integrated functions */
-#define MCA_DUMMY_POS_START	0x10000
-#define MCA_INTEGSCSI_POS	(MCA_DUMMY_POS_START+1)
-#define MCA_INTEGVIDEO_POS	(MCA_DUMMY_POS_START+2)
-#define MCA_MOTHERBOARD_POS	(MCA_DUMMY_POS_START+3)
-
-/* MCA registers */
-
-#define MCA_MOTHERBOARD_SETUP_REG	0x94
-#define MCA_ADAPTER_SETUP_REG		0x96
-#define MCA_POS_REG(n)			(0x100+(n))
-
-#define MCA_ENABLED	0x01	/* POS 2, set if adapter enabled */
-
-/* Max number of adapters, including both slots and various integrated
- * things.
- */
-#define MCA_NUMADAPTERS (MCA_MAX_SLOT_NR+3)
-
-#endif /* ASM_X86__MCA_H */
diff --git a/include/asm-x86/mca_dma.h b/include/asm-x86/mca_dma.h
deleted file mode 100644
index 49f22be237d2..000000000000
--- a/include/asm-x86/mca_dma.h
+++ /dev/null
@@ -1,201 +0,0 @@
-#ifndef ASM_X86__MCA_DMA_H
-#define ASM_X86__MCA_DMA_H
-
-#include <asm/io.h>
-#include <linux/ioport.h>
-
-/*
- * Microchannel specific DMA stuff.  DMA on an MCA machine is fairly similar to
- *   standard PC dma, but it certainly has its quirks.  DMA register addresses
- *   are in a different place and there are some added functions.  Most of this
- *   should be pretty obvious on inspection.  Note that the user must divide
- *   count by 2 when using 16-bit dma; that is not handled by these functions.
- *
- * Ramen Noodles are yummy.
- *
- *  1998 Tymm Twillman <tymm@computer.org>
- */
-
-/*
- * Registers that are used by the DMA controller; FN is the function register
- *   (tell the controller what to do) and EXE is the execution register (how
- *   to do it)
- */
-
-#define MCA_DMA_REG_FN  0x18
-#define MCA_DMA_REG_EXE 0x1A
-
-/*
- * Functions that the DMA controller can do
- */
-
-#define MCA_DMA_FN_SET_IO       0x00
-#define MCA_DMA_FN_SET_ADDR     0x20
-#define MCA_DMA_FN_GET_ADDR     0x30
-#define MCA_DMA_FN_SET_COUNT    0x40
-#define MCA_DMA_FN_GET_COUNT    0x50
-#define MCA_DMA_FN_GET_STATUS   0x60
-#define MCA_DMA_FN_SET_MODE     0x70
-#define MCA_DMA_FN_SET_ARBUS    0x80
-#define MCA_DMA_FN_MASK         0x90
-#define MCA_DMA_FN_RESET_MASK   0xA0
-#define MCA_DMA_FN_MASTER_CLEAR 0xD0
-
-/*
- * Modes (used by setting MCA_DMA_FN_MODE in the function register)
- *
- * Note that the MODE_READ is read from memory (write to device), and
- *   MODE_WRITE is vice-versa.
- */
-
-#define MCA_DMA_MODE_XFER  0x04  /* read by default */
-#define MCA_DMA_MODE_READ  0x04  /* same as XFER */
-#define MCA_DMA_MODE_WRITE 0x08  /* OR with MODE_XFER to use */
-#define MCA_DMA_MODE_IO    0x01  /* DMA from IO register */
-#define MCA_DMA_MODE_16    0x40  /* 16 bit xfers */
-
-
-/**
- *	mca_enable_dma	-	channel to enable DMA on
- *	@dmanr: DMA channel
- *
- *	Enable the MCA bus DMA on a channel. This can be called from
- *	IRQ context.
- */
-
-static inline void mca_enable_dma(unsigned int dmanr)
-{
-	outb(MCA_DMA_FN_RESET_MASK | dmanr, MCA_DMA_REG_FN);
-}
-
-/**
- *	mca_disble_dma	-	channel to disable DMA on
- *	@dmanr: DMA channel
- *
- *	Enable the MCA bus DMA on a channel. This can be called from
- *	IRQ context.
- */
-
-static inline void mca_disable_dma(unsigned int dmanr)
-{
-	outb(MCA_DMA_FN_MASK | dmanr, MCA_DMA_REG_FN);
-}
-
-/**
- *	mca_set_dma_addr -	load a 24bit DMA address
- *	@dmanr: DMA channel
- *	@a: 24bit bus address
- *
- *	Load the address register in the DMA controller. This has a 24bit
- *	limitation (16Mb).
- */
-
-static inline void mca_set_dma_addr(unsigned int dmanr, unsigned int a)
-{
-	outb(MCA_DMA_FN_SET_ADDR | dmanr, MCA_DMA_REG_FN);
-	outb(a & 0xff, MCA_DMA_REG_EXE);
-	outb((a >> 8) & 0xff, MCA_DMA_REG_EXE);
-	outb((a >> 16) & 0xff, MCA_DMA_REG_EXE);
-}
-
-/**
- *	mca_get_dma_addr -	load a 24bit DMA address
- *	@dmanr: DMA channel
- *
- *	Read the address register in the DMA controller. This has a 24bit
- *	limitation (16Mb). The return is a bus address.
- */
-
-static inline unsigned int mca_get_dma_addr(unsigned int dmanr)
-{
-	unsigned int addr;
-
-	outb(MCA_DMA_FN_GET_ADDR | dmanr, MCA_DMA_REG_FN);
-	addr = inb(MCA_DMA_REG_EXE);
-	addr |= inb(MCA_DMA_REG_EXE) << 8;
-	addr |= inb(MCA_DMA_REG_EXE) << 16;
-
-	return addr;
-}
-
-/**
- *	mca_set_dma_count -	load a 16bit transfer count
- *	@dmanr: DMA channel
- *	@count: count
- *
- *	Set the DMA count for this channel. This can be up to 64Kbytes.
- *	Setting a count of zero will not do what you expect.
- */
-
-static inline void mca_set_dma_count(unsigned int dmanr, unsigned int count)
-{
-	count--;  /* transfers one more than count -- correct for this */
-
-	outb(MCA_DMA_FN_SET_COUNT | dmanr, MCA_DMA_REG_FN);
-	outb(count & 0xff, MCA_DMA_REG_EXE);
-	outb((count >> 8) & 0xff, MCA_DMA_REG_EXE);
-}
-
-/**
- *	mca_get_dma_residue -	get the remaining bytes to transfer
- *	@dmanr: DMA channel
- *
- *	This function returns the number of bytes left to transfer
- *	on this DMA channel.
- */
-
-static inline unsigned int mca_get_dma_residue(unsigned int dmanr)
-{
-	unsigned short count;
-
-	outb(MCA_DMA_FN_GET_COUNT | dmanr, MCA_DMA_REG_FN);
-	count = 1 + inb(MCA_DMA_REG_EXE);
-	count += inb(MCA_DMA_REG_EXE) << 8;
-
-	return count;
-}
-
-/**
- *	mca_set_dma_io -	set the port for an I/O transfer
- *	@dmanr: DMA channel
- *	@io_addr: an I/O port number
- *
- *	Unlike the ISA bus DMA controllers the DMA on MCA bus can transfer
- *	with an I/O port target.
- */
-
-static inline void mca_set_dma_io(unsigned int dmanr, unsigned int io_addr)
-{
-	/*
-	 * DMA from a port address -- set the io address
-	 */
-
-	outb(MCA_DMA_FN_SET_IO | dmanr, MCA_DMA_REG_FN);
-	outb(io_addr & 0xff, MCA_DMA_REG_EXE);
-	outb((io_addr >>  8) & 0xff, MCA_DMA_REG_EXE);
-}
-
-/**
- *	mca_set_dma_mode -	set the DMA mode
- *	@dmanr: DMA channel
- *	@mode: mode to set
- *
- *	The DMA controller supports several modes. The mode values you can
- *	set are-
- *
- *	%MCA_DMA_MODE_READ when reading from the DMA device.
- *
- *	%MCA_DMA_MODE_WRITE to writing to the DMA device.
- *
- *	%MCA_DMA_MODE_IO to do DMA to or from an I/O port.
- *
- *	%MCA_DMA_MODE_16 to do 16bit transfers.
- */
-
-static inline void mca_set_dma_mode(unsigned int dmanr, unsigned int mode)
-{
-	outb(MCA_DMA_FN_SET_MODE | dmanr, MCA_DMA_REG_FN);
-	outb(mode, MCA_DMA_REG_EXE);
-}
-
-#endif /* ASM_X86__MCA_DMA_H */
diff --git a/include/asm-x86/mce.h b/include/asm-x86/mce.h
deleted file mode 100644
index 036133eaf744..000000000000
--- a/include/asm-x86/mce.h
+++ /dev/null
@@ -1,130 +0,0 @@
-#ifndef ASM_X86__MCE_H
-#define ASM_X86__MCE_H
-
-#ifdef __x86_64__
-
-#include <asm/ioctls.h>
-#include <asm/types.h>
-
-/*
- * Machine Check support for x86
- */
-
-#define MCG_CTL_P	 (1UL<<8)   /* MCG_CAP register available */
-
-#define MCG_STATUS_RIPV  (1UL<<0)   /* restart ip valid */
-#define MCG_STATUS_EIPV  (1UL<<1)   /* ip points to correct instruction */
-#define MCG_STATUS_MCIP  (1UL<<2)   /* machine check in progress */
-
-#define MCI_STATUS_VAL   (1UL<<63)  /* valid error */
-#define MCI_STATUS_OVER  (1UL<<62)  /* previous errors lost */
-#define MCI_STATUS_UC    (1UL<<61)  /* uncorrected error */
-#define MCI_STATUS_EN    (1UL<<60)  /* error enabled */
-#define MCI_STATUS_MISCV (1UL<<59)  /* misc error reg. valid */
-#define MCI_STATUS_ADDRV (1UL<<58)  /* addr reg. valid */
-#define MCI_STATUS_PCC   (1UL<<57)  /* processor context corrupt */
-
-/* Fields are zero when not available */
-struct mce {
-	__u64 status;
-	__u64 misc;
-	__u64 addr;
-	__u64 mcgstatus;
-	__u64 ip;
-	__u64 tsc;	/* cpu time stamp counter */
-	__u64 res1;	/* for future extension */
-	__u64 res2;	/* dito. */
-	__u8  cs;		/* code segment */
-	__u8  bank;	/* machine check bank */
-	__u8  cpu;	/* cpu that raised the error */
-	__u8  finished;   /* entry is valid */
-	__u32 pad;
-};
-
-/*
- * This structure contains all data related to the MCE log.  Also
- * carries a signature to make it easier to find from external
- * debugging tools.  Each entry is only valid when its finished flag
- * is set.
- */
-
-#define MCE_LOG_LEN 32
-
-struct mce_log {
-	char signature[12]; /* "MACHINECHECK" */
-	unsigned len;	    /* = MCE_LOG_LEN */
-	unsigned next;
-	unsigned flags;
-	unsigned pad0;
-	struct mce entry[MCE_LOG_LEN];
-};
-
-#define MCE_OVERFLOW 0		/* bit 0 in flags means overflow */
-
-#define MCE_LOG_SIGNATURE	"MACHINECHECK"
-
-#define MCE_GET_RECORD_LEN   _IOR('M', 1, int)
-#define MCE_GET_LOG_LEN      _IOR('M', 2, int)
-#define MCE_GETCLEAR_FLAGS   _IOR('M', 3, int)
-
-/* Software defined banks */
-#define MCE_EXTENDED_BANK	128
-#define MCE_THERMAL_BANK	MCE_EXTENDED_BANK + 0
-
-#define K8_MCE_THRESHOLD_BASE      (MCE_EXTENDED_BANK + 1)      /* MCE_AMD */
-#define K8_MCE_THRESHOLD_BANK_0    (MCE_THRESHOLD_BASE + 0 * 9)
-#define K8_MCE_THRESHOLD_BANK_1    (MCE_THRESHOLD_BASE + 1 * 9)
-#define K8_MCE_THRESHOLD_BANK_2    (MCE_THRESHOLD_BASE + 2 * 9)
-#define K8_MCE_THRESHOLD_BANK_3    (MCE_THRESHOLD_BASE + 3 * 9)
-#define K8_MCE_THRESHOLD_BANK_4    (MCE_THRESHOLD_BASE + 4 * 9)
-#define K8_MCE_THRESHOLD_BANK_5    (MCE_THRESHOLD_BASE + 5 * 9)
-#define K8_MCE_THRESHOLD_DRAM_ECC  (MCE_THRESHOLD_BANK_4 + 0)
-
-#endif /* __x86_64__ */
-
-#ifdef __KERNEL__
-
-#ifdef CONFIG_X86_32
-extern int mce_disabled;
-#else /* CONFIG_X86_32 */
-
-#include <asm/atomic.h>
-
-void mce_log(struct mce *m);
-DECLARE_PER_CPU(struct sys_device, device_mce);
-extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
-
-#ifdef CONFIG_X86_MCE_INTEL
-void mce_intel_feature_init(struct cpuinfo_x86 *c);
-#else
-static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
-#endif
-
-#ifdef CONFIG_X86_MCE_AMD
-void mce_amd_feature_init(struct cpuinfo_x86 *c);
-#else
-static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
-#endif
-
-void mce_log_therm_throt_event(unsigned int cpu, __u64 status);
-
-extern atomic_t mce_entry;
-
-extern void do_machine_check(struct pt_regs *, long);
-extern int mce_notify_user(void);
-
-#endif /* !CONFIG_X86_32 */
-
-
-
-#ifdef CONFIG_X86_MCE
-extern void mcheck_init(struct cpuinfo_x86 *c);
-#else
-#define mcheck_init(c) do { } while (0)
-#endif
-extern void stop_mce(void);
-extern void restart_mce(void);
-
-#endif /* __KERNEL__ */
-
-#endif /* ASM_X86__MCE_H */
diff --git a/include/asm-x86/microcode.h b/include/asm-x86/microcode.h
deleted file mode 100644
index 62c793bb70ca..000000000000
--- a/include/asm-x86/microcode.h
+++ /dev/null
@@ -1,47 +0,0 @@
-#ifndef ASM_X86__MICROCODE_H
-#define ASM_X86__MICROCODE_H
-
-struct cpu_signature {
-	unsigned int sig;
-	unsigned int pf;
-	unsigned int rev;
-};
-
-struct device;
-
-struct microcode_ops {
-	int  (*request_microcode_user) (int cpu, const void __user *buf, size_t size);
-	int  (*request_microcode_fw) (int cpu, struct device *device);
-
-	void (*apply_microcode) (int cpu);
-
-	int  (*collect_cpu_info) (int cpu, struct cpu_signature *csig);
-	void (*microcode_fini_cpu) (int cpu);
-};
-
-struct ucode_cpu_info {
-	struct cpu_signature cpu_sig;
-	int valid;
-	void *mc;
-};
-extern struct ucode_cpu_info ucode_cpu_info[];
-
-#ifdef CONFIG_MICROCODE_INTEL
-extern struct microcode_ops * __init init_intel_microcode(void);
-#else
-static inline struct microcode_ops * __init init_intel_microcode(void)
-{
-	return NULL;
-}
-#endif /* CONFIG_MICROCODE_INTEL */
-
-#ifdef CONFIG_MICROCODE_AMD
-extern struct microcode_ops * __init init_amd_microcode(void);
-#else
-static inline struct microcode_ops * __init init_amd_microcode(void)
-{
-	return NULL;
-}
-#endif
-
-#endif /* ASM_X86__MICROCODE_H */
diff --git a/include/asm-x86/mman.h b/include/asm-x86/mman.h
deleted file mode 100644
index 4ef28e6de383..000000000000
--- a/include/asm-x86/mman.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef ASM_X86__MMAN_H
-#define ASM_X86__MMAN_H
-
-#include <asm-generic/mman.h>
-
-#define MAP_32BIT	0x40		/* only give out 32bit addresses */
-
-#define MAP_GROWSDOWN	0x0100		/* stack-like segment */
-#define MAP_DENYWRITE	0x0800		/* ETXTBSY */
-#define MAP_EXECUTABLE	0x1000		/* mark it as an executable */
-#define MAP_LOCKED	0x2000		/* pages are locked */
-#define MAP_NORESERVE	0x4000		/* don't check for reservations */
-#define MAP_POPULATE	0x8000		/* populate (prefault) pagetables */
-#define MAP_NONBLOCK	0x10000		/* do not block on IO */
-#define MAP_STACK	0x20000		/* give out an address that is best suited for process/thread stacks */
-
-#define MCL_CURRENT	1		/* lock all current mappings */
-#define MCL_FUTURE	2		/* lock all future mappings */
-
-#endif /* ASM_X86__MMAN_H */
diff --git a/include/asm-x86/mmconfig.h b/include/asm-x86/mmconfig.h
deleted file mode 100644
index fb79b1cf5d07..000000000000
--- a/include/asm-x86/mmconfig.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef ASM_X86__MMCONFIG_H
-#define ASM_X86__MMCONFIG_H
-
-#ifdef CONFIG_PCI_MMCONFIG
-extern void __cpuinit fam10h_check_enable_mmcfg(void);
-extern void __cpuinit check_enable_amd_mmconf_dmi(void);
-#else
-static inline void fam10h_check_enable_mmcfg(void) { }
-static inline void check_enable_amd_mmconf_dmi(void) { }
-#endif
-
-#endif /* ASM_X86__MMCONFIG_H */
diff --git a/include/asm-x86/mmu.h b/include/asm-x86/mmu.h
deleted file mode 100644
index 9d5aff14334a..000000000000
--- a/include/asm-x86/mmu.h
+++ /dev/null
@@ -1,26 +0,0 @@
-#ifndef ASM_X86__MMU_H
-#define ASM_X86__MMU_H
-
-#include <linux/spinlock.h>
-#include <linux/mutex.h>
-
-/*
- * The x86 doesn't have a mmu context, but
- * we put the segment information here.
- */
-typedef struct {
-	void *ldt;
-	int size;
-	struct mutex lock;
-	void *vdso;
-} mm_context_t;
-
-#ifdef CONFIG_SMP
-void leave_mm(int cpu);
-#else
-static inline void leave_mm(int cpu)
-{
-}
-#endif
-
-#endif /* ASM_X86__MMU_H */
diff --git a/include/asm-x86/mmu_context.h b/include/asm-x86/mmu_context.h
deleted file mode 100644
index 8ec940bfd079..000000000000
--- a/include/asm-x86/mmu_context.h
+++ /dev/null
@@ -1,37 +0,0 @@
-#ifndef ASM_X86__MMU_CONTEXT_H
-#define ASM_X86__MMU_CONTEXT_H
-
-#include <asm/desc.h>
-#include <asm/atomic.h>
-#include <asm/pgalloc.h>
-#include <asm/tlbflush.h>
-#include <asm/paravirt.h>
-#ifndef CONFIG_PARAVIRT
-#include <asm-generic/mm_hooks.h>
-
-static inline void paravirt_activate_mm(struct mm_struct *prev,
-					struct mm_struct *next)
-{
-}
-#endif	/* !CONFIG_PARAVIRT */
-
-/*
- * Used for LDT copy/destruction.
- */
-int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
-void destroy_context(struct mm_struct *mm);
-
-#ifdef CONFIG_X86_32
-# include "mmu_context_32.h"
-#else
-# include "mmu_context_64.h"
-#endif
-
-#define activate_mm(prev, next)			\
-do {						\
-	paravirt_activate_mm((prev), (next));	\
-	switch_mm((prev), (next), NULL);	\
-} while (0);
-
-
-#endif /* ASM_X86__MMU_CONTEXT_H */
diff --git a/include/asm-x86/mmu_context_32.h b/include/asm-x86/mmu_context_32.h
deleted file mode 100644
index cce6f6e4afd6..000000000000
--- a/include/asm-x86/mmu_context_32.h
+++ /dev/null
@@ -1,56 +0,0 @@
-#ifndef ASM_X86__MMU_CONTEXT_32_H
-#define ASM_X86__MMU_CONTEXT_32_H
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-#ifdef CONFIG_SMP
-	unsigned cpu = smp_processor_id();
-	if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
-		per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_LAZY;
-#endif
-}
-
-static inline void switch_mm(struct mm_struct *prev,
-			     struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-	int cpu = smp_processor_id();
-
-	if (likely(prev != next)) {
-		/* stop flush ipis for the previous mm */
-		cpu_clear(cpu, prev->cpu_vm_mask);
-#ifdef CONFIG_SMP
-		per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
-		per_cpu(cpu_tlbstate, cpu).active_mm = next;
-#endif
-		cpu_set(cpu, next->cpu_vm_mask);
-
-		/* Re-load page tables */
-		load_cr3(next->pgd);
-
-		/*
-		 * load the LDT, if the LDT is different:
-		 */
-		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_LDT_nolock(&next->context);
-	}
-#ifdef CONFIG_SMP
-	else {
-		per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
-		BUG_ON(per_cpu(cpu_tlbstate, cpu).active_mm != next);
-
-		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
-			/* We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload %cr3.
-			 */
-			load_cr3(next->pgd);
-			load_LDT_nolock(&next->context);
-		}
-	}
-#endif
-}
-
-#define deactivate_mm(tsk, mm)			\
-	asm("movl %0,%%gs": :"r" (0));
-
-#endif /* ASM_X86__MMU_CONTEXT_32_H */
diff --git a/include/asm-x86/mmu_context_64.h b/include/asm-x86/mmu_context_64.h
deleted file mode 100644
index 26758673c828..000000000000
--- a/include/asm-x86/mmu_context_64.h
+++ /dev/null
@@ -1,54 +0,0 @@
-#ifndef ASM_X86__MMU_CONTEXT_64_H
-#define ASM_X86__MMU_CONTEXT_64_H
-
-#include <asm/pda.h>
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-#ifdef CONFIG_SMP
-	if (read_pda(mmu_state) == TLBSTATE_OK)
-		write_pda(mmu_state, TLBSTATE_LAZY);
-#endif
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
-			     struct task_struct *tsk)
-{
-	unsigned cpu = smp_processor_id();
-	if (likely(prev != next)) {
-		/* stop flush ipis for the previous mm */
-		cpu_clear(cpu, prev->cpu_vm_mask);
-#ifdef CONFIG_SMP
-		write_pda(mmu_state, TLBSTATE_OK);
-		write_pda(active_mm, next);
-#endif
-		cpu_set(cpu, next->cpu_vm_mask);
-		load_cr3(next->pgd);
-
-		if (unlikely(next->context.ldt != prev->context.ldt))
-			load_LDT_nolock(&next->context);
-	}
-#ifdef CONFIG_SMP
-	else {
-		write_pda(mmu_state, TLBSTATE_OK);
-		if (read_pda(active_mm) != next)
-			BUG();
-		if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
-			/* We were in lazy tlb mode and leave_mm disabled
-			 * tlb flush IPI delivery. We must reload CR3
-			 * to make sure to use no freed page tables.
-			 */
-			load_cr3(next->pgd);
-			load_LDT_nolock(&next->context);
-		}
-	}
-#endif
-}
-
-#define deactivate_mm(tsk, mm)			\
-do {						\
-	load_gs_index(0);			\
-	asm volatile("movl %0,%%fs"::"r"(0));	\
-} while (0)
-
-#endif /* ASM_X86__MMU_CONTEXT_64_H */
diff --git a/include/asm-x86/mmx.h b/include/asm-x86/mmx.h
deleted file mode 100644
index 2e7299bb3653..000000000000
--- a/include/asm-x86/mmx.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef ASM_X86__MMX_H
-#define ASM_X86__MMX_H
-
-/*
- *	MMX 3Dnow! helper operations
- */
-
-#include <linux/types.h>
-
-extern void *_mmx_memcpy(void *to, const void *from, size_t size);
-extern void mmx_clear_page(void *page);
-extern void mmx_copy_page(void *to, void *from);
-
-#endif /* ASM_X86__MMX_H */
diff --git a/include/asm-x86/mmzone.h b/include/asm-x86/mmzone.h
deleted file mode 100644
index 64217ea16a36..000000000000
--- a/include/asm-x86/mmzone.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "mmzone_32.h"
-#else
-# include "mmzone_64.h"
-#endif
diff --git a/include/asm-x86/mmzone_32.h b/include/asm-x86/mmzone_32.h
deleted file mode 100644
index 121b65d61d86..000000000000
--- a/include/asm-x86/mmzone_32.h
+++ /dev/null
@@ -1,134 +0,0 @@
-/*
- * Written by Pat Gaughen (gone@us.ibm.com) Mar 2002
- *
- */
-
-#ifndef ASM_X86__MMZONE_32_H
-#define ASM_X86__MMZONE_32_H
-
-#include <asm/smp.h>
-
-#ifdef CONFIG_NUMA
-extern struct pglist_data *node_data[];
-#define NODE_DATA(nid)	(node_data[nid])
-
-#include <asm/numaq.h>
-/* summit or generic arch */
-#include <asm/srat.h>
-
-extern int get_memcfg_numa_flat(void);
-/*
- * This allows any one NUMA architecture to be compiled
- * for, and still fall back to the flat function if it
- * fails.
- */
-static inline void get_memcfg_numa(void)
-{
-
-	if (get_memcfg_numaq())
-		return;
-	if (get_memcfg_from_srat())
-		return;
-	get_memcfg_numa_flat();
-}
-
-extern int early_pfn_to_nid(unsigned long pfn);
-
-#else /* !CONFIG_NUMA */
-
-#define get_memcfg_numa get_memcfg_numa_flat
-
-#endif /* CONFIG_NUMA */
-
-#ifdef CONFIG_DISCONTIGMEM
-
-/*
- * generic node memory support, the following assumptions apply:
- *
- * 1) memory comes in 64Mb contigious chunks which are either present or not
- * 2) we will not have more than 64Gb in total
- *
- * for now assume that 64Gb is max amount of RAM for whole system
- *    64Gb / 4096bytes/page = 16777216 pages
- */
-#define MAX_NR_PAGES 16777216
-#define MAX_ELEMENTS 1024
-#define PAGES_PER_ELEMENT (MAX_NR_PAGES/MAX_ELEMENTS)
-
-extern s8 physnode_map[];
-
-static inline int pfn_to_nid(unsigned long pfn)
-{
-#ifdef CONFIG_NUMA
-	return((int) physnode_map[(pfn) / PAGES_PER_ELEMENT]);
-#else
-	return 0;
-#endif
-}
-
-/*
- * Following are macros that each numa implmentation must define.
- */
-
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)						\
-({									\
-	pg_data_t *__pgdat = NODE_DATA(nid);				\
-	__pgdat->node_start_pfn + __pgdat->node_spanned_pages;		\
-})
-
-static inline int pfn_valid(int pfn)
-{
-	int nid = pfn_to_nid(pfn);
-
-	if (nid >= 0)
-		return (pfn < node_end_pfn(nid));
-	return 0;
-}
-
-#endif /* CONFIG_DISCONTIGMEM */
-
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-
-/*
- * Following are macros that are specific to this numa platform.
- */
-#define reserve_bootmem(addr, size, flags) \
-	reserve_bootmem_node(NODE_DATA(0), (addr), (size), (flags))
-#define alloc_bootmem(x) \
-	__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_nopanic(x) \
-	__alloc_bootmem_node_nopanic(NODE_DATA(0), (x), SMP_CACHE_BYTES, \
-				__pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_low(x) \
-	__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES, 0)
-#define alloc_bootmem_pages(x) \
-	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, __pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_pages_nopanic(x) \
-	__alloc_bootmem_node_nopanic(NODE_DATA(0), (x), PAGE_SIZE, \
-				__pa(MAX_DMA_ADDRESS))
-#define alloc_bootmem_low_pages(x) \
-	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0)
-#define alloc_bootmem_node(pgdat, x)					\
-({									\
-	struct pglist_data  __maybe_unused			\
-				*__alloc_bootmem_node__pgdat = (pgdat);	\
-	__alloc_bootmem_node(NODE_DATA(0), (x), SMP_CACHE_BYTES,	\
-						__pa(MAX_DMA_ADDRESS));	\
-})
-#define alloc_bootmem_pages_node(pgdat, x)				\
-({									\
-	struct pglist_data  __maybe_unused			\
-				*__alloc_bootmem_node__pgdat = (pgdat);	\
-	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE,		\
-						__pa(MAX_DMA_ADDRESS));	\
-})
-#define alloc_bootmem_low_pages_node(pgdat, x)				\
-({									\
-	struct pglist_data  __maybe_unused			\
-				*__alloc_bootmem_node__pgdat = (pgdat);	\
-	__alloc_bootmem_node(NODE_DATA(0), (x), PAGE_SIZE, 0);		\
-})
-#endif /* CONFIG_NEED_MULTIPLE_NODES */
-
-#endif /* ASM_X86__MMZONE_32_H */
diff --git a/include/asm-x86/mmzone_64.h b/include/asm-x86/mmzone_64.h
deleted file mode 100644
index 6480f3333b2a..000000000000
--- a/include/asm-x86/mmzone_64.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/* K8 NUMA support */
-/* Copyright 2002,2003 by Andi Kleen, SuSE Labs */
-/* 2.5 Version loosely based on the NUMAQ Code by Pat Gaughen. */
-#ifndef ASM_X86__MMZONE_64_H
-#define ASM_X86__MMZONE_64_H
-
-
-#ifdef CONFIG_NUMA
-
-#include <linux/mmdebug.h>
-
-#include <asm/smp.h>
-
-/* Simple perfect hash to map physical addresses to node numbers */
-struct memnode {
-	int shift;
-	unsigned int mapsize;
-	s16 *map;
-	s16 embedded_map[64 - 8];
-} ____cacheline_aligned; /* total size = 128 bytes */
-extern struct memnode memnode;
-#define memnode_shift memnode.shift
-#define memnodemap memnode.map
-#define memnodemapsize memnode.mapsize
-
-extern struct pglist_data *node_data[];
-
-static inline __attribute__((pure)) int phys_to_nid(unsigned long addr)
-{
-	unsigned nid;
-	VIRTUAL_BUG_ON(!memnodemap);
-	nid = memnodemap[addr >> memnode_shift];
-	VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]);
-	return nid;
-}
-
-#define NODE_DATA(nid)		(node_data[nid])
-
-#define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
-#define node_end_pfn(nid)       (NODE_DATA(nid)->node_start_pfn +	\
-				 NODE_DATA(nid)->node_spanned_pages)
-
-extern int early_pfn_to_nid(unsigned long pfn);
-
-#ifdef CONFIG_NUMA_EMU
-#define FAKE_NODE_MIN_SIZE	(64 * 1024 * 1024)
-#define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))
-#endif
-
-#endif
-#endif /* ASM_X86__MMZONE_64_H */
diff --git a/include/asm-x86/module.h b/include/asm-x86/module.h
deleted file mode 100644
index 864f2005fc1d..000000000000
--- a/include/asm-x86/module.h
+++ /dev/null
@@ -1,80 +0,0 @@
-#ifndef ASM_X86__MODULE_H
-#define ASM_X86__MODULE_H
-
-/* x86_32/64 are simple */
-struct mod_arch_specific {};
-
-#ifdef CONFIG_X86_32
-# define Elf_Shdr Elf32_Shdr
-# define Elf_Sym Elf32_Sym
-# define Elf_Ehdr Elf32_Ehdr
-#else
-# define Elf_Shdr Elf64_Shdr
-# define Elf_Sym Elf64_Sym
-# define Elf_Ehdr Elf64_Ehdr
-#endif
-
-#ifdef CONFIG_X86_64
-/* X86_64 does not define MODULE_PROC_FAMILY */
-#elif defined CONFIG_M386
-#define MODULE_PROC_FAMILY "386 "
-#elif defined CONFIG_M486
-#define MODULE_PROC_FAMILY "486 "
-#elif defined CONFIG_M586
-#define MODULE_PROC_FAMILY "586 "
-#elif defined CONFIG_M586TSC
-#define MODULE_PROC_FAMILY "586TSC "
-#elif defined CONFIG_M586MMX
-#define MODULE_PROC_FAMILY "586MMX "
-#elif defined CONFIG_MCORE2
-#define MODULE_PROC_FAMILY "CORE2 "
-#elif defined CONFIG_M686
-#define MODULE_PROC_FAMILY "686 "
-#elif defined CONFIG_MPENTIUMII
-#define MODULE_PROC_FAMILY "PENTIUMII "
-#elif defined CONFIG_MPENTIUMIII
-#define MODULE_PROC_FAMILY "PENTIUMIII "
-#elif defined CONFIG_MPENTIUMM
-#define MODULE_PROC_FAMILY "PENTIUMM "
-#elif defined CONFIG_MPENTIUM4
-#define MODULE_PROC_FAMILY "PENTIUM4 "
-#elif defined CONFIG_MK6
-#define MODULE_PROC_FAMILY "K6 "
-#elif defined CONFIG_MK7
-#define MODULE_PROC_FAMILY "K7 "
-#elif defined CONFIG_MK8
-#define MODULE_PROC_FAMILY "K8 "
-#elif defined CONFIG_X86_ELAN
-#define MODULE_PROC_FAMILY "ELAN "
-#elif defined CONFIG_MCRUSOE
-#define MODULE_PROC_FAMILY "CRUSOE "
-#elif defined CONFIG_MEFFICEON
-#define MODULE_PROC_FAMILY "EFFICEON "
-#elif defined CONFIG_MWINCHIPC6
-#define MODULE_PROC_FAMILY "WINCHIPC6 "
-#elif defined CONFIG_MWINCHIP3D
-#define MODULE_PROC_FAMILY "WINCHIP3D "
-#elif defined CONFIG_MCYRIXIII
-#define MODULE_PROC_FAMILY "CYRIXIII "
-#elif defined CONFIG_MVIAC3_2
-#define MODULE_PROC_FAMILY "VIAC3-2 "
-#elif defined CONFIG_MVIAC7
-#define MODULE_PROC_FAMILY "VIAC7 "
-#elif defined CONFIG_MGEODEGX1
-#define MODULE_PROC_FAMILY "GEODEGX1 "
-#elif defined CONFIG_MGEODE_LX
-#define MODULE_PROC_FAMILY "GEODE "
-#else
-#error unknown processor family
-#endif
-
-#ifdef CONFIG_X86_32
-# ifdef CONFIG_4KSTACKS
-#  define MODULE_STACKSIZE "4KSTACKS "
-# else
-#  define MODULE_STACKSIZE ""
-# endif
-# define MODULE_ARCH_VERMAGIC MODULE_PROC_FAMILY MODULE_STACKSIZE
-#endif
-
-#endif /* ASM_X86__MODULE_H */
diff --git a/include/asm-x86/mpspec.h b/include/asm-x86/mpspec.h
deleted file mode 100644
index be2241a818f1..000000000000
--- a/include/asm-x86/mpspec.h
+++ /dev/null
@@ -1,145 +0,0 @@
-#ifndef ASM_X86__MPSPEC_H
-#define ASM_X86__MPSPEC_H
-
-#include <linux/init.h>
-
-#include <asm/mpspec_def.h>
-
-extern int apic_version[MAX_APICS];
-
-#ifdef CONFIG_X86_32
-#include <mach_mpspec.h>
-
-extern unsigned int def_to_bigsmp;
-extern u8 apicid_2_node[];
-extern int pic_mode;
-
-#ifdef CONFIG_X86_NUMAQ
-extern int mp_bus_id_to_node[MAX_MP_BUSSES];
-extern int mp_bus_id_to_local[MAX_MP_BUSSES];
-extern int quad_local_to_mp_bus_id [NR_CPUS/4][4];
-#endif
-
-#define MAX_APICID 256
-
-#else
-
-#define MAX_MP_BUSSES 256
-/* Each PCI slot may be a combo card with its own bus.  4 IRQ pins per slot. */
-#define MAX_IRQ_SOURCES (MAX_MP_BUSSES * 4)
-
-#endif
-
-extern void early_find_smp_config(void);
-extern void early_get_smp_config(void);
-
-#if defined(CONFIG_MCA) || defined(CONFIG_EISA)
-extern int mp_bus_id_to_type[MAX_MP_BUSSES];
-#endif
-
-extern DECLARE_BITMAP(mp_bus_not_pci, MAX_MP_BUSSES);
-
-extern unsigned int boot_cpu_physical_apicid;
-extern unsigned int max_physical_apicid;
-extern int smp_found_config;
-extern int mpc_default_type;
-extern unsigned long mp_lapic_addr;
-
-extern void find_smp_config(void);
-extern void get_smp_config(void);
-#ifdef CONFIG_X86_MPPARSE
-extern void early_reserve_e820_mpc_new(void);
-#else
-static inline void early_reserve_e820_mpc_new(void) { }
-#endif
-
-void __cpuinit generic_processor_info(int apicid, int version);
-#ifdef CONFIG_ACPI
-extern void mp_register_ioapic(int id, u32 address, u32 gsi_base);
-extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
-				   u32 gsi);
-extern void mp_config_acpi_legacy_irqs(void);
-extern int mp_register_gsi(u32 gsi, int edge_level, int active_high_low);
-#ifdef CONFIG_X86_IO_APIC
-extern int mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
-				u32 gsi, int triggering, int polarity);
-#else
-static inline int
-mp_config_acpi_gsi(unsigned char number, unsigned int devfn, u8 pin,
-		   u32 gsi, int triggering, int polarity)
-{
-	return 0;
-}
-#endif
-#endif /* CONFIG_ACPI */
-
-#define PHYSID_ARRAY_SIZE	BITS_TO_LONGS(MAX_APICS)
-
-struct physid_mask {
-	unsigned long mask[PHYSID_ARRAY_SIZE];
-};
-
-typedef struct physid_mask physid_mask_t;
-
-#define physid_set(physid, map)			set_bit(physid, (map).mask)
-#define physid_clear(physid, map)		clear_bit(physid, (map).mask)
-#define physid_isset(physid, map)		test_bit(physid, (map).mask)
-#define physid_test_and_set(physid, map)			\
-	test_and_set_bit(physid, (map).mask)
-
-#define physids_and(dst, src1, src2)					\
-	bitmap_and((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
-
-#define physids_or(dst, src1, src2)					\
-	bitmap_or((dst).mask, (src1).mask, (src2).mask, MAX_APICS)
-
-#define physids_clear(map)					\
-	bitmap_zero((map).mask, MAX_APICS)
-
-#define physids_complement(dst, src)				\
-	bitmap_complement((dst).mask, (src).mask, MAX_APICS)
-
-#define physids_empty(map)					\
-	bitmap_empty((map).mask, MAX_APICS)
-
-#define physids_equal(map1, map2)				\
-	bitmap_equal((map1).mask, (map2).mask, MAX_APICS)
-
-#define physids_weight(map)					\
-	bitmap_weight((map).mask, MAX_APICS)
-
-#define physids_shift_right(d, s, n)				\
-	bitmap_shift_right((d).mask, (s).mask, n, MAX_APICS)
-
-#define physids_shift_left(d, s, n)				\
-	bitmap_shift_left((d).mask, (s).mask, n, MAX_APICS)
-
-#define physids_coerce(map)			((map).mask[0])
-
-#define physids_promote(physids)					\
-	({								\
-		physid_mask_t __physid_mask = PHYSID_MASK_NONE;		\
-		__physid_mask.mask[0] = physids;			\
-		__physid_mask;						\
-	})
-
-/* Note: will create very large stack frames if physid_mask_t is big */
-#define physid_mask_of_physid(physid)					\
-	({								\
-		physid_mask_t __physid_mask = PHYSID_MASK_NONE;		\
-		physid_set(physid, __physid_mask);			\
-		__physid_mask;						\
-	})
-
-static inline void physid_set_mask_of_physid(int physid, physid_mask_t *map)
-{
-	physids_clear(*map);
-	physid_set(physid, *map);
-}
-
-#define PHYSID_MASK_ALL		{ {[0 ... PHYSID_ARRAY_SIZE-1] = ~0UL} }
-#define PHYSID_MASK_NONE	{ {[0 ... PHYSID_ARRAY_SIZE-1] = 0UL} }
-
-extern physid_mask_t phys_cpu_present_map;
-
-#endif /* ASM_X86__MPSPEC_H */
diff --git a/include/asm-x86/mpspec_def.h b/include/asm-x86/mpspec_def.h
deleted file mode 100644
index 79166b048012..000000000000
--- a/include/asm-x86/mpspec_def.h
+++ /dev/null
@@ -1,180 +0,0 @@
-#ifndef ASM_X86__MPSPEC_DEF_H
-#define ASM_X86__MPSPEC_DEF_H
-
-/*
- * Structure definitions for SMP machines following the
- * Intel Multiprocessing Specification 1.1 and 1.4.
- */
-
-/*
- * This tag identifies where the SMP configuration
- * information is.
- */
-
-#define SMP_MAGIC_IDENT	(('_'<<24) | ('P'<<16) | ('M'<<8) | '_')
-
-#ifdef CONFIG_X86_32
-# define MAX_MPC_ENTRY 1024
-# define MAX_APICS      256
-#else
-# if NR_CPUS <= 255
-#  define MAX_APICS     255
-# else
-#  define MAX_APICS   32768
-# endif
-#endif
-
-struct intel_mp_floating {
-	char mpf_signature[4];		/* "_MP_"			*/
-	unsigned int mpf_physptr;	/* Configuration table address	*/
-	unsigned char mpf_length;	/* Our length (paragraphs)	*/
-	unsigned char mpf_specification;/* Specification version	*/
-	unsigned char mpf_checksum;	/* Checksum (makes sum 0)	*/
-	unsigned char mpf_feature1;	/* Standard or configuration ?	*/
-	unsigned char mpf_feature2;	/* Bit7 set for IMCR|PIC	*/
-	unsigned char mpf_feature3;	/* Unused (0)			*/
-	unsigned char mpf_feature4;	/* Unused (0)			*/
-	unsigned char mpf_feature5;	/* Unused (0)			*/
-};
-
-#define MPC_SIGNATURE "PCMP"
-
-struct mp_config_table {
-	char mpc_signature[4];
-	unsigned short mpc_length;	/* Size of table */
-	char mpc_spec;			/* 0x01 */
-	char mpc_checksum;
-	char mpc_oem[8];
-	char mpc_productid[12];
-	unsigned int mpc_oemptr;	/* 0 if not present */
-	unsigned short mpc_oemsize;	/* 0 if not present */
-	unsigned short mpc_oemcount;
-	unsigned int mpc_lapic;	/* APIC address */
-	unsigned int reserved;
-};
-
-/* Followed by entries */
-
-#define	MP_PROCESSOR		0
-#define	MP_BUS			1
-#define	MP_IOAPIC		2
-#define	MP_INTSRC		3
-#define	MP_LINTSRC		4
-/* Used by IBM NUMA-Q to describe node locality */
-#define	MP_TRANSLATION		192
-
-#define CPU_ENABLED		1	/* Processor is available */
-#define CPU_BOOTPROCESSOR	2	/* Processor is the BP */
-
-#define CPU_STEPPING_MASK	0x000F
-#define CPU_MODEL_MASK		0x00F0
-#define CPU_FAMILY_MASK		0x0F00
-
-struct mpc_config_processor {
-	unsigned char mpc_type;
-	unsigned char mpc_apicid;	/* Local APIC number */
-	unsigned char mpc_apicver;	/* Its versions */
-	unsigned char mpc_cpuflag;
-	unsigned int mpc_cpufeature;
-	unsigned int mpc_featureflag;	/* CPUID feature value */
-	unsigned int mpc_reserved[2];
-};
-
-struct mpc_config_bus {
-	unsigned char mpc_type;
-	unsigned char mpc_busid;
-	unsigned char mpc_bustype[6];
-};
-
-/* List of Bus Type string values, Intel MP Spec. */
-#define BUSTYPE_EISA	"EISA"
-#define BUSTYPE_ISA	"ISA"
-#define BUSTYPE_INTERN	"INTERN"	/* Internal BUS */
-#define BUSTYPE_MCA	"MCA"
-#define BUSTYPE_VL	"VL"		/* Local bus */
-#define BUSTYPE_PCI	"PCI"
-#define BUSTYPE_PCMCIA	"PCMCIA"
-#define BUSTYPE_CBUS	"CBUS"
-#define BUSTYPE_CBUSII	"CBUSII"
-#define BUSTYPE_FUTURE	"FUTURE"
-#define BUSTYPE_MBI	"MBI"
-#define BUSTYPE_MBII	"MBII"
-#define BUSTYPE_MPI	"MPI"
-#define BUSTYPE_MPSA	"MPSA"
-#define BUSTYPE_NUBUS	"NUBUS"
-#define BUSTYPE_TC	"TC"
-#define BUSTYPE_VME	"VME"
-#define BUSTYPE_XPRESS	"XPRESS"
-
-#define MPC_APIC_USABLE		0x01
-
-struct mpc_config_ioapic {
-	unsigned char mpc_type;
-	unsigned char mpc_apicid;
-	unsigned char mpc_apicver;
-	unsigned char mpc_flags;
-	unsigned int mpc_apicaddr;
-};
-
-struct mpc_config_intsrc {
-	unsigned char mpc_type;
-	unsigned char mpc_irqtype;
-	unsigned short mpc_irqflag;
-	unsigned char mpc_srcbus;
-	unsigned char mpc_srcbusirq;
-	unsigned char mpc_dstapic;
-	unsigned char mpc_dstirq;
-};
-
-enum mp_irq_source_types {
-	mp_INT = 0,
-	mp_NMI = 1,
-	mp_SMI = 2,
-	mp_ExtINT = 3
-};
-
-#define MP_IRQDIR_DEFAULT	0
-#define MP_IRQDIR_HIGH		1
-#define MP_IRQDIR_LOW		3
-
-#define MP_APIC_ALL	0xFF
-
-struct mpc_config_lintsrc {
-	unsigned char mpc_type;
-	unsigned char mpc_irqtype;
-	unsigned short mpc_irqflag;
-	unsigned char mpc_srcbusid;
-	unsigned char mpc_srcbusirq;
-	unsigned char mpc_destapic;
-	unsigned char mpc_destapiclint;
-};
-
-#define MPC_OEM_SIGNATURE "_OEM"
-
-struct mp_config_oemtable {
-	char oem_signature[4];
-	unsigned short oem_length;	/* Size of table */
-	char  oem_rev;			/* 0x01 */
-	char  oem_checksum;
-	char  mpc_oem[8];
-};
-
-/*
- *	Default configurations
- *
- *	1	2 CPU ISA 82489DX
- *	2	2 CPU EISA 82489DX neither IRQ 0 timer nor IRQ 13 DMA chaining
- *	3	2 CPU EISA 82489DX
- *	4	2 CPU MCA 82489DX
- *	5	2 CPU ISA+PCI
- *	6	2 CPU EISA+PCI
- *	7	2 CPU MCA+PCI
- */
-
-enum mp_bustype {
-	MP_BUS_ISA = 1,
-	MP_BUS_EISA,
-	MP_BUS_PCI,
-	MP_BUS_MCA,
-};
-#endif /* ASM_X86__MPSPEC_DEF_H */
diff --git a/include/asm-x86/msgbuf.h b/include/asm-x86/msgbuf.h
deleted file mode 100644
index 1b538c907a3d..000000000000
--- a/include/asm-x86/msgbuf.h
+++ /dev/null
@@ -1,39 +0,0 @@
-#ifndef ASM_X86__MSGBUF_H
-#define ASM_X86__MSGBUF_H
-
-/*
- * The msqid64_ds structure for i386 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space on i386 is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- *
- * Pad space on x8664 is left for:
- * - 2 miscellaneous 64-bit values
- */
-struct msqid64_ds {
-	struct ipc64_perm msg_perm;
-	__kernel_time_t msg_stime;	/* last msgsnd time */
-#ifdef __i386__
-	unsigned long	__unused1;
-#endif
-	__kernel_time_t msg_rtime;	/* last msgrcv time */
-#ifdef __i386__
-	unsigned long	__unused2;
-#endif
-	__kernel_time_t msg_ctime;	/* last change time */
-#ifdef __i386__
-	unsigned long	__unused3;
-#endif
-	unsigned long  msg_cbytes;	/* current number of bytes on queue */
-	unsigned long  msg_qnum;	/* number of messages in queue */
-	unsigned long  msg_qbytes;	/* max number of bytes on queue */
-	__kernel_pid_t msg_lspid;	/* pid of last msgsnd */
-	__kernel_pid_t msg_lrpid;	/* last receive pid */
-	unsigned long  __unused4;
-	unsigned long  __unused5;
-};
-
-#endif /* ASM_X86__MSGBUF_H */
diff --git a/include/asm-x86/msidef.h b/include/asm-x86/msidef.h
deleted file mode 100644
index ed9190246876..000000000000
--- a/include/asm-x86/msidef.h
+++ /dev/null
@@ -1,55 +0,0 @@
-#ifndef ASM_X86__MSIDEF_H
-#define ASM_X86__MSIDEF_H
-
-/*
- * Constants for Intel APIC based MSI messages.
- */
-
-/*
- * Shifts for MSI data
- */
-
-#define MSI_DATA_VECTOR_SHIFT		0
-#define  MSI_DATA_VECTOR_MASK		0x000000ff
-#define	 MSI_DATA_VECTOR(v)		(((v) << MSI_DATA_VECTOR_SHIFT) & \
-					 MSI_DATA_VECTOR_MASK)
-
-#define MSI_DATA_DELIVERY_MODE_SHIFT	8
-#define  MSI_DATA_DELIVERY_FIXED	(0 << MSI_DATA_DELIVERY_MODE_SHIFT)
-#define  MSI_DATA_DELIVERY_LOWPRI	(1 << MSI_DATA_DELIVERY_MODE_SHIFT)
-
-#define MSI_DATA_LEVEL_SHIFT		14
-#define	 MSI_DATA_LEVEL_DEASSERT	(0 << MSI_DATA_LEVEL_SHIFT)
-#define	 MSI_DATA_LEVEL_ASSERT		(1 << MSI_DATA_LEVEL_SHIFT)
-
-#define MSI_DATA_TRIGGER_SHIFT		15
-#define  MSI_DATA_TRIGGER_EDGE		(0 << MSI_DATA_TRIGGER_SHIFT)
-#define  MSI_DATA_TRIGGER_LEVEL		(1 << MSI_DATA_TRIGGER_SHIFT)
-
-/*
- * Shift/mask fields for msi address
- */
-
-#define MSI_ADDR_BASE_HI		0
-#define MSI_ADDR_BASE_LO		0xfee00000
-
-#define MSI_ADDR_DEST_MODE_SHIFT	2
-#define  MSI_ADDR_DEST_MODE_PHYSICAL	(0 << MSI_ADDR_DEST_MODE_SHIFT)
-#define	 MSI_ADDR_DEST_MODE_LOGICAL	(1 << MSI_ADDR_DEST_MODE_SHIFT)
-
-#define MSI_ADDR_REDIRECTION_SHIFT	3
-#define  MSI_ADDR_REDIRECTION_CPU	(0 << MSI_ADDR_REDIRECTION_SHIFT)
-					/* dedicated cpu */
-#define  MSI_ADDR_REDIRECTION_LOWPRI	(1 << MSI_ADDR_REDIRECTION_SHIFT)
-					/* lowest priority */
-
-#define MSI_ADDR_DEST_ID_SHIFT		12
-#define	 MSI_ADDR_DEST_ID_MASK		0x00ffff0
-#define  MSI_ADDR_DEST_ID(dest)		(((dest) << MSI_ADDR_DEST_ID_SHIFT) & \
-					 MSI_ADDR_DEST_ID_MASK)
-
-#define MSI_ADDR_IR_EXT_INT		(1 << 4)
-#define MSI_ADDR_IR_SHV			(1 << 3)
-#define MSI_ADDR_IR_INDEX1(index)	((index & 0x8000) >> 13)
-#define MSI_ADDR_IR_INDEX2(index)	((index & 0x7fff) << 5)
-#endif /* ASM_X86__MSIDEF_H */
diff --git a/include/asm-x86/msr-index.h b/include/asm-x86/msr-index.h
deleted file mode 100644
index dabd10f0bbee..000000000000
--- a/include/asm-x86/msr-index.h
+++ /dev/null
@@ -1,332 +0,0 @@
-#ifndef ASM_X86__MSR_INDEX_H
-#define ASM_X86__MSR_INDEX_H
-
-/* CPU model specific register (MSR) numbers */
-
-/* x86-64 specific MSRs */
-#define MSR_EFER		0xc0000080 /* extended feature register */
-#define MSR_STAR		0xc0000081 /* legacy mode SYSCALL target */
-#define MSR_LSTAR		0xc0000082 /* long mode SYSCALL target */
-#define MSR_CSTAR		0xc0000083 /* compat mode SYSCALL target */
-#define MSR_SYSCALL_MASK	0xc0000084 /* EFLAGS mask for syscall */
-#define MSR_FS_BASE		0xc0000100 /* 64bit FS base */
-#define MSR_GS_BASE		0xc0000101 /* 64bit GS base */
-#define MSR_KERNEL_GS_BASE	0xc0000102 /* SwapGS GS shadow */
-
-/* EFER bits: */
-#define _EFER_SCE		0  /* SYSCALL/SYSRET */
-#define _EFER_LME		8  /* Long mode enable */
-#define _EFER_LMA		10 /* Long mode active (read-only) */
-#define _EFER_NX		11 /* No execute enable */
-
-#define EFER_SCE		(1<<_EFER_SCE)
-#define EFER_LME		(1<<_EFER_LME)
-#define EFER_LMA		(1<<_EFER_LMA)
-#define EFER_NX			(1<<_EFER_NX)
-
-/* Intel MSRs. Some also available on other CPUs */
-#define MSR_IA32_PERFCTR0		0x000000c1
-#define MSR_IA32_PERFCTR1		0x000000c2
-#define MSR_FSB_FREQ			0x000000cd
-
-#define MSR_MTRRcap			0x000000fe
-#define MSR_IA32_BBL_CR_CTL		0x00000119
-
-#define MSR_IA32_SYSENTER_CS		0x00000174
-#define MSR_IA32_SYSENTER_ESP		0x00000175
-#define MSR_IA32_SYSENTER_EIP		0x00000176
-
-#define MSR_IA32_MCG_CAP		0x00000179
-#define MSR_IA32_MCG_STATUS		0x0000017a
-#define MSR_IA32_MCG_CTL		0x0000017b
-
-#define MSR_IA32_PEBS_ENABLE		0x000003f1
-#define MSR_IA32_DS_AREA		0x00000600
-#define MSR_IA32_PERF_CAPABILITIES	0x00000345
-
-#define MSR_MTRRfix64K_00000		0x00000250
-#define MSR_MTRRfix16K_80000		0x00000258
-#define MSR_MTRRfix16K_A0000		0x00000259
-#define MSR_MTRRfix4K_C0000		0x00000268
-#define MSR_MTRRfix4K_C8000		0x00000269
-#define MSR_MTRRfix4K_D0000		0x0000026a
-#define MSR_MTRRfix4K_D8000		0x0000026b
-#define MSR_MTRRfix4K_E0000		0x0000026c
-#define MSR_MTRRfix4K_E8000		0x0000026d
-#define MSR_MTRRfix4K_F0000		0x0000026e
-#define MSR_MTRRfix4K_F8000		0x0000026f
-#define MSR_MTRRdefType			0x000002ff
-
-#define MSR_IA32_CR_PAT			0x00000277
-
-#define MSR_IA32_DEBUGCTLMSR		0x000001d9
-#define MSR_IA32_LASTBRANCHFROMIP	0x000001db
-#define MSR_IA32_LASTBRANCHTOIP		0x000001dc
-#define MSR_IA32_LASTINTFROMIP		0x000001dd
-#define MSR_IA32_LASTINTTOIP		0x000001de
-
-/* DEBUGCTLMSR bits (others vary by model): */
-#define _DEBUGCTLMSR_LBR	0 /* last branch recording */
-#define _DEBUGCTLMSR_BTF	1 /* single-step on branches */
-
-#define DEBUGCTLMSR_LBR		(1UL << _DEBUGCTLMSR_LBR)
-#define DEBUGCTLMSR_BTF		(1UL << _DEBUGCTLMSR_BTF)
-
-#define MSR_IA32_MC0_CTL		0x00000400
-#define MSR_IA32_MC0_STATUS		0x00000401
-#define MSR_IA32_MC0_ADDR		0x00000402
-#define MSR_IA32_MC0_MISC		0x00000403
-
-#define MSR_P6_PERFCTR0			0x000000c1
-#define MSR_P6_PERFCTR1			0x000000c2
-#define MSR_P6_EVNTSEL0			0x00000186
-#define MSR_P6_EVNTSEL1			0x00000187
-
-/* AMD64 MSRs. Not complete. See the architecture manual for a more
-   complete list. */
-
-#define MSR_AMD64_NB_CFG		0xc001001f
-#define MSR_AMD64_IBSFETCHCTL		0xc0011030
-#define MSR_AMD64_IBSFETCHLINAD		0xc0011031
-#define MSR_AMD64_IBSFETCHPHYSAD	0xc0011032
-#define MSR_AMD64_IBSOPCTL		0xc0011033
-#define MSR_AMD64_IBSOPRIP		0xc0011034
-#define MSR_AMD64_IBSOPDATA		0xc0011035
-#define MSR_AMD64_IBSOPDATA2		0xc0011036
-#define MSR_AMD64_IBSOPDATA3		0xc0011037
-#define MSR_AMD64_IBSDCLINAD		0xc0011038
-#define MSR_AMD64_IBSDCPHYSAD		0xc0011039
-#define MSR_AMD64_IBSCTL		0xc001103a
-
-/* Fam 10h MSRs */
-#define MSR_FAM10H_MMIO_CONF_BASE	0xc0010058
-#define FAM10H_MMIO_CONF_ENABLE		(1<<0)
-#define FAM10H_MMIO_CONF_BUSRANGE_MASK	0xf
-#define FAM10H_MMIO_CONF_BUSRANGE_SHIFT 2
-#define FAM10H_MMIO_CONF_BASE_MASK	0xfffffff
-#define FAM10H_MMIO_CONF_BASE_SHIFT	20
-
-/* K8 MSRs */
-#define MSR_K8_TOP_MEM1			0xc001001a
-#define MSR_K8_TOP_MEM2			0xc001001d
-#define MSR_K8_SYSCFG			0xc0010010
-#define MSR_K8_HWCR			0xc0010015
-#define MSR_K8_INT_PENDING_MSG		0xc0010055
-/* C1E active bits in int pending message */
-#define K8_INTP_C1E_ACTIVE_MASK		0x18000000
-#define MSR_K8_TSEG_ADDR		0xc0010112
-#define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
-#define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
-#define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
-
-/* K7 MSRs */
-#define MSR_K7_EVNTSEL0			0xc0010000
-#define MSR_K7_PERFCTR0			0xc0010004
-#define MSR_K7_EVNTSEL1			0xc0010001
-#define MSR_K7_PERFCTR1			0xc0010005
-#define MSR_K7_EVNTSEL2			0xc0010002
-#define MSR_K7_PERFCTR2			0xc0010006
-#define MSR_K7_EVNTSEL3			0xc0010003
-#define MSR_K7_PERFCTR3			0xc0010007
-#define MSR_K7_CLK_CTL			0xc001001b
-#define MSR_K7_HWCR			0xc0010015
-#define MSR_K7_FID_VID_CTL		0xc0010041
-#define MSR_K7_FID_VID_STATUS		0xc0010042
-
-/* K6 MSRs */
-#define MSR_K6_EFER			0xc0000080
-#define MSR_K6_STAR			0xc0000081
-#define MSR_K6_WHCR			0xc0000082
-#define MSR_K6_UWCCR			0xc0000085
-#define MSR_K6_EPMR			0xc0000086
-#define MSR_K6_PSOR			0xc0000087
-#define MSR_K6_PFIR			0xc0000088
-
-/* Centaur-Hauls/IDT defined MSRs. */
-#define MSR_IDT_FCR1			0x00000107
-#define MSR_IDT_FCR2			0x00000108
-#define MSR_IDT_FCR3			0x00000109
-#define MSR_IDT_FCR4			0x0000010a
-
-#define MSR_IDT_MCR0			0x00000110
-#define MSR_IDT_MCR1			0x00000111
-#define MSR_IDT_MCR2			0x00000112
-#define MSR_IDT_MCR3			0x00000113
-#define MSR_IDT_MCR4			0x00000114
-#define MSR_IDT_MCR5			0x00000115
-#define MSR_IDT_MCR6			0x00000116
-#define MSR_IDT_MCR7			0x00000117
-#define MSR_IDT_MCR_CTRL		0x00000120
-
-/* VIA Cyrix defined MSRs*/
-#define MSR_VIA_FCR			0x00001107
-#define MSR_VIA_LONGHAUL		0x0000110a
-#define MSR_VIA_RNG			0x0000110b
-#define MSR_VIA_BCR2			0x00001147
-
-/* Transmeta defined MSRs */
-#define MSR_TMTA_LONGRUN_CTRL		0x80868010
-#define MSR_TMTA_LONGRUN_FLAGS		0x80868011
-#define MSR_TMTA_LRTI_READOUT		0x80868018
-#define MSR_TMTA_LRTI_VOLT_MHZ		0x8086801a
-
-/* Intel defined MSRs. */
-#define MSR_IA32_P5_MC_ADDR		0x00000000
-#define MSR_IA32_P5_MC_TYPE		0x00000001
-#define MSR_IA32_TSC			0x00000010
-#define MSR_IA32_PLATFORM_ID		0x00000017
-#define MSR_IA32_EBL_CR_POWERON		0x0000002a
-#define MSR_IA32_FEATURE_CONTROL        0x0000003a
-
-#define FEATURE_CONTROL_LOCKED		(1<<0)
-#define FEATURE_CONTROL_VMXON_ENABLED	(1<<2)
-
-#define MSR_IA32_APICBASE		0x0000001b
-#define MSR_IA32_APICBASE_BSP		(1<<8)
-#define MSR_IA32_APICBASE_ENABLE	(1<<11)
-#define MSR_IA32_APICBASE_BASE		(0xfffff<<12)
-
-#define MSR_IA32_UCODE_WRITE		0x00000079
-#define MSR_IA32_UCODE_REV		0x0000008b
-
-#define MSR_IA32_PERF_STATUS		0x00000198
-#define MSR_IA32_PERF_CTL		0x00000199
-
-#define MSR_IA32_MPERF			0x000000e7
-#define MSR_IA32_APERF			0x000000e8
-
-#define MSR_IA32_THERM_CONTROL		0x0000019a
-#define MSR_IA32_THERM_INTERRUPT	0x0000019b
-#define MSR_IA32_THERM_STATUS		0x0000019c
-#define MSR_IA32_MISC_ENABLE		0x000001a0
-
-/* Intel Model 6 */
-#define MSR_P6_EVNTSEL0			0x00000186
-#define MSR_P6_EVNTSEL1			0x00000187
-
-/* P4/Xeon+ specific */
-#define MSR_IA32_MCG_EAX		0x00000180
-#define MSR_IA32_MCG_EBX		0x00000181
-#define MSR_IA32_MCG_ECX		0x00000182
-#define MSR_IA32_MCG_EDX		0x00000183
-#define MSR_IA32_MCG_ESI		0x00000184
-#define MSR_IA32_MCG_EDI		0x00000185
-#define MSR_IA32_MCG_EBP		0x00000186
-#define MSR_IA32_MCG_ESP		0x00000187
-#define MSR_IA32_MCG_EFLAGS		0x00000188
-#define MSR_IA32_MCG_EIP		0x00000189
-#define MSR_IA32_MCG_RESERVED		0x0000018a
-
-/* Pentium IV performance counter MSRs */
-#define MSR_P4_BPU_PERFCTR0		0x00000300
-#define MSR_P4_BPU_PERFCTR1		0x00000301
-#define MSR_P4_BPU_PERFCTR2		0x00000302
-#define MSR_P4_BPU_PERFCTR3		0x00000303
-#define MSR_P4_MS_PERFCTR0		0x00000304
-#define MSR_P4_MS_PERFCTR1		0x00000305
-#define MSR_P4_MS_PERFCTR2		0x00000306
-#define MSR_P4_MS_PERFCTR3		0x00000307
-#define MSR_P4_FLAME_PERFCTR0		0x00000308
-#define MSR_P4_FLAME_PERFCTR1		0x00000309
-#define MSR_P4_FLAME_PERFCTR2		0x0000030a
-#define MSR_P4_FLAME_PERFCTR3		0x0000030b
-#define MSR_P4_IQ_PERFCTR0		0x0000030c
-#define MSR_P4_IQ_PERFCTR1		0x0000030d
-#define MSR_P4_IQ_PERFCTR2		0x0000030e
-#define MSR_P4_IQ_PERFCTR3		0x0000030f
-#define MSR_P4_IQ_PERFCTR4		0x00000310
-#define MSR_P4_IQ_PERFCTR5		0x00000311
-#define MSR_P4_BPU_CCCR0		0x00000360
-#define MSR_P4_BPU_CCCR1		0x00000361
-#define MSR_P4_BPU_CCCR2		0x00000362
-#define MSR_P4_BPU_CCCR3		0x00000363
-#define MSR_P4_MS_CCCR0			0x00000364
-#define MSR_P4_MS_CCCR1			0x00000365
-#define MSR_P4_MS_CCCR2			0x00000366
-#define MSR_P4_MS_CCCR3			0x00000367
-#define MSR_P4_FLAME_CCCR0		0x00000368
-#define MSR_P4_FLAME_CCCR1		0x00000369
-#define MSR_P4_FLAME_CCCR2		0x0000036a
-#define MSR_P4_FLAME_CCCR3		0x0000036b
-#define MSR_P4_IQ_CCCR0			0x0000036c
-#define MSR_P4_IQ_CCCR1			0x0000036d
-#define MSR_P4_IQ_CCCR2			0x0000036e
-#define MSR_P4_IQ_CCCR3			0x0000036f
-#define MSR_P4_IQ_CCCR4			0x00000370
-#define MSR_P4_IQ_CCCR5			0x00000371
-#define MSR_P4_ALF_ESCR0		0x000003ca
-#define MSR_P4_ALF_ESCR1		0x000003cb
-#define MSR_P4_BPU_ESCR0		0x000003b2
-#define MSR_P4_BPU_ESCR1		0x000003b3
-#define MSR_P4_BSU_ESCR0		0x000003a0
-#define MSR_P4_BSU_ESCR1		0x000003a1
-#define MSR_P4_CRU_ESCR0		0x000003b8
-#define MSR_P4_CRU_ESCR1		0x000003b9
-#define MSR_P4_CRU_ESCR2		0x000003cc
-#define MSR_P4_CRU_ESCR3		0x000003cd
-#define MSR_P4_CRU_ESCR4		0x000003e0
-#define MSR_P4_CRU_ESCR5		0x000003e1
-#define MSR_P4_DAC_ESCR0		0x000003a8
-#define MSR_P4_DAC_ESCR1		0x000003a9
-#define MSR_P4_FIRM_ESCR0		0x000003a4
-#define MSR_P4_FIRM_ESCR1		0x000003a5
-#define MSR_P4_FLAME_ESCR0		0x000003a6
-#define MSR_P4_FLAME_ESCR1		0x000003a7
-#define MSR_P4_FSB_ESCR0		0x000003a2
-#define MSR_P4_FSB_ESCR1		0x000003a3
-#define MSR_P4_IQ_ESCR0			0x000003ba
-#define MSR_P4_IQ_ESCR1			0x000003bb
-#define MSR_P4_IS_ESCR0			0x000003b4
-#define MSR_P4_IS_ESCR1			0x000003b5
-#define MSR_P4_ITLB_ESCR0		0x000003b6
-#define MSR_P4_ITLB_ESCR1		0x000003b7
-#define MSR_P4_IX_ESCR0			0x000003c8
-#define MSR_P4_IX_ESCR1			0x000003c9
-#define MSR_P4_MOB_ESCR0		0x000003aa
-#define MSR_P4_MOB_ESCR1		0x000003ab
-#define MSR_P4_MS_ESCR0			0x000003c0
-#define MSR_P4_MS_ESCR1			0x000003c1
-#define MSR_P4_PMH_ESCR0		0x000003ac
-#define MSR_P4_PMH_ESCR1		0x000003ad
-#define MSR_P4_RAT_ESCR0		0x000003bc
-#define MSR_P4_RAT_ESCR1		0x000003bd
-#define MSR_P4_SAAT_ESCR0		0x000003ae
-#define MSR_P4_SAAT_ESCR1		0x000003af
-#define MSR_P4_SSU_ESCR0		0x000003be
-#define MSR_P4_SSU_ESCR1		0x000003bf /* guess: not in manual */
-
-#define MSR_P4_TBPU_ESCR0		0x000003c2
-#define MSR_P4_TBPU_ESCR1		0x000003c3
-#define MSR_P4_TC_ESCR0			0x000003c4
-#define MSR_P4_TC_ESCR1			0x000003c5
-#define MSR_P4_U2L_ESCR0		0x000003b0
-#define MSR_P4_U2L_ESCR1		0x000003b1
-
-/* Intel Core-based CPU performance counters */
-#define MSR_CORE_PERF_FIXED_CTR0	0x00000309
-#define MSR_CORE_PERF_FIXED_CTR1	0x0000030a
-#define MSR_CORE_PERF_FIXED_CTR2	0x0000030b
-#define MSR_CORE_PERF_FIXED_CTR_CTRL	0x0000038d
-#define MSR_CORE_PERF_GLOBAL_STATUS	0x0000038e
-#define MSR_CORE_PERF_GLOBAL_CTRL	0x0000038f
-#define MSR_CORE_PERF_GLOBAL_OVF_CTRL	0x00000390
-
-/* Geode defined MSRs */
-#define MSR_GEODE_BUSCONT_CONF0		0x00001900
-
-/* Intel VT MSRs */
-#define MSR_IA32_VMX_BASIC              0x00000480
-#define MSR_IA32_VMX_PINBASED_CTLS      0x00000481
-#define MSR_IA32_VMX_PROCBASED_CTLS     0x00000482
-#define MSR_IA32_VMX_EXIT_CTLS          0x00000483
-#define MSR_IA32_VMX_ENTRY_CTLS         0x00000484
-#define MSR_IA32_VMX_MISC               0x00000485
-#define MSR_IA32_VMX_CR0_FIXED0         0x00000486
-#define MSR_IA32_VMX_CR0_FIXED1         0x00000487
-#define MSR_IA32_VMX_CR4_FIXED0         0x00000488
-#define MSR_IA32_VMX_CR4_FIXED1         0x00000489
-#define MSR_IA32_VMX_VMCS_ENUM          0x0000048a
-#define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
-#define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
-
-#endif /* ASM_X86__MSR_INDEX_H */
diff --git a/include/asm-x86/msr.h b/include/asm-x86/msr.h
deleted file mode 100644
index 530af1f6389e..000000000000
--- a/include/asm-x86/msr.h
+++ /dev/null
@@ -1,247 +0,0 @@
-#ifndef ASM_X86__MSR_H
-#define ASM_X86__MSR_H
-
-#include <asm/msr-index.h>
-
-#ifndef __ASSEMBLY__
-# include <linux/types.h>
-#endif
-
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-
-#include <asm/asm.h>
-#include <asm/errno.h>
-
-static inline unsigned long long native_read_tscp(unsigned int *aux)
-{
-	unsigned long low, high;
-	asm volatile(".byte 0x0f,0x01,0xf9"
-		     : "=a" (low), "=d" (high), "=c" (*aux));
-	return low | ((u64)high << 32);
-}
-
-/*
- * i386 calling convention returns 64-bit value in edx:eax, while
- * x86_64 returns at rax. Also, the "A" constraint does not really
- * mean rdx:rax in x86_64, so we need specialized behaviour for each
- * architecture
- */
-#ifdef CONFIG_X86_64
-#define DECLARE_ARGS(val, low, high)	unsigned low, high
-#define EAX_EDX_VAL(val, low, high)	((low) | ((u64)(high) << 32))
-#define EAX_EDX_ARGS(val, low, high)	"a" (low), "d" (high)
-#define EAX_EDX_RET(val, low, high)	"=a" (low), "=d" (high)
-#else
-#define DECLARE_ARGS(val, low, high)	unsigned long long val
-#define EAX_EDX_VAL(val, low, high)	(val)
-#define EAX_EDX_ARGS(val, low, high)	"A" (val)
-#define EAX_EDX_RET(val, low, high)	"=A" (val)
-#endif
-
-static inline unsigned long long native_read_msr(unsigned int msr)
-{
-	DECLARE_ARGS(val, low, high);
-
-	asm volatile("rdmsr" : EAX_EDX_RET(val, low, high) : "c" (msr));
-	return EAX_EDX_VAL(val, low, high);
-}
-
-static inline unsigned long long native_read_msr_safe(unsigned int msr,
-						      int *err)
-{
-	DECLARE_ARGS(val, low, high);
-
-	asm volatile("2: rdmsr ; xor %[err],%[err]\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
-		     : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
-		     : "c" (msr), [fault] "i" (-EFAULT));
-	return EAX_EDX_VAL(val, low, high);
-}
-
-static inline unsigned long long native_read_msr_amd_safe(unsigned int msr,
-						      int *err)
-{
-	DECLARE_ARGS(val, low, high);
-
-	asm volatile("2: rdmsr ; xor %0,%0\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %3,%0 ; jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
-		     : "=r" (*err), EAX_EDX_RET(val, low, high)
-		     : "c" (msr), "D" (0x9c5a203a), "i" (-EFAULT));
-	return EAX_EDX_VAL(val, low, high);
-}
-
-static inline void native_write_msr(unsigned int msr,
-				    unsigned low, unsigned high)
-{
-	asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
-}
-
-static inline int native_write_msr_safe(unsigned int msr,
-					unsigned low, unsigned high)
-{
-	int err;
-	asm volatile("2: wrmsr ; xor %[err],%[err]\n"
-		     "1:\n\t"
-		     ".section .fixup,\"ax\"\n\t"
-		     "3:  mov %[fault],%[err] ; jmp 1b\n\t"
-		     ".previous\n\t"
-		     _ASM_EXTABLE(2b, 3b)
-		     : [err] "=a" (err)
-		     : "c" (msr), "0" (low), "d" (high),
-		       [fault] "i" (-EFAULT)
-		     : "memory");
-	return err;
-}
-
-extern unsigned long long native_read_tsc(void);
-
-static __always_inline unsigned long long __native_read_tsc(void)
-{
-	DECLARE_ARGS(val, low, high);
-
-	rdtsc_barrier();
-	asm volatile("rdtsc" : EAX_EDX_RET(val, low, high));
-	rdtsc_barrier();
-
-	return EAX_EDX_VAL(val, low, high);
-}
-
-static inline unsigned long long native_read_pmc(int counter)
-{
-	DECLARE_ARGS(val, low, high);
-
-	asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter));
-	return EAX_EDX_VAL(val, low, high);
-}
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-#include <linux/errno.h>
-/*
- * Access to machine-specific registers (available on 586 and better only)
- * Note: the rd* operations modify the parameters directly (without using
- * pointer indirection), this allows gcc to optimize better
- */
-
-#define rdmsr(msr, val1, val2)					\
-do {								\
-	u64 __val = native_read_msr((msr));			\
-	(val1) = (u32)__val;					\
-	(val2) = (u32)(__val >> 32);				\
-} while (0)
-
-static inline void wrmsr(unsigned msr, unsigned low, unsigned high)
-{
-	native_write_msr(msr, low, high);
-}
-
-#define rdmsrl(msr, val)			\
-	((val) = native_read_msr((msr)))
-
-#define wrmsrl(msr, val)						\
-	native_write_msr((msr), (u32)((u64)(val)), (u32)((u64)(val) >> 32))
-
-/* wrmsr with exception handling */
-static inline int wrmsr_safe(unsigned msr, unsigned low, unsigned high)
-{
-	return native_write_msr_safe(msr, low, high);
-}
-
-/* rdmsr with exception handling */
-#define rdmsr_safe(msr, p1, p2)					\
-({								\
-	int __err;						\
-	u64 __val = native_read_msr_safe((msr), &__err);	\
-	(*p1) = (u32)__val;					\
-	(*p2) = (u32)(__val >> 32);				\
-	__err;							\
-})
-
-static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
-{
-	int err;
-
-	*p = native_read_msr_safe(msr, &err);
-	return err;
-}
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
-{
-	int err;
-
-	*p = native_read_msr_amd_safe(msr, &err);
-	return err;
-}
-
-#define rdtscl(low)						\
-	((low) = (u32)native_read_tsc())
-
-#define rdtscll(val)						\
-	((val) = native_read_tsc())
-
-#define rdpmc(counter, low, high)			\
-do {							\
-	u64 _l = native_read_pmc((counter));		\
-	(low)  = (u32)_l;				\
-	(high) = (u32)(_l >> 32);			\
-} while (0)
-
-#define rdtscp(low, high, aux)					\
-do {                                                            \
-	unsigned long long _val = native_read_tscp(&(aux));     \
-	(low) = (u32)_val;                                      \
-	(high) = (u32)(_val >> 32);                             \
-} while (0)
-
-#define rdtscpll(val, aux) (val) = native_read_tscp(&(aux))
-
-#endif	/* !CONFIG_PARAVIRT */
-
-
-#define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val),		\
-					     (u32)((val) >> 32))
-
-#define write_tsc(val1, val2) wrmsr(0x10, (val1), (val2))
-
-#define write_rdtscp_aux(val) wrmsr(0xc0000103, (val), 0)
-
-#ifdef CONFIG_SMP
-int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
-int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
-int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
-int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
-#else  /*  CONFIG_SMP  */
-static inline int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
-{
-	rdmsr(msr_no, *l, *h);
-	return 0;
-}
-static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
-{
-	wrmsr(msr_no, l, h);
-	return 0;
-}
-static inline int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no,
-				    u32 *l, u32 *h)
-{
-	return rdmsr_safe(msr_no, l, h);
-}
-static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
-{
-	return wrmsr_safe(msr_no, l, h);
-}
-#endif  /* CONFIG_SMP */
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
-
-#endif /* ASM_X86__MSR_H */
diff --git a/include/asm-x86/mtrr.h b/include/asm-x86/mtrr.h
deleted file mode 100644
index 23a7f83da953..000000000000
--- a/include/asm-x86/mtrr.h
+++ /dev/null
@@ -1,173 +0,0 @@
-/*  Generic MTRR (Memory Type Range Register) ioctls.
-
-    Copyright (C) 1997-1999  Richard Gooch
-
-    This library is free software; you can redistribute it and/or
-    modify it under the terms of the GNU Library General Public
-    License as published by the Free Software Foundation; either
-    version 2 of the License, or (at your option) any later version.
-
-    This library is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-    Library General Public License for more details.
-
-    You should have received a copy of the GNU Library General Public
-    License along with this library; if not, write to the Free
-    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-
-    Richard Gooch may be reached by email at  rgooch@atnf.csiro.au
-    The postal address is:
-      Richard Gooch, c/o ATNF, P. O. Box 76, Epping, N.S.W., 2121, Australia.
-*/
-#ifndef ASM_X86__MTRR_H
-#define ASM_X86__MTRR_H
-
-#include <linux/ioctl.h>
-#include <linux/errno.h>
-
-#define	MTRR_IOCTL_BASE	'M'
-
-struct mtrr_sentry {
-    unsigned long base;    /*  Base address     */
-    unsigned int size;    /*  Size of region   */
-    unsigned int type;     /*  Type of region   */
-};
-
-/* Warning: this structure has a different order from i386
-   on x86-64. The 32bit emulation code takes care of that.
-   But you need to use this for 64bit, otherwise your X server
-   will break. */
-
-#ifdef __i386__
-struct mtrr_gentry {
-    unsigned int regnum;   /*  Register number  */
-    unsigned long base;    /*  Base address     */
-    unsigned int size;    /*  Size of region   */
-    unsigned int type;     /*  Type of region   */
-};
-
-#else /* __i386__ */
-
-struct mtrr_gentry {
-    unsigned long base;    /*  Base address     */
-    unsigned int size;    /*  Size of region   */
-    unsigned int regnum;   /*  Register number  */
-    unsigned int type;     /*  Type of region   */
-};
-#endif /* !__i386__ */
-
-/*  These are the various ioctls  */
-#define MTRRIOC_ADD_ENTRY        _IOW(MTRR_IOCTL_BASE,  0, struct mtrr_sentry)
-#define MTRRIOC_SET_ENTRY        _IOW(MTRR_IOCTL_BASE,  1, struct mtrr_sentry)
-#define MTRRIOC_DEL_ENTRY        _IOW(MTRR_IOCTL_BASE,  2, struct mtrr_sentry)
-#define MTRRIOC_GET_ENTRY        _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry)
-#define MTRRIOC_KILL_ENTRY       _IOW(MTRR_IOCTL_BASE,  4, struct mtrr_sentry)
-#define MTRRIOC_ADD_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  5, struct mtrr_sentry)
-#define MTRRIOC_SET_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  6, struct mtrr_sentry)
-#define MTRRIOC_DEL_PAGE_ENTRY   _IOW(MTRR_IOCTL_BASE,  7, struct mtrr_sentry)
-#define MTRRIOC_GET_PAGE_ENTRY   _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry)
-#define MTRRIOC_KILL_PAGE_ENTRY  _IOW(MTRR_IOCTL_BASE,  9, struct mtrr_sentry)
-
-/*  These are the region types  */
-#define MTRR_TYPE_UNCACHABLE 0
-#define MTRR_TYPE_WRCOMB     1
-/*#define MTRR_TYPE_         2*/
-/*#define MTRR_TYPE_         3*/
-#define MTRR_TYPE_WRTHROUGH  4
-#define MTRR_TYPE_WRPROT     5
-#define MTRR_TYPE_WRBACK     6
-#define MTRR_NUM_TYPES       7
-
-#ifdef __KERNEL__
-
-/*  The following functions are for use by other drivers  */
-# ifdef CONFIG_MTRR
-extern u8 mtrr_type_lookup(u64 addr, u64 end);
-extern void mtrr_save_fixed_ranges(void *);
-extern void mtrr_save_state(void);
-extern int mtrr_add(unsigned long base, unsigned long size,
-		    unsigned int type, bool increment);
-extern int mtrr_add_page(unsigned long base, unsigned long size,
-			 unsigned int type, bool increment);
-extern int mtrr_del(int reg, unsigned long base, unsigned long size);
-extern int mtrr_del_page(int reg, unsigned long base, unsigned long size);
-extern void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi);
-extern void mtrr_ap_init(void);
-extern void mtrr_bp_init(void);
-extern int mtrr_trim_uncached_memory(unsigned long end_pfn);
-extern int amd_special_default_mtrr(void);
-#  else
-static inline u8 mtrr_type_lookup(u64 addr, u64 end)
-{
-	/*
-	 * Return no-MTRRs:
-	 */
-	return 0xff;
-}
-#define mtrr_save_fixed_ranges(arg) do {} while (0)
-#define mtrr_save_state() do {} while (0)
-static inline int mtrr_add(unsigned long base, unsigned long size,
-			   unsigned int type, bool increment)
-{
-    return -ENODEV;
-}
-static inline int mtrr_add_page(unsigned long base, unsigned long size,
-				unsigned int type, bool increment)
-{
-    return -ENODEV;
-}
-static inline int mtrr_del(int reg, unsigned long base, unsigned long size)
-{
-    return -ENODEV;
-}
-static inline int mtrr_del_page(int reg, unsigned long base, unsigned long size)
-{
-    return -ENODEV;
-}
-static inline int mtrr_trim_uncached_memory(unsigned long end_pfn)
-{
-	return 0;
-}
-static inline void mtrr_centaur_report_mcr(int mcr, u32 lo, u32 hi)
-{
-}
-
-#define mtrr_ap_init() do {} while (0)
-#define mtrr_bp_init() do {} while (0)
-#  endif
-
-#ifdef CONFIG_COMPAT
-#include <linux/compat.h>
-
-struct mtrr_sentry32 {
-    compat_ulong_t base;    /*  Base address     */
-    compat_uint_t size;    /*  Size of region   */
-    compat_uint_t type;     /*  Type of region   */
-};
-
-struct mtrr_gentry32 {
-    compat_ulong_t regnum;   /*  Register number  */
-    compat_uint_t base;    /*  Base address     */
-    compat_uint_t size;    /*  Size of region   */
-    compat_uint_t type;     /*  Type of region   */
-};
-
-#define MTRR_IOCTL_BASE 'M'
-
-#define MTRRIOC32_ADD_ENTRY      _IOW(MTRR_IOCTL_BASE,  0, struct mtrr_sentry32)
-#define MTRRIOC32_SET_ENTRY      _IOW(MTRR_IOCTL_BASE,  1, struct mtrr_sentry32)
-#define MTRRIOC32_DEL_ENTRY      _IOW(MTRR_IOCTL_BASE,  2, struct mtrr_sentry32)
-#define MTRRIOC32_GET_ENTRY      _IOWR(MTRR_IOCTL_BASE, 3, struct mtrr_gentry32)
-#define MTRRIOC32_KILL_ENTRY     _IOW(MTRR_IOCTL_BASE,  4, struct mtrr_sentry32)
-#define MTRRIOC32_ADD_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE,  5, struct mtrr_sentry32)
-#define MTRRIOC32_SET_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE,  6, struct mtrr_sentry32)
-#define MTRRIOC32_DEL_PAGE_ENTRY _IOW(MTRR_IOCTL_BASE,  7, struct mtrr_sentry32)
-#define MTRRIOC32_GET_PAGE_ENTRY _IOWR(MTRR_IOCTL_BASE, 8, struct mtrr_gentry32)
-#define MTRRIOC32_KILL_PAGE_ENTRY		\
-				 _IOW(MTRR_IOCTL_BASE,  9, struct mtrr_sentry32)
-#endif /* CONFIG_COMPAT */
-
-#endif /* __KERNEL__ */
-
-#endif /* ASM_X86__MTRR_H */
diff --git a/include/asm-x86/mutex.h b/include/asm-x86/mutex.h
deleted file mode 100644
index a731b9c573a6..000000000000
--- a/include/asm-x86/mutex.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "mutex_32.h"
-#else
-# include "mutex_64.h"
-#endif
diff --git a/include/asm-x86/mutex_32.h b/include/asm-x86/mutex_32.h
deleted file mode 100644
index 25c16d8ba3c7..000000000000
--- a/include/asm-x86/mutex_32.h
+++ /dev/null
@@ -1,125 +0,0 @@
-/*
- * Assembly implementation of the mutex fastpath, based on atomic
- * decrement/increment.
- *
- * started by Ingo Molnar:
- *
- *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- */
-#ifndef ASM_X86__MUTEX_32_H
-#define ASM_X86__MUTEX_32_H
-
-#include <asm/alternative.h>
-
-/**
- *  __mutex_fastpath_lock - try to take the lock by moving the count
- *                          from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *  @fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fn> if it
- * wasn't 1 originally. This function MUST leave the value lower than 1
- * even when the "1" assertion wasn't true.
- */
-#define __mutex_fastpath_lock(count, fail_fn)			\
-do {								\
-	unsigned int dummy;					\
-								\
-	typecheck(atomic_t *, count);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   decl (%%eax)\n"		\
-		     "   jns 1f	\n"				\
-		     "   call " #fail_fn "\n"			\
-		     "1:\n"					\
-		     : "=a" (dummy)				\
-		     : "a" (count)				\
-		     : "memory", "ecx", "edx");			\
-} while (0)
-
-
-/**
- *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
- *                                 from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fail_fn> if it
- * wasn't 1 originally. This function returns 0 if the fastpath succeeds,
- * or anything the slow path function returns
- */
-static inline int __mutex_fastpath_lock_retval(atomic_t *count,
-					       int (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_dec_return(count) < 0))
-		return fail_fn(count);
-	else
-		return 0;
-}
-
-/**
- *  __mutex_fastpath_unlock - try to promote the mutex from 0 to 1
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 0
- *
- * try to promote the mutex from 0 to 1. if it wasn't 0, call <fail_fn>.
- * In the failure case, this function is allowed to either set the value
- * to 1, or to set it to a value lower than 1.
- *
- * If the implementation sets it to a value of lower than 1, the
- * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
- * to return 0 otherwise.
- */
-#define __mutex_fastpath_unlock(count, fail_fn)			\
-do {								\
-	unsigned int dummy;					\
-								\
-	typecheck(atomic_t *, count);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   incl (%%eax)\n"		\
-		     "   jg	1f\n"				\
-		     "   call " #fail_fn "\n"			\
-		     "1:\n"					\
-		     : "=a" (dummy)				\
-		     : "a" (count)				\
-		     : "memory", "ecx", "edx");			\
-} while (0)
-
-#define __mutex_slowpath_needs_to_unlock()	1
-
-/**
- * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
- *
- *  @count: pointer of type atomic_t
- *  @fail_fn: fallback function
- *
- * Change the count from 1 to a value lower than 1, and return 0 (failure)
- * if it wasn't 1 originally, or return 1 (success) otherwise. This function
- * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
- * Additionally, if the value was < 0 originally, this function must not leave
- * it to 0 on failure.
- */
-static inline int __mutex_fastpath_trylock(atomic_t *count,
-					   int (*fail_fn)(atomic_t *))
-{
-	/*
-	 * We have two variants here. The cmpxchg based one is the best one
-	 * because it never induce a false contention state.  It is included
-	 * here because architectures using the inc/dec algorithms over the
-	 * xchg ones are much more likely to support cmpxchg natively.
-	 *
-	 * If not we fall back to the spinlock based variant - that is
-	 * just as efficient (and simpler) as a 'destructive' probing of
-	 * the mutex state would be.
-	 */
-#ifdef __HAVE_ARCH_CMPXCHG
-	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
-		return 1;
-	return 0;
-#else
-	return fail_fn(count);
-#endif
-}
-
-#endif /* ASM_X86__MUTEX_32_H */
diff --git a/include/asm-x86/mutex_64.h b/include/asm-x86/mutex_64.h
deleted file mode 100644
index 918ba21ab9d9..000000000000
--- a/include/asm-x86/mutex_64.h
+++ /dev/null
@@ -1,100 +0,0 @@
-/*
- * Assembly implementation of the mutex fastpath, based on atomic
- * decrement/increment.
- *
- * started by Ingo Molnar:
- *
- *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- */
-#ifndef ASM_X86__MUTEX_64_H
-#define ASM_X86__MUTEX_64_H
-
-/**
- * __mutex_fastpath_lock - decrement and call function if negative
- * @v: pointer of type atomic_t
- * @fail_fn: function to call if the result is negative
- *
- * Atomically decrements @v and calls <fail_fn> if the result is negative.
- */
-#define __mutex_fastpath_lock(v, fail_fn)			\
-do {								\
-	unsigned long dummy;					\
-								\
-	typecheck(atomic_t *, v);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   decl (%%rdi)\n"		\
-		     "   jns 1f		\n"			\
-		     "   call " #fail_fn "\n"			\
-		     "1:"					\
-		     : "=D" (dummy)				\
-		     : "D" (v)					\
-		     : "rax", "rsi", "rdx", "rcx",		\
-		       "r8", "r9", "r10", "r11", "memory");	\
-} while (0)
-
-/**
- *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
- *                                 from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fail_fn> if
- * it wasn't 1 originally. This function returns 0 if the fastpath succeeds,
- * or anything the slow path function returns
- */
-static inline int __mutex_fastpath_lock_retval(atomic_t *count,
-					       int (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_dec_return(count) < 0))
-		return fail_fn(count);
-	else
-		return 0;
-}
-
-/**
- * __mutex_fastpath_unlock - increment and call function if nonpositive
- * @v: pointer of type atomic_t
- * @fail_fn: function to call if the result is nonpositive
- *
- * Atomically increments @v and calls <fail_fn> if the result is nonpositive.
- */
-#define __mutex_fastpath_unlock(v, fail_fn)			\
-do {								\
-	unsigned long dummy;					\
-								\
-	typecheck(atomic_t *, v);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   incl (%%rdi)\n"		\
-		     "   jg 1f\n"				\
-		     "   call " #fail_fn "\n"			\
-		     "1:"					\
-		     : "=D" (dummy)				\
-		     : "D" (v)					\
-		     : "rax", "rsi", "rdx", "rcx",		\
-		       "r8", "r9", "r10", "r11", "memory");	\
-} while (0)
-
-#define __mutex_slowpath_needs_to_unlock()	1
-
-/**
- * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
- *
- *  @count: pointer of type atomic_t
- *  @fail_fn: fallback function
- *
- * Change the count from 1 to 0 and return 1 (success), or return 0 (failure)
- * if it wasn't 1 originally. [the fallback function is never used on
- * x86_64, because all x86_64 CPUs have a CMPXCHG instruction.]
- */
-static inline int __mutex_fastpath_trylock(atomic_t *count,
-					   int (*fail_fn)(atomic_t *))
-{
-	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
-		return 1;
-	else
-		return 0;
-}
-
-#endif /* ASM_X86__MUTEX_64_H */
diff --git a/include/asm-x86/nmi.h b/include/asm-x86/nmi.h
deleted file mode 100644
index a53f829a97c5..000000000000
--- a/include/asm-x86/nmi.h
+++ /dev/null
@@ -1,81 +0,0 @@
-#ifndef ASM_X86__NMI_H
-#define ASM_X86__NMI_H
-
-#include <linux/pm.h>
-#include <asm/irq.h>
-#include <asm/io.h>
-
-#ifdef ARCH_HAS_NMI_WATCHDOG
-
-/**
- * do_nmi_callback
- *
- * Check to see if a callback exists and execute it.  Return 1
- * if the handler exists and was handled successfully.
- */
-int do_nmi_callback(struct pt_regs *regs, int cpu);
-
-extern void die_nmi(char *str, struct pt_regs *regs, int do_panic);
-extern int check_nmi_watchdog(void);
-extern int nmi_watchdog_enabled;
-extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
-extern int avail_to_resrv_perfctr_nmi(unsigned int);
-extern int reserve_perfctr_nmi(unsigned int);
-extern void release_perfctr_nmi(unsigned int);
-extern int reserve_evntsel_nmi(unsigned int);
-extern void release_evntsel_nmi(unsigned int);
-
-extern void setup_apic_nmi_watchdog(void *);
-extern void stop_apic_nmi_watchdog(void *);
-extern void disable_timer_nmi_watchdog(void);
-extern void enable_timer_nmi_watchdog(void);
-extern int nmi_watchdog_tick(struct pt_regs *regs, unsigned reason);
-extern void cpu_nmi_set_wd_enabled(void);
-
-extern atomic_t nmi_active;
-extern unsigned int nmi_watchdog;
-#define NMI_NONE	0
-#define NMI_IO_APIC	1
-#define NMI_LOCAL_APIC	2
-#define NMI_INVALID	3
-
-struct ctl_table;
-struct file;
-extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
-			void __user *, size_t *, loff_t *);
-extern int unknown_nmi_panic;
-
-void __trigger_all_cpu_backtrace(void);
-#define trigger_all_cpu_backtrace() __trigger_all_cpu_backtrace()
-
-static inline void localise_nmi_watchdog(void)
-{
-	if (nmi_watchdog == NMI_IO_APIC)
-		nmi_watchdog = NMI_LOCAL_APIC;
-}
-
-/* check if nmi_watchdog is active (ie was specified at boot) */
-static inline int nmi_watchdog_active(void)
-{
-	/*
-	 * actually it should be:
-	 * 	return (nmi_watchdog == NMI_LOCAL_APIC ||
-	 * 		nmi_watchdog == NMI_IO_APIC)
-	 * but since they are power of two we could use a
-	 * cheaper way --cvg
-	 */
-	return nmi_watchdog & 0x3;
-}
-#endif
-
-void lapic_watchdog_stop(void);
-int lapic_watchdog_init(unsigned nmi_hz);
-int lapic_wd_event(unsigned nmi_hz);
-unsigned lapic_adjust_nmi_hz(unsigned hz);
-int lapic_watchdog_ok(void);
-void disable_lapic_nmi_watchdog(void);
-void enable_lapic_nmi_watchdog(void);
-void stop_nmi(void);
-void restart_nmi(void);
-
-#endif /* ASM_X86__NMI_H */
diff --git a/include/asm-x86/nops.h b/include/asm-x86/nops.h
deleted file mode 100644
index ae742721ae73..000000000000
--- a/include/asm-x86/nops.h
+++ /dev/null
@@ -1,118 +0,0 @@
-#ifndef ASM_X86__NOPS_H
-#define ASM_X86__NOPS_H
-
-/* Define nops for use with alternative() */
-
-/* generic versions from gas
-   1: nop
-   the following instructions are NOT nops in 64-bit mode,
-   for 64-bit mode use K8 or P6 nops instead
-   2: movl %esi,%esi
-   3: leal 0x00(%esi),%esi
-   4: leal 0x00(,%esi,1),%esi
-   6: leal 0x00000000(%esi),%esi
-   7: leal 0x00000000(,%esi,1),%esi
-*/
-#define GENERIC_NOP1 ".byte 0x90\n"
-#define GENERIC_NOP2 ".byte 0x89,0xf6\n"
-#define GENERIC_NOP3 ".byte 0x8d,0x76,0x00\n"
-#define GENERIC_NOP4 ".byte 0x8d,0x74,0x26,0x00\n"
-#define GENERIC_NOP5 GENERIC_NOP1 GENERIC_NOP4
-#define GENERIC_NOP6 ".byte 0x8d,0xb6,0x00,0x00,0x00,0x00\n"
-#define GENERIC_NOP7 ".byte 0x8d,0xb4,0x26,0x00,0x00,0x00,0x00\n"
-#define GENERIC_NOP8 GENERIC_NOP1 GENERIC_NOP7
-
-/* Opteron 64bit nops
-   1: nop
-   2: osp nop
-   3: osp osp nop
-   4: osp osp osp nop
-*/
-#define K8_NOP1 GENERIC_NOP1
-#define K8_NOP2	".byte 0x66,0x90\n"
-#define K8_NOP3	".byte 0x66,0x66,0x90\n"
-#define K8_NOP4	".byte 0x66,0x66,0x66,0x90\n"
-#define K8_NOP5	K8_NOP3 K8_NOP2
-#define K8_NOP6	K8_NOP3 K8_NOP3
-#define K8_NOP7	K8_NOP4 K8_NOP3
-#define K8_NOP8	K8_NOP4 K8_NOP4
-
-/* K7 nops
-   uses eax dependencies (arbitary choice)
-   1: nop
-   2: movl %eax,%eax
-   3: leal (,%eax,1),%eax
-   4: leal 0x00(,%eax,1),%eax
-   6: leal 0x00000000(%eax),%eax
-   7: leal 0x00000000(,%eax,1),%eax
-*/
-#define K7_NOP1	GENERIC_NOP1
-#define K7_NOP2	".byte 0x8b,0xc0\n"
-#define K7_NOP3	".byte 0x8d,0x04,0x20\n"
-#define K7_NOP4	".byte 0x8d,0x44,0x20,0x00\n"
-#define K7_NOP5	K7_NOP4 ASM_NOP1
-#define K7_NOP6	".byte 0x8d,0x80,0,0,0,0\n"
-#define K7_NOP7	".byte 0x8D,0x04,0x05,0,0,0,0\n"
-#define K7_NOP8	K7_NOP7 ASM_NOP1
-
-/* P6 nops
-   uses eax dependencies (Intel-recommended choice)
-   1: nop
-   2: osp nop
-   3: nopl (%eax)
-   4: nopl 0x00(%eax)
-   5: nopl 0x00(%eax,%eax,1)
-   6: osp nopl 0x00(%eax,%eax,1)
-   7: nopl 0x00000000(%eax)
-   8: nopl 0x00000000(%eax,%eax,1)
-*/
-#define P6_NOP1	GENERIC_NOP1
-#define P6_NOP2	".byte 0x66,0x90\n"
-#define P6_NOP3	".byte 0x0f,0x1f,0x00\n"
-#define P6_NOP4	".byte 0x0f,0x1f,0x40,0\n"
-#define P6_NOP5	".byte 0x0f,0x1f,0x44,0x00,0\n"
-#define P6_NOP6	".byte 0x66,0x0f,0x1f,0x44,0x00,0\n"
-#define P6_NOP7	".byte 0x0f,0x1f,0x80,0,0,0,0\n"
-#define P6_NOP8	".byte 0x0f,0x1f,0x84,0x00,0,0,0,0\n"
-
-#if defined(CONFIG_MK7)
-#define ASM_NOP1 K7_NOP1
-#define ASM_NOP2 K7_NOP2
-#define ASM_NOP3 K7_NOP3
-#define ASM_NOP4 K7_NOP4
-#define ASM_NOP5 K7_NOP5
-#define ASM_NOP6 K7_NOP6
-#define ASM_NOP7 K7_NOP7
-#define ASM_NOP8 K7_NOP8
-#elif defined(CONFIG_X86_P6_NOP)
-#define ASM_NOP1 P6_NOP1
-#define ASM_NOP2 P6_NOP2
-#define ASM_NOP3 P6_NOP3
-#define ASM_NOP4 P6_NOP4
-#define ASM_NOP5 P6_NOP5
-#define ASM_NOP6 P6_NOP6
-#define ASM_NOP7 P6_NOP7
-#define ASM_NOP8 P6_NOP8
-#elif defined(CONFIG_X86_64)
-#define ASM_NOP1 K8_NOP1
-#define ASM_NOP2 K8_NOP2
-#define ASM_NOP3 K8_NOP3
-#define ASM_NOP4 K8_NOP4
-#define ASM_NOP5 K8_NOP5
-#define ASM_NOP6 K8_NOP6
-#define ASM_NOP7 K8_NOP7
-#define ASM_NOP8 K8_NOP8
-#else
-#define ASM_NOP1 GENERIC_NOP1
-#define ASM_NOP2 GENERIC_NOP2
-#define ASM_NOP3 GENERIC_NOP3
-#define ASM_NOP4 GENERIC_NOP4
-#define ASM_NOP5 GENERIC_NOP5
-#define ASM_NOP6 GENERIC_NOP6
-#define ASM_NOP7 GENERIC_NOP7
-#define ASM_NOP8 GENERIC_NOP8
-#endif
-
-#define ASM_NOP_MAX 8
-
-#endif /* ASM_X86__NOPS_H */
diff --git a/include/asm-x86/numa.h b/include/asm-x86/numa.h
deleted file mode 100644
index 27da400d3138..000000000000
--- a/include/asm-x86/numa.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "numa_32.h"
-#else
-# include "numa_64.h"
-#endif
diff --git a/include/asm-x86/numa_32.h b/include/asm-x86/numa_32.h
deleted file mode 100644
index 44cb07855c5b..000000000000
--- a/include/asm-x86/numa_32.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef ASM_X86__NUMA_32_H
-#define ASM_X86__NUMA_32_H
-
-extern int pxm_to_nid(int pxm);
-extern void numa_remove_cpu(int cpu);
-
-#ifdef CONFIG_NUMA
-extern void set_highmem_pages_init(void);
-#endif
-
-#endif /* ASM_X86__NUMA_32_H */
diff --git a/include/asm-x86/numa_64.h b/include/asm-x86/numa_64.h
deleted file mode 100644
index 15c990395b02..000000000000
--- a/include/asm-x86/numa_64.h
+++ /dev/null
@@ -1,43 +0,0 @@
-#ifndef ASM_X86__NUMA_64_H
-#define ASM_X86__NUMA_64_H
-
-#include <linux/nodemask.h>
-#include <asm/apicdef.h>
-
-struct bootnode {
-	u64 start;
-	u64 end;
-};
-
-extern int compute_hash_shift(struct bootnode *nodes, int numblks,
-			      int *nodeids);
-
-#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT))
-
-extern void numa_init_array(void);
-extern int numa_off;
-
-extern void srat_reserve_add_area(int nodeid);
-extern int hotadd_percent;
-
-extern s16 apicid_to_node[MAX_LOCAL_APIC];
-
-extern unsigned long numa_free_all_bootmem(void);
-extern void setup_node_bootmem(int nodeid, unsigned long start,
-			       unsigned long end);
-
-#ifdef CONFIG_NUMA
-extern void __init init_cpu_to_node(void);
-extern void __cpuinit numa_set_node(int cpu, int node);
-extern void __cpuinit numa_clear_node(int cpu);
-extern void __cpuinit numa_add_cpu(int cpu);
-extern void __cpuinit numa_remove_cpu(int cpu);
-#else
-static inline void init_cpu_to_node(void)		{ }
-static inline void numa_set_node(int cpu, int node)	{ }
-static inline void numa_clear_node(int cpu)		{ }
-static inline void numa_add_cpu(int cpu, int node)	{ }
-static inline void numa_remove_cpu(int cpu)		{ }
-#endif
-
-#endif /* ASM_X86__NUMA_64_H */
diff --git a/include/asm-x86/numaq.h b/include/asm-x86/numaq.h
deleted file mode 100644
index 124bf7d4b70a..000000000000
--- a/include/asm-x86/numaq.h
+++ /dev/null
@@ -1,169 +0,0 @@
-/*
- * Written by: Patricia Gaughen, IBM Corporation
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to <gone@us.ibm.com>
- */
-
-#ifndef ASM_X86__NUMAQ_H
-#define ASM_X86__NUMAQ_H
-
-#ifdef CONFIG_X86_NUMAQ
-
-extern int found_numaq;
-extern int get_memcfg_numaq(void);
-
-/*
- * SYS_CFG_DATA_PRIV_ADDR, struct eachquadmem, and struct sys_cfg_data are the
- */
-#define SYS_CFG_DATA_PRIV_ADDR		0x0009d000 /* place for scd in private
-						      quad space */
-
-/*
- * Communication area for each processor on lynxer-processor tests.
- *
- * NOTE: If you change the size of this eachproc structure you need
- *       to change the definition for EACH_QUAD_SIZE.
- */
-struct eachquadmem {
-	unsigned int	priv_mem_start;		/* Starting address of this */
-						/* quad's private memory. */
-						/* This is always 0. */
-						/* In MB. */
-	unsigned int	priv_mem_size;		/* Size of this quad's */
-						/* private memory. */
-						/* In MB. */
-	unsigned int	low_shrd_mem_strp_start;/* Starting address of this */
-						/* quad's low shared block */
-						/* (untranslated). */
-						/* In MB. */
-	unsigned int	low_shrd_mem_start;	/* Starting address of this */
-						/* quad's low shared memory */
-						/* (untranslated). */
-						/* In MB. */
-	unsigned int	low_shrd_mem_size;	/* Size of this quad's low */
-						/* shared memory. */
-						/* In MB. */
-	unsigned int	lmmio_copb_start;	/* Starting address of this */
-						/* quad's local memory */
-						/* mapped I/O in the */
-						/* compatibility OPB. */
-						/* In MB. */
-	unsigned int	lmmio_copb_size;	/* Size of this quad's local */
-						/* memory mapped I/O in the */
-						/* compatibility OPB. */
-						/* In MB. */
-	unsigned int	lmmio_nopb_start;	/* Starting address of this */
-						/* quad's local memory */
-						/* mapped I/O in the */
-						/* non-compatibility OPB. */
-						/* In MB. */
-	unsigned int	lmmio_nopb_size;	/* Size of this quad's local */
-						/* memory mapped I/O in the */
-						/* non-compatibility OPB. */
-						/* In MB. */
-	unsigned int	io_apic_0_start;	/* Starting address of I/O */
-						/* APIC 0. */
-	unsigned int	io_apic_0_sz;		/* Size I/O APIC 0. */
-	unsigned int	io_apic_1_start;	/* Starting address of I/O */
-						/* APIC 1. */
-	unsigned int	io_apic_1_sz;		/* Size I/O APIC 1. */
-	unsigned int	hi_shrd_mem_start;	/* Starting address of this */
-						/* quad's high shared memory.*/
-						/* In MB. */
-	unsigned int	hi_shrd_mem_size;	/* Size of this quad's high */
-						/* shared memory. */
-						/* In MB. */
-	unsigned int	mps_table_addr;		/* Address of this quad's */
-						/* MPS tables from BIOS, */
-						/* in system space.*/
-	unsigned int	lcl_MDC_pio_addr;	/* Port-I/O address for */
-						/* local access of MDC. */
-	unsigned int	rmt_MDC_mmpio_addr;	/* MM-Port-I/O address for */
-						/* remote access of MDC. */
-	unsigned int	mm_port_io_start;	/* Starting address of this */
-						/* quad's memory mapped Port */
-						/* I/O space. */
-	unsigned int	mm_port_io_size;	/* Size of this quad's memory*/
-						/* mapped Port I/O space. */
-	unsigned int	mm_rmt_io_apic_start;	/* Starting address of this */
-						/* quad's memory mapped */
-						/* remote I/O APIC space. */
-	unsigned int	mm_rmt_io_apic_size;	/* Size of this quad's memory*/
-						/* mapped remote I/O APIC */
-						/* space. */
-	unsigned int	mm_isa_start;		/* Starting address of this */
-						/* quad's memory mapped ISA */
-						/* space (contains MDC */
-						/* memory space). */
-	unsigned int	mm_isa_size;		/* Size of this quad's memory*/
-						/* mapped ISA space (contains*/
-						/* MDC memory space). */
-	unsigned int	rmt_qmi_addr;		/* Remote addr to access QMI.*/
-	unsigned int	lcl_qmi_addr;		/* Local addr to access QMI. */
-};
-
-/*
- * Note: This structure must be NOT be changed unless the multiproc and
- * OS are changed to reflect the new structure.
- */
-struct sys_cfg_data {
-	unsigned int	quad_id;
-	unsigned int	bsp_proc_id; /* Boot Strap Processor in this quad. */
-	unsigned int	scd_version; /* Version number of this table. */
-	unsigned int	first_quad_id;
-	unsigned int	quads_present31_0; /* 1 bit for each quad */
-	unsigned int	quads_present63_32; /* 1 bit for each quad */
-	unsigned int	config_flags;
-	unsigned int	boot_flags;
-	unsigned int	csr_start_addr; /* Absolute value (not in MB) */
-	unsigned int	csr_size; /* Absolute value (not in MB) */
-	unsigned int	lcl_apic_start_addr; /* Absolute value (not in MB) */
-	unsigned int	lcl_apic_size; /* Absolute value (not in MB) */
-	unsigned int	low_shrd_mem_base; /* 0 or 512MB or 1GB */
-	unsigned int	low_shrd_mem_quad_offset; /* 0,128M,256M,512M,1G */
-					/* may not be totally populated */
-	unsigned int	split_mem_enbl; /* 0 for no low shared memory */
-	unsigned int	mmio_sz; /* Size of total system memory mapped I/O */
-				 /* (in MB). */
-	unsigned int	quad_spin_lock; /* Spare location used for quad */
-					/* bringup. */
-	unsigned int	nonzero55; /* For checksumming. */
-	unsigned int	nonzeroaa; /* For checksumming. */
-	unsigned int	scd_magic_number;
-	unsigned int	system_type;
-	unsigned int	checksum;
-	/*
-	 *	memory configuration area for each quad
-	 */
-	struct		eachquadmem eq[MAX_NUMNODES];	/* indexed by quad id */
-};
-
-void numaq_tsc_disable(void);
-
-#else
-static inline int get_memcfg_numaq(void)
-{
-	return 0;
-}
-#endif /* CONFIG_X86_NUMAQ */
-#endif /* ASM_X86__NUMAQ_H */
-
diff --git a/include/asm-x86/numaq/apic.h b/include/asm-x86/numaq/apic.h
deleted file mode 100644
index 0bf2a06b7a4e..000000000000
--- a/include/asm-x86/numaq/apic.h
+++ /dev/null
@@ -1,136 +0,0 @@
-#ifndef __ASM_NUMAQ_APIC_H
-#define __ASM_NUMAQ_APIC_H
-
-#include <asm/io.h>
-#include <linux/mmzone.h>
-#include <linux/nodemask.h>
-
-#define APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
-
-static inline cpumask_t target_cpus(void)
-{
-	return CPU_MASK_ALL;
-}
-
-#define NO_BALANCE_IRQ (1)
-#define esr_disable (1)
-
-#define INT_DELIVERY_MODE dest_LowestPrio
-#define INT_DEST_MODE 0     /* physical delivery on LOCAL quad */
- 
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return physid_isset(apicid, bitmap);
-}
-static inline unsigned long check_apicid_present(int bit)
-{
-	return physid_isset(bit, phys_cpu_present_map);
-}
-#define apicid_cluster(apicid) (apicid & 0xF0)
-
-static inline int apic_id_registered(void)
-{
-	return 1;
-}
-
-static inline void init_apic_ldr(void)
-{
-	/* Already done in NUMA-Q firmware */
-}
-
-static inline void setup_apic_routing(void)
-{
-	printk("Enabling APIC mode:  %s.  Using %d I/O APICs\n",
-		"NUMA-Q", nr_ioapics);
-}
-
-/*
- * Skip adding the timer int on secondary nodes, which causes
- * a small but painful rift in the time-space continuum.
- */
-static inline int multi_timer_check(int apic, int irq)
-{
-	return apic != 0 && irq == 0;
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_map)
-{
-	/* We don't have a good way to do this yet - hack */
-	return physids_promote(0xFUL);
-}
-
-/* Mapping from cpu number to logical apicid */
-extern u8 cpu_2_logical_apicid[];
-static inline int cpu_to_logical_apicid(int cpu)
-{
-       if (cpu >= NR_CPUS)
-	       return BAD_APICID;
-	return (int)cpu_2_logical_apicid[cpu];
-}
-
-/*
- * Supporting over 60 cpus on NUMA-Q requires a locality-dependent
- * cpu to APIC ID relation to properly interact with the intelligent
- * mode of the cluster controller.
- */
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (mps_cpu < 60)
-		return ((mps_cpu >> 2) << 4) | (1 << (mps_cpu & 0x3));
-	else
-		return BAD_APICID;
-}
-
-static inline int apicid_to_node(int logical_apicid) 
-{
-	return logical_apicid >> 4;
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int logical_apicid)
-{
-	int node = apicid_to_node(logical_apicid);
-	int cpu = __ffs(logical_apicid & 0xf);
-
-	return physid_mask_of_physid(cpu + 4*node);
-}
-
-extern void *xquad_portio;
-
-static inline void setup_portio_remap(void)
-{
-	int num_quads = num_online_nodes();
-
-	if (num_quads <= 1)
-       		return;
-
-	printk("Remapping cross-quad port I/O for %d quads\n", num_quads);
-	xquad_portio = ioremap(XQUAD_PORTIO_BASE, num_quads*XQUAD_PORTIO_QUAD);
-	printk("xquad_portio vaddr 0x%08lx, len %08lx\n",
-		(u_long) xquad_portio, (u_long) num_quads*XQUAD_PORTIO_QUAD);
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-	return (1);
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-/*
- * We use physical apicids here, not logical, so just return the default
- * physical broadcast to stop people from breaking us
- */
-static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
-{
-	return (int) 0xF;
-}
-
-/* No NUMA-Q box has a HT CPU, but it can't hurt to use the default code. */
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return cpuid_apic >> index_msb;
-}
-
-#endif /* __ASM_NUMAQ_APIC_H */
diff --git a/include/asm-x86/numaq/apicdef.h b/include/asm-x86/numaq/apicdef.h
deleted file mode 100644
index e012a46cc22a..000000000000
--- a/include/asm-x86/numaq/apicdef.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef __ASM_NUMAQ_APICDEF_H
-#define __ASM_NUMAQ_APICDEF_H
-
-
-#define APIC_ID_MASK (0xF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-	        return (((x)>>24)&0x0F);
-}
-
-#define         GET_APIC_ID(x)  get_apic_id(x)
-
-#endif
diff --git a/include/asm-x86/numaq/ipi.h b/include/asm-x86/numaq/ipi.h
deleted file mode 100644
index 935588d286cf..000000000000
--- a/include/asm-x86/numaq/ipi.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __ASM_NUMAQ_IPI_H
-#define __ASM_NUMAQ_IPI_H
-
-void send_IPI_mask_sequence(cpumask_t, int vector);
-
-static inline void send_IPI_mask(cpumask_t mask, int vector)
-{
-	send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
-
-	if (!cpus_empty(mask))
-		send_IPI_mask(mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-	send_IPI_mask(cpu_online_map, vector);
-}
-
-#endif /* __ASM_NUMAQ_IPI_H */
diff --git a/include/asm-x86/numaq/mpparse.h b/include/asm-x86/numaq/mpparse.h
deleted file mode 100644
index 252292e077b6..000000000000
--- a/include/asm-x86/numaq/mpparse.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __ASM_NUMAQ_MPPARSE_H
-#define __ASM_NUMAQ_MPPARSE_H
-
-extern void numaq_mps_oem_check(struct mp_config_table *mpc, char *oem,
-				char *productid);
-
-#endif /* __ASM_NUMAQ_MPPARSE_H */
diff --git a/include/asm-x86/numaq/wakecpu.h b/include/asm-x86/numaq/wakecpu.h
deleted file mode 100644
index c577bda5b1c5..000000000000
--- a/include/asm-x86/numaq/wakecpu.h
+++ /dev/null
@@ -1,43 +0,0 @@
-#ifndef __ASM_NUMAQ_WAKECPU_H
-#define __ASM_NUMAQ_WAKECPU_H
-
-/* This file copes with machines that wakeup secondary CPUs by NMIs */
-
-#define WAKE_SECONDARY_VIA_NMI
-
-#define TRAMPOLINE_LOW phys_to_virt(0x8)
-#define TRAMPOLINE_HIGH phys_to_virt(0xa)
-
-#define boot_cpu_apicid boot_cpu_logical_apicid
-
-/* We don't do anything here because we use NMI's to boot instead */
-static inline void wait_for_init_deassert(atomic_t *deassert)
-{
-}
-
-/*
- * Because we use NMIs rather than the INIT-STARTUP sequence to
- * bootstrap the CPUs, the APIC may be in a weird state. Kick it.
- */
-static inline void smp_callin_clear_local_apic(void)
-{
-	clear_local_APIC();
-}
-
-static inline void store_NMI_vector(unsigned short *high, unsigned short *low)
-{
-	printk("Storing NMI vector\n");
-	*high = *((volatile unsigned short *) TRAMPOLINE_HIGH);
-	*low = *((volatile unsigned short *) TRAMPOLINE_LOW);
-}
-
-static inline void restore_NMI_vector(unsigned short *high, unsigned short *low)
-{
-	printk("Restoring NMI vector\n");
-	*((volatile unsigned short *) TRAMPOLINE_HIGH) = *high;
-	*((volatile unsigned short *) TRAMPOLINE_LOW) = *low;
-}
-
-#define inquire_remote_apic(apicid) {}
-
-#endif /* __ASM_NUMAQ_WAKECPU_H */
diff --git a/include/asm-x86/olpc.h b/include/asm-x86/olpc.h
deleted file mode 100644
index d7328b1a05c1..000000000000
--- a/include/asm-x86/olpc.h
+++ /dev/null
@@ -1,132 +0,0 @@
-/* OLPC machine specific definitions */
-
-#ifndef ASM_X86__OLPC_H
-#define ASM_X86__OLPC_H
-
-#include <asm/geode.h>
-
-struct olpc_platform_t {
-	int flags;
-	uint32_t boardrev;
-	int ecver;
-};
-
-#define OLPC_F_PRESENT		0x01
-#define OLPC_F_DCON		0x02
-#define OLPC_F_VSA		0x04
-
-#ifdef CONFIG_OLPC
-
-extern struct olpc_platform_t olpc_platform_info;
-
-/*
- * OLPC board IDs contain the major build number within the mask 0x0ff0,
- * and the minor build number withing 0x000f.  Pre-builds have a minor
- * number less than 8, and normal builds start at 8.  For example, 0x0B10
- * is a PreB1, and 0x0C18 is a C1.
- */
-
-static inline uint32_t olpc_board(uint8_t id)
-{
-	return (id << 4) | 0x8;
-}
-
-static inline uint32_t olpc_board_pre(uint8_t id)
-{
-	return id << 4;
-}
-
-static inline int machine_is_olpc(void)
-{
-	return (olpc_platform_info.flags & OLPC_F_PRESENT) ? 1 : 0;
-}
-
-/*
- * The DCON is OLPC's Display Controller.  It has a number of unique
- * features that we might want to take advantage of..
- */
-static inline int olpc_has_dcon(void)
-{
-	return (olpc_platform_info.flags & OLPC_F_DCON) ? 1 : 0;
-}
-
-/*
- * The VSA is software from AMD that typical Geode bioses will include.
- * It is used to emulate the PCI bus, VGA, etc.  OLPC's Open Firmware does
- * not include the VSA; instead, PCI is emulated by the kernel.
- *
- * The VSA is described further in arch/x86/pci/olpc.c.
- */
-static inline int olpc_has_vsa(void)
-{
-	return (olpc_platform_info.flags & OLPC_F_VSA) ? 1 : 0;
-}
-
-/*
- * The "Mass Production" version of OLPC's XO is identified as being model
- * C2.  During the prototype phase, the following models (in chronological
- * order) were created: A1, B1, B2, B3, B4, C1.  The A1 through B2 models
- * were based on Geode GX CPUs, and models after that were based upon
- * Geode LX CPUs.  There were also some hand-assembled models floating
- * around, referred to as PreB1, PreB2, etc.
- */
-static inline int olpc_board_at_least(uint32_t rev)
-{
-	return olpc_platform_info.boardrev >= rev;
-}
-
-#else
-
-static inline int machine_is_olpc(void)
-{
-	return 0;
-}
-
-static inline int olpc_has_dcon(void)
-{
-	return 0;
-}
-
-static inline int olpc_has_vsa(void)
-{
-	return 0;
-}
-
-#endif
-
-/* EC related functions */
-
-extern int olpc_ec_cmd(unsigned char cmd, unsigned char *inbuf, size_t inlen,
-		unsigned char *outbuf, size_t outlen);
-
-extern int olpc_ec_mask_set(uint8_t bits);
-extern int olpc_ec_mask_unset(uint8_t bits);
-
-/* EC commands */
-
-#define EC_FIRMWARE_REV		0x08
-
-/* SCI source values */
-
-#define EC_SCI_SRC_EMPTY	0x00
-#define EC_SCI_SRC_GAME		0x01
-#define EC_SCI_SRC_BATTERY	0x02
-#define EC_SCI_SRC_BATSOC	0x04
-#define EC_SCI_SRC_BATERR	0x08
-#define EC_SCI_SRC_EBOOK	0x10
-#define EC_SCI_SRC_WLAN		0x20
-#define EC_SCI_SRC_ACPWR	0x40
-#define EC_SCI_SRC_ALL		0x7F
-
-/* GPIO assignments */
-
-#define OLPC_GPIO_MIC_AC	geode_gpio(1)
-#define OLPC_GPIO_DCON_IRQ	geode_gpio(7)
-#define OLPC_GPIO_THRM_ALRM	geode_gpio(10)
-#define OLPC_GPIO_SMB_CLK	geode_gpio(14)
-#define OLPC_GPIO_SMB_DATA	geode_gpio(15)
-#define OLPC_GPIO_WORKAUX	geode_gpio(24)
-#define OLPC_GPIO_LID		geode_gpio(26)
-#define OLPC_GPIO_ECSCI		geode_gpio(27)
-
-#endif /* ASM_X86__OLPC_H */
diff --git a/include/asm-x86/page.h b/include/asm-x86/page.h
deleted file mode 100644
index d4f1d5791fc1..000000000000
--- a/include/asm-x86/page.h
+++ /dev/null
@@ -1,209 +0,0 @@
-#ifndef ASM_X86__PAGE_H
-#define ASM_X86__PAGE_H
-
-#include <linux/const.h>
-
-/* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT	12
-#define PAGE_SIZE	(_AC(1,UL) << PAGE_SHIFT)
-#define PAGE_MASK	(~(PAGE_SIZE-1))
-
-#ifdef __KERNEL__
-
-#define __PHYSICAL_MASK		((phys_addr_t)(1ULL << __PHYSICAL_MASK_SHIFT) - 1)
-#define __VIRTUAL_MASK		((1UL << __VIRTUAL_MASK_SHIFT) - 1)
-
-/* Cast PAGE_MASK to a signed type so that it is sign-extended if
-   virtual addresses are 32-bits but physical addresses are larger
-   (ie, 32-bit PAE). */
-#define PHYSICAL_PAGE_MASK	(((signed long)PAGE_MASK) & __PHYSICAL_MASK)
-
-/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
-#define PTE_PFN_MASK		((pteval_t)PHYSICAL_PAGE_MASK)
-
-/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */
-#define PTE_FLAGS_MASK		(~PTE_PFN_MASK)
-
-#define PMD_PAGE_SIZE		(_AC(1, UL) << PMD_SHIFT)
-#define PMD_PAGE_MASK		(~(PMD_PAGE_SIZE-1))
-
-#define HPAGE_SHIFT		PMD_SHIFT
-#define HPAGE_SIZE		(_AC(1,UL) << HPAGE_SHIFT)
-#define HPAGE_MASK		(~(HPAGE_SIZE - 1))
-#define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
-
-#define HUGE_MAX_HSTATE 2
-
-#ifndef __ASSEMBLY__
-#include <linux/types.h>
-#endif
-
-#ifdef CONFIG_X86_64
-#include <asm/page_64.h>
-#else
-#include <asm/page_32.h>
-#endif	/* CONFIG_X86_64 */
-
-#define PAGE_OFFSET		((unsigned long)__PAGE_OFFSET)
-
-#define VM_DATA_DEFAULT_FLAGS \
-	(((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0 ) | \
-	 VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
-
-
-#ifndef __ASSEMBLY__
-
-typedef struct { pgdval_t pgd; } pgd_t;
-typedef struct { pgprotval_t pgprot; } pgprot_t;
-
-extern int page_is_ram(unsigned long pagenr);
-extern int pagerange_is_ram(unsigned long start, unsigned long end);
-extern int devmem_is_allowed(unsigned long pagenr);
-extern void map_devmem(unsigned long pfn, unsigned long size,
-		       pgprot_t vma_prot);
-extern void unmap_devmem(unsigned long pfn, unsigned long size,
-			 pgprot_t vma_prot);
-
-extern unsigned long max_low_pfn_mapped;
-extern unsigned long max_pfn_mapped;
-
-struct page;
-
-static inline void clear_user_page(void *page, unsigned long vaddr,
-				struct page *pg)
-{
-	clear_page(page);
-}
-
-static inline void copy_user_page(void *to, void *from, unsigned long vaddr,
-				struct page *topage)
-{
-	copy_page(to, from);
-}
-
-#define __alloc_zeroed_user_highpage(movableflags, vma, vaddr) \
-	alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO | movableflags, vma, vaddr)
-#define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
-
-static inline pgd_t native_make_pgd(pgdval_t val)
-{
-	return (pgd_t) { val };
-}
-
-static inline pgdval_t native_pgd_val(pgd_t pgd)
-{
-	return pgd.pgd;
-}
-
-#if PAGETABLE_LEVELS >= 3
-#if PAGETABLE_LEVELS == 4
-typedef struct { pudval_t pud; } pud_t;
-
-static inline pud_t native_make_pud(pmdval_t val)
-{
-	return (pud_t) { val };
-}
-
-static inline pudval_t native_pud_val(pud_t pud)
-{
-	return pud.pud;
-}
-#else	/* PAGETABLE_LEVELS == 3 */
-#include <asm-generic/pgtable-nopud.h>
-
-static inline pudval_t native_pud_val(pud_t pud)
-{
-	return native_pgd_val(pud.pgd);
-}
-#endif	/* PAGETABLE_LEVELS == 4 */
-
-typedef struct { pmdval_t pmd; } pmd_t;
-
-static inline pmd_t native_make_pmd(pmdval_t val)
-{
-	return (pmd_t) { val };
-}
-
-static inline pmdval_t native_pmd_val(pmd_t pmd)
-{
-	return pmd.pmd;
-}
-#else  /* PAGETABLE_LEVELS == 2 */
-#include <asm-generic/pgtable-nopmd.h>
-
-static inline pmdval_t native_pmd_val(pmd_t pmd)
-{
-	return native_pgd_val(pmd.pud.pgd);
-}
-#endif	/* PAGETABLE_LEVELS >= 3 */
-
-static inline pte_t native_make_pte(pteval_t val)
-{
-	return (pte_t) { .pte = val };
-}
-
-static inline pteval_t native_pte_val(pte_t pte)
-{
-	return pte.pte;
-}
-
-static inline pteval_t native_pte_flags(pte_t pte)
-{
-	return native_pte_val(pte) & PTE_FLAGS_MASK;
-}
-
-#define pgprot_val(x)	((x).pgprot)
-#define __pgprot(x)	((pgprot_t) { (x) } )
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else  /* !CONFIG_PARAVIRT */
-
-#define pgd_val(x)	native_pgd_val(x)
-#define __pgd(x)	native_make_pgd(x)
-
-#ifndef __PAGETABLE_PUD_FOLDED
-#define pud_val(x)	native_pud_val(x)
-#define __pud(x)	native_make_pud(x)
-#endif
-
-#ifndef __PAGETABLE_PMD_FOLDED
-#define pmd_val(x)	native_pmd_val(x)
-#define __pmd(x)	native_make_pmd(x)
-#endif
-
-#define pte_val(x)	native_pte_val(x)
-#define pte_flags(x)	native_pte_flags(x)
-#define __pte(x)	native_make_pte(x)
-
-#endif	/* CONFIG_PARAVIRT */
-
-#define __pa(x)		__phys_addr((unsigned long)(x))
-#define __pa_nodebug(x)	__phys_addr_nodebug((unsigned long)(x))
-/* __pa_symbol should be used for C visible symbols.
-   This seems to be the official gcc blessed way to do such arithmetic. */
-#define __pa_symbol(x)	__pa(__phys_reloc_hide((unsigned long)(x)))
-
-#define __va(x)			((void *)((unsigned long)(x)+PAGE_OFFSET))
-
-#define __boot_va(x)		__va(x)
-#define __boot_pa(x)		__pa(x)
-
-/*
- * virt_to_page(kaddr) returns a valid pointer if and only if
- * virt_addr_valid(kaddr) returns true.
- */
-#define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define pfn_to_kaddr(pfn)      __va((pfn) << PAGE_SHIFT)
-extern bool __virt_addr_valid(unsigned long kaddr);
-#define virt_addr_valid(kaddr)	__virt_addr_valid((unsigned long) (kaddr))
-
-#endif	/* __ASSEMBLY__ */
-
-#include <asm-generic/memory_model.h>
-#include <asm-generic/page.h>
-
-#define __HAVE_ARCH_GATE_AREA 1
-
-#endif	/* __KERNEL__ */
-#endif /* ASM_X86__PAGE_H */
diff --git a/include/asm-x86/page_32.h b/include/asm-x86/page_32.h
deleted file mode 100644
index bdf5dba4cfb0..000000000000
--- a/include/asm-x86/page_32.h
+++ /dev/null
@@ -1,136 +0,0 @@
-#ifndef ASM_X86__PAGE_32_H
-#define ASM_X86__PAGE_32_H
-
-/*
- * This handles the memory map.
- *
- * A __PAGE_OFFSET of 0xC0000000 means that the kernel has
- * a virtual address space of one gigabyte, which limits the
- * amount of physical memory you can use to about 950MB.
- *
- * If you want more physical memory than this then see the CONFIG_HIGHMEM4G
- * and CONFIG_HIGHMEM64G options in the kernel configuration.
- */
-#define __PAGE_OFFSET		_AC(CONFIG_PAGE_OFFSET, UL)
-
-#ifdef CONFIG_4KSTACKS
-#define THREAD_ORDER	0
-#else
-#define THREAD_ORDER	1
-#endif
-#define THREAD_SIZE 	(PAGE_SIZE << THREAD_ORDER)
-
-#define STACKFAULT_STACK 0
-#define DOUBLEFAULT_STACK 1
-#define NMI_STACK 0
-#define DEBUG_STACK 0
-#define MCE_STACK 0
-#define N_EXCEPTION_STACKS 1
-
-#ifdef CONFIG_X86_PAE
-/* 44=32+12, the limit we can fit into an unsigned long pfn */
-#define __PHYSICAL_MASK_SHIFT	44
-#define __VIRTUAL_MASK_SHIFT	32
-#define PAGETABLE_LEVELS	3
-
-#ifndef __ASSEMBLY__
-typedef u64	pteval_t;
-typedef u64	pmdval_t;
-typedef u64	pudval_t;
-typedef u64	pgdval_t;
-typedef u64	pgprotval_t;
-
-typedef union {
-	struct {
-		unsigned long pte_low, pte_high;
-	};
-	pteval_t pte;
-} pte_t;
-#endif	/* __ASSEMBLY__
- */
-#else  /* !CONFIG_X86_PAE */
-#define __PHYSICAL_MASK_SHIFT	32
-#define __VIRTUAL_MASK_SHIFT	32
-#define PAGETABLE_LEVELS	2
-
-#ifndef __ASSEMBLY__
-typedef unsigned long	pteval_t;
-typedef unsigned long	pmdval_t;
-typedef unsigned long	pudval_t;
-typedef unsigned long	pgdval_t;
-typedef unsigned long	pgprotval_t;
-
-typedef union {
-	pteval_t pte;
-	pteval_t pte_low;
-} pte_t;
-
-#endif	/* __ASSEMBLY__ */
-#endif	/* CONFIG_X86_PAE */
-
-#ifndef __ASSEMBLY__
-typedef struct page *pgtable_t;
-#endif
-
-#ifdef CONFIG_HUGETLB_PAGE
-#define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-#endif
-
-#ifndef __ASSEMBLY__
-#define __phys_addr_nodebug(x)	((x) - PAGE_OFFSET)
-#ifdef CONFIG_DEBUG_VIRTUAL
-extern unsigned long __phys_addr(unsigned long);
-#else
-#define __phys_addr(x)		__phys_addr_nodebug(x)
-#endif
-#define __phys_reloc_hide(x)	RELOC_HIDE((x), 0)
-
-#ifdef CONFIG_FLATMEM
-#define pfn_valid(pfn)		((pfn) < max_mapnr)
-#endif /* CONFIG_FLATMEM */
-
-extern int nx_enabled;
-
-/*
- * This much address space is reserved for vmalloc() and iomap()
- * as well as fixmap mappings.
- */
-extern unsigned int __VMALLOC_RESERVE;
-extern int sysctl_legacy_va_layout;
-
-extern void find_low_pfn_range(void);
-extern unsigned long init_memory_mapping(unsigned long start,
-					 unsigned long end);
-extern void initmem_init(unsigned long, unsigned long);
-extern void free_initmem(void);
-extern void setup_bootmem_allocator(void);
-
-
-#ifdef CONFIG_X86_USE_3DNOW
-#include <asm/mmx.h>
-
-static inline void clear_page(void *page)
-{
-	mmx_clear_page(page);
-}
-
-static inline void copy_page(void *to, void *from)
-{
-	mmx_copy_page(to, from);
-}
-#else  /* !CONFIG_X86_USE_3DNOW */
-#include <linux/string.h>
-
-static inline void clear_page(void *page)
-{
-	memset(page, 0, PAGE_SIZE);
-}
-
-static inline void copy_page(void *to, void *from)
-{
-	memcpy(to, from, PAGE_SIZE);
-}
-#endif	/* CONFIG_X86_3DNOW */
-#endif	/* !__ASSEMBLY__ */
-
-#endif /* ASM_X86__PAGE_32_H */
diff --git a/include/asm-x86/page_64.h b/include/asm-x86/page_64.h
deleted file mode 100644
index 49380b8c7e25..000000000000
--- a/include/asm-x86/page_64.h
+++ /dev/null
@@ -1,105 +0,0 @@
-#ifndef ASM_X86__PAGE_64_H
-#define ASM_X86__PAGE_64_H
-
-#define PAGETABLE_LEVELS	4
-
-#define THREAD_ORDER	1
-#define THREAD_SIZE  (PAGE_SIZE << THREAD_ORDER)
-#define CURRENT_MASK (~(THREAD_SIZE - 1))
-
-#define EXCEPTION_STACK_ORDER 0
-#define EXCEPTION_STKSZ (PAGE_SIZE << EXCEPTION_STACK_ORDER)
-
-#define DEBUG_STACK_ORDER (EXCEPTION_STACK_ORDER + 1)
-#define DEBUG_STKSZ (PAGE_SIZE << DEBUG_STACK_ORDER)
-
-#define IRQSTACK_ORDER 2
-#define IRQSTACKSIZE (PAGE_SIZE << IRQSTACK_ORDER)
-
-#define STACKFAULT_STACK 1
-#define DOUBLEFAULT_STACK 2
-#define NMI_STACK 3
-#define DEBUG_STACK 4
-#define MCE_STACK 5
-#define N_EXCEPTION_STACKS 5  /* hw limit: 7 */
-
-#define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
-#define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
-
-/*
- * Set __PAGE_OFFSET to the most negative possible address +
- * PGDIR_SIZE*16 (pgd slot 272).  The gap is to allow a space for a
- * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
- * what Xen requires.
- */
-#define __PAGE_OFFSET           _AC(0xffff880000000000, UL)
-
-#define __PHYSICAL_START	CONFIG_PHYSICAL_START
-#define __KERNEL_ALIGN		0x200000
-
-/*
- * Make sure kernel is aligned to 2MB address. Catching it at compile
- * time is better. Change your config file and compile the kernel
- * for a 2MB aligned address (CONFIG_PHYSICAL_START)
- */
-#if (CONFIG_PHYSICAL_START % __KERNEL_ALIGN) != 0
-#error "CONFIG_PHYSICAL_START must be a multiple of 2MB"
-#endif
-
-#define __START_KERNEL		(__START_KERNEL_map + __PHYSICAL_START)
-#define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
-
-/* See Documentation/x86_64/mm.txt for a description of the memory map. */
-#define __PHYSICAL_MASK_SHIFT	46
-#define __VIRTUAL_MASK_SHIFT	48
-
-/*
- * Kernel image size is limited to 512 MB (see level2_kernel_pgt in
- * arch/x86/kernel/head_64.S), and it is mapped here:
- */
-#define KERNEL_IMAGE_SIZE	(512 * 1024 * 1024)
-#define KERNEL_IMAGE_START	_AC(0xffffffff80000000, UL)
-
-#ifndef __ASSEMBLY__
-void clear_page(void *page);
-void copy_page(void *to, void *from);
-
-/* duplicated to the one in bootmem.h */
-extern unsigned long max_pfn;
-extern unsigned long phys_base;
-
-extern unsigned long __phys_addr(unsigned long);
-#define __phys_reloc_hide(x)	(x)
-
-/*
- * These are used to make use of C type-checking..
- */
-typedef unsigned long	pteval_t;
-typedef unsigned long	pmdval_t;
-typedef unsigned long	pudval_t;
-typedef unsigned long	pgdval_t;
-typedef unsigned long	pgprotval_t;
-
-typedef struct page *pgtable_t;
-
-typedef struct { pteval_t pte; } pte_t;
-
-#define vmemmap ((struct page *)VMEMMAP_START)
-
-extern unsigned long init_memory_mapping(unsigned long start,
-					 unsigned long end);
-
-extern void initmem_init(unsigned long start_pfn, unsigned long end_pfn);
-extern void free_initmem(void);
-
-extern void init_extra_mapping_uc(unsigned long phys, unsigned long size);
-extern void init_extra_mapping_wb(unsigned long phys, unsigned long size);
-
-#endif	/* !__ASSEMBLY__ */
-
-#ifdef CONFIG_FLATMEM
-#define pfn_valid(pfn)          ((pfn) < max_pfn)
-#endif
-
-
-#endif /* ASM_X86__PAGE_64_H */
diff --git a/include/asm-x86/param.h b/include/asm-x86/param.h
deleted file mode 100644
index 0009cfb11a5f..000000000000
--- a/include/asm-x86/param.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef ASM_X86__PARAM_H
-#define ASM_X86__PARAM_H
-
-#ifdef __KERNEL__
-# define HZ		CONFIG_HZ	/* Internal kernel timer frequency */
-# define USER_HZ	100		/* some user interfaces are */
-# define CLOCKS_PER_SEC	(USER_HZ)       /* in "ticks" like times() */
-#endif
-
-#ifndef HZ
-#define HZ 100
-#endif
-
-#define EXEC_PAGESIZE	4096
-
-#ifndef NOGROUP
-#define NOGROUP		(-1)
-#endif
-
-#define MAXHOSTNAMELEN	64	/* max length of hostname */
-
-#endif /* ASM_X86__PARAM_H */
diff --git a/include/asm-x86/paravirt.h b/include/asm-x86/paravirt.h
deleted file mode 100644
index 8d6ae2f760d0..000000000000
--- a/include/asm-x86/paravirt.h
+++ /dev/null
@@ -1,1650 +0,0 @@
-#ifndef ASM_X86__PARAVIRT_H
-#define ASM_X86__PARAVIRT_H
-/* Various instructions on x86 need to be replaced for
- * para-virtualization: those hooks are defined here. */
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/page.h>
-#include <asm/asm.h>
-
-/* Bitmask of what can be clobbered: usually at least eax. */
-#define CLBR_NONE 0
-#define CLBR_EAX  (1 << 0)
-#define CLBR_ECX  (1 << 1)
-#define CLBR_EDX  (1 << 2)
-
-#ifdef CONFIG_X86_64
-#define CLBR_RSI  (1 << 3)
-#define CLBR_RDI  (1 << 4)
-#define CLBR_R8   (1 << 5)
-#define CLBR_R9   (1 << 6)
-#define CLBR_R10  (1 << 7)
-#define CLBR_R11  (1 << 8)
-#define CLBR_ANY  ((1 << 9) - 1)
-#include <asm/desc_defs.h>
-#else
-/* CLBR_ANY should match all regs platform has. For i386, that's just it */
-#define CLBR_ANY  ((1 << 3) - 1)
-#endif /* X86_64 */
-
-#ifndef __ASSEMBLY__
-#include <linux/types.h>
-#include <linux/cpumask.h>
-#include <asm/kmap_types.h>
-#include <asm/desc_defs.h>
-
-struct page;
-struct thread_struct;
-struct desc_ptr;
-struct tss_struct;
-struct mm_struct;
-struct desc_struct;
-
-/* general info */
-struct pv_info {
-	unsigned int kernel_rpl;
-	int shared_kernel_pmd;
-	int paravirt_enabled;
-	const char *name;
-};
-
-struct pv_init_ops {
-	/*
-	 * Patch may replace one of the defined code sequences with
-	 * arbitrary code, subject to the same register constraints.
-	 * This generally means the code is not free to clobber any
-	 * registers other than EAX.  The patch function should return
-	 * the number of bytes of code generated, as we nop pad the
-	 * rest in generic code.
-	 */
-	unsigned (*patch)(u8 type, u16 clobber, void *insnbuf,
-			  unsigned long addr, unsigned len);
-
-	/* Basic arch-specific setup */
-	void (*arch_setup)(void);
-	char *(*memory_setup)(void);
-	void (*post_allocator_init)(void);
-
-	/* Print a banner to identify the environment */
-	void (*banner)(void);
-};
-
-
-struct pv_lazy_ops {
-	/* Set deferred update mode, used for batching operations. */
-	void (*enter)(void);
-	void (*leave)(void);
-};
-
-struct pv_time_ops {
-	void (*time_init)(void);
-
-	/* Set and set time of day */
-	unsigned long (*get_wallclock)(void);
-	int (*set_wallclock)(unsigned long);
-
-	unsigned long long (*sched_clock)(void);
-	unsigned long (*get_tsc_khz)(void);
-};
-
-struct pv_cpu_ops {
-	/* hooks for various privileged instructions */
-	unsigned long (*get_debugreg)(int regno);
-	void (*set_debugreg)(int regno, unsigned long value);
-
-	void (*clts)(void);
-
-	unsigned long (*read_cr0)(void);
-	void (*write_cr0)(unsigned long);
-
-	unsigned long (*read_cr4_safe)(void);
-	unsigned long (*read_cr4)(void);
-	void (*write_cr4)(unsigned long);
-
-#ifdef CONFIG_X86_64
-	unsigned long (*read_cr8)(void);
-	void (*write_cr8)(unsigned long);
-#endif
-
-	/* Segment descriptor handling */
-	void (*load_tr_desc)(void);
-	void (*load_gdt)(const struct desc_ptr *);
-	void (*load_idt)(const struct desc_ptr *);
-	void (*store_gdt)(struct desc_ptr *);
-	void (*store_idt)(struct desc_ptr *);
-	void (*set_ldt)(const void *desc, unsigned entries);
-	unsigned long (*store_tr)(void);
-	void (*load_tls)(struct thread_struct *t, unsigned int cpu);
-#ifdef CONFIG_X86_64
-	void (*load_gs_index)(unsigned int idx);
-#endif
-	void (*write_ldt_entry)(struct desc_struct *ldt, int entrynum,
-				const void *desc);
-	void (*write_gdt_entry)(struct desc_struct *,
-				int entrynum, const void *desc, int size);
-	void (*write_idt_entry)(gate_desc *,
-				int entrynum, const gate_desc *gate);
-	void (*alloc_ldt)(struct desc_struct *ldt, unsigned entries);
-	void (*free_ldt)(struct desc_struct *ldt, unsigned entries);
-
-	void (*load_sp0)(struct tss_struct *tss, struct thread_struct *t);
-
-	void (*set_iopl_mask)(unsigned mask);
-
-	void (*wbinvd)(void);
-	void (*io_delay)(void);
-
-	/* cpuid emulation, mostly so that caps bits can be disabled */
-	void (*cpuid)(unsigned int *eax, unsigned int *ebx,
-		      unsigned int *ecx, unsigned int *edx);
-
-	/* MSR, PMC and TSR operations.
-	   err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
-	u64 (*read_msr_amd)(unsigned int msr, int *err);
-	u64 (*read_msr)(unsigned int msr, int *err);
-	int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
-
-	u64 (*read_tsc)(void);
-	u64 (*read_pmc)(int counter);
-	unsigned long long (*read_tscp)(unsigned int *aux);
-
-	/*
-	 * Atomically enable interrupts and return to userspace.  This
-	 * is only ever used to return to 32-bit processes; in a
-	 * 64-bit kernel, it's used for 32-on-64 compat processes, but
-	 * never native 64-bit processes.  (Jump, not call.)
-	 */
-	void (*irq_enable_sysexit)(void);
-
-	/*
-	 * Switch to usermode gs and return to 64-bit usermode using
-	 * sysret.  Only used in 64-bit kernels to return to 64-bit
-	 * processes.  Usermode register state, including %rsp, must
-	 * already be restored.
-	 */
-	void (*usergs_sysret64)(void);
-
-	/*
-	 * Switch to usermode gs and return to 32-bit usermode using
-	 * sysret.  Used to return to 32-on-64 compat processes.
-	 * Other usermode register state, including %esp, must already
-	 * be restored.
-	 */
-	void (*usergs_sysret32)(void);
-
-	/* Normal iret.  Jump to this with the standard iret stack
-	   frame set up. */
-	void (*iret)(void);
-
-	void (*swapgs)(void);
-
-	struct pv_lazy_ops lazy_mode;
-};
-
-struct pv_irq_ops {
-	void (*init_IRQ)(void);
-
-	/*
-	 * Get/set interrupt state.  save_fl and restore_fl are only
-	 * expected to use X86_EFLAGS_IF; all other bits
-	 * returned from save_fl are undefined, and may be ignored by
-	 * restore_fl.
-	 */
-	unsigned long (*save_fl)(void);
-	void (*restore_fl)(unsigned long);
-	void (*irq_disable)(void);
-	void (*irq_enable)(void);
-	void (*safe_halt)(void);
-	void (*halt)(void);
-
-#ifdef CONFIG_X86_64
-	void (*adjust_exception_frame)(void);
-#endif
-};
-
-struct pv_apic_ops {
-#ifdef CONFIG_X86_LOCAL_APIC
-	void (*setup_boot_clock)(void);
-	void (*setup_secondary_clock)(void);
-
-	void (*startup_ipi_hook)(int phys_apicid,
-				 unsigned long start_eip,
-				 unsigned long start_esp);
-#endif
-};
-
-struct pv_mmu_ops {
-	/*
-	 * Called before/after init_mm pagetable setup. setup_start
-	 * may reset %cr3, and may pre-install parts of the pagetable;
-	 * pagetable setup is expected to preserve any existing
-	 * mapping.
-	 */
-	void (*pagetable_setup_start)(pgd_t *pgd_base);
-	void (*pagetable_setup_done)(pgd_t *pgd_base);
-
-	unsigned long (*read_cr2)(void);
-	void (*write_cr2)(unsigned long);
-
-	unsigned long (*read_cr3)(void);
-	void (*write_cr3)(unsigned long);
-
-	/*
-	 * Hooks for intercepting the creation/use/destruction of an
-	 * mm_struct.
-	 */
-	void (*activate_mm)(struct mm_struct *prev,
-			    struct mm_struct *next);
-	void (*dup_mmap)(struct mm_struct *oldmm,
-			 struct mm_struct *mm);
-	void (*exit_mmap)(struct mm_struct *mm);
-
-
-	/* TLB operations */
-	void (*flush_tlb_user)(void);
-	void (*flush_tlb_kernel)(void);
-	void (*flush_tlb_single)(unsigned long addr);
-	void (*flush_tlb_others)(const cpumask_t *cpus, struct mm_struct *mm,
-				 unsigned long va);
-
-	/* Hooks for allocating and freeing a pagetable top-level */
-	int  (*pgd_alloc)(struct mm_struct *mm);
-	void (*pgd_free)(struct mm_struct *mm, pgd_t *pgd);
-
-	/*
-	 * Hooks for allocating/releasing pagetable pages when they're
-	 * attached to a pagetable
-	 */
-	void (*alloc_pte)(struct mm_struct *mm, unsigned long pfn);
-	void (*alloc_pmd)(struct mm_struct *mm, unsigned long pfn);
-	void (*alloc_pmd_clone)(unsigned long pfn, unsigned long clonepfn, unsigned long start, unsigned long count);
-	void (*alloc_pud)(struct mm_struct *mm, unsigned long pfn);
-	void (*release_pte)(unsigned long pfn);
-	void (*release_pmd)(unsigned long pfn);
-	void (*release_pud)(unsigned long pfn);
-
-	/* Pagetable manipulation functions */
-	void (*set_pte)(pte_t *ptep, pte_t pteval);
-	void (*set_pte_at)(struct mm_struct *mm, unsigned long addr,
-			   pte_t *ptep, pte_t pteval);
-	void (*set_pmd)(pmd_t *pmdp, pmd_t pmdval);
-	void (*pte_update)(struct mm_struct *mm, unsigned long addr,
-			   pte_t *ptep);
-	void (*pte_update_defer)(struct mm_struct *mm,
-				 unsigned long addr, pte_t *ptep);
-
-	pte_t (*ptep_modify_prot_start)(struct mm_struct *mm, unsigned long addr,
-					pte_t *ptep);
-	void (*ptep_modify_prot_commit)(struct mm_struct *mm, unsigned long addr,
-					pte_t *ptep, pte_t pte);
-
-	pteval_t (*pte_val)(pte_t);
-	pteval_t (*pte_flags)(pte_t);
-	pte_t (*make_pte)(pteval_t pte);
-
-	pgdval_t (*pgd_val)(pgd_t);
-	pgd_t (*make_pgd)(pgdval_t pgd);
-
-#if PAGETABLE_LEVELS >= 3
-#ifdef CONFIG_X86_PAE
-	void (*set_pte_atomic)(pte_t *ptep, pte_t pteval);
-	void (*set_pte_present)(struct mm_struct *mm, unsigned long addr,
-				pte_t *ptep, pte_t pte);
-	void (*pte_clear)(struct mm_struct *mm, unsigned long addr,
-			  pte_t *ptep);
-	void (*pmd_clear)(pmd_t *pmdp);
-
-#endif	/* CONFIG_X86_PAE */
-
-	void (*set_pud)(pud_t *pudp, pud_t pudval);
-
-	pmdval_t (*pmd_val)(pmd_t);
-	pmd_t (*make_pmd)(pmdval_t pmd);
-
-#if PAGETABLE_LEVELS == 4
-	pudval_t (*pud_val)(pud_t);
-	pud_t (*make_pud)(pudval_t pud);
-
-	void (*set_pgd)(pgd_t *pudp, pgd_t pgdval);
-#endif	/* PAGETABLE_LEVELS == 4 */
-#endif	/* PAGETABLE_LEVELS >= 3 */
-
-#ifdef CONFIG_HIGHPTE
-	void *(*kmap_atomic_pte)(struct page *page, enum km_type type);
-#endif
-
-	struct pv_lazy_ops lazy_mode;
-
-	/* dom0 ops */
-
-	/* Sometimes the physical address is a pfn, and sometimes its
-	   an mfn.  We can tell which is which from the index. */
-	void (*set_fixmap)(unsigned /* enum fixed_addresses */ idx,
-			   unsigned long phys, pgprot_t flags);
-};
-
-struct raw_spinlock;
-struct pv_lock_ops {
-	int (*spin_is_locked)(struct raw_spinlock *lock);
-	int (*spin_is_contended)(struct raw_spinlock *lock);
-	void (*spin_lock)(struct raw_spinlock *lock);
-	void (*spin_lock_flags)(struct raw_spinlock *lock, unsigned long flags);
-	int (*spin_trylock)(struct raw_spinlock *lock);
-	void (*spin_unlock)(struct raw_spinlock *lock);
-};
-
-/* This contains all the paravirt structures: we get a convenient
- * number for each function using the offset which we use to indicate
- * what to patch. */
-struct paravirt_patch_template {
-	struct pv_init_ops pv_init_ops;
-	struct pv_time_ops pv_time_ops;
-	struct pv_cpu_ops pv_cpu_ops;
-	struct pv_irq_ops pv_irq_ops;
-	struct pv_apic_ops pv_apic_ops;
-	struct pv_mmu_ops pv_mmu_ops;
-	struct pv_lock_ops pv_lock_ops;
-};
-
-extern struct pv_info pv_info;
-extern struct pv_init_ops pv_init_ops;
-extern struct pv_time_ops pv_time_ops;
-extern struct pv_cpu_ops pv_cpu_ops;
-extern struct pv_irq_ops pv_irq_ops;
-extern struct pv_apic_ops pv_apic_ops;
-extern struct pv_mmu_ops pv_mmu_ops;
-extern struct pv_lock_ops pv_lock_ops;
-
-#define PARAVIRT_PATCH(x)					\
-	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))
-
-#define paravirt_type(op)				\
-	[paravirt_typenum] "i" (PARAVIRT_PATCH(op)),	\
-	[paravirt_opptr] "m" (op)
-#define paravirt_clobber(clobber)		\
-	[paravirt_clobber] "i" (clobber)
-
-/*
- * Generate some code, and mark it as patchable by the
- * apply_paravirt() alternate instruction patcher.
- */
-#define _paravirt_alt(insn_string, type, clobber)	\
-	"771:\n\t" insn_string "\n" "772:\n"		\
-	".pushsection .parainstructions,\"a\"\n"	\
-	_ASM_ALIGN "\n"					\
-	_ASM_PTR " 771b\n"				\
-	"  .byte " type "\n"				\
-	"  .byte 772b-771b\n"				\
-	"  .short " clobber "\n"			\
-	".popsection\n"
-
-/* Generate patchable code, with the default asm parameters. */
-#define paravirt_alt(insn_string)					\
-	_paravirt_alt(insn_string, "%c[paravirt_typenum]", "%c[paravirt_clobber]")
-
-/* Simple instruction patching code. */
-#define DEF_NATIVE(ops, name, code) 					\
-	extern const char start_##ops##_##name[], end_##ops##_##name[];	\
-	asm("start_" #ops "_" #name ": " code "; end_" #ops "_" #name ":")
-
-unsigned paravirt_patch_nop(void);
-unsigned paravirt_patch_ignore(unsigned len);
-unsigned paravirt_patch_call(void *insnbuf,
-			     const void *target, u16 tgt_clobbers,
-			     unsigned long addr, u16 site_clobbers,
-			     unsigned len);
-unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
-			    unsigned long addr, unsigned len);
-unsigned paravirt_patch_default(u8 type, u16 clobbers, void *insnbuf,
-				unsigned long addr, unsigned len);
-
-unsigned paravirt_patch_insns(void *insnbuf, unsigned len,
-			      const char *start, const char *end);
-
-unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
-		      unsigned long addr, unsigned len);
-
-int paravirt_disable_iospace(void);
-
-/*
- * This generates an indirect call based on the operation type number.
- * The type number, computed in PARAVIRT_PATCH, is derived from the
- * offset into the paravirt_patch_template structure, and can therefore be
- * freely converted back into a structure offset.
- */
-#define PARAVIRT_CALL	"call *%[paravirt_opptr];"
-
-/*
- * These macros are intended to wrap calls through one of the paravirt
- * ops structs, so that they can be later identified and patched at
- * runtime.
- *
- * Normally, a call to a pv_op function is a simple indirect call:
- * (pv_op_struct.operations)(args...).
- *
- * Unfortunately, this is a relatively slow operation for modern CPUs,
- * because it cannot necessarily determine what the destination
- * address is.  In this case, the address is a runtime constant, so at
- * the very least we can patch the call to e a simple direct call, or
- * ideally, patch an inline implementation into the callsite.  (Direct
- * calls are essentially free, because the call and return addresses
- * are completely predictable.)
- *
- * For i386, these macros rely on the standard gcc "regparm(3)" calling
- * convention, in which the first three arguments are placed in %eax,
- * %edx, %ecx (in that order), and the remaining arguments are placed
- * on the stack.  All caller-save registers (eax,edx,ecx) are expected
- * to be modified (either clobbered or used for return values).
- * X86_64, on the other hand, already specifies a register-based calling
- * conventions, returning at %rax, with parameteres going on %rdi, %rsi,
- * %rdx, and %rcx. Note that for this reason, x86_64 does not need any
- * special handling for dealing with 4 arguments, unlike i386.
- * However, x86_64 also have to clobber all caller saved registers, which
- * unfortunately, are quite a bit (r8 - r11)
- *
- * The call instruction itself is marked by placing its start address
- * and size into the .parainstructions section, so that
- * apply_paravirt() in arch/i386/kernel/alternative.c can do the
- * appropriate patching under the control of the backend pv_init_ops
- * implementation.
- *
- * Unfortunately there's no way to get gcc to generate the args setup
- * for the call, and then allow the call itself to be generated by an
- * inline asm.  Because of this, we must do the complete arg setup and
- * return value handling from within these macros.  This is fairly
- * cumbersome.
- *
- * There are 5 sets of PVOP_* macros for dealing with 0-4 arguments.
- * It could be extended to more arguments, but there would be little
- * to be gained from that.  For each number of arguments, there are
- * the two VCALL and CALL variants for void and non-void functions.
- *
- * When there is a return value, the invoker of the macro must specify
- * the return type.  The macro then uses sizeof() on that type to
- * determine whether its a 32 or 64 bit value, and places the return
- * in the right register(s) (just %eax for 32-bit, and %edx:%eax for
- * 64-bit). For x86_64 machines, it just returns at %rax regardless of
- * the return value size.
- *
- * 64-bit arguments are passed as a pair of adjacent 32-bit arguments
- * i386 also passes 64-bit arguments as a pair of adjacent 32-bit arguments
- * in low,high order
- *
- * Small structures are passed and returned in registers.  The macro
- * calling convention can't directly deal with this, so the wrapper
- * functions must do this.
- *
- * These PVOP_* macros are only defined within this header.  This
- * means that all uses must be wrapped in inline functions.  This also
- * makes sure the incoming and outgoing types are always correct.
- */
-#ifdef CONFIG_X86_32
-#define PVOP_VCALL_ARGS			unsigned long __eax, __edx, __ecx
-#define PVOP_CALL_ARGS			PVOP_VCALL_ARGS
-#define PVOP_VCALL_CLOBBERS		"=a" (__eax), "=d" (__edx),	\
-					"=c" (__ecx)
-#define PVOP_CALL_CLOBBERS		PVOP_VCALL_CLOBBERS
-#define EXTRA_CLOBBERS
-#define VEXTRA_CLOBBERS
-#else
-#define PVOP_VCALL_ARGS		unsigned long __edi, __esi, __edx, __ecx
-#define PVOP_CALL_ARGS		PVOP_VCALL_ARGS, __eax
-#define PVOP_VCALL_CLOBBERS	"=D" (__edi),				\
-				"=S" (__esi), "=d" (__edx),		\
-				"=c" (__ecx)
-
-#define PVOP_CALL_CLOBBERS	PVOP_VCALL_CLOBBERS, "=a" (__eax)
-
-#define EXTRA_CLOBBERS	 , "r8", "r9", "r10", "r11"
-#define VEXTRA_CLOBBERS	 , "rax", "r8", "r9", "r10", "r11"
-#endif
-
-#ifdef CONFIG_PARAVIRT_DEBUG
-#define PVOP_TEST_NULL(op)	BUG_ON(op == NULL)
-#else
-#define PVOP_TEST_NULL(op)	((void)op)
-#endif
-
-#define __PVOP_CALL(rettype, op, pre, post, ...)			\
-	({								\
-		rettype __ret;						\
-		PVOP_CALL_ARGS;					\
-		PVOP_TEST_NULL(op);					\
-		/* This is 32-bit specific, but is okay in 64-bit */	\
-		/* since this condition will never hold */		\
-		if (sizeof(rettype) > sizeof(unsigned long)) {		\
-			asm volatile(pre				\
-				     paravirt_alt(PARAVIRT_CALL)	\
-				     post				\
-				     : PVOP_CALL_CLOBBERS		\
-				     : paravirt_type(op),		\
-				       paravirt_clobber(CLBR_ANY),	\
-				       ##__VA_ARGS__			\
-				     : "memory", "cc" EXTRA_CLOBBERS);	\
-			__ret = (rettype)((((u64)__edx) << 32) | __eax); \
-		} else {						\
-			asm volatile(pre				\
-				     paravirt_alt(PARAVIRT_CALL)	\
-				     post				\
-				     : PVOP_CALL_CLOBBERS		\
-				     : paravirt_type(op),		\
-				       paravirt_clobber(CLBR_ANY),	\
-				       ##__VA_ARGS__			\
-				     : "memory", "cc" EXTRA_CLOBBERS);	\
-			__ret = (rettype)__eax;				\
-		}							\
-		__ret;							\
-	})
-#define __PVOP_VCALL(op, pre, post, ...)				\
-	({								\
-		PVOP_VCALL_ARGS;					\
-		PVOP_TEST_NULL(op);					\
-		asm volatile(pre					\
-			     paravirt_alt(PARAVIRT_CALL)		\
-			     post					\
-			     : PVOP_VCALL_CLOBBERS			\
-			     : paravirt_type(op),			\
-			       paravirt_clobber(CLBR_ANY),		\
-			       ##__VA_ARGS__				\
-			     : "memory", "cc" VEXTRA_CLOBBERS);		\
-	})
-
-#define PVOP_CALL0(rettype, op)						\
-	__PVOP_CALL(rettype, op, "", "")
-#define PVOP_VCALL0(op)							\
-	__PVOP_VCALL(op, "", "")
-
-#define PVOP_CALL1(rettype, op, arg1)					\
-	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)))
-#define PVOP_VCALL1(op, arg1)						\
-	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)))
-
-#define PVOP_CALL2(rettype, op, arg1, arg2)				\
-	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)), 	\
-	"1" ((unsigned long)(arg2)))
-#define PVOP_VCALL2(op, arg1, arg2)					\
-	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)), 		\
-	"1" ((unsigned long)(arg2)))
-
-#define PVOP_CALL3(rettype, op, arg1, arg2, arg3)			\
-	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)),	\
-	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)))
-#define PVOP_VCALL3(op, arg1, arg2, arg3)				\
-	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)),		\
-	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)))
-
-/* This is the only difference in x86_64. We can make it much simpler */
-#ifdef CONFIG_X86_32
-#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
-	__PVOP_CALL(rettype, op,					\
-		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
-		    "0" ((u32)(arg1)), "1" ((u32)(arg2)),		\
-		    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
-#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
-	__PVOP_VCALL(op,						\
-		    "push %[_arg4];", "lea 4(%%esp),%%esp;",		\
-		    "0" ((u32)(arg1)), "1" ((u32)(arg2)),		\
-		    "2" ((u32)(arg3)), [_arg4] "mr" ((u32)(arg4)))
-#else
-#define PVOP_CALL4(rettype, op, arg1, arg2, arg3, arg4)			\
-	__PVOP_CALL(rettype, op, "", "", "0" ((unsigned long)(arg1)),	\
-	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)),		\
-	"3"((unsigned long)(arg4)))
-#define PVOP_VCALL4(op, arg1, arg2, arg3, arg4)				\
-	__PVOP_VCALL(op, "", "", "0" ((unsigned long)(arg1)),		\
-	"1"((unsigned long)(arg2)), "2"((unsigned long)(arg3)),		\
-	"3"((unsigned long)(arg4)))
-#endif
-
-static inline int paravirt_enabled(void)
-{
-	return pv_info.paravirt_enabled;
-}
-
-static inline void load_sp0(struct tss_struct *tss,
-			     struct thread_struct *thread)
-{
-	PVOP_VCALL2(pv_cpu_ops.load_sp0, tss, thread);
-}
-
-#define ARCH_SETUP			pv_init_ops.arch_setup();
-static inline unsigned long get_wallclock(void)
-{
-	return PVOP_CALL0(unsigned long, pv_time_ops.get_wallclock);
-}
-
-static inline int set_wallclock(unsigned long nowtime)
-{
-	return PVOP_CALL1(int, pv_time_ops.set_wallclock, nowtime);
-}
-
-static inline void (*choose_time_init(void))(void)
-{
-	return pv_time_ops.time_init;
-}
-
-/* The paravirtualized CPUID instruction. */
-static inline void __cpuid(unsigned int *eax, unsigned int *ebx,
-			   unsigned int *ecx, unsigned int *edx)
-{
-	PVOP_VCALL4(pv_cpu_ops.cpuid, eax, ebx, ecx, edx);
-}
-
-/*
- * These special macros can be used to get or set a debugging register
- */
-static inline unsigned long paravirt_get_debugreg(int reg)
-{
-	return PVOP_CALL1(unsigned long, pv_cpu_ops.get_debugreg, reg);
-}
-#define get_debugreg(var, reg) var = paravirt_get_debugreg(reg)
-static inline void set_debugreg(unsigned long val, int reg)
-{
-	PVOP_VCALL2(pv_cpu_ops.set_debugreg, reg, val);
-}
-
-static inline void clts(void)
-{
-	PVOP_VCALL0(pv_cpu_ops.clts);
-}
-
-static inline unsigned long read_cr0(void)
-{
-	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr0);
-}
-
-static inline void write_cr0(unsigned long x)
-{
-	PVOP_VCALL1(pv_cpu_ops.write_cr0, x);
-}
-
-static inline unsigned long read_cr2(void)
-{
-	return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr2);
-}
-
-static inline void write_cr2(unsigned long x)
-{
-	PVOP_VCALL1(pv_mmu_ops.write_cr2, x);
-}
-
-static inline unsigned long read_cr3(void)
-{
-	return PVOP_CALL0(unsigned long, pv_mmu_ops.read_cr3);
-}
-
-static inline void write_cr3(unsigned long x)
-{
-	PVOP_VCALL1(pv_mmu_ops.write_cr3, x);
-}
-
-static inline unsigned long read_cr4(void)
-{
-	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4);
-}
-static inline unsigned long read_cr4_safe(void)
-{
-	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr4_safe);
-}
-
-static inline void write_cr4(unsigned long x)
-{
-	PVOP_VCALL1(pv_cpu_ops.write_cr4, x);
-}
-
-#ifdef CONFIG_X86_64
-static inline unsigned long read_cr8(void)
-{
-	return PVOP_CALL0(unsigned long, pv_cpu_ops.read_cr8);
-}
-
-static inline void write_cr8(unsigned long x)
-{
-	PVOP_VCALL1(pv_cpu_ops.write_cr8, x);
-}
-#endif
-
-static inline void raw_safe_halt(void)
-{
-	PVOP_VCALL0(pv_irq_ops.safe_halt);
-}
-
-static inline void halt(void)
-{
-	PVOP_VCALL0(pv_irq_ops.safe_halt);
-}
-
-static inline void wbinvd(void)
-{
-	PVOP_VCALL0(pv_cpu_ops.wbinvd);
-}
-
-#define get_kernel_rpl()  (pv_info.kernel_rpl)
-
-static inline u64 paravirt_read_msr(unsigned msr, int *err)
-{
-	return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
-}
-static inline u64 paravirt_read_msr_amd(unsigned msr, int *err)
-{
-	return PVOP_CALL2(u64, pv_cpu_ops.read_msr_amd, msr, err);
-}
-static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
-{
-	return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
-}
-
-/* These should all do BUG_ON(_err), but our headers are too tangled. */
-#define rdmsr(msr, val1, val2)			\
-do {						\
-	int _err;				\
-	u64 _l = paravirt_read_msr(msr, &_err);	\
-	val1 = (u32)_l;				\
-	val2 = _l >> 32;			\
-} while (0)
-
-#define wrmsr(msr, val1, val2)			\
-do {						\
-	paravirt_write_msr(msr, val1, val2);	\
-} while (0)
-
-#define rdmsrl(msr, val)			\
-do {						\
-	int _err;				\
-	val = paravirt_read_msr(msr, &_err);	\
-} while (0)
-
-#define wrmsrl(msr, val)	wrmsr(msr, (u32)((u64)(val)), ((u64)(val))>>32)
-#define wrmsr_safe(msr, a, b)	paravirt_write_msr(msr, a, b)
-
-/* rdmsr with exception handling */
-#define rdmsr_safe(msr, a, b)			\
-({						\
-	int _err;				\
-	u64 _l = paravirt_read_msr(msr, &_err);	\
-	(*a) = (u32)_l;				\
-	(*b) = _l >> 32;			\
-	_err;					\
-})
-
-static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
-{
-	int err;
-
-	*p = paravirt_read_msr(msr, &err);
-	return err;
-}
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
-{
-	int err;
-
-	*p = paravirt_read_msr_amd(msr, &err);
-	return err;
-}
-
-static inline u64 paravirt_read_tsc(void)
-{
-	return PVOP_CALL0(u64, pv_cpu_ops.read_tsc);
-}
-
-#define rdtscl(low)				\
-do {						\
-	u64 _l = paravirt_read_tsc();		\
-	low = (int)_l;				\
-} while (0)
-
-#define rdtscll(val) (val = paravirt_read_tsc())
-
-static inline unsigned long long paravirt_sched_clock(void)
-{
-	return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
-}
-#define calibrate_tsc() (pv_time_ops.get_tsc_khz())
-
-static inline unsigned long long paravirt_read_pmc(int counter)
-{
-	return PVOP_CALL1(u64, pv_cpu_ops.read_pmc, counter);
-}
-
-#define rdpmc(counter, low, high)		\
-do {						\
-	u64 _l = paravirt_read_pmc(counter);	\
-	low = (u32)_l;				\
-	high = _l >> 32;			\
-} while (0)
-
-static inline unsigned long long paravirt_rdtscp(unsigned int *aux)
-{
-	return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux);
-}
-
-#define rdtscp(low, high, aux)				\
-do {							\
-	int __aux;					\
-	unsigned long __val = paravirt_rdtscp(&__aux);	\
-	(low) = (u32)__val;				\
-	(high) = (u32)(__val >> 32);			\
-	(aux) = __aux;					\
-} while (0)
-
-#define rdtscpll(val, aux)				\
-do {							\
-	unsigned long __aux; 				\
-	val = paravirt_rdtscp(&__aux);			\
-	(aux) = __aux;					\
-} while (0)
-
-static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
-{
-	PVOP_VCALL2(pv_cpu_ops.alloc_ldt, ldt, entries);
-}
-
-static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries)
-{
-	PVOP_VCALL2(pv_cpu_ops.free_ldt, ldt, entries);
-}
-
-static inline void load_TR_desc(void)
-{
-	PVOP_VCALL0(pv_cpu_ops.load_tr_desc);
-}
-static inline void load_gdt(const struct desc_ptr *dtr)
-{
-	PVOP_VCALL1(pv_cpu_ops.load_gdt, dtr);
-}
-static inline void load_idt(const struct desc_ptr *dtr)
-{
-	PVOP_VCALL1(pv_cpu_ops.load_idt, dtr);
-}
-static inline void set_ldt(const void *addr, unsigned entries)
-{
-	PVOP_VCALL2(pv_cpu_ops.set_ldt, addr, entries);
-}
-static inline void store_gdt(struct desc_ptr *dtr)
-{
-	PVOP_VCALL1(pv_cpu_ops.store_gdt, dtr);
-}
-static inline void store_idt(struct desc_ptr *dtr)
-{
-	PVOP_VCALL1(pv_cpu_ops.store_idt, dtr);
-}
-static inline unsigned long paravirt_store_tr(void)
-{
-	return PVOP_CALL0(unsigned long, pv_cpu_ops.store_tr);
-}
-#define store_tr(tr)	((tr) = paravirt_store_tr())
-static inline void load_TLS(struct thread_struct *t, unsigned cpu)
-{
-	PVOP_VCALL2(pv_cpu_ops.load_tls, t, cpu);
-}
-
-#ifdef CONFIG_X86_64
-static inline void load_gs_index(unsigned int gs)
-{
-	PVOP_VCALL1(pv_cpu_ops.load_gs_index, gs);
-}
-#endif
-
-static inline void write_ldt_entry(struct desc_struct *dt, int entry,
-				   const void *desc)
-{
-	PVOP_VCALL3(pv_cpu_ops.write_ldt_entry, dt, entry, desc);
-}
-
-static inline void write_gdt_entry(struct desc_struct *dt, int entry,
-				   void *desc, int type)
-{
-	PVOP_VCALL4(pv_cpu_ops.write_gdt_entry, dt, entry, desc, type);
-}
-
-static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
-{
-	PVOP_VCALL3(pv_cpu_ops.write_idt_entry, dt, entry, g);
-}
-static inline void set_iopl_mask(unsigned mask)
-{
-	PVOP_VCALL1(pv_cpu_ops.set_iopl_mask, mask);
-}
-
-/* The paravirtualized I/O functions */
-static inline void slow_down_io(void)
-{
-	pv_cpu_ops.io_delay();
-#ifdef REALLY_SLOW_IO
-	pv_cpu_ops.io_delay();
-	pv_cpu_ops.io_delay();
-	pv_cpu_ops.io_delay();
-#endif
-}
-
-#ifdef CONFIG_X86_LOCAL_APIC
-static inline void setup_boot_clock(void)
-{
-	PVOP_VCALL0(pv_apic_ops.setup_boot_clock);
-}
-
-static inline void setup_secondary_clock(void)
-{
-	PVOP_VCALL0(pv_apic_ops.setup_secondary_clock);
-}
-#endif
-
-static inline void paravirt_post_allocator_init(void)
-{
-	if (pv_init_ops.post_allocator_init)
-		(*pv_init_ops.post_allocator_init)();
-}
-
-static inline void paravirt_pagetable_setup_start(pgd_t *base)
-{
-	(*pv_mmu_ops.pagetable_setup_start)(base);
-}
-
-static inline void paravirt_pagetable_setup_done(pgd_t *base)
-{
-	(*pv_mmu_ops.pagetable_setup_done)(base);
-}
-
-#ifdef CONFIG_SMP
-static inline void startup_ipi_hook(int phys_apicid, unsigned long start_eip,
-				    unsigned long start_esp)
-{
-	PVOP_VCALL3(pv_apic_ops.startup_ipi_hook,
-		    phys_apicid, start_eip, start_esp);
-}
-#endif
-
-static inline void paravirt_activate_mm(struct mm_struct *prev,
-					struct mm_struct *next)
-{
-	PVOP_VCALL2(pv_mmu_ops.activate_mm, prev, next);
-}
-
-static inline void arch_dup_mmap(struct mm_struct *oldmm,
-				 struct mm_struct *mm)
-{
-	PVOP_VCALL2(pv_mmu_ops.dup_mmap, oldmm, mm);
-}
-
-static inline void arch_exit_mmap(struct mm_struct *mm)
-{
-	PVOP_VCALL1(pv_mmu_ops.exit_mmap, mm);
-}
-
-static inline void __flush_tlb(void)
-{
-	PVOP_VCALL0(pv_mmu_ops.flush_tlb_user);
-}
-static inline void __flush_tlb_global(void)
-{
-	PVOP_VCALL0(pv_mmu_ops.flush_tlb_kernel);
-}
-static inline void __flush_tlb_single(unsigned long addr)
-{
-	PVOP_VCALL1(pv_mmu_ops.flush_tlb_single, addr);
-}
-
-static inline void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
-				    unsigned long va)
-{
-	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, &cpumask, mm, va);
-}
-
-static inline int paravirt_pgd_alloc(struct mm_struct *mm)
-{
-	return PVOP_CALL1(int, pv_mmu_ops.pgd_alloc, mm);
-}
-
-static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	PVOP_VCALL2(pv_mmu_ops.pgd_free, mm, pgd);
-}
-
-static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)
-{
-	PVOP_VCALL2(pv_mmu_ops.alloc_pte, mm, pfn);
-}
-static inline void paravirt_release_pte(unsigned long pfn)
-{
-	PVOP_VCALL1(pv_mmu_ops.release_pte, pfn);
-}
-
-static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)
-{
-	PVOP_VCALL2(pv_mmu_ops.alloc_pmd, mm, pfn);
-}
-
-static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
-					    unsigned long start, unsigned long count)
-{
-	PVOP_VCALL4(pv_mmu_ops.alloc_pmd_clone, pfn, clonepfn, start, count);
-}
-static inline void paravirt_release_pmd(unsigned long pfn)
-{
-	PVOP_VCALL1(pv_mmu_ops.release_pmd, pfn);
-}
-
-static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)
-{
-	PVOP_VCALL2(pv_mmu_ops.alloc_pud, mm, pfn);
-}
-static inline void paravirt_release_pud(unsigned long pfn)
-{
-	PVOP_VCALL1(pv_mmu_ops.release_pud, pfn);
-}
-
-#ifdef CONFIG_HIGHPTE
-static inline void *kmap_atomic_pte(struct page *page, enum km_type type)
-{
-	unsigned long ret;
-	ret = PVOP_CALL2(unsigned long, pv_mmu_ops.kmap_atomic_pte, page, type);
-	return (void *)ret;
-}
-#endif
-
-static inline void pte_update(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
-{
-	PVOP_VCALL3(pv_mmu_ops.pte_update, mm, addr, ptep);
-}
-
-static inline void pte_update_defer(struct mm_struct *mm, unsigned long addr,
-				    pte_t *ptep)
-{
-	PVOP_VCALL3(pv_mmu_ops.pte_update_defer, mm, addr, ptep);
-}
-
-static inline pte_t __pte(pteval_t val)
-{
-	pteval_t ret;
-
-	if (sizeof(pteval_t) > sizeof(long))
-		ret = PVOP_CALL2(pteval_t,
-				 pv_mmu_ops.make_pte,
-				 val, (u64)val >> 32);
-	else
-		ret = PVOP_CALL1(pteval_t,
-				 pv_mmu_ops.make_pte,
-				 val);
-
-	return (pte_t) { .pte = ret };
-}
-
-static inline pteval_t pte_val(pte_t pte)
-{
-	pteval_t ret;
-
-	if (sizeof(pteval_t) > sizeof(long))
-		ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_val,
-				 pte.pte, (u64)pte.pte >> 32);
-	else
-		ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_val,
-				 pte.pte);
-
-	return ret;
-}
-
-static inline pteval_t pte_flags(pte_t pte)
-{
-	pteval_t ret;
-
-	if (sizeof(pteval_t) > sizeof(long))
-		ret = PVOP_CALL2(pteval_t, pv_mmu_ops.pte_flags,
-				 pte.pte, (u64)pte.pte >> 32);
-	else
-		ret = PVOP_CALL1(pteval_t, pv_mmu_ops.pte_flags,
-				 pte.pte);
-
-#ifdef CONFIG_PARAVIRT_DEBUG
-	BUG_ON(ret & PTE_PFN_MASK);
-#endif
-	return ret;
-}
-
-static inline pgd_t __pgd(pgdval_t val)
-{
-	pgdval_t ret;
-
-	if (sizeof(pgdval_t) > sizeof(long))
-		ret = PVOP_CALL2(pgdval_t, pv_mmu_ops.make_pgd,
-				 val, (u64)val >> 32);
-	else
-		ret = PVOP_CALL1(pgdval_t, pv_mmu_ops.make_pgd,
-				 val);
-
-	return (pgd_t) { ret };
-}
-
-static inline pgdval_t pgd_val(pgd_t pgd)
-{
-	pgdval_t ret;
-
-	if (sizeof(pgdval_t) > sizeof(long))
-		ret =  PVOP_CALL2(pgdval_t, pv_mmu_ops.pgd_val,
-				  pgd.pgd, (u64)pgd.pgd >> 32);
-	else
-		ret =  PVOP_CALL1(pgdval_t, pv_mmu_ops.pgd_val,
-				  pgd.pgd);
-
-	return ret;
-}
-
-#define  __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
-static inline pte_t ptep_modify_prot_start(struct mm_struct *mm, unsigned long addr,
-					   pte_t *ptep)
-{
-	pteval_t ret;
-
-	ret = PVOP_CALL3(pteval_t, pv_mmu_ops.ptep_modify_prot_start,
-			 mm, addr, ptep);
-
-	return (pte_t) { .pte = ret };
-}
-
-static inline void ptep_modify_prot_commit(struct mm_struct *mm, unsigned long addr,
-					   pte_t *ptep, pte_t pte)
-{
-	if (sizeof(pteval_t) > sizeof(long))
-		/* 5 arg words */
-		pv_mmu_ops.ptep_modify_prot_commit(mm, addr, ptep, pte);
-	else
-		PVOP_VCALL4(pv_mmu_ops.ptep_modify_prot_commit,
-			    mm, addr, ptep, pte.pte);
-}
-
-static inline void set_pte(pte_t *ptep, pte_t pte)
-{
-	if (sizeof(pteval_t) > sizeof(long))
-		PVOP_VCALL3(pv_mmu_ops.set_pte, ptep,
-			    pte.pte, (u64)pte.pte >> 32);
-	else
-		PVOP_VCALL2(pv_mmu_ops.set_pte, ptep,
-			    pte.pte);
-}
-
-static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep, pte_t pte)
-{
-	if (sizeof(pteval_t) > sizeof(long))
