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.

3 files changed, 91 insertions, 73 deletions

diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 47b9b6f1905..2e9972468a5 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -195,41 +195,4 @@ static inline long local_sub_return(long i, local_t *l)
 #define __local_add(i, l)	local_add((i), (l))
 #define __local_sub(i, l)	local_sub((i), (l))
 
-/* Use these for per-cpu local_t variables: on some archs they are
- * much more efficient than these naive implementations.  Note they take
- * a variable, not an address.
- *
- * X86_64: This could be done better if we moved the per cpu data directly
- * after GS.
- */
-
-/* Need to disable preemption for the cpu local counters otherwise we could
-   still access a variable of a previous CPU in a non atomic way. */
-#define cpu_local_wrap_v(l)		\
-({					\
-	local_t res__;			\
-	preempt_disable(); 		\
-	res__ = (l);			\
-	preempt_enable();		\
-	res__;				\
-})
-#define cpu_local_wrap(l)		\
-({					\
-	preempt_disable();		\
-	(l);				\
-	preempt_enable();		\
-})					\
-
-#define cpu_local_read(l)    cpu_local_wrap_v(local_read(&__get_cpu_var((l))))
-#define cpu_local_set(l, i)  cpu_local_wrap(local_set(&__get_cpu_var((l)), (i)))
-#define cpu_local_inc(l)     cpu_local_wrap(local_inc(&__get_cpu_var((l))))
-#define cpu_local_dec(l)     cpu_local_wrap(local_dec(&__get_cpu_var((l))))
-#define cpu_local_add(i, l)  cpu_local_wrap(local_add((i), &__get_cpu_var((l))))
-#define cpu_local_sub(i, l)  cpu_local_wrap(local_sub((i), &__get_cpu_var((l))))
-
-#define __cpu_local_inc(l)	cpu_local_inc((l))
-#define __cpu_local_dec(l)	cpu_local_dec((l))
-#define __cpu_local_add(i, l)	cpu_local_add((i), (l))
-#define __cpu_local_sub(i, l)	cpu_local_sub((i), (l))
-
 #endif /* _ASM_X86_LOCAL_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 0c44196b78a..66a272dfd8b 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -25,19 +25,18 @@
  */
 #ifdef CONFIG_SMP
 #define PER_CPU(var, reg)						\
-	__percpu_mov_op %__percpu_seg:per_cpu__this_cpu_off, reg;	\
-	lea per_cpu__##var(reg), reg
-#define PER_CPU_VAR(var)	%__percpu_seg:per_cpu__##var
+	__percpu_mov_op %__percpu_seg:this_cpu_off, reg;		\
+	lea var(reg), reg
+#define PER_CPU_VAR(var)	%__percpu_seg:var
 #else /* ! SMP */
-#define PER_CPU(var, reg)						\
-	__percpu_mov_op $per_cpu__##var, reg
-#define PER_CPU_VAR(var)	per_cpu__##var
+#define PER_CPU(var, reg)	__percpu_mov_op $var, reg
+#define PER_CPU_VAR(var)	var
 #endif	/* SMP */
 
 #ifdef CONFIG_X86_64_SMP
 #define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
 #else
-#define INIT_PER_CPU_VAR(var)  per_cpu__##var
+#define INIT_PER_CPU_VAR(var)  var
 #endif
 
 #else /* ...!ASSEMBLY */
@@ -60,12 +59,12 @@
  * There also must be an entry in vmlinux_64.lds.S
  */
 #define DECLARE_INIT_PER_CPU(var) \
-       extern typeof(per_cpu_var(var)) init_per_cpu_var(var)
+       extern typeof(var) init_per_cpu_var(var)
 
 #ifdef CONFIG_X86_64_SMP
 #define init_per_cpu_var(var)  init_per_cpu__##var
 #else
-#define init_per_cpu_var(var)  per_cpu_var(var)
+#define init_per_cpu_var(var)  var
 #endif
 
