Merge branch 'sh/dmaengine' into sh-latest

author: Paul Mundt <lethal@linux-sh.org> 2012-08-01 13:49:13 +0900
committer: Paul Mundt <lethal@linux-sh.org> 2012-08-01 13:49:13 +0900
commit: 91ba548cfd5cc8ee93b9435527efb8fa4caf5c5e (patch)
tree: c96ed92413044a28d17783e84a8824bfd2437af1 /arch
parent: b9ccfda293ee6fca9a89a1584f0900e0627b975e (diff)
parent: 4dc4c51675c137c30838425ecc8d471ff5eb138b (diff)
510 files changed, 16618 insertions, 8244 deletions
diff --git a/arch/Kconfig b/arch/Kconfig
index 8c3d957fa8e2..72f2fa189cc5 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -248,7 +248,14 @@ config HAVE_CMPXCHG_LOCAL
 config HAVE_CMPXCHG_DOUBLE
 	bool
 
+config ARCH_WANT_IPC_PARSE_VERSION
+	bool
+
+config ARCH_WANT_COMPAT_IPC_PARSE_VERSION
+	bool
+
 config ARCH_WANT_OLD_COMPAT_IPC
+	select ARCH_WANT_COMPAT_IPC_PARSE_VERSION
 	bool
 
 config HAVE_ARCH_SECCOMP_FILTER
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 3de74c9f9610..d5b9b5e645cc 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -14,6 +14,7 @@ config ALPHA
 	select AUTO_IRQ_AFFINITY if SMP
 	select GENERIC_IRQ_SHOW
 	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_CMOS_UPDATE
diff --git a/arch/alpha/include/asm/unistd.h b/arch/alpha/include/asm/unistd.h
index d1f23b722df4..633b23b0664a 100644
--- a/arch/alpha/include/asm/unistd.h
+++ b/arch/alpha/include/asm/unistd.h
@@ -470,7 +470,6 @@
 
 #define NR_SYSCALLS			504
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/alpha/kernel/smc37c669.c b/arch/alpha/kernel/smc37c669.c
index 0435921d41c6..c803fc76ae4f 100644
--- a/arch/alpha/kernel/smc37c669.c
+++ b/arch/alpha/kernel/smc37c669.c
@@ -933,18 +933,6 @@ void SMC37c669_display_device_info(
  *
  *--
  */
-#if 0
-/* $INCLUDE_OPTIONS$ */
-#include    "cp$inc:platform_io.h"
-/* $INCLUDE_OPTIONS_END$ */
-#include    "cp$src:common.h"
-#include    "cp$inc:prototypes.h"
-#include    "cp$src:kernel_def.h"
-#include    "cp$src:msg_def.h"
-#include    "cp$src:smcc669_def.h"
-/* Platform-specific includes */
-#include    "cp$src:platform.h"
-#endif
 
 #ifndef TRUE
 #define TRUE 1
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index b25c9d3c379a..7980873525b2 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -11,6 +11,7 @@ config ARM
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
 	select GENERIC_ATOMIC64 if (CPU_V6 || !CPU_32v6K || !AEABI)
+	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL
 	select HAVE_ARCH_KGDB
@@ -38,6 +39,7 @@ config ARM
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_PROBE
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select HARDIRQS_SW_RESEND
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select GENERIC_PCI_IOMAP
@@ -45,6 +47,9 @@ config ARM
 	select GENERIC_SMP_IDLE_THREAD
 	select KTIME_SCALAR
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
+	select DCACHE_WORD_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && !CPU_BIG_ENDIAN
 	help
 	  The ARM series is a line of low-power-consumption RISC chip designs
 	  licensed by ARM Ltd and targeted at embedded applications and
@@ -279,7 +284,6 @@ config ARCH_INTEGRATOR
 	select ICST
 	select GENERIC_CLOCKEVENTS
 	select PLAT_VERSATILE
-	select PLAT_VERSATILE_CLOCK
 	select PLAT_VERSATILE_FPGA_IRQ
 	select NEED_MACH_IO_H
 	select NEED_MACH_MEMORY_H
@@ -336,7 +340,6 @@ config ARCH_VEXPRESS
 	select ICST
 	select NO_IOPORT
 	select PLAT_VERSATILE
-	select PLAT_VERSATILE_CLOCK
 	select PLAT_VERSATILE_CLCD
 	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	help
@@ -1008,7 +1011,6 @@ config ARCH_VT8500
 	select ARCH_HAS_CPUFREQ
 	select GENERIC_CLOCKEVENTS
 	select ARCH_REQUIRE_GPIOLIB
-	select HAVE_PWM
 	help
 	  Support for VIA/WonderMedia VT8500/WM85xx System-on-Chip.
 
@@ -2006,6 +2008,25 @@ config ARM_ATAG_DTB_COMPAT
 	  bootloaders, this option allows zImage to extract the information
 	  from the ATAG list and store it at run time into the appended DTB.
 
+choice
+	prompt "Kernel command line type" if ARM_ATAG_DTB_COMPAT
+	default ARM_ATAG_DTB_COMPAT_CMDLINE_FROM_BOOTLOADER
+
+config ARM_ATAG_DTB_COMPAT_CMDLINE_FROM_BOOTLOADER
+	bool "Use bootloader kernel arguments if available"
+	help
+	  Uses the command-line options passed by the boot loader instead of
+	  the device tree bootargs property. If the boot loader doesn't provide
+	  any, the device tree bootargs property will be used.
+
+config ARM_ATAG_DTB_COMPAT_CMDLINE_EXTEND
+	bool "Extend with bootloader kernel arguments"
+	help
+	  The command-line arguments provided by the boot loader will be
+	  appended to the the device tree bootargs property.
+
+endchoice
+
 config CMDLINE
 	string "Default kernel command string"
 	default ""
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index a03b5a7059e2..f15f82bf3a50 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -395,4 +395,13 @@ config ARM_KPROBES_TEST
 	help
 	  Perform tests of kprobes API and instruction set simulation.
 
+config PID_IN_CONTEXTIDR
+	bool "Write the current PID to the CONTEXTIDR register"
+	depends on CPU_COPY_V6
+	help
+	  Enabling this option causes the kernel to write the current PID to
+	  the PROCID field of the CONTEXTIDR register, at the expense of some
+	  additional instructions during context switch. Say Y here only if you
+	  are planning to use hardware trace tools with this kernel.
+
 endmenu
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 4d6d31115cf2..30eae87ead6d 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -10,6 +10,9 @@
 #
 # Copyright (C) 1995-2001 by Russell King
 
+# Ensure linker flags are correct
+LDFLAGS		:=
+
 LDFLAGS_vmlinux	:=-p --no-undefined -X
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux	+= --be8
diff --git a/arch/arm/boot/compressed/atags_to_fdt.c b/arch/arm/boot/compressed/atags_to_fdt.c
index 797f04bedb47..aabc02a68482 100644
--- a/arch/arm/boot/compressed/atags_to_fdt.c
+++ b/arch/arm/boot/compressed/atags_to_fdt.c
@@ -1,6 +1,12 @@
 #include <asm/setup.h>
 #include <libfdt.h>
 
+#if defined(CONFIG_ARM_ATAG_DTB_COMPAT_CMDLINE_EXTEND)
+#define do_extend_cmdline 1
+#else
+#define do_extend_cmdline 0
+#endif
+
 static int node_offset(void *fdt, const char *node_path)
 {
 	int offset = fdt_path_offset(fdt, node_path);
@@ -36,6 +42,48 @@ static int setprop_cell(void *fdt, const char *node_path,
 	return fdt_setprop_cell(fdt, offset, property, val);
 }
 
+static const void *getprop(const void *fdt, const char *node_path,
+			   const char *property, int *len)
+{
+	int offset = fdt_path_offset(fdt, node_path);
+
+	if (offset == -FDT_ERR_NOTFOUND)
+		return NULL;
+
+	return fdt_getprop(fdt, offset, property, len);
+}
+
+static void merge_fdt_bootargs(void *fdt, const char *fdt_cmdline)
+{
+	char cmdline[COMMAND_LINE_SIZE];
+	const char *fdt_bootargs;
+	char *ptr = cmdline;
+	int len = 0;
+
+	/* copy the fdt command line into the buffer */
+	fdt_bootargs = getprop(fdt, "/chosen", "bootargs", &len);
+	if (fdt_bootargs)
+		if (len < COMMAND_LINE_SIZE) {
+			memcpy(ptr, fdt_bootargs, len);
+			/* len is the length of the string
+			 * including the NULL terminator */
+			ptr += len - 1;
+		}
+
+	/* and append the ATAG_CMDLINE */
+	if (fdt_cmdline) {
+		len = strlen(fdt_cmdline);
+		if (ptr - cmdline + len + 2 < COMMAND_LINE_SIZE) {
+			*ptr++ = ' ';
+			memcpy(ptr, fdt_cmdline, len);
+			ptr += len;
+		}
+	}
+	*ptr = '\0';
+
+	setprop_string(fdt, "/chosen", "bootargs", cmdline);
+}
+
 /*
  * Convert and fold provided ATAGs into the provided FDT.
  *
@@ -72,8 +120,18 @@ int atags_to_fdt(void *atag_list, void *fdt, int total_space)
 
 	for_each_tag(atag, atag_list) {
 		if (atag->hdr.tag == ATAG_CMDLINE) {
-			setprop_string(fdt, "/chosen", "bootargs",
-					atag->u.cmdline.cmdline);
+			/* Append the ATAGS command line to the device tree
+			 * command line.
+			 * NB: This means that if the same parameter is set in
+			 * the device tree and in the tags, the one from the
+			 * tags will be chosen.
+			 */
+			if (do_extend_cmdline)
+				merge_fdt_bootargs(fdt,
+						   atag->u.cmdline.cmdline);
+			else
+				setprop_string(fdt, "/chosen", "bootargs",
+					       atag->u.cmdline.cmdline);
 		} else if (atag->hdr.tag == ATAG_MEM) {
 			if (memcount >= sizeof(mem_reg_property)/4)
 				continue;
diff --git a/arch/arm/boot/dts/highbank.dts b/arch/arm/boot/dts/highbank.dts
index 2e1cfa00c25b..9fecf1ae777b 100644
--- a/arch/arm/boot/dts/highbank.dts
+++ b/arch/arm/boot/dts/highbank.dts
@@ -130,6 +130,12 @@
 			clocks = <&eclk>;
 		};
 
+		memory-controller@fff00000 {
+			compatible = "calxeda,hb-ddr-ctrl";
+			reg = <0xfff00000 0x1000>;
+			interrupts = <0 91 4>;
+		};
+
 		ipc@fff20000 {
 			compatible = "arm,pl320", "arm,primecell";
 			reg = <0xfff20000 0x1000>;
@@ -275,6 +281,12 @@
 			};
 		};
 
+		sregs@fff3c200 {
+			compatible = "calxeda,hb-sregs-l2-ecc";
+			reg = <0xfff3c200 0x100>;
+			interrupts = <0 71 4  0 72 4>;
+		};
+
 		dma@fff3d000 {
 			compatible = "arm,pl330", "arm,primecell";
 			reg = <0xfff3d000 0x1000>;
diff --git a/arch/arm/boot/dts/imx28.dtsi b/arch/arm/boot/dts/imx28.dtsi
index 915db89e3644..787efac68da8 100644
--- a/arch/arm/boot/dts/imx28.dtsi
+++ b/arch/arm/boot/dts/imx28.dtsi
@@ -660,6 +660,7 @@
 				compatible = "fsl,imx28-i2c";
 				reg = <0x80058000 2000>;
 				interrupts = <111 68>;
+				clock-frequency = <100000>;
 				status = "disabled";
 			};
 
@@ -669,6 +670,7 @@
 				compatible = "fsl,imx28-i2c";
 				reg = <0x8005a000 2000>;
 				interrupts = <110 69>;
+				clock-frequency = <100000>;
 				status = "disabled";
 			};
 
diff --git a/arch/arm/boot/dts/imx51.dtsi b/arch/arm/boot/dts/imx51.dtsi
index 922adefdd291..53cbaa3d4f90 100644
--- a/arch/arm/boot/dts/imx51.dtsi
+++ b/arch/arm/boot/dts/imx51.dtsi
@@ -127,7 +127,7 @@
 			};
 
 			gpio1: gpio@73f84000 {
-				compatible = "fsl,imx51-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx51-gpio", "fsl,imx35-gpio";
 				reg = <0x73f84000 0x4000>;
 				interrupts = <50 51>;
 				gpio-controller;
@@ -137,7 +137,7 @@
 			};
 
 			gpio2: gpio@73f88000 {
-				compatible = "fsl,imx51-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx51-gpio", "fsl,imx35-gpio";
 				reg = <0x73f88000 0x4000>;
 				interrupts = <52 53>;
 				gpio-controller;
@@ -147,7 +147,7 @@
 			};
 
 			gpio3: gpio@73f8c000 {
-				compatible = "fsl,imx51-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx51-gpio", "fsl,imx35-gpio";
 				reg = <0x73f8c000 0x4000>;
 				interrupts = <54 55>;
 				gpio-controller;
@@ -157,7 +157,7 @@
 			};
 
 			gpio4: gpio@73f90000 {
-				compatible = "fsl,imx51-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx51-gpio", "fsl,imx35-gpio";
 				reg = <0x73f90000 0x4000>;
 				interrupts = <56 57>;
 				gpio-controller;
diff --git a/arch/arm/boot/dts/imx53.dtsi b/arch/arm/boot/dts/imx53.dtsi
index 4e735edc78ed..fc79cdc4b4e6 100644
--- a/arch/arm/boot/dts/imx53.dtsi
+++ b/arch/arm/boot/dts/imx53.dtsi
@@ -129,7 +129,7 @@
 			};
 
 			gpio1: gpio@53f84000 {
-				compatible = "fsl,imx53-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx53-gpio", "fsl,imx35-gpio";
 				reg = <0x53f84000 0x4000>;
 				interrupts = <50 51>;
 				gpio-controller;
@@ -139,7 +139,7 @@
 			};
 
 			gpio2: gpio@53f88000 {
-				compatible = "fsl,imx53-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx53-gpio", "fsl,imx35-gpio";
 				reg = <0x53f88000 0x4000>;
 				interrupts = <52 53>;
 				gpio-controller;
@@ -149,7 +149,7 @@
 			};
 
 			gpio3: gpio@53f8c000 {
-				compatible = "fsl,imx53-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx53-gpio", "fsl,imx35-gpio";
 				reg = <0x53f8c000 0x4000>;
 				interrupts = <54 55>;
 				gpio-controller;
@@ -159,7 +159,7 @@
 			};
 
 			gpio4: gpio@53f90000 {
-				compatible = "fsl,imx53-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx53-gpio", "fsl,imx35-gpio";
 				reg = <0x53f90000 0x4000>;
 				interrupts = <56 57>;
 				gpio-controller;
@@ -197,7 +197,7 @@
 			};
 
 			gpio5: gpio@53fdc000 {
-				compatible = "fsl,imx53-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx53-gpio", "fsl,imx35-gpio";
 				reg = <0x53fdc000 0x4000>;
 				interrupts = <103 104>;
 				gpio-controller;
@@ -207,7 +207,7 @@
 			};
 
 			gpio6: gpio@53fe0000 {
-				compatible = "fsl,imx53-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx53-gpio", "fsl,imx35-gpio";
 				reg = <0x53fe0000 0x4000>;
 				interrupts = <105 106>;
 				gpio-controller;
@@ -217,7 +217,7 @@
 			};
 
 			gpio7: gpio@53fe4000 {
-				compatible = "fsl,imx53-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx53-gpio", "fsl,imx35-gpio";
 				reg = <0x53fe4000 0x4000>;
 				interrupts = <107 108>;
 				gpio-controller;
diff --git a/arch/arm/boot/dts/imx6q.dtsi b/arch/arm/boot/dts/imx6q.dtsi
index c25d49584814..3d3c64b014e6 100644
--- a/arch/arm/boot/dts/imx6q.dtsi
+++ b/arch/arm/boot/dts/imx6q.dtsi
@@ -277,7 +277,7 @@
 			};
 
 			gpio1: gpio@0209c000 {
-				compatible = "fsl,imx6q-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx6q-gpio", "fsl,imx35-gpio";
 				reg = <0x0209c000 0x4000>;
 				interrupts = <0 66 0x04 0 67 0x04>;
 				gpio-controller;
@@ -287,7 +287,7 @@
 			};
 
 			gpio2: gpio@020a0000 {
-				compatible = "fsl,imx6q-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx6q-gpio", "fsl,imx35-gpio";
 				reg = <0x020a0000 0x4000>;
 				interrupts = <0 68 0x04 0 69 0x04>;
 				gpio-controller;
@@ -297,7 +297,7 @@
 			};
 
 			gpio3: gpio@020a4000 {
-				compatible = "fsl,imx6q-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx6q-gpio", "fsl,imx35-gpio";
 				reg = <0x020a4000 0x4000>;
 				interrupts = <0 70 0x04 0 71 0x04>;
 				gpio-controller;
@@ -307,7 +307,7 @@
 			};
 
 			gpio4: gpio@020a8000 {
-				compatible = "fsl,imx6q-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx6q-gpio", "fsl,imx35-gpio";
 				reg = <0x020a8000 0x4000>;
 				interrupts = <0 72 0x04 0 73 0x04>;
 				gpio-controller;
@@ -317,7 +317,7 @@
 			};
 
 			gpio5: gpio@020ac000 {
-				compatible = "fsl,imx6q-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx6q-gpio", "fsl,imx35-gpio";
 				reg = <0x020ac000 0x4000>;
 				interrupts = <0 74 0x04 0 75 0x04>;
 				gpio-controller;
@@ -327,7 +327,7 @@
 			};
 
 			gpio6: gpio@020b0000 {
-				compatible = "fsl,imx6q-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx6q-gpio", "fsl,imx35-gpio";
 				reg = <0x020b0000 0x4000>;
 				interrupts = <0 76 0x04 0 77 0x04>;
 				gpio-controller;
@@ -337,7 +337,7 @@
 			};
 
 			gpio7: gpio@020b4000 {
-				compatible = "fsl,imx6q-gpio", "fsl,imx31-gpio";
+				compatible = "fsl,imx6q-gpio", "fsl,imx35-gpio";
 				reg = <0x020b4000 0x4000>;
 				interrupts = <0 78 0x04 0 79 0x04>;
 				gpio-controller;
diff --git a/arch/arm/boot/dts/kirkwood-dns320.dts b/arch/arm/boot/dts/kirkwood-dns320.dts
index dc09a735b04a..9a33077130e8 100644
--- a/arch/arm/boot/dts/kirkwood-dns320.dts
+++ b/arch/arm/boot/dts/kirkwood-dns320.dts
@@ -4,7 +4,7 @@
 
 / {
 	model = "D-Link DNS-320 NAS (Rev A1)";
-	compatible = "dlink,dns-320-a1", "dlink,dns-320", "dlink,dns-kirkwood", "mrvl,kirkwood-88f6281", "mrvl,kirkwood";
+	compatible = "dlink,dns-320-a1", "dlink,dns-320", "dlink,dns-kirkwood", "marvell,kirkwood-88f6281", "marvell,kirkwood";
 
 	memory {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/kirkwood-dns325.dts b/arch/arm/boot/dts/kirkwood-dns325.dts
index c2a5562525d2..16734c1b5dfe 100644
--- a/arch/arm/boot/dts/kirkwood-dns325.dts
+++ b/arch/arm/boot/dts/kirkwood-dns325.dts
@@ -4,7 +4,7 @@
 
 / {
 	model = "D-Link DNS-325 NAS (Rev A1)";
-	compatible = "dlink,dns-325-a1", "dlink,dns-325", "dlink,dns-kirkwood", "mrvl,kirkwood-88f6281", "mrvl,kirkwood";
+	compatible = "dlink,dns-325-a1", "dlink,dns-325", "dlink,dns-kirkwood", "marvell,kirkwood-88f6281", "marvell,kirkwood";
 
 	memory {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/kirkwood-dreamplug.dts b/arch/arm/boot/dts/kirkwood-dreamplug.dts
index a5376b84227f..78b0f06a09a2 100644
--- a/arch/arm/boot/dts/kirkwood-dreamplug.dts
+++ b/arch/arm/boot/dts/kirkwood-dreamplug.dts
@@ -4,7 +4,7 @@
 
 / {
 	model = "Globalscale Technologies Dreamplug";
-	compatible = "globalscale,dreamplug-003-ds2001", "globalscale,dreamplug", "mrvl,kirkwood-88f6281", "mrvl,kirkwood";
+	compatible = "globalscale,dreamplug-003-ds2001", "globalscale,dreamplug", "marvell,kirkwood-88f6281", "marvell,kirkwood";
 
 	memory {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/kirkwood-ib62x0.dts b/arch/arm/boot/dts/kirkwood-ib62x0.dts
index ada0f0c23085..f59dcf6dc45f 100644
--- a/arch/arm/boot/dts/kirkwood-ib62x0.dts
+++ b/arch/arm/boot/dts/kirkwood-ib62x0.dts
@@ -4,7 +4,7 @@
 
 / {
 	model = "RaidSonic ICY BOX IB-NAS62x0 (Rev B)";
-	compatible = "raidsonic,ib-nas6210-b", "raidsonic,ib-nas6220-b", "raidsonic,ib-nas6210", "raidsonic,ib-nas6220", "raidsonic,ib-nas62x0",  "mrvl,kirkwood-88f6281", "mrvl,kirkwood";
+	compatible = "raidsonic,ib-nas6210-b", "raidsonic,ib-nas6220-b", "raidsonic,ib-nas6210", "raidsonic,ib-nas6220", "raidsonic,ib-nas62x0",  "marvell,kirkwood-88f6281", "marvell,kirkwood";
 
 	memory {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/kirkwood-iconnect.dts b/arch/arm/boot/dts/kirkwood-iconnect.dts
index 1ba75d4adecc..026a1f82d813 100644
--- a/arch/arm/boot/dts/kirkwood-iconnect.dts
+++ b/arch/arm/boot/dts/kirkwood-iconnect.dts
@@ -4,7 +4,7 @@
 
 / {
 	model = "Iomega Iconnect";
-	compatible = "iom,iconnect-1.1", "iom,iconnect", "mrvl,kirkwood-88f6281", "mrvl,kirkwood";
+	compatible = "iom,iconnect-1.1", "iom,iconnect", "marvell,kirkwood-88f6281", "marvell,kirkwood";
 
 	memory {
 		device_type = "memory";
diff --git a/arch/arm/boot/dts/kirkwood.dtsi b/arch/arm/boot/dts/kirkwood.dtsi
index 926528b81baa..f95dbc190ab6 100644
--- a/arch/arm/boot/dts/kirkwood.dtsi
+++ b/arch/arm/boot/dts/kirkwood.dtsi
@@ -1,7 +1,7 @@
 /include/ "skeleton.dtsi"
 
 / {
-	compatible = "mrvl,kirkwood";
+	compatible = "marvell,kirkwood";
 
 	ocp@f1000000 {
 		compatible = "simple-bus";
@@ -28,7 +28,7 @@
 		};
 
 		rtc@10300 {
-			compatible = "mrvl,kirkwood-rtc", "mrvl,orion-rtc";
+			compatible = "marvell,kirkwood-rtc", "marvell,orion-rtc";
 			reg = <0x10300 0x20>;
 			interrupts = <53>;
 		};
@@ -39,7 +39,7 @@
 			cle = <0>;
 			ale = <1>;
 			bank-width = <1>;
-			compatible = "mrvl,orion-nand";
+			compatible = "marvell,orion-nand";
 			reg = <0x3000000 0x400>;
 			chip-delay = <25>;
 			/* set partition map and/or chip-delay in board dts */
diff --git a/arch/arm/boot/dts/r8a7740.dtsi b/arch/arm/boot/dts/r8a7740.dtsi
new file mode 100644
index 000000000000..798fa35c0005
--- /dev/null
+++ b/arch/arm/boot/dts/r8a7740.dtsi
@@ -0,0 +1,21 @@
+/*
+ * Device Tree Source for the r8a7740 SoC
+ *
+ * Copyright (C) 2012 Renesas Solutions Corp.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "renesas,r8a7740";
+
+	cpus {
+		cpu@0 {
+			compatible = "arm,cortex-a9";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/sh7377.dtsi b/arch/arm/boot/dts/sh7377.dtsi
new file mode 100644
index 000000000000..767ee0796daa
--- /dev/null
+++ b/arch/arm/boot/dts/sh7377.dtsi
@@ -0,0 +1,21 @@
+/*
+ * Device Tree Source for the sh7377 SoC
+ *
+ * Copyright (C) 2012 Renesas Solutions Corp.
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ */
+
+/include/ "skeleton.dtsi"
+
+/ {
+	compatible = "renesas,sh7377";
+
+	cpus {
+		cpu@0 {
+			compatible = "arm,cortex-a8";
+		};
+	};
+};
diff --git a/arch/arm/boot/dts/tegra20-trimslice.dts b/arch/arm/boot/dts/tegra20-trimslice.dts
index 9de5636023f6..27fb8a67ea42 100644
--- a/arch/arm/boot/dts/tegra20-trimslice.dts
+++ b/arch/arm/boot/dts/tegra20-trimslice.dts
@@ -276,9 +276,11 @@
 
 	usb@c5000000 {
 		status = "okay";
+		nvidia,vbus-gpio = <&gpio 170 0>; /* gpio PV2 */
 	};
 
 	usb@c5004000 {
+		status = "okay";
 		nvidia,phy-reset-gpio = <&gpio 168 0>; /* gpio PV0 */
 	};
 
diff --git a/arch/arm/boot/dts/tegra20.dtsi b/arch/arm/boot/dts/tegra20.dtsi
index 9f1921634eb7..405d1673904e 100644
--- a/arch/arm/boot/dts/tegra20.dtsi
+++ b/arch/arm/boot/dts/tegra20.dtsi
@@ -123,6 +123,12 @@
 		status = "disabled";
 	};
 
+	pwm {
+		compatible = "nvidia,tegra20-pwm";
+		reg = <0x7000a000 0x100>;
+		#pwm-cells = <2>;
+	};
+
 	i2c@7000c000 {
 		compatible = "nvidia,tegra20-i2c";
 		reg = <0x7000c000 0x100>;
diff --git a/arch/arm/boot/dts/tegra30.dtsi b/arch/arm/boot/dts/tegra30.dtsi
index da740191771f..3e4334d14efb 100644
--- a/arch/arm/boot/dts/tegra30.dtsi
+++ b/arch/arm/boot/dts/tegra30.dtsi
@@ -117,6 +117,12 @@
 		status = "disabled";
 	};
 
+	pwm {
+		compatible = "nvidia,tegra30-pwm", "nvidia,tegra20-pwm";
+		reg = <0x7000a000 0x100>;
+		#pwm-cells = <2>;
+	};
+
 	i2c@7000c000 {
 		compatible =  "nvidia,tegra30-i2c", "nvidia,tegra20-i2c";
 		reg = <0x7000c000 0x100>;
diff --git a/arch/arm/common/dmabounce.c b/arch/arm/common/dmabounce.c
index aa07f5938f05..1143c4d5c567 100644
--- a/arch/arm/common/dmabounce.c
+++ b/arch/arm/common/dmabounce.c
@@ -452,6 +452,7 @@ static struct dma_map_ops dmabounce_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
 	.mmap			= arm_dma_mmap,
+	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= dmabounce_map_page,
 	.unmap_page		= dmabounce_unmap_page,
 	.sync_single_for_cpu	= dmabounce_sync_for_cpu,
diff --git a/arch/arm/configs/armadillo800eva_defconfig b/arch/arm/configs/armadillo800eva_defconfig
index ddc9fe6a78ac..7d8718468e0d 100644
--- a/arch/arm/configs/armadillo800eva_defconfig
+++ b/arch/arm/configs/armadillo800eva_defconfig
@@ -5,10 +5,7 @@ CONFIG_IKCONFIG_PROC=y
 CONFIG_LOG_BUF_SHIFT=16
 # CONFIG_UTS_NS is not set
 # CONFIG_IPC_NS is not set
-# CONFIG_USER_NS is not set
 # CONFIG_PID_NS is not set
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_CC_OPTIMIZE_FOR_SIZE=y
 CONFIG_SLAB=y
 CONFIG_MODULES=y
@@ -21,7 +18,7 @@ CONFIG_ARCH_SHMOBILE=y
 CONFIG_ARCH_R8A7740=y
 CONFIG_MACH_ARMADILLO800EVA=y
 # CONFIG_SH_TIMER_TMU is not set
-# CONFIG_ARM_THUMB is not set
+CONFIG_ARM_THUMB=y
 CONFIG_CPU_BPREDICT_DISABLE=y
 # CONFIG_CACHE_L2X0 is not set
 CONFIG_ARM_ERRATA_430973=y
@@ -39,6 +36,7 @@ CONFIG_ZBOOT_ROM_BSS=0x0
 CONFIG_CMDLINE="console=tty0 console=ttySC1,115200 earlyprintk=sh-sci.1,115200 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096"
 CONFIG_CMDLINE_FORCE=y
 CONFIG_KEXEC=y
+CONFIG_VFP=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_SUSPEND is not set
 CONFIG_NET=y
@@ -89,26 +87,32 @@ CONFIG_SERIAL_SH_SCI_CONSOLE=y
 CONFIG_I2C=y
 CONFIG_I2C_SH_MOBILE=y
 # CONFIG_HWMON is not set
+CONFIG_MEDIA_SUPPORT=y
+CONFIG_VIDEO_DEV=y
+# CONFIG_RC_CORE is not set
+# CONFIG_VIDEO_HELPER_CHIPS_AUTO is not set
+# CONFIG_V4L_USB_DRIVERS is not set
+CONFIG_V4L_PLATFORM_DRIVERS=y
+CONFIG_SOC_CAMERA=y
+CONFIG_SOC_CAMERA_MT9T112=y
+CONFIG_VIDEO_SH_MOBILE_CEU=y
+# CONFIG_RADIO_ADAPTERS is not set
 CONFIG_FB=y
-CONFIG_FB_MODE_HELPERS=y
 CONFIG_FB_SH_MOBILE_LCDC=y
+CONFIG_FB_SH_MOBILE_HDMI=y
 CONFIG_LCD_CLASS_DEVICE=y
 CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_LOGO=y
 # CONFIG_LOGO_LINUX_MONO is not set
 # CONFIG_LOGO_LINUX_VGA16 is not set
-CONFIG_SOUND=y
-CONFIG_SND=y
 # CONFIG_SND_SUPPORT_OLD_API is not set
 # CONFIG_SND_VERBOSE_PROCFS is not set
 # CONFIG_SND_DRIVERS is not set
 # CONFIG_SND_ARM is not set
-CONFIG_SND_SOC=y
 CONFIG_SND_SOC_SH4_FSI=y
 # CONFIG_HID_SUPPORT is not set
 CONFIG_USB=y
-# CONFIG_USB_DEVICE_CLASS is not set
 CONFIG_USB_RENESAS_USBHS=y
 CONFIG_USB_GADGET=y
 CONFIG_USB_RENESAS_USBHS_UDC=y
@@ -116,6 +120,8 @@ CONFIG_USB_ETH=m
 CONFIG_MMC=y
 CONFIG_MMC_SDHI=y
 CONFIG_MMC_SH_MMCIF=y
+CONFIG_DMADEVICES=y
+CONFIG_SH_DMAE=y
 CONFIG_UIO=y
 CONFIG_UIO_PDRV_GENIRQ=y
 # CONFIG_DNOTIFY is not set
@@ -124,7 +130,6 @@ CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
 CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_NFS_V4_1=y
diff --git a/arch/arm/configs/kzm9d_defconfig b/arch/arm/configs/kzm9d_defconfig
new file mode 100644
index 000000000000..26146ffea1a5
--- /dev/null
+++ b/arch/arm/configs/kzm9d_defconfig
@@ -0,0 +1,89 @@
+# CONFIG_ARM_PATCH_PHYS_VIRT is not set
+CONFIG_EXPERIMENTAL=y
+CONFIG_SYSVIPC=y
+CONFIG_NO_HZ=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_EMBEDDED=y
+CONFIG_SLAB=y
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+# CONFIG_IOSCHED_CFQ is not set
+CONFIG_ARCH_SHMOBILE=y
+CONFIG_ARCH_EMEV2=y
+CONFIG_MACH_KZM9D=y
+CONFIG_MEMORY_START=0x40000000
+CONFIG_MEMORY_SIZE=0x10000000
+# CONFIG_SH_TIMER_TMU is not set
+# CONFIG_SWP_EMULATE is not set
+# CONFIG_CACHE_L2X0 is not set
+CONFIG_SMP=y
+CONFIG_NR_CPUS=2
+CONFIG_HOTPLUG_CPU=y
+# CONFIG_LOCAL_TIMERS is not set
+CONFIG_AEABI=y
+# CONFIG_OABI_COMPAT is not set
+# CONFIG_CROSS_MEMORY_ATTACH is not set
+CONFIG_FORCE_MAX_ZONEORDER=13
+CONFIG_ZBOOT_ROM_TEXT=0x0
+CONFIG_ZBOOT_ROM_BSS=0x0
+CONFIG_ARM_APPENDED_DTB=y
+CONFIG_CMDLINE="console=tty0 console=ttyS1,115200n81 earlyprintk=serial8250-em.1,115200n81 mem=128M@0x40000000 ignore_loglevel root=/dev/nfs ip=dhcp nfsroot=,rsize=4096,wsize=4096"
+CONFIG_CMDLINE_FORCE=y
+CONFIG_VFP=y
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_SUSPEND is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+# CONFIG_BLK_DEV is not set
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_CHELSIO is not set
+# CONFIG_NET_VENDOR_CIRRUS is not set
+# CONFIG_NET_VENDOR_FARADAY is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+CONFIG_SMSC911X=y
+# CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_WLAN is not set
+# CONFIG_INPUT_MOUSEDEV is not set
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_EM=y
+# CONFIG_HW_RANDOM is not set
+CONFIG_GPIOLIB=y
+CONFIG_GPIO_EM=y
+# CONFIG_HWMON is not set
+# CONFIG_HID_SUPPORT is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_IOMMU_SUPPORT is not set
+# CONFIG_DNOTIFY is not set
+CONFIG_TMPFS=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+CONFIG_ROOT_NFS=y
+# CONFIG_FTRACE is not set
diff --git a/arch/arm/configs/kzm9g_defconfig b/arch/arm/configs/kzm9g_defconfig
index e3ebc20ed0a7..2388c8610627 100644
--- a/arch/arm/configs/kzm9g_defconfig
+++ b/arch/arm/configs/kzm9g_defconfig
@@ -100,7 +100,12 @@ CONFIG_SND_SOC_SH4_FSI=y
 CONFIG_USB=y
 CONFIG_USB_DEVICEFS=y
 CONFIG_USB_R8A66597_HCD=y
+CONFIG_USB_RENESAS_USBHS=y
 CONFIG_USB_STORAGE=y
+CONFIG_USB_GADGET=y
+CONFIG_USB_RENESAS_USBHS_UDC=y
+CONFIG_USB_ETH=m
+CONFIG_USB_MASS_STORAGE=m
 CONFIG_MMC=y
 # CONFIG_MMC_BLOCK_BOUNCE is not set
 CONFIG_MMC_SDHI=y
@@ -108,12 +113,13 @@ CONFIG_MMC_SH_MMCIF=y
 CONFIG_NEW_LEDS=y
 CONFIG_LEDS_CLASS=y
 CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_RS5C372=y
 CONFIG_DMADEVICES=y
 CONFIG_SH_DMAE=y
 CONFIG_ASYNC_TX_DMA=y
 CONFIG_STAGING=y
 # CONFIG_DNOTIFY is not set
-# CONFIG_INOTIFY_USER is not set
+CONFIG_INOTIFY_USER=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
 # CONFIG_MISC_FILESYSTEMS is not set
diff --git a/arch/arm/configs/tegra_defconfig b/arch/arm/configs/tegra_defconfig
index 4be9c1e80ee6..db2245353f0f 100644
--- a/arch/arm/configs/tegra_defconfig
+++ b/arch/arm/configs/tegra_defconfig
@@ -106,6 +106,7 @@ CONFIG_I2C_TEGRA=y
 CONFIG_SPI=y
 CONFIG_SPI_TEGRA=y
 CONFIG_GPIO_TPS65910=y
+CONFIG_GPIO_TPS6586X=y
 CONFIG_POWER_SUPPLY=y
 CONFIG_BATTERY_SBS=y
 CONFIG_SENSORS_LM90=y
diff --git a/arch/arm/include/asm/arch_timer.h b/arch/arm/include/asm/arch_timer.h
index ed2e95d46e29..62e75475e57e 100644
--- a/arch/arm/include/asm/arch_timer.h
+++ b/arch/arm/include/asm/arch_timer.h
@@ -1,7 +1,10 @@
 #ifndef __ASMARM_ARCH_TIMER_H
 #define __ASMARM_ARCH_TIMER_H
 
+#include <asm/errno.h>
+
 #ifdef CONFIG_ARM_ARCH_TIMER
+#define ARCH_HAS_READ_CURRENT_TIMER
 int arch_timer_of_register(void);
 int arch_timer_sched_clock_init(void);
 #else
diff --git a/arch/arm/include/asm/delay.h b/arch/arm/include/asm/delay.h
index b2deda181549..dc6145120de3 100644
--- a/arch/arm/include/asm/delay.h
+++ b/arch/arm/include/asm/delay.h
@@ -6,9 +6,22 @@
 #ifndef __ASM_ARM_DELAY_H
 #define __ASM_ARM_DELAY_H
 
+#include <asm/memory.h>
 #include <asm/param.h>	/* HZ */
 
-extern void __delay(int loops);
+#define MAX_UDELAY_MS	2
+#define UDELAY_MULT	((UL(2199023) * HZ) >> 11)
+#define UDELAY_SHIFT	30
+
+#ifndef __ASSEMBLY__
+
+extern struct arm_delay_ops {
+	void (*delay)(unsigned long);
+	void (*const_udelay)(unsigned long);
+	void (*udelay)(unsigned long);
+} arm_delay_ops;
+
+#define __delay(n)		arm_delay_ops.delay(n)
 
 /*
  * This function intentionally does not exist; if you see references to
@@ -23,22 +36,27 @@ extern void __bad_udelay(void);
  * division by multiplication: you don't have to worry about
  * loss of precision.
  *
- * Use only for very small delays ( < 1 msec).  Should probably use a
+ * Use only for very small delays ( < 2 msec).  Should probably use a
  * lookup table, really, as the multiplications take much too long with
  * short delays.  This is a "reasonable" implementation, though (and the
  * first constant multiplications gets optimized away if the delay is
  * a constant)
  */
-extern void __udelay(unsigned long usecs);
-extern void __const_udelay(unsigned long);
-
-#define MAX_UDELAY_MS 2
+#define __udelay(n)		arm_delay_ops.udelay(n)
+#define __const_udelay(n)	arm_delay_ops.const_udelay(n)
 
 #define udelay(n)							\
 	(__builtin_constant_p(n) ?					\
 	  ((n) > (MAX_UDELAY_MS * 1000) ? __bad_udelay() :		\
-			__const_udelay((n) * ((2199023U*HZ)>>11))) :	\
+			__const_udelay((n) * UDELAY_MULT)) :		\
 	  __udelay(n))
 
+/* Loop-based definitions for assembly code. */
+extern void __loop_delay(unsigned long loops);
+extern void __loop_udelay(unsigned long usecs);
+extern void __loop_const_udelay(unsigned long);
+
+#endif /* __ASSEMBLY__ */
+
 #endif /* defined(_ARM_DELAY_H) */
 
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index bbef15d04890..2ae842df4551 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@@ -186,17 +186,6 @@ extern int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 			void *cpu_addr, dma_addr_t dma_addr, size_t size,
 			struct dma_attrs *attrs);
 
-#define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, NULL)
-
-static inline int dma_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
-				  void *cpu_addr, dma_addr_t dma_addr,
-				  size_t size, struct dma_attrs *attrs)
-{
-	struct dma_map_ops *ops = get_dma_ops(dev);
-	BUG_ON(!ops);
-	return ops->mmap(dev, vma, cpu_addr, dma_addr, size, attrs);
-}
-
 static inline void *dma_alloc_writecombine(struct device *dev, size_t size,
 				       dma_addr_t *dma_handle, gfp_t flag)
 {
@@ -213,20 +202,12 @@ static inline void dma_free_writecombine(struct device *dev, size_t size,
 	return dma_free_attrs(dev, size, cpu_addr, dma_handle, &attrs);
 }
 
-static inline int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
-		      void *cpu_addr, dma_addr_t dma_addr, size_t size)
-{
-	DEFINE_DMA_ATTRS(attrs);
-	dma_set_attr(DMA_ATTR_WRITE_COMBINE, &attrs);
-	return dma_mmap_attrs(dev, vma, cpu_addr, dma_addr, size, &attrs);
-}
-
 /*
  * This can be called during boot to increase the size of the consistent
  * DMA region above it's default value of 2MB. It must be called before the
  * memory allocator is initialised, i.e. before any core_initcall.
  */
-extern void __init init_consistent_dma_size(unsigned long size);
+static inline void init_consistent_dma_size(unsigned long size) { }
 
 /*
  * For SA-1111, IXP425, and ADI systems  the dma-mapping functions are "magic"
@@ -280,6 +261,9 @@ extern void arm_dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int,
 		enum dma_data_direction);
 extern void arm_dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
 		enum dma_data_direction);
+extern int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		struct dma_attrs *attrs);
 
 #endif /* __KERNEL__ */
 #endif
diff --git a/arch/arm/include/asm/kmap_types.h b/arch/arm/include/asm/kmap_types.h
index e51b1e81df05..83eb2f772911 100644
--- a/arch/arm/include/asm/kmap_types.h
+++ b/arch/arm/include/asm/kmap_types.h
@@ -4,30 +4,6 @@
 /*
  * This is the "bare minimum".  AIO seems to require this.
  */
-enum km_type {
-	KM_BOUNCE_READ,
-	KM_SKB_SUNRPC_DATA,
-	KM_SKB_DATA_SOFTIRQ,
-	KM_USER0,
-	KM_USER1,
-	KM_BIO_SRC_IRQ,
-	KM_BIO_DST_IRQ,
-	KM_PTE0,
-	KM_PTE1,
-	KM_IRQ0,
-	KM_IRQ1,
-	KM_SOFTIRQ0,
-	KM_SOFTIRQ1,
-	KM_L1_CACHE,
-	KM_L2_CACHE,
-	KM_KDB,
-	KM_TYPE_NR
-};
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-#define KM_NMI		(-1)
-#define KM_NMI_PTE	(-1)
-#define KM_IRQ_PTE	(-1)
-#endif
+#define KM_TYPE_NR 16
 
 #endif
diff --git a/arch/arm/include/asm/locks.h b/arch/arm/include/asm/locks.h
deleted file mode 100644
index ef4c897772d1..000000000000
--- a/arch/arm/include/asm/locks.h
+++ /dev/null
@@ -1,274 +0,0 @@
-/*
- *  arch/arm/include/asm/locks.h
- *
- *  Copyright (C) 2000 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- *  Interrupt safe locking assembler. 
- */
-#ifndef __ASM_PROC_LOCKS_H
-#define __ASM_PROC_LOCKS_H
-
-#if __LINUX_ARM_ARCH__ >= 6
-
-#define __down_op(ptr,fail)			\
-	({					\
-	__asm__ __volatile__(			\
-	"@ down_op\n"				\
-"1:	ldrex	lr, [%0]\n"			\
-"	sub	lr, lr, %1\n"			\
-"	strex	ip, lr, [%0]\n"			\
-"	teq	ip, #0\n"			\
-"	bne	1b\n"				\
-"	teq	lr, #0\n"			\
-"	movmi	ip, %0\n"			\
-"	blmi	" #fail				\
-	:					\
-	: "r" (ptr), "I" (1)			\
-	: "ip", "lr", "cc");			\
-	smp_mb();				\
-	})
-
-#define __down_op_ret(ptr,fail)			\
-	({					\
-		unsigned int ret;		\
-	__asm__ __volatile__(			\
-	"@ down_op_ret\n"			\
-"1:	ldrex	lr, [%1]\n"			\
-"	sub	lr, lr, %2\n"			\
-"	strex	ip, lr, [%1]\n"			\
-"	teq	ip, #0\n"			\
-"	bne	1b\n"				\
-"	teq	lr, #0\n"			\
-"	movmi	ip, %1\n"			\
-"	movpl	ip, #0\n"			\
-"	blmi	" #fail "\n"			\
-"	mov	%0, ip"				\
-	: "=&r" (ret)				\
-	: "r" (ptr), "I" (1)			\
-	: "ip", "lr", "cc");			\
-	smp_mb();				\
-	ret;					\
-	})
-
-#define __up_op(ptr,wake)			\
-	({					\
-	smp_mb();				\
-	__asm__ __volatile__(			\
-	"@ up_op\n"				\
-"1:	ldrex	lr, [%0]\n"			\
-"	add	lr, lr, %1\n"			\
-"	strex	ip, lr, [%0]\n"			\
-"	teq	ip, #0\n"			\
-"	bne	1b\n"				\
-"	cmp	lr, #0\n"			\
-"	movle	ip, %0\n"			\
-"	blle	" #wake				\
-	:					\
-	: "r" (ptr), "I" (1)			\
-	: "ip", "lr", "cc");			\
-	})
-
-/*
- * The value 0x01000000 supports up to 128 processors and
- * lots of processes.  BIAS must be chosen such that sub'ing
- * BIAS once per CPU will result in the long remaining
- * negative.
- */
-#define RW_LOCK_BIAS      0x01000000
-#define RW_LOCK_BIAS_STR "0x01000000"
-
-#define __down_op_write(ptr,fail)		\
-	({					\
-	__asm__ __volatile__(			\
-	"@ down_op_write\n"			\
-"1:	ldrex	lr, [%0]\n"			\
-"	sub	lr, lr, %1\n"			\
-"	strex	ip, lr, [%0]\n"			\
-"	teq	ip, #0\n"			\
-"	bne	1b\n"				\
-"	teq	lr, #0\n"			\
-"	movne	ip, %0\n"			\
-"	blne	" #fail				\
-	:					\
-	: "r" (ptr), "I" (RW_LOCK_BIAS)		\
-	: "ip", "lr", "cc");			\
-	smp_mb();				\
-	})
-
-#define __up_op_write(ptr,wake)			\
-	({					\
-	smp_mb();				\
-	__asm__ __volatile__(			\
-	"@ up_op_write\n"			\
-"1:	ldrex	lr, [%0]\n"			\
-"	adds	lr, lr, %1\n"			\
-"	strex	ip, lr, [%0]\n"			\
-"	teq	ip, #0\n"			\
-"	bne	1b\n"				\
-"	movcs	ip, %0\n"			\
-"	blcs	" #wake				\
-	:					\
-	: "r" (ptr), "I" (RW_LOCK_BIAS)		\
-	: "ip", "lr", "cc");			\
-	})
-
-#define __down_op_read(ptr,fail)		\
-	__down_op(ptr, fail)
-
-#define __up_op_read(ptr,wake)			\
-	({					\
-	smp_mb();				\
-	__asm__ __volatile__(			\
-	"@ up_op_read\n"			\
-"1:	ldrex	lr, [%0]\n"			\
-"	add	lr, lr, %1\n"			\
-"	strex	ip, lr, [%0]\n"			\
-"	teq	ip, #0\n"			\
-"	bne	1b\n"				\
-"	teq	lr, #0\n"			\
-"	moveq	ip, %0\n"			\
-"	bleq	" #wake				\
-	:					\
-	: "r" (ptr), "I" (1)			\
-	: "ip", "lr", "cc");			\
-	})
-
-#else
-
-#define __down_op(ptr,fail)			\
-	({					\
-	__asm__ __volatile__(			\
-	"@ down_op\n"				\
-"	mrs	ip, cpsr\n"			\
-"	orr	lr, ip, #128\n"			\
-"	msr	cpsr_c, lr\n"			\
-"	ldr	lr, [%0]\n"			\
-"	subs	lr, lr, %1\n"			\
-"	str	lr, [%0]\n"			\
-"	msr	cpsr_c, ip\n"			\
-"	movmi	ip, %0\n"			\
-"	blmi	" #fail				\
-	:					\
-	: "r" (ptr), "I" (1)			\
-	: "ip", "lr", "cc");			\
-	smp_mb();				\
-	})
-
-#define __down_op_ret(ptr,fail)			\
-	({					\
-		unsigned int ret;		\
-	__asm__ __volatile__(			\
-	"@ down_op_ret\n"			\
-"	mrs	ip, cpsr\n"			\
-"	orr	lr, ip, #128\n"			\
-"	msr	cpsr_c, lr\n"			\
-"	ldr	lr, [%1]\n"			\
-"	subs	lr, lr, %2\n"			\
-"	str	lr, [%1]\n"			\
-"	msr	cpsr_c, ip\n"			\
-"	movmi	ip, %1\n"			\
-"	movpl	ip, #0\n"			\
-"	blmi	" #fail "\n"			\
-"	mov	%0, ip"				\
-	: "=&r" (ret)				\
-	: "r" (ptr), "I" (1)			\
-	: "ip", "lr", "cc");			\
-	smp_mb();				\
-	ret;					\
-	})
-
-#define __up_op(ptr,wake)			\
-	({					\
-	smp_mb();				\
-	__asm__ __volatile__(			\
-	"@ up_op\n"				\
-"	mrs	ip, cpsr\n"			\
-"	orr	lr, ip, #128\n"			\
-"	msr	cpsr_c, lr\n"			\
-"	ldr	lr, [%0]\n"			\
-"	adds	lr, lr, %1\n"			\
-"	str	lr, [%0]\n"			\
-"	msr	cpsr_c, ip\n"			\
-"	movle	ip, %0\n"			\
-"	blle	" #wake				\
-	:					\
-	: "r" (ptr), "I" (1)			\
-	: "ip", "lr", "cc");			\
-	})
-
-/*
- * The value 0x01000000 supports up to 128 processors and
- * lots of processes.  BIAS must be chosen such that sub'ing
- * BIAS once per CPU will result in the long remaining
- * negative.
- */
-#define RW_LOCK_BIAS      0x01000000
-#define RW_LOCK_BIAS_STR "0x01000000"
-
-#define __down_op_write(ptr,fail)		\
-	({					\
-	__asm__ __volatile__(			\
-	"@ down_op_write\n"			\
-"	mrs	ip, cpsr\n"			\
-"	orr	lr, ip, #128\n"			\
-"	msr	cpsr_c, lr\n"			\
-"	ldr	lr, [%0]\n"			\
-"	subs	lr, lr, %1\n"			\
-"	str	lr, [%0]\n"			\
-"	msr	cpsr_c, ip\n"			\
-"	movne	ip, %0\n"			\
-"	blne	" #fail				\
-	:					\
-	: "r" (ptr), "I" (RW_LOCK_BIAS)		\
-	: "ip", "lr", "cc");			\
-	smp_mb();				\
-	})
-
-#define __up_op_write(ptr,wake)			\
-	({					\
-	__asm__ __volatile__(			\
-	"@ up_op_write\n"			\
-"	mrs	ip, cpsr\n"			\
-"	orr	lr, ip, #128\n"			\
-"	msr	cpsr_c, lr\n"			\
-"	ldr	lr, [%0]\n"			\
-"	adds	lr, lr, %1\n"			\
-"	str	lr, [%0]\n"			\
-"	msr	cpsr_c, ip\n"			\
-"	movcs	ip, %0\n"			\
-"	blcs	" #wake				\
-	:					\
-	: "r" (ptr), "I" (RW_LOCK_BIAS)		\
-	: "ip", "lr", "cc");			\
-	smp_mb();				\
-	})
-
-#define __down_op_read(ptr,fail)		\
-	__down_op(ptr, fail)
-
-#define __up_op_read(ptr,wake)			\
-	({					\
-	smp_mb();				\
-	__asm__ __volatile__(			\
-	"@ up_op_read\n"			\
-"	mrs	ip, cpsr\n"			\
-"	orr	lr, ip, #128\n"			\
-"	msr	cpsr_c, lr\n"			\
-"	ldr	lr, [%0]\n"			\
-"	adds	lr, lr, %1\n"			\
-"	str	lr, [%0]\n"			\
-"	msr	cpsr_c, ip\n"			\
-"	moveq	ip, %0\n"			\
-"	bleq	" #wake				\
-	:					\
-	: "r" (ptr), "I" (1)			\
-	: "ip", "lr", "cc");			\
-	})
-
-#endif
-
-#endif
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index fcb575747e5e..e965f1b560f1 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -16,7 +16,7 @@
 #include <linux/compiler.h>
 #include <linux/const.h>
 #include <linux/types.h>
-#include <asm/sizes.h>
+#include <linux/sizes.h>
 
 #ifdef CONFIG_NEED_MACH_MEMORY_H
 #include <mach/memory.h>
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index 00cbe10a50e3..e074948d8143 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -12,21 +12,6 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-/* ARM perf PMU IDs for use by internal perf clients. */
-enum arm_perf_pmu_ids {
-	ARM_PERF_PMU_ID_XSCALE1	= 0,
-	ARM_PERF_PMU_ID_XSCALE2,
-	ARM_PERF_PMU_ID_V6,
-	ARM_PERF_PMU_ID_V6MP,
-	ARM_PERF_PMU_ID_CA8,
-	ARM_PERF_PMU_ID_CA9,
-	ARM_PERF_PMU_ID_CA5,
-	ARM_PERF_PMU_ID_CA15,
-	ARM_PERF_PMU_ID_CA7,
-	ARM_NUM_PMU_IDS,
-};
-
-extern enum arm_perf_pmu_ids
-armpmu_get_pmu_id(void);
+/* Nothing to see here... */
 
 #endif /* __ARM_PERF_EVENT_H__ */
diff --git a/arch/arm/include/asm/pmu.h b/arch/arm/include/asm/pmu.h
index 90114faa9f3c..4432305f4a2a 100644
--- a/arch/arm/include/asm/pmu.h
+++ b/arch/arm/include/asm/pmu.h
@@ -103,10 +103,9 @@ struct pmu_hw_events {
 
 struct arm_pmu {
 	struct pmu	pmu;
-	enum arm_perf_pmu_ids id;
 	enum arm_pmu_type type;
 	cpumask_t	active_irqs;
-	const char	*name;
+	char		*name;
 	irqreturn_t	(*handle_irq)(int irq_num, void *dev);
 	void		(*enable)(struct hw_perf_event *evt, int idx);
 	void		(*disable)(struct hw_perf_event *evt, int idx);
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 65fa3c88095c..b4ca707d0a69 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -59,18 +59,13 @@ static inline void dsb_sev(void)
 }
 
 /*
- * ARMv6 Spin-locking.
+ * ARMv6 ticket-based spin-locking.
  *
- * We exclusively read the old value.  If it is zero, we may have
- * won the lock, so we try exclusively storing it.  A memory barrier
- * is required after we get a lock, and before we release it, because
- * V6 CPUs are assumed to have weakly ordered memory.
- *
- * Unlocked value: 0
- * Locked value: 1
+ * A memory barrier is required after we get a lock, and before we
+ * release it, because V6 CPUs are assumed to have weakly ordered
+ * memory.
  */
 
-#define arch_spin_is_locked(x)		((x)->lock != 0)
 #define arch_spin_unlock_wait(lock) \
 	do { while (arch_spin_is_locked(lock)) cpu_relax(); } while (0)
 
@@ -79,31 +74,39 @@ static inline void dsb_sev(void)
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
+	u32 newval;
+	arch_spinlock_t lockval;
 
 	__asm__ __volatile__(
-"1:	ldrex	%0, [%1]\n"
-"	teq	%0, #0\n"
-	WFE("ne")
-"	strexeq	%0, %2, [%1]\n"
-"	teqeq	%0, #0\n"
+"1:	ldrex	%0, [%3]\n"
+"	add	%1, %0, %4\n"
+"	strex	%2, %1, [%3]\n"
+"	teq	%2, #0\n"
 "	bne	1b"
-	: "=&r" (tmp)
-	: "r" (&lock->lock), "r" (1)
+	: "=&r" (lockval), "=&r" (newval), "=&r" (tmp)
+	: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
 	: "cc");
 
+	while (lockval.tickets.next != lockval.tickets.owner) {
+		wfe();
+		lockval.tickets.owner = ACCESS_ONCE(lock->tickets.owner);
+	}
+
 	smp_mb();
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
 	unsigned long tmp;
+	u32 slock;
 
 	__asm__ __volatile__(
-"	ldrex	%0, [%1]\n"
-"	teq	%0, #0\n"
-"	strexeq	%0, %2, [%1]"
-	: "=&r" (tmp)
-	: "r" (&lock->lock), "r" (1)
+"	ldrex	%0, [%2]\n"
+"	subs	%1, %0, %0, ror #16\n"
+"	addeq	%0, %0, %3\n"
+"	strexeq	%1, %0, [%2]"
+	: "=&r" (slock), "=&r" (tmp)
+	: "r" (&lock->slock), "I" (1 << TICKET_SHIFT)
 	: "cc");
 
 	if (tmp == 0) {
@@ -116,17 +119,38 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
+	unsigned long tmp;
+	u32 slock;
+
 	smp_mb();
 
 	__asm__ __volatile__(
-"	str	%1, [%0]\n"
-	:
-	: "r" (&lock->lock), "r" (0)
+"	mov	%1, #1\n"
+"1:	ldrex	%0, [%2]\n"
+"	uadd16	%0, %0, %1\n"
+"	strex	%1, %0, [%2]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (slock), "=&r" (tmp)
+	: "r" (&lock->slock)
 	: "cc");
 
 	dsb_sev();
 }
 
+static inline int arch_spin_is_locked(arch_spinlock_t *lock)
+{
+	struct __raw_tickets tickets = ACCESS_ONCE(lock->tickets);
+	return tickets.owner != tickets.next;
+}
+
+static inline int arch_spin_is_contended(arch_spinlock_t *lock)
+{
+	struct __raw_tickets tickets = ACCESS_ONCE(lock->tickets);
+	return (tickets.next - tickets.owner) > 1;
+}
+#define arch_spin_is_contended	arch_spin_is_contended
+
 /*
  * RWLOCKS
  *
@@ -158,7 +182,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 	unsigned long tmp;
 
 	__asm__ __volatile__(
-"1:	ldrex	%0, [%1]\n"
+"	ldrex	%0, [%1]\n"
 "	teq	%0, #0\n"
 "	strexeq	%0, %2, [%1]"
 	: "=&r" (tmp)
@@ -244,7 +268,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 	unsigned long tmp, tmp2 = 1;
 
 	__asm__ __volatile__(
-"1:	ldrex	%0, [%2]\n"
+"	ldrex	%0, [%2]\n"
 "	adds	%0, %0, #1\n"
 "	strexpl	%1, %0, [%2]\n"
 	: "=&r" (tmp), "+r" (tmp2)
diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h
index d14d197ae04a..b262d2f8b478 100644
--- a/arch/arm/include/asm/spinlock_types.h
+++ b/arch/arm/include/asm/spinlock_types.h
@@ -5,11 +5,24 @@
 # error "please don't include this file directly"
 #endif
 
+#define TICKET_SHIFT	16
+
 typedef struct {
-	volatile unsigned int lock;
+	union {
+		u32 slock;
+		struct __raw_tickets {
+#ifdef __ARMEB__
+			u16 next;
+			u16 owner;
+#else
+			u16 owner;
+			u16 next;
+#endif
+		} tickets;
+	};
 } arch_spinlock_t;
 
-#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 }
+#define __ARCH_SPIN_LOCK_UNLOCKED	{ { 0 } }
 
 typedef struct {
 	volatile unsigned int lock;
diff --git a/arch/arm/include/asm/timex.h b/arch/arm/include/asm/timex.h
index 3be8de3adaba..ce119442277c 100644
--- a/arch/arm/include/asm/timex.h
+++ b/arch/arm/include/asm/timex.h
@@ -12,13 +12,15 @@
 #ifndef _ASMARM_TIMEX_H
 #define _ASMARM_TIMEX_H
 
+#include <asm/arch_timer.h>
 #include <mach/timex.h>
 
 typedef unsigned long cycles_t;
 
-static inline cycles_t get_cycles (void)
-{
-	return 0;
-}
+#ifdef ARCH_HAS_READ_CURRENT_TIMER
+#define get_cycles()	({ cycles_t c; read_current_timer(&c) ? 0 : c; })
+#else
+#define get_cycles()	(0)
+#endif
 
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 71f6536d17ac..479a6352e0b5 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -189,6 +189,9 @@ static inline void set_fs(mm_segment_t fs)
 
 #define access_ok(type,addr,size)	(__range_ok(addr,size) == 0)
 
+#define user_addr_max() \
+	(segment_eq(get_fs(), USER_DS) ? TASK_SIZE : ~0UL)
+
 /*
  * The "__xxx" versions of the user access functions do not verify the
  * address space - it must have been done previously with a separate
@@ -398,9 +401,6 @@ extern unsigned long __must_check __clear_user_std(void __user *addr, unsigned l
 #define __clear_user(addr,n)		(memset((void __force *)addr, 0, n), 0)
 #endif
 
-extern unsigned long __must_check __strncpy_from_user(char *to, const char __user *from, unsigned long count);
-extern unsigned long __must_check __strnlen_user(const char __user *s, long n);
-
 static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n)
 {
 	if (access_ok(VERIFY_READ, from, n))
@@ -427,24 +427,9 @@ static inline unsigned long __must_check clear_user(void __user *to, unsigned lo
 	return n;
 }
 
-static inline long __must_check strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res = -EFAULT;
-	if (access_ok(VERIFY_READ, src, 1))
-		res = __strncpy_from_user(dst, src, count);
-	return res;
-}
-
-#define strlen_user(s)	strnlen_user(s, ~0UL >> 1)
+extern long strncpy_from_user(char *dest, const char __user *src, long count);
 
-static inline long __must_check strnlen_user(const char __user *s, long n)
-{
-	unsigned long res = 0;
-
-	if (__addr_ok(s))
-		res = __strnlen_user(s, n);
-
-	return res;
-}
+extern __must_check long strlen_user(const char __user *str);
+extern __must_check long strnlen_user(const char __user *str, long n);
 
 #endif /* _ASMARM_UACCESS_H */
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 512cd1473454..0cab47d4a83f 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -446,7 +446,6 @@
 
 #ifdef __KERNEL__
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_GETHOSTNAME
 #define __ARCH_WANT_SYS_PAUSE
diff --git a/arch/arm/include/asm/word-at-a-time.h b/arch/arm/include/asm/word-at-a-time.h
new file mode 100644
index 000000000000..4d52f92967a6
--- /dev/null
+++ b/arch/arm/include/asm/word-at-a-time.h
@@ -0,0 +1,96 @@
+#ifndef __ASM_ARM_WORD_AT_A_TIME_H
+#define __ASM_ARM_WORD_AT_A_TIME_H
+
+#ifndef __ARMEB__
+
+/*
+ * Little-endian word-at-a-time zero byte handling.
+ * Heavily based on the x86 algorithm.
+ */
+#include <linux/kernel.h>
+
+struct word_at_a_time {
+	const unsigned long one_bits, high_bits;
+};
+
+#define WORD_AT_A_TIME_CONSTANTS { REPEAT_BYTE(0x01), REPEAT_BYTE(0x80) }
+
+static inline unsigned long has_zero(unsigned long a, unsigned long *bits,
+				     const struct word_at_a_time *c)
+{
+	unsigned long mask = ((a - c->one_bits) & ~a) & c->high_bits;
+	*bits = mask;
+	return mask;
+}
+
+#define prep_zero_mask(a, bits, c) (bits)
+
+static inline unsigned long create_zero_mask(unsigned long bits)
+{
+	bits = (bits - 1) & ~bits;
+	return bits >> 7;
+}
+
+static inline unsigned long find_zero(unsigned long mask)
+{
+	unsigned long ret;
+
+#if __LINUX_ARM_ARCH__ >= 5
+	/* We have clz available. */
+	ret = fls(mask) >> 3;
+#else
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	ret = (0x0ff0001 + mask) >> 23;
+	/* Fix the 1 for 00 case */
+	ret &= mask;
+#endif
+
+	return ret;
+}
+
+#ifdef CONFIG_DCACHE_WORD_ACCESS
+
+#define zero_bytemask(mask) (mask)
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long ret, offset;
+
+	/* Load word from unaligned pointer addr */
+	asm(
+	"1:	ldr	%0, [%2]\n"
+	"2:\n"
+	"	.pushsection .fixup,\"ax\"\n"
+	"	.align 2\n"
+	"3:	and	%1, %2, #0x3\n"
+	"	bic	%2, %2, #0x3\n"
+	"	ldr	%0, [%2]\n"
+	"	lsl	%1, %1, #0x3\n"
+	"	lsr	%0, %0, %1\n"
+	"	b	2b\n"
+	"	.popsection\n"
+	"	.pushsection __ex_table,\"a\"\n"
+	"	.align	3\n"
+	"	.long	1b, 3b\n"
+	"	.popsection"
+	: "=&r" (ret), "=&r" (offset)
+	: "r" (addr), "Qo" (*(unsigned long *)addr));
+
+	return ret;
+}
+
+
+#endif	/* DCACHE_WORD_ACCESS */
+
+#else	/* __ARMEB__ */
+#include <asm-generic/word-at-a-time.h>
+#endif
+
+#endif /* __ASM_ARM_WORD_AT_A_TIME_H */
diff --git a/arch/arm/kernel/arch_timer.c b/arch/arm/kernel/arch_timer.c
index dd58035621f7..cf258807160d 100644
--- a/arch/arm/kernel/arch_timer.c
+++ b/arch/arm/kernel/arch_timer.c
@@ -32,6 +32,8 @@ static int arch_timer_ppi2;
 
 static struct clock_event_device __percpu **arch_timer_evt;
 
+extern void init_current_timer_delay(unsigned long freq);
+
 /*
  * Architected system timer support.
  */
@@ -137,7 +139,7 @@ static int __cpuinit arch_timer_setup(struct clock_event_device *clk)
 	/* Be safe... */
 	arch_timer_disable();
 
-	clk->features = CLOCK_EVT_FEAT_ONESHOT;
+	clk->features = CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_C3STOP;
 	clk->name = "arch_sys_timer";
 	clk->rating = 450;
 	clk->set_mode = arch_timer_set_mode;
@@ -223,6 +225,14 @@ static cycle_t arch_counter_read(struct clocksource *cs)
 	return arch_counter_get_cntpct();
 }
 
+int read_current_timer(unsigned long *timer_val)
+{
+	if (!arch_timer_rate)
+		return -ENXIO;
+	*timer_val = arch_counter_get_cntpct();
+	return 0;
+}
+
 static struct clocksource clocksource_counter = {
 	.name	= "arch_sys_counter",
 	.rating	= 400,
@@ -296,6 +306,7 @@ static int __init arch_timer_register(void)
 	if (err)
 		goto out_free_irq;
 
+	init_current_timer_delay(arch_timer_rate);
 	return 0;
 
 out_free_irq:
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index b57c75e0b01f..60d3b738d420 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -49,8 +49,7 @@ extern void __aeabi_ulcmp(void);
 extern void fpundefinstr(void);
 
 	/* platform dependent support */
-EXPORT_SYMBOL(__udelay);
-EXPORT_SYMBOL(__const_udelay);
+EXPORT_SYMBOL(arm_delay_ops);
 
 	/* networking */
 EXPORT_SYMBOL(csum_partial);
@@ -87,10 +86,6 @@ EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(memchr);
 EXPORT_SYMBOL(__memzero);
 
-	/* user mem (segment) */
-EXPORT_SYMBOL(__strnlen_user);
-EXPORT_SYMBOL(__strncpy_from_user);
-
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);
 
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 4afed88d250a..49d9f9305247 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -95,13 +95,7 @@ ENDPROC(ret_to_user)
 ENTRY(ret_from_fork)
 	bl	schedule_tail
 	get_thread_info tsk
-	ldr	r1, [tsk, #TI_FLAGS]		@ check for syscall tracing
 	mov	why, #1
-	tst	r1, #_TIF_SYSCALL_WORK		@ are we tracing syscalls?
-	beq	ret_slow_syscall
-	mov	r1, sp
-	mov	r0, #1				@ trace exit [IP = 1]
-	bl	syscall_trace
 	b	ret_slow_syscall
 ENDPROC(ret_from_fork)
 
@@ -448,10 +442,9 @@ ENDPROC(vector_swi)
 	 * context switches, and waiting for our parent to respond.
 	 */
 __sys_trace:
-	mov	r2, scno
-	add	r1, sp, #S_OFF
-	mov	r0, #0				@ trace entry [IP = 0]
-	bl	syscall_trace
+	mov	r1, scno
+	add	r0, sp, #S_OFF
+	bl	syscall_trace_enter
 
 	adr	lr, BSYM(__sys_trace_return)	@ return address
 	mov	scno, r0			@ syscall number (possibly new)
@@ -463,10 +456,9 @@ __sys_trace:
 
 __sys_trace_return:
 	str	r0, [sp, #S_R0 + S_OFF]!	@ save returned r0
-	mov	r2, scno
-	mov	r1, sp
-	mov	r0, #1				@ trace exit [IP = 1]
-	bl	syscall_trace
+	mov	r1, scno
+	mov	r0, sp
+	bl	syscall_trace_exit
 	b	ret_slow_syscall
 
 	.align	5
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 835898e7d704..3db960e20cb8 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -55,14 +55,6 @@
 	add	\rd, \phys, #TEXT_OFFSET - PG_DIR_SIZE
 	.endm
 
-#ifdef CONFIG_XIP_KERNEL
-#define KERNEL_START	XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR)
-#define KERNEL_END	_edata_loc
-#else
-#define KERNEL_START	KERNEL_RAM_VADDR
-#define KERNEL_END	_end
-#endif
-
 /*
  * Kernel startup entry point.
  * ---------------------------
@@ -218,51 +210,46 @@ __create_page_tables:
 	blo	1b
 
 	/*
-	 * Now setup the pagetables for our kernel direct
-	 * mapped region.
+	 * Map our RAM from the start to the end of the kernel .bss section.
 	 */
-	mov	r3, pc
-	mov	r3, r3, lsr #SECTION_SHIFT
-	orr	r3, r7, r3, lsl #SECTION_SHIFT
-	add	r0, r4,  #(KERNEL_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
-	str	r3, [r0, #((KERNEL_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ORDER]!
-	ldr	r6, =(KERNEL_END - 1)
-	add	r0, r0, #1 << PMD_ORDER
+	add	r0, r4, #PAGE_OFFSET >> (SECTION_SHIFT - PMD_ORDER)
+	ldr	r6, =(_end - 1)
+	orr	r3, r8, r7
 	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
-1:	cmp	r0, r6
+1:	str	r3, [r0], #1 << PMD_ORDER
 	add	r3, r3, #1 << SECTION_SHIFT
-	strls	r3, [r0], #1 << PMD_ORDER
+	cmp	r0, r6
 	bls	1b
 
 #ifdef CONFIG_XIP_KERNEL
 	/*
-	 * Map some ram to cover our .data and .bss areas.
+	 * Map the kernel image separately as it is not located in RAM.
 	 */
-	add	r3, r8, #TEXT_OFFSET
-	orr	r3, r3, r7
-	add	r0, r4,  #(KERNEL_RAM_VADDR & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
-	str	r3, [r0, #(KERNEL_RAM_VADDR & 0x00f00000) >> (SECTION_SHIFT - PMD_ORDER)]!
-	ldr	r6, =(_end - 1)
-	add	r0, r0, #4
+#define XIP_START XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR)
+	mov	r3, pc
+	mov	r3, r3, lsr #SECTION_SHIFT
+	orr	r3, r7, r3, lsl #SECTION_SHIFT
+	add	r0, r4,  #(XIP_START & 0xff000000) >> (SECTION_SHIFT - PMD_ORDER)
+	str	r3, [r0, #((XIP_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ORDER]!
+	ldr	r6, =(_edata_loc - 1)
+	add	r0, r0, #1 << PMD_ORDER
 	add	r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ORDER)
 1:	cmp	r0, r6
-	add	r3, r3, #1 << 20
-	strls	r3, [r0], #4
+	add	r3, r3, #1 << SECTION_SHIFT
+	strls	r3, [r0], #1 << PMD_ORDER
 	bls	1b
 #endif
 
 	/*
-	 * Then map boot params address in r2 or the first 1MB (2MB with LPAE)
-	 * of ram if boot params address is not specified.
+	 * Then map boot params address in r2 if specified.
 	 */
 	mov	r0, r2, lsr #SECTION_SHIFT
 	movs	r0, r0, lsl #SECTION_SHIFT
-	moveq	r0, r8
-	sub	r3, r0, r8
-	add	r3, r3, #PAGE_OFFSET
-	add	r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER)
-	orr	r6, r7, r0
-	str	r6, [r3]
+	subne	r3, r0, r8
+	addne	r3, r3, #PAGE_OFFSET
+	addne	r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER)
+	orrne	r6, r7, r0
+	strne	r6, [r3]
 
 #ifdef CONFIG_DEBUG_LL
 #if !defined(CONFIG_DEBUG_ICEDCC) && !defined(CONFIG_DEBUG_SEMIHOSTING)
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index a02eada3aa5d..ab243b87118d 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -47,17 +47,14 @@ static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
 /* Set at runtime when we know what CPU type we are. */
 static struct arm_pmu *cpu_pmu;
 
-enum arm_perf_pmu_ids
-armpmu_get_pmu_id(void)
+const char *perf_pmu_name(void)
 {
-	int id = -ENODEV;
-
-	if (cpu_pmu != NULL)
-		id = cpu_pmu->id;
+	if (!cpu_pmu)
+		return NULL;
 
-	return id;
+	return cpu_pmu->pmu.name;
 }
-EXPORT_SYMBOL_GPL(armpmu_get_pmu_id);
+EXPORT_SYMBOL_GPL(perf_pmu_name);
 
 int perf_num_counters(void)
 {
@@ -760,7 +757,7 @@ init_hw_perf_events(void)
 			cpu_pmu->name, cpu_pmu->num_events);
 		cpu_pmu_init(cpu_pmu);
 		register_cpu_notifier(&pmu_cpu_notifier);
-		armpmu_register(cpu_pmu, "cpu", PERF_TYPE_RAW);
+		armpmu_register(cpu_pmu, cpu_pmu->name, PERF_TYPE_RAW);
 	} else {
 		pr_info("no hardware support available\n");
 	}
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index ab627a740fa3..c90fcb2b6967 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -650,7 +650,6 @@ static int armv6_map_event(struct perf_event *event)
 }
 
 static struct arm_pmu armv6pmu = {
-	.id			= ARM_PERF_PMU_ID_V6,
 	.name			= "v6",
 	.handle_irq		= armv6pmu_handle_irq,
 	.enable			= armv6pmu_enable_event,
@@ -685,7 +684,6 @@ static int armv6mpcore_map_event(struct perf_event *event)
 }
 
 static struct arm_pmu armv6mpcore_pmu = {
-	.id			= ARM_PERF_PMU_ID_V6MP,
 	.name			= "v6mpcore",
 	.handle_irq		= armv6pmu_handle_irq,
 	.enable			= armv6pmu_enable_event,
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index d3c536068162..f04070bd2183 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -1258,7 +1258,6 @@ static u32 __init armv7_read_num_pmnc_events(void)
 
 static struct arm_pmu *__init armv7_a8_pmu_init(void)
 {
-	armv7pmu.id		= ARM_PERF_PMU_ID_CA8;
 	armv7pmu.name		= "ARMv7 Cortex-A8";
 	armv7pmu.map_event	= armv7_a8_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
@@ -1267,7 +1266,6 @@ static struct arm_pmu *__init armv7_a8_pmu_init(void)
 
 static struct arm_pmu *__init armv7_a9_pmu_init(void)
 {
-	armv7pmu.id		= ARM_PERF_PMU_ID_CA9;
 	armv7pmu.name		= "ARMv7 Cortex-A9";
 	armv7pmu.map_event	= armv7_a9_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
@@ -1276,7 +1274,6 @@ static struct arm_pmu *__init armv7_a9_pmu_init(void)
 
 static struct arm_pmu *__init armv7_a5_pmu_init(void)
 {
-	armv7pmu.id		= ARM_PERF_PMU_ID_CA5;
 	armv7pmu.name		= "ARMv7 Cortex-A5";
 	armv7pmu.map_event	= armv7_a5_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
@@ -1285,7 +1282,6 @@ static struct arm_pmu *__init armv7_a5_pmu_init(void)
 
 static struct arm_pmu *__init armv7_a15_pmu_init(void)
 {
-	armv7pmu.id		= ARM_PERF_PMU_ID_CA15;
 	armv7pmu.name		= "ARMv7 Cortex-A15";
 	armv7pmu.map_event	= armv7_a15_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
@@ -1295,7 +1291,6 @@ static struct arm_pmu *__init armv7_a15_pmu_init(void)
 
 static struct arm_pmu *__init armv7_a7_pmu_init(void)
 {
-	armv7pmu.id		= ARM_PERF_PMU_ID_CA7;
 	armv7pmu.name		= "ARMv7 Cortex-A7";
 	armv7pmu.map_event	= armv7_a7_map_event;
 	armv7pmu.num_events	= armv7_read_num_pmnc_events();
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index e34e7254e652..f759fe0bab63 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -435,7 +435,6 @@ static int xscale_map_event(struct perf_event *event)
 }
 
 static struct arm_pmu xscale1pmu = {
-	.id		= ARM_PERF_PMU_ID_XSCALE1,
 	.name		= "xscale1",
 	.handle_irq	= xscale1pmu_handle_irq,
 	.enable		= xscale1pmu_enable_event,
@@ -803,7 +802,6 @@ xscale2pmu_write_counter(int counter, u32 val)
 }
 
 static struct arm_pmu xscale2pmu = {
-	.id		= ARM_PERF_PMU_ID_XSCALE2,
 	.name		= "xscale2",
 	.handle_irq	= xscale2pmu_handle_irq,
 	.enable		= xscale2pmu_enable_event,
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 14e38261cd31..dab711e6e1ca 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -907,16 +907,16 @@ long arch_ptrace(struct task_struct *child, long request,
 	return ret;
 }
 
-asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
+enum ptrace_syscall_dir {
+	PTRACE_SYSCALL_ENTER = 0,
+	PTRACE_SYSCALL_EXIT,
+};
+
+static int ptrace_syscall_trace(struct pt_regs *regs, int scno,
+				enum ptrace_syscall_dir dir)
 {
 	unsigned long ip;
 
-	if (why)
-		audit_syscall_exit(regs);
-	else
-		audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0,
-				    regs->ARM_r1, regs->ARM_r2, regs->ARM_r3);
-
 	if (!test_thread_flag(TIF_SYSCALL_TRACE))
 		return scno;
 
@@ -927,14 +927,28 @@ asmlinkage int syscall_trace(int why, struct pt_regs *regs, int scno)
 	 * IP = 0 -> entry, =1 -> exit
 	 */
 	ip = regs->ARM_ip;
-	regs->ARM_ip = why;
+	regs->ARM_ip = dir;
 
-	if (why)
+	if (dir == PTRACE_SYSCALL_EXIT)
 		tracehook_report_syscall_exit(regs, 0);
 	else if (tracehook_report_syscall_entry(regs))
 		current_thread_info()->syscall = -1;
 
 	regs->ARM_ip = ip;
-
 	return current_thread_info()->syscall;
 }
+
+asmlinkage int syscall_trace_enter(struct pt_regs *regs, int scno)
+{
+	int ret = ptrace_syscall_trace(regs, scno, PTRACE_SYSCALL_ENTER);
+	audit_syscall_entry(AUDIT_ARCH_ARM, scno, regs->ARM_r0, regs->ARM_r1,
+			    regs->ARM_r2, regs->ARM_r3);
+	return ret;
+}
+
+asmlinkage int syscall_trace_exit(struct pt_regs *regs, int scno)
+{
+	int ret = ptrace_syscall_trace(regs, scno, PTRACE_SYSCALL_EXIT);
+	audit_syscall_exit(regs);
+	return ret;
+}
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 2c7217d971db..aea74f5bc34a 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -179,7 +179,7 @@ void __ref cpu_die(void)
 	mb();
 
 	/* Tell __cpu_die() that this CPU is now safe to dispose of */
-	complete(&cpu_died);
+	RCU_NONIDLE(complete(&cpu_died));
 
 	/*
 	 * actual CPU shutdown procedure is at least platform (if not
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 8200deaa14f6..198b08456e90 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -17,11 +17,190 @@
 #include <linux/percpu.h>
 #include <linux/node.h>
 #include <linux/nodemask.h>
+#include <linux/of.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 
 #include <asm/cputype.h>
 #include <asm/topology.h>
 
+/*
+ * cpu power scale management
+ */
+
+/*
+ * cpu power table
+ * This per cpu data structure describes the relative capacity of each core.
+ * On a heteregenous system, cores don't have the same computation capacity
+ * and we reflect that difference in the cpu_power field so the scheduler can
+ * take this difference into account during load balance. A per cpu structure
+ * is preferred because each CPU updates its own cpu_power field during the
+ * load balance except for idle cores. One idle core is selected to run the
+ * rebalance_domains for all idle cores and the cpu_power can be updated
+ * during this sequence.
+ */
+static DEFINE_PER_CPU(unsigned long, cpu_scale);
+
+unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
+{
+	return per_cpu(cpu_scale, cpu);
+}
+
+static void set_power_scale(unsigned int cpu, unsigned long power)
+{
+	per_cpu(cpu_scale, cpu) = power;
+}
+
+#ifdef CONFIG_OF
+struct cpu_efficiency {
+	const char *compatible;
+	unsigned long efficiency;
+};
+
+/*
+ * Table of relative efficiency of each processors
+ * The efficiency value must fit in 20bit and the final
+ * cpu_scale value must be in the range
+ *   0 < cpu_scale < 3*SCHED_POWER_SCALE/2
+ * in order to return at most 1 when DIV_ROUND_CLOSEST
+ * is used to compute the capacity of a CPU.
+ * Processors that are not defined in the table,
+ * use the default SCHED_POWER_SCALE value for cpu_scale.
+ */
+struct cpu_efficiency table_efficiency[] = {
+	{"arm,cortex-a15", 3891},
+	{"arm,cortex-a7",  2048},
+	{NULL, },
+};
+
+struct cpu_capacity {
+	unsigned long hwid;
+	unsigned long capacity;
+};
+
+struct cpu_capacity *cpu_capacity;
+
+unsigned long middle_capacity = 1;
+
+/*
+ * Iterate all CPUs' descriptor in DT and compute the efficiency
+ * (as per table_efficiency). Also calculate a middle efficiency
+ * as close as possible to  (max{eff_i} - min{eff_i}) / 2
+ * This is later used to scale the cpu_power field such that an
+ * 'average' CPU is of middle power. Also see the comments near
+ * table_efficiency[] and update_cpu_power().
+ */
+static void __init parse_dt_topology(void)
+{
+	struct cpu_efficiency *cpu_eff;
+	struct device_node *cn = NULL;
+	unsigned long min_capacity = (unsigned long)(-1);
+	unsigned long max_capacity = 0;
+	unsigned long capacity = 0;
+	int alloc_size, cpu = 0;
+
+	alloc_size = nr_cpu_ids * sizeof(struct cpu_capacity);
+	cpu_capacity = (struct cpu_capacity *)kzalloc(alloc_size, GFP_NOWAIT);
+
+	while ((cn = of_find_node_by_type(cn, "cpu"))) {
+		const u32 *rate, *reg;
+		int len;
+
+		if (cpu >= num_possible_cpus())
+			break;
+
+		for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++)
+			if (of_device_is_compatible(cn, cpu_eff->compatible))
+				break;
+
+		if (cpu_eff->compatible == NULL)
+			continue;
+
+		rate = of_get_property(cn, "clock-frequency", &len);
+		if (!rate || len != 4) {
+			pr_err("%s missing clock-frequency property\n",
+				cn->full_name);
+			continue;
+		}
+
+		reg = of_get_property(cn, "reg", &len);
+		if (!reg || len != 4) {
+			pr_err("%s missing reg property\n", cn->full_name);
+			continue;
+		}
+
+		capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency;
+
+		/* Save min capacity of the system */
+		if (capacity < min_capacity)
+			min_capacity = capacity;
+
+		/* Save max capacity of the system */
+		if (capacity > max_capacity)
+			max_capacity = capacity;
+
+		cpu_capacity[cpu].capacity = capacity;
+		cpu_capacity[cpu++].hwid = be32_to_cpup(reg);
+	}
+
+	if (cpu < num_possible_cpus())
+		cpu_capacity[cpu].hwid = (unsigned long)(-1);
+
+	/* If min and max capacities are equals, we bypass the update of the
+	 * cpu_scale because all CPUs have the same capacity. Otherwise, we
+	 * compute a middle_capacity factor that will ensure that the capacity
+	 * of an 'average' CPU of the system will be as close as possible to
+	 * SCHED_POWER_SCALE, which is the default value, but with the
+	 * constraint explained near table_efficiency[].
+	 */
+	if (min_capacity == max_capacity)
+		cpu_capacity[0].hwid = (unsigned long)(-1);
+	else if (4*max_capacity < (3*(max_capacity + min_capacity)))
+		middle_capacity = (min_capacity + max_capacity)
+				>> (SCHED_POWER_SHIFT+1);
+	else
+		middle_capacity = ((max_capacity / 3)
+				>> (SCHED_POWER_SHIFT-1)) + 1;
+
+}
+
+/*
+ * Look for a customed capacity of a CPU in the cpu_capacity table during the
+ * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the
+ * function returns directly for SMP system.
+ */
+void update_cpu_power(unsigned int cpu, unsigned long hwid)
+{
+	unsigned int idx = 0;
+
+	/* look for the cpu's hwid in the cpu capacity table */
+	for (idx = 0; idx < num_possible_cpus(); idx++) {
+		if (cpu_capacity[idx].hwid == hwid)
+			break;
+
+		if (cpu_capacity[idx].hwid == -1)
+			return;
+	}
+
+	if (idx == num_possible_cpus())
+		return;
+
+	set_power_scale(cpu, cpu_capacity[idx].capacity / middle_capacity);
+
+	printk(KERN_INFO "CPU%u: update cpu_power %lu\n",
+		cpu, arch_scale_freq_power(NULL, cpu));
+}
+
+#else
+static inline void parse_dt_topology(void) {}
+static inline void update_cpu_power(unsigned int cpuid, unsigned int mpidr) {}
+#endif
+
+
+/*
+ * cpu topology management
+ */
+
 #define MPIDR_SMP_BITMASK (0x3 << 30)
 #define MPIDR_SMP_VALUE (0x2 << 30)
 
@@ -31,6 +210,7 @@
  * These masks reflect the current use of the affinity levels.
  * The affinity level can be up to 16 bits according to ARM ARM
  */
+#define MPIDR_HWID_BITMASK 0xFFFFFF
 
 #define MPIDR_LEVEL0_MASK 0x3
 #define MPIDR_LEVEL0_SHIFT 0
@@ -41,6 +221,9 @@
 #define MPIDR_LEVEL2_MASK 0xFF
 #define MPIDR_LEVEL2_SHIFT 16
 
+/*
+ * cpu topology table
+ */
 struct cputopo_arm cpu_topology[NR_CPUS];
 
 const struct cpumask *cpu_coregroup_mask(int cpu)
@@ -48,6 +231,32 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	return &cpu_topology[cpu].core_sibling;
 }
 
+void update_siblings_masks(unsigned int cpuid)
+{
+	struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid];
+	int cpu;
+
+	/* update core and thread sibling masks */
+	for_each_possible_cpu(cpu) {
+		cpu_topo = &cpu_topology[cpu];
+
+		if (cpuid_topo->socket_id != cpu_topo->socket_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+
+		if (cpuid_topo->core_id != cpu_topo->core_id)
+			continue;
+
+		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
+		if (cpu != cpuid)
+			cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+	}
+	smp_wmb();
+}
+
 /*
  * store_cpu_topology is called at boot when only one cpu is running
  * and with the mutex cpu_hotplug.lock locked, when several cpus have booted,
@@ -57,7 +266,6 @@ void store_cpu_topology(unsigned int cpuid)
 {
 	struct cputopo_arm *cpuid_topo = &cpu_topology[cpuid];
 	unsigned int mpidr;
-	unsigned int cpu;
 
 	/* If the cpu topology has been already set, just return */
 	if (cpuid_topo->core_id != -1)
@@ -99,26 +307,9 @@ void store_cpu_topology(unsigned int cpuid)
 		cpuid_topo->socket_id = -1;
 	}
 
-	/* update core and thread sibling masks */
-	for_each_possible_cpu(cpu) {
-		struct cputopo_arm *cpu_topo = &cpu_topology[cpu];
-
-		if (cpuid_topo->socket_id == cpu_topo->socket_id) {
-			cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
-			if (cpu != cpuid)
-				cpumask_set_cpu(cpu,
-					&cpuid_topo->core_sibling);
-
-			if (cpuid_topo->core_id == cpu_topo->core_id) {
-				cpumask_set_cpu(cpuid,
-					&cpu_topo->thread_sibling);
-				if (cpu != cpuid)
-					cpumask_set_cpu(cpu,
-						&cpuid_topo->thread_sibling);
-			}
-		}
-	}
-	smp_wmb();
+	update_siblings_masks(cpuid);
+
+	update_cpu_power(cpuid, mpidr & MPIDR_HWID_BITMASK);
 
 	printk(KERN_INFO "CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
 		cpuid, cpu_topology[cpuid].thread_id,
@@ -134,7 +325,7 @@ void init_cpu_topology(void)
 {
 	unsigned int cpu;
 
-	/* init core mask */
+	/* init core mask and power*/
 	for_each_possible_cpu(cpu) {
 		struct cputopo_arm *cpu_topo = &(cpu_topology[cpu]);
 
@@ -143,6 +334,10 @@ void init_cpu_topology(void)
 		cpu_topo->socket_id = -1;
 		cpumask_clear(&cpu_topo->core_sibling);
 		cpumask_clear(&cpu_topo->thread_sibling);
+
+		set_power_scale(cpu, SCHED_POWER_SCALE);
 	}
 	smp_wmb();
+
+	parse_dt_topology();
 }
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 3647170e9a16..8b97d739b17b 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -233,9 +233,9 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 #define S_ISA " ARM"
 #endif
 
-static int __die(const char *str, int err, struct thread_info *thread, struct pt_regs *regs)
+static int __die(const char *str, int err, struct pt_regs *regs)
 {
-	struct task_struct *tsk = thread->task;
+	struct task_struct *tsk = current;
 	static int die_counter;
 	int ret;
 
@@ -245,12 +245,12 @@ static int __die(const char *str, int err, struct thread_info *thread, struct pt
 	/* trap and error numbers are mostly meaningless on ARM */
 	ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV);
 	if (ret == NOTIFY_STOP)
-		return ret;
+		return 1;
 
 	print_modules();
 	__show_regs(regs);
 	printk(KERN_EMERG "Process %.*s (pid: %d, stack limit = 0x%p)\n",
-		TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), thread + 1);
+		TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), end_of_stack(tsk));
 
 	if (!user_mode(regs) || in_interrupt()) {
 		dump_mem(KERN_EMERG, "Stack: ", regs->ARM_sp,
@@ -259,45 +259,77 @@ static int __die(const char *str, int err, struct thread_info *thread, struct pt
 		dump_instr(KERN_EMERG, regs);
 	}
 
-	return ret;
+	return 0;
 }
 
-static DEFINE_RAW_SPINLOCK(die_lock);
+static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED;
+static int die_owner = -1;
+static unsigned int die_nest_count;
 
-/*
- * This function is protected against re-entrancy.
- */
-void die(const char *str, struct pt_regs *regs, int err)
+static unsigned long oops_begin(void)
 {
-	struct thread_info *thread = current_thread_info();
-	int ret;
-	enum bug_trap_type bug_type = BUG_TRAP_TYPE_NONE;
+	int cpu;
+	unsigned long flags;
 
 	oops_enter();
 
-	raw_spin_lock_irq(&die_lock);
+	/* racy, but better than risking deadlock. */
+	raw_local_irq_save(flags);
+	cpu = smp_processor_id();
+	if (!arch_spin_trylock(&die_lock)) {
+		if (cpu == die_owner)
+			/* nested oops. should stop eventually */;
+		else
+			arch_spin_lock(&die_lock);
+	}
+	die_nest_count++;
+	die_owner = cpu;
 	console_verbose();
 	bust_spinlocks(1);
-	if (!user_mode(regs))
-		bug_type = report_bug(regs->ARM_pc, regs);
-	if (bug_type != BUG_TRAP_TYPE_NONE)
-		str = "Oops - BUG";
-	ret = __die(str, err, thread, regs);
+	return flags;
+}
 
-	if (regs && kexec_should_crash(thread->task))
+static void oops_end(unsigned long flags, struct pt_regs *regs, int signr)
+{
+	if (regs && kexec_should_crash(current))
 		crash_kexec(regs);
 
 	bust_spinlocks(0);
+	die_owner = -1;
 	add_taint(TAINT_DIE);
-	raw_spin_unlock_irq(&die_lock);
+	die_nest_count--;
+	if (!die_nest_count)
+		/* Nest count reaches zero, release the lock. */
+		arch_spin_unlock(&die_lock);
+	raw_local_irq_restore(flags);
 	oops_exit();
 
 	if (in_interrupt())
 		panic("Fatal exception in interrupt");
 	if (panic_on_oops)
 		panic("Fatal exception");
-	if (ret != NOTIFY_STOP)
-		do_exit(SIGSEGV);
+	if (signr)
+		do_exit(signr);
+}
+
+/*
+ * This function is protected against re-entrancy.
+ */
+void die(const char *str, struct pt_regs *regs, int err)
+{
+	enum bug_trap_type bug_type = BUG_TRAP_TYPE_NONE;
+	unsigned long flags = oops_begin();
+	int sig = SIGSEGV;
+
+	if (!user_mode(regs))
+		bug_type = report_bug(regs->ARM_pc, regs);
+	if (bug_type != BUG_TRAP_TYPE_NONE)
+		str = "Oops - BUG";
+
+	if (__die(str, err, regs))
+		sig = 0;
+
+	oops_end(flags, regs, sig);
 }
 
 void arm_notify_die(const char *str, struct pt_regs *regs,
diff --git a/arch/arm/lib/Makefile b/arch/arm/lib/Makefile
index 992769ae2599..2473fd1fd51c 100644
--- a/arch/arm/lib/Makefile
+++ b/arch/arm/lib/Makefile
@@ -6,9 +6,8 @@
 
 lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 		   csumpartialcopy.o csumpartialcopyuser.o clearbit.o \
-		   delay.o findbit.o memchr.o memcpy.o		      \
+		   delay.o delay-loop.o findbit.o memchr.o memcpy.o   \
 		   memmove.o memset.o memzero.o setbit.o              \
-		   strncpy_from_user.o strnlen_user.o                 \
 		   strchr.o strrchr.o                                 \
 		   testchangebit.o testclearbit.o testsetbit.o        \
 		   ashldi3.o ashrdi3.o lshrdi3.o muldi3.o             \
diff --git a/arch/arm/lib/delay.S b/arch/arm/lib/delay-loop.S
index 3c9a05c8d20b..36b668d8e121 100644
--- a/arch/arm/lib/delay.S
+++ b/arch/arm/lib/delay-loop.S
@@ -9,11 +9,11 @@
  */
 #include <linux/linkage.h>
 #include <asm/assembler.h>
-#include <asm/param.h>
+#include <asm/delay.h>
 		.text
 
 .LC0:		.word	loops_per_jiffy
-.LC1:		.word	(2199023*HZ)>>11
+.LC1:		.word	UDELAY_MULT
 
 /*
  * r0  <= 2000
@@ -21,10 +21,10 @@
  * HZ  <= 1000
  */
 
-ENTRY(__udelay)
+ENTRY(__loop_udelay)
 		ldr	r2, .LC1
 		mul	r0, r2, r0
-ENTRY(__const_udelay)				@ 0 <= r0 <= 0x7fffff06
+ENTRY(__loop_const_udelay)			@ 0 <= r0 <= 0x7fffff06
 		mov	r1, #-1
 		ldr	r2, .LC0
 		ldr	r2, [r2]		@ max = 0x01ffffff
@@ -39,12 +39,10 @@ ENTRY(__const_udelay)				@ 0 <= r0 <= 0x7fffff06
 
 /*
  * loops = r0 * HZ * loops_per_jiffy / 1000000
- *
- * Oh, if only we had a cycle counter...
  */
 
 @ Delay routine
-ENTRY(__delay)
+ENTRY(__loop_delay)
 		subs	r0, r0, #1
 #if 0
 		movls	pc, lr
@@ -62,8 +60,8 @@ ENTRY(__delay)
 		movls	pc, lr
 		subs	r0, r0, #1
 #endif
-		bhi	__delay
+		bhi	__loop_delay
 		mov	pc, lr
-ENDPROC(__udelay)
-ENDPROC(__const_udelay)
-ENDPROC(__delay)
+ENDPROC(__loop_udelay)
+ENDPROC(__loop_const_udelay)
+ENDPROC(__loop_delay)
diff --git a/arch/arm/lib/delay.c b/arch/arm/lib/delay.c
new file mode 100644
index 000000000000..d6dacc69254e
--- /dev/null
+++ b/arch/arm/lib/delay.c
@@ -0,0 +1,71 @@
+/*
+ * Delay loops based on the OpenRISC implementation.
+ *
+ * Copyright (C) 2012 ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ *
+ * Author: Will Deacon <will.deacon@arm.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/timex.h>
+
+/*
+ * Default to the loop-based delay implementation.
+ */
+struct arm_delay_ops arm_delay_ops = {
+	.delay		= __loop_delay,
+	.const_udelay	= __loop_const_udelay,
+	.udelay		= __loop_udelay,
+};
+
+#ifdef ARCH_HAS_READ_CURRENT_TIMER
+static void __timer_delay(unsigned long cycles)
+{
+	cycles_t start = get_cycles();
+
+	while ((get_cycles() - start) < cycles)
+		cpu_relax();
+}
+
+static void __timer_const_udelay(unsigned long xloops)
+{
+	unsigned long long loops = xloops;
+	loops *= loops_per_jiffy;
+	__timer_delay(loops >> UDELAY_SHIFT);
+}
+
+static void __timer_udelay(unsigned long usecs)
+{
+	__timer_const_udelay(usecs * UDELAY_MULT);
+}
+
+void __init init_current_timer_delay(unsigned long freq)
+{
+	pr_info("Switching to timer-based delay loop\n");
+	lpj_fine			= freq / HZ;
+	arm_delay_ops.delay		= __timer_delay;
+	arm_delay_ops.const_udelay	= __timer_const_udelay;
+	arm_delay_ops.udelay		= __timer_udelay;
+}
+
+unsigned long __cpuinit calibrate_delay_is_known(void)
+{
+	return lpj_fine;
+}
+#endif
diff --git a/arch/arm/lib/io-acorn.S b/arch/arm/lib/io-acorn.S
index 1b197ea7aab3..69719bad674d 100644
--- a/arch/arm/lib/io-acorn.S
+++ b/arch/arm/lib/io-acorn.S
@@ -11,13 +11,14 @@
  *
  */
 #include <linux/linkage.h>
+#include <linux/kern_levels.h>
 #include <asm/assembler.h>
 
 		.text
 		.align
 
 .Liosl_warning:
-		.ascii	"<4>insl/outsl not implemented, called from %08lX\0"
+		.ascii	KERN_WARNING "insl/outsl not implemented, called from %08lX\0"
 		.align
 
 /*
diff --git a/arch/arm/lib/strncpy_from_user.S b/arch/arm/lib/strncpy_from_user.S
deleted file mode 100644
index f202d7bd1647..000000000000
--- a/arch/arm/lib/strncpy_from_user.S
+++ /dev/null
@@ -1,43 +0,0 @@
-/*
- *  linux/arch/arm/lib/strncpy_from_user.S
- *
- *  Copyright (C) 1995-2000 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/errno.h>
-
-	.text
-	.align	5
-
-/*
- * Copy a string from user space to kernel space.
- *  r0 = dst, r1 = src, r2 = byte length
- * returns the number of characters copied (strlen of copied string),
- *  -EFAULT on exception, or "len" if we fill the whole buffer
- */
-ENTRY(__strncpy_from_user)
-	mov	ip, r1
-1:	subs	r2, r2, #1
-	ldrusr	r3, r1, 1, pl
-	bmi	2f
-	strb	r3, [r0], #1
-	teq	r3, #0
-	bne	1b
-	sub	r1, r1, #1	@ take NUL character out of count
-2:	sub	r0, r1, ip
-	mov	pc, lr
-ENDPROC(__strncpy_from_user)
-
-	.pushsection .fixup,"ax"
-	.align	0
-9001:	mov	r3, #0
-	strb	r3, [r0, #0]	@ null terminate
-	mov	r0, #-EFAULT
-	mov	pc, lr
-	.popsection
-
diff --git a/arch/arm/lib/strnlen_user.S b/arch/arm/lib/strnlen_user.S
deleted file mode 100644
index 0ecbb459c4f1..000000000000
--- a/arch/arm/lib/strnlen_user.S
+++ /dev/null
@@ -1,40 +0,0 @@
-/*
- *  linux/arch/arm/lib/strnlen_user.S
- *
- *  Copyright (C) 1995-2000 Russell King
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/errno.h>
-
-	.text
-	.align	5
-
-/* Prototype: unsigned long __strnlen_user(const char *str, long n)
- * Purpose  : get length of a string in user memory
- * Params   : str - address of string in user memory
- * Returns  : length of string *including terminator*
- *	      or zero on exception, or n + 1 if too long
- */
-ENTRY(__strnlen_user)
-	mov	r2, r0
-1:
-	ldrusr	r3, r0, 1
-	teq	r3, #0
-	beq	2f
-	subs	r1, r1, #1
-	bne	1b
-	add	r0, r0, #1
-2:	sub	r0, r0, r2
-	mov	pc, lr
-ENDPROC(__strnlen_user)
-
-	.pushsection .fixup,"ax"
-	.align	0
-9001:	mov	r0, #0
-	mov	pc, lr
-	.popsection
diff --git a/arch/arm/mach-at91/at91sam9g45.c b/arch/arm/mach-at91/at91sam9g45.c
index 977127368a7d..ef6cedd52e3c 100644
--- a/arch/arm/mach-at91/at91sam9g45.c
+++ b/arch/arm/mach-at91/at91sam9g45.c
@@ -183,6 +183,13 @@ static struct clk adc_op_clk = {
 	.rate_hz	= 13200000,
 };
 
+/* AES/TDES/SHA clock - Only for sam9m11/sam9g56 */
+static struct clk aestdessha_clk = {
+	.name		= "aestdessha_clk",
+	.pmc_mask	= 1 << AT91SAM9G45_ID_AESTDESSHA,
+	.type		= CLK_TYPE_PERIPHERAL,
+};
+
 static struct clk *periph_clocks[] __initdata = {
 	&pioA_clk,
 	&pioB_clk,
@@ -212,6 +219,7 @@ static struct clk *periph_clocks[] __initdata = {
 	&udphs_clk,
 	&mmc1_clk,
 	&adc_op_clk,
+	&aestdessha_clk,
 	// irq0
 };
 
@@ -232,6 +240,9 @@ static struct clk_lookup periph_clocks_lookups[] = {
 	CLKDEV_CON_DEV_ID("pclk", "ssc.0", &ssc0_clk),
 	CLKDEV_CON_DEV_ID("pclk", "ssc.1", &ssc1_clk),
 	CLKDEV_CON_DEV_ID(NULL, "atmel-trng", &trng_clk),
+	CLKDEV_CON_DEV_ID(NULL, "atmel_sha", &aestdessha_clk),
+	CLKDEV_CON_DEV_ID(NULL, "atmel_tdes", &aestdessha_clk),
+	CLKDEV_CON_DEV_ID(NULL, "atmel_aes", &aestdessha_clk),
 	/* more usart lookup table for DT entries */
 	CLKDEV_CON_DEV_ID("usart", "ffffee00.serial", &mck),
 	CLKDEV_CON_DEV_ID("usart", "fff8c000.serial", &usart0_clk),
@@ -388,7 +399,7 @@ static unsigned int at91sam9g45_default_irq_priority[NR_AIC_IRQS] __initdata = {
 	3,	/* Ethernet */
 	0,	/* Image Sensor Interface */
 	2,	/* USB Device High speed port */
-	0,
+	0,	/* AESTDESSHA Crypto HW Accelerators */
 	0,	/* Multimedia Card Interface 1 */
 	0,
 	0,	/* Advanced Interrupt Controller (IRQ0) */
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 40fb79df2de0..06073996a382 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -18,6 +18,7 @@
 #include <linux/platform_device.h>
 #include <linux/i2c-gpio.h>
 #include <linux/atmel-mci.h>
+#include <linux/platform_data/atmel-aes.h>
 
 #include <linux/platform_data/at91_adc.h>
 
@@ -1830,6 +1831,130 @@ void __init at91_register_uart(unsigned id, unsigned portnr, unsigned pins) {}
 void __init at91_add_device_serial(void) {}
 #endif
 
+/* --------------------------------------------------------------------
+ *  SHA1/SHA256
+ * -------------------------------------------------------------------- */
+
+#if defined(CONFIG_CRYPTO_DEV_ATMEL_SHA) || defined(CONFIG_CRYPTO_DEV_ATMEL_SHA_MODULE)
+static struct resource sha_resources[] = {
+	{
+		.start	= AT91SAM9G45_BASE_SHA,
+		.end	= AT91SAM9G45_BASE_SHA + SZ_16K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= AT91SAM9G45_ID_AESTDESSHA,
+		.end	= AT91SAM9G45_ID_AESTDESSHA,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device at91sam9g45_sha_device = {
+	.name	= "atmel_sha",
+	.id		= -1,
+	.resource	= sha_resources,
+	.num_resources	= ARRAY_SIZE(sha_resources),
+};
+
+static void __init at91_add_device_sha(void)
+{
+	platform_device_register(&at91sam9g45_sha_device);
+}
+#else
+static void __init at91_add_device_sha(void) {}
+#endif
+
+/* --------------------------------------------------------------------
+ *  DES/TDES
+ * -------------------------------------------------------------------- */
+
+#if defined(CONFIG_CRYPTO_DEV_ATMEL_TDES) || defined(CONFIG_CRYPTO_DEV_ATMEL_TDES_MODULE)
+static struct resource tdes_resources[] = {
+	[0] = {
+		.start	= AT91SAM9G45_BASE_TDES,
+		.end	= AT91SAM9G45_BASE_TDES + SZ_16K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= AT91SAM9G45_ID_AESTDESSHA,
+		.end	= AT91SAM9G45_ID_AESTDESSHA,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device at91sam9g45_tdes_device = {
+	.name	= "atmel_tdes",
+	.id		= -1,
+	.resource	= tdes_resources,
+	.num_resources	= ARRAY_SIZE(tdes_resources),
+};
+
+static void __init at91_add_device_tdes(void)
+{
+	platform_device_register(&at91sam9g45_tdes_device);
+}
+#else
+static void __init at91_add_device_tdes(void) {}
+#endif
+
+/* --------------------------------------------------------------------
+ *  AES
+ * -------------------------------------------------------------------- */
+
+#if defined(CONFIG_CRYPTO_DEV_ATMEL_AES) || defined(CONFIG_CRYPTO_DEV_ATMEL_AES_MODULE)
+static struct aes_platform_data aes_data;
+static u64 aes_dmamask = DMA_BIT_MASK(32);
+
+static struct resource aes_resources[] = {
+	[0] = {
+		.start	= AT91SAM9G45_BASE_AES,
+		.end	= AT91SAM9G45_BASE_AES + SZ_16K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= AT91SAM9G45_ID_AESTDESSHA,
+		.end	= AT91SAM9G45_ID_AESTDESSHA,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device at91sam9g45_aes_device = {
+	.name	= "atmel_aes",
+	.id		= -1,
+	.dev	= {
+		.dma_mask		= &aes_dmamask,
+		.coherent_dma_mask	= DMA_BIT_MASK(32),
+		.platform_data		= &aes_data,
+	},
+	.resource	= aes_resources,
+	.num_resources	= ARRAY_SIZE(aes_resources),
+};
+
+static void __init at91_add_device_aes(void)
+{
+	struct at_dma_slave	*atslave;
+	struct aes_dma_data	*alt_atslave;
+
+	alt_atslave = kzalloc(sizeof(struct aes_dma_data), GFP_KERNEL);
+
+	/* DMA TX slave channel configuration */
+	atslave = &alt_atslave->txdata;
+	atslave->dma_dev = &at_hdmac_device.dev;
+	atslave->cfg = ATC_FIFOCFG_ENOUGHSPACE	| ATC_SRC_H2SEL_HW |
+						ATC_SRC_PER(AT_DMA_ID_AES_RX);
+
+	/* DMA RX slave channel configuration */
+	atslave = &alt_atslave->rxdata;
+	atslave->dma_dev = &at_hdmac_device.dev;
+	atslave->cfg = ATC_FIFOCFG_ENOUGHSPACE	| ATC_DST_H2SEL_HW |
+						ATC_DST_PER(AT_DMA_ID_AES_TX);
+
+	aes_data.dma_slave = alt_atslave;
+	platform_device_register(&at91sam9g45_aes_device);
+}
+#else
+static void __init at91_add_device_aes(void) {}
+#endif
 
 /* -------------------------------------------------------------------- */
 /*
@@ -1847,6 +1972,9 @@ static int __init at91_add_standard_devices(void)
 	at91_add_device_trng();
 	at91_add_device_watchdog();
 	at91_add_device_tc();
+	at91_add_device_sha();
+	at91_add_device_tdes();
+	at91_add_device_aes();
 	return 0;
 }
 
diff --git a/arch/arm/mach-at91/include/mach/at91sam9g45.h b/arch/arm/mach-at91/include/mach/at91sam9g45.h
index 3a4da24d5911..8eba1021f533 100644
--- a/arch/arm/mach-at91/include/mach/at91sam9g45.h
+++ b/arch/arm/mach-at91/include/mach/at91sam9g45.h
@@ -136,6 +136,8 @@
 #define AT_DMA_ID_SSC1_RX	 8
 #define AT_DMA_ID_AC97_TX	 9
 #define AT_DMA_ID_AC97_RX	10
+#define AT_DMA_ID_AES_TX	11
+#define AT_DMA_ID_AES_RX	12
 #define AT_DMA_ID_MCI1		13
 
 #endif
diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c
index 9493076fc594..4db5de54b6a7 100644
--- a/arch/arm/mach-dove/common.c
+++ b/arch/arm/mach-dove/common.c
@@ -101,8 +101,8 @@ void __init dove_ehci1_init(void)
  ****************************************************************************/
 void __init dove_ge00_init(struct mv643xx_eth_platform_data *eth_data)
 {
-	orion_ge00_init(eth_data,
-			DOVE_GE00_PHYS_BASE, IRQ_DOVE_GE00_SUM, 0);
+	orion_ge00_init(eth_data, DOVE_GE00_PHYS_BASE,
+			IRQ_DOVE_GE00_SUM, IRQ_DOVE_GE00_ERR);
 }
 
 /*****************************************************************************
diff --git a/arch/arm/mach-exynos/clock-exynos4.c b/arch/arm/mach-exynos/clock-exynos4.c
index 26fe9de35ecb..2f51293c1875 100644
--- a/arch/arm/mach-exynos/clock-exynos4.c
+++ b/arch/arm/mach-exynos/clock-exynos4.c
@@ -620,10 +620,6 @@ static struct clk exynos4_init_clocks_off[] = {
 		.enable		= exynos4_clk_ip_peril_ctrl,
 		.ctrlbit	= (1 << 27),
 	}, {
-		.name		= "fimg2d",
-		.enable		= exynos4_clk_ip_image_ctrl,
-		.ctrlbit	= (1 << 0),
-	}, {
 		.name		= "mfc",
 		.devname	= "s5p-mfc",
 		.enable		= exynos4_clk_ip_mfc_ctrl,
@@ -819,47 +815,21 @@ static struct clk *exynos4_clkset_mout_g2d0_list[] = {
 	[1] = &exynos4_clk_sclk_apll.clk,
 };
 
-static struct clksrc_sources exynos4_clkset_mout_g2d0 = {
+struct clksrc_sources exynos4_clkset_mout_g2d0 = {
 	.sources	= exynos4_clkset_mout_g2d0_list,
 	.nr_sources	= ARRAY_SIZE(exynos4_clkset_mout_g2d0_list),
 };
 
-static struct clksrc_clk exynos4_clk_mout_g2d0 = {
-	.clk	= {
-		.name		= "mout_g2d0",
-	},
-	.sources = &exynos4_clkset_mout_g2d0,
-	.reg_src = { .reg = EXYNOS4_CLKSRC_IMAGE, .shift = 0, .size = 1 },
-};
-
 static struct clk *exynos4_clkset_mout_g2d1_list[] = {
 	[0] = &exynos4_clk_mout_epll.clk,
 	[1] = &exynos4_clk_sclk_vpll.clk,
 };
 
-static struct clksrc_sources exynos4_clkset_mout_g2d1 = {
+struct clksrc_sources exynos4_clkset_mout_g2d1 = {
 	.sources	= exynos4_clkset_mout_g2d1_list,
 	.nr_sources	= ARRAY_SIZE(exynos4_clkset_mout_g2d1_list),
 };
 
-static struct clksrc_clk exynos4_clk_mout_g2d1 = {
-	.clk	= {
-		.name		= "mout_g2d1",
-	},
-	.sources = &exynos4_clkset_mout_g2d1,
-	.reg_src = { .reg = EXYNOS4_CLKSRC_IMAGE, .shift = 4, .size = 1 },
-};
-
-static struct clk *exynos4_clkset_mout_g2d_list[] = {
-	[0] = &exynos4_clk_mout_g2d0.clk,
-	[1] = &exynos4_clk_mout_g2d1.clk,
-};
-
-static struct clksrc_sources exynos4_clkset_mout_g2d = {
-	.sources	= exynos4_clkset_mout_g2d_list,
-	.nr_sources	= ARRAY_SIZE(exynos4_clkset_mout_g2d_list),
-};
-
 static struct clk *exynos4_clkset_mout_mfc0_list[] = {
 	[0] = &exynos4_clk_mout_mpll.clk,
 	[1] = &exynos4_clk_sclk_apll.clk,
@@ -1126,13 +1096,6 @@ static struct clksrc_clk exynos4_clksrcs[] = {
 		.reg_div = { .reg = EXYNOS4_CLKDIV_LCD0, .shift = 0, .size = 4 },
 	}, {
 		.clk	= {
-			.name		= "sclk_fimg2d",
-		},
-		.sources = &exynos4_clkset_mout_g2d,
-		.reg_src = { .reg = EXYNOS4_CLKSRC_IMAGE, .shift = 8, .size = 1 },
-		.reg_div = { .reg = EXYNOS4_CLKDIV_IMAGE, .shift = 0, .size = 4 },
-	}, {
-		.clk	= {
 			.name		= "sclk_mfc",
 			.devname	= "s5p-mfc",
 		},
diff --git a/arch/arm/mach-exynos/clock-exynos4.h b/arch/arm/mach-exynos/clock-exynos4.h
index 28a119701182..bd12d5f8b63d 100644
--- a/arch/arm/mach-exynos/clock-exynos4.h
+++ b/arch/arm/mach-exynos/clock-exynos4.h
@@ -23,6 +23,9 @@ extern struct clksrc_sources exynos4_clkset_group;
 extern struct clk *exynos4_clkset_aclk_top_list[];
 extern struct clk *exynos4_clkset_group_list[];
 
+extern struct clksrc_sources exynos4_clkset_mout_g2d0;
+extern struct clksrc_sources exynos4_clkset_mout_g2d1;
+
 extern int exynos4_clksrc_mask_fsys_ctrl(struct clk *clk, int enable);
 extern int exynos4_clk_ip_fsys_ctrl(struct clk *clk, int enable);
 extern int exynos4_clk_ip_lcd1_ctrl(struct clk *clk, int enable);
diff --git a/arch/arm/mach-exynos/clock-exynos4210.c b/arch/arm/mach-exynos/clock-exynos4210.c
index b8689ff60baf..fed4c26e9dad 100644
--- a/arch/arm/mach-exynos/clock-exynos4210.c
+++ b/arch/arm/mach-exynos/clock-exynos4210.c
@@ -48,6 +48,32 @@ static struct clksrc_clk *sysclks[] = {
 	/* nothing here yet */
 };
 
+static struct clksrc_clk exynos4210_clk_mout_g2d0 = {
+	.clk	= {
+		.name		= "mout_g2d0",
+	},
+	.sources = &exynos4_clkset_mout_g2d0,
+	.reg_src = { .reg = EXYNOS4_CLKSRC_IMAGE, .shift = 0, .size = 1 },
+};
+
+static struct clksrc_clk exynos4210_clk_mout_g2d1 = {
+	.clk	= {
+		.name		= "mout_g2d1",
+	},
+	.sources = &exynos4_clkset_mout_g2d1,
+	.reg_src = { .reg = EXYNOS4_CLKSRC_IMAGE, .shift = 4, .size = 1 },
+};
+
+static struct clk *exynos4210_clkset_mout_g2d_list[] = {
+	[0] = &exynos4210_clk_mout_g2d0.clk,
+	[1] = &exynos4210_clk_mout_g2d1.clk,
+};
+
+static struct clksrc_sources exynos4210_clkset_mout_g2d = {
+	.sources	= exynos4210_clkset_mout_g2d_list,
+	.nr_sources	= ARRAY_SIZE(exynos4210_clkset_mout_g2d_list),
+};
+
 static int exynos4_clksrc_mask_lcd1_ctrl(struct clk *clk, int enable)
 {
 	return s5p_gatectrl(EXYNOS4210_CLKSRC_MASK_LCD1, clk, enable);
@@ -74,6 +100,13 @@ static struct clksrc_clk clksrcs[] = {
 		.sources = &exynos4_clkset_group,
 		.reg_src = { .reg = EXYNOS4210_CLKSRC_LCD1, .shift = 0, .size = 4 },
 		.reg_div = { .reg = EXYNOS4210_CLKDIV_LCD1, .shift = 0, .size = 4 },
+	}, {
+		.clk	= {
+			.name		= "sclk_fimg2d",
+		},
+		.sources = &exynos4210_clkset_mout_g2d,
+		.reg_src = { .reg = EXYNOS4_CLKSRC_IMAGE, .shift = 8, .size = 1 },
+		.reg_div = { .reg = EXYNOS4_CLKDIV_IMAGE, .shift = 0, .size = 4 },
 	},
 };
 
@@ -105,6 +138,10 @@ static struct clk init_clocks_off[] = {
 		.devname	= SYSMMU_CLOCK_DEVNAME(fimd1, 11),
 		.enable		= exynos4_clk_ip_lcd1_ctrl,
 		.ctrlbit	= (1 << 4),
+	}, {
+		.name		= "fimg2d",
+		.enable		= exynos4_clk_ip_image_ctrl,
+		.ctrlbit	= (1 << 0),
 	},
 };
 
diff --git a/arch/arm/mach-exynos/clock-exynos4212.c b/arch/arm/mach-exynos/clock-exynos4212.c
index da397d21bbcf..8fba0b5fb8ab 100644
--- a/arch/arm/mach-exynos/clock-exynos4212.c
+++ b/arch/arm/mach-exynos/clock-exynos4212.c
@@ -68,12 +68,45 @@ static struct clksrc_clk clk_mout_mpll_user = {
 	.reg_src	= { .reg = EXYNOS4_CLKSRC_CPU, .shift = 24, .size = 1 },
 };
 
+static struct clksrc_clk exynos4x12_clk_mout_g2d0 = {
+	.clk	= {
+		.name		= "mout_g2d0",
+	},
+	.sources = &exynos4_clkset_mout_g2d0,
+	.reg_src = { .reg = EXYNOS4_CLKSRC_DMC, .shift = 20, .size = 1 },
+};
+
+static struct clksrc_clk exynos4x12_clk_mout_g2d1 = {
+	.clk	= {
+		.name		= "mout_g2d1",
+	},
+	.sources = &exynos4_clkset_mout_g2d1,
+	.reg_src = { .reg = EXYNOS4_CLKSRC_DMC, .shift = 24, .size = 1 },
+};
+
+static struct clk *exynos4x12_clkset_mout_g2d_list[] = {
+	[0] = &exynos4x12_clk_mout_g2d0.clk,
+	[1] = &exynos4x12_clk_mout_g2d1.clk,
+};
+
+static struct clksrc_sources exynos4x12_clkset_mout_g2d = {
+	.sources	= exynos4x12_clkset_mout_g2d_list,
+	.nr_sources	= ARRAY_SIZE(exynos4x12_clkset_mout_g2d_list),
+};
+
 static struct clksrc_clk *sysclks[] = {
 	&clk_mout_mpll_user,
 };
 
 static struct clksrc_clk clksrcs[] = {
-	/* nothing here yet */
+	{
+		.clk	= {
+			.name		= "sclk_fimg2d",
+		},
+		.sources = &exynos4x12_clkset_mout_g2d,
+		.reg_src = { .reg = EXYNOS4_CLKSRC_DMC, .shift = 28, .size = 1 },
+		.reg_div = { .reg = EXYNOS4_CLKDIV_DMC1, .shift = 0, .size = 4 },
+	},
 };
 
 static struct clk init_clocks_off[] = {
@@ -102,7 +135,11 @@ static struct clk init_clocks_off[] = {
 		.devname	= "exynos-fimc-lite.1",
 		.enable		= exynos4212_clk_ip_isp0_ctrl,
 		.ctrlbit	= (1 << 3),
-	}
+	}, {
+		.name		= "fimg2d",
+		.enable		= exynos4_clk_ip_dmc_ctrl,
+		.ctrlbit	= (1 << 23),
+	},
 };
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/arch/arm/mach-exynos/mach-nuri.c b/arch/arm/mach-exynos/mach-nuri.c
index f98a83a81ce7..ea785fcaf6c3 100644
--- a/arch/arm/mach-exynos/mach-nuri.c
+++ b/arch/arm/mach-exynos/mach-nuri.c
@@ -1066,12 +1066,8 @@ static struct platform_device nuri_max8903_device = {
 static void __init nuri_power_init(void)
 {
 	int gpio;
-	int irq_base = IRQ_GPIO_END + 1;
 	int ta_en = 0;
 
-	nuri_max8997_pdata.irq_base = irq_base;
-	irq_base += MAX8997_IRQ_NR;
-
 	gpio = EXYNOS4_GPX0(7);
 	gpio_request(gpio, "AP_PMIC_IRQ");
 	s3c_gpio_cfgpin(gpio, S3C_GPIO_SFN(0xf));
diff --git a/arch/arm/mach-exynos/mach-origen.c b/arch/arm/mach-exynos/mach-origen.c
index 5a12dc26f496..5ca80307d6d7 100644
--- a/arch/arm/mach-exynos/mach-origen.c
+++ b/arch/arm/mach-exynos/mach-origen.c
@@ -426,7 +426,6 @@ static struct max8997_platform_data __initdata origen_max8997_pdata = {
 	.buck1_gpiodvs	= false,
 	.buck2_gpiodvs	= false,
 	.buck5_gpiodvs	= false,
-	.irq_base	= IRQ_GPIO_END + 1,
 
 	.ignore_gpiodvs_side_effect = true,
 	.buck125_default_idx = 0x0,
diff --git a/arch/arm/mach-imx/mm-imx25.c b/arch/arm/mach-imx/mm-imx25.c
index 388928fdb11a..f3f5c6542ab4 100644
--- a/arch/arm/mach-imx/mm-imx25.c
+++ b/arch/arm/mach-imx/mm-imx25.c
@@ -89,11 +89,11 @@ static const struct resource imx25_audmux_res[] __initconst = {
 
 void __init imx25_soc_init(void)
 {
-	/* i.mx25 has the i.mx31 type gpio */
-	mxc_register_gpio("imx31-gpio", 0, MX25_GPIO1_BASE_ADDR, SZ_16K, MX25_INT_GPIO1, 0);
-	mxc_register_gpio("imx31-gpio", 1, MX25_GPIO2_BASE_ADDR, SZ_16K, MX25_INT_GPIO2, 0);
-	mxc_register_gpio("imx31-gpio", 2, MX25_GPIO3_BASE_ADDR, SZ_16K, MX25_INT_GPIO3, 0);
-	mxc_register_gpio("imx31-gpio", 3, MX25_GPIO4_BASE_ADDR, SZ_16K, MX25_INT_GPIO4, 0);
+	/* i.mx25 has the i.mx35 type gpio */
+	mxc_register_gpio("imx35-gpio", 0, MX25_GPIO1_BASE_ADDR, SZ_16K, MX25_INT_GPIO1, 0);
+	mxc_register_gpio("imx35-gpio", 1, MX25_GPIO2_BASE_ADDR, SZ_16K, MX25_INT_GPIO2, 0);
+	mxc_register_gpio("imx35-gpio", 2, MX25_GPIO3_BASE_ADDR, SZ_16K, MX25_INT_GPIO3, 0);
+	mxc_register_gpio("imx35-gpio", 3, MX25_GPIO4_BASE_ADDR, SZ_16K, MX25_INT_GPIO4, 0);
 
 	pinctrl_provide_dummies();
 	/* i.mx25 has the i.mx35 type sdma */
diff --git a/arch/arm/mach-imx/mm-imx3.c b/arch/arm/mach-imx/mm-imx3.c
index fe96105109b3..9d2c843bde02 100644
--- a/arch/arm/mach-imx/mm-imx3.c
+++ b/arch/arm/mach-imx/mm-imx3.c
@@ -272,10 +272,9 @@ void __init imx35_soc_init(void)
 
 	imx3_init_l2x0();
 
-	/* i.mx35 has the i.mx31 type gpio */
-	mxc_register_gpio("imx31-gpio", 0, MX35_GPIO1_BASE_ADDR, SZ_16K, MX35_INT_GPIO1, 0);
-	mxc_register_gpio("imx31-gpio", 1, MX35_GPIO2_BASE_ADDR, SZ_16K, MX35_INT_GPIO2, 0);
-	mxc_register_gpio("imx31-gpio", 2, MX35_GPIO3_BASE_ADDR, SZ_16K, MX35_INT_GPIO3, 0);
+	mxc_register_gpio("imx35-gpio", 0, MX35_GPIO1_BASE_ADDR, SZ_16K, MX35_INT_GPIO1, 0);
+	mxc_register_gpio("imx35-gpio", 1, MX35_GPIO2_BASE_ADDR, SZ_16K, MX35_INT_GPIO2, 0);
+	mxc_register_gpio("imx35-gpio", 2, MX35_GPIO3_BASE_ADDR, SZ_16K, MX35_INT_GPIO3, 0);
 
 	pinctrl_provide_dummies();
 	if (to_version == 1) {
diff --git a/arch/arm/mach-imx/mm-imx5.c b/arch/arm/mach-imx/mm-imx5.c
index f19d604e1b2a..52d8f534be10 100644
--- a/arch/arm/mach-imx/mm-imx5.c
+++ b/arch/arm/mach-imx/mm-imx5.c
@@ -161,13 +161,13 @@ static const struct resource imx53_audmux_res[] __initconst = {
 
 void __init imx50_soc_init(void)
 {
-	/* i.mx50 has the i.mx31 type gpio */
-	mxc_register_gpio("imx31-gpio", 0, MX50_GPIO1_BASE_ADDR, SZ_16K, MX50_INT_GPIO1_LOW, MX50_INT_GPIO1_HIGH);
-	mxc_register_gpio("imx31-gpio", 1, MX50_GPIO2_BASE_ADDR, SZ_16K, MX50_INT_GPIO2_LOW, MX50_INT_GPIO2_HIGH);
-	mxc_register_gpio("imx31-gpio", 2, MX50_GPIO3_BASE_ADDR, SZ_16K, MX50_INT_GPIO3_LOW, MX50_INT_GPIO3_HIGH);
-	mxc_register_gpio("imx31-gpio", 3, MX50_GPIO4_BASE_ADDR, SZ_16K, MX50_INT_GPIO4_LOW, MX50_INT_GPIO4_HIGH);
-	mxc_register_gpio("imx31-gpio", 4, MX50_GPIO5_BASE_ADDR, SZ_16K, MX50_INT_GPIO5_LOW, MX50_INT_GPIO5_HIGH);
-	mxc_register_gpio("imx31-gpio", 5, MX50_GPIO6_BASE_ADDR, SZ_16K, MX50_INT_GPIO6_LOW, MX50_INT_GPIO6_HIGH);
+	/* i.mx50 has the i.mx35 type gpio */
+	mxc_register_gpio("imx35-gpio", 0, MX50_GPIO1_BASE_ADDR, SZ_16K, MX50_INT_GPIO1_LOW, MX50_INT_GPIO1_HIGH);
+	mxc_register_gpio("imx35-gpio", 1, MX50_GPIO2_BASE_ADDR, SZ_16K, MX50_INT_GPIO2_LOW, MX50_INT_GPIO2_HIGH);
+	mxc_register_gpio("imx35-gpio", 2, MX50_GPIO3_BASE_ADDR, SZ_16K, MX50_INT_GPIO3_LOW, MX50_INT_GPIO3_HIGH);
+	mxc_register_gpio("imx35-gpio", 3, MX50_GPIO4_BASE_ADDR, SZ_16K, MX50_INT_GPIO4_LOW, MX50_INT_GPIO4_HIGH);
+	mxc_register_gpio("imx35-gpio", 4, MX50_GPIO5_BASE_ADDR, SZ_16K, MX50_INT_GPIO5_LOW, MX50_INT_GPIO5_HIGH);
+	mxc_register_gpio("imx35-gpio", 5, MX50_GPIO6_BASE_ADDR, SZ_16K, MX50_INT_GPIO6_LOW, MX50_INT_GPIO6_HIGH);
 
 	/* i.mx50 has the i.mx31 type audmux */
 	platform_device_register_simple("imx31-audmux", 0, imx50_audmux_res,
@@ -176,11 +176,11 @@ void __init imx50_soc_init(void)
 
 void __init imx51_soc_init(void)
 {
-	/* i.mx51 has the i.mx31 type gpio */
-	mxc_register_gpio("imx31-gpio", 0, MX51_GPIO1_BASE_ADDR, SZ_16K, MX51_INT_GPIO1_LOW, MX51_INT_GPIO1_HIGH);
-	mxc_register_gpio("imx31-gpio", 1, MX51_GPIO2_BASE_ADDR, SZ_16K, MX51_INT_GPIO2_LOW, MX51_INT_GPIO2_HIGH);
-	mxc_register_gpio("imx31-gpio", 2, MX51_GPIO3_BASE_ADDR, SZ_16K, MX51_INT_GPIO3_LOW, MX51_INT_GPIO3_HIGH);
-	mxc_register_gpio("imx31-gpio", 3, MX51_GPIO4_BASE_ADDR, SZ_16K, MX51_INT_GPIO4_LOW, MX51_INT_GPIO4_HIGH);
+	/* i.mx51 has the i.mx35 type gpio */
+	mxc_register_gpio("imx35-gpio", 0, MX51_GPIO1_BASE_ADDR, SZ_16K, MX51_INT_GPIO1_LOW, MX51_INT_GPIO1_HIGH);
+	mxc_register_gpio("imx35-gpio", 1, MX51_GPIO2_BASE_ADDR, SZ_16K, MX51_INT_GPIO2_LOW, MX51_INT_GPIO2_HIGH);
+	mxc_register_gpio("imx35-gpio", 2, MX51_GPIO3_BASE_ADDR, SZ_16K, MX51_INT_GPIO3_LOW, MX51_INT_GPIO3_HIGH);
+	mxc_register_gpio("imx35-gpio", 3, MX51_GPIO4_BASE_ADDR, SZ_16K, MX51_INT_GPIO4_LOW, MX51_INT_GPIO4_HIGH);
 
 	pinctrl_provide_dummies();
 
@@ -198,14 +198,14 @@ void __init imx51_soc_init(void)
 
 void __init imx53_soc_init(void)
 {
-	/* i.mx53 has the i.mx31 type gpio */
-	mxc_register_gpio("imx31-gpio", 0, MX53_GPIO1_BASE_ADDR, SZ_16K, MX53_INT_GPIO1_LOW, MX53_INT_GPIO1_HIGH);
-	mxc_register_gpio("imx31-gpio", 1, MX53_GPIO2_BASE_ADDR, SZ_16K, MX53_INT_GPIO2_LOW, MX53_INT_GPIO2_HIGH);
-	mxc_register_gpio("imx31-gpio", 2, MX53_GPIO3_BASE_ADDR, SZ_16K, MX53_INT_GPIO3_LOW, MX53_INT_GPIO3_HIGH);
-	mxc_register_gpio("imx31-gpio", 3, MX53_GPIO4_BASE_ADDR, SZ_16K, MX53_INT_GPIO4_LOW, MX53_INT_GPIO4_HIGH);
-	mxc_register_gpio("imx31-gpio", 4, MX53_GPIO5_BASE_ADDR, SZ_16K, MX53_INT_GPIO5_LOW, MX53_INT_GPIO5_HIGH);
-	mxc_register_gpio("imx31-gpio", 5, MX53_GPIO6_BASE_ADDR, SZ_16K, MX53_INT_GPIO6_LOW, MX53_INT_GPIO6_HIGH);
-	mxc_register_gpio("imx31-gpio", 6, MX53_GPIO7_BASE_ADDR, SZ_16K, MX53_INT_GPIO7_LOW, MX53_INT_GPIO7_HIGH);
+	/* i.mx53 has the i.mx35 type gpio */
+	mxc_register_gpio("imx35-gpio", 0, MX53_GPIO1_BASE_ADDR, SZ_16K, MX53_INT_GPIO1_LOW, MX53_INT_GPIO1_HIGH);
+	mxc_register_gpio("imx35-gpio", 1, MX53_GPIO2_BASE_ADDR, SZ_16K, MX53_INT_GPIO2_LOW, MX53_INT_GPIO2_HIGH);
+	mxc_register_gpio("imx35-gpio", 2, MX53_GPIO3_BASE_ADDR, SZ_16K, MX53_INT_GPIO3_LOW, MX53_INT_GPIO3_HIGH);
+	mxc_register_gpio("imx35-gpio", 3, MX53_GPIO4_BASE_ADDR, SZ_16K, MX53_INT_GPIO4_LOW, MX53_INT_GPIO4_HIGH);
+	mxc_register_gpio("imx35-gpio", 4, MX53_GPIO5_BASE_ADDR, SZ_16K, MX53_INT_GPIO5_LOW, MX53_INT_GPIO5_HIGH);
+	mxc_register_gpio("imx35-gpio", 5, MX53_GPIO6_BASE_ADDR, SZ_16K, MX53_INT_GPIO6_LOW, MX53_INT_GPIO6_HIGH);
+	mxc_register_gpio("imx35-gpio", 6, MX53_GPIO7_BASE_ADDR, SZ_16K, MX53_INT_GPIO7_LOW, MX53_INT_GPIO7_HIGH);
 
 	pinctrl_provide_dummies();
 	/* i.mx53 has the i.mx35 type sdma */
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index f261cd242643..c9201539ffbd 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -67,6 +67,14 @@ void __init kirkwood_map_io(void)
  * CLK tree
  ****************************************************************************/
 
+static void enable_sata0(void)
+{
+	/* Enable PLL and IVREF */
+	writel(readl(SATA0_PHY_MODE_2) | 0xf, SATA0_PHY_MODE_2);
+	/* Enable PHY */
+	writel(readl(SATA0_IF_CTRL) & ~0x200, SATA0_IF_CTRL);
+}
+
 static void disable_sata0(void)
 {
 	/* Disable PLL and IVREF */
@@ -75,6 +83,14 @@ static void disable_sata0(void)
 	writel(readl(SATA0_IF_CTRL) | 0x200, SATA0_IF_CTRL);
 }
 
+static void enable_sata1(void)
+{
+	/* Enable PLL and IVREF */
+	writel(readl(SATA1_PHY_MODE_2) | 0xf, SATA1_PHY_MODE_2);
+	/* Enable PHY */
+	writel(readl(SATA1_IF_CTRL) & ~0x200, SATA1_IF_CTRL);
+}
+
 static void disable_sata1(void)
 {
 	/* Disable PLL and IVREF */
@@ -107,23 +123,38 @@ static void disable_pcie1(void)
 	}
 }
 
-/* An extended version of the gated clk. This calls fn() before
- * disabling the clock. We use this to turn off PHYs etc. */
+/* An extended version of the gated clk. This calls fn_en()/fn_dis
+ * before enabling/disabling the clock.  We use this to turn on/off
+ * PHYs etc.  */
 struct clk_gate_fn {
 	struct clk_gate gate;
-	void (*fn)(void);
+	void (*fn_en)(void);
+	void (*fn_dis)(void);
 };
 
 #define to_clk_gate_fn(_gate) container_of(_gate, struct clk_gate_fn, gate)
 #define to_clk_gate(_hw) container_of(_hw, struct clk_gate, hw)
 
+static int clk_gate_fn_enable(struct clk_hw *hw)
+{
+	struct clk_gate *gate = to_clk_gate(hw);
+	struct clk_gate_fn *gate_fn = to_clk_gate_fn(gate);
+	int ret;
+
+	ret = clk_gate_ops.enable(hw);
+	if (!ret && gate_fn->fn_en)
+		gate_fn->fn_en();
+
+	return ret;
+}
+
 static void clk_gate_fn_disable(struct clk_hw *hw)
 {
 	struct clk_gate *gate = to_clk_gate(hw);
 	struct clk_gate_fn *gate_fn = to_clk_gate_fn(gate);
 
-	if (gate_fn->fn)
-		gate_fn->fn();
+	if (gate_fn->fn_dis)
+		gate_fn->fn_dis();
 
 	clk_gate_ops.disable(hw);
 }
@@ -135,7 +166,7 @@ static struct clk __init *clk_register_gate_fn(struct device *dev,
 		const char *parent_name, unsigned long flags,
 		void __iomem *reg, u8 bit_idx,
 		u8 clk_gate_flags, spinlock_t *lock,
-		void (*fn)(void))
+		void (*fn_en)(void), void (*fn_dis)(void))
 {
 	struct clk_gate_fn *gate_fn;
 	struct clk *clk;
@@ -159,11 +190,14 @@ static struct clk __init *clk_register_gate_fn(struct device *dev,
 	gate_fn->gate.flags = clk_gate_flags;
 	gate_fn->gate.lock = lock;
 	gate_fn->gate.hw.init = &init;
-	gate_fn->fn = fn;
+	gate_fn->fn_en = fn_en;
+	gate_fn->fn_dis = fn_dis;
 
-	/* ops is the gate ops, but with our disable function */
-	if (clk_gate_fn_ops.disable != clk_gate_fn_disable) {
+	/* ops is the gate ops, but with our enable/disable functions */
+	if (clk_gate_fn_ops.enable != clk_gate_fn_enable ||
+	    clk_gate_fn_ops.disable != clk_gate_fn_disable) {
 		clk_gate_fn_ops = clk_gate_ops;
+		clk_gate_fn_ops.enable = clk_gate_fn_enable;
 		clk_gate_fn_ops.disable = clk_gate_fn_disable;
 	}
 
@@ -187,11 +221,12 @@ static struct clk __init *kirkwood_register_gate(const char *name, u8 bit_idx)
 
 static struct clk __init *kirkwood_register_gate_fn(const char *name,
 						    u8 bit_idx,
-						    void (*fn)(void))
+						    void (*fn_en)(void),
+						    void (*fn_dis)(void))
 {
 	return clk_register_gate_fn(NULL, name, "tclk", 0,
 				    (void __iomem *)CLOCK_GATING_CTRL,
-				    bit_idx, 0, &gating_lock, fn);
+				    bit_idx, 0, &gating_lock, fn_en, fn_dis);
 }
 
 static struct clk *ge0, *ge1;
@@ -208,18 +243,18 @@ void __init kirkwood_clk_init(void)
 	ge0 = kirkwood_register_gate("ge0",    CGC_BIT_GE0);
 	ge1 = kirkwood_register_gate("ge1",    CGC_BIT_GE1);
 	sata0 = kirkwood_register_gate_fn("sata0",  CGC_BIT_SATA0,
-					  disable_sata0);
+					  enable_sata0, disable_sata0);
 	sata1 = kirkwood_register_gate_fn("sata1",  CGC_BIT_SATA1,
-					  disable_sata1);
+					  enable_sata1, disable_sata1);
 	usb0 = kirkwood_register_gate("usb0",   CGC_BIT_USB0);
 	sdio = kirkwood_register_gate("sdio",   CGC_BIT_SDIO);
 	crypto = kirkwood_register_gate("crypto", CGC_BIT_CRYPTO);
 	xor0 = kirkwood_register_gate("xor0",   CGC_BIT_XOR0);
 	xor1 = kirkwood_register_gate("xor1",   CGC_BIT_XOR1);
 	pex0 = kirkwood_register_gate_fn("pex0",   CGC_BIT_PEX0,
-					 disable_pcie0);
+					 NULL, disable_pcie0);
 	pex1 = kirkwood_register_gate_fn("pex1",   CGC_BIT_PEX1,
-					 disable_pcie1);
+					 NULL, disable_pcie1);
 	audio = kirkwood_register_gate("audio",  CGC_BIT_AUDIO);
 	kirkwood_register_gate("tdm",    CGC_BIT_TDM);
 	kirkwood_register_gate("tsu",    CGC_BIT_TSU);
@@ -241,6 +276,11 @@ void __init kirkwood_clk_init(void)
 	orion_clkdev_add("0", "pcie", pex0);
 	orion_clkdev_add("1", "pcie", pex1);
 	orion_clkdev_add(NULL, "kirkwood-i2s", audio);
+
+	/* Marvell says runit is used by SPI, UART, NAND, TWSI, ...,
+	 * so should never be gated.
+	 */
+	clk_prepare_enable(runit);
 }
 
 /*****************************************************************************
diff --git a/arch/arm/mach-msm/platsmp.c b/arch/arm/mach-msm/platsmp.c
index db0117ec55f4..e012dc8391cf 100644
--- a/arch/arm/mach-msm/platsmp.c
+++ b/arch/arm/mach-msm/platsmp.c
@@ -127,7 +127,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * the boot monitor to read the system wide flags register,
 	 * and branch to the address found there.
 	 */
-	gic_raise_softirq(cpumask_of(cpu), 1);
+	gic_raise_softirq(cpumask_of(cpu), 0);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
diff --git a/arch/arm/mach-mxs/mach-mxs.c b/arch/arm/mach-mxs/mach-mxs.c
index 648bdd05d38b..8dabfe81d07c 100644
--- a/arch/arm/mach-mxs/mach-mxs.c
+++ b/arch/arm/mach-mxs/mach-mxs.c
@@ -162,7 +162,7 @@ enum mac_oui {
 static void __init update_fec_mac_prop(enum mac_oui oui)
 {
 	struct device_node *np, *from = NULL;
-	struct property *oldmac, *newmac;
+	struct property *newmac;
 	const u32 *ocotp = mxs_get_ocotp();
 	u8 *macaddr;
 	u32 val;
@@ -208,11 +208,7 @@ static void __init update_fec_mac_prop(enum mac_oui oui)
 		macaddr[4] = (val >> 8) & 0xff;
 		macaddr[5] = (val >> 0) & 0xff;
 
-		oldmac = of_find_property(np, newmac->name, NULL);
-		if (oldmac)
-			prom_update_property(np, newmac, oldmac);
-		else
-			prom_add_property(np, newmac);
+		prom_update_property(np, newmac);
 	}
 }
 
diff --git a/arch/arm/mach-netx/fb.c b/arch/arm/mach-netx/fb.c
index 2cdf6ef69bee..d122ee6ab991 100644
--- a/arch/arm/mach-netx/fb.c
+++ b/arch/arm/mach-netx/fb.c
@@ -69,29 +69,6 @@ void netx_clcd_remove(struct clcd_fb *fb)
 			      fb->fb.screen_base, fb->fb.fix.smem_start);
 }
 
-void clk_disable(struct clk *clk)
-{
-}
-
-int clk_set_rate(struct clk *clk, unsigned long rate)
-{
-	return 0;
-}
-
-int clk_enable(struct clk *clk)
-{
-	return 0;
-}
-
-struct clk *clk_get(struct device *dev, const char *id)
-{
-	return dev && strcmp(dev_name(dev), "fb") == 0 ? NULL : ERR_PTR(-ENOENT);
-}
-
-void clk_put(struct clk *clk)
-{
-}
-
 static AMBA_AHB_DEVICE(fb, "fb", 0, 0x00104000, { NETX_IRQ_LCD }, NULL);
 
 int netx_fb_init(struct clcd_board *board, struct clcd_panel *panel)
diff --git a/arch/arm/mach-omap1/board-palmz71.c b/arch/arm/mach-omap1/board-palmz71.c
index cc71a26723ef..355980321c2d 100644
--- a/arch/arm/mach-omap1/board-palmz71.c
+++ b/arch/arm/mach-omap1/board-palmz71.c
@@ -288,8 +288,7 @@ palmz71_gpio_setup(int early)
 		}
 		gpio_direction_input(PALMZ71_USBDETECT_GPIO);
 		if (request_irq(gpio_to_irq(PALMZ71_USBDETECT_GPIO),
-				palmz71_powercable, IRQF_SAMPLE_RANDOM,
-				"palmz71-cable", NULL))
+				palmz71_powercable, 0, "palmz71-cable", NULL))
 			printk(KERN_ERR
 					"IRQ request for power cable failed!\n");
 		palmz71_powercable(gpio_to_irq(PALMZ71_USBDETECT_GPIO), NULL);
diff --git a/arch/arm/mach-omap2/clock3xxx_data.c b/arch/arm/mach-omap2/clock3xxx_data.c
index 91b3d5c60bfe..83bed9ad3017 100644
--- a/arch/arm/mach-omap2/clock3xxx_data.c
+++ b/arch/arm/mach-omap2/clock3xxx_data.c
@@ -3376,15 +3376,15 @@ static struct omap_clk omap3xxx_clks[] = {
 	CLK(NULL,	"usbhost_48m_fck", &usbhost_48m_fck, CK_3430ES2PLUS | CK_AM35XX | CK_36XX),
 	CLK(NULL,	"usbhost_ick",	&usbhost_ick,	CK_3430ES2PLUS | CK_AM35XX | CK_36XX),
 	CLK("usbhs_omap",	"usbhost_ick",	&usbhost_ick,	CK_3430ES2PLUS | CK_AM35XX | CK_36XX),
-	CLK("usbhs_omap",	"utmi_p1_gfclk",	&dummy_ck,	CK_3XXX),
-	CLK("usbhs_omap",	"utmi_p2_gfclk",	&dummy_ck,	CK_3XXX),
-	CLK("usbhs_omap",	"xclk60mhsp1_ck",	&dummy_ck,	CK_3XXX),
-	CLK("usbhs_omap",	"xclk60mhsp2_ck",	&dummy_ck,	CK_3XXX),
-	CLK("usbhs_omap",	"usb_host_hs_utmi_p1_clk",	&dummy_ck,	CK_3XXX),
-	CLK("usbhs_omap",	"usb_host_hs_utmi_p2_clk",	&dummy_ck,	CK_3XXX),
+	CLK(NULL,	"utmi_p1_gfclk",	&dummy_ck,	CK_3XXX),
+	CLK(NULL,	"utmi_p2_gfclk",	&dummy_ck,	CK_3XXX),
+	CLK(NULL,	"xclk60mhsp1_ck",	&dummy_ck,	CK_3XXX),
+	CLK(NULL,	"xclk60mhsp2_ck",	&dummy_ck,	CK_3XXX),
+	CLK(NULL,	"usb_host_hs_utmi_p1_clk",	&dummy_ck,	CK_3XXX),
+	CLK(NULL,	"usb_host_hs_utmi_p2_clk",	&dummy_ck,	CK_3XXX),
 	CLK("usbhs_omap",	"usb_tll_hs_usb_ch0_clk",	&dummy_ck,	CK_3XXX),
 	CLK("usbhs_omap",	"usb_tll_hs_usb_ch1_clk",	&dummy_ck,	CK_3XXX),
-	CLK("usbhs_omap",	"init_60m_fclk",	&dummy_ck,	CK_3XXX),
+	CLK(NULL,	"init_60m_fclk",	&dummy_ck,	CK_3XXX),
 	CLK(NULL,	"usim_fck",	&usim_fck,	CK_3430ES2PLUS | CK_36XX),
 	CLK(NULL,	"gpt1_fck",	&gpt1_fck,	CK_3XXX),
 	CLK(NULL,	"wkup_32k_fck",	&wkup_32k_fck,	CK_3XXX),
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 7d118b9bdd5f..9a35adf91232 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -125,7 +125,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 		booted = true;
 	}
 
-	gic_raise_softirq(cpumask_of(cpu), 1);
+	gic_raise_softirq(cpumask_of(cpu), 0);
 
 	/*
 	 * Now the secondary core is starting up let it run its
diff --git a/arch/arm/mach-pxa/eseries.h b/arch/arm/mach-pxa/eseries.h
deleted file mode 100644
index b96949dd5adb..000000000000
--- a/arch/arm/mach-pxa/eseries.h
+++ /dev/null
@@ -1,14 +0,0 @@
-void __init eseries_fixup(struct tag *tags, char **cmdline, struct meminfo *mi);
-
-extern struct pxa2xx_udc_mach_info e7xx_udc_mach_info;
-extern struct pxaficp_platform_data e7xx_ficp_platform_data;
-extern int e7xx_irda_init(void);
-
-extern int eseries_tmio_enable(struct platform_device *dev);
-extern int eseries_tmio_disable(struct platform_device *dev);
-extern int eseries_tmio_suspend(struct platform_device *dev);
-extern int eseries_tmio_resume(struct platform_device *dev);
-extern void eseries_get_tmio_gpios(void);
-extern struct resource eseries_tmio_resources[];
-extern struct platform_device e300_tc6387xb_device;
-
diff --git a/arch/arm/mach-pxa/hx4700.c b/arch/arm/mach-pxa/hx4700.c
index d3de84b0dcbe..e6311988add2 100644
--- a/arch/arm/mach-pxa/hx4700.c
+++ b/arch/arm/mach-pxa/hx4700.c
@@ -296,27 +296,11 @@ static struct asic3_led asic3_leds[ASIC3_NUM_LEDS] = {
 
 static struct resource asic3_resources[] = {
 	/* GPIO part */
-	[0] = {
-		.start	= ASIC3_PHYS,
-		.end	= ASIC3_PHYS + ASIC3_MAP_SIZE_16BIT - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[1] = {
-		.start	= PXA_GPIO_TO_IRQ(GPIO12_HX4700_ASIC3_IRQ),
-		.end	= PXA_GPIO_TO_IRQ(GPIO12_HX4700_ASIC3_IRQ),
-		.flags	= IORESOURCE_IRQ,
-	},
+	[0] = DEFINE_RES_MEM(ASIC3_PHYS, ASIC3_MAP_SIZE_16BIT),
+	[1] = DEFINE_RES_IRQ(PXA_GPIO_TO_IRQ(GPIO12_HX4700_ASIC3_IRQ)),
 	/* SD part */
-	[2] = {
-		.start	= ASIC3_SD_PHYS,
-		.end	= ASIC3_SD_PHYS + ASIC3_MAP_SIZE_16BIT - 1,
-		.flags	= IORESOURCE_MEM,
-	},
-	[3] = {
-		.start	= PXA_GPIO_TO_IRQ(GPIO66_HX4700_ASIC3_nSDIO_IRQ),
-		.end	= PXA_GPIO_TO_IRQ(GPIO66_HX4700_ASIC3_nSDIO_IRQ),
-		.flags	= IORESOURCE_IRQ,
-	},
+	[2] = DEFINE_RES_MEM(ASIC3_SD_PHYS, ASIC3_MAP_SIZE_16BIT),
+	[3] = DEFINE_RES_IRQ(PXA_GPIO_TO_IRQ(GPIO66_HX4700_ASIC3_nSDIO_IRQ)),
 };
 
 static struct asic3_platform_data asic3_platform_data = {
@@ -343,11 +327,7 @@ static struct platform_device asic3 = {
  */
 
 static struct resource egpio_resources[] = {
-	[0] = {
-		.start = PXA_CS5_PHYS,
-		.end   = PXA_CS5_PHYS + 0x4 - 1,
-		.flags = IORESOURCE_MEM,
-	},
+	[0] = DEFINE_RES_MEM(PXA_CS5_PHYS, 0x4),
 };
 
 static struct htc_egpio_chip egpio_chips[] = {
@@ -537,11 +517,7 @@ static struct w100fb_mach_info w3220_info = {
 };
 
 static struct resource w3220_resources[] = {
-	[0] = {
-		.start	= ATI_W3220_PHYS,
-		.end	= ATI_W3220_PHYS + 0x00ffffff,
-		.flags	= IORESOURCE_MEM,
-	},
+	[0] = DEFINE_RES_MEM(ATI_W3220_PHYS, SZ_16M),
 };
 
 static struct platform_device w3220 = {
@@ -683,20 +659,12 @@ static struct pda_power_pdata power_supply_info = {
 };
 
 static struct resource power_supply_resources[] = {
-	[0] = {
-		.name  = "ac",
-		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE |
-		         IORESOURCE_IRQ_LOWEDGE,
-		.start = PXA_GPIO_TO_IRQ(GPIOD9_nAC_IN),
-		.end   = PXA_GPIO_TO_IRQ(GPIOD9_nAC_IN),
-	},
-	[1] = {
-		.name  = "usb",
-		.flags = IORESOURCE_IRQ | IORESOURCE_IRQ_HIGHEDGE |
-		         IORESOURCE_IRQ_LOWEDGE,
-		.start = PXA_GPIO_TO_IRQ(GPIOD14_nUSBC_DETECT),
-		.end   = PXA_GPIO_TO_IRQ(GPIOD14_nUSBC_DETECT),
-	},
+	[0] = DEFINE_RES_NAMED(PXA_GPIO_TO_IRQ(GPIOD9_nAC_IN), 1, "ac",
+		IORESOURCE_IRQ |
+		IORESOURCE_IRQ_HIGHEDGE | IORESOURCE_IRQ_LOWEDGE),
+	[1] = DEFINE_RES_NAMED(PXA_GPIO_TO_IRQ(GPIOD14_nUSBC_DETECT), 1, "usb",
+		IORESOURCE_IRQ |
+		IORESOURCE_IRQ_HIGHEDGE | IORESOURCE_IRQ_LOWEDGE),
 };
 
 static struct platform_device power_supply = {
diff --git a/arch/arm/mach-pxa/include/mach/regs-ost.h b/arch/arm/mach-pxa/include/mach/regs-ost.h
index a3e5f86ef67e..628819995c52 100644
--- a/arch/arm/mach-pxa/include/mach/regs-ost.h
+++ b/arch/arm/mach-pxa/include/mach/regs-ost.h
@@ -7,17 +7,17 @@
  * OS Timer & Match Registers
  */
 
-#define OSMR0		__REG(0x40A00000)  /* */
-#define OSMR1		__REG(0x40A00004)  /* */
-#define OSMR2		__REG(0x40A00008)  /* */
-#define OSMR3		__REG(0x40A0000C)  /* */
-#define OSMR4		__REG(0x40A00080)  /* */
-#define OSCR		__REG(0x40A00010)  /* OS Timer Counter Register */
-#define OSCR4		__REG(0x40A00040)  /* OS Timer Counter Register */
-#define OMCR4		__REG(0x40A000C0)  /* */
-#define OSSR		__REG(0x40A00014)  /* OS Timer Status Register */
-#define OWER		__REG(0x40A00018)  /* OS Timer Watchdog Enable Register */
-#define OIER		__REG(0x40A0001C)  /* OS Timer Interrupt Enable Register */
+#define OSMR0		io_p2v(0x40A00000)  /* */
+#define OSMR1		io_p2v(0x40A00004)  /* */
+#define OSMR2		io_p2v(0x40A00008)  /* */
+#define OSMR3		io_p2v(0x40A0000C)  /* */
+#define OSMR4		io_p2v(0x40A00080)  /* */
+#define OSCR		io_p2v(0x40A00010)  /* OS Timer Counter Register */
+#define OSCR4		io_p2v(0x40A00040)  /* OS Timer Counter Register */
+#define OMCR4		io_p2v(0x40A000C0)  /* */
+#define OSSR		io_p2v(0x40A00014)  /* OS Timer Status Register */
+#define OWER		io_p2v(0x40A00018)  /* OS Timer Watchdog Enable Register */
+#define OIER		io_p2v(0x40A0001C)  /* OS Timer Interrupt Enable Register */
 
 #define OSSR_M3		(1 << 3)	/* Match status channel 3 */
 #define OSSR_M2		(1 << 2)	/* Match status channel 2 */
diff --git a/arch/arm/mach-pxa/lubbock.c b/arch/arm/mach-pxa/lubbock.c
index 6bb3f47b1f14..0ca0db787903 100644
--- a/arch/arm/mach-pxa/lubbock.c
+++ b/arch/arm/mach-pxa/lubbock.c
@@ -456,7 +456,7 @@ static int lubbock_mci_init(struct device *dev,
 	init_timer(&mmc_timer);
 	mmc_timer.data = (unsigned long) data;
 	return request_irq(LUBBOCK_SD_IRQ, lubbock_detect_int,
-			IRQF_SAMPLE_RANDOM, "lubbock-sd-detect", data);
+			   0, "lubbock-sd-detect", data);
 }
 
 static int lubbock_mci_get_ro(struct device *dev)
diff --git a/arch/arm/mach-pxa/magician.c b/arch/arm/mach-pxa/magician.c
index 2db697cd2b4e..39561dcf65f2 100644
--- a/arch/arm/mach-pxa/magician.c
+++ b/arch/arm/mach-pxa/magician.c
@@ -633,9 +633,8 @@ static struct platform_device bq24022 = {
 static int magician_mci_init(struct device *dev,
 				irq_handler_t detect_irq, void *data)
 {
-	return request_irq(IRQ_MAGICIAN_SD, detect_irq,
-				IRQF_DISABLED | IRQF_SAMPLE_RANDOM,
-				"mmc card detect", data);
+	return request_irq(IRQ_MAGICIAN_SD, detect_irq, IRQF_DISABLED,
+			   "mmc card detect", data);
 }
 
 static void magician_mci_exit(struct device *dev, void *data)
diff --git a/arch/arm/mach-pxa/reset.c b/arch/arm/mach-pxa/reset.c
index b4528899ef08..3fab583755d4 100644
--- a/arch/arm/mach-pxa/reset.c
+++ b/arch/arm/mach-pxa/reset.c
@@ -77,9 +77,10 @@ static void do_gpio_reset(void)
 static void do_hw_reset(void)
 {
 	/* Initialize the watchdog and let it fire */
-	OWER = OWER_WME;
-	OSSR = OSSR_M3;
-	OSMR3 = OSCR + 368640;	/* ... in 100 ms */
+	writel_relaxed(OWER_WME, OWER);
+	writel_relaxed(OSSR_M3, OSSR);
+	/* ... in 100 ms */
+	writel_relaxed(readl_relaxed(OSCR) + 368640, OSMR3);
 }
 
 void pxa_restart(char mode, const char *cmd)
diff --git a/arch/arm/mach-pxa/time.c b/arch/arm/mach-pxa/time.c
index 3d6c9bd90de6..4bc47d63698b 100644
--- a/arch/arm/mach-pxa/time.c
+++ b/arch/arm/mach-pxa/time.c
@@ -35,7 +35,7 @@
 
 static u32 notrace pxa_read_sched_clock(void)
 {
-	return OSCR;
+	return readl_relaxed(OSCR);
 }
 
 
@@ -47,8 +47,8 @@ pxa_ost0_interrupt(int irq, void *dev_id)
 	struct clock_event_device *c = dev_id;
 
 	/* Disarm the compare/match, signal the event. */
-	OIER &= ~OIER_E0;
-	OSSR = OSSR_M0;
+	writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER);
+	writel_relaxed(OSSR_M0, OSSR);
 	c->event_handler(c);
 
 	return IRQ_HANDLED;
@@ -59,10 +59,10 @@ pxa_osmr0_set_next_event(unsigned long delta, struct clock_event_device *dev)
 {
 	unsigned long next, oscr;
 
-	OIER |= OIER_E0;
-	next = OSCR + delta;
-	OSMR0 = next;
-	oscr = OSCR;
+	writel_relaxed(readl_relaxed(OIER) | OIER_E0, OIER);
+	next = readl_relaxed(OSCR) + delta;
+	writel_relaxed(next, OSMR0);
+	oscr = readl_relaxed(OSCR);
 
 	return (signed)(next - oscr) <= MIN_OSCR_DELTA ? -ETIME : 0;
 }
@@ -72,15 +72,15 @@ pxa_osmr0_set_mode(enum clock_event_mode mode, struct clock_event_device *dev)
 {
 	switch (mode) {
 	case CLOCK_EVT_MODE_ONESHOT:
-		OIER &= ~OIER_E0;
-		OSSR = OSSR_M0;
+		writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER);
+		writel_relaxed(OSSR_M0, OSSR);
 		break;
 
 	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
 		/* initializing, released, or preparing for suspend */
-		OIER &= ~OIER_E0;
-		OSSR = OSSR_M0;
+		writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER);
+		writel_relaxed(OSSR_M0, OSSR);
 		break;
 
 	case CLOCK_EVT_MODE_RESUME:
@@ -108,8 +108,8 @@ static void __init pxa_timer_init(void)
 {
 	unsigned long clock_tick_rate = get_clock_tick_rate();
 
-	OIER = 0;
-	OSSR = OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3;
+	writel_relaxed(0, OIER);
+	writel_relaxed(OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3, OSSR);
 
 	setup_sched_clock(pxa_read_sched_clock, 32, clock_tick_rate);
 
@@ -122,7 +122,7 @@ static void __init pxa_timer_init(void)
 
 	setup_irq(IRQ_OST0, &pxa_ost0_irq);
 
-	clocksource_mmio_init(&OSCR, "oscr0", clock_tick_rate, 200, 32,
+	clocksource_mmio_init(OSCR, "oscr0", clock_tick_rate, 200, 32,
 		clocksource_mmio_readl_up);
 	clockevents_register_device(&ckevt_pxa_osmr0);
 }
@@ -132,12 +132,12 @@ static unsigned long osmr[4], oier, oscr;
 
 static void pxa_timer_suspend(void)
 {
-	osmr[0] = OSMR0;
-	osmr[1] = OSMR1;
-	osmr[2] = OSMR2;
-	osmr[3] = OSMR3;
-	oier = OIER;
-	oscr = OSCR;
+	osmr[0] = readl_relaxed(OSMR0);
+	osmr[1] = readl_relaxed(OSMR1);
+	osmr[2] = readl_relaxed(OSMR2);
+	osmr[3] = readl_relaxed(OSMR3);
+	oier = readl_relaxed(OIER);
+	oscr = readl_relaxed(OSCR);
 }
 
 static void pxa_timer_resume(void)
@@ -151,12 +151,12 @@ static void pxa_timer_resume(void)
 	if (osmr[0] - oscr < MIN_OSCR_DELTA)
 		osmr[0] += MIN_OSCR_DELTA;
 
-	OSMR0 = osmr[0];
-	OSMR1 = osmr[1];
-	OSMR2 = osmr[2];
-	OSMR3 = osmr[3];
-	OIER = oier;
-	OSCR = oscr;
+	writel_relaxed(osmr[0], OSMR0);
+	writel_relaxed(osmr[1], OSMR1);
+	writel_relaxed(osmr[2], OSMR2);
+	writel_relaxed(osmr[3], OSMR3);
+	writel_relaxed(oier, OIER);
+	writel_relaxed(oscr, OSCR);
 }
 #else
 #define pxa_timer_suspend NULL
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index 2b6ac00b2cd9..166dd32cc1d3 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -332,8 +332,8 @@ static int trizeps4_mci_init(struct device *dev, irq_handler_t mci_detect_int,
 	int err;
 
 	err = request_irq(TRIZEPS4_MMC_IRQ, mci_detect_int,
-		IRQF_DISABLED | IRQF_TRIGGER_RISING | IRQF_SAMPLE_RANDOM,
-		"MMC card detect", data);
+			  IRQF_DISABLED | IRQF_TRIGGER_RISING,
+			  "MMC card detect", data);
 	if (err) {
 		printk(KERN_ERR "trizeps4_mci_init: MMC/SD: can't request"
 						"MMC card detect IRQ\n");
diff --git a/arch/arm/mach-s3c64xx/include/mach/pm-core.h b/arch/arm/mach-s3c64xx/include/mach/pm-core.h
index fcf3dcabb694..c0537f40a3d8 100644
--- a/arch/arm/mach-s3c64xx/include/mach/pm-core.h
+++ b/arch/arm/mach-s3c64xx/include/mach/pm-core.h
@@ -12,6 +12,9 @@
  * published by the Free Software Foundation.
  */
 
+#ifndef __MACH_S3C64XX_PM_CORE_H
+#define __MACH_S3C64XX_PM_CORE_H __FILE__
+
 #include <mach/regs-gpio.h>
 
 static inline void s3c_pm_debug_init_uart(void)
@@ -113,3 +116,4 @@ static inline void samsung_pm_saved_gpios(void)
 
 	__raw_writel(S3C64XX_SLPEN_USE_xSLP, S3C64XX_SLPEN);
 }
+#endif /* __MACH_S3C64XX_PM_CORE_H */
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index d1dc7f1a239c..d673211f121c 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -362,7 +362,7 @@ static void __init assabet_init(void)
 static void __init map_sa1100_gpio_regs( void )
 {
 	unsigned long phys = __PREG(GPLR) & PMD_MASK;
-	unsigned long virt = io_p2v(phys);
+	unsigned long virt = (unsigned long)io_p2v(phys);
 	int prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_DOMAIN(DOMAIN_IO);
 	pmd_t *pmd;
 
diff --git a/arch/arm/mach-sa1100/cpu-sa1100.c b/arch/arm/mach-sa1100/cpu-sa1100.c
index 19b2053f5af4..e8f4d1e19233 100644
--- a/arch/arm/mach-sa1100/cpu-sa1100.c
+++ b/arch/arm/mach-sa1100/cpu-sa1100.c
@@ -87,6 +87,7 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/cpufreq.h>
+#include <linux/io.h>
 
 #include <asm/cputype.h>
 
diff --git a/arch/arm/mach-sa1100/cpu-sa1110.c b/arch/arm/mach-sa1100/cpu-sa1110.c
index 675bf8ef97e8..48c45b0c92bb 100644
--- a/arch/arm/mach-sa1100/cpu-sa1110.c
+++ b/arch/arm/mach-sa1100/cpu-sa1110.c
@@ -19,6 +19,7 @@
 #include <linux/cpufreq.h>
 #include <linux/delay.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/moduleparam.h>
 #include <linux/types.h>
diff --git a/arch/arm/mach-sa1100/include/mach/SA-1100.h b/arch/arm/mach-sa1100/include/mach/SA-1100.h
index 3f2d1b60188c..0ac6cc08a19c 100644
--- a/arch/arm/mach-sa1100/include/mach/SA-1100.h
+++ b/arch/arm/mach-sa1100/include/mach/SA-1100.h
@@ -830,14 +830,14 @@
  *              	(read/write).
  */
 
-#define OSMR0  		__REG(0x90000000)  /* OS timer Match Reg. 0 */
-#define OSMR1  		__REG(0x90000004)  /* OS timer Match Reg. 1 */
-#define OSMR2  		__REG(0x90000008)  /* OS timer Match Reg. 2 */
-#define OSMR3  		__REG(0x9000000c)  /* OS timer Match Reg. 3 */
-#define OSCR   	__REG(0x90000010)  /* OS timer Counter Reg. */
-#define OSSR   	__REG(0x90000014	)  /* OS timer Status Reg. */
-#define OWER   	__REG(0x90000018	)  /* OS timer Watch-dog Enable Reg. */
-#define OIER   	__REG(0x9000001C	)  /* OS timer Interrupt Enable Reg. */
+#define OSMR0  		io_p2v(0x90000000)  /* OS timer Match Reg. 0 */
+#define OSMR1  		io_p2v(0x90000004)  /* OS timer Match Reg. 1 */
+#define OSMR2  		io_p2v(0x90000008)  /* OS timer Match Reg. 2 */
+#define OSMR3  		io_p2v(0x9000000c)  /* OS timer Match Reg. 3 */
+#define OSCR   		io_p2v(0x90000010)  /* OS timer Counter Reg. */
+#define OSSR   		io_p2v(0x90000014)  /* OS timer Status Reg. */
+#define OWER   		io_p2v(0x90000018)  /* OS timer Watch-dog Enable Reg. */
+#define OIER  	 	io_p2v(0x9000001C)  /* OS timer Interrupt Enable Reg. */
 
 #define OSSR_M(Nb)	        	/* Match detected [0..3]           */ \
                 	(0x00000001 << (Nb))
diff --git a/arch/arm/mach-sa1100/include/mach/gpio.h b/arch/arm/mach-sa1100/include/mach/gpio.h
index a38fc4f54241..6a9eecf3137e 100644
--- a/arch/arm/mach-sa1100/include/mach/gpio.h
+++ b/arch/arm/mach-sa1100/include/mach/gpio.h
@@ -24,6 +24,7 @@
 #ifndef __ASM_ARCH_SA1100_GPIO_H
 #define __ASM_ARCH_SA1100_GPIO_H
 
+#include <linux/io.h>
 #include <mach/hardware.h>
 #include <asm/irq.h>
 #include <asm-generic/gpio.h>
diff --git a/arch/arm/mach-sa1100/include/mach/hardware.h b/arch/arm/mach-sa1100/include/mach/hardware.h
index 99f5856d8de4..cbedd75a9d65 100644
--- a/arch/arm/mach-sa1100/include/mach/hardware.h
+++ b/arch/arm/mach-sa1100/include/mach/hardware.h
@@ -32,7 +32,7 @@
 #define PIO_START       0x80000000	/* physical start of IO space */
 