-		/* 5 arg words */
-		pv_mmu_ops.set_pte_at(mm, addr, ptep, pte);
-	else
-		PVOP_VCALL4(pv_mmu_ops.set_pte_at, mm, addr, ptep, pte.pte);
-}
-
-static inline void set_pmd(pmd_t *pmdp, pmd_t pmd)
-{
-	pmdval_t val = native_pmd_val(pmd);
-
-	if (sizeof(pmdval_t) > sizeof(long))
-		PVOP_VCALL3(pv_mmu_ops.set_pmd, pmdp, val, (u64)val >> 32);
-	else
-		PVOP_VCALL2(pv_mmu_ops.set_pmd, pmdp, val);
-}
-
-#if PAGETABLE_LEVELS >= 3
-static inline pmd_t __pmd(pmdval_t val)
-{
-	pmdval_t ret;
-
-	if (sizeof(pmdval_t) > sizeof(long))
-		ret = PVOP_CALL2(pmdval_t, pv_mmu_ops.make_pmd,
-				 val, (u64)val >> 32);
-	else
-		ret = PVOP_CALL1(pmdval_t, pv_mmu_ops.make_pmd,
-				 val);
-
-	return (pmd_t) { ret };
-}
-
-static inline pmdval_t pmd_val(pmd_t pmd)
-{
-	pmdval_t ret;
-
-	if (sizeof(pmdval_t) > sizeof(long))
-		ret =  PVOP_CALL2(pmdval_t, pv_mmu_ops.pmd_val,
-				  pmd.pmd, (u64)pmd.pmd >> 32);
-	else
-		ret =  PVOP_CALL1(pmdval_t, pv_mmu_ops.pmd_val,
-				  pmd.pmd);
-
-	return ret;
-}
-
-static inline void set_pud(pud_t *pudp, pud_t pud)
-{
-	pudval_t val = native_pud_val(pud);
-
-	if (sizeof(pudval_t) > sizeof(long))
-		PVOP_VCALL3(pv_mmu_ops.set_pud, pudp,
-			    val, (u64)val >> 32);
-	else
-		PVOP_VCALL2(pv_mmu_ops.set_pud, pudp,
-			    val);
-}
-#if PAGETABLE_LEVELS == 4
-static inline pud_t __pud(pudval_t val)
-{
-	pudval_t ret;
-
-	if (sizeof(pudval_t) > sizeof(long))
-		ret = PVOP_CALL2(pudval_t, pv_mmu_ops.make_pud,
-				 val, (u64)val >> 32);
-	else
-		ret = PVOP_CALL1(pudval_t, pv_mmu_ops.make_pud,
-				 val);
-
-	return (pud_t) { ret };
-}
-
-static inline pudval_t pud_val(pud_t pud)
-{
-	pudval_t ret;
-
-	if (sizeof(pudval_t) > sizeof(long))
-		ret =  PVOP_CALL2(pudval_t, pv_mmu_ops.pud_val,
-				  pud.pud, (u64)pud.pud >> 32);
-	else
-		ret =  PVOP_CALL1(pudval_t, pv_mmu_ops.pud_val,
-				  pud.pud);
-
-	return ret;
-}
-
-static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
-{
-	pgdval_t val = native_pgd_val(pgd);
-
-	if (sizeof(pgdval_t) > sizeof(long))
-		PVOP_VCALL3(pv_mmu_ops.set_pgd, pgdp,
-			    val, (u64)val >> 32);
-	else
-		PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp,
-			    val);
-}
-
-static inline void pgd_clear(pgd_t *pgdp)
-{
-	set_pgd(pgdp, __pgd(0));
-}
-
-static inline void pud_clear(pud_t *pudp)
-{
-	set_pud(pudp, __pud(0));
-}
-
-#endif	/* PAGETABLE_LEVELS == 4 */
-
-#endif	/* PAGETABLE_LEVELS >= 3 */
-
-#ifdef CONFIG_X86_PAE
-/* Special-case pte-setting operations for PAE, which can't update a
-   64-bit pte atomically */
-static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	PVOP_VCALL3(pv_mmu_ops.set_pte_atomic, ptep,
-		    pte.pte, pte.pte >> 32);
-}
-
-static inline void set_pte_present(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	/* 5 arg words */
-	pv_mmu_ops.set_pte_present(mm, addr, ptep, pte);
-}
-
-static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
-			     pte_t *ptep)
-{
-	PVOP_VCALL3(pv_mmu_ops.pte_clear, mm, addr, ptep);
-}
-
-static inline void pmd_clear(pmd_t *pmdp)
-{
-	PVOP_VCALL1(pv_mmu_ops.pmd_clear, pmdp);
-}
-#else  /* !CONFIG_X86_PAE */
-static inline void set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	set_pte(ptep, pte);
-}
-
-static inline void set_pte_present(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte(ptep, pte);
-}
-
-static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
-			     pte_t *ptep)
-{
-	set_pte_at(mm, addr, ptep, __pte(0));
-}
-
-static inline void pmd_clear(pmd_t *pmdp)
-{
-	set_pmd(pmdp, __pmd(0));
-}
-#endif	/* CONFIG_X86_PAE */
-
-/* Lazy mode for batching updates / context switch */
-enum paravirt_lazy_mode {
-	PARAVIRT_LAZY_NONE,
-	PARAVIRT_LAZY_MMU,
-	PARAVIRT_LAZY_CPU,
-};
-
-enum paravirt_lazy_mode paravirt_get_lazy_mode(void);
-void paravirt_enter_lazy_cpu(void);
-void paravirt_leave_lazy_cpu(void);
-void paravirt_enter_lazy_mmu(void);
-void paravirt_leave_lazy_mmu(void);
-void paravirt_leave_lazy(enum paravirt_lazy_mode mode);
-
-#define  __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-static inline void arch_enter_lazy_cpu_mode(void)
-{
-	PVOP_VCALL0(pv_cpu_ops.lazy_mode.enter);
-}
-
-static inline void arch_leave_lazy_cpu_mode(void)
-{
-	PVOP_VCALL0(pv_cpu_ops.lazy_mode.leave);
-}
-
-static inline void arch_flush_lazy_cpu_mode(void)
-{
-	if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU)) {
-		arch_leave_lazy_cpu_mode();
-		arch_enter_lazy_cpu_mode();
-	}
-}
-
-
-#define  __HAVE_ARCH_ENTER_LAZY_MMU_MODE
-static inline void arch_enter_lazy_mmu_mode(void)
-{
-	PVOP_VCALL0(pv_mmu_ops.lazy_mode.enter);
-}
-
-static inline void arch_leave_lazy_mmu_mode(void)
-{
-	PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
-}
-
-static inline void arch_flush_lazy_mmu_mode(void)
-{
-	if (unlikely(paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU)) {
-		arch_leave_lazy_mmu_mode();
-		arch_enter_lazy_mmu_mode();
-	}
-}
-
-static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
-				unsigned long phys, pgprot_t flags)
-{
-	pv_mmu_ops.set_fixmap(idx, phys, flags);
-}
-
-void _paravirt_nop(void);
-#define paravirt_nop	((void *)_paravirt_nop)
-
-void paravirt_use_bytelocks(void);
-
-#ifdef CONFIG_SMP
-
-static inline int __raw_spin_is_locked(struct raw_spinlock *lock)
-{
-	return PVOP_CALL1(int, pv_lock_ops.spin_is_locked, lock);
-}
-
-static inline int __raw_spin_is_contended(struct raw_spinlock *lock)
-{
-	return PVOP_CALL1(int, pv_lock_ops.spin_is_contended, lock);
-}
-
-static __always_inline void __raw_spin_lock(struct raw_spinlock *lock)
-{
-	PVOP_VCALL1(pv_lock_ops.spin_lock, lock);
-}
-
-static __always_inline void __raw_spin_lock_flags(struct raw_spinlock *lock,
-						  unsigned long flags)
-{
-	PVOP_VCALL2(pv_lock_ops.spin_lock_flags, lock, flags);
-}
-
-static __always_inline int __raw_spin_trylock(struct raw_spinlock *lock)
-{
-	return PVOP_CALL1(int, pv_lock_ops.spin_trylock, lock);
-}
-
-static __always_inline void __raw_spin_unlock(struct raw_spinlock *lock)
-{
-	PVOP_VCALL1(pv_lock_ops.spin_unlock, lock);
-}
-
-#endif
-
-/* These all sit in the .parainstructions section to tell us what to patch. */
-struct paravirt_patch_site {
-	u8 *instr; 		/* original instructions */
-	u8 instrtype;		/* type of this instruction */
-	u8 len;			/* length of original instruction */
-	u16 clobbers;		/* what registers you may clobber */
-};
-
-extern struct paravirt_patch_site __parainstructions[],
-	__parainstructions_end[];
-
-#ifdef CONFIG_X86_32
-#define PV_SAVE_REGS "pushl %%ecx; pushl %%edx;"
-#define PV_RESTORE_REGS "popl %%edx; popl %%ecx"
-#define PV_FLAGS_ARG "0"
-#define PV_EXTRA_CLOBBERS
-#define PV_VEXTRA_CLOBBERS
-#else
-/* We save some registers, but all of them, that's too much. We clobber all
- * caller saved registers but the argument parameter */
-#define PV_SAVE_REGS "pushq %%rdi;"
-#define PV_RESTORE_REGS "popq %%rdi;"
-#define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx", "rsi"
-#define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx", "rsi"
-#define PV_FLAGS_ARG "D"
-#endif
-
-static inline unsigned long __raw_local_save_flags(void)
-{
-	unsigned long f;
-
-	asm volatile(paravirt_alt(PV_SAVE_REGS
-				  PARAVIRT_CALL
-				  PV_RESTORE_REGS)
-		     : "=a"(f)
-		     : paravirt_type(pv_irq_ops.save_fl),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "cc" PV_VEXTRA_CLOBBERS);
-	return f;
-}
-
-static inline void raw_local_irq_restore(unsigned long f)
-{
-	asm volatile(paravirt_alt(PV_SAVE_REGS
-				  PARAVIRT_CALL
-				  PV_RESTORE_REGS)
-		     : "=a"(f)
-		     : PV_FLAGS_ARG(f),
-		       paravirt_type(pv_irq_ops.restore_fl),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "cc" PV_EXTRA_CLOBBERS);
-}
-
-static inline void raw_local_irq_disable(void)
-{
-	asm volatile(paravirt_alt(PV_SAVE_REGS
-				  PARAVIRT_CALL
-				  PV_RESTORE_REGS)
-		     :
-		     : paravirt_type(pv_irq_ops.irq_disable),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "eax", "cc" PV_EXTRA_CLOBBERS);
-}
-
-static inline void raw_local_irq_enable(void)
-{
-	asm volatile(paravirt_alt(PV_SAVE_REGS
-				  PARAVIRT_CALL
-				  PV_RESTORE_REGS)
-		     :
-		     : paravirt_type(pv_irq_ops.irq_enable),
-		       paravirt_clobber(CLBR_EAX)
-		     : "memory", "eax", "cc" PV_EXTRA_CLOBBERS);
-}
-
-static inline unsigned long __raw_local_irq_save(void)
-{
-	unsigned long f;
-
-	f = __raw_local_save_flags();
-	raw_local_irq_disable();
-	return f;
-}
-
-
-/* Make sure as little as possible of this mess escapes. */
-#undef PARAVIRT_CALL
-#undef __PVOP_CALL
-#undef __PVOP_VCALL
-#undef PVOP_VCALL0
-#undef PVOP_CALL0
-#undef PVOP_VCALL1
-#undef PVOP_CALL1
-#undef PVOP_VCALL2
-#undef PVOP_CALL2
-#undef PVOP_VCALL3
-#undef PVOP_CALL3
-#undef PVOP_VCALL4
-#undef PVOP_CALL4
-
-#else  /* __ASSEMBLY__ */
-
-#define _PVSITE(ptype, clobbers, ops, word, algn)	\
-771:;						\
-	ops;					\
-772:;						\
-	.pushsection .parainstructions,"a";	\
-	 .align	algn;				\
-	 word 771b;				\
-	 .byte ptype;				\
-	 .byte 772b-771b;			\
-	 .short clobbers;			\
-	.popsection
-
-
-#ifdef CONFIG_X86_64
-#define PV_SAVE_REGS				\
-	push %rax;				\
-	push %rcx;				\
-	push %rdx;				\
-	push %rsi;				\
-	push %rdi;				\
-	push %r8;				\
-	push %r9;				\
-	push %r10;				\
-	push %r11
-#define PV_RESTORE_REGS				\
-	pop %r11;				\
-	pop %r10;				\
-	pop %r9;				\
-	pop %r8;				\
-	pop %rdi;				\
-	pop %rsi;				\
-	pop %rdx;				\
-	pop %rcx;				\
-	pop %rax
-#define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 8)
-#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .quad, 8)
-#define PARA_INDIRECT(addr)	*addr(%rip)
-#else
-#define PV_SAVE_REGS   pushl %eax; pushl %edi; pushl %ecx; pushl %edx
-#define PV_RESTORE_REGS popl %edx; popl %ecx; popl %edi; popl %eax
-#define PARA_PATCH(struct, off)        ((PARAVIRT_PATCH_##struct + (off)) / 4)
-#define PARA_SITE(ptype, clobbers, ops) _PVSITE(ptype, clobbers, ops, .long, 4)
-#define PARA_INDIRECT(addr)	*%cs:addr
-#endif
-
-#define INTERRUPT_RETURN						\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE,	\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret))
-
-#define DISABLE_INTERRUPTS(clobbers)					\
-	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
-		  PV_SAVE_REGS;						\
-		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable);	\
-		  PV_RESTORE_REGS;)			\
-
-#define ENABLE_INTERRUPTS(clobbers)					\
-	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers,	\
-		  PV_SAVE_REGS;						\
-		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable);	\
-		  PV_RESTORE_REGS;)
-
-#define USERGS_SYSRET32							\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret32),	\
-		  CLBR_NONE,						\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret32))
-
-#ifdef CONFIG_X86_32
-#define GET_CR0_INTO_EAX				\
-	push %ecx; push %edx;				\
-	call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0);	\
-	pop %edx; pop %ecx
-
-#define ENABLE_INTERRUPTS_SYSEXIT					\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),	\
-		  CLBR_NONE,						\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
-
-
-#else	/* !CONFIG_X86_32 */
-
-/*
- * If swapgs is used while the userspace stack is still current,
- * there's no way to call a pvop.  The PV replacement *must* be
- * inlined, or the swapgs instruction must be trapped and emulated.
- */
-#define SWAPGS_UNSAFE_STACK						\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
-		  swapgs)
-
-#define SWAPGS								\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE,	\
-		  PV_SAVE_REGS;						\
-		  call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs);		\
-		  PV_RESTORE_REGS					\
-		 )
-
-#define GET_CR2_INTO_RCX				\
-	call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2);	\
-	movq %rax, %rcx;				\
-	xorq %rax, %rax;
-
-#define PARAVIRT_ADJUST_EXCEPTION_FRAME					\
-	PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_adjust_exception_frame), \
-		  CLBR_NONE,						\
-		  call PARA_INDIRECT(pv_irq_ops+PV_IRQ_adjust_exception_frame))
-
-#define USERGS_SYSRET64							\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64),	\
-		  CLBR_NONE,						\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
-
-#define ENABLE_INTERRUPTS_SYSEXIT32					\
-	PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_irq_enable_sysexit),	\
-		  CLBR_NONE,						\
-		  jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_irq_enable_sysexit))
-#endif	/* CONFIG_X86_32 */
-
-#endif /* __ASSEMBLY__ */
-#endif /* CONFIG_PARAVIRT */
-#endif /* ASM_X86__PARAVIRT_H */
diff --git a/include/asm-x86/parport.h b/include/asm-x86/parport.h
deleted file mode 100644
index 2e3dda4dc3d9..000000000000
--- a/include/asm-x86/parport.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef ASM_X86__PARPORT_H
-#define ASM_X86__PARPORT_H
-
-static int __devinit parport_pc_find_isa_ports(int autoirq, int autodma);
-static int __devinit parport_pc_find_nonpci_ports(int autoirq, int autodma)
-{
-	return parport_pc_find_isa_ports(autoirq, autodma);
-}
-
-#endif /* ASM_X86__PARPORT_H */
diff --git a/include/asm-x86/pat.h b/include/asm-x86/pat.h
deleted file mode 100644
index 482c3e3f9879..000000000000
--- a/include/asm-x86/pat.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef ASM_X86__PAT_H
-#define ASM_X86__PAT_H
-
-#include <linux/types.h>
-
-#ifdef CONFIG_X86_PAT
-extern int pat_enabled;
-extern void validate_pat_support(struct cpuinfo_x86 *c);
-#else
-static const int pat_enabled;
-static inline void validate_pat_support(struct cpuinfo_x86 *c) { }
-#endif
-
-extern void pat_init(void);
-
-extern int reserve_memtype(u64 start, u64 end,
-		unsigned long req_type, unsigned long *ret_type);
-extern int free_memtype(u64 start, u64 end);
-
-extern void pat_disable(char *reason);
-
-#endif /* ASM_X86__PAT_H */
diff --git a/include/asm-x86/pci-direct.h b/include/asm-x86/pci-direct.h
deleted file mode 100644
index da42be07b690..000000000000
--- a/include/asm-x86/pci-direct.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef ASM_X86__PCI_DIRECT_H
-#define ASM_X86__PCI_DIRECT_H
-
-#include <linux/types.h>
-
-/* Direct PCI access. This is used for PCI accesses in early boot before
-   the PCI subsystem works. */
-
-extern u32 read_pci_config(u8 bus, u8 slot, u8 func, u8 offset);
-extern u8 read_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset);
-extern u16 read_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset);
-extern void write_pci_config(u8 bus, u8 slot, u8 func, u8 offset, u32 val);
-extern void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val);
-extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val);
-
-extern int early_pci_allowed(void);
-
-extern unsigned int pci_early_dump_regs;
-extern void early_dump_pci_device(u8 bus, u8 slot, u8 func);
-extern void early_dump_pci_devices(void);
-#endif /* ASM_X86__PCI_DIRECT_H */
diff --git a/include/asm-x86/pci.h b/include/asm-x86/pci.h
deleted file mode 100644
index 602583192991..000000000000
--- a/include/asm-x86/pci.h
+++ /dev/null
@@ -1,114 +0,0 @@
-#ifndef ASM_X86__PCI_H
-#define ASM_X86__PCI_H
-
-#include <linux/mm.h> /* for struct page */
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/string.h>
-#include <asm/scatterlist.h>
-#include <asm/io.h>
-
-#ifdef __KERNEL__
-
-struct pci_sysdata {
-	int		domain;		/* PCI domain */
-	int		node;		/* NUMA node */
-#ifdef CONFIG_X86_64
-	void		*iommu;		/* IOMMU private data */
-#endif
-};
-
-extern int pci_routeirq;
-
-/* scan a bus after allocating a pci_sysdata for it */
-extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops,
-					    int node);
-extern struct pci_bus *pci_scan_bus_with_sysdata(int busno);
-
-static inline int pci_domain_nr(struct pci_bus *bus)
-{
-	struct pci_sysdata *sd = bus->sysdata;
-	return sd->domain;
-}
-
-static inline int pci_proc_domain(struct pci_bus *bus)
-{
-	return pci_domain_nr(bus);
-}
-
-
-/* Can be used to override the logic in pci_scan_bus for skipping
-   already-configured bus numbers - to be used for buggy BIOSes
-   or architectures with incomplete PCI setup by the loader */
-
-#ifdef CONFIG_PCI
-extern unsigned int pcibios_assign_all_busses(void);
-#else
-#define pcibios_assign_all_busses()	0
-#endif
-#define pcibios_scan_all_fns(a, b)	0
-
-extern unsigned long pci_mem_start;
-#define PCIBIOS_MIN_IO		0x1000
-#define PCIBIOS_MIN_MEM		(pci_mem_start)
-
-#define PCIBIOS_MIN_CARDBUS_IO	0x4000
-
-void pcibios_config_init(void);
-struct pci_bus *pcibios_scan_root(int bus);
-
-void pcibios_set_master(struct pci_dev *dev);
-void pcibios_penalize_isa_irq(int irq, int active);
-struct irq_routing_table *pcibios_get_irq_routing_table(void);
-int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq);
-
-
-#define HAVE_PCI_MMAP
-extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
-			       enum pci_mmap_state mmap_state,
-			       int write_combine);
-
-
-#ifdef CONFIG_PCI
-extern void early_quirks(void);
-static inline void pci_dma_burst_advice(struct pci_dev *pdev,
-					enum pci_dma_burst_strategy *strat,
-					unsigned long *strategy_parameter)
-{
-	*strat = PCI_DMA_BURST_INFINITY;
-	*strategy_parameter = ~0UL;
-}
-#else
-static inline void early_quirks(void) { }
-#endif
-
-#endif  /* __KERNEL__ */
-
-#ifdef CONFIG_X86_32
-# include "pci_32.h"
-#else
-# include "pci_64.h"
-#endif
-
-/* implement the pci_ DMA API in terms of the generic device dma_ one */
-#include <asm-generic/pci-dma-compat.h>
-
-/* generic pci stuff */
-#include <asm-generic/pci.h>
-
-#ifdef CONFIG_NUMA
-/* Returns the node based on pci bus */
-static inline int __pcibus_to_node(struct pci_bus *bus)
-{
-	struct pci_sysdata *sd = bus->sysdata;
-
-	return sd->node;
-}
-
-static inline cpumask_t __pcibus_to_cpumask(struct pci_bus *bus)
-{
-	return node_to_cpumask(__pcibus_to_node(bus));
-}
-#endif
-
-#endif /* ASM_X86__PCI_H */
diff --git a/include/asm-x86/pci_32.h b/include/asm-x86/pci_32.h
deleted file mode 100644
index 3f2288207c0c..000000000000
--- a/include/asm-x86/pci_32.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef ASM_X86__PCI_32_H
-#define ASM_X86__PCI_32_H
-
-
-#ifdef __KERNEL__
-
-
-/* Dynamic DMA mapping stuff.
- * i386 has everything mapped statically.
- */
-
-struct pci_dev;
-
-/* The PCI address space does equal the physical memory
- * address space.  The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS	(1)
-
-/* pci_unmap_{page,single} is a nop so... */
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	dma_addr_t ADDR_NAME[0];
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)	unsigned LEN_NAME[0];
-#define pci_unmap_addr(PTR, ADDR_NAME)	sizeof((PTR)->ADDR_NAME)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
-	do { break; } while (pci_unmap_addr(PTR, ADDR_NAME))
-#define pci_unmap_len(PTR, LEN_NAME)		sizeof((PTR)->LEN_NAME)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
-	do { break; } while (pci_unmap_len(PTR, LEN_NAME))
-
-
-#endif /* __KERNEL__ */
-
-
-#endif /* ASM_X86__PCI_32_H */
diff --git a/include/asm-x86/pci_64.h b/include/asm-x86/pci_64.h
deleted file mode 100644
index f72e12d5770e..000000000000
--- a/include/asm-x86/pci_64.h
+++ /dev/null
@@ -1,66 +0,0 @@
-#ifndef ASM_X86__PCI_64_H
-#define ASM_X86__PCI_64_H
-
-#ifdef __KERNEL__
-
-#ifdef CONFIG_CALGARY_IOMMU
-static inline void *pci_iommu(struct pci_bus *bus)
-{
-	struct pci_sysdata *sd = bus->sysdata;
-	return sd->iommu;
-}
-
-static inline void set_pci_iommu(struct pci_bus *bus, void *val)
-{
-	struct pci_sysdata *sd = bus->sysdata;
-	sd->iommu = val;
-}
-#endif /* CONFIG_CALGARY_IOMMU */
-
-extern int (*pci_config_read)(int seg, int bus, int dev, int fn,
-			      int reg, int len, u32 *value);
-extern int (*pci_config_write)(int seg, int bus, int dev, int fn,
-			       int reg, int len, u32 value);
-
-extern void dma32_reserve_bootmem(void);
-extern void pci_iommu_alloc(void);
-
-/* The PCI address space does equal the physical memory
- * address space.  The networking and block device layers use
- * this boolean for bounce buffer decisions
- *
- * On AMD64 it mostly equals, but we set it to zero if a hardware
- * IOMMU (gart) of sotware IOMMU (swiotlb) is available.
- */
-#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
-
-#if defined(CONFIG_GART_IOMMU) || defined(CONFIG_CALGARY_IOMMU)
-
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	\
-	dma_addr_t ADDR_NAME;
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)		\
-	__u32 LEN_NAME;
-#define pci_unmap_addr(PTR, ADDR_NAME)			\
-	((PTR)->ADDR_NAME)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)		\
-	(((PTR)->ADDR_NAME) = (VAL))
-#define pci_unmap_len(PTR, LEN_NAME)			\
-	((PTR)->LEN_NAME)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)		\
-	(((PTR)->LEN_NAME) = (VAL))
-
-#else
-/* No IOMMU */
-
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)
-#define pci_unmap_addr(PTR, ADDR_NAME)		(0)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)	do { } while (0)
-#define pci_unmap_len(PTR, LEN_NAME)		(0)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)	do { } while (0)
-
-#endif
-
-#endif /* __KERNEL__ */
-
-#endif /* ASM_X86__PCI_64_H */
diff --git a/include/asm-x86/pda.h b/include/asm-x86/pda.h
deleted file mode 100644
index 80860afffbdb..000000000000
--- a/include/asm-x86/pda.h
+++ /dev/null
@@ -1,137 +0,0 @@
-#ifndef ASM_X86__PDA_H
-#define ASM_X86__PDA_H
-
-#ifndef __ASSEMBLY__
-#include <linux/stddef.h>
-#include <linux/types.h>
-#include <linux/cache.h>
-#include <asm/page.h>
-
-/* Per processor datastructure. %gs points to it while the kernel runs */
-struct x8664_pda {
-	struct task_struct *pcurrent;	/* 0  Current process */
-	unsigned long data_offset;	/* 8 Per cpu data offset from linker
-					   address */
-	unsigned long kernelstack;	/* 16 top of kernel stack for current */
-	unsigned long oldrsp;		/* 24 user rsp for system call */
-	int irqcount;			/* 32 Irq nesting counter. Starts -1 */
-	unsigned int cpunumber;		/* 36 Logical CPU number */
-#ifdef CONFIG_CC_STACKPROTECTOR
-	unsigned long stack_canary;	/* 40 stack canary value */
-					/* gcc-ABI: this canary MUST be at
-					   offset 40!!! */
-#endif
-	char *irqstackptr;
-	short nodenumber;		/* number of current node (32k max) */
-	short in_bootmem;		/* pda lives in bootmem */
-	unsigned int __softirq_pending;
-	unsigned int __nmi_count;	/* number of NMI on this CPUs */
-	short mmu_state;
-	short isidle;
-	struct mm_struct *active_mm;
-	unsigned apic_timer_irqs;
-	unsigned irq0_irqs;
-	unsigned irq_resched_count;
-	unsigned irq_call_count;
-	unsigned irq_tlb_count;
-	unsigned irq_thermal_count;
-	unsigned irq_threshold_count;
-	unsigned irq_spurious_count;
-} ____cacheline_aligned_in_smp;
-
-extern struct x8664_pda **_cpu_pda;
-extern void pda_init(int);
-
-#define cpu_pda(i) (_cpu_pda[i])
-
-/*
- * There is no fast way to get the base address of the PDA, all the accesses
- * have to mention %fs/%gs.  So it needs to be done this Torvaldian way.
- */
-extern void __bad_pda_field(void) __attribute__((noreturn));
-
-/*
- * proxy_pda doesn't actually exist, but tell gcc it is accessed for
- * all PDA accesses so it gets read/write dependencies right.
- */
-extern struct x8664_pda _proxy_pda;
-
-#define pda_offset(field) offsetof(struct x8664_pda, field)
-
-#define pda_to_op(op, field, val)					\
-do {									\
-	typedef typeof(_proxy_pda.field) T__;				\
-	if (0) { T__ tmp__; tmp__ = (val); }	/* type checking */	\
-	switch (sizeof(_proxy_pda.field)) {				\
-	case 2:								\
-		asm(op "w %1,%%gs:%c2" :				\
-		    "+m" (_proxy_pda.field) :				\
-		    "ri" ((T__)val),					\
-		    "i"(pda_offset(field)));				\
-		break;							\
-	case 4:								\
-		asm(op "l %1,%%gs:%c2" :				\
-		    "+m" (_proxy_pda.field) :				\
-		    "ri" ((T__)val),					\
-		    "i" (pda_offset(field)));				\
-		break;							\
-	case 8:								\
-		asm(op "q %1,%%gs:%c2":					\
-		    "+m" (_proxy_pda.field) :				\
-		    "ri" ((T__)val),					\
-		    "i"(pda_offset(field)));				\
-		break;							\
-	default:							\
-		__bad_pda_field();					\
-	}								\
-} while (0)
-
-#define pda_from_op(op, field)			\
-({						\
-	typeof(_proxy_pda.field) ret__;		\
-	switch (sizeof(_proxy_pda.field)) {	\
-	case 2:					\
-		asm(op "w %%gs:%c1,%0" :	\
-		    "=r" (ret__) :		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	case 4:					\
-		asm(op "l %%gs:%c1,%0":		\
-		    "=r" (ret__):		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	case 8:					\
-		asm(op "q %%gs:%c1,%0":		\
-		    "=r" (ret__) :		\
-		    "i" (pda_offset(field)),	\
-		    "m" (_proxy_pda.field));	\
-		break;				\
-	default:				\
-		__bad_pda_field();		\
-	}					\
-	ret__;					\
-})
-
-#define read_pda(field)		pda_from_op("mov", field)
-#define write_pda(field, val)	pda_to_op("mov", field, val)
-#define add_pda(field, val)	pda_to_op("add", field, val)
-#define sub_pda(field, val)	pda_to_op("sub", field, val)
-#define or_pda(field, val)	pda_to_op("or", field, val)
-
-/* This is not atomic against other CPUs -- CPU preemption needs to be off */
-#define test_and_clear_bit_pda(bit, field)				\
-({									\
-	int old__;							\
-	asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0"			\
-		     : "=r" (old__), "+m" (_proxy_pda.field)		\
-		     : "dIr" (bit), "i" (pda_offset(field)) : "memory");\
-	old__;								\
-})
-
-#endif
-
-#define PDA_STACKOFFSET (5*8)
-
-#endif /* ASM_X86__PDA_H */
diff --git a/include/asm-x86/percpu.h b/include/asm-x86/percpu.h
deleted file mode 100644
index e10a1d0678cf..000000000000
--- a/include/asm-x86/percpu.h
+++ /dev/null
@@ -1,218 +0,0 @@
-#ifndef ASM_X86__PERCPU_H
-#define ASM_X86__PERCPU_H
-
-#ifdef CONFIG_X86_64
-#include <linux/compiler.h>
-
-/* Same as asm-generic/percpu.h, except that we store the per cpu offset
-   in the PDA. Longer term the PDA and every per cpu variable
-   should be just put into a single section and referenced directly
-   from %gs */
-
-#ifdef CONFIG_SMP
-#include <asm/pda.h>
-
-#define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
-#define __my_cpu_offset read_pda(data_offset)
-
-#define per_cpu_offset(x) (__per_cpu_offset(x))
-
-#endif
-#include <asm-generic/percpu.h>
-
-DECLARE_PER_CPU(struct x8664_pda, pda);
-
-/*
- * These are supposed to be implemented as a single instruction which
- * operates on the per-cpu data base segment.  x86-64 doesn't have
- * that yet, so this is a fairly inefficient workaround for the
- * meantime.  The single instruction is atomic with respect to
- * preemption and interrupts, so we need to explicitly disable
- * interrupts here to achieve the same effect.  However, because it
- * can be used from within interrupt-disable/enable, we can't actually
- * disable interrupts; disabling preemption is enough.
- */
-#define x86_read_percpu(var)						\
-	({								\
-		typeof(per_cpu_var(var)) __tmp;				\
-		preempt_disable();					\
-		__tmp = __get_cpu_var(var);				\
-		preempt_enable();					\
-		__tmp;							\
-	})
-
-#define x86_write_percpu(var, val)					\
-	do {								\
-		preempt_disable();					\
-		__get_cpu_var(var) = (val);				\
-		preempt_enable();					\
-	} while(0)
-
-#else /* CONFIG_X86_64 */
-
-#ifdef __ASSEMBLY__
-
-/*
- * PER_CPU finds an address of a per-cpu variable.
- *
- * Args:
- *    var - variable name
- *    reg - 32bit register
- *
- * The resulting address is stored in the "reg" argument.
- *
- * Example:
- *    PER_CPU(cpu_gdt_descr, %ebx)
- */
-#ifdef CONFIG_SMP
-#define PER_CPU(var, reg)				\
-	movl %fs:per_cpu__##this_cpu_off, reg;		\
-	lea per_cpu__##var(reg), reg
-#define PER_CPU_VAR(var)	%fs:per_cpu__##var
-#else /* ! SMP */
-#define PER_CPU(var, reg)			\
-	movl $per_cpu__##var, reg
-#define PER_CPU_VAR(var)	per_cpu__##var
-#endif	/* SMP */
-
-#else /* ...!ASSEMBLY */
-
-/*
- * PER_CPU finds an address of a per-cpu variable.
- *
- * Args:
- *    var - variable name
- *    cpu - 32bit register containing the current CPU number
- *
- * The resulting address is stored in the "cpu" argument.
- *
- * Example:
- *    PER_CPU(cpu_gdt_descr, %ebx)
- */
-#ifdef CONFIG_SMP
-
-#define __my_cpu_offset x86_read_percpu(this_cpu_off)
-
-/* fs segment starts at (positive) offset == __per_cpu_offset[cpu] */
-#define __percpu_seg "%%fs:"
-
-#else  /* !SMP */
-
-#define __percpu_seg ""
-
-#endif	/* SMP */
-
-#include <asm-generic/percpu.h>
-
-/* We can use this directly for local CPU (faster). */
-DECLARE_PER_CPU(unsigned long, this_cpu_off);
-
-/* For arch-specific code, we can use direct single-insn ops (they
- * don't give an lvalue though). */
-extern void __bad_percpu_size(void);
-
-#define percpu_to_op(op, var, val)			\
-do {							\
-	typedef typeof(var) T__;			\
-	if (0) {					\
-		T__ tmp__;				\
-		tmp__ = (val);				\
-	}						\
-	switch (sizeof(var)) {				\
-	case 1:						\
-		asm(op "b %1,"__percpu_seg"%0"		\
-		    : "+m" (var)			\
-		    : "ri" ((T__)val));			\
-		break;					\
-	case 2:						\
-		asm(op "w %1,"__percpu_seg"%0"		\
-		    : "+m" (var)			\
-		    : "ri" ((T__)val));			\
-		break;					\
-	case 4:						\
-		asm(op "l %1,"__percpu_seg"%0"		\
-		    : "+m" (var)			\
-		    : "ri" ((T__)val));			\
-		break;					\
-	default: __bad_percpu_size();			\
-	}						\
-} while (0)
-
-#define percpu_from_op(op, var)				\
-({							\
-	typeof(var) ret__;				\
-	switch (sizeof(var)) {				\
-	case 1:						\
-		asm(op "b "__percpu_seg"%1,%0"		\
-		    : "=r" (ret__)			\
-		    : "m" (var));			\
-		break;					\
-	case 2:						\
-		asm(op "w "__percpu_seg"%1,%0"		\
-		    : "=r" (ret__)			\
-		    : "m" (var));			\
-		break;					\
-	case 4:						\
-		asm(op "l "__percpu_seg"%1,%0"		\
-		    : "=r" (ret__)			\
-		    : "m" (var));			\
-		break;					\
-	default: __bad_percpu_size();			\
-	}						\
-	ret__;						\
-})
-
-#define x86_read_percpu(var) percpu_from_op("mov", per_cpu__##var)
-#define x86_write_percpu(var, val) percpu_to_op("mov", per_cpu__##var, val)
-#define x86_add_percpu(var, val) percpu_to_op("add", per_cpu__##var, val)
-#define x86_sub_percpu(var, val) percpu_to_op("sub", per_cpu__##var, val)
-#define x86_or_percpu(var, val) percpu_to_op("or", per_cpu__##var, val)
-#endif /* !__ASSEMBLY__ */
-#endif /* !CONFIG_X86_64 */
-
-#ifdef CONFIG_SMP
-
-/*
- * Define the "EARLY_PER_CPU" macros.  These are used for some per_cpu
- * variables that are initialized and accessed before there are per_cpu
- * areas allocated.
- */
-
-#define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)			\
-	DEFINE_PER_CPU(_type, _name) = _initvalue;			\
-	__typeof__(_type) _name##_early_map[NR_CPUS] __initdata =	\
-				{ [0 ... NR_CPUS-1] = _initvalue };	\
-	__typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map
-
-#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
-	EXPORT_PER_CPU_SYMBOL(_name)
-
-#define DECLARE_EARLY_PER_CPU(_type, _name)			\
-	DECLARE_PER_CPU(_type, _name);				\
-	extern __typeof__(_type) *_name##_early_ptr;		\
-	extern __typeof__(_type)  _name##_early_map[]
-
-#define	early_per_cpu_ptr(_name) (_name##_early_ptr)
-#define	early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
-#define	early_per_cpu(_name, _cpu) 				\
-	(early_per_cpu_ptr(_name) ?				\
-		early_per_cpu_ptr(_name)[_cpu] :		\
-		per_cpu(_name, _cpu))
-
-#else	/* !CONFIG_SMP */
-#define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)		\
-	DEFINE_PER_CPU(_type, _name) = _initvalue
-
-#define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
-	EXPORT_PER_CPU_SYMBOL(_name)
-
-#define DECLARE_EARLY_PER_CPU(_type, _name)			\
-	DECLARE_PER_CPU(_type, _name)
-
-#define	early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
-#define	early_per_cpu_ptr(_name) NULL
-/* no early_per_cpu_map() */
-
-#endif	/* !CONFIG_SMP */
-
-#endif /* ASM_X86__PERCPU_H */
diff --git a/include/asm-x86/pgalloc.h b/include/asm-x86/pgalloc.h
deleted file mode 100644
index 3cd23adedae8..000000000000
--- a/include/asm-x86/pgalloc.h
+++ /dev/null
@@ -1,114 +0,0 @@
-#ifndef ASM_X86__PGALLOC_H
-#define ASM_X86__PGALLOC_H
-
-#include <linux/threads.h>
-#include <linux/mm.h>		/* for struct page */
-#include <linux/pagemap.h>
-
-static inline int  __paravirt_pgd_alloc(struct mm_struct *mm) { return 0; }
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-#define paravirt_pgd_alloc(mm)	__paravirt_pgd_alloc(mm)
-static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) {}
-static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn)	{}
-static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn)	{}
-static inline void paravirt_alloc_pmd_clone(unsigned long pfn, unsigned long clonepfn,
-					    unsigned long start, unsigned long count) {}
-static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn)	{}
-static inline void paravirt_release_pte(unsigned long pfn) {}
-static inline void paravirt_release_pmd(unsigned long pfn) {}
-static inline void paravirt_release_pud(unsigned long pfn) {}
-#endif
-
-/*
- * Allocate and free page tables.
- */
-extern pgd_t *pgd_alloc(struct mm_struct *);
-extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
-
-extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
-extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long);
-
-/* Should really implement gc for free page table pages. This could be
-   done with a reference count in struct page. */
-
-static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
-{
-	BUG_ON((unsigned long)pte & (PAGE_SIZE-1));
-	free_page((unsigned long)pte);
-}
-
-static inline void pte_free(struct mm_struct *mm, struct page *pte)
-{
-	__free_page(pte);
-}
-
-extern void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
-
-static inline void pmd_populate_kernel(struct mm_struct *mm,
-				       pmd_t *pmd, pte_t *pte)
-{
-	paravirt_alloc_pte(mm, __pa(pte) >> PAGE_SHIFT);
-	set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
-}
-
-static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
-				struct page *pte)
-{
-	unsigned long pfn = page_to_pfn(pte);
-
-	paravirt_alloc_pte(mm, pfn);
-	set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE));
-}
-
-#define pmd_pgtable(pmd) pmd_page(pmd)
-
-#if PAGETABLE_LEVELS > 2
-static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
-	return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
-}
-
-static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
-{
-	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
-	free_page((unsigned long)pmd);
-}
-
-extern void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
-
-#ifdef CONFIG_X86_PAE
-extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
-#else	/* !CONFIG_X86_PAE */
-static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
-{
-	paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
-	set_pud(pud, __pud(_PAGE_TABLE | __pa(pmd)));
-}
-#endif	/* CONFIG_X86_PAE */
-
-#if PAGETABLE_LEVELS > 3
-static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pud_t *pud)
-{
-	paravirt_alloc_pud(mm, __pa(pud) >> PAGE_SHIFT);
-	set_pgd(pgd, __pgd(_PAGE_TABLE | __pa(pud)));
-}
-
-static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
-	return (pud_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
-}
-
-static inline void pud_free(struct mm_struct *mm, pud_t *pud)
-{
-	BUG_ON((unsigned long)pud & (PAGE_SIZE-1));
-	free_page((unsigned long)pud);
-}
-
-extern void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud);
-#endif	/* PAGETABLE_LEVELS > 3 */
-#endif	/* PAGETABLE_LEVELS > 2 */
-
-#endif /* ASM_X86__PGALLOC_H */
diff --git a/include/asm-x86/pgtable-2level-defs.h b/include/asm-x86/pgtable-2level-defs.h
deleted file mode 100644
index 7ec48f4e5347..000000000000
--- a/include/asm-x86/pgtable-2level-defs.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef ASM_X86__PGTABLE_2LEVEL_DEFS_H
-#define ASM_X86__PGTABLE_2LEVEL_DEFS_H
-
-#define SHARED_KERNEL_PMD	0
-
-/*
- * traditional i386 two-level paging structure:
- */
-
-#define PGDIR_SHIFT	22
-#define PTRS_PER_PGD	1024
-
-/*
- * the i386 is two-level, so we don't really have any
- * PMD directory physically.
- */
-
-#define PTRS_PER_PTE	1024
-
-#endif /* ASM_X86__PGTABLE_2LEVEL_DEFS_H */
diff --git a/include/asm-x86/pgtable-2level.h b/include/asm-x86/pgtable-2level.h
deleted file mode 100644
index 81762081dcd8..000000000000
--- a/include/asm-x86/pgtable-2level.h
+++ /dev/null
@@ -1,79 +0,0 @@
-#ifndef ASM_X86__PGTABLE_2LEVEL_H
-#define ASM_X86__PGTABLE_2LEVEL_H
-
-#define pte_ERROR(e) \
-	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
-#define pgd_ERROR(e) \
-	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
-
-/*
- * Certain architectures need to do special things when PTEs
- * within a page table are directly modified.  Thus, the following
- * hook is made available.
- */
-static inline void native_set_pte(pte_t *ptep , pte_t pte)
-{
-	*ptep = pte;
-}
-
-static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
-{
-	*pmdp = pmd;
-}
-
-static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	native_set_pte(ptep, pte);
-}
-
-static inline void native_set_pte_present(struct mm_struct *mm,
-					  unsigned long addr,
-					  pte_t *ptep, pte_t pte)
-{
-	native_set_pte(ptep, pte);
-}
-
-static inline void native_pmd_clear(pmd_t *pmdp)
-{
-	native_set_pmd(pmdp, __pmd(0));
-}
-
-static inline void native_pte_clear(struct mm_struct *mm,
-				    unsigned long addr, pte_t *xp)
-{
-	*xp = native_make_pte(0);
-}
-
-#ifdef CONFIG_SMP
-static inline pte_t native_ptep_get_and_clear(pte_t *xp)
-{
-	return __pte(xchg(&xp->pte_low, 0));
-}
-#else
-#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
-#endif
-
-#define pte_none(x)		(!(x).pte_low)
-
-/*
- * Bits 0, 6 and 7 are taken, split up the 29 bits of offset
- * into this range:
- */
-#define PTE_FILE_MAX_BITS	29
-
-#define pte_to_pgoff(pte)						\
-	((((pte).pte_low >> 1) & 0x1f) + (((pte).pte_low >> 8) << 5))
-
-#define pgoff_to_pte(off)						\
-	((pte_t) { .pte_low = (((off) & 0x1f) << 1) +			\
-			(((off) >> 5) << 8) + _PAGE_FILE })
-
-/* Encode and de-code a swap entry */
-#define __swp_type(x)			(((x).val >> 1) & 0x1f)
-#define __swp_offset(x)			((x).val >> 8)
-#define __swp_entry(type, offset)				\
-	((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
-#define __pte_to_swp_entry(pte)		((swp_entry_t) { (pte).pte_low })
-#define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
-
-#endif /* ASM_X86__PGTABLE_2LEVEL_H */
diff --git a/include/asm-x86/pgtable-3level-defs.h b/include/asm-x86/pgtable-3level-defs.h
deleted file mode 100644
index c05fe6ff3720..000000000000
--- a/include/asm-x86/pgtable-3level-defs.h
+++ /dev/null
@@ -1,28 +0,0 @@
-#ifndef ASM_X86__PGTABLE_3LEVEL_DEFS_H
-#define ASM_X86__PGTABLE_3LEVEL_DEFS_H
-
-#ifdef CONFIG_PARAVIRT
-#define SHARED_KERNEL_PMD	(pv_info.shared_kernel_pmd)
-#else
-#define SHARED_KERNEL_PMD	1
-#endif
-
-/*
- * PGDIR_SHIFT determines what a top-level page table entry can map
- */
-#define PGDIR_SHIFT	30
-#define PTRS_PER_PGD	4
-
-/*
- * PMD_SHIFT determines the size of the area a middle-level
- * page table can map
- */
-#define PMD_SHIFT	21
-#define PTRS_PER_PMD	512
-
-/*
- * entries per page directory level
- */
-#define PTRS_PER_PTE	512
-
-#endif /* ASM_X86__PGTABLE_3LEVEL_DEFS_H */
diff --git a/include/asm-x86/pgtable-3level.h b/include/asm-x86/pgtable-3level.h
deleted file mode 100644
index 75f4276b5ddb..000000000000
--- a/include/asm-x86/pgtable-3level.h
+++ /dev/null
@@ -1,175 +0,0 @@
-#ifndef ASM_X86__PGTABLE_3LEVEL_H
-#define ASM_X86__PGTABLE_3LEVEL_H
-
-/*
- * Intel Physical Address Extension (PAE) Mode - three-level page
- * tables on PPro+ CPUs.
- *
- * Copyright (C) 1999 Ingo Molnar <mingo@redhat.com>
- */
-
-#define pte_ERROR(e)							\
-	printk("%s:%d: bad pte %p(%08lx%08lx).\n",			\
-	       __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
-#define pmd_ERROR(e)							\
-	printk("%s:%d: bad pmd %p(%016Lx).\n",				\
-	       __FILE__, __LINE__, &(e), pmd_val(e))
-#define pgd_ERROR(e)							\
-	printk("%s:%d: bad pgd %p(%016Lx).\n",				\
-	       __FILE__, __LINE__, &(e), pgd_val(e))
-
-static inline int pud_none(pud_t pud)
-{
-	return pud_val(pud) == 0;
-}
-
-static inline int pud_bad(pud_t pud)
-{
-	return (pud_val(pud) & ~(PTE_PFN_MASK | _KERNPG_TABLE | _PAGE_USER)) != 0;
-}
-
-static inline int pud_present(pud_t pud)
-{
-	return pud_val(pud) & _PAGE_PRESENT;
-}
-
-/* Rules for using set_pte: the pte being assigned *must* be
- * either not present or in a state where the hardware will
- * not attempt to update the pte.  In places where this is
- * not possible, use pte_get_and_clear to obtain the old pte
- * value and then use set_pte to update it.  -ben
- */
-static inline void native_set_pte(pte_t *ptep, pte_t pte)
-{
-	ptep->pte_high = pte.pte_high;
-	smp_wmb();
-	ptep->pte_low = pte.pte_low;
-}
-
-/*
- * Since this is only called on user PTEs, and the page fault handler
- * must handle the already racy situation of simultaneous page faults,
- * we are justified in merely clearing the PTE present bit, followed
- * by a set.  The ordering here is important.
- */
-static inline void native_set_pte_present(struct mm_struct *mm,
-					  unsigned long addr,
-					  pte_t *ptep, pte_t pte)
-{
-	ptep->pte_low = 0;
-	smp_wmb();
-	ptep->pte_high = pte.pte_high;
-	smp_wmb();
-	ptep->pte_low = pte.pte_low;
-}
-
-static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	set_64bit((unsigned long long *)(ptep), native_pte_val(pte));
-}
-
-static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
-{
-	set_64bit((unsigned long long *)(pmdp), native_pmd_val(pmd));
-}
-
-static inline void native_set_pud(pud_t *pudp, pud_t pud)
-{
-	set_64bit((unsigned long long *)(pudp), native_pud_val(pud));
-}
-
-/*
- * For PTEs and PDEs, we must clear the P-bit first when clearing a page table
- * entry, so clear the bottom half first and enforce ordering with a compiler
- * barrier.
- */
-static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
-				    pte_t *ptep)
-{
-	ptep->pte_low = 0;
-	smp_wmb();
-	ptep->pte_high = 0;
-}
-
-static inline void native_pmd_clear(pmd_t *pmd)
-{
-	u32 *tmp = (u32 *)pmd;
-	*tmp = 0;
-	smp_wmb();
-	*(tmp + 1) = 0;
-}
-
-static inline void pud_clear(pud_t *pudp)
-{
-	unsigned long pgd;
-
-	set_pud(pudp, __pud(0));
-
-	/*
-	 * According to Intel App note "TLBs, Paging-Structure Caches,
-	 * and Their Invalidation", April 2007, document 317080-001,
-	 * section 8.1: in PAE mode we explicitly have to flush the
-	 * TLB via cr3 if the top-level pgd is changed...
-	 *
-	 * Make sure the pud entry we're updating is within the
-	 * current pgd to avoid unnecessary TLB flushes.
-	 */
-	pgd = read_cr3();
-	if (__pa(pudp) >= pgd && __pa(pudp) <
-	    (pgd + sizeof(pgd_t)*PTRS_PER_PGD))
-		write_cr3(pgd);
-}
-
-#define pud_page(pud) ((struct page *) __va(pud_val(pud) & PTE_PFN_MASK))
-
-#define pud_page_vaddr(pud) ((unsigned long) __va(pud_val(pud) & PTE_PFN_MASK))
-
-
-/* Find an entry in the second-level page table.. */
-#define pmd_offset(pud, address) ((pmd_t *)pud_page(*(pud)) +	\
-				  pmd_index(address))
-
-#ifdef CONFIG_SMP
-static inline pte_t native_ptep_get_and_clear(pte_t *ptep)
-{
-	pte_t res;
-
-	/* xchg acts as a barrier before the setting of the high bits */
-	res.pte_low = xchg(&ptep->pte_low, 0);
-	res.pte_high = ptep->pte_high;
-	ptep->pte_high = 0;
-
-	return res;
-}
-#else
-#define native_ptep_get_and_clear(xp) native_local_ptep_get_and_clear(xp)
-#endif
-
-#define __HAVE_ARCH_PTE_SAME
-static inline int pte_same(pte_t a, pte_t b)
-{
-	return a.pte_low == b.pte_low && a.pte_high == b.pte_high;
-}
-
-static inline int pte_none(pte_t pte)
-{
-	return !pte.pte_low && !pte.pte_high;
-}
-
-/*
- * Bits 0, 6 and 7 are taken in the low part of the pte,
- * put the 32 bits of offset into the high part.
- */
-#define pte_to_pgoff(pte) ((pte).pte_high)
-#define pgoff_to_pte(off)						\
-	((pte_t) { { .pte_low = _PAGE_FILE, .pte_high = (off) } })
-#define PTE_FILE_MAX_BITS       32
-
-/* Encode and de-code a swap entry */
-#define __swp_type(x)			(((x).val) & 0x1f)
-#define __swp_offset(x)			((x).val >> 5)
-#define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) << 5})
-#define __pte_to_swp_entry(pte)		((swp_entry_t){ (pte).pte_high })
-#define __swp_entry_to_pte(x)		((pte_t){ { .pte_high = (x).val } })
-
-#endif /* ASM_X86__PGTABLE_3LEVEL_H */
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
deleted file mode 100644
index 88a53b1a17f0..000000000000
--- a/include/asm-x86/pgtable.h
+++ /dev/null
@@ -1,561 +0,0 @@
-#ifndef ASM_X86__PGTABLE_H
-#define ASM_X86__PGTABLE_H
-
-#define FIRST_USER_ADDRESS	0
-
-#define _PAGE_BIT_PRESENT	0	/* is present */
-#define _PAGE_BIT_RW		1	/* writeable */
-#define _PAGE_BIT_USER		2	/* userspace addressable */
-#define _PAGE_BIT_PWT		3	/* page write through */
-#define _PAGE_BIT_PCD		4	/* page cache disabled */
-#define _PAGE_BIT_ACCESSED	5	/* was accessed (raised by CPU) */
-#define _PAGE_BIT_DIRTY		6	/* was written to (raised by CPU) */
-#define _PAGE_BIT_FILE		6
-#define _PAGE_BIT_PSE		7	/* 4 MB (or 2MB) page */
-#define _PAGE_BIT_PAT		7	/* on 4KB pages */
-#define _PAGE_BIT_GLOBAL	8	/* Global TLB entry PPro+ */
-#define _PAGE_BIT_UNUSED1	9	/* available for programmer */
-#define _PAGE_BIT_IOMAP		10	/* flag used to indicate IO mapping */
-#define _PAGE_BIT_UNUSED3	11
-#define _PAGE_BIT_PAT_LARGE	12	/* On 2MB or 1GB pages */
-#define _PAGE_BIT_SPECIAL	_PAGE_BIT_UNUSED1
-#define _PAGE_BIT_CPA_TEST	_PAGE_BIT_UNUSED1
-#define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
-
-#define _PAGE_PRESENT	(_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
-#define _PAGE_RW	(_AT(pteval_t, 1) << _PAGE_BIT_RW)
-#define _PAGE_USER	(_AT(pteval_t, 1) << _PAGE_BIT_USER)
-#define _PAGE_PWT	(_AT(pteval_t, 1) << _PAGE_BIT_PWT)
-#define _PAGE_PCD	(_AT(pteval_t, 1) << _PAGE_BIT_PCD)
-#define _PAGE_ACCESSED	(_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
-#define _PAGE_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
-#define _PAGE_PSE	(_AT(pteval_t, 1) << _PAGE_BIT_PSE)
-#define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
-#define _PAGE_UNUSED1	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
-#define _PAGE_IOMAP	(_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
-#define _PAGE_UNUSED3	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
-#define _PAGE_PAT	(_AT(pteval_t, 1) << _PAGE_BIT_PAT)
-#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
-#define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
-#define _PAGE_CPA_TEST	(_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
-#define __HAVE_ARCH_PTE_SPECIAL
-
-#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-#define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
-#else
-#define _PAGE_NX	(_AT(pteval_t, 0))
-#endif
-
-/* If _PAGE_PRESENT is clear, we use these: */
-#define _PAGE_FILE	_PAGE_DIRTY	/* nonlinear file mapping,
-					 * saved PTE; unset:swap */
-#define _PAGE_PROTNONE	_PAGE_PSE	/* if the user mapped it with PROT_NONE;
-					   pte_present gives true */
-
-#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |	\
-			 _PAGE_ACCESSED | _PAGE_DIRTY)
-#define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |	\
-			 _PAGE_DIRTY)
-
-/* Set of bits not changed in pte_modify */
-#define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
-			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)
-
-#define _PAGE_CACHE_MASK	(_PAGE_PCD | _PAGE_PWT)
-#define _PAGE_CACHE_WB		(0)
-#define _PAGE_CACHE_WC		(_PAGE_PWT)
-#define _PAGE_CACHE_UC_MINUS	(_PAGE_PCD)
-#define _PAGE_CACHE_UC		(_PAGE_PCD | _PAGE_PWT)
-
-#define PAGE_NONE	__pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
-#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
-				 _PAGE_ACCESSED | _PAGE_NX)
-
-#define PAGE_SHARED_EXEC	__pgprot(_PAGE_PRESENT | _PAGE_RW |	\
-					 _PAGE_USER | _PAGE_ACCESSED)
-#define PAGE_COPY_NOEXEC	__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
-					 _PAGE_ACCESSED | _PAGE_NX)
-#define PAGE_COPY_EXEC		__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
-					 _PAGE_ACCESSED)
-#define PAGE_COPY		PAGE_COPY_NOEXEC
-#define PAGE_READONLY		__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
-					 _PAGE_ACCESSED | _PAGE_NX)
-#define PAGE_READONLY_EXEC	__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
-					 _PAGE_ACCESSED)
-
-#define __PAGE_KERNEL_EXEC						\
-	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
-#define __PAGE_KERNEL		(__PAGE_KERNEL_EXEC | _PAGE_NX)
-
-#define __PAGE_KERNEL_RO		(__PAGE_KERNEL & ~_PAGE_RW)
-#define __PAGE_KERNEL_RX		(__PAGE_KERNEL_EXEC & ~_PAGE_RW)
-#define __PAGE_KERNEL_EXEC_NOCACHE	(__PAGE_KERNEL_EXEC | _PAGE_PCD | _PAGE_PWT)
-#define __PAGE_KERNEL_WC		(__PAGE_KERNEL | _PAGE_CACHE_WC)
-#define __PAGE_KERNEL_NOCACHE		(__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
-#define __PAGE_KERNEL_UC_MINUS		(__PAGE_KERNEL | _PAGE_PCD)
-#define __PAGE_KERNEL_VSYSCALL		(__PAGE_KERNEL_RX | _PAGE_USER)
-#define __PAGE_KERNEL_VSYSCALL_NOCACHE	(__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
-#define __PAGE_KERNEL_LARGE		(__PAGE_KERNEL | _PAGE_PSE)
-#define __PAGE_KERNEL_LARGE_NOCACHE	(__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
-#define __PAGE_KERNEL_LARGE_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)
-
-#define __PAGE_KERNEL_IO		(__PAGE_KERNEL | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_NOCACHE	(__PAGE_KERNEL_NOCACHE | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_UC_MINUS	(__PAGE_KERNEL_UC_MINUS | _PAGE_IOMAP)
-#define __PAGE_KERNEL_IO_WC		(__PAGE_KERNEL_WC | _PAGE_IOMAP)
-
-#define PAGE_KERNEL			__pgprot(__PAGE_KERNEL)
-#define PAGE_KERNEL_RO			__pgprot(__PAGE_KERNEL_RO)
-#define PAGE_KERNEL_EXEC		__pgprot(__PAGE_KERNEL_EXEC)
-#define PAGE_KERNEL_RX			__pgprot(__PAGE_KERNEL_RX)
-#define PAGE_KERNEL_WC			__pgprot(__PAGE_KERNEL_WC)
-#define PAGE_KERNEL_NOCACHE		__pgprot(__PAGE_KERNEL_NOCACHE)
-#define PAGE_KERNEL_UC_MINUS		__pgprot(__PAGE_KERNEL_UC_MINUS)
-#define PAGE_KERNEL_EXEC_NOCACHE	__pgprot(__PAGE_KERNEL_EXEC_NOCACHE)
-#define PAGE_KERNEL_LARGE		__pgprot(__PAGE_KERNEL_LARGE)
-#define PAGE_KERNEL_LARGE_NOCACHE	__pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
-#define PAGE_KERNEL_LARGE_EXEC		__pgprot(__PAGE_KERNEL_LARGE_EXEC)
-#define PAGE_KERNEL_VSYSCALL		__pgprot(__PAGE_KERNEL_VSYSCALL)
-#define PAGE_KERNEL_VSYSCALL_NOCACHE	__pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
-
-#define PAGE_KERNEL_IO			__pgprot(__PAGE_KERNEL_IO)
-#define PAGE_KERNEL_IO_NOCACHE		__pgprot(__PAGE_KERNEL_IO_NOCACHE)
-#define PAGE_KERNEL_IO_UC_MINUS		__pgprot(__PAGE_KERNEL_IO_UC_MINUS)
-#define PAGE_KERNEL_IO_WC		__pgprot(__PAGE_KERNEL_IO_WC)
-
-/*         xwr */
-#define __P000	PAGE_NONE
-#define __P001	PAGE_READONLY
-#define __P010	PAGE_COPY
-#define __P011	PAGE_COPY
-#define __P100	PAGE_READONLY_EXEC
-#define __P101	PAGE_READONLY_EXEC
-#define __P110	PAGE_COPY_EXEC
-#define __P111	PAGE_COPY_EXEC
-
-#define __S000	PAGE_NONE
-#define __S001	PAGE_READONLY
-#define __S010	PAGE_SHARED
-#define __S011	PAGE_SHARED
-#define __S100	PAGE_READONLY_EXEC
-#define __S101	PAGE_READONLY_EXEC
-#define __S110	PAGE_SHARED_EXEC
-#define __S111	PAGE_SHARED_EXEC
-
-/*
- * early identity mapping  pte attrib macros.
- */
-#ifdef CONFIG_X86_64
-#define __PAGE_KERNEL_IDENT_LARGE_EXEC	__PAGE_KERNEL_LARGE_EXEC
-#else
-/*
- * For PDE_IDENT_ATTR include USER bit. As the PDE and PTE protection
- * bits are combined, this will alow user to access the high address mapped
- * VDSO in the presence of CONFIG_COMPAT_VDSO
- */
-#define PTE_IDENT_ATTR	 0x003		/* PRESENT+RW */
-#define PDE_IDENT_ATTR	 0x067		/* PRESENT+RW+USER+DIRTY+ACCESSED */
-#define PGD_IDENT_ATTR	 0x001		/* PRESENT (no other attributes) */
-#endif
-
-#ifndef __ASSEMBLY__
-
-/*
- * ZERO_PAGE is a global shared page that is always zero: used
- * for zero-mapped memory areas etc..
- */
-extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
-#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
-
-extern spinlock_t pgd_lock;
-extern struct list_head pgd_list;
-
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
-static inline int pte_dirty(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_DIRTY;
-}
-
-static inline int pte_young(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_ACCESSED;
-}
-
-static inline int pte_write(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_RW;
-}
-
-static inline int pte_file(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_FILE;
-}
-
-static inline int pte_huge(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_PSE;
-}
-
-static inline int pte_global(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_GLOBAL;
-}
-
-static inline int pte_exec(pte_t pte)
-{
-	return !(pte_flags(pte) & _PAGE_NX);
-}
-
-static inline int pte_special(pte_t pte)
-{
-	return pte_flags(pte) & _PAGE_SPECIAL;
-}
-
-static inline unsigned long pte_pfn(pte_t pte)
-{
-	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
-}
-
-#define pte_page(pte)	pfn_to_page(pte_pfn(pte))
-
-static inline int pmd_large(pmd_t pte)
-{
-	return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
-		(_PAGE_PSE | _PAGE_PRESENT);
-}
-
-static inline pte_t pte_mkclean(pte_t pte)
-{
-	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
-}
-
-static inline pte_t pte_mkold(pte_t pte)
-{
-	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
-}
-
-static inline pte_t pte_wrprotect(pte_t pte)
-{
-	return __pte(pte_val(pte) & ~_PAGE_RW);
-}
-
-static inline pte_t pte_mkexec(pte_t pte)
-{
-	return __pte(pte_val(pte) & ~_PAGE_NX);
-}
-
-static inline pte_t pte_mkdirty(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_DIRTY);
-}
-
-static inline pte_t pte_mkyoung(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_ACCESSED);
-}
-
-static inline pte_t pte_mkwrite(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_RW);
-}
-
-static inline pte_t pte_mkhuge(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_PSE);
-}
-
-static inline pte_t pte_clrhuge(pte_t pte)
-{
-	return __pte(pte_val(pte) & ~_PAGE_PSE);
-}
-
-static inline pte_t pte_mkglobal(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_GLOBAL);
-}
-
-static inline pte_t pte_clrglobal(pte_t pte)
-{
-	return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
-}
-
-static inline pte_t pte_mkspecial(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_SPECIAL);
-}
-
-extern pteval_t __supported_pte_mask;
-
-static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
-{
-	return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) |
-		      pgprot_val(pgprot)) & __supported_pte_mask);
-}
-
-static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
-{
-	return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) |
-		      pgprot_val(pgprot)) & __supported_pte_mask);
-}
-
-static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
-{
-	pteval_t val = pte_val(pte);
-
-	/*
-	 * Chop off the NX bit (if present), and add the NX portion of
-	 * the newprot (if present):
-	 */
-	val &= _PAGE_CHG_MASK;
-	val |= pgprot_val(newprot) & (~_PAGE_CHG_MASK) & __supported_pte_mask;
-
-	return __pte(val);
-}
-
-/* mprotect needs to preserve PAT bits when updating vm_page_prot */
-#define pgprot_modify pgprot_modify
-static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
-{
-	pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK;
-	pgprotval_t addbits = pgprot_val(newprot);
-	return __pgprot(preservebits | addbits);
-}
-
-#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)
-
-#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
-
-#ifndef __ASSEMBLY__
-#define __HAVE_PHYS_MEM_ACCESS_PROT
-struct file;
-pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
-                              unsigned long size, pgprot_t vma_prot);
-int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
-                              unsigned long size, pgprot_t *vma_prot);
-#endif
-
-/* Install a pte for a particular vaddr in kernel space. */
-void set_pte_vaddr(unsigned long vaddr, pte_t pte);
-
-#ifdef CONFIG_X86_32
-extern void native_pagetable_setup_start(pgd_t *base);
-extern void native_pagetable_setup_done(pgd_t *base);
-#else
-static inline void native_pagetable_setup_start(pgd_t *base) {}
-static inline void native_pagetable_setup_done(pgd_t *base) {}
-#endif
-
-extern int arch_report_meminfo(char *page);
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else  /* !CONFIG_PARAVIRT */
-#define set_pte(ptep, pte)		native_set_pte(ptep, pte)
-#define set_pte_at(mm, addr, ptep, pte)	native_set_pte_at(mm, addr, ptep, pte)
-
-#define set_pte_present(mm, addr, ptep, pte)				\
-	native_set_pte_present(mm, addr, ptep, pte)
-#define set_pte_atomic(ptep, pte)					\
-	native_set_pte_atomic(ptep, pte)
-
-#define set_pmd(pmdp, pmd)		native_set_pmd(pmdp, pmd)
-
-#ifndef __PAGETABLE_PUD_FOLDED
-#define set_pgd(pgdp, pgd)		native_set_pgd(pgdp, pgd)
-#define pgd_clear(pgd)			native_pgd_clear(pgd)
-#endif
-
-#ifndef set_pud
-# define set_pud(pudp, pud)		native_set_pud(pudp, pud)
-#endif
-
-#ifndef __PAGETABLE_PMD_FOLDED
-#define pud_clear(pud)			native_pud_clear(pud)
-#endif
-
-#define pte_clear(mm, addr, ptep)	native_pte_clear(mm, addr, ptep)
-#define pmd_clear(pmd)			native_pmd_clear(pmd)
-
-#define pte_update(mm, addr, ptep)              do { } while (0)
-#define pte_update_defer(mm, addr, ptep)        do { } while (0)
-
-static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
-{
-	native_pagetable_setup_start(base);
-}
-
-static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
-{
-	native_pagetable_setup_done(base);
-}
-#endif	/* CONFIG_PARAVIRT */
-
-#endif	/* __ASSEMBLY__ */
-
-#ifdef CONFIG_X86_32
-# include "pgtable_32.h"
-#else
-# include "pgtable_64.h"
-#endif
-
-/*
- * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
- *
- * this macro returns the index of the entry in the pgd page which would
- * control the given virtual address
- */
-#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
-
-/*
- * pgd_offset() returns a (pgd_t *)
- * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
- */
-#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
-/*
- * a shortcut which implies the use of the kernel's pgd, instead
- * of a process's
- */
-#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
-
-
-#define KERNEL_PGD_BOUNDARY	pgd_index(PAGE_OFFSET)
-#define KERNEL_PGD_PTRS		(PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
-
-#ifndef __ASSEMBLY__
-
-enum {
-	PG_LEVEL_NONE,
-	PG_LEVEL_4K,
-	PG_LEVEL_2M,
-	PG_LEVEL_1G,
-	PG_LEVEL_NUM
-};
-
-#ifdef CONFIG_PROC_FS
-extern void update_page_count(int level, unsigned long pages);
-#else
-static inline void update_page_count(int level, unsigned long pages) { }
-#endif
-
-/*
- * Helper function that returns the kernel pagetable entry controlling
- * the virtual address 'address'. NULL means no pagetable entry present.
- * NOTE: the return type is pte_t but if the pmd is PSE then we return it
- * as a pte too.
- */
-extern pte_t *lookup_address(unsigned long address, unsigned int *level);
-
-/* local pte updates need not use xchg for locking */
-static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
-{
-	pte_t res = *ptep;
-
-	/* Pure native function needs no input for mm, addr */
-	native_pte_clear(NULL, 0, ptep);
-	return res;
-}
-
-static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
-				     pte_t *ptep , pte_t pte)
-{
-	native_set_pte(ptep, pte);
-}
-
-#ifndef CONFIG_PARAVIRT
-/*
- * Rules for using pte_update - it must be called after any PTE update which
- * has not been done using the set_pte / clear_pte interfaces.  It is used by
- * shadow mode hypervisors to resynchronize the shadow page tables.  Kernel PTE
- * updates should either be sets, clears, or set_pte_atomic for P->P
- * transitions, which means this hook should only be called for user PTEs.
- * This hook implies a P->P protection or access change has taken place, which
- * requires a subsequent TLB flush.  The notification can optionally be delayed
- * until the TLB flush event by using the pte_update_defer form of the
- * interface, but care must be taken to assure that the flush happens while
- * still holding the same page table lock so that the shadow and primary pages
- * do not become out of sync on SMP.
- */
-#define pte_update(mm, addr, ptep)		do { } while (0)
-#define pte_update_defer(mm, addr, ptep)	do { } while (0)
-#endif
-
-/*
- * We only update the dirty/accessed state if we set
- * the dirty bit by hand in the kernel, since the hardware
- * will do the accessed bit for us, and we don't want to
- * race with other CPU's that might be updating the dirty
- * bit at the same time.
- */
-struct vm_area_struct;
-
-#define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
-extern int ptep_set_access_flags(struct vm_area_struct *vma,
-				 unsigned long address, pte_t *ptep,
-				 pte_t entry, int dirty);
-
-#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
-extern int ptep_test_and_clear_young(struct vm_area_struct *vma,
-				     unsigned long addr, pte_t *ptep);
-
-#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
-extern int ptep_clear_flush_young(struct vm_area_struct *vma,
-				  unsigned long address, pte_t *ptep);
-
-#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
-static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-				       pte_t *ptep)
-{
-	pte_t pte = native_ptep_get_and_clear(ptep);
-	pte_update(mm, addr, ptep);
-	return pte;
-}
-
-#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
-static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep,
-					    int full)
-{
-	pte_t pte;
-	if (full) {
-		/*
-		 * Full address destruction in progress; paravirt does not
-		 * care about updates and native needs no locking
-		 */
-		pte = native_local_ptep_get_and_clear(ptep);
-	} else {
-		pte = ptep_get_and_clear(mm, addr, ptep);
-	}
-	return pte;
-}
-
-#define __HAVE_ARCH_PTEP_SET_WRPROTECT
-static inline void ptep_set_wrprotect(struct mm_struct *mm,
-				      unsigned long addr, pte_t *ptep)
-{
-	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
-	pte_update(mm, addr, ptep);
-}
-
-/*
- * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
- *
- *  dst - pointer to pgd range anwhere on a pgd page
- *  src - ""
- *  count - the number of pgds to copy.
- *
- * dst and src can be on the same page, but the range must not overlap,
- * and must not cross a page boundary.
- */
-static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
-{
-       memcpy(dst, src, count * sizeof(pgd_t));
-}
-
-
-#include <asm-generic/pgtable.h>
-#endif	/* __ASSEMBLY__ */
-
-#endif /* ASM_X86__PGTABLE_H */
diff --git a/include/asm-x86/pgtable_32.h b/include/asm-x86/pgtable_32.h
deleted file mode 100644
index 8de702dc7d62..000000000000
--- a/include/asm-x86/pgtable_32.h
+++ /dev/null
@@ -1,191 +0,0 @@
-#ifndef ASM_X86__PGTABLE_32_H
-#define ASM_X86__PGTABLE_32_H
-
-
-/*
- * The Linux memory management assumes a three-level page table setup. On
- * the i386, we use that, but "fold" the mid level into the top-level page
- * table, so that we physically have the same two-level page table as the
- * i386 mmu expects.
- *
- * This file contains the functions and defines necessary to modify and use
- * the i386 page table tree.
- */
-#ifndef __ASSEMBLY__
-#include <asm/processor.h>
-#include <asm/fixmap.h>
-#include <linux/threads.h>
-#include <asm/paravirt.h>
-
-#include <linux/bitops.h>
-#include <linux/slab.h>
-#include <linux/list.h>
-#include <linux/spinlock.h>
-
-struct mm_struct;
-struct vm_area_struct;
-
-extern pgd_t swapper_pg_dir[1024];
-
-static inline void pgtable_cache_init(void) { }
-static inline void check_pgt_cache(void) { }
-void paging_init(void);
-
-extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
-
-/*
- * The Linux x86 paging architecture is 'compile-time dual-mode', it
- * implements both the traditional 2-level x86 page tables and the
- * newer 3-level PAE-mode page tables.
- */
-#ifdef CONFIG_X86_PAE
-# include <asm/pgtable-3level-defs.h>
-# define PMD_SIZE	(1UL << PMD_SHIFT)
-# define PMD_MASK	(~(PMD_SIZE - 1))
-#else
-# include <asm/pgtable-2level-defs.h>
-#endif
-
-#define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
-#define PGDIR_MASK	(~(PGDIR_SIZE - 1))
-
-/* Just any arbitrary offset to the start of the vmalloc VM area: the
- * current 8MB value just means that there will be a 8MB "hole" after the
- * physical memory until the kernel virtual memory starts.  That means that
- * any out-of-bounds memory accesses will hopefully be caught.
- * The vmalloc() routines leaves a hole of 4kB between each vmalloced
- * area for the same reason. ;)
- */
-#define VMALLOC_OFFSET	(8 * 1024 * 1024)
-#define VMALLOC_START	((unsigned long)high_memory + VMALLOC_OFFSET)
-#ifdef CONFIG_X86_PAE
-#define LAST_PKMAP 512
-#else
-#define LAST_PKMAP 1024
-#endif
-
-#define PKMAP_BASE ((FIXADDR_BOOT_START - PAGE_SIZE * (LAST_PKMAP + 1))	\
-		    & PMD_MASK)
-
-#ifdef CONFIG_HIGHMEM
-# define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
-#else
-# define VMALLOC_END	(FIXADDR_START - 2 * PAGE_SIZE)
-#endif
-
-#define MAXMEM	(VMALLOC_END - PAGE_OFFSET - __VMALLOC_RESERVE)
-
-/*
- * Define this if things work differently on an i386 and an i486:
- * it will (on an i486) warn about kernel memory accesses that are
- * done without a 'access_ok(VERIFY_WRITE,..)'
- */
-#undef TEST_ACCESS_OK
-
-/* The boot page tables (all created as a single array) */
-extern unsigned long pg0[];
-
-#define pte_present(x)	((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
-
-/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
-#define pmd_none(x)	(!(unsigned long)pmd_val((x)))
-#define pmd_present(x)	(pmd_val((x)) & _PAGE_PRESENT)
-#define pmd_bad(x) ((pmd_val(x) & (PTE_FLAGS_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
-
-#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
-
-#ifdef CONFIG_X86_PAE
-# include <asm/pgtable-3level.h>
-#else
-# include <asm/pgtable-2level.h>
-#endif
-
-/*
- * Macro to mark a page protection value as "uncacheable".
- * On processors which do not support it, this is a no-op.
- */
-#define pgprot_noncached(prot)					\
-	((boot_cpu_data.x86 > 3)				\
-	 ? (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT))	\
-	 : (prot))
-
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn(page), (pgprot))
-
-
-static inline int pud_large(pud_t pud) { return 0; }
-
-/*
- * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
- *
- * this macro returns the index of the entry in the pmd page which would
- * control the given virtual address
- */
-#define pmd_index(address)				\
-	(((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
-
-/*
- * the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
- *
- * this macro returns the index of the entry in the pte page which would
- * control the given virtual address
- */
-#define pte_index(address)					\
-	(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_kernel(dir, address)				\
-	((pte_t *)pmd_page_vaddr(*(dir)) +  pte_index((address)))
-
-#define pmd_page(pmd) (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
-
-#define pmd_page_vaddr(pmd)					\
-	((unsigned long)__va(pmd_val((pmd)) & PTE_PFN_MASK))
-
-#if defined(CONFIG_HIGHPTE)
-#define pte_offset_map(dir, address)					\
-	((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE0) +		\
-	 pte_index((address)))
-#define pte_offset_map_nested(dir, address)				\
-	((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE1) +		\
-	 pte_index((address)))
-#define pte_unmap(pte) kunmap_atomic((pte), KM_PTE0)
-#define pte_unmap_nested(pte) kunmap_atomic((pte), KM_PTE1)
-#else
-#define pte_offset_map(dir, address)					\
-	((pte_t *)page_address(pmd_page(*(dir))) + pte_index((address)))
-#define pte_offset_map_nested(dir, address) pte_offset_map((dir), (address))
-#define pte_unmap(pte) do { } while (0)
-#define pte_unmap_nested(pte) do { } while (0)
-#endif
-
-/* Clear a kernel PTE and flush it from the TLB */
-#define kpte_clear_flush(ptep, vaddr)		\
-do {						\
-	pte_clear(&init_mm, (vaddr), (ptep));	\
-	__flush_tlb_one((vaddr));		\
-} while (0)
-
-/*
- * The i386 doesn't have any external MMU info: the kernel page
- * tables contain all the necessary information.
- */
-#define update_mmu_cache(vma, address, pte) do { } while (0)
-
-#endif /* !__ASSEMBLY__ */
-
-/*
- * kern_addr_valid() is (1) for FLATMEM and (0) for
- * SPARSEMEM and DISCONTIGMEM
- */
-#ifdef CONFIG_FLATMEM
-#define kern_addr_valid(addr)	(1)
-#else
-#define kern_addr_valid(kaddr)	(0)
-#endif
-
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)	\
-	remap_pfn_range(vma, vaddr, pfn, size, prot)
-
-#endif /* ASM_X86__PGTABLE_32_H */
diff --git a/include/asm-x86/pgtable_64.h b/include/asm-x86/pgtable_64.h
deleted file mode 100644
index fde9770e53d1..000000000000
--- a/include/asm-x86/pgtable_64.h
+++ /dev/null
@@ -1,285 +0,0 @@
-#ifndef ASM_X86__PGTABLE_64_H
-#define ASM_X86__PGTABLE_64_H
-
-#include <linux/const.h>
-#ifndef __ASSEMBLY__
-
-/*
- * This file contains the functions and defines necessary to modify and use
- * the x86-64 page table tree.
- */
-#include <asm/processor.h>
-#include <linux/bitops.h>
-#include <linux/threads.h>
-#include <asm/pda.h>
-
-extern pud_t level3_kernel_pgt[512];
-extern pud_t level3_ident_pgt[512];
-extern pmd_t level2_kernel_pgt[512];
-extern pmd_t level2_fixmap_pgt[512];
-extern pmd_t level2_ident_pgt[512];
-extern pgd_t init_level4_pgt[];
-
-#define swapper_pg_dir init_level4_pgt
-
-extern void paging_init(void);
-
-#endif /* !__ASSEMBLY__ */
-
-#define SHARED_KERNEL_PMD	0
-
-/*
- * PGDIR_SHIFT determines what a top-level page table entry can map
- */
-#define PGDIR_SHIFT	39
-#define PTRS_PER_PGD	512
-
-/*
- * 3rd level page
- */
-#define PUD_SHIFT	30
-#define PTRS_PER_PUD	512
-
-/*
- * PMD_SHIFT determines the size of the area a middle-level
- * page table can map
- */
-#define PMD_SHIFT	21
-#define PTRS_PER_PMD	512
-
-/*
- * entries per page directory level
- */
-#define PTRS_PER_PTE	512
-
-#ifndef __ASSEMBLY__
-
-#define pte_ERROR(e)					\
-	printk("%s:%d: bad pte %p(%016lx).\n",		\
-	       __FILE__, __LINE__, &(e), pte_val(e))
-#define pmd_ERROR(e)					\
-	printk("%s:%d: bad pmd %p(%016lx).\n",		\
-	       __FILE__, __LINE__, &(e), pmd_val(e))
-#define pud_ERROR(e)					\
-	printk("%s:%d: bad pud %p(%016lx).\n",		\
-	       __FILE__, __LINE__, &(e), pud_val(e))
-#define pgd_ERROR(e)					\
-	printk("%s:%d: bad pgd %p(%016lx).\n",		\
-	       __FILE__, __LINE__, &(e), pgd_val(e))
-
-#define pgd_none(x)	(!pgd_val(x))
-#define pud_none(x)	(!pud_val(x))
-
-struct mm_struct;
-
-void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
-
-
-static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
-				    pte_t *ptep)
-{
-	*ptep = native_make_pte(0);
-}
-
-static inline void native_set_pte(pte_t *ptep, pte_t pte)
-{
-	*ptep = pte;
-}
-
-static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
-{
-	native_set_pte(ptep, pte);
-}
-
-static inline pte_t native_ptep_get_and_clear(pte_t *xp)
-{
-#ifdef CONFIG_SMP
-	return native_make_pte(xchg(&xp->pte, 0));
-#else
-	/* native_local_ptep_get_and_clear,
-	   but duplicated because of cyclic dependency */
-	pte_t ret = *xp;
-	native_pte_clear(NULL, 0, xp);
-	return ret;
-#endif
-}
-
-static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
-{
-	*pmdp = pmd;
-}
-
-static inline void native_pmd_clear(pmd_t *pmd)
-{
-	native_set_pmd(pmd, native_make_pmd(0));
-}
-
-static inline void native_set_pud(pud_t *pudp, pud_t pud)
-{
-	*pudp = pud;
-}
-
-static inline void native_pud_clear(pud_t *pud)
-{
-	native_set_pud(pud, native_make_pud(0));
-}
-
-static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
-{
-	*pgdp = pgd;
-}
-
-static inline void native_pgd_clear(pgd_t *pgd)
-{
-	native_set_pgd(pgd, native_make_pgd(0));
-}
-
-#define pte_same(a, b)		((a).pte == (b).pte)
-
-#endif /* !__ASSEMBLY__ */
-
-#define PMD_SIZE	(_AC(1, UL) << PMD_SHIFT)
-#define PMD_MASK	(~(PMD_SIZE - 1))
-#define PUD_SIZE	(_AC(1, UL) << PUD_SHIFT)
-#define PUD_MASK	(~(PUD_SIZE - 1))
-#define PGDIR_SIZE	(_AC(1, UL) << PGDIR_SHIFT)
-#define PGDIR_MASK	(~(PGDIR_SIZE - 1))
-
-
-#define MAXMEM		 _AC(0x00003fffffffffff, UL)
-#define VMALLOC_START    _AC(0xffffc20000000000, UL)
-#define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
-#define VMEMMAP_START	 _AC(0xffffe20000000000, UL)
-#define MODULES_VADDR    _AC(0xffffffffa0000000, UL)
-#define MODULES_END      _AC(0xffffffffff000000, UL)
-#define MODULES_LEN   (MODULES_END - MODULES_VADDR)
-
-#ifndef __ASSEMBLY__
-
-static inline int pgd_bad(pgd_t pgd)
-{
-	return (pgd_val(pgd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-static inline int pud_bad(pud_t pud)
-{
-	return (pud_val(pud) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-static inline int pmd_bad(pmd_t pmd)
-{
-	return (pmd_val(pmd) & ~(PTE_PFN_MASK | _PAGE_USER)) != _KERNPG_TABLE;
-}
-
-#define pte_none(x)	(!pte_val((x)))
-#define pte_present(x)	(pte_val((x)) & (_PAGE_PRESENT | _PAGE_PROTNONE))
-
-#define pages_to_mb(x)	((x) >> (20 - PAGE_SHIFT))   /* FIXME: is this right? */
-
-/*
- * Macro to mark a page protection value as "uncacheable".
- */
-#define pgprot_noncached(prot)					\
-	(__pgprot(pgprot_val((prot)) | _PAGE_PCD | _PAGE_PWT))
-
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- */
-
-/*
- * Level 4 access.
- */
-#define pgd_page_vaddr(pgd)						\
-	((unsigned long)__va((unsigned long)pgd_val((pgd)) & PTE_PFN_MASK))
-#define pgd_page(pgd)		(pfn_to_page(pgd_val((pgd)) >> PAGE_SHIFT))
-#define pgd_present(pgd) (pgd_val(pgd) & _PAGE_PRESENT)
-static inline int pgd_large(pgd_t pgd) { return 0; }
-#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
-
-/* PUD - Level3 access */
-/* to find an entry in a page-table-directory. */
-#define pud_page_vaddr(pud)						\
-	((unsigned long)__va(pud_val((pud)) & PHYSICAL_PAGE_MASK))
-#define pud_page(pud)	(pfn_to_page(pud_val((pud)) >> PAGE_SHIFT))
-#define pud_index(address) (((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
-#define pud_offset(pgd, address)					\
-	((pud_t *)pgd_page_vaddr(*(pgd)) + pud_index((address)))
-#define pud_present(pud) (pud_val((pud)) & _PAGE_PRESENT)
-
-static inline int pud_large(pud_t pte)
-{
-	return (pud_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
-		(_PAGE_PSE | _PAGE_PRESENT);
-}
-
-/* PMD  - Level 2 access */
-#define pmd_page_vaddr(pmd) ((unsigned long) __va(pmd_val((pmd)) & PTE_PFN_MASK))
-#define pmd_page(pmd)		(pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
-
-#define pmd_index(address) (((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
-#define pmd_offset(dir, address) ((pmd_t *)pud_page_vaddr(*(dir)) + \
-				  pmd_index(address))
-#define pmd_none(x)	(!pmd_val((x)))
-#define pmd_present(x)	(pmd_val((x)) & _PAGE_PRESENT)
-#define pfn_pmd(nr, prot) (__pmd(((nr) << PAGE_SHIFT) | pgprot_val((prot))))
-#define pmd_pfn(x)  ((pmd_val((x)) & __PHYSICAL_MASK) >> PAGE_SHIFT)
-
-#define pte_to_pgoff(pte) ((pte_val((pte)) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
-#define pgoff_to_pte(off) ((pte_t) { .pte = ((off) << PAGE_SHIFT) |	\
-					    _PAGE_FILE })
-#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT
-
-/* PTE - Level 1 access. */
-
-/* page, protection -> pte */
-#define mk_pte(page, pgprot)	pfn_pte(page_to_pfn((page)), (pgprot))
-
-#define pte_index(address) (((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
-#define pte_offset_kernel(dir, address) ((pte_t *) pmd_page_vaddr(*(dir)) + \
-					 pte_index((address)))
-
-/* x86-64 always has all page tables mapped. */
-#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
-#define pte_offset_map_nested(dir, address) pte_offset_kernel((dir), (address))
-#define pte_unmap(pte) /* NOP */
-#define pte_unmap_nested(pte) /* NOP */
-
-#define update_mmu_cache(vma, address, pte) do { } while (0)
-
-extern int direct_gbpages;
-
-/* Encode and de-code a swap entry */
-#define __swp_type(x)			(((x).val >> 1) & 0x3f)
-#define __swp_offset(x)			((x).val >> 8)
-#define __swp_entry(type, offset)	((swp_entry_t) { ((type) << 1) | \
-							 ((offset) << 8) })
-#define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
-#define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
-
-extern int kern_addr_valid(unsigned long addr);
-extern void cleanup_highmap(void);
-
-#define io_remap_pfn_range(vma, vaddr, pfn, size, prot)	\
-	remap_pfn_range(vma, vaddr, pfn, size, prot)
-
-#define HAVE_ARCH_UNMAPPED_AREA
-#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
-
-#define pgtable_cache_init()   do { } while (0)
-#define check_pgt_cache()      do { } while (0)
-
-#define PAGE_AGP    PAGE_KERNEL_NOCACHE
-#define HAVE_PAGE_AGP 1
-
-/* fs/proc/kcore.c */
-#define	kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK)
-#define	kc_offset_to_vaddr(o)				\
-	(((o) & (1UL << (__VIRTUAL_MASK_SHIFT - 1)))	\
-	 ? ((o) | ~__VIRTUAL_MASK)			\
-	 : (o))
-
-#define __HAVE_ARCH_PTE_SAME
-#endif /* !__ASSEMBLY__ */
-
-#endif /* ASM_X86__PGTABLE_64_H */
diff --git a/include/asm-x86/poll.h b/include/asm-x86/poll.h
deleted file mode 100644
index c98509d3149e..000000000000
--- a/include/asm-x86/poll.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/poll.h>
diff --git a/include/asm-x86/posix_types.h b/include/asm-x86/posix_types.h
deleted file mode 100644
index bb7133dc155d..000000000000
--- a/include/asm-x86/posix_types.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "posix_types_32.h"
-# else
-#  include "posix_types_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "posix_types_32.h"
-# else
-#  include "posix_types_64.h"
-# endif
-#endif
diff --git a/include/asm-x86/posix_types_32.h b/include/asm-x86/posix_types_32.h
deleted file mode 100644
index 70cf2bb05939..000000000000
--- a/include/asm-x86/posix_types_32.h
+++ /dev/null
@@ -1,85 +0,0 @@
-#ifndef ASM_X86__POSIX_TYPES_32_H
-#define ASM_X86__POSIX_TYPES_32_H
-
-/*
- * This file is generally used by user-level software, so you need to
- * be a little careful about namespace pollution etc.  Also, we cannot
- * assume GCC is being used.
- */
-
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned short	__kernel_mode_t;
-typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
-typedef unsigned short	__kernel_ipc_pid_t;
-typedef unsigned short	__kernel_uid_t;
-typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
-
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
-typedef unsigned short	__kernel_old_dev_t;
-
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define __FD_SET(fd,fdsetp)					\
-	asm volatile("btsl %1,%0":				\
-		     "+m" (*(__kernel_fd_set *)(fdsetp))	\
-		     : "r" ((int)(fd)))
-
-#undef	__FD_CLR
-#define __FD_CLR(fd,fdsetp)					\
-	asm volatile("btrl %1,%0":				\
-		     "+m" (*(__kernel_fd_set *)(fdsetp))	\
-		     : "r" ((int) (fd)))
-
-#undef	__FD_ISSET
-#define __FD_ISSET(fd,fdsetp)					\
-	(__extension__						\
-	 ({							\
-	 unsigned char __result;				\
-	 asm volatile("btl %1,%2 ; setb %0"			\
-		      : "=q" (__result)				\
-		      : "r" ((int)(fd)),			\
-			"m" (*(__kernel_fd_set *)(fdsetp)));	\
-	 __result;						\
-}))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp)					\
-do {								\
-	int __d0, __d1;						\
-	asm volatile("cld ; rep ; stosl"			\
-		     : "=m" (*(__kernel_fd_set *)(fdsetp)),	\
-		       "=&c" (__d0), "=&D" (__d1)		\
-		     : "a" (0), "1" (__FDSET_LONGS),		\
-		       "2" ((__kernel_fd_set *)(fdsetp))	\
-		     : "memory");				\
-} while (0)
-
-#endif /* defined(__KERNEL__) */
-
-#endif /* ASM_X86__POSIX_TYPES_32_H */
diff --git a/include/asm-x86/posix_types_64.h b/include/asm-x86/posix_types_64.h
deleted file mode 100644
index 388b4e7f4a44..000000000000
--- a/include/asm-x86/posix_types_64.h
+++ /dev/null
@@ -1,119 +0,0 @@
-#ifndef ASM_X86__POSIX_TYPES_64_H
-#define ASM_X86__POSIX_TYPES_64_H
-
-/*
- * This file is generally used by user-level software, so you need to
- * be a little careful about namespace pollution etc.  Also, we cannot
- * assume GCC is being used.
- */
-
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
-typedef unsigned long	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
-typedef int		__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-typedef unsigned short __kernel_old_uid_t;
-typedef unsigned short __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
-
-typedef unsigned long	__kernel_old_dev_t;
-
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long fd, __const__ __kernel_fd_set *p)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant cases (8 or 32 longs,
- * for 256 and 1024-bit fd_sets respectively)
- */
-#undef __FD_ZERO
-static inline void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 32:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			tmp[16] = 0; tmp[17] = 0; tmp[18] = 0; tmp[19] = 0;
-			tmp[20] = 0; tmp[21] = 0; tmp[22] = 0; tmp[23] = 0;
-			tmp[24] = 0; tmp[25] = 0; tmp[26] = 0; tmp[27] = 0;
-			tmp[28] = 0; tmp[29] = 0; tmp[30] = 0; tmp[31] = 0;
-			return;
-		case 16:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			return;
-		case 8:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			return;
-		case 4:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
-
-#endif /* ASM_X86__POSIX_TYPES_64_H */
diff --git a/include/asm-x86/prctl.h b/include/asm-x86/prctl.h
deleted file mode 100644
index e7ae34eb4103..000000000000
--- a/include/asm-x86/prctl.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef ASM_X86__PRCTL_H
-#define ASM_X86__PRCTL_H
-
-#define ARCH_SET_GS 0x1001
-#define ARCH_SET_FS 0x1002
-#define ARCH_GET_FS 0x1003
-#define ARCH_GET_GS 0x1004
-
-
-#endif /* ASM_X86__PRCTL_H */
diff --git a/include/asm-x86/processor-cyrix.h b/include/asm-x86/processor-cyrix.h
deleted file mode 100644
index 1198f2a0e42c..000000000000
--- a/include/asm-x86/processor-cyrix.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * NSC/Cyrix CPU indexed register access. Must be inlined instead of
- * macros to ensure correct access ordering
- * Access order is always 0x22 (=offset), 0x23 (=value)
- *
- * When using the old macros a line like
- *   setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
- * gets expanded to:
- *  do {
- *    outb((CX86_CCR2), 0x22);
- *    outb((({
- *        outb((CX86_CCR2), 0x22);
- *        inb(0x23);
- *    }) | 0x88), 0x23);
- *  } while (0);
- *
- * which in fact violates the access order (= 0x22, 0x22, 0x23, 0x23).
- */
-
-static inline u8 getCx86(u8 reg)
-{
-	outb(reg, 0x22);
-	return inb(0x23);
-}
-
-static inline void setCx86(u8 reg, u8 data)
-{
-	outb(reg, 0x22);
-	outb(data, 0x23);
-}
-
-#define getCx86_old(reg) ({ outb((reg), 0x22); inb(0x23); })
-
-#define setCx86_old(reg, data) do { \
-	outb((reg), 0x22); \
-	outb((data), 0x23); \
-} while (0)
-
diff --git a/include/asm-x86/processor-flags.h b/include/asm-x86/processor-flags.h
deleted file mode 100644
index dc5f0712f9fa..000000000000
--- a/include/asm-x86/processor-flags.h
+++ /dev/null
@@ -1,100 +0,0 @@
-#ifndef ASM_X86__PROCESSOR_FLAGS_H
-#define ASM_X86__PROCESSOR_FLAGS_H
-/* Various flags defined: can be included from assembler. */
-
-/*
- * EFLAGS bits
- */
-#define X86_EFLAGS_CF	0x00000001 /* Carry Flag */
-#define X86_EFLAGS_PF	0x00000004 /* Parity Flag */
-#define X86_EFLAGS_AF	0x00000010 /* Auxillary carry Flag */
-#define X86_EFLAGS_ZF	0x00000040 /* Zero Flag */
-#define X86_EFLAGS_SF	0x00000080 /* Sign Flag */
-#define X86_EFLAGS_TF	0x00000100 /* Trap Flag */
-#define X86_EFLAGS_IF	0x00000200 /* Interrupt Flag */
-#define X86_EFLAGS_DF	0x00000400 /* Direction Flag */
-#define X86_EFLAGS_OF	0x00000800 /* Overflow Flag */
-#define X86_EFLAGS_IOPL	0x00003000 /* IOPL mask */
-#define X86_EFLAGS_NT	0x00004000 /* Nested Task */
-#define X86_EFLAGS_RF	0x00010000 /* Resume Flag */
-#define X86_EFLAGS_VM	0x00020000 /* Virtual Mode */
-#define X86_EFLAGS_AC	0x00040000 /* Alignment Check */
-#define X86_EFLAGS_VIF	0x00080000 /* Virtual Interrupt Flag */
-#define X86_EFLAGS_VIP	0x00100000 /* Virtual Interrupt Pending */
-#define X86_EFLAGS_ID	0x00200000 /* CPUID detection flag */
-
-/*
- * Basic CPU control in CR0
- */
-#define X86_CR0_PE	0x00000001 /* Protection Enable */
-#define X86_CR0_MP	0x00000002 /* Monitor Coprocessor */
-#define X86_CR0_EM	0x00000004 /* Emulation */
-#define X86_CR0_TS	0x00000008 /* Task Switched */
-#define X86_CR0_ET	0x00000010 /* Extension Type */
-#define X86_CR0_NE	0x00000020 /* Numeric Error */
-#define X86_CR0_WP	0x00010000 /* Write Protect */
-#define X86_CR0_AM	0x00040000 /* Alignment Mask */
-#define X86_CR0_NW	0x20000000 /* Not Write-through */
-#define X86_CR0_CD	0x40000000 /* Cache Disable */
-#define X86_CR0_PG	0x80000000 /* Paging */
-
-/*
- * Paging options in CR3
- */
-#define X86_CR3_PWT	0x00000008 /* Page Write Through */
-#define X86_CR3_PCD	0x00000010 /* Page Cache Disable */
-
-/*
- * Intel CPU features in CR4
- */
-#define X86_CR4_VME	0x00000001 /* enable vm86 extensions */
-#define X86_CR4_PVI	0x00000002 /* virtual interrupts flag enable */
-#define X86_CR4_TSD	0x00000004 /* disable time stamp at ipl 3 */
-#define X86_CR4_DE	0x00000008 /* enable debugging extensions */
-#define X86_CR4_PSE	0x00000010 /* enable page size extensions */
-#define X86_CR4_PAE	0x00000020 /* enable physical address extensions */
-#define X86_CR4_MCE	0x00000040 /* Machine check enable */
-#define X86_CR4_PGE	0x00000080 /* enable global pages */
-#define X86_CR4_PCE	0x00000100 /* enable performance counters at ipl 3 */
-#define X86_CR4_OSFXSR	0x00000200 /* enable fast FPU save and restore */
-#define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */
-#define X86_CR4_VMXE	0x00002000 /* enable VMX virtualization */
-#define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
-
-/*
- * x86-64 Task Priority Register, CR8
- */
-#define X86_CR8_TPR	0x0000000F /* task priority register */
-
-/*
- * AMD and Transmeta use MSRs for configuration; see <asm/msr-index.h>
- */
-
-/*
- *      NSC/Cyrix CPU configuration register indexes
- */
-#define CX86_PCR0	0x20
-#define CX86_GCR	0xb8
-#define CX86_CCR0	0xc0
-#define CX86_CCR1	0xc1
-#define CX86_CCR2	0xc2
-#define CX86_CCR3	0xc3
-#define CX86_CCR4	0xe8
-#define CX86_CCR5	0xe9
-#define CX86_CCR6	0xea
-#define CX86_CCR7	0xeb
-#define CX86_PCR1	0xf0
-#define CX86_DIR0	0xfe
-#define CX86_DIR1	0xff
-#define CX86_ARR_BASE	0xc4
-#define CX86_RCR_BASE	0xdc
-
-#ifdef __KERNEL__
-#ifdef CONFIG_VM86
-#define X86_VM_MASK	X86_EFLAGS_VM
-#else
-#define X86_VM_MASK	0 /* No VM86 support */
-#endif
-#endif
-
-#endif /* ASM_X86__PROCESSOR_FLAGS_H */
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
deleted file mode 100644
index ee7cbb30773a..000000000000
--- a/include/asm-x86/processor.h
+++ /dev/null
@@ -1,936 +0,0 @@
-#ifndef ASM_X86__PROCESSOR_H
-#define ASM_X86__PROCESSOR_H
-
-#include <asm/processor-flags.h>
-
-/* Forward declaration, a strange C thing */
-struct task_struct;
-struct mm_struct;
-
-#include <asm/vm86.h>
-#include <asm/math_emu.h>
-#include <asm/segment.h>
-#include <asm/types.h>
-#include <asm/sigcontext.h>
-#include <asm/current.h>
-#include <asm/cpufeature.h>
-#include <asm/system.h>
-#include <asm/page.h>
-#include <asm/percpu.h>
-#include <asm/msr.h>
-#include <asm/desc_defs.h>
-#include <asm/nops.h>
-#include <asm/ds.h>
-
-#include <linux/personality.h>
-#include <linux/cpumask.h>
-#include <linux/cache.h>
-#include <linux/threads.h>
-#include <linux/init.h>
-
-/*
- * Default implementation of macro that returns current
- * instruction pointer ("program counter").
- */
-static inline void *current_text_addr(void)
-{
-	void *pc;
-
-	asm volatile("mov $1f, %0; 1:":"=r" (pc));
-
-	return pc;
-}
-
-#ifdef CONFIG_X86_VSMP
-# define ARCH_MIN_TASKALIGN		(1 << INTERNODE_CACHE_SHIFT)
-# define ARCH_MIN_MMSTRUCT_ALIGN	(1 << INTERNODE_CACHE_SHIFT)
-#else
-# define ARCH_MIN_TASKALIGN		16
-# define ARCH_MIN_MMSTRUCT_ALIGN	0
-#endif
-
-/*
- *  CPU type and hardware bug flags. Kept separately for each CPU.
- *  Members of this structure are referenced in head.S, so think twice
- *  before touching them. [mj]
- */
-
-struct cpuinfo_x86 {
-	__u8			x86;		/* CPU family */
-	__u8			x86_vendor;	/* CPU vendor */
-	__u8			x86_model;
-	__u8			x86_mask;
-#ifdef CONFIG_X86_32
-	char			wp_works_ok;	/* It doesn't on 386's */
-
-	/* Problems on some 486Dx4's and old 386's: */
-	char			hlt_works_ok;
-	char			hard_math;
-	char			rfu;
-	char			fdiv_bug;
-	char			f00f_bug;
-	char			coma_bug;
-	char			pad0;
-#else
-	/* Number of 4K pages in DTLB/ITLB combined(in pages): */
-	int			 x86_tlbsize;
-	__u8			x86_virt_bits;
-	__u8			x86_phys_bits;
-#endif
-	/* CPUID returned core id bits: */
-	__u8			x86_coreid_bits;
-	/* Max extended CPUID function supported: */
-	__u32			extended_cpuid_level;
-	/* Maximum supported CPUID level, -1=no CPUID: */
-	int			cpuid_level;
-	__u32			x86_capability[NCAPINTS];
-	char			x86_vendor_id[16];
-	char			x86_model_id[64];
-	/* in KB - valid for CPUS which support this call: */
-	int			x86_cache_size;
-	int			x86_cache_alignment;	/* In bytes */
-	int			x86_power;
-	unsigned long		loops_per_jiffy;
-#ifdef CONFIG_SMP
-	/* cpus sharing the last level cache: */
-	cpumask_t		llc_shared_map;
-#endif
-	/* cpuid returned max cores value: */
-	u16			 x86_max_cores;
-	u16			apicid;
-	u16			initial_apicid;
-	u16			x86_clflush_size;
-#ifdef CONFIG_SMP
-	/* number of cores as seen by the OS: */
-	u16			booted_cores;
-	/* Physical processor id: */
-	u16			phys_proc_id;
-	/* Core id: */
-	u16			cpu_core_id;
-	/* Index into per_cpu list: */
-	u16			cpu_index;
-#endif
-} __attribute__((__aligned__(SMP_CACHE_BYTES)));
-
-#define X86_VENDOR_INTEL	0
-#define X86_VENDOR_CYRIX	1
-#define X86_VENDOR_AMD		2
-#define X86_VENDOR_UMC		3
-#define X86_VENDOR_CENTAUR	5
-#define X86_VENDOR_TRANSMETA	7
-#define X86_VENDOR_NSC		8
-#define X86_VENDOR_NUM		9
-
-#define X86_VENDOR_UNKNOWN	0xff
-
-/*
- * capabilities of CPUs
- */
-extern struct cpuinfo_x86	boot_cpu_data;
-extern struct cpuinfo_x86	new_cpu_data;
-
-extern struct tss_struct	doublefault_tss;
-extern __u32			cleared_cpu_caps[NCAPINTS];
-
-#ifdef CONFIG_SMP
-DECLARE_PER_CPU(struct cpuinfo_x86, cpu_info);
-#define cpu_data(cpu)		per_cpu(cpu_info, cpu)
-#define current_cpu_data	__get_cpu_var(cpu_info)
-#else
-#define cpu_data(cpu)		boot_cpu_data
-#define current_cpu_data	boot_cpu_data
-#endif
-
-extern const struct seq_operations cpuinfo_op;
-
-static inline int hlt_works(int cpu)
-{
-#ifdef CONFIG_X86_32
-	return cpu_data(cpu).hlt_works_ok;
-#else
-	return 1;
-#endif
-}
-
-#define cache_line_size()	(boot_cpu_data.x86_cache_alignment)
-
-extern void cpu_detect(struct cpuinfo_x86 *c);
-
-extern struct pt_regs *idle_regs(struct pt_regs *);
-
-extern void early_cpu_init(void);
-extern void identify_boot_cpu(void);
-extern void identify_secondary_cpu(struct cpuinfo_x86 *);
-extern void print_cpu_info(struct cpuinfo_x86 *);
-extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
-extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
-extern unsigned short num_cache_leaves;
-
-extern void detect_extended_topology(struct cpuinfo_x86 *c);
-extern void detect_ht(struct cpuinfo_x86 *c);
-
-static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
-				unsigned int *ecx, unsigned int *edx)
-{
-	/* ecx is often an input as well as an output. */
-	asm("cpuid"
-	    : "=a" (*eax),
-	      "=b" (*ebx),
-	      "=c" (*ecx),
-	      "=d" (*edx)
-	    : "0" (*eax), "2" (*ecx));
-}
-
-static inline void load_cr3(pgd_t *pgdir)
-{
-	write_cr3(__pa(pgdir));
-}
-
-#ifdef CONFIG_X86_32
-/* This is the TSS defined by the hardware. */
-struct x86_hw_tss {
-	unsigned short		back_link, __blh;
-	unsigned long		sp0;
-	unsigned short		ss0, __ss0h;
-	unsigned long		sp1;
-	/* ss1 caches MSR_IA32_SYSENTER_CS: */
-	unsigned short		ss1, __ss1h;
-	unsigned long		sp2;
-	unsigned short		ss2, __ss2h;
-	unsigned long		__cr3;
-	unsigned long		ip;
-	unsigned long		flags;
-	unsigned long		ax;
-	unsigned long		cx;
-	unsigned long		dx;
-	unsigned long		bx;
-	unsigned long		sp;
-	unsigned long		bp;
-	unsigned long		si;
-	unsigned long		di;
-	unsigned short		es, __esh;
-	unsigned short		cs, __csh;
-	unsigned short		ss, __ssh;
-	unsigned short		ds, __dsh;
-	unsigned short		fs, __fsh;
-	unsigned short		gs, __gsh;
-	unsigned short		ldt, __ldth;
-	unsigned short		trace;
-	unsigned short		io_bitmap_base;
-
-} __attribute__((packed));
-#else
-struct x86_hw_tss {
-	u32			reserved1;
-	u64			sp0;
-	u64			sp1;
-	u64			sp2;
-	u64			reserved2;
-	u64			ist[7];
-	u32			reserved3;
-	u32			reserved4;
-	u16			reserved5;
-	u16			io_bitmap_base;
-
-} __attribute__((packed)) ____cacheline_aligned;
-#endif
-
-/*
- * IO-bitmap sizes:
- */
-#define IO_BITMAP_BITS			65536
-#define IO_BITMAP_BYTES			(IO_BITMAP_BITS/8)
-#define IO_BITMAP_LONGS			(IO_BITMAP_BYTES/sizeof(long))
-#define IO_BITMAP_OFFSET		offsetof(struct tss_struct, io_bitmap)
-#define INVALID_IO_BITMAP_OFFSET	0x8000
-#define INVALID_IO_BITMAP_OFFSET_LAZY	0x9000
-
-struct tss_struct {
-	/*
-	 * The hardware state:
-	 */
-	struct x86_hw_tss	x86_tss;
-
-	/*
-	 * The extra 1 is there because the CPU will access an
-	 * additional byte beyond the end of the IO permission
-	 * bitmap. The extra byte must be all 1 bits, and must
-	 * be within the limit.
-	 */
-	unsigned long		io_bitmap[IO_BITMAP_LONGS + 1];
-	/*
-	 * Cache the current maximum and the last task that used the bitmap:
-	 */
-	unsigned long		io_bitmap_max;
-	struct thread_struct	*io_bitmap_owner;
-
-	/*
-	 * .. and then another 0x100 bytes for the emergency kernel stack:
-	 */
-	unsigned long		stack[64];
-
-} ____cacheline_aligned;
-
-DECLARE_PER_CPU(struct tss_struct, init_tss);
-
-/*
- * Save the original ist values for checking stack pointers during debugging
- */
-struct orig_ist {
-	unsigned long		ist[7];
-};
-
-#define	MXCSR_DEFAULT		0x1f80
-
-struct i387_fsave_struct {
-	u32			cwd;	/* FPU Control Word		*/
-	u32			swd;	/* FPU Status Word		*/
-	u32			twd;	/* FPU Tag Word			*/
-	u32			fip;	/* FPU IP Offset		*/
-	u32			fcs;	/* FPU IP Selector		*/
-	u32			foo;	/* FPU Operand Pointer Offset	*/
-	u32			fos;	/* FPU Operand Pointer Selector	*/
-
-	/* 8*10 bytes for each FP-reg = 80 bytes:			*/
-	u32			st_space[20];
-
-	/* Software status information [not touched by FSAVE ]:		*/
-	u32			status;
-};
-
-struct i387_fxsave_struct {
-	u16			cwd; /* Control Word			*/
-	u16			swd; /* Status Word			*/
-	u16			twd; /* Tag Word			*/
-	u16			fop; /* Last Instruction Opcode		*/
-	union {
-		struct {
-			u64	rip; /* Instruction Pointer		*/
-			u64	rdp; /* Data Pointer			*/
-		};
-		struct {
-			u32	fip; /* FPU IP Offset			*/
-			u32	fcs; /* FPU IP Selector			*/
-			u32	foo; /* FPU Operand Offset		*/
-			u32	fos; /* FPU Operand Selector		*/
-		};
-	};
-	u32			mxcsr;		/* MXCSR Register State */
-	u32			mxcsr_mask;	/* MXCSR Mask		*/
-
-	/* 8*16 bytes for each FP-reg = 128 bytes:			*/
-	u32			st_space[32];
-
-	/* 16*16 bytes for each XMM-reg = 256 bytes:			*/
-	u32			xmm_space[64];
-
-	u32			padding[12];
-
-	union {
-		u32		padding1[12];
-		u32		sw_reserved[12];
-	};
-
-} __attribute__((aligned(16)));
-
-struct i387_soft_struct {
-	u32			cwd;
-	u32			swd;
-	u32			twd;
-	u32			fip;
-	u32			fcs;
-	u32			foo;
-	u32			fos;
-	/* 8*10 bytes for each FP-reg = 80 bytes: */
-	u32			st_space[20];
-	u8			ftop;
-	u8			changed;
-	u8			lookahead;
-	u8			no_update;
-	u8			rm;
-	u8			alimit;
-	struct info		*info;
-	u32			entry_eip;
-};
-
-struct xsave_hdr_struct {
-	u64 xstate_bv;
-	u64 reserved1[2];
-	u64 reserved2[5];
-} __attribute__((packed));
-
-struct xsave_struct {
-	struct i387_fxsave_struct i387;
-	struct xsave_hdr_struct xsave_hdr;
-	/* new processor state extensions will go here */
-} __attribute__ ((packed, aligned (64)));
-
-union thread_xstate {
-	struct i387_fsave_struct	fsave;
-	struct i387_fxsave_struct	fxsave;
-	struct i387_soft_struct		soft;
-	struct xsave_struct		xsave;
-};
-
-#ifdef CONFIG_X86_64
-DECLARE_PER_CPU(struct orig_ist, orig_ist);
-#endif
-
-extern void print_cpu_info(struct cpuinfo_x86 *);
-extern unsigned int xstate_size;
-extern void free_thread_xstate(struct task_struct *);
-extern struct kmem_cache *task_xstate_cachep;
-extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
-extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
-extern unsigned short num_cache_leaves;
-
-struct thread_struct {
-	/* Cached TLS descriptors: */
-	struct desc_struct	tls_array[GDT_ENTRY_TLS_ENTRIES];
-	unsigned long		sp0;
-	unsigned long		sp;
-#ifdef CONFIG_X86_32
-	unsigned long		sysenter_cs;
-#else
-	unsigned long		usersp;	/* Copy from PDA */
-	unsigned short		es;
-	unsigned short		ds;
-	unsigned short		fsindex;
-	unsigned short		gsindex;
-#endif
-	unsigned long		ip;
-	unsigned long		fs;
-	unsigned long		gs;
-	/* Hardware debugging registers: */
-	unsigned long		debugreg0;
-	unsigned long		debugreg1;
-	unsigned long		debugreg2;
-	unsigned long		debugreg3;
-	unsigned long		debugreg6;
-	unsigned long		debugreg7;
-	/* Fault info: */
-	unsigned long		cr2;
-	unsigned long		trap_no;
-	unsigned long		error_code;
-	/* floating point and extended processor state */
-	union thread_xstate	*xstate;
-#ifdef CONFIG_X86_32
-	/* Virtual 86 mode info */
-	struct vm86_struct __user *vm86_info;
-	unsigned long		screen_bitmap;
-	unsigned long		v86flags;
-	unsigned long		v86mask;
-	unsigned long		saved_sp0;
-	unsigned int		saved_fs;
-	unsigned int		saved_gs;
-#endif
-	/* IO permissions: */
-	unsigned long		*io_bitmap_ptr;
-	unsigned long		iopl;
-	/* Max allowed port in the bitmap, in bytes: */
-	unsigned		io_bitmap_max;
-/* MSR_IA32_DEBUGCTLMSR value to switch in if TIF_DEBUGCTLMSR is set.  */
-	unsigned long	debugctlmsr;
-#ifdef CONFIG_X86_DS
-/* Debug Store context; see include/asm-x86/ds.h; goes into MSR_IA32_DS_AREA */
-	struct ds_context	*ds_ctx;
-#endif /* CONFIG_X86_DS */
-#ifdef CONFIG_X86_PTRACE_BTS
-/* the signal to send on a bts buffer overflow */
-	unsigned int	bts_ovfl_signal;
-#endif /* CONFIG_X86_PTRACE_BTS */
-};
-
-static inline unsigned long native_get_debugreg(int regno)
-{
-	unsigned long val = 0;	/* Damn you, gcc! */
-
-	switch (regno) {
-	case 0:
-		asm("mov %%db0, %0" :"=r" (val));
-		break;
-	case 1:
-		asm("mov %%db1, %0" :"=r" (val));
-		break;
-	case 2:
-		asm("mov %%db2, %0" :"=r" (val));
-		break;
-	case 3:
-		asm("mov %%db3, %0" :"=r" (val));
-		break;
-	case 6:
-		asm("mov %%db6, %0" :"=r" (val));
-		break;
-	case 7:
-		asm("mov %%db7, %0" :"=r" (val));
-		break;
-	default:
-		BUG();
-	}
-	return val;
-}
-
-static inline void native_set_debugreg(int regno, unsigned long value)
-{
-	switch (regno) {
-	case 0:
-		asm("mov %0, %%db0"	::"r" (value));
-		break;
-	case 1:
-		asm("mov %0, %%db1"	::"r" (value));
-		break;
-	case 2:
-		asm("mov %0, %%db2"	::"r" (value));
-		break;
-	case 3:
-		asm("mov %0, %%db3"	::"r" (value));
-		break;
-	case 6:
-		asm("mov %0, %%db6"	::"r" (value));
-		break;
-	case 7:
-		asm("mov %0, %%db7"	::"r" (value));
-		break;
-	default:
-		BUG();
-	}
-}
-
-/*
- * Set IOPL bits in EFLAGS from given mask
- */
-static inline void native_set_iopl_mask(unsigned mask)
-{
-#ifdef CONFIG_X86_32
-	unsigned int reg;
-
-	asm volatile ("pushfl;"
-		      "popl %0;"
-		      "andl %1, %0;"
-		      "orl %2, %0;"
-		      "pushl %0;"
-		      "popfl"
-		      : "=&r" (reg)
-		      : "i" (~X86_EFLAGS_IOPL), "r" (mask));
-#endif
-}
-
-static inline void
-native_load_sp0(struct tss_struct *tss, struct thread_struct *thread)
-{
-	tss->x86_tss.sp0 = thread->sp0;
-#ifdef CONFIG_X86_32
-	/* Only happens when SEP is enabled, no need to test "SEP"arately: */
-	if (unlikely(tss->x86_tss.ss1 != thread->sysenter_cs)) {
-		tss->x86_tss.ss1 = thread->sysenter_cs;
-		wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
-	}
-#endif
-}
-
-static inline void native_swapgs(void)
-{
-#ifdef CONFIG_X86_64
-	asm volatile("swapgs" ::: "memory");
-#endif
-}
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-#define __cpuid			native_cpuid
-#define paravirt_enabled()	0
-
-/*
- * These special macros can be used to get or set a debugging register
- */
-#define get_debugreg(var, register)				\
-	(var) = native_get_debugreg(register)
-#define set_debugreg(value, register)				\
-	native_set_debugreg(register, value)
-
-static inline void load_sp0(struct tss_struct *tss,
-			    struct thread_struct *thread)
-{
-	native_load_sp0(tss, thread);
-}
-
-#define set_iopl_mask native_set_iopl_mask
-#endif /* CONFIG_PARAVIRT */
-
-/*
- * Save the cr4 feature set we're using (ie
- * Pentium 4MB enable and PPro Global page
- * enable), so that any CPU's that boot up
- * after us can get the correct flags.
- */
-extern unsigned long		mmu_cr4_features;
-
-static inline void set_in_cr4(unsigned long mask)
-{
-	unsigned cr4;
-
-	mmu_cr4_features |= mask;
-	cr4 = read_cr4();
-	cr4 |= mask;
-	write_cr4(cr4);
-}
-
-static inline void clear_in_cr4(unsigned long mask)
-{
-	unsigned cr4;
-
-	mmu_cr4_features &= ~mask;
-	cr4 = read_cr4();
-	cr4 &= ~mask;
-	write_cr4(cr4);
-}
-
-typedef struct {
-	unsigned long		seg;
-} mm_segment_t;
-
-
-/*
- * create a kernel thread without removing it from tasklists
- */
-extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
-
-/* Free all resources held by a thread. */
-extern void release_thread(struct task_struct *);
-
-/* Prepare to copy thread state - unlazy all lazy state */
-extern void prepare_to_copy(struct task_struct *tsk);
-
-unsigned long get_wchan(struct task_struct *p);
-
-/*
- * Generic CPUID function
- * clear %ecx since some cpus (Cyrix MII) do not set or clear %ecx
- * resulting in stale register contents being returned.
- */
-static inline void cpuid(unsigned int op,
-			 unsigned int *eax, unsigned int *ebx,
-			 unsigned int *ecx, unsigned int *edx)
-{
-	*eax = op;
-	*ecx = 0;
-	__cpuid(eax, ebx, ecx, edx);
-}
-
-/* Some CPUID calls want 'count' to be placed in ecx */
-static inline void cpuid_count(unsigned int op, int count,
-			       unsigned int *eax, unsigned int *ebx,
-			       unsigned int *ecx, unsigned int *edx)
-{
-	*eax = op;
-	*ecx = count;
-	__cpuid(eax, ebx, ecx, edx);
-}
-
-/*
- * CPUID functions returning a single datum
- */
-static inline unsigned int cpuid_eax(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return eax;
-}
-
-static inline unsigned int cpuid_ebx(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return ebx;
-}
-
-static inline unsigned int cpuid_ecx(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return ecx;
-}
-
-static inline unsigned int cpuid_edx(unsigned int op)
-{
-	unsigned int eax, ebx, ecx, edx;
-
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	return edx;
-}
-
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static inline void rep_nop(void)
-{
-	asm volatile("rep; nop" ::: "memory");
-}
-
-static inline void cpu_relax(void)
-{
-	rep_nop();
-}
-
-/* Stop speculative execution: */
-static inline void sync_core(void)
-{
-	int tmp;
-
-	asm volatile("cpuid" : "=a" (tmp) : "0" (1)
-		     : "ebx", "ecx", "edx", "memory");
-}
-
-static inline void __monitor(const void *eax, unsigned long ecx,
-			     unsigned long edx)
-{
-	/* "monitor %eax, %ecx, %edx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc8;"
-		     :: "a" (eax), "c" (ecx), "d"(edx));
-}
-
-static inline void __mwait(unsigned long eax, unsigned long ecx)
-{
-	/* "mwait %eax, %ecx;" */
-	asm volatile(".byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
-}
-
-static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
-{
-	trace_hardirqs_on();
-	/* "mwait %eax, %ecx;" */
-	asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
-		     :: "a" (eax), "c" (ecx));
-}
-
-extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
-
-extern void select_idle_routine(const struct cpuinfo_x86 *c);
-
-extern unsigned long		boot_option_idle_override;
-extern unsigned long		idle_halt;
-extern unsigned long		idle_nomwait;
-
-/*
- * on systems with caches, caches must be flashed as the absolute
- * last instruction before going into a suspended halt.  Otherwise,
- * dirty data can linger in the cache and become stale on resume,
- * leading to strange errors.
- *
- * perform a variety of operations to guarantee that the compiler
- * will not reorder instructions.  wbinvd itself is serializing
- * so the processor will not reorder.
- *
- * Systems without cache can just go into halt.
- */
-static inline void wbinvd_halt(void)
-{
-	mb();
-	/* check for clflush to determine if wbinvd is legal */
-	if (cpu_has_clflush)
-		asm volatile("cli; wbinvd; 1: hlt; jmp 1b" : : : "memory");
-	else
-		while (1)
-			halt();
-}
-
-extern void enable_sep_cpu(void);
-extern int sysenter_setup(void);
-
-/* Defined in head.S */
-extern struct desc_ptr		early_gdt_descr;
-
-extern void cpu_set_gdt(int);
-extern void switch_to_new_gdt(void);
-extern void cpu_init(void);
-extern void init_gdt(int cpu);
-
-static inline void update_debugctlmsr(unsigned long debugctlmsr)
-{
-#ifndef CONFIG_X86_DEBUGCTLMSR
-	if (boot_cpu_data.x86 < 6)
-		return;
-#endif
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
-}
-
-/*
- * from system description table in BIOS. Mostly for MCA use, but
- * others may find it useful:
- */
-extern unsigned int		machine_id;
-extern unsigned int		machine_submodel_id;
-extern unsigned int		BIOS_revision;
-
-/* Boot loader type from the setup header: */
-extern int			bootloader_type;
-
-extern char			ignore_fpu_irq;
-
-#define HAVE_ARCH_PICK_MMAP_LAYOUT 1
-#define ARCH_HAS_PREFETCHW
-#define ARCH_HAS_SPINLOCK_PREFETCH
-
-#ifdef CONFIG_X86_32
-# define BASE_PREFETCH		ASM_NOP4
-# define ARCH_HAS_PREFETCH
-#else
-# define BASE_PREFETCH		"prefetcht0 (%1)"
-#endif
-
-/*
- * Prefetch instructions for Pentium III (+) and AMD Athlon (+)
- *
- * It's not worth to care about 3dnow prefetches for the K6
- * because they are microcoded there and very slow.
- */
-static inline void prefetch(const void *x)
-{
-	alternative_input(BASE_PREFETCH,
-			  "prefetchnta (%1)",
-			  X86_FEATURE_XMM,
-			  "r" (x));
-}
-
-/*
- * 3dnow prefetch to get an exclusive cache line.
- * Useful for spinlocks to avoid one state transition in the
- * cache coherency protocol:
- */
-static inline void prefetchw(const void *x)
-{
-	alternative_input(BASE_PREFETCH,
-			  "prefetchw (%1)",
-			  X86_FEATURE_3DNOW,
-			  "r" (x));
-}
-
-static inline void spin_lock_prefetch(const void *x)
-{
-	prefetchw(x);
-}
-
-#ifdef CONFIG_X86_32
-/*
- * User space process size: 3GB (default).
- */
-#define TASK_SIZE		PAGE_OFFSET
-#define STACK_TOP		TASK_SIZE
-#define STACK_TOP_MAX		STACK_TOP
-
-#define INIT_THREAD  {							  \
-	.sp0			= sizeof(init_stack) + (long)&init_stack, \
-	.vm86_info		= NULL,					  \
-	.sysenter_cs		= __KERNEL_CS,				  \
-	.io_bitmap_ptr		= NULL,					  \
-	.fs			= __KERNEL_PERCPU,			  \
-}
-
-/*
- * Note that the .io_bitmap member must be extra-big. This is because
- * the CPU will access an additional byte beyond the end of the IO
- * permission bitmap. The extra byte must be all 1 bits, and must
- * be within the limit.
- */
-#define INIT_TSS  {							  \
-	.x86_tss = {							  \
-		.sp0		= sizeof(init_stack) + (long)&init_stack, \
-		.ss0		= __KERNEL_DS,				  \
-		.ss1		= __KERNEL_CS,				  \
-		.io_bitmap_base	= INVALID_IO_BITMAP_OFFSET,		  \
-	 },								  \
-	.io_bitmap		= { [0 ... IO_BITMAP_LONGS] = ~0 },	  \
-}
-
-extern unsigned long thread_saved_pc(struct task_struct *tsk);
-
-#define THREAD_SIZE_LONGS      (THREAD_SIZE/sizeof(unsigned long))
-#define KSTK_TOP(info)                                                 \
-({                                                                     \
-       unsigned long *__ptr = (unsigned long *)(info);                 \
-       (unsigned long)(&__ptr[THREAD_SIZE_LONGS]);                     \
-})
-
-/*
- * The below -8 is to reserve 8 bytes on top of the ring0 stack.
- * This is necessary to guarantee that the entire "struct pt_regs"
- * is accessable even if the CPU haven't stored the SS/ESP registers
- * on the stack (interrupt gate does not save these registers
- * when switching to the same priv ring).
- * Therefore beware: accessing the ss/esp fields of the
- * "struct pt_regs" is possible, but they may contain the
- * completely wrong values.
- */
-#define task_pt_regs(task)                                             \
-({                                                                     \
-       struct pt_regs *__regs__;                                       \
-       __regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task))-8); \
-       __regs__ - 1;                                                   \
-})
-
-#define KSTK_ESP(task)		(task_pt_regs(task)->sp)
-
-#else
-/*
- * User space process size. 47bits minus one guard page.
- */
-#define TASK_SIZE64	((1UL << 47) - PAGE_SIZE)
-
-/* This decides where the kernel will search for a free chunk of vm
- * space during mmap's.
- */
-#define IA32_PAGE_OFFSET	((current->personality & ADDR_LIMIT_3GB) ? \
-					0xc0000000 : 0xFFFFe000)
-
-#define TASK_SIZE		(test_thread_flag(TIF_IA32) ? \
-					IA32_PAGE_OFFSET : TASK_SIZE64)
-#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_IA32)) ? \
-					IA32_PAGE_OFFSET : TASK_SIZE64)
-
-#define STACK_TOP		TASK_SIZE
-#define STACK_TOP_MAX		TASK_SIZE64
-
-#define INIT_THREAD  { \
-	.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
-}
-
-#define INIT_TSS  { \
-	.x86_tss.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
-}
-
-/*
- * Return saved PC of a blocked thread.
- * What is this good for? it will be always the scheduler or ret_from_fork.
- */
-#define thread_saved_pc(t)	(*(unsigned long *)((t)->thread.sp - 8))
-
-#define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
-#define KSTK_ESP(tsk)		-1 /* sorry. doesn't work for syscall. */
-#endif /* CONFIG_X86_64 */
-
-extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
-					       unsigned long new_sp);
-
-/*
- * This decides where the kernel will search for a free chunk of vm
- * space during mmap's.
- */
-#define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 3))
-
-#define KSTK_EIP(task)		(task_pt_regs(task)->ip)
-
-/* Get/set a process' ability to use the timestamp counter instruction */
-#define GET_TSC_CTL(adr)	get_tsc_mode((adr))
-#define SET_TSC_CTL(val)	set_tsc_mode((val))
-
-extern int get_tsc_mode(unsigned long adr);
-extern int set_tsc_mode(unsigned int val);
-
-#endif /* ASM_X86__PROCESSOR_H */
diff --git a/include/asm-x86/proto.h b/include/asm-x86/proto.h
deleted file mode 100644
index 6e89e8b4de0e..000000000000
--- a/include/asm-x86/proto.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef ASM_X86__PROTO_H
-#define ASM_X86__PROTO_H
-
-#include <asm/ldt.h>
-
-/* misc architecture specific prototypes */
-
-extern void early_idt_handler(void);
-
-extern void system_call(void);
-extern void syscall_init(void);
-
-extern void ia32_syscall(void);
-extern void ia32_cstar_target(void);
-extern void ia32_sysenter_target(void);
-
-extern void syscall32_cpu_init(void);
-
-extern void check_efer(void);
-
-#ifdef CONFIG_X86_BIOS_REBOOT
-extern int reboot_force;
-#else
-static const int reboot_force = 0;
-#endif
-
-long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
-
-#define round_up(x, y) (((x) + (y) - 1) & ~((y) - 1))
-#define round_down(x, y) ((x) & ~((y) - 1))
-
-#endif /* ASM_X86__PROTO_H */
diff --git a/include/asm-x86/ptrace-abi.h b/include/asm-x86/ptrace-abi.h
deleted file mode 100644
index 4298b8882a78..000000000000
--- a/include/asm-x86/ptrace-abi.h
+++ /dev/null
@@ -1,145 +0,0 @@
-#ifndef ASM_X86__PTRACE_ABI_H
-#define ASM_X86__PTRACE_ABI_H
-
-#ifdef __i386__
-
-#define EBX 0
-#define ECX 1
-#define EDX 2
-#define ESI 3
-#define EDI 4
-#define EBP 5
-#define EAX 6
-#define DS 7
-#define ES 8
-#define FS 9
-#define GS 10
-#define ORIG_EAX 11
-#define EIP 12
-#define CS  13
-#define EFL 14
-#define UESP 15
-#define SS   16
-#define FRAME_SIZE 17
-
-#else /* __i386__ */
-
-#if defined(__ASSEMBLY__) || defined(__FRAME_OFFSETS)
-#define R15 0
-#define R14 8
-#define R13 16
-#define R12 24
-#define RBP 32
-#define RBX 40
-/* arguments: interrupts/non tracing syscalls only save upto here*/
-#define R11 48
-#define R10 56
-#define R9 64
-#define R8 72
-#define RAX 80
-#define RCX 88
-#define RDX 96
-#define RSI 104
-#define RDI 112
-#define ORIG_RAX 120       /* = ERROR */
-/* end of arguments */
-/* cpu exception frame or undefined in case of fast syscall. */
-#define RIP 128
-#define CS 136
-#define EFLAGS 144
-#define RSP 152
-#define SS 160
-#define ARGOFFSET R11
-#endif /* __ASSEMBLY__ */
-
-/* top of stack page */
-#define FRAME_SIZE 168
-
-#endif /* !__i386__ */
-
-/* Arbitrarily choose the same ptrace numbers as used by the Sparc code. */
-#define PTRACE_GETREGS            12
-#define PTRACE_SETREGS            13
-#define PTRACE_GETFPREGS          14
-#define PTRACE_SETFPREGS          15
-#define PTRACE_GETFPXREGS         18
-#define PTRACE_SETFPXREGS         19
-
-#define PTRACE_OLDSETOPTIONS      21
-
-/* only useful for access 32bit programs / kernels */
-#define PTRACE_GET_THREAD_AREA    25
-#define PTRACE_SET_THREAD_AREA    26
-
-#ifdef __x86_64__
-# define PTRACE_ARCH_PRCTL	  30
-#endif
-
-#define PTRACE_SYSEMU		  31
-#define PTRACE_SYSEMU_SINGLESTEP  32
-
-#define PTRACE_SINGLEBLOCK	33	/* resume execution until next branch */
-
-#ifdef CONFIG_X86_PTRACE_BTS
-
-#ifndef __ASSEMBLY__
-#include <asm/types.h>
-
-/* configuration/status structure used in PTRACE_BTS_CONFIG and
-   PTRACE_BTS_STATUS commands.
-*/
-struct ptrace_bts_config {
-	/* requested or actual size of BTS buffer in bytes */
-	__u32 size;
-	/* bitmask of below flags */
-	__u32 flags;
-	/* buffer overflow signal */
-	__u32 signal;
-	/* actual size of bts_struct in bytes */
-	__u32 bts_size;
-};
-#endif /* __ASSEMBLY__ */
-
-#define PTRACE_BTS_O_TRACE	0x1 /* branch trace */
-#define PTRACE_BTS_O_SCHED	0x2 /* scheduling events w/ jiffies */
-#define PTRACE_BTS_O_SIGNAL     0x4 /* send SIG<signal> on buffer overflow
-				       instead of wrapping around */
-#define PTRACE_BTS_O_ALLOC	0x8 /* (re)allocate buffer */
-
-#define PTRACE_BTS_CONFIG	40
-/* Configure branch trace recording.
-   ADDR points to a struct ptrace_bts_config.
-   DATA gives the size of that buffer.
-   A new buffer is allocated, if requested in the flags.
-   An overflow signal may only be requested for new buffers.
-   Returns the number of bytes read.
-*/
-#define PTRACE_BTS_STATUS	41
-/* Return the current configuration in a struct ptrace_bts_config
-   pointed to by ADDR; DATA gives the size of that buffer.
-   Returns the number of bytes written.
-*/
-#define PTRACE_BTS_SIZE		42
-/* Return the number of available BTS records for draining.
-   DATA and ADDR are ignored.
-*/
-#define PTRACE_BTS_GET		43
-/* Get a single BTS record.
-   DATA defines the index into the BTS array, where 0 is the newest
-   entry, and higher indices refer to older entries.
-   ADDR is pointing to struct bts_struct (see asm/ds.h).
-*/
-#define PTRACE_BTS_CLEAR	44
-/* Clear the BTS buffer.
-   DATA and ADDR are ignored.
-*/
-#define PTRACE_BTS_DRAIN	45
-/* Read all available BTS records and clear the buffer.
-   ADDR points to an array of struct bts_struct.
-   DATA gives the size of that buffer.
-   BTS records are read from oldest to newest.
-   Returns number of BTS records drained.
-*/
-#endif /* CONFIG_X86_PTRACE_BTS */
-
-#endif /* ASM_X86__PTRACE_ABI_H */
diff --git a/include/asm-x86/ptrace.h b/include/asm-x86/ptrace.h
deleted file mode 100644
index a2025525a15a..000000000000
--- a/include/asm-x86/ptrace.h
+++ /dev/null
@@ -1,280 +0,0 @@
-#ifndef ASM_X86__PTRACE_H
-#define ASM_X86__PTRACE_H
-
-#include <linux/compiler.h>	/* For __user */
-#include <asm/ptrace-abi.h>
-#include <asm/processor-flags.h>
-
-#ifdef __KERNEL__
-#include <asm/ds.h>		/* the DS BTS struct is used for ptrace too */
-#include <asm/segment.h>
-#endif
-
-#ifndef __ASSEMBLY__
-
-#ifdef __i386__
-/* this struct defines the way the registers are stored on the
-   stack during a system call. */
-
-#ifndef __KERNEL__
-
-struct pt_regs {
-	long ebx;
-	long ecx;
-	long edx;
-	long esi;
-	long edi;
-	long ebp;
-	long eax;
-	int  xds;
-	int  xes;
-	int  xfs;
-	/* int  gs; */
-	long orig_eax;
-	long eip;
-	int  xcs;
-	long eflags;
-	long esp;
-	int  xss;
-};
-
-#else /* __KERNEL__ */
-
-struct pt_regs {
-	unsigned long bx;
-	unsigned long cx;
-	unsigned long dx;
-	unsigned long si;
-	unsigned long di;
-	unsigned long bp;
-	unsigned long ax;
-	unsigned long ds;
-	unsigned long es;
-	unsigned long fs;
-	/* int  gs; */
-	unsigned long orig_ax;
-	unsigned long ip;
-	unsigned long cs;
-	unsigned long flags;
-	unsigned long sp;
-	unsigned long ss;
-};
-
-#endif /* __KERNEL__ */
-
-#else /* __i386__ */
-
-#ifndef __KERNEL__
-
-struct pt_regs {
-	unsigned long r15;
-	unsigned long r14;
-	unsigned long r13;
-	unsigned long r12;
-	unsigned long rbp;
-	unsigned long rbx;
-/* arguments: non interrupts/non tracing syscalls only save upto here*/
-	unsigned long r11;
-	unsigned long r10;
-	unsigned long r9;
-	unsigned long r8;
-	unsigned long rax;
-	unsigned long rcx;
-	unsigned long rdx;
-	unsigned long rsi;
-	unsigned long rdi;
-	unsigned long orig_rax;
-/* end of arguments */
-/* cpu exception frame or undefined */
-	unsigned long rip;
-	unsigned long cs;
-	unsigned long eflags;
-	unsigned long rsp;
-	unsigned long ss;
-/* top of stack page */
-};
-
-#else /* __KERNEL__ */
-
-struct pt_regs {
-	unsigned long r15;
-	unsigned long r14;
-	unsigned long r13;
-	unsigned long r12;
-	unsigned long bp;
-	unsigned long bx;
-/* arguments: non interrupts/non tracing syscalls only save upto here*/
-	unsigned long r11;
-	unsigned long r10;
-	unsigned long r9;
-	unsigned long r8;
-	unsigned long ax;
-	unsigned long cx;
-	unsigned long dx;
-	unsigned long si;
-	unsigned long di;
-	unsigned long orig_ax;
-/* end of arguments */
-/* cpu exception frame or undefined */
-	unsigned long ip;
-	unsigned long cs;
-	unsigned long flags;
-	unsigned long sp;
-	unsigned long ss;
-/* top of stack page */
-};
-
-#endif /* __KERNEL__ */
-#endif /* !__i386__ */
-
-
-#ifdef CONFIG_X86_PTRACE_BTS
-/* a branch trace record entry
- *
- * In order to unify the interface between various processor versions,
- * we use the below data structure for all processors.
- */
-enum bts_qualifier {
-	BTS_INVALID = 0,
-	BTS_BRANCH,
-	BTS_TASK_ARRIVES,
-	BTS_TASK_DEPARTS
-};
-
-struct bts_struct {
-	__u64 qualifier;
-	union {
-		/* BTS_BRANCH */
-		struct {
-			__u64 from_ip;
-			__u64 to_ip;
-		} lbr;
-		/* BTS_TASK_ARRIVES or
-		   BTS_TASK_DEPARTS */
-		__u64 jiffies;
-	} variant;
-};
-#endif /* CONFIG_X86_PTRACE_BTS */
-
-#ifdef __KERNEL__
-
-#include <linux/init.h>
-
-struct cpuinfo_x86;
-struct task_struct;
-
-#ifdef CONFIG_X86_PTRACE_BTS
-extern void __cpuinit ptrace_bts_init_intel(struct cpuinfo_x86 *);
-extern void ptrace_bts_take_timestamp(struct task_struct *, enum bts_qualifier);
-#else
-#define ptrace_bts_init_intel(config) do {} while (0)
-#endif /* CONFIG_X86_PTRACE_BTS */
-
-extern unsigned long profile_pc(struct pt_regs *regs);
-
-extern unsigned long
-convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
-extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
-			 int error_code, int si_code);
-void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
-
-extern long syscall_trace_enter(struct pt_regs *);
-extern void syscall_trace_leave(struct pt_regs *);
-
-static inline unsigned long regs_return_value(struct pt_regs *regs)
-{
-	return regs->ax;
-}
-
-/*
- * user_mode_vm(regs) determines whether a register set came from user mode.
- * This is true if V8086 mode was enabled OR if the register set was from
- * protected mode with RPL-3 CS value.  This tricky test checks that with
- * one comparison.  Many places in the kernel can bypass this full check
- * if they have already ruled out V8086 mode, so user_mode(regs) can be used.
- */
-static inline int user_mode(struct pt_regs *regs)
-{
-#ifdef CONFIG_X86_32
-	return (regs->cs & SEGMENT_RPL_MASK) == USER_RPL;
-#else
-	return !!(regs->cs & 3);
-#endif
-}
-
-static inline int user_mode_vm(struct pt_regs *regs)
-{
-#ifdef CONFIG_X86_32
-	return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >=
-		USER_RPL;
-#else
-	return user_mode(regs);
-#endif
-}
-
-static inline int v8086_mode(struct pt_regs *regs)
-{
-#ifdef CONFIG_X86_32
-	return (regs->flags & X86_VM_MASK);
-#else
-	return 0;	/* No V86 mode support in long mode */
-#endif
-}
-
-/*
- * X86_32 CPUs don't save ss and esp if the CPU is already in kernel mode
- * when it traps.  So regs will be the current sp.
- *
- * This is valid only for kernel mode traps.
- */
-static inline unsigned long kernel_trap_sp(struct pt_regs *regs)
-{
-#ifdef CONFIG_X86_32
-	return (unsigned long)regs;
-#else
-	return regs->sp;
-#endif
-}
-
-static inline unsigned long instruction_pointer(struct pt_regs *regs)
-{
-	return regs->ip;
-}
-
-static inline unsigned long frame_pointer(struct pt_regs *regs)
-{
-	return regs->bp;
-}
-
-static inline unsigned long user_stack_pointer(struct pt_regs *regs)
-{
-	return regs->sp;
-}
-
-/*
- * These are defined as per linux/ptrace.h, which see.
- */
-#define arch_has_single_step()	(1)
-extern void user_enable_single_step(struct task_struct *);
-extern void user_disable_single_step(struct task_struct *);
-
-extern void user_enable_block_step(struct task_struct *);
-#ifdef CONFIG_X86_DEBUGCTLMSR
-#define arch_has_block_step()	(1)
-#else
-#define arch_has_block_step()	(boot_cpu_data.x86 >= 6)
-#endif
-
-struct user_desc;
-extern int do_get_thread_area(struct task_struct *p, int idx,
-			      struct user_desc __user *info);
-extern int do_set_thread_area(struct task_struct *p, int idx,
-			      struct user_desc __user *info, int can_allocate);
-
-#define __ARCH_WANT_COMPAT_SYS_PTRACE
-
-#endif /* __KERNEL__ */
-
-#endif /* !__ASSEMBLY__ */
-
-#endif /* ASM_X86__PTRACE_H */
diff --git a/include/asm-x86/pvclock-abi.h b/include/asm-x86/pvclock-abi.h
deleted file mode 100644
index edb3b4ecfc81..000000000000
--- a/include/asm-x86/pvclock-abi.h
+++ /dev/null
@@ -1,42 +0,0 @@
-#ifndef ASM_X86__PVCLOCK_ABI_H
-#define ASM_X86__PVCLOCK_ABI_H
-#ifndef __ASSEMBLY__
-
-/*
- * These structs MUST NOT be changed.
- * They are the ABI between hypervisor and guest OS.
- * Both Xen and KVM are using this.
- *
- * pvclock_vcpu_time_info holds the system time and the tsc timestamp
- * of the last update. So the guest can use the tsc delta to get a
- * more precise system time.  There is one per virtual cpu.
- *
- * pvclock_wall_clock references the point in time when the system
- * time was zero (usually boot time), thus the guest calculates the
- * current wall clock by adding the system time.
- *
- * Protocol for the "version" fields is: hypervisor raises it (making
- * it uneven) before it starts updating the fields and raises it again
- * (making it even) when it is done.  Thus the guest can make sure the
- * time values it got are consistent by checking the version before
- * and after reading them.
- */
-
-struct pvclock_vcpu_time_info {
-	u32   version;
-	u32   pad0;
-	u64   tsc_timestamp;
-	u64   system_time;
-	u32   tsc_to_system_mul;
-	s8    tsc_shift;
-	u8    pad[3];
-} __attribute__((__packed__)); /* 32 bytes */
-
-struct pvclock_wall_clock {
-	u32   version;
-	u32   sec;
-	u32   nsec;
-} __attribute__((__packed__));
-
-#endif /* __ASSEMBLY__ */
-#endif /* ASM_X86__PVCLOCK_ABI_H */
diff --git a/include/asm-x86/pvclock.h b/include/asm-x86/pvclock.h
deleted file mode 100644
index ad29e277fd6d..000000000000
--- a/include/asm-x86/pvclock.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef ASM_X86__PVCLOCK_H
-#define ASM_X86__PVCLOCK_H
-
-#include <linux/clocksource.h>
-#include <asm/pvclock-abi.h>
-
-/* some helper functions for xen and kvm pv clock sources */
-cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src);
-unsigned long pvclock_tsc_khz(struct pvclock_vcpu_time_info *src);
-void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
-			    struct pvclock_vcpu_time_info *vcpu,
-			    struct timespec *ts);
-
-#endif /* ASM_X86__PVCLOCK_H */
diff --git a/include/asm-x86/reboot.h b/include/asm-x86/reboot.h
deleted file mode 100644
index 1c2f0ce9e31e..000000000000
--- a/include/asm-x86/reboot.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef ASM_X86__REBOOT_H
-#define ASM_X86__REBOOT_H
-
-struct pt_regs;
-
-struct machine_ops {
-	void (*restart)(char *cmd);
-	void (*halt)(void);
-	void (*power_off)(void);
-	void (*shutdown)(void);
-	void (*crash_shutdown)(struct pt_regs *);
-	void (*emergency_restart)(void);
-};
-
-extern struct machine_ops machine_ops;
-
-void native_machine_crash_shutdown(struct pt_regs *regs);
-void native_machine_shutdown(void);
-void machine_real_restart(const unsigned char *code, int length);
-
-#endif /* ASM_X86__REBOOT_H */
diff --git a/include/asm-x86/reboot_fixups.h b/include/asm-x86/reboot_fixups.h
deleted file mode 100644
index 2c2987d97570..000000000000
--- a/include/asm-x86/reboot_fixups.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef ASM_X86__REBOOT_FIXUPS_H
-#define ASM_X86__REBOOT_FIXUPS_H
-
-extern void mach_reboot_fixups(void);
-
-#endif /* ASM_X86__REBOOT_FIXUPS_H */
diff --git a/include/asm-x86/required-features.h b/include/asm-x86/required-features.h
deleted file mode 100644
index a01c4e376331..000000000000
--- a/include/asm-x86/required-features.h
+++ /dev/null
@@ -1,82 +0,0 @@
-#ifndef ASM_X86__REQUIRED_FEATURES_H
-#define ASM_X86__REQUIRED_FEATURES_H
-
-/* Define minimum CPUID feature set for kernel These bits are checked
-   really early to actually display a visible error message before the
-   kernel dies.  Make sure to assign features to the proper mask!
-
-   Some requirements that are not in CPUID yet are also in the
-   CONFIG_X86_MINIMUM_CPU_FAMILY which is checked too.
-
-   The real information is in arch/x86/Kconfig.cpu, this just converts
-   the CONFIGs into a bitmask */
-
-#ifndef CONFIG_MATH_EMULATION
-# define NEED_FPU	(1<<(X86_FEATURE_FPU & 31))
-#else
-# define NEED_FPU	0
-#endif
-
-#if defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
-# define NEED_PAE	(1<<(X86_FEATURE_PAE & 31))
-#else
-# define NEED_PAE	0
-#endif
-
-#ifdef CONFIG_X86_CMPXCHG64
-# define NEED_CX8	(1<<(X86_FEATURE_CX8 & 31))
-#else
-# define NEED_CX8	0
-#endif
-
-#if defined(CONFIG_X86_CMOV) || defined(CONFIG_X86_64)
-# define NEED_CMOV	(1<<(X86_FEATURE_CMOV & 31))
-#else
-# define NEED_CMOV	0
-#endif
-
-#ifdef CONFIG_X86_USE_3DNOW
-# define NEED_3DNOW	(1<<(X86_FEATURE_3DNOW & 31))
-#else
-# define NEED_3DNOW	0
-#endif
-
-#if defined(CONFIG_X86_P6_NOP) || defined(CONFIG_X86_64)
-# define NEED_NOPL	(1<<(X86_FEATURE_NOPL & 31))
-#else
-# define NEED_NOPL	0
-#endif
-
-#ifdef CONFIG_X86_64
-#define NEED_PSE	0
-#define NEED_MSR	(1<<(X86_FEATURE_MSR & 31))
-#define NEED_PGE	(1<<(X86_FEATURE_PGE & 31))
-#define NEED_FXSR	(1<<(X86_FEATURE_FXSR & 31))
-#define NEED_XMM	(1<<(X86_FEATURE_XMM & 31))
-#define NEED_XMM2	(1<<(X86_FEATURE_XMM2 & 31))
-#define NEED_LM		(1<<(X86_FEATURE_LM & 31))
-#else
-#define NEED_PSE	0
-#define NEED_MSR	0
-#define NEED_PGE	0
-#define NEED_FXSR	0
-#define NEED_XMM	0
-#define NEED_XMM2	0
-#define NEED_LM		0
-#endif
-
-#define REQUIRED_MASK0	(NEED_FPU|NEED_PSE|NEED_MSR|NEED_PAE|\
-			 NEED_CX8|NEED_PGE|NEED_FXSR|NEED_CMOV|\
-			 NEED_XMM|NEED_XMM2)
-#define SSE_MASK	(NEED_XMM|NEED_XMM2)
-
-#define REQUIRED_MASK1	(NEED_LM|NEED_3DNOW)
-
-#define REQUIRED_MASK2	0
-#define REQUIRED_MASK3	(NEED_NOPL)
-#define REQUIRED_MASK4	0
-#define REQUIRED_MASK5	0
-#define REQUIRED_MASK6	0
-#define REQUIRED_MASK7	0
-
-#endif /* ASM_X86__REQUIRED_FEATURES_H */
diff --git a/include/asm-x86/resource.h b/include/asm-x86/resource.h
deleted file mode 100644
index 04bc4db8921b..000000000000
--- a/include/asm-x86/resource.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/resource.h>
diff --git a/include/asm-x86/resume-trace.h b/include/asm-x86/resume-trace.h
deleted file mode 100644
index e39376d7de50..000000000000
--- a/include/asm-x86/resume-trace.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef ASM_X86__RESUME_TRACE_H
-#define ASM_X86__RESUME_TRACE_H
-
-#include <asm/asm.h>
-
-#define TRACE_RESUME(user)					\
-do {								\
-	if (pm_trace_enabled) {					\
-		const void *tracedata;				\
-		asm volatile(_ASM_MOV " $1f,%0\n"		\
-			     ".section .tracedata,\"a\"\n"	\
-			     "1:\t.word %c1\n\t"		\
-			     _ASM_PTR " %c2\n"			\
-			     ".previous"			\
-			     :"=r" (tracedata)			\
-			     : "i" (__LINE__), "i" (__FILE__));	\
-		generate_resume_trace(tracedata, user);		\
-	}							\
-} while (0)
-
-#endif /* ASM_X86__RESUME_TRACE_H */
diff --git a/include/asm-x86/rio.h b/include/asm-x86/rio.h
deleted file mode 100644
index 5e1256bdee83..000000000000
--- a/include/asm-x86/rio.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * Derived from include/asm-x86/mach-summit/mach_mpparse.h
- *          and include/asm-x86/mach-default/bios_ebda.h
- *
- * Author: Laurent Vivier <Laurent.Vivier@bull.net>
- */
-
-#ifndef ASM_X86__RIO_H
-#define ASM_X86__RIO_H
-
-#define RIO_TABLE_VERSION	3
-
-struct rio_table_hdr {
-	u8 version;		/* Version number of this data structure  */
-	u8 num_scal_dev;	/* # of Scalability devices               */
-	u8 num_rio_dev;		/* # of RIO I/O devices                   */
-} __attribute__((packed));
-
-struct scal_detail {
-	u8 node_id;		/* Scalability Node ID                    */
-	u32 CBAR;		/* Address of 1MB register space          */
-	u8 port0node;		/* Node ID port connected to: 0xFF=None   */
-	u8 port0port;		/* Port num port connected to: 0,1,2, or  */
-				/* 0xFF=None                              */
-	u8 port1node;		/* Node ID port connected to: 0xFF = None */
-	u8 port1port;		/* Port num port connected to: 0,1,2, or  */
-				/* 0xFF=None                              */
-	u8 port2node;		/* Node ID port connected to: 0xFF = None */
-	u8 port2port;		/* Port num port connected to: 0,1,2, or  */
-				/* 0xFF=None                              */
-	u8 chassis_num;		/* 1 based Chassis number (1 = boot node) */
-} __attribute__((packed));
-
-struct rio_detail {
-	u8 node_id;		/* RIO Node ID                            */
-	u32 BBAR;		/* Address of 1MB register space          */
-	u8 type;		/* Type of device                         */
-	u8 owner_id;		/* Node ID of Hurricane that owns this    */
-				/* node                                   */
-	u8 port0node;		/* Node ID port connected to: 0xFF=None   */
-	u8 port0port;		/* Port num port connected to: 0,1,2, or  */
-				/* 0xFF=None                              */
-	u8 port1node;		/* Node ID port connected to: 0xFF=None   */
-	u8 port1port;		/* Port num port connected to: 0,1,2, or  */
-				/* 0xFF=None                              */
-	u8 first_slot;		/* Lowest slot number below this Calgary  */
-	u8 status;		/* Bit 0 = 1 : the XAPIC is used          */
-				/*       = 0 : the XAPIC is not used, ie: */
-				/*            ints fwded to another XAPIC */
-				/*           Bits1:7 Reserved             */
-	u8 WP_index;		/* instance index - lower ones have       */
-				/*     lower slot numbers/PCI bus numbers */
-	u8 chassis_num;		/* 1 based Chassis number                 */
-} __attribute__((packed));
-
-enum {
-	HURR_SCALABILTY	= 0,	/* Hurricane Scalability info */
-	HURR_RIOIB	= 2,	/* Hurricane RIOIB info       */
-	COMPAT_CALGARY	= 4,	/* Compatibility Calgary      */
-	ALT_CALGARY	= 5,	/* Second Planar Calgary      */
-};
-
-#endif /* ASM_X86__RIO_H */
diff --git a/include/asm-x86/rtc.h b/include/asm-x86/rtc.h
deleted file mode 100644
index f71c3b0ed360..000000000000
--- a/include/asm-x86/rtc.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/rtc.h>
diff --git a/include/asm-x86/rwlock.h b/include/asm-x86/rwlock.h
deleted file mode 100644
index 48a3109e1a7d..000000000000
--- a/include/asm-x86/rwlock.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef ASM_X86__RWLOCK_H
-#define ASM_X86__RWLOCK_H
-
-#define RW_LOCK_BIAS		 0x01000000
-
-/* Actual code is in asm/spinlock.h or in arch/x86/lib/rwlock.S */
-
-#endif /* ASM_X86__RWLOCK_H */
diff --git a/include/asm-x86/rwsem.h b/include/asm-x86/rwsem.h
deleted file mode 100644
index 3ff3015b71a8..000000000000
--- a/include/asm-x86/rwsem.h
+++ /dev/null
@@ -1,265 +0,0 @@
-/* rwsem.h: R/W semaphores implemented using XADD/CMPXCHG for i486+
- *
- * Written by David Howells (dhowells@redhat.com).
- *
- * Derived from asm-x86/semaphore.h
- *
- *
- * The MSW of the count is the negated number of active writers and waiting
- * lockers, and the LSW is the total number of active locks
- *
- * The lock count is initialized to 0 (no active and no waiting lockers).
- *
- * When a writer subtracts WRITE_BIAS, it'll get 0xffff0001 for the case of an
- * uncontended lock. This can be determined because XADD returns the old value.
- * Readers increment by 1 and see a positive value when uncontended, negative
- * if there are writers (and maybe) readers waiting (in which case it goes to
- * sleep).
- *
- * The value of WAITING_BIAS supports up to 32766 waiting processes. This can
- * be extended to 65534 by manually checking the whole MSW rather than relying
- * on the S flag.
- *
- * The value of ACTIVE_BIAS supports up to 65535 active processes.
- *
- * This should be totally fair - if anything is waiting, a process that wants a
- * lock will go to the back of the queue. When the currently active lock is
- * released, if there's a writer at the front of the queue, then that and only
- * that will be woken up; if there's a bunch of consequtive readers at the
- * front, then they'll all be woken up, but no other readers will be.
- */
-
-#ifndef ASM_X86__RWSEM_H
-#define ASM_X86__RWSEM_H
-
-#ifndef _LINUX_RWSEM_H
-#error "please don't include asm/rwsem.h directly, use linux/rwsem.h instead"
-#endif
-
-#ifdef __KERNEL__
-
-#include <linux/list.h>
-#include <linux/spinlock.h>
-#include <linux/lockdep.h>
-
-struct rwsem_waiter;
-
-extern asmregparm struct rw_semaphore *
- rwsem_down_read_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *
- rwsem_down_write_failed(struct rw_semaphore *sem);
-extern asmregparm struct rw_semaphore *
- rwsem_wake(struct rw_semaphore *);
-extern asmregparm struct rw_semaphore *
- rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-/*
- * the semaphore definition
- */
-
-#define RWSEM_UNLOCKED_VALUE		0x00000000
-#define RWSEM_ACTIVE_BIAS		0x00000001
-#define RWSEM_ACTIVE_MASK		0x0000ffff
-#define RWSEM_WAITING_BIAS		(-0x00010000)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-struct rw_semaphore {
-	signed long		count;
-	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
-};
-
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-# define __RWSEM_DEP_MAP_INIT(lockname) , .dep_map = { .name = #lockname }
-#else
-# define __RWSEM_DEP_MAP_INIT(lockname)
-#endif
-
-
-#define __RWSEM_INITIALIZER(name)				\
-{								\
-	RWSEM_UNLOCKED_VALUE, __SPIN_LOCK_UNLOCKED((name).wait_lock), \
-	LIST_HEAD_INIT((name).wait_list) __RWSEM_DEP_MAP_INIT(name) \
-}
-
-#define DECLARE_RWSEM(name)					\
-	struct rw_semaphore name = __RWSEM_INITIALIZER(name)
-
-extern void __init_rwsem(struct rw_semaphore *sem, const char *name,
-			 struct lock_class_key *key);
-
-#define init_rwsem(sem)						\
-do {								\
-	static struct lock_class_key __key;			\
-								\
-	__init_rwsem((sem), #sem, &__key);			\
-} while (0)
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	asm volatile("# beginning down_read\n\t"
-		     LOCK_PREFIX "  incl      (%%eax)\n\t"
-		     /* adds 0x00000001, returns the old value */
-		     "  jns        1f\n"
-		     "  call call_rwsem_down_read_failed\n"
-		     "1:\n\t"
-		     "# ending down_read\n\t"
-		     : "+m" (sem->count)
-		     : "a" (sem)
-		     : "memory", "cc");
-}
-
-/*
- * trylock for reading -- returns 1 if successful, 0 if contention
- */
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	__s32 result, tmp;
-	asm volatile("# beginning __down_read_trylock\n\t"
-		     "  movl      %0,%1\n\t"
-		     "1:\n\t"
-		     "  movl	     %1,%2\n\t"
-		     "  addl      %3,%2\n\t"
-		     "  jle	     2f\n\t"
-		     LOCK_PREFIX "  cmpxchgl  %2,%0\n\t"
-		     "  jnz	     1b\n\t"
-		     "2:\n\t"
-		     "# ending __down_read_trylock\n\t"
-		     : "+m" (sem->count), "=&a" (result), "=&r" (tmp)
-		     : "i" (RWSEM_ACTIVE_READ_BIAS)
-		     : "memory", "cc");
-	return result >= 0 ? 1 : 0;
-}
-
-/*
- * lock for writing
- */
-static inline void __down_write_nested(struct rw_semaphore *sem, int subclass)
-{
-	int tmp;
-
-	tmp = RWSEM_ACTIVE_WRITE_BIAS;
-	asm volatile("# beginning down_write\n\t"
-		     LOCK_PREFIX "  xadd      %%edx,(%%eax)\n\t"
-		     /* subtract 0x0000ffff, returns the old value */
-		     "  testl     %%edx,%%edx\n\t"
-		     /* was the count 0 before? */
-		     "  jz        1f\n"
-		     "  call call_rwsem_down_write_failed\n"
-		     "1:\n"
-		     "# ending down_write"
-		     : "+m" (sem->count), "=d" (tmp)
-		     : "a" (sem), "1" (tmp)
-		     : "memory", "cc");
-}
-
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	__down_write_nested(sem, 0);
-}
-
-/*
- * trylock for writing -- returns 1 if successful, 0 if contention
- */
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
-	signed long ret = cmpxchg(&sem->count,
-				  RWSEM_UNLOCKED_VALUE,
-				  RWSEM_ACTIVE_WRITE_BIAS);
-	if (ret == RWSEM_UNLOCKED_VALUE)
-		return 1;
-	return 0;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	__s32 tmp = -RWSEM_ACTIVE_READ_BIAS;
-	asm volatile("# beginning __up_read\n\t"
-		     LOCK_PREFIX "  xadd      %%edx,(%%eax)\n\t"
-		     /* subtracts 1, returns the old value */
-		     "  jns        1f\n\t"
-		     "  call call_rwsem_wake\n"
-		     "1:\n"
-		     "# ending __up_read\n"
-		     : "+m" (sem->count), "=d" (tmp)
-		     : "a" (sem), "1" (tmp)
-		     : "memory", "cc");
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	asm volatile("# beginning __up_write\n\t"
-		     "  movl      %2,%%edx\n\t"
-		     LOCK_PREFIX "  xaddl     %%edx,(%%eax)\n\t"
-		     /* tries to transition
-			0xffff0001 -> 0x00000000 */
-		     "  jz       1f\n"
-		     "  call call_rwsem_wake\n"
-		     "1:\n\t"
-		     "# ending __up_write\n"
-		     : "+m" (sem->count)
-		     : "a" (sem), "i" (-RWSEM_ACTIVE_WRITE_BIAS)
-		     : "memory", "cc", "edx");
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	asm volatile("# beginning __downgrade_write\n\t"
-		     LOCK_PREFIX "  addl      %2,(%%eax)\n\t"
-		     /* transitions 0xZZZZ0001 -> 0xYYYY0001 */
-		     "  jns       1f\n\t"
-		     "  call call_rwsem_downgrade_wake\n"
-		     "1:\n\t"
-		     "# ending __downgrade_write\n"
-		     : "+m" (sem->count)
-		     : "a" (sem), "i" (-RWSEM_WAITING_BIAS)
-		     : "memory", "cc");
-}
-
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(int delta, struct rw_semaphore *sem)
-{
-	asm volatile(LOCK_PREFIX "addl %1,%0"
-		     : "+m" (sem->count)
-		     : "ir" (delta));
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline int rwsem_atomic_update(int delta, struct rw_semaphore *sem)
-{
-	int tmp = delta;
-
-	asm volatile(LOCK_PREFIX "xadd %0,%1"
-		     : "+r" (tmp), "+m" (sem->count)
-		     : : "memory");
-
-	return tmp + delta;
-}
-
-static inline int rwsem_is_locked(struct rw_semaphore *sem)
-{
-	return (sem->count != 0);
-}
-
-#endif /* __KERNEL__ */
-#endif /* ASM_X86__RWSEM_H */
diff --git a/include/asm-x86/scatterlist.h b/include/asm-x86/scatterlist.h
deleted file mode 100644
index ee48f880005d..000000000000
--- a/include/asm-x86/scatterlist.h
+++ /dev/null
@@ -1,33 +0,0 @@
-#ifndef ASM_X86__SCATTERLIST_H
-#define ASM_X86__SCATTERLIST_H
-
-#include <asm/types.h>
-
-struct scatterlist {
-#ifdef CONFIG_DEBUG_SG
-	unsigned long	sg_magic;
-#endif
-	unsigned long	page_link;
-	unsigned int	offset;
-	unsigned int	length;
-	dma_addr_t	dma_address;
-	unsigned int	dma_length;
-};
-
-#define ARCH_HAS_SG_CHAIN
-#define ISA_DMA_THRESHOLD (0x00ffffff)
-
-/*
- * These macros should be used after a pci_map_sg call has been done
- * to get bus addresses of each of the SG entries and their lengths.
- * You should only work with the number of sg entries pci_map_sg
- * returns.
- */
-#define sg_dma_address(sg)	((sg)->dma_address)
-#ifdef CONFIG_X86_32
-# define sg_dma_len(sg)		((sg)->length)
-#else
-# define sg_dma_len(sg)		((sg)->dma_length)
-#endif
-
-#endif /* ASM_X86__SCATTERLIST_H */
diff --git a/include/asm-x86/seccomp.h b/include/asm-x86/seccomp.h
deleted file mode 100644
index c62e58a5a90d..000000000000
--- a/include/asm-x86/seccomp.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "seccomp_32.h"
-#else
-# include "seccomp_64.h"
-#endif
diff --git a/include/asm-x86/seccomp_32.h b/include/asm-x86/seccomp_32.h
deleted file mode 100644
index cf9ab2dbcef1..000000000000
--- a/include/asm-x86/seccomp_32.h
+++ /dev/null
@@ -1,17 +0,0 @@
-#ifndef ASM_X86__SECCOMP_32_H
-#define ASM_X86__SECCOMP_32_H
-
-#include <linux/thread_info.h>
-
-#ifdef TIF_32BIT
-#error "unexpected TIF_32BIT on i386"
-#endif
-
-#include <linux/unistd.h>
-
-#define __NR_seccomp_read __NR_read
-#define __NR_seccomp_write __NR_write
-#define __NR_seccomp_exit __NR_exit
-#define __NR_seccomp_sigreturn __NR_sigreturn
-
-#endif /* ASM_X86__SECCOMP_32_H */
diff --git a/include/asm-x86/seccomp_64.h b/include/asm-x86/seccomp_64.h
deleted file mode 100644
index 03274cea751f..000000000000
--- a/include/asm-x86/seccomp_64.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef ASM_X86__SECCOMP_64_H
-#define ASM_X86__SECCOMP_64_H
-
-#include <linux/thread_info.h>
-
-#ifdef TIF_32BIT
-#error "unexpected TIF_32BIT on x86_64"
-#else
-#define TIF_32BIT TIF_IA32
-#endif
-
-#include <linux/unistd.h>
-#include <asm/ia32_unistd.h>
-
-#define __NR_seccomp_read __NR_read
-#define __NR_seccomp_write __NR_write
-#define __NR_seccomp_exit __NR_exit
-#define __NR_seccomp_sigreturn __NR_rt_sigreturn
-
-#define __NR_seccomp_read_32 __NR_ia32_read
-#define __NR_seccomp_write_32 __NR_ia32_write
-#define __NR_seccomp_exit_32 __NR_ia32_exit
-#define __NR_seccomp_sigreturn_32 __NR_ia32_sigreturn
-
-#endif /* ASM_X86__SECCOMP_64_H */
diff --git a/include/asm-x86/sections.h b/include/asm-x86/sections.h
deleted file mode 100644
index 2b8c5160388f..000000000000
--- a/include/asm-x86/sections.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/sections.h>
diff --git a/include/asm-x86/segment.h b/include/asm-x86/segment.h
