Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (34 commits)
  m68k: rename global variable vmalloc_end to m68k_vmalloc_end
  percpu: add missing per_cpu_ptr_to_phys() definition for UP
  percpu: Fix kdump failure if booted with percpu_alloc=page
  percpu: make misc percpu symbols unique
  percpu: make percpu symbols in ia64 unique
  percpu: make percpu symbols in powerpc unique
  percpu: make percpu symbols in x86 unique
  percpu: make percpu symbols in xen unique
  percpu: make percpu symbols in cpufreq unique
  percpu: make percpu symbols in oprofile unique
  percpu: make percpu symbols in tracer unique
  percpu: make percpu symbols under kernel/ and mm/ unique
  percpu: remove some sparse warnings
  percpu: make alloc_percpu() handle array types
  vmalloc: fix use of non-existent percpu variable in put_cpu_var()
  this_cpu: Use this_cpu_xx in trace_functions_graph.c
  this_cpu: Use this_cpu_xx for ftrace
  this_cpu: Use this_cpu_xx in nmi handling
  this_cpu: Use this_cpu operations in RCU
  this_cpu: Use this_cpu ops for VM statistics
  ...

Fix up trivial (famous last words) global per-cpu naming conflicts in
	arch/x86/kvm/svm.c
	mm/slab.c

7 files changed, 439 insertions, 72 deletions

diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 90079c373f1..8087b90d467 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -56,6 +56,9 @@ extern unsigned long __per_cpu_offset[NR_CPUS];
 #define __raw_get_cpu_var(var) \
 	(*SHIFT_PERCPU_PTR(&per_cpu_var(var), __my_cpu_offset))
 
+#define this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, my_cpu_offset)
+#define __this_cpu_ptr(ptr) SHIFT_PERCPU_PTR(ptr, __my_cpu_offset)
+
 
 #ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
 extern void setup_per_cpu_areas(void);
@@ -66,6 +69,8 @@ extern void setup_per_cpu_areas(void);
 #define per_cpu(var, cpu)			(*((void)(cpu), &per_cpu_var(var)))
 #define __get_cpu_var(var)			per_cpu_var(var)
 #define __raw_get_cpu_var(var)			per_cpu_var(var)
+#define this_cpu_ptr(ptr) per_cpu_ptr(ptr, 0)
+#define __this_cpu_ptr(ptr) this_cpu_ptr(ptr)
 
 #endif	/* SMP */
 
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 9bd03193ecd..5a5d6ce4bd5 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -60,6 +60,7 @@
 
 #define DEFINE_PER_CPU_SECTION(type, name, sec)				\
 	__PCPU_DUMMY_ATTRS char __pcpu_scope_##name;			\
+	extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name;		\
 	__PCPU_DUMMY_ATTRS char __pcpu_unique_##name;			\
 	__PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak			\
 	__typeof__(type) per_cpu__##name
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 878836ca999..cf5efbcf716 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -34,8 +34,6 @@
 
 #ifdef CONFIG_SMP
 
-#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
-
 /* minimum unit size, also is the maximum supported allocation size */
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(64 << 10)
 
@@ -130,30 +128,9 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size,
 #define per_cpu_ptr(ptr, cpu)	SHIFT_PERCPU_PTR((ptr), per_cpu_offset((cpu)))
 
 extern void *__alloc_reserved_percpu(size_t size, size_t align);
-
-#else /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
-struct percpu_data {
-	void *ptrs[1];
-};
-
-/* pointer disguising messes up the kmemleak objects tracking */
-#ifndef CONFIG_DEBUG_KMEMLEAK
-#define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
-#else
-#define __percpu_disguise(pdata) (struct percpu_data *)(pdata)
-#endif
-
-#define per_cpu_ptr(ptr, cpu)						\
-({									\
-        struct percpu_data *__p = __percpu_disguise(ptr);		\
-        (__typeof__(ptr))__p->ptrs[(cpu)];				\
-})
-
-#endif /* CONFIG_HAVE_LEGACY_PER_CPU_AREA */
-
 extern void *__alloc_percpu(size_t size, size_t align);
 extern void free_percpu(void *__pdata);
+extern phys_addr_t per_cpu_ptr_to_phys(void *addr);
 
