7 files changed, 29 insertions, 110 deletions

diff --git a/include/asm-alpha/tlbflush.h b/include/asm-alpha/tlbflush.h
index eefab3fb51ae..b9e9147226f7 100644
--- a/include/asm-alpha/tlbflush.h
+++ b/include/asm-alpha/tlbflush.h
@@ -3,6 +3,7 @@
 
 #include <linux/mm.h>
 #include <asm/compiler.h>
+#include <asm/pgalloc.h>
 
 #ifndef __EXTERN_INLINE
 #define __EXTERN_INLINE extern inline
diff --git a/include/asm-ia64/percpu.h b/include/asm-ia64/percpu.h
index 0095bcf79848..77f30b664b4e 100644
--- a/include/asm-ia64/percpu.h
+++ b/include/asm-ia64/percpu.h
@@ -15,38 +15,20 @@
 
 #include <linux/threads.h>
 
+#ifdef CONFIG_SMP
+
 #ifdef HAVE_MODEL_SMALL_ATTRIBUTE
 # define PER_CPU_ATTRIBUTES     __attribute__((__model__ (__small__)))
 #endif
 
-#define DECLARE_PER_CPU(type, name)                             \
-        extern PER_CPU_ATTRIBUTES __typeof__(type) per_cpu__##name
-
-/*
- * Pretty much a literal copy of asm-generic/percpu.h, except that percpu_modcopy() is an
- * external routine, to avoid include-hell.
- */
-#ifdef CONFIG_SMP
-
-extern unsigned long __per_cpu_offset[NR_CPUS];
-#define per_cpu_offset(x) (__per_cpu_offset[x])
-
-/* Equal to __per_cpu_offset[smp_processor_id()], but faster to access: */
-DECLARE_PER_CPU(unsigned long, local_per_cpu_offset);
+#define __my_cpu_offset __ia64_per_cpu_var(local_per_cpu_offset)
 
-#define per_cpu(var, cpu)  (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset[cpu]))
-#define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __ia64_per_cpu_var(local_per_cpu_offset)))
-#define __raw_get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __ia64_per_cpu_var(local_per_cpu_offset)))
-
-extern void percpu_modcopy(void *pcpudst, const void *src, unsigned long size);
-extern void setup_per_cpu_areas (void);
 extern void *per_cpu_init(void);
 
 #else /* ! SMP */
 
-#define per_cpu(var, cpu)                       (*((void)(cpu), &per_cpu__##var))
-#define __get_cpu_var(var)                      per_cpu__##var
-#define __raw_get_cpu_var(var)                  per_cpu__##var
+#define PER_CPU_ATTRIBUTES      __attribute__((__section__(".data.percpu")))
+
 #define per_cpu_init()                          (__phys_per_cpu_start)
 
 #endif  /* SMP */
@@ -57,7 +39,12 @@ extern void *per_cpu_init(void);
  * On the positive side, using __ia64_per_cpu_var() instead of __get_cpu_var() is slightly
  * more efficient.
  */
-#define __ia64_per_cpu_var(var) (per_cpu__##var)
+#define __ia64_per_cpu_var(var) per_cpu__##var
+
+#include <asm-generic/percpu.h>
+
+/* Equal to __per_cpu_offset[smp_processor_id()], but faster to access: */
+DECLARE_PER_CPU(unsigned long, local_per_cpu_offset);
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/include/asm-powerpc/percpu.h b/include/asm-powerpc/percpu.h
index cc1cbf656b02..ccb0523eb3b4 100644
--- a/include/asm-powerpc/percpu.h
+++ b/include/asm-powerpc/percpu.h
@@ -13,37 +13,12 @@
 #include <asm/paca.h>
 
 #define __per_cpu_offset(cpu) (paca[cpu].data_offset)
-#define __my_cpu_offset() get_paca()->data_offset
+#define __my_cpu_offset get_paca()->data_offset
 #define per_cpu_offset(x) (__per_cpu_offset(x))
 