deleted file mode 100644
index 5d6e69454891..000000000000
--- a/include/asm-x86/segment.h
+++ /dev/null
@@ -1,209 +0,0 @@
-#ifndef ASM_X86__SEGMENT_H
-#define ASM_X86__SEGMENT_H
-
-/* Constructor for a conventional segment GDT (or LDT) entry */
-/* This is a macro so it can be used in initializers */
-#define GDT_ENTRY(flags, base, limit)			\
-	((((base)  & 0xff000000ULL) << (56-24)) |	\
-	 (((flags) & 0x0000f0ffULL) << 40) |		\
-	 (((limit) & 0x000f0000ULL) << (48-16)) |	\
-	 (((base)  & 0x00ffffffULL) << 16) |		\
-	 (((limit) & 0x0000ffffULL)))
-
-/* Simple and small GDT entries for booting only */
-
-#define GDT_ENTRY_BOOT_CS	2
-#define __BOOT_CS		(GDT_ENTRY_BOOT_CS * 8)
-
-#define GDT_ENTRY_BOOT_DS	(GDT_ENTRY_BOOT_CS + 1)
-#define __BOOT_DS		(GDT_ENTRY_BOOT_DS * 8)
-
-#define GDT_ENTRY_BOOT_TSS	(GDT_ENTRY_BOOT_CS + 2)
-#define __BOOT_TSS		(GDT_ENTRY_BOOT_TSS * 8)
-
-#ifdef CONFIG_X86_32
-/*
- * The layout of the per-CPU GDT under Linux:
- *
- *   0 - null
- *   1 - reserved
- *   2 - reserved
- *   3 - reserved
- *
- *   4 - unused			<==== new cacheline
- *   5 - unused
- *
- *  ------- start of TLS (Thread-Local Storage) segments:
- *
- *   6 - TLS segment #1			[ glibc's TLS segment ]
- *   7 - TLS segment #2			[ Wine's %fs Win32 segment ]
- *   8 - TLS segment #3
- *   9 - reserved
- *  10 - reserved
- *  11 - reserved
- *
- *  ------- start of kernel segments:
- *
- *  12 - kernel code segment		<==== new cacheline
- *  13 - kernel data segment
- *  14 - default user CS
- *  15 - default user DS
- *  16 - TSS
- *  17 - LDT
- *  18 - PNPBIOS support (16->32 gate)
- *  19 - PNPBIOS support
- *  20 - PNPBIOS support
- *  21 - PNPBIOS support
- *  22 - PNPBIOS support
- *  23 - APM BIOS support
- *  24 - APM BIOS support
- *  25 - APM BIOS support
- *
- *  26 - ESPFIX small SS
- *  27 - per-cpu			[ offset to per-cpu data area ]
- *  28 - unused
- *  29 - unused
- *  30 - unused
- *  31 - TSS for double fault handler
- */
-#define GDT_ENTRY_TLS_MIN	6
-#define GDT_ENTRY_TLS_MAX 	(GDT_ENTRY_TLS_MIN + GDT_ENTRY_TLS_ENTRIES - 1)
-
-#define GDT_ENTRY_DEFAULT_USER_CS	14
-
-#define GDT_ENTRY_DEFAULT_USER_DS	15
-
-#define GDT_ENTRY_KERNEL_BASE	12
-
-#define GDT_ENTRY_KERNEL_CS		(GDT_ENTRY_KERNEL_BASE + 0)
-
-#define GDT_ENTRY_KERNEL_DS		(GDT_ENTRY_KERNEL_BASE + 1)
-
-#define GDT_ENTRY_TSS			(GDT_ENTRY_KERNEL_BASE + 4)
-#define GDT_ENTRY_LDT			(GDT_ENTRY_KERNEL_BASE + 5)
-
-#define GDT_ENTRY_PNPBIOS_BASE		(GDT_ENTRY_KERNEL_BASE + 6)
-#define GDT_ENTRY_APMBIOS_BASE		(GDT_ENTRY_KERNEL_BASE + 11)
-
-#define GDT_ENTRY_ESPFIX_SS		(GDT_ENTRY_KERNEL_BASE + 14)
-#define __ESPFIX_SS (GDT_ENTRY_ESPFIX_SS * 8)
-
-#define GDT_ENTRY_PERCPU			(GDT_ENTRY_KERNEL_BASE + 15)
-#ifdef CONFIG_SMP
-#define __KERNEL_PERCPU (GDT_ENTRY_PERCPU * 8)
-#else
-#define __KERNEL_PERCPU 0
-#endif
-
-#define GDT_ENTRY_DOUBLEFAULT_TSS	31
-
-/*
- * The GDT has 32 entries
- */
-#define GDT_ENTRIES 32
-
-/* The PnP BIOS entries in the GDT */
-#define GDT_ENTRY_PNPBIOS_CS32		(GDT_ENTRY_PNPBIOS_BASE + 0)
-#define GDT_ENTRY_PNPBIOS_CS16		(GDT_ENTRY_PNPBIOS_BASE + 1)
-#define GDT_ENTRY_PNPBIOS_DS		(GDT_ENTRY_PNPBIOS_BASE + 2)
-#define GDT_ENTRY_PNPBIOS_TS1		(GDT_ENTRY_PNPBIOS_BASE + 3)
-#define GDT_ENTRY_PNPBIOS_TS2		(GDT_ENTRY_PNPBIOS_BASE + 4)
-
-/* The PnP BIOS selectors */
-#define PNP_CS32   (GDT_ENTRY_PNPBIOS_CS32 * 8)	/* segment for calling fn */
-#define PNP_CS16   (GDT_ENTRY_PNPBIOS_CS16 * 8)	/* code segment for BIOS */
-#define PNP_DS     (GDT_ENTRY_PNPBIOS_DS * 8)	/* data segment for BIOS */
-#define PNP_TS1    (GDT_ENTRY_PNPBIOS_TS1 * 8)	/* transfer data segment */
-#define PNP_TS2    (GDT_ENTRY_PNPBIOS_TS2 * 8)	/* another data segment */
-
-/* Bottom two bits of selector give the ring privilege level */
-#define SEGMENT_RPL_MASK	0x3
-/* Bit 2 is table indicator (LDT/GDT) */
-#define SEGMENT_TI_MASK		0x4
-
-/* User mode is privilege level 3 */
-#define USER_RPL		0x3
-/* LDT segment has TI set, GDT has it cleared */
-#define SEGMENT_LDT		0x4
-#define SEGMENT_GDT		0x0
-
-/*
- * Matching rules for certain types of segments.
- */
-
-/* Matches PNP_CS32 and PNP_CS16 (they must be consecutive) */
-#define SEGMENT_IS_PNP_CODE(x)   (((x) & 0xf4) == GDT_ENTRY_PNPBIOS_BASE * 8)
-
-
-#else
-#include <asm/cache.h>
-
-#define GDT_ENTRY_KERNEL32_CS 1
-#define GDT_ENTRY_KERNEL_CS 2
-#define GDT_ENTRY_KERNEL_DS 3
-
-#define __KERNEL32_CS   (GDT_ENTRY_KERNEL32_CS * 8)
-
-/*
- * we cannot use the same code segment descriptor for user and kernel
- * -- not even in the long flat mode, because of different DPL /kkeil
- * The segment offset needs to contain a RPL. Grr. -AK
- * GDT layout to get 64bit syscall right (sysret hardcodes gdt offsets)
- */
-#define GDT_ENTRY_DEFAULT_USER32_CS 4
-#define GDT_ENTRY_DEFAULT_USER_DS 5
-#define GDT_ENTRY_DEFAULT_USER_CS 6
-#define __USER32_CS   (GDT_ENTRY_DEFAULT_USER32_CS * 8 + 3)
-#define __USER32_DS	__USER_DS
-
-#define GDT_ENTRY_TSS 8	/* needs two entries */
-#define GDT_ENTRY_LDT 10 /* needs two entries */
-#define GDT_ENTRY_TLS_MIN 12
-#define GDT_ENTRY_TLS_MAX 14
-
-#define GDT_ENTRY_PER_CPU 15	/* Abused to load per CPU data from limit */
-#define __PER_CPU_SEG	(GDT_ENTRY_PER_CPU * 8 + 3)
-
-/* TLS indexes for 64bit - hardcoded in arch_prctl */
-#define FS_TLS 0
-#define GS_TLS 1
-
-#define GS_TLS_SEL ((GDT_ENTRY_TLS_MIN+GS_TLS)*8 + 3)
-#define FS_TLS_SEL ((GDT_ENTRY_TLS_MIN+FS_TLS)*8 + 3)
-
-#define GDT_ENTRIES 16
-
-#endif
-
-#define __KERNEL_CS	(GDT_ENTRY_KERNEL_CS * 8)
-#define __KERNEL_DS	(GDT_ENTRY_KERNEL_DS * 8)
-#define __USER_DS     (GDT_ENTRY_DEFAULT_USER_DS* 8 + 3)
-#define __USER_CS     (GDT_ENTRY_DEFAULT_USER_CS* 8 + 3)
-#ifndef CONFIG_PARAVIRT
-#define get_kernel_rpl()  0
-#endif
-
-/* User mode is privilege level 3 */
-#define USER_RPL		0x3
-/* LDT segment has TI set, GDT has it cleared */
-#define SEGMENT_LDT		0x4
-#define SEGMENT_GDT		0x0
-
-/* Bottom two bits of selector give the ring privilege level */
-#define SEGMENT_RPL_MASK	0x3
-/* Bit 2 is table indicator (LDT/GDT) */
-#define SEGMENT_TI_MASK		0x4
-
-#define IDT_ENTRIES 256
-#define NUM_EXCEPTION_VECTORS 32
-#define GDT_SIZE (GDT_ENTRIES * 8)
-#define GDT_ENTRY_TLS_ENTRIES 3
-#define TLS_SIZE (GDT_ENTRY_TLS_ENTRIES * 8)
-
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
-extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10];
-#endif
-#endif
-
-#endif /* ASM_X86__SEGMENT_H */
diff --git a/include/asm-x86/sembuf.h b/include/asm-x86/sembuf.h
deleted file mode 100644
index 81f06b7e5a3f..000000000000
--- a/include/asm-x86/sembuf.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef ASM_X86__SEMBUF_H
-#define ASM_X86__SEMBUF_H
-
-/*
- * The semid64_ds structure for x86 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- */
-struct semid64_ds {
-	struct ipc64_perm sem_perm;	/* permissions .. see ipc.h */
-	__kernel_time_t	sem_otime;	/* last semop time */
-	unsigned long	__unused1;
-	__kernel_time_t	sem_ctime;	/* last change time */
-	unsigned long	__unused2;
-	unsigned long	sem_nsems;	/* no. of semaphores in array */
-	unsigned long	__unused3;
-	unsigned long	__unused4;
-};
-
-#endif /* ASM_X86__SEMBUF_H */
diff --git a/include/asm-x86/serial.h b/include/asm-x86/serial.h
deleted file mode 100644
index 303660b671e5..000000000000
--- a/include/asm-x86/serial.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef ASM_X86__SERIAL_H
-#define ASM_X86__SERIAL_H
-
-/*
- * This assumes you have a 1.8432 MHz clock for your UART.
- *
- * It'd be nice if someone built a serial card with a 24.576 MHz
- * clock, since the 16550A is capable of handling a top speed of 1.5
- * megabits/second; but this requires the faster clock.
- */
-#define BASE_BAUD ( 1843200 / 16 )
-
-/* Standard COM flags (except for COM4, because of the 8514 problem) */
-#ifdef CONFIG_SERIAL_DETECT_IRQ
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST | ASYNC_AUTO_IRQ)
-#define STD_COM4_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_AUTO_IRQ)
-#else
-#define STD_COM_FLAGS (ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST)
-#define STD_COM4_FLAGS ASYNC_BOOT_AUTOCONF
-#endif
-
-#define SERIAL_PORT_DFNS			\
-	/* UART CLK   PORT IRQ     FLAGS        */			\
-	{ 0, BASE_BAUD, 0x3F8, 4, STD_COM_FLAGS },	/* ttyS0 */	\
-	{ 0, BASE_BAUD, 0x2F8, 3, STD_COM_FLAGS },	/* ttyS1 */	\
-	{ 0, BASE_BAUD, 0x3E8, 4, STD_COM_FLAGS },	/* ttyS2 */	\
-	{ 0, BASE_BAUD, 0x2E8, 3, STD_COM4_FLAGS },	/* ttyS3 */
-
-#endif /* ASM_X86__SERIAL_H */
diff --git a/include/asm-x86/setup.h b/include/asm-x86/setup.h
deleted file mode 100644
index 11b6cc14b289..000000000000
--- a/include/asm-x86/setup.h
+++ /dev/null
@@ -1,105 +0,0 @@
-#ifndef ASM_X86__SETUP_H
-#define ASM_X86__SETUP_H
-
-#define COMMAND_LINE_SIZE 2048
-
-#ifndef __ASSEMBLY__
-
-/* Interrupt control for vSMPowered x86_64 systems */
-void vsmp_init(void);
-
-#ifdef CONFIG_X86_VISWS
-extern void visws_early_detect(void);
-extern int is_visws_box(void);
-#else
-static inline void visws_early_detect(void) { }
-static inline int is_visws_box(void) { return 0; }
-#endif
-
-/*
- * Any setup quirks to be performed?
- */
-struct mpc_config_processor;
-struct mpc_config_bus;
-struct mp_config_oemtable;
-struct x86_quirks {
-	int (*arch_pre_time_init)(void);
-	int (*arch_time_init)(void);
-	int (*arch_pre_intr_init)(void);
-	int (*arch_intr_init)(void);
-	int (*arch_trap_init)(void);
-	char * (*arch_memory_setup)(void);
-	int (*mach_get_smp_config)(unsigned int early);
-	int (*mach_find_smp_config)(unsigned int reserve);
-
-	int *mpc_record;
-	int (*mpc_apic_id)(struct mpc_config_processor *m);
-	void (*mpc_oem_bus_info)(struct mpc_config_bus *m, char *name);
-	void (*mpc_oem_pci_bus)(struct mpc_config_bus *m);
-	void (*smp_read_mpc_oem)(struct mp_config_oemtable *oemtable,
-                                    unsigned short oemsize);
-	int (*setup_ioapic_ids)(void);
-};
-
-extern struct x86_quirks *x86_quirks;
-extern unsigned long saved_video_mode;
-
-#ifndef CONFIG_PARAVIRT
-#define paravirt_post_allocator_init()	do {} while (0)
-#endif
-#endif /* __ASSEMBLY__ */
-
-#ifdef __KERNEL__
-
-#ifdef __i386__
-
-#include <linux/pfn.h>
-/*
- * Reserved space for vmalloc and iomap - defined in asm/page.h
- */
-#define MAXMEM_PFN	PFN_DOWN(MAXMEM)
-#define MAX_NONPAE_PFN	(1 << 20)
-
-#endif /* __i386__ */
-
-#define PARAM_SIZE 4096		/* sizeof(struct boot_params) */
-
-#define OLD_CL_MAGIC		0xA33F
-#define OLD_CL_ADDRESS		0x020	/* Relative to real mode data */
-#define NEW_CL_POINTER		0x228	/* Relative to real mode data */
-
-#ifndef __ASSEMBLY__
-#include <asm/bootparam.h>
-
-#ifndef _SETUP
-
-/*
- * This is set up by the setup-routine at boot-time
- */
-extern struct boot_params boot_params;
-
-/*
- * Do NOT EVER look at the BIOS memory size location.
- * It does not work on many machines.
- */
-#define LOWMEMSIZE()	(0x9f000)
-
-#ifdef __i386__
-
-void __init i386_start_kernel(void);
-extern void probe_roms(void);
-
-extern unsigned long init_pg_tables_start;
-extern unsigned long init_pg_tables_end;
-
-#else
-void __init x86_64_init_pda(void);
-void __init x86_64_start_kernel(char *real_mode);
-void __init x86_64_start_reservations(char *real_mode_data);
-
-#endif /* __i386__ */
-#endif /* _SETUP */
-#endif /* __ASSEMBLY__ */
-#endif  /*  __KERNEL__  */
-
-#endif /* ASM_X86__SETUP_H */
diff --git a/include/asm-x86/shmbuf.h b/include/asm-x86/shmbuf.h
deleted file mode 100644
index f51aec2298e9..000000000000
--- a/include/asm-x86/shmbuf.h
+++ /dev/null
@@ -1,51 +0,0 @@
-#ifndef ASM_X86__SHMBUF_H
-#define ASM_X86__SHMBUF_H
-
-/*
- * The shmid64_ds structure for x86 architecture.
- * Note extra padding because this structure is passed back and forth
- * between kernel and user space.
- *
- * Pad space on 32 bit is left for:
- * - 64-bit time_t to solve y2038 problem
- * - 2 miscellaneous 32-bit values
- *
- * Pad space on 64 bit is left for:
- * - 2 miscellaneous 64-bit values
- */
-
-struct shmid64_ds {
-	struct ipc64_perm	shm_perm;	/* operation perms */
-	size_t			shm_segsz;	/* size of segment (bytes) */
-	__kernel_time_t		shm_atime;	/* last attach time */
-#ifdef __i386__
-	unsigned long		__unused1;
-#endif
-	__kernel_time_t		shm_dtime;	/* last detach time */
-#ifdef __i386__
-	unsigned long		__unused2;
-#endif
-	__kernel_time_t		shm_ctime;	/* last change time */
-#ifdef __i386__
-	unsigned long		__unused3;
-#endif
-	__kernel_pid_t		shm_cpid;	/* pid of creator */
-	__kernel_pid_t		shm_lpid;	/* pid of last operator */
-	unsigned long		shm_nattch;	/* no. of current attaches */
-	unsigned long		__unused4;
-	unsigned long		__unused5;
-};
-
-struct shminfo64 {
-	unsigned long	shmmax;
-	unsigned long	shmmin;
-	unsigned long	shmmni;
-	unsigned long	shmseg;
-	unsigned long	shmall;
-	unsigned long	__unused1;
-	unsigned long	__unused2;
-	unsigned long	__unused3;
-	unsigned long	__unused4;
-};
-
-#endif /* ASM_X86__SHMBUF_H */
diff --git a/include/asm-x86/shmparam.h b/include/asm-x86/shmparam.h
deleted file mode 100644
index a83a1fd96a0e..000000000000
--- a/include/asm-x86/shmparam.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef ASM_X86__SHMPARAM_H
-#define ASM_X86__SHMPARAM_H
-
-#define SHMLBA PAGE_SIZE	 /* attach addr a multiple of this */
-
-#endif /* ASM_X86__SHMPARAM_H */
diff --git a/include/asm-x86/sigcontext.h b/include/asm-x86/sigcontext.h
deleted file mode 100644
index ee813f4fe5d5..000000000000
--- a/include/asm-x86/sigcontext.h
+++ /dev/null
@@ -1,284 +0,0 @@
-#ifndef ASM_X86__SIGCONTEXT_H
-#define ASM_X86__SIGCONTEXT_H
-
-#include <linux/compiler.h>
-#include <asm/types.h>
-
-#define FP_XSTATE_MAGIC1	0x46505853U
-#define FP_XSTATE_MAGIC2	0x46505845U
-#define FP_XSTATE_MAGIC2_SIZE	sizeof(FP_XSTATE_MAGIC2)
-
-/*
- * bytes 464..511 in the current 512byte layout of fxsave/fxrstor frame
- * are reserved for SW usage. On cpu's supporting xsave/xrstor, these bytes
- * are used to extended the fpstate pointer in the sigcontext, which now
- * includes the extended state information along with fpstate information.
- *
- * Presence of FP_XSTATE_MAGIC1 at the beginning of this SW reserved
- * area and FP_XSTATE_MAGIC2 at the end of memory layout
- * (extended_size - FP_XSTATE_MAGIC2_SIZE) indicates the presence of the
- * extended state information in the memory layout pointed by the fpstate
- * pointer in sigcontext.
- */
-struct _fpx_sw_bytes {
-	__u32 magic1;		/* FP_XSTATE_MAGIC1 */
-	__u32 extended_size;	/* total size of the layout referred by
-				 * fpstate pointer in the sigcontext.
-				 */
-	__u64 xstate_bv;
-				/* feature bit mask (including fp/sse/extended
-				 * state) that is present in the memory
-				 * layout.
-				 */
-	__u32 xstate_size;	/* actual xsave state size, based on the
-				 * features saved in the layout.
-				 * 'extended_size' will be greater than
-				 * 'xstate_size'.
-				 */
-	__u32 padding[7];	/*  for future use. */
-};
-
-#ifdef __i386__
-/*
- * As documented in the iBCS2 standard..
- *
- * The first part of "struct _fpstate" is just the normal i387
- * hardware setup, the extra "status" word is used to save the
- * coprocessor status word before entering the handler.
- *
- * Pentium III FXSR, SSE support
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- *
- * The FPU state data structure has had to grow to accommodate the
- * extended FPU state required by the Streaming SIMD Extensions.
- * There is no documented standard to accomplish this at the moment.
- */
-struct _fpreg {
-	unsigned short significand[4];
-	unsigned short exponent;
-};
-
-struct _fpxreg {
-	unsigned short significand[4];
-	unsigned short exponent;
-	unsigned short padding[3];
-};
-
-struct _xmmreg {
-	unsigned long element[4];
-};
-
-struct _fpstate {
-	/* Regular FPU environment */
-	unsigned long	cw;
-	unsigned long	sw;
-	unsigned long	tag;
-	unsigned long	ipoff;
-	unsigned long	cssel;
-	unsigned long	dataoff;
-	unsigned long	datasel;
-	struct _fpreg	_st[8];
-	unsigned short	status;
-	unsigned short	magic;		/* 0xffff = regular FPU data only */
-
-	/* FXSR FPU environment */
-	unsigned long	_fxsr_env[6];	/* FXSR FPU env is ignored */
-	unsigned long	mxcsr;
-	unsigned long	reserved;
-	struct _fpxreg	_fxsr_st[8];	/* FXSR FPU reg data is ignored */
-	struct _xmmreg	_xmm[8];
-	unsigned long	padding1[44];
-
-	union {
-		unsigned long	padding2[12];
-		struct _fpx_sw_bytes sw_reserved; /* represents the extended
-						   * state info */
-	};
-};
-
-#define X86_FXSR_MAGIC		0x0000
-
-#ifdef __KERNEL__
-struct sigcontext {
-	unsigned short gs, __gsh;
-	unsigned short fs, __fsh;
-	unsigned short es, __esh;
-	unsigned short ds, __dsh;
-	unsigned long di;
-	unsigned long si;
-	unsigned long bp;
-	unsigned long sp;
-	unsigned long bx;
-	unsigned long dx;
-	unsigned long cx;
-	unsigned long ax;
-	unsigned long trapno;
-	unsigned long err;
-	unsigned long ip;
-	unsigned short cs, __csh;
-	unsigned long flags;
-	unsigned long sp_at_signal;
-	unsigned short ss, __ssh;
-
-	/*
-	 * fpstate is really (struct _fpstate *) or (struct _xstate *)
-	 * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
-	 * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
-	 * of extended memory layout. See comments at the defintion of
-	 * (struct _fpx_sw_bytes)
-	 */
-	void __user *fpstate;		/* zero when no FPU/extended context */
-	unsigned long oldmask;
-	unsigned long cr2;
-};
-#else /* __KERNEL__ */
-/*
- * User-space might still rely on the old definition:
- */
-struct sigcontext {
-	unsigned short gs, __gsh;
-	unsigned short fs, __fsh;
-	unsigned short es, __esh;
-	unsigned short ds, __dsh;
-	unsigned long edi;
-	unsigned long esi;
-	unsigned long ebp;
-	unsigned long esp;
-	unsigned long ebx;
-	unsigned long edx;
-	unsigned long ecx;
-	unsigned long eax;
-	unsigned long trapno;
-	unsigned long err;
-	unsigned long eip;
-	unsigned short cs, __csh;
-	unsigned long eflags;
-	unsigned long esp_at_signal;
-	unsigned short ss, __ssh;
-	struct _fpstate __user *fpstate;
-	unsigned long oldmask;
-	unsigned long cr2;
-};
-#endif /* !__KERNEL__ */
-
-#else /* __i386__ */
-
-/* FXSAVE frame */
-/* Note: reserved1/2 may someday contain valuable data. Always save/restore
-   them when you change signal frames. */
-struct _fpstate {
-	__u16	cwd;
-	__u16	swd;
-	__u16	twd;		/* Note this is not the same as the
-				   32bit/x87/FSAVE twd */
-	__u16	fop;
-	__u64	rip;
-	__u64	rdp;
-	__u32	mxcsr;
-	__u32	mxcsr_mask;
-	__u32	st_space[32];	/* 8*16 bytes for each FP-reg */
-	__u32	xmm_space[64];	/* 16*16 bytes for each XMM-reg  */
-	__u32	reserved2[12];
-	union {
-		__u32	reserved3[12];
-		struct _fpx_sw_bytes sw_reserved; /* represents the extended
-						   * state information */
-	};
-};
-
-#ifdef __KERNEL__
-struct sigcontext {
-	unsigned long r8;
-	unsigned long r9;
-	unsigned long r10;
-	unsigned long r11;
-	unsigned long r12;
-	unsigned long r13;
-	unsigned long r14;
-	unsigned long r15;
-	unsigned long di;
-	unsigned long si;
-	unsigned long bp;
-	unsigned long bx;
-	unsigned long dx;
-	unsigned long ax;
-	unsigned long cx;
-	unsigned long sp;
-	unsigned long ip;
-	unsigned long flags;
-	unsigned short cs;
-	unsigned short gs;
-	unsigned short fs;
-	unsigned short __pad0;
-	unsigned long err;
-	unsigned long trapno;
-	unsigned long oldmask;
-	unsigned long cr2;
-
-	/*
-	 * fpstate is really (struct _fpstate *) or (struct _xstate *)
-	 * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
-	 * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
-	 * of extended memory layout. See comments at the defintion of
-	 * (struct _fpx_sw_bytes)
-	 */
-	void __user *fpstate;		/* zero when no FPU/extended context */
-	unsigned long reserved1[8];
-};
-#else /* __KERNEL__ */
-/*
- * User-space might still rely on the old definition:
- */
-struct sigcontext {
-	unsigned long r8;
-	unsigned long r9;
-	unsigned long r10;
-	unsigned long r11;
-	unsigned long r12;
-	unsigned long r13;
-	unsigned long r14;
-	unsigned long r15;
-	unsigned long rdi;
-	unsigned long rsi;
-	unsigned long rbp;
-	unsigned long rbx;
-	unsigned long rdx;
-	unsigned long rax;
-	unsigned long rcx;
-	unsigned long rsp;
-	unsigned long rip;
-	unsigned long eflags;		/* RFLAGS */
-	unsigned short cs;
-	unsigned short gs;
-	unsigned short fs;
-	unsigned short __pad0;
-	unsigned long err;
-	unsigned long trapno;
-	unsigned long oldmask;
-	unsigned long cr2;
-	struct _fpstate __user *fpstate;	/* zero when no FPU context */
-	unsigned long reserved1[8];
-};
-#endif /* !__KERNEL__ */
-
-#endif /* !__i386__ */
-
-struct _xsave_hdr {
-	__u64 xstate_bv;
-	__u64 reserved1[2];
-	__u64 reserved2[5];
-};
-
-/*
- * Extended state pointed by the fpstate pointer in the sigcontext.
- * In addition to the fpstate, information encoded in the xstate_hdr
- * indicates the presence of other extended state information
- * supported by the processor and OS.
- */
-struct _xstate {
-	struct _fpstate fpstate;
-	struct _xsave_hdr xstate_hdr;
-	/* new processor state extensions go here */
-};
-
-#endif /* ASM_X86__SIGCONTEXT_H */
diff --git a/include/asm-x86/sigcontext32.h b/include/asm-x86/sigcontext32.h
deleted file mode 100644
index 8c347032c2f2..000000000000
--- a/include/asm-x86/sigcontext32.h
+++ /dev/null
@@ -1,75 +0,0 @@
-#ifndef ASM_X86__SIGCONTEXT32_H
-#define ASM_X86__SIGCONTEXT32_H
-
-/* signal context for 32bit programs. */
-
-#define X86_FXSR_MAGIC		0x0000
-
-struct _fpreg {
-	unsigned short significand[4];
-	unsigned short exponent;
-};
-
-struct _fpxreg {
-	unsigned short significand[4];
-	unsigned short exponent;
-	unsigned short padding[3];
-};
-
-struct _xmmreg {
-	__u32	element[4];
-};
-
-/* FSAVE frame with extensions */
-struct _fpstate_ia32 {
-	/* Regular FPU environment */
-	__u32 	cw;
-	__u32	sw;
-	__u32	tag;	/* not compatible to 64bit twd */
-	__u32	ipoff;
-	__u32	cssel;
-	__u32	dataoff;
-	__u32	datasel;
-	struct _fpreg	_st[8];
-	unsigned short	status;
-	unsigned short	magic;		/* 0xffff = regular FPU data only */
-
-	/* FXSR FPU environment */
-	__u32	_fxsr_env[6];
-	__u32	mxcsr;
-	__u32	reserved;
-	struct _fpxreg	_fxsr_st[8];
-	struct _xmmreg	_xmm[8];	/* It's actually 16 */
-	__u32	padding[44];
-	union {
-		__u32 padding2[12];
-		struct _fpx_sw_bytes sw_reserved;
-	};
-};
-
-struct sigcontext_ia32 {
-       unsigned short gs, __gsh;
-       unsigned short fs, __fsh;
-       unsigned short es, __esh;
-       unsigned short ds, __dsh;
-       unsigned int di;
-       unsigned int si;
-       unsigned int bp;
-       unsigned int sp;
-       unsigned int bx;
-       unsigned int dx;
-       unsigned int cx;
-       unsigned int ax;
-       unsigned int trapno;
-       unsigned int err;
-       unsigned int ip;
-       unsigned short cs, __csh;
-       unsigned int flags;
-       unsigned int sp_at_signal;
-       unsigned short ss, __ssh;
-       unsigned int fpstate;		/* really (struct _fpstate_ia32 *) */
-       unsigned int oldmask;
-       unsigned int cr2;
-};
-
-#endif /* ASM_X86__SIGCONTEXT32_H */
diff --git a/include/asm-x86/siginfo.h b/include/asm-x86/siginfo.h
deleted file mode 100644
index 808bdfb2958c..000000000000
--- a/include/asm-x86/siginfo.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef ASM_X86__SIGINFO_H
-#define ASM_X86__SIGINFO_H
-
-#ifdef __x86_64__
-# define __ARCH_SI_PREAMBLE_SIZE	(4 * sizeof(int))
-#endif
-
-#include <asm-generic/siginfo.h>
-
-#endif /* ASM_X86__SIGINFO_H */
diff --git a/include/asm-x86/signal.h b/include/asm-x86/signal.h
deleted file mode 100644
index 65acc82d267a..000000000000
--- a/include/asm-x86/signal.h
+++ /dev/null
@@ -1,262 +0,0 @@
-#ifndef ASM_X86__SIGNAL_H
-#define ASM_X86__SIGNAL_H
-
-#ifndef __ASSEMBLY__
-#include <linux/types.h>
-#include <linux/time.h>
-#include <linux/compiler.h>
-
-/* Avoid too many header ordering problems.  */
-struct siginfo;
-
-#ifdef __KERNEL__
-#include <linux/linkage.h>
-
-/* Most things should be clean enough to redefine this at will, if care
-   is taken to make libc match.  */
-
-#define _NSIG		64
-
-#ifdef __i386__
-# define _NSIG_BPW	32
-#else
-# define _NSIG_BPW	64
-#endif
-
-#define _NSIG_WORDS	(_NSIG / _NSIG_BPW)
-
-typedef unsigned long old_sigset_t;		/* at least 32 bits */
-
-typedef struct {
-	unsigned long sig[_NSIG_WORDS];
-} sigset_t;
-
-#else
-/* Here we must cater to libcs that poke about in kernel headers.  */
-
-#define NSIG		32
-typedef unsigned long sigset_t;
-
-#endif /* __KERNEL__ */
-#endif /* __ASSEMBLY__ */
-
-#define SIGHUP		 1
-#define SIGINT		 2
-#define SIGQUIT		 3
-#define SIGILL		 4
-#define SIGTRAP		 5
-#define SIGABRT		 6
-#define SIGIOT		 6
-#define SIGBUS		 7
-#define SIGFPE		 8
-#define SIGKILL		 9
-#define SIGUSR1		10
-#define SIGSEGV		11
-#define SIGUSR2		12
-#define SIGPIPE		13
-#define SIGALRM		14
-#define SIGTERM		15
-#define SIGSTKFLT	16
-#define SIGCHLD		17
-#define SIGCONT		18
-#define SIGSTOP		19
-#define SIGTSTP		20
-#define SIGTTIN		21
-#define SIGTTOU		22
-#define SIGURG		23
-#define SIGXCPU		24
-#define SIGXFSZ		25
-#define SIGVTALRM	26
-#define SIGPROF		27
-#define SIGWINCH	28
-#define SIGIO		29
-#define SIGPOLL		SIGIO
-/*
-#define SIGLOST		29
-*/
-#define SIGPWR		30
-#define SIGSYS		31
-#define	SIGUNUSED	31
-
-/* These should not be considered constants from userland.  */
-#define SIGRTMIN	32
-#define SIGRTMAX	_NSIG
-
-/*
- * SA_FLAGS values:
- *
- * SA_ONSTACK indicates that a registered stack_t will be used.
- * SA_RESTART flag to get restarting signals (which were the default long ago)
- * SA_NOCLDSTOP flag to turn off SIGCHLD when children stop.
- * SA_RESETHAND clears the handler when the signal is delivered.
- * SA_NOCLDWAIT flag on SIGCHLD to inhibit zombies.
- * SA_NODEFER prevents the current signal from being masked in the handler.
- *
- * SA_ONESHOT and SA_NOMASK are the historical Linux names for the Single
- * Unix names RESETHAND and NODEFER respectively.
- */
-#define SA_NOCLDSTOP	0x00000001u
-#define SA_NOCLDWAIT	0x00000002u
-#define SA_SIGINFO	0x00000004u
-#define SA_ONSTACK	0x08000000u
-#define SA_RESTART	0x10000000u
-#define SA_NODEFER	0x40000000u
-#define SA_RESETHAND	0x80000000u
-
-#define SA_NOMASK	SA_NODEFER
-#define SA_ONESHOT	SA_RESETHAND
-
-#define SA_RESTORER	0x04000000
-
-/*
- * sigaltstack controls
- */
-#define SS_ONSTACK	1
-#define SS_DISABLE	2
-
-#define MINSIGSTKSZ	2048
-#define SIGSTKSZ	8192
-
-#include <asm-generic/signal.h>
-
-#ifndef __ASSEMBLY__
-
-#ifdef __i386__
-# ifdef __KERNEL__
-struct old_sigaction {
-	__sighandler_t sa_handler;
-	old_sigset_t sa_mask;
-	unsigned long sa_flags;
-	__sigrestore_t sa_restorer;
-};
-
-struct sigaction {
-	__sighandler_t sa_handler;
-	unsigned long sa_flags;
-	__sigrestore_t sa_restorer;
-	sigset_t sa_mask;		/* mask last for extensibility */
-};
-
-struct k_sigaction {
-	struct sigaction sa;
-};
-
-extern void do_notify_resume(struct pt_regs *, void *, __u32);
-
-# else /* __KERNEL__ */
-/* Here we must cater to libcs that poke about in kernel headers.  */
-
-struct sigaction {
-	union {
-	  __sighandler_t _sa_handler;
-	  void (*_sa_sigaction)(int, struct siginfo *, void *);
-	} _u;
-	sigset_t sa_mask;
-	unsigned long sa_flags;
-	void (*sa_restorer)(void);
-};
-
-#define sa_handler	_u._sa_handler
-#define sa_sigaction	_u._sa_sigaction
-
-# endif /* ! __KERNEL__ */
-#else /* __i386__ */
-
-struct sigaction {
-	__sighandler_t sa_handler;
-	unsigned long sa_flags;
-	__sigrestore_t sa_restorer;
-	sigset_t sa_mask;		/* mask last for extensibility */
-};
-
-struct k_sigaction {
-	struct sigaction sa;
-};
-
-#endif /* !__i386__ */
-
-typedef struct sigaltstack {
-	void __user *ss_sp;
-	int ss_flags;
-	size_t ss_size;
-} stack_t;
-
-#ifdef __KERNEL__
-#include <asm/sigcontext.h>
-
-#ifdef __i386__
-
-#define __HAVE_ARCH_SIG_BITOPS
-
-#define sigaddset(set,sig)		    \
-	(__builtin_constant_p(sig)	    \
-	 ? __const_sigaddset((set), (sig))  \
-	 : __gen_sigaddset((set), (sig)))
-
-static inline void __gen_sigaddset(sigset_t *set, int _sig)
-{
-	asm("btsl %1,%0" : "+m"(*set) : "Ir"(_sig - 1) : "cc");
-}
-
-static inline void __const_sigaddset(sigset_t *set, int _sig)
-{
-	unsigned long sig = _sig - 1;
-	set->sig[sig / _NSIG_BPW] |= 1 << (sig % _NSIG_BPW);
-}
-
-#define sigdelset(set, sig)		    \
-	(__builtin_constant_p(sig)	    \
-	 ? __const_sigdelset((set), (sig))  \
-	 : __gen_sigdelset((set), (sig)))
-
-
-static inline void __gen_sigdelset(sigset_t *set, int _sig)
-{
-	asm("btrl %1,%0" : "+m"(*set) : "Ir"(_sig - 1) : "cc");
-}
-
-static inline void __const_sigdelset(sigset_t *set, int _sig)
-{
-	unsigned long sig = _sig - 1;
-	set->sig[sig / _NSIG_BPW] &= ~(1 << (sig % _NSIG_BPW));
-}
-
-static inline int __const_sigismember(sigset_t *set, int _sig)
-{
-	unsigned long sig = _sig - 1;
-	return 1 & (set->sig[sig / _NSIG_BPW] >> (sig % _NSIG_BPW));
-}
-
-static inline int __gen_sigismember(sigset_t *set, int _sig)
-{
-	int ret;
-	asm("btl %2,%1\n\tsbbl %0,%0"
-	    : "=r"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
-	return ret;
-}
-
-#define sigismember(set, sig)			\
-	(__builtin_constant_p(sig)		\
-	 ? __const_sigismember((set), (sig))	\
-	 : __gen_sigismember((set), (sig)))
-
-static inline int sigfindinword(unsigned long word)
-{
-	asm("bsfl %1,%0" : "=r"(word) : "rm"(word) : "cc");
-	return word;
-}
-
-struct pt_regs;
-
-#else /* __i386__ */
-
-#undef __HAVE_ARCH_SIG_BITOPS
-
-#endif /* !__i386__ */
-
-#define ptrace_signal_deliver(regs, cookie) do { } while (0)
-
-#endif /* __KERNEL__ */
-#endif /* __ASSEMBLY__ */
-
-#endif /* ASM_X86__SIGNAL_H */
diff --git a/include/asm-x86/smp.h b/include/asm-x86/smp.h
deleted file mode 100644
index a6afc29f2dd9..000000000000
--- a/include/asm-x86/smp.h
+++ /dev/null
@@ -1,229 +0,0 @@
-#ifndef ASM_X86__SMP_H
-#define ASM_X86__SMP_H
-#ifndef __ASSEMBLY__
-#include <linux/cpumask.h>
-#include <linux/init.h>
-#include <asm/percpu.h>
-
-/*
- * We need the APIC definitions automatically as part of 'smp.h'
- */
-#ifdef CONFIG_X86_LOCAL_APIC
-# include <asm/mpspec.h>
-# include <asm/apic.h>
-# ifdef CONFIG_X86_IO_APIC
-#  include <asm/io_apic.h>
-# endif
-#endif
-#include <asm/pda.h>
-#include <asm/thread_info.h>
-
-extern cpumask_t cpu_callout_map;
-extern cpumask_t cpu_initialized;
-extern cpumask_t cpu_callin_map;
-
-extern void (*mtrr_hook)(void);
-extern void zap_low_mappings(void);
-
-extern int __cpuinit get_local_pda(int cpu);
-
-extern int smp_num_siblings;
-extern unsigned int num_processors;
-extern cpumask_t cpu_initialized;
-
-DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
-DECLARE_PER_CPU(cpumask_t, cpu_core_map);
-DECLARE_PER_CPU(u16, cpu_llc_id);
-#ifdef CONFIG_X86_32
-DECLARE_PER_CPU(int, cpu_number);
-#endif
-
-DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
-DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
-
-/* Static state in head.S used to set up a CPU */
-extern struct {
-	void *sp;
-	unsigned short ss;
-} stack_start;
-
-struct smp_ops {
-	void (*smp_prepare_boot_cpu)(void);
-	void (*smp_prepare_cpus)(unsigned max_cpus);
-	void (*smp_cpus_done)(unsigned max_cpus);
-
-	void (*smp_send_stop)(void);
-	void (*smp_send_reschedule)(int cpu);
-
-	int (*cpu_up)(unsigned cpu);
-	int (*cpu_disable)(void);
-	void (*cpu_die)(unsigned int cpu);
-	void (*play_dead)(void);
-
-	void (*send_call_func_ipi)(cpumask_t mask);
-	void (*send_call_func_single_ipi)(int cpu);
-};
-
-/* Globals due to paravirt */
-extern void set_cpu_sibling_map(int cpu);
-
-#ifdef CONFIG_SMP
-#ifndef CONFIG_PARAVIRT
-#define startup_ipi_hook(phys_apicid, start_eip, start_esp) do { } while (0)
-#endif
-extern struct smp_ops smp_ops;
-
-static inline void smp_send_stop(void)
-{
-	smp_ops.smp_send_stop();
-}
-
-static inline void smp_prepare_boot_cpu(void)
-{
-	smp_ops.smp_prepare_boot_cpu();
-}
-
-static inline void smp_prepare_cpus(unsigned int max_cpus)
-{
-	smp_ops.smp_prepare_cpus(max_cpus);
-}
-
-static inline void smp_cpus_done(unsigned int max_cpus)
-{
-	smp_ops.smp_cpus_done(max_cpus);
-}
-
-static inline int __cpu_up(unsigned int cpu)
-{
-	return smp_ops.cpu_up(cpu);
-}
-
-static inline int __cpu_disable(void)
-{
-	return smp_ops.cpu_disable();
-}
-
-static inline void __cpu_die(unsigned int cpu)
-{
-	smp_ops.cpu_die(cpu);
-}
-
-static inline void play_dead(void)
-{
-	smp_ops.play_dead();
-}
-
-static inline void smp_send_reschedule(int cpu)
-{
-	smp_ops.smp_send_reschedule(cpu);
-}
-
-static inline void arch_send_call_function_single_ipi(int cpu)
-{
-	smp_ops.send_call_func_single_ipi(cpu);
-}
-
-static inline void arch_send_call_function_ipi(cpumask_t mask)
-{
-	smp_ops.send_call_func_ipi(mask);
-}
-
-void cpu_disable_common(void);
-void native_smp_prepare_boot_cpu(void);
-void native_smp_prepare_cpus(unsigned int max_cpus);
-void native_smp_cpus_done(unsigned int max_cpus);
-int native_cpu_up(unsigned int cpunum);
-int native_cpu_disable(void);
-void native_cpu_die(unsigned int cpu);
-void native_play_dead(void);
-void play_dead_common(void);
-
-void native_send_call_func_ipi(cpumask_t mask);
-void native_send_call_func_single_ipi(int cpu);
-
-extern void prefill_possible_map(void);
-
-void smp_store_cpu_info(int id);
-#define cpu_physical_id(cpu)	per_cpu(x86_cpu_to_apicid, cpu)
-
-/* We don't mark CPUs online until __cpu_up(), so we need another measure */
-static inline int num_booting_cpus(void)
-{
-	return cpus_weight(cpu_callout_map);
-}
-#else
-static inline void prefill_possible_map(void)
-{
-}
-#endif /* CONFIG_SMP */
-
-extern unsigned disabled_cpus __cpuinitdata;
-
-#ifdef CONFIG_X86_32_SMP
-/*
- * This function is needed by all SMP systems. It must _always_ be valid
- * from the initial startup. We map APIC_BASE very early in page_setup(),
- * so this is correct in the x86 case.
- */
-#define raw_smp_processor_id() (x86_read_percpu(cpu_number))
-extern int safe_smp_processor_id(void);
-
-#elif defined(CONFIG_X86_64_SMP)
-#define raw_smp_processor_id()	read_pda(cpunumber)
-
-#define stack_smp_processor_id()					\
-({								\
-	struct thread_info *ti;						\
-	__asm__("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK));	\
-	ti->cpu;							\
-})
-#define safe_smp_processor_id()		smp_processor_id()
-
-#else /* !CONFIG_X86_32_SMP && !CONFIG_X86_64_SMP */
-#define cpu_physical_id(cpu)		boot_cpu_physical_apicid
-#define safe_smp_processor_id()		0
-#define stack_smp_processor_id() 	0
-#endif
-
-#ifdef CONFIG_X86_LOCAL_APIC
-
-#ifndef CONFIG_X86_64
-static inline int logical_smp_processor_id(void)
-{
-	/* we don't want to mark this access volatile - bad code generation */
-	return GET_APIC_LOGICAL_ID(*(u32 *)(APIC_BASE + APIC_LDR));
-}
-
-#include <mach_apicdef.h>
-static inline unsigned int read_apic_id(void)
-{
-	unsigned int reg;
-
-	reg = *(u32 *)(APIC_BASE + APIC_ID);
-
-	return GET_APIC_ID(reg);
-}
-#endif
-
-
-# if defined(APIC_DEFINITION) || defined(CONFIG_X86_64)
-extern int hard_smp_processor_id(void);
-# else
-#include <mach_apicdef.h>
-static inline int hard_smp_processor_id(void)
-{
-	/* we don't want to mark this access volatile - bad code generation */
-	return read_apic_id();
-}
-# endif /* APIC_DEFINITION */
-
-#else /* CONFIG_X86_LOCAL_APIC */
-
-# ifndef CONFIG_SMP
-#  define hard_smp_processor_id()	0
-# endif
-
-#endif /* CONFIG_X86_LOCAL_APIC */
-
-#endif /* __ASSEMBLY__ */
-#endif /* ASM_X86__SMP_H */
diff --git a/include/asm-x86/socket.h b/include/asm-x86/socket.h
deleted file mode 100644
index db73274c83c3..000000000000
--- a/include/asm-x86/socket.h
+++ /dev/null
@@ -1,57 +0,0 @@
-#ifndef ASM_X86__SOCKET_H
-#define ASM_X86__SOCKET_H
-
-#include <asm/sockios.h>
-
-/* For setsockopt(2) */
-#define SOL_SOCKET	1
-
-#define SO_DEBUG	1
-#define SO_REUSEADDR	2
-#define SO_TYPE		3
-#define SO_ERROR	4
-#define SO_DONTROUTE	5
-#define SO_BROADCAST	6
-#define SO_SNDBUF	7
-#define SO_RCVBUF	8
-#define SO_SNDBUFFORCE	32
-#define SO_RCVBUFFORCE	33
-#define SO_KEEPALIVE	9
-#define SO_OOBINLINE	10
-#define SO_NO_CHECK	11
-#define SO_PRIORITY	12
-#define SO_LINGER	13
-#define SO_BSDCOMPAT	14
-/* To add :#define SO_REUSEPORT 15 */
-#define SO_PASSCRED	16
-#define SO_PEERCRED	17
-#define SO_RCVLOWAT	18
-#define SO_SNDLOWAT	19
-#define SO_RCVTIMEO	20
-#define SO_SNDTIMEO	21
-
-/* Security levels - as per NRL IPv6 - don't actually do anything */
-#define SO_SECURITY_AUTHENTICATION		22
-#define SO_SECURITY_ENCRYPTION_TRANSPORT	23
-#define SO_SECURITY_ENCRYPTION_NETWORK		24
-
-#define SO_BINDTODEVICE	25
-
-/* Socket filtering */
-#define SO_ATTACH_FILTER        26
-#define SO_DETACH_FILTER        27
-
-#define SO_PEERNAME		28
-#define SO_TIMESTAMP		29
-#define SCM_TIMESTAMP		SO_TIMESTAMP
-
-#define SO_ACCEPTCONN		30
-
-#define SO_PEERSEC		31
-#define SO_PASSSEC		34
-#define SO_TIMESTAMPNS		35
-#define SCM_TIMESTAMPNS		SO_TIMESTAMPNS
-
-#define SO_MARK			36
-
-#endif /* ASM_X86__SOCKET_H */
diff --git a/include/asm-x86/sockios.h b/include/asm-x86/sockios.h
deleted file mode 100644
index a006704fdc84..000000000000
--- a/include/asm-x86/sockios.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef ASM_X86__SOCKIOS_H
-#define ASM_X86__SOCKIOS_H
-
-/* Socket-level I/O control calls. */
-#define FIOSETOWN	0x8901
-#define SIOCSPGRP	0x8902
-#define FIOGETOWN	0x8903
-#define SIOCGPGRP	0x8904
-#define SIOCATMARK	0x8905
-#define SIOCGSTAMP	0x8906		/* Get stamp (timeval) */
-#define SIOCGSTAMPNS	0x8907		/* Get stamp (timespec) */
-
-#endif /* ASM_X86__SOCKIOS_H */
diff --git a/include/asm-x86/sparsemem.h b/include/asm-x86/sparsemem.h
deleted file mode 100644
index 38f8e6bc3186..000000000000
--- a/include/asm-x86/sparsemem.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef ASM_X86__SPARSEMEM_H
-#define ASM_X86__SPARSEMEM_H
-
-#ifdef CONFIG_SPARSEMEM
-/*
- * generic non-linear memory support:
- *
- * 1) we will not split memory into more chunks than will fit into the flags
- *    field of the struct page
- *
- * SECTION_SIZE_BITS		2^n: size of each section
- * MAX_PHYSADDR_BITS		2^n: max size of physical address space
- * MAX_PHYSMEM_BITS		2^n: how much memory we can have in that space
- *
- */
-
-#ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_PAE
-#  define SECTION_SIZE_BITS	29
-#  define MAX_PHYSADDR_BITS	36
-#  define MAX_PHYSMEM_BITS	36
-# else
-#  define SECTION_SIZE_BITS	26
-#  define MAX_PHYSADDR_BITS	32
-#  define MAX_PHYSMEM_BITS	32
-# endif
-#else /* CONFIG_X86_32 */
-# define SECTION_SIZE_BITS	27 /* matt - 128 is convenient right now */
-# define MAX_PHYSADDR_BITS	44
-# define MAX_PHYSMEM_BITS	44
-#endif
-
-#endif /* CONFIG_SPARSEMEM */
-#endif /* ASM_X86__SPARSEMEM_H */
diff --git a/include/asm-x86/spinlock.h b/include/asm-x86/spinlock.h
deleted file mode 100644
index 157ff7fab97a..000000000000
--- a/include/asm-x86/spinlock.h
+++ /dev/null
@@ -1,364 +0,0 @@
-#ifndef ASM_X86__SPINLOCK_H
-#define ASM_X86__SPINLOCK_H
-
-#include <asm/atomic.h>
-#include <asm/rwlock.h>
-#include <asm/page.h>
-#include <asm/processor.h>
-#include <linux/compiler.h>
-#include <asm/paravirt.h>
-/*
- * Your basic SMP spinlocks, allowing only a single CPU anywhere
- *
- * Simple spin lock operations.  There are two variants, one clears IRQ's
- * on the local processor, one does not.
- *
- * These are fair FIFO ticket locks, which are currently limited to 256
- * CPUs.
- *
- * (the type definitions are in asm/spinlock_types.h)
- */
-
-#ifdef CONFIG_X86_32
-# define LOCK_PTR_REG "a"
-# define REG_PTR_MODE "k"
-#else
-# define LOCK_PTR_REG "D"
-# define REG_PTR_MODE "q"
-#endif
-
-#if defined(CONFIG_X86_32) && \
-	(defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE))
-/*
- * On PPro SMP or if we are using OOSTORE, we use a locked operation to unlock
- * (PPro errata 66, 92)
- */
-# define UNLOCK_LOCK_PREFIX LOCK_PREFIX
-#else
-# define UNLOCK_LOCK_PREFIX
-#endif
-
-/*
- * Ticket locks are conceptually two parts, one indicating the current head of
- * the queue, and the other indicating the current tail. The lock is acquired
- * by atomically noting the tail and incrementing it by one (thus adding
- * ourself to the queue and noting our position), then waiting until the head
- * becomes equal to the the initial value of the tail.
- *
- * We use an xadd covering *both* parts of the lock, to increment the tail and
- * also load the position of the head, which takes care of memory ordering
- * issues and should be optimal for the uncontended case. Note the tail must be
- * in the high part, because a wide xadd increment of the low part would carry
- * up and contaminate the high part.
- *
- * With fewer than 2^8 possible CPUs, we can use x86's partial registers to
- * save some instructions and make the code more elegant. There really isn't
- * much between them in performance though, especially as locks are out of line.
- */
-#if (NR_CPUS < 256)
-#define TICKET_SHIFT 8
-
-static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
-{
-	short inc = 0x0100;
-
-	asm volatile (
-		LOCK_PREFIX "xaddw %w0, %1\n"
-		"1:\t"
-		"cmpb %h0, %b0\n\t"
-		"je 2f\n\t"
-		"rep ; nop\n\t"
-		"movb %1, %b0\n\t"
-		/* don't need lfence here, because loads are in-order */
-		"jmp 1b\n"
-		"2:"
-		: "+Q" (inc), "+m" (lock->slock)
-		:
-		: "memory", "cc");
-}
-
-static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
-{
-	int tmp, new;
-
-	asm volatile("movzwl %2, %0\n\t"
-		     "cmpb %h0,%b0\n\t"
-		     "leal 0x100(%" REG_PTR_MODE "0), %1\n\t"
-		     "jne 1f\n\t"
-		     LOCK_PREFIX "cmpxchgw %w1,%2\n\t"
-		     "1:"
-		     "sete %b1\n\t"
-		     "movzbl %b1,%0\n\t"
-		     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
-		     :
-		     : "memory", "cc");
-
-	return tmp;
-}
-
-static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
-{
-	asm volatile(UNLOCK_LOCK_PREFIX "incb %0"
-		     : "+m" (lock->slock)
-		     :
-		     : "memory", "cc");
-}
-#else
-#define TICKET_SHIFT 16
-
-static __always_inline void __ticket_spin_lock(raw_spinlock_t *lock)
-{
-	int inc = 0x00010000;
-	int tmp;
-
-	asm volatile(LOCK_PREFIX "xaddl %0, %1\n"
-		     "movzwl %w0, %2\n\t"
-		     "shrl $16, %0\n\t"
-		     "1:\t"
-		     "cmpl %0, %2\n\t"
-		     "je 2f\n\t"
-		     "rep ; nop\n\t"
-		     "movzwl %1, %2\n\t"
-		     /* don't need lfence here, because loads are in-order */
-		     "jmp 1b\n"
-		     "2:"
-		     : "+r" (inc), "+m" (lock->slock), "=&r" (tmp)
-		     :
-		     : "memory", "cc");
-}
-
-static __always_inline int __ticket_spin_trylock(raw_spinlock_t *lock)
-{
-	int tmp;
-	int new;
-
-	asm volatile("movl %2,%0\n\t"
-		     "movl %0,%1\n\t"
-		     "roll $16, %0\n\t"
-		     "cmpl %0,%1\n\t"
-		     "leal 0x00010000(%" REG_PTR_MODE "0), %1\n\t"
-		     "jne 1f\n\t"
-		     LOCK_PREFIX "cmpxchgl %1,%2\n\t"
-		     "1:"
-		     "sete %b1\n\t"
-		     "movzbl %b1,%0\n\t"
-		     : "=&a" (tmp), "=&q" (new), "+m" (lock->slock)
-		     :
-		     : "memory", "cc");
-
-	return tmp;
-}
-
-static __always_inline void __ticket_spin_unlock(raw_spinlock_t *lock)
-{
-	asm volatile(UNLOCK_LOCK_PREFIX "incw %0"
-		     : "+m" (lock->slock)
-		     :
-		     : "memory", "cc");
-}
-#endif
-
-static inline int __ticket_spin_is_locked(raw_spinlock_t *lock)
-{
-	int tmp = ACCESS_ONCE(lock->slock);
-
-	return !!(((tmp >> TICKET_SHIFT) ^ tmp) & ((1 << TICKET_SHIFT) - 1));
-}
-
-static inline int __ticket_spin_is_contended(raw_spinlock_t *lock)
-{
-	int tmp = ACCESS_ONCE(lock->slock);
-
-	return (((tmp >> TICKET_SHIFT) - tmp) & ((1 << TICKET_SHIFT) - 1)) > 1;
-}
-
-#ifdef CONFIG_PARAVIRT
-/*
- * Define virtualization-friendly old-style lock byte lock, for use in
- * pv_lock_ops if desired.
- *
- * This differs from the pre-2.6.24 spinlock by always using xchgb
- * rather than decb to take the lock; this allows it to use a
- * zero-initialized lock structure.  It also maintains a 1-byte
- * contention counter, so that we can implement
- * __byte_spin_is_contended.
- */
-struct __byte_spinlock {
-	s8 lock;
-	s8 spinners;
-};
-
-static inline int __byte_spin_is_locked(raw_spinlock_t *lock)
-{
-	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-	return bl->lock != 0;
-}
-
-static inline int __byte_spin_is_contended(raw_spinlock_t *lock)
-{
-	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-	return bl->spinners != 0;
-}
-
-static inline void __byte_spin_lock(raw_spinlock_t *lock)
-{
-	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-	s8 val = 1;
-
-	asm("1: xchgb %1, %0\n"
-	    "   test %1,%1\n"
-	    "   jz 3f\n"
-	    "   " LOCK_PREFIX "incb %2\n"
-	    "2: rep;nop\n"
-	    "   cmpb $1, %0\n"
-	    "   je 2b\n"
-	    "   " LOCK_PREFIX "decb %2\n"
-	    "   jmp 1b\n"
-	    "3:"
-	    : "+m" (bl->lock), "+q" (val), "+m" (bl->spinners): : "memory");
-}
-
-static inline int __byte_spin_trylock(raw_spinlock_t *lock)
-{
-	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-	u8 old = 1;
-
-	asm("xchgb %1,%0"
-	    : "+m" (bl->lock), "+q" (old) : : "memory");
-
-	return old == 0;
-}
-
-static inline void __byte_spin_unlock(raw_spinlock_t *lock)
-{
-	struct __byte_spinlock *bl = (struct __byte_spinlock *)lock;
-	smp_wmb();
-	bl->lock = 0;
-}
-#else  /* !CONFIG_PARAVIRT */
-static inline int __raw_spin_is_locked(raw_spinlock_t *lock)
-{
-	return __ticket_spin_is_locked(lock);
-}
-
-static inline int __raw_spin_is_contended(raw_spinlock_t *lock)
-{
-	return __ticket_spin_is_contended(lock);
-}
-
-static __always_inline void __raw_spin_lock(raw_spinlock_t *lock)
-{
-	__ticket_spin_lock(lock);
-}
-
-static __always_inline int __raw_spin_trylock(raw_spinlock_t *lock)
-{
-	return __ticket_spin_trylock(lock);
-}
-
-static __always_inline void __raw_spin_unlock(raw_spinlock_t *lock)
-{
-	__ticket_spin_unlock(lock);
-}
-
-static __always_inline void __raw_spin_lock_flags(raw_spinlock_t *lock,
-						  unsigned long flags)
-{
-	__raw_spin_lock(lock);
-}
-
-#endif	/* CONFIG_PARAVIRT */
-
-static inline void __raw_spin_unlock_wait(raw_spinlock_t *lock)
-{
-	while (__raw_spin_is_locked(lock))
-		cpu_relax();
-}
-
-/*
- * Read-write spinlocks, allowing multiple readers
- * but only one writer.
- *
- * NOTE! it is quite common to have readers in interrupts
- * but no interrupt writers. For those circumstances we
- * can "mix" irq-safe locks - any writer needs to get a
- * irq-safe write-lock, but readers can get non-irqsafe
- * read-locks.
- *
- * On x86, we implement read-write locks as a 32-bit counter
- * with the high bit (sign) being the "contended" bit.
- */
-
-/**
- * read_can_lock - would read_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static inline int __raw_read_can_lock(raw_rwlock_t *lock)
-{
-	return (int)(lock)->lock > 0;
-}
-
-/**
- * write_can_lock - would write_trylock() succeed?
- * @lock: the rwlock in question.
- */
-static inline int __raw_write_can_lock(raw_rwlock_t *lock)
-{
-	return (lock)->lock == RW_LOCK_BIAS;
-}
-
-static inline void __raw_read_lock(raw_rwlock_t *rw)
-{
-	asm volatile(LOCK_PREFIX " subl $1,(%0)\n\t"
-		     "jns 1f\n"
-		     "call __read_lock_failed\n\t"
-		     "1:\n"
-		     ::LOCK_PTR_REG (rw) : "memory");
-}
-
-static inline void __raw_write_lock(raw_rwlock_t *rw)
-{
-	asm volatile(LOCK_PREFIX " subl %1,(%0)\n\t"
-		     "jz 1f\n"
-		     "call __write_lock_failed\n\t"
-		     "1:\n"
-		     ::LOCK_PTR_REG (rw), "i" (RW_LOCK_BIAS) : "memory");
-}
-
-static inline int __raw_read_trylock(raw_rwlock_t *lock)
-{
-	atomic_t *count = (atomic_t *)lock;
-
-	atomic_dec(count);
-	if (atomic_read(count) >= 0)
-		return 1;
-	atomic_inc(count);
-	return 0;
-}
-
-static inline int __raw_write_trylock(raw_rwlock_t *lock)
-{
-	atomic_t *count = (atomic_t *)lock;
-
-	if (atomic_sub_and_test(RW_LOCK_BIAS, count))
-		return 1;
-	atomic_add(RW_LOCK_BIAS, count);
-	return 0;
-}
-
-static inline void __raw_read_unlock(raw_rwlock_t *rw)
-{
-	asm volatile(LOCK_PREFIX "incl %0" :"+m" (rw->lock) : : "memory");
-}
-
-static inline void __raw_write_unlock(raw_rwlock_t *rw)
-{
-	asm volatile(LOCK_PREFIX "addl %1, %0"
-		     : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory");
-}
-
-#define _raw_spin_relax(lock)	cpu_relax()
-#define _raw_read_relax(lock)	cpu_relax()
-#define _raw_write_relax(lock)	cpu_relax()
-
-#endif /* ASM_X86__SPINLOCK_H */
diff --git a/include/asm-x86/spinlock_types.h b/include/asm-x86/spinlock_types.h
deleted file mode 100644
index 6aa9b562c508..000000000000
--- a/include/asm-x86/spinlock_types.h
+++ /dev/null
@@ -1,20 +0,0 @@
-#ifndef ASM_X86__SPINLOCK_TYPES_H
-#define ASM_X86__SPINLOCK_TYPES_H
-
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
-typedef struct raw_spinlock {
-	unsigned int slock;
-} raw_spinlock_t;
-
-#define __RAW_SPIN_LOCK_UNLOCKED	{ 0 }
-
-typedef struct {
-	unsigned int lock;
-} raw_rwlock_t;
-
-#define __RAW_RW_LOCK_UNLOCKED		{ RW_LOCK_BIAS }
-
-#endif /* ASM_X86__SPINLOCK_TYPES_H */
diff --git a/include/asm-x86/srat.h b/include/asm-x86/srat.h
deleted file mode 100644
index 5363e4f7e1cd..000000000000
--- a/include/asm-x86/srat.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Some of the code in this file has been gleaned from the 64 bit
- * discontigmem support code base.
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to Pat Gaughen <gone@us.ibm.com>
- */
-
-#ifndef ASM_X86__SRAT_H
-#define ASM_X86__SRAT_H
-
-#ifdef CONFIG_ACPI_NUMA
-extern int get_memcfg_from_srat(void);
-#else
-static inline int get_memcfg_from_srat(void)
-{
-	return 0;
-}
-#endif
-
-#endif /* ASM_X86__SRAT_H */
diff --git a/include/asm-x86/stacktrace.h b/include/asm-x86/stacktrace.h
deleted file mode 100644
index f43517e28532..000000000000
--- a/include/asm-x86/stacktrace.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef ASM_X86__STACKTRACE_H
-#define ASM_X86__STACKTRACE_H
-
-extern int kstack_depth_to_print;
-
-/* Generic stack tracer with callbacks */
-
-struct stacktrace_ops {
-	void (*warning)(void *data, char *msg);
-	/* msg must contain %s for the symbol */
-	void (*warning_symbol)(void *data, char *msg, unsigned long symbol);
-	void (*address)(void *data, unsigned long address, int reliable);
-	/* On negative return stop dumping */
-	int (*stack)(void *data, char *name);
-};
-
-void dump_trace(struct task_struct *tsk, struct pt_regs *regs,
-		unsigned long *stack, unsigned long bp,
-		const struct stacktrace_ops *ops, void *data);
-
-#endif /* ASM_X86__STACKTRACE_H */
diff --git a/include/asm-x86/stat.h b/include/asm-x86/stat.h
deleted file mode 100644
index 1e120f628905..000000000000
--- a/include/asm-x86/stat.h
+++ /dev/null
@@ -1,114 +0,0 @@
-#ifndef ASM_X86__STAT_H
-#define ASM_X86__STAT_H
-
-#define STAT_HAVE_NSEC 1
-
-#ifdef __i386__
-struct stat {
-	unsigned long  st_dev;
-	unsigned long  st_ino;
-	unsigned short st_mode;
-	unsigned short st_nlink;
-	unsigned short st_uid;
-	unsigned short st_gid;
-	unsigned long  st_rdev;
-	unsigned long  st_size;
-	unsigned long  st_blksize;
-	unsigned long  st_blocks;
-	unsigned long  st_atime;
-	unsigned long  st_atime_nsec;
-	unsigned long  st_mtime;
-	unsigned long  st_mtime_nsec;
-	unsigned long  st_ctime;
-	unsigned long  st_ctime_nsec;
-	unsigned long  __unused4;
-	unsigned long  __unused5;
-};
-
-#define STAT64_HAS_BROKEN_ST_INO	1
-
-/* This matches struct stat64 in glibc2.1, hence the absolutely
- * insane amounts of padding around dev_t's.
- */
-struct stat64 {
-	unsigned long long	st_dev;
-	unsigned char	__pad0[4];
-
-	unsigned long	__st_ino;
-
-	unsigned int	st_mode;
-	unsigned int	st_nlink;
-
-	unsigned long	st_uid;
-	unsigned long	st_gid;
-
-	unsigned long long	st_rdev;
-	unsigned char	__pad3[4];
-
-	long long	st_size;
-	unsigned long	st_blksize;
-
-	/* Number 512-byte blocks allocated. */
-	unsigned long long	st_blocks;
-
-	unsigned long	st_atime;
-	unsigned long	st_atime_nsec;
-
-	unsigned long	st_mtime;
-	unsigned int	st_mtime_nsec;
-
-	unsigned long	st_ctime;
-	unsigned long	st_ctime_nsec;
-
-	unsigned long long	st_ino;
-};
-
-#else /* __i386__ */
-
-struct stat {
-	unsigned long	st_dev;
-	unsigned long	st_ino;
-	unsigned long	st_nlink;
-
-	unsigned int	st_mode;
-	unsigned int	st_uid;
-	unsigned int	st_gid;
-	unsigned int	__pad0;
-	unsigned long	st_rdev;
-	long		st_size;
-	long		st_blksize;
-	long		st_blocks;	/* Number 512-byte blocks allocated. */
-
-	unsigned long	st_atime;
-	unsigned long	st_atime_nsec;
-	unsigned long	st_mtime;
-	unsigned long	st_mtime_nsec;
-	unsigned long	st_ctime;
-	unsigned long   st_ctime_nsec;
-	long		__unused[3];
-};
-#endif
-
-/* for 32bit emulation and 32 bit kernels */
-struct __old_kernel_stat {
-	unsigned short st_dev;
-	unsigned short st_ino;
-	unsigned short st_mode;
-	unsigned short st_nlink;
-	unsigned short st_uid;
-	unsigned short st_gid;
-	unsigned short st_rdev;
-#ifdef __i386__
-	unsigned long  st_size;
-	unsigned long  st_atime;
-	unsigned long  st_mtime;
-	unsigned long  st_ctime;
-#else
-	unsigned int  st_size;
-	unsigned int  st_atime;
-	unsigned int  st_mtime;
-	unsigned int  st_ctime;
-#endif
-};
-
-#endif /* ASM_X86__STAT_H */
diff --git a/include/asm-x86/statfs.h b/include/asm-x86/statfs.h
deleted file mode 100644
index ca5dc19dd461..000000000000
--- a/include/asm-x86/statfs.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef ASM_X86__STATFS_H
-#define ASM_X86__STATFS_H
-
-/*
- * We need compat_statfs64 to be packed, because the i386 ABI won't
- * add padding at the end to bring it to a multiple of 8 bytes, but
- * the x86_64 ABI will.
- */
-#define ARCH_PACK_COMPAT_STATFS64 __attribute__((packed,aligned(4)))
-
-#include <asm-generic/statfs.h>
-#endif /* ASM_X86__STATFS_H */
diff --git a/include/asm-x86/string.h b/include/asm-x86/string.h
deleted file mode 100644
index 6dfd6d9373a0..000000000000
--- a/include/asm-x86/string.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "string_32.h"
-#else
-# include "string_64.h"
-#endif
diff --git a/include/asm-x86/string_32.h b/include/asm-x86/string_32.h
deleted file mode 100644
index 487843ed245a..000000000000
--- a/include/asm-x86/string_32.h
+++ /dev/null
@@ -1,326 +0,0 @@
-#ifndef ASM_X86__STRING_32_H
-#define ASM_X86__STRING_32_H
-
-#ifdef __KERNEL__
-
-/* Let gcc decide whether to inline or use the out of line functions */
-
-#define __HAVE_ARCH_STRCPY
-extern char *strcpy(char *dest, const char *src);
-
-#define __HAVE_ARCH_STRNCPY
-extern char *strncpy(char *dest, const char *src, size_t count);
-
-#define __HAVE_ARCH_STRCAT
-extern char *strcat(char *dest, const char *src);
-
-#define __HAVE_ARCH_STRNCAT
-extern char *strncat(char *dest, const char *src, size_t count);
-
-#define __HAVE_ARCH_STRCMP
-extern int strcmp(const char *cs, const char *ct);
-
-#define __HAVE_ARCH_STRNCMP
-extern int strncmp(const char *cs, const char *ct, size_t count);
-
-#define __HAVE_ARCH_STRCHR
-extern char *strchr(const char *s, int c);
-
-#define __HAVE_ARCH_STRLEN
-extern size_t strlen(const char *s);
-
-static __always_inline void *__memcpy(void *to, const void *from, size_t n)
-{
-	int d0, d1, d2;
-	asm volatile("rep ; movsl\n\t"
-		     "movl %4,%%ecx\n\t"
-		     "andl $3,%%ecx\n\t"
-		     "jz 1f\n\t"
-		     "rep ; movsb\n\t"
-		     "1:"
-		     : "=&c" (d0), "=&D" (d1), "=&S" (d2)
-		     : "0" (n / 4), "g" (n), "1" ((long)to), "2" ((long)from)
-		     : "memory");
-	return to;
-}
-
-/*
- * This looks ugly, but the compiler can optimize it totally,
- * as the count is constant.
- */
-static __always_inline void *__constant_memcpy(void *to, const void *from,
-					       size_t n)
-{
-	long esi, edi;
-	if (!n)
-		return to;
-
-	switch (n) {
-	case 1:
-		*(char *)to = *(char *)from;
-		return to;
-	case 2:
-		*(short *)to = *(short *)from;
-		return to;
-	case 4:
-		*(int *)to = *(int *)from;
-		return to;
-
-	case 3:
-		*(short *)to = *(short *)from;
-		*((char *)to + 2) = *((char *)from + 2);
-		return to;
-	case 5:
-		*(int *)to = *(int *)from;
-		*((char *)to + 4) = *((char *)from + 4);
-		return to;
-	case 6:
-		*(int *)to = *(int *)from;
-		*((short *)to + 2) = *((short *)from + 2);
-		return to;
-	case 8:
-		*(int *)to = *(int *)from;
-		*((int *)to + 1) = *((int *)from + 1);
-		return to;
-	}
-
-	esi = (long)from;
-	edi = (long)to;
-	if (n >= 5 * 4) {
-		/* large block: use rep prefix */
-		int ecx;
-		asm volatile("rep ; movsl"
-			     : "=&c" (ecx), "=&D" (edi), "=&S" (esi)
-			     : "0" (n / 4), "1" (edi), "2" (esi)
-			     : "memory"
-		);
-	} else {
-		/* small block: don't clobber ecx + smaller code */
-		if (n >= 4 * 4)
-			asm volatile("movsl"
-				     : "=&D"(edi), "=&S"(esi)
-				     : "0"(edi), "1"(esi)
-				     : "memory");
-		if (n >= 3 * 4)
-			asm volatile("movsl"
-				     : "=&D"(edi), "=&S"(esi)
-				     : "0"(edi), "1"(esi)
-				     : "memory");
-		if (n >= 2 * 4)
-			asm volatile("movsl"
-				     : "=&D"(edi), "=&S"(esi)
-				     : "0"(edi), "1"(esi)
-				     : "memory");
-		if (n >= 1 * 4)
-			asm volatile("movsl"
-				     : "=&D"(edi), "=&S"(esi)
-				     : "0"(edi), "1"(esi)
-				     : "memory");
-	}
-	switch (n % 4) {
-		/* tail */
-	case 0:
-		return to;
-	case 1:
-		asm volatile("movsb"
-			     : "=&D"(edi), "=&S"(esi)
-			     : "0"(edi), "1"(esi)
-			     : "memory");
-		return to;
-	case 2:
-		asm volatile("movsw"
-			     : "=&D"(edi), "=&S"(esi)
-			     : "0"(edi), "1"(esi)
-			     : "memory");
-		return to;
-	default:
-		asm volatile("movsw\n\tmovsb"
-			     : "=&D"(edi), "=&S"(esi)
-			     : "0"(edi), "1"(esi)
-			     : "memory");
-		return to;
-	}
-}
-
-#define __HAVE_ARCH_MEMCPY
-
-#ifdef CONFIG_X86_USE_3DNOW
-
-#include <asm/mmx.h>
-
-/*
- *	This CPU favours 3DNow strongly (eg AMD Athlon)
- */
-
-static inline void *__constant_memcpy3d(void *to, const void *from, size_t len)
-{
-	if (len < 512)
-		return __constant_memcpy(to, from, len);
-	return _mmx_memcpy(to, from, len);
-}
-
-static inline void *__memcpy3d(void *to, const void *from, size_t len)
-{
-	if (len < 512)
-		return __memcpy(to, from, len);
-	return _mmx_memcpy(to, from, len);
-}
-
-#define memcpy(t, f, n)				\
-	(__builtin_constant_p((n))		\
-	 ? __constant_memcpy3d((t), (f), (n))	\
-	 : __memcpy3d((t), (f), (n)))
-
-#else
-
-/*
- *	No 3D Now!
- */
-
-#define memcpy(t, f, n)				\
-	(__builtin_constant_p((n))		\
-	 ? __constant_memcpy((t), (f), (n))	\
-	 : __memcpy((t), (f), (n)))
-
-#endif
-
-#define __HAVE_ARCH_MEMMOVE
-void *memmove(void *dest, const void *src, size_t n);
-
-#define memcmp __builtin_memcmp
-
-#define __HAVE_ARCH_MEMCHR
-extern void *memchr(const void *cs, int c, size_t count);
-
-static inline void *__memset_generic(void *s, char c, size_t count)
-{
-	int d0, d1;
-	asm volatile("rep\n\t"
-		     "stosb"
-		     : "=&c" (d0), "=&D" (d1)
-		     : "a" (c), "1" (s), "0" (count)
-		     : "memory");
-	return s;
-}
-
-/* we might want to write optimized versions of these later */
-#define __constant_count_memset(s, c, count) __memset_generic((s), (c), (count))
-
-/*
- * memset(x, 0, y) is a reasonably common thing to do, so we want to fill
- * things 32 bits at a time even when we don't know the size of the
- * area at compile-time..
- */
-static __always_inline
-void *__constant_c_memset(void *s, unsigned long c, size_t count)
-{
-	int d0, d1;
-	asm volatile("rep ; stosl\n\t"
-		     "testb $2,%b3\n\t"
-		     "je 1f\n\t"
-		     "stosw\n"
-		     "1:\ttestb $1,%b3\n\t"
-		     "je 2f\n\t"
-		     "stosb\n"
-		     "2:"
-		     : "=&c" (d0), "=&D" (d1)
-		     : "a" (c), "q" (count), "0" (count/4), "1" ((long)s)
-		     : "memory");
-	return s;
-}
-
-/* Added by Gertjan van Wingerde to make minix and sysv module work */
-#define __HAVE_ARCH_STRNLEN
-extern size_t strnlen(const char *s, size_t count);
-/* end of additional stuff */
-
-#define __HAVE_ARCH_STRSTR
-extern char *strstr(const char *cs, const char *ct);
-
-/*
- * This looks horribly ugly, but the compiler can optimize it totally,
- * as we by now know that both pattern and count is constant..
- */
-static __always_inline
-void *__constant_c_and_count_memset(void *s, unsigned long pattern,
-				    size_t count)
-{
-	switch (count) {
-	case 0:
-		return s;
-	case 1:
-		*(unsigned char *)s = pattern & 0xff;
-		return s;
-	case 2:
-		*(unsigned short *)s = pattern & 0xffff;
-		return s;
-	case 3:
-		*(unsigned short *)s = pattern & 0xffff;
-		*((unsigned char *)s + 2) = pattern & 0xff;
-		return s;
-	case 4:
-		*(unsigned long *)s = pattern;
-		return s;
-	}
-
-#define COMMON(x)							\
-	asm volatile("rep ; stosl"					\
-		     x							\
-		     : "=&c" (d0), "=&D" (d1)				\
-		     : "a" (eax), "0" (count/4), "1" ((long)s)	\
-		     : "memory")
-
-	{
-		int d0, d1;
-#if __GNUC__ == 4 && __GNUC_MINOR__ == 0
-		/* Workaround for broken gcc 4.0 */
-		register unsigned long eax asm("%eax") = pattern;
-#else
-		unsigned long eax = pattern;
-#endif
-
-		switch (count % 4) {
-		case 0:
-			COMMON("");
-			return s;
-		case 1:
-			COMMON("\n\tstosb");
-			return s;
-		case 2:
-			COMMON("\n\tstosw");
-			return s;
-		default:
-			COMMON("\n\tstosw\n\tstosb");
-			return s;
-		}
-	}
-
-#undef COMMON
-}
-
-#define __constant_c_x_memset(s, c, count)			\
-	(__builtin_constant_p(count)				\
-	 ? __constant_c_and_count_memset((s), (c), (count))	\
-	 : __constant_c_memset((s), (c), (count)))
-
-#define __memset(s, c, count)				\
-	(__builtin_constant_p(count)			\
-	 ? __constant_count_memset((s), (c), (count))	\
-	 : __memset_generic((s), (c), (count)))
-
-#define __HAVE_ARCH_MEMSET
-#define memset(s, c, count)						\
-	(__builtin_constant_p(c)					\
-	 ? __constant_c_x_memset((s), (0x01010101UL * (unsigned char)(c)), \
-				 (count))				\
-	 : __memset((s), (c), (count)))
-
-/*
- * find the first occurrence of byte 'c', or 1 past the area if none
- */
-#define __HAVE_ARCH_MEMSCAN
-extern void *memscan(void *addr, int c, size_t size);
-
-#endif /* __KERNEL__ */
-
-#endif /* ASM_X86__STRING_32_H */
diff --git a/include/asm-x86/string_64.h b/include/asm-x86/string_64.h
deleted file mode 100644
index a2add11d3b66..000000000000
--- a/include/asm-x86/string_64.h
+++ /dev/null
@@ -1,60 +0,0 @@
-#ifndef ASM_X86__STRING_64_H
-#define ASM_X86__STRING_64_H
-
-#ifdef __KERNEL__
-
-/* Written 2002 by Andi Kleen */
-
-/* Only used for special circumstances. Stolen from i386/string.h */
-static __always_inline void *__inline_memcpy(void *to, const void *from, size_t n)
-{
-	unsigned long d0, d1, d2;
-	asm volatile("rep ; movsl\n\t"
-		     "testb $2,%b4\n\t"
-		     "je 1f\n\t"
-		     "movsw\n"
-		     "1:\ttestb $1,%b4\n\t"
-		     "je 2f\n\t"
-		     "movsb\n"
-		     "2:"
-		     : "=&c" (d0), "=&D" (d1), "=&S" (d2)
-		     : "0" (n / 4), "q" (n), "1" ((long)to), "2" ((long)from)
-		     : "memory");
-	return to;
-}
-
-/* Even with __builtin_ the compiler may decide to use the out of line
-   function. */
-
-#define __HAVE_ARCH_MEMCPY 1
-#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4
-extern void *memcpy(void *to, const void *from, size_t len);
-#else
-extern void *__memcpy(void *to, const void *from, size_t len);
-#define memcpy(dst, src, len)					\
-({								\
-	size_t __len = (len);					\
-	void *__ret;						\
-	if (__builtin_constant_p(len) && __len >= 64)		\
-		__ret = __memcpy((dst), (src), __len);		\
-	else							\
-		__ret = __builtin_memcpy((dst), (src), __len);	\
-	__ret;							\
-})
-#endif
-
-#define __HAVE_ARCH_MEMSET
-void *memset(void *s, int c, size_t n);
-
-#define __HAVE_ARCH_MEMMOVE
-void *memmove(void *dest, const void *src, size_t count);
-
-int memcmp(const void *cs, const void *ct, size_t count);
-size_t strlen(const char *s);
-char *strcpy(char *dest, const char *src);
-char *strcat(char *dest, const char *src);
-int strcmp(const char *cs, const char *ct);
-
-#endif /* __KERNEL__ */
-
-#endif /* ASM_X86__STRING_64_H */
diff --git a/include/asm-x86/summit/apic.h b/include/asm-x86/summit/apic.h
deleted file mode 100644
index 9b3070f1c2ac..000000000000
--- a/include/asm-x86/summit/apic.h
+++ /dev/null
@@ -1,184 +0,0 @@
-#ifndef __ASM_SUMMIT_APIC_H
-#define __ASM_SUMMIT_APIC_H
-
-#include <asm/smp.h>
-
-#define esr_disable (1)
-#define NO_BALANCE_IRQ (0)
-
-/* In clustered mode, the high nibble of APIC ID is a cluster number.
- * The low nibble is a 4-bit bitmap. */
-#define XAPIC_DEST_CPUS_SHIFT	4
-#define XAPIC_DEST_CPUS_MASK	((1u << XAPIC_DEST_CPUS_SHIFT) - 1)
-#define XAPIC_DEST_CLUSTER_MASK	(XAPIC_DEST_CPUS_MASK << XAPIC_DEST_CPUS_SHIFT)
-
-#define APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
-
-static inline cpumask_t target_cpus(void)
-{
-	/* CPU_MASK_ALL (0xff) has undefined behaviour with
-	 * dest_LowestPrio mode logical clustered apic interrupt routing
-	 * Just start on cpu 0.  IRQ balancing will spread load
-	 */
-	return cpumask_of_cpu(0);
-}
-
-#define INT_DELIVERY_MODE (dest_LowestPrio)
-#define INT_DEST_MODE 1     /* logical delivery broadcast to all procs */
-
-static inline unsigned long check_apicid_used(physid_mask_t bitmap, int apicid)
-{
-	return 0;
-}
-
-/* we don't use the phys_cpu_present_map to indicate apicid presence */
-static inline unsigned long check_apicid_present(int bit)
-{
-	return 1;
-}
-
-#define apicid_cluster(apicid) ((apicid) & XAPIC_DEST_CLUSTER_MASK)
-
-extern u8 cpu_2_logical_apicid[];
-
-static inline void init_apic_ldr(void)
-{
-	unsigned long val, id;
-	int count = 0;
-	u8 my_id = (u8)hard_smp_processor_id();
-	u8 my_cluster = (u8)apicid_cluster(my_id);
-#ifdef CONFIG_SMP
-	u8 lid;
-	int i;
-
-	/* Create logical APIC IDs by counting CPUs already in cluster. */
-	for (count = 0, i = NR_CPUS; --i >= 0; ) {
-		lid = cpu_2_logical_apicid[i];
-		if (lid != BAD_APICID && apicid_cluster(lid) == my_cluster)
-			++count;
-	}
-#endif
-	/* We only have a 4 wide bitmap in cluster mode.  If a deranged
-	 * BIOS puts 5 CPUs in one APIC cluster, we're hosed. */
-	BUG_ON(count >= XAPIC_DEST_CPUS_SHIFT);
-	id = my_cluster | (1UL << count);
-	apic_write(APIC_DFR, APIC_DFR_VALUE);
-	val = apic_read(APIC_LDR) & ~APIC_LDR_MASK;
-	val |= SET_APIC_LOGICAL_ID(id);
-	apic_write(APIC_LDR, val);
-}
-
-static inline int multi_timer_check(int apic, int irq)
-{
-	return 0;
-}
-
-static inline int apic_id_registered(void)
-{
-	return 1;
-}
-
-static inline void setup_apic_routing(void)
-{
-	printk("Enabling APIC mode:  Summit.  Using %d I/O APICs\n",
-						nr_ioapics);
-}
-
-static inline int apicid_to_node(int logical_apicid)
-{
-#ifdef CONFIG_SMP
-	return apicid_2_node[hard_smp_processor_id()];
-#else
-	return 0;
-#endif
-}
-
-/* Mapping from cpu number to logical apicid */
-static inline int cpu_to_logical_apicid(int cpu)
-{
-#ifdef CONFIG_SMP
-       if (cpu >= NR_CPUS)
-	       return BAD_APICID;
-	return (int)cpu_2_logical_apicid[cpu];
-#else
-	return logical_smp_processor_id();
-#endif
-}
-
-static inline int cpu_present_to_apicid(int mps_cpu)
-{
-	if (mps_cpu < NR_CPUS)
-		return (int)per_cpu(x86_bios_cpu_apicid, mps_cpu);
-	else
-		return BAD_APICID;
-}
-
-static inline physid_mask_t ioapic_phys_id_map(physid_mask_t phys_id_map)
-{
-	/* For clustered we don't have a good way to do this yet - hack */
-	return physids_promote(0x0F);
-}
-
-static inline physid_mask_t apicid_to_cpu_present(int apicid)
-{
-	return physid_mask_of_physid(0);
-}
-
-static inline void setup_portio_remap(void)
-{
-}
-
-static inline int check_phys_apicid_present(int boot_cpu_physical_apicid)
-{
-	return 1;
-}
-
-static inline void enable_apic_mode(void)
-{
-}
-
-static inline unsigned int cpu_mask_to_apicid(cpumask_t cpumask)
-{
-	int num_bits_set;
-	int cpus_found = 0;
-	int cpu;
-	int apicid;
-
-	num_bits_set = cpus_weight(cpumask);
-	/* Return id to all */
-	if (num_bits_set == NR_CPUS)
-		return (int) 0xFF;
-	/*
-	 * The cpus in the mask must all be on the apic cluster.  If are not
-	 * on the same apicid cluster return default value of TARGET_CPUS.
-	 */
-	cpu = first_cpu(cpumask);
-	apicid = cpu_to_logical_apicid(cpu);
-	while (cpus_found < num_bits_set) {
-		if (cpu_isset(cpu, cpumask)) {
-			int new_apicid = cpu_to_logical_apicid(cpu);
-			if (apicid_cluster(apicid) !=
-					apicid_cluster(new_apicid)){
-				printk ("%s: Not a valid mask!\n", __func__);
-				return 0xFF;
-			}
-			apicid = apicid | new_apicid;
-			cpus_found++;
-		}
-		cpu++;
-	}
-	return apicid;
-}
-
-/* cpuid returns the value latched in the HW at reset, not the APIC ID
- * register's value.  For any box whose BIOS changes APIC IDs, like
- * clustered APIC systems, we must use hard_smp_processor_id.
- *
- * See Intel's IA-32 SW Dev's Manual Vol2 under CPUID.
- */
-static inline u32 phys_pkg_id(u32 cpuid_apic, int index_msb)
-{
-	return hard_smp_processor_id() >> index_msb;
-}
-
-#endif /* __ASM_SUMMIT_APIC_H */
diff --git a/include/asm-x86/summit/apicdef.h b/include/asm-x86/summit/apicdef.h
deleted file mode 100644
index f3fbca1f61c1..000000000000
--- a/include/asm-x86/summit/apicdef.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __ASM_SUMMIT_APICDEF_H
-#define __ASM_SUMMIT_APICDEF_H
-
-#define		APIC_ID_MASK		(0xFF<<24)
-
-static inline unsigned get_apic_id(unsigned long x)
-{
-	return (x>>24)&0xFF;
-}
-
-#define		GET_APIC_ID(x)	get_apic_id(x)
-
-#endif
diff --git a/include/asm-x86/summit/ipi.h b/include/asm-x86/summit/ipi.h
deleted file mode 100644
index 53bd1e7bd7b4..000000000000
--- a/include/asm-x86/summit/ipi.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __ASM_SUMMIT_IPI_H
-#define __ASM_SUMMIT_IPI_H
-
-void send_IPI_mask_sequence(cpumask_t mask, int vector);
-
-static inline void send_IPI_mask(cpumask_t mask, int vector)
-{
-	send_IPI_mask_sequence(mask, vector);
-}
-
-static inline void send_IPI_allbutself(int vector)
-{
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
-
-	if (!cpus_empty(mask))
-		send_IPI_mask(mask, vector);
-}
-
-static inline void send_IPI_all(int vector)
-{
-	send_IPI_mask(cpu_online_map, vector);
-}
-
-#endif /* __ASM_SUMMIT_IPI_H */
diff --git a/include/asm-x86/summit/mpparse.h b/include/asm-x86/summit/mpparse.h
deleted file mode 100644
index 013ce6fab2d5..000000000000
--- a/include/asm-x86/summit/mpparse.h
+++ /dev/null
@@ -1,109 +0,0 @@
-#ifndef __ASM_SUMMIT_MPPARSE_H
-#define __ASM_SUMMIT_MPPARSE_H
-
-#include <asm/tsc.h>
-
-extern int use_cyclone;
-
-#ifdef CONFIG_X86_SUMMIT_NUMA
-extern void setup_summit(void);
-#else
-#define setup_summit()	{}
-#endif
-
-static inline int mps_oem_check(struct mp_config_table *mpc, char *oem,
-		char *productid)
-{
-	if (!strncmp(oem, "IBM ENSW", 8) &&
-			(!strncmp(productid, "VIGIL SMP", 9)
-			 || !strncmp(productid, "EXA", 3)
-			 || !strncmp(productid, "RUTHLESS SMP", 12))){
-		mark_tsc_unstable("Summit based system");
-		use_cyclone = 1; /*enable cyclone-timer*/
-		setup_summit();
-		return 1;
-	}
-	return 0;
-}
-
-/* Hook from generic ACPI tables.c */
-static inline int acpi_madt_oem_check(char *oem_id, char *oem_table_id)
-{
-	if (!strncmp(oem_id, "IBM", 3) &&
-	    (!strncmp(oem_table_id, "SERVIGIL", 8)
-	     || !strncmp(oem_table_id, "EXA", 3))){
-		mark_tsc_unstable("Summit based system");
-		use_cyclone = 1; /*enable cyclone-timer*/
-		setup_summit();
-		return 1;
-	}
-	return 0;
-}
-
-struct rio_table_hdr {
-	unsigned char version;      /* Version number of this data structure           */
-	                            /* Version 3 adds chassis_num & WP_index           */
-	unsigned char num_scal_dev; /* # of Scalability devices (Twisters for Vigil)   */
-	unsigned char num_rio_dev;  /* # of RIO I/O devices (Cyclones and Winnipegs)   */
-} __attribute__((packed));
-
-struct scal_detail {
-	unsigned char node_id;      /* Scalability Node ID                             */
-	unsigned long CBAR;         /* Address of 1MB register space                   */
-	unsigned char port0node;    /* Node ID port connected to: 0xFF=None            */
-	unsigned char port0port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-	unsigned char port1node;    /* Node ID port connected to: 0xFF = None          */
-	unsigned char port1port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-	unsigned char port2node;    /* Node ID port connected to: 0xFF = None          */
-	unsigned char port2port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-	unsigned char chassis_num;  /* 1 based Chassis number (1 = boot node)          */
-} __attribute__((packed));
-
-struct rio_detail {
-	unsigned char node_id;      /* RIO Node ID                                     */
-	unsigned long BBAR;         /* Address of 1MB register space                   */
-	unsigned char type;         /* Type of device                                  */
-	unsigned char owner_id;     /* For WPEG: Node ID of Cyclone that owns this WPEG*/
-	                            /* For CYC:  Node ID of Twister that owns this CYC */
-	unsigned char port0node;    /* Node ID port connected to: 0xFF=None            */
-	unsigned char port0port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-	unsigned char port1node;    /* Node ID port connected to: 0xFF=None            */
-	unsigned char port1port;    /* Port num port connected to: 0,1,2, or 0xFF=None */
-	unsigned char first_slot;   /* For WPEG: Lowest slot number below this WPEG    */
-	                            /* For CYC:  0                                     */
-	unsigned char status;       /* For WPEG: Bit 0 = 1 : the XAPIC is used         */
-	                            /*                 = 0 : the XAPIC is not used, ie:*/
-	                            /*                     ints fwded to another XAPIC */
-	                            /*           Bits1:7 Reserved                      */
-	                            /* For CYC:  Bits0:7 Reserved                      */
-	unsigned char WP_index;     /* For WPEG: WPEG instance index - lower ones have */
-	                            /*           lower slot numbers/PCI bus numbers    */
-	                            /* For CYC:  No meaning                            */
-	unsigned char chassis_num;  /* 1 based Chassis number                          */
-	                            /* For LookOut WPEGs this field indicates the      */
-	                            /* Expansion Chassis #, enumerated from Boot       */
-	                            /* Node WPEG external port, then Boot Node CYC     */
-	                            /* external port, then Next Vigil chassis WPEG     */
-	                            /* external port, etc.                             */
-	                            /* Shared Lookouts have only 1 chassis number (the */
-	                            /* first one assigned)                             */
-} __attribute__((packed));
-
-
-typedef enum {
-	CompatTwister = 0,  /* Compatibility Twister               */
-	AltTwister    = 1,  /* Alternate Twister of internal 8-way */
-	CompatCyclone = 2,  /* Compatibility Cyclone               */
-	AltCyclone    = 3,  /* Alternate Cyclone of internal 8-way */
-	CompatWPEG    = 4,  /* Compatibility WPEG                  */
-	AltWPEG       = 5,  /* Second Planar WPEG                  */
-	LookOutAWPEG  = 6,  /* LookOut WPEG                        */
-	LookOutBWPEG  = 7,  /* LookOut WPEG                        */
-} node_type;
-
-static inline int is_WPEG(struct rio_detail *rio){
-	return (rio->type == CompatWPEG || rio->type == AltWPEG ||
-		rio->type == LookOutAWPEG || rio->type == LookOutBWPEG);
-}
-
-#endif /* __ASM_SUMMIT_MPPARSE_H */
diff --git a/include/asm-x86/suspend.h b/include/asm-x86/suspend.h
deleted file mode 100644
index 9bd521fe4570..000000000000
--- a/include/asm-x86/suspend.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "suspend_32.h"
-#else
-# include "suspend_64.h"
-#endif
diff --git a/include/asm-x86/suspend_32.h b/include/asm-x86/suspend_32.h
deleted file mode 100644
index acb6d4d491f4..000000000000
--- a/include/asm-x86/suspend_32.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/*
- * Copyright 2001-2002 Pavel Machek <pavel@suse.cz>
- * Based on code
- * Copyright 2001 Patrick Mochel <mochel@osdl.org>
- */
-#ifndef ASM_X86__SUSPEND_32_H
-#define ASM_X86__SUSPEND_32_H
-
-#include <asm/desc.h>
-#include <asm/i387.h>
-
-static inline int arch_prepare_suspend(void) { return 0; }
-
-/* image of the saved processor state */
-struct saved_context {
-	u16 es, fs, gs, ss;
-	unsigned long cr0, cr2, cr3, cr4;
-	struct desc_ptr gdt;
-	struct desc_ptr idt;
-	u16 ldt;
-	u16 tss;
-	unsigned long tr;
-	unsigned long safety;
-	unsigned long return_address;
-} __attribute__((packed));
-
-#ifdef CONFIG_ACPI
-extern unsigned long saved_eip;
-extern unsigned long saved_esp;
-extern unsigned long saved_ebp;
-extern unsigned long saved_ebx;
-extern unsigned long saved_esi;
-extern unsigned long saved_edi;
-
-static inline void acpi_save_register_state(unsigned long return_point)
-{
-	saved_eip = return_point;
-	asm volatile("movl %%esp,%0" : "=m" (saved_esp));
-	asm volatile("movl %%ebp,%0" : "=m" (saved_ebp));
-	asm volatile("movl %%ebx,%0" : "=m" (saved_ebx));
-	asm volatile("movl %%edi,%0" : "=m" (saved_edi));
-	asm volatile("movl %%esi,%0" : "=m" (saved_esi));
-}
-
-#define acpi_restore_register_state()  do {} while (0)
-
-/* routines for saving/restoring kernel state */
-extern int acpi_save_state_mem(void);
-#endif
-
-#endif /* ASM_X86__SUSPEND_32_H */
diff --git a/include/asm-x86/suspend_64.h b/include/asm-x86/suspend_64.h
deleted file mode 100644
index cf821dd310e8..000000000000
--- a/include/asm-x86/suspend_64.h
+++ /dev/null
@@ -1,52 +0,0 @@
-/*
- * Copyright 2001-2003 Pavel Machek <pavel@suse.cz>
- * Based on code
- * Copyright 2001 Patrick Mochel <mochel@osdl.org>
- */
-#ifndef ASM_X86__SUSPEND_64_H
-#define ASM_X86__SUSPEND_64_H
-
-#include <asm/desc.h>
-#include <asm/i387.h>
-
-static inline int arch_prepare_suspend(void)
-{
-	return 0;
-}
-
-/*
- * Image of the saved processor state, used by the low level ACPI suspend to
- * RAM code and by the low level hibernation code.
- *
- * If you modify it, fix arch/x86/kernel/acpi/wakeup_64.S and make sure that
- * __save/__restore_processor_state(), defined in arch/x86/kernel/suspend_64.c,
- * still work as required.
- */
-struct saved_context {
-	struct pt_regs regs;
-	u16 ds, es, fs, gs, ss;
-	unsigned long gs_base, gs_kernel_base, fs_base;
-	unsigned long cr0, cr2, cr3, cr4, cr8;
-	unsigned long efer;
-	u16 gdt_pad;
-	u16 gdt_limit;
-	unsigned long gdt_base;
-	u16 idt_pad;
-	u16 idt_limit;
-	unsigned long idt_base;
-	u16 ldt;
-	u16 tss;
-	unsigned long tr;
-	unsigned long safety;
-	unsigned long return_address;
-} __attribute__((packed));
-
-#define loaddebug(thread,register) \
-	set_debugreg((thread)->debugreg##register, register)
-
-/* routines for saving/restoring kernel state */
-extern int acpi_save_state_mem(void);
-extern char core_restore_code;
-extern char restore_registers;
-
-#endif /* ASM_X86__SUSPEND_64_H */
diff --git a/include/asm-x86/swiotlb.h b/include/asm-x86/swiotlb.h
deleted file mode 100644
index 1e20adbcad4b..000000000000
--- a/include/asm-x86/swiotlb.h
+++ /dev/null
@@ -1,58 +0,0 @@
-#ifndef ASM_X86__SWIOTLB_H
-#define ASM_X86__SWIOTLB_H
-
-#include <asm/dma-mapping.h>
-
-/* SWIOTLB interface */
-
-extern dma_addr_t swiotlb_map_single(struct device *hwdev, void *ptr,
-				     size_t size, int dir);
-extern void *swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-				    dma_addr_t *dma_handle, gfp_t flags);
-extern void swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr,
-				 size_t size, int dir);
-extern void swiotlb_sync_single_for_cpu(struct device *hwdev,
-					dma_addr_t dev_addr,
-					size_t size, int dir);
-extern void swiotlb_sync_single_for_device(struct device *hwdev,
-					   dma_addr_t dev_addr,
-					   size_t size, int dir);
-extern void swiotlb_sync_single_range_for_cpu(struct device *hwdev,
-					      dma_addr_t dev_addr,
-					      unsigned long offset,
-					      size_t size, int dir);
-extern void swiotlb_sync_single_range_for_device(struct device *hwdev,
-						 dma_addr_t dev_addr,
-						 unsigned long offset,
-						 size_t size, int dir);
-extern void swiotlb_sync_sg_for_cpu(struct device *hwdev,
-				    struct scatterlist *sg, int nelems,
-				    int dir);
-extern void swiotlb_sync_sg_for_device(struct device *hwdev,
-				       struct scatterlist *sg, int nelems,
-				       int dir);
-extern int swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg,
-			  int nents, int direction);
-extern void swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg,
-			     int nents, int direction);
-extern int swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr);
-extern void swiotlb_free_coherent(struct device *hwdev, size_t size,
-				  void *vaddr, dma_addr_t dma_handle);
-extern int swiotlb_dma_supported(struct device *hwdev, u64 mask);
-extern void swiotlb_init(void);
-
-extern int swiotlb_force;
-
-#ifdef CONFIG_SWIOTLB
-extern int swiotlb;
-extern void pci_swiotlb_init(void);
-#else
-#define swiotlb 0
-static inline void pci_swiotlb_init(void)
-{
-}
-#endif
-
-static inline void dma_mark_clean(void *addr, size_t size) {}
-
-#endif /* ASM_X86__SWIOTLB_H */
diff --git a/include/asm-x86/sync_bitops.h b/include/asm-x86/sync_bitops.h
deleted file mode 100644
index b689bee71104..000000000000
--- a/include/asm-x86/sync_bitops.h
+++ /dev/null
@@ -1,130 +0,0 @@
-#ifndef ASM_X86__SYNC_BITOPS_H
-#define ASM_X86__SYNC_BITOPS_H
-
-/*
- * Copyright 1992, Linus Torvalds.
- */
-
-/*
- * These have to be done with inline assembly: that way the bit-setting
- * is guaranteed to be atomic. All bit operations return 0 if the bit
- * was cleared before the operation and != 0 if it was not.
- *
- * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
- */
-
-#define ADDR (*(volatile long *)addr)
-
-/**
- * sync_set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered.  See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void sync_set_bit(int nr, volatile unsigned long *addr)
-{
-	asm volatile("lock; btsl %1,%0"
-		     : "+m" (ADDR)
-		     : "Ir" (nr)
-		     : "memory");
-}
-
-/**
- * sync_clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * sync_clear_bit() is atomic and may not be reordered.  However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
- * in order to ensure changes are visible on other processors.
- */
-static inline void sync_clear_bit(int nr, volatile unsigned long *addr)
-{
-	asm volatile("lock; btrl %1,%0"
-		     : "+m" (ADDR)
-		     : "Ir" (nr)
-		     : "memory");
-}
-
-/**
- * sync_change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * sync_change_bit() is atomic and may not be reordered.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void sync_change_bit(int nr, volatile unsigned long *addr)
-{
-	asm volatile("lock; btcl %1,%0"
-		     : "+m" (ADDR)
-		     : "Ir" (nr)
-		     : "memory");
-}
-
-/**
- * sync_test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int sync_test_and_set_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	asm volatile("lock; btsl %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
-}
-
-/**
- * sync_test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int sync_test_and_clear_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	asm volatile("lock; btrl %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
-}
-
-/**
- * sync_test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int sync_test_and_change_bit(int nr, volatile unsigned long *addr)
-{
-	int oldbit;
-
-	asm volatile("lock; btcl %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
-		     : "Ir" (nr) : "memory");
-	return oldbit;
-}
-
-#define sync_test_bit(nr, addr) test_bit(nr, addr)
-
-#undef ADDR
-
-#endif /* ASM_X86__SYNC_BITOPS_H */
diff --git a/include/asm-x86/syscall.h b/include/asm-x86/syscall.h
deleted file mode 100644
index 04c47dc5597c..000000000000
--- a/include/asm-x86/syscall.h
+++ /dev/null
@@ -1,211 +0,0 @@
-/*
- * Access to user system call parameters and results
- *
- * Copyright (C) 2008 Red Hat, Inc.  All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License v.2.
- *
- * See asm-generic/syscall.h for descriptions of what we must do here.
- */
-
-#ifndef _ASM_SYSCALL_H
-#define _ASM_SYSCALL_H	1
-
-#include <linux/sched.h>
-#include <linux/err.h>
-
-static inline long syscall_get_nr(struct task_struct *task,
-				  struct pt_regs *regs)
-{
-	/*
-	 * We always sign-extend a -1 value being set here,
-	 * so this is always either -1L or a syscall number.
-	 */
-	return regs->orig_ax;
-}
-
-static inline void syscall_rollback(struct task_struct *task,
-				    struct pt_regs *regs)
-{
-	regs->ax = regs->orig_ax;
-}
-
-static inline long syscall_get_error(struct task_struct *task,
-				     struct pt_regs *regs)
-{
-	unsigned long error = regs->ax;
-#ifdef CONFIG_IA32_EMULATION
-	/*
-	 * TS_COMPAT is set for 32-bit syscall entries and then
-	 * remains set until we return to user mode.
-	 */
-	if (task_thread_info(task)->status & TS_COMPAT)
-		/*
-		 * Sign-extend the value so (int)-EFOO becomes (long)-EFOO
-		 * and will match correctly in comparisons.
-		 */
-		error = (long) (int) error;
-#endif
-	return IS_ERR_VALUE(error) ? error : 0;
-}
-
-static inline long syscall_get_return_value(struct task_struct *task,
-					    struct pt_regs *regs)
-{
-	return regs->ax;
-}
-
-static inline void syscall_set_return_value(struct task_struct *task,
-					    struct pt_regs *regs,
-					    int error, long val)
-{
-	regs->ax = (long) error ?: val;
-}
-
-#ifdef CONFIG_X86_32
-
-static inline void syscall_get_arguments(struct task_struct *task,
-					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
-					 unsigned long *args)
-{
-	BUG_ON(i + n > 6);
-	memcpy(args, &regs->bx + i, n * sizeof(args[0]));
-}
-
-static inline void syscall_set_arguments(struct task_struct *task,
-					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
-					 const unsigned long *args)
-{
-	BUG_ON(i + n > 6);
-	memcpy(&regs->bx + i, args, n * sizeof(args[0]));
-}
-
-#else	 /* CONFIG_X86_64 */
-
-static inline void syscall_get_arguments(struct task_struct *task,
-					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
-					 unsigned long *args)
-{
-# ifdef CONFIG_IA32_EMULATION
-	if (task_thread_info(task)->status & TS_COMPAT)
-		switch (i + n) {
-		case 6:
-			if (!n--) break;
-			*args++ = regs->bp;
-		case 5:
-			if (!n--) break;
-			*args++ = regs->di;
-		case 4:
-			if (!n--) break;
-			*args++ = regs->si;
-		case 3:
-			if (!n--) break;
-			*args++ = regs->dx;
-		case 2:
-			if (!n--) break;
-			*args++ = regs->cx;
-		case 1:
-			if (!n--) break;
-			*args++ = regs->bx;
-		case 0:
-			if (!n--) break;
-		default:
-			BUG();
-			break;
-		}
-	else
-# endif
-		switch (i + n) {
-		case 6:
-			if (!n--) break;
-			*args++ = regs->r9;
-		case 5:
-			if (!n--) break;
-			*args++ = regs->r8;
-		case 4:
-			if (!n--) break;
-			*args++ = regs->r10;
-		case 3:
-			if (!n--) break;
-			*args++ = regs->dx;
-		case 2:
-			if (!n--) break;
-			*args++ = regs->si;
-		case 1:
-			if (!n--) break;
-			*args++ = regs->di;
-		case 0:
-			if (!n--) break;
-		default:
-			BUG();
-			break;
-		}
-}
-
-static inline void syscall_set_arguments(struct task_struct *task,
-					 struct pt_regs *regs,
-					 unsigned int i, unsigned int n,
-					 const unsigned long *args)
-{
-# ifdef CONFIG_IA32_EMULATION
-	if (task_thread_info(task)->status & TS_COMPAT)
-		switch (i + n) {
-		case 6:
-			if (!n--) break;
-			regs->bp = *args++;
-		case 5:
-			if (!n--) break;
-			regs->di = *args++;
-		case 4:
-			if (!n--) break;
-			regs->si = *args++;
-		case 3:
-			if (!n--) break;
-			regs->dx = *args++;
-		case 2:
-			if (!n--) break;
-			regs->cx = *args++;
-		case 1:
-			if (!n--) break;
-			regs->bx = *args++;
-		case 0:
-			if (!n--) break;
-		default:
-			BUG();
-		}
-	else
-# endif
-		switch (i + n) {
-		case 6:
-			if (!n--) break;
-			regs->r9 = *args++;
-		case 5:
-			if (!n--) break;
-			regs->r8 = *args++;
-		case 4:
-			if (!n--) break;
-			regs->r10 = *args++;
-		case 3:
-			if (!n--) break;
-			regs->dx = *args++;
-		case 2:
-			if (!n--) break;
-			regs->si = *args++;
-		case 1:
-			if (!n--) break;
-			regs->di = *args++;
-		case 0:
-			if (!n--) break;
-		default:
-			BUG();
-		}
-}
-
-#endif	/* CONFIG_X86_32 */
-
-#endif	/* _ASM_SYSCALL_H */
diff --git a/include/asm-x86/syscalls.h b/include/asm-x86/syscalls.h
deleted file mode 100644
index 87803da44010..000000000000
--- a/include/asm-x86/syscalls.h
+++ /dev/null
@@ -1,93 +0,0 @@
-/*
- * syscalls.h - Linux syscall interfaces (arch-specific)
- *
- * Copyright (c) 2008 Jaswinder Singh
- *
- * This file is released under the GPLv2.
- * See the file COPYING for more details.
- */
-
-#ifndef _ASM_X86_SYSCALLS_H
-#define _ASM_X86_SYSCALLS_H
-
-#include <linux/compiler.h>
-#include <linux/linkage.h>
-#include <linux/types.h>
-#include <linux/signal.h>
-
-/* Common in X86_32 and X86_64 */
-/* kernel/ioport.c */
-asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
-
-/* X86_32 only */
-#ifdef CONFIG_X86_32
-/* kernel/process_32.c */
-asmlinkage int sys_fork(struct pt_regs);
-asmlinkage int sys_clone(struct pt_regs);
-asmlinkage int sys_vfork(struct pt_regs);
-asmlinkage int sys_execve(struct pt_regs);
-
-/* kernel/signal_32.c */
-asmlinkage int sys_sigsuspend(int, int, old_sigset_t);
-asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
-			     struct old_sigaction __user *);
-asmlinkage int sys_sigaltstack(unsigned long);
-asmlinkage unsigned long sys_sigreturn(unsigned long);
-asmlinkage int sys_rt_sigreturn(unsigned long);
-
-/* kernel/ioport.c */
-asmlinkage long sys_iopl(unsigned long);
-
-/* kernel/ldt.c */
-asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
-
-/* kernel/sys_i386_32.c */
-asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
-			  unsigned long, unsigned long, unsigned long);
-struct mmap_arg_struct;
-asmlinkage int old_mmap(struct mmap_arg_struct __user *);
-struct sel_arg_struct;
-asmlinkage int old_select(struct sel_arg_struct __user *);
-asmlinkage int sys_ipc(uint, int, int, int, void __user *, long);
-struct old_utsname;
-asmlinkage int sys_uname(struct old_utsname __user *);
-struct oldold_utsname;
-asmlinkage int sys_olduname(struct oldold_utsname __user *);
-
-/* kernel/tls.c */
-asmlinkage int sys_set_thread_area(struct user_desc __user *);
-asmlinkage int sys_get_thread_area(struct user_desc __user *);
-
-/* kernel/vm86_32.c */
-asmlinkage int sys_vm86old(struct pt_regs);
-asmlinkage int sys_vm86(struct pt_regs);
-
-#else /* CONFIG_X86_32 */
-
-/* X86_64 only */
-/* kernel/process_64.c */
-asmlinkage long sys_fork(struct pt_regs *);
-asmlinkage long sys_clone(unsigned long, unsigned long,
-			  void __user *, void __user *,
-			  struct pt_regs *);
-asmlinkage long sys_vfork(struct pt_regs *);
-asmlinkage long sys_execve(char __user *, char __user * __user *,
-			   char __user * __user *,
-			   struct pt_regs *);
-
-/* kernel/ioport.c */
-asmlinkage long sys_iopl(unsigned int, struct pt_regs *);
-
-/* kernel/signal_64.c */
-asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
-				struct pt_regs *);
-asmlinkage long sys_rt_sigreturn(struct pt_regs *);
-
-/* kernel/sys_x86_64.c */
-asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
-			 unsigned long, unsigned long, unsigned long);
-struct new_utsname;
-asmlinkage long sys_uname(struct new_utsname __user *);
-
-#endif /* CONFIG_X86_32 */
-#endif /* _ASM_X86_SYSCALLS_H */
diff --git a/include/asm-x86/system.h b/include/asm-x86/system.h
deleted file mode 100644
index b20c894660f9..000000000000
--- a/include/asm-x86/system.h
+++ /dev/null
@@ -1,425 +0,0 @@
-#ifndef ASM_X86__SYSTEM_H
-#define ASM_X86__SYSTEM_H
-
-#include <asm/asm.h>
-#include <asm/segment.h>
-#include <asm/cpufeature.h>
-#include <asm/cmpxchg.h>
-#include <asm/nops.h>
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-
-/* entries in ARCH_DLINFO: */
-#ifdef CONFIG_IA32_EMULATION
-# define AT_VECTOR_SIZE_ARCH 2
-#else
-# define AT_VECTOR_SIZE_ARCH 1
-#endif
-
-#ifdef CONFIG_X86_32
-
-struct task_struct; /* one of the stranger aspects of C forward declarations */
-struct task_struct *__switch_to(struct task_struct *prev,
-				struct task_struct *next);
-
-/*
- * Saving eflags is important. It switches not only IOPL between tasks,
- * it also protects other tasks from NT leaking through sysenter etc.
- */
-#define switch_to(prev, next, last)					\
-do {									\
-	/*								\
-	 * Context-switching clobbers all registers, so we clobber	\
-	 * them explicitly, via unused output variables.		\
-	 * (EAX and EBP is not listed because EBP is saved/restored	\
-	 * explicitly for wchan access and EAX is the return value of	\
-	 * __switch_to())						\
-	 */								\
-	unsigned long ebx, ecx, edx, esi, edi;				\
-									\
-	asm volatile("pushfl\n\t"		/* save    flags */	\
-		     "pushl %%ebp\n\t"		/* save    EBP   */	\
-		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
-		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
-		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
-		     "pushl %[next_ip]\n\t"	/* restore EIP   */	\
-		     "jmp __switch_to\n"	/* regparm call  */	\
-		     "1:\t"						\
-		     "popl %%ebp\n\t"		/* restore EBP   */	\
-		     "popfl\n"			/* restore flags */	\
-									\
-		     /* output parameters */				\
-		     : [prev_sp] "=m" (prev->thread.sp),		\
-		       [prev_ip] "=m" (prev->thread.ip),		\
-		       "=a" (last),					\
-									\
-		       /* clobbered output registers: */		\
-		       "=b" (ebx), "=c" (ecx), "=d" (edx),		\
-		       "=S" (esi), "=D" (edi)				\
-		       							\
-		       /* input parameters: */				\
-		     : [next_sp]  "m" (next->thread.sp),		\
-		       [next_ip]  "m" (next->thread.ip),		\
-		       							\
-		       /* regparm parameters for __switch_to(): */	\
-		       [prev]     "a" (prev),				\
-		       [next]     "d" (next)				\
-									\
-		     : /* reloaded segment registers */			\
-			"memory");					\
-} while (0)
-
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-#else
-#define __SAVE(reg, offset) "movq %%" #reg ",(14-" #offset ")*8(%%rsp)\n\t"
-#define __RESTORE(reg, offset) "movq (14-" #offset ")*8(%%rsp),%%" #reg "\n\t"
-
-/* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
-
-#define __EXTRA_CLOBBER  \
-	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
-	  "r12", "r13", "r14", "r15"
-
-/* Save restore flags to clear handle leaking NT */
-#define switch_to(prev, next, last) \
-	asm volatile(SAVE_CONTEXT						    \
-	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
-	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
-	     "call __switch_to\n\t"					  \
-	     ".globl thread_return\n"					  \
-	     "thread_return:\n\t"					  \
-	     "movq %%gs:%P[pda_pcurrent],%%rsi\n\t"			  \
-	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
-	     LOCK_PREFIX "btr  %[tif_fork],%P[ti_flags](%%r8)\n\t"	  \
-	     "movq %%rax,%%rdi\n\t" 					  \
-	     "jc   ret_from_fork\n\t"					  \
-	     RESTORE_CONTEXT						  \
-	     : "=a" (last)					  	  \
-	     : [next] "S" (next), [prev] "D" (prev),			  \
-	       [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
-	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
-	       [tif_fork] "i" (TIF_FORK),			  	  \
-	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-	       [pda_pcurrent] "i" (offsetof(struct x8664_pda, pcurrent))  \
-	     : "memory", "cc" __EXTRA_CLOBBER)
-#endif
-
-#ifdef __KERNEL__
-#define _set_base(addr, base) do { unsigned long __pr; \
-__asm__ __volatile__ ("movw %%dx,%1\n\t" \
-	"rorl $16,%%edx\n\t" \
-	"movb %%dl,%2\n\t" \
-	"movb %%dh,%3" \
-	:"=&d" (__pr) \
-	:"m" (*((addr)+2)), \
-	 "m" (*((addr)+4)), \
-	 "m" (*((addr)+7)), \
-	 "0" (base) \
-	); } while (0)
-
-#define _set_limit(addr, limit) do { unsigned long __lr; \
-__asm__ __volatile__ ("movw %%dx,%1\n\t" \
-	"rorl $16,%%edx\n\t" \
-	"movb %2,%%dh\n\t" \
-	"andb $0xf0,%%dh\n\t" \
-	"orb %%dh,%%dl\n\t" \
-	"movb %%dl,%2" \
-	:"=&d" (__lr) \
-	:"m" (*(addr)), \
-	 "m" (*((addr)+6)), \
-	 "0" (limit) \
-	); } while (0)
-
-#define set_base(ldt, base) _set_base(((char *)&(ldt)) , (base))
-#define set_limit(ldt, limit) _set_limit(((char *)&(ldt)) , ((limit)-1))
-
-extern void native_load_gs_index(unsigned);
-
-/*
- * Load a segment. Fall back on loading the zero
- * segment if something goes wrong..
- */
-#define loadsegment(seg, value)			\
-	asm volatile("\n"			\
-		     "1:\t"			\
-		     "movl %k0,%%" #seg "\n"	\
-		     "2:\n"			\
-		     ".section .fixup,\"ax\"\n"	\
-		     "3:\t"			\
-		     "movl %k1, %%" #seg "\n\t"	\
-		     "jmp 2b\n"			\
-		     ".previous\n"		\
-		     _ASM_EXTABLE(1b,3b)	\
-		     : :"r" (value), "r" (0) : "memory")
-
-
-/*
- * Save a segment register away
- */
-#define savesegment(seg, value)				\
-	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
-
-static inline unsigned long get_limit(unsigned long segment)
-{
-	unsigned long __limit;
-	asm("lsll %1,%0" : "=r" (__limit) : "r" (segment));
-	return __limit + 1;
-}
-
-static inline void native_clts(void)
-{
-	asm volatile("clts");
-}
-
-/*
- * Volatile isn't enough to prevent the compiler from reordering the
- * read/write functions for the control registers and messing everything up.
- * A memory clobber would solve the problem, but would prevent reordering of
- * all loads stores around it, which can hurt performance. Solution is to
- * use a variable and mimic reads and writes to it to enforce serialization
- */
-static unsigned long __force_order;
-
-static inline unsigned long native_read_cr0(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr0(unsigned long val)
-{
-	asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr2(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr2(unsigned long val)
-{
-	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr3(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr3(unsigned long val)
-{
-	asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr4(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline unsigned long native_read_cr4_safe(void)
-{
-	unsigned long val;
-	/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
-	 * exists, so it will never fail. */
-#ifdef CONFIG_X86_32
-	asm volatile("1: mov %%cr4, %0\n"
-		     "2:\n"
-		     _ASM_EXTABLE(1b, 2b)
-		     : "=r" (val), "=m" (__force_order) : "0" (0));
-#else
-	val = native_read_cr4();
-#endif
-	return val;
-}
-
-static inline void native_write_cr4(unsigned long val)
-{
-	asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
-}
-
-#ifdef CONFIG_X86_64
-static inline unsigned long native_read_cr8(void)
-{
-	unsigned long cr8;
-	asm volatile("movq %%cr8,%0" : "=r" (cr8));
-	return cr8;
-}
-
-static inline void native_write_cr8(unsigned long val)
-{
-	asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
-}
-#endif
-
-static inline void native_wbinvd(void)
-{
-	asm volatile("wbinvd": : :"memory");
-}
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-#define read_cr0()	(native_read_cr0())
-#define write_cr0(x)	(native_write_cr0(x))
-#define read_cr2()	(native_read_cr2())
-#define write_cr2(x)	(native_write_cr2(x))
-#define read_cr3()	(native_read_cr3())
-#define write_cr3(x)	(native_write_cr3(x))
-#define read_cr4()	(native_read_cr4())
-#define read_cr4_safe()	(native_read_cr4_safe())
-#define write_cr4(x)	(native_write_cr4(x))
-#define wbinvd()	(native_wbinvd())
-#ifdef CONFIG_X86_64
-#define read_cr8()	(native_read_cr8())
-#define write_cr8(x)	(native_write_cr8(x))
-#define load_gs_index   native_load_gs_index
-#endif
-
-/* Clear the 'TS' bit */
-#define clts()		(native_clts())
-
-#endif/* CONFIG_PARAVIRT */
-
-#define stts() write_cr0(read_cr0() | X86_CR0_TS)
-
-#endif /* __KERNEL__ */
-
-static inline void clflush(volatile void *__p)
-{
-	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
-}
-
-#define nop() asm volatile ("nop")
-
-void disable_hlt(void);
-void enable_hlt(void);
-
-void cpu_idle_wait(void);
-
-extern unsigned long arch_align_stack(unsigned long sp);
-extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
-
-void default_idle(void);
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- */
-#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
-#else
-#define mb() 	asm volatile("mfence":::"memory")
-#define rmb()	asm volatile("lfence":::"memory")
-#define wmb()	asm volatile("sfence" ::: "memory")
-#endif
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb()	rmb()
-#else
-# define smp_rmb()	barrier()
-#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() 	wmb()
-#else
-# define smp_wmb()	barrier()
-#endif
-#define smp_read_barrier_depends()	read_barrier_depends()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- *
- * (Could use an alternative three way for this if there was one.)
- */
-static inline void rdtsc_barrier(void)
-{
-	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
-	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
-#endif /* ASM_X86__SYSTEM_H */
diff --git a/include/asm-x86/system_64.h b/include/asm-x86/system_64.h
deleted file mode 100644
index 5aedb8bffc5a..000000000000
--- a/include/asm-x86/system_64.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef ASM_X86__SYSTEM_64_H
-#define ASM_X86__SYSTEM_64_H
-
-#include <asm/segment.h>
-#include <asm/cmpxchg.h>
-
-
-static inline unsigned long read_cr8(void)
-{
-	unsigned long cr8;
-	asm volatile("movq %%cr8,%0" : "=r" (cr8));
-	return cr8;
-}
-
-static inline void write_cr8(unsigned long val)
-{
-	asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
-}
-
-#include <linux/irqflags.h>
-
-#endif /* ASM_X86__SYSTEM_64_H */
diff --git a/include/asm-x86/tce.h b/include/asm-x86/tce.h
deleted file mode 100644
index e7932d7fbbab..000000000000
--- a/include/asm-x86/tce.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/*
- * This file is derived from asm-powerpc/tce.h.
- *
- * Copyright (C) IBM Corporation, 2006
- *
- * Author: Muli Ben-Yehuda <muli@il.ibm.com>
- * Author: Jon Mason <jdmason@us.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- */
-
-#ifndef ASM_X86__TCE_H
-#define ASM_X86__TCE_H
-
-extern unsigned int specified_table_size;
-struct iommu_table;
-
-#define TCE_ENTRY_SIZE   8   /* in bytes */
-
-#define TCE_READ_SHIFT   0
-#define TCE_WRITE_SHIFT  1
-#define TCE_HUBID_SHIFT  2   /* unused */
-#define TCE_RSVD_SHIFT   8   /* unused */
-#define TCE_RPN_SHIFT    12
-#define TCE_UNUSED_SHIFT 48  /* unused */
-
-#define TCE_RPN_MASK     0x0000fffffffff000ULL
-
-extern void tce_build(struct iommu_table *tbl, unsigned long index,
-		      unsigned int npages, unsigned long uaddr, int direction);
-extern void tce_free(struct iommu_table *tbl, long index, unsigned int npages);
-extern void * __init alloc_tce_table(void);
-extern void __init free_tce_table(void *tbl);
-extern int __init build_tce_table(struct pci_dev *dev, void __iomem *bbar);
-
-#endif /* ASM_X86__TCE_H */
diff --git a/include/asm-x86/termbits.h b/include/asm-x86/termbits.h
deleted file mode 100644
index 3d00dc5e0c71..000000000000
--- a/include/asm-x86/termbits.h
+++ /dev/null
@@ -1,198 +0,0 @@
-#ifndef ASM_X86__TERMBITS_H
-#define ASM_X86__TERMBITS_H
-
-#include <linux/posix_types.h>
-
-typedef unsigned char	cc_t;
-typedef unsigned int	speed_t;
-typedef unsigned int	tcflag_t;
-
-#define NCCS 19
-struct termios {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-};
-
-struct termios2 {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-	speed_t c_ispeed;		/* input speed */
-	speed_t c_ospeed;		/* output speed */
-};
-
-struct ktermios {
-	tcflag_t c_iflag;		/* input mode flags */
-	tcflag_t c_oflag;		/* output mode flags */
-	tcflag_t c_cflag;		/* control mode flags */
-	tcflag_t c_lflag;		/* local mode flags */
-	cc_t c_line;			/* line discipline */
-	cc_t c_cc[NCCS];		/* control characters */
-	speed_t c_ispeed;		/* input speed */
-	speed_t c_ospeed;		/* output speed */
-};
-
-/* c_cc characters */
-#define VINTR 0
-#define VQUIT 1
-#define VERASE 2
-#define VKILL 3
-#define VEOF 4
-#define VTIME 5
-#define VMIN 6
-#define VSWTC 7
-#define VSTART 8
-#define VSTOP 9
-#define VSUSP 10
-#define VEOL 11
-#define VREPRINT 12
-#define VDISCARD 13
-#define VWERASE 14
-#define VLNEXT 15
-#define VEOL2 16
-
-/* c_iflag bits */
-#define IGNBRK	0000001
-#define BRKINT	0000002
-#define IGNPAR	0000004
-#define PARMRK	0000010
-#define INPCK	0000020
-#define ISTRIP	0000040
-#define INLCR	0000100
-#define IGNCR	0000200
-#define ICRNL	0000400
-#define IUCLC	0001000
-#define IXON	0002000
-#define IXANY	0004000
-#define IXOFF	0010000
-#define IMAXBEL	0020000
-#define IUTF8	0040000
-
-/* c_oflag bits */
-#define OPOST	0000001
-#define OLCUC	0000002
-#define ONLCR	0000004
-#define OCRNL	0000010
-#define ONOCR	0000020
-#define ONLRET	0000040
-#define OFILL	0000100
-#define OFDEL	0000200
-#define NLDLY	0000400
-#define   NL0	0000000
-#define   NL1	0000400
-#define CRDLY	0003000
-#define   CR0	0000000
-#define   CR1	0001000
-#define   CR2	0002000
-#define   CR3	0003000
-#define TABDLY	0014000
-#define   TAB0	0000000
-#define   TAB1	0004000
-#define   TAB2	0010000
-#define   TAB3	0014000
-#define   XTABS	0014000
-#define BSDLY	0020000
-#define   BS0	0000000
-#define   BS1	0020000
-#define VTDLY	0040000
-#define   VT0	0000000
-#define   VT1	0040000
-#define FFDLY	0100000
-#define   FF0	0000000
-#define   FF1	0100000
-
-/* c_cflag bit meaning */
-#define CBAUD	0010017
-#define  B0	0000000		/* hang up */
-#define  B50	0000001
-#define  B75	0000002
-#define  B110	0000003
-#define  B134	0000004
-#define  B150	0000005
-#define  B200	0000006
-#define  B300	0000007
-#define  B600	0000010
-#define  B1200	0000011
-#define  B1800	0000012
-#define  B2400	0000013
-#define  B4800	0000014
-#define  B9600	0000015
-#define  B19200	0000016
-#define  B38400	0000017
-#define EXTA B19200
-#define EXTB B38400
-#define CSIZE	0000060
-#define   CS5	0000000
-#define   CS6	0000020
-#define   CS7	0000040
-#define   CS8	0000060
-#define CSTOPB	0000100
-#define CREAD	0000200
-#define PARENB	0000400
-#define PARODD	0001000
-#define HUPCL	0002000
-#define CLOCAL	0004000
-#define CBAUDEX 0010000
-#define	   BOTHER 0010000		/* non standard rate */
-#define    B57600 0010001
-#define   B115200 0010002
-#define   B230400 0010003
-#define   B460800 0010004
-#define   B500000 0010005
-#define   B576000 0010006
-#define   B921600 0010007
-#define  B1000000 0010010
-#define  B1152000 0010011
-#define  B1500000 0010012
-#define  B2000000 0010013
-#define  B2500000 0010014
-#define  B3000000 0010015
-#define  B3500000 0010016
-#define  B4000000 0010017
-#define CIBAUD	  002003600000	/* input baud rate */
-#define CMSPAR	  010000000000	/* mark or space (stick) parity */
-#define CRTSCTS	  020000000000	/* flow control */
-
-#define IBSHIFT	  16		/* Shift from CBAUD to CIBAUD */
-
-/* c_lflag bits */
-#define ISIG	0000001
-#define ICANON	0000002
-#define XCASE	0000004
-#define ECHO	0000010
-#define ECHOE	0000020
-#define ECHOK	0000040
-#define ECHONL	0000100
-#define NOFLSH	0000200
-#define TOSTOP	0000400
-#define ECHOCTL	0001000
-#define ECHOPRT	0002000
-#define ECHOKE	0004000
-#define FLUSHO	0010000
-#define PENDIN	0040000
-#define IEXTEN	0100000
-
-/* tcflow() and TCXONC use these */
-#define	TCOOFF		0
-#define	TCOON		1
-#define	TCIOFF		2
-#define	TCION		3
-
-/* tcflush() and TCFLSH use these */
-#define	TCIFLUSH	0
-#define	TCOFLUSH	1
-#define	TCIOFLUSH	2
-
-/* tcsetattr uses these */
-#define	TCSANOW		0
-#define	TCSADRAIN	1
-#define	TCSAFLUSH	2
-
-#endif /* ASM_X86__TERMBITS_H */
diff --git a/include/asm-x86/termios.h b/include/asm-x86/termios.h
deleted file mode 100644
index e235db248071..000000000000
--- a/include/asm-x86/termios.h
+++ /dev/null
@@ -1,113 +0,0 @@
-#ifndef ASM_X86__TERMIOS_H
-#define ASM_X86__TERMIOS_H
-
-#include <asm/termbits.h>
-#include <asm/ioctls.h>
-
-struct winsize {
-	unsigned short ws_row;
-	unsigned short ws_col;
-	unsigned short ws_xpixel;
-	unsigned short ws_ypixel;
-};
-
-#define NCC 8
-struct termio {
-	unsigned short c_iflag;		/* input mode flags */
-	unsigned short c_oflag;		/* output mode flags */
-	unsigned short c_cflag;		/* control mode flags */
-	unsigned short c_lflag;		/* local mode flags */
-	unsigned char c_line;		/* line discipline */
-	unsigned char c_cc[NCC];	/* control characters */
-};
-
-/* modem lines */
-#define TIOCM_LE	0x001
-#define TIOCM_DTR	0x002
-#define TIOCM_RTS	0x004
-#define TIOCM_ST	0x008
-#define TIOCM_SR	0x010
-#define TIOCM_CTS	0x020
-#define TIOCM_CAR	0x040
-#define TIOCM_RNG	0x080
-#define TIOCM_DSR	0x100
-#define TIOCM_CD	TIOCM_CAR
-#define TIOCM_RI	TIOCM_RNG
-#define TIOCM_OUT1	0x2000
-#define TIOCM_OUT2	0x4000
-#define TIOCM_LOOP	0x8000
-
-/* ioctl (fd, TIOCSERGETLSR, &result) where result may be as below */
-
-#ifdef __KERNEL__
-
-#include <asm/uaccess.h>
-
-/*	intr=^C		quit=^\		erase=del	kill=^U
-	eof=^D		vtime=\0	vmin=\1		sxtc=\0
-	start=^Q	stop=^S		susp=^Z		eol=\0
-	reprint=^R	discard=^U	werase=^W	lnext=^V
-	eol2=\0
-*/
-#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0"
-
-/*
- * Translate a "termio" structure into a "termios". Ugh.
- */
-#define SET_LOW_TERMIOS_BITS(termios, termio, x) { \
-	unsigned short __tmp; \
-	get_user(__tmp,&(termio)->x); \
-	*(unsigned short *) &(termios)->x = __tmp; \
-}
-
-static inline int user_termio_to_kernel_termios(struct ktermios *termios,
-						struct termio __user *termio)
-{
-	SET_LOW_TERMIOS_BITS(termios, termio, c_iflag);
-	SET_LOW_TERMIOS_BITS(termios, termio, c_oflag);
-	SET_LOW_TERMIOS_BITS(termios, termio, c_cflag);
-	SET_LOW_TERMIOS_BITS(termios, termio, c_lflag);
-	return copy_from_user(termios->c_cc, termio->c_cc, NCC);
-}
-
-/*
- * Translate a "termios" structure into a "termio". Ugh.
- */
-static inline int kernel_termios_to_user_termio(struct termio __user *termio,
-					    struct ktermios *termios)
-{
-	put_user((termios)->c_iflag, &(termio)->c_iflag);
-	put_user((termios)->c_oflag, &(termio)->c_oflag);
-	put_user((termios)->c_cflag, &(termio)->c_cflag);
-	put_user((termios)->c_lflag, &(termio)->c_lflag);
-	put_user((termios)->c_line,  &(termio)->c_line);
-	return copy_to_user((termio)->c_cc, (termios)->c_cc, NCC);
-}
-
-static inline int user_termios_to_kernel_termios(struct ktermios *k,
-						 struct termios2 __user *u)
-{
-	return copy_from_user(k, u, sizeof(struct termios2));
-}
-
-static inline int kernel_termios_to_user_termios(struct termios2 __user *u,
-						 struct ktermios *k)
-{
-	return copy_to_user(u, k, sizeof(struct termios2));
-}
-
-static inline int user_termios_to_kernel_termios_1(struct ktermios *k,
-						   struct termios __user *u)
-{
-	return copy_from_user(k, u, sizeof(struct termios));
-}
-
-static inline int kernel_termios_to_user_termios_1(struct termios __user *u,
-						   struct ktermios *k)
-{
-	return copy_to_user(u, k, sizeof(struct termios));
-}
-
-#endif	/* __KERNEL__ */
-
-#endif /* ASM_X86__TERMIOS_H */
diff --git a/include/asm-x86/therm_throt.h b/include/asm-x86/therm_throt.h
deleted file mode 100644
index 1c7f57b6b66e..000000000000
--- a/include/asm-x86/therm_throt.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef ASM_X86__THERM_THROT_H
-#define ASM_X86__THERM_THROT_H
-
-#include <asm/atomic.h>
-
-extern atomic_t therm_throt_en;
-int therm_throt_process(int curr);
-
-#endif /* ASM_X86__THERM_THROT_H */
diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h
deleted file mode 100644
index 3f4e52bb77f5..000000000000
--- a/include/asm-x86/thread_info.h
+++ /dev/null
@@ -1,264 +0,0 @@
-/* thread_info.h: low-level thread information
- *
- * Copyright (C) 2002  David Howells (dhowells@redhat.com)
- * - Incorporating suggestions made by Linus Torvalds and Dave Miller
- */
-
-#ifndef ASM_X86__THREAD_INFO_H
-#define ASM_X86__THREAD_INFO_H
-
-#include <linux/compiler.h>
-#include <asm/page.h>
-#include <asm/types.h>
-
-/*
- * low level task data that entry.S needs immediate access to
- * - this struct should fit entirely inside of one cache line
- * - this struct shares the supervisor stack pages
- */
-#ifndef __ASSEMBLY__
-struct task_struct;
-struct exec_domain;
-#include <asm/processor.h>
-
-struct thread_info {
-	struct task_struct	*task;		/* main task structure */
-	struct exec_domain	*exec_domain;	/* execution domain */
-	unsigned long		flags;		/* low level flags */
-	__u32			status;		/* thread synchronous flags */
-	__u32			cpu;		/* current CPU */
-	int			preempt_count;	/* 0 => preemptable,
-						   <0 => BUG */
-	mm_segment_t		addr_limit;
-	struct restart_block    restart_block;
-	void __user		*sysenter_return;
-#ifdef CONFIG_X86_32
-	unsigned long           previous_esp;   /* ESP of the previous stack in
-						   case of nested (IRQ) stacks
-						*/
-	__u8			supervisor_stack[0];
-#endif
-};
-
-#define INIT_THREAD_INFO(tsk)			\
-{						\
-	.task		= &tsk,			\
-	.exec_domain	= &default_exec_domain,	\
-	.flags		= 0,			\
-	.cpu		= 0,			\
-	.preempt_count	= 1,			\
-	.addr_limit	= KERNEL_DS,		\
-	.restart_block = {			\
-		.fn = do_no_restart_syscall,	\
-	},					\
-}
-
-#define init_thread_info	(init_thread_union.thread_info)
-#define init_stack		(init_thread_union.stack)
-
-#else /* !__ASSEMBLY__ */
-
-#include <asm/asm-offsets.h>
-
-#endif
-
-/*
- * thread information flags
- * - these are process state flags that various assembly files
- *   may need to access
- * - pending work-to-be-done flags are in LSW
- * - other flags in MSW
- * Warning: layout of LSW is hardcoded in entry.S
- */
-#define TIF_SYSCALL_TRACE	0	/* syscall trace active */
-#define TIF_NOTIFY_RESUME	1	/* callback before returning to user */
-#define TIF_SIGPENDING		2	/* signal pending */
-#define TIF_NEED_RESCHED	3	/* rescheduling necessary */
-#define TIF_SINGLESTEP		4	/* reenable singlestep on user return*/
-#define TIF_IRET		5	/* force IRET */
-#define TIF_SYSCALL_EMU		6	/* syscall emulation active */
-#define TIF_SYSCALL_AUDIT	7	/* syscall auditing active */
-#define TIF_SECCOMP		8	/* secure computing */
-#define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
-#define TIF_NOTSC		16	/* TSC is not accessible in userland */
-#define TIF_IA32		17	/* 32bit process */
-#define TIF_FORK		18	/* ret_from_fork */
-#define TIF_ABI_PENDING		19
-#define TIF_MEMDIE		20
-#define TIF_DEBUG		21	/* uses debug registers */
-#define TIF_IO_BITMAP		22	/* uses I/O bitmap */
-#define TIF_FREEZE		23	/* is freezing for suspend */
-#define TIF_FORCED_TF		24	/* true if TF in eflags artificially */
-#define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
-#define TIF_BTS_TRACE_TS	27      /* record scheduling event timestamps */
-
-#define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
-#define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
-#define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
-#define _TIF_SINGLESTEP		(1 << TIF_SINGLESTEP)
-#define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
-#define _TIF_IRET		(1 << TIF_IRET)
-#define _TIF_SYSCALL_EMU	(1 << TIF_SYSCALL_EMU)
-#define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
-#define _TIF_SECCOMP		(1 << TIF_SECCOMP)
-#define _TIF_MCE_NOTIFY		(1 << TIF_MCE_NOTIFY)
-#define _TIF_NOTSC		(1 << TIF_NOTSC)
-#define _TIF_IA32		(1 << TIF_IA32)
-#define _TIF_FORK		(1 << TIF_FORK)
-#define _TIF_ABI_PENDING	(1 << TIF_ABI_PENDING)
-#define _TIF_DEBUG		(1 << TIF_DEBUG)
-#define _TIF_IO_BITMAP		(1 << TIF_IO_BITMAP)
-#define _TIF_FREEZE		(1 << TIF_FREEZE)
-#define _TIF_FORCED_TF		(1 << TIF_FORCED_TF)
-#define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
-#define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
-#define _TIF_BTS_TRACE_TS	(1 << TIF_BTS_TRACE_TS)
-
-/* work to do in syscall_trace_enter() */
-#define _TIF_WORK_SYSCALL_ENTRY	\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | \
-	 _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP)
-
-/* work to do in syscall_trace_leave() */
-#define _TIF_WORK_SYSCALL_EXIT	\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP)
-
-/* work to do on interrupt/exception return */
-#define _TIF_WORK_MASK							\
-	(0x0000FFFF &							\
-	 ~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT|			\
-	   _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU))
-
-/* work to do on any return to user space */
-#define _TIF_ALLWORK_MASK (0x0000FFFF & ~_TIF_SECCOMP)
-
-/* Only used for 64 bit */
-#define _TIF_DO_NOTIFY_MASK						\
-	(_TIF_SIGPENDING|_TIF_MCE_NOTIFY|_TIF_NOTIFY_RESUME)
-
-/* flags to check in __switch_to() */
-#define _TIF_WORK_CTXSW							\
-	(_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_BTS_TRACE_TS| \
-								_TIF_NOTSC)
-
-#define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
-#define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
-
-#define PREEMPT_ACTIVE		0x10000000
-
-/* thread information allocation */
-#ifdef CONFIG_DEBUG_STACK_USAGE
-#define THREAD_FLAGS (GFP_KERNEL | __GFP_ZERO)
-#else
-#define THREAD_FLAGS GFP_KERNEL
-#endif
-
-#define __HAVE_ARCH_THREAD_INFO_ALLOCATOR
-
-#define alloc_thread_info(tsk)						\
-	((struct thread_info *)__get_free_pages(THREAD_FLAGS, THREAD_ORDER))
-
-#ifdef CONFIG_X86_32
-
-#define STACK_WARN	(THREAD_SIZE/8)
-/*
- * macros/functions for gaining access to the thread information structure
- *
- * preempt_count needs to be 1 initially, until the scheduler is functional.
- */
-#ifndef __ASSEMBLY__
-
-
-/* how to get the current stack pointer from C */
-register unsigned long current_stack_pointer asm("esp") __used;
-
-/* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-	return (struct thread_info *)
-		(current_stack_pointer & ~(THREAD_SIZE - 1));
-}
-
-#else /* !__ASSEMBLY__ */
-
-/* how to get the thread information struct from ASM */
-#define GET_THREAD_INFO(reg)	 \
-	movl $-THREAD_SIZE, reg; \
-	andl %esp, reg
-
-/* use this one if reg already contains %esp */
-#define GET_THREAD_INFO_WITH_ESP(reg) \
-	andl $-THREAD_SIZE, reg
-
-#endif
-
-#else /* X86_32 */
-
-#include <asm/pda.h>
-
-/*
- * macros/functions for gaining access to the thread information structure
- * preempt_count needs to be 1 initially, until the scheduler is functional.
- */
-#ifndef __ASSEMBLY__
-static inline struct thread_info *current_thread_info(void)
-{
-	struct thread_info *ti;
-	ti = (void *)(read_pda(kernelstack) + PDA_STACKOFFSET - THREAD_SIZE);
-	return ti;
-}
-
-/* do not use in interrupt context */
-static inline struct thread_info *stack_thread_info(void)
-{
-	struct thread_info *ti;
-	asm("andq %%rsp,%0; " : "=r" (ti) : "0" (~(THREAD_SIZE - 1)));
-	return ti;
-}
-
-#else /* !__ASSEMBLY__ */
-
-/* how to get the thread information struct from ASM */
-#define GET_THREAD_INFO(reg) \
-	movq %gs:pda_kernelstack,reg ; \
-	subq $(THREAD_SIZE-PDA_STACKOFFSET),reg
-
-#endif
-
-#endif /* !X86_32 */
-
-/*
- * Thread-synchronous status.
- *
- * This is different from the flags in that nobody else
- * ever touches our thread-synchronous status, so we don't
- * have to worry about atomic accesses.
- */
-#define TS_USEDFPU		0x0001	/* FPU was used by this task
-					   this quantum (SMP) */
-#define TS_COMPAT		0x0002	/* 32bit syscall active (64BIT)*/
-#define TS_POLLING		0x0004	/* true if in idle loop
-					   and not sleeping */
-#define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal() */
-#define TS_XSAVE		0x0010	/* Use xsave/xrstor */
-
-#define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
-
-#ifndef __ASSEMBLY__
-#define HAVE_SET_RESTORE_SIGMASK	1
-static inline void set_restore_sigmask(void)
-{
-	struct thread_info *ti = current_thread_info();
-	ti->status |= TS_RESTORE_SIGMASK;
-	set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags);
-}
-#endif	/* !__ASSEMBLY__ */
-
-#ifndef __ASSEMBLY__
-extern void arch_task_cache_init(void);
-extern void free_thread_info(struct thread_info *ti);
-extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
-#define arch_task_cache_init arch_task_cache_init
-#endif
-#endif /* ASM_X86__THREAD_INFO_H */
diff --git a/include/asm-x86/time.h b/include/asm-x86/time.h
deleted file mode 100644
index 3e724eef7ac4..000000000000
--- a/include/asm-x86/time.h
+++ /dev/null
@@ -1,63 +0,0 @@
-#ifndef ASM_X86__TIME_H
-#define ASM_X86__TIME_H
-
-extern void hpet_time_init(void);
-
-#include <asm/mc146818rtc.h>
-#ifdef CONFIG_X86_32
-#include <linux/efi.h>
-
-static inline unsigned long native_get_wallclock(void)
-{
-	unsigned long retval;
-
-	if (efi_enabled)
-		retval = efi_get_time();
-	else
-		retval = mach_get_cmos_time();
-
-	return retval;
-}
-
-static inline int native_set_wallclock(unsigned long nowtime)
-{
-	int retval;
-
-	if (efi_enabled)
-		retval = efi_set_rtc_mmss(nowtime);
-	else
-		retval = mach_set_rtc_mmss(nowtime);
-
-	return retval;
-}
-
-#else
-extern void native_time_init_hook(void);
-
-static inline unsigned long native_get_wallclock(void)
-{
-	return mach_get_cmos_time();
-}
-
-static inline int native_set_wallclock(unsigned long nowtime)
-{
-	return mach_set_rtc_mmss(nowtime);
-}
-
-#endif
-
-extern void time_init(void);
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else /* !CONFIG_PARAVIRT */
-
-#define get_wallclock() native_get_wallclock()
-#define set_wallclock(x) native_set_wallclock(x)
-#define choose_time_init() hpet_time_init
-
-#endif /* CONFIG_PARAVIRT */
-
-extern unsigned long __init calibrate_cpu(void);
-
-#endif /* ASM_X86__TIME_H */
diff --git a/include/asm-x86/timer.h b/include/asm-x86/timer.h
deleted file mode 100644
index d0babce4b47a..000000000000
--- a/include/asm-x86/timer.h
+++ /dev/null
@@ -1,66 +0,0 @@
-#ifndef ASM_X86__TIMER_H
-#define ASM_X86__TIMER_H
-#include <linux/init.h>
-#include <linux/pm.h>
-#include <linux/percpu.h>
-
-#define TICK_SIZE (tick_nsec / 1000)
-
-unsigned long long native_sched_clock(void);
-unsigned long native_calibrate_tsc(void);
-
-#ifdef CONFIG_X86_32
-extern int timer_ack;
-extern int recalibrate_cpu_khz(void);
-#endif /* CONFIG_X86_32 */
-
-extern int no_timer_check;
-
-#ifndef CONFIG_PARAVIRT
-#define calibrate_tsc() native_calibrate_tsc()
-#endif
-
-/* Accelerators for sched_clock()
- * convert from cycles(64bits) => nanoseconds (64bits)
- *  basic equation:
- *		ns = cycles / (freq / ns_per_sec)
- *		ns = cycles * (ns_per_sec / freq)
- *		ns = cycles * (10^9 / (cpu_khz * 10^3))
- *		ns = cycles * (10^6 / cpu_khz)
- *
- *	Then we use scaling math (suggested by george@mvista.com) to get:
- *		ns = cycles * (10^6 * SC / cpu_khz) / SC
- *		ns = cycles * cyc2ns_scale / SC
- *
- *	And since SC is a constant power of two, we can convert the div
- *  into a shift.
- *
- *  We can use khz divisor instead of mhz to keep a better precision, since
- *  cyc2ns_scale is limited to 10^6 * 2^10, which fits in 32 bits.
- *  (mathieu.desnoyers@polymtl.ca)
- *
- *			-johnstul@us.ibm.com "math is hard, lets go shopping!"
- */
-
-DECLARE_PER_CPU(unsigned long, cyc2ns);
-
-#define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
-
-static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
-{
-	return cyc * per_cpu(cyc2ns, smp_processor_id()) >> CYC2NS_SCALE_FACTOR;
-}
-
-static inline unsigned long long cycles_2_ns(unsigned long long cyc)
-{
-	unsigned long long ns;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	ns = __cycles_2_ns(cyc);
-	local_irq_restore(flags);
-
-	return ns;
-}
-
-#endif /* ASM_X86__TIMER_H */
diff --git a/include/asm-x86/timex.h b/include/asm-x86/timex.h
deleted file mode 100644
index d1ce2416a5da..000000000000
--- a/include/asm-x86/timex.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* x86 architecture timex specifications */
-#ifndef ASM_X86__TIMEX_H
-#define ASM_X86__TIMEX_H
-
-#include <asm/processor.h>
-#include <asm/tsc.h>
-
-#ifdef CONFIG_X86_ELAN
-#  define PIT_TICK_RATE 1189200 /* AMD Elan has different frequency! */
-#elif defined(CONFIG_X86_RDC321X)
-#  define PIT_TICK_RATE 1041667 /* Underlying HZ for R8610 */
-#else
-#  define PIT_TICK_RATE 1193182 /* Underlying HZ */
-#endif
-#define CLOCK_TICK_RATE	PIT_TICK_RATE
-
-#define ARCH_HAS_READ_CURRENT_TIMER
-
-#endif /* ASM_X86__TIMEX_H */
diff --git a/include/asm-x86/tlb.h b/include/asm-x86/tlb.h
deleted file mode 100644
index db36e9e89e87..000000000000
--- a/include/asm-x86/tlb.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef ASM_X86__TLB_H
-#define ASM_X86__TLB_H
-
-#define tlb_start_vma(tlb, vma) do { } while (0)
-#define tlb_end_vma(tlb, vma) do { } while (0)
-#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
-
-#include <asm-generic/tlb.h>
-
-#endif /* ASM_X86__TLB_H */
diff --git a/include/asm-x86/tlbflush.h b/include/asm-x86/tlbflush.h
deleted file mode 100644
index 3cdd08b5bdb7..000000000000
--- a/include/asm-x86/tlbflush.h
+++ /dev/null
@@ -1,178 +0,0 @@
-#ifndef ASM_X86__TLBFLUSH_H
-#define ASM_X86__TLBFLUSH_H
-
-#include <linux/mm.h>
-#include <linux/sched.h>
-
-#include <asm/processor.h>
-#include <asm/system.h>
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-#define __flush_tlb() __native_flush_tlb()
-#define __flush_tlb_global() __native_flush_tlb_global()
-#define __flush_tlb_single(addr) __native_flush_tlb_single(addr)
-#endif
-
-static inline void __native_flush_tlb(void)
-{
-	write_cr3(read_cr3());
-}
-
-static inline void __native_flush_tlb_global(void)
-{
-	unsigned long flags;
-	unsigned long cr4;
-
-	/*
-	 * Read-modify-write to CR4 - protect it from preemption and
-	 * from interrupts. (Use the raw variant because this code can
-	 * be called from deep inside debugging code.)
-	 */
-	raw_local_irq_save(flags);
-
-	cr4 = read_cr4();
-	/* clear PGE */
-	write_cr4(cr4 & ~X86_CR4_PGE);
-	/* write old PGE again and flush TLBs */
-	write_cr4(cr4);
-
-	raw_local_irq_restore(flags);
-}
-
-static inline void __native_flush_tlb_single(unsigned long addr)
-{
-	asm volatile("invlpg (%0)" ::"r" (addr) : "memory");
-}
-
-static inline void __flush_tlb_all(void)
-{
-	if (cpu_has_pge)
-		__flush_tlb_global();
-	else
-		__flush_tlb();
-}
-
-static inline void __flush_tlb_one(unsigned long addr)
-{
-	if (cpu_has_invlpg)
-		__flush_tlb_single(addr);
-	else
-		__flush_tlb();
-}
-
-#ifdef CONFIG_X86_32
-# define TLB_FLUSH_ALL	0xffffffff
-#else
-# define TLB_FLUSH_ALL	-1ULL
-#endif
-
-/*
- * TLB flushing:
- *
- *  - flush_tlb() flushes the current mm struct TLBs
- *  - flush_tlb_all() flushes all processes TLBs
- *  - flush_tlb_mm(mm) flushes the specified mm context TLB's
- *  - flush_tlb_page(vma, vmaddr) flushes one page
- *  - flush_tlb_range(vma, start, end) flushes a range of pages
- *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
- *  - flush_tlb_others(cpumask, mm, va) flushes TLBs on other cpus
- *
- * ..but the i386 has somewhat limited tlb flushing capabilities,
- * and page-granular flushes are available only on i486 and up.
- *
- * x86-64 can only flush individual pages or full VMs. For a range flush
- * we always do the full VM. Might be worth trying if for a small
- * range a few INVLPGs in a row are a win.
- */
-
-#ifndef CONFIG_SMP
-
-#define flush_tlb() __flush_tlb()
-#define flush_tlb_all() __flush_tlb_all()
-#define local_flush_tlb() __flush_tlb()
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	if (mm == current->active_mm)
-		__flush_tlb();
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma,
-				  unsigned long addr)
-{
-	if (vma->vm_mm == current->active_mm)
-		__flush_tlb_one(addr);
-}
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end)
-{
-	if (vma->vm_mm == current->active_mm)
-		__flush_tlb();
-}
-
-static inline void native_flush_tlb_others(const cpumask_t *cpumask,
-					   struct mm_struct *mm,
-					   unsigned long va)
-{
-}
-
-static inline void reset_lazy_tlbstate(void)
-{
-}
-
-#else  /* SMP */
-
-#include <asm/smp.h>
-
-#define local_flush_tlb() __flush_tlb()
-
-extern void flush_tlb_all(void);
-extern void flush_tlb_current_task(void);
-extern void flush_tlb_mm(struct mm_struct *);
-extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
-
-#define flush_tlb()	flush_tlb_current_task()
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end)
-{
-	flush_tlb_mm(vma->vm_mm);
-}
-
-void native_flush_tlb_others(const cpumask_t *cpumask, struct mm_struct *mm,
-			     unsigned long va);
-
-#define TLBSTATE_OK	1
-#define TLBSTATE_LAZY	2
-
-#ifdef CONFIG_X86_32
-struct tlb_state {
-	struct mm_struct *active_mm;
-	int state;
-	char __cacheline_padding[L1_CACHE_BYTES-8];
-};
-DECLARE_PER_CPU(struct tlb_state, cpu_tlbstate);
-
-void reset_lazy_tlbstate(void);
-#else
-static inline void reset_lazy_tlbstate(void)
-{
-}
-#endif
-
-#endif	/* SMP */
-
-#ifndef CONFIG_PARAVIRT
-#define flush_tlb_others(mask, mm, va)	native_flush_tlb_others(&mask, mm, va)
-#endif
-
-static inline void flush_tlb_kernel_range(unsigned long start,
-					  unsigned long end)
-{
-	flush_tlb_all();
-}
-
-#endif /* ASM_X86__TLBFLUSH_H */
diff --git a/include/asm-x86/topology.h b/include/asm-x86/topology.h
deleted file mode 100644
index 7eca9bc022b2..000000000000
--- a/include/asm-x86/topology.h
+++ /dev/null
@@ -1,258 +0,0 @@
-/*
- * Written by: Matthew Dobson, IBM Corporation
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to <colpatch@us.ibm.com>
- */
-#ifndef ASM_X86__TOPOLOGY_H
-#define ASM_X86__TOPOLOGY_H
-
-#ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_HT
-#  define ENABLE_TOPO_DEFINES
-# endif
-#else
-# ifdef CONFIG_SMP
-#  define ENABLE_TOPO_DEFINES
-# endif
-#endif
-
-/* Node not present */
-#define NUMA_NO_NODE	(-1)
-
-#ifdef CONFIG_NUMA
-#include <linux/cpumask.h>
-#include <asm/mpspec.h>
-
-#ifdef CONFIG_X86_32
-
-/* Mappings between node number and cpus on that node. */
-extern cpumask_t node_to_cpumask_map[];
-
-/* Mappings between logical cpu number and node number */
-extern int cpu_to_node_map[];
-
-/* Returns the number of the node containing CPU 'cpu' */
-static inline int cpu_to_node(int cpu)
-{
-	return cpu_to_node_map[cpu];
-}
-#define early_cpu_to_node(cpu)	cpu_to_node(cpu)
-
-/* Returns a bitmask of CPUs on Node 'node'.
- *
- * Side note: this function creates the returned cpumask on the stack
- * so with a high NR_CPUS count, excessive stack space is used.  The
- * node_to_cpumask_ptr function should be used whenever possible.
- */
-static inline cpumask_t node_to_cpumask(int node)
-{
-	return node_to_cpumask_map[node];
-}
-
-#else /* CONFIG_X86_64 */
-
-/* Mappings between node number and cpus on that node. */
-extern cpumask_t *node_to_cpumask_map;
-
-/* Mappings between logical cpu number and node number */
-DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
-
-/* Returns the number of the current Node. */
-#define numa_node_id()		read_pda(nodenumber)
-
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-extern int cpu_to_node(int cpu);
-extern int early_cpu_to_node(int cpu);
-extern const cpumask_t *_node_to_cpumask_ptr(int node);
-extern cpumask_t node_to_cpumask(int node);
-
-#else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
-
-/* Returns the number of the node containing CPU 'cpu' */
-static inline int cpu_to_node(int cpu)
-{
-	return per_cpu(x86_cpu_to_node_map, cpu);
-}
-
-/* Same function but used if called before per_cpu areas are setup */
-static inline int early_cpu_to_node(int cpu)
-{
-	if (early_per_cpu_ptr(x86_cpu_to_node_map))
-		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
-
-	return per_cpu(x86_cpu_to_node_map, cpu);
-}
-
-/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
-static inline const cpumask_t *_node_to_cpumask_ptr(int node)
-{
-	return &node_to_cpumask_map[node];
-}
-
-/* Returns a bitmask of CPUs on Node 'node'. */
-static inline cpumask_t node_to_cpumask(int node)
-{
-	return node_to_cpumask_map[node];
-}
-
-#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
-
-/* Replace default node_to_cpumask_ptr with optimized version */
-#define node_to_cpumask_ptr(v, node)		\
-		const cpumask_t *v = _node_to_cpumask_ptr(node)
-
-#define node_to_cpumask_ptr_next(v, node)	\
-			   v = _node_to_cpumask_ptr(node)
-
-#endif /* CONFIG_X86_64 */
-
-/*
- * Returns the number of the node containing Node 'node'. This
- * architecture is flat, so it is a pretty simple function!
- */
-#define parent_node(node) (node)
-
-#define pcibus_to_node(bus) __pcibus_to_node(bus)
-#define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus)
-
-#ifdef CONFIG_X86_32
-extern unsigned long node_start_pfn[];
-extern unsigned long node_end_pfn[];
-extern unsigned long node_remap_size[];
-#define node_has_online_mem(nid) (node_start_pfn[nid] != node_end_pfn[nid])
-
-# define SD_CACHE_NICE_TRIES	1
-# define SD_IDLE_IDX		1
-# define SD_NEWIDLE_IDX		2
-# define SD_FORKEXEC_IDX	0
-
-#else
-
-# define SD_CACHE_NICE_TRIES	2
-# define SD_IDLE_IDX		2
-# define SD_NEWIDLE_IDX		2
-# define SD_FORKEXEC_IDX	1
-
-#endif
-
-/* sched_domains SD_NODE_INIT for NUMAQ machines */
-#define SD_NODE_INIT (struct sched_domain) {		\
-	.min_interval		= 8,			\
-	.max_interval		= 32,			\
-	.busy_factor		= 32,			\
-	.imbalance_pct		= 125,			\
-	.cache_nice_tries	= SD_CACHE_NICE_TRIES,	\
-	.busy_idx		= 3,			\
-	.idle_idx		= SD_IDLE_IDX,		\
-	.newidle_idx		= SD_NEWIDLE_IDX,	\
-	.wake_idx		= 1,			\
-	.forkexec_idx		= SD_FORKEXEC_IDX,	\
-	.flags			= SD_LOAD_BALANCE	\
-				| SD_BALANCE_EXEC	\
-				| SD_BALANCE_FORK	\
-				| SD_SERIALIZE		\
-				| SD_WAKE_BALANCE,	\
-	.last_balance		= jiffies,		\
-	.balance_interval	= 1,			\
-}
-
-#ifdef CONFIG_X86_64_ACPI_NUMA
-extern int __node_distance(int, int);
-#define node_distance(a, b) __node_distance(a, b)
-#endif
-
-#else /* !CONFIG_NUMA */
-
-#define numa_node_id()		0
-#define	cpu_to_node(cpu)	0
-#define	early_cpu_to_node(cpu)	0
-
-static inline const cpumask_t *_node_to_cpumask_ptr(int node)
-{
-	return &cpu_online_map;
-}
-static inline cpumask_t node_to_cpumask(int node)
-{
-	return cpu_online_map;
-}
-static inline int node_to_first_cpu(int node)
-{
-	return first_cpu(cpu_online_map);
-}
-
-/* Replace default node_to_cpumask_ptr with optimized version */
-#define node_to_cpumask_ptr(v, node)		\
-		const cpumask_t *v = _node_to_cpumask_ptr(node)
-
-#define node_to_cpumask_ptr_next(v, node)	\
-			   v = _node_to_cpumask_ptr(node)
-#endif
-
-#include <asm-generic/topology.h>
-
-#ifdef CONFIG_NUMA
-/* Returns the number of the first CPU on Node 'node'. */
-static inline int node_to_first_cpu(int node)
-{
-	node_to_cpumask_ptr(mask, node);
-	return first_cpu(*mask);
-}
-#endif
-
-extern cpumask_t cpu_coregroup_map(int cpu);
-
-#ifdef ENABLE_TOPO_DEFINES
-#define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
-#define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
-#define topology_core_siblings(cpu)		(per_cpu(cpu_core_map, cpu))
-#define topology_thread_siblings(cpu)		(per_cpu(cpu_sibling_map, cpu))
-
-/* indicates that pointers to the topology cpumask_t maps are valid */
-#define arch_provides_topology_pointers		yes
-#endif
-
-static inline void arch_fix_phys_package_id(int num, u32 slot)
-{
-}
-
-struct pci_bus;
-void set_pci_bus_resources_arch_default(struct pci_bus *b);
-
-#ifdef CONFIG_SMP
-#define mc_capable()			(boot_cpu_data.x86_max_cores > 1)
-#define smt_capable()			(smp_num_siblings > 1)
-#endif
-
-#ifdef CONFIG_NUMA
-extern int get_mp_bus_to_node(int busnum);
-extern void set_mp_bus_to_node(int busnum, int node);
-#else
-static inline int get_mp_bus_to_node(int busnum)
-{
-	return 0;
-}
-static inline void set_mp_bus_to_node(int busnum, int node)
-{
-}
-#endif
-
-#endif /* ASM_X86__TOPOLOGY_H */
diff --git a/include/asm-x86/trampoline.h b/include/asm-x86/trampoline.h
deleted file mode 100644
index 0406bbd898a9..000000000000
--- a/include/asm-x86/trampoline.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef ASM_X86__TRAMPOLINE_H
-#define ASM_X86__TRAMPOLINE_H
-
-#ifndef __ASSEMBLY__
-
-/*
- * Trampoline 80x86 program as an array.
- */
-extern const unsigned char trampoline_data [];
-extern const unsigned char trampoline_end  [];
-extern unsigned char *trampoline_base;
-
-extern unsigned long init_rsp;
-extern unsigned long initial_code;
-
-#define TRAMPOLINE_BASE 0x6000
-extern unsigned long setup_trampoline(void);
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* ASM_X86__TRAMPOLINE_H */
diff --git a/include/asm-x86/traps.h b/include/asm-x86/traps.h
deleted file mode 100644
index 6c3dc2c65751..000000000000
--- a/include/asm-x86/traps.h
+++ /dev/null
@@ -1,81 +0,0 @@
-#ifndef ASM_X86__TRAPS_H
-#define ASM_X86__TRAPS_H
-
-#include <asm/debugreg.h>
-
-#ifdef CONFIG_X86_32
-#define dotraplinkage
-#else
-#define dotraplinkage asmlinkage
-#endif
-
-asmlinkage void divide_error(void);
-asmlinkage void debug(void);
-asmlinkage void nmi(void);
-asmlinkage void int3(void);
-asmlinkage void overflow(void);
-asmlinkage void bounds(void);
-asmlinkage void invalid_op(void);
-asmlinkage void device_not_available(void);
-#ifdef CONFIG_X86_64
-asmlinkage void double_fault(void);
-#endif
-asmlinkage void coprocessor_segment_overrun(void);
-asmlinkage void invalid_TSS(void);
-asmlinkage void segment_not_present(void);
-asmlinkage void stack_segment(void);
-asmlinkage void general_protection(void);
-asmlinkage void page_fault(void);
-asmlinkage void spurious_interrupt_bug(void);
-asmlinkage void coprocessor_error(void);
-asmlinkage void alignment_check(void);
-#ifdef CONFIG_X86_MCE
-asmlinkage void machine_check(void);
-#endif /* CONFIG_X86_MCE */
-asmlinkage void simd_coprocessor_error(void);
-
-dotraplinkage void do_divide_error(struct pt_regs *, long);
-dotraplinkage void do_debug(struct pt_regs *, long);
-dotraplinkage void do_nmi(struct pt_regs *, long);
-dotraplinkage void do_int3(struct pt_regs *, long);
-dotraplinkage void do_overflow(struct pt_regs *, long);
-dotraplinkage void do_bounds(struct pt_regs *, long);
-dotraplinkage void do_invalid_op(struct pt_regs *, long);
-dotraplinkage void do_device_not_available(struct pt_regs *, long);
-dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long);
-dotraplinkage void do_invalid_TSS(struct pt_regs *, long);
-dotraplinkage void do_segment_not_present(struct pt_regs *, long);
-dotraplinkage void do_stack_segment(struct pt_regs *, long);
-dotraplinkage void do_general_protection(struct pt_regs *, long);
-dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
-dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long);
-dotraplinkage void do_coprocessor_error(struct pt_regs *, long);
-dotraplinkage void do_alignment_check(struct pt_regs *, long);
-#ifdef CONFIG_X86_MCE
-dotraplinkage void do_machine_check(struct pt_regs *, long);
-#endif
-dotraplinkage void do_simd_coprocessor_error(struct pt_regs *, long);
-#ifdef CONFIG_X86_32
-dotraplinkage void do_iret_error(struct pt_regs *, long);
-#endif
-
-static inline int get_si_code(unsigned long condition)
-{
-	if (condition & DR_STEP)
-		return TRAP_TRACE;
-	else if (condition & (DR_TRAP0|DR_TRAP1|DR_TRAP2|DR_TRAP3))
-		return TRAP_HWBKPT;
-	else
-		return TRAP_BRKPT;
-}
-
-extern int panic_on_unrecovered_nmi;
-extern int kstack_depth_to_print;
-
-#ifdef CONFIG_X86_32
-void math_error(void __user *);
-unsigned long patch_espfix_desc(unsigned long, unsigned long);
-asmlinkage void math_emulate(long);
-#endif
-
-#endif /* ASM_X86__TRAPS_H */
diff --git a/include/asm-x86/tsc.h b/include/asm-x86/tsc.h
deleted file mode 100644
index ad0f5c41e78c..000000000000
--- a/include/asm-x86/tsc.h
+++ /dev/null
@@ -1,62 +0,0 @@
-/*
- * x86 TSC related functions
- */
-#ifndef ASM_X86__TSC_H
-#define ASM_X86__TSC_H
-
-#include <asm/processor.h>
-
-#define NS_SCALE	10 /* 2^10, carefully chosen */
-#define US_SCALE	32 /* 2^32, arbitralrily chosen */
-
-/*
- * Standard way to access the cycle counter.
- */
-typedef unsigned long long cycles_t;
-
-extern unsigned int cpu_khz;
-extern unsigned int tsc_khz;
-
-extern void disable_TSC(void);
-
-static inline cycles_t get_cycles(void)
-{
-	unsigned long long ret = 0;
-
-#ifndef CONFIG_X86_TSC
-	if (!cpu_has_tsc)
-		return 0;
-#endif
-	rdtscll(ret);
-
-	return ret;
-}
-
-static __always_inline cycles_t vget_cycles(void)
-{
-	/*
-	 * We only do VDSOs on TSC capable CPUs, so this shouldnt
-	 * access boot_cpu_data (which is not VDSO-safe):
-	 */
-#ifndef CONFIG_X86_TSC
-	if (!cpu_has_tsc)
-		return 0;
-#endif
-	return (cycles_t)__native_read_tsc();
-}
-
-extern void tsc_init(void);
-extern void mark_tsc_unstable(char *reason);
-extern int unsynchronized_tsc(void);
-int check_tsc_unstable(void);
-
-/*
- * Boot-time check whether the TSCs are synchronized across
- * all CPUs/cores:
- */
-extern void check_tsc_sync_source(int cpu);
-extern void check_tsc_sync_target(void);
-
-extern int notsc_setup(char *);
-
-#endif /* ASM_X86__TSC_H */
diff --git a/include/asm-x86/types.h b/include/asm-x86/types.h
deleted file mode 100644
index e78b52e17444..000000000000
--- a/include/asm-x86/types.h
+++ /dev/null
@@ -1,36 +0,0 @@
-#ifndef ASM_X86__TYPES_H
-#define ASM_X86__TYPES_H
-
-#include <asm-generic/int-ll64.h>
-
-#ifndef __ASSEMBLY__
-
-typedef unsigned short umode_t;
-
-#endif /* __ASSEMBLY__ */
-
-/*
- * These aren't exported outside the kernel to avoid name space clashes
- */
-#ifdef __KERNEL__
-
-#ifdef CONFIG_X86_32
-# define BITS_PER_LONG 32
-#else
-# define BITS_PER_LONG 64
-#endif
-
-#ifndef __ASSEMBLY__
-
-typedef u64 dma64_addr_t;
-#if defined(CONFIG_X86_64) || defined(CONFIG_HIGHMEM64G)
-/* DMA addresses come in 32-bit and 64-bit flavours. */
-typedef u64 dma_addr_t;
-#else
-typedef u32 dma_addr_t;
-#endif
-
-#endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
-#endif /* ASM_X86__TYPES_H */
diff --git a/include/asm-x86/uaccess.h b/include/asm-x86/uaccess.h
deleted file mode 100644
index 48ebc0ad40ec..000000000000
--- a/include/asm-x86/uaccess.h
+++ /dev/null
@@ -1,454 +0,0 @@
-#ifndef ASM_X86__UACCESS_H
-#define ASM_X86__UACCESS_H
-/*
- * User space memory access functions
- */
-#include <linux/errno.h>
-#include <linux/compiler.h>
-#include <linux/thread_info.h>
-#include <linux/prefetch.h>
-#include <linux/string.h>
-#include <asm/asm.h>
-#include <asm/page.h>
-
-#define VERIFY_READ 0
-#define VERIFY_WRITE 1
-
-/*
- * The fs value determines whether argument validity checking should be
- * performed or not.  If get_fs() == USER_DS, checking is performed, with
- * get_fs() == KERNEL_DS, checking is bypassed.
- *
- * For historical reasons, these macros are grossly misnamed.
- */
-
-#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
-
-#define KERNEL_DS	MAKE_MM_SEG(-1UL)
-#define USER_DS		MAKE_MM_SEG(PAGE_OFFSET)
-
-#define get_ds()	(KERNEL_DS)
-#define get_fs()	(current_thread_info()->addr_limit)
-#define set_fs(x)	(current_thread_info()->addr_limit = (x))
-
-#define segment_eq(a, b)	((a).seg == (b).seg)
-
-#define __addr_ok(addr)					\
-	((unsigned long __force)(addr) <		\
-	 (current_thread_info()->addr_limit.seg))
-
-/*
- * Test whether a block of memory is a valid user space address.
- * Returns 0 if the range is valid, nonzero otherwise.
- *
- * This is equivalent to the following test:
- * (u33)addr + (u33)size >= (u33)current->addr_limit.seg (u65 for x86_64)
