From 2fbe7b25c8edaf2d10e6c1a4cc9f8afe714c4764 Mon Sep 17 00:00:00 2001
From: Don Zickus <dzickus@redhat.com>
Date: Tue, 26 Sep 2006 10:52:27 +0200
Subject: [PATCH] i386/x86-64: Remove un/set_nmi_callback and
 reserve/release_lapic_nmi functions

Removes the un/set_nmi_callback and reserve/release_lapic_nmi functions as
they are no longer needed.  The various subsystems are modified to register
with the die_notifier instead.

Also includes compile fixes by Andrew Morton.

Signed-off-by:  Don Zickus <dzickus@redhat.com>
Signed-off-by: Andi Kleen <ak@suse.de>
---
 kernel/sysctl.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

(limited to 'kernel')

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 362a0cc37138..83f168361624 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -76,8 +76,6 @@ extern int compat_log;
 
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
 int unknown_nmi_panic;
-extern int proc_unknown_nmi_panic(ctl_table *, int, struct file *,
-				  void __user *, size_t *, loff_t *);
 #endif
 
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
@@ -628,7 +626,7 @@ static ctl_table kern_table[] = {
 		.data           = &unknown_nmi_panic,
 		.maxlen         = sizeof (int),
 		.mode           = 0644,
-		.proc_handler   = &proc_unknown_nmi_panic,
+		.proc_handler   = &proc_dointvec,
 	},
 #endif
 #if defined(CONFIG_X86)
-- 
cgit v1.2.3


From 407984f1af259b31957c7c05075a454a751bb801 Mon Sep 17 00:00:00 2001
From: Don Zickus <dzickus@redhat.com>
Date: Tue, 26 Sep 2006 10:52:27 +0200
Subject: [PATCH] x86: Add abilty to enable/disable nmi watchdog with sysctl

Adds a new /proc/sys/kernel/nmi call that will enable/disable the nmi
watchdog.

Signed-off-by:  Don Zickus <dzickus@redhat.com>
Signed-off-by: Andi Kleen <ak@suse.de>
---
 arch/i386/kernel/nmi.c   | 52 ++++++++++++++++++++++++++++++++++++++++++++++++
 arch/x86_64/kernel/nmi.c | 48 ++++++++++++++++++++++++++++++++++++++++++++
 include/asm-i386/nmi.h   |  1 +
 include/asm-x86_64/nmi.h |  1 +
 include/linux/sysctl.h   |  1 +
 kernel/sysctl.c          | 11 ++++++++++
 6 files changed, 114 insertions(+)

(limited to 'kernel')

diff --git a/arch/i386/kernel/nmi.c b/arch/i386/kernel/nmi.c
index acd3fdea2a21..28065d0b71a9 100644
--- a/arch/i386/kernel/nmi.c
+++ b/arch/i386/kernel/nmi.c
@@ -846,6 +846,58 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
 	return 0;
 }
 
+/*
+ * proc handler for /proc/sys/kernel/nmi_watchdog
+ */
+int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
+			void __user *buffer, size_t *length, loff_t *ppos)
+{
+	int old_state;
+
+	nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
+	old_state = nmi_watchdog_enabled;
+	proc_dointvec(table, write, file, buffer, length, ppos);
+	if (!!old_state == !!nmi_watchdog_enabled)
+		return 0;
+
+	if (atomic_read(&nmi_active) < 0) {
+		printk(KERN_WARNING "NMI watchdog is permanently disabled\n");
+		return -EINVAL;
+	}
+
+	if (nmi_watchdog == NMI_DEFAULT) {
+		if (nmi_known_cpu() > 0)
+			nmi_watchdog = NMI_LOCAL_APIC;
+		else
+			nmi_watchdog = NMI_IO_APIC;
+	}
+
+	if (nmi_watchdog == NMI_LOCAL_APIC)
+	{
+		if (nmi_watchdog_enabled)
+			enable_lapic_nmi_watchdog();
+		else
+			disable_lapic_nmi_watchdog();
+	} else if (nmi_watchdog == NMI_IO_APIC) {
+		/* FIXME
+		 * for some reason these functions don't work
+		 */
+		printk("Can not enable/disable NMI on IO APIC\n");
+		return -EINVAL;
+#if 0
+		if (nmi_watchdog_enabled)
+			enable_timer_nmi_watchdog();
+		else
+			disable_timer_nmi_watchdog();
+#endif
+	} else {
+		printk( KERN_WARNING
+			"NMI watchdog doesn't know what hardware to touch\n");
+		return -EIO;
+	}
+	return 0;
+}
+
 #endif
 
 EXPORT_SYMBOL(nmi_active);
diff --git a/arch/x86_64/kernel/nmi.c b/arch/x86_64/kernel/nmi.c
index 9d175dcf3a2d..3a17411a9a19 100644
--- a/arch/x86_64/kernel/nmi.c
+++ b/arch/x86_64/kernel/nmi.c
@@ -750,6 +750,54 @@ static int unknown_nmi_panic_callback(struct pt_regs *regs, int cpu)
 	return 0;
 }
 
+/*
+ * proc handler for /proc/sys/kernel/nmi
+ */
+int proc_nmi_enabled(struct ctl_table *table, int write, struct file *file,
+			void __user *buffer, size_t *length, loff_t *ppos)
+{
+	int old_state;
+
+	nmi_watchdog_enabled = (atomic_read(&nmi_active) > 0) ? 1 : 0;
+	old_state = nmi_watchdog_enabled;
+	proc_dointvec(table, write, file, buffer, length, ppos);
+	if (!!old_state == !!nmi_watchdog_enabled)
+		return 0;
+
+	if (atomic_read(&nmi_active) < 0) {
+		printk( KERN_WARNING "NMI watchdog is permanently disabled\n");
+		return -EINVAL;
+	}
+
+	/* if nmi_watchdog is not set yet, then set it */
+	nmi_watchdog_default();
+
+	if (nmi_watchdog == NMI_LOCAL_APIC)
+	{
+		if (nmi_watchdog_enabled)
+			enable_lapic_nmi_watchdog();
+		else
+			disable_lapic_nmi_watchdog();
+	} else if (nmi_watchdog == NMI_IO_APIC) {
+		/* FIXME
+		 * for some reason these functions don't work
+		 */
+		printk("Can not enable/disable NMI on IO APIC\n");
+		return -EIO;
+#if 0
+		if (nmi_watchdog_enabled)
+			enable_timer_nmi_watchdog();
+		else
+			disable_timer_nmi_watchdog();
+#endif
+	} else {
+		printk(KERN_WARNING
+			"NMI watchdog doesn't know what hardware to touch\n");
+		return -EIO;
+	}
+	return 0;
+}
+
 #endif
 