-/* var is in discarded region: offset to particular copy we want */
-#define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)))
-#define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __my_cpu_offset()))
-#define __raw_get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, local_paca->data_offset))
+#endif /* CONFIG_SMP */
+#endif /* __powerpc64__ */
 
-/* A macro to avoid #include hell... */
-#define percpu_modcopy(pcpudst, src, size)                      \
-do {                                                            \
-        unsigned int __i;                                       \
-        for_each_possible_cpu(__i)                              \
-                memcpy((pcpudst)+__per_cpu_offset(__i),         \
-                       (src), (size));                          \
-} while (0)
-
-extern void setup_per_cpu_areas(void);
-
-#else /* ! SMP */
-
-#define per_cpu(var, cpu)                       (*((void)(cpu), &per_cpu__##var))
-#define __get_cpu_var(var)                      per_cpu__##var
-#define __raw_get_cpu_var(var)                  per_cpu__##var
-
-#endif  /* SMP */
-
-#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
-
-#else
 #include <asm-generic/percpu.h>
-#endif
 
 #endif /* _ASM_POWERPC_PERCPU_H_ */
diff --git a/include/asm-s390/percpu.h b/include/asm-s390/percpu.h
index 2d676a873858..408d60b4f75b 100644
--- a/include/asm-s390/percpu.h
+++ b/include/asm-s390/percpu.h
@@ -13,49 +13,25 @@
  */
 #if defined(__s390x__) && defined(MODULE)
 
-#define __reloc_hide(var,offset) (*({                   \
+#define SHIFT_PERCPU_PTR(ptr,offset) (({                        \
         extern int simple_identifier_##var(void);       \
         unsigned long *__ptr;                           \
-        asm ( "larl %0,per_cpu__"#var"@GOTENT"          \
-            : "=a" (__ptr) : "X" (per_cpu__##var) );    \
-        (typeof(&per_cpu__##var))((*__ptr) + (offset)); }))
+        asm ( "larl %0, %1@GOTENT"              \
+            : "=a" (__ptr) : "X" (ptr) );               \
+        (typeof(ptr))((*__ptr) + (offset));     }))
 
 #else
 
-#define __reloc_hide(var, offset) (*({                          \
+#define SHIFT_PERCPU_PTR(ptr, offset) (({                               \
         extern int simple_identifier_##var(void);               \
         unsigned long __ptr;                                    \
-        asm ( "" : "=a" (__ptr) : "0" (&per_cpu__##var) );      \
-        (typeof(&per_cpu__##var)) (__ptr + (offset)); }))
+        asm ( "" : "=a" (__ptr) : "0" (ptr) );                  \
+        (typeof(ptr)) (__ptr + (offset)); }))
 
 #endif
 
-#ifdef CONFIG_SMP
+#define __my_cpu_offset S390_lowcore.percpu_offset
 
-extern unsigned long __per_cpu_offset[NR_CPUS];
-
-#define __get_cpu_var(var) __reloc_hide(var,S390_lowcore.percpu_offset)
-#define __raw_get_cpu_var(var) __reloc_hide(var,S390_lowcore.percpu_offset)
-#define per_cpu(var,cpu) __reloc_hide(var,__per_cpu_offset[cpu])
-#define per_cpu_offset(x) (__per_cpu_offset[x])
-
-/* A macro to avoid #include hell... */
-#define percpu_modcopy(pcpudst, src, size)                      \
-do {                                                            \
-        unsigned int __i;                                       \
-        for_each_possible_cpu(__i)                              \
-                memcpy((pcpudst)+__per_cpu_offset[__i],         \
-                       (src), (size));                          \
-} while (0)
-
-#else /* ! SMP */
-
-#define __get_cpu_var(var) __reloc_hide(var,0)
-#define __raw_get_cpu_var(var) __reloc_hide(var,0)
-#define per_cpu(var,cpu) __reloc_hide(var,0)
-
-#endif /* SMP */
-
-#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
+#include <asm-generic/percpu.h>
 