- *
- * This needs 33-bit (65-bit for x86_64) arithmetic. We have a carry...
- */
-
-#define __range_not_ok(addr, size)					\
-({									\
-	unsigned long flag, roksum;					\
-	__chk_user_ptr(addr);						\
-	asm("add %3,%1 ; sbb %0,%0 ; cmp %1,%4 ; sbb $0,%0"		\
-	    : "=&r" (flag), "=r" (roksum)				\
-	    : "1" (addr), "g" ((long)(size)),				\
-	      "rm" (current_thread_info()->addr_limit.seg));		\
-	flag;								\
-})
-
-/**
- * access_ok: - Checks if a user space pointer is valid
- * @type: Type of access: %VERIFY_READ or %VERIFY_WRITE.  Note that
- *        %VERIFY_WRITE is a superset of %VERIFY_READ - if it is safe
- *        to write to a block, it is always safe to read from it.
- * @addr: User space pointer to start of block to check
- * @size: Size of block to check
- *
- * Context: User context only.  This function may sleep.
- *
- * Checks if a pointer to a block of memory in user space is valid.
- *
- * Returns true (nonzero) if the memory block may be valid, false (zero)
- * if it is definitely invalid.
- *
- * Note that, depending on architecture, this function probably just
- * checks that the pointer is in the user space range - after calling
- * this function, memory access functions may still return -EFAULT.
- */
-#define access_ok(type, addr, size) (likely(__range_not_ok(addr, size) == 0))
-
-/*
- * The exception table consists of pairs of addresses: the first is the
- * address of an instruction that is allowed to fault, and the second is
- * the address at which the program should continue.  No registers are
- * modified, so it is entirely up to the continuation code to figure out
- * what to do.
- *
- * All the routines below use bits of fixup code that are out of line
- * with the main instruction path.  This means when everything is well,
- * we don't even have to jump over them.  Further, they do not intrude
- * on our cache or tlb entries.
- */
-
-struct exception_table_entry {
-	unsigned long insn, fixup;
-};
-
-extern int fixup_exception(struct pt_regs *regs);
-
-/*
- * These are the main single-value transfer routines.  They automatically
- * use the right size if we just have the right pointer type.
- *
- * This gets kind of ugly. We want to return _two_ values in "get_user()"
- * and yet we don't want to do any pointers, because that is too much
- * of a performance impact. Thus we have a few rather ugly macros here,
- * and hide all the ugliness from the user.
- *
- * The "__xxx" versions of the user access functions are versions that
- * do not verify the address space, that must have been done previously
- * with a separate "access_ok()" call (this is used when we do multiple
- * accesses to the same area of user memory).
- */
-
-extern int __get_user_1(void);
-extern int __get_user_2(void);
-extern int __get_user_4(void);
-extern int __get_user_8(void);
-extern int __get_user_bad(void);
-
-#define __get_user_x(size, ret, x, ptr)		      \
-	asm volatile("call __get_user_" #size	      \
-		     : "=a" (ret),"=d" (x)	      \
-		     : "0" (ptr))		      \
-
-/* Careful: we have to cast the result to the type of the pointer
- * for sign reasons */
-
-/**
- * get_user: - Get a simple variable from user space.
- * @x:   Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-#ifdef CONFIG_X86_32
-#define __get_user_8(__ret_gu, __val_gu, ptr)				\
-		__get_user_x(X, __ret_gu, __val_gu, ptr)
-#else
-#define __get_user_8(__ret_gu, __val_gu, ptr)				\
-		__get_user_x(8, __ret_gu, __val_gu, ptr)
-#endif
-
-#define get_user(x, ptr)						\
-({									\
-	int __ret_gu;							\
-	unsigned long __val_gu;						\
-	__chk_user_ptr(ptr);						\
-	switch (sizeof(*(ptr))) {					\
-	case 1:								\
-		__get_user_x(1, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	case 2:								\
-		__get_user_x(2, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	case 4:								\
-		__get_user_x(4, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	case 8:								\
-		__get_user_8(__ret_gu, __val_gu, ptr);			\
-		break;							\
-	default:							\
-		__get_user_x(X, __ret_gu, __val_gu, ptr);		\
-		break;							\
-	}								\
-	(x) = (__typeof__(*(ptr)))__val_gu;				\
-	__ret_gu;							\
-})
-
-#define __put_user_x(size, x, ptr, __ret_pu)			\
-	asm volatile("call __put_user_" #size : "=a" (__ret_pu)	\
-		     :"0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
-
-
-
-#ifdef CONFIG_X86_32
-#define __put_user_u64(x, addr, err)					\
-	asm volatile("1:	movl %%eax,0(%2)\n"			\
-		     "2:	movl %%edx,4(%2)\n"			\
-		     "3:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "4:	movl %3,%0\n"				\
-		     "	jmp 3b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 4b)				\
-		     _ASM_EXTABLE(2b, 4b)				\
-		     : "=r" (err)					\
-		     : "A" (x), "r" (addr), "i" (-EFAULT), "0" (err))
-
-#define __put_user_x8(x, ptr, __ret_pu)				\
-	asm volatile("call __put_user_8" : "=a" (__ret_pu)	\
-		     : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
-#else
-#define __put_user_u64(x, ptr, retval) \
-	__put_user_asm(x, ptr, retval, "q", "", "Zr", -EFAULT)
-#define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu)
-#endif
-
-extern void __put_user_bad(void);
-
-/*
- * Strange magic calling convention: pointer in %ecx,
- * value in %eax(:%edx), return value in %eax. clobbers %rbx
- */
-extern void __put_user_1(void);
-extern void __put_user_2(void);
-extern void __put_user_4(void);
-extern void __put_user_8(void);
-
-#ifdef CONFIG_X86_WP_WORKS_OK
-
-/**
- * put_user: - Write a simple value into user space.
- * @x:   Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple value from kernel space to user
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-#define put_user(x, ptr)					\
-({								\
-	int __ret_pu;						\
-	__typeof__(*(ptr)) __pu_val;				\
-	__chk_user_ptr(ptr);					\
-	__pu_val = x;						\
-	switch (sizeof(*(ptr))) {				\
-	case 1:							\
-		__put_user_x(1, __pu_val, ptr, __ret_pu);	\
-		break;						\
-	case 2:							\
-		__put_user_x(2, __pu_val, ptr, __ret_pu);	\
-		break;						\
-	case 4:							\
-		__put_user_x(4, __pu_val, ptr, __ret_pu);	\
-		break;						\
-	case 8:							\
-		__put_user_x8(__pu_val, ptr, __ret_pu);		\
-		break;						\
-	default:						\
-		__put_user_x(X, __pu_val, ptr, __ret_pu);	\
-		break;						\
-	}							\
-	__ret_pu;						\
-})
-
-#define __put_user_size(x, ptr, size, retval, errret)			\
-do {									\
-	retval = 0;							\
-	__chk_user_ptr(ptr);						\
-	switch (size) {							\
-	case 1:								\
-		__put_user_asm(x, ptr, retval, "b", "b", "iq", errret);	\
-		break;							\
-	case 2:								\
-		__put_user_asm(x, ptr, retval, "w", "w", "ir", errret);	\
-		break;							\
-	case 4:								\
-		__put_user_asm(x, ptr, retval, "l", "k",  "ir", errret);\
-		break;							\
-	case 8:								\
-		__put_user_u64((__typeof__(*ptr))(x), ptr, retval);	\
-		break;							\
-	default:							\
-		__put_user_bad();					\
-	}								\
-} while (0)
-
-#else
-
-#define __put_user_size(x, ptr, size, retval, errret)			\
-do {									\
-	__typeof__(*(ptr))__pus_tmp = x;				\
-	retval = 0;							\
-									\
-	if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp, size) != 0))	\
-		retval = errret;					\
-} while (0)
-
-#define put_user(x, ptr)					\
-({								\
-	int __ret_pu;						\
-	__typeof__(*(ptr))__pus_tmp = x;			\
-	__ret_pu = 0;						\
-	if (unlikely(__copy_to_user_ll(ptr, &__pus_tmp,		\
-				       sizeof(*(ptr))) != 0))	\
-		__ret_pu = -EFAULT;				\
-	__ret_pu;						\
-})
-#endif
-
-#ifdef CONFIG_X86_32
-#define __get_user_asm_u64(x, ptr, retval, errret)	(x) = __get_user_bad()
-#else
-#define __get_user_asm_u64(x, ptr, retval, errret) \
-	 __get_user_asm(x, ptr, retval, "q", "", "=r", errret)
-#endif
-
-#define __get_user_size(x, ptr, size, retval, errret)			\
-do {									\
-	retval = 0;							\
-	__chk_user_ptr(ptr);						\
-	switch (size) {							\
-	case 1:								\
-		__get_user_asm(x, ptr, retval, "b", "b", "=q", errret);	\
-		break;							\
-	case 2:								\
-		__get_user_asm(x, ptr, retval, "w", "w", "=r", errret);	\
-		break;							\
-	case 4:								\
-		__get_user_asm(x, ptr, retval, "l", "k", "=r", errret);	\
-		break;							\
-	case 8:								\
-		__get_user_asm_u64(x, ptr, retval, errret);		\
-		break;							\
-	default:							\
-		(x) = __get_user_bad();					\
-	}								\
-} while (0)
-
-#define __get_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
-	asm volatile("1:	mov"itype" %2,%"rtype"1\n"		\
-		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:	mov %3,%0\n"				\
-		     "	xor"itype" %"rtype"1,%"rtype"1\n"		\
-		     "	jmp 2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : "=r" (err), ltype(x)				\
-		     : "m" (__m(addr)), "i" (errret), "0" (err))
-
-#define __put_user_nocheck(x, ptr, size)			\
-({								\
-	long __pu_err;						\
-	__put_user_size((x), (ptr), (size), __pu_err, -EFAULT);	\
-	__pu_err;						\
-})
-
-#define __get_user_nocheck(x, ptr, size)				\
-({									\
-	long __gu_err;							\
-	unsigned long __gu_val;						\
-	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
-	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
-	__gu_err;							\
-})
-
-/* FIXME: this hack is definitely wrong -AK */
-struct __large_struct { unsigned long buf[100]; };
-#define __m(x) (*(struct __large_struct __user *)(x))
-
-/*
- * Tell gcc we read from memory instead of writing: this is because
- * we do not write to any memory gcc knows about, so there are no
- * aliasing issues.
- */
-#define __put_user_asm(x, addr, err, itype, rtype, ltype, errret)	\
-	asm volatile("1:	mov"itype" %"rtype"1,%2\n"		\
-		     "2:\n"						\
-		     ".section .fixup,\"ax\"\n"				\
-		     "3:	mov %3,%0\n"				\
-		     "	jmp 2b\n"					\
-		     ".previous\n"					\
-		     _ASM_EXTABLE(1b, 3b)				\
-		     : "=r"(err)					\
-		     : ltype(x), "m" (__m(addr)), "i" (errret), "0" (err))
-/**
- * __get_user: - Get a simple variable from user space, with less checking.
- * @x:   Variable to store result.
- * @ptr: Source address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple variable from user space to kernel
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and the result of
- * dereferencing @ptr must be assignable to @x without a cast.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- * On error, the variable @x is set to zero.
- */
-
-#define __get_user(x, ptr)						\
-	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
-/**
- * __put_user: - Write a simple value into user space, with less checking.
- * @x:   Value to copy to user space.
- * @ptr: Destination address, in user space.
- *
- * Context: User context only.  This function may sleep.
- *
- * This macro copies a single simple value from kernel space to user
- * space.  It supports simple types like char and int, but not larger
- * data types like structures or arrays.
- *
- * @ptr must have pointer-to-simple-variable type, and @x must be assignable
- * to the result of dereferencing @ptr.
- *
- * Caller must check the pointer with access_ok() before calling this
- * function.
- *
- * Returns zero on success, or -EFAULT on error.
- */
-
-#define __put_user(x, ptr)						\
-	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
-
-#define __get_user_unaligned __get_user
-#define __put_user_unaligned __put_user
-
-/*
- * movsl can be slow when source and dest are not both 8-byte aligned
- */
-#ifdef CONFIG_X86_INTEL_USERCOPY
-extern struct movsl_mask {
-	int mask;
-} ____cacheline_aligned_in_smp movsl_mask;
-#endif
-
-#define ARCH_HAS_NOCACHE_UACCESS 1
-
-#ifdef CONFIG_X86_32
-# include "uaccess_32.h"
-#else
-# define ARCH_HAS_SEARCH_EXTABLE
-# include "uaccess_64.h"
-#endif
-
-#endif /* ASM_X86__UACCESS_H */
-
diff --git a/include/asm-x86/uaccess_32.h b/include/asm-x86/uaccess_32.h
deleted file mode 100644
index 6b5b57d9c6d1..000000000000
--- a/include/asm-x86/uaccess_32.h
+++ /dev/null
@@ -1,218 +0,0 @@
-#ifndef ASM_X86__UACCESS_32_H
-#define ASM_X86__UACCESS_32_H
-
-/*
- * User space memory access functions
- */
-#include <linux/errno.h>
-#include <linux/thread_info.h>
-#include <linux/prefetch.h>
-#include <linux/string.h>
-#include <asm/asm.h>
-#include <asm/page.h>
-
-unsigned long __must_check __copy_to_user_ll
-		(void __user *to, const void *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll
-		(void *to, const void __user *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll_nozero
-		(void *to, const void __user *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll_nocache
-		(void *to, const void __user *from, unsigned long n);
-unsigned long __must_check __copy_from_user_ll_nocache_nozero
-		(void *to, const void __user *from, unsigned long n);
-
-/**
- * __copy_to_user_inatomic: - Copy a block of data into user space, with less checking.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only.
- *
- * Copy data from kernel space to user space.  Caller must check
- * the specified block with access_ok() before calling this function.
- * The caller should also make sure he pins the user space address
- * so that the we don't result in page fault and sleep.
- *
- * Here we special-case 1, 2 and 4-byte copy_*_user invocations.  On a fault
- * we return the initial request size (1, 2 or 4), as copy_*_user should do.
- * If a store crosses a page boundary and gets a fault, the x86 will not write
- * anything, so this is accurate.
- */
-
-static __always_inline unsigned long __must_check
-__copy_to_user_inatomic(void __user *to, const void *from, unsigned long n)
-{
-	if (__builtin_constant_p(n)) {
-		unsigned long ret;
-
-		switch (n) {
-		case 1:
-			__put_user_size(*(u8 *)from, (u8 __user *)to,
-					1, ret, 1);
-			return ret;
-		case 2:
-			__put_user_size(*(u16 *)from, (u16 __user *)to,
-					2, ret, 2);
-			return ret;
-		case 4:
-			__put_user_size(*(u32 *)from, (u32 __user *)to,
-					4, ret, 4);
-			return ret;
-		}
-	}
-	return __copy_to_user_ll(to, from, n);
-}
-
-/**
- * __copy_to_user: - Copy a block of data into user space, with less checking.
- * @to:   Destination address, in user space.
- * @from: Source address, in kernel space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only.  This function may sleep.
- *
- * Copy data from kernel space to user space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- */
-static __always_inline unsigned long __must_check
-__copy_to_user(void __user *to, const void *from, unsigned long n)
-{
-       might_sleep();
-       return __copy_to_user_inatomic(to, from, n);
-}
-
-static __always_inline unsigned long
-__copy_from_user_inatomic(void *to, const void __user *from, unsigned long n)
-{
-	/* Avoid zeroing the tail if the copy fails..
-	 * If 'n' is constant and 1, 2, or 4, we do still zero on a failure,
-	 * but as the zeroing behaviour is only significant when n is not
-	 * constant, that shouldn't be a problem.
-	 */
-	if (__builtin_constant_p(n)) {
-		unsigned long ret;
-
-		switch (n) {
-		case 1:
-			__get_user_size(*(u8 *)to, from, 1, ret, 1);
-			return ret;
-		case 2:
-			__get_user_size(*(u16 *)to, from, 2, ret, 2);
-			return ret;
-		case 4:
-			__get_user_size(*(u32 *)to, from, 4, ret, 4);
-			return ret;
-		}
-	}
-	return __copy_from_user_ll_nozero(to, from, n);
-}
-
-/**
- * __copy_from_user: - Copy a block of data from user space, with less checking.
- * @to:   Destination address, in kernel space.
- * @from: Source address, in user space.
- * @n:    Number of bytes to copy.
- *
- * Context: User context only.  This function may sleep.
- *
- * Copy data from user space to kernel space.  Caller must check
- * the specified block with access_ok() before calling this function.
- *
- * Returns number of bytes that could not be copied.
- * On success, this will be zero.
- *
- * If some data could not be copied, this function will pad the copied
- * data to the requested size using zero bytes.
- *
- * An alternate version - __copy_from_user_inatomic() - may be called from
- * atomic context and will fail rather than sleep.  In this case the
- * uncopied bytes will *NOT* be padded with zeros.  See fs/filemap.h
- * for explanation of why this is needed.
- */
-static __always_inline unsigned long
-__copy_from_user(void *to, const void __user *from, unsigned long n)
-{
-	might_sleep();
-	if (__builtin_constant_p(n)) {
-		unsigned long ret;
-
-		switch (n) {
-		case 1:
-			__get_user_size(*(u8 *)to, from, 1, ret, 1);
-			return ret;
-		case 2:
-			__get_user_size(*(u16 *)to, from, 2, ret, 2);
-			return ret;
-		case 4:
-			__get_user_size(*(u32 *)to, from, 4, ret, 4);
-			return ret;
-		}
-	}
-	return __copy_from_user_ll(to, from, n);
-}
-
-static __always_inline unsigned long __copy_from_user_nocache(void *to,
-				const void __user *from, unsigned long n)
-{
-	might_sleep();
-	if (__builtin_constant_p(n)) {
-		unsigned long ret;
-
-		switch (n) {
-		case 1:
-			__get_user_size(*(u8 *)to, from, 1, ret, 1);
-			return ret;
-		case 2:
-			__get_user_size(*(u16 *)to, from, 2, ret, 2);
-			return ret;
-		case 4:
-			__get_user_size(*(u32 *)to, from, 4, ret, 4);
-			return ret;
-		}
-	}
-	return __copy_from_user_ll_nocache(to, from, n);
-}
-
-static __always_inline unsigned long
-__copy_from_user_inatomic_nocache(void *to, const void __user *from,
-				  unsigned long n)
-{
-       return __copy_from_user_ll_nocache_nozero(to, from, n);
-}
-
-unsigned long __must_check copy_to_user(void __user *to,
-					const void *from, unsigned long n);
-unsigned long __must_check copy_from_user(void *to,
-					  const void __user *from,
-					  unsigned long n);
-long __must_check strncpy_from_user(char *dst, const char __user *src,
-				    long count);
-long __must_check __strncpy_from_user(char *dst,
-				      const char __user *src, long count);
-
-/**
- * strlen_user: - Get the size of a string in user space.
- * @str: The string to measure.
- *
- * Context: User context only.  This function may sleep.
- *
- * Get the size of a NUL-terminated string in user space.
- *
- * Returns the size of the string INCLUDING the terminating NUL.
- * On exception, returns 0.
- *
- * If there is a limit on the length of a valid string, you may wish to
- * consider using strnlen_user() instead.
- */
-#define strlen_user(str) strnlen_user(str, LONG_MAX)
-
-long strnlen_user(const char __user *str, long n);
-unsigned long __must_check clear_user(void __user *mem, unsigned long len);
-unsigned long __must_check __clear_user(void __user *mem, unsigned long len);
-
-#endif /* ASM_X86__UACCESS_32_H */
diff --git a/include/asm-x86/uaccess_64.h b/include/asm-x86/uaccess_64.h
deleted file mode 100644
index c96c1f5d07a2..000000000000
--- a/include/asm-x86/uaccess_64.h
+++ /dev/null
@@ -1,202 +0,0 @@
-#ifndef ASM_X86__UACCESS_64_H
-#define ASM_X86__UACCESS_64_H
-
-/*
- * User space memory access functions
- */
-#include <linux/compiler.h>
-#include <linux/errno.h>
-#include <linux/prefetch.h>
-#include <linux/lockdep.h>
-#include <asm/page.h>
-
-/*
- * Copy To/From Userspace
- */
-
-/* Handles exceptions in both to and from, but doesn't do access_ok */
-__must_check unsigned long
-copy_user_generic(void *to, const void *from, unsigned len);
-
-__must_check unsigned long
-copy_to_user(void __user *to, const void *from, unsigned len);
-__must_check unsigned long
-copy_from_user(void *to, const void __user *from, unsigned len);
-__must_check unsigned long
-copy_in_user(void __user *to, const void __user *from, unsigned len);
-
-static __always_inline __must_check
-int __copy_from_user(void *dst, const void __user *src, unsigned size)
-{
-	int ret = 0;
-	if (!__builtin_constant_p(size))
-		return copy_user_generic(dst, (__force void *)src, size);
-	switch (size) {
-	case 1:__get_user_asm(*(u8 *)dst, (u8 __user *)src,
-			      ret, "b", "b", "=q", 1);
-		return ret;
-	case 2:__get_user_asm(*(u16 *)dst, (u16 __user *)src,
-			      ret, "w", "w", "=r", 2);
-		return ret;
-	case 4:__get_user_asm(*(u32 *)dst, (u32 __user *)src,
-			      ret, "l", "k", "=r", 4);
-		return ret;
-	case 8:__get_user_asm(*(u64 *)dst, (u64 __user *)src,
-			      ret, "q", "", "=r", 8);
-		return ret;
-	case 10:
-		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
-			       ret, "q", "", "=r", 16);
-		if (unlikely(ret))
-			return ret;
-		__get_user_asm(*(u16 *)(8 + (char *)dst),
-			       (u16 __user *)(8 + (char __user *)src),
-			       ret, "w", "w", "=r", 2);
-		return ret;
-	case 16:
-		__get_user_asm(*(u64 *)dst, (u64 __user *)src,
-			       ret, "q", "", "=r", 16);
-		if (unlikely(ret))
-			return ret;
-		__get_user_asm(*(u64 *)(8 + (char *)dst),
-			       (u64 __user *)(8 + (char __user *)src),
-			       ret, "q", "", "=r", 8);
-		return ret;
-	default:
-		return copy_user_generic(dst, (__force void *)src, size);
-	}
-}
-
-static __always_inline __must_check
-int __copy_to_user(void __user *dst, const void *src, unsigned size)
-{
-	int ret = 0;
-	if (!__builtin_constant_p(size))
-		return copy_user_generic((__force void *)dst, src, size);
-	switch (size) {
-	case 1:__put_user_asm(*(u8 *)src, (u8 __user *)dst,
-			      ret, "b", "b", "iq", 1);
-		return ret;
-	case 2:__put_user_asm(*(u16 *)src, (u16 __user *)dst,
-			      ret, "w", "w", "ir", 2);
-		return ret;
-	case 4:__put_user_asm(*(u32 *)src, (u32 __user *)dst,
-			      ret, "l", "k", "ir", 4);
-		return ret;
-	case 8:__put_user_asm(*(u64 *)src, (u64 __user *)dst,
-			      ret, "q", "", "ir", 8);
-		return ret;
-	case 10:
-		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
-			       ret, "q", "", "ir", 10);
-		if (unlikely(ret))
-			return ret;
-		asm("":::"memory");
-		__put_user_asm(4[(u16 *)src], 4 + (u16 __user *)dst,
-			       ret, "w", "w", "ir", 2);
-		return ret;
-	case 16:
-		__put_user_asm(*(u64 *)src, (u64 __user *)dst,
-			       ret, "q", "", "ir", 16);
-		if (unlikely(ret))
-			return ret;
-		asm("":::"memory");
-		__put_user_asm(1[(u64 *)src], 1 + (u64 __user *)dst,
-			       ret, "q", "", "ir", 8);
-		return ret;
-	default:
-		return copy_user_generic((__force void *)dst, src, size);
-	}
-}
-
-static __always_inline __must_check
-int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
-{
-	int ret = 0;
-	if (!__builtin_constant_p(size))
-		return copy_user_generic((__force void *)dst,
-					 (__force void *)src, size);
-	switch (size) {
-	case 1: {
-		u8 tmp;
-		__get_user_asm(tmp, (u8 __user *)src,
-			       ret, "b", "b", "=q", 1);
-		if (likely(!ret))
-			__put_user_asm(tmp, (u8 __user *)dst,
-				       ret, "b", "b", "iq", 1);
-		return ret;
-	}
-	case 2: {
-		u16 tmp;
-		__get_user_asm(tmp, (u16 __user *)src,
-			       ret, "w", "w", "=r", 2);
-		if (likely(!ret))
-			__put_user_asm(tmp, (u16 __user *)dst,
-				       ret, "w", "w", "ir", 2);
-		return ret;
-	}
-
-	case 4: {
-		u32 tmp;
-		__get_user_asm(tmp, (u32 __user *)src,
-			       ret, "l", "k", "=r", 4);
-		if (likely(!ret))
-			__put_user_asm(tmp, (u32 __user *)dst,
-				       ret, "l", "k", "ir", 4);
-		return ret;
-	}
-	case 8: {
-		u64 tmp;
-		__get_user_asm(tmp, (u64 __user *)src,
-			       ret, "q", "", "=r", 8);
-		if (likely(!ret))
-			__put_user_asm(tmp, (u64 __user *)dst,
-				       ret, "q", "", "ir", 8);
-		return ret;
-	}
-	default:
-		return copy_user_generic((__force void *)dst,
-					 (__force void *)src, size);
-	}
-}
-
-__must_check long
-strncpy_from_user(char *dst, const char __user *src, long count);
-__must_check long
-__strncpy_from_user(char *dst, const char __user *src, long count);
-__must_check long strnlen_user(const char __user *str, long n);
-__must_check long __strnlen_user(const char __user *str, long n);
-__must_check long strlen_user(const char __user *str);
-__must_check unsigned long clear_user(void __user *mem, unsigned long len);
-__must_check unsigned long __clear_user(void __user *mem, unsigned long len);
-
-__must_check long __copy_from_user_inatomic(void *dst, const void __user *src,
-					    unsigned size);
-
-static __must_check __always_inline int
-__copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
-{
-	return copy_user_generic((__force void *)dst, src, size);
-}
-
-extern long __copy_user_nocache(void *dst, const void __user *src,
-				unsigned size, int zerorest);
-
-static inline int __copy_from_user_nocache(void *dst, const void __user *src,
-					   unsigned size)
-{
-	might_sleep();
-	return __copy_user_nocache(dst, src, size, 1);
-}
-
-static inline int __copy_from_user_inatomic_nocache(void *dst,
-						    const void __user *src,
-						    unsigned size)
-{
-	return __copy_user_nocache(dst, src, size, 0);
-}
-
-unsigned long
-copy_user_handle_tail(char *to, char *from, unsigned len, unsigned zerorest);
-
-#endif /* ASM_X86__UACCESS_64_H */
diff --git a/include/asm-x86/ucontext.h b/include/asm-x86/ucontext.h
deleted file mode 100644
index 89eaa5456a7e..000000000000
--- a/include/asm-x86/ucontext.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef ASM_X86__UCONTEXT_H
-#define ASM_X86__UCONTEXT_H
-
-#define UC_FP_XSTATE	0x1	/* indicates the presence of extended state
-				 * information in the memory layout pointed
-				 * by the fpstate pointer in the ucontext's
-				 * sigcontext struct (uc_mcontext).
-				 */
-
-struct ucontext {
-	unsigned long	  uc_flags;
-	struct ucontext  *uc_link;
-	stack_t		  uc_stack;
-	struct sigcontext uc_mcontext;
-	sigset_t	  uc_sigmask;	/* mask last for extensibility */
-};
-
-#endif /* ASM_X86__UCONTEXT_H */
diff --git a/include/asm-x86/unaligned.h b/include/asm-x86/unaligned.h
deleted file mode 100644
index 59dcdec37160..000000000000
--- a/include/asm-x86/unaligned.h
+++ /dev/null
@@ -1,14 +0,0 @@
-#ifndef ASM_X86__UNALIGNED_H
-#define ASM_X86__UNALIGNED_H
-
-/*
- * The x86 can do unaligned accesses itself.
- */
-
-#include <linux/unaligned/access_ok.h>
-#include <linux/unaligned/generic.h>
-
-#define get_unaligned __get_unaligned_le
-#define put_unaligned __put_unaligned_le
-
-#endif /* ASM_X86__UNALIGNED_H */
diff --git a/include/asm-x86/unistd.h b/include/asm-x86/unistd.h
deleted file mode 100644
index 2a58ed3e51d8..000000000000
--- a/include/asm-x86/unistd.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifdef __KERNEL__
-# ifdef CONFIG_X86_32
-#  include "unistd_32.h"
-# else
-#  include "unistd_64.h"
-# endif
-#else
-# ifdef __i386__
-#  include "unistd_32.h"
-# else
-#  include "unistd_64.h"
-# endif
-#endif
diff --git a/include/asm-x86/unistd_32.h b/include/asm-x86/unistd_32.h
deleted file mode 100644
index 017f4a87c913..000000000000
--- a/include/asm-x86/unistd_32.h
+++ /dev/null
@@ -1,379 +0,0 @@
-#ifndef ASM_X86__UNISTD_32_H
-#define ASM_X86__UNISTD_32_H
-
-/*
- * This file contains the system call numbers.
- */
-
-#define __NR_restart_syscall      0
-#define __NR_exit		  1
-#define __NR_fork		  2
-#define __NR_read		  3
-#define __NR_write		  4
-#define __NR_open		  5
-#define __NR_close		  6
-#define __NR_waitpid		  7
-#define __NR_creat		  8
-#define __NR_link		  9
-#define __NR_unlink		 10
-#define __NR_execve		 11
-#define __NR_chdir		 12
-#define __NR_time		 13
-#define __NR_mknod		 14
-#define __NR_chmod		 15
-#define __NR_lchown		 16
-#define __NR_break		 17
-#define __NR_oldstat		 18
-#define __NR_lseek		 19
-#define __NR_getpid		 20
-#define __NR_mount		 21
-#define __NR_umount		 22
-#define __NR_setuid		 23
-#define __NR_getuid		 24
-#define __NR_stime		 25
-#define __NR_ptrace		 26
-#define __NR_alarm		 27
-#define __NR_oldfstat		 28
-#define __NR_pause		 29
-#define __NR_utime		 30
-#define __NR_stty		 31
-#define __NR_gtty		 32
-#define __NR_access		 33
-#define __NR_nice		 34
-#define __NR_ftime		 35
-#define __NR_sync		 36
-#define __NR_kill		 37
-#define __NR_rename		 38
-#define __NR_mkdir		 39
-#define __NR_rmdir		 40
-#define __NR_dup		 41
-#define __NR_pipe		 42
-#define __NR_times		 43
-#define __NR_prof		 44
-#define __NR_brk		 45
-#define __NR_setgid		 46
-#define __NR_getgid		 47
-#define __NR_signal		 48
-#define __NR_geteuid		 49
-#define __NR_getegid		 50
-#define __NR_acct		 51
-#define __NR_umount2		 52
-#define __NR_lock		 53
-#define __NR_ioctl		 54
-#define __NR_fcntl		 55
-#define __NR_mpx		 56
-#define __NR_setpgid		 57
-#define __NR_ulimit		 58
-#define __NR_oldolduname	 59
-#define __NR_umask		 60
-#define __NR_chroot		 61
-#define __NR_ustat		 62
-#define __NR_dup2		 63
-#define __NR_getppid		 64
-#define __NR_getpgrp		 65
-#define __NR_setsid		 66
-#define __NR_sigaction		 67
-#define __NR_sgetmask		 68
-#define __NR_ssetmask		 69
-#define __NR_setreuid		 70
-#define __NR_setregid		 71
-#define __NR_sigsuspend		 72
-#define __NR_sigpending		 73
-#define __NR_sethostname	 74
-#define __NR_setrlimit		 75
-#define __NR_getrlimit		 76   /* Back compatible 2Gig limited rlimit */
-#define __NR_getrusage		 77
-#define __NR_gettimeofday	 78
-#define __NR_settimeofday	 79
-#define __NR_getgroups		 80
-#define __NR_setgroups		 81
-#define __NR_select		 82
-#define __NR_symlink		 83
-#define __NR_oldlstat		 84
-#define __NR_readlink		 85
-#define __NR_uselib		 86
-#define __NR_swapon		 87
-#define __NR_reboot		 88
-#define __NR_readdir		 89
-#define __NR_mmap		 90
-#define __NR_munmap		 91
-#define __NR_truncate		 92
-#define __NR_ftruncate		 93
-#define __NR_fchmod		 94
-#define __NR_fchown		 95
-#define __NR_getpriority	 96
-#define __NR_setpriority	 97
-#define __NR_profil		 98
-#define __NR_statfs		 99
-#define __NR_fstatfs		100
-#define __NR_ioperm		101
-#define __NR_socketcall		102
-#define __NR_syslog		103
-#define __NR_setitimer		104
-#define __NR_getitimer		105
-#define __NR_stat		106
-#define __NR_lstat		107
-#define __NR_fstat		108
-#define __NR_olduname		109
-#define __NR_iopl		110
-#define __NR_vhangup		111
-#define __NR_idle		112
-#define __NR_vm86old		113
-#define __NR_wait4		114
-#define __NR_swapoff		115
-#define __NR_sysinfo		116
-#define __NR_ipc		117
-#define __NR_fsync		118
-#define __NR_sigreturn		119
-#define __NR_clone		120
-#define __NR_setdomainname	121
-#define __NR_uname		122
-#define __NR_modify_ldt		123
-#define __NR_adjtimex		124
-#define __NR_mprotect		125
-#define __NR_sigprocmask	126
-#define __NR_create_module	127
-#define __NR_init_module	128
-#define __NR_delete_module	129
-#define __NR_get_kernel_syms	130
-#define __NR_quotactl		131
-#define __NR_getpgid		132
-#define __NR_fchdir		133
-#define __NR_bdflush		134
-#define __NR_sysfs		135
-#define __NR_personality	136
-#define __NR_afs_syscall	137 /* Syscall for Andrew File System */
-#define __NR_setfsuid		138
-#define __NR_setfsgid		139
-#define __NR__llseek		140
-#define __NR_getdents		141
-#define __NR__newselect		142
-#define __NR_flock		143
-#define __NR_msync		144
-#define __NR_readv		145
-#define __NR_writev		146
-#define __NR_getsid		147
-#define __NR_fdatasync		148
-#define __NR__sysctl		149
-#define __NR_mlock		150
-#define __NR_munlock		151
-#define __NR_mlockall		152
-#define __NR_munlockall		153
-#define __NR_sched_setparam		154
-#define __NR_sched_getparam		155
-#define __NR_sched_setscheduler		156
-#define __NR_sched_getscheduler		157
-#define __NR_sched_yield		158
-#define __NR_sched_get_priority_max	159
-#define __NR_sched_get_priority_min	160
-#define __NR_sched_rr_get_interval	161
-#define __NR_nanosleep		162
-#define __NR_mremap		163
-#define __NR_setresuid		164
-#define __NR_getresuid		165
-#define __NR_vm86		166
-#define __NR_query_module	167
-#define __NR_poll		168
-#define __NR_nfsservctl		169
-#define __NR_setresgid		170
-#define __NR_getresgid		171
-#define __NR_prctl              172
-#define __NR_rt_sigreturn	173
-#define __NR_rt_sigaction	174
-#define __NR_rt_sigprocmask	175
-#define __NR_rt_sigpending	176
-#define __NR_rt_sigtimedwait	177
-#define __NR_rt_sigqueueinfo	178
-#define __NR_rt_sigsuspend	179
-#define __NR_pread64		180
-#define __NR_pwrite64		181
-#define __NR_chown		182
-#define __NR_getcwd		183
-#define __NR_capget		184
-#define __NR_capset		185
-#define __NR_sigaltstack	186
-#define __NR_sendfile		187
-#define __NR_getpmsg		188	/* some people actually want streams */
-#define __NR_putpmsg		189	/* some people actually want streams */
-#define __NR_vfork		190
-#define __NR_ugetrlimit		191	/* SuS compliant getrlimit */
-#define __NR_mmap2		192
-#define __NR_truncate64		193
-#define __NR_ftruncate64	194
-#define __NR_stat64		195
-#define __NR_lstat64		196
-#define __NR_fstat64		197
-#define __NR_lchown32		198
-#define __NR_getuid32		199
-#define __NR_getgid32		200
-#define __NR_geteuid32		201
-#define __NR_getegid32		202
-#define __NR_setreuid32		203
-#define __NR_setregid32		204
-#define __NR_getgroups32	205
-#define __NR_setgroups32	206
-#define __NR_fchown32		207
-#define __NR_setresuid32	208
-#define __NR_getresuid32	209
-#define __NR_setresgid32	210
-#define __NR_getresgid32	211
-#define __NR_chown32		212
-#define __NR_setuid32		213
-#define __NR_setgid32		214
-#define __NR_setfsuid32		215
-#define __NR_setfsgid32		216
-#define __NR_pivot_root		217
-#define __NR_mincore		218
-#define __NR_madvise		219
-#define __NR_madvise1		219	/* delete when C lib stub is removed */
-#define __NR_getdents64		220
-#define __NR_fcntl64		221
-/* 223 is unused */
-#define __NR_gettid		224
-#define __NR_readahead		225
-#define __NR_setxattr		226
-#define __NR_lsetxattr		227
-#define __NR_fsetxattr		228
-#define __NR_getxattr		229
-#define __NR_lgetxattr		230
-#define __NR_fgetxattr		231
-#define __NR_listxattr		232
-#define __NR_llistxattr		233
-#define __NR_flistxattr		234
-#define __NR_removexattr	235
-#define __NR_lremovexattr	236
-#define __NR_fremovexattr	237
-#define __NR_tkill		238
-#define __NR_sendfile64		239
-#define __NR_futex		240
-#define __NR_sched_setaffinity	241
-#define __NR_sched_getaffinity	242
-#define __NR_set_thread_area	243
-#define __NR_get_thread_area	244
-#define __NR_io_setup		245
-#define __NR_io_destroy		246
-#define __NR_io_getevents	247
-#define __NR_io_submit		248
-#define __NR_io_cancel		249
-#define __NR_fadvise64		250
-/* 251 is available for reuse (was briefly sys_set_zone_reclaim) */
-#define __NR_exit_group		252
-#define __NR_lookup_dcookie	253
-#define __NR_epoll_create	254
-#define __NR_epoll_ctl		255
-#define __NR_epoll_wait		256
-#define __NR_remap_file_pages	257
-#define __NR_set_tid_address	258
-#define __NR_timer_create	259
-#define __NR_timer_settime	(__NR_timer_create+1)
-#define __NR_timer_gettime	(__NR_timer_create+2)
-#define __NR_timer_getoverrun	(__NR_timer_create+3)
-#define __NR_timer_delete	(__NR_timer_create+4)
-#define __NR_clock_settime	(__NR_timer_create+5)
-#define __NR_clock_gettime	(__NR_timer_create+6)
-#define __NR_clock_getres	(__NR_timer_create+7)
-#define __NR_clock_nanosleep	(__NR_timer_create+8)
-#define __NR_statfs64		268
-#define __NR_fstatfs64		269
-#define __NR_tgkill		270
-#define __NR_utimes		271
-#define __NR_fadvise64_64	272
-#define __NR_vserver		273
-#define __NR_mbind		274
-#define __NR_get_mempolicy	275
-#define __NR_set_mempolicy	276
-#define __NR_mq_open 		277
-#define __NR_mq_unlink		(__NR_mq_open+1)
-#define __NR_mq_timedsend	(__NR_mq_open+2)
-#define __NR_mq_timedreceive	(__NR_mq_open+3)
-#define __NR_mq_notify		(__NR_mq_open+4)
-#define __NR_mq_getsetattr	(__NR_mq_open+5)
-#define __NR_kexec_load		283
-#define __NR_waitid		284
-/* #define __NR_sys_setaltroot	285 */
-#define __NR_add_key		286
-#define __NR_request_key	287
-#define __NR_keyctl		288
-#define __NR_ioprio_set		289
-#define __NR_ioprio_get		290
-#define __NR_inotify_init	291
-#define __NR_inotify_add_watch	292
-#define __NR_inotify_rm_watch	293
-#define __NR_migrate_pages	294
-#define __NR_openat		295
-#define __NR_mkdirat		296
-#define __NR_mknodat		297
-#define __NR_fchownat		298
-#define __NR_futimesat		299
-#define __NR_fstatat64		300
-#define __NR_unlinkat		301
-#define __NR_renameat		302
-#define __NR_linkat		303
-#define __NR_symlinkat		304
-#define __NR_readlinkat		305
-#define __NR_fchmodat		306
-#define __NR_faccessat		307
-#define __NR_pselect6		308
-#define __NR_ppoll		309
-#define __NR_unshare		310
-#define __NR_set_robust_list	311
-#define __NR_get_robust_list	312
-#define __NR_splice		313
-#define __NR_sync_file_range	314
-#define __NR_tee		315
-#define __NR_vmsplice		316
-#define __NR_move_pages		317
-#define __NR_getcpu		318
-#define __NR_epoll_pwait	319
-#define __NR_utimensat		320
-#define __NR_signalfd		321
-#define __NR_timerfd_create	322
-#define __NR_eventfd		323
-#define __NR_fallocate		324
-#define __NR_timerfd_settime	325
-#define __NR_timerfd_gettime	326
-#define __NR_signalfd4		327
-#define __NR_eventfd2		328
-#define __NR_epoll_create1	329
-#define __NR_dup3		330
-#define __NR_pipe2		331
-#define __NR_inotify_init1	332
-
-#ifdef __KERNEL__
-
-#define __ARCH_WANT_IPC_PARSE_VERSION
-#define __ARCH_WANT_OLD_READDIR
-#define __ARCH_WANT_OLD_STAT
-#define __ARCH_WANT_STAT64
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_SGETMASK
-#define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_SOCKETCALL
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_NICE
-#define __ARCH_WANT_SYS_OLD_GETRLIMIT
-#define __ARCH_WANT_SYS_OLDUMOUNT
-#define __ARCH_WANT_SYS_SIGPENDING
-#define __ARCH_WANT_SYS_SIGPROCMASK
-#define __ARCH_WANT_SYS_RT_SIGACTION
-#define __ARCH_WANT_SYS_RT_SIGSUSPEND
-
-/*
- * "Conditional" syscalls
- *
- * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
- * but it doesn't work on all toolchains, so we just do it by hand
- */
-#ifndef cond_syscall
-#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
-#endif
-
-#endif /* __KERNEL__ */
-#endif /* ASM_X86__UNISTD_32_H */
diff --git a/include/asm-x86/unistd_64.h b/include/asm-x86/unistd_64.h
deleted file mode 100644
index ace83f1f6787..000000000000
--- a/include/asm-x86/unistd_64.h
+++ /dev/null
@@ -1,693 +0,0 @@
-#ifndef ASM_X86__UNISTD_64_H
-#define ASM_X86__UNISTD_64_H
-
-#ifndef __SYSCALL
-#define __SYSCALL(a, b)
-#endif
-
-/*
- * This file contains the system call numbers.
- *
- * Note: holes are not allowed.
- */
-
-/* at least 8 syscall per cacheline */
-#define __NR_read				0
-__SYSCALL(__NR_read, sys_read)
-#define __NR_write				1
-__SYSCALL(__NR_write, sys_write)
-#define __NR_open				2
-__SYSCALL(__NR_open, sys_open)
-#define __NR_close				3
-__SYSCALL(__NR_close, sys_close)
-#define __NR_stat				4
-__SYSCALL(__NR_stat, sys_newstat)
-#define __NR_fstat				5
-__SYSCALL(__NR_fstat, sys_newfstat)
-#define __NR_lstat				6
-__SYSCALL(__NR_lstat, sys_newlstat)
-#define __NR_poll				7
-__SYSCALL(__NR_poll, sys_poll)
-
-#define __NR_lseek				8
-__SYSCALL(__NR_lseek, sys_lseek)
-#define __NR_mmap				9
-__SYSCALL(__NR_mmap, sys_mmap)
-#define __NR_mprotect				10
-__SYSCALL(__NR_mprotect, sys_mprotect)
-#define __NR_munmap				11
-__SYSCALL(__NR_munmap, sys_munmap)
-#define __NR_brk				12
-__SYSCALL(__NR_brk, sys_brk)
-#define __NR_rt_sigaction			13
-__SYSCALL(__NR_rt_sigaction, sys_rt_sigaction)
-#define __NR_rt_sigprocmask			14
-__SYSCALL(__NR_rt_sigprocmask, sys_rt_sigprocmask)
-#define __NR_rt_sigreturn			15
-__SYSCALL(__NR_rt_sigreturn, stub_rt_sigreturn)
-
-#define __NR_ioctl				16
-__SYSCALL(__NR_ioctl, sys_ioctl)
-#define __NR_pread64				17
-__SYSCALL(__NR_pread64, sys_pread64)
-#define __NR_pwrite64				18
-__SYSCALL(__NR_pwrite64, sys_pwrite64)
-#define __NR_readv				19
-__SYSCALL(__NR_readv, sys_readv)
-#define __NR_writev				20
-__SYSCALL(__NR_writev, sys_writev)
-#define __NR_access				21
-__SYSCALL(__NR_access, sys_access)
-#define __NR_pipe				22
-__SYSCALL(__NR_pipe, sys_pipe)
-#define __NR_select				23
-__SYSCALL(__NR_select, sys_select)
-
-#define __NR_sched_yield			24
-__SYSCALL(__NR_sched_yield, sys_sched_yield)
-#define __NR_mremap				25
-__SYSCALL(__NR_mremap, sys_mremap)
-#define __NR_msync				26
-__SYSCALL(__NR_msync, sys_msync)
-#define __NR_mincore				27
-__SYSCALL(__NR_mincore, sys_mincore)
-#define __NR_madvise				28
-__SYSCALL(__NR_madvise, sys_madvise)
-#define __NR_shmget				29
-__SYSCALL(__NR_shmget, sys_shmget)
-#define __NR_shmat				30
-__SYSCALL(__NR_shmat, sys_shmat)
-#define __NR_shmctl				31
-__SYSCALL(__NR_shmctl, sys_shmctl)
-
-#define __NR_dup				32
-__SYSCALL(__NR_dup, sys_dup)
-#define __NR_dup2				33
-__SYSCALL(__NR_dup2, sys_dup2)
-#define __NR_pause				34
-__SYSCALL(__NR_pause, sys_pause)
-#define __NR_nanosleep				35
-__SYSCALL(__NR_nanosleep, sys_nanosleep)
-#define __NR_getitimer				36
-__SYSCALL(__NR_getitimer, sys_getitimer)
-#define __NR_alarm				37
-__SYSCALL(__NR_alarm, sys_alarm)
-#define __NR_setitimer				38
-__SYSCALL(__NR_setitimer, sys_setitimer)
-#define __NR_getpid				39
-__SYSCALL(__NR_getpid, sys_getpid)
-
-#define __NR_sendfile				40
-__SYSCALL(__NR_sendfile, sys_sendfile64)
-#define __NR_socket				41
-__SYSCALL(__NR_socket, sys_socket)
-#define __NR_connect				42
-__SYSCALL(__NR_connect, sys_connect)
-#define __NR_accept				43
-__SYSCALL(__NR_accept, sys_accept)
-#define __NR_sendto				44
-__SYSCALL(__NR_sendto, sys_sendto)
-#define __NR_recvfrom				45
-__SYSCALL(__NR_recvfrom, sys_recvfrom)
-#define __NR_sendmsg				46
-__SYSCALL(__NR_sendmsg, sys_sendmsg)
-#define __NR_recvmsg				47
-__SYSCALL(__NR_recvmsg, sys_recvmsg)
-
-#define __NR_shutdown				48
-__SYSCALL(__NR_shutdown, sys_shutdown)
-#define __NR_bind				49
-__SYSCALL(__NR_bind, sys_bind)
-#define __NR_listen				50
-__SYSCALL(__NR_listen, sys_listen)
-#define __NR_getsockname			51
-__SYSCALL(__NR_getsockname, sys_getsockname)
-#define __NR_getpeername			52
-__SYSCALL(__NR_getpeername, sys_getpeername)
-#define __NR_socketpair				53
-__SYSCALL(__NR_socketpair, sys_socketpair)
-#define __NR_setsockopt				54
-__SYSCALL(__NR_setsockopt, sys_setsockopt)
-#define __NR_getsockopt				55
-__SYSCALL(__NR_getsockopt, sys_getsockopt)
-
-#define __NR_clone				56
-__SYSCALL(__NR_clone, stub_clone)
-#define __NR_fork				57
-__SYSCALL(__NR_fork, stub_fork)
-#define __NR_vfork				58
-__SYSCALL(__NR_vfork, stub_vfork)
-#define __NR_execve				59
-__SYSCALL(__NR_execve, stub_execve)
-#define __NR_exit				60
-__SYSCALL(__NR_exit, sys_exit)
-#define __NR_wait4				61
-__SYSCALL(__NR_wait4, sys_wait4)
-#define __NR_kill				62
-__SYSCALL(__NR_kill, sys_kill)
-#define __NR_uname				63
-__SYSCALL(__NR_uname, sys_uname)
-
-#define __NR_semget				64
-__SYSCALL(__NR_semget, sys_semget)
-#define __NR_semop				65
-__SYSCALL(__NR_semop, sys_semop)
-#define __NR_semctl				66
-__SYSCALL(__NR_semctl, sys_semctl)
-#define __NR_shmdt				67
-__SYSCALL(__NR_shmdt, sys_shmdt)
-#define __NR_msgget				68
-__SYSCALL(__NR_msgget, sys_msgget)
-#define __NR_msgsnd				69
-__SYSCALL(__NR_msgsnd, sys_msgsnd)
-#define __NR_msgrcv				70
-__SYSCALL(__NR_msgrcv, sys_msgrcv)
-#define __NR_msgctl				71
-__SYSCALL(__NR_msgctl, sys_msgctl)
-
-#define __NR_fcntl				72
-__SYSCALL(__NR_fcntl, sys_fcntl)
-#define __NR_flock				73
-__SYSCALL(__NR_flock, sys_flock)
-#define __NR_fsync				74
-__SYSCALL(__NR_fsync, sys_fsync)
-#define __NR_fdatasync				75
-__SYSCALL(__NR_fdatasync, sys_fdatasync)
-#define __NR_truncate				76
-__SYSCALL(__NR_truncate, sys_truncate)
-#define __NR_ftruncate				77
-__SYSCALL(__NR_ftruncate, sys_ftruncate)
-#define __NR_getdents				78
-__SYSCALL(__NR_getdents, sys_getdents)
-#define __NR_getcwd				79
-__SYSCALL(__NR_getcwd, sys_getcwd)
-
-#define __NR_chdir				80
-__SYSCALL(__NR_chdir, sys_chdir)
-#define __NR_fchdir				81
-__SYSCALL(__NR_fchdir, sys_fchdir)
-#define __NR_rename				82
-__SYSCALL(__NR_rename, sys_rename)
-#define __NR_mkdir				83
-__SYSCALL(__NR_mkdir, sys_mkdir)
-#define __NR_rmdir				84
-__SYSCALL(__NR_rmdir, sys_rmdir)
-#define __NR_creat				85
-__SYSCALL(__NR_creat, sys_creat)
-#define __NR_link				86
-__SYSCALL(__NR_link, sys_link)
-#define __NR_unlink				87
-__SYSCALL(__NR_unlink, sys_unlink)
-
-#define __NR_symlink				88
-__SYSCALL(__NR_symlink, sys_symlink)
-#define __NR_readlink				89
-__SYSCALL(__NR_readlink, sys_readlink)
-#define __NR_chmod				90
-__SYSCALL(__NR_chmod, sys_chmod)
-#define __NR_fchmod				91
-__SYSCALL(__NR_fchmod, sys_fchmod)
-#define __NR_chown				92
-__SYSCALL(__NR_chown, sys_chown)
-#define __NR_fchown				93
-__SYSCALL(__NR_fchown, sys_fchown)
-#define __NR_lchown				94
-__SYSCALL(__NR_lchown, sys_lchown)
-#define __NR_umask				95
-__SYSCALL(__NR_umask, sys_umask)
-
-#define __NR_gettimeofday			96
-__SYSCALL(__NR_gettimeofday, sys_gettimeofday)
-#define __NR_getrlimit				97
-__SYSCALL(__NR_getrlimit, sys_getrlimit)
-#define __NR_getrusage				98
-__SYSCALL(__NR_getrusage, sys_getrusage)
-#define __NR_sysinfo				99
-__SYSCALL(__NR_sysinfo, sys_sysinfo)
-#define __NR_times				100
-__SYSCALL(__NR_times, sys_times)
-#define __NR_ptrace				101
-__SYSCALL(__NR_ptrace, sys_ptrace)
-#define __NR_getuid				102
-__SYSCALL(__NR_getuid, sys_getuid)
-#define __NR_syslog				103
-__SYSCALL(__NR_syslog, sys_syslog)
-
-/* at the very end the stuff that never runs during the benchmarks */
-#define __NR_getgid				104
-__SYSCALL(__NR_getgid, sys_getgid)
-#define __NR_setuid				105
-__SYSCALL(__NR_setuid, sys_setuid)
-#define __NR_setgid				106
-__SYSCALL(__NR_setgid, sys_setgid)
-#define __NR_geteuid				107
-__SYSCALL(__NR_geteuid, sys_geteuid)
-#define __NR_getegid				108
-__SYSCALL(__NR_getegid, sys_getegid)
-#define __NR_setpgid				109
-__SYSCALL(__NR_setpgid, sys_setpgid)
-#define __NR_getppid				110
-__SYSCALL(__NR_getppid, sys_getppid)
-#define __NR_getpgrp				111
-__SYSCALL(__NR_getpgrp, sys_getpgrp)
-
-#define __NR_setsid				112
-__SYSCALL(__NR_setsid, sys_setsid)
-#define __NR_setreuid				113
-__SYSCALL(__NR_setreuid, sys_setreuid)
-#define __NR_setregid				114
-__SYSCALL(__NR_setregid, sys_setregid)
-#define __NR_getgroups				115
-__SYSCALL(__NR_getgroups, sys_getgroups)
-#define __NR_setgroups				116
-__SYSCALL(__NR_setgroups, sys_setgroups)
-#define __NR_setresuid				117
-__SYSCALL(__NR_setresuid, sys_setresuid)
-#define __NR_getresuid				118
-__SYSCALL(__NR_getresuid, sys_getresuid)
-#define __NR_setresgid				119
-__SYSCALL(__NR_setresgid, sys_setresgid)
-
-#define __NR_getresgid				120
-__SYSCALL(__NR_getresgid, sys_getresgid)
-#define __NR_getpgid				121
-__SYSCALL(__NR_getpgid, sys_getpgid)
-#define __NR_setfsuid				122
-__SYSCALL(__NR_setfsuid, sys_setfsuid)
-#define __NR_setfsgid				123
-__SYSCALL(__NR_setfsgid, sys_setfsgid)
-#define __NR_getsid				124
-__SYSCALL(__NR_getsid, sys_getsid)
-#define __NR_capget				125
-__SYSCALL(__NR_capget, sys_capget)
-#define __NR_capset				126
-__SYSCALL(__NR_capset, sys_capset)
-
-#define __NR_rt_sigpending			127
-__SYSCALL(__NR_rt_sigpending, sys_rt_sigpending)
-#define __NR_rt_sigtimedwait			128
-__SYSCALL(__NR_rt_sigtimedwait, sys_rt_sigtimedwait)
-#define __NR_rt_sigqueueinfo			129
-__SYSCALL(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo)
-#define __NR_rt_sigsuspend			130
-__SYSCALL(__NR_rt_sigsuspend, sys_rt_sigsuspend)
-#define __NR_sigaltstack			131
-__SYSCALL(__NR_sigaltstack, stub_sigaltstack)
-#define __NR_utime				132
-__SYSCALL(__NR_utime, sys_utime)
-#define __NR_mknod				133
-__SYSCALL(__NR_mknod, sys_mknod)
-
-/* Only needed for a.out */
-#define __NR_uselib				134
-__SYSCALL(__NR_uselib, sys_ni_syscall)
-#define __NR_personality			135
-__SYSCALL(__NR_personality, sys_personality)
-
-#define __NR_ustat				136
-__SYSCALL(__NR_ustat, sys_ustat)
-#define __NR_statfs				137
-__SYSCALL(__NR_statfs, sys_statfs)
-#define __NR_fstatfs				138
-__SYSCALL(__NR_fstatfs, sys_fstatfs)
-#define __NR_sysfs				139
-__SYSCALL(__NR_sysfs, sys_sysfs)
-
-#define __NR_getpriority			140
-__SYSCALL(__NR_getpriority, sys_getpriority)
-#define __NR_setpriority			141
-__SYSCALL(__NR_setpriority, sys_setpriority)
-#define __NR_sched_setparam			142
-__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
-#define __NR_sched_getparam			143
-__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
-#define __NR_sched_setscheduler			144
-__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
-#define __NR_sched_getscheduler			145
-__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
-#define __NR_sched_get_priority_max		146
-__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
-#define __NR_sched_get_priority_min		147
-__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
-#define __NR_sched_rr_get_interval		148
-__SYSCALL(__NR_sched_rr_get_interval, sys_sched_rr_get_interval)
-
-#define __NR_mlock				149
-__SYSCALL(__NR_mlock, sys_mlock)
-#define __NR_munlock				150
-__SYSCALL(__NR_munlock, sys_munlock)
-#define __NR_mlockall				151
-__SYSCALL(__NR_mlockall, sys_mlockall)
-#define __NR_munlockall				152
-__SYSCALL(__NR_munlockall, sys_munlockall)
-
-#define __NR_vhangup				153
-__SYSCALL(__NR_vhangup, sys_vhangup)
-
-#define __NR_modify_ldt				154
-__SYSCALL(__NR_modify_ldt, sys_modify_ldt)
-
-#define __NR_pivot_root				155
-__SYSCALL(__NR_pivot_root, sys_pivot_root)
-
-#define __NR__sysctl				156
-__SYSCALL(__NR__sysctl, sys_sysctl)
-
-#define __NR_prctl				157
-__SYSCALL(__NR_prctl, sys_prctl)
-#define __NR_arch_prctl				158
-__SYSCALL(__NR_arch_prctl, sys_arch_prctl)
-
-#define __NR_adjtimex				159
-__SYSCALL(__NR_adjtimex, sys_adjtimex)
-
-#define __NR_setrlimit				160
-__SYSCALL(__NR_setrlimit, sys_setrlimit)
-
-#define __NR_chroot				161
-__SYSCALL(__NR_chroot, sys_chroot)
-
-#define __NR_sync				162
-__SYSCALL(__NR_sync, sys_sync)
-
-#define __NR_acct				163
-__SYSCALL(__NR_acct, sys_acct)
-
-#define __NR_settimeofday			164
-__SYSCALL(__NR_settimeofday, sys_settimeofday)
-
-#define __NR_mount				165
-__SYSCALL(__NR_mount, sys_mount)
-#define __NR_umount2				166
-__SYSCALL(__NR_umount2, sys_umount)
-
-#define __NR_swapon				167
-__SYSCALL(__NR_swapon, sys_swapon)
-#define __NR_swapoff				168
-__SYSCALL(__NR_swapoff, sys_swapoff)
-
-#define __NR_reboot				169
-__SYSCALL(__NR_reboot, sys_reboot)
-
-#define __NR_sethostname			170
-__SYSCALL(__NR_sethostname, sys_sethostname)
-#define __NR_setdomainname			171
-__SYSCALL(__NR_setdomainname, sys_setdomainname)
-
-#define __NR_iopl				172
-__SYSCALL(__NR_iopl, stub_iopl)
-#define __NR_ioperm				173
-__SYSCALL(__NR_ioperm, sys_ioperm)
-
-#define __NR_create_module			174
-__SYSCALL(__NR_create_module, sys_ni_syscall)
-#define __NR_init_module			175
-__SYSCALL(__NR_init_module, sys_init_module)
-#define __NR_delete_module			176
-__SYSCALL(__NR_delete_module, sys_delete_module)
-#define __NR_get_kernel_syms			177
-__SYSCALL(__NR_get_kernel_syms, sys_ni_syscall)
-#define __NR_query_module			178
-__SYSCALL(__NR_query_module, sys_ni_syscall)
-
-#define __NR_quotactl				179
-__SYSCALL(__NR_quotactl, sys_quotactl)
-
-#define __NR_nfsservctl				180
-__SYSCALL(__NR_nfsservctl, sys_nfsservctl)
-
-/* reserved for LiS/STREAMS */
-#define __NR_getpmsg				181
-__SYSCALL(__NR_getpmsg, sys_ni_syscall)
-#define __NR_putpmsg				182
-__SYSCALL(__NR_putpmsg, sys_ni_syscall)
-
-/* reserved for AFS */
-#define __NR_afs_syscall			183
-__SYSCALL(__NR_afs_syscall, sys_ni_syscall)
-
-/* reserved for tux */
-#define __NR_tuxcall				184
-__SYSCALL(__NR_tuxcall, sys_ni_syscall)
-
-#define __NR_security				185
-__SYSCALL(__NR_security, sys_ni_syscall)
-
-#define __NR_gettid				186
-__SYSCALL(__NR_gettid, sys_gettid)
-
-#define __NR_readahead				187
-__SYSCALL(__NR_readahead, sys_readahead)
-#define __NR_setxattr				188
-__SYSCALL(__NR_setxattr, sys_setxattr)
-#define __NR_lsetxattr				189
-__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
-#define __NR_fsetxattr				190
-__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
-#define __NR_getxattr				191
-__SYSCALL(__NR_getxattr, sys_getxattr)
-#define __NR_lgetxattr				192
-__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
-#define __NR_fgetxattr				193
-__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
-#define __NR_listxattr				194
-__SYSCALL(__NR_listxattr, sys_listxattr)
-#define __NR_llistxattr				195
-__SYSCALL(__NR_llistxattr, sys_llistxattr)
-#define __NR_flistxattr				196
-__SYSCALL(__NR_flistxattr, sys_flistxattr)
-#define __NR_removexattr			197
-__SYSCALL(__NR_removexattr, sys_removexattr)
-#define __NR_lremovexattr			198
-__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
-#define __NR_fremovexattr			199
-__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
-#define __NR_tkill				200
-__SYSCALL(__NR_tkill, sys_tkill)
-#define __NR_time				201
-__SYSCALL(__NR_time, sys_time)
-#define __NR_futex				202
-__SYSCALL(__NR_futex, sys_futex)
-#define __NR_sched_setaffinity			203
-__SYSCALL(__NR_sched_setaffinity, sys_sched_setaffinity)
-#define __NR_sched_getaffinity			204
-__SYSCALL(__NR_sched_getaffinity, sys_sched_getaffinity)
-#define __NR_set_thread_area			205
-__SYSCALL(__NR_set_thread_area, sys_ni_syscall)	/* use arch_prctl */
-#define __NR_io_setup				206
-__SYSCALL(__NR_io_setup, sys_io_setup)
-#define __NR_io_destroy				207
-__SYSCALL(__NR_io_destroy, sys_io_destroy)
-#define __NR_io_getevents			208
-__SYSCALL(__NR_io_getevents, sys_io_getevents)
-#define __NR_io_submit				209
-__SYSCALL(__NR_io_submit, sys_io_submit)
-#define __NR_io_cancel				210
-__SYSCALL(__NR_io_cancel, sys_io_cancel)
-#define __NR_get_thread_area			211
-__SYSCALL(__NR_get_thread_area, sys_ni_syscall)	/* use arch_prctl */
-#define __NR_lookup_dcookie			212
-__SYSCALL(__NR_lookup_dcookie, sys_lookup_dcookie)
-#define __NR_epoll_create			213
-__SYSCALL(__NR_epoll_create, sys_epoll_create)
-#define __NR_epoll_ctl_old			214
-__SYSCALL(__NR_epoll_ctl_old, sys_ni_syscall)
-#define __NR_epoll_wait_old			215
-__SYSCALL(__NR_epoll_wait_old, sys_ni_syscall)
-#define __NR_remap_file_pages			216
-__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
-#define __NR_getdents64				217
-__SYSCALL(__NR_getdents64, sys_getdents64)
-#define __NR_set_tid_address			218
-__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
-#define __NR_restart_syscall			219
-__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
-#define __NR_semtimedop				220
-__SYSCALL(__NR_semtimedop, sys_semtimedop)
-#define __NR_fadvise64				221
-__SYSCALL(__NR_fadvise64, sys_fadvise64)
-#define __NR_timer_create			222
-__SYSCALL(__NR_timer_create, sys_timer_create)
-#define __NR_timer_settime			223
-__SYSCALL(__NR_timer_settime, sys_timer_settime)
-#define __NR_timer_gettime			224
-__SYSCALL(__NR_timer_gettime, sys_timer_gettime)
-#define __NR_timer_getoverrun			225
-__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
-#define __NR_timer_delete			226
-__SYSCALL(__NR_timer_delete, sys_timer_delete)
-#define __NR_clock_settime			227
-__SYSCALL(__NR_clock_settime, sys_clock_settime)
-#define __NR_clock_gettime			228
-__SYSCALL(__NR_clock_gettime, sys_clock_gettime)
-#define __NR_clock_getres			229
-__SYSCALL(__NR_clock_getres, sys_clock_getres)
-#define __NR_clock_nanosleep			230
-__SYSCALL(__NR_clock_nanosleep, sys_clock_nanosleep)
-#define __NR_exit_group				231
-__SYSCALL(__NR_exit_group, sys_exit_group)
-#define __NR_epoll_wait				232
-__SYSCALL(__NR_epoll_wait, sys_epoll_wait)
-#define __NR_epoll_ctl				233
-__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
-#define __NR_tgkill				234
-__SYSCALL(__NR_tgkill, sys_tgkill)
-#define __NR_utimes				235
-__SYSCALL(__NR_utimes, sys_utimes)
-#define __NR_vserver				236
-__SYSCALL(__NR_vserver, sys_ni_syscall)
-#define __NR_mbind				237
-__SYSCALL(__NR_mbind, sys_mbind)
-#define __NR_set_mempolicy			238
-__SYSCALL(__NR_set_mempolicy, sys_set_mempolicy)
-#define __NR_get_mempolicy			239
-__SYSCALL(__NR_get_mempolicy, sys_get_mempolicy)
-#define __NR_mq_open				240
-__SYSCALL(__NR_mq_open, sys_mq_open)
-#define __NR_mq_unlink				241
-__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
-#define __NR_mq_timedsend			242
-__SYSCALL(__NR_mq_timedsend, sys_mq_timedsend)
-#define __NR_mq_timedreceive			243
-__SYSCALL(__NR_mq_timedreceive, sys_mq_timedreceive)
-#define __NR_mq_notify				244
-__SYSCALL(__NR_mq_notify, sys_mq_notify)
-#define __NR_mq_getsetattr			245
-__SYSCALL(__NR_mq_getsetattr, sys_mq_getsetattr)
-#define __NR_kexec_load				246
-__SYSCALL(__NR_kexec_load, sys_kexec_load)
-#define __NR_waitid				247
-__SYSCALL(__NR_waitid, sys_waitid)
-#define __NR_add_key				248
-__SYSCALL(__NR_add_key, sys_add_key)
-#define __NR_request_key			249
-__SYSCALL(__NR_request_key, sys_request_key)
-#define __NR_keyctl				250
-__SYSCALL(__NR_keyctl, sys_keyctl)
-#define __NR_ioprio_set				251
-__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
-#define __NR_ioprio_get				252
-__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
-#define __NR_inotify_init			253
-__SYSCALL(__NR_inotify_init, sys_inotify_init)
-#define __NR_inotify_add_watch			254
-__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
-#define __NR_inotify_rm_watch			255
-__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
-#define __NR_migrate_pages			256
-__SYSCALL(__NR_migrate_pages, sys_migrate_pages)
-#define __NR_openat				257
-__SYSCALL(__NR_openat, sys_openat)
-#define __NR_mkdirat				258
-__SYSCALL(__NR_mkdirat, sys_mkdirat)
-#define __NR_mknodat				259
-__SYSCALL(__NR_mknodat, sys_mknodat)
-#define __NR_fchownat				260
-__SYSCALL(__NR_fchownat, sys_fchownat)
-#define __NR_futimesat				261
-__SYSCALL(__NR_futimesat, sys_futimesat)
-#define __NR_newfstatat				262
-__SYSCALL(__NR_newfstatat, sys_newfstatat)
-#define __NR_unlinkat				263
-__SYSCALL(__NR_unlinkat, sys_unlinkat)
-#define __NR_renameat				264
-__SYSCALL(__NR_renameat, sys_renameat)
-#define __NR_linkat				265
-__SYSCALL(__NR_linkat, sys_linkat)
-#define __NR_symlinkat				266
-__SYSCALL(__NR_symlinkat, sys_symlinkat)
-#define __NR_readlinkat				267
-__SYSCALL(__NR_readlinkat, sys_readlinkat)
-#define __NR_fchmodat				268
-__SYSCALL(__NR_fchmodat, sys_fchmodat)
-#define __NR_faccessat				269
-__SYSCALL(__NR_faccessat, sys_faccessat)
-#define __NR_pselect6				270
-__SYSCALL(__NR_pselect6, sys_pselect6)
-#define __NR_ppoll				271
-__SYSCALL(__NR_ppoll,	sys_ppoll)
-#define __NR_unshare				272
-__SYSCALL(__NR_unshare,	sys_unshare)
-#define __NR_set_robust_list			273
-__SYSCALL(__NR_set_robust_list, sys_set_robust_list)
-#define __NR_get_robust_list			274
-__SYSCALL(__NR_get_robust_list, sys_get_robust_list)
-#define __NR_splice				275
-__SYSCALL(__NR_splice, sys_splice)
-#define __NR_tee				276
-__SYSCALL(__NR_tee, sys_tee)
-#define __NR_sync_file_range			277
-__SYSCALL(__NR_sync_file_range, sys_sync_file_range)
-#define __NR_vmsplice				278
-__SYSCALL(__NR_vmsplice, sys_vmsplice)
-#define __NR_move_pages				279
-__SYSCALL(__NR_move_pages, sys_move_pages)
-#define __NR_utimensat				280
-__SYSCALL(__NR_utimensat, sys_utimensat)
-#define __IGNORE_getcpu		/* implemented as a vsyscall */
-#define __NR_epoll_pwait			281
-__SYSCALL(__NR_epoll_pwait, sys_epoll_pwait)
-#define __NR_signalfd				282
-__SYSCALL(__NR_signalfd, sys_signalfd)
-#define __NR_timerfd_create			283
-__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
-#define __NR_eventfd				284
-__SYSCALL(__NR_eventfd, sys_eventfd)
-#define __NR_fallocate				285
-__SYSCALL(__NR_fallocate, sys_fallocate)
-#define __NR_timerfd_settime			286
-__SYSCALL(__NR_timerfd_settime, sys_timerfd_settime)
-#define __NR_timerfd_gettime			287
-__SYSCALL(__NR_timerfd_gettime, sys_timerfd_gettime)
-#define __NR_paccept				288
-__SYSCALL(__NR_paccept, sys_paccept)
-#define __NR_signalfd4				289
-__SYSCALL(__NR_signalfd4, sys_signalfd4)
-#define __NR_eventfd2				290
-__SYSCALL(__NR_eventfd2, sys_eventfd2)
-#define __NR_epoll_create1			291
-__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
-#define __NR_dup3				292
-__SYSCALL(__NR_dup3, sys_dup3)
-#define __NR_pipe2				293
-__SYSCALL(__NR_pipe2, sys_pipe2)
-#define __NR_inotify_init1			294
-__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
-
-
-#ifndef __NO_STUBS
-#define __ARCH_WANT_OLD_READDIR
-#define __ARCH_WANT_OLD_STAT
-#define __ARCH_WANT_SYS_ALARM
-#define __ARCH_WANT_SYS_GETHOSTNAME
-#define __ARCH_WANT_SYS_PAUSE
-#define __ARCH_WANT_SYS_SGETMASK
-#define __ARCH_WANT_SYS_SIGNAL
-#define __ARCH_WANT_SYS_UTIME
-#define __ARCH_WANT_SYS_WAITPID
-#define __ARCH_WANT_SYS_SOCKETCALL
-#define __ARCH_WANT_SYS_FADVISE64
-#define __ARCH_WANT_SYS_GETPGRP
-#define __ARCH_WANT_SYS_LLSEEK
-#define __ARCH_WANT_SYS_NICE
-#define __ARCH_WANT_SYS_OLD_GETRLIMIT
-#define __ARCH_WANT_SYS_OLDUMOUNT
-#define __ARCH_WANT_SYS_SIGPENDING
-#define __ARCH_WANT_SYS_SIGPROCMASK
-#define __ARCH_WANT_SYS_RT_SIGACTION
-#define __ARCH_WANT_SYS_RT_SIGSUSPEND
-#define __ARCH_WANT_SYS_TIME
-#define __ARCH_WANT_COMPAT_SYS_TIME
-#endif	/* __NO_STUBS */
-
-#ifdef __KERNEL__
-/*
- * "Conditional" syscalls
- *
- * What we want is __attribute__((weak,alias("sys_ni_syscall"))),
- * but it doesn't work on all toolchains, so we just do it by hand
- */
-#define cond_syscall(x) asm(".weak\t" #x "\n\t.set\t" #x ",sys_ni_syscall")
-#endif	/* __KERNEL__ */
-
-#endif /* ASM_X86__UNISTD_64_H */
diff --git a/include/asm-x86/unwind.h b/include/asm-x86/unwind.h
deleted file mode 100644
index a2151567db44..000000000000
--- a/include/asm-x86/unwind.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef ASM_X86__UNWIND_H
-#define ASM_X86__UNWIND_H
-
-#define UNW_PC(frame) ((void)(frame), 0UL)
-#define UNW_SP(frame) ((void)(frame), 0UL)
-#define UNW_FP(frame) ((void)(frame), 0UL)
-
-static inline int arch_unw_user_mode(const void *info)
-{
-	return 0;
-}
-
-#endif /* ASM_X86__UNWIND_H */
diff --git a/include/asm-x86/user.h b/include/asm-x86/user.h
deleted file mode 100644
index 999873b22e7f..000000000000
--- a/include/asm-x86/user.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "user_32.h"
-#else
-# include "user_64.h"
-#endif
diff --git a/include/asm-x86/user32.h b/include/asm-x86/user32.h
deleted file mode 100644
index aa66c1857f06..000000000000
--- a/include/asm-x86/user32.h
+++ /dev/null
@@ -1,70 +0,0 @@
-#ifndef ASM_X86__USER32_H
-#define ASM_X86__USER32_H
-
-/* IA32 compatible user structures for ptrace.
- * These should be used for 32bit coredumps too. */
-
-struct user_i387_ia32_struct {
-	u32	cwd;
-	u32	swd;
-	u32	twd;
-	u32	fip;
-	u32	fcs;
-	u32	foo;
-	u32	fos;
-	u32	st_space[20];   /* 8*10 bytes for each FP-reg = 80 bytes */
-};
-
-/* FSAVE frame with extensions */
-struct user32_fxsr_struct {
-	unsigned short	cwd;
-	unsigned short	swd;
-	unsigned short	twd;	/* not compatible to 64bit twd */
-	unsigned short	fop;
-	int	fip;
-	int	fcs;
-	int	foo;
-	int	fos;
-	int	mxcsr;
-	int	reserved;
-	int	st_space[32];	/* 8*16 bytes for each FP-reg = 128 bytes */
-	int	xmm_space[32];	/* 8*16 bytes for each XMM-reg = 128 bytes */
-	int	padding[56];
-};
-
-struct user_regs_struct32 {
-	__u32 ebx, ecx, edx, esi, edi, ebp, eax;
-	unsigned short ds, __ds, es, __es;
-	unsigned short fs, __fs, gs, __gs;
-	__u32 orig_eax, eip;
-	unsigned short cs, __cs;
-	__u32 eflags, esp;
-	unsigned short ss, __ss;
-};
-
-struct user32 {
-  struct user_regs_struct32 regs; /* Where the registers are actually stored */
-  int u_fpvalid;		/* True if math co-processor being used. */
-				/* for this mess. Not yet used. */
-  struct user_i387_ia32_struct i387;	/* Math Co-processor registers. */
-/* The rest of this junk is to help gdb figure out what goes where */
-  __u32 u_tsize;	/* Text segment size (pages). */
-  __u32 u_dsize;	/* Data segment size (pages). */
-  __u32 u_ssize;	/* Stack segment size (pages). */
-  __u32 start_code;     /* Starting virtual address of text. */
-  __u32 start_stack;	/* Starting virtual address of stack area.
-				   This is actually the bottom of the stack,
-				   the top of the stack is always found in the
-				   esp register.  */
-  __u32 signal;     		/* Signal that caused the core dump. */
-  int reserved;			/* No __u32er used */
-  __u32 u_ar0;	/* Used by gdb to help find the values for */
-				/* the registers. */
-  __u32 u_fpstate;	/* Math Co-processor pointer. */
-  __u32 magic;		/* To uniquely identify a core file */
-  char u_comm[32];		/* User command that was responsible */
-  int u_debugreg[8];
-};
-
-
-#endif /* ASM_X86__USER32_H */
diff --git a/include/asm-x86/user_32.h b/include/asm-x86/user_32.h
deleted file mode 100644
index e0fe2f55f1a6..000000000000
--- a/include/asm-x86/user_32.h
+++ /dev/null
@@ -1,131 +0,0 @@
-#ifndef ASM_X86__USER_32_H
-#define ASM_X86__USER_32_H
-
-#include <asm/page.h>
-/* Core file format: The core file is written in such a way that gdb
-   can understand it and provide useful information to the user (under
-   linux we use the 'trad-core' bfd).  There are quite a number of
-   obstacles to being able to view the contents of the floating point
-   registers, and until these are solved you will not be able to view the
-   contents of them.  Actually, you can read in the core file and look at
-   the contents of the user struct to find out what the floating point
-   registers contain.
-   The actual file contents are as follows:
-   UPAGE: 1 page consisting of a user struct that tells gdb what is present
-   in the file.  Directly after this is a copy of the task_struct, which
-   is currently not used by gdb, but it may come in useful at some point.
-   All of the registers are stored as part of the upage.  The upage should
-   always be only one page.
-   DATA: The data area is stored.  We use current->end_text to
-   current->brk to pick up all of the user variables, plus any memory
-   that may have been malloced.  No attempt is made to determine if a page
-   is demand-zero or if a page is totally unused, we just cover the entire
-   range.  All of the addresses are rounded in such a way that an integral
-   number of pages is written.
-   STACK: We need the stack information in order to get a meaningful
-   backtrace.  We need to write the data from (esp) to
-   current->start_stack, so we round each of these off in order to be able
-   to write an integer number of pages.
-   The minimum core file size is 3 pages, or 12288 bytes.
-*/
-
-/*
- * Pentium III FXSR, SSE support
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- *
- * Provide support for the GDB 5.0+ PTRACE_{GET|SET}FPXREGS requests for
- * interacting with the FXSR-format floating point environment.  Floating
- * point data can be accessed in the regular format in the usual manner,
- * and both the standard and SIMD floating point data can be accessed via
- * the new ptrace requests.  In either case, changes to the FPU environment
- * will be reflected in the task's state as expected.
- */
-
-struct user_i387_struct {
-	long	cwd;
-	long	swd;
-	long	twd;
-	long	fip;
-	long	fcs;
-	long	foo;
-	long	fos;
-	long	st_space[20];	/* 8*10 bytes for each FP-reg = 80 bytes */
-};
-
-struct user_fxsr_struct {
-	unsigned short	cwd;
-	unsigned short	swd;
-	unsigned short	twd;
-	unsigned short	fop;
-	long	fip;
-	long	fcs;
-	long	foo;
-	long	fos;
-	long	mxcsr;
-	long	reserved;
-	long	st_space[32];	/* 8*16 bytes for each FP-reg = 128 bytes */
-	long	xmm_space[32];	/* 8*16 bytes for each XMM-reg = 128 bytes */
-	long	padding[56];
-};
-
-/*
- * This is the old layout of "struct pt_regs", and
- * is still the layout used by user mode (the new
- * pt_regs doesn't have all registers as the kernel
- * doesn't use the extra segment registers)
- */
-struct user_regs_struct {
-	unsigned long	bx;
-	unsigned long	cx;
-	unsigned long	dx;
-	unsigned long	si;
-	unsigned long	di;
-	unsigned long	bp;
-	unsigned long	ax;
-	unsigned long	ds;
-	unsigned long	es;
-	unsigned long	fs;
-	unsigned long	gs;
-	unsigned long	orig_ax;
-	unsigned long	ip;
-	unsigned long	cs;
-	unsigned long	flags;
-	unsigned long	sp;
-	unsigned long	ss;
-};
-
-/* When the kernel dumps core, it starts by dumping the user struct -
-   this will be used by gdb to figure out where the data and stack segments
-   are within the file, and what virtual addresses to use. */
-struct user{
-/* We start with the registers, to mimic the way that "memory" is returned
-   from the ptrace(3,...) function.  */
-  struct user_regs_struct regs;	/* Where the registers are actually stored */
-/* ptrace does not yet supply these.  Someday.... */
-  int u_fpvalid;		/* True if math co-processor being used. */
-				/* for this mess. Not yet used. */
-  struct user_i387_struct i387;	/* Math Co-processor registers. */
-/* The rest of this junk is to help gdb figure out what goes where */
-  unsigned long int u_tsize;	/* Text segment size (pages). */
-  unsigned long int u_dsize;	/* Data segment size (pages). */
-  unsigned long int u_ssize;	/* Stack segment size (pages). */
-  unsigned long start_code;     /* Starting virtual address of text. */
-  unsigned long start_stack;	/* Starting virtual address of stack area.
-				   This is actually the bottom of the stack,
-				   the top of the stack is always found in the
-				   esp register.  */
-  long int signal;     		/* Signal that caused the core dump. */
-  int reserved;			/* No longer used */
-  unsigned long u_ar0;		/* Used by gdb to help find the values for */
-				/* the registers. */
-  struct user_i387_struct *u_fpstate;	/* Math Co-processor pointer. */
-  unsigned long magic;		/* To uniquely identify a core file */
-  char u_comm[32];		/* User command that was responsible */
-  int u_debugreg[8];
-};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
-
-#endif /* ASM_X86__USER_32_H */
diff --git a/include/asm-x86/user_64.h b/include/asm-x86/user_64.h
deleted file mode 100644
index 38b5799863b4..000000000000
--- a/include/asm-x86/user_64.h
+++ /dev/null
@@ -1,137 +0,0 @@
-#ifndef ASM_X86__USER_64_H
-#define ASM_X86__USER_64_H
-
-#include <asm/types.h>
-#include <asm/page.h>
-/* Core file format: The core file is written in such a way that gdb
-   can understand it and provide useful information to the user.
-   There are quite a number of obstacles to being able to view the
-   contents of the floating point registers, and until these are
-   solved you will not be able to view the contents of them.
-   Actually, you can read in the core file and look at the contents of
-   the user struct to find out what the floating point registers
-   contain.
-
-   The actual file contents are as follows:
-   UPAGE: 1 page consisting of a user struct that tells gdb what is present
-   in the file.  Directly after this is a copy of the task_struct, which
-   is currently not used by gdb, but it may come in useful at some point.
-   All of the registers are stored as part of the upage.  The upage should
-   always be only one page.
-   DATA: The data area is stored.  We use current->end_text to
-   current->brk to pick up all of the user variables, plus any memory
-   that may have been malloced.  No attempt is made to determine if a page
-   is demand-zero or if a page is totally unused, we just cover the entire
-   range.  All of the addresses are rounded in such a way that an integral
-   number of pages is written.
-   STACK: We need the stack information in order to get a meaningful
-   backtrace.  We need to write the data from (esp) to
-   current->start_stack, so we round each of these off in order to be able
-   to write an integer number of pages.
-   The minimum core file size is 3 pages, or 12288 bytes.  */
-
-/*
- * Pentium III FXSR, SSE support
- *	Gareth Hughes <gareth@valinux.com>, May 2000
- *
- * Provide support for the GDB 5.0+ PTRACE_{GET|SET}FPXREGS requests for
- * interacting with the FXSR-format floating point environment.  Floating
- * point data can be accessed in the regular format in the usual manner,
- * and both the standard and SIMD floating point data can be accessed via
- * the new ptrace requests.  In either case, changes to the FPU environment
- * will be reflected in the task's state as expected.
- *
- * x86-64 support by Andi Kleen.
- */
-
-/* This matches the 64bit FXSAVE format as defined by AMD. It is the same
-   as the 32bit format defined by Intel, except that the selector:offset pairs
-   for data and eip are replaced with flat 64bit pointers. */
-struct user_i387_struct {
-	unsigned short	cwd;
-	unsigned short	swd;
-	unsigned short	twd;	/* Note this is not the same as
-				   the 32bit/x87/FSAVE twd */
-	unsigned short	fop;
-	__u64	rip;
-	__u64	rdp;
-	__u32	mxcsr;
-	__u32	mxcsr_mask;
-	__u32	st_space[32];	/* 8*16 bytes for each FP-reg = 128 bytes */
-	__u32	xmm_space[64];	/* 16*16 bytes for each XMM-reg = 256 bytes */
-	__u32	padding[24];
-};
-
-/*
- * Segment register layout in coredumps.
- */
-struct user_regs_struct {
-	unsigned long	r15;
-	unsigned long	r14;
-	unsigned long	r13;
-	unsigned long	r12;
-	unsigned long	bp;
-	unsigned long	bx;
-	unsigned long	r11;
-	unsigned long	r10;
-	unsigned long	r9;
-	unsigned long	r8;
-	unsigned long	ax;
-	unsigned long	cx;
-	unsigned long	dx;
-	unsigned long	si;
-	unsigned long	di;
-	unsigned long	orig_ax;
-	unsigned long	ip;
-	unsigned long	cs;
-	unsigned long	flags;
-	unsigned long	sp;
-	unsigned long	ss;
-	unsigned long	fs_base;
-	unsigned long	gs_base;
-	unsigned long	ds;
-	unsigned long	es;
-	unsigned long	fs;
-	unsigned long	gs;
-};
-
-/* When the kernel dumps core, it starts by dumping the user struct -
-   this will be used by gdb to figure out where the data and stack segments
-   are within the file, and what virtual addresses to use. */
-
-struct user {
-/* We start with the registers, to mimic the way that "memory" is returned
-   from the ptrace(3,...) function.  */
-  struct user_regs_struct regs;	/* Where the registers are actually stored */
-/* ptrace does not yet supply these.  Someday.... */
-  int u_fpvalid;		/* True if math co-processor being used. */
-				/* for this mess. Not yet used. */
-  int pad0;
-  struct user_i387_struct i387;	/* Math Co-processor registers. */
-/* The rest of this junk is to help gdb figure out what goes where */
-  unsigned long int u_tsize;	/* Text segment size (pages). */
-  unsigned long int u_dsize;	/* Data segment size (pages). */
-  unsigned long int u_ssize;	/* Stack segment size (pages). */
-  unsigned long start_code;     /* Starting virtual address of text. */
-  unsigned long start_stack;	/* Starting virtual address of stack area.
-				   This is actually the bottom of the stack,
-				   the top of the stack is always found in the
-				   esp register.  */
-  long int signal;		/* Signal that caused the core dump. */
-  int reserved;			/* No longer used */
-  int pad1;
-  unsigned long u_ar0;		/* Used by gdb to help find the values for */
-				/* the registers. */
-  struct user_i387_struct *u_fpstate;	/* Math Co-processor pointer. */
-  unsigned long magic;		/* To uniquely identify a core file */
-  char u_comm[32];		/* User command that was responsible */
-  unsigned long u_debugreg[8];
-  unsigned long error_code; /* CPU error code or 0 */
-  unsigned long fault_address; /* CR3 or 0 */
-};
-#define NBPG PAGE_SIZE
-#define UPAGES 1
-#define HOST_TEXT_START_ADDR (u.start_code)
-#define HOST_STACK_END_ADDR (u.start_stack + u.u_ssize * NBPG)
-
-#endif /* ASM_X86__USER_64_H */
diff --git a/include/asm-x86/uv/bios.h b/include/asm-x86/uv/bios.h
deleted file mode 100644
index 215f1969c266..000000000000
--- a/include/asm-x86/uv/bios.h
+++ /dev/null
@@ -1,94 +0,0 @@
-#ifndef ASM_X86__UV__BIOS_H
-#define ASM_X86__UV__BIOS_H
-
-/*
- * UV BIOS layer definitions.
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; if not, write to the Free Software
- *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
- *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
- *  Copyright (c) Russ Anderson
- */
-
-#include <linux/rtc.h>
-
-/*
- * Values for the BIOS calls.  It is passed as the first * argument in the
- * BIOS call.  Passing any other value in the first argument will result
- * in a BIOS_STATUS_UNIMPLEMENTED return status.
- */
-enum uv_bios_cmd {
-	UV_BIOS_COMMON,
-	UV_BIOS_GET_SN_INFO,
-	UV_BIOS_FREQ_BASE
-};
-
-/*
- * Status values returned from a BIOS call.
- */
-enum {
-	BIOS_STATUS_SUCCESS		=  0,
-	BIOS_STATUS_UNIMPLEMENTED	= -ENOSYS,
-	BIOS_STATUS_EINVAL		= -EINVAL,
-	BIOS_STATUS_UNAVAIL		= -EBUSY
-};
-
-/*
- * The UV system table describes specific firmware
- * capabilities available to the Linux kernel at runtime.
- */
-struct uv_systab {
-	char signature[4];	/* must be "UVST" */
-	u32 revision;		/* distinguish different firmware revs */
-	u64 function;		/* BIOS runtime callback function ptr */
-};
-
-enum {
-	BIOS_FREQ_BASE_PLATFORM = 0,
-	BIOS_FREQ_BASE_INTERVAL_TIMER = 1,
-	BIOS_FREQ_BASE_REALTIME_CLOCK = 2
-};
-
-union partition_info_u {
-	u64	val;
-	struct {
-		u64	hub_version	:  8,
-			partition_id	: 16,
-			coherence_id	: 16,
-			region_size	: 24;
-	};
-};
-
-/*
- * bios calls have 6 parameters
- */
-extern s64 uv_bios_call(enum uv_bios_cmd, u64, u64, u64, u64, u64);
-extern s64 uv_bios_call_irqsave(enum uv_bios_cmd, u64, u64, u64, u64, u64);
-extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64);
-
-extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *);
-extern s64 uv_bios_freq_base(u64, u64 *);
-
-extern void uv_bios_init(void);
-
-extern int uv_type;
-extern long sn_partition_id;
-extern long uv_coherency_id;
-extern long uv_region_size;
-#define partition_coherence_id()	(uv_coherency_id)
-
-extern struct kobject *sgi_uv_kobj;	/* /sys/firmware/sgi_uv */
-
-#endif /* ASM_X86__UV__BIOS_H */
diff --git a/include/asm-x86/uv/uv_bau.h b/include/asm-x86/uv/uv_bau.h
deleted file mode 100644
index 77153fb18f5e..000000000000
--- a/include/asm-x86/uv/uv_bau.h
+++ /dev/null
@@ -1,332 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * SGI UV Broadcast Assist Unit definitions
- *
- * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
- */
-
-#ifndef ASM_X86__UV__UV_BAU_H
-#define ASM_X86__UV__UV_BAU_H
-
-#include <linux/bitmap.h>
-#define BITSPERBYTE 8
-
-/*
- * Broadcast Assist Unit messaging structures
- *
- * Selective Broadcast activations are induced by software action
- * specifying a particular 8-descriptor "set" via a 6-bit index written
- * to an MMR.
- * Thus there are 64 unique 512-byte sets of SB descriptors - one set for
- * each 6-bit index value. These descriptor sets are mapped in sequence
- * starting with set 0 located at the address specified in the
- * BAU_SB_DESCRIPTOR_BASE register, set 1 is located at BASE + 512,
- * set 2 is at BASE + 2*512, set 3 at BASE + 3*512, and so on.
- *
- * We will use 31 sets, one for sending BAU messages from each of the 32
- * cpu's on the node.
- *
- * TLB shootdown will use the first of the 8 descriptors of each set.
- * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set).
- */
-
-#define UV_ITEMS_PER_DESCRIPTOR		8
-#define UV_CPUS_PER_ACT_STATUS		32
-#define UV_ACT_STATUS_MASK		0x3
-#define UV_ACT_STATUS_SIZE		2
-#define UV_ACTIVATION_DESCRIPTOR_SIZE	32
-#define UV_DISTRIBUTION_SIZE		256
-#define UV_SW_ACK_NPENDING		8
-#define UV_NET_ENDPOINT_INTD		0x38
-#define UV_DESC_BASE_PNODE_SHIFT	49
-#define UV_PAYLOADQ_PNODE_SHIFT		49
-#define UV_PTC_BASENAME			"sgi_uv/ptc_statistics"
-#define uv_physnodeaddr(x)		((__pa((unsigned long)(x)) & uv_mmask))
-
-/*
- * bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1
- */
-#define DESC_STATUS_IDLE		0
-#define DESC_STATUS_ACTIVE		1
-#define DESC_STATUS_DESTINATION_TIMEOUT	2
-#define DESC_STATUS_SOURCE_TIMEOUT	3
-
-/*
- * source side threshholds at which message retries print a warning
- */
-#define SOURCE_TIMEOUT_LIMIT		20
-#define DESTINATION_TIMEOUT_LIMIT	20
-
-/*
- * number of entries in the destination side payload queue
- */
-#define DEST_Q_SIZE			17
-/*
- * number of destination side software ack resources
- */
-#define DEST_NUM_RESOURCES		8
-#define MAX_CPUS_PER_NODE		32
-/*
- * completion statuses for sending a TLB flush message
- */
-#define	FLUSH_RETRY			1
-#define	FLUSH_GIVEUP			2
-#define	FLUSH_COMPLETE			3
-
-/*
- * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor)
- * If the 'multilevel' flag in the header portion of the descriptor
- * has been set to 0, then endpoint multi-unicast mode is selected.
- * The distribution specification (32 bytes) is interpreted as a 256-bit
- * distribution vector. Adjacent bits correspond to consecutive even numbered
- * nodeIDs. The result of adding the index of a given bit to the 15-bit
- * 'base_dest_nodeid' field of the header corresponds to the
- * destination nodeID associated with that specified bit.
- */
-struct bau_target_nodemask {
-	unsigned long bits[BITS_TO_LONGS(256)];
-};
-
-/*
- * mask of cpu's on a node
- * (during initialization we need to check that unsigned long has
- *  enough bits for max. cpu's per node)
- */
-struct bau_local_cpumask {
-	unsigned long bits;
-};
-
-/*
- * Payload: 16 bytes (128 bits) (bytes 0x20-0x2f of descriptor)
- * only 12 bytes (96 bits) of the payload area are usable.
- * An additional 3 bytes (bits 27:4) of the header address are carried
- * to the next bytes of the destination payload queue.
- * And an additional 2 bytes of the header Suppl_A field are also
- * carried to the destination payload queue.
- * But the first byte of the Suppl_A becomes bits 127:120 (the 16th byte)
- * of the destination payload queue, which is written by the hardware
- * with the s/w ack resource bit vector.
- * [ effective message contents (16 bytes (128 bits) maximum), not counting
- *   the s/w ack bit vector  ]
- */
-
-/*
- * The payload is software-defined for INTD transactions
- */
-struct bau_msg_payload {
-	unsigned long address;		/* signifies a page or all TLB's
-						of the cpu */
-	/* 64 bits */
-	unsigned short sending_cpu;	/* filled in by sender */
-	/* 16 bits */
-	unsigned short acknowledge_count;/* filled in by destination */
-	/* 16 bits */
-	unsigned int reserved1:32;	/* not usable */
-};
-
-
-/*
- * Message header:  16 bytes (128 bits) (bytes 0x30-0x3f of descriptor)
- * see table 4.2.3.0.1 in broacast_assist spec.
- */
-struct bau_msg_header {
-	int dest_subnodeid:6;	/* must be zero */
-	/* bits 5:0 */
-	int base_dest_nodeid:15; /* nasid>>1 (pnode) of first bit in node_map */
-	/* bits 20:6 */
-	int command:8;		/* message type */
-	/* bits 28:21 */
-				/* 0x38: SN3net EndPoint Message */
-	int rsvd_1:3;		/* must be zero */
-	/* bits 31:29 */
-				/* int will align on 32 bits */
-	int rsvd_2:9;		/* must be zero */
-	/* bits 40:32 */
-				/* Suppl_A is 56-41 */
-	int payload_2a:8;	/* becomes byte 16 of msg */
-	/* bits 48:41 */	/* not currently using */
-	int payload_2b:8;	/* becomes byte 17 of msg */
-	/* bits 56:49 */	/* not currently using */
-				/* Address field (96:57) is never used as an
-				   address (these are address bits 42:3) */
-	int rsvd_3:1;		/* must be zero */
-	/* bit 57 */
-				/* address bits 27:4 are payload */
-				/* these 24 bits become bytes 12-14 of msg */
-	int replied_to:1;	/* sent as 0 by the source to byte 12 */
-	/* bit 58 */
-
-	int payload_1a:5;	/* not currently used */
-	/* bits 63:59 */
-	int payload_1b:8;	/* not currently used */
-	/* bits 71:64 */
-	int payload_1c:8;	/* not currently used */
-	/* bits 79:72 */
-	int payload_1d:2;	/* not currently used */
-	/* bits 81:80 */
-
-	int rsvd_4:7;		/* must be zero */
-	/* bits 88:82 */
-	int sw_ack_flag:1;	/* software acknowledge flag */
-	/* bit 89 */
-				/* INTD trasactions at destination are to
-				   wait for software acknowledge */
-	int rsvd_5:6;		/* must be zero */
-	/* bits 95:90 */
-	int rsvd_6:5;		/* must be zero */
-	/* bits 100:96 */
-	int int_both:1;		/* if 1, interrupt both sockets on the blade */
-	/* bit 101*/
-	int fairness:3;		/* usually zero */
-	/* bits 104:102 */
-	int multilevel:1;	/* multi-level multicast format */
-	/* bit 105 */
-				/* 0 for TLB: endpoint multi-unicast messages */
-	int chaining:1;		/* next descriptor is part of this activation*/
-	/* bit 106 */
-	int rsvd_7:21;		/* must be zero */
-	/* bits 127:107 */
-};
-
-/*
- * The activation descriptor:
- * The format of the message to send, plus all accompanying control
- * Should be 64 bytes
- */
-struct bau_desc {
-	struct bau_target_nodemask distribution;
-	/*
-	 * message template, consisting of header and payload:
-	 */
-	struct bau_msg_header header;
-	struct bau_msg_payload payload;
-};
-/*
- *   -payload--    ---------header------
- *   bytes 0-11    bits 41-56  bits 58-81
- *       A           B  (2)      C (3)
- *
- *            A/B/C are moved to:
- *       A            C          B
- *   bytes 0-11  bytes 12-14  bytes 16-17  (byte 15 filled in by hw as vector)
- *   ------------payload queue-----------
- */
-
-/*
- * The payload queue on the destination side is an array of these.
- * With BAU_MISC_CONTROL set for software acknowledge mode, the messages
- * are 32 bytes (2 micropackets) (256 bits) in length, but contain only 17
- * bytes of usable data, including the sw ack vector in byte 15 (bits 127:120)
- * (12 bytes come from bau_msg_payload, 3 from payload_1, 2 from
- *  sw_ack_vector and payload_2)
- * "Enabling Software Acknowledgment mode (see Section 4.3.3 Software
- *  Acknowledge Processing) also selects 32 byte (17 bytes usable) payload
- *  operation."
- */
-struct bau_payload_queue_entry {
-	unsigned long address;		/* signifies a page or all TLB's
-						of the cpu */
-	/* 64 bits, bytes 0-7 */
-
-	unsigned short sending_cpu;	/* cpu that sent the message */
-	/* 16 bits, bytes 8-9 */
-
-	unsigned short acknowledge_count; /* filled in by destination */
-	/* 16 bits, bytes 10-11 */
-
-	unsigned short replied_to:1;	/* sent as 0 by the source */
-	/* 1 bit */
-	unsigned short unused1:7;       /* not currently using */
-	/* 7 bits: byte 12) */
-
-	unsigned char unused2[2];	/* not currently using */
-	/* bytes 13-14 */
-
-	unsigned char sw_ack_vector;	/* filled in by the hardware */
-	/* byte 15 (bits 127:120) */
-
-	unsigned char unused4[3];	/* not currently using bytes 17-19 */
-	/* bytes 17-19 */
-
-	int number_of_cpus;		/* filled in at destination */
-	/* 32 bits, bytes 20-23 (aligned) */
-
-	unsigned char unused5[8];       /* not using */
-	/* bytes 24-31 */
-};
-
-/*
- * one for every slot in the destination payload queue
- */
-struct bau_msg_status {
-	struct bau_local_cpumask seen_by;	/* map of cpu's */
-};
-
-/*
- * one for every slot in the destination software ack resources
- */
-struct bau_sw_ack_status {
-	struct bau_payload_queue_entry *msg;	/* associated message */
-	int watcher;				/* cpu monitoring, or -1 */
-};
-
-/*
- * one on every node and per-cpu; to locate the software tables
- */
-struct bau_control {
-	struct bau_desc *descriptor_base;
-	struct bau_payload_queue_entry *bau_msg_head;
-	struct bau_payload_queue_entry *va_queue_first;
-	struct bau_payload_queue_entry *va_queue_last;
-	struct bau_msg_status *msg_statuses;
-	int *watching; /* pointer to array */
-};
-
-/*
- * This structure is allocated per_cpu for UV TLB shootdown statistics.
- */
-struct ptc_stats {
-	unsigned long ptc_i;	/* number of IPI-style flushes */
-	unsigned long requestor;	/* number of nodes this cpu sent to */
-	unsigned long requestee;	/* times cpu was remotely requested */
-	unsigned long alltlb;	/* times all tlb's on this cpu were flushed */
-	unsigned long onetlb;	/* times just one tlb on this cpu was flushed */
-	unsigned long s_retry;	/* retries on source side timeouts */
-	unsigned long d_retry;	/* retries on destination side timeouts */
-	unsigned long sflush;	/* cycles spent in uv_flush_tlb_others */
-	unsigned long dflush;	/* cycles spent on destination side */
-	unsigned long retriesok; /* successes on retries */
-	unsigned long nomsg;	/* interrupts with no message */
-	unsigned long multmsg;	/* interrupts with multiple messages */
-	unsigned long ntargeted;/* nodes targeted */
-};
-
-static inline int bau_node_isset(int node, struct bau_target_nodemask *dstp)
-{
-	return constant_test_bit(node, &dstp->bits[0]);
-}
-static inline void bau_node_set(int node, struct bau_target_nodemask *dstp)
-{
-	__set_bit(node, &dstp->bits[0]);
-}
-static inline void bau_nodes_clear(struct bau_target_nodemask *dstp, int nbits)
-{
-	bitmap_zero(&dstp->bits[0], nbits);
-}
-
-static inline void bau_cpubits_clear(struct bau_local_cpumask *dstp, int nbits)
-{
-	bitmap_zero(&dstp->bits, nbits);
-}
-
-#define cpubit_isset(cpu, bau_local_cpumask) \
-	test_bit((cpu), (bau_local_cpumask).bits)
-
-extern int uv_flush_tlb_others(cpumask_t *, struct mm_struct *, unsigned long);
-extern void uv_bau_message_intr1(void);
-extern void uv_bau_timeout_intr1(void);
-
-#endif /* ASM_X86__UV__UV_BAU_H */
diff --git a/include/asm-x86/uv/uv_hub.h b/include/asm-x86/uv/uv_hub.h
deleted file mode 100644
index bdb5b01afbf5..000000000000
--- a/include/asm-x86/uv/uv_hub.h
+++ /dev/null
@@ -1,354 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * SGI UV architectural definitions
- *
- * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
- */
-
-#ifndef ASM_X86__UV__UV_HUB_H
-#define ASM_X86__UV__UV_HUB_H
-
-#include <linux/numa.h>
-#include <linux/percpu.h>
-#include <asm/types.h>
-#include <asm/percpu.h>
-
-
-/*
- * Addressing Terminology
- *
- *	M       - The low M bits of a physical address represent the offset
- *		  into the blade local memory. RAM memory on a blade is physically
- *		  contiguous (although various IO spaces may punch holes in
- *		  it)..
- *
- * 	N	- Number of bits in the node portion of a socket physical
- * 		  address.
- *
- * 	NASID   - network ID of a router, Mbrick or Cbrick. Nasid values of
- * 	 	  routers always have low bit of 1, C/MBricks have low bit
- * 		  equal to 0. Most addressing macros that target UV hub chips
- * 		  right shift the NASID by 1 to exclude the always-zero bit.
- * 		  NASIDs contain up to 15 bits.
- *
- *	GNODE   - NASID right shifted by 1 bit. Most mmrs contain gnodes instead
- *		  of nasids.
- *
- * 	PNODE   - the low N bits of the GNODE. The PNODE is the most useful variant
- * 		  of the nasid for socket usage.
- *
- *
- *  NumaLink Global Physical Address Format:
- *  +--------------------------------+---------------------+
- *  |00..000|      GNODE             |      NodeOffset     |
- *  +--------------------------------+---------------------+
- *          |<-------53 - M bits --->|<--------M bits ----->
- *
- *	M - number of node offset bits (35 .. 40)
- *
- *
- *  Memory/UV-HUB Processor Socket Address Format:
- *  +----------------+---------------+---------------------+
- *  |00..000000000000|   PNODE       |      NodeOffset     |
- *  +----------------+---------------+---------------------+
- *                   <--- N bits --->|<--------M bits ----->
- *
- *	M - number of node offset bits (35 .. 40)
- *	N - number of PNODE bits (0 .. 10)
- *
- *		Note: M + N cannot currently exceed 44 (x86_64) or 46 (IA64).
- *		The actual values are configuration dependent and are set at
- *		boot time. M & N values are set by the hardware/BIOS at boot.
- *
- *
- * APICID format
- * 	NOTE!!!!!! This is the current format of the APICID. However, code
- * 	should assume that this will change in the future. Use functions
- * 	in this file for all APICID bit manipulations and conversion.
- *
- * 		1111110000000000
- * 		5432109876543210
- *		pppppppppplc0cch
- *		sssssssssss
- *
- *			p  = pnode bits
- *			l =  socket number on board
- *			c  = core
- *			h  = hyperthread
- *			s  = bits that are in the SOCKET_ID CSR
- *
- *	Note: Processor only supports 12 bits in the APICID register. The ACPI
- *	      tables hold all 16 bits. Software needs to be aware of this.
- *
- * 	      Unless otherwise specified, all references to APICID refer to
- * 	      the FULL value contained in ACPI tables, not the subset in the
- * 	      processor APICID register.
- */
-
-
-/*
- * Maximum number of bricks in all partitions and in all coherency domains.
- * This is the total number of bricks accessible in the numalink fabric. It
- * includes all C & M bricks. Routers are NOT included.
- *
- * This value is also the value of the maximum number of non-router NASIDs
- * in the numalink fabric.
- *
- * NOTE: a brick may contain 1 or 2 OS nodes. Don't get these confused.
- */
-#define UV_MAX_NUMALINK_BLADES	16384
-
-/*
- * Maximum number of C/Mbricks within a software SSI (hardware may support
- * more).
- */
-#define UV_MAX_SSI_BLADES	256
-
-/*
- * The largest possible NASID of a C or M brick (+ 2)
- */
-#define UV_MAX_NASID_VALUE	(UV_MAX_NUMALINK_NODES * 2)
-
-/*
- * The following defines attributes of the HUB chip. These attributes are
- * frequently referenced and are kept in the per-cpu data areas of each cpu.
- * They are kept together in a struct to minimize cache misses.
- */
-struct uv_hub_info_s {
-	unsigned long	global_mmr_base;
-	unsigned long	gpa_mask;
-	unsigned long	gnode_upper;
-	unsigned long	lowmem_remap_top;
-	unsigned long	lowmem_remap_base;
-	unsigned short	pnode;
-	unsigned short	pnode_mask;
-	unsigned short	coherency_domain_number;
-	unsigned short	numa_blade_id;
-	unsigned char	blade_processor_id;
-	unsigned char	m_val;
-	unsigned char	n_val;
-};
-DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
-#define uv_hub_info 		(&__get_cpu_var(__uv_hub_info))
-#define uv_cpu_hub_info(cpu)	(&per_cpu(__uv_hub_info, cpu))
-
-/*
- * Local & Global MMR space macros.
- * 	Note: macros are intended to be used ONLY by inline functions
- * 	in this file - not by other kernel code.
- * 		n -  NASID (full 15-bit global nasid)
- * 		g -  GNODE (full 15-bit global nasid, right shifted 1)
- * 		p -  PNODE (local part of nsids, right shifted 1)
- */
-#define UV_NASID_TO_PNODE(n)		(((n) >> 1) & uv_hub_info->pnode_mask)
-#define UV_PNODE_TO_NASID(p)		(((p) << 1) | uv_hub_info->gnode_upper)
-
-#define UV_LOCAL_MMR_BASE		0xf4000000UL
-#define UV_GLOBAL_MMR32_BASE		0xf8000000UL
-#define UV_GLOBAL_MMR64_BASE		(uv_hub_info->global_mmr_base)
-#define UV_LOCAL_MMR_SIZE		(64UL * 1024 * 1024)
-#define UV_GLOBAL_MMR32_SIZE		(64UL * 1024 * 1024)
-
-#define UV_GLOBAL_MMR32_PNODE_SHIFT	15
-#define UV_GLOBAL_MMR64_PNODE_SHIFT	26
-
-#define UV_GLOBAL_MMR32_PNODE_BITS(p)	((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
-
-#define UV_GLOBAL_MMR64_PNODE_BITS(p)					\
-	((unsigned long)(p) << UV_GLOBAL_MMR64_PNODE_SHIFT)
-
-#define UV_APIC_PNODE_SHIFT	6
-
-/*
- * Macros for converting between kernel virtual addresses, socket local physical
- * addresses, and UV global physical addresses.
- * 	Note: use the standard __pa() & __va() macros for converting
- * 	      between socket virtual and socket physical addresses.
- */
-
-/* socket phys RAM --> UV global physical address */
-static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
-{
-	if (paddr < uv_hub_info->lowmem_remap_top)
-		paddr += uv_hub_info->lowmem_remap_base;
-	return paddr | uv_hub_info->gnode_upper;
-}
-
-
-/* socket virtual --> UV global physical address */
-static inline unsigned long uv_gpa(void *v)
-{
-	return __pa(v) | uv_hub_info->gnode_upper;
-}
-
-/* socket virtual --> UV global physical address */
-static inline void *uv_vgpa(void *v)
-{
-	return (void *)uv_gpa(v);
-}
-
-/* UV global physical address --> socket virtual */
-static inline void *uv_va(unsigned long gpa)
-{
-	return __va(gpa & uv_hub_info->gpa_mask);
-}
-
-/* pnode, offset --> socket virtual */
-static inline void *uv_pnode_offset_to_vaddr(int pnode, unsigned long offset)
-{
-	return __va(((unsigned long)pnode << uv_hub_info->m_val) | offset);
-}
-
-
-/*
- * Extract a PNODE from an APICID (full apicid, not processor subset)
- */
-static inline int uv_apicid_to_pnode(int apicid)
-{
-	return (apicid >> UV_APIC_PNODE_SHIFT);
-}
-
-/*
- * Access global MMRs using the low memory MMR32 space. This region supports
- * faster MMR access but not all MMRs are accessible in this space.
- */
-static inline unsigned long *uv_global_mmr32_address(int pnode,
-				unsigned long offset)
-{
-	return __va(UV_GLOBAL_MMR32_BASE |
-		       UV_GLOBAL_MMR32_PNODE_BITS(pnode) | offset);
-}
-
-static inline void uv_write_global_mmr32(int pnode, unsigned long offset,
-				 unsigned long val)
-{
-	*uv_global_mmr32_address(pnode, offset) = val;
-}
-
-static inline unsigned long uv_read_global_mmr32(int pnode,
-						 unsigned long offset)
-{
-	return *uv_global_mmr32_address(pnode, offset);
-}
-
-/*
- * Access Global MMR space using the MMR space located at the top of physical
- * memory.
- */
-static inline unsigned long *uv_global_mmr64_address(int pnode,
-				unsigned long offset)
-{
-	return __va(UV_GLOBAL_MMR64_BASE |
-		    UV_GLOBAL_MMR64_PNODE_BITS(pnode) | offset);
-}
-
-static inline void uv_write_global_mmr64(int pnode, unsigned long offset,
-				unsigned long val)
-{
-	*uv_global_mmr64_address(pnode, offset) = val;
-}
-
-static inline unsigned long uv_read_global_mmr64(int pnode,
-						 unsigned long offset)
-{
-	return *uv_global_mmr64_address(pnode, offset);
-}
-
-/*
- * Access hub local MMRs. Faster than using global space but only local MMRs
- * are accessible.
- */
-static inline unsigned long *uv_local_mmr_address(unsigned long offset)
-{
-	return __va(UV_LOCAL_MMR_BASE | offset);
-}
-
-static inline unsigned long uv_read_local_mmr(unsigned long offset)
-{
-	return *uv_local_mmr_address(offset);
-}
-
-static inline void uv_write_local_mmr(unsigned long offset, unsigned long val)
-{
-	*uv_local_mmr_address(offset) = val;
-}
-
-/*
- * Structures and definitions for converting between cpu, node, pnode, and blade
- * numbers.
- */
-struct uv_blade_info {
-	unsigned short	nr_possible_cpus;
-	unsigned short	nr_online_cpus;
-	unsigned short	pnode;
-};
-extern struct uv_blade_info *uv_blade_info;
-extern short *uv_node_to_blade;
-extern short *uv_cpu_to_blade;
-extern short uv_possible_blades;
-
-/* Blade-local cpu number of current cpu. Numbered 0 .. <# cpus on the blade> */
-static inline int uv_blade_processor_id(void)
-{
-	return uv_hub_info->blade_processor_id;
-}
-
-/* Blade number of current cpu. Numnbered 0 .. <#blades -1> */
-static inline int uv_numa_blade_id(void)
-{
-	return uv_hub_info->numa_blade_id;
-}
-
-/* Convert a cpu number to the the UV blade number */
-static inline int uv_cpu_to_blade_id(int cpu)
-{
-	return uv_cpu_to_blade[cpu];
-}
-
-/* Convert linux node number to the UV blade number */
-static inline int uv_node_to_blade_id(int nid)
-{
-	return uv_node_to_blade[nid];
-}
-
-/* Convert a blade id to the PNODE of the blade */
-static inline int uv_blade_to_pnode(int bid)
-{
-	return uv_blade_info[bid].pnode;
-}
-
-/* Determine the number of possible cpus on a blade */
-static inline int uv_blade_nr_possible_cpus(int bid)
-{
-	return uv_blade_info[bid].nr_possible_cpus;
-}
-
-/* Determine the number of online cpus on a blade */
-static inline int uv_blade_nr_online_cpus(int bid)
-{
-	return uv_blade_info[bid].nr_online_cpus;
-}
-
-/* Convert a cpu id to the PNODE of the blade containing the cpu */
-static inline int uv_cpu_to_pnode(int cpu)
-{
-	return uv_blade_info[uv_cpu_to_blade_id(cpu)].pnode;
-}
-
-/* Convert a linux node number to the PNODE of the blade */
-static inline int uv_node_to_pnode(int nid)
-{
-	return uv_blade_info[uv_node_to_blade_id(nid)].pnode;
-}
-
-/* Maximum possible number of blades */
-static inline int uv_num_possible_blades(void)
-{
-	return uv_possible_blades;
-}
-
-#endif /* ASM_X86__UV__UV_HUB_H */
-
diff --git a/include/asm-x86/uv/uv_irq.h b/include/asm-x86/uv/uv_irq.h
deleted file mode 100644
index 8bf5f32da9c6..000000000000
--- a/include/asm-x86/uv/uv_irq.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * SGI UV IRQ definitions
- *
- * Copyright (C) 2008 Silicon Graphics, Inc. All rights reserved.
- */
-
-#ifndef ASM_X86__UV__UV_IRQ_H
-#define ASM_X86__UV__UV_IRQ_H
-
-/* If a generic version of this structure gets defined, eliminate this one. */
-struct uv_IO_APIC_route_entry {
-	__u64	vector		:  8,
-		delivery_mode	:  3,
-		dest_mode	:  1,
-		delivery_status	:  1,
-		polarity	:  1,
-		__reserved_1	:  1,
-		trigger		:  1,
-		mask		:  1,
-		__reserved_2	: 15,
-		dest		: 32;
-};
-
-extern struct irq_chip uv_irq_chip;
-
-extern int arch_enable_uv_irq(char *, unsigned int, int, int, unsigned long);
-extern void arch_disable_uv_irq(int, unsigned long);
-
-extern int uv_setup_irq(char *, int, int, unsigned long);
-extern void uv_teardown_irq(unsigned int, int, unsigned long);
-
-#endif /* ASM_X86__UV__UV_IRQ_H */
diff --git a/include/asm-x86/uv/uv_mmrs.h b/include/asm-x86/uv/uv_mmrs.h
deleted file mode 100644
index 8b03d89d2459..000000000000
--- a/include/asm-x86/uv/uv_mmrs.h
+++ /dev/null
@@ -1,1295 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * SGI UV MMR definitions
- *
- * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
- */
-
-#ifndef ASM_X86__UV__UV_MMRS_H
-#define ASM_X86__UV__UV_MMRS_H
-
-#define UV_MMR_ENABLE		(1UL << 63)
-
-/* ========================================================================= */
-/*                           UVH_BAU_DATA_CONFIG                             */
-/* ========================================================================= */
-#define UVH_BAU_DATA_CONFIG 0x61680UL
-#define UVH_BAU_DATA_CONFIG_32 0x0438
-
-#define UVH_BAU_DATA_CONFIG_VECTOR_SHFT 0
-#define UVH_BAU_DATA_CONFIG_VECTOR_MASK 0x00000000000000ffUL
-#define UVH_BAU_DATA_CONFIG_DM_SHFT 8
-#define UVH_BAU_DATA_CONFIG_DM_MASK 0x0000000000000700UL
-#define UVH_BAU_DATA_CONFIG_DESTMODE_SHFT 11
-#define UVH_BAU_DATA_CONFIG_DESTMODE_MASK 0x0000000000000800UL
-#define UVH_BAU_DATA_CONFIG_STATUS_SHFT 12
-#define UVH_BAU_DATA_CONFIG_STATUS_MASK 0x0000000000001000UL
-#define UVH_BAU_DATA_CONFIG_P_SHFT 13
-#define UVH_BAU_DATA_CONFIG_P_MASK 0x0000000000002000UL
-#define UVH_BAU_DATA_CONFIG_T_SHFT 15
-#define UVH_BAU_DATA_CONFIG_T_MASK 0x0000000000008000UL
-#define UVH_BAU_DATA_CONFIG_M_SHFT 16
-#define UVH_BAU_DATA_CONFIG_M_MASK 0x0000000000010000UL
-#define UVH_BAU_DATA_CONFIG_APIC_ID_SHFT 32
-#define UVH_BAU_DATA_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
-
-union uvh_bau_data_config_u {
-    unsigned long	v;
-    struct uvh_bau_data_config_s {
-	unsigned long	vector_  :  8;  /* RW */
-	unsigned long	dm       :  3;  /* RW */
-	unsigned long	destmode :  1;  /* RW */
-	unsigned long	status   :  1;  /* RO */
-	unsigned long	p        :  1;  /* RO */
-	unsigned long	rsvd_14  :  1;  /*    */
-	unsigned long	t        :  1;  /* RO */
-	unsigned long	m        :  1;  /* RW */
-	unsigned long	rsvd_17_31: 15;  /*    */
-	unsigned long	apic_id  : 32;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                           UVH_EVENT_OCCURRED0                             */
-/* ========================================================================= */
-#define UVH_EVENT_OCCURRED0 0x70000UL
-#define UVH_EVENT_OCCURRED0_32 0x005e8
-
-#define UVH_EVENT_OCCURRED0_LB_HCERR_SHFT 0
-#define UVH_EVENT_OCCURRED0_LB_HCERR_MASK 0x0000000000000001UL
-#define UVH_EVENT_OCCURRED0_GR0_HCERR_SHFT 1
-#define UVH_EVENT_OCCURRED0_GR0_HCERR_MASK 0x0000000000000002UL
-#define UVH_EVENT_OCCURRED0_GR1_HCERR_SHFT 2
-#define UVH_EVENT_OCCURRED0_GR1_HCERR_MASK 0x0000000000000004UL
-#define UVH_EVENT_OCCURRED0_LH_HCERR_SHFT 3
-#define UVH_EVENT_OCCURRED0_LH_HCERR_MASK 0x0000000000000008UL
-#define UVH_EVENT_OCCURRED0_RH_HCERR_SHFT 4
-#define UVH_EVENT_OCCURRED0_RH_HCERR_MASK 0x0000000000000010UL
-#define UVH_EVENT_OCCURRED0_XN_HCERR_SHFT 5
-#define UVH_EVENT_OCCURRED0_XN_HCERR_MASK 0x0000000000000020UL
-#define UVH_EVENT_OCCURRED0_SI_HCERR_SHFT 6
-#define UVH_EVENT_OCCURRED0_SI_HCERR_MASK 0x0000000000000040UL
-#define UVH_EVENT_OCCURRED0_LB_AOERR0_SHFT 7
-#define UVH_EVENT_OCCURRED0_LB_AOERR0_MASK 0x0000000000000080UL
-#define UVH_EVENT_OCCURRED0_GR0_AOERR0_SHFT 8
-#define UVH_EVENT_OCCURRED0_GR0_AOERR0_MASK 0x0000000000000100UL
-#define UVH_EVENT_OCCURRED0_GR1_AOERR0_SHFT 9
-#define UVH_EVENT_OCCURRED0_GR1_AOERR0_MASK 0x0000000000000200UL
-#define UVH_EVENT_OCCURRED0_LH_AOERR0_SHFT 10
-#define UVH_EVENT_OCCURRED0_LH_AOERR0_MASK 0x0000000000000400UL
-#define UVH_EVENT_OCCURRED0_RH_AOERR0_SHFT 11
-#define UVH_EVENT_OCCURRED0_RH_AOERR0_MASK 0x0000000000000800UL
-#define UVH_EVENT_OCCURRED0_XN_AOERR0_SHFT 12
-#define UVH_EVENT_OCCURRED0_XN_AOERR0_MASK 0x0000000000001000UL
-#define UVH_EVENT_OCCURRED0_SI_AOERR0_SHFT 13
-#define UVH_EVENT_OCCURRED0_SI_AOERR0_MASK 0x0000000000002000UL
-#define UVH_EVENT_OCCURRED0_LB_AOERR1_SHFT 14
-#define UVH_EVENT_OCCURRED0_LB_AOERR1_MASK 0x0000000000004000UL
-#define UVH_EVENT_OCCURRED0_GR0_AOERR1_SHFT 15
-#define UVH_EVENT_OCCURRED0_GR0_AOERR1_MASK 0x0000000000008000UL
-#define UVH_EVENT_OCCURRED0_GR1_AOERR1_SHFT 16
-#define UVH_EVENT_OCCURRED0_GR1_AOERR1_MASK 0x0000000000010000UL
-#define UVH_EVENT_OCCURRED0_LH_AOERR1_SHFT 17
-#define UVH_EVENT_OCCURRED0_LH_AOERR1_MASK 0x0000000000020000UL
-#define UVH_EVENT_OCCURRED0_RH_AOERR1_SHFT 18
-#define UVH_EVENT_OCCURRED0_RH_AOERR1_MASK 0x0000000000040000UL
-#define UVH_EVENT_OCCURRED0_XN_AOERR1_SHFT 19
-#define UVH_EVENT_OCCURRED0_XN_AOERR1_MASK 0x0000000000080000UL
-#define UVH_EVENT_OCCURRED0_SI_AOERR1_SHFT 20
-#define UVH_EVENT_OCCURRED0_SI_AOERR1_MASK 0x0000000000100000UL
-#define UVH_EVENT_OCCURRED0_RH_VPI_INT_SHFT 21
-#define UVH_EVENT_OCCURRED0_RH_VPI_INT_MASK 0x0000000000200000UL
-#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_SHFT 22
-#define UVH_EVENT_OCCURRED0_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_SHFT 23
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_0_MASK 0x0000000000800000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_SHFT 24
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_1_MASK 0x0000000001000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_SHFT 25
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_2_MASK 0x0000000002000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_SHFT 26
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_3_MASK 0x0000000004000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_SHFT 27
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_4_MASK 0x0000000008000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_SHFT 28
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_5_MASK 0x0000000010000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_SHFT 29
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_6_MASK 0x0000000020000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_SHFT 30
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_7_MASK 0x0000000040000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_SHFT 31
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_8_MASK 0x0000000080000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_SHFT 32
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_9_MASK 0x0000000100000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_SHFT 33
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_10_MASK 0x0000000200000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_SHFT 34
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_11_MASK 0x0000000400000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_SHFT 35
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_12_MASK 0x0000000800000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_SHFT 36
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_13_MASK 0x0000001000000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_SHFT 37
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_14_MASK 0x0000002000000000UL
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_SHFT 38
-#define UVH_EVENT_OCCURRED0_LB_IRQ_INT_15_MASK 0x0000004000000000UL
-#define UVH_EVENT_OCCURRED0_L1_NMI_INT_SHFT 39
-#define UVH_EVENT_OCCURRED0_L1_NMI_INT_MASK 0x0000008000000000UL
-#define UVH_EVENT_OCCURRED0_STOP_CLOCK_SHFT 40
-#define UVH_EVENT_OCCURRED0_STOP_CLOCK_MASK 0x0000010000000000UL
-#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_SHFT 41
-#define UVH_EVENT_OCCURRED0_ASIC_TO_L1_MASK 0x0000020000000000UL
-#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_SHFT 42
-#define UVH_EVENT_OCCURRED0_L1_TO_ASIC_MASK 0x0000040000000000UL
-#define UVH_EVENT_OCCURRED0_LTC_INT_SHFT 43
-#define UVH_EVENT_OCCURRED0_LTC_INT_MASK 0x0000080000000000UL
-#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_SHFT 44
-#define UVH_EVENT_OCCURRED0_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
-#define UVH_EVENT_OCCURRED0_IPI_INT_SHFT 45
-#define UVH_EVENT_OCCURRED0_IPI_INT_MASK 0x0000200000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT0_SHFT 46
-#define UVH_EVENT_OCCURRED0_EXTIO_INT0_MASK 0x0000400000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT1_SHFT 47
-#define UVH_EVENT_OCCURRED0_EXTIO_INT1_MASK 0x0000800000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT2_SHFT 48
-#define UVH_EVENT_OCCURRED0_EXTIO_INT2_MASK 0x0001000000000000UL
-#define UVH_EVENT_OCCURRED0_EXTIO_INT3_SHFT 49
-#define UVH_EVENT_OCCURRED0_EXTIO_INT3_MASK 0x0002000000000000UL
-#define UVH_EVENT_OCCURRED0_PROFILE_INT_SHFT 50
-#define UVH_EVENT_OCCURRED0_PROFILE_INT_MASK 0x0004000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC0_SHFT 51
-#define UVH_EVENT_OCCURRED0_RTC0_MASK 0x0008000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC1_SHFT 52
-#define UVH_EVENT_OCCURRED0_RTC1_MASK 0x0010000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC2_SHFT 53
-#define UVH_EVENT_OCCURRED0_RTC2_MASK 0x0020000000000000UL
-#define UVH_EVENT_OCCURRED0_RTC3_SHFT 54
-#define UVH_EVENT_OCCURRED0_RTC3_MASK 0x0040000000000000UL
-#define UVH_EVENT_OCCURRED0_BAU_DATA_SHFT 55
-#define UVH_EVENT_OCCURRED0_BAU_DATA_MASK 0x0080000000000000UL
-#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_SHFT 56
-#define UVH_EVENT_OCCURRED0_POWER_MANAGEMENT_REQ_MASK 0x0100000000000000UL
-union uvh_event_occurred0_u {
-    unsigned long	v;
-    struct uvh_event_occurred0_s {
-	unsigned long	lb_hcerr             :  1;  /* RW, W1C */
-	unsigned long	gr0_hcerr            :  1;  /* RW, W1C */
-	unsigned long	gr1_hcerr            :  1;  /* RW, W1C */
-	unsigned long	lh_hcerr             :  1;  /* RW, W1C */
-	unsigned long	rh_hcerr             :  1;  /* RW, W1C */
-	unsigned long	xn_hcerr             :  1;  /* RW, W1C */
-	unsigned long	si_hcerr             :  1;  /* RW, W1C */
-	unsigned long	lb_aoerr0            :  1;  /* RW, W1C */
-	unsigned long	gr0_aoerr0           :  1;  /* RW, W1C */
-	unsigned long	gr1_aoerr0           :  1;  /* RW, W1C */
-	unsigned long	lh_aoerr0            :  1;  /* RW, W1C */
-	unsigned long	rh_aoerr0            :  1;  /* RW, W1C */
-	unsigned long	xn_aoerr0            :  1;  /* RW, W1C */
-	unsigned long	si_aoerr0            :  1;  /* RW, W1C */
-	unsigned long	lb_aoerr1            :  1;  /* RW, W1C */
-	unsigned long	gr0_aoerr1           :  1;  /* RW, W1C */
-	unsigned long	gr1_aoerr1           :  1;  /* RW, W1C */
-	unsigned long	lh_aoerr1            :  1;  /* RW, W1C */
-	unsigned long	rh_aoerr1            :  1;  /* RW, W1C */
-	unsigned long	xn_aoerr1            :  1;  /* RW, W1C */
-	unsigned long	si_aoerr1            :  1;  /* RW, W1C */
-	unsigned long	rh_vpi_int           :  1;  /* RW, W1C */
-	unsigned long	system_shutdown_int  :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_0         :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_1         :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_2         :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_3         :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_4         :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_5         :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_6         :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_7         :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_8         :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_9         :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_10        :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_11        :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_12        :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_13        :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_14        :  1;  /* RW, W1C */
-	unsigned long	lb_irq_int_15        :  1;  /* RW, W1C */
-	unsigned long	l1_nmi_int           :  1;  /* RW, W1C */
-	unsigned long	stop_clock           :  1;  /* RW, W1C */
-	unsigned long	asic_to_l1           :  1;  /* RW, W1C */
-	unsigned long	l1_to_asic           :  1;  /* RW, W1C */
-	unsigned long	ltc_int              :  1;  /* RW, W1C */
-	unsigned long	la_seq_trigger       :  1;  /* RW, W1C */
-	unsigned long	ipi_int              :  1;  /* RW, W1C */
-	unsigned long	extio_int0           :  1;  /* RW, W1C */
-	unsigned long	extio_int1           :  1;  /* RW, W1C */
-	unsigned long	extio_int2           :  1;  /* RW, W1C */
-	unsigned long	extio_int3           :  1;  /* RW, W1C */
-	unsigned long	profile_int          :  1;  /* RW, W1C */
-	unsigned long	rtc0                 :  1;  /* RW, W1C */
-	unsigned long	rtc1                 :  1;  /* RW, W1C */
-	unsigned long	rtc2                 :  1;  /* RW, W1C */
-	unsigned long	rtc3                 :  1;  /* RW, W1C */
-	unsigned long	bau_data             :  1;  /* RW, W1C */
-	unsigned long	power_management_req :  1;  /* RW, W1C */
-	unsigned long	rsvd_57_63           :  7;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                        UVH_EVENT_OCCURRED0_ALIAS                          */
-/* ========================================================================= */
-#define UVH_EVENT_OCCURRED0_ALIAS 0x0000000000070008UL
-#define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0
-
-/* ========================================================================= */
-/*                               UVH_INT_CMPB                                */
-/* ========================================================================= */
-#define UVH_INT_CMPB 0x22080UL
-
-#define UVH_INT_CMPB_REAL_TIME_CMPB_SHFT 0
-#define UVH_INT_CMPB_REAL_TIME_CMPB_MASK 0x00ffffffffffffffUL
-
-union uvh_int_cmpb_u {
-    unsigned long	v;
-    struct uvh_int_cmpb_s {
-	unsigned long	real_time_cmpb : 56;  /* RW */
-	unsigned long	rsvd_56_63     :  8;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                               UVH_INT_CMPC                                */
-/* ========================================================================= */
-#define UVH_INT_CMPC 0x22100UL
-
-#define UVH_INT_CMPC_REAL_TIME_CMPC_SHFT 0
-#define UVH_INT_CMPC_REAL_TIME_CMPC_MASK 0x00ffffffffffffffUL
-
-union uvh_int_cmpc_u {
-    unsigned long	v;
-    struct uvh_int_cmpc_s {
-	unsigned long	real_time_cmpc : 56;  /* RW */
-	unsigned long	rsvd_56_63     :  8;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                               UVH_INT_CMPD                                */
-/* ========================================================================= */
-#define UVH_INT_CMPD 0x22180UL
-
-#define UVH_INT_CMPD_REAL_TIME_CMPD_SHFT 0
-#define UVH_INT_CMPD_REAL_TIME_CMPD_MASK 0x00ffffffffffffffUL
-
-union uvh_int_cmpd_u {
-    unsigned long	v;
-    struct uvh_int_cmpd_s {
-	unsigned long	real_time_cmpd : 56;  /* RW */
-	unsigned long	rsvd_56_63     :  8;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                               UVH_IPI_INT                                 */
-/* ========================================================================= */
-#define UVH_IPI_INT 0x60500UL
-#define UVH_IPI_INT_32 0x0348
-
-#define UVH_IPI_INT_VECTOR_SHFT 0
-#define UVH_IPI_INT_VECTOR_MASK 0x00000000000000ffUL
-#define UVH_IPI_INT_DELIVERY_MODE_SHFT 8
-#define UVH_IPI_INT_DELIVERY_MODE_MASK 0x0000000000000700UL
-#define UVH_IPI_INT_DESTMODE_SHFT 11
-#define UVH_IPI_INT_DESTMODE_MASK 0x0000000000000800UL
-#define UVH_IPI_INT_APIC_ID_SHFT 16
-#define UVH_IPI_INT_APIC_ID_MASK 0x0000ffffffff0000UL
-#define UVH_IPI_INT_SEND_SHFT 63
-#define UVH_IPI_INT_SEND_MASK 0x8000000000000000UL
-
-union uvh_ipi_int_u {
-    unsigned long	v;
-    struct uvh_ipi_int_s {
-	unsigned long	vector_       :  8;  /* RW */
-	unsigned long	delivery_mode :  3;  /* RW */
-	unsigned long	destmode      :  1;  /* RW */
-	unsigned long	rsvd_12_15    :  4;  /*    */
-	unsigned long	apic_id       : 32;  /* RW */
-	unsigned long	rsvd_48_62    : 15;  /*    */
-	unsigned long	send          :  1;  /* WP */
-    } s;
-};
-
-/* ========================================================================= */
-/*                   UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST                     */
-/* ========================================================================= */
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST 0x320050UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_32 0x009c0
-
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_SHFT 4
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_ADDRESS_MASK 0x000007fffffffff0UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_SHFT 49
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_FIRST_NODE_ID_MASK 0x7ffe000000000000UL
-
-union uvh_lb_bau_intd_payload_queue_first_u {
-    unsigned long	v;
-    struct uvh_lb_bau_intd_payload_queue_first_s {
-	unsigned long	rsvd_0_3:  4;  /*    */
-	unsigned long	address : 39;  /* RW */
-	unsigned long	rsvd_43_48:  6;  /*    */
-	unsigned long	node_id : 14;  /* RW */
-	unsigned long	rsvd_63 :  1;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST                     */
-/* ========================================================================= */
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST 0x320060UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_32 0x009c8
-
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_SHFT 4
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_LAST_ADDRESS_MASK 0x000007fffffffff0UL
-
-union uvh_lb_bau_intd_payload_queue_last_u {
-    unsigned long	v;
-    struct uvh_lb_bau_intd_payload_queue_last_s {
-	unsigned long	rsvd_0_3:  4;  /*    */
-	unsigned long	address : 39;  /* RW */
-	unsigned long	rsvd_43_63: 21;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                    UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL                     */
-/* ========================================================================= */
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL 0x320070UL
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_32 0x009d0
-
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_SHFT 4
-#define UVH_LB_BAU_INTD_PAYLOAD_QUEUE_TAIL_ADDRESS_MASK 0x000007fffffffff0UL
-
-union uvh_lb_bau_intd_payload_queue_tail_u {
-    unsigned long	v;
-    struct uvh_lb_bau_intd_payload_queue_tail_s {
-	unsigned long	rsvd_0_3:  4;  /*    */
-	unsigned long	address : 39;  /* RW */
-	unsigned long	rsvd_43_63: 21;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                   UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE                    */
-/* ========================================================================= */
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE 0x320080UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_32 0x0a68
-
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_SHFT 0
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_0_MASK 0x0000000000000001UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_SHFT 1
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_1_MASK 0x0000000000000002UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_SHFT 2
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_2_MASK 0x0000000000000004UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_SHFT 3
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_3_MASK 0x0000000000000008UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_SHFT 4
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_4_MASK 0x0000000000000010UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_SHFT 5
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_5_MASK 0x0000000000000020UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_SHFT 6
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_6_MASK 0x0000000000000040UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_SHFT 7
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_PENDING_7_MASK 0x0000000000000080UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_SHFT 8
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_0_MASK 0x0000000000000100UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_SHFT 9
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_1_MASK 0x0000000000000200UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_SHFT 10
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_2_MASK 0x0000000000000400UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_SHFT 11
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_3_MASK 0x0000000000000800UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_SHFT 12
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_4_MASK 0x0000000000001000UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_SHFT 13
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_5_MASK 0x0000000000002000UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_SHFT 14
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_6_MASK 0x0000000000004000UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_SHFT 15
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_TIMEOUT_7_MASK 0x0000000000008000UL
-union uvh_lb_bau_intd_software_acknowledge_u {
-    unsigned long	v;
-    struct uvh_lb_bau_intd_software_acknowledge_s {
-	unsigned long	pending_0 :  1;  /* RW, W1C */
-	unsigned long	pending_1 :  1;  /* RW, W1C */
-	unsigned long	pending_2 :  1;  /* RW, W1C */
-	unsigned long	pending_3 :  1;  /* RW, W1C */
-	unsigned long	pending_4 :  1;  /* RW, W1C */
-	unsigned long	pending_5 :  1;  /* RW, W1C */
-	unsigned long	pending_6 :  1;  /* RW, W1C */
-	unsigned long	pending_7 :  1;  /* RW, W1C */
-	unsigned long	timeout_0 :  1;  /* RW, W1C */
-	unsigned long	timeout_1 :  1;  /* RW, W1C */
-	unsigned long	timeout_2 :  1;  /* RW, W1C */
-	unsigned long	timeout_3 :  1;  /* RW, W1C */
-	unsigned long	timeout_4 :  1;  /* RW, W1C */
-	unsigned long	timeout_5 :  1;  /* RW, W1C */
-	unsigned long	timeout_6 :  1;  /* RW, W1C */
-	unsigned long	timeout_7 :  1;  /* RW, W1C */
-	unsigned long	rsvd_16_63: 48;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS                 */
-/* ========================================================================= */
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS 0x0000000000320088UL
-#define UVH_LB_BAU_INTD_SOFTWARE_ACKNOWLEDGE_ALIAS_32 0x0a70
-
-/* ========================================================================= */
-/*                     UVH_LB_BAU_SB_ACTIVATION_CONTROL                      */
-/* ========================================================================= */
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL 0x320020UL
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_32 0x009a8
-
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_SHFT 0
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INDEX_MASK 0x000000000000003fUL
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_SHFT 62
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_PUSH_MASK 0x4000000000000000UL
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INIT_SHFT 63
-#define UVH_LB_BAU_SB_ACTIVATION_CONTROL_INIT_MASK 0x8000000000000000UL
-
-union uvh_lb_bau_sb_activation_control_u {
-    unsigned long	v;
-    struct uvh_lb_bau_sb_activation_control_s {
-	unsigned long	index :  6;  /* RW */
-	unsigned long	rsvd_6_61: 56;  /*    */
-	unsigned long	push  :  1;  /* WP */
-	unsigned long	init  :  1;  /* WP */
-    } s;
-};
-
-/* ========================================================================= */
-/*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_0                      */
-/* ========================================================================= */
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0 0x320030UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_32 0x009b0
-
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_SHFT 0
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_0_STATUS_MASK 0xffffffffffffffffUL
-
-union uvh_lb_bau_sb_activation_status_0_u {
-    unsigned long	v;
-    struct uvh_lb_bau_sb_activation_status_0_s {
-	unsigned long	status : 64;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                    UVH_LB_BAU_SB_ACTIVATION_STATUS_1                      */
-/* ========================================================================= */
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1 0x320040UL
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_32 0x009b8
-
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_SHFT 0
-#define UVH_LB_BAU_SB_ACTIVATION_STATUS_1_STATUS_MASK 0xffffffffffffffffUL
-
-union uvh_lb_bau_sb_activation_status_1_u {
-    unsigned long	v;
-    struct uvh_lb_bau_sb_activation_status_1_s {
-	unsigned long	status : 64;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                      UVH_LB_BAU_SB_DESCRIPTOR_BASE                        */
-/* ========================================================================= */
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE 0x320010UL
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_32 0x009a0
-
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_SHFT 12
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_PAGE_ADDRESS_MASK 0x000007fffffff000UL
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT 49
-#define UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_MASK 0x7ffe000000000000UL
-
-union uvh_lb_bau_sb_descriptor_base_u {
-    unsigned long	v;
-    struct uvh_lb_bau_sb_descriptor_base_s {
-	unsigned long	rsvd_0_11    : 12;  /*    */
-	unsigned long	page_address : 31;  /* RW */
-	unsigned long	rsvd_43_48   :  6;  /*    */
-	unsigned long	node_id      : 14;  /* RW */
-	unsigned long	rsvd_63      :  1;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                      UVH_LB_MCAST_AOERR0_RPT_ENABLE                       */
-/* ========================================================================= */
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE 0x50b20UL
-
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_SHFT 0
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_OBESE_MSG_MASK 0x0000000000000001UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_SHFT 1
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_DATA_SB_ERR_MASK 0x0000000000000002UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_SHFT 2
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_NACK_BUFF_PARITY_MASK 0x0000000000000004UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_SHFT 3
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_TIMEOUT_MASK 0x0000000000000008UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_SHFT 4
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_INACTIVE_REPLY_MASK 0x0000000000000010UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_SHFT 5
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_UPGRADE_ERROR_MASK 0x0000000000000020UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_SHFT 6
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REG_COUNT_UNDERFLOW_MASK 0x0000000000000040UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_SHFT 7
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MCAST_REP_OBESE_MSG_MASK 0x0000000000000080UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_SHFT 8
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_RUNT_MSG_MASK 0x0000000000000100UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_SHFT 9
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_OBESE_MSG_MASK 0x0000000000000200UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_SHFT 10
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REQ_DATA_SB_ERR_MASK 0x0000000000000400UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_SHFT 11
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_RUNT_MSG_MASK 0x0000000000000800UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_SHFT 12
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_OBESE_MSG_MASK 0x0000000000001000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_SHFT 13
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_DATA_SB_ERR_MASK 0x0000000000002000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_SHFT 14
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_REP_COMMAND_ERR_MASK 0x0000000000004000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_SHFT 15
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_UCACHE_PEND_TIMEOUT_MASK 0x0000000000008000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_SHFT 16
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_RUNT_MSG_MASK 0x0000000000010000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_SHFT 17
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_OBESE_MSG_MASK 0x0000000000020000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_SHFT 18
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REQ_DATA_SB_ERR_MASK 0x0000000000040000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_SHFT 19
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_RUNT_MSG_MASK 0x0000000000080000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_SHFT 20
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_OBESE_MSG_MASK 0x0000000000100000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_SHFT 21
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_REP_DATA_SB_ERR_MASK 0x0000000000200000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_SHFT 22
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_AMO_TIMEOUT_MASK 0x0000000000400000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_SHFT 23
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_PUT_TIMEOUT_MASK 0x0000000000800000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_SHFT 24
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_MACC_SPURIOUS_EVENT_MASK 0x0000000001000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_SHFT 25
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IOH_DESTINATION_TABLE_PARITY_MASK 0x0000000002000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_SHFT 26
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_HAD_ERROR_REPLY_MASK 0x0000000004000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_SHFT 27
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_GET_TIMEOUT_MASK 0x0000000008000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_SHFT 28
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_LOCK_MANAGER_HAD_ERROR_REPLY_MASK 0x0000000010000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_SHFT 29
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_HAD_ERROR_REPLY_MASK 0x0000000020000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_SHFT 30
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_PUT_TIMEOUT_MASK 0x0000000040000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_SHFT 31
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SB_ACTIVATION_OVERRUN_MASK 0x0000000080000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_SHFT 32
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_HAD_ERROR_REPLY_MASK 0x0000000100000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_SHFT 33
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_COMPLETED_GB_ACTIVATION_TIMEOUT_MASK 0x0000000200000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_SHFT 34
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_0_PARITY_MASK 0x0000000400000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_SHFT 35
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_DESCRIPTOR_BUFFER_1_PARITY_MASK 0x0000000800000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_SHFT 36
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_SOCKET_DESTINATION_TABLE_PARITY_MASK 0x0000001000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_SHFT 37
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_BAU_REPLY_PAYLOAD_CORRUPTION_MASK 0x0000002000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_SHFT 38
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_IO_PORT_DESTINATION_TABLE_PARITY_MASK 0x0000004000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_SHFT 39
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INTD_SOFT_ACK_TIMEOUT_MASK 0x0000008000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_SHFT 40
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_OBESE_MSG_MASK 0x0000010000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_SHFT 41
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_REP_COMMAND_ERR_MASK 0x0000020000000000UL
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_SHFT 42
-#define UVH_LB_MCAST_AOERR0_RPT_ENABLE_INT_TIMEOUT_MASK 0x0000040000000000UL
-
-union uvh_lb_mcast_aoerr0_rpt_enable_u {
-    unsigned long	v;
-    struct uvh_lb_mcast_aoerr0_rpt_enable_s {
-	unsigned long	mcast_obese_msg                         :  1;  /* RW */
-	unsigned long	mcast_data_sb_err                       :  1;  /* RW */
-	unsigned long	mcast_nack_buff_parity                  :  1;  /* RW */
-	unsigned long	mcast_timeout                           :  1;  /* RW */
-	unsigned long	mcast_inactive_reply                    :  1;  /* RW */
-	unsigned long	mcast_upgrade_error                     :  1;  /* RW */
-	unsigned long	mcast_reg_count_underflow               :  1;  /* RW */
-	unsigned long	mcast_rep_obese_msg                     :  1;  /* RW */
-	unsigned long	ucache_req_runt_msg                     :  1;  /* RW */
-	unsigned long	ucache_req_obese_msg                    :  1;  /* RW */
-	unsigned long	ucache_req_data_sb_err                  :  1;  /* RW */
-	unsigned long	ucache_rep_runt_msg                     :  1;  /* RW */
-	unsigned long	ucache_rep_obese_msg                    :  1;  /* RW */
-	unsigned long	ucache_rep_data_sb_err                  :  1;  /* RW */
-	unsigned long	ucache_rep_command_err                  :  1;  /* RW */
-	unsigned long	ucache_pend_timeout                     :  1;  /* RW */
-	unsigned long	macc_req_runt_msg                       :  1;  /* RW */
-	unsigned long	macc_req_obese_msg                      :  1;  /* RW */
-	unsigned long	macc_req_data_sb_err                    :  1;  /* RW */
-	unsigned long	macc_rep_runt_msg                       :  1;  /* RW */
-	unsigned long	macc_rep_obese_msg                      :  1;  /* RW */
-	unsigned long	macc_rep_data_sb_err                    :  1;  /* RW */
-	unsigned long	macc_amo_timeout                        :  1;  /* RW */
-	unsigned long	macc_put_timeout                        :  1;  /* RW */
-	unsigned long	macc_spurious_event                     :  1;  /* RW */
-	unsigned long	ioh_destination_table_parity            :  1;  /* RW */
-	unsigned long	get_had_error_reply                     :  1;  /* RW */
-	unsigned long	get_timeout                             :  1;  /* RW */
-	unsigned long	lock_manager_had_error_reply            :  1;  /* RW */
-	unsigned long	put_had_error_reply                     :  1;  /* RW */
-	unsigned long	put_timeout                             :  1;  /* RW */
-	unsigned long	sb_activation_overrun                   :  1;  /* RW */
-	unsigned long	completed_gb_activation_had_error_reply :  1;  /* RW */
-	unsigned long	completed_gb_activation_timeout         :  1;  /* RW */
-	unsigned long	descriptor_buffer_0_parity              :  1;  /* RW */
-	unsigned long	descriptor_buffer_1_parity              :  1;  /* RW */
-	unsigned long	socket_destination_table_parity         :  1;  /* RW */
-	unsigned long	bau_reply_payload_corruption            :  1;  /* RW */
-	unsigned long	io_port_destination_table_parity        :  1;  /* RW */
-	unsigned long	intd_soft_ack_timeout                   :  1;  /* RW */
-	unsigned long	int_rep_obese_msg                       :  1;  /* RW */
-	unsigned long	int_rep_command_err                     :  1;  /* RW */
-	unsigned long	int_timeout                             :  1;  /* RW */
-	unsigned long	rsvd_43_63                              : 21;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                          UVH_LOCAL_INT0_CONFIG                            */
-/* ========================================================================= */
-#define UVH_LOCAL_INT0_CONFIG 0x61000UL
-
-#define UVH_LOCAL_INT0_CONFIG_VECTOR_SHFT 0
-#define UVH_LOCAL_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL
-#define UVH_LOCAL_INT0_CONFIG_DM_SHFT 8
-#define UVH_LOCAL_INT0_CONFIG_DM_MASK 0x0000000000000700UL
-#define UVH_LOCAL_INT0_CONFIG_DESTMODE_SHFT 11
-#define UVH_LOCAL_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL
-#define UVH_LOCAL_INT0_CONFIG_STATUS_SHFT 12
-#define UVH_LOCAL_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL
-#define UVH_LOCAL_INT0_CONFIG_P_SHFT 13
-#define UVH_LOCAL_INT0_CONFIG_P_MASK 0x0000000000002000UL
-#define UVH_LOCAL_INT0_CONFIG_T_SHFT 15
-#define UVH_LOCAL_INT0_CONFIG_T_MASK 0x0000000000008000UL
-#define UVH_LOCAL_INT0_CONFIG_M_SHFT 16
-#define UVH_LOCAL_INT0_CONFIG_M_MASK 0x0000000000010000UL
-#define UVH_LOCAL_INT0_CONFIG_APIC_ID_SHFT 32
-#define UVH_LOCAL_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
-
-union uvh_local_int0_config_u {
-    unsigned long	v;
-    struct uvh_local_int0_config_s {
-	unsigned long	vector_  :  8;  /* RW */
-	unsigned long	dm       :  3;  /* RW */
-	unsigned long	destmode :  1;  /* RW */
-	unsigned long	status   :  1;  /* RO */
-	unsigned long	p        :  1;  /* RO */
-	unsigned long	rsvd_14  :  1;  /*    */
-	unsigned long	t        :  1;  /* RO */
-	unsigned long	m        :  1;  /* RW */
-	unsigned long	rsvd_17_31: 15;  /*    */
-	unsigned long	apic_id  : 32;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                          UVH_LOCAL_INT0_ENABLE                            */
-/* ========================================================================= */
-#define UVH_LOCAL_INT0_ENABLE 0x65000UL
-
-#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_SHFT 0
-#define UVH_LOCAL_INT0_ENABLE_LB_HCERR_MASK 0x0000000000000001UL
-#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_SHFT 1
-#define UVH_LOCAL_INT0_ENABLE_GR0_HCERR_MASK 0x0000000000000002UL
-#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_SHFT 2
-#define UVH_LOCAL_INT0_ENABLE_GR1_HCERR_MASK 0x0000000000000004UL
-#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_SHFT 3
-#define UVH_LOCAL_INT0_ENABLE_LH_HCERR_MASK 0x0000000000000008UL
-#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_SHFT 4
-#define UVH_LOCAL_INT0_ENABLE_RH_HCERR_MASK 0x0000000000000010UL
-#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_SHFT 5
-#define UVH_LOCAL_INT0_ENABLE_XN_HCERR_MASK 0x0000000000000020UL
-#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_SHFT 6
-#define UVH_LOCAL_INT0_ENABLE_SI_HCERR_MASK 0x0000000000000040UL
-#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_SHFT 7
-#define UVH_LOCAL_INT0_ENABLE_LB_AOERR0_MASK 0x0000000000000080UL
-#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_SHFT 8
-#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR0_MASK 0x0000000000000100UL
-#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_SHFT 9
-#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR0_MASK 0x0000000000000200UL
-#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_SHFT 10
-#define UVH_LOCAL_INT0_ENABLE_LH_AOERR0_MASK 0x0000000000000400UL
-#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_SHFT 11
-#define UVH_LOCAL_INT0_ENABLE_RH_AOERR0_MASK 0x0000000000000800UL
-#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_SHFT 12
-#define UVH_LOCAL_INT0_ENABLE_XN_AOERR0_MASK 0x0000000000001000UL
-#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_SHFT 13
-#define UVH_LOCAL_INT0_ENABLE_SI_AOERR0_MASK 0x0000000000002000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_SHFT 14
-#define UVH_LOCAL_INT0_ENABLE_LB_AOERR1_MASK 0x0000000000004000UL
-#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_SHFT 15
-#define UVH_LOCAL_INT0_ENABLE_GR0_AOERR1_MASK 0x0000000000008000UL
-#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_SHFT 16
-#define UVH_LOCAL_INT0_ENABLE_GR1_AOERR1_MASK 0x0000000000010000UL
-#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_SHFT 17
-#define UVH_LOCAL_INT0_ENABLE_LH_AOERR1_MASK 0x0000000000020000UL
-#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_SHFT 18
-#define UVH_LOCAL_INT0_ENABLE_RH_AOERR1_MASK 0x0000000000040000UL
-#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_SHFT 19
-#define UVH_LOCAL_INT0_ENABLE_XN_AOERR1_MASK 0x0000000000080000UL
-#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_SHFT 20
-#define UVH_LOCAL_INT0_ENABLE_SI_AOERR1_MASK 0x0000000000100000UL
-#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_SHFT 21
-#define UVH_LOCAL_INT0_ENABLE_RH_VPI_INT_MASK 0x0000000000200000UL
-#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_SHFT 22
-#define UVH_LOCAL_INT0_ENABLE_SYSTEM_SHUTDOWN_INT_MASK 0x0000000000400000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_SHFT 23
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_0_MASK 0x0000000000800000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_SHFT 24
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_1_MASK 0x0000000001000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_SHFT 25
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_2_MASK 0x0000000002000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_SHFT 26
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_3_MASK 0x0000000004000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_SHFT 27
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_4_MASK 0x0000000008000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_SHFT 28
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_5_MASK 0x0000000010000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_SHFT 29
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_6_MASK 0x0000000020000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_SHFT 30
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_7_MASK 0x0000000040000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_SHFT 31
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_8_MASK 0x0000000080000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_SHFT 32
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_9_MASK 0x0000000100000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_SHFT 33
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_10_MASK 0x0000000200000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_SHFT 34
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_11_MASK 0x0000000400000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_SHFT 35
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_12_MASK 0x0000000800000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_SHFT 36