 EXPORT_SYMBOL(nmi_active);
diff --git a/include/asm-i386/nmi.h b/include/asm-i386/nmi.h
index 34d6bf063b6e..13b5d8311bf7 100644
--- a/include/asm-i386/nmi.h
+++ b/include/asm-i386/nmi.h
@@ -14,6 +14,7 @@
  */
 int do_nmi_callback(struct pt_regs *regs, int cpu);
 
+extern int nmi_watchdog_enabled;
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
 extern int avail_to_resrv_perfctr_nmi(unsigned int);
 extern int reserve_perfctr_nmi(unsigned int);
diff --git a/include/asm-x86_64/nmi.h b/include/asm-x86_64/nmi.h
index 8818c39d34e0..2c23b0df87d2 100644
--- a/include/asm-x86_64/nmi.h
+++ b/include/asm-x86_64/nmi.h
@@ -43,6 +43,7 @@ extern void die_nmi(char *str, struct pt_regs *regs);
 
 extern int panic_on_timeout;
 extern int unknown_nmi_panic;
+extern int nmi_watchdog_enabled;
 
 extern int check_nmi_watchdog(void);
 extern int avail_to_resrv_perfctr_nmi_bit(unsigned int);
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 736ed917a4f8..ecb79ba52ae1 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -150,6 +150,7 @@ enum
 	KERN_IA64_UNALIGNED=72, /* int: ia64 unaligned userland trap enable */
 	KERN_COMPAT_LOG=73,	/* int: print compat layer  messages */
 	KERN_MAX_LOCK_DEPTH=74,
+	KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */
 };
 
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 83f168361624..040de6bd74dd 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -76,6 +76,9 @@ extern int compat_log;
 
 #if defined(CONFIG_X86_LOCAL_APIC) && defined(CONFIG_X86)
 int unknown_nmi_panic;
+int nmi_watchdog_enabled;
+extern int proc_nmi_enabled(struct ctl_table *, int , struct file *,
+			void __user *, size_t *, loff_t *);
 #endif
 
 /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */
@@ -628,6 +631,14 @@ static ctl_table kern_table[] = {
 		.mode           = 0644,
 		.proc_handler   = &proc_dointvec,
 	},
+	{
+		.ctl_name       = KERN_NMI_WATCHDOG,
+		.procname       = "nmi_watchdog",
+		.data           = &nmi_watchdog_enabled,
+		.maxlen         = sizeof (int),
+		.mode           = 0644,
+		.proc_handler   = &proc_nmi_enabled,
+	},
 #endif
 #if defined(CONFIG_X86)
 	{
-- 
cgit v1.2.3


From 8da5adda91df3d2fcc5300e68da491694c9af019 Mon Sep 17 00:00:00 2001
From: Don Zickus <dzickus@redhat.com>
Date: Tue, 26 Sep 2006 10:52:27 +0200
Subject: [PATCH] x86: Allow users to force a panic on NMI

To quote Alan Cox:

The default Linux behaviour on an NMI of either memory or unknown is to
continue operation. For many environments such as scientific computing
it is preferable that the box is taken out and the error dealt with than
an uncorrected parity/ECC error get propogated.

A small number of systems do generate NMI's for bizarre random reasons
such as power management so the default is unchanged. In other respects
the new proc/sys entry works like the existing panic controls already in
that directory.

This is separate to the edac support - EDAC allows supported chipsets to
handle ECC errors well, this change allows unsupported cases to at least
panic rather than cause problems further down the line.

Signed-off-by: Don Zickus <dzickus@redhat.com>
Signed-off-by: Andi Kleen <ak@suse.de>
---
 arch/i386/kernel/traps.c   | 6 ++++++
 arch/x86_64/kernel/traps.c | 6 ++++++
 include/linux/kernel.h     | 1 +
 include/linux/sysctl.h     | 1 +
 kernel/panic.c             | 1 +
 kernel/sysctl.c            | 8 ++++++++
 6 files changed, 23 insertions(+)

(limited to 'kernel')

diff --git a/arch/i386/kernel/traps.c b/arch/i386/kernel/traps.c
index 7db664d0b25c..2f6cb8276480 100644
--- a/arch/i386/kernel/traps.c
+++ b/arch/i386/kernel/traps.c
@@ -635,6 +635,8 @@ static void mem_parity_error(unsigned char reason, struct pt_regs * regs)
 			"to continue\n");
 	printk(KERN_EMERG "You probably have a hardware problem with your RAM "
 			"chips\n");
+	if (panic_on_unrecovered_nmi)
+                panic("NMI: Not continuing");
 
 	/* Clear and disable the memory parity error line. */
 	clear_mem_error(reason);
@@ -670,6 +672,10 @@ static void unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
 		reason, smp_processor_id());
 	printk("Dazed and confused, but trying to continue\n");
 	printk("Do you have a strange power saving mode enabled?\n");
+
+	if (panic_on_unrecovered_nmi)
+                panic("NMI: Not continuing");
+
 }
 
 static DEFINE_SPINLOCK(nmi_print_lock);
diff --git a/arch/x86_64/kernel/traps.c b/arch/x86_64/kernel/traps.c
index 42bc070fdf11..b18829db2a6a 100644
--- a/arch/x86_64/kernel/traps.c
+++ b/arch/x86_64/kernel/traps.c
@@ -732,6 +732,8 @@ mem_parity_error(unsigned char reason, struct pt_regs * regs)
 {
 	printk("Uhhuh. NMI received. Dazed and confused, but trying to continue\n");
 	printk("You probably have a hardware problem with your RAM chips\n");
+	if (panic_on_unrecovered_nmi)
+               panic("NMI: Not continuing");
 
 	/* Clear and disable the memory parity error line. */
 	reason = (reason & 0xf) | 4;
@@ -757,6 +759,10 @@ unknown_nmi_error(unsigned char reason, struct pt_regs * regs)
 {	printk("Uhhuh. NMI received for unknown reason %02x.\n", reason);
 	printk("Dazed and confused, but trying to continue\n");
 	printk("Do you have a strange power saving mode enabled?\n");
+
+	if (panic_on_unrecovered_nmi)
+                panic("NMI: Not continuing");
+
 }
 
 /* Runs on IST stack. This code must keep interrupts off all the time.
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 2b2ae4fdce8b..1ff9609300b4 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -186,6 +186,7 @@ extern void bust_spinlocks(int yes);
 extern int oops_in_progress;		/* If set, an oops, panic(), BUG() or die() is in progress */
 extern int panic_timeout;
 extern int panic_on_oops;
+extern int panic_on_unrecovered_nmi;
 extern int tainted;
 extern const char *print_tainted(void);
 extern void add_taint(unsigned);
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index ecb79ba52ae1..432778446ad2 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -151,6 +151,7 @@ enum
 	KERN_COMPAT_LOG=73,	/* int: print compat layer  messages */
 	KERN_MAX_LOCK_DEPTH=74,
 	KERN_NMI_WATCHDOG=75, /* int: enable/disable nmi watchdog */
+	KERN_PANIC_ON_NMI=76, /* int: whether we will panic on an unrecovered */
 };
 
 
diff --git a/kernel/panic.c b/kernel/panic.c
index 8010b9b17aca..d2db3e2209e0 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -21,6 +21,7 @@
 #include <linux/debug_locks.h>
 
 int panic_on_oops;
+int panic_on_unrecovered_nmi;
 int tainted;
 static int pause_on_oops;
 static int pause_on_oops_flag;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 040de6bd74dd..220e20564124 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -641,6 +641,14 @@ static ctl_table kern_table[] = {
 	},
 #endif
 #if defined(CONFIG_X86)
+	{
+		.ctl_name	= KERN_PANIC_ON_NMI,
+		.procname	= "panic_on_unrecovered_nmi",
+		.data		= &panic_on_unrecovered_nmi,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 	{
 		.ctl_name	= KERN_BOOTLOADER_TYPE,
 		.procname	= "bootloader_type",
-- 
cgit v1.2.3