 #define io_p2v( x )             \
-   ( (((x)&0x00ffffff) | (((x)&0x30000000)>>VIO_SHIFT)) + VIO_BASE )
+   IOMEM( (((x)&0x00ffffff) | (((x)&0x30000000)>>VIO_SHIFT)) + VIO_BASE )
 #define io_v2p( x )             \
    ( (((x)&0x00ffffff) | (((x)&(0x30000000>>VIO_SHIFT))<<VIO_SHIFT)) + PIO_START )
 
@@ -47,6 +47,8 @@
 #define CPU_SA1110_ID	(0x6901b110)
 #define CPU_SA1110_MASK	(0xfffffff0)
 
+#define __MREG(x)	IOMEM(io_p2v(x))
+
 #ifndef __ASSEMBLY__
 
 #include <asm/cputype.h>
@@ -56,7 +58,7 @@
 #define cpu_is_sa1100()	((read_cpuid_id() & CPU_SA1100_MASK) == CPU_SA1100_ID)
 #define cpu_is_sa1110()	((read_cpuid_id() & CPU_SA1110_MASK) == CPU_SA1110_ID)
 
-# define __REG(x)	(*((volatile unsigned long *)io_p2v(x)))
+# define __REG(x)	(*((volatile unsigned long __iomem *)io_p2v(x)))
 # define __PREG(x)	(io_v2p((unsigned long)&(x)))
 
 static inline unsigned long get_clock_tick_rate(void)
diff --git a/arch/arm/mach-sa1100/include/mach/uncompress.h b/arch/arm/mach-sa1100/include/mach/uncompress.h
index 6cb39ddde656..5cf71da60e42 100644
--- a/arch/arm/mach-sa1100/include/mach/uncompress.h
+++ b/arch/arm/mach-sa1100/include/mach/uncompress.h
@@ -8,6 +8,8 @@
 
 #include "hardware.h"
 
+#define IOMEM(x)	(x)
+
 /*
  * The following code assumes the serial port has already been
  * initialized by the bootloader.  We search for the first enabled
diff --git a/arch/arm/mach-sa1100/irq.c b/arch/arm/mach-sa1100/irq.c
index 516ccc25d7fd..2124f1fc2fbe 100644
--- a/arch/arm/mach-sa1100/irq.c
+++ b/arch/arm/mach-sa1100/irq.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
+#include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/ioport.h>
 #include <linux/syscore_ops.h>
diff --git a/arch/arm/mach-sa1100/jornada720_ssp.c b/arch/arm/mach-sa1100/jornada720_ssp.c
index b412fc09c80c..7f07f08d8968 100644
--- a/arch/arm/mach-sa1100/jornada720_ssp.c
+++ b/arch/arm/mach-sa1100/jornada720_ssp.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/sched.h>
+#include <linux/io.h>
 
 #include <mach/hardware.h>
 #include <mach/jornada720.h>
diff --git a/arch/arm/mach-sa1100/leds-cerf.c b/arch/arm/mach-sa1100/leds-cerf.c
index 040540fb7d8a..30fc3b2bf555 100644
--- a/arch/arm/mach-sa1100/leds-cerf.c
+++ b/arch/arm/mach-sa1100/leds-cerf.c
@@ -4,6 +4,7 @@
  * Author: ???
  */
 #include <linux/init.h>
+#include <linux/io.h>
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
diff --git a/arch/arm/mach-sa1100/leds-lart.c b/arch/arm/mach-sa1100/leds-lart.c
index a51830c60e53..50a5b143b460 100644
--- a/arch/arm/mach-sa1100/leds-lart.c
+++ b/arch/arm/mach-sa1100/leds-lart.c
@@ -10,6 +10,7 @@
  *  pace of the LED.
  */
 #include <linux/init.h>
+#include <linux/io.h>
 
 #include <mach/hardware.h>
 #include <asm/leds.h>
diff --git a/arch/arm/mach-sa1100/pm.c b/arch/arm/mach-sa1100/pm.c
index 690cf0ce5c0c..6645d1e31f14 100644
--- a/arch/arm/mach-sa1100/pm.c
+++ b/arch/arm/mach-sa1100/pm.c
@@ -23,6 +23,7 @@
  * 				Storage is local on the stack now.
  */
 #include <linux/init.h>
+#include <linux/io.h>
 #include <linux/suspend.h>
 #include <linux/errno.h>
 #include <linux/time.h>
diff --git a/arch/arm/mach-sa1100/sleep.S b/arch/arm/mach-sa1100/sleep.S
index 30cc6721665b..85863741ef8b 100644
--- a/arch/arm/mach-sa1100/sleep.S
+++ b/arch/arm/mach-sa1100/sleep.S
@@ -38,9 +38,9 @@ ENTRY(sa1100_finish_suspend)
 	orr     r4, r4, #MDREFR_K1DB2
 	ldr	r5, =PPCR
 
-	@ Pre-load __udelay into the I-cache
+	@ Pre-load __loop_udelay into the I-cache
 	mov	r0, #1
-	bl	__udelay
+	bl	__loop_udelay
 	mov	r0, r0
 
 	@ The following must all exist in a single cache line to
@@ -53,11 +53,11 @@ ENTRY(sa1100_finish_suspend)
 	@ delay 90us and set CPU PLL to lowest speed
 	@ fixes resume problem on high speed SA1110
 	mov	r0, #90
-	bl	__udelay
+	bl	__loop_udelay
 	mov	r1, #0
 	str	r1, [r5]
 	mov	r0, #90
-	bl	__udelay
+	bl	__loop_udelay
 
 	/*
 	 * SA1110 SDRAM controller workaround.  register values:
diff --git a/arch/arm/mach-sa1100/time.c b/arch/arm/mach-sa1100/time.c
index 6af26e8d55e6..80702c9ecc77 100644
--- a/arch/arm/mach-sa1100/time.c
+++ b/arch/arm/mach-sa1100/time.c
@@ -22,7 +22,7 @@
 
 static u32 notrace sa1100_read_sched_clock(void)
 {
-	return OSCR;
+	return readl_relaxed(OSCR);
 }
 
 #define MIN_OSCR_DELTA 2
@@ -32,8 +32,8 @@ static irqreturn_t sa1100_ost0_interrupt(int irq, void *dev_id)
 	struct clock_event_device *c = dev_id;
 
 	/* Disarm the compare/match, signal the event. */
-	OIER &= ~OIER_E0;
-	OSSR = OSSR_M0;
+	writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER);
+	writel_relaxed(OSSR_M0, OSSR);
 	c->event_handler(c);
 
 	return IRQ_HANDLED;
@@ -44,10 +44,10 @@ sa1100_osmr0_set_next_event(unsigned long delta, struct clock_event_device *c)
 {
 	unsigned long next, oscr;
 
-	OIER |= OIER_E0;
-	next = OSCR + delta;
-	OSMR0 = next;
-	oscr = OSCR;
+	writel_relaxed(readl_relaxed(OIER) | OIER_E0, OIER);
+	next = readl_relaxed(OSCR) + delta;
+	writel_relaxed(next, OSMR0);
+	oscr = readl_relaxed(OSCR);
 
 	return (signed)(next - oscr) <= MIN_OSCR_DELTA ? -ETIME : 0;
 }
@@ -59,8 +59,8 @@ sa1100_osmr0_set_mode(enum clock_event_mode mode, struct clock_event_device *c)
 	case CLOCK_EVT_MODE_ONESHOT:
 	case CLOCK_EVT_MODE_UNUSED:
 	case CLOCK_EVT_MODE_SHUTDOWN:
-		OIER &= ~OIER_E0;
-		OSSR = OSSR_M0;
+		writel_relaxed(readl_relaxed(OIER) & ~OIER_E0, OIER);
+		writel_relaxed(OSSR_M0, OSSR);
 		break;
 
 	case CLOCK_EVT_MODE_RESUME:
@@ -86,8 +86,8 @@ static struct irqaction sa1100_timer_irq = {
 
 static void __init sa1100_timer_init(void)
 {
-	OIER = 0;
-	OSSR = OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3;
+	writel_relaxed(0, OIER);
+	writel_relaxed(OSSR_M0 | OSSR_M1 | OSSR_M2 | OSSR_M3, OSSR);
 
 	setup_sched_clock(sa1100_read_sched_clock, 32, 3686400);
 
@@ -100,7 +100,7 @@ static void __init sa1100_timer_init(void)
 
 	setup_irq(IRQ_OST0, &sa1100_timer_irq);
 
-	clocksource_mmio_init(&OSCR, "oscr", CLOCK_TICK_RATE, 200, 32,
+	clocksource_mmio_init(OSCR, "oscr", CLOCK_TICK_RATE, 200, 32,
 		clocksource_mmio_readl_up);
 	clockevents_register_device(&ckevt_sa1100_osmr0);
 }
@@ -110,26 +110,26 @@ unsigned long osmr[4], oier;
 
 static void sa1100_timer_suspend(void)
 {
-	osmr[0] = OSMR0;
-	osmr[1] = OSMR1;
-	osmr[2] = OSMR2;
-	osmr[3] = OSMR3;
-	oier = OIER;
+	osmr[0] = readl_relaxed(OSMR0);
+	osmr[1] = readl_relaxed(OSMR1);
+	osmr[2] = readl_relaxed(OSMR2);
+	osmr[3] = readl_relaxed(OSMR3);
+	oier = readl_relaxed(OIER);
 }
 
 static void sa1100_timer_resume(void)
 {
-	OSSR = 0x0f;
-	OSMR0 = osmr[0];
-	OSMR1 = osmr[1];
-	OSMR2 = osmr[2];
-	OSMR3 = osmr[3];
-	OIER = oier;
+	writel_relaxed(0x0f, OSSR);
+	writel_relaxed(osmr[0], OSMR0);
+	writel_relaxed(osmr[1], OSMR1);
+	writel_relaxed(osmr[2], OSMR2);
+	writel_relaxed(osmr[3], OSMR3);
+	writel_relaxed(oier, OIER);
 
 	/*
 	 * OSMR0 is the system timer: make sure OSCR is sufficiently behind
 	 */
-	OSCR = OSMR0 - LATCH;
+	writel_relaxed(OSMR0 - LATCH, OSCR);
 }
 #else
 #define sa1100_timer_suspend NULL
diff --git a/arch/arm/mach-shmobile/Kconfig b/arch/arm/mach-shmobile/Kconfig
index df33909205e2..4cacc2d22fbe 100644
--- a/arch/arm/mach-shmobile/Kconfig
+++ b/arch/arm/mach-shmobile/Kconfig
@@ -19,6 +19,7 @@ config ARCH_SH7372
 	select CPU_V7
 	select SH_CLK_CPG
 	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select ARM_CPU_SUSPEND if PM || CPU_IDLE
 
 config ARCH_SH73A0
 	bool "SH-Mobile AG5 (R8A73A00)"
@@ -58,6 +59,7 @@ config MACH_G4EVM
 	bool "G4EVM board"
 	depends on ARCH_SH7377
 	select ARCH_REQUIRE_GPIOLIB
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 config MACH_AP4EVB
 	bool "AP4EVB board"
@@ -65,6 +67,7 @@ config MACH_AP4EVB
 	select ARCH_REQUIRE_GPIOLIB
 	select SH_LCD_MIPI_DSI
 	select SND_SOC_AK4642 if SND_SIMPLE_CARD
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 choice
 	prompt "AP4EVB LCD panel selection"
@@ -83,6 +86,7 @@ config MACH_AG5EVM
 	bool "AG5EVM board"
 	select ARCH_REQUIRE_GPIOLIB
 	select SH_LCD_MIPI_DSI
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	depends on ARCH_SH73A0
 
 config MACH_MACKEREL
@@ -90,15 +94,18 @@ config MACH_MACKEREL
 	depends on ARCH_SH7372
 	select ARCH_REQUIRE_GPIOLIB
 	select SND_SOC_AK4642 if SND_SIMPLE_CARD
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 config MACH_KOTA2
 	bool "KOTA2 board"
 	select ARCH_REQUIRE_GPIOLIB
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	depends on ARCH_SH73A0
 
 config MACH_BONITO
 	bool "bonito board"
 	select ARCH_REQUIRE_GPIOLIB
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 	depends on ARCH_R8A7740
 
 config MACH_ARMADILLO800EVA
@@ -106,22 +113,28 @@ config MACH_ARMADILLO800EVA
 	depends on ARCH_R8A7740
 	select ARCH_REQUIRE_GPIOLIB
 	select USE_OF
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
+	select SND_SOC_WM8978 if SND_SIMPLE_CARD
 
 config MACH_MARZEN
 	bool "MARZEN board"
 	depends on ARCH_R8A7779
 	select ARCH_REQUIRE_GPIOLIB
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 config MACH_KZM9D
 	bool "KZM9D board"
 	depends on ARCH_EMEV2
 	select USE_OF
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 config MACH_KZM9G
 	bool "KZM-A9-GT board"
 	depends on ARCH_SH73A0
 	select ARCH_REQUIRE_GPIOLIB
 	select USE_OF
+	select SND_SOC_AK4642 if SND_SIMPLE_CARD
+	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 comment "SH-Mobile System Configuration"
 
diff --git a/arch/arm/mach-shmobile/Makefile b/arch/arm/mach-shmobile/Makefile
index 8aa1962c22a2..0df5ae6740c6 100644
--- a/arch/arm/mach-shmobile/Makefile
+++ b/arch/arm/mach-shmobile/Makefile
@@ -39,7 +39,9 @@ obj-$(CONFIG_ARCH_R8A7740)	+= entry-intc.o
 # PM objects
 obj-$(CONFIG_SUSPEND)		+= suspend.o
 obj-$(CONFIG_CPU_IDLE)		+= cpuidle.o
+obj-$(CONFIG_ARCH_SHMOBILE)	+= pm-rmobile.o
 obj-$(CONFIG_ARCH_SH7372)	+= pm-sh7372.o sleep-sh7372.o
+obj-$(CONFIG_ARCH_R8A7740)	+= pm-r8a7740.o
 obj-$(CONFIG_ARCH_R8A7779)	+= pm-r8a7779.o
 
 # Board objects
diff --git a/arch/arm/mach-shmobile/board-ag5evm.c b/arch/arm/mach-shmobile/board-ag5evm.c
index 5a6f22f05e99..d82c010fdfc6 100644
--- a/arch/arm/mach-shmobile/board-ag5evm.c
+++ b/arch/arm/mach-shmobile/board-ag5evm.c
@@ -27,6 +27,8 @@
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/dma-mapping.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 #include <linux/serial_sci.h>
 #include <linux/smsc911x.h>
 #include <linux/gpio.h>
@@ -52,6 +54,12 @@
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/traps.h>
 
+/* Dummy supplies, where voltage doesn't matter */
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+};
+
 static struct resource smsc9220_resources[] = {
 	[0] = {
 		.start		= 0x14000000,
@@ -142,6 +150,13 @@ static struct platform_device fsi_device = {
 	.resource	= fsi_resources,
 };
 
+/* Fixed 1.8V regulator to be used by MMCIF */
+static struct regulator_consumer_supply fixed1v8_power_consumers[] =
+{
+	REGULATOR_SUPPLY("vmmc", "sh_mmcif.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mmcif.0"),
+};
+
 static struct resource sh_mmcif_resources[] = {
 	[0] = {
 		.name	= "MMCIF",
@@ -364,6 +379,13 @@ static struct platform_device mipidsi0_device = {
 	},
 };
 
+/* Fixed 2.8V regulators to be used by SDHI0 */
+static struct regulator_consumer_supply fixed2v8_power_consumers[] =
+{
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.0"),
+};
+
 /* SDHI0 */
 static struct sh_mobile_sdhi_info sdhi0_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI0_TX,
@@ -408,8 +430,57 @@ static struct platform_device sdhi0_device = {
 	},
 };
 
-void ag5evm_sdhi1_set_pwr(struct platform_device *pdev, int state)
+/* Fixed 3.3V regulator to be used by SDHI1 */
+static struct regulator_consumer_supply cn4_power_consumers[] =
 {
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.1"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.1"),
+};
+
+static struct regulator_init_data cn4_power_init_data = {
+	.constraints = {
+		.valid_ops_mask = REGULATOR_CHANGE_STATUS,
+	},
+	.num_consumer_supplies  = ARRAY_SIZE(cn4_power_consumers),
+	.consumer_supplies      = cn4_power_consumers,
+};
+
+static struct fixed_voltage_config cn4_power_info = {
+	.supply_name = "CN4 SD/MMC Vdd",
+	.microvolts = 3300000,
+	.gpio = GPIO_PORT114,
+	.enable_high = 1,
+	.init_data = &cn4_power_init_data,
+};
+
+static struct platform_device cn4_power = {
+	.name = "reg-fixed-voltage",
+	.id   = 2,
+	.dev  = {
+		.platform_data = &cn4_power_info,
+	},
+};
+
+static void ag5evm_sdhi1_set_pwr(struct platform_device *pdev, int state)
+{
+	static int power_gpio = -EINVAL;
+
+	if (power_gpio < 0) {
+		int ret = gpio_request(GPIO_PORT114, "sdhi1_power");
+		if (!ret) {
+			power_gpio = GPIO_PORT114;
+			gpio_direction_output(power_gpio, 0);
+		}
+	}
+
+	/*
+	 * If requesting the GPIO above failed, it means, that the regulator got
+	 * probed and grabbed the GPIO, but we don't know, whether the sdhi
+	 * driver already uses the regulator. If it doesn't, we have to toggle
+	 * the GPIO ourselves, even though it is now owned by the fixed
+	 * regulator driver. We have to live with the race in case the driver
+	 * gets unloaded and the GPIO freed between these two steps.
+	 */
 	gpio_set_value(GPIO_PORT114, state);
 }
 
@@ -455,6 +526,7 @@ static struct platform_device sdhi1_device = {
 };
 
 static struct platform_device *ag5evm_devices[] __initdata = {
+	&cn4_power,
 	&eth_device,
 	&keysc_device,
 	&fsi_device,
@@ -468,6 +540,12 @@ static struct platform_device *ag5evm_devices[] __initdata = {
 
 static void __init ag5evm_init(void)
 {
+	regulator_register_always_on(0, "fixed-1.8V", fixed1v8_power_consumers,
+				     ARRAY_SIZE(fixed1v8_power_consumers), 1800000);
+	regulator_register_always_on(1, "fixed-2.8V", fixed2v8_power_consumers,
+				     ARRAY_SIZE(fixed2v8_power_consumers), 3300000);
+	regulator_register_fixed(3, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	sh73a0_pinmux_init();
 
 	/* enable SCIFA2 */
@@ -562,8 +640,6 @@ static void __init ag5evm_init(void)
 	gpio_request(GPIO_FN_SDHID1_2_PU, NULL);
 	gpio_request(GPIO_FN_SDHID1_1_PU, NULL);
 	gpio_request(GPIO_FN_SDHID1_0_PU, NULL);
-	gpio_request(GPIO_PORT114, "sdhi1_power");
-	gpio_direction_output(GPIO_PORT114, 0);
 
 #ifdef CONFIG_CACHE_L2X0
 	/* Shared attribute override enable, 64K*8way */
diff --git a/arch/arm/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c
index ace60246a5df..f172ca85905c 100644
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@@ -34,6 +34,8 @@
 #include <linux/i2c.h>
 #include <linux/i2c/tsc2007.h>
 #include <linux/io.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 #include <linux/smsc911x.h>
 #include <linux/sh_intc.h>
 #include <linux/sh_clk.h>
@@ -159,6 +161,27 @@
  * CN12: 3.3v
  */
 
+/* Dummy supplies, where voltage doesn't matter */
+static struct regulator_consumer_supply fixed1v8_power_consumers[] =
+{
+	/* J22 default position: 1.8V */
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.1"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.1"),
+	REGULATOR_SUPPLY("vmmc", "sh_mmcif.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mmcif.0"),
+};
+
+static struct regulator_consumer_supply fixed3v3_power_consumers[] =
+{
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.0"),
+};
+
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+};
+
 /* MTD */
 static struct mtd_partition nor_flash_partitions[] = {
 	{
@@ -1138,21 +1161,6 @@ static void __init fsi_init_pm_clock(void)
 	clk_put(fsia_ick);
 }
 
-/*
- * FIXME !!
- *
- * gpio_no_direction
- * are quick_hack.
- *
- * current gpio frame work doesn't have
- * the method to control only pull up/down/free.
- * this function should be replaced by correct gpio function
- */
-static void __init gpio_no_direction(u32 addr)
-{
-	__raw_writeb(0x00, addr);
-}
-
 /* TouchScreen */
 #ifdef CONFIG_AP4EVB_QHD
 # define GPIO_TSC_IRQ	GPIO_FN_IRQ28_123
@@ -1224,6 +1232,12 @@ static void __init ap4evb_init(void)
 	u32 srcr4;
 	struct clk *clk;
 
+	regulator_register_always_on(0, "fixed-1.8V", fixed1v8_power_consumers,
+				     ARRAY_SIZE(fixed1v8_power_consumers), 1800000);
+	regulator_register_always_on(1, "fixed-3.3V", fixed3v3_power_consumers,
+				     ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
+	regulator_register_fixed(2, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	/* External clock source */
 	clk_set_rate(&sh7372_dv_clki_clk, 27000000);
 
@@ -1302,8 +1316,8 @@ static void __init ap4evb_init(void)
 
 	gpio_request(GPIO_PORT9, NULL);
 	gpio_request(GPIO_PORT10, NULL);
-	gpio_no_direction(GPIO_PORT9CR);  /* FSIAOBT needs no direction */
-	gpio_no_direction(GPIO_PORT10CR); /* FSIAOLR needs no direction */
+	gpio_direction_none(GPIO_PORT9CR);  /* FSIAOBT needs no direction */
+	gpio_direction_none(GPIO_PORT10CR); /* FSIAOLR needs no direction */
 
 	/* card detect pin for MMC slot (CN7) */
 	gpio_request(GPIO_PORT41, NULL);
@@ -1447,14 +1461,14 @@ static void __init ap4evb_init(void)
 
 	platform_add_devices(ap4evb_devices, ARRAY_SIZE(ap4evb_devices));
 
-	sh7372_add_device_to_domain(&sh7372_a4lc, &lcdc1_device);
-	sh7372_add_device_to_domain(&sh7372_a4lc, &lcdc_device);
-	sh7372_add_device_to_domain(&sh7372_a4mp, &fsi_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4lc, &lcdc1_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4lc, &lcdc_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4mp, &fsi_device);
 
-	sh7372_add_device_to_domain(&sh7372_a3sp, &sh_mmcif_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi0_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi1_device);
-	sh7372_add_device_to_domain(&sh7372_a4r, &ceu_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sh_mmcif_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sdhi0_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sdhi1_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4r, &ceu_device);
 
 	hdmi_init_pm_clock();
 	fsi_init_pm_clock();
diff --git a/arch/arm/mach-shmobile/board-armadillo800eva.c b/arch/arm/mach-shmobile/board-armadillo800eva.c
index 9bd135531d76..cf10f92856dc 100644
--- a/arch/arm/mach-shmobile/board-armadillo800eva.c
+++ b/arch/arm/mach-shmobile/board-armadillo800eva.c
@@ -28,6 +28,8 @@
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
 #include <linux/gpio_keys.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 #include <linux/sh_eth.h>
 #include <linux/videodev2.h>
 #include <linux/usb/renesas_usbhs.h>
@@ -37,14 +39,20 @@
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <mach/common.h>
 #include <mach/irqs.h>
+#include <mach/r8a7740.h>
+#include <media/mt9t112.h>
+#include <media/sh_mobile_ceu.h>
+#include <media/soc_camera.h>
 #include <asm/page.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 #include <asm/mach/time.h>
 #include <asm/hardware/cache-l2x0.h>
-#include <mach/r8a7740.h>
 #include <video/sh_mobile_lcdc.h>
+#include <video/sh_mobile_hdmi.h>
+#include <sound/sh_fsi.h>
+#include <sound/simple_card.h>
 
 /*
  * CON1		Camera Module
@@ -108,6 +116,14 @@
  */
 
 /*
+ * FSI-WM8978
+ *
+ * this command is required when playback.
+ *
+ * # amixer set "Headphone" 50
+ */
+
+/*
  * USB function
  *
  * When you use USB Function,
@@ -117,14 +133,8 @@
  * These are a little bit complex.
  * see
  *	usbhsf_power_ctrl()
- *
- * CAUTION
- *
- * It uses autonomy mode for USB hotplug at this point
- * (= usbhs_private.platform_callback.get_vbus is NULL),
- * since we don't know what's happen on PM control
- * on this workaround.
  */
+#define IRQ7		evt2irq(0x02e0)
 #define USBCR1		0xe605810a
 #define USBH		0xC6700000
 #define USBH_USBCTR	0x10834
@@ -204,6 +214,20 @@ static void usbhsf_power_ctrl(struct platform_device *pdev,
 	}
 }
 
+static int usbhsf_get_vbus(struct platform_device *pdev)
+{
+	return gpio_get_value(GPIO_PORT209);
+}
+
+static irqreturn_t usbhsf_interrupt(int irq, void *data)
+{
+	struct platform_device *pdev = data;
+
+	renesas_usbhs_call_notify_hotplug(pdev);
+
+	return IRQ_HANDLED;
+}
+
 static void usbhsf_hardware_exit(struct platform_device *pdev)
 {
 	struct usbhsf_private *priv = usbhsf_get_priv(pdev);
@@ -227,11 +251,14 @@ static void usbhsf_hardware_exit(struct platform_device *pdev)
 	priv->host	= NULL;
 	priv->func	= NULL;
 	priv->usbh_base	= NULL;
+
+	free_irq(IRQ7, pdev);
 }
 
 static int usbhsf_hardware_init(struct platform_device *pdev)
 {
 	struct usbhsf_private *priv = usbhsf_get_priv(pdev);
+	int ret;
 
 	priv->phy	= clk_get(&pdev->dev, "phy");
 	priv->usb24	= clk_get(&pdev->dev, "usb24");
@@ -251,6 +278,14 @@ static int usbhsf_hardware_init(struct platform_device *pdev)
 		return -EIO;
 	}
 
+	ret = request_irq(IRQ7, usbhsf_interrupt, IRQF_TRIGGER_NONE,
+			  dev_name(&pdev->dev), pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "request_irq err\n");
+		return ret;
+	}
+	irq_set_irq_type(IRQ7, IRQ_TYPE_EDGE_BOTH);
+
 	/* usb24 use 1/1 of parent clock (= usb24s = 24MHz) */
 	clk_set_rate(priv->usb24,
 		     clk_get_rate(clk_get_parent(priv->usb24)));
@@ -262,6 +297,7 @@ static struct usbhsf_private usbhsf_private = {
 	.info = {
 		.platform_callback = {
 			.get_id		= usbhsf_get_id,
+			.get_vbus	= usbhsf_get_vbus,
 			.hardware_init	= usbhsf_hardware_init,
 			.hardware_exit	= usbhsf_hardware_exit,
 			.power_ctrl	= usbhsf_power_ctrl,
@@ -269,6 +305,8 @@ static struct usbhsf_private usbhsf_private = {
 		.driver_param = {
 			.buswait_bwait		= 5,
 			.detection_delay	= 5,
+			.d0_rx_id	= SHDMA_SLAVE_USBHS_RX,
+			.d1_tx_id	= SHDMA_SLAVE_USBHS_TX,
 		},
 	}
 };
@@ -384,6 +422,103 @@ static struct platform_device lcdc0_device = {
 	},
 };
 
+/*
+ * LCDC1/HDMI
+ */
+static struct sh_mobile_hdmi_info hdmi_info = {
+	.flags		= HDMI_OUTPUT_PUSH_PULL |
+			  HDMI_OUTPUT_POLARITY_HI |
+			  HDMI_32BIT_REG |
+			  HDMI_HAS_HTOP1 |
+			  HDMI_SND_SRC_SPDIF,
+};
+
+static struct resource hdmi_resources[] = {
+	[0] = {
+		.name	= "HDMI",
+		.start	= 0xe6be0000,
+		.end	= 0xe6be03ff,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= evt2irq(0x1700),
+		.flags	= IORESOURCE_IRQ,
+	},
+	[2] = {
+		.name	= "HDMI emma3pf",
+		.start	= 0xe6be4000,
+		.end	= 0xe6be43ff,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device hdmi_device = {
+	.name		= "sh-mobile-hdmi",
+	.num_resources	= ARRAY_SIZE(hdmi_resources),
+	.resource	= hdmi_resources,
+	.id             = -1,
+	.dev	= {
+		.platform_data	= &hdmi_info,
+	},
+};
+
+static const struct fb_videomode lcdc1_mode = {
+	.name		= "HDMI 720p",
+	.xres		= 1280,
+	.yres		= 720,
+	.pixclock	= 13468,
+	.left_margin	= 220,
+	.right_margin	= 110,
+	.hsync_len	= 40,
+	.upper_margin	= 20,
+	.lower_margin	= 5,
+	.vsync_len	= 5,
+	.refresh	= 60,
+	.sync		= FB_SYNC_VERT_HIGH_ACT | FB_SYNC_HOR_HIGH_ACT,
+};
+
+static struct sh_mobile_lcdc_info hdmi_lcdc_info = {
+	.clock_source	= LCDC_CLK_PERIPHERAL, /* HDMI clock */
+	.ch[0] = {
+		.chan			= LCDC_CHAN_MAINLCD,
+		.fourcc			= V4L2_PIX_FMT_RGB565,
+		.interface_type		= RGB24,
+		.clock_divider		= 1,
+		.flags			= LCDC_FLAGS_DWPOL,
+		.lcd_modes		= &lcdc1_mode,
+		.num_modes		= 1,
+		.tx_dev			= &hdmi_device,
+		.panel_cfg = {
+			.width	= 1280,
+			.height = 720,
+		},
+	},
+};
+
+static struct resource hdmi_lcdc_resources[] = {
+	[0] = {
+		.name	= "LCDC1",
+		.start	= 0xfe944000,
+		.end	= 0xfe948000 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= intcs_evt2irq(0x1780),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device hdmi_lcdc_device = {
+	.name		= "sh_mobile_lcdc_fb",
+	.num_resources	= ARRAY_SIZE(hdmi_lcdc_resources),
+	.resource	= hdmi_lcdc_resources,
+	.id		= 1,
+	.dev	= {
+		.platform_data	= &hdmi_lcdc_info,
+		.coherent_dma_mask = ~0,
+	},
+};
+
 /* GPIO KEY */
 #define GPIO_KEY(c, g, d) { .code = c, .gpio = g, .desc = d, .active_low = 1 }
 
@@ -407,6 +542,17 @@ static struct platform_device gpio_keys_device = {
 	},
 };
 
+/* Fixed 3.3V regulator to be used by SDHI0, SDHI1, MMCIF */
+static struct regulator_consumer_supply fixed3v3_power_consumers[] =
+{
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.1"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.1"),
+	REGULATOR_SUPPLY("vmmc", "sh_mmcif"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mmcif"),
+};
+
 /* SDHI0 */
 /*
  * FIXME
@@ -418,6 +564,8 @@ static struct platform_device gpio_keys_device = {
  */
 #define IRQ31	evt2irq(0x33E0)
 static struct sh_mobile_sdhi_info sdhi0_info = {
+	.dma_slave_tx	= SHDMA_SLAVE_SDHI0_TX,
+	.dma_slave_rx	= SHDMA_SLAVE_SDHI0_RX,
 	.tmio_caps	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ |\
 			  MMC_CAP_NEEDS_POLL,
 	.tmio_ocr_mask	= MMC_VDD_165_195 | MMC_VDD_32_33 | MMC_VDD_33_34,
@@ -458,6 +606,8 @@ static struct platform_device sdhi0_device = {
 
 /* SDHI1 */
 static struct sh_mobile_sdhi_info sdhi1_info = {
+	.dma_slave_tx	= SHDMA_SLAVE_SDHI1_TX,
+	.dma_slave_rx	= SHDMA_SLAVE_SDHI1_RX,
 	.tmio_caps	= MMC_CAP_SD_HIGHSPEED | MMC_CAP_SDIO_IRQ,
 	.tmio_ocr_mask	= MMC_VDD_165_195 | MMC_VDD_32_33 | MMC_VDD_33_34,
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT,
@@ -532,12 +682,209 @@ static struct platform_device sh_mmcif_device = {
 	.resource	= sh_mmcif_resources,
 };
 
+/* Camera */
+static int mt9t111_power(struct device *dev, int mode)
+{
+	struct clk *mclk = clk_get(NULL, "video1");
+
+	if (IS_ERR(mclk)) {
+		dev_err(dev, "can't get video1 clock\n");
+		return -EINVAL;
+	}
+
+	if (mode) {
+		/* video1 (= CON1 camera) expect 24MHz */
+		clk_set_rate(mclk, clk_round_rate(mclk, 24000000));
+		clk_enable(mclk);
+		gpio_direction_output(GPIO_PORT158, 1);
+	} else {
+		gpio_direction_output(GPIO_PORT158, 0);
+		clk_disable(mclk);
+	}
+
+	clk_put(mclk);
+
+	return 0;
+}
+
+static struct i2c_board_info i2c_camera_mt9t111 = {
+	I2C_BOARD_INFO("mt9t112", 0x3d),
+};
+
+static struct mt9t112_camera_info mt9t111_info = {
+	.divider = { 16, 0, 0, 7, 0, 10, 14, 7, 7 },
+};
+
+static struct soc_camera_link mt9t111_link = {
+	.i2c_adapter_id	= 0,
+	.bus_id		= 0,
+	.board_info	= &i2c_camera_mt9t111,
+	.power		= mt9t111_power,
+	.priv		= &mt9t111_info,
+};
+
+static struct platform_device camera_device = {
+	.name	= "soc-camera-pdrv",
+	.id	= 0,
+	.dev	= {
+		.platform_data = &mt9t111_link,
+	},
+};
+
+/* CEU0 */
+static struct sh_mobile_ceu_info sh_mobile_ceu0_info = {
+	.flags = SH_CEU_FLAG_LOWER_8BIT,
+};
+
+static struct resource ceu0_resources[] = {
+	[0] = {
+		.name	= "CEU",
+		.start	= 0xfe910000,
+		.end	= 0xfe91009f,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start  = intcs_evt2irq(0x0500),
+		.flags  = IORESOURCE_IRQ,
+	},
+	[2] = {
+		/* place holder for contiguous memory */
+	},
+};
+
+static struct platform_device ceu0_device = {
+	.name		= "sh_mobile_ceu",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(ceu0_resources),
+	.resource	= ceu0_resources,
+	.dev	= {
+		.platform_data		= &sh_mobile_ceu0_info,
+		.coherent_dma_mask	= 0xffffffff,
+	},
+};
+
+/* FSI */
+static int fsi_hdmi_set_rate(struct device *dev, int rate, int enable)
+{
+	struct clk *fsib;
+	int ret;
+
+	/* it support 48KHz only */
+	if (48000 != rate)
+		return -EINVAL;
+
+	fsib = clk_get(dev, "ickb");
+	if (IS_ERR(fsib))
+		return -EINVAL;
+
+	if (enable) {
+		ret = SH_FSI_ACKMD_256 | SH_FSI_BPFMD_64;
+		clk_enable(fsib);
+	} else {
+		ret = 0;
+		clk_disable(fsib);
+	}
+
+	clk_put(fsib);
+
+	return ret;
+}
+
+static struct sh_fsi_platform_info fsi_info = {
+	/* FSI-WM8978 */
+	.port_a = {
+		.tx_id = SHDMA_SLAVE_FSIA_TX,
+	},
+	/* FSI-HDMI */
+	.port_b = {
+		.flags		= SH_FSI_FMT_SPDIF |
+				  SH_FSI_ENABLE_STREAM_MODE,
+		.set_rate	= fsi_hdmi_set_rate,
+		.tx_id		= SHDMA_SLAVE_FSIB_TX,
+	}
+};
+
+static struct resource fsi_resources[] = {
+	[0] = {
+		.name	= "FSI",
+		.start	= 0xfe1f0000,
+		.end	= 0xfe1f8400 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start  = evt2irq(0x1840),
+		.flags  = IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device fsi_device = {
+	.name		= "sh_fsi2",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(fsi_resources),
+	.resource	= fsi_resources,
+	.dev	= {
+		.platform_data	= &fsi_info,
+	},
+};
+
+/* FSI-WM8978 */
+static struct asoc_simple_dai_init_info fsi_wm8978_init_info = {
+	.fmt		= SND_SOC_DAIFMT_I2S,
+	.codec_daifmt	= SND_SOC_DAIFMT_CBM_CFM | SND_SOC_DAIFMT_NB_NF,
+	.cpu_daifmt	= SND_SOC_DAIFMT_CBS_CFS,
+	.sysclk		= 12288000,
+};
+
+static struct asoc_simple_card_info fsi_wm8978_info = {
+	.name		= "wm8978",
+	.card		= "FSI2A-WM8978",
+	.cpu_dai	= "fsia-dai",
+	.codec		= "wm8978.0-001a",
+	.platform	= "sh_fsi2",
+	.codec_dai	= "wm8978-hifi",
+	.init		= &fsi_wm8978_init_info,
+};
+
+static struct platform_device fsi_wm8978_device = {
+	.name	= "asoc-simple-card",
+	.id	= 0,
+	.dev	= {
+		.platform_data	= &fsi_wm8978_info,
+	},
+};
+
+/* FSI-HDMI */
+static struct asoc_simple_dai_init_info fsi2_hdmi_init_info = {
+	.cpu_daifmt	= SND_SOC_DAIFMT_CBM_CFM,
+};
+
+static struct asoc_simple_card_info fsi2_hdmi_info = {
+	.name		= "HDMI",
+	.card		= "FSI2B-HDMI",
+	.cpu_dai	= "fsib-dai",
+	.codec		= "sh-mobile-hdmi",
+	.platform	= "sh_fsi2",
+	.codec_dai	= "sh_mobile_hdmi-hifi",
+	.init		= &fsi2_hdmi_init_info,
+};
+
+static struct platform_device fsi_hdmi_device = {
+	.name	= "asoc-simple-card",
+	.id	= 1,
+	.dev	= {
+		.platform_data	= &fsi2_hdmi_info,
+	},
+};
+
 /* I2C */
 static struct i2c_board_info i2c0_devices[] = {
 	{
 		I2C_BOARD_INFO("st1232-ts", 0x55),
 		.irq = evt2irq(0x0340),
 	},
+	{
+		I2C_BOARD_INFO("wm8978", 0x1a),
+	},
 };
 
 /*
@@ -549,6 +896,13 @@ static struct platform_device *eva_devices[] __initdata = {
 	&sh_eth_device,
 	&sdhi0_device,
 	&sh_mmcif_device,
+	&hdmi_device,
+	&hdmi_lcdc_device,
+	&camera_device,
+	&ceu0_device,
+	&fsi_device,
+	&fsi_hdmi_device,
+	&fsi_wm8978_device,
 };
 
 static void __init eva_clock_init(void)
@@ -556,10 +910,14 @@ static void __init eva_clock_init(void)
 	struct clk *system	= clk_get(NULL, "system_clk");
 	struct clk *xtal1	= clk_get(NULL, "extal1");
 	struct clk *usb24s	= clk_get(NULL, "usb24s");
+	struct clk *fsibck	= clk_get(NULL, "fsibck");
+	struct clk *fsib	= clk_get(&fsi_device.dev, "ickb");
 
 	if (IS_ERR(system)	||
 	    IS_ERR(xtal1)	||
-	    IS_ERR(usb24s)) {
+	    IS_ERR(usb24s)	||
+	    IS_ERR(fsibck)	||
+	    IS_ERR(fsib)) {
 		pr_err("armadillo800eva board clock init failed\n");
 		goto clock_error;
 	}
@@ -570,6 +928,11 @@ static void __init eva_clock_init(void)
 	/* usb24s use extal1 (= system) clock (= 24MHz) */
 	clk_set_parent(usb24s, system);
 
+	/* FSIBCK is 12.288MHz, and it is parent of FSI-B */
+	clk_set_parent(fsib, fsibck);
+	clk_set_rate(fsibck, 12288000);
+	clk_set_rate(fsib,   12288000);
+
 clock_error:
 	if (!IS_ERR(system))
 		clk_put(system);
@@ -577,16 +940,26 @@ clock_error:
 		clk_put(xtal1);
 	if (!IS_ERR(usb24s))
 		clk_put(usb24s);
+	if (!IS_ERR(fsibck))
+		clk_put(fsibck);
+	if (!IS_ERR(fsib))
+		clk_put(fsib);
 }
 
 /*
  * board init
  */
+#define GPIO_PORT7CR	0xe6050007
+#define GPIO_PORT8CR	0xe6050008
 static void __init eva_init(void)
 {
-	eva_clock_init();
+	struct platform_device *usb = NULL;
+
+	regulator_register_always_on(0, "fixed-3.3V", fixed3v3_power_consumers,
+				     ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
 
 	r8a7740_pinmux_init();
+	r8a7740_meram_workaround();
 
 	/* SCIFA1 */
 	gpio_request(GPIO_FN_SCIFA1_RXD, NULL);
@@ -667,8 +1040,19 @@ static void __init eva_init(void)
 		/* USB Host */
 	} else {
 		/* USB Func */
-		gpio_request(GPIO_FN_VBUS, NULL);
+		/*
+		 * A1 chip has 2 IRQ7 pin and it was controled by MSEL register.
+		 * OTOH, usbhs interrupt needs its value (HI/LOW) to decide
+		 * USB connection/disconnection (usbhsf_get_vbus()).
+		 * This means we needs to select GPIO_FN_IRQ7_PORT209 first,
+		 * and select GPIO_PORT209 here
+		 */
+		gpio_request(GPIO_FN_IRQ7_PORT209, NULL);
+		gpio_request(GPIO_PORT209, NULL);
+		gpio_direction_input(GPIO_PORT209);
+
 		platform_device_register(&usbhsf_device);
+		usb = &usbhsf_device;
 	}
 
 	/* SDHI0 */
@@ -706,6 +1090,48 @@ static void __init eva_init(void)
 	gpio_request(GPIO_FN_MMC1_D6_PORT143,	NULL);
 	gpio_request(GPIO_FN_MMC1_D7_PORT142,	NULL);
 
+	/* CEU0 */
+	gpio_request(GPIO_FN_VIO0_D7,		NULL);
+	gpio_request(GPIO_FN_VIO0_D6,		NULL);
+	gpio_request(GPIO_FN_VIO0_D5,		NULL);
+	gpio_request(GPIO_FN_VIO0_D4,		NULL);
+	gpio_request(GPIO_FN_VIO0_D3,		NULL);
+	gpio_request(GPIO_FN_VIO0_D2,		NULL);
+	gpio_request(GPIO_FN_VIO0_D1,		NULL);
+	gpio_request(GPIO_FN_VIO0_D0,		NULL);
+	gpio_request(GPIO_FN_VIO0_CLK,		NULL);
+	gpio_request(GPIO_FN_VIO0_HD,		NULL);
+	gpio_request(GPIO_FN_VIO0_VD,		NULL);
+	gpio_request(GPIO_FN_VIO0_FIELD,	NULL);
+	gpio_request(GPIO_FN_VIO_CKO,		NULL);
+
+	/* CON1/CON15 Camera */
+	gpio_request(GPIO_PORT173, NULL); /* STANDBY */
+	gpio_request(GPIO_PORT172, NULL); /* RST */
+	gpio_request(GPIO_PORT158, NULL); /* CAM_PON */
+	gpio_direction_output(GPIO_PORT173, 0);
+	gpio_direction_output(GPIO_PORT172, 1);
+	gpio_direction_output(GPIO_PORT158, 0); /* see mt9t111_power() */
+
+	/* FSI-WM8978 */
+	gpio_request(GPIO_FN_FSIAIBT,		NULL);
+	gpio_request(GPIO_FN_FSIAILR,		NULL);
+	gpio_request(GPIO_FN_FSIAOMC,		NULL);
+	gpio_request(GPIO_FN_FSIAOSLD,		NULL);
+	gpio_request(GPIO_FN_FSIAISLD_PORT5,	NULL);
+
+	gpio_request(GPIO_PORT7, NULL);
+	gpio_request(GPIO_PORT8, NULL);
+	gpio_direction_none(GPIO_PORT7CR); /* FSIAOBT needs no direction */
+	gpio_direction_none(GPIO_PORT8CR); /* FSIAOLR needs no direction */
+
+	/* FSI-HDMI */
+	gpio_request(GPIO_FN_FSIBCK,		NULL);
+
+	/* HDMI */
+	gpio_request(GPIO_FN_HDMI_HPD,		NULL);
+	gpio_request(GPIO_FN_HDMI_CEC,		NULL);
+
 	/*
 	 * CAUTION
 	 *
@@ -752,6 +1178,13 @@ static void __init eva_init(void)
 
 	platform_add_devices(eva_devices,
 			     ARRAY_SIZE(eva_devices));
+
+	eva_clock_init();
+
+	rmobile_add_device_to_domain(&r8a7740_pd_a4lc, &lcdc0_device);
+	rmobile_add_device_to_domain(&r8a7740_pd_a4lc, &hdmi_lcdc_device);
+	if (usb)
+		rmobile_add_device_to_domain(&r8a7740_pd_a3sp, usb);
 }
 
 static void __init eva_earlytimer_init(void)
diff --git a/arch/arm/mach-shmobile/board-bonito.c b/arch/arm/mach-shmobile/board-bonito.c
index e9b32cfbf741..4129008eae29 100644
--- a/arch/arm/mach-shmobile/board-bonito.c
+++ b/arch/arm/mach-shmobile/board-bonito.c
@@ -26,6 +26,8 @@
 #include <linux/irq.h>
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 #include <linux/smsc911x.h>
 #include <linux/videodev2.h>
 #include <mach/common.h>
@@ -75,6 +77,12 @@
  * S38.2 = OFF
  */
 
+/* Dummy supplies, where voltage doesn't matter */
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+};
+
 /*
  * FPGA
  */
@@ -360,6 +368,8 @@ static void __init bonito_init(void)
 {
 	u16 val;
 
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	r8a7740_pinmux_init();
 	bonito_fpga_init();
 
diff --git a/arch/arm/mach-shmobile/board-g4evm.c b/arch/arm/mach-shmobile/board-g4evm.c
index f1257321999a..fa5dfc5c8ed6 100644
--- a/arch/arm/mach-shmobile/board-g4evm.c
+++ b/arch/arm/mach-shmobile/board-g4evm.c
@@ -26,6 +26,8 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 #include <linux/usb/r8a66597.h>
 #include <linux/io.h>
 #include <linux/input.h>
@@ -196,6 +198,15 @@ static struct platform_device keysc_device = {
 	},
 };
 
+/* Fixed 3.3V regulator to be used by SDHI0 and SDHI1 */
+static struct regulator_consumer_supply fixed3v3_power_consumers[] =
+{
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.1"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.1"),
+};
+
 /* SDHI */
 static struct sh_mobile_sdhi_info sdhi0_info = {
 	.tmio_caps	= MMC_CAP_SDIO_IRQ,
@@ -271,26 +282,11 @@ static struct platform_device *g4evm_devices[] __initdata = {
 #define GPIO_SDHID1_D3	0xe6052106
 #define GPIO_SDHICMD1	0xe6052107
 
-/*
- * FIXME !!
- *
- * gpio_pull_up is quick_hack.
- *
- * current gpio frame work doesn't have
- * the method to control only pull up/down/free.
- * this function should be replaced by correct gpio function
- */
-static void __init gpio_pull_up(u32 addr)
-{
-	u8 data = __raw_readb(addr);
-
-	data &= 0x0F;
-	data |= 0xC0;
-	__raw_writeb(data, addr);
-}
-
 static void __init g4evm_init(void)
 {
+	regulator_register_always_on(0, "fixed-3.3V", fixed3v3_power_consumers,
+				     ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
+
 	sh7377_pinmux_init();
 
 	/* Lit DS14 LED */
@@ -351,11 +347,11 @@ static void __init g4evm_init(void)
 	gpio_request(GPIO_FN_SDHID0_3, NULL);
 	gpio_request(GPIO_FN_SDHICMD0, NULL);
 	gpio_request(GPIO_FN_SDHIWP0, NULL);
-	gpio_pull_up(GPIO_SDHID0_D0);
-	gpio_pull_up(GPIO_SDHID0_D1);
-	gpio_pull_up(GPIO_SDHID0_D2);
-	gpio_pull_up(GPIO_SDHID0_D3);
-	gpio_pull_up(GPIO_SDHICMD0);
+	gpio_request_pullup(GPIO_SDHID0_D0);
+	gpio_request_pullup(GPIO_SDHID0_D1);
+	gpio_request_pullup(GPIO_SDHID0_D2);
+	gpio_request_pullup(GPIO_SDHID0_D3);
+	gpio_request_pullup(GPIO_SDHICMD0);
 
 	/* SDHI1 */
 	gpio_request(GPIO_FN_SDHICLK1, NULL);
@@ -364,11 +360,11 @@ static void __init g4evm_init(void)
 	gpio_request(GPIO_FN_SDHID1_2, NULL);
 	gpio_request(GPIO_FN_SDHID1_3, NULL);
 	gpio_request(GPIO_FN_SDHICMD1, NULL);
-	gpio_pull_up(GPIO_SDHID1_D0);
-	gpio_pull_up(GPIO_SDHID1_D1);
-	gpio_pull_up(GPIO_SDHID1_D2);
-	gpio_pull_up(GPIO_SDHID1_D3);
-	gpio_pull_up(GPIO_SDHICMD1);
+	gpio_request_pullup(GPIO_SDHID1_D0);
+	gpio_request_pullup(GPIO_SDHID1_D1);
+	gpio_request_pullup(GPIO_SDHID1_D2);
+	gpio_request_pullup(GPIO_SDHID1_D3);
+	gpio_request_pullup(GPIO_SDHICMD1);
 
 	sh7377_add_standard_devices();
 
diff --git a/arch/arm/mach-shmobile/board-kota2.c b/arch/arm/mach-shmobile/board-kota2.c
index f60f1b281cc4..21dbe54304d5 100644
--- a/arch/arm/mach-shmobile/board-kota2.c
+++ b/arch/arm/mach-shmobile/board-kota2.c
@@ -27,6 +27,8 @@
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/io.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 #include <linux/smsc911x.h>
 #include <linux/gpio.h>
 #include <linux/input.h>
@@ -49,6 +51,12 @@
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/traps.h>
 
+/* Dummy supplies, where voltage doesn't matter */
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+};
+
 /* SMSC 9220 */
 static struct resource smsc9220_resources[] = {
 	[0] = {
@@ -288,6 +296,13 @@ static struct platform_device leds_tpu30_device = {
 	.resource	= tpu30_resources,
 };
 
+/* Fixed 1.8V regulator to be used by MMCIF */
+static struct regulator_consumer_supply fixed1v8_power_consumers[] =
+{
+	REGULATOR_SUPPLY("vmmc", "sh_mmcif.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mmcif.0"),
+};
+
 /* MMCIF */
 static struct resource mmcif_resources[] = {
 	[0] = {
@@ -321,6 +336,15 @@ static struct platform_device mmcif_device = {
 	.resource       = mmcif_resources,
 };
 
+/* Fixed 3.3V regulator to be used by SDHI0 and SDHI1 */
+static struct regulator_consumer_supply fixed3v3_power_consumers[] =
+{
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.1"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.1"),
+};
+
 /* SDHI0 */
 static struct sh_mobile_sdhi_info sdhi0_info = {
 	.tmio_caps      = MMC_CAP_SD_HIGHSPEED,
@@ -411,6 +435,12 @@ static struct platform_device *kota2_devices[] __initdata = {
 
 static void __init kota2_init(void)
 {
+	regulator_register_always_on(0, "fixed-1.8V", fixed1v8_power_consumers,
+				     ARRAY_SIZE(fixed1v8_power_consumers), 1800000);
+	regulator_register_always_on(1, "fixed-3.3V", fixed3v3_power_consumers,
+				     ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
+	regulator_register_fixed(2, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	sh73a0_pinmux_init();
 
 	/* SCIFA2 (UART2) */
diff --git a/arch/arm/mach-shmobile/board-kzm9d.c b/arch/arm/mach-shmobile/board-kzm9d.c
index 6a33cf393428..2c986eaae7b4 100644
--- a/arch/arm/mach-shmobile/board-kzm9d.c
+++ b/arch/arm/mach-shmobile/board-kzm9d.c
@@ -21,6 +21,8 @@
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 #include <linux/smsc911x.h>
 #include <mach/common.h>
 #include <mach/emev2.h>
@@ -28,6 +30,12 @@
 #include <asm/mach/arch.h>
 #include <asm/hardware/gic.h>
 
+/* Dummy supplies, where voltage doesn't matter */
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+};
+
 /* Ether */
 static struct resource smsc911x_resources[] = {
 	[0] = {
@@ -63,6 +71,8 @@ static struct platform_device *kzm9d_devices[] __initdata = {
 
 void __init kzm9d_add_standard_devices(void)
 {
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	emev2_add_standard_devices();
 
 	platform_add_devices(kzm9d_devices, ARRAY_SIZE(kzm9d_devices));
diff --git a/arch/arm/mach-shmobile/board-kzm9g.c b/arch/arm/mach-shmobile/board-kzm9g.c
index c0ae815e7beb..53b7ea92c32c 100644
--- a/arch/arm/mach-shmobile/board-kzm9g.c
+++ b/arch/arm/mach-shmobile/board-kzm9g.c
@@ -30,9 +30,14 @@
 #include <linux/mmc/sh_mobile_sdhi.h>
 #include <linux/mfd/tmio.h>
 #include <linux/platform_device.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 #include <linux/smsc911x.h>
 #include <linux/usb/r8a66597.h>
+#include <linux/usb/renesas_usbhs.h>
 #include <linux/videodev2.h>
+#include <sound/sh_fsi.h>
+#include <sound/simple_card.h>
 #include <mach/irqs.h>
 #include <mach/sh73a0.h>
 #include <mach/common.h>
@@ -54,6 +59,20 @@
 #define GPIO_PCF8575_PORT15	(GPIO_NR + 13)
 #define GPIO_PCF8575_PORT16	(GPIO_NR + 14)
 
+/* Dummy supplies, where voltage doesn't matter */
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+};
+
+/*
+ * FSI-AK4648
+ *
+ * this command is required when playback.
+ *
+ * # amixer set "LINEOUT Mixer DACL" on
+ */
+
 /* SMSC 9221 */
 static struct resource smsc9221_resources[] = {
 	[0] = {
@@ -112,6 +131,151 @@ static struct platform_device usb_host_device = {
 	.resource	= usb_resources,
 };
 
+/* USB Func CN17 */
+struct usbhs_private {
+	unsigned int phy;
+	unsigned int cr2;
+	struct renesas_usbhs_platform_info info;
+};
+
+#define IRQ15			intcs_evt2irq(0x03e0)
+#define USB_PHY_MODE		(1 << 4)
+#define USB_PHY_INT_EN		((1 << 3) | (1 << 2))
+#define USB_PHY_ON		(1 << 1)
+#define USB_PHY_OFF		(1 << 0)
+#define USB_PHY_INT_CLR		(USB_PHY_ON | USB_PHY_OFF)
+
+#define usbhs_get_priv(pdev) \
+	container_of(renesas_usbhs_get_info(pdev), struct usbhs_private, info)
+
+static int usbhs_get_vbus(struct platform_device *pdev)
+{
+	struct usbhs_private *priv = usbhs_get_priv(pdev);
+
+	return !((1 << 7) & __raw_readw(priv->cr2));
+}
+
+static void usbhs_phy_reset(struct platform_device *pdev)
+{
+	struct usbhs_private *priv = usbhs_get_priv(pdev);
+
+	/* init phy */
+	__raw_writew(0x8a0a, priv->cr2);
+}
+
+static int usbhs_get_id(struct platform_device *pdev)
+{
+	return USBHS_GADGET;
+}
+
+static irqreturn_t usbhs_interrupt(int irq, void *data)
+{
+	struct platform_device *pdev = data;
+	struct usbhs_private *priv = usbhs_get_priv(pdev);
+
+	renesas_usbhs_call_notify_hotplug(pdev);
+
+	/* clear status */
+	__raw_writew(__raw_readw(priv->phy) | USB_PHY_INT_CLR, priv->phy);
+
+	return IRQ_HANDLED;
+}
+
+static int usbhs_hardware_init(struct platform_device *pdev)
+{
+	struct usbhs_private *priv = usbhs_get_priv(pdev);
+	int ret;
+
+	/* clear interrupt status */
+	__raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->phy);
+
+	ret = request_irq(IRQ15, usbhs_interrupt, IRQF_TRIGGER_HIGH,
+			  dev_name(&pdev->dev), pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "request_irq err\n");
+		return ret;
+	}
+
+	/* enable USB phy interrupt */
+	__raw_writew(USB_PHY_MODE | USB_PHY_INT_EN, priv->phy);
+
+	return 0;
+}
+
+static void usbhs_hardware_exit(struct platform_device *pdev)
+{
+	struct usbhs_private *priv = usbhs_get_priv(pdev);
+
+	/* clear interrupt status */
+	__raw_writew(USB_PHY_MODE | USB_PHY_INT_CLR, priv->phy);
+
+	free_irq(IRQ15, pdev);
+}
+
+static u32 usbhs_pipe_cfg[] = {
+	USB_ENDPOINT_XFER_CONTROL,
+	USB_ENDPOINT_XFER_ISOC,
+	USB_ENDPOINT_XFER_ISOC,
+	USB_ENDPOINT_XFER_BULK,
+	USB_ENDPOINT_XFER_BULK,
+	USB_ENDPOINT_XFER_BULK,
+	USB_ENDPOINT_XFER_INT,
+	USB_ENDPOINT_XFER_INT,
+	USB_ENDPOINT_XFER_INT,
+	USB_ENDPOINT_XFER_BULK,
+	USB_ENDPOINT_XFER_BULK,
+	USB_ENDPOINT_XFER_BULK,
+	USB_ENDPOINT_XFER_BULK,
+	USB_ENDPOINT_XFER_BULK,
+	USB_ENDPOINT_XFER_BULK,
+	USB_ENDPOINT_XFER_BULK,
+};
+
+static struct usbhs_private usbhs_private = {
+	.phy	= 0xe60781e0,		/* USBPHYINT */
+	.cr2	= 0xe605810c,		/* USBCR2 */
+	.info = {
+		.platform_callback = {
+			.hardware_init	= usbhs_hardware_init,
+			.hardware_exit	= usbhs_hardware_exit,
+			.get_id		= usbhs_get_id,
+			.phy_reset	= usbhs_phy_reset,
+			.get_vbus	= usbhs_get_vbus,
+		},
+		.driver_param = {
+			.buswait_bwait	= 4,
+			.has_otg	= 1,
+			.pipe_type	= usbhs_pipe_cfg,
+			.pipe_size	= ARRAY_SIZE(usbhs_pipe_cfg),
+		},
+	},
+};
+
+static struct resource usbhs_resources[] = {
+	[0] = {
+		.start	= 0xE6890000,
+		.end	= 0xE68900e6 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= gic_spi(62),
+		.end	= gic_spi(62),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device usbhs_device = {
+	.name	= "renesas_usbhs",
+	.id	= -1,
+	.dev = {
+		.dma_mask		= NULL,
+		.coherent_dma_mask	= 0xffffffff,
+		.platform_data		= &usbhs_private.info,
+	},
+	.num_resources	= ARRAY_SIZE(usbhs_resources),
+	.resource	= usbhs_resources,
+};
+
 /* LCDC */
 static struct fb_videomode kzm_lcdc_mode = {
 	.name		= "WVGA Panel",
@@ -166,6 +330,13 @@ static struct platform_device lcdc_device = {
 	},
 };
 
+/* Fixed 1.8V regulator to be used by MMCIF */
+static struct regulator_consumer_supply fixed1v8_power_consumers[] =
+{
+	REGULATOR_SUPPLY("vmmc", "sh_mmcif.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mmcif.0"),
+};
+
 /* MMCIF */
 static struct resource sh_mmcif_resources[] = {
 	[0] = {
@@ -187,6 +358,8 @@ static struct resource sh_mmcif_resources[] = {
 static struct sh_mmcif_plat_data sh_mmcif_platdata = {
 	.ocr		= MMC_VDD_165_195,
 	.caps		= MMC_CAP_8_BIT_DATA | MMC_CAP_NONREMOVABLE,
+	.slave_id_tx	= SHDMA_SLAVE_MMCIF_TX,
+	.slave_id_rx	= SHDMA_SLAVE_MMCIF_RX,
 };
 
 static struct platform_device mmc_device = {
@@ -200,6 +373,15 @@ static struct platform_device mmc_device = {
 	.resource	= sh_mmcif_resources,
 };
 
+/* Fixed 2.8V regulators to be used by SDHI0 and SDHI2 */
+static struct regulator_consumer_supply fixed2v8_power_consumers[] =
+{
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.2"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.2"),
+};
+
 /* SDHI */
 static struct sh_mobile_sdhi_info sdhi0_info = {
 	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT,
@@ -240,6 +422,50 @@ static struct platform_device sdhi0_device = {
 	},
 };
 
+/* Micro SD */
+static struct sh_mobile_sdhi_info sdhi2_info = {
+	.tmio_flags	= TMIO_MMC_HAS_IDLE_WAIT |
+			  TMIO_MMC_USE_GPIO_CD |
+			  TMIO_MMC_WRPROTECT_DISABLE,
+	.tmio_caps	= MMC_CAP_SD_HIGHSPEED,
+	.tmio_ocr_mask	= MMC_VDD_27_28 | MMC_VDD_28_29,
+	.cd_gpio	= GPIO_PORT13,
+};
+
+static struct resource sdhi2_resources[] = {
+	[0] = {
+		.name	= "SDHI2",
+		.start	= 0xee140000,
+		.end	= 0xee1400ff,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.name	= SH_MOBILE_SDHI_IRQ_CARD_DETECT,
+		.start	= gic_spi(103),
+		.flags	= IORESOURCE_IRQ,
+	},
+	[2] = {
+		.name	= SH_MOBILE_SDHI_IRQ_SDCARD,
+		.start	= gic_spi(104),
+		.flags	= IORESOURCE_IRQ,
+	},
+	[3] = {
+		.name	= SH_MOBILE_SDHI_IRQ_SDIO,
+		.start	= gic_spi(105),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device sdhi2_device = {
+	.name		= "sh_mobile_sdhi",
+	.id		= 2,
+	.num_resources	= ARRAY_SIZE(sdhi2_resources),
+	.resource	= sdhi2_resources,
+	.dev	= {
+		.platform_data	= &sdhi2_info,
+	},
+};
+
 /* KEY */
 #define GPIO_KEY(c, g, d) { .code = c, .gpio = g, .desc = d, .active_low = 1 }
 
@@ -267,11 +493,74 @@ static struct platform_device gpio_keys_device = {
 	},
 };
 
+/* FSI-AK4648 */
+static struct sh_fsi_platform_info fsi_info = {
+	.port_a = {
+		.tx_id = SHDMA_SLAVE_FSI2A_TX,
+	},
+};
+
+static struct resource fsi_resources[] = {
+	[0] = {
+		.name	= "FSI",
+		.start	= 0xEC230000,
+		.end	= 0xEC230400 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start  = gic_spi(146),
+		.flags  = IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device fsi_device = {
+	.name		= "sh_fsi2",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(fsi_resources),
+	.resource	= fsi_resources,
+	.dev	= {
+		.platform_data	= &fsi_info,
+	},
+};
+
+static struct asoc_simple_dai_init_info fsi2_ak4648_init_info = {
+	.fmt		= SND_SOC_DAIFMT_LEFT_J,
+	.codec_daifmt	= SND_SOC_DAIFMT_CBM_CFM,
+	.cpu_daifmt	= SND_SOC_DAIFMT_CBS_CFS,
+	.sysclk		= 11289600,
+};
+
+static struct asoc_simple_card_info fsi2_ak4648_info = {
+	.name		= "AK4648",
+	.card		= "FSI2A-AK4648",
+	.cpu_dai	= "fsia-dai",
+	.codec		= "ak4642-codec.0-0012",
+	.platform	= "sh_fsi2",
+	.codec_dai	= "ak4642-hifi",
+	.init		= &fsi2_ak4648_init_info,
+};
+
+static struct platform_device fsi_ak4648_device = {
+	.name	= "asoc-simple-card",
+	.dev	= {
+		.platform_data	= &fsi2_ak4648_info,
+	},
+};
+
 /* I2C */
 static struct pcf857x_platform_data pcf8575_pdata = {
 	.gpio_base	= GPIO_PCF8575_BASE,
 };
 
+static struct i2c_board_info i2c0_devices[] = {
+	{
+		I2C_BOARD_INFO("ak4648", 0x12),
+	},
+	{
+		I2C_BOARD_INFO("r2025sd", 0x32),
+	}
+};
+
 static struct i2c_board_info i2c1_devices[] = {
 	{
 		I2C_BOARD_INFO("st1232-ts", 0x55),
@@ -289,10 +578,14 @@ static struct i2c_board_info i2c3_devices[] = {
 static struct platform_device *kzm_devices[] __initdata = {
 	&smsc_device,
 	&usb_host_device,
+	&usbhs_device,
 	&lcdc_device,
 	&mmc_device,
 	&sdhi0_device,
+	&sdhi2_device,
 	&gpio_keys_device,
+	&fsi_device,
+	&fsi_ak4648_device,
 };
 
 /*
@@ -350,6 +643,12 @@ device_initcall(as3711_enable_lcdc_backlight);
 
 static void __init kzm_init(void)
 {
+	regulator_register_always_on(0, "fixed-1.8V", fixed1v8_power_consumers,
+				     ARRAY_SIZE(fixed1v8_power_consumers), 1800000);
+	regulator_register_always_on(1, "fixed-2.8V", fixed2v8_power_consumers,
+				     ARRAY_SIZE(fixed2v8_power_consumers), 2800000);
+	regulator_register_fixed(2, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	sh73a0_pinmux_init();
 
 	/* enable SCIFA4 */
@@ -427,15 +726,36 @@ static void __init kzm_init(void)
 	gpio_request(GPIO_PORT15, NULL);
 	gpio_direction_output(GPIO_PORT15, 1); /* power */
 
+	/* enable Micro SD */
+	gpio_request(GPIO_FN_SDHID2_0,		NULL);
+	gpio_request(GPIO_FN_SDHID2_1,		NULL);
+	gpio_request(GPIO_FN_SDHID2_2,		NULL);
+	gpio_request(GPIO_FN_SDHID2_3,		NULL);
+	gpio_request(GPIO_FN_SDHICMD2,		NULL);
+	gpio_request(GPIO_FN_SDHICLK2,		NULL);
+	gpio_request(GPIO_PORT14, NULL);
+	gpio_direction_output(GPIO_PORT14, 1); /* power */
+
 	/* I2C 3 */
 	gpio_request(GPIO_FN_PORT27_I2C_SCL3, NULL);
 	gpio_request(GPIO_FN_PORT28_I2C_SDA3, NULL);
 
+	/* enable FSI2 port A (ak4648) */
+	gpio_request(GPIO_FN_FSIACK,	NULL);
+	gpio_request(GPIO_FN_FSIAILR,	NULL);
+	gpio_request(GPIO_FN_FSIAIBT,	NULL);
+	gpio_request(GPIO_FN_FSIAISLD,	NULL);
+	gpio_request(GPIO_FN_FSIAOSLD,	NULL);
+
+	/* enable USB */
+	gpio_request(GPIO_FN_VBUS_0,	NULL);
+
 #ifdef CONFIG_CACHE_L2X0
 	/* Early BRESP enable, Shared attribute override enable, 64K*8way */
 	l2x0_init(IOMEM(0xf0100000), 0x40460000, 0x82000fff);
 #endif
 
+	i2c_register_board_info(0, i2c0_devices, ARRAY_SIZE(i2c0_devices));
 	i2c_register_board_info(1, i2c1_devices, ARRAY_SIZE(i2c1_devices));
 	i2c_register_board_info(3, i2c3_devices, ARRAY_SIZE(i2c3_devices));
 
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 150122a44630..7ea2b31e3199 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -41,6 +41,8 @@
 #include <linux/mtd/physmap.h>
 #include <linux/mtd/sh_flctl.h>
 #include <linux/pm_clock.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 #include <linux/smsc911x.h>
 #include <linux/sh_intc.h>
 #include <linux/tca6416_keypad.h>
@@ -203,31 +205,32 @@
  * amixer set "HPOUTR Mixer DACH" on
  */
 
-/*
- * FIXME !!
- *
- * gpio_no_direction
- * gpio_pull_down
- * are quick_hack.
- *
- * current gpio frame work doesn't have
- * the method to control only pull up/down/free.
- * this function should be replaced by correct gpio function
- */
-static void __init gpio_no_direction(u32 addr)
+/* Fixed 3.3V and 1.8V regulators to be used by multiple devices */
+static struct regulator_consumer_supply fixed1v8_power_consumers[] =
 {
-	__raw_writeb(0x00, addr);
-}
+	/*
+	 * J22 on mackerel switches mmcif.0 and sdhi.1 between 1.8V and 3.3V
+	 * Since we cannot support both voltages, we support the default 1.8V
+	 */
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.1"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.1"),
+	REGULATOR_SUPPLY("vmmc", "sh_mmcif.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mmcif.0"),
+};
 
-static void __init gpio_pull_down(u32 addr)
+static struct regulator_consumer_supply fixed3v3_power_consumers[] =
 {
-	u8 data = __raw_readb(addr);
-
-	data &= 0x0F;
-	data |= 0xA0;
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.0"),
+	REGULATOR_SUPPLY("vmmc", "sh_mobile_sdhi.2"),
+	REGULATOR_SUPPLY("vqmmc", "sh_mobile_sdhi.2"),
+};
 
-	__raw_writeb(data, addr);
-}
+/* Dummy supplies, where voltage doesn't matter */
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+};
 
 /* MTD */
 static struct mtd_partition nor_flash_partitions[] = {
@@ -1409,6 +1412,12 @@ static void __init mackerel_init(void)
 	u32 srcr4;
 	struct clk *clk;
 
+	regulator_register_always_on(0, "fixed-1.8V", fixed1v8_power_consumers,
+				     ARRAY_SIZE(fixed1v8_power_consumers), 1800000);
+	regulator_register_always_on(1, "fixed-3.3V", fixed3v3_power_consumers,
+				     ARRAY_SIZE(fixed3v3_power_consumers), 3300000);
+	regulator_register_fixed(2, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	/* External clock source */
 	clk_set_rate(&sh7372_dv_clki_clk, 27000000);
 
@@ -1458,11 +1467,11 @@ static void __init mackerel_init(void)
 
 	/* USBHS0 */
 	gpio_request(GPIO_FN_VBUS0_0, NULL);
-	gpio_pull_down(GPIO_PORT168CR); /* VBUS0_0 pull down */
+	gpio_request_pulldown(GPIO_PORT168CR); /* VBUS0_0 pull down */
 
 	/* USBHS1 */
 	gpio_request(GPIO_FN_VBUS0_1, NULL);
-	gpio_pull_down(GPIO_PORT167CR); /* VBUS0_1 pull down */
+	gpio_request_pulldown(GPIO_PORT167CR); /* VBUS0_1 pull down */
 	gpio_request(GPIO_FN_IDIN_1_113, NULL);
 
 	/* enable FSI2 port A (ak4643) */
@@ -1475,8 +1484,8 @@ static void __init mackerel_init(void)
 
 	gpio_request(GPIO_PORT9,  NULL);
 	gpio_request(GPIO_PORT10, NULL);
-	gpio_no_direction(GPIO_PORT9CR);  /* FSIAOBT needs no direction */
-	gpio_no_direction(GPIO_PORT10CR); /* FSIAOLR needs no direction */
+	gpio_direction_none(GPIO_PORT9CR);  /* FSIAOBT needs no direction */
+	gpio_direction_none(GPIO_PORT10CR); /* FSIAOLR needs no direction */
 
 	intc_set_priority(IRQ_FSI, 3); /* irq priority FSI(3) > SMSC911X(2) */
 
@@ -1614,20 +1623,20 @@ static void __init mackerel_init(void)
 
 	platform_add_devices(mackerel_devices, ARRAY_SIZE(mackerel_devices));
 
-	sh7372_add_device_to_domain(&sh7372_a4lc, &lcdc_device);
-	sh7372_add_device_to_domain(&sh7372_a4lc, &hdmi_lcdc_device);
-	sh7372_add_device_to_domain(&sh7372_a4lc, &meram_device);
-	sh7372_add_device_to_domain(&sh7372_a4mp, &fsi_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &usbhs0_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &usbhs1_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &nand_flash_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &sh_mmcif_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi0_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4lc, &lcdc_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4lc, &hdmi_lcdc_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4lc, &meram_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4mp, &fsi_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &usbhs0_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &usbhs1_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &nand_flash_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sh_mmcif_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sdhi0_device);
 #if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
-	sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi1_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sdhi1_device);
 #endif
-	sh7372_add_device_to_domain(&sh7372_a3sp, &sdhi2_device);
-	sh7372_add_device_to_domain(&sh7372_a4r, &ceu_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &sdhi2_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4r, &ceu_device);
 
 	hdmi_init_pm_clock();
 	sh7372_pm_init();
diff --git a/arch/arm/mach-shmobile/board-marzen.c b/arch/arm/mach-shmobile/board-marzen.c
index 14de3787cafc..3a528cf4366c 100644
--- a/arch/arm/mach-shmobile/board-marzen.c
+++ b/arch/arm/mach-shmobile/board-marzen.c
@@ -27,6 +27,8 @@
 #include <linux/io.h>
 #include <linux/gpio.h>
 #include <linux/dma-mapping.h>
+#include <linux/regulator/fixed.h>
+#include <linux/regulator/machine.h>
 #include <linux/smsc911x.h>
 #include <mach/hardware.h>
 #include <mach/r8a7779.h>
@@ -37,6 +39,12 @@
 #include <asm/hardware/gic.h>
 #include <asm/traps.h>
 
+/* Dummy supplies, where voltage doesn't matter */
+static struct regulator_consumer_supply dummy_supplies[] = {
+	REGULATOR_SUPPLY("vddvario", "smsc911x"),
+	REGULATOR_SUPPLY("vdd33a", "smsc911x"),
+};
+
 /* SMSC LAN89218 */
 static struct resource smsc911x_resources[] = {
 	[0] = {
@@ -73,6 +81,8 @@ static struct platform_device *marzen_devices[] __initdata = {
 
 static void __init marzen_init(void)
 {
+	regulator_register_fixed(0, dummy_supplies, ARRAY_SIZE(dummy_supplies));
+
 	r8a7779_pinmux_init();
 
 	/* SCIF2 (CN18: DEBUG0) */
diff --git a/arch/arm/mach-shmobile/clock-r8a7740.c b/arch/arm/mach-shmobile/clock-r8a7740.c
index 26eea5f21054..ad5fccc7b5e7 100644
--- a/arch/arm/mach-shmobile/clock-r8a7740.c
+++ b/arch/arm/mach-shmobile/clock-r8a7740.c
@@ -43,7 +43,10 @@
 /* CPG registers */
 #define FRQCRA		0xe6150000
 #define FRQCRB		0xe6150004
+#define VCLKCR1		0xE6150008
+#define VCLKCR2		0xE615000c
 #define FRQCRC		0xe61500e0
+#define FSIACKCR	0xe6150018
 #define PLLC01CR	0xe6150028
 
 #define SUBCKCR		0xe6150080
@@ -54,6 +57,8 @@
 #define MSTPSR2		0xe6150040
 #define MSTPSR3		0xe6150048
 #define MSTPSR4		0xe615004c
+#define FSIBCKCR	0xe6150090
+#define HDMICKCR	0xe6150094
 #define SMSTPCR0	0xe6150130
 #define SMSTPCR1	0xe6150134
 #define SMSTPCR2	0xe6150138
@@ -271,6 +276,13 @@ static struct clk usb24_clk = {
 	.parent		= &usb24s_clk,
 };
 
+/* External FSIACK/FSIBCK clock */
+static struct clk fsiack_clk = {
+};
+
+static struct clk fsibck_clk = {
+};
+
 struct clk *main_clks[] = {
 	&extalr_clk,
 	&extal1_clk,
@@ -288,6 +300,8 @@ struct clk *main_clks[] = {
 	&pllc1_div2_clk,
 	&usb24s_clk,
 	&usb24_clk,
+	&fsiack_clk,
+	&fsibck_clk,
 };
 
 static void div4_kick(struct clk *clk)
@@ -313,6 +327,107 @@ static struct clk_div4_table div4_table = {
 	.kick = div4_kick,
 };
 
+/* DIV6 reparent */
+enum {
+	DIV6_HDMI,
+	DIV6_VCLK1, DIV6_VCLK2,
+	DIV6_FSIA, DIV6_FSIB,
+	DIV6_REPARENT_NR,
+};
+
+static struct clk *hdmi_parent[] = {
+	[0] = &pllc1_div2_clk,
+	[1] = &system_clk,
+	[2] = &dv_clk
+};
+
+static struct clk *vclk_parents[8] = {
+	[0] = &pllc1_div2_clk,
+	[2] = &dv_clk,
+	[3] = &usb24s_clk,
+	[4] = &extal1_div2_clk,
+	[5] = &extalr_clk,
+};
+
+static struct clk *fsia_parents[] = {
+	[0] = &pllc1_div2_clk,
+	[1] = &fsiack_clk, /* external clock */
+};
+
+static struct clk *fsib_parents[] = {
+	[0] = &pllc1_div2_clk,
+	[1] = &fsibck_clk, /* external clock */
+};
+
+static struct clk div6_reparent_clks[DIV6_REPARENT_NR] = {
+	[DIV6_HDMI] = SH_CLK_DIV6_EXT(HDMICKCR, 0,
+				      hdmi_parent, ARRAY_SIZE(hdmi_parent), 6, 2),
+	[DIV6_VCLK1] = SH_CLK_DIV6_EXT(VCLKCR1, 0,
+				       vclk_parents, ARRAY_SIZE(vclk_parents), 12, 3),
+	[DIV6_VCLK2] = SH_CLK_DIV6_EXT(VCLKCR2, 0,
+				       vclk_parents, ARRAY_SIZE(vclk_parents), 12, 3),
+	[DIV6_FSIA] = SH_CLK_DIV6_EXT(FSIACKCR, 0,
+				      fsia_parents, ARRAY_SIZE(fsia_parents), 6, 2),
+	[DIV6_FSIB] = SH_CLK_DIV6_EXT(FSIBCKCR, 0,
+				      fsib_parents, ARRAY_SIZE(fsib_parents), 6, 2),
+};
+
+/* HDMI1/2 clock */
+static unsigned long hdmi12_recalc(struct clk *clk)
+{
+	u32 val = __raw_readl(HDMICKCR);
+	int shift = (int)clk->priv;
+
+	val >>= shift;
+	val &= 0x3;
+
+	return clk->parent->rate / (1 << val);
+};
+
+static int hdmi12_set_rate(struct clk *clk, unsigned long rate)
+{
+	u32 val, mask;
+	int i, shift;
+
+	for (i = 0; i < 3; i++)
+		if (rate == clk->parent->rate / (1 << i))
+			goto find;
+	return -ENODEV;
+
+find:
+	shift = (int)clk->priv;
+
+	val = __raw_readl(HDMICKCR);
+	mask = ~(0x3 << shift);
+	val = (val & mask) | i << shift;
+	__raw_writel(val, HDMICKCR);
+
+	return 0;
+};
+
+static struct sh_clk_ops hdmi12_clk_ops = {
+	.recalc		= hdmi12_recalc,
+	.set_rate	= hdmi12_set_rate,
+};
+
+static struct clk hdmi1_clk = {
+	.ops		= &hdmi12_clk_ops,
+	.priv		= (void *)9,
+	.parent		= &div6_reparent_clks[DIV6_HDMI],  /* late install */
+};
+
+static struct clk hdmi2_clk = {
+	.ops		= &hdmi12_clk_ops,
+	.priv		= (void *)11,
+	.parent		= &div6_reparent_clks[DIV6_HDMI], /* late install */
+};
+
+static struct clk *late_main_clks[] = {
+	&hdmi1_clk,
+	&hdmi2_clk,
+};
+
+/* MSTP */
 enum {
 	DIV4_I, DIV4_ZG, DIV4_B, DIV4_M1, DIV4_HP,
 	DIV4_HPP, DIV4_USBP, DIV4_S, DIV4_ZB, DIV4_M3, DIV4_CP,
@@ -343,11 +458,12 @@ static struct clk div6_clks[DIV6_NR] = {
 };
 
 enum {
-	MSTP125,
+	MSTP128, MSTP127, MSTP125,
 	MSTP116, MSTP111, MSTP100, MSTP117,
 
 	MSTP230,
 	MSTP222,
+	MSTP218, MSTP217, MSTP216, MSTP214,
 	MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
 
 	MSTP329, MSTP328, MSTP323, MSTP320,
@@ -360,6 +476,8 @@ enum {
 };
 
 static struct clk mstp_clks[MSTP_NR] = {
+	[MSTP128] = SH_CLK_MSTP32(&div4_clks[DIV4_S],	SMSTPCR1, 28, 0), /* CEU21 */
+	[MSTP127] = SH_CLK_MSTP32(&div4_clks[DIV4_S],	SMSTPCR1, 27, 0), /* CEU20 */
 	[MSTP125] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR1, 25, 0), /* TMU0 */
 	[MSTP117] = SH_CLK_MSTP32(&div4_clks[DIV4_B],	SMSTPCR1, 17, 0), /* LCDC1 */
 	[MSTP116] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR1, 16, 0), /* IIC0 */
@@ -368,6 +486,10 @@ static struct clk mstp_clks[MSTP_NR] = {
 
 	[MSTP230] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2, 30, 0), /* SCIFA6 */
 	[MSTP222] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2, 22, 0), /* SCIFA7 */
+	[MSTP218] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],  SMSTPCR2, 18, 0), /* DMAC1 */
+	[MSTP217] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],  SMSTPCR2, 17, 0), /* DMAC2 */
+	[MSTP216] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],  SMSTPCR2, 16, 0), /* DMAC3 */
+	[MSTP214] = SH_CLK_MSTP32(&div4_clks[DIV4_HP],  SMSTPCR2, 14, 0), /* USBDMAC */
 	[MSTP207] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2,  7, 0), /* SCIFA5 */
 	[MSTP206] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2,  6, 0), /* SCIFB */
 	[MSTP204] = SH_CLK_MSTP32(&div6_clks[DIV6_SUB],	SMSTPCR2,  4, 0), /* SCIFA0 */
@@ -408,6 +530,12 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_CON_ID("pllc1_clk",		&pllc1_clk),
 	CLKDEV_CON_ID("pllc1_div2_clk",		&pllc1_div2_clk),
 	CLKDEV_CON_ID("usb24s",			&usb24s_clk),
+	CLKDEV_CON_ID("hdmi1",			&hdmi1_clk),
+	CLKDEV_CON_ID("hdmi2",			&hdmi2_clk),
+	CLKDEV_CON_ID("video1",			&div6_reparent_clks[DIV6_VCLK1]),
+	CLKDEV_CON_ID("video2",			&div6_reparent_clks[DIV6_VCLK2]),
+	CLKDEV_CON_ID("fsiack",			&fsiack_clk),
+	CLKDEV_CON_ID("fsibck",			&fsibck_clk),
 
 	/* DIV4 clocks */
 	CLKDEV_CON_ID("i_clk",			&div4_clks[DIV4_I]),
@@ -430,6 +558,8 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("i2c-sh_mobile.0",	&mstp_clks[MSTP116]),
 	CLKDEV_DEV_ID("sh_mobile_lcdc_fb.1",	&mstp_clks[MSTP117]),
 	CLKDEV_DEV_ID("sh_tmu.0",		&mstp_clks[MSTP125]),
+	CLKDEV_DEV_ID("sh_mobile_ceu.0",	&mstp_clks[MSTP127]),
+	CLKDEV_DEV_ID("sh_mobile_ceu.1",	&mstp_clks[MSTP128]),
 
 	CLKDEV_DEV_ID("sh-sci.4",		&mstp_clks[MSTP200]),
 	CLKDEV_DEV_ID("sh-sci.3",		&mstp_clks[MSTP201]),
@@ -438,7 +568,10 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("sh-sci.0",		&mstp_clks[MSTP204]),
 	CLKDEV_DEV_ID("sh-sci.8",		&mstp_clks[MSTP206]),
 	CLKDEV_DEV_ID("sh-sci.5",		&mstp_clks[MSTP207]),
-
+	CLKDEV_DEV_ID("sh-dma-engine.3",	&mstp_clks[MSTP214]),
+	CLKDEV_DEV_ID("sh-dma-engine.2",	&mstp_clks[MSTP216]),
+	CLKDEV_DEV_ID("sh-dma-engine.1",	&mstp_clks[MSTP217]),
+	CLKDEV_DEV_ID("sh-dma-engine.0",	&mstp_clks[MSTP218]),
 	CLKDEV_DEV_ID("sh-sci.7",		&mstp_clks[MSTP222]),
 	CLKDEV_DEV_ID("sh-sci.6",		&mstp_clks[MSTP230]),
 
@@ -459,6 +592,10 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_ICK_ID("phy",	"renesas_usbhs",	&mstp_clks[MSTP406]),
 	CLKDEV_ICK_ID("pci",	"renesas_usbhs",	&div4_clks[DIV4_USBP]),
 	CLKDEV_ICK_ID("usb24",	"renesas_usbhs",	&usb24_clk),
+	CLKDEV_ICK_ID("ick",	"sh-mobile-hdmi",	&div6_reparent_clks[DIV6_HDMI]),
+
+	CLKDEV_ICK_ID("icka", "sh_fsi2",	&div6_reparent_clks[DIV6_FSIA]),
+	CLKDEV_ICK_ID("ickb", "sh_fsi2",	&div6_reparent_clks[DIV6_FSIB]),
 };
 
 void __init r8a7740_clock_init(u8 md_ck)
@@ -495,7 +632,14 @@ void __init r8a7740_clock_init(u8 md_ck)
 		ret = sh_clk_div6_register(div6_clks, DIV6_NR);
 
 	if (!ret)
-		ret = sh_clk_mstp32_register(mstp_clks, MSTP_NR);
+		ret = sh_clk_div6_reparent_register(div6_reparent_clks,
+						    DIV6_REPARENT_NR);
+
+	if (!ret)
+		ret = sh_clk_mstp_register(mstp_clks, MSTP_NR);
+
+	for (k = 0; !ret && (k < ARRAY_SIZE(late_main_clks)); k++)
+		ret = clk_register(late_main_clks[k]);
 
 	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
diff --git a/arch/arm/mach-shmobile/clock-r8a7779.c b/arch/arm/mach-shmobile/clock-r8a7779.c
index 7d6e9fe47b56..339c62c824d5 100644
--- a/arch/arm/mach-shmobile/clock-r8a7779.c
+++ b/arch/arm/mach-shmobile/clock-r8a7779.c
@@ -162,7 +162,7 @@ void __init r8a7779_clock_init(void)
 		ret = sh_clk_div4_register(div4_clks, DIV4_NR, &div4_table);
 
 	if (!ret)
-		ret = sh_clk_mstp32_register(mstp_clks, MSTP_NR);
+		ret = sh_clk_mstp_register(mstp_clks, MSTP_NR);
 
 	for (k = 0; !ret && (k < ARRAY_SIZE(late_main_clks)); k++)
 		ret = clk_register(late_main_clks[k]);
diff --git a/arch/arm/mach-shmobile/clock-sh7367.c b/arch/arm/mach-shmobile/clock-sh7367.c
index 006e7b5d304c..162b791b8984 100644
--- a/arch/arm/mach-shmobile/clock-sh7367.c
+++ b/arch/arm/mach-shmobile/clock-sh7367.c
@@ -344,7 +344,7 @@ void __init sh7367_clock_init(void)
 		ret = sh_clk_div6_register(div6_clks, DIV6_NR);
 
 	if (!ret)
-		ret = sh_clk_mstp32_register(mstp_clks, MSTP_NR);
+		ret = sh_clk_mstp_register(mstp_clks, MSTP_NR);
 
 	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c
index 94d1f88246d3..5a2894b1c965 100644
--- a/arch/arm/mach-shmobile/clock-sh7372.c
+++ b/arch/arm/mach-shmobile/clock-sh7372.c
@@ -704,7 +704,7 @@ void __init sh7372_clock_init(void)
 		ret = sh_clk_div6_reparent_register(div6_reparent_clks, DIV6_REPARENT_NR);
 
 	if (!ret)
-		ret = sh_clk_mstp32_register(mstp_clks, MSTP_NR);
+		ret = sh_clk_mstp_register(mstp_clks, MSTP_NR);
 
 	for (k = 0; !ret && (k < ARRAY_SIZE(late_main_clks)); k++)
 		ret = clk_register(late_main_clks[k]);
diff --git a/arch/arm/mach-shmobile/clock-sh7377.c b/arch/arm/mach-shmobile/clock-sh7377.c
index 0798a15936c3..85f2a3ec2c44 100644
--- a/arch/arm/mach-shmobile/clock-sh7377.c
+++ b/arch/arm/mach-shmobile/clock-sh7377.c
@@ -355,7 +355,7 @@ void __init sh7377_clock_init(void)
 		ret = sh_clk_div6_register(div6_clks, DIV6_NR);
 
 	if (!ret)
-		ret = sh_clk_mstp32_register(mstp_clks, MSTP_NR);
+		ret = sh_clk_mstp_register(mstp_clks, MSTP_NR);
 
 	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
 
diff --git a/arch/arm/mach-shmobile/clock-sh73a0.c b/arch/arm/mach-shmobile/clock-sh73a0.c
index 3946c4ba2aa8..7f8da18a8580 100644
--- a/arch/arm/mach-shmobile/clock-sh73a0.c
+++ b/arch/arm/mach-shmobile/clock-sh73a0.c
@@ -475,9 +475,9 @@ static struct clk *late_main_clks[] = {
 
 enum { MSTP001,
 	MSTP129, MSTP128, MSTP127, MSTP126, MSTP125, MSTP118, MSTP116, MSTP100,
-	MSTP219, MSTP218,
+	MSTP219, MSTP218, MSTP217,
 	MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
-	MSTP331, MSTP329, MSTP325, MSTP323,
+	MSTP331, MSTP329, MSTP328, MSTP325, MSTP323, MSTP322,
 	MSTP314, MSTP313, MSTP312, MSTP311,
 	MSTP303, MSTP302, MSTP301, MSTP300,
 	MSTP411, MSTP410, MSTP403,
@@ -498,6 +498,7 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP100] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 0, 0), /* LCDC0 */
 	[MSTP219] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 19, 0), /* SCIFA7 */
 	[MSTP218] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 18, 0), /* SY-DMAC */
+	[MSTP217] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 17, 0), /* MP-DMAC */
 	[MSTP207] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 7, 0), /* SCIFA5 */
 	[MSTP206] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 6, 0), /* SCIFB */
 	[MSTP204] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 4, 0), /* SCIFA0 */
@@ -507,8 +508,10 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP200] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 0, 0), /* SCIFA4 */
 	[MSTP331] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 31, 0), /* SCIFA6 */
 	[MSTP329] = MSTP(&r_clk, SMSTPCR3, 29, 0), /* CMT10 */
+	[MSTP328] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 28, 0), /*FSI*/
 	[MSTP325] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 25, 0), /* IrDA */
 	[MSTP323] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 23, 0), /* IIC1 */
+	[MSTP322] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 22, 0), /* USB */
 	[MSTP314] = MSTP(&div6_clks[DIV6_SDHI0], SMSTPCR3, 14, 0), /* SDHI0 */
 	[MSTP313] = MSTP(&div6_clks[DIV6_SDHI1], SMSTPCR3, 13, 0), /* SDHI1 */
 	[MSTP312] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 12, 0), /* MMCIF0 */
@@ -553,6 +556,7 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */
 	CLKDEV_DEV_ID("sh-sci.7", &mstp_clks[MSTP219]), /* SCIFA7 */
 	CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP218]), /* SY-DMAC */
+	CLKDEV_DEV_ID("sh-dma-engine.1", &mstp_clks[MSTP217]), /* MP-DMAC */
 	CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */
 	CLKDEV_DEV_ID("sh-sci.8", &mstp_clks[MSTP206]), /* SCIFB */
 	CLKDEV_DEV_ID("sh-sci.0", &mstp_clks[MSTP204]), /* SCIFA0 */
@@ -562,8 +566,10 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("sh-sci.4", &mstp_clks[MSTP200]), /* SCIFA4 */
 	CLKDEV_DEV_ID("sh-sci.6", &mstp_clks[MSTP331]), /* SCIFA6 */
 	CLKDEV_DEV_ID("sh_cmt.10", &mstp_clks[MSTP329]), /* CMT10 */
+	CLKDEV_DEV_ID("sh_fsi2", &mstp_clks[MSTP328]), /* FSI */
 	CLKDEV_DEV_ID("sh_irda.0", &mstp_clks[MSTP325]), /* IrDA */
 	CLKDEV_DEV_ID("i2c-sh_mobile.1", &mstp_clks[MSTP323]), /* I2C1 */
+	CLKDEV_DEV_ID("renesas_usbhs", &mstp_clks[MSTP322]), /* USB */
 	CLKDEV_DEV_ID("sh_mobile_sdhi.0", &mstp_clks[MSTP314]), /* SDHI0 */
 	CLKDEV_DEV_ID("sh_mobile_sdhi.1", &mstp_clks[MSTP313]), /* SDHI1 */
 	CLKDEV_DEV_ID("sh_mmcif.0", &mstp_clks[MSTP312]), /* MMCIF0 */
@@ -612,7 +618,7 @@ void __init sh73a0_clock_init(void)
 		ret = sh_clk_div6_reparent_register(div6_clks, DIV6_NR);
 
 	if (!ret)
-		ret = sh_clk_mstp32_register(mstp_clks, MSTP_NR);
+		ret = sh_clk_mstp_register(mstp_clks, MSTP_NR);
 
 	for (k = 0; !ret && (k < ARRAY_SIZE(late_main_clks)); k++)
 		ret = clk_register(late_main_clks[k]);
diff --git a/arch/arm/mach-shmobile/include/mach/common.h b/arch/arm/mach-shmobile/include/mach/common.h
index 01e2bc014f15..45e61dada030 100644
--- a/arch/arm/mach-shmobile/include/mach/common.h
+++ b/arch/arm/mach-shmobile/include/mach/common.h
@@ -77,6 +77,7 @@ extern void r8a7779_add_standard_devices(void);
 extern void r8a7779_clock_init(void);
 extern void r8a7779_pinmux_init(void);
 extern void r8a7779_pm_init(void);
+extern void r8a7740_meram_workaround(void);
 
 extern unsigned int r8a7779_get_core_count(void);
 extern int r8a7779_platform_cpu_kill(unsigned int cpu);
diff --git a/arch/arm/mach-shmobile/include/mach/dma-register.h b/arch/arm/mach-shmobile/include/mach/dma-register.h
new file mode 100644
index 000000000000..97c40bd9b94f
--- /dev/null
+++ b/arch/arm/mach-shmobile/include/mach/dma-register.h
@@ -0,0 +1,84 @@
+/*
+ * SH-ARM CPU-specific DMA definitions, used by both DMA drivers
+ *
+ * Copyright (C) 2012 Renesas Solutions Corp
+ *
+ * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ *
+ * Based on arch/sh/include/cpu-sh4/cpu/dma-register.h
+ * Copyright (C) 2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef DMA_REGISTER_H
+#define DMA_REGISTER_H
+
+/*
+ *		Direct Memory Access Controller
+ */
+
+/* Transmit sizes and respective CHCR register values */
+enum {
+	XMIT_SZ_8BIT		= 0,
+	XMIT_SZ_16BIT		= 1,
+	XMIT_SZ_32BIT		= 2,
+	XMIT_SZ_64BIT		= 7,
+	XMIT_SZ_128BIT		= 3,
+	XMIT_SZ_256BIT		= 4,
+	XMIT_SZ_512BIT		= 5,
+};
+
+/* log2(size / 8) - used to calculate number of transfers */
+static const unsigned int dma_ts_shift[] = {
+	[XMIT_SZ_8BIT]		= 0,
+	[XMIT_SZ_16BIT]		= 1,
+	[XMIT_SZ_32BIT]		= 2,
+	[XMIT_SZ_64BIT]		= 3,
+	[XMIT_SZ_128BIT]	= 4,
+	[XMIT_SZ_256BIT]	= 5,
+	[XMIT_SZ_512BIT]	= 6,
+};
+
+#define TS_LOW_BIT	0x3 /* --xx */
+#define TS_HI_BIT	0xc /* xx-- */
+
+#define TS_LOW_SHIFT	(3)
+#define TS_HI_SHIFT	(20 - 2)	/* 2 bits for shifted low TS */
+
+#define TS_INDEX2VAL(i) \
+	((((i) & TS_LOW_BIT) << TS_LOW_SHIFT) |\
+	 (((i) & TS_HI_BIT)  << TS_HI_SHIFT))
+
+#define CHCR_TX(xmit_sz) (DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL((xmit_sz)))
+#define CHCR_RX(xmit_sz) (DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL((xmit_sz)))
+
+
+/*
+ *		USB High-Speed DMAC
+ */
+/* Transmit sizes and respective CHCR register values */
+enum {
+	USBTS_XMIT_SZ_8BYTE		= 0,
+	USBTS_XMIT_SZ_16BYTE		= 1,
+	USBTS_XMIT_SZ_32BYTE		= 2,
+};
+
+/* log2(size / 8) - used to calculate number of transfers */
+static const unsigned int dma_usbts_shift[] = {
+	[USBTS_XMIT_SZ_8BYTE]	= 3,
+	[USBTS_XMIT_SZ_16BYTE]	= 4,
+	[USBTS_XMIT_SZ_32BYTE]	= 5,
+};
+
+#define USBTS_LOW_BIT	0x3 /* --xx */
+#define USBTS_HI_BIT	0x0 /* ---- */
+
+#define USBTS_LOW_SHIFT	6
+#define USBTS_HI_SHIFT	0
+
+#define USBTS_INDEX2VAL(i) (((i) & 3) << 6)
+
+#endif /* DMA_REGISTER_H */
diff --git a/arch/arm/mach-shmobile/include/mach/gpio.h b/arch/arm/mach-shmobile/include/mach/gpio.h
index de795b42232a..844507d937cb 100644
--- a/arch/arm/mach-shmobile/include/mach/gpio.h
+++ b/arch/arm/mach-shmobile/include/mach/gpio.h
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/sh_pfc.h>
+#include <linux/io.h>
 
 #ifdef CONFIG_GPIOLIB
 
@@ -27,4 +28,35 @@ static inline int irq_to_gpio(unsigned int irq)
 
 #endif /* CONFIG_GPIOLIB */
 
+/*
+ * FIXME !!
+ *
+ * current gpio frame work doesn't have
+ * the method to control only pull up/down/free.
+ * this function should be replaced by correct gpio function
+ */
+static inline void __init gpio_direction_none(u32 addr)
+{
+	__raw_writeb(0x00, addr);
+}
+
+static inline void __init gpio_request_pullup(u32 addr)
+{
+	u8 data = __raw_readb(addr);
+
+	data &= 0x0F;
+	data |= 0xC0;
+	__raw_writeb(data, addr);
+}
+
+static inline void __init gpio_request_pulldown(u32 addr)
+{
+	u8 data = __raw_readb(addr);
+
+	data &= 0x0F;
+	data |= 0xA0;
+
+	__raw_writeb(data, addr);
+}
+
 #endif /* __ASM_ARCH_GPIO_H */
diff --git a/arch/arm/mach-shmobile/include/mach/pm-rmobile.h b/arch/arm/mach-shmobile/include/mach/pm-rmobile.h
new file mode 100644
index 000000000000..5a402840fe28
--- /dev/null
+++ b/arch/arm/mach-shmobile/include/mach/pm-rmobile.h
@@ -0,0 +1,44 @@
+/*
+ * Copyright (C) 2012 Renesas Solutions Corp.
+ *
+ * Kuninori Morimoto <morimoto.kuninori@renesas.com>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#ifndef PM_RMOBILE_H
+#define PM_RMOBILE_H
+
+#include <linux/pm_domain.h>
+
+struct platform_device;
+
+struct rmobile_pm_domain {
+	struct generic_pm_domain genpd;
+	struct dev_power_governor *gov;
+	int (*suspend)(void);
+	void (*resume)(void);
+	unsigned int bit_shift;
+	bool no_debug;
+};
+
+static inline
+struct rmobile_pm_domain *to_rmobile_pd(struct generic_pm_domain *d)
+{
+	return container_of(d, struct rmobile_pm_domain, genpd);
+}
+
+#ifdef CONFIG_PM
+extern void rmobile_init_pm_domain(struct rmobile_pm_domain *rmobile_pd);
+extern void rmobile_add_device_to_domain(struct rmobile_pm_domain *rmobile_pd,
+					struct platform_device *pdev);
+extern void rmobile_pm_add_subdomain(struct rmobile_pm_domain *rmobile_pd,
+				    struct rmobile_pm_domain *rmobile_sd);
+#else
+#define rmobile_init_pm_domain(pd) do { } while (0)
+#define rmobile_add_device_to_domain(pd, pdev) do { } while (0)
+#define rmobile_pm_add_subdomain(pd, sd) do { } while (0)
+#endif /* CONFIG_PM */
+
+#endif /* PM_RMOBILE_H */
diff --git a/arch/arm/mach-shmobile/include/mach/r8a7740.h b/arch/arm/mach-shmobile/include/mach/r8a7740.h
index 9d447abb969c..7143147780df 100644
--- a/arch/arm/mach-shmobile/include/mach/r8a7740.h
+++ b/arch/arm/mach-shmobile/include/mach/r8a7740.h
@@ -19,6 +19,8 @@
 #ifndef __ASM_R8A7740_H__
 #define __ASM_R8A7740_H__
 
+#include <mach/pm-rmobile.h>
+
 /*
  * MD_CKx pin
  */
@@ -139,7 +141,7 @@ enum {
 	GPIO_FN_DBGMD10,	GPIO_FN_DBGMD11,	GPIO_FN_DBGMD20,
 	GPIO_FN_DBGMD21,
 
-	/* FSI */
+	/* FSI-A */
 	GPIO_FN_FSIAISLD_PORT0,		/* FSIAISLD Port 0/5 */
 	GPIO_FN_FSIAISLD_PORT5,
 	GPIO_FN_FSIASPDIF_PORT9,	/* FSIASPDIF Port 9/18 */
@@ -150,6 +152,9 @@ enum {
 	GPIO_FN_FSIACK,		GPIO_FN_FSIAILR,
 	GPIO_FN_FSIAIBT,
 
+	/* FSI-B */
+	GPIO_FN_FSIBCK,
+
 	/* FMSI */
 	GPIO_FN_FMSISLD_PORT1, /* FMSISLD Port 1/6 */
 	GPIO_FN_FMSISLD_PORT6,
@@ -565,6 +570,10 @@ enum {
 	GPIO_FN_RESETP_PULLUP,
 	GPIO_FN_RESETP_PLAIN,
 
+	/* HDMI */
+	GPIO_FN_HDMI_HPD,
+	GPIO_FN_HDMI_CEC,
+
 	/* SDENC */
 	GPIO_FN_SDENC_CPG,
 	GPIO_FN_SDENC_DV_CLKI,
@@ -581,4 +590,26 @@ enum {
 	GPIO_FN_TRACEAUD_FROM_MEMC,
 };
 
+/* DMA slave IDs */
+enum {
+	SHDMA_SLAVE_INVALID,
+	SHDMA_SLAVE_SDHI0_RX,
+	SHDMA_SLAVE_SDHI0_TX,
+	SHDMA_SLAVE_SDHI1_RX,
+	SHDMA_SLAVE_SDHI1_TX,
+	SHDMA_SLAVE_SDHI2_RX,
+	SHDMA_SLAVE_SDHI2_TX,
+	SHDMA_SLAVE_FSIA_RX,
+	SHDMA_SLAVE_FSIA_TX,
+	SHDMA_SLAVE_FSIB_TX,
+	SHDMA_SLAVE_USBHS_TX,
+	SHDMA_SLAVE_USBHS_RX,
+};
+
+#ifdef CONFIG_PM
+extern struct rmobile_pm_domain r8a7740_pd_a4s;
+extern struct rmobile_pm_domain r8a7740_pd_a3sp;
+extern struct rmobile_pm_domain r8a7740_pd_a4lc;
+#endif /* CONFIG_PM */
+
 #endif /* __ASM_R8A7740_H__ */
diff --git a/arch/arm/mach-shmobile/include/mach/sh7372.h b/arch/arm/mach-shmobile/include/mach/sh7372.h
index 915d0093da08..b59048e6d8fd 100644
--- a/arch/arm/mach-shmobile/include/mach/sh7372.h
+++ b/arch/arm/mach-shmobile/include/mach/sh7372.h
@@ -13,6 +13,7 @@
 
 #include <linux/sh_clk.h>
 #include <linux/pm_domain.h>
+#include <mach/pm-rmobile.h>
 
 /*
  * Pin Function Controller:
@@ -477,42 +478,16 @@ extern struct clk sh7372_fsibck_clk;
 extern struct clk sh7372_fsidiva_clk;
 extern struct clk sh7372_fsidivb_clk;
 
-struct platform_device;
-
-struct sh7372_pm_domain {
-	struct generic_pm_domain genpd;
-	struct dev_power_governor *gov;
-	int (*suspend)(void);
-	void (*resume)(void);
-	unsigned int bit_shift;
-	bool no_debug;
-};
-
-static inline struct sh7372_pm_domain *to_sh7372_pd(struct generic_pm_domain *d)
-{
-	return container_of(d, struct sh7372_pm_domain, genpd);
-}
-
 #ifdef CONFIG_PM
-extern struct sh7372_pm_domain sh7372_a4lc;
-extern struct sh7372_pm_domain sh7372_a4mp;
-extern struct sh7372_pm_domain sh7372_d4;
-extern struct sh7372_pm_domain sh7372_a4r;
-extern struct sh7372_pm_domain sh7372_a3rv;
-extern struct sh7372_pm_domain sh7372_a3ri;
-extern struct sh7372_pm_domain sh7372_a4s;
-extern struct sh7372_pm_domain sh7372_a3sp;
-extern struct sh7372_pm_domain sh7372_a3sg;
-
-extern void sh7372_init_pm_domain(struct sh7372_pm_domain *sh7372_pd);
-extern void sh7372_add_device_to_domain(struct sh7372_pm_domain *sh7372_pd,
-					struct platform_device *pdev);
-extern void sh7372_pm_add_subdomain(struct sh7372_pm_domain *sh7372_pd,
-				    struct sh7372_pm_domain *sh7372_sd);
-#else
-#define sh7372_init_pm_domain(pd) do { } while(0)
-#define sh7372_add_device_to_domain(pd, pdev) do { } while(0)
-#define sh7372_pm_add_subdomain(pd, sd) do { } while(0)
+extern struct rmobile_pm_domain sh7372_pd_a4lc;
+extern struct rmobile_pm_domain sh7372_pd_a4mp;
+extern struct rmobile_pm_domain sh7372_pd_d4;
+extern struct rmobile_pm_domain sh7372_pd_a4r;
+extern struct rmobile_pm_domain sh7372_pd_a3rv;
+extern struct rmobile_pm_domain sh7372_pd_a3ri;
+extern struct rmobile_pm_domain sh7372_pd_a4s;
+extern struct rmobile_pm_domain sh7372_pd_a3sp;
+extern struct rmobile_pm_domain sh7372_pd_a3sg;
 #endif /* CONFIG_PM */
 
 extern void sh7372_intcs_suspend(void);
diff --git a/arch/arm/mach-shmobile/include/mach/sh73a0.h b/arch/arm/mach-shmobile/include/mach/sh73a0.h
index 398e2c10913b..fe950f25d793 100644
--- a/arch/arm/mach-shmobile/include/mach/sh73a0.h
+++ b/arch/arm/mach-shmobile/include/mach/sh73a0.h
@@ -516,6 +516,13 @@ enum {
 	SHDMA_SLAVE_SDHI2_RX,
 	SHDMA_SLAVE_MMCIF_TX,
 	SHDMA_SLAVE_MMCIF_RX,
+	SHDMA_SLAVE_FSI2A_TX,
+	SHDMA_SLAVE_FSI2A_RX,
+	SHDMA_SLAVE_FSI2B_TX,
+	SHDMA_SLAVE_FSI2B_RX,
+	SHDMA_SLAVE_FSI2C_TX,
+	SHDMA_SLAVE_FSI2C_RX,
+	SHDMA_SLAVE_FSI2D_RX,
 };
 
 /*
diff --git a/arch/arm/mach-shmobile/intc-r8a7740.c b/arch/arm/mach-shmobile/intc-r8a7740.c
index 09c42afcb22d..9a69a31918ba 100644
--- a/arch/arm/mach-shmobile/intc-r8a7740.c
+++ b/arch/arm/mach-shmobile/intc-r8a7740.c
@@ -71,10 +71,12 @@ enum {
 	DMAC3_1_DEI0, DMAC3_1_DEI1, DMAC3_1_DEI2, DMAC3_1_DEI3,
 	DMAC3_2_DEI4, DMAC3_2_DEI5, DMAC3_2_DADERR,
 	SHWYSTAT_RT, SHWYSTAT_HS, SHWYSTAT_COM,
+	HDMI,
 	USBH_INT, USBH_OHCI, USBH_EHCI, USBH_PME, USBH_BIND,
 	RSPI_OVRF, RSPI_SPTEF, RSPI_SPRF,
 	SPU2_0, SPU2_1,
 	FSI, FMSI,
+	HDMI_SSS, HDMI_KEY,
 	IPMMU,
 	AP_ARM_CTIIRQ, AP_ARM_PMURQ,
 	MFIS2,
@@ -182,6 +184,7 @@ static struct intc_vect intca_vectors[] __initdata = {
 	INTC_VECT(USBH_EHCI,		0x1580),
 	INTC_VECT(USBH_PME,		0x15A0),
 	INTC_VECT(USBH_BIND,		0x15C0),
+	INTC_VECT(HDMI,			0x1700),
 	INTC_VECT(RSPI_OVRF,		0x1780),
 	INTC_VECT(RSPI_SPTEF,		0x17A0),
 	INTC_VECT(RSPI_SPRF,		0x17C0),
@@ -189,6 +192,8 @@ static struct intc_vect intca_vectors[] __initdata = {
 	INTC_VECT(SPU2_1,		0x1820),
 	INTC_VECT(FSI,			0x1840),
 	INTC_VECT(FMSI,			0x1860),
+	INTC_VECT(HDMI_SSS,		0x18A0),
+	INTC_VECT(HDMI_KEY,		0x18C0),
 	INTC_VECT(IPMMU,		0x1920),
 	INTC_VECT(AP_ARM_CTIIRQ,	0x1980),
 	INTC_VECT(AP_ARM_PMURQ,		0x19A0),
@@ -304,11 +309,11 @@ static struct intc_mask_reg intca_mask_registers[] __initdata = {
 	    USBH_EHCI, USBH_PME, USBH_BIND, 0 } },
 	  /* IMR3A3 / IMCR3A3 */
 	{ /* IMR4A3 / IMCR4A3 */ 0xe6950090, 0xe69500d0, 8,
-	  { 0, 0, 0, 0,
+	  { HDMI, 0, 0, 0,
 	    RSPI_OVRF, RSPI_SPTEF, RSPI_SPRF, 0 } },
 	{ /* IMR5A3 / IMCR5A3 */ 0xe6950094, 0xe69500d4, 8,
 	  { SPU2_0, SPU2_1, FSI, FMSI,
-	    0, 0, 0, 0 } },
+	    0, HDMI_SSS, HDMI_KEY, 0 } },
 	{ /* IMR6A3 / IMCR6A3 */ 0xe6950098, 0xe69500d8, 8,
 	  { 0, IPMMU, 0, 0,
 	    AP_ARM_CTIIRQ, AP_ARM_PMURQ, 0, 0 } },
@@ -353,10 +358,10 @@ static struct intc_prio_reg intca_prio_registers[] __initdata = {
 	{ 0xe6950014, 0, 16, 4, /* IPRFA3 */ { USBH2, 0, 0, 0 } },
 				/* IPRGA3 */
 				/* IPRHA3 */
-				/* IPRIA3 */
+	{ 0xe6950020, 0, 16, 4, /* IPRIA3 */ { HDMI, 0, 0, 0 } },
 	{ 0xe6950024, 0, 16, 4, /* IPRJA3 */ { RSPI, 0, 0, 0 } },
 	{ 0xe6950028, 0, 16, 4, /* IPRKA3 */ { SPU2, 0, FSI, FMSI } },
-				/* IPRLA3 */
+	{ 0xe695002c, 0, 16, 4, /* IPRLA3 */ { 0, HDMI_SSS, HDMI_KEY, 0 } },
 	{ 0xe6950030, 0, 16, 4, /* IPRMA3 */ { IPMMU, 0, 0, 0 } },
 	{ 0xe6950034, 0, 16, 4, /* IPRNA3 */ { AP_ARM2, 0, 0, 0 } },
 	{ 0xe6950038, 0, 16, 4, /* IPROA3 */ { MFIS2, CPORTR2S,
diff --git a/arch/arm/mach-shmobile/pfc-r8a7740.c b/arch/arm/mach-shmobile/pfc-r8a7740.c
index 670fe1869dbc..ce9e7fa5cc8a 100644
--- a/arch/arm/mach-shmobile/pfc-r8a7740.c
+++ b/arch/arm/mach-shmobile/pfc-r8a7740.c
@@ -169,7 +169,7 @@ enum {
 	DBGMD10_MARK,	DBGMD11_MARK,	DBGMD20_MARK,
 	DBGMD21_MARK,
 
-	/* FSI */
+	/* FSI-A */
 	FSIAISLD_PORT0_MARK,	/* FSIAISLD Port 0/5 */
 	FSIAISLD_PORT5_MARK,
 	FSIASPDIF_PORT9_MARK,	/* FSIASPDIF Port 9/18 */
@@ -178,6 +178,9 @@ enum {
 	FSIAOBT_MARK,	FSIAOSLD_MARK,	FSIAOMC_MARK,
 	FSIACK_MARK,	FSIAILR_MARK,	FSIAIBT_MARK,
 
+	/* FSI-B */
+	FSIBCK_MARK,
+
 	/* FMSI */
 	FMSISLD_PORT1_MARK, /* FMSISLD Port 1/6 */
 	FMSISLD_PORT6_MARK,
@@ -560,6 +563,9 @@ enum {
 	/* SDENC */
 	SDENC_CPG_MARK,		SDENC_DV_CLKI_MARK,
 
+	/* HDMI */
+	HDMI_HPD_MARK, HDMI_CEC_MARK,
+
 	/* DEBUG */
 	EDEBGREQ_PULLUP_MARK,	/* for JTAG */
 	EDEBGREQ_PULLDOWN_MARK,
@@ -771,6 +777,7 @@ static pinmux_enum_t pinmux_data[] = {
 
 	/* Port11 */
 	PINMUX_DATA(FSIACK_MARK,		PORT11_FN1),
+	PINMUX_DATA(FSIBCK_MARK,		PORT11_FN2),
 	PINMUX_DATA(IRQ2_PORT11_MARK,		PORT11_FN0,	MSEL1CR_2_0),
 
 	/* Port12 */
@@ -1254,7 +1261,7 @@ static pinmux_enum_t pinmux_data[] = {
 	PINMUX_DATA(A21_MARK,			PORT120_FN1),
 	PINMUX_DATA(MSIOF0_RSYNC_MARK,		PORT120_FN2),
 	PINMUX_DATA(MSIOF1_TSYNC_PORT120_MARK,	PORT120_FN3,	MSEL4CR_10_0),
-	PINMUX_DATA(IRQ7_PORT120_MARK,		PORT120_FN0,	MSEL1CR_7_0),
+	PINMUX_DATA(IRQ7_PORT120_MARK,		PORT120_FN0,	MSEL1CR_7_1),
 
 	/* Port121 */
 	PINMUX_DATA(A20_MARK,			PORT121_FN1),
@@ -1616,13 +1623,15 @@ static pinmux_enum_t pinmux_data[] = {
 
 	/* Port209 */
 	PINMUX_DATA(VBUS_MARK,			PORT209_FN1),
-	PINMUX_DATA(IRQ7_PORT209_MARK,		PORT209_FN0,	MSEL1CR_7_1),
+	PINMUX_DATA(IRQ7_PORT209_MARK,		PORT209_FN0,	MSEL1CR_7_0),
 
 	/* Port210 */
 	PINMUX_DATA(IRQ9_PORT210_MARK,		PORT210_FN0,	MSEL1CR_9_1),
+	PINMUX_DATA(HDMI_HPD_MARK,		PORT210_FN1),
 
 	/* Port211 */
 	PINMUX_DATA(IRQ16_PORT211_MARK,		PORT211_FN0,	MSEL1CR_16_1),
+	PINMUX_DATA(HDMI_CEC_MARK,		PORT211_FN1),
 
 	/* LCDC select */
 	PINMUX_DATA(LCDC0_SELECT_MARK,				MSEL3CR_6_0),
@@ -1691,7 +1700,7 @@ static struct pinmux_gpio pinmux_gpios[] = {
 	GPIO_FN(DBGMD10),	GPIO_FN(DBGMD11),	GPIO_FN(DBGMD20),
 	GPIO_FN(DBGMD21),
 
-	/* FSI */
+	/* FSI-A */
 	GPIO_FN(FSIAISLD_PORT0),	/* FSIAISLD Port 0/5 */
 	GPIO_FN(FSIAISLD_PORT5),
 	GPIO_FN(FSIASPDIF_PORT9),	/* FSIASPDIF Port 9/18 */
@@ -1700,6 +1709,9 @@ static struct pinmux_gpio pinmux_gpios[] = {
 	GPIO_FN(FSIAOBT),	GPIO_FN(FSIAOSLD),	GPIO_FN(FSIAOMC),
 	GPIO_FN(FSIACK),	GPIO_FN(FSIAILR),	GPIO_FN(FSIAIBT),
 
+	/* FSI-B */
+	GPIO_FN(FSIBCK),
+
 	/* FMSI */
 	GPIO_FN(FMSISLD_PORT1), /* FMSISLD Port 1/6 */
 	GPIO_FN(FMSISLD_PORT6),
@@ -2097,6 +2109,10 @@ static struct pinmux_gpio pinmux_gpios[] = {
 	GPIO_FN(SDENC_CPG),
 	GPIO_FN(SDENC_DV_CLKI),
 
+	/* HDMI */
+	GPIO_FN(HDMI_HPD),
+	GPIO_FN(HDMI_CEC),
+
 	/* SYSC */
 	GPIO_FN(RESETP_PULLUP),
 	GPIO_FN(RESETP_PLAIN),
diff --git a/arch/arm/mach-shmobile/pm-r8a7740.c b/arch/arm/mach-shmobile/pm-r8a7740.c
new file mode 100644
index 000000000000..893504d012a6
--- /dev/null
+++ b/arch/arm/mach-shmobile/pm-r8a7740.c
@@ -0,0 +1,54 @@
+/*
+ * r8a7740 power management support
+ *
+ * Copyright (C) 2012  Renesas Solutions Corp.
+ * Copyright (C) 2012  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/console.h>
+#include <mach/pm-rmobile.h>
+
+#ifdef CONFIG_PM
+static int r8a7740_pd_a4s_suspend(void)
+{
+	/*
+	 * The A4S domain contains the CPU core and therefore it should
+	 * only be turned off if the CPU is in use.
+	 */
+	return -EBUSY;
+}
+
+struct rmobile_pm_domain r8a7740_pd_a4s = {
+	.genpd.name	= "A4S",
+	.bit_shift	= 10,
+	.gov		= &pm_domain_always_on_gov,
+	.no_debug	= true,
+	.suspend	= r8a7740_pd_a4s_suspend,
+};
+
+static int r8a7740_pd_a3sp_suspend(void)
+{
+	/*
+	 * Serial consoles make use of SCIF hardware located in A3SP,
+	 * keep such power domain on if "no_console_suspend" is set.
+	 */
+	return console_suspend_enabled ? 0 : -EBUSY;
+}
+
+struct rmobile_pm_domain r8a7740_pd_a3sp = {
+	.genpd.name	= "A3SP",
+	.bit_shift	= 11,
+	.gov		= &pm_domain_always_on_gov,
+	.no_debug	= true,
+	.suspend	= r8a7740_pd_a3sp_suspend,
+};
+
+struct rmobile_pm_domain r8a7740_pd_a4lc = {
+	.genpd.name	= "A4LC",
+	.bit_shift	= 1,
+};
+
+#endif /* CONFIG_PM */
diff --git a/arch/arm/mach-shmobile/pm-rmobile.c b/arch/arm/mach-shmobile/pm-rmobile.c
new file mode 100644
index 000000000000..a8562540f1d6
--- /dev/null
+++ b/arch/arm/mach-shmobile/pm-rmobile.c
@@ -0,0 +1,167 @@
+/*
+ * rmobile power management support
+ *
+ * Copyright (C) 2012  Renesas Solutions Corp.
+ * Copyright (C) 2012  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+ *
+ * based on pm-sh7372.c
+ *  Copyright (C) 2011 Magnus Damm
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/console.h>
+#include <linux/delay.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pm_clock.h>
+#include <asm/io.h>
+#include <mach/pm-rmobile.h>
+
+/* SYSC */
+#define SPDCR		0xe6180008
+#define SWUCR		0xe6180014
+#define PSTR		0xe6180080
+
+#define PSTR_RETRIES	100
+#define PSTR_DELAY_US	10
+
+#ifdef CONFIG_PM
+static int rmobile_pd_power_down(struct generic_pm_domain *genpd)
+{
+	struct rmobile_pm_domain *rmobile_pd = to_rmobile_pd(genpd);
+	unsigned int mask = 1 << rmobile_pd->bit_shift;
+
+	if (rmobile_pd->suspend) {
+		int ret = rmobile_pd->suspend();
+
+		if (ret)
+			return ret;
+	}
+
+	if (__raw_readl(PSTR) & mask) {
+		unsigned int retry_count;
+		__raw_writel(mask, SPDCR);
+
+		for (retry_count = PSTR_RETRIES; retry_count; retry_count--) {
+			if (!(__raw_readl(SPDCR) & mask))
+				break;
+			cpu_relax();
+		}
+	}
+
+	if (!rmobile_pd->no_debug)
+		pr_debug("%s: Power off, 0x%08x -> PSTR = 0x%08x\n",
+			 genpd->name, mask, __raw_readl(PSTR));
+
+	return 0;
+}
+
+static int __rmobile_pd_power_up(struct rmobile_pm_domain *rmobile_pd,
+				 bool do_resume)
+{
+	unsigned int mask = 1 << rmobile_pd->bit_shift;
+	unsigned int retry_count;
+	int ret = 0;
+
+	if (__raw_readl(PSTR) & mask)
+		goto out;
+
+	__raw_writel(mask, SWUCR);
+
+	for (retry_count = 2 * PSTR_RETRIES; retry_count; retry_count--) {
+		if (!(__raw_readl(SWUCR) & mask))
+			break;
+		if (retry_count > PSTR_RETRIES)
+			udelay(PSTR_DELAY_US);
+		else
+			cpu_relax();
+	}
+	if (!retry_count)
+		ret = -EIO;
+
+	if (!rmobile_pd->no_debug)
+		pr_debug("%s: Power on, 0x%08x -> PSTR = 0x%08x\n",
+			 rmobile_pd->genpd.name, mask, __raw_readl(PSTR));
+
+out:
+	if (ret == 0 && rmobile_pd->resume && do_resume)
+		rmobile_pd->resume();
+
+	return ret;
+}
+
+static int rmobile_pd_power_up(struct generic_pm_domain *genpd)
+{
+	return __rmobile_pd_power_up(to_rmobile_pd(genpd), true);
+}
+
+static bool rmobile_pd_active_wakeup(struct device *dev)
+{
+	bool (*active_wakeup)(struct device *dev);
+
+	active_wakeup = dev_gpd_data(dev)->ops.active_wakeup;
+	return active_wakeup ? active_wakeup(dev) : true;
+}
+
+static int rmobile_pd_stop_dev(struct device *dev)
+{
+	int (*stop)(struct device *dev);
+
+	stop = dev_gpd_data(dev)->ops.stop;
+	if (stop) {
+		int ret = stop(dev);
+		if (ret)
+			return ret;
+	}
+	return pm_clk_suspend(dev);
+}
+
+static int rmobile_pd_start_dev(struct device *dev)
+{
+	int (*start)(struct device *dev);
+	int ret;
+
+	ret = pm_clk_resume(dev);
+	if (ret)
+		return ret;
+
+	start = dev_gpd_data(dev)->ops.start;
+	if (start)
+		ret = start(dev);
+
+	return ret;
+}
+
+void rmobile_init_pm_domain(struct rmobile_pm_domain *rmobile_pd)
+{
+	struct generic_pm_domain *genpd = &rmobile_pd->genpd;
+	struct dev_power_governor *gov = rmobile_pd->gov;
+
+	pm_genpd_init(genpd, gov ? : &simple_qos_governor, false);
+	genpd->dev_ops.stop		= rmobile_pd_stop_dev;
+	genpd->dev_ops.start		= rmobile_pd_start_dev;
+	genpd->dev_ops.active_wakeup	= rmobile_pd_active_wakeup;
+	genpd->dev_irq_safe		= true;
+	genpd->power_off		= rmobile_pd_power_down;
+	genpd->power_on			= rmobile_pd_power_up;
+	__rmobile_pd_power_up(rmobile_pd, false);
+}
+
+void rmobile_add_device_to_domain(struct rmobile_pm_domain *rmobile_pd,
+				 struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+
+	pm_genpd_add_device(&rmobile_pd->genpd, dev);
+	if (pm_clk_no_clocks(dev))
+		pm_clk_add(dev, NULL);
+}
+
+void rmobile_pm_add_subdomain(struct rmobile_pm_domain *rmobile_pd,
+			     struct rmobile_pm_domain *rmobile_sd)
+{
+	pm_genpd_add_subdomain(&rmobile_pd->genpd, &rmobile_sd->genpd);
+}
+#endif /* CONFIG_PM */
diff --git a/arch/arm/mach-shmobile/pm-sh7372.c b/arch/arm/mach-shmobile/pm-sh7372.c
index a3bdb12acde9..792037069226 100644
--- a/arch/arm/mach-shmobile/pm-sh7372.c
+++ b/arch/arm/mach-shmobile/pm-sh7372.c
@@ -26,6 +26,7 @@
 #include <asm/suspend.h>
 #include <mach/common.h>
 #include <mach/sh7372.h>
+#include <mach/pm-rmobile.h>
 
 /* DBG */
 #define DBGREG1 0xe6100020
@@ -41,13 +42,10 @@
 #define PLLC01STPCR 0xe61500c8
 
 /* SYSC */
-#define SPDCR 0xe6180008
-#define SWUCR 0xe6180014
 #define SBAR 0xe6180020
 #define WUPRMSK 0xe6180028
 #define WUPSMSK 0xe618002c
 #define WUPSMSK2 0xe6180048
-#define PSTR 0xe6180080
 #define WUPSFAC 0xe6180098
 #define IRQCR 0xe618022c
 #define IRQCR2 0xe6180238
@@ -71,188 +69,48 @@
 /* AP-System Core */
 #define APARMBAREA 0xe6f10020
 
-#define PSTR_RETRIES 100
-#define PSTR_DELAY_US 10
-
 #ifdef CONFIG_PM
 
-static int pd_power_down(struct generic_pm_domain *genpd)
-{
-	struct sh7372_pm_domain *sh7372_pd = to_sh7372_pd(genpd);
-	unsigned int mask = 1 << sh7372_pd->bit_shift;
-
-	if (sh7372_pd->suspend) {
-		int ret = sh7372_pd->suspend();
-
-		if (ret)
-			return ret;
-	}
-
-	if (__raw_readl(PSTR) & mask) {
-		unsigned int retry_count;
-
-		__raw_writel(mask, SPDCR);
-
-		for (retry_count = PSTR_RETRIES; retry_count; retry_count--) {
-			if (!(__raw_readl(SPDCR) & mask))
-				break;
-			cpu_relax();
-		}
-	}
-
-	if (!sh7372_pd->no_debug)
-		pr_debug("%s: Power off, 0x%08x -> PSTR = 0x%08x\n",
-			 genpd->name, mask, __raw_readl(PSTR));
-
-	return 0;
-}
-
-static int __pd_power_up(struct sh7372_pm_domain *sh7372_pd, bool do_resume)
-{
-	unsigned int mask = 1 << sh7372_pd->bit_shift;
-	unsigned int retry_count;
-	int ret = 0;
-
-	if (__raw_readl(PSTR) & mask)
-		goto out;
-
-	__raw_writel(mask, SWUCR);
-
-	for (retry_count = 2 * PSTR_RETRIES; retry_count; retry_count--) {
-		if (!(__raw_readl(SWUCR) & mask))
-			break;
-		if (retry_count > PSTR_RETRIES)
-			udelay(PSTR_DELAY_US);
-		else
-			cpu_relax();
-	}
-	if (!retry_count)
-		ret = -EIO;
-
-	if (!sh7372_pd->no_debug)
-		pr_debug("%s: Power on, 0x%08x -> PSTR = 0x%08x\n",
-			 sh7372_pd->genpd.name, mask, __raw_readl(PSTR));
-
- out:
-	if (ret == 0 && sh7372_pd->resume && do_resume)
-		sh7372_pd->resume();
-
-	return ret;
-}
-
-static int pd_power_up(struct generic_pm_domain *genpd)
-{
-	 return __pd_power_up(to_sh7372_pd(genpd), true);
-}
-
-static int sh7372_a4r_suspend(void)
-{
-	sh7372_intcs_suspend();
-	__raw_writel(0x300fffff, WUPRMSK); /* avoid wakeup */
-	return 0;
-}
-
-static bool pd_active_wakeup(struct device *dev)
-{
-	bool (*active_wakeup)(struct device *dev);
-
-	active_wakeup = dev_gpd_data(dev)->ops.active_wakeup;
-	return active_wakeup ? active_wakeup(dev) : true;
-}
-
-static int sh7372_stop_dev(struct device *dev)
-{
-	int (*stop)(struct device *dev);
-
-	stop = dev_gpd_data(dev)->ops.stop;
-	if (stop) {
-		int ret = stop(dev);
-		if (ret)
-			return ret;
-	}
-	return pm_clk_suspend(dev);
-}
-
-static int sh7372_start_dev(struct device *dev)
-{
-	int (*start)(struct device *dev);
-	int ret;
-
-	ret = pm_clk_resume(dev);
-	if (ret)
-		return ret;
-
-	start = dev_gpd_data(dev)->ops.start;
-	if (start)
-		ret = start(dev);
-
-	return ret;
-}
-
-void sh7372_init_pm_domain(struct sh7372_pm_domain *sh7372_pd)
-{
-	struct generic_pm_domain *genpd = &sh7372_pd->genpd;
-	struct dev_power_governor *gov = sh7372_pd->gov;
-
-	pm_genpd_init(genpd, gov ? : &simple_qos_governor, false);
-	genpd->dev_ops.stop = sh7372_stop_dev;
-	genpd->dev_ops.start = sh7372_start_dev;
-	genpd->dev_ops.active_wakeup = pd_active_wakeup;
-	genpd->dev_irq_safe = true;
-	genpd->power_off = pd_power_down;
-	genpd->power_on = pd_power_up;
-	__pd_power_up(sh7372_pd, false);
-}
-
-void sh7372_add_device_to_domain(struct sh7372_pm_domain *sh7372_pd,
-				 struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-
-	pm_genpd_add_device(&sh7372_pd->genpd, dev);
-	if (pm_clk_no_clocks(dev))
-		pm_clk_add(dev, NULL);
-}
-
-void sh7372_pm_add_subdomain(struct sh7372_pm_domain *sh7372_pd,
-			     struct sh7372_pm_domain *sh7372_sd)
-{
-	pm_genpd_add_subdomain(&sh7372_pd->genpd, &sh7372_sd->genpd);
-}
-
-struct sh7372_pm_domain sh7372_a4lc = {
+struct rmobile_pm_domain sh7372_pd_a4lc = {
 	.genpd.name = "A4LC",
 	.bit_shift = 1,
 };
 
-struct sh7372_pm_domain sh7372_a4mp = {
+struct rmobile_pm_domain sh7372_pd_a4mp = {
 	.genpd.name = "A4MP",
 	.bit_shift = 2,
 };
 
-struct sh7372_pm_domain sh7372_d4 = {
+struct rmobile_pm_domain sh7372_pd_d4 = {
 	.genpd.name = "D4",
 	.bit_shift = 3,
 };
 
-struct sh7372_pm_domain sh7372_a4r = {
+static int sh7372_a4r_pd_suspend(void)
+{
+	sh7372_intcs_suspend();
+	__raw_writel(0x300fffff, WUPRMSK); /* avoid wakeup */
+	return 0;
+}
+
+struct rmobile_pm_domain sh7372_pd_a4r = {
 	.genpd.name = "A4R",
 	.bit_shift = 5,
-	.suspend = sh7372_a4r_suspend,
+	.suspend = sh7372_a4r_pd_suspend,
 	.resume = sh7372_intcs_resume,
 };
 
-struct sh7372_pm_domain sh7372_a3rv = {
+struct rmobile_pm_domain sh7372_pd_a3rv = {
 	.genpd.name = "A3RV",
 	.bit_shift = 6,
 };
 
-struct sh7372_pm_domain sh7372_a3ri = {
+struct rmobile_pm_domain sh7372_pd_a3ri = {
 	.genpd.name = "A3RI",
 	.bit_shift = 8,
 };
 
-static int sh7372_a4s_suspend(void)
+static int sh7372_pd_a4s_suspend(void)
 {
 	/*
 	 * The A4S domain contains the CPU core and therefore it should
@@ -261,15 +119,15 @@ static int sh7372_a4s_suspend(void)
 	return -EBUSY;
 }
 
-struct sh7372_pm_domain sh7372_a4s = {
+struct rmobile_pm_domain sh7372_pd_a4s = {
 	.genpd.name = "A4S",
 	.bit_shift = 10,
 	.gov = &pm_domain_always_on_gov,
 	.no_debug = true,
-	.suspend = sh7372_a4s_suspend,
+	.suspend = sh7372_pd_a4s_suspend,
 };
 
-static int sh7372_a3sp_suspend(void)
+static int sh7372_a3sp_pd_suspend(void)
 {
 	/*
 	 * Serial consoles make use of SCIF hardware located in A3SP,
@@ -278,32 +136,22 @@ static int sh7372_a3sp_suspend(void)
 	return console_suspend_enabled ? 0 : -EBUSY;
 }
 
-struct sh7372_pm_domain sh7372_a3sp = {
+struct rmobile_pm_domain sh7372_pd_a3sp = {
 	.genpd.name = "A3SP",
 	.bit_shift = 11,
 	.gov = &pm_domain_always_on_gov,
 	.no_debug = true,
-	.suspend = sh7372_a3sp_suspend,
+	.suspend = sh7372_a3sp_pd_suspend,
 };
 
-struct sh7372_pm_domain sh7372_a3sg = {
+struct rmobile_pm_domain sh7372_pd_a3sg = {
 	.genpd.name = "A3SG",
 	.bit_shift = 13,
 };
 
-#else /* !CONFIG_PM */
-
-static inline void sh7372_a3sp_init(void) {}
-
-#endif /* !CONFIG_PM */
+#endif /* CONFIG_PM */
 
 #if defined(CONFIG_SUSPEND) || defined(CONFIG_CPU_IDLE)
-static int sh7372_do_idle_core_standby(unsigned long unused)
-{
-	cpu_do_idle(); /* WFI when SYSTBCR == 0x10 -> Core Standby */
-	return 0;
-}
-
 static void sh7372_set_reset_vector(unsigned long address)
 {
 	/* set reset vector, translate 4k */
@@ -311,21 +159,6 @@ static void sh7372_set_reset_vector(unsigned long address)
 	__raw_writel(0, APARMBAREA);
 }
 
-static void sh7372_enter_core_standby(void)
-{
-	sh7372_set_reset_vector(__pa(sh7372_resume_core_standby_sysc));
-
-	/* enter sleep mode with SYSTBCR to 0x10 */
-	__raw_writel(0x10, SYSTBCR);
-	cpu_suspend(0, sh7372_do_idle_core_standby);
-	__raw_writel(0, SYSTBCR);
-
-	 /* disable reset vector translation */
-	__raw_writel(0, SBAR);
-}
-#endif
-
-#ifdef CONFIG_SUSPEND
 static void sh7372_enter_sysc(int pllc0_on, unsigned long sleep_mode)
 {
 	if (pllc0_on)
@@ -465,22 +298,42 @@ static void sh7372_setup_sysc(unsigned long msk, unsigned long msk2)
 
 static void sh7372_enter_a3sm_common(int pllc0_on)
 {
+	/* use INTCA together with SYSC for wakeup */
+	sh7372_setup_sysc(1 << 0, 0);
 	sh7372_set_reset_vector(__pa(sh7372_resume_core_standby_sysc));
 	sh7372_enter_sysc(pllc0_on, 1 << 12);
 }
+#endif /* CONFIG_SUSPEND || CONFIG_CPU_IDLE */
 
-static void sh7372_enter_a4s_common(int pllc0_on)
+#ifdef CONFIG_CPU_IDLE
+static int sh7372_do_idle_core_standby(unsigned long unused)
 {
-	sh7372_intca_suspend();
-	memcpy((void *)SMFRAM, sh7372_resume_core_standby_sysc, 0x100);
-	sh7372_set_reset_vector(SMFRAM);
-	sh7372_enter_sysc(pllc0_on, 1 << 10);
-	sh7372_intca_resume();
+	cpu_do_idle(); /* WFI when SYSTBCR == 0x10 -> Core Standby */
+	return 0;
 }
 
-#endif
+static void sh7372_enter_core_standby(void)
+{
+	sh7372_set_reset_vector(__pa(sh7372_resume_core_standby_sysc));
 
-#ifdef CONFIG_CPU_IDLE
+	/* enter sleep mode with SYSTBCR to 0x10 */
+	__raw_writel(0x10, SYSTBCR);
+	cpu_suspend(0, sh7372_do_idle_core_standby);
+	__raw_writel(0, SYSTBCR);
+
+	 /* disable reset vector translation */
+	__raw_writel(0, SBAR);
+}
+
+static void sh7372_enter_a3sm_pll_on(void)
+{
+	sh7372_enter_a3sm_common(1);
+}
+
+static void sh7372_enter_a3sm_pll_off(void)
+{
+	sh7372_enter_a3sm_common(0);
+}
 
 static void sh7372_cpuidle_setup(struct cpuidle_driver *drv)
 {
@@ -492,7 +345,24 @@ static void sh7372_cpuidle_setup(struct cpuidle_driver *drv)
 	state->target_residency = 20 + 10;
 	state->flags = CPUIDLE_FLAG_TIME_VALID;
 	shmobile_cpuidle_modes[drv->state_count] = sh7372_enter_core_standby;
+	drv->state_count++;
+
+	state = &drv->states[drv->state_count];
+	snprintf(state->name, CPUIDLE_NAME_LEN, "C3");
+	strncpy(state->desc, "A3SM PLL ON", CPUIDLE_DESC_LEN);
+	state->exit_latency = 20;
+	state->target_residency = 30 + 20;
+	state->flags = CPUIDLE_FLAG_TIME_VALID;
+	shmobile_cpuidle_modes[drv->state_count] = sh7372_enter_a3sm_pll_on;
+	drv->state_count++;
 
+	state = &drv->states[drv->state_count];
+	snprintf(state->name, CPUIDLE_NAME_LEN, "C4");
+	strncpy(state->desc, "A3SM PLL OFF", CPUIDLE_DESC_LEN);
+	state->exit_latency = 120;
+	state->target_residency = 30 + 120;
+	state->flags = CPUIDLE_FLAG_TIME_VALID;
+	shmobile_cpuidle_modes[drv->state_count] = sh7372_enter_a3sm_pll_off;
 	drv->state_count++;
 }
 
@@ -505,6 +375,14 @@ static void sh7372_cpuidle_init(void) {}
 #endif
 
 #ifdef CONFIG_SUSPEND
+static void sh7372_enter_a4s_common(int pllc0_on)
+{
+	sh7372_intca_suspend();
+	memcpy((void *)SMFRAM, sh7372_resume_core_standby_sysc, 0x100);
+	sh7372_set_reset_vector(SMFRAM);
+	sh7372_enter_sysc(pllc0_on, 1 << 10);
+	sh7372_intca_resume();
+}
 
 static int sh7372_enter_suspend(suspend_state_t suspend_state)
 {
@@ -512,24 +390,21 @@ static int sh7372_enter_suspend(suspend_state_t suspend_state)
 
 	/* check active clocks to determine potential wakeup sources */
 	if (sh7372_sysc_valid(&msk, &msk2)) {
-		/* convert INTC mask and sense to SYSC mask and sense */
-		sh7372_setup_sysc(msk, msk2);
-
 		if (!console_suspend_enabled &&
-		    sh7372_a4s.genpd.status == GPD_STATE_POWER_OFF) {
+		    sh7372_pd_a4s.genpd.status == GPD_STATE_POWER_OFF) {
+			/* convert INTC mask/sense to SYSC mask/sense */
+			sh7372_setup_sysc(msk, msk2);
+
 			/* enter A4S sleep with PLLC0 off */
 			pr_debug("entering A4S\n");
 			sh7372_enter_a4s_common(0);
-		} else {
-			/* enter A3SM sleep with PLLC0 off */
-			pr_debug("entering A3SM\n");
-			sh7372_enter_a3sm_common(0);
+			return 0;
 		}
-	} else {
-		/* default to Core Standby that supports all wakeup sources */
-		pr_debug("entering Core Standby\n");
-		sh7372_enter_core_standby();
 	}
+
+	/* default to enter A3SM sleep with PLLC0 off */
+	pr_debug("entering A3SM\n");
+	sh7372_enter_a3sm_common(0);
 	return 0;
 }
 
@@ -550,7 +425,7 @@ static int sh7372_pm_notifier_fn(struct notifier_block *notifier,
 		 * executed during system suspend and resume, respectively, so
 		 * that those functions don't crash while accessing the INTCS.
 		 */
-		pm_genpd_poweron(&sh7372_a4r.genpd);
+		pm_genpd_poweron(&sh7372_pd_a4r.genpd);
 		break;
 	case PM_POST_SUSPEND:
 		pm_genpd_poweroff_unused();
diff --git a/arch/arm/mach-shmobile/setup-r8a7740.c b/arch/arm/mach-shmobile/setup-r8a7740.c
index ec4eb49c1693..78948a9dba0e 100644
--- a/arch/arm/mach-shmobile/setup-r8a7740.c
+++ b/arch/arm/mach-shmobile/setup-r8a7740.c
@@ -23,9 +23,14 @@
 #include <linux/init.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/of_platform.h>
 #include <linux/serial_sci.h>
+#include <linux/sh_dma.h>
 #include <linux/sh_timer.h>
+#include <linux/dma-mapping.h>
+#include <mach/dma-register.h>
 #include <mach/r8a7740.h>
+#include <mach/pm-rmobile.h>
 #include <mach/common.h>
 #include <mach/irqs.h>
 #include <asm/mach-types.h>
@@ -276,6 +281,272 @@ static struct platform_device *r8a7740_early_devices[] __initdata = {
 	&cmt10_device,
 };
 
+/* DMA */
+static const struct sh_dmae_slave_config r8a7740_dmae_slaves[] = {
+	{
+		.slave_id	= SHDMA_SLAVE_SDHI0_TX,
+		.addr		= 0xe6850030,
+		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
+		.mid_rid	= 0xc1,
+	}, {
+		.slave_id	= SHDMA_SLAVE_SDHI0_RX,
+		.addr		= 0xe6850030,
+		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
+		.mid_rid	= 0xc2,
+	}, {
+		.slave_id	= SHDMA_SLAVE_SDHI1_TX,
+		.addr		= 0xe6860030,
+		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
+		.mid_rid	= 0xc9,
+	}, {
+		.slave_id	= SHDMA_SLAVE_SDHI1_RX,
+		.addr		= 0xe6860030,
+		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
+		.mid_rid	= 0xca,
+	}, {
+		.slave_id	= SHDMA_SLAVE_SDHI2_TX,
+		.addr		= 0xe6870030,
+		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
+		.mid_rid	= 0xcd,
+	}, {
+		.slave_id	= SHDMA_SLAVE_SDHI2_RX,
+		.addr		= 0xe6870030,
+		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
+		.mid_rid	= 0xce,
+	}, {
+		.slave_id	= SHDMA_SLAVE_FSIA_TX,
+		.addr		= 0xfe1f0024,
+		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xb1,
+	}, {
+		.slave_id	= SHDMA_SLAVE_FSIA_RX,
+		.addr		= 0xfe1f0020,
+		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xb2,
+	}, {
+		.slave_id	= SHDMA_SLAVE_FSIB_TX,
+		.addr		= 0xfe1f0064,
+		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xb5,
+	},
+};
+
+#define DMA_CHANNEL(a, b, c)			\
+{						\
+	.offset		= a,			\
+	.dmars		= b,			\
+	.dmars_bit	= c,			\
+	.chclr_offset	= (0x220 - 0x20) + a	\
+}
+
+static const struct sh_dmae_channel r8a7740_dmae_channels[] = {
+	DMA_CHANNEL(0x00, 0, 0),
+	DMA_CHANNEL(0x10, 0, 8),
+	DMA_CHANNEL(0x20, 4, 0),
+	DMA_CHANNEL(0x30, 4, 8),
+	DMA_CHANNEL(0x50, 8, 0),
+	DMA_CHANNEL(0x60, 8, 8),
+};
+
+static struct sh_dmae_pdata dma_platform_data = {
+	.slave		= r8a7740_dmae_slaves,
+	.slave_num	= ARRAY_SIZE(r8a7740_dmae_slaves),
+	.channel	= r8a7740_dmae_channels,
+	.channel_num	= ARRAY_SIZE(r8a7740_dmae_channels),
+	.ts_low_shift	= TS_LOW_SHIFT,
+	.ts_low_mask	= TS_LOW_BIT << TS_LOW_SHIFT,
+	.ts_high_shift	= TS_HI_SHIFT,
+	.ts_high_mask	= TS_HI_BIT << TS_HI_SHIFT,
+	.ts_shift	= dma_ts_shift,
+	.ts_shift_num	= ARRAY_SIZE(dma_ts_shift),
+	.dmaor_init	= DMAOR_DME,
+	.chclr_present	= 1,
+};
+
+/* Resource order important! */
+static struct resource r8a7740_dmae0_resources[] = {
+	{
+		/* Channel registers and DMAOR */
+		.start	= 0xfe008020,
+		.end	= 0xfe00828f,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* DMARSx */
+		.start	= 0xfe009000,
+		.end	= 0xfe00900b,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.name	= "error_irq",
+		.start	= evt2irq(0x20c0),
+		.end	= evt2irq(0x20c0),
+		.flags	= IORESOURCE_IRQ,
+	},
+	{
+		/* IRQ for channels 0-5 */
+		.start	= evt2irq(0x2000),
+		.end	= evt2irq(0x20a0),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+/* Resource order important! */
+static struct resource r8a7740_dmae1_resources[] = {
+	{
+		/* Channel registers and DMAOR */
+		.start	= 0xfe018020,
+		.end	= 0xfe01828f,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* DMARSx */
+		.start	= 0xfe019000,
+		.end	= 0xfe01900b,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.name	= "error_irq",
+		.start	= evt2irq(0x21c0),
+		.end	= evt2irq(0x21c0),
+		.flags	= IORESOURCE_IRQ,
+	},
+	{
+		/* IRQ for channels 0-5 */
+		.start	= evt2irq(0x2100),
+		.end	= evt2irq(0x21a0),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+/* Resource order important! */
+static struct resource r8a7740_dmae2_resources[] = {
+	{
+		/* Channel registers and DMAOR */
+		.start	= 0xfe028020,
+		.end	= 0xfe02828f,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* DMARSx */
+		.start	= 0xfe029000,
+		.end	= 0xfe02900b,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.name	= "error_irq",
+		.start	= evt2irq(0x22c0),
+		.end	= evt2irq(0x22c0),
+		.flags	= IORESOURCE_IRQ,
+	},
+	{
+		/* IRQ for channels 0-5 */
+		.start	= evt2irq(0x2200),
+		.end	= evt2irq(0x22a0),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device dma0_device = {
+	.name		= "sh-dma-engine",
+	.id		= 0,
+	.resource	= r8a7740_dmae0_resources,
+	.num_resources	= ARRAY_SIZE(r8a7740_dmae0_resources),
+	.dev		= {
+		.platform_data	= &dma_platform_data,
+	},
+};
+
+static struct platform_device dma1_device = {
+	.name		= "sh-dma-engine",
+	.id		= 1,
+	.resource	= r8a7740_dmae1_resources,
+	.num_resources	= ARRAY_SIZE(r8a7740_dmae1_resources),
+	.dev		= {
+		.platform_data	= &dma_platform_data,
+	},
+};
+
+static struct platform_device dma2_device = {
+	.name		= "sh-dma-engine",
+	.id		= 2,
+	.resource	= r8a7740_dmae2_resources,
+	.num_resources	= ARRAY_SIZE(r8a7740_dmae2_resources),
+	.dev		= {
+		.platform_data	= &dma_platform_data,
+	},
+};
+
+/* USB-DMAC */
+static const struct sh_dmae_channel r8a7740_usb_dma_channels[] = {
+	{
+		.offset = 0,
+	}, {
+		.offset = 0x20,
+	},
+};
+
+static const struct sh_dmae_slave_config r8a7740_usb_dma_slaves[] = {
+	{
+		.slave_id	= SHDMA_SLAVE_USBHS_TX,
+		.chcr		= USBTS_INDEX2VAL(USBTS_XMIT_SZ_8BYTE),
+	}, {
+		.slave_id	= SHDMA_SLAVE_USBHS_RX,
+		.chcr		= USBTS_INDEX2VAL(USBTS_XMIT_SZ_8BYTE),
+	},
+};
+
+static struct sh_dmae_pdata usb_dma_platform_data = {
+	.slave		= r8a7740_usb_dma_slaves,
+	.slave_num	= ARRAY_SIZE(r8a7740_usb_dma_slaves),
+	.channel	= r8a7740_usb_dma_channels,
+	.channel_num	= ARRAY_SIZE(r8a7740_usb_dma_channels),
+	.ts_low_shift	= USBTS_LOW_SHIFT,
+	.ts_low_mask	= USBTS_LOW_BIT << USBTS_LOW_SHIFT,
+	.ts_high_shift	= USBTS_HI_SHIFT,
+	.ts_high_mask	= USBTS_HI_BIT << USBTS_HI_SHIFT,
+	.ts_shift	= dma_usbts_shift,
+	.ts_shift_num	= ARRAY_SIZE(dma_usbts_shift),
+	.dmaor_init	= DMAOR_DME,
+	.chcr_offset	= 0x14,
+	.chcr_ie_bit	= 1 << 5,
+	.dmaor_is_32bit	= 1,
+	.needs_tend_set	= 1,
+	.no_dmars	= 1,
+	.slave_only	= 1,
+};
+
+static struct resource r8a7740_usb_dma_resources[] = {
+	{
+		/* Channel registers and DMAOR */
+		.start	= 0xe68a0020,
+		.end	= 0xe68a0064 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* VCR/SWR/DMICR */
+		.start	= 0xe68a0000,
+		.end	= 0xe68a0014 - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* IRQ for channels */
+		.start	= evt2irq(0x0a00),
+		.end	= evt2irq(0x0a00),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device usb_dma_device = {
+	.name		= "sh-dma-engine",
+	.id		= 3,
+	.resource	= r8a7740_usb_dma_resources,
+	.num_resources	= ARRAY_SIZE(r8a7740_usb_dma_resources),
+	.dev		= {
+		.platform_data	= &usb_dma_platform_data,
+	},
+};
+
 /* I2C */
 static struct resource i2c0_resources[] = {
 	[0] = {
@@ -322,8 +593,30 @@ static struct platform_device i2c1_device = {
 static struct platform_device *r8a7740_late_devices[] __initdata = {
 	&i2c0_device,
 	&i2c1_device,
+	&dma0_device,
+	&dma1_device,
+	&dma2_device,
+	&usb_dma_device,
 };
 
+/*
+ * r8a7740 chip has lasting errata on MERAM buffer.
+ * this is work-around for it.
+ * see
+ *	"Media RAM (MERAM)" on r8a7740 documentation
+ */
+#define MEBUFCNTR	0xFE950098
+void r8a7740_meram_workaround(void)
+{
+	void __iomem *reg;
+
+	reg = ioremap_nocache(MEBUFCNTR, 4);
+	if (reg) {
+		iowrite32(0x01600164, reg);
+		iounmap(reg);
+	}
+}
+
 #define ICCR	0x0004
 #define ICSTART	0x0070
 
@@ -380,10 +673,31 @@ void __init r8a7740_add_standard_devices(void)
 	r8a7740_i2c_workaround(&i2c0_device);
 	r8a7740_i2c_workaround(&i2c1_device);
 
+	/* PM domain */
+	rmobile_init_pm_domain(&r8a7740_pd_a4s);
+	rmobile_init_pm_domain(&r8a7740_pd_a3sp);
+	rmobile_init_pm_domain(&r8a7740_pd_a4lc);
+
+	rmobile_pm_add_subdomain(&r8a7740_pd_a4s, &r8a7740_pd_a3sp);
+
+	/* add devices */
 	platform_add_devices(r8a7740_early_devices,
 			    ARRAY_SIZE(r8a7740_early_devices));
 	platform_add_devices(r8a7740_late_devices,
 			     ARRAY_SIZE(r8a7740_late_devices));
+
+	/* add devices to PM domain  */
+
+	rmobile_add_device_to_domain(&r8a7740_pd_a3sp,	&scif0_device);
+	rmobile_add_device_to_domain(&r8a7740_pd_a3sp,	&scif1_device);
+	rmobile_add_device_to_domain(&r8a7740_pd_a3sp,	&scif2_device);
+	rmobile_add_device_to_domain(&r8a7740_pd_a3sp,	&scif3_device);
+	rmobile_add_device_to_domain(&r8a7740_pd_a3sp,	&scif4_device);
+	rmobile_add_device_to_domain(&r8a7740_pd_a3sp,	&scif5_device);
+	rmobile_add_device_to_domain(&r8a7740_pd_a3sp,	&scif6_device);
+	rmobile_add_device_to_domain(&r8a7740_pd_a3sp,	&scif7_device);
+	rmobile_add_device_to_domain(&r8a7740_pd_a3sp,	&scifb_device);
+	rmobile_add_device_to_domain(&r8a7740_pd_a3sp,	&i2c1_device);
 }
 
 static void __init r8a7740_earlytimer_init(void)
@@ -403,3 +717,49 @@ void __init r8a7740_add_early_devices(void)
 	/* override timer setup with soc-specific code */
 	shmobile_timer.init = r8a7740_earlytimer_init;
 }
+
+#ifdef CONFIG_USE_OF
+
+void __init r8a7740_add_early_devices_dt(void)
+{
+	shmobile_setup_delay(800, 1, 3); /* Cortex-A9 @ 800MHz */
+
+	early_platform_add_devices(r8a7740_early_devices,
+				   ARRAY_SIZE(r8a7740_early_devices));
+
+	/* setup early console here as well */
+	shmobile_setup_console();
+}
+
+static const struct of_dev_auxdata r8a7740_auxdata_lookup[] __initconst = {
+	{ }
+};
+
+void __init r8a7740_add_standard_devices_dt(void)
+{
+	/* clocks are setup late during boot in the case of DT */
+	r8a7740_clock_init(0);
+
+	platform_add_devices(r8a7740_early_devices,
+			    ARRAY_SIZE(r8a7740_early_devices));
+
+	of_platform_populate(NULL, of_default_bus_match_table,
+			     r8a7740_auxdata_lookup, NULL);
+}
+
+static const char *r8a7740_boards_compat_dt[] __initdata = {
+	"renesas,r8a7740",
+	NULL,
+};
+
+DT_MACHINE_START(SH7372_DT, "Generic R8A7740 (Flattened Device Tree)")
+	.map_io		= r8a7740_map_io,
+	.init_early	= r8a7740_add_early_devices_dt,
+	.init_irq	= r8a7740_init_irq,
+	.handle_irq	= shmobile_handle_irq_intc,
+	.init_machine	= r8a7740_add_standard_devices_dt,
+	.timer		= &shmobile_timer,
+	.dt_compat	= r8a7740_boards_compat_dt,
+MACHINE_END
+
+#endif /* CONFIG_USE_OF */
diff --git a/arch/arm/mach-shmobile/setup-sh7372.c b/arch/arm/mach-shmobile/setup-sh7372.c
index fafce9ce8218..838a87be1d5c 100644
--- a/arch/arm/mach-shmobile/setup-sh7372.c
+++ b/arch/arm/mach-shmobile/setup-sh7372.c
@@ -33,6 +33,7 @@
 #include <linux/sh_timer.h>
 #include <linux/pm_domain.h>
 #include <linux/dma-mapping.h>
+#include <mach/dma-register.h>
 #include <mach/hardware.h>
 #include <mach/irqs.h>
 #include <mach/sh7372.h>
@@ -335,151 +336,126 @@ static struct platform_device iic1_device = {
 };
 
 /* DMA */
-/* Transmit sizes and respective CHCR register values */
-enum {
-	XMIT_SZ_8BIT		= 0,
-	XMIT_SZ_16BIT		= 1,
-	XMIT_SZ_32BIT		= 2,
-	XMIT_SZ_64BIT		= 7,
-	XMIT_SZ_128BIT		= 3,
-	XMIT_SZ_256BIT		= 4,
-	XMIT_SZ_512BIT		= 5,
-};
-
-/* log2(size / 8) - used to calculate number of transfers */
-#define TS_SHIFT {			\
-	[XMIT_SZ_8BIT]		= 0,	\
-	[XMIT_SZ_16BIT]		= 1,	\
-	[XMIT_SZ_32BIT]		= 2,	\
-	[XMIT_SZ_64BIT]		= 3,	\
-	[XMIT_SZ_128BIT]	= 4,	\
-	[XMIT_SZ_256BIT]	= 5,	\
-	[XMIT_SZ_512BIT]	= 6,	\
-}
-
-#define TS_INDEX2VAL(i) ((((i) & 3) << 3) | \
-			 (((i) & 0xc) << (20 - 2)))
-
 static const struct sh_dmae_slave_config sh7372_dmae_slaves[] = {
 	{
 		.slave_id	= SHDMA_SLAVE_SCIF0_TX,
 		.addr		= 0xe6c40020,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x21,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF0_RX,
 		.addr		= 0xe6c40024,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x22,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF1_TX,
 		.addr		= 0xe6c50020,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x25,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF1_RX,
 		.addr		= 0xe6c50024,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x26,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF2_TX,
 		.addr		= 0xe6c60020,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x29,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF2_RX,
 		.addr		= 0xe6c60024,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x2a,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF3_TX,
 		.addr		= 0xe6c70020,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x2d,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF3_RX,
 		.addr		= 0xe6c70024,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x2e,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF4_TX,
 		.addr		= 0xe6c80020,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x39,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF4_RX,
 		.addr		= 0xe6c80024,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x3a,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF5_TX,
 		.addr		= 0xe6cb0020,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x35,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF5_RX,
 		.addr		= 0xe6cb0024,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x36,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF6_TX,
 		.addr		= 0xe6c30040,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x3d,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SCIF6_RX,
 		.addr		= 0xe6c30060,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_8BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_8BIT),
 		.mid_rid	= 0x3e,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SDHI0_TX,
 		.addr		= 0xe6850030,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_16BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
 		.mid_rid	= 0xc1,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SDHI0_RX,
 		.addr		= 0xe6850030,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_16BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
 		.mid_rid	= 0xc2,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SDHI1_TX,
 		.addr		= 0xe6860030,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_16BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
 		.mid_rid	= 0xc9,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SDHI1_RX,
 		.addr		= 0xe6860030,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_16BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
 		.mid_rid	= 0xca,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SDHI2_TX,
 		.addr		= 0xe6870030,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_16BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_16BIT),
 		.mid_rid	= 0xcd,
 	}, {
 		.slave_id	= SHDMA_SLAVE_SDHI2_RX,
 		.addr		= 0xe6870030,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_16BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_16BIT),
 		.mid_rid	= 0xce,
 	}, {
 		.slave_id	= SHDMA_SLAVE_FSIA_TX,
 		.addr		= 0xfe1f0024,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
 		.mid_rid	= 0xb1,
 	}, {
 		.slave_id	= SHDMA_SLAVE_FSIA_RX,
 		.addr		= 0xfe1f0020,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
 		.mid_rid	= 0xb2,
 	}, {
 		.slave_id	= SHDMA_SLAVE_MMCIF_TX,
 		.addr		= 0xe6bd0034,
-		.chcr		= DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
 		.mid_rid	= 0xd1,
 	}, {
 		.slave_id	= SHDMA_SLAVE_MMCIF_RX,
 		.addr		= 0xe6bd0034,
-		.chcr		= DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL(XMIT_SZ_32BIT),
+		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
 		.mid_rid	= 0xd2,
 	},
 };
@@ -520,19 +496,17 @@ static const struct sh_dmae_channel sh7372_dmae_channels[] = {
 	}
 };
 
-static const unsigned int ts_shift[] = TS_SHIFT;
-
 static struct sh_dmae_pdata dma_platform_data = {
 	.slave		= sh7372_dmae_slaves,
 	.slave_num	= ARRAY_SIZE(sh7372_dmae_slaves),
 	.channel	= sh7372_dmae_channels,
 	.channel_num	= ARRAY_SIZE(sh7372_dmae_channels),
-	.ts_low_shift	= 3,
-	.ts_low_mask	= 0x18,
-	.ts_high_shift	= (20 - 2),	/* 2 bits for shifted low TS */
-	.ts_high_mask	= 0x00300000,
-	.ts_shift	= ts_shift,
-	.ts_shift_num	= ARRAY_SIZE(ts_shift),
+	.ts_low_shift	= TS_LOW_SHIFT,
+	.ts_low_mask	= TS_LOW_BIT << TS_LOW_SHIFT,
+	.ts_high_shift	= TS_HI_SHIFT,
+	.ts_high_mask	= TS_HI_BIT << TS_HI_SHIFT,
+	.ts_shift	= dma_ts_shift,
+	.ts_shift_num	= ARRAY_SIZE(dma_ts_shift),
 	.dmaor_init	= DMAOR_DME,
 	.chclr_present	= 1,
 };
@@ -654,17 +628,6 @@ static struct platform_device dma2_device = {
 /*
  * USB-DMAC
  */
-
-unsigned int usbts_shift[] = {3, 4, 5};
-
-enum {
-	XMIT_SZ_8BYTE		= 0,
-	XMIT_SZ_16BYTE		= 1,
-	XMIT_SZ_32BYTE		= 2,
-};
-
-#define USBTS_INDEX2VAL(i) (((i) & 3) << 6)
-
 static const struct sh_dmae_channel sh7372_usb_dmae_channels[] = {
 	{
 		.offset = 0,
@@ -677,10 +640,10 @@ static const struct sh_dmae_channel sh7372_usb_dmae_channels[] = {
 static const struct sh_dmae_slave_config sh7372_usb_dmae0_slaves[] = {
 	{
 		.slave_id	= SHDMA_SLAVE_USB0_TX,
-		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+		.chcr		= USBTS_INDEX2VAL(USBTS_XMIT_SZ_8BYTE),
 	}, {
 		.slave_id	= SHDMA_SLAVE_USB0_RX,
-		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+		.chcr		= USBTS_INDEX2VAL(USBTS_XMIT_SZ_8BYTE),
 	},
 };
 
@@ -689,12 +652,12 @@ static struct sh_dmae_pdata usb_dma0_platform_data = {
 	.slave_num	= ARRAY_SIZE(sh7372_usb_dmae0_slaves),
 	.channel	= sh7372_usb_dmae_channels,
 	.channel_num	= ARRAY_SIZE(sh7372_usb_dmae_channels),
-	.ts_low_shift	= 6,
-	.ts_low_mask	= 0xc0,
-	.ts_high_shift	= 0,
-	.ts_high_mask	= 0,
-	.ts_shift	= usbts_shift,
-	.ts_shift_num	= ARRAY_SIZE(usbts_shift),
+	.ts_low_shift	= USBTS_LOW_SHIFT,
+	.ts_low_mask	= USBTS_LOW_BIT << USBTS_LOW_SHIFT,
+	.ts_high_shift	= USBTS_HI_SHIFT,
+	.ts_high_mask	= USBTS_HI_BIT << USBTS_HI_SHIFT,
+	.ts_shift	= dma_usbts_shift,
+	.ts_shift_num	= ARRAY_SIZE(dma_usbts_shift),
 	.dmaor_init	= DMAOR_DME,
 	.chcr_offset	= 0x14,
 	.chcr_ie_bit	= 1 << 5,
@@ -739,10 +702,10 @@ static struct platform_device usb_dma0_device = {
 static const struct sh_dmae_slave_config sh7372_usb_dmae1_slaves[] = {
 	{
 		.slave_id	= SHDMA_SLAVE_USB1_TX,
-		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+		.chcr		= USBTS_INDEX2VAL(USBTS_XMIT_SZ_8BYTE),
 	}, {
 		.slave_id	= SHDMA_SLAVE_USB1_RX,
-		.chcr		= USBTS_INDEX2VAL(XMIT_SZ_8BYTE),
+		.chcr		= USBTS_INDEX2VAL(USBTS_XMIT_SZ_8BYTE),
 	},
 };
 
@@ -751,12 +714,12 @@ static struct sh_dmae_pdata usb_dma1_platform_data = {
 	.slave_num	= ARRAY_SIZE(sh7372_usb_dmae1_slaves),
 	.channel	= sh7372_usb_dmae_channels,
 	.channel_num	= ARRAY_SIZE(sh7372_usb_dmae_channels),
-	.ts_low_shift	= 6,
-	.ts_low_mask	= 0xc0,
-	.ts_high_shift	= 0,
-	.ts_high_mask	= 0,
-	.ts_shift	= usbts_shift,
-	.ts_shift_num	= ARRAY_SIZE(usbts_shift),
+	.ts_low_shift	= USBTS_LOW_SHIFT,
+	.ts_low_mask	= USBTS_LOW_BIT << USBTS_LOW_SHIFT,
+	.ts_high_shift	= USBTS_HI_SHIFT,
+	.ts_high_mask	= USBTS_HI_BIT << USBTS_HI_SHIFT,
+	.ts_shift	= dma_usbts_shift,
+	.ts_shift_num	= ARRAY_SIZE(dma_usbts_shift),
 	.dmaor_init	= DMAOR_DME,
 	.chcr_offset	= 0x14,
 	.chcr_ie_bit	= 1 << 5,
@@ -1038,21 +1001,21 @@ static struct platform_device *sh7372_late_devices[] __initdata = {
 
 void __init sh7372_add_standard_devices(void)
 {
-	sh7372_init_pm_domain(&sh7372_a4lc);
-	sh7372_init_pm_domain(&sh7372_a4mp);
-	sh7372_init_pm_domain(&sh7372_d4);
-	sh7372_init_pm_domain(&sh7372_a4r);
-	sh7372_init_pm_domain(&sh7372_a3rv);
-	sh7372_init_pm_domain(&sh7372_a3ri);
-	sh7372_init_pm_domain(&sh7372_a4s);
-	sh7372_init_pm_domain(&sh7372_a3sp);
-	sh7372_init_pm_domain(&sh7372_a3sg);
-
-	sh7372_pm_add_subdomain(&sh7372_a4lc, &sh7372_a3rv);
-	sh7372_pm_add_subdomain(&sh7372_a4r, &sh7372_a4lc);
-
-	sh7372_pm_add_subdomain(&sh7372_a4s, &sh7372_a3sg);
-	sh7372_pm_add_subdomain(&sh7372_a4s, &sh7372_a3sp);
+	rmobile_init_pm_domain(&sh7372_pd_a4lc);
+	rmobile_init_pm_domain(&sh7372_pd_a4mp);
+	rmobile_init_pm_domain(&sh7372_pd_d4);
+	rmobile_init_pm_domain(&sh7372_pd_a4r);
+	rmobile_init_pm_domain(&sh7372_pd_a3rv);
+	rmobile_init_pm_domain(&sh7372_pd_a3ri);
+	rmobile_init_pm_domain(&sh7372_pd_a4s);
+	rmobile_init_pm_domain(&sh7372_pd_a3sp);
+	rmobile_init_pm_domain(&sh7372_pd_a3sg);
+
+	rmobile_pm_add_subdomain(&sh7372_pd_a4lc, &sh7372_pd_a3rv);
+	rmobile_pm_add_subdomain(&sh7372_pd_a4r, &sh7372_pd_a4lc);
+
+	rmobile_pm_add_subdomain(&sh7372_pd_a4s, &sh7372_pd_a3sg);
+	rmobile_pm_add_subdomain(&sh7372_pd_a4s, &sh7372_pd_a3sp);
 
 	platform_add_devices(sh7372_early_devices,
 			    ARRAY_SIZE(sh7372_early_devices));
@@ -1060,30 +1023,30 @@ void __init sh7372_add_standard_devices(void)
 	platform_add_devices(sh7372_late_devices,
 			    ARRAY_SIZE(sh7372_late_devices));
 
