Merge remote branch 'percpu/for-next'

Conflicts:
	arch/x86/kvm/svm.c
	mm/slab.c

4 files changed, 464 insertions, 61 deletions

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 5be3dab4a695..a5a472b10746 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -5,7 +5,7 @@
 
 #ifdef __CHECKER__
 # define __user		__attribute__((noderef, address_space(1)))
-# define __kernel	/* default address space */
+# define __kernel	__attribute__((address_space(0)))
 # define __safe		__attribute__((safe))
 # define __force	__attribute__((force))
 # define __nocast	__attribute__((nocast))
@@ -15,6 +15,7 @@
 # define __acquire(x)	__context__(x,1)
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
+# define __percpu	__attribute__((noderef, address_space(3)))
 extern void __chk_user_ptr(const volatile void __user *);
 extern void __chk_io_ptr(const volatile void __iomem *);
 #else
@@ -32,6 +33,7 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # define __acquire(x) (void)0
 # define __release(x) (void)0
 # define __cond_lock(x,c) (c)
+# define __percpu
 #endif
 
 #ifdef __KERNEL__
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 9bd03193ecd4..68567c0b3a5d 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -2,12 +2,6 @@
 #define _LINUX_PERCPU_DEFS_H
 
 /*
- * Determine the real variable name from the name visible in the
- * kernel sources.
- */
-#define per_cpu_var(var) per_cpu__##var
-
-/*
  * Base implementations of per-CPU variable declarations and definitions, where
  * the section in which the variable is to be placed is provided by the
  * 'sec' argument.  This may be used to affect the parameters governing the
@@ -18,13 +12,23 @@
  * that section.
  */
 #define __PCPU_ATTRS(sec)						\
-	__attribute__((section(PER_CPU_BASE_SECTION sec)))		\
+	__percpu __attribute__((section(PER_CPU_BASE_SECTION sec)))	\
 	PER_CPU_ATTRIBUTES
 
 #define __PCPU_DUMMY_ATTRS						\
 	__attribute__((section(".discard"), unused))
 
 /*
+ * Macro which verifies @ptr is a percpu pointer without evaluating
+ * @ptr.  This is to be used in percpu accessors to verify that the
+ * input parameter is a percpu pointer.
+ */
+#define __verify_pcpu_ptr(ptr)	do {					\
+	const void __percpu *__vpp_verify = (typeof(ptr))NULL;		\
+	(void)__vpp_verify;						\
+} while (0)
+
+/*
  * s390 and alpha modules require percpu variables to be defined as
  * weak to force the compiler to generate GOT based external
  * references for them.  This is necessary because percpu sections
@@ -56,23 +60,24 @@
  */
 #define DECLARE_PER_CPU_SECTION(type, name, sec)			\
 	extern __PCPU_DUMMY_ATTRS char __pcpu_scope_##name;		\
-	extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name
+	extern __PCPU_ATTRS(sec) __typeof__(type) name
 
 #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
+	__typeof__(type) name
 #else
 /*
  * Normal declaration and definition macros.
  */
 #define DECLARE_PER_CPU_SECTION(type, name, sec)			\
-	extern __PCPU_ATTRS(sec) __typeof__(type) per_cpu__##name
+	extern __PCPU_ATTRS(sec) __typeof__(type) name
 
 #define DEFINE_PER_CPU_SECTION(type, name, sec)				\
 	__PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES			\
-	__typeof__(type) per_cpu__##name
+	__typeof__(type) name
 #endif
 
 /*
@@ -134,10 +139,16 @@
 	__aligned(PAGE_SIZE)
 