From 3cfc348bf90ffaa777c188652aa297f04eb94de8 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@suse.de>
Date: Tue, 26 Sep 2006 10:52:28 +0200
Subject: [PATCH] x86: Add portable getcpu call

For NUMA optimization and some other algorithms it is useful to have a fast
to get the current CPU and node numbers in user space.

x86-64 added a fast way to do this in a vsyscall. This adds a generic
syscall for other architectures to make it a generic portable facility.

I expect some of them will also implement it as a faster vsyscall.

The cache is an optimization for the x86-64 vsyscall optimization. Since
what the syscall returns is an approximation anyways and user space
often wants very fast results it can be cached for some time.  The norma
methods to get this information in user space are relatively slow

The vsyscall is in a better position to manage the cache because it has direct
access to a fast time stamp (jiffies). For the generic syscall optimization
it doesn't help much, but enforce a valid argument to keep programs
portable

I only added an i386 syscall entry for now. Other architectures can follow
as needed.

AK: Also added some cleanups from Andrew Morton

Signed-off-by: Andi Kleen <ak@suse.de>
---
 arch/i386/kernel/syscall_table.S |  1 +
 arch/x86_64/ia32/ia32entry.S     |  1 +
 include/asm-i386/unistd.h        |  3 ++-
 include/linux/syscalls.h         |  2 ++
 kernel/sys.c                     | 31 +++++++++++++++++++++++++++++++
 5 files changed, 37 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
index dd63d4775398..7e639f78b0b9 100644
--- a/arch/i386/kernel/syscall_table.S
+++ b/arch/i386/kernel/syscall_table.S
@@ -317,3 +317,4 @@ ENTRY(sys_call_table)
 	.long sys_tee			/* 315 */
 	.long sys_vmsplice
 	.long sys_move_pages
+	.long sys_getcpu
diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S
index 30ed0f6f4a2b..32fd32bea07c 100644
--- a/arch/x86_64/ia32/ia32entry.S
+++ b/arch/x86_64/ia32/ia32entry.S
@@ -713,4 +713,5 @@ ia32_sys_call_table:
 	.quad sys_tee
 	.quad compat_sys_vmsplice
 	.quad compat_sys_move_pages
+	.quad sys_getcpu
 ia32_syscall_end:		
diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
index fc1c8ddae149..565d0897b205 100644
--- a/include/asm-i386/unistd.h
+++ b/include/asm-i386/unistd.h
@@ -323,10 +323,11 @@
 #define __NR_tee		315
 #define __NR_vmsplice		316
 #define __NR_move_pages		317
+#define __NR_getcpu		318
 
 #ifdef __KERNEL__
 
-#define NR_syscalls 318
+#define NR_syscalls 319
 
 /*
  * user-visible error numbers are in the range -1 - -128: see
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 008f04c56737..3f0f716225ec 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -53,6 +53,7 @@ struct mq_attr;
 struct compat_stat;
 struct compat_timeval;
 struct robust_list_head;
+struct getcpu_cache;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -596,5 +597,6 @@ asmlinkage long sys_get_robust_list(int pid,
 				    size_t __user *len_ptr);
 asmlinkage long sys_set_robust_list(struct robust_list_head __user *head,
 				    size_t len);
+asmlinkage long sys_getcpu(unsigned *cpu, unsigned *node, struct getcpu_cache *cache);
 
 #endif
diff --git a/kernel/sys.c b/kernel/sys.c
index e236f98f7ec5..3f894775488d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -28,6 +28,7 @@
 #include <linux/tty.h>
 #include <linux/signal.h>
 #include <linux/cn_proc.h>
+#include <linux/getcpu.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -2062,3 +2063,33 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 	}
 	return error;
 }
+
+asmlinkage long sys_getcpu(unsigned __user *cpup, unsigned __user *nodep,
+	   		   struct getcpu_cache __user *cache)
+{
+	int err = 0;
+	int cpu = raw_smp_processor_id();
+	if (cpup)
+		err |= put_user(cpu, cpup);
+	if (nodep)
+		err |= put_user(cpu_to_node(cpu), nodep);
+	if (cache) {
+		/*
+		 * The cache is not needed for this implementation,
+		 * but make sure user programs pass something
+		 * valid. vsyscall implementations can instead make
+		 * good use of the cache. Only use t0 and t1 because
+		 * these are available in both 32bit and 64bit ABI (no
+		 * need for a compat_getcpu). 32bit has enough
+		 * padding
+		 */
+		unsigned long t0, t1;
+		get_user(t0, &cache->t0);
+		get_user(t1, &cache->t1);
+		t0++;
+		t1++;
+		put_user(t0, &cache->t0);
+		put_user(t1, &cache->t1);
+	}
+	return err ? -EFAULT : 0;
+}
-- 
cgit v1.2.3


From 0cb91a2293648507886563ccb91979cfc94d6a4b Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@suse.de>
Date: Tue, 26 Sep 2006 10:52:28 +0200
Subject: [PATCH] i386: Account spinlocks to the caller during profiling for
 !FP kernels

This ports the algorithm from x86-64 (with improvements) to i386.
Previously this only worked for frame pointer enabled kernels.
But spinlocks have a very simple stack frame that can be manually
analyzed. Do this.