-	sh7372_add_device_to_domain(&sh7372_a3rv, &vpu_device);
-	sh7372_add_device_to_domain(&sh7372_a4mp, &spu0_device);
-	sh7372_add_device_to_domain(&sh7372_a4mp, &spu1_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &scif0_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &scif1_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &scif2_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &scif3_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &scif4_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &scif5_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &scif6_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &iic1_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &dma0_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &dma1_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &dma2_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &usb_dma0_device);
-	sh7372_add_device_to_domain(&sh7372_a3sp, &usb_dma1_device);
-	sh7372_add_device_to_domain(&sh7372_a4r, &iic0_device);
-	sh7372_add_device_to_domain(&sh7372_a4r, &veu0_device);
-	sh7372_add_device_to_domain(&sh7372_a4r, &veu1_device);
-	sh7372_add_device_to_domain(&sh7372_a4r, &veu2_device);
-	sh7372_add_device_to_domain(&sh7372_a4r, &veu3_device);
-	sh7372_add_device_to_domain(&sh7372_a4r, &jpu_device);
-	sh7372_add_device_to_domain(&sh7372_a4r, &tmu00_device);
-	sh7372_add_device_to_domain(&sh7372_a4r, &tmu01_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3rv, &vpu_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4mp, &spu0_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4mp, &spu1_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif0_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif1_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif2_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif3_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif4_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif5_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &scif6_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &iic1_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &dma0_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &dma1_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &dma2_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &usb_dma0_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a3sp, &usb_dma1_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4r, &iic0_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4r, &veu0_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4r, &veu1_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4r, &veu2_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4r, &veu3_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4r, &jpu_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4r, &tmu00_device);
+	rmobile_add_device_to_domain(&sh7372_pd_a4r, &tmu01_device);
 }
 
 static void __init sh7372_earlytimer_init(void)
diff --git a/arch/arm/mach-shmobile/setup-sh7377.c b/arch/arm/mach-shmobile/setup-sh7377.c
index d576a6abbade..855b1506caf8 100644
--- a/arch/arm/mach-shmobile/setup-sh7377.c
+++ b/arch/arm/mach-shmobile/setup-sh7377.c
@@ -22,6 +22,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/platform_device.h>
+#include <linux/of_platform.h>
 #include <linux/uio_driver.h>
 #include <linux/delay.h>
 #include <linux/input.h>
@@ -500,3 +501,49 @@ void __init sh7377_add_early_devices(void)
 	/* override timer setup with soc-specific code */
 	shmobile_timer.init = sh7377_earlytimer_init;
 }
+
+#ifdef CONFIG_USE_OF
+
+void __init sh7377_add_early_devices_dt(void)
+{
+	shmobile_setup_delay(600, 1, 3); /* Cortex-A8 @ 600MHz */
+
+	early_platform_add_devices(sh7377_early_devices,
+				   ARRAY_SIZE(sh7377_early_devices));
+
+	/* setup early console here as well */
+	shmobile_setup_console();
+}
+
+static const struct of_dev_auxdata sh7377_auxdata_lookup[] __initconst = {
+	{ }
+};
+
+void __init sh7377_add_standard_devices_dt(void)
+{
+	/* clocks are setup late during boot in the case of DT */
+	sh7377_clock_init();
+
+	platform_add_devices(sh7377_early_devices,
+			    ARRAY_SIZE(sh7377_early_devices));
+
+	of_platform_populate(NULL, of_default_bus_match_table,
+			     sh7377_auxdata_lookup, NULL);
+}
+
+static const char *sh7377_boards_compat_dt[] __initdata = {
+	"renesas,sh7377",
+	NULL,
+};
+
+DT_MACHINE_START(SH7377_DT, "Generic SH7377 (Flattened Device Tree)")
+	.map_io		= sh7377_map_io,
+	.init_early	= sh7377_add_early_devices_dt,
+	.init_irq	= sh7377_init_irq,
+	.handle_irq	= shmobile_handle_irq_intc,
+	.init_machine	= sh7377_add_standard_devices_dt,
+	.timer		= &shmobile_timer,
+	.dt_compat	= sh7377_boards_compat_dt,
+MACHINE_END
+
+#endif /* CONFIG_USE_OF */
diff --git a/arch/arm/mach-shmobile/setup-sh73a0.c b/arch/arm/mach-shmobile/setup-sh73a0.c
index 04a0dfe75493..d230af656fc9 100644
--- a/arch/arm/mach-shmobile/setup-sh73a0.c
+++ b/arch/arm/mach-shmobile/setup-sh73a0.c
@@ -30,6 +30,7 @@
 #include <linux/sh_dma.h>
 #include <linux/sh_intc.h>
 #include <linux/sh_timer.h>
+#include <mach/dma-register.h>
 #include <mach/hardware.h>
 #include <mach/irqs.h>
 #include <mach/sh73a0.h>
@@ -415,32 +416,6 @@ static struct platform_device i2c4_device = {
 	.num_resources	= ARRAY_SIZE(i2c4_resources),
 };
 
-/* Transmit sizes and respective CHCR register values */
-enum {
-	XMIT_SZ_8BIT		= 0,
-	XMIT_SZ_16BIT		= 1,
-	XMIT_SZ_32BIT		= 2,
-	XMIT_SZ_64BIT		= 7,
-	XMIT_SZ_128BIT		= 3,
-	XMIT_SZ_256BIT		= 4,
-	XMIT_SZ_512BIT		= 5,
-};
-
-/* log2(size / 8) - used to calculate number of transfers */
-#define TS_SHIFT {			\
-	[XMIT_SZ_8BIT]		= 0,	\
-	[XMIT_SZ_16BIT]		= 1,	\
-	[XMIT_SZ_32BIT]		= 2,	\
-	[XMIT_SZ_64BIT]		= 3,	\
-	[XMIT_SZ_128BIT]	= 4,	\
-	[XMIT_SZ_256BIT]	= 5,	\
-	[XMIT_SZ_512BIT]	= 6,	\
-}
-
-#define TS_INDEX2VAL(i) ((((i) & 3) << 3) | (((i) & 0xc) << (20 - 2)))
-#define CHCR_TX(xmit_sz) (DM_FIX | SM_INC | 0x800 | TS_INDEX2VAL((xmit_sz)))
-#define CHCR_RX(xmit_sz) (DM_INC | SM_FIX | 0x800 | TS_INDEX2VAL((xmit_sz)))
-
 static const struct sh_dmae_slave_config sh73a0_dmae_slaves[] = {
 	{
 		.slave_id	= SHDMA_SLAVE_SCIF0_TX,
@@ -604,19 +579,17 @@ static const struct sh_dmae_channel sh73a0_dmae_channels[] = {
 	DMAE_CHANNEL(0x8980),
 };
 
-static const unsigned int ts_shift[] = TS_SHIFT;
-
 static struct sh_dmae_pdata sh73a0_dmae_platform_data = {
 	.slave          = sh73a0_dmae_slaves,
 	.slave_num      = ARRAY_SIZE(sh73a0_dmae_slaves),
 	.channel        = sh73a0_dmae_channels,
 	.channel_num    = ARRAY_SIZE(sh73a0_dmae_channels),
-	.ts_low_shift   = 3,
-	.ts_low_mask    = 0x18,
-	.ts_high_shift  = (20 - 2),     /* 2 bits for shifted low TS */
-	.ts_high_mask   = 0x00300000,
-	.ts_shift       = ts_shift,
-	.ts_shift_num   = ARRAY_SIZE(ts_shift),
+	.ts_low_shift   = TS_LOW_SHIFT,
+	.ts_low_mask    = TS_LOW_BIT << TS_LOW_SHIFT,
+	.ts_high_shift  = TS_HI_SHIFT,
+	.ts_high_mask   = TS_HI_BIT << TS_HI_SHIFT,
+	.ts_shift       = dma_ts_shift,
+	.ts_shift_num   = ARRAY_SIZE(dma_ts_shift),
 	.dmaor_init     = DMAOR_DME,
 };
 
@@ -651,6 +624,116 @@ static struct platform_device dma0_device = {
 	},
 };
 
+/* MPDMAC */
+static const struct sh_dmae_slave_config sh73a0_mpdma_slaves[] = {
+	{
+		.slave_id	= SHDMA_SLAVE_FSI2A_RX,
+		.addr		= 0xec230020,
+		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xd6, /* CHECK ME */
+	}, {
+		.slave_id	= SHDMA_SLAVE_FSI2A_TX,
+		.addr		= 0xec230024,
+		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xd5, /* CHECK ME */
+	}, {
+		.slave_id	= SHDMA_SLAVE_FSI2C_RX,
+		.addr		= 0xec230060,
+		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xda, /* CHECK ME */
+	}, {
+		.slave_id	= SHDMA_SLAVE_FSI2C_TX,
+		.addr		= 0xec230064,
+		.chcr		= CHCR_TX(XMIT_SZ_32BIT),
+		.mid_rid	= 0xd9, /* CHECK ME */
+	}, {
+		.slave_id	= SHDMA_SLAVE_FSI2B_RX,
+		.addr		= 0xec240020,
+		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
+		.mid_rid	= 0x8e, /* CHECK ME */
+	}, {
+		.slave_id	= SHDMA_SLAVE_FSI2B_TX,
+		.addr		= 0xec240024,
+		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
+		.mid_rid	= 0x8d, /* CHECK ME */
+	}, {
+		.slave_id	= SHDMA_SLAVE_FSI2D_RX,
+		.addr		=  0xec240060,
+		.chcr		= CHCR_RX(XMIT_SZ_32BIT),
+		.mid_rid	= 0x9a, /* CHECK ME */
+	},
+};
+
+#define MPDMA_CHANNEL(a, b, c)			\
+{						\
+	.offset		= a,			\
+	.dmars		= b,			\
+	.dmars_bit	= c,			\
+	.chclr_offset	= (0x220 - 0x20) + a	\
+}
+
+static const struct sh_dmae_channel sh73a0_mpdma_channels[] = {
+	MPDMA_CHANNEL(0x00, 0, 0),
+	MPDMA_CHANNEL(0x10, 0, 8),
+	MPDMA_CHANNEL(0x20, 4, 0),
+	MPDMA_CHANNEL(0x30, 4, 8),
+	MPDMA_CHANNEL(0x50, 8, 0),
+	MPDMA_CHANNEL(0x70, 8, 8),
+};
+
+static struct sh_dmae_pdata sh73a0_mpdma_platform_data = {
+	.slave		= sh73a0_mpdma_slaves,
+	.slave_num	= ARRAY_SIZE(sh73a0_mpdma_slaves),
+	.channel	= sh73a0_mpdma_channels,
+	.channel_num	= ARRAY_SIZE(sh73a0_mpdma_channels),
+	.ts_low_shift	= TS_LOW_SHIFT,
+	.ts_low_mask	= TS_LOW_BIT << TS_LOW_SHIFT,
+	.ts_high_shift	= TS_HI_SHIFT,
+	.ts_high_mask	= TS_HI_BIT << TS_HI_SHIFT,
+	.ts_shift	= dma_ts_shift,
+	.ts_shift_num	= ARRAY_SIZE(dma_ts_shift),
+	.dmaor_init	= DMAOR_DME,
+	.chclr_present	= 1,
+};
+
+/* Resource order important! */
+static struct resource sh73a0_mpdma_resources[] = {
+	{
+		/* Channel registers and DMAOR */
+		.start	= 0xec618020,
+		.end	= 0xec61828f,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		/* DMARSx */
+		.start	= 0xec619000,
+		.end	= 0xec61900b,
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.name	= "error_irq",
+		.start	= gic_spi(181),
+		.end	= gic_spi(181),
+		.flags	= IORESOURCE_IRQ,
+	},
+	{
+		/* IRQ for channels 0-5 */
+		.start	= gic_spi(175),
+		.end	= gic_spi(180),
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct platform_device mpdma0_device = {
+	.name		= "sh-dma-engine",
+	.id		= 1,
+	.resource	= sh73a0_mpdma_resources,
+	.num_resources	= ARRAY_SIZE(sh73a0_mpdma_resources),
+	.dev		= {
+		.platform_data	= &sh73a0_mpdma_platform_data,
+	},
+};
+
 static struct platform_device *sh73a0_early_devices[] __initdata = {
 	&scif0_device,
 	&scif1_device,
@@ -673,6 +756,7 @@ static struct platform_device *sh73a0_late_devices[] __initdata = {
 	&i2c3_device,
 	&i2c4_device,
 	&dma0_device,
+	&mpdma0_device,
 };
 
 #define SRCR2          0xe61580b0
diff --git a/arch/arm/mach-tegra/board-dt-tegra20.c b/arch/arm/mach-tegra/board-dt-tegra20.c
index d0de9c1192f7..c0999633a9ab 100644
--- a/arch/arm/mach-tegra/board-dt-tegra20.c
+++ b/arch/arm/mach-tegra/board-dt-tegra20.c
@@ -64,7 +64,8 @@ struct of_dev_auxdata tegra20_auxdata_lookup[] __initdata = {
 		       &tegra_ehci2_pdata),
 	OF_DEV_AUXDATA("nvidia,tegra20-ehci", TEGRA_USB3_BASE, "tegra-ehci.2",
 		       &tegra_ehci3_pdata),
-	OF_DEV_AUXDATA("nvidia,tegra20-apbdma", 0x6000a000, "tegra-apbdma", NULL),
+	OF_DEV_AUXDATA("nvidia,tegra20-apbdma", TEGRA_APB_DMA_BASE, "tegra-apbdma", NULL),
+	OF_DEV_AUXDATA("nvidia,tegra20-pwm", TEGRA_PWFM_BASE, "tegra-pwm", NULL),
 	{}
 };
 
diff --git a/arch/arm/mach-tegra/board-dt-tegra30.c b/arch/arm/mach-tegra/board-dt-tegra30.c
index ee48214bfd89..53bf60f11580 100644
--- a/arch/arm/mach-tegra/board-dt-tegra30.c
+++ b/arch/arm/mach-tegra/board-dt-tegra30.c
@@ -33,6 +33,8 @@
 #include <asm/mach/arch.h>
 #include <asm/hardware/gic.h>
 
+#include <mach/iomap.h>
+
 #include "board.h"
 #include "clock.h"
 
@@ -48,6 +50,7 @@ struct of_dev_auxdata tegra30_auxdata_lookup[] __initdata = {
 	OF_DEV_AUXDATA("nvidia,tegra20-i2c", 0x7000D000, "tegra-i2c.4", NULL),
 	OF_DEV_AUXDATA("nvidia,tegra30-ahub", 0x70080000, "tegra30-ahub", NULL),
 	OF_DEV_AUXDATA("nvidia,tegra30-apbdma", 0x6000a000, "tegra-apbdma", NULL),
+	OF_DEV_AUXDATA("nvidia,tegra30-pwm", TEGRA_PWFM_BASE, "tegra-pwm", NULL),
 	{}
 };
 
diff --git a/arch/arm/mach-tegra/board-harmony-power.c b/arch/arm/mach-tegra/board-harmony-power.c
index 44dcb2e869b5..8fd387bf31f0 100644
--- a/arch/arm/mach-tegra/board-harmony-power.c
+++ b/arch/arm/mach-tegra/board-harmony-power.c
@@ -19,6 +19,7 @@
 #include <linux/platform_device.h>
 #include <linux/gpio.h>
 #include <linux/regulator/machine.h>
+#include <linux/regulator/fixed.h>
 #include <linux/mfd/tps6586x.h>
 #include <linux/of.h>
 #include <linux/of_i2c.h>
@@ -34,7 +35,9 @@ static struct regulator_consumer_supply tps658621_ldo0_supply[] = {
 };
 
 static struct regulator_init_data ldo0_data = {
+	.supply_regulator = "vdd_sm2",
 	.constraints = {
+		.name = "vdd_ldo0",
 		.min_uV = 3300 * 1000,
 		.max_uV = 3300 * 1000,
 		.valid_modes_mask = (REGULATOR_MODE_NORMAL |
@@ -48,9 +51,11 @@ static struct regulator_init_data ldo0_data = {
 	.consumer_supplies = tps658621_ldo0_supply,
 };
 
-#define HARMONY_REGULATOR_INIT(_id, _minmv, _maxmv)			\
+#define HARMONY_REGULATOR_INIT(_id, _name, _supply, _minmv, _maxmv)	\
 	static struct regulator_init_data _id##_data = {		\
+		.supply_regulator = _supply,				\
 		.constraints = {					\
+			.name = _name,					\
 			.min_uV = (_minmv)*1000,			\
 			.max_uV = (_maxmv)*1000,			\
 			.valid_modes_mask = (REGULATOR_MODE_NORMAL |	\
@@ -61,18 +66,18 @@ static struct regulator_init_data ldo0_data = {
 		},							\
 	}
 
-HARMONY_REGULATOR_INIT(sm0, 725, 1500);
-HARMONY_REGULATOR_INIT(sm1, 725, 1500);
-HARMONY_REGULATOR_INIT(sm2, 3000, 4550);
-HARMONY_REGULATOR_INIT(ldo1, 725, 1500);
-HARMONY_REGULATOR_INIT(ldo2, 725, 1500);
-HARMONY_REGULATOR_INIT(ldo3, 1250, 3300);
-HARMONY_REGULATOR_INIT(ldo4, 1700, 2475);
-HARMONY_REGULATOR_INIT(ldo5, 1250, 3300);
-HARMONY_REGULATOR_INIT(ldo6, 1250, 3300);
-HARMONY_REGULATOR_INIT(ldo7, 1250, 3300);
-HARMONY_REGULATOR_INIT(ldo8, 1250, 3300);
-HARMONY_REGULATOR_INIT(ldo9, 1250, 3300);
+HARMONY_REGULATOR_INIT(sm0,  "vdd_sm0",  "vdd_sys", 725, 1500);
+HARMONY_REGULATOR_INIT(sm1,  "vdd_sm1",  "vdd_sys", 725, 1500);
+HARMONY_REGULATOR_INIT(sm2,  "vdd_sm2",  "vdd_sys", 3000, 4550);
+HARMONY_REGULATOR_INIT(ldo1, "vdd_ldo1", "vdd_sm2", 725, 1500);
+HARMONY_REGULATOR_INIT(ldo2, "vdd_ldo2", "vdd_sm2", 725, 1500);
+HARMONY_REGULATOR_INIT(ldo3, "vdd_ldo3", "vdd_sm2", 1250, 3300);
+HARMONY_REGULATOR_INIT(ldo4, "vdd_ldo4", "vdd_sm2", 1700, 2475);
+HARMONY_REGULATOR_INIT(ldo5, "vdd_ldo5", NULL,	    1250, 3300);
+HARMONY_REGULATOR_INIT(ldo6, "vdd_ldo6", "vdd_sm2", 1250, 3300);
+HARMONY_REGULATOR_INIT(ldo7, "vdd_ldo7", "vdd_sm2", 1250, 3300);
+HARMONY_REGULATOR_INIT(ldo8, "vdd_ldo8", "vdd_sm2", 1250, 3300);
+HARMONY_REGULATOR_INIT(ldo9, "vdd_ldo9", "vdd_sm2", 1250, 3300);
 
 #define TPS_REG(_id, _data)			\
 	{					\
@@ -115,6 +120,8 @@ static struct i2c_board_info __initdata harmony_regulators[] = {
 int __init harmony_regulator_init(void)
 {
 	if (machine_is_harmony()) {
+		regulator_register_always_on(0, "vdd_sys",
+			NULL, 0, 5000000);
 		i2c_register_board_info(3, harmony_regulators, 1);
 	} else { /* Harmony, booted using device tree */
 		struct device_node *np;
diff --git a/arch/arm/mach-ux500/board-mop500.c b/arch/arm/mach-ux500/board-mop500.c
index a310222951da..8674a890fd1c 100644
--- a/arch/arm/mach-ux500/board-mop500.c
+++ b/arch/arm/mach-ux500/board-mop500.c
@@ -15,6 +15,7 @@
 #include <linux/platform_device.h>
 #include <linux/io.h>
 #include <linux/i2c.h>
+#include <linux/platform_data/i2c-nomadik.h>
 #include <linux/gpio.h>
 #include <linux/amba/bus.h>
 #include <linux/amba/pl022.h>
@@ -40,7 +41,6 @@
 #include <asm/mach/arch.h>
 #include <asm/hardware/gic.h>
 
-#include <plat/i2c.h>
 #include <plat/ste_dma40.h>
 #include <plat/gpio-nomadik.h>
 
@@ -211,24 +211,6 @@ static struct ab8500_platform_data ab8500_platdata = {
 	.codec		= &ab8500_codec_pdata,
 };
 
-static struct resource ab8500_resources[] = {
-	[0] = {
-		.start	= IRQ_DB8500_AB8500,
-		.end	= IRQ_DB8500_AB8500,
-		.flags	= IORESOURCE_IRQ
-	}
-};
-
-struct platform_device ab8500_device = {
-	.name = "ab8500-core",
-	.id = 0,
-	.dev = {
-		.platform_data = &ab8500_platdata,
-	},
-	.num_resources = 1,
-	.resource = ab8500_resources,
-};
-
 /*
  * TPS61052
  */
@@ -443,7 +425,6 @@ static struct hash_platform_data u8500_hash1_platform_data = {
 /* add any platform devices here - TODO */
 static struct platform_device *mop500_platform_devs[] __initdata = {
 	&mop500_gpio_keys_device,
-	&ab8500_device,
 };
 
 #ifdef CONFIG_STE_DMA40
@@ -605,7 +586,6 @@ static struct platform_device *snowball_platform_devs[] __initdata = {
 	&snowball_led_dev,
 	&snowball_key_dev,
 	&snowball_sbnet_dev,
-	&ab8500_device,
 };
 
 static void __init mop500_init_machine(void)
@@ -617,9 +597,8 @@ static void __init mop500_init_machine(void)
 	mop500_gpio_keys[0].gpio = GPIO_PROX_SENSOR;
 
 	mop500_pinmaps_init();
-	parent = u8500_init_devices();
+	parent = u8500_init_devices(&ab8500_platdata);
 
-	/* FIXME: parent of ab8500 should be prcmu */
 	for (i = 0; i < ARRAY_SIZE(mop500_platform_devs); i++)
 		mop500_platform_devs[i]->dev.parent = parent;
 
@@ -652,7 +631,7 @@ static void __init snowball_init_machine(void)
 	int i;
 
 	snowball_pinmaps_init();
-	parent = u8500_init_devices();
+	parent = u8500_init_devices(&ab8500_platdata);
 
 	for (i = 0; i < ARRAY_SIZE(snowball_platform_devs); i++)
 		snowball_platform_devs[i]->dev.parent = parent;
@@ -684,7 +663,7 @@ static void __init hrefv60_init_machine(void)
 	mop500_gpio_keys[0].gpio = HREFV60_PROX_SENSE_GPIO;
 
 	hrefv60_pinmaps_init();
-	parent = u8500_init_devices();
+	parent = u8500_init_devices(&ab8500_platdata);
 
 	for (i = 0; i < ARRAY_SIZE(mop500_platform_devs); i++)
 		mop500_platform_devs[i]->dev.parent = parent;
@@ -785,9 +764,6 @@ static const struct of_device_id u8500_local_bus_nodes[] = {
 	/* only create devices below soc node */
 	{ .compatible = "stericsson,db8500", },
 	{ .compatible = "stericsson,db8500-prcmu", },
-	{ .compatible = "stericsson,db8500-prcmu-regulator", },
-	{ .compatible = "stericsson,ab8500", },
-	{ .compatible = "stericsson,ab8500-regulator", },
 	{ .compatible = "simple-bus"},
 	{ },
 };
diff --git a/arch/arm/mach-ux500/cpu-db8500.c b/arch/arm/mach-ux500/cpu-db8500.c
index c8dd94f606dc..db3c52d56ca4 100644
--- a/arch/arm/mach-ux500/cpu-db8500.c
+++ b/arch/arm/mach-ux500/cpu-db8500.c
@@ -16,6 +16,7 @@
 #include <linux/irq.h>
 #include <linux/platform_device.h>
 #include <linux/io.h>
+#include <linux/mfd/abx500/ab8500.h>
 
 #include <asm/mach/map.h>
 #include <asm/pmu.h>
@@ -115,7 +116,7 @@ static irqreturn_t db8500_pmu_handler(int irq, void *dev, irq_handler_t handler)
 	return ret;
 }
 
-static struct arm_pmu_platdata db8500_pmu_platdata = {
+struct arm_pmu_platdata db8500_pmu_platdata = {
 	.handle_irq		= db8500_pmu_handler,
 };
 
@@ -206,7 +207,7 @@ static struct device * __init db8500_soc_device_init(void)
 /*
  * This function is called from the board init
  */
-struct device * __init u8500_init_devices(void)
+struct device * __init u8500_init_devices(struct ab8500_platform_data *ab8500)
 {
 	struct device *parent;
 	int i;
@@ -223,6 +224,8 @@ struct device * __init u8500_init_devices(void)
 	for (i = 0; i < ARRAY_SIZE(platform_devs); i++)
 		platform_devs[i]->dev.parent = parent;
 
+	db8500_prcmu_device.dev.platform_data = ab8500;
+
 	platform_add_devices(platform_devs, ARRAY_SIZE(platform_devs));
 
 	return parent;
diff --git a/arch/arm/mach-ux500/devices-common.h b/arch/arm/mach-ux500/devices-common.h
index 6e4706560266..ecdd8386cffb 100644
--- a/arch/arm/mach-ux500/devices-common.h
+++ b/arch/arm/mach-ux500/devices-common.h
@@ -12,7 +12,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/sys_soc.h>
 #include <linux/amba/bus.h>
-#include <plat/i2c.h>
+#include <linux/platform_data/i2c-nomadik.h>
 #include <mach/crypto-ux500.h>
 
 struct spi_master_cntlr;
@@ -56,27 +56,15 @@ dbx500_add_uart(struct device *parent, const char *name, resource_size_t base,
 
 struct nmk_i2c_controller;
 
-static inline struct platform_device *
+static inline struct amba_device *
 dbx500_add_i2c(struct device *parent, int id, resource_size_t base, int irq,
 	       struct nmk_i2c_controller *data)
 {
-	struct resource res[] = {
-		DEFINE_RES_MEM(base, SZ_4K),
-		DEFINE_RES_IRQ(irq),
-	};
+	/* Conjure a name similar to what the platform device used to have */
+	char name[16];
 
-	struct platform_device_info pdevinfo = {
-		.parent = parent,
-		.name = "nmk-i2c",
-		.id = id,
-		.res = res,
-		.num_res = ARRAY_SIZE(res),
-		.data = data,
-		.size_data = sizeof(*data),
-		.dma_mask = DMA_BIT_MASK(32),
-	};
-
-	return platform_device_register_full(&pdevinfo);
+	snprintf(name, sizeof(name), "nmk-i2c.%d", id);
+	return amba_apb_device_add(parent, name, base, SZ_4K, irq, 0, data, 0);
 }
 
 static inline struct amba_device *
diff --git a/arch/arm/mach-ux500/include/mach/setup.h b/arch/arm/mach-ux500/include/mach/setup.h
index 8b7ed82a2866..7914e5eaa9c7 100644
--- a/arch/arm/mach-ux500/include/mach/setup.h
+++ b/arch/arm/mach-ux500/include/mach/setup.h
@@ -13,11 +13,12 @@
 
 #include <asm/mach/time.h>
 #include <linux/init.h>
+#include <linux/mfd/abx500/ab8500.h>
 
 void __init ux500_map_io(void);
 extern void __init u8500_map_io(void);
 
-extern struct device * __init u8500_init_devices(void);
+extern struct device * __init u8500_init_devices(struct ab8500_platform_data *ab8500);
 
 extern void __init ux500_init_irq(void);
 extern void __init ux500_init_late(void);
diff --git a/arch/arm/mach-vt8500/Makefile b/arch/arm/mach-vt8500/Makefile
index 54e69973f39b..7ce51767c99c 100644
--- a/arch/arm/mach-vt8500/Makefile
+++ b/arch/arm/mach-vt8500/Makefile
@@ -5,5 +5,3 @@ obj-$(CONFIG_VTWM_VERSION_WM8505) += devices-wm8505.o
 
 obj-$(CONFIG_MACH_BV07) += bv07.o
 obj-$(CONFIG_MACH_WM8505_7IN_NETBOOK) += wm8505_7in.o
-
-obj-$(CONFIG_HAVE_PWM) += pwm.o
diff --git a/arch/arm/mach-vt8500/pwm.c b/arch/arm/mach-vt8500/pwm.c
deleted file mode 100644
index 8ad825e93592..000000000000
--- a/arch/arm/mach-vt8500/pwm.c
+++ /dev/null
@@ -1,265 +0,0 @@
-/*
- * arch/arm/mach-vt8500/pwm.c
- *
- *  Copyright (C) 2010 Alexey Charkov <alchark@gmail.com>
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/err.h>
-#include <linux/io.h>
-#include <linux/pwm.h>
-#include <linux/delay.h>
-
-#include <asm/div64.h>
-
-#define VT8500_NR_PWMS 4
-
-static DEFINE_MUTEX(pwm_lock);
-static LIST_HEAD(pwm_list);
-
-struct pwm_device {
-	struct list_head	node;
-	struct platform_device	*pdev;
-
-	const char	*label;
-
-	void __iomem	*regbase;
-
-	unsigned int	use_count;
-	unsigned int	pwm_id;
-};
-
-#define msecs_to_loops(t) (loops_per_jiffy / 1000 * HZ * t)
-static inline void pwm_busy_wait(void __iomem *reg, u8 bitmask)
-{
-	int loops = msecs_to_loops(10);
-	while ((readb(reg) & bitmask) && --loops)
-		cpu_relax();
-
-	if (unlikely(!loops))
-		pr_warning("Waiting for status bits 0x%x to clear timed out\n",
-			   bitmask);
-}
-
-int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns)
-{
-	unsigned long long c;
-	unsigned long period_cycles, prescale, pv, dc;
-
-	if (pwm == NULL || period_ns == 0 || duty_ns > period_ns)
-		return -EINVAL;
-
-	c = 25000000/2; /* wild guess --- need to implement clocks */
-	c = c * period_ns;
-	do_div(c, 1000000000);
-	period_cycles = c;
-
-	if (period_cycles < 1)
-		period_cycles = 1;
-	prescale = (period_cycles - 1) / 4096;
-	pv = period_cycles / (prescale + 1) - 1;
-	if (pv > 4095)
-		pv = 4095;
-
-	if (prescale > 1023)
-		return -EINVAL;
-
-	c = (unsigned long long)pv * duty_ns;
-	do_div(c, period_ns);
-	dc = c;
-
-	pwm_busy_wait(pwm->regbase + 0x40 + pwm->pwm_id, (1 << 1));
-	writel(prescale, pwm->regbase + 0x4 + (pwm->pwm_id << 4));
-
-	pwm_busy_wait(pwm->regbase + 0x40 + pwm->pwm_id, (1 << 2));
-	writel(pv, pwm->regbase + 0x8 + (pwm->pwm_id << 4));
-
-	pwm_busy_wait(pwm->regbase + 0x40 + pwm->pwm_id, (1 << 3));
-	writel(dc, pwm->regbase + 0xc + (pwm->pwm_id << 4));
-
-	return 0;
-}
-EXPORT_SYMBOL(pwm_config);
-
-int pwm_enable(struct pwm_device *pwm)
-{
-	pwm_busy_wait(pwm->regbase + 0x40 + pwm->pwm_id, (1 << 0));
-	writel(5, pwm->regbase + (pwm->pwm_id << 4));
-	return 0;
-}
-EXPORT_SYMBOL(pwm_enable);
-
-void pwm_disable(struct pwm_device *pwm)
-{
-	pwm_busy_wait(pwm->regbase + 0x40 + pwm->pwm_id, (1 << 0));
-	writel(0, pwm->regbase + (pwm->pwm_id << 4));
-}
-EXPORT_SYMBOL(pwm_disable);
-
-struct pwm_device *pwm_request(int pwm_id, const char *label)
-{
-	struct pwm_device *pwm;
-	int found = 0;
-
-	mutex_lock(&pwm_lock);
-
-	list_for_each_entry(pwm, &pwm_list, node) {
-		if (pwm->pwm_id == pwm_id) {
-			found = 1;
-			break;
-		}
-	}
-
-	if (found) {
-		if (pwm->use_count == 0) {
-			pwm->use_count++;
-			pwm->label = label;
-		} else {
-			pwm = ERR_PTR(-EBUSY);
-		}
-	} else {
-		pwm = ERR_PTR(-ENOENT);
-	}
-
-	mutex_unlock(&pwm_lock);
-	return pwm;
-}
-EXPORT_SYMBOL(pwm_request);
-
-void pwm_free(struct pwm_device *pwm)
-{
-	mutex_lock(&pwm_lock);
-
-	if (pwm->use_count) {
-		pwm->use_count--;
-		pwm->label = NULL;
-	} else {
-		pr_warning("PWM device already freed\n");
-	}
-
-	mutex_unlock(&pwm_lock);
-}
-EXPORT_SYMBOL(pwm_free);
-
-static inline void __add_pwm(struct pwm_device *pwm)
-{
-	mutex_lock(&pwm_lock);
-	list_add_tail(&pwm->node, &pwm_list);
-	mutex_unlock(&pwm_lock);
-}
-
-static int __devinit pwm_probe(struct platform_device *pdev)
-{
-	struct pwm_device *pwms;
-	struct resource *r;
-	int ret = 0;
-	int i;
-
-	pwms = kzalloc(sizeof(struct pwm_device) * VT8500_NR_PWMS, GFP_KERNEL);
-	if (pwms == NULL) {
-		dev_err(&pdev->dev, "failed to allocate memory\n");
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < VT8500_NR_PWMS; i++) {
-		pwms[i].use_count = 0;
-		pwms[i].pwm_id = i;
-		pwms[i].pdev = pdev;
-	}
-
-	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (r == NULL) {
-		dev_err(&pdev->dev, "no memory resource defined\n");
-		ret = -ENODEV;
-		goto err_free;
-	}
-
-	r = request_mem_region(r->start, resource_size(r), pdev->name);
-	if (r == NULL) {
-		dev_err(&pdev->dev, "failed to request memory resource\n");
-		ret = -EBUSY;
-		goto err_free;
-	}
-
-	pwms[0].regbase = ioremap(r->start, resource_size(r));
-	if (pwms[0].regbase == NULL) {
-		dev_err(&pdev->dev, "failed to ioremap() registers\n");
-		ret = -ENODEV;
-		goto err_free_mem;
-	}
-
-	for (i = 1; i < VT8500_NR_PWMS; i++)
-		pwms[i].regbase = pwms[0].regbase;
-
-	for (i = 0; i < VT8500_NR_PWMS; i++)
-		__add_pwm(&pwms[i]);
-
-	platform_set_drvdata(pdev, pwms);
-	return 0;
-
-err_free_mem:
-	release_mem_region(r->start, resource_size(r));
-err_free:
-	kfree(pwms);
-	return ret;
-}
-
-static int __devexit pwm_remove(struct platform_device *pdev)
-{
-	struct pwm_device *pwms;
-	struct resource *r;
-	int i;
-
-	pwms = platform_get_drvdata(pdev);
-	if (pwms == NULL)
-		return -ENODEV;
-
-	mutex_lock(&pwm_lock);
-
-	for (i = 0; i < VT8500_NR_PWMS; i++)
-		list_del(&pwms[i].node);
-	mutex_unlock(&pwm_lock);
-
-	iounmap(pwms[0].regbase);
-
-	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(r->start, resource_size(r));
-
-	kfree(pwms);
-	return 0;
-}
-
-static struct platform_driver pwm_driver = {
-	.driver		= {
-		.name	= "vt8500-pwm",
-		.owner	= THIS_MODULE,
-	},
-	.probe		= pwm_probe,
-	.remove		= __devexit_p(pwm_remove),
-};
-
-static int __init pwm_init(void)
-{
-	return platform_driver_register(&pwm_driver);
-}
-arch_initcall(pwm_init);
-
-static void __exit pwm_exit(void)
-{
-	platform_driver_unregister(&pwm_driver);
-}
-module_exit(pwm_exit);
-
-MODULE_LICENSE("GPL");
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 806cc4f63516..119bc52ab93e 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -14,6 +14,7 @@
 #include <linux/percpu.h>
 
 #include <asm/mmu_context.h>
+#include <asm/thread_notify.h>
 #include <asm/tlbflush.h>
 
 static DEFINE_RAW_SPINLOCK(cpu_asid_lock);
@@ -48,6 +49,40 @@ void cpu_set_reserved_ttbr0(void)
 }
 #endif
 
+#ifdef CONFIG_PID_IN_CONTEXTIDR
+static int contextidr_notifier(struct notifier_block *unused, unsigned long cmd,
+			       void *t)
+{
+	u32 contextidr;
+	pid_t pid;
+	struct thread_info *thread = t;
+
+	if (cmd != THREAD_NOTIFY_SWITCH)
+		return NOTIFY_DONE;
+
+	pid = task_pid_nr(thread->task) << ASID_BITS;
+	asm volatile(
+	"	mrc	p15, 0, %0, c13, c0, 1\n"
+	"	bfi	%1, %0, #0, %2\n"
+	"	mcr	p15, 0, %1, c13, c0, 1\n"
+	: "=r" (contextidr), "+r" (pid)
+	: "I" (ASID_BITS));
+	isb();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block contextidr_notifier_block = {
+	.notifier_call = contextidr_notifier,
+};
+
+static int __init contextidr_notifier_init(void)
+{
+	return thread_register_notifier(&contextidr_notifier_block);
+}
+arch_initcall(contextidr_notifier_init);
+#endif
+
 /*
  * We fork()ed a process, and we need a new context for the child
  * to run in.
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 655878bcc96d..c2cdf6500f75 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -22,13 +22,14 @@
 #include <linux/memblock.h>
 #include <linux/slab.h>
 #include <linux/iommu.h>
+#include <linux/io.h>
 #include <linux/vmalloc.h>
+#include <linux/sizes.h>
 
 #include <asm/memory.h>
 #include <asm/highmem.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
-#include <asm/sizes.h>
 #include <asm/mach/arch.h>
 #include <asm/dma-iommu.h>
 #include <asm/mach/map.h>
@@ -72,7 +73,7 @@ static dma_addr_t arm_dma_map_page(struct device *dev, struct page *page,
 	     unsigned long offset, size_t size, enum dma_data_direction dir,
 	     struct dma_attrs *attrs)
 {
-	if (!arch_is_coherent())
+	if (!arch_is_coherent() && !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 		__dma_page_cpu_to_dev(page, offset, size, dir);
 	return pfn_to_dma(dev, page_to_pfn(page)) + offset;
 }
@@ -95,7 +96,7 @@ static void arm_dma_unmap_page(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir,
 		struct dma_attrs *attrs)
 {
-	if (!arch_is_coherent())
+	if (!arch_is_coherent() && !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 		__dma_page_dev_to_cpu(pfn_to_page(dma_to_pfn(dev, handle)),
 				      handle & ~PAGE_MASK, size, dir);
 }
@@ -124,6 +125,7 @@ struct dma_map_ops arm_dma_ops = {
 	.alloc			= arm_dma_alloc,
 	.free			= arm_dma_free,
 	.mmap			= arm_dma_mmap,
+	.get_sgtable		= arm_dma_get_sgtable,
 	.map_page		= arm_dma_map_page,
 	.unmap_page		= arm_dma_unmap_page,
 	.map_sg			= arm_dma_map_sg,
@@ -217,115 +219,70 @@ static void __dma_free_buffer(struct page *page, size_t size)
 }
 
 #ifdef CONFIG_MMU
+#ifdef CONFIG_HUGETLB_PAGE
+#error ARM Coherent DMA allocator does not (yet) support huge TLB
+#endif
 
-#define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - consistent_base) >> PAGE_SHIFT)
-#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - consistent_base) >> PMD_SHIFT)
-
-/*
- * These are the page tables (2MB each) covering uncached, DMA consistent allocations
- */
-static pte_t **consistent_pte;
-
-#define DEFAULT_CONSISTENT_DMA_SIZE SZ_2M
+static void *__alloc_from_contiguous(struct device *dev, size_t size,
+				     pgprot_t prot, struct page **ret_page);
 
-static unsigned long consistent_base = CONSISTENT_END - DEFAULT_CONSISTENT_DMA_SIZE;
+static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
+				 pgprot_t prot, struct page **ret_page,
+				 const void *caller);
 
-void __init init_consistent_dma_size(unsigned long size)
+static void *
+__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
+	const void *caller)
 {
-	unsigned long base = CONSISTENT_END - ALIGN(size, SZ_2M);
+	struct vm_struct *area;
+	unsigned long addr;
 
-	BUG_ON(consistent_pte); /* Check we're called before DMA region init */
-	BUG_ON(base < VMALLOC_END);
+	/*
+	 * DMA allocation can be mapped to user space, so lets
+	 * set VM_USERMAP flags too.
+	 */
+	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
+				  caller);
+	if (!area)
+		return NULL;
+	addr = (unsigned long)area->addr;
+	area->phys_addr = __pfn_to_phys(page_to_pfn(page));
 
-	/* Grow region to accommodate specified size  */
-	if (base < consistent_base)
-		consistent_base = base;
+	if (ioremap_page_range(addr, addr + size, area->phys_addr, prot)) {
+		vunmap((void *)addr);
+		return NULL;
+	}
+	return (void *)addr;
 }
 
-#include "vmregion.h"
-
-static struct arm_vmregion_head consistent_head = {
-	.vm_lock	= __SPIN_LOCK_UNLOCKED(&consistent_head.vm_lock),
-	.vm_list	= LIST_HEAD_INIT(consistent_head.vm_list),
-	.vm_end		= CONSISTENT_END,
-};
-
-#ifdef CONFIG_HUGETLB_PAGE
-#error ARM Coherent DMA allocator does not (yet) support huge TLB
-#endif
-
-/*
- * Initialise the consistent memory allocation.
- */
-static int __init consistent_init(void)
+static void __dma_free_remap(void *cpu_addr, size_t size)
 {
-	int ret = 0;
-	pgd_t *pgd;
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
-	int i = 0;
-	unsigned long base = consistent_base;
-	unsigned long num_ptes = (CONSISTENT_END - base) >> PMD_SHIFT;
-
-	if (IS_ENABLED(CONFIG_CMA) && !IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU))
-		return 0;
-
-	consistent_pte = kmalloc(num_ptes * sizeof(pte_t), GFP_KERNEL);
-	if (!consistent_pte) {
-		pr_err("%s: no memory\n", __func__);
-		return -ENOMEM;
+	unsigned int flags = VM_ARM_DMA_CONSISTENT | VM_USERMAP;
+	struct vm_struct *area = find_vm_area(cpu_addr);
+	if (!area || (area->flags & flags) != flags) {
+		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+		return;
 	}
-
-	pr_debug("DMA memory: 0x%08lx - 0x%08lx:\n", base, CONSISTENT_END);
-	consistent_head.vm_start = base;
-
-	do {
-		pgd = pgd_offset(&init_mm, base);
-
-		pud = pud_alloc(&init_mm, pgd, base);
-		if (!pud) {
-			pr_err("%s: no pud tables\n", __func__);
-			ret = -ENOMEM;
-			break;
-		}
-
-		pmd = pmd_alloc(&init_mm, pud, base);
-		if (!pmd) {
-			pr_err("%s: no pmd tables\n", __func__);
-			ret = -ENOMEM;
-			break;
-		}
-		WARN_ON(!pmd_none(*pmd));
-
-		pte = pte_alloc_kernel(pmd, base);
-		if (!pte) {
-			pr_err("%s: no pte tables\n", __func__);
-			ret = -ENOMEM;
-			break;
-		}
-
-		consistent_pte[i++] = pte;
-		base += PMD_SIZE;
-	} while (base < CONSISTENT_END);
-
-	return ret;
+	unmap_kernel_range((unsigned long)cpu_addr, size);
+	vunmap(cpu_addr);
 }
-core_initcall(consistent_init);
 
-static void *__alloc_from_contiguous(struct device *dev, size_t size,
-				     pgprot_t prot, struct page **ret_page);
-
-static struct arm_vmregion_head coherent_head = {
-	.vm_lock	= __SPIN_LOCK_UNLOCKED(&coherent_head.vm_lock),
-	.vm_list	= LIST_HEAD_INIT(coherent_head.vm_list),
+struct dma_pool {
+	size_t size;
+	spinlock_t lock;
+	unsigned long *bitmap;
+	unsigned long nr_pages;
+	void *vaddr;
+	struct page *page;
 };
 
-static size_t coherent_pool_size = DEFAULT_CONSISTENT_DMA_SIZE / 8;
+static struct dma_pool atomic_pool = {
+	.size = SZ_256K,
+};
 
 static int __init early_coherent_pool(char *p)
 {
-	coherent_pool_size = memparse(p, &p);
+	atomic_pool.size = memparse(p, &p);
 	return 0;
 }
 early_param("coherent_pool", early_coherent_pool);
@@ -333,32 +290,45 @@ early_param("coherent_pool", early_coherent_pool);
 /*
  * Initialise the coherent pool for atomic allocations.
  */
-static int __init coherent_init(void)
+static int __init atomic_pool_init(void)
 {
+	struct dma_pool *pool = &atomic_pool;
 	pgprot_t prot = pgprot_dmacoherent(pgprot_kernel);
-	size_t size = coherent_pool_size;
+	unsigned long nr_pages = pool->size >> PAGE_SHIFT;
+	unsigned long *bitmap;
 	struct page *page;
 	void *ptr;
+	int bitmap_size = BITS_TO_LONGS(nr_pages) * sizeof(long);
 
-	if (!IS_ENABLED(CONFIG_CMA))
-		return 0;
+	bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!bitmap)
+		goto no_bitmap;
 
-	ptr = __alloc_from_contiguous(NULL, size, prot, &page);
+	if (IS_ENABLED(CONFIG_CMA))
+		ptr = __alloc_from_contiguous(NULL, pool->size, prot, &page);
+	else
+		ptr = __alloc_remap_buffer(NULL, pool->size, GFP_KERNEL, prot,
+					   &page, NULL);
 	if (ptr) {
-		coherent_head.vm_start = (unsigned long) ptr;
-		coherent_head.vm_end = (unsigned long) ptr + size;
-		printk(KERN_INFO "DMA: preallocated %u KiB pool for atomic coherent allocations\n",
-		       (unsigned)size / 1024);
+		spin_lock_init(&pool->lock);
+		pool->vaddr = ptr;
+		pool->page = page;
+		pool->bitmap = bitmap;
+		pool->nr_pages = nr_pages;
+		pr_info("DMA: preallocated %u KiB pool for atomic coherent allocations\n",
+		       (unsigned)pool->size / 1024);
 		return 0;
 	}
-	printk(KERN_ERR "DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
-	       (unsigned)size / 1024);
+	kfree(bitmap);
+no_bitmap:
+	pr_err("DMA: failed to allocate %u KiB pool for atomic coherent allocation\n",
+	       (unsigned)pool->size / 1024);
 	return -ENOMEM;
 }
 /*
  * CMA is activated by core_initcall, so we must be called after it.
  */
-postcore_initcall(coherent_init);
+postcore_initcall(atomic_pool_init);
 
 struct dma_contig_early_reserve {
 	phys_addr_t base;
@@ -406,112 +376,6 @@ void __init dma_contiguous_remap(void)
 	}
 }
 
-static void *
-__dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
-	const void *caller)
-{
-	struct arm_vmregion *c;
-	size_t align;
-	int bit;
-
-	if (!consistent_pte) {
-		pr_err("%s: not initialised\n", __func__);
-		dump_stack();
-		return NULL;
-	}
-
-	/*
-	 * Align the virtual region allocation - maximum alignment is
-	 * a section size, minimum is a page size.  This helps reduce
-	 * fragmentation of the DMA space, and also prevents allocations
-	 * smaller than a section from crossing a section boundary.
-	 */
-	bit = fls(size - 1);
-	if (bit > SECTION_SHIFT)
-		bit = SECTION_SHIFT;
-	align = 1 << bit;
-
-	/*
-	 * Allocate a virtual address in the consistent mapping region.
-	 */
-	c = arm_vmregion_alloc(&consistent_head, align, size,
-			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM), caller);
-	if (c) {
-		pte_t *pte;
-		int idx = CONSISTENT_PTE_INDEX(c->vm_start);
-		u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
-
-		pte = consistent_pte[idx] + off;
-		c->priv = page;
-
-		do {
-			BUG_ON(!pte_none(*pte));
-
-			set_pte_ext(pte, mk_pte(page, prot), 0);
-			page++;
-			pte++;
-			off++;
-			if (off >= PTRS_PER_PTE) {
-				off = 0;
-				pte = consistent_pte[++idx];
-			}
-		} while (size -= PAGE_SIZE);
-
-		dsb();
-
-		return (void *)c->vm_start;
-	}
-	return NULL;
-}
-
-static void __dma_free_remap(void *cpu_addr, size_t size)
-{
-	struct arm_vmregion *c;
-	unsigned long addr;
-	pte_t *ptep;
-	int idx;
-	u32 off;
-
-	c = arm_vmregion_find_remove(&consistent_head, (unsigned long)cpu_addr);
-	if (!c) {
-		pr_err("%s: trying to free invalid coherent area: %p\n",
-		       __func__, cpu_addr);
-		dump_stack();
-		return;
-	}
-
-	if ((c->vm_end - c->vm_start) != size) {
-		pr_err("%s: freeing wrong coherent size (%ld != %d)\n",
-		       __func__, c->vm_end - c->vm_start, size);
-		dump_stack();
-		size = c->vm_end - c->vm_start;
-	}
-
-	idx = CONSISTENT_PTE_INDEX(c->vm_start);
-	off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
-	ptep = consistent_pte[idx] + off;
-	addr = c->vm_start;
-	do {
-		pte_t pte = ptep_get_and_clear(&init_mm, addr, ptep);
-
-		ptep++;
-		addr += PAGE_SIZE;
-		off++;
-		if (off >= PTRS_PER_PTE) {
-			off = 0;
-			ptep = consistent_pte[++idx];
-		}
-
-		if (pte_none(pte) || !pte_present(pte))
-			pr_crit("%s: bad page in kernel page table\n",
-				__func__);
-	} while (size -= PAGE_SIZE);
-
-	flush_tlb_kernel_range(c->vm_start, c->vm_end);
-
-	arm_vmregion_free(&consistent_head, c);
-}
-
 static int __dma_update_pte(pte_t *pte, pgtable_t token, unsigned long addr,
 			    void *data)
 {
@@ -552,16 +416,17 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 	return ptr;
 }
 
-static void *__alloc_from_pool(struct device *dev, size_t size,
-			       struct page **ret_page, const void *caller)
+static void *__alloc_from_pool(size_t size, struct page **ret_page)
 {
-	struct arm_vmregion *c;
+	struct dma_pool *pool = &atomic_pool;
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned int pageno;
+	unsigned long flags;
+	void *ptr = NULL;
 	size_t align;
 
-	if (!coherent_head.vm_start) {
-		printk(KERN_ERR "%s: coherent pool not initialised!\n",
-		       __func__);
-		dump_stack();
+	if (!pool->vaddr) {
+		WARN(1, "coherent pool not initialised!\n");
 		return NULL;
 	}
 
@@ -571,35 +436,41 @@ static void *__alloc_from_pool(struct device *dev, size_t size,
 	 * size. This helps reduce fragmentation of the DMA space.
 	 */
 	align = PAGE_SIZE << get_order(size);
-	c = arm_vmregion_alloc(&coherent_head, align, size, 0, caller);
-	if (c) {
-		void *ptr = (void *)c->vm_start;
-		struct page *page = virt_to_page(ptr);
-		*ret_page = page;
-		return ptr;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	pageno = bitmap_find_next_zero_area(pool->bitmap, pool->nr_pages,
+					    0, count, (1 << align) - 1);
+	if (pageno < pool->nr_pages) {
+		bitmap_set(pool->bitmap, pageno, count);
+		ptr = pool->vaddr + PAGE_SIZE * pageno;
+		*ret_page = pool->page + pageno;
 	}
-	return NULL;
+	spin_unlock_irqrestore(&pool->lock, flags);
+
+	return ptr;
 }
 
-static int __free_from_pool(void *cpu_addr, size_t size)
+static int __free_from_pool(void *start, size_t size)
 {
-	unsigned long start = (unsigned long)cpu_addr;
-	unsigned long end = start + size;
-	struct arm_vmregion *c;
+	struct dma_pool *pool = &atomic_pool;
+	unsigned long pageno, count;
+	unsigned long flags;
 
-	if (start < coherent_head.vm_start || end > coherent_head.vm_end)
+	if (start < pool->vaddr || start > pool->vaddr + pool->size)
 		return 0;
 
-	c = arm_vmregion_find_remove(&coherent_head, (unsigned long)start);
-
-	if ((c->vm_end - c->vm_start) != size) {
-		printk(KERN_ERR "%s: freeing wrong coherent size (%ld != %d)\n",
-		       __func__, c->vm_end - c->vm_start, size);
-		dump_stack();
-		size = c->vm_end - c->vm_start;
+	if (start + size > pool->vaddr + pool->size) {
+		WARN(1, "freeing wrong coherent size from pool\n");
+		return 0;
 	}
 
-	arm_vmregion_free(&coherent_head, c);
+	pageno = (start - pool->vaddr) >> PAGE_SHIFT;
+	count = size >> PAGE_SHIFT;
+
+	spin_lock_irqsave(&pool->lock, flags);
+	bitmap_clear(pool->bitmap, pageno, count);
+	spin_unlock_irqrestore(&pool->lock, flags);
+
 	return 1;
 }
 
@@ -644,7 +515,7 @@ static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot)
 
 #define __get_dma_pgprot(attrs, prot)	__pgprot(0)
 #define __alloc_remap_buffer(dev, size, gfp, prot, ret, c)	NULL
-#define __alloc_from_pool(dev, size, ret_page, c)		NULL
+#define __alloc_from_pool(size, ret_page)			NULL
 #define __alloc_from_contiguous(dev, size, prot, ret)		NULL
 #define __free_from_pool(cpu_addr, size)			0
 #define __free_from_contiguous(dev, page, size)			do { } while (0)
@@ -702,10 +573,10 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 
 	if (arch_is_coherent() || nommu())
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
+	else if (gfp & GFP_ATOMIC)
+		addr = __alloc_from_pool(size, &page);
 	else if (!IS_ENABLED(CONFIG_CMA))
 		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
-	else if (gfp & GFP_ATOMIC)
-		addr = __alloc_from_pool(dev, size, &page, caller);
 	else
 		addr = __alloc_from_contiguous(dev, size, prot, &page);
 
@@ -741,16 +612,22 @@ int arm_dma_mmap(struct device *dev, struct vm_area_struct *vma,
 {
 	int ret = -ENXIO;
 #ifdef CONFIG_MMU
+	unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
+	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long pfn = dma_to_pfn(dev, dma_addr);
+	unsigned long off = vma->vm_pgoff;
+
 	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
 
 	if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret))
 		return ret;
 
-	ret = remap_pfn_range(vma, vma->vm_start,
-			      pfn + vma->vm_pgoff,
-			      vma->vm_end - vma->vm_start,
-			      vma->vm_page_prot);
+	if (off < nr_pages && nr_vma_pages <= (nr_pages - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      vma->vm_end - vma->vm_start,
+				      vma->vm_page_prot);
+	}
 #endif	/* CONFIG_MMU */
 
 	return ret;
@@ -785,6 +662,21 @@ void arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 	}
 }
 
+int arm_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+		 void *cpu_addr, dma_addr_t handle, size_t size,
+		 struct dma_attrs *attrs)
+{
+	struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
+	int ret;
+
+	ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+	if (unlikely(ret))
+		return ret;
+
+	sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+	return 0;
+}
+
 static void dma_cache_maint_page(struct page *page, unsigned long offset,
 	size_t size, enum dma_data_direction dir,
 	void (*op)(const void *, size_t, int))
@@ -998,9 +890,6 @@ static int arm_dma_set_mask(struct device *dev, u64 dma_mask)
 
 static int __init dma_debug_do_init(void)
 {
-#ifdef CONFIG_MMU
-	arm_vmregion_create_proc("dma-mappings", &consistent_head);
-#endif
 	dma_debug_init(PREALLOC_DMA_DEBUG_ENTRIES);
 	return 0;
 }
@@ -1088,7 +977,7 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size, gfp_t
 
 	return pages;
 error:
-	while (--i)
+	while (i--)
 		if (pages[i])
 			__free_pages(pages[i], 0);
 	if (array_size <= PAGE_SIZE)
@@ -1117,61 +1006,32 @@ static int __iommu_free_buffer(struct device *dev, struct page **pages, size_t s
  * Create a CPU mapping for a specified pages
  */
 static void *
-__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot)
+__iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
+		    const void *caller)
 {
-	struct arm_vmregion *c;
-	size_t align;
-	size_t count = size >> PAGE_SHIFT;
-	int bit;
+	unsigned int i, nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct vm_struct *area;
+	unsigned long p;
 
-	if (!consistent_pte[0]) {
-		pr_err("%s: not initialised\n", __func__);
-		dump_stack();
+	area = get_vm_area_caller(size, VM_ARM_DMA_CONSISTENT | VM_USERMAP,
+				  caller);
+	if (!area)
 		return NULL;
-	}
-
-	/*
-	 * Align the virtual region allocation - maximum alignment is
-	 * a section size, minimum is a page size.  This helps reduce
-	 * fragmentation of the DMA space, and also prevents allocations
-	 * smaller than a section from crossing a section boundary.
-	 */
-	bit = fls(size - 1);
-	if (bit > SECTION_SHIFT)
-		bit = SECTION_SHIFT;
-	align = 1 << bit;
-
-	/*
-	 * Allocate a virtual address in the consistent mapping region.
-	 */
-	c = arm_vmregion_alloc(&consistent_head, align, size,
-			    gfp & ~(__GFP_DMA | __GFP_HIGHMEM), NULL);
-	if (c) {
-		pte_t *pte;
-		int idx = CONSISTENT_PTE_INDEX(c->vm_start);
-		int i = 0;
-		u32 off = CONSISTENT_OFFSET(c->vm_start) & (PTRS_PER_PTE-1);
-
-		pte = consistent_pte[idx] + off;
-		c->priv = pages;
-
-		do {
-			BUG_ON(!pte_none(*pte));
-
-			set_pte_ext(pte, mk_pte(pages[i], prot), 0);
-			pte++;
-			off++;
-			i++;
-			if (off >= PTRS_PER_PTE) {
-				off = 0;
-				pte = consistent_pte[++idx];
-			}
-		} while (i < count);
 
-		dsb();
+	area->pages = pages;
+	area->nr_pages = nr_pages;
+	p = (unsigned long)area->addr;
 
-		return (void *)c->vm_start;
+	for (i = 0; i < nr_pages; i++) {
+		phys_addr_t phys = __pfn_to_phys(page_to_pfn(pages[i]));
+		if (ioremap_page_range(p, p + PAGE_SIZE, phys, prot))
+			goto err;
+		p += PAGE_SIZE;
 	}
+	return area->addr;
+err:
+	unmap_kernel_range((unsigned long)area->addr, size);
+	vunmap(area->addr);
 	return NULL;
 }
 
@@ -1230,6 +1090,19 @@ static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t si
 	return 0;
 }
 
+static struct page **__iommu_get_pages(void *cpu_addr, struct dma_attrs *attrs)
+{
+	struct vm_struct *area;
+
+	if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
+		return cpu_addr;
+
+	area = find_vm_area(cpu_addr);
+	if (area && (area->flags & VM_ARM_DMA_CONSISTENT))
+		return area->pages;
+	return NULL;
+}
+
 static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	    dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
@@ -1248,7 +1121,11 @@ static void *arm_iommu_alloc_attrs(struct device *dev, size_t size,
 	if (*handle == DMA_ERROR_CODE)
 		goto err_buffer;
 
-	addr = __iommu_alloc_remap(pages, size, gfp, prot);
+	if (dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs))
+		return pages;
+
+	addr = __iommu_alloc_remap(pages, size, gfp, prot,
+				   __builtin_return_address(0));
 	if (!addr)
 		goto err_mapping;
 
@@ -1265,31 +1142,25 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 		    void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		    struct dma_attrs *attrs)
 {
-	struct arm_vmregion *c;
+	unsigned long uaddr = vma->vm_start;
+	unsigned long usize = vma->vm_end - vma->vm_start;
+	struct page **pages = __iommu_get_pages(cpu_addr, attrs);
 
 	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
-	c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr);
-
-	if (c) {
-		struct page **pages = c->priv;
-
-		unsigned long uaddr = vma->vm_start;
-		unsigned long usize = vma->vm_end - vma->vm_start;
-		int i = 0;
 
-		do {
-			int ret;
+	if (!pages)
+		return -ENXIO;
 
-			ret = vm_insert_page(vma, uaddr, pages[i++]);
-			if (ret) {
-				pr_err("Remapping memory, error: %d\n", ret);
-				return ret;
-			}
+	do {
+		int ret = vm_insert_page(vma, uaddr, *pages++);
+		if (ret) {
+			pr_err("Remapping memory failed: %d\n", ret);
+			return ret;
+		}
+		uaddr += PAGE_SIZE;
+		usize -= PAGE_SIZE;
+	} while (usize > 0);
 
-			uaddr += PAGE_SIZE;
-			usize -= PAGE_SIZE;
-		} while (usize > 0);
-	}
 	return 0;
 }
 
@@ -1300,16 +1171,35 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 			  dma_addr_t handle, struct dma_attrs *attrs)
 {
-	struct arm_vmregion *c;
+	struct page **pages = __iommu_get_pages(cpu_addr, attrs);
 	size = PAGE_ALIGN(size);
 
-	c = arm_vmregion_find(&consistent_head, (unsigned long)cpu_addr);
-	if (c) {
-		struct page **pages = c->priv;
-		__dma_free_remap(cpu_addr, size);
-		__iommu_remove_mapping(dev, handle, size);
-		__iommu_free_buffer(dev, pages, size);
+	if (!pages) {
+		WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+		return;
 	}
+
+	if (!dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs)) {
+		unmap_kernel_range((unsigned long)cpu_addr, size);
+		vunmap(cpu_addr);
+	}
+
+	__iommu_remove_mapping(dev, handle, size);
+	__iommu_free_buffer(dev, pages, size);
+}
+
+static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
+				 void *cpu_addr, dma_addr_t dma_addr,
+				 size_t size, struct dma_attrs *attrs)
+{
+	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	struct page **pages = __iommu_get_pages(cpu_addr, attrs);
+
+	if (!pages)
+		return -ENXIO;
+
+	return sg_alloc_table_from_pages(sgt, pages, count, 0, size,
+					 GFP_KERNEL);
 }
 
 /*
@@ -1317,7 +1207,7 @@ void arm_iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
  */
 static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 			  size_t size, dma_addr_t *handle,
-			  enum dma_data_direction dir)
+			  enum dma_data_direction dir, struct dma_attrs *attrs)
 {
 	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
 	dma_addr_t iova, iova_base;
@@ -1336,7 +1226,8 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 		phys_addr_t phys = page_to_phys(sg_page(s));
 		unsigned int len = PAGE_ALIGN(s->offset + s->length);
 
-		if (!arch_is_coherent())
+		if (!arch_is_coherent() &&
+		    !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
 
 		ret = iommu_map(mapping->domain, iova, phys, len, 0);
@@ -1383,7 +1274,7 @@ int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 
 		if (s->offset || (size & ~PAGE_MASK) || size + s->length > max) {
 			if (__map_sg_chunk(dev, start, size, &dma->dma_address,
-			    dir) < 0)
+			    dir, attrs) < 0)
 				goto bad_mapping;
 
 			dma->dma_address += offset;
@@ -1396,7 +1287,7 @@ int arm_iommu_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		}
 		size += s->length;
 	}
-	if (__map_sg_chunk(dev, start, size, &dma->dma_address, dir) < 0)
+	if (__map_sg_chunk(dev, start, size, &dma->dma_address, dir, attrs) < 0)
 		goto bad_mapping;
 
 	dma->dma_address += offset;
@@ -1430,7 +1321,8 @@ void arm_iommu_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 		if (sg_dma_len(s))
 			__iommu_remove_mapping(dev, sg_dma_address(s),
 					       sg_dma_len(s));
-		if (!arch_is_coherent())
+		if (!arch_is_coherent() &&
+		    !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 			__dma_page_dev_to_cpu(sg_page(s), s->offset,
 					      s->length, dir);
 	}
@@ -1492,7 +1384,7 @@ static dma_addr_t arm_iommu_map_page(struct device *dev, struct page *page,
 	dma_addr_t dma_addr;
 	int ret, len = PAGE_ALIGN(size + offset);
 
-	if (!arch_is_coherent())
+	if (!arch_is_coherent() && !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 		__dma_page_cpu_to_dev(page, offset, size, dir);
 
 	dma_addr = __alloc_iova(mapping, len);
@@ -1531,7 +1423,7 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 	if (!iova)
 		return;
 
-	if (!arch_is_coherent())
+	if (!arch_is_coherent() && !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 		__dma_page_dev_to_cpu(page, offset, size, dir);
 
 	iommu_unmap(mapping->domain, iova, len);
@@ -1571,6 +1463,7 @@ struct dma_map_ops iommu_ops = {
 	.alloc		= arm_iommu_alloc_attrs,
 	.free		= arm_iommu_free_attrs,
 	.mmap		= arm_iommu_mmap_attrs,
+	.get_sgtable	= arm_iommu_get_sgtable,
 
 	.map_page		= arm_iommu_map_page,
 	.unmap_page		= arm_iommu_unmap_page,
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index f54d59219764..9aec41fa80ae 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -21,13 +21,13 @@
 #include <linux/gfp.h>
 #include <linux/memblock.h>
 #include <linux/dma-contiguous.h>
+#include <linux/sizes.h>
 
 #include <asm/mach-types.h>
 #include <asm/memblock.h>
 #include <asm/prom.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
-#include <asm/sizes.h>
 #include <asm/tlb.h>
 #include <asm/fixmap.h>
 
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 4f55f5062ab7..566750fa57d4 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -25,6 +25,7 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/io.h>
+#include <linux/sizes.h>
 
 #include <asm/cp15.h>
 #include <asm/cputype.h>
@@ -32,7 +33,6 @@
 #include <asm/mmu_context.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
-#include <asm/sizes.h>
 #include <asm/system_info.h>
 
 #include <asm/mach/map.h>
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 2e8a1efdf7b8..6776160618ef 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -59,6 +59,9 @@ extern void __flush_dcache_page(struct address_space *mapping, struct page *page
 #define VM_ARM_MTYPE(mt)		((mt) << 20)
 #define VM_ARM_MTYPE_MASK	(0x1f << 20)
 
+/* consistent regions used by dma_alloc_attrs() */
+#define VM_ARM_DMA_CONSISTENT	0x20000000
+
 #endif
 
 #ifdef CONFIG_ZONE_DMA
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index cf4528d51774..4c2d0451e84a 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -16,13 +16,13 @@
 #include <linux/memblock.h>
 #include <linux/fs.h>
 #include <linux/vmalloc.h>
+#include <linux/sizes.h>
 
 #include <asm/cp15.h>
 #include <asm/cputype.h>
 #include <asm/sections.h>
 #include <asm/cachetype.h>
 #include <asm/setup.h>
-#include <asm/sizes.h>
 #include <asm/smp_plat.h>
 #include <asm/tlb.h>
 #include <asm/highmem.h>
@@ -422,12 +422,6 @@ static void __init build_mem_type_table(void)
 	vecs_pgprot = kern_pgprot = user_pgprot = cp->pte;
 
 	/*
-	 * Only use write-through for non-SMP systems
-	 */
-	if (!is_smp() && cpu_arch >= CPU_ARCH_ARMv5 && cachepolicy > CPOLICY_WRITETHROUGH)
-		vecs_pgprot = cache_policies[CPOLICY_WRITETHROUGH].pte;
-
-	/*
 	 * Enable CPU-specific coherency if supported.
 	 * (Only available on XSC3 at the moment.)
 	 */
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 5900cd520e84..86b8b480634f 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -107,6 +107,12 @@ ENTRY(cpu_v6_switch_mm)
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 	mcr	p15, 0, r2, c7, c10, 4		@ drain write buffer
 	mcr	p15, 0, r0, c2, c0, 0		@ set TTB 0
+#ifdef CONFIG_PID_IN_CONTEXTIDR
+	mrc	p15, 0, r2, c13, c0, 1		@ read current context ID
+	bic	r2, r2, #0xff			@ extract the PID
+	and	r1, r1, #0xff
+	orr	r1, r1, r2			@ insert into new context ID
+#endif
 	mcr	p15, 0, r1, c13, c0, 1		@ set context ID
 #endif
 	mov	pc, lr
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index 42ac069c8012..fd045e706390 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -46,6 +46,11 @@ ENTRY(cpu_v7_switch_mm)
 #ifdef CONFIG_ARM_ERRATA_430973
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 #endif
+#ifdef CONFIG_PID_IN_CONTEXTIDR
+	mrc	p15, 0, r2, c13, c0, 1		@ read current context ID
+	lsr	r2, r2, #8			@ extract the PID
+	bfi	r1, r2, #8, #24			@ insert into new context ID
+#endif
 #ifdef CONFIG_ARM_ERRATA_754322
 	dsb
 #endif
diff --git a/arch/arm/oprofile/common.c b/arch/arm/oprofile/common.c
index 4e0a371630b3..99c63d4b6af8 100644
--- a/arch/arm/oprofile/common.c
+++ b/arch/arm/oprofile/common.c
@@ -23,26 +23,37 @@
 #include <asm/ptrace.h>
 
 #ifdef CONFIG_HW_PERF_EVENTS
+
+/*
+ * OProfile has a curious naming scheme for the ARM PMUs, but they are
+ * part of the user ABI so we need to map from the perf PMU name for
+ * supported PMUs.
+ */
+static struct op_perf_name {
+	char *perf_name;
+	char *op_name;
+} op_perf_name_map[] = {
+	{ "xscale1",		"arm/xscale1"	},
+	{ "xscale1",		"arm/xscale2"	},
+	{ "v6",			"arm/armv6"	},
+	{ "v6mpcore",		"arm/mpcore"	},
+	{ "ARMv7 Cortex-A8",	"arm/armv7"	},
+	{ "ARMv7 Cortex-A9",	"arm/armv7-ca9"	},
+};
+
 char *op_name_from_perf_id(void)
 {
-	enum arm_perf_pmu_ids id = armpmu_get_pmu_id();
-
-	switch (id) {
-	case ARM_PERF_PMU_ID_XSCALE1:
-		return "arm/xscale1";
-	case ARM_PERF_PMU_ID_XSCALE2:
-		return "arm/xscale2";
-	case ARM_PERF_PMU_ID_V6:
-		return "arm/armv6";
-	case ARM_PERF_PMU_ID_V6MP:
-		return "arm/mpcore";
-	case ARM_PERF_PMU_ID_CA8:
-		return "arm/armv7";
-	case ARM_PERF_PMU_ID_CA9:
-		return "arm/armv7-ca9";
-	default:
-		return NULL;
+	int i;
+	struct op_perf_name names;
+	const char *perf_name = perf_pmu_name();
+
+	for (i = 0; i < ARRAY_SIZE(op_perf_name_map); ++i) {
+		names = op_perf_name_map[i];
+		if (!strcmp(names.perf_name, perf_name))
+			return names.op_name;
 	}
+
+	return NULL;
 }
 #endif
 
diff --git a/arch/arm/plat-mxc/Kconfig b/arch/arm/plat-mxc/Kconfig
index c722f9ce6918..baf9064c0844 100644
--- a/arch/arm/plat-mxc/Kconfig
+++ b/arch/arm/plat-mxc/Kconfig
@@ -47,12 +47,6 @@ config MXC_TZIC
 config MXC_AVIC
 	bool
 
-config MXC_PWM
-	tristate "Enable PWM driver"
-	select HAVE_PWM
-	help
-	  Enable support for the i.MX PWM controller(s).
-
 config MXC_DEBUG_BOARD
 	bool "Enable MXC debug board(for 3-stack)"
 	help
diff --git a/arch/arm/plat-mxc/Makefile b/arch/arm/plat-mxc/Makefile
index 63b064b5c1d5..6ac720031150 100644
--- a/arch/arm/plat-mxc/Makefile
+++ b/arch/arm/plat-mxc/Makefile
@@ -11,7 +11,6 @@ obj-$(CONFIG_MXC_AVIC) += avic.o
 obj-$(CONFIG_IMX_HAVE_IOMUX_V1) += iomux-v1.o
 obj-$(CONFIG_ARCH_MXC_IOMUX_V3) += iomux-v3.o
 obj-$(CONFIG_IRAM_ALLOC) += iram_alloc.o
-obj-$(CONFIG_MXC_PWM)  += pwm.o
 obj-$(CONFIG_MXC_ULPI) += ulpi.o
 obj-$(CONFIG_MXC_USE_EPIT) += epit.o
 obj-$(CONFIG_MXC_DEBUG_BOARD) += 3ds_debugboard.o
diff --git a/arch/arm/plat-mxc/include/mach/i2c.h b/arch/arm/plat-mxc/include/mach/i2c.h
index 375cdd0cf876..8289d915e615 100644
--- a/arch/arm/plat-mxc/include/mach/i2c.h
+++ b/arch/arm/plat-mxc/include/mach/i2c.h
@@ -15,7 +15,7 @@
  *
  **/
 struct imxi2c_platform_data {
-	int bitrate;
+	u32 bitrate;
 };
 
 #endif /* __ASM_ARCH_I2C_H_ */
diff --git a/arch/arm/plat-mxc/pwm.c b/arch/arm/plat-mxc/pwm.c
deleted file mode 100644
index c0cab2270dd1..000000000000
--- a/arch/arm/plat-mxc/pwm.c
+++ /dev/null
@@ -1,306 +0,0 @@
-/*
- * simple driver for PWM (Pulse Width Modulator) controller
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Derived from pxa PWM driver by eric miao <eric.miao@marvell.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/pwm.h>
-#include <mach/hardware.h>
-
-
-/* i.MX1 and i.MX21 share the same PWM function block: */
-
-#define MX1_PWMC    0x00   /* PWM Control Register */
-#define MX1_PWMS    0x04   /* PWM Sample Register */
-#define MX1_PWMP    0x08   /* PWM Period Register */
-
-
-/* i.MX27, i.MX31, i.MX35 share the same PWM function block: */
-
-#define MX3_PWMCR                 0x00    /* PWM Control Register */
-#define MX3_PWMSAR                0x0C    /* PWM Sample Register */
-#define MX3_PWMPR                 0x10    /* PWM Period Register */
-#define MX3_PWMCR_PRESCALER(x)    (((x - 1) & 0xFFF) << 4)
-#define MX3_PWMCR_DOZEEN                (1 << 24)
-#define MX3_PWMCR_WAITEN                (1 << 23)
-#define MX3_PWMCR_DBGEN			(1 << 22)
-#define MX3_PWMCR_CLKSRC_IPG_HIGH (2 << 16)
-#define MX3_PWMCR_CLKSRC_IPG      (1 << 16)
-#define MX3_PWMCR_EN              (1 << 0)
-
-
-
-struct pwm_device {
-	struct list_head	node;
-	struct platform_device *pdev;
-
-	const char	*label;
-	struct clk	*clk;
-
-	int		clk_enabled;
-	void __iomem	*mmio_base;
-
-	unsigned int	use_count;
-	unsigned int	pwm_id;
-};
-
-int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns)
-{
-	if (pwm == NULL || period_ns == 0 || duty_ns > period_ns)
-		return -EINVAL;
-
-	if (!(cpu_is_mx1() || cpu_is_mx21())) {
-		unsigned long long c;
-		unsigned long period_cycles, duty_cycles, prescale;
-		u32 cr;
-
-		c = clk_get_rate(pwm->clk);
-		c = c * period_ns;
-		do_div(c, 1000000000);
-		period_cycles = c;
-
-		prescale = period_cycles / 0x10000 + 1;
-
-		period_cycles /= prescale;
-		c = (unsigned long long)period_cycles * duty_ns;
-		do_div(c, period_ns);
-		duty_cycles = c;
-
-		/*
-		 * according to imx pwm RM, the real period value should be
-		 * PERIOD value in PWMPR plus 2.
-		 */
-		if (period_cycles > 2)
-			period_cycles -= 2;
-		else
-			period_cycles = 0;
-
-		writel(duty_cycles, pwm->mmio_base + MX3_PWMSAR);
-		writel(period_cycles, pwm->mmio_base + MX3_PWMPR);
-
-		cr = MX3_PWMCR_PRESCALER(prescale) |
-			MX3_PWMCR_DOZEEN | MX3_PWMCR_WAITEN |
-			MX3_PWMCR_DBGEN | MX3_PWMCR_EN;
-
-		if (cpu_is_mx25())
-			cr |= MX3_PWMCR_CLKSRC_IPG;
-		else
-			cr |= MX3_PWMCR_CLKSRC_IPG_HIGH;
-
-		writel(cr, pwm->mmio_base + MX3_PWMCR);
-	} else if (cpu_is_mx1() || cpu_is_mx21()) {
-		/* The PWM subsystem allows for exact frequencies. However,
-		 * I cannot connect a scope on my device to the PWM line and
-		 * thus cannot provide the program the PWM controller
-		 * exactly. Instead, I'm relying on the fact that the
-		 * Bootloader (u-boot or WinCE+haret) has programmed the PWM
-		 * function group already. So I'll just modify the PWM sample
-		 * register to follow the ratio of duty_ns vs. period_ns
-		 * accordingly.
-		 *
-		 * This is good enough for programming the brightness of
-		 * the LCD backlight.
-		 *
-		 * The real implementation would divide PERCLK[0] first by
-		 * both the prescaler (/1 .. /128) and then by CLKSEL
-		 * (/2 .. /16).
-		 */
-		u32 max = readl(pwm->mmio_base + MX1_PWMP);
-		u32 p = max * duty_ns / period_ns;
-		writel(max - p, pwm->mmio_base + MX1_PWMS);
-	} else {
-		BUG();
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(pwm_config);
-
-int pwm_enable(struct pwm_device *pwm)
-{
-	int rc = 0;
-
-	if (!pwm->clk_enabled) {
-		rc = clk_prepare_enable(pwm->clk);
-		if (!rc)
-			pwm->clk_enabled = 1;
-	}
-	return rc;
-}
-EXPORT_SYMBOL(pwm_enable);
-
-void pwm_disable(struct pwm_device *pwm)
-{
-	writel(0, pwm->mmio_base + MX3_PWMCR);
-
-	if (pwm->clk_enabled) {
-		clk_disable_unprepare(pwm->clk);
-		pwm->clk_enabled = 0;
-	}
-}
-EXPORT_SYMBOL(pwm_disable);
-
-static DEFINE_MUTEX(pwm_lock);
-static LIST_HEAD(pwm_list);
-
-struct pwm_device *pwm_request(int pwm_id, const char *label)
-{
-	struct pwm_device *pwm;
-	int found = 0;
-
-	mutex_lock(&pwm_lock);
-
-	list_for_each_entry(pwm, &pwm_list, node) {
-		if (pwm->pwm_id == pwm_id) {
-			found = 1;
-			break;
-		}
-	}
-
-	if (found) {
-		if (pwm->use_count == 0) {
-			pwm->use_count++;
-			pwm->label = label;
-		} else
-			pwm = ERR_PTR(-EBUSY);
-	} else
-		pwm = ERR_PTR(-ENOENT);
-
-	mutex_unlock(&pwm_lock);
-	return pwm;
-}
-EXPORT_SYMBOL(pwm_request);
-
-void pwm_free(struct pwm_device *pwm)
-{
-	mutex_lock(&pwm_lock);
-
-	if (pwm->use_count) {
-		pwm->use_count--;
-		pwm->label = NULL;
-	} else
-		pr_warning("PWM device already freed\n");
-
-	mutex_unlock(&pwm_lock);
-}
-EXPORT_SYMBOL(pwm_free);
-
-static int __devinit mxc_pwm_probe(struct platform_device *pdev)
-{
-	struct pwm_device *pwm;
-	struct resource *r;
-	int ret = 0;
-
-	pwm = kzalloc(sizeof(struct pwm_device), GFP_KERNEL);
-	if (pwm == NULL) {
-		dev_err(&pdev->dev, "failed to allocate memory\n");
-		return -ENOMEM;
-	}
-
-	pwm->clk = clk_get(&pdev->dev, "pwm");
-
-	if (IS_ERR(pwm->clk)) {
-		ret = PTR_ERR(pwm->clk);
-		goto err_free;
-	}
-
-	pwm->clk_enabled = 0;
-
-	pwm->use_count = 0;
-	pwm->pwm_id = pdev->id;
-	pwm->pdev = pdev;
-
-	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (r == NULL) {
-		dev_err(&pdev->dev, "no memory resource defined\n");
-		ret = -ENODEV;
-		goto err_free_clk;
-	}
-
-	r = request_mem_region(r->start, resource_size(r), pdev->name);
-	if (r == NULL) {
-		dev_err(&pdev->dev, "failed to request memory resource\n");
-		ret = -EBUSY;
-		goto err_free_clk;
-	}
-
-	pwm->mmio_base = ioremap(r->start, resource_size(r));
-	if (pwm->mmio_base == NULL) {
-		dev_err(&pdev->dev, "failed to ioremap() registers\n");
-		ret = -ENODEV;
-		goto err_free_mem;
-	}
-
-	mutex_lock(&pwm_lock);
-	list_add_tail(&pwm->node, &pwm_list);
-	mutex_unlock(&pwm_lock);
-
-	platform_set_drvdata(pdev, pwm);
-	return 0;
-
-err_free_mem:
-	release_mem_region(r->start, resource_size(r));
-err_free_clk:
-	clk_put(pwm->clk);
-err_free:
-	kfree(pwm);
-	return ret;
-}
-
-static int __devexit mxc_pwm_remove(struct platform_device *pdev)
-{
-	struct pwm_device *pwm;
-	struct resource *r;
-
-	pwm = platform_get_drvdata(pdev);
-	if (pwm == NULL)
-		return -ENODEV;
-
-	mutex_lock(&pwm_lock);
-	list_del(&pwm->node);
-	mutex_unlock(&pwm_lock);
-
-	iounmap(pwm->mmio_base);
-
-	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(r->start, resource_size(r));
-
-	clk_put(pwm->clk);
-
-	kfree(pwm);
-	return 0;
-}
-
-static struct platform_driver mxc_pwm_driver = {
-	.driver		= {
-		.name	= "mxc_pwm",
-	},
-	.probe		= mxc_pwm_probe,
-	.remove		= __devexit_p(mxc_pwm_remove),
-};
-
-static int __init mxc_pwm_init(void)
-{
-	return platform_driver_register(&mxc_pwm_driver);
-}
-arch_initcall(mxc_pwm_init);
-
-static void __exit mxc_pwm_exit(void)
-{
-	platform_driver_unregister(&mxc_pwm_driver);
-}
-module_exit(mxc_pwm_exit);
-
-MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Sascha Hauer <s.hauer@pengutronix.de>");
diff --git a/arch/arm/plat-nomadik/include/plat/i2c.h b/arch/arm/plat-nomadik/include/plat/i2c.h
deleted file mode 100644
index 8ba70ffc31ec..000000000000
--- a/arch/arm/plat-nomadik/include/plat/i2c.h
+++ /dev/null
@@ -1,39 +0,0 @@
-/*
- * Copyright (C) 2009 ST-Ericsson
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2, as
- * published by the Free Software Foundation.
- */
-#ifndef __PLAT_I2C_H
-#define __PLAT_I2C_H
-
-enum i2c_freq_mode {
-	I2C_FREQ_MODE_STANDARD,		/* up to 100 Kb/s */
-	I2C_FREQ_MODE_FAST,		/* up to 400 Kb/s */
-	I2C_FREQ_MODE_HIGH_SPEED,	/* up to 3.4 Mb/s */
-	I2C_FREQ_MODE_FAST_PLUS,	/* up to 1 Mb/s */
-};
-
-/**
- * struct nmk_i2c_controller - client specific controller configuration
- * @clk_freq:	clock frequency for the operation mode
- * @slsu:	Slave data setup time in ns.
- *		The needed setup time for three modes of operation
- *		are 250ns, 100ns and 10ns respectively thus leading
- *		to the values of 14, 6, 2 for a 48 MHz i2c clk
- * @tft:	Tx FIFO Threshold in bytes
- * @rft:	Rx FIFO Threshold in bytes
- * @timeout	Slave response timeout(ms)
- * @sm:		speed mode
- */
-struct nmk_i2c_controller {
-	unsigned long	clk_freq;
-	unsigned short	slsu;
-	unsigned char	tft;
-	unsigned char	rft;
-	int timeout;
-	enum i2c_freq_mode	sm;
-};
-
-#endif	/* __PLAT_I2C_H */
diff --git a/arch/arm/plat-pxa/Makefile b/arch/arm/plat-pxa/Makefile
index f302d048392d..af8e484001e5 100644
--- a/arch/arm/plat-pxa/Makefile
+++ b/arch/arm/plat-pxa/Makefile
@@ -8,5 +8,4 @@ obj-$(CONFIG_PXA3xx)		+= mfp.o
 obj-$(CONFIG_PXA95x)		+= mfp.o
 obj-$(CONFIG_ARCH_MMP)		+= mfp.o
 
-obj-$(CONFIG_HAVE_PWM)		+= pwm.o
 obj-$(CONFIG_PXA_SSP)		+= ssp.o
diff --git a/arch/arm/plat-pxa/pwm.c b/arch/arm/plat-pxa/pwm.c
deleted file mode 100644
index ef32686feef9..000000000000
--- a/arch/arm/plat-pxa/pwm.c
+++ /dev/null
@@ -1,304 +0,0 @@
-/*
- * linux/arch/arm/mach-pxa/pwm.c
- *
- * simple driver for PWM (Pulse Width Modulator) controller
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * 2008-02-13	initial version
- * 		eric miao <eric.miao@marvell.com>
- */
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/pwm.h>
-
-#include <asm/div64.h>
-
-#define HAS_SECONDARY_PWM	0x10
-#define PWM_ID_BASE(d)		((d) & 0xf)
-
-static const struct platform_device_id pwm_id_table[] = {
-	/*   PWM    has_secondary_pwm? */
-	{ "pxa25x-pwm", 0 },
-	{ "pxa27x-pwm", 0 | HAS_SECONDARY_PWM },
-	{ "pxa168-pwm", 1 },
-	{ "pxa910-pwm", 1 },
-	{ },
-};
-MODULE_DEVICE_TABLE(platform, pwm_id_table);
-
-/* PWM registers and bits definitions */
-#define PWMCR		(0x00)
-#define PWMDCR		(0x04)
-#define PWMPCR		(0x08)
-
-#define PWMCR_SD	(1 << 6)
-#define PWMDCR_FD	(1 << 10)
-
-struct pwm_device {
-	struct list_head	node;
-	struct pwm_device	*secondary;
-	struct platform_device	*pdev;
-
-	const char	*label;
-	struct clk	*clk;
-	int		clk_enabled;
-	void __iomem	*mmio_base;
-
-	unsigned int	use_count;
-	unsigned int	pwm_id;
-};
-
-/*
- * period_ns = 10^9 * (PRESCALE + 1) * (PV + 1) / PWM_CLK_RATE
- * duty_ns   = 10^9 * (PRESCALE + 1) * DC / PWM_CLK_RATE
- */
-int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns)
-{
-	unsigned long long c;
-	unsigned long period_cycles, prescale, pv, dc;
-
-	if (pwm == NULL || period_ns == 0 || duty_ns > period_ns)
-		return -EINVAL;
-
-	c = clk_get_rate(pwm->clk);
-	c = c * period_ns;
-	do_div(c, 1000000000);
-	period_cycles = c;
-
-	if (period_cycles < 1)
-		period_cycles = 1;
-	prescale = (period_cycles - 1) / 1024;
-	pv = period_cycles / (prescale + 1) - 1;
-
-	if (prescale > 63)
-		return -EINVAL;
-
-	if (duty_ns == period_ns)
-		dc = PWMDCR_FD;
-	else
-		dc = (pv + 1) * duty_ns / period_ns;
-
-	/* NOTE: the clock to PWM has to be enabled first
-	 * before writing to the registers
-	 */
-	clk_enable(pwm->clk);
-	__raw_writel(prescale, pwm->mmio_base + PWMCR);
-	__raw_writel(dc, pwm->mmio_base + PWMDCR);
-	__raw_writel(pv, pwm->mmio_base + PWMPCR);
-	clk_disable(pwm->clk);
-
-	return 0;
-}
-EXPORT_SYMBOL(pwm_config);
-
-int pwm_enable(struct pwm_device *pwm)
-{
-	int rc = 0;
-
-	if (!pwm->clk_enabled) {
-		rc = clk_enable(pwm->clk);
-		if (!rc)
-			pwm->clk_enabled = 1;
-	}
-	return rc;
-}
-EXPORT_SYMBOL(pwm_enable);
-
-void pwm_disable(struct pwm_device *pwm)
-{
-	if (pwm->clk_enabled) {
-		clk_disable(pwm->clk);
-		pwm->clk_enabled = 0;
-	}
-}
-EXPORT_SYMBOL(pwm_disable);
-
-static DEFINE_MUTEX(pwm_lock);
-static LIST_HEAD(pwm_list);
-
-struct pwm_device *pwm_request(int pwm_id, const char *label)
-{
-	struct pwm_device *pwm;
-	int found = 0;
-
-	mutex_lock(&pwm_lock);
-
-	list_for_each_entry(pwm, &pwm_list, node) {
-		if (pwm->pwm_id == pwm_id) {
-			found = 1;
-			break;
-		}
-	}
-
-	if (found) {
-		if (pwm->use_count == 0) {
-			pwm->use_count++;
-			pwm->label = label;
-		} else
-			pwm = ERR_PTR(-EBUSY);
-	} else
-		pwm = ERR_PTR(-ENOENT);
-
-	mutex_unlock(&pwm_lock);
-	return pwm;
-}
-EXPORT_SYMBOL(pwm_request);
-
-void pwm_free(struct pwm_device *pwm)
-{
-	mutex_lock(&pwm_lock);
-
-	if (pwm->use_count) {
-		pwm->use_count--;
-		pwm->label = NULL;
-	} else
-		pr_warning("PWM device already freed\n");
-
-	mutex_unlock(&pwm_lock);
-}
-EXPORT_SYMBOL(pwm_free);
-
-static inline void __add_pwm(struct pwm_device *pwm)
-{
-	mutex_lock(&pwm_lock);
-	list_add_tail(&pwm->node, &pwm_list);
-	mutex_unlock(&pwm_lock);
-}
-
-static int __devinit pwm_probe(struct platform_device *pdev)
-{
-	const struct platform_device_id *id = platform_get_device_id(pdev);
-	struct pwm_device *pwm, *secondary = NULL;
-	struct resource *r;
-	int ret = 0;
-
-	pwm = kzalloc(sizeof(struct pwm_device), GFP_KERNEL);
-	if (pwm == NULL) {
-		dev_err(&pdev->dev, "failed to allocate memory\n");
-		return -ENOMEM;
-	}
-
-	pwm->clk = clk_get(&pdev->dev, NULL);
-	if (IS_ERR(pwm->clk)) {
-		ret = PTR_ERR(pwm->clk);
-		goto err_free;
-	}
-	pwm->clk_enabled = 0;
-
-	pwm->use_count = 0;
-	pwm->pwm_id = PWM_ID_BASE(id->driver_data) + pdev->id;
-	pwm->pdev = pdev;
-
-	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (r == NULL) {
-		dev_err(&pdev->dev, "no memory resource defined\n");
-		ret = -ENODEV;
-		goto err_free_clk;
-	}
-
-	r = request_mem_region(r->start, resource_size(r), pdev->name);
-	if (r == NULL) {
-		dev_err(&pdev->dev, "failed to request memory resource\n");
-		ret = -EBUSY;
-		goto err_free_clk;
-	}
-
-	pwm->mmio_base = ioremap(r->start, resource_size(r));
-	if (pwm->mmio_base == NULL) {
-		dev_err(&pdev->dev, "failed to ioremap() registers\n");
-		ret = -ENODEV;
-		goto err_free_mem;
-	}
-
-	if (id->driver_data & HAS_SECONDARY_PWM) {
-		secondary = kzalloc(sizeof(struct pwm_device), GFP_KERNEL);
-		if (secondary == NULL) {
-			ret = -ENOMEM;
-			goto err_free_mem;
-		}
-
-		*secondary = *pwm;
-		pwm->secondary = secondary;
-
-		/* registers for the second PWM has offset of 0x10 */
-		secondary->mmio_base = pwm->mmio_base + 0x10;
-		secondary->pwm_id = pdev->id + 2;
-	}
-
-	__add_pwm(pwm);
-	if (secondary)
-		__add_pwm(secondary);
-
-	platform_set_drvdata(pdev, pwm);
-	return 0;
-
-err_free_mem:
-	release_mem_region(r->start, resource_size(r));
-err_free_clk:
-	clk_put(pwm->clk);
-err_free:
-	kfree(pwm);
-	return ret;
-}
-
-static int __devexit pwm_remove(struct platform_device *pdev)
-{
-	struct pwm_device *pwm;
-	struct resource *r;
-
-	pwm = platform_get_drvdata(pdev);
-	if (pwm == NULL)
-		return -ENODEV;
-
-	mutex_lock(&pwm_lock);
-
-	if (pwm->secondary) {
-		list_del(&pwm->secondary->node);
-		kfree(pwm->secondary);
-	}
-
-	list_del(&pwm->node);
-	mutex_unlock(&pwm_lock);
-
-	iounmap(pwm->mmio_base);
-
-	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	release_mem_region(r->start, resource_size(r));
-
-	clk_put(pwm->clk);
-	kfree(pwm);
-	return 0;
-}
-
-static struct platform_driver pwm_driver = {
-	.driver		= {
-		.name	= "pxa25x-pwm",
-		.owner	= THIS_MODULE,
-	},
-	.probe		= pwm_probe,
-	.remove		= __devexit_p(pwm_remove),
-	.id_table	= pwm_id_table,
-};
-
-static int __init pwm_init(void)
-{
-	return platform_driver_register(&pwm_driver);
-}
-arch_initcall(pwm_init);
-
-static void __exit pwm_exit(void)
-{
-	platform_driver_unregister(&pwm_driver);
-}
-module_exit(pwm_exit);
-
-MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/plat-samsung/Makefile b/arch/arm/plat-samsung/Makefile
index b78717496677..9e40e8d00740 100644
--- a/arch/arm/plat-samsung/Makefile
+++ b/arch/arm/plat-samsung/Makefile
@@ -59,7 +59,3 @@ obj-$(CONFIG_SAMSUNG_WAKEMASK)	+= wakeup-mask.o
 
 obj-$(CONFIG_S5P_PM)		+= s5p-pm.o s5p-irq-pm.o
 obj-$(CONFIG_S5P_SLEEP)		+= s5p-sleep.o
-
-# PWM support
-
-obj-$(CONFIG_HAVE_PWM)		+= pwm.o
diff --git a/arch/arm/plat-samsung/pwm.c b/arch/arm/plat-samsung/pwm.c
deleted file mode 100644
index d3583050fb05..000000000000
--- a/arch/arm/plat-samsung/pwm.c
+++ /dev/null
@@ -1,416 +0,0 @@
-/* arch/arm/plat-s3c/pwm.c
- *
- * Copyright (c) 2007 Ben Dooks
- * Copyright (c) 2008 Simtec Electronics
- *	Ben Dooks <ben@simtec.co.uk>, <ben-linux@fluff.org>
- *
- * S3C series PWM device core
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License.
-*/
-
-#include <linux/export.h>
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-#include <linux/slab.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/pwm.h>
-
-#include <mach/map.h>
-
-#include <plat/regs-timer.h>
-
-struct pwm_device {
-	struct list_head	 list;
-	struct platform_device	*pdev;
-
-	struct clk		*clk_div;
-	struct clk		*clk;
-	const char		*label;
-
-	unsigned int		 period_ns;
-	unsigned int		 duty_ns;
-
-	unsigned char		 tcon_base;
-	unsigned char		 use_count;
-	unsigned char		 pwm_id;
-};
-
-#define pwm_dbg(_pwm, msg...) dev_dbg(&(_pwm)->pdev->dev, msg)
-
-static struct clk *clk_scaler[2];
-
-static inline int pwm_is_tdiv(struct pwm_device *pwm)
-{
-	return clk_get_parent(pwm->clk) == pwm->clk_div;
-}
-
-static DEFINE_MUTEX(pwm_lock);
-static LIST_HEAD(pwm_list);
-
-struct pwm_device *pwm_request(int pwm_id, const char *label)
-{
-	struct pwm_device *pwm;
-	int found = 0;
-
-	mutex_lock(&pwm_lock);
-
-	list_for_each_entry(pwm, &pwm_list, list) {
-		if (pwm->pwm_id == pwm_id) {
-			found = 1;
-			break;
-		}
-	}
-
-	if (found) {
-		if (pwm->use_count == 0) {
-			pwm->use_count = 1;
-			pwm->label = label;
-		} else
-			pwm = ERR_PTR(-EBUSY);
-	} else
-		pwm = ERR_PTR(-ENOENT);
-
-	mutex_unlock(&pwm_lock);
-	return pwm;
-}
-
-EXPORT_SYMBOL(pwm_request);
-
-
-void pwm_free(struct pwm_device *pwm)
-{
-	mutex_lock(&pwm_lock);
-
-	if (pwm->use_count) {
-		pwm->use_count--;
-		pwm->label = NULL;
-	} else
-		printk(KERN_ERR "PWM%d device already freed\n", pwm->pwm_id);
-
-	mutex_unlock(&pwm_lock);
-}
-
-EXPORT_SYMBOL(pwm_free);
-
-#define pwm_tcon_start(pwm) (1 << (pwm->tcon_base + 0))
-#define pwm_tcon_invert(pwm) (1 << (pwm->tcon_base + 2))
-#define pwm_tcon_autoreload(pwm) (1 << (pwm->tcon_base + 3))
-#define pwm_tcon_manulupdate(pwm) (1 << (pwm->tcon_base + 1))
-
-int pwm_enable(struct pwm_device *pwm)
-{
-	unsigned long flags;
-	unsigned long tcon;
-
-	local_irq_save(flags);
-
-	tcon = __raw_readl(S3C2410_TCON);
-	tcon |= pwm_tcon_start(pwm);
-	__raw_writel(tcon, S3C2410_TCON);
-
-	local_irq_restore(flags);
-
-	return 0;
-}
-
-EXPORT_SYMBOL(pwm_enable);
-
-void pwm_disable(struct pwm_device *pwm)
-{
-	unsigned long flags;
-	unsigned long tcon;
-
-	local_irq_save(flags);
-
-	tcon = __raw_readl(S3C2410_TCON);
-	tcon &= ~pwm_tcon_start(pwm);
-	__raw_writel(tcon, S3C2410_TCON);
-
-	local_irq_restore(flags);
-}
-
-EXPORT_SYMBOL(pwm_disable);
-
-static unsigned long pwm_calc_tin(struct pwm_device *pwm, unsigned long freq)
-{
-	unsigned long tin_parent_rate;
-	unsigned int div;
-
-	tin_parent_rate = clk_get_rate(clk_get_parent(pwm->clk_div));
-	pwm_dbg(pwm, "tin parent at %lu\n", tin_parent_rate);
-
-	for (div = 2; div <= 16; div *= 2) {
-		if ((tin_parent_rate / (div << 16)) < freq)
-			return tin_parent_rate / div;
-	}
-
-	return tin_parent_rate / 16;
-}
-
-#define NS_IN_HZ (1000000000UL)
-
-int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns)
-{
-	unsigned long tin_rate;
-	unsigned long tin_ns;
-	unsigned long period;
-	unsigned long flags;
-	unsigned long tcon;
-	unsigned long tcnt;
-	long tcmp;
-
-	/* We currently avoid using 64bit arithmetic by using the
-	 * fact that anything faster than 1Hz is easily representable
-	 * by 32bits. */
-
-	if (period_ns > NS_IN_HZ || duty_ns > NS_IN_HZ)
-		return -ERANGE;
-
-	if (duty_ns > period_ns)
-		return -EINVAL;
-
-	if (period_ns == pwm->period_ns &&
-	    duty_ns == pwm->duty_ns)
-		return 0;
-
-	/* The TCMP and TCNT can be read without a lock, they're not
-	 * shared between the timers. */
-
-	tcmp = __raw_readl(S3C2410_TCMPB(pwm->pwm_id));
-	tcnt = __raw_readl(S3C2410_TCNTB(pwm->pwm_id));
-
-	period = NS_IN_HZ / period_ns;
-
-	pwm_dbg(pwm, "duty_ns=%d, period_ns=%d (%lu)\n",
-		duty_ns, period_ns, period);
-
-	/* Check to see if we are changing the clock rate of the PWM */
-
-	if (pwm->period_ns != period_ns) {
-		if (pwm_is_tdiv(pwm)) {
-			tin_rate = pwm_calc_tin(pwm, period);
-			clk_set_rate(pwm->clk_div, tin_rate);
-		} else
-			tin_rate = clk_get_rate(pwm->clk);
-
-		pwm->period_ns = period_ns;
-
-		pwm_dbg(pwm, "tin_rate=%lu\n", tin_rate);
-
-		tin_ns = NS_IN_HZ / tin_rate;
-		tcnt = period_ns / tin_ns;
-	} else
-		tin_ns = NS_IN_HZ / clk_get_rate(pwm->clk);
-
-	/* Note, counters count down */
-
-	tcmp = duty_ns / tin_ns;
-	tcmp = tcnt - tcmp;
-	/* the pwm hw only checks the compare register after a decrement,
-	   so the pin never toggles if tcmp = tcnt */
-	if (tcmp == tcnt)
-		tcmp--;
-
-	pwm_dbg(pwm, "tin_ns=%lu, tcmp=%ld/%lu\n", tin_ns, tcmp, tcnt);
-
-	if (tcmp < 0)
-		tcmp = 0;
-
-	/* Update the PWM register block. */
-
-	local_irq_save(flags);
-
-	__raw_writel(tcmp, S3C2410_TCMPB(pwm->pwm_id));
-	__raw_writel(tcnt, S3C2410_TCNTB(pwm->pwm_id));
-
-	tcon = __raw_readl(S3C2410_TCON);
-	tcon |= pwm_tcon_manulupdate(pwm);
-	tcon |= pwm_tcon_autoreload(pwm);
-	__raw_writel(tcon, S3C2410_TCON);
-
-	tcon &= ~pwm_tcon_manulupdate(pwm);
-	__raw_writel(tcon, S3C2410_TCON);
-
-	local_irq_restore(flags);
-
-	return 0;
-}
-
-EXPORT_SYMBOL(pwm_config);
-
-static int pwm_register(struct pwm_device *pwm)
-{
-	pwm->duty_ns = -1;
-	pwm->period_ns = -1;
-
-	mutex_lock(&pwm_lock);
-	list_add_tail(&pwm->list, &pwm_list);
-	mutex_unlock(&pwm_lock);
-
-	return 0;
-}
-
-static int s3c_pwm_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct pwm_device *pwm;
-	unsigned long flags;
-	unsigned long tcon;
-	unsigned int id = pdev->id;
-	int ret;
-
-	if (id == 4) {
-		dev_err(dev, "TIMER4 is currently not supported\n");
-		return -ENXIO;
-	}
-
-	pwm = kzalloc(sizeof(struct pwm_device), GFP_KERNEL);
-	if (pwm == NULL) {
-		dev_err(dev, "failed to allocate pwm_device\n");
-		return -ENOMEM;
-	}
-
-	pwm->pdev = pdev;
-	pwm->pwm_id = id;
-
-	/* calculate base of control bits in TCON */
-	pwm->tcon_base = id == 0 ? 0 : (id * 4) + 4;
-
-	pwm->clk = clk_get(dev, "pwm-tin");
-	if (IS_ERR(pwm->clk)) {
-		dev_err(dev, "failed to get pwm tin clk\n");
-		ret = PTR_ERR(pwm->clk);
-		goto err_alloc;
-	}
-
-	pwm->clk_div = clk_get(dev, "pwm-tdiv");
-	if (IS_ERR(pwm->clk_div)) {
-		dev_err(dev, "failed to get pwm tdiv clk\n");
-		ret = PTR_ERR(pwm->clk_div);
-		goto err_clk_tin;
-	}
-
-	clk_enable(pwm->clk);
-	clk_enable(pwm->clk_div);
-
-	local_irq_save(flags);
-
-	tcon = __raw_readl(S3C2410_TCON);
-	tcon |= pwm_tcon_invert(pwm);
-	__raw_writel(tcon, S3C2410_TCON);
-
-	local_irq_restore(flags);
-
-
-	ret = pwm_register(pwm);
-	if (ret) {
-		dev_err(dev, "failed to register pwm\n");
-		goto err_clk_tdiv;
-	}
-
-	pwm_dbg(pwm, "config bits %02x\n",
-		(__raw_readl(S3C2410_TCON) >> pwm->tcon_base) & 0x0f);
-
-	dev_info(dev, "tin at %lu, tdiv at %lu, tin=%sclk, base %d\n",
-		 clk_get_rate(pwm->clk),
-		 clk_get_rate(pwm->clk_div),
-		 pwm_is_tdiv(pwm) ? "div" : "ext", pwm->tcon_base);
-
-	platform_set_drvdata(pdev, pwm);
-	return 0;
-
- err_clk_tdiv:
-	clk_disable(pwm->clk_div);
-	clk_disable(pwm->clk);
-	clk_put(pwm->clk_div);
-
- err_clk_tin:
-	clk_put(pwm->clk);
-
- err_alloc:
-	kfree(pwm);
-	return ret;
-}
-
-static int __devexit s3c_pwm_remove(struct platform_device *pdev)
-{
-	struct pwm_device *pwm = platform_get_drvdata(pdev);
-
-	clk_disable(pwm->clk_div);
-	clk_disable(pwm->clk);
-	clk_put(pwm->clk_div);
-	clk_put(pwm->clk);
-	kfree(pwm);
-
-	return 0;
-}
-
-#ifdef CONFIG_PM
-static int s3c_pwm_suspend(struct platform_device *pdev, pm_message_t state)
-{
-	struct pwm_device *pwm = platform_get_drvdata(pdev);
-
-	/* No one preserve these values during suspend so reset them
-	 * Otherwise driver leaves PWM unconfigured if same values
-	 * passed to pwm_config
-	 */
-	pwm->period_ns = 0;
-	pwm->duty_ns = 0;
-
-	return 0;
-}
-
-static int s3c_pwm_resume(struct platform_device *pdev)
-{
-	struct pwm_device *pwm = platform_get_drvdata(pdev);
-	unsigned long tcon;
-
-	/* Restore invertion */
-	tcon = __raw_readl(S3C2410_TCON);
-	tcon |= pwm_tcon_invert(pwm);
-	__raw_writel(tcon, S3C2410_TCON);
-
-	return 0;
-}
-
-#else
-#define s3c_pwm_suspend NULL
-#define s3c_pwm_resume NULL
-#endif
-
-static struct platform_driver s3c_pwm_driver = {
-	.driver		= {
-		.name	= "s3c24xx-pwm",
-		.owner	= THIS_MODULE,
-	},
-	.probe		= s3c_pwm_probe,
-	.remove		= __devexit_p(s3c_pwm_remove),
-	.suspend	= s3c_pwm_suspend,
-	.resume		= s3c_pwm_resume,
-};
-
-static int __init pwm_init(void)
-{
-	int ret;
-
-	clk_scaler[0] = clk_get(NULL, "pwm-scaler0");
-	clk_scaler[1] = clk_get(NULL, "pwm-scaler1");
-
-	if (IS_ERR(clk_scaler[0]) || IS_ERR(clk_scaler[1])) {
-		printk(KERN_ERR "%s: failed to get scaler clocks\n", __func__);
-		return -EINVAL;
-	}
-
-	ret = platform_driver_register(&s3c_pwm_driver);
-	if (ret)
-		printk(KERN_ERR "%s: failed to add pwm driver\n", __func__);
-
-	return ret;
-}
-
-arch_initcall(pwm_init);
diff --git a/arch/arm/plat-spear/include/plat/keyboard.h b/arch/arm/plat-spear/include/plat/keyboard.h
index 0562f134621d..9248e3a7e333 100644
--- a/arch/arm/plat-spear/include/plat/keyboard.h
+++ b/arch/arm/plat-spear/include/plat/keyboard.h
@@ -149,6 +149,7 @@ int _name[] = { \
  * keymap: pointer to keymap data (table and size)
  * rep: enables key autorepeat
  * mode: choose keyboard support(9x9, 6x6, 2x2)
+ * suspended_rate: rate at which keyboard would operate in suspended mode
  *
  * This structure is supposed to be used by platform code to supply
  * keymaps to drivers that implement keyboards.
@@ -157,6 +158,7 @@ struct kbd_platform_data {
 	const struct matrix_keymap_data *keymap;
 	bool rep;
 	unsigned int mode;
+	unsigned int suspended_rate;
 };
 
 #endif /* __PLAT_KEYBOARD_H */
diff --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c
index 49c7db48c7f1..d7c5c171f5aa 100644
--- a/arch/arm/plat-versatile/platsmp.c
+++ b/arch/arm/plat-versatile/platsmp.c
@@ -85,7 +85,7 @@ int __cpuinit boot_secondary(unsigned int cpu, struct task_struct *idle)
 	 * the boot monitor to read the system wide flags register,
 	 * and branch to the address found there.
 	 */
-	gic_raise_softirq(cpumask_of(cpu), 1);
+	gic_raise_softirq(cpumask_of(cpu), 0);
 
 	timeout = jiffies + (1 * HZ);
 	while (time_before(jiffies, timeout)) {
diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S
index 2d30c7f6edd3..d50f0e486cf2 100644
--- a/arch/arm/vfp/vfphw.S
+++ b/arch/arm/vfp/vfphw.S
@@ -16,6 +16,7 @@
  */
 #include <asm/thread_info.h>
 #include <asm/vfpmacros.h>
+#include <linux/kern_levels.h>
 #include "../kernel/entry-header.S"
 
 	.macro	DBGSTR, str
@@ -24,7 +25,7 @@
 	add	r0, pc, #4
 	bl	printk
 	b	1f
-	.asciz  "<7>VFP: \str\n"
+	.asciz  KERN_DEBUG "VFP: \str\n"
 	.balign 4
 1:	ldmfd	sp!, {r0-r3, ip, lr}
 #endif
@@ -37,7 +38,7 @@
 	add	r0, pc, #4
 	bl	printk
 	b	1f
-	.asciz  "<7>VFP: \str\n"
+	.asciz  KERN_DEBUG "VFP: \str\n"
 	.balign 4
 1:	ldmfd	sp!, {r0-r3, ip, lr}
 #endif
@@ -52,7 +53,7 @@
 	add	r0, pc, #4
 	bl	printk
 	b	1f
-	.asciz  "<7>VFP: \str\n"
+	.asciz  KERN_DEBUG "VFP: \str\n"
 	.balign 4
 1:	ldmfd	sp!, {r0-r3, ip, lr}
 #endif
diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index 71d38c76726c..5ade51c8a87f 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -12,6 +12,7 @@ config AVR32
 	select HARDIRQS_SW_RESEND
 	select GENERIC_IRQ_SHOW
 	select ARCH_HAVE_CUSTOM_GPIO_H
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_CLOCKEVENTS
 	help
diff --git a/arch/avr32/boards/atstk1000/atstk1002.c b/arch/avr32/boards/atstk1000/atstk1002.c
index dc5263321480..6c80aba7bf96 100644
--- a/arch/avr32/boards/atstk1000/atstk1002.c
+++ b/arch/avr32/boards/atstk1000/atstk1002.c
@@ -97,7 +97,7 @@ static struct atmel_nand_data atstk1006_nand_data __initdata = {
 	.enable_pin	= GPIO_PIN_PB(29),
 	.ecc_mode	= NAND_ECC_SOFT,
 	.parts		= nand_partitions,
-	.num_parts	= ARRAY_SIZE(num_partitions),
+	.num_parts	= ARRAY_SIZE(nand_partitions),
 };
 #endif
 
diff --git a/arch/avr32/include/asm/kmap_types.h b/arch/avr32/include/asm/kmap_types.h
index b7f5c6870107..479330b89796 100644
--- a/arch/avr32/include/asm/kmap_types.h
+++ b/arch/avr32/include/asm/kmap_types.h
@@ -2,29 +2,9 @@
 #define __ASM_AVR32_KMAP_TYPES_H
 
 #ifdef CONFIG_DEBUG_HIGHMEM
-# define D(n) __KM_FENCE_##n ,
+# define KM_TYPE_NR 29
 #else
-# define D(n)
+# define KM_TYPE_NR 14
 #endif
 
-enum km_type {
-D(0)	KM_BOUNCE_READ,
-D(1)	KM_SKB_SUNRPC_DATA,
-D(2)	KM_SKB_DATA_SOFTIRQ,
-D(3)	KM_USER0,
-D(4)	KM_USER1,
-D(5)	KM_BIO_SRC_IRQ,
-D(6)	KM_BIO_DST_IRQ,
-D(7)	KM_PTE0,
-D(8)	KM_PTE1,
-D(9)	KM_PTE2,
-D(10)	KM_IRQ0,
-D(11)	KM_IRQ1,
-D(12)	KM_SOFTIRQ0,
-D(13)	KM_SOFTIRQ1,
-D(14)	KM_TYPE_NR
-};
-
-#undef D
-
 #endif /* __ASM_AVR32_KMAP_TYPES_H */
diff --git a/arch/avr32/include/asm/unistd.h b/arch/avr32/include/asm/unistd.h
index f714544e5560..1358e366f4be 100644
--- a/arch/avr32/include/asm/unistd.h
+++ b/arch/avr32/include/asm/unistd.h
@@ -318,7 +318,6 @@
 /* SMP stuff */
 #define __IGNORE_getcpu
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_ALARM
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/avr32/mm/fault.c b/arch/avr32/mm/fault.c
index f7040a1e399f..b92e60958617 100644
--- a/arch/avr32/mm/fault.c
+++ b/arch/avr32/mm/fault.c
@@ -61,10 +61,10 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
 	const struct exception_table_entry *fixup;
 	unsigned long address;
 	unsigned long page;
-	int writeaccess;
 	long signr;
 	int code;
 	int fault;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	if (notify_page_fault(regs, ecr))
 		return;
@@ -86,6 +86,7 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
 
 	local_irq_enable();
 
+retry:
 	down_read(&mm->mmap_sem);
 
 	vma = find_vma(mm, address);
@@ -104,7 +105,6 @@ asmlinkage void do_page_fault(unsigned long ecr, struct pt_regs *regs)
 	 */
 good_area:
 	code = SEGV_ACCERR;
-	writeaccess = 0;
 
 	switch (ecr) {
 	case ECR_PROTECTION_X:
@@ -121,7 +121,7 @@ good_area:
 	case ECR_TLB_MISS_W:
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
-		writeaccess = 1;
+		flags |= FAULT_FLAG_WRITE;
 		break;
 	default:
 		panic("Unhandled case %lu in do_page_fault!", ecr);
@@ -132,7 +132,11 @@ good_area:
 	 * sure we exit gracefully rather than endlessly redo the
 	 * fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, writeaccess ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, address, flags);
+
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return;
+
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -140,10 +144,23 @@ good_area:
 			goto do_sigbus;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR)
-		tsk->maj_flt++;
-	else
-		tsk->min_flt++;
+
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR)
+			tsk->maj_flt++;
+		else
+			tsk->min_flt++;
+		if (fault & VM_FAULT_RETRY) {
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+			/*
+			 * No need to up_read(&mm->mmap_sem) as we would have
+			 * already released it in __lock_page_or_retry() in
+			 * mm/filemap.c.
+			 */
+			goto retry;
+		}
+	}
 
 	up_read(&mm->mmap_sem);
 	return;
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index 9b765107e15c..f34861920634 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -33,6 +33,7 @@ config BLACKFIN
 	select HAVE_PERF_EVENTS
 	select ARCH_HAVE_CUSTOM_GPIO_H
 	select ARCH_WANT_OPTIONAL_GPIOLIB
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_ATOMIC64
 	select GENERIC_IRQ_PROBE
@@ -1002,16 +1003,6 @@ config BFIN_GPTIMERS
 	  To compile this driver as a module, choose M here: the module
 	  will be called gptimers.
 
-config HAVE_PWM
-	tristate "Enable PWM API support"
-	depends on BFIN_GPTIMERS
-	help
-	  Enable support for the Pulse Width Modulation framework (as
-	  found in linux/pwm.h).
-
-	  To compile this driver as a module, choose M here: the module
-	  will be called pwm.
-
 choice
 	prompt "Uncached DMA region"
 	default DMA_UNCACHED_1M
diff --git a/arch/blackfin/include/asm/unistd.h b/arch/blackfin/include/asm/unistd.h
index 3287222cba34..5b2a0748d7d3 100644
--- a/arch/blackfin/include/asm/unistd.h
+++ b/arch/blackfin/include/asm/unistd.h
@@ -434,7 +434,6 @@
 #define __IGNORE_getcpu
 
 #ifdef __KERNEL__
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_ALARM
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/blackfin/kernel/Makefile b/arch/blackfin/kernel/Makefile
index 08e6625106be..735f24e07425 100644
--- a/arch/blackfin/kernel/Makefile
+++ b/arch/blackfin/kernel/Makefile
@@ -21,7 +21,6 @@ obj-$(CONFIG_FUNCTION_TRACER)        += ftrace-entry.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)  += ftrace.o
 CFLAGS_REMOVE_ftrace.o = -pg
 
-obj-$(CONFIG_HAVE_PWM)               += pwm.o
 obj-$(CONFIG_IPIPE)                  += ipipe.o
 obj-$(CONFIG_BFIN_GPTIMERS)          += gptimers.o
 obj-$(CONFIG_CPLB_INFO)              += cplbinfo.o
diff --git a/arch/blackfin/kernel/pwm.c b/arch/blackfin/kernel/pwm.c
deleted file mode 100644
index 33f5942733bd..000000000000
--- a/arch/blackfin/kernel/pwm.c
+++ /dev/null
@@ -1,100 +0,0 @@
-/*
- * Blackfin Pulse Width Modulation (PWM) core
- *
- * Copyright (c) 2011 Analog Devices Inc.
- *
- * Licensed under the GPL-2 or later.
- */
-
-#include <linux/module.h>
-#include <linux/pwm.h>
-#include <linux/slab.h>
-
-#include <asm/gptimers.h>
-#include <asm/portmux.h>
-
-struct pwm_device {
-	unsigned id;
-	unsigned short pin;
-};
-
-static const unsigned short pwm_to_gptimer_per[] = {
-	P_TMR0, P_TMR1, P_TMR2, P_TMR3, P_TMR4, P_TMR5,
-	P_TMR6, P_TMR7, P_TMR8, P_TMR9, P_TMR10, P_TMR11,
-};
-
-struct pwm_device *pwm_request(int pwm_id, const char *label)
-{
-	struct pwm_device *pwm;
-	int ret;
-
-	/* XXX: pwm_id really should be unsigned */
-	if (pwm_id < 0)
-		return NULL;
-
-	pwm = kzalloc(sizeof(*pwm), GFP_KERNEL);
-	if (!pwm)
-		return pwm;
-
-	pwm->id = pwm_id;
-	if (pwm->id >= ARRAY_SIZE(pwm_to_gptimer_per))
-		goto err;
-
-	pwm->pin = pwm_to_gptimer_per[pwm->id];
-	ret = peripheral_request(pwm->pin, label);
-	if (ret)
-		goto err;
-
-	return pwm;
- err:
-	kfree(pwm);
-	return NULL;
-}
-EXPORT_SYMBOL(pwm_request);
-
-void pwm_free(struct pwm_device *pwm)
-{
-	peripheral_free(pwm->pin);
-	kfree(pwm);
-}
-EXPORT_SYMBOL(pwm_free);
-
-int pwm_config(struct pwm_device *pwm, int duty_ns, int period_ns)
-{
-	unsigned long period, duty;
-	unsigned long long val;
-
-	if (duty_ns < 0 || duty_ns > period_ns)
-		return -EINVAL;
-
-	val = (unsigned long long)get_sclk() * period_ns;
-	do_div(val, NSEC_PER_SEC);
-	period = val;
-
-	val = (unsigned long long)period * duty_ns;
-	do_div(val, period_ns);
-	duty = period - val;
-
-	if (duty >= period)
-		duty = period - 1;
-
-	set_gptimer_config(pwm->id, TIMER_MODE_PWM | TIMER_PERIOD_CNT);
-	set_gptimer_pwidth(pwm->id, duty);
-	set_gptimer_period(pwm->id, period);
-
-	return 0;
-}
-EXPORT_SYMBOL(pwm_config);
-
-int pwm_enable(struct pwm_device *pwm)
-{
-	enable_gptimer(pwm->id);
-	return 0;
-}
-EXPORT_SYMBOL(pwm_enable);
-
-void pwm_disable(struct pwm_device *pwm)
-{
-	disable_gptimer(pwm->id);
-}
-EXPORT_SYMBOL(pwm_disable);
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index bb344650a14f..e92215428a37 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -42,6 +42,7 @@ config CRIS
 	select HAVE_IDE
 	select GENERIC_ATOMIC64
 	select HAVE_GENERIC_HARDIRQS
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IOMAP
 	select GENERIC_SMP_IDLE_THREAD if ETRAX_ARCH_V32
diff --git a/arch/cris/include/asm/unistd.h b/arch/cris/include/asm/unistd.h
index f921b8b0f97e..51873a446f87 100644
--- a/arch/cris/include/asm/unistd.h
+++ b/arch/cris/include/asm/unistd.h
@@ -347,7 +347,6 @@
 
 #include <arch/unistd.h>
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
 #define __ARCH_WANT_STAT64
diff --git a/arch/frv/Kconfig b/arch/frv/Kconfig
index a685910d2d5c..971c0a19facb 100644
--- a/arch/frv/Kconfig
+++ b/arch/frv/Kconfig
@@ -9,6 +9,7 @@ config FRV
 	select GENERIC_IRQ_SHOW
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_CPU_DEVICES
+	select ARCH_WANT_IPC_PARSE_VERSION
 
 config ZONE_DMA
 	bool
diff --git a/arch/frv/include/asm/cpumask.h b/arch/frv/include/asm/cpumask.h
deleted file mode 100644
index d999c20c84d2..000000000000
--- a/arch/frv/include/asm/cpumask.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_CPUMASK_H
-#define _ASM_CPUMASK_H
-
-#include <asm-generic/cpumask.h>
-
-#endif /* _ASM_CPUMASK_H */
diff --git a/arch/frv/include/asm/highmem.h b/arch/frv/include/asm/highmem.h
index 716956a5317b..b3adc93611f3 100644
--- a/arch/frv/include/asm/highmem.h
+++ b/arch/frv/include/asm/highmem.h
@@ -76,15 +76,16 @@ extern struct page *kmap_atomic_to_page(void *ptr);
 
 #ifndef __ASSEMBLY__
 
-#define __kmap_atomic_primary(type, paddr, ampr)						\
+#define __kmap_atomic_primary(cached, paddr, ampr)						\
 ({												\
 	unsigned long damlr, dampr;								\
 												\
 	dampr = paddr | xAMPRx_L | xAMPRx_M | xAMPRx_S | xAMPRx_SS_16Kb | xAMPRx_V;		\
 												\
-	if (type != __KM_CACHE)									\
+	if (!cached)										\
 		asm volatile("movgs %0,dampr"#ampr :: "r"(dampr) : "memory");			\
 	else											\
+		/* cache flush page attachment point */						\
 		asm volatile("movgs %0,iampr"#ampr"\n"						\
 			     "movgs %0,dampr"#ampr"\n"						\
 			     :: "r"(dampr) : "memory"						\
@@ -112,29 +113,20 @@ extern struct page *kmap_atomic_to_page(void *ptr);
 	(void *) damlr;										  \
 })
 
-static inline void *kmap_atomic_primary(struct page *page, enum km_type type)
+static inline void *kmap_atomic_primary(struct page *page)
 {
 	unsigned long paddr;
 
 	pagefault_disable();
 	paddr = page_to_phys(page);
 
-	switch (type) {
-        case 0:		return __kmap_atomic_primary(0, paddr, 2);
-        case 1:		return __kmap_atomic_primary(1, paddr, 3);
-        case 2:		return __kmap_atomic_primary(2, paddr, 4);
-        case 3:		return __kmap_atomic_primary(3, paddr, 5);
-
-	default:
-		BUG();
-		return NULL;
-	}
+        return __kmap_atomic_primary(1, paddr, 2);
 }
 
-#define __kunmap_atomic_primary(type, ampr)				\
+#define __kunmap_atomic_primary(cached, ampr)				\
 do {									\
 	asm volatile("movgs gr0,dampr"#ampr"\n" ::: "memory");		\
-	if (type == __KM_CACHE)						\
+	if (cached)							\
 		asm volatile("movgs gr0,iampr"#ampr"\n" ::: "memory");	\
 } while(0)
 
@@ -143,17 +135,9 @@ do {									\
 	asm volatile("tlbpr %0,gr0,#4,#1" : : "r"(vaddr) : "memory");	\
 } while(0)
 
-static inline void kunmap_atomic_primary(void *kvaddr, enum km_type type)
+static inline void kunmap_atomic_primary(void *kvaddr)
 {
-	switch (type) {
-        case 0:		__kunmap_atomic_primary(0, 2);	break;
-        case 1:		__kunmap_atomic_primary(1, 3);	break;
-        case 2:		__kunmap_atomic_primary(2, 4);	break;
-        case 3:		__kunmap_atomic_primary(3, 5);	break;
-
-	default:
-		BUG();
-	}
+        __kunmap_atomic_primary(1, 2);
 	pagefault_enable();
 }
 
diff --git a/arch/frv/include/asm/kmap_types.h b/arch/frv/include/asm/kmap_types.h
index f8e16b2a5804..43901f220963 100644
--- a/arch/frv/include/asm/kmap_types.h
+++ b/arch/frv/include/asm/kmap_types.h
@@ -2,28 +2,6 @@
 #ifndef _ASM_KMAP_TYPES_H
 #define _ASM_KMAP_TYPES_H
 
-enum km_type {
-	/* arch specific kmaps - change the numbers attached to these at your peril */
-	__KM_CACHE,		/* cache flush page attachment point */
-	__KM_PGD,		/* current page directory */
-	__KM_ITLB_PTD,		/* current instruction TLB miss page table lookup */
-	__KM_DTLB_PTD,		/* current data TLB miss page table lookup */
-
-	/* general kmaps */
-        KM_BOUNCE_READ,
-        KM_SKB_SUNRPC_DATA,
-        KM_SKB_DATA_SOFTIRQ,
-        KM_USER0,
-        KM_USER1,
-	KM_BIO_SRC_IRQ,
-	KM_BIO_DST_IRQ,
-	KM_PTE0,
-	KM_PTE1,
-	KM_IRQ0,
-	KM_IRQ1,
-	KM_SOFTIRQ0,
-	KM_SOFTIRQ1,
-	KM_TYPE_NR
-};
+#define KM_TYPE_NR 17
 
 #endif
diff --git a/arch/frv/include/asm/unistd.h b/arch/frv/include/asm/unistd.h
index a569dff7cd59..67f23a311db6 100644
--- a/arch/frv/include/asm/unistd.h
+++ b/arch/frv/include/asm/unistd.h
@@ -349,7 +349,6 @@
 
 #define NR_syscalls 338
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
 /* #define __ARCH_WANT_OLD_READDIR */
 #define __ARCH_WANT_OLD_STAT
 #define __ARCH_WANT_STAT64
diff --git a/arch/frv/kernel/kernel_thread.S b/arch/frv/kernel/kernel_thread.S
index 4531c830d20b..f0e52943f923 100644
--- a/arch/frv/kernel/kernel_thread.S
+++ b/arch/frv/kernel/kernel_thread.S
@@ -10,10 +10,10 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/kern_levels.h>
 #include <asm/unistd.h>
 
 #define CLONE_VM	0x00000100	/* set if VM shared between processes */
-#define	KERN_ERR	"<3>"
 
 	.section .rodata
 kernel_thread_emsg:
diff --git a/arch/frv/mb93090-mb00/pci-dma.c b/arch/frv/mb93090-mb00/pci-dma.c
index 4f8d8bcdc7de..82478979ac9a 100644
--- a/arch/frv/mb93090-mb00/pci-dma.c
+++ b/arch/frv/mb93090-mb00/pci-dma.c
@@ -62,14 +62,14 @@ int dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	dampr2 = __get_DAMPR(2);
 
 	for (i = 0; i < nents; i++) {
-		vaddr = kmap_atomic_primary(sg_page(&sg[i]), __KM_CACHE);
+		vaddr = kmap_atomic_primary(sg_page(&sg[i]));
 
 		frv_dcache_writeback((unsigned long) vaddr,
 				     (unsigned long) vaddr + PAGE_SIZE);
 
 	}
 
-	kunmap_atomic_primary(vaddr, __KM_CACHE);
+	kunmap_atomic_primary(vaddr);
 	if (dampr2) {
 		__set_DAMPR(2, dampr2);
 		__set_IAMPR(2, dampr2);
diff --git a/arch/frv/mm/cache-page.c b/arch/frv/mm/cache-page.c
index b24ade27a0f0..8e09dae0ec3f 100644
--- a/arch/frv/mm/cache-page.c
+++ b/arch/frv/mm/cache-page.c
@@ -26,11 +26,11 @@ void flush_dcache_page(struct page *page)
 
 	dampr2 = __get_DAMPR(2);
 
-	vaddr = kmap_atomic_primary(page, __KM_CACHE);
+	vaddr = kmap_atomic_primary(page);
 
 	frv_dcache_writeback((unsigned long) vaddr, (unsigned long) vaddr + PAGE_SIZE);
 
-	kunmap_atomic_primary(vaddr, __KM_CACHE);
+	kunmap_atomic_primary(vaddr);
 
 	if (dampr2) {
 		__set_DAMPR(2, dampr2);
@@ -54,12 +54,12 @@ void flush_icache_user_range(struct vm_area_struct *vma, struct page *page,
 
 	dampr2 = __get_DAMPR(2);
 
-	vaddr = kmap_atomic_primary(page, __KM_CACHE);
+	vaddr = kmap_atomic_primary(page);
 
 	start = (start & ~PAGE_MASK) | (unsigned long) vaddr;
 	frv_cache_wback_inv(start, start + len);
 
-	kunmap_atomic_primary(vaddr, __KM_CACHE);
+	kunmap_atomic_primary(vaddr);
 
 	if (dampr2) {
 		__set_DAMPR(2, dampr2);
diff --git a/arch/frv/mm/highmem.c b/arch/frv/mm/highmem.c
index 31902c9d5be5..bed9a9bd3c10 100644
--- a/arch/frv/mm/highmem.c
+++ b/arch/frv/mm/highmem.c
@@ -50,11 +50,11 @@ void *kmap_atomic(struct page *page)
 	/*
 	 * The first 4 primary maps are reserved for architecture code
 	 */
-	case 0:		return __kmap_atomic_primary(4, paddr, 6);
-	case 1:		return __kmap_atomic_primary(5, paddr, 7);
-	case 2:		return __kmap_atomic_primary(6, paddr, 8);
-	case 3:		return __kmap_atomic_primary(7, paddr, 9);
-	case 4:		return __kmap_atomic_primary(8, paddr, 10);
+	case 0:		return __kmap_atomic_primary(0, paddr, 6);
+	case 1:		return __kmap_atomic_primary(0, paddr, 7);
+	case 2:		return __kmap_atomic_primary(0, paddr, 8);
+	case 3:		return __kmap_atomic_primary(0, paddr, 9);
+	case 4:		return __kmap_atomic_primary(0, paddr, 10);
 
 	case 5 ... 5 + NR_TLB_LINES - 1:
 		return __kmap_atomic_secondary(type - 5, paddr);
@@ -70,11 +70,11 @@ void __kunmap_atomic(void *kvaddr)
 {
 	int type = kmap_atomic_idx();
 	switch (type) {
-	case 0:		__kunmap_atomic_primary(4, 6);	break;
-	case 1:		__kunmap_atomic_primary(5, 7);	break;
-	case 2:		__kunmap_atomic_primary(6, 8);	break;
-	case 3:		__kunmap_atomic_primary(7, 9);	break;
-	case 4:		__kunmap_atomic_primary(8, 10);	break;
+	case 0:		__kunmap_atomic_primary(0, 6);	break;
+	case 1:		__kunmap_atomic_primary(0, 7);	break;
+	case 2:		__kunmap_atomic_primary(0, 8);	break;
+	case 3:		__kunmap_atomic_primary(0, 9);	break;
+	case 4:		__kunmap_atomic_primary(0, 10);	break;
 
 	case 5 ... 5 + NR_TLB_LINES - 1:
 		__kunmap_atomic_secondary(type - 5, kvaddr);
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index 56e890df5053..5e8a0d9a09ce 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -3,6 +3,7 @@ config H8300
 	default y
 	select HAVE_IDE
 	select HAVE_GENERIC_HARDIRQS
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 
diff --git a/arch/h8300/include/asm/unistd.h b/arch/h8300/include/asm/unistd.h
index 718511303b4e..5cd882801d79 100644
--- a/arch/h8300/include/asm/unistd.h
+++ b/arch/h8300/include/asm/unistd.h
@@ -331,7 +331,6 @@
 
 #define NR_syscalls 321
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
 #define __ARCH_WANT_STAT64
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 9aa17f1917ea..06906427c0ac 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -7,7 +7,6 @@ header-y += user.h
 generic-y += auxvec.h
 generic-y += bug.h
 generic-y += bugs.h
-generic-y += cpumask.h
 generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
@@ -23,7 +22,6 @@ generic-y += ioctl.h
 generic-y += ioctls.h
 generic-y += iomap.h
 generic-y += ipcbuf.h
-generic-y += ipc.h
 generic-y += irq_regs.h
 generic-y += kdebug.h
 generic-y += kmap_types.h
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 8186ec5ea151..310cf5781fad 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -126,6 +126,7 @@ config AUDIT_ARCH
 
 menuconfig PARAVIRT_GUEST
 	bool "Paravirtualized guest support"
+	depends on BROKEN
 	help
 	  Say Y here to get to see options related to running Linux under
 	  various hypervisors.  This option alone does not add any kernel code.
@@ -138,8 +139,6 @@ config PARAVIRT
 	bool "Enable paravirtualization code"
 	depends on PARAVIRT_GUEST
 	default y
-	bool
-	default y
 	help
 	  This changes the kernel so it can modify itself when it is run
 	  under a hypervisor, potentially improving performance significantly
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 7d9116600a36..6e6fe1839f5d 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -17,8 +17,8 @@
 #include <asm/intrinsics.h>
 
 
-#define ATOMIC_INIT(i)		((atomic_t) { (i) })
-#define ATOMIC64_INIT(i)	((atomic64_t) { (i) })
+#define ATOMIC_INIT(i)		{ (i) }
+#define ATOMIC64_INIT(i)	{ (i) }
 
 #define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic64_read(v)	(*(volatile long *)&(v)->counter)
diff --git a/arch/ia64/include/asm/machvec.h b/arch/ia64/include/asm/machvec.h
index 367d299d9938..2d1ad4b11a85 100644
--- a/arch/ia64/include/asm/machvec.h
+++ b/arch/ia64/include/asm/machvec.h
@@ -120,7 +120,7 @@ extern void machvec_tlb_migrate_finish (struct mm_struct *);
 # ifdef MACHVEC_PLATFORM_HEADER
 #  include MACHVEC_PLATFORM_HEADER
 # else
-#  define platform_name		ia64_mv.name
+#  define ia64_platform_name	ia64_mv.name
 #  define platform_setup	ia64_mv.setup
 #  define platform_cpu_init	ia64_mv.cpu_init
 #  define platform_irq_init	ia64_mv.irq_init
diff --git a/arch/ia64/include/asm/machvec_dig.h b/arch/ia64/include/asm/machvec_dig.h
index 8a0752f40987..1f7403a2fbee 100644
--- a/arch/ia64/include/asm/machvec_dig.h
+++ b/arch/ia64/include/asm/machvec_dig.h
@@ -10,7 +10,7 @@ extern ia64_mv_setup_t dig_setup;
  * platform's machvec structure.  When compiling a non-generic kernel,
  * the macros are used directly.
  */
-#define platform_name		"dig"
+#define ia64_platform_name	"dig"
 #define platform_setup		dig_setup
 
 #endif /* _ASM_IA64_MACHVEC_DIG_h */
diff --git a/arch/ia64/include/asm/machvec_dig_vtd.h b/arch/ia64/include/asm/machvec_dig_vtd.h
index 6ab1de5c45ef..44308b4c3f6e 100644
--- a/arch/ia64/include/asm/machvec_dig_vtd.h
+++ b/arch/ia64/include/asm/machvec_dig_vtd.h
@@ -11,7 +11,7 @@ extern ia64_mv_dma_init			pci_iommu_alloc;
  * platform's machvec structure.  When compiling a non-generic kernel,
  * the macros are used directly.
  */
-#define platform_name				"dig_vtd"
+#define ia64_platform_name			"dig_vtd"
 #define platform_setup				dig_setup
 #define platform_dma_init			pci_iommu_alloc
 
diff --git a/arch/ia64/include/asm/machvec_hpsim.h b/arch/ia64/include/asm/machvec_hpsim.h
index cf72fc87fdfe..e75711279366 100644
--- a/arch/ia64/include/asm/machvec_hpsim.h
+++ b/arch/ia64/include/asm/machvec_hpsim.h
@@ -11,7 +11,7 @@ extern ia64_mv_irq_init_t hpsim_irq_init;
  * platform's machvec structure.  When compiling a non-generic kernel,
  * the macros are used directly.
  */
-#define platform_name		"hpsim"
+#define ia64_platform_name	"hpsim"
 #define platform_setup		hpsim_setup
 #define platform_irq_init	hpsim_irq_init
 
diff --git a/arch/ia64/include/asm/machvec_hpzx1.h b/arch/ia64/include/asm/machvec_hpzx1.h
index 3bd83d78a412..c74d3159e9eb 100644
--- a/arch/ia64/include/asm/machvec_hpzx1.h
+++ b/arch/ia64/include/asm/machvec_hpzx1.h
@@ -11,7 +11,7 @@ extern ia64_mv_dma_init			sba_dma_init;
  * platform's machvec structure.  When compiling a non-generic kernel,
  * the macros are used directly.
  */
-#define platform_name				"hpzx1"
+#define ia64_platform_name			"hpzx1"
 #define platform_setup				dig_setup
 #define platform_dma_init			sba_dma_init
 
diff --git a/arch/ia64/include/asm/machvec_hpzx1_swiotlb.h b/arch/ia64/include/asm/machvec_hpzx1_swiotlb.h
index 1091ac39740c..906ef6210774 100644
--- a/arch/ia64/include/asm/machvec_hpzx1_swiotlb.h
+++ b/arch/ia64/include/asm/machvec_hpzx1_swiotlb.h
@@ -11,7 +11,7 @@ extern ia64_mv_dma_get_ops			hwsw_dma_get_ops;
  * platform's machvec structure.  When compiling a non-generic kernel,
  * the macros are used directly.
  */
-#define platform_name				"hpzx1_swiotlb"
+#define ia64_platform_name			"hpzx1_swiotlb"
 #define platform_setup				dig_setup
 #define platform_dma_init			machvec_noop
 #define platform_dma_get_ops			hwsw_dma_get_ops
diff --git a/arch/ia64/include/asm/machvec_sn2.h b/arch/ia64/include/asm/machvec_sn2.h
index f061a30aac42..ece9fa85be88 100644
--- a/arch/ia64/include/asm/machvec_sn2.h
+++ b/arch/ia64/include/asm/machvec_sn2.h
@@ -71,7 +71,7 @@ extern ia64_mv_pci_fixup_bus_t		sn_pci_fixup_bus;
  * platform's machvec structure.  When compiling a non-generic kernel,
  * the macros are used directly.
  */
-#define platform_name			"sn2"
+#define ia64_platform_name		"sn2"
 #define platform_setup			sn_setup
 #define platform_cpu_init		sn_cpu_init
 #define platform_irq_init		sn_irq_init
diff --git a/arch/ia64/include/asm/machvec_uv.h b/arch/ia64/include/asm/machvec_uv.h
index 2931447f3813..2c50853f35ac 100644
--- a/arch/ia64/include/asm/machvec_uv.h
+++ b/arch/ia64/include/asm/machvec_uv.h
@@ -20,7 +20,7 @@ extern ia64_mv_setup_t uv_setup;
  * platform's machvec structure.  When compiling a non-generic kernel,
  * the macros are used directly.
  */
-#define platform_name			"uv"
+#define ia64_platform_name		"uv"
 #define platform_setup			uv_setup
 
 #endif /* _ASM_IA64_MACHVEC_UV_H */
diff --git a/arch/ia64/include/asm/machvec_xen.h b/arch/ia64/include/asm/machvec_xen.h
index 55f9228056cd..8b8bd0eb3923 100644
--- a/arch/ia64/include/asm/machvec_xen.h
+++ b/arch/ia64/include/asm/machvec_xen.h
@@ -13,7 +13,7 @@ extern ia64_mv_send_ipi_t		xen_platform_send_ipi;
  * platform's machvec structure.  When compiling a non-generic kernel,
  * the macros are used directly.
  */
-#define platform_name				"xen"
+#define ia64_platform_name			"xen"
 #define platform_setup				dig_setup
 #define platform_cpu_init			xen_cpu_init
 #define platform_irq_init			xen_irq_init
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 832dd3789e9d..944152a50912 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -719,7 +719,7 @@ enum idle_boot_override {IDLE_NO_OVERRIDE=0, IDLE_HALT, IDLE_FORCE_MWAIT,
 
 void default_idle(void);
 
-#define ia64_platform_is(x) (strcmp(x, platform_name) == 0)
+#define ia64_platform_is(x) (strcmp(x, ia64_platform_name) == 0)
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/ia64/kernel/irq_ia64.c b/arch/ia64/kernel/irq_ia64.c
index 5c3e0888265a..1034884b77da 100644
--- a/arch/ia64/kernel/irq_ia64.c
+++ b/arch/ia64/kernel/irq_ia64.c
@@ -23,7 +23,6 @@
 #include <linux/ioport.h>
 #include <linux/kernel_stat.h>
 #include <linux/ptrace.h>
-#include <linux/random.h>	/* for rand_initialize_irq() */
 #include <linux/signal.h>
 #include <linux/smp.h>
 #include <linux/threads.h>
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index d7f558c1e711..3fa4bc536953 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -2353,7 +2353,6 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 	 */
 	insert_vm_struct(mm, vma);
 
-	mm->total_vm  += size >> PAGE_SHIFT;
 	vm_stat_account(vma->vm_mm, vma->vm_flags, vma->vm_file,
 							vma_pages(vma));
 	up_write(&task->mm->mmap_sem);
diff --git a/arch/ia64/kvm/Kconfig b/arch/ia64/kvm/Kconfig
index df5351e3eed7..e7947528aee6 100644
--- a/arch/ia64/kvm/Kconfig
+++ b/arch/ia64/kvm/Kconfig
@@ -23,6 +23,7 @@ config KVM
 	depends on HAVE_KVM && MODULES && EXPERIMENTAL
 	# for device assignment:
 	depends on PCI
+	depends on BROKEN
 	select PREEMPT_NOTIFIERS
 	select ANON_INODES
 	select HAVE_KVM_IRQCHIP
diff --git a/arch/ia64/pci/fixup.c b/arch/ia64/pci/fixup.c
index f5959c0c1810..eab28e314022 100644
--- a/arch/ia64/pci/fixup.c
+++ b/arch/ia64/pci/fixup.c
@@ -30,8 +30,8 @@ static void __devinit pci_fixup_video(struct pci_dev *pdev)
 	struct pci_bus *bus;
 	u16 config;
 
-	if ((strcmp(platform_name, "dig") != 0)
-	    && (strcmp(platform_name, "hpzx1")  != 0))
+	if ((strcmp(ia64_platform_name, "dig") != 0)
+	    && (strcmp(ia64_platform_name, "hpzx1")  != 0))
 		return;
 	/* Maybe, this machine supports legacy memory map. */
 
diff --git a/arch/m32r/Kconfig b/arch/m32r/Kconfig
index b638d5bfa14d..49498bbb9616 100644
--- a/arch/m32r/Kconfig
+++ b/arch/m32r/Kconfig
@@ -7,6 +7,7 @@ config M32R
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_LZMA
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
diff --git a/arch/m32r/include/asm/unistd.h b/arch/m32r/include/asm/unistd.h
index 3e1db561aacc..d5e66a480782 100644
--- a/arch/m32r/include/asm/unistd.h
+++ b/arch/m32r/include/asm/unistd.h
@@ -336,7 +336,6 @@
 
 #define NR_syscalls 326
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_ALARM
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 147120128260..0b0f8b8c4a26 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -10,6 +10,7 @@ config M68K
 	select GENERIC_STRNCPY_FROM_USER if MMU
 	select GENERIC_STRNLEN_USER if MMU
 	select FPU if MMU
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select ARCH_USES_GETTIMEOFFSET if MMU && !COLDFIRE
 
 config RWSEM_GENERIC_SPINLOCK
diff --git a/arch/m68k/include/asm/unistd.h b/arch/m68k/include/asm/unistd.h
index ea0b502f845e..045cfd6a9e31 100644
--- a/arch/m68k/include/asm/unistd.h
+++ b/arch/m68k/include/asm/unistd.h
@@ -357,7 +357,6 @@
 
 #define NR_syscalls		347
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
 #define __ARCH_WANT_STAT64
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index 0bf44231aaf9..ab9afcaa7f6a 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -15,6 +15,7 @@ config MICROBLAZE
 	select TRACING_SUPPORT
 	select OF
 	select OF_EARLY_FLATTREE
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select IRQ_DOMAIN
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_PROBE
diff --git a/arch/microblaze/include/asm/unistd.h b/arch/microblaze/include/asm/unistd.h
index d20ffbc86beb..6985e6e9d826 100644
--- a/arch/microblaze/include/asm/unistd.h
+++ b/arch/microblaze/include/asm/unistd.h
@@ -400,7 +400,6 @@
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
 /* #define __ARCH_WANT_OLD_READDIR */
 /* #define __ARCH_WANT_OLD_STAT */
 #define __ARCH_WANT_STAT64
diff --git a/arch/mips/Kbuild.platforms b/arch/mips/Kbuild.platforms
index 5ce8029f558b..d64786d5e2f3 100644
--- a/arch/mips/Kbuild.platforms
+++ b/arch/mips/Kbuild.platforms
@@ -14,6 +14,7 @@ platforms += jz4740
 platforms += lantiq
 platforms += lasat
 platforms += loongson
+platforms += loongson1
 platforms += mipssim
 platforms += mti-malta
 platforms += netlogic
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index b3e10fdd3898..e3efc06e6409 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -20,12 +20,14 @@ config MIPS
 	select ARCH_BINFMT_ELF_RANDOMIZE_PIE
 	select RTC_LIB if !MACH_LOONGSON
 	select GENERIC_ATOMIC64 if !64BIT
+	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select HAVE_ARCH_JUMP_LABEL
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select IRQ_FORCED_THREADING
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
@@ -209,6 +211,7 @@ config MACH_JZ4740
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
+	select SYS_SUPPORTS_ZBOOT_UART16550
 	select DMA_NONCOHERENT
 	select IRQ_CPU
 	select GENERIC_GPIO
@@ -264,6 +267,16 @@ config MACH_LOONGSON
 	  Chinese Academy of Sciences (CAS) in the People's Republic
 	  of China. The chief architect is Professor Weiwu Hu.
 
+config MACH_LOONGSON1
+	bool "Loongson 1 family of machines"
+	select SYS_SUPPORTS_ZBOOT
+	help
+	  This enables support for the Loongson 1 based machines.
+
+	  Loongson 1 is a family of 32-bit MIPS-compatible SoCs developed by
+	  the ICT (Institute of Computing Technology) and the Chinese Academy
+	  of Sciences.
+
 config MIPS_MALTA
 	bool "MIPS Malta board"
 	select ARCH_MAY_HAVE_PC_FDC
@@ -787,6 +800,8 @@ config NLM_XLR_BOARD
 	select ZONE_DMA if 64BIT
 	select SYNC_R4K
 	select SYS_HAS_EARLY_PRINTK
+	select USB_ARCH_HAS_OHCI if USB_SUPPORT
+	select USB_ARCH_HAS_EHCI if USB_SUPPORT
 	help
 	  Support for systems based on Netlogic XLR and XLS processors.
 	  Say Y here if you have a XLR or XLS based board.
@@ -799,7 +814,6 @@ config NLM_XLP_BOARD
 	select SYS_HAS_CPU_XLP
 	select SYS_SUPPORTS_SMP
 	select HW_HAS_PCI
-	select SWAP_IO_SPACE
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select 64BIT_PHYS_ADDR
@@ -836,6 +850,7 @@ source "arch/mips/txx9/Kconfig"
 source "arch/mips/vr41xx/Kconfig"
 source "arch/mips/cavium-octeon/Kconfig"
 source "arch/mips/loongson/Kconfig"
+source "arch/mips/loongson1/Kconfig"
 source "arch/mips/netlogic/Kconfig"
 
 endmenu
@@ -1217,6 +1232,14 @@ config CPU_LOONGSON2F
 	  have a similar programming interface with FPGA northbridge used in
 	  Loongson2E.
 