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_13_MASK 0x0000001000000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_SHFT 37
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_14_MASK 0x0000002000000000UL
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_SHFT 38
-#define UVH_LOCAL_INT0_ENABLE_LB_IRQ_INT_15_MASK 0x0000004000000000UL
-#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_SHFT 39
-#define UVH_LOCAL_INT0_ENABLE_L1_NMI_INT_MASK 0x0000008000000000UL
-#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_SHFT 40
-#define UVH_LOCAL_INT0_ENABLE_STOP_CLOCK_MASK 0x0000010000000000UL
-#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_SHFT 41
-#define UVH_LOCAL_INT0_ENABLE_ASIC_TO_L1_MASK 0x0000020000000000UL
-#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_SHFT 42
-#define UVH_LOCAL_INT0_ENABLE_L1_TO_ASIC_MASK 0x0000040000000000UL
-#define UVH_LOCAL_INT0_ENABLE_LTC_INT_SHFT 43
-#define UVH_LOCAL_INT0_ENABLE_LTC_INT_MASK 0x0000080000000000UL
-#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_SHFT 44
-#define UVH_LOCAL_INT0_ENABLE_LA_SEQ_TRIGGER_MASK 0x0000100000000000UL
-
-union uvh_local_int0_enable_u {
-    unsigned long	v;
-    struct uvh_local_int0_enable_s {
-	unsigned long	lb_hcerr            :  1;  /* RW */
-	unsigned long	gr0_hcerr           :  1;  /* RW */
-	unsigned long	gr1_hcerr           :  1;  /* RW */
-	unsigned long	lh_hcerr            :  1;  /* RW */
-	unsigned long	rh_hcerr            :  1;  /* RW */
-	unsigned long	xn_hcerr            :  1;  /* RW */
-	unsigned long	si_hcerr            :  1;  /* RW */
-	unsigned long	lb_aoerr0           :  1;  /* RW */
-	unsigned long	gr0_aoerr0          :  1;  /* RW */
-	unsigned long	gr1_aoerr0          :  1;  /* RW */
-	unsigned long	lh_aoerr0           :  1;  /* RW */
-	unsigned long	rh_aoerr0           :  1;  /* RW */
-	unsigned long	xn_aoerr0           :  1;  /* RW */
-	unsigned long	si_aoerr0           :  1;  /* RW */
-	unsigned long	lb_aoerr1           :  1;  /* RW */
-	unsigned long	gr0_aoerr1          :  1;  /* RW */
-	unsigned long	gr1_aoerr1          :  1;  /* RW */
-	unsigned long	lh_aoerr1           :  1;  /* RW */
-	unsigned long	rh_aoerr1           :  1;  /* RW */
-	unsigned long	xn_aoerr1           :  1;  /* RW */
-	unsigned long	si_aoerr1           :  1;  /* RW */
-	unsigned long	rh_vpi_int          :  1;  /* RW */
-	unsigned long	system_shutdown_int :  1;  /* RW */
-	unsigned long	lb_irq_int_0        :  1;  /* RW */
-	unsigned long	lb_irq_int_1        :  1;  /* RW */
-	unsigned long	lb_irq_int_2        :  1;  /* RW */
-	unsigned long	lb_irq_int_3        :  1;  /* RW */
-	unsigned long	lb_irq_int_4        :  1;  /* RW */
-	unsigned long	lb_irq_int_5        :  1;  /* RW */
-	unsigned long	lb_irq_int_6        :  1;  /* RW */
-	unsigned long	lb_irq_int_7        :  1;  /* RW */
-	unsigned long	lb_irq_int_8        :  1;  /* RW */
-	unsigned long	lb_irq_int_9        :  1;  /* RW */
-	unsigned long	lb_irq_int_10       :  1;  /* RW */
-	unsigned long	lb_irq_int_11       :  1;  /* RW */
-	unsigned long	lb_irq_int_12       :  1;  /* RW */
-	unsigned long	lb_irq_int_13       :  1;  /* RW */
-	unsigned long	lb_irq_int_14       :  1;  /* RW */
-	unsigned long	lb_irq_int_15       :  1;  /* RW */
-	unsigned long	l1_nmi_int          :  1;  /* RW */
-	unsigned long	stop_clock          :  1;  /* RW */
-	unsigned long	asic_to_l1          :  1;  /* RW */
-	unsigned long	l1_to_asic          :  1;  /* RW */
-	unsigned long	ltc_int             :  1;  /* RW */
-	unsigned long	la_seq_trigger      :  1;  /* RW */
-	unsigned long	rsvd_45_63          : 19;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                               UVH_NODE_ID                                 */
-/* ========================================================================= */
-#define UVH_NODE_ID 0x0UL
-
-#define UVH_NODE_ID_FORCE1_SHFT 0
-#define UVH_NODE_ID_FORCE1_MASK 0x0000000000000001UL
-#define UVH_NODE_ID_MANUFACTURER_SHFT 1
-#define UVH_NODE_ID_MANUFACTURER_MASK 0x0000000000000ffeUL
-#define UVH_NODE_ID_PART_NUMBER_SHFT 12
-#define UVH_NODE_ID_PART_NUMBER_MASK 0x000000000ffff000UL
-#define UVH_NODE_ID_REVISION_SHFT 28
-#define UVH_NODE_ID_REVISION_MASK 0x00000000f0000000UL
-#define UVH_NODE_ID_NODE_ID_SHFT 32
-#define UVH_NODE_ID_NODE_ID_MASK 0x00007fff00000000UL
-#define UVH_NODE_ID_NODES_PER_BIT_SHFT 48
-#define UVH_NODE_ID_NODES_PER_BIT_MASK 0x007f000000000000UL
-#define UVH_NODE_ID_NI_PORT_SHFT 56
-#define UVH_NODE_ID_NI_PORT_MASK 0x0f00000000000000UL
-
-union uvh_node_id_u {
-    unsigned long	v;
-    struct uvh_node_id_s {
-	unsigned long	force1        :  1;  /* RO */
-	unsigned long	manufacturer  : 11;  /* RO */
-	unsigned long	part_number   : 16;  /* RO */
-	unsigned long	revision      :  4;  /* RO */
-	unsigned long	node_id       : 15;  /* RW */
-	unsigned long	rsvd_47       :  1;  /*    */
-	unsigned long	nodes_per_bit :  7;  /* RW */
-	unsigned long	rsvd_55       :  1;  /*    */
-	unsigned long	ni_port       :  4;  /* RO */
-	unsigned long	rsvd_60_63    :  4;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                          UVH_NODE_PRESENT_TABLE                           */
-/* ========================================================================= */
-#define UVH_NODE_PRESENT_TABLE 0x1400UL
-#define UVH_NODE_PRESENT_TABLE_DEPTH 16
-
-#define UVH_NODE_PRESENT_TABLE_NODES_SHFT 0
-#define UVH_NODE_PRESENT_TABLE_NODES_MASK 0xffffffffffffffffUL
-
-union uvh_node_present_table_u {
-    unsigned long	v;
-    struct uvh_node_present_table_s {
-	unsigned long	nodes : 64;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR                  */
-/* ========================================================================= */
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR 0x16000d0UL
-
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT 24
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_MASK 0x00003fffff000000UL
-
-union uvh_rh_gam_alias210_redirect_config_0_mmr_u {
-    unsigned long	v;
-    struct uvh_rh_gam_alias210_redirect_config_0_mmr_s {
-	unsigned long	rsvd_0_23 : 24;  /*    */
-	unsigned long	dest_base : 22;  /* RW */
-	unsigned long	rsvd_46_63: 18;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR                  */
-/* ========================================================================= */
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR 0x16000e0UL
-
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_SHFT 24
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR_DEST_BASE_MASK 0x00003fffff000000UL
-
-union uvh_rh_gam_alias210_redirect_config_1_mmr_u {
-    unsigned long	v;
-    struct uvh_rh_gam_alias210_redirect_config_1_mmr_s {
-	unsigned long	rsvd_0_23 : 24;  /*    */
-	unsigned long	dest_base : 22;  /* RW */
-	unsigned long	rsvd_46_63: 18;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR                  */
-/* ========================================================================= */
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR 0x16000f0UL
-
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_SHFT 24
-#define UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR_DEST_BASE_MASK 0x00003fffff000000UL
-
-union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
-    unsigned long	v;
-    struct uvh_rh_gam_alias210_redirect_config_2_mmr_s {
-	unsigned long	rsvd_0_23 : 24;  /*    */
-	unsigned long	dest_base : 22;  /* RW */
-	unsigned long	rsvd_46_63: 18;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                    UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR                      */
-/* ========================================================================= */
-#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR 0x1600020UL
-
-#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_SHFT 26
-#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
-#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_CFG_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_rh_gam_cfg_overlay_config_mmr_u {
-    unsigned long	v;
-    struct uvh_rh_gam_cfg_overlay_config_mmr_s {
-	unsigned long	rsvd_0_25: 26;  /*    */
-	unsigned long	base   : 20;  /* RW */
-	unsigned long	rsvd_46_62: 17;  /*    */
-	unsigned long	enable :  1;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                    UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR                      */
-/* ========================================================================= */
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR 0x1600010UL
-
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_SHFT 28
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffff0000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_SHFT 48
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_GR4_MASK 0x0001000000000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_SHFT 52
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_N_GRU_MASK 0x00f0000000000000UL
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_rh_gam_gru_overlay_config_mmr_u {
-    unsigned long	v;
-    struct uvh_rh_gam_gru_overlay_config_mmr_s {
-	unsigned long	rsvd_0_27: 28;  /*    */
-	unsigned long	base   : 18;  /* RW */
-	unsigned long	rsvd_46_47:  2;  /*    */
-	unsigned long	gr4    :  1;  /* RW */
-	unsigned long	rsvd_49_51:  3;  /*    */
-	unsigned long	n_gru  :  4;  /* RW */
-	unsigned long	rsvd_56_62:  7;  /*    */
-	unsigned long	enable :  1;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                   UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR                     */
-/* ========================================================================= */
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR 0x1600030UL
-
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_SHFT 30
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003fffc0000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_SHFT 46
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_M_IO_MASK 0x000fc00000000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_SHFT 52
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_N_IO_MASK 0x00f0000000000000UL
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_MMIOH_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_rh_gam_mmioh_overlay_config_mmr_u {
-    unsigned long	v;
-    struct uvh_rh_gam_mmioh_overlay_config_mmr_s {
-	unsigned long	rsvd_0_29: 30;  /*    */
-	unsigned long	base   : 16;  /* RW */
-	unsigned long	m_io   :  6;  /* RW */
-	unsigned long	n_io   :  4;  /* RW */
-	unsigned long	rsvd_56_62:  7;  /*    */
-	unsigned long	enable :  1;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                    UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR                      */
-/* ========================================================================= */
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR 0x1600028UL
-
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_SHFT 26
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_BASE_MASK 0x00003ffffc000000UL
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_SHFT 46
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_DUAL_HUB_MASK 0x0000400000000000UL
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_SHFT 63
-#define UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_rh_gam_mmr_overlay_config_mmr_u {
-    unsigned long	v;
-    struct uvh_rh_gam_mmr_overlay_config_mmr_s {
-	unsigned long	rsvd_0_25: 26;  /*    */
-	unsigned long	base     : 20;  /* RW */
-	unsigned long	dual_hub :  1;  /* RW */
-	unsigned long	rsvd_47_62: 16;  /*    */
-	unsigned long	enable   :  1;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                                 UVH_RTC                                   */
-/* ========================================================================= */
-#define UVH_RTC 0x340000UL
-
-#define UVH_RTC_REAL_TIME_CLOCK_SHFT 0
-#define UVH_RTC_REAL_TIME_CLOCK_MASK 0x00ffffffffffffffUL
-
-union uvh_rtc_u {
-    unsigned long	v;
-    struct uvh_rtc_s {
-	unsigned long	real_time_clock : 56;  /* RW */
-	unsigned long	rsvd_56_63      :  8;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                           UVH_RTC1_INT_CONFIG                             */
-/* ========================================================================= */
-#define UVH_RTC1_INT_CONFIG 0x615c0UL
-
-#define UVH_RTC1_INT_CONFIG_VECTOR_SHFT 0
-#define UVH_RTC1_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
-#define UVH_RTC1_INT_CONFIG_DM_SHFT 8
-#define UVH_RTC1_INT_CONFIG_DM_MASK 0x0000000000000700UL
-#define UVH_RTC1_INT_CONFIG_DESTMODE_SHFT 11
-#define UVH_RTC1_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
-#define UVH_RTC1_INT_CONFIG_STATUS_SHFT 12
-#define UVH_RTC1_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
-#define UVH_RTC1_INT_CONFIG_P_SHFT 13
-#define UVH_RTC1_INT_CONFIG_P_MASK 0x0000000000002000UL
-#define UVH_RTC1_INT_CONFIG_T_SHFT 15
-#define UVH_RTC1_INT_CONFIG_T_MASK 0x0000000000008000UL
-#define UVH_RTC1_INT_CONFIG_M_SHFT 16
-#define UVH_RTC1_INT_CONFIG_M_MASK 0x0000000000010000UL
-#define UVH_RTC1_INT_CONFIG_APIC_ID_SHFT 32
-#define UVH_RTC1_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
-
-union uvh_rtc1_int_config_u {
-    unsigned long	v;
-    struct uvh_rtc1_int_config_s {
-	unsigned long	vector_  :  8;  /* RW */
-	unsigned long	dm       :  3;  /* RW */
-	unsigned long	destmode :  1;  /* RW */
-	unsigned long	status   :  1;  /* RO */
-	unsigned long	p        :  1;  /* RO */
-	unsigned long	rsvd_14  :  1;  /*    */
-	unsigned long	t        :  1;  /* RO */
-	unsigned long	m        :  1;  /* RW */
-	unsigned long	rsvd_17_31: 15;  /*    */
-	unsigned long	apic_id  : 32;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                           UVH_RTC2_INT_CONFIG                             */
-/* ========================================================================= */
-#define UVH_RTC2_INT_CONFIG 0x61600UL
-
-#define UVH_RTC2_INT_CONFIG_VECTOR_SHFT 0
-#define UVH_RTC2_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
-#define UVH_RTC2_INT_CONFIG_DM_SHFT 8
-#define UVH_RTC2_INT_CONFIG_DM_MASK 0x0000000000000700UL
-#define UVH_RTC2_INT_CONFIG_DESTMODE_SHFT 11
-#define UVH_RTC2_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
-#define UVH_RTC2_INT_CONFIG_STATUS_SHFT 12
-#define UVH_RTC2_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
-#define UVH_RTC2_INT_CONFIG_P_SHFT 13
-#define UVH_RTC2_INT_CONFIG_P_MASK 0x0000000000002000UL
-#define UVH_RTC2_INT_CONFIG_T_SHFT 15
-#define UVH_RTC2_INT_CONFIG_T_MASK 0x0000000000008000UL
-#define UVH_RTC2_INT_CONFIG_M_SHFT 16
-#define UVH_RTC2_INT_CONFIG_M_MASK 0x0000000000010000UL
-#define UVH_RTC2_INT_CONFIG_APIC_ID_SHFT 32
-#define UVH_RTC2_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
-
-union uvh_rtc2_int_config_u {
-    unsigned long	v;
-    struct uvh_rtc2_int_config_s {
-	unsigned long	vector_  :  8;  /* RW */
-	unsigned long	dm       :  3;  /* RW */
-	unsigned long	destmode :  1;  /* RW */
-	unsigned long	status   :  1;  /* RO */
-	unsigned long	p        :  1;  /* RO */
-	unsigned long	rsvd_14  :  1;  /*    */
-	unsigned long	t        :  1;  /* RO */
-	unsigned long	m        :  1;  /* RW */
-	unsigned long	rsvd_17_31: 15;  /*    */
-	unsigned long	apic_id  : 32;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                           UVH_RTC3_INT_CONFIG                             */
-/* ========================================================================= */
-#define UVH_RTC3_INT_CONFIG 0x61640UL
-
-#define UVH_RTC3_INT_CONFIG_VECTOR_SHFT 0
-#define UVH_RTC3_INT_CONFIG_VECTOR_MASK 0x00000000000000ffUL
-#define UVH_RTC3_INT_CONFIG_DM_SHFT 8
-#define UVH_RTC3_INT_CONFIG_DM_MASK 0x0000000000000700UL
-#define UVH_RTC3_INT_CONFIG_DESTMODE_SHFT 11
-#define UVH_RTC3_INT_CONFIG_DESTMODE_MASK 0x0000000000000800UL
-#define UVH_RTC3_INT_CONFIG_STATUS_SHFT 12
-#define UVH_RTC3_INT_CONFIG_STATUS_MASK 0x0000000000001000UL
-#define UVH_RTC3_INT_CONFIG_P_SHFT 13
-#define UVH_RTC3_INT_CONFIG_P_MASK 0x0000000000002000UL
-#define UVH_RTC3_INT_CONFIG_T_SHFT 15
-#define UVH_RTC3_INT_CONFIG_T_MASK 0x0000000000008000UL
-#define UVH_RTC3_INT_CONFIG_M_SHFT 16
-#define UVH_RTC3_INT_CONFIG_M_MASK 0x0000000000010000UL
-#define UVH_RTC3_INT_CONFIG_APIC_ID_SHFT 32
-#define UVH_RTC3_INT_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
-
-union uvh_rtc3_int_config_u {
-    unsigned long	v;
-    struct uvh_rtc3_int_config_s {
-	unsigned long	vector_  :  8;  /* RW */
-	unsigned long	dm       :  3;  /* RW */
-	unsigned long	destmode :  1;  /* RW */
-	unsigned long	status   :  1;  /* RO */
-	unsigned long	p        :  1;  /* RO */
-	unsigned long	rsvd_14  :  1;  /*    */
-	unsigned long	t        :  1;  /* RO */
-	unsigned long	m        :  1;  /* RW */
-	unsigned long	rsvd_17_31: 15;  /*    */
-	unsigned long	apic_id  : 32;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                            UVH_RTC_INC_RATIO                              */
-/* ========================================================================= */
-#define UVH_RTC_INC_RATIO 0x350000UL
-
-#define UVH_RTC_INC_RATIO_FRACTION_SHFT 0
-#define UVH_RTC_INC_RATIO_FRACTION_MASK 0x00000000000fffffUL
-#define UVH_RTC_INC_RATIO_RATIO_SHFT 20
-#define UVH_RTC_INC_RATIO_RATIO_MASK 0x0000000000700000UL
-
-union uvh_rtc_inc_ratio_u {
-    unsigned long	v;
-    struct uvh_rtc_inc_ratio_s {
-	unsigned long	fraction : 20;  /* RW */
-	unsigned long	ratio    :  3;  /* RW */
-	unsigned long	rsvd_23_63: 41;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                          UVH_SI_ADDR_MAP_CONFIG                           */
-/* ========================================================================= */
-#define UVH_SI_ADDR_MAP_CONFIG 0xc80000UL
-
-#define UVH_SI_ADDR_MAP_CONFIG_M_SKT_SHFT 0
-#define UVH_SI_ADDR_MAP_CONFIG_M_SKT_MASK 0x000000000000003fUL
-#define UVH_SI_ADDR_MAP_CONFIG_N_SKT_SHFT 8
-#define UVH_SI_ADDR_MAP_CONFIG_N_SKT_MASK 0x0000000000000f00UL
-
-union uvh_si_addr_map_config_u {
-    unsigned long	v;
-    struct uvh_si_addr_map_config_s {
-	unsigned long	m_skt :  6;  /* RW */
-	unsigned long	rsvd_6_7:  2;  /*    */
-	unsigned long	n_skt :  4;  /* RW */
-	unsigned long	rsvd_12_63: 52;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                       UVH_SI_ALIAS0_OVERLAY_CONFIG                        */
-/* ========================================================================= */
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG 0xc80008UL
-
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_si_alias0_overlay_config_u {
-    unsigned long	v;
-    struct uvh_si_alias0_overlay_config_s {
-	unsigned long	rsvd_0_23: 24;  /*    */
-	unsigned long	base    :  8;  /* RW */
-	unsigned long	rsvd_32_47: 16;  /*    */
-	unsigned long	m_alias :  5;  /* RW */
-	unsigned long	rsvd_53_62: 10;  /*    */
-	unsigned long	enable  :  1;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                       UVH_SI_ALIAS1_OVERLAY_CONFIG                        */
-/* ========================================================================= */
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG 0xc80010UL
-
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_si_alias1_overlay_config_u {
-    unsigned long	v;
-    struct uvh_si_alias1_overlay_config_s {
-	unsigned long	rsvd_0_23: 24;  /*    */
-	unsigned long	base    :  8;  /* RW */
-	unsigned long	rsvd_32_47: 16;  /*    */
-	unsigned long	m_alias :  5;  /* RW */
-	unsigned long	rsvd_53_62: 10;  /*    */
-	unsigned long	enable  :  1;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                       UVH_SI_ALIAS2_OVERLAY_CONFIG                        */
-/* ========================================================================= */
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG 0xc80018UL
-
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_si_alias2_overlay_config_u {
-    unsigned long	v;
-    struct uvh_si_alias2_overlay_config_s {
-	unsigned long	rsvd_0_23: 24;  /*    */
-	unsigned long	base    :  8;  /* RW */
-	unsigned long	rsvd_32_47: 16;  /*    */
-	unsigned long	m_alias :  5;  /* RW */
-	unsigned long	rsvd_53_62: 10;  /*    */
-	unsigned long	enable  :  1;  /* RW */
-    } s;
-};
-
-
-#endif /* ASM_X86__UV__UV_MMRS_H */
diff --git a/include/asm-x86/vdso.h b/include/asm-x86/vdso.h
deleted file mode 100644
index 4ab320913ea3..000000000000
--- a/include/asm-x86/vdso.h
+++ /dev/null
@@ -1,47 +0,0 @@
-#ifndef ASM_X86__VDSO_H
-#define ASM_X86__VDSO_H
-
-#ifdef CONFIG_X86_64
-extern const char VDSO64_PRELINK[];
-
-/*
- * Given a pointer to the vDSO image, find the pointer to VDSO64_name
- * as that symbol is defined in the vDSO sources or linker script.
- */
-#define VDSO64_SYMBOL(base, name)					\
-({									\
-	extern const char VDSO64_##name[];				\
-	(void *)(VDSO64_##name - VDSO64_PRELINK + (unsigned long)(base)); \
-})
-#endif
-
-#if defined CONFIG_X86_32 || defined CONFIG_COMPAT
-extern const char VDSO32_PRELINK[];
-
-/*
- * Given a pointer to the vDSO image, find the pointer to VDSO32_name
- * as that symbol is defined in the vDSO sources or linker script.
- */
-#define VDSO32_SYMBOL(base, name)					\
-({									\
-	extern const char VDSO32_##name[];				\
-	(void *)(VDSO32_##name - VDSO32_PRELINK + (unsigned long)(base)); \
-})
-#endif
-
-/*
- * These symbols are defined with the addresses in the vsyscall page.
- * See vsyscall-sigreturn.S.
- */
-extern void __user __kernel_sigreturn;
-extern void __user __kernel_rt_sigreturn;
-
-/*
- * These symbols are defined by vdso32.S to mark the bounds
- * of the ELF DSO images included therein.
- */
-extern const char vdso32_int80_start, vdso32_int80_end;
-extern const char vdso32_syscall_start, vdso32_syscall_end;
-extern const char vdso32_sysenter_start, vdso32_sysenter_end;
-
-#endif /* ASM_X86__VDSO_H */
diff --git a/include/asm-x86/vga.h b/include/asm-x86/vga.h
deleted file mode 100644
index b9e493d07d07..000000000000
--- a/include/asm-x86/vga.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- *	Access to VGA videoram
- *
- *	(c) 1998 Martin Mares <mj@ucw.cz>
- */
-
-#ifndef ASM_X86__VGA_H
-#define ASM_X86__VGA_H
-
-/*
- *	On the PC, we can just recalculate addresses and then
- *	access the videoram directly without any black magic.
- */
-
-#define VGA_MAP_MEM(x, s) (unsigned long)phys_to_virt(x)
-
-#define vga_readb(x) (*(x))
-#define vga_writeb(x, y) (*(y) = (x))
-
-#endif /* ASM_X86__VGA_H */
diff --git a/include/asm-x86/vgtod.h b/include/asm-x86/vgtod.h
deleted file mode 100644
index 38fd13364021..000000000000
--- a/include/asm-x86/vgtod.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef ASM_X86__VGTOD_H
-#define ASM_X86__VGTOD_H
-
-#include <asm/vsyscall.h>
-#include <linux/clocksource.h>
-
-struct vsyscall_gtod_data {
-	seqlock_t	lock;
-
-	/* open coded 'struct timespec' */
-	time_t		wall_time_sec;
-	u32		wall_time_nsec;
-
-	int		sysctl_enabled;
-	struct timezone sys_tz;
-	struct { /* extract of a clocksource struct */
-		cycle_t (*vread)(void);
-		cycle_t	cycle_last;
-		cycle_t	mask;
-		u32	mult;
-		u32	shift;
-	} clock;
-	struct timespec wall_to_monotonic;
-};
-extern struct vsyscall_gtod_data __vsyscall_gtod_data
-__section_vsyscall_gtod_data;
-extern struct vsyscall_gtod_data vsyscall_gtod_data;
-
-#endif /* ASM_X86__VGTOD_H */
diff --git a/include/asm-x86/vic.h b/include/asm-x86/vic.h
deleted file mode 100644
index 53100f353612..000000000000
--- a/include/asm-x86/vic.h
+++ /dev/null
@@ -1,61 +0,0 @@
-/* Copyright (C) 1999,2001
- *
- * Author: J.E.J.Bottomley@HansenPartnership.com
- *
- * Standard include definitions for the NCR Voyager Interrupt Controller */
-
-/* The eight CPI vectors.  To activate a CPI, you write a bit mask
- * corresponding to the processor set to be interrupted into the
- * relevant register.  That set of CPUs will then be interrupted with
- * the CPI */
-static const int VIC_CPI_Registers[] =
-	{0xFC00, 0xFC01, 0xFC08, 0xFC09,
-	 0xFC10, 0xFC11, 0xFC18, 0xFC19 };
-
-#define VIC_PROC_WHO_AM_I		0xfc29
-#	define	QUAD_IDENTIFIER		0xC0
-#	define  EIGHT_SLOT_IDENTIFIER	0xE0
-#define QIC_EXTENDED_PROCESSOR_SELECT	0xFC72
-#define VIC_CPI_BASE_REGISTER		0xFC41
-#define VIC_PROCESSOR_ID		0xFC21
-#	define VIC_CPU_MASQUERADE_ENABLE 0x8
-
-#define VIC_CLAIM_REGISTER_0		0xFC38
-#define VIC_CLAIM_REGISTER_1		0xFC39
-#define VIC_REDIRECT_REGISTER_0		0xFC60
-#define VIC_REDIRECT_REGISTER_1		0xFC61
-#define VIC_PRIORITY_REGISTER		0xFC20
-
-#define VIC_PRIMARY_MC_BASE		0xFC48
-#define VIC_SECONDARY_MC_BASE		0xFC49
-
-#define QIC_PROCESSOR_ID		0xFC71
-#	define	QIC_CPUID_ENABLE	0x08
-
-#define QIC_VIC_CPI_BASE_REGISTER	0xFC79
-#define QIC_CPI_BASE_REGISTER		0xFC7A
-
-#define QIC_MASK_REGISTER0		0xFC80
-/* NOTE: these are masked high, enabled low */
-#	define QIC_PERF_TIMER		0x01
-#	define QIC_LPE			0x02
-#	define QIC_SYS_INT		0x04
-#	define QIC_CMN_INT		0x08
-/* at the moment, just enable CMN_INT, disable SYS_INT */
-#	define QIC_DEFAULT_MASK0	(~(QIC_CMN_INT /* | VIC_SYS_INT */))
-#define QIC_MASK_REGISTER1		0xFC81
-#	define QIC_BOOT_CPI_MASK	0xFE
-/* Enable CPI's 1-6 inclusive */
-#	define QIC_CPI_ENABLE		0x81
-
-#define QIC_INTERRUPT_CLEAR0		0xFC8A
-#define QIC_INTERRUPT_CLEAR1		0xFC8B
-
-/* this is where we place the CPI vectors */
-#define VIC_DEFAULT_CPI_BASE		0xC0
-/* this is where we place the QIC CPI vectors */
-#define QIC_DEFAULT_CPI_BASE		0xD0
-
-#define VIC_BOOT_INTERRUPT_MASK		0xfe
-
-extern void smp_vic_timer_interrupt(void);
diff --git a/include/asm-x86/visws/cobalt.h b/include/asm-x86/visws/cobalt.h
deleted file mode 100644
index 9627a8fe84e9..000000000000
--- a/include/asm-x86/visws/cobalt.h
+++ /dev/null
@@ -1,125 +0,0 @@
-#ifndef ASM_X86__VISWS__COBALT_H
-#define ASM_X86__VISWS__COBALT_H
-
-#include <asm/fixmap.h>
-
-/*
- * Cobalt SGI Visual Workstation system ASIC
- */ 
-
-#define CO_CPU_NUM_PHYS 0x1e00
-#define CO_CPU_TAB_PHYS (CO_CPU_NUM_PHYS + 2)
-
-#define CO_CPU_MAX 4
-
-#define	CO_CPU_PHYS		0xc2000000
-#define	CO_APIC_PHYS		0xc4000000
-
-/* see set_fixmap() and asm/fixmap.h */
-#define	CO_CPU_VADDR		(fix_to_virt(FIX_CO_CPU))
-#define	CO_APIC_VADDR		(fix_to_virt(FIX_CO_APIC))
-
-/* Cobalt CPU registers -- relative to CO_CPU_VADDR, use co_cpu_*() */
-#define	CO_CPU_REV		0x08
-#define	CO_CPU_CTRL		0x10
-#define	CO_CPU_STAT		0x20
-#define	CO_CPU_TIMEVAL		0x30
-
-/* CO_CPU_CTRL bits */
-#define	CO_CTRL_TIMERUN		0x04		/* 0 == disabled */
-#define	CO_CTRL_TIMEMASK	0x08		/* 0 == unmasked */
-
-/* CO_CPU_STATUS bits */
-#define	CO_STAT_TIMEINTR	0x02	/* (r) 1 == int pend, (w) 0 == clear */
-
-/* CO_CPU_TIMEVAL value */
-#define	CO_TIME_HZ		100000000	/* Cobalt core rate */
-
-/* Cobalt APIC registers -- relative to CO_APIC_VADDR, use co_apic_*() */
-#define	CO_APIC_HI(n)		(((n) * 0x10) + 4)
-#define	CO_APIC_LO(n)		((n) * 0x10)
-#define	CO_APIC_ID		0x0ffc
-
-/* CO_APIC_ID bits */
-#define	CO_APIC_ENABLE		0x00000100
-
-/* CO_APIC_LO bits */
-#define	CO_APIC_MASK		0x00010000	/* 0 = enabled */
-#define	CO_APIC_LEVEL		0x00008000	/* 0 = edge */
-
-/*
- * Where things are physically wired to Cobalt
- * #defines with no board _<type>_<rev>_ are common to all (thus far)
- */
-#define	CO_APIC_IDE0		4
-#define CO_APIC_IDE1		2		/* Only on 320 */
-
-#define	CO_APIC_8259		12		/* serial, floppy, par-l-l */
-
-/* Lithium PCI Bridge A -- "the one with 82557 Ethernet" */
-#define	CO_APIC_PCIA_BASE0	0 /* and 1 */	/* slot 0, line 0 */
-#define	CO_APIC_PCIA_BASE123	5 /* and 6 */	/* slot 0, line 1 */
-
-#define	CO_APIC_PIIX4_USB	7		/* this one is weird */
-
-/* Lithium PCI Bridge B -- "the one with PIIX4" */
-#define	CO_APIC_PCIB_BASE0	8 /* and 9-12 *//* slot 0, line 0 */
-#define	CO_APIC_PCIB_BASE123	13 /* 14.15 */	/* slot 0, line 1 */
-
-#define	CO_APIC_VIDOUT0		16
-#define	CO_APIC_VIDOUT1		17
-#define	CO_APIC_VIDIN0		18
-#define	CO_APIC_VIDIN1		19
-
-#define	CO_APIC_LI_AUDIO	22
-
-#define	CO_APIC_AS		24
-#define	CO_APIC_RE		25
-
-#define CO_APIC_CPU		28		/* Timer and Cache interrupt */
-#define	CO_APIC_NMI		29
-#define	CO_APIC_LAST		CO_APIC_NMI
-
-/*
- * This is how irqs are assigned on the Visual Workstation.
- * Legacy devices get irq's 1-15 (system clock is 0 and is CO_APIC_CPU).
- * All other devices (including PCI) go to Cobalt and are irq's 16 on up.
- */
-#define	CO_IRQ_APIC0	16			/* irq of apic entry 0 */
-#define	IS_CO_APIC(irq)	((irq) >= CO_IRQ_APIC0)
-#define	CO_IRQ(apic)	(CO_IRQ_APIC0 + (apic))	/* apic ent to irq */
-#define	CO_APIC(irq)	((irq) - CO_IRQ_APIC0)	/* irq to apic ent */
-#define CO_IRQ_IDE0	14			/* knowledge of... */
-#define CO_IRQ_IDE1	15			/* ... ide driver defaults! */
-#define	CO_IRQ_8259	CO_IRQ(CO_APIC_8259)
-
-#ifdef CONFIG_X86_VISWS_APIC
-static inline void co_cpu_write(unsigned long reg, unsigned long v)
-{
-	*((volatile unsigned long *)(CO_CPU_VADDR+reg))=v;
-}
-
-static inline unsigned long co_cpu_read(unsigned long reg)
-{
-	return *((volatile unsigned long *)(CO_CPU_VADDR+reg));
-}            
-             
-static inline void co_apic_write(unsigned long reg, unsigned long v)
-{
-	*((volatile unsigned long *)(CO_APIC_VADDR+reg))=v;
-}            
-             
-static inline unsigned long co_apic_read(unsigned long reg)
-{
-	return *((volatile unsigned long *)(CO_APIC_VADDR+reg));
-}
-#endif
-
-extern char visws_board_type;
-
-#define	VISWS_320	0
-#define	VISWS_540	1
-
-extern char visws_board_rev;
-
-#endif /* ASM_X86__VISWS__COBALT_H */
diff --git a/include/asm-x86/visws/lithium.h b/include/asm-x86/visws/lithium.h
deleted file mode 100644
index b36d3b378c63..000000000000
--- a/include/asm-x86/visws/lithium.h
+++ /dev/null
@@ -1,53 +0,0 @@
-#ifndef ASM_X86__VISWS__LITHIUM_H
-#define ASM_X86__VISWS__LITHIUM_H
-
-#include <asm/fixmap.h>
-
-/*
- * Lithium is the SGI Visual Workstation I/O ASIC
- */
-
-#define	LI_PCI_A_PHYS		0xfc000000	/* Enet is dev 3 */
-#define	LI_PCI_B_PHYS		0xfd000000	/* PIIX4 is here */
-
-/* see set_fixmap() and asm/fixmap.h */
-#define LI_PCIA_VADDR   (fix_to_virt(FIX_LI_PCIA))
-#define LI_PCIB_VADDR   (fix_to_virt(FIX_LI_PCIB))
-
-/* Not a standard PCI? (not in linux/pci.h) */
-#define	LI_PCI_BUSNUM	0x44			/* lo8: primary, hi8: sub */
-#define LI_PCI_INTEN    0x46
-
-/* LI_PCI_INTENT bits */
-#define	LI_INTA_0	0x0001
-#define	LI_INTA_1	0x0002
-#define	LI_INTA_2	0x0004
-#define	LI_INTA_3	0x0008
-#define	LI_INTA_4	0x0010
-#define	LI_INTB		0x0020
-#define	LI_INTC		0x0040
-#define	LI_INTD		0x0080
-
-/* More special purpose macros... */
-static inline void li_pcia_write16(unsigned long reg, unsigned short v)
-{
-	*((volatile unsigned short *)(LI_PCIA_VADDR+reg))=v;
-}
-
-static inline unsigned short li_pcia_read16(unsigned long reg)
-{
-	 return *((volatile unsigned short *)(LI_PCIA_VADDR+reg));
-}
-
-static inline void li_pcib_write16(unsigned long reg, unsigned short v)
-{
-	*((volatile unsigned short *)(LI_PCIB_VADDR+reg))=v;
-}
-
-static inline unsigned short li_pcib_read16(unsigned long reg)
-{
-	return *((volatile unsigned short *)(LI_PCIB_VADDR+reg));
-}
-
-#endif /* ASM_X86__VISWS__LITHIUM_H */
-
diff --git a/include/asm-x86/visws/piix4.h b/include/asm-x86/visws/piix4.h
deleted file mode 100644
index 61c938045ec9..000000000000
--- a/include/asm-x86/visws/piix4.h
+++ /dev/null
@@ -1,107 +0,0 @@
-#ifndef ASM_X86__VISWS__PIIX4_H
-#define ASM_X86__VISWS__PIIX4_H
-
-/*
- * PIIX4 as used on SGI Visual Workstations
- */
-
-#define	PIIX_PM_START		0x0F80
-
-#define	SIO_GPIO_START		0x0FC0
-
-#define	SIO_PM_START		0x0FC8
-
-#define	PMBASE			PIIX_PM_START
-#define	GPIREG0			(PMBASE+0x30)
-#define	GPIREG(x)		(GPIREG0+((x)/8))
-#define	GPIBIT(x)		(1 << ((x)%8))
-
-#define	PIIX_GPI_BD_ID1		18
-#define	PIIX_GPI_BD_ID2		19
-#define	PIIX_GPI_BD_ID3		20
-#define	PIIX_GPI_BD_ID4		21
-#define	PIIX_GPI_BD_REG		GPIREG(PIIX_GPI_BD_ID1)
-#define	PIIX_GPI_BD_MASK	(GPIBIT(PIIX_GPI_BD_ID1) | \
-				GPIBIT(PIIX_GPI_BD_ID2) | \
-				GPIBIT(PIIX_GPI_BD_ID3) | \
-				GPIBIT(PIIX_GPI_BD_ID4) )
-
-#define	PIIX_GPI_BD_SHIFT	(PIIX_GPI_BD_ID1 % 8)
-
-#define	SIO_INDEX		0x2e
-#define	SIO_DATA		0x2f
-
-#define	SIO_DEV_SEL		0x7
-#define	SIO_DEV_ENB		0x30
-#define	SIO_DEV_MSB		0x60
-#define	SIO_DEV_LSB		0x61
-
-#define	SIO_GP_DEV		0x7
-
-#define	SIO_GP_BASE		SIO_GPIO_START
-#define	SIO_GP_MSB		(SIO_GP_BASE>>8)
-#define	SIO_GP_LSB		(SIO_GP_BASE&0xff)
-
-#define	SIO_GP_DATA1		(SIO_GP_BASE+0)
-
-#define	SIO_PM_DEV		0x8
-
-#define	SIO_PM_BASE		SIO_PM_START
-#define	SIO_PM_MSB		(SIO_PM_BASE>>8)
-#define	SIO_PM_LSB		(SIO_PM_BASE&0xff)
-#define	SIO_PM_INDEX		(SIO_PM_BASE+0)
-#define	SIO_PM_DATA		(SIO_PM_BASE+1)
-
-#define	SIO_PM_FER2		0x1
-
-#define	SIO_PM_GP_EN		0x80
-
-
-
-/*
- * This is the dev/reg where generating a config cycle will
- * result in a PCI special cycle.
- */
-#define SPECIAL_DEV		0xff
-#define SPECIAL_REG		0x00
-
-/*
- * PIIX4 needs to see a special cycle with the following data
- * to be convinced the processor has gone into the stop grant
- * state.  PIIX4 insists on seeing this before it will power
- * down a system.
- */
-#define PIIX_SPECIAL_STOP		0x00120002
-
-#define PIIX4_RESET_PORT	0xcf9
-#define PIIX4_RESET_VAL		0x6
-
-#define PMSTS_PORT		0xf80	// 2 bytes	PM Status
-#define PMEN_PORT		0xf82	// 2 bytes	PM Enable
-#define	PMCNTRL_PORT		0xf84	// 2 bytes	PM Control
-
-#define PM_SUSPEND_ENABLE	0x2000	// start sequence to suspend state
-
-/*
- * PMSTS and PMEN I/O bit definitions.
- * (Bits are the same in both registers)
- */
-#define PM_STS_RSM		(1<<15)	// Resume Status
-#define PM_STS_PWRBTNOR		(1<<11)	// Power Button Override
-#define PM_STS_RTC		(1<<10)	// RTC status
-#define PM_STS_PWRBTN		(1<<8)	// Power Button Pressed?
-#define PM_STS_GBL		(1<<5)	// Global Status
-#define PM_STS_BM		(1<<4)	// Bus Master Status
-#define PM_STS_TMROF		(1<<0)	// Timer Overflow Status.
-
-/*
- * Stop clock GPI register
- */
-#define PIIX_GPIREG0			(0xf80 + 0x30)
-
-/*
- * Stop clock GPI bit in GPIREG0
- */
-#define	PIIX_GPI_STPCLK		0x4	// STPCLK signal routed back in
-
-#endif /* ASM_X86__VISWS__PIIX4_H */
diff --git a/include/asm-x86/visws/sgivw.h b/include/asm-x86/visws/sgivw.h
deleted file mode 100644
index 5fbf63e1003c..000000000000
--- a/include/asm-x86/visws/sgivw.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/*
- * Frame buffer position and size:
- */
-extern unsigned long sgivwfb_mem_phys;
-extern unsigned long sgivwfb_mem_size;
diff --git a/include/asm-x86/vm86.h b/include/asm-x86/vm86.h
deleted file mode 100644
index 998bd18eb737..000000000000
--- a/include/asm-x86/vm86.h
+++ /dev/null
@@ -1,208 +0,0 @@
-#ifndef ASM_X86__VM86_H
-#define ASM_X86__VM86_H
-
-/*
- * I'm guessing at the VIF/VIP flag usage, but hope that this is how
- * the Pentium uses them. Linux will return from vm86 mode when both
- * VIF and VIP is set.
- *
- * On a Pentium, we could probably optimize the virtual flags directly
- * in the eflags register instead of doing it "by hand" in vflags...
- *
- * Linus
- */
-
-#include <asm/processor-flags.h>
-
-#define BIOSSEG		0x0f000
-
-#define CPU_086		0
-#define CPU_186		1
-#define CPU_286		2
-#define CPU_386		3
-#define CPU_486		4
-#define CPU_586		5
-
-/*
- * Return values for the 'vm86()' system call
- */
-#define VM86_TYPE(retval)	((retval) & 0xff)
-#define VM86_ARG(retval)	((retval) >> 8)
-
-#define VM86_SIGNAL	0	/* return due to signal */
-#define VM86_UNKNOWN	1	/* unhandled GP fault
-				   - IO-instruction or similar */
-#define VM86_INTx	2	/* int3/int x instruction (ARG = x) */
-#define VM86_STI	3	/* sti/popf/iret instruction enabled
-				   virtual interrupts */
-
-/*
- * Additional return values when invoking new vm86()
- */
-#define VM86_PICRETURN	4	/* return due to pending PIC request */
-#define VM86_TRAP	6	/* return due to DOS-debugger request */
-
-/*
- * function codes when invoking new vm86()
- */
-#define VM86_PLUS_INSTALL_CHECK	0
-#define VM86_ENTER		1
-#define VM86_ENTER_NO_BYPASS	2
-#define	VM86_REQUEST_IRQ	3
-#define VM86_FREE_IRQ		4
-#define VM86_GET_IRQ_BITS	5
-#define VM86_GET_AND_RESET_IRQ	6
-
-/*
- * This is the stack-layout seen by the user space program when we have
- * done a translation of "SAVE_ALL" from vm86 mode. The real kernel layout
- * is 'kernel_vm86_regs' (see below).
- */
-
-struct vm86_regs {
-/*
- * normal regs, with special meaning for the segment descriptors..
- */
-	long ebx;
-	long ecx;
-	long edx;
-	long esi;
-	long edi;
-	long ebp;
-	long eax;
-	long __null_ds;
-	long __null_es;
-	long __null_fs;
-	long __null_gs;
-	long orig_eax;
-	long eip;
-	unsigned short cs, __csh;
-	long eflags;
-	long esp;
-	unsigned short ss, __ssh;
-/*
- * these are specific to v86 mode:
- */
-	unsigned short es, __esh;
-	unsigned short ds, __dsh;
-	unsigned short fs, __fsh;
-	unsigned short gs, __gsh;
-};
-
-struct revectored_struct {
-	unsigned long __map[8];			/* 256 bits */
-};
-
-struct vm86_struct {
-	struct vm86_regs regs;
-	unsigned long flags;
-	unsigned long screen_bitmap;
-	unsigned long cpu_type;
-	struct revectored_struct int_revectored;
-	struct revectored_struct int21_revectored;
-};
-
-/*
- * flags masks
- */
-#define VM86_SCREEN_BITMAP	0x0001
-
-struct vm86plus_info_struct {
-	unsigned long force_return_for_pic:1;
-	unsigned long vm86dbg_active:1;       /* for debugger */
-	unsigned long vm86dbg_TFpendig:1;     /* for debugger */
-	unsigned long unused:28;
-	unsigned long is_vm86pus:1;	      /* for vm86 internal use */
-	unsigned char vm86dbg_intxxtab[32];   /* for debugger */
-};
-struct vm86plus_struct {
-	struct vm86_regs regs;
-	unsigned long flags;
-	unsigned long screen_bitmap;
-	unsigned long cpu_type;
-	struct revectored_struct int_revectored;
-	struct revectored_struct int21_revectored;
-	struct vm86plus_info_struct vm86plus;
-};
-
-#ifdef __KERNEL__
-
-#include <asm/ptrace.h>
-
-/*
- * This is the (kernel) stack-layout when we have done a "SAVE_ALL" from vm86
- * mode - the main change is that the old segment descriptors aren't
- * useful any more and are forced to be zero by the kernel (and the
- * hardware when a trap occurs), and the real segment descriptors are
- * at the end of the structure. Look at ptrace.h to see the "normal"
- * setup. For user space layout see 'struct vm86_regs' above.
- */
-
-struct kernel_vm86_regs {
-/*
- * normal regs, with special meaning for the segment descriptors..
- */
-	struct pt_regs pt;
-/*
- * these are specific to v86 mode:
- */
-	unsigned short es, __esh;
-	unsigned short ds, __dsh;
-	unsigned short fs, __fsh;
-	unsigned short gs, __gsh;
-};
-
-struct kernel_vm86_struct {
-	struct kernel_vm86_regs regs;
-/*
- * the below part remains on the kernel stack while we are in VM86 mode.
- * 'tss.esp0' then contains the address of VM86_TSS_ESP0 below, and when we
- * get forced back from VM86, the CPU and "SAVE_ALL" will restore the above
- * 'struct kernel_vm86_regs' with the then actual values.
- * Therefore, pt_regs in fact points to a complete 'kernel_vm86_struct'
- * in kernelspace, hence we need not reget the data from userspace.
- */
-#define VM86_TSS_ESP0 flags
-	unsigned long flags;
-	unsigned long screen_bitmap;
-	unsigned long cpu_type;
-	struct revectored_struct int_revectored;
-	struct revectored_struct int21_revectored;
-	struct vm86plus_info_struct vm86plus;
-	struct pt_regs *regs32;   /* here we save the pointer to the old regs */
-/*
- * The below is not part of the structure, but the stack layout continues
- * this way. In front of 'return-eip' may be some data, depending on
- * compilation, so we don't rely on this and save the pointer to 'oldregs'
- * in 'regs32' above.
- * However, with GCC-2.7.2 and the current CFLAGS you see exactly this:
-
-	long return-eip;        from call to vm86()
-	struct pt_regs oldregs;  user space registers as saved by syscall
- */
-};
-
-#ifdef CONFIG_VM86
-
-void handle_vm86_fault(struct kernel_vm86_regs *, long);
-int handle_vm86_trap(struct kernel_vm86_regs *, long, int);
-struct pt_regs *save_v86_state(struct kernel_vm86_regs *);
-
-struct task_struct;
-void release_vm86_irqs(struct task_struct *);
-
-#else
-
-#define handle_vm86_fault(a, b)
-#define release_vm86_irqs(a)
-
-static inline int handle_vm86_trap(struct kernel_vm86_regs *a, long b, int c)
-{
-	return 0;
-}
-
-#endif /* CONFIG_VM86 */
-
-#endif /* __KERNEL__ */
-
-#endif /* ASM_X86__VM86_H */
diff --git a/include/asm-x86/vmi.h b/include/asm-x86/vmi.h
deleted file mode 100644
index b7c0dea119fe..000000000000
--- a/include/asm-x86/vmi.h
+++ /dev/null
@@ -1,263 +0,0 @@
-/*
- * VMI interface definition
- *
- * Copyright (C) 2005, VMware, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Maintained by: Zachary Amsden zach@vmware.com
- *
- */
-#include <linux/types.h>
-
-/*
- *---------------------------------------------------------------------
- *
- *  VMI Option ROM API
- *
- *---------------------------------------------------------------------
- */
-#define VMI_SIGNATURE 0x696d5663   /* "cVmi" */
-
-#define PCI_VENDOR_ID_VMWARE            0x15AD
-#define PCI_DEVICE_ID_VMWARE_VMI        0x0801
-
-/*
- * We use two version numbers for compatibility, with the major
- * number signifying interface breakages, and the minor number
- * interface extensions.
- */
-#define VMI_API_REV_MAJOR       3
-#define VMI_API_REV_MINOR       0
-
-#define VMI_CALL_CPUID			0
-#define VMI_CALL_WRMSR			1
-#define VMI_CALL_RDMSR			2
-#define VMI_CALL_SetGDT			3
-#define VMI_CALL_SetLDT			4
-#define VMI_CALL_SetIDT			5
-#define VMI_CALL_SetTR			6
-#define VMI_CALL_GetGDT			7
-#define VMI_CALL_GetLDT			8
-#define VMI_CALL_GetIDT			9
-#define VMI_CALL_GetTR			10
-#define VMI_CALL_WriteGDTEntry		11
-#define VMI_CALL_WriteLDTEntry		12
-#define VMI_CALL_WriteIDTEntry		13
-#define VMI_CALL_UpdateKernelStack	14
-#define VMI_CALL_SetCR0			15
-#define VMI_CALL_SetCR2			16
-#define VMI_CALL_SetCR3			17
-#define VMI_CALL_SetCR4			18
-#define VMI_CALL_GetCR0			19
-#define VMI_CALL_GetCR2			20
-#define VMI_CALL_GetCR3			21
-#define VMI_CALL_GetCR4			22
-#define VMI_CALL_WBINVD			23
-#define VMI_CALL_SetDR			24
-#define VMI_CALL_GetDR			25
-#define VMI_CALL_RDPMC			26
-#define VMI_CALL_RDTSC			27
-#define VMI_CALL_CLTS			28
-#define VMI_CALL_EnableInterrupts	29
-#define VMI_CALL_DisableInterrupts	30
-#define VMI_CALL_GetInterruptMask	31
-#define VMI_CALL_SetInterruptMask	32
-#define VMI_CALL_IRET			33
-#define VMI_CALL_SYSEXIT		34
-#define VMI_CALL_Halt			35
-#define VMI_CALL_Reboot			36
-#define VMI_CALL_Shutdown		37
-#define VMI_CALL_SetPxE			38
-#define VMI_CALL_SetPxELong		39
-#define VMI_CALL_UpdatePxE		40
-#define VMI_CALL_UpdatePxELong		41
-#define VMI_CALL_MachineToPhysical	42
-#define VMI_CALL_PhysicalToMachine	43
-#define VMI_CALL_AllocatePage		44
-#define VMI_CALL_ReleasePage		45
-#define VMI_CALL_InvalPage		46
-#define VMI_CALL_FlushTLB		47
-#define VMI_CALL_SetLinearMapping	48
-
-#define VMI_CALL_SetIOPLMask		61
-#define VMI_CALL_SetInitialAPState	62
-#define VMI_CALL_APICWrite		63
-#define VMI_CALL_APICRead		64
-#define VMI_CALL_IODelay		65
-#define VMI_CALL_SetLazyMode		73
-
-/*
- *---------------------------------------------------------------------
- *
- * MMU operation flags
- *
- *---------------------------------------------------------------------
- */
-
-/* Flags used by VMI_{Allocate|Release}Page call */
-#define VMI_PAGE_PAE             0x10  /* Allocate PAE shadow */
-#define VMI_PAGE_CLONE           0x20  /* Clone from another shadow */
-#define VMI_PAGE_ZEROED          0x40  /* Page is pre-zeroed */
-
-
-/* Flags shared by Allocate|Release Page and PTE updates */
-#define VMI_PAGE_PT              0x01
-#define VMI_PAGE_PD              0x02
-#define VMI_PAGE_PDP             0x04
-#define VMI_PAGE_PML4            0x08
-
-#define VMI_PAGE_NORMAL          0x00 /* for debugging */
-
-/* Flags used by PTE updates */
-#define VMI_PAGE_CURRENT_AS      0x10 /* implies VMI_PAGE_VA_MASK is valid */
-#define VMI_PAGE_DEFER           0x20 /* may queue update until TLB inval */
-#define VMI_PAGE_VA_MASK         0xfffff000
-
-#ifdef CONFIG_X86_PAE
-#define VMI_PAGE_L1		(VMI_PAGE_PT | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
-#define VMI_PAGE_L2		(VMI_PAGE_PD | VMI_PAGE_PAE | VMI_PAGE_ZEROED)
-#else
-#define VMI_PAGE_L1		(VMI_PAGE_PT | VMI_PAGE_ZEROED)
-#define VMI_PAGE_L2		(VMI_PAGE_PD | VMI_PAGE_ZEROED)
-#endif
-
-/* Flags used by VMI_FlushTLB call */
-#define VMI_FLUSH_TLB            0x01
-#define VMI_FLUSH_GLOBAL         0x02
-
-/*
- *---------------------------------------------------------------------
- *
- *  VMI relocation definitions for ROM call get_reloc
- *
- *---------------------------------------------------------------------
- */
-
-/* VMI Relocation types */
-#define VMI_RELOCATION_NONE     0
-#define VMI_RELOCATION_CALL_REL 1
-#define VMI_RELOCATION_JUMP_REL 2
-#define VMI_RELOCATION_NOP	3
-
-#ifndef __ASSEMBLY__
-struct vmi_relocation_info {
-	unsigned char           *eip;
-	unsigned char           type;
-	unsigned char           reserved[3];
-};
-#endif
-
-
-/*
- *---------------------------------------------------------------------
- *
- *  Generic ROM structures and definitions
- *
- *---------------------------------------------------------------------
- */
-
-#ifndef __ASSEMBLY__
-
-struct vrom_header {
-	u16     rom_signature;  /* option ROM signature */
-	u8      rom_length;     /* ROM length in 512 byte chunks */
-	u8      rom_entry[4];   /* 16-bit code entry point */
-	u8      rom_pad0;       /* 4-byte align pad */
-	u32     vrom_signature; /* VROM identification signature */
-	u8      api_version_min;/* Minor version of API */
-	u8      api_version_maj;/* Major version of API */
-	u8      jump_slots;     /* Number of jump slots */
-	u8      reserved1;      /* Reserved for expansion */
-	u32     virtual_top;    /* Hypervisor virtual address start */
-	u16     reserved2;      /* Reserved for expansion */
-	u16	license_offs;	/* Offset to License string */
-	u16     pci_header_offs;/* Offset to PCI OPROM header */
-	u16     pnp_header_offs;/* Offset to PnP OPROM header */
-	u32     rom_pad3;       /* PnP reserverd / VMI reserved */
-	u8      reserved[96];   /* Reserved for headers */
-	char    vmi_init[8];    /* VMI_Init jump point */
-	char    get_reloc[8];   /* VMI_GetRelocationInfo jump point */
-} __attribute__((packed));
-
-struct pnp_header {
-	char sig[4];
-	char rev;
-	char size;
-	short next;
-	short res;
-	long devID;
-	unsigned short manufacturer_offset;
-	unsigned short product_offset;
-} __attribute__((packed));
-
-struct pci_header {
-	char sig[4];
-	short vendorID;
-	short deviceID;
-	short vpdData;
-	short size;
-	char rev;
-	char class;
-	char subclass;
-	char interface;
-	short chunks;
-	char rom_version_min;
-	char rom_version_maj;
-	char codetype;
-	char lastRom;
-	short reserved;
-} __attribute__((packed));
-
-/* Function prototypes for bootstrapping */
-extern void vmi_init(void);
-extern void vmi_bringup(void);
-extern void vmi_apply_boot_page_allocations(void);
-
-/* State needed to start an application processor in an SMP system. */
-struct vmi_ap_state {
-	u32 cr0;
-	u32 cr2;
-	u32 cr3;
-	u32 cr4;
-
-	u64 efer;
-
-	u32 eip;
-	u32 eflags;
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 edx;
-	u32 esp;
-	u32 ebp;
-	u32 esi;
-	u32 edi;
-	u16 cs;
-	u16 ss;
-	u16 ds;
-	u16 es;
-	u16 fs;
-	u16 gs;
-	u16 ldtr;
-
-	u16 gdtr_limit;
-	u32 gdtr_base;
-	u32 idtr_base;
-	u16 idtr_limit;
-};
-
-#endif
diff --git a/include/asm-x86/vmi_time.h b/include/asm-x86/vmi_time.h
deleted file mode 100644
index b2d39e6a08b7..000000000000
--- a/include/asm-x86/vmi_time.h
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * VMI Time wrappers
- *
- * Copyright (C) 2006, VMware, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- *
- * Send feedback to dhecht@vmware.com
- *
- */
-
-#ifndef ASM_X86__VMI_TIME_H
-#define ASM_X86__VMI_TIME_H
-
-/*
- * Raw VMI call indices for timer functions
- */
-#define VMI_CALL_GetCycleFrequency	66
-#define VMI_CALL_GetCycleCounter	67
-#define VMI_CALL_SetAlarm		68
-#define VMI_CALL_CancelAlarm		69
-#define VMI_CALL_GetWallclockTime	70
-#define VMI_CALL_WallclockUpdated	71
-
-/* Cached VMI timer operations */
-extern struct vmi_timer_ops {
-	u64 (*get_cycle_frequency)(void);
-	u64 (*get_cycle_counter)(int);
-	u64 (*get_wallclock)(void);
-	int (*wallclock_updated)(void);
-	void (*set_alarm)(u32 flags, u64 expiry, u64 period);
-	void (*cancel_alarm)(u32 flags);
-} vmi_timer_ops;
-
-/* Prototypes */
-extern void __init vmi_time_init(void);
-extern unsigned long vmi_get_wallclock(void);
-extern int vmi_set_wallclock(unsigned long now);
-extern unsigned long long vmi_sched_clock(void);
-extern unsigned long vmi_tsc_khz(void);
-
-#ifdef CONFIG_X86_LOCAL_APIC
-extern void __devinit vmi_time_bsp_init(void);
-extern void __devinit vmi_time_ap_init(void);
-#endif
-
-/*
- * When run under a hypervisor, a vcpu is always in one of three states:
- * running, halted, or ready.  The vcpu is in the 'running' state if it
- * is executing.  When the vcpu executes the halt interface, the vcpu
- * enters the 'halted' state and remains halted until there is some work
- * pending for the vcpu (e.g. an alarm expires, host I/O completes on
- * behalf of virtual I/O).  At this point, the vcpu enters the 'ready'
- * state (waiting for the hypervisor to reschedule it).  Finally, at any
- * time when the vcpu is not in the 'running' state nor the 'halted'
- * state, it is in the 'ready' state.
- *
- * Real time is advances while the vcpu is 'running', 'ready', or
- * 'halted'.  Stolen time is the time in which the vcpu is in the
- * 'ready' state.  Available time is the remaining time -- the vcpu is
- * either 'running' or 'halted'.
- *
- * All three views of time are accessible through the VMI cycle
- * counters.
- */
-
-/* The cycle counters. */
-#define VMI_CYCLES_REAL         0
-#define VMI_CYCLES_AVAILABLE    1
-#define VMI_CYCLES_STOLEN       2
-
-/* The alarm interface 'flags' bits */
-#define VMI_ALARM_COUNTERS      2
-
-#define VMI_ALARM_COUNTER_MASK  0x000000ff
-
-#define VMI_ALARM_WIRED_IRQ0    0x00000000
-#define VMI_ALARM_WIRED_LVTT    0x00010000
-
-#define VMI_ALARM_IS_ONESHOT    0x00000000
-#define VMI_ALARM_IS_PERIODIC   0x00000100
-
-#define CONFIG_VMI_ALARM_HZ	100
-
-#endif /* ASM_X86__VMI_TIME_H */
diff --git a/include/asm-x86/voyager.h b/include/asm-x86/voyager.h
deleted file mode 100644
index 9c811d2e6f91..000000000000
--- a/include/asm-x86/voyager.h
+++ /dev/null
@@ -1,528 +0,0 @@
-/* Copyright (C) 1999,2001
- *
- * Author: J.E.J.Bottomley@HansenPartnership.com
- *
- * Standard include definitions for the NCR Voyager system */
-
-#undef	VOYAGER_DEBUG
-#undef	VOYAGER_CAT_DEBUG
-
-#ifdef VOYAGER_DEBUG
-#define VDEBUG(x)	printk x
-#else
-#define VDEBUG(x)
-#endif
-
-/* There are three levels of voyager machine: 3,4 and 5. The rule is
- * if it's less than 3435 it's a Level 3 except for a 3360 which is
- * a level 4.  A 3435 or above is a Level 5 */
-#define VOYAGER_LEVEL5_AND_ABOVE	0x3435
-#define VOYAGER_LEVEL4			0x3360
-
-/* The L4 DINO ASIC */
-#define VOYAGER_DINO			0x43
-
-/* voyager ports in standard I/O space */
-#define VOYAGER_MC_SETUP	0x96
-
-
-#define	VOYAGER_CAT_CONFIG_PORT			0x97
-#	define VOYAGER_CAT_DESELECT		0xff
-#define VOYAGER_SSPB_RELOCATION_PORT		0x98
-
-/* Valid CAT controller commands */
-/* start instruction register cycle */
-#define VOYAGER_CAT_IRCYC			0x01
-/* start data register cycle */
-#define VOYAGER_CAT_DRCYC			0x02
-/* move to execute state */
-#define VOYAGER_CAT_RUN				0x0F
-/* end operation */
-#define VOYAGER_CAT_END				0x80
-/* hold in idle state */
-#define VOYAGER_CAT_HOLD			0x90
-/* single step an "intest" vector */
-#define VOYAGER_CAT_STEP			0xE0
-/* return cat controller to CLEMSON mode */
-#define VOYAGER_CAT_CLEMSON			0xFF
-
-/* the default cat command header */
-#define VOYAGER_CAT_HEADER			0x7F
-
-/* the range of possible CAT module ids in the system */
-#define VOYAGER_MIN_MODULE			0x10
-#define VOYAGER_MAX_MODULE			0x1f
-
-/* The voyager registers per asic */
-#define VOYAGER_ASIC_ID_REG			0x00
-#define VOYAGER_ASIC_TYPE_REG			0x01
-/* the sub address registers can be made auto incrementing on reads */
-#define VOYAGER_AUTO_INC_REG			0x02
-#	define VOYAGER_AUTO_INC			0x04
-#	define VOYAGER_NO_AUTO_INC		0xfb
-#define VOYAGER_SUBADDRDATA			0x03
-#define VOYAGER_SCANPATH			0x05
-#	define VOYAGER_CONNECT_ASIC		0x01
-#	define VOYAGER_DISCONNECT_ASIC		0xfe
-#define VOYAGER_SUBADDRLO			0x06
-#define VOYAGER_SUBADDRHI			0x07
-#define VOYAGER_SUBMODSELECT			0x08
-#define VOYAGER_SUBMODPRESENT			0x09
-
-#define VOYAGER_SUBADDR_LO			0xff
-#define VOYAGER_SUBADDR_HI			0xffff
-
-/* the maximum size of a scan path -- used to form instructions */
-#define VOYAGER_MAX_SCAN_PATH			0x100
-/* the biggest possible register size (in bytes) */
-#define VOYAGER_MAX_REG_SIZE			4
-
-/* Total number of possible modules (including submodules) */
-#define VOYAGER_MAX_MODULES			16
-/* Largest number of asics per module */
-#define VOYAGER_MAX_ASICS_PER_MODULE		7
-
-/* the CAT asic of each module is always the first one */
-#define VOYAGER_CAT_ID				0
-#define VOYAGER_PSI				0x1a
-
-/* voyager instruction operations and registers */
-#define VOYAGER_READ_CONFIG			0x1
-#define VOYAGER_WRITE_CONFIG			0x2
-#define VOYAGER_BYPASS				0xff
-
-typedef struct voyager_asic {
-	__u8	asic_addr;	/* ASIC address; Level 4 */
-	__u8	asic_type;      /* ASIC type */
-	__u8	asic_id;	/* ASIC id */
-	__u8	jtag_id[4];	/* JTAG id */
-	__u8	asic_location;	/* Location within scan path; start w/ 0 */
-	__u8	bit_location;	/* Location within bit stream; start w/ 0 */
-	__u8	ireg_length;	/* Instruction register length */
-	__u16	subaddr;	/* Amount of sub address space */
-	struct voyager_asic *next;	/* Next asic in linked list */
-} voyager_asic_t;
-
-typedef struct voyager_module {
-	__u8	module_addr;		/* Module address */
-	__u8	scan_path_connected;	/* Scan path connected */
-	__u16   ee_size;		/* Size of the EEPROM */
-	__u16   num_asics;		/* Number of Asics */
-	__u16   inst_bits;		/* Instruction bits in the scan path */
-	__u16   largest_reg;		/* Largest register in the scan path */
-	__u16   smallest_reg;		/* Smallest register in the scan path */
-	voyager_asic_t   *asic;		/* First ASIC in scan path (CAT_I) */
-	struct   voyager_module *submodule;	/* Submodule pointer */
-	struct   voyager_module *next;		/* Next module in linked list */
-} voyager_module_t;
-
-typedef struct voyager_eeprom_hdr {
-	 __u8  module_id[4];
-	 __u8  version_id;
-	 __u8  config_id;
-	 __u16 boundry_id;	/* boundary scan id */
-	 __u16 ee_size;		/* size of EEPROM */
-	 __u8  assembly[11];	/* assembly # */
-	 __u8  assembly_rev;	/* assembly rev */
-	 __u8  tracer[4];	/* tracer number */
-	 __u16 assembly_cksum;	/* asm checksum */
-	 __u16 power_consump;	/* pwr requirements */
-	 __u16 num_asics;	/* number of asics */
-	 __u16 bist_time;	/* min. bist time */
-	 __u16 err_log_offset;	/* error log offset */
-	 __u16 scan_path_offset;/* scan path offset */
-	 __u16 cct_offset;
-	 __u16 log_length;	/* length of err log */
-	 __u16 xsum_end;	/* offset to end of
-				   checksum */
-	 __u8  reserved[4];
-	 __u8  sflag;		/* starting sentinal */
-	 __u8  part_number[13];	/* prom part number */
-	 __u8  version[10];	/* version number */
-	 __u8  signature[8];
-	 __u16 eeprom_chksum;
-	 __u32  data_stamp_offset;
-	 __u8  eflag ;		 /* ending sentinal */
-} __attribute__((packed)) voyager_eprom_hdr_t;
-
-
-
-#define VOYAGER_EPROM_SIZE_OFFSET				\
-	((__u16)(&(((voyager_eprom_hdr_t *)0)->ee_size)))
-#define VOYAGER_XSUM_END_OFFSET		0x2a
-
-/* the following three definitions are for internal table layouts
- * in the module EPROMs.  We really only care about the IDs and
- * offsets */
-typedef struct voyager_sp_table {
-	__u8 asic_id;
-	__u8 bypass_flag;
-	__u16 asic_data_offset;
-	__u16 config_data_offset;
-} __attribute__((packed)) voyager_sp_table_t;
-
-typedef struct voyager_jtag_table {
-	__u8 icode[4];
-	__u8 runbist[4];
-	__u8 intest[4];
-	__u8 samp_preld[4];
-	__u8 ireg_len;
-} __attribute__((packed)) voyager_jtt_t;
-
-typedef struct voyager_asic_data_table {
-	__u8 jtag_id[4];
-	__u16 length_bsr;
-	__u16 length_bist_reg;
-	__u32 bist_clk;
-	__u16 subaddr_bits;
-	__u16 seed_bits;
-	__u16 sig_bits;
-	__u16 jtag_offset;
-} __attribute__((packed)) voyager_at_t;
-
-/* Voyager Interrupt Controller (VIC) registers */
-
-/* Base to add to Cross Processor Interrupts (CPIs) when triggering
- * the CPU IRQ line */
-/* register defines for the WCBICs (one per processor) */
-#define VOYAGER_WCBIC0	0x41		/* bus A node P1 processor 0 */
-#define VOYAGER_WCBIC1	0x49		/* bus A node P1 processor 1 */
-#define VOYAGER_WCBIC2	0x51		/* bus A node P2 processor 0 */
-#define VOYAGER_WCBIC3	0x59		/* bus A node P2 processor 1 */
-#define VOYAGER_WCBIC4	0x61		/* bus B node P1 processor 0 */
-#define VOYAGER_WCBIC5	0x69		/* bus B node P1 processor 1 */
-#define VOYAGER_WCBIC6	0x71		/* bus B node P2 processor 0 */
-#define VOYAGER_WCBIC7	0x79		/* bus B node P2 processor 1 */
-
-
-/* top of memory registers */
-#define VOYAGER_WCBIC_TOM_L	0x4
-#define VOYAGER_WCBIC_TOM_H	0x5
-
-/* register defines for Voyager Memory Contol (VMC)
- * these are present on L4 machines only */
-#define	VOYAGER_VMC1		0x81
-#define VOYAGER_VMC2		0x91
-#define VOYAGER_VMC3		0xa1
-#define VOYAGER_VMC4		0xb1
-
-/* VMC Ports */
-#define VOYAGER_VMC_MEMORY_SETUP	0x9
-#	define VMC_Interleaving		0x01
-#	define VMC_4Way			0x02
-#	define VMC_EvenCacheLines	0x04
-#	define VMC_HighLine		0x08
-#	define VMC_Start0_Enable	0x20
-#	define VMC_Start1_Enable	0x40
-#	define VMC_Vremap		0x80
-#define VOYAGER_VMC_BANK_DENSITY	0xa
-#	define	VMC_BANK_EMPTY		0
-#	define	VMC_BANK_4MB		1
-#	define	VMC_BANK_16MB		2
-#	define	VMC_BANK_64MB		3
-#	define	VMC_BANK0_MASK		0x03
-#	define	VMC_BANK1_MASK		0x0C
-#	define	VMC_BANK2_MASK		0x30
-#	define	VMC_BANK3_MASK		0xC0
-
-/* Magellan Memory Controller (MMC) defines - present on L5 */
-#define VOYAGER_MMC_ASIC_ID		1
-/* the two memory modules corresponding to memory cards in the system */
-#define VOYAGER_MMC_MEMORY0_MODULE	0x14
-#define VOYAGER_MMC_MEMORY1_MODULE	0x15
-/* the Magellan Memory Address (MMA) defines */
-#define VOYAGER_MMA_ASIC_ID		2
-
-/* Submodule number for the Quad Baseboard */
-#define VOYAGER_QUAD_BASEBOARD		1
-
-/* ASIC defines for the Quad Baseboard */
-#define VOYAGER_QUAD_QDATA0		1
-#define VOYAGER_QUAD_QDATA1		2
-#define VOYAGER_QUAD_QABC		3
-
-/* Useful areas in extended CMOS */
-#define VOYAGER_PROCESSOR_PRESENT_MASK	0x88a
-#define VOYAGER_MEMORY_CLICKMAP		0xa23
-#define VOYAGER_DUMP_LOCATION		0xb1a
-
-/* SUS In Control bit - used to tell SUS that we don't need to be
- * babysat anymore */
-#define VOYAGER_SUS_IN_CONTROL_PORT	0x3ff
-#	define VOYAGER_IN_CONTROL_FLAG	0x80
-
-/* Voyager PSI defines */
-#define VOYAGER_PSI_STATUS_REG		0x08
-#	define PSI_DC_FAIL		0x01
-#	define PSI_MON			0x02
-#	define PSI_FAULT		0x04
-#	define PSI_ALARM		0x08
-#	define PSI_CURRENT		0x10
-#	define PSI_DVM			0x20
-#	define PSI_PSCFAULT		0x40
-#	define PSI_STAT_CHG		0x80
-
-#define VOYAGER_PSI_SUPPLY_REG		0x8000
-	/* read */
-#	define PSI_FAIL_DC		0x01
-#	define PSI_FAIL_AC		0x02
-#	define PSI_MON_INT		0x04
-#	define PSI_SWITCH_OFF		0x08
-#	define PSI_HX_OFF		0x10
-#	define PSI_SECURITY		0x20
-#	define PSI_CMOS_BATT_LOW	0x40
-#	define PSI_CMOS_BATT_FAIL	0x80
-	/* write */
-#	define PSI_CLR_SWITCH_OFF	0x13
-#	define PSI_CLR_HX_OFF		0x14
-#	define PSI_CLR_CMOS_BATT_FAIL	0x17
-
-#define VOYAGER_PSI_MASK		0x8001
-#	define PSI_MASK_MASK		0x10
-
-#define VOYAGER_PSI_AC_FAIL_REG		0x8004
-#define	AC_FAIL_STAT_CHANGE		0x80
-
-#define VOYAGER_PSI_GENERAL_REG		0x8007
-	/* read */
-#	define PSI_SWITCH_ON		0x01
-#	define PSI_SWITCH_ENABLED	0x02
-#	define PSI_ALARM_ENABLED	0x08
-#	define PSI_SECURE_ENABLED	0x10
-#	define PSI_COLD_RESET		0x20
-#	define PSI_COLD_START		0x80
-	/* write */
-#	define PSI_POWER_DOWN		0x10
-#	define PSI_SWITCH_DISABLE	0x01
-#	define PSI_SWITCH_ENABLE	0x11
-#	define PSI_CLEAR		0x12
-#	define PSI_ALARM_DISABLE	0x03
-#	define PSI_ALARM_ENABLE		0x13
-#	define PSI_CLEAR_COLD_RESET	0x05
-#	define PSI_SET_COLD_RESET	0x15
-#	define PSI_CLEAR_COLD_START	0x07
-#	define PSI_SET_COLD_START	0x17
-
-
-
-struct voyager_bios_info {
-	__u8	len;
-	__u8	major;
-	__u8	minor;
-	__u8	debug;
-	__u8	num_classes;
-	__u8	class_1;
-	__u8	class_2;
-};
-
-/* The following structures and definitions are for the Kernel/SUS
- * interface these are needed to find out how SUS initialised any Quad
- * boards in the system */
-
-#define	NUMBER_OF_MC_BUSSES	2
-#define SLOTS_PER_MC_BUS	8
-#define MAX_CPUS                16      /* 16 way CPU system */
-#define MAX_PROCESSOR_BOARDS	4	/* 4 processor slot system */
-#define MAX_CACHE_LEVELS	4	/* # of cache levels supported */
-#define MAX_SHARED_CPUS		4	/* # of CPUs that can share a LARC */
-#define NUMBER_OF_POS_REGS	8
-
-typedef struct {
-	__u8	MC_Slot;
-	__u8	POS_Values[NUMBER_OF_POS_REGS];
-} __attribute__((packed)) MC_SlotInformation_t;
-
-struct QuadDescription {
-	__u8  Type;	/* for type 0 (DYADIC or MONADIC) all fields
-			 * will be zero except for slot */
-	__u8 StructureVersion;
-	__u32 CPI_BaseAddress;
-	__u32  LARC_BankSize;
-	__u32 LocalMemoryStateBits;
-	__u8  Slot; /* Processor slots 1 - 4 */
-} __attribute__((packed));
-
-struct ProcBoardInfo {
-	__u8 Type;
-	__u8 StructureVersion;
-	__u8 NumberOfBoards;
-	struct QuadDescription QuadData[MAX_PROCESSOR_BOARDS];
-} __attribute__((packed));
-
-struct CacheDescription {
-	__u8 Level;
-	__u32 TotalSize;
-	__u16 LineSize;
-	__u8  Associativity;
-	__u8  CacheType;
-	__u8  WriteType;
-	__u8  Number_CPUs_SharedBy;
-	__u8  Shared_CPUs_Hardware_IDs[MAX_SHARED_CPUS];
-
-} __attribute__((packed));
-
-struct CPU_Description {
-	__u8 CPU_HardwareId;
-	char *FRU_String;
-	__u8 NumberOfCacheLevels;
-	struct CacheDescription CacheLevelData[MAX_CACHE_LEVELS];
-} __attribute__((packed));
-
-struct CPU_Info {
-	__u8 Type;
-	__u8 StructureVersion;
-	__u8 NumberOf_CPUs;
-	struct CPU_Description CPU_Data[MAX_CPUS];
-} __attribute__((packed));
-
-
-/*
- * This structure will be used by SUS and the OS.
- * The assumption about this structure is that no blank space is
- * packed in it by our friend the compiler.
- */
-typedef struct {
-	__u8	Mailbox_SUS;		/* Written to by SUS to give
-					   commands/response to the OS */
-	__u8	Mailbox_OS;		/* Written to by the OS to give
-					   commands/response to SUS */
-	__u8	SUS_MailboxVersion;	/* Tells the OS which iteration of the
-					   interface SUS supports */
-	__u8	OS_MailboxVersion;	/* Tells SUS which iteration of the
-					   interface the OS supports */
-	__u32	OS_Flags;		/* Flags set by the OS as info for
-					   SUS */
-	__u32	SUS_Flags;		/* Flags set by SUS as info
-					   for the OS */
-	__u32	WatchDogPeriod;		/* Watchdog period (in seconds) which
-					   the DP uses to see if the OS
-					   is dead */
-	__u32	WatchDogCount;		/* Updated by the OS on every tic. */
-	__u32	MemoryFor_SUS_ErrorLog;	/* Flat 32 bit address which tells SUS
-					   where to stuff the SUS error log
-					   on a dump */
-	MC_SlotInformation_t MC_SlotInfo[NUMBER_OF_MC_BUSSES*SLOTS_PER_MC_BUS];
-					/* Storage for MCA POS data */
-	/* All new SECOND_PASS_INTERFACE fields added from this point */
-	struct ProcBoardInfo    *BoardData;
-	struct CPU_Info         *CPU_Data;
-	/* All new fields must be added from this point */
-} Voyager_KernelSUS_Mbox_t;
-
-/* structure for finding the right memory address to send a QIC CPI to */
-struct voyager_qic_cpi {
-	/* Each cache line (32 bytes) can trigger a cpi.  The cpi
-	 * read/write may occur anywhere in the cache line---pick the
-	 * middle to be safe */
-	struct  {
-		__u32 pad1[3];
-		__u32 cpi;
-		__u32 pad2[4];
-	} qic_cpi[8];
-};
-
-struct voyager_status {
-	__u32	power_fail:1;
-	__u32	switch_off:1;
-	__u32	request_from_kernel:1;
-};
-
-struct voyager_psi_regs {
-	__u8 cat_id;
-	__u8 cat_dev;
-	__u8 cat_control;
-	__u8 subaddr;
-	__u8 dummy4;
-	__u8 checkbit;
-	__u8 subaddr_low;
-	__u8 subaddr_high;
-	__u8 intstatus;
-	__u8 stat1;
-	__u8 stat3;
-	__u8 fault;
-	__u8 tms;
-	__u8 gen;
-	__u8 sysconf;
-	__u8 dummy15;
-};
-
-struct voyager_psi_subregs {
-	__u8 supply;
-	__u8 mask;
-	__u8 present;
-	__u8 DCfail;
-	__u8 ACfail;
-	__u8 fail;
-	__u8 UPSfail;
-	__u8 genstatus;
-};
-
-struct voyager_psi {
-	struct voyager_psi_regs regs;
-	struct voyager_psi_subregs subregs;
-};
-
-struct voyager_SUS {
-#define	VOYAGER_DUMP_BUTTON_NMI		0x1
-#define VOYAGER_SUS_VALID		0x2
-#define VOYAGER_SYSINT_COMPLETE		0x3
-	__u8	SUS_mbox;
-#define VOYAGER_NO_COMMAND		0x0
-#define VOYAGER_IGNORE_DUMP		0x1
-#define VOYAGER_DO_DUMP			0x2
-#define VOYAGER_SYSINT_HANDSHAKE	0x3
-#define VOYAGER_DO_MEM_DUMP		0x4
-#define VOYAGER_SYSINT_WAS_RECOVERED	0x5
-	__u8	kernel_mbox;
-#define	VOYAGER_MAILBOX_VERSION		0x10
-	__u8	SUS_version;
-	__u8	kernel_version;
-#define VOYAGER_OS_HAS_SYSINT		0x1
-#define VOYAGER_OS_IN_PROGRESS		0x2
-#define VOYAGER_UPDATING_WDPERIOD	0x4
-	__u32	kernel_flags;
-#define VOYAGER_SUS_BOOTING		0x1
-#define VOYAGER_SUS_IN_PROGRESS		0x2
-	__u32	SUS_flags;
-	__u32	watchdog_period;
-	__u32	watchdog_count;
-	__u32	SUS_errorlog;
-	/* lots of system configuration stuff under here */
-};
-
-/* Variables exported by voyager_smp */
-extern __u32 voyager_extended_vic_processors;
-extern __u32 voyager_allowed_boot_processors;
-extern __u32 voyager_quad_processors;
-extern struct voyager_qic_cpi *voyager_quad_cpi_addr[NR_CPUS];
-extern struct voyager_SUS *voyager_SUS;
-
-/* variables exported always */
-extern struct task_struct *voyager_thread;
-extern int voyager_level;
-extern struct voyager_status voyager_status;
-
-/* functions exported by the voyager and voyager_smp modules */
-extern int voyager_cat_readb(__u8 module, __u8 asic, int reg);
-extern void voyager_cat_init(void);
-extern void voyager_detect(struct voyager_bios_info *);
-extern void voyager_trap_init(void);
-extern void voyager_setup_irqs(void);
-extern int voyager_memory_detect(int region, __u32 *addr, __u32 *length);
-extern void voyager_smp_intr_init(void);
-extern __u8 voyager_extended_cmos_read(__u16 cmos_address);
-extern void voyager_smp_dump(void);
-extern void voyager_timer_interrupt(void);
-extern void smp_local_timer_interrupt(void);
-extern void voyager_power_off(void);
-extern void smp_voyager_power_off(void *dummy);
-extern void voyager_restart(void);
-extern void voyager_cat_power_off(void);
-extern void voyager_cat_do_common_interrupt(void);
-extern void voyager_handle_nmi(void);
-/* Commands for the following are */
-#define	VOYAGER_PSI_READ	0
-#define VOYAGER_PSI_WRITE	1
-#define VOYAGER_PSI_SUBREAD	2
-#define VOYAGER_PSI_SUBWRITE	3
-extern void voyager_cat_psi(__u8, __u16, __u8 *);
diff --git a/include/asm-x86/vsyscall.h b/include/asm-x86/vsyscall.h
deleted file mode 100644
index dcd4682413de..000000000000
--- a/include/asm-x86/vsyscall.h
+++ /dev/null
@@ -1,44 +0,0 @@
-#ifndef ASM_X86__VSYSCALL_H
-#define ASM_X86__VSYSCALL_H
-
-enum vsyscall_num {
-	__NR_vgettimeofday,
-	__NR_vtime,
-	__NR_vgetcpu,
-};
-
-#define VSYSCALL_START (-10UL << 20)
-#define VSYSCALL_SIZE 1024
-#define VSYSCALL_END (-2UL << 20)
-#define VSYSCALL_MAPPED_PAGES 1
-#define VSYSCALL_ADDR(vsyscall_nr) (VSYSCALL_START+VSYSCALL_SIZE*(vsyscall_nr))
-
-#ifdef __KERNEL__
-#include <linux/seqlock.h>
-
-#define __section_vgetcpu_mode __attribute__ ((unused, __section__ (".vgetcpu_mode"), aligned(16)))
-#define __section_jiffies __attribute__ ((unused, __section__ (".jiffies"), aligned(16)))
-
-/* Definitions for CONFIG_GENERIC_TIME definitions */
-#define __section_vsyscall_gtod_data __attribute__ \
-	((unused, __section__ (".vsyscall_gtod_data"),aligned(16)))
-#define __section_vsyscall_clock __attribute__ \
-	((unused, __section__ (".vsyscall_clock"),aligned(16)))
-#define __vsyscall_fn \
-	__attribute__ ((unused, __section__(".vsyscall_fn"))) notrace
-
-#define VGETCPU_RDTSCP	1
-#define VGETCPU_LSL	2
-
-extern int __vgetcpu_mode;
-extern volatile unsigned long __jiffies;
-
-/* kernel space (writeable) */
-extern int vgetcpu_mode;
-extern struct timezone sys_tz;
-
-extern void map_vsyscall(void);
-
-#endif /* __KERNEL__ */
-
-#endif /* ASM_X86__VSYSCALL_H */
diff --git a/include/asm-x86/xcr.h b/include/asm-x86/xcr.h
deleted file mode 100644
index f2cba4e79a23..000000000000
--- a/include/asm-x86/xcr.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* -*- linux-c -*- ------------------------------------------------------- *
- *
- *   Copyright 2008 rPath, Inc. - All Rights Reserved
- *
- *   This file is part of the Linux kernel, and is made available under
- *   the terms of the GNU General Public License version 2 or (at your
- *   option) any later version; incorporated herein by reference.
- *
- * ----------------------------------------------------------------------- */
-
-/*
- * asm-x86/xcr.h
- *
- * Definitions for the eXtended Control Register instructions
- */
-
-#ifndef _ASM_X86_XCR_H
-#define _ASM_X86_XCR_H
-
-#define XCR_XFEATURE_ENABLED_MASK	0x00000000
-
-#ifdef __KERNEL__
-# ifndef __ASSEMBLY__
-
-#include <linux/types.h>
-
-static inline u64 xgetbv(u32 index)
-{
-	u32 eax, edx;
-
-	asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
-		     : "=a" (eax), "=d" (edx)
-		     : "c" (index));
-	return eax + ((u64)edx << 32);
-}
-
-static inline void xsetbv(u32 index, u64 value)
-{
-	u32 eax = value;
-	u32 edx = value >> 32;
-
-	asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
-		     : : "a" (eax), "d" (edx), "c" (index));
-}
-
-# endif /* __ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
-#endif /* _ASM_X86_XCR_H */
diff --git a/include/asm-x86/xen/events.h b/include/asm-x86/xen/events.h
deleted file mode 100644
index 8151f5b8b6cb..000000000000
--- a/include/asm-x86/xen/events.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef ASM_X86__XEN__EVENTS_H
-#define ASM_X86__XEN__EVENTS_H
-
-enum ipi_vector {
-	XEN_RESCHEDULE_VECTOR,
-	XEN_CALL_FUNCTION_VECTOR,
-	XEN_CALL_FUNCTION_SINGLE_VECTOR,
-	XEN_SPIN_UNLOCK_VECTOR,
-
-	XEN_NR_IPIS,
-};
-
-static inline int xen_irqs_disabled(struct pt_regs *regs)
-{
-	return raw_irqs_disabled_flags(regs->flags);
-}
-
-static inline void xen_do_IRQ(int irq, struct pt_regs *regs)
-{
-	regs->orig_ax = ~irq;
-	do_IRQ(regs);
-}
-
-#endif /* ASM_X86__XEN__EVENTS_H */
diff --git a/include/asm-x86/xen/grant_table.h b/include/asm-x86/xen/grant_table.h
deleted file mode 100644
index c4baab4d2b68..000000000000
--- a/include/asm-x86/xen/grant_table.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef ASM_X86__XEN__GRANT_TABLE_H
-#define ASM_X86__XEN__GRANT_TABLE_H
-
-#define xen_alloc_vm_area(size)	alloc_vm_area(size)
-#define xen_free_vm_area(area)	free_vm_area(area)
-
-#endif /* ASM_X86__XEN__GRANT_TABLE_H */
diff --git a/include/asm-x86/xen/hypercall.h b/include/asm-x86/xen/hypercall.h
deleted file mode 100644
index 44f4259bee3f..000000000000
--- a/include/asm-x86/xen/hypercall.h
+++ /dev/null
@@ -1,527 +0,0 @@
-/******************************************************************************
- * hypercall.h
- *
- * Linux-specific hypervisor handling.
- *
- * Copyright (c) 2002-2004, K A Fraser
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation; or, when distributed
- * separately from the Linux kernel or incorporated into other
- * software packages, subject to the following license:
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this source file (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy, modify,
- * merge, publish, distribute, sublicense, and/or sell copies of the Software,
- * and to permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- */
-
-#ifndef ASM_X86__XEN__HYPERCALL_H
-#define ASM_X86__XEN__HYPERCALL_H
-
-#include <linux/errno.h>
-#include <linux/string.h>
-
-#include <xen/interface/xen.h>
-#include <xen/interface/sched.h>
-#include <xen/interface/physdev.h>
-
-/*
- * The hypercall asms have to meet several constraints:
- * - Work on 32- and 64-bit.
- *    The two architectures put their arguments in different sets of
- *    registers.
- *
- * - Work around asm syntax quirks
- *    It isn't possible to specify one of the rNN registers in a
- *    constraint, so we use explicit register variables to get the
- *    args into the right place.
- *
- * - Mark all registers as potentially clobbered
- *    Even unused parameters can be clobbered by the hypervisor, so we
- *    need to make sure gcc knows it.
- *
- * - Avoid compiler bugs.
- *    This is the tricky part.  Because x86_32 has such a constrained
- *    register set, gcc versions below 4.3 have trouble generating
- *    code when all the arg registers and memory are trashed by the
- *    asm.  There are syntactically simpler ways of achieving the
- *    semantics below, but they cause the compiler to crash.
- *
- *    The only combination I found which works is:
- *     - assign the __argX variables first
- *     - list all actually used parameters as "+r" (__argX)
- *     - clobber the rest
- *
- * The result certainly isn't pretty, and it really shows up cpp's
- * weakness as as macro language.  Sorry.  (But let's just give thanks
- * there aren't more than 5 arguments...)
- */
-
-extern struct { char _entry[32]; } hypercall_page[];
-
-#define __HYPERCALL		"call hypercall_page+%c[offset]"
-#define __HYPERCALL_ENTRY(x)						\
-	[offset] "i" (__HYPERVISOR_##x * sizeof(hypercall_page[0]))
-
-#ifdef CONFIG_X86_32
-#define __HYPERCALL_RETREG	"eax"
-#define __HYPERCALL_ARG1REG	"ebx"
-#define __HYPERCALL_ARG2REG	"ecx"
-#define __HYPERCALL_ARG3REG	"edx"
-#define __HYPERCALL_ARG4REG	"esi"
-#define __HYPERCALL_ARG5REG	"edi"
-#else
-#define __HYPERCALL_RETREG	"rax"
-#define __HYPERCALL_ARG1REG	"rdi"
-#define __HYPERCALL_ARG2REG	"rsi"
-#define __HYPERCALL_ARG3REG	"rdx"
-#define __HYPERCALL_ARG4REG	"r10"
-#define __HYPERCALL_ARG5REG	"r8"
-#endif
-
-#define __HYPERCALL_DECLS						\
-	register unsigned long __res  asm(__HYPERCALL_RETREG);		\
-	register unsigned long __arg1 asm(__HYPERCALL_ARG1REG) = __arg1; \
-	register unsigned long __arg2 asm(__HYPERCALL_ARG2REG) = __arg2; \
-	register unsigned long __arg3 asm(__HYPERCALL_ARG3REG) = __arg3; \
-	register unsigned long __arg4 asm(__HYPERCALL_ARG4REG) = __arg4; \
-	register unsigned long __arg5 asm(__HYPERCALL_ARG5REG) = __arg5;
-
-#define __HYPERCALL_0PARAM	"=r" (__res)
-#define __HYPERCALL_1PARAM	__HYPERCALL_0PARAM, "+r" (__arg1)
-#define __HYPERCALL_2PARAM	__HYPERCALL_1PARAM, "+r" (__arg2)
-#define __HYPERCALL_3PARAM	__HYPERCALL_2PARAM, "+r" (__arg3)
-#define __HYPERCALL_4PARAM	__HYPERCALL_3PARAM, "+r" (__arg4)
-#define __HYPERCALL_5PARAM	__HYPERCALL_4PARAM, "+r" (__arg5)
-
-#define __HYPERCALL_0ARG()
-#define __HYPERCALL_1ARG(a1)						\
-	__HYPERCALL_0ARG()		__arg1 = (unsigned long)(a1);
-#define __HYPERCALL_2ARG(a1,a2)						\
-	__HYPERCALL_1ARG(a1)		__arg2 = (unsigned long)(a2);
-#define __HYPERCALL_3ARG(a1,a2,a3)					\
-	__HYPERCALL_2ARG(a1,a2)		__arg3 = (unsigned long)(a3);
-#define __HYPERCALL_4ARG(a1,a2,a3,a4)					\
-	__HYPERCALL_3ARG(a1,a2,a3)	__arg4 = (unsigned long)(a4);
-#define __HYPERCALL_5ARG(a1,a2,a3,a4,a5)				\
-	__HYPERCALL_4ARG(a1,a2,a3,a4)	__arg5 = (unsigned long)(a5);
-
-#define __HYPERCALL_CLOBBER5	"memory"
-#define __HYPERCALL_CLOBBER4	__HYPERCALL_CLOBBER5, __HYPERCALL_ARG5REG
-#define __HYPERCALL_CLOBBER3	__HYPERCALL_CLOBBER4, __HYPERCALL_ARG4REG
-#define __HYPERCALL_CLOBBER2	__HYPERCALL_CLOBBER3, __HYPERCALL_ARG3REG
-#define __HYPERCALL_CLOBBER1	__HYPERCALL_CLOBBER2, __HYPERCALL_ARG2REG
-#define __HYPERCALL_CLOBBER0	__HYPERCALL_CLOBBER1, __HYPERCALL_ARG1REG
-
-#define _hypercall0(type, name)						\
-({									\
-	__HYPERCALL_DECLS;						\
-	__HYPERCALL_0ARG();						\
-	asm volatile (__HYPERCALL					\
-		      : __HYPERCALL_0PARAM				\
-		      : __HYPERCALL_ENTRY(name)				\
-		      : __HYPERCALL_CLOBBER0);				\
-	(type)__res;							\
-})
-
-#define _hypercall1(type, name, a1)					\
-({									\
-	__HYPERCALL_DECLS;						\
-	__HYPERCALL_1ARG(a1);						\
-	asm volatile (__HYPERCALL					\
-		      : __HYPERCALL_1PARAM				\
-		      : __HYPERCALL_ENTRY(name)				\
-		      : __HYPERCALL_CLOBBER1);				\
-	(type)__res;							\
-})
-
-#define _hypercall2(type, name, a1, a2)					\
-({									\
-	__HYPERCALL_DECLS;						\
-	__HYPERCALL_2ARG(a1, a2);					\
-	asm volatile (__HYPERCALL					\
-		      : __HYPERCALL_2PARAM				\
-		      : __HYPERCALL_ENTRY(name)				\
-		      : __HYPERCALL_CLOBBER2);				\
-	(type)__res;							\
-})
-
-#define _hypercall3(type, name, a1, a2, a3)				\
-({									\
-	__HYPERCALL_DECLS;						\
-	__HYPERCALL_3ARG(a1, a2, a3);					\
-	asm volatile (__HYPERCALL					\
-		      : __HYPERCALL_3PARAM				\
-		      : __HYPERCALL_ENTRY(name)				\
-		      : __HYPERCALL_CLOBBER3);				\
-	(type)__res;							\
-})
-
-#define _hypercall4(type, name, a1, a2, a3, a4)				\
-({									\
-	__HYPERCALL_DECLS;						\
-	__HYPERCALL_4ARG(a1, a2, a3, a4);				\
-	asm volatile (__HYPERCALL					\
-		      : __HYPERCALL_4PARAM				\
-		      : __HYPERCALL_ENTRY(name)				\
-		      : __HYPERCALL_CLOBBER4);				\
-	(type)__res;							\
-})
-
-#define _hypercall5(type, name, a1, a2, a3, a4, a5)			\
-({									\
-	__HYPERCALL_DECLS;						\
-	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);				\
-	asm volatile (__HYPERCALL					\
-		      : __HYPERCALL_5PARAM				\
-		      : __HYPERCALL_ENTRY(name)				\
-		      : __HYPERCALL_CLOBBER5);				\
-	(type)__res;							\
-})
-
-static inline int
-HYPERVISOR_set_trap_table(struct trap_info *table)
-{
-	return _hypercall1(int, set_trap_table, table);
-}
-
-static inline int
-HYPERVISOR_mmu_update(struct mmu_update *req, int count,
-		      int *success_count, domid_t domid)
-{
-	return _hypercall4(int, mmu_update, req, count, success_count, domid);
-}
-
-static inline int
-HYPERVISOR_mmuext_op(struct mmuext_op *op, int count,
-		     int *success_count, domid_t domid)
-{
-	return _hypercall4(int, mmuext_op, op, count, success_count, domid);
-}
-
-static inline int
-HYPERVISOR_set_gdt(unsigned long *frame_list, int entries)
-{
-	return _hypercall2(int, set_gdt, frame_list, entries);
-}
-
-static inline int
-HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp)
-{
-	return _hypercall2(int, stack_switch, ss, esp);
-}
-
-#ifdef CONFIG_X86_32
-static inline int
-HYPERVISOR_set_callbacks(unsigned long event_selector,
-			 unsigned long event_address,
-			 unsigned long failsafe_selector,
-			 unsigned long failsafe_address)
-{
-	return _hypercall4(int, set_callbacks,
-			   event_selector, event_address,
-			   failsafe_selector, failsafe_address);
-}
-#else  /* CONFIG_X86_64 */
-static inline int
-HYPERVISOR_set_callbacks(unsigned long event_address,
-			unsigned long failsafe_address,
-			unsigned long syscall_address)
-{
-	return _hypercall3(int, set_callbacks,
-			   event_address, failsafe_address,
-			   syscall_address);
-}
-#endif  /* CONFIG_X86_{32,64} */
-
-static inline int
-HYPERVISOR_callback_op(int cmd, void *arg)
-{
-	return _hypercall2(int, callback_op, cmd, arg);
-}
-
-static inline int
-HYPERVISOR_fpu_taskswitch(int set)
-{
-	return _hypercall1(int, fpu_taskswitch, set);
-}
-
-static inline int
-HYPERVISOR_sched_op(int cmd, void *arg)
-{
-	return _hypercall2(int, sched_op_new, cmd, arg);
-}
-
-static inline long
-HYPERVISOR_set_timer_op(u64 timeout)
-{
-	unsigned long timeout_hi = (unsigned long)(timeout>>32);
-	unsigned long timeout_lo = (unsigned long)timeout;
-	return _hypercall2(long, set_timer_op, timeout_lo, timeout_hi);
-}
-
-static inline int
-HYPERVISOR_set_debugreg(int reg, unsigned long value)
-{
-	return _hypercall2(int, set_debugreg, reg, value);
-}
-
-static inline unsigned long
-HYPERVISOR_get_debugreg(int reg)
-{
-	return _hypercall1(unsigned long, get_debugreg, reg);
-}
-
-static inline int
-HYPERVISOR_update_descriptor(u64 ma, u64 desc)
-{
-	return _hypercall4(int, update_descriptor, ma, ma>>32, desc, desc>>32);
-}
-
-static inline int
-HYPERVISOR_memory_op(unsigned int cmd, void *arg)
-{
-	return _hypercall2(int, memory_op, cmd, arg);
-}
-
-static inline int
-HYPERVISOR_multicall(void *call_list, int nr_calls)
-{
-	return _hypercall2(int, multicall, call_list, nr_calls);
-}
-
-static inline int
-HYPERVISOR_update_va_mapping(unsigned long va, pte_t new_val,
-			     unsigned long flags)
-{
-	if (sizeof(new_val) == sizeof(long))
-		return _hypercall3(int, update_va_mapping, va,
-				   new_val.pte, flags);
-	else
-		return _hypercall4(int, update_va_mapping, va,
-				   new_val.pte, new_val.pte >> 32, flags);
-}
-
-static inline int
-HYPERVISOR_event_channel_op(int cmd, void *arg)
-{
-	int rc = _hypercall2(int, event_channel_op, cmd, arg);
-	if (unlikely(rc == -ENOSYS)) {
-		struct evtchn_op op;
-		op.cmd = cmd;
-		memcpy(&op.u, arg, sizeof(op.u));
-		rc = _hypercall1(int, event_channel_op_compat, &op);
-		memcpy(arg, &op.u, sizeof(op.u));
-	}
-	return rc;
-}
-
-static inline int
-HYPERVISOR_xen_version(int cmd, void *arg)
-{
-	return _hypercall2(int, xen_version, cmd, arg);
-}
-
-static inline int
-HYPERVISOR_console_io(int cmd, int count, char *str)
-{
-	return _hypercall3(int, console_io, cmd, count, str);
-}
-
-static inline int
-HYPERVISOR_physdev_op(int cmd, void *arg)
-{
-	int rc = _hypercall2(int, physdev_op, cmd, arg);
-	if (unlikely(rc == -ENOSYS)) {
-		struct physdev_op op;
-		op.cmd = cmd;
-		memcpy(&op.u, arg, sizeof(op.u));
-		rc = _hypercall1(int, physdev_op_compat, &op);
-		memcpy(arg, &op.u, sizeof(op.u));
-	}
-	return rc;
-}
-
-static inline int
-HYPERVISOR_grant_table_op(unsigned int cmd, void *uop, unsigned int count)
-{
-	return _hypercall3(int, grant_table_op, cmd, uop, count);
-}
-
-static inline int
-HYPERVISOR_update_va_mapping_otherdomain(unsigned long va, pte_t new_val,
-					 unsigned long flags, domid_t domid)
-{
-	if (sizeof(new_val) == sizeof(long))
-		return _hypercall4(int, update_va_mapping_otherdomain, va,
-				   new_val.pte, flags, domid);
-	else
-		return _hypercall5(int, update_va_mapping_otherdomain, va,
-				   new_val.pte, new_val.pte >> 32,
-				   flags, domid);
-}
-
-static inline int
-HYPERVISOR_vm_assist(unsigned int cmd, unsigned int type)
-{
-	return _hypercall2(int, vm_assist, cmd, type);
-}
-
-static inline int
-HYPERVISOR_vcpu_op(int cmd, int vcpuid, void *extra_args)
-{
-	return _hypercall3(int, vcpu_op, cmd, vcpuid, extra_args);
-}
-
-#ifdef CONFIG_X86_64
-static inline int
-HYPERVISOR_set_segment_base(int reg, unsigned long value)
-{
-	return _hypercall2(int, set_segment_base, reg, value);
-}
-#endif
-
-static inline int
-HYPERVISOR_suspend(unsigned long srec)
-{
-	return _hypercall3(int, sched_op, SCHEDOP_shutdown,
-			   SHUTDOWN_suspend, srec);
-}
-
-static inline int
-HYPERVISOR_nmi_op(unsigned long op, unsigned long arg)
-{
-	return _hypercall2(int, nmi_op, op, arg);
-}
-
-static inline void
-MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set)
-{
-	mcl->op = __HYPERVISOR_fpu_taskswitch;
-	mcl->args[0] = set;
-}
-
-static inline void
-MULTI_update_va_mapping(struct multicall_entry *mcl, unsigned long va,
-			pte_t new_val, unsigned long flags)
-{
-	mcl->op = __HYPERVISOR_update_va_mapping;
-	mcl->args[0] = va;
-	if (sizeof(new_val) == sizeof(long)) {
-		mcl->args[1] = new_val.pte;
-		mcl->args[2] = flags;
-	} else {
-		mcl->args[1] = new_val.pte;
-		mcl->args[2] = new_val.pte >> 32;
-		mcl->args[3] = flags;
-	}
-}
-
-static inline void
-MULTI_grant_table_op(struct multicall_entry *mcl, unsigned int cmd,
-		     void *uop, unsigned int count)
-{
-	mcl->op = __HYPERVISOR_grant_table_op;
-	mcl->args[0] = cmd;
-	mcl->args[1] = (unsigned long)uop;
-	mcl->args[2] = count;
-}
-
-static inline void
-MULTI_update_va_mapping_otherdomain(struct multicall_entry *mcl, unsigned long va,
-				    pte_t new_val, unsigned long flags,
-				    domid_t domid)
-{
-	mcl->op = __HYPERVISOR_update_va_mapping_otherdomain;
-	mcl->args[0] = va;
-	if (sizeof(new_val) == sizeof(long)) {
-		mcl->args[1] = new_val.pte;
-		mcl->args[2] = flags;
-		mcl->args[3] = domid;
-	} else {
-		mcl->args[1] = new_val.pte;
-		mcl->args[2] = new_val.pte >> 32;
-		mcl->args[3] = flags;
-		mcl->args[4] = domid;
-	}
-}
-
-static inline void
-MULTI_update_descriptor(struct multicall_entry *mcl, u64 maddr,
-			struct desc_struct desc)
-{
-	mcl->op = __HYPERVISOR_update_descriptor;
-	if (sizeof(maddr) == sizeof(long)) {
-		mcl->args[0] = maddr;
-		mcl->args[1] = *(unsigned long *)&desc;
-	} else {
-		mcl->args[0] = maddr;
-		mcl->args[1] = maddr >> 32;
-		mcl->args[2] = desc.a;
-		mcl->args[3] = desc.b;
-	}
-}
-
-static inline void
-MULTI_memory_op(struct multicall_entry *mcl, unsigned int cmd, void *arg)
-{
-	mcl->op = __HYPERVISOR_memory_op;
-	mcl->args[0] = cmd;
-	mcl->args[1] = (unsigned long)arg;
-}
-
-static inline void
-MULTI_mmu_update(struct multicall_entry *mcl, struct mmu_update *req,
-		 int count, int *success_count, domid_t domid)
-{
-	mcl->op = __HYPERVISOR_mmu_update;
-	mcl->args[0] = (unsigned long)req;
-	mcl->args[1] = count;
-	mcl->args[2] = (unsigned long)success_count;
-	mcl->args[3] = domid;
-}
-
-static inline void
-MULTI_mmuext_op(struct multicall_entry *mcl, struct mmuext_op *op, int count,
-		int *success_count, domid_t domid)
-{
-	mcl->op = __HYPERVISOR_mmuext_op;
-	mcl->args[0] = (unsigned long)op;
-	mcl->args[1] = count;
-	mcl->args[2] = (unsigned long)success_count;
-	mcl->args[3] = domid;
-}
-
-static inline void
-MULTI_set_gdt(struct multicall_entry *mcl, unsigned long *frames, int entries)
-{
-	mcl->op = __HYPERVISOR_set_gdt;
-	mcl->args[0] = (unsigned long)frames;
-	mcl->args[1] = entries;
-}
-
-static inline void
-MULTI_stack_switch(struct multicall_entry *mcl,
-		   unsigned long ss, unsigned long esp)
-{
-	mcl->op = __HYPERVISOR_stack_switch;
-	mcl->args[0] = ss;
-	mcl->args[1] = esp;
-}
-
-#endif /* ASM_X86__XEN__HYPERCALL_H */
diff --git a/include/asm-x86/xen/hypervisor.h b/include/asm-x86/xen/hypervisor.h
deleted file mode 100644
index 445a24759560..000000000000
--- a/include/asm-x86/xen/hypervisor.h
+++ /dev/null
@@ -1,82 +0,0 @@
-/******************************************************************************
- * hypervisor.h
- *
- * Linux-specific hypervisor handling.
- *
- * Copyright (c) 2002-2004, K A Fraser
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation; or, when distributed
- * separately from the Linux kernel or incorporated into other
- * software packages, subject to the following license:
- *
- * Permission is hereby granted, free of charge, to any person obtaining a copy
- * of this source file (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy, modify,
- * merge, publish, distribute, sublicense, and/or sell copies of the Software,
- * and to permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
- * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
- * IN THE SOFTWARE.
- */
-
-#ifndef ASM_X86__XEN__HYPERVISOR_H
-#define ASM_X86__XEN__HYPERVISOR_H
-
-#include <linux/types.h>
-#include <linux/kernel.h>
-
-#include <xen/interface/xen.h>
-#include <xen/interface/version.h>
-
-#include <asm/ptrace.h>
-#include <asm/page.h>
-#include <asm/desc.h>
-#if defined(__i386__)
-#  ifdef CONFIG_X86_PAE
-#   include <asm-generic/pgtable-nopud.h>
-#  else
-#   include <asm-generic/pgtable-nopmd.h>
-#  endif
-#endif
-#include <asm/xen/hypercall.h>
-
-/* arch/i386/kernel/setup.c */
-extern struct shared_info *HYPERVISOR_shared_info;
-extern struct start_info *xen_start_info;
-
-/* arch/i386/mach-xen/evtchn.c */
-/* Force a proper event-channel callback from Xen. */
-extern void force_evtchn_callback(void);
-
-/* Turn jiffies into Xen system time. */
-u64 jiffies_to_st(unsigned long jiffies);
-
-
-#define MULTI_UVMFLAGS_INDEX 3
-#define MULTI_UVMDOMID_INDEX 4
-
-enum xen_domain_type {
-	XEN_NATIVE,
-	XEN_PV_DOMAIN,
-	XEN_HVM_DOMAIN,
-};
-
-extern enum xen_domain_type xen_domain_type;
-
-#define xen_domain()		(xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()		(xen_domain_type == XEN_PV_DOMAIN)
-#define xen_initial_domain()	(xen_pv_domain() && xen_start_info->flags & SIF_INITDOMAIN)
-#define xen_hvm_domain()	(xen_domain_type == XEN_HVM_DOMAIN)
-
-#endif /* ASM_X86__XEN__HYPERVISOR_H */
diff --git a/include/asm-x86/xen/interface.h b/include/asm-x86/xen/interface.h
deleted file mode 100644
index d077bba96da9..000000000000
--- a/include/asm-x86/xen/interface.h
+++ /dev/null
@@ -1,175 +0,0 @@
-/******************************************************************************
- * arch-x86_32.h
- *
- * Guest OS interface to x86 Xen.
- *
- * Copyright (c) 2004, K A Fraser
- */
-
-#ifndef ASM_X86__XEN__INTERFACE_H
-#define ASM_X86__XEN__INTERFACE_H
-
-#ifdef __XEN__
-#define __DEFINE_GUEST_HANDLE(name, type) \
-    typedef struct { type *p; } __guest_handle_ ## name
-#else
-#define __DEFINE_GUEST_HANDLE(name, type) \
-    typedef type * __guest_handle_ ## name
-#endif
-
-#define DEFINE_GUEST_HANDLE_STRUCT(name) \
-	__DEFINE_GUEST_HANDLE(name, struct name)
-#define DEFINE_GUEST_HANDLE(name) __DEFINE_GUEST_HANDLE(name, name)
-#define GUEST_HANDLE(name)        __guest_handle_ ## name
-
-#ifdef __XEN__
-#if defined(__i386__)
-#define set_xen_guest_handle(hnd, val)			\
-	do {						\
-		if (sizeof(hnd) == 8)			\
-			*(uint64_t *)&(hnd) = 0;	\
-		(hnd).p = val;				\
-	} while (0)
-#elif defined(__x86_64__)
-#define set_xen_guest_handle(hnd, val)	do { (hnd).p = val; } while (0)
-#endif
-#else
-#if defined(__i386__)
-#define set_xen_guest_handle(hnd, val)			\
-	do {						\
-		if (sizeof(hnd) == 8)			\
-			*(uint64_t *)&(hnd) = 0;	\
-		(hnd) = val;				\
-	} while (0)
-#elif defined(__x86_64__)
-#define set_xen_guest_handle(hnd, val)	do { (hnd) = val; } while (0)
-#endif
-#endif
-
-#ifndef __ASSEMBLY__
-/* Guest handles for primitive C types. */
-__DEFINE_GUEST_HANDLE(uchar, unsigned char);
-__DEFINE_GUEST_HANDLE(uint,  unsigned int);
-__DEFINE_GUEST_HANDLE(ulong, unsigned long);
-DEFINE_GUEST_HANDLE(char);
-DEFINE_GUEST_HANDLE(int);
-DEFINE_GUEST_HANDLE(long);
-DEFINE_GUEST_HANDLE(void);
-#endif
-
-#ifndef HYPERVISOR_VIRT_START
-#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
-#endif
-
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
-
-/* Maximum number of virtual CPUs in multi-processor guests. */
-#define MAX_VIRT_CPUS 32
-
-/*
- * SEGMENT DESCRIPTOR TABLES
- */
-/*
- * A number of GDT entries are reserved by Xen. These are not situated at the
- * start of the GDT because some stupid OSes export hard-coded selector values
- * in their ABI. These hard-coded values are always near the start of the GDT,
- * so Xen places itself out of the way, at the far end of the GDT.
- */
-#define FIRST_RESERVED_GDT_PAGE  14
-#define FIRST_RESERVED_GDT_BYTE  (FIRST_RESERVED_GDT_PAGE * 4096)
-#define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8)
-
-/*
- * Send an array of these to HYPERVISOR_set_trap_table()
- * The privilege level specifies which modes may enter a trap via a software
- * interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
- * privilege levels as follows:
- *  Level == 0: Noone may enter
- *  Level == 1: Kernel may enter
- *  Level == 2: Kernel may enter
- *  Level == 3: Everyone may enter
- */
-#define TI_GET_DPL(_ti)		((_ti)->flags & 3)
-#define TI_GET_IF(_ti)		((_ti)->flags & 4)
-#define TI_SET_DPL(_ti, _dpl)	((_ti)->flags |= (_dpl))
-#define TI_SET_IF(_ti, _if)	((_ti)->flags |= ((!!(_if))<<2))
-
-#ifndef __ASSEMBLY__
-struct trap_info {
-    uint8_t       vector;  /* exception vector                              */
-    uint8_t       flags;   /* 0-3: privilege level; 4: clear event enable?  */
-    uint16_t      cs;      /* code selector                                 */
-    unsigned long address; /* code offset                                   */
-};
-DEFINE_GUEST_HANDLE_STRUCT(trap_info);
-
-struct arch_shared_info {
-    unsigned long max_pfn;                  /* max pfn that appears in table */
-    /* Frame containing list of mfns containing list of mfns containing p2m. */
-    unsigned long pfn_to_mfn_frame_list_list;
-    unsigned long nmi_reason;
-};
-#endif	/* !__ASSEMBLY__ */
-
-#ifdef CONFIG_X86_32
-#include "interface_32.h"
-#else
-#include "interface_64.h"
-#endif
-
-#ifndef __ASSEMBLY__
-/*
- * The following is all CPU context. Note that the fpu_ctxt block is filled
- * in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
- */
-struct vcpu_guest_context {
-    /* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */
-    struct { char x[512]; } fpu_ctxt;       /* User-level FPU registers     */
-#define VGCF_I387_VALID (1<<0)
-#define VGCF_HVM_GUEST  (1<<1)
-#define VGCF_IN_KERNEL  (1<<2)
-    unsigned long flags;                    /* VGCF_* flags                 */
-    struct cpu_user_regs user_regs;         /* User-level CPU registers     */
-    struct trap_info trap_ctxt[256];        /* Virtual IDT                  */
-    unsigned long ldt_base, ldt_ents;       /* LDT (linear address, # ents) */
-    unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */
-    unsigned long kernel_ss, kernel_sp;     /* Virtual TSS (only SS1/SP1)   */
-    /* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */
-    unsigned long ctrlreg[8];               /* CR0-CR7 (control registers)  */
-    unsigned long debugreg[8];              /* DB0-DB7 (debug registers)    */
-#ifdef __i386__
-    unsigned long event_callback_cs;        /* CS:EIP of event callback     */
-    unsigned long event_callback_eip;
-    unsigned long failsafe_callback_cs;     /* CS:EIP of failsafe callback  */
-    unsigned long failsafe_callback_eip;
-#else
-    unsigned long event_callback_eip;
-    unsigned long failsafe_callback_eip;
-    unsigned long syscall_callback_eip;
-#endif
-    unsigned long vm_assist;                /* VMASST_TYPE_* bitmap */
-#ifdef __x86_64__
-    /* Segment base addresses. */
-    uint64_t      fs_base;
-    uint64_t      gs_base_kernel;
-    uint64_t      gs_base_user;
-#endif
-};
-DEFINE_GUEST_HANDLE_STRUCT(vcpu_guest_context);
-#endif	/* !__ASSEMBLY__ */
-
-/*
- * Prefix forces emulation of some non-trapping instructions.
- * Currently only CPUID.
- */
-#ifdef __ASSEMBLY__
-#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ;
-#define XEN_CPUID          XEN_EMULATE_PREFIX cpuid
-#else
-#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; "
-#define XEN_CPUID          XEN_EMULATE_PREFIX "cpuid"
-#endif
-
-#endif /* ASM_X86__XEN__INTERFACE_H */
diff --git a/include/asm-x86/xen/interface_32.h b/include/asm-x86/xen/interface_32.h
deleted file mode 100644
index 08167e19fc66..000000000000
--- a/include/asm-x86/xen/interface_32.h
+++ /dev/null
@@ -1,97 +0,0 @@
-/******************************************************************************
- * arch-x86_32.h
- *
- * Guest OS interface to x86 32-bit Xen.
- *
- * Copyright (c) 2004, K A Fraser
- */
-
-#ifndef ASM_X86__XEN__INTERFACE_32_H
-#define ASM_X86__XEN__INTERFACE_32_H
-
-
-/*
- * These flat segments are in the Xen-private section of every GDT. Since these
- * are also present in the initial GDT, many OSes will be able to avoid
- * installing their own GDT.
- */
-#define FLAT_RING1_CS 0xe019    /* GDT index 259 */
-#define FLAT_RING1_DS 0xe021    /* GDT index 260 */
-#define FLAT_RING1_SS 0xe021    /* GDT index 260 */
-#define FLAT_RING3_CS 0xe02b    /* GDT index 261 */
-#define FLAT_RING3_DS 0xe033    /* GDT index 262 */
-#define FLAT_RING3_SS 0xe033    /* GDT index 262 */
-
-#define FLAT_KERNEL_CS FLAT_RING1_CS
-#define FLAT_KERNEL_DS FLAT_RING1_DS
-#define FLAT_KERNEL_SS FLAT_RING1_SS
-#define FLAT_USER_CS    FLAT_RING3_CS
-#define FLAT_USER_DS    FLAT_RING3_DS
-#define FLAT_USER_SS    FLAT_RING3_SS
-
-/* And the trap vector is... */
-#define TRAP_INSTR "int $0x82"
-
-/*
- * Virtual addresses beyond this are not modifiable by guest OSes. The
- * machine->physical mapping table starts at this address, read-only.
- */
-#define __HYPERVISOR_VIRT_START 0xF5800000
-
-#ifndef __ASSEMBLY__
-
-struct cpu_user_regs {
-    uint32_t ebx;
-    uint32_t ecx;
-    uint32_t edx;
-    uint32_t esi;
-    uint32_t edi;
-    uint32_t ebp;
-    uint32_t eax;
-    uint16_t error_code;    /* private */
-    uint16_t entry_vector;  /* private */
-    uint32_t eip;
-    uint16_t cs;
-    uint8_t  saved_upcall_mask;
-    uint8_t  _pad0;
-    uint32_t eflags;        /* eflags.IF == !saved_upcall_mask */
-    uint32_t esp;
-    uint16_t ss, _pad1;
-    uint16_t es, _pad2;
-    uint16_t ds, _pad3;
-    uint16_t fs, _pad4;
-    uint16_t gs, _pad5;
-};
-DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
-
-typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */
-
-struct arch_vcpu_info {
-    unsigned long cr2;
-    unsigned long pad[5]; /* sizeof(struct vcpu_info) == 64 */
-};
-
-struct xen_callback {
-	unsigned long cs;
-	unsigned long eip;
-};
-typedef struct xen_callback xen_callback_t;
-
-#define XEN_CALLBACK(__cs, __eip)				\
-	((struct xen_callback){ .cs = (__cs), .eip = (unsigned long)(__eip) })
-#endif /* !__ASSEMBLY__ */
-
-
-/*
- * Page-directory addresses above 4GB do not fit into architectural %cr3.
- * When accessing %cr3, or equivalent field in vcpu_guest_context, guests
- * must use the following accessor macros to pack/unpack valid MFNs.
- *
- * Note that Xen is using the fact that the pagetable base is always
- * page-aligned, and putting the 12 MSB of the address into the 12 LSB
- * of cr3.
- */
-#define xen_pfn_to_cr3(pfn) (((unsigned)(pfn) << 12) | ((unsigned)(pfn) >> 20))
-#define xen_cr3_to_pfn(cr3) (((unsigned)(cr3) >> 12) | ((unsigned)(cr3) << 20))
-
-#endif /* ASM_X86__XEN__INTERFACE_32_H */
diff --git a/include/asm-x86/xen/interface_64.h b/include/asm-x86/xen/interface_64.h
deleted file mode 100644
index 046c0f1e01d4..000000000000
--- a/include/asm-x86/xen/interface_64.h
+++ /dev/null
@@ -1,159 +0,0 @@
-#ifndef ASM_X86__XEN__INTERFACE_64_H
-#define ASM_X86__XEN__INTERFACE_64_H
-
-/*
- * 64-bit segment selectors
- * These flat segments are in the Xen-private section of every GDT. Since these
- * are also present in the initial GDT, many OSes will be able to avoid
- * installing their own GDT.
- */
-
-#define FLAT_RING3_CS32 0xe023  /* GDT index 260 */
-#define FLAT_RING3_CS64 0xe033  /* GDT index 261 */
-#define FLAT_RING3_DS32 0xe02b  /* GDT index 262 */
-#define FLAT_RING3_DS64 0x0000  /* NULL selector */
-#define FLAT_RING3_SS32 0xe02b  /* GDT index 262 */
-#define FLAT_RING3_SS64 0xe02b  /* GDT index 262 */
-
-#define FLAT_KERNEL_DS64 FLAT_RING3_DS64
-#define FLAT_KERNEL_DS32 FLAT_RING3_DS32
-#define FLAT_KERNEL_DS   FLAT_KERNEL_DS64
-#define FLAT_KERNEL_CS64 FLAT_RING3_CS64
-#define FLAT_KERNEL_CS32 FLAT_RING3_CS32
-#define FLAT_KERNEL_CS   FLAT_KERNEL_CS64
-#define FLAT_KERNEL_SS64 FLAT_RING3_SS64
-#define FLAT_KERNEL_SS32 FLAT_RING3_SS32
-#define FLAT_KERNEL_SS   FLAT_KERNEL_SS64
-
-#define FLAT_USER_DS64 FLAT_RING3_DS64
-#define FLAT_USER_DS32 FLAT_RING3_DS32
-#define FLAT_USER_DS   FLAT_USER_DS64
-#define FLAT_USER_CS64 FLAT_RING3_CS64
-#define FLAT_USER_CS32 FLAT_RING3_CS32
-#define FLAT_USER_CS   FLAT_USER_CS64
-#define FLAT_USER_SS64 FLAT_RING3_SS64
-#define FLAT_USER_SS32 FLAT_RING3_SS32
-#define FLAT_USER_SS   FLAT_USER_SS64
-
-#define __HYPERVISOR_VIRT_START 0xFFFF800000000000
-#define __HYPERVISOR_VIRT_END   0xFFFF880000000000
-#define __MACH2PHYS_VIRT_START  0xFFFF800000000000
-#define __MACH2PHYS_VIRT_END    0xFFFF804000000000
-
-#ifndef HYPERVISOR_VIRT_START
-#define HYPERVISOR_VIRT_START mk_unsigned_long(__HYPERVISOR_VIRT_START)
-#define HYPERVISOR_VIRT_END   mk_unsigned_long(__HYPERVISOR_VIRT_END)
-#endif
-
-#define MACH2PHYS_VIRT_START  mk_unsigned_long(__MACH2PHYS_VIRT_START)
-#define MACH2PHYS_VIRT_END    mk_unsigned_long(__MACH2PHYS_VIRT_END)
-#define MACH2PHYS_NR_ENTRIES  ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3)
-#ifndef machine_to_phys_mapping
-#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
-#endif
-
-/*
- * int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base)
- *  @which == SEGBASE_*  ;  @base == 64-bit base address
- * Returns 0 on success.
- */
-#define SEGBASE_FS          0
-#define SEGBASE_GS_USER     1
-#define SEGBASE_GS_KERNEL   2
-#define SEGBASE_GS_USER_SEL 3 /* Set user %gs specified in base[15:0] */
-
-/*
- * int HYPERVISOR_iret(void)
- * All arguments are on the kernel stack, in the following format.
- * Never returns if successful. Current kernel context is lost.
- * The saved CS is mapped as follows:
- *   RING0 -> RING3 kernel mode.
- *   RING1 -> RING3 kernel mode.
- *   RING2 -> RING3 kernel mode.
- *   RING3 -> RING3 user mode.
- * However RING0 indicates that the guest kernel should return to iteself
- * directly with
- *      orb   $3,1*8(%rsp)
- *      iretq
- * If flags contains VGCF_in_syscall:
- *   Restore RAX, RIP, RFLAGS, RSP.
- *   Discard R11, RCX, CS, SS.
- * Otherwise:
- *   Restore RAX, R11, RCX, CS:RIP, RFLAGS, SS:RSP.
- * All other registers are saved on hypercall entry and restored to user.
- */
-/* Guest exited in SYSCALL context? Return to guest with SYSRET? */
-#define _VGCF_in_syscall 8
-#define VGCF_in_syscall  (1<<_VGCF_in_syscall)
-#define VGCF_IN_SYSCALL  VGCF_in_syscall
-
-#ifndef __ASSEMBLY__
-
-struct iret_context {
-    /* Top of stack (%rsp at point of hypercall). */
-    uint64_t rax, r11, rcx, flags, rip, cs, rflags, rsp, ss;
-    /* Bottom of iret stack frame. */
-};
-
-#if defined(__GNUC__) && !defined(__STRICT_ANSI__)
-/* Anonymous union includes both 32- and 64-bit names (e.g., eax/rax). */
-#define __DECL_REG(name) union { \
-    uint64_t r ## name, e ## name; \
-    uint32_t _e ## name; \
-}
-#else
-/* Non-gcc sources must always use the proper 64-bit name (e.g., rax). */
-#define __DECL_REG(name) uint64_t r ## name
-#endif
-
-struct cpu_user_regs {
-    uint64_t r15;
-    uint64_t r14;
-    uint64_t r13;
-    uint64_t r12;
-    __DECL_REG(bp);
-    __DECL_REG(bx);
-    uint64_t r11;
-    uint64_t r10;
-    uint64_t r9;
-    uint64_t r8;
-    __DECL_REG(ax);
-    __DECL_REG(cx);
-    __DECL_REG(dx);
-    __DECL_REG(si);
-    __DECL_REG(di);
-    uint32_t error_code;    /* private */
-    uint32_t entry_vector;  /* private */
-    __DECL_REG(ip);
-    uint16_t cs, _pad0[1];
-    uint8_t  saved_upcall_mask;
-    uint8_t  _pad1[3];
-    __DECL_REG(flags);      /* rflags.IF == !saved_upcall_mask */
-    __DECL_REG(sp);
-    uint16_t ss, _pad2[3];
-    uint16_t es, _pad3[3];
-    uint16_t ds, _pad4[3];
-    uint16_t fs, _pad5[3]; /* Non-zero => takes precedence over fs_base.     */
-    uint16_t gs, _pad6[3]; /* Non-zero => takes precedence over gs_base_usr. */
-};
-DEFINE_GUEST_HANDLE_STRUCT(cpu_user_regs);
-
-#undef __DECL_REG
-
-#define xen_pfn_to_cr3(pfn) ((unsigned long)(pfn) << 12)
-#define xen_cr3_to_pfn(cr3) ((unsigned long)(cr3) >> 12)
-
-struct arch_vcpu_info {
-    unsigned long cr2;
-    unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
-};
-
-typedef unsigned long xen_callback_t;
-
-#define XEN_CALLBACK(__cs, __rip)				\
-	((unsigned long)(__rip))
-
-#endif /* !__ASSEMBLY__ */
-
-
-#endif /* ASM_X86__XEN__INTERFACE_64_H */
diff --git a/include/asm-x86/xen/page.h b/include/asm-x86/xen/page.h
deleted file mode 100644
index d5eada0a48d9..000000000000
--- a/include/asm-x86/xen/page.h
+++ /dev/null
@@ -1,165 +0,0 @@
-#ifndef ASM_X86__XEN__PAGE_H
-#define ASM_X86__XEN__PAGE_H
-
-#include <linux/pfn.h>
-
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
-
-#include <xen/features.h>
-
-/* Xen machine address */
-typedef struct xmaddr {
-	phys_addr_t maddr;
-} xmaddr_t;
-
-/* Xen pseudo-physical address */
-typedef struct xpaddr {
-	phys_addr_t paddr;
-} xpaddr_t;
-
-#define XMADDR(x)	((xmaddr_t) { .maddr = (x) })
-#define XPADDR(x)	((xpaddr_t) { .paddr = (x) })
-
-/**** MACHINE <-> PHYSICAL CONVERSION MACROS ****/
-#define INVALID_P2M_ENTRY	(~0UL)
-#define FOREIGN_FRAME_BIT	(1UL<<31)
-#define FOREIGN_FRAME(m)	((m) | FOREIGN_FRAME_BIT)
-
-/* Maximum amount of memory we can handle in a domain in pages */
-#define MAX_DOMAIN_PAGES						\
-    ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE))
-
-
-extern unsigned long get_phys_to_machine(unsigned long pfn);
-extern void set_phys_to_machine(unsigned long pfn, unsigned long mfn);
-
-static inline unsigned long pfn_to_mfn(unsigned long pfn)
-{
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return pfn;
-
-	return get_phys_to_machine(pfn) & ~FOREIGN_FRAME_BIT;
-}
-
-static inline int phys_to_machine_mapping_valid(unsigned long pfn)
-{
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return 1;
-
-	return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
-}
-
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
-{
-	unsigned long pfn;
-
-	if (xen_feature(XENFEAT_auto_translated_physmap))
-		return mfn;
-
-#if 0
-	if (unlikely((mfn >> machine_to_phys_order) != 0))
-		return max_mapnr;
-#endif
-
-	pfn = 0;
-	/*
-	 * The array access can fail (e.g., device space beyond end of RAM).
-	 * In such cases it doesn't matter what we return (we return garbage),
-	 * but we must handle the fault without crashing!
-	 */
-	__get_user(pfn, &machine_to_phys_mapping[mfn]);
-
-	return pfn;
-}
-
-static inline xmaddr_t phys_to_machine(xpaddr_t phys)
-{
-	unsigned offset = phys.paddr & ~PAGE_MASK;
-	return XMADDR(PFN_PHYS(pfn_to_mfn(PFN_DOWN(phys.paddr))) | offset);
-}
-
-static inline xpaddr_t machine_to_phys(xmaddr_t machine)
-{
-	unsigned offset = machine.maddr & ~PAGE_MASK;
-	return XPADDR(PFN_PHYS(mfn_to_pfn(PFN_DOWN(machine.maddr))) | offset);
-}
-
-/*
- * We detect special mappings in one of two ways:
- *  1. If the MFN is an I/O page then Xen will set the m2p entry
- *     to be outside our maximum possible pseudophys range.
- *  2. If the MFN belongs to a different domain then we will certainly
- *     not have MFN in our p2m table. Conversely, if the page is ours,
- *     then we'll have p2m(m2p(MFN))==MFN.
- * If we detect a special mapping then it doesn't have a 'struct page'.
- * We force !pfn_valid() by returning an out-of-range pointer.
- *
- * NB. These checks require that, for any MFN that is not in our reservation,
- * there is no PFN such that p2m(PFN) == MFN. Otherwise we can get confused if
- * we are foreign-mapping the MFN, and the other domain as m2p(MFN) == PFN.
- * Yikes! Various places must poke in INVALID_P2M_ENTRY for safety.
- *
- * NB2. When deliberately mapping foreign pages into the p2m table, you *must*
- *      use FOREIGN_FRAME(). This will cause pte_pfn() to choke on it, as we
- *      require. In all the cases we care about, the FOREIGN_FRAME bit is
- *      masked (e.g., pfn_to_mfn()) so behaviour there is correct.
- */
-static inline unsigned long mfn_to_local_pfn(unsigned long mfn)
-{
-	extern unsigned long max_mapnr;
-	unsigned long pfn = mfn_to_pfn(mfn);
-	if ((pfn < max_mapnr)
-	    && !xen_feature(XENFEAT_auto_translated_physmap)
-	    && (get_phys_to_machine(pfn) != mfn))
-		return max_mapnr; /* force !pfn_valid() */
-	/* XXX fixme; not true with sparsemem */
-	return pfn;
-}
-
-/* VIRT <-> MACHINE conversion */
-#define virt_to_machine(v)	(phys_to_machine(XPADDR(__pa(v))))
-#define virt_to_mfn(v)		(pfn_to_mfn(PFN_DOWN(__pa(v))))
-#define mfn_to_virt(m)		(__va(mfn_to_pfn(m) << PAGE_SHIFT))
-
-static inline unsigned long pte_mfn(pte_t pte)
-{
-	return (pte.pte & PTE_PFN_MASK) >> PAGE_SHIFT;
-}
-
-static inline pte_t mfn_pte(unsigned long page_nr, pgprot_t pgprot)
-{
-	pte_t pte;
-
-	pte.pte = ((phys_addr_t)page_nr << PAGE_SHIFT) |
-		(pgprot_val(pgprot) & __supported_pte_mask);
-
-	return pte;
-}
-
-static inline pteval_t pte_val_ma(pte_t pte)
-{
-	return pte.pte;
-}
-
-static inline pte_t __pte_ma(pteval_t x)
-{
-	return (pte_t) { .pte = x };
-}
-
-#define pmd_val_ma(v) ((v).pmd)
-#ifdef __PAGETABLE_PUD_FOLDED
-#define pud_val_ma(v) ((v).pgd.pgd)
-#else
-#define pud_val_ma(v) ((v).pud)
-#endif
-#define __pmd_ma(x)	((pmd_t) { (x) } )
-
-#define pgd_val_ma(x)	((x).pgd)
-
-
-xmaddr_t arbitrary_virt_to_machine(void *address);
-void make_lowmem_page_readonly(void *vaddr);
-void make_lowmem_page_readwrite(void *vaddr);
-
-#endif /* ASM_X86__XEN__PAGE_H */
diff --git a/include/asm-x86/xor.h b/include/asm-x86/xor.h
deleted file mode 100644
index 11b3bb86e17b..000000000000
--- a/include/asm-x86/xor.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include "xor_32.h"
-#else
-# include "xor_64.h"
-#endif
diff --git a/include/asm-x86/xor_32.h b/include/asm-x86/xor_32.h
deleted file mode 100644
index 921b45840449..000000000000
--- a/include/asm-x86/xor_32.h
+++ /dev/null
@@ -1,888 +0,0 @@
-#ifndef ASM_X86__XOR_32_H
-#define ASM_X86__XOR_32_H
-
-/*
- * Optimized RAID-5 checksumming functions for MMX and SSE.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * You should have received a copy of the GNU General Public License
- * (for example /usr/src/linux/COPYING); if not, write to the Free
- * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-/*
- * High-speed RAID5 checksumming functions utilizing MMX instructions.
- * Copyright (C) 1998 Ingo Molnar.
- */
-
-#define LD(x, y)	"       movq   8*("#x")(%1), %%mm"#y"   ;\n"
-#define ST(x, y)	"       movq %%mm"#y",   8*("#x")(%1)   ;\n"
-#define XO1(x, y)	"       pxor   8*("#x")(%2), %%mm"#y"   ;\n"
-#define XO2(x, y)	"       pxor   8*("#x")(%3), %%mm"#y"   ;\n"
-#define XO3(x, y)	"       pxor   8*("#x")(%4), %%mm"#y"   ;\n"
-#define XO4(x, y)	"       pxor   8*("#x")(%5), %%mm"#y"   ;\n"
-
-#include <asm/i387.h>
-
-static void
-xor_pII_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
-{
-	unsigned long lines = bytes >> 7;
-
-	kernel_fpu_begin();
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i)				\
-	LD(i, 0)				\
-		LD(i + 1, 1)			\
-			LD(i + 2, 2)		\
-				LD(i + 3, 3)	\
-	XO1(i, 0)				\
-	ST(i, 0)				\
-		XO1(i+1, 1)			\
-		ST(i+1, 1)			\
-			XO1(i + 2, 2)		\
-			ST(i + 2, 2)		\
-				XO1(i + 3, 3)	\
-				ST(i + 3, 3)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-	BLOCK(0)
-	BLOCK(4)
-	BLOCK(8)
-	BLOCK(12)
-
-	"       addl $128, %1         ;\n"
-	"       addl $128, %2         ;\n"
-	"       decl %0               ;\n"
-	"       jnz 1b                ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r" (p2)
-	:
-	: "memory");
-
-	kernel_fpu_end();
-}
-
-static void
-xor_pII_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	      unsigned long *p3)
-{
-	unsigned long lines = bytes >> 7;
-
-	kernel_fpu_begin();
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i)				\
-	LD(i, 0)				\
-		LD(i + 1, 1)			\
-			LD(i + 2, 2)		\
-				LD(i + 3, 3)	\
-	XO1(i, 0)				\
-		XO1(i + 1, 1)			\
-			XO1(i + 2, 2)		\
-				XO1(i + 3, 3)	\
-	XO2(i, 0)				\
-	ST(i, 0)				\
-		XO2(i + 1, 1)			\
-		ST(i + 1, 1)			\
-			XO2(i + 2, 2)		\
-			ST(i + 2, 2)		\
-				XO2(i + 3, 3)	\
-				ST(i + 3, 3)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-	BLOCK(0)
-	BLOCK(4)
-	BLOCK(8)
-	BLOCK(12)
-
-	"       addl $128, %1         ;\n"
-	"       addl $128, %2         ;\n"
-	"       addl $128, %3         ;\n"
-	"       decl %0               ;\n"
-	"       jnz 1b                ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r" (p2), "+r" (p3)
-	:
-	: "memory");
-
-	kernel_fpu_end();
-}
-
-static void
-xor_pII_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	      unsigned long *p3, unsigned long *p4)
-{
-	unsigned long lines = bytes >> 7;
-
-	kernel_fpu_begin();
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i)				\
-	LD(i, 0)				\
-		LD(i + 1, 1)			\
-			LD(i + 2, 2)		\
-				LD(i + 3, 3)	\
-	XO1(i, 0)				\
-		XO1(i + 1, 1)			\
-			XO1(i + 2, 2)		\
-				XO1(i + 3, 3)	\
-	XO2(i, 0)				\
-		XO2(i + 1, 1)			\
-			XO2(i + 2, 2)		\
-				XO2(i + 3, 3)	\
-	XO3(i, 0)				\
-	ST(i, 0)				\
-		XO3(i + 1, 1)			\
-		ST(i + 1, 1)			\
-			XO3(i + 2, 2)		\
-			ST(i + 2, 2)		\
-				XO3(i + 3, 3)	\
-				ST(i + 3, 3)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-	BLOCK(0)
-	BLOCK(4)
-	BLOCK(8)
-	BLOCK(12)
-
-	"       addl $128, %1         ;\n"
-	"       addl $128, %2         ;\n"
-	"       addl $128, %3         ;\n"
-	"       addl $128, %4         ;\n"
-	"       decl %0               ;\n"
-	"       jnz 1b                ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
-	:
-	: "memory");
-
-	kernel_fpu_end();
-}
-
-
-static void
-xor_pII_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	      unsigned long *p3, unsigned long *p4, unsigned long *p5)
-{
-	unsigned long lines = bytes >> 7;
-
-	kernel_fpu_begin();
-
-	/* Make sure GCC forgets anything it knows about p4 or p5,
-	   such that it won't pass to the asm volatile below a
-	   register that is shared with any other variable.  That's
-	   because we modify p4 and p5 there, but we can't mark them
-	   as read/write, otherwise we'd overflow the 10-asm-operands
-	   limit of GCC < 3.1.  */
-	asm("" : "+r" (p4), "+r" (p5));
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i)				\
-	LD(i, 0)				\
-		LD(i + 1, 1)			\
-			LD(i + 2, 2)		\
-				LD(i + 3, 3)	\
-	XO1(i, 0)				\
-		XO1(i + 1, 1)			\
-			XO1(i + 2, 2)		\
-				XO1(i + 3, 3)	\
-	XO2(i, 0)				\
-		XO2(i + 1, 1)			\
-			XO2(i + 2, 2)		\
-				XO2(i + 3, 3)	\
-	XO3(i, 0)				\
-		XO3(i + 1, 1)			\
-			XO3(i + 2, 2)		\
-				XO3(i + 3, 3)	\
-	XO4(i, 0)				\
-	ST(i, 0)				\
-		XO4(i + 1, 1)			\
-		ST(i + 1, 1)			\
-			XO4(i + 2, 2)		\
-			ST(i + 2, 2)		\
-				XO4(i + 3, 3)	\
-				ST(i + 3, 3)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-	BLOCK(0)
-	BLOCK(4)
-	BLOCK(8)
-	BLOCK(12)
-
-	"       addl $128, %1         ;\n"
-	"       addl $128, %2         ;\n"
-	"       addl $128, %3         ;\n"
-	"       addl $128, %4         ;\n"
-	"       addl $128, %5         ;\n"
-	"       decl %0               ;\n"
-	"       jnz 1b                ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r" (p2), "+r" (p3)
-	: "r" (p4), "r" (p5)
-	: "memory");
-
-	/* p4 and p5 were modified, and now the variables are dead.
-	   Clobber them just to be sure nobody does something stupid
-	   like assuming they have some legal value.  */
-	asm("" : "=r" (p4), "=r" (p5));
-
-	kernel_fpu_end();
-}
-
-#undef LD
-#undef XO1
-#undef XO2
-#undef XO3
-#undef XO4
-#undef ST
-#undef BLOCK
-
-static void
-xor_p5_mmx_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
-{
-	unsigned long lines = bytes >> 6;
-
-	kernel_fpu_begin();
-
-	asm volatile(
-	" .align 32	             ;\n"
-	" 1:                         ;\n"
-	"       movq   (%1), %%mm0   ;\n"
-	"       movq  8(%1), %%mm1   ;\n"
-	"       pxor   (%2), %%mm0   ;\n"
-	"       movq 16(%1), %%mm2   ;\n"
-	"       movq %%mm0,   (%1)   ;\n"
-	"       pxor  8(%2), %%mm1   ;\n"
-	"       movq 24(%1), %%mm3   ;\n"
-	"       movq %%mm1,  8(%1)   ;\n"
-	"       pxor 16(%2), %%mm2   ;\n"
-	"       movq 32(%1), %%mm4   ;\n"
-	"       movq %%mm2, 16(%1)   ;\n"
-	"       pxor 24(%2), %%mm3   ;\n"
-	"       movq 40(%1), %%mm5   ;\n"
-	"       movq %%mm3, 24(%1)   ;\n"
-	"       pxor 32(%2), %%mm4   ;\n"
-	"       movq 48(%1), %%mm6   ;\n"
-	"       movq %%mm4, 32(%1)   ;\n"
-	"       pxor 40(%2), %%mm5   ;\n"
-	"       movq 56(%1), %%mm7   ;\n"
-	"       movq %%mm5, 40(%1)   ;\n"
-	"       pxor 48(%2), %%mm6   ;\n"
-	"       pxor 56(%2), %%mm7   ;\n"
-	"       movq %%mm6, 48(%1)   ;\n"
-	"       movq %%mm7, 56(%1)   ;\n"
-
-	"       addl $64, %1         ;\n"
-	"       addl $64, %2         ;\n"
-	"       decl %0              ;\n"
-	"       jnz 1b               ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r" (p2)
-	:
-	: "memory");
-
-	kernel_fpu_end();
-}
-
-static void
-xor_p5_mmx_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	     unsigned long *p3)
-{
-	unsigned long lines = bytes >> 6;
-
-	kernel_fpu_begin();
-
-	asm volatile(
-	" .align 32,0x90             ;\n"
-	" 1:                         ;\n"
-	"       movq   (%1), %%mm0   ;\n"
-	"       movq  8(%1), %%mm1   ;\n"
-	"       pxor   (%2), %%mm0   ;\n"
-	"       movq 16(%1), %%mm2   ;\n"
-	"       pxor  8(%2), %%mm1   ;\n"
-	"       pxor   (%3), %%mm0   ;\n"
-	"       pxor 16(%2), %%mm2   ;\n"
-	"       movq %%mm0,   (%1)   ;\n"
-	"       pxor  8(%3), %%mm1   ;\n"
-	"       pxor 16(%3), %%mm2   ;\n"
-	"       movq 24(%1), %%mm3   ;\n"
-	"       movq %%mm1,  8(%1)   ;\n"
-	"       movq 32(%1), %%mm4   ;\n"
-	"       movq 40(%1), %%mm5   ;\n"
-	"       pxor 24(%2), %%mm3   ;\n"
-	"       movq %%mm2, 16(%1)   ;\n"
-	"       pxor 32(%2), %%mm4   ;\n"
-	"       pxor 24(%3), %%mm3   ;\n"
-	"       pxor 40(%2), %%mm5   ;\n"
-	"       movq %%mm3, 24(%1)   ;\n"
-	"       pxor 32(%3), %%mm4   ;\n"
-	"       pxor 40(%3), %%mm5   ;\n"
-	"       movq 48(%1), %%mm6   ;\n"
-	"       movq %%mm4, 32(%1)   ;\n"
-	"       movq 56(%1), %%mm7   ;\n"
-	"       pxor 48(%2), %%mm6   ;\n"
-	"       movq %%mm5, 40(%1)   ;\n"
-	"       pxor 56(%2), %%mm7   ;\n"
-	"       pxor 48(%3), %%mm6   ;\n"
-	"       pxor 56(%3), %%mm7   ;\n"
-	"       movq %%mm6, 48(%1)   ;\n"
-	"       movq %%mm7, 56(%1)   ;\n"
-
-	"       addl $64, %1         ;\n"
-	"       addl $64, %2         ;\n"
-	"       addl $64, %3         ;\n"
-	"       decl %0              ;\n"
-	"       jnz 1b               ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r" (p2), "+r" (p3)
-	:
-	: "memory" );
-
-	kernel_fpu_end();
-}
-
-static void
-xor_p5_mmx_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	     unsigned long *p3, unsigned long *p4)
-{
-	unsigned long lines = bytes >> 6;
-
-	kernel_fpu_begin();
-
-	asm volatile(
-	" .align 32,0x90             ;\n"
-	" 1:                         ;\n"
-	"       movq   (%1), %%mm0   ;\n"
-	"       movq  8(%1), %%mm1   ;\n"
-	"       pxor   (%2), %%mm0   ;\n"
-	"       movq 16(%1), %%mm2   ;\n"
-	"       pxor  8(%2), %%mm1   ;\n"
-	"       pxor   (%3), %%mm0   ;\n"
-	"       pxor 16(%2), %%mm2   ;\n"
-	"       pxor  8(%3), %%mm1   ;\n"
-	"       pxor   (%4), %%mm0   ;\n"
-	"       movq 24(%1), %%mm3   ;\n"
-	"       pxor 16(%3), %%mm2   ;\n"
-	"       pxor  8(%4), %%mm1   ;\n"
-	"       movq %%mm0,   (%1)   ;\n"
-	"       movq 32(%1), %%mm4   ;\n"
-	"       pxor 24(%2), %%mm3   ;\n"
-	"       pxor 16(%4), %%mm2   ;\n"
-	"       movq %%mm1,  8(%1)   ;\n"
-	"       movq 40(%1), %%mm5   ;\n"
-	"       pxor 32(%2), %%mm4   ;\n"
-	"       pxor 24(%3), %%mm3   ;\n"
-	"       movq %%mm2, 16(%1)   ;\n"
-	"       pxor 40(%2), %%mm5   ;\n"
-	"       pxor 32(%3), %%mm4   ;\n"
-	"       pxor 24(%4), %%mm3   ;\n"
-	"       movq %%mm3, 24(%1)   ;\n"
-	"       movq 56(%1), %%mm7   ;\n"
-	"       movq 48(%1), %%mm6   ;\n"
-	"       pxor 40(%3), %%mm5   ;\n"
-	"       pxor 32(%4), %%mm4   ;\n"
-	"       pxor 48(%2), %%mm6   ;\n"
-	"       movq %%mm4, 32(%1)   ;\n"
-	"       pxor 56(%2), %%mm7   ;\n"
-	"       pxor 40(%4), %%mm5   ;\n"
-	"       pxor 48(%3), %%mm6   ;\n"
-	"       pxor 56(%3), %%mm7   ;\n"
-	"       movq %%mm5, 40(%1)   ;\n"
-	"       pxor 48(%4), %%mm6   ;\n"
-	"       pxor 56(%4), %%mm7   ;\n"
-	"       movq %%mm6, 48(%1)   ;\n"
-	"       movq %%mm7, 56(%1)   ;\n"
-
-	"       addl $64, %1         ;\n"
-	"       addl $64, %2         ;\n"
-	"       addl $64, %3         ;\n"
-	"       addl $64, %4         ;\n"
-	"       decl %0              ;\n"
-	"       jnz 1b               ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
-	:
-	: "memory");
-
-	kernel_fpu_end();
-}
-
-static void
-xor_p5_mmx_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	     unsigned long *p3, unsigned long *p4, unsigned long *p5)
-{
-	unsigned long lines = bytes >> 6;
-
-	kernel_fpu_begin();
-
-	/* Make sure GCC forgets anything it knows about p4 or p5,
-	   such that it won't pass to the asm volatile below a
-	   register that is shared with any other variable.  That's
-	   because we modify p4 and p5 there, but we can't mark them
-	   as read/write, otherwise we'd overflow the 10-asm-operands
-	   limit of GCC < 3.1.  */
-	asm("" : "+r" (p4), "+r" (p5));
-
-	asm volatile(
-	" .align 32,0x90             ;\n"
-	" 1:                         ;\n"
-	"       movq   (%1), %%mm0   ;\n"
-	"       movq  8(%1), %%mm1   ;\n"
-	"       pxor   (%2), %%mm0   ;\n"
-	"       pxor  8(%2), %%mm1   ;\n"
-	"       movq 16(%1), %%mm2   ;\n"
-	"       pxor   (%3), %%mm0   ;\n"
-	"       pxor  8(%3), %%mm1   ;\n"
-	"       pxor 16(%2), %%mm2   ;\n"
-	"       pxor   (%4), %%mm0   ;\n"
-	"       pxor  8(%4), %%mm1   ;\n"
-	"       pxor 16(%3), %%mm2   ;\n"
-	"       movq 24(%1), %%mm3   ;\n"
-	"       pxor   (%5), %%mm0   ;\n"
-	"       pxor  8(%5), %%mm1   ;\n"
-	"       movq %%mm0,   (%1)   ;\n"
-	"       pxor 16(%4), %%mm2   ;\n"
-	"       pxor 24(%2), %%mm3   ;\n"
-	"       movq %%mm1,  8(%1)   ;\n"
-	"       pxor 16(%5), %%mm2   ;\n"
-	"       pxor 24(%3), %%mm3   ;\n"
-	"       movq 32(%1), %%mm4   ;\n"
-	"       movq %%mm2, 16(%1)   ;\n"
-	"       pxor 24(%4), %%mm3   ;\n"
-	"       pxor 32(%2), %%mm4   ;\n"
-	"       movq 40(%1), %%mm5   ;\n"
-	"       pxor 24(%5), %%mm3   ;\n"
-	"       pxor 32(%3), %%mm4   ;\n"
-	"       pxor 40(%2), %%mm5   ;\n"
-	"       movq %%mm3, 24(%1)   ;\n"
-	"       pxor 32(%4), %%mm4   ;\n"
-	"       pxor 40(%3), %%mm5   ;\n"
-	"       movq 48(%1), %%mm6   ;\n"
-	"       movq 56(%1), %%mm7   ;\n"
-	"       pxor 32(%5), %%mm4   ;\n"
-	"       pxor 40(%4), %%mm5   ;\n"
-	"       pxor 48(%2), %%mm6   ;\n"
-	"       pxor 56(%2), %%mm7   ;\n"
-	"       movq %%mm4, 32(%1)   ;\n"
-	"       pxor 48(%3), %%mm6   ;\n"
-	"       pxor 56(%3), %%mm7   ;\n"
-	"       pxor 40(%5), %%mm5   ;\n"
-	"       pxor 48(%4), %%mm6   ;\n"
-	"       pxor 56(%4), %%mm7   ;\n"
-	"       movq %%mm5, 40(%1)   ;\n"
-	"       pxor 48(%5), %%mm6   ;\n"
-	"       pxor 56(%5), %%mm7   ;\n"
-	"       movq %%mm6, 48(%1)   ;\n"
-	"       movq %%mm7, 56(%1)   ;\n"
-
-	"       addl $64, %1         ;\n"
-	"       addl $64, %2         ;\n"
-	"       addl $64, %3         ;\n"
-	"       addl $64, %4         ;\n"
-	"       addl $64, %5         ;\n"
-	"       decl %0              ;\n"
-	"       jnz 1b               ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r" (p2), "+r" (p3)
-	: "r" (p4), "r" (p5)
-	: "memory");
-
-	/* p4 and p5 were modified, and now the variables are dead.
-	   Clobber them just to be sure nobody does something stupid
-	   like assuming they have some legal value.  */
-	asm("" : "=r" (p4), "=r" (p5));
-
-	kernel_fpu_end();
-}
-
-static struct xor_block_template xor_block_pII_mmx = {
-	.name = "pII_mmx",
-	.do_2 = xor_pII_mmx_2,
-	.do_3 = xor_pII_mmx_3,
-	.do_4 = xor_pII_mmx_4,
-	.do_5 = xor_pII_mmx_5,
-};
-
-static struct xor_block_template xor_block_p5_mmx = {
-	.name = "p5_mmx",
-	.do_2 = xor_p5_mmx_2,
-	.do_3 = xor_p5_mmx_3,
-	.do_4 = xor_p5_mmx_4,
-	.do_5 = xor_p5_mmx_5,
-};
-
-/*
- * Cache avoiding checksumming functions utilizing KNI instructions
- * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
- */
-
-#define XMMS_SAVE				\
-do {						\
-	preempt_disable();			\
-	cr0 = read_cr0();			\
-	clts();					\
-	asm volatile(				\
-		"movups %%xmm0,(%0)	;\n\t"	\
-		"movups %%xmm1,0x10(%0)	;\n\t"	\
-		"movups %%xmm2,0x20(%0)	;\n\t"	\
-		"movups %%xmm3,0x30(%0)	;\n\t"	\
-		:				\
-		: "r" (xmm_save) 		\
-		: "memory");			\
-} while (0)
-
-#define XMMS_RESTORE				\
-do {						\
-	asm volatile(				\
-		"sfence			;\n\t"	\
-		"movups (%0),%%xmm0	;\n\t"	\
-		"movups 0x10(%0),%%xmm1	;\n\t"	\
-		"movups 0x20(%0),%%xmm2	;\n\t"	\
-		"movups 0x30(%0),%%xmm3	;\n\t"	\
-		:				\
-		: "r" (xmm_save)		\
-		: "memory");			\
-	write_cr0(cr0);				\
-	preempt_enable();			\
-} while (0)
-
-#define ALIGN16 __attribute__((aligned(16)))
-
-#define OFFS(x)		"16*("#x")"
-#define PF_OFFS(x)	"256+16*("#x")"
-#define	PF0(x)		"	prefetchnta "PF_OFFS(x)"(%1)		;\n"
-#define LD(x, y)	"       movaps   "OFFS(x)"(%1), %%xmm"#y"	;\n"
-#define ST(x, y)	"       movaps %%xmm"#y",   "OFFS(x)"(%1)	;\n"
-#define PF1(x)		"	prefetchnta "PF_OFFS(x)"(%2)		;\n"
-#define PF2(x)		"	prefetchnta "PF_OFFS(x)"(%3)		;\n"
-#define PF3(x)		"	prefetchnta "PF_OFFS(x)"(%4)		;\n"
-#define PF4(x)		"	prefetchnta "PF_OFFS(x)"(%5)		;\n"
-#define PF5(x)		"	prefetchnta "PF_OFFS(x)"(%6)		;\n"
-#define XO1(x, y)	"       xorps   "OFFS(x)"(%2), %%xmm"#y"	;\n"
-#define XO2(x, y)	"       xorps   "OFFS(x)"(%3), %%xmm"#y"	;\n"
-#define XO3(x, y)	"       xorps   "OFFS(x)"(%4), %%xmm"#y"	;\n"
-#define XO4(x, y)	"       xorps   "OFFS(x)"(%5), %%xmm"#y"	;\n"
-#define XO5(x, y)	"       xorps   "OFFS(x)"(%6), %%xmm"#y"	;\n"
-
-
-static void
-xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
-{
-	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
-
-	XMMS_SAVE;
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i)					\
-		LD(i, 0)				\
-			LD(i + 1, 1)			\
-		PF1(i)					\
-				PF1(i + 2)		\
-				LD(i + 2, 2)		\
-					LD(i + 3, 3)	\
-		PF0(i + 4)				\
-				PF0(i + 6)		\
-		XO1(i, 0)				\
-			XO1(i + 1, 1)			\
-				XO1(i + 2, 2)		\
-					XO1(i + 3, 3)	\
-		ST(i, 0)				\
-			ST(i + 1, 1)			\
-				ST(i + 2, 2)		\
-					ST(i + 3, 3)	\
-
-
-		PF0(0)
-				PF0(2)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-		BLOCK(0)
-		BLOCK(4)
-		BLOCK(8)
-		BLOCK(12)
-
-	"       addl $256, %1           ;\n"
-	"       addl $256, %2           ;\n"
-	"       decl %0                 ;\n"
-	"       jnz 1b                  ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r" (p2)
-	:
-	: "memory");
-
-	XMMS_RESTORE;
-}
-
-static void
-xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	  unsigned long *p3)
-{
-	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
-
-	XMMS_SAVE;
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i) \
-		PF1(i)					\
-				PF1(i + 2)		\
-		LD(i,0)					\
-			LD(i + 1, 1)			\
-				LD(i + 2, 2)		\
-					LD(i + 3, 3)	\
-		PF2(i)					\
-				PF2(i + 2)		\
-		PF0(i + 4)				\
-				PF0(i + 6)		\
-		XO1(i,0)				\
-			XO1(i + 1, 1)			\
-				XO1(i + 2, 2)		\
-					XO1(i + 3, 3)	\
-		XO2(i,0)				\
-			XO2(i + 1, 1)			\
-				XO2(i + 2, 2)		\
-					XO2(i + 3, 3)	\
-		ST(i,0)					\
-			ST(i + 1, 1)			\
-				ST(i + 2, 2)		\
-					ST(i + 3, 3)	\
-
-
-		PF0(0)
-				PF0(2)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-		BLOCK(0)
-		BLOCK(4)
-		BLOCK(8)
-		BLOCK(12)
-
-	"       addl $256, %1           ;\n"
-	"       addl $256, %2           ;\n"
-	"       addl $256, %3           ;\n"
-	"       decl %0                 ;\n"
-	"       jnz 1b                  ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r"(p2), "+r"(p3)
-	:
-	: "memory" );
-
-	XMMS_RESTORE;
-}
-
-static void
-xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	  unsigned long *p3, unsigned long *p4)
-{
-	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
-
-	XMMS_SAVE;
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i) \
-		PF1(i)					\
-				PF1(i + 2)		\
-		LD(i,0)					\
-			LD(i + 1, 1)			\
-				LD(i + 2, 2)		\
-					LD(i + 3, 3)	\
-		PF2(i)					\
-				PF2(i + 2)		\
-		XO1(i,0)				\
-			XO1(i + 1, 1)			\
-				XO1(i + 2, 2)		\
-					XO1(i + 3, 3)	\
-		PF3(i)					\
-				PF3(i + 2)		\
-		PF0(i + 4)				\
-				PF0(i + 6)		\
-		XO2(i,0)				\
-			XO2(i + 1, 1)			\
-				XO2(i + 2, 2)		\
-					XO2(i + 3, 3)	\
-		XO3(i,0)				\
-			XO3(i + 1, 1)			\
-				XO3(i + 2, 2)		\
-					XO3(i + 3, 3)	\
-		ST(i,0)					\
-			ST(i + 1, 1)			\
-				ST(i + 2, 2)		\
-					ST(i + 3, 3)	\
-
-
-		PF0(0)
-				PF0(2)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-		BLOCK(0)
-		BLOCK(4)
-		BLOCK(8)
-		BLOCK(12)
-
-	"       addl $256, %1           ;\n"
-	"       addl $256, %2           ;\n"
-	"       addl $256, %3           ;\n"
-	"       addl $256, %4           ;\n"
-	"       decl %0                 ;\n"
-	"       jnz 1b                  ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r" (p2), "+r" (p3), "+r" (p4)
-	:
-	: "memory" );
-
-	XMMS_RESTORE;
-}
-
-static void
-xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	  unsigned long *p3, unsigned long *p4, unsigned long *p5)
-{
-	unsigned long lines = bytes >> 8;
-	char xmm_save[16*4] ALIGN16;
-	int cr0;
-
-	XMMS_SAVE;
-
-	/* Make sure GCC forgets anything it knows about p4 or p5,
-	   such that it won't pass to the asm volatile below a
-	   register that is shared with any other variable.  That's
-	   because we modify p4 and p5 there, but we can't mark them
-	   as read/write, otherwise we'd overflow the 10-asm-operands
-	   limit of GCC < 3.1.  */
-	asm("" : "+r" (p4), "+r" (p5));
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i) \
-		PF1(i)					\
-				PF1(i + 2)		\
-		LD(i,0)					\
-			LD(i + 1, 1)			\
-				LD(i + 2, 2)		\
-					LD(i + 3, 3)	\
-		PF2(i)					\
-				PF2(i + 2)		\
-		XO1(i,0)				\
-			XO1(i + 1, 1)			\
-				XO1(i + 2, 2)		\
-					XO1(i + 3, 3)	\
-		PF3(i)					\
-				PF3(i + 2)		\
-		XO2(i,0)				\
-			XO2(i + 1, 1)			\
-				XO2(i + 2, 2)		\
-					XO2(i + 3, 3)	\
-		PF4(i)					\
-				PF4(i + 2)		\
-		PF0(i + 4)				\
-				PF0(i + 6)		\
-		XO3(i,0)				\
-			XO3(i + 1, 1)			\
-				XO3(i + 2, 2)		\
-					XO3(i + 3, 3)	\
-		XO4(i,0)				\
-			XO4(i + 1, 1)			\
-				XO4(i + 2, 2)		\
-					XO4(i + 3, 3)	\
-		ST(i,0)					\
-			ST(i + 1, 1)			\
-				ST(i + 2, 2)		\
-					ST(i + 3, 3)	\
-
-
-		PF0(0)
-				PF0(2)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-		BLOCK(0)
-		BLOCK(4)
-		BLOCK(8)
-		BLOCK(12)
-
-	"       addl $256, %1           ;\n"
-	"       addl $256, %2           ;\n"
-	"       addl $256, %3           ;\n"
-	"       addl $256, %4           ;\n"
-	"       addl $256, %5           ;\n"
-	"       decl %0                 ;\n"
-	"       jnz 1b                  ;\n"
-	: "+r" (lines),
-	  "+r" (p1), "+r" (p2), "+r" (p3)
-	: "r" (p4), "r" (p5)
-	: "memory");
-
-	/* p4 and p5 were modified, and now the variables are dead.
-	   Clobber them just to be sure nobody does something stupid
-	   like assuming they have some legal value.  */
-	asm("" : "=r" (p4), "=r" (p5));
-
-	XMMS_RESTORE;
-}
-
-static struct xor_block_template xor_block_pIII_sse = {
-	.name = "pIII_sse",
-	.do_2 = xor_sse_2,
-	.do_3 = xor_sse_3,
-	.do_4 = xor_sse_4,
-	.do_5 = xor_sse_5,
-};
-
-/* Also try the generic routines.  */
-#include <asm-generic/xor.h>
-
-#undef XOR_TRY_TEMPLATES
-#define XOR_TRY_TEMPLATES				\
-do {							\
-	xor_speed(&xor_block_8regs);			\
-	xor_speed(&xor_block_8regs_p);			\
-	xor_speed(&xor_block_32regs);			\
-	xor_speed(&xor_block_32regs_p);			\
-	if (cpu_has_xmm)				\
-		xor_speed(&xor_block_pIII_sse);		\
-	if (cpu_has_mmx) {				\
-		xor_speed(&xor_block_pII_mmx);		\
-		xor_speed(&xor_block_p5_mmx);		\
-	}						\
-} while (0)
-
-/* We force the use of the SSE xor block because it can write around L2.
-   We may also be able to load into the L1 only depending on how the cpu
-   deals with a load to a line that is being prefetched.  */
-#define XOR_SELECT_TEMPLATE(FASTEST)			\
-	(cpu_has_xmm ? &xor_block_pIII_sse : FASTEST)
-
-#endif /* ASM_X86__XOR_32_H */
diff --git a/include/asm-x86/xor_64.h b/include/asm-x86/xor_64.h
deleted file mode 100644
index 2d3a18de295b..000000000000
--- a/include/asm-x86/xor_64.h
+++ /dev/null
@@ -1,361 +0,0 @@
-#ifndef ASM_X86__XOR_64_H
-#define ASM_X86__XOR_64_H
-
-/*
- * Optimized RAID-5 checksumming functions for MMX and SSE.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2, or (at your option)
- * any later version.
- *
- * You should have received a copy of the GNU General Public License
- * (for example /usr/src/linux/COPYING); if not, write to the Free
- * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-
-/*
- * Cache avoiding checksumming functions utilizing KNI instructions
- * Copyright (C) 1999 Zach Brown (with obvious credit due Ingo)
- */
-
-/*
- * Based on
- * High-speed RAID5 checksumming functions utilizing SSE instructions.
- * Copyright (C) 1998 Ingo Molnar.
- */
-
-/*
- * x86-64 changes / gcc fixes from Andi Kleen.
- * Copyright 2002 Andi Kleen, SuSE Labs.
- *
- * This hasn't been optimized for the hammer yet, but there are likely
- * no advantages to be gotten from x86-64 here anyways.
- */
-
-typedef struct {
-	unsigned long a, b;
-} __attribute__((aligned(16))) xmm_store_t;
-
-/* Doesn't use gcc to save the XMM registers, because there is no easy way to
-   tell it to do a clts before the register saving. */
-#define XMMS_SAVE				\
-do {						\
-	preempt_disable();			\
-	asm volatile(				\
-		"movq %%cr0,%0		;\n\t"	\
-		"clts			;\n\t"	\
-		"movups %%xmm0,(%1)	;\n\t"	\
-		"movups %%xmm1,0x10(%1)	;\n\t"	\
-		"movups %%xmm2,0x20(%1)	;\n\t"	\
-		"movups %%xmm3,0x30(%1)	;\n\t"	\
-		: "=&r" (cr0)			\
-		: "r" (xmm_save) 		\
-		: "memory");			\
-} while (0)
-
-#define XMMS_RESTORE				\
-do {						\
-	asm volatile(				\
-		"sfence			;\n\t"	\
-		"movups (%1),%%xmm0	;\n\t"	\
-		"movups 0x10(%1),%%xmm1	;\n\t"	\
-		"movups 0x20(%1),%%xmm2	;\n\t"	\
-		"movups 0x30(%1),%%xmm3	;\n\t"	\
-		"movq 	%0,%%cr0	;\n\t"	\
-		:				\
-		: "r" (cr0), "r" (xmm_save)	\
-		: "memory");			\
-	preempt_enable();			\
-} while (0)
-
-#define OFFS(x)		"16*("#x")"
-#define PF_OFFS(x)	"256+16*("#x")"
-#define	PF0(x)		"	prefetchnta "PF_OFFS(x)"(%[p1])		;\n"
-#define LD(x, y)	"       movaps   "OFFS(x)"(%[p1]), %%xmm"#y"	;\n"
-#define ST(x, y)	"       movaps %%xmm"#y",   "OFFS(x)"(%[p1])	;\n"
-#define PF1(x)		"	prefetchnta "PF_OFFS(x)"(%[p2])		;\n"
-#define PF2(x)		"	prefetchnta "PF_OFFS(x)"(%[p3])		;\n"
-#define PF3(x)		"	prefetchnta "PF_OFFS(x)"(%[p4])		;\n"
-#define PF4(x)		"	prefetchnta "PF_OFFS(x)"(%[p5])		;\n"
-#define PF5(x)		"	prefetchnta "PF_OFFS(x)"(%[p6])		;\n"
-#define XO1(x, y)	"       xorps   "OFFS(x)"(%[p2]), %%xmm"#y"	;\n"
-#define XO2(x, y)	"       xorps   "OFFS(x)"(%[p3]), %%xmm"#y"	;\n"
-#define XO3(x, y)	"       xorps   "OFFS(x)"(%[p4]), %%xmm"#y"	;\n"
-#define XO4(x, y)	"       xorps   "OFFS(x)"(%[p5]), %%xmm"#y"	;\n"
-#define XO5(x, y)	"       xorps   "OFFS(x)"(%[p6]), %%xmm"#y"	;\n"
-
-
-static void
-xor_sse_2(unsigned long bytes, unsigned long *p1, unsigned long *p2)
-{
-	unsigned int lines = bytes >> 8;
-	unsigned long cr0;
-	xmm_store_t xmm_save[4];
-
-	XMMS_SAVE;
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i) \
-		LD(i, 0)				\
-			LD(i + 1, 1)			\
-		PF1(i)					\
-				PF1(i + 2)		\
-				LD(i + 2, 2)		\
-					LD(i + 3, 3)	\
-		PF0(i + 4)				\
-				PF0(i + 6)		\
-		XO1(i, 0)				\
-			XO1(i + 1, 1)			\
-				XO1(i + 2, 2)		\
-					XO1(i + 3, 3)	\
-		ST(i, 0)				\
-			ST(i + 1, 1)			\
-				ST(i + 2, 2)		\
-					ST(i + 3, 3)	\
-
-
-		PF0(0)
-				PF0(2)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-		BLOCK(0)
-		BLOCK(4)
-		BLOCK(8)
-		BLOCK(12)
-
-	"       addq %[inc], %[p1]           ;\n"
-	"       addq %[inc], %[p2]           ;\n"
-		"		decl %[cnt] ; jnz 1b"
-	: [p1] "+r" (p1), [p2] "+r" (p2), [cnt] "+r" (lines)
-	: [inc] "r" (256UL)
-	: "memory");
-
-	XMMS_RESTORE;
-}
-
-static void
-xor_sse_3(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	  unsigned long *p3)
-{
-	unsigned int lines = bytes >> 8;
-	xmm_store_t xmm_save[4];
-	unsigned long cr0;
-
-	XMMS_SAVE;
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i) \
-		PF1(i)					\
-				PF1(i + 2)		\
-		LD(i, 0)					\
-			LD(i + 1, 1)			\
-				LD(i + 2, 2)		\
-					LD(i + 3, 3)	\
-		PF2(i)					\
-				PF2(i + 2)		\
-		PF0(i + 4)				\
-				PF0(i + 6)		\
-		XO1(i, 0)				\
-			XO1(i + 1, 1)			\
-				XO1(i + 2, 2)		\
-					XO1(i + 3, 3)	\
-		XO2(i, 0)				\
-			XO2(i + 1, 1)			\
-				XO2(i + 2, 2)		\
-					XO2(i + 3, 3)	\
-		ST(i, 0)				\
-			ST(i + 1, 1)			\
-				ST(i + 2, 2)		\
-					ST(i + 3, 3)	\
-
-
-		PF0(0)
-				PF0(2)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-		BLOCK(0)
-		BLOCK(4)
-		BLOCK(8)
-		BLOCK(12)
-
-	"       addq %[inc], %[p1]           ;\n"
-	"       addq %[inc], %[p2]          ;\n"
-	"       addq %[inc], %[p3]           ;\n"
-		"		decl %[cnt] ; jnz 1b"
-	: [cnt] "+r" (lines),
-	  [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3)
-	: [inc] "r" (256UL)
-	: "memory");
-	XMMS_RESTORE;
-}
-
-static void
-xor_sse_4(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	  unsigned long *p3, unsigned long *p4)
-{
-	unsigned int lines = bytes >> 8;
-	xmm_store_t xmm_save[4];
-	unsigned long cr0;
-
-	XMMS_SAVE;
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i) \
-		PF1(i)					\
-				PF1(i + 2)		\
-		LD(i, 0)				\
-			LD(i + 1, 1)			\
-				LD(i + 2, 2)		\
-					LD(i + 3, 3)	\
-		PF2(i)					\
-				PF2(i + 2)		\
-		XO1(i, 0)				\
-			XO1(i + 1, 1)			\
-				XO1(i + 2, 2)		\
-					XO1(i + 3, 3)	\
-		PF3(i)					\
-				PF3(i + 2)		\
-		PF0(i + 4)				\
-				PF0(i + 6)		\
-		XO2(i, 0)				\
-			XO2(i + 1, 1)			\
-				XO2(i + 2, 2)		\
-					XO2(i + 3, 3)	\
-		XO3(i, 0)				\
-			XO3(i + 1, 1)			\
-				XO3(i + 2, 2)		\
-					XO3(i + 3, 3)	\
-		ST(i, 0)				\
-			ST(i + 1, 1)			\
-				ST(i + 2, 2)		\
-					ST(i + 3, 3)	\
-
-
-		PF0(0)
-				PF0(2)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-		BLOCK(0)
-		BLOCK(4)
-		BLOCK(8)
-		BLOCK(12)
-
-	"       addq %[inc], %[p1]           ;\n"
-	"       addq %[inc], %[p2]           ;\n"
-	"       addq %[inc], %[p3]           ;\n"
-	"       addq %[inc], %[p4]           ;\n"
-	"	decl %[cnt] ; jnz 1b"
-	: [cnt] "+c" (lines),
-	  [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4)
-	: [inc] "r" (256UL)
-	: "memory" );
-
-	XMMS_RESTORE;
-}
-
-static void
-xor_sse_5(unsigned long bytes, unsigned long *p1, unsigned long *p2,
-	  unsigned long *p3, unsigned long *p4, unsigned long *p5)
-{
-	unsigned int lines = bytes >> 8;
-	xmm_store_t xmm_save[4];
-	unsigned long cr0;
-
-	XMMS_SAVE;
-
-	asm volatile(
-#undef BLOCK
-#define BLOCK(i) \
-		PF1(i)					\
-				PF1(i + 2)		\
-		LD(i, 0)				\
-			LD(i + 1, 1)			\
-				LD(i + 2, 2)		\
-					LD(i + 3, 3)	\
-		PF2(i)					\
-				PF2(i + 2)		\
-		XO1(i, 0)				\
-			XO1(i + 1, 1)			\
-				XO1(i + 2, 2)		\
-					XO1(i + 3, 3)	\
-		PF3(i)					\
-				PF3(i + 2)		\
-		XO2(i, 0)				\
-			XO2(i + 1, 1)			\
-				XO2(i + 2, 2)		\
-					XO2(i + 3, 3)	\
-		PF4(i)					\
-				PF4(i + 2)		\
-		PF0(i + 4)				\
-				PF0(i + 6)		\
-		XO3(i, 0)				\
-			XO3(i + 1, 1)			\
-				XO3(i + 2, 2)		\
-					XO3(i + 3, 3)	\
-		XO4(i, 0)				\
-			XO4(i + 1, 1)			\
-				XO4(i + 2, 2)		\
-					XO4(i + 3, 3)	\
-		ST(i, 0)				\
-			ST(i + 1, 1)			\
-				ST(i + 2, 2)		\
-					ST(i + 3, 3)	\
-
-
-		PF0(0)
-				PF0(2)
-
-	" .align 32			;\n"
-	" 1:                            ;\n"
-
-		BLOCK(0)
-		BLOCK(4)
-		BLOCK(8)
-		BLOCK(12)
-
-	"       addq %[inc], %[p1]           ;\n"
-	"       addq %[inc], %[p2]           ;\n"
-	"       addq %[inc], %[p3]           ;\n"
-	"       addq %[inc], %[p4]           ;\n"
-	"       addq %[inc], %[p5]           ;\n"
-	"	decl %[cnt] ; jnz 1b"
-	: [cnt] "+c" (lines),
-	  [p1] "+r" (p1), [p2] "+r" (p2), [p3] "+r" (p3), [p4] "+r" (p4),
-	  [p5] "+r" (p5)
-	: [inc] "r" (256UL)
-	: "memory");
-
-	XMMS_RESTORE;
-}
-
-static struct xor_block_template xor_block_sse = {
-	.name = "generic_sse",
-	.do_2 = xor_sse_2,
-	.do_3 = xor_sse_3,
-	.do_4 = xor_sse_4,
-	.do_5 = xor_sse_5,
-};
-
-#undef XOR_TRY_TEMPLATES
-#define XOR_TRY_TEMPLATES			\
-do {						\
-	xor_speed(&xor_block_sse);		\
-} while (0)
-
-/* We force the use of the SSE xor block because it can write around L2.
-   We may also be able to load into the L1 only depending on how the cpu
-   deals with a load to a line that is being prefetched.  */
-#define XOR_SELECT_TEMPLATE(FASTEST) (&xor_block_sse)
-
-#endif /* ASM_X86__XOR_64_H */
diff --git a/include/asm-x86/xsave.h b/include/asm-x86/xsave.h
deleted file mode 100644
index 08e9a1ac07a9..000000000000
--- a/include/asm-x86/xsave.h
+++ /dev/null
@@ -1,118 +0,0 @@
-#ifndef __ASM_X86_XSAVE_H
-#define __ASM_X86_XSAVE_H
-
-#include <linux/types.h>
-#include <asm/processor.h>
-#include <asm/i387.h>
-
-#define XSTATE_FP	0x1
-#define XSTATE_SSE	0x2
-
-#define XSTATE_FPSSE	(XSTATE_FP | XSTATE_SSE)
-
-#define FXSAVE_SIZE	512
-
-/*
- * These are the features that the OS can handle currently.
- */
-#define XCNTXT_MASK	(XSTATE_FP | XSTATE_SSE)
-
-#ifdef CONFIG_X86_64
-#define REX_PREFIX	"0x48, "
-#else
-#define REX_PREFIX
-#endif
-
-extern unsigned int xstate_size;
-extern u64 pcntxt_mask;
-extern struct xsave_struct *init_xstate_buf;
-
-extern void xsave_cntxt_init(void);
-extern void xsave_init(void);
-extern int init_fpu(struct task_struct *child);
-extern int check_for_xstate(struct i387_fxsave_struct __user *buf,
-			    void __user *fpstate,
-			    struct _fpx_sw_bytes *sw);
-
-static inline int xrstor_checking(struct xsave_struct *fx)
-{
-	int err;
-
-	asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err)
-		     : "D" (fx), "m" (*fx), "a" (-1), "d" (-1), "0" (0)
-		     : "memory");
-
-	return err;
-}
-
-static inline int xsave_user(struct xsave_struct __user *buf)
-{
-	int err;
-	__asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x27\n"
-			     "2:\n"
-			     ".section .fixup,\"ax\"\n"
-			     "3:  movl $-1,%[err]\n"
-			     "    jmp  2b\n"
-			     ".previous\n"
-			     ".section __ex_table,\"a\"\n"
-			     _ASM_ALIGN "\n"
-			     _ASM_PTR "1b,3b\n"
-			     ".previous"
-			     : [err] "=r" (err)
-			     : "D" (buf), "a" (-1), "d" (-1), "0" (0)
-			     : "memory");
-	if (unlikely(err) && __clear_user(buf, xstate_size))
-		err = -EFAULT;
-	/* No need to clear here because the caller clears USED_MATH */
-	return err;
-}
-
-static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
-{
-	int err;
-	struct xsave_struct *xstate = ((__force struct xsave_struct *)buf);
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-
-	__asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n"
-			     "2:\n"
-			     ".section .fixup,\"ax\"\n"
-			     "3:  movl $-1,%[err]\n"
-			     "    jmp  2b\n"
-			     ".previous\n"
-			     ".section __ex_table,\"a\"\n"
-			     _ASM_ALIGN "\n"
-			     _ASM_PTR "1b,3b\n"
-			     ".previous"
-			     : [err] "=r" (err)
-			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
-			     : "memory");	/* memory required? */
-	return err;
-}
-
-static inline void xrstor_state(struct xsave_struct *fx, u64 mask)
-{
-	u32 lmask = mask;
-	u32 hmask = mask >> 32;
-
-	asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
-		     : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
-		     :   "memory");
-}
-
-static inline void xsave(struct task_struct *tsk)
-{
-	/* This, however, we can work around by forcing the compiler to select
-	   an addressing mode that doesn't require extended registers. */
-	__asm__ __volatile__(".byte " REX_PREFIX "0x0f,0xae,0x27"
-			     : : "D" (&(tsk->thread.xstate->xsave)),
-				 "a" (-1), "d"(-1) : "memory");
-}
-#endif
diff --git a/scripts/checksyscalls.sh b/scripts/checksyscalls.sh
index 366f8c7f62bf..41564b142c04 100755
--- a/scripts/checksyscalls.sh
+++ b/scripts/checksyscalls.sh
@@ -119,5 +119,5 @@ sed -n -e '/^\#define/ { s/[^_]*__NR_\([^[:space:]]*\).*/\
 \#endif/p }' $1
 }
 
