---
 arch/x86/include/asm/percpu.h |   63 +++++++++++++-----------------------------
 1 file changed, 20 insertions(+), 43 deletions(-)

Index: linux-2.6/arch/x86/include/asm/percpu.h
===================================================================
--- linux-2.6.orig/arch/x86/include/asm/percpu.h	2009-09-16 15:40:42.000000000 -0500
+++ linux-2.6/arch/x86/include/asm/percpu.h	2009-09-16 16:20:39.000000000 -0500
@@ -79,60 +79,25 @@ do {							\
 		T__ tmp__;				\
 		tmp__ = (val);				\
 	}						\
-	switch (sizeof(var)) {				\
-	case 1:						\
-		asm(op "b %1,"__percpu_arg(0)		\
+	asm(op " %1,"__percpu_arg(0)			\
 		    : "+m" (var)			\
 		    : "qi" ((T__)(val)));		\
-		break;					\
-	case 2:						\
-		asm(op "w %1,"__percpu_arg(0)		\
-		    : "+m" (var)			\
-		    : "ri" ((T__)(val)));		\
-		break;					\
-	case 4:						\
-		asm(op "l %1,"__percpu_arg(0)		\
-		    : "+m" (var)			\
-		    : "ri" ((T__)(val)));		\
-		break;					\
-	case 8:						\
-		asm(op "q %1,"__percpu_arg(0)		\
-		    : "+m" (var)			\
-		    : "re" ((T__)(val)));		\
-		break;					\
-	default: __bad_percpu_size();			\
-	}						\
 } while (0)
 
 #define percpu_from_op(op, var, constraint)		\
 ({							\
 	typeof(var) ret__;				\
-	switch (sizeof(var)) {				\
-	case 1:						\
-		asm(op "b "__percpu_arg(1)",%0"		\
+	asm(op " "__percpu_arg(1)",%0"			\
 		    : "=q" (ret__)			\
 		    : constraint);			\
-		break;					\
-	case 2:						\
-		asm(op "w "__percpu_arg(1)",%0"		\
-		    : "=r" (ret__)			\
-		    : constraint);			\
-		break;					\
-	case 4:						\
-		asm(op "l "__percpu_arg(1)",%0"		\
-		    : "=r" (ret__)			\
-		    : constraint);			\
-		break;					\
-	case 8:						\
-		asm(op "q "__percpu_arg(1)",%0"		\
-		    : "=r" (ret__)			\
-		    : constraint);			\
-		break;					\
-	default: __bad_percpu_size();			\
-	}						\
 	ret__;						\
 })
 
+#define __this_cpu_read(pcp)	__this_cpu_read_##sizeof(pcp)(pcp)
+#define __this_cpu_write(pcp, val)	__this_cpu_write_##sizeof(pcp)(pcp, val)
+#define __this_cpu_add(pcp, val)	__this_cpu_add_##sizeof(pcp)(pcp, val)
+
+
 /*
  * percpu_read() makes gcc load the percpu variable every time it is
  * accessed while percpu_read_stable() allows the value to be cached.
@@ -142,7 +107,13 @@ do {							\
  * per-thread variables implemented as per-cpu variables and thus
  * stable for the duration of the respective task.
  */
-#define percpu_read(var)	percpu_from_op("mov", per_cpu__##var,	\
+#define percpu_read_1(var)	percpu_from_op("movb", per_cpu__##var,	\
+					       "m" (per_cpu__##var))
+#define percpu_read_2(var)	percpu_from_op("movb", per_cpu__##var,	\
+					       "m" (per_cpu__##var))
+#define percpu_read_4(var)	percpu_from_op("movb", per_cpu__##var,	\
+					       "m" (per_cpu__##var))
+#define percpu_read_8(var)	generic_from_op(per_cpu__##var,	\
 					       "m" (per_cpu__##var))
 #define percpu_read_stable(var)	percpu_from_op("mov", per_cpu__##var,	\
 					       "p" (&per_cpu__##var))
@@ -161,6 +132,12 @@ do {							\
 #define __this_cpu_or(pcp, val)		percpu_to_op("or", (pcp), val)
 #define __this_cpu_xor(pcp, val)	percpu_to_op("xor", (pcp), val)
 
+#define __this_cpu_read(pcp)		__this_cpu_read##sizoef(pcp)(pcp)
+
+#define __this_cpu_read_1(pcp)		percpu_from_op("mov", "b", pcp)
+#define __this_cpu_read_2(pcp)		percpu_from_op("mov", "w", pcp)
+#define __this_cpu_read_4(pcp)		per_cpu_
+
 #define this_cpu_read(pcp)		percpu_from_op("mov", (pcp))
 #define this_cpu_write(pcp, val)	percpu_to_op("mov", (pcp), val)
 #define this_cpu_add(pcp, val)		percpu_to_op("add", (pcp), val)