+config CPU_LOONGSON1B
+	bool "Loongson 1B"
+	depends on SYS_HAS_CPU_LOONGSON1B
+	select CPU_LOONGSON1
+	help
+	  The Loongson 1B is a 32-bit SoC, which implements the MIPS32
+	  release 2 instruction set.
+
 config CPU_MIPS32_R1
 	bool "MIPS32 Release 1"
 	depends on SYS_HAS_CPU_MIPS32_R1
@@ -1432,6 +1455,8 @@ config CPU_CAVIUM_OCTEON
 	select WEAK_ORDERING
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
+	select LIBFDT
+	select USE_OF
 	help
 	  The Cavium Octeon processor is a highly integrated chip containing
 	  many ethernet hardware widgets for networking tasks. The processor
@@ -1544,6 +1569,14 @@ config CPU_LOONGSON2
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 
+config CPU_LOONGSON1
+	bool
+	select CPU_MIPS32
+	select CPU_MIPSR2
+	select CPU_HAS_PREFETCH
+	select CPU_SUPPORTS_32BIT_KERNEL
+	select CPU_SUPPORTS_HIGHMEM
+
 config CPU_BMIPS
 	bool
 	select CPU_MIPS32
@@ -1562,6 +1595,9 @@ config SYS_HAS_CPU_LOONGSON2F
 	select CPU_SUPPORTS_ADDRWINCFG if 64BIT
 	select CPU_SUPPORTS_UNCACHED_ACCELERATED
 
+config SYS_HAS_CPU_LOONGSON1B
+	bool
+
 config SYS_HAS_CPU_MIPS32_R1
 	bool
 
@@ -2366,6 +2402,8 @@ config PCI_DOMAINS
 
 source "drivers/pci/Kconfig"
 
+source "drivers/pci/pcie/Kconfig"
+
 #
 # ISA support is now enabled via select.  Too many systems still have the one
 # or other ISA chip on the board that users don't know about so don't expect
diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c
index 295f1a95f745..99969484c475 100644
--- a/arch/mips/alchemy/board-mtx1.c
+++ b/arch/mips/alchemy/board-mtx1.c
@@ -81,10 +81,10 @@ static void mtx1_power_off(void)
 
 void __init board_setup(void)
 {
-#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
+#if IS_ENABLED(CONFIG_USB_OHCI_HCD)
 	/* Enable USB power switch */
 	alchemy_gpio_direction_output(204, 0);
-#endif /* defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) */
+#endif /* IS_ENABLED(CONFIG_USB_OHCI_HCD) */
 
 	/* Initialize sys_pinfunc */
 	au_writel(SYS_PF_NI2, SYS_PINFUNC);
diff --git a/arch/mips/alchemy/common/platform.c b/arch/mips/alchemy/common/platform.c
index 95cb9113b12c..c0f3ce6dcb56 100644
--- a/arch/mips/alchemy/common/platform.c
+++ b/arch/mips/alchemy/common/platform.c
@@ -334,13 +334,12 @@ static void __init alchemy_setup_macs(int ctype)
 	if (alchemy_get_macs(ctype) < 1)
 		return;
 
-	macres = kmalloc(sizeof(struct resource) * MAC_RES_COUNT, GFP_KERNEL);
+	macres = kmemdup(au1xxx_eth0_resources[ctype],
+			 sizeof(struct resource) * MAC_RES_COUNT, GFP_KERNEL);
 	if (!macres) {
 		printk(KERN_INFO "Alchemy: no memory for MAC0 resources\n");
 		return;
 	}
-	memcpy(macres, au1xxx_eth0_resources[ctype],
-	       sizeof(struct resource) * MAC_RES_COUNT);
 	au1xxx_eth0_device.resource = macres;
 
 	i = prom_get_ethernet_addr(ethaddr);
@@ -356,13 +355,12 @@ static void __init alchemy_setup_macs(int ctype)
 	if (alchemy_get_macs(ctype) < 2)
 		return;
 
-	macres = kmalloc(sizeof(struct resource) * MAC_RES_COUNT, GFP_KERNEL);
+	macres = kmemdup(au1xxx_eth1_resources[ctype],
+			 sizeof(struct resource) * MAC_RES_COUNT, GFP_KERNEL);
 	if (!macres) {
 		printk(KERN_INFO "Alchemy: no memory for MAC1 resources\n");
 		return;
 	}
-	memcpy(macres, au1xxx_eth1_resources[ctype],
-	       sizeof(struct resource) * MAC_RES_COUNT);
 	au1xxx_eth1_device.resource = macres;
 
 	ethaddr[5] += 1;	/* next addr for 2nd MAC */
diff --git a/arch/mips/alchemy/devboards/Makefile b/arch/mips/alchemy/devboards/Makefile
index 3c37fb303364..c9e747dd9fc2 100644
--- a/arch/mips/alchemy/devboards/Makefile
+++ b/arch/mips/alchemy/devboards/Makefile
@@ -2,7 +2,7 @@
 # Alchemy Develboards
 #
 
-obj-y += prom.o bcsr.o platform.o
+obj-y += bcsr.o platform.o
 obj-$(CONFIG_PM)		+= pm.o
 obj-$(CONFIG_MIPS_PB1100)	+= pb1100.o
 obj-$(CONFIG_MIPS_PB1500)	+= pb1500.o
diff --git a/arch/mips/alchemy/devboards/bcsr.c b/arch/mips/alchemy/devboards/bcsr.c
index 1e83ce2e1147..f2039ef2c293 100644
--- a/arch/mips/alchemy/devboards/bcsr.c
+++ b/arch/mips/alchemy/devboards/bcsr.c
@@ -90,10 +90,7 @@ static void bcsr_csc_handler(unsigned int irq, struct irq_desc *d)
 	unsigned short bisr = __raw_readw(bcsr_virt + BCSR_REG_INTSTAT);
 
 	disable_irq_nosync(irq);
-
-	for ( ; bisr; bisr &= bisr - 1)
-		generic_handle_irq(bcsr_csc_base + __ffs(bisr));
-
+	generic_handle_irq(bcsr_csc_base + __ffs(bisr));
 	enable_irq(irq);
 }
 
diff --git a/arch/mips/alchemy/devboards/pb1100.c b/arch/mips/alchemy/devboards/pb1100.c
index cff50d05ddd4..78c77a44a317 100644
--- a/arch/mips/alchemy/devboards/pb1100.c
+++ b/arch/mips/alchemy/devboards/pb1100.c
@@ -46,7 +46,7 @@ void __init board_setup(void)
 	alchemy_gpio1_input_enable();
 	udelay(100);
 
-#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
+#if IS_ENABLED(CONFIG_USB_OHCI_HCD)
 	{
 		u32 pin_func, sys_freqctrl, sys_clksrc;
 
@@ -93,7 +93,7 @@ void __init board_setup(void)
 		pin_func |= SYS_PF_USB;
 		au_writel(pin_func, SYS_PINFUNC);
 	}
-#endif /* defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) */
+#endif /* IS_ENABLED(CONFIG_USB_OHCI_HCD) */
 
 	/* Enable sys bus clock divider when IDLE state or no bus activity. */
 	au_writel(au_readl(SYS_POWERCTRL) | (0x3 << 5), SYS_POWERCTRL);
diff --git a/arch/mips/alchemy/devboards/pb1500.c b/arch/mips/alchemy/devboards/pb1500.c
index e7b807b3ec51..232fee942000 100644
--- a/arch/mips/alchemy/devboards/pb1500.c
+++ b/arch/mips/alchemy/devboards/pb1500.c
@@ -53,7 +53,7 @@ void __init board_setup(void)
 	alchemy_gpio_direction_input(201);
 	alchemy_gpio_direction_input(203);
 
-#if defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE)
+#if IS_ENABLED(CONFIG_USB_OHCI_HCD)
 
 	/* Zero and disable FREQ2 */
 	sys_freqctrl = au_readl(SYS_FREQCTRL0);
@@ -87,7 +87,7 @@ void __init board_setup(void)
 	/* 2nd USB port is USB host */
 	pin_func |= SYS_PF_USB;
 	au_writel(pin_func, SYS_PINFUNC);
-#endif /* defined(CONFIG_USB_OHCI_HCD) || defined(CONFIG_USB_OHCI_HCD_MODULE) */
+#endif /* IS_ENABLED(CONFIG_USB_OHCI_HCD) */
 
 #ifdef CONFIG_PCI
 	{
diff --git a/arch/mips/alchemy/devboards/platform.c b/arch/mips/alchemy/devboards/platform.c
index 621f70afb63a..f39042e99d0d 100644
--- a/arch/mips/alchemy/devboards/platform.c
+++ b/arch/mips/alchemy/devboards/platform.c
@@ -10,9 +10,39 @@
 #include <linux/platform_device.h>
 #include <linux/pm.h>
 
+#include <asm/bootinfo.h>
 #include <asm/reboot.h>
+#include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-db1x00/bcsr.h>
 
+#include <prom.h>
+
+void __init prom_init(void)
+{
+	unsigned char *memsize_str;
+	unsigned long memsize;
+
+	prom_argc = (int)fw_arg0;
+	prom_argv = (char **)fw_arg1;
+	prom_envp = (char **)fw_arg2;
+
+	prom_init_cmdline();
+	memsize_str = prom_getenv("memsize");
+	if (!memsize_str || kstrtoul(memsize_str, 0, &memsize))
+		memsize = 64 << 20; /* all devboards have at least 64MB RAM */
+
+	add_memory_region(0, memsize, BOOT_MEM_RAM);
+}
+
+void prom_putchar(unsigned char c)
+{
+#ifdef CONFIG_MIPS_DB1300
+	alchemy_uart_putchar(AU1300_UART2_PHYS_ADDR, c);
+#else
+	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
+#endif
+}
+
 
 static struct platform_device db1x00_rtc_dev = {
 	.name	= "rtc-au1xxx",
diff --git a/arch/mips/alchemy/devboards/prom.c b/arch/mips/alchemy/devboards/prom.c
deleted file mode 100644
index 93a22107cc41..000000000000
--- a/arch/mips/alchemy/devboards/prom.c
+++ /dev/null
@@ -1,69 +0,0 @@
-/*
- * Common code used by all Alchemy develboards.
- *
- * Extracted from files which had this to say:
- *
- * Copyright 2000, 2008 MontaVista Software Inc.
- * Author: MontaVista Software, Inc. <source@mvista.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- *  THIS  SOFTWARE  IS PROVIDED   ``AS  IS'' AND   ANY  EXPRESS OR IMPLIED
- *  WARRANTIES,   INCLUDING, BUT NOT  LIMITED  TO, THE IMPLIED WARRANTIES OF
- *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN
- *  NO  EVENT  SHALL   THE AUTHOR  BE    LIABLE FOR ANY   DIRECT, INDIRECT,
- *  INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
- *  NOT LIMITED   TO, PROCUREMENT OF  SUBSTITUTE GOODS  OR SERVICES; LOSS OF
- *  USE, DATA,  OR PROFITS; OR  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
- *  ANY THEORY OF LIABILITY, WHETHER IN  CONTRACT, STRICT LIABILITY, OR TORT
- *  (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
- *  THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *  You should have received a copy of the  GNU General Public License along
- *  with this program; if not, write  to the Free Software Foundation, Inc.,
- *  675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <asm/bootinfo.h>
-#include <asm/mach-au1x00/au1000.h>
-#include <prom.h>
-
-#if defined(CONFIG_MIPS_DB1000) || \
-    defined(CONFIG_MIPS_PB1100) || \
-    defined(CONFIG_MIPS_PB1500)
-#define ALCHEMY_BOARD_DEFAULT_MEMSIZE	0x04000000
-
-#else	/* Au1550/Au1200-based develboards */
-#define ALCHEMY_BOARD_DEFAULT_MEMSIZE	0x08000000
-#endif
-
-void __init prom_init(void)
-{
-	unsigned char *memsize_str;
-	unsigned long memsize;
-
-	prom_argc = (int)fw_arg0;
-	prom_argv = (char **)fw_arg1;
-	prom_envp = (char **)fw_arg2;
-
-	prom_init_cmdline();
-	memsize_str = prom_getenv("memsize");
-	if (!memsize_str || strict_strtoul(memsize_str, 0, &memsize))
-		memsize = ALCHEMY_BOARD_DEFAULT_MEMSIZE;
-
-	add_memory_region(0, memsize, BOOT_MEM_RAM);
-}
-
-void prom_putchar(unsigned char c)
-{
-#ifdef CONFIG_MIPS_DB1300
-	alchemy_uart_putchar(AU1300_UART2_PHYS_ADDR, c);
-#else
-	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
-#endif
-}
diff --git a/arch/mips/bcm63xx/Kconfig b/arch/mips/bcm63xx/Kconfig
index 6b1b9ad8d857..d03e8799d1cf 100644
--- a/arch/mips/bcm63xx/Kconfig
+++ b/arch/mips/bcm63xx/Kconfig
@@ -1,6 +1,10 @@
 menu "CPU support"
 	depends on BCM63XX
 
+config BCM63XX_CPU_6328
+	bool "support 6328 CPU"
+	select HW_HAS_PCI
+
 config BCM63XX_CPU_6338
 	bool "support 6338 CPU"
 	select HW_HAS_PCI
diff --git a/arch/mips/bcm63xx/Makefile b/arch/mips/bcm63xx/Makefile
index 6dfdc69928ac..833af72c852a 100644
--- a/arch/mips/bcm63xx/Makefile
+++ b/arch/mips/bcm63xx/Makefile
@@ -1,5 +1,6 @@
 obj-y		+= clk.o cpu.o cs.o gpio.o irq.o prom.o setup.o timer.o \
-		   dev-dsp.o dev-enet.o dev-pcmcia.o dev-uart.o dev-wdt.o
+		   dev-dsp.o dev-enet.o dev-flash.o dev-pcmcia.o dev-rng.o \
+		   dev-spi.o dev-uart.o dev-wdt.o
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 
 obj-y		+= boards/
diff --git a/arch/mips/bcm63xx/boards/board_bcm963xx.c b/arch/mips/bcm63xx/boards/board_bcm963xx.c
index 2f1773f3fb7a..feb05258a4d1 100644
--- a/arch/mips/bcm63xx/boards/board_bcm963xx.c
+++ b/arch/mips/bcm63xx/boards/board_bcm963xx.c
@@ -11,9 +11,6 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/platform_device.h>
-#include <linux/mtd/mtd.h>
-#include <linux/mtd/partitions.h>
-#include <linux/mtd/physmap.h>
 #include <linux/ssb/ssb.h>
 #include <asm/addrspace.h>
 #include <bcm63xx_board.h>
@@ -24,7 +21,9 @@
 #include <bcm63xx_dev_pci.h>
 #include <bcm63xx_dev_enet.h>
 #include <bcm63xx_dev_dsp.h>
+#include <bcm63xx_dev_flash.h>
 #include <bcm63xx_dev_pcmcia.h>
+#include <bcm63xx_dev_spi.h>
 #include <board_bcm963xx.h>
 
 #define PFX	"board_bcm963xx: "
@@ -34,6 +33,48 @@ static unsigned int mac_addr_used;
 static struct board_info board;
 
 /*
+ * known 6328 boards
+ */
+#ifdef CONFIG_BCM63XX_CPU_6328
+static struct board_info __initdata board_96328avng = {
+	.name				= "96328avng",
+	.expected_cpu_id		= 0x6328,
+
+	.has_uart0			= 1,
+	.has_pci			= 1,
+
+	.leds = {
+		{
+			.name		= "96328avng::ppp-fail",
+			.gpio		= 2,
+			.active_low	= 1,
+		},
+		{
+			.name		= "96328avng::power",
+			.gpio		= 4,
+			.active_low	= 1,
+			.default_trigger = "default-on",
+		},
+		{
+			.name		= "96328avng::power-fail",
+			.gpio		= 8,
+			.active_low	= 1,
+		},
+		{
+			.name		= "96328avng::wps",
+			.gpio		= 9,
+			.active_low	= 1,
+		},
+		{
+			.name		= "96328avng::ppp",
+			.gpio		= 11,
+			.active_low	= 1,
+		},
+	},
+};
+#endif
+
+/*
  * known 6338 boards
  */
 #ifdef CONFIG_BCM63XX_CPU_6338
@@ -592,6 +633,9 @@ static struct board_info __initdata board_DWVS0 = {
  * all boards
  */
 static const struct board_info __initdata *bcm963xx_boards[] = {
+#ifdef CONFIG_BCM63XX_CPU_6328
+	&board_96328avng,
+#endif
 #ifdef CONFIG_BCM63XX_CPU_6338
 	&board_96338gw,
 	&board_96338w,
@@ -709,9 +753,15 @@ void __init board_prom_init(void)
 	char cfe_version[32];
 	u32 val;
 
-	/* read base address of boot chip select (0) */
-	val = bcm_mpi_readl(MPI_CSBASE_REG(0));
-	val &= MPI_CSBASE_BASE_MASK;
+	/* read base address of boot chip select (0)
+	 * 6328 does not have MPI but boots from a fixed address
+	 */
+	if (BCMCPU_IS_6328())
+		val = 0x18000000;
+	else {
+		val = bcm_mpi_readl(MPI_CSBASE_REG(0));
+		val &= MPI_CSBASE_BASE_MASK;
+	}
 	boot_addr = (u8 *)KSEG1ADDR(val);
 
 	/* dump cfe version */
@@ -808,40 +858,6 @@ void __init board_setup(void)
 		panic("unexpected CPU for bcm963xx board");
 }
 
-static struct mtd_partition mtd_partitions[] = {
-	{
-		.name		= "cfe",
-		.offset		= 0x0,
-		.size		= 0x40000,
-	}
-};
-
-static const char *bcm63xx_part_types[] = { "bcm63xxpart", NULL };
-
-static struct physmap_flash_data flash_data = {
-	.width			= 2,
-	.nr_parts		= ARRAY_SIZE(mtd_partitions),
-	.parts			= mtd_partitions,
-	.part_probe_types	= bcm63xx_part_types,
-};
-
-static struct resource mtd_resources[] = {
-	{
-		.start		= 0,	/* filled at runtime */
-		.end		= 0,	/* filled at runtime */
-		.flags		= IORESOURCE_MEM,
-	}
-};
-
-static struct platform_device mtd_dev = {
-	.name			= "physmap-flash",
-	.resource		= mtd_resources,
-	.num_resources		= ARRAY_SIZE(mtd_resources),
-	.dev			= {
-		.platform_data	= &flash_data,
-	},
-};
-
 static struct gpio_led_platform_data bcm63xx_led_data;
 
 static struct platform_device bcm63xx_gpio_leds = {
@@ -855,8 +871,6 @@ static struct platform_device bcm63xx_gpio_leds = {
  */
 int __init board_register_devices(void)
 {
-	u32 val;
-
 	if (board.has_uart0)
 		bcm63xx_uart_register(0);
 
@@ -890,14 +904,9 @@ int __init board_register_devices(void)
 	}
 #endif
 
-	/* read base address of boot chip select (0) */
-	val = bcm_mpi_readl(MPI_CSBASE_REG(0));
-	val &= MPI_CSBASE_BASE_MASK;
-
-	mtd_resources[0].start = val;
-	mtd_resources[0].end = 0x1FFFFFFF;
+	bcm63xx_spi_register();
 
-	platform_device_register(&mtd_dev);
+	bcm63xx_flash_register();
 
 	bcm63xx_led_data.num_leds = ARRAY_SIZE(board.leds);
 	bcm63xx_led_data.leds = board.leds;
diff --git a/arch/mips/bcm63xx/clk.c b/arch/mips/bcm63xx/clk.c
index 9d57c71b7b58..1db48adb543a 100644
--- a/arch/mips/bcm63xx/clk.c
+++ b/arch/mips/bcm63xx/clk.c
@@ -120,7 +120,7 @@ static void enetsw_set(struct clk *clk, int enable)
 {
 	if (!BCMCPU_IS_6368())
 		return;
-	bcm_hwclock_set(CKCTL_6368_ROBOSW_CLK_EN |
+	bcm_hwclock_set(CKCTL_6368_ROBOSW_EN |
 			CKCTL_6368_SWPKT_USB_EN |
 			CKCTL_6368_SWPKT_SAR_EN, enable);
 	if (enable) {
@@ -163,7 +163,7 @@ static void usbh_set(struct clk *clk, int enable)
 	if (BCMCPU_IS_6348())
 		bcm_hwclock_set(CKCTL_6348_USBH_EN, enable);
 	else if (BCMCPU_IS_6368())
-		bcm_hwclock_set(CKCTL_6368_USBH_CLK_EN, enable);
+		bcm_hwclock_set(CKCTL_6368_USBH_EN, enable);
 }
 
 static struct clk clk_usbh = {
@@ -181,9 +181,11 @@ static void spi_set(struct clk *clk, int enable)
 		mask = CKCTL_6338_SPI_EN;
 	else if (BCMCPU_IS_6348())
 		mask = CKCTL_6348_SPI_EN;
-	else
-		/* BCMCPU_IS_6358 */
+	else if (BCMCPU_IS_6358())
 		mask = CKCTL_6358_SPI_EN;
+	else
+		/* BCMCPU_IS_6368 */
+		mask = CKCTL_6368_SPI_EN;
 	bcm_hwclock_set(mask, enable);
 }
 
@@ -199,7 +201,7 @@ static void xtm_set(struct clk *clk, int enable)
 	if (!BCMCPU_IS_6368())
 		return;
 
-	bcm_hwclock_set(CKCTL_6368_SAR_CLK_EN |
+	bcm_hwclock_set(CKCTL_6368_SAR_EN |
 			CKCTL_6368_SWPKT_SAR_EN, enable);
 
 	if (enable) {
@@ -222,6 +224,18 @@ static struct clk clk_xtm = {
 };
 
 /*
+ * IPsec clock
+ */
+static void ipsec_set(struct clk *clk, int enable)
+{
+	bcm_hwclock_set(CKCTL_6368_IPSEC_EN, enable);
+}
+
+static struct clk clk_ipsec = {
+	.set	= ipsec_set,
+};
+
+/*
  * Internal peripheral clock
  */
 static struct clk clk_periph = {
@@ -278,6 +292,8 @@ struct clk *clk_get(struct device *dev, const char *id)
 		return &clk_periph;
 	if (BCMCPU_IS_6358() && !strcmp(id, "pcm"))
 		return &clk_pcm;
+	if (BCMCPU_IS_6368() && !strcmp(id, "ipsec"))
+		return &clk_ipsec;
 	return ERR_PTR(-ENOENT);
 }
 
diff --git a/arch/mips/bcm63xx/cpu.c b/arch/mips/bcm63xx/cpu.c
index 8f0d6c7725ea..a7afb289b15a 100644
--- a/arch/mips/bcm63xx/cpu.c
+++ b/arch/mips/bcm63xx/cpu.c
@@ -29,6 +29,14 @@ static u16 bcm63xx_cpu_rev;
 static unsigned int bcm63xx_cpu_freq;
 static unsigned int bcm63xx_memory_size;
 
+static const unsigned long bcm6328_regs_base[] = {
+	__GEN_CPU_REGS_TABLE(6328)
+};
+
+static const int bcm6328_irqs[] = {
+	__GEN_CPU_IRQ_TABLE(6328)
+};
+
 static const unsigned long bcm6338_regs_base[] = {
 	__GEN_CPU_REGS_TABLE(6338)
 };
@@ -99,6 +107,33 @@ unsigned int bcm63xx_get_memory_size(void)
 static unsigned int detect_cpu_clock(void)
 {
 	switch (bcm63xx_get_cpu_id()) {
+	case BCM6328_CPU_ID:
+	{
+		unsigned int tmp, mips_pll_fcvo;
+
+		tmp = bcm_misc_readl(MISC_STRAPBUS_6328_REG);
+		mips_pll_fcvo = (tmp & STRAPBUS_6328_FCVO_MASK)
+				>> STRAPBUS_6328_FCVO_SHIFT;
+
+		switch (mips_pll_fcvo) {
+		case 0x12:
+		case 0x14:
+		case 0x19:
+			return 160000000;
+		case 0x1c:
+			return 192000000;
+		case 0x13:
+		case 0x15:
+			return 200000000;
+		case 0x1a:
+			return 384000000;
+		case 0x16:
+			return 400000000;
+		default:
+			return 320000000;
+		}
+
+	}
 	case BCM6338_CPU_ID:
 		/* BCM6338 has a fixed 240 Mhz frequency */
 		return 240000000;
@@ -170,6 +205,9 @@ static unsigned int detect_memory_size(void)
 	unsigned int cols = 0, rows = 0, is_32bits = 0, banks = 0;
 	u32 val;
 
+	if (BCMCPU_IS_6328())
+		return bcm_ddr_readl(DDR_CSEND_REG) << 24;
+
 	if (BCMCPU_IS_6345()) {
 		val = bcm_sdram_readl(SDRAM_MBASE_REG);
 		return (val * 8 * 1024 * 1024);
@@ -228,17 +266,26 @@ void __init bcm63xx_cpu_init(void)
 		bcm63xx_irqs = bcm6345_irqs;
 		break;
 	case CPU_BMIPS4350:
-		switch (read_c0_prid() & 0xf0) {
-		case 0x10:
+		if ((read_c0_prid() & 0xf0) == 0x10) {
 			expected_cpu_id = BCM6358_CPU_ID;
 			bcm63xx_regs_base = bcm6358_regs_base;
 			bcm63xx_irqs = bcm6358_irqs;
-			break;
-		case 0x30:
-			expected_cpu_id = BCM6368_CPU_ID;
-			bcm63xx_regs_base = bcm6368_regs_base;
-			bcm63xx_irqs = bcm6368_irqs;
-			break;
+		} else {
+			/* all newer chips have the same chip id location */
+			u16 chip_id = bcm_readw(BCM_6368_PERF_BASE);
+
+			switch (chip_id) {
+			case BCM6328_CPU_ID:
+				expected_cpu_id = BCM6328_CPU_ID;
+				bcm63xx_regs_base = bcm6328_regs_base;
+				bcm63xx_irqs = bcm6328_irqs;
+				break;
+			case BCM6368_CPU_ID:
+				expected_cpu_id = BCM6368_CPU_ID;
+				bcm63xx_regs_base = bcm6368_regs_base;
+				bcm63xx_irqs = bcm6368_irqs;
+				break;
+			}
 		}
 		break;
 	}
diff --git a/arch/mips/bcm63xx/dev-dsp.c b/arch/mips/bcm63xx/dev-dsp.c
index da46d1d3c77c..5bb5b154c9bd 100644
--- a/arch/mips/bcm63xx/dev-dsp.c
+++ b/arch/mips/bcm63xx/dev-dsp.c
@@ -31,7 +31,7 @@ static struct resource voip_dsp_resources[] = {
 
 static struct platform_device bcm63xx_voip_dsp_device = {
 	.name		= "bcm63xx-voip-dsp",
-	.id		= 0,
+	.id		= -1,
 	.num_resources	= ARRAY_SIZE(voip_dsp_resources),
 	.resource	= voip_dsp_resources,
 };
diff --git a/arch/mips/bcm63xx/dev-flash.c b/arch/mips/bcm63xx/dev-flash.c
new file mode 100644
index 000000000000..58371c7deac2
--- /dev/null
+++ b/arch/mips/bcm63xx/dev-flash.c
@@ -0,0 +1,123 @@
+/*
+ * Broadcom BCM63xx flash registration
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2008 Maxime Bizon <mbizon@freebox.fr>
+ * Copyright (C) 2008 Florian Fainelli <florian@openwrt.org>
+ * Copyright (C) 2012 Jonas Gorski <jonas.gorski@gmail.com>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/physmap.h>
+
+#include <bcm63xx_cpu.h>
+#include <bcm63xx_dev_flash.h>
+#include <bcm63xx_regs.h>
+#include <bcm63xx_io.h>
+
+static struct mtd_partition mtd_partitions[] = {
+	{
+		.name		= "cfe",
+		.offset		= 0x0,
+		.size		= 0x40000,
+	}
+};
+
+static const char *bcm63xx_part_types[] = { "bcm63xxpart", NULL };
+
+static struct physmap_flash_data flash_data = {
+	.width			= 2,
+	.parts			= mtd_partitions,
+	.part_probe_types	= bcm63xx_part_types,
+};
+
+static struct resource mtd_resources[] = {
+	{
+		.start		= 0,	/* filled at runtime */
+		.end		= 0,	/* filled at runtime */
+		.flags		= IORESOURCE_MEM,
+	}
+};
+
+static struct platform_device mtd_dev = {
+	.name			= "physmap-flash",
+	.resource		= mtd_resources,
+	.num_resources		= ARRAY_SIZE(mtd_resources),
+	.dev			= {
+		.platform_data	= &flash_data,
+	},
+};
+
+static int __init bcm63xx_detect_flash_type(void)
+{
+	u32 val;
+
+	switch (bcm63xx_get_cpu_id()) {
+	case BCM6328_CPU_ID:
+		val = bcm_misc_readl(MISC_STRAPBUS_6328_REG);
+		if (val & STRAPBUS_6328_BOOT_SEL_SERIAL)
+			return BCM63XX_FLASH_TYPE_SERIAL;
+		else
+			return BCM63XX_FLASH_TYPE_NAND;
+	case BCM6338_CPU_ID:
+	case BCM6345_CPU_ID:
+	case BCM6348_CPU_ID:
+		/* no way to auto detect so assume parallel */
+		return BCM63XX_FLASH_TYPE_PARALLEL;
+	case BCM6358_CPU_ID:
+		val = bcm_gpio_readl(GPIO_STRAPBUS_REG);
+		if (val & STRAPBUS_6358_BOOT_SEL_PARALLEL)
+			return BCM63XX_FLASH_TYPE_PARALLEL;
+		else
+			return BCM63XX_FLASH_TYPE_SERIAL;
+	case BCM6368_CPU_ID:
+		val = bcm_gpio_readl(GPIO_STRAPBUS_REG);
+		switch (val & STRAPBUS_6368_BOOT_SEL_MASK) {
+		case STRAPBUS_6368_BOOT_SEL_NAND:
+			return BCM63XX_FLASH_TYPE_NAND;
+		case STRAPBUS_6368_BOOT_SEL_SERIAL:
+			return BCM63XX_FLASH_TYPE_SERIAL;
+		case STRAPBUS_6368_BOOT_SEL_PARALLEL:
+			return BCM63XX_FLASH_TYPE_PARALLEL;
+		}
+	default:
+		return -EINVAL;
+	}
+}
+
+int __init bcm63xx_flash_register(void)
+{
+	int flash_type;
+	u32 val;
+
+	flash_type = bcm63xx_detect_flash_type();
+
+	switch (flash_type) {
+	case BCM63XX_FLASH_TYPE_PARALLEL:
+		/* read base address of boot chip select (0) */
+		val = bcm_mpi_readl(MPI_CSBASE_REG(0));
+		val &= MPI_CSBASE_BASE_MASK;
+
+		mtd_resources[0].start = val;
+		mtd_resources[0].end = 0x1FFFFFFF;
+
+		return platform_device_register(&mtd_dev);
+	case BCM63XX_FLASH_TYPE_SERIAL:
+		pr_warn("unsupported serial flash detected\n");
+		return -ENODEV;
+	case BCM63XX_FLASH_TYPE_NAND:
+		pr_warn("unsupported NAND flash detected\n");
+		return -ENODEV;
+	default:
+		pr_err("flash detection failed for BCM%x: %d\n",
+		       bcm63xx_get_cpu_id(), flash_type);
+		return -ENODEV;
+	}
+}
diff --git a/arch/mips/bcm63xx/dev-rng.c b/arch/mips/bcm63xx/dev-rng.c
new file mode 100644
index 000000000000..d277b4dc6c68
--- /dev/null
+++ b/arch/mips/bcm63xx/dev-rng.c
@@ -0,0 +1,40 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2011 Florian Fainelli <florian@openwrt.org>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <bcm63xx_cpu.h>
+
+static struct resource rng_resources[] = {
+	{
+		.start		= -1, /* filled at runtime */
+		.end		= -1, /* filled at runtime */
+		.flags		= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device bcm63xx_rng_device = {
+	.name		= "bcm63xx-rng",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(rng_resources),
+	.resource	= rng_resources,
+};
+
+int __init bcm63xx_rng_register(void)
+{
+	if (!BCMCPU_IS_6368())
+		return -ENODEV;
+
+	rng_resources[0].start = bcm63xx_regset_address(RSET_RNG);
+	rng_resources[0].end = rng_resources[0].start;
+	rng_resources[0].end += RSET_RNG_SIZE - 1;
+
+	return platform_device_register(&bcm63xx_rng_device);
+}
+arch_initcall(bcm63xx_rng_register);
diff --git a/arch/mips/bcm63xx/dev-spi.c b/arch/mips/bcm63xx/dev-spi.c
new file mode 100644
index 000000000000..e39f73048d4f
--- /dev/null
+++ b/arch/mips/bcm63xx/dev-spi.c
@@ -0,0 +1,119 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2009-2011 Florian Fainelli <florian@openwrt.org>
+ * Copyright (C) 2010 Tanguy Bouzeloc <tanguy.bouzeloc@efixo.com>
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/platform_device.h>
+#include <linux/err.h>
+#include <linux/clk.h>
+
+#include <bcm63xx_cpu.h>
+#include <bcm63xx_dev_spi.h>
+#include <bcm63xx_regs.h>
+
+#ifdef BCMCPU_RUNTIME_DETECT
+/*
+ * register offsets
+ */
+static const unsigned long bcm6338_regs_spi[] = {
+	__GEN_SPI_REGS_TABLE(6338)
+};
+
+static const unsigned long bcm6348_regs_spi[] = {
+	__GEN_SPI_REGS_TABLE(6348)
+};
+
+static const unsigned long bcm6358_regs_spi[] = {
+	__GEN_SPI_REGS_TABLE(6358)
+};
+
+static const unsigned long bcm6368_regs_spi[] = {
+	__GEN_SPI_REGS_TABLE(6368)
+};
+
+const unsigned long *bcm63xx_regs_spi;
+EXPORT_SYMBOL(bcm63xx_regs_spi);
+
+static __init void bcm63xx_spi_regs_init(void)
+{
+	if (BCMCPU_IS_6338())
+		bcm63xx_regs_spi = bcm6338_regs_spi;
+	if (BCMCPU_IS_6348())
+		bcm63xx_regs_spi = bcm6348_regs_spi;
+	if (BCMCPU_IS_6358())
+		bcm63xx_regs_spi = bcm6358_regs_spi;
+	if (BCMCPU_IS_6368())
+		bcm63xx_regs_spi = bcm6368_regs_spi;
+}
+#else
+static __init void bcm63xx_spi_regs_init(void) { }
+#endif
+
+static struct resource spi_resources[] = {
+	{
+		.start		= -1, /* filled at runtime */
+		.end		= -1, /* filled at runtime */
+		.flags		= IORESOURCE_MEM,
+	},
+	{
+		.start		= -1, /* filled at runtime */
+		.flags		= IORESOURCE_IRQ,
+	},
+};
+
+static struct bcm63xx_spi_pdata spi_pdata = {
+	.bus_num		= 0,
+	.num_chipselect		= 8,
+};
+
+static struct platform_device bcm63xx_spi_device = {
+	.name		= "bcm63xx-spi",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(spi_resources),
+	.resource	= spi_resources,
+	.dev		= {
+		.platform_data = &spi_pdata,
+	},
+};
+
+int __init bcm63xx_spi_register(void)
+{
+	struct clk *periph_clk;
+
+	if (BCMCPU_IS_6328() || BCMCPU_IS_6345())
+		return -ENODEV;
+
+	periph_clk = clk_get(NULL, "periph");
+	if (IS_ERR(periph_clk)) {
+		pr_err("unable to get periph clock\n");
+		return -ENODEV;
+	}
+
+	/* Set bus frequency */
+	spi_pdata.speed_hz = clk_get_rate(periph_clk);
+
+	spi_resources[0].start = bcm63xx_regset_address(RSET_SPI);
+	spi_resources[0].end = spi_resources[0].start;
+	spi_resources[1].start = bcm63xx_get_irq_number(IRQ_SPI);
+
+	if (BCMCPU_IS_6338() || BCMCPU_IS_6348()) {
+		spi_resources[0].end += BCM_6338_RSET_SPI_SIZE - 1;
+		spi_pdata.fifo_size = SPI_6338_MSG_DATA_SIZE;
+	}
+
+	if (BCMCPU_IS_6358() || BCMCPU_IS_6368()) {
+		spi_resources[0].end += BCM_6358_RSET_SPI_SIZE - 1;
+		spi_pdata.fifo_size = SPI_6358_MSG_DATA_SIZE;
+	}
+
+	bcm63xx_spi_regs_init();
+
+	return platform_device_register(&bcm63xx_spi_device);
+}
diff --git a/arch/mips/bcm63xx/dev-wdt.c b/arch/mips/bcm63xx/dev-wdt.c
index 3e6c716a4c11..2a2346a99bcb 100644
--- a/arch/mips/bcm63xx/dev-wdt.c
+++ b/arch/mips/bcm63xx/dev-wdt.c
@@ -21,7 +21,7 @@ static struct resource wdt_resources[] = {
 
 static struct platform_device bcm63xx_wdt_device = {
 	.name		= "bcm63xx-wdt",
-	.id		= 0,
+	.id		= -1,
 	.num_resources	= ARRAY_SIZE(wdt_resources),
 	.resource	= wdt_resources,
 };
diff --git a/arch/mips/bcm63xx/irq.c b/arch/mips/bcm63xx/irq.c
index 9a216a451d92..18e051ad18a5 100644
--- a/arch/mips/bcm63xx/irq.c
+++ b/arch/mips/bcm63xx/irq.c
@@ -27,6 +27,17 @@ static void __internal_irq_unmask_32(unsigned int irq) __maybe_unused;
 static void __internal_irq_unmask_64(unsigned int irq) __maybe_unused;
 
 #ifndef BCMCPU_RUNTIME_DETECT
+#ifdef CONFIG_BCM63XX_CPU_6328
+#define irq_stat_reg		PERF_IRQSTAT_6328_REG
+#define irq_mask_reg		PERF_IRQMASK_6328_REG
+#define irq_bits		64
+#define is_ext_irq_cascaded	1
+#define ext_irq_start		(BCM_6328_EXT_IRQ0 - IRQ_INTERNAL_BASE)
+#define ext_irq_end		(BCM_6328_EXT_IRQ3 - IRQ_INTERNAL_BASE)
+#define ext_irq_count		4
+#define ext_irq_cfg_reg1	PERF_EXTIRQ_CFG_REG_6328
+#define ext_irq_cfg_reg2	0
+#endif
 #ifdef CONFIG_BCM63XX_CPU_6338
 #define irq_stat_reg		PERF_IRQSTAT_6338_REG
 #define irq_mask_reg		PERF_IRQMASK_6338_REG
@@ -118,6 +129,16 @@ static void bcm63xx_init_irq(void)
 	irq_mask_addr = bcm63xx_regset_address(RSET_PERF);
 
 	switch (bcm63xx_get_cpu_id()) {
+	case BCM6328_CPU_ID:
+		irq_stat_addr += PERF_IRQSTAT_6328_REG;
+		irq_mask_addr += PERF_IRQMASK_6328_REG;
+		irq_bits = 64;
+		ext_irq_count = 4;
+		is_ext_irq_cascaded = 1;
+		ext_irq_start = BCM_6328_EXT_IRQ0 - IRQ_INTERNAL_BASE;
+		ext_irq_end = BCM_6328_EXT_IRQ3 - IRQ_INTERNAL_BASE;
+		ext_irq_cfg_reg1 = PERF_EXTIRQ_CFG_REG_6328;
+		break;
 	case BCM6338_CPU_ID:
 		irq_stat_addr += PERF_IRQSTAT_6338_REG;
 		irq_mask_addr += PERF_IRQMASK_6338_REG;
diff --git a/arch/mips/bcm63xx/prom.c b/arch/mips/bcm63xx/prom.c
index 99d7f405cbeb..10eaff458071 100644
--- a/arch/mips/bcm63xx/prom.c
+++ b/arch/mips/bcm63xx/prom.c
@@ -26,7 +26,9 @@ void __init prom_init(void)
 	bcm_wdt_writel(WDT_STOP_2, WDT_CTL_REG);
 
 	/* disable all hardware blocks clock for now */
-	if (BCMCPU_IS_6338())
+	if (BCMCPU_IS_6328())
+		mask = CKCTL_6328_ALL_SAFE_EN;
+	else if (BCMCPU_IS_6338())
 		mask = CKCTL_6338_ALL_SAFE_EN;
 	else if (BCMCPU_IS_6345())
 		mask = CKCTL_6345_ALL_SAFE_EN;
diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c
index 356b05583e14..0e74a13639cd 100644
--- a/arch/mips/bcm63xx/setup.c
+++ b/arch/mips/bcm63xx/setup.c
@@ -68,6 +68,9 @@ void bcm63xx_machine_reboot(void)
 
 	/* mask and clear all external irq */
 	switch (bcm63xx_get_cpu_id()) {
+	case BCM6328_CPU_ID:
+		perf_regs[0] = PERF_EXTIRQ_CFG_REG_6328;
+		break;
 	case BCM6338_CPU_ID:
 		perf_regs[0] = PERF_EXTIRQ_CFG_REG_6338;
 		break;
@@ -95,9 +98,13 @@ void bcm63xx_machine_reboot(void)
 		bcm6348_a1_reboot();
 
 	printk(KERN_INFO "triggering watchdog soft-reset...\n");
-	reg = bcm_perf_readl(PERF_SYS_PLL_CTL_REG);
-	reg |= SYS_PLL_SOFT_RESET;
-	bcm_perf_writel(reg, PERF_SYS_PLL_CTL_REG);
+	if (BCMCPU_IS_6328()) {
+		bcm_wdt_writel(1, WDT_SOFTRESET_REG);
+	} else {
+		reg = bcm_perf_readl(PERF_SYS_PLL_CTL_REG);
+		reg |= SYS_PLL_SOFT_RESET;
+		bcm_perf_writel(reg, PERF_SYS_PLL_CTL_REG);
+	}
 	while (1)
 		;
 }
diff --git a/arch/mips/boot/compressed/Makefile b/arch/mips/boot/compressed/Makefile
index 5042d51b0512..c2a3fb0ffc87 100644
--- a/arch/mips/boot/compressed/Makefile
+++ b/arch/mips/boot/compressed/Makefile
@@ -58,8 +58,12 @@ $(obj)/piggy.o: $(obj)/dummy.o $(obj)/vmlinux.bin.z FORCE
 # Calculate the load address of the compressed kernel image
 hostprogs-y := calc_vmlinuz_load_addr
 
+ifeq ($(CONFIG_MACH_JZ4740),y)
+VMLINUZ_LOAD_ADDRESS := 0x80600000
+else
 VMLINUZ_LOAD_ADDRESS = $(shell $(obj)/calc_vmlinuz_load_addr \
 		$(obj)/vmlinux.bin $(VMLINUX_LOAD_ADDRESS))
+endif
 
 vmlinuzobjs-y += $(obj)/piggy.o
 
diff --git a/arch/mips/boot/compressed/uart-16550.c b/arch/mips/boot/compressed/uart-16550.c
index c9caaf4fbf60..1c7b739b6a1d 100644
--- a/arch/mips/boot/compressed/uart-16550.c
+++ b/arch/mips/boot/compressed/uart-16550.c
@@ -18,6 +18,11 @@
 #define PORT(offset) (CKSEG1ADDR(AR7_REGS_UART0) + (4 * offset))
 #endif
 
+#ifdef CONFIG_MACH_JZ4740
+#define UART0_BASE  0xB0030000
+#define PORT(offset) (UART0_BASE + (4 * offset))
+#endif
+
 #ifndef PORT
 #error please define the serial port address for your own machine
 #endif
diff --git a/arch/mips/cavium-octeon/.gitignore b/arch/mips/cavium-octeon/.gitignore
new file mode 100644
index 000000000000..39c968605ff6
--- /dev/null
+++ b/arch/mips/cavium-octeon/.gitignore
@@ -0,0 +1,2 @@
+*.dtb.S
+*.dtb
diff --git a/arch/mips/cavium-octeon/Makefile b/arch/mips/cavium-octeon/Makefile
index 19eb0434269f..bc96e2908f14 100644
--- a/arch/mips/cavium-octeon/Makefile
+++ b/arch/mips/cavium-octeon/Makefile
@@ -9,9 +9,25 @@
 # Copyright (C) 2005-2009 Cavium Networks
 #
 
+CFLAGS_octeon-platform.o = -I$(src)/../../../scripts/dtc/libfdt
+CFLAGS_setup.o = -I$(src)/../../../scripts/dtc/libfdt
+
 obj-y := cpu.o setup.o serial.o octeon-platform.o octeon-irq.o csrc-octeon.o
 obj-y += dma-octeon.o flash_setup.o
 obj-y += octeon-memcpy.o
 obj-y += executive/
 
 obj-$(CONFIG_SMP)                     += smp.o
+
+DTS_FILES = octeon_3xxx.dts octeon_68xx.dts
+DTB_FILES = $(patsubst %.dts, %.dtb, $(DTS_FILES))
+
+obj-y += $(patsubst %.dts, %.dtb.o, $(DTS_FILES))
+
+$(obj)/%.dtb: $(src)/%.dts FORCE
+	$(call if_changed_dep,dtc)
+
+# Let's keep the .dtb files around in case we want to look at them.
+.SECONDARY:  $(addprefix $(obj)/, $(DTB_FILES))
+
+clean-files += $(DTB_FILES) $(patsubst %.dtb, %.dtb.S, $(DTB_FILES))
diff --git a/arch/mips/cavium-octeon/executive/cvmx-fpa.c b/arch/mips/cavium-octeon/executive/cvmx-fpa.c
deleted file mode 100644
index ad44b8bd8057..000000000000
--- a/arch/mips/cavium-octeon/executive/cvmx-fpa.c
+++ /dev/null
@@ -1,183 +0,0 @@
-/***********************license start***************
- * Author: Cavium Networks
- *
- * Contact: support@caviumnetworks.com
- * This file is part of the OCTEON SDK
- *
- * Copyright (c) 2003-2008 Cavium Networks
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- *
- * This file is distributed in the hope that it will be useful, but
- * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this file; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- * or visit http://www.gnu.org/licenses/.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium Networks for more information
- ***********************license end**************************************/
-
-/**
- * @file
- *
- * Support library for the hardware Free Pool Allocator.
- *
- *
- */
-
-#include "cvmx-config.h"
-#include "cvmx.h"
-#include "cvmx-fpa.h"
-#include "cvmx-ipd.h"
-
-/**
- * Current state of all the pools. Use access functions
- * instead of using it directly.
- */
-CVMX_SHARED cvmx_fpa_pool_info_t cvmx_fpa_pool_info[CVMX_FPA_NUM_POOLS];
-
-/**
- * Setup a FPA pool to control a new block of memory. The
- * buffer pointer must be a physical address.
- *
- * @pool:       Pool to initialize
- *                   0 <= pool < 8
- * @name:       Constant character string to name this pool.
- *                   String is not copied.
- * @buffer:     Pointer to the block of memory to use. This must be
- *                   accessible by all processors and external hardware.
- * @block_size: Size for each block controlled by the FPA
- * @num_blocks: Number of blocks
- *
- * Returns 0 on Success,
- *         -1 on failure
- */
-int cvmx_fpa_setup_pool(uint64_t pool, const char *name, void *buffer,
-			uint64_t block_size, uint64_t num_blocks)
-{
-	char *ptr;
-	if (!buffer) {
-		cvmx_dprintf
-		    ("ERROR: cvmx_fpa_setup_pool: NULL buffer pointer!\n");
-		return -1;
-	}
-	if (pool >= CVMX_FPA_NUM_POOLS) {
-		cvmx_dprintf("ERROR: cvmx_fpa_setup_pool: Illegal pool!\n");
-		return -1;
-	}
-
-	if (block_size < CVMX_FPA_MIN_BLOCK_SIZE) {
-		cvmx_dprintf
-		    ("ERROR: cvmx_fpa_setup_pool: Block size too small.\n");
-		return -1;
-	}
-
-	if (((unsigned long)buffer & (CVMX_FPA_ALIGNMENT - 1)) != 0) {
-		cvmx_dprintf
-		    ("ERROR: cvmx_fpa_setup_pool: Buffer not aligned properly.\n");
-		return -1;
-	}
-
-	cvmx_fpa_pool_info[pool].name = name;
-	cvmx_fpa_pool_info[pool].size = block_size;
-	cvmx_fpa_pool_info[pool].starting_element_count = num_blocks;
-	cvmx_fpa_pool_info[pool].base = buffer;
-
-	ptr = (char *)buffer;
-	while (num_blocks--) {
-		cvmx_fpa_free(ptr, pool, 0);
-		ptr += block_size;
-	}
-	return 0;
-}
-
-/**
- * Shutdown a Memory pool and validate that it had all of
- * the buffers originally placed in it.
- *
- * @pool:   Pool to shutdown
- * Returns Zero on success
- *         - Positive is count of missing buffers
- *         - Negative is too many buffers or corrupted pointers
- */
-uint64_t cvmx_fpa_shutdown_pool(uint64_t pool)
-{
-	uint64_t errors = 0;
-	uint64_t count = 0;
-	uint64_t base = cvmx_ptr_to_phys(cvmx_fpa_pool_info[pool].base);
-	uint64_t finish =
-	    base +
-	    cvmx_fpa_pool_info[pool].size *
-	    cvmx_fpa_pool_info[pool].starting_element_count;
-	void *ptr;
-	uint64_t address;
-
-	count = 0;
-	do {
-		ptr = cvmx_fpa_alloc(pool);
-		if (ptr)
-			address = cvmx_ptr_to_phys(ptr);
-		else
-			address = 0;
-		if (address) {
-			if ((address >= base) && (address < finish) &&
-			    (((address -
-			       base) % cvmx_fpa_pool_info[pool].size) == 0)) {
-				count++;
-			} else {
-				cvmx_dprintf
-				    ("ERROR: cvmx_fpa_shutdown_pool: Illegal address 0x%llx in pool %s(%d)\n",
-				     (unsigned long long)address,
-				     cvmx_fpa_pool_info[pool].name, (int)pool);
-				errors++;
-			}
-		}
-	} while (address);
-
-#ifdef CVMX_ENABLE_PKO_FUNCTIONS
-	if (pool == 0)
-		cvmx_ipd_free_ptr();
-#endif
-
-	if (errors) {
-		cvmx_dprintf
-		    ("ERROR: cvmx_fpa_shutdown_pool: Pool %s(%d) started at 0x%llx, ended at 0x%llx, with a step of 0x%llx\n",
-		     cvmx_fpa_pool_info[pool].name, (int)pool,
-		     (unsigned long long)base, (unsigned long long)finish,
-		     (unsigned long long)cvmx_fpa_pool_info[pool].size);
-		return -errors;
-	} else
-		return 0;
-}
-
-uint64_t cvmx_fpa_get_block_size(uint64_t pool)
-{
-	switch (pool) {
-	case 0:
-		return CVMX_FPA_POOL_0_SIZE;
-	case 1:
-		return CVMX_FPA_POOL_1_SIZE;
-	case 2:
-		return CVMX_FPA_POOL_2_SIZE;
-	case 3:
-		return CVMX_FPA_POOL_3_SIZE;
-	case 4:
-		return CVMX_FPA_POOL_4_SIZE;
-	case 5:
-		return CVMX_FPA_POOL_5_SIZE;
-	case 6:
-		return CVMX_FPA_POOL_6_SIZE;
-	case 7:
-		return CVMX_FPA_POOL_7_SIZE;
-	default:
-		return 0;
-	}
-}
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-fpa.c b/arch/mips/cavium-octeon/executive/cvmx-helper-fpa.c
deleted file mode 100644
index c239e5f4ab9a..000000000000
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-fpa.c
+++ /dev/null
@@ -1,243 +0,0 @@
-/***********************license start***************
- * Author: Cavium Networks
- *
- * Contact: support@caviumnetworks.com
- * This file is part of the OCTEON SDK
- *
- * Copyright (c) 2003-2008 Cavium Networks
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- *
- * This file is distributed in the hope that it will be useful, but
- * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this file; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- * or visit http://www.gnu.org/licenses/.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium Networks for more information
- ***********************license end**************************************/
-
-/**
- * @file
- *
- * Helper functions for FPA setup.
- *
- */
-#include "executive-config.h"
-#include "cvmx-config.h"
-#include "cvmx.h"
-#include "cvmx-bootmem.h"
-#include "cvmx-fpa.h"
-#include "cvmx-helper-fpa.h"
-
-/**
- * Allocate memory for and initialize a single FPA pool.
- *
- * @pool:    Pool to initialize
- * @buffer_size:  Size of buffers to allocate in bytes
- * @buffers: Number of buffers to put in the pool. Zero is allowed
- * @name:    String name of the pool for debugging purposes
- * Returns Zero on success, non-zero on failure
- */
-static int __cvmx_helper_initialize_fpa_pool(int pool, uint64_t buffer_size,
-					     uint64_t buffers, const char *name)
-{
-	uint64_t current_num;
-	void *memory;
-	uint64_t align = CVMX_CACHE_LINE_SIZE;
-
-	/*
-	 * Align the allocation so that power of 2 size buffers are
-	 * naturally aligned.
-	 */
-	while (align < buffer_size)
-		align = align << 1;
-
-	if (buffers == 0)
-		return 0;
-
-	current_num = cvmx_read_csr(CVMX_FPA_QUEX_AVAILABLE(pool));
-	if (current_num) {
-		cvmx_dprintf("Fpa pool %d(%s) already has %llu buffers. "
-			     "Skipping setup.\n",
-		     pool, name, (unsigned long long)current_num);
-		return 0;
-	}
-
-	memory = cvmx_bootmem_alloc(buffer_size * buffers, align);
-	if (memory == NULL) {
-		cvmx_dprintf("Out of memory initializing fpa pool %d(%s).\n",
-			     pool, name);
-		return -1;
-	}
-	cvmx_fpa_setup_pool(pool, name, memory, buffer_size, buffers);
-	return 0;
-}
-
-/**
- * Allocate memory and initialize the FPA pools using memory
- * from cvmx-bootmem. Specifying zero for the number of
- * buffers will cause that FPA pool to not be setup. This is
- * useful if you aren't using some of the hardware and want
- * to save memory. Use cvmx_helper_initialize_fpa instead of
- * this function directly.
- *
- * @pip_pool: Should always be CVMX_FPA_PACKET_POOL
- * @pip_size: Should always be CVMX_FPA_PACKET_POOL_SIZE
- * @pip_buffers:
- *                 Number of packet buffers.
- * @wqe_pool: Should always be CVMX_FPA_WQE_POOL
- * @wqe_size: Should always be CVMX_FPA_WQE_POOL_SIZE
- * @wqe_entries:
- *                 Number of work queue entries
- * @pko_pool: Should always be CVMX_FPA_OUTPUT_BUFFER_POOL
- * @pko_size: Should always be CVMX_FPA_OUTPUT_BUFFER_POOL_SIZE
- * @pko_buffers:
- *                 PKO Command buffers. You should at minimum have two per
- *                 each PKO queue.
- * @tim_pool: Should always be CVMX_FPA_TIMER_POOL
- * @tim_size: Should always be CVMX_FPA_TIMER_POOL_SIZE
- * @tim_buffers:
- *                 TIM ring buffer command queues. At least two per timer bucket
- *                 is recommened.
- * @dfa_pool: Should always be CVMX_FPA_DFA_POOL
- * @dfa_size: Should always be CVMX_FPA_DFA_POOL_SIZE
- * @dfa_buffers:
- *                 DFA command buffer. A relatively small (32 for example)
- *                 number should work.
- * Returns Zero on success, non-zero if out of memory
- */
-static int __cvmx_helper_initialize_fpa(int pip_pool, int pip_size,
-					int pip_buffers, int wqe_pool,
-					int wqe_size, int wqe_entries,
-					int pko_pool, int pko_size,
-					int pko_buffers, int tim_pool,
-					int tim_size, int tim_buffers,
-					int dfa_pool, int dfa_size,
-					int dfa_buffers)
-{
-	int status;
-
-	cvmx_fpa_enable();
-
-	if ((pip_buffers > 0) && (pip_buffers <= 64))
-		cvmx_dprintf
-		    ("Warning: %d packet buffers may not be enough for hardware"
-		     " prefetch. 65 or more is recommended.\n", pip_buffers);
-
-	if (pip_pool >= 0) {
-		status =
-		    __cvmx_helper_initialize_fpa_pool(pip_pool, pip_size,
-						      pip_buffers,
-						      "Packet Buffers");
-		if (status)
-			return status;
-	}
-
-	if (wqe_pool >= 0) {
-		status =
-		    __cvmx_helper_initialize_fpa_pool(wqe_pool, wqe_size,
-						      wqe_entries,
-						      "Work Queue Entries");
-		if (status)
-			return status;
-	}
-
-	if (pko_pool >= 0) {
-		status =
-		    __cvmx_helper_initialize_fpa_pool(pko_pool, pko_size,
-						      pko_buffers,
-						      "PKO Command Buffers");
-		if (status)
-			return status;
-	}
-
-	if (tim_pool >= 0) {
-		status =
-		    __cvmx_helper_initialize_fpa_pool(tim_pool, tim_size,
-						      tim_buffers,
-						      "TIM Command Buffers");
-		if (status)
-			return status;
-	}
-
-	if (dfa_pool >= 0) {
-		status =
-		    __cvmx_helper_initialize_fpa_pool(dfa_pool, dfa_size,
-						      dfa_buffers,
-						      "DFA Command Buffers");
-		if (status)
-			return status;
-	}
-
-	return 0;
-}
-
-/**
- * Allocate memory and initialize the FPA pools using memory
- * from cvmx-bootmem. Sizes of each element in the pools is
- * controlled by the cvmx-config.h header file. Specifying
- * zero for any parameter will cause that FPA pool to not be
- * setup. This is useful if you aren't using some of the
- * hardware and want to save memory.
- *
- * @packet_buffers:
- *               Number of packet buffers to allocate
- * @work_queue_entries:
- *               Number of work queue entries
- * @pko_buffers:
- *               PKO Command buffers. You should at minimum have two per
- *               each PKO queue.
- * @tim_buffers:
- *               TIM ring buffer command queues. At least two per timer bucket
- *               is recommened.
- * @dfa_buffers:
- *               DFA command buffer. A relatively small (32 for example)
- *               number should work.
- * Returns Zero on success, non-zero if out of memory
- */
-int cvmx_helper_initialize_fpa(int packet_buffers, int work_queue_entries,
-			       int pko_buffers, int tim_buffers,
-			       int dfa_buffers)
-{
-#ifndef CVMX_FPA_PACKET_POOL
-#define CVMX_FPA_PACKET_POOL -1
-#define CVMX_FPA_PACKET_POOL_SIZE 0
-#endif
-#ifndef CVMX_FPA_WQE_POOL
-#define CVMX_FPA_WQE_POOL -1
-#define CVMX_FPA_WQE_POOL_SIZE 0
-#endif
-#ifndef CVMX_FPA_OUTPUT_BUFFER_POOL
-#define CVMX_FPA_OUTPUT_BUFFER_POOL -1
-#define CVMX_FPA_OUTPUT_BUFFER_POOL_SIZE 0
-#endif
-#ifndef CVMX_FPA_TIMER_POOL
-#define CVMX_FPA_TIMER_POOL -1
-#define CVMX_FPA_TIMER_POOL_SIZE 0
-#endif
-#ifndef CVMX_FPA_DFA_POOL
-#define CVMX_FPA_DFA_POOL -1
-#define CVMX_FPA_DFA_POOL_SIZE 0
-#endif
-	return __cvmx_helper_initialize_fpa(CVMX_FPA_PACKET_POOL,
-					    CVMX_FPA_PACKET_POOL_SIZE,
-					    packet_buffers, CVMX_FPA_WQE_POOL,
-					    CVMX_FPA_WQE_POOL_SIZE,
-					    work_queue_entries,
-					    CVMX_FPA_OUTPUT_BUFFER_POOL,
-					    CVMX_FPA_OUTPUT_BUFFER_POOL_SIZE,
-					    pko_buffers, CVMX_FPA_TIMER_POOL,
-					    CVMX_FPA_TIMER_POOL_SIZE,
-					    tim_buffers, CVMX_FPA_DFA_POOL,
-					    CVMX_FPA_DFA_POOL_SIZE,
-					    dfa_buffers);
-}
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index ffd4ae660f79..7fb1f222b8a5 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -3,14 +3,17 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 2004-2008, 2009, 2010, 2011 Cavium Networks
+ * Copyright (C) 2004-2012 Cavium, Inc.
  */
 
 #include <linux/interrupt.h>
+#include <linux/irqdomain.h>
 #include <linux/bitops.h>
 #include <linux/percpu.h>
+#include <linux/slab.h>
 #include <linux/irq.h>
 #include <linux/smp.h>
+#include <linux/of.h>
 
 #include <asm/octeon/octeon.h>
 
@@ -42,9 +45,9 @@ struct octeon_core_chip_data {
 
 static struct octeon_core_chip_data octeon_irq_core_chip_data[MIPS_CORE_IRQ_LINES];
 
-static void __init octeon_irq_set_ciu_mapping(int irq, int line, int bit,
-					      struct irq_chip *chip,
-					      irq_flow_handler_t handler)
+static void octeon_irq_set_ciu_mapping(int irq, int line, int bit,
+				       struct irq_chip *chip,
+				       irq_flow_handler_t handler)
 {
 	union octeon_ciu_chip_data cd;
 
@@ -505,6 +508,85 @@ static void octeon_irq_ciu_enable_all_v2(struct irq_data *data)
 	}
 }
 
+static void octeon_irq_gpio_setup(struct irq_data *data)
+{
+	union cvmx_gpio_bit_cfgx cfg;
+	union octeon_ciu_chip_data cd;
+	u32 t = irqd_get_trigger_type(data);
+
+	cd.p = irq_data_get_irq_chip_data(data);
+
+	cfg.u64 = 0;
+	cfg.s.int_en = 1;
+	cfg.s.int_type = (t & IRQ_TYPE_EDGE_BOTH) != 0;
+	cfg.s.rx_xor = (t & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_EDGE_FALLING)) != 0;
+
+	/* 140 nS glitch filter*/
+	cfg.s.fil_cnt = 7;
+	cfg.s.fil_sel = 3;
+
+	cvmx_write_csr(CVMX_GPIO_BIT_CFGX(cd.s.bit - 16), cfg.u64);
+}
+
+static void octeon_irq_ciu_enable_gpio_v2(struct irq_data *data)
+{
+	octeon_irq_gpio_setup(data);
+	octeon_irq_ciu_enable_v2(data);
+}
+
+static void octeon_irq_ciu_enable_gpio(struct irq_data *data)
+{
+	octeon_irq_gpio_setup(data);
+	octeon_irq_ciu_enable(data);
+}
+
+static int octeon_irq_ciu_gpio_set_type(struct irq_data *data, unsigned int t)
+{
+	irqd_set_trigger_type(data, t);
+	octeon_irq_gpio_setup(data);
+
+	return IRQ_SET_MASK_OK;
+}
+
+static void octeon_irq_ciu_disable_gpio_v2(struct irq_data *data)
+{
+	union octeon_ciu_chip_data cd;
+
+	cd.p = irq_data_get_irq_chip_data(data);
+	cvmx_write_csr(CVMX_GPIO_BIT_CFGX(cd.s.bit - 16), 0);
+
+	octeon_irq_ciu_disable_all_v2(data);
+}
+
+static void octeon_irq_ciu_disable_gpio(struct irq_data *data)
+{
+	union octeon_ciu_chip_data cd;
+
+	cd.p = irq_data_get_irq_chip_data(data);
+	cvmx_write_csr(CVMX_GPIO_BIT_CFGX(cd.s.bit - 16), 0);
+
+	octeon_irq_ciu_disable_all(data);
+}
+
+static void octeon_irq_ciu_gpio_ack(struct irq_data *data)
+{
+	union octeon_ciu_chip_data cd;
+	u64 mask;
+
+	cd.p = irq_data_get_irq_chip_data(data);
+	mask = 1ull << (cd.s.bit - 16);
+
+	cvmx_write_csr(CVMX_GPIO_INT_CLR, mask);
+}
+
+static void octeon_irq_handle_gpio(unsigned int irq, struct irq_desc *desc)
+{
+	if (irqd_get_trigger_type(irq_desc_get_irq_data(desc)) & IRQ_TYPE_EDGE_BOTH)
+		handle_edge_irq(irq, desc);
+	else
+		handle_level_irq(irq, desc);
+}
+
 #ifdef CONFIG_SMP
 
 static void octeon_irq_cpu_offline_ciu(struct irq_data *data)
@@ -650,18 +732,6 @@ static struct irq_chip octeon_irq_chip_ciu_v2 = {
 	.name = "CIU",
 	.irq_enable = octeon_irq_ciu_enable_v2,
 	.irq_disable = octeon_irq_ciu_disable_all_v2,
-	.irq_mask = octeon_irq_ciu_disable_local_v2,
-	.irq_unmask = octeon_irq_ciu_enable_v2,
-#ifdef CONFIG_SMP
-	.irq_set_affinity = octeon_irq_ciu_set_affinity_v2,
-	.irq_cpu_offline = octeon_irq_cpu_offline_ciu,
-#endif
-};
-
-static struct irq_chip octeon_irq_chip_ciu_edge_v2 = {
-	.name = "CIU-E",
-	.irq_enable = octeon_irq_ciu_enable_v2,
-	.irq_disable = octeon_irq_ciu_disable_all_v2,
 	.irq_ack = octeon_irq_ciu_ack,
 	.irq_mask = octeon_irq_ciu_disable_local_v2,
 	.irq_unmask = octeon_irq_ciu_enable_v2,
@@ -675,19 +745,8 @@ static struct irq_chip octeon_irq_chip_ciu = {
 	.name = "CIU",
 	.irq_enable = octeon_irq_ciu_enable,
 	.irq_disable = octeon_irq_ciu_disable_all,
-	.irq_mask = octeon_irq_dummy_mask,
-#ifdef CONFIG_SMP
-	.irq_set_affinity = octeon_irq_ciu_set_affinity,
-	.irq_cpu_offline = octeon_irq_cpu_offline_ciu,
-#endif
-};
-
-static struct irq_chip octeon_irq_chip_ciu_edge = {
-	.name = "CIU-E",
-	.irq_enable = octeon_irq_ciu_enable,
-	.irq_disable = octeon_irq_ciu_disable_all,
-	.irq_mask = octeon_irq_dummy_mask,
 	.irq_ack = octeon_irq_ciu_ack,
+	.irq_mask = octeon_irq_dummy_mask,
 #ifdef CONFIG_SMP
 	.irq_set_affinity = octeon_irq_ciu_set_affinity,
 	.irq_cpu_offline = octeon_irq_cpu_offline_ciu,
@@ -717,6 +776,33 @@ static struct irq_chip octeon_irq_chip_ciu_mbox = {
 	.flags = IRQCHIP_ONOFFLINE_ENABLED,
 };
 
+static struct irq_chip octeon_irq_chip_ciu_gpio_v2 = {
+	.name = "CIU-GPIO",
+	.irq_enable = octeon_irq_ciu_enable_gpio_v2,
+	.irq_disable = octeon_irq_ciu_disable_gpio_v2,
+	.irq_ack = octeon_irq_ciu_gpio_ack,
+	.irq_mask = octeon_irq_ciu_disable_local_v2,
+	.irq_unmask = octeon_irq_ciu_enable_v2,
+	.irq_set_type = octeon_irq_ciu_gpio_set_type,
+#ifdef CONFIG_SMP
+	.irq_set_affinity = octeon_irq_ciu_set_affinity_v2,
+#endif
+	.flags = IRQCHIP_SET_TYPE_MASKED,
+};
+
+static struct irq_chip octeon_irq_chip_ciu_gpio = {
+	.name = "CIU-GPIO",
+	.irq_enable = octeon_irq_ciu_enable_gpio,
+	.irq_disable = octeon_irq_ciu_disable_gpio,
+	.irq_mask = octeon_irq_dummy_mask,
+	.irq_ack = octeon_irq_ciu_gpio_ack,
+	.irq_set_type = octeon_irq_ciu_gpio_set_type,
+#ifdef CONFIG_SMP
+	.irq_set_affinity = octeon_irq_ciu_set_affinity,
+#endif
+	.flags = IRQCHIP_SET_TYPE_MASKED,
+};
+
 /*
  * Watchdog interrupts are special.  They are associated with a single
  * core, so we hardwire the affinity to that core.
@@ -764,6 +850,178 @@ static struct irq_chip octeon_irq_chip_ciu_wd = {
 	.irq_mask = octeon_irq_dummy_mask,
 };
 
+static bool octeon_irq_ciu_is_edge(unsigned int line, unsigned int bit)
+{
+	bool edge = false;
+
+	if (line == 0)
+		switch (bit) {
+		case 48 ... 49: /* GMX DRP */
+		case 50: /* IPD_DRP */
+		case 52 ... 55: /* Timers */
+		case 58: /* MPI */
+			edge = true;
+			break;
+		default:
+			break;
+		}
+	else /* line == 1 */
+		switch (bit) {
+		case 47: /* PTP */
+			edge = true;
+			break;
+		default:
+			break;
+		}
+	return edge;
+}
+
+struct octeon_irq_gpio_domain_data {
+	unsigned int base_hwirq;
+};
+
+static int octeon_irq_gpio_xlat(struct irq_domain *d,
+				struct device_node *node,
+				const u32 *intspec,
+				unsigned int intsize,
+				unsigned long *out_hwirq,
+				unsigned int *out_type)
+{
+	unsigned int type;
+	unsigned int pin;
+	unsigned int trigger;
+	struct octeon_irq_gpio_domain_data *gpiod;
+
+	if (d->of_node != node)
+		return -EINVAL;
+
+	if (intsize < 2)
+		return -EINVAL;
+
+	pin = intspec[0];
+	if (pin >= 16)
+		return -EINVAL;
+
+	trigger = intspec[1];
+
+	switch (trigger) {
+	case 1:
+		type = IRQ_TYPE_EDGE_RISING;
+		break;
+	case 2:
+		type = IRQ_TYPE_EDGE_FALLING;
+		break;
+	case 4:
+		type = IRQ_TYPE_LEVEL_HIGH;
+		break;
+	case 8:
+		type = IRQ_TYPE_LEVEL_LOW;
+		break;
+	default:
+		pr_err("Error: (%s) Invalid irq trigger specification: %x\n",
+		       node->name,
+		       trigger);
+		type = IRQ_TYPE_LEVEL_LOW;
+		break;
+	}
+	*out_type = type;
+	gpiod = d->host_data;
+	*out_hwirq = gpiod->base_hwirq + pin;
+
+	return 0;
+}
+
+static int octeon_irq_ciu_xlat(struct irq_domain *d,
+			       struct device_node *node,
+			       const u32 *intspec,
+			       unsigned int intsize,
+			       unsigned long *out_hwirq,
+			       unsigned int *out_type)
+{
+	unsigned int ciu, bit;
+
+	ciu = intspec[0];
+	bit = intspec[1];
+
+	if (ciu > 1 || bit > 63)
+		return -EINVAL;
+
+	/* These are the GPIO lines */
+	if (ciu == 0 && bit >= 16 && bit < 32)
+		return -EINVAL;
+
+	*out_hwirq = (ciu << 6) | bit;
+	*out_type = 0;
+
+	return 0;
+}
+
+static struct irq_chip *octeon_irq_ciu_chip;
+static struct irq_chip *octeon_irq_gpio_chip;
+
+static bool octeon_irq_virq_in_range(unsigned int virq)
+{
+	/* We cannot let it overflow the mapping array. */
+	if (virq < (1ul << 8 * sizeof(octeon_irq_ciu_to_irq[0][0])))
+		return true;
+
+	WARN_ONCE(true, "virq out of range %u.\n", virq);
+	return false;
+}
+
+static int octeon_irq_ciu_map(struct irq_domain *d,
+			      unsigned int virq, irq_hw_number_t hw)
+{
+	unsigned int line = hw >> 6;
+	unsigned int bit = hw & 63;
+
+	if (!octeon_irq_virq_in_range(virq))
+		return -EINVAL;
+
+	if (line > 1 || octeon_irq_ciu_to_irq[line][bit] != 0)
+		return -EINVAL;
+
+	if (octeon_irq_ciu_is_edge(line, bit))
+		octeon_irq_set_ciu_mapping(virq, line, bit,
+					   octeon_irq_ciu_chip,
+					   handle_edge_irq);
+	else
+		octeon_irq_set_ciu_mapping(virq, line, bit,
+					   octeon_irq_ciu_chip,
+					   handle_level_irq);
+
+	return 0;
+}
+
+static int octeon_irq_gpio_map(struct irq_domain *d,
+			       unsigned int virq, irq_hw_number_t hw)
+{
+	unsigned int line = hw >> 6;
+	unsigned int bit = hw & 63;
+
+	if (!octeon_irq_virq_in_range(virq))
+		return -EINVAL;
+
+	if (line > 1 || octeon_irq_ciu_to_irq[line][bit] != 0)
+		return -EINVAL;
+
+	octeon_irq_set_ciu_mapping(virq, line, bit,
+				   octeon_irq_gpio_chip,
+				   octeon_irq_handle_gpio);
+
+	return 0;
+}
+
+static struct irq_domain_ops octeon_irq_domain_ciu_ops = {
+	.map = octeon_irq_ciu_map,
+	.xlate = octeon_irq_ciu_xlat,
+};
+
+static struct irq_domain_ops octeon_irq_domain_gpio_ops = {
+	.map = octeon_irq_gpio_map,
+	.xlate = octeon_irq_gpio_xlat,
+};
+
 static void octeon_irq_ip2_v1(void)
 {
 	const unsigned long core_id = cvmx_get_core_num();
@@ -887,9 +1145,10 @@ static void __init octeon_irq_init_ciu(void)
 {
 	unsigned int i;
 	struct irq_chip *chip;
-	struct irq_chip *chip_edge;
 	struct irq_chip *chip_mbox;
 	struct irq_chip *chip_wd;
+	struct device_node *gpio_node;
+	struct device_node *ciu_node;
 
 	octeon_irq_init_ciu_percpu();
 	octeon_irq_setup_secondary = octeon_irq_setup_secondary_ciu;
@@ -901,17 +1160,18 @@ static void __init octeon_irq_init_ciu(void)
 		octeon_irq_ip2 = octeon_irq_ip2_v2;
 		octeon_irq_ip3 = octeon_irq_ip3_v2;
 		chip = &octeon_irq_chip_ciu_v2;
-		chip_edge = &octeon_irq_chip_ciu_edge_v2;
 		chip_mbox = &octeon_irq_chip_ciu_mbox_v2;
 		chip_wd = &octeon_irq_chip_ciu_wd_v2;
+		octeon_irq_gpio_chip = &octeon_irq_chip_ciu_gpio_v2;
 	} else {
 		octeon_irq_ip2 = octeon_irq_ip2_v1;
 		octeon_irq_ip3 = octeon_irq_ip3_v1;
 		chip = &octeon_irq_chip_ciu;
-		chip_edge = &octeon_irq_chip_ciu_edge;
 		chip_mbox = &octeon_irq_chip_ciu_mbox;
 		chip_wd = &octeon_irq_chip_ciu_wd;
+		octeon_irq_gpio_chip = &octeon_irq_chip_ciu_gpio;
 	}
+	octeon_irq_ciu_chip = chip;
 	octeon_irq_ip4 = octeon_irq_ip4_mask;
 
 	/* Mips internal */
@@ -920,80 +1180,49 @@ static void __init octeon_irq_init_ciu(void)
 	/* CIU_0 */
 	for (i = 0; i < 16; i++)
 		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_WORKQ0, 0, i + 0, chip, handle_level_irq);
-	for (i = 0; i < 16; i++)
-		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_GPIO0, 0, i + 16, chip, handle_level_irq);
 
 	octeon_irq_set_ciu_mapping(OCTEON_IRQ_MBOX0, 0, 32, chip_mbox, handle_percpu_irq);
 	octeon_irq_set_ciu_mapping(OCTEON_IRQ_MBOX1, 0, 33, chip_mbox, handle_percpu_irq);
 
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_UART0, 0, 34, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_UART1, 0, 35, chip, handle_level_irq);
-
 	for (i = 0; i < 4; i++)
 		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_PCI_INT0, 0, i + 36, chip, handle_level_irq);
 	for (i = 0; i < 4; i++)
 		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_PCI_MSI0, 0, i + 40, chip, handle_level_irq);
 
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_TWSI, 0, 45, chip, handle_level_irq);
 	octeon_irq_set_ciu_mapping(OCTEON_IRQ_RML, 0, 46, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_TRACE0, 0, 47, chip, handle_level_irq);
-
-	for (i = 0; i < 2; i++)
-		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_GMX_DRP0, 0, i + 48, chip_edge, handle_edge_irq);
-
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_IPD_DRP, 0, 50, chip_edge, handle_edge_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_KEY_ZERO, 0, 51, chip_edge, handle_edge_irq);
-
 	for (i = 0; i < 4; i++)
-		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_TIMER0, 0, i + 52, chip_edge, handle_edge_irq);
+		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_TIMER0, 0, i + 52, chip, handle_edge_irq);
 
 	octeon_irq_set_ciu_mapping(OCTEON_IRQ_USB0, 0, 56, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_PCM, 0, 57, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_MPI, 0, 58, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_TWSI2, 0, 59, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_POWIQ, 0, 60, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_IPDPPTHR, 0, 61, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_MII0, 0, 62, chip, handle_level_irq);
 	octeon_irq_set_ciu_mapping(OCTEON_IRQ_BOOTDMA, 0, 63, chip, handle_level_irq);
 
 	/* CIU_1 */
 	for (i = 0; i < 16; i++)
 		octeon_irq_set_ciu_mapping(i + OCTEON_IRQ_WDOG0, 1, i + 0, chip_wd, handle_level_irq);
 
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_UART2, 1, 16, chip, handle_level_irq);
 	octeon_irq_set_ciu_mapping(OCTEON_IRQ_USB1, 1, 17, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_MII1, 1, 18, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_NAND, 1, 19, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_MIO, 1, 20, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_IOB, 1, 21, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_FPA, 1, 22, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_POW, 1, 23, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_L2C, 1, 24, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_IPD, 1, 25, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_PIP, 1, 26, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_PKO, 1, 27, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_ZIP, 1, 28, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_TIM, 1, 29, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_RAD, 1, 30, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_KEY, 1, 31, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_DFA, 1, 32, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_USBCTL, 1, 33, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_SLI, 1, 34, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_DPI, 1, 35, chip, handle_level_irq);
-
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_AGX0, 1, 36, chip, handle_level_irq);
-
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_AGL, 1, 46, chip, handle_level_irq);
-
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_PTP, 1, 47, chip_edge, handle_edge_irq);
-
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_PEM0, 1, 48, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_PEM1, 1, 49, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_SRIO0, 1, 50, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_SRIO1, 1, 51, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_LMC0, 1, 52, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_DFM, 1, 56, chip, handle_level_irq);
-	octeon_irq_set_ciu_mapping(OCTEON_IRQ_RST, 1, 63, chip, handle_level_irq);
+
+	gpio_node = of_find_compatible_node(NULL, NULL, "cavium,octeon-3860-gpio");
+	if (gpio_node) {
+		struct octeon_irq_gpio_domain_data *gpiod;
+
+		gpiod = kzalloc(sizeof(*gpiod), GFP_KERNEL);
+		if (gpiod) {
+			/* gpio domain host_data is the base hwirq number. */
+			gpiod->base_hwirq = 16;
+			irq_domain_add_linear(gpio_node, 16, &octeon_irq_domain_gpio_ops, gpiod);
+			of_node_put(gpio_node);
+		} else
+			pr_warn("Cannot allocate memory for GPIO irq_domain.\n");
+	} else
+		pr_warn("Cannot find device node for cavium,octeon-3860-gpio.\n");
+
+	ciu_node = of_find_compatible_node(NULL, NULL, "cavium,octeon-3860-ciu");
+	if (ciu_node) {
+		irq_domain_add_tree(ciu_node, &octeon_irq_domain_ciu_ops, NULL);
+		of_node_put(ciu_node);
+	} else
+		pr_warn("Cannot find device node for cavium,octeon-3860-ciu.\n");
 
 	/* Enable the CIU lines */
 	set_c0_status(STATUSF_IP3 | STATUSF_IP2);
diff --git a/arch/mips/cavium-octeon/octeon-memcpy.S b/arch/mips/cavium-octeon/octeon-memcpy.S
index 88e0cddca205..db478dbb9c7b 100644
--- a/arch/mips/cavium-octeon/octeon-memcpy.S
+++ b/arch/mips/cavium-octeon/octeon-memcpy.S
@@ -164,6 +164,14 @@
 	.set	noat
 
 /*
+ * t7 is used as a flag to note inatomic mode.
+ */
+LEAF(__copy_user_inatomic)
+	b	__copy_user_common
+	 li	t7, 1
+	END(__copy_user_inatomic)
+
+/*
  * A combined memcpy/__copy_user
  * __copy_user sets len to 0 for success; else to an upper bound of
  * the number of uncopied bytes.
@@ -174,6 +182,8 @@ LEAF(memcpy)					/* a0=dst a1=src a2=len */
 	move	v0, dst				/* return value */
 __memcpy:
 FEXPORT(__copy_user)
+	li	t7, 0				/* not inatomic */
+__copy_user_common:
 	/*
 	 * Note: dst & src may be unaligned, len may be 0
 	 * Temps
@@ -412,7 +422,6 @@ l_exc_copy:
 	 * Assumes src < THREAD_BUADDR($28)
 	 */
 	LOAD	t0, TI_TASK($28)
-	 nop
 	LOAD	t0, THREAD_BUADDR(t0)
 1:
 EXC(	lb	t1, 0(src),	l_exc)
@@ -422,10 +431,9 @@ EXC(	lb	t1, 0(src),	l_exc)
 	 ADD	dst, dst, 1
 l_exc:
 	LOAD	t0, TI_TASK($28)
-	 nop
 	LOAD	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
-	 nop
 	SUB	len, AT, t0		# len number of uncopied bytes
+	bnez	t7, 2f		/* Skip the zeroing out part if inatomic */
 	/*
 	 * Here's where we rely on src and dst being incremented in tandem,
 	 *   See (3) above.
@@ -443,7 +451,7 @@ l_exc:
 	ADD	dst, dst, 1
 	bnez	src, 1b
 	 SUB	src, src, 1
-	jr	ra
+2:	jr	ra
 	 nop
 
 
diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c
index cd61d7281d91..0938df10a71c 100644
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -3,7 +3,7 @@
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
  *
- * Copyright (C) 2004-2010 Cavium Networks
+ * Copyright (C) 2004-2011 Cavium Networks
  * Copyright (C) 2008 Wind River Systems
  */
 
@@ -13,10 +13,16 @@
 #include <linux/usb.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
+#include <linux/slab.h>
 #include <linux/platform_device.h>
+#include <linux/of_platform.h>
+#include <linux/of_fdt.h>
+#include <linux/libfdt.h>
 
 #include <asm/octeon/octeon.h>
 #include <asm/octeon/cvmx-rnm-defs.h>
+#include <asm/octeon/cvmx-helper.h>
+#include <asm/octeon/cvmx-helper-board.h>
 
 static struct octeon_cf_data octeon_cf_data;
 
@@ -162,182 +168,6 @@ out:
 }
 device_initcall(octeon_rng_device_init);
 
-static struct i2c_board_info __initdata octeon_i2c_devices[] = {
-	{
-		I2C_BOARD_INFO("ds1337", 0x68),
-	},
-};
-
-static int __init octeon_i2c_devices_init(void)
-{
-	return i2c_register_board_info(0, octeon_i2c_devices,
-				       ARRAY_SIZE(octeon_i2c_devices));
-}
-arch_initcall(octeon_i2c_devices_init);
-
-#define OCTEON_I2C_IO_BASE 0x1180000001000ull
-#define OCTEON_I2C_IO_UNIT_OFFSET 0x200
-
-static struct octeon_i2c_data octeon_i2c_data[2];
-
-static int __init octeon_i2c_device_init(void)
-{
-	struct platform_device *pd;
-	int ret = 0;
-	int port, num_ports;
-
-	struct resource i2c_resources[] = {
-		{
-			.flags	= IORESOURCE_MEM,
-		}, {
-			.flags	= IORESOURCE_IRQ,
-		}
-	};
-
-	if (OCTEON_IS_MODEL(OCTEON_CN56XX) || OCTEON_IS_MODEL(OCTEON_CN52XX))
-		num_ports = 2;
-	else
-		num_ports = 1;
-
-	for (port = 0; port < num_ports; port++) {
-		octeon_i2c_data[port].sys_freq = octeon_get_io_clock_rate();
-		/*FIXME: should be examined. At the moment is set for 100Khz */
-		octeon_i2c_data[port].i2c_freq = 100000;
-
-		pd = platform_device_alloc("i2c-octeon", port);
-		if (!pd) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		pd->dev.platform_data = octeon_i2c_data + port;
-
-		i2c_resources[0].start =
-			OCTEON_I2C_IO_BASE + (port * OCTEON_I2C_IO_UNIT_OFFSET);
-		i2c_resources[0].end = i2c_resources[0].start + 0x1f;
-		switch (port) {
-		case 0:
-			i2c_resources[1].start = OCTEON_IRQ_TWSI;
-			i2c_resources[1].end = OCTEON_IRQ_TWSI;
-			break;
-		case 1:
-			i2c_resources[1].start = OCTEON_IRQ_TWSI2;
-			i2c_resources[1].end = OCTEON_IRQ_TWSI2;
-			break;
-		default:
-			BUG();
-		}
-
-		ret = platform_device_add_resources(pd,
-						    i2c_resources,
-						    ARRAY_SIZE(i2c_resources));
-		if (ret)
-			goto fail;
-
-		ret = platform_device_add(pd);
-		if (ret)
-			goto fail;
-	}
-	return ret;
-fail:
-	platform_device_put(pd);
-out:
-	return ret;
-}
-device_initcall(octeon_i2c_device_init);
-
-/* Octeon SMI/MDIO interface.  */
-static int __init octeon_mdiobus_device_init(void)
-{
-	struct platform_device *pd;
-	int ret = 0;
-
-	if (octeon_is_simulation())
-		return 0; /* No mdio in the simulator. */
-
-	/* The bus number is the platform_device id.  */
-	pd = platform_device_alloc("mdio-octeon", 0);
-	if (!pd) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	ret = platform_device_add(pd);
-	if (ret)
-		goto fail;
-
-	return ret;
-fail:
-	platform_device_put(pd);
-
-out:
-	return ret;
-
-}
-device_initcall(octeon_mdiobus_device_init);
-
-/* Octeon mgmt port Ethernet interface.  */
-static int __init octeon_mgmt_device_init(void)
-{
-	struct platform_device *pd;
-	int ret = 0;
-	int port, num_ports;
-
-	struct resource mgmt_port_resource = {
-		.flags	= IORESOURCE_IRQ,
-		.start	= -1,
-		.end	= -1
-	};
-
-	if (!OCTEON_IS_MODEL(OCTEON_CN56XX) && !OCTEON_IS_MODEL(OCTEON_CN52XX))
-		return 0;
-
-	if (OCTEON_IS_MODEL(OCTEON_CN56XX))
-		num_ports = 1;
-	else
-		num_ports = 2;
-
-	for (port = 0; port < num_ports; port++) {
-		pd = platform_device_alloc("octeon_mgmt", port);
-		if (!pd) {
-			ret = -ENOMEM;
-			goto out;
-		}
-		/* No DMA restrictions */
-		pd->dev.coherent_dma_mask = DMA_BIT_MASK(64);
-		pd->dev.dma_mask = &pd->dev.coherent_dma_mask;
-
-		switch (port) {
-		case 0:
-			mgmt_port_resource.start = OCTEON_IRQ_MII0;
-			break;
-		case 1:
-			mgmt_port_resource.start = OCTEON_IRQ_MII1;
-			break;
-		default:
-			BUG();
-		}
-		mgmt_port_resource.end = mgmt_port_resource.start;
-
-		ret = platform_device_add_resources(pd, &mgmt_port_resource, 1);
-
-		if (ret)
-			goto fail;
-
-		ret = platform_device_add(pd);
-		if (ret)
-			goto fail;
-	}
-	return ret;
-fail:
-	platform_device_put(pd);
-
-out:
-	return ret;
-
-}
-device_initcall(octeon_mgmt_device_init);
-
 #ifdef CONFIG_USB
 
 static int __init octeon_ehci_device_init(void)
@@ -440,6 +270,521 @@ device_initcall(octeon_ohci_device_init);
 
 #endif /* CONFIG_USB */
 
+static struct of_device_id __initdata octeon_ids[] = {
+	{ .compatible = "simple-bus", },
+	{ .compatible = "cavium,octeon-6335-uctl", },
+	{ .compatible = "cavium,octeon-3860-bootbus", },
+	{ .compatible = "cavium,mdio-mux", },
+	{ .compatible = "gpio-leds", },
+	{},
+};
+
+static bool __init octeon_has_88e1145(void)
+{
+	return !OCTEON_IS_MODEL(OCTEON_CN52XX) &&
+	       !OCTEON_IS_MODEL(OCTEON_CN6XXX) &&
+	       !OCTEON_IS_MODEL(OCTEON_CN56XX);
+}
+
+static void __init octeon_fdt_set_phy(int eth, int phy_addr)
+{
+	const __be32 *phy_handle;
+	const __be32 *alt_phy_handle;
+	const __be32 *reg;
+	u32 phandle;
+	int phy;
+	int alt_phy;
+	const char *p;
+	int current_len;
+	char new_name[20];
+
+	phy_handle = fdt_getprop(initial_boot_params, eth, "phy-handle", NULL);
+	if (!phy_handle)
+		return;
+
+	phandle = be32_to_cpup(phy_handle);
+	phy = fdt_node_offset_by_phandle(initial_boot_params, phandle);
+
+	alt_phy_handle = fdt_getprop(initial_boot_params, eth, "cavium,alt-phy-handle", NULL);
+	if (alt_phy_handle) {
+		u32 alt_phandle = be32_to_cpup(alt_phy_handle);
+		alt_phy = fdt_node_offset_by_phandle(initial_boot_params, alt_phandle);
+	} else {
+		alt_phy = -1;
+	}
+
+	if (phy_addr < 0 || phy < 0) {
+		/* Delete the PHY things */
+		fdt_nop_property(initial_boot_params, eth, "phy-handle");
+		/* This one may fail */
+		fdt_nop_property(initial_boot_params, eth, "cavium,alt-phy-handle");
+		if (phy >= 0)
+			fdt_nop_node(initial_boot_params, phy);
+		if (alt_phy >= 0)
+			fdt_nop_node(initial_boot_params, alt_phy);
+		return;
+	}
+
+	if (phy_addr >= 256 && alt_phy > 0) {
+		const struct fdt_property *phy_prop;
+		struct fdt_property *alt_prop;
+		u32 phy_handle_name;
+
+		/* Use the alt phy node instead.*/
+		phy_prop = fdt_get_property(initial_boot_params, eth, "phy-handle", NULL);
+		phy_handle_name = phy_prop->nameoff;
+		fdt_nop_node(initial_boot_params, phy);
+		fdt_nop_property(initial_boot_params, eth, "phy-handle");
+		alt_prop = fdt_get_property_w(initial_boot_params, eth, "cavium,alt-phy-handle", NULL);
+		alt_prop->nameoff = phy_handle_name;
+		phy = alt_phy;
+	}
+
+	phy_addr &= 0xff;
+
+	if (octeon_has_88e1145()) {
+		fdt_nop_property(initial_boot_params, phy, "marvell,reg-init");
+		memset(new_name, 0, sizeof(new_name));
+		strcpy(new_name, "marvell,88e1145");
+		p = fdt_getprop(initial_boot_params, phy, "compatible",
+				&current_len);
+		if (p && current_len >= strlen(new_name))
+			fdt_setprop_inplace(initial_boot_params, phy,
+					"compatible", new_name, current_len);
+	}
+
+	reg = fdt_getprop(initial_boot_params, phy, "reg", NULL);
+	if (phy_addr == be32_to_cpup(reg))
+		return;
+
+	fdt_setprop_inplace_cell(initial_boot_params, phy, "reg", phy_addr);
+
+	snprintf(new_name, sizeof(new_name), "ethernet-phy@%x", phy_addr);
+
+	p = fdt_get_name(initial_boot_params, phy, &current_len);
+	if (p && current_len == strlen(new_name))
+		fdt_set_name(initial_boot_params, phy, new_name);
+	else
+		pr_err("Error: could not rename ethernet phy: <%s>", p);
+}
+
+static void __init octeon_fdt_set_mac_addr(int n, u64 *pmac)
+{
+	u8 new_mac[6];
+	u64 mac = *pmac;
+	int r;
+
+	new_mac[0] = (mac >> 40) & 0xff;
+	new_mac[1] = (mac >> 32) & 0xff;
+	new_mac[2] = (mac >> 24) & 0xff;
+	new_mac[3] = (mac >> 16) & 0xff;
+	new_mac[4] = (mac >> 8) & 0xff;
+	new_mac[5] = mac & 0xff;
+
+	r = fdt_setprop_inplace(initial_boot_params, n, "local-mac-address",
+				new_mac, sizeof(new_mac));
+
+	if (r) {
+		pr_err("Setting \"local-mac-address\" failed %d", r);
+		return;
+	}
+	*pmac = mac + 1;
+}
+
+static void __init octeon_fdt_rm_ethernet(int node)
+{
+	const __be32 *phy_handle;
+
+	phy_handle = fdt_getprop(initial_boot_params, node, "phy-handle", NULL);
+	if (phy_handle) {
+		u32 ph = be32_to_cpup(phy_handle);
+		int p = fdt_node_offset_by_phandle(initial_boot_params, ph);
+		if (p >= 0)
+			fdt_nop_node(initial_boot_params, p);
+	}
+	fdt_nop_node(initial_boot_params, node);
+}
+
+static void __init octeon_fdt_pip_port(int iface, int i, int p, int max, u64 *pmac)
+{
+	char name_buffer[20];
+	int eth;
+	int phy_addr;
+	int ipd_port;
+
+	snprintf(name_buffer, sizeof(name_buffer), "ethernet@%x", p);
+	eth = fdt_subnode_offset(initial_boot_params, iface, name_buffer);
+	if (eth < 0)
+		return;
+	if (p > max) {
+		pr_debug("Deleting port %x:%x\n", i, p);
+		octeon_fdt_rm_ethernet(eth);
+		return;
+	}
+	if (OCTEON_IS_MODEL(OCTEON_CN68XX))
+		ipd_port = (0x100 * i) + (0x10 * p) + 0x800;
+	else
+		ipd_port = 16 * i + p;
+
+	phy_addr = cvmx_helper_board_get_mii_address(ipd_port);
+	octeon_fdt_set_phy(eth, phy_addr);
+	octeon_fdt_set_mac_addr(eth, pmac);
+}
+
+static void __init octeon_fdt_pip_iface(int pip, int idx, u64 *pmac)
+{
+	char name_buffer[20];
+	int iface;
+	int p;
+	int count;
+
+	count = cvmx_helper_interface_enumerate(idx);
+
+	snprintf(name_buffer, sizeof(name_buffer), "interface@%d", idx);
+	iface = fdt_subnode_offset(initial_boot_params, pip, name_buffer);
+	if (iface < 0)
+		return;
+
+	for (p = 0; p < 16; p++)
+		octeon_fdt_pip_port(iface, idx, p, count - 1, pmac);
+}
+
+int __init octeon_prune_device_tree(void)
+{
+	int i, max_port, uart_mask;
+	const char *pip_path;
+	const char *alias_prop;
+	char name_buffer[20];
+	int aliases;
+	u64 mac_addr_base;
+
+	if (fdt_check_header(initial_boot_params))
+		panic("Corrupt Device Tree.");
+
+	aliases = fdt_path_offset(initial_boot_params, "/aliases");
+	if (aliases < 0) {
+		pr_err("Error: No /aliases node in device tree.");
+		return -EINVAL;
+	}
+
+
+	mac_addr_base =
+		((octeon_bootinfo->mac_addr_base[0] & 0xffull)) << 40 |
+		((octeon_bootinfo->mac_addr_base[1] & 0xffull)) << 32 |
+		((octeon_bootinfo->mac_addr_base[2] & 0xffull)) << 24 |
+		((octeon_bootinfo->mac_addr_base[3] & 0xffull)) << 16 |
+		((octeon_bootinfo->mac_addr_base[4] & 0xffull)) << 8 |
+		(octeon_bootinfo->mac_addr_base[5] & 0xffull);
+
+	if (OCTEON_IS_MODEL(OCTEON_CN52XX) || OCTEON_IS_MODEL(OCTEON_CN63XX))
+		max_port = 2;
+	else if (OCTEON_IS_MODEL(OCTEON_CN56XX) || OCTEON_IS_MODEL(OCTEON_CN68XX))
+		max_port = 1;
+	else
+		max_port = 0;
+
+	if (octeon_bootinfo->board_type == CVMX_BOARD_TYPE_NIC10E)
+		max_port = 0;
+
+	for (i = 0; i < 2; i++) {
+		int mgmt;
+		snprintf(name_buffer, sizeof(name_buffer),
+			 "mix%d", i);
+		alias_prop = fdt_getprop(initial_boot_params, aliases,
+					name_buffer, NULL);
+		if (alias_prop) {
+			mgmt = fdt_path_offset(initial_boot_params, alias_prop);
+			if (mgmt < 0)
+				continue;
+			if (i >= max_port) {
+				pr_debug("Deleting mix%d\n", i);
+				octeon_fdt_rm_ethernet(mgmt);
+				fdt_nop_property(initial_boot_params, aliases,
+						 name_buffer);
+			} else {
+				int phy_addr = cvmx_helper_board_get_mii_address(CVMX_HELPER_BOARD_MGMT_IPD_PORT + i);
+				octeon_fdt_set_phy(mgmt, phy_addr);
+				octeon_fdt_set_mac_addr(mgmt, &mac_addr_base);
+			}
+		}
+	}
+
+	pip_path = fdt_getprop(initial_boot_params, aliases, "pip", NULL);
+	if (pip_path) {
+		int pip = fdt_path_offset(initial_boot_params, pip_path);
+		if (pip  >= 0)
+			for (i = 0; i <= 4; i++)
+				octeon_fdt_pip_iface(pip, i, &mac_addr_base);
+	}
+
+	/* I2C */
+	if (OCTEON_IS_MODEL(OCTEON_CN52XX) ||
+	    OCTEON_IS_MODEL(OCTEON_CN63XX) ||
+	    OCTEON_IS_MODEL(OCTEON_CN68XX) ||
+	    OCTEON_IS_MODEL(OCTEON_CN56XX))
+		max_port = 2;
+	else
+		max_port = 1;
+
+	for (i = 0; i < 2; i++) {
+		int i2c;
+		snprintf(name_buffer, sizeof(name_buffer),
+			 "twsi%d", i);
+		alias_prop = fdt_getprop(initial_boot_params, aliases,
+					name_buffer, NULL);
+
+		if (alias_prop) {
+			i2c = fdt_path_offset(initial_boot_params, alias_prop);
+			if (i2c < 0)
+				continue;
+			if (i >= max_port) {
+				pr_debug("Deleting twsi%d\n", i);
+				fdt_nop_node(initial_boot_params, i2c);
+				fdt_nop_property(initial_boot_params, aliases,
+						 name_buffer);
+			}
+		}
+	}
+
+	/* SMI/MDIO */
+	if (OCTEON_IS_MODEL(OCTEON_CN68XX))
+		max_port = 4;
+	else if (OCTEON_IS_MODEL(OCTEON_CN52XX) ||
+		 OCTEON_IS_MODEL(OCTEON_CN63XX) ||
+		 OCTEON_IS_MODEL(OCTEON_CN56XX))
+		max_port = 2;
+	else
+		max_port = 1;
+
+	for (i = 0; i < 2; i++) {
+		int i2c;
+		snprintf(name_buffer, sizeof(name_buffer),
+			 "smi%d", i);
+		alias_prop = fdt_getprop(initial_boot_params, aliases,
+					name_buffer, NULL);
+
+		if (alias_prop) {
+			i2c = fdt_path_offset(initial_boot_params, alias_prop);
+			if (i2c < 0)
+				continue;
+			if (i >= max_port) {
+				pr_debug("Deleting smi%d\n", i);
+				fdt_nop_node(initial_boot_params, i2c);
+				fdt_nop_property(initial_boot_params, aliases,
+						 name_buffer);
+			}
+		}
+	}
+
+	/* Serial */
+	uart_mask = 3;
+
+	/* Right now CN52XX is the only chip with a third uart */
+	if (OCTEON_IS_MODEL(OCTEON_CN52XX))
+		uart_mask |= 4; /* uart2 */
+
+	for (i = 0; i < 3; i++) {
+		int uart;
+		snprintf(name_buffer, sizeof(name_buffer),
+			 "uart%d", i);
+		alias_prop = fdt_getprop(initial_boot_params, aliases,
+					name_buffer, NULL);
+
+		if (alias_prop) {
+			uart = fdt_path_offset(initial_boot_params, alias_prop);
+			if (uart_mask & (1 << i))
+				continue;
+			pr_debug("Deleting uart%d\n", i);
+			fdt_nop_node(initial_boot_params, uart);
+			fdt_nop_property(initial_boot_params, aliases,
+					 name_buffer);
+		}
+	}
+
+	/* Compact Flash */
+	alias_prop = fdt_getprop(initial_boot_params, aliases,
+				 "cf0", NULL);
+	if (alias_prop) {
+		union cvmx_mio_boot_reg_cfgx mio_boot_reg_cfg;
+		unsigned long base_ptr, region_base, region_size;
+		unsigned long region1_base = 0;
+		unsigned long region1_size = 0;
+		int cs, bootbus;
+		bool is_16bit = false;
+		bool is_true_ide = false;
+		__be32 new_reg[6];
+		__be32 *ranges;
+		int len;
+
+		int cf = fdt_path_offset(initial_boot_params, alias_prop);
+		base_ptr = 0;
+		if (octeon_bootinfo->major_version == 1
+			&& octeon_bootinfo->minor_version >= 1) {
+			if (octeon_bootinfo->compact_flash_common_base_addr)
+				base_ptr = octeon_bootinfo->compact_flash_common_base_addr;
+		} else {
+			base_ptr = 0x1d000800;
+		}
+
+		if (!base_ptr)
+			goto no_cf;
+
+		/* Find CS0 region. */
+		for (cs = 0; cs < 8; cs++) {
+			mio_boot_reg_cfg.u64 = cvmx_read_csr(CVMX_MIO_BOOT_REG_CFGX(cs));
+			region_base = mio_boot_reg_cfg.s.base << 16;
+			region_size = (mio_boot_reg_cfg.s.size + 1) << 16;
+			if (mio_boot_reg_cfg.s.en && base_ptr >= region_base
+				&& base_ptr < region_base + region_size) {
+				is_16bit = mio_boot_reg_cfg.s.width;
+				break;
+			}
+		}
+		if (cs >= 7) {
+			/* cs and cs + 1 are CS0 and CS1, both must be less than 8. */
+			goto no_cf;
+		}
+
+		if (!(base_ptr & 0xfffful)) {
+			/*
+			 * Boot loader signals availability of DMA (true_ide
+			 * mode) by setting low order bits of base_ptr to
+			 * zero.
+			 */
+
+			/* Asume that CS1 immediately follows. */
+			mio_boot_reg_cfg.u64 =
+				cvmx_read_csr(CVMX_MIO_BOOT_REG_CFGX(cs + 1));
+			region1_base = mio_boot_reg_cfg.s.base << 16;
+			region1_size = (mio_boot_reg_cfg.s.size + 1) << 16;
+			if (!mio_boot_reg_cfg.s.en)
+				goto no_cf;
+			is_true_ide = true;
+
+		} else {
+			fdt_nop_property(initial_boot_params, cf, "cavium,true-ide");
+			fdt_nop_property(initial_boot_params, cf, "cavium,dma-engine-handle");
+			if (!is_16bit) {
+				__be32 width = cpu_to_be32(8);
+				fdt_setprop_inplace(initial_boot_params, cf,
+						"cavium,bus-width", &width, sizeof(width));
+			}
+		}
+		new_reg[0] = cpu_to_be32(cs);
+		new_reg[1] = cpu_to_be32(0);
+		new_reg[2] = cpu_to_be32(0x10000);
+		new_reg[3] = cpu_to_be32(cs + 1);
+		new_reg[4] = cpu_to_be32(0);
+		new_reg[5] = cpu_to_be32(0x10000);
+		fdt_setprop_inplace(initial_boot_params, cf,
+				    "reg",  new_reg, sizeof(new_reg));
+
+		bootbus = fdt_parent_offset(initial_boot_params, cf);
+		if (bootbus < 0)
+			goto no_cf;
+		ranges = fdt_getprop_w(initial_boot_params, bootbus, "ranges", &len);
+		if (!ranges || len < (5 * 8 * sizeof(__be32)))
+			goto no_cf;
+
+		ranges[(cs * 5) + 2] = cpu_to_be32(region_base >> 32);
+		ranges[(cs * 5) + 3] = cpu_to_be32(region_base & 0xffffffff);
+		ranges[(cs * 5) + 4] = cpu_to_be32(region_size);
+		if (is_true_ide) {
+			cs++;
+			ranges[(cs * 5) + 2] = cpu_to_be32(region1_base >> 32);
+			ranges[(cs * 5) + 3] = cpu_to_be32(region1_base & 0xffffffff);
+			ranges[(cs * 5) + 4] = cpu_to_be32(region1_size);
+		}
+		goto end_cf;
+no_cf:
+		fdt_nop_node(initial_boot_params, cf);
+
+end_cf:
+		;
+	}
+
+	/* 8 char LED */
+	alias_prop = fdt_getprop(initial_boot_params, aliases,
+				 "led0", NULL);
+	if (alias_prop) {
+		union cvmx_mio_boot_reg_cfgx mio_boot_reg_cfg;
+		unsigned long base_ptr, region_base, region_size;
+		int cs, bootbus;
+		__be32 new_reg[6];
+		__be32 *ranges;
+		int len;
+		int led = fdt_path_offset(initial_boot_params, alias_prop);
+
+		base_ptr = octeon_bootinfo->led_display_base_addr;
+		if (base_ptr == 0)
+			goto no_led;
+		/* Find CS0 region. */
+		for (cs = 0; cs < 8; cs++) {
+			mio_boot_reg_cfg.u64 = cvmx_read_csr(CVMX_MIO_BOOT_REG_CFGX(cs));
+			region_base = mio_boot_reg_cfg.s.base << 16;
+			region_size = (mio_boot_reg_cfg.s.size + 1) << 16;
+			if (mio_boot_reg_cfg.s.en && base_ptr >= region_base
+				&& base_ptr < region_base + region_size)
+				break;
+		}
+
+		if (cs > 7)
+			goto no_led;
+
+		new_reg[0] = cpu_to_be32(cs);
+		new_reg[1] = cpu_to_be32(0x20);
+		new_reg[2] = cpu_to_be32(0x20);
+		new_reg[3] = cpu_to_be32(cs);
+		new_reg[4] = cpu_to_be32(0);
+		new_reg[5] = cpu_to_be32(0x20);
+		fdt_setprop_inplace(initial_boot_params, led,
+				    "reg",  new_reg, sizeof(new_reg));
+
+		bootbus = fdt_parent_offset(initial_boot_params, led);
+		if (bootbus < 0)
+			goto no_led;
+		ranges = fdt_getprop_w(initial_boot_params, bootbus, "ranges", &len);
+		if (!ranges || len < (5 * 8 * sizeof(__be32)))
+			goto no_led;
+
+		ranges[(cs * 5) + 2] = cpu_to_be32(region_base >> 32);
+		ranges[(cs * 5) + 3] = cpu_to_be32(region_base & 0xffffffff);
+		ranges[(cs * 5) + 4] = cpu_to_be32(region_size);
+		goto end_led;
+
+no_led:
+		fdt_nop_node(initial_boot_params, led);
+end_led:
+		;
+	}
+
+	/* OHCI/UHCI USB */
+	alias_prop = fdt_getprop(initial_boot_params, aliases,
+				 "uctl", NULL);
+	if (alias_prop) {
+		int uctl = fdt_path_offset(initial_boot_params, alias_prop);
+
+		if (uctl >= 0 && (!OCTEON_IS_MODEL(OCTEON_CN6XXX) ||
+				  octeon_bootinfo->board_type == CVMX_BOARD_TYPE_NIC2E)) {
+			pr_debug("Deleting uctl\n");
+			fdt_nop_node(initial_boot_params, uctl);
+			fdt_nop_property(initial_boot_params, aliases, "uctl");
+		} else if (octeon_bootinfo->board_type == CVMX_BOARD_TYPE_NIC10E ||
+			   octeon_bootinfo->board_type == CVMX_BOARD_TYPE_NIC4E) {
+			/* Missing "refclk-type" defaults to crystal. */
+			fdt_nop_property(initial_boot_params, uctl, "refclk-type");
+		}
+	}
+
+	return 0;
+}
+
+static int __init octeon_publish_devices(void)
+{
+	return of_platform_bus_probe(NULL, octeon_ids, NULL);
+}
+device_initcall(octeon_publish_devices);
+
 MODULE_AUTHOR("David Daney <ddaney@caviumnetworks.com>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Platform driver for Octeon SOC");
diff --git a/arch/mips/cavium-octeon/octeon_3xxx.dts b/arch/mips/cavium-octeon/octeon_3xxx.dts
new file mode 100644
index 000000000000..f28b2d0fde22
--- /dev/null
+++ b/arch/mips/cavium-octeon/octeon_3xxx.dts
@@ -0,0 +1,571 @@
+/dts-v1/;
+/*
+ * OCTEON 3XXX, 5XXX, 63XX device tree skeleton.
+ *
+ * This device tree is pruned and patched by early boot code before
+ * use.  Because of this, it contains a super-set of the available
+ * devices and properties.
+ */
+/ {
+	compatible = "cavium,octeon-3860";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&ciu>;
+
+	soc@0 {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges; /* Direct mapping */
+
+		ciu: interrupt-controller@1070000000000 {
+			compatible = "cavium,octeon-3860-ciu";
+			interrupt-controller;
+			/* Interrupts are specified by two parts:
+			 * 1) Controller register (0 or 1)
+			 * 2) Bit within the register (0..63)
+			 */
+			#interrupt-cells = <2>;
+			reg = <0x10700 0x00000000 0x0 0x7000>;
+		};
+
+		gpio: gpio-controller@1070000000800 {
+			#gpio-cells = <2>;
+			compatible = "cavium,octeon-3860-gpio";
+			reg = <0x10700 0x00000800 0x0 0x100>;
+			gpio-controller;
+			/* Interrupts are specified by two parts:
+			 * 1) GPIO pin number (0..15)
+			 * 2) Triggering (1 - edge rising
+			 *		  2 - edge falling
+			 *		  4 - level active high
+			 *		  8 - level active low)
+			 */
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			/* The GPIO pin connect to 16 consecutive CUI bits */
+			interrupts = <0 16>, <0 17>, <0 18>, <0 19>,
+				     <0 20>, <0 21>, <0 22>, <0 23>,
+				     <0 24>, <0 25>, <0 26>, <0 27>,
+				     <0 28>, <0 29>, <0 30>, <0 31>;
+		};
+
+		smi0: mdio@1180000001800 {
+			compatible = "cavium,octeon-3860-mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x11800 0x00001800 0x0 0x40>;
+
+			phy0: ethernet-phy@0 {
+				compatible = "marvell,88e1118";
+				marvell,reg-init =
+					/* Fix rx and tx clock transition timing */
+					<2 0x15 0xffcf 0>, /* Reg 2,21 Clear bits 4, 5 */
+					/* Adjust LED drive. */
+					<3 0x11 0 0x442a>, /* Reg 3,17 <- 0442a */
+					/* irq, blink-activity, blink-link */
+					<3 0x10 0 0x0242>; /* Reg 3,16 <- 0x0242 */
+				reg = <0>;
+			};
+
+			phy1: ethernet-phy@1 {
+				compatible = "marvell,88e1118";
+				marvell,reg-init =
+					/* Fix rx and tx clock transition timing */
+					<2 0x15 0xffcf 0>, /* Reg 2,21 Clear bits 4, 5 */
+					/* Adjust LED drive. */
+					<3 0x11 0 0x442a>, /* Reg 3,17 <- 0442a */
+					/* irq, blink-activity, blink-link */
+					<3 0x10 0 0x0242>; /* Reg 3,16 <- 0x0242 */
+				reg = <1>;
+			};
+
+			phy2: ethernet-phy@2 {
+				reg = <2>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy3: ethernet-phy@3 {
+				reg = <3>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy4: ethernet-phy@4 {
+				reg = <4>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy5: ethernet-phy@5 {
+				reg = <5>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+
+			phy6: ethernet-phy@6 {
+				reg = <6>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy7: ethernet-phy@7 {
+				reg = <7>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy8: ethernet-phy@8 {
+				reg = <8>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy9: ethernet-phy@9 {
+				reg = <9>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+		};
+
+		smi1: mdio@1180000001900 {
+			compatible = "cavium,octeon-3860-mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x11800 0x00001900 0x0 0x40>;
+
+			phy100: ethernet-phy@1 {
+				reg = <1>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+				interrupt-parent = <&gpio>;
+				interrupts = <12 8>; /* Pin 12, active low */
+			};
+			phy101: ethernet-phy@2 {
+				reg = <2>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+				interrupt-parent = <&gpio>;
+				interrupts = <12 8>; /* Pin 12, active low */
+			};
+			phy102: ethernet-phy@3 {
+				reg = <3>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+				interrupt-parent = <&gpio>;
+				interrupts = <12 8>; /* Pin 12, active low */
+			};
+			phy103: ethernet-phy@4 {
+				reg = <4>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+				interrupt-parent = <&gpio>;
+				interrupts = <12 8>; /* Pin 12, active low */
+			};
+		};
+
+		mix0: ethernet@1070000100000 {
+			compatible = "cavium,octeon-5750-mix";
+			reg = <0x10700 0x00100000 0x0 0x100>, /* MIX */
+			      <0x11800 0xE0000000 0x0 0x300>, /* AGL */
+			      <0x11800 0xE0000400 0x0 0x400>, /* AGL_SHARED  */
+			      <0x11800 0xE0002000 0x0 0x8>;   /* AGL_PRT_CTL */
+			cell-index = <0>;
+			interrupts = <0 62>, <1 46>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			phy-handle = <&phy0>;
+		};
+
+		mix1: ethernet@1070000100800 {
+			compatible = "cavium,octeon-5750-mix";
+			reg = <0x10700 0x00100800 0x0 0x100>, /* MIX */
+			      <0x11800 0xE0000800 0x0 0x300>, /* AGL */
+			      <0x11800 0xE0000400 0x0 0x400>, /* AGL_SHARED  */
+			      <0x11800 0xE0002008 0x0 0x8>;   /* AGL_PRT_CTL */
+			cell-index = <1>;
+			interrupts = <1 18>, < 1 46>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			phy-handle = <&phy1>;
+		};
+
+		pip: pip@11800a0000000 {
+			compatible = "cavium,octeon-3860-pip";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x11800 0xa0000000 0x0 0x2000>;
+
+			interface@0 {
+				compatible = "cavium,octeon-3860-pip-interface";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0>; /* interface */
+
+				ethernet@0 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x0>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy2>;
+					cavium,alt-phy-handle = <&phy100>;
+				};
+				ethernet@1 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x1>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy3>;
+					cavium,alt-phy-handle = <&phy101>;
+				};
+				ethernet@2 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x2>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy4>;
+					cavium,alt-phy-handle = <&phy102>;
+				};
+				ethernet@3 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x3>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy5>;
+					cavium,alt-phy-handle = <&phy103>;
+				};
+				ethernet@4 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x4>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+				ethernet@5 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x5>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+				ethernet@6 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x6>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+				ethernet@7 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x7>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+				ethernet@8 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x8>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+				ethernet@9 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x9>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+				ethernet@a {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0xa>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+				ethernet@b {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0xb>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+				ethernet@c {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0xc>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+				ethernet@d {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0xd>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+				ethernet@e {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0xe>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+				ethernet@f {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0xf>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+			};
+
+			interface@1 {
+				compatible = "cavium,octeon-3860-pip-interface";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <1>; /* interface */
+
+				ethernet@0 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x0>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy6>;
+				};
+				ethernet@1 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x1>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy7>;
+				};
+				ethernet@2 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x2>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy8>;
+				};
+				ethernet@3 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x3>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy9>;
+				};
+			};
+		};
+
+		twsi0: i2c@1180000001000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "cavium,octeon-3860-twsi";
+			reg = <0x11800 0x00001000 0x0 0x200>;
+			interrupts = <0 45>;
+			clock-frequency = <100000>;
+
+			rtc@68 {
+				compatible = "dallas,ds1337";
+				reg = <0x68>;
+			};
+			tmp@4c {
+				compatible = "ti,tmp421";
+				reg = <0x4c>;
+			};
+		};
+
+		twsi1: i2c@1180000001200 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "cavium,octeon-3860-twsi";
+			reg = <0x11800 0x00001200 0x0 0x200>;
+			interrupts = <0 59>;
+			clock-frequency = <100000>;
+		};
+
+		uart0: serial@1180000000800 {
+			compatible = "cavium,octeon-3860-uart","ns16550";
+			reg = <0x11800 0x00000800 0x0 0x400>;
+			clock-frequency = <0>;
+			current-speed = <115200>;
+			reg-shift = <3>;
+			interrupts = <0 34>;
+		};
+
+		uart1: serial@1180000000c00 {
+			compatible = "cavium,octeon-3860-uart","ns16550";
+			reg = <0x11800 0x00000c00 0x0 0x400>;
+			clock-frequency = <0>;
+			current-speed = <115200>;
+			reg-shift = <3>;
+			interrupts = <0 35>;
+		};
+
+		uart2: serial@1180000000400 {
+			compatible = "cavium,octeon-3860-uart","ns16550";
+			reg = <0x11800 0x00000400 0x0 0x400>;
+			clock-frequency = <0>;
+			current-speed = <115200>;
+			reg-shift = <3>;
+			interrupts = <1 16>;
+		};
+
+		bootbus: bootbus@1180000000000 {
+			compatible = "cavium,octeon-3860-bootbus";
+			reg = <0x11800 0x00000000 0x0 0x200>;
+			/* The chip select number and offset */
+			#address-cells = <2>;
+			/* The size of the chip select region */
+			#size-cells = <1>;
+			ranges = <0 0  0x0 0x1f400000  0xc00000>,
+				 <1 0  0x10000 0x30000000  0>,
+				 <2 0  0x10000 0x40000000  0>,
+				 <3 0  0x10000 0x50000000  0>,
+				 <4 0  0x0 0x1d020000  0x10000>,
+				 <5 0  0x0 0x1d040000  0x10000>,
+				 <6 0  0x0 0x1d050000  0x10000>,
+				 <7 0  0x10000 0x90000000  0>;
+
+			cavium,cs-config@0 {
+				compatible = "cavium,octeon-3860-bootbus-config";
+				cavium,cs-index = <0>;
+				cavium,t-adr  = <20>;
+				cavium,t-ce   = <60>;
+				cavium,t-oe   = <60>;
+				cavium,t-we   = <45>;
+				cavium,t-rd-hld = <35>;
+				cavium,t-wr-hld = <45>;
+				cavium,t-pause  = <0>;
+				cavium,t-wait   = <0>;
+				cavium,t-page   = <35>;
+				cavium,t-rd-dly = <0>;
+
+				cavium,pages     = <0>;
+				cavium,bus-width = <8>;
+			};
+			cavium,cs-config@4 {
+				compatible = "cavium,octeon-3860-bootbus-config";
+				cavium,cs-index = <4>;
+				cavium,t-adr  = <320>;
+				cavium,t-ce   = <320>;
+				cavium,t-oe   = <320>;
+				cavium,t-we   = <320>;
+				cavium,t-rd-hld = <320>;
+				cavium,t-wr-hld = <320>;
+				cavium,t-pause  = <320>;
+				cavium,t-wait   = <320>;
+				cavium,t-page   = <320>;
+				cavium,t-rd-dly = <0>;
+
+				cavium,pages     = <0>;
+				cavium,bus-width = <8>;
+			};
+			cavium,cs-config@5 {
+				compatible = "cavium,octeon-3860-bootbus-config";
+				cavium,cs-index = <5>;
+				cavium,t-adr  = <5>;
+				cavium,t-ce   = <300>;
+				cavium,t-oe   = <125>;
+				cavium,t-we   = <150>;
+				cavium,t-rd-hld = <100>;
+				cavium,t-wr-hld = <30>;
+				cavium,t-pause  = <0>;
+				cavium,t-wait   = <30>;
+				cavium,t-page   = <320>;
+				cavium,t-rd-dly = <0>;
+
+				cavium,pages     = <0>;
+				cavium,bus-width = <16>;
+			};
+			cavium,cs-config@6 {
+				compatible = "cavium,octeon-3860-bootbus-config";
+				cavium,cs-index = <6>;
+				cavium,t-adr  = <5>;
+				cavium,t-ce   = <300>;
+				cavium,t-oe   = <270>;
+				cavium,t-we   = <150>;
+				cavium,t-rd-hld = <100>;
+				cavium,t-wr-hld = <70>;
+				cavium,t-pause  = <0>;
+				cavium,t-wait   = <0>;
+				cavium,t-page   = <320>;
+				cavium,t-rd-dly = <0>;
+
+				cavium,pages     = <0>;
+				cavium,wait-mode;
+				cavium,bus-width = <16>;
+			};
+
+			flash0: nor@0,0 {
+				compatible = "cfi-flash";
+				reg = <0 0 0x800000>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+			};
+
+			led0: led-display@4,0 {
+				compatible = "avago,hdsp-253x";
+				reg = <4 0x20 0x20>, <4 0 0x20>;
+			};
+
+			cf0: compact-flash@5,0 {
+				compatible = "cavium,ebt3000-compact-flash";
+				reg = <5 0 0x10000>, <6 0 0x10000>;
+				cavium,bus-width = <16>;
+				cavium,true-ide;
+				cavium,dma-engine-handle = <&dma0>;
+			};
+		};
+
+		dma0: dma-engine@1180000000100 {
+			compatible = "cavium,octeon-5750-bootbus-dma";
+			reg = <0x11800 0x00000100 0x0 0x8>;
+			interrupts = <0 63>;
+		};
+		dma1: dma-engine@1180000000108 {
+			compatible = "cavium,octeon-5750-bootbus-dma";
+			reg = <0x11800 0x00000108 0x0 0x8>;
+			interrupts = <0 63>;
+		};
+
+		uctl: uctl@118006f000000 {
+			compatible = "cavium,octeon-6335-uctl";
+			reg = <0x11800 0x6f000000 0x0 0x100>;
+			ranges; /* Direct mapping */
+			#address-cells = <2>;
+			#size-cells = <2>;
+			/* 12MHz, 24MHz and 48MHz allowed */
+			refclk-frequency = <12000000>;
+			/* Either "crystal" or "external" */
+			refclk-type = "crystal";
+
+			ehci@16f0000000000 {
+				compatible = "cavium,octeon-6335-ehci","usb-ehci";
+				reg = <0x16f00 0x00000000 0x0 0x100>;
+				interrupts = <0 56>;
+				big-endian-regs;
+			};
+			ohci@16f0000000400 {
+				compatible = "cavium,octeon-6335-ohci","usb-ohci";
+				reg = <0x16f00 0x00000400 0x0 0x100>;
+				interrupts = <0 56>;
+				big-endian-regs;
+			};
+		};
+	};
+
+	aliases {
+		mix0 = &mix0;
+		mix1 = &mix1;
+		pip = &pip;
+		smi0 = &smi0;
+		smi1 = &smi1;
+		twsi0 = &twsi0;
+		twsi1 = &twsi1;
+		uart0 = &uart0;
+		uart1 = &uart1;
+		uart2 = &uart2;
+		flash0 = &flash0;
+		cf0 = &cf0;
+		uctl = &uctl;
+		led0 = &led0;
+	};
+ };
diff --git a/arch/mips/cavium-octeon/octeon_68xx.dts b/arch/mips/cavium-octeon/octeon_68xx.dts
new file mode 100644
index 000000000000..1839468932b6
--- /dev/null
+++ b/arch/mips/cavium-octeon/octeon_68xx.dts
@@ -0,0 +1,625 @@
+/dts-v1/;
+/*
+ * OCTEON 68XX device tree skeleton.
+ *
+ * This device tree is pruned and patched by early boot code before
+ * use.  Because of this, it contains a super-set of the available
+ * devices and properties.
+ */
+/ {
+	compatible = "cavium,octeon-6880";
+	#address-cells = <2>;
+	#size-cells = <2>;
+	interrupt-parent = <&ciu2>;
+
+	soc@0 {
+		compatible = "simple-bus";
+		#address-cells = <2>;
+		#size-cells = <2>;
+		ranges; /* Direct mapping */
+
+		ciu2: interrupt-controller@1070100000000 {
+			compatible = "cavium,octeon-6880-ciu2";
+			interrupt-controller;
+			/* Interrupts are specified by two parts:
+			 * 1) Controller register (0 or 7)
+			 * 2) Bit within the register (0..63)
+			 */
+			#address-cells = <0>;
+			#interrupt-cells = <2>;
+			reg = <0x10701 0x00000000 0x0 0x4000000>;
+		};
+
+		gpio: gpio-controller@1070000000800 {
+			#gpio-cells = <2>;
+			compatible = "cavium,octeon-3860-gpio";
+			reg = <0x10700 0x00000800 0x0 0x100>;
+			gpio-controller;
+			/* Interrupts are specified by two parts:
+			 * 1) GPIO pin number (0..15)
+			 * 2) Triggering (1 - edge rising
+			 *		  2 - edge falling
+			 *		  4 - level active high
+			 *		  8 - level active low)
+			 */
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			/* The GPIO pins connect to 16 consecutive CUI bits */
+			interrupts = <7 0>,  <7 1>,  <7 2>,  <7 3>,
+				     <7 4>,  <7 5>,  <7 6>,  <7 7>,
+				     <7 8>,  <7 9>,  <7 10>, <7 11>,
+				     <7 12>, <7 13>, <7 14>, <7 15>;
+		};
+
+		smi0: mdio@1180000003800 {
+			compatible = "cavium,octeon-3860-mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x11800 0x00003800 0x0 0x40>;
+
+			phy0: ethernet-phy@6 {
+				compatible = "marvell,88e1118";
+				marvell,reg-init =
+					/* Fix rx and tx clock transition timing */
+					<2 0x15 0xffcf 0>, /* Reg 2,21 Clear bits 4, 5 */
+					/* Adjust LED drive. */
+					<3 0x11 0 0x442a>, /* Reg 3,17 <- 0442a */
+					/* irq, blink-activity, blink-link */
+					<3 0x10 0 0x0242>; /* Reg 3,16 <- 0x0242 */
+				reg = <6>;
+			};
+
+			phy1: ethernet-phy@1 {
+				cavium,qlm-trim = "4,sgmii";
+				reg = <1>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy2: ethernet-phy@2 {
+				cavium,qlm-trim = "4,sgmii";
+				reg = <2>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy3: ethernet-phy@3 {
+				cavium,qlm-trim = "4,sgmii";
+				reg = <3>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy4: ethernet-phy@4 {
+				cavium,qlm-trim = "4,sgmii";
+				reg = <4>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+		};
+
+		smi1: mdio@1180000003880 {
+			compatible = "cavium,octeon-3860-mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x11800 0x00003880 0x0 0x40>;
+
+			phy41: ethernet-phy@1 {
+				cavium,qlm-trim = "0,sgmii";
+				reg = <1>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy42: ethernet-phy@2 {
+				cavium,qlm-trim = "0,sgmii";
+				reg = <2>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy43: ethernet-phy@3 {
+				cavium,qlm-trim = "0,sgmii";
+				reg = <3>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy44: ethernet-phy@4 {
+				cavium,qlm-trim = "0,sgmii";
+				reg = <4>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+		};
+
+		smi2: mdio@1180000003900 {
+			compatible = "cavium,octeon-3860-mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x11800 0x00003900 0x0 0x40>;
+
+			phy21: ethernet-phy@1 {
+				cavium,qlm-trim = "2,sgmii";
+				reg = <1>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy22: ethernet-phy@2 {
+				cavium,qlm-trim = "2,sgmii";
+				reg = <2>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy23: ethernet-phy@3 {
+				cavium,qlm-trim = "2,sgmii";
+				reg = <3>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy24: ethernet-phy@4 {
+				cavium,qlm-trim = "2,sgmii";
+				reg = <4>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+		};
+
+		smi3: mdio@1180000003980 {
+			compatible = "cavium,octeon-3860-mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x11800 0x00003980 0x0 0x40>;
+
+			phy11: ethernet-phy@1 {
+				cavium,qlm-trim = "3,sgmii";
+				reg = <1>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy12: ethernet-phy@2 {
+				cavium,qlm-trim = "3,sgmii";
+				reg = <2>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy13: ethernet-phy@3 {
+				cavium,qlm-trim = "3,sgmii";
+				reg = <3>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+			phy14: ethernet-phy@4 {
+				cavium,qlm-trim = "3,sgmii";
+				reg = <4>;
+				compatible = "marvell,88e1149r";
+				marvell,reg-init = <3 0x10 0 0x5777>,
+					<3 0x11 0 0x00aa>,
+					<3 0x12 0 0x4105>,
+					<3 0x13 0 0x0a60>;
+			};
+		};
+
+		mix0: ethernet@1070000100000 {
+			compatible = "cavium,octeon-5750-mix";
+			reg = <0x10700 0x00100000 0x0 0x100>, /* MIX */
+			      <0x11800 0xE0000000 0x0 0x300>, /* AGL */
+			      <0x11800 0xE0000400 0x0 0x400>, /* AGL_SHARED  */
+			      <0x11800 0xE0002000 0x0 0x8>;   /* AGL_PRT_CTL */
+			cell-index = <0>;
+			interrupts = <6 40>, <6 32>;
+			local-mac-address = [ 00 00 00 00 00 00 ];
+			phy-handle = <&phy0>;
+		};
+
+		pip: pip@11800a0000000 {
+			compatible = "cavium,octeon-3860-pip";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x11800 0xa0000000 0x0 0x2000>;
+
+			interface@4 {
+				compatible = "cavium,octeon-3860-pip-interface";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0x4>; /* interface */
+
+				ethernet@0 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x0>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy1>;
+				};
+				ethernet@1 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x1>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy2>;
+				};
+				ethernet@2 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x2>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy3>;
+				};
+				ethernet@3 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x3>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy4>;
+				};
+			};
+
+			interface@3 {
+				compatible = "cavium,octeon-3860-pip-interface";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0x3>; /* interface */
+
+				ethernet@0 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x0>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy11>;
+				};
+				ethernet@1 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x1>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy12>;
+				};
+				ethernet@2 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x2>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy13>;
+				};
+				ethernet@3 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x3>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy14>;
+				};
+			};
+
+			interface@2 {
+				compatible = "cavium,octeon-3860-pip-interface";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0x2>; /* interface */
+
+				ethernet@0 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x0>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy21>;
+				};
+				ethernet@1 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x1>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy22>;
+				};
+				ethernet@2 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x2>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy23>;
+				};
+				ethernet@3 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x3>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy24>;
+				};
+			};
+
+			interface@1 {
+				compatible = "cavium,octeon-3860-pip-interface";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0x1>; /* interface */
+
+				ethernet@0 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x0>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+				};
+			};
+
+			interface@0 {
+				compatible = "cavium,octeon-3860-pip-interface";
+				#address-cells = <1>;
+				#size-cells = <0>;
+				reg = <0x0>; /* interface */
+
+				ethernet@0 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x0>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy41>;
+				};
+				ethernet@1 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x1>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy42>;
+				};
+				ethernet@2 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x2>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy43>;
+				};
+				ethernet@3 {
+					compatible = "cavium,octeon-3860-pip-port";
+					reg = <0x3>; /* Port */
+					local-mac-address = [ 00 00 00 00 00 00 ];
+					phy-handle = <&phy44>;
+				};
+			};
+		};
+
+		twsi0: i2c@1180000001000 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "cavium,octeon-3860-twsi";
+			reg = <0x11800 0x00001000 0x0 0x200>;
+			interrupts = <3 32>;
+			clock-frequency = <100000>;
+
+			rtc@68 {
+				compatible = "dallas,ds1337";
+				reg = <0x68>;
+			};
+			tmp@4c {
+				compatible = "ti,tmp421";
+				reg = <0x4c>;
+			};
+		};
+
+		twsi1: i2c@1180000001200 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "cavium,octeon-3860-twsi";
+			reg = <0x11800 0x00001200 0x0 0x200>;
+			interrupts = <3 33>;
+			clock-frequency = <100000>;
+		};
+
+		uart0: serial@1180000000800 {
+			compatible = "cavium,octeon-3860-uart","ns16550";
+			reg = <0x11800 0x00000800 0x0 0x400>;
+			clock-frequency = <0>;
+			current-speed = <115200>;
+			reg-shift = <3>;
+			interrupts = <3 36>;
+		};
+
+		uart1: serial@1180000000c00 {
+			compatible = "cavium,octeon-3860-uart","ns16550";
+			reg = <0x11800 0x00000c00 0x0 0x400>;
+			clock-frequency = <0>;
+			current-speed = <115200>;
+			reg-shift = <3>;
+			interrupts = <3 37>;
+		};
+
+		bootbus: bootbus@1180000000000 {
+			compatible = "cavium,octeon-3860-bootbus";
+			reg = <0x11800 0x00000000 0x0 0x200>;
+			/* The chip select number and offset */
+			#address-cells = <2>;
+			/* The size of the chip select region */
+			#size-cells = <1>;
+			ranges = <0 0  0       0x1f400000  0xc00000>,
+				 <1 0  0x10000 0x30000000  0>,
+				 <2 0  0x10000 0x40000000  0>,
+				 <3 0  0x10000 0x50000000  0>,
+				 <4 0  0       0x1d020000  0x10000>,
+				 <5 0  0       0x1d040000  0x10000>,
+				 <6 0  0       0x1d050000  0x10000>,
+				 <7 0  0x10000 0x90000000  0>;
+
+			cavium,cs-config@0 {
+				compatible = "cavium,octeon-3860-bootbus-config";
+				cavium,cs-index = <0>;
+				cavium,t-adr  = <10>;
+				cavium,t-ce   = <50>;
+				cavium,t-oe   = <50>;
+				cavium,t-we   = <35>;
+				cavium,t-rd-hld = <25>;
+				cavium,t-wr-hld = <35>;
+				cavium,t-pause  = <0>;
+				cavium,t-wait   = <300>;
+				cavium,t-page   = <25>;
+				cavium,t-rd-dly = <0>;
+
+				cavium,pages     = <0>;
+				cavium,bus-width = <8>;
+			};
+			cavium,cs-config@4 {
+				compatible = "cavium,octeon-3860-bootbus-config";
+				cavium,cs-index = <4>;
+				cavium,t-adr  = <320>;
+				cavium,t-ce   = <320>;
+				cavium,t-oe   = <320>;
+				cavium,t-we   = <320>;
+				cavium,t-rd-hld = <320>;
+				cavium,t-wr-hld = <320>;
+				cavium,t-pause  = <320>;
+				cavium,t-wait   = <320>;
+				cavium,t-page   = <320>;
+				cavium,t-rd-dly = <0>;
+
+				cavium,pages     = <0>;
+				cavium,bus-width = <8>;
+			};
+			cavium,cs-config@5 {
+				compatible = "cavium,octeon-3860-bootbus-config";
+				cavium,cs-index = <5>;
+				cavium,t-adr  = <0>;
+				cavium,t-ce   = <300>;
+				cavium,t-oe   = <125>;
+				cavium,t-we   = <150>;
+				cavium,t-rd-hld = <100>;
+				cavium,t-wr-hld = <300>;
+				cavium,t-pause  = <0>;
+				cavium,t-wait   = <300>;
+				cavium,t-page   = <310>;
+				cavium,t-rd-dly = <0>;
+
+				cavium,pages     = <0>;
+				cavium,bus-width = <16>;
+			};
+			cavium,cs-config@6 {
+				compatible = "cavium,octeon-3860-bootbus-config";
+				cavium,cs-index = <6>;
+				cavium,t-adr  = <0>;
+				cavium,t-ce   = <30>;
+				cavium,t-oe   = <125>;
+				cavium,t-we   = <150>;
+				cavium,t-rd-hld = <100>;
+				cavium,t-wr-hld = <30>;
+				cavium,t-pause  = <0>;
+				cavium,t-wait   = <30>;
+				cavium,t-page   = <310>;
+				cavium,t-rd-dly = <0>;
+
+				cavium,pages     = <0>;
+				cavium,wait-mode;
+				cavium,bus-width = <16>;
+			};
+
+			flash0: nor@0,0 {
+				compatible = "cfi-flash";
+				reg = <0 0 0x800000>;
+				#address-cells = <1>;
+				#size-cells = <1>;
+
+				partition@0 {
+					label = "bootloader";
+					reg = <0 0x200000>;
+					read-only;
+				};
+				partition@200000 {
+					label = "kernel";
+					reg = <0x200000 0x200000>;
+				};
+				partition@400000 {
+					label = "cramfs";
+					reg = <0x400000 0x3fe000>;
+				};
+				partition@7fe000 {
+					label = "environment";
+					reg = <0x7fe000 0x2000>;
+					read-only;
+				};
+			};
+
+			led0: led-display@4,0 {
+				compatible = "avago,hdsp-253x";
+				reg = <4 0x20 0x20>, <4 0 0x20>;
+			};
+
+			compact-flash@5,0 {
+				compatible = "cavium,ebt3000-compact-flash";
+				reg = <5 0 0x10000>, <6 0 0x10000>;
+				cavium,bus-width = <16>;
+				cavium,true-ide;
+				cavium,dma-engine-handle = <&dma0>;
+			};
+		};
+
+		dma0: dma-engine@1180000000100 {
+			compatible = "cavium,octeon-5750-bootbus-dma";
+			reg = <0x11800 0x00000100 0x0 0x8>;
+			interrupts = <0 63>;
+		};
+		dma1: dma-engine@1180000000108 {
+			compatible = "cavium,octeon-5750-bootbus-dma";
+			reg = <0x11800 0x00000108 0x0 0x8>;
+			interrupts = <0 63>;
+		};
+
+		uctl: uctl@118006f000000 {
+			compatible = "cavium,octeon-6335-uctl";
+			reg = <0x11800 0x6f000000 0x0 0x100>;
+			ranges; /* Direct mapping */
+			#address-cells = <2>;
+			#size-cells = <2>;
+			/* 12MHz, 24MHz and 48MHz allowed */
+			refclk-frequency = <12000000>;
+			/* Either "crystal" or "external" */
+			refclk-type = "crystal";
+
+			ehci@16f0000000000 {
+				compatible = "cavium,octeon-6335-ehci","usb-ehci";
+				reg = <0x16f00 0x00000000 0x0 0x100>;
+				interrupts = <3 44>;
+				big-endian-regs;
+			};
+			ohci@16f0000000400 {
+				compatible = "cavium,octeon-6335-ohci","usb-ohci";
+				reg = <0x16f00 0x00000400 0x0 0x100>;
+				interrupts = <3 44>;
+				big-endian-regs;
+			};
+		};
+	};
+
+	aliases {
+		mix0 = &mix0;
+		pip = &pip;
+		smi0 = &smi0;
+		smi1 = &smi1;
+		smi2 = &smi2;
+		smi3 = &smi3;
+		twsi0 = &twsi0;
+		twsi1 = &twsi1;
+		uart0 = &uart0;
+		uart1 = &uart1;
+		uctl = &uctl;
+		led0 = &led0;
+		flash0 = &flash0;
+	};
+ };
diff --git a/arch/mips/cavium-octeon/serial.c b/arch/mips/cavium-octeon/serial.c
index 057f0ae88c99..138b2216b4f8 100644
--- a/arch/mips/cavium-octeon/serial.c
+++ b/arch/mips/cavium-octeon/serial.c
@@ -43,95 +43,67 @@ void octeon_serial_out(struct uart_port *up, int offset, int value)
 	cvmx_write_csr((uint64_t)(up->membase + (offset << 3)), (u8)value);
 }
 
-/*
- * Allocated in .bss, so it is all zeroed.
- */
-#define OCTEON_MAX_UARTS 3
-static struct plat_serial8250_port octeon_uart8250_data[OCTEON_MAX_UARTS + 1];
-static struct platform_device octeon_uart8250_device = {
-	.name			= "serial8250",
-	.id			= PLAT8250_DEV_PLATFORM,
-	.dev			= {
-		.platform_data	= octeon_uart8250_data,
-	},
-};
-
-static void __init octeon_uart_set_common(struct plat_serial8250_port *p)
+static int __devinit octeon_serial_probe(struct platform_device *pdev)
 {
-	p->flags = ASYNC_SKIP_TEST | UPF_SHARE_IRQ | UPF_FIXED_TYPE;
-	p->type = PORT_OCTEON;
-	p->iotype = UPIO_MEM;
-	p->regshift = 3;	/* I/O addresses are every 8 bytes */
+	int irq, res;
+	struct resource *res_mem;
+	struct uart_port port;
+
+	/* All adaptors have an irq.  */
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	memset(&port, 0, sizeof(port));
+
+	port.flags = ASYNC_SKIP_TEST | UPF_SHARE_IRQ | UPF_FIXED_TYPE;
+	port.type = PORT_OCTEON;
+	port.iotype = UPIO_MEM;
+	port.regshift = 3;
+	port.dev = &pdev->dev;
+
 	if (octeon_is_simulation())
 		/* Make simulator output fast*/
-		p->uartclk = 115200 * 16;
+		port.uartclk = 115200 * 16;
 	else
-		p->uartclk = octeon_get_io_clock_rate();
-	p->serial_in = octeon_serial_in;
-	p->serial_out = octeon_serial_out;
-}
+		port.uartclk = octeon_get_io_clock_rate();
 
-static int __init octeon_serial_init(void)
-{
-	int enable_uart0;
-	int enable_uart1;
-	int enable_uart2;
-	struct plat_serial8250_port *p;
-
-#ifdef CONFIG_CAVIUM_OCTEON_2ND_KERNEL
-	/*
-	 * If we are configured to run as the second of two kernels,
-	 * disable uart0 and enable uart1. Uart0 is owned by the first
-	 * kernel
-	 */
-	enable_uart0 = 0;
-	enable_uart1 = 1;
-#else
-	/*
-	 * We are configured for the first kernel. We'll enable uart0
-	 * if the bootloader told us to use 0, otherwise will enable
-	 * uart 1.
-	 */
-	enable_uart0 = (octeon_get_boot_uart() == 0);
-	enable_uart1 = (octeon_get_boot_uart() == 1);
-#ifdef CONFIG_KGDB
-	enable_uart1 = 1;
-#endif
-#endif
-
-	/* Right now CN52XX is the only chip with a third uart */
-	enable_uart2 = OCTEON_IS_MODEL(OCTEON_CN52XX);
-
-	p = octeon_uart8250_data;
-	if (enable_uart0) {
-		/* Add a ttyS device for hardware uart 0 */
-		octeon_uart_set_common(p);
-		p->membase = (void *) CVMX_MIO_UARTX_RBR(0);
-		p->mapbase = CVMX_MIO_UARTX_RBR(0) & ((1ull << 49) - 1);
-		p->irq = OCTEON_IRQ_UART0;
-		p++;
-	}
+	port.serial_in = octeon_serial_in;
+	port.serial_out = octeon_serial_out;
+	port.irq = irq;
 
-	if (enable_uart1) {
-		/* Add a ttyS device for hardware uart 1 */
-		octeon_uart_set_common(p);
-		p->membase = (void *) CVMX_MIO_UARTX_RBR(1);
-		p->mapbase = CVMX_MIO_UARTX_RBR(1) & ((1ull << 49) - 1);
-		p->irq = OCTEON_IRQ_UART1;
-		p++;
-	}
-	if (enable_uart2) {
-		/* Add a ttyS device for hardware uart 2 */
-		octeon_uart_set_common(p);
-		p->membase = (void *) CVMX_MIO_UART2_RBR;
-		p->mapbase = CVMX_MIO_UART2_RBR & ((1ull << 49) - 1);
-		p->irq = OCTEON_IRQ_UART2;
-		p++;
+	res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res_mem == NULL) {
+		dev_err(&pdev->dev, "found no memory resource\n");
+		return -ENXIO;
 	}
+	port.mapbase = res_mem->start;
+	port.membase = ioremap(res_mem->start, resource_size(res_mem));
 
-	BUG_ON(p > &octeon_uart8250_data[OCTEON_MAX_UARTS]);
+	res = serial8250_register_port(&port);
 
-	return platform_device_register(&octeon_uart8250_device);
+	return res >= 0 ? 0 : res;
 }
 
-device_initcall(octeon_serial_init);
+static struct of_device_id octeon_serial_match[] = {
+	{
+		.compatible = "cavium,octeon-3860-uart",
+	},
+	{},
+};
+MODULE_DEVICE_TABLE(of, octeon_serial_match);
+
+static struct platform_driver octeon_serial_driver = {
+	.probe		= octeon_serial_probe,
+	.driver		= {
+		.owner	= THIS_MODULE,
+		.name	= "octeon_serial",
+		.of_match_table = octeon_serial_match,
+	},
+};
+
+static int __init octeon_serial_init(void)
+{
+	return platform_driver_register(&octeon_serial_driver);
+}
+late_initcall(octeon_serial_init);
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 260dc247c052..919b0fb7bb1a 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -21,6 +21,8 @@
 #include <linux/platform_device.h>
 #include <linux/serial_core.h>
 #include <linux/serial_8250.h>
+#include <linux/of_fdt.h>
+#include <linux/libfdt.h>
 
 #include <asm/processor.h>
 #include <asm/reboot.h>
@@ -775,3 +777,46 @@ void prom_free_prom_memory(void)
 	}
 #endif
 }
+
+int octeon_prune_device_tree(void);
+
+extern const char __dtb_octeon_3xxx_begin;
+extern const char __dtb_octeon_3xxx_end;
+extern const char __dtb_octeon_68xx_begin;
+extern const char __dtb_octeon_68xx_end;
+void __init device_tree_init(void)
+{
+	int dt_size;
+	struct boot_param_header *fdt;
+	bool do_prune;
+
+	if (octeon_bootinfo->minor_version >= 3 && octeon_bootinfo->fdt_addr) {
+		fdt = phys_to_virt(octeon_bootinfo->fdt_addr);
+		if (fdt_check_header(fdt))
+			panic("Corrupt Device Tree passed to kernel.");
+		dt_size = be32_to_cpu(fdt->totalsize);
+		do_prune = false;
+	} else if (OCTEON_IS_MODEL(OCTEON_CN68XX)) {
+		fdt = (struct boot_param_header *)&__dtb_octeon_68xx_begin;
+		dt_size = &__dtb_octeon_68xx_end - &__dtb_octeon_68xx_begin;
+		do_prune = true;
+	} else {
+		fdt = (struct boot_param_header *)&__dtb_octeon_3xxx_begin;
+		dt_size = &__dtb_octeon_3xxx_end - &__dtb_octeon_3xxx_begin;
+		do_prune = true;
+	}
+
+	/* Copy the default tree from init memory. */
+	initial_boot_params = early_init_dt_alloc_memory_arch(dt_size, 8);
+	if (initial_boot_params == NULL)
+		panic("Could not allocate initial_boot_params\n");
+	memcpy(initial_boot_params, fdt, dt_size);
+
+	if (do_prune) {
+		octeon_prune_device_tree();
+		pr_info("Using internal Device Tree.\n");
+	} else {
+		pr_info("Using passed Device Tree.\n");
+	}
+	unflatten_device_tree();
+}
diff --git a/arch/mips/configs/ls1b_defconfig b/arch/mips/configs/ls1b_defconfig
new file mode 100644
index 000000000000..80cff8bea8e8
--- /dev/null
+++ b/arch/mips/configs/ls1b_defconfig
@@ -0,0 +1,109 @@
+CONFIG_MACH_LOONGSON1=y
+CONFIG_PREEMPT=y
+# CONFIG_SECCOMP is not set
+CONFIG_EXPERIMENTAL=y
+# CONFIG_LOCALVERSION_AUTO is not set
+CONFIG_SYSVIPC=y
+CONFIG_BSD_PROCESS_ACCT=y
+CONFIG_BSD_PROCESS_ACCT_V3=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=16
+CONFIG_NAMESPACES=y
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_RD_BZIP2=y
+CONFIG_RD_LZMA=y
+CONFIG_EXPERT=y
+CONFIG_PERF_EVENTS=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_MODULES=y
+CONFIG_MODULE_UNLOAD=y
+CONFIG_MODVERSIONS=y
+# CONFIG_LBDAF is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
+# CONFIG_SUSPEND is not set
+CONFIG_NET=y
+CONFIG_PACKET=y
+CONFIG_UNIX=y
+CONFIG_INET=y
+CONFIG_IP_PNP=y
+CONFIG_IP_PNP_DHCP=y
+CONFIG_SYN_COOKIES=y
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_WIRELESS is not set
+CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
+CONFIG_DEVTMPFS=y
+CONFIG_DEVTMPFS_MOUNT=y
+# CONFIG_STANDALONE is not set
+CONFIG_BLK_DEV_LOOP=y
+CONFIG_SCSI=m
+# CONFIG_SCSI_PROC_FS is not set
+CONFIG_BLK_DEV_SD=m
+# CONFIG_SCSI_LOWLEVEL is not set
+CONFIG_NETDEVICES=y
+# CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_VENDOR_CHELSIO is not set
+# CONFIG_NET_VENDOR_INTEL is not set
+# CONFIG_NET_VENDOR_MARVELL is not set
+# CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_NATSEMI is not set
+# CONFIG_NET_VENDOR_SEEQ is not set
+# CONFIG_NET_VENDOR_SMSC is not set
+CONFIG_STMMAC_ETH=y
+CONFIG_STMMAC_DA=y
+# CONFIG_NET_VENDOR_WIZNET is not set
+# CONFIG_WLAN is not set
+CONFIG_INPUT_EVDEV=y
+# CONFIG_INPUT_KEYBOARD is not set
+# CONFIG_INPUT_MOUSE is not set
+# CONFIG_SERIO is not set
+CONFIG_VT_HW_CONSOLE_BINDING=y
+CONFIG_LEGACY_PTY_COUNT=8
+# CONFIG_DEVKMEM is not set
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+# CONFIG_HW_RANDOM is not set
+# CONFIG_HWMON is not set
+# CONFIG_VGA_CONSOLE is not set
+CONFIG_USB_HID=m
+CONFIG_HID_GENERIC=m
+CONFIG_USB=y
+CONFIG_USB_ANNOUNCE_NEW_DEVICES=y
+CONFIG_USB_EHCI_HCD=y
+# CONFIG_USB_EHCI_TT_NEWSCHED is not set
+CONFIG_USB_STORAGE=m
+CONFIG_USB_SERIAL=m
+CONFIG_USB_SERIAL_PL2303=m
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_LOONGSON1=y
+# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_EXT2_FS=y
+CONFIG_EXT2_FS_XATTR=y
+CONFIG_EXT2_FS_POSIX_ACL=y
+CONFIG_EXT2_FS_SECURITY=y
+CONFIG_EXT3_FS=y
+CONFIG_EXT3_FS_POSIX_ACL=y
+CONFIG_EXT3_FS_SECURITY=y
+# CONFIG_DNOTIFY is not set
+CONFIG_VFAT_FS=y
+CONFIG_PROC_KCORE=y
+CONFIG_TMPFS=y
+CONFIG_TMPFS_POSIX_ACL=y
+# CONFIG_MISC_FILESYSTEMS is not set
+CONFIG_NFS_FS=y
+CONFIG_ROOT_NFS=y
+CONFIG_NLS_CODEPAGE_437=m
+CONFIG_NLS_ISO8859_1=m
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_MAGIC_SYSRQ=y
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_DEBUG_PREEMPT is not set
+# CONFIG_FTRACE is not set
+# CONFIG_EARLY_PRINTK is not set
diff --git a/arch/mips/configs/nlm_xlr_defconfig b/arch/mips/configs/nlm_xlr_defconfig
index d0b857d98c91..138f698d7c00 100644
--- a/arch/mips/configs/nlm_xlr_defconfig
+++ b/arch/mips/configs/nlm_xlr_defconfig
@@ -367,6 +367,10 @@ CONFIG_SERIAL_8250_RSA=y
 CONFIG_HW_RANDOM=y
 CONFIG_HW_RANDOM_TIMERIOMEM=m
 CONFIG_RAW_DRIVER=m
+CONFIG_I2C=y
+CONFIG_I2C_XLR=y
+CONFIG_RTC_CLASS=y
+CONFIG_RTC_DRV_DS1374=y
 # CONFIG_HWMON is not set
 # CONFIG_VGA_CONSOLE is not set
 # CONFIG_HID_SUPPORT is not set
diff --git a/arch/mips/dec/prom/memory.c b/arch/mips/dec/prom/memory.c
index e95ff3054ff6..8c62316f22f4 100644
--- a/arch/mips/dec/prom/memory.c
+++ b/arch/mips/dec/prom/memory.c
@@ -101,7 +101,7 @@ void __init prom_free_prom_memory(void)
 	 * the first page reserved for the exception handlers.
 	 */
 
-#if defined(CONFIG_DECLANCE) || defined(CONFIG_DECLANCE_MODULE)
+#if IS_ENABLED(CONFIG_DECLANCE)
 	/*
 	 * Leave 128 KB reserved for Lance memory for
 	 * IOASIC DECstations.
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 95e40c1e8ed1..f21b7c04e95a 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -197,6 +197,7 @@
 #define PRID_REV_VR4181A	0x0070	/* Same as VR4122 */
 #define PRID_REV_VR4130		0x0080
 #define PRID_REV_34K_V1_0_2	0x0022
+#define PRID_REV_LOONGSON1B	0x0020
 #define PRID_REV_LOONGSON2E	0x0002
 #define PRID_REV_LOONGSON2F	0x0003
 
@@ -261,7 +262,7 @@ enum cpu_type_enum {
 	 */
 	CPU_4KC, CPU_4KEC, CPU_4KSC, CPU_24K, CPU_34K, CPU_1004K, CPU_74K,
 	CPU_ALCHEMY, CPU_PR4450, CPU_BMIPS32, CPU_BMIPS3300, CPU_BMIPS4350,
-	CPU_BMIPS4380, CPU_BMIPS5000, CPU_JZRISC, CPU_M14KC,
+	CPU_BMIPS4380, CPU_BMIPS5000, CPU_JZRISC, CPU_LOONGSON1, CPU_M14KC,
 
 	/*
 	 * MIPS64 class processors
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_cpu.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_cpu.h
index 5b8d15bb5fe8..e104ddb694a8 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_cpu.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_cpu.h
@@ -9,6 +9,7 @@
  * compile time if only one CPU support is enabled (idea stolen from
  * arm mach-types)
  */
+#define BCM6328_CPU_ID		0x6328
 #define BCM6338_CPU_ID		0x6338
 #define BCM6345_CPU_ID		0x6345
 #define BCM6348_CPU_ID		0x6348
@@ -20,6 +21,19 @@ u16 __bcm63xx_get_cpu_id(void);
 u16 bcm63xx_get_cpu_rev(void);
 unsigned int bcm63xx_get_cpu_freq(void);
 
+#ifdef CONFIG_BCM63XX_CPU_6328
+# ifdef bcm63xx_get_cpu_id
+#  undef bcm63xx_get_cpu_id
+#  define bcm63xx_get_cpu_id()	__bcm63xx_get_cpu_id()
+#  define BCMCPU_RUNTIME_DETECT
+# else
+#  define bcm63xx_get_cpu_id()	BCM6328_CPU_ID
+# endif
+# define BCMCPU_IS_6328()	(bcm63xx_get_cpu_id() == BCM6328_CPU_ID)
+#else
+# define BCMCPU_IS_6328()	(0)
+#endif
+
 #ifdef CONFIG_BCM63XX_CPU_6338
 # ifdef bcm63xx_get_cpu_id
 #  undef bcm63xx_get_cpu_id
@@ -102,13 +116,13 @@ enum bcm63xx_regs_set {
 	RSET_UART1,
 	RSET_GPIO,
 	RSET_SPI,
-	RSET_SPI2,
 	RSET_UDC0,
 	RSET_OHCI0,
 	RSET_OHCI_PRIV,
 	RSET_USBH_PRIV,
 	RSET_MPI,
 	RSET_PCMCIA,
+	RSET_PCIE,
 	RSET_DSL,
 	RSET_ENET0,
 	RSET_ENET1,
@@ -130,11 +144,17 @@ enum bcm63xx_regs_set {
 	RSET_PCMDMA,
 	RSET_PCMDMAC,
 	RSET_PCMDMAS,
+	RSET_RNG,
+	RSET_MISC
 };
 
 #define RSET_DSL_LMEM_SIZE		(64 * 1024 * 4)
 #define RSET_DSL_SIZE			4096
 #define RSET_WDT_SIZE			12
+#define BCM_6338_RSET_SPI_SIZE		64
+#define BCM_6348_RSET_SPI_SIZE		64
+#define BCM_6358_RSET_SPI_SIZE		1804
+#define BCM_6368_RSET_SPI_SIZE		1804
 #define RSET_ENET_SIZE			2048
 #define RSET_ENETDMA_SIZE		2048
 #define RSET_ENETSW_SIZE		65536
@@ -149,8 +169,53 @@ enum bcm63xx_regs_set {
 #define RSET_XTMDMA_SIZE		256
 #define RSET_XTMDMAC_SIZE(chans)	(16 * (chans))
 #define RSET_XTMDMAS_SIZE(chans)	(16 * (chans))
+#define RSET_RNG_SIZE			20
 
 /*
+ * 6328 register sets base address
+ */
+#define BCM_6328_DSL_LMEM_BASE		(0xdeadbeef)
+#define BCM_6328_PERF_BASE		(0xb0000000)
+#define BCM_6328_TIMER_BASE		(0xb0000040)
+#define BCM_6328_WDT_BASE		(0xb000005c)
+#define BCM_6328_UART0_BASE             (0xb0000100)
+#define BCM_6328_UART1_BASE		(0xb0000120)
+#define BCM_6328_GPIO_BASE		(0xb0000080)
+#define BCM_6328_SPI_BASE		(0xdeadbeef)
+#define BCM_6328_UDC0_BASE		(0xdeadbeef)
+#define BCM_6328_USBDMA_BASE		(0xdeadbeef)
+#define BCM_6328_OHCI0_BASE		(0xdeadbeef)
+#define BCM_6328_OHCI_PRIV_BASE		(0xdeadbeef)
+#define BCM_6328_USBH_PRIV_BASE		(0xdeadbeef)
+#define BCM_6328_MPI_BASE		(0xdeadbeef)
+#define BCM_6328_PCMCIA_BASE		(0xdeadbeef)
+#define BCM_6328_PCIE_BASE		(0xb0e40000)
+#define BCM_6328_SDRAM_REGS_BASE	(0xdeadbeef)
+#define BCM_6328_DSL_BASE		(0xb0001900)
+#define BCM_6328_UBUS_BASE		(0xdeadbeef)
+#define BCM_6328_ENET0_BASE		(0xdeadbeef)
+#define BCM_6328_ENET1_BASE		(0xdeadbeef)
+#define BCM_6328_ENETDMA_BASE		(0xb000d800)
+#define BCM_6328_ENETDMAC_BASE		(0xb000da00)
+#define BCM_6328_ENETDMAS_BASE		(0xb000dc00)
+#define BCM_6328_ENETSW_BASE		(0xb0e00000)
+#define BCM_6328_EHCI0_BASE		(0x10002500)
+#define BCM_6328_SDRAM_BASE		(0xdeadbeef)
+#define BCM_6328_MEMC_BASE		(0xdeadbeef)
+#define BCM_6328_DDR_BASE		(0xb0003000)
+#define BCM_6328_M2M_BASE		(0xdeadbeef)
+#define BCM_6328_ATM_BASE		(0xdeadbeef)
+#define BCM_6328_XTM_BASE		(0xdeadbeef)
+#define BCM_6328_XTMDMA_BASE		(0xb000b800)
+#define BCM_6328_XTMDMAC_BASE		(0xdeadbeef)
+#define BCM_6328_XTMDMAS_BASE		(0xdeadbeef)
+#define BCM_6328_PCM_BASE		(0xb000a800)
+#define BCM_6328_PCMDMA_BASE		(0xdeadbeef)
+#define BCM_6328_PCMDMAC_BASE		(0xdeadbeef)
+#define BCM_6328_PCMDMAS_BASE		(0xdeadbeef)
+#define BCM_6328_RNG_BASE		(0xdeadbeef)
+#define BCM_6328_MISC_BASE		(0xb0001800)
+/*
  * 6338 register sets base address
  */
 #define BCM_6338_DSL_LMEM_BASE		(0xfff00000)
@@ -162,7 +227,6 @@ enum bcm63xx_regs_set {
 #define BCM_6338_UART1_BASE		(0xdeadbeef)
 #define BCM_6338_GPIO_BASE		(0xfffe0400)
 #define BCM_6338_SPI_BASE		(0xfffe0c00)
-#define BCM_6338_SPI2_BASE		(0xdeadbeef)
 #define BCM_6338_UDC0_BASE		(0xdeadbeef)
 #define BCM_6338_USBDMA_BASE		(0xfffe2400)
 #define BCM_6338_OHCI0_BASE		(0xdeadbeef)
@@ -170,6 +234,7 @@ enum bcm63xx_regs_set {
 #define BCM_6338_USBH_PRIV_BASE		(0xdeadbeef)
 #define BCM_6338_MPI_BASE		(0xfffe3160)
 #define BCM_6338_PCMCIA_BASE		(0xdeadbeef)
+#define BCM_6338_PCIE_BASE		(0xdeadbeef)
 #define BCM_6338_SDRAM_REGS_BASE	(0xfffe3100)
 #define BCM_6338_DSL_BASE		(0xfffe1000)
 #define BCM_6338_UBUS_BASE		(0xdeadbeef)
@@ -193,6 +258,8 @@ enum bcm63xx_regs_set {
 #define BCM_6338_PCMDMA_BASE		(0xdeadbeef)
 #define BCM_6338_PCMDMAC_BASE		(0xdeadbeef)
 #define BCM_6338_PCMDMAS_BASE		(0xdeadbeef)
+#define BCM_6338_RNG_BASE		(0xdeadbeef)
+#define BCM_6338_MISC_BASE		(0xdeadbeef)
 
 /*
  * 6345 register sets base address
@@ -206,7 +273,6 @@ enum bcm63xx_regs_set {
 #define BCM_6345_UART1_BASE		(0xdeadbeef)
 #define BCM_6345_GPIO_BASE		(0xfffe0400)
 #define BCM_6345_SPI_BASE		(0xdeadbeef)
-#define BCM_6345_SPI2_BASE		(0xdeadbeef)
 #define BCM_6345_UDC0_BASE		(0xdeadbeef)
 #define BCM_6345_USBDMA_BASE		(0xfffe2800)
 #define BCM_6345_ENET0_BASE		(0xfffe1800)
@@ -216,6 +282,7 @@ enum bcm63xx_regs_set {
 #define BCM_6345_ENETSW_BASE		(0xdeadbeef)
 #define BCM_6345_PCMCIA_BASE		(0xfffe2028)
 #define BCM_6345_MPI_BASE		(0xfffe2000)
+#define BCM_6345_PCIE_BASE		(0xdeadbeef)
 #define BCM_6345_OHCI0_BASE		(0xfffe2100)
 #define BCM_6345_OHCI_PRIV_BASE		(0xfffe2200)
 #define BCM_6345_USBH_PRIV_BASE		(0xdeadbeef)
@@ -237,6 +304,8 @@ enum bcm63xx_regs_set {
 #define BCM_6345_PCMDMA_BASE		(0xdeadbeef)
 #define BCM_6345_PCMDMAC_BASE		(0xdeadbeef)
 #define BCM_6345_PCMDMAS_BASE		(0xdeadbeef)
+#define BCM_6345_RNG_BASE		(0xdeadbeef)
+#define BCM_6345_MISC_BASE		(0xdeadbeef)
 
 /*
  * 6348 register sets base address
@@ -249,13 +318,13 @@ enum bcm63xx_regs_set {
 #define BCM_6348_UART1_BASE		(0xdeadbeef)
 #define BCM_6348_GPIO_BASE		(0xfffe0400)
 #define BCM_6348_SPI_BASE		(0xfffe0c00)
-#define BCM_6348_SPI2_BASE		(0xdeadbeef)
 #define BCM_6348_UDC0_BASE		(0xfffe1000)
 #define BCM_6348_OHCI0_BASE		(0xfffe1b00)
 #define BCM_6348_OHCI_PRIV_BASE		(0xfffe1c00)
 #define BCM_6348_USBH_PRIV_BASE		(0xdeadbeef)
 #define BCM_6348_MPI_BASE		(0xfffe2000)
 #define BCM_6348_PCMCIA_BASE		(0xfffe2054)
+#define BCM_6348_PCIE_BASE		(0xdeadbeef)
 #define BCM_6348_SDRAM_REGS_BASE	(0xfffe2300)
 #define BCM_6348_M2M_BASE		(0xfffe2800)
 #define BCM_6348_DSL_BASE		(0xfffe3000)
@@ -278,6 +347,8 @@ enum bcm63xx_regs_set {
 #define BCM_6348_PCMDMA_BASE		(0xdeadbeef)
 #define BCM_6348_PCMDMAC_BASE		(0xdeadbeef)
 #define BCM_6348_PCMDMAS_BASE		(0xdeadbeef)
+#define BCM_6348_RNG_BASE		(0xdeadbeef)
+#define BCM_6348_MISC_BASE		(0xdeadbeef)
 
 /*
  * 6358 register sets base address
@@ -289,14 +360,14 @@ enum bcm63xx_regs_set {
 #define BCM_6358_UART0_BASE		(0xfffe0100)
 #define BCM_6358_UART1_BASE		(0xfffe0120)
 #define BCM_6358_GPIO_BASE		(0xfffe0080)
-#define BCM_6358_SPI_BASE		(0xdeadbeef)
-#define BCM_6358_SPI2_BASE		(0xfffe0800)
+#define BCM_6358_SPI_BASE		(0xfffe0800)
 #define BCM_6358_UDC0_BASE		(0xfffe0800)
 #define BCM_6358_OHCI0_BASE		(0xfffe1400)
 #define BCM_6358_OHCI_PRIV_BASE		(0xdeadbeef)
 #define BCM_6358_USBH_PRIV_BASE		(0xfffe1500)
 #define BCM_6358_MPI_BASE		(0xfffe1000)
 #define BCM_6358_PCMCIA_BASE		(0xfffe1054)
+#define BCM_6358_PCIE_BASE		(0xdeadbeef)
 #define BCM_6358_SDRAM_REGS_BASE	(0xfffe2300)
 #define BCM_6358_M2M_BASE		(0xdeadbeef)
 #define BCM_6358_DSL_BASE		(0xfffe3000)
@@ -319,6 +390,8 @@ enum bcm63xx_regs_set {
 #define BCM_6358_PCMDMA_BASE		(0xfffe1800)
 #define BCM_6358_PCMDMAC_BASE		(0xfffe1900)
 #define BCM_6358_PCMDMAS_BASE		(0xfffe1a00)
+#define BCM_6358_RNG_BASE		(0xdeadbeef)
+#define BCM_6358_MISC_BASE		(0xdeadbeef)
 
 
 /*
@@ -331,14 +404,14 @@ enum bcm63xx_regs_set {
 #define BCM_6368_UART0_BASE		(0xb0000100)
 #define BCM_6368_UART1_BASE		(0xb0000120)
 #define BCM_6368_GPIO_BASE		(0xb0000080)
-#define BCM_6368_SPI_BASE		(0xdeadbeef)
-#define BCM_6368_SPI2_BASE		(0xb0000800)
+#define BCM_6368_SPI_BASE		(0xb0000800)
 #define BCM_6368_UDC0_BASE		(0xdeadbeef)
 #define BCM_6368_OHCI0_BASE		(0xb0001600)
 #define BCM_6368_OHCI_PRIV_BASE		(0xdeadbeef)
 #define BCM_6368_USBH_PRIV_BASE		(0xb0001700)
 #define BCM_6368_MPI_BASE		(0xb0001000)
 #define BCM_6368_PCMCIA_BASE		(0xb0001054)
+#define BCM_6368_PCIE_BASE		(0xdeadbeef)
 #define BCM_6368_SDRAM_REGS_BASE	(0xdeadbeef)
 #define BCM_6368_M2M_BASE		(0xdeadbeef)
 #define BCM_6368_DSL_BASE		(0xdeadbeef)
@@ -361,6 +434,8 @@ enum bcm63xx_regs_set {
 #define BCM_6368_PCMDMA_BASE		(0xb0005800)
 #define BCM_6368_PCMDMAC_BASE		(0xb0005a00)
 #define BCM_6368_PCMDMAS_BASE		(0xb0005c00)
+#define BCM_6368_RNG_BASE		(0xb0004180)
+#define BCM_6368_MISC_BASE		(0xdeadbeef)
 
 
 extern const unsigned long *bcm63xx_regs_base;
@@ -379,13 +454,13 @@ extern const unsigned long *bcm63xx_regs_base;
 	__GEN_RSET_BASE(__cpu, UART1)					\
 	__GEN_RSET_BASE(__cpu, GPIO)					\
 	__GEN_RSET_BASE(__cpu, SPI)					\
-	__GEN_RSET_BASE(__cpu, SPI2)					\
 	__GEN_RSET_BASE(__cpu, UDC0)					\
 	__GEN_RSET_BASE(__cpu, OHCI0)					\
 	__GEN_RSET_BASE(__cpu, OHCI_PRIV)				\
 	__GEN_RSET_BASE(__cpu, USBH_PRIV)				\
 	__GEN_RSET_BASE(__cpu, MPI)					\
 	__GEN_RSET_BASE(__cpu, PCMCIA)					\
+	__GEN_RSET_BASE(__cpu, PCIE)					\
 	__GEN_RSET_BASE(__cpu, DSL)					\
 	__GEN_RSET_BASE(__cpu, ENET0)					\
 	__GEN_RSET_BASE(__cpu, ENET1)					\
@@ -407,6 +482,8 @@ extern const unsigned long *bcm63xx_regs_base;
 	__GEN_RSET_BASE(__cpu, PCMDMA)					\
 	__GEN_RSET_BASE(__cpu, PCMDMAC)					\
 	__GEN_RSET_BASE(__cpu, PCMDMAS)					\
+	__GEN_RSET_BASE(__cpu, RNG)					\
+	__GEN_RSET_BASE(__cpu, MISC)					\
 	}
 
 #define __GEN_CPU_REGS_TABLE(__cpu)					\
@@ -418,13 +495,13 @@ extern const unsigned long *bcm63xx_regs_base;
 	[RSET_UART1]		= BCM_## __cpu ##_UART1_BASE,		\
 	[RSET_GPIO]		= BCM_## __cpu ##_GPIO_BASE,		\
 	[RSET_SPI]		= BCM_## __cpu ##_SPI_BASE,		\
-	[RSET_SPI2]		= BCM_## __cpu ##_SPI2_BASE,		\
 	[RSET_UDC0]		= BCM_## __cpu ##_UDC0_BASE,		\
 	[RSET_OHCI0]		= BCM_## __cpu ##_OHCI0_BASE,		\
 	[RSET_OHCI_PRIV]	= BCM_## __cpu ##_OHCI_PRIV_BASE,	\
 	[RSET_USBH_PRIV]	= BCM_## __cpu ##_USBH_PRIV_BASE,	\
 	[RSET_MPI]		= BCM_## __cpu ##_MPI_BASE,		\
 	[RSET_PCMCIA]		= BCM_## __cpu ##_PCMCIA_BASE,		\
+	[RSET_PCIE]		= BCM_## __cpu ##_PCIE_BASE,		\
 	[RSET_DSL]		= BCM_## __cpu ##_DSL_BASE,		\
 	[RSET_ENET0]		= BCM_## __cpu ##_ENET0_BASE,		\
 	[RSET_ENET1]		= BCM_## __cpu ##_ENET1_BASE,		\
@@ -446,6 +523,8 @@ extern const unsigned long *bcm63xx_regs_base;
 	[RSET_PCMDMA]		= BCM_## __cpu ##_PCMDMA_BASE,		\
 	[RSET_PCMDMAC]		= BCM_## __cpu ##_PCMDMAC_BASE,		\
 	[RSET_PCMDMAS]		= BCM_## __cpu ##_PCMDMAS_BASE,		\
+	[RSET_RNG]		= BCM_## __cpu ##_RNG_BASE,		\
+	[RSET_MISC]		= BCM_## __cpu ##_MISC_BASE,		\
 
 
 static inline unsigned long bcm63xx_regset_address(enum bcm63xx_regs_set set)
@@ -453,6 +532,9 @@ static inline unsigned long bcm63xx_regset_address(enum bcm63xx_regs_set set)
 #ifdef BCMCPU_RUNTIME_DETECT
 	return bcm63xx_regs_base[set];
 #else
+#ifdef CONFIG_BCM63XX_CPU_6328
+	__GEN_RSET(6328)
+#endif
 #ifdef CONFIG_BCM63XX_CPU_6338
 	__GEN_RSET(6338)
 #endif
@@ -478,6 +560,7 @@ static inline unsigned long bcm63xx_regset_address(enum bcm63xx_regs_set set)
  */
 enum bcm63xx_irq {
 	IRQ_TIMER = 0,
+	IRQ_SPI,
 	IRQ_UART0,
 	IRQ_UART1,
 	IRQ_DSL,
@@ -506,9 +589,51 @@ enum bcm63xx_irq {
 };
 
 /*
+ * 6328 irqs
+ */
+#define BCM_6328_HIGH_IRQ_BASE		(IRQ_INTERNAL_BASE + 32)
+
+#define BCM_6328_TIMER_IRQ		(IRQ_INTERNAL_BASE + 31)
+#define BCM_6328_SPI_IRQ		0
+#define BCM_6328_UART0_IRQ		(IRQ_INTERNAL_BASE + 28)
+#define BCM_6328_UART1_IRQ		(BCM_6328_HIGH_IRQ_BASE + 7)
+#define BCM_6328_DSL_IRQ		(IRQ_INTERNAL_BASE + 4)
+#define BCM_6328_UDC0_IRQ		0
+#define BCM_6328_ENET0_IRQ		0
+#define BCM_6328_ENET1_IRQ		0
+#define BCM_6328_ENET_PHY_IRQ		(IRQ_INTERNAL_BASE + 12)
+#define BCM_6328_OHCI0_IRQ		(IRQ_INTERNAL_BASE + 9)
+#define BCM_6328_EHCI0_IRQ		(IRQ_INTERNAL_BASE + 10)
+#define BCM_6328_PCMCIA_IRQ		0
+#define BCM_6328_ENET0_RXDMA_IRQ	0
+#define BCM_6328_ENET0_TXDMA_IRQ	0
+#define BCM_6328_ENET1_RXDMA_IRQ	0
+#define BCM_6328_ENET1_TXDMA_IRQ	0
+#define BCM_6328_PCI_IRQ		(IRQ_INTERNAL_BASE + 23)
+#define BCM_6328_ATM_IRQ		0
+#define BCM_6328_ENETSW_RXDMA0_IRQ	(BCM_6328_HIGH_IRQ_BASE + 0)
+#define BCM_6328_ENETSW_RXDMA1_IRQ	(BCM_6328_HIGH_IRQ_BASE + 1)
+#define BCM_6328_ENETSW_RXDMA2_IRQ	(BCM_6328_HIGH_IRQ_BASE + 2)
+#define BCM_6328_ENETSW_RXDMA3_IRQ	(BCM_6328_HIGH_IRQ_BASE + 3)
+#define BCM_6328_ENETSW_TXDMA0_IRQ	(BCM_6328_HIGH_IRQ_BASE + 4)
+#define BCM_6328_ENETSW_TXDMA1_IRQ	(BCM_6328_HIGH_IRQ_BASE + 5)
+#define BCM_6328_ENETSW_TXDMA2_IRQ	(BCM_6328_HIGH_IRQ_BASE + 6)
+#define BCM_6328_ENETSW_TXDMA3_IRQ	(BCM_6328_HIGH_IRQ_BASE + 7)
+#define BCM_6328_XTM_IRQ		(BCM_6328_HIGH_IRQ_BASE + 31)
+#define BCM_6328_XTM_DMA0_IRQ		(BCM_6328_HIGH_IRQ_BASE + 11)
+
+#define BCM_6328_PCM_DMA0_IRQ		(IRQ_INTERNAL_BASE + 2)
+#define BCM_6328_PCM_DMA1_IRQ		(IRQ_INTERNAL_BASE + 3)
+#define BCM_6328_EXT_IRQ0		(IRQ_INTERNAL_BASE + 24)
+#define BCM_6328_EXT_IRQ1		(IRQ_INTERNAL_BASE + 25)
+#define BCM_6328_EXT_IRQ2		(IRQ_INTERNAL_BASE + 26)
+#define BCM_6328_EXT_IRQ3		(IRQ_INTERNAL_BASE + 27)
+
+/*
  * 6338 irqs
  */
 #define BCM_6338_TIMER_IRQ		(IRQ_INTERNAL_BASE + 0)
+#define BCM_6338_SPI_IRQ		(IRQ_INTERNAL_BASE + 1)
 #define BCM_6338_UART0_IRQ		(IRQ_INTERNAL_BASE + 2)
 #define BCM_6338_UART1_IRQ		0
 #define BCM_6338_DSL_IRQ		(IRQ_INTERNAL_BASE + 5)
@@ -539,6 +664,7 @@ enum bcm63xx_irq {
  * 6345 irqs
  */
 #define BCM_6345_TIMER_IRQ		(IRQ_INTERNAL_BASE + 0)
+#define BCM_6345_SPI_IRQ		0
 #define BCM_6345_UART0_IRQ		(IRQ_INTERNAL_BASE + 2)
 #define BCM_6345_UART1_IRQ		0
 #define BCM_6345_DSL_IRQ		(IRQ_INTERNAL_BASE + 3)
@@ -569,6 +695,7 @@ enum bcm63xx_irq {
  * 6348 irqs
  */
 #define BCM_6348_TIMER_IRQ		(IRQ_INTERNAL_BASE + 0)
+#define BCM_6348_SPI_IRQ		(IRQ_INTERNAL_BASE + 1)
 #define BCM_6348_UART0_IRQ		(IRQ_INTERNAL_BASE + 2)
 #define BCM_6348_UART1_IRQ		0
 #define BCM_6348_DSL_IRQ		(IRQ_INTERNAL_BASE + 4)
@@ -599,6 +726,7 @@ enum bcm63xx_irq {
  * 6358 irqs
  */
 #define BCM_6358_TIMER_IRQ		(IRQ_INTERNAL_BASE + 0)
+#define BCM_6358_SPI_IRQ		(IRQ_INTERNAL_BASE + 1)
 #define BCM_6358_UART0_IRQ		(IRQ_INTERNAL_BASE + 2)
 #define BCM_6358_UART1_IRQ		(IRQ_INTERNAL_BASE + 3)
 #define BCM_6358_DSL_IRQ		(IRQ_INTERNAL_BASE + 29)
@@ -638,6 +766,7 @@ enum bcm63xx_irq {
 #define BCM_6368_HIGH_IRQ_BASE		(IRQ_INTERNAL_BASE + 32)
 
 #define BCM_6368_TIMER_IRQ		(IRQ_INTERNAL_BASE + 0)
+#define BCM_6368_SPI_IRQ		(IRQ_INTERNAL_BASE + 1)
 #define BCM_6368_UART0_IRQ		(IRQ_INTERNAL_BASE + 2)
 #define BCM_6368_UART1_IRQ		(IRQ_INTERNAL_BASE + 3)
 #define BCM_6368_DSL_IRQ		(IRQ_INTERNAL_BASE + 4)
@@ -677,6 +806,7 @@ extern const int *bcm63xx_irqs;
 
 #define __GEN_CPU_IRQ_TABLE(__cpu)					\
 	[IRQ_TIMER]		= BCM_## __cpu ##_TIMER_IRQ,		\
+	[IRQ_SPI]		= BCM_## __cpu ##_SPI_IRQ,		\
 	[IRQ_UART0]		= BCM_## __cpu ##_UART0_IRQ,		\
 	[IRQ_UART1]		= BCM_## __cpu ##_UART1_IRQ,		\
 	[IRQ_DSL]		= BCM_## __cpu ##_DSL_IRQ,		\
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_flash.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_flash.h
new file mode 100644
index 000000000000..354b8481ec4a
--- /dev/null
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_flash.h
@@ -0,0 +1,12 @@
+#ifndef __BCM63XX_FLASH_H
+#define __BCM63XX_FLASH_H
+
+enum {
+	BCM63XX_FLASH_TYPE_PARALLEL,
+	BCM63XX_FLASH_TYPE_SERIAL,
+	BCM63XX_FLASH_TYPE_NAND,
+};
+
+int __init bcm63xx_flash_register(void);
+
+#endif /* __BCM63XX_FLASH_H */
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h
new file mode 100644
index 000000000000..7d98dbe5d4b5
--- /dev/null
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_dev_spi.h
@@ -0,0 +1,89 @@
+#ifndef BCM63XX_DEV_SPI_H
+#define BCM63XX_DEV_SPI_H
+
+#include <linux/types.h>
+#include <bcm63xx_io.h>
+#include <bcm63xx_regs.h>
+
+int __init bcm63xx_spi_register(void);
+
+struct bcm63xx_spi_pdata {
+	unsigned int	fifo_size;
+	int		bus_num;
+	int		num_chipselect;
+	u32		speed_hz;
+};
+
+enum bcm63xx_regs_spi {
+	SPI_CMD,
+	SPI_INT_STATUS,
+	SPI_INT_MASK_ST,
+	SPI_INT_MASK,
+	SPI_ST,
+	SPI_CLK_CFG,
+	SPI_FILL_BYTE,
+	SPI_MSG_TAIL,
+	SPI_RX_TAIL,
+	SPI_MSG_CTL,
+	SPI_MSG_DATA,
+	SPI_RX_DATA,
+};
+
+#define __GEN_SPI_RSET_BASE(__cpu, __rset)				\
+	case SPI_## __rset:						\
+		return SPI_## __cpu ##_## __rset;
+
+#define __GEN_SPI_RSET(__cpu)						\
+	switch (reg) {							\
+	__GEN_SPI_RSET_BASE(__cpu, CMD)					\
+	__GEN_SPI_RSET_BASE(__cpu, INT_STATUS)				\
+	__GEN_SPI_RSET_BASE(__cpu, INT_MASK_ST)				\
+	__GEN_SPI_RSET_BASE(__cpu, INT_MASK)				\
+	__GEN_SPI_RSET_BASE(__cpu, ST)					\
+	__GEN_SPI_RSET_BASE(__cpu, CLK_CFG)				\
+	__GEN_SPI_RSET_BASE(__cpu, FILL_BYTE)				\
+	__GEN_SPI_RSET_BASE(__cpu, MSG_TAIL)				\
+	__GEN_SPI_RSET_BASE(__cpu, RX_TAIL)				\
+	__GEN_SPI_RSET_BASE(__cpu, MSG_CTL)				\
+	__GEN_SPI_RSET_BASE(__cpu, MSG_DATA)				\
+	__GEN_SPI_RSET_BASE(__cpu, RX_DATA)				\
+	}
+
+#define __GEN_SPI_REGS_TABLE(__cpu)					\
+	[SPI_CMD]		= SPI_## __cpu ##_CMD,			\
+	[SPI_INT_STATUS]	= SPI_## __cpu ##_INT_STATUS,		\
+	[SPI_INT_MASK_ST]	= SPI_## __cpu ##_INT_MASK_ST,		\
+	[SPI_INT_MASK]		= SPI_## __cpu ##_INT_MASK,		\
+	[SPI_ST]		= SPI_## __cpu ##_ST,			\
+	[SPI_CLK_CFG]		= SPI_## __cpu ##_CLK_CFG,		\
+	[SPI_FILL_BYTE]		= SPI_## __cpu ##_FILL_BYTE,		\
+	[SPI_MSG_TAIL]		= SPI_## __cpu ##_MSG_TAIL,		\
+	[SPI_RX_TAIL]		= SPI_## __cpu ##_RX_TAIL,		\
+	[SPI_MSG_CTL]		= SPI_## __cpu ##_MSG_CTL,		\
+	[SPI_MSG_DATA]		= SPI_## __cpu ##_MSG_DATA,		\
+	[SPI_RX_DATA]		= SPI_## __cpu ##_RX_DATA,
+
+static inline unsigned long bcm63xx_spireg(enum bcm63xx_regs_spi reg)
+{
+#ifdef BCMCPU_RUNTIME_DETECT
+	extern const unsigned long *bcm63xx_regs_spi;
+
+	return bcm63xx_regs_spi[reg];
+#else
+#ifdef CONFIG_BCM63XX_CPU_6338
+	__GEN_SPI_RSET(6338)
+#endif
+#ifdef CONFIG_BCM63XX_CPU_6348
+	__GEN_SPI_RSET(6348)
+#endif
+#ifdef CONFIG_BCM63XX_CPU_6358
+	__GEN_SPI_RSET(6358)
+#endif
+#ifdef CONFIG_BCM63XX_CPU_6368
+	__GEN_SPI_RSET(6368)
+#endif
+#endif
+	return 0;
+}
+
+#endif /* BCM63XX_DEV_SPI_H */
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_gpio.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_gpio.h
index 1d7dd96aa460..0a9891f7580d 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_gpio.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_gpio.h
@@ -9,6 +9,8 @@ int __init bcm63xx_gpio_init(void);
 static inline unsigned long bcm63xx_gpio_count(void)
 {
 	switch (bcm63xx_get_cpu_id()) {
+	case BCM6328_CPU_ID:
+		return 32;
 	case BCM6358_CPU_ID:
 		return 40;
 	case BCM6338_CPU_ID:
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_io.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_io.h
index 72477a6441dd..9203d90e610c 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_io.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_io.h
@@ -40,6 +40,10 @@
 #define BCM_CB_MEM_END_PA		(BCM_CB_MEM_BASE_PA +		\
 					BCM_CB_MEM_SIZE - 1)
 
+#define BCM_PCIE_MEM_BASE_PA		0x10f00000
+#define BCM_PCIE_MEM_SIZE		(16 * 1024 * 1024)
+#define BCM_PCIE_MEM_END_PA		(BCM_PCIE_MEM_BASE_PA +		\
+					BCM_PCIE_MEM_SIZE - 1)
 
 /*
  * Internal registers are accessed through KSEG3
@@ -85,11 +89,15 @@
 #define bcm_mpi_writel(v, o)	bcm_rset_writel(RSET_MPI, (v), (o))
 #define bcm_pcmcia_readl(o)	bcm_rset_readl(RSET_PCMCIA, (o))
 #define bcm_pcmcia_writel(v, o)	bcm_rset_writel(RSET_PCMCIA, (v), (o))
+#define bcm_pcie_readl(o)	bcm_rset_readl(RSET_PCIE, (o))
+#define bcm_pcie_writel(v, o)	bcm_rset_writel(RSET_PCIE, (v), (o))
 #define bcm_sdram_readl(o)	bcm_rset_readl(RSET_SDRAM, (o))
 #define bcm_sdram_writel(v, o)	bcm_rset_writel(RSET_SDRAM, (v), (o))
 #define bcm_memc_readl(o)	bcm_rset_readl(RSET_MEMC, (o))
 #define bcm_memc_writel(v, o)	bcm_rset_writel(RSET_MEMC, (v), (o))
 #define bcm_ddr_readl(o)	bcm_rset_readl(RSET_DDR, (o))
 #define bcm_ddr_writel(v, o)	bcm_rset_writel(RSET_DDR, (v), (o))
+#define bcm_misc_readl(o)	bcm_rset_readl(RSET_MISC, (o))
+#define bcm_misc_writel(v, o)	bcm_rset_writel(RSET_MISC, (v), (o))
 
 #endif /* ! BCM63XX_IO_H_ */
diff --git a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h
index fdcd78ca1b03..4ccc2a748aff 100644
--- a/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h
+++ b/arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h
@@ -15,6 +15,30 @@
 /* Clock Control register */
 #define PERF_CKCTL_REG			0x4
 
+#define CKCTL_6328_PHYMIPS_EN		(1 << 0)
+#define CKCTL_6328_ADSL_QPROC_EN	(1 << 1)
+#define CKCTL_6328_ADSL_AFE_EN		(1 << 2)
+#define CKCTL_6328_ADSL_EN		(1 << 3)
+#define CKCTL_6328_MIPS_EN		(1 << 4)
+#define CKCTL_6328_SAR_EN		(1 << 5)
+#define CKCTL_6328_PCM_EN		(1 << 6)
+#define CKCTL_6328_USBD_EN		(1 << 7)
+#define CKCTL_6328_USBH_EN		(1 << 8)
+#define CKCTL_6328_HSSPI_EN		(1 << 9)
+#define CKCTL_6328_PCIE_EN		(1 << 10)
+#define CKCTL_6328_ROBOSW_EN		(1 << 11)
+
+#define CKCTL_6328_ALL_SAFE_EN		(CKCTL_6328_PHYMIPS_EN |	\
+					CKCTL_6328_ADSL_QPROC_EN |	\
+					CKCTL_6328_ADSL_AFE_EN |	\
+					CKCTL_6328_ADSL_EN |		\
+					CKCTL_6328_SAR_EN  |		\
+					CKCTL_6328_PCM_EN  |		\
+					CKCTL_6328_USBD_EN |		\
+					CKCTL_6328_USBH_EN |		\
+					CKCTL_6328_ROBOSW_EN |		\
+					CKCTL_6328_PCIE_EN)
+
 #define CKCTL_6338_ADSLPHY_EN		(1 << 0)
 #define CKCTL_6338_MPI_EN		(1 << 1)
 #define CKCTL_6338_DRAM_EN		(1 << 2)
@@ -90,35 +114,36 @@
 #define CKCTL_6368_PHYMIPS_EN		(1 << 6)
 #define CKCTL_6368_SWPKT_USB_EN		(1 << 7)
 #define CKCTL_6368_SWPKT_SAR_EN		(1 << 8)
-#define CKCTL_6368_SPI_CLK_EN		(1 << 9)
-#define CKCTL_6368_USBD_CLK_EN		(1 << 10)
-#define CKCTL_6368_SAR_CLK_EN		(1 << 11)
-#define CKCTL_6368_ROBOSW_CLK_EN	(1 << 12)
-#define CKCTL_6368_UTOPIA_CLK_EN	(1 << 13)
-#define CKCTL_6368_PCM_CLK_EN		(1 << 14)
-#define CKCTL_6368_USBH_CLK_EN		(1 << 15)
+#define CKCTL_6368_SPI_EN		(1 << 9)
+#define CKCTL_6368_USBD_EN		(1 << 10)
+#define CKCTL_6368_SAR_EN		(1 << 11)
+#define CKCTL_6368_ROBOSW_EN		(1 << 12)
+#define CKCTL_6368_UTOPIA_EN		(1 << 13)
+#define CKCTL_6368_PCM_EN		(1 << 14)
+#define CKCTL_6368_USBH_EN		(1 << 15)
 #define CKCTL_6368_DISABLE_GLESS_EN	(1 << 16)
-#define CKCTL_6368_NAND_CLK_EN		(1 << 17)
-#define CKCTL_6368_IPSEC_CLK_EN		(1 << 18)
+#define CKCTL_6368_NAND_EN		(1 << 17)
+#define CKCTL_6368_IPSEC_EN		(1 << 18)
 