 #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
 extern void __init setup_per_cpu_areas(void);
@@ -179,6 +156,11 @@ static inline void free_percpu(void *p)
 	kfree(p);
 }
 
+static inline phys_addr_t per_cpu_ptr_to_phys(void *addr)
+{
+	return __pa(addr);
+}
+
 static inline void __init setup_per_cpu_areas(void) { }
 
 static inline void *pcpu_lpage_remapped(void *kaddr)
@@ -188,8 +170,8 @@ static inline void *pcpu_lpage_remapped(void *kaddr)
 
 #endif /* CONFIG_SMP */
 
-#define alloc_percpu(type)	(type *)__alloc_percpu(sizeof(type), \
-						       __alignof__(type))
+#define alloc_percpu(type)	\
+	(typeof(type) *)__alloc_percpu(sizeof(type), __alignof__(type))
 
 /*
  * Optional methods for optimized non-lvalue per-cpu variable access.
@@ -243,4 +225,404 @@ do {									\
 # define percpu_xor(var, val)		__percpu_generic_to_op(var, (val), ^=)
 #endif
 
+/*
+ * Branching function to split up a function into a set of functions that
+ * are called for different scalar sizes of the objects handled.
+ */
+
+extern void __bad_size_call_parameter(void);
+
+#define __pcpu_size_call_return(stem, variable)				\
+({	typeof(variable) pscr_ret__;					\
+	switch(sizeof(variable)) {					\
+	case 1: pscr_ret__ = stem##1(variable);break;			\
+	case 2: pscr_ret__ = stem##2(variable);break;			\
+	case 4: pscr_ret__ = stem##4(variable);break;			\
+	case 8: pscr_ret__ = stem##8(variable);break;			\
+	default:							\
+		__bad_size_call_parameter();break;			\
+	}								\
+	pscr_ret__;							\
+})
+
+#define __pcpu_size_call(stem, variable, ...)				\
+do {									\
+	switch(sizeof(variable)) {					\
+		case 1: stem##1(variable, __VA_ARGS__);break;		\
+		case 2: stem##2(variable, __VA_ARGS__);break;		\
+		case 4: stem##4(variable, __VA_ARGS__);break;		\
+		case 8: stem##8(variable, __VA_ARGS__);break;		\
+		default: 						\
+			__bad_size_call_parameter();break;		\
+	}								\
+} while (0)
+
+/*
+ * Optimized manipulation for memory allocated through the per cpu
+ * allocator or for addresses of per cpu variables (can be determined
+ * using per_cpu_var(xx).
+ *
+ * These operation guarantee exclusivity of access for other operations
+ * on the *same* processor. The assumption is that per cpu data is only
+ * accessed by a single processor instance (the current one).
+ *
+ * The first group is used for accesses that must be done in a
+ * preemption safe way since we know that the context is not preempt
+ * safe. Interrupts may occur. If the interrupt modifies the variable
+ * too then RMW actions will not be reliable.
+ *
+ * The arch code can provide optimized functions in two ways:
+ *
+ * 1. Override the function completely. F.e. define this_cpu_add().
+ *    The arch must then ensure that the various scalar format passed
+ *    are handled correctly.
+ *
+ * 2. Provide functions for certain scalar sizes. F.e. provide
+ *    this_cpu_add_2() to provide per cpu atomic operations for 2 byte
+ *    sized RMW actions. If arch code does not provide operations for
+ *    a scalar size then the fallback in the generic code will be
+ *    used.
+ */
+
+#define _this_cpu_generic_read(pcp)					\
+({	typeof(pcp) ret__;						\
+	preempt_disable();						\
+	ret__ = *this_cpu_ptr(&(pcp));					\
+	preempt_enable();						\
+	ret__;								\
+})
+
+#ifndef this_cpu_read
+# ifndef this_cpu_read_1
+#  define this_cpu_read_1(pcp)	_this_cpu_generic_read(pcp)
+# endif
+# ifndef this_cpu_read_2
+#  define this_cpu_read_2(pcp)	_this_cpu_generic_read(pcp)
+# endif
+# ifndef this_cpu_read_4
+#  define this_cpu_read_4(pcp)	_this_cpu_generic_read(pcp)
+# endif
+# ifndef this_cpu_read_8
+#  define this_cpu_read_8(pcp)	_this_cpu_generic_read(pcp)
+# endif
+# define this_cpu_read(pcp)	__pcpu_size_call_return(this_cpu_read_, (pcp))
+#endif
+
+#define _this_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	preempt_disable();						\
+	*__this_cpu_ptr(&pcp) op val;					\
+	preempt_enable();						\
+} while (0)
+
+#ifndef this_cpu_write
+# ifndef this_cpu_write_1
+#  define this_cpu_write_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef this_cpu_write_2
+#  define this_cpu_write_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef this_cpu_write_4
+#  define this_cpu_write_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef this_cpu_write_8
+#  define this_cpu_write_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# define this_cpu_write(pcp, val)	__pcpu_size_call(this_cpu_write_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_add
+# ifndef this_cpu_add_1
+#  define this_cpu_add_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef this_cpu_add_2
+#  define this_cpu_add_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef this_cpu_add_4