Signed-off-by: Andi Kleen <ak@suse.de>
---
 arch/i386/kernel/time.c   | 23 +++++++++++++++++++----
 include/asm-i386/ptrace.h |  4 ----
 kernel/spinlock.c         |  5 +++++
 3 files changed, 24 insertions(+), 8 deletions(-)

(limited to 'kernel')

diff --git a/arch/i386/kernel/time.c b/arch/i386/kernel/time.c
index edd00f6cee37..5af802ef00b2 100644
--- a/arch/i386/kernel/time.c
+++ b/arch/i386/kernel/time.c
@@ -130,18 +130,33 @@ static int set_rtc_mmss(unsigned long nowtime)
 
 int timer_ack;
 
-#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER)
 unsigned long profile_pc(struct pt_regs *regs)
 {
 	unsigned long pc = instruction_pointer(regs);
 
-	if (!user_mode_vm(regs) && in_lock_functions(pc))
+#ifdef CONFIG_SMP
+	if (!user_mode_vm(regs) && in_lock_functions(pc)) {
+#ifdef CONFIG_FRAME_POINTER
 		return *(unsigned long *)(regs->ebp + 4);
-
+#else
+		unsigned long *sp;
+		if ((regs->xcs & 3) == 0)
+			sp = (unsigned long *)&regs->esp;
+		else
+			sp = (unsigned long *)regs->esp;
+		/* Return address is either directly at stack pointer
+		   or above a saved eflags. Eflags has bits 22-31 zero,
+		   kernel addresses don't. */
+ 		if (sp[0] >> 22)
+			return sp[0];
+		if (sp[1] >> 22)
+			return sp[1];
+#endif
+	}
+#endif
 	return pc;
 }
 EXPORT_SYMBOL(profile_pc);
-#endif
 
 /*
  * This is the same as the above, except we _also_ save the current
diff --git a/include/asm-i386/ptrace.h b/include/asm-i386/ptrace.h
index f324c53b6f9a..30a442ec2059 100644
--- a/include/asm-i386/ptrace.h
+++ b/include/asm-i386/ptrace.h
@@ -80,11 +80,7 @@ static inline int user_mode_vm(struct pt_regs *regs)
 	return ((regs->xcs & 3) | (regs->eflags & VM_MASK)) != 0;
 }
 #define instruction_pointer(regs) ((regs)->eip)
-#if defined(CONFIG_SMP) && defined(CONFIG_FRAME_POINTER)
 extern unsigned long profile_pc(struct pt_regs *regs);
-#else
-#define profile_pc(regs) instruction_pointer(regs)
-#endif
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index fb524b009eef..9644a41e0bef 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -7,6 +7,11 @@
  *
  * This file contains the spinlock/rwlock implementations for the
  * SMP and the DEBUG_SPINLOCK cases. (UP-nondebug inlines them)
+ *
+ * Note that some architectures have special knowledge about the
+ * stack frames of these functions in their profile_pc. If you
+ * change anything significant here that could change the stack
+ * frame contact the architecture maintainers.
  */
 
 #include <linux/linkage.h>
-- 
cgit v1.2.3


From 5a1b3999d6cb7ab87f1f3b1700bc91839fd6fa29 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@suse.de>
Date: Tue, 26 Sep 2006 10:52:34 +0200
Subject: [PATCH] x86: Some preparationary cleanup for stack trace

- Remove unused all_contexts parameter
No caller used it
- Move skip argument into the structure (needed for
followon patches)

Cc: mingo@elte.hu

Signed-off-by: Andi Kleen <ak@suse.de>
---
 arch/i386/kernel/stacktrace.c   | 11 +++--------
 arch/s390/kernel/stacktrace.c   | 17 ++++++++---------
 arch/x86_64/kernel/stacktrace.c | 14 +++++---------
 include/linux/stacktrace.h      |  7 ++++---
 kernel/lockdep.c                |  5 ++++-
 5 files changed, 24 insertions(+), 30 deletions(-)

(limited to 'kernel')

diff --git a/arch/i386/kernel/stacktrace.c b/arch/i386/kernel/stacktrace.c
index e62a037ab399..ae3c32a87add 100644
--- a/arch/i386/kernel/stacktrace.c
+++ b/arch/i386/kernel/stacktrace.c
@@ -61,12 +61,8 @@ save_context_stack(struct stack_trace *trace, unsigned int skip,
 
 /*
  * Save stack-backtrace addresses into a stack_trace buffer.
- * If all_contexts is set, all contexts (hardirq, softirq and process)
- * are saved. If not set then only the current context is saved.
  */
-void save_stack_trace(struct stack_trace *trace,
-		      struct task_struct *task, int all_contexts,
-		      unsigned int skip)
+void save_stack_trace(struct stack_trace *trace, struct task_struct *task)
 {
 	unsigned long ebp;
 	unsigned long *stack = &ebp;
@@ -85,10 +81,9 @@ void save_stack_trace(struct stack_trace *trace,
 		struct thread_info *context = (struct thread_info *)
 				((unsigned long)stack & (~(THREAD_SIZE - 1)));
 
-		ebp = save_context_stack(trace, skip, context, stack, ebp);
+		ebp = save_context_stack(trace, trace->skip, context, stack, ebp);
 		stack = (unsigned long *)context->previous_esp;
-		if (!all_contexts || !stack ||
-				trace->nr_entries >= trace->max_entries)
+		if (!stack || trace->nr_entries >= trace->max_entries)
 			break;
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 		if (trace->nr_entries >= trace->max_entries)
diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
index de83f38288d0..d9428a0fc8fb 100644
--- a/arch/s390/kernel/stacktrace.c
+++ b/arch/s390/kernel/stacktrace.c
@@ -59,9 +59,7 @@ static inline unsigned long save_context_stack(struct stack_trace *trace,
 	}
 }
 
-void save_stack_trace(struct stack_trace *trace,
-		      struct task_struct *task, int all_contexts,
-		      unsigned int skip)
+void save_stack_trace(struct stack_trace *trace, struct task_struct *task)
 {
 	register unsigned long sp asm ("15");
 	unsigned long orig_sp;
@@ -69,22 +67,23 @@ void save_stack_trace(struct stack_trace *trace,
 	sp &= PSW_ADDR_INSN;
 	orig_sp = sp;
 
-	sp = save_context_stack(trace, &skip, sp,
+	sp = save_context_stack(trace, &trace->skip, sp,
 				S390_lowcore.panic_stack - PAGE_SIZE,
 				S390_lowcore.panic_stack);
-	if ((sp != orig_sp) && !all_contexts)
+	if ((sp != orig_sp) && !trace->all_contexts)
 		return;
-	sp = save_context_stack(trace, &skip, sp,
+	sp = save_context_stack(trace, &trace->skip, sp,
 				S390_lowcore.async_stack - ASYNC_SIZE,
 				S390_lowcore.async_stack);
-	if ((sp != orig_sp) && !all_contexts)
+	if ((sp != orig_sp) && !trace->all_contexts)
 		return;
 	if (task)
-		save_context_stack(trace, &skip, sp,
+		save_context_stack(trace, &trace->skip, sp,
 				   (unsigned long) task_stack_page(task),
 				   (unsigned long) task_stack_page(task) + THREAD_SIZE);
 	else
-		save_context_stack(trace, &skip, sp, S390_lowcore.thread_info,
+		save_context_stack(trace, &trace->skip, sp,
+				   S390_lowcore.thread_info,
 				   S390_lowcore.thread_info + THREAD_SIZE);
 	return;
 }
diff --git a/arch/x86_64/kernel/stacktrace.c b/arch/x86_64/kernel/stacktrace.c
index 32cf55eb9af8..1c022af8fe1e 100644
--- a/arch/x86_64/kernel/stacktrace.c
+++ b/arch/x86_64/kernel/stacktrace.c
@@ -109,9 +109,10 @@ out_restore:
  * Save stack-backtrace addresses into a stack_trace buffer:
  */
 static inline unsigned long
-save_context_stack(struct stack_trace *trace, unsigned int skip,
+save_context_stack(struct stack_trace *trace,
 		   unsigned long stack, unsigned long stack_end)
 {
+	int skip = trace->skip;
 	unsigned long addr;
 