 #define CKCTL_6368_ALL_SAFE_EN		(CKCTL_6368_SWPKT_USB_EN |	\
 					CKCTL_6368_SWPKT_SAR_EN |	\
-					CKCTL_6368_SPI_CLK_EN |		\
-					CKCTL_6368_USBD_CLK_EN |	\
-					CKCTL_6368_SAR_CLK_EN |		\
-					CKCTL_6368_ROBOSW_CLK_EN |	\
-					CKCTL_6368_UTOPIA_CLK_EN |	\
-					CKCTL_6368_PCM_CLK_EN |		\
-					CKCTL_6368_USBH_CLK_EN |	\
+					CKCTL_6368_SPI_EN |		\
+					CKCTL_6368_USBD_EN |		\
+					CKCTL_6368_SAR_EN |		\
+					CKCTL_6368_ROBOSW_EN |		\
+					CKCTL_6368_UTOPIA_EN |		\
+					CKCTL_6368_PCM_EN |		\
+					CKCTL_6368_USBH_EN |		\
 					CKCTL_6368_DISABLE_GLESS_EN |	\
-					CKCTL_6368_NAND_CLK_EN |	\
-					CKCTL_6368_IPSEC_CLK_EN)
+					CKCTL_6368_NAND_EN |		\
+					CKCTL_6368_IPSEC_EN)
 
 /* System PLL Control register  */
 #define PERF_SYS_PLL_CTL_REG		0x8
 #define SYS_PLL_SOFT_RESET		0x1
 
 /* Interrupt Mask register */
+#define PERF_IRQMASK_6328_REG		0x20
 #define PERF_IRQMASK_6338_REG		0xc
 #define PERF_IRQMASK_6345_REG		0xc
 #define PERF_IRQMASK_6348_REG		0xc
@@ -126,6 +151,7 @@
 #define PERF_IRQMASK_6368_REG		0x20
 
 /* Interrupt Status register */
+#define PERF_IRQSTAT_6328_REG		0x28
 #define PERF_IRQSTAT_6338_REG		0x10
 #define PERF_IRQSTAT_6345_REG		0x10
 #define PERF_IRQSTAT_6348_REG		0x10
@@ -133,6 +159,7 @@
 #define PERF_IRQSTAT_6368_REG		0x28
 
 /* External Interrupt Configuration register */
+#define PERF_EXTIRQ_CFG_REG_6328	0x18
 #define PERF_EXTIRQ_CFG_REG_6338	0x14
 #define PERF_EXTIRQ_CFG_REG_6348	0x14
 #define PERF_EXTIRQ_CFG_REG_6358	0x14
@@ -162,8 +189,21 @@
 
 /* Soft Reset register */
 #define PERF_SOFTRESET_REG		0x28
+#define PERF_SOFTRESET_6328_REG		0x10
 #define PERF_SOFTRESET_6368_REG		0x10
 
+#define SOFTRESET_6328_SPI_MASK		(1 << 0)
+#define SOFTRESET_6328_EPHY_MASK	(1 << 1)
+#define SOFTRESET_6328_SAR_MASK		(1 << 2)
+#define SOFTRESET_6328_ENETSW_MASK	(1 << 3)
+#define SOFTRESET_6328_USBS_MASK	(1 << 4)
+#define SOFTRESET_6328_USBH_MASK	(1 << 5)
+#define SOFTRESET_6328_PCM_MASK		(1 << 6)
+#define SOFTRESET_6328_PCIE_CORE_MASK	(1 << 7)
+#define SOFTRESET_6328_PCIE_MASK	(1 << 8)
+#define SOFTRESET_6328_PCIE_EXT_MASK	(1 << 9)
+#define SOFTRESET_6328_PCIE_HARD_MASK	(1 << 10)
+
 #define SOFTRESET_6338_SPI_MASK		(1 << 0)
 #define SOFTRESET_6338_ENET_MASK	(1 << 2)
 #define SOFTRESET_6338_USBH_MASK	(1 << 3)
@@ -307,6 +347,8 @@
 /* Watchdog reset length register */
 #define WDT_RSTLEN_REG			0x8
 
+/* Watchdog soft reset register (BCM6328 only) */
+#define WDT_SOFTRESET_REG		0xc
 
 /*************************************************************************
  * _REG relative to RSET_UARTx
@@ -507,6 +549,15 @@
 #define GPIO_BASEMODE_6368_MASK		0x7
 /* those bits must be kept as read in gpio basemode register*/
 
+#define GPIO_STRAPBUS_REG		0x40
+#define STRAPBUS_6358_BOOT_SEL_PARALLEL	(1 << 1)
+#define STRAPBUS_6358_BOOT_SEL_SERIAL	(0 << 1)
+#define STRAPBUS_6368_BOOT_SEL_MASK	0x3
+#define STRAPBUS_6368_BOOT_SEL_NAND	0
+#define STRAPBUS_6368_BOOT_SEL_SERIAL	1
+#define STRAPBUS_6368_BOOT_SEL_PARALLEL	3
+
+
 /*************************************************************************
  * _REG relative to RSET_ENET
  *************************************************************************/
@@ -924,6 +975,8 @@
  * _REG relative to RSET_DDR
  *************************************************************************/
 
+#define DDR_CSEND_REG			0x8
+
 #define DDR_DMIPSPLLCFG_REG		0x18
 #define DMIPSPLLCFG_M1_SHIFT		0
 #define DMIPSPLLCFG_M1_MASK		(0xff << DMIPSPLLCFG_M1_SHIFT)
@@ -973,4 +1026,201 @@
 #define M2M_SRCID_REG(x)		((x) * 0x40 + 0x14)
 #define M2M_DSTID_REG(x)		((x) * 0x40 + 0x18)
 
+/*************************************************************************
+ * _REG relative to RSET_RNG
+ *************************************************************************/
+
+#define RNG_CTRL			0x00
+#define RNG_EN				(1 << 0)
+
+#define RNG_STAT			0x04
+#define RNG_AVAIL_MASK			(0xff000000)
+
+#define RNG_DATA			0x08
+#define RNG_THRES			0x0c
+#define RNG_MASK			0x10
+
+/*************************************************************************
+ * _REG relative to RSET_SPI
+ *************************************************************************/
+
+/* BCM 6338 SPI core */
+#define SPI_6338_CMD			0x00	/* 16-bits register */
+#define SPI_6338_INT_STATUS		0x02
+#define SPI_6338_INT_MASK_ST		0x03
+#define SPI_6338_INT_MASK		0x04
+#define SPI_6338_ST			0x05
+#define SPI_6338_CLK_CFG		0x06
+#define SPI_6338_FILL_BYTE		0x07
+#define SPI_6338_MSG_TAIL		0x09
+#define SPI_6338_RX_TAIL		0x0b
+#define SPI_6338_MSG_CTL		0x40
+#define SPI_6338_MSG_DATA		0x41
+#define SPI_6338_MSG_DATA_SIZE		0x3f
+#define SPI_6338_RX_DATA		0x80
+#define SPI_6338_RX_DATA_SIZE		0x3f
+
+/* BCM 6348 SPI core */
+#define SPI_6348_CMD			0x00	/* 16-bits register */
+#define SPI_6348_INT_STATUS		0x02
+#define SPI_6348_INT_MASK_ST		0x03
+#define SPI_6348_INT_MASK		0x04
+#define SPI_6348_ST			0x05
+#define SPI_6348_CLK_CFG		0x06
+#define SPI_6348_FILL_BYTE		0x07
+#define SPI_6348_MSG_TAIL		0x09
+#define SPI_6348_RX_TAIL		0x0b
+#define SPI_6348_MSG_CTL		0x40
+#define SPI_6348_MSG_DATA		0x41
+#define SPI_6348_MSG_DATA_SIZE		0x3f
+#define SPI_6348_RX_DATA		0x80
+#define SPI_6348_RX_DATA_SIZE		0x3f
+
+/* BCM 6358 SPI core */
+#define SPI_6358_MSG_CTL		0x00	/* 16-bits register */
+#define SPI_6358_MSG_DATA		0x02
+#define SPI_6358_MSG_DATA_SIZE		0x21e
+#define SPI_6358_RX_DATA		0x400
+#define SPI_6358_RX_DATA_SIZE		0x220
+#define SPI_6358_CMD			0x700	/* 16-bits register */
+#define SPI_6358_INT_STATUS		0x702
+#define SPI_6358_INT_MASK_ST		0x703
+#define SPI_6358_INT_MASK		0x704
+#define SPI_6358_ST			0x705
+#define SPI_6358_CLK_CFG		0x706
+#define SPI_6358_FILL_BYTE		0x707
+#define SPI_6358_MSG_TAIL		0x709
+#define SPI_6358_RX_TAIL		0x70B
+
+/* BCM 6358 SPI core */
+#define SPI_6368_MSG_CTL		0x00	/* 16-bits register */
+#define SPI_6368_MSG_DATA		0x02
+#define SPI_6368_MSG_DATA_SIZE		0x21e
+#define SPI_6368_RX_DATA		0x400
+#define SPI_6368_RX_DATA_SIZE		0x220
+#define SPI_6368_CMD			0x700	/* 16-bits register */
+#define SPI_6368_INT_STATUS		0x702
+#define SPI_6368_INT_MASK_ST		0x703
+#define SPI_6368_INT_MASK		0x704
+#define SPI_6368_ST			0x705
+#define SPI_6368_CLK_CFG		0x706
+#define SPI_6368_FILL_BYTE		0x707
+#define SPI_6368_MSG_TAIL		0x709
+#define SPI_6368_RX_TAIL		0x70B
+
+/* Shared SPI definitions */
+
+/* Message configuration */
+#define SPI_FD_RW			0x00
+#define SPI_HD_W			0x01
+#define SPI_HD_R			0x02
+#define SPI_BYTE_CNT_SHIFT		0
+#define SPI_MSG_TYPE_SHIFT		14
+
+/* Command */
+#define SPI_CMD_NOOP			0x00
+#define SPI_CMD_SOFT_RESET		0x01
+#define SPI_CMD_HARD_RESET		0x02
+#define SPI_CMD_START_IMMEDIATE		0x03
+#define SPI_CMD_COMMAND_SHIFT		0
+#define SPI_CMD_COMMAND_MASK		0x000f
+#define SPI_CMD_DEVICE_ID_SHIFT		4
+#define SPI_CMD_PREPEND_BYTE_CNT_SHIFT	8
+#define SPI_CMD_ONE_BYTE_SHIFT		11
+#define SPI_CMD_ONE_WIRE_SHIFT		12
+#define SPI_DEV_ID_0			0
+#define SPI_DEV_ID_1			1
+#define SPI_DEV_ID_2			2
+#define SPI_DEV_ID_3			3
+
+/* Interrupt mask */
+#define SPI_INTR_CMD_DONE		0x01
+#define SPI_INTR_RX_OVERFLOW		0x02
+#define SPI_INTR_TX_UNDERFLOW		0x04
+#define SPI_INTR_TX_OVERFLOW		0x08
+#define SPI_INTR_RX_UNDERFLOW		0x10
+#define SPI_INTR_CLEAR_ALL		0x1f
+
+/* Status */
+#define SPI_RX_EMPTY			0x02
+#define SPI_CMD_BUSY			0x04
+#define SPI_SERIAL_BUSY			0x08
+
+/* Clock configuration */
+#define SPI_CLK_20MHZ			0x00
+#define SPI_CLK_0_391MHZ		0x01
+#define SPI_CLK_0_781MHZ		0x02 /* default */
+#define SPI_CLK_1_563MHZ		0x03
+#define SPI_CLK_3_125MHZ		0x04
+#define SPI_CLK_6_250MHZ		0x05
+#define SPI_CLK_12_50MHZ		0x06
+#define SPI_CLK_MASK			0x07
+#define SPI_SSOFFTIME_MASK		0x38
+#define SPI_SSOFFTIME_SHIFT		3
+#define SPI_BYTE_SWAP			0x80
+
+/*************************************************************************
+ * _REG relative to RSET_MISC
+ *************************************************************************/
+#define MISC_SERDES_CTRL_REG		0x0
+#define SERDES_PCIE_EN			(1 << 0)
+#define SERDES_PCIE_EXD_EN		(1 << 15)
+
+#define MISC_STRAPBUS_6328_REG		0x240
+#define STRAPBUS_6328_FCVO_SHIFT	7
+#define STRAPBUS_6328_FCVO_MASK		(0x1f << STRAPBUS_6328_FCVO_SHIFT)
+#define STRAPBUS_6328_BOOT_SEL_SERIAL	(1 << 28)
+#define STRAPBUS_6328_BOOT_SEL_NAND	(0 << 28)
+
+/*************************************************************************
+ * _REG relative to RSET_PCIE
+ *************************************************************************/
+
+#define PCIE_CONFIG2_REG		0x408
+#define CONFIG2_BAR1_SIZE_EN		1
+#define CONFIG2_BAR1_SIZE_MASK		0xf
+
+#define PCIE_IDVAL3_REG			0x43c
+#define IDVAL3_CLASS_CODE_MASK		0xffffff
+#define IDVAL3_SUBCLASS_SHIFT		8
+#define IDVAL3_CLASS_SHIFT		16
+
+#define PCIE_DLSTATUS_REG		0x1048
+#define DLSTATUS_PHYLINKUP		(1 << 13)
+
+#define PCIE_BRIDGE_OPT1_REG		0x2820
+#define OPT1_RD_BE_OPT_EN		(1 << 7)
+#define OPT1_RD_REPLY_BE_FIX_EN		(1 << 9)
+#define OPT1_PCIE_BRIDGE_HOLE_DET_EN	(1 << 11)
+#define OPT1_L1_INT_STATUS_MASK_POL	(1 << 12)
+
+#define PCIE_BRIDGE_OPT2_REG		0x2824
+#define OPT2_UBUS_UR_DECODE_DIS		(1 << 2)
+#define OPT2_TX_CREDIT_CHK_EN		(1 << 4)
+#define OPT2_CFG_TYPE1_BD_SEL		(1 << 7)
+#define OPT2_CFG_TYPE1_BUS_NO_SHIFT	16
+#define OPT2_CFG_TYPE1_BUS_NO_MASK	(0xff << OPT2_CFG_TYPE1_BUS_NO_SHIFT)
+
+#define PCIE_BRIDGE_BAR0_BASEMASK_REG	0x2828
+#define PCIE_BRIDGE_BAR1_BASEMASK_REG	0x2830
+#define BASEMASK_REMAP_EN		(1 << 0)
+#define BASEMASK_SWAP_EN		(1 << 1)
+#define BASEMASK_MASK_SHIFT		4
+#define BASEMASK_MASK_MASK		(0xfff << BASEMASK_MASK_SHIFT)
+#define BASEMASK_BASE_SHIFT		20
+#define BASEMASK_BASE_MASK		(0xfff << BASEMASK_BASE_SHIFT)
+
+#define PCIE_BRIDGE_BAR0_REBASE_ADDR_REG 0x282c
+#define PCIE_BRIDGE_BAR1_REBASE_ADDR_REG 0x2834
+#define REBASE_ADDR_BASE_SHIFT		20
+#define REBASE_ADDR_BASE_MASK		(0xfff << REBASE_ADDR_BASE_SHIFT)
+
+#define PCIE_BRIDGE_RC_INT_MASK_REG	0x2854
+#define PCIE_RC_INT_A			(1 << 0)
+#define PCIE_RC_INT_B			(1 << 1)
+#define PCIE_RC_INT_C			(1 << 2)
+#define PCIE_RC_INT_D			(1 << 3)
+
+#define PCIE_DEVICE_OFFSET		0x8000
+
 #endif /* BCM63XX_REGS_H_ */
diff --git a/arch/mips/include/asm/mach-bcm63xx/ioremap.h b/arch/mips/include/asm/mach-bcm63xx/ioremap.h
index ef94ba73646e..30931c42379d 100644
--- a/arch/mips/include/asm/mach-bcm63xx/ioremap.h
+++ b/arch/mips/include/asm/mach-bcm63xx/ioremap.h
@@ -18,6 +18,7 @@ static inline int is_bcm63xx_internal_registers(phys_t offset)
 		if (offset >= 0xfff00000)
 			return 1;
 		break;
+	case BCM6328_CPU_ID:
 	case BCM6368_CPU_ID:
 		if (offset >= 0xb0000000 && offset < 0xb1000000)
 			return 1;
diff --git a/arch/mips/include/asm/mach-cavium-octeon/irq.h b/arch/mips/include/asm/mach-cavium-octeon/irq.h
index 5b05f186e395..418992042f6f 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/irq.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/irq.h
@@ -41,61 +41,26 @@ enum octeon_irq {
 	OCTEON_IRQ_TWSI,
 	OCTEON_IRQ_TWSI2,
 	OCTEON_IRQ_RML,
-	OCTEON_IRQ_TRACE0,
-	OCTEON_IRQ_GMX_DRP0 = OCTEON_IRQ_TRACE0 + 4,
-	OCTEON_IRQ_IPD_DRP = OCTEON_IRQ_GMX_DRP0 + 5,
-	OCTEON_IRQ_KEY_ZERO,
 	OCTEON_IRQ_TIMER0,
 	OCTEON_IRQ_TIMER1,
 	OCTEON_IRQ_TIMER2,
 	OCTEON_IRQ_TIMER3,
 	OCTEON_IRQ_USB0,
 	OCTEON_IRQ_USB1,
-	OCTEON_IRQ_PCM,
-	OCTEON_IRQ_MPI,
-	OCTEON_IRQ_POWIQ,
-	OCTEON_IRQ_IPDPPTHR,
 	OCTEON_IRQ_MII0,
 	OCTEON_IRQ_MII1,
 	OCTEON_IRQ_BOOTDMA,
-
-	OCTEON_IRQ_NAND,
-	OCTEON_IRQ_MIO,		/* Summary of MIO_BOOT_ERR */
-	OCTEON_IRQ_IOB,		/* Summary of IOB_INT_SUM */
-	OCTEON_IRQ_FPA,		/* Summary of FPA_INT_SUM */
-	OCTEON_IRQ_POW,		/* Summary of POW_ECC_ERR */
-	OCTEON_IRQ_L2C,		/* Summary of L2C_INT_STAT */
-	OCTEON_IRQ_IPD,		/* Summary of IPD_INT_SUM */
-	OCTEON_IRQ_PIP,		/* Summary of PIP_INT_REG */
-	OCTEON_IRQ_PKO,		/* Summary of PKO_REG_ERROR */
-	OCTEON_IRQ_ZIP,		/* Summary of ZIP_ERROR */
-	OCTEON_IRQ_TIM,		/* Summary of TIM_REG_ERROR */
-	OCTEON_IRQ_RAD,		/* Summary of RAD_REG_ERROR */
-	OCTEON_IRQ_KEY,		/* Summary of KEY_INT_SUM */
-	OCTEON_IRQ_DFA,		/* Summary of DFA */
-	OCTEON_IRQ_USBCTL,	/* Summary of USBN0_INT_SUM */
-	OCTEON_IRQ_SLI,		/* Summary of SLI_INT_SUM */
-	OCTEON_IRQ_DPI,		/* Summary of DPI_INT_SUM */
-	OCTEON_IRQ_AGX0,	/* Summary of GMX0*+PCS0_INT*_REG */
-	OCTEON_IRQ_AGL  = OCTEON_IRQ_AGX0 + 5,
-	OCTEON_IRQ_PTP,
-	OCTEON_IRQ_PEM0,
-	OCTEON_IRQ_PEM1,
-	OCTEON_IRQ_SRIO0,
-	OCTEON_IRQ_SRIO1,
-	OCTEON_IRQ_LMC0,
-	OCTEON_IRQ_DFM = OCTEON_IRQ_LMC0 + 4,		/* Summary of DFM */
-	OCTEON_IRQ_RST,
+#ifndef CONFIG_PCI_MSI
+	OCTEON_IRQ_LAST = 127
+#endif
 };
 
 #ifdef CONFIG_PCI_MSI
-/* 152 - 407 represent the MSI interrupts 0-255 */
-#define OCTEON_IRQ_MSI_BIT0	(OCTEON_IRQ_RST + 1)
+/* 256 - 511 represent the MSI interrupts 0-255 */
+#define OCTEON_IRQ_MSI_BIT0	(256)
 
 #define OCTEON_IRQ_MSI_LAST      (OCTEON_IRQ_MSI_BIT0 + 255)
 #define OCTEON_IRQ_LAST          (OCTEON_IRQ_MSI_LAST + 1)
-#else
-#define OCTEON_IRQ_LAST         (OCTEON_IRQ_RST + 1)
 #endif
 
 #endif
diff --git a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h b/arch/mips/include/asm/mach-jz4740/jz4740_nand.h
index bb5b9a4e29c8..986982db7c38 100644
--- a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h
+++ b/arch/mips/include/asm/mach-jz4740/jz4740_nand.h
@@ -19,6 +19,8 @@
 #include <linux/mtd/nand.h>
 #include <linux/mtd/partitions.h>
 
+#define JZ_NAND_NUM_BANKS 4
+
 struct jz_nand_platform_data {
 	int			num_partitions;
 	struct mtd_partition	*partitions;
@@ -27,6 +29,8 @@ struct jz_nand_platform_data {
 
 	unsigned int busy_gpio;
 
+	unsigned char banks[JZ_NAND_NUM_BANKS];
+
 	void (*ident_callback)(struct platform_device *, struct nand_chip *,
 				struct mtd_partition **, int *num_partitions);
 };
diff --git a/arch/mips/include/asm/mach-loongson/loongson.h b/arch/mips/include/asm/mach-loongson/loongson.h
index 1e29b9dd1d73..06367c37e1b2 100644
--- a/arch/mips/include/asm/mach-loongson/loongson.h
+++ b/arch/mips/include/asm/mach-loongson/loongson.h
@@ -14,6 +14,7 @@
 #include <linux/io.h>
 #include <linux/init.h>
 #include <linux/irq.h>
+#include <linux/kconfig.h>
 
 /* loongson internal northbridge initialization */
 extern void bonito_irq_init(void);
@@ -66,7 +67,7 @@ extern int mach_i8259_irq(void);
 #include <linux/interrupt.h>
 static inline void do_perfcnt_IRQ(void)
 {
-#if defined(CONFIG_OPROFILE) || defined(CONFIG_OPROFILE_MODULE)
+#if IS_ENABLED(CONFIG_OPROFILE)
 	do_IRQ(LOONGSON2_PERFCNT_IRQ);
 #endif
 }
diff --git a/arch/mips/include/asm/mach-loongson1/irq.h b/arch/mips/include/asm/mach-loongson1/irq.h
new file mode 100644
index 000000000000..da96ed42f733
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson1/irq.h
@@ -0,0 +1,73 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * IRQ mappings for Loongson 1
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+
+#ifndef __ASM_MACH_LOONGSON1_IRQ_H
+#define __ASM_MACH_LOONGSON1_IRQ_H
+
+/*
+ * CPU core Interrupt Numbers
+ */
+#define MIPS_CPU_IRQ_BASE		0
+#define MIPS_CPU_IRQ(x)			(MIPS_CPU_IRQ_BASE + (x))
+
+#define SOFTINT0_IRQ			MIPS_CPU_IRQ(0)
+#define SOFTINT1_IRQ			MIPS_CPU_IRQ(1)
+#define INT0_IRQ			MIPS_CPU_IRQ(2)
+#define INT1_IRQ			MIPS_CPU_IRQ(3)
+#define INT2_IRQ			MIPS_CPU_IRQ(4)
+#define INT3_IRQ			MIPS_CPU_IRQ(5)
+#define INT4_IRQ			MIPS_CPU_IRQ(6)
+#define TIMER_IRQ			MIPS_CPU_IRQ(7)		/* cpu timer */
+
+#define MIPS_CPU_IRQS		(MIPS_CPU_IRQ(7) + 1 - MIPS_CPU_IRQ_BASE)
+
+/*
+ * INT0~3 Interrupt Numbers
+ */
+#define LS1X_IRQ_BASE			MIPS_CPU_IRQS
+#define LS1X_IRQ(n, x)			(LS1X_IRQ_BASE + (n << 5) + (x))
+
+#define LS1X_UART0_IRQ			LS1X_IRQ(0, 2)
+#define LS1X_UART1_IRQ			LS1X_IRQ(0, 3)
+#define LS1X_UART2_IRQ			LS1X_IRQ(0, 4)
+#define LS1X_UART3_IRQ			LS1X_IRQ(0, 5)
+#define LS1X_CAN0_IRQ			LS1X_IRQ(0, 6)
+#define LS1X_CAN1_IRQ			LS1X_IRQ(0, 7)
+#define LS1X_SPI0_IRQ			LS1X_IRQ(0, 8)
+#define LS1X_SPI1_IRQ			LS1X_IRQ(0, 9)
+#define LS1X_AC97_IRQ			LS1X_IRQ(0, 10)
+#define LS1X_DMA0_IRQ			LS1X_IRQ(0, 13)
+#define LS1X_DMA1_IRQ			LS1X_IRQ(0, 14)
+#define LS1X_DMA2_IRQ			LS1X_IRQ(0, 15)
+#define LS1X_PWM0_IRQ			LS1X_IRQ(0, 17)
+#define LS1X_PWM1_IRQ			LS1X_IRQ(0, 18)
+#define LS1X_PWM2_IRQ			LS1X_IRQ(0, 19)
+#define LS1X_PWM3_IRQ			LS1X_IRQ(0, 20)
+#define LS1X_RTC_INT0_IRQ		LS1X_IRQ(0, 21)
+#define LS1X_RTC_INT1_IRQ		LS1X_IRQ(0, 22)
+#define LS1X_RTC_INT2_IRQ		LS1X_IRQ(0, 23)
+#define LS1X_TOY_INT0_IRQ		LS1X_IRQ(0, 24)
+#define LS1X_TOY_INT1_IRQ		LS1X_IRQ(0, 25)
+#define LS1X_TOY_INT2_IRQ		LS1X_IRQ(0, 26)
+#define LS1X_RTC_TICK_IRQ		LS1X_IRQ(0, 27)
+#define LS1X_TOY_TICK_IRQ		LS1X_IRQ(0, 28)
+
+#define LS1X_EHCI_IRQ			LS1X_IRQ(1, 0)
+#define LS1X_OHCI_IRQ			LS1X_IRQ(1, 1)
+#define LS1X_GMAC0_IRQ			LS1X_IRQ(1, 2)
+#define LS1X_GMAC1_IRQ			LS1X_IRQ(1, 3)
+
+#define LS1X_IRQS		(LS1X_IRQ(4, 31) + 1 - LS1X_IRQ_BASE)
+
+#define NR_IRQS			(MIPS_CPU_IRQS + LS1X_IRQS)
+
+#endif /* __ASM_MACH_LOONGSON1_IRQ_H */
diff --git a/arch/mips/include/asm/mach-loongson1/loongson1.h b/arch/mips/include/asm/mach-loongson1/loongson1.h
new file mode 100644
index 000000000000..4e18e88cebbf
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson1/loongson1.h
@@ -0,0 +1,44 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * Register mappings for Loongson 1
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+
+#ifndef __ASM_MACH_LOONGSON1_LOONGSON1_H
+#define __ASM_MACH_LOONGSON1_LOONGSON1_H
+
+#define DEFAULT_MEMSIZE			256	/* If no memsize provided */
+
+/* Loongson 1 Register Bases */
+#define LS1X_INTC_BASE			0x1fd01040
+#define LS1X_EHCI_BASE			0x1fe00000
+#define LS1X_OHCI_BASE			0x1fe08000
+#define LS1X_GMAC0_BASE			0x1fe10000
+#define LS1X_GMAC1_BASE			0x1fe20000
+
+#define LS1X_UART0_BASE			0x1fe40000
+#define LS1X_UART1_BASE			0x1fe44000
+#define LS1X_UART2_BASE			0x1fe48000
+#define LS1X_UART3_BASE			0x1fe4c000
+#define LS1X_CAN0_BASE			0x1fe50000
+#define LS1X_CAN1_BASE			0x1fe54000
+#define LS1X_I2C0_BASE			0x1fe58000
+#define LS1X_I2C1_BASE			0x1fe68000
+#define LS1X_I2C2_BASE			0x1fe70000
+#define LS1X_PWM_BASE			0x1fe5c000
+#define LS1X_WDT_BASE			0x1fe5c060
+#define LS1X_RTC_BASE			0x1fe64000
+#define LS1X_AC97_BASE			0x1fe74000
+#define LS1X_NAND_BASE			0x1fe78000
+#define LS1X_CLK_BASE			0x1fe78030
+
+#include <regs-clk.h>
+#include <regs-wdt.h>
+
+#endif /* __ASM_MACH_LOONGSON1_LOONGSON1_H */
diff --git a/arch/mips/include/asm/mach-loongson1/platform.h b/arch/mips/include/asm/mach-loongson1/platform.h
new file mode 100644
index 000000000000..2f171617bade
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson1/platform.h
@@ -0,0 +1,23 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+
+#ifndef __ASM_MACH_LOONGSON1_PLATFORM_H
+#define __ASM_MACH_LOONGSON1_PLATFORM_H
+
+#include <linux/platform_device.h>
+
+extern struct platform_device ls1x_uart_device;
+extern struct platform_device ls1x_eth0_device;
+extern struct platform_device ls1x_ehci_device;
+extern struct platform_device ls1x_rtc_device;
+
+void ls1x_serial_setup(void);
+
+#endif /* __ASM_MACH_LOONGSON1_PLATFORM_H */
diff --git a/arch/mips/include/asm/mach-loongson1/prom.h b/arch/mips/include/asm/mach-loongson1/prom.h
new file mode 100644
index 000000000000..b871dc41b8d9
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson1/prom.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __ASM_MACH_LOONGSON1_PROM_H
+#define __ASM_MACH_LOONGSON1_PROM_H
+
+#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+
+/* environment arguments from bootloader */
+extern unsigned long memsize, highmemsize;
+
+/* loongson-specific command line, env and memory initialization */
+extern char *prom_getenv(char *name);
+extern void __init prom_init_cmdline(void);
+
+#endif /* __ASM_MACH_LOONGSON1_PROM_H */
diff --git a/arch/mips/include/asm/mach-loongson1/regs-clk.h b/arch/mips/include/asm/mach-loongson1/regs-clk.h
new file mode 100644
index 000000000000..8efa7fb9f73a
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson1/regs-clk.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * Loongson 1 Clock Register Definitions.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __ASM_MACH_LOONGSON1_REGS_CLK_H
+#define __ASM_MACH_LOONGSON1_REGS_CLK_H
+
+#define LS1X_CLK_REG(x) \
+		((void __iomem *)KSEG1ADDR(LS1X_CLK_BASE + (x)))
+
+#define LS1X_CLK_PLL_FREQ		LS1X_CLK_REG(0x0)
+#define LS1X_CLK_PLL_DIV		LS1X_CLK_REG(0x4)
+
+/* Clock PLL Divisor Register Bits */
+#define DIV_DC_EN			(0x1 << 31)
+#define DIV_DC				(0x1f << 26)
+#define DIV_CPU_EN			(0x1 << 25)
+#define DIV_CPU				(0x1f << 20)
+#define DIV_DDR_EN			(0x1 << 19)
+#define DIV_DDR				(0x1f << 14)
+
+#define DIV_DC_SHIFT			26
+#define DIV_CPU_SHIFT			20
+#define DIV_DDR_SHIFT			14
+
+#endif /* __ASM_MACH_LOONGSON1_REGS_CLK_H */
diff --git a/arch/mips/include/asm/mach-loongson1/regs-wdt.h b/arch/mips/include/asm/mach-loongson1/regs-wdt.h
new file mode 100644
index 000000000000..f897de68c527
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson1/regs-wdt.h
@@ -0,0 +1,22 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * Loongson 1 watchdog register definitions.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef __ASM_MACH_LOONGSON1_REGS_WDT_H
+#define __ASM_MACH_LOONGSON1_REGS_WDT_H
+
+#define LS1X_WDT_REG(x) \
+		((void __iomem *)KSEG1ADDR(LS1X_WDT_BASE + (x)))
+
+#define LS1X_WDT_EN			LS1X_WDT_REG(0x0)
+#define LS1X_WDT_SET			LS1X_WDT_REG(0x4)
+#define LS1X_WDT_TIMER			LS1X_WDT_REG(0x8)
+
+#endif /* __ASM_MACH_LOONGSON1_REGS_WDT_H */
diff --git a/arch/mips/include/asm/mach-loongson1/war.h b/arch/mips/include/asm/mach-loongson1/war.h
new file mode 100644
index 000000000000..e3680a8fb349
--- /dev/null
+++ b/arch/mips/include/asm/mach-loongson1/war.h
@@ -0,0 +1,25 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2002, 2004, 2007 by Ralf Baechle <ralf@linux-mips.org>
+ */
+#ifndef __ASM_MACH_LOONGSON1_WAR_H
+#define __ASM_MACH_LOONGSON1_WAR_H
+
+#define R4600_V1_INDEX_ICACHEOP_WAR	0
+#define R4600_V1_HIT_CACHEOP_WAR	0
+#define R4600_V2_HIT_CACHEOP_WAR	0
+#define R5432_CP0_INTERRUPT_WAR		0
+#define BCM1250_M3_WAR			0
+#define SIBYTE_1956_WAR			0
+#define MIPS4K_ICACHE_REFILL_WAR	0
+#define MIPS_CACHE_SYNC_WAR		0
+#define TX49XX_ICACHE_INDEX_INV_WAR	0
+#define RM9000_CDEX_SMP_WAR		0
+#define ICACHE_REFILLS_WORKAROUND_WAR	0
+#define R10000_LLSC_WAR			0
+#define MIPS34K_MISSED_ITLB_WAR		0
+
+#endif /* __ASM_MACH_LOONGSON1_WAR_H */
diff --git a/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h b/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h
index d193fb68cf27..966db4be377c 100644
--- a/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-netlogic/cpu-feature-overrides.h
@@ -48,7 +48,6 @@
 #define cpu_has_userlocal	1
 #define cpu_has_mips32r2	1
 #define cpu_has_mips64r2	1
-#define cpu_has_dc_aliases	1
 #else
 #error "Unknown Netlogic CPU"
 #endif
diff --git a/arch/mips/include/asm/mach-tx49xx/mangle-port.h b/arch/mips/include/asm/mach-tx49xx/mangle-port.h
index 5e6912fdd0ed..490867b03c8f 100644
--- a/arch/mips/include/asm/mach-tx49xx/mangle-port.h
+++ b/arch/mips/include/asm/mach-tx49xx/mangle-port.h
@@ -9,7 +9,7 @@
 #define ioswabb(a, x)		(x)
 #define __mem_ioswabb(a, x)	(x)
 #if defined(CONFIG_TOSHIBA_RBTX4939) && \
-	(defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE)) && \
+	IS_ENABLED(CONFIG_SMC91X) && \
 	defined(__BIG_ENDIAN)
 #define NEEDS_TXX9_IOSWABW
 extern u16 (*ioswabw)(volatile u16 *a, u16 x);
diff --git a/arch/mips/include/asm/mipsmtregs.h b/arch/mips/include/asm/mipsmtregs.h
index e71ff4c317f2..5b3cb8553e9a 100644
--- a/arch/mips/include/asm/mipsmtregs.h
+++ b/arch/mips/include/asm/mipsmtregs.h
@@ -28,6 +28,9 @@
 #define read_c0_vpeconf0()		__read_32bit_c0_register($1, 2)
 #define write_c0_vpeconf0(val)		__write_32bit_c0_register($1, 2, val)
 
+#define read_c0_vpeconf1()		__read_32bit_c0_register($1, 3)
+#define write_c0_vpeconf1(val)		__write_32bit_c0_register($1, 3, val)
+
 #define read_c0_tcstatus()		__read_32bit_c0_register($2, 1)
 #define write_c0_tcstatus(val)		__write_32bit_c0_register($2, 1, val)
 
@@ -124,6 +127,14 @@
 #define VPECONF0_XTC_SHIFT	21
 #define VPECONF0_XTC		(_ULCAST_(0xff) << VPECONF0_XTC_SHIFT)
 
+/* VPEConf1 fields (per VPE) */
+#define VPECONF1_NCP1_SHIFT	0
+#define VPECONF1_NCP1		(_ULCAST_(0xff) << VPECONF1_NCP1_SHIFT)
+#define VPECONF1_NCP2_SHIFT	10
+#define VPECONF1_NCP2		(_ULCAST_(0xff) << VPECONF1_NCP2_SHIFT)
+#define VPECONF1_NCX_SHIFT	20
+#define VPECONF1_NCX		(_ULCAST_(0xff) << VPECONF1_NCX_SHIFT)
+
 /* TCStatus fields (per TC) */
 #define TCSTATUS_TASID		(_ULCAST_(0xff))
 #define TCSTATUS_IXMT_SHIFT	10
@@ -350,6 +361,8 @@ do {									\
 #define write_vpe_c0_vpecontrol(val)	mttc0(1, 1, val)
 #define read_vpe_c0_vpeconf0()		mftc0(1, 2)
 #define write_vpe_c0_vpeconf0(val)	mttc0(1, 2, val)
+#define read_vpe_c0_vpeconf1()		mftc0(1, 3)
+#define write_vpe_c0_vpeconf1(val)	mttc0(1, 3, val)
 #define read_vpe_c0_count()		mftc0(9, 0)
 #define write_vpe_c0_count(val)		mttc0(9, 0, val)
 #define read_vpe_c0_status()		mftc0(12, 0)
diff --git a/arch/mips/include/asm/module.h b/arch/mips/include/asm/module.h
index 530008048c62..7531ecd654d6 100644
--- a/arch/mips/include/asm/module.h
+++ b/arch/mips/include/asm/module.h
@@ -117,6 +117,8 @@ search_module_dbetables(unsigned long addr)
 #define MODULE_PROC_FAMILY "RM9000 "
 #elif defined CONFIG_CPU_SB1
 #define MODULE_PROC_FAMILY "SB1 "
+#elif defined CONFIG_CPU_LOONGSON1
+#define MODULE_PROC_FAMILY "LOONGSON1 "
 #elif defined CONFIG_CPU_LOONGSON2
 #define MODULE_PROC_FAMILY "LOONGSON2 "
 #elif defined CONFIG_CPU_CAVIUM_OCTEON
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/cpucontrol.h b/arch/mips/include/asm/netlogic/xlp-hal/cpucontrol.h
index bf7d41deb9be..7b63a6b722a0 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/cpucontrol.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/cpucontrol.h
@@ -47,7 +47,9 @@
 #define CPU_BLOCKID_MAP		10
 
 #define LSU_DEFEATURE		0x304
-#define LSU_CERRLOG_REGID	0x09
+#define LSU_DEBUG_ADDR		0x305
+#define LSU_DEBUG_DATA0		0x306
+#define LSU_CERRLOG_REGID	0x309
 #define SCHED_DEFEATURE		0x700
 
 /* Offsets of interest from the 'MAP' Block */
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/iomap.h b/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
index 86cc3391e50c..2c63f9754640 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/iomap.h
@@ -36,6 +36,9 @@
 #define __NLM_HAL_IOMAP_H__
 
 #define XLP_DEFAULT_IO_BASE             0x18000000
+#define XLP_DEFAULT_PCI_ECFG_BASE	XLP_DEFAULT_IO_BASE
+#define XLP_DEFAULT_PCI_CFG_BASE	0x1c000000
+
 #define NMI_BASE			0xbfc00000
 #define	XLP_IO_CLK			133333333
 
@@ -129,7 +132,7 @@
 #define	PCI_DEVICE_ID_NLM_PIC		0x1003
 #define	PCI_DEVICE_ID_NLM_PCIE		0x1004
 #define	PCI_DEVICE_ID_NLM_EHCI		0x1007
-#define	PCI_DEVICE_ID_NLM_ILK		0x1008
+#define	PCI_DEVICE_ID_NLM_OHCI		0x1008
 #define	PCI_DEVICE_ID_NLM_NAE		0x1009
 #define	PCI_DEVICE_ID_NLM_POE		0x100A
 #define	PCI_DEVICE_ID_NLM_FMN		0x100B
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/pcibus.h b/arch/mips/include/asm/netlogic/xlp-hal/pcibus.h
new file mode 100644
index 000000000000..66c323d1bd7d
--- /dev/null
+++ b/arch/mips/include/asm/netlogic/xlp-hal/pcibus.h
@@ -0,0 +1,76 @@
+/*
+ * Copyright (c) 2003-2012 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the Broadcom
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __NLM_HAL_PCIBUS_H__
+#define	__NLM_HAL_PCIBUS_H__
+
+/* PCIE Memory and IO regions */
+#define	PCIE_MEM_BASE			0xd0000000ULL
+#define	PCIE_MEM_LIMIT			0xdfffffffULL
+#define	PCIE_IO_BASE			0x14000000ULL
+#define	PCIE_IO_LIMIT			0x15ffffffULL
+
+#define	PCIE_BRIDGE_CMD			0x1
+#define	PCIE_BRIDGE_MSI_CAP		0x14
+#define	PCIE_BRIDGE_MSI_ADDRL		0x15
+#define	PCIE_BRIDGE_MSI_ADDRH		0x16
+#define	PCIE_BRIDGE_MSI_DATA		0x17
+
+/* XLP Global PCIE configuration space registers */
+#define	PCIE_BYTE_SWAP_MEM_BASE		0x247
+#define	PCIE_BYTE_SWAP_MEM_LIM		0x248
+#define	PCIE_BYTE_SWAP_IO_BASE		0x249
+#define	PCIE_BYTE_SWAP_IO_LIM		0x24A
+#define	PCIE_MSI_STATUS			0x25A
+#define	PCIE_MSI_EN			0x25B
+#define	PCIE_INT_EN0			0x261
+
+/* PCIE_MSI_EN */
+#define	PCIE_MSI_VECTOR_INT_EN		0xFFFFFFFF
+
+/* PCIE_INT_EN0 */
+#define	PCIE_MSI_INT_EN			(1 << 9)
+
+#ifndef __ASSEMBLY__
+
+#define	nlm_read_pcie_reg(b, r)		nlm_read_reg(b, r)
+#define	nlm_write_pcie_reg(b, r, v)	nlm_write_reg(b, r, v)
+#define	nlm_get_pcie_base(node, inst)	\
+			nlm_pcicfg_base(XLP_IO_PCIE_OFFSET(node, inst))
+#define	nlm_get_pcie_regbase(node, inst)	\
+			(nlm_get_pcie_base(node, inst) + XLP_IO_PCI_HDRSZ)
+
+int xlp_pcie_link_irt(int link);
+#endif
+#endif /* __NLM_HAL_PCIBUS_H__ */
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/pic.h b/arch/mips/include/asm/netlogic/xlp-hal/pic.h
index b6628f7ccf74..ad8b80233a63 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/pic.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/pic.h
@@ -201,7 +201,11 @@
 #define PIC_NUM_USB_IRTS		6
 #define PIC_IRT_USB_0_INDEX		115
 #define PIC_IRT_EHCI_0_INDEX		115
+#define PIC_IRT_OHCI_0_INDEX		116
+#define PIC_IRT_OHCI_1_INDEX		117
 #define PIC_IRT_EHCI_1_INDEX		118
+#define PIC_IRT_OHCI_2_INDEX		119
+#define PIC_IRT_OHCI_3_INDEX		120
 #define PIC_IRT_USB_INDEX(num)		((num) + PIC_IRT_USB_0_INDEX)
 /* 115 to 120 */
 #define PIC_IRT_GDX_INDEX		121
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/usb.h b/arch/mips/include/asm/netlogic/xlp-hal/usb.h
new file mode 100644
index 000000000000..a9cd350dfb6c
--- /dev/null
+++ b/arch/mips/include/asm/netlogic/xlp-hal/usb.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright (c) 2003-2012 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the Broadcom
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef __NLM_HAL_USB_H__
+#define __NLM_HAL_USB_H__
+
+#define USB_CTL_0			0x01
+#define USB_PHY_0			0x0A
+#define USB_PHY_RESET			0x01
+#define USB_PHY_PORT_RESET_0		0x10
+#define USB_PHY_PORT_RESET_1		0x20
+#define USB_CONTROLLER_RESET		0x01
+#define USB_INT_STATUS			0x0E
+#define USB_INT_EN			0x0F
+#define USB_PHY_INTERRUPT_EN		0x01
+#define USB_OHCI_INTERRUPT_EN		0x02
+#define USB_OHCI_INTERRUPT1_EN		0x04
+#define USB_OHCI_INTERRUPT2_EN		0x08
+#define USB_CTRL_INTERRUPT_EN		0x10
+
+#ifndef __ASSEMBLY__
+
+#define nlm_read_usb_reg(b, r)			nlm_read_reg(b, r)
+#define nlm_write_usb_reg(b, r, v)		nlm_write_reg(b, r, v)
+#define nlm_get_usb_pcibase(node, inst)		\
+	nlm_pcicfg_base(XLP_IO_USB_OFFSET(node, inst))
+#define nlm_get_usb_hcd_base(node, inst)	\
+	nlm_xkphys_map_pcibar0(nlm_get_usb_pcibase(node, inst))
+#define nlm_get_usb_regbase(node, inst)		\
+	(nlm_get_usb_pcibase(node, inst) + XLP_IO_PCI_HDRSZ)
+
+#endif
+#endif /* __NLM_HAL_USB_H__ */
diff --git a/arch/mips/include/asm/netlogic/xlp-hal/xlp.h b/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
index 1540588e396d..7e47209327a5 100644
--- a/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
+++ b/arch/mips/include/asm/netlogic/xlp-hal/xlp.h
@@ -35,8 +35,21 @@
 #ifndef _NLM_HAL_XLP_H
 #define _NLM_HAL_XLP_H
 
-#define PIC_UART_0_IRQ           17
-#define PIC_UART_1_IRQ           18
+#define PIC_UART_0_IRQ			17
+#define PIC_UART_1_IRQ			18
+#define PIC_PCIE_LINK_0_IRQ		19
+#define PIC_PCIE_LINK_1_IRQ		20
+#define PIC_PCIE_LINK_2_IRQ		21
+#define PIC_PCIE_LINK_3_IRQ		22
+#define PIC_EHCI_0_IRQ			23
+#define PIC_EHCI_1_IRQ			24
+#define PIC_OHCI_0_IRQ			25
+#define PIC_OHCI_1_IRQ			26
+#define PIC_OHCI_2_IRQ			27
+#define PIC_OHCI_3_IRQ			28
+#define PIC_MMC_IRQ			29
+#define PIC_I2C_0_IRQ			30
+#define PIC_I2C_1_IRQ			31
 
 #ifndef __ASSEMBLY__
 
diff --git a/arch/mips/include/asm/netlogic/xlr/bridge.h b/arch/mips/include/asm/netlogic/xlr/bridge.h
new file mode 100644
index 000000000000..2d02428c4f1b
--- /dev/null
+++ b/arch/mips/include/asm/netlogic/xlr/bridge.h
@@ -0,0 +1,104 @@
+/*
+ * Copyright (c) 2003-2012 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the Broadcom
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef _ASM_NLM_BRIDGE_H_
+#define _ASM_NLM_BRIDGE_H_
+
+#define BRIDGE_DRAM_0_BAR		0
+#define BRIDGE_DRAM_1_BAR		1
+#define BRIDGE_DRAM_2_BAR		2
+#define BRIDGE_DRAM_3_BAR		3
+#define BRIDGE_DRAM_4_BAR		4
+#define BRIDGE_DRAM_5_BAR		5
+#define BRIDGE_DRAM_6_BAR		6
+#define BRIDGE_DRAM_7_BAR		7
+#define BRIDGE_DRAM_CHN_0_MTR_0_BAR	8
+#define BRIDGE_DRAM_CHN_0_MTR_1_BAR	9
+#define BRIDGE_DRAM_CHN_0_MTR_2_BAR	10
+#define BRIDGE_DRAM_CHN_0_MTR_3_BAR	11
+#define BRIDGE_DRAM_CHN_0_MTR_4_BAR	12
+#define BRIDGE_DRAM_CHN_0_MTR_5_BAR	13
+#define BRIDGE_DRAM_CHN_0_MTR_6_BAR	14
+#define BRIDGE_DRAM_CHN_0_MTR_7_BAR	15
+#define BRIDGE_DRAM_CHN_1_MTR_0_BAR	16
+#define BRIDGE_DRAM_CHN_1_MTR_1_BAR	17
+#define BRIDGE_DRAM_CHN_1_MTR_2_BAR	18
+#define BRIDGE_DRAM_CHN_1_MTR_3_BAR	19
+#define BRIDGE_DRAM_CHN_1_MTR_4_BAR	20
+#define BRIDGE_DRAM_CHN_1_MTR_5_BAR	21
+#define BRIDGE_DRAM_CHN_1_MTR_6_BAR	22
+#define BRIDGE_DRAM_CHN_1_MTR_7_BAR	23
+#define BRIDGE_CFG_BAR			24
+#define BRIDGE_PHNX_IO_BAR		25
+#define BRIDGE_FLASH_BAR		26
+#define BRIDGE_SRAM_BAR			27
+#define BRIDGE_HTMEM_BAR		28
+#define BRIDGE_HTINT_BAR		29
+#define BRIDGE_HTPIC_BAR		30
+#define BRIDGE_HTSM_BAR			31
+#define BRIDGE_HTIO_BAR			32
+#define BRIDGE_HTCFG_BAR		33
+#define BRIDGE_PCIXCFG_BAR		34
+#define BRIDGE_PCIXMEM_BAR		35
+#define BRIDGE_PCIXIO_BAR		36
+#define BRIDGE_DEVICE_MASK		37
+#define BRIDGE_AERR_INTR_LOG1		38
+#define BRIDGE_AERR_INTR_LOG2		39
+#define BRIDGE_AERR_INTR_LOG3		40
+#define BRIDGE_AERR_DEV_STAT		41
+#define BRIDGE_AERR1_LOG1		42
+#define BRIDGE_AERR1_LOG2		43
+#define BRIDGE_AERR1_LOG3		44
+#define BRIDGE_AERR1_DEV_STAT		45
+#define BRIDGE_AERR_INTR_EN		46
+#define BRIDGE_AERR_UPG			47
+#define BRIDGE_AERR_CLEAR		48
+#define BRIDGE_AERR1_CLEAR		49
+#define BRIDGE_SBE_COUNTS		50
+#define BRIDGE_DBE_COUNTS		51
+#define BRIDGE_BITERR_INT_EN		52
+
+#define BRIDGE_SYS2IO_CREDITS		53
+#define BRIDGE_EVNT_CNT_CTRL1		54
+#define BRIDGE_EVNT_COUNTER1		55
+#define BRIDGE_EVNT_CNT_CTRL2		56
+#define BRIDGE_EVNT_COUNTER2		57
+#define BRIDGE_RESERVED1		58
+
+#define BRIDGE_DEFEATURE		59
+#define BRIDGE_SCRATCH0			60
+#define BRIDGE_SCRATCH1			61
+#define BRIDGE_SCRATCH2			62
+#define BRIDGE_SCRATCH3			63
+
+#endif
diff --git a/arch/mips/include/asm/netlogic/xlr/flash.h b/arch/mips/include/asm/netlogic/xlr/flash.h
new file mode 100644
index 000000000000..f8aca5472b6c
--- /dev/null
+++ b/arch/mips/include/asm/netlogic/xlr/flash.h
@@ -0,0 +1,55 @@
+/*
+ * Copyright (c) 2003-2012 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the Broadcom
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+#ifndef _ASM_NLM_FLASH_H_
+#define _ASM_NLM_FLASH_H_
+
+#define FLASH_CSBASE_ADDR(cs)		(cs)
+#define FLASH_CSADDR_MASK(cs)		(0x10 + (cs))
+#define FLASH_CSDEV_PARM(cs)		(0x20 + (cs))
+#define FLASH_CSTIME_PARMA(cs)		(0x30 + (cs))
+#define FLASH_CSTIME_PARMB(cs)		(0x40 + (cs))
+
+#define FLASH_INT_MASK			0x50
+#define FLASH_INT_STATUS		0x60
+#define FLASH_ERROR_STATUS		0x70
+#define FLASH_ERROR_ADDR		0x80
+
+#define FLASH_NAND_CLE(cs)		(0x90 + (cs))
+#define FLASH_NAND_ALE(cs)		(0xa0 + (cs))
+
+#define FLASH_NAND_CSDEV_PARAM		0x000041e6
+#define FLASH_NAND_CSTIME_PARAMA	0x4f400e22
+#define FLASH_NAND_CSTIME_PARAMB	0x000083cf
+
+#endif
diff --git a/arch/mips/include/asm/netlogic/xlr/gpio.h b/arch/mips/include/asm/netlogic/xlr/gpio.h
index 51f6ad4aeb14..8492e835b110 100644
--- a/arch/mips/include/asm/netlogic/xlr/gpio.h
+++ b/arch/mips/include/asm/netlogic/xlr/gpio.h
@@ -35,39 +35,40 @@
 #ifndef _ASM_NLM_GPIO_H
 #define _ASM_NLM_GPIO_H
 
-#define NETLOGIC_GPIO_INT_EN_REG		0
-#define NETLOGIC_GPIO_INPUT_INVERSION_REG	1
-#define NETLOGIC_GPIO_IO_DIR_REG		2
-#define NETLOGIC_GPIO_IO_DATA_WR_REG		3
-#define NETLOGIC_GPIO_IO_DATA_RD_REG		4
+#define GPIO_INT_EN_REG			0
+#define GPIO_INPUT_INVERSION_REG	1
+#define GPIO_IO_DIR_REG			2
+#define GPIO_IO_DATA_WR_REG		3
+#define GPIO_IO_DATA_RD_REG		4
 
-#define NETLOGIC_GPIO_SWRESET_REG		8
-#define NETLOGIC_GPIO_DRAM1_CNTRL_REG		9
-#define NETLOGIC_GPIO_DRAM1_RATIO_REG		10
-#define NETLOGIC_GPIO_DRAM1_RESET_REG		11
-#define NETLOGIC_GPIO_DRAM1_STATUS_REG		12
-#define NETLOGIC_GPIO_DRAM2_CNTRL_REG		13
-#define NETLOGIC_GPIO_DRAM2_RATIO_REG		14
-#define NETLOGIC_GPIO_DRAM2_RESET_REG		15
-#define NETLOGIC_GPIO_DRAM2_STATUS_REG		16
+#define GPIO_SWRESET_REG		8
+#define GPIO_DRAM1_CNTRL_REG		9
+#define GPIO_DRAM1_RATIO_REG		10
+#define GPIO_DRAM1_RESET_REG		11
+#define GPIO_DRAM1_STATUS_REG		12
+#define GPIO_DRAM2_CNTRL_REG		13
+#define GPIO_DRAM2_RATIO_REG		14
+#define GPIO_DRAM2_RESET_REG		15
+#define GPIO_DRAM2_STATUS_REG		16
 
-#define NETLOGIC_GPIO_PWRON_RESET_CFG_REG	21
-#define NETLOGIC_GPIO_BIST_ALL_GO_STATUS_REG	24
-#define NETLOGIC_GPIO_BIST_CPU_GO_STATUS_REG	25
-#define NETLOGIC_GPIO_BIST_DEV_GO_STATUS_REG	26
+#define GPIO_PWRON_RESET_CFG_REG	21
+#define GPIO_BIST_ALL_GO_STATUS_REG	24
+#define GPIO_BIST_CPU_GO_STATUS_REG	25
+#define GPIO_BIST_DEV_GO_STATUS_REG	26
 
-#define NETLOGIC_GPIO_FUSE_BANK_REG		35
-#define NETLOGIC_GPIO_CPU_RESET_REG		40
-#define NETLOGIC_GPIO_RNG_REG			43
+#define GPIO_FUSE_BANK_REG		35
+#define GPIO_CPU_RESET_REG		40
+#define GPIO_RNG_REG			43
 
-#define NETLOGIC_PWRON_RESET_PCMCIA_BOOT	17
-#define NETLOGIC_GPIO_LED_BITMAP	0x1700000
-#define NETLOGIC_GPIO_LED_0_SHIFT		20
-#define NETLOGIC_GPIO_LED_1_SHIFT		24
+#define PWRON_RESET_PCMCIA_BOOT		17
 
-#define NETLOGIC_GPIO_LED_OUTPUT_CODE_RESET	0x01
-#define NETLOGIC_GPIO_LED_OUTPUT_CODE_HARD_RESET 0x02
-#define NETLOGIC_GPIO_LED_OUTPUT_CODE_SOFT_RESET 0x03
-#define NETLOGIC_GPIO_LED_OUTPUT_CODE_MAIN	0x04
+#define GPIO_LED_BITMAP			0x1700000
+#define GPIO_LED_0_SHIFT		20
+#define GPIO_LED_1_SHIFT		24
+
+#define GPIO_LED_OUTPUT_CODE_RESET	0x01
+#define GPIO_LED_OUTPUT_CODE_HARD_RESET 0x02
+#define GPIO_LED_OUTPUT_CODE_SOFT_RESET 0x03
+#define GPIO_LED_OUTPUT_CODE_MAIN	0x04
 
 #endif
diff --git a/arch/mips/include/asm/octeon/cvmx-helper-fpa.h b/arch/mips/include/asm/octeon/cvmx-helper-fpa.h
deleted file mode 100644
index 5ff8c93198de..000000000000
--- a/arch/mips/include/asm/octeon/cvmx-helper-fpa.h
+++ /dev/null
@@ -1,64 +0,0 @@
-/***********************license start***************
- * Author: Cavium Networks
- *
- * Contact: support@caviumnetworks.com
- * This file is part of the OCTEON SDK
- *
- * Copyright (c) 2003-2008 Cavium Networks
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- *
- * This file is distributed in the hope that it will be useful, but
- * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this file; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- * or visit http://www.gnu.org/licenses/.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium Networks for more information
- ***********************license end**************************************/
-
-/**
- * @file
- *
- * Helper functions for FPA setup.
- *
- */
-#ifndef __CVMX_HELPER_H_FPA__
-#define __CVMX_HELPER_H_FPA__
-
-/**
- * Allocate memory and initialize the FPA pools using memory
- * from cvmx-bootmem. Sizes of each element in the pools is
- * controlled by the cvmx-config.h header file. Specifying
- * zero for any parameter will cause that FPA pool to not be
- * setup. This is useful if you aren't using some of the
- * hardware and want to save memory.
- *
- * @packet_buffers:
- *               Number of packet buffers to allocate
- * @work_queue_entries:
- *               Number of work queue entries
- * @pko_buffers:
- *               PKO Command buffers. You should at minimum have two per
- *               each PKO queue.
- * @tim_buffers:
- *               TIM ring buffer command queues. At least two per timer bucket
- *               is recommened.
- * @dfa_buffers:
- *               DFA command buffer. A relatively small (32 for example)
- *               number should work.
- * Returns Zero on success, non-zero if out of memory
- */
-extern int cvmx_helper_initialize_fpa(int packet_buffers,
-				      int work_queue_entries, int pko_buffers,
-				      int tim_buffers, int dfa_buffers);
-
-#endif /* __CVMX_HELPER_H__ */
diff --git a/arch/mips/include/asm/octeon/cvmx-helper.h b/arch/mips/include/asm/octeon/cvmx-helper.h
index 3169cd79f2ac..0ac6b9f412be 100644
--- a/arch/mips/include/asm/octeon/cvmx-helper.h
+++ b/arch/mips/include/asm/octeon/cvmx-helper.h
@@ -61,8 +61,6 @@ typedef union {
 	} s;
 } cvmx_helper_link_info_t;
 
-#include "cvmx-helper-fpa.h"
-
 #include <asm/octeon/cvmx-helper-errata.h>
 #include "cvmx-helper-loop.h"
 #include "cvmx-helper-npi.h"
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index f72f768cd3a4..1e2486e23573 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -215,11 +215,6 @@ struct octeon_cf_data {
 	int		dma_engine;	/* -1 for no DMA */
 };
 
-struct octeon_i2c_data {
-	unsigned int	sys_freq;
-	unsigned int	i2c_freq;
-};
-
 extern void octeon_write_lcd(const char *s);
 extern void octeon_check_cpu_bist(void);
 extern int octeon_get_boot_debug_flag(void);
diff --git a/arch/mips/include/asm/prom.h b/arch/mips/include/asm/prom.h
index 7206d445bab8..8808bf548b99 100644
--- a/arch/mips/include/asm/prom.h
+++ b/arch/mips/include/asm/prom.h
@@ -20,9 +20,6 @@
 extern int early_init_dt_scan_memory_arch(unsigned long node,
 	const char *uname, int depth, void *data);
 
-extern int reserve_mem_mach(unsigned long addr, unsigned long size);
-extern void free_mem_mach(unsigned long addr, unsigned long size);
-
 extern void device_tree_init(void);
 
 static inline unsigned long pci_address_to_pio(phys_addr_t address)
diff --git a/arch/mips/include/asm/smtc.h b/arch/mips/include/asm/smtc.h
index c9736fc06325..8935426a56ab 100644
--- a/arch/mips/include/asm/smtc.h
+++ b/arch/mips/include/asm/smtc.h
@@ -33,6 +33,12 @@ typedef long asiduse;
 #endif
 #endif
 
+/*
+ * VPE Management information
+ */
+
+#define MAX_SMTC_VPES	MAX_SMTC_TLBS	/* FIXME: May not always be true. */
+
 extern asiduse smtc_live_asid[MAX_SMTC_TLBS][MAX_SMTC_ASIDS];
 
 struct mm_struct;
diff --git a/arch/mips/include/asm/uaccess.h b/arch/mips/include/asm/uaccess.h
index 653a412c036c..3b92efef56d3 100644
--- a/arch/mips/include/asm/uaccess.h
+++ b/arch/mips/include/asm/uaccess.h
@@ -687,7 +687,7 @@ extern size_t __copy_user(void *__to, const void *__from, size_t __n);
 	__MODULE_JAL(__copy_user)					\
 	: "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r)	\
 	:								\
-	: "$8", "$9", "$10", "$11", "$12", "$15", "$24", "$31",		\
+	: "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31",	\
 	  DADDI_SCRATCH, "memory");					\
 	__cu_len_r;							\
 })
@@ -797,7 +797,7 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
 	".set\treorder"							\
 	: "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r)	\
 	:								\
-	: "$8", "$9", "$10", "$11", "$12", "$15", "$24", "$31",		\
+	: "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31",	\
 	  DADDI_SCRATCH, "memory");					\
 	__cu_len_r;							\
 })
@@ -820,7 +820,7 @@ extern size_t __copy_user_inatomic(void *__to, const void *__from, size_t __n);
 	".set\treorder"							\
 	: "+r" (__cu_to_r), "+r" (__cu_from_r), "+r" (__cu_len_r)	\
 	:								\
-	: "$8", "$9", "$10", "$11", "$12", "$15", "$24", "$31",		\
+	: "$8", "$9", "$10", "$11", "$12", "$14", "$15", "$24", "$31",	\
 	  DADDI_SCRATCH, "memory");					\
 	__cu_len_r;							\
 })
diff --git a/arch/mips/include/asm/uasm.h b/arch/mips/include/asm/uasm.h
index 440a21dab575..3d9f75f7ffc9 100644
--- a/arch/mips/include/asm/uasm.h
+++ b/arch/mips/include/asm/uasm.h
@@ -6,6 +6,7 @@
  * Copyright (C) 2004, 2005, 2006, 2008  Thiemo Seufer
  * Copyright (C) 2005  Maciej W. Rozycki
  * Copyright (C) 2006  Ralf Baechle (ralf@linux-mips.org)
+ * Copyright (C) 2012  MIPS Technologies, Inc.
  */
 
 #include <linux/types.h>
@@ -62,8 +63,10 @@ void __uasminit uasm_i##op(u32 **buf, unsigned int a, signed int b)
 
 Ip_u2u1s3(_addiu);
 Ip_u3u1u2(_addu);
-Ip_u2u1u3(_andi);
 Ip_u3u1u2(_and);
+Ip_u2u1u3(_andi);
+Ip_u1u2s3(_bbit0);
+Ip_u1u2s3(_bbit1);
 Ip_u1u2s3(_beq);
 Ip_u1u2s3(_beql);
 Ip_u1s2(_bgez);
@@ -72,55 +75,54 @@ Ip_u1s2(_bltz);
 Ip_u1s2(_bltzl);
 Ip_u1u2s3(_bne);
 Ip_u2s3u1(_cache);
-Ip_u1u2u3(_dmfc0);
-Ip_u1u2u3(_dmtc0);
 Ip_u2u1s3(_daddiu);
 Ip_u3u1u2(_daddu);
+Ip_u2u1msbu3(_dins);
+Ip_u2u1msbu3(_dinsm);
+Ip_u1u2u3(_dmfc0);
+Ip_u1u2u3(_dmtc0);
+Ip_u2u1u3(_drotr);
+Ip_u2u1u3(_drotr32);
 Ip_u2u1u3(_dsll);
 Ip_u2u1u3(_dsll32);
 Ip_u2u1u3(_dsra);
 Ip_u2u1u3(_dsrl);
 Ip_u2u1u3(_dsrl32);
-Ip_u2u1u3(_drotr);
-Ip_u2u1u3(_drotr32);
 Ip_u3u1u2(_dsubu);
 Ip_0(_eret);
 Ip_u1(_j);
 Ip_u1(_jal);
 Ip_u1(_jr);
 Ip_u2s3u1(_ld);
+Ip_u3u1u2(_ldx);
 Ip_u2s3u1(_ll);
 Ip_u2s3u1(_lld);
 Ip_u1s2(_lui);
 Ip_u2s3u1(_lw);
+Ip_u3u1u2(_lwx);
 Ip_u1u2u3(_mfc0);
 Ip_u1u2u3(_mtc0);
-Ip_u2u1u3(_ori);
 Ip_u3u1u2(_or);
+Ip_u2u1u3(_ori);
 Ip_u2s3u1(_pref);
 Ip_0(_rfe);
+Ip_u2u1u3(_rotr);
 Ip_u2s3u1(_sc);
 Ip_u2s3u1(_scd);
 Ip_u2s3u1(_sd);
 Ip_u2u1u3(_sll);
 Ip_u2u1u3(_sra);
 Ip_u2u1u3(_srl);
-Ip_u2u1u3(_rotr);
 Ip_u3u1u2(_subu);
 Ip_u2s3u1(_sw);
+Ip_u1(_syscall);
 Ip_0(_tlbp);
 Ip_0(_tlbr);
 Ip_0(_tlbwi);
 Ip_0(_tlbwr);
 Ip_u3u1u2(_xor);
 Ip_u2u1u3(_xori);
-Ip_u2u1msbu3(_dins);
-Ip_u2u1msbu3(_dinsm);
-Ip_u1(_syscall);
-Ip_u1u2s3(_bbit0);
-Ip_u1u2s3(_bbit1);
-Ip_u3u1u2(_lwx);
-Ip_u3u1u2(_ldx);
+
 
 /* Handle labels. */
 struct uasm_label {
@@ -145,37 +147,37 @@ static inline void __uasminit uasm_l##lb(struct uasm_label **lab, u32 *addr) \
 
 /* convenience macros for instructions */
 #ifdef CONFIG_64BIT
+# define UASM_i_ADDIU(buf, rs, rt, val) uasm_i_daddiu(buf, rs, rt, val)
+# define UASM_i_ADDU(buf, rs, rt, rd) uasm_i_daddu(buf, rs, rt, rd)
+# define UASM_i_LL(buf, rs, rt, off) uasm_i_lld(buf, rs, rt, off)
 # define UASM_i_LW(buf, rs, rt, off) uasm_i_ld(buf, rs, rt, off)
-# define UASM_i_SW(buf, rs, rt, off) uasm_i_sd(buf, rs, rt, off)
+# define UASM_i_LWX(buf, rs, rt, rd) uasm_i_ldx(buf, rs, rt, rd)
+# define UASM_i_MFC0(buf, rt, rd...) uasm_i_dmfc0(buf, rt, rd)
+# define UASM_i_MTC0(buf, rt, rd...) uasm_i_dmtc0(buf, rt, rd)
+# define UASM_i_ROTR(buf, rs, rt, sh) uasm_i_drotr(buf, rs, rt, sh)
+# define UASM_i_SC(buf, rs, rt, off) uasm_i_scd(buf, rs, rt, off)
 # define UASM_i_SLL(buf, rs, rt, sh) uasm_i_dsll(buf, rs, rt, sh)
 # define UASM_i_SRA(buf, rs, rt, sh) uasm_i_dsra(buf, rs, rt, sh)
 # define UASM_i_SRL(buf, rs, rt, sh) uasm_i_dsrl(buf, rs, rt, sh)
 # define UASM_i_SRL_SAFE(buf, rs, rt, sh) uasm_i_dsrl_safe(buf, rs, rt, sh)
-# define UASM_i_ROTR(buf, rs, rt, sh) uasm_i_drotr(buf, rs, rt, sh)
-# define UASM_i_MFC0(buf, rt, rd...) uasm_i_dmfc0(buf, rt, rd)
-# define UASM_i_MTC0(buf, rt, rd...) uasm_i_dmtc0(buf, rt, rd)
-# define UASM_i_ADDIU(buf, rs, rt, val) uasm_i_daddiu(buf, rs, rt, val)
-# define UASM_i_ADDU(buf, rs, rt, rd) uasm_i_daddu(buf, rs, rt, rd)
 # define UASM_i_SUBU(buf, rs, rt, rd) uasm_i_dsubu(buf, rs, rt, rd)
-# define UASM_i_LL(buf, rs, rt, off) uasm_i_lld(buf, rs, rt, off)
-# define UASM_i_SC(buf, rs, rt, off) uasm_i_scd(buf, rs, rt, off)
-# define UASM_i_LWX(buf, rs, rt, rd) uasm_i_ldx(buf, rs, rt, rd)
+# define UASM_i_SW(buf, rs, rt, off) uasm_i_sd(buf, rs, rt, off)
 #else
+# define UASM_i_ADDIU(buf, rs, rt, val) uasm_i_addiu(buf, rs, rt, val)
+# define UASM_i_ADDU(buf, rs, rt, rd) uasm_i_addu(buf, rs, rt, rd)
+# define UASM_i_LL(buf, rs, rt, off) uasm_i_ll(buf, rs, rt, off)
 # define UASM_i_LW(buf, rs, rt, off) uasm_i_lw(buf, rs, rt, off)
-# define UASM_i_SW(buf, rs, rt, off) uasm_i_sw(buf, rs, rt, off)
+# define UASM_i_LWX(buf, rs, rt, rd) uasm_i_lwx(buf, rs, rt, rd)
+# define UASM_i_MFC0(buf, rt, rd...) uasm_i_mfc0(buf, rt, rd)
+# define UASM_i_MTC0(buf, rt, rd...) uasm_i_mtc0(buf, rt, rd)
+# define UASM_i_ROTR(buf, rs, rt, sh) uasm_i_rotr(buf, rs, rt, sh)
+# define UASM_i_SC(buf, rs, rt, off) uasm_i_sc(buf, rs, rt, off)
 # define UASM_i_SLL(buf, rs, rt, sh) uasm_i_sll(buf, rs, rt, sh)
 # define UASM_i_SRA(buf, rs, rt, sh) uasm_i_sra(buf, rs, rt, sh)
 # define UASM_i_SRL(buf, rs, rt, sh) uasm_i_srl(buf, rs, rt, sh)
 # define UASM_i_SRL_SAFE(buf, rs, rt, sh) uasm_i_srl(buf, rs, rt, sh)
-# define UASM_i_ROTR(buf, rs, rt, sh) uasm_i_rotr(buf, rs, rt, sh)
-# define UASM_i_MFC0(buf, rt, rd...) uasm_i_mfc0(buf, rt, rd)
-# define UASM_i_MTC0(buf, rt, rd...) uasm_i_mtc0(buf, rt, rd)
-# define UASM_i_ADDIU(buf, rs, rt, val) uasm_i_addiu(buf, rs, rt, val)
-# define UASM_i_ADDU(buf, rs, rt, rd) uasm_i_addu(buf, rs, rt, rd)
 # define UASM_i_SUBU(buf, rs, rt, rd) uasm_i_subu(buf, rs, rt, rd)
-# define UASM_i_LL(buf, rs, rt, off) uasm_i_ll(buf, rs, rt, off)
-# define UASM_i_SC(buf, rs, rt, off) uasm_i_sc(buf, rs, rt, off)
-# define UASM_i_LWX(buf, rs, rt, rd) uasm_i_lwx(buf, rs, rt, rd)
+# define UASM_i_SW(buf, rs, rt, off) uasm_i_sw(buf, rs, rt, off)
 #endif
 
 #define uasm_i_b(buf, off) uasm_i_beq(buf, 0, 0, off)
@@ -183,19 +185,10 @@ static inline void __uasminit uasm_l##lb(struct uasm_label **lab, u32 *addr) \
 #define uasm_i_beqzl(buf, rs, off) uasm_i_beql(buf, rs, 0, off)
 #define uasm_i_bnez(buf, rs, off) uasm_i_bne(buf, rs, 0, off)
 #define uasm_i_bnezl(buf, rs, off) uasm_i_bnel(buf, rs, 0, off)
+#define uasm_i_ehb(buf) uasm_i_sll(buf, 0, 0, 3)
 #define uasm_i_move(buf, a, b) UASM_i_ADDU(buf, a, 0, b)
 #define uasm_i_nop(buf) uasm_i_sll(buf, 0, 0, 0)
 #define uasm_i_ssnop(buf) uasm_i_sll(buf, 0, 0, 1)
-#define uasm_i_ehb(buf) uasm_i_sll(buf, 0, 0, 3)
-
-static inline void uasm_i_dsrl_safe(u32 **p, unsigned int a1,
-				    unsigned int a2, unsigned int a3)
-{
-	if (a3 < 32)
-		uasm_i_dsrl(p, a1, a2, a3);
-	else
-		uasm_i_dsrl32(p, a1, a2, a3 - 32);
-}
 
 static inline void uasm_i_drotr_safe(u32 **p, unsigned int a1,
 				     unsigned int a2, unsigned int a3)
@@ -215,6 +208,15 @@ static inline void uasm_i_dsll_safe(u32 **p, unsigned int a1,
 		uasm_i_dsll32(p, a1, a2, a3 - 32);
 }
 
+static inline void uasm_i_dsrl_safe(u32 **p, unsigned int a1,
+				    unsigned int a2, unsigned int a3)
+{
+	if (a3 < 32)
+		uasm_i_dsrl(p, a1, a2, a3);
+	else
+		uasm_i_dsrl32(p, a1, a2, a3 - 32);
+}
+
 /* Handle relocations. */
 struct uasm_reloc {
 	u32 *addr;
@@ -234,16 +236,16 @@ void uasm_copy_handler(struct uasm_reloc *rel, struct uasm_label *lab,
 int uasm_insn_has_bdelay(struct uasm_reloc *rel, u32 *addr);
 
 /* Convenience functions for labeled branches. */
-void uasm_il_bltz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
 void uasm_il_b(u32 **p, struct uasm_reloc **r, int lid);
+void uasm_il_bbit0(u32 **p, struct uasm_reloc **r, unsigned int reg,
+		   unsigned int bit, int lid);
+void uasm_il_bbit1(u32 **p, struct uasm_reloc **r, unsigned int reg,
+		   unsigned int bit, int lid);
 void uasm_il_beqz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
 void uasm_il_beqzl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
+void uasm_il_bgezl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
+void uasm_il_bgez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
+void uasm_il_bltz(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
 void uasm_il_bne(u32 **p, struct uasm_reloc **r, unsigned int reg1,
 		 unsigned int reg2, int lid);
 void uasm_il_bnez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
-void uasm_il_bgezl(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
-void uasm_il_bgez(u32 **p, struct uasm_reloc **r, unsigned int reg, int lid);
-void uasm_il_bbit0(u32 **p, struct uasm_reloc **r, unsigned int reg,
-		   unsigned int bit, int lid);
-void uasm_il_bbit1(u32 **p, struct uasm_reloc **r, unsigned int reg,
-		   unsigned int bit, int lid);
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index d8dad5340ea3..bebbde01be92 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -1034,7 +1034,6 @@
 #ifndef __ASSEMBLY__
 
 #define __ARCH_OMIT_COMPAT_SYS_GETDENTS64
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_ALARM
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c
index 9a91fe9de696..9a3d9de4d04e 100644
--- a/arch/mips/jz4740/board-qi_lb60.c
+++ b/arch/mips/jz4740/board-qi_lb60.c
@@ -140,6 +140,7 @@ static void qi_lb60_nand_ident(struct platform_device *pdev,
 static struct jz_nand_platform_data qi_lb60_nand_pdata = {
 	.ident_callback = qi_lb60_nand_ident,
 	.busy_gpio = 94,
+	.banks = { 1 },
 };
 
 /* Keyboard*/
diff --git a/arch/mips/jz4740/platform.c b/arch/mips/jz4740/platform.c
index 10929e2bc6d8..e342ed4cbd43 100644
--- a/arch/mips/jz4740/platform.c
+++ b/arch/mips/jz4740/platform.c
@@ -157,11 +157,29 @@ static struct resource jz4740_nand_resources[] = {
 		.flags	= IORESOURCE_MEM,
 	},
 	{
-		.name	= "bank",
+		.name	= "bank1",
 		.start	= 0x18000000,
 		.end	= 0x180C0000 - 1,
 		.flags = IORESOURCE_MEM,
 	},
+	{
+		.name	= "bank2",
+		.start	= 0x14000000,
+		.end	= 0x140C0000 - 1,
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name	= "bank3",
+		.start	= 0x0C000000,
+		.end	= 0x0C0C0000 - 1,
+		.flags = IORESOURCE_MEM,
+	},
+	{
+		.name	= "bank4",
+		.start	= 0x08000000,
+		.end	= 0x080C0000 - 1,
+		.flags = IORESOURCE_MEM,
+	},
 };
 
 struct platform_device jz4740_nand_device = {
diff --git a/arch/mips/jz4740/reset.c b/arch/mips/jz4740/reset.c
index 5f1fb95c0d0d..6c0da5afcf17 100644
--- a/arch/mips/jz4740/reset.c
+++ b/arch/mips/jz4740/reset.c
@@ -21,6 +21,9 @@
 #include <asm/mach-jz4740/base.h>
 #include <asm/mach-jz4740/timer.h>
 
+#include "reset.h"
+#include "clock.h"
+
 static void jz4740_halt(void)
 {
 	while (1) {
@@ -53,21 +56,57 @@ static void jz4740_restart(char *command)
 	jz4740_halt();
 }
 
-#define JZ_REG_RTC_CTRL		0x00
-#define JZ_REG_RTC_HIBERNATE	0x20
+#define JZ_REG_RTC_CTRL			0x00
+#define JZ_REG_RTC_HIBERNATE		0x20
+#define JZ_REG_RTC_WAKEUP_FILTER	0x24
+#define JZ_REG_RTC_RESET_COUNTER	0x28
 
-#define JZ_RTC_CTRL_WRDY	BIT(7)
+#define JZ_RTC_CTRL_WRDY		BIT(7)
+#define JZ_RTC_WAKEUP_FILTER_MASK	0x0000FFE0
+#define JZ_RTC_RESET_COUNTER_MASK	0x00000FE0
 
-static void jz4740_power_off(void)
+static inline void jz4740_rtc_wait_ready(void __iomem *rtc_base)
 {
-	void __iomem *rtc_base = ioremap(JZ4740_RTC_BASE_ADDR, 0x24);
 	uint32_t ctrl;
 
 	do {
 		ctrl = readl(rtc_base + JZ_REG_RTC_CTRL);
 	} while (!(ctrl & JZ_RTC_CTRL_WRDY));
+}
 
+static void jz4740_power_off(void)
+{
+	void __iomem *rtc_base = ioremap(JZ4740_RTC_BASE_ADDR, 0x38);
+	unsigned long wakeup_filter_ticks;
+	unsigned long reset_counter_ticks;
+
+	/*
+	 * Set minimum wakeup pin assertion time: 100 ms.
+	 * Range is 0 to 2 sec if RTC is clocked at 32 kHz.
+	 */
+	wakeup_filter_ticks = (100 * jz4740_clock_bdata.rtc_rate) / 1000;
+	if (wakeup_filter_ticks < JZ_RTC_WAKEUP_FILTER_MASK)
+		wakeup_filter_ticks &= JZ_RTC_WAKEUP_FILTER_MASK;
+	else
+		wakeup_filter_ticks = JZ_RTC_WAKEUP_FILTER_MASK;
+	jz4740_rtc_wait_ready(rtc_base);
+	writel(wakeup_filter_ticks, rtc_base + JZ_REG_RTC_WAKEUP_FILTER);
+
+	/*
+	 * Set reset pin low-level assertion time after wakeup: 60 ms.
+	 * Range is 0 to 125 ms if RTC is clocked at 32 kHz.
+	 */
+	reset_counter_ticks = (60 * jz4740_clock_bdata.rtc_rate) / 1000;
+	if (reset_counter_ticks < JZ_RTC_RESET_COUNTER_MASK)
+		reset_counter_ticks &= JZ_RTC_RESET_COUNTER_MASK;
+	else
+		reset_counter_ticks = JZ_RTC_RESET_COUNTER_MASK;
+	jz4740_rtc_wait_ready(rtc_base);
+	writel(reset_counter_ticks, rtc_base + JZ_REG_RTC_RESET_COUNTER);
+
+	jz4740_rtc_wait_ready(rtc_base);
 	writel(1, rtc_base + JZ_REG_RTC_HIBERNATE);
+
 	jz4740_halt();
 }
 
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index f4630e1082ab..1b51046191e8 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -190,6 +190,7 @@ void __init check_wait(void)
 	case CPU_CAVIUM_OCTEON_PLUS:
 	case CPU_CAVIUM_OCTEON2:
 	case CPU_JZRISC:
+	case CPU_LOONGSON1:
 	case CPU_XLR:
 	case CPU_XLP:
 		cpu_wait = r4k_wait;
@@ -330,6 +331,154 @@ static inline void cpu_probe_vmbits(struct cpuinfo_mips *c)
 #endif
 }
 
+static char unknown_isa[] __cpuinitdata = KERN_ERR \
+	"Unsupported ISA type, c0.config0: %d.";
+
+static inline unsigned int decode_config0(struct cpuinfo_mips *c)
+{
+	unsigned int config0;
+	int isa;
+
+	config0 = read_c0_config();
+
+	if (((config0 & MIPS_CONF_MT) >> 7) == 1)
+		c->options |= MIPS_CPU_TLB;
+	isa = (config0 & MIPS_CONF_AT) >> 13;
+	switch (isa) {
+	case 0:
+		switch ((config0 & MIPS_CONF_AR) >> 10) {
+		case 0:
+			c->isa_level = MIPS_CPU_ISA_M32R1;
+			break;
+		case 1:
+			c->isa_level = MIPS_CPU_ISA_M32R2;
+			break;
+		default:
+			goto unknown;
+		}
+		break;
+	case 2:
+		switch ((config0 & MIPS_CONF_AR) >> 10) {
+		case 0:
+			c->isa_level = MIPS_CPU_ISA_M64R1;
+			break;
+		case 1:
+			c->isa_level = MIPS_CPU_ISA_M64R2;
+			break;
+		default:
+			goto unknown;
+		}
+		break;
+	default:
+		goto unknown;
+	}
+
+	return config0 & MIPS_CONF_M;
+
+unknown:
+	panic(unknown_isa, config0);
+}
+
+static inline unsigned int decode_config1(struct cpuinfo_mips *c)
+{
+	unsigned int config1;
+
+	config1 = read_c0_config1();
+
+	if (config1 & MIPS_CONF1_MD)
+		c->ases |= MIPS_ASE_MDMX;
+	if (config1 & MIPS_CONF1_WR)
+		c->options |= MIPS_CPU_WATCH;
+	if (config1 & MIPS_CONF1_CA)
+		c->ases |= MIPS_ASE_MIPS16;
+	if (config1 & MIPS_CONF1_EP)
+		c->options |= MIPS_CPU_EJTAG;
+	if (config1 & MIPS_CONF1_FP) {
+		c->options |= MIPS_CPU_FPU;
+		c->options |= MIPS_CPU_32FPR;
+	}
+	if (cpu_has_tlb)
+		c->tlbsize = ((config1 & MIPS_CONF1_TLBS) >> 25) + 1;
+
+	return config1 & MIPS_CONF_M;
+}
+
+static inline unsigned int decode_config2(struct cpuinfo_mips *c)
+{
+	unsigned int config2;
+
+	config2 = read_c0_config2();
+
+	if (config2 & MIPS_CONF2_SL)
+		c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT;
+
+	return config2 & MIPS_CONF_M;
+}
+
+static inline unsigned int decode_config3(struct cpuinfo_mips *c)
+{
+	unsigned int config3;
+
+	config3 = read_c0_config3();
+
+	if (config3 & MIPS_CONF3_SM)
+		c->ases |= MIPS_ASE_SMARTMIPS;
+	if (config3 & MIPS_CONF3_DSP)
+		c->ases |= MIPS_ASE_DSP;
+	if (config3 & MIPS_CONF3_VINT)
+		c->options |= MIPS_CPU_VINT;
+	if (config3 & MIPS_CONF3_VEIC)
+		c->options |= MIPS_CPU_VEIC;
+	if (config3 & MIPS_CONF3_MT)
+		c->ases |= MIPS_ASE_MIPSMT;
+	if (config3 & MIPS_CONF3_ULRI)
+		c->options |= MIPS_CPU_ULRI;
+
+	return config3 & MIPS_CONF_M;
+}
+
+static inline unsigned int decode_config4(struct cpuinfo_mips *c)
+{
+	unsigned int config4;
+
+	config4 = read_c0_config4();
+
+	if ((config4 & MIPS_CONF4_MMUEXTDEF) == MIPS_CONF4_MMUEXTDEF_MMUSIZEEXT
+	    && cpu_has_tlb)
+		c->tlbsize += (config4 & MIPS_CONF4_MMUSIZEEXT) * 0x40;
+
+	c->kscratch_mask = (config4 >> 16) & 0xff;
+
+	return config4 & MIPS_CONF_M;
+}
+
+static void __cpuinit decode_configs(struct cpuinfo_mips *c)
+{
+	int ok;
+
+	/* MIPS32 or MIPS64 compliant CPU.  */
+	c->options = MIPS_CPU_4KEX | MIPS_CPU_4K_CACHE | MIPS_CPU_COUNTER |
+		     MIPS_CPU_DIVEC | MIPS_CPU_LLSC | MIPS_CPU_MCHECK;
+
+	c->scache.flags = MIPS_CACHE_NOT_PRESENT;
+
+	ok = decode_config0(c);			/* Read Config registers.  */
+	BUG_ON(!ok);				/* Arch spec violation!  */
+	if (ok)
+		ok = decode_config1(c);
+	if (ok)
+		ok = decode_config2(c);
+	if (ok)
+		ok = decode_config3(c);
+	if (ok)
+		ok = decode_config4(c);
+
+	mips_probe_watch_registers(c);
+
+	if (cpu_has_mips_r2)
+		c->core = read_c0_ebase() & 0x3ff;
+}
+
 #define R4K_OPTS (MIPS_CPU_TLB | MIPS_CPU_4KEX | MIPS_CPU_4K_CACHE \
 		| MIPS_CPU_COUNTER)
 
@@ -638,155 +787,19 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 			     MIPS_CPU_32FPR;
 		c->tlbsize = 64;
 		break;
-	}
-}
-
-static char unknown_isa[] __cpuinitdata = KERN_ERR \
-	"Unsupported ISA type, c0.config0: %d.";
+	case PRID_IMP_LOONGSON1:
+		decode_configs(c);
 
-static inline unsigned int decode_config0(struct cpuinfo_mips *c)
-{
-	unsigned int config0;
-	int isa;
+		c->cputype = CPU_LOONGSON1;
 
-	config0 = read_c0_config();
-
-	if (((config0 & MIPS_CONF_MT) >> 7) == 1)
-		c->options |= MIPS_CPU_TLB;
-	isa = (config0 & MIPS_CONF_AT) >> 13;
-	switch (isa) {
-	case 0:
-		switch ((config0 & MIPS_CONF_AR) >> 10) {
-		case 0:
-			c->isa_level = MIPS_CPU_ISA_M32R1;
-			break;
-		case 1:
-			c->isa_level = MIPS_CPU_ISA_M32R2;
+		switch (c->processor_id & PRID_REV_MASK) {
+		case PRID_REV_LOONGSON1B:
+			__cpu_name[cpu] = "Loongson 1B";
 			break;
-		default:
-			goto unknown;
 		}
-		break;
-	case 2:
-		switch ((config0 & MIPS_CONF_AR) >> 10) {
-		case 0:
-			c->isa_level = MIPS_CPU_ISA_M64R1;
-			break;
-		case 1:
-			c->isa_level = MIPS_CPU_ISA_M64R2;
-			break;
-		default:
-			goto unknown;
-		}
-		break;
-	default:
-		goto unknown;
-	}
-
-	return config0 & MIPS_CONF_M;
-
-unknown:
-	panic(unknown_isa, config0);
-}
 
-static inline unsigned int decode_config1(struct cpuinfo_mips *c)
-{
-	unsigned int config1;
-
-	config1 = read_c0_config1();
-
-	if (config1 & MIPS_CONF1_MD)
-		c->ases |= MIPS_ASE_MDMX;
-	if (config1 & MIPS_CONF1_WR)
-		c->options |= MIPS_CPU_WATCH;
-	if (config1 & MIPS_CONF1_CA)
-		c->ases |= MIPS_ASE_MIPS16;
-	if (config1 & MIPS_CONF1_EP)
-		c->options |= MIPS_CPU_EJTAG;
-	if (config1 & MIPS_CONF1_FP) {
-		c->options |= MIPS_CPU_FPU;
-		c->options |= MIPS_CPU_32FPR;
+		break;
 	}
-	if (cpu_has_tlb)
-		c->tlbsize = ((config1 & MIPS_CONF1_TLBS) >> 25) + 1;
-
-	return config1 & MIPS_CONF_M;
-}
-
-static inline unsigned int decode_config2(struct cpuinfo_mips *c)
-{
-	unsigned int config2;
-
-	config2 = read_c0_config2();
-
-	if (config2 & MIPS_CONF2_SL)
-		c->scache.flags &= ~MIPS_CACHE_NOT_PRESENT;
-
-	return config2 & MIPS_CONF_M;
-}
-
-static inline unsigned int decode_config3(struct cpuinfo_mips *c)
-{
-	unsigned int config3;
-
-	config3 = read_c0_config3();
-
-	if (config3 & MIPS_CONF3_SM)
-		c->ases |= MIPS_ASE_SMARTMIPS;
-	if (config3 & MIPS_CONF3_DSP)
-		c->ases |= MIPS_ASE_DSP;
-	if (config3 & MIPS_CONF3_VINT)
-		c->options |= MIPS_CPU_VINT;
-	if (config3 & MIPS_CONF3_VEIC)
-		c->options |= MIPS_CPU_VEIC;
-	if (config3 & MIPS_CONF3_MT)
-		c->ases |= MIPS_ASE_MIPSMT;
-	if (config3 & MIPS_CONF3_ULRI)
-		c->options |= MIPS_CPU_ULRI;
-
-	return config3 & MIPS_CONF_M;
-}
-
-static inline unsigned int decode_config4(struct cpuinfo_mips *c)
-{
-	unsigned int config4;
-
-	config4 = read_c0_config4();
-
-	if ((config4 & MIPS_CONF4_MMUEXTDEF) == MIPS_CONF4_MMUEXTDEF_MMUSIZEEXT
-	    && cpu_has_tlb)
-		c->tlbsize += (config4 & MIPS_CONF4_MMUSIZEEXT) * 0x40;
-
-	c->kscratch_mask = (config4 >> 16) & 0xff;
-
-	return config4 & MIPS_CONF_M;
-}
-
-static void __cpuinit decode_configs(struct cpuinfo_mips *c)
-{
-	int ok;
-
-	/* MIPS32 or MIPS64 compliant CPU.  */
-	c->options = MIPS_CPU_4KEX | MIPS_CPU_4K_CACHE | MIPS_CPU_COUNTER |
-		     MIPS_CPU_DIVEC | MIPS_CPU_LLSC | MIPS_CPU_MCHECK;
-
-	c->scache.flags = MIPS_CACHE_NOT_PRESENT;
-
-	ok = decode_config0(c);			/* Read Config registers.  */
-	BUG_ON(!ok);				/* Arch spec violation!  */
-	if (ok)
-		ok = decode_config1(c);
-	if (ok)
-		ok = decode_config2(c);
-	if (ok)
-		ok = decode_config3(c);
-	if (ok)
-		ok = decode_config4(c);
-
-	mips_probe_watch_registers(c);
-
-	if (cpu_has_mips_r2)
-		c->core = read_c0_ebase() & 0x3ff;
 }
 
 static inline void cpu_probe_mips(struct cpuinfo_mips *c, unsigned int cpu)
diff --git a/arch/mips/kernel/kspd.c b/arch/mips/kernel/kspd.c
index 84d0639e4580..b77f56bbb477 100644
--- a/arch/mips/kernel/kspd.c
+++ b/arch/mips/kernel/kspd.c
@@ -323,7 +323,7 @@ static void sp_cleanup(void)
 	fdt = files_fdtable(files);
 	for (;;) {
 		unsigned long set;
-		i = j * __NFDBITS;
+		i = j * BITS_PER_LONG;
 		if (i >= fdt->max_fds)
 			break;
 		set = fdt->open_fds[j++];
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index eb5e394a4650..2f28d3b55687 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -1559,6 +1559,11 @@ init_hw_perf_events(void)
 		mipspmu.general_event_map = &mipsxxcore_event_map;
 		mipspmu.cache_event_map = &mipsxxcore_cache_map;
 		break;
+	case CPU_LOONGSON1:
+		mipspmu.name = "mips/loongson1";
+		mipspmu.general_event_map = &mipsxxcore_event_map;
+		mipspmu.cache_event_map = &mipsxxcore_cache_map;
+		break;
 	case CPU_CAVIUM_OCTEON:
 	case CPU_CAVIUM_OCTEON_PLUS:
 	case CPU_CAVIUM_OCTEON2:
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index f11b2bbb826d..028f6f837ef9 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -35,16 +35,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	return add_memory_region(base, size, BOOT_MEM_RAM);
 }
 
-int __init reserve_mem_mach(unsigned long addr, unsigned long size)
-{
-	return reserve_bootmem(addr, size, BOOTMEM_DEFAULT);
-}
-
-void __init free_mem_mach(unsigned long addr, unsigned long size)
-{
-	return free_bootmem(addr, size);
-}
-
 void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align)
 {
 	return __alloc_bootmem(size, align, __pa(MAX_DMA_ADDRESS));
@@ -77,25 +67,6 @@ void __init early_init_devtree(void *params)
 	of_scan_flat_dt(early_init_dt_scan_memory_arch, NULL);
 }
 
-void __init device_tree_init(void)
-{
-	unsigned long base, size;
-
-	if (!initial_boot_params)
-		return;
-
-	base = virt_to_phys((void *)initial_boot_params);
-	size = be32_to_cpu(initial_boot_params->totalsize);
-
-	/* Before we do anything, lets reserve the dt blob */
-	reserve_mem_mach(base, size);
-
-	unflatten_device_tree();
-
-	/* free the space reserved for the dt blob */
-	free_mem_mach(base, size);
-}
-
 void __init __dt_setup_arch(struct boot_param_header *bph)
 {
 	if (be32_to_cpu(bph->magic) != OF_DT_HEADER) {
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index 1268392f1d27..31637d8c8738 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -102,7 +102,9 @@ asmlinkage __cpuinit void start_secondary(void)
 
 #ifdef CONFIG_MIPS_MT_SMTC
 	/* Only do cpu_probe for first TC of CPU */
-	if ((read_c0_tcbind() & TCBIND_CURTC) == 0)
+	if ((read_c0_tcbind() & TCBIND_CURTC) != 0)
+		__cpu_name[smp_processor_id()] = __cpu_name[0];
+	else
 #endif /* CONFIG_MIPS_MT_SMTC */
 	cpu_probe();
 	cpu_report();
diff --git a/arch/mips/kernel/smtc.c b/arch/mips/kernel/smtc.c
index 15b5f3cfd20c..1d47843d3cc0 100644
--- a/arch/mips/kernel/smtc.c
+++ b/arch/mips/kernel/smtc.c
@@ -86,6 +86,13 @@ struct smtc_ipi_q IPIQ[NR_CPUS];
 static struct smtc_ipi_q freeIPIq;
 
 
+/*
+ * Number of FPU contexts for each VPE
+ */
+
+static int smtc_nconf1[MAX_SMTC_VPES];
+
+
 /* Forward declarations */
 
 void ipi_decode(struct smtc_ipi *);
@@ -174,9 +181,9 @@ static int __init tintq(char *str)
 
 __setup("tintq=", tintq);
 
-static int imstuckcount[2][8];
+static int imstuckcount[MAX_SMTC_VPES][8];
 /* vpemask represents IM/IE bits of per-VPE Status registers, low-to-high */
-static int vpemask[2][8] = {
+static int vpemask[MAX_SMTC_VPES][8] = {
 	{0, 0, 1, 0, 0, 0, 0, 1},
 	{0, 0, 0, 0, 0, 0, 0, 1}
 };
@@ -331,6 +338,22 @@ int __init smtc_build_cpu_map(int start_cpu_slot)
 
 static void smtc_tc_setup(int vpe, int tc, int cpu)
 {
+	static int cp1contexts[MAX_SMTC_VPES];
+
+	/*
+	 * Make a local copy of the available FPU contexts in order
+	 * to keep track of TCs that can have one.
+	 */
+	if (tc == 1)
+	{
+		/*
+		 * FIXME: Multi-core SMTC hasn't been tested and the
+		 *        maximum number of VPEs may change.
+		 */
+		cp1contexts[0] = smtc_nconf1[0] - 1;
+		cp1contexts[1] = smtc_nconf1[1];
+	}
+
 	settc(tc);
 	write_tc_c0_tchalt(TCHALT_H);
 	mips_ihb();
@@ -343,22 +366,29 @@ static void smtc_tc_setup(int vpe, int tc, int cpu)
 	 * an active IPI queue.
 	 */
 	write_tc_c0_tccontext((sizeof(struct smtc_ipi_q) * cpu) << 16);
-	/* Bind tc to vpe */
+
+	/* Bind TC to VPE. */
 	write_tc_c0_tcbind(vpe);
+
 	/* In general, all TCs should have the same cpu_data indications. */
 	memcpy(&cpu_data[cpu], &cpu_data[0], sizeof(struct cpuinfo_mips));
-	/* For 34Kf, start with TC/CPU 0 as sole owner of single FPU context */
-	if (cpu_data[0].cputype == CPU_34K ||
-	    cpu_data[0].cputype == CPU_1004K)
+
+	/* Check to see if there is a FPU context available for this TC. */
+	if (!cp1contexts[vpe])
 		cpu_data[cpu].options &= ~MIPS_CPU_FPU;
+	else
+		cp1contexts[vpe]--;
+
+	/* Store the TC and VPE into the cpu_data structure. */
 	cpu_data[cpu].vpe_id = vpe;
 	cpu_data[cpu].tc_id = tc;
-	/* Multi-core SMTC hasn't been tested, but be prepared */
+
+	/* FIXME: Multi-core SMTC hasn't been tested, but be prepared. */
 	cpu_data[cpu].core = (read_vpe_c0_ebase() >> 1) & 0xff;
 }
 
 /*
- * Tweak to get Count registes in as close a sync as possible.  The
+ * Tweak to get Count registers synced as closely as possible. The
  * value seems good for 34K-class cores.
  */
 
@@ -466,6 +496,24 @@ void smtc_prepare_cpus(int cpus)
 	smtc_configure_tlb();
 
 	for (tc = 0, vpe = 0 ; (vpe < nvpe) && (tc < ntc) ; vpe++) {
+		/* Get number of CP1 contexts for each VPE. */
+		if (tc == 0)
+		{
+			/*
+			 * Do not call settc() for TC0 or the FPU context
+			 * value will be incorrect. Besides, we know that
+			 * we are TC0 anyway.
+			 */
+			smtc_nconf1[0] = ((read_vpe_c0_vpeconf1() &
+				VPECONF1_NCP1) >> VPECONF1_NCP1_SHIFT);
+			if (nvpe == 2)
+			{
+				settc(1);
+				smtc_nconf1[1] = ((read_vpe_c0_vpeconf1() &
+					VPECONF1_NCP1) >> VPECONF1_NCP1_SHIFT);
+				settc(0);
+			}
+		}
 		if (tcpervpe[vpe] == 0)
 			continue;
 		if (vpe != 0)
@@ -479,6 +527,18 @@ void smtc_prepare_cpus(int cpus)
 			 */
 			if (tc != 0) {
 				smtc_tc_setup(vpe, tc, cpu);
+				if (vpe != 0) {
+					/*
+					 * Set MVP bit (possibly again).  Do it
+					 * here to catch CPUs that have no TCs
+					 * bound to the VPE at reset.  In that
+					 * case, a TC must be bound to the VPE
+					 * before we can set VPEControl[MVP]
+					 */
+					write_vpe_c0_vpeconf0(
+						read_vpe_c0_vpeconf0() |
+						VPECONF0_MVP);
+				}
 				cpu++;
 			}
 			printk(" %d", tc);
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index c3c293543703..9be3df1fa8a4 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1253,6 +1253,7 @@ static inline void parity_protection_init(void)
 
 	case CPU_5KC:
 	case CPU_5KE:
+	case CPU_LOONGSON1:
 		write_c0_ecc(0x80000000);
 		back_to_back_c0_hazard();
 		/* Set the PE bit (bit 31) in the c0_errctl register. */
diff --git a/arch/mips/lib/Makefile b/arch/mips/lib/Makefile
index 2a7c74fc15fc..399a50a541d4 100644
--- a/arch/mips/lib/Makefile
+++ b/arch/mips/lib/Makefile
@@ -2,7 +2,7 @@
 # Makefile for MIPS-specific library files..
 #
 
-lib-y	+= csum_partial.o delay.o memcpy.o memcpy-inatomic.o memset.o \
+lib-y	+= csum_partial.o delay.o memcpy.o memset.o \
 	   strlen_user.o strncpy_user.o strnlen_user.o uncached.o
 
 obj-y			+= iomap.o
diff --git a/arch/mips/lib/memcpy-inatomic.S b/arch/mips/lib/memcpy-inatomic.S
deleted file mode 100644
index 68853a038d3f..000000000000
--- a/arch/mips/lib/memcpy-inatomic.S
+++ /dev/null
@@ -1,451 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Unified implementation of memcpy, memmove and the __copy_user backend.
- *
- * Copyright (C) 1998, 99, 2000, 01, 2002 Ralf Baechle (ralf@gnu.org)
- * Copyright (C) 1999, 2000, 01, 2002 Silicon Graphics, Inc.
- * Copyright (C) 2002 Broadcom, Inc.
- *   memcpy/copy_user author: Mark Vandevoorde
- * Copyright (C) 2007  Maciej W. Rozycki
- *
- * Mnemonic names for arguments to memcpy/__copy_user
- */
-
-/*
- * Hack to resolve longstanding prefetch issue
- *
- * Prefetching may be fatal on some systems if we're prefetching beyond the
- * end of memory on some systems.  It's also a seriously bad idea on non
- * dma-coherent systems.
- */
-#ifdef CONFIG_DMA_NONCOHERENT
-#undef CONFIG_CPU_HAS_PREFETCH
-#endif
-#ifdef CONFIG_MIPS_MALTA
-#undef CONFIG_CPU_HAS_PREFETCH
-#endif
-
-#include <asm/asm.h>
-#include <asm/asm-offsets.h>
-#include <asm/regdef.h>
-
-#define dst a0
-#define src a1
-#define len a2
-
-/*
- * Spec
- *
- * memcpy copies len bytes from src to dst and sets v0 to dst.
- * It assumes that
- *   - src and dst don't overlap
- *   - src is readable
- *   - dst is writable
- * memcpy uses the standard calling convention
- *
- * __copy_user copies up to len bytes from src to dst and sets a2 (len) to
- * the number of uncopied bytes due to an exception caused by a read or write.
- * __copy_user assumes that src and dst don't overlap, and that the call is
- * implementing one of the following:
- *   copy_to_user
- *     - src is readable  (no exceptions when reading src)
- *   copy_from_user
- *     - dst is writable  (no exceptions when writing dst)
- * __copy_user uses a non-standard calling convention; see
- * include/asm-mips/uaccess.h
- *
- * When an exception happens on a load, the handler must
- # ensure that all of the destination buffer is overwritten to prevent
- * leaking information to user mode programs.
- */
-
-/*
- * Implementation
- */
-
-/*
- * The exception handler for loads requires that:
- *  1- AT contain the address of the byte just past the end of the source
- *     of the copy,
- *  2- src_entry <= src < AT, and
- *  3- (dst - src) == (dst_entry - src_entry),
- * The _entry suffix denotes values when __copy_user was called.
- *
- * (1) is set up up by uaccess.h and maintained by not writing AT in copy_user
- * (2) is met by incrementing src by the number of bytes copied
- * (3) is met by not doing loads between a pair of increments of dst and src
- *
- * The exception handlers for stores adjust len (if necessary) and return.
- * These handlers do not need to overwrite any data.
- *
- * For __rmemcpy and memmove an exception is always a kernel bug, therefore
- * they're not protected.
- */
-
-#define EXC(inst_reg,addr,handler)		\
-9:	inst_reg, addr;				\
-	.section __ex_table,"a";		\
-	PTR	9b, handler;			\
-	.previous
-
-/*
- * Only on the 64-bit kernel we can made use of 64-bit registers.
- */
-#ifdef CONFIG_64BIT
-#define USE_DOUBLE
-#endif
-
-#ifdef USE_DOUBLE
-
-#define LOAD   ld
-#define LOADL  ldl
-#define LOADR  ldr
-#define STOREL sdl
-#define STORER sdr
-#define STORE  sd
-#define ADD    daddu
-#define SUB    dsubu
-#define SRL    dsrl
-#define SRA    dsra
-#define SLL    dsll
-#define SLLV   dsllv
-#define SRLV   dsrlv
-#define NBYTES 8
-#define LOG_NBYTES 3
-
-/*
- * As we are sharing code base with the mips32 tree (which use the o32 ABI
- * register definitions). We need to redefine the register definitions from
- * the n64 ABI register naming to the o32 ABI register naming.
- */
-#undef t0
-#undef t1
-#undef t2
-#undef t3
-#define t0	$8
-#define t1	$9
-#define t2	$10
-#define t3	$11
-#define t4	$12
-#define t5	$13
-#define t6	$14
-#define t7	$15
-
-#else
-
-#define LOAD   lw
-#define LOADL  lwl
-#define LOADR  lwr
-#define STOREL swl
-#define STORER swr
-#define STORE  sw
-#define ADD    addu
-#define SUB    subu
-#define SRL    srl
-#define SLL    sll
-#define SRA    sra
-#define SLLV   sllv
-#define SRLV   srlv
-#define NBYTES 4
-#define LOG_NBYTES 2
-
-#endif /* USE_DOUBLE */
-
-#ifdef CONFIG_CPU_LITTLE_ENDIAN
-#define LDFIRST LOADR
-#define LDREST  LOADL
-#define STFIRST STORER
-#define STREST  STOREL
-#define SHIFT_DISCARD SLLV
-#else
-#define LDFIRST LOADL
-#define LDREST  LOADR
-#define STFIRST STOREL
-#define STREST  STORER
-#define SHIFT_DISCARD SRLV
-#endif
-
-#define FIRST(unit) ((unit)*NBYTES)
-#define REST(unit)  (FIRST(unit)+NBYTES-1)
-#define UNIT(unit)  FIRST(unit)
-
-#define ADDRMASK (NBYTES-1)
-
-	.text
-	.set	noreorder
-#ifndef CONFIG_CPU_DADDI_WORKAROUNDS
-	.set	noat
-#else
-	.set	at=v1
-#endif
-
-/*
- * A combined memcpy/__copy_user
- * __copy_user sets len to 0 for success; else to an upper bound of
- * the number of uncopied bytes.
- * memcpy sets v0 to dst.
- */
-	.align	5
-LEAF(__copy_user_inatomic)
-	/*
-	 * Note: dst & src may be unaligned, len may be 0
-	 * Temps
-	 */
-#define rem t8
-
-	/*
-	 * The "issue break"s below are very approximate.
-	 * Issue delays for dcache fills will perturb the schedule, as will
-	 * load queue full replay traps, etc.
-	 *
-	 * If len < NBYTES use byte operations.
-	 */
-	PREF(	0, 0(src) )
-	PREF(	1, 0(dst) )
-	sltu	t2, len, NBYTES
-	and	t1, dst, ADDRMASK
-	PREF(	0, 1*32(src) )
-	PREF(	1, 1*32(dst) )
-	bnez	t2, .Lcopy_bytes_checklen
-	 and	t0, src, ADDRMASK
-	PREF(	0, 2*32(src) )
-	PREF(	1, 2*32(dst) )
-	bnez	t1, .Ldst_unaligned
-	 nop
-	bnez	t0, .Lsrc_unaligned_dst_aligned
-	/*
-	 * use delay slot for fall-through
-	 * src and dst are aligned; need to compute rem
-	 */
-.Lboth_aligned:
-	 SRL	t0, len, LOG_NBYTES+3    	# +3 for 8 units/iter
-	beqz	t0, .Lcleanup_both_aligned	# len < 8*NBYTES
-	 and	rem, len, (8*NBYTES-1)	 	# rem = len % (8*NBYTES)
-	PREF(	0, 3*32(src) )
-	PREF(	1, 3*32(dst) )
-	.align	4
-1:
-EXC(	LOAD	t0, UNIT(0)(src),	.Ll_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	.Ll_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	.Ll_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	.Ll_exc_copy)
-	SUB	len, len, 8*NBYTES
-EXC(	LOAD	t4, UNIT(4)(src),	.Ll_exc_copy)
-EXC(	LOAD	t7, UNIT(5)(src),	.Ll_exc_copy)
-	STORE	t0, UNIT(0)(dst)
-	STORE	t1, UNIT(1)(dst)
-EXC(	LOAD	t0, UNIT(6)(src),	.Ll_exc_copy)
-EXC(	LOAD	t1, UNIT(7)(src),	.Ll_exc_copy)
-	ADD	src, src, 8*NBYTES
-	ADD	dst, dst, 8*NBYTES
-	STORE	t2, UNIT(-6)(dst)
-	STORE	t3, UNIT(-5)(dst)
-	STORE	t4, UNIT(-4)(dst)
-	STORE	t7, UNIT(-3)(dst)
-	STORE	t0, UNIT(-2)(dst)
-	STORE	t1, UNIT(-1)(dst)
-	PREF(	0, 8*32(src) )
-	PREF(	1, 8*32(dst) )
-	bne	len, rem, 1b
-	 nop
-
-	/*
-	 * len == rem == the number of bytes left to copy < 8*NBYTES
-	 */
-.Lcleanup_both_aligned:
-	beqz	len, .Ldone
-	 sltu	t0, len, 4*NBYTES
-	bnez	t0, .Lless_than_4units
-	 and	rem, len, (NBYTES-1)	# rem = len % NBYTES
-	/*
-	 * len >= 4*NBYTES
-	 */
-EXC(	LOAD	t0, UNIT(0)(src),	.Ll_exc)
-EXC(	LOAD	t1, UNIT(1)(src),	.Ll_exc_copy)
-EXC(	LOAD	t2, UNIT(2)(src),	.Ll_exc_copy)
-EXC(	LOAD	t3, UNIT(3)(src),	.Ll_exc_copy)
-	SUB	len, len, 4*NBYTES
-	ADD	src, src, 4*NBYTES
-	STORE	t0, UNIT(0)(dst)
-	STORE	t1, UNIT(1)(dst)
-	STORE	t2, UNIT(2)(dst)
-	STORE	t3, UNIT(3)(dst)
-	.set	reorder				/* DADDI_WAR */
-	ADD	dst, dst, 4*NBYTES
-	beqz	len, .Ldone
-	.set	noreorder
-.Lless_than_4units:
-	/*
-	 * rem = len % NBYTES
-	 */
-	beq	rem, len, .Lcopy_bytes
-	 nop
-1:
-EXC(	LOAD	t0, 0(src),		.Ll_exc)
-	ADD	src, src, NBYTES
-	SUB	len, len, NBYTES
-	STORE	t0, 0(dst)
-	.set	reorder				/* DADDI_WAR */
-	ADD	dst, dst, NBYTES
-	bne	rem, len, 1b
-	.set	noreorder
-
-	/*
-	 * src and dst are aligned, need to copy rem bytes (rem < NBYTES)
-	 * A loop would do only a byte at a time with possible branch
-	 * mispredicts.  Can't do an explicit LOAD dst,mask,or,STORE
-	 * because can't assume read-access to dst.  Instead, use
-	 * STREST dst, which doesn't require read access to dst.
-	 *
-	 * This code should perform better than a simple loop on modern,
-	 * wide-issue mips processors because the code has fewer branches and
-	 * more instruction-level parallelism.
-	 */
-#define bits t2
-	beqz	len, .Ldone
-	 ADD	t1, dst, len	# t1 is just past last byte of dst
-	li	bits, 8*NBYTES
-	SLL	rem, len, 3	# rem = number of bits to keep
-EXC(	LOAD	t0, 0(src),		.Ll_exc)
-	SUB	bits, bits, rem	# bits = number of bits to discard
-	SHIFT_DISCARD t0, t0, bits
-	STREST	t0, -1(t1)
-	jr	ra
-	 move	len, zero
-.Ldst_unaligned:
-	/*
-	 * dst is unaligned
-	 * t0 = src & ADDRMASK
-	 * t1 = dst & ADDRMASK; T1 > 0
-	 * len >= NBYTES
-	 *
-	 * Copy enough bytes to align dst
-	 * Set match = (src and dst have same alignment)
-	 */
-#define match rem
-EXC(	LDFIRST	t3, FIRST(0)(src),	.Ll_exc)
-	ADD	t2, zero, NBYTES
-EXC(	LDREST	t3, REST(0)(src),	.Ll_exc_copy)
-	SUB	t2, t2, t1	# t2 = number of bytes copied
-	xor	match, t0, t1
-	STFIRST t3, FIRST(0)(dst)
-	beq	len, t2, .Ldone
-	 SUB	len, len, t2
-	ADD	dst, dst, t2
-	beqz	match, .Lboth_aligned
-	 ADD	src, src, t2
-
-.Lsrc_unaligned_dst_aligned:
-	SRL	t0, len, LOG_NBYTES+2    # +2 for 4 units/iter
-	PREF(	0, 3*32(src) )
-	beqz	t0, .Lcleanup_src_unaligned
-	 and	rem, len, (4*NBYTES-1)   # rem = len % 4*NBYTES
-	PREF(	1, 3*32(dst) )
-1:
-/*
- * Avoid consecutive LD*'s to the same register since some mips
- * implementations can't issue them in the same cycle.
- * It's OK to load FIRST(N+1) before REST(N) because the two addresses
- * are to the same unit (unless src is aligned, but it's not).
- */
-EXC(	LDFIRST	t0, FIRST(0)(src),	.Ll_exc)
-EXC(	LDFIRST	t1, FIRST(1)(src),	.Ll_exc_copy)
-	SUB     len, len, 4*NBYTES
-EXC(	LDREST	t0, REST(0)(src),	.Ll_exc_copy)
-EXC(	LDREST	t1, REST(1)(src),	.Ll_exc_copy)
-EXC(	LDFIRST	t2, FIRST(2)(src),	.Ll_exc_copy)
-EXC(	LDFIRST	t3, FIRST(3)(src),	.Ll_exc_copy)
-EXC(	LDREST	t2, REST(2)(src),	.Ll_exc_copy)
-EXC(	LDREST	t3, REST(3)(src),	.Ll_exc_copy)
-	PREF(	0, 9*32(src) )		# 0 is PREF_LOAD  (not streamed)
-	ADD	src, src, 4*NBYTES
-#ifdef CONFIG_CPU_SB1
-	nop				# improves slotting
-#endif
-	STORE	t0, UNIT(0)(dst)
-	STORE	t1, UNIT(1)(dst)
-	STORE	t2, UNIT(2)(dst)
-	STORE	t3, UNIT(3)(dst)
-	PREF(	1, 9*32(dst) )     	# 1 is PREF_STORE (not streamed)
-	.set	reorder				/* DADDI_WAR */
-	ADD	dst, dst, 4*NBYTES
-	bne	len, rem, 1b
-	.set	noreorder
-
-.Lcleanup_src_unaligned:
-	beqz	len, .Ldone
-	 and	rem, len, NBYTES-1  # rem = len % NBYTES
-	beq	rem, len, .Lcopy_bytes
-	 nop
-1:
-EXC(	LDFIRST t0, FIRST(0)(src),	.Ll_exc)
-EXC(	LDREST	t0, REST(0)(src),	.Ll_exc_copy)
-	ADD	src, src, NBYTES
-	SUB	len, len, NBYTES
-	STORE	t0, 0(dst)
-	.set	reorder				/* DADDI_WAR */
-	ADD	dst, dst, NBYTES
-	bne	len, rem, 1b
-	.set	noreorder
-
-.Lcopy_bytes_checklen:
-	beqz	len, .Ldone
-	 nop
-.Lcopy_bytes:
-	/* 0 < len < NBYTES  */
-#define COPY_BYTE(N)			\
-EXC(	lb	t0, N(src), .Ll_exc);	\
-	SUB	len, len, 1;		\
-	beqz	len, .Ldone;		\
-	 sb	t0, N(dst)
-
-	COPY_BYTE(0)
-	COPY_BYTE(1)
-#ifdef USE_DOUBLE
-	COPY_BYTE(2)
-	COPY_BYTE(3)
-	COPY_BYTE(4)
-	COPY_BYTE(5)
-#endif
-EXC(	lb	t0, NBYTES-2(src), .Ll_exc)
-	SUB	len, len, 1
-	jr	ra
-	 sb	t0, NBYTES-2(dst)
-.Ldone:
-	jr	ra
-	 nop
-	END(__copy_user_inatomic)
-
-.Ll_exc_copy:
-	/*
-	 * Copy bytes from src until faulting load address (or until a
-	 * lb faults)
-	 *
-	 * When reached by a faulting LDFIRST/LDREST, THREAD_BUADDR($28)
-	 * may be more than a byte beyond the last address.
-	 * Hence, the lb below may get an exception.
-	 *
-	 * Assumes src < THREAD_BUADDR($28)
-	 */
-	LOAD	t0, TI_TASK($28)
-	 nop
-	LOAD	t0, THREAD_BUADDR(t0)
-1:
-EXC(	lb	t1, 0(src),	.Ll_exc)
-	ADD	src, src, 1
-	sb	t1, 0(dst)	# can't fault -- we're copy_from_user
-	.set	reorder				/* DADDI_WAR */
-	ADD	dst, dst, 1
-	bne	src, t0, 1b
-	.set	noreorder
-.Ll_exc:
-	LOAD	t0, TI_TASK($28)
-	 nop
-	LOAD	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
-	 nop
-	SUB	len, AT, t0		# len number of uncopied bytes
-	jr	ra
-	 nop
diff --git a/arch/mips/lib/memcpy.S b/arch/mips/lib/memcpy.S
index 56a1f85a1ce8..65192c06781e 100644
--- a/arch/mips/lib/memcpy.S
+++ b/arch/mips/lib/memcpy.S
@@ -183,6 +183,14 @@
 #endif
 
 /*
+ * t6 is used as a flag to note inatomic mode.
+ */
+LEAF(__copy_user_inatomic)
+	b	__copy_user_common
+	 li	t6, 1
+	END(__copy_user_inatomic)
+
+/*
  * A combined memcpy/__copy_user
  * __copy_user sets len to 0 for success; else to an upper bound of
  * the number of uncopied bytes.
@@ -193,6 +201,8 @@ LEAF(memcpy)					/* a0=dst a1=src a2=len */
 	move	v0, dst				/* return value */
 .L__memcpy:
 FEXPORT(__copy_user)
+	li	t6, 0	/* not inatomic */
+__copy_user_common:
 	/*
 	 * Note: dst & src may be unaligned, len may be 0
 	 * Temps
@@ -458,6 +468,7 @@ EXC(	lb	t1, 0(src),	.Ll_exc)
 	LOAD	t0, THREAD_BUADDR(t0)	# t0 is just past last good address
 	 nop
 	SUB	len, AT, t0		# len number of uncopied bytes
+	bnez	t6, .Ldone	/* Skip the zeroing part if inatomic */
 	/*
 	 * Here's where we rely on src and dst being incremented in tandem,
 	 *   See (3) above.
diff --git a/arch/mips/loongson1/Kconfig b/arch/mips/loongson1/Kconfig
new file mode 100644
index 000000000000..237fa214de9f
--- /dev/null
+++ b/arch/mips/loongson1/Kconfig
@@ -0,0 +1,21 @@
+if MACH_LOONGSON1
+
+choice
+	prompt "Machine Type"
+
+config LOONGSON1_LS1B
+	bool "Loongson LS1B board"
+	select CEVT_R4K
+	select CSRC_R4K
+	select SYS_HAS_CPU_LOONGSON1B
+	select DMA_NONCOHERENT
+	select BOOT_ELF32
+	select IRQ_CPU
+	select SYS_SUPPORTS_32BIT_KERNEL
+	select SYS_SUPPORTS_LITTLE_ENDIAN
+	select SYS_SUPPORTS_HIGHMEM
+	select SYS_HAS_EARLY_PRINTK
+
+endchoice
+
+endif # MACH_LOONGSON1
diff --git a/arch/mips/loongson1/Makefile b/arch/mips/loongson1/Makefile
new file mode 100644
index 000000000000..9719c75886f5
--- /dev/null
+++ b/arch/mips/loongson1/Makefile
@@ -0,0 +1,11 @@
+#
+# Common code for all Loongson 1 based systems
+#
+
+obj-$(CONFIG_MACH_LOONGSON1) += common/
+
+#
+# Loongson LS1B board
+#
+
+obj-$(CONFIG_LOONGSON1_LS1B)  += ls1b/
diff --git a/arch/mips/loongson1/Platform b/arch/mips/loongson1/Platform
new file mode 100644
index 000000000000..99bdefe627af
--- /dev/null
+++ b/arch/mips/loongson1/Platform
@@ -0,0 +1,7 @@
+cflags-$(CONFIG_CPU_LOONGSON1)  += \
+	$(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
+	-Wa,-mips32r2 -Wa,--trap
+
+platform-$(CONFIG_MACH_LOONGSON1)	+= loongson1/
+cflags-$(CONFIG_MACH_LOONGSON1)		+= -I$(srctree)/arch/mips/include/asm/mach-loongson1
+load-$(CONFIG_LOONGSON1_LS1B)		+= 0xffffffff80100000
diff --git a/arch/mips/loongson1/common/Makefile b/arch/mips/loongson1/common/Makefile
new file mode 100644
index 000000000000..b2797709ef5b
--- /dev/null
+++ b/arch/mips/loongson1/common/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for common code of loongson1 based machines.
+#
+
+obj-y	+= clock.o irq.o platform.o prom.o reset.o setup.o
diff --git a/arch/mips/loongson1/common/clock.c b/arch/mips/loongson1/common/clock.c
new file mode 100644
index 000000000000..2d98fb030596
--- /dev/null
+++ b/arch/mips/loongson1/common/clock.c
@@ -0,0 +1,165 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <asm/clock.h>
+#include <asm/time.h>
+
+#include <loongson1.h>
+
+static LIST_HEAD(clocks);
+static DEFINE_MUTEX(clocks_mutex);
+
+struct clk *clk_get(struct device *dev, const char *name)
+{
+	struct clk *c;
+	struct clk *ret = NULL;
+
+	mutex_lock(&clocks_mutex);
+	list_for_each_entry(c, &clocks, node) {
+		if (!strcmp(c->name, name)) {
+			ret = c;
+			break;
+		}
+	}
+	mutex_unlock(&clocks_mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL(clk_get);
+
+unsigned long clk_get_rate(struct clk *clk)
+{
+	return clk->rate;
+}
+EXPORT_SYMBOL(clk_get_rate);
+
+static void pll_clk_init(struct clk *clk)
+{
+	u32 pll;
+
+	pll = __raw_readl(LS1X_CLK_PLL_FREQ);
+	clk->rate = (12 + (pll & 0x3f)) * 33 / 2
+			+ ((pll >> 8) & 0x3ff) * 33 / 1024 / 2;
+	clk->rate *= 1000000;
+}
+
+static void cpu_clk_init(struct clk *clk)
+{
+	u32 pll, ctrl;
+
+	pll = clk_get_rate(clk->parent);
+	ctrl = __raw_readl(LS1X_CLK_PLL_DIV) & DIV_CPU;
+	clk->rate = pll / (ctrl >> DIV_CPU_SHIFT);
+}
+
+static void ddr_clk_init(struct clk *clk)
+{
+	u32 pll, ctrl;
+
+	pll = clk_get_rate(clk->parent);
+	ctrl = __raw_readl(LS1X_CLK_PLL_DIV) & DIV_DDR;
+	clk->rate = pll / (ctrl >> DIV_DDR_SHIFT);
+}
+
+static void dc_clk_init(struct clk *clk)
+{
+	u32 pll, ctrl;
+
+	pll = clk_get_rate(clk->parent);
+	ctrl = __raw_readl(LS1X_CLK_PLL_DIV) & DIV_DC;
+	clk->rate = pll / (ctrl >> DIV_DC_SHIFT);
+}
+
+static struct clk_ops pll_clk_ops = {
+	.init	= pll_clk_init,
+};
+
+static struct clk_ops cpu_clk_ops = {
+	.init	= cpu_clk_init,
+};
+
+static struct clk_ops ddr_clk_ops = {
+	.init	= ddr_clk_init,
+};
+
+static struct clk_ops dc_clk_ops = {
+	.init	= dc_clk_init,
+};
+
+static struct clk pll_clk = {
+	.name	= "pll",
+	.ops	= &pll_clk_ops,
+};
+
+static struct clk cpu_clk = {
+	.name	= "cpu",
+	.parent = &pll_clk,
+	.ops	= &cpu_clk_ops,
+};
+
+static struct clk ddr_clk = {
+	.name	= "ddr",
+	.parent = &pll_clk,
+	.ops	= &ddr_clk_ops,
+};
+
+static struct clk dc_clk = {
+	.name	= "dc",
+	.parent = &pll_clk,
+	.ops	= &dc_clk_ops,
+};
+
+int clk_register(struct clk *clk)
+{
+	mutex_lock(&clocks_mutex);
+	list_add(&clk->node, &clocks);
+	if (clk->ops->init)
+		clk->ops->init(clk);
+	mutex_unlock(&clocks_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL(clk_register);
+
+static struct clk *ls1x_clks[] = {
+	&pll_clk,
+	&cpu_clk,
+	&ddr_clk,
+	&dc_clk,
+};
+
+int __init ls1x_clock_init(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ls1x_clks); i++)
+		clk_register(ls1x_clks[i]);
+
+	return 0;
+}
+
+void __init plat_time_init(void)
+{
+	struct clk *clk;
+
+	/* Initialize LS1X clocks */
+	ls1x_clock_init();
+
+	/* setup mips r4k timer */
+	clk = clk_get(NULL, "cpu");
+	if (IS_ERR(clk))
+		panic("unable to get dc clock, err=%ld", PTR_ERR(clk));
+
+	mips_hpt_frequency = clk_get_rate(clk) / 2;
+}
diff --git a/arch/mips/loongson1/common/irq.c b/arch/mips/loongson1/common/irq.c
new file mode 100644
index 000000000000..41bc8ffe7bba
--- /dev/null
+++ b/arch/mips/loongson1/common/irq.c
@@ -0,0 +1,147 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <asm/irq_cpu.h>
+
+#include <loongson1.h>
+#include <irq.h>
+
+#define LS1X_INTC_REG(n, x) \
+		((void __iomem *)KSEG1ADDR(LS1X_INTC_BASE + (n * 0x18) + (x)))
+
+#define LS1X_INTC_INTISR(n)		LS1X_INTC_REG(n, 0x0)
+#define LS1X_INTC_INTIEN(n)		LS1X_INTC_REG(n, 0x4)
+#define LS1X_INTC_INTSET(n)		LS1X_INTC_REG(n, 0x8)
+#define LS1X_INTC_INTCLR(n)		LS1X_INTC_REG(n, 0xc)
+#define LS1X_INTC_INTPOL(n)		LS1X_INTC_REG(n, 0x10)
+#define LS1X_INTC_INTEDGE(n)		LS1X_INTC_REG(n, 0x14)
+
+static void ls1x_irq_ack(struct irq_data *d)
+{
+	unsigned int bit = (d->irq - LS1X_IRQ_BASE) & 0x1f;
+	unsigned int n = (d->irq - LS1X_IRQ_BASE) >> 5;
+
+	__raw_writel(__raw_readl(LS1X_INTC_INTCLR(n))
+			| (1 << bit), LS1X_INTC_INTCLR(n));
+}
+
+static void ls1x_irq_mask(struct irq_data *d)
+{
+	unsigned int bit = (d->irq - LS1X_IRQ_BASE) & 0x1f;
+	unsigned int n = (d->irq - LS1X_IRQ_BASE) >> 5;
+
+	__raw_writel(__raw_readl(LS1X_INTC_INTIEN(n))
+			& ~(1 << bit), LS1X_INTC_INTIEN(n));
+}
+
+static void ls1x_irq_mask_ack(struct irq_data *d)
+{
+	unsigned int bit = (d->irq - LS1X_IRQ_BASE) & 0x1f;
+	unsigned int n = (d->irq - LS1X_IRQ_BASE) >> 5;
+
+	__raw_writel(__raw_readl(LS1X_INTC_INTIEN(n))
+			& ~(1 << bit), LS1X_INTC_INTIEN(n));
+	__raw_writel(__raw_readl(LS1X_INTC_INTCLR(n))
+			| (1 << bit), LS1X_INTC_INTCLR(n));
+}
+
+static void ls1x_irq_unmask(struct irq_data *d)
+{
+	unsigned int bit = (d->irq - LS1X_IRQ_BASE) & 0x1f;
+	unsigned int n = (d->irq - LS1X_IRQ_BASE) >> 5;
+
+	__raw_writel(__raw_readl(LS1X_INTC_INTIEN(n))
+			| (1 << bit), LS1X_INTC_INTIEN(n));
+}
+
+static struct irq_chip ls1x_irq_chip = {
+	.name		= "LS1X-INTC",
+	.irq_ack	= ls1x_irq_ack,
+	.irq_mask	= ls1x_irq_mask,
+	.irq_mask_ack	= ls1x_irq_mask_ack,
+	.irq_unmask	= ls1x_irq_unmask,
+};
+
+static void ls1x_irq_dispatch(int n)
+{
+	u32 int_status, irq;
+
+	/* Get pending sources, masked by current enables */
+	int_status = __raw_readl(LS1X_INTC_INTISR(n)) &
+			__raw_readl(LS1X_INTC_INTIEN(n));
+
+	if (int_status) {
+		irq = LS1X_IRQ(n, __ffs(int_status));
+		do_IRQ(irq);
+	}
+}
+
+asmlinkage void plat_irq_dispatch(void)
+{
+	unsigned int pending;
+
+	pending = read_c0_cause() & read_c0_status() & ST0_IM;
+
+	if (pending & CAUSEF_IP7)
+		do_IRQ(TIMER_IRQ);
+	else if (pending & CAUSEF_IP2)
+		ls1x_irq_dispatch(0); /* INT0 */
+	else if (pending & CAUSEF_IP3)
+		ls1x_irq_dispatch(1); /* INT1 */
+	else if (pending & CAUSEF_IP4)
+		ls1x_irq_dispatch(2); /* INT2 */
+	else if (pending & CAUSEF_IP5)
+		ls1x_irq_dispatch(3); /* INT3 */
+	else if (pending & CAUSEF_IP6)
+		ls1x_irq_dispatch(4); /* INT4 */
+	else
+		spurious_interrupt();
+
+}
+
+struct irqaction cascade_irqaction = {
+	.handler = no_action,
+	.name = "cascade",
+	.flags = IRQF_NO_THREAD,
+};
+
+static void __init ls1x_irq_init(int base)
+{
+	int n;
+
+	/* Disable interrupts and clear pending,
+	 * setup all IRQs as high level triggered
+	 */
+	for (n = 0; n < 4; n++) {
+		__raw_writel(0x0, LS1X_INTC_INTIEN(n));
+		__raw_writel(0xffffffff, LS1X_INTC_INTCLR(n));
+		__raw_writel(0xffffffff, LS1X_INTC_INTPOL(n));
+		/* set DMA0, DMA1 and DMA2 to edge trigger */
+		__raw_writel(n ? 0x0 : 0xe000, LS1X_INTC_INTEDGE(n));
+	}
+
+
+	for (n = base; n < LS1X_IRQS; n++) {
+		irq_set_chip_and_handler(n, &ls1x_irq_chip,
+					 handle_level_irq);
+	}
+
+	setup_irq(INT0_IRQ, &cascade_irqaction);
+	setup_irq(INT1_IRQ, &cascade_irqaction);
+	setup_irq(INT2_IRQ, &cascade_irqaction);
+	setup_irq(INT3_IRQ, &cascade_irqaction);
+}
+
+void __init arch_init_irq(void)
+{
+	mips_cpu_irq_init();
+	ls1x_irq_init(LS1X_IRQ_BASE);
+}
diff --git a/arch/mips/loongson1/common/platform.c b/arch/mips/loongson1/common/platform.c
new file mode 100644
index 000000000000..e92d59c4bd78
--- /dev/null
+++ b/arch/mips/loongson1/common/platform.c
@@ -0,0 +1,124 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/clk.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/phy.h>
+#include <linux/serial_8250.h>
+#include <linux/stmmac.h>
+#include <asm-generic/sizes.h>
+
+#include <loongson1.h>
+
+#define LS1X_UART(_id)						\
+	{							\
+		.mapbase	= LS1X_UART ## _id ## _BASE,	\
+		.irq		= LS1X_UART ## _id ## _IRQ,	\
+		.iotype		= UPIO_MEM,			\
+		.flags		= UPF_IOREMAP | UPF_FIXED_TYPE,	\
+		.type		= PORT_16550A,			\
+	}
+
+static struct plat_serial8250_port ls1x_serial8250_port[] = {
+	LS1X_UART(0),
+	LS1X_UART(1),
+	LS1X_UART(2),
+	LS1X_UART(3),
+	{},
+};
+
+struct platform_device ls1x_uart_device = {
+	.name		= "serial8250",
+	.id		= PLAT8250_DEV_PLATFORM,
+	.dev		= {
+		.platform_data = ls1x_serial8250_port,
+	},
+};
+
+void __init ls1x_serial_setup(void)
+{
+	struct clk *clk;
+	struct plat_serial8250_port *p;
+
+	clk = clk_get(NULL, "dc");
+	if (IS_ERR(clk))
+		panic("unable to get dc clock, err=%ld", PTR_ERR(clk));
+
+	for (p = ls1x_serial8250_port; p->flags != 0; ++p)
+		p->uartclk = clk_get_rate(clk);
+}
+
+/* Synopsys Ethernet GMAC */
+static struct resource ls1x_eth0_resources[] = {
+	[0] = {
+		.start	= LS1X_GMAC0_BASE,
+		.end	= LS1X_GMAC0_BASE + SZ_64K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.name	= "macirq",
+		.start	= LS1X_GMAC0_IRQ,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+static struct stmmac_mdio_bus_data ls1x_mdio_bus_data = {
+	.bus_id		= 0,
+	.phy_mask	= 0,
+};
+
+static struct plat_stmmacenet_data ls1x_eth_data = {
+	.bus_id		= 0,
+	.phy_addr	= -1,
+	.mdio_bus_data	= &ls1x_mdio_bus_data,
+	.has_gmac	= 1,
+	.tx_coe		= 1,
+};
+
+struct platform_device ls1x_eth0_device = {
+	.name		= "stmmaceth",
+	.id		= 0,
+	.num_resources	= ARRAY_SIZE(ls1x_eth0_resources),
+	.resource	= ls1x_eth0_resources,
+	.dev		= {
+		.platform_data = &ls1x_eth_data,
+	},
+};
+
+/* USB EHCI */
+static u64 ls1x_ehci_dmamask = DMA_BIT_MASK(32);
+
+static struct resource ls1x_ehci_resources[] = {
+	[0] = {
+		.start	= LS1X_EHCI_BASE,
+		.end	= LS1X_EHCI_BASE + SZ_32K - 1,
+		.flags	= IORESOURCE_MEM,
+	},
+	[1] = {
+		.start	= LS1X_EHCI_IRQ,
+		.flags	= IORESOURCE_IRQ,
+	},
+};
+
+struct platform_device ls1x_ehci_device = {
+	.name		= "ls1x-ehci",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(ls1x_ehci_resources),
+	.resource	= ls1x_ehci_resources,
+	.dev		= {
+		.dma_mask = &ls1x_ehci_dmamask,
+	},
+};
+
+/* Real Time Clock */
+struct platform_device ls1x_rtc_device = {
+	.name		= "ls1x-rtc",
+	.id		= -1,
+};
diff --git a/arch/mips/loongson1/common/prom.c b/arch/mips/loongson1/common/prom.c
new file mode 100644
index 000000000000..1f8e49f9886d
--- /dev/null
+++ b/arch/mips/loongson1/common/prom.c
@@ -0,0 +1,87 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * Modified from arch/mips/pnx833x/common/prom.c.
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/serial_reg.h>
+#include <asm/bootinfo.h>
+
+#include <loongson1.h>
+#include <prom.h>
+
+int prom_argc;
+char **prom_argv, **prom_envp;
+unsigned long memsize, highmemsize;
+
+char *prom_getenv(char *envname)
+{
+	char **env = prom_envp;
+	int i;
+
+	i = strlen(envname);
+
+	while (*env) {
+		if (strncmp(envname, *env, i) == 0 && *(*env+i) == '=')
+			return *env + i + 1;
+		env++;
+	}
+
+	return 0;
+}
+
+static inline unsigned long env_or_default(char *env, unsigned long dfl)
+{
+	char *str = prom_getenv(env);
+	return str ? simple_strtol(str, 0, 0) : dfl;
+}
+
+void __init prom_init_cmdline(void)
+{
+	char *c = &(arcs_cmdline[0]);
+	int i;
+
+	for (i = 1; i < prom_argc; i++) {
+		strcpy(c, prom_argv[i]);
+		c += strlen(prom_argv[i]);
+		if (i < prom_argc-1)
+			*c++ = ' ';
+	}
+	*c = 0;
+}
+
+void __init prom_init(void)
+{
+	prom_argc = fw_arg0;
+	prom_argv = (char **)fw_arg1;
+	prom_envp = (char **)fw_arg2;
+
+	prom_init_cmdline();
+
+	memsize = env_or_default("memsize", DEFAULT_MEMSIZE);
+	highmemsize = env_or_default("highmemsize", 0x0);
+}
+
+void __init prom_free_prom_memory(void)
+{
+}
+
+#define PORT(offset)	(u8 *)(KSEG1ADDR(LS1X_UART0_BASE + offset))
+
+void __init prom_putchar(char c)
+{
+	int timeout;
+
+	timeout = 1024;
+
+	while (((readb(PORT(UART_LSR)) & UART_LSR_THRE) == 0)
+			&& (timeout-- > 0))
+		;
+
+	writeb(c, PORT(UART_TX));
+}
diff --git a/arch/mips/loongson1/common/reset.c b/arch/mips/loongson1/common/reset.c
new file mode 100644
index 000000000000..fb979a784eca
--- /dev/null
+++ b/arch/mips/loongson1/common/reset.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <linux/io.h>
+#include <linux/pm.h>
+#include <asm/reboot.h>
+
+#include <loongson1.h>
+
+static void ls1x_restart(char *command)
+{
+	__raw_writel(0x1, LS1X_WDT_EN);
+	__raw_writel(0x5000000, LS1X_WDT_TIMER);
+	__raw_writel(0x1, LS1X_WDT_SET);
+}
+
+static void ls1x_halt(void)
+{
+	while (1) {
+		if (cpu_wait)
+			cpu_wait();
+	}
+}
+
+static void ls1x_power_off(void)
+{
+	ls1x_halt();
+}
+
+static int __init ls1x_reboot_setup(void)
+{
+	_machine_restart = ls1x_restart;
+	_machine_halt = ls1x_halt;
+	pm_power_off = ls1x_power_off;
+
+	return 0;
+}
+
+arch_initcall(ls1x_reboot_setup);
diff --git a/arch/mips/loongson1/common/setup.c b/arch/mips/loongson1/common/setup.c
new file mode 100644
index 000000000000..62128cc27e68
--- /dev/null
+++ b/arch/mips/loongson1/common/setup.c
@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <asm/bootinfo.h>
+
+#include <prom.h>
+
+void __init plat_mem_setup(void)
+{
+	add_memory_region(0x0, (memsize << 20), BOOT_MEM_RAM);
+}
+
+const char *get_system_type(void)
+{
+	unsigned int processor_id = (&current_cpu_data)->processor_id;
+
+	switch (processor_id & PRID_REV_MASK) {
+	case PRID_REV_LOONGSON1B:
+		return "LOONGSON LS1B";
+	default:
+		return "LOONGSON (unknown)";
+	}
+}
diff --git a/arch/mips/loongson1/ls1b/Makefile b/arch/mips/loongson1/ls1b/Makefile
new file mode 100644
index 000000000000..891eac482b82
--- /dev/null
+++ b/arch/mips/loongson1/ls1b/Makefile
@@ -0,0 +1,5 @@
+#
+# Makefile for loongson1B based machines.
+#
+
+obj-y += board.o
diff --git a/arch/mips/loongson1/ls1b/board.c b/arch/mips/loongson1/ls1b/board.c
new file mode 100644
index 000000000000..295b1be893e3
--- /dev/null
+++ b/arch/mips/loongson1/ls1b/board.c
@@ -0,0 +1,33 @@
+/*
+ * Copyright (c) 2011 Zhang, Keguang <keguang.zhang@gmail.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#include <platform.h>
+
+#include <linux/serial_8250.h>
+#include <loongson1.h>
+
+static struct platform_device *ls1b_platform_devices[] __initdata = {
+	&ls1x_uart_device,
+	&ls1x_eth0_device,
+	&ls1x_ehci_device,
+	&ls1x_rtc_device,
+};
+
+static int __init ls1b_platform_init(void)
+{
+	int err;
+
+	ls1x_serial_setup();
+
+	err = platform_add_devices(ls1b_platform_devices,
+				   ARRAY_SIZE(ls1b_platform_devices));
+	return err;
+}
+
+arch_initcall(ls1b_platform_init);
diff --git a/arch/mips/mm/uasm.c b/arch/mips/mm/uasm.c
index 5fa185151fc8..64a28e819064 100644
--- a/arch/mips/mm/uasm.c
+++ b/arch/mips/mm/uasm.c
@@ -58,18 +58,16 @@ enum fields {
 
 enum opcode {
 	insn_invalid,
-	insn_addu, insn_addiu, insn_and, insn_andi, insn_beq,
-	insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl,
-	insn_bne, insn_cache, insn_daddu, insn_daddiu, insn_dmfc0,
-	insn_dmtc0, insn_dsll, insn_dsll32, insn_dsra, insn_dsrl,
-	insn_dsrl32, insn_drotr, insn_drotr32, insn_dsubu, insn_eret,
-	insn_j, insn_jal, insn_jr, insn_ld, insn_ll, insn_lld,
-	insn_lui, insn_lw, insn_mfc0, insn_mtc0, insn_or, insn_ori,
-	insn_pref, insn_rfe, insn_sc, insn_scd, insn_sd, insn_sll,
-	insn_sra, insn_srl, insn_rotr, insn_subu, insn_sw, insn_tlbp,
+	insn_addiu, insn_addu, insn_and, insn_andi, insn_bbit0, insn_bbit1,
+	insn_beq, insn_beql, insn_bgez, insn_bgezl, insn_bltz, insn_bltzl,
+	insn_bne, insn_cache, insn_daddiu, insn_daddu, insn_dins, insn_dinsm,
+	insn_dmfc0, insn_dmtc0, insn_drotr, insn_drotr32, insn_dsll,
+	insn_dsll32, insn_dsra, insn_dsrl, insn_dsrl32, insn_dsubu, insn_eret,
+	insn_j, insn_jal, insn_jr, insn_ld, insn_ldx, insn_ll, insn_lld,
+	insn_lui, insn_lw, insn_lwx, insn_mfc0, insn_mtc0, insn_or, insn_ori,
+	insn_pref, insn_rfe, insn_rotr, insn_sc, insn_scd, insn_sd, insn_sll,
+	insn_sra, insn_srl, insn_subu, insn_sw, insn_syscall, insn_tlbp,
 	insn_tlbr, insn_tlbwi, insn_tlbwr, insn_xor, insn_xori,
-	insn_dins, insn_dinsm, insn_syscall, insn_bbit0, insn_bbit1,
-	insn_lwx, insn_ldx
 };
 
 struct insn {
@@ -90,65 +88,65 @@ struct insn {
 static struct insn insn_table[] __uasminitdata = {
 	{ insn_addiu, M(addiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
 	{ insn_addu, M(spec_op, 0, 0, 0, 0, addu_op), RS | RT | RD },
-	{ insn_and, M(spec_op, 0, 0, 0, 0, and_op), RS | RT | RD },
 	{ insn_andi, M(andi_op, 0, 0, 0, 0, 0), RS | RT | UIMM },
-	{ insn_beq, M(beq_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
+	{ insn_and, M(spec_op, 0, 0, 0, 0, and_op), RS | RT | RD },
+	{ insn_bbit0, M(lwc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
+	{ insn_bbit1, M(swc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
 	{ insn_beql, M(beql_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
-	{ insn_bgez, M(bcond_op, 0, bgez_op, 0, 0, 0), RS | BIMM },
+	{ insn_beq, M(beq_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
 	{ insn_bgezl, M(bcond_op, 0, bgezl_op, 0, 0, 0), RS | BIMM },
-	{ insn_bltz, M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM },
+	{ insn_bgez, M(bcond_op, 0, bgez_op, 0, 0, 0), RS | BIMM },
 	{ insn_bltzl, M(bcond_op, 0, bltzl_op, 0, 0, 0), RS | BIMM },
+	{ insn_bltz, M(bcond_op, 0, bltz_op, 0, 0, 0), RS | BIMM },
 	{ insn_bne, M(bne_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
 	{ insn_cache,  M(cache_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_daddiu, M(daddiu_op, 0, 0, 0, 0, 0), RS | RT | SIMM },
 	{ insn_daddu, M(spec_op, 0, 0, 0, 0, daddu_op), RS | RT | RD },
+	{ insn_dinsm, M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE },
+	{ insn_dins, M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE },
 	{ insn_dmfc0, M(cop0_op, dmfc_op, 0, 0, 0, 0), RT | RD | SET},
 	{ insn_dmtc0, M(cop0_op, dmtc_op, 0, 0, 0, 0), RT | RD | SET},
-	{ insn_dsll, M(spec_op, 0, 0, 0, 0, dsll_op), RT | RD | RE },
+	{ insn_drotr32, M(spec_op, 1, 0, 0, 0, dsrl32_op), RT | RD | RE },
+	{ insn_drotr, M(spec_op, 1, 0, 0, 0, dsrl_op), RT | RD | RE },
 	{ insn_dsll32, M(spec_op, 0, 0, 0, 0, dsll32_op), RT | RD | RE },
+	{ insn_dsll, M(spec_op, 0, 0, 0, 0, dsll_op), RT | RD | RE },
 	{ insn_dsra, M(spec_op, 0, 0, 0, 0, dsra_op), RT | RD | RE },
-	{ insn_dsrl, M(spec_op, 0, 0, 0, 0, dsrl_op), RT | RD | RE },
 	{ insn_dsrl32, M(spec_op, 0, 0, 0, 0, dsrl32_op), RT | RD | RE },
-	{ insn_drotr, M(spec_op, 1, 0, 0, 0, dsrl_op), RT | RD | RE },
-	{ insn_drotr32, M(spec_op, 1, 0, 0, 0, dsrl32_op), RT | RD | RE },
+	{ insn_dsrl, M(spec_op, 0, 0, 0, 0, dsrl_op), RT | RD | RE },
 	{ insn_dsubu, M(spec_op, 0, 0, 0, 0, dsubu_op), RS | RT | RD },
 	{ insn_eret,  M(cop0_op, cop_op, 0, 0, 0, eret_op),  0 },
-	{ insn_j,  M(j_op, 0, 0, 0, 0, 0),  JIMM },
 	{ insn_jal,  M(jal_op, 0, 0, 0, 0, 0),  JIMM },
+	{ insn_j,  M(j_op, 0, 0, 0, 0, 0),  JIMM },
 	{ insn_jr,  M(spec_op, 0, 0, 0, 0, jr_op),  RS },
 	{ insn_ld,  M(ld_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
-	{ insn_ll,  M(ll_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+	{ insn_ldx, M(spec3_op, 0, 0, 0, ldx_op, lx_op), RS | RT | RD },
 	{ insn_lld,  M(lld_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+	{ insn_ll,  M(ll_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_lui,  M(lui_op, 0, 0, 0, 0, 0),  RT | SIMM },
 	{ insn_lw,  M(lw_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+	{ insn_lwx, M(spec3_op, 0, 0, 0, lwx_op, lx_op), RS | RT | RD },
 	{ insn_mfc0,  M(cop0_op, mfc_op, 0, 0, 0, 0),  RT | RD | SET},
 	{ insn_mtc0,  M(cop0_op, mtc_op, 0, 0, 0, 0),  RT | RD | SET},
-	{ insn_or,  M(spec_op, 0, 0, 0, 0, or_op),  RS | RT | RD },
 	{ insn_ori,  M(ori_op, 0, 0, 0, 0, 0),  RS | RT | UIMM },
+	{ insn_or,  M(spec_op, 0, 0, 0, 0, or_op),  RS | RT | RD },
 	{ insn_pref,  M(pref_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_rfe,  M(cop0_op, cop_op, 0, 0, 0, rfe_op),  0 },
-	{ insn_sc,  M(sc_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+	{ insn_rotr,  M(spec_op, 1, 0, 0, 0, srl_op),  RT | RD | RE },
 	{ insn_scd,  M(scd_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+	{ insn_sc,  M(sc_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_sd,  M(sd_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
 	{ insn_sll,  M(spec_op, 0, 0, 0, 0, sll_op),  RT | RD | RE },
 	{ insn_sra,  M(spec_op, 0, 0, 0, 0, sra_op),  RT | RD | RE },
 	{ insn_srl,  M(spec_op, 0, 0, 0, 0, srl_op),  RT | RD | RE },
-	{ insn_rotr,  M(spec_op, 1, 0, 0, 0, srl_op),  RT | RD | RE },
 	{ insn_subu,  M(spec_op, 0, 0, 0, 0, subu_op),  RS | RT | RD },
 	{ insn_sw,  M(sw_op, 0, 0, 0, 0, 0),  RS | RT | SIMM },
+	{ insn_syscall, M(spec_op, 0, 0, 0, 0, syscall_op), SCIMM},
 	{ insn_tlbp,  M(cop0_op, cop_op, 0, 0, 0, tlbp_op),  0 },
 	{ insn_tlbr,  M(cop0_op, cop_op, 0, 0, 0, tlbr_op),  0 },
 	{ insn_tlbwi,  M(cop0_op, cop_op, 0, 0, 0, tlbwi_op),  0 },
 	{ insn_tlbwr,  M(cop0_op, cop_op, 0, 0, 0, tlbwr_op),  0 },
-	{ insn_xor,  M(spec_op, 0, 0, 0, 0, xor_op),  RS | RT | RD },
 	{ insn_xori,  M(xori_op, 0, 0, 0, 0, 0),  RS | RT | UIMM },
-	{ insn_dins, M(spec3_op, 0, 0, 0, 0, dins_op), RS | RT | RD | RE },
-	{ insn_dinsm, M(spec3_op, 0, 0, 0, 0, dinsm_op), RS | RT | RD | RE },
-	{ insn_syscall, M(spec_op, 0, 0, 0, 0, syscall_op), SCIMM},
-	{ insn_bbit0, M(lwc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
-	{ insn_bbit1, M(swc2_op, 0, 0, 0, 0, 0), RS | RT | BIMM },
-	{ insn_lwx, M(spec3_op, 0, 0, 0, lwx_op, lx_op), RS | RT | RD },
-	{ insn_ldx, M(spec3_op, 0, 0, 0, ldx_op, lx_op), RS | RT | RD },
+	{ insn_xor,  M(spec_op, 0, 0, 0, 0, xor_op),  RS | RT | RD },
 	{ insn_invalid, 0, 0 }
 };
 
diff --git a/arch/mips/netlogic/common/earlycons.c b/arch/mips/netlogic/common/earlycons.c
index f193f7b3bd81..1902fa22d277 100644
--- a/arch/mips/netlogic/common/earlycons.c
+++ b/arch/mips/netlogic/common/earlycons.c
@@ -54,7 +54,7 @@ void prom_putchar(char c)
 #elif defined(CONFIG_CPU_XLR)
 	uartbase = nlm_mmio_base(NETLOGIC_IO_UART_0_OFFSET);
 #endif
-	while (nlm_read_reg(uartbase, UART_LSR) == 0)
+	while ((nlm_read_reg(uartbase, UART_LSR) & UART_LSR_THRE) == 0)
 		;
 	nlm_write_reg(uartbase, UART_TX, c);
 }
diff --git a/arch/mips/netlogic/common/smpboot.S b/arch/mips/netlogic/common/smpboot.S
index c138b1a6dec3..a13355cc97eb 100644
--- a/arch/mips/netlogic/common/smpboot.S
+++ b/arch/mips/netlogic/common/smpboot.S
@@ -54,28 +54,68 @@
 			XLP_IO_SYS_OFFSET(node) + XLP_IO_PCI_HDRSZ + \
 			SYS_CPU_NONCOHERENT_MODE * 4
 
-.macro __config_lsu
-	li      t0, LSU_DEFEATURE
-	mfcr    t1, t0
+#define	XLP_AX_WORKAROUND	/* enable Ax silicon workarounds */
 
-	lui     t2, 0x4080  /* Enable Unaligned Access, L2HPE */
-	or      t1, t1, t2
-	li	t2, ~0xe    /* S1RCM */
+/* Enable XLP features and workarounds in the LSU */
+.macro xlp_config_lsu
+	li	t0, LSU_DEFEATURE
+	mfcr	t1, t0
+
+	lui	t2, 0x4080	/* Enable Unaligned Access, L2HPE */
+	or	t1, t1, t2
+#ifdef XLP_AX_WORKAROUND
+	li	t2, ~0xe	/* S1RCM */
 	and	t1, t1, t2
-	mtcr    t1, t0
+#endif
+	mtcr	t1, t0
 
-	li      t0, SCHED_DEFEATURE
-	lui     t1, 0x0100  /* Experimental: Disable BRU accepting ALU ops */
-	mtcr    t1, t0
+#ifdef XLP_AX_WORKAROUND
+	li	t0, SCHED_DEFEATURE
+	lui	t1, 0x0100	/* Disable BRU accepting ALU ops */
+	mtcr	t1, t0
+#endif
+.endm
+
+/*
+ * This is the code that will be copied to the reset entry point for
+ * XLR and XLP. The XLP cores start here when they are woken up. This
+ * is also the NMI entry point.
+ */
+.macro	xlp_flush_l1_dcache
+	li	t0, LSU_DEBUG_DATA0
+	li	t1, LSU_DEBUG_ADDR
+	li	t2, 0		/* index */
+	li 	t3, 0x1000	/* loop count */
+1:
+	sll	v0, t2, 5
+	mtcr	zero, t0
+	ori	v1, v0, 0x3	/* way0 | write_enable | write_active */
+	mtcr	v1, t1
+2:
+	mfcr	v1, t1
+	andi	v1, 0x1		/* wait for write_active == 0 */
+	bnez	v1, 2b
+	nop
+	mtcr	zero, t0
+	ori	v1, v0, 0x7	/* way1 | write_enable | write_active */
+	mtcr	v1, t1
+3:
+	mfcr	v1, t1
+	andi	v1, 0x1		/* wait for write_active == 0 */
+	bnez	v1, 3b
+	nop
+	addi	t2, 1
+	bne	t3, t2, 1b
+	nop
 .endm
 
 /*
  * The cores can come start when they are woken up. This is also the NMI
  * entry, so check that first.
  *
- * The data corresponding to reset is stored at RESET_DATA_PHYS location,
- * this will have the thread mask (used when core is woken up) and the
- * current NMI handler in case we reached here for an NMI.
+ * The data corresponding to reset/NMI is stored at RESET_DATA_PHYS
+ * location, this will have the thread mask (used when core is woken up)
+ * and the current NMI handler in case we reached here for an NMI.
  *
  * When a core or thread is newly woken up, it loops in a 'wait'. When
  * the CPU really needs waking up, we send an NMI to it, with the NMI
@@ -89,12 +129,12 @@
 FEXPORT(nlm_reset_entry)
 	dmtc0	k0, $22, 6
 	dmtc0	k1, $22, 7
-	mfc0    k0, CP0_STATUS
-	li      k1, 0x80000
-	and     k1, k0, k1
-	beqz    k1, 1f         /* go to real reset entry */
+	mfc0	k0, CP0_STATUS
+	li	k1, 0x80000
+	and	k1, k0, k1
+	beqz	k1, 1f		/* go to real reset entry */
 	nop
-	li	k1, CKSEG1ADDR(RESET_DATA_PHYS)   /* NMI */
+	li	k1, CKSEG1ADDR(RESET_DATA_PHYS)	/* NMI */
 	ld	k0, BOOT_NMI_HANDLER(k1)
 	jr	k0
 	nop
@@ -114,21 +154,25 @@ FEXPORT(nlm_reset_entry)
 	li	t2, SYS_CPU_COHERENT_BASE(0)
 	add	t2, t2, t3		/* t2 <- SYS offset for node */
 	lw	t1, 0(t2)
-	and     t1, t1, t0
-	sw      t1, 0(t2)
+	and	t1, t1, t0
+	sw	t1, 0(t2)
 
 	/* read back to ensure complete */
-	lw      t1, 0(t2)
+	lw	t1, 0(t2)
 	sync
 
 	/* Configure LSU on Non-0 Cores. */
-	__config_lsu
+	xlp_config_lsu
+	/* FALL THROUGH */
 
 /*
  * Wake up sibling threads from the initial thread in
  * a core.
  */
 EXPORT(nlm_boot_siblings)
+	/* core L1D flush before enable threads */
+	xlp_flush_l1_dcache
+	/* Enable hw threads by writing to MAP_THREADMODE of the core */
 	li	t0, CKSEG1ADDR(RESET_DATA_PHYS)
 	lw	t1, BOOT_THREAD_MODE(t0)	/* t1 <- thread mode */
 	li	t0, ((CPU_BLOCKID_MAP << 8) | MAP_THREADMODE)
@@ -139,31 +183,28 @@ EXPORT(nlm_boot_siblings)
 	/*
 	 * The new hardware thread starts at the next instruction
 	 * For all the cases other than core 0 thread 0, we will
-         * jump to the secondary wait function.
-         */
+	* jump to the secondary wait function.
+	*/
 	mfc0	v0, CP0_EBASE, 1
 	andi	v0, 0x7f		/* v0 <- node/core */
 
-#if 1
-	/* A0 errata - Write MMU_SETUP after changing thread mode register. */
+	/* Init MMU in the first thread after changing THREAD_MODE
+	 * register (Ax Errata?)
+	 */
 	andi	v1, v0, 0x3		/* v1 <- thread id */
 	bnez	v1, 2f
 	nop
 
-        li	t0, MMU_SETUP
-        li	t1, 0
-        mtcr	t1, t0
-	ehb
-#endif
+	li	t0, MMU_SETUP
+	li	t1, 0
+	mtcr	t1, t0
+	_ehb
 
-2:	beqz	v0, 4f
+2:	beqz	v0, 4f		/* boot cpu (cpuid == 0)? */
 	nop
 
 	/* setup status reg */
-	mfc0	t1, CP0_STATUS
-	li	t0, ST0_BEV
-	or	t1, t0
-	xor	t1, t0
+	move	t1, zero
 #ifdef CONFIG_64BIT
 	ori	t1, ST0_KX
 #endif
@@ -183,9 +224,9 @@ EXPORT(nlm_boot_siblings)
 	 * For the boot CPU, we have to restore registers and
 	 * return
 	 */
-4:	dmfc0	t0, $4, 2       /* restore SP from UserLocal */
+4:	dmfc0	t0, $4, 2	/* restore SP from UserLocal */
 	li	t1, 0xfadebeef
-	dmtc0	t1, $4, 2       /* restore SP from UserLocal */
+	dmtc0	t1, $4, 2	/* restore SP from UserLocal */
 	PTR_SUBU sp, t0, PT_SIZE
 	RESTORE_ALL
 	jr   ra
@@ -193,7 +234,7 @@ EXPORT(nlm_boot_siblings)
 EXPORT(nlm_reset_entry_end)
 
 FEXPORT(xlp_boot_core0_siblings)	/* "Master" cpu starts from here */
-	__config_lsu
+	xlp_config_lsu
 	dmtc0   sp, $4, 2		/* SP saved in UserLocal */
 	SAVE_ALL
 	sync
@@ -210,6 +251,12 @@ FEXPORT(xlp_boot_core0_siblings)	/* "Master" cpu starts from here */
 
 	__CPUINIT
 NESTED(nlm_boot_secondary_cpus, 16, sp)
+	/* Initialize CP0 Status */
+	move	t1, zero
+#ifdef CONFIG_64BIT
+	ori	t1, ST0_KX
+#endif
+	mtc0	t1, CP0_STATUS
 	PTR_LA	t1, nlm_next_sp
 	PTR_L	sp, 0(t1)
 	PTR_LA	t1, nlm_next_gp
@@ -234,36 +281,36 @@ END(nlm_boot_secondary_cpus)
  */
 	__CPUINIT
 NESTED(nlm_rmiboot_preboot, 16, sp)
-	mfc0	t0, $15, 1	# read ebase
-	andi	t0, 0x1f	# t0 has the processor_id()
-	andi	t2, t0, 0x3	# thread no
-	sll	t0, 2		# offset in cpu array
+	mfc0	t0, $15, 1	/* read ebase */
+	andi	t0, 0x1f	/* t0 has the processor_id() */
+	andi	t2, t0, 0x3	/* thread num */
+	sll	t0, 2		/* offset in cpu array */
 
-	PTR_LA	t1, nlm_cpu_ready # mark CPU ready
+	PTR_LA	t1, nlm_cpu_ready /* mark CPU ready */
 	PTR_ADDU t1, t0
 	li	t3, 1
 	sw	t3, 0(t1)
 
-	bnez	t2, 1f		# skip thread programming
-	nop			# for non zero hw threads
+	bnez	t2, 1f		/* skip thread programming */
+	nop			/* for thread id != 0 */
 
 	/*
-	 * MMU setup only for first thread in core
+	 * XLR MMU setup only for first thread in core
 	 */
 	li	t0, 0x400
 	mfcr	t1, t0
-	li	t2, 6 		# XLR thread mode mask
+	li	t2, 6 		/* XLR thread mode mask */
 	nor	t3, t2, zero
-	and	t2, t1, t2	# t2 - current thread mode
+	and	t2, t1, t2	/* t2 - current thread mode */
 	li	v0, CKSEG1ADDR(RESET_DATA_PHYS)
-	lw	v1, BOOT_THREAD_MODE(v0) # v1 - new thread mode
+	lw	v1, BOOT_THREAD_MODE(v0) /* v1 - new thread mode */
 	sll	v1, 1
-	beq	v1, t2, 1f 	# same as request value
-	nop			# nothing to do */
+	beq	v1, t2, 1f 	/* same as request value */
+	nop			/* nothing to do */
 
-	and	t2, t1, t3	# mask out old thread mode
-	or	t1, t2, v1	# put in new value
-	mtcr	t1, t0		# update core control
+	and	t2, t1, t3	/* mask out old thread mode */
+	or	t1, t2, v1	/* put in new value */
+	mtcr	t1, t0		/* update core control */
 
 1:	wait
 	j	1b
diff --git a/arch/mips/netlogic/xlp/Makefile b/arch/mips/netlogic/xlp/Makefile
index b93ed83474ec..6b4b972218f0 100644
--- a/arch/mips/netlogic/xlp/Makefile
+++ b/arch/mips/netlogic/xlp/Makefile
@@ -1,2 +1,4 @@
 obj-y				+= setup.o platform.o nlm_hal.o
+obj-$(CONFIG_OF)		+= of.o
 obj-$(CONFIG_SMP)		+= wakeup.o
+obj-$(CONFIG_USB)		+= usb-init.o
diff --git a/arch/mips/netlogic/xlp/nlm_hal.c b/arch/mips/netlogic/xlp/nlm_hal.c
index 9428e7125fed..6c65ac701912 100644
--- a/arch/mips/netlogic/xlp/nlm_hal.c
+++ b/arch/mips/netlogic/xlp/nlm_hal.c
@@ -69,6 +69,32 @@ int nlm_irq_to_irt(int irq)
 		return PIC_IRT_UART_0_INDEX;
 	case PIC_UART_1_IRQ:
 		return PIC_IRT_UART_1_INDEX;
+	case PIC_PCIE_LINK_0_IRQ:
+	       return PIC_IRT_PCIE_LINK_0_INDEX;
+	case PIC_PCIE_LINK_1_IRQ:
+	       return PIC_IRT_PCIE_LINK_1_INDEX;
+	case PIC_PCIE_LINK_2_IRQ:
+	       return PIC_IRT_PCIE_LINK_2_INDEX;
+	case PIC_PCIE_LINK_3_IRQ:
+	       return PIC_IRT_PCIE_LINK_3_INDEX;
+	case PIC_EHCI_0_IRQ:
+	       return PIC_IRT_EHCI_0_INDEX;
+	case PIC_EHCI_1_IRQ:
+	       return PIC_IRT_EHCI_1_INDEX;
+	case PIC_OHCI_0_IRQ:
+	       return PIC_IRT_OHCI_0_INDEX;
+	case PIC_OHCI_1_IRQ:
+	       return PIC_IRT_OHCI_1_INDEX;
+	case PIC_OHCI_2_IRQ:
+	       return PIC_IRT_OHCI_2_INDEX;
+	case PIC_OHCI_3_IRQ:
+	       return PIC_IRT_OHCI_3_INDEX;
+	case PIC_MMC_IRQ:
+	       return PIC_IRT_MMC_INDEX;
+	case PIC_I2C_0_IRQ:
+		return PIC_IRT_I2C_0_INDEX;
+	case PIC_I2C_1_IRQ:
+		return PIC_IRT_I2C_1_INDEX;
 	default:
 		return -1;
 	}
@@ -81,6 +107,32 @@ int nlm_irt_to_irq(int irt)
 		return PIC_UART_0_IRQ;
 	case PIC_IRT_UART_1_INDEX:
 		return PIC_UART_1_IRQ;
+	case PIC_IRT_PCIE_LINK_0_INDEX:
+	       return PIC_PCIE_LINK_0_IRQ;
+	case PIC_IRT_PCIE_LINK_1_INDEX:
+	       return PIC_PCIE_LINK_1_IRQ;
+	case PIC_IRT_PCIE_LINK_2_INDEX:
+	       return PIC_PCIE_LINK_2_IRQ;
+	case PIC_IRT_PCIE_LINK_3_INDEX:
+	       return PIC_PCIE_LINK_3_IRQ;
+	case PIC_IRT_EHCI_0_INDEX:
+		return PIC_EHCI_0_IRQ;
+	case PIC_IRT_EHCI_1_INDEX:
+		return PIC_EHCI_1_IRQ;
+	case PIC_IRT_OHCI_0_INDEX:
+		return PIC_OHCI_0_IRQ;
+	case PIC_IRT_OHCI_1_INDEX:
+		return PIC_OHCI_1_IRQ;
+	case PIC_IRT_OHCI_2_INDEX:
+		return PIC_OHCI_2_IRQ;
+	case PIC_IRT_OHCI_3_INDEX:
+		return PIC_OHCI_3_IRQ;
+	case PIC_IRT_MMC_INDEX:
+	       return PIC_MMC_IRQ;
+	case PIC_IRT_I2C_0_INDEX:
+		return PIC_I2C_0_IRQ;
+	case PIC_IRT_I2C_1_INDEX:
+		return PIC_I2C_1_IRQ;
 	default:
 		return -1;
 	}
diff --git a/arch/mips/netlogic/xlp/of.c b/arch/mips/netlogic/xlp/of.c
new file mode 100644
index 000000000000..8e3921c0c201
--- /dev/null
+++ b/arch/mips/netlogic/xlp/of.c
@@ -0,0 +1,34 @@
+#include <linux/bootmem.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/of_fdt.h>
+#include <asm/byteorder.h>
+
+static int __init reserve_mem_mach(unsigned long addr, unsigned long size)
+{
+	return reserve_bootmem(addr, size, BOOTMEM_DEFAULT);
+}
+
+void __init free_mem_mach(unsigned long addr, unsigned long size)
+{
+	return free_bootmem(addr, size);
+}
+
+void __init device_tree_init(void)
+{
+	unsigned long base, size;
+
+	if (!initial_boot_params)
+		return;
+
+	base = virt_to_phys((void *)initial_boot_params);
+	size = be32_to_cpu(initial_boot_params->totalsize);
+
+	/* Before we do anything, lets reserve the dt blob */
+	reserve_mem_mach(base, size);
+
+	unflatten_device_tree();
+
+	/* free the space reserved for the dt blob */
+	free_mem_mach(base, size);
+}
diff --git a/arch/mips/netlogic/xlp/platform.c b/arch/mips/netlogic/xlp/platform.c
index 1f5e4cba891d..2c510d585447 100644
--- a/arch/mips/netlogic/xlp/platform.c
+++ b/arch/mips/netlogic/xlp/platform.c
@@ -53,7 +53,7 @@
 
 static unsigned int nlm_xlp_uart_in(struct uart_port *p, int offset)
 {
-	 return nlm_read_reg(p->iobase, offset);
+	return nlm_read_reg(p->iobase, offset);
 }
 
 static void nlm_xlp_uart_out(struct uart_port *p, int offset, int value)
diff --git a/arch/mips/netlogic/xlp/setup.c b/arch/mips/netlogic/xlp/setup.c
index b3df7c2aad1e..3dec9f28b65b 100644
--- a/arch/mips/netlogic/xlp/setup.c
+++ b/arch/mips/netlogic/xlp/setup.c
@@ -41,6 +41,8 @@
 #include <asm/bootinfo.h>
 