+#  define this_cpu_add_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef this_cpu_add_8
+#  define this_cpu_add_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# define this_cpu_add(pcp, val)		__pcpu_size_call(this_cpu_add_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_sub
+# define this_cpu_sub(pcp, val)		this_cpu_add((pcp), -(val))
+#endif
+
+#ifndef this_cpu_inc
+# define this_cpu_inc(pcp)		this_cpu_add((pcp), 1)
+#endif
+
+#ifndef this_cpu_dec
+# define this_cpu_dec(pcp)		this_cpu_sub((pcp), 1)
+#endif
+
+#ifndef this_cpu_and
+# ifndef this_cpu_and_1
+#  define this_cpu_and_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef this_cpu_and_2
+#  define this_cpu_and_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef this_cpu_and_4
+#  define this_cpu_and_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef this_cpu_and_8
+#  define this_cpu_and_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# define this_cpu_and(pcp, val)		__pcpu_size_call(this_cpu_and_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_or
+# ifndef this_cpu_or_1
+#  define this_cpu_or_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef this_cpu_or_2
+#  define this_cpu_or_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef this_cpu_or_4
+#  define this_cpu_or_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef this_cpu_or_8
+#  define this_cpu_or_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# define this_cpu_or(pcp, val)		__pcpu_size_call(this_cpu_or_, (pcp), (val))
+#endif
+
+#ifndef this_cpu_xor
+# ifndef this_cpu_xor_1
+#  define this_cpu_xor_1(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef this_cpu_xor_2
+#  define this_cpu_xor_2(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef this_cpu_xor_4
+#  define this_cpu_xor_4(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef this_cpu_xor_8
+#  define this_cpu_xor_8(pcp, val)	_this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# define this_cpu_xor(pcp, val)		__pcpu_size_call(this_cpu_or_, (pcp), (val))
+#endif
+
+/*
+ * Generic percpu operations that do not require preemption handling.
+ * Either we do not care about races or the caller has the
+ * responsibility of handling preemptions issues. Arch code can still
+ * override these instructions since the arch per cpu code may be more
+ * efficient and may actually get race freeness for free (that is the
+ * case for x86 for example).
+ *
+ * If there is no other protection through preempt disable and/or
+ * disabling interupts then one of these RMW operations can show unexpected
+ * behavior because the execution thread was rescheduled on another processor
+ * or an interrupt occurred and the same percpu variable was modified from
+ * the interrupt context.
+ */
+#ifndef __this_cpu_read
+# ifndef __this_cpu_read_1
+#  define __this_cpu_read_1(pcp)	(*__this_cpu_ptr(&(pcp)))
+# endif
+# ifndef __this_cpu_read_2
+#  define __this_cpu_read_2(pcp)	(*__this_cpu_ptr(&(pcp)))
+# endif
+# ifndef __this_cpu_read_4
+#  define __this_cpu_read_4(pcp)	(*__this_cpu_ptr(&(pcp)))
+# endif
+# ifndef __this_cpu_read_8
+#  define __this_cpu_read_8(pcp)	(*__this_cpu_ptr(&(pcp)))
+# endif
+# define __this_cpu_read(pcp)	__pcpu_size_call_return(__this_cpu_read_, (pcp))
+#endif
+
+#define __this_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	*__this_cpu_ptr(&(pcp)) op val;					\
+} while (0)
+
+#ifndef __this_cpu_write
+# ifndef __this_cpu_write_1
+#  define __this_cpu_write_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef __this_cpu_write_2
+#  define __this_cpu_write_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef __this_cpu_write_4
+#  define __this_cpu_write_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# ifndef __this_cpu_write_8
+#  define __this_cpu_write_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), =)
+# endif
+# define __this_cpu_write(pcp, val)	__pcpu_size_call(__this_cpu_write_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_add
+# ifndef __this_cpu_add_1
+#  define __this_cpu_add_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef __this_cpu_add_2
+#  define __this_cpu_add_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef __this_cpu_add_4
+#  define __this_cpu_add_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef __this_cpu_add_8
+#  define __this_cpu_add_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# define __this_cpu_add(pcp, val)	__pcpu_size_call(__this_cpu_add_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_sub
+# define __this_cpu_sub(pcp, val)	__this_cpu_add((pcp), -(val))
+#endif
+
+#ifndef __this_cpu_inc
+# define __this_cpu_inc(pcp)		__this_cpu_add((pcp), 1)
+#endif
+
+#ifndef __this_cpu_dec
+# define __this_cpu_dec(pcp)		__this_cpu_sub((pcp), 1)
+#endif
+
+#ifndef __this_cpu_and