 #endif /* __ARCH_S390_PERCPU__ */
diff --git a/include/asm-sparc64/percpu.h b/include/asm-sparc64/percpu.h
index c7e52decba98..bee64593023e 100644
--- a/include/asm-sparc64/percpu.h
+++ b/include/asm-sparc64/percpu.h
@@ -7,7 +7,6 @@ register unsigned long __local_per_cpu_offset asm("g5");
 
 #ifdef CONFIG_SMP
 
-#define setup_per_cpu_areas()                   do { } while (0)
 extern void real_setup_per_cpu_areas(void);
 
 extern unsigned long __per_cpu_base;
@@ -16,29 +15,14 @@ extern unsigned long __per_cpu_shift;
         (__per_cpu_base + ((unsigned long)(__cpu) << __per_cpu_shift))
 #define per_cpu_offset(x) (__per_cpu_offset(x))
 
-/* var is in discarded region: offset to particular copy we want */
-#define per_cpu(var, cpu) (*RELOC_HIDE(&per_cpu__##var, __per_cpu_offset(cpu)))
-#define __get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __local_per_cpu_offset))
-#define __raw_get_cpu_var(var) (*RELOC_HIDE(&per_cpu__##var, __local_per_cpu_offset))
-
-/* A macro to avoid #include hell... */
-#define percpu_modcopy(pcpudst, src, size)                      \
-do {                                                            \
-        unsigned int __i;                                       \
-        for_each_possible_cpu(__i)                              \
-                memcpy((pcpudst)+__per_cpu_offset(__i),         \
-                       (src), (size));                          \
-} while (0)
+#define __my_cpu_offset __local_per_cpu_offset
+
 #else /* ! SMP */
 
 #define real_setup_per_cpu_areas()              do { } while (0)
 
-#define per_cpu(var, cpu)                       (*((void)cpu, &per_cpu__##var))
-#define __get_cpu_var(var)                      per_cpu__##var
-#define __raw_get_cpu_var(var)                  per_cpu__##var
-
 #endif  /* SMP */
 
-#define DECLARE_PER_CPU(type, name) extern __typeof__(type) per_cpu__##name
+#include <asm-generic/percpu.h>
 
 #endif /* __ARCH_SPARC64_PERCPU__ */
diff --git a/include/asm-x86/thread_info_64.h b/include/asm-x86/thread_info_64.h
index 9b531ea015a8..6c9b214b8fc3 100644
--- a/include/asm-x86/thread_info_64.h
+++ b/include/asm-x86/thread_info_64.h
@@ -123,8 +123,8 @@ static inline struct thread_info *stack_thread_info(void)
 #define TIF_FREEZE              23      /* is freezing for suspend */
 #define TIF_FORCED_TF           24      /* true if TF in eflags artificially */
 #define TIF_DEBUGCTLMSR         25      /* uses thread_struct.debugctlmsr */
-#define TIF_DS_AREA_MSR 25      /* uses thread_struct.ds_area_msr */
-#define TIF_BTS_TRACE_TS        26      /* record scheduling event timestamps */
+#define TIF_DS_AREA_MSR         26      /* uses thread_struct.ds_area_msr */
+#define TIF_BTS_TRACE_TS        27      /* record scheduling event timestamps */
 
 #define _TIF_SYSCALL_TRACE      (1<<TIF_SYSCALL_TRACE)
 #define _TIF_SIGPENDING         (1<<TIF_SIGPENDING)
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 00412bb494c4..50faa0ea28e4 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -9,10 +9,6 @@
 
 #include <asm/percpu.h>
 
-#ifndef PER_CPU_ATTRIBUTES
-#define PER_CPU_ATTRIBUTES
-#endif
-
 #ifdef CONFIG_SMP
 #define DEFINE_PER_CPU(type, name)                                      \
         __attribute__((__section__(".data.percpu")))                    \