 #include <linux/of_fdt.h>
+#include <linux/of_platform.h>
+#include <linux/of_device.h>
 
 #include <asm/netlogic/haldefs.h>
 #include <asm/netlogic/common.h>
@@ -109,3 +111,17 @@ void __init prom_init(void)
 	register_smp_ops(&nlm_smp_ops);
 #endif
 }
+
+static struct of_device_id __initdata xlp_ids[] = {
+	{ .compatible = "simple-bus", },
+	{},
+};
+
+int __init xlp8xx_ds_publish_devices(void)
+{
+	if (!of_have_populated_dt())
+		return 0;
+	return of_platform_bus_probe(NULL, xlp_ids, NULL);
+}
+
+device_initcall(xlp8xx_ds_publish_devices);
diff --git a/arch/mips/netlogic/xlp/usb-init.c b/arch/mips/netlogic/xlp/usb-init.c
new file mode 100644
index 000000000000..dbe083a93538
--- /dev/null
+++ b/arch/mips/netlogic/xlp/usb-init.c
@@ -0,0 +1,124 @@
+/*
+ * Copyright (c) 2003-2012 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the Broadcom
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/dma-mapping.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+
+#include <asm/netlogic/haldefs.h>
+#include <asm/netlogic/xlp-hal/iomap.h>
+#include <asm/netlogic/xlp-hal/xlp.h>
+#include <asm/netlogic/xlp-hal/usb.h>
+
+static void nlm_usb_intr_en(int node, int port)
+{
+	uint32_t val;
+	uint64_t port_addr;
+
+	port_addr = nlm_get_usb_regbase(node, port);
+	val = nlm_read_usb_reg(port_addr, USB_INT_EN);
+	val = USB_CTRL_INTERRUPT_EN  | USB_OHCI_INTERRUPT_EN |
+		USB_OHCI_INTERRUPT1_EN | USB_CTRL_INTERRUPT_EN  |
+		USB_OHCI_INTERRUPT_EN | USB_OHCI_INTERRUPT2_EN;
+	nlm_write_usb_reg(port_addr, USB_INT_EN, val);
+}
+
+static void nlm_usb_hw_reset(int node, int port)
+{
+	uint64_t port_addr;
+	uint32_t val;
+
+	/* reset USB phy */
+	port_addr = nlm_get_usb_regbase(node, port);
+	val = nlm_read_usb_reg(port_addr, USB_PHY_0);
+	val &= ~(USB_PHY_RESET | USB_PHY_PORT_RESET_0 | USB_PHY_PORT_RESET_1);
+	nlm_write_usb_reg(port_addr, USB_PHY_0, val);
+
+	mdelay(100);
+	val = nlm_read_usb_reg(port_addr, USB_CTL_0);
+	val &= ~(USB_CONTROLLER_RESET);
+	val |= 0x4;
+	nlm_write_usb_reg(port_addr, USB_CTL_0, val);
+}
+
+static int __init nlm_platform_usb_init(void)
+{
+	pr_info("Initializing USB Interface\n");
+	nlm_usb_hw_reset(0, 0);
+	nlm_usb_hw_reset(0, 3);
+
+	/* Enable PHY interrupts */
+	nlm_usb_intr_en(0, 0);
+	nlm_usb_intr_en(0, 3);
+
+	return 0;
+}
+
+arch_initcall(nlm_platform_usb_init);
+
+static u64 xlp_usb_dmamask = ~(u32)0;
+
+/* Fixup the IRQ for USB devices which is exist on XLP SOC PCIE bus */
+static void nlm_usb_fixup_final(struct pci_dev *dev)
+{
+	dev->dev.dma_mask		= &xlp_usb_dmamask;
+	dev->dev.coherent_dma_mask	= DMA_BIT_MASK(64);
+	switch (dev->devfn) {
+	case 0x10:
+	       dev->irq = PIC_EHCI_0_IRQ;
+	       break;
+	case 0x11:
+	       dev->irq = PIC_OHCI_0_IRQ;
+	       break;
+	case 0x12:
+	       dev->irq = PIC_OHCI_1_IRQ;
+	       break;
+	case 0x13:
+	       dev->irq = PIC_EHCI_1_IRQ;
+	       break;
+	case 0x14:
+	       dev->irq = PIC_OHCI_2_IRQ;
+	       break;
+	case 0x15:
+	       dev->irq = PIC_OHCI_3_IRQ;
+	       break;
+	}
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_NETLOGIC, PCI_DEVICE_ID_NLM_EHCI,
+		nlm_usb_fixup_final);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_NETLOGIC, PCI_DEVICE_ID_NLM_OHCI,
+		nlm_usb_fixup_final);
diff --git a/arch/mips/netlogic/xlr/Makefile b/arch/mips/netlogic/xlr/Makefile
index f01e4d7a0600..c287dea87570 100644
--- a/arch/mips/netlogic/xlr/Makefile
+++ b/arch/mips/netlogic/xlr/Makefile
@@ -1,2 +1,2 @@
-obj-y				+= setup.o platform.o
+obj-y				+= setup.o platform.o platform-flash.o
 obj-$(CONFIG_SMP)		+= wakeup.o
diff --git a/arch/mips/netlogic/xlr/platform-flash.c b/arch/mips/netlogic/xlr/platform-flash.c
new file mode 100644
index 000000000000..340ab1601c42
--- /dev/null
+++ b/arch/mips/netlogic/xlr/platform-flash.c
@@ -0,0 +1,220 @@
+/*
+ * Copyright 2011, Netlogic Microsystems.
+ * Copyright 2004, Matt Porter <mporter@kernel.crashing.org>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2.  This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/ioport.h>
+#include <linux/resource.h>
+#include <linux/spi/flash.h>
+
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/physmap.h>
+#include <linux/mtd/nand.h>
+#include <linux/mtd/partitions.h>
+
+#include <asm/netlogic/haldefs.h>
+#include <asm/netlogic/xlr/iomap.h>
+#include <asm/netlogic/xlr/flash.h>
+#include <asm/netlogic/xlr/bridge.h>
+#include <asm/netlogic/xlr/gpio.h>
+#include <asm/netlogic/xlr/xlr.h>
+
+/*
+ * Default NOR partition layout
+ */
+static struct mtd_partition xlr_nor_parts[] = {
+	{
+		.name = "User FS",
+		.offset = 0x800000,
+		.size   = MTDPART_SIZ_FULL,
+	}
+};
+
+/*
+ * Default NAND partition layout
+ */
+static struct mtd_partition xlr_nand_parts[] = {
+	{
+		.name	= "Root Filesystem",
+		.offset	= 64 * 64 * 2048,
+		.size	= 432 * 64 * 2048,
+	},
+	{
+		.name	= "Home Filesystem",
+		.offset	= MTDPART_OFS_APPEND,
+		.size   = MTDPART_SIZ_FULL,
+	},
+};
+
+/* Use PHYSMAP flash for NOR */
+struct physmap_flash_data xlr_nor_data = {
+	.width		= 2,
+	.parts		= xlr_nor_parts,
+	.nr_parts	= ARRAY_SIZE(xlr_nor_parts),
+};
+
+static struct resource xlr_nor_res[] = {
+	{
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device xlr_nor_dev = {
+	.name	= "physmap-flash",
+	.dev	= {
+		.platform_data	= &xlr_nor_data,
+	},
+	.num_resources  = ARRAY_SIZE(xlr_nor_res),
+	.resource       = xlr_nor_res,
+};
+
+const char *xlr_part_probes[] = { "cmdlinepart", NULL };
+
+/*
+ * Use "gen_nand" driver for NAND flash
+ *
+ * There seems to be no way to store a private pointer containing
+ * platform specific info in gen_nand drivier. We will use a global
+ * struct for now, since we currently have only one NAND chip per board.
+ */
+struct xlr_nand_flash_priv {
+	int cs;
+	uint64_t flash_mmio;
+};
+
+static struct xlr_nand_flash_priv nand_priv;
+
+static void xlr_nand_ctrl(struct mtd_info *mtd, int cmd,
+		unsigned int ctrl)
+{
+	if (ctrl & NAND_CLE)
+		nlm_write_reg(nand_priv.flash_mmio,
+			FLASH_NAND_CLE(nand_priv.cs), cmd);
+	else if (ctrl & NAND_ALE)
+		nlm_write_reg(nand_priv.flash_mmio,
+			FLASH_NAND_ALE(nand_priv.cs), cmd);
+}
+
+struct platform_nand_data xlr_nand_data = {
+	.chip = {
+		.nr_chips	= 1,
+		.nr_partitions	= ARRAY_SIZE(xlr_nand_parts),
+		.chip_delay	= 50,
+		.partitions	= xlr_nand_parts,
+		.part_probe_types = xlr_part_probes,
+	},
+	.ctrl = {
+		.cmd_ctrl	= xlr_nand_ctrl,
+	},
+};
+
+static struct resource xlr_nand_res[] = {
+	{
+		.flags		= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device xlr_nand_dev = {
+	.name		= "gen_nand",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(xlr_nand_res),
+	.resource	= xlr_nand_res,
+	.dev		= {
+		.platform_data	= &xlr_nand_data,
+	}
+};
+
+/*
+ * XLR/XLS supports upto 8 devices on its FLASH interface. The value in
+ * FLASH_BAR (on the MEM/IO bridge) gives the base for mapping all the
+ * flash devices.
+ * Under this, each flash device has an offset and size given by the
+ * CSBASE_ADDR and CSBASE_MASK registers for the device.
+ *
+ * The CSBASE_ registers are expected to be setup by the bootloader.
+ */
+static void setup_flash_resource(uint64_t flash_mmio,
+	uint64_t flash_map_base, int cs, struct resource *res)
+{
+	u32 base, mask;
+
+	base = nlm_read_reg(flash_mmio, FLASH_CSBASE_ADDR(cs));
+	mask = nlm_read_reg(flash_mmio, FLASH_CSADDR_MASK(cs));
+
+	res->start = flash_map_base + ((unsigned long)base << 16);
+	res->end = res->start + (mask + 1) * 64 * 1024;
+}
+
+static int __init xlr_flash_init(void)
+{
+	uint64_t gpio_mmio, flash_mmio, flash_map_base;
+	u32 gpio_resetcfg, flash_bar;
+	int cs, boot_nand, boot_nor;
+
+	/* Flash address bits 39:24 is in bridge flash BAR */
+	flash_bar = nlm_read_reg(nlm_io_base, BRIDGE_FLASH_BAR);
+	flash_map_base = (flash_bar & 0xffff0000) << 8;
+
+	gpio_mmio = nlm_mmio_base(NETLOGIC_IO_GPIO_OFFSET);
+	flash_mmio = nlm_mmio_base(NETLOGIC_IO_FLASH_OFFSET);
+
+	/* Get the chip reset config */
+	gpio_resetcfg = nlm_read_reg(gpio_mmio, GPIO_PWRON_RESET_CFG_REG);
+
+	/* Check for boot flash type */
+	boot_nor = boot_nand = 0;
+	if (nlm_chip_is_xls()) {
+		/* On XLS, check boot from NAND bit (GPIO reset reg bit 16) */
+		if (gpio_resetcfg & (1 << 16))
+			boot_nand = 1;
+
+		/* check boot from PCMCIA, (GPIO reset reg bit 15 */
+		if ((gpio_resetcfg & (1 << 15)) == 0)
+			boot_nor = 1;	/* not set, booted from NOR */
+	} else { /* XLR */
+		/* check boot from PCMCIA (bit 16 in GPIO reset on XLR) */
+		if ((gpio_resetcfg & (1 << 16)) == 0)
+			boot_nor = 1;	/* not set, booted from NOR */
+	}
+
+	/* boot flash at chip select 0 */
+	cs = 0;
+
+	if (boot_nand) {
+		nand_priv.cs = cs;
+		nand_priv.flash_mmio = flash_mmio;
+		setup_flash_resource(flash_mmio, flash_map_base, cs,
+			 xlr_nand_res);
+
+		/* Initialize NAND flash at CS 0 */
+		nlm_write_reg(flash_mmio, FLASH_CSDEV_PARM(cs),
+				FLASH_NAND_CSDEV_PARAM);
+		nlm_write_reg(flash_mmio, FLASH_CSTIME_PARMA(cs),
+				FLASH_NAND_CSTIME_PARAMA);
+		nlm_write_reg(flash_mmio, FLASH_CSTIME_PARMB(cs),
+				FLASH_NAND_CSTIME_PARAMB);
+
+		pr_info("ChipSelect %d: NAND Flash %pR\n", cs, xlr_nand_res);
+		return platform_device_register(&xlr_nand_dev);
+	}
+
+	if (boot_nor) {
+		setup_flash_resource(flash_mmio, flash_map_base, cs,
+			xlr_nor_res);
+		pr_info("ChipSelect %d: NOR Flash %pR\n", cs, xlr_nor_res);
+		return platform_device_register(&xlr_nor_dev);
+	}
+	return 0;
+}
+
+arch_initcall(xlr_flash_init);
diff --git a/arch/mips/netlogic/xlr/platform.c b/arch/mips/netlogic/xlr/platform.c
index eab64b45dffd..71b44d82621d 100644
--- a/arch/mips/netlogic/xlr/platform.c
+++ b/arch/mips/netlogic/xlr/platform.c
@@ -14,6 +14,7 @@
 #include <linux/resource.h>
 #include <linux/serial_8250.h>
 #include <linux/serial_reg.h>
+#include <linux/i2c.h>
 
 #include <asm/netlogic/haldefs.h>
 #include <asm/netlogic/xlr/iomap.h>
@@ -97,3 +98,142 @@ static int __init nlm_uart_init(void)
 }
 
 arch_initcall(nlm_uart_init);
+
+#ifdef CONFIG_USB
+/* Platform USB devices, only on XLS chips */
+static u64 xls_usb_dmamask = ~(u32)0;
+#define USB_PLATFORM_DEV(n, i, irq)					\
+	{								\
+		.name		= n,					\
+		.id		= i,					\
+		.num_resources	= 2,					\
+		.dev		= {					\
+			.dma_mask	= &xls_usb_dmamask,		\
+			.coherent_dma_mask = 0xffffffff,		\
+		},							\
+		.resource	= (struct resource[]) {			\
+			{						\
+				.flags = IORESOURCE_MEM,		\
+			},						\
+			{						\
+				.start	= irq,				\
+				.end	= irq,				\
+				.flags = IORESOURCE_IRQ,		\
+			},						\
+		},							\
+	}
+
+static struct platform_device xls_usb_ehci_device =
+			 USB_PLATFORM_DEV("ehci-xls", 0, PIC_USB_IRQ);
+static struct platform_device xls_usb_ohci_device_0 =
+			 USB_PLATFORM_DEV("ohci-xls-0", 1, PIC_USB_IRQ);
+static struct platform_device xls_usb_ohci_device_1 =
+			 USB_PLATFORM_DEV("ohci-xls-1", 2, PIC_USB_IRQ);
+
+static struct platform_device *xls_platform_devices[] = {
+	&xls_usb_ehci_device,
+	&xls_usb_ohci_device_0,
+	&xls_usb_ohci_device_1,
+};
+
+int xls_platform_usb_init(void)
+{
+	uint64_t usb_mmio, gpio_mmio;
+	unsigned long memres;
+	uint32_t val;
+
+	if (!nlm_chip_is_xls())
+		return 0;
+
+	gpio_mmio = nlm_mmio_base(NETLOGIC_IO_GPIO_OFFSET);
+	usb_mmio  = nlm_mmio_base(NETLOGIC_IO_USB_1_OFFSET);
+
+	/* Clear Rogue Phy INTs */
+	nlm_write_reg(usb_mmio, 49, 0x10000000);
+	/* Enable all interrupts */
+	nlm_write_reg(usb_mmio, 50, 0x1f000000);
+
+	/* Enable ports */
+	nlm_write_reg(usb_mmio,  1, 0x07000500);
+
+	val = nlm_read_reg(gpio_mmio, 21);
+	if (((val >> 22) & 0x01) == 0) {
+		pr_info("Detected USB Device mode - Not supported!\n");
+		nlm_write_reg(usb_mmio,  0, 0x01000000);
+		return 0;
+	}
+
+	pr_info("Detected USB Host mode - Adding XLS USB devices.\n");
+	/* Clear reset, host mode */
+	nlm_write_reg(usb_mmio,  0, 0x02000000);
+
+	/* Memory resource for various XLS usb ports */
+	usb_mmio = nlm_mmio_base(NETLOGIC_IO_USB_0_OFFSET);
+	memres = CPHYSADDR((unsigned long)usb_mmio);
+	xls_usb_ehci_device.resource[0].start = memres;
+	xls_usb_ehci_device.resource[0].end = memres + 0x400 - 1;
+
+	memres += 0x400;
+	xls_usb_ohci_device_0.resource[0].start = memres;
+	xls_usb_ohci_device_0.resource[0].end = memres + 0x400 - 1;
+
+	memres += 0x400;
+	xls_usb_ohci_device_1.resource[0].start = memres;
+	xls_usb_ohci_device_1.resource[0].end = memres + 0x400 - 1;
+
+	return platform_add_devices(xls_platform_devices,
+				ARRAY_SIZE(xls_platform_devices));
+}
+
+arch_initcall(xls_platform_usb_init);
+#endif
+
+#ifdef CONFIG_I2C
+static struct i2c_board_info nlm_i2c_board_info1[] __initdata = {
+	/* All XLR boards have this RTC and Max6657 Temp Chip */
+	[0] = {
+		.type	= "ds1374",
+		.addr	= 0x68
+	},
+	[1] = {
+		.type	= "lm90",
+		.addr	= 0x4c
+	},
+};
+
+static struct resource i2c_resources[] = {
+	[0] = {
+		.start	= 0,	/* filled at init */
+		.end	= 0,
+		.flags	= IORESOURCE_MEM,
+	},
+};
+
+static struct platform_device nlm_xlr_i2c_1 = {
+	.name           = "xlr-i2cbus",
+	.id             = 1,
+	.num_resources	= 1,
+	.resource	= i2c_resources,
+};
+
+static int __init nlm_i2c_init(void)
+{
+	int err = 0;
+	unsigned int offset;
+
+	/* I2C bus 0 does not have any useful devices, configure only bus 1 */
+	offset = NETLOGIC_IO_I2C_1_OFFSET;
+	nlm_xlr_i2c_1.resource[0].start = CPHYSADDR(nlm_mmio_base(offset));
+	nlm_xlr_i2c_1.resource[0].end = nlm_xlr_i2c_1.resource[0].start + 0xfff;
+
+	platform_device_register(&nlm_xlr_i2c_1);
+
+	err = i2c_register_board_info(1, nlm_i2c_board_info1,
+				ARRAY_SIZE(nlm_i2c_board_info1));
+	if (err < 0)
+		pr_err("nlm-i2c: cannot register board I2C devices\n");
+	return err;
+}
+
+arch_initcall(nlm_i2c_init);
+#endif
diff --git a/arch/mips/netlogic/xlr/setup.c b/arch/mips/netlogic/xlr/setup.c
index c9d066dedc4e..81b1d311834f 100644
--- a/arch/mips/netlogic/xlr/setup.c
+++ b/arch/mips/netlogic/xlr/setup.c
@@ -85,7 +85,7 @@ static void nlm_linux_exit(void)
 
 	gpiobase = nlm_mmio_base(NETLOGIC_IO_GPIO_OFFSET);
 	/* trigger a chip reset by writing 1 to GPIO_SWRESET_REG */
-	nlm_write_reg(gpiobase, NETLOGIC_GPIO_SWRESET_REG, 1);
+	nlm_write_reg(gpiobase, GPIO_SWRESET_REG, 1);
 	for ( ; ; )
 		cpu_wait();
 }
diff --git a/arch/mips/oprofile/common.c b/arch/mips/oprofile/common.c
index b6e378211a2c..f80480a5a032 100644
--- a/arch/mips/oprofile/common.c
+++ b/arch/mips/oprofile/common.c
@@ -85,6 +85,7 @@ int __init oprofile_arch_init(struct oprofile_operations *ops)
 	case CPU_34K:
 	case CPU_1004K:
 	case CPU_74K:
+	case CPU_LOONGSON1:
 	case CPU_SB1:
 	case CPU_SB1A:
 	case CPU_R10000:
diff --git a/arch/mips/oprofile/op_model_mipsxx.c b/arch/mips/oprofile/op_model_mipsxx.c
index 4d80a856048d..28ea1a4cc576 100644
--- a/arch/mips/oprofile/op_model_mipsxx.c
+++ b/arch/mips/oprofile/op_model_mipsxx.c
@@ -339,12 +339,6 @@ static int __init mipsxx_init(void)
 		break;
 
 	case CPU_1004K:
-#if 0
-		/* FIXME: report as 34K for now */
-		op_model_mipsxx_ops.cpu_type = "mips/1004K";
-		break;
-#endif
-
 	case CPU_34K:
 		op_model_mipsxx_ops.cpu_type = "mips/34K";
 		break;
@@ -374,6 +368,10 @@ static int __init mipsxx_init(void)
 		op_model_mipsxx_ops.cpu_type = "mips/sb1";
 		break;
 
+	case CPU_LOONGSON1:
+		op_model_mipsxx_ops.cpu_type = "mips/loongson1";
+		break;
+
 	default:
 		printk(KERN_ERR "Profiling unsupported for this CPU\n");
 
diff --git a/arch/mips/pci/Makefile b/arch/mips/pci/Makefile
index c703f43a9914..e13a71cbc3c7 100644
--- a/arch/mips/pci/Makefile
+++ b/arch/mips/pci/Makefile
@@ -59,6 +59,7 @@ obj-$(CONFIG_WR_PPMC)		+= fixup-wrppmc.o
 obj-$(CONFIG_MIKROTIK_RB532)	+= pci-rc32434.o ops-rc32434.o fixup-rc32434.o
 obj-$(CONFIG_CPU_CAVIUM_OCTEON)	+= pci-octeon.o pcie-octeon.o
 obj-$(CONFIG_CPU_XLR)		+= pci-xlr.o
+obj-$(CONFIG_CPU_XLP)		+= pci-xlp.o
 
 ifdef CONFIG_PCI_MSI
 obj-$(CONFIG_CPU_CAVIUM_OCTEON)	+= msi-octeon.o
diff --git a/arch/mips/pci/fixup-cobalt.c b/arch/mips/pci/fixup-cobalt.c
index 9553b14002dd..3e7ce65d776c 100644
--- a/arch/mips/pci/fixup-cobalt.c
+++ b/arch/mips/pci/fixup-cobalt.c
@@ -37,7 +37,7 @@
 #define VIA_COBALT_BRD_ID_REG  0x94
 #define VIA_COBALT_BRD_REG_to_ID(reg)	((unsigned char)(reg) >> 4)
 
-static void qube_raq_galileo_early_fixup(struct pci_dev *dev)
+static void __devinit qube_raq_galileo_early_fixup(struct pci_dev *dev)
 {
 	if (dev->devfn == PCI_DEVFN(0, 0) &&
 		(dev->class >> 8) == PCI_CLASS_MEMORY_OTHER) {
@@ -51,7 +51,7 @@ static void qube_raq_galileo_early_fixup(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_MARVELL, PCI_DEVICE_ID_MARVELL_GT64111,
 	 qube_raq_galileo_early_fixup);
 
-static void qube_raq_via_bmIDE_fixup(struct pci_dev *dev)
+static void __devinit qube_raq_via_bmIDE_fixup(struct pci_dev *dev)
 {
 	unsigned short cfgword;
 	unsigned char lt;
@@ -74,7 +74,7 @@ static void qube_raq_via_bmIDE_fixup(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_82C586_1,
 	 qube_raq_via_bmIDE_fixup);
 
-static void qube_raq_galileo_fixup(struct pci_dev *dev)
+static void __devinit qube_raq_galileo_fixup(struct pci_dev *dev)
 {
 	if (dev->devfn != PCI_DEVFN(0, 0))
 		return;
@@ -129,7 +129,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL, PCI_DEVICE_ID_MARVELL_GT64111,
 
 int cobalt_board_id;
 
-static void qube_raq_via_board_id_fixup(struct pci_dev *dev)
+static void __devinit qube_raq_via_board_id_fixup(struct pci_dev *dev)
 {
 	u8 id;
 	int retval;
diff --git a/arch/mips/pci/fixup-malta.c b/arch/mips/pci/fixup-malta.c
index 70073c98ed32..819622f93e9c 100644
--- a/arch/mips/pci/fixup-malta.c
+++ b/arch/mips/pci/fixup-malta.c
@@ -101,3 +101,17 @@ static void __devinit malta_piix_func1_fixup(struct pci_dev *pdev)
 
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB,
 	 malta_piix_func1_fixup);
+
+/* Enable PCI 2.1 compatibility in PIIX4 */
+static void __devinit quirk_dlcsetup(struct pci_dev *dev)
+{
+	u8 odlc, ndlc;
+
+	(void) pci_read_config_byte(dev, 0x82, &odlc);
+	/* Enable passive releases and delayed transaction */
+	ndlc = odlc | 7;
+	(void) pci_write_config_byte(dev, 0x82, ndlc);
+}
+
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82371AB_0,
+	quirk_dlcsetup);
diff --git a/arch/mips/pci/fixup-rc32434.c b/arch/mips/pci/fixup-rc32434.c
index 3d86823d03a0..76bb1be99d43 100644
--- a/arch/mips/pci/fixup-rc32434.c
+++ b/arch/mips/pci/fixup-rc32434.c
@@ -47,7 +47,7 @@ int __devinit pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 	return irq + GROUP4_IRQ_BASE + 4;
 }
 
-static void rc32434_pci_early_fixup(struct pci_dev *dev)
+static void __devinit rc32434_pci_early_fixup(struct pci_dev *dev)
 {
 	if (PCI_SLOT(dev->devfn) == 6 && dev->bus->number == 0) {
 		/* disable prefetched memory range */
diff --git a/arch/mips/pci/ops-bcm63xx.c b/arch/mips/pci/ops-bcm63xx.c
index 822ae179bc56..65c7bd100486 100644
--- a/arch/mips/pci/ops-bcm63xx.c
+++ b/arch/mips/pci/ops-bcm63xx.c
@@ -411,7 +411,7 @@ struct pci_ops bcm63xx_cb_ops = {
  * only one IO window, so it  cannot be shared by PCI and cardbus, use
  * fixup to choose and detect unhandled configuration
  */
-static void bcm63xx_fixup(struct pci_dev *dev)
+static void __devinit bcm63xx_fixup(struct pci_dev *dev)
 {
 	static int io_window = -1;
 	int i, found, new_io_window;
@@ -465,3 +465,64 @@ static void bcm63xx_fixup(struct pci_dev *dev)
 
 DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, bcm63xx_fixup);
 #endif
+
+static int bcm63xx_pcie_can_access(struct pci_bus *bus, int devfn)
+{
+	switch (bus->number) {
+	case PCIE_BUS_BRIDGE:
+		return (PCI_SLOT(devfn) == 0);
+	case PCIE_BUS_DEVICE:
+		if (PCI_SLOT(devfn) == 0)
+			return bcm_pcie_readl(PCIE_DLSTATUS_REG)
+					& DLSTATUS_PHYLINKUP;
+	default:
+		return false;
+	}
+}
+
+static int bcm63xx_pcie_read(struct pci_bus *bus, unsigned int devfn,
+			     int where, int size, u32 *val)
+{
+	u32 data;
+	u32 reg = where & ~3;
+
+	if (!bcm63xx_pcie_can_access(bus, devfn))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (bus->number == PCIE_BUS_DEVICE)
+		reg += PCIE_DEVICE_OFFSET;
+
+	data = bcm_pcie_readl(reg);
+
+	*val = postprocess_read(data, where, size);
+
+	return PCIBIOS_SUCCESSFUL;
+
+}
+
+static int bcm63xx_pcie_write(struct pci_bus *bus, unsigned int devfn,
+			      int where, int size, u32 val)
+{
+	u32 data;
+	u32 reg = where & ~3;
+
+	if (!bcm63xx_pcie_can_access(bus, devfn))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (bus->number == PCIE_BUS_DEVICE)
+		reg += PCIE_DEVICE_OFFSET;
+
+
+	data = bcm_pcie_readl(reg);
+
+	data = preprocess_write(data, val, where, size);
+	bcm_pcie_writel(data, reg);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+
+struct pci_ops bcm63xx_pcie_ops = {
+	.read   = bcm63xx_pcie_read,
+	.write  = bcm63xx_pcie_write
+};
diff --git a/arch/mips/pci/pci-bcm63xx.c b/arch/mips/pci/pci-bcm63xx.c
index 39eb7c417e2f..8a48139d219c 100644
--- a/arch/mips/pci/pci-bcm63xx.c
+++ b/arch/mips/pci/pci-bcm63xx.c
@@ -10,6 +10,7 @@
 #include <linux/pci.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
+#include <linux/delay.h>
 #include <asm/bootinfo.h>
 
 #include "pci-bcm63xx.h"
@@ -71,6 +72,26 @@ struct pci_controller bcm63xx_cb_controller = {
 };
 #endif
 
+static struct resource bcm_pcie_mem_resource = {
+	.name   = "bcm63xx PCIe memory space",
+	.start  = BCM_PCIE_MEM_BASE_PA,
+	.end    = BCM_PCIE_MEM_END_PA,
+	.flags  = IORESOURCE_MEM,
+};
+
+static struct resource bcm_pcie_io_resource = {
+	.name   = "bcm63xx PCIe IO space",
+	.start  = 0,
+	.end    = 0,
+	.flags  = 0,
+};
+
+struct pci_controller bcm63xx_pcie_controller = {
+	.pci_ops	= &bcm63xx_pcie_ops,
+	.io_resource	= &bcm_pcie_io_resource,
+	.mem_resource	= &bcm_pcie_mem_resource,
+};
+
 static u32 bcm63xx_int_cfg_readl(u32 reg)
 {
 	u32 tmp;
@@ -94,17 +115,99 @@ static void bcm63xx_int_cfg_writel(u32 val, u32 reg)
 
 void __iomem *pci_iospace_start;
 
-static int __init bcm63xx_pci_init(void)
+static void __init bcm63xx_reset_pcie(void)
 {
-	unsigned int mem_size;
 	u32 val;
 
-	if (!BCMCPU_IS_6348() && !BCMCPU_IS_6358() && !BCMCPU_IS_6368())
-		return -ENODEV;
+	/* enable clock */
+	val = bcm_perf_readl(PERF_CKCTL_REG);
+	val |= CKCTL_6328_PCIE_EN;
+	bcm_perf_writel(val, PERF_CKCTL_REG);
+
+	/* enable SERDES */
+	val = bcm_misc_readl(MISC_SERDES_CTRL_REG);
+	val |= SERDES_PCIE_EN | SERDES_PCIE_EXD_EN;
+	bcm_misc_writel(val, MISC_SERDES_CTRL_REG);
+
+	/* reset the PCIe core */
+	val = bcm_perf_readl(PERF_SOFTRESET_6328_REG);
+
+	val &= ~SOFTRESET_6328_PCIE_MASK;
+	val &= ~SOFTRESET_6328_PCIE_CORE_MASK;
+	val &= ~SOFTRESET_6328_PCIE_HARD_MASK;
+	val &= ~SOFTRESET_6328_PCIE_EXT_MASK;
+	bcm_perf_writel(val, PERF_SOFTRESET_6328_REG);
+	mdelay(10);
+
+	val |= SOFTRESET_6328_PCIE_MASK;
+	val |= SOFTRESET_6328_PCIE_CORE_MASK;
+	val |= SOFTRESET_6328_PCIE_HARD_MASK;
+	bcm_perf_writel(val, PERF_SOFTRESET_6328_REG);
+	mdelay(10);
+
+	val |= SOFTRESET_6328_PCIE_EXT_MASK;
+	bcm_perf_writel(val, PERF_SOFTRESET_6328_REG);
+	mdelay(200);
+}
 
-	if (!bcm63xx_pci_enabled)
-		return -ENODEV;
+static int __init bcm63xx_register_pcie(void)
+{
+	u32 val;
 
+	bcm63xx_reset_pcie();
+
+	/* configure the PCIe bridge */
+	val = bcm_pcie_readl(PCIE_BRIDGE_OPT1_REG);
+	val |= OPT1_RD_BE_OPT_EN;
+	val |= OPT1_RD_REPLY_BE_FIX_EN;
+	val |= OPT1_PCIE_BRIDGE_HOLE_DET_EN;
+	val |= OPT1_L1_INT_STATUS_MASK_POL;
+	bcm_pcie_writel(val, PCIE_BRIDGE_OPT1_REG);
+
+	/* setup the interrupts */
+	val = bcm_pcie_readl(PCIE_BRIDGE_RC_INT_MASK_REG);
+	val |= PCIE_RC_INT_A | PCIE_RC_INT_B | PCIE_RC_INT_C | PCIE_RC_INT_D;
+	bcm_pcie_writel(val, PCIE_BRIDGE_RC_INT_MASK_REG);
+
+	val = bcm_pcie_readl(PCIE_BRIDGE_OPT2_REG);
+	/* enable credit checking and error checking */
+	val |= OPT2_TX_CREDIT_CHK_EN;
+	val |= OPT2_UBUS_UR_DECODE_DIS;
+
+	/* set device bus/func for the pcie device */
+	val |= (PCIE_BUS_DEVICE << OPT2_CFG_TYPE1_BUS_NO_SHIFT);
+	val |= OPT2_CFG_TYPE1_BD_SEL;
+	bcm_pcie_writel(val, PCIE_BRIDGE_OPT2_REG);
+
+	/* setup class code as bridge */
+	val = bcm_pcie_readl(PCIE_IDVAL3_REG);
+	val &= ~IDVAL3_CLASS_CODE_MASK;
+	val |= (PCI_CLASS_BRIDGE_PCI << IDVAL3_SUBCLASS_SHIFT);
+	bcm_pcie_writel(val, PCIE_IDVAL3_REG);
+
+	/* disable bar1 size */
+	val = bcm_pcie_readl(PCIE_CONFIG2_REG);
+	val &= ~CONFIG2_BAR1_SIZE_MASK;
+	bcm_pcie_writel(val, PCIE_CONFIG2_REG);
+
+	/* set bar0 to little endian */
+	val = (BCM_PCIE_MEM_BASE_PA >> 20) << BASEMASK_BASE_SHIFT;
+	val |= (BCM_PCIE_MEM_BASE_PA >> 20) << BASEMASK_MASK_SHIFT;
+	val |= BASEMASK_REMAP_EN;
+	bcm_pcie_writel(val, PCIE_BRIDGE_BAR0_BASEMASK_REG);
+
+	val = (BCM_PCIE_MEM_BASE_PA >> 20) << REBASE_ADDR_BASE_SHIFT;
+	bcm_pcie_writel(val, PCIE_BRIDGE_BAR0_REBASE_ADDR_REG);
+
+	register_pci_controller(&bcm63xx_pcie_controller);
+
+	return 0;
+}
+
+static int __init bcm63xx_register_pci(void)
+{
+	unsigned int mem_size;
+	u32 val;
 	/*
 	 * configuration  access are  done through  IO space,  remap 4
 	 * first bytes to access it from CPU.
@@ -221,4 +324,22 @@ static int __init bcm63xx_pci_init(void)
 	return 0;
 }
 
+
+static int __init bcm63xx_pci_init(void)
+{
+	if (!bcm63xx_pci_enabled)
+		return -ENODEV;
+
+	switch (bcm63xx_get_cpu_id()) {
+	case BCM6328_CPU_ID:
+		return bcm63xx_register_pcie();
+	case BCM6348_CPU_ID:
+	case BCM6358_CPU_ID:
+	case BCM6368_CPU_ID:
+		return bcm63xx_register_pci();
+	default:
+		return -ENODEV;
+	}
+}
+
 arch_initcall(bcm63xx_pci_init);
diff --git a/arch/mips/pci/pci-bcm63xx.h b/arch/mips/pci/pci-bcm63xx.h
index a6e594ef3d6a..e6736d558ac7 100644
--- a/arch/mips/pci/pci-bcm63xx.h
+++ b/arch/mips/pci/pci-bcm63xx.h
@@ -13,11 +13,16 @@
  */
 #define CARDBUS_PCI_IDSEL	0x8
 
+
+#define PCIE_BUS_BRIDGE		0
+#define PCIE_BUS_DEVICE		1
+
 /*
  * defined in ops-bcm63xx.c
  */
 extern struct pci_ops bcm63xx_pci_ops;
 extern struct pci_ops bcm63xx_cb_ops;
+extern struct pci_ops bcm63xx_pcie_ops;
 
 /*
  * defined in pci-bcm63xx.c
diff --git a/arch/mips/pci/pci-xlp.c b/arch/mips/pci/pci-xlp.c
new file mode 100644
index 000000000000..140557a20488
--- /dev/null
+++ b/arch/mips/pci/pci-xlp.c
@@ -0,0 +1,248 @@
+/*
+ * Copyright (c) 2003-2012 Broadcom Corporation
+ * All Rights Reserved
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the Broadcom
+ * license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY BROADCOM ``AS IS'' AND ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+ * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL BROADCOM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE
+ * OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN
+ * IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/msi.h>
+#include <linux/mm.h>
+#include <linux/irq.h>
+#include <linux/irqdesc.h>
+#include <linux/console.h>
+
+#include <asm/io.h>
+
+#include <asm/netlogic/interrupt.h>
+#include <asm/netlogic/haldefs.h>
+
+#include <asm/netlogic/xlp-hal/iomap.h>
+#include <asm/netlogic/xlp-hal/pic.h>
+#include <asm/netlogic/xlp-hal/xlp.h>
+#include <asm/netlogic/xlp-hal/pcibus.h>
+#include <asm/netlogic/xlp-hal/bridge.h>
+
+static void *pci_config_base;
+
+#define	pci_cfg_addr(bus, devfn, off) (((bus) << 20) | ((devfn) << 12) | (off))
+
+/* PCI ops */
+static inline u32 pci_cfg_read_32bit(struct pci_bus *bus, unsigned int devfn,
+	int where)
+{
+	u32 data;
+	u32 *cfgaddr;
+
+	cfgaddr = (u32 *)(pci_config_base +
+			pci_cfg_addr(bus->number, devfn, where & ~3));
+	data = *cfgaddr;
+	return data;
+}
+
+static inline void pci_cfg_write_32bit(struct pci_bus *bus, unsigned int devfn,
+	int where, u32 data)
+{
+	u32 *cfgaddr;
+
+	cfgaddr = (u32 *)(pci_config_base +
+			pci_cfg_addr(bus->number, devfn, where & ~3));
+	*cfgaddr = data;
+}
+
+static int nlm_pcibios_read(struct pci_bus *bus, unsigned int devfn,
+	int where, int size, u32 *val)
+{
+	u32 data;
+
+	if ((size == 2) && (where & 1))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	else if ((size == 4) && (where & 3))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	data = pci_cfg_read_32bit(bus, devfn, where);
+
+	if (size == 1)
+		*val = (data >> ((where & 3) << 3)) & 0xff;
+	else if (size == 2)
+		*val = (data >> ((where & 3) << 3)) & 0xffff;
+	else
+		*val = data;
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+
+static int nlm_pcibios_write(struct pci_bus *bus, unsigned int devfn,
+		int where, int size, u32 val)
+{
+	u32 data;
+
+	if ((size == 2) && (where & 1))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	else if ((size == 4) && (where & 3))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	data = pci_cfg_read_32bit(bus, devfn, where);
+
+	if (size == 1)
+		data = (data & ~(0xff << ((where & 3) << 3))) |
+			(val << ((where & 3) << 3));
+	else if (size == 2)
+		data = (data & ~(0xffff << ((where & 3) << 3))) |
+			(val << ((where & 3) << 3));
+	else
+		data = val;
+
+	pci_cfg_write_32bit(bus, devfn, where, data);
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+struct pci_ops nlm_pci_ops = {
+	.read  = nlm_pcibios_read,
+	.write = nlm_pcibios_write
+};
+
+static struct resource nlm_pci_mem_resource = {
+	.name           = "XLP PCI MEM",
+	.start          = 0xd0000000UL,	/* 256MB PCI mem @ 0xd000_0000 */
+	.end            = 0xdfffffffUL,
+	.flags          = IORESOURCE_MEM,
+};
+
+static struct resource nlm_pci_io_resource = {
+	.name           = "XLP IO MEM",
+	.start          = 0x14000000UL,	/* 64MB PCI IO @ 0x1000_0000 */
+	.end            = 0x17ffffffUL,
+	.flags          = IORESOURCE_IO,
+};
+
+struct pci_controller nlm_pci_controller = {
+	.index          = 0,
+	.pci_ops        = &nlm_pci_ops,
+	.mem_resource   = &nlm_pci_mem_resource,
+	.mem_offset     = 0x00000000UL,
+	.io_resource    = &nlm_pci_io_resource,
+	.io_offset      = 0x00000000UL,
+};
+
+static int get_irq_vector(const struct pci_dev *dev)
+{
+	/*
+	 * For XLP PCIe, there is an IRQ per Link, find out which
+	 * link the device is on to assign interrupts
+	*/
+	if (dev->bus->self == NULL)
+		return 0;
+
+	switch	(dev->bus->self->devfn) {
+	case 0x8:
+		return PIC_PCIE_LINK_0_IRQ;
+	case 0x9:
+		return PIC_PCIE_LINK_1_IRQ;
+	case 0xa:
+		return PIC_PCIE_LINK_2_IRQ;
+	case 0xb:
+		return PIC_PCIE_LINK_3_IRQ;
+	}
+	WARN(1, "Unexpected devfn %d\n", dev->bus->self->devfn);
+	return 0;
+}
+
+int __init pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+	return get_irq_vector(dev);
+}
+
+/* Do platform specific device initialization at pci_enable_device() time */
+int pcibios_plat_dev_init(struct pci_dev *dev)
+{
+	return 0;
+}
+
+static int xlp_enable_pci_bswap(void)
+{
+	uint64_t pciebase, sysbase;
+	int node, i;
+	u32 reg;
+
+	/* Chip-0 so node set to 0 */
+	node = 0;
+	sysbase = nlm_get_bridge_regbase(node);
+	/*
+	 *  Enable byte swap in hardware. Program each link's PCIe SWAP regions
+	 * from the link's address ranges.
+	 */
+	for (i = 0; i < 4; i++) {
+		pciebase = nlm_pcicfg_base(XLP_IO_PCIE_OFFSET(node, i));
+		if (nlm_read_pci_reg(pciebase, 0) == 0xffffffff)
+			continue;
+
+		reg = nlm_read_bridge_reg(sysbase, BRIDGE_PCIEMEM_BASE0 + i);
+		nlm_write_pci_reg(pciebase, PCIE_BYTE_SWAP_MEM_BASE, reg);
+
+		reg = nlm_read_bridge_reg(sysbase, BRIDGE_PCIEMEM_LIMIT0 + i);
+		nlm_write_pci_reg(pciebase, PCIE_BYTE_SWAP_MEM_LIM,
+			reg | 0xfff);
+
+		reg = nlm_read_bridge_reg(sysbase, BRIDGE_PCIEIO_BASE0 + i);
+		nlm_write_pci_reg(pciebase, PCIE_BYTE_SWAP_IO_BASE, reg);
+
+		reg = nlm_read_bridge_reg(sysbase, BRIDGE_PCIEIO_LIMIT0 + i);
+		nlm_write_pci_reg(pciebase, PCIE_BYTE_SWAP_IO_LIM, reg | 0xfff);
+	}
+	return 0;
+}
+
+static int __init pcibios_init(void)
+{
+	/* Firmware assigns PCI resources */
+	pci_set_flags(PCI_PROBE_ONLY);
+	pci_config_base = ioremap(XLP_DEFAULT_PCI_ECFG_BASE, 64 << 20);
+
+	/* Extend IO port for memory mapped io */
+	ioport_resource.start =  0;
+	ioport_resource.end   = ~0;
+
+	xlp_enable_pci_bswap();
+	set_io_port_base(CKSEG1);
+	nlm_pci_controller.io_map_base = CKSEG1;
+
+	register_pci_controller(&nlm_pci_controller);
+	pr_info("XLP PCIe Controller %pR%pR.\n", &nlm_pci_io_resource,
+		&nlm_pci_mem_resource);
+
+	return 0;
+}
+arch_initcall(pcibios_init);
diff --git a/arch/mips/pci/pci-xlr.c b/arch/mips/pci/pci-xlr.c
index 172af1cd5867..18af021d289a 100644
--- a/arch/mips/pci/pci-xlr.c
+++ b/arch/mips/pci/pci-xlr.c
@@ -375,7 +375,3 @@ static int __init pcibios_init(void)
 }
 
 arch_initcall(pcibios_init);
-
-struct pci_fixup pcibios_fixups[] = {
-	{0}
-};
diff --git a/arch/mips/pnx833x/stb22x/board.c b/arch/mips/pnx833x/stb22x/board.c
index 644eb7c3210f..4b328ac43050 100644
--- a/arch/mips/pnx833x/stb22x/board.c
+++ b/arch/mips/pnx833x/stb22x/board.c
@@ -91,7 +91,7 @@ void __init pnx833x_board_setup(void)
 	pnx833x_gpio_select_function_alt(32);
 	pnx833x_gpio_select_function_alt(33);
 
-#if defined(CONFIG_MTD_NAND_PLATFORM) || defined(CONFIG_MTD_NAND_PLATFORM_MODULE)
+#if IS_ENABLED(CONFIG_MTD_NAND_PLATFORM)
 	/* Setup MIU for NAND access on CS0...
 	 *
 	 * (it seems that we must also configure CS1 for reliable operation,
@@ -117,7 +117,7 @@ void __init pnx833x_board_setup(void)
 	pnx833x_gpio_select_output(5);
 	pnx833x_gpio_write(1, 5);
 
-#elif defined(CONFIG_MTD_CFI) || defined(CONFIG_MTD_CFI_MODULE)
+#elif IS_ENABLED(CONFIG_MTD_CFI)
 
 	/* Set up MIU for 16-bit NOR access on CS0 and CS1... */
 
diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c
index b105eca3c020..cd8fcab6b054 100644
--- a/arch/mips/sgi-ip27/ip27-memory.c
+++ b/arch/mips/sgi-ip27/ip27-memory.c
@@ -401,6 +401,7 @@ static void __init node_mem_init(cnodeid_t node)
 	 * Allocate the node data structures on the node first.
 	 */
 	__node_data[node] = __va(slot_freepfn << PAGE_SHIFT);
+	memset(__node_data[node], 0, PAGE_SIZE);
 
 	NODE_DATA(node)->bdata = &bootmem_node_data[node];
 	NODE_DATA(node)->node_start_pfn = start_pfn;
diff --git a/arch/mips/txx9/generic/pci.c b/arch/mips/txx9/generic/pci.c
index 125db323ab1e..4efd9185f294 100644
--- a/arch/mips/txx9/generic/pci.c
+++ b/arch/mips/txx9/generic/pci.c
@@ -304,7 +304,7 @@ static void __devinit quirk_slc90e66_bridge(struct pci_dev *dev)
 	smsc_fdc37m81x_config_end();
 }
 
-static void quirk_slc90e66_ide(struct pci_dev *dev)
+static void __devinit quirk_slc90e66_ide(struct pci_dev *dev)
 {
 	unsigned char dat;
 	int regs[2] = {0x41, 0x43};
@@ -339,7 +339,7 @@ static void quirk_slc90e66_ide(struct pci_dev *dev)
 }
 #endif /* CONFIG_TOSHIBA_FPCIB0 */
 
-static void tc35815_fixup(struct pci_dev *dev)
+static void __devinit tc35815_fixup(struct pci_dev *dev)
 {
 	/* This device may have PM registers but not they are not suported. */
 	if (dev->pm_cap) {
@@ -348,7 +348,7 @@ static void tc35815_fixup(struct pci_dev *dev)
 	}
 }
 
-static void final_fixup(struct pci_dev *dev)
+static void __devinit final_fixup(struct pci_dev *dev)
 {
 	unsigned char bist;
 
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index ae77a7916c03..560fe8991753 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -632,7 +632,7 @@ void __init txx9_physmap_flash_init(int no, unsigned long addr,
 				    unsigned long size,
 				    const struct physmap_flash_data *pdata)
 {
-#if defined(CONFIG_MTD_PHYSMAP) || defined(CONFIG_MTD_PHYSMAP_MODULE)
+#if IS_ENABLED(CONFIG_MTD_PHYSMAP)
 	struct resource res = {
 		.start = addr,
 		.end = addr + size - 1,
@@ -670,8 +670,7 @@ void __init txx9_physmap_flash_init(int no, unsigned long addr,
 void __init txx9_ndfmc_init(unsigned long baseaddr,
 			    const struct txx9ndfmc_platform_data *pdata)
 {
-#if defined(CONFIG_MTD_NAND_TXX9NDFMC) || \
-	defined(CONFIG_MTD_NAND_TXX9NDFMC_MODULE)
+#if IS_ENABLED(CONFIG_MTD_NAND_TXX9NDFMC)
 	struct resource res = {
 		.start = baseaddr,
 		.end = baseaddr + 0x1000 - 1,
@@ -687,7 +686,7 @@ void __init txx9_ndfmc_init(unsigned long baseaddr,
 #endif
 }
 
-#if defined(CONFIG_LEDS_GPIO) || defined(CONFIG_LEDS_GPIO_MODULE)
+#if IS_ENABLED(CONFIG_LEDS_GPIO)
 static DEFINE_SPINLOCK(txx9_iocled_lock);
 
 #define TXX9_IOCLED_MAXLEDS 8
@@ -810,7 +809,7 @@ void __init txx9_iocled_init(unsigned long baseaddr,
 void __init txx9_dmac_init(int id, unsigned long baseaddr, int irq,
 			   const struct txx9dmac_platform_data *pdata)
 {
-#if defined(CONFIG_TXX9_DMAC) || defined(CONFIG_TXX9_DMAC_MODULE)
+#if IS_ENABLED(CONFIG_TXX9_DMAC)
 	struct resource res[] = {
 		{
 			.start = baseaddr,
@@ -866,8 +865,7 @@ void __init txx9_aclc_init(unsigned long baseaddr, int irq,
 			   unsigned int dma_chan_out,
 			   unsigned int dma_chan_in)
 {
-#if defined(CONFIG_SND_SOC_TXX9ACLC) || \
-	defined(CONFIG_SND_SOC_TXX9ACLC_MODULE)
+#if IS_ENABLED(CONFIG_SND_SOC_TXX9ACLC)
 	unsigned int dma_base = dmac_id * TXX9_DMA_MAX_NR_CHANNELS;
 	struct resource res[] = {
 		{
diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c
index 6567895d1f59..5ff7a9584daf 100644
--- a/arch/mips/txx9/generic/setup_tx4939.c
+++ b/arch/mips/txx9/generic/setup_tx4939.c
@@ -317,7 +317,7 @@ void __init tx4939_sio_init(unsigned int sclk, unsigned int cts_mask)
 	}
 }
 
-#if defined(CONFIG_TC35815) || defined(CONFIG_TC35815_MODULE)
+#if IS_ENABLED(CONFIG_TC35815)
 static u32 tx4939_get_eth_speed(struct net_device *dev)
 {
 	struct ethtool_cmd cmd;
diff --git a/arch/mips/txx9/rbtx4939/setup.c b/arch/mips/txx9/rbtx4939/setup.c
index 2ad8973ba13d..e15641d93092 100644
--- a/arch/mips/txx9/rbtx4939/setup.c
+++ b/arch/mips/txx9/rbtx4939/setup.c
@@ -40,8 +40,7 @@ static void __init rbtx4939_time_init(void)
 	tx4939_time_init(0);
 }
 
-#if defined(__BIG_ENDIAN) && \
-	(defined(CONFIG_SMC91X) || defined(CONFIG_SMC91X_MODULE))
+#if defined(__BIG_ENDIAN) && IS_ENABLED(CONFIG_SMC91X)
 #define HAVE_RBTX4939_IOSWAB
 #define IS_CE1_ADDR(addr) \
 	((((unsigned long)(addr) - IO_BASE) & 0xfff00000) == TXX9_CE(1))
@@ -187,7 +186,7 @@ static void __init rbtx4939_update_ioc_pen(void)
 
 #define RBTX4939_MAX_7SEGLEDS	8
 
-#if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
+#if IS_ENABLED(CONFIG_LEDS_CLASS)
 static u8 led_val[RBTX4939_MAX_7SEGLEDS];
 struct rbtx4939_led_data {
 	struct led_classdev cdev;
@@ -263,7 +262,7 @@ static inline void rbtx4939_led_setup(void)
 
 static void __rbtx4939_7segled_putc(unsigned int pos, unsigned char val)
 {
-#if defined(CONFIG_LEDS_CLASS) || defined(CONFIG_LEDS_CLASS_MODULE)
+#if IS_ENABLED(CONFIG_LEDS_CLASS)
 	unsigned long flags;
 	local_irq_save(flags);
 	/* bit7: reserved for LED class */
@@ -287,7 +286,7 @@ static void rbtx4939_7segled_putc(unsigned int pos, unsigned char val)
 	__rbtx4939_7segled_putc(pos, val);
 }
 
-#if defined(CONFIG_MTD_RBTX4939) || defined(CONFIG_MTD_RBTX4939_MODULE)
+#if IS_ENABLED(CONFIG_MTD_RBTX4939)
 /* special mapping for boot rom */
 static unsigned long rbtx4939_flash_fixup_ofs(unsigned long ofs)
 {
@@ -463,7 +462,7 @@ static void __init rbtx4939_device_init(void)
 		.flags = SMC91X_USE_16BIT,
 	};
 	struct platform_device *pdev;
-#if defined(CONFIG_TC35815) || defined(CONFIG_TC35815_MODULE)
+#if IS_ENABLED(CONFIG_TC35815)
 	int i, j;
 	unsigned char ethaddr[2][6];
 	u8 bdipsw = readb(rbtx4939_bdipsw_addr) & 0x0f;
diff --git a/arch/mn10300/Kconfig b/arch/mn10300/Kconfig
index 687f9b4a2ed6..5cfb086b3903 100644
--- a/arch/mn10300/Kconfig
+++ b/arch/mn10300/Kconfig
@@ -3,6 +3,7 @@ config MN10300
 	select HAVE_OPROFILE
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_KGDB
 	select HAVE_NMI_WATCHDOG if MN10300_WD_TIMER
diff --git a/arch/mn10300/include/asm/ipc.h b/arch/mn10300/include/asm/ipc.h
deleted file mode 100644
index a46e3d9c2a3f..000000000000
--- a/arch/mn10300/include/asm/ipc.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/ipc.h>
diff --git a/arch/mn10300/include/asm/unistd.h b/arch/mn10300/include/asm/unistd.h
index 9051f921cbc7..866eb14749d7 100644
--- a/arch/mn10300/include/asm/unistd.h
+++ b/arch/mn10300/include/asm/unistd.h
@@ -358,7 +358,6 @@
 /*
  * specify the deprecated syscalls we want to support on this arch
  */
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
 #define __ARCH_WANT_STAT64
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 3f35c38d7b64..0922959663a0 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -13,7 +13,6 @@ generic-y += cacheflush.h
 generic-y += checksum.h
 generic-y += cmpxchg.h
 generic-y += cmpxchg-local.h
-generic-y += cpumask.h
 generic-y += cputime.h
 generic-y += current.h
 generic-y += device.h
@@ -43,7 +42,6 @@ generic-y += percpu.h
 generic-y += poll.h
 generic-y += posix_types.h
 generic-y += resource.h
-generic-y += rmap.h
 generic-y += scatterlist.h
 generic-y += sections.h
 generic-y += segment.h
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 9a5d3cdc3e12..352f416269ce 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -115,11 +115,13 @@ config PPC
 	select HAVE_OPROFILE
 	select HAVE_SYSCALL_WRAPPERS if PPC64
 	select GENERIC_ATOMIC64 if PPC32
+	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select HAVE_IRQ_WORK
 	select HAVE_PERF_EVENTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && PPC_BOOK3S_64
 	select HAVE_GENERIC_HARDIRQS
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select SPARSE_IRQ
 	select IRQ_PER_CPU
 	select IRQ_DOMAIN
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 950d1f7a5a39..159e94f4b22a 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -149,7 +149,6 @@ core-$(CONFIG_KVM) 		+= arch/powerpc/kvm/
 core-$(CONFIG_PERF_EVENTS)	+= arch/powerpc/perf/
 
 drivers-$(CONFIG_OPROFILE)	+= arch/powerpc/oprofile/
-drivers-$(CONFIG_CRYPTO_DEV_NX) += drivers/crypto/nx/
 
 # Default to zImage, override when needed
 all: zImage
diff --git a/arch/powerpc/boot/dts/p2020rdb-pc_32b.dts b/arch/powerpc/boot/dts/p2020rdb-pc_32b.dts
index 852e5b27485d..57573bd52caa 100644
--- a/arch/powerpc/boot/dts/p2020rdb-pc_32b.dts
+++ b/arch/powerpc/boot/dts/p2020rdb-pc_32b.dts
@@ -56,7 +56,7 @@
 		ranges = <0x0 0x0 0xffe00000 0x100000>;
 	};
 
-	pci0: pcie@ffe08000 {
+	pci2: pcie@ffe08000 {
 		reg = <0 0xffe08000 0 0x1000>;
 		status = "disabled";
 	};
@@ -76,7 +76,7 @@
 		};
 	};
 
-	pci2: pcie@ffe0a000 {
+	pci0: pcie@ffe0a000 {
 		reg = <0 0xffe0a000 0 0x1000>;
 		ranges = <0x2000000 0x0 0xe0000000 0 0x80000000 0x0 0x20000000
 			  0x1000000 0x0 0x00000000 0 0xffc00000 0x0 0x10000>;
diff --git a/arch/powerpc/boot/dts/p2020rdb-pc_36b.dts b/arch/powerpc/boot/dts/p2020rdb-pc_36b.dts
index b5a56ca51cf7..470247ea68b4 100644
--- a/arch/powerpc/boot/dts/p2020rdb-pc_36b.dts
+++ b/arch/powerpc/boot/dts/p2020rdb-pc_36b.dts
@@ -56,7 +56,7 @@
 		ranges = <0x0 0xf 0xffe00000 0x100000>;
 	};
 
-	pci0: pcie@fffe08000 {
+	pci2: pcie@fffe08000 {
 		reg = <0xf 0xffe08000 0 0x1000>;
 		status = "disabled";
 	};
@@ -76,7 +76,7 @@
 		};
 	};
 
-	pci2: pcie@fffe0a000 {
+	pci0: pcie@fffe0a000 {
 		reg = <0xf 0xffe0a000 0 0x1000>;
 		ranges = <0x2000000 0x0 0xe0000000 0xc 0x00000000 0x0 0x20000000
 			  0x1000000 0x0 0x00000000 0xf 0xffc00000 0x0 0x10000>;
diff --git a/arch/powerpc/boot/dts/p3041ds.dts b/arch/powerpc/boot/dts/p3041ds.dts
index 22a215e94162..6cdcadc80c30 100644
--- a/arch/powerpc/boot/dts/p3041ds.dts
+++ b/arch/powerpc/boot/dts/p3041ds.dts
@@ -58,7 +58,7 @@
 				#size-cells = <1>;
 				compatible = "spansion,s25sl12801";
 				reg = <0>;
-				spi-max-frequency = <40000000>; /* input clock */
+				spi-max-frequency = <35000000>; /* input clock */
 				partition@u-boot {
 					label = "u-boot";
 					reg = <0x00000000 0x00100000>;
diff --git a/arch/powerpc/configs/chroma_defconfig b/arch/powerpc/configs/chroma_defconfig
index b1f9597fe312..29bb11ec6c64 100644
--- a/arch/powerpc/configs/chroma_defconfig
+++ b/arch/powerpc/configs/chroma_defconfig
@@ -21,8 +21,8 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_NAMESPACES=y
 CONFIG_RELAY=y
 CONFIG_BLK_DEV_INITRD=y
diff --git a/arch/powerpc/configs/g5_defconfig b/arch/powerpc/configs/g5_defconfig
index 07b7f2af2dca..15130066e5e2 100644
--- a/arch/powerpc/configs/g5_defconfig
+++ b/arch/powerpc/configs/g5_defconfig
@@ -1,10 +1,8 @@
-CONFIG_PPC64=y
-CONFIG_ALTIVEC=y
-CONFIG_SMP=y
-CONFIG_NR_CPUS=4
 CONFIG_EXPERIMENTAL=y
 CONFIG_SYSVIPC=y
 CONFIG_POSIX_MQUEUE=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_BLK_DEV_INITRD=y
@@ -15,16 +13,15 @@ CONFIG_MODULES=y
 CONFIG_MODULE_UNLOAD=y
 CONFIG_MODVERSIONS=y
 CONFIG_MODULE_SRCVERSION_ALL=y
-# CONFIG_PPC_PSERIES is not set
+CONFIG_PARTITION_ADVANCED=y
+CONFIG_MAC_PARTITION=y
+CONFIG_SMP=y
+CONFIG_NR_CPUS=4
+CONFIG_KEXEC=y
+# CONFIG_RELOCATABLE is not set
 CONFIG_CPU_FREQ=y
 CONFIG_CPU_FREQ_GOV_POWERSAVE=y
 CONFIG_CPU_FREQ_GOV_USERSPACE=y
-CONFIG_CPU_FREQ_PMAC64=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
-CONFIG_KEXEC=y
-CONFIG_IRQ_ALL_CPUS=y
-# CONFIG_MIGRATION is not set
 CONFIG_PCI_MSI=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -52,7 +49,6 @@ CONFIG_NF_CT_NETLINK=m
 CONFIG_NF_CONNTRACK_IPV4=m
 CONFIG_IP_NF_QUEUE=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
-CONFIG_PROC_DEVICETREE=y
 CONFIG_BLK_DEV_LOOP=y
 CONFIG_BLK_DEV_NBD=m
 CONFIG_BLK_DEV_RAM=y
@@ -60,8 +56,6 @@ CONFIG_BLK_DEV_RAM_SIZE=65536
 CONFIG_CDROM_PKTCDVD=m
 CONFIG_IDE=y
 CONFIG_BLK_DEV_IDECD=y
-CONFIG_BLK_DEV_IDE_PMAC=y
-CONFIG_BLK_DEV_IDE_PMAC_ATA100FIRST=y
 CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=y
 CONFIG_BLK_DEV_SR=y
@@ -85,33 +79,24 @@ CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_ZERO=m
-CONFIG_IEEE1394=y
-CONFIG_IEEE1394_OHCI1394=y
-CONFIG_IEEE1394_SBP2=m
-CONFIG_IEEE1394_ETH1394=m
-CONFIG_IEEE1394_RAWIO=y
-CONFIG_IEEE1394_VIDEO1394=m
-CONFIG_IEEE1394_DV1394=m
-CONFIG_ADB_PMU=y
-CONFIG_PMAC_SMU=y
+CONFIG_MACINTOSH_DRIVERS=y
 CONFIG_MAC_EMUMOUSEBTN=y
-CONFIG_THERM_PM72=y
-CONFIG_WINDFARM=y
-CONFIG_WINDFARM_PM81=y
-CONFIG_WINDFARM_PM91=y
-CONFIG_WINDFARM_PM112=y
-CONFIG_WINDFARM_PM121=y
 CONFIG_NETDEVICES=y
-CONFIG_DUMMY=m
 CONFIG_BONDING=m
-CONFIG_TUN=m
-CONFIG_NET_ETHERNET=y
+CONFIG_DUMMY=m
 CONFIG_MII=y
-CONFIG_SUNGEM=y
+CONFIG_TUN=m
 CONFIG_ACENIC=m
 CONFIG_ACENIC_OMIT_TIGON_I=y
-CONFIG_E1000=y
 CONFIG_TIGON3=y
+CONFIG_E1000=y
+CONFIG_SUNGEM=y
+CONFIG_PPP=m
+CONFIG_PPP_BSDCOMP=m
+CONFIG_PPP_DEFLATE=m
+CONFIG_PPPOE=m
+CONFIG_PPP_ASYNC=m
+CONFIG_PPP_SYNC_TTY=m
 CONFIG_USB_CATC=m
 CONFIG_USB_KAWETH=m
 CONFIG_USB_PEGASUS=m
@@ -121,36 +106,24 @@ CONFIG_USB_USBNET=m
 # CONFIG_USB_NET_NET1080 is not set
 # CONFIG_USB_NET_CDC_SUBSET is not set
 # CONFIG_USB_NET_ZAURUS is not set
-CONFIG_PPP=m
-CONFIG_PPP_ASYNC=m
-CONFIG_PPP_SYNC_TTY=m
-CONFIG_PPP_DEFLATE=m
-CONFIG_PPP_BSDCOMP=m
-CONFIG_PPPOE=m
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
 CONFIG_INPUT_JOYDEV=m
 CONFIG_INPUT_EVDEV=y
-# CONFIG_KEYBOARD_ATKBD is not set
 # CONFIG_MOUSE_PS2 is not set
-# CONFIG_SERIO_I8042 is not set
 # CONFIG_SERIO_SERPORT is not set
+CONFIG_VT_HW_CONSOLE_BINDING=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_GEN_RTC=y
 CONFIG_RAW_DRIVER=y
 CONFIG_I2C_CHARDEV=y
 # CONFIG_HWMON is not set
-CONFIG_AGP=m
-CONFIG_AGP_UNINORTH=m
+CONFIG_AGP=y
+CONFIG_DRM=y
+CONFIG_DRM_NOUVEAU=y
 CONFIG_VIDEO_OUTPUT_CONTROL=m
-CONFIG_FB=y
 CONFIG_FIRMWARE_EDID=y
 CONFIG_FB_TILEBLITTING=y
-CONFIG_FB_OF=y
-CONFIG_FB_NVIDIA=y
-CONFIG_FB_NVIDIA_I2C=y
 CONFIG_FB_RADEON=y
-# CONFIG_VGA_CONSOLE is not set
-CONFIG_FRAMEBUFFER_CONSOLE=y
 CONFIG_LOGO=y
 CONFIG_SOUND=m
 CONFIG_SND=m
@@ -158,15 +131,7 @@ CONFIG_SND_SEQUENCER=m
 CONFIG_SND_MIXER_OSS=m
 CONFIG_SND_PCM_OSS=m
 CONFIG_SND_SEQUENCER_OSS=y
-CONFIG_SND_POWERMAC=m
-CONFIG_SND_AOA=m
-CONFIG_SND_AOA_FABRIC_LAYOUT=m
-CONFIG_SND_AOA_ONYX=m
-CONFIG_SND_AOA_TAS=m
-CONFIG_SND_AOA_TOONIE=m
 CONFIG_SND_USB_AUDIO=m
-CONFIG_HID_PID=y
-CONFIG_USB_HIDDEV=y
 CONFIG_HID_GYRATION=y
 CONFIG_LOGITECH_FF=y
 CONFIG_HID_PANTHERLORD=y
@@ -174,13 +139,12 @@ CONFIG_HID_PETALYNX=y
 CONFIG_HID_SAMSUNG=y
 CONFIG_HID_SONY=y
 CONFIG_HID_SUNPLUS=y
+CONFIG_HID_PID=y
+CONFIG_USB_HIDDEV=y
 CONFIG_USB=y
-CONFIG_USB_DEVICEFS=y
 CONFIG_USB_MON=y
 CONFIG_USB_EHCI_HCD=y
-# CONFIG_USB_EHCI_HCD_PPC_OF is not set
 CONFIG_USB_OHCI_HCD=y
-CONFIG_USB_OHCI_HCD_PPC_OF_BE=y
 CONFIG_USB_ACM=m
 CONFIG_USB_PRINTER=y
 CONFIG_USB_STORAGE=y
@@ -244,8 +208,6 @@ CONFIG_REISERFS_FS_POSIX_ACL=y
 CONFIG_REISERFS_FS_SECURITY=y
 CONFIG_XFS_FS=m
 CONFIG_XFS_POSIX_ACL=y
-CONFIG_INOTIFY=y
-CONFIG_AUTOFS_FS=m
 CONFIG_ISO9660_FS=y
 CONFIG_JOLIET=y
 CONFIG_ZISOFS=y
@@ -259,14 +221,12 @@ CONFIG_HFS_FS=m
 CONFIG_HFSPLUS_FS=m
 CONFIG_CRAMFS=y
 CONFIG_NFS_FS=y
-CONFIG_NFS_V3=y
 CONFIG_NFS_V3_ACL=y
 CONFIG_NFS_V4=y
 CONFIG_NFSD=y
 CONFIG_NFSD_V3_ACL=y
 CONFIG_NFSD_V4=y
 CONFIG_CIFS=m
-CONFIG_PARTITION_ADVANCED=y
 CONFIG_NLS_CODEPAGE_437=y
 CONFIG_NLS_CODEPAGE_1250=y
 CONFIG_NLS_CODEPAGE_1251=y
@@ -274,29 +234,23 @@ CONFIG_NLS_ASCII=y
 CONFIG_NLS_ISO8859_1=y
 CONFIG_NLS_ISO8859_15=y
 CONFIG_NLS_UTF8=y
-CONFIG_CRC_T10DIF=y
-CONFIG_LIBCRC32C=m
 CONFIG_MAGIC_SYSRQ=y
+# CONFIG_UNUSED_SYMBOLS is not set
 CONFIG_DEBUG_FS=y
 CONFIG_DEBUG_KERNEL=y
 CONFIG_DEBUG_MUTEXES=y
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_LATENCYTOP=y
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_BOOTX_TEXT=y
+CONFIG_STRICT_DEVMEM=y
 CONFIG_CRYPTO_NULL=m
 CONFIG_CRYPTO_TEST=m
-CONFIG_CRYPTO_ECB=m
 CONFIG_CRYPTO_PCBC=m
 CONFIG_CRYPTO_HMAC=y
-CONFIG_CRYPTO_MD4=m
 CONFIG_CRYPTO_MICHAEL_MIC=m
 CONFIG_CRYPTO_SHA256=m
 CONFIG_CRYPTO_SHA512=m
 CONFIG_CRYPTO_WP512=m
 CONFIG_CRYPTO_AES=m
 CONFIG_CRYPTO_ANUBIS=m
-CONFIG_CRYPTO_ARC4=m
 CONFIG_CRYPTO_BLOWFISH=m
 CONFIG_CRYPTO_CAST5=m
 CONFIG_CRYPTO_CAST6=m
@@ -306,3 +260,6 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
 # CONFIG_CRYPTO_HW is not set
+# CONFIG_VIRTUALIZATION is not set
+CONFIG_CRC_T10DIF=y
+CONFIG_LIBCRC32C=m
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index f2fe0c2b41e4..db27c82e0542 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -279,7 +279,8 @@ CONFIG_HVC_RTAS=y
 CONFIG_HVC_BEAT=y
 CONFIG_HVCS=m
 CONFIG_IBM_BSR=m
-# CONFIG_HW_RANDOM is not set
+CONFIG_HW_RANDOM=m
+CONFIG_HW_RANDOM_PSERIES=m
 CONFIG_RAW_DRIVER=y
 CONFIG_I2C_CHARDEV=y
 CONFIG_I2C_AMD8111=y
@@ -485,7 +486,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-# CONFIG_CRYPTO_HW is not set
+CONFIG_CRYPTO_HW=y
+CONFIG_CRYPTO_DEV_NX=m
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM_BOOK3S_64=m
 CONFIG_KVM_BOOK3S_64_HV=y
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index 187fb8d53605..1f65b3c9b59a 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -226,7 +226,8 @@ CONFIG_HVC_CONSOLE=y
 CONFIG_HVC_RTAS=y
 CONFIG_HVCS=m
 CONFIG_IBM_BSR=m
-# CONFIG_HW_RANDOM is not set
+CONFIG_HW_RANDOM=m
+CONFIG_HW_RANDOM_PSERIES=m
 CONFIG_GEN_RTC=y
 CONFIG_RAW_DRIVER=y
 CONFIG_MAX_RAW_DEVS=1024
@@ -367,7 +368,8 @@ CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 CONFIG_CRYPTO_LZO=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-# CONFIG_CRYPTO_HW is not set
+CONFIG_CRYPTO_HW=y
+CONFIG_CRYPTO_DEV_NX=m
 CONFIG_VIRTUALIZATION=y
 CONFIG_KVM_BOOK3S_64=m
 CONFIG_KVM_BOOK3S_64_HV=y
diff --git a/arch/powerpc/include/asm/dma-mapping.h b/arch/powerpc/include/asm/dma-mapping.h
index 62678e365ca0..78160874809a 100644
--- a/arch/powerpc/include/asm/dma-mapping.h
+++ b/arch/powerpc/include/asm/dma-mapping.h
@@ -27,7 +27,10 @@ extern void *dma_direct_alloc_coherent(struct device *dev, size_t size,
 extern void dma_direct_free_coherent(struct device *dev, size_t size,
 				     void *vaddr, dma_addr_t dma_handle,
 				     struct dma_attrs *attrs);
-
+extern int dma_direct_mmap_coherent(struct device *dev,
+				    struct vm_area_struct *vma,
+				    void *cpu_addr, dma_addr_t handle,
+				    size_t size, struct dma_attrs *attrs);
 
 #ifdef CONFIG_NOT_COHERENT_CACHE
 /*
@@ -207,11 +210,8 @@ static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr)
 #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f)
 #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h)
 
-extern int dma_mmap_coherent(struct device *, struct vm_area_struct *,
-			     void *, dma_addr_t, size_t);
 #define ARCH_HAS_DMA_MMAP_COHERENT
 
-
 static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		enum dma_data_direction direction)
 {
diff --git a/arch/powerpc/include/asm/kmap_types.h b/arch/powerpc/include/asm/kmap_types.h
index bca8fdcd2542..5acabbd7ac6f 100644
--- a/arch/powerpc/include/asm/kmap_types.h
+++ b/arch/powerpc/include/asm/kmap_types.h
@@ -10,36 +10,7 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-enum km_type {
-	KM_BOUNCE_READ,
-	KM_SKB_SUNRPC_DATA,
-	KM_SKB_DATA_SOFTIRQ,
-	KM_USER0,
-	KM_USER1,
-	KM_BIO_SRC_IRQ,
-	KM_BIO_DST_IRQ,
-	KM_PTE0,
-	KM_PTE1,
-	KM_IRQ0,
-	KM_IRQ1,
-	KM_SOFTIRQ0,
-	KM_SOFTIRQ1,
-	KM_PPC_SYNC_PAGE,
-	KM_PPC_SYNC_ICACHE,
-	KM_KDB,
-	KM_TYPE_NR
-};
-
-/*
- * This is a temporary build fix that (so they say on lkml....) should no longer
- * be required after 2.6.33, because of changes planned to the kmap code.
- * Let's try to remove this cruft then.
- */
-#ifdef CONFIG_DEBUG_HIGHMEM
-#define KM_NMI		(-1)
-#define KM_NMI_PTE	(-1)
-#define KM_IRQ_PTE	(-1)
-#endif
+#define KM_TYPE_NR 16
 
 #endif	/* __KERNEL__ */
 #endif	/* _ASM_POWERPC_KMAP_TYPES_H */
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index d3d1b5efd7eb..bd377a368611 100644
--- a/arch/powerpc/include/asm/unistd.h
+++ b/arch/powerpc/include/asm/unistd.h
@@ -389,7 +389,6 @@
 #include <linux/compiler.h>
 #include <linux/linkage.h>
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_ALARM
diff --git a/arch/powerpc/kernel/dma-iommu.c b/arch/powerpc/kernel/dma-iommu.c
index bcfdcd22c766..2d7bb8ced136 100644
--- a/arch/powerpc/kernel/dma-iommu.c
+++ b/arch/powerpc/kernel/dma-iommu.c
@@ -109,6 +109,7 @@ static u64 dma_iommu_get_required_mask(struct device *dev)
 struct dma_map_ops dma_iommu_ops = {
 	.alloc			= dma_iommu_alloc_coherent,
 	.free			= dma_iommu_free_coherent,
+	.mmap			= dma_direct_mmap_coherent,
 	.map_sg			= dma_iommu_map_sg,
 	.unmap_sg		= dma_iommu_unmap_sg,
 	.dma_supported		= dma_iommu_dma_supported,
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 4ab88dafb235..46943651da23 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -49,6 +49,7 @@ static u64 swiotlb_powerpc_get_required(struct device *dev)
 struct dma_map_ops swiotlb_dma_ops = {
 	.alloc = dma_direct_alloc_coherent,
 	.free = dma_direct_free_coherent,
+	.mmap = dma_direct_mmap_coherent,
 	.map_sg = swiotlb_map_sg_attrs,
 	.unmap_sg = swiotlb_unmap_sg_attrs,
 	.dma_supported = swiotlb_dma_supported,
diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 289be751cd75..355b9d84b0f8 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -67,6 +67,24 @@ void dma_direct_free_coherent(struct device *dev, size_t size,
 #endif
 }
 
+int dma_direct_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
+			     void *cpu_addr, dma_addr_t handle, size_t size,
+			     struct dma_attrs *attrs)
+{
+	unsigned long pfn;
+
+#ifdef CONFIG_NOT_COHERENT_CACHE
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	pfn = __dma_get_coherent_pfn((unsigned long)cpu_addr);
+#else
+	pfn = page_to_pfn(virt_to_page(cpu_addr));
+#endif
+	return remap_pfn_range(vma, vma->vm_start,
+			       pfn + vma->vm_pgoff,
+			       vma->vm_end - vma->vm_start,
+			       vma->vm_page_prot);
+}
+
 static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 			     int nents, enum dma_data_direction direction,
 			     struct dma_attrs *attrs)
@@ -156,6 +174,7 @@ static inline void dma_direct_sync_single(struct device *dev,
 struct dma_map_ops dma_direct_ops = {
 	.alloc				= dma_direct_alloc_coherent,
 	.free				= dma_direct_free_coherent,
+	.mmap				= dma_direct_mmap_coherent,
 	.map_sg				= dma_direct_map_sg,
 	.unmap_sg			= dma_direct_unmap_sg,
 	.dma_supported			= dma_direct_dma_supported,
@@ -219,20 +238,3 @@ static int __init dma_init(void)
 }
 fs_initcall(dma_init);
 
-int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
-		      void *cpu_addr, dma_addr_t handle, size_t size)
-{
-	unsigned long pfn;
-
-#ifdef CONFIG_NOT_COHERENT_CACHE
-	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	pfn = __dma_get_coherent_pfn((unsigned long)cpu_addr);
-#else
-	pfn = page_to_pfn(virt_to_page(cpu_addr));
-#endif
-	return remap_pfn_range(vma, vma->vm_start,
-			       pfn + vma->vm_pgoff,
-			       vma->vm_end - vma->vm_start,
-			       vma->vm_page_prot);
-}
-EXPORT_SYMBOL_GPL(dma_mmap_coherent);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index 5207d5a405e2..ead5016b02d0 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -89,10 +89,14 @@ crit_transfer_to_handler:
 	mfspr	r0,SPRN_SRR1
 	stw	r0,_SRR1(r11)
 
+	/* set the stack limit to the current stack
+	 * and set the limit to protect the thread_info
+	 * struct
+	 */
 	mfspr	r8,SPRN_SPRG_THREAD
 	lwz	r0,KSP_LIMIT(r8)
 	stw	r0,SAVED_KSP_LIMIT(r11)
-	CURRENT_THREAD_INFO(r0, r1)
+	rlwimi	r0,r1,0,0,(31-THREAD_SHIFT)
 	stw	r0,KSP_LIMIT(r8)
 	/* fall through */
 #endif
@@ -109,10 +113,14 @@ crit_transfer_to_handler:
 	mfspr	r0,SPRN_SRR1
 	stw	r0,crit_srr1@l(0)
 
+	/* set the stack limit to the current stack
+	 * and set the limit to protect the thread_info
+	 * struct
+	 */
 	mfspr	r8,SPRN_SPRG_THREAD
 	lwz	r0,KSP_LIMIT(r8)
 	stw	r0,saved_ksp_limit@l(0)
-	CURRENT_THREAD_INFO(r0, r1)
+	rlwimi	r0,r1,0,0,(31-THREAD_SHIFT)
 	stw	r0,KSP_LIMIT(r8)
 	/* fall through */
 #endif
diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c
index 91b46b7f6f0d..1fb78561096a 100644
--- a/arch/powerpc/kernel/ftrace.c
+++ b/arch/powerpc/kernel/ftrace.c
@@ -630,18 +630,17 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
 		return;
 	}
 
-	if (ftrace_push_return_trace(old, self_addr, &trace.depth, 0) == -EBUSY) {
-		*parent = old;
-		return;
-	}
-
 	trace.func = self_addr;
+	trace.depth = current->curr_ret_stack + 1;
 
 	/* Only trace if the calling function expects to */
 	if (!ftrace_graph_entry(&trace)) {
-		current->curr_ret_stack--;
 		*parent = old;
+		return;
 	}
+
+	if (ftrace_push_return_trace(old, self_addr, &trace.depth, 0) == -EBUSY)
+		*parent = old;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 4174b4b23246..2c0ee6405633 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -709,7 +709,7 @@ static int __init rtas_flash_init(void)
 
 	if (rtas_token("ibm,update-flash-64-and-reboot") ==
 		       RTAS_UNKNOWN_SERVICE) {
-		printk(KERN_ERR "rtas_flash: no firmware flash support\n");
+		pr_info("rtas_flash: no firmware flash support\n");
 		return 1;
 	}
 
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index 3052a931f2b5..02b32216bbc3 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -611,6 +611,7 @@ static u64 vio_dma_get_required_mask(struct device *dev)
 struct dma_map_ops vio_dma_mapping_ops = {
 	.alloc             = vio_dma_iommu_alloc_coherent,
 	.free              = vio_dma_iommu_free_coherent,
+	.mmap		   = dma_direct_mmap_coherent,
 	.map_sg            = vio_dma_iommu_map_sg,
 	.unmap_sg          = vio_dma_iommu_unmap_sg,
 	.map_page          = vio_dma_iommu_map_page,
diff --git a/arch/powerpc/kvm/book3s_rmhandlers.S b/arch/powerpc/kvm/book3s_rmhandlers.S
index ab523f3c1731..9ecf6e35cd8d 100644
--- a/arch/powerpc/kvm/book3s_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_rmhandlers.S
@@ -67,7 +67,6 @@ kvmppc_skip_Hinterrupt:
 #elif defined(CONFIG_PPC_BOOK3S_32)
 
 #define FUNC(name)		name
-#define MTMSR_EERI(reg)		mtmsr	(reg)
 
 .macro INTERRUPT_TRAMPOLINE intno
 
diff --git a/arch/powerpc/kvm/bookehv_interrupts.S b/arch/powerpc/kvm/bookehv_interrupts.S
index d28c2d43ac1b..099fe8272b57 100644
--- a/arch/powerpc/kvm/bookehv_interrupts.S
+++ b/arch/powerpc/kvm/bookehv_interrupts.S
@@ -50,8 +50,9 @@
 #define HOST_R2         (3 * LONGBYTES)
 #define HOST_CR         (4 * LONGBYTES)
 #define HOST_NV_GPRS    (5 * LONGBYTES)
-#define HOST_NV_GPR(n)  (HOST_NV_GPRS + ((n - 14) * LONGBYTES))
-#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(31) + LONGBYTES)
+#define __HOST_NV_GPR(n)  (HOST_NV_GPRS + ((n - 14) * LONGBYTES))
+#define HOST_NV_GPR(n)  __HOST_NV_GPR(__REG_##n)
+#define HOST_MIN_STACK_SIZE (HOST_NV_GPR(R31) + LONGBYTES)
 #define HOST_STACK_SIZE ((HOST_MIN_STACK_SIZE + 15) & ~15) /* Align. */
 #define HOST_STACK_LR   (HOST_STACK_SIZE + LONGBYTES) /* In caller stack frame. */
 
@@ -410,24 +411,24 @@ heavyweight_exit:
 	PPC_STL	r31, VCPU_GPR(R31)(r4)
 
 	/* Load host non-volatile register state from host stack. */
-	PPC_LL	r14, HOST_NV_GPR(r14)(r1)
-	PPC_LL	r15, HOST_NV_GPR(r15)(r1)
-	PPC_LL	r16, HOST_NV_GPR(r16)(r1)
-	PPC_LL	r17, HOST_NV_GPR(r17)(r1)
-	PPC_LL	r18, HOST_NV_GPR(r18)(r1)
-	PPC_LL	r19, HOST_NV_GPR(r19)(r1)
-	PPC_LL	r20, HOST_NV_GPR(r20)(r1)
-	PPC_LL	r21, HOST_NV_GPR(r21)(r1)
-	PPC_LL	r22, HOST_NV_GPR(r22)(r1)
-	PPC_LL	r23, HOST_NV_GPR(r23)(r1)
-	PPC_LL	r24, HOST_NV_GPR(r24)(r1)
-	PPC_LL	r25, HOST_NV_GPR(r25)(r1)
-	PPC_LL	r26, HOST_NV_GPR(r26)(r1)
-	PPC_LL	r27, HOST_NV_GPR(r27)(r1)
-	PPC_LL	r28, HOST_NV_GPR(r28)(r1)
-	PPC_LL	r29, HOST_NV_GPR(r29)(r1)
-	PPC_LL	r30, HOST_NV_GPR(r30)(r1)
-	PPC_LL	r31, HOST_NV_GPR(r31)(r1)
+	PPC_LL	r14, HOST_NV_GPR(R14)(r1)
+	PPC_LL	r15, HOST_NV_GPR(R15)(r1)
+	PPC_LL	r16, HOST_NV_GPR(R16)(r1)
+	PPC_LL	r17, HOST_NV_GPR(R17)(r1)
+	PPC_LL	r18, HOST_NV_GPR(R18)(r1)
+	PPC_LL	r19, HOST_NV_GPR(R19)(r1)
+	PPC_LL	r20, HOST_NV_GPR(R20)(r1)
+	PPC_LL	r21, HOST_NV_GPR(R21)(r1)
+	PPC_LL	r22, HOST_NV_GPR(R22)(r1)
+	PPC_LL	r23, HOST_NV_GPR(R23)(r1)
+	PPC_LL	r24, HOST_NV_GPR(R24)(r1)
+	PPC_LL	r25, HOST_NV_GPR(R25)(r1)
+	PPC_LL	r26, HOST_NV_GPR(R26)(r1)
+	PPC_LL	r27, HOST_NV_GPR(R27)(r1)
+	PPC_LL	r28, HOST_NV_GPR(R28)(r1)
+	PPC_LL	r29, HOST_NV_GPR(R29)(r1)
+	PPC_LL	r30, HOST_NV_GPR(R30)(r1)
+	PPC_LL	r31, HOST_NV_GPR(R31)(r1)
 
 	/* Return to kvm_vcpu_run(). */
 	mtlr	r5
@@ -453,24 +454,24 @@ _GLOBAL(__kvmppc_vcpu_run)
 	stw	r5, HOST_CR(r1)
 
 	/* Save host non-volatile register state to stack. */
-	PPC_STL	r14, HOST_NV_GPR(r14)(r1)
-	PPC_STL	r15, HOST_NV_GPR(r15)(r1)
-	PPC_STL	r16, HOST_NV_GPR(r16)(r1)
-	PPC_STL	r17, HOST_NV_GPR(r17)(r1)
-	PPC_STL	r18, HOST_NV_GPR(r18)(r1)
-	PPC_STL	r19, HOST_NV_GPR(r19)(r1)
-	PPC_STL	r20, HOST_NV_GPR(r20)(r1)
-	PPC_STL	r21, HOST_NV_GPR(r21)(r1)
-	PPC_STL	r22, HOST_NV_GPR(r22)(r1)
-	PPC_STL	r23, HOST_NV_GPR(r23)(r1)
-	PPC_STL	r24, HOST_NV_GPR(r24)(r1)
-	PPC_STL	r25, HOST_NV_GPR(r25)(r1)
-	PPC_STL	r26, HOST_NV_GPR(r26)(r1)
-	PPC_STL	r27, HOST_NV_GPR(r27)(r1)
-	PPC_STL	r28, HOST_NV_GPR(r28)(r1)
-	PPC_STL	r29, HOST_NV_GPR(r29)(r1)
-	PPC_STL	r30, HOST_NV_GPR(r30)(r1)
-	PPC_STL	r31, HOST_NV_GPR(r31)(r1)
+	PPC_STL	r14, HOST_NV_GPR(R14)(r1)
+	PPC_STL	r15, HOST_NV_GPR(R15)(r1)
+	PPC_STL	r16, HOST_NV_GPR(R16)(r1)
+	PPC_STL	r17, HOST_NV_GPR(R17)(r1)
+	PPC_STL	r18, HOST_NV_GPR(R18)(r1)
+	PPC_STL	r19, HOST_NV_GPR(R19)(r1)
+	PPC_STL	r20, HOST_NV_GPR(R20)(r1)
+	PPC_STL	r21, HOST_NV_GPR(R21)(r1)
+	PPC_STL	r22, HOST_NV_GPR(R22)(r1)
+	PPC_STL	r23, HOST_NV_GPR(R23)(r1)
+	PPC_STL	r24, HOST_NV_GPR(R24)(r1)
+	PPC_STL	r25, HOST_NV_GPR(R25)(r1)
+	PPC_STL	r26, HOST_NV_GPR(R26)(r1)
+	PPC_STL	r27, HOST_NV_GPR(R27)(r1)
+	PPC_STL	r28, HOST_NV_GPR(R28)(r1)
+	PPC_STL	r29, HOST_NV_GPR(R29)(r1)
+	PPC_STL	r30, HOST_NV_GPR(R30)(r1)
+	PPC_STL	r31, HOST_NV_GPR(R31)(r1)
 
 	/* Load guest non-volatiles. */
 	PPC_LL	r14, VCPU_GPR(R14)(r4)
diff --git a/arch/powerpc/platforms/85xx/p1022_ds.c b/arch/powerpc/platforms/85xx/p1022_ds.c
index 89ee02c54561..3c732acf331d 100644
--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@@ -208,6 +208,7 @@ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port)
 	u8 __iomem *lbc_lcs0_ba = NULL;
 	u8 __iomem *lbc_lcs1_ba = NULL;
 	phys_addr_t cs0_addr, cs1_addr;
+	u32 br0, or0, br1, or1;
 	const __be32 *iprop;
 	unsigned int num_laws;
 	u8 b;
@@ -256,11 +257,70 @@ static void p1022ds_set_monitor_port(enum fsl_diu_monitor_port port)
 	}
 	num_laws = be32_to_cpup(iprop);
 
-	cs0_addr = lbc_br_to_phys(ecm, num_laws, in_be32(&lbc->bank[0].br));
-	cs1_addr = lbc_br_to_phys(ecm, num_laws, in_be32(&lbc->bank[1].br));
+	/*
+	 * Indirect mode requires both BR0 and BR1 to be set to "GPCM",
+	 * otherwise writes to these addresses won't actually appear on the
+	 * local bus, and so the PIXIS won't see them.
+	 *
+	 * In FCM mode, writes go to the NAND controller, which does not pass
+	 * them to the localbus directly.  So we force BR0 and BR1 into GPCM
+	 * mode, since we don't care about what's behind the localbus any
+	 * more.
+	 */
+	br0 = in_be32(&lbc->bank[0].br);
+	br1 = in_be32(&lbc->bank[1].br);
+	or0 = in_be32(&lbc->bank[0].or);
+	or1 = in_be32(&lbc->bank[1].or);
+
+	/* Make sure CS0 and CS1 are programmed */
+	if (!(br0 & BR_V) || !(br1 & BR_V)) {
+		pr_err("p1022ds: CS0 and/or CS1 is not programmed\n");
+		goto exit;
+	}
+
+	/*
+	 * Use the existing BRx/ORx values if it's already GPCM. Otherwise,
+	 * force the values to simple 32KB GPCM windows with the most
+	 * conservative timing.
+	 */
+	if ((br0 & BR_MSEL) != BR_MS_GPCM) {
+		br0 = (br0 & BR_BA) | BR_V;
+		or0 = 0xFFFF8000 | 0xFF7;
+		out_be32(&lbc->bank[0].br, br0);
+		out_be32(&lbc->bank[0].or, or0);
+	}
+	if ((br1 & BR_MSEL) != BR_MS_GPCM) {
+		br1 = (br1 & BR_BA) | BR_V;
+		or1 = 0xFFFF8000 | 0xFF7;
+		out_be32(&lbc->bank[1].br, br1);
+		out_be32(&lbc->bank[1].or, or1);
+	}
+
+	cs0_addr = lbc_br_to_phys(ecm, num_laws, br0);
+	if (!cs0_addr) {
+		pr_err("p1022ds: could not determine physical address for CS0"
+		       " (BR0=%08x)\n", br0);
+		goto exit;
+	}
+	cs1_addr = lbc_br_to_phys(ecm, num_laws, br1);
+	if (!cs0_addr) {
+		pr_err("p1022ds: could not determine physical address for CS1"
+		       " (BR1=%08x)\n", br1);
+		goto exit;
+	}
 
 	lbc_lcs0_ba = ioremap(cs0_addr, 1);
+	if (!lbc_lcs0_ba) {
+		pr_err("p1022ds: could not ioremap CS0 address %llx\n",
+		       (unsigned long long)cs0_addr);
+		goto exit;
+	}
 	lbc_lcs1_ba = ioremap(cs1_addr, 1);
+	if (!lbc_lcs1_ba) {
+		pr_err("p1022ds: could not ioremap CS1 address %llx\n",
+		       (unsigned long long)cs1_addr);
+		goto exit;
+	}
 
 	/* Make sure we're in indirect mode first. */
 	if ((in_be32(&guts->pmuxcr) & PMUXCR_ELBCDIU_MASK) !=
@@ -419,18 +479,6 @@ void __init p1022_ds_pic_init(void)
 
 #if defined(CONFIG_FB_FSL_DIU) || defined(CONFIG_FB_FSL_DIU_MODULE)
 
-/*
- * Disables a node in the device tree.
- *
- * This function is called before kmalloc() is available, so the 'new' object
- * should be allocated in the global area.  The easiest way is to do that is
- * to allocate one static local variable for each call to this function.
- */
-static void __init disable_one_node(struct device_node *np, struct property *new)
-{
-	prom_update_property(np, new);
-}
-
 /* TRUE if there is a "video=fslfb" command-line parameter. */
 static bool fslfb;
 
@@ -493,28 +541,58 @@ static void __init p1022_ds_setup_arch(void)
 	diu_ops.valid_monitor_port	= p1022ds_valid_monitor_port;
 
 	/*
-	 * Disable the NOR flash node if there is video=fslfb... command-line
-	 * parameter.  When the DIU is active, NOR flash is unavailable, so we
-	 * have to disable the node before the MTD driver loads.
+	 * Disable the NOR and NAND flash nodes if there is video=fslfb...
+	 * command-line parameter.  When the DIU is active, the localbus is
+	 * unavailable, so we have to disable these nodes before the MTD
+	 * driver loads.
 	 */
 	if (fslfb) {
 		struct device_node *np =
 			of_find_compatible_node(NULL, NULL, "fsl,p1022-elbc");
 
 		if (np) {
-			np = of_find_compatible_node(np, NULL, "cfi-flash");
-			if (np) {
+			struct device_node *np2;
+
+			of_node_get(np);
+			np2 = of_find_compatible_node(np, NULL, "cfi-flash");
+			if (np2) {
 				static struct property nor_status = {
 					.name = "status",
 					.value = "disabled",
 					.length = sizeof("disabled"),
 				};
 
+				/*
+				 * prom_update_property() is called before
+				 * kmalloc() is available, so the 'new' object
+				 * should be allocated in the global area.
+				 * The easiest way is to do that is to
+				 * allocate one static local variable for each
+				 * call to this function.
+				 */
 				pr_info("p1022ds: disabling %s node",
-					np->full_name);
-				disable_one_node(np, &nor_status);
-				of_node_put(np);
+					np2->full_name);
+				prom_update_property(np2, &nor_status);
+				of_node_put(np2);
 			}
+
+			of_node_get(np);
+			np2 = of_find_compatible_node(np, NULL,
+						      "fsl,elbc-fcm-nand");
+			if (np2) {
+				static struct property nand_status = {
+					.name = "status",
+					.value = "disabled",
+					.length = sizeof("disabled"),
+				};
+
+				pr_info("p1022ds: disabling %s node",
+					np2->full_name);
+				prom_update_property(np2, &nand_status);
+				of_node_put(np2);
+			}
+
+			of_node_put(np);
 		}
 
 	}
diff --git a/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h b/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h
index 60c9c0bd5ba2..2aa97ddb7b78 100644
--- a/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h
+++ b/arch/powerpc/sysdev/fsl_85xx_cache_ctlr.h
@@ -1,5 +1,5 @@
 /*
- * Copyright 2009-2010 Freescale Semiconductor, Inc
+ * Copyright 2009-2010, 2012 Freescale Semiconductor, Inc
  *
  * QorIQ based Cache Controller Memory Mapped Registers
  *
@@ -91,7 +91,7 @@ struct mpc85xx_l2ctlr {
 
 struct sram_parameters {
 	unsigned int sram_size;
-	uint64_t sram_offset;
+	phys_addr_t sram_offset;
 };
 
 extern int instantiate_cache_sram(struct platform_device *dev,
diff --git a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
index cedabd0f4bfe..68ac3aacb191 100644
--- a/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
+++ b/arch/powerpc/sysdev/fsl_85xx_l2ctlr.c
@@ -1,5 +1,5 @@
 /*
- * Copyright 2009-2010 Freescale Semiconductor, Inc.
+ * Copyright 2009-2010, 2012 Freescale Semiconductor, Inc.
  *
  * QorIQ (P1/P2) L2 controller init for Cache-SRAM instantiation
  *
@@ -31,24 +31,21 @@ static char *sram_size;
 static char *sram_offset;
 struct mpc85xx_l2ctlr __iomem *l2ctlr;
 
-static long get_cache_sram_size(void)
+static int get_cache_sram_params(struct sram_parameters *sram_params)
 {
-	unsigned long val;
+	unsigned long long addr;
+	unsigned int size;
 
-	if (!sram_size || (strict_strtoul(sram_size, 0, &val) < 0))
+	if (!sram_size || (kstrtouint(sram_size, 0, &size) < 0))
 		return -EINVAL;
 
-	return val;
-}
-
-static long get_cache_sram_offset(void)
-{
-	unsigned long val;
-
-	if (!sram_offset || (strict_strtoul(sram_offset, 0, &val) < 0))
+	if (!sram_offset || (kstrtoull(sram_offset, 0, &addr) < 0))
 		return -EINVAL;
 
-	return val;
+	sram_params->sram_offset = addr;
+	sram_params->sram_size = size;
+
+	return 0;
 }
 
 static int __init get_size_from_cmdline(char *str)
@@ -93,17 +90,9 @@ static int __devinit mpc85xx_l2ctlr_of_probe(struct platform_device *dev)
 	}
 	l2cache_size = *prop;
 
-	sram_params.sram_size  = get_cache_sram_size();
-	if ((int)sram_params.sram_size <= 0) {
-		dev_err(&dev->dev,
-			"Entire L2 as cache, Aborting Cache-SRAM stuff\n");
-		return -EINVAL;
-	}
-
-	sram_params.sram_offset  = get_cache_sram_offset();
-	if ((int64_t)sram_params.sram_offset <= 0) {
+	if (get_cache_sram_params(&sram_params)) {
 		dev_err(&dev->dev,
-			"Entire L2 as cache, provide a valid sram offset\n");
+			"Entire L2 as cache, provide valid sram offset and size\n");
 		return -EINVAL;
 	}
 
@@ -125,14 +114,14 @@ static int __devinit mpc85xx_l2ctlr_of_probe(struct platform_device *dev)
 	 * Write bits[0-17] to srbar0
 	 */
 	out_be32(&l2ctlr->srbar0,
-		sram_params.sram_offset & L2SRAM_BAR_MSK_LO18);
+		lower_32_bits(sram_params.sram_offset) & L2SRAM_BAR_MSK_LO18);
 
 	/*
 	 * Write bits[18-21] to srbare0
 	 */
 #ifdef CONFIG_PHYS_64BIT
 	out_be32(&l2ctlr->srbarea0,
-		(sram_params.sram_offset >> 32) & L2SRAM_BARE_MSK_HI4);
+		upper_32_bits(sram_params.sram_offset) & L2SRAM_BARE_MSK_HI4);
 #endif
 
 	clrsetbits_be32(&l2ctlr->ctl, L2CR_L2E, L2CR_L2FI);
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index a39b4690c171..76de6b68487c 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -85,10 +85,12 @@ config S390
 	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
 	select ARCH_SAVE_PAGE_KEYS if HIBERNATION
+	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_CMPXCHG_LOCAL
 	select ARCH_DISCARD_MEMBLOCK
+	select BUILDTIME_EXTABLE_SORT
 	select ARCH_INLINE_SPIN_TRYLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK_BH
 	select ARCH_INLINE_SPIN_LOCK
@@ -117,6 +119,7 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_BH
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select GENERIC_CLOCKEVENTS
diff --git a/arch/s390/crypto/crypto_des.h b/arch/s390/crypto/crypto_des.h
deleted file mode 100644
index 6210457ceebb..000000000000
--- a/arch/s390/crypto/crypto_des.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * Cryptographic API.
- *
- * Function for checking keys for the DES and Tripple DES Encryption
- * algorithms.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- */
-#ifndef __CRYPTO_DES_H__
-#define __CRYPTO_DES_H__
-
-extern int crypto_des_check_key(const u8*, unsigned int, u32*);
-
-#endif /*__CRYPTO_DES_H__*/
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 37d2bf267964..f39cd710980b 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -7,13 +7,16 @@ CONFIG_TASK_DELAY_ACCT=y
 CONFIG_TASK_XACCT=y
 CONFIG_TASK_IO_ACCOUNTING=y
 CONFIG_AUDIT=y
+CONFIG_NO_HZ=y
+CONFIG_HIGH_RES_TIMERS=y
+CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_IKCONFIG=y
 CONFIG_IKCONFIG_PROC=y
 CONFIG_CGROUPS=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
@@ -35,8 +38,6 @@ CONFIG_MODVERSIONS=y
 CONFIG_PARTITION_ADVANCED=y
 CONFIG_IBM_PARTITION=y
 CONFIG_DEFAULT_DEADLINE=y
-CONFIG_NO_HZ=y
-CONFIG_HIGH_RES_TIMERS=y
 CONFIG_PREEMPT=y
 CONFIG_MEMORY_HOTPLUG=y
 CONFIG_MEMORY_HOTREMOVE=y
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index 5c63615f1349..b749c5733657 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -11,7 +11,6 @@
 #include <asm/uaccess.h>
 #include <asm/tlbflush.h>
 #include <asm/ctl_reg.h>
-#include <asm-generic/mm_hooks.h>
 
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
@@ -58,7 +57,7 @@ static inline void update_mm(struct mm_struct *mm, struct task_struct *tsk)
 	pgd_t *pgd = mm->pgd;
 
 	S390_lowcore.user_asce = mm->context.asce_bits | __pa(pgd);
-	if (user_mode != HOME_SPACE_MODE) {
+	if (addressing_mode != HOME_SPACE_MODE) {
 		/* Load primary space page table origin. */
 		asm volatile(LCTL_OPCODE" 1,1,%0\n"
 			     : : "m" (S390_lowcore.user_asce) );
@@ -91,4 +90,17 @@ static inline void activate_mm(struct mm_struct *prev,
         switch_mm(prev, next, current);
 }
 
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+#ifdef CONFIG_64BIT
+	if (oldmm->context.asce_limit < mm->context.asce_limit)
+		crst_table_downgrade(mm, oldmm->context.asce_limit);
+#endif
+}
+
+static inline void arch_exit_mmap(struct mm_struct *mm)
+{
+}
+
 #endif /* __S390_MMU_CONTEXT_H */
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index c40fa91e38a8..11e4e3236937 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -120,7 +120,9 @@ struct stack_frame {
 	regs->psw.mask	= psw_user_bits | PSW_MASK_BA;			\
 	regs->psw.addr	= new_psw | PSW_ADDR_AMODE;			\
 	regs->gprs[15]	= new_stackp;					\
+	__tlb_flush_mm(current->mm);					\
 	crst_table_downgrade(current->mm, 1UL << 31);			\
+	update_mm(current->mm, current);				\
 } while (0)
 
 /* Forward declaration, a strange C thing */
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 57e80534375a..e6859d16ee2d 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -60,7 +60,7 @@ void create_mem_hole(struct mem_chunk memory_chunk[], unsigned long addr,
 #define SECONDARY_SPACE_MODE	2
 #define HOME_SPACE_MODE		3
 
-extern unsigned int user_mode;
+extern unsigned int addressing_mode;
 
 /*
  * Machine features detected in head.S
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 2e37157ba6a9..6756e78f4808 100644
--- a/arch/s390/include/asm/unistd.h
+++ b/arch/s390/include/asm/unistd.h
@@ -388,7 +388,6 @@
 #define __IGNORE_recvmmsg
 #define __IGNORE_sendmmsg
 
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_SYS_ALARM
 #define __ARCH_WANT_SYS_GETHOSTNAME
diff --git a/arch/s390/kernel/debug.c b/arch/s390/kernel/debug.c
index 21be961e8a43..ba500d8dc392 100644
--- a/arch/s390/kernel/debug.c
+++ b/arch/s390/kernel/debug.c
@@ -110,6 +110,7 @@ struct debug_view debug_raw_view = {
 	NULL,
 	NULL
 };
+EXPORT_SYMBOL(debug_raw_view);
 
 struct debug_view debug_hex_ascii_view = {
 	"hex_ascii",
@@ -119,6 +120,7 @@ struct debug_view debug_hex_ascii_view = {
 	NULL,
 	NULL
 };
+EXPORT_SYMBOL(debug_hex_ascii_view);
 
 static struct debug_view debug_level_view = {
 	"level",
@@ -155,6 +157,7 @@ struct debug_view debug_sprintf_view = {
 	NULL,
 	NULL
 };
+EXPORT_SYMBOL(debug_sprintf_view);
 
 /* used by dump analysis tools to determine version of debug feature */
 static unsigned int __used debug_feature_version = __DEBUG_FEATURE_VERSION;
@@ -730,6 +733,7 @@ debug_info_t *debug_register(const char *name, int pages_per_area,
 	return debug_register_mode(name, pages_per_area, nr_areas, buf_size,
 				   S_IRUSR | S_IWUSR, 0, 0);
 }
+EXPORT_SYMBOL(debug_register);
 
 /*
  * debug_unregister:
@@ -748,6 +752,7 @@ debug_unregister(debug_info_t * id)
 out:
 	return;
 }
+EXPORT_SYMBOL(debug_unregister);
 
 /*
  * debug_set_size:
@@ -810,7 +815,7 @@ debug_set_level(debug_info_t* id, int new_level)
         }
 	spin_unlock_irqrestore(&id->lock,flags);
 }
-
+EXPORT_SYMBOL(debug_set_level);
 
 /*
  * proceed_active_entry:
@@ -930,7 +935,7 @@ debug_stop_all(void)
 	if (debug_stoppable)
 		debug_active = 0;
 }
-
+EXPORT_SYMBOL(debug_stop_all);
 
 void debug_set_critical(void)
 {
@@ -963,6 +968,7 @@ debug_event_common(debug_info_t * id, int level, const void *buf, int len)
 
 	return active;
 }
+EXPORT_SYMBOL(debug_event_common);
 
 /*
  * debug_exception_common:
@@ -990,6 +996,7 @@ debug_entry_t
 
 	return active;
 }
+EXPORT_SYMBOL(debug_exception_common);
 
 /*
  * counts arguments in format string for sprintf view
@@ -1043,6 +1050,7 @@ debug_sprintf_event(debug_info_t* id, int level,char *string,...)
 
 	return active;
 }
+EXPORT_SYMBOL(debug_sprintf_event);
 
 /*
  * debug_sprintf_exception:
@@ -1081,25 +1089,7 @@ debug_sprintf_exception(debug_info_t* id, int level,char *string,...)
 
 	return active;
 }
-
-/*
- * debug_init:
- * - is called exactly once to initialize the debug feature
- */
-
-static int
-__init debug_init(void)
-{
-	int rc = 0;
-
-	s390dbf_sysctl_header = register_sysctl_table(s390dbf_dir_table);
-	mutex_lock(&debug_mutex);
-	debug_debugfs_root_entry = debugfs_create_dir(DEBUG_DIR_ROOT,NULL);
-	initialized = 1;
-	mutex_unlock(&debug_mutex);
-
-	return rc;
-}
+EXPORT_SYMBOL(debug_sprintf_exception);
 
 /*
  * debug_register_view:
@@ -1147,6 +1137,7 @@ debug_register_view(debug_info_t * id, struct debug_view *view)
 out:
 	return rc;
 }
+EXPORT_SYMBOL(debug_register_view);
 
 /*
  * debug_unregister_view:
@@ -1176,6 +1167,7 @@ debug_unregister_view(debug_info_t * id, struct debug_view *view)
 out:
 	return rc;
 }
+EXPORT_SYMBOL(debug_unregister_view);
 
 static inline char *
 debug_get_user_string(const char __user *user_buf, size_t user_len)
@@ -1485,6 +1477,7 @@ debug_dflt_header_fn(debug_info_t * id, struct debug_view *view,
 		      except_str, entry->id.fields.cpuid, (void *) caller);
 	return rc;
 }
+EXPORT_SYMBOL(debug_dflt_header_fn);
 
 /*
  * prints debug data sprintf-formated:
@@ -1533,33 +1526,16 @@ out:
 }
 
 /*
- * clean up module
+ * debug_init:
+ * - is called exactly once to initialize the debug feature
  */
-static void __exit debug_exit(void)
+static int __init debug_init(void)
 {
-	debugfs_remove(debug_debugfs_root_entry);
-	unregister_sysctl_table(s390dbf_sysctl_header);
-	return;
+	s390dbf_sysctl_header = register_sysctl_table(s390dbf_dir_table);
+	mutex_lock(&debug_mutex);
+	debug_debugfs_root_entry = debugfs_create_dir(DEBUG_DIR_ROOT, NULL);
+	initialized = 1;
+	mutex_unlock(&debug_mutex);
+	return 0;
 }
-
-/*
- * module definitions
- */
 postcore_initcall(debug_init);
-module_exit(debug_exit);
-MODULE_LICENSE("GPL");
-
-EXPORT_SYMBOL(debug_register);
-EXPORT_SYMBOL(debug_unregister); 
-EXPORT_SYMBOL(debug_set_level);
-EXPORT_SYMBOL(debug_stop_all);
-EXPORT_SYMBOL(debug_register_view);
-EXPORT_SYMBOL(debug_unregister_view);
-EXPORT_SYMBOL(debug_event_common);
-EXPORT_SYMBOL(debug_exception_common);
-EXPORT_SYMBOL(debug_hex_ascii_view);
-EXPORT_SYMBOL(debug_raw_view);
-EXPORT_SYMBOL(debug_dflt_header_fn);
-EXPORT_SYMBOL(debug_sprintf_view);
-EXPORT_SYMBOL(debug_sprintf_exception);
-EXPORT_SYMBOL(debug_sprintf_event);
diff --git a/arch/s390/kernel/dis.c b/arch/s390/kernel/dis.c
index 1f6b428e2762..619c5d350726 100644
--- a/arch/s390/kernel/dis.c
+++ b/arch/s390/kernel/dis.c
@@ -1531,7 +1531,7 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 
 void show_code(struct pt_regs *regs)
 {
-	char *mode = (regs->psw.mask & PSW_MASK_PSTATE) ? "User" : "Krnl";
+	char *mode = user_mode(regs) ? "User" : "Krnl";
 	unsigned char code[64];
 	char buffer[64], *ptr;
 	mm_segment_t old_fs;
@@ -1540,7 +1540,7 @@ void show_code(struct pt_regs *regs)
 
 	/* Get a snapshot of the 64 bytes surrounding the fault address. */
 	old_fs = get_fs();
-	set_fs((regs->psw.mask & PSW_MASK_PSTATE) ? USER_DS : KERNEL_DS);
+	set_fs(user_mode(regs) ? USER_DS : KERNEL_DS);
 	for (start = 32; start && regs->psw.addr >= 34 - start; start -= 2) {
 		addr = regs->psw.addr - 34 + start;
 		if (__copy_from_user(code + start - 2,
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index bc95a8ebd9cc..83c3271c442b 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -455,7 +455,6 @@ void __init startup_init(void)
 	init_kernel_storage_key();
 	lockdep_init();
 	lockdep_off();
-	sort_main_extable();
 	setup_lowcore_early();
 	setup_facility_list();
 	detect_machine_type();
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index e64d141555ce..6ffcd3203215 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -1583,7 +1583,7 @@ static struct kset *vmcmd_kset;
 
 static void vmcmd_run(struct shutdown_trigger *trigger)
 {
-	char *cmd, *next_cmd;
+	char *cmd;
 
 	if (strcmp(trigger->name, ON_REIPL_STR) == 0)
 		cmd = vmcmd_on_reboot;
@@ -1600,15 +1600,7 @@ static void vmcmd_run(struct shutdown_trigger *trigger)
 
 	if (strlen(cmd) == 0)
 		return;
-	do {
-		next_cmd = strchr(cmd, '\n');
-		if (next_cmd) {
-			next_cmd[0] = 0;
-			next_cmd += 1;
-		}
-		__cpcmd(cmd, NULL, 0, NULL);
-		cmd = next_cmd;
-	} while (cmd != NULL);
+	__cpcmd(cmd, NULL, 0, NULL);
 }
 
 static int vmcmd_init(void)
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index 743c0f32fe3b..f86c81e13c37 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -302,8 +302,8 @@ static int __init parse_vmalloc(char *arg)
 }
 early_param("vmalloc", parse_vmalloc);
 
-unsigned int user_mode = HOME_SPACE_MODE;
-EXPORT_SYMBOL_GPL(user_mode);
+unsigned int addressing_mode = HOME_SPACE_MODE;
+EXPORT_SYMBOL_GPL(addressing_mode);
 
 static int set_amode_primary(void)
 {
@@ -328,7 +328,7 @@ static int set_amode_primary(void)
  */
 static int __init early_parse_switch_amode(char *p)
 {
-	user_mode = PRIMARY_SPACE_MODE;
+	addressing_mode = PRIMARY_SPACE_MODE;
 	return 0;
 }
 early_param("switch_amode", early_parse_switch_amode);
@@ -336,9 +336,9 @@ early_param("switch_amode", early_parse_switch_amode);
 static int __init early_parse_user_mode(char *p)
 {
 	if (p && strcmp(p, "primary") == 0)
-		user_mode = PRIMARY_SPACE_MODE;
+		addressing_mode = PRIMARY_SPACE_MODE;
 	else if (!p || strcmp(p, "home") == 0)
-		user_mode = HOME_SPACE_MODE;
+		addressing_mode = HOME_SPACE_MODE;
 	else
 		return 1;
 	return 0;
@@ -347,7 +347,7 @@ early_param("user_mode", early_parse_user_mode);
 
 static void setup_addressing_mode(void)
 {
-	if (user_mode == PRIMARY_SPACE_MODE) {
+	if (addressing_mode == PRIMARY_SPACE_MODE) {
 		if (set_amode_primary())
 			pr_info("Address spaces switched, "
 				"mvcos available\n");
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index af2421a0f315..01775c04a90e 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -185,7 +185,7 @@ void show_registers(struct pt_regs *regs)
 {
 	char *mode;
 
-	mode = (regs->psw.mask & PSW_MASK_PSTATE) ? "User" : "Krnl";
+	mode = user_mode(regs) ? "User" : "Krnl";
 	printk("%s PSW : %p %p",
 	       mode, (void *) regs->psw.mask,
 	       (void *) regs->psw.addr);
@@ -225,7 +225,7 @@ void show_regs(struct pt_regs *regs)
 	       (void *) current->thread.ksp);
 	show_registers(regs);
 	/* Show stack backtrace if pt_regs is from kernel mode */
-	if (!(regs->psw.mask & PSW_MASK_PSTATE))
+	if (!user_mode(regs))
 		show_trace(NULL, (unsigned long *) regs->gprs[15]);
 	show_last_breaking_event(regs);
 }
@@ -300,7 +300,7 @@ static void __kprobes do_trap(struct pt_regs *regs,
 		       regs->int_code, si_signo) == NOTIFY_STOP)
 		return;
 
-        if (regs->psw.mask & PSW_MASK_PSTATE) {
+	if (user_mode(regs)) {
 		info.si_signo = si_signo;
 		info.si_errno = 0;
 		info.si_code = si_code;
@@ -341,7 +341,7 @@ void __kprobes do_per_trap(struct pt_regs *regs)
 
 static void default_trap_handler(struct pt_regs *regs)
 {
-        if (regs->psw.mask & PSW_MASK_PSTATE) {
+	if (user_mode(regs)) {
 		report_user_fault(regs, SIGSEGV);
 		do_exit(SIGSEGV);
 	} else
@@ -410,7 +410,7 @@ static void __kprobes illegal_op(struct pt_regs *regs)
 
 	location = get_psw_address(regs);
 
-	if (regs->psw.mask & PSW_MASK_PSTATE) {
+	if (user_mode(regs)) {
 		if (get_user(*((__u16 *) opcode), (__u16 __user *) location))
 			return;
 		if (*((__u16 *) opcode) == S390_BREAKPOINT_U16) {
@@ -478,7 +478,7 @@ void specification_exception(struct pt_regs *regs)
 
 	location = (__u16 __user *) get_psw_address(regs);
 
-        if (regs->psw.mask & PSW_MASK_PSTATE) {
+	if (user_mode(regs)) {
 		get_user(*((__u16 *) opcode), location);
 		switch (opcode[0]) {
 		case 0x28: /* LDR Rx,Ry   */
@@ -531,7 +531,7 @@ static void data_exception(struct pt_regs *regs)
 		asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
 
 #ifdef CONFIG_MATHEMU
-        else if (regs->psw.mask & PSW_MASK_PSTATE) {
+	else if (user_mode(regs)) {
         	__u8 opcode[6];
 		get_user(*((__u16 *) opcode), location);
 		switch (opcode[0]) {
@@ -598,7 +598,7 @@ static void data_exception(struct pt_regs *regs)
 static void space_switch_exception(struct pt_regs *regs)
 {
 	/* Set user psw back to home space mode. */
-	if (regs->psw.mask & PSW_MASK_PSTATE)
+	if (user_mode(regs))
 		regs->psw.mask |= PSW_ASC_HOME;
 	/* Send SIGILL. */
 	do_trap(regs, SIGILL, ILL_PRVOPC, "space switch event");
diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index ea5590fdca3b..9a19ca367c17 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -84,7 +84,8 @@ struct vdso_data *vdso_data = &vdso_data_store.data;
  */
 static void vdso_init_data(struct vdso_data *vd)
 {
-	vd->ectg_available = user_mode != HOME_SPACE_MODE && test_facility(31);
+	vd->ectg_available =
+		addressing_mode != HOME_SPACE_MODE && test_facility(31);
 }
 
 #ifdef CONFIG_64BIT
@@ -101,7 +102,7 @@ int vdso_alloc_per_cpu(struct _lowcore *lowcore)
 
 	lowcore->vdso_per_cpu_data = __LC_PASTE;
 
-	if (user_mode == HOME_SPACE_MODE || !vdso_enabled)
+	if (addressing_mode == HOME_SPACE_MODE || !vdso_enabled)
 		return 0;
 
 	segment_table = __get_free_pages(GFP_KERNEL, SEGMENT_ORDER);
@@ -146,7 +147,7 @@ void vdso_free_per_cpu(struct _lowcore *lowcore)
 	unsigned long segment_table, page_table, page_frame;
 	u32 *psal, *aste;
 
-	if (user_mode == HOME_SPACE_MODE || !vdso_enabled)
+	if (addressing_mode == HOME_SPACE_MODE || !vdso_enabled)
 		return;
 
 	psal = (u32 *)(addr_t) lowcore->paste[4];
@@ -164,7 +165,7 @@ static void vdso_init_cr5(void)
 {
 	unsigned long cr5;
 
-	if (user_mode == HOME_SPACE_MODE || !vdso_enabled)
+	if (addressing_mode == HOME_SPACE_MODE || !vdso_enabled)
 		return;
 	cr5 = offsetof(struct _lowcore, paste);
 	__ctl_load(cr5, 5, 5);
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 21109c63eb12..de8fa9bbd35e 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -45,7 +45,7 @@ SECTIONS
 
 	.dummy : { *(.dummy) } :data
 
-	RODATA
+	RO_DATA_SECTION(PAGE_SIZE)
 
 #ifdef CONFIG_SHARED_KERNEL
 	. = ALIGN(0x100000);	/* VM shared segments are 1MB aligned */
diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index 6a12d1bb6e09..6c013f544146 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -49,6 +49,7 @@
 #define VM_FAULT_BADCONTEXT	0x010000
 #define VM_FAULT_BADMAP		0x020000
 #define VM_FAULT_BADACCESS	0x040000
+#define VM_FAULT_SIGNAL	0x080000
 
 static unsigned long store_indication;
 
@@ -110,7 +111,7 @@ static inline int user_space_fault(unsigned long trans_exc_code)
 	if (trans_exc_code == 2)
 		/* Access via secondary space, set_fs setting decides */
 		return current->thread.mm_segment.ar4;
-	if (user_mode == HOME_SPACE_MODE)
+	if (addressing_mode == HOME_SPACE_MODE)
 		/* User space if the access has been done via home space. */
 		return trans_exc_code == 3;
 	/*
@@ -219,7 +220,7 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault)
 	case VM_FAULT_BADACCESS:
 	case VM_FAULT_BADMAP:
 		/* Bad memory access. Check if it is kernel or user space. */
-		if (regs->psw.mask & PSW_MASK_PSTATE) {
+		if (user_mode(regs)) {
 			/* User mode accesses just cause a SIGSEGV */
 			si_code = (fault == VM_FAULT_BADMAP) ?
 				SEGV_MAPERR : SEGV_ACCERR;
@@ -229,15 +230,19 @@ static noinline void do_fault_error(struct pt_regs *regs, int fault)
 	case VM_FAULT_BADCONTEXT:
 		do_no_context(regs);
 		break;
+	case VM_FAULT_SIGNAL:
+		if (!user_mode(regs))
+			do_no_context(regs);
+		break;
 	default: /* fault & VM_FAULT_ERROR */
 		if (fault & VM_FAULT_OOM) {
-			if (!(regs->psw.mask & PSW_MASK_PSTATE))
+			if (!user_mode(regs))
 				do_no_context(regs);
 			else
 				pagefault_out_of_memory();
 		} else if (fault & VM_FAULT_SIGBUS) {
 			/* Kernel mode? Handle exceptions or die */
-			if (!(regs->psw.mask & PSW_MASK_PSTATE))
+			if (!user_mode(regs))
 				do_no_context(regs);
 			else
 				do_sigbus(regs);
@@ -286,7 +291,7 @@ static inline int do_exception(struct pt_regs *regs, int access)
 
 	address = trans_exc_code & __FAIL_ADDR_MASK;
 	perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, address);
-	flags = FAULT_FLAG_ALLOW_RETRY;
+	flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 	if (access == VM_WRITE || (trans_exc_code & store_indication) == 0x400)
 		flags |= FAULT_FLAG_WRITE;
 	down_read(&mm->mmap_sem);
@@ -335,6 +340,11 @@ retry:
 	 * the fault.
 	 */
 	fault = handle_mm_fault(mm, vma, address, flags);
+	/* No reason to continue if interrupted by SIGKILL. */
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
+		fault = VM_FAULT_SIGNAL;
+		goto out;
+	}
 	if (unlikely(fault & VM_FAULT_ERROR))
 		goto out_up;
 
@@ -426,7 +436,7 @@ void __kprobes do_asce_exception(struct pt_regs *regs)
 	}
 
 	/* User mode accesses just cause a SIGSEGV */
-	if (regs->psw.mask & PSW_MASK_PSTATE) {
+	if (user_mode(regs)) {
 		do_sigsegv(regs, SEGV_MAPERR);
 		return;
 	}
@@ -441,6 +451,7 @@ int __handle_fault(unsigned long uaddr, unsigned long pgm_int_code, int write)
 	struct pt_regs regs;
 	int access, fault;
 
+	/* Emulate a uaccess fault from kernel mode. */
 	regs.psw.mask = psw_kernel_bits | PSW_MASK_DAT | PSW_MASK_MCHECK;
 	if (!irqs_disabled())
 		regs.psw.mask |= PSW_MASK_IO | PSW_MASK_EXT;
@@ -450,12 +461,12 @@ int __handle_fault(unsigned long uaddr, unsigned long pgm_int_code, int write)
 	regs.int_parm_long = (uaddr & PAGE_MASK) | 2;
 	access = write ? VM_WRITE : VM_READ;
 	fault = do_exception(&regs, access);
-	if (unlikely(fault)) {
-		if (fault & VM_FAULT_OOM)
-			return -EFAULT;
-		else if (fault & VM_FAULT_SIGBUS)
-			do_sigbus(&regs);
-	}
+	/*
+	 * Since the fault happened in kernel mode while performing a uaccess
+	 * all we need to do now is emulating a fixup in case "fault" is not
+	 * zero.
+	 * For the calling uaccess functions this results always in -EFAULT.
+	 */
 	return fault ? -EFAULT : 0;
 }
 
diff --git a/arch/s390/mm/mmap.c b/arch/s390/mm/mmap.c
index 573384256c5c..c59a5efa58b1 100644
--- a/arch/s390/mm/mmap.c
+++ b/arch/s390/mm/mmap.c
@@ -103,9 +103,15 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 
 int s390_mmap_check(unsigned long addr, unsigned long len)
 {
+	int rc;
+
 	if (!is_compat_task() &&
-	    len >= TASK_SIZE && TASK_SIZE < (1UL << 53))
-		return crst_table_upgrade(current->mm, 1UL << 53);
+	    len >= TASK_SIZE && TASK_SIZE < (1UL << 53)) {
+		rc = crst_table_upgrade(current->mm, 1UL << 53);
+		if (rc)
+			return rc;
+		update_mm(current->mm, current);
+	}
 	return 0;
 }
 
@@ -125,6 +131,7 @@ s390_get_unmapped_area(struct file *filp, unsigned long addr,
 		rc = crst_table_upgrade(mm, 1UL << 53);
 		if (rc)
 			return (unsigned long) rc;
+		update_mm(mm, current);
 		area = arch_get_unmapped_area(filp, addr, len, pgoff, flags);
 	}
 	return area;
@@ -147,6 +154,7 @@ s390_get_unmapped_area_topdown(struct file *filp, const unsigned long addr,
 		rc = crst_table_upgrade(mm, 1UL << 53);
 		if (rc)
 			return (unsigned long) rc;
+		update_mm(mm, current);
 		area = arch_get_unmapped_area_topdown(filp, addr, len,
 						      pgoff, flags);
 	}
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 1cab221077cc..18df31d1f2c9 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -85,7 +85,6 @@ repeat:
 		crst_table_free(mm, table);
 	if (mm->context.asce_limit < limit)
 		goto repeat;
-	update_mm(mm, current);
 	return 0;
 }
 
@@ -93,9 +92,6 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
 {
 	pgd_t *pgd;
 
-	if (mm->context.asce_limit <= limit)
-		return;
-	__tlb_flush_mm(mm);
 	while (mm->context.asce_limit > limit) {
 		pgd = mm->pgd;
 		switch (pgd_val(*pgd) & _REGION_ENTRY_TYPE_MASK) {
@@ -118,7 +114,6 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
 		mm->task_size = mm->context.asce_limit;
 		crst_table_free(mm, (unsigned long *) pgd);
 	}
-	update_mm(mm, current);
 }
 #endif
 
@@ -801,7 +796,7 @@ int s390_enable_sie(void)
 	struct mm_struct *mm, *old_mm;
 
 	/* Do we have switched amode? If no, we cannot do sie */
-	if (user_mode == HOME_SPACE_MODE)
+	if (addressing_mode == HOME_SPACE_MODE)
 		return -EINVAL;
 
 	/* Do we have pgstes? if yes, we are done */
diff --git a/arch/s390/oprofile/backtrace.c b/arch/s390/oprofile/backtrace.c
index c82f62fb9c28..8a6811b2cdb9 100644
--- a/arch/s390/oprofile/backtrace.c
+++ b/arch/s390/oprofile/backtrace.c
@@ -58,7 +58,7 @@ void s390_backtrace(struct pt_regs * const regs, unsigned int depth)
 	unsigned long head;
 	struct stack_frame* head_sf;
 
-	if (user_mode (regs))
+	if (user_mode(regs))
 		return;
 
 	head = regs->gprs[15];
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index a24595d83ad6..36f5141e8041 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -21,6 +21,7 @@ config SUPERH
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_XZ
 	select HAVE_KERNEL_LZO
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_GENERIC_HARDIRQS
@@ -50,6 +51,7 @@ config SUPERH32
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_ARCH_KGDB
 	select HAVE_HW_BREAKPOINT
diff --git a/arch/sh/configs/apsh4ad0a_defconfig b/arch/sh/configs/apsh4ad0a_defconfig
index e7583484cc07..95ae23fcfdd6 100644
--- a/arch/sh/configs/apsh4ad0a_defconfig
+++ b/arch/sh/configs/apsh4ad0a_defconfig
@@ -11,7 +11,7 @@ CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_BLK_CGROUP=y
 CONFIG_NAMESPACES=y
 CONFIG_BLK_DEV_INITRD=y
diff --git a/arch/sh/configs/sdk7786_defconfig b/arch/sh/configs/sdk7786_defconfig
index 8a7dd7b59c5c..76a76a295d74 100644
--- a/arch/sh/configs/sdk7786_defconfig
+++ b/arch/sh/configs/sdk7786_defconfig
@@ -18,8 +18,8 @@ CONFIG_CPUSETS=y
 # CONFIG_PROC_PID_CPUSET is not set
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y
diff --git a/arch/sh/configs/se7206_defconfig b/arch/sh/configs/se7206_defconfig
index 72c3fad7383f..6bc30ab9fd18 100644
--- a/arch/sh/configs/se7206_defconfig
+++ b/arch/sh/configs/se7206_defconfig
@@ -11,7 +11,7 @@ CONFIG_CGROUP_DEBUG=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_RELAY=y
 CONFIG_NAMESPACES=y
 CONFIG_UTS_NS=y
diff --git a/arch/sh/configs/shx3_defconfig b/arch/sh/configs/shx3_defconfig
index 6bb413036892..cd6c519f8fad 100644
--- a/arch/sh/configs/shx3_defconfig
+++ b/arch/sh/configs/shx3_defconfig
@@ -13,7 +13,7 @@ CONFIG_CGROUP_FREEZER=y
 CONFIG_CGROUP_DEVICE=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
+CONFIG_CGROUP_MEMCG=y
 CONFIG_RELAY=y
 CONFIG_NAMESPACES=y
 CONFIG_UTS_NS=y
diff --git a/arch/sh/configs/urquell_defconfig b/arch/sh/configs/urquell_defconfig
index 8bfa4d056d7a..d7f89be9f474 100644
--- a/arch/sh/configs/urquell_defconfig
+++ b/arch/sh/configs/urquell_defconfig
@@ -15,8 +15,8 @@ CONFIG_CPUSETS=y
 # CONFIG_PROC_PID_CPUSET is not set
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_DEV_INITRD=y
diff --git a/arch/sh/include/asm/unistd.h b/arch/sh/include/asm/unistd.h
index e800a38c9f8d..7bc67076baac 100644
--- a/arch/sh/include/asm/unistd.h
+++ b/arch/sh/include/asm/unistd.h
@@ -6,7 +6,6 @@
 # endif
 
 # define __ARCH_WANT_SYS_RT_SIGSUSPEND
-# define __ARCH_WANT_IPC_PARSE_VERSION
 # define __ARCH_WANT_OLD_READDIR
 # define __ARCH_WANT_OLD_STAT
 # define __ARCH_WANT_STAT64
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index e74ff1377626..67f1f6f5f4e1 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -27,6 +27,7 @@ config SPARC
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select USE_GENERIC_SMP_HELPERS if SMP
 	select GENERIC_PCI_IOMAP
 	select HAVE_NMI_WATCHDOG if SPARC64
diff --git a/arch/sparc/include/asm/fixmap.h b/arch/sparc/include/asm/fixmap.h
deleted file mode 100644
index f18fc0755adf..000000000000
--- a/arch/sparc/include/asm/fixmap.h
+++ /dev/null
@@ -1,110 +0,0 @@
-/*
- * fixmap.h: compile-time virtual memory allocation
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 1998 Ingo Molnar
- *
- * Support of BIGMEM added by Gerhard Wichert, Siemens AG, July 1999
- */
-
-#ifndef _ASM_FIXMAP_H
-#define _ASM_FIXMAP_H
-
-#include <linux/kernel.h>
-#include <asm/page.h>
-#ifdef CONFIG_HIGHMEM
-#include <linux/threads.h>
-#include <asm/kmap_types.h>
-#endif
-
-/*
- * Here we define all the compile-time 'special' virtual
- * addresses. The point is to have a constant address at
- * compile time, but to set the physical address only
- * in the boot process. We allocate these special  addresses
- * from the top of unused virtual memory (0xfd000000 - 1 page) backwards.
- * Also this lets us do fail-safe vmalloc(), we
- * can guarantee that these special addresses and
- * vmalloc()-ed addresses never overlap.
- *
- * these 'compile-time allocated' memory buffers are
- * fixed-size 4k pages. (or larger if used with an increment
- * highger than 1) use fixmap_set(idx,phys) to associate
- * physical memory with fixmap indices.
- *
- * TLB entries of such buffers will not be flushed across
- * task switches.
- */
-
-/*
- * on UP currently we will have no trace of the fixmap mechanism,
- * no page table allocations, etc. This might change in the
- * future, say framebuffers for the console driver(s) could be
- * fix-mapped?
- */
-enum fixed_addresses {
-	FIX_HOLE,
-#ifdef CONFIG_HIGHMEM
-	FIX_KMAP_BEGIN,
-	FIX_KMAP_END = FIX_KMAP_BEGIN+(KM_TYPE_NR*NR_CPUS)-1,
-#endif
-	__end_of_fixed_addresses
-};
-
-extern void __set_fixmap (enum fixed_addresses idx,
-					unsigned long phys, pgprot_t flags);
-
-#define set_fixmap(idx, phys) \
-		__set_fixmap(idx, phys, PAGE_KERNEL)
-/*
- * Some hardware wants to get fixmapped without caching.
- */
-#define set_fixmap_nocache(idx, phys) \
-		__set_fixmap(idx, phys, PAGE_KERNEL_NOCACHE)
-/*
- * used by vmalloc.c.
- *
- * Leave one empty page between IO pages at 0xfd000000 and
- * the start of the fixmap.
- */
-#define FIXADDR_TOP	(0xfcfff000UL)
-#define FIXADDR_SIZE	((__end_of_fixed_addresses) << PAGE_SHIFT)
-#define FIXADDR_START	(FIXADDR_TOP - FIXADDR_SIZE)
-
-#define __fix_to_virt(x)	(FIXADDR_TOP - ((x) << PAGE_SHIFT))
-#define __virt_to_fix(x)	((FIXADDR_TOP - ((x)&PAGE_MASK)) >> PAGE_SHIFT)
-
-extern void __this_fixmap_does_not_exist(void);
-
-/*
- * 'index to address' translation. If anyone tries to use the idx
- * directly without tranlation, we catch the bug with a NULL-deference
- * kernel oops. Illegal ranges of incoming indices are caught too.
- */
-static inline unsigned long fix_to_virt(const unsigned int idx)
-{
-	/*
-	 * this branch gets completely eliminated after inlining,
-	 * except when someone tries to use fixaddr indices in an
-	 * illegal way. (such as mixing up address types or using
-	 * out-of-range indices).
-	 *
-	 * If it doesn't get removed, the linker will complain
-	 * loudly with a reasonably clear error message..
-	 */
-	if (idx >= __end_of_fixed_addresses)
-		__this_fixmap_does_not_exist();
-
-        return __fix_to_virt(idx);
-}
-
-static inline unsigned long virt_to_fix(const unsigned long vaddr)
-{
-	BUG_ON(vaddr >= FIXADDR_TOP || vaddr < FIXADDR_START);
-	return __virt_to_fix(vaddr);
-}
-
-#endif
diff --git a/arch/sparc/include/asm/highmem.h b/arch/sparc/include/asm/highmem.h
index 3b6e00dd96e5..4f9e15c757e2 100644
--- a/arch/sparc/include/asm/highmem.h
+++ b/arch/sparc/include/asm/highmem.h
@@ -21,7 +21,6 @@
 #ifdef __KERNEL__
 
 #include <linux/interrupt.h>
-#include <asm/fixmap.h>
 #include <asm/vaddrs.h>
 #include <asm/kmap_types.h>
 #include <asm/pgtable.h>
@@ -29,7 +28,6 @@
 /* declarations for highmem.c */
 extern unsigned long highstart_pfn, highend_pfn;
 
-extern pte_t *kmap_pte;
 extern pgprot_t kmap_prot;
 extern pte_t *pkmap_page_table;
 
@@ -72,7 +70,6 @@ static inline void kunmap(struct page *page)
 
 extern void *kmap_atomic(struct page *page);
 extern void __kunmap_atomic(void *kvaddr);
-extern struct page *kmap_atomic_to_page(void *vaddr);
 
 #define flush_cache_kmaps()	flush_cache_all()
 
diff --git a/arch/sparc/include/asm/leon.h b/arch/sparc/include/asm/leon.h
index 3375c6293893..15a716934e4d 100644
--- a/arch/sparc/include/asm/leon.h
+++ b/arch/sparc/include/asm/leon.h
@@ -82,7 +82,6 @@ static inline unsigned long leon_load_reg(unsigned long paddr)
 #define LEON_BYPASS_LOAD_PA(x)      leon_load_reg((unsigned long)(x))
 #define LEON_BYPASS_STORE_PA(x, v)  leon_store_reg((unsigned long)(x), (unsigned long)(v))
 
-extern void leon_init(void);
 extern void leon_switch_mm(void);
 extern void leon_init_IRQ(void);
 
diff --git a/arch/sparc/include/asm/mmu_context_32.h b/arch/sparc/include/asm/mmu_context_32.h
index 01456c900720..2df2a9be8f6d 100644
--- a/arch/sparc/include/asm/mmu_context_32.h
+++ b/arch/sparc/include/asm/mmu_context_32.h
@@ -9,14 +9,12 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 }
 
-/*
- * Initialize a new mmu context.  This is invoked when a new
+/* Initialize a new mmu context.  This is invoked when a new
  * address space instance (unique or shared) is instantiated.
  */
-#define init_new_context(tsk, mm) (((mm)->context = NO_CONTEXT), 0)
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
 
-/*
- * Destroy a dead context.  This occurs when mmput drops the
+/* Destroy a dead context.  This occurs when mmput drops the
  * mm_users count to zero, the mmaps have been released, and
  * all the page tables have been flushed.  Our job is to destroy
  * any remaining processor-specific state.
diff --git a/arch/sparc/include/asm/page_32.h b/arch/sparc/include/asm/page_32.h
index fab78a308ebf..f82a1f36b655 100644
--- a/arch/sparc/include/asm/page_32.h
+++ b/arch/sparc/include/asm/page_32.h
@@ -107,8 +107,7 @@ typedef unsigned long iopgprot_t;
 
 typedef struct page *pgtable_t;
 
-extern unsigned long sparc_unmapped_base;
-#define TASK_UNMAPPED_BASE	sparc_unmapped_base
+#define TASK_UNMAPPED_BASE	0x50000000
 
 #else /* !(__ASSEMBLY__) */
 
diff --git a/arch/sparc/include/asm/pgalloc_32.h b/arch/sparc/include/asm/pgalloc_32.h
index e5b169b46d21..9b1c36de0f18 100644
--- a/arch/sparc/include/asm/pgalloc_32.h
+++ b/arch/sparc/include/asm/pgalloc_32.h
@@ -11,28 +11,15 @@
 
 struct page;
 
-extern struct pgtable_cache_struct {
-	unsigned long *pgd_cache;
-	unsigned long *pte_cache;
-	unsigned long pgtable_cache_sz;
-	unsigned long pgd_cache_sz;
-} pgt_quicklists;
-
-unsigned long srmmu_get_nocache(int size, int align);
-void srmmu_free_nocache(unsigned long vaddr, int size);
-
-#define pgd_quicklist           (pgt_quicklists.pgd_cache)
-#define pmd_quicklist           ((unsigned long *)0)
-#define pte_quicklist           (pgt_quicklists.pte_cache)
-#define pgtable_cache_size      (pgt_quicklists.pgtable_cache_sz)
-#define pgd_cache_size		(pgt_quicklists.pgd_cache_sz)
+void *srmmu_get_nocache(int size, int align);
+void srmmu_free_nocache(void *addr, int size);
 
 #define check_pgt_cache()	do { } while (0)
 
 pgd_t *get_pgd_fast(void);
 static inline void free_pgd_fast(pgd_t *pgd)
 {
-	srmmu_free_nocache((unsigned long)pgd, SRMMU_PGD_TABLE_SIZE);
+	srmmu_free_nocache(pgd, SRMMU_PGD_TABLE_SIZE);
 }
 
 #define pgd_free(mm, pgd)	free_pgd_fast(pgd)
@@ -50,13 +37,13 @@ static inline void pgd_set(pgd_t * pgdp, pmd_t * pmdp)
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm,
 				   unsigned long address)
 {
-	return (pmd_t *)srmmu_get_nocache(SRMMU_PMD_TABLE_SIZE,
-					  SRMMU_PMD_TABLE_SIZE);
+	return srmmu_get_nocache(SRMMU_PMD_TABLE_SIZE,
+				 SRMMU_PMD_TABLE_SIZE);
 }
 
 static inline void free_pmd_fast(pmd_t * pmd)
 {
-	srmmu_free_nocache((unsigned long)pmd, SRMMU_PMD_TABLE_SIZE);
+	srmmu_free_nocache(pmd, SRMMU_PMD_TABLE_SIZE);
 }
 
 #define pmd_free(mm, pmd)		free_pmd_fast(pmd)
@@ -73,13 +60,13 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address);
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
 					  unsigned long address)
 {
-	return (pte_t *)srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
+	return srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
 }
 
 
 static inline void free_pte_fast(pte_t *pte)
 {
-	srmmu_free_nocache((unsigned long)pte, PTE_SIZE);
+	srmmu_free_nocache(pte, PTE_SIZE);
 }
 
 #define pte_free_kernel(mm, pte)	free_pte_fast(pte)
diff --git a/arch/sparc/include/asm/pgtable_32.h b/arch/sparc/include/asm/pgtable_32.h
index cbbbed5cb3aa..6fc13483f702 100644
--- a/arch/sparc/include/asm/pgtable_32.h
+++ b/arch/sparc/include/asm/pgtable_32.h
@@ -52,8 +52,9 @@ extern unsigned long calc_highpages(void);
 #define PAGE_READONLY	SRMMU_PAGE_RDONLY
 #define PAGE_KERNEL	SRMMU_PAGE_KERNEL
 
-/* Top-level page directory */
-extern pgd_t swapper_pg_dir[1024];
+/* Top-level page directory - dummy used by init-mm.
+ * srmmu.c will assign the real one (which is dynamically sized) */
+#define swapper_pg_dir NULL
 
 extern void paging_init(void);
 
@@ -78,8 +79,6 @@ extern unsigned long ptr_in_current_pgd;
 #define __S110	PAGE_SHARED
 #define __S111	PAGE_SHARED
 
-extern int num_contexts;
-
 /* First physical page can be anywhere, the following is needed so that
  * va-->pa and vice versa conversions work properly without performance
  * hit for all __pa()/__va() operations.
@@ -88,18 +87,11 @@ extern unsigned long phys_base;
 extern unsigned long pfn_base;
 
 /*
- * BAD_PAGETABLE is used when we need a bogus page-table, while
- * BAD_PAGE is used for a bogus page.
- *
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
  */
-extern pte_t * __bad_pagetable(void);
-extern pte_t __bad_page(void);
 extern unsigned long empty_zero_page;
 
-#define BAD_PAGETABLE __bad_pagetable()
-#define BAD_PAGE __bad_page()
 #define ZERO_PAGE(vaddr) (virt_to_page(&empty_zero_page))
 
 /*
@@ -398,36 +390,6 @@ static inline pte_t pgoff_to_pte(unsigned long pgoff)
  */
 #define PTE_FILE_MAX_BITS 24
 
-/*
- */
-struct ctx_list {
-	struct ctx_list *next;
-	struct ctx_list *prev;
-	unsigned int ctx_number;
-	struct mm_struct *ctx_mm;
-};
-
-extern struct ctx_list *ctx_list_pool;  /* Dynamically allocated */
-extern struct ctx_list ctx_free;        /* Head of free list */
-extern struct ctx_list ctx_used;        /* Head of used contexts list */
-
-#define NO_CONTEXT     -1
-
-static inline void remove_from_ctx_list(struct ctx_list *entry)
-{
-	entry->next->prev = entry->prev;
-	entry->prev->next = entry->next;
-}
-
-static inline void add_to_ctx_list(struct ctx_list *head, struct ctx_list *entry)
-{
-	entry->next = head;
-	(entry->prev = head->prev)->next = entry;
-	head->prev = entry;
-}
-#define add_to_free_ctxlist(entry) add_to_ctx_list(&ctx_free, entry)
-#define add_to_used_ctxlist(entry) add_to_ctx_list(&ctx_used, entry)
-
 static inline unsigned long
 __get_phys (unsigned long addr)
 {
diff --git a/arch/sparc/include/asm/unistd.h b/arch/sparc/include/asm/unistd.h
index c7cb0af0eb59..fb2693464807 100644
--- a/arch/sparc/include/asm/unistd.h
+++ b/arch/sparc/include/asm/unistd.h
@@ -423,7 +423,6 @@
 #endif
 
 #ifdef __KERNEL__
-#define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_ALARM
diff --git a/arch/sparc/include/asm/vaddrs.h b/arch/sparc/include/asm/vaddrs.h
index da6535d88a72..c3dbcf902034 100644
--- a/arch/sparc/include/asm/vaddrs.h
+++ b/arch/sparc/include/asm/vaddrs.h
@@ -30,6 +30,28 @@
  */
 #define SRMMU_NOCACHE_ALCRATIO	64	/* 256 pages per 64MB of system RAM */
 
+#ifndef __ASSEMBLY__
+#include <asm/kmap_types.h>
+
+enum fixed_addresses {
+	FIX_HOLE,
+#ifdef CONFIG_HIGHMEM
+	FIX_KMAP_BEGIN,
+	FIX_KMAP_END = (KM_TYPE_NR * NR_CPUS),
+#endif
+	__end_of_fixed_addresses
+};
+#endif
+
+/* Leave one empty page between IO pages at 0xfd000000 and
+ * the top of the fixmap.
+ */
+#define FIXADDR_TOP		(0xfcfff000UL)
+#define FIXADDR_SIZE		((FIX_KMAP_END + 1) << PAGE_SHIFT)
+#define FIXADDR_START		(FIXADDR_TOP - FIXADDR_SIZE)
+
+#define __fix_to_virt(x)        (FIXADDR_TOP - ((x) << PAGE_SHIFT))
+
 #define SUN4M_IOBASE_VADDR	0xfd000000 /* Base for mapping pages */
 #define IOBASE_VADDR		0xfe000000
 #define IOBASE_END		0xfe600000
diff --git a/arch/sparc/kernel/head_32.S b/arch/sparc/kernel/head_32.S
index afeb1d770303..3d92c0a8f6c4 100644
--- a/arch/sparc/kernel/head_32.S
+++ b/arch/sparc/kernel/head_32.S
@@ -58,8 +58,6 @@ sun4e_notsup:
 /* This was the only reasonable way I could think of to properly align
  * these page-table data structures.
  */
-	.globl swapper_pg_dir
-swapper_pg_dir:		.skip PAGE_SIZE
 	.globl empty_zero_page
 empty_zero_page:	.skip PAGE_SIZE
 
diff --git a/arch/sparc/kernel/ldc.c b/arch/sparc/kernel/ldc.c
index 435e406fdec3..81d92fc9983b 100644
--- a/arch/sparc/kernel/ldc.c
+++ b/arch/sparc/kernel/ldc.c
@@ -1250,14 +1250,12 @@ int ldc_bind(struct ldc_channel *lp, const char *name)
 	snprintf(lp->rx_irq_name, LDC_IRQ_NAME_MAX, "%s RX", name);
 	snprintf(lp->tx_irq_name, LDC_IRQ_NAME_MAX, "%s TX", name);
 
-	err = request_irq(lp->cfg.rx_irq, ldc_rx,
-			  IRQF_SAMPLE_RANDOM | IRQF_DISABLED,
+	err = request_irq(lp->cfg.rx_irq, ldc_rx, IRQF_DISABLED,
 			  lp->rx_irq_name, lp);
 	if (err)
 		return err;
 
-	err = request_irq(lp->cfg.tx_irq, ldc_tx,
-			  IRQF_SAMPLE_RANDOM | IRQF_DISABLED,
+	err = request_irq(lp->cfg.tx_irq, ldc_tx, IRQF_DISABLED,
 			  lp->tx_irq_name, lp);
 	if (err) {
 		free_irq(lp->cfg.rx_irq, lp);
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index e34e2c40c060..f8b6eee40bde 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -486,17 +486,6 @@ void __init leon_trans_init(struct device_node *dp)
 	}
 }
 
-void __initdata (*prom_amba_init)(struct device_node *dp, struct device_node ***nextp) = 0;
-
-void __init leon_node_init(struct device_node *dp, struct device_node ***nextp)
-{
-	if (prom_amba_init &&
-	    strcmp(dp->type, "ambapp") == 0 &&
-	    strcmp(dp->name, "ambapp0") == 0) {
-		prom_amba_init(dp, nextp);
-	}
-}
-
 #ifdef CONFIG_SMP
 void leon_clear_profile_irq(int cpu)
 {
@@ -522,8 +511,3 @@ void __init leon_init_IRQ(void)
 	sparc_config.clear_clock_irq  = leon_clear_clock_irq;
 	sparc_config.load_profile_irq = leon_load_profile_irq;
 }
-
-void __init leon_init(void)
-{
-	of_pdt_build_more = &leon_node_init;
-}
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index cb36e82dcd5d..14006d8aca28 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -333,9 +333,6 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 		put_psr(get_psr() | PSR_EF);
 		fpsave(&p->thread.float_regs[0], &p->thread.fsr,
 		       &p->thread.fpqueue[0], &p->thread.fpqdepth);
-#ifdef CONFIG_SMP
-		clear_thread_flag(TIF_USEDFPU);
-#endif
 	}
 
 	/*
@@ -413,6 +410,7 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 #ifdef CONFIG_SMP
 	/* FPU must be disabled on SMP. */
 	childregs->psr &= ~PSR_EF;
+	clear_tsk_thread_flag(p, TIF_USEDFPU);
 #endif
 
 	/* Set the return value for the child. */
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index efe3e64bba38..38bf80a22f02 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -371,7 +371,6 @@ void __init setup_arch(char **cmdline_p)
 		(*(linux_dbvec->teach_debugger))();
 	}
 
-	init_mm.context = (unsigned long) NO_CONTEXT;
 	init_task.thread.kregs = &fake_swapper_regs;
 
 	/* Run-time patch instructions to match the cpu model */
diff --git a/arch/sparc/kernel/sys_sparc_64.c b/arch/sparc/kernel/sys_sparc_64.c
index 275f74fd6f6a..0dc1f5786081 100644
--- a/arch/sparc/kernel/sys_sparc_64.c
+++ b/arch/sparc/kernel/sys_sparc_64.c
@@ -66,23 +66,6 @@ static inline int invalid_64bit_range(unsigned long addr, unsigned long len)
 	return 0;
 }
 
-/* Does start,end straddle the VA-space hole?  */
-static inline int straddles_64bit_va_hole(unsigned long start, unsigned long end)
-{
-	unsigned long va_exclude_start, va_exclude_end;
-
-	va_exclude_start = VA_EXCLUDE_START;
-	va_exclude_end   = VA_EXCLUDE_END;
-
-	if (likely(start < va_exclude_start && end < va_exclude_start))
-		return 0;
-
-	if (likely(start >= va_exclude_end && end >= va_exclude_end))
-		return 0;
-
-	return 1;
-}
-
 /* These functions differ from the default implementations in
  * mm/mmap.c in two ways:
  *
@@ -487,7 +470,7 @@ SYSCALL_DEFINE6(sparc_ipc, unsigned int, call, int, first, unsigned long, second
 		switch (call) {
 		case SHMAT: {
 			ulong raddr;
-			err = do_shmat(first, ptr, (int)second, &raddr);
+			err = do_shmat(first, ptr, (int)second, &raddr, SHMLBA);
 			if (!err) {
 				if (put_user(raddr,
 					     (ulong __user *) third))
diff --git a/arch/sparc/lib/NG2memcpy.S b/arch/sparc/lib/NG2memcpy.S
index 0aed75653b50..03eadf66b0d3 100644
--- a/arch/sparc/lib/NG2memcpy.S
+++ b/arch/sparc/lib/NG2memcpy.S
@@ -90,49 +90,49 @@
 	faligndata	%x7, %x8, %f14;
 
 #define FREG_MOVE_1(x0) \
-	fmovd		%x0, %f0;
+	fsrc2		%x0, %f0;
 #define FREG_MOVE_2(x0, x1) \
-	fmovd		%x0, %f0; \
-	fmovd		%x1, %f2;
+	fsrc2		%x0, %f0; \
+	fsrc2		%x1, %f2;
 #define FREG_MOVE_3(x0, x1, x2) \
-	fmovd		%x0, %f0; \
-	fmovd		%x1, %f2; \
-	fmovd		%x2, %f4;
+	fsrc2		%x0, %f0; \
+	fsrc2		%x1, %f2; \
+	fsrc2		%x2, %f4;
 #define FREG_MOVE_4(x0, x1, x2, x3) \
-	fmovd		%x0, %f0; \
-	fmovd		%x1, %f2; \
-	fmovd		%x2, %f4; \
-	fmovd		%x3, %f6;
+	fsrc2		%x0, %f0; \
+	fsrc2		%x1, %f2; \
+	fsrc2		%x2, %f4; \
+	fsrc2		%x3, %f6;
 #define FREG_MOVE_5(x0, x1, x2, x3, x4) \
-	fmovd		%x0, %f0; \
-	fmovd		%x1, %f2; \
-	fmovd		%x2, %f4; \
-	fmovd		%x3, %f6; \
-	fmovd		%x4, %f8;
+	fsrc2		%x0, %f0; \
+	fsrc2		%x1, %f2; \
+	fsrc2		%x2, %f4; \
+	fsrc2		%x3, %f6; \
+	fsrc2		%x4, %f8;
 #define FREG_MOVE_6(x0, x1, x2, x3, x4, x5) \
-	fmovd		%x0, %f0; \
-	fmovd		%x1, %f2; \
-	fmovd		%x2, %f4; \
-	fmovd		%x3, %f6; \
-	fmovd		%x4, %f8; \
-	fmovd		%x5, %f10;
+	fsrc2		%x0, %f0; \
+	fsrc2		%x1, %f2; \
+	fsrc2		%x2, %f4; \
+	fsrc2		%x3, %f6; \
+	fsrc2		%x4, %f8; \
+	fsrc2		%x5, %f10;
 #define FREG_MOVE_7(x0, x1, x2, x3, x4, x5, x6) \
-	fmovd		%x0, %f0; \
-	fmovd		%x1, %f2; \
-	fmovd		%x2, %f4; \
-	fmovd		%x3, %f6; \
-	fmovd		%x4, %f8; \
-	fmovd		%x5, %f10; \
-	fmovd		%x6, %f12;
+	fsrc2		%x0, %f0; \
+	fsrc2		%x1, %f2; \
+	fsrc2		%x2, %f4; \
+	fsrc2		%x3, %f6; \
+	fsrc2		%x4, %f8; \
+	fsrc2		%x5, %f10; \
+	fsrc2		%x6, %f12;
 #define FREG_MOVE_8(x0, x1, x2, x3, x4, x5, x6, x7) \
-	fmovd		%x0, %f0; \
-	fmovd		%x1, %f2; \
-	fmovd		%x2, %f4; \
-	fmovd		%x3, %f6; \
-	fmovd		%x4, %f8; \
-	fmovd		%x5, %f10; \
-	fmovd		%x6, %f12; \
-	fmovd		%x7, %f14;
+	fsrc2		%x0, %f0; \
+	fsrc2		%x1, %f2; \
+	fsrc2		%x2, %f4; \
+	fsrc2		%x3, %f6; \
+	fsrc2		%x4, %f8; \
+	fsrc2		%x5, %f10; \
+	fsrc2		%x6, %f12; \
+	fsrc2		%x7, %f14;
 #define FREG_LOAD_1(base, x0) \
 	EX_LD(LOAD(ldd, base + 0x00, %x0))
 #define FREG_LOAD_2(base, x0, x1) \
diff --git a/arch/sparc/lib/U1memcpy.S b/arch/sparc/lib/U1memcpy.S
index bafd2fc07acb..b67142b7768e 100644
--- a/arch/sparc/lib/U1memcpy.S
+++ b/arch/sparc/lib/U1memcpy.S
@@ -109,7 +109,7 @@
 #define UNEVEN_VISCHUNK_LAST(dest, f0, f1, left)	\
 	subcc			%left, 8, %left;	\
 	bl,pn			%xcc, 95f;		\
-	 fsrc1			%f0, %f1;
+	 fsrc2			%f0, %f1;
 
 #define UNEVEN_VISCHUNK(dest, f0, f1, left)		\
 	UNEVEN_VISCHUNK_LAST(dest, f0, f1, left)	\
@@ -201,7 +201,7 @@ FUNC_NAME:		/* %o0=dst, %o1=src, %o2=len */
 	andn		%o1, (0x40 - 1), %o1
 	and		%g2, 7, %g2
 	andncc		%g3, 0x7, %g3
-	fmovd		%f0, %f2
+	fsrc2		%f0, %f2
 	sub		%g3, 0x8, %g3
 	sub		%o2, %GLOBAL_SPARE, %o2
 
diff --git a/arch/sparc/lib/copy_page.S b/arch/sparc/lib/copy_page.S
index b243d3b606ba..4d2df328e514 100644
--- a/arch/sparc/lib/copy_page.S
+++ b/arch/sparc/lib/copy_page.S
@@ -34,10 +34,10 @@
 #endif
 
 #define TOUCH(reg0, reg1, reg2, reg3, reg4, reg5, reg6, reg7)	\
-	fmovd	%reg0, %f48; 	fmovd	%reg1, %f50;		\
-	fmovd	%reg2, %f52; 	fmovd	%reg3, %f54;		\
-	fmovd	%reg4, %f56; 	fmovd	%reg5, %f58;		\
-	fmovd	%reg6, %f60; 	fmovd	%reg7, %f62;
+	fsrc2	%reg0, %f48; 	fsrc2	%reg1, %f50;		\
+	fsrc2	%reg2, %f52; 	fsrc2	%reg3, %f54;		\
+	fsrc2	%reg4, %f56; 	fsrc2	%reg5, %f58;		\
+	fsrc2	%reg6, %f60; 	fsrc2	%reg7, %f62;
 
 	.text
 
@@ -104,60 +104,60 @@ cheetah_copy_page_insn:
 	prefetch	[%o1 + 0x140], #one_read
 	ldd		[%o1 + 0x010], %f4
 	prefetch	[%o1 + 0x180], #one_read
-	fmovd		%f0, %f16
+	fsrc2		%f0, %f16
 	ldd		[%o1 + 0x018], %f6
-	fmovd		%f2, %f18
+	fsrc2		%f2, %f18
 	ldd		[%o1 + 0x020], %f8
-	fmovd		%f4, %f20
+	fsrc2		%f4, %f20
 	ldd		[%o1 + 0x028], %f10
-	fmovd		%f6, %f22
+	fsrc2		%f6, %f22
 	ldd		[%o1 + 0x030], %f12
-	fmovd		%f8, %f24
+	fsrc2		%f8, %f24
 	ldd		[%o1 + 0x038], %f14
-	fmovd		%f10, %f26
+	fsrc2		%f10, %f26
 	ldd		[%o1 + 0x040], %f0
 1:	ldd		[%o1 + 0x048], %f2
-	fmovd		%f12, %f28
+	fsrc2		%f12, %f28
 	ldd		[%o1 + 0x050], %f4
-	fmovd		%f14, %f30
+	fsrc2		%f14, %f30
 	stda		%f16, [%o0] ASI_BLK_P
 	ldd		[%o1 + 0x058], %f6
-	fmovd		%f0, %f16
+	fsrc2		%f0, %f16
 	ldd		[%o1 + 0x060], %f8
-	fmovd		%f2, %f18
+	fsrc2		%f2, %f18
 	ldd		[%o1 + 0x068], %f10
-	fmovd		%f4, %f20
+	fsrc2		%f4, %f20
 	ldd		[%o1 + 0x070], %f12
-	fmovd		%f6, %f22
+	fsrc2		%f6, %f22
 	ldd		[%o1 + 0x078], %f14
-	fmovd		%f8, %f24
+	fsrc2		%f8, %f24
 	ldd		[%o1 + 0x080], %f0
 	prefetch	[%o1 + 0x180], #one_read
-	fmovd		%f10, %f26
+	fsrc2		%f10, %f26
 	subcc		%o2, 1, %o2
 	add		%o0, 0x40, %o0
 	bne,pt		%xcc, 1b
 	 add		%o1, 0x40, %o1
 
 	ldd		[%o1 + 0x048], %f2
-	fmovd		%f12, %f28
+	fsrc2		%f12, %f28
 	ldd		[%o1 + 0x050], %f4
-	fmovd		%f14, %f30
+	fsrc2		%f14, %f30
 	stda		%f16, [%o0] ASI_BLK_P
 	ldd		[%o1 + 0x058], %f6
-	fmovd		%f0, %f16
+	fsrc2		%f0, %f16
 	ldd		[%o1 + 0x060], %f8
-	fmovd		%f2, %f18
+	fsrc2		%f2, %f18
 	ldd		[%o1 + 0x068], %f10
-	fmovd		%f4, %f20
+	fsrc2		%f4, %f20
 	ldd		[%o1 + 0x070], %f12
-	fmovd		%f6, %f22
+	fsrc2		%f6, %f22
 	add		%o0, 0x40, %o0
 	ldd		[%o1 + 0x078], %f14
-	fmovd		%f8, %f24
-	fmovd		%f10, %f26
-	fmovd		%f12, %f28
-	fmovd		%f14, %f30
+	fsrc2		%f8, %f24
+	fsrc2		%f10, %f26
+	fsrc2		%f12, %f28
+	fsrc2		%f14, %f30
 	stda		%f16, [%o0] ASI_BLK_P
 	membar		#Sync
 	VISExitHalf
diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c
index f46cf6be3370..77ac917be152 100644
--- a/arch/sparc/mm/fault_32.c
+++ b/arch/sparc/mm/fault_32.c
@@ -32,24 +32,6 @@
 
 int show_unhandled_signals = 1;
 
-/* At boot time we determine these two values necessary for setting
- * up the segment maps and page table entries (pte's).
- */
-
-int num_contexts;
-
-/* Return how much physical memory we have.  */
-unsigned long probe_memory(void)
-{
-	unsigned long total = 0;
-	int i;
-
-	for (i = 0; sp_banks[i].num_bytes; i++)
-		total += sp_banks[i].num_bytes;
-
-	return total;
-}
-
 static void unhandled_fault(unsigned long, struct task_struct *,
 		struct pt_regs *) __attribute__ ((noreturn));
 
diff --git a/arch/sparc/mm/highmem.c b/arch/sparc/mm/highmem.c
index 055c66cf1bf4..449f864f0cef 100644
--- a/arch/sparc/mm/highmem.c
+++ b/arch/sparc/mm/highmem.c
@@ -22,13 +22,31 @@
  * shared by CPUs, and so precious, and establishing them requires IPI.
  * Atomic kmaps are lightweight and we may have NCPUS more of them.
  */
-#include <linux/mm.h>
 #include <linux/highmem.h>
 #include <linux/export.h>
-#include <asm/pgalloc.h>
+#include <linux/mm.h>
+
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
-#include <asm/fixmap.h>
+#include <asm/pgalloc.h>
+#include <asm/vaddrs.h>
+
+pgprot_t kmap_prot;
+
+static pte_t *kmap_pte;
+
+void __init kmap_init(void)
+{
+	unsigned long address;
+	pmd_t *dir;
+
+	address = __fix_to_virt(FIX_KMAP_BEGIN);
+	dir = pmd_offset(pgd_offset_k(address), address);
+
+        /* cache the first kmap pte */
+        kmap_pte = pte_offset_kernel(dir, address);
+        kmap_prot = __pgprot(SRMMU_ET_PTE | SRMMU_PRIV | SRMMU_CACHE);
+}
 
 void *kmap_atomic(struct page *page)
 {
@@ -110,21 +128,3 @@ void __kunmap_atomic(void *kvaddr)
 	pagefault_enable();
 }
 EXPORT_SYMBOL(__kunmap_atomic);
-
-/* We may be fed a pagetable here by ptep_to_xxx and others. */
-struct page *kmap_atomic_to_page(void *ptr)
-{
-	unsigned long idx, vaddr = (unsigned long)ptr;
-	pte_t *pte;
-
-	if (vaddr < SRMMU_NOCACHE_VADDR)
-		return virt_to_page(ptr);
-	if (vaddr < PKMAP_BASE)
-		return pfn_to_page(__nocache_pa(vaddr) >> PAGE_SHIFT);
-	BUG_ON(vaddr < FIXADDR_START);
-	BUG_ON(vaddr > FIXADDR_TOP);
-
-	idx = virt_to_fix(vaddr);
-	pte = kmap_pte - (idx - FIX_KMAP_BEGIN);
-	return pte_page(*pte);
-}
diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index ef5c779ec855..dde85ef1c56d 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -45,9 +45,6 @@ unsigned long pfn_base;
 EXPORT_SYMBOL(pfn_base);
 
 struct sparc_phys_banks sp_banks[SPARC_PHYS_BANKS+1];
-unsigned long sparc_unmapped_base;
-
-struct pgtable_cache_struct pgt_quicklists;
 
 /* Initial ramdisk setup */
 extern unsigned int sparc_ramdisk_image;
@@ -55,19 +52,6 @@ extern unsigned int sparc_ramdisk_size;
 
 unsigned long highstart_pfn, highend_pfn;
 
-pte_t *kmap_pte;
-pgprot_t kmap_prot;
-
-#define kmap_get_fixmap_pte(vaddr) \
-	pte_offset_kernel(pmd_offset(pgd_offset_k(vaddr), (vaddr)), (vaddr))
-
-void __init kmap_init(void)
-{
-	/* cache the first kmap pte */
-	kmap_pte = kmap_get_fixmap_pte(__fix_to_virt(FIX_KMAP_BEGIN));
-	kmap_prot = __pgprot(SRMMU_ET_PTE | SRMMU_PRIV | SRMMU_CACHE);
-}
-
 void show_mem(unsigned int filter)
 {
 	printk("Mem-info:\n");
@@ -76,33 +60,8 @@ void show_mem(unsigned int filter)
 	       nr_swap_pages << (PAGE_SHIFT-10));
 	printk("%ld pages of RAM\n", totalram_pages);
 	printk("%ld free pages\n", nr_free_pages());
-#if 0 /* undefined pgtable_cache_size, pgd_cache_size */
-	printk("%ld pages in page table cache\n",pgtable_cache_size);
-#ifndef CONFIG_SMP
-	if (sparc_cpu_model == sun4m || sparc_cpu_model == sun4d)
-		printk("%ld entries in page dir cache\n",pgd_cache_size);
-#endif	
-#endif
 }
 
-void __init sparc_context_init(int numctx)
-{
-	int ctx;
-
-	ctx_list_pool = __alloc_bootmem(numctx * sizeof(struct ctx_list), SMP_CACHE_BYTES, 0UL);
-
-	for(ctx = 0; ctx < numctx; ctx++) {
-		struct ctx_list *clist;
-
-		clist = (ctx_list_pool + ctx);
-		clist->ctx_number = ctx;
-		clist->ctx_mm = NULL;
-	}
-	ctx_free.next = ctx_free.prev = &ctx_free;
-	ctx_used.next = ctx_used.prev = &ctx_used;
-	for(ctx = 0; ctx < numctx; ctx++)
-		add_to_free_ctxlist(ctx_list_pool + ctx);
-}
 
 extern unsigned long cmdline_memory_size;
 unsigned long last_valid_pfn;
@@ -292,22 +251,7 @@ extern void device_scan(void);
 
 void __init paging_init(void)
 {
-	switch(sparc_cpu_model) {
-	case sparc_leon:
-		leon_init();
-		/* fall through */
-	case sun4m:
-	case sun4d:
-		srmmu_paging_init();
-		sparc_unmapped_base = 0x50000000;
-		break;
-	default:
-		prom_printf("paging_init: Cannot init paging on this Sparc\n");
-		prom_printf("paging_init: sparc_cpu_model = %d\n", sparc_cpu_model);
-		prom_printf("paging_init: Halting...\n");
-		prom_halt();
-	}
-
+	srmmu_paging_init();
 	prom_build_devicetree();
 	of_fill_in_cpu_data();
 	device_scan();
diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c
index 62e3f5773303..c38bb72e3e80 100644
--- a/arch/sparc/mm/srmmu.c
+++ b/arch/sparc/mm/srmmu.c
@@ -8,45 +8,45 @@
  * Copyright (C) 1999,2000 Anton Blanchard (anton@samba.org)
  */
 
-#include <linux/kernel.h>
-#include <linux/mm.h>
-#include <linux/vmalloc.h>
-#include <linux/pagemap.h>
-#include <linux/init.h>
+#include <linux/seq_file.h>
 #include <linux/spinlock.h>
 #include <linux/bootmem.h>
-#include <linux/fs.h>
-#include <linux/seq_file.h>
+#include <linux/pagemap.h>
+#include <linux/vmalloc.h>
 #include <linux/kdebug.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
 #include <linux/log2.h>
 #include <linux/gfp.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
 