+# ifndef __this_cpu_and_1
+#  define __this_cpu_and_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef __this_cpu_and_2
+#  define __this_cpu_and_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef __this_cpu_and_4
+#  define __this_cpu_and_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef __this_cpu_and_8
+#  define __this_cpu_and_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# define __this_cpu_and(pcp, val)	__pcpu_size_call(__this_cpu_and_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_or
+# ifndef __this_cpu_or_1
+#  define __this_cpu_or_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef __this_cpu_or_2
+#  define __this_cpu_or_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef __this_cpu_or_4
+#  define __this_cpu_or_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef __this_cpu_or_8
+#  define __this_cpu_or_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# define __this_cpu_or(pcp, val)	__pcpu_size_call(__this_cpu_or_, (pcp), (val))
+#endif
+
+#ifndef __this_cpu_xor
+# ifndef __this_cpu_xor_1
+#  define __this_cpu_xor_1(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef __this_cpu_xor_2
+#  define __this_cpu_xor_2(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef __this_cpu_xor_4
+#  define __this_cpu_xor_4(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef __this_cpu_xor_8
+#  define __this_cpu_xor_8(pcp, val)	__this_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# define __this_cpu_xor(pcp, val)	__pcpu_size_call(__this_cpu_xor_, (pcp), (val))
+#endif
+
+/*
+ * IRQ safe versions of the per cpu RMW operations. Note that these operations
+ * are *not* safe against modification of the same variable from another
+ * processors (which one gets when using regular atomic operations)
+ . They are guaranteed to be atomic vs. local interrupts and
+ * preemption only.
+ */
+#define irqsafe_cpu_generic_to_op(pcp, val, op)				\
+do {									\
+	unsigned long flags;						\
+	local_irq_save(flags);						\
+	*__this_cpu_ptr(&(pcp)) op val;					\
+	local_irq_restore(flags);					\
+} while (0)
+
+#ifndef irqsafe_cpu_add
+# ifndef irqsafe_cpu_add_1
+#  define irqsafe_cpu_add_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef irqsafe_cpu_add_2
+#  define irqsafe_cpu_add_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef irqsafe_cpu_add_4
+#  define irqsafe_cpu_add_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# ifndef irqsafe_cpu_add_8
+#  define irqsafe_cpu_add_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
+# endif
+# define irqsafe_cpu_add(pcp, val) __pcpu_size_call(irqsafe_cpu_add_, (pcp), (val))
+#endif
+
+#ifndef irqsafe_cpu_sub
+# define irqsafe_cpu_sub(pcp, val)	irqsafe_cpu_add((pcp), -(val))
+#endif
+
+#ifndef irqsafe_cpu_inc
+# define irqsafe_cpu_inc(pcp)	irqsafe_cpu_add((pcp), 1)
+#endif
+
+#ifndef irqsafe_cpu_dec
+# define irqsafe_cpu_dec(pcp)	irqsafe_cpu_sub((pcp), 1)
+#endif
+
+#ifndef irqsafe_cpu_and
+# ifndef irqsafe_cpu_and_1
+#  define irqsafe_cpu_and_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef irqsafe_cpu_and_2
+#  define irqsafe_cpu_and_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef irqsafe_cpu_and_4
+#  define irqsafe_cpu_and_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# ifndef irqsafe_cpu_and_8
+#  define irqsafe_cpu_and_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
+# endif
+# define irqsafe_cpu_and(pcp, val) __pcpu_size_call(irqsafe_cpu_and_, (val))
+#endif
+
+#ifndef irqsafe_cpu_or
+# ifndef irqsafe_cpu_or_1
+#  define irqsafe_cpu_or_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef irqsafe_cpu_or_2
+#  define irqsafe_cpu_or_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef irqsafe_cpu_or_4
+#  define irqsafe_cpu_or_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# ifndef irqsafe_cpu_or_8
+#  define irqsafe_cpu_or_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
+# endif
+# define irqsafe_cpu_or(pcp, val) __pcpu_size_call(irqsafe_cpu_or_, (val))
+#endif
+
+#ifndef irqsafe_cpu_xor
+# ifndef irqsafe_cpu_xor_1
+#  define irqsafe_cpu_xor_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef irqsafe_cpu_xor_2
+#  define irqsafe_cpu_xor_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef irqsafe_cpu_xor_4
+#  define irqsafe_cpu_xor_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# ifndef irqsafe_cpu_xor_8
+#  define irqsafe_cpu_xor_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
+# endif
+# define irqsafe_cpu_xor(pcp, val) __pcpu_size_call(irqsafe_cpu_xor_, (val))
+#endif
+
 #endif /* __LINUX_PERCPU_H */
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 2d0f222388a..d85889710f9 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -76,24 +76,22 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
 