 #ifdef CONFIG_FRAME_POINTER
@@ -159,12 +160,8 @@ save_context_stack(struct stack_trace *trace, unsigned int skip,
 
 /*
  * Save stack-backtrace addresses into a stack_trace buffer.
- * If all_contexts is set, all contexts (hardirq, softirq and process)
- * are saved. If not set then only the current context is saved.
  */
-void save_stack_trace(struct stack_trace *trace,
-		      struct task_struct *task, int all_contexts,
-		      unsigned int skip)
+void save_stack_trace(struct stack_trace *trace, struct task_struct *task)
 {
 	unsigned long stack = (unsigned long)&stack;
 	int i, nr_stacks = 0, stacks_done[MAX_STACKS];
@@ -207,9 +204,8 @@ void save_stack_trace(struct stack_trace *trace,
 				return;
 		stacks_done[nr_stacks] = stack_end;
 
-		stack = save_context_stack(trace, skip, stack, stack_end);
-		if (!all_contexts || !stack ||
-				trace->nr_entries >= trace->max_entries)
+		stack = save_context_stack(trace, stack, stack_end);
+		if (!stack || trace->nr_entries >= trace->max_entries)
 			return;
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 		if (trace->nr_entries >= trace->max_entries)
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index 9cc81e572224..50e2b01e517c 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -5,15 +5,16 @@
 struct stack_trace {
 	unsigned int nr_entries, max_entries;
 	unsigned long *entries;
+	int skip;	/* input argument: How many entries to skip */
+	int all_contexts; /* input argument: if true do than one stack */
 };
 
 extern void save_stack_trace(struct stack_trace *trace,
-			     struct task_struct *task, int all_contexts,
-			     unsigned int skip);
+			     struct task_struct *task);
 
 extern void print_stack_trace(struct stack_trace *trace, int spaces);
 #else
-# define save_stack_trace(trace, task, all, skip)	do { } while (0)
+# define save_stack_trace(trace, task)			do { } while (0)
 # define print_stack_trace(trace)			do { } while (0)
 #endif
 
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 9bad17884513..900b4cb1a024 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -224,7 +224,10 @@ static int save_trace(struct stack_trace *trace)
 	trace->max_entries = MAX_STACK_TRACE_ENTRIES - nr_stack_trace_entries;
 	trace->entries = stack_trace + nr_stack_trace_entries;
 
-	save_stack_trace(trace, NULL, 0, 3);
+	trace->skip = 3;
+	trace->all_contexts = 0;
+
+	save_stack_trace(trace, NULL);
 
 	trace->max_entries = trace->nr_entries;
 
-- 
cgit v1.2.3


From 3fa7c794fe4dc127f7fac3fad4d13628e68f89ce Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@suse.de>
Date: Tue, 26 Sep 2006 10:52:34 +0200
Subject: [PATCH] Avoid recursion in lockdep when stack tracer takes locks

The new dwarf2 unwinder needs to take locks to do backtraces
inside modules. This patch makes sure lockdep which calls
stacktrace is not reentered.

Thanks to Ingo for suggesting this simpler approach.

Cc: mingo@elte.hu
Signed-off-by: Andi Kleen <ak@suse.de>
---
 kernel/lockdep.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'kernel')

diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 900b4cb1a024..c088e5542e84 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -227,7 +227,11 @@ static int save_trace(struct stack_trace *trace)
 	trace->skip = 3;
 	trace->all_contexts = 0;
 
+	/* Make sure to not recurse in case the the unwinder needs to tak
+e	   locks. */
+	lockdep_off();
 	save_stack_trace(trace, NULL);
+	lockdep_on();
 
 	trace->max_entries = trace->nr_entries;
 
-- 
cgit v1.2.3


From 0a4254058037eb172758961d0a5b94f4320a1425 Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Tue, 26 Sep 2006 10:52:38 +0200
Subject: [PATCH] Add the canary field to the PDA area and the task struct

This patch adds the per thread cookie field to the task struct and the PDA.
Also it makes sure that the PDA value gets the new cookie value at context
switch, and that a new task gets a new cookie at task creation time.

Signed-off-by: Arjan van Ven <arjan@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andi Kleen <ak@suse.de>
CC: Andi Kleen <ak@suse.de>
---
 arch/x86_64/kernel/process.c | 8 ++++++++
 include/asm-x86_64/pda.h     | 7 ++++++-
 include/linux/sched.h        | 5 +++++
 kernel/fork.c                | 5 +++++
 4 files changed, 24 insertions(+), 1 deletion(-)

(limited to 'kernel')

diff --git a/arch/x86_64/kernel/process.c b/arch/x86_64/kernel/process.c
index 9e9a70e50c72..fba8dfeda67c 100644
--- a/arch/x86_64/kernel/process.c
+++ b/arch/x86_64/kernel/process.c
@@ -625,6 +625,14 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	unlazy_fpu(prev_p);
 	write_pda(kernelstack,
 		  task_stack_page(next_p) + THREAD_SIZE - PDA_STACKOFFSET);
+#ifdef CONFIG_CC_STACKPROTECTOR
+	write_pda(stack_canary, next_p->stack_canary);
+	/*
+	 * Build time only check to make sure the stack_canary is at
+	 * offset 40 in the pda; this is a gcc ABI requirement
+	 */
+	BUILD_BUG_ON(offsetof(struct x8664_pda, stack_canary) != 40);
+#endif
 
 	/*
 	 * Now maybe reload the debug registers and handle I/O bitmaps
diff --git a/include/asm-x86_64/pda.h b/include/asm-x86_64/pda.h
index 6794ffaae433..e7773e0af865 100644
--- a/include/asm-x86_64/pda.h
+++ b/include/asm-x86_64/pda.h
@@ -16,7 +16,12 @@ struct x8664_pda {
 	unsigned long oldrsp; 	    /* 24 user rsp for system call */
         int irqcount;		    /* 32 Irq nesting counter. Starts with -1 */
 	int cpunumber;		    /* 36 Logical CPU number */
-	char *irqstackptr;	/* 40 top of irqstack */
+#ifdef CONFIG_CC_STACKPROTECTOR
+	unsigned long stack_canary;	/* 40 stack canary value */
+					/* gcc-ABI: this canary MUST be at
+					   offset 40!!! */
+#endif
+	char *irqstackptr;
 	int nodenumber;		    /* number of current node */
 	unsigned int __softirq_pending;
 	unsigned int __nmi_count;	/* number of NMI on this CPUs */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 807556c5bcd2..9d4aa7f95bc8 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -819,6 +819,11 @@ struct task_struct {
 	unsigned did_exec:1;
 	pid_t pid;
 	pid_t tgid;
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+	/* Canary value for the -fstack-protector gcc feature */
+	unsigned long stack_canary;
+#endif
 	/* 
 	 * pointers to (original) parent process, youngest child, younger sibling,
 	 * older sibling, respectively.  (p->father can be replaced with 
diff --git a/kernel/fork.c b/kernel/fork.c
index f9b014e3e700..a0dad84567c9 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -45,6 +45,7 @@
 #include <linux/cn_proc.h>
 #include <linux/delayacct.h>
 #include <linux/taskstats_kern.h>
+#include <linux/random.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -175,6 +176,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 	tsk->thread_info = ti;
 	setup_thread_stack(tsk, orig);
 