 /* For arch-specific code, we can use direct single-insn ops (they
@@ -104,6 +103,64 @@ do {							\
 	}						\
 } while (0)
 
+/*
+ * Generate a percpu add to memory instruction and optimize code
+ * if a one is added or subtracted.
+ */
+#define percpu_add_op(var, val)						\
+do {									\
+	typedef typeof(var) pao_T__;					\
+	const int pao_ID__ = (__builtin_constant_p(val) &&		\
+			      ((val) == 1 || (val) == -1)) ? (val) : 0;	\
+	if (0) {							\
+		pao_T__ pao_tmp__;					\
+		pao_tmp__ = (val);					\
+	}								\
+	switch (sizeof(var)) {						\
+	case 1:								\
+		if (pao_ID__ == 1)					\
+			asm("incb "__percpu_arg(0) : "+m" (var));	\
+		else if (pao_ID__ == -1)				\
+			asm("decb "__percpu_arg(0) : "+m" (var));	\
+		else							\
+			asm("addb %1, "__percpu_arg(0)			\
+			    : "+m" (var)				\
+			    : "qi" ((pao_T__)(val)));			\
+		break;							\
+	case 2:								\
+		if (pao_ID__ == 1)					\
+			asm("incw "__percpu_arg(0) : "+m" (var));	\
+		else if (pao_ID__ == -1)				\
+			asm("decw "__percpu_arg(0) : "+m" (var));	\
+		else							\
+			asm("addw %1, "__percpu_arg(0)			\
+			    : "+m" (var)				\
+			    : "ri" ((pao_T__)(val)));			\
+		break;							\
+	case 4:								\
+		if (pao_ID__ == 1)					\
+			asm("incl "__percpu_arg(0) : "+m" (var));	\
+		else if (pao_ID__ == -1)				\
+			asm("decl "__percpu_arg(0) : "+m" (var));	\
+		else							\
+			asm("addl %1, "__percpu_arg(0)			\
+			    : "+m" (var)				\
+			    : "ri" ((pao_T__)(val)));			\
+		break;							\
+	case 8:								\
+		if (pao_ID__ == 1)					\
+			asm("incq "__percpu_arg(0) : "+m" (var));	\
+		else if (pao_ID__ == -1)				\
+			asm("decq "__percpu_arg(0) : "+m" (var));	\
+		else							\
+			asm("addq %1, "__percpu_arg(0)			\
+			    : "+m" (var)				\
+			    : "re" ((pao_T__)(val)));			\
+		break;							\
+	default: __bad_percpu_size();					\
+	}								\
+} while (0)
+
 #define percpu_from_op(op, var, constraint)		\
 ({							\
 	typeof(var) pfo_ret__;				\
@@ -142,16 +199,14 @@ do {							\
  * per-thread variables implemented as per-cpu variables and thus
  * stable for the duration of the respective task.
  */
-#define percpu_read(var)	percpu_from_op("mov", per_cpu__##var,	\
-					       "m" (per_cpu__##var))
-#define percpu_read_stable(var)	percpu_from_op("mov", per_cpu__##var,	\
-					       "p" (&per_cpu__##var))
-#define percpu_write(var, val)	percpu_to_op("mov", per_cpu__##var, val)
-#define percpu_add(var, val)	percpu_to_op("add", per_cpu__##var, val)
-#define percpu_sub(var, val)	percpu_to_op("sub", per_cpu__##var, val)
-#define percpu_and(var, val)	percpu_to_op("and", per_cpu__##var, val)
-#define percpu_or(var, val)	percpu_to_op("or", per_cpu__##var, val)
-#define percpu_xor(var, val)	percpu_to_op("xor", per_cpu__##var, val)
+#define percpu_read(var)		percpu_from_op("mov", var, "m" (var))
+#define percpu_read_stable(var)		percpu_from_op("mov", var, "p" (&(var)))
+#define percpu_write(var, val)		percpu_to_op("mov", var, val)
+#define percpu_add(var, val)		percpu_add_op(var, val)
+#define percpu_sub(var, val)		percpu_add_op(var, -(val))
+#define percpu_and(var, val)		percpu_to_op("and", var, val)
+#define percpu_or(var, val)		percpu_to_op("or", var, val)
+#define percpu_xor(var, val)		percpu_to_op("xor", var, val)
 
