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:
  percpu: add __percpu sparse annotations to what's left
  percpu: add __percpu sparse annotations to fs
  percpu: add __percpu sparse annotations to core kernel subsystems
  local_t: Remove leftover local.h
  this_cpu: Remove pageset_notifier
  this_cpu: Page allocator conversion
  percpu, x86: Generic inc / dec percpu instructions
  local_t: Move local.h include to ringbuffer.c and ring_buffer_benchmark.c
  module: Use this_cpu_xx to dynamically allocate counters
  local_t: Remove cpu_local_xx macros
  percpu: refactor the code in pcpu_[de]populate_chunk()
  percpu: remove compile warnings caused by __verify_pcpu_ptr()
  percpu: make accessors check for percpu pointer in sparse
  percpu: add __percpu for sparse.
  percpu: make access macros universal
  percpu: remove per_cpu__ prefix.

15 files changed, 82 insertions, 83 deletions

diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index 3b73b9992b2..416bf62d6d4 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -150,8 +150,8 @@ struct blk_user_trace_setup {
 struct blk_trace {
 	int trace_state;
 	struct rchan *rchan;
-	unsigned long *sequence;
-	unsigned char *msg_data;
+	unsigned long __percpu *sequence;
+	unsigned char __percpu *msg_data;
 	u16 act_mask;
 	u64 start_lba;
 	u64 end_lba;
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 188fcae10a9..a5a472b1074 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))
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 78784982b33..21fd9b7c6a4 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -162,7 +162,7 @@ struct dma_chan {
 	struct dma_chan_dev *dev;
 
 	struct list_head device_node;
-	struct dma_chan_percpu *local;
+	struct dma_chan_percpu __percpu *local;
 	int client_count;
 	int table_count;
 	void *private;
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 9717081c75a..56b50514ab2 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -101,7 +101,7 @@ struct hd_struct {
 	unsigned long stamp;
 	int in_flight[2];
 #ifdef	CONFIG_SMP
-	struct disk_stats *dkstats;
+	struct disk_stats __percpu *dkstats;
 #else
 	struct disk_stats dkstats;
 #endif
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index c356b6914ff..03e8e8dbc57 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -199,7 +199,7 @@ extern struct kimage *kexec_crash_image;
  */
 extern struct resource crashk_res;
 typedef u32 note_buf_t[KEXEC_NOTE_BYTES/4];
-extern note_buf_t *crash_notes;
+extern note_buf_t __percpu *crash_notes;
 extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
 extern size_t vmcoreinfo_size;
 extern size_t vmcoreinfo_max_size;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8b2fa8593c6..2e724c877ec 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1081,11 +1081,7 @@ extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 extern int after_bootmem;
 
-#ifdef CONFIG_NUMA
 extern void setup_per_cpu_pageset(void);
-#else
-static inline void setup_per_cpu_pageset(void) {}
-#endif
 
 extern void zone_pcp_update(struct zone *zone);
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 30fe668c254..41acd4bf766 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -184,13 +184,7 @@ struct per_cpu_pageset {
 	s8 stat_threshold;
 	s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
 #endif
-} ____cacheline_aligned_in_smp;
-
-#ifdef CONFIG_NUMA
-#define zone_pcp(__z, __cpu) ((__z)->pageset[(__cpu)])
-#else
-#define zone_pcp(__z, __cpu) (&(__z)->pageset[(__cpu)])
-#endif
+};
 
 #endif /* !__GENERATING_BOUNDS.H */
 
@@ -306,10 +300,8 @@ struct zone {
 	 */
 	unsigned long		min_unmapped_pages;
 	unsigned long		min_slab_pages;
-	struct per_cpu_pageset	*pageset[NR_CPUS];
-#else
-	struct per_cpu_pageset	pageset[NR_CPUS];
 #endif
+	struct per_cpu_pageset __percpu *pageset;
 	/*
 	 * free areas of different sizes
 	 */
diff --git a/include/linux/module.h b/include/linux/module.h
index 6cb1a3cab5d..dd618eb026a 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -17,7 +17,7 @@
 #include <linux/moduleparam.h>
 #include <linux/tracepoint.h>
 
-#include <asm/local.h>
+#include <linux/percpu.h>
 #include <asm/module.h>
 
 #include <trace/events/module.h>
@@ -363,11 +363,9 @@ struct module
 	/* Destruction function. */
 	void (*exit)(void);
 
-#ifdef CONFIG_SMP
-	char *refptr;
-#else
-	local_t ref;
-#endif
+	struct module_ref {
+		int count;
+	} __percpu *refptr;
 #endif
 
 #ifdef CONFIG_CONSTRUCTORS
@@ -454,25 +452,16 @@ void __symbol_put(const char *symbol);
 #define symbol_put(x) __symbol_put(MODULE_SYMBOL_PREFIX #x)
 void symbol_put_addr(void *addr);
 
