---
 include/asm-x86/current_64.h     |    2 
 include/asm-x86/pda.h            |   81 +++------------------------------------
 include/asm-x86/percpu.h         |    9 ++--
 include/asm-x86/thread_info_64.h |    2 
 4 files changed, 15 insertions(+), 79 deletions(-)

Index: linux-2.6/include/asm-x86/pda.h
===================================================================
--- linux-2.6.orig/include/asm-x86/pda.h	2007-11-24 23:31:37.433100882 -0800
+++ linux-2.6/include/asm-x86/pda.h	2007-11-24 23:45:49.213350568 -0800
@@ -42,85 +42,18 @@ extern struct x8664_pda *_cpu_pda[];
 
 #define cpu_pda(i) (_cpu_pda[i])
 
-/* 
- * There is no fast way to get the base address of the PDA, all the accesses
- * have to mention %fs/%gs.  So it needs to be done this Torvaldian way.
- */ 
-extern void __bad_pda_field(void) __attribute__((noreturn));
-
-/*
- * proxy_pda doesn't actually exist, but tell gcc it is accessed for
- * all PDA accesses so it gets read/write dependencies right.
- */
-extern struct x8664_pda _proxy_pda;
-
-#define pda_offset(field) offsetof(struct x8664_pda, field)
-
-#define pda_to_op(op,field,val) do {		\
-	typedef typeof(_proxy_pda.field) T__;	\
-	if (0) { T__ tmp__; tmp__ = (val); }	/* type checking */ \
-	switch (sizeof(_proxy_pda.field)) {	\
-	case 2:					\
-		asm(op "w %1,%%gs:%c2" : 	\
-		    "+m" (_proxy_pda.field) :	\
-		    "ri" ((T__)val),		\
-		    "i"(pda_offset(field))); 	\
- 		break;				\
-	case 4:					\
-		asm(op "l %1,%%gs:%c2" : 	\
-		    "+m" (_proxy_pda.field) :	\
-		    "ri" ((T__)val),		\
-		    "i" (pda_offset(field))); 	\
-		break;				\
-	case 8:					\
-		asm(op "q %1,%%gs:%c2": 	\
-		    "+m" (_proxy_pda.field) :	\
-		    "ri" ((T__)val),		\
-		    "i"(pda_offset(field))); 	\
-		break;				\
-       default: 				\
-		__bad_pda_field();		\
-       }					\
-       } while (0)
-
-#define pda_from_op(op,field) ({		\
-	typeof(_proxy_pda.field) ret__;		\
-	switch (sizeof(_proxy_pda.field)) {	\
-       	case 2:					\
-		asm(op "w %%gs:%c1,%0" : 	\
-		    "=r" (ret__) :		\
-		    "i" (pda_offset(field)), 	\
-		    "m" (_proxy_pda.field)); 	\
-		 break;				\
-	case 4:					\
-		asm(op "l %%gs:%c1,%0":		\
-		    "=r" (ret__):		\
-		    "i" (pda_offset(field)), 	\
-		    "m" (_proxy_pda.field)); 	\
-		 break;				\
-       case 8:					\
-		asm(op "q %%gs:%c1,%0":		\
-		    "=r" (ret__) :		\
-		    "i" (pda_offset(field)), 	\
-		    "m" (_proxy_pda.field)); 	\
-		 break;				\
-       default: 				\
-		__bad_pda_field();		\
-       }					\
-       ret__; })
-
-#define read_pda(field) pda_from_op("mov",field)
-#define write_pda(field,val) pda_to_op("mov",field,val)
-#define add_pda(field,val) pda_to_op("add",field,val)
-#define sub_pda(field,val) pda_to_op("sub",field,val)
-#define or_pda(field,val) pda_to_op("or",field,val)
+#define read_pda(field) x86_read_percpu(pda.field)
+#define write_pda(field,val) x86_write_percpu(pda.field,val)
+#define add_pda(field,val) x86_add_percpu(pda.field,val)
+#define sub_pda(field,val) x86_sub_percpu(pda.field,val)
+#define or_pda(field,val) x86_or_percpu(pda.field,val)
 
 /* This is not atomic against other CPUs -- CPU preemption needs to be off */
 #define test_and_clear_bit_pda(bit,field) ({		\
 	int old__;						\
 	asm volatile("btr %2,%%gs:%c3\n\tsbbl %0,%0"		\
-	    : "=r" (old__), "+m" (_proxy_pda.field) 		\
-	    : "dIr" (bit), "i" (pda_offset(field)) : "memory");	\
+	    : "=r" (old__), "+m" (&per_cpu__pda.field) 		\
+	    : "dIr" (bit), "i" (&per_cpu__pda.field)) : "memory");	\
 	old__;							\
 })
 
Index: linux-2.6/include/asm-x86/current_64.h
===================================================================
--- linux-2.6.orig/include/asm-x86/current_64.h	2007-11-24 23:39:02.180351232 -0800
+++ linux-2.6/include/asm-x86/current_64.h	2007-11-24 23:39:13.268350807 -0800
@@ -4,7 +4,7 @@
 #if !defined(__ASSEMBLY__) 
 struct task_struct;
 
-#include <asm/pda.h>
+#include <asm/percpu.h>
 
 static inline struct task_struct *get_current(void) 
 { 
Index: linux-2.6/include/asm-x86/percpu.h
===================================================================
--- linux-2.6.orig/include/asm-x86/percpu.h	2007-11-24 23:36:38.313350988 -0800
+++ linux-2.6/include/asm-x86/percpu.h	2007-11-24 23:43:03.115840885 -0800
@@ -11,6 +11,7 @@
 
 #ifdef CONFIG_SMP
 #include <asm/pda.h>
+#ifndef __ASSEMBLY__
 
 #define __per_cpu_offset(cpu) (cpu_pda(cpu)->data_offset)
 #define __my_cpu_offset read_pda(data_offset)
@@ -23,7 +24,7 @@
 #include <asm-generic/percpu.h>
 
 DECLARE_PER_CPU(struct x8664_pda, pda);
-
+#endif
 #else /* CONFIG_X86_64 */
 
 #ifdef __ASSEMBLY__
@@ -77,12 +78,14 @@ DECLARE_PER_CPU(struct x8664_pda, pda);
 #define __percpu_seg ""
 
 #endif	/* SMP */
-
 #include <asm-generic/percpu.h>
+#endif  /* ASSEMBLY */
+#endif /* !CONFIG_X86_64 */
 
+#ifndef __ASSEMBLY__
 /* We can use this directly for local CPU (faster). */
 DECLARE_PER_CPU(unsigned long, this_cpu_off);
-#endif
+
 
 /* For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though). */
Index: linux-2.6/include/asm-x86/thread_info_64.h
===================================================================
--- linux-2.6.orig/include/asm-x86/thread_info_64.h	2007-11-24 23:39:42.944350541 -0800
+++ linux-2.6/include/asm-x86/thread_info_64.h	2007-11-24 23:39:49.808600549 -0800
@@ -11,7 +11,7 @@
 
 #include <asm/page.h>
 #include <asm/types.h>
-#include <asm/pda.h>
+#include <asm/percpu.h>
 
 /*
  * low level task data that entry.S needs immediate access to