[cpuops cmpxchg V2 5/5] cpuops: Use cmpxchg for xchg to avoid lock semantics

[Christoph Lameter <cl@linux.com>]

[-- Attachment #1: cpuops_xchg_with_cmpxchg --]
[-- Type: text/plain, Size: 2614 bytes --]

Use cmpxchg instead of xchg to realize this_cpu_xchg.

xchg will cause LOCK overhead since LOCK is always implied but cmpxchg
will not.

Baselines:

xchg()		= 18 cycles (no segment prefix, LOCK semantics)
__this_cpu_xchg = 1 cycle

(simulated using this_cpu_read/write, two prefixes. Looks like the
cpu can use loop optimization to get rid of most of the overhead)

Cycles before:

this_cpu_xchg	 = 37 cycles (segment prefix and LOCK (implied by xchg))

After:

this_cpu_xchg	= 11 cycle (using cmpxchg without lock semantics)

Signed-off-by: Christoph Lameter <cl@linux.com>

---
 arch/x86/include/asm/percpu.h |   21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

Index: linux-2.6/arch/x86/include/asm/percpu.h
===================================================================
--- linux-2.6.orig/arch/x86/include/asm/percpu.h	2010-12-10 12:46:31.000000000 -0600
+++ linux-2.6/arch/x86/include/asm/percpu.h	2010-12-10 13:25:21.000000000 -0600
@@ -213,8 +213,9 @@ do {									\
 })
 
 /*
- * Beware: xchg on x86 has an implied lock prefix. There will be the cost of
- * full lock semantics even though they are not needed.
+ * xchg is implemented using cmpxchg without a lock prefix. xchg is
+ * expensive due to the implied lock prefix. The processor cannot prefetch
+ * cachelines if xchg is used.
  */
 #define percpu_xchg_op(var, nval)					\
 ({									\
@@ -222,25 +223,33 @@ do {									\
 	typeof(var) __new = (nval);					\
 	switch (sizeof(var)) {						\
 	case 1:								\
-		asm("xchgb %2, "__percpu_arg(1)			\
+		asm("\n1:mov "__percpu_arg(1)",%%al"			\
+		    "\n\tcmpxchgb %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
 			    : "=a" (__ret), "+m" (var)			\
 			    : "q" (__new)				\
 			    : "memory");				\
 		break;							\
 	case 2:								\
-		asm("xchgw %2, "__percpu_arg(1)			\
+		asm("\n1:mov "__percpu_arg(1)",%%ax"			\
+		    "\n\tcmpxchgw %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
 			    : "=a" (__ret), "+m" (var)			\
 			    : "r" (__new)				\
 			    : "memory");				\
 		break;							\
 	case 4:								\
-		asm("xchgl %2, "__percpu_arg(1)			\
+		asm("\n1:mov "__percpu_arg(1)",%%eax"			\
+		    "\n\tcmpxchgl %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
 			    : "=a" (__ret), "+m" (var)			\
 			    : "r" (__new)				\
 			    : "memory");				\
 		break;							\
 	case 8:								\
-		asm("xchgq %2, "__percpu_arg(1)			\
+		asm("\n1:mov "__percpu_arg(1)",%%rax"			\
+		    "\n\tcmpxchgq %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
 			    : "=a" (__ret), "+m" (var)			\
 			    : "r" (__new)				\
 			    : "memory");				\