 static inline void __count_vm_event(enum vm_event_item item)
 {
-	__get_cpu_var(vm_event_states).event[item]++;
+	__this_cpu_inc(per_cpu_var(vm_event_states).event[item]);
 }
 
 static inline void count_vm_event(enum vm_event_item item)
 {
-	get_cpu_var(vm_event_states).event[item]++;
-	put_cpu();
+	this_cpu_inc(per_cpu_var(vm_event_states).event[item]);
 }
 
 static inline void __count_vm_events(enum vm_event_item item, long delta)
 {
-	__get_cpu_var(vm_event_states).event[item] += delta;
+	__this_cpu_add(per_cpu_var(vm_event_states).event[item], delta);
 }
 
 static inline void count_vm_events(enum vm_event_item item, long delta)
 {
-	get_cpu_var(vm_event_states).event[item] += delta;
-	put_cpu();
+	this_cpu_add(per_cpu_var(vm_event_states).event[item], delta);
 }
 
 extern void all_vm_events(unsigned long *);
diff --git a/include/net/neighbour.h b/include/net/neighbour.h
index 0302f31a2fb..b0173202cad 100644
--- a/include/net/neighbour.h
+++ b/include/net/neighbour.h
@@ -88,12 +88,7 @@ struct neigh_statistics {
 	unsigned long unres_discards;	/* number of unresolved drops */
 };
 
-#define NEIGH_CACHE_STAT_INC(tbl, field)				\
-	do {								\
-		preempt_disable();					\
-		(per_cpu_ptr((tbl)->stats, smp_processor_id())->field)++; \
-		preempt_enable();					\
-	} while (0)
+#define NEIGH_CACHE_STAT_INC(tbl, field) this_cpu_inc((tbl)->stats->field)
 
 struct neighbour {
 	struct neighbour	*next;
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 5cf7270e3ff..a0904adfb8f 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -293,11 +293,11 @@ extern unsigned int nf_conntrack_htable_size;
 extern unsigned int nf_conntrack_max;
 