-static inline local_t *__module_ref_addr(struct module *mod, int cpu)
-{
-#ifdef CONFIG_SMP
-	return (local_t *) (mod->refptr + per_cpu_offset(cpu));
-#else
-	return &mod->ref;
-#endif
-}
-
 /* Sometimes we know we already have a refcount, and it's easier not
    to handle the error case (which only happens with rmmod --wait). */
 static inline void __module_get(struct module *module)
 {
 	if (module) {
-		unsigned int cpu = get_cpu();
-		local_inc(__module_ref_addr(module, cpu));
+		preempt_disable();
+		__this_cpu_inc(module->refptr->count);
 		trace_module_get(module, _THIS_IP_,
-				 local_read(__module_ref_addr(module, cpu)));
-		put_cpu();
+				 __this_cpu_read(module->refptr->count));
+		preempt_enable();
 	}
 }
 
@@ -481,15 +470,17 @@ static inline int try_module_get(struct module *module)
 	int ret = 1;
 
 	if (module) {
-		unsigned int cpu = get_cpu();
+		preempt_disable();
+
 		if (likely(module_is_live(module))) {
-			local_inc(__module_ref_addr(module, cpu));
+			__this_cpu_inc(module->refptr->count);
 			trace_module_get(module, _THIS_IP_,
-				local_read(__module_ref_addr(module, cpu)));
+				__this_cpu_read(module->refptr->count));
 		}
 		else
 			ret = 0;
-		put_cpu();
+
+		preempt_enable();
 	}
 	return ret;
 }
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 5d527536486..b5f43a34ef8 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -66,7 +66,7 @@ struct vfsmount {
 	int mnt_pinned;
 	int mnt_ghosts;
 #ifdef CONFIG_SMP
-	int *mnt_writers;
+	int __percpu *mnt_writers;
 #else
 	int mnt_writers;
 #endif
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 34fc6be5bfc..6a2e44fd75e 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -105,7 +105,7 @@ struct nfs_server {
 	struct rpc_clnt *	client;		/* RPC client handle */
 	struct rpc_clnt *	client_acl;	/* ACL RPC client handle */
 	struct nlm_host		*nlm_host;	/* NLM client handle */
-	struct nfs_iostats *	io_stats;	/* I/O statistics */
+	struct nfs_iostats __percpu *io_stats;	/* I/O statistics */
 	struct backing_dev_info	backing_dev_info;
 	atomic_long_t		writeback;	/* number of writeback pages */
 	int			flags;		/* various flags */
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 5a5d6ce4bd5..68567c0b3a5 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
@@ -56,24 +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
 
 /*
@@ -135,10 +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 cf5efbcf716..a93e5bfdccb 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -27,10 +27,17 @@
  * 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()
+
+/*
+ * 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)
 
 #ifdef CONFIG_SMP
 
@@ -127,9 +134,9 @@ 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);
-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
@@ -140,7 +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
@@ -151,7 +158,7 @@ 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);
 }
@@ -171,7 +178,7 @@ static inline void *pcpu_lpage_remapped(void *kaddr)
 #endif /* CONFIG_SMP */
 
 #define alloc_percpu(type)	\
-	(typeof(type) *)__alloc_percpu(sizeof(type), __alignof__(type))
+	(typeof(type) __percpu *)__alloc_percpu(sizeof(type), __alignof__(type))
 
 /*
  * Optional methods for optimized non-lvalue per-cpu variable access.
@@ -188,17 +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
@@ -234,6 +243,7 @@ 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;			\
@@ -247,6 +257,7 @@ extern void __bad_size_call_parameter(void);
 
 #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;		\
@@ -259,8 +270,7 @@ do {									\
 
 /*
  * 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).
+ * 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
@@ -311,7 +321,7 @@ do {									\
 #define _this_cpu_generic_to_op(pcp, val, op)				\
 do {									\
 	preempt_disable();						\
-	*__this_cpu_ptr(&pcp) op val;					\
+	*__this_cpu_ptr(&(pcp)) op val;					\
 	preempt_enable();						\
 } while (0)
 
diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 794662b2be5..c88d67b5939 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -21,7 +21,7 @@ struct percpu_counter {
 #ifdef CONFIG_HOTPLUG_CPU
 	struct list_head list;	/* All percpu_counters are on a list */
 #endif
-	s32 *counters;
+	s32 __percpu *counters;
 };
 
 extern int percpu_counter_batch;
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 3084f80909c..4d5ecb222af 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -33,7 +33,7 @@ struct srcu_struct_array {
 
 struct srcu_struct {
 	int completed;
-	struct srcu_struct_array *per_cpu_ref;
+	struct srcu_struct_array __percpu *per_cpu_ref;
 	struct mutex mutex;
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map dep_map;
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index ee03bba9c5d..117f0dd8ad0 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -78,22 +78,22 @@ DECLARE_PER_CPU(struct vm_event_state, vm_event_states);
 
 static inline void __count_vm_event(enum vm_event_item item)
 {
-	__this_cpu_inc(per_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)
 {
-	this_cpu_inc(per_cpu_var(vm_event_states).event[item]);
+	this_cpu_inc(vm_event_states.event[item]);
 }
 
 static inline void __count_vm_events(enum vm_event_item item, long delta)
 {
-	__this_cpu_add(per_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)
 {
-	this_cpu_add(per_cpu_var(vm_event_states).event[item], delta);
+	this_cpu_add(vm_event_states.event[item], delta);
 }
 
 extern void all_vm_events(unsigned long *);