-#include <asm/bitext.h>
-#include <asm/page.h>
+#include <asm/mmu_context.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+#include <asm/io-unit.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
-#include <asm/io.h>
+#include <asm/bitext.h>
 #include <asm/vaddrs.h>
-#include <asm/traps.h>
-#include <asm/smp.h>
-#include <asm/mbus.h>
 #include <asm/cache.h>
+#include <asm/traps.h>
 #include <asm/oplib.h>
+#include <asm/mbus.h>
+#include <asm/page.h>
 #include <asm/asi.h>
 #include <asm/msi.h>
-#include <asm/mmu_context.h>
-#include <asm/io-unit.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
+#include <asm/smp.h>
+#include <asm/io.h>
 
 /* Now the cpu specific definitions. */
-#include <asm/viking.h>
-#include <asm/mxcc.h>
-#include <asm/ross.h>
+#include <asm/turbosparc.h>
 #include <asm/tsunami.h>
+#include <asm/viking.h>
 #include <asm/swift.h>
-#include <asm/turbosparc.h>
 #include <asm/leon.h>
+#include <asm/mxcc.h>
+#include <asm/ross.h>
 
 #include "srmmu.h"
 
@@ -55,10 +55,6 @@ static unsigned int hwbug_bitmask;
 int vac_cache_size;
 int vac_line_size;
 
-struct ctx_list *ctx_list_pool;
-struct ctx_list ctx_free;
-struct ctx_list ctx_used;
-
 extern struct resource sparc_iomap;
 
 extern unsigned long last_valid_pfn;
@@ -136,8 +132,8 @@ void pmd_populate(struct mm_struct *mm, pmd_t *pmdp, struct page *ptep)
 	}
 }
 
-/* Find an entry in the third-level page table.. */ 
-pte_t *pte_offset_kernel(pmd_t * dir, unsigned long address)
+/* Find an entry in the third-level page table.. */
+pte_t *pte_offset_kernel(pmd_t *dir, unsigned long address)
 {
 	void *pte;
 
@@ -151,55 +147,61 @@ pte_t *pte_offset_kernel(pmd_t * dir, unsigned long address)
  * align: bytes, number to align at.
  * Returns the virtual address of the allocated area.
  */
-static unsigned long __srmmu_get_nocache(int size, int align)
+static void *__srmmu_get_nocache(int size, int align)
 {
 	int offset;
+	unsigned long addr;
 
 	if (size < SRMMU_NOCACHE_BITMAP_SHIFT) {
-		printk("Size 0x%x too small for nocache request\n", size);
+		printk(KERN_ERR "Size 0x%x too small for nocache request\n",
+		       size);
 		size = SRMMU_NOCACHE_BITMAP_SHIFT;
 	}
-	if (size & (SRMMU_NOCACHE_BITMAP_SHIFT-1)) {
-		printk("Size 0x%x unaligned int nocache request\n", size);
-		size += SRMMU_NOCACHE_BITMAP_SHIFT-1;
+	if (size & (SRMMU_NOCACHE_BITMAP_SHIFT - 1)) {
+		printk(KERN_ERR "Size 0x%x unaligned int nocache request\n",
+		       size);
+		size += SRMMU_NOCACHE_BITMAP_SHIFT - 1;
 	}
 	BUG_ON(align > SRMMU_NOCACHE_ALIGN_MAX);
 
 	offset = bit_map_string_get(&srmmu_nocache_map,
-		       			size >> SRMMU_NOCACHE_BITMAP_SHIFT,
-					align >> SRMMU_NOCACHE_BITMAP_SHIFT);
+				    size >> SRMMU_NOCACHE_BITMAP_SHIFT,
+				    align >> SRMMU_NOCACHE_BITMAP_SHIFT);
 	if (offset == -1) {
-		printk("srmmu: out of nocache %d: %d/%d\n",
-		    size, (int) srmmu_nocache_size,
-		    srmmu_nocache_map.used << SRMMU_NOCACHE_BITMAP_SHIFT);
+		printk(KERN_ERR "srmmu: out of nocache %d: %d/%d\n",
+		       size, (int) srmmu_nocache_size,
+		       srmmu_nocache_map.used << SRMMU_NOCACHE_BITMAP_SHIFT);
 		return 0;
 	}
 
-	return (SRMMU_NOCACHE_VADDR + (offset << SRMMU_NOCACHE_BITMAP_SHIFT));
+	addr = SRMMU_NOCACHE_VADDR + (offset << SRMMU_NOCACHE_BITMAP_SHIFT);
+	return (void *)addr;
 }
 
-unsigned long srmmu_get_nocache(int size, int align)
+void *srmmu_get_nocache(int size, int align)
 {
-	unsigned long tmp;
+	void *tmp;
 
 	tmp = __srmmu_get_nocache(size, align);
 
 	if (tmp)
-		memset((void *)tmp, 0, size);
+		memset(tmp, 0, size);
 
 	return tmp;
 }
 
-void srmmu_free_nocache(unsigned long vaddr, int size)
+void srmmu_free_nocache(void *addr, int size)
 {
+	unsigned long vaddr;
 	int offset;
 
+	vaddr = (unsigned long)addr;
 	if (vaddr < SRMMU_NOCACHE_VADDR) {
 		printk("Vaddr %lx is smaller than nocache base 0x%lx\n",
 		    vaddr, (unsigned long)SRMMU_NOCACHE_VADDR);
 		BUG();
 	}
-	if (vaddr+size > srmmu_nocache_end) {
+	if (vaddr + size > srmmu_nocache_end) {
 		printk("Vaddr %lx is bigger than nocache end 0x%lx\n",
 		    vaddr, srmmu_nocache_end);
 		BUG();
@@ -212,7 +214,7 @@ void srmmu_free_nocache(unsigned long vaddr, int size)
 		printk("Size 0x%x is too small\n", size);
 		BUG();
 	}
-	if (vaddr & (size-1)) {
+	if (vaddr & (size - 1)) {
 		printk("Vaddr %lx is not aligned to size 0x%x\n", vaddr, size);
 		BUG();
 	}
@@ -226,13 +228,23 @@ void srmmu_free_nocache(unsigned long vaddr, int size)
 static void srmmu_early_allocate_ptable_skeleton(unsigned long start,
 						 unsigned long end);
 
-extern unsigned long probe_memory(void);	/* in fault.c */
+/* Return how much physical memory we have.  */
+static unsigned long __init probe_memory(void)
+{
+	unsigned long total = 0;
+	int i;
+
+	for (i = 0; sp_banks[i].num_bytes; i++)
+		total += sp_banks[i].num_bytes;
+
+	return total;
+}
 
 /*
  * Reserve nocache dynamically proportionally to the amount of
  * system RAM. -- Tomas Szepe <szepe@pinerecords.com>, June 2002
  */
-static void srmmu_nocache_calcsize(void)
+static void __init srmmu_nocache_calcsize(void)
 {
 	unsigned long sysmemavail = probe_memory() / 1024;
 	int srmmu_nocache_npages;
@@ -271,7 +283,7 @@ static void __init srmmu_nocache_init(void)
 	srmmu_nocache_bitmap = __alloc_bootmem(bitmap_bits >> 3, SMP_CACHE_BYTES, 0UL);
 	bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits);
 
-	srmmu_swapper_pg_dir = (pgd_t *)__srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE);
+	srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE);
 	memset(__nocache_fix(srmmu_swapper_pg_dir), 0, SRMMU_PGD_TABLE_SIZE);
 	init_mm.pgd = srmmu_swapper_pg_dir;
 
@@ -304,7 +316,7 @@ pgd_t *get_pgd_fast(void)
 {
 	pgd_t *pgd = NULL;
 
-	pgd = (pgd_t *)__srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE);
+	pgd = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE);
 	if (pgd) {
 		pgd_t *init = pgd_offset_k(0);
 		memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
@@ -330,7 +342,7 @@ pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
 
 	if ((pte = (unsigned long)pte_alloc_one_kernel(mm, address)) == 0)
 		return NULL;
-	page = pfn_to_page( __nocache_pa(pte) >> PAGE_SHIFT );
+	page = pfn_to_page(__nocache_pa(pte) >> PAGE_SHIFT);
 	pgtable_page_ctor(page);
 	return page;
 }
@@ -344,18 +356,50 @@ void pte_free(struct mm_struct *mm, pgtable_t pte)
 	if (p == 0)
 		BUG();
 	p = page_to_pfn(pte) << PAGE_SHIFT;	/* Physical address */
-	p = (unsigned long) __nocache_va(p);	/* Nocached virtual */
-	srmmu_free_nocache(p, PTE_SIZE);
+
+	/* free non cached virtual address*/
+	srmmu_free_nocache(__nocache_va(p), PTE_SIZE);
 }
 
-/*
- */
+/* context handling - a dynamically sized pool is used */
+#define NO_CONTEXT	-1
+
+struct ctx_list {
+	struct ctx_list *next;
+	struct ctx_list *prev;
+	unsigned int ctx_number;
+	struct mm_struct *ctx_mm;
+};
+
+static struct ctx_list *ctx_list_pool;
+static struct ctx_list ctx_free;
+static struct ctx_list ctx_used;
+
+/* At boot time we determine the number of contexts */
+static int num_contexts;
+
+static inline void remove_from_ctx_list(struct ctx_list *entry)
+{
+	entry->next->prev = entry->prev;
+	entry->prev->next = entry->next;
+}
+
+static inline void add_to_ctx_list(struct ctx_list *head, struct ctx_list *entry)
+{
+	entry->next = head;
+	(entry->prev = head->prev)->next = entry;
+	head->prev = entry;
+}
+#define add_to_free_ctxlist(entry) add_to_ctx_list(&ctx_free, entry)
+#define add_to_used_ctxlist(entry) add_to_ctx_list(&ctx_used, entry)
+
+
 static inline void alloc_context(struct mm_struct *old_mm, struct mm_struct *mm)
 {
 	struct ctx_list *ctxp;
 
 	ctxp = ctx_free.next;
-	if(ctxp != &ctx_free) {
+	if (ctxp != &ctx_free) {
 		remove_from_ctx_list(ctxp);
 		add_to_used_ctxlist(ctxp);
 		mm->context = ctxp->ctx_number;
@@ -363,9 +407,9 @@ static inline void alloc_context(struct mm_struct *old_mm, struct mm_struct *mm)
 		return;
 	}
 	ctxp = ctx_used.next;
-	if(ctxp->ctx_mm == old_mm)
+	if (ctxp->ctx_mm == old_mm)
 		ctxp = ctxp->next;
-	if(ctxp == &ctx_used)
+	if (ctxp == &ctx_used)
 		panic("out of mmu contexts");
 	flush_cache_mm(ctxp->ctx_mm);
 	flush_tlb_mm(ctxp->ctx_mm);
@@ -385,11 +429,31 @@ static inline void free_context(int context)
 	add_to_free_ctxlist(ctx_old);
 }
 
+static void __init sparc_context_init(int numctx)
+{
+	int ctx;
+	unsigned long size;
+
+	size = numctx * sizeof(struct ctx_list);
+	ctx_list_pool = __alloc_bootmem(size, SMP_CACHE_BYTES, 0UL);
+
+	for (ctx = 0; ctx < numctx; ctx++) {
+		struct ctx_list *clist;
+
+		clist = (ctx_list_pool + ctx);
+		clist->ctx_number = ctx;
+		clist->ctx_mm = NULL;
+	}
+	ctx_free.next = ctx_free.prev = &ctx_free;
+	ctx_used.next = ctx_used.prev = &ctx_used;
+	for (ctx = 0; ctx < numctx; ctx++)
+		add_to_free_ctxlist(ctx_list_pool + ctx);
+}
 
 void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm,
 	       struct task_struct *tsk)
 {
-	if(mm->context == NO_CONTEXT) {
+	if (mm->context == NO_CONTEXT) {
 		spin_lock(&srmmu_context_spinlock);
 		alloc_context(old_mm, mm);
 		spin_unlock(&srmmu_context_spinlock);
@@ -407,7 +471,7 @@ void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm,
 
 /* Low level IO area allocation on the SRMMU. */
 static inline void srmmu_mapioaddr(unsigned long physaddr,
-    unsigned long virt_addr, int bus_type)
+				   unsigned long virt_addr, int bus_type)
 {
 	pgd_t *pgdp;
 	pmd_t *pmdp;
@@ -420,8 +484,7 @@ static inline void srmmu_mapioaddr(unsigned long physaddr,
 	ptep = pte_offset_kernel(pmdp, virt_addr);
 	tmp = (physaddr >> 4) | SRMMU_ET_PTE;
 
-	/*
-	 * I need to test whether this is consistent over all
+	/* I need to test whether this is consistent over all
 	 * sun4m's.  The bus_type represents the upper 4 bits of
 	 * 36-bit physical address on the I/O space lines...
 	 */
@@ -591,10 +654,10 @@ static void __init srmmu_early_allocate_ptable_skeleton(unsigned long start,
 	pmd_t *pmdp;
 	pte_t *ptep;
 
-	while(start < end) {
+	while (start < end) {
 		pgdp = pgd_offset_k(start);
 		if (pgd_none(*(pgd_t *)__nocache_fix(pgdp))) {
-			pmdp = (pmd_t *) __srmmu_get_nocache(
+			pmdp = __srmmu_get_nocache(
 			    SRMMU_PMD_TABLE_SIZE, SRMMU_PMD_TABLE_SIZE);
 			if (pmdp == NULL)
 				early_pgtable_allocfail("pmd");
@@ -602,8 +665,8 @@ static void __init srmmu_early_allocate_ptable_skeleton(unsigned long start,
 			pgd_set(__nocache_fix(pgdp), pmdp);
 		}
 		pmdp = pmd_offset(__nocache_fix(pgdp), start);
-		if(srmmu_pmd_none(*(pmd_t *)__nocache_fix(pmdp))) {
-			ptep = (pte_t *)__srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
+		if (srmmu_pmd_none(*(pmd_t *)__nocache_fix(pmdp))) {
+			ptep = __srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
 			if (ptep == NULL)
 				early_pgtable_allocfail("pte");
 			memset(__nocache_fix(ptep), 0, PTE_SIZE);
@@ -622,18 +685,18 @@ static void __init srmmu_allocate_ptable_skeleton(unsigned long start,
 	pmd_t *pmdp;
 	pte_t *ptep;
 
-	while(start < end) {
+	while (start < end) {
 		pgdp = pgd_offset_k(start);
 		if (pgd_none(*pgdp)) {
-			pmdp = (pmd_t *)__srmmu_get_nocache(SRMMU_PMD_TABLE_SIZE, SRMMU_PMD_TABLE_SIZE);
+			pmdp = __srmmu_get_nocache(SRMMU_PMD_TABLE_SIZE, SRMMU_PMD_TABLE_SIZE);
 			if (pmdp == NULL)
 				early_pgtable_allocfail("pmd");
 			memset(pmdp, 0, SRMMU_PMD_TABLE_SIZE);
 			pgd_set(pgdp, pmdp);
 		}
 		pmdp = pmd_offset(pgdp, start);
-		if(srmmu_pmd_none(*pmdp)) {
-			ptep = (pte_t *) __srmmu_get_nocache(PTE_SIZE,
+		if (srmmu_pmd_none(*pmdp)) {
+			ptep = __srmmu_get_nocache(PTE_SIZE,
 							     PTE_SIZE);
 			if (ptep == NULL)
 				early_pgtable_allocfail("pte");
@@ -671,72 +734,76 @@ static inline unsigned long srmmu_probe(unsigned long vaddr)
 static void __init srmmu_inherit_prom_mappings(unsigned long start,
 					       unsigned long end)
 {
+	unsigned long probed;
+	unsigned long addr;
 	pgd_t *pgdp;
 	pmd_t *pmdp;
 	pte_t *ptep;
-	int what = 0; /* 0 = normal-pte, 1 = pmd-level pte, 2 = pgd-level pte */
-	unsigned long prompte;
+	int what; /* 0 = normal-pte, 1 = pmd-level pte, 2 = pgd-level pte */
 
-	while(start <= end) {
+	while (start <= end) {
 		if (start == 0)
 			break; /* probably wrap around */
-		if(start == 0xfef00000)
+		if (start == 0xfef00000)
 			start = KADB_DEBUGGER_BEGVM;
-		if(!(prompte = srmmu_probe(start))) {
+		probed = srmmu_probe(start);
+		if (!probed) {
+			/* continue probing until we find an entry */
 			start += PAGE_SIZE;
 			continue;
 		}
-    
+
 		/* A red snapper, see what it really is. */
 		what = 0;
-    
-		if(!(start & ~(SRMMU_REAL_PMD_MASK))) {
-			if(srmmu_probe((start-PAGE_SIZE) + SRMMU_REAL_PMD_SIZE) == prompte)
+		addr = start - PAGE_SIZE;
+
+		if (!(start & ~(SRMMU_REAL_PMD_MASK))) {
+			if (srmmu_probe(addr + SRMMU_REAL_PMD_SIZE) == probed)
 				what = 1;
 		}
-    
-		if(!(start & ~(SRMMU_PGDIR_MASK))) {
-			if(srmmu_probe((start-PAGE_SIZE) + SRMMU_PGDIR_SIZE) ==
-			   prompte)
+
+		if (!(start & ~(SRMMU_PGDIR_MASK))) {
+			if (srmmu_probe(addr + SRMMU_PGDIR_SIZE) == probed)
 				what = 2;
 		}
-    
+
 		pgdp = pgd_offset_k(start);
-		if(what == 2) {
-			*(pgd_t *)__nocache_fix(pgdp) = __pgd(prompte);
+		if (what == 2) {
+			*(pgd_t *)__nocache_fix(pgdp) = __pgd(probed);
 			start += SRMMU_PGDIR_SIZE;
 			continue;
 		}
 		if (pgd_none(*(pgd_t *)__nocache_fix(pgdp))) {
-			pmdp = (pmd_t *)__srmmu_get_nocache(SRMMU_PMD_TABLE_SIZE, SRMMU_PMD_TABLE_SIZE);
+			pmdp = __srmmu_get_nocache(SRMMU_PMD_TABLE_SIZE,
+						   SRMMU_PMD_TABLE_SIZE);
 			if (pmdp == NULL)
 				early_pgtable_allocfail("pmd");
 			memset(__nocache_fix(pmdp), 0, SRMMU_PMD_TABLE_SIZE);
 			pgd_set(__nocache_fix(pgdp), pmdp);
 		}
 		pmdp = pmd_offset(__nocache_fix(pgdp), start);
-		if(srmmu_pmd_none(*(pmd_t *)__nocache_fix(pmdp))) {
-			ptep = (pte_t *) __srmmu_get_nocache(PTE_SIZE,
-							     PTE_SIZE);
+		if (srmmu_pmd_none(*(pmd_t *)__nocache_fix(pmdp))) {
+			ptep = __srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
 			if (ptep == NULL)
 				early_pgtable_allocfail("pte");
 			memset(__nocache_fix(ptep), 0, PTE_SIZE);
 			pmd_set(__nocache_fix(pmdp), ptep);
 		}
-		if(what == 1) {
-			/*
-			 * We bend the rule where all 16 PTPs in a pmd_t point
+		if (what == 1) {
+			/* We bend the rule where all 16 PTPs in a pmd_t point
 			 * inside the same PTE page, and we leak a perfectly
 			 * good hardware PTE piece. Alternatives seem worse.
 			 */
 			unsigned int x;	/* Index of HW PMD in soft cluster */
+			unsigned long *val;
 			x = (start >> PMD_SHIFT) & 15;
-			*(unsigned long *)__nocache_fix(&pmdp->pmdv[x]) = prompte;
+			val = &pmdp->pmdv[x];
+			*(unsigned long *)__nocache_fix(val) = probed;
 			start += SRMMU_REAL_PMD_SIZE;
 			continue;
 		}
 		ptep = pte_offset_kernel(__nocache_fix(pmdp), start);
-		*(pte_t *)__nocache_fix(ptep) = __pte(prompte);
+		*(pte_t *)__nocache_fix(ptep) = __pte(probed);
 		start += PAGE_SIZE;
 	}
 }
@@ -765,18 +832,18 @@ static unsigned long __init map_spbank(unsigned long vbase, int sp_entry)
 
 	if (vstart < min_vaddr || vstart >= max_vaddr)
 		return vstart;
-	
+
 	if (vend > max_vaddr || vend < min_vaddr)
 		vend = max_vaddr;
 
-	while(vstart < vend) {
+	while (vstart < vend) {
 		do_large_mapping(vstart, pstart);
 		vstart += SRMMU_PGDIR_SIZE; pstart += SRMMU_PGDIR_SIZE;
 	}
 	return vstart;
 }
 
-static inline void map_kernel(void)
+static void __init map_kernel(void)
 {
 	int i;
 
@@ -789,9 +856,6 @@ static inline void map_kernel(void)
 	}
 }
 
-/* Paging initialization on the Sparc Reference MMU. */
-extern void sparc_context_init(int);
-
 void (*poke_srmmu)(void) __cpuinitdata = NULL;
 
 extern unsigned long bootmem_init(unsigned long *pages_avail);
@@ -806,6 +870,7 @@ void __init srmmu_paging_init(void)
 	pte_t *pte;
 	unsigned long pages_avail;
 
+	init_mm.context = (unsigned long) NO_CONTEXT;
 	sparc_iomap.start = SUN4M_IOBASE_VADDR;	/* 16MB of IOSPACE on all sun4m's. */
 
 	if (sparc_cpu_model == sun4d)
@@ -814,9 +879,9 @@ void __init srmmu_paging_init(void)
 		/* Find the number of contexts on the srmmu. */
 		cpunode = prom_getchild(prom_root_node);
 		num_contexts = 0;
-		while(cpunode != 0) {
+		while (cpunode != 0) {
 			prom_getstring(cpunode, "device_type", node_str, sizeof(node_str));
-			if(!strcmp(node_str, "cpu")) {
+			if (!strcmp(node_str, "cpu")) {
 				num_contexts = prom_getintdefault(cpunode, "mmu-nctx", 0x8);
 				break;
 			}
@@ -824,7 +889,7 @@ void __init srmmu_paging_init(void)
 		}
 	}
 
-	if(!num_contexts) {
+	if (!num_contexts) {
 		prom_printf("Something wrong, can't find cpu node in paging_init.\n");
 		prom_halt();
 	}
@@ -834,14 +899,14 @@ void __init srmmu_paging_init(void)
 
 	srmmu_nocache_calcsize();
 	srmmu_nocache_init();
-        srmmu_inherit_prom_mappings(0xfe400000,(LINUX_OPPROM_ENDVM-PAGE_SIZE));
+	srmmu_inherit_prom_mappings(0xfe400000, (LINUX_OPPROM_ENDVM - PAGE_SIZE));
 	map_kernel();
 
 	/* ctx table has to be physically aligned to its size */
-	srmmu_context_table = (ctxd_t *)__srmmu_get_nocache(num_contexts*sizeof(ctxd_t), num_contexts*sizeof(ctxd_t));
+	srmmu_context_table = __srmmu_get_nocache(num_contexts * sizeof(ctxd_t), num_contexts * sizeof(ctxd_t));
 	srmmu_ctx_table_phys = (ctxd_t *)__nocache_pa((unsigned long)srmmu_context_table);
 
-	for(i = 0; i < num_contexts; i++)
+	for (i = 0; i < num_contexts; i++)
 		srmmu_ctxd_set((ctxd_t *)__nocache_fix(&srmmu_context_table[i]), srmmu_swapper_pg_dir);
 
 	flush_cache_all();
@@ -897,7 +962,7 @@ void __init srmmu_paging_init(void)
 
 void mmu_info(struct seq_file *m)
 {
-	seq_printf(m, 
+	seq_printf(m,
 		   "MMU type\t: %s\n"
 		   "contexts\t: %d\n"
 		   "nocache total\t: %ld\n"
@@ -908,10 +973,16 @@ void mmu_info(struct seq_file *m)
 		   srmmu_nocache_map.used << SRMMU_NOCACHE_BITMAP_SHIFT);
 }
 
+int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+	mm->context = NO_CONTEXT;
+	return 0;
+}
+
 void destroy_context(struct mm_struct *mm)
 {
 
-	if(mm->context != NO_CONTEXT) {
+	if (mm->context != NO_CONTEXT) {
 		flush_cache_mm(mm);
 		srmmu_ctxd_set(&srmmu_context_table[mm->context], srmmu_swapper_pg_dir);
 		flush_tlb_mm(mm);
@@ -941,13 +1012,12 @@ static void __init init_vac_layout(void)
 #endif
 
 	nd = prom_getchild(prom_root_node);
-	while((nd = prom_getsibling(nd)) != 0) {
+	while ((nd = prom_getsibling(nd)) != 0) {
 		prom_getstring(nd, "device_type", node_str, sizeof(node_str));
-		if(!strcmp(node_str, "cpu")) {
+		if (!strcmp(node_str, "cpu")) {
 			vac_line_size = prom_getint(nd, "cache-line-size");
 			if (vac_line_size == -1) {
-				prom_printf("can't determine cache-line-size, "
-					    "halting.\n");
+				prom_printf("can't determine cache-line-size, halting.\n");
 				prom_halt();
 			}
 			cache_lines = prom_getint(nd, "cache-nlines");
@@ -958,9 +1028,9 @@ static void __init init_vac_layout(void)
 
 			vac_cache_size = cache_lines * vac_line_size;
 #ifdef CONFIG_SMP
-			if(vac_cache_size > max_size)
+			if (vac_cache_size > max_size)
 				max_size = vac_cache_size;
-			if(vac_line_size < min_line_size)
+			if (vac_line_size < min_line_size)
 				min_line_size = vac_line_size;
 			//FIXME: cpus not contiguous!!
 			cpu++;
@@ -971,7 +1041,7 @@ static void __init init_vac_layout(void)
 #endif
 		}
 	}
-	if(nd == 0) {
+	if (nd == 0) {
 		prom_printf("No CPU nodes found, halting.\n");
 		prom_halt();
 	}
@@ -1082,7 +1152,7 @@ static void __init init_swift(void)
 			     "=r" (swift_rev) :
 			     "r" (SWIFT_MASKID_ADDR), "i" (ASI_M_BYPASS));
 	srmmu_name = "Fujitsu Swift";
-	switch(swift_rev) {
+	switch (swift_rev) {
 	case 0x11:
 	case 0x20:
 	case 0x23:
@@ -1222,10 +1292,11 @@ static void __cpuinit poke_turbosparc(void)
 
 	/* Clear any crap from the cache or else... */
 	turbosparc_flush_cache_all();
-	mreg &= ~(TURBOSPARC_ICENABLE | TURBOSPARC_DCENABLE); /* Temporarily disable I & D caches */
+	/* Temporarily disable I & D caches */
+	mreg &= ~(TURBOSPARC_ICENABLE | TURBOSPARC_DCENABLE);
 	mreg &= ~(TURBOSPARC_PCENABLE);		/* Don't check parity */
 	srmmu_set_mmureg(mreg);
-	
+
 	ccreg = turbosparc_get_ccreg();
 
 #ifdef TURBOSPARC_WRITEBACK
@@ -1248,7 +1319,7 @@ static void __cpuinit poke_turbosparc(void)
 	default:
 		ccreg |= (TURBOSPARC_SCENABLE);
 	}
-	turbosparc_set_ccreg (ccreg);
+	turbosparc_set_ccreg(ccreg);
 
 	mreg |= (TURBOSPARC_ICENABLE | TURBOSPARC_DCENABLE); /* I & D caches on */
 	mreg |= (TURBOSPARC_ICSNOOP);		/* Icache snooping on */
@@ -1342,7 +1413,7 @@ static void __cpuinit poke_viking(void)
 		unsigned long bpreg;
 
 		mreg &= ~(VIKING_TCENABLE);
-		if(smp_catch++) {
+		if (smp_catch++) {
 			/* Must disable mixed-cmd mode here for other cpu's. */
 			bpreg = viking_get_bpreg();
 			bpreg &= ~(VIKING_ACTION_MIX);
@@ -1411,7 +1482,7 @@ static void __init init_viking(void)
 	unsigned long mreg = srmmu_get_mmureg();
 
 	/* Ahhh, the viking.  SRMMU VLSI abortion number two... */
-	if(mreg & VIKING_MMODE) {
+	if (mreg & VIKING_MMODE) {
 		srmmu_name = "TI Viking";
 		viking_mxcc_present = 0;
 		msi_set_sync();
@@ -1467,8 +1538,8 @@ static void __init get_srmmu_type(void)
 	}
 
 	/* Second, check for HyperSparc or Cypress. */
-	if(mod_typ == 1) {
-		switch(mod_rev) {
+	if (mod_typ == 1) {
+		switch (mod_rev) {
 		case 7:
 			/* UP or MP Hypersparc */
 			init_hypersparc();
@@ -1488,9 +1559,8 @@ static void __init get_srmmu_type(void)
 		}
 		return;
 	}
-	
-	/*
-	 * Now Fujitsu TurboSparc. It might happen that it is
+
+	/* Now Fujitsu TurboSparc. It might happen that it is
 	 * in Swift emulation mode, so we will check later...
 	 */
 	if (psr_typ == 0 && psr_vers == 5) {
@@ -1499,15 +1569,15 @@ static void __init get_srmmu_type(void)
 	}
 
 	/* Next check for Fujitsu Swift. */
-	if(psr_typ == 0 && psr_vers == 4) {
+	if (psr_typ == 0 && psr_vers == 4) {
 		phandle cpunode;
 		char node_str[128];
 
 		/* Look if it is not a TurboSparc emulating Swift... */
 		cpunode = prom_getchild(prom_root_node);
-		while((cpunode = prom_getsibling(cpunode)) != 0) {
+		while ((cpunode = prom_getsibling(cpunode)) != 0) {
 			prom_getstring(cpunode, "device_type", node_str, sizeof(node_str));
-			if(!strcmp(node_str, "cpu")) {
+			if (!strcmp(node_str, "cpu")) {
 				if (!prom_getintdefault(cpunode, "psr-implementation", 1) &&
 				    prom_getintdefault(cpunode, "psr-version", 1) == 5) {
 					init_turbosparc();
@@ -1516,13 +1586,13 @@ static void __init get_srmmu_type(void)
 				break;
 			}
 		}
-		
+
 		init_swift();
 		return;
 	}
 
 	/* Now the Viking family of srmmu. */
-	if(psr_typ == 4 &&
+	if (psr_typ == 4 &&
 	   ((psr_vers == 0) ||
 	    ((psr_vers == 1) && (mod_typ == 0) && (mod_rev == 0)))) {
 		init_viking();
@@ -1530,7 +1600,7 @@ static void __init get_srmmu_type(void)
 	}
 
 	/* Finally the Tsunami. */
-	if(psr_typ == 4 && psr_vers == 1 && (mod_typ || mod_rev)) {
+	if (psr_typ == 4 && psr_vers == 1 && (mod_typ || mod_rev)) {
 		init_tsunami();
 		return;
 	}
diff --git a/arch/sparc/prom/init_32.c b/arch/sparc/prom/init_32.c
index 26c64cea3c9c..9ac30c2b7dba 100644
--- a/arch/sparc/prom/init_32.c
+++ b/arch/sparc/prom/init_32.c
@@ -27,13 +27,10 @@ EXPORT_SYMBOL(prom_root_node);
 struct linux_nodeops *prom_nodeops;
 
 /* You must call prom_init() before you attempt to use any of the
- * routines in the prom library.  It returns 0 on success, 1 on
- * failure.  It gets passed the pointer to the PROM vector.
+ * routines in the prom library.
+ * It gets passed the pointer to the PROM vector.
  */
 
-extern void prom_meminit(void);
-extern void prom_ranges_init(void);
-
 void __init prom_init(struct linux_romvec *rp)
 {
 	romvec = rp;
diff --git a/arch/sparc/prom/init_64.c b/arch/sparc/prom/init_64.c
index 5016c5e20575..d95db755828f 100644
--- a/arch/sparc/prom/init_64.c
+++ b/arch/sparc/prom/init_64.c
@@ -22,8 +22,8 @@ int prom_stdout;
 phandle prom_chosen_node;
 
 /* You must call prom_init() before you attempt to use any of the
- * routines in the prom library.  It returns 0 on success, 1 on
- * failure.  It gets passed the pointer to the PROM vector.
+ * routines in the prom library.
+ * It gets passed the pointer to the PROM vector.
  */
 
 extern void prom_cif_init(void *, void *);
diff --git a/arch/tile/configs/tilegx_defconfig b/arch/tile/configs/tilegx_defconfig
index b8d99aca5431..0270620a1692 100644
--- a/arch/tile/configs/tilegx_defconfig
+++ b/arch/tile/configs/tilegx_defconfig
@@ -18,8 +18,8 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y
diff --git a/arch/tile/configs/tilepro_defconfig b/arch/tile/configs/tilepro_defconfig
index 2b1fd31894f1..c11de27a9bcb 100644
--- a/arch/tile/configs/tilepro_defconfig
+++ b/arch/tile/configs/tilepro_defconfig
@@ -17,8 +17,8 @@ CONFIG_CGROUP_DEVICE=y
 CONFIG_CPUSETS=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_RT_GROUP_SCHED=y
 CONFIG_BLK_CGROUP=y
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index fb7c65ae8de0..5bd71994452d 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -16,7 +16,6 @@ generic-y += fb.h
 generic-y += fcntl.h
 generic-y += ioctl.h
 generic-y += ioctls.h
-generic-y += ipc.h
 generic-y += ipcbuf.h
 generic-y += irq_regs.h
 generic-y += kdebug.h
diff --git a/arch/tile/include/asm/kmap_types.h b/arch/tile/include/asm/kmap_types.h
index 3d0f20246260..92b28e3e9972 100644
--- a/arch/tile/include/asm/kmap_types.h
+++ b/arch/tile/include/asm/kmap_types.h
@@ -23,35 +23,6 @@
  * adds 4MB of required address-space.  For now we leave KM_TYPE_NR
  * set to depth 8.
  */
-enum km_type {
-	KM_TYPE_NR = 8
-};
-
-/*
- * We provide dummy definitions of all the stray values that used to be
- * required for kmap_atomic() and no longer are.
- */
-enum {
-	KM_BOUNCE_READ,
-	KM_SKB_SUNRPC_DATA,
-	KM_SKB_DATA_SOFTIRQ,
-	KM_USER0,
-	KM_USER1,
-	KM_BIO_SRC_IRQ,
-	KM_BIO_DST_IRQ,
-	KM_PTE0,
-	KM_PTE1,
-	KM_IRQ0,
-	KM_IRQ1,
-	KM_SOFTIRQ0,
-	KM_SOFTIRQ1,
-	KM_SYNC_ICACHE,
-	KM_SYNC_DCACHE,
-	KM_UML_USERCOPY,
-	KM_IRQ_PTE,
-	KM_NMI,
-	KM_NMI_PTE,
-	KM_KDB
-};
+#define	KM_TYPE_NR 8
 
 #endif /* _ASM_TILE_KMAP_TYPES_H */
diff --git a/arch/tile/kernel/pci.c b/arch/tile/kernel/pci.c
index 0fdd99d0d8b7..33c10864d2f7 100644
--- a/arch/tile/kernel/pci.c
+++ b/arch/tile/kernel/pci.c
@@ -369,7 +369,7 @@ int __init pcibios_init(void)
 				 */
 				if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI &&
 					(PCI_SLOT(dev->devfn) == 0)) {
-					next_bus = dev->busn_res.end;
+					next_bus = dev->subordinate;
 					controllers[i].mem_resources[0] =
 						*next_bus->resource[0];
 					controllers[i].mem_resources[1] =
diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c
index fa75264a82ae..0e213e35ffc3 100644
--- a/arch/tile/kernel/pci_gx.c
+++ b/arch/tile/kernel/pci_gx.c
@@ -853,7 +853,7 @@ int __init pcibios_init(void)
 		bus = pci_scan_root_bus(NULL, next_busno, controller->ops,
 					controller, &resources);
 		controller->root_bus = bus;
-		next_busno = bus->subordinate + 1;
+		next_busno = bus->busn_res.end + 1;
 
 	}
 
diff --git a/arch/tile/mm/highmem.c b/arch/tile/mm/highmem.c
index ef8e5a62b6e3..347d123b14be 100644
--- a/arch/tile/mm/highmem.c
+++ b/arch/tile/mm/highmem.c
@@ -93,7 +93,7 @@ static DEFINE_PER_CPU(struct kmap_amps, amps);
  * If we examine it earlier we are exposed to a race where it looks
  * writable earlier, but becomes immutable before we write the PTE.
  */
-static void kmap_atomic_register(struct page *page, enum km_type type,
+static void kmap_atomic_register(struct page *page, int type,
 				 unsigned long va, pte_t *ptep, pte_t pteval)
 {
 	unsigned long flags;
diff --git a/arch/um/defconfig b/arch/um/defconfig
index 7823ab12e6a4..fec0d5d27460 100644
--- a/arch/um/defconfig
+++ b/arch/um/defconfig
@@ -155,10 +155,10 @@ CONFIG_CPUSETS=y
 CONFIG_PROC_PID_CPUSET=y
 CONFIG_CGROUP_CPUACCT=y
 CONFIG_RESOURCE_COUNTERS=y
-CONFIG_CGROUP_MEM_RES_CTLR=y
-CONFIG_CGROUP_MEM_RES_CTLR_SWAP=y
-# CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED is not set
-# CONFIG_CGROUP_MEM_RES_CTLR_KMEM is not set
+CONFIG_CGROUP_MEMCG=y
+CONFIG_CGROUP_MEMCG_SWAP=y
+# CONFIG_CGROUP_MEMCG_SWAP_ENABLED is not set
+# CONFIG_CGROUP_MEMCG_KMEM is not set
 CONFIG_CGROUP_SCHED=y
 CONFIG_FAIR_GROUP_SCHED=y
 # CONFIG_CFS_BANDWIDTH is not set
diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
index acfd0e0fd0c9..ac9d25c8dc01 100644
--- a/arch/um/drivers/line.c
+++ b/arch/um/drivers/line.c
@@ -362,18 +362,18 @@ static irqreturn_t line_write_interrupt(int irq, void *data)
 int line_setup_irq(int fd, int input, int output, struct line *line, void *data)
 {
 	const struct line_driver *driver = line->driver;
-	int err = 0, flags = IRQF_SHARED | IRQF_SAMPLE_RANDOM;
+	int err = 0;
 
 	if (input)
 		err = um_request_irq(driver->read_irq, fd, IRQ_READ,
-				       line_interrupt, flags,
-				       driver->read_irq_name, data);
+				     line_interrupt, IRQF_SHARED,
+				     driver->read_irq_name, data);
 	if (err)
 		return err;
 	if (output)
 		err = um_request_irq(driver->write_irq, fd, IRQ_WRITE,
-					line_write_interrupt, flags,
-					driver->write_irq_name, data);
+				     line_write_interrupt, IRQF_SHARED,
+				     driver->write_irq_name, data);
 	return err;
 }
 
@@ -779,8 +779,7 @@ void register_winch_irq(int fd, int tty_fd, int pid, struct tty_struct *tty,
 				   .stack	= stack });
 
 	if (um_request_irq(WINCH_IRQ, fd, IRQ_READ, winch_interrupt,
-			   IRQF_SHARED | IRQF_SAMPLE_RANDOM,
-			   "winch", winch) < 0) {
+			   IRQF_SHARED, "winch", winch) < 0) {
 		printk(KERN_ERR "register_winch_irq - failed to register "
 		       "IRQ\n");
 		goto out_free;
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index 43b39d61b538..664a60e8dfb4 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -774,8 +774,7 @@ static int __init mconsole_init(void)
 	register_reboot_notifier(&reboot_notifier);
 
 	err = um_request_irq(MCONSOLE_IRQ, sock, IRQ_READ, mconsole_interrupt,
-			     IRQF_SHARED | IRQF_SAMPLE_RANDOM,
-			     "mconsole", (void *)sock);
+			     IRQF_SHARED, "mconsole", (void *)sock);
 	if (err) {
 		printk(KERN_ERR "Failed to get IRQ for management console\n");
 		goto out;
diff --git a/arch/um/drivers/port_kern.c b/arch/um/drivers/port_kern.c
index 11866ffd45a9..1d83d50236e1 100644
--- a/arch/um/drivers/port_kern.c
+++ b/arch/um/drivers/port_kern.c
@@ -100,8 +100,7 @@ static int port_accept(struct port_list *port)
 		  .port 	= port });
 
 	if (um_request_irq(TELNETD_IRQ, socket[0], IRQ_READ, pipe_interrupt,
-			  IRQF_SHARED | IRQF_SAMPLE_RANDOM,
-			  "telnetd", conn)) {
+			  IRQF_SHARED, "telnetd", conn)) {
 		printk(KERN_ERR "port_accept : failed to get IRQ for "
 		       "telnetd\n");
 		goto out_free;
@@ -184,8 +183,7 @@ void *port_data(int port_num)
 	}
 
 	if (um_request_irq(ACCEPT_IRQ, fd, IRQ_READ, port_interrupt,
-			  IRQF_SHARED | IRQF_SAMPLE_RANDOM,
-			  "port", port)) {
+			  IRQF_SHARED, "port", port)) {
 		printk(KERN_ERR "Failed to get IRQ for port %d\n", port_num);
 		goto out_close;
 	}
diff --git a/arch/um/drivers/random.c b/arch/um/drivers/random.c
index b25296e6218a..e32c6aa6396f 100644
--- a/arch/um/drivers/random.c
+++ b/arch/um/drivers/random.c
@@ -131,8 +131,7 @@ static int __init rng_init (void)
 	random_fd = err;
 
 	err = um_request_irq(RANDOM_IRQ, random_fd, IRQ_READ, random_interrupt,
-			     IRQF_SAMPLE_RANDOM, "random",
-			     NULL);
+			     0, "random", NULL);
 	if (err)
 		goto err_out_cleanup_hw;
 
diff --git a/arch/um/drivers/xterm_kern.c b/arch/um/drivers/xterm_kern.c
index b68bbe269e01..e3031e69445d 100644
--- a/arch/um/drivers/xterm_kern.c
+++ b/arch/um/drivers/xterm_kern.c
@@ -50,8 +50,7 @@ int xterm_fd(int socket, int *pid_out)
 	init_completion(&data->ready);
 
 	err = um_request_irq(XTERM_IRQ, socket, IRQ_READ, xterm_interrupt,
-			     IRQF_SHARED | IRQF_SAMPLE_RANDOM,
-			     "xterm", data);
+			     IRQF_SHARED, "xterm", data);
 	if (err) {
 		printk(KERN_ERR "xterm_fd : failed to get IRQ for xterm, "
 		       "err = %d\n",  err);
diff --git a/arch/um/include/asm/kmap_types.h b/arch/um/include/asm/kmap_types.h
index 6c03acdb4405..2e0a6b1d8300 100644
--- a/arch/um/include/asm/kmap_types.h
+++ b/arch/um/include/asm/kmap_types.h
@@ -8,22 +8,6 @@
 
 /* No more #include "asm/arch/kmap_types.h" ! */
 
-enum km_type {
-	KM_BOUNCE_READ,
-	KM_SKB_SUNRPC_DATA,
-	KM_SKB_DATA_SOFTIRQ,
-	KM_USER0,
-	KM_USER1,
-	KM_UML_USERCOPY,	/* UML specific, for copy_*_user - used in do_op_one_page */
-	KM_BIO_SRC_IRQ,
-	KM_BIO_DST_IRQ,
-	KM_PTE0,
-	KM_PTE1,
-	KM_IRQ0,
-	KM_IRQ1,
-	KM_SOFTIRQ0,
-	KM_SOFTIRQ1,
-	KM_TYPE_NR
-};
+#define KM_TYPE_NR 14
 
 #endif
diff --git a/arch/um/kernel/sigio.c b/arch/um/kernel/sigio.c
index 2a1639255763..c88211139a51 100644
--- a/arch/um/kernel/sigio.c
+++ b/arch/um/kernel/sigio.c
@@ -25,8 +25,7 @@ int write_sigio_irq(int fd)
 	int err;
 
 	err = um_request_irq(SIGIO_WRITE_IRQ, fd, IRQ_READ, sigio_interrupt,
-			     IRQF_SAMPLE_RANDOM, "write sigio",
-			     NULL);
+			     0, "write sigio", NULL);
 	if (err) {
 		printk(KERN_ERR "write_sigio_irq : um_request_irq failed, "
 		       "err = %d\n", err);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index c70684f859e1..ba2657c49217 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -70,6 +70,7 @@ config X86
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_TEXT_POKE_SMP
 	select HAVE_GENERIC_HARDIRQS
+	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select SPARSE_IRQ
 	select GENERIC_FIND_FIRST_BIT
 	select GENERIC_IRQ_PROBE
@@ -84,6 +85,7 @@ config X86
 	select GENERIC_IOMAP
 	select DCACHE_WORD_ACCESS
 	select GENERIC_SMP_IDLE_THREAD
+	select ARCH_WANT_IPC_PARSE_VERSION if X86_32
 	select HAVE_ARCH_SECCOMP_FILTER
 	select BUILDTIME_EXTABLE_SORT
 	select GENERIC_CMOS_UPDATE
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index e46c2147397f..b322f124ee3c 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -129,6 +129,25 @@ config DOUBLEFAULT
 	  option saves about 4k and might cause you much additional grey
 	  hair.
 
+config DEBUG_TLBFLUSH
+	bool "Set upper limit of TLB entries to flush one-by-one"
+	depends on DEBUG_KERNEL && (X86_64 || X86_INVLPG)
+	---help---
+
+	X86-only for now.
+
+	This option allows the user to tune the amount of TLB entries the
+	kernel flushes one-by-one instead of doing a full TLB flush. In
+	certain situations, the former is cheaper. This is controlled by the
+	tlb_flushall_shift knob under /sys/kernel/debug/x86. If you set it
+	to -1, the code flushes the whole TLB unconditionally. Otherwise,
+	for positive values of it, the kernel will use single TLB entry
+	invalidating instructions according to the following formula:
+
+	flush_entries <= active_tlb_entries / 2^tlb_flushall_shift
+
+	If in doubt, say "N".
+
 config IOMMU_DEBUG
 	bool "Enable IOMMU debugging"
 	depends on GART_IOMMU && DEBUG_KERNEL
diff --git a/arch/x86/boot/compressed/cmdline.c b/arch/x86/boot/compressed/cmdline.c
index cb62f786990d..10f6b1178c68 100644
--- a/arch/x86/boot/compressed/cmdline.c
+++ b/arch/x86/boot/compressed/cmdline.c
@@ -1,5 +1,7 @@
 #include "misc.h"
 
+#ifdef CONFIG_EARLY_PRINTK
+
 static unsigned long fs;
 static inline void set_fs(unsigned long seg)
 {
@@ -19,3 +21,5 @@ int cmdline_find_option_bool(const char *option)
 {
 	return __cmdline_find_option_bool(real_mode->hdr.cmd_line_ptr, option);
 }
+
+#endif
diff --git a/arch/x86/boot/compressed/early_serial_console.c b/arch/x86/boot/compressed/early_serial_console.c
index 261e81fb9582..d3d003cb5481 100644
--- a/arch/x86/boot/compressed/early_serial_console.c
+++ b/arch/x86/boot/compressed/early_serial_console.c
@@ -1,5 +1,9 @@
 #include "misc.h"
 
+#ifdef CONFIG_EARLY_PRINTK
+
 int early_serial_base;
 
 #include "../early_serial_console.c"
+
+#endif
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 4e85f5f85837..b3e0227df2c9 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -729,32 +729,68 @@ fail:
  * need to create one ourselves (usually the bootloader would create
  * one for us).
  */
-static efi_status_t make_boot_params(struct boot_params *boot_params,
-				     efi_loaded_image_t *image,
-				     void *handle)
+struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
 {
-	struct efi_info *efi = &boot_params->efi_info;
-	struct apm_bios_info *bi = &boot_params->apm_bios_info;
-	struct sys_desc_table *sdt = &boot_params->sys_desc_table;
-	struct e820entry *e820_map = &boot_params->e820_map[0];
-	struct e820entry *prev = NULL;
-	struct setup_header *hdr = &boot_params->hdr;
-	unsigned long size, key, desc_size, _size;
-	efi_memory_desc_t *mem_map;
-	void *options = image->load_options;
-	u32 load_options_size = image->load_options_size / 2; /* ASCII */
+	struct boot_params *boot_params;
+	struct sys_desc_table *sdt;
+	struct apm_bios_info *bi;
+	struct setup_header *hdr;
+	struct efi_info *efi;
+	efi_loaded_image_t *image;
+	void *options;
+	u32 load_options_size;
+	efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
 	int options_size = 0;
 	efi_status_t status;
-	__u32 desc_version;
 	unsigned long cmdline;
-	u8 nr_entries;
 	u16 *s2;
 	u8 *s1;
 	int i;
 
+	sys_table = _table;
+
+	/* Check if we were booted by the EFI firmware */
+	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+		return NULL;
+
+	status = efi_call_phys3(sys_table->boottime->handle_protocol,
+				handle, &proto, (void *)&image);
+	if (status != EFI_SUCCESS) {
+		efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
+		return NULL;
+	}
+
+	status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
+	if (status != EFI_SUCCESS) {
+		efi_printk("Failed to alloc lowmem for boot params\n");
+		return NULL;
+	}
+
+	memset(boot_params, 0x0, 0x4000);
+
+	hdr = &boot_params->hdr;
+	efi = &boot_params->efi_info;
+	bi = &boot_params->apm_bios_info;
+	sdt = &boot_params->sys_desc_table;
+
+	/* Copy the second sector to boot_params */
+	memcpy(&hdr->jump, image->image_base + 512, 512);
+
+	/*
+	 * Fill out some of the header fields ourselves because the
+	 * EFI firmware loader doesn't load the first sector.
+	 */
+	hdr->root_flags = 1;
+	hdr->vid_mode = 0xffff;
+	hdr->boot_flag = 0xAA55;
+
+	hdr->code32_start = (__u64)(unsigned long)image->image_base;
+
 	hdr->type_of_loader = 0x21;
 
 	/* Convert unicode cmdline to ascii */
+	options = image->load_options;
+	load_options_size = image->load_options_size / 2; /* ASCII */
 	cmdline = 0;
 	s2 = (u16 *)options;
 
@@ -791,18 +827,36 @@ static efi_status_t make_boot_params(struct boot_params *boot_params,
 	hdr->ramdisk_image = 0;
 	hdr->ramdisk_size = 0;
 
-	status = handle_ramdisks(image, hdr);
-	if (status != EFI_SUCCESS)
-		goto free_cmdline;
-
-	setup_graphics(boot_params);
-
 	/* Clear APM BIOS info */
 	memset(bi, 0, sizeof(*bi));
 
 	memset(sdt, 0, sizeof(*sdt));
 
-	memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32));
+	status = handle_ramdisks(image, hdr);
+	if (status != EFI_SUCCESS)
+		goto fail2;
+
+	return boot_params;
+fail2:
+	if (options_size)
+		low_free(options_size, hdr->cmd_line_ptr);
+fail:
+	low_free(0x4000, (unsigned long)boot_params);
+	return NULL;
+}
+
+static efi_status_t exit_boot(struct boot_params *boot_params,
+			      void *handle)
+{
+	struct efi_info *efi = &boot_params->efi_info;
+	struct e820entry *e820_map = &boot_params->e820_map[0];
+	struct e820entry *prev = NULL;
+	unsigned long size, key, desc_size, _size;
+	efi_memory_desc_t *mem_map;
+	efi_status_t status;
+	__u32 desc_version;
+	u8 nr_entries;
+	int i;
 
 	size = sizeof(*mem_map) * 32;
 
@@ -811,7 +865,7 @@ again:
 	_size = size;
 	status = low_alloc(size, 1, (unsigned long *)&mem_map);
 	if (status != EFI_SUCCESS)
-		goto free_cmdline;
+		return status;
 
 	status = efi_call_phys5(sys_table->boottime->get_memory_map, &size,
 				mem_map, &key, &desc_size, &desc_version);
@@ -823,6 +877,7 @@ again:
 	if (status != EFI_SUCCESS)
 		goto free_mem_map;
 
+	memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32));
 	efi->efi_systab = (unsigned long)sys_table;
 	efi->efi_memdesc_size = desc_size;
 	efi->efi_memdesc_version = desc_version;
@@ -906,61 +961,13 @@ again:
 
 free_mem_map:
 	low_free(_size, (unsigned long)mem_map);
-free_cmdline:
-	if (options_size)
-		low_free(options_size, hdr->cmd_line_ptr);
-fail:
 	return status;
 }
 
-/*
- * On success we return a pointer to a boot_params structure, and NULL
- * on failure.
- */
-struct boot_params *efi_main(void *handle, efi_system_table_t *_table)
+static efi_status_t relocate_kernel(struct setup_header *hdr)
 {
-	struct boot_params *boot_params;
 	unsigned long start, nr_pages;
-	struct desc_ptr *gdt, *idt;
-	efi_loaded_image_t *image;
-	struct setup_header *hdr;
 	efi_status_t status;
-	efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
-	struct desc_struct *desc;
-
-	sys_table = _table;
-
-	/* Check if we were booted by the EFI firmware */
-	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
-		goto fail;
-
-	status = efi_call_phys3(sys_table->boottime->handle_protocol,
-				handle, &proto, (void *)&image);
-	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
-		goto fail;
-	}
-
-	status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
-	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to alloc lowmem for boot params\n");
-		goto fail;
-	}
-
-	memset(boot_params, 0x0, 0x4000);
-
-	hdr = &boot_params->hdr;
-
-	/* Copy the second sector to boot_params */
-	memcpy(&hdr->jump, image->image_base + 512, 512);
-
-	/*
-	 * Fill out some of the header fields ourselves because the
-	 * EFI firmware loader doesn't load the first sector.
-	 */
-	hdr->root_flags = 1;
-	hdr->vid_mode = 0xffff;
-	hdr->boot_flag = 0xAA55;
 
 	/*
 	 * The EFI firmware loader could have placed the kernel image
@@ -978,16 +985,40 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table)
 	if (status != EFI_SUCCESS) {
 		status = low_alloc(hdr->init_size, hdr->kernel_alignment,
 				   &start);
-		if (status != EFI_SUCCESS) {
+		if (status != EFI_SUCCESS)
 			efi_printk("Failed to alloc mem for kernel\n");
-			goto fail;
-		}
 	}
 
+	if (status == EFI_SUCCESS)
+		memcpy((void *)start, (void *)(unsigned long)hdr->code32_start,
+		       hdr->init_size);
+
+	hdr->pref_address = hdr->code32_start;
 	hdr->code32_start = (__u32)start;
-	hdr->pref_address = (__u64)(unsigned long)image->image_base;
 
-	memcpy((void *)start, image->image_base, image->image_size);
+	return status;
+}
+
+/*
+ * On success we return a pointer to a boot_params structure, and NULL
+ * on failure.
+ */
+struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
+			     struct boot_params *boot_params)
+{
+	struct desc_ptr *gdt, *idt;
+	efi_loaded_image_t *image;
+	struct setup_header *hdr = &boot_params->hdr;
+	efi_status_t status;
+	struct desc_struct *desc;
+
+	sys_table = _table;
+
+	/* Check if we were booted by the EFI firmware */
+	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+		goto fail;
+
+	setup_graphics(boot_params);
 
 	status = efi_call_phys3(sys_table->boottime->allocate_pool,
 				EFI_LOADER_DATA, sizeof(*gdt),
@@ -1015,7 +1046,18 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table)
 	idt->size = 0;
 	idt->address = 0;
 
-	status = make_boot_params(boot_params, image, handle);
+	/*
+	 * If the kernel isn't already loaded at the preferred load
+	 * address, relocate it.
+	 */
+	if (hdr->pref_address != hdr->code32_start) {
+		status = relocate_kernel(hdr);
+
+		if (status != EFI_SUCCESS)
+			goto fail;
+	}
+
+	status = exit_boot(boot_params, handle);
 	if (status != EFI_SUCCESS)
 		goto fail;
 
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index c85e3ac99bba..aa4aaf1b2380 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -42,6 +42,16 @@ ENTRY(startup_32)
 	 */
 	add	$0x4, %esp
 
+	call	make_boot_params
+	cmpl	$0, %eax
+	je	1f
+	movl	0x4(%esp), %esi
+	movl	(%esp), %ecx
+	pushl	%eax
+	pushl	%esi
+	pushl	%ecx
+
+	.org 0x30,0x90
 	call	efi_main
 	cmpl	$0, %eax
 	movl	%eax, %esi
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 87e03a13d8e3..2c4b171eec33 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -209,6 +209,16 @@ ENTRY(startup_64)
 	.org 0x210
 	mov	%rcx, %rdi
 	mov	%rdx, %rsi
+	pushq	%rdi
+	pushq	%rsi
+	call	make_boot_params
+	cmpq	$0,%rax
+	je	1f
+	mov	%rax, %rdx
+	popq	%rsi
+	popq	%rdi
+
+	.org 0x230,0x90
 	call	efi_main
 	movq	%rax,%rsi
 	cmpq	$0,%rax
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 7116dcba0c9e..88f7ff6da404 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -108,8 +108,6 @@ static void error(char *m);
  * This is set up by the setup-routine at boot-time
  */
 struct boot_params *real_mode;		/* Pointer to real-mode data */
-static int quiet;
-static int debug;
 
 void *memset(void *s, int c, size_t n);
 void *memcpy(void *dest, const void *src, size_t n);
@@ -170,15 +168,11 @@ static void serial_putchar(int ch)
 	outb(ch, early_serial_base + TXR);
 }
 
-void __putstr(int error, const char *s)
+void __putstr(const char *s)
 {
 	int x, y, pos;
 	char c;
 
-#ifndef CONFIG_X86_VERBOSE_BOOTUP
-	if (!error)
-		return;
-#endif
 	if (early_serial_base) {
 		const char *str = s;
 		while (*str) {
@@ -265,9 +259,9 @@ void *memcpy(void *dest, const void *src, size_t n)
 
 static void error(char *x)
 {
-	__putstr(1, "\n\n");
-	__putstr(1, x);
-	__putstr(1, "\n\n -- System halted");
+	error_putstr("\n\n");
+	error_putstr(x);
+	error_putstr("\n\n -- System halted");
 
 	while (1)
 		asm("hlt");
@@ -294,8 +288,7 @@ static void parse_elf(void *output)
 		return;
 	}
 
-	if (!quiet)
-		putstr("Parsing ELF... ");
+	debug_putstr("Parsing ELF... ");
 
 	phdrs = malloc(sizeof(*phdrs) * ehdr.e_phnum);
 	if (!phdrs)
@@ -332,11 +325,6 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 {
 	real_mode = rmode;
 
-	if (cmdline_find_option_bool("quiet"))
-		quiet = 1;
-	if (cmdline_find_option_bool("debug"))
-		debug = 1;
-
 	if (real_mode->screen_info.orig_video_mode == 7) {
 		vidmem = (char *) 0xb0000;
 		vidport = 0x3b4;
@@ -349,8 +337,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	cols = real_mode->screen_info.orig_video_cols;
 
 	console_init();
-	if (debug)
-		putstr("early console in decompress_kernel\n");
+	debug_putstr("early console in decompress_kernel\n");
 
 	free_mem_ptr     = heap;	/* Heap */
 	free_mem_end_ptr = heap + BOOT_HEAP_SIZE;
@@ -369,11 +356,9 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 		error("Wrong destination address");
 #endif
 
-	if (!quiet)
-		putstr("\nDecompressing Linux... ");
+	debug_putstr("\nDecompressing Linux... ");
 	decompress(input_data, input_len, NULL, NULL, output, NULL, error);
 	parse_elf(output);
-	if (!quiet)
-		putstr("done.\nBooting the kernel.\n");
+	debug_putstr("done.\nBooting the kernel.\n");
 	return;
 }
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 3f19c81a6203..0e6dc0ee0eea 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -24,9 +24,21 @@
 
 /* misc.c */
 extern struct boot_params *real_mode;		/* Pointer to real-mode data */
-void __putstr(int error, const char *s);
-#define putstr(__x)  __putstr(0, __x)
-#define puts(__x)  __putstr(0, __x)
+void __putstr(const char *s);
+#define error_putstr(__x)  __putstr(__x)
+
+#ifdef CONFIG_X86_VERBOSE_BOOTUP
+
+#define debug_putstr(__x)  __putstr(__x)
+
+#else
+
+static inline void debug_putstr(const char *s)
+{ }
+
+#endif
+
+#ifdef CONFIG_EARLY_PRINTK
 
 /* cmdline.c */
 int cmdline_find_option(const char *option, char *buffer, int bufsize);
@@ -36,4 +48,13 @@ int cmdline_find_option_bool(const char *option);
 extern int early_serial_base;
 void console_init(void);
 
+#else
+
+/* early_serial_console.c */
+static const int early_serial_base;
+static inline void console_init(void)
+{ }
+
+#endif
+
 #endif
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index efe5acfc79c3..b4e15dd6786a 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -283,7 +283,7 @@ _start:
 	# Part 2 of the header, from the old setup.S
 
 		.ascii	"HdrS"		# header signature
-		.word	0x020a		# header version number (>= 0x0105)
+		.word	0x020b		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 		.globl realmode_swtch
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
@@ -401,18 +401,13 @@ pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
 #define INIT_SIZE VO_INIT_SIZE
 #endif
 init_size:		.long INIT_SIZE		# kernel initialization size
+handover_offset:	.long 0x30		# offset to the handover
+						# protocol entry point
 
 # End of setup header #####################################################
 
 	.section ".entrytext", "ax"
 start_of_setup:
-#ifdef SAFE_RESET_DISK_CONTROLLER
-# Reset the disk controller.
-	movw	$0x0000, %ax		# Reset disk controller
-	movb	$0x80, %dl		# All disks
-	int	$0x13
-#endif
-
 # Force %es = %ds
 	movw	%ds, %ax
 	movw	%ax, %es
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index e191ac048b59..e908e5de82d3 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -2,6 +2,9 @@
 # Arch-specific CryptoAPI modules.
 #
 
+obj-$(CONFIG_CRYPTO_ABLK_HELPER_X86) += ablk_helper.o
+obj-$(CONFIG_CRYPTO_GLUE_HELPER_X86) += glue_helper.o
+
 obj-$(CONFIG_CRYPTO_AES_586) += aes-i586.o
 obj-$(CONFIG_CRYPTO_TWOFISH_586) += twofish-i586.o
 obj-$(CONFIG_CRYPTO_SALSA20_586) += salsa20-i586.o
@@ -12,8 +15,10 @@ obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
 obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
+obj-$(CONFIG_CRYPTO_TWOFISH_AVX_X86_64) += twofish-avx-x86_64.o
 obj-$(CONFIG_CRYPTO_SALSA20_X86_64) += salsa20-x86_64.o
 obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
+obj-$(CONFIG_CRYPTO_SERPENT_AVX_X86_64) += serpent-avx-x86_64.o
 obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
 obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
 
@@ -30,16 +35,11 @@ camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
 blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
 twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
 twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
+twofish-avx-x86_64-y := twofish-avx-x86_64-asm_64.o twofish_avx_glue.o
 salsa20-x86_64-y := salsa20-x86_64-asm_64.o salsa20_glue.o
 serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
+serpent-avx-x86_64-y := serpent-avx-x86_64-asm_64.o serpent_avx_glue.o
 
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o fpu.o
-
 ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
-
-# enable AVX support only when $(AS) can actually assemble the instructions
-ifeq ($(call as-instr,vpxor %xmm0$(comma)%xmm1$(comma)%xmm2,yes,no),yes)
-AFLAGS_sha1_ssse3_asm.o += -DSHA1_ENABLE_AVX_SUPPORT
-CFLAGS_sha1_ssse3_glue.o += -DSHA1_ENABLE_AVX_SUPPORT
-endif
 sha1-ssse3-y := sha1_ssse3_asm.o sha1_ssse3_glue.o
diff --git a/arch/x86/crypto/ablk_helper.c b/arch/x86/crypto/ablk_helper.c
new file mode 100644
index 000000000000..43282fe04a8b
--- /dev/null
+++ b/arch/x86/crypto/ablk_helper.c
@@ -0,0 +1,149 @@
+/*
+ * Shared async block cipher helpers
+ *
+ * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * Based on aesni-intel_glue.c by:
+ *  Copyright (C) 2008, Intel Corp.
+ *    Author: Huang Ying <ying.huang@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/crypto.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <crypto/algapi.h>
+#include <crypto/cryptd.h>
+#include <asm/i387.h>
+#include <asm/crypto/ablk_helper.h>
+
+int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+		 unsigned int key_len)
+{
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct crypto_ablkcipher *child = &ctx->cryptd_tfm->base;
+	int err;
+
+	crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(tfm)
+				    & CRYPTO_TFM_REQ_MASK);
+	err = crypto_ablkcipher_setkey(child, key, key_len);
+	crypto_ablkcipher_set_flags(tfm, crypto_ablkcipher_get_flags(child)
+				    & CRYPTO_TFM_RES_MASK);
+	return err;
+}
+EXPORT_SYMBOL_GPL(ablk_set_key);
+
+int __ablk_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	struct blkcipher_desc desc;
+
+	desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+	desc.info = req->info;
+	desc.flags = 0;
+
+	return crypto_blkcipher_crt(desc.tfm)->encrypt(
+		&desc, req->dst, req->src, req->nbytes);
+}
+EXPORT_SYMBOL_GPL(__ablk_encrypt);
+
+int ablk_encrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+	if (!irq_fpu_usable()) {
+		struct ablkcipher_request *cryptd_req =
+			ablkcipher_request_ctx(req);
+
+		memcpy(cryptd_req, req, sizeof(*req));
+		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+		return crypto_ablkcipher_encrypt(cryptd_req);
+	} else {
+		return __ablk_encrypt(req);
+	}
+}
+EXPORT_SYMBOL_GPL(ablk_encrypt);
+
+int ablk_decrypt(struct ablkcipher_request *req)
+{
+	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
+	struct async_helper_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+
+	if (!irq_fpu_usable()) {
+		struct ablkcipher_request *cryptd_req =
+			ablkcipher_request_ctx(req);
+
+		memcpy(cryptd_req, req, sizeof(*req));
+		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
+
+		return crypto_ablkcipher_decrypt(cryptd_req);
+	} else {
+		struct blkcipher_desc desc;
+
+		desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
+		desc.info = req->info;
+		desc.flags = 0;
+
+		return crypto_blkcipher_crt(desc.tfm)->decrypt(
+			&desc, req->dst, req->src, req->nbytes);
+	}
+}
+EXPORT_SYMBOL_GPL(ablk_decrypt);
+
+void ablk_exit(struct crypto_tfm *tfm)
+{
+	struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	cryptd_free_ablkcipher(ctx->cryptd_tfm);
+}
+EXPORT_SYMBOL_GPL(ablk_exit);
+
+int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name)
+{
+	struct async_helper_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct cryptd_ablkcipher *cryptd_tfm;
+
+	cryptd_tfm = cryptd_alloc_ablkcipher(drv_name, 0, 0);
+	if (IS_ERR(cryptd_tfm))
+		return PTR_ERR(cryptd_tfm);
+
+	ctx->cryptd_tfm = cryptd_tfm;
+	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
+		crypto_ablkcipher_reqsize(&cryptd_tfm->base);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ablk_init_common);
+
+int ablk_init(struct crypto_tfm *tfm)
+{
+	char drv_name[CRYPTO_MAX_ALG_NAME];
+
+	snprintf(drv_name, sizeof(drv_name), "__driver-%s",
+					crypto_tfm_alg_driver_name(tfm));
+
+	return ablk_init_common(tfm, drv_name);
+}
+EXPORT_SYMBOL_GPL(ablk_init);
+
+MODULE_LICENSE("GPL");
diff --git a/arch/x86/crypto/aes_glue.c b/arch/x86/crypto/aes_glue.c
index 8efcf42a9d7e..59b37deb8c8d 100644
--- a/arch/x86/crypto/aes_glue.c
+++ b/arch/x86/crypto/aes_glue.c
@@ -5,7 +5,7 @@
 
 #include <linux/module.h>
 #include <crypto/aes.h>
-#include <asm/aes.h>
+#include <asm/crypto/aes.h>
 
 asmlinkage void aes_enc_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in);
 asmlinkage void aes_dec_blk(struct crypto_aes_ctx *ctx, u8 *out, const u8 *in);
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index ac7f5cd019e8..34fdcff4d2c8 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -30,7 +30,8 @@
 #include <crypto/ctr.h>
 #include <asm/cpu_device_id.h>
 #include <asm/i387.h>
-#include <asm/aes.h>
+#include <asm/crypto/aes.h>
+#include <asm/crypto/ablk_helper.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/aead.h>
 #include <linux/workqueue.h>
@@ -52,10 +53,6 @@
 #define HAS_XTS
 #endif
 
-struct async_aes_ctx {
-	struct cryptd_ablkcipher *cryptd_tfm;
-};
-
 /* This data is stored at the end of the crypto_tfm struct.
  * It's a type of per "session" data storage location.
  * This needs to be 16 byte aligned.
@@ -377,87 +374,6 @@ static int ctr_crypt(struct blkcipher_desc *desc,
 }
 #endif
 
-static int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
-			unsigned int key_len)
-{
-	struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct crypto_ablkcipher *child = &ctx->cryptd_tfm->base;
-	int err;
-
-	crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(tfm)
-				    & CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(child, key, key_len);
-	crypto_ablkcipher_set_flags(tfm, crypto_ablkcipher_get_flags(child)
-				    & CRYPTO_TFM_RES_MASK);
-	return err;
-}
-
-static int ablk_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-
-	if (!irq_fpu_usable()) {
-		struct ablkcipher_request *cryptd_req =
-			ablkcipher_request_ctx(req);
-		memcpy(cryptd_req, req, sizeof(*req));
-		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-		return crypto_ablkcipher_encrypt(cryptd_req);
-	} else {
-		struct blkcipher_desc desc;
-		desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
-		desc.info = req->info;
-		desc.flags = 0;
-		return crypto_blkcipher_crt(desc.tfm)->encrypt(
-			&desc, req->dst, req->src, req->nbytes);
-	}
-}
-
-static int ablk_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct async_aes_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-
-	if (!irq_fpu_usable()) {
-		struct ablkcipher_request *cryptd_req =
-			ablkcipher_request_ctx(req);
-		memcpy(cryptd_req, req, sizeof(*req));
-		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-		return crypto_ablkcipher_decrypt(cryptd_req);
-	} else {
-		struct blkcipher_desc desc;
-		desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
-		desc.info = req->info;
-		desc.flags = 0;
-		return crypto_blkcipher_crt(desc.tfm)->decrypt(
-			&desc, req->dst, req->src, req->nbytes);
-	}
-}
-
-static void ablk_exit(struct crypto_tfm *tfm)
-{
-	struct async_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	cryptd_free_ablkcipher(ctx->cryptd_tfm);
-}
-
-static int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name)
-{
-	struct async_aes_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct cryptd_ablkcipher *cryptd_tfm;
-
-	cryptd_tfm = cryptd_alloc_ablkcipher(drv_name, 0, 0);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	ctx->cryptd_tfm = cryptd_tfm;
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
-		crypto_ablkcipher_reqsize(&cryptd_tfm->base);
-
-	return 0;
-}
-
 static int ablk_ecb_init(struct crypto_tfm *tfm)
 {
 	return ablk_init_common(tfm, "__driver-ecb-aes-aesni");
@@ -613,7 +529,7 @@ static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key,
 	struct crypto_aead *cryptd_child = cryptd_aead_child(ctx->cryptd_tfm);
 	struct aesni_rfc4106_gcm_ctx *child_ctx =
                                  aesni_rfc4106_gcm_ctx_get(cryptd_child);
-	u8 *new_key_mem = NULL;
+	u8 *new_key_align, *new_key_mem = NULL;
 
 	if (key_len < 4) {
 		crypto_tfm_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
@@ -637,9 +553,9 @@ static int rfc4106_set_key(struct crypto_aead *parent, const u8 *key,
 		if (!new_key_mem)
 			return -ENOMEM;
 
-		new_key_mem = PTR_ALIGN(new_key_mem, AESNI_ALIGN);
-		memcpy(new_key_mem, key, key_len);
-		key = new_key_mem;
+		new_key_align = PTR_ALIGN(new_key_mem, AESNI_ALIGN);
+		memcpy(new_key_align, key, key_len);
+		key = new_key_align;
 	}
 
 	if (!irq_fpu_usable())
@@ -968,7 +884,7 @@ static struct crypto_alg aesni_algs[] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_aes_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
@@ -989,7 +905,7 @@ static struct crypto_alg aesni_algs[] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_aes_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
@@ -1033,7 +949,7 @@ static struct crypto_alg aesni_algs[] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct async_aes_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
@@ -1098,7 +1014,7 @@ static struct crypto_alg aesni_algs[] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct async_aes_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
@@ -1126,7 +1042,7 @@ static struct crypto_alg aesni_algs[] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_aes_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
@@ -1150,7 +1066,7 @@ static struct crypto_alg aesni_algs[] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_aes_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
@@ -1174,7 +1090,7 @@ static struct crypto_alg aesni_algs[] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= AES_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_aes_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index 3306dc0b139e..eeb2b3b743e9 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -5,10 +5,6 @@
  *
  * Camellia parts based on code by:
  *  Copyright (C) 2006 NTT (Nippon Telegraph and Telephone Corporation)
- * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
- *   Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
- * CTR part based on code (crypto/ctr.c) by:
- *   (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -34,9 +30,9 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <crypto/algapi.h>
-#include <crypto/b128ops.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
+#include <asm/crypto/glue_helper.h>
 
 #define CAMELLIA_MIN_KEY_SIZE	16
 #define CAMELLIA_MAX_KEY_SIZE	32
@@ -1312,307 +1308,128 @@ static int camellia_setkey(struct crypto_tfm *tfm, const u8 *in_key,
 				 &tfm->crt_flags);
 }
 
-static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
-		     void (*fn)(struct camellia_ctx *, u8 *, const u8 *),
-		     void (*fn_2way)(struct camellia_ctx *, u8 *, const u8 *))
+static void camellia_decrypt_cbc_2way(void *ctx, u128 *dst, const u128 *src)
 {
-	struct camellia_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	unsigned int bsize = CAMELLIA_BLOCK_SIZE;
-	unsigned int nbytes;
-	int err;
-
-	err = blkcipher_walk_virt(desc, walk);
-
-	while ((nbytes = walk->nbytes)) {
-		u8 *wsrc = walk->src.virt.addr;
-		u8 *wdst = walk->dst.virt.addr;
-
-		/* Process two block batch */
-		if (nbytes >= bsize * 2) {
-			do {
-				fn_2way(ctx, wdst, wsrc);
-
-				wsrc += bsize * 2;
-				wdst += bsize * 2;
-				nbytes -= bsize * 2;
-			} while (nbytes >= bsize * 2);
-
-			if (nbytes < bsize)
-				goto done;
-		}
-
-		/* Handle leftovers */
-		do {
-			fn(ctx, wdst, wsrc);
-
-			wsrc += bsize;
-			wdst += bsize;
-			nbytes -= bsize;
-		} while (nbytes >= bsize);
-
-done:
-		err = blkcipher_walk_done(desc, walk, nbytes);
-	}
-
-	return err;
-}
-
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, camellia_enc_blk, camellia_enc_blk_2way);
-}
+	u128 iv = *src;
 
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, camellia_dec_blk, camellia_dec_blk_2way);
-}
+	camellia_dec_blk_2way(ctx, (u8 *)dst, (u8 *)src);
 
-static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
-{
-	struct camellia_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	unsigned int bsize = CAMELLIA_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	u128 *iv = (u128 *)walk->iv;
-
-	do {
-		u128_xor(dst, src, iv);
-		camellia_enc_blk(ctx, (u8 *)dst, (u8 *)dst);
-		iv = dst;
-
-		src += 1;
-		dst += 1;
-		nbytes -= bsize;
-	} while (nbytes >= bsize);
-
-	u128_xor((u128 *)walk->iv, (u128 *)walk->iv, iv);
-	return nbytes;
+	u128_xor(&dst[1], &dst[1], &iv);
 }
 
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static void camellia_crypt_ctr(void *ctx, u128 *dst, const u128 *src, u128 *iv)
 {
-	struct blkcipher_walk walk;
-	int err;
+	be128 ctrblk;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	if (dst != src)
+		*dst = *src;
 
-	while ((nbytes = walk.nbytes)) {
-		nbytes = __cbc_encrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
+	u128_to_be128(&ctrblk, iv);
+	u128_inc(iv);
 
-	return err;
+	camellia_enc_blk_xor(ctx, (u8 *)dst, (u8 *)&ctrblk);
 }
 
-static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
+static void camellia_crypt_ctr_2way(void *ctx, u128 *dst, const u128 *src,
+				    u128 *iv)
 {
-	struct camellia_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	unsigned int bsize = CAMELLIA_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	u128 ivs[2 - 1];
-	u128 last_iv;
+	be128 ctrblks[2];
 
-	/* Start of the last block. */
-	src += nbytes / bsize - 1;
-	dst += nbytes / bsize - 1;
-
-	last_iv = *src;
-
-	/* Process two block batch */
-	if (nbytes >= bsize * 2) {
-		do {
-			nbytes -= bsize * (2 - 1);
-			src -= 2 - 1;
-			dst -= 2 - 1;
-
-			ivs[0] = src[0];
-
-			camellia_dec_blk_2way(ctx, (u8 *)dst, (u8 *)src);
-
-			u128_xor(dst + 1, dst + 1, ivs + 0);
-
-			nbytes -= bsize;
-			if (nbytes < bsize)
-				goto done;
-
-			u128_xor(dst, dst, src - 1);
-			src -= 1;
-			dst -= 1;
-		} while (nbytes >= bsize * 2);
-
-		if (nbytes < bsize)
-			goto done;
+	if (dst != src) {
+		dst[0] = src[0];
+		dst[1] = src[1];
 	}
 
-	/* Handle leftovers */
-	for (;;) {
-		camellia_dec_blk(ctx, (u8 *)dst, (u8 *)src);
-
-		nbytes -= bsize;
-		if (nbytes < bsize)
-			break;
+	u128_to_be128(&ctrblks[0], iv);
+	u128_inc(iv);
+	u128_to_be128(&ctrblks[1], iv);
+	u128_inc(iv);
 
-		u128_xor(dst, dst, src - 1);
-		src -= 1;
-		dst -= 1;
-	}
-
-done:
-	u128_xor(dst, dst, (u128 *)walk->iv);
-	*(u128 *)walk->iv = last_iv;
-
-	return nbytes;
+	camellia_enc_blk_xor_2way(ctx, (u8 *)dst, (u8 *)ctrblks);
 }
 
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+static const struct common_glue_ctx camellia_enc = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = -1,
+
+	.funcs = { {
+		.num_blocks = 2,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_enc_blk) }
+	} }
+};
 
-	while ((nbytes = walk.nbytes)) {
-		nbytes = __cbc_decrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
+static const struct common_glue_ctx camellia_ctr = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = -1,
+
+	.funcs = { {
+		.num_blocks = 2,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(camellia_crypt_ctr) }
+	} }
+};
 
-	return err;
-}
+static const struct common_glue_ctx camellia_dec = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = -1,
+
+	.funcs = { {
+		.num_blocks = 2,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(camellia_dec_blk) }
+	} }
+};
 
-static inline void u128_to_be128(be128 *dst, const u128 *src)
-{
-	dst->a = cpu_to_be64(src->a);
-	dst->b = cpu_to_be64(src->b);
-}
+static const struct common_glue_ctx camellia_dec_cbc = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = -1,
+
+	.funcs = { {
+		.num_blocks = 2,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_decrypt_cbc_2way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(camellia_dec_blk) }
+	} }
+};
 
-static inline void be128_to_u128(u128 *dst, const be128 *src)
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
 {
-	dst->a = be64_to_cpu(src->a);
-	dst->b = be64_to_cpu(src->b);
+	return glue_ecb_crypt_128bit(&camellia_enc, desc, dst, src, nbytes);
 }
 
-static inline void u128_inc(u128 *i)
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
 {
-	i->b++;
-	if (!i->b)
-		i->a++;
+	return glue_ecb_crypt_128bit(&camellia_dec, desc, dst, src, nbytes);
 }
 
-static void ctr_crypt_final(struct blkcipher_desc *desc,
-			    struct blkcipher_walk *walk)
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
 {
-	struct camellia_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	u8 keystream[CAMELLIA_BLOCK_SIZE];
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	unsigned int nbytes = walk->nbytes;
-	u128 ctrblk;
-
-	memcpy(keystream, src, nbytes);
-	camellia_enc_blk_xor(ctx, keystream, walk->iv);
-	memcpy(dst, keystream, nbytes);
-
-	be128_to_u128(&ctrblk, (be128 *)walk->iv);
-	u128_inc(&ctrblk);
-	u128_to_be128((be128 *)walk->iv, &ctrblk);
+	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(camellia_enc_blk), desc,
+				       dst, src, nbytes);
 }
 
-static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
-				struct blkcipher_walk *walk)
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
 {
-	struct camellia_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	unsigned int bsize = CAMELLIA_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	u128 ctrblk;
-	be128 ctrblocks[2];
-
-	be128_to_u128(&ctrblk, (be128 *)walk->iv);
-
-	/* Process two block batch */
-	if (nbytes >= bsize * 2) {
-		do {
-			if (dst != src) {
-				dst[0] = src[0];
-				dst[1] = src[1];
-			}
-
-			/* create ctrblks for parallel encrypt */
-			u128_to_be128(&ctrblocks[0], &ctrblk);
-			u128_inc(&ctrblk);
-			u128_to_be128(&ctrblocks[1], &ctrblk);
-			u128_inc(&ctrblk);
-
-			camellia_enc_blk_xor_2way(ctx, (u8 *)dst,
-						 (u8 *)ctrblocks);
-
-			src += 2;
-			dst += 2;
-			nbytes -= bsize * 2;
-		} while (nbytes >= bsize * 2);
-
-		if (nbytes < bsize)
-			goto done;
-	}
-
-	/* Handle leftovers */
-	do {
-		if (dst != src)
-			*dst = *src;
-
-		u128_to_be128(&ctrblocks[0], &ctrblk);
-		u128_inc(&ctrblk);
-
-		camellia_enc_blk_xor(ctx, (u8 *)dst, (u8 *)ctrblocks);
-
-		src += 1;
-		dst += 1;
-		nbytes -= bsize;
-	} while (nbytes >= bsize);
-
-done:
-	u128_to_be128((be128 *)walk->iv, &ctrblk);
-	return nbytes;
+	return glue_cbc_decrypt_128bit(&camellia_dec_cbc, desc, dst, src,
+				       nbytes);
 }
 
 static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		     struct scatterlist *src, unsigned int nbytes)
 {
-	struct blkcipher_walk walk;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, CAMELLIA_BLOCK_SIZE);
-
-	while ((nbytes = walk.nbytes) >= CAMELLIA_BLOCK_SIZE) {
-		nbytes = __ctr_crypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-
-	if (walk.nbytes) {
-		ctr_crypt_final(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, 0);
-	}
-
-	return err;
+	return glue_ctr_crypt_128bit(&camellia_ctr, desc, dst, src, nbytes);
 }
 
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
new file mode 100644
index 000000000000..4854f0f31e4f
--- /dev/null
+++ b/arch/x86/crypto/glue_helper.c
@@ -0,0 +1,307 @@
+/*
+ * Shared glue code for 128bit block ciphers
+ *
+ * Copyright (c) 2012 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
+ *   Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
+ * CTR part based on code (crypto/ctr.c) by:
+ *   (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/module.h>
+#include <crypto/b128ops.h>
+#include <crypto/lrw.h>
+#include <crypto/xts.h>
+#include <asm/crypto/glue_helper.h>
+#include <crypto/scatterwalk.h>
+
+static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
+				   struct blkcipher_desc *desc,
+				   struct blkcipher_walk *walk)
+{
+	void *ctx = crypto_blkcipher_ctx(desc->tfm);
+	const unsigned int bsize = 128 / 8;
+	unsigned int nbytes, i, func_bytes;
+	bool fpu_enabled = false;
+	int err;
+
+	err = blkcipher_walk_virt(desc, walk);
+
+	while ((nbytes = walk->nbytes)) {
+		u8 *wsrc = walk->src.virt.addr;
+		u8 *wdst = walk->dst.virt.addr;
+
+		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
+					     desc, fpu_enabled, nbytes);
+
+		for (i = 0; i < gctx->num_funcs; i++) {
+			func_bytes = bsize * gctx->funcs[i].num_blocks;
+
+			/* Process multi-block batch */
+			if (nbytes >= func_bytes) {
+				do {
+					gctx->funcs[i].fn_u.ecb(ctx, wdst,
+								wsrc);
+
+					wsrc += func_bytes;
+					wdst += func_bytes;
+					nbytes -= func_bytes;
+				} while (nbytes >= func_bytes);
+
+				if (nbytes < bsize)
+					goto done;
+			}
+		}
+
+done:
+		err = blkcipher_walk_done(desc, walk, nbytes);
+	}
+
+	glue_fpu_end(fpu_enabled);
+	return err;
+}
+
+int glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
+			  struct blkcipher_desc *desc, struct scatterlist *dst,
+			  struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	return __glue_ecb_crypt_128bit(gctx, desc, &walk);
+}
+EXPORT_SYMBOL_GPL(glue_ecb_crypt_128bit);
+
+static unsigned int __glue_cbc_encrypt_128bit(const common_glue_func_t fn,
+					      struct blkcipher_desc *desc,
+					      struct blkcipher_walk *walk)
+{
+	void *ctx = crypto_blkcipher_ctx(desc->tfm);
+	const unsigned int bsize = 128 / 8;
+	unsigned int nbytes = walk->nbytes;
+	u128 *src = (u128 *)walk->src.virt.addr;
+	u128 *dst = (u128 *)walk->dst.virt.addr;
+	u128 *iv = (u128 *)walk->iv;
+
+	do {
+		u128_xor(dst, src, iv);
+		fn(ctx, (u8 *)dst, (u8 *)dst);
+		iv = dst;
+
+		src += 1;
+		dst += 1;
+		nbytes -= bsize;
+	} while (nbytes >= bsize);
+
+	u128_xor((u128 *)walk->iv, (u128 *)walk->iv, iv);
+	return nbytes;
+}
+
+int glue_cbc_encrypt_128bit(const common_glue_func_t fn,
+			    struct blkcipher_desc *desc,
+			    struct scatterlist *dst,
+			    struct scatterlist *src, unsigned int nbytes)
+{
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	while ((nbytes = walk.nbytes)) {
+		nbytes = __glue_cbc_encrypt_128bit(fn, desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(glue_cbc_encrypt_128bit);
+
+static unsigned int
+__glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
+			  struct blkcipher_desc *desc,
+			  struct blkcipher_walk *walk)
+{
+	void *ctx = crypto_blkcipher_ctx(desc->tfm);
+	const unsigned int bsize = 128 / 8;
+	unsigned int nbytes = walk->nbytes;
+	u128 *src = (u128 *)walk->src.virt.addr;
+	u128 *dst = (u128 *)walk->dst.virt.addr;
+	u128 last_iv;
+	unsigned int num_blocks, func_bytes;
+	unsigned int i;
+
+	/* Start of the last block. */
+	src += nbytes / bsize - 1;
+	dst += nbytes / bsize - 1;
+
+	last_iv = *src;
+
+	for (i = 0; i < gctx->num_funcs; i++) {
+		num_blocks = gctx->funcs[i].num_blocks;
+		func_bytes = bsize * num_blocks;
+
+		/* Process multi-block batch */
+		if (nbytes >= func_bytes) {
+			do {
+				nbytes -= func_bytes - bsize;
+				src -= num_blocks - 1;
+				dst -= num_blocks - 1;
+
+				gctx->funcs[i].fn_u.cbc(ctx, dst, src);
+
+				nbytes -= bsize;
+				if (nbytes < bsize)
+					goto done;
+
+				u128_xor(dst, dst, src - 1);
+				src -= 1;
+				dst -= 1;
+			} while (nbytes >= func_bytes);
+
+			if (nbytes < bsize)
+				goto done;
+		}
+	}
+
+done:
+	u128_xor(dst, dst, (u128 *)walk->iv);
+	*(u128 *)walk->iv = last_iv;
+
+	return nbytes;
+}
+
+int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
+			    struct blkcipher_desc *desc,
+			    struct scatterlist *dst,
+			    struct scatterlist *src, unsigned int nbytes)
+{
+	const unsigned int bsize = 128 / 8;
+	bool fpu_enabled = false;
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt(desc, &walk);
+
+	while ((nbytes = walk.nbytes)) {
+		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
+					     desc, fpu_enabled, nbytes);
+		nbytes = __glue_cbc_decrypt_128bit(gctx, desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	glue_fpu_end(fpu_enabled);
+	return err;
+}
+EXPORT_SYMBOL_GPL(glue_cbc_decrypt_128bit);
+
+static void glue_ctr_crypt_final_128bit(const common_glue_ctr_func_t fn_ctr,
+					struct blkcipher_desc *desc,
+					struct blkcipher_walk *walk)
+{
+	void *ctx = crypto_blkcipher_ctx(desc->tfm);
+	u8 *src = (u8 *)walk->src.virt.addr;
+	u8 *dst = (u8 *)walk->dst.virt.addr;
+	unsigned int nbytes = walk->nbytes;
+	u128 ctrblk;
+	u128 tmp;
+
+	be128_to_u128(&ctrblk, (be128 *)walk->iv);
+
+	memcpy(&tmp, src, nbytes);
+	fn_ctr(ctx, &tmp, &tmp, &ctrblk);
+	memcpy(dst, &tmp, nbytes);
+
+	u128_to_be128((be128 *)walk->iv, &ctrblk);
+}
+EXPORT_SYMBOL_GPL(glue_ctr_crypt_final_128bit);
+
+static unsigned int __glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
+					    struct blkcipher_desc *desc,
+					    struct blkcipher_walk *walk)
+{
+	const unsigned int bsize = 128 / 8;
+	void *ctx = crypto_blkcipher_ctx(desc->tfm);
+	unsigned int nbytes = walk->nbytes;
+	u128 *src = (u128 *)walk->src.virt.addr;
+	u128 *dst = (u128 *)walk->dst.virt.addr;
+	u128 ctrblk;
+	unsigned int num_blocks, func_bytes;
+	unsigned int i;
+
+	be128_to_u128(&ctrblk, (be128 *)walk->iv);
+
+	/* Process multi-block batch */
+	for (i = 0; i < gctx->num_funcs; i++) {
+		num_blocks = gctx->funcs[i].num_blocks;
+		func_bytes = bsize * num_blocks;
+
+		if (nbytes >= func_bytes) {
+			do {
+				gctx->funcs[i].fn_u.ctr(ctx, dst, src, &ctrblk);
+
+				src += num_blocks;
+				dst += num_blocks;
+				nbytes -= func_bytes;
+			} while (nbytes >= func_bytes);
+
+			if (nbytes < bsize)
+				goto done;
+		}
+	}
+
+done:
+	u128_to_be128((be128 *)walk->iv, &ctrblk);
+	return nbytes;
+}
+
+int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
+			  struct blkcipher_desc *desc, struct scatterlist *dst,
+			  struct scatterlist *src, unsigned int nbytes)
+{
+	const unsigned int bsize = 128 / 8;
+	bool fpu_enabled = false;
+	struct blkcipher_walk walk;
+	int err;
+
+	blkcipher_walk_init(&walk, dst, src, nbytes);
+	err = blkcipher_walk_virt_block(desc, &walk, bsize);
+
+	while ((nbytes = walk.nbytes) >= bsize) {
+		fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
+					     desc, fpu_enabled, nbytes);
+		nbytes = __glue_ctr_crypt_128bit(gctx, desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, nbytes);
+	}
+
+	glue_fpu_end(fpu_enabled);
+
+	if (walk.nbytes) {
+		glue_ctr_crypt_final_128bit(
+			gctx->funcs[gctx->num_funcs - 1].fn_u.ctr, desc, &walk);
+		err = blkcipher_walk_done(desc, &walk, 0);
+	}
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(glue_ctr_crypt_128bit);
+
+MODULE_LICENSE("GPL");
diff --git a/arch/x86/crypto/serpent-avx-x86_64-asm_64.S b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
new file mode 100644
index 000000000000..504106bf04a2
--- /dev/null
+++ b/arch/x86/crypto/serpent-avx-x86_64-asm_64.S
@@ -0,0 +1,704 @@
+/*
+ * Serpent Cipher 8-way parallel algorithm (x86_64/AVX)
+ *
+ * Copyright (C) 2012 Johannes Goetzfried
+ *     <Johannes.Goetzfried@informatik.stud.uni-erlangen.de>
+ *
+ * Based on arch/x86/crypto/serpent-sse2-x86_64-asm_64.S by
+ *  Copyright (C) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+.file "serpent-avx-x86_64-asm_64.S"
+.text
+
+#define CTX %rdi
+
+/**********************************************************************
+  8-way AVX serpent
+ **********************************************************************/
+#define RA1 %xmm0
+#define RB1 %xmm1
+#define RC1 %xmm2
+#define RD1 %xmm3
+#define RE1 %xmm4
+
+#define tp  %xmm5
+
+#define RA2 %xmm6
+#define RB2 %xmm7
+#define RC2 %xmm8
+#define RD2 %xmm9
+#define RE2 %xmm10
+
+#define RNOT %xmm11
+
+#define RK0 %xmm12
+#define RK1 %xmm13
+#define RK2 %xmm14
+#define RK3 %xmm15
+
+
+#define S0_1(x0, x1, x2, x3, x4)      \
+	vpor		x0,   x3, tp; \
+	vpxor		x3,   x0, x0; \
+	vpxor		x2,   x3, x4; \
+	vpxor		RNOT, x4, x4; \
+	vpxor		x1,   tp, x3; \
+	vpand		x0,   x1, x1; \
+	vpxor		x4,   x1, x1; \
+	vpxor		x0,   x2, x2;
+#define S0_2(x0, x1, x2, x3, x4)      \
+	vpxor		x3,   x0, x0; \
+	vpor		x0,   x4, x4; \
+	vpxor		x2,   x0, x0; \
+	vpand		x1,   x2, x2; \
+	vpxor		x2,   x3, x3; \
+	vpxor		RNOT, x1, x1; \
+	vpxor		x4,   x2, x2; \
+	vpxor		x2,   x1, x1;
+
+#define S1_1(x0, x1, x2, x3, x4)      \
+	vpxor		x0,   x1, tp; \
+	vpxor		x3,   x0, x0; \
+	vpxor		RNOT, x3, x3; \
+	vpand		tp,   x1, x4; \
+	vpor		tp,   x0, x0; \
+	vpxor		x2,   x3, x3; \
+	vpxor		x3,   x0, x0; \
+	vpxor		x3,   tp, x1;
+#define S1_2(x0, x1, x2, x3, x4)      \
+	vpxor		x4,   x3, x3; \
+	vpor		x4,   x1, x1; \
+	vpxor		x2,   x4, x4; \
+	vpand		x0,   x2, x2; \
+	vpxor		x1,   x2, x2; \
+	vpor		x0,   x1, x1; \
+	vpxor		RNOT, x0, x0; \
+	vpxor		x2,   x0, x0; \
+	vpxor		x1,   x4, x4;
+
+#define S2_1(x0, x1, x2, x3, x4)      \
+	vpxor		RNOT, x3, x3; \
+	vpxor		x0,   x1, x1; \
+	vpand		x2,   x0, tp; \
+	vpxor		x3,   tp, tp; \
+	vpor		x0,   x3, x3; \
+	vpxor		x1,   x2, x2; \
+	vpxor		x1,   x3, x3; \
+	vpand		tp,   x1, x1;
+#define S2_2(x0, x1, x2, x3, x4)      \
+	vpxor		x2,   tp, tp; \
+	vpand		x3,   x2, x2; \
+	vpor		x1,   x3, x3; \
+	vpxor		RNOT, tp, tp; \
+	vpxor		tp,   x3, x3; \
+	vpxor		tp,   x0, x4; \
+	vpxor		x2,   tp, x0; \
+	vpor		x2,   x1, x1;
+
+#define S3_1(x0, x1, x2, x3, x4)      \
+	vpxor		x3,   x1, tp; \
+	vpor		x0,   x3, x3; \
+	vpand		x0,   x1, x4; \
+	vpxor		x2,   x0, x0; \
+	vpxor		tp,   x2, x2; \
+	vpand		x3,   tp, x1; \
+	vpxor		x3,   x2, x2; \
+	vpor		x4,   x0, x0; \
+	vpxor		x3,   x4, x4;
+#define S3_2(x0, x1, x2, x3, x4)      \
+	vpxor		x0,   x1, x1; \
+	vpand		x3,   x0, x0; \
+	vpand		x4,   x3, x3; \
+	vpxor		x2,   x3, x3; \
+	vpor		x1,   x4, x4; \
+	vpand		x1,   x2, x2; \
+	vpxor		x3,   x4, x4; \
+	vpxor		x3,   x0, x0; \
+	vpxor		x2,   x3, x3;
+
+#define S4_1(x0, x1, x2, x3, x4)      \
+	vpand		x0,   x3, tp; \
+	vpxor		x3,   x0, x0; \
+	vpxor		x2,   tp, tp; \
+	vpor		x3,   x2, x2; \
+	vpxor		x1,   x0, x0; \
+	vpxor		tp,   x3, x4; \
+	vpor		x0,   x2, x2; \
+	vpxor		x1,   x2, x2;
+#define S4_2(x0, x1, x2, x3, x4)      \
+	vpand		x0,   x1, x1; \
+	vpxor		x4,   x1, x1; \
+	vpand		x2,   x4, x4; \
+	vpxor		tp,   x2, x2; \
+	vpxor		x0,   x4, x4; \
+	vpor		x1,   tp, x3; \
+	vpxor		RNOT, x1, x1; \
+	vpxor		x0,   x3, x3;
+
+#define S5_1(x0, x1, x2, x3, x4)      \
+	vpor		x0,   x1, tp; \
+	vpxor		tp,   x2, x2; \
+	vpxor		RNOT, x3, x3; \
+	vpxor		x0,   x1, x4; \
+	vpxor		x2,   x0, x0; \
+	vpand		x4,   tp, x1; \
+	vpor		x3,   x4, x4; \
+	vpxor		x0,   x4, x4;
+#define S5_2(x0, x1, x2, x3, x4)      \
+	vpand		x3,   x0, x0; \
+	vpxor		x3,   x1, x1; \
+	vpxor		x2,   x3, x3; \
+	vpxor		x1,   x0, x0; \
+	vpand		x4,   x2, x2; \
+	vpxor		x2,   x1, x1; \
+	vpand		x0,   x2, x2; \
+	vpxor		x2,   x3, x3;
+
+#define S6_1(x0, x1, x2, x3, x4)      \
+	vpxor		x0,   x3, x3; \
+	vpxor		x2,   x1, tp; \
+	vpxor		x0,   x2, x2; \
+	vpand		x3,   x0, x0; \
+	vpor		x3,   tp, tp; \
+	vpxor		RNOT, x1, x4; \
+	vpxor		tp,   x0, x0; \
+	vpxor		x2,   tp, x1;
+#define S6_2(x0, x1, x2, x3, x4)      \
+	vpxor		x4,   x3, x3; \
+	vpxor		x0,   x4, x4; \
+	vpand		x0,   x2, x2; \
+	vpxor		x1,   x4, x4; \
+	vpxor		x3,   x2, x2; \
+	vpand		x1,   x3, x3; \
+	vpxor		x0,   x3, x3; \
+	vpxor		x2,   x1, x1;
+
+#define S7_1(x0, x1, x2, x3, x4)      \
+	vpxor		RNOT, x1, tp; \
+	vpxor		RNOT, x0, x0; \
+	vpand		x2,   tp, x1; \
+	vpxor		x3,   x1, x1; \
+	vpor		tp,   x3, x3; \
+	vpxor		x2,   tp, x4; \
+	vpxor		x3,   x2, x2; \
+	vpxor		x0,   x3, x3; \
+	vpor		x1,   x0, x0;
+#define S7_2(x0, x1, x2, x3, x4)      \
+	vpand		x0,   x2, x2; \
+	vpxor		x4,   x0, x0; \
+	vpxor		x3,   x4, x4; \
+	vpand		x0,   x3, x3; \
+	vpxor		x1,   x4, x4; \
+	vpxor		x4,   x2, x2; \
+	vpxor		x1,   x3, x3; \
+	vpor		x0,   x4, x4; \
+	vpxor		x1,   x4, x4;
+
+#define SI0_1(x0, x1, x2, x3, x4)     \
+	vpxor		x0,   x1, x1; \
+	vpor		x1,   x3, tp; \
+	vpxor		x1,   x3, x4; \
+	vpxor		RNOT, x0, x0; \
+	vpxor		tp,   x2, x2; \
+	vpxor		x0,   tp, x3; \
+	vpand		x1,   x0, x0; \
+	vpxor		x2,   x0, x0;
+#define SI0_2(x0, x1, x2, x3, x4)     \
+	vpand		x3,   x2, x2; \
+	vpxor		x4,   x3, x3; \
+	vpxor		x3,   x2, x2; \
+	vpxor		x3,   x1, x1; \
+	vpand		x0,   x3, x3; \
+	vpxor		x0,   x1, x1; \
+	vpxor		x2,   x0, x0; \
+	vpxor		x3,   x4, x4;
+
+#define SI1_1(x0, x1, x2, x3, x4)     \
+	vpxor		x3,   x1, x1; \
+	vpxor		x2,   x0, tp; \
+	vpxor		RNOT, x2, x2; \
+	vpor		x1,   x0, x4; \
+	vpxor		x3,   x4, x4; \
+	vpand		x1,   x3, x3; \
+	vpxor		x2,   x1, x1; \
+	vpand		x4,   x2, x2;
+#define SI1_2(x0, x1, x2, x3, x4)     \
+	vpxor		x1,   x4, x4; \
+	vpor		x3,   x1, x1; \
+	vpxor		tp,   x3, x3; \
+	vpxor		tp,   x2, x2; \
+	vpor		x4,   tp, x0; \
+	vpxor		x4,   x2, x2; \
+	vpxor		x0,   x1, x1; \
+	vpxor		x1,   x4, x4;
+
+#define SI2_1(x0, x1, x2, x3, x4)     \
+	vpxor		x1,   x2, x2; \
+	vpxor		RNOT, x3, tp; \
+	vpor		x2,   tp, tp; \
+	vpxor		x3,   x2, x2; \
+	vpxor		x0,   x3, x4; \
+	vpxor		x1,   tp, x3; \
+	vpor		x2,   x1, x1; \
+	vpxor		x0,   x2, x2;
+#define SI2_2(x0, x1, x2, x3, x4)     \
+	vpxor		x4,   x1, x1; \
+	vpor		x3,   x4, x4; \
+	vpxor		x3,   x2, x2; \
+	vpxor		x2,   x4, x4; \
+	vpand		x1,   x2, x2; \
+	vpxor		x3,   x2, x2; \
+	vpxor		x4,   x3, x3; \
+	vpxor		x0,   x4, x4;
+
+#define SI3_1(x0, x1, x2, x3, x4)     \
+	vpxor		x1,   x2, x2; \
+	vpand		x2,   x1, tp; \
+	vpxor		x0,   tp, tp; \
+	vpor		x1,   x0, x0; \
+	vpxor		x3,   x1, x4; \
+	vpxor		x3,   x0, x0; \
+	vpor		tp,   x3, x3; \
+	vpxor		x2,   tp, x1;
+#define SI3_2(x0, x1, x2, x3, x4)     \
+	vpxor		x3,   x1, x1; \
+	vpxor		x2,   x0, x0; \
+	vpxor		x3,   x2, x2; \
+	vpand		x1,   x3, x3; \
+	vpxor		x0,   x1, x1; \
+	vpand		x2,   x0, x0; \
+	vpxor		x3,   x4, x4; \
+	vpxor		x0,   x3, x3; \
+	vpxor		x1,   x0, x0;
+
+#define SI4_1(x0, x1, x2, x3, x4)     \
+	vpxor		x3,   x2, x2; \
+	vpand		x1,   x0, tp; \
+	vpxor		x2,   tp, tp; \
+	vpor		x3,   x2, x2; \
+	vpxor		RNOT, x0, x4; \
+	vpxor		tp,   x1, x1; \
+	vpxor		x2,   tp, x0; \
+	vpand		x4,   x2, x2;
+#define SI4_2(x0, x1, x2, x3, x4)     \
+	vpxor		x0,   x2, x2; \
+	vpor		x4,   x0, x0; \
+	vpxor		x3,   x0, x0; \
+	vpand		x2,   x3, x3; \
+	vpxor		x3,   x4, x4; \
+	vpxor		x1,   x3, x3; \
+	vpand		x0,   x1, x1; \
+	vpxor		x1,   x4, x4; \
+	vpxor		x3,   x0, x0;
+
+#define SI5_1(x0, x1, x2, x3, x4)     \
+	vpor		x2,   x1, tp; \
+	vpxor		x1,   x2, x2; \
+	vpxor		x3,   tp, tp; \
+	vpand		x1,   x3, x3; \
+	vpxor		x3,   x2, x2; \
+	vpor		x0,   x3, x3; \
+	vpxor		RNOT, x0, x0; \
+	vpxor		x2,   x3, x3; \
+	vpor		x0,   x2, x2;
+#define SI5_2(x0, x1, x2, x3, x4)     \
+	vpxor		tp,   x1, x4; \
+	vpxor		x4,   x2, x2; \
+	vpand		x0,   x4, x4; \
+	vpxor		tp,   x0, x0; \
+	vpxor		x3,   tp, x1; \
+	vpand		x2,   x0, x0; \
+	vpxor		x3,   x2, x2; \
+	vpxor		x2,   x0, x0; \
+	vpxor		x4,   x2, x2; \
+	vpxor		x3,   x4, x4;
+
+#define SI6_1(x0, x1, x2, x3, x4)     \
+	vpxor		x2,   x0, x0; \
+	vpand		x3,   x0, tp; \
+	vpxor		x3,   x2, x2; \
+	vpxor		x2,   tp, tp; \
+	vpxor		x1,   x3, x3; \
+	vpor		x0,   x2, x2; \
+	vpxor		x3,   x2, x2; \
+	vpand		tp,   x3, x3;
+#define SI6_2(x0, x1, x2, x3, x4)     \
+	vpxor		RNOT, tp, tp; \
+	vpxor		x1,   x3, x3; \
+	vpand		x2,   x1, x1; \
+	vpxor		tp,   x0, x4; \
+	vpxor		x4,   x3, x3; \
+	vpxor		x2,   x4, x4; \
+	vpxor		x1,   tp, x0; \
+	vpxor		x0,   x2, x2;
+
+#define SI7_1(x0, x1, x2, x3, x4)     \
+	vpand		x0,   x3, tp; \
+	vpxor		x2,   x0, x0; \
+	vpor		x3,   x2, x2; \
+	vpxor		x1,   x3, x4; \
+	vpxor		RNOT, x0, x0; \
+	vpor		tp,   x1, x1; \
+	vpxor		x0,   x4, x4; \
+	vpand		x2,   x0, x0; \
+	vpxor		x1,   x0, x0;
+#define SI7_2(x0, x1, x2, x3, x4)     \
+	vpand		x2,   x1, x1; \
+	vpxor		x2,   tp, x3; \
+	vpxor		x3,   x4, x4; \
+	vpand		x3,   x2, x2; \
+	vpor		x0,   x3, x3; \
+	vpxor		x4,   x1, x1; \
+	vpxor		x4,   x3, x3; \
+	vpand		x0,   x4, x4; \
+	vpxor		x2,   x4, x4;
+
+#define get_key(i, j, t) \
+	vbroadcastss (4*(i)+(j))*4(CTX), t;
+
+#define K2(x0, x1, x2, x3, x4, i) \
+	get_key(i, 0, RK0); \
+	get_key(i, 1, RK1); \
+	get_key(i, 2, RK2); \
+	get_key(i, 3, RK3); \
+	vpxor RK0,	x0 ## 1, x0 ## 1; \
+	vpxor RK1,	x1 ## 1, x1 ## 1; \
+	vpxor RK2,	x2 ## 1, x2 ## 1; \
+	vpxor RK3,	x3 ## 1, x3 ## 1; \
+		vpxor RK0,	x0 ## 2, x0 ## 2; \
+		vpxor RK1,	x1 ## 2, x1 ## 2; \
+		vpxor RK2,	x2 ## 2, x2 ## 2; \
+		vpxor RK3,	x3 ## 2, x3 ## 2;
+
+#define LK2(x0, x1, x2, x3, x4, i) \
+	vpslld $13,		x0 ## 1, x4 ## 1;          \
+	vpsrld $(32 - 13),	x0 ## 1, x0 ## 1;          \
+	vpor			x4 ## 1, x0 ## 1, x0 ## 1; \
+	vpxor			x0 ## 1, x1 ## 1, x1 ## 1; \
+	vpslld $3,		x2 ## 1, x4 ## 1;          \
+	vpsrld $(32 - 3),	x2 ## 1, x2 ## 1;          \
+	vpor			x4 ## 1, x2 ## 1, x2 ## 1; \
+	vpxor			x2 ## 1, x1 ## 1, x1 ## 1; \
+		vpslld $13,		x0 ## 2, x4 ## 2;          \
+		vpsrld $(32 - 13),	x0 ## 2, x0 ## 2;          \
+		vpor			x4 ## 2, x0 ## 2, x0 ## 2; \
+		vpxor			x0 ## 2, x1 ## 2, x1 ## 2; \
+		vpslld $3,		x2 ## 2, x4 ## 2;          \
+		vpsrld $(32 - 3),	x2 ## 2, x2 ## 2;          \
+		vpor			x4 ## 2, x2 ## 2, x2 ## 2; \
+		vpxor			x2 ## 2, x1 ## 2, x1 ## 2; \
+	vpslld $1,		x1 ## 1, x4 ## 1;          \
+	vpsrld $(32 - 1),	x1 ## 1, x1 ## 1;          \
+	vpor			x4 ## 1, x1 ## 1, x1 ## 1; \
+	vpslld $3,		x0 ## 1, x4 ## 1;          \
+	vpxor			x2 ## 1, x3 ## 1, x3 ## 1; \
+	vpxor			x4 ## 1, x3 ## 1, x3 ## 1; \
+	get_key(i, 1, RK1); \
+		vpslld $1,		x1 ## 2, x4 ## 2;          \
+		vpsrld $(32 - 1),	x1 ## 2, x1 ## 2;          \
+		vpor			x4 ## 2, x1 ## 2, x1 ## 2; \
+		vpslld $3,		x0 ## 2, x4 ## 2;          \
+		vpxor			x2 ## 2, x3 ## 2, x3 ## 2; \
+		vpxor			x4 ## 2, x3 ## 2, x3 ## 2; \
+		get_key(i, 3, RK3); \
+	vpslld $7,		x3 ## 1, x4 ## 1;          \
+	vpsrld $(32 - 7),	x3 ## 1, x3 ## 1;          \
+	vpor			x4 ## 1, x3 ## 1, x3 ## 1; \
+	vpslld $7,		x1 ## 1, x4 ## 1;          \
+	vpxor			x1 ## 1, x0 ## 1, x0 ## 1; \
+	vpxor			x3 ## 1, x0 ## 1, x0 ## 1; \
+	vpxor			x3 ## 1, x2 ## 1, x2 ## 1; \
+	vpxor			x4 ## 1, x2 ## 1, x2 ## 1; \
+	get_key(i, 0, RK0); \
+		vpslld $7,		x3 ## 2, x4 ## 2;          \
+		vpsrld $(32 - 7),	x3 ## 2, x3 ## 2;          \
+		vpor			x4 ## 2, x3 ## 2, x3 ## 2; \
+		vpslld $7,		x1 ## 2, x4 ## 2;          \
+		vpxor			x1 ## 2, x0 ## 2, x0 ## 2; \
+		vpxor			x3 ## 2, x0 ## 2, x0 ## 2; \
+		vpxor			x3 ## 2, x2 ## 2, x2 ## 2; \
+		vpxor			x4 ## 2, x2 ## 2, x2 ## 2; \
+		get_key(i, 2, RK2); \
+	vpxor			RK1, x1 ## 1, x1 ## 1;     \
+	vpxor			RK3, x3 ## 1, x3 ## 1;     \
+	vpslld $5,		x0 ## 1, x4 ## 1;          \
+	vpsrld $(32 - 5),	x0 ## 1, x0 ## 1;          \
+	vpor			x4 ## 1, x0 ## 1, x0 ## 1; \
+	vpslld $22,		x2 ## 1, x4 ## 1;          \
+	vpsrld $(32 - 22),	x2 ## 1, x2 ## 1;          \
+	vpor			x4 ## 1, x2 ## 1, x2 ## 1; \
+	vpxor			RK0, x0 ## 1, x0 ## 1;     \
+	vpxor			RK2, x2 ## 1, x2 ## 1;     \
+		vpxor			RK1, x1 ## 2, x1 ## 2;     \
+		vpxor			RK3, x3 ## 2, x3 ## 2;     \
+		vpslld $5,		x0 ## 2, x4 ## 2;          \
+		vpsrld $(32 - 5),	x0 ## 2, x0 ## 2;          \
+		vpor			x4 ## 2, x0 ## 2, x0 ## 2; \
+		vpslld $22,		x2 ## 2, x4 ## 2;          \
+		vpsrld $(32 - 22),	x2 ## 2, x2 ## 2;          \
+		vpor			x4 ## 2, x2 ## 2, x2 ## 2; \
+		vpxor			RK0, x0 ## 2, x0 ## 2;     \
+		vpxor			RK2, x2 ## 2, x2 ## 2;
+
+#define KL2(x0, x1, x2, x3, x4, i) \
+	vpxor			RK0, x0 ## 1, x0 ## 1;     \
+	vpxor			RK2, x2 ## 1, x2 ## 1;     \
+	vpsrld $5,		x0 ## 1, x4 ## 1;          \
+	vpslld $(32 - 5),	x0 ## 1, x0 ## 1;          \
+	vpor			x4 ## 1, x0 ## 1, x0 ## 1; \
+	vpxor			RK3, x3 ## 1, x3 ## 1;     \
+	vpxor			RK1, x1 ## 1, x1 ## 1;     \
+	vpsrld $22,		x2 ## 1, x4 ## 1;          \
+	vpslld $(32 - 22),	x2 ## 1, x2 ## 1;          \
+	vpor			x4 ## 1, x2 ## 1, x2 ## 1; \
+	vpxor			x3 ## 1, x2 ## 1, x2 ## 1; \
+		vpxor			RK0, x0 ## 2, x0 ## 2;     \
+		vpxor			RK2, x2 ## 2, x2 ## 2;     \
+		vpsrld $5,		x0 ## 2, x4 ## 2;          \
+		vpslld $(32 - 5),	x0 ## 2, x0 ## 2;          \
+		vpor			x4 ## 2, x0 ## 2, x0 ## 2; \
+		vpxor			RK3, x3 ## 2, x3 ## 2;     \
+		vpxor			RK1, x1 ## 2, x1 ## 2;     \
+		vpsrld $22,		x2 ## 2, x4 ## 2;          \
+		vpslld $(32 - 22),	x2 ## 2, x2 ## 2;          \
+		vpor			x4 ## 2, x2 ## 2, x2 ## 2; \
+		vpxor			x3 ## 2, x2 ## 2, x2 ## 2; \
+	vpxor			x3 ## 1, x0 ## 1, x0 ## 1; \
+	vpslld $7,		x1 ## 1, x4 ## 1;          \
+	vpxor			x1 ## 1, x0 ## 1, x0 ## 1; \
+	vpxor			x4 ## 1, x2 ## 1, x2 ## 1; \
+	vpsrld $1,		x1 ## 1, x4 ## 1;          \
+	vpslld $(32 - 1),	x1 ## 1, x1 ## 1;          \
+	vpor			x4 ## 1, x1 ## 1, x1 ## 1; \
+		vpxor			x3 ## 2, x0 ## 2, x0 ## 2; \
+		vpslld $7,		x1 ## 2, x4 ## 2;          \
+		vpxor			x1 ## 2, x0 ## 2, x0 ## 2; \
+		vpxor			x4 ## 2, x2 ## 2, x2 ## 2; \
+		vpsrld $1,		x1 ## 2, x4 ## 2;          \
+		vpslld $(32 - 1),	x1 ## 2, x1 ## 2;          \
+		vpor			x4 ## 2, x1 ## 2, x1 ## 2; \
+	vpsrld $7,		x3 ## 1, x4 ## 1;          \
+	vpslld $(32 - 7),	x3 ## 1, x3 ## 1;          \
+	vpor			x4 ## 1, x3 ## 1, x3 ## 1; \
+	vpxor			x0 ## 1, x1 ## 1, x1 ## 1; \
+	vpslld $3,		x0 ## 1, x4 ## 1;          \
+	vpxor			x4 ## 1, x3 ## 1, x3 ## 1; \
+		vpsrld $7,		x3 ## 2, x4 ## 2;          \
+		vpslld $(32 - 7),	x3 ## 2, x3 ## 2;          \
+		vpor			x4 ## 2, x3 ## 2, x3 ## 2; \
+		vpxor			x0 ## 2, x1 ## 2, x1 ## 2; \
+		vpslld $3,		x0 ## 2, x4 ## 2;          \
+		vpxor			x4 ## 2, x3 ## 2, x3 ## 2; \
+	vpsrld $13,		x0 ## 1, x4 ## 1;          \
+	vpslld $(32 - 13),	x0 ## 1, x0 ## 1;          \
+	vpor			x4 ## 1, x0 ## 1, x0 ## 1; \
+	vpxor			x2 ## 1, x1 ## 1, x1 ## 1; \
+	vpxor			x2 ## 1, x3 ## 1, x3 ## 1; \
+	vpsrld $3,		x2 ## 1, x4 ## 1;          \
+	vpslld $(32 - 3),	x2 ## 1, x2 ## 1;          \
+	vpor			x4 ## 1, x2 ## 1, x2 ## 1; \
+		vpsrld $13,		x0 ## 2, x4 ## 2;          \
+		vpslld $(32 - 13),	x0 ## 2, x0 ## 2;          \
+		vpor			x4 ## 2, x0 ## 2, x0 ## 2; \
+		vpxor			x2 ## 2, x1 ## 2, x1 ## 2; \
+		vpxor			x2 ## 2, x3 ## 2, x3 ## 2; \
+		vpsrld $3,		x2 ## 2, x4 ## 2;          \
+		vpslld $(32 - 3),	x2 ## 2, x2 ## 2;          \
+		vpor			x4 ## 2, x2 ## 2, x2 ## 2;
+
+#define S(SBOX, x0, x1, x2, x3, x4) \
+	SBOX ## _1(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+	SBOX ## _2(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+	SBOX ## _1(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
+	SBOX ## _2(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2);
+
+#define SP(SBOX, x0, x1, x2, x3, x4, i) \
+	get_key(i, 0, RK0); \
+	SBOX ## _1(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+	get_key(i, 2, RK2); \
+	SBOX ## _2(x0 ## 1, x1 ## 1, x2 ## 1, x3 ## 1, x4 ## 1); \
+	get_key(i, 3, RK3); \
+	SBOX ## _1(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
+	get_key(i, 1, RK1); \
+	SBOX ## _2(x0 ## 2, x1 ## 2, x2 ## 2, x3 ## 2, x4 ## 2); \
+
+#define transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	vpunpckldq		x1, x0, t0; \
+	vpunpckhdq		x1, x0, t2; \
+	vpunpckldq		x3, x2, t1; \
+	vpunpckhdq		x3, x2, x3; \
+	\
+	vpunpcklqdq		t1, t0, x0; \
+	vpunpckhqdq		t1, t0, x1; \
+	vpunpcklqdq		x3, t2, x2; \
+	vpunpckhqdq		x3, t2, x3;
+
+#define read_blocks(in, x0, x1, x2, x3, t0, t1, t2) \
+	vmovdqu (0*4*4)(in),	x0; \
+	vmovdqu (1*4*4)(in),	x1; \
+	vmovdqu (2*4*4)(in),	x2; \
+	vmovdqu (3*4*4)(in),	x3; \
+	\
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
+
+#define write_blocks(out, x0, x1, x2, x3, t0, t1, t2) \
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	\
+	vmovdqu x0,		(0*4*4)(out); \
+	vmovdqu x1,		(1*4*4)(out); \
+	vmovdqu x2,		(2*4*4)(out); \
+	vmovdqu x3,		(3*4*4)(out);
+
+#define xor_blocks(out, x0, x1, x2, x3, t0, t1, t2) \
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	\
+	vpxor (0*4*4)(out),	x0, x0;       \
+	vmovdqu x0,		(0*4*4)(out); \
+	vpxor (1*4*4)(out),	x1, x1;       \
+	vmovdqu x1,		(1*4*4)(out); \
+	vpxor (2*4*4)(out),	x2, x2;       \
+	vmovdqu x2,		(2*4*4)(out); \
+	vpxor (3*4*4)(out),	x3, x3;       \
+	vmovdqu x3,		(3*4*4)(out);
+
+.align 8
+.global __serpent_enc_blk_8way_avx
+.type   __serpent_enc_blk_8way_avx,@function;
+
+__serpent_enc_blk_8way_avx:
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 *	%rcx: bool, if true: xor output
+	 */
+
+	vpcmpeqd RNOT, RNOT, RNOT;
+
+	leaq (4*4*4)(%rdx), %rax;
+	read_blocks(%rdx, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
+	read_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
+
+						 K2(RA, RB, RC, RD, RE, 0);
+	S(S0, RA, RB, RC, RD, RE);		LK2(RC, RB, RD, RA, RE, 1);
+	S(S1, RC, RB, RD, RA, RE);		LK2(RE, RD, RA, RC, RB, 2);
+	S(S2, RE, RD, RA, RC, RB);		LK2(RB, RD, RE, RC, RA, 3);
+	S(S3, RB, RD, RE, RC, RA);		LK2(RC, RA, RD, RB, RE, 4);
+	S(S4, RC, RA, RD, RB, RE);		LK2(RA, RD, RB, RE, RC, 5);
+	S(S5, RA, RD, RB, RE, RC);		LK2(RC, RA, RD, RE, RB, 6);
+	S(S6, RC, RA, RD, RE, RB);		LK2(RD, RB, RA, RE, RC, 7);
+	S(S7, RD, RB, RA, RE, RC);		LK2(RC, RA, RE, RD, RB, 8);
+	S(S0, RC, RA, RE, RD, RB);		LK2(RE, RA, RD, RC, RB, 9);
+	S(S1, RE, RA, RD, RC, RB);		LK2(RB, RD, RC, RE, RA, 10);
+	S(S2, RB, RD, RC, RE, RA);		LK2(RA, RD, RB, RE, RC, 11);
+	S(S3, RA, RD, RB, RE, RC);		LK2(RE, RC, RD, RA, RB, 12);
+	S(S4, RE, RC, RD, RA, RB);		LK2(RC, RD, RA, RB, RE, 13);
+	S(S5, RC, RD, RA, RB, RE);		LK2(RE, RC, RD, RB, RA, 14);
+	S(S6, RE, RC, RD, RB, RA);		LK2(RD, RA, RC, RB, RE, 15);
+	S(S7, RD, RA, RC, RB, RE);		LK2(RE, RC, RB, RD, RA, 16);
+	S(S0, RE, RC, RB, RD, RA);		LK2(RB, RC, RD, RE, RA, 17);
+	S(S1, RB, RC, RD, RE, RA);		LK2(RA, RD, RE, RB, RC, 18);
+	S(S2, RA, RD, RE, RB, RC);		LK2(RC, RD, RA, RB, RE, 19);
+	S(S3, RC, RD, RA, RB, RE);		LK2(RB, RE, RD, RC, RA, 20);
+	S(S4, RB, RE, RD, RC, RA);		LK2(RE, RD, RC, RA, RB, 21);
+	S(S5, RE, RD, RC, RA, RB);		LK2(RB, RE, RD, RA, RC, 22);
+	S(S6, RB, RE, RD, RA, RC);		LK2(RD, RC, RE, RA, RB, 23);
+	S(S7, RD, RC, RE, RA, RB);		LK2(RB, RE, RA, RD, RC, 24);
+	S(S0, RB, RE, RA, RD, RC);		LK2(RA, RE, RD, RB, RC, 25);
+	S(S1, RA, RE, RD, RB, RC);		LK2(RC, RD, RB, RA, RE, 26);
+	S(S2, RC, RD, RB, RA, RE);		LK2(RE, RD, RC, RA, RB, 27);
+	S(S3, RE, RD, RC, RA, RB);		LK2(RA, RB, RD, RE, RC, 28);
+	S(S4, RA, RB, RD, RE, RC);		LK2(RB, RD, RE, RC, RA, 29);
+	S(S5, RB, RD, RE, RC, RA);		LK2(RA, RB, RD, RC, RE, 30);
+	S(S6, RA, RB, RD, RC, RE);		LK2(RD, RE, RB, RC, RA, 31);
+	S(S7, RD, RE, RB, RC, RA);		 K2(RA, RB, RC, RD, RE, 32);
+
+	leaq (4*4*4)(%rsi), %rax;
+
+	testb %cl, %cl;
+	jnz __enc_xor8;
+
+	write_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
+	write_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
+
+	ret;
+
+__enc_xor8:
+	xor_blocks(%rsi, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
+	xor_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
+
+	ret;
+
+.align 8
+.global serpent_dec_blk_8way_avx
+.type   serpent_dec_blk_8way_avx,@function;
+
+serpent_dec_blk_8way_avx:
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+
+	vpcmpeqd RNOT, RNOT, RNOT;
+
+	leaq (4*4*4)(%rdx), %rax;
+	read_blocks(%rdx, RA1, RB1, RC1, RD1, RK0, RK1, RK2);
+	read_blocks(%rax, RA2, RB2, RC2, RD2, RK0, RK1, RK2);
+
+						 K2(RA, RB, RC, RD, RE, 32);
+	SP(SI7, RA, RB, RC, RD, RE, 31);	KL2(RB, RD, RA, RE, RC, 31);
+	SP(SI6, RB, RD, RA, RE, RC, 30);	KL2(RA, RC, RE, RB, RD, 30);
+	SP(SI5, RA, RC, RE, RB, RD, 29);	KL2(RC, RD, RA, RE, RB, 29);
+	SP(SI4, RC, RD, RA, RE, RB, 28);	KL2(RC, RA, RB, RE, RD, 28);
+	SP(SI3, RC, RA, RB, RE, RD, 27);	KL2(RB, RC, RD, RE, RA, 27);
+	SP(SI2, RB, RC, RD, RE, RA, 26);	KL2(RC, RA, RE, RD, RB, 26);
+	SP(SI1, RC, RA, RE, RD, RB, 25);	KL2(RB, RA, RE, RD, RC, 25);
+	SP(SI0, RB, RA, RE, RD, RC, 24);	KL2(RE, RC, RA, RB, RD, 24);
+	SP(SI7, RE, RC, RA, RB, RD, 23);	KL2(RC, RB, RE, RD, RA, 23);
+	SP(SI6, RC, RB, RE, RD, RA, 22);	KL2(RE, RA, RD, RC, RB, 22);
+	SP(SI5, RE, RA, RD, RC, RB, 21);	KL2(RA, RB, RE, RD, RC, 21);
+	SP(SI4, RA, RB, RE, RD, RC, 20);	KL2(RA, RE, RC, RD, RB, 20);
+	SP(SI3, RA, RE, RC, RD, RB, 19);	KL2(RC, RA, RB, RD, RE, 19);
+	SP(SI2, RC, RA, RB, RD, RE, 18);	KL2(RA, RE, RD, RB, RC, 18);
+	SP(SI1, RA, RE, RD, RB, RC, 17);	KL2(RC, RE, RD, RB, RA, 17);
+	SP(SI0, RC, RE, RD, RB, RA, 16);	KL2(RD, RA, RE, RC, RB, 16);
+	SP(SI7, RD, RA, RE, RC, RB, 15);	KL2(RA, RC, RD, RB, RE, 15);
+	SP(SI6, RA, RC, RD, RB, RE, 14);	KL2(RD, RE, RB, RA, RC, 14);
+	SP(SI5, RD, RE, RB, RA, RC, 13);	KL2(RE, RC, RD, RB, RA, 13);
+	SP(SI4, RE, RC, RD, RB, RA, 12);	KL2(RE, RD, RA, RB, RC, 12);
+	SP(SI3, RE, RD, RA, RB, RC, 11);	KL2(RA, RE, RC, RB, RD, 11);
+	SP(SI2, RA, RE, RC, RB, RD, 10);	KL2(RE, RD, RB, RC, RA, 10);
+	SP(SI1, RE, RD, RB, RC, RA, 9);		KL2(RA, RD, RB, RC, RE, 9);
+	SP(SI0, RA, RD, RB, RC, RE, 8);		KL2(RB, RE, RD, RA, RC, 8);
+	SP(SI7, RB, RE, RD, RA, RC, 7);		KL2(RE, RA, RB, RC, RD, 7);
+	SP(SI6, RE, RA, RB, RC, RD, 6);		KL2(RB, RD, RC, RE, RA, 6);
+	SP(SI5, RB, RD, RC, RE, RA, 5);		KL2(RD, RA, RB, RC, RE, 5);
+	SP(SI4, RD, RA, RB, RC, RE, 4);		KL2(RD, RB, RE, RC, RA, 4);
+	SP(SI3, RD, RB, RE, RC, RA, 3);		KL2(RE, RD, RA, RC, RB, 3);
+	SP(SI2, RE, RD, RA, RC, RB, 2);		KL2(RD, RB, RC, RA, RE, 2);
+	SP(SI1, RD, RB, RC, RA, RE, 1);		KL2(RE, RB, RC, RA, RD, 1);
+	S(SI0, RE, RB, RC, RA, RD);		 K2(RC, RD, RB, RE, RA, 0);
+
+	leaq (4*4*4)(%rsi), %rax;
+	write_blocks(%rsi, RC1, RD1, RB1, RE1, RK0, RK1, RK2);
+	write_blocks(%rax, RC2, RD2, RB2, RE2, RK0, RK1, RK2);
+
+	ret;
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
new file mode 100644
index 000000000000..b36bdac237eb
--- /dev/null
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -0,0 +1,636 @@
+/*
+ * Glue Code for AVX assembler versions of Serpent Cipher
+ *
+ * Copyright (C) 2012 Johannes Goetzfried
+ *     <Johannes.Goetzfried@informatik.stud.uni-erlangen.de>
+ *
+ * Glue code based on serpent_sse2_glue.c by:
+ *  Copyright (C) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <crypto/algapi.h>
+#include <crypto/serpent.h>
+#include <crypto/cryptd.h>
+#include <crypto/b128ops.h>
+#include <crypto/ctr.h>
+#include <crypto/lrw.h>
+#include <crypto/xts.h>
+#include <asm/xcr.h>
+#include <asm/xsave.h>
+#include <asm/crypto/serpent-avx.h>
+#include <asm/crypto/ablk_helper.h>
+#include <asm/crypto/glue_helper.h>
+
+static void serpent_decrypt_cbc_xway(void *ctx, u128 *dst, const u128 *src)
+{
+	u128 ivs[SERPENT_PARALLEL_BLOCKS - 1];
+	unsigned int j;
+
+	for (j = 0; j < SERPENT_PARALLEL_BLOCKS - 1; j++)
+		ivs[j] = src[j];
+
+	serpent_dec_blk_xway(ctx, (u8 *)dst, (u8 *)src);
+
+	for (j = 0; j < SERPENT_PARALLEL_BLOCKS - 1; j++)
+		u128_xor(dst + (j + 1), dst + (j + 1), ivs + j);
+}
+
+static void serpent_crypt_ctr(void *ctx, u128 *dst, const u128 *src, u128 *iv)
+{
+	be128 ctrblk;
+
+	u128_to_be128(&ctrblk, iv);
+	u128_inc(iv);
+
+	__serpent_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk);
+	u128_xor(dst, src, (u128 *)&ctrblk);
+}
+
+static void serpent_crypt_ctr_xway(void *ctx, u128 *dst, const u128 *src,
+				   u128 *iv)
+{
+	be128 ctrblks[SERPENT_PARALLEL_BLOCKS];
+	unsigned int i;
+
+	for (i = 0; i < SERPENT_PARALLEL_BLOCKS; i++) {
+		if (dst != src)
+			dst[i] = src[i];
+
+		u128_to_be128(&ctrblks[i], iv);
+		u128_inc(iv);
+	}
+
+	serpent_enc_blk_xway_xor(ctx, (u8 *)dst, (u8 *)ctrblks);
+}
+
+static const struct common_glue_ctx serpent_enc = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = SERPENT_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(serpent_enc_blk_xway) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(__serpent_encrypt) }
+	} }
+};
+
+static const struct common_glue_ctx serpent_ctr = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = SERPENT_PARALLEL_BLOCKS,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(serpent_crypt_ctr_xway) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(serpent_crypt_ctr) }
+	} }
+};
+
+static const struct common_glue_ctx serpent_dec = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = SERPENT_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(serpent_dec_blk_xway) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(__serpent_decrypt) }
+	} }
+};
+
+static const struct common_glue_ctx serpent_dec_cbc = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = SERPENT_PARALLEL_BLOCKS,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(serpent_decrypt_cbc_xway) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(__serpent_decrypt) }
+	} }
+};
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ecb_crypt_128bit(&serpent_enc, desc, dst, src, nbytes);
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ecb_crypt_128bit(&serpent_dec, desc, dst, src, nbytes);
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(__serpent_encrypt), desc,
+				     dst, src, nbytes);
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_cbc_decrypt_128bit(&serpent_dec_cbc, desc, dst, src,
+				       nbytes);
+}
+
+static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		     struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ctr_crypt_128bit(&serpent_ctr, desc, dst, src, nbytes);
+}
+
+static inline bool serpent_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+{
+	return glue_fpu_begin(SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS,
+			      NULL, fpu_enabled, nbytes);
+}
+
+static inline void serpent_fpu_end(bool fpu_enabled)
+{
+	glue_fpu_end(fpu_enabled);
+}
+
+struct crypt_priv {
+	struct serpent_ctx *ctx;
+	bool fpu_enabled;
+};
+
+static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = SERPENT_BLOCK_SIZE;
+	struct crypt_priv *ctx = priv;
+	int i;
+
+	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
+
+	if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+		serpent_enc_blk_xway(ctx->ctx, srcdst, srcdst);
+		return;
+	}
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		__serpent_encrypt(ctx->ctx, srcdst, srcdst);
+}
+
+static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = SERPENT_BLOCK_SIZE;
+	struct crypt_priv *ctx = priv;
+	int i;
+
+	ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
+
+	if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+		serpent_dec_blk_xway(ctx->ctx, srcdst, srcdst);
+		return;
+	}
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		__serpent_decrypt(ctx->ctx, srcdst, srcdst);
+}
+
+struct serpent_lrw_ctx {
+	struct lrw_table_ctx lrw_table;
+	struct serpent_ctx serpent_ctx;
+};
+
+static int lrw_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct serpent_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+	int err;
+
+	err = __serpent_setkey(&ctx->serpent_ctx, key, keylen -
+							SERPENT_BLOCK_SIZE);
+	if (err)
+		return err;
+
+	return lrw_init_table(&ctx->lrw_table, key + keylen -
+						SERPENT_BLOCK_SIZE);
+}
+
+static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct serpent_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[SERPENT_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->serpent_ctx,
+		.fpu_enabled = false,
+	};
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = encrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = lrw_crypt(desc, dst, src, nbytes, &req);
+	serpent_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct serpent_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[SERPENT_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->serpent_ctx,
+		.fpu_enabled = false,
+	};
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = decrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = lrw_crypt(desc, dst, src, nbytes, &req);
+	serpent_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static void lrw_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct serpent_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	lrw_free_table(&ctx->lrw_table);
+}
+
+struct serpent_xts_ctx {
+	struct serpent_ctx tweak_ctx;
+	struct serpent_ctx crypt_ctx;
+};
+
+static int xts_serpent_setkey(struct crypto_tfm *tfm, const u8 *key,
+			      unsigned int keylen)
+{
+	struct serpent_xts_ctx *ctx = crypto_tfm_ctx(tfm);
+	u32 *flags = &tfm->crt_flags;
+	int err;
+
+	/* key consists of keys of equal size concatenated, therefore
+	 * the length must be even
+	 */
+	if (keylen % 2) {
+		*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
+		return -EINVAL;
+	}
+
+	/* first half of xts-key is for crypt */
+	err = __serpent_setkey(&ctx->crypt_ctx, key, keylen / 2);
+	if (err)
+		return err;
+
+	/* second half of xts-key is for tweak */
+	return __serpent_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2);
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[SERPENT_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->crypt_ctx,
+		.fpu_enabled = false,
+	};
+	struct xts_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.tweak_ctx = &ctx->tweak_ctx,
+		.tweak_fn = XTS_TWEAK_CAST(__serpent_encrypt),
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = encrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = xts_crypt(desc, dst, src, nbytes, &req);
+	serpent_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct serpent_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[SERPENT_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->crypt_ctx,
+		.fpu_enabled = false,
+	};
+	struct xts_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.tweak_ctx = &ctx->tweak_ctx,
+		.tweak_fn = XTS_TWEAK_CAST(__serpent_encrypt),
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = decrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = xts_crypt(desc, dst, src, nbytes, &req);
+	serpent_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static struct crypto_alg serpent_algs[10] = { {
+	.cra_name		= "__ecb-serpent-avx",
+	.cra_driver_name	= "__driver-ecb-serpent-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= SERPENT_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct serpent_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(serpent_algs[0].cra_list),
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= SERPENT_MIN_KEY_SIZE,
+			.max_keysize	= SERPENT_MAX_KEY_SIZE,
+			.setkey		= serpent_setkey,
+			.encrypt	= ecb_encrypt,
+			.decrypt	= ecb_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__cbc-serpent-avx",
+	.cra_driver_name	= "__driver-cbc-serpent-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= SERPENT_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct serpent_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(serpent_algs[1].cra_list),
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= SERPENT_MIN_KEY_SIZE,
+			.max_keysize	= SERPENT_MAX_KEY_SIZE,
+			.setkey		= serpent_setkey,
+			.encrypt	= cbc_encrypt,
+			.decrypt	= cbc_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__ctr-serpent-avx",
+	.cra_driver_name	= "__driver-ctr-serpent-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct serpent_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(serpent_algs[2].cra_list),
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= SERPENT_MIN_KEY_SIZE,
+			.max_keysize	= SERPENT_MAX_KEY_SIZE,
+			.ivsize		= SERPENT_BLOCK_SIZE,
+			.setkey		= serpent_setkey,
+			.encrypt	= ctr_crypt,
+			.decrypt	= ctr_crypt,
+		},
+	},
+}, {
+	.cra_name		= "__lrw-serpent-avx",
+	.cra_driver_name	= "__driver-lrw-serpent-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= SERPENT_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct serpent_lrw_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(serpent_algs[3].cra_list),
+	.cra_exit		= lrw_exit_tfm,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= SERPENT_MIN_KEY_SIZE +
+					  SERPENT_BLOCK_SIZE,
+			.max_keysize	= SERPENT_MAX_KEY_SIZE +
+					  SERPENT_BLOCK_SIZE,
+			.ivsize		= SERPENT_BLOCK_SIZE,
+			.setkey		= lrw_serpent_setkey,
+			.encrypt	= lrw_encrypt,
+			.decrypt	= lrw_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__xts-serpent-avx",
+	.cra_driver_name	= "__driver-xts-serpent-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= SERPENT_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct serpent_xts_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(serpent_algs[4].cra_list),
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= SERPENT_MIN_KEY_SIZE * 2,
+			.max_keysize	= SERPENT_MAX_KEY_SIZE * 2,
+			.ivsize		= SERPENT_BLOCK_SIZE,
+			.setkey		= xts_serpent_setkey,
+			.encrypt	= xts_encrypt,
+			.decrypt	= xts_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ecb(serpent)",
+	.cra_driver_name	= "ecb-serpent-avx",
+	.cra_priority		= 500,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= SERPENT_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(serpent_algs[5].cra_list),
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= SERPENT_MIN_KEY_SIZE,
+			.max_keysize	= SERPENT_MAX_KEY_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "cbc(serpent)",
+	.cra_driver_name	= "cbc-serpent-avx",
+	.cra_priority		= 500,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= SERPENT_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(serpent_algs[6].cra_list),
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= SERPENT_MIN_KEY_SIZE,
+			.max_keysize	= SERPENT_MAX_KEY_SIZE,
+			.ivsize		= SERPENT_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= __ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ctr(serpent)",
+	.cra_driver_name	= "ctr-serpent-avx",
+	.cra_priority		= 500,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(serpent_algs[7].cra_list),
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= SERPENT_MIN_KEY_SIZE,
+			.max_keysize	= SERPENT_MAX_KEY_SIZE,
+			.ivsize		= SERPENT_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_encrypt,
+			.geniv		= "chainiv",
+		},
+	},
+}, {
+	.cra_name		= "lrw(serpent)",
+	.cra_driver_name	= "lrw-serpent-avx",
+	.cra_priority		= 500,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= SERPENT_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(serpent_algs[8].cra_list),
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= SERPENT_MIN_KEY_SIZE +
+					  SERPENT_BLOCK_SIZE,
+			.max_keysize	= SERPENT_MAX_KEY_SIZE +
+					  SERPENT_BLOCK_SIZE,
+			.ivsize		= SERPENT_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "xts(serpent)",
+	.cra_driver_name	= "xts-serpent-avx",
+	.cra_priority		= 500,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= SERPENT_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(serpent_algs[9].cra_list),
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= SERPENT_MIN_KEY_SIZE * 2,
+			.max_keysize	= SERPENT_MAX_KEY_SIZE * 2,
+			.ivsize		= SERPENT_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+} };
+
+static int __init serpent_init(void)
+{
+	u64 xcr0;
+
+	if (!cpu_has_avx || !cpu_has_osxsave) {
+		printk(KERN_INFO "AVX instructions are not detected.\n");
+		return -ENODEV;
+	}
+
+	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
+		printk(KERN_INFO "AVX detected but unusable.\n");
+		return -ENODEV;
+	}
+
+	return crypto_register_algs(serpent_algs, ARRAY_SIZE(serpent_algs));
+}
+
+static void __exit serpent_exit(void)
+{
+	crypto_unregister_algs(serpent_algs, ARRAY_SIZE(serpent_algs));
+}
+
+module_init(serpent_init);
+module_exit(serpent_exit);
+
+MODULE_DESCRIPTION("Serpent Cipher Algorithm, AVX optimized");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("serpent");
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index 4b21be85e0a1..d679c8675f4a 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -41,358 +41,145 @@
 #include <crypto/ctr.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
-#include <asm/i387.h>
-#include <asm/serpent.h>
-#include <crypto/scatterwalk.h>
-#include <linux/workqueue.h>
-#include <linux/spinlock.h>
-
-struct async_serpent_ctx {
-	struct cryptd_ablkcipher *cryptd_tfm;
-};
+#include <asm/crypto/serpent-sse2.h>
+#include <asm/crypto/ablk_helper.h>
+#include <asm/crypto/glue_helper.h>
 
-static inline bool serpent_fpu_begin(bool fpu_enabled, unsigned int nbytes)
-{
-	if (fpu_enabled)
-		return true;
-
-	/* SSE2 is only used when chunk to be processed is large enough, so
-	 * do not enable FPU until it is necessary.
-	 */
-	if (nbytes < SERPENT_BLOCK_SIZE * SERPENT_PARALLEL_BLOCKS)
-		return false;
-
-	kernel_fpu_begin();
-	return true;
-}
-
-static inline void serpent_fpu_end(bool fpu_enabled)
+static void serpent_decrypt_cbc_xway(void *ctx, u128 *dst, const u128 *src)
 {
-	if (fpu_enabled)
-		kernel_fpu_end();
-}
-
-static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
-		     bool enc)
-{
-	bool fpu_enabled = false;
-	struct serpent_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	const unsigned int bsize = SERPENT_BLOCK_SIZE;
-	unsigned int nbytes;
-	int err;
-
-	err = blkcipher_walk_virt(desc, walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
-	while ((nbytes = walk->nbytes)) {
-		u8 *wsrc = walk->src.virt.addr;
-		u8 *wdst = walk->dst.virt.addr;
-
-		fpu_enabled = serpent_fpu_begin(fpu_enabled, nbytes);
-
-		/* Process multi-block batch */
-		if (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS) {
-			do {
-				if (enc)
-					serpent_enc_blk_xway(ctx, wdst, wsrc);
-				else
-					serpent_dec_blk_xway(ctx, wdst, wsrc);
-
-				wsrc += bsize * SERPENT_PARALLEL_BLOCKS;
-				wdst += bsize * SERPENT_PARALLEL_BLOCKS;
-				nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
-			} while (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS);
-
-			if (nbytes < bsize)
-				goto done;
-		}
-
-		/* Handle leftovers */
-		do {
-			if (enc)
-				__serpent_encrypt(ctx, wdst, wsrc);
-			else
-				__serpent_decrypt(ctx, wdst, wsrc);
-
-			wsrc += bsize;
-			wdst += bsize;
-			nbytes -= bsize;
-		} while (nbytes >= bsize);
-
-done:
-		err = blkcipher_walk_done(desc, walk, nbytes);
-	}
+	u128 ivs[SERPENT_PARALLEL_BLOCKS - 1];
+	unsigned int j;
 
-	serpent_fpu_end(fpu_enabled);
-	return err;
-}
+	for (j = 0; j < SERPENT_PARALLEL_BLOCKS - 1; j++)
+		ivs[j] = src[j];
 
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
+	serpent_dec_blk_xway(ctx, (u8 *)dst, (u8 *)src);
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, true);
+	for (j = 0; j < SERPENT_PARALLEL_BLOCKS - 1; j++)
+		u128_xor(dst + (j + 1), dst + (j + 1), ivs + j);
 }
 
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static void serpent_crypt_ctr(void *ctx, u128 *dst, const u128 *src, u128 *iv)
 {
-	struct blkcipher_walk walk;
+	be128 ctrblk;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, false);
-}
+	u128_to_be128(&ctrblk, iv);
+	u128_inc(iv);
 
-static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
-{
-	struct serpent_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	const unsigned int bsize = SERPENT_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	u128 *iv = (u128 *)walk->iv;
-
-	do {
-		u128_xor(dst, src, iv);
-		__serpent_encrypt(ctx, (u8 *)dst, (u8 *)dst);
-		iv = dst;
-
-		src += 1;
-		dst += 1;
-		nbytes -= bsize;
-	} while (nbytes >= bsize);
-
-	u128_xor((u128 *)walk->iv, (u128 *)walk->iv, iv);
-	return nbytes;
+	__serpent_encrypt(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk);
+	u128_xor(dst, src, (u128 *)&ctrblk);
 }
 
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+static void serpent_crypt_ctr_xway(void *ctx, u128 *dst, const u128 *src,
+				   u128 *iv)
 {
-	struct blkcipher_walk walk;
-	int err;
+	be128 ctrblks[SERPENT_PARALLEL_BLOCKS];
+	unsigned int i;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	for (i = 0; i < SERPENT_PARALLEL_BLOCKS; i++) {
+		if (dst != src)
+			dst[i] = src[i];
 
-	while ((nbytes = walk.nbytes)) {
-		nbytes = __cbc_encrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
+		u128_to_be128(&ctrblks[i], iv);
+		u128_inc(iv);
 	}
 
-	return err;
+	serpent_enc_blk_xway_xor(ctx, (u8 *)dst, (u8 *)ctrblks);
 }
 
-static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
-{
-	struct serpent_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	const unsigned int bsize = SERPENT_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	u128 ivs[SERPENT_PARALLEL_BLOCKS - 1];
-	u128 last_iv;
-	int i;
-
-	/* Start of the last block. */
-	src += nbytes / bsize - 1;
-	dst += nbytes / bsize - 1;
-
-	last_iv = *src;
-
-	/* Process multi-block batch */
-	if (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS) {
-		do {
-			nbytes -= bsize * (SERPENT_PARALLEL_BLOCKS - 1);
-			src -= SERPENT_PARALLEL_BLOCKS - 1;
-			dst -= SERPENT_PARALLEL_BLOCKS - 1;
-
-			for (i = 0; i < SERPENT_PARALLEL_BLOCKS - 1; i++)
-				ivs[i] = src[i];
-
-			serpent_dec_blk_xway(ctx, (u8 *)dst, (u8 *)src);
-
-			for (i = 0; i < SERPENT_PARALLEL_BLOCKS - 1; i++)
-				u128_xor(dst + (i + 1), dst + (i + 1), ivs + i);
-
-			nbytes -= bsize;
-			if (nbytes < bsize)
-				goto done;
+static const struct common_glue_ctx serpent_enc = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
 
-			u128_xor(dst, dst, src - 1);
-			src -= 1;
-			dst -= 1;
-		} while (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS);
-
-		if (nbytes < bsize)
-			goto done;
-	}
-
-	/* Handle leftovers */
-	for (;;) {
-		__serpent_decrypt(ctx, (u8 *)dst, (u8 *)src);
-
-		nbytes -= bsize;
-		if (nbytes < bsize)
-			break;
+	.funcs = { {
+		.num_blocks = SERPENT_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(serpent_enc_blk_xway) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(__serpent_encrypt) }
+	} }
+};
 
-		u128_xor(dst, dst, src - 1);
-		src -= 1;
-		dst -= 1;
-	}
+static const struct common_glue_ctx serpent_ctr = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = SERPENT_PARALLEL_BLOCKS,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(serpent_crypt_ctr_xway) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(serpent_crypt_ctr) }
+	} }
+};
 
-done:
-	u128_xor(dst, dst, (u128 *)walk->iv);
-	*(u128 *)walk->iv = last_iv;
+static const struct common_glue_ctx serpent_dec = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = SERPENT_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(serpent_dec_blk_xway) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(__serpent_decrypt) }
+	} }
+};
 
-	return nbytes;
-}
+static const struct common_glue_ctx serpent_dec_cbc = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = SERPENT_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = SERPENT_PARALLEL_BLOCKS,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(serpent_decrypt_cbc_xway) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(__serpent_decrypt) }
+	} }
+};
 
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		       struct scatterlist *src, unsigned int nbytes)
 {
-	bool fpu_enabled = false;
-	struct blkcipher_walk walk;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
-	while ((nbytes = walk.nbytes)) {
-		fpu_enabled = serpent_fpu_begin(fpu_enabled, nbytes);
-		nbytes = __cbc_decrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-
-	serpent_fpu_end(fpu_enabled);
-	return err;
+	return glue_ecb_crypt_128bit(&serpent_enc, desc, dst, src, nbytes);
 }
 
-static inline void u128_to_be128(be128 *dst, const u128 *src)
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
 {
-	dst->a = cpu_to_be64(src->a);
-	dst->b = cpu_to_be64(src->b);
+	return glue_ecb_crypt_128bit(&serpent_dec, desc, dst, src, nbytes);
 }
 
-static inline void be128_to_u128(u128 *dst, const be128 *src)
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
 {
-	dst->a = be64_to_cpu(src->a);
-	dst->b = be64_to_cpu(src->b);
+	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(__serpent_encrypt), desc,
+				     dst, src, nbytes);
 }
 
-static inline void u128_inc(u128 *i)
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
 {
-	i->b++;
-	if (!i->b)
-		i->a++;
+	return glue_cbc_decrypt_128bit(&serpent_dec_cbc, desc, dst, src,
+				       nbytes);
 }
 
-static void ctr_crypt_final(struct blkcipher_desc *desc,
-			    struct blkcipher_walk *walk)
+static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		     struct scatterlist *src, unsigned int nbytes)
 {
-	struct serpent_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	u8 *ctrblk = walk->iv;
-	u8 keystream[SERPENT_BLOCK_SIZE];
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	unsigned int nbytes = walk->nbytes;
-
-	__serpent_encrypt(ctx, keystream, ctrblk);
-	crypto_xor(keystream, src, nbytes);
-	memcpy(dst, keystream, nbytes);
-
-	crypto_inc(ctrblk, SERPENT_BLOCK_SIZE);
+	return glue_ctr_crypt_128bit(&serpent_ctr, desc, dst, src, nbytes);
 }
 
-static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
-				struct blkcipher_walk *walk)
+static inline bool serpent_fpu_begin(bool fpu_enabled, unsigned int nbytes)
 {
-	struct serpent_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	const unsigned int bsize = SERPENT_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	u128 ctrblk;
-	be128 ctrblocks[SERPENT_PARALLEL_BLOCKS];
-	int i;
-
-	be128_to_u128(&ctrblk, (be128 *)walk->iv);
-
-	/* Process multi-block batch */
-	if (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS) {
-		do {
-			/* create ctrblks for parallel encrypt */
-			for (i = 0; i < SERPENT_PARALLEL_BLOCKS; i++) {
-				if (dst != src)
-					dst[i] = src[i];
-
-				u128_to_be128(&ctrblocks[i], &ctrblk);
-				u128_inc(&ctrblk);
-			}
-
-			serpent_enc_blk_xway_xor(ctx, (u8 *)dst,
-						 (u8 *)ctrblocks);
-
-			src += SERPENT_PARALLEL_BLOCKS;
-			dst += SERPENT_PARALLEL_BLOCKS;
-			nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
-		} while (nbytes >= bsize * SERPENT_PARALLEL_BLOCKS);
-
-		if (nbytes < bsize)
-			goto done;
-	}
-
-	/* Handle leftovers */
-	do {
-		if (dst != src)
-			*dst = *src;
-
-		u128_to_be128(&ctrblocks[0], &ctrblk);
-		u128_inc(&ctrblk);
-
-		__serpent_encrypt(ctx, (u8 *)ctrblocks, (u8 *)ctrblocks);
-		u128_xor(dst, dst, (u128 *)ctrblocks);
-
-		src += 1;
-		dst += 1;
-		nbytes -= bsize;
-	} while (nbytes >= bsize);
-
-done:
-	u128_to_be128((be128 *)walk->iv, &ctrblk);
-	return nbytes;
+	return glue_fpu_begin(SERPENT_BLOCK_SIZE, SERPENT_PARALLEL_BLOCKS,
+			      NULL, fpu_enabled, nbytes);
 }
 
-static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes)
+static inline void serpent_fpu_end(bool fpu_enabled)
 {
-	bool fpu_enabled = false;
-	struct blkcipher_walk walk;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, SERPENT_BLOCK_SIZE);
-	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
-
-	while ((nbytes = walk.nbytes) >= SERPENT_BLOCK_SIZE) {
-		fpu_enabled = serpent_fpu_begin(fpu_enabled, nbytes);
-		nbytes = __ctr_crypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-
-	serpent_fpu_end(fpu_enabled);
-
-	if (walk.nbytes) {
-		ctr_crypt_final(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, 0);
-	}
-
-	return err;
+	glue_fpu_end(fpu_enabled);
 }
 
 struct crypt_priv {
@@ -596,106 +383,6 @@ static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 	return ret;
 }
 
-static int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
-			unsigned int key_len)
-{
-	struct async_serpent_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct crypto_ablkcipher *child = &ctx->cryptd_tfm->base;
-	int err;
-
-	crypto_ablkcipher_clear_flags(child, CRYPTO_TFM_REQ_MASK);
-	crypto_ablkcipher_set_flags(child, crypto_ablkcipher_get_flags(tfm)
-				    & CRYPTO_TFM_REQ_MASK);
-	err = crypto_ablkcipher_setkey(child, key, key_len);
-	crypto_ablkcipher_set_flags(tfm, crypto_ablkcipher_get_flags(child)
-				    & CRYPTO_TFM_RES_MASK);
-	return err;
-}
-
-static int __ablk_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct async_serpent_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-	struct blkcipher_desc desc;
-
-	desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
-	desc.info = req->info;
-	desc.flags = 0;
-
-	return crypto_blkcipher_crt(desc.tfm)->encrypt(
-		&desc, req->dst, req->src, req->nbytes);
-}
-
-static int ablk_encrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct async_serpent_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-
-	if (!irq_fpu_usable()) {
-		struct ablkcipher_request *cryptd_req =
-			ablkcipher_request_ctx(req);
-
-		memcpy(cryptd_req, req, sizeof(*req));
-		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-
-		return crypto_ablkcipher_encrypt(cryptd_req);
-	} else {
-		return __ablk_encrypt(req);
-	}
-}
-
-static int ablk_decrypt(struct ablkcipher_request *req)
-{
-	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
-	struct async_serpent_ctx *ctx = crypto_ablkcipher_ctx(tfm);
-
-	if (!irq_fpu_usable()) {
-		struct ablkcipher_request *cryptd_req =
-			ablkcipher_request_ctx(req);
-
-		memcpy(cryptd_req, req, sizeof(*req));
-		ablkcipher_request_set_tfm(cryptd_req, &ctx->cryptd_tfm->base);
-
-		return crypto_ablkcipher_decrypt(cryptd_req);
-	} else {
-		struct blkcipher_desc desc;
-
-		desc.tfm = cryptd_ablkcipher_child(ctx->cryptd_tfm);
-		desc.info = req->info;
-		desc.flags = 0;
-
-		return crypto_blkcipher_crt(desc.tfm)->decrypt(
-			&desc, req->dst, req->src, req->nbytes);
-	}
-}
-
-static void ablk_exit(struct crypto_tfm *tfm)
-{
-	struct async_serpent_ctx *ctx = crypto_tfm_ctx(tfm);
-
-	cryptd_free_ablkcipher(ctx->cryptd_tfm);
-}
-
-static int ablk_init(struct crypto_tfm *tfm)
-{
-	struct async_serpent_ctx *ctx = crypto_tfm_ctx(tfm);
-	struct cryptd_ablkcipher *cryptd_tfm;
-	char drv_name[CRYPTO_MAX_ALG_NAME];
-
-	snprintf(drv_name, sizeof(drv_name), "__driver-%s",
-					crypto_tfm_alg_driver_name(tfm));
-
-	cryptd_tfm = cryptd_alloc_ablkcipher(drv_name, 0, 0);
-	if (IS_ERR(cryptd_tfm))
-		return PTR_ERR(cryptd_tfm);
-
-	ctx->cryptd_tfm = cryptd_tfm;
-	tfm->crt_ablkcipher.reqsize = sizeof(struct ablkcipher_request) +
-		crypto_ablkcipher_reqsize(&cryptd_tfm->base);
-
-	return 0;
-}
-
 static struct crypto_alg serpent_algs[10] = { {
 	.cra_name		= "__ecb-serpent-sse2",
 	.cra_driver_name	= "__driver-ecb-serpent-sse2",
@@ -808,7 +495,7 @@ static struct crypto_alg serpent_algs[10] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_serpent_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
@@ -830,7 +517,7 @@ static struct crypto_alg serpent_algs[10] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_serpent_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
@@ -853,7 +540,7 @@ static struct crypto_alg serpent_algs[10] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= 1,
-	.cra_ctxsize		= sizeof(struct async_serpent_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
@@ -877,7 +564,7 @@ static struct crypto_alg serpent_algs[10] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_serpent_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
@@ -902,7 +589,7 @@ static struct crypto_alg serpent_algs[10] = { {
 	.cra_priority		= 400,
 	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize		= SERPENT_BLOCK_SIZE,
-	.cra_ctxsize		= sizeof(struct async_serpent_ctx),
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
 	.cra_alignmask		= 0,
 	.cra_type		= &crypto_ablkcipher_type,
 	.cra_module		= THIS_MODULE,
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index b2c2f57d70e8..49d6987a73d9 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -468,7 +468,7 @@ W_PRECALC_SSSE3
  */
 SHA1_VECTOR_ASM     sha1_transform_ssse3
 
-#ifdef SHA1_ENABLE_AVX_SUPPORT
+#ifdef CONFIG_AS_AVX
 
 .macro W_PRECALC_AVX
 
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index f916499d0abe..4a11a9d72451 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -35,7 +35,7 @@
 
 asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data,
 				     unsigned int rounds);
-#ifdef SHA1_ENABLE_AVX_SUPPORT
+#ifdef CONFIG_AS_AVX
 asmlinkage void sha1_transform_avx(u32 *digest, const char *data,
 				   unsigned int rounds);
 #endif
@@ -184,7 +184,7 @@ static struct shash_alg alg = {
 	}
 };
 
-#ifdef SHA1_ENABLE_AVX_SUPPORT
+#ifdef CONFIG_AS_AVX
 static bool __init avx_usable(void)
 {
 	u64 xcr0;
@@ -209,7 +209,7 @@ static int __init sha1_ssse3_mod_init(void)
 	if (cpu_has_ssse3)
 		sha1_transform_asm = sha1_transform_ssse3;
 