+#ifdef CONFIG_CC_STACKPROTECTOR
+	tsk->stack_canary = get_random_int();
+#endif
+
 	/* One for us, one for whoever does the "release_task()" (usually parent) */
 	atomic_set(&tsk->usage,2);
 	atomic_set(&tsk->fs_excl, 0);
-- 
cgit v1.2.3


From 3162f751d04086a9d006342de63ac8f44fe0f72a Mon Sep 17 00:00:00 2001
From: Arjan van de Ven <arjan@linux.intel.com>
Date: Tue, 26 Sep 2006 10:52:39 +0200
Subject: [PATCH] Add the __stack_chk_fail() function

GCC emits a call to a __stack_chk_fail() function when the stack canary is
not matching the expected value.

Since this is a bad security issue; lets panic the kernel rather than limping
along; the kernel really can't be trusted anymore when this happens.

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andi Kleen <ak@suse.de>
CC: Andi Kleen <ak@suse.de>
---
 kernel/panic.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'kernel')

diff --git a/kernel/panic.c b/kernel/panic.c
index d2db3e2209e0..6ceb664fb52a 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -271,3 +271,15 @@ void oops_exit(void)
 {
 	do_oops_enter_exit();
 }
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+/*
+ * Called when gcc's -fstack-protector feature is used, and
+ * gcc detects corruption of the on-stack canary value
+ */
+void __stack_chk_fail(void)
+{
+	panic("stack-protector: Kernel stack is corrupted");
+}
+EXPORT_SYMBOL(__stack_chk_fail);
+#endif
-- 
cgit v1.2.3


From adf1423698f00d00b267f7dca8231340ce7d65ef Mon Sep 17 00:00:00 2001
From: Jan Beulich <jbeulich@novell.com>
Date: Tue, 26 Sep 2006 10:52:41 +0200
Subject: [PATCH] i386/x86-64: Work around gcc bug with noreturn functions in
 unwinder

Current gcc generates calls not jumps to noreturn functions. When that happens the
return address can point to the next function, which confuses the unwinder.

This patch works around it by marking asynchronous exception
frames in contrast normal call frames in the unwind information.  Then teach
the unwinder to decode this.

For normal call frames the unwinder now subtracts one from the address which avoids
this problem.  The standard libgcc unwinder uses the same trick.

It doesn't include adjustment of the printed address (i.e. for the original
example, it'd still be kernel_math_error+0 that gets displayed, but the
unwinder wouldn't get confused anymore.

This only works with binutils 2.6.17+ and some versions of H.J.Lu's 2.6.16
unfortunately because earlier binutils don't support .cfi_signal_frame

[AK: added automatic detection of the new binutils and wrote description]

Signed-off-by: Jan Beulich <jbeulich@novell.com>
Signed-off-by: Andi Kleen <ak@suse.de>
---
 arch/i386/Makefile           |  4 ++++
 arch/i386/kernel/entry.S     |  4 ++++
 arch/x86_64/Makefile         |  4 ++++
 arch/x86_64/ia32/ia32entry.S |  4 ++++
 arch/x86_64/kernel/entry.S   |  4 ++++
 include/asm-i386/dwarf2.h    |  7 +++++++
 include/asm-i386/unwind.h    |  5 +++++
 include/asm-x86_64/dwarf2.h  |  6 ++++++
 include/asm-x86_64/unwind.h  |  5 +++++
 kernel/unwind.c              | 35 ++++++++++++++++++++++++++++-------
 scripts/Kbuild.include       |  4 ++--
 11 files changed, 73 insertions(+), 9 deletions(-)

(limited to 'kernel')

diff --git a/arch/i386/Makefile b/arch/i386/Makefile
index 508cdbeb3a09..7cc0b189b82b 100644
--- a/arch/i386/Makefile
+++ b/arch/i386/Makefile
@@ -50,6 +50,10 @@ CFLAGS				+= $(shell if [ $(call cc-version) -lt 0400 ] ; then echo $(call cc-op
 cflags-y += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
 AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
 
+# is .cfi_signal_frame supported too?
+cflags-y += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
+
 CFLAGS += $(cflags-y)
 
 # Default subarch .c files
diff --git a/arch/i386/kernel/entry.S b/arch/i386/kernel/entry.S
index 284f2e908ad0..5a63d6fdb70e 100644
--- a/arch/i386/kernel/entry.S
+++ b/arch/i386/kernel/entry.S
@@ -183,18 +183,21 @@ VM_MASK		= 0x00020000
 
 #define RING0_INT_FRAME \
 	CFI_STARTPROC simple;\
+	CFI_SIGNAL_FRAME;\
 	CFI_DEF_CFA esp, 3*4;\
 	/*CFI_OFFSET cs, -2*4;*/\
 	CFI_OFFSET eip, -3*4
 
 #define RING0_EC_FRAME \
 	CFI_STARTPROC simple;\
+	CFI_SIGNAL_FRAME;\
 	CFI_DEF_CFA esp, 4*4;\
 	/*CFI_OFFSET cs, -2*4;*/\
 	CFI_OFFSET eip, -3*4
 
 #define RING0_PTREGS_FRAME \
 	CFI_STARTPROC simple;\
+	CFI_SIGNAL_FRAME;\
 	CFI_DEF_CFA esp, OLDESP-EBX;\
 	/*CFI_OFFSET cs, CS-OLDESP;*/\
 	CFI_OFFSET eip, EIP-OLDESP;\
@@ -275,6 +278,7 @@ need_resched:
 	# sysenter call handler stub
 ENTRY(sysenter_entry)
 	CFI_STARTPROC simple
+	CFI_SIGNAL_FRAME
 	CFI_DEF_CFA esp, 0
 	CFI_REGISTER esp, ebp
 	movl TSS_sysenter_esp0(%esp),%esp
diff --git a/arch/x86_64/Makefile b/arch/x86_64/Makefile
index 2b8d07c70106..1c0f18d4f887 100644
--- a/arch/x86_64/Makefile
+++ b/arch/x86_64/Makefile
@@ -58,6 +58,10 @@ cflags-y += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
 cflags-y += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
 AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_endproc,-DCONFIG_AS_CFI=1,)
 