 #define NF_CT_STAT_INC(net, count)	\
-	(per_cpu_ptr((net)->ct.stat, raw_smp_processor_id())->count++)
+	__this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count)		\
 do {							\
 	local_bh_disable();				\
-	per_cpu_ptr((net)->ct.stat, raw_smp_processor_id())->count++;	\
+	__this_cpu_inc((net)->ct.stat->count);		\
 	local_bh_enable();				\
 } while (0)
 
diff --git a/include/net/snmp.h b/include/net/snmp.h
index 8c842e06bec..f0d756f2ac9 100644
--- a/include/net/snmp.h
+++ b/include/net/snmp.h
@@ -136,45 +136,31 @@ struct linux_xfrm_mib {
 #define SNMP_STAT_BHPTR(name)	(name[0])
 #define SNMP_STAT_USRPTR(name)	(name[1])
 
-#define SNMP_INC_STATS_BH(mib, field) 	\
-	(per_cpu_ptr(mib[0], raw_smp_processor_id())->mibs[field]++)
-#define SNMP_INC_STATS_USER(mib, field) \
-	do { \
-		per_cpu_ptr(mib[1], get_cpu())->mibs[field]++; \
-		put_cpu(); \
-	} while (0)
-#define SNMP_INC_STATS(mib, field) 	\
-	do { \
-		per_cpu_ptr(mib[!in_softirq()], get_cpu())->mibs[field]++; \
-		put_cpu(); \
-	} while (0)
-#define SNMP_DEC_STATS(mib, field) 	\
-	do { \
-		per_cpu_ptr(mib[!in_softirq()], get_cpu())->mibs[field]--; \
-		put_cpu(); \
-	} while (0)
-#define SNMP_ADD_STATS(mib, field, addend) 	\
-	do { \
-		per_cpu_ptr(mib[!in_softirq()], get_cpu())->mibs[field] += addend; \
-		put_cpu(); \
-	} while (0)
-#define SNMP_ADD_STATS_BH(mib, field, addend) 	\
-	(per_cpu_ptr(mib[0], raw_smp_processor_id())->mibs[field] += addend)
-#define SNMP_ADD_STATS_USER(mib, field, addend) 	\
-	do { \
-		per_cpu_ptr(mib[1], get_cpu())->mibs[field] += addend; \
-		put_cpu(); \
-	} while (0)
+#define SNMP_INC_STATS_BH(mib, field)	\
+			__this_cpu_inc(mib[0]->mibs[field])
+#define SNMP_INC_STATS_USER(mib, field)	\
+			this_cpu_inc(mib[1]->mibs[field])
+#define SNMP_INC_STATS(mib, field)	\
+			this_cpu_inc(mib[!in_softirq()]->mibs[field])
+#define SNMP_DEC_STATS(mib, field)	\
+			this_cpu_dec(mib[!in_softirq()]->mibs[field])
+#define SNMP_ADD_STATS_BH(mib, field, addend)	\
+			__this_cpu_add(mib[0]->mibs[field], addend)
+#define SNMP_ADD_STATS_USER(mib, field, addend)	\
+			this_cpu_add(mib[1]->mibs[field], addend)
 #define SNMP_UPD_PO_STATS(mib, basefield, addend)	\
 	do { \
-		__typeof__(mib[0]) ptr = per_cpu_ptr(mib[!in_softirq()], get_cpu());\
+		__typeof__(mib[0]) ptr; \
+		preempt_disable(); \
+		ptr = this_cpu_ptr((mib)[!in_softirq()]); \
 		ptr->mibs[basefield##PKTS]++; \
 		ptr->mibs[basefield##OCTETS] += addend;\
-		put_cpu(); \
+		preempt_enable(); \
 	} while (0)
 #define SNMP_UPD_PO_STATS_BH(mib, basefield, addend)	\
 	do { \
-		__typeof__(mib[0]) ptr = per_cpu_ptr(mib[!in_softirq()], raw_smp_processor_id());\
+		__typeof__(mib[0]) ptr = \
+			__this_cpu_ptr((mib)[!in_softirq()]); \
 		ptr->mibs[basefield##PKTS]++; \
 		ptr->mibs[basefield##OCTETS] += addend;\
 	} while (0)