-#ifdef SHA1_ENABLE_AVX_SUPPORT
+#ifdef CONFIG_AS_AVX
 	/* allow AVX to override SSSE3, it's a little faster */
 	if (avx_usable())
 		sha1_transform_asm = sha1_transform_avx;
diff --git a/arch/x86/crypto/twofish-avx-x86_64-asm_64.S b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
new file mode 100644
index 000000000000..35f45574390d
--- /dev/null
+++ b/arch/x86/crypto/twofish-avx-x86_64-asm_64.S
@@ -0,0 +1,300 @@
+/*
+ * Twofish Cipher 8-way parallel algorithm (AVX/x86_64)
+ *
+ * Copyright (C) 2012 Johannes Goetzfried
+ *     <Johannes.Goetzfried@informatik.stud.uni-erlangen.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+.file "twofish-avx-x86_64-asm_64.S"
+.text
+
+/* structure of crypto context */
+#define s0	0
+#define s1	1024
+#define s2	2048
+#define s3	3072
+#define w	4096
+#define k	4128
+
+/**********************************************************************
+  8-way AVX twofish
+ **********************************************************************/
+#define CTX %rdi
+
+#define RA1 %xmm0
+#define RB1 %xmm1
+#define RC1 %xmm2
+#define RD1 %xmm3
+
+#define RA2 %xmm4
+#define RB2 %xmm5
+#define RC2 %xmm6
+#define RD2 %xmm7
+
+#define RX %xmm8
+#define RY %xmm9
+
+#define RK1 %xmm10
+#define RK2 %xmm11
+
+#define RID1  %rax
+#define RID1b %al
+#define RID2  %rbx
+#define RID2b %bl
+
+#define RGI1   %rdx
+#define RGI1bl %dl
+#define RGI1bh %dh
+#define RGI2   %rcx
+#define RGI2bl %cl
+#define RGI2bh %ch
+
+#define RGS1  %r8
+#define RGS1d %r8d
+#define RGS2  %r9
+#define RGS2d %r9d
+#define RGS3  %r10
+#define RGS3d %r10d
+
+
+#define lookup_32bit(t0, t1, t2, t3, src, dst) \
+	movb		src ## bl,        RID1b;     \
+	movb		src ## bh,        RID2b;     \
+	movl		t0(CTX, RID1, 4), dst ## d;  \
+	xorl		t1(CTX, RID2, 4), dst ## d;  \
+	shrq $16,	src;                         \
+	movb		src ## bl,        RID1b;     \
+	movb		src ## bh,        RID2b;     \
+	xorl		t2(CTX, RID1, 4), dst ## d;  \
+	xorl		t3(CTX, RID2, 4), dst ## d;
+
+#define G(a, x, t0, t1, t2, t3) \
+	vmovq		a,    RGI1;               \
+	vpsrldq $8,	a,    x;                  \
+	vmovq		x,    RGI2;               \
+	\
+	lookup_32bit(t0, t1, t2, t3, RGI1, RGS1); \
+	shrq $16,	RGI1;                     \
+	lookup_32bit(t0, t1, t2, t3, RGI1, RGS2); \
+	shlq $32,	RGS2;                     \
+	orq		RGS1, RGS2;               \
+	\
+	lookup_32bit(t0, t1, t2, t3, RGI2, RGS1); \
+	shrq $16,	RGI2;                     \
+	lookup_32bit(t0, t1, t2, t3, RGI2, RGS3); \
+	shlq $32,	RGS3;                     \
+	orq		RGS1, RGS3;               \
+	\
+	vmovq		RGS2, x;                  \
+	vpinsrq $1,	RGS3, x, x;
+
+#define encround(a, b, c, d, x, y) \
+	G(a, x, s0, s1, s2, s3);           \
+	G(b, y, s1, s2, s3, s0);           \
+	vpaddd			x, y,   x; \
+	vpaddd			y, x,   y; \
+	vpaddd			x, RK1, x; \
+	vpaddd			y, RK2, y; \
+	vpxor			x, c,   c; \
+	vpsrld $1,		c, x;      \
+	vpslld $(32 - 1),	c, c;      \
+	vpor			c, x,   c; \
+	vpslld $1,		d, x;      \
+	vpsrld $(32 - 1),	d, d;      \
+	vpor			d, x,   d; \
+	vpxor			d, y,   d;
+
+#define decround(a, b, c, d, x, y) \
+	G(a, x, s0, s1, s2, s3);           \
+	G(b, y, s1, s2, s3, s0);           \
+	vpaddd			x, y,   x; \
+	vpaddd			y, x,   y; \
+	vpaddd			y, RK2, y; \
+	vpxor			d, y,   d; \
+	vpsrld $1,		d, y;      \
+	vpslld $(32 - 1),	d, d;      \
+	vpor			d, y,   d; \
+	vpslld $1,		c, y;      \
+	vpsrld $(32 - 1),	c, c;      \
+	vpor			c, y,   c; \
+	vpaddd			x, RK1, x; \
+	vpxor			x, c,   c;
+
+#define encrypt_round(n, a, b, c, d) \
+	vbroadcastss (k+4*(2*(n)))(CTX),   RK1;           \
+	vbroadcastss (k+4*(2*(n)+1))(CTX), RK2;           \
+	encround(a ## 1, b ## 1, c ## 1, d ## 1, RX, RY); \
+	encround(a ## 2, b ## 2, c ## 2, d ## 2, RX, RY);
+
+#define decrypt_round(n, a, b, c, d) \
+	vbroadcastss (k+4*(2*(n)))(CTX),   RK1;           \
+	vbroadcastss (k+4*(2*(n)+1))(CTX), RK2;           \
+	decround(a ## 1, b ## 1, c ## 1, d ## 1, RX, RY); \
+	decround(a ## 2, b ## 2, c ## 2, d ## 2, RX, RY);
+
+#define encrypt_cycle(n) \
+	encrypt_round((2*n), RA, RB, RC, RD);       \
+	encrypt_round(((2*n) + 1), RC, RD, RA, RB);
+
+#define decrypt_cycle(n) \
+	decrypt_round(((2*n) + 1), RC, RD, RA, RB); \
+	decrypt_round((2*n), RA, RB, RC, RD);
+
+
+#define transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	vpunpckldq		x1, x0, t0; \
+	vpunpckhdq		x1, x0, t2; \
+	vpunpckldq		x3, x2, t1; \
+	vpunpckhdq		x3, x2, x3; \
+	\
+	vpunpcklqdq		t1, t0, x0; \
+	vpunpckhqdq		t1, t0, x1; \
+	vpunpcklqdq		x3, t2, x2; \
+	vpunpckhqdq		x3, t2, x3;
+
+#define inpack_blocks(in, x0, x1, x2, x3, wkey, t0, t1, t2) \
+	vpxor (0*4*4)(in),	wkey, x0; \
+	vpxor (1*4*4)(in),	wkey, x1; \
+	vpxor (2*4*4)(in),	wkey, x2; \
+	vpxor (3*4*4)(in),	wkey, x3; \
+	\
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2)
+
+#define outunpack_blocks(out, x0, x1, x2, x3, wkey, t0, t1, t2) \
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	\
+	vpxor		x0, wkey, x0;     \
+	vmovdqu 	x0, (0*4*4)(out); \
+	vpxor		x1, wkey, x1;     \
+	vmovdqu		x1, (1*4*4)(out); \
+	vpxor		x2, wkey, x2;     \
+	vmovdqu		x2, (2*4*4)(out); \
+	vpxor		x3, wkey, x3;     \
+	vmovdqu		x3, (3*4*4)(out);
+
+#define outunpack_xor_blocks(out, x0, x1, x2, x3, wkey, t0, t1, t2) \
+	transpose_4x4(x0, x1, x2, x3, t0, t1, t2) \
+	\
+	vpxor		x0, wkey, x0;         \
+	vpxor		(0*4*4)(out), x0, x0; \
+	vmovdqu 	x0, (0*4*4)(out);     \
+	vpxor		x1, wkey, x1;         \
+	vpxor		(1*4*4)(out), x1, x1; \
+	vmovdqu	        x1, (1*4*4)(out);     \
+	vpxor		x2, wkey, x2;         \
+	vpxor           (2*4*4)(out), x2, x2; \
+	vmovdqu		x2, (2*4*4)(out);     \
+	vpxor		x3, wkey, x3;         \
+	vpxor           (3*4*4)(out), x3, x3; \
+	vmovdqu		x3, (3*4*4)(out);
+
+.align 8
+.global __twofish_enc_blk_8way
+.type   __twofish_enc_blk_8way,@function;
+
+__twofish_enc_blk_8way:
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 *	%rcx: bool, if true: xor output
+	 */
+
+	pushq %rbx;
+	pushq %rcx;
+
+	vmovdqu w(CTX), RK1;
+
+	leaq (4*4*4)(%rdx), %rax;
+	inpack_blocks(%rdx, RA1, RB1, RC1, RD1, RK1, RX, RY, RK2);
+	inpack_blocks(%rax, RA2, RB2, RC2, RD2, RK1, RX, RY, RK2);
+
+	xorq RID1, RID1;
+	xorq RID2, RID2;
+
+	encrypt_cycle(0);
+	encrypt_cycle(1);
+	encrypt_cycle(2);
+	encrypt_cycle(3);
+	encrypt_cycle(4);
+	encrypt_cycle(5);
+	encrypt_cycle(6);
+	encrypt_cycle(7);
+
+	vmovdqu (w+4*4)(CTX), RK1;
+
+	popq %rcx;
+	popq %rbx;
+
+	leaq (4*4*4)(%rsi), %rax;
+
+	testb %cl, %cl;
+	jnz __enc_xor8;
+
+	outunpack_blocks(%rsi, RC1, RD1, RA1, RB1, RK1, RX, RY, RK2);
+	outunpack_blocks(%rax, RC2, RD2, RA2, RB2, RK1, RX, RY, RK2);
+
+	ret;
+
+__enc_xor8:
+	outunpack_xor_blocks(%rsi, RC1, RD1, RA1, RB1, RK1, RX, RY, RK2);
+	outunpack_xor_blocks(%rax, RC2, RD2, RA2, RB2, RK1, RX, RY, RK2);
+
+	ret;
+
+.align 8
+.global twofish_dec_blk_8way
+.type   twofish_dec_blk_8way,@function;
+
+twofish_dec_blk_8way:
+	/* input:
+	 *	%rdi: ctx, CTX
+	 *	%rsi: dst
+	 *	%rdx: src
+	 */
+
+	pushq %rbx;
+
+	vmovdqu (w+4*4)(CTX), RK1;
+
+	leaq (4*4*4)(%rdx), %rax;
+	inpack_blocks(%rdx, RC1, RD1, RA1, RB1, RK1, RX, RY, RK2);
+	inpack_blocks(%rax, RC2, RD2, RA2, RB2, RK1, RX, RY, RK2);
+
+	xorq RID1, RID1;
+	xorq RID2, RID2;
+
+	decrypt_cycle(7);
+	decrypt_cycle(6);
+	decrypt_cycle(5);
+	decrypt_cycle(4);
+	decrypt_cycle(3);
+	decrypt_cycle(2);
+	decrypt_cycle(1);
+	decrypt_cycle(0);
+
+	vmovdqu (w)(CTX), RK1;
+
+	popq %rbx;
+
+	leaq (4*4*4)(%rsi), %rax;
+	outunpack_blocks(%rsi, RA1, RB1, RC1, RD1, RK1, RX, RY, RK2);
+	outunpack_blocks(%rax, RA2, RB2, RC2, RD2, RK1, RX, RY, RK2);
+
+	ret;
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
new file mode 100644
index 000000000000..782b67ddaf6a
--- /dev/null
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -0,0 +1,624 @@
+/*
+ * Glue Code for AVX assembler version of Twofish Cipher
+ *
+ * Copyright (C) 2012 Johannes Goetzfried
+ *     <Johannes.Goetzfried@informatik.stud.uni-erlangen.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307
+ * USA
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/hardirq.h>
+#include <linux/types.h>
+#include <linux/crypto.h>
+#include <linux/err.h>
+#include <crypto/algapi.h>
+#include <crypto/twofish.h>
+#include <crypto/cryptd.h>
+#include <crypto/b128ops.h>
+#include <crypto/ctr.h>
+#include <crypto/lrw.h>
+#include <crypto/xts.h>
+#include <asm/i387.h>
+#include <asm/xcr.h>
+#include <asm/xsave.h>
+#include <asm/crypto/twofish.h>
+#include <asm/crypto/ablk_helper.h>
+#include <asm/crypto/glue_helper.h>
+#include <crypto/scatterwalk.h>
+#include <linux/workqueue.h>
+#include <linux/spinlock.h>
+
+#define TWOFISH_PARALLEL_BLOCKS 8
+
+static inline void twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
+					const u8 *src)
+{
+	__twofish_enc_blk_3way(ctx, dst, src, false);
+}
+
+/* 8-way parallel cipher functions */
+asmlinkage void __twofish_enc_blk_8way(struct twofish_ctx *ctx, u8 *dst,
+				       const u8 *src, bool xor);
+asmlinkage void twofish_dec_blk_8way(struct twofish_ctx *ctx, u8 *dst,
+				     const u8 *src);
+
+static inline void twofish_enc_blk_xway(struct twofish_ctx *ctx, u8 *dst,
+					const u8 *src)
+{
+	__twofish_enc_blk_8way(ctx, dst, src, false);
+}
+
+static inline void twofish_enc_blk_xway_xor(struct twofish_ctx *ctx, u8 *dst,
+					    const u8 *src)
+{
+	__twofish_enc_blk_8way(ctx, dst, src, true);
+}
+
+static inline void twofish_dec_blk_xway(struct twofish_ctx *ctx, u8 *dst,
+					const u8 *src)
+{
+	twofish_dec_blk_8way(ctx, dst, src);
+}
+
+static void twofish_dec_blk_cbc_xway(void *ctx, u128 *dst, const u128 *src)
+{
+	u128 ivs[TWOFISH_PARALLEL_BLOCKS - 1];
+	unsigned int j;
+
+	for (j = 0; j < TWOFISH_PARALLEL_BLOCKS - 1; j++)
+		ivs[j] = src[j];
+
+	twofish_dec_blk_xway(ctx, (u8 *)dst, (u8 *)src);
+
+	for (j = 0; j < TWOFISH_PARALLEL_BLOCKS - 1; j++)
+		u128_xor(dst + (j + 1), dst + (j + 1), ivs + j);
+}
+
+static void twofish_enc_blk_ctr_xway(void *ctx, u128 *dst, const u128 *src,
+				     u128 *iv)
+{
+	be128 ctrblks[TWOFISH_PARALLEL_BLOCKS];
+	unsigned int i;
+
+	for (i = 0; i < TWOFISH_PARALLEL_BLOCKS; i++) {
+		if (dst != src)
+			dst[i] = src[i];
+
+		u128_to_be128(&ctrblks[i], iv);
+		u128_inc(iv);
+	}
+
+	twofish_enc_blk_xway_xor(ctx, (u8 *)dst, (u8 *)ctrblks);
+}
+
+static const struct common_glue_ctx twofish_enc = {
+	.num_funcs = 3,
+	.fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = TWOFISH_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk_xway) }
+	}, {
+		.num_blocks = 3,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk_3way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk) }
+	} }
+};
+
+static const struct common_glue_ctx twofish_ctr = {
+	.num_funcs = 3,
+	.fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = TWOFISH_PARALLEL_BLOCKS,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(twofish_enc_blk_ctr_xway) }
+	}, {
+		.num_blocks = 3,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(twofish_enc_blk_ctr_3way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ctr = GLUE_CTR_FUNC_CAST(twofish_enc_blk_ctr) }
+	} }
+};
+
+static const struct common_glue_ctx twofish_dec = {
+	.num_funcs = 3,
+	.fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = TWOFISH_PARALLEL_BLOCKS,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_dec_blk_xway) }
+	}, {
+		.num_blocks = 3,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_dec_blk_3way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_dec_blk) }
+	} }
+};
+
+static const struct common_glue_ctx twofish_dec_cbc = {
+	.num_funcs = 3,
+	.fpu_blocks_limit = TWOFISH_PARALLEL_BLOCKS,
+
+	.funcs = { {
+		.num_blocks = TWOFISH_PARALLEL_BLOCKS,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(twofish_dec_blk_cbc_xway) }
+	}, {
+		.num_blocks = 3,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(twofish_dec_blk_cbc_3way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(twofish_dec_blk) }
+	} }
+};
+
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ecb_crypt_128bit(&twofish_enc, desc, dst, src, nbytes);
+}
+
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ecb_crypt_128bit(&twofish_dec, desc, dst, src, nbytes);
+}
+
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(twofish_enc_blk), desc,
+				       dst, src, nbytes);
+}
+
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_cbc_decrypt_128bit(&twofish_dec_cbc, desc, dst, src,
+				       nbytes);
+}
+
+static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		     struct scatterlist *src, unsigned int nbytes)
+{
+	return glue_ctr_crypt_128bit(&twofish_ctr, desc, dst, src, nbytes);
+}
+
+static inline bool twofish_fpu_begin(bool fpu_enabled, unsigned int nbytes)
+{
+	return glue_fpu_begin(TF_BLOCK_SIZE, TWOFISH_PARALLEL_BLOCKS, NULL,
+			      fpu_enabled, nbytes);
+}
+
+static inline void twofish_fpu_end(bool fpu_enabled)
+{
+	glue_fpu_end(fpu_enabled);
+}
+
+struct crypt_priv {
+	struct twofish_ctx *ctx;
+	bool fpu_enabled;
+};
+
+static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = TF_BLOCK_SIZE;
+	struct crypt_priv *ctx = priv;
+	int i;
+
+	ctx->fpu_enabled = twofish_fpu_begin(ctx->fpu_enabled, nbytes);
+
+	if (nbytes == bsize * TWOFISH_PARALLEL_BLOCKS) {
+		twofish_enc_blk_xway(ctx->ctx, srcdst, srcdst);
+		return;
+	}
+
+	for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3)
+		twofish_enc_blk_3way(ctx->ctx, srcdst, srcdst);
+
+	nbytes %= bsize * 3;
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		twofish_enc_blk(ctx->ctx, srcdst, srcdst);
+}
+
+static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
+{
+	const unsigned int bsize = TF_BLOCK_SIZE;
+	struct crypt_priv *ctx = priv;
+	int i;
+
+	ctx->fpu_enabled = twofish_fpu_begin(ctx->fpu_enabled, nbytes);
+
+	if (nbytes == bsize * TWOFISH_PARALLEL_BLOCKS) {
+		twofish_dec_blk_xway(ctx->ctx, srcdst, srcdst);
+		return;
+	}
+
+	for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3)
+		twofish_dec_blk_3way(ctx->ctx, srcdst, srcdst);
+
+	nbytes %= bsize * 3;
+
+	for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
+		twofish_dec_blk(ctx->ctx, srcdst, srcdst);
+}
+
+static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct twofish_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[TWOFISH_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->twofish_ctx,
+		.fpu_enabled = false,
+	};
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = encrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = lrw_crypt(desc, dst, src, nbytes, &req);
+	twofish_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct twofish_lrw_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[TWOFISH_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->twofish_ctx,
+		.fpu_enabled = false,
+	};
+	struct lrw_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.table_ctx = &ctx->lrw_table,
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = decrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = lrw_crypt(desc, dst, src, nbytes, &req);
+	twofish_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[TWOFISH_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->crypt_ctx,
+		.fpu_enabled = false,
+	};
+	struct xts_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.tweak_ctx = &ctx->tweak_ctx,
+		.tweak_fn = XTS_TWEAK_CAST(twofish_enc_blk),
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = encrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = xts_crypt(desc, dst, src, nbytes, &req);
+	twofish_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static int xts_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
+{
+	struct twofish_xts_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
+	be128 buf[TWOFISH_PARALLEL_BLOCKS];
+	struct crypt_priv crypt_ctx = {
+		.ctx = &ctx->crypt_ctx,
+		.fpu_enabled = false,
+	};
+	struct xts_crypt_req req = {
+		.tbuf = buf,
+		.tbuflen = sizeof(buf),
+
+		.tweak_ctx = &ctx->tweak_ctx,
+		.tweak_fn = XTS_TWEAK_CAST(twofish_enc_blk),
+		.crypt_ctx = &crypt_ctx,
+		.crypt_fn = decrypt_callback,
+	};
+	int ret;
+
+	desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	ret = xts_crypt(desc, dst, src, nbytes, &req);
+	twofish_fpu_end(crypt_ctx.fpu_enabled);
+
+	return ret;
+}
+
+static struct crypto_alg twofish_algs[10] = { {
+	.cra_name		= "__ecb-twofish-avx",
+	.cra_driver_name	= "__driver-ecb-twofish-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= TF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct twofish_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(twofish_algs[0].cra_list),
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE,
+			.max_keysize	= TF_MAX_KEY_SIZE,
+			.setkey		= twofish_setkey,
+			.encrypt	= ecb_encrypt,
+			.decrypt	= ecb_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__cbc-twofish-avx",
+	.cra_driver_name	= "__driver-cbc-twofish-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= TF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct twofish_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(twofish_algs[1].cra_list),
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE,
+			.max_keysize	= TF_MAX_KEY_SIZE,
+			.setkey		= twofish_setkey,
+			.encrypt	= cbc_encrypt,
+			.decrypt	= cbc_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__ctr-twofish-avx",
+	.cra_driver_name	= "__driver-ctr-twofish-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct twofish_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(twofish_algs[2].cra_list),
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE,
+			.max_keysize	= TF_MAX_KEY_SIZE,
+			.ivsize		= TF_BLOCK_SIZE,
+			.setkey		= twofish_setkey,
+			.encrypt	= ctr_crypt,
+			.decrypt	= ctr_crypt,
+		},
+	},
+}, {
+	.cra_name		= "__lrw-twofish-avx",
+	.cra_driver_name	= "__driver-lrw-twofish-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= TF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct twofish_lrw_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(twofish_algs[3].cra_list),
+	.cra_exit		= lrw_twofish_exit_tfm,
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE +
+					  TF_BLOCK_SIZE,
+			.max_keysize	= TF_MAX_KEY_SIZE +
+					  TF_BLOCK_SIZE,
+			.ivsize		= TF_BLOCK_SIZE,
+			.setkey		= lrw_twofish_setkey,
+			.encrypt	= lrw_encrypt,
+			.decrypt	= lrw_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "__xts-twofish-avx",
+	.cra_driver_name	= "__driver-xts-twofish-avx",
+	.cra_priority		= 0,
+	.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
+	.cra_blocksize		= TF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct twofish_xts_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_blkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(twofish_algs[4].cra_list),
+	.cra_u = {
+		.blkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE * 2,
+			.max_keysize	= TF_MAX_KEY_SIZE * 2,
+			.ivsize		= TF_BLOCK_SIZE,
+			.setkey		= xts_twofish_setkey,
+			.encrypt	= xts_encrypt,
+			.decrypt	= xts_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ecb(twofish)",
+	.cra_driver_name	= "ecb-twofish-avx",
+	.cra_priority		= 400,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= TF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(twofish_algs[5].cra_list),
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE,
+			.max_keysize	= TF_MAX_KEY_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "cbc(twofish)",
+	.cra_driver_name	= "cbc-twofish-avx",
+	.cra_priority		= 400,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= TF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(twofish_algs[6].cra_list),
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE,
+			.max_keysize	= TF_MAX_KEY_SIZE,
+			.ivsize		= TF_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= __ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "ctr(twofish)",
+	.cra_driver_name	= "ctr-twofish-avx",
+	.cra_priority		= 400,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= 1,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(twofish_algs[7].cra_list),
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE,
+			.max_keysize	= TF_MAX_KEY_SIZE,
+			.ivsize		= TF_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_encrypt,
+			.geniv		= "chainiv",
+		},
+	},
+}, {
+	.cra_name		= "lrw(twofish)",
+	.cra_driver_name	= "lrw-twofish-avx",
+	.cra_priority		= 400,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= TF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(twofish_algs[8].cra_list),
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE +
+					  TF_BLOCK_SIZE,
+			.max_keysize	= TF_MAX_KEY_SIZE +
+					  TF_BLOCK_SIZE,
+			.ivsize		= TF_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+}, {
+	.cra_name		= "xts(twofish)",
+	.cra_driver_name	= "xts-twofish-avx",
+	.cra_priority		= 400,
+	.cra_flags		= CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+	.cra_blocksize		= TF_BLOCK_SIZE,
+	.cra_ctxsize		= sizeof(struct async_helper_ctx),
+	.cra_alignmask		= 0,
+	.cra_type		= &crypto_ablkcipher_type,
+	.cra_module		= THIS_MODULE,
+	.cra_list		= LIST_HEAD_INIT(twofish_algs[9].cra_list),
+	.cra_init		= ablk_init,
+	.cra_exit		= ablk_exit,
+	.cra_u = {
+		.ablkcipher = {
+			.min_keysize	= TF_MIN_KEY_SIZE * 2,
+			.max_keysize	= TF_MAX_KEY_SIZE * 2,
+			.ivsize		= TF_BLOCK_SIZE,
+			.setkey		= ablk_set_key,
+			.encrypt	= ablk_encrypt,
+			.decrypt	= ablk_decrypt,
+		},
+	},
+} };
+
+static int __init twofish_init(void)
+{
+	u64 xcr0;
+
+	if (!cpu_has_avx || !cpu_has_osxsave) {
+		printk(KERN_INFO "AVX instructions are not detected.\n");
+		return -ENODEV;
+	}
+
+	xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+	if ((xcr0 & (XSTATE_SSE | XSTATE_YMM)) != (XSTATE_SSE | XSTATE_YMM)) {
+		printk(KERN_INFO "AVX detected but unusable.\n");
+		return -ENODEV;
+	}
+
+	return crypto_register_algs(twofish_algs, ARRAY_SIZE(twofish_algs));
+}
+
+static void __exit twofish_exit(void)
+{
+	crypto_unregister_algs(twofish_algs, ARRAY_SIZE(twofish_algs));
+}
+
+module_init(twofish_init);
+module_exit(twofish_exit);
+
+MODULE_DESCRIPTION("Twofish Cipher Algorithm, AVX optimized");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("twofish");
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 922ab24cce31..15f9347316c8 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -3,11 +3,6 @@
  *
  * Copyright (c) 2011 Jussi Kivilinna <jussi.kivilinna@mbnet.fi>
  *
- * CBC & ECB parts based on code (crypto/cbc.c,ecb.c) by:
- *   Copyright (c) 2006 Herbert Xu <herbert@gondor.apana.org.au>
- * CTR part based on code (crypto/ctr.c) by:
- *   (C) Copyright IBM Corp. 2007 - Joy Latten <latten@us.ibm.com>
- *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -33,20 +28,13 @@
 #include <crypto/algapi.h>
 #include <crypto/twofish.h>
 #include <crypto/b128ops.h>
+#include <asm/crypto/twofish.h>
+#include <asm/crypto/glue_helper.h>
 #include <crypto/lrw.h>
 #include <crypto/xts.h>
 
-/* regular block cipher functions from twofish_x86_64 module */
-asmlinkage void twofish_enc_blk(struct twofish_ctx *ctx, u8 *dst,
-				const u8 *src);
-asmlinkage void twofish_dec_blk(struct twofish_ctx *ctx, u8 *dst,
-				const u8 *src);
-
-/* 3-way parallel cipher functions */
-asmlinkage void __twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
-				       const u8 *src, bool xor);
-asmlinkage void twofish_dec_blk_3way(struct twofish_ctx *ctx, u8 *dst,
-				     const u8 *src);
+EXPORT_SYMBOL_GPL(__twofish_enc_blk_3way);
+EXPORT_SYMBOL_GPL(twofish_dec_blk_3way);
 
 static inline void twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
 					const u8 *src)
@@ -60,311 +48,139 @@ static inline void twofish_enc_blk_xor_3way(struct twofish_ctx *ctx, u8 *dst,
 	__twofish_enc_blk_3way(ctx, dst, src, true);
 }
 
-static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
-		     void (*fn)(struct twofish_ctx *, u8 *, const u8 *),
-		     void (*fn_3way)(struct twofish_ctx *, u8 *, const u8 *))
-{
-	struct twofish_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	unsigned int bsize = TF_BLOCK_SIZE;
-	unsigned int nbytes;
-	int err;
-
-	err = blkcipher_walk_virt(desc, walk);
-
-	while ((nbytes = walk->nbytes)) {
-		u8 *wsrc = walk->src.virt.addr;
-		u8 *wdst = walk->dst.virt.addr;
-
-		/* Process three block batch */
-		if (nbytes >= bsize * 3) {
-			do {
-				fn_3way(ctx, wdst, wsrc);
-
-				wsrc += bsize * 3;
-				wdst += bsize * 3;
-				nbytes -= bsize * 3;
-			} while (nbytes >= bsize * 3);
-
-			if (nbytes < bsize)
-				goto done;
-		}
-
-		/* Handle leftovers */
-		do {
-			fn(ctx, wdst, wsrc);
-
-			wsrc += bsize;
-			wdst += bsize;
-			nbytes -= bsize;
-		} while (nbytes >= bsize);
-
-done:
-		err = blkcipher_walk_done(desc, walk, nbytes);
-	}
-
-	return err;
-}
-
-static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+void twofish_dec_blk_cbc_3way(void *ctx, u128 *dst, const u128 *src)
 {
-	struct blkcipher_walk walk;
+	u128 ivs[2];
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, twofish_enc_blk, twofish_enc_blk_3way);
-}
+	ivs[0] = src[0];
+	ivs[1] = src[1];
 
-static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
+	twofish_dec_blk_3way(ctx, (u8 *)dst, (u8 *)src);
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	return ecb_crypt(desc, &walk, twofish_dec_blk, twofish_dec_blk_3way);
+	u128_xor(&dst[1], &dst[1], &ivs[0]);
+	u128_xor(&dst[2], &dst[2], &ivs[1]);
 }
+EXPORT_SYMBOL_GPL(twofish_dec_blk_cbc_3way);
 
-static unsigned int __cbc_encrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
-{
-	struct twofish_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	unsigned int bsize = TF_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	u128 *iv = (u128 *)walk->iv;
-
-	do {
-		u128_xor(dst, src, iv);
-		twofish_enc_blk(ctx, (u8 *)dst, (u8 *)dst);
-		iv = dst;
-
-		src += 1;
-		dst += 1;
-		nbytes -= bsize;
-	} while (nbytes >= bsize);
-
-	u128_xor((u128 *)walk->iv, (u128 *)walk->iv, iv);
-	return nbytes;
-}
-
-static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
+void twofish_enc_blk_ctr(void *ctx, u128 *dst, const u128 *src, u128 *iv)
 {
-	struct blkcipher_walk walk;
-	int err;
+	be128 ctrblk;
 
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+	if (dst != src)
+		*dst = *src;
 
-	while ((nbytes = walk.nbytes)) {
-		nbytes = __cbc_encrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
+	u128_to_be128(&ctrblk, iv);
+	u128_inc(iv);
 
-	return err;
+	twofish_enc_blk(ctx, (u8 *)&ctrblk, (u8 *)&ctrblk);
+	u128_xor(dst, dst, (u128 *)&ctrblk);
 }
+EXPORT_SYMBOL_GPL(twofish_enc_blk_ctr);
 
-static unsigned int __cbc_decrypt(struct blkcipher_desc *desc,
-				  struct blkcipher_walk *walk)
+void twofish_enc_blk_ctr_3way(void *ctx, u128 *dst, const u128 *src,
+				     u128 *iv)
 {
-	struct twofish_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	unsigned int bsize = TF_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	u128 ivs[3 - 1];
-	u128 last_iv;
-
-	/* Start of the last block. */
-	src += nbytes / bsize - 1;
-	dst += nbytes / bsize - 1;
-
-	last_iv = *src;
-
-	/* Process three block batch */
-	if (nbytes >= bsize * 3) {
-		do {
-			nbytes -= bsize * (3 - 1);
-			src -= 3 - 1;
-			dst -= 3 - 1;
-
-			ivs[0] = src[0];
-			ivs[1] = src[1];
-
-			twofish_dec_blk_3way(ctx, (u8 *)dst, (u8 *)src);
-
-			u128_xor(dst + 1, dst + 1, ivs + 0);
-			u128_xor(dst + 2, dst + 2, ivs + 1);
-
-			nbytes -= bsize;
-			if (nbytes < bsize)
-				goto done;
-
-			u128_xor(dst, dst, src - 1);
-			src -= 1;
-			dst -= 1;
-		} while (nbytes >= bsize * 3);
-
-		if (nbytes < bsize)
-			goto done;
-	}
-
-	/* Handle leftovers */
-	for (;;) {
-		twofish_dec_blk(ctx, (u8 *)dst, (u8 *)src);
-
-		nbytes -= bsize;
-		if (nbytes < bsize)
-			break;
+	be128 ctrblks[3];
 
-		u128_xor(dst, dst, src - 1);
-		src -= 1;
-		dst -= 1;
+	if (dst != src) {
+		dst[0] = src[0];
+		dst[1] = src[1];
+		dst[2] = src[2];
 	}
 
-done:
-	u128_xor(dst, dst, (u128 *)walk->iv);
-	*(u128 *)walk->iv = last_iv;
+	u128_to_be128(&ctrblks[0], iv);
+	u128_inc(iv);
+	u128_to_be128(&ctrblks[1], iv);
+	u128_inc(iv);
+	u128_to_be128(&ctrblks[2], iv);
+	u128_inc(iv);
 
-	return nbytes;
+	twofish_enc_blk_xor_3way(ctx, (u8 *)dst, (u8 *)ctrblks);
 }
+EXPORT_SYMBOL_GPL(twofish_enc_blk_ctr_3way);
+
+static const struct common_glue_ctx twofish_enc = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = -1,
+
+	.funcs = { {
+		.num_blocks = 3,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk_3way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk) }
+	} }
+};
 
-static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		       struct scatterlist *src, unsigned int nbytes)
-{
-	struct blkcipher_walk walk;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt(desc, &walk);
+static const struct common_glue_ctx twofish_ctr = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = -1,
+
+	.funcs = { {
+		.num_blocks = 3,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk_ctr_3way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_enc_blk_ctr) }
+	} }
+};
 
-	while ((nbytes = walk.nbytes)) {
-		nbytes = __cbc_decrypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
+static const struct common_glue_ctx twofish_dec = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = -1,
+
+	.funcs = { {
+		.num_blocks = 3,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_dec_blk_3way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .ecb = GLUE_FUNC_CAST(twofish_dec_blk) }
+	} }
+};
 
-	return err;
-}
+static const struct common_glue_ctx twofish_dec_cbc = {
+	.num_funcs = 2,
+	.fpu_blocks_limit = -1,
+
+	.funcs = { {
+		.num_blocks = 3,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(twofish_dec_blk_cbc_3way) }
+	}, {
+		.num_blocks = 1,
+		.fn_u = { .cbc = GLUE_CBC_FUNC_CAST(twofish_dec_blk) }
+	} }
+};
 
-static inline void u128_to_be128(be128 *dst, const u128 *src)
+static int ecb_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
 {
-	dst->a = cpu_to_be64(src->a);
-	dst->b = cpu_to_be64(src->b);
+	return glue_ecb_crypt_128bit(&twofish_enc, desc, dst, src, nbytes);
 }
 
-static inline void be128_to_u128(u128 *dst, const be128 *src)
+static int ecb_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
 {
-	dst->a = be64_to_cpu(src->a);
-	dst->b = be64_to_cpu(src->b);
+	return glue_ecb_crypt_128bit(&twofish_dec, desc, dst, src, nbytes);
 }
 
-static inline void u128_inc(u128 *i)
+static int cbc_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
 {
-	i->b++;
-	if (!i->b)
-		i->a++;
+	return glue_cbc_encrypt_128bit(GLUE_FUNC_CAST(twofish_enc_blk), desc,
+				       dst, src, nbytes);
 }
 
-static void ctr_crypt_final(struct blkcipher_desc *desc,
-			    struct blkcipher_walk *walk)
+static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
+		       struct scatterlist *src, unsigned int nbytes)
 {
-	struct twofish_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	u8 *ctrblk = walk->iv;
-	u8 keystream[TF_BLOCK_SIZE];
-	u8 *src = walk->src.virt.addr;
-	u8 *dst = walk->dst.virt.addr;
-	unsigned int nbytes = walk->nbytes;
-
-	twofish_enc_blk(ctx, keystream, ctrblk);
-	crypto_xor(keystream, src, nbytes);
-	memcpy(dst, keystream, nbytes);
-
-	crypto_inc(ctrblk, TF_BLOCK_SIZE);
-}
-
-static unsigned int __ctr_crypt(struct blkcipher_desc *desc,
-				struct blkcipher_walk *walk)
-{
-	struct twofish_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
-	unsigned int bsize = TF_BLOCK_SIZE;
-	unsigned int nbytes = walk->nbytes;
-	u128 *src = (u128 *)walk->src.virt.addr;
-	u128 *dst = (u128 *)walk->dst.virt.addr;
-	u128 ctrblk;
-	be128 ctrblocks[3];
-
-	be128_to_u128(&ctrblk, (be128 *)walk->iv);
-
-	/* Process three block batch */
-	if (nbytes >= bsize * 3) {
-		do {
-			if (dst != src) {
-				dst[0] = src[0];
-				dst[1] = src[1];
-				dst[2] = src[2];
-			}
-
-			/* create ctrblks for parallel encrypt */
-			u128_to_be128(&ctrblocks[0], &ctrblk);
-			u128_inc(&ctrblk);
-			u128_to_be128(&ctrblocks[1], &ctrblk);
-			u128_inc(&ctrblk);
-			u128_to_be128(&ctrblocks[2], &ctrblk);
-			u128_inc(&ctrblk);
-
-			twofish_enc_blk_xor_3way(ctx, (u8 *)dst,
-						 (u8 *)ctrblocks);
-
-			src += 3;
-			dst += 3;
-			nbytes -= bsize * 3;
-		} while (nbytes >= bsize * 3);
-
-		if (nbytes < bsize)
-			goto done;
-	}
-
-	/* Handle leftovers */
-	do {
-		if (dst != src)
-			*dst = *src;
-
-		u128_to_be128(&ctrblocks[0], &ctrblk);
-		u128_inc(&ctrblk);
-
-		twofish_enc_blk(ctx, (u8 *)ctrblocks, (u8 *)ctrblocks);
-		u128_xor(dst, dst, (u128 *)ctrblocks);
-
-		src += 1;
-		dst += 1;
-		nbytes -= bsize;
-	} while (nbytes >= bsize);
-
-done:
-	u128_to_be128((be128 *)walk->iv, &ctrblk);
-	return nbytes;
+	return glue_cbc_decrypt_128bit(&twofish_dec_cbc, desc, dst, src,
+				       nbytes);
 }
 
 static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		     struct scatterlist *src, unsigned int nbytes)
 {
-	struct blkcipher_walk walk;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, TF_BLOCK_SIZE);
-
-	while ((nbytes = walk.nbytes) >= TF_BLOCK_SIZE) {
-		nbytes = __ctr_crypt(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-
-	if (walk.nbytes) {
-		ctr_crypt_final(desc, &walk);
-		err = blkcipher_walk_done(desc, &walk, 0);
-	}
-
-	return err;
+	return glue_ctr_crypt_128bit(&twofish_ctr, desc, dst, src, nbytes);
 }
 
 static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
@@ -397,13 +213,8 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
 		twofish_dec_blk(ctx, srcdst, srcdst);
 }
 
-struct twofish_lrw_ctx {
-	struct lrw_table_ctx lrw_table;
-	struct twofish_ctx twofish_ctx;
-};
-
-static int lrw_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
-			      unsigned int keylen)
+int lrw_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+		       unsigned int keylen)
 {
 	struct twofish_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
 	int err;
@@ -415,6 +226,7 @@ static int lrw_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
 
 	return lrw_init_table(&ctx->lrw_table, key + keylen - TF_BLOCK_SIZE);
 }
+EXPORT_SYMBOL_GPL(lrw_twofish_setkey);
 
 static int lrw_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		       struct scatterlist *src, unsigned int nbytes)
@@ -450,20 +262,16 @@ static int lrw_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 	return lrw_crypt(desc, dst, src, nbytes, &req);
 }
 
-static void lrw_exit_tfm(struct crypto_tfm *tfm)
+void lrw_twofish_exit_tfm(struct crypto_tfm *tfm)
 {
 	struct twofish_lrw_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	lrw_free_table(&ctx->lrw_table);
 }
+EXPORT_SYMBOL_GPL(lrw_twofish_exit_tfm);
 
-struct twofish_xts_ctx {
-	struct twofish_ctx tweak_ctx;
-	struct twofish_ctx crypt_ctx;
-};
-
-static int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
-			      unsigned int keylen)
+int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+		       unsigned int keylen)
 {
 	struct twofish_xts_ctx *ctx = crypto_tfm_ctx(tfm);
 	u32 *flags = &tfm->crt_flags;
@@ -486,6 +294,7 @@ static int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
 	return __twofish_setkey(&ctx->tweak_ctx, key + keylen / 2, keylen / 2,
 				flags);
 }
+EXPORT_SYMBOL_GPL(xts_twofish_setkey);
 
 static int xts_encrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
 		       struct scatterlist *src, unsigned int nbytes)
@@ -596,7 +405,7 @@ static struct crypto_alg tf_algs[5] = { {
 	.cra_type		= &crypto_blkcipher_type,
 	.cra_module		= THIS_MODULE,
 	.cra_list		= LIST_HEAD_INIT(tf_algs[3].cra_list),
-	.cra_exit		= lrw_exit_tfm,
+	.cra_exit		= lrw_twofish_exit_tfm,
 	.cra_u = {
 		.blkcipher = {
 			.min_keysize	= TF_MIN_KEY_SIZE + TF_BLOCK_SIZE,
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 3ea51a84a0e4..f34261296ffb 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -546,7 +546,7 @@ static inline const struct cpumask *online_target_cpus(void)
 	return cpu_online_mask;
 }
 
-DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
 
 
 static inline unsigned int read_apic_id(void)
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index eb45aa6b1f27..2ad874cb661c 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -66,6 +66,7 @@ struct setup_header {
 	__u64	setup_data;
 	__u64	pref_address;
 	__u32	init_size;
+	__u32	handover_offset;
 } __attribute__((packed));
 
 struct sys_desc_table {
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index f91e80f4f180..6b7ee5ff6820 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -207,6 +207,8 @@
 #define X86_FEATURE_ERMS	(9*32+ 9) /* Enhanced REP MOVSB/STOSB */
 #define X86_FEATURE_INVPCID	(9*32+10) /* Invalidate Processor Context ID */
 #define X86_FEATURE_RTM		(9*32+11) /* Restricted Transactional Memory */
+#define X86_FEATURE_RDSEED	(9*32+18) /* The RDSEED instruction */
+#define X86_FEATURE_ADX		(9*32+19) /* The ADCX and ADOX instructions */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
diff --git a/arch/x86/include/asm/crypto/ablk_helper.h b/arch/x86/include/asm/crypto/ablk_helper.h
new file mode 100644
index 000000000000..4f93df50c23e
--- /dev/null
+++ b/arch/x86/include/asm/crypto/ablk_helper.h
@@ -0,0 +1,31 @@
+/*
+ * Shared async block cipher helpers
+ */
+
+#ifndef _CRYPTO_ABLK_HELPER_H
+#define _CRYPTO_ABLK_HELPER_H
+
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <crypto/cryptd.h>
+
+struct async_helper_ctx {
+	struct cryptd_ablkcipher *cryptd_tfm;
+};
+
+extern int ablk_set_key(struct crypto_ablkcipher *tfm, const u8 *key,
+			unsigned int key_len);
+
+extern int __ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_encrypt(struct ablkcipher_request *req);
+
+extern int ablk_decrypt(struct ablkcipher_request *req);
+
+extern void ablk_exit(struct crypto_tfm *tfm);
+
+extern int ablk_init_common(struct crypto_tfm *tfm, const char *drv_name);
+
+extern int ablk_init(struct crypto_tfm *tfm);
+
+#endif /* _CRYPTO_ABLK_HELPER_H */
diff --git a/arch/x86/include/asm/aes.h b/arch/x86/include/asm/crypto/aes.h
index 80545a1cbe39..80545a1cbe39 100644
--- a/arch/x86/include/asm/aes.h
+++ b/arch/x86/include/asm/crypto/aes.h
diff --git a/arch/x86/include/asm/crypto/glue_helper.h b/arch/x86/include/asm/crypto/glue_helper.h
new file mode 100644
index 000000000000..3e408bddc96f
--- /dev/null
+++ b/arch/x86/include/asm/crypto/glue_helper.h
@@ -0,0 +1,115 @@
+/*
+ * Shared glue code for 128bit block ciphers
+ */
+
+#ifndef _CRYPTO_GLUE_HELPER_H
+#define _CRYPTO_GLUE_HELPER_H
+
+#include <linux/kernel.h>
+#include <linux/crypto.h>
+#include <asm/i387.h>
+#include <crypto/b128ops.h>
+
+typedef void (*common_glue_func_t)(void *ctx, u8 *dst, const u8 *src);
+typedef void (*common_glue_cbc_func_t)(void *ctx, u128 *dst, const u128 *src);
+typedef void (*common_glue_ctr_func_t)(void *ctx, u128 *dst, const u128 *src,
+				       u128 *iv);
+
+#define GLUE_FUNC_CAST(fn) ((common_glue_func_t)(fn))
+#define GLUE_CBC_FUNC_CAST(fn) ((common_glue_cbc_func_t)(fn))
+#define GLUE_CTR_FUNC_CAST(fn) ((common_glue_ctr_func_t)(fn))
+
+struct common_glue_func_entry {
+	unsigned int num_blocks; /* number of blocks that @fn will process */
+	union {
+		common_glue_func_t ecb;
+		common_glue_cbc_func_t cbc;
+		common_glue_ctr_func_t ctr;
+	} fn_u;
+};
+
+struct common_glue_ctx {
+	unsigned int num_funcs;
+	int fpu_blocks_limit; /* -1 means fpu not needed at all */
+
+	/*
+	 * First funcs entry must have largest num_blocks and last funcs entry
+	 * must have num_blocks == 1!
+	 */
+	struct common_glue_func_entry funcs[];
+};
+
+static inline bool glue_fpu_begin(unsigned int bsize, int fpu_blocks_limit,
+				  struct blkcipher_desc *desc,
+				  bool fpu_enabled, unsigned int nbytes)
+{
+	if (likely(fpu_blocks_limit < 0))
+		return false;
+
+	if (fpu_enabled)
+		return true;
+
+	/*
+	 * Vector-registers are only used when chunk to be processed is large
+	 * enough, so do not enable FPU until it is necessary.
+	 */
+	if (nbytes < bsize * (unsigned int)fpu_blocks_limit)
+		return false;
+
+	if (desc) {
+		/* prevent sleeping if FPU is in use */
+		desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+	}
+
+	kernel_fpu_begin();
+	return true;
+}
+
+static inline void glue_fpu_end(bool fpu_enabled)
+{
+	if (fpu_enabled)
+		kernel_fpu_end();
+}
+
+static inline void u128_to_be128(be128 *dst, const u128 *src)
+{
+	dst->a = cpu_to_be64(src->a);
+	dst->b = cpu_to_be64(src->b);
+}
+
+static inline void be128_to_u128(u128 *dst, const be128 *src)
+{
+	dst->a = be64_to_cpu(src->a);
+	dst->b = be64_to_cpu(src->b);
+}
+
+static inline void u128_inc(u128 *i)
+{
+	i->b++;
+	if (!i->b)
+		i->a++;
+}
+
+extern int glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
+				 struct blkcipher_desc *desc,
+				 struct scatterlist *dst,
+				 struct scatterlist *src, unsigned int nbytes);
+
+extern int glue_cbc_encrypt_128bit(const common_glue_func_t fn,
+				   struct blkcipher_desc *desc,
+				   struct scatterlist *dst,
+				   struct scatterlist *src,
+				   unsigned int nbytes);
+
+extern int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
+				   struct blkcipher_desc *desc,
+				   struct scatterlist *dst,
+				   struct scatterlist *src,
+				   unsigned int nbytes);
+
+extern int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
+				 struct blkcipher_desc *desc,
+				 struct scatterlist *dst,
+				 struct scatterlist *src, unsigned int nbytes);
+
+#endif /* _CRYPTO_GLUE_HELPER_H */
diff --git a/arch/x86/include/asm/crypto/serpent-avx.h b/arch/x86/include/asm/crypto/serpent-avx.h
new file mode 100644
index 000000000000..432deedd2945
--- /dev/null
+++ b/arch/x86/include/asm/crypto/serpent-avx.h
@@ -0,0 +1,32 @@
+#ifndef ASM_X86_SERPENT_AVX_H
+#define ASM_X86_SERPENT_AVX_H
+
+#include <linux/crypto.h>
+#include <crypto/serpent.h>
+
+#define SERPENT_PARALLEL_BLOCKS 8
+
+asmlinkage void __serpent_enc_blk_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+					   const u8 *src, bool xor);
+asmlinkage void serpent_dec_blk_8way_avx(struct serpent_ctx *ctx, u8 *dst,
+					 const u8 *src);
+
+static inline void serpent_enc_blk_xway(struct serpent_ctx *ctx, u8 *dst,
+				   const u8 *src)
+{
+	__serpent_enc_blk_8way_avx(ctx, dst, src, false);
+}
+
+static inline void serpent_enc_blk_xway_xor(struct serpent_ctx *ctx, u8 *dst,
+				       const u8 *src)
+{
+	__serpent_enc_blk_8way_avx(ctx, dst, src, true);
+}
+
+static inline void serpent_dec_blk_xway(struct serpent_ctx *ctx, u8 *dst,
+				   const u8 *src)
+{
+	serpent_dec_blk_8way_avx(ctx, dst, src);
+}
+
+#endif
diff --git a/arch/x86/include/asm/serpent.h b/arch/x86/include/asm/crypto/serpent-sse2.h
index d3ef63fe0c81..e6e77dffbdab 100644
--- a/arch/x86/include/asm/serpent.h
+++ b/arch/x86/include/asm/crypto/serpent-sse2.h
@@ -1,5 +1,5 @@
-#ifndef ASM_X86_SERPENT_H
-#define ASM_X86_SERPENT_H
+#ifndef ASM_X86_SERPENT_SSE2_H
+#define ASM_X86_SERPENT_SSE2_H
 
 #include <linux/crypto.h>
 #include <crypto/serpent.h>
diff --git a/arch/x86/include/asm/crypto/twofish.h b/arch/x86/include/asm/crypto/twofish.h
new file mode 100644
index 000000000000..9d2c514bd5f9
--- /dev/null
+++ b/arch/x86/include/asm/crypto/twofish.h
@@ -0,0 +1,46 @@
+#ifndef ASM_X86_TWOFISH_H
+#define ASM_X86_TWOFISH_H
+
+#include <linux/crypto.h>
+#include <crypto/twofish.h>
+#include <crypto/lrw.h>
+#include <crypto/b128ops.h>
+
+struct twofish_lrw_ctx {
+	struct lrw_table_ctx lrw_table;
+	struct twofish_ctx twofish_ctx;
+};
+
+struct twofish_xts_ctx {
+	struct twofish_ctx tweak_ctx;
+	struct twofish_ctx crypt_ctx;
+};
+
+/* regular block cipher functions from twofish_x86_64 module */
+asmlinkage void twofish_enc_blk(struct twofish_ctx *ctx, u8 *dst,
+				const u8 *src);
+asmlinkage void twofish_dec_blk(struct twofish_ctx *ctx, u8 *dst,
+				const u8 *src);
+
+/* 3-way parallel cipher functions */
+asmlinkage void __twofish_enc_blk_3way(struct twofish_ctx *ctx, u8 *dst,
+				       const u8 *src, bool xor);
+asmlinkage void twofish_dec_blk_3way(struct twofish_ctx *ctx, u8 *dst,
+				     const u8 *src);
+
+/* helpers from twofish_x86_64-3way module */
+extern void twofish_dec_blk_cbc_3way(void *ctx, u128 *dst, const u128 *src);
+extern void twofish_enc_blk_ctr(void *ctx, u128 *dst, const u128 *src,
+				u128 *iv);
+extern void twofish_enc_blk_ctr_3way(void *ctx, u128 *dst, const u128 *src,
+				     u128 *iv);
+
+extern int lrw_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+			      unsigned int keylen);
+
+extern void lrw_twofish_exit_tfm(struct crypto_tfm *tfm);
+
+extern int xts_twofish_setkey(struct crypto_tfm *tfm, const u8 *key,
+			      unsigned int keylen);
+
+#endif /* ASM_X86_TWOFISH_H */
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index 0baa628e330c..40afa0005c69 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -15,15 +15,6 @@ BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
 BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
 BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR)
-
-.irp idx,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
-	16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
-.if NUM_INVALIDATE_TLB_VECTORS > \idx
-BUILD_INTERRUPT3(invalidate_interrupt\idx,
-		 (INVALIDATE_TLB_VECTOR_START)+\idx,
-		 smp_invalidate_interrupt)
-.endif
-.endr
 #endif
 
 BUILD_INTERRUPT(x86_platform_ipi, X86_PLATFORM_IPI_VECTOR)
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index 4b4448761e88..1508e518c7e3 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -119,17 +119,6 @@
  */
 #define LOCAL_TIMER_VECTOR		0xef
 
-/* up to 32 vectors used for spreading out TLB flushes: */
-#if NR_CPUS <= 32
-# define NUM_INVALIDATE_TLB_VECTORS	(NR_CPUS)
-#else
-# define NUM_INVALIDATE_TLB_VECTORS	(32)
-#endif
-
-#define INVALIDATE_TLB_VECTOR_END	(0xee)
-#define INVALIDATE_TLB_VECTOR_START	\
-	(INVALIDATE_TLB_VECTOR_END-NUM_INVALIDATE_TLB_VECTORS+1)
-
 #define NR_VECTORS			 256
 
 #define FPU_IRQ				  13
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 0b47ddb6f00b..a0facf3908d7 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -360,9 +360,10 @@ static inline void __flush_tlb_single(unsigned long addr)
 
 static inline void flush_tlb_others(const struct cpumask *cpumask,
 				    struct mm_struct *mm,
-				    unsigned long va)
+				    unsigned long start,
+				    unsigned long end)
 {
-	PVOP_VCALL3(pv_mmu_ops.flush_tlb_others, cpumask, mm, va);
+	PVOP_VCALL4(pv_mmu_ops.flush_tlb_others, cpumask, mm, start, end);
 }
 
 static inline int paravirt_pgd_alloc(struct mm_struct *mm)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 8613cbb7ba41..142236ed83af 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -248,7 +248,8 @@ struct pv_mmu_ops {
 	void (*flush_tlb_single)(unsigned long addr);
 	void (*flush_tlb_others)(const struct cpumask *cpus,
 				 struct mm_struct *mm,
-				 unsigned long va);
+				 unsigned long start,
+				 unsigned long end);
 
 	/* Hooks for allocating and freeing a pagetable top-level */
 	int  (*pgd_alloc)(struct mm_struct *mm);
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index d9b8e3f7f42a..1104afaba52b 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -551,6 +551,12 @@ DECLARE_PER_CPU(unsigned long, this_cpu_off);
 				{ [0 ... NR_CPUS-1] = _initvalue };	\
 	__typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map
 
+#define DEFINE_EARLY_PER_CPU_READ_MOSTLY(_type, _name, _initvalue)	\
+	DEFINE_PER_CPU_READ_MOSTLY(_type, _name) = _initvalue;		\
+	__typeof__(_type) _name##_early_map[NR_CPUS] __initdata =	\
+				{ [0 ... NR_CPUS-1] = _initvalue };	\
+	__typeof__(_type) *_name##_early_ptr __refdata = _name##_early_map
+
 #define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
 	EXPORT_PER_CPU_SYMBOL(_name)
 
@@ -559,6 +565,11 @@ DECLARE_PER_CPU(unsigned long, this_cpu_off);
 	extern __typeof__(_type) *_name##_early_ptr;		\
 	extern __typeof__(_type)  _name##_early_map[]
 
+#define DECLARE_EARLY_PER_CPU_READ_MOSTLY(_type, _name)		\
+	DECLARE_PER_CPU_READ_MOSTLY(_type, _name);		\
+	extern __typeof__(_type) *_name##_early_ptr;		\
+	extern __typeof__(_type)  _name##_early_map[]
+
 #define	early_per_cpu_ptr(_name) (_name##_early_ptr)
 #define	early_per_cpu_map(_name, _idx) (_name##_early_map[_idx])
 #define	early_per_cpu(_name, _cpu) 				\
@@ -570,12 +581,18 @@ DECLARE_PER_CPU(unsigned long, this_cpu_off);
 #define	DEFINE_EARLY_PER_CPU(_type, _name, _initvalue)		\
 	DEFINE_PER_CPU(_type, _name) = _initvalue
 
+#define DEFINE_EARLY_PER_CPU_READ_MOSTLY(_type, _name, _initvalue)	\
+	DEFINE_PER_CPU_READ_MOSTLY(_type, _name) = _initvalue
+
 #define EXPORT_EARLY_PER_CPU_SYMBOL(_name)			\
 	EXPORT_PER_CPU_SYMBOL(_name)
 
 #define DECLARE_EARLY_PER_CPU(_type, _name)			\
 	DECLARE_PER_CPU(_type, _name)
 
+#define DECLARE_EARLY_PER_CPU_READ_MOSTLY(_type, _name)		\
+	DECLARE_PER_CPU_READ_MOSTLY(_type, _name)
+
 #define	early_per_cpu(_name, _cpu) per_cpu(_name, _cpu)
 #define	early_per_cpu_ptr(_name) NULL
 /* no early_per_cpu_map() */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index c78f14a0df00..dab39350e51e 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -234,7 +234,7 @@ extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
 extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
 extern void perf_check_microcode(void);
 #else
-static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
+static inline struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
 	*nr = 0;
 	return NULL;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 39bc5777211a..d048cad9bcad 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -61,6 +61,19 @@ static inline void *current_text_addr(void)
 # define ARCH_MIN_MMSTRUCT_ALIGN	0
 #endif
 
+enum tlb_infos {
+	ENTRIES,
+	NR_INFO
+};
+
+extern u16 __read_mostly tlb_lli_4k[NR_INFO];
+extern u16 __read_mostly tlb_lli_2m[NR_INFO];
+extern u16 __read_mostly tlb_lli_4m[NR_INFO];
+extern u16 __read_mostly tlb_lld_4k[NR_INFO];
+extern u16 __read_mostly tlb_lld_2m[NR_INFO];
+extern u16 __read_mostly tlb_lld_4m[NR_INFO];
+extern s8  __read_mostly tlb_flushall_shift;
+
 /*
  *  CPU type and hardware bug flags. Kept separately for each CPU.
  *  Members of this structure are referenced in head.S, so think twice
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 2ffa95dc2333..4f19a1526037 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -31,12 +31,12 @@ static inline bool cpu_has_ht_siblings(void)
 	return has_siblings;
 }
 
-DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
-DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
+DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
+DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
 /* cpus sharing the last level cache: */
-DECLARE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
-DECLARE_PER_CPU(u16, cpu_llc_id);
-DECLARE_PER_CPU(int, cpu_number);
+DECLARE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
+DECLARE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id);
+DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
 
 static inline struct cpumask *cpu_sibling_mask(int cpu)
 {
@@ -53,10 +53,10 @@ static inline struct cpumask *cpu_llc_shared_mask(int cpu)
 	return per_cpu(cpu_llc_shared_map, cpu);
 }
 
-DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
-DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
+DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid);
+DECLARE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid);
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86_32)
-DECLARE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid);
+DECLARE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid);
 #endif
 
 /* Static state in head.S used to set up a CPU */
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 829215fef9ee..4fef20773b8f 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -4,7 +4,14 @@
 #define tlb_start_vma(tlb, vma) do { } while (0)
 #define tlb_end_vma(tlb, vma) do { } while (0)
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
-#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
+
+#define tlb_flush(tlb)							\
+{									\
+	if (tlb->fullmm == 0)						\
+		flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL);	\
+	else								\
+		flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL);	\
+}
 
 #include <asm-generic/tlb.h>
 
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 36a1a2ab87d2..74a44333545a 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -73,14 +73,10 @@ static inline void __flush_tlb_one(unsigned long addr)
  *  - flush_tlb_page(vma, vmaddr) flushes one page
  *  - flush_tlb_range(vma, start, end) flushes a range of pages
  *  - flush_tlb_kernel_range(start, end) flushes a range of kernel pages
- *  - flush_tlb_others(cpumask, mm, va) flushes TLBs on other cpus
+ *  - flush_tlb_others(cpumask, mm, start, end) flushes TLBs on other cpus
  *
  * ..but the i386 has somewhat limited tlb flushing capabilities,
  * and page-granular flushes are available only on i486 and up.
- *
- * x86-64 can only flush individual pages or full VMs. For a range flush
- * we always do the full VM. Might be worth trying if for a small
- * range a few INVLPGs in a row are a win.
  */
 
 #ifndef CONFIG_SMP
@@ -109,9 +105,17 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
 		__flush_tlb();
 }
 
+static inline void flush_tlb_mm_range(struct mm_struct *mm,
+	   unsigned long start, unsigned long end, unsigned long vmflag)
+{
+	if (mm == current->active_mm)
+		__flush_tlb();
+}
+
 static inline void native_flush_tlb_others(const struct cpumask *cpumask,
 					   struct mm_struct *mm,
-					   unsigned long va)
+					   unsigned long start,
+					   unsigned long end)
 {
 }
 
@@ -119,27 +123,35 @@ static inline void reset_lazy_tlbstate(void)
 {
 }
 
+static inline void flush_tlb_kernel_range(unsigned long start,
+					  unsigned long end)
+{
+	flush_tlb_all();
+}
+
 #else  /* SMP */
 
 #include <asm/smp.h>
 
 #define local_flush_tlb() __flush_tlb()
 
+#define flush_tlb_mm(mm)	flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL)
+
+#define flush_tlb_range(vma, start, end)	\
+		flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags)
+
 extern void flush_tlb_all(void);
 extern void flush_tlb_current_task(void);
-extern void flush_tlb_mm(struct mm_struct *);
 extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
+extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+				unsigned long end, unsigned long vmflag);
+extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #define flush_tlb()	flush_tlb_current_task()
 
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end)
-{
-	flush_tlb_mm(vma->vm_mm);
-}
-
 void native_flush_tlb_others(const struct cpumask *cpumask,
-			     struct mm_struct *mm, unsigned long va);
+				struct mm_struct *mm,
+				unsigned long start, unsigned long end);
 
 #define TLBSTATE_OK	1
 #define TLBSTATE_LAZY	2
@@ -159,13 +171,8 @@ static inline void reset_lazy_tlbstate(void)
 #endif	/* SMP */
 
 #ifndef CONFIG_PARAVIRT
-#define flush_tlb_others(mask, mm, va)	native_flush_tlb_others(mask, mm, va)
+#define flush_tlb_others(mask, mm, start, end)	\
+	native_flush_tlb_others(mask, mm, start, end)
 #endif
 
-static inline void flush_tlb_kernel_range(unsigned long start,
-					  unsigned long end)
-{
-	flush_tlb_all();
-}
-
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 4437001d8e3d..0d9776e9e2dc 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -15,7 +15,6 @@
 # ifdef CONFIG_X86_32
 
 #  include <asm/unistd_32.h>
-#  define __ARCH_WANT_IPC_PARSE_VERSION
 #  define __ARCH_WANT_STAT64
 #  define __ARCH_WANT_SYS_IPC
 #  define __ARCH_WANT_SYS_OLD_MMAP
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index 3bb9491b7659..b47c2a82ff15 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -15,7 +15,8 @@ extern void uv_nmi_init(void);
 extern void uv_system_init(void);
 extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 						 struct mm_struct *mm,
-						 unsigned long va,
+						 unsigned long start,
+						 unsigned end,
 						 unsigned int cpu);
 
 #else	/* X86_UV */
@@ -26,7 +27,7 @@ static inline void uv_cpu_init(void)	{ }
 static inline void uv_system_init(void)	{ }
 static inline const struct cpumask *
 uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm,
-		    unsigned long va, unsigned int cpu)
+		    unsigned long start, unsigned long end, unsigned int cpu)
 { return cpumask; }
 
 #endif	/* X86_UV */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 98e24131ff3a..24deb3082328 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -75,8 +75,8 @@ physid_mask_t phys_cpu_present_map;
 /*
  * Map cpu index to physical APIC ID
  */
-DEFINE_EARLY_PER_CPU(u16, x86_cpu_to_apicid, BAD_APICID);
-DEFINE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid, BAD_APICID);
+DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_cpu_to_apicid, BAD_APICID);
+DEFINE_EARLY_PER_CPU_READ_MOSTLY(u16, x86_bios_cpu_apicid, BAD_APICID);
 EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_apicid);
 EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
 
@@ -88,7 +88,7 @@ EXPORT_EARLY_PER_CPU_SYMBOL(x86_bios_cpu_apicid);
  * used for the mapping.  This is where the behaviors of x86_64 and 32
  * actually diverge.  Let's keep it ugly for now.
  */
-DEFINE_EARLY_PER_CPU(int, x86_cpu_to_logical_apicid, BAD_APICID);
+DEFINE_EARLY_PER_CPU_READ_MOSTLY(int, x86_cpu_to_logical_apicid, BAD_APICID);
 
 /*
  * Knob to control our willingness to enable the local APIC.
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index bac4c3804cc7..d30a6a9a0121 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -14,7 +14,7 @@ CFLAGS_common.o		:= $(nostackp)
 
 obj-y			:= intel_cacheinfo.o scattered.o topology.o
 obj-y			+= proc.o capflags.o powerflags.o common.o
-obj-y			+= vmware.o hypervisor.o sched.o mshyperv.o
+obj-y			+= vmware.o hypervisor.o mshyperv.o
 obj-y			+= rdrand.o
 obj-y			+= match.o
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 5bbc082c47ad..46d8786d655e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -452,6 +452,35 @@ void __cpuinit cpu_detect_cache_sizes(struct cpuinfo_x86 *c)
 	c->x86_cache_size = l2size;
 }
 
+u16 __read_mostly tlb_lli_4k[NR_INFO];
+u16 __read_mostly tlb_lli_2m[NR_INFO];
+u16 __read_mostly tlb_lli_4m[NR_INFO];
+u16 __read_mostly tlb_lld_4k[NR_INFO];
+u16 __read_mostly tlb_lld_2m[NR_INFO];
+u16 __read_mostly tlb_lld_4m[NR_INFO];
+
+/*
+ * tlb_flushall_shift shows the balance point in replacing cr3 write
+ * with multiple 'invlpg'. It will do this replacement when
+ *   flush_tlb_lines <= active_lines/2^tlb_flushall_shift.
+ * If tlb_flushall_shift is -1, means the replacement will be disabled.
+ */
+s8  __read_mostly tlb_flushall_shift = -1;
+
+void __cpuinit cpu_detect_tlb(struct cpuinfo_x86 *c)
+{
+	if (this_cpu->c_detect_tlb)
+		this_cpu->c_detect_tlb(c);
+
+	printk(KERN_INFO "Last level iTLB entries: 4KB %d, 2MB %d, 4MB %d\n" \
+		"Last level dTLB entries: 4KB %d, 2MB %d, 4MB %d\n"	     \
+		"tlb_flushall_shift is 0x%x\n",
+		tlb_lli_4k[ENTRIES], tlb_lli_2m[ENTRIES],
+		tlb_lli_4m[ENTRIES], tlb_lld_4k[ENTRIES],
+		tlb_lld_2m[ENTRIES], tlb_lld_4m[ENTRIES],
+		tlb_flushall_shift);
+}
+
 void __cpuinit detect_ht(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_HT
@@ -911,6 +940,8 @@ void __init identify_boot_cpu(void)
 #else
 	vgetcpu_set_mode();
 #endif
+	if (boot_cpu_data.cpuid_level >= 2)
+		cpu_detect_tlb(&boot_cpu_data);
 }
 
 void __cpuinit identify_secondary_cpu(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 8bacc7826fb3..4041c24ae7db 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -20,10 +20,19 @@ struct cpu_dev {
 	void		(*c_bsp_init)(struct cpuinfo_x86 *);
 	void		(*c_init)(struct cpuinfo_x86 *);
 	void		(*c_identify)(struct cpuinfo_x86 *);
+	void		(*c_detect_tlb)(struct cpuinfo_x86 *);
 	unsigned int	(*c_size_cache)(struct cpuinfo_x86 *, unsigned int);
 	int		c_x86_vendor;
 };
 
+struct _tlb_table {
+	unsigned char descriptor;
+	char tlb_type;
+	unsigned int entries;
+	/* unsigned int ways; */
+	char info[128];
+};
+
 #define cpu_dev_register(cpu_devX) \
 	static const struct cpu_dev *const __cpu_dev_##cpu_devX __used \
 	__attribute__((__section__(".x86_cpu_dev.init"))) = \
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3e6ff6cbf42a..0a4ce2980a5a 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -491,6 +491,181 @@ static unsigned int __cpuinit intel_size_cache(struct cpuinfo_x86 *c, unsigned i
 }
 #endif
 
+#define TLB_INST_4K	0x01
+#define TLB_INST_4M	0x02
+#define TLB_INST_2M_4M	0x03
+
+#define TLB_INST_ALL	0x05
+#define TLB_INST_1G	0x06
+
+#define TLB_DATA_4K	0x11
+#define TLB_DATA_4M	0x12
+#define TLB_DATA_2M_4M	0x13
+#define TLB_DATA_4K_4M	0x14
+
+#define TLB_DATA_1G	0x16
+
+#define TLB_DATA0_4K	0x21
+#define TLB_DATA0_4M	0x22
+#define TLB_DATA0_2M_4M	0x23
+
+#define STLB_4K		0x41
+
+static const struct _tlb_table intel_tlb_table[] __cpuinitconst = {
+	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
+	{ 0x02, TLB_INST_4M,		2,	" TLB_INST 4 MByte pages, full associative" },
+	{ 0x03, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way set associative" },
+	{ 0x04, TLB_DATA_4M,		8,	" TLB_DATA 4 MByte pages, 4-way set associative" },
+	{ 0x05, TLB_DATA_4M,		32,	" TLB_DATA 4 MByte pages, 4-way set associative" },
+	{ 0x0b, TLB_INST_4M,		4,	" TLB_INST 4 MByte pages, 4-way set associative" },
+	{ 0x4f, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages */" },
+	{ 0x50, TLB_INST_ALL,		64,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
+	{ 0x51, TLB_INST_ALL,		128,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
+	{ 0x52, TLB_INST_ALL,		256,	" TLB_INST 4 KByte and 2-MByte or 4-MByte pages" },
+	{ 0x55, TLB_INST_2M_4M,		7,	" TLB_INST 2-MByte or 4-MByte pages, fully associative" },
+	{ 0x56, TLB_DATA0_4M,		16,	" TLB_DATA0 4 MByte pages, 4-way set associative" },
+	{ 0x57, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, 4-way associative" },
+	{ 0x59, TLB_DATA0_4K,		16,	" TLB_DATA0 4 KByte pages, fully associative" },
+	{ 0x5a, TLB_DATA0_2M_4M,	32,	" TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative" },
+	{ 0x5b, TLB_DATA_4K_4M,		64,	" TLB_DATA 4 KByte and 4 MByte pages" },
+	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
+	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
+	{ 0xb0, TLB_INST_4K,		128,	" TLB_INST 4 KByte pages, 4-way set associative" },
+	{ 0xb1, TLB_INST_2M_4M,		4,	" TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries" },
+	{ 0xb2, TLB_INST_4K,		64,	" TLB_INST 4KByte pages, 4-way set associative" },
+	{ 0xb3, TLB_DATA_4K,		128,	" TLB_DATA 4 KByte pages, 4-way set associative" },
+	{ 0xb4, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 4-way associative" },
+	{ 0xba, TLB_DATA_4K,		64,	" TLB_DATA 4 KByte pages, 4-way associative" },
+	{ 0xc0, TLB_DATA_4K_4M,		8,	" TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
+	{ 0xca, STLB_4K,		512,	" STLB 4 KByte pages, 4-way associative" },
+	{ 0x00, 0, 0 }
+};
+
+static void __cpuinit intel_tlb_lookup(const unsigned char desc)
+{
+	unsigned char k;
+	if (desc == 0)
+		return;
+
+	/* look up this descriptor in the table */
+	for (k = 0; intel_tlb_table[k].descriptor != desc && \
+			intel_tlb_table[k].descriptor != 0; k++)
+		;
+
+	if (intel_tlb_table[k].tlb_type == 0)
+		return;
+
+	switch (intel_tlb_table[k].tlb_type) {
+	case STLB_4K:
+		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		break;
+	case TLB_INST_ALL:
+		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		break;
+	case TLB_INST_4K:
+		if (tlb_lli_4k[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_4k[ENTRIES] = intel_tlb_table[k].entries;
+		break;
+	case TLB_INST_4M:
+		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		break;
+	case TLB_INST_2M_4M:
+		if (tlb_lli_2m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_2m[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lli_4m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lli_4m[ENTRIES] = intel_tlb_table[k].entries;
+		break;
+	case TLB_DATA_4K:
+	case TLB_DATA0_4K:
+		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		break;
+	case TLB_DATA_4M:
+	case TLB_DATA0_4M:
+		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		break;
+	case TLB_DATA_2M_4M:
+	case TLB_DATA0_2M_4M:
+		if (tlb_lld_2m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_2m[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		break;
+	case TLB_DATA_4K_4M:
+		if (tlb_lld_4k[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_4k[ENTRIES] = intel_tlb_table[k].entries;
+		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
+			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
+		break;
+	}
+}
+
+static void __cpuinit intel_tlb_flushall_shift_set(struct cpuinfo_x86 *c)
+{
+	if (!cpu_has_invlpg) {
+		tlb_flushall_shift = -1;
+		return;
+	}
+	switch ((c->x86 << 8) + c->x86_model) {
+	case 0x60f: /* original 65 nm celeron/pentium/core2/xeon, "Merom"/"Conroe" */
+	case 0x616: /* single-core 65 nm celeron/core2solo "Merom-L"/"Conroe-L" */
+	case 0x617: /* current 45 nm celeron/core2/xeon "Penryn"/"Wolfdale" */
+	case 0x61d: /* six-core 45 nm xeon "Dunnington" */
+		tlb_flushall_shift = -1;
+		break;
+	case 0x61a: /* 45 nm nehalem, "Bloomfield" */
+	case 0x61e: /* 45 nm nehalem, "Lynnfield" */
+	case 0x625: /* 32 nm nehalem, "Clarkdale" */
+	case 0x62c: /* 32 nm nehalem, "Gulftown" */
+	case 0x62e: /* 45 nm nehalem-ex, "Beckton" */
+	case 0x62f: /* 32 nm Xeon E7 */
+		tlb_flushall_shift = 6;
+		break;
+	case 0x62a: /* SandyBridge */
+	case 0x62d: /* SandyBridge, "Romely-EP" */
+		tlb_flushall_shift = 5;
+		break;
+	case 0x63a: /* Ivybridge */
+		tlb_flushall_shift = 1;
+		break;
+	default:
+		tlb_flushall_shift = 6;
+	}
+}
+
+static void __cpuinit intel_detect_tlb(struct cpuinfo_x86 *c)
+{
+	int i, j, n;
+	unsigned int regs[4];
+	unsigned char *desc = (unsigned char *)regs;
+	/* Number of times to iterate */
+	n = cpuid_eax(2) & 0xFF;
+
+	for (i = 0 ; i < n ; i++) {
+		cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
+
+		/* If bit 31 is set, this is an unknown format */
+		for (j = 0 ; j < 3 ; j++)
+			if (regs[j] & (1 << 31))
+				regs[j] = 0;
+
+		/* Byte 0 is level count, not a descriptor */
+		for (j = 1 ; j < 16 ; j++)
+			intel_tlb_lookup(desc[j]);
+	}
+	intel_tlb_flushall_shift_set(c);
+}
+
 static const struct cpu_dev __cpuinitconst intel_cpu_dev = {
 	.c_vendor	= "Intel",
 	.c_ident	= { "GenuineIntel" },
@@ -546,6 +721,7 @@ static const struct cpu_dev __cpuinitconst intel_cpu_dev = {
 	},
 	.c_size_cache	= intel_size_cache,
 #endif
+	.c_detect_tlb	= intel_detect_tlb,
 	.c_early_init   = early_init_intel,
 	.c_init		= init_intel,
 	.c_x86_vendor	= X86_VENDOR_INTEL,
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index a15df4be151f..821d53b696d1 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -374,7 +374,7 @@ struct x86_pmu {
 	/*
 	 * Intel DebugStore bits
 	 */
-	int		bts		:1,
+	unsigned int	bts		:1,
 			bts_active	:1,
 			pebs		:1,
 			pebs_active	:1,
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 7a8b9d0abcaa..382366977d4c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -138,6 +138,84 @@ static u64 intel_pmu_event_map(int hw_event)
 	return intel_perfmon_event_map[hw_event];
 }
 
+#define SNB_DMND_DATA_RD	(1ULL << 0)
+#define SNB_DMND_RFO		(1ULL << 1)
+#define SNB_DMND_IFETCH		(1ULL << 2)
+#define SNB_DMND_WB		(1ULL << 3)
+#define SNB_PF_DATA_RD		(1ULL << 4)
+#define SNB_PF_RFO		(1ULL << 5)
+#define SNB_PF_IFETCH		(1ULL << 6)
+#define SNB_LLC_DATA_RD		(1ULL << 7)
+#define SNB_LLC_RFO		(1ULL << 8)
+#define SNB_LLC_IFETCH		(1ULL << 9)
+#define SNB_BUS_LOCKS		(1ULL << 10)
+#define SNB_STRM_ST		(1ULL << 11)
+#define SNB_OTHER		(1ULL << 15)
+#define SNB_RESP_ANY		(1ULL << 16)
+#define SNB_NO_SUPP		(1ULL << 17)
+#define SNB_LLC_HITM		(1ULL << 18)
+#define SNB_LLC_HITE		(1ULL << 19)
+#define SNB_LLC_HITS		(1ULL << 20)
+#define SNB_LLC_HITF		(1ULL << 21)
+#define SNB_LOCAL		(1ULL << 22)
+#define SNB_REMOTE		(0xffULL << 23)
+#define SNB_SNP_NONE		(1ULL << 31)
+#define SNB_SNP_NOT_NEEDED	(1ULL << 32)
+#define SNB_SNP_MISS		(1ULL << 33)
+#define SNB_NO_FWD		(1ULL << 34)
+#define SNB_SNP_FWD		(1ULL << 35)
+#define SNB_HITM		(1ULL << 36)
+#define SNB_NON_DRAM		(1ULL << 37)
+
+#define SNB_DMND_READ		(SNB_DMND_DATA_RD|SNB_LLC_DATA_RD)
+#define SNB_DMND_WRITE		(SNB_DMND_RFO|SNB_LLC_RFO)
+#define SNB_DMND_PREFETCH	(SNB_PF_DATA_RD|SNB_PF_RFO)
+
+#define SNB_SNP_ANY		(SNB_SNP_NONE|SNB_SNP_NOT_NEEDED| \
+				 SNB_SNP_MISS|SNB_NO_FWD|SNB_SNP_FWD| \
+				 SNB_HITM)
+
+#define SNB_DRAM_ANY		(SNB_LOCAL|SNB_REMOTE|SNB_SNP_ANY)
+#define SNB_DRAM_REMOTE		(SNB_REMOTE|SNB_SNP_ANY)
+
+#define SNB_L3_ACCESS		SNB_RESP_ANY
+#define SNB_L3_MISS		(SNB_DRAM_ANY|SNB_NON_DRAM)
+
+static __initconst const u64 snb_hw_cache_extra_regs
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = SNB_DMND_READ|SNB_L3_MISS,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = SNB_DMND_WRITE|SNB_L3_MISS,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_L3_ACCESS,
+		[ C(RESULT_MISS)   ] = SNB_DMND_PREFETCH|SNB_L3_MISS,
+	},
+ },
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_DRAM_ANY,
+		[ C(RESULT_MISS)   ] = SNB_DMND_READ|SNB_DRAM_REMOTE,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_DRAM_ANY,
+		[ C(RESULT_MISS)   ] = SNB_DMND_WRITE|SNB_DRAM_REMOTE,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_DRAM_ANY,
+		[ C(RESULT_MISS)   ] = SNB_DMND_PREFETCH|SNB_DRAM_REMOTE,
+	},
+ },
+};
+
 static __initconst const u64 snb_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -235,16 +313,16 @@ static __initconst const u64 snb_hw_cache_event_ids
  },
  [ C(NODE) ] = {
 	[ C(OP_READ) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_WRITE) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
 	[ C(OP_PREFETCH) ] = {
-		[ C(RESULT_ACCESS) ] = -1,
-		[ C(RESULT_MISS)   ] = -1,
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		[ C(RESULT_MISS)   ] = 0x01b7,
 	},
  },
 
@@ -1964,6 +2042,8 @@ __init int intel_pmu_init(void)
 	case 58: /* IvyBridge */
 		memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
 		       sizeof(hw_cache_event_ids));
+		memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
+		       sizeof(hw_cache_extra_regs));
 
 		intel_pmu_lbr_init_snb();
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 19faffc60886..7563fda9f033 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -18,6 +18,7 @@ static struct event_constraint constraint_empty =
 	EVENT_CONSTRAINT(0, 0, 0);
 
 DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21");
 DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15");
 DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
 DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
@@ -33,10 +34,81 @@ DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4");
 DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17");
 DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22");
 DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31");
-DEFINE_UNCORE_FORMAT_ATTR(filter_brand0, filter_brand0, "config1:0-7");
-DEFINE_UNCORE_FORMAT_ATTR(filter_brand1, filter_brand1, "config1:8-15");
-DEFINE_UNCORE_FORMAT_ATTR(filter_brand2, filter_brand2, "config1:16-23");
-DEFINE_UNCORE_FORMAT_ATTR(filter_brand3, filter_brand3, "config1:24-31");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23");
+DEFINE_UNCORE_FORMAT_ATTR(filter_band3, filter_band3, "config1:24-31");
+
+static u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *event)
+{
+	u64 count;
+
+	rdmsrl(event->hw.event_base, count);
+
+	return count;
+}
+
+/*
+ * generic get constraint function for shared match/mask registers.
+ */
+static struct event_constraint *
+uncore_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct intel_uncore_extra_reg *er;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	unsigned long flags;
+	bool ok = false;
+
+	/*
+	 * reg->alloc can be set due to existing state, so for fake box we
+	 * need to ignore this, otherwise we might fail to allocate proper
+	 * fake state for this extra reg constraint.
+	 */
+	if (reg1->idx == EXTRA_REG_NONE ||
+	    (!uncore_box_is_fake(box) && reg1->alloc))
+		return NULL;
+
+	er = &box->shared_regs[reg1->idx];
+	raw_spin_lock_irqsave(&er->lock, flags);
+	if (!atomic_read(&er->ref) ||
+	    (er->config1 == reg1->config && er->config2 == reg2->config)) {
+		atomic_inc(&er->ref);
+		er->config1 = reg1->config;
+		er->config2 = reg2->config;
+		ok = true;
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	if (ok) {
+		if (!uncore_box_is_fake(box))
+			reg1->alloc = 1;
+		return NULL;
+	}
+
+	return &constraint_empty;
+}
+
+static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct intel_uncore_extra_reg *er;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+
+	/*
+	 * Only put constraint if extra reg was actually allocated. Also
+	 * takes care of event which do not use an extra shared reg.
+	 *
+	 * Also, if this is a fake box we shouldn't touch any event state
+	 * (reg->alloc) and we don't care about leaving inconsistent box
+	 * state either since it will be thrown out.
+	 */
+	if (uncore_box_is_fake(box) || !reg1->alloc)
+		return;
+
+	er = &box->shared_regs[reg1->idx];
+	atomic_dec(&er->ref);
+	reg1->alloc = 0;
+}
 
 /* Sandy Bridge-EP uncore support */
 static struct intel_uncore_type snbep_uncore_cbox;
@@ -64,18 +136,15 @@ static void snbep_uncore_pci_enable_box(struct intel_uncore_box *box)
 	pci_write_config_dword(pdev, box_ctl, config);
 }
 
-static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void snbep_uncore_pci_enable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct pci_dev *pdev = box->pci_dev;
 	struct hw_perf_event *hwc = &event->hw;
 
-	pci_write_config_dword(pdev, hwc->config_base, hwc->config |
-				SNBEP_PMON_CTL_EN);
+	pci_write_config_dword(pdev, hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
 }
 
-static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct pci_dev *pdev = box->pci_dev;
 	struct hw_perf_event *hwc = &event->hw;
@@ -83,8 +152,7 @@ static void snbep_uncore_pci_disable_event(struct intel_uncore_box *box,
 	pci_write_config_dword(pdev, hwc->config_base, hwc->config);
 }
 
-static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box,
-					struct perf_event *event)
+static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct pci_dev *pdev = box->pci_dev;
 	struct hw_perf_event *hwc = &event->hw;
@@ -92,14 +160,15 @@ static u64 snbep_uncore_pci_read_counter(struct intel_uncore_box *box,
 
 	pci_read_config_dword(pdev, hwc->event_base, (u32 *)&count);
 	pci_read_config_dword(pdev, hwc->event_base + 4, (u32 *)&count + 1);
+
 	return count;
 }
 
 static void snbep_uncore_pci_init_box(struct intel_uncore_box *box)
 {
 	struct pci_dev *pdev = box->pci_dev;
-	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL,
-				SNBEP_PMON_BOX_CTL_INT);
+
+	pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, SNBEP_PMON_BOX_CTL_INT);
 }
 
 static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
@@ -112,7 +181,6 @@ static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
 		rdmsrl(msr, config);
 		config |= SNBEP_PMON_BOX_CTL_FRZ;
 		wrmsrl(msr, config);
-		return;
 	}
 }
 
@@ -126,12 +194,10 @@ static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
 		rdmsrl(msr, config);
 		config &= ~SNBEP_PMON_BOX_CTL_FRZ;
 		wrmsrl(msr, config);
-		return;
 	}
 }
 
-static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
@@ -150,68 +216,15 @@ static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
 	wrmsrl(hwc->config_base, hwc->config);
 }
 
-static u64 snbep_uncore_msr_read_counter(struct intel_uncore_box *box,
-					struct perf_event *event)
-{
-	struct hw_perf_event *hwc = &event->hw;
-	u64 count;
-
-	rdmsrl(hwc->event_base, count);
-	return count;
-}
-
 static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
 {
 	unsigned msr = uncore_msr_box_ctl(box);
+
 	if (msr)
 		wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
 }
 
-static struct event_constraint *
-snbep_uncore_get_constraint(struct intel_uncore_box *box,
-			    struct perf_event *event)
-{
-	struct intel_uncore_extra_reg *er;
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-	unsigned long flags;
-	bool ok = false;
-
-	if (reg1->idx == EXTRA_REG_NONE || (box->phys_id >= 0 && reg1->alloc))
-		return NULL;
-
-	er = &box->shared_regs[reg1->idx];
-	raw_spin_lock_irqsave(&er->lock, flags);
-	if (!atomic_read(&er->ref) || er->config1 == reg1->config) {
-		atomic_inc(&er->ref);
-		er->config1 = reg1->config;
-		ok = true;
-	}
-	raw_spin_unlock_irqrestore(&er->lock, flags);
-
-	if (ok) {
-		if (box->phys_id >= 0)
-			reg1->alloc = 1;
-		return NULL;
-	}
-	return &constraint_empty;
-}
-
-static void snbep_uncore_put_constraint(struct intel_uncore_box *box,
-					struct perf_event *event)
-{
-	struct intel_uncore_extra_reg *er;
-	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
-
-	if (box->phys_id < 0 || !reg1->alloc)
-		return;
-
-	er = &box->shared_regs[reg1->idx];
-	atomic_dec(&er->ref);
-	reg1->alloc = 0;
-}
-
-static int snbep_uncore_hw_config(struct intel_uncore_box *box,
-				  struct perf_event *event)
+static int snbep_uncore_hw_config(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
@@ -221,14 +234,16 @@ static int snbep_uncore_hw_config(struct intel_uncore_box *box,
 			SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx;
 		reg1->config = event->attr.config1 &
 			SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK;
-	} else if (box->pmu->type == &snbep_uncore_pcu) {
-		reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
-		reg1->config = event->attr.config1 &
-			SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK;
 	} else {
-		return 0;
+		if (box->pmu->type == &snbep_uncore_pcu) {
+			reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER;
+			reg1->config = event->attr.config1 & SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK;
+		} else {
+			return 0;
+		}
 	}
 	reg1->idx = 0;
+
 	return 0;
 }
 
@@ -272,10 +287,19 @@ static struct attribute *snbep_uncore_pcu_formats_attr[] = {
 	&format_attr_thresh5.attr,
 	&format_attr_occ_invert.attr,
 	&format_attr_occ_edge.attr,
-	&format_attr_filter_brand0.attr,
-	&format_attr_filter_brand1.attr,
-	&format_attr_filter_brand2.attr,
-	&format_attr_filter_brand3.attr,
+	&format_attr_filter_band0.attr,
+	&format_attr_filter_band1.attr,
+	&format_attr_filter_band2.attr,
+	&format_attr_filter_band3.attr,
+	NULL,
+};
+
+static struct attribute *snbep_uncore_qpi_formats_attr[] = {
+	&format_attr_event_ext.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
 	NULL,
 };
 
@@ -314,15 +338,20 @@ static struct attribute_group snbep_uncore_pcu_format_group = {
 	.attrs = snbep_uncore_pcu_formats_attr,
 };
 
+static struct attribute_group snbep_uncore_qpi_format_group = {
+	.name = "format",
+	.attrs = snbep_uncore_qpi_formats_attr,
+};
+
 static struct intel_uncore_ops snbep_uncore_msr_ops = {
 	.init_box	= snbep_uncore_msr_init_box,
 	.disable_box	= snbep_uncore_msr_disable_box,
 	.enable_box	= snbep_uncore_msr_enable_box,
 	.disable_event	= snbep_uncore_msr_disable_event,
 	.enable_event	= snbep_uncore_msr_enable_event,
-	.read_counter	= snbep_uncore_msr_read_counter,
-	.get_constraint = snbep_uncore_get_constraint,
-	.put_constraint = snbep_uncore_put_constraint,
+	.read_counter	= uncore_msr_read_counter,
+	.get_constraint = uncore_get_constraint,
+	.put_constraint = uncore_put_constraint,
 	.hw_config	= snbep_uncore_hw_config,
 };
 
@@ -485,8 +514,13 @@ static struct intel_uncore_type snbep_uncore_qpi = {
 	.num_counters   = 4,
 	.num_boxes	= 2,
 	.perf_ctr_bits	= 48,
+	.perf_ctr	= SNBEP_PCI_PMON_CTR0,
+	.event_ctl	= SNBEP_PCI_PMON_CTL0,
+	.event_mask	= SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK,
+	.box_ctl	= SNBEP_PCI_PMON_BOX_CTL,
+	.ops		= &snbep_uncore_pci_ops,
 	.event_descs	= snbep_uncore_qpi_events,
-	SNBEP_UNCORE_PCI_COMMON_INIT(),
+	.format_group	= &snbep_uncore_qpi_format_group,
 };
 
 
@@ -603,10 +637,8 @@ static void snbep_pci2phy_map_init(void)
 }
 /* end of Sandy Bridge-EP uncore support */
 
-
 /* Sandy Bridge uncore support */
-static void snb_uncore_msr_enable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -616,20 +648,11 @@ static void snb_uncore_msr_enable_event(struct intel_uncore_box *box,
 		wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
 }
 
-static void snb_uncore_msr_disable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
 	wrmsrl(event->hw.config_base, 0);
 }
 
-static u64 snb_uncore_msr_read_counter(struct intel_uncore_box *box,
-					struct perf_event *event)
-{
-	u64 count;
-	rdmsrl(event->hw.event_base, count);
-	return count;
-}
-
 static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
 {
 	if (box->pmu->pmu_idx == 0) {
@@ -648,15 +671,15 @@ static struct attribute *snb_uncore_formats_attr[] = {
 };
 
 static struct attribute_group snb_uncore_format_group = {
-	.name = "format",
-	.attrs = snb_uncore_formats_attr,
+	.name		= "format",
+	.attrs		= snb_uncore_formats_attr,
 };
 
 static struct intel_uncore_ops snb_uncore_msr_ops = {
 	.init_box	= snb_uncore_msr_init_box,
 	.disable_event	= snb_uncore_msr_disable_event,
 	.enable_event	= snb_uncore_msr_enable_event,
-	.read_counter	= snb_uncore_msr_read_counter,
+	.read_counter	= uncore_msr_read_counter,
 };
 
 static struct event_constraint snb_uncore_cbox_constraints[] = {
@@ -697,12 +720,10 @@ static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
 
 static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
 {
-	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL,
-		NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
+	wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
 }
 
-static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -744,7 +765,7 @@ static struct intel_uncore_ops nhm_uncore_msr_ops = {
 	.enable_box	= nhm_uncore_msr_enable_box,
 	.disable_event	= snb_uncore_msr_disable_event,
 	.enable_event	= nhm_uncore_msr_enable_event,
-	.read_counter	= snb_uncore_msr_read_counter,
+	.read_counter	= uncore_msr_read_counter,
 };
 
 static struct intel_uncore_type nhm_uncore = {
@@ -769,8 +790,1041 @@ static struct intel_uncore_type *nhm_msr_uncores[] = {
 };
 /* end of Nehalem uncore support */
 
-static void uncore_assign_hw_event(struct intel_uncore_box *box,
-				struct perf_event *event, int idx)
+/* Nehalem-EX uncore support */
+#define __BITS_VALUE(x, i, n)  ((typeof(x))(((x) >> ((i) * (n))) & \
+				((1ULL << (n)) - 1)))
+
+DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5");
+DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7");
+DEFINE_UNCORE_FORMAT_ATTR(mm_cfg, mm_cfg, "config:63");
+DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
+
+static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
+{
+	wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
+}
+
+static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+	u64 config;
+
+	if (msr) {
+		rdmsrl(msr, config);
+		config &= ~((1ULL << uncore_num_counters(box)) - 1);
+		/* WBox has a fixed counter */
+		if (uncore_msr_fixed_ctl(box))
+			config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN;
+		wrmsrl(msr, config);
+	}
+}
+
+static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box)
+{
+	unsigned msr = uncore_msr_box_ctl(box);
+	u64 config;
+
+	if (msr) {
+		rdmsrl(msr, config);
+		config |= (1ULL << uncore_num_counters(box)) - 1;
+		/* WBox has a fixed counter */
+		if (uncore_msr_fixed_ctl(box))
+			config |= NHMEX_W_PMON_GLOBAL_FIXED_EN;
+		wrmsrl(msr, config);
+	}
+}
+
+static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	wrmsrl(event->hw.config_base, 0);
+}
+
+static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->idx >= UNCORE_PMC_IDX_FIXED)
+		wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
+	else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
+		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+	else
+		wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+#define NHMEX_UNCORE_OPS_COMMON_INIT()				\
+	.init_box	= nhmex_uncore_msr_init_box,		\
+	.disable_box	= nhmex_uncore_msr_disable_box,		\
+	.enable_box	= nhmex_uncore_msr_enable_box,		\
+	.disable_event	= nhmex_uncore_msr_disable_event,	\
+	.read_counter	= uncore_msr_read_counter
+
+static struct intel_uncore_ops nhmex_uncore_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event	= nhmex_uncore_msr_enable_event,
+};
+
+static struct attribute *nhmex_uncore_ubox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_edge.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_ubox_format_group = {
+	.name		= "format",
+	.attrs		= nhmex_uncore_ubox_formats_attr,
+};
+
+static struct intel_uncore_type nhmex_uncore_ubox = {
+	.name		= "ubox",
+	.num_counters	= 1,
+	.num_boxes	= 1,
+	.perf_ctr_bits	= 48,
+	.event_ctl	= NHMEX_U_MSR_PMON_EV_SEL,
+	.perf_ctr	= NHMEX_U_MSR_PMON_CTR,
+	.event_mask	= NHMEX_U_PMON_RAW_EVENT_MASK,
+	.box_ctl	= NHMEX_U_MSR_PMON_GLOBAL_CTL,
+	.ops		= &nhmex_uncore_ops,
+	.format_group	= &nhmex_uncore_ubox_format_group
+};
+
+static struct attribute *nhmex_uncore_cbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_cbox_format_group = {
+	.name = "format",
+	.attrs = nhmex_uncore_cbox_formats_attr,
+};
+
+static struct intel_uncore_type nhmex_uncore_cbox = {
+	.name			= "cbox",
+	.num_counters		= 6,
+	.num_boxes		= 8,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_C0_MSR_PMON_EV_SEL0,
+	.perf_ctr		= NHMEX_C0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_C0_MSR_PMON_GLOBAL_CTL,
+	.msr_offset		= NHMEX_C_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.ops			= &nhmex_uncore_ops,
+	.format_group		= &nhmex_uncore_cbox_format_group
+};
+
+static struct uncore_event_desc nhmex_uncore_wbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(clockticks, "event=0xff,umask=0"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_type nhmex_uncore_wbox = {
+	.name			= "wbox",
+	.num_counters		= 4,
+	.num_boxes		= 1,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_W_MSR_PMON_CNT0,
+	.perf_ctr		= NHMEX_W_MSR_PMON_EVT_SEL0,
+	.fixed_ctr		= NHMEX_W_MSR_PMON_FIXED_CTR,
+	.fixed_ctl		= NHMEX_W_MSR_PMON_FIXED_CTL,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_W_MSR_GLOBAL_CTL,
+	.pair_ctr_ctl		= 1,
+	.event_descs		= nhmex_uncore_wbox_events,
+	.ops			= &nhmex_uncore_ops,
+	.format_group		= &nhmex_uncore_cbox_format_group
+};
+
+static int nhmex_bbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int ctr, ev_sel;
+
+	ctr = (hwc->config & NHMEX_B_PMON_CTR_MASK) >>
+		NHMEX_B_PMON_CTR_SHIFT;
+	ev_sel = (hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK) >>
+		  NHMEX_B_PMON_CTL_EV_SEL_SHIFT;
+
+	/* events that do not use the match/mask registers */
+	if ((ctr == 0 && ev_sel > 0x3) || (ctr == 1 && ev_sel > 0x6) ||
+	    (ctr == 2 && ev_sel != 0x4) || ctr == 3)
+		return 0;
+
+	if (box->pmu->pmu_idx == 0)
+		reg1->reg = NHMEX_B0_MSR_MATCH;
+	else
+		reg1->reg = NHMEX_B1_MSR_MATCH;
+	reg1->idx = 0;
+	reg1->config = event->attr.config1;
+	reg2->config = event->attr.config2;
+	return 0;
+}
+
+static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	if (reg1->idx != EXTRA_REG_NONE) {
+		wrmsrl(reg1->reg, reg1->config);
+		wrmsrl(reg1->reg + 1, reg2->config);
+	}
+	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+		(hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK));
+}
+
+/*
+ * The Bbox has 4 counters, but each counter monitors different events.
+ * Use bits 6-7 in the event config to select counter.
+ */
+static struct event_constraint nhmex_uncore_bbox_constraints[] = {
+	EVENT_CONSTRAINT(0 , 1, 0xc0),
+	EVENT_CONSTRAINT(0x40, 2, 0xc0),
+	EVENT_CONSTRAINT(0x80, 4, 0xc0),
+	EVENT_CONSTRAINT(0xc0, 8, 0xc0),
+	EVENT_CONSTRAINT_END,
+};
+
+static struct attribute *nhmex_uncore_bbox_formats_attr[] = {
+	&format_attr_event5.attr,
+	&format_attr_counter.attr,
+	&format_attr_match.attr,
+	&format_attr_mask.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_bbox_format_group = {
+	.name = "format",
+	.attrs = nhmex_uncore_bbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_bbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_bbox_msr_enable_event,
+	.hw_config		= nhmex_bbox_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_bbox = {
+	.name			= "bbox",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_B0_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_B0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_B_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_B0_MSR_PMON_GLOBAL_CTL,
+	.msr_offset		= NHMEX_B_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 1,
+	.constraints		= nhmex_uncore_bbox_constraints,
+	.ops			= &nhmex_uncore_bbox_ops,
+	.format_group		= &nhmex_uncore_bbox_format_group
+};
+
+static int nhmex_sbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+
+	if (event->attr.config & NHMEX_S_PMON_MM_CFG_EN) {
+		reg1->config = event->attr.config1;
+		reg2->config = event->attr.config2;
+	} else {
+		reg1->config = ~0ULL;
+		reg2->config = ~0ULL;
+	}
+
+	if (box->pmu->pmu_idx == 0)
+		reg1->reg = NHMEX_S0_MSR_MM_CFG;
+	else
+		reg1->reg = NHMEX_S1_MSR_MM_CFG;
+
+	reg1->idx = 0;
+
+	return 0;
+}
+
+static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+
+	wrmsrl(reg1->reg, 0);
+	if (reg1->config != ~0ULL || reg2->config != ~0ULL) {
+		wrmsrl(reg1->reg + 1, reg1->config);
+		wrmsrl(reg1->reg + 2, reg2->config);
+		wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
+	}
+	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+}
+
+static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_thresh8.attr,
+	&format_attr_mm_cfg.attr,
+	&format_attr_match.attr,
+	&format_attr_mask.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_sbox_format_group = {
+	.name			= "format",
+	.attrs			= nhmex_uncore_sbox_formats_attr,
+};
+
+static struct intel_uncore_ops nhmex_uncore_sbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_sbox_msr_enable_event,
+	.hw_config		= nhmex_sbox_hw_config,
+	.get_constraint		= uncore_get_constraint,
+	.put_constraint		= uncore_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_sbox = {
+	.name			= "sbox",
+	.num_counters		= 4,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_S0_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_S0_MSR_PMON_CTR0,
+	.event_mask		= NHMEX_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_S0_MSR_PMON_GLOBAL_CTL,
+	.msr_offset		= NHMEX_S_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 1,
+	.ops			= &nhmex_uncore_sbox_ops,
+	.format_group		= &nhmex_uncore_sbox_format_group
+};
+
+enum {
+	EXTRA_REG_NHMEX_M_FILTER,
+	EXTRA_REG_NHMEX_M_DSP,
+	EXTRA_REG_NHMEX_M_ISS,
+	EXTRA_REG_NHMEX_M_MAP,
+	EXTRA_REG_NHMEX_M_MSC_THR,
+	EXTRA_REG_NHMEX_M_PGT,
+	EXTRA_REG_NHMEX_M_PLD,
+	EXTRA_REG_NHMEX_M_ZDP_CTL_FVC,
+};
+
+static struct extra_reg nhmex_uncore_mbox_extra_regs[] = {
+	MBOX_INC_SEL_EXTAR_REG(0x0, DSP),
+	MBOX_INC_SEL_EXTAR_REG(0x4, MSC_THR),
+	MBOX_INC_SEL_EXTAR_REG(0x5, MSC_THR),
+	MBOX_INC_SEL_EXTAR_REG(0x9, ISS),
+	/* event 0xa uses two extra registers */
+	MBOX_INC_SEL_EXTAR_REG(0xa, ISS),
+	MBOX_INC_SEL_EXTAR_REG(0xa, PLD),
+	MBOX_INC_SEL_EXTAR_REG(0xb, PLD),
+	/* events 0xd ~ 0x10 use the same extra register */
+	MBOX_INC_SEL_EXTAR_REG(0xd, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0xe, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0xf, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0x10, ZDP_CTL_FVC),
+	MBOX_INC_SEL_EXTAR_REG(0x16, PGT),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x0, DSP),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x1, ISS),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x5, PGT),
+	MBOX_SET_FLAG_SEL_EXTRA_REG(0x6, MAP),
+	EVENT_EXTRA_END
+};
+
+static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config)
+{
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	bool ret = false;
+	u64 mask;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		er = &box->shared_regs[idx];
+		raw_spin_lock_irqsave(&er->lock, flags);
+		if (!atomic_read(&er->ref) || er->config == config) {
+			atomic_inc(&er->ref);
+			er->config = config;
+			ret = true;
+		}
+		raw_spin_unlock_irqrestore(&er->lock, flags);
+
+		return ret;
+	}
+	/*
+	 * The ZDP_CTL_FVC MSR has 4 fields which are used to control
+	 * events 0xd ~ 0x10. Besides these 4 fields, there are additional
+	 * fields which are shared.
+	 */
+	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	if (WARN_ON_ONCE(idx >= 4))
+		return false;
+
+	/* mask of the shared fields */
+	mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK;
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+
+	raw_spin_lock_irqsave(&er->lock, flags);
+	/* add mask of the non-shared field if it's in use */
+	if (__BITS_VALUE(atomic_read(&er->ref), idx, 8))
+		mask |= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+
+	if (!atomic_read(&er->ref) || !((er->config ^ config) & mask)) {
+		atomic_add(1 << (idx * 8), &er->ref);
+		mask = NHMEX_M_PMON_ZDP_CTL_FVC_MASK |
+			NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+		er->config &= ~mask;
+		er->config |= (config & mask);
+		ret = true;
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	return ret;
+}
+
+static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx)
+{
+	struct intel_uncore_extra_reg *er;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		er = &box->shared_regs[idx];
+		atomic_dec(&er->ref);
+		return;
+	}
+
+	idx -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+	atomic_sub(1 << (idx * 8), &er->ref);
+}
+
+u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	int idx, orig_idx = __BITS_VALUE(reg1->idx, 0, 8);
+	u64 config = reg1->config;
+
+	/* get the non-shared control bits and shift them */
+	idx = orig_idx - EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+	config &= NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(idx);
+	if (new_idx > orig_idx) {
+		idx = new_idx - orig_idx;
+		config <<= 3 * idx;
+	} else {
+		idx = orig_idx - new_idx;
+		config >>= 3 * idx;
+	}
+
+	/* add the shared control bits back */
+	config |= NHMEX_M_PMON_ZDP_CTL_FVC_MASK & reg1->config;
+	if (modify) {
+		/* adjust the main event selector */
+		if (new_idx > orig_idx)
+			hwc->config += idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+		else
+			hwc->config -= idx << NHMEX_M_PMON_CTL_INC_SEL_SHIFT;
+		reg1->config = config;
+		reg1->idx = ~0xff | new_idx;
+	}
+	return config;
+}
+
+static struct event_constraint *
+nhmex_mbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	int i, idx[2], alloc = 0;
+	u64 config1 = reg1->config;
+
+	idx[0] = __BITS_VALUE(reg1->idx, 0, 8);
+	idx[1] = __BITS_VALUE(reg1->idx, 1, 8);
+again:
+	for (i = 0; i < 2; i++) {
+		if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i)))
+			idx[i] = 0xff;
+
+		if (idx[i] == 0xff)
+			continue;
+
+		if (!nhmex_mbox_get_shared_reg(box, idx[i],
+				__BITS_VALUE(config1, i, 32)))
+			goto fail;
+		alloc |= (0x1 << i);
+	}
+
+	/* for the match/mask registers */
+	if ((uncore_box_is_fake(box) || !reg2->alloc) &&
+	    !nhmex_mbox_get_shared_reg(box, reg2->idx, reg2->config))
+		goto fail;
+
+	/*
+	 * If it's a fake box -- as per validate_{group,event}() we
+	 * shouldn't touch event state and we can avoid doing so
+	 * since both will only call get_event_constraints() once
+	 * on each event, this avoids the need for reg->alloc.
+	 */
+	if (!uncore_box_is_fake(box)) {
+		if (idx[0] != 0xff && idx[0] != __BITS_VALUE(reg1->idx, 0, 8))
+			nhmex_mbox_alter_er(event, idx[0], true);
+		reg1->alloc |= alloc;
+		reg2->alloc = 1;
+	}
+	return NULL;
+fail:
+	if (idx[0] != 0xff && !(alloc & 0x1) &&
+	    idx[0] >= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC) {
+		/*
+		 * events 0xd ~ 0x10 are functional identical, but are
+		 * controlled by different fields in the ZDP_CTL_FVC
+		 * register. If we failed to take one field, try the
+		 * rest 3 choices.
+		 */
+		BUG_ON(__BITS_VALUE(reg1->idx, 1, 8) != 0xff);
+		idx[0] -= EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+		idx[0] = (idx[0] + 1) % 4;
+		idx[0] += EXTRA_REG_NHMEX_M_ZDP_CTL_FVC;
+		if (idx[0] != __BITS_VALUE(reg1->idx, 0, 8)) {
+			config1 = nhmex_mbox_alter_er(event, idx[0], false);
+			goto again;
+		}
+	}
+
+	if (alloc & 0x1)
+		nhmex_mbox_put_shared_reg(box, idx[0]);
+	if (alloc & 0x2)
+		nhmex_mbox_put_shared_reg(box, idx[1]);
+	return &constraint_empty;
+}
+
+static void nhmex_mbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+
+	if (uncore_box_is_fake(box))
+		return;
+
+	if (reg1->alloc & 0x1)
+		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 0, 8));
+	if (reg1->alloc & 0x2)
+		nhmex_mbox_put_shared_reg(box, __BITS_VALUE(reg1->idx, 1, 8));
+	reg1->alloc = 0;
+
+	if (reg2->alloc) {
+		nhmex_mbox_put_shared_reg(box, reg2->idx);
+		reg2->alloc = 0;
+	}
+}
+
+static int nhmex_mbox_extra_reg_idx(struct extra_reg *er)
+{
+	if (er->idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+		return er->idx;
+	return er->idx + (er->event >> NHMEX_M_PMON_CTL_INC_SEL_SHIFT) - 0xd;
+}
+
+static int nhmex_mbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct intel_uncore_type *type = box->pmu->type;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	struct extra_reg *er;
+	unsigned msr;
+	int reg_idx = 0;
+
+	if (WARN_ON_ONCE(reg1->idx != -1))
+		return -EINVAL;
+	/*
+	 * The mbox events may require 2 extra MSRs at the most. But only
+	 * the lower 32 bits in these MSRs are significant, so we can use
+	 * config1 to pass two MSRs' config.
+	 */
+	for (er = nhmex_uncore_mbox_extra_regs; er->msr; er++) {
+		if (er->event != (event->hw.config & er->config_mask))
+			continue;
+		if (event->attr.config1 & ~er->valid_mask)
+			return -EINVAL;
+		if (er->idx == __BITS_VALUE(reg1->idx, 0, 8) ||
+		    er->idx == __BITS_VALUE(reg1->idx, 1, 8))
+			continue;
+		if (WARN_ON_ONCE(reg_idx >= 2))
+			return -EINVAL;
+
+		msr = er->msr + type->msr_offset * box->pmu->pmu_idx;
+		if (WARN_ON_ONCE(msr >= 0xffff || er->idx >= 0xff))
+			return -EINVAL;
+
+		/* always use the 32~63 bits to pass the PLD config */
+		if (er->idx == EXTRA_REG_NHMEX_M_PLD)
+			reg_idx = 1;
+
+		reg1->idx &= ~(0xff << (reg_idx * 8));
+		reg1->reg &= ~(0xffff << (reg_idx * 16));
+		reg1->idx |= nhmex_mbox_extra_reg_idx(er) << (reg_idx * 8);
+		reg1->reg |= msr << (reg_idx * 16);
+		reg1->config = event->attr.config1;
+		reg_idx++;
+	}
+	/* use config2 to pass the filter config */
+	reg2->idx = EXTRA_REG_NHMEX_M_FILTER;
+	if (event->attr.config2 & NHMEX_M_PMON_MM_CFG_EN)
+		reg2->config = event->attr.config2;
+	else
+		reg2->config = ~0ULL;
+	if (box->pmu->pmu_idx == 0)
+		reg2->reg = NHMEX_M0_MSR_PMU_MM_CFG;
+	else
+		reg2->reg = NHMEX_M1_MSR_PMU_MM_CFG;
+
+	return 0;
+}
+
+static u64 nhmex_mbox_shared_reg_config(struct intel_uncore_box *box, int idx)
+{
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	u64 config;
+
+	if (idx < EXTRA_REG_NHMEX_M_ZDP_CTL_FVC)
+		return box->shared_regs[idx].config;
+
+	er = &box->shared_regs[EXTRA_REG_NHMEX_M_ZDP_CTL_FVC];
+	raw_spin_lock_irqsave(&er->lock, flags);
+	config = er->config;
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+	return config;
+}
+
+static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int idx;
+
+	idx = __BITS_VALUE(reg1->idx, 0, 8);
+	if (idx != 0xff)
+		wrmsrl(__BITS_VALUE(reg1->reg, 0, 16),
+			nhmex_mbox_shared_reg_config(box, idx));
+	idx = __BITS_VALUE(reg1->idx, 1, 8);
+	if (idx != 0xff)
+		wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
+			nhmex_mbox_shared_reg_config(box, idx));
+
+	wrmsrl(reg2->reg, 0);
+	if (reg2->config != ~0ULL) {
+		wrmsrl(reg2->reg + 1,
+			reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
+		wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
+			(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
+		wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+	}
+
+	wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(count_mode,	count_mode,	"config:2-3");
+DEFINE_UNCORE_FORMAT_ATTR(storage_mode, storage_mode,	"config:4-5");
+DEFINE_UNCORE_FORMAT_ATTR(wrap_mode,	wrap_mode,	"config:6");
+DEFINE_UNCORE_FORMAT_ATTR(flag_mode,	flag_mode,	"config:7");
+DEFINE_UNCORE_FORMAT_ATTR(inc_sel,	inc_sel,	"config:9-13");
+DEFINE_UNCORE_FORMAT_ATTR(set_flag_sel,	set_flag_sel,	"config:19-21");
+DEFINE_UNCORE_FORMAT_ATTR(filter_cfg,	filter_cfg,	"config2:63");
+DEFINE_UNCORE_FORMAT_ATTR(filter_match,	filter_match,	"config2:0-33");
+DEFINE_UNCORE_FORMAT_ATTR(filter_mask,	filter_mask,	"config2:34-61");
+DEFINE_UNCORE_FORMAT_ATTR(dsp,		dsp,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(thr,		thr,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(fvc,		fvc,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pgt,		pgt,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(map,		map,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(iss,		iss,		"config1:0-31");
+DEFINE_UNCORE_FORMAT_ATTR(pld,		pld,		"config1:32-63");
+
+static struct attribute *nhmex_uncore_mbox_formats_attr[] = {
+	&format_attr_count_mode.attr,
+	&format_attr_storage_mode.attr,
+	&format_attr_wrap_mode.attr,
+	&format_attr_flag_mode.attr,
+	&format_attr_inc_sel.attr,
+	&format_attr_set_flag_sel.attr,
+	&format_attr_filter_cfg.attr,
+	&format_attr_filter_match.attr,
+	&format_attr_filter_mask.attr,
+	&format_attr_dsp.attr,
+	&format_attr_thr.attr,
+	&format_attr_fvc.attr,
+	&format_attr_pgt.attr,
+	&format_attr_map.attr,
+	&format_attr_iss.attr,
+	&format_attr_pld.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_mbox_format_group = {
+	.name		= "format",
+	.attrs		= nhmex_uncore_mbox_formats_attr,
+};
+
+static struct uncore_event_desc nhmex_uncore_mbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_read, "inc_sel=0xd,fvc=0x2800"),
+	INTEL_UNCORE_EVENT_DESC(bbox_cmds_write, "inc_sel=0xd,fvc=0x2820"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhmex_uncore_mbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event	= nhmex_mbox_msr_enable_event,
+	.hw_config	= nhmex_mbox_hw_config,
+	.get_constraint	= nhmex_mbox_get_constraint,
+	.put_constraint	= nhmex_mbox_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_mbox = {
+	.name			= "mbox",
+	.num_counters		= 6,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_M0_MSR_PMU_CTL0,
+	.perf_ctr		= NHMEX_M0_MSR_PMU_CNT0,
+	.event_mask		= NHMEX_M_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_M0_MSR_GLOBAL_CTL,
+	.msr_offset		= NHMEX_M_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 8,
+	.event_descs		= nhmex_uncore_mbox_events,
+	.ops			= &nhmex_uncore_mbox_ops,
+	.format_group		= &nhmex_uncore_mbox_format_group,
+};
+
+void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	int port;
+
+	/* adjust the main event selector */
+	if (reg1->idx % 2) {
+		reg1->idx--;
+		hwc->config -= 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	} else {
+		reg1->idx++;
+		hwc->config += 1 << NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	}
+
+	/* adjust address or config of extra register */
+	port = reg1->idx / 6 + box->pmu->pmu_idx * 4;
+	switch (reg1->idx % 6) {
+	case 0:
+		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port);
+		break;
+	case 1:
+		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port);
+		break;
+	case 2:
+		/* the 8~15 bits to the 0~7 bits */
+		reg1->config >>= 8;
+		break;
+	case 3:
+		/* the 0~7 bits to the 8~15 bits */
+		reg1->config <<= 8;
+		break;
+	case 4:
+		reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port);
+		break;
+	case 5:
+		reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port);
+		break;
+	};
+}
+
+/*
+ * Each rbox has 4 event set which monitor PQI port 0~3 or 4~7.
+ * An event set consists of 6 events, the 3rd and 4th events in
+ * an event set use the same extra register. So an event set uses
+ * 5 extra registers.
+ */
+static struct event_constraint *
+nhmex_rbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	int idx, er_idx;
+	u64 config1;
+	bool ok = false;
+
+	if (!uncore_box_is_fake(box) && reg1->alloc)
+		return NULL;
+
+	idx = reg1->idx % 6;
+	config1 = reg1->config;
+again:
+	er_idx = idx;
+	/* the 3rd and 4th events use the same extra register */
+	if (er_idx > 2)
+		er_idx--;
+	er_idx += (reg1->idx / 6) * 5;
+
+	er = &box->shared_regs[er_idx];
+	raw_spin_lock_irqsave(&er->lock, flags);
+	if (idx < 2) {
+		if (!atomic_read(&er->ref) || er->config == reg1->config) {
+			atomic_inc(&er->ref);
+			er->config = reg1->config;
+			ok = true;
+		}
+	} else if (idx == 2 || idx == 3) {
+		/*
+		 * these two events use different fields in a extra register,
+		 * the 0~7 bits and the 8~15 bits respectively.
+		 */
+		u64 mask = 0xff << ((idx - 2) * 8);
+		if (!__BITS_VALUE(atomic_read(&er->ref), idx - 2, 8) ||
+				!((er->config ^ config1) & mask)) {
+			atomic_add(1 << ((idx - 2) * 8), &er->ref);
+			er->config &= ~mask;
+			er->config |= config1 & mask;
+			ok = true;
+		}
+	} else {
+		if (!atomic_read(&er->ref) ||
+				(er->config == (hwc->config >> 32) &&
+				 er->config1 == reg1->config &&
+				 er->config2 == reg2->config)) {
+			atomic_inc(&er->ref);
+			er->config = (hwc->config >> 32);
+			er->config1 = reg1->config;
+			er->config2 = reg2->config;
+			ok = true;
+		}
+	}
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	if (!ok) {
+		/*
+		 * The Rbox events are always in pairs. The paired
+		 * events are functional identical, but use different
+		 * extra registers. If we failed to take an extra
+		 * register, try the alternative.
+		 */
+		if (idx % 2)
+			idx--;
+		else
+			idx++;
+		if (idx != reg1->idx % 6) {
+			if (idx == 2)
+				config1 >>= 8;
+			else if (idx == 3)
+				config1 <<= 8;
+			goto again;
+		}
+	} else {
+		if (!uncore_box_is_fake(box)) {
+			if (idx != reg1->idx % 6)
+				nhmex_rbox_alter_er(box, event);
+			reg1->alloc = 1;
+		}
+		return NULL;
+	}
+	return &constraint_empty;
+}
+
+static void nhmex_rbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct intel_uncore_extra_reg *er;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	int idx, er_idx;
+
+	if (uncore_box_is_fake(box) || !reg1->alloc)
+		return;
+
+	idx = reg1->idx % 6;
+	er_idx = idx;
+	if (er_idx > 2)
+		er_idx--;
+	er_idx += (reg1->idx / 6) * 5;
+
+	er = &box->shared_regs[er_idx];
+	if (idx == 2 || idx == 3)
+		atomic_sub(1 << ((idx - 2) * 8), &er->ref);
+	else
+		atomic_dec(&er->ref);
+
+	reg1->alloc = 0;
+}
+
+static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
+	struct hw_perf_event_extra *reg2 = &event->hw.branch_reg;
+	int port, idx;
+
+	idx = (event->hw.config & NHMEX_R_PMON_CTL_EV_SEL_MASK) >>
+		NHMEX_R_PMON_CTL_EV_SEL_SHIFT;
+	if (idx >= 0x18)
+		return -EINVAL;
+
+	reg1->idx = idx;
+	reg1->config = event->attr.config1;
+
+	port = idx / 6 + box->pmu->pmu_idx * 4;
+	idx %= 6;
+	switch (idx) {
+	case 0:
+		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG0(port);
+		break;
+	case 1:
+		reg1->reg = NHMEX_R_MSR_PORTN_IPERF_CFG1(port);
+		break;
+	case 2:
+	case 3:
+		reg1->reg = NHMEX_R_MSR_PORTN_QLX_CFG(port);
+		break;
+	case 4:
+	case 5:
+		if (idx == 4)
+			reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port);
+		else
+			reg1->reg = NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port);
+		reg2->config = event->attr.config2;
+		hwc->config |= event->attr.config & (~0ULL << 32);
+		break;
+	};
+	return 0;
+}
+
+static u64 nhmex_rbox_shared_reg_config(struct intel_uncore_box *box, int idx)
+{
+	struct intel_uncore_extra_reg *er;
+	unsigned long flags;
+	u64 config;
+
+	er = &box->shared_regs[idx];
+
+	raw_spin_lock_irqsave(&er->lock, flags);
+	config = er->config;
+	raw_spin_unlock_irqrestore(&er->lock, flags);
+
+	return config;
+}
+
+static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
+	struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
+	int idx, er_idx;
+
+	idx = reg1->idx % 6;
+	er_idx = idx;
+	if (er_idx > 2)
+		er_idx--;
+	er_idx += (reg1->idx / 6) * 5;
+
+	switch (idx) {
+	case 0:
+	case 1:
+		wrmsrl(reg1->reg, reg1->config);
+		break;
+	case 2:
+	case 3:
+		wrmsrl(reg1->reg, nhmex_rbox_shared_reg_config(box, er_idx));
+		break;
+	case 4:
+	case 5:
+		wrmsrl(reg1->reg, reg1->config);
+		wrmsrl(reg1->reg + 1, hwc->config >> 32);
+		wrmsrl(reg1->reg + 2, reg2->config);
+		break;
+	};
+
+	wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+		(hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
+}
+
+DEFINE_UNCORE_FORMAT_ATTR(xbr_match, xbr_match, "config:32-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mm_cfg, xbr_mm_cfg, "config1:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(xbr_mask, xbr_mask, "config2:0-63");
+DEFINE_UNCORE_FORMAT_ATTR(qlx_cfg, qlx_cfg, "config1:0-15");
+DEFINE_UNCORE_FORMAT_ATTR(iperf_cfg, iperf_cfg, "config1:0-31");
+
+static struct attribute *nhmex_uncore_rbox_formats_attr[] = {
+	&format_attr_event5.attr,
+	&format_attr_xbr_mm_cfg.attr,
+	&format_attr_xbr_match.attr,
+	&format_attr_xbr_mask.attr,
+	&format_attr_qlx_cfg.attr,
+	&format_attr_iperf_cfg.attr,
+	NULL,
+};
+
+static struct attribute_group nhmex_uncore_rbox_format_group = {
+	.name = "format",
+	.attrs = nhmex_uncore_rbox_formats_attr,
+};
+
+static struct uncore_event_desc nhmex_uncore_rbox_events[] = {
+	INTEL_UNCORE_EVENT_DESC(qpi0_flit_send,		"event=0x0,iperf_cfg=0x80000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_filt_send,		"event=0x6,iperf_cfg=0x80000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi0_idle_filt,		"event=0x0,iperf_cfg=0x40000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_idle_filt,		"event=0x6,iperf_cfg=0x40000000"),
+	INTEL_UNCORE_EVENT_DESC(qpi0_date_response,	"event=0x0,iperf_cfg=0xc4"),
+	INTEL_UNCORE_EVENT_DESC(qpi1_date_response,	"event=0x6,iperf_cfg=0xc4"),
+	{ /* end: all zeroes */ },
+};
+
+static struct intel_uncore_ops nhmex_uncore_rbox_ops = {
+	NHMEX_UNCORE_OPS_COMMON_INIT(),
+	.enable_event		= nhmex_rbox_msr_enable_event,
+	.hw_config		= nhmex_rbox_hw_config,
+	.get_constraint		= nhmex_rbox_get_constraint,
+	.put_constraint		= nhmex_rbox_put_constraint,
+};
+
+static struct intel_uncore_type nhmex_uncore_rbox = {
+	.name			= "rbox",
+	.num_counters		= 8,
+	.num_boxes		= 2,
+	.perf_ctr_bits		= 48,
+	.event_ctl		= NHMEX_R_MSR_PMON_CTL0,
+	.perf_ctr		= NHMEX_R_MSR_PMON_CNT0,
+	.event_mask		= NHMEX_R_PMON_RAW_EVENT_MASK,
+	.box_ctl		= NHMEX_R_MSR_GLOBAL_CTL,
+	.msr_offset		= NHMEX_R_MSR_OFFSET,
+	.pair_ctr_ctl		= 1,
+	.num_shared_regs	= 20,
+	.event_descs		= nhmex_uncore_rbox_events,
+	.ops			= &nhmex_uncore_rbox_ops,
+	.format_group		= &nhmex_uncore_rbox_format_group
+};
+
+static struct intel_uncore_type *nhmex_msr_uncores[] = {
+	&nhmex_uncore_ubox,
+	&nhmex_uncore_cbox,
+	&nhmex_uncore_bbox,
+	&nhmex_uncore_sbox,
+	&nhmex_uncore_mbox,
+	&nhmex_uncore_rbox,
+	&nhmex_uncore_wbox,
+	NULL,
+};
+/* end of Nehalem-EX uncore support */
+
+static void uncore_assign_hw_event(struct intel_uncore_box *box, struct perf_event *event, int idx)
 {
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -787,8 +1841,7 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box,
 	hwc->event_base  = uncore_perf_ctr(box, hwc->idx);
 }
 
-static void uncore_perf_event_update(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void uncore_perf_event_update(struct intel_uncore_box *box, struct perf_event *event)
 {
 	u64 prev_count, new_count, delta;
 	int shift;
@@ -858,14 +1911,12 @@ static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
 	box->hrtimer.function = uncore_pmu_hrtimer;
 }
 
-struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
-					  int cpu)
+struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type, int cpu)
 {
 	struct intel_uncore_box *box;
 	int i, size;
 
-	size = sizeof(*box) + type->num_shared_regs *
-		sizeof(struct intel_uncore_extra_reg);
+	size = sizeof(*box) + type->num_shared_regs * sizeof(struct intel_uncore_extra_reg);
 
 	box = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO, cpu_to_node(cpu));
 	if (!box)
@@ -915,12 +1966,11 @@ static struct intel_uncore_box *uncore_event_to_box(struct perf_event *event)
 	 * perf core schedules event on the basis of cpu, uncore events are
 	 * collected by one of the cpus inside a physical package.
 	 */
-	return uncore_pmu_to_box(uncore_event_to_pmu(event),
-				 smp_processor_id());
+	return uncore_pmu_to_box(uncore_event_to_pmu(event), smp_processor_id());
 }
 
-static int uncore_collect_events(struct intel_uncore_box *box,
-				struct perf_event *leader, bool dogrp)
+static int
+uncore_collect_events(struct intel_uncore_box *box, struct perf_event *leader, bool dogrp)
 {
 	struct perf_event *event;
 	int n, max_count;
@@ -952,8 +2002,7 @@ static int uncore_collect_events(struct intel_uncore_box *box,
 }
 
 static struct event_constraint *
-uncore_get_event_constraint(struct intel_uncore_box *box,
-			    struct perf_event *event)
+uncore_get_event_constraint(struct intel_uncore_box *box, struct perf_event *event)
 {
 	struct intel_uncore_type *type = box->pmu->type;
 	struct event_constraint *c;
@@ -977,15 +2026,13 @@ uncore_get_event_constraint(struct intel_uncore_box *box,
 	return &type->unconstrainted;
 }
 
-static void uncore_put_event_constraint(struct intel_uncore_box *box,
-					struct perf_event *event)
+static void uncore_put_event_constraint(struct intel_uncore_box *box, struct perf_event *event)
 {
 	if (box->pmu->type->ops->put_constraint)
 		box->pmu->type->ops->put_constraint(box, event);
 }
 
-static int uncore_assign_events(struct intel_uncore_box *box,
-				int assign[], int n)
+static int uncore_assign_events(struct intel_uncore_box *box, int assign[], int n)
 {
 	unsigned long used_mask[BITS_TO_LONGS(UNCORE_PMC_IDX_MAX)];
 	struct event_constraint *c, *constraints[UNCORE_PMC_IDX_MAX];
@@ -1407,8 +2454,7 @@ static bool pcidrv_registered;
 /*
  * add a pci uncore device
  */
-static int __devinit uncore_pci_add(struct intel_uncore_type *type,
-				    struct pci_dev *pdev)
+static int __devinit uncore_pci_add(struct intel_uncore_type *type, struct pci_dev *pdev)
 {
 	struct intel_uncore_pmu *pmu;
 	struct intel_uncore_box *box;
@@ -1485,6 +2531,7 @@ static int __devinit uncore_pci_probe(struct pci_dev *pdev,
 	struct intel_uncore_type *type;
 
 	type = (struct intel_uncore_type *)id->driver_data;
+
 	return uncore_pci_add(type, pdev);
 }
 
@@ -1612,8 +2659,8 @@ static int __cpuinit uncore_cpu_prepare(int cpu, int phys_id)
 	return 0;
 }
 
-static void __cpuinit uncore_change_context(struct intel_uncore_type **uncores,
-					    int old_cpu, int new_cpu)
+static void __cpuinit
+uncore_change_context(struct intel_uncore_type **uncores, int old_cpu, int new_cpu)
 {
 	struct intel_uncore_type *type;
 	struct intel_uncore_pmu *pmu;
@@ -1694,8 +2741,8 @@ static void __cpuinit uncore_event_init_cpu(int cpu)
 	uncore_change_context(pci_uncores, -1, cpu);
 }
 
-static int __cpuinit uncore_cpu_notifier(struct notifier_block *self,
-					 unsigned long action, void *hcpu)
+static int
+ __cpuinit uncore_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
 
@@ -1732,12 +2779,12 @@ static int __cpuinit uncore_cpu_notifier(struct notifier_block *self,
 }
 
 static struct notifier_block uncore_cpu_nb __cpuinitdata = {
-	.notifier_call = uncore_cpu_notifier,
+	.notifier_call	= uncore_cpu_notifier,
 	/*
 	 * to migrate uncore events, our notifier should be executed
 	 * before perf core's notifier.
 	 */
-	.priority = CPU_PRI_PERF + 1,
+	.priority	= CPU_PRI_PERF + 1,
 };
 
 static void __init uncore_cpu_setup(void *dummy)
@@ -1767,6 +2814,9 @@ static int __init uncore_cpu_init(void)
 			snbep_uncore_cbox.num_boxes = max_cores;
 		msr_uncores = snbep_msr_uncores;
 		break;
+	case 46:
+		msr_uncores = nhmex_msr_uncores;
+		break;
 	default:
 		return 0;
 	}
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
index b13e9ea81def..f3851892e077 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h
@@ -5,8 +5,6 @@
 #include "perf_event.h"
 
 #define UNCORE_PMU_NAME_LEN		32
-#define UNCORE_BOX_HASH_SIZE		8
-
 #define UNCORE_PMU_HRTIMER_INTERVAL	(60 * NSEC_PER_SEC)
 
 #define UNCORE_FIXED_EVENT		0xff
@@ -115,6 +113,10 @@
 				 SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \
 				 SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET)
 
+#define SNBEP_QPI_PCI_PMON_RAW_EVENT_MASK	\
+				(SNBEP_PMON_RAW_EVENT_MASK | \
+				 SNBEP_PMON_CTL_EV_SEL_EXT)
+
 /* SNB-EP pci control register */
 #define SNBEP_PCI_PMON_BOX_CTL			0xf4
 #define SNBEP_PCI_PMON_CTL0			0xd8
@@ -158,6 +160,193 @@
 #define SNBEP_PCU_MSR_CORE_C3_CTR		0x3fc
 #define SNBEP_PCU_MSR_CORE_C6_CTR		0x3fd
 
+/* NHM-EX event control */
+#define NHMEX_PMON_CTL_EV_SEL_MASK	0x000000ff
+#define NHMEX_PMON_CTL_UMASK_MASK	0x0000ff00
+#define NHMEX_PMON_CTL_EN_BIT0		(1 << 0)
+#define NHMEX_PMON_CTL_EDGE_DET		(1 << 18)
+#define NHMEX_PMON_CTL_PMI_EN		(1 << 20)
+#define NHMEX_PMON_CTL_EN_BIT22		(1 << 22)
+#define NHMEX_PMON_CTL_INVERT		(1 << 23)
+#define NHMEX_PMON_CTL_TRESH_MASK	0xff000000
+#define NHMEX_PMON_RAW_EVENT_MASK	(NHMEX_PMON_CTL_EV_SEL_MASK | \
+					 NHMEX_PMON_CTL_UMASK_MASK | \
+					 NHMEX_PMON_CTL_EDGE_DET | \
+					 NHMEX_PMON_CTL_INVERT | \
+					 NHMEX_PMON_CTL_TRESH_MASK)
+
+/* NHM-EX Ubox */
+#define NHMEX_U_MSR_PMON_GLOBAL_CTL		0xc00
+#define NHMEX_U_MSR_PMON_CTR			0xc11
+#define NHMEX_U_MSR_PMON_EV_SEL			0xc10
+
+#define NHMEX_U_PMON_GLOBAL_EN			(1 << 0)
+#define NHMEX_U_PMON_GLOBAL_PMI_CORE_SEL	0x0000001e
+#define NHMEX_U_PMON_GLOBAL_EN_ALL		(1 << 28)
+#define NHMEX_U_PMON_GLOBAL_RST_ALL		(1 << 29)
+#define NHMEX_U_PMON_GLOBAL_FRZ_ALL		(1 << 31)
+
+#define NHMEX_U_PMON_RAW_EVENT_MASK		\
+		(NHMEX_PMON_CTL_EV_SEL_MASK |	\
+		 NHMEX_PMON_CTL_EDGE_DET)
+
+/* NHM-EX Cbox */
+#define NHMEX_C0_MSR_PMON_GLOBAL_CTL		0xd00
+#define NHMEX_C0_MSR_PMON_CTR0			0xd11
+#define NHMEX_C0_MSR_PMON_EV_SEL0		0xd10
+#define NHMEX_C_MSR_OFFSET			0x20
+
+/* NHM-EX Bbox */
+#define NHMEX_B0_MSR_PMON_GLOBAL_CTL		0xc20
+#define NHMEX_B0_MSR_PMON_CTR0			0xc31
+#define NHMEX_B0_MSR_PMON_CTL0			0xc30
+#define NHMEX_B_MSR_OFFSET			0x40
+#define NHMEX_B0_MSR_MATCH			0xe45
+#define NHMEX_B0_MSR_MASK			0xe46
+#define NHMEX_B1_MSR_MATCH			0xe4d
+#define NHMEX_B1_MSR_MASK			0xe4e
+
+#define NHMEX_B_PMON_CTL_EN			(1 << 0)
+#define NHMEX_B_PMON_CTL_EV_SEL_SHIFT		1
+#define NHMEX_B_PMON_CTL_EV_SEL_MASK		\
+		(0x1f << NHMEX_B_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_B_PMON_CTR_SHIFT		6
+#define NHMEX_B_PMON_CTR_MASK		\
+		(0x3 << NHMEX_B_PMON_CTR_SHIFT)
+#define NHMEX_B_PMON_RAW_EVENT_MASK		\
+		(NHMEX_B_PMON_CTL_EV_SEL_MASK | \
+		 NHMEX_B_PMON_CTR_MASK)
+
+/* NHM-EX Sbox */
+#define NHMEX_S0_MSR_PMON_GLOBAL_CTL		0xc40
+#define NHMEX_S0_MSR_PMON_CTR0			0xc51
+#define NHMEX_S0_MSR_PMON_CTL0			0xc50
+#define NHMEX_S_MSR_OFFSET			0x80
+#define NHMEX_S0_MSR_MM_CFG			0xe48
+#define NHMEX_S0_MSR_MATCH			0xe49
+#define NHMEX_S0_MSR_MASK			0xe4a
+#define NHMEX_S1_MSR_MM_CFG			0xe58
+#define NHMEX_S1_MSR_MATCH			0xe59
+#define NHMEX_S1_MSR_MASK			0xe5a
+
+#define NHMEX_S_PMON_MM_CFG_EN			(0x1ULL << 63)
+
+/* NHM-EX Mbox */
+#define NHMEX_M0_MSR_GLOBAL_CTL			0xca0
+#define NHMEX_M0_MSR_PMU_DSP			0xca5
+#define NHMEX_M0_MSR_PMU_ISS			0xca6
+#define NHMEX_M0_MSR_PMU_MAP			0xca7
+#define NHMEX_M0_MSR_PMU_MSC_THR		0xca8
+#define NHMEX_M0_MSR_PMU_PGT			0xca9
+#define NHMEX_M0_MSR_PMU_PLD			0xcaa
+#define NHMEX_M0_MSR_PMU_ZDP_CTL_FVC		0xcab
+#define NHMEX_M0_MSR_PMU_CTL0			0xcb0
+#define NHMEX_M0_MSR_PMU_CNT0			0xcb1
+#define NHMEX_M_MSR_OFFSET			0x40
+#define NHMEX_M0_MSR_PMU_MM_CFG			0xe54
+#define NHMEX_M1_MSR_PMU_MM_CFG			0xe5c
+
+#define NHMEX_M_PMON_MM_CFG_EN			(1ULL << 63)
+#define NHMEX_M_PMON_ADDR_MATCH_MASK		0x3ffffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_MASK		0x7ffffffULL
+#define NHMEX_M_PMON_ADDR_MASK_SHIFT		34
+
+#define NHMEX_M_PMON_CTL_EN			(1 << 0)
+#define NHMEX_M_PMON_CTL_PMI_EN			(1 << 1)
+#define NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT	2
+#define NHMEX_M_PMON_CTL_COUNT_MODE_MASK	\
+	(0x3 << NHMEX_M_PMON_CTL_COUNT_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT	4
+#define NHMEX_M_PMON_CTL_STORAGE_MODE_MASK	\
+	(0x3 << NHMEX_M_PMON_CTL_STORAGE_MODE_SHIFT)
+#define NHMEX_M_PMON_CTL_WRAP_MODE		(1 << 6)
+#define NHMEX_M_PMON_CTL_FLAG_MODE		(1 << 7)
+#define NHMEX_M_PMON_CTL_INC_SEL_SHIFT		9
+#define NHMEX_M_PMON_CTL_INC_SEL_MASK		\
+	(0x1f << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT	19
+#define NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK	\
+	(0x7 << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT)
+#define NHMEX_M_PMON_RAW_EVENT_MASK			\
+		(NHMEX_M_PMON_CTL_COUNT_MODE_MASK |	\
+		 NHMEX_M_PMON_CTL_STORAGE_MODE_MASK |	\
+		 NHMEX_M_PMON_CTL_WRAP_MODE |		\
+		 NHMEX_M_PMON_CTL_FLAG_MODE |		\
+		 NHMEX_M_PMON_CTL_INC_SEL_MASK |	\
+		 NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK)
+
+
+#define NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK	0x1f
+#define NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK	(0x7 << 5)
+#define NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK	(0x7 << 8)
+#define NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR	(1 << 23)
+#define NHMEX_M_PMON_ZDP_CTL_FVC_MASK			\
+		(NHMEX_M_PMON_ZDP_CTL_FVC_FVID_MASK |	\
+		 NHMEX_M_PMON_ZDP_CTL_FVC_BCMD_MASK |	\
+		 NHMEX_M_PMON_ZDP_CTL_FVC_RSP_MASK  |	\
+		 NHMEX_M_PMON_ZDP_CTL_FVC_PBOX_INIT_ERR)
+#define NHMEX_M_PMON_ZDP_CTL_FVC_EVENT_MASK(n)	(0x7 << (11 + 3 * (n)))
+
+/*
+ * use the 9~13 bits to select event If the 7th bit is not set,
+ * otherwise use the 19~21 bits to select event.
+ */
+#define MBOX_INC_SEL(x) ((x) << NHMEX_M_PMON_CTL_INC_SEL_SHIFT)
+#define MBOX_SET_FLAG_SEL(x) (((x) << NHMEX_M_PMON_CTL_SET_FLAG_SEL_SHIFT) | \
+				NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_MASK (NHMEX_M_PMON_CTL_INC_SEL_MASK | \
+			   NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_SET_FLAG_SEL_MASK (NHMEX_M_PMON_CTL_SET_FLAG_SEL_MASK | \
+				NHMEX_M_PMON_CTL_FLAG_MODE)
+#define MBOX_INC_SEL_EXTAR_REG(c, r) \
+		EVENT_EXTRA_REG(MBOX_INC_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+				MBOX_INC_SEL_MASK, (u64)-1, NHMEX_M_##r)
+#define MBOX_SET_FLAG_SEL_EXTRA_REG(c, r) \
+		EVENT_EXTRA_REG(MBOX_SET_FLAG_SEL(c), NHMEX_M0_MSR_PMU_##r, \
+				MBOX_SET_FLAG_SEL_MASK, \
+				(u64)-1, NHMEX_M_##r)
+
+/* NHM-EX Rbox */
+#define NHMEX_R_MSR_GLOBAL_CTL			0xe00
+#define NHMEX_R_MSR_PMON_CTL0			0xe10
+#define NHMEX_R_MSR_PMON_CNT0			0xe11
+#define NHMEX_R_MSR_OFFSET			0x20
+
+#define NHMEX_R_MSR_PORTN_QLX_CFG(n)		\
+		((n) < 4 ? (0xe0c + (n)) : (0xe2c + (n) - 4))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG0(n)		(0xe04 + (n))
+#define NHMEX_R_MSR_PORTN_IPERF_CFG1(n)		(0xe24 + (n))
+#define NHMEX_R_MSR_PORTN_XBR_OFFSET(n)		\
+		(((n) < 4 ? 0 : 0x10) + (n) * 4)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n)	\
+		(0xe60 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET1_MASK(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(n) + 2)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n)	\
+		(0xe70 + NHMEX_R_MSR_PORTN_XBR_OFFSET(n))
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 1)
+#define NHMEX_R_MSR_PORTN_XBR_SET2_MASK(n)	\
+		(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(n) + 2)
+
+#define NHMEX_R_PMON_CTL_EN			(1 << 0)
+#define NHMEX_R_PMON_CTL_EV_SEL_SHIFT		1
+#define NHMEX_R_PMON_CTL_EV_SEL_MASK		\
+		(0x1f << NHMEX_R_PMON_CTL_EV_SEL_SHIFT)
+#define NHMEX_R_PMON_CTL_PMI_EN			(1 << 6)
+#define NHMEX_R_PMON_RAW_EVENT_MASK		NHMEX_R_PMON_CTL_EV_SEL_MASK
+
+/* NHM-EX Wbox */
+#define NHMEX_W_MSR_GLOBAL_CTL			0xc80
+#define NHMEX_W_MSR_PMON_CNT0			0xc90
+#define NHMEX_W_MSR_PMON_EVT_SEL0		0xc91
+#define NHMEX_W_MSR_PMON_FIXED_CTR		0x394
+#define NHMEX_W_MSR_PMON_FIXED_CTL		0x395
+
+#define NHMEX_W_PMON_GLOBAL_FIXED_EN		(1ULL << 31)
+
 struct intel_uncore_ops;
 struct intel_uncore_pmu;
 struct intel_uncore_box;
@@ -178,6 +367,7 @@ struct intel_uncore_type {
 	unsigned msr_offset;
 	unsigned num_shared_regs:8;
 	unsigned single_fixed:1;
+	unsigned pair_ctr_ctl:1;
 	struct event_constraint unconstrainted;
 	struct event_constraint *constraints;
 	struct intel_uncore_pmu *pmus;
@@ -213,7 +403,7 @@ struct intel_uncore_pmu {
 
 struct intel_uncore_extra_reg {
 	raw_spinlock_t lock;
-	u64 config1;
+	u64 config, config1, config2;
 	atomic_t ref;
 };
 
@@ -323,14 +513,16 @@ unsigned uncore_msr_fixed_ctr(struct intel_uncore_box *box)
 static inline
 unsigned uncore_msr_event_ctl(struct intel_uncore_box *box, int idx)
 {
-	return idx + box->pmu->type->event_ctl +
+	return box->pmu->type->event_ctl +
+		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
 		box->pmu->type->msr_offset * box->pmu->pmu_idx;
 }
 
 static inline
 unsigned uncore_msr_perf_ctr(struct intel_uncore_box *box, int idx)
 {
-	return idx + box->pmu->type->perf_ctr +
+	return box->pmu->type->perf_ctr +
+		(box->pmu->type->pair_ctr_ctl ? 2 * idx : idx) +
 		box->pmu->type->msr_offset * box->pmu->pmu_idx;
 }
 
@@ -422,3 +614,8 @@ static inline void uncore_box_init(struct intel_uncore_box *box)
 			box->pmu->type->ops->init_box(box);
 	}
 }
+
+static inline bool uncore_box_is_fake(struct intel_uncore_box *box)
+{
+	return (box->phys_id < 0);
+}
diff --git a/arch/x86/kernel/cpu/sched.c b/arch/x86/kernel/cpu/sched.c
deleted file mode 100644
index a640ae5ad201..000000000000
--- a/arch/x86/kernel/cpu/sched.c
+++ /dev/null
@@ -1,55 +0,0 @@
-#include <linux/sched.h>
-#include <linux/math64.h>
-#include <linux/percpu.h>
-#include <linux/irqflags.h>
-
-#include <asm/cpufeature.h>
-#include <asm/processor.h>
-
-#ifdef CONFIG_SMP
-
-static DEFINE_PER_CPU(struct aperfmperf, old_perf_sched);
-
-static unsigned long scale_aperfmperf(void)
-{
-	struct aperfmperf val, *old = &__get_cpu_var(old_perf_sched);
-	unsigned long ratio, flags;
-
-	local_irq_save(flags);
-	get_aperfmperf(&val);
-	local_irq_restore(flags);
-
-	ratio = calc_aperfmperf_ratio(old, &val);
-	*old = val;
-
-	return ratio;
-}
-
-unsigned long arch_scale_freq_power(struct sched_domain *sd, int cpu)
-{
-	/*
-	 * do aperf/mperf on the cpu level because it includes things
-	 * like turbo mode, which are relevant to full cores.
-	 */
-	if (boot_cpu_has(X86_FEATURE_APERFMPERF))
-		return scale_aperfmperf();
-
-	/*
-	 * maybe have something cpufreq here
-	 */
-
-	return default_scale_freq_power(sd, cpu);
-}
-
-unsigned long arch_scale_smt_power(struct sched_domain *sd, int cpu)
-{
-	/*
-	 * aperf/mperf already includes the smt gain
-	 */
-	if (boot_cpu_has(X86_FEATURE_APERFMPERF))
-		return SCHED_LOAD_SCALE;
-
-	return default_scale_smt_power(sd, cpu);
-}
-
-#endif
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 41857970517f..ed858e9e9a74 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -944,7 +944,7 @@ void __init e820_reserve_resources(void)
 	for (i = 0; i < e820_saved.nr_map; i++) {
 		struct e820entry *entry = &e820_saved.map[i];
 		firmware_map_add_early(entry->addr,
-			entry->addr + entry->size - 1,
+			entry->addr + entry->size,
 			e820_type_to_string(entry->type));
 	}
 }
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 111f6bbd8b38..69babd8c834f 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1048,24 +1048,6 @@ apicinterrupt LOCAL_TIMER_VECTOR \
 apicinterrupt X86_PLATFORM_IPI_VECTOR \
 	x86_platform_ipi smp_x86_platform_ipi
 
-#ifdef CONFIG_SMP
-	ALIGN
-	INTR_FRAME
-.irp idx,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15, \
-	16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
-.if NUM_INVALIDATE_TLB_VECTORS > \idx
-ENTRY(invalidate_interrupt\idx)
-	pushq_cfi $~(INVALIDATE_TLB_VECTOR_START+\idx)
-	jmp .Lcommon_invalidate_interrupt0
-	CFI_ADJUST_CFA_OFFSET -8
-END(invalidate_interrupt\idx)
-.endif
-.endr
-	CFI_ENDPROC
-apicinterrupt INVALIDATE_TLB_VECTOR_START, \
-	invalidate_interrupt0, smp_invalidate_interrupt
-#endif
-
 apicinterrupt THRESHOLD_APIC_VECTOR \
 	threshold_interrupt smp_threshold_interrupt
 apicinterrupt THERMAL_APIC_VECTOR \
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 252981afd6c4..6e03b0d69138 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -171,79 +171,6 @@ static void __init smp_intr_init(void)
 	 */
 	alloc_intr_gate(RESCHEDULE_VECTOR, reschedule_interrupt);
 
-	/* IPIs for invalidation */
-#define ALLOC_INVTLB_VEC(NR) \
-	alloc_intr_gate(INVALIDATE_TLB_VECTOR_START+NR, \
-		invalidate_interrupt##NR)
-
-	switch (NUM_INVALIDATE_TLB_VECTORS) {
-	default:
-		ALLOC_INVTLB_VEC(31);
-	case 31:
-		ALLOC_INVTLB_VEC(30);
-	case 30:
-		ALLOC_INVTLB_VEC(29);
-	case 29:
-		ALLOC_INVTLB_VEC(28);
-	case 28:
-		ALLOC_INVTLB_VEC(27);
-	case 27:
-		ALLOC_INVTLB_VEC(26);
-	case 26:
-		ALLOC_INVTLB_VEC(25);
-	case 25:
-		ALLOC_INVTLB_VEC(24);
-	case 24:
-		ALLOC_INVTLB_VEC(23);
-	case 23:
-		ALLOC_INVTLB_VEC(22);
-	case 22:
-		ALLOC_INVTLB_VEC(21);
-	case 21:
-		ALLOC_INVTLB_VEC(20);
-	case 20:
-		ALLOC_INVTLB_VEC(19);
-	case 19:
-		ALLOC_INVTLB_VEC(18);
-	case 18:
-		ALLOC_INVTLB_VEC(17);
-	case 17:
-		ALLOC_INVTLB_VEC(16);
-	case 16:
-		ALLOC_INVTLB_VEC(15);
-	case 15:
-		ALLOC_INVTLB_VEC(14);
-	case 14:
-		ALLOC_INVTLB_VEC(13);
-	case 13:
-		ALLOC_INVTLB_VEC(12);
-	case 12:
-		ALLOC_INVTLB_VEC(11);
-	case 11:
-		ALLOC_INVTLB_VEC(10);
-	case 10:
-		ALLOC_INVTLB_VEC(9);
-	case 9:
-		ALLOC_INVTLB_VEC(8);
-	case 8:
-		ALLOC_INVTLB_VEC(7);
-	case 7:
-		ALLOC_INVTLB_VEC(6);
-	case 6:
-		ALLOC_INVTLB_VEC(5);
-	case 5:
-		ALLOC_INVTLB_VEC(4);
-	case 4:
-		ALLOC_INVTLB_VEC(3);
-	case 3:
-		ALLOC_INVTLB_VEC(2);
-	case 2:
-		ALLOC_INVTLB_VEC(1);
-	case 1:
-		ALLOC_INVTLB_VEC(0);
-		break;
-	}
-
 	/* IPI for generic function call */
 	alloc_intr_gate(CALL_FUNCTION_VECTOR, call_function_interrupt);
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 5a98aa272184..5cdff0357746 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -21,7 +21,7 @@
 #include <asm/cpu.h>
 #include <asm/stackprotector.h>
 
-DEFINE_PER_CPU(int, cpu_number);
+DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number);
 EXPORT_PER_CPU_SYMBOL(cpu_number);
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c1a310fb8309..7c5a8c314c02 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -106,17 +106,17 @@ int smp_num_siblings = 1;
 EXPORT_SYMBOL(smp_num_siblings);
 
 /* Last level cache ID of each logical CPU */
-DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID;
+DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID;
 
 /* representing HT siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 
 /* representing HT and core siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_core_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
-DEFINE_PER_CPU(cpumask_var_t, cpu_llc_shared_map);
+DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 
 /* Per CPU bogomips and other parameters */
 DEFINE_PER_CPU_SHARED_ALIGNED(struct cpuinfo_x86, cpu_info);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index a718e0d23503..931930a96160 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -919,11 +919,13 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	/*
 	 * On success we use clflush, when the CPU supports it to
-	 * avoid the wbindv. If the CPU does not support it and in the
-	 * error case we fall back to cpa_flush_all (which uses
-	 * wbindv):
+	 * avoid the wbindv. If the CPU does not support it, in the
+	 * error case, and during early boot (for EFI) we fall back
+	 * to cpa_flush_all (which uses wbinvd):
 	 */
-	if (!ret && cpu_has_clflush) {
+	if (early_boot_irqs_disabled)
+		__cpa_flush_all((void *)(long)cache);
+	else if (!ret && cpu_has_clflush) {
 		if (cpa.flags & (CPA_PAGES_ARRAY | CPA_ARRAY)) {
 			cpa_flush_array(addr, numpages, cache,
 					cpa.flags, pages);
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 5e57e113b72c..613cd83e8c0c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -12,6 +12,7 @@
 #include <asm/cache.h>
 #include <asm/apic.h>
 #include <asm/uv/uv.h>
+#include <linux/debugfs.h>
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate)
 			= { &init_mm, 0, };
@@ -27,33 +28,14 @@ DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate)
  *
  *	More scalable flush, from Andi Kleen
  *
- *	To avoid global state use 8 different call vectors.
- *	Each CPU uses a specific vector to trigger flushes on other
- *	CPUs. Depending on the received vector the target CPUs look into
- *	the right array slot for the flush data.
- *
- *	With more than 8 CPUs they are hashed to the 8 available
- *	vectors. The limited global vector space forces us to this right now.
- *	In future when interrupts are split into per CPU domains this could be
- *	fixed, at the cost of triggering multiple IPIs in some cases.
+ *	Implement flush IPI by CALL_FUNCTION_VECTOR, Alex Shi
  */
 
-union smp_flush_state {
-	struct {
-		struct mm_struct *flush_mm;
-		unsigned long flush_va;
-		raw_spinlock_t tlbstate_lock;
-		DECLARE_BITMAP(flush_cpumask, NR_CPUS);
-	};
-	char pad[INTERNODE_CACHE_BYTES];
-} ____cacheline_internodealigned_in_smp;
-
-/* State is put into the per CPU data section, but padded
-   to a full cache line because other CPUs can access it and we don't
-   want false sharing in the per cpu data segment. */
-static union smp_flush_state flush_state[NUM_INVALIDATE_TLB_VECTORS];
-
-static DEFINE_PER_CPU_READ_MOSTLY(int, tlb_vector_offset);
+struct flush_tlb_info {
+	struct mm_struct *flush_mm;
+	unsigned long flush_start;
+	unsigned long flush_end;
+};
 
 /*
  * We cannot call mmdrop() because we are in interrupt context,
@@ -72,28 +54,25 @@ void leave_mm(int cpu)
 EXPORT_SYMBOL_GPL(leave_mm);
 
 /*
- *
  * The flush IPI assumes that a thread switch happens in this order:
  * [cpu0: the cpu that switches]
  * 1) switch_mm() either 1a) or 1b)
  * 1a) thread switch to a different mm
- * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask);
- *	Stop ipi delivery for the old mm. This is not synchronized with
- *	the other cpus, but smp_invalidate_interrupt ignore flush ipis
- *	for the wrong mm, and in the worst case we perform a superfluous
- *	tlb flush.
- * 1a2) set cpu mmu_state to TLBSTATE_OK
- *	Now the smp_invalidate_interrupt won't call leave_mm if cpu0
- *	was in lazy tlb mode.
- * 1a3) update cpu active_mm
+ * 1a1) set cpu_tlbstate to TLBSTATE_OK
+ *	Now the tlb flush NMI handler flush_tlb_func won't call leave_mm
+ *	if cpu0 was in lazy tlb mode.
+ * 1a2) update cpu active_mm
  *	Now cpu0 accepts tlb flushes for the new mm.
- * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask);
+ * 1a3) cpu_set(cpu, new_mm->cpu_vm_mask);
  *	Now the other cpus will send tlb flush ipis.
  * 1a4) change cr3.
+ * 1a5) cpu_clear(cpu, old_mm->cpu_vm_mask);
+ *	Stop ipi delivery for the old mm. This is not synchronized with
+ *	the other cpus, but flush_tlb_func ignore flush ipis for the wrong
+ *	mm, and in the worst case we perform a superfluous tlb flush.
  * 1b) thread switch without mm change
- *	cpu active_mm is correct, cpu0 already handles
- *	flush ipis.
- * 1b1) set cpu mmu_state to TLBSTATE_OK
+ *	cpu active_mm is correct, cpu0 already handles flush ipis.
+ * 1b1) set cpu_tlbstate to TLBSTATE_OK
  * 1b2) test_and_set the cpu bit in cpu_vm_mask.
  *	Atomically set the bit [other cpus will start sending flush ipis],
  *	and test the bit.
@@ -106,174 +85,62 @@ EXPORT_SYMBOL_GPL(leave_mm);
  *   runs in kernel space, the cpu could load tlb entries for user space
  *   pages.
  *
- * The good news is that cpu mmu_state is local to each cpu, no
+ * The good news is that cpu_tlbstate is local to each cpu, no
  * write/read ordering problems.
  */
 
 /*
- * TLB flush IPI:
- *
+ * TLB flush funcation:
  * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
  * 2) Leave the mm if we are in the lazy tlb mode.
- *
- * Interrupts are disabled.
- */
-
-/*
- * FIXME: use of asmlinkage is not consistent.  On x86_64 it's noop
- * but still used for documentation purpose but the usage is slightly
- * inconsistent.  On x86_32, asmlinkage is regparm(0) but interrupt
- * entry calls in with the first parameter in %eax.  Maybe define
- * intrlinkage?
  */
-#ifdef CONFIG_X86_64
-asmlinkage
-#endif
-void smp_invalidate_interrupt(struct pt_regs *regs)
+static void flush_tlb_func(void *info)
 {
-	unsigned int cpu;
-	unsigned int sender;
-	union smp_flush_state *f;
-
-	cpu = smp_processor_id();
-	/*
-	 * orig_rax contains the negated interrupt vector.
-	 * Use that to determine where the sender put the data.
-	 */
-	sender = ~regs->orig_ax - INVALIDATE_TLB_VECTOR_START;
-	f = &flush_state[sender];
-
-	if (!cpumask_test_cpu(cpu, to_cpumask(f->flush_cpumask)))
-		goto out;
-		/*
-		 * This was a BUG() but until someone can quote me the
-		 * line from the intel manual that guarantees an IPI to
-		 * multiple CPUs is retried _only_ on the erroring CPUs
-		 * its staying as a return
-		 *
-		 * BUG();
-		 */
-
-	if (f->flush_mm == this_cpu_read(cpu_tlbstate.active_mm)) {
-		if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
-			if (f->flush_va == TLB_FLUSH_ALL)
-				local_flush_tlb();
-			else
-				__flush_tlb_one(f->flush_va);
-		} else
-			leave_mm(cpu);
-	}
-out:
-	ack_APIC_irq();
-	smp_mb__before_clear_bit();
-	cpumask_clear_cpu(cpu, to_cpumask(f->flush_cpumask));
-	smp_mb__after_clear_bit();
-	inc_irq_stat(irq_tlb_count);
-}
+	struct flush_tlb_info *f = info;
 
-static void flush_tlb_others_ipi(const struct cpumask *cpumask,
-				 struct mm_struct *mm, unsigned long va)
-{
-	unsigned int sender;
-	union smp_flush_state *f;
-
-	/* Caller has disabled preemption */
-	sender = this_cpu_read(tlb_vector_offset);
-	f = &flush_state[sender];
-
-	if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS)
-		raw_spin_lock(&f->tlbstate_lock);
-
-	f->flush_mm = mm;
-	f->flush_va = va;
-	if (cpumask_andnot(to_cpumask(f->flush_cpumask), cpumask, cpumask_of(smp_processor_id()))) {
-		/*
-		 * We have to send the IPI only to
-		 * CPUs affected.
-		 */
-		apic->send_IPI_mask(to_cpumask(f->flush_cpumask),
-			      INVALIDATE_TLB_VECTOR_START + sender);
-
-		while (!cpumask_empty(to_cpumask(f->flush_cpumask)))
-			cpu_relax();
-	}
+	if (f->flush_mm != this_cpu_read(cpu_tlbstate.active_mm))
+		return;
+
+	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
+		if (f->flush_end == TLB_FLUSH_ALL || !cpu_has_invlpg)
+			local_flush_tlb();
+		else if (!f->flush_end)
+			__flush_tlb_single(f->flush_start);
+		else {
+			unsigned long addr;
+			addr = f->flush_start;
+			while (addr < f->flush_end) {
+				__flush_tlb_single(addr);
+				addr += PAGE_SIZE;
+			}
+		}
+	} else
+		leave_mm(smp_processor_id());
 
-	f->flush_mm = NULL;
-	f->flush_va = 0;
-	if (nr_cpu_ids > NUM_INVALIDATE_TLB_VECTORS)
-		raw_spin_unlock(&f->tlbstate_lock);
 }
 
 void native_flush_tlb_others(const struct cpumask *cpumask,
-			     struct mm_struct *mm, unsigned long va)
+				 struct mm_struct *mm, unsigned long start,
+				 unsigned long end)
 {
+	struct flush_tlb_info info;
+	info.flush_mm = mm;
+	info.flush_start = start;
+	info.flush_end = end;
+
 	if (is_uv_system()) {
 		unsigned int cpu;
 
 		cpu = smp_processor_id();
-		cpumask = uv_flush_tlb_others(cpumask, mm, va, cpu);
+		cpumask = uv_flush_tlb_others(cpumask, mm, start, end, cpu);
 		if (cpumask)
-			flush_tlb_others_ipi(cpumask, mm, va);
+			smp_call_function_many(cpumask, flush_tlb_func,
+								&info, 1);
 		return;
 	}
-	flush_tlb_others_ipi(cpumask, mm, va);
+	smp_call_function_many(cpumask, flush_tlb_func, &info, 1);
 }
 
-static void __cpuinit calculate_tlb_offset(void)
-{
-	int cpu, node, nr_node_vecs, idx = 0;
-	/*
-	 * we are changing tlb_vector_offset for each CPU in runtime, but this
-	 * will not cause inconsistency, as the write is atomic under X86. we
-	 * might see more lock contentions in a short time, but after all CPU's
-	 * tlb_vector_offset are changed, everything should go normal
-	 *
-	 * Note: if NUM_INVALIDATE_TLB_VECTORS % nr_online_nodes !=0, we might
-	 * waste some vectors.
-	 **/
-	if (nr_online_nodes > NUM_INVALIDATE_TLB_VECTORS)
-		nr_node_vecs = 1;
-	else
-		nr_node_vecs = NUM_INVALIDATE_TLB_VECTORS/nr_online_nodes;
-
-	for_each_online_node(node) {
-		int node_offset = (idx % NUM_INVALIDATE_TLB_VECTORS) *
-			nr_node_vecs;
-		int cpu_offset = 0;
-		for_each_cpu(cpu, cpumask_of_node(node)) {
-			per_cpu(tlb_vector_offset, cpu) = node_offset +
-				cpu_offset;
-			cpu_offset++;
-			cpu_offset = cpu_offset % nr_node_vecs;
-		}
-		idx++;
-	}
-}
-
-static int __cpuinit tlb_cpuhp_notify(struct notifier_block *n,
-		unsigned long action, void *hcpu)
-{
-	switch (action & 0xf) {
-	case CPU_ONLINE:
-	case CPU_DEAD:
-		calculate_tlb_offset();
-	}
-	return NOTIFY_OK;
-}
-
-static int __cpuinit init_smp_flush(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(flush_state); i++)
-		raw_spin_lock_init(&flush_state[i].tlbstate_lock);
-
-	calculate_tlb_offset();
-	hotcpu_notifier(tlb_cpuhp_notify, 0);
-	return 0;
-}
-core_initcall(init_smp_flush);
-
 void flush_tlb_current_task(void)
 {
 	struct mm_struct *mm = current->mm;
@@ -282,27 +149,91 @@ void flush_tlb_current_task(void)
 
 	local_flush_tlb();
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, TLB_FLUSH_ALL);
+		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
 	preempt_enable();
 }
 
-void flush_tlb_mm(struct mm_struct *mm)
+/*
+ * It can find out the THP large page, or
+ * HUGETLB page in tlb_flush when THP disabled
+ */
+static inline unsigned long has_large_page(struct mm_struct *mm,
+				 unsigned long start, unsigned long end)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	unsigned long addr = ALIGN(start, HPAGE_SIZE);
+	for (; addr < end; addr += HPAGE_SIZE) {
+		pgd = pgd_offset(mm, addr);
+		if (likely(!pgd_none(*pgd))) {
+			pud = pud_offset(pgd, addr);
+			if (likely(!pud_none(*pud))) {
+				pmd = pmd_offset(pud, addr);
+				if (likely(!pmd_none(*pmd)))
+					if (pmd_large(*pmd))
+						return addr;
+			}
+		}
+	}
+	return 0;
+}
+
+void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
+				unsigned long end, unsigned long vmflag)
 {
+	unsigned long addr;
+	unsigned act_entries, tlb_entries = 0;
+
 	preempt_disable();
+	if (current->active_mm != mm)
+		goto flush_all;
 
-	if (current->active_mm == mm) {
-		if (current->mm)
+	if (!current->mm) {
+		leave_mm(smp_processor_id());
+		goto flush_all;
+	}
+
+	if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1
+					|| vmflag == VM_HUGETLB) {
+		local_flush_tlb();
+		goto flush_all;
+	}
+
+	/* In modern CPU, last level tlb used for both data/ins */
+	if (vmflag & VM_EXEC)
+		tlb_entries = tlb_lli_4k[ENTRIES];
+	else
+		tlb_entries = tlb_lld_4k[ENTRIES];
+	/* Assume all of TLB entries was occupied by this task */
+	act_entries = mm->total_vm > tlb_entries ? tlb_entries : mm->total_vm;
+
+	/* tlb_flushall_shift is on balance point, details in commit log */
+	if ((end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift)
+		local_flush_tlb();
+	else {
+		if (has_large_page(mm, start, end)) {
 			local_flush_tlb();
-		else
-			leave_mm(smp_processor_id());
+			goto flush_all;
+		}
+		/* flush range by one by one 'invlpg' */
+		for (addr = start; addr < end;	addr += PAGE_SIZE)
+			__flush_tlb_single(addr);
+
+		if (cpumask_any_but(mm_cpumask(mm),
+				smp_processor_id()) < nr_cpu_ids)
+			flush_tlb_others(mm_cpumask(mm), mm, start, end);
+		preempt_enable();
+		return;
 	}
-	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, TLB_FLUSH_ALL);
 
+flush_all:
+	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(mm_cpumask(mm), mm, 0UL, TLB_FLUSH_ALL);
 	preempt_enable();
 }
 
-void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long start)
 {
 	struct mm_struct *mm = vma->vm_mm;
 
@@ -310,13 +241,13 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
 
 	if (current->active_mm == mm) {
 		if (current->mm)
-			__flush_tlb_one(va);
+			__flush_tlb_one(start);
 		else
 			leave_mm(smp_processor_id());
 	}
 
 	if (cpumask_any_but(mm_cpumask(mm), smp_processor_id()) < nr_cpu_ids)
-		flush_tlb_others(mm_cpumask(mm), mm, va);
+		flush_tlb_others(mm_cpumask(mm), mm, start, 0UL);
 
 	preempt_enable();
 }
@@ -332,3 +263,83 @@ void flush_tlb_all(void)
 {
 	on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
+
+static void do_kernel_range_flush(void *info)
+{
+	struct flush_tlb_info *f = info;
+	unsigned long addr;
+
+	/* flush range by one by one 'invlpg' */
+	for (addr = f->flush_start; addr < f->flush_end; addr += PAGE_SIZE)
+		__flush_tlb_single(addr);
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	unsigned act_entries;
+	struct flush_tlb_info info;
+
+	/* In modern CPU, last level tlb used for both data/ins */
+	act_entries = tlb_lld_4k[ENTRIES];
+
+	/* Balance as user space task's flush, a bit conservative */
+	if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1 ||
+		(end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift)
+
+		on_each_cpu(do_flush_tlb_all, NULL, 1);
+	else {
+		info.flush_start = start;
+		info.flush_end = end;
+		on_each_cpu(do_kernel_range_flush, &info, 1);
+	}
+}
+
+#ifdef CONFIG_DEBUG_TLBFLUSH
+static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf,
+			     size_t count, loff_t *ppos)
+{
+	char buf[32];
+	unsigned int len;
+
+	len = sprintf(buf, "%hd\n", tlb_flushall_shift);
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t tlbflush_write_file(struct file *file,
+		 const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	char buf[32];
+	ssize_t len;
+	s8 shift;
+
+	len = min(count, sizeof(buf) - 1);
+	if (copy_from_user(buf, user_buf, len))
+		return -EFAULT;
+
+	buf[len] = '\0';
+	if (kstrtos8(buf, 0, &shift))
+		return -EINVAL;
+
+	if (shift > 64)
+		return -EINVAL;
+
+	tlb_flushall_shift = shift;
+	return count;
+}
+
+static const struct file_operations fops_tlbflush = {
+	.read = tlbflush_read_file,
+	.write = tlbflush_write_file,
+	.llseek = default_llseek,
+};
+
+static int __cpuinit create_tlb_flushall_shift(void)
+{
+	if (cpu_has_invlpg) {
+		debugfs_create_file("tlb_flushall_shift", S_IRUSR | S_IWUSR,
+			arch_debugfs_dir, NULL, &fops_tlbflush);
+	}
+	return 0;
+}
+late_initcall(create_tlb_flushall_shift);
+#endif
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 92660edaa1e7..2dc29f51e75a 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -234,22 +234,7 @@ static efi_status_t __init phys_efi_set_virtual_address_map(
 	return status;
 }
 
-static efi_status_t __init phys_efi_get_time(efi_time_t *tm,
-					     efi_time_cap_t *tc)
-{
-	unsigned long flags;
-	efi_status_t status;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	efi_call_phys_prelog();
-	status = efi_call_phys2(efi_phys.get_time, virt_to_phys(tm),
-				virt_to_phys(tc));
-	efi_call_phys_epilog();
-	spin_unlock_irqrestore(&rtc_lock, flags);
-	return status;
-}
-
-int efi_set_rtc_mmss(unsigned long nowtime)
+static int efi_set_rtc_mmss(unsigned long nowtime)
 {
 	int real_seconds, real_minutes;
 	efi_status_t 	status;
@@ -278,7 +263,7 @@ int efi_set_rtc_mmss(unsigned long nowtime)
 	return 0;
 }
 
-unsigned long efi_get_time(void)
+static unsigned long efi_get_time(void)
 {
 	efi_status_t status;
 	efi_time_t eft;
@@ -621,18 +606,13 @@ static int __init efi_runtime_init(void)
 	}
 	/*
 	 * We will only need *early* access to the following
-	 * two EFI runtime services before set_virtual_address_map
+	 * EFI runtime service before set_virtual_address_map
 	 * is invoked.
 	 */
-	efi_phys.get_time = (efi_get_time_t *)runtime->get_time;
 	efi_phys.set_virtual_address_map =
 		(efi_set_virtual_address_map_t *)
 		runtime->set_virtual_address_map;
-	/*
-	 * Make efi_get_time can be called before entering
-	 * virtual mode.
-	 */
-	efi.get_time = phys_efi_get_time;
+
 	early_iounmap(runtime, sizeof(efi_runtime_services_t));
 
 	return 0;
@@ -720,12 +700,10 @@ void __init efi_init(void)
 		efi_enabled = 0;
 		return;
 	}
-#ifdef CONFIG_X86_32
 	if (efi_native) {
 		x86_platform.get_wallclock = efi_get_time;
 		x86_platform.set_wallclock = efi_set_rtc_mmss;
 	}
-#endif
 
 #if EFI_DEBUG
 	print_efi_memmap();
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 71b5d5a07d7b..b8b3a37c80cd 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1055,8 +1055,8 @@ static int set_distrib_bits(struct cpumask *flush_mask, struct bau_control *bcp,
  * done.  The returned pointer is valid till preemption is re-enabled.
  */
 const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
-				struct mm_struct *mm, unsigned long va,
-				unsigned int cpu)
+				struct mm_struct *mm, unsigned long start,
+				unsigned end, unsigned int cpu)
 {
 	int locals = 0;
 	int remotes = 0;
@@ -1113,7 +1113,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 
 	record_send_statistics(stat, locals, hubs, remotes, bau_desc);
 
-	bau_desc->payload.address = va;
+	bau_desc->payload.address = start;
 	bau_desc->payload.sending_cpu = cpu;
 	/*
 	 * uv_flush_send_and_wait returns 0 if all cpu's were messaged,
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 27336dfcda8e..b65a76133f4f 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1256,7 +1256,8 @@ static void xen_flush_tlb_single(unsigned long addr)
 }
 
 static void xen_flush_tlb_others(const struct cpumask *cpus,
-				 struct mm_struct *mm, unsigned long va)
+				 struct mm_struct *mm, unsigned long start,
+				 unsigned long end)
 {
 	struct {
 		struct mmuext_op op;
@@ -1268,7 +1269,7 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 	} *args;
 	struct multicall_space mcs;
 
-	trace_xen_mmu_flush_tlb_others(cpus, mm, va);
+	trace_xen_mmu_flush_tlb_others(cpus, mm, start, end);
 
 	if (cpumask_empty(cpus))
 		return;		/* nothing to do */
@@ -1281,11 +1282,10 @@ static void xen_flush_tlb_others(const struct cpumask *cpus,
 	cpumask_and(to_cpumask(args->mask), cpus, cpu_online_mask);
 	cpumask_clear_cpu(smp_processor_id(), to_cpumask(args->mask));
 
-	if (va == TLB_FLUSH_ALL) {
-		args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
-	} else {
+	args->op.cmd = MMUEXT_TLB_FLUSH_MULTI;
+	if (start != TLB_FLUSH_ALL && (end - start) <= PAGE_SIZE) {
 		args->op.cmd = MMUEXT_INVLPG_MULTI;
-		args->op.arg1.linear_addr = va;
+		args->op.arg1.linear_addr = start;
 	}
 
 	MULTI_mmuext_op(mcs.mc, &args->op, 1, NULL, DOMID_SELF);
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 8a3f8351f438..8ed64cfae4ff 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -7,6 +7,7 @@ config ZONE_DMA
 config XTENSA
 	def_bool y
 	select HAVE_IDE
+	select GENERIC_ATOMIC64
 	select HAVE_GENERIC_HARDIRQS
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
diff --git a/arch/xtensa/include/asm/cpumask.h b/arch/xtensa/include/asm/cpumask.h
deleted file mode 100644
index ebeede397db3..000000000000
--- a/arch/xtensa/include/asm/cpumask.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * include/asm-xtensa/cpumask.h
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2001 - 2005 Tensilica Inc.
- */
-
-#ifndef _XTENSA_CPUMASK_H
-#define _XTENSA_CPUMASK_H
-
-#include <asm-generic/cpumask.h>
-
-#endif /* _XTENSA_CPUMASK_H */
diff --git a/arch/xtensa/include/asm/rmap.h b/arch/xtensa/include/asm/rmap.h
deleted file mode 100644
index 649588b7e9ad..000000000000
--- a/arch/xtensa/include/asm/rmap.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- * include/asm-xtensa/rmap.h
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2001 - 2005 Tensilica Inc.
- */
-
-#ifndef _XTENSA_RMAP_H
-#define _XTENSA_RMAP_H
-
-#include <asm-generic/rmap.h>
-
-#endif
diff --git a/arch/xtensa/kernel/syscall.c b/arch/xtensa/kernel/syscall.c
index 816e6d0d686c..05b3f093d5d7 100644
--- a/arch/xtensa/kernel/syscall.c
+++ b/arch/xtensa/kernel/syscall.c
@@ -44,7 +44,7 @@ asmlinkage long xtensa_shmat(int shmid, char __user *shmaddr, int shmflg)
 	unsigned long ret;
 	long err;
 
-	err = do_shmat(shmid, shmaddr, shmflg, &ret);
+	err = do_shmat(shmid, shmaddr, shmflg, &ret, SHMLBA);
 	if (err)
 		return err;
 	return (long)ret;
diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c
index b17885a0b508..5a74c53bc69c 100644
--- a/arch/xtensa/mm/fault.c
+++ b/arch/xtensa/mm/fault.c
@@ -44,6 +44,7 @@ void do_page_fault(struct pt_regs *regs)
 
 	int is_write, is_exec;
 	int fault;
+	unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	info.si_code = SEGV_MAPERR;
 
@@ -71,6 +72,7 @@ void do_page_fault(struct pt_regs *regs)
 	       address, exccause, regs->pc, is_write? "w":"", is_exec? "x":"");
 #endif
 
+retry:
 	down_read(&mm->mmap_sem);
 	vma = find_vma(mm, address);
 
@@ -93,6 +95,7 @@ good_area:
 	if (is_write) {
 		if (!(vma->vm_flags & VM_WRITE))
 			goto bad_area;
+		flags |= FAULT_FLAG_WRITE;
 	} else if (is_exec) {
 		if (!(vma->vm_flags & VM_EXEC))
 			goto bad_area;
@@ -104,7 +107,11 @@ good_area:
 	 * make sure we exit gracefully rather than endlessly redo
 	 * the fault.
 	 */
-	fault = handle_mm_fault(mm, vma, address, is_write ? FAULT_FLAG_WRITE : 0);
+	fault = handle_mm_fault(mm, vma, address, flags);
+
+	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current))
+		return;
+
 	if (unlikely(fault & VM_FAULT_ERROR)) {
 		if (fault & VM_FAULT_OOM)
 			goto out_of_memory;
@@ -112,10 +119,22 @@ good_area:
 			goto do_sigbus;
 		BUG();
 	}
-	if (fault & VM_FAULT_MAJOR)
-		current->maj_flt++;
-	else
-		current->min_flt++;
+	if (flags & FAULT_FLAG_ALLOW_RETRY) {
+		if (fault & VM_FAULT_MAJOR)
+			current->maj_flt++;
+		else
+			current->min_flt++;
+		if (fault & VM_FAULT_RETRY) {
+			flags &= ~FAULT_FLAG_ALLOW_RETRY;
+
+			 /* No need to up_read(&mm->mmap_sem) as we would
+			 * have already released it in __lock_page_or_retry
+			 * in mm/filemap.c.
+			 */
+
+			goto retry;
+		}
+	}
 
 	up_read(&mm->mmap_sem);
 	return;
author	Paul Mundt <lethal@linux-sh.org>	2012-08-01 13:49:13 +0900
committer	Paul Mundt <lethal@linux-sh.org>	2012-08-01 13:49:13 +0900
commit	91ba548cfd5cc8ee93b9435527efb8fa4caf5c5e (patch)
tree	c96ed92413044a28d17783e84a8824bfd2437af1 /arch
parent	b9ccfda293ee6fca9a89a1584f0900e0627b975e (diff)
parent	4dc4c51675c137c30838425ecc8d471ff5eb138b (diff)