+# is .cfi_signal_frame supported too?
+cflags-y += $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1,)
+AFLAGS += $(call as-instr,.cfi_startproc\n.cfi_signal_frame\n.cfi_endproc,-DCONFIG_AS_CFI_SIGNAL_FRAME=1,)
+
 cflags-$(CONFIG_CC_STACKPROTECTOR) += $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC) -fstack-protector )
 cflags-$(CONFIG_CC_STACKPROTECTOR_ALL) += $(shell $(CONFIG_SHELL) $(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC) -fstack-protector-all )
 
diff --git a/arch/x86_64/ia32/ia32entry.S b/arch/x86_64/ia32/ia32entry.S
index 32fd32bea07c..b4aa875e175b 100644
--- a/arch/x86_64/ia32/ia32entry.S
+++ b/arch/x86_64/ia32/ia32entry.S
@@ -71,6 +71,7 @@
  */ 	
 ENTRY(ia32_sysenter_target)
 	CFI_STARTPROC32	simple
+	CFI_SIGNAL_FRAME
 	CFI_DEF_CFA	rsp,0
 	CFI_REGISTER	rsp,rbp
 	swapgs
@@ -186,6 +187,7 @@ ENDPROC(ia32_sysenter_target)
  */ 	
 ENTRY(ia32_cstar_target)
 	CFI_STARTPROC32	simple
+	CFI_SIGNAL_FRAME
 	CFI_DEF_CFA	rsp,PDA_STACKOFFSET
 	CFI_REGISTER	rip,rcx
 	/*CFI_REGISTER	rflags,r11*/
@@ -293,6 +295,7 @@ ia32_badarg:
 
 ENTRY(ia32_syscall)
 	CFI_STARTPROC	simple
+	CFI_SIGNAL_FRAME
 	CFI_DEF_CFA	rsp,SS+8-RIP
 	/*CFI_REL_OFFSET	ss,SS-RIP*/
 	CFI_REL_OFFSET	rsp,RSP-RIP
@@ -370,6 +373,7 @@ ENTRY(ia32_ptregs_common)
 	popq %r11
 	CFI_ENDPROC
 	CFI_STARTPROC32	simple
+	CFI_SIGNAL_FRAME
 	CFI_DEF_CFA	rsp,SS+8-ARGOFFSET
 	CFI_REL_OFFSET	rax,RAX-ARGOFFSET
 	CFI_REL_OFFSET	rcx,RCX-ARGOFFSET
diff --git a/arch/x86_64/kernel/entry.S b/arch/x86_64/kernel/entry.S
index ea32688386fd..4cbc65290ae7 100644
--- a/arch/x86_64/kernel/entry.S
+++ b/arch/x86_64/kernel/entry.S
@@ -123,6 +123,7 @@
 	.macro	CFI_DEFAULT_STACK start=1
 	.if \start
 	CFI_STARTPROC	simple
+	CFI_SIGNAL_FRAME
 	CFI_DEF_CFA	rsp,SS+8
 	.else
 	CFI_DEF_CFA_OFFSET SS+8
@@ -207,6 +208,7 @@ END(ret_from_fork)
 
 ENTRY(system_call)
 	CFI_STARTPROC	simple
+	CFI_SIGNAL_FRAME
 	CFI_DEF_CFA	rsp,PDA_STACKOFFSET
 	CFI_REGISTER	rip,rcx
 	/*CFI_REGISTER	rflags,r11*/
@@ -324,6 +326,7 @@ END(system_call)
  */ 	
 ENTRY(int_ret_from_sys_call)
 	CFI_STARTPROC	simple
+	CFI_SIGNAL_FRAME
 	CFI_DEF_CFA	rsp,SS+8-ARGOFFSET
 	/*CFI_REL_OFFSET	ss,SS-ARGOFFSET*/
 	CFI_REL_OFFSET	rsp,RSP-ARGOFFSET
@@ -484,6 +487,7 @@ END(stub_rt_sigreturn)
  */
 	.macro _frame ref
 	CFI_STARTPROC simple
+	CFI_SIGNAL_FRAME
 	CFI_DEF_CFA rsp,SS+8-\ref
 	/*CFI_REL_OFFSET ss,SS-\ref*/
 	CFI_REL_OFFSET rsp,RSP-\ref
diff --git a/include/asm-i386/dwarf2.h b/include/asm-i386/dwarf2.h
index 5d1a8db5a9b0..6d66398a307d 100644
--- a/include/asm-i386/dwarf2.h
+++ b/include/asm-i386/dwarf2.h
@@ -28,6 +28,12 @@
 #define CFI_RESTORE_STATE .cfi_restore_state
 #define CFI_UNDEFINED .cfi_undefined
 
+#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
+#define CFI_SIGNAL_FRAME .cfi_signal_frame
+#else
+#define CFI_SIGNAL_FRAME
+#endif
+
 #else
 
 /* Due to the structure of pre-exisiting code, don't use assembler line
@@ -48,6 +54,7 @@
 #define CFI_REMEMBER_STATE ignore
 #define CFI_RESTORE_STATE ignore
 #define CFI_UNDEFINED ignore
+#define CFI_SIGNAL_FRAME ignore
 
 #endif
 
diff --git a/include/asm-i386/unwind.h b/include/asm-i386/unwind.h
index f0ac399bae3c..5031d693b89d 100644
--- a/include/asm-i386/unwind.h
+++ b/include/asm-i386/unwind.h
@@ -18,6 +18,7 @@ struct unwind_frame_info
 {
 	struct pt_regs regs;
 	struct task_struct *task;
+	unsigned call_frame:1;
 };
 
 #define UNW_PC(frame)        (frame)->regs.eip
@@ -44,6 +45,10 @@ struct unwind_frame_info
 	PTREGS_INFO(edi), \
 	PTREGS_INFO(eip)
 
+#define UNW_DEFAULT_RA(raItem, dataAlign) \
+	((raItem).where == Memory && \
+	 !((raItem).value * (dataAlign) + 4))
+
 static inline void arch_unw_init_frame_info(struct unwind_frame_info *info,
                                             /*const*/ struct pt_regs *regs)
 {
diff --git a/include/asm-x86_64/dwarf2.h b/include/asm-x86_64/dwarf2.h
index 2b9368365fad..eedc08526b0b 100644
--- a/include/asm-x86_64/dwarf2.h
+++ b/include/asm-x86_64/dwarf2.h
@@ -28,6 +28,11 @@
 #define CFI_REMEMBER_STATE .cfi_remember_state
 #define CFI_RESTORE_STATE .cfi_restore_state
 #define CFI_UNDEFINED .cfi_undefined
+#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
+#define CFI_SIGNAL_FRAME .cfi_signal_frame
+#else
+#define CFI_SIGNAL_FRAME
+#endif
 