-(ignore_list && syscall_list ${srctree}/include/asm-x86/unistd_32.h) | \
+(ignore_list && syscall_list ${srctree}/arch/x86/include/asm/unistd_32.h) | \
 $* -E -x c - > /dev/null
-- 
cgit v1.2.3


From d181146572c4fa9af2a068b967cb53dcac7da944 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 2 Aug 2008 00:49:18 -0400
Subject: [PATCH] new helper - kern_path()

Analog of lookup_path(), takes struct path *.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c            | 10 ++++++++++
 include/linux/namei.h |  2 ++
 2 files changed, 12 insertions(+)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index 4ea63ed5e791..4a56f9b59e8c 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1106,6 +1106,15 @@ int path_lookup(const char *name, unsigned int flags,
 	return do_path_lookup(AT_FDCWD, name, flags, nd);
 }
 
+int kern_path(const char *name, unsigned int flags, struct path *path)
+{
+	struct nameidata nd;
+	int res = do_path_lookup(AT_FDCWD, name, flags, &nd);
+	if (!res)
+		*path = nd.path;
+	return res;
+}
+
 /**
  * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair
  * @dentry:  pointer to dentry of the base directory
@@ -2855,6 +2864,7 @@ EXPORT_SYMBOL(__page_symlink);
 EXPORT_SYMBOL(page_symlink);
 EXPORT_SYMBOL(page_symlink_inode_operations);
 EXPORT_SYMBOL(path_lookup);
+EXPORT_SYMBOL(kern_path);
 EXPORT_SYMBOL(vfs_path_lookup);
 EXPORT_SYMBOL(inode_permission);
 EXPORT_SYMBOL(vfs_permission);
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 68f8c3203c89..221e8bc894ba 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -61,6 +61,8 @@ extern int user_path_at(int, const char __user *, unsigned, struct path *);
 #define user_path_dir(name, path) \
 	user_path_at(AT_FDCWD, name, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, path)
 
