Merge branch 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'sched-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  sched_clock: Fix atomicity/continuity bug by using cmpxchg64()
  x86: Provide an alternative() based cmpxchg64()

5 files changed, 85 insertions, 16 deletions

diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 82ceb78..ee1931b 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -312,19 +312,23 @@ static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
 
 extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64);
 
-#define cmpxchg64(ptr, o, n)						\
-({									\
-	__typeof__(*(ptr)) __ret;					\
-	if (likely(boot_cpu_data.x86 > 4))				\
-		__ret = (__typeof__(*(ptr)))__cmpxchg64((ptr),		\
-				(unsigned long long)(o),		\
-				(unsigned long long)(n));		\
-	else								\
-		__ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr),	\
-				(unsigned long long)(o),		\
-				(unsigned long long)(n));		\
-	__ret;								\
-})
+#define cmpxchg64(ptr, o, n)					\
+({								\
+	__typeof__(*(ptr)) __ret;				\
+	__typeof__(*(ptr)) __old = (o);				\
+	__typeof__(*(ptr)) __new = (n);				\
+	alternative_io("call cmpxchg8b_emu",			\
+			"lock; cmpxchg8b (%%esi)" ,		\
+		       X86_FEATURE_CX8,				\
+		       "=A" (__ret),				\
+		       "S" ((ptr)), "0" (__old),		\
+		       "b" ((unsigned int)__new),		\
+		       "c" ((unsigned int)(__new>>32))		\
+		       : "memory");				\
+	__ret; })
+
+
+
 #define cmpxchg64_local(ptr, o, n)					\
 ({									\
 	__typeof__(*(ptr)) __ret;					\
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 43cec6b..1736c5a 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -10,6 +10,14 @@
 EXPORT_SYMBOL(mcount);
 #endif
 
+/*
+ * Note, this is a prototype to get at the symbol for
+ * the export, but dont use it from C code, it is used
+ * by assembly code and is not using C calling convention!
+ */
+extern void cmpxchg8b_emu(void);
+EXPORT_SYMBOL(cmpxchg8b_emu);
+
 /* Networking helper routines. */
 EXPORT_SYMBOL(csum_partial_copy_generic);
 
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 9e60920..3e549b8 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -15,7 +15,7 @@ ifeq ($(CONFIG_X86_32),y)
         obj-y += atomic64_32.o
         lib-y += checksum_32.o
         lib-y += strstr_32.o
-        lib-y += semaphore_32.o string_32.o
+        lib-y += semaphore_32.o string_32.o cmpxchg8b_emu.o
 
         lib-$(CONFIG_X86_USE_3DNOW) += mmx_32.o
 else
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
new file mode 100644
index 0000000..828cb71
--- /dev/null
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -0,0 +1,57 @@
+/*
+ *	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; version 2
+ *	of the License.
+ *
+ */
+
+#include <linux/linkage.h>
+#include <asm/alternative-asm.h>
+#include <asm/frame.h>
+#include <asm/dwarf2.h>
+
+
+.text
+
+/*
+ * Inputs:
+ * %esi : memory location to compare
+ * %eax : low 32 bits of old value
+ * %edx : high 32 bits of old value
+ * %ebx : low 32 bits of new value
+ * %ecx : high 32 bits of new value
+ */
+ENTRY(cmpxchg8b_emu)
+CFI_STARTPROC
+
+#
+# Emulate 'cmpxchg8b (%esi)' on UP except we don't
+# set the whole ZF thing (caller will just compare
+# eax:edx with the expected value)
+#
+cmpxchg8b_emu:
+	pushfl
+	cli
+
+	cmpl  (%esi), %eax
+	jne not_same
+	cmpl 4(%esi), %edx
+	jne half_same
+
+	movl %ebx,  (%esi)
+	movl %ecx, 4(%esi)
+
+	popfl
+	ret
+
+ not_same:
+	movl  (%esi), %eax
+ half_same:
+	movl 4(%esi), %edx
+
+	popfl
+	ret
+
+CFI_ENDPROC
+ENDPROC(cmpxchg8b_emu)
diff --git a/kernel/sched_clock.c b/kernel/sched_clock.c
index ac2e1dc..479ce56 100644
--- a/kernel/sched_clock.c
+++ b/kernel/sched_clock.c
@@ -127,7 +127,7 @@ again:
 	clock = wrap_max(clock, min_clock);
 	clock = wrap_min(clock, max_clock);
 
-	if (cmpxchg(&scd->clock, old_clock, clock) != old_clock)
+	if (cmpxchg64(&scd->clock, old_clock, clock) != old_clock)
 		goto again;
 
 	return clock;
@@ -163,7 +163,7 @@ again:
 		val = remote_clock;
 	}
 
-	if (cmpxchg(ptr, old_val, val) != old_val)
+	if (cmpxchg64(ptr, old_val, val) != old_val)
 		goto again;
 
 	return val;