 #else
 
@@ -45,6 +50,7 @@
 #define CFI_REMEMBER_STATE	#
 #define CFI_RESTORE_STATE	#
 #define CFI_UNDEFINED	#
+#define CFI_SIGNAL_FRAME	#
 
 #endif
 
diff --git a/include/asm-x86_64/unwind.h b/include/asm-x86_64/unwind.h
index 1f6e9bfb569e..b8fa5cb7ff88 100644
--- a/include/asm-x86_64/unwind.h
+++ b/include/asm-x86_64/unwind.h
@@ -18,6 +18,7 @@ struct unwind_frame_info
 {
 	struct pt_regs regs;
 	struct task_struct *task;
+	unsigned call_frame:1;
 };
 
 #define UNW_PC(frame)        (frame)->regs.rip
@@ -57,6 +58,10 @@ struct unwind_frame_info
 	PTREGS_INFO(r15), \
 	PTREGS_INFO(rip)
 
+#define UNW_DEFAULT_RA(raItem, dataAlign) \
+	((raItem).where == Memory && \
+	 !((raItem).value * (dataAlign) + 8))
+
 static inline void arch_unw_init_frame_info(struct unwind_frame_info *info,
                                             /*const*/ struct pt_regs *regs)
 {
diff --git a/kernel/unwind.c b/kernel/unwind.c
index f69c804c8e62..3430475fcd88 100644
--- a/kernel/unwind.c
+++ b/kernel/unwind.c
@@ -603,6 +603,7 @@ int unwind(struct unwind_frame_info *frame)
 #define FRAME_REG(r, t) (((t *)frame)[reg_info[r].offs])
 	const u32 *fde = NULL, *cie = NULL;
 	const u8 *ptr = NULL, *end = NULL;
+	unsigned long pc = UNW_PC(frame) - frame->call_frame;
 	unsigned long startLoc = 0, endLoc = 0, cfa;
 	unsigned i;
 	signed ptrType = -1;
@@ -612,7 +613,7 @@ int unwind(struct unwind_frame_info *frame)
 
 	if (UNW_PC(frame) == 0)
 		return -EINVAL;
-	if ((table = find_table(UNW_PC(frame))) != NULL
+	if ((table = find_table(pc)) != NULL
 	    && !(table->size & (sizeof(*fde) - 1))) {
 		unsigned long tableSize = table->size;
 
@@ -647,7 +648,7 @@ int unwind(struct unwind_frame_info *frame)
 			                        ptrType & DW_EH_PE_indirect
 			                        ? ptrType
 			                        : ptrType & (DW_EH_PE_FORM|DW_EH_PE_signed));
-			if (UNW_PC(frame) >= startLoc && UNW_PC(frame) < endLoc)
+			if (pc >= startLoc && pc < endLoc)
 				break;
 			cie = NULL;
 		}
@@ -657,16 +658,28 @@ int unwind(struct unwind_frame_info *frame)
 		state.cieEnd = ptr; /* keep here temporarily */
 		ptr = (const u8 *)(cie + 2);
 		end = (const u8 *)(cie + 1) + *cie;
+		frame->call_frame = 1;
 		if ((state.version = *ptr) != 1)
 			cie = NULL; /* unsupported version */
 		else if (*++ptr) {
 			/* check if augmentation size is first (and thus present) */
 			if (*ptr == 'z') {
-				/* check for ignorable (or already handled)
-				 * nul-terminated augmentation string */
-				while (++ptr < end && *ptr)
-					if (strchr("LPR", *ptr) == NULL)
+				while (++ptr < end && *ptr) {
+					switch(*ptr) {
+					/* check for ignorable (or already handled)
+					 * nul-terminated augmentation string */
+					case 'L':
+					case 'P':
+					case 'R':
+						continue;
+					case 'S':
+						frame->call_frame = 0;
+						continue;
+					default:
 						break;
+					}
+					break;
+				}
 			}
 			if (ptr >= end || *ptr)
 				cie = NULL;
@@ -755,7 +768,7 @@ int unwind(struct unwind_frame_info *frame)
 	state.org = startLoc;
 	memcpy(&state.cfa, &badCFA, sizeof(state.cfa));
 	/* process instructions */
-	if (!processCFI(ptr, end, UNW_PC(frame), ptrType, &state)
+	if (!processCFI(ptr, end, pc, ptrType, &state)
 	   || state.loc > endLoc
 	   || state.regs[retAddrReg].where == Nowhere
 	   || state.cfa.reg >= ARRAY_SIZE(reg_info)
@@ -763,6 +776,11 @@ int unwind(struct unwind_frame_info *frame)
 	   || state.cfa.offs % sizeof(unsigned long))
 		return -EIO;
 	/* update frame */
+#ifndef CONFIG_AS_CFI_SIGNAL_FRAME
+	if(frame->call_frame
+	   && !UNW_DEFAULT_RA(state.regs[retAddrReg], state.dataAlign))
+		frame->call_frame = 0;
+#endif
 	cfa = FRAME_REG(state.cfa.reg, unsigned long) + state.cfa.offs;
 	startLoc = min((unsigned long)UNW_SP(frame), cfa);
 	endLoc = max((unsigned long)UNW_SP(frame), cfa);
@@ -866,6 +884,7 @@ int unwind_init_frame_info(struct unwind_frame_info *info,
                            /*const*/ struct pt_regs *regs)
 {
 	info->task = tsk;
+	info->call_frame = 0;
 	arch_unw_init_frame_info(info, regs);
 
 	return 0;
@@ -879,6 +898,7 @@ int unwind_init_blocked(struct unwind_frame_info *info,
                         struct task_struct *tsk)
 {
 	info->task = tsk;
+	info->call_frame = 0;
 	arch_unw_init_blocked(info);
 
 	return 0;
@@ -894,6 +914,7 @@ int unwind_init_running(struct unwind_frame_info *info,
                         void *arg)
 {
 	info->task = current;
+	info->call_frame = 0;
 
 	return arch_unwind_init_running(info, callback, arg);
 }
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 7adef12a0c26..4f5ff19b992b 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -66,8 +66,8 @@ as-option = $(shell if $(CC) $(CFLAGS) $(1) -Wa,-Z -c -o /dev/null \
 # as-instr
 # Usage: cflags-y += $(call as-instr, instr, option1, option2)
 
-as-instr = $(shell if echo -e "$(1)" | $(AS) -Z -o astest$$$$.out \
-		   2>&1 >/dev/null ; then echo "$(2)"; else echo "$(3)"; fi; \
+as-instr = $(shell if echo -e "$(1)" | $(AS) >/dev/null 2>&1 -W -Z -o astest$$$$.out ; \
+		   then echo "$(2)"; else echo "$(3)"; fi; \
 	           rm -f astest$$$$.out)
 
 # cc-option
-- 
cgit v1.2.3