 /*
- * Intermodule exports for per-CPU variables.
+ * Intermodule exports for per-CPU variables.  sparse forgets about
+ * address space across EXPORT_SYMBOL(), change EXPORT_SYMBOL() to
+ * noop if __CHECKER__.
  */
-#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(per_cpu__##var)
-#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(per_cpu__##var)
-
+#ifndef __CHECKER__
+#define EXPORT_PER_CPU_SYMBOL(var) EXPORT_SYMBOL(var)
+#define EXPORT_PER_CPU_SYMBOL_GPL(var) EXPORT_SYMBOL_GPL(var)
+#else
+#define EXPORT_PER_CPU_SYMBOL(var)
+#define EXPORT_PER_CPU_SYMBOL_GPL(var)
+#endif
 
 #endif /* _LINUX_PERCPU_DEFS_H */
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 878836ca999c..a93e5bfdccb8 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -27,14 +27,19 @@
  * we force a syntax error here if it isn't.
  */
 #define get_cpu_var(var) (*({				\
-	extern int simple_identifier_##var(void);	\
 	preempt_disable();				\
 	&__get_cpu_var(var); }))
-#define put_cpu_var(var) preempt_enable()
 
-#ifdef CONFIG_SMP
+/*
+ * The weird & is necessary because sparse considers (void)(var) to be
+ * a direct dereference of percpu variable (var).
+ */
+#define put_cpu_var(var) do {				\
+	(void)&(var);					\
+	preempt_enable();				\
+} while (0)
 
-#ifndef CONFIG_HAVE_LEGACY_PER_CPU_AREA
+#ifdef CONFIG_SMP
 
 /* minimum unit size, also is the maximum supported allocation size */
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(64 << 10)
@@ -129,31 +134,10 @@ 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 void __percpu *__alloc_reserved_percpu(size_t size, size_t align);
+extern void __percpu *__alloc_percpu(size_t size, size_t align);
+extern void free_percpu(void __percpu *__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);
@@ -163,7 +147,7 @@ extern void __init setup_per_cpu_areas(void);
 
 #define per_cpu_ptr(ptr, cpu) ({ (void)(cpu); (ptr); })
 
-static inline void *__alloc_percpu(size_t size, size_t align)
+static inline void __percpu *__alloc_percpu(size_t size, size_t align)
 {
 	/*
 	 * Can't easily make larger alignment work with kmalloc.  WARN
@@ -174,11 +158,16 @@ static inline void *__alloc_percpu(size_t size, size_t align)
 	return kzalloc(size, GFP_KERNEL);
 }
 
-static inline void free_percpu(void *p)
+static inline void free_percpu(void __percpu *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 +177,8 @@ 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) __percpu *)__alloc_percpu(sizeof(type), __alignof__(type))
 
 /*
  * Optional methods for optimized non-lvalue per-cpu variable access.
@@ -206,17 +195,19 @@ static inline void *pcpu_lpage_remapped(void *kaddr)
 #ifndef percpu_read
 # define percpu_read(var)						\
   ({									\
-	typeof(per_cpu_var(var)) __tmp_var__;				\
-	__tmp_var__ = get_cpu_var(var);					\
-	put_cpu_var(var);						\
-	__tmp_var__;							\
+	typeof(var) *pr_ptr__ = &(var);					\
+	typeof(var) pr_ret__;						\
+	pr_ret__ = get_cpu_var(*pr_ptr__);				\
+	put_cpu_var(*pr_ptr__);						\
+	pr_ret__;							\
   })
 #endif
 
 #define __percpu_generic_to_op(var, val, op)				\
 do {									\
-	get_cpu_var(var) op val;					\
-	put_cpu_var(var);						\
+	typeof(var) *pgto_ptr__ = &(var);				\
+	get_cpu_var(*pgto_ptr__) op val;				\
+	put_cpu_var(*pgto_ptr__);					\
 } while (0)
 
 #ifndef percpu_write
@@ -243,4 +234,405 @@ 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__;					\
+	__verify_pcpu_ptr(&(variable));					\
+	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 {									\
+	__verify_pcpu_ptr(&(variable));					\
+	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.
+ *
+ * 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 2d0f222388a8..3e489fda11a1 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(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(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(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(vm_event_states.event[item], delta);
 }
 
 extern void all_vm_events(unsigned long *);