+extern int kern_path(const char *, unsigned, struct path *);
+
 extern int path_lookup(const char *, unsigned, struct nameidata *);
 extern int vfs_path_lookup(struct dentry *, struct vfsmount *,
 			   const char *, unsigned int, struct nameidata *);
-- 
cgit v1.2.3


From 2e3f92dad6bdbee796274bae5c1c50a6ddd31cbb Mon Sep 17 00:00:00 2001
From: Wei Yongjun <yjwei@cn.fujitsu.com>
Date: Thu, 23 Oct 2008 01:01:18 -0700
Subject: sctp: Fix to handle SHUTDOWN in SHUTDOWN_RECEIVED state

Once an endpoint has reached the SHUTDOWN-RECEIVED state,
it MUST NOT send a SHUTDOWN in response to a ULP request.
The Cumulative TSN Ack of the received SHUTDOWN chunk
MUST be processed.

This patch fix to process Cumulative TSN Ack of the received
SHUTDOWN chunk in SHUTDOWN_RECEIVED state.

Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com>
Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/sm.h    |  1 +
 net/sctp/sm_statefuns.c  | 45 +++++++++++++++++++++++++++++++++++++++++++++
 net/sctp/sm_statetable.c |  2 +-
 3 files changed, 47 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h
index 029a54a02396..c1dd89365833 100644
--- a/include/net/sctp/sm.h
+++ b/include/net/sctp/sm.h
@@ -125,6 +125,7 @@ sctp_state_fn_t sctp_sf_beat_8_3;
 sctp_state_fn_t sctp_sf_backbeat_8_3;
 sctp_state_fn_t sctp_sf_do_9_2_final;
 sctp_state_fn_t sctp_sf_do_9_2_shutdown;
+sctp_state_fn_t sctp_sf_do_9_2_shut_ctsn;
 sctp_state_fn_t sctp_sf_do_ecn_cwr;
 sctp_state_fn_t sctp_sf_do_ecne;
 sctp_state_fn_t sctp_sf_ootb;
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 12f62174f4a1..a6a0ea71ae93 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -2608,6 +2608,51 @@ out:
 	return disposition;
 }
 
+/*
+ * sctp_sf_do_9_2_shut_ctsn
+ *
+ * Once an endpoint has reached the SHUTDOWN-RECEIVED state,
+ * it MUST NOT send a SHUTDOWN in response to a ULP request.
+ * The Cumulative TSN Ack of the received SHUTDOWN chunk
+ * MUST be processed.
+ */
+sctp_disposition_t sctp_sf_do_9_2_shut_ctsn(const struct sctp_endpoint *ep,
+					   const struct sctp_association *asoc,
+					   const sctp_subtype_t type,
+					   void *arg,
+					   sctp_cmd_seq_t *commands)
+{
+	struct sctp_chunk *chunk = arg;
+	sctp_shutdownhdr_t *sdh;
+
+	if (!sctp_vtag_verify(chunk, asoc))
+		return sctp_sf_pdiscard(ep, asoc, type, arg, commands);
+
+	/* Make sure that the SHUTDOWN chunk has a valid length. */
+	if (!sctp_chunk_length_valid(chunk,
+				      sizeof(struct sctp_shutdown_chunk_t)))
+		return sctp_sf_violation_chunklen(ep, asoc, type, arg,
+						  commands);
+
+	sdh = (sctp_shutdownhdr_t *)chunk->skb->data;
+
+	/* If Cumulative TSN Ack beyond the max tsn currently
+	 * send, terminating the association and respond to the
+	 * sender with an ABORT.
+	 */
+	if (!TSN_lt(ntohl(sdh->cum_tsn_ack), asoc->next_tsn))
+		return sctp_sf_violation_ctsn(ep, asoc, type, arg, commands);
+
+	/* verify, by checking the Cumulative TSN Ack field of the
+	 * chunk, that all its outstanding DATA chunks have been
+	 * received by the SHUTDOWN sender.
+	 */
+	sctp_add_cmd_sf(commands, SCTP_CMD_PROCESS_CTSN,
+			SCTP_BE32(sdh->cum_tsn_ack));
+
+	return SCTP_DISPOSITION_CONSUME;
+}
+
 /* RFC 2960 9.2
  * If an endpoint is in SHUTDOWN-ACK-SENT state and receives an INIT chunk
  * (e.g., if the SHUTDOWN COMPLETE was lost) with source and destination
diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c
index a5b5590dc1a6..5c8186d88c61 100644
--- a/net/sctp/sm_statetable.c
+++ b/net/sctp/sm_statetable.c
@@ -270,7 +270,7 @@ const sctp_sm_table_entry_t *sctp_sm_lookup_event(sctp_event_t event_type,
 	/* SCTP_STATE_SHUTDOWN_SENT */ \
 	TYPE_SCTP_FUNC(sctp_sf_do_9_2_shutdown_ack), \
 	/* SCTP_STATE_SHUTDOWN_RECEIVED */ \
-	TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \
+	TYPE_SCTP_FUNC(sctp_sf_do_9_2_shut_ctsn), \
 	/* SCTP_STATE_SHUTDOWN_ACK_SENT */ \
 	TYPE_SCTP_FUNC(sctp_sf_discard_chunk), \
 } /* TYPE_SCTP_SHUTDOWN */
-- 
cgit v1.2.3


From b63365a2d60268a3988285d6c3c6003d7066f93a Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Thu, 23 Oct 2008 01:11:29 -0700
Subject: net: Fix disjunct computation of netdev features

My change

    commit e2a6b85247aacc52d6ba0d9b37a99b8d1a3e0d83
    net: Enable TSO if supported by at least one device

didn't do what was intended because the netdev_compute_features
function was designed for conjunctions.  So what happened was that
it would simply take the TSO status of the last constituent device.

This patch extends it to support both conjunctions and disjunctions
under the new name of netdev_increment_features.

It also adds a new function netdev_fix_features which does the
sanity checking that usually occurs upon registration.  This ensures
that the computation doesn't result in an illegal combination
since this checking is absent when the change is initiated via
ethtool.

The two users of netdev_compute_features have been converted.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_main.c |  16 +++--
 include/linux/netdevice.h       |  12 +++-
 net/bridge/br_device.c          |   2 +-
 net/bridge/br_if.c              |  14 +++--
 net/core/dev.c                  | 135 +++++++++++++++++++++-------------------
 5 files changed, 104 insertions(+), 75 deletions(-)

(limited to 'include')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 8e2be24f3fe4..832739f38db4 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1341,18 +1341,24 @@ static int bond_compute_features(struct bonding *bond)
 	int i;
 
 	features &= ~(NETIF_F_ALL_CSUM | BOND_VLAN_FEATURES);
-	features |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
-		    NETIF_F_GSO_MASK | NETIF_F_NO_CSUM;
+	features |=  NETIF_F_GSO_MASK | NETIF_F_NO_CSUM;
+
+	if (!bond->first_slave)
+		goto done;
+
+	features &= ~NETIF_F_ONE_FOR_ALL;
 
 	bond_for_each_slave(bond, slave, i) {
-		features = netdev_compute_features(features,
-						   slave->dev->features);
+		features = netdev_increment_features(features,
+						     slave->dev->features,
+						     NETIF_F_ONE_FOR_ALL);
 		if (slave->dev->hard_header_len > max_hard_header_len)
 			max_hard_header_len = slave->dev->hard_header_len;
 	}
 
+done:
 	features |= (bond_dev->features & BOND_VLAN_FEATURES);
-	bond_dev->features = features;
+	bond_dev->features = netdev_fix_features(features, NULL);
 	bond_dev->hard_header_len = max_hard_header_len;
 
 	return 0;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 64875859d654..c8bcb59adfdf 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -541,6 +541,14 @@ struct net_device
 #define NETIF_F_V6_CSUM		(NETIF_F_GEN_CSUM | NETIF_F_IPV6_CSUM)
 #define NETIF_F_ALL_CSUM	(NETIF_F_V4_CSUM | NETIF_F_V6_CSUM)
 
+	/*
+	 * If one device supports one of these features, then enable them
+	 * for all in netdev_increment_features.
+	 */
+#define NETIF_F_ONE_FOR_ALL	(NETIF_F_GSO_SOFTWARE | NETIF_F_GSO_ROBUST | \
+				 NETIF_F_SG | NETIF_F_HIGHDMA | \
+				 NETIF_F_FRAGLIST)
+
 	/* Interface index. Unique device identifier	*/
 	int			ifindex;
 	int			iflink;
@@ -1698,7 +1706,9 @@ extern char *netdev_drivername(const struct net_device *dev, char *buffer, int l
 
 extern void linkwatch_run_queue(void);
 
-extern int netdev_compute_features(unsigned long all, unsigned long one);
+unsigned long netdev_increment_features(unsigned long all, unsigned long one,
+					unsigned long mask);
+unsigned long netdev_fix_features(unsigned long features, const char *name);
 
 static inline int net_gso_ok(int features, int gso_type)
 {
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 22ba8632196f..6c023f0f8252 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -179,5 +179,5 @@ void br_dev_setup(struct net_device *dev)
 
 	dev->features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA |
 			NETIF_F_GSO_MASK | NETIF_F_NO_CSUM | NETIF_F_LLTX |
-			NETIF_F_NETNS_LOCAL;
+			NETIF_F_NETNS_LOCAL | NETIF_F_GSO;
 }
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 573e20f7dba4..0a09ccf68c1c 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -347,15 +347,21 @@ int br_min_mtu(const struct net_bridge *br)
 void br_features_recompute(struct net_bridge *br)
 {
 	struct net_bridge_port *p;
-	unsigned long features;
+	unsigned long features, mask;
 
-	features = br->feature_mask;
+	features = mask = br->feature_mask;
+	if (list_empty(&br->port_list))
+		goto done;
+
+	features &= ~NETIF_F_ONE_FOR_ALL;
 
 	list_for_each_entry(p, &br->port_list, list) {
-		features = netdev_compute_features(features, p->dev->features);
+		features = netdev_increment_features(features,
+						     p->dev->features, mask);
 	}
 
-	br->dev->features = features;
+done:
+	br->dev->features = netdev_fix_features(features, NULL);
 }
 
 /* called with RTNL */
diff --git a/net/core/dev.c b/net/core/dev.c
index b8a4fd0806af..d9038e328cc1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3947,6 +3947,46 @@ static void netdev_init_queue_locks(struct net_device *dev)
 	__netdev_init_queue_locks_one(dev, &dev->rx_queue, NULL);
 }
 
+unsigned long netdev_fix_features(unsigned long features, const char *name)
+{
+	/* Fix illegal SG+CSUM combinations. */
+	if ((features & NETIF_F_SG) &&
+	    !(features & NETIF_F_ALL_CSUM)) {
+		if (name)
+			printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no "
+			       "checksum feature.\n", name);
+		features &= ~NETIF_F_SG;
+	}
+
+	/* TSO requires that SG is present as well. */
+	if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) {
+		if (name)
+			printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no "
+			       "SG feature.\n", name);
+		features &= ~NETIF_F_TSO;
+	}
+
+	if (features & NETIF_F_UFO) {
+		if (!(features & NETIF_F_GEN_CSUM)) {
+			if (name)
+				printk(KERN_ERR "%s: Dropping NETIF_F_UFO "
+				       "since no NETIF_F_HW_CSUM feature.\n",
+				       name);
+			features &= ~NETIF_F_UFO;
+		}
+
+		if (!(features & NETIF_F_SG)) {
+			if (name)
+				printk(KERN_ERR "%s: Dropping NETIF_F_UFO "
+				       "since no NETIF_F_SG feature.\n", name);
+			features &= ~NETIF_F_UFO;
+		}
+	}
+
+	return features;
+}
+EXPORT_SYMBOL(netdev_fix_features);
+
 /**
  *	register_netdevice	- register a network device
  *	@dev: device to register
@@ -4032,36 +4072,7 @@ int register_netdevice(struct net_device *dev)
 		dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM);
 	}
 
-
-	/* Fix illegal SG+CSUM combinations. */
-	if ((dev->features & NETIF_F_SG) &&
-	    !(dev->features & NETIF_F_ALL_CSUM)) {
-		printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no checksum feature.\n",
-		       dev->name);
-		dev->features &= ~NETIF_F_SG;
-	}
-
-	/* TSO requires that SG is present as well. */
-	if ((dev->features & NETIF_F_TSO) &&
-	    !(dev->features & NETIF_F_SG)) {
-		printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no SG feature.\n",
-		       dev->name);
-		dev->features &= ~NETIF_F_TSO;
-	}
-	if (dev->features & NETIF_F_UFO) {
-		if (!(dev->features & NETIF_F_HW_CSUM)) {
-			printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
-					"NETIF_F_HW_CSUM feature.\n",
-							dev->name);
-			dev->features &= ~NETIF_F_UFO;
-		}
-		if (!(dev->features & NETIF_F_SG)) {
-			printk(KERN_ERR "%s: Dropping NETIF_F_UFO since no "
-					"NETIF_F_SG feature.\n",
-					dev->name);
-			dev->features &= ~NETIF_F_UFO;
-		}
-	}
+	dev->features = netdev_fix_features(dev->features, dev->name);
 
 	/* Enable software GSO if SG is supported. */
 	if (dev->features & NETIF_F_SG)
@@ -4700,49 +4711,45 @@ static int __init netdev_dma_register(void) { return -ENODEV; }
 #endif /* CONFIG_NET_DMA */
 
 /**
- *	netdev_compute_feature - compute conjunction of two feature sets
- *	@all: first feature set
- *	@one: second feature set
+ *	netdev_increment_features - increment feature set by one
+ *	@all: current feature set
+ *	@one: new feature set
+ *	@mask: mask feature set
  *
  *	Computes a new feature set after adding a device with feature set
- *	@one to the master device with current feature set @all.  Returns
- *	the new feature set.
+ *	@one to the master device with current feature set @all.  Will not
+ *	enable anything that is off in @mask. Returns the new feature set.
  */
-int netdev_compute_features(unsigned long all, unsigned long one)
-{
-	/* if device needs checksumming, downgrade to hw checksumming */
-	if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
-		all ^= NETIF_F_NO_CSUM | NETIF_F_HW_CSUM;
-
-	/* if device can't do all checksum, downgrade to ipv4/ipv6 */
-	if (all & NETIF_F_HW_CSUM && !(one & NETIF_F_HW_CSUM))
-		all ^= NETIF_F_HW_CSUM
-			| NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
-
-	if (one & NETIF_F_GSO)
-		one |= NETIF_F_GSO_SOFTWARE;
-	one |= NETIF_F_GSO;
-
-	/*
-	 * If even one device supports a GSO protocol with software fallback,
-	 * enable it for all.
-	 */
-	all |= one & NETIF_F_GSO_SOFTWARE;
+unsigned long netdev_increment_features(unsigned long all, unsigned long one,
+					unsigned long mask)
+{
+	/* If device needs checksumming, downgrade to it. */
+        if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM))
+		all ^= NETIF_F_NO_CSUM | (one & NETIF_F_ALL_CSUM);
+	else if (mask & NETIF_F_ALL_CSUM) {
+		/* If one device supports v4/v6 checksumming, set for all. */
+		if (one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM) &&
+		    !(all & NETIF_F_GEN_CSUM)) {
+			all &= ~NETIF_F_ALL_CSUM;
+			all |= one & (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
+		}
 
-	/* If even one device supports robust GSO, enable it for all. */
-	if (one & NETIF_F_GSO_ROBUST)
-		all |= NETIF_F_GSO_ROBUST;
+		/* If one device supports hw checksumming, set for all. */
+		if (one & NETIF_F_GEN_CSUM && !(all & NETIF_F_GEN_CSUM)) {
+			all &= ~NETIF_F_ALL_CSUM;
+			all |= NETIF_F_HW_CSUM;
+		}
+	}
 
-	all &= one | NETIF_F_LLTX;
+	one |= NETIF_F_ALL_CSUM;
 
-	if (!(all & NETIF_F_ALL_CSUM))
-		all &= ~NETIF_F_SG;
-	if (!(all & NETIF_F_SG))
-		all &= ~NETIF_F_GSO_MASK;
+	one |= all & NETIF_F_ONE_FOR_ALL;
+	all &= one | NETIF_F_LLTX | NETIF_F_GSO;
+	all |= one & mask & NETIF_F_ONE_FOR_ALL;
 
 	return all;
 }
-EXPORT_SYMBOL(netdev_compute_features);
+EXPORT_SYMBOL(netdev_increment_features);
 
 static struct hlist_head *netdev_create_hash(void)
 {
-- 
cgit v1.2.3


From 3516586a424ea5727be089da6541cbd5644f0497 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 5 Aug 2008 03:00:49 -0400
Subject: [PATCH] make O_EXCL in nd->intent.flags visible in nd->flags

New flag: LOOKUP_EXCL.  Set before doing the final step of pathname
resolution on the paths that have LOOKUP_CREATE and O_EXCL.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/gfs2/ops_inode.c   | 2 +-
 fs/namei.c            | 4 +++-
 fs/nfs/dir.c          | 6 ++----
 include/linux/namei.h | 5 +++--
 4 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 534e1e2c65ca..d232991b9046 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -69,7 +69,7 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry,
 			mark_inode_dirty(inode);
 			break;
 		} else if (PTR_ERR(inode) != -EEXIST ||
-			   (nd && (nd->intent.open.flags & O_EXCL))) {
+			   (nd && nd->flags & LOOKUP_EXCL)) {
 			gfs2_holder_uninit(ghs);
 			return PTR_ERR(inode);
 		}
diff --git a/fs/namei.c b/fs/namei.c
index e584f04745b5..2b8f823eda44 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1709,6 +1709,8 @@ struct file *do_filp_open(int dfd, const char *pathname,
 	dir = nd.path.dentry;
 	nd.flags &= ~LOOKUP_PARENT;
 	nd.flags |= LOOKUP_CREATE | LOOKUP_OPEN;
+	if (flag & O_EXCL)
+		nd.flags |= LOOKUP_EXCL;
 	mutex_lock(&dir->d_inode->i_mutex);
 	path.dentry = lookup_hash(&nd);
 	path.mnt = nd.path.mnt;
@@ -1906,7 +1908,7 @@ struct dentry *lookup_create(struct nameidata *nd, int is_dir)
 	if (nd->last_type != LAST_NORM)
 		goto fail;
 	nd->flags &= ~LOOKUP_PARENT;
-	nd->flags |= LOOKUP_CREATE;
+	nd->flags |= LOOKUP_CREATE | LOOKUP_EXCL;
 	nd->intent.open.flags = O_EXCL;
 
 	/*
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index efdba2e802d7..c216c8786c51 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -707,9 +707,7 @@ static int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd)
 {
 	if (NFS_PROTO(dir)->version == 2)
 		return 0;
-	if (nd == NULL || nfs_lookup_check_intent(nd, LOOKUP_CREATE) == 0)
-		return 0;
-	return (nd->intent.open.flags & O_EXCL) != 0;
+	return nd && nfs_lookup_check_intent(nd, LOOKUP_EXCL);
 }
 
 /*
@@ -1009,7 +1007,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 
 	/* Let vfs_create() deal with O_EXCL. Instantiate, but don't hash
 	 * the dentry. */
-	if (nd->intent.open.flags & O_EXCL) {
+	if (nd->flags & LOOKUP_EXCL) {
 		d_instantiate(dentry, NULL);
 		goto out;
 	}
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 221e8bc894ba..6b5627afd2eb 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -51,8 +51,9 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 /*
  * Intent data
  */
-#define LOOKUP_OPEN		(0x0100)
-#define LOOKUP_CREATE		(0x0200)
+#define LOOKUP_OPEN		0x0100
+#define LOOKUP_CREATE		0x0200
+#define LOOKUP_EXCL		0x0400
 
 extern int user_path_at(int, const char __user *, unsigned, struct path *);
 
-- 
cgit v1.2.3


From 4ea3ada2955e4519befa98ff55dd62d6dfbd1705 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 11 Aug 2008 15:48:57 +0200
Subject: [PATCH] new helper: d_obtain_alias

The calling conventions of d_alloc_anon are rather unfortunate for all
users, and it's name is not very descriptive either.

Add d_obtain_alias as a new exported helper that drops the inode
reference in the failure case, too and allows to pass-through NULL
pointers and inodes to allow for tail-calls in the export operations.

Incidentally this helper already existed as a private function in
libfs.c as exportfs_d_alloc so kill that one and switch the callers
to d_obtain_alias.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 35 +++++++++++++++++++++++++++++++++++
 fs/libfs.c             | 26 ++------------------------
 include/linux/dcache.h |  1 +
 3 files changed, 38 insertions(+), 24 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index e7a1a99b7464..46fc78206782 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1174,6 +1174,41 @@ struct dentry * d_alloc_anon(struct inode *inode)
 	return res;
 }
 
+/**
+ * d_obtain_alias - find or allocate a dentry for a given inode
+ * @inode: inode to allocate the dentry for
+ *
+ * Obtain a dentry for an inode resulting from NFS filehandle conversion or
+ * similar open by handle operations.  The returned dentry may be anonymous,
+ * or may have a full name (if the inode was already in the cache).
+ *
+ * When called on a directory inode, we must ensure that the inode only ever
+ * has one dentry.  If a dentry is found, that is returned instead of
+ * allocating a new one.
+ *
+ * On successful return, the reference to the inode has been transferred
+ * to the dentry.  If %NULL is returned (indicating kmalloc failure),
+ * the reference on the inode has been released.  To make it easier
+ * to use in export operations a NULL or IS_ERR inode may be passed in
+ * and will be casted to the corresponding NULL or IS_ERR dentry.
+ */
+struct dentry *d_obtain_alias(struct inode *inode)
+{
+	struct dentry *dentry;
+
+	if (!inode)
+		return NULL;
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	dentry = d_alloc_anon(inode);
+	if (!dentry) {
+		iput(inode);
+		dentry = ERR_PTR(-ENOMEM);
+	}
+	return dentry;
+}
+EXPORT_SYMBOL_GPL(d_obtain_alias);
 
 /**
  * d_splice_alias - splice a disconnected dentry into the tree if one exists
diff --git a/fs/libfs.c b/fs/libfs.c
index 1add676a19df..74688598bcf7 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -732,28 +732,6 @@ out:
 	return ret;
 }
 
-/*
- * This is what d_alloc_anon should have been.  Once the exportfs
- * argument transition has been finished I will update d_alloc_anon
- * to this prototype and this wrapper will go away.   --hch
- */
-static struct dentry *exportfs_d_alloc(struct inode *inode)
-{
-	struct dentry *dentry;
-
-	if (!inode)
-		return NULL;
-	if (IS_ERR(inode))
-		return ERR_PTR(PTR_ERR(inode));
-
-	dentry = d_alloc_anon(inode);
-	if (!dentry) {
-		iput(inode);
-		dentry = ERR_PTR(-ENOMEM);
-	}
-	return dentry;
-}
-
 /**
  * generic_fh_to_dentry - generic helper for the fh_to_dentry export operation
  * @sb:		filesystem to do the file handle conversion on
@@ -782,7 +760,7 @@ struct dentry *generic_fh_to_dentry(struct super_block *sb, struct fid *fid,
 		break;
 	}
 
-	return exportfs_d_alloc(inode);
+	return d_obtain_alias(inode);
 }
 EXPORT_SYMBOL_GPL(generic_fh_to_dentry);
 
@@ -815,7 +793,7 @@ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid,
 		break;
 	}
 
-	return exportfs_d_alloc(inode);
+	return d_obtain_alias(inode);
 }
 EXPORT_SYMBOL_GPL(generic_fh_to_parent);
 
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index efba1de629ac..2404257d6c67 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -231,6 +231,7 @@ extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
 extern struct dentry * d_alloc_anon(struct inode *);
 extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
 extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
+extern struct dentry * d_obtain_alias(struct inode *);
 extern void shrink_dcache_sb(struct super_block *);
 extern void shrink_dcache_parent(struct dentry *);
 extern void shrink_dcache_for_umount(struct super_block *);
-- 
cgit v1.2.3


From 9308a6128d9074e348d9f9b5822546fe12a794a9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 11 Aug 2008 15:49:12 +0200
Subject: [PATCH] kill d_alloc_anon

Remove d_alloc_anon now that no users are left.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 108 +++++++++++++++++--------------------------------
 include/linux/dcache.h |   1 -
 2 files changed, 37 insertions(+), 72 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index d45ff7f5ecc2..1710d2484fd9 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1110,70 +1110,6 @@ static inline struct hlist_head *d_hash(struct dentry *parent,
 	return dentry_hashtable + (hash & D_HASHMASK);
 }
 
-/**
- * d_alloc_anon - allocate an anonymous dentry
- * @inode: inode to allocate the dentry for
- *
- * This is similar to d_alloc_root.  It is used by filesystems when
- * creating a dentry for a given inode, often in the process of 
- * mapping a filehandle to a dentry.  The returned dentry may be
- * anonymous, or may have a full name (if the inode was already
- * in the cache).  The file system may need to make further
- * efforts to connect this dentry into the dcache properly.
- *
- * When called on a directory inode, we must ensure that
- * the inode only ever has one dentry.  If a dentry is
- * found, that is returned instead of allocating a new one.
- *
- * On successful return, the reference to the inode has been transferred
- * to the dentry.  If %NULL is returned (indicating kmalloc failure),
- * the reference on the inode has not been released.
- */
-
-struct dentry * d_alloc_anon(struct inode *inode)
-{
-	static const struct qstr anonstring = { .name = "" };
-	struct dentry *tmp;
-	struct dentry *res;
-
-	if ((res = d_find_alias(inode))) {
-		iput(inode);
-		return res;
-	}
-
-	tmp = d_alloc(NULL, &anonstring);
-	if (!tmp)
-		return NULL;
-
-	tmp->d_parent = tmp; /* make sure dput doesn't croak */
-	
-	spin_lock(&dcache_lock);
-	res = __d_find_alias(inode, 0);
-	if (!res) {
-		/* attach a disconnected dentry */
-		res = tmp;
-		tmp = NULL;
-		spin_lock(&res->d_lock);
-		res->d_sb = inode->i_sb;
-		res->d_parent = res;
-		res->d_inode = inode;
-		res->d_flags |= DCACHE_DISCONNECTED;
-		res->d_flags &= ~DCACHE_UNHASHED;
-		list_add(&res->d_alias, &inode->i_dentry);
-		hlist_add_head(&res->d_hash, &inode->i_sb->s_anon);
-		spin_unlock(&res->d_lock);
-
-		inode = NULL; /* don't drop reference */
-	}
-	spin_unlock(&dcache_lock);
-
-	if (inode)
-		iput(inode);
-	if (tmp)
-		dput(tmp);
-	return res;
-}
-
 /**
  * d_obtain_alias - find or allocate a dentry for a given inode
  * @inode: inode to allocate the dentry for
@@ -1194,19 +1130,50 @@ struct dentry * d_alloc_anon(struct inode *inode)
  */
 struct dentry *d_obtain_alias(struct inode *inode)
 {
-	struct dentry *dentry;
+	static const struct qstr anonstring = { .name = "" };
+	struct dentry *tmp;
+	struct dentry *res;
 
 	if (!inode)
 		return ERR_PTR(-ESTALE);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
-	dentry = d_alloc_anon(inode);
-	if (!dentry) {
-		iput(inode);
-		dentry = ERR_PTR(-ENOMEM);
+	res = d_find_alias(inode);
+	if (res)
+		goto out_iput;
+
+	tmp = d_alloc(NULL, &anonstring);
+	if (!tmp) {
+		res = ERR_PTR(-ENOMEM);
+		goto out_iput;
 	}
-	return dentry;
+	tmp->d_parent = tmp; /* make sure dput doesn't croak */
+
+	spin_lock(&dcache_lock);
+	res = __d_find_alias(inode, 0);
+	if (res) {
+		spin_unlock(&dcache_lock);
+		dput(tmp);
+		goto out_iput;
+	}
+
+	/* attach a disconnected dentry */
+	spin_lock(&tmp->d_lock);
+	tmp->d_sb = inode->i_sb;
+	tmp->d_inode = inode;
+	tmp->d_flags |= DCACHE_DISCONNECTED;
+	tmp->d_flags &= ~DCACHE_UNHASHED;
+	list_add(&tmp->d_alias, &inode->i_dentry);
+	hlist_add_head(&tmp->d_hash, &inode->i_sb->s_anon);
+	spin_unlock(&tmp->d_lock);
+
+	spin_unlock(&dcache_lock);
+	return tmp;
+
+ out_iput:
+	iput(inode);
+	return res;
 }
 EXPORT_SYMBOL_GPL(d_obtain_alias);
 
@@ -2379,7 +2346,6 @@ void __init vfs_caches_init(unsigned long mempages)
 }
 
 EXPORT_SYMBOL(d_alloc);
-EXPORT_SYMBOL(d_alloc_anon);
 EXPORT_SYMBOL(d_alloc_root);
 EXPORT_SYMBOL(d_delete);
 EXPORT_SYMBOL(d_find_alias);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 2404257d6c67..74c64ae30cf0 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -228,7 +228,6 @@ extern void d_delete(struct dentry *);
 
 /* allocate/de-allocate */
 extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
-extern struct dentry * d_alloc_anon(struct inode *);
 extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
 extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
 extern struct dentry * d_obtain_alias(struct inode *);
-- 
cgit v1.2.3


From 6de24f0ed08054b2a202902e4d63beff27654db8 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Thu, 28 Aug 2008 06:25:49 +0400
Subject: [PATCH 1/2] anondev: init IDR statically

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 fs/super.c         | 7 +------
 include/linux/fs.h | 1 -
 init/main.c        | 1 -
 3 files changed, 1 insertion(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/super.c b/fs/super.c
index e931ae9511fe..dd23bf927fbc 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -682,7 +682,7 @@ void emergency_remount(void)
  * filesystems which don't use real block-devices.  -- jrs
  */
 
-static struct idr unnamed_dev_idr;
+static DEFINE_IDR(unnamed_dev_idr);
 static DEFINE_SPINLOCK(unnamed_dev_lock);/* protects the above */
 
 int set_anon_super(struct super_block *s, void *data)
@@ -726,11 +726,6 @@ void kill_anon_super(struct super_block *sb)
 
 EXPORT_SYMBOL(kill_anon_super);
 
-void __init unnamed_dev_init(void)
-{
-	idr_init(&unnamed_dev_idr);
-}
-
 void kill_litter_super(struct super_block *sb)
 {
 	if (sb->s_root)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a6a625be13fc..5f70aa62cf0f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1593,7 +1593,6 @@ extern int get_sb_pseudo(struct file_system_type *, char *,
 	struct vfsmount *mnt);
 extern int simple_set_mnt(struct vfsmount *mnt, struct super_block *sb);
 int __put_super_and_need_restart(struct super_block *sb);
-void unnamed_dev_init(void);
 
 /* Alas, no aliases. Too much hassle with bringing module.h everywhere */
 #define fops_get(fops) \
diff --git a/init/main.c b/init/main.c
index 3e17a3bafe60..c6a1024a27a3 100644
--- a/init/main.c
+++ b/init/main.c
@@ -670,7 +670,6 @@ asmlinkage void __init start_kernel(void)
 	fork_init(num_physpages);
 	proc_caches_init();
 	buffer_init();
-	unnamed_dev_init();
 	key_init();
 	security_init();
 	vfs_caches_init(num_physpages);
-- 
cgit v1.2.3


From e2761a1167633ed943fea29002f990194923d060 Mon Sep 17 00:00:00 2001
From: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Date: Thu, 16 Oct 2008 07:50:28 +0900
Subject: [PATCH vfs-2.6 2/6] vfs: add d_ancestor()

This adds d_ancestor() instead of d_isparent(), then use it.

If new_dentry == old_dentry, is_subdir() returns 1, looks strange.
"new_dentry == old_dentry" is not subdir obviously. But I'm not
checking callers for now, so this keeps current behavior.

Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
---
 fs/dcache.c            | 45 +++++++++++++++++++++++----------------------
 fs/namei.c             | 22 ++++++++++------------
 include/linux/dcache.h |  1 +
 3 files changed, 34 insertions(+), 34 deletions(-)

(limited to 'include')

diff --git a/fs/dcache.c b/fs/dcache.c
index c6fd1f27da57..64024005da43 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1720,18 +1720,23 @@ void d_move(struct dentry * dentry, struct dentry * target)
 	spin_unlock(&dcache_lock);
 }
 
-/*
- * Helper that returns 1 if p1 is a parent of p2, else 0
+/**
+ * d_ancestor - search for an ancestor
+ * @p1: ancestor dentry
+ * @p2: child dentry
+ *
+ * Returns the ancestor dentry of p2 which is a child of p1, if p1 is
+ * an ancestor of p2, else NULL.
  */
-static int d_isparent(struct dentry *p1, struct dentry *p2)
+struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
 {
 	struct dentry *p;
 
 	for (p = p2; !IS_ROOT(p); p = p->d_parent) {
 		if (p->d_parent == p1)
-			return 1;
+			return p;
 	}
-	return 0;
+	return NULL;
 }
 
 /*
@@ -1755,7 +1760,7 @@ static struct dentry *__d_unalias(struct dentry *dentry, struct dentry *alias)
 
 	/* Check for loops */
 	ret = ERR_PTR(-ELOOP);
-	if (d_isparent(alias, dentry))
+	if (d_ancestor(alias, dentry))
 		goto out_err;
 
 	/* See lock_rename() */
@@ -2155,31 +2160,27 @@ out:
  * Caller must ensure that "new_dentry" is pinned before calling is_subdir()
  */
   
-int is_subdir(struct dentry * new_dentry, struct dentry * old_dentry)
+int is_subdir(struct dentry *new_dentry, struct dentry *old_dentry)
 {
 	int result;
-	struct dentry * saved = new_dentry;
 	unsigned long seq;
 
-	/* need rcu_readlock to protect against the d_parent trashing due to
-	 * d_move
+	/* FIXME: This is old behavior, needed? Please check callers. */
+	if (new_dentry == old_dentry)
+		return 1;
+
+	/*
+	 * Need rcu_readlock to protect against the d_parent trashing
+	 * due to d_move
 	 */
 	rcu_read_lock();
-        do {
+	do {
 		/* for restarting inner loop in case of seq retry */
-		new_dentry = saved;
-		result = 0;
 		seq = read_seqbegin(&rename_lock);
-		for (;;) {
-			if (new_dentry != old_dentry) {
-				if (IS_ROOT(new_dentry))
-					break;
-				new_dentry = new_dentry->d_parent;
-				continue;
-			}
+		if (d_ancestor(old_dentry, new_dentry))
 			result = 1;
-			break;
-		}
+		else
+			result = 0;
 	} while (read_seqretry(&rename_lock, seq));
 	rcu_read_unlock();
 
diff --git a/fs/namei.c b/fs/namei.c
index 068a9e50c8c0..b7cd65224d60 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1454,20 +1454,18 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2)
 
 	mutex_lock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
 
-	for (p = p1; !IS_ROOT(p); p = p->d_parent) {
-		if (p->d_parent == p2) {
-			mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT);
-			mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD);
-			return p;
-		}
+	p = d_ancestor(p2, p1);
+	if (p) {
+		mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT);
+		mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD);
+		return p;
 	}
 
-	for (p = p2; !IS_ROOT(p); p = p->d_parent) {
-		if (p->d_parent == p1) {
-			mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
-			mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
-			return p;
-		}
+	p = d_ancestor(p1, p2);
+	if (p) {
+		mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
+		mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD);
+		return p;
 	}
 
 	mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT);
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 74c64ae30cf0..a37359d0bad1 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -287,6 +287,7 @@ static inline struct dentry *d_add_unique(struct dentry *entry, struct inode *in
 
 /* used for rename() and baskets */
 extern void d_move(struct dentry *, struct dentry *);
+extern struct dentry *d_ancestor(struct dentry *, struct dentry *);
 
 /* appendix may either be NULL or be used for transname suffixes */
 extern struct dentry * d_lookup(struct dentry *, struct qstr *);
-- 
cgit v1.2.3


From 4e9ed2f85af7adfa7c3f0efa839a53186254fdcb Mon Sep 17 00:00:00 2001
From: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Date: Thu, 16 Oct 2008 07:50:29 +0900
Subject: [PATCH vfs-2.6 6/6] vfs: add LOOKUP_RENAME_TARGET intent

This adds LOOKUP_RENAME_TARGET intent for lookup of rename destination.

LOOKUP_RENAME_TARGET is going to be used like LOOKUP_CREATE. But since
the destination of rename() can be existing directory entry, so it has a
difference. Although that difference doesn't matter in my usage, this
tells it to user of this intent.

Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
---
 fs/namei.c            | 1 +
 include/linux/namei.h | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include')

diff --git a/fs/namei.c b/fs/namei.c
index 18894fdf048a..9e2a534383d9 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2654,6 +2654,7 @@ asmlinkage long sys_renameat(int olddfd, const char __user *oldname,
 
 	oldnd.flags &= ~LOOKUP_PARENT;
 	newnd.flags &= ~LOOKUP_PARENT;
+	newnd.flags |= LOOKUP_RENAME_TARGET;
 
 	trap = lock_rename(new_dir, old_dir);
 
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 6b5627afd2eb..99eb80306dc5 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -54,6 +54,7 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
 #define LOOKUP_OPEN		0x0100
 #define LOOKUP_CREATE		0x0200
 #define LOOKUP_EXCL		0x0400
+#define LOOKUP_RENAME_TARGET	0x0800
 
 extern int user_path_at(int, const char __user *, unsigned, struct path *);
 
-- 
cgit v1.2.3


From f696a3659fc4b3a3bf4bc83d9dbec5e5a2ffd929 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <miklos@szeredi.hu>
Date: Thu, 31 Jul 2008 13:41:58 +0200
Subject: [PATCH] move executable checking into ->permission()

For execute permission on a regular files we need to check if file has
any execute bits at all, regardless of capabilites.

This check is normally performed by generic_permission() but was also
added to the case when the filesystem defines its own ->permission()
method.  In the latter case the filesystem should be responsible for
performing this check.

Move the check from inode_permission() inside filesystems which are
not calling generic_permission().

Create a helper function execute_ok() that returns true if the inode
is a directory or if any execute bits are present in i_mode.

Also fix up the following code:

 - coda control file is never executable
 - sysctl files are never executable
 - hfs_permission seems broken on MAY_EXEC, remove
 - hfsplus_permission is eqivalent to generic_permission(), remove

Signed-off-by: Miklos Szeredi <mszeredi@suse.cz>
---
 fs/cifs/cifsfs.c      |  9 ++++++---
 fs/coda/dir.c         |  3 +++
 fs/coda/pioctl.c      |  2 +-
 fs/hfs/inode.c        |  8 --------
 fs/hfsplus/inode.c    | 13 -------------
 fs/namei.c            | 21 ++++-----------------
 fs/nfs/dir.c          |  3 +++
 fs/proc/proc_sysctl.c | 10 ++++++++--
 include/linux/fs.h    |  5 +++++
 9 files changed, 30 insertions(+), 44 deletions(-)

(limited to 'include')

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 89c64a8dcb99..84cc011a16e4 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -275,9 +275,12 @@ static int cifs_permission(struct inode *inode, int mask)
 
 	cifs_sb = CIFS_SB(inode->i_sb);
 
-	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM)
-		return 0;
-	else /* file mode might have been restricted at mount time
+	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NO_PERM) {
+		if ((mask & MAY_EXEC) && !execute_ok(inode))
+			return -EACCES;
+		else
+			return 0;
+	} else /* file mode might have been restricted at mount time
 		on the client (above and beyond ACL on servers) for
 		servers which do not support setting and viewing mode bits,
 		so allowing client to check permissions is useful */
diff --git a/fs/coda/dir.c b/fs/coda/dir.c
index c5916228243c..75b1fa90b2cb 100644
--- a/fs/coda/dir.c
+++ b/fs/coda/dir.c
@@ -146,6 +146,9 @@ int coda_permission(struct inode *inode, int mask)
 	if (!mask)
 		return 0; 
 
+	if ((mask & MAY_EXEC) && !execute_ok(inode))
+		return -EACCES;
+
 	lock_kernel();
 
 	if (coda_cache_check(inode, mask))
diff --git a/fs/coda/pioctl.c b/fs/coda/pioctl.c
index c51365422aa8..773f2ce9aa06 100644
--- a/fs/coda/pioctl.c
+++ b/fs/coda/pioctl.c
@@ -43,7 +43,7 @@ const struct file_operations coda_ioctl_operations = {
 /* the coda pioctl inode ops */
 static int coda_ioctl_permission(struct inode *inode, int mask)
 {
-        return 0;
+	return (mask & MAY_EXEC) ? -EACCES : 0;
 }
 
 static int coda_pioctl(struct inode * inode, struct file * filp, 
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 7e19835efa2e..c69b7ac75bf7 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -511,13 +511,6 @@ void hfs_clear_inode(struct inode *inode)
 	}
 }
 
-static int hfs_permission(struct inode *inode, int mask)
-{
-	if (S_ISREG(inode->i_mode) && mask & MAY_EXEC)
-		return 0;
-	return generic_permission(inode, mask, NULL);
-}
-
 static int hfs_file_open(struct inode *inode, struct file *file)
 {
 	if (HFS_IS_RSRC(inode))
@@ -616,7 +609,6 @@ static const struct inode_operations hfs_file_inode_operations = {
 	.lookup		= hfs_file_lookup,
 	.truncate	= hfs_file_truncate,
 	.setattr	= hfs_inode_setattr,
-	.permission	= hfs_permission,
 	.setxattr	= hfs_setxattr,
 	.getxattr	= hfs_getxattr,
 	.listxattr	= hfs_listxattr,
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 963be644297a..b207f0e6fc22 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -238,18 +238,6 @@ static void hfsplus_set_perms(struct inode *inode, struct hfsplus_perm *perms)
 	perms->dev = cpu_to_be32(HFSPLUS_I(inode).dev);
 }
 
-static int hfsplus_permission(struct inode *inode, int mask)
-{
-	/* MAY_EXEC is also used for lookup, if no x bit is set allow lookup,
-	 * open_exec has the same test, so it's still not executable, if a x bit
-	 * is set fall back to standard permission check.
-	 */
-	if (S_ISREG(inode->i_mode) && mask & MAY_EXEC && !(inode->i_mode & 0111))
-		return 0;
-	return generic_permission(inode, mask, NULL);
-}
-
-
 static int hfsplus_file_open(struct inode *inode, struct file *file)
 {
 	if (HFSPLUS_IS_RSRC(inode))
@@ -281,7 +269,6 @@ static int hfsplus_file_release(struct inode *inode, struct file *file)
 static const struct inode_operations hfsplus_file_inode_operations = {
 	.lookup		= hfsplus_file_lookup,
 	.truncate	= hfsplus_file_truncate,
-	.permission	= hfsplus_permission,
 	.setxattr	= hfsplus_setxattr,
 	.getxattr	= hfsplus_getxattr,
 	.listxattr	= hfsplus_listxattr,
diff --git a/fs/namei.c b/fs/namei.c
index 9e2a534383d9..09ce58e49e72 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -212,8 +212,7 @@ int generic_permission(struct inode *inode, int mask,
 	 * Read/write DACs are always overridable.
 	 * Executable DACs are overridable if at least one exec bit is set.
 	 */
-	if (!(mask & MAY_EXEC) ||
-	    (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode))
+	if (!(mask & MAY_EXEC) || execute_ok(inode))
 		if (capable(CAP_DAC_OVERRIDE))
 			return 0;
 
@@ -249,23 +248,11 @@ int inode_permission(struct inode *inode, int mask)
 	}
 
 	/* Ordinary permission routines do not understand MAY_APPEND. */
-	if (inode->i_op && inode->i_op->permission) {
+	if (inode->i_op && inode->i_op->permission)
 		retval = inode->i_op->permission(inode, mask);
-		if (!retval) {
-			/*
-			 * Exec permission on a regular file is denied if none
-			 * of the execute bits are set.
-			 *
-			 * This check should be done by the ->permission()
-			 * method.
-			 */
-			if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode) &&
-			    !(inode->i_mode & S_IXUGO))
-				return -EACCES;
-		}
-	} else {
+	else
 		retval = generic_permission(inode, mask, NULL);
-	}
+
 	if (retval)
 		return retval;
 
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index c216c8786c51..3e64b98f3a93 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1957,6 +1957,9 @@ force_lookup:
 	} else
 		res = PTR_ERR(cred);
 out:
+	if (!res && (mask & MAY_EXEC) && !execute_ok(inode))
+		res = -EACCES;
+
 	dfprintk(VFS, "NFS: permission(%s/%ld), mask=0x%x, res=%d\n",
 		inode->i_sb->s_id, inode->i_ino, mask, res);
 	return res;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 5fe210c09171..7b997754a25e 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -298,13 +298,19 @@ static int proc_sys_permission(struct inode *inode, int mask)
 	 * sysctl entries that are not writeable,
 	 * are _NOT_ writeable, capabilities or not.
 	 */
-	struct ctl_table_header *head = grab_header(inode);
-	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
+	struct ctl_table_header *head;
+	struct ctl_table *table;
 	int error;
 
+	/* Executable files are not allowed under /proc/sys/ */
+	if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode))
+		return -EACCES;
+
+	head = grab_header(inode);
 	if (IS_ERR(head))
 		return PTR_ERR(head);
 
+	table = PROC_I(inode)->sysctl_entry;
 	if (!table) /* global root - r-xr-xr-x */
 		error = mask & MAY_WRITE ? -EACCES : 0;
 	else /* Use the permissions on the sysctl table entry */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5f70aa62cf0f..025a4a251b64 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1851,6 +1851,11 @@ extern int inode_permission(struct inode *, int);
 extern int generic_permission(struct inode *, int,
 		int (*check_acl)(struct inode *, int));
 
+static inline bool execute_ok(struct inode *inode)
+{
+	return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
+}
+
 extern int get_write_access(struct inode *);
 extern int deny_write_access(struct file *);
 static inline void put_write_access(struct inode * inode)
-- 
cgit v1.2.3


From 08b9fe6b12d32324f311c46b88102b6b9067d434 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Mon, 13 Oct 2008 00:09:50 -0400
Subject: [PATCH] i_version: remount support

Add support for remounting a filesystem with the i_version option.

Signed-off-by: Mimi Zohar <zohar@us.ibm.com>
---
 include/linux/fs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 025a4a251b64..7d719c1a18e3 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -136,7 +136,7 @@ extern int dir_notify_enable;
 /*
  * Superblock flags that can be altered by MS_REMOUNT
  */
-#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK)
+#define MS_RMT_MASK	(MS_RDONLY|MS_SYNCHRONOUS|MS_MANDLOCK|MS_I_VERSION)
 
 /*
  * Old magic mount flag and mask
-- 
cgit v1.2.3


From e1759c215bee5abbcb6cb066590ab20905154ed5 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Wed, 15 Oct 2008 23:50:22 +0400
Subject: proc: switch /proc/meminfo to seq_file

and move it to fs/proc/meminfo.c while I'm at it.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 arch/x86/mm/pageattr.c    |  11 ++-
 fs/proc/Makefile          |   1 +
 fs/proc/meminfo.c         | 168 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/proc/proc_misc.c       | 137 -------------------------------------
 include/asm-x86/pgtable.h |   3 +-
 include/linux/hugetlb.h   |   6 +-
 mm/hugetlb.c              |   5 +-
 7 files changed, 183 insertions(+), 148 deletions(-)
 create mode 100644 fs/proc/meminfo.c

(limited to 'include')

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 407d8784f669..f1dc1b75d166 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -65,23 +65,22 @@ static void split_page_count(int level)
 	direct_pages_count[level - 1] += PTRS_PER_PTE;
 }
 
-int arch_report_meminfo(char *page)
+void arch_report_meminfo(struct seq_file *m)
 {
-	int n = sprintf(page, "DirectMap4k:  %8lu kB\n",
+	seq_printf(m, "DirectMap4k:  %8lu kB\n",
 			direct_pages_count[PG_LEVEL_4K] << 2);
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
-	n += sprintf(page + n, "DirectMap2M:  %8lu kB\n",
+	seq_printf(m, "DirectMap2M:  %8lu kB\n",
 			direct_pages_count[PG_LEVEL_2M] << 11);
 #else
-	n += sprintf(page + n, "DirectMap4M:  %8lu kB\n",
+	seq_printf(m, "DirectMap4M:  %8lu kB\n",
 			direct_pages_count[PG_LEVEL_2M] << 12);
 #endif
 #ifdef CONFIG_X86_64
 	if (direct_gbpages)
-		n += sprintf(page + n, "DirectMap1G:  %8lu kB\n",
+		seq_printf(m, "DirectMap1G:  %8lu kB\n",
 			direct_pages_count[PG_LEVEL_1G] << 20);
 #endif
-	return n;
 }
 #else
 static inline void split_page_count(int level) { }
diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index 27efa14963b1..70607a03839d 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -10,6 +10,7 @@ proc-$(CONFIG_MMU)	:= mmu.o task_mmu.o
 proc-y       += inode.o root.o base.o generic.o array.o \
 		proc_tty.o proc_misc.o
 proc-y	+= loadavg.o
+proc-y	+= meminfo.o
 proc-y	+= uptime.o
 proc-$(CONFIG_PROC_SYSCTL)	+= proc_sysctl.o
 proc-$(CONFIG_NET)		+= proc_net.o
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
new file mode 100644
index 000000000000..b1675c4e66da
--- /dev/null
+++ b/fs/proc/meminfo.c
@@ -0,0 +1,168 @@
+#include <linux/fs.h>
+#include <linux/hugetlb.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mmzone.h>
+#include <linux/proc_fs.h>
+#include <linux/quicklist.h>
+#include <linux/seq_file.h>
+#include <linux/swap.h>
+#include <linux/vmstat.h>
+#include <asm/atomic.h>
+#include <asm/page.h>
+#include <asm/pgtable.h>
+#include "internal.h"
+
+void __attribute__((weak)) arch_report_meminfo(struct seq_file *m)
+{
+}
+
+static int meminfo_proc_show(struct seq_file *m, void *v)
+{
+	struct sysinfo i;
+	unsigned long committed;
+	unsigned long allowed;
+	struct vmalloc_info vmi;
+	long cached;
+	unsigned long pages[NR_LRU_LISTS];
+	int lru;
+
+/*
+ * display in kilobytes.
+ */
+#define K(x) ((x) << (PAGE_SHIFT - 10))
+	si_meminfo(&i);
+	si_swapinfo(&i);
+	committed = atomic_long_read(&vm_committed_space);
+	allowed = ((totalram_pages - hugetlb_total_pages())
+		* sysctl_overcommit_ratio / 100) + total_swap_pages;
+
+	cached = global_page_state(NR_FILE_PAGES) -
+			total_swapcache_pages - i.bufferram;
+	if (cached < 0)
+		cached = 0;
+
+	get_vmalloc_info(&vmi);
+
+	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
+		pages[lru] = global_page_state(NR_LRU_BASE + lru);
+
+	/*
+	 * Tagged format, for easy grepping and expansion.
+	 */
+	seq_printf(m,
+		"MemTotal:       %8lu kB\n"
+		"MemFree:        %8lu kB\n"
+		"Buffers:        %8lu kB\n"
+		"Cached:         %8lu kB\n"
+		"SwapCached:     %8lu kB\n"
+		"Active:         %8lu kB\n"
+		"Inactive:       %8lu kB\n"
+		"Active(anon):   %8lu kB\n"
+		"Inactive(anon): %8lu kB\n"
+		"Active(file):   %8lu kB\n"
+		"Inactive(file): %8lu kB\n"
+#ifdef CONFIG_UNEVICTABLE_LRU
+		"Unevictable:    %8lu kB\n"
+		"Mlocked:        %8lu kB\n"
+#endif
+#ifdef CONFIG_HIGHMEM
+		"HighTotal:      %8lu kB\n"
+		"HighFree:       %8lu kB\n"
+		"LowTotal:       %8lu kB\n"
+		"LowFree:        %8lu kB\n"
+#endif
+		"SwapTotal:      %8lu kB\n"
+		"SwapFree:       %8lu kB\n"
+		"Dirty:          %8lu kB\n"
+		"Writeback:      %8lu kB\n"
+		"AnonPages:      %8lu kB\n"
+		"Mapped:         %8lu kB\n"
+		"Slab:           %8lu kB\n"
+		"SReclaimable:   %8lu kB\n"
+		"SUnreclaim:     %8lu kB\n"
+		"PageTables:     %8lu kB\n"
+#ifdef CONFIG_QUICKLIST
+		"Quicklists:     %8lu kB\n"
+#endif
+		"NFS_Unstable:   %8lu kB\n"
+		"Bounce:         %8lu kB\n"
+		"WritebackTmp:   %8lu kB\n"
+		"CommitLimit:    %8lu kB\n"
+		"Committed_AS:   %8lu kB\n"
+		"VmallocTotal:   %8lu kB\n"
+		"VmallocUsed:    %8lu kB\n"
+		"VmallocChunk:   %8lu kB\n",
+		K(i.totalram),
+		K(i.freeram),
+		K(i.bufferram),
+		K(cached),
+		K(total_swapcache_pages),
+		K(pages[LRU_ACTIVE_ANON]   + pages[LRU_ACTIVE_FILE]),
+		K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]),
+		K(pages[LRU_ACTIVE_ANON]),
+		K(pages[LRU_INACTIVE_ANON]),
+		K(pages[LRU_ACTIVE_FILE]),
+		K(pages[LRU_INACTIVE_FILE]),
+#ifdef CONFIG_UNEVICTABLE_LRU
+		K(pages[LRU_UNEVICTABLE]),
+		K(global_page_state(NR_MLOCK)),
+#endif
+#ifdef CONFIG_HIGHMEM
+		K(i.totalhigh),
+		K(i.freehigh),
+		K(i.totalram-i.totalhigh),
+		K(i.freeram-i.freehigh),
+#endif
+		K(i.totalswap),
+		K(i.freeswap),
+		K(global_page_state(NR_FILE_DIRTY)),
+		K(global_page_state(NR_WRITEBACK)),
+		K(global_page_state(NR_ANON_PAGES)),
+		K(global_page_state(NR_FILE_MAPPED)),
+		K(global_page_state(NR_SLAB_RECLAIMABLE) +
+				global_page_state(NR_SLAB_UNRECLAIMABLE)),
+		K(global_page_state(NR_SLAB_RECLAIMABLE)),
+		K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
+		K(global_page_state(NR_PAGETABLE)),
+#ifdef CONFIG_QUICKLIST
+		K(quicklist_total_size()),
+#endif
+		K(global_page_state(NR_UNSTABLE_NFS)),
+		K(global_page_state(NR_BOUNCE)),
+		K(global_page_state(NR_WRITEBACK_TEMP)),
+		K(allowed),
+		K(committed),
+		(unsigned long)VMALLOC_TOTAL >> 10,
+		vmi.used >> 10,
+		vmi.largest_chunk >> 10
+		);
+
+	hugetlb_report_meminfo(m);
+
+	arch_report_meminfo(m);
+
+	return 0;
+#undef K
+}
+
+static int meminfo_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, meminfo_proc_show, NULL);
+}
+
+static const struct file_operations meminfo_proc_fops = {
+	.open		= meminfo_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init proc_meminfo_init(void)
+{
+	proc_create("meminfo", 0, NULL, &meminfo_proc_fops);
+	return 0;
+}
+module_init(proc_meminfo_init);
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 484b6011bf0b..1aba51b0a0c4 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -78,142 +78,6 @@ static int proc_calc_metrics(char *page, char **start, off_t off,
 	return len;
 }
 
-int __attribute__((weak)) arch_report_meminfo(char *page)
-{
-	return 0;
-}
-
-static int meminfo_read_proc(char *page, char **start, off_t off,
-				 int count, int *eof, void *data)
-{
-	struct sysinfo i;
-	int len;
-	unsigned long committed;
-	unsigned long allowed;
-	struct vmalloc_info vmi;
-	long cached;
-	unsigned long pages[NR_LRU_LISTS];
-	int lru;
-
-/*
- * display in kilobytes.
- */
-#define K(x) ((x) << (PAGE_SHIFT - 10))
-	si_meminfo(&i);
-	si_swapinfo(&i);
-	committed = atomic_long_read(&vm_committed_space);
-	allowed = ((totalram_pages - hugetlb_total_pages())
-		* sysctl_overcommit_ratio / 100) + total_swap_pages;
-
-	cached = global_page_state(NR_FILE_PAGES) -
-			total_swapcache_pages - i.bufferram;
-	if (cached < 0)
-		cached = 0;
-
-	get_vmalloc_info(&vmi);
-
-	for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
-		pages[lru] = global_page_state(NR_LRU_BASE + lru);
-
-	/*
-	 * Tagged format, for easy grepping and expansion.
-	 */
-	len = sprintf(page,
-		"MemTotal:       %8lu kB\n"
-		"MemFree:        %8lu kB\n"
-		"Buffers:        %8lu kB\n"
-		"Cached:         %8lu kB\n"
-		"SwapCached:     %8lu kB\n"
-		"Active:         %8lu kB\n"
-		"Inactive:       %8lu kB\n"
-		"Active(anon):   %8lu kB\n"
-		"Inactive(anon): %8lu kB\n"
-		"Active(file):   %8lu kB\n"
-		"Inactive(file): %8lu kB\n"
-#ifdef CONFIG_UNEVICTABLE_LRU
-		"Unevictable:    %8lu kB\n"
-		"Mlocked:        %8lu kB\n"
-#endif
-#ifdef CONFIG_HIGHMEM
-		"HighTotal:      %8lu kB\n"
-		"HighFree:       %8lu kB\n"
-		"LowTotal:       %8lu kB\n"
-		"LowFree:        %8lu kB\n"
-#endif
-		"SwapTotal:      %8lu kB\n"
-		"SwapFree:       %8lu kB\n"
-		"Dirty:          %8lu kB\n"
-		"Writeback:      %8lu kB\n"
-		"AnonPages:      %8lu kB\n"
-		"Mapped:         %8lu kB\n"
-		"Slab:           %8lu kB\n"
-		"SReclaimable:   %8lu kB\n"
-		"SUnreclaim:     %8lu kB\n"
-		"PageTables:     %8lu kB\n"
-#ifdef CONFIG_QUICKLIST
-		"Quicklists:     %8lu kB\n"
-#endif
-		"NFS_Unstable:   %8lu kB\n"
-		"Bounce:         %8lu kB\n"
-		"WritebackTmp:   %8lu kB\n"
-		"CommitLimit:    %8lu kB\n"
-		"Committed_AS:   %8lu kB\n"
-		"VmallocTotal:   %8lu kB\n"
-		"VmallocUsed:    %8lu kB\n"
-		"VmallocChunk:   %8lu kB\n",
-		K(i.totalram),
-		K(i.freeram),
-		K(i.bufferram),
-		K(cached),
-		K(total_swapcache_pages),
-		K(pages[LRU_ACTIVE_ANON]   + pages[LRU_ACTIVE_FILE]),
-		K(pages[LRU_INACTIVE_ANON] + pages[LRU_INACTIVE_FILE]),
-		K(pages[LRU_ACTIVE_ANON]),
-		K(pages[LRU_INACTIVE_ANON]),
-		K(pages[LRU_ACTIVE_FILE]),
-		K(pages[LRU_INACTIVE_FILE]),
-#ifdef CONFIG_UNEVICTABLE_LRU
-		K(pages[LRU_UNEVICTABLE]),
-		K(global_page_state(NR_MLOCK)),
-#endif
-#ifdef CONFIG_HIGHMEM
-		K(i.totalhigh),
-		K(i.freehigh),
-		K(i.totalram-i.totalhigh),
-		K(i.freeram-i.freehigh),
-#endif
-		K(i.totalswap),
-		K(i.freeswap),
-		K(global_page_state(NR_FILE_DIRTY)),
-		K(global_page_state(NR_WRITEBACK)),
-		K(global_page_state(NR_ANON_PAGES)),
-		K(global_page_state(NR_FILE_MAPPED)),
-		K(global_page_state(NR_SLAB_RECLAIMABLE) +
-				global_page_state(NR_SLAB_UNRECLAIMABLE)),
-		K(global_page_state(NR_SLAB_RECLAIMABLE)),
-		K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
-		K(global_page_state(NR_PAGETABLE)),
-#ifdef CONFIG_QUICKLIST
-		K(quicklist_total_size()),
-#endif
-		K(global_page_state(NR_UNSTABLE_NFS)),
-		K(global_page_state(NR_BOUNCE)),
-		K(global_page_state(NR_WRITEBACK_TEMP)),
-		K(allowed),
-		K(committed),
-		(unsigned long)VMALLOC_TOTAL >> 10,
-		vmi.used >> 10,
-		vmi.largest_chunk >> 10
-		);
-
-		len += hugetlb_report_meminfo(page + len);
-
-	len += arch_report_meminfo(page + len);
-
-	return proc_calc_metrics(page, start, off, count, eof, len);
-#undef K
-}
-
 static int fragmentation_open(struct inode *inode, struct file *file)
 {
 	(void)inode;
@@ -816,7 +680,6 @@ void __init proc_misc_init(void)
 		char *name;
 		int (*read_proc)(char*,char**,off_t,int,int*,void*);
 	} *p, simple_ones[] = {
-		{"meminfo",	meminfo_read_proc},
 		{"version",	version_read_proc},
 #ifdef CONFIG_PROC_HARDWARE
 		{"hardware",	hardware_read_proc},
diff --git a/include/asm-x86/pgtable.h b/include/asm-x86/pgtable.h
index 88a53b1a17f0..a3dda6d615be 100644
--- a/include/asm-x86/pgtable.h
+++ b/include/asm-x86/pgtable.h
@@ -348,7 +348,8 @@ static inline void native_pagetable_setup_start(pgd_t *base) {}
 static inline void native_pagetable_setup_done(pgd_t *base) {}
 #endif
 
-extern int arch_report_meminfo(char *page);
+struct seq_file;
+extern void arch_report_meminfo(struct seq_file *m);
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 32e0ef0f6e1f..e1c8afc002c0 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -27,7 +27,7 @@ void unmap_hugepage_range(struct vm_area_struct *,
 void __unmap_hugepage_range(struct vm_area_struct *,
 			unsigned long, unsigned long, struct page *);
 int hugetlb_prefault(struct address_space *, struct vm_area_struct *);
-int hugetlb_report_meminfo(char *);
+void hugetlb_report_meminfo(struct seq_file *);
 int hugetlb_report_node_meminfo(int, char *);
 unsigned long hugetlb_total_pages(void);
 int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
@@ -79,7 +79,9 @@ static inline unsigned long hugetlb_total_pages(void)
 #define copy_hugetlb_page_range(src, dst, vma)	({ BUG(); 0; })
 #define hugetlb_prefault(mapping, vma)		({ BUG(); 0; })
 #define unmap_hugepage_range(vma, start, end, page)	BUG()
-#define hugetlb_report_meminfo(buf)		0
+static inline void hugetlb_report_meminfo(struct seq_file *m)
+{
+}
 #define hugetlb_report_node_meminfo(n, buf)	0
 #define follow_huge_pmd(mm, addr, pmd, write)	NULL
 #define follow_huge_pud(mm, addr, pud, write)	NULL
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ce8cbb29860b..421aee99b84a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <linux/seq_file.h>
 #include <linux/sysctl.h>
 #include <linux/highmem.h>
 #include <linux/mmu_notifier.h>
@@ -1455,10 +1456,10 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 
 #endif /* CONFIG_SYSCTL */
 
-int hugetlb_report_meminfo(char *buf)
+void hugetlb_report_meminfo(struct seq_file *m)
 {
 	struct hstate *h = &default_hstate;
-	return sprintf(buf,
+	seq_printf(m,
 			"HugePages_Total:   %5lu\n"
 			"HugePages_Free:    %5lu\n"
 			"HugePages_Rsvd:    %5lu\n"
-- 
cgit v1.2.3


From 813dcf7a6e642feb1ea566b96ce2912249d2b57d Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Fri, 3 Oct 2008 22:42:36 +0400
Subject: proc: move /proc/hardware to m68k-specific code

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 arch/m68k/amiga/config.c    | 21 +++++++++------------
 arch/m68k/atari/config.c    | 15 +++++++--------
 arch/m68k/bvme6000/config.c | 11 -----------
 arch/m68k/kernel/setup.c    | 35 ++++++++++++++++++++++++++++-------
 arch/m68k/mvme147/config.c  | 10 ----------
 arch/m68k/mvme16x/config.c  | 15 +++++----------
 arch/m68k/q40/config.c      | 10 ----------
 arch/m68k/sun3/config.c     | 12 +++---------
 arch/m68k/sun3x/config.c    | 12 +++---------
 fs/proc/proc_misc.c         | 13 -------------
 include/asm-m68k/machdep.h  |  2 +-
 11 files changed, 56 insertions(+), 100 deletions(-)

(limited to 'include')

diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
index 0a3f9e8ebde0..ab9862c3a136 100644
--- a/arch/m68k/amiga/config.c
+++ b/arch/m68k/amiga/config.c
@@ -15,6 +15,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/seq_file.h>
 #include <linux/tty.h>
 #include <linux/console.h>
 #include <linux/rtc.h>
@@ -93,7 +94,7 @@ static char amiga_model_name[13] = "Amiga ";
 
 static void amiga_sched_init(irq_handler_t handler);
 static void amiga_get_model(char *model);
-static int amiga_get_hardware_list(char *buffer);
+static void amiga_get_hardware_list(struct seq_file *m);
 /* amiga specific timer functions */
 static unsigned long amiga_gettimeoffset(void);
 static int a3000_hwclk(int, struct rtc_time *);
@@ -911,13 +912,11 @@ static void amiga_get_model(char *model)
 }
 
 
-static int amiga_get_hardware_list(char *buffer)
+static void amiga_get_hardware_list(struct seq_file *m)
 {
-	int len = 0;
-
 	if (AMIGAHW_PRESENT(CHIP_RAM))
-		len += sprintf(buffer+len, "Chip RAM:\t%ldK\n", amiga_chip_size>>10);
-	len += sprintf(buffer+len, "PS Freq:\t%dHz\nEClock Freq:\t%ldHz\n",
+		seq_printf(m, "Chip RAM:\t%ldK\n", amiga_chip_size>>10);
+	seq_printf(m, "PS Freq:\t%dHz\nEClock Freq:\t%ldHz\n",
 			amiga_psfreq, amiga_eclock);
 	if (AMIGAHW_PRESENT(AMI_VIDEO)) {
 		char *type;
@@ -935,14 +934,14 @@ static int amiga_get_hardware_list(char *buffer)
 			type = "Old or Unknown";
 			break;
 		}
-		len += sprintf(buffer+len, "Graphics:\t%s\n", type);
+		seq_printf(m, "Graphics:\t%s\n", type);
 	}
 
 #define AMIGAHW_ANNOUNCE(name, str)			\
 	if (AMIGAHW_PRESENT(name))			\
-		len += sprintf (buffer+len, "\t%s\n", str)
+		seq_printf (m, "\t%s\n", str)
 
-	len += sprintf (buffer + len, "Detected hardware:\n");
+	seq_printf (m, "Detected hardware:\n");
 
 	AMIGAHW_ANNOUNCE(AMI_VIDEO, "Amiga Video");
 	AMIGAHW_ANNOUNCE(AMI_BLITTER, "Blitter");
@@ -975,15 +974,13 @@ static int amiga_get_hardware_list(char *buffer)
 	AMIGAHW_ANNOUNCE(PCMCIA, "PCMCIA Slot");
 #ifdef CONFIG_ZORRO
 	if (AMIGAHW_PRESENT(ZORRO))
-		len += sprintf(buffer+len, "\tZorro II%s AutoConfig: %d Expansion "
+		seq_printf(m, "\tZorro II%s AutoConfig: %d Expansion "
 				"Device%s\n",
 				AMIGAHW_PRESENT(ZORRO3) ? "I" : "",
 				zorro_num_autocon, zorro_num_autocon == 1 ? "" : "s");
 #endif /* CONFIG_ZORRO */
 
 #undef AMIGAHW_ANNOUNCE
-
-	return len;
 }
 
 /*
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index af031855f796..49c28cdbea5c 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -26,6 +26,7 @@
 
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/seq_file.h>
 #include <linux/console.h>
 #include <linux/init.h>
 #include <linux/delay.h>
@@ -63,7 +64,7 @@ int atari_rtc_year_offset;
 /* local function prototypes */
 static void atari_reset(void);
 static void atari_get_model(char *model);
-static int atari_get_hardware_list(char *buffer);
+static void atari_get_hardware_list(struct seq_file *m);
 
 /* atari specific irq functions */
 extern void atari_init_IRQ (void);
@@ -611,21 +612,21 @@ static void atari_get_model(char *model)
 }
 
 
-static int atari_get_hardware_list(char *buffer)
+static void atari_get_hardware_list(struct seq_file *m)
 {
-	int len = 0, i;
+	int i;
 
 	for (i = 0; i < m68k_num_memory; i++)
-		len += sprintf(buffer+len, "\t%3ld MB at 0x%08lx (%s)\n",
+		seq_printf(m, "\t%3ld MB at 0x%08lx (%s)\n",
 				m68k_memory[i].size >> 20, m68k_memory[i].addr,
 				(m68k_memory[i].addr & 0xff000000 ?
 				 "alternate RAM" : "ST-RAM"));
 
 #define ATARIHW_ANNOUNCE(name, str)			\
 	if (ATARIHW_PRESENT(name))			\
-		len += sprintf(buffer + len, "\t%s\n", str)
+		seq_printf(m, "\t%s\n", str)
 
-	len += sprintf(buffer + len, "Detected hardware:\n");
+	seq_printf(m, "Detected hardware:\n");
 	ATARIHW_ANNOUNCE(STND_SHIFTER, "ST Shifter");
 	ATARIHW_ANNOUNCE(EXTD_SHIFTER, "STe Shifter");
 	ATARIHW_ANNOUNCE(TT_SHIFTER, "TT Shifter");
@@ -654,6 +655,4 @@ static int atari_get_hardware_list(char *buffer)
 	ATARIHW_ANNOUNCE(BLITTER, "Blitter");
 	ATARIHW_ANNOUNCE(VME, "VME Bus");
 	ATARIHW_ANNOUNCE(DSP56K, "DSP56001 processor");
-
-	return len;
 }
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 65c9204ab9ac..c072595928c0 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -38,7 +38,6 @@
 #include <asm/bvme6000hw.h>
 
 static void bvme6000_get_model(char *model);
-static int  bvme6000_get_hardware_list(char *buffer);
 extern void bvme6000_sched_init(irq_handler_t handler);
 extern unsigned long bvme6000_gettimeoffset (void);
 extern int bvme6000_hwclk (int, struct rtc_time *);
@@ -82,15 +81,6 @@ static void bvme6000_get_model(char *model)
     sprintf(model, "BVME%d000", m68k_cputype == CPU_68060 ? 6 : 4);
 }
 
-
-/* No hardware options on BVME6000? */
-
-static int bvme6000_get_hardware_list(char *buffer)
-{
-    *buffer = '\0';
-    return 0;
-}
-
 /*
  * This function is called during kernel startup to initialize
  * the bvme6000 IRQ handling routines.
@@ -127,7 +117,6 @@ void __init config_bvme6000(void)
     mach_set_clock_mmss	 = bvme6000_set_clock_mmss;
     mach_reset		 = bvme6000_reset;
     mach_get_model       = bvme6000_get_model;
-    mach_get_hardware_list = bvme6000_get_hardware_list;
 
     printk ("Board is %sconfigured as a System Controller\n",
 		*config_reg_ptr & BVME_CONFIG_SW1 ? "" : "not ");
diff --git a/arch/m68k/kernel/setup.c b/arch/m68k/kernel/setup.c
index ea1e44da19b9..4d97bd2bd573 100644
--- a/arch/m68k/kernel/setup.c
+++ b/arch/m68k/kernel/setup.c
@@ -20,6 +20,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/module.h>
 #include <linux/initrd.h>
@@ -80,7 +81,7 @@ void (*mach_sched_init) (irq_handler_t handler) __initdata = NULL;
 /* machine dependent irq functions */
 void (*mach_init_IRQ) (void) __initdata = NULL;
 void (*mach_get_model) (char *model);
-int (*mach_get_hardware_list) (char *buffer);
+void (*mach_get_hardware_list) (struct seq_file *m);
 /* machine dependent timer functions */
 unsigned long (*mach_gettimeoffset) (void);
 int (*mach_hwclk) (int, struct rtc_time*);
@@ -467,9 +468,9 @@ const struct seq_operations cpuinfo_op = {
 	.show	= show_cpuinfo,
 };
 
-int get_hardware_list(char *buffer)
+#ifdef CONFIG_PROC_HARDWARE
+static int hardware_proc_show(struct seq_file *m, void *v)
 {
-	int len = 0;
 	char model[80];
 	unsigned long mem;
 	int i;
@@ -479,17 +480,37 @@ int get_hardware_list(char *buffer)
 	else
 		strcpy(model, "Unknown m68k");
 
-	len += sprintf(buffer + len, "Model:\t\t%s\n", model);
+	seq_printf(m, "Model:\t\t%s\n", model);
 	for (mem = 0, i = 0; i < m68k_num_memory; i++)
 		mem += m68k_memory[i].size;
-	len += sprintf(buffer + len, "System Memory:\t%ldK\n", mem >> 10);
+	seq_printf(m, "System Memory:\t%ldK\n", mem >> 10);
 
 	if (mach_get_hardware_list)
-		len += mach_get_hardware_list(buffer + len);
+		mach_get_hardware_list(m);
 
-	return len;
+	return 0;
+}
+
+static int hardware_proc_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, hardware_proc_show, NULL);
 }
 
+static const struct file_operations hardware_proc_fops = {
+	.open		= hardware_proc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+static int __init proc_hardware_init(void)
+{
+	proc_create("hardware", 0, NULL, &hardware_proc_fops);
+	return 0;
+}
+module_init(proc_hardware_init);
+#endif
+
 void check_bugs(void)
 {
 #ifndef CONFIG_M68KFPU_EMU
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index 92fe50714112..43cdf476ffab 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -37,7 +37,6 @@
 
 
 static void mvme147_get_model(char *model);
-static int  mvme147_get_hardware_list(char *buffer);
 extern void mvme147_sched_init(irq_handler_t handler);
 extern unsigned long mvme147_gettimeoffset (void);
 extern int mvme147_hwclk (int, struct rtc_time *);
@@ -76,14 +75,6 @@ static void mvme147_get_model(char *model)
 	sprintf(model, "Motorola MVME147");
 }
 
-
-static int mvme147_get_hardware_list(char *buffer)
-{
-	*buffer = '\0';
-
-	return 0;
-}
-
 /*
  * This function is called during kernel startup to initialize
  * the mvme147 IRQ handling routines.
@@ -104,7 +95,6 @@ void __init config_mvme147(void)
 	mach_set_clock_mmss	= mvme147_set_clock_mmss;
 	mach_reset		= mvme147_reset;
 	mach_get_model		= mvme147_get_model;
-	mach_get_hardware_list	= mvme147_get_hardware_list;
 
 	/* Board type is only set by newer versions of vmelilo/tftplilo */
 	if (!vme_brdtype)
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 24cbc3030454..1521826fc3c7 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -17,6 +17,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/seq_file.h>
 #include <linux/tty.h>
 #include <linux/console.h>
 #include <linux/linkage.h>
@@ -42,7 +43,6 @@ extern t_bdid mvme_bdid;
 static MK48T08ptr_t volatile rtc = (MK48T08ptr_t)MVME_RTC_BASE;
 
 static void mvme16x_get_model(char *model);
-static int  mvme16x_get_hardware_list(char *buffer);
 extern void mvme16x_sched_init(irq_handler_t handler);
 extern unsigned long mvme16x_gettimeoffset (void);
 extern int mvme16x_hwclk (int, struct rtc_time *);
@@ -93,26 +93,21 @@ static void mvme16x_get_model(char *model)
 }
 
 
-static int mvme16x_get_hardware_list(char *buffer)
+static void mvme16x_get_hardware_list(struct seq_file *m)
 {
     p_bdid p = &mvme_bdid;
-    int len = 0;
 
     if (p->brdno == 0x0162 || p->brdno == 0x0172)
     {
 	unsigned char rev = *(unsigned char *)MVME162_VERSION_REG;
 
-	len += sprintf (buffer+len, "VMEchip2        %spresent\n",
+	seq_printf (m, "VMEchip2        %spresent\n",
 			rev & MVME16x_CONFIG_NO_VMECHIP2 ? "NOT " : "");
-	len += sprintf (buffer+len, "SCSI interface  %spresent\n",
+	seq_printf (m, "SCSI interface  %spresent\n",
 			rev & MVME16x_CONFIG_NO_SCSICHIP ? "NOT " : "");
-	len += sprintf (buffer+len, "Ethernet i/f    %spresent\n",
+	seq_printf (m, "Ethernet i/f    %spresent\n",
 			rev & MVME16x_CONFIG_NO_ETHERNET ? "NOT " : "");
     }
-    else
-	*buffer = '\0';
-
-    return (len);
 }
 
 /*
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index 9c7eefa3f98a..7110546e3c00 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -39,7 +39,6 @@
 extern irqreturn_t q40_process_int(int level, struct pt_regs *regs);
 extern void q40_init_IRQ(void);
 static void q40_get_model(char *model);
-static int  q40_get_hardware_list(char *buffer);
 extern void q40_sched_init(irq_handler_t handler);
 
 static unsigned long q40_gettimeoffset(void);
@@ -153,14 +152,6 @@ static void q40_get_model(char *model)
 	sprintf(model, "Q40");
 }
 
-/* No hardware options on Q40? */
-
-static int q40_get_hardware_list(char *buffer)
-{
-	*buffer = '\0';
-	return 0;
-}
-
 static unsigned int serports[] =
 {
 	0x3f8,0x2f8,0x3e8,0x2e8,0
@@ -191,7 +182,6 @@ void __init config_q40(void)
 
 	mach_reset = q40_reset;
 	mach_get_model = q40_get_model;
-	mach_get_hardware_list = q40_get_hardware_list;
 
 #if defined(CONFIG_INPUT_M68K_BEEP) || defined(CONFIG_INPUT_M68K_BEEP_MODULE)
 	mach_beep = q40_mksound;
diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c
index 732087d0735c..8dfaa201342e 100644
--- a/arch/m68k/sun3/config.c
+++ b/arch/m68k/sun3/config.c
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
+#include <linux/seq_file.h>
 #include <linux/tty.h>
 #include <linux/console.h>
 #include <linux/init.h>
@@ -46,16 +47,9 @@ extern volatile unsigned char* sun3_intreg;
 extern unsigned long availmem;
 unsigned long num_pages;
 
-static int sun3_get_hardware_list(char *buffer)
+static void sun3_get_hardware_list(struct seq_file *m)
 {
-
-	int len = 0;
-
-	len += sprintf(buffer + len, "PROM Revision:\t%s\n",
-		       romvec->pv_monid);
-
-	return len;
-
+	seq_printf(m, "PROM Revision:\t%s\n", romvec->pv_monid);
 }
 
 void __init sun3_init(void)
diff --git a/arch/m68k/sun3x/config.c b/arch/m68k/sun3x/config.c
index 987891783a47..2b1ca2db070f 100644
--- a/arch/m68k/sun3x/config.c
+++ b/arch/m68k/sun3x/config.c
@@ -8,6 +8,7 @@
 
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/seq_file.h>
 #include <linux/console.h>
 #include <linux/init.h>
 
@@ -31,16 +32,9 @@ void sun3_leds(unsigned int i)
 
 }
 
-static int sun3x_get_hardware_list(char *buffer)
+static void sun3x_get_hardware_list(struct seq_file *m)
 {
-
-	int len = 0;
-
-	len += sprintf(buffer + len, "PROM Revision:\t%s\n",
-		       romvec->pv_monid);
-
-	return len;
-
+	seq_printf(m, "PROM Revision:\t%s\n", romvec->pv_monid);
 }
 
 /*
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 4814b111d836..542527f6630f 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -63,7 +63,6 @@
  * have a way to deal with that gracefully. Right now I used straightforward
  * wrappers, but this needs further analysis wrt potential overflows.
  */
-extern int get_hardware_list(char *);
 extern int get_stram_list(char *);
 extern int get_exec_domain_list(char *);
 
@@ -198,15 +197,6 @@ static const struct file_operations proc_vmstat_file_operations = {
 	.release	= seq_release,
 };
 
-#ifdef CONFIG_PROC_HARDWARE
-static int hardware_read_proc(char *page, char **start, off_t off,
-				 int count, int *eof, void *data)
-{
-	int len = get_hardware_list(page);
-	return proc_calc_metrics(page, start, off, count, eof, len);
-}
-#endif
-
 #ifdef CONFIG_STRAM_PROC
 static int stram_read_proc(char *page, char **start, off_t off,
 				 int count, int *eof, void *data)
@@ -668,9 +658,6 @@ void __init proc_misc_init(void)
 		char *name;
 		int (*read_proc)(char*,char**,off_t,int,int*,void*);
 	} *p, simple_ones[] = {
-#ifdef CONFIG_PROC_HARDWARE
-		{"hardware",	hardware_read_proc},
-#endif
 #ifdef CONFIG_STRAM_PROC
 		{"stram",	stram_read_proc},
 #endif
diff --git a/include/asm-m68k/machdep.h b/include/asm-m68k/machdep.h
index 26d2b91209c5..5637dcef314e 100644
--- a/include/asm-m68k/machdep.h
+++ b/include/asm-m68k/machdep.h
@@ -14,7 +14,7 @@ extern void (*mach_sched_init) (irq_handler_t handler);
 /* machine dependent irq functions */
 extern void (*mach_init_IRQ) (void);
 extern void (*mach_get_model) (char *model);
-extern int (*mach_get_hardware_list) (char *buffer);
+extern void (*mach_get_hardware_list) (struct seq_file *m);
 /* machine dependent timer functions */
 extern unsigned long (*mach_gettimeoffset)(void);
 extern int (*mach_hwclk)(int, struct rtc_time*);
-- 
cgit v1.2.3


From d8ba7a363393f803c93c8cffabd6d0362618bc2a Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Sat, 4 Oct 2008 22:34:18 +0400
Subject: proc: move rest of /proc/locks to fs/locks.c

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 fs/locks.c          | 22 +++++++++++++++++++++-
 fs/proc/proc_misc.c | 17 -----------------
 include/linux/fs.h  |  1 -
 3 files changed, 21 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/fs/locks.c b/fs/locks.c
index 5eb259e3cd38..90e87f57b331 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2078,6 +2078,7 @@ int vfs_cancel_lock(struct file *filp, struct file_lock *fl)
 EXPORT_SYMBOL_GPL(vfs_cancel_lock);
 
 #ifdef CONFIG_PROC_FS
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
 static void lock_get_status(struct seq_file *f, struct file_lock *fl,
@@ -2183,12 +2184,31 @@ static void locks_stop(struct seq_file *f, void *v)
 	unlock_kernel();
 }
 
-struct seq_operations locks_seq_operations = {
+static const struct seq_operations locks_seq_operations = {
 	.start	= locks_start,
 	.next	= locks_next,
 	.stop	= locks_stop,
 	.show	= locks_show,
 };
+
+static int locks_open(struct inode *inode, struct file *filp)
+{
+	return seq_open(filp, &locks_seq_operations);
+}
+
+static const struct file_operations proc_locks_operations = {
+	.open		= locks_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int __init proc_locks_init(void)
+{
+	proc_create("locks", 0, NULL, &proc_locks_operations);
+	return 0;
+}
+module_init(proc_locks_init);
 #endif
 
 /**
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index fcac25edaef7..fea7d658fff6 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -453,20 +453,6 @@ static const struct file_operations proc_interrupts_operations = {
 	.release	= seq_release,
 };
 
-#ifdef CONFIG_FILE_LOCKING
-static int locks_open(struct inode *inode, struct file *filp)
-{
-	return seq_open(filp, &locks_seq_operations);
-}
-
-static const struct file_operations proc_locks_operations = {
-	.open		= locks_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-#endif /* CONFIG_FILE_LOCKING */
-
 #ifdef CONFIG_PROC_PAGE_MONITOR
 #define KPMSIZE sizeof(u64)
 #define KPMMASK (KPMSIZE - 1)
@@ -605,9 +591,6 @@ void __init proc_misc_init(void)
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-#ifdef CONFIG_FILE_LOCKING
-	proc_create("locks", 0, NULL, &proc_locks_operations);
-#endif
 	proc_create("devices", 0, NULL, &proc_devinfo_operations);
 	proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations);
 #ifdef CONFIG_BLOCK
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a6a625be13fc..024049543ae1 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1037,7 +1037,6 @@ extern int vfs_setlease(struct file *, long, struct file_lock **);
 extern int lease_modify(struct file_lock **, int);
 extern int lock_may_read(struct inode *, loff_t start, unsigned long count);
 extern int lock_may_write(struct inode *, loff_t start, unsigned long count);
-extern struct seq_operations locks_seq_operations;
 #else /* !CONFIG_FILE_LOCKING */
 #define fcntl_getlk(a, b) ({ -EINVAL; })
 #define fcntl_setlk(a, b, c, d) ({ -EACCES; })
-- 
cgit v1.2.3


From f500975a3f3ecf3611d79f1d933906753460b9f2 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Sat, 4 Oct 2008 23:53:21 +0400
Subject: proc: move rest of /proc/partitions code to block/genhd.c

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Acked-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/genhd.c         | 22 +++++++++++++++++++++-
 fs/proc/proc_misc.c   | 14 --------------
 include/linux/genhd.h |  1 -
 3 files changed, 21 insertions(+), 16 deletions(-)

(limited to 'include')

diff --git a/block/genhd.c b/block/genhd.c
index 646e1d2507c7..15f4d2b12c48 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -10,6 +10,7 @@
 #include <linux/blkdev.h>
 #include <linux/init.h>
 #include <linux/spinlock.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/kmod.h>
@@ -727,12 +728,24 @@ static int show_partition(struct seq_file *seqf, void *v)
 	return 0;
 }
 
-const struct seq_operations partitions_op = {
+static const struct seq_operations partitions_op = {
 	.start	= show_partition_start,
 	.next	= disk_seqf_next,
 	.stop	= disk_seqf_stop,
 	.show	= show_partition
 };
+
+static int partitions_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &partitions_op);
+}
+
+static const struct file_operations proc_partitions_operations = {
+	.open		= partitions_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
 #endif
 
 
@@ -998,6 +1011,13 @@ const struct seq_operations diskstats_op = {
 	.stop	= disk_seqf_stop,
 	.show	= diskstats_show
 };
+
+static int __init proc_genhd_init(void)
+{
+	proc_create("partitions", 0, NULL, &proc_partitions_operations);
+	return 0;
+}
+module_init(proc_genhd_init);
 #endif /* CONFIG_PROC_FS */
 
 static void media_change_notify_thread(struct work_struct *work)
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 8974809be5f6..253ea50c4393 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -106,17 +106,6 @@ static const struct file_operations proc_vmstat_file_operations = {
 };
 
 #ifdef CONFIG_BLOCK
-static int partitions_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &partitions_op);
-}
-static const struct file_operations proc_partitions_operations = {
-	.open		= partitions_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static int diskstats_open(struct inode *inode, struct file *file)
 {
 	return seq_open(file, &diskstats_op);
@@ -519,9 +508,6 @@ void __init proc_misc_init(void)
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-#ifdef CONFIG_BLOCK
-	proc_create("partitions", 0, NULL, &proc_partitions_operations);
-#endif
 	proc_create("stat", 0, NULL, &proc_stat_operations);
 	proc_create("interrupts", 0, NULL, &proc_interrupts_operations);
 #ifdef CONFIG_SLABINFO
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 206cdf96c3a7..074a4fdf4365 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -25,7 +25,6 @@ extern struct device_type part_type;
 extern struct kobject *block_depr;
 extern struct class block_class;
 
-extern const struct seq_operations partitions_op;
 extern const struct seq_operations diskstats_op;
 
 enum {
-- 
cgit v1.2.3


From 7b3c3a50a3e0ea46815150d420fa276ac254572b Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Mon, 6 Oct 2008 02:42:17 +0400
Subject: proc: move /proc/slabinfo boilerplate to mm/slub.c, mm/slab.c

Lose dummy ->write hook in case of SLUB, it's possible now.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Acked-by: Pekka Enberg <penberg@cs.helsinki.fi>
---
 fs/proc/proc_misc.c  | 17 -----------------
 include/linux/slab.h |  5 -----
 mm/slab.c            | 16 +++++++++++++++-
 mm/slub.c            | 29 ++++++++++++++++++++---------
 4 files changed, 35 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 5bca02842d07..1d6d5c5cc2a8 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -132,20 +132,6 @@ static const struct file_operations proc_modules_operations = {
 };
 #endif
 
-#ifdef CONFIG_SLABINFO
-static int slabinfo_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &slabinfo_op);
-}
-static const struct file_operations proc_slabinfo_operations = {
-	.open		= slabinfo_open,
-	.read		= seq_read,
-	.write		= slabinfo_write,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-#endif
-
 #ifdef CONFIG_MMU
 static int vmalloc_open(struct inode *inode, struct file *file)
 {
@@ -309,9 +295,6 @@ void __init proc_misc_init(void)
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-#ifdef CONFIG_SLABINFO
-	proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations);
-#endif
 #ifdef CONFIG_MMU
 	proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations);
 #endif
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 5ff9676c1e2c..ba965c84ae06 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -288,9 +288,4 @@ static inline void *kzalloc_node(size_t size, gfp_t flags, int node)
 	return kmalloc_node(size, flags | __GFP_ZERO, node);
 }
 
-#ifdef CONFIG_SLABINFO
-extern const struct seq_operations slabinfo_op;
-ssize_t slabinfo_write(struct file *, const char __user *, size_t, loff_t *);
-#endif
-
 #endif	/* _LINUX_SLAB_H */
diff --git a/mm/slab.c b/mm/slab.c
index d53ac9c26ab7..09187517f9dc 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -4259,7 +4259,7 @@ static int s_show(struct seq_file *m, void *p)
  * + further values on SMP and with statistics enabled
  */
 
-const struct seq_operations slabinfo_op = {
+static const struct seq_operations slabinfo_op = {
 	.start = s_start,
 	.next = s_next,
 	.stop = s_stop,
@@ -4316,6 +4316,19 @@ ssize_t slabinfo_write(struct file *file, const char __user * buffer,
 	return res;
 }
 
+static int slabinfo_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &slabinfo_op);
+}
+
+static const struct file_operations proc_slabinfo_operations = {
+	.open		= slabinfo_open,
+	.read		= seq_read,
+	.write		= slabinfo_write,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 #ifdef CONFIG_DEBUG_SLAB_LEAK
 
 static void *leaks_start(struct seq_file *m, loff_t *pos)
@@ -4478,6 +4491,7 @@ static const struct file_operations proc_slabstats_operations = {
 
 static int __init slab_proc_init(void)
 {
+	proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations);
 #ifdef CONFIG_DEBUG_SLAB_LEAK
 	proc_create("slab_allocators", 0, NULL, &proc_slabstats_operations);
 #endif
diff --git a/mm/slub.c b/mm/slub.c
index 0c83e6afe7b2..7ad489af9561 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -14,6 +14,7 @@
 #include <linux/interrupt.h>
 #include <linux/bitops.h>
 #include <linux/slab.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
@@ -4417,14 +4418,6 @@ __initcall(slab_sysfs_init);
  * The /proc/slabinfo ABI
  */
 #ifdef CONFIG_SLABINFO
-
-ssize_t slabinfo_write(struct file *file, const char __user *buffer,
-		       size_t count, loff_t *ppos)
-{
-	return -EINVAL;
-}
-
-
 static void print_slabinfo_header(struct seq_file *m)
 {
 	seq_puts(m, "slabinfo - version: 2.1\n");
@@ -4492,11 +4485,29 @@ static int s_show(struct seq_file *m, void *p)
 	return 0;
 }
 
-const struct seq_operations slabinfo_op = {
+static const struct seq_operations slabinfo_op = {
 	.start = s_start,
 	.next = s_next,
 	.stop = s_stop,
 	.show = s_show,
 };
 
+static int slabinfo_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &slabinfo_op);
+}
+
+static const struct file_operations proc_slabinfo_operations = {
+	.open		= slabinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+static int __init slab_proc_init(void)
+{
+	proc_create("slabinfo",S_IWUSR|S_IRUGO,NULL,&proc_slabinfo_operations);
+	return 0;
+}
+module_init(slab_proc_init);
 #endif /* CONFIG_SLABINFO */
-- 
cgit v1.2.3


From 5f6a6a9c4e4d790aae55cb412a7643329057c5e0 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Mon, 6 Oct 2008 03:50:47 +0400
Subject: proc: move /proc/vmallocinfo to mm/vmalloc.c

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Acked-by: Christoph Lameter <cl@linux-foundation.org>
---
 fs/proc/proc_misc.c     | 28 ----------------------------
 include/linux/vmalloc.h |  2 --
 mm/vmalloc.c            | 33 ++++++++++++++++++++++++++++++++-
 3 files changed, 32 insertions(+), 31 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 1d6d5c5cc2a8..fd41a032456b 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -132,31 +132,6 @@ static const struct file_operations proc_modules_operations = {
 };
 #endif
 
-#ifdef CONFIG_MMU
-static int vmalloc_open(struct inode *inode, struct file *file)
-{
-	unsigned int *ptr = NULL;
-	int ret;
-
-	if (NUMA_BUILD)
-		ptr = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
-	ret = seq_open(file, &vmalloc_op);
-	if (!ret) {
-		struct seq_file *m = file->private_data;
-		m->private = ptr;
-	} else
-		kfree(ptr);
-	return ret;
-}
-
-static const struct file_operations proc_vmalloc_operations = {
-	.open		= vmalloc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_private,
-};
-#endif
-
 #ifdef CONFIG_PROC_PAGE_MONITOR
 #define KPMSIZE sizeof(u64)
 #define KPMMASK (KPMSIZE - 1)
@@ -295,9 +270,6 @@ void __init proc_misc_init(void)
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-#ifdef CONFIG_MMU
-	proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations);
-#endif
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
 	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
 	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 4c28c4d564e2..307b88577eaa 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -103,6 +103,4 @@ extern void free_vm_area(struct vm_struct *area);
 extern rwlock_t vmlist_lock;
 extern struct vm_struct *vmlist;
 
-extern const struct seq_operations vmalloc_op;
-
 #endif /* _LINUX_VMALLOC_H */
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 65ae576030da..036536945dd9 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -15,6 +15,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/debugobjects.h>
 #include <linux/kallsyms.h>
@@ -1718,11 +1719,41 @@ static int s_show(struct seq_file *m, void *p)
 	return 0;
 }
 
-const struct seq_operations vmalloc_op = {
+static const struct seq_operations vmalloc_op = {
 	.start = s_start,
 	.next = s_next,
 	.stop = s_stop,
 	.show = s_show,
 };
+
+static int vmalloc_open(struct inode *inode, struct file *file)
+{
+	unsigned int *ptr = NULL;
+	int ret;
+
+	if (NUMA_BUILD)
+		ptr = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
+	ret = seq_open(file, &vmalloc_op);
+	if (!ret) {
+		struct seq_file *m = file->private_data;
+		m->private = ptr;
+	} else
+		kfree(ptr);
+	return ret;
+}
+
+static const struct file_operations proc_vmalloc_operations = {
+	.open		= vmalloc_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+static int __init proc_vmalloc_init(void)
+{
+	proc_create("vmallocinfo", S_IRUSR, NULL, &proc_vmalloc_operations);
+	return 0;
+}
+module_init(proc_vmalloc_init);
 #endif
 
-- 
cgit v1.2.3


From 8f32f7e5ac2ed11b0659b6b55af926f3d58ffd9d Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Mon, 6 Oct 2008 04:13:52 +0400
Subject: proc: move /proc/buddyinfo boilerplate to mm/vmstat.c

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 fs/proc/proc_misc.c    | 14 --------------
 include/linux/vmstat.h |  1 -
 mm/vmstat.c            | 25 +++++++++++++++++++++----
 3 files changed, 21 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index fd41a032456b..a35e50659b8d 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -57,19 +57,6 @@
 #include <asm/div64.h>
 #include "internal.h"
 
-static int fragmentation_open(struct inode *inode, struct file *file)
-{
-	(void)inode;
-	return seq_open(file, &fragmentation_op);
-}
-
-static const struct file_operations fragmentation_file_operations = {
-	.open		= fragmentation_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static int pagetypeinfo_open(struct inode *inode, struct file *file)
 {
 	return seq_open(file, &pagetypeinfo_op);
@@ -270,7 +257,6 @@ void __init proc_misc_init(void)
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
 	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
 	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
 	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 9cd3ab0f554d..d4551f206409 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -54,7 +54,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		NR_VM_EVENT_ITEMS
 };
 
-extern const struct seq_operations fragmentation_op;
 extern const struct seq_operations pagetypeinfo_op;
 extern const struct seq_operations zoneinfo_op;
 extern const struct seq_operations vmstat_op;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 9343227c5c60..f45d7245a282 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -8,7 +8,7 @@
  *  Copyright (C) 2006 Silicon Graphics, Inc.,
  *		Christoph Lameter <christoph@lameter.com>
  */
-
+#include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/err.h>
 #include <linux/module.h>
@@ -384,7 +384,7 @@ void zone_statistics(struct zone *preferred_zone, struct zone *z)
 #endif
 
 #ifdef CONFIG_PROC_FS
-
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
 static char * const migratetype_names[MIGRATE_TYPES] = {
@@ -581,13 +581,25 @@ static int pagetypeinfo_show(struct seq_file *m, void *arg)
 	return 0;
 }
 
-const struct seq_operations fragmentation_op = {
+static const struct seq_operations fragmentation_op = {
 	.start	= frag_start,
 	.next	= frag_next,
 	.stop	= frag_stop,
 	.show	= frag_show,
 };
 
+static int fragmentation_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &fragmentation_op);
+}
+
+static const struct file_operations fragmentation_file_operations = {
+	.open		= fragmentation_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 const struct seq_operations pagetypeinfo_op = {
 	.start	= frag_start,
 	.next	= frag_next,
@@ -898,9 +910,11 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
 
 static struct notifier_block __cpuinitdata vmstat_notifier =
 	{ &vmstat_cpuup_callback, NULL, 0 };
+#endif
 
 static int __init setup_vmstat(void)
 {
+#ifdef CONFIG_SMP
 	int cpu;
 
 	refresh_zone_stat_thresholds();
@@ -908,7 +922,10 @@ static int __init setup_vmstat(void)
 
 	for_each_online_cpu(cpu)
 		start_cpu_timer(cpu);
+#endif
+#ifdef CONFIG_PROC_FS
+	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
+#endif
 	return 0;
 }
 module_init(setup_vmstat)
-#endif
-- 
cgit v1.2.3


From 74e2e8e8ce7b3c0f878a349f9fa6cf2831548eef Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Mon, 6 Oct 2008 04:15:36 +0400
Subject: proc: move /proc/pagetypeinfo boilerplate to mm/vmstat.c

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 fs/proc/proc_misc.c    | 13 -------------
 include/linux/vmstat.h |  1 -
 mm/vmstat.c            | 15 ++++++++++++++-
 3 files changed, 14 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index a35e50659b8d..900331a634ef 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -57,18 +57,6 @@
 #include <asm/div64.h>
 #include "internal.h"
 
-static int pagetypeinfo_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &pagetypeinfo_op);
-}
-
-static const struct file_operations pagetypeinfo_file_ops = {
-	.open		= pagetypeinfo_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 static int zoneinfo_open(struct inode *inode, struct file *file)
 {
 	return seq_open(file, &zoneinfo_op);
@@ -257,7 +245,6 @@ void __init proc_misc_init(void)
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
 	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
 	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
 #ifdef CONFIG_BLOCK
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index d4551f206409..33ffd89a88ac 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -54,7 +54,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		NR_VM_EVENT_ITEMS
 };
 
-extern const struct seq_operations pagetypeinfo_op;
 extern const struct seq_operations zoneinfo_op;
 extern const struct seq_operations vmstat_op;
 extern int sysctl_stat_interval;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f45d7245a282..d624d251946d 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -600,13 +600,25 @@ static const struct file_operations fragmentation_file_operations = {
 	.release	= seq_release,
 };
 
-const struct seq_operations pagetypeinfo_op = {
+static const struct seq_operations pagetypeinfo_op = {
 	.start	= frag_start,
 	.next	= frag_next,
 	.stop	= frag_stop,
 	.show	= pagetypeinfo_show,
 };
 
+static int pagetypeinfo_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &pagetypeinfo_op);
+}
+
+static const struct file_operations pagetypeinfo_file_ops = {
+	.open		= pagetypeinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 #ifdef CONFIG_ZONE_DMA
 #define TEXT_FOR_DMA(xx) xx "_dma",
 #else
@@ -925,6 +937,7 @@ static int __init setup_vmstat(void)
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
+	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
 #endif
 	return 0;
 }
-- 
cgit v1.2.3


From b6aa44ab698c7df9d951d3eb45c4fcb8ba68fb25 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Mon, 6 Oct 2008 04:17:48 +0400
Subject: proc: move /proc/vmstat boilerplate to mm/vmstat.c

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Acked-by: Christoph Lameter <cl@linux-foundation.org>
---
 fs/proc/proc_misc.c    | 12 ------------
 include/linux/vmstat.h |  1 -
 mm/vmstat.c            | 14 +++++++++++++-
 3 files changed, 13 insertions(+), 14 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 900331a634ef..e7a301d5d432 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -69,17 +69,6 @@ static const struct file_operations proc_zoneinfo_file_operations = {
 	.release	= seq_release,
 };
 
-static int vmstat_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &vmstat_op);
-}
-static const struct file_operations proc_vmstat_file_operations = {
-	.open		= vmstat_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 #ifdef CONFIG_BLOCK
 static int diskstats_open(struct inode *inode, struct file *file)
 {
@@ -245,7 +234,6 @@ void __init proc_misc_init(void)
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
 	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
 #ifdef CONFIG_BLOCK
 	proc_create("diskstats", 0, NULL, &proc_diskstats_operations);
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 33ffd89a88ac..7b68c4c1e19c 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -55,7 +55,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 };
 
 extern const struct seq_operations zoneinfo_op;
-extern const struct seq_operations vmstat_op;
 extern int sysctl_stat_interval;
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
diff --git a/mm/vmstat.c b/mm/vmstat.c
index d624d251946d..7e1854b81868 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -858,13 +858,24 @@ static void vmstat_stop(struct seq_file *m, void *arg)
 	m->private = NULL;
 }
 
-const struct seq_operations vmstat_op = {
+static const struct seq_operations vmstat_op = {
 	.start	= vmstat_start,
 	.next	= vmstat_next,
 	.stop	= vmstat_stop,
 	.show	= vmstat_show,
 };
 
+static int vmstat_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &vmstat_op);
+}
+
+static const struct file_operations proc_vmstat_file_operations = {
+	.open		= vmstat_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
 #endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_SMP
@@ -938,6 +949,7 @@ static int __init setup_vmstat(void)
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
 	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
+	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
 #endif
 	return 0;
 }
-- 
cgit v1.2.3


From 5c9fe6281b75832e8d2555ec8700ea763d9a865e Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Mon, 6 Oct 2008 04:19:42 +0400
Subject: proc: move /proc/zoneinfo boilerplate to mm/vmstat.c

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Acked-by: Christoph Lameter <cl@linux-foundation.org>
---
 fs/proc/proc_misc.c    | 13 -------------
 include/linux/vmstat.h |  1 -
 mm/vmstat.c            | 15 ++++++++++++++-
 3 files changed, 14 insertions(+), 15 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index e7a301d5d432..8f3a6f085c5f 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -57,18 +57,6 @@
 #include <asm/div64.h>
 #include "internal.h"
 
-static int zoneinfo_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &zoneinfo_op);
-}
-
-static const struct file_operations proc_zoneinfo_file_operations = {
-	.open		= zoneinfo_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-
 #ifdef CONFIG_BLOCK
 static int diskstats_open(struct inode *inode, struct file *file)
 {
@@ -234,7 +222,6 @@ void __init proc_misc_init(void)
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
 #ifdef CONFIG_BLOCK
 	proc_create("diskstats", 0, NULL, &proc_diskstats_operations);
 #endif
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 7b68c4c1e19c..524cd1b28ecb 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -54,7 +54,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		NR_VM_EVENT_ITEMS
 };
 
-extern const struct seq_operations zoneinfo_op;
 extern int sysctl_stat_interval;
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 7e1854b81868..c3ccfda23adc 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -795,7 +795,7 @@ static int zoneinfo_show(struct seq_file *m, void *arg)
 	return 0;
 }
 
-const struct seq_operations zoneinfo_op = {
+static const struct seq_operations zoneinfo_op = {
 	.start	= frag_start, /* iterate over all zones. The same as in
 			       * fragmentation. */
 	.next	= frag_next,
@@ -803,6 +803,18 @@ const struct seq_operations zoneinfo_op = {
 	.show	= zoneinfo_show,
 };
 
+static int zoneinfo_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &zoneinfo_op);
+}
+
+static const struct file_operations proc_zoneinfo_file_operations = {
+	.open		= zoneinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 static void *vmstat_start(struct seq_file *m, loff_t *pos)
 {
 	unsigned long *v;
@@ -950,6 +962,7 @@ static int __init setup_vmstat(void)
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);
 	proc_create("pagetypeinfo", S_IRUGO, NULL, &pagetypeinfo_file_ops);
 	proc_create("vmstat", S_IRUGO, NULL, &proc_vmstat_file_operations);
+	proc_create("zoneinfo", S_IRUGO, NULL, &proc_zoneinfo_file_operations);
 #endif
 	return 0;
 }
-- 
cgit v1.2.3


From 31d85ab28e71b0c938e0ef48af45747e80d99b53 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Mon, 6 Oct 2008 12:55:38 +0400
Subject: proc: move /proc/diskstats boilerplate to block/genhd.c

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Acked-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/genhd.c         | 15 ++++++++++++++-
 fs/proc/proc_misc.c   | 16 ----------------
 include/linux/genhd.h |  2 --
 3 files changed, 14 insertions(+), 19 deletions(-)

(limited to 'include')

diff --git a/block/genhd.c b/block/genhd.c
index 15f4d2b12c48..4e5e7493f676 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1005,15 +1005,28 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 	return 0;
 }
 
-const struct seq_operations diskstats_op = {
+static const struct seq_operations diskstats_op = {
 	.start	= disk_seqf_start,
 	.next	= disk_seqf_next,
 	.stop	= disk_seqf_stop,
 	.show	= diskstats_show
 };
 
+static int diskstats_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &diskstats_op);
+}
+
+static const struct file_operations proc_diskstats_operations = {
+	.open		= diskstats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
 static int __init proc_genhd_init(void)
 {
+	proc_create("diskstats", 0, NULL, &proc_diskstats_operations);
 	proc_create("partitions", 0, NULL, &proc_partitions_operations);
 	return 0;
 }
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 8f3a6f085c5f..7c22831efd94 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -57,19 +57,6 @@
 #include <asm/div64.h>
 #include "internal.h"
 
-#ifdef CONFIG_BLOCK
-static int diskstats_open(struct inode *inode, struct file *file)
-{
-	return seq_open(file, &diskstats_op);
-}
-static const struct file_operations proc_diskstats_operations = {
-	.open		= diskstats_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release,
-};
-#endif
-
 #ifdef CONFIG_MODULES
 extern const struct seq_operations modules_op;
 static int modules_open(struct inode *inode, struct file *file)
@@ -222,9 +209,6 @@ void __init proc_misc_init(void)
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-#ifdef CONFIG_BLOCK
-	proc_create("diskstats", 0, NULL, &proc_diskstats_operations);
-#endif
 #ifdef CONFIG_MODULES
 	proc_create("modules", 0, NULL, &proc_modules_operations);
 #endif
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 074a4fdf4365..e439e6aed832 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -25,8 +25,6 @@ extern struct device_type part_type;
 extern struct kobject *block_depr;
 extern struct class block_class;
 
-extern const struct seq_operations diskstats_op;
-
 enum {
 /* These three have identical behaviour; use the second one if DOS FDISK gets
    confused about extended/logical partitions starting past cylinder 1023. */
-- 
cgit v1.2.3


From b5aadf7f14c1acc94956aa257e018e9de3881f41 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Mon, 6 Oct 2008 13:23:43 +0400
Subject: proc: move /proc/schedstat boilerplate to kernel/sched_stats.h

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 fs/proc/proc_misc.c   | 3 ---
 include/linux/sched.h | 4 ----
 kernel/sched.c        | 1 +
 kernel/sched_stats.h  | 9 ++++++++-
 4 files changed, 9 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index f6d25db98922..4a768ed5da2e 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -195,9 +195,6 @@ void __init proc_misc_init(void)
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-#ifdef CONFIG_SCHEDSTATS
-	proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
-#endif
 #ifdef CONFIG_PROC_KCORE
 	proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations);
 	if (proc_root_kcore)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5c38db536e07..7f60cb9b53cb 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -681,10 +681,6 @@ struct sched_info {
 };
 #endif /* defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) */
 
-#ifdef CONFIG_SCHEDSTATS
-extern const struct file_operations proc_schedstat_operations;
-#endif /* CONFIG_SCHEDSTATS */
-
 #ifdef CONFIG_TASK_DELAY_ACCT
 struct task_delay_info {
 	spinlock_t	lock;
diff --git a/kernel/sched.c b/kernel/sched.c
index d906f72b42d2..5a70189d5051 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -55,6 +55,7 @@
 #include <linux/cpuset.h>
 #include <linux/percpu.h>
 #include <linux/kthread.h>
+#include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/sysctl.h>
 #include <linux/syscalls.h>
diff --git a/kernel/sched_stats.h b/kernel/sched_stats.h
index b8c156979cf2..3d14ce273902 100644
--- a/kernel/sched_stats.h
+++ b/kernel/sched_stats.h
@@ -90,13 +90,20 @@ static int schedstat_open(struct inode *inode, struct file *file)
 	return res;
 }
 
-const struct file_operations proc_schedstat_operations = {
+static const struct file_operations proc_schedstat_operations = {
 	.open    = schedstat_open,
 	.read    = seq_read,
 	.llseek  = seq_lseek,
 	.release = single_release,
 };
 
+static int __init proc_schedstat_init(void)
+{
+	proc_create("schedstat", 0, NULL, &proc_schedstat_operations);
+	return 0;
+}
+module_init(proc_schedstat_init);
+
 /*
  * Expects runqueue lock to be held for atomicity of update
  */
-- 
cgit v1.2.3


From 97ce5d6dcb07c403c0fc6001b755aacc38b5d7ff Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Mon, 6 Oct 2008 14:14:19 +0400
Subject: proc: move all /proc/kcore stuff to fs/proc/kcore.c

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 fs/proc/kcore.c         | 14 +++++++++++++-
 fs/proc/proc_misc.c     |  8 --------
 include/linux/proc_fs.h |  4 ----
 3 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include')

diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index c2370c76fb71..59b43a068872 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -27,6 +27,8 @@
 #define ELF_CORE_EFLAGS	0
 #endif
 
+static struct proc_dir_entry *proc_root_kcore;
+
 static int open_kcore(struct inode * inode, struct file * filp)
 {
 	return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
@@ -34,7 +36,7 @@ static int open_kcore(struct inode * inode, struct file * filp)
 
 static ssize_t read_kcore(struct file *, char __user *, size_t, loff_t *);
 
-const struct file_operations proc_kcore_operations = {
+static const struct file_operations proc_kcore_operations = {
 	.read		= read_kcore,
 	.open		= open_kcore,
 };
@@ -399,3 +401,13 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 
 	return acc;
 }
+
+static int __init proc_kcore_init(void)
+{
+	proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations);
+	if (proc_root_kcore)
+		proc_root_kcore->size =
+				(size_t)high_memory - PAGE_OFFSET + PAGE_SIZE;
+	return 0;
+}
+module_init(proc_kcore_init);
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 4a768ed5da2e..5ed15ff8fd1d 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -188,19 +188,11 @@ static struct file_operations proc_kpageflags_operations = {
 };
 #endif /* CONFIG_PROC_PAGE_MONITOR */
 
-struct proc_dir_entry *proc_root_kcore;
-
 void __init proc_misc_init(void)
 {
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-#ifdef CONFIG_PROC_KCORE
-	proc_root_kcore = proc_create("kcore", S_IRUSR, NULL, &proc_kcore_operations);
-	if (proc_root_kcore)
-		proc_root_kcore->size =
-				(size_t)high_memory - PAGE_OFFSET + PAGE_SIZE;
-#endif
 #ifdef CONFIG_PROC_PAGE_MONITOR
 	proc_create("kpagecount", S_IRUSR, NULL, &proc_kpagecount_operations);
 	proc_create("kpageflags", S_IRUSR, NULL, &proc_kpageflags_operations);
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 27d534f4470d..9d8308905053 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -97,8 +97,6 @@ struct vmcore {
 
 #ifdef CONFIG_PROC_FS
 
-extern struct proc_dir_entry *proc_root_kcore;
-
 extern spinlock_t proc_subdir_lock;
 
 extern void proc_root_init(void);
@@ -138,8 +136,6 @@ extern struct inode *proc_get_inode(struct super_block *, unsigned int, struct p
 extern int proc_readdir(struct file *, void *, filldir_t);
 extern struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *);
 
-extern const struct file_operations proc_kcore_operations;
-
 extern int pid_ns_prepare_proc(struct pid_namespace *ns);
 extern void pid_ns_release_proc(struct pid_namespace *ns);
 
-- 
cgit v1.2.3


From 5aa140c2deca3701238d5acddf436ad7b02664c7 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Mon, 6 Oct 2008 14:36:31 +0400
Subject: proc: move /proc/vmcore creation to fs/proc/vmcore.c

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 fs/proc/proc_misc.c        | 3 ---
 fs/proc/vmcore.c           | 6 +++---
 include/linux/crash_dump.h | 2 --
 3 files changed, 3 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
index 2ef9ef9bc8c1..e2db35006c05 100644
--- a/fs/proc/proc_misc.c
+++ b/fs/proc/proc_misc.c
@@ -62,7 +62,4 @@ void __init proc_misc_init(void)
 	proc_symlink("mounts", NULL, "self/mounts");
 
 	/* And now for trickier ones */
-#ifdef CONFIG_PROC_VMCORE
-	proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
-#endif
 }
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index cd9ca67f841b..03ec59504906 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -32,7 +32,7 @@ static size_t elfcorebuf_sz;
 /* Total size of vmcore file. */
 static u64 vmcore_size;
 
-struct proc_dir_entry *proc_vmcore = NULL;
+static struct proc_dir_entry *proc_vmcore = NULL;
 
 /* Reads a page from the oldmem device from given offset. */
 static ssize_t read_from_oldmem(char *buf, size_t count,
@@ -162,7 +162,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 	return acc;
 }
 
-const struct file_operations proc_vmcore_operations = {
+static const struct file_operations proc_vmcore_operations = {
 	.read		= read_vmcore,
 };
 
@@ -652,7 +652,7 @@ static int __init vmcore_init(void)
 		return rc;
 	}
 
-	/* Initialize /proc/vmcore size if proc is already up. */
+	proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
 	if (proc_vmcore)
 		proc_vmcore->size = vmcore_size;
 	return 0;
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 0acf3b737e2e..2dac064d8359 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -14,8 +14,6 @@ extern unsigned long long elfcorehdr_addr;
 
 extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
 						unsigned long, int);
-extern const struct file_operations proc_vmcore_operations;
-extern struct proc_dir_entry *proc_vmcore;
 
 /* Architecture code defines this if there are other possible ELF
  * machine types, e.g. on bi-arch capable hardware. */
-- 
cgit v1.2.3


From 59c7572e82d69483a66eaa67b46548baeb69ecf4 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Mon, 6 Oct 2008 14:49:39 +0400
Subject: proc: remove fs/proc/proc_misc.c

Now that everything was moved to their more or less expected places,
apply rm(1).

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
---
 fs/proc/Makefile        |  2 +-
 fs/proc/proc_misc.c     | 65 -------------------------------------------------
 fs/proc/root.c          |  2 +-
 include/linux/proc_fs.h |  1 -
 4 files changed, 2 insertions(+), 68 deletions(-)
 delete mode 100644 fs/proc/proc_misc.c

(limited to 'include')

diff --git a/fs/proc/Makefile b/fs/proc/Makefile
index fef524410e86..63d965193b22 100644
--- a/fs/proc/Makefile
+++ b/fs/proc/Makefile
@@ -8,7 +8,7 @@ proc-y			:= nommu.o task_nommu.o
 proc-$(CONFIG_MMU)	:= mmu.o task_mmu.o
 
 proc-y       += inode.o root.o base.o generic.o array.o \
-		proc_tty.o proc_misc.o
+		proc_tty.o
 proc-y	+= cmdline.o
 proc-y	+= cpuinfo.o
 proc-y	+= devices.o
diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c
deleted file mode 100644
index e2db35006c05..000000000000
--- a/fs/proc/proc_misc.c
+++ /dev/null
@@ -1,65 +0,0 @@
-/*
- *  linux/fs/proc/proc_misc.c
- *
- *  linux/fs/proc/array.c
- *  Copyright (C) 1992  by Linus Torvalds
- *  based on ideas by Darren Senn
- *
- *  This used to be the part of array.c. See the rest of history and credits
- *  there. I took this into a separate file and switched the thing to generic
- *  proc_file_inode_operations, leaving in array.c only per-process stuff.
- *  Inumbers allocation made dynamic (via create_proc_entry()).  AV, May 1999.
- *
- * Changes:
- * Fulton Green      :  Encapsulated position metric calculations.
- *			<kernel@FultonGreen.com>
- */
-
-#include <linux/types.h>
-#include <linux/errno.h>
-#include <linux/time.h>
-#include <linux/kernel.h>
-#include <linux/kernel_stat.h>
-#include <linux/fs.h>
-#include <linux/tty.h>
-#include <linux/string.h>
-#include <linux/mman.h>
-#include <linux/quicklist.h>
-#include <linux/proc_fs.h>
-#include <linux/ioport.h>
-#include <linux/mm.h>
-#include <linux/mmzone.h>
-#include <linux/pagemap.h>
-#include <linux/irq.h>
-#include <linux/interrupt.h>
-#include <linux/swap.h>
-#include <linux/slab.h>
-#include <linux/genhd.h>
-#include <linux/smp.h>
-#include <linux/signal.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/seq_file.h>
-#include <linux/times.h>
-#include <linux/profile.h>
-#include <linux/utsname.h>
-#include <linux/blkdev.h>
-#include <linux/hugetlb.h>
-#include <linux/jiffies.h>
-#include <linux/vmalloc.h>
-#include <linux/crash_dump.h>
-#include <linux/pid_namespace.h>
-#include <linux/bootmem.h>
-#include <asm/uaccess.h>
-#include <asm/pgtable.h>
-#include <asm/io.h>
-#include <asm/tlb.h>
-#include <asm/div64.h>
-#include "internal.h"
-
-void __init proc_misc_init(void)
-{
-	proc_symlink("mounts", NULL, "self/mounts");
-
-	/* And now for trickier ones */
-}
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 2a3abd25b30b..7761602af9de 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -117,7 +117,7 @@ void __init proc_root_init(void)
 		return;
 	}
 
-	proc_misc_init();
+	proc_symlink("mounts", NULL, "self/mounts");
 
 	proc_net_init();
 
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 9d8308905053..b8bdb96eff78 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -100,7 +100,6 @@ struct vmcore {
 extern spinlock_t proc_subdir_lock;
 
 extern void proc_root_init(void);
-extern void proc_misc_init(void);
 
 void proc_flush_task(struct task_struct *task);
 struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *);
-- 
cgit v1.2.3


From 66f50ee3cee4c9d98eea0add6f439e6e5e0ca4a5 Mon Sep 17 00:00:00 2001
From: Paul Mundt <lethal@linux-sh.org>
Date: Wed, 22 Oct 2008 14:14:59 -0700
Subject: profiling: fix up CONFIG_PROC_FS=n build

In the case where procfs is disabled, create_proc_profile() does not
exist. Stub it in with the others.

Signed-off-by: Paul Mundt <lethal@linux-sh.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/profile.h | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/include/linux/profile.h b/include/linux/profile.h
index 570045053ce9..a0fc32279fc0 100644
--- a/include/linux/profile.h
+++ b/include/linux/profile.h
@@ -19,10 +19,16 @@ struct notifier_block;
 
 #if defined(CONFIG_PROFILING) && defined(CONFIG_PROC_FS)
 void create_prof_cpu_mask(struct proc_dir_entry *de);
+int create_proc_profile(void);
 #else
 static inline void create_prof_cpu_mask(struct proc_dir_entry *de)
 {
 }
+
+static inline int create_proc_profile(void)
+{
+	return 0;
+}
 #endif
 
 enum profile_type {
@@ -37,7 +43,6 @@ extern int prof_on __read_mostly;
 /* init basic kernel profiler */
 int profile_init(void);
 int profile_setup(char *str);
-int create_proc_profile(void);
 void profile_tick(int type);
 
 /*
-- 
cgit v1.2.3


From 4afe978530702c934dfdb11f54073136818b2119 Mon Sep 17 00:00:00 2001
From: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Date: Wed, 22 Oct 2008 14:15:00 -0700
Subject: jbd: fix error handling for checkpoint io

When a checkpointing IO fails, current JBD code doesn't check the error
and continue journaling.  This means latest metadata can be lost from both
the journal and filesystem.

This patch leaves the failed metadata blocks in the journal space and
aborts journaling in the case of log_do_checkpoint().  To achieve this, we
need to do:

1. don't remove the failed buffer from the checkpoint list where in
   the case of __try_to_free_cp_buf() because it may be released or
   overwritten by a later transaction
2. log_do_checkpoint() is the last chance, remove the failed buffer
   from the checkpoint list and abort the journal
3. when checkpointing fails, don't update the journal super block to
   prevent the journaled contents from being cleaned.  For safety,
   don't update j_tail and j_tail_sequence either
4. when checkpointing fails, notify this error to the ext3 layer so
   that ext3 don't clear the needs_recovery flag, otherwise the
   journaled contents are ignored and cleaned in the recovery phase
5. if the recovery fails, keep the needs_recovery flag
6. prevent cleanup_journal_tail() from being called between
   __journal_drop_transaction() and journal_abort() (a race issue
   between journal_flush() and __log_wait_for_space()

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Acked-by: Jan Kara <jack@suse.cz>
Cc: <linux-ext4@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/jbd/checkpoint.c | 49 +++++++++++++++++++++++++++++++++++++------------
 fs/jbd/journal.c    | 28 ++++++++++++++++++++++------
 fs/jbd/recovery.c   |  7 +++++--
 include/linux/jbd.h |  2 +-
 4 files changed, 65 insertions(+), 21 deletions(-)

(limited to 'include')

diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index a5432bbbfb88..e29293501d42 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -93,7 +93,8 @@ static int __try_to_free_cp_buf(struct journal_head *jh)
 	int ret = 0;
 	struct buffer_head *bh = jh2bh(jh);
 
-	if (jh->b_jlist == BJ_None && !buffer_locked(bh) && !buffer_dirty(bh)) {
+	if (jh->b_jlist == BJ_None && !buffer_locked(bh) &&
+	    !buffer_dirty(bh) && buffer_uptodate(bh)) {
 		JBUFFER_TRACE(jh, "remove from checkpoint list");
 		ret = __journal_remove_checkpoint(jh) + 1;
 		jbd_unlock_bh_state(bh);
@@ -160,21 +161,25 @@ static void jbd_sync_bh(journal_t *journal, struct buffer_head *bh)
  * buffers. Note that we take the buffers in the opposite ordering
  * from the one in which they were submitted for IO.
  *
+ * Return 0 on success, and return <0 if some buffers have failed
+ * to be written out.
+ *
  * Called with j_list_lock held.
  */
-static void __wait_cp_io(journal_t *journal, transaction_t *transaction)
+static int __wait_cp_io(journal_t *journal, transaction_t *transaction)
 {
 	struct journal_head *jh;
 	struct buffer_head *bh;
 	tid_t this_tid;
 	int released = 0;
+	int ret = 0;
 
 	this_tid = transaction->t_tid;
 restart:
 	/* Did somebody clean up the transaction in the meanwhile? */
 	if (journal->j_checkpoint_transactions != transaction ||
 			transaction->t_tid != this_tid)
-		return;
+		return ret;
 	while (!released && transaction->t_checkpoint_io_list) {
 		jh = transaction->t_checkpoint_io_list;
 		bh = jh2bh(jh);
@@ -194,6 +199,9 @@ restart:
 			spin_lock(&journal->j_list_lock);
 			goto restart;
 		}
+		if (unlikely(!buffer_uptodate(bh)))
+			ret = -EIO;
+
 		/*
 		 * Now in whatever state the buffer currently is, we know that
 		 * it has been written out and so we can drop it from the list
@@ -203,6 +211,8 @@ restart:
 		journal_remove_journal_head(bh);
 		__brelse(bh);
 	}
+
+	return ret;
 }
 
 #define NR_BATCH	64
@@ -226,7 +236,8 @@ __flush_batch(journal_t *journal, struct buffer_head **bhs, int *batch_count)
  * Try to flush one buffer from the checkpoint list to disk.
  *
  * Return 1 if something happened which requires us to abort the current
- * scan of the checkpoint list.
+ * scan of the checkpoint list.  Return <0 if the buffer has failed to
+ * be written out.
  *
  * Called with j_list_lock held and drops it if 1 is returned
  * Called under jbd_lock_bh_state(jh2bh(jh)), and drops it
@@ -256,6 +267,9 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		log_wait_commit(journal, tid);
 		ret = 1;
 	} else if (!buffer_dirty(bh)) {
+		ret = 1;
+		if (unlikely(!buffer_uptodate(bh)))
+			ret = -EIO;
 		J_ASSERT_JH(jh, !buffer_jbddirty(bh));
 		BUFFER_TRACE(bh, "remove from checkpoint");
 		__journal_remove_checkpoint(jh);
@@ -263,7 +277,6 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
 		jbd_unlock_bh_state(bh);
 		journal_remove_journal_head(bh);
 		__brelse(bh);
-		ret = 1;
 	} else {
 		/*
 		 * Important: we are about to write the buffer, and
@@ -295,6 +308,7 @@ static int __process_buffer(journal_t *journal, struct journal_head *jh,
  * to disk. We submit larger chunks of data at once.
  *
  * The journal should be locked before calling this function.
+ * Called with j_checkpoint_mutex held.
  */
 int log_do_checkpoint(journal_t *journal)
 {
@@ -318,6 +332,7 @@ int log_do_checkpoint(journal_t *journal)
 	 * OK, we need to start writing disk blocks.  Take one transaction
 	 * and write it.
 	 */
+	result = 0;
 	spin_lock(&journal->j_list_lock);
 	if (!journal->j_checkpoint_transactions)
 		goto out;
@@ -334,7 +349,7 @@ restart:
 		int batch_count = 0;
 		struct buffer_head *bhs[NR_BATCH];
 		struct journal_head *jh;
-		int retry = 0;
+		int retry = 0, err;
 
 		while (!retry && transaction->t_checkpoint_list) {
 			struct buffer_head *bh;
@@ -347,6 +362,8 @@ restart:
 				break;
 			}
 			retry = __process_buffer(journal, jh, bhs,&batch_count);
+			if (retry < 0 && !result)
+				result = retry;
 			if (!retry && (need_resched() ||
 				spin_needbreak(&journal->j_list_lock))) {
 				spin_unlock(&journal->j_list_lock);
@@ -371,14 +388,18 @@ restart:
 		 * Now we have cleaned up the first transaction's checkpoint
 		 * list. Let's clean up the second one
 		 */
-		__wait_cp_io(journal, transaction);
+		err = __wait_cp_io(journal, transaction);
+		if (!result)
+			result = err;
 	}
 out:
 	spin_unlock(&journal->j_list_lock);
-	result = cleanup_journal_tail(journal);
 	if (result < 0)
-		return result;
-	return 0;
+		journal_abort(journal, result);
+	else
+		result = cleanup_journal_tail(journal);
+
+	return (result < 0) ? result : 0;
 }
 
 /*
@@ -394,8 +415,9 @@ out:
  * This is the only part of the journaling code which really needs to be
  * aware of transaction aborts.  Checkpointing involves writing to the
  * main filesystem area rather than to the journal, so it can proceed
- * even in abort state, but we must not update the journal superblock if
- * we have an abort error outstanding.
+ * even in abort state, but we must not update the super block if
+ * checkpointing may have failed.  Otherwise, we would lose some metadata
+ * buffers which should be written-back to the filesystem.
  */
 
 int cleanup_journal_tail(journal_t *journal)
@@ -404,6 +426,9 @@ int cleanup_journal_tail(journal_t *journal)
 	tid_t		first_tid;
 	unsigned long	blocknr, freed;
 
+	if (is_journal_aborted(journal))
+		return 1;
+
 	/* OK, work out the oldest transaction remaining in the log, and
 	 * the log block it starts at.
 	 *
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index aa7143a8349b..9e4fa52d7dc8 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -1121,9 +1121,12 @@ recovery_error:
  *
  * Release a journal_t structure once it is no longer in use by the
  * journaled object.
+ * Return <0 if we couldn't clean up the journal.
  */
-void journal_destroy(journal_t *journal)
+int journal_destroy(journal_t *journal)
 {
+	int err = 0;
+
 	/* Wait for the commit thread to wake up and die. */
 	journal_kill_thread(journal);
 
@@ -1146,11 +1149,16 @@ void journal_destroy(journal_t *journal)
 	J_ASSERT(journal->j_checkpoint_transactions == NULL);
 	spin_unlock(&journal->j_list_lock);
 
-	/* We can now mark the journal as empty. */
-	journal->j_tail = 0;
-	journal->j_tail_sequence = ++journal->j_transaction_sequence;
 	if (journal->j_sb_buffer) {
-		journal_update_superblock(journal, 1);
+		if (!is_journal_aborted(journal)) {
+			/* We can now mark the journal as empty. */
+			journal->j_tail = 0;
+			journal->j_tail_sequence =
+				++journal->j_transaction_sequence;
+			journal_update_superblock(journal, 1);
+		} else {
+			err = -EIO;
+		}
 		brelse(journal->j_sb_buffer);
 	}
 
@@ -1160,6 +1168,8 @@ void journal_destroy(journal_t *journal)
 		journal_destroy_revoke(journal);
 	kfree(journal->j_wbuf);
 	kfree(journal);
+
+	return err;
 }
 
 
@@ -1359,10 +1369,16 @@ int journal_flush(journal_t *journal)
 	spin_lock(&journal->j_list_lock);
 	while (!err && journal->j_checkpoint_transactions != NULL) {
 		spin_unlock(&journal->j_list_lock);
+		mutex_lock(&journal->j_checkpoint_mutex);
 		err = log_do_checkpoint(journal);
+		mutex_unlock(&journal->j_checkpoint_mutex);
 		spin_lock(&journal->j_list_lock);
 	}
 	spin_unlock(&journal->j_list_lock);
+
+	if (is_journal_aborted(journal))
+		return -EIO;
+
 	cleanup_journal_tail(journal);
 
 	/* Finally, mark the journal as really needing no recovery.
@@ -1384,7 +1400,7 @@ int journal_flush(journal_t *journal)
 	J_ASSERT(journal->j_head == journal->j_tail);
 	J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence);
 	spin_unlock(&journal->j_state_lock);
-	return err;
+	return 0;
 }
 
 /**
diff --git a/fs/jbd/recovery.c b/fs/jbd/recovery.c
index 43bc5e5ed064..db5e982c5ddf 100644
--- a/fs/jbd/recovery.c
+++ b/fs/jbd/recovery.c
@@ -223,7 +223,7 @@ do {									\
  */
 int journal_recover(journal_t *journal)
 {
-	int			err;
+	int			err, err2;
 	journal_superblock_t *	sb;
 
 	struct recovery_info	info;
@@ -261,7 +261,10 @@ int journal_recover(journal_t *journal)
 	journal->j_transaction_sequence = ++info.end_transaction;
 
 	journal_clear_revoke(journal);
-	sync_blockdev(journal->j_fs_dev);
+	err2 = sync_blockdev(journal->j_fs_dev);
+	if (!err)
+		err = err2;
+
 	return err;
 }
 
diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index 35d4f6342fac..346e2b80be7d 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -911,7 +911,7 @@ extern int	   journal_set_features
 		   (journal_t *, unsigned long, unsigned long, unsigned long);
 extern int	   journal_create     (journal_t *);
 extern int	   journal_load       (journal_t *journal);
-extern void	   journal_destroy    (journal_t *);
+extern int	   journal_destroy    (journal_t *);
 extern int	   journal_recover    (journal_t *journal);
 extern int	   journal_wipe       (journal_t *, int);
 extern int	   journal_skip_recovery	(journal_t *);
-- 
cgit v1.2.3


From 94b6da5ab8293b04a300ba35c72eddfa94db8b02 Mon Sep 17 00:00:00 2001
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Date: Wed, 22 Oct 2008 14:15:05 -0700
Subject: memcg: fix page_cgroup allocation

page_cgroup_init() is called from mem_cgroup_init(). But at this
point, we cannot call alloc_bootmem().
(and this caused panic at boot.)

This patch moves page_cgroup_init() to init/main.c.

Time table is following:
==
  parse_args(). # we can trust mem_cgroup_subsys.disabled bit after this.
  ....
  cgroup_init_early()  # "early" init of cgroup.
  ....
  setup_arch()         # memmap is allocated.
  ...
  page_cgroup_init();
  mem_init();   # we cannot call alloc_bootmem after this.
  ....
  cgroup_init() # mem_cgroup is initialized.
==

Before page_cgroup_init(), mem_map must be initialized. So,
I added page_cgroup_init() to init/main.c directly.

(*) maybe this is not very clean but
    - cgroup_init_early() is too early
    - in cgroup_init(), we have to use vmalloc instead of alloc_bootmem().
    use of vmalloc area in x86-32 is important and we should avoid very large
    vmalloc() in x86-32. So, we want to use alloc_bootmem() and added page_cgroup_init()
    directly to init/main.c

[akpm@linux-foundation.org: remove unneeded/bad mem_cgroup_subsys declaration]
[akpm@linux-foundation.org: fix build]
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/page_cgroup.h |  5 +++++
 init/main.c                 |  2 ++
 mm/memcontrol.c             |  1 -
 mm/page_cgroup.c            | 32 +++++++++++++++++++++++++-------
 4 files changed, 32 insertions(+), 8 deletions(-)

(limited to 'include')

diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 0fd39f2231ec..f546ad6fc028 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -99,5 +99,10 @@ static inline struct page_cgroup *lookup_page_cgroup(struct page *page)
 {
 	return NULL;
 }
+
+static inline void page_cgroup_init(void)
+{
+}
+
 #endif
 #endif
diff --git a/init/main.c b/init/main.c
index 3e17a3bafe60..672ae75b2059 100644
--- a/init/main.c
+++ b/init/main.c
@@ -52,6 +52,7 @@
 #include <linux/key.h>
 #include <linux/unwind.h>
 #include <linux/buffer_head.h>
+#include <linux/page_cgroup.h>
 #include <linux/debug_locks.h>
 #include <linux/debugobjects.h>
 #include <linux/lockdep.h>
@@ -647,6 +648,7 @@ asmlinkage void __init start_kernel(void)
 	vmalloc_init();
 	vfs_caches_init_early();
 	cpuset_init_early();
+	page_cgroup_init();
 	mem_init();
 	enable_debug_pagealloc();
 	cpu_hotplug_init();
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index d4a92b63e98e..866dcc7eeb0c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1088,7 +1088,6 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	int node;
 
 	if (unlikely((cont->parent) == NULL)) {
-		page_cgroup_init();
 		mem = &init_mem_cgroup;
 	} else {
 		mem = mem_cgroup_alloc();
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 78242b4d7edf..f59d797dc5a9 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -4,8 +4,10 @@
 #include <linux/bit_spinlock.h>
 #include <linux/page_cgroup.h>
 #include <linux/hash.h>
+#include <linux/slab.h>
 #include <linux/memory.h>
 #include <linux/vmalloc.h>
+#include <linux/cgroup.h>
 
 static void __meminit
 __init_page_cgroup(struct page_cgroup *pc, unsigned long pfn)
@@ -67,6 +69,9 @@ void __init page_cgroup_init(void)
 
 	int nid, fail;
 
+	if (mem_cgroup_subsys.disabled)
+		return;
+
 	for_each_online_node(nid)  {
 		fail = alloc_node_page_cgroup(nid);
 		if (fail)
@@ -107,9 +112,14 @@ int __meminit init_section_page_cgroup(unsigned long pfn)
 	nid = page_to_nid(pfn_to_page(pfn));
 
 	table_size = sizeof(struct page_cgroup) * PAGES_PER_SECTION;
-	base = kmalloc_node(table_size, GFP_KERNEL, nid);
-	if (!base)
-		base = vmalloc_node(table_size, nid);
+	if (slab_is_available()) {
+		base = kmalloc_node(table_size, GFP_KERNEL, nid);
+		if (!base)
+			base = vmalloc_node(table_size, nid);
+	} else {
+		base = __alloc_bootmem_node_nopanic(NODE_DATA(nid), table_size,
+				PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	}
 
 	if (!base) {
 		printk(KERN_ERR "page cgroup allocation failure\n");
@@ -136,11 +146,16 @@ void __free_page_cgroup(unsigned long pfn)
 	if (!ms || !ms->page_cgroup)
 		return;
 	base = ms->page_cgroup + pfn;
-	ms->page_cgroup = NULL;
-	if (is_vmalloc_addr(base))
+	if (is_vmalloc_addr(base)) {
 		vfree(base);
-	else
-		kfree(base);
+		ms->page_cgroup = NULL;
+	} else {
+		struct page *page = virt_to_page(base);
+		if (!PageReserved(page)) { /* Is bootmem ? */
+			kfree(base);
+			ms->page_cgroup = NULL;
+		}
+	}
 }
 
 int online_page_cgroup(unsigned long start_pfn,
@@ -214,6 +229,9 @@ void __init page_cgroup_init(void)
 	unsigned long pfn;
 	int fail = 0;
 
+	if (mem_cgroup_subsys.disabled)
+		return;
+
 	for (pfn = 0; !fail && pfn < max_pfn; pfn += PAGES_PER_SECTION) {
 		if (!pfn_present(pfn))
 			continue;
-- 
cgit v1.2.3


From a8ddac7e53e89cb877965097d05adfeb1c91def3 Mon Sep 17 00:00:00 2001
From: Nick Piggin <npiggin@suse.de>
Date: Tue, 21 Oct 2008 10:59:15 +0200
Subject: mutex: speed up generic mutex implementations

- atomic operations which both modify the variable and return something imply
  full smp memory barriers before and after the memory operations involved
  (failing atomic_cmpxchg, atomic_add_unless, etc don't imply a barrier because
  they don't modify the target). See Documentation/atomic_ops.txt.
  So remove extra barriers and branches.

- All architectures support atomic_cmpxchg. This has no relation to
  __HAVE_ARCH_CMPXCHG. We can just take the atomic_cmpxchg path unconditionally

This reduces a simple single threaded fastpath lock+unlock test from 590 cycles
to 203 cycles on a ppc970 system.

Signed-off-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/asm-generic/mutex-dec.h  | 26 ++------------------------
 include/asm-generic/mutex-xchg.h |  9 +--------
 2 files changed, 3 insertions(+), 32 deletions(-)

(limited to 'include')

diff --git a/include/asm-generic/mutex-dec.h b/include/asm-generic/mutex-dec.h
index ed108be6743f..f104af7cf437 100644
--- a/include/asm-generic/mutex-dec.h
+++ b/include/asm-generic/mutex-dec.h
@@ -22,8 +22,6 @@ __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
 {
 	if (unlikely(atomic_dec_return(count) < 0))
 		fail_fn(count);
-	else
-		smp_mb();
 }
 
 /**
@@ -41,10 +39,7 @@ __mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
 {
 	if (unlikely(atomic_dec_return(count) < 0))
 		return fail_fn(count);
-	else {
-		smp_mb();
-		return 0;
-	}
+	return 0;
 }
 
 /**
@@ -63,7 +58,6 @@ __mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
 static inline void
 __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
 {
-	smp_mb();
 	if (unlikely(atomic_inc_return(count) <= 0))
 		fail_fn(count);
 }
@@ -88,25 +82,9 @@ __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
 static inline int
 __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
 {
-	/*
-	 * We have two variants here. The cmpxchg based one is the best one
-	 * because it never induce a false contention state.  It is included
-	 * here because architectures using the inc/dec algorithms over the
-	 * xchg ones are much more likely to support cmpxchg natively.
-	 *
-	 * If not we fall back to the spinlock based variant - that is
-	 * just as efficient (and simpler) as a 'destructive' probing of
-	 * the mutex state would be.
-	 */
-#ifdef __HAVE_ARCH_CMPXCHG
-	if (likely(atomic_cmpxchg(count, 1, 0) == 1)) {
-		smp_mb();
+	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
 		return 1;
-	}
 	return 0;
-#else
-	return fail_fn(count);
-#endif
 }
 
 #endif
diff --git a/include/asm-generic/mutex-xchg.h b/include/asm-generic/mutex-xchg.h
index 7b9cd2cbfebe..580a6d35c700 100644
--- a/include/asm-generic/mutex-xchg.h
+++ b/include/asm-generic/mutex-xchg.h
@@ -27,8 +27,6 @@ __mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
 {
 	if (unlikely(atomic_xchg(count, 0) != 1))
 		fail_fn(count);
-	else
-		smp_mb();
 }
 
 /**
@@ -46,10 +44,7 @@ __mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
 {
 	if (unlikely(atomic_xchg(count, 0) != 1))
 		return fail_fn(count);
-	else {
-		smp_mb();
-		return 0;
-	}
+	return 0;
 }
 
 /**
@@ -67,7 +62,6 @@ __mutex_fastpath_lock_retval(atomic_t *count, int (*fail_fn)(atomic_t *))
 static inline void
 __mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
 {
-	smp_mb();
 	if (unlikely(atomic_xchg(count, 1) != 0))
 		fail_fn(count);
 }
@@ -110,7 +104,6 @@ __mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
 		if (prev < 0)
 			prev = 0;
 	}
-	smp_mb();
 
 	return prev;
 }
-- 
cgit v1.2.3


From 7106b4e333baeaf3c596e4d240438059b8a7616d Mon Sep 17 00:00:00 2001
From: Lee Howard <lee.howard@mainpine.com>
Date: Tue, 21 Oct 2008 13:48:58 +0100
Subject: 8250: Oxford Semiconductor Devices

Add support for the OxSemi 'Tornado' devices.

Reformatted and reworked a bit by Alan Cox

Signed-off-by: Lee Howard <lee.howard@mainpine.com>
Signed-off-by: Alan Cox <alan@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/parport/parport_pc.c |  20 +++-
 drivers/serial/8250_pci.c    | 211 +++++++++++++++++++++++++++++++++++++++++++
 include/linux/pci_ids.h      |   8 ++
 3 files changed, 238 insertions(+), 1 deletion(-)

(limited to 'include')

diff --git a/drivers/parport/parport_pc.c b/drivers/parport/parport_pc.c
index 8a846adf1dcf..96f3bdf0ec4b 100644
--- a/drivers/parport/parport_pc.c
+++ b/drivers/parport/parport_pc.c
@@ -2791,6 +2791,7 @@ enum parport_pc_pci_cards {
 	oxsemi_952,
 	oxsemi_954,
 	oxsemi_840,
+	oxsemi_pcie_pport,
 	aks_0100,
 	mobility_pp,
 	netmos_9705,
@@ -2868,6 +2869,7 @@ static struct parport_pc_pci {
 	/* oxsemi_952 */		{ 1, { { 0, 1 }, } },
 	/* oxsemi_954 */		{ 1, { { 0, -1 }, } },
 	/* oxsemi_840 */		{ 1, { { 0, 1 }, } },
+	/* oxsemi_pcie_pport */		{ 1, { { 0, 1 }, } },
 	/* aks_0100 */                  { 1, { { 0, -1 }, } },
 	/* mobility_pp */		{ 1, { { 0, 1 }, } },
 	/* netmos_9705 */               { 1, { { 0, -1 }, } }, /* untested */
@@ -2928,7 +2930,6 @@ static const struct pci_device_id parport_pc_pci_tbl[] = {
 	{ 0x1409, 0x7268, 0x1409, 0x0103, 0, 0, timedia_4008a },
 	{ 0x1409, 0x7268, 0x1409, 0x0104, 0, 0, timedia_4018 },
 	{ 0x1409, 0x7268, 0x1409, 0x9018, 0, 0, timedia_9018a },
-	{ 0x14f2, 0x0121, PCI_ANY_ID, PCI_ANY_ID, 0, 0, mobility_pp },
 	{ PCI_VENDOR_ID_SYBA, PCI_DEVICE_ID_SYBA_2P_EPP,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, syba_2p_epp },
 	{ PCI_VENDOR_ID_SYBA, PCI_DEVICE_ID_SYBA_1P_ECP,
@@ -2946,8 +2947,25 @@ static const struct pci_device_id parport_pc_pci_tbl[] = {
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_954 },
 	{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_12PCI840,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_840 },
+	{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_PCIe840,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
+	{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_PCIe840_G,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
+	{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_PCIe952_0,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
+	{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_PCIe952_0_G,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
+	{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_PCIe952_1,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
+	{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_PCIe952_1_G,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
+	{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_PCIe952_1_U,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
+	{ PCI_VENDOR_ID_OXSEMI, PCI_DEVICE_ID_OXSEMI_PCIe952_1_GU,
+	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, oxsemi_pcie_pport },
 	{ PCI_VENDOR_ID_AKS, PCI_DEVICE_ID_AKS_ALADDINCARD,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, aks_0100 },
+	{ 0x14f2, 0x0121, PCI_ANY_ID, PCI_ANY_ID, 0, 0, mobility_pp },
 	/* NetMos communication controllers */
 	{ PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9705,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9705 },
diff --git a/drivers/serial/8250_pci.c b/drivers/serial/8250_pci.c
index c014ffb110e9..1bdb08b41f73 100644
--- a/drivers/serial/8250_pci.c
+++ b/drivers/serial/8250_pci.c
@@ -1100,6 +1100,8 @@ enum pci_board_num_t {
 	pbn_b0_4_1843200_200,
 	pbn_b0_8_1843200_200,
 
+	pbn_b0_1_4000000,
+
 	pbn_b0_bt_1_115200,
 	pbn_b0_bt_2_115200,
 	pbn_b0_bt_8_115200,
@@ -1167,6 +1169,10 @@ enum pci_board_num_t {
 	pbn_exsys_4055,
 	pbn_plx_romulus,
 	pbn_oxsemi,
+	pbn_oxsemi_1_4000000,
+	pbn_oxsemi_2_4000000,
+	pbn_oxsemi_4_4000000,
+	pbn_oxsemi_8_4000000,
 	pbn_intel_i960,
 	pbn_sgi_ioc3,
 	pbn_computone_4,
@@ -1290,6 +1296,12 @@ static struct pciserial_board pci_boards[] __devinitdata = {
 		.base_baud	= 1843200,
 		.uart_offset	= 0x200,
 	},
+	[pbn_b0_1_4000000] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 1,
+		.base_baud	= 4000000,
+		.uart_offset	= 8,
+	},
 
 	[pbn_b0_bt_1_115200] = {
 		.flags		= FL_BASE0|FL_BASE_BARS,
@@ -1625,6 +1637,35 @@ static struct pciserial_board pci_boards[] __devinitdata = {
 		.base_baud	= 115200,
 		.uart_offset	= 8,
 	},
+	[pbn_oxsemi_1_4000000] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 1,
+		.base_baud	= 4000000,
+		.uart_offset	= 0x200,
+		.first_offset	= 0x1000,
+	},
+	[pbn_oxsemi_2_4000000] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 2,
+		.base_baud	= 4000000,
+		.uart_offset	= 0x200,
+		.first_offset	= 0x1000,
+	},
+	[pbn_oxsemi_4_4000000] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 4,
+		.base_baud	= 4000000,
+		.uart_offset	= 0x200,
+		.first_offset	= 0x1000,
+	},
+	[pbn_oxsemi_8_4000000] = {
+		.flags		= FL_BASE0,
+		.num_ports	= 8,
+		.base_baud	= 4000000,
+		.uart_offset	= 0x200,
+		.first_offset	= 0x1000,
+	},
+
 
 	/*
 	 * EKF addition for i960 Boards form EKF with serial port.
@@ -1813,6 +1854,34 @@ serial_pci_matches(struct pciserial_board *board,
 	    board->first_offset == guessed->first_offset;
 }
 
+/*
+ * Oxford Semiconductor Inc.
+ * Check that device is part of the Tornado range of devices, then determine
+ * the number of ports available on the device.
+ */
+static int pci_oxsemi_tornado_init(struct pci_dev *dev, struct pciserial_board *board)
+{
+	u8 __iomem *p;
+	unsigned long deviceID;
+	unsigned int  number_uarts;
+
+	p = pci_iomap(dev, 0, 5);
+	if (p == NULL)
+		return -ENOMEM;
+
+	deviceID = ioread32(p);
+	/* Tornado device */
+	if (deviceID == 0x07000200) {
+		number_uarts = ioread8(p + 4);
+		board->num_ports = number_uarts;
+		printk(KERN_DEBUG
+			"%d ports detected on Oxford PCI Express device\n",
+								number_uarts);
+	}
+	pci_iounmap(dev, p);
+	return 0;
+}
+
 struct serial_private *
 pciserial_init_ports(struct pci_dev *dev, struct pciserial_board *board)
 {
@@ -1821,6 +1890,12 @@ pciserial_init_ports(struct pci_dev *dev, struct pciserial_board *board)
 	struct pci_serial_quirk *quirk;
 	int rc, nr_ports, i;
 
+	/*
+	 * Find number of ports on board
+	 */
+	if (dev->vendor == PCI_VENDOR_ID_OXSEMI)
+		pci_oxsemi_tornado_init(dev, board);
+
 	nr_ports = board->num_ports;
 
 	/*
@@ -2300,6 +2375,142 @@ static struct pci_device_id serial_pci_tbl[] = {
 		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
 		pbn_b0_bt_2_921600 },
 
+	/*
+	 * Oxford Semiconductor Inc. Tornado PCI express device range.
+	 */
+	{	PCI_VENDOR_ID_OXSEMI, 0xc101,    /* OXPCIe952 1 Legacy UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_b0_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc105,    /* OXPCIe952 1 Legacy UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_b0_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc11b,    /* OXPCIe952 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc11f,    /* OXPCIe952 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc120,    /* OXPCIe952 1 Legacy UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_b0_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc124,    /* OXPCIe952 1 Legacy UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_b0_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc138,    /* OXPCIe952 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc13d,    /* OXPCIe952 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc140,    /* OXPCIe952 1 Legacy UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_b0_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc141,    /* OXPCIe952 1 Legacy UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_b0_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc144,    /* OXPCIe952 1 Legacy UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_b0_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc145,    /* OXPCIe952 1 Legacy UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_b0_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc158,    /* OXPCIe952 2 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_2_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc15d,    /* OXPCIe952 2 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_2_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc208,    /* OXPCIe954 4 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_4_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc20d,    /* OXPCIe954 4 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_4_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc308,    /* OXPCIe958 8 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_8_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc30d,    /* OXPCIe958 8 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_8_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc40b,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc40f,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc41b,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc41f,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc42b,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc42f,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc43b,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc43f,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc44b,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc44f,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc45b,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc45f,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc46b,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc46f,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc47b,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc47f,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc48b,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc48f,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc49b,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc49f,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc4ab,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc4af,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc4bb,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc4bf,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc4cb,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+	{	PCI_VENDOR_ID_OXSEMI, 0xc4cf,    /* OXPCIe200 1 Native UART */
+		PCI_ANY_ID, PCI_ANY_ID, 0, 0,
+		pbn_oxsemi_1_4000000 },
+
 	/*
 	 * SBS Technologies, Inc. P-Octal and PMC-OCTPRO cards,
 	 * from skokodyn@yahoo.com
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index e5d344bfcb7e..369f44286353 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1944,6 +1944,14 @@
 
 #define PCI_VENDOR_ID_OXSEMI		0x1415
 #define PCI_DEVICE_ID_OXSEMI_12PCI840	0x8403
+#define PCI_DEVICE_ID_OXSEMI_PCIe840		0xC000
+#define PCI_DEVICE_ID_OXSEMI_PCIe840_G		0xC004
+#define PCI_DEVICE_ID_OXSEMI_PCIe952_0		0xC100
+#define PCI_DEVICE_ID_OXSEMI_PCIe952_0_G	0xC104
+#define PCI_DEVICE_ID_OXSEMI_PCIe952_1		0xC110
+#define PCI_DEVICE_ID_OXSEMI_PCIe952_1_G	0xC114
+#define PCI_DEVICE_ID_OXSEMI_PCIe952_1_U	0xC118
+#define PCI_DEVICE_ID_OXSEMI_PCIe952_1_GU	0xC11C
 #define PCI_DEVICE_ID_OXSEMI_16PCI954	0x9501
 #define PCI_DEVICE_ID_OXSEMI_16PCI95N	0x9511
 #define PCI_DEVICE_ID_OXSEMI_16PCI954PP	0x9513
-- 
cgit v1.2.3


From 388c8c16abafc2e74dff173b5de9ee519ea8d32f Mon Sep 17 00:00:00 2001
From: James Bottomley <James.Bottomley@HansenPartnership.com>
Date: Sun, 3 Aug 2008 13:02:12 -0500
Subject: PCI: add routines for debugging and handling lost interrupts

We're getting a lot of storage drivers blamed for interrupt misrouting
issues.  This patch provides a standard way of reporting the problem
... and, if possible, correcting it.

Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Jesse Barnes <jbarnes@virtuousgeek.org>
---
 drivers/pci/Makefile |  3 ++-
 drivers/pci/irq.c    | 60 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pci.h  |  7 ++++++
 3 files changed, 69 insertions(+), 1 deletion(-)
 create mode 100644 drivers/pci/irq.c

(limited to 'include')

diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index 4b47f4ece5b7..af3bfe22847b 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -3,7 +3,8 @@
 #
 
 obj-y		+= access.o bus.o probe.o remove.o pci.o quirks.o slot.o \
-			pci-driver.o search.o pci-sysfs.o rom.o setup-res.o
+			pci-driver.o search.o pci-sysfs.o rom.o setup-res.o \
+			irq.o
 obj-$(CONFIG_PROC_FS) += proc.o
 
 # Build PCI Express stuff if needed
diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c
new file mode 100644
index 000000000000..6441dfa969a3
--- /dev/null
+++ b/drivers/pci/irq.c
@@ -0,0 +1,60 @@
+/*
+ * PCI IRQ failure handing code
+ *
+ * Copyright (c) 2008 James Bottomley <James.Bottomley@HansenPartnership.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+
+static void pci_note_irq_problem(struct pci_dev *pdev, const char *reason)
+{
+	struct pci_dev *parent = to_pci_dev(pdev->dev.parent);
+
+	dev_printk(KERN_ERR, &pdev->dev,
+		   "Potentially misrouted IRQ (Bridge %s %04x:%04x)\n",
+		   parent->dev.bus_id, parent->vendor, parent->device);
+	dev_printk(KERN_ERR, &pdev->dev, "%s\n", reason);
+	dev_printk(KERN_ERR, &pdev->dev, "Please report to linux-kernel@vger.kernel.org\n");
+	WARN_ON(1);
+}
+
+/**
+ * pci_lost_interrupt - reports a lost PCI interrupt
+ * @pdev:	device whose interrupt is lost
+ * 
+ * The primary function of this routine is to report a lost interrupt
+ * in a standard way which users can recognise (instead of blaming the
+ * driver).
+ *
+ * Returns:
+ *  a suggestion for fixing it (although the driver is not required to
+ * act on this).
+ */
+enum pci_lost_interrupt_reason pci_lost_interrupt(struct pci_dev *pdev)
+{
+	if (pdev->msi_enabled || pdev->msix_enabled) {
+		enum pci_lost_interrupt_reason ret;
+
+		if (pdev->msix_enabled) {
+			pci_note_irq_problem(pdev, "MSIX routing failure");
+			ret = PCI_LOST_IRQ_DISABLE_MSIX;
+		} else {
+			pci_note_irq_problem(pdev, "MSI routing failure");
+			ret = PCI_LOST_IRQ_DISABLE_MSI;
+		}
+		return ret;
+	}
+#ifdef CONFIG_ACPI
+	if (!(acpi_disabled || acpi_noirq)) {
+		pci_note_irq_problem(pdev, "Potential ACPI misrouting please reboot with acpi=noirq");
+		/* currently no way to fix acpi on the fly */
+		return PCI_LOST_IRQ_DISABLE_ACPI;
+	}
+#endif
+	pci_note_irq_problem(pdev, "unknown cause (not MSI or ACPI)");
+	return PCI_LOST_IRQ_NO_INFORMATION;
+}
+EXPORT_SYMBOL(pci_lost_interrupt);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 752def8a2ef4..c75b82bda327 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -546,6 +546,13 @@ struct pci_dev __deprecated *pci_find_slot(unsigned int bus,
 					   unsigned int devfn);
 #endif /* CONFIG_PCI_LEGACY */
 
+enum pci_lost_interrupt_reason {
+	PCI_LOST_IRQ_NO_INFORMATION = 0,
+	PCI_LOST_IRQ_DISABLE_MSI,
+	PCI_LOST_IRQ_DISABLE_MSIX,
+	PCI_LOST_IRQ_DISABLE_ACPI,
+};
+enum pci_lost_interrupt_reason pci_lost_interrupt(struct pci_dev *dev);
 int pci_find_capability(struct pci_dev *dev, int cap);
 int pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap);
 int pci_find_ext_capability(struct pci_dev *dev, int cap);
-- 
cgit v1.2.3


From 2fca5ccf97d2c28bcfce44f5b07d85e74e3cd18e Mon Sep 17 00:00:00 2001
From: Jens Axboe <jens.axboe@oracle.com>
Date: Wed, 22 Oct 2008 09:34:49 +0200
Subject: libata: switch to using block layer tagging support

libata currently has a pretty dumb ATA_MAX_QUEUE loop for finding
a free tag to use. Instead of fixing that up, convert libata to
using block layer tagging - gets rid of code in libata, and is also
much faster.

Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/ata/libata-core.c | 66 +++++------------------------------------------
 drivers/ata/libata-scsi.c | 10 +++++--
 drivers/ata/libata.h      | 19 ++++++++++++--
 include/linux/libata.h    |  1 -
 4 files changed, 31 insertions(+), 65 deletions(-)

(limited to 'include')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index bbb3cae57492..8cb0b360bfd8 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -1713,8 +1713,6 @@ unsigned ata_exec_internal_sg(struct ata_device *dev,
 	else
 		tag = 0;
 
-	if (test_and_set_bit(tag, &ap->qc_allocated))
-		BUG();
 	qc = __ata_qc_from_tag(ap, tag);
 
 	qc->tag = tag;
@@ -4552,37 +4550,6 @@ void swap_buf_le16(u16 *buf, unsigned int buf_words)
 #endif /* __BIG_ENDIAN */
 }
 
-/**
- *	ata_qc_new - Request an available ATA command, for queueing
- *	@ap: Port associated with device @dev
- *	@dev: Device from whom we request an available command structure
- *
- *	LOCKING:
- *	None.
- */
-
-static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
-{
-	struct ata_queued_cmd *qc = NULL;
-	unsigned int i;
-
-	/* no command while frozen */
-	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
-		return NULL;
-
-	/* the last tag is reserved for internal command. */
-	for (i = 0; i < ATA_MAX_QUEUE - 1; i++)
-		if (!test_and_set_bit(i, &ap->qc_allocated)) {
-			qc = __ata_qc_from_tag(ap, i);
-			break;
-		}
-
-	if (qc)
-		qc->tag = i;
-
-	return qc;
-}
-
 /**
  *	ata_qc_new_init - Request an available ATA command, and initialize it
  *	@dev: Device from whom we request an available command structure
@@ -4591,16 +4558,20 @@ static struct ata_queued_cmd *ata_qc_new(struct ata_port *ap)
  *	None.
  */
 
-struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev)
+struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag)
 {
 	struct ata_port *ap = dev->link->ap;
 	struct ata_queued_cmd *qc;
 
-	qc = ata_qc_new(ap);
+	if (unlikely(ap->pflags & ATA_PFLAG_FROZEN))
+		return NULL;
+
+	qc = __ata_qc_from_tag(ap, tag);
 	if (qc) {
 		qc->scsicmd = NULL;
 		qc->ap = ap;
 		qc->dev = dev;
+		qc->tag = tag;
 
 		ata_qc_reinit(qc);
 	}
@@ -4608,31 +4579,6 @@ struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev)
 	return qc;
 }
 
-/**
- *	ata_qc_free - free unused ata_queued_cmd
- *	@qc: Command to complete
- *
- *	Designed to free unused ata_queued_cmd object
- *	in case something prevents using it.
- *
- *	LOCKING:
- *	spin_lock_irqsave(host lock)
- */
-void ata_qc_free(struct ata_queued_cmd *qc)
-{
-	struct ata_port *ap = qc->ap;
-	unsigned int tag;
-
-	WARN_ON(qc == NULL);	/* ata_qc_from_tag _might_ return NULL */
-
-	qc->flags = 0;
-	tag = qc->tag;
-	if (likely(ata_tag_valid(tag))) {
-		qc->tag = ATA_TAG_POISON;
-		clear_bit(tag, &ap->qc_allocated);
-	}
-}
-
 void __ata_qc_complete(struct ata_queued_cmd *qc)
 {
 	struct ata_port *ap = qc->ap;
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 5d312dc9be9f..d5b9b7266c8b 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -708,7 +708,7 @@ static struct ata_queued_cmd *ata_scsi_qc_new(struct ata_device *dev,
 {
 	struct ata_queued_cmd *qc;
 
-	qc = ata_qc_new_init(dev);
+	qc = ata_qc_new_init(dev, cmd->request->tag);
 	if (qc) {
 		qc->scsicmd = cmd;
 		qc->scsidone = done;
@@ -1103,7 +1103,8 @@ static int ata_scsi_dev_config(struct scsi_device *sdev,
 
 		depth = min(sdev->host->can_queue, ata_id_queue_depth(dev->id));
 		depth = min(ATA_MAX_QUEUE - 1, depth);
-		scsi_adjust_queue_depth(sdev, MSG_SIMPLE_TAG, depth);
+		scsi_set_tag_type(sdev, MSG_SIMPLE_TAG);
+		scsi_activate_tcq(sdev, depth);
 	}
 
 	return 0;
@@ -1943,6 +1944,11 @@ static unsigned int ata_scsiop_inq_std(struct ata_scsi_args *args, u8 *rbuf)
 		hdr[1] |= (1 << 7);
 
 	memcpy(rbuf, hdr, sizeof(hdr));
+
+	/* if ncq, set tags supported */
+	if (ata_id_has_ncq(args->id))
+		rbuf[7] |= (1 << 1);
+
 	memcpy(&rbuf[8], "ATA     ", 8);
 	ata_id_string(args->id, &rbuf[16], ATA_ID_PROD, 16);
 	ata_id_string(args->id, &rbuf[32], ATA_ID_FW_REV, 4);
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index fe2839e58774..d3831d39bdaa 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -74,7 +74,7 @@ extern struct ata_link *ata_dev_phys_link(struct ata_device *dev);
 extern void ata_force_cbl(struct ata_port *ap);
 extern u64 ata_tf_to_lba(const struct ata_taskfile *tf);
 extern u64 ata_tf_to_lba48(const struct ata_taskfile *tf);
-extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev);
+extern struct ata_queued_cmd *ata_qc_new_init(struct ata_device *dev, int tag);
 extern int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev,
 			   u64 block, u32 n_block, unsigned int tf_flags,
 			   unsigned int tag);
@@ -103,7 +103,6 @@ extern int ata_dev_configure(struct ata_device *dev);
 extern int sata_down_spd_limit(struct ata_link *link);
 extern int ata_down_xfermask_limit(struct ata_device *dev, unsigned int sel);
 extern void ata_sg_clean(struct ata_queued_cmd *qc);
-extern void ata_qc_free(struct ata_queued_cmd *qc);
 extern void ata_qc_issue(struct ata_queued_cmd *qc);
 extern void __ata_qc_complete(struct ata_queued_cmd *qc);
 extern int atapi_check_dma(struct ata_queued_cmd *qc);
@@ -119,6 +118,22 @@ extern struct ata_port *ata_port_alloc(struct ata_host *host);
 extern void ata_dev_enable_pm(struct ata_device *dev, enum link_pm policy);
 extern void ata_lpm_schedule(struct ata_port *ap, enum link_pm);
 
+/**
+ *	ata_qc_free - free unused ata_queued_cmd
+ *	@qc: Command to complete
+ *
+ *	Designed to free unused ata_queued_cmd object
+ *	in case something prevents using it.
+ *
+ *	LOCKING:
+ *	spin_lock_irqsave(host lock)
+ */
+static inline void ata_qc_free(struct ata_queued_cmd *qc)
+{
+	qc->flags = 0;
+	qc->tag = ATA_TAG_POISON;
+}
+
 /* libata-acpi.c */
 #ifdef CONFIG_ATA_ACPI
 extern void ata_acpi_associate_sata_port(struct ata_port *ap);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index c261aa0584b1..507f53ef8038 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -695,7 +695,6 @@ struct ata_port {
 	unsigned int		cbl;	/* cable type; ATA_CBL_xxx */
 
 	struct ata_queued_cmd	qcmd[ATA_MAX_QUEUE];
-	unsigned long		qc_allocated;
 	unsigned int		qc_active;
 	int			nr_active_links; /* #links with active qcs */
 
-- 
cgit v1.2.3