 #define __this_cpu_read_1(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
 #define __this_cpu_read_2(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
@@ -160,9 +215,9 @@ do {							\
 #define __this_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
 #define __this_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
 #define __this_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define __this_cpu_add_1(pcp, val)	percpu_to_op("add", (pcp), val)
-#define __this_cpu_add_2(pcp, val)	percpu_to_op("add", (pcp), val)
-#define __this_cpu_add_4(pcp, val)	percpu_to_op("add", (pcp), val)
+#define __this_cpu_add_1(pcp, val)	percpu_add_op((pcp), val)
+#define __this_cpu_add_2(pcp, val)	percpu_add_op((pcp), val)
+#define __this_cpu_add_4(pcp, val)	percpu_add_op((pcp), val)
 #define __this_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
 #define __this_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
 #define __this_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
@@ -179,9 +234,9 @@ do {							\
 #define this_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
 #define this_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
 #define this_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define this_cpu_add_1(pcp, val)	percpu_to_op("add", (pcp), val)
-#define this_cpu_add_2(pcp, val)	percpu_to_op("add", (pcp), val)
-#define this_cpu_add_4(pcp, val)	percpu_to_op("add", (pcp), val)
+#define this_cpu_add_1(pcp, val)	percpu_add_op((pcp), val)
+#define this_cpu_add_2(pcp, val)	percpu_add_op((pcp), val)
+#define this_cpu_add_4(pcp, val)	percpu_add_op((pcp), val)
 #define this_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
 #define this_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
 #define this_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
@@ -192,9 +247,9 @@ do {							\
 #define this_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
 #define this_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
 
-#define irqsafe_cpu_add_1(pcp, val)	percpu_to_op("add", (pcp), val)
-#define irqsafe_cpu_add_2(pcp, val)	percpu_to_op("add", (pcp), val)
-#define irqsafe_cpu_add_4(pcp, val)	percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_add_1(pcp, val)	percpu_add_op((pcp), val)
+#define irqsafe_cpu_add_2(pcp, val)	percpu_add_op((pcp), val)
+#define irqsafe_cpu_add_4(pcp, val)	percpu_add_op((pcp), val)
 #define irqsafe_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
 #define irqsafe_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
 #define irqsafe_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
@@ -212,19 +267,19 @@ do {							\
 #ifdef CONFIG_X86_64
 #define __this_cpu_read_8(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
 #define __this_cpu_write_8(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define __this_cpu_add_8(pcp, val)	percpu_to_op("add", (pcp), val)
+#define __this_cpu_add_8(pcp, val)	percpu_add_op((pcp), val)
 #define __this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
 #define __this_cpu_or_8(pcp, val)	percpu_to_op("or", (pcp), val)
 #define __this_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
 
 #define this_cpu_read_8(pcp)		percpu_from_op("mov", (pcp), "m"(pcp))
 #define this_cpu_write_8(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define this_cpu_add_8(pcp, val)	percpu_to_op("add", (pcp), val)
+#define this_cpu_add_8(pcp, val)	percpu_add_op((pcp), val)
 #define this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
 #define this_cpu_or_8(pcp, val)		percpu_to_op("or", (pcp), val)
 #define this_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
 
-#define irqsafe_cpu_add_8(pcp, val)	percpu_to_op("add", (pcp), val)
+#define irqsafe_cpu_add_8(pcp, val)	percpu_add_op((pcp), val)
 #define irqsafe_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
 #define irqsafe_cpu_or_8(pcp, val)	percpu_to_op("or", (pcp), val)
 #define irqsafe_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
@@ -236,7 +291,7 @@ do {							\
 ({									\
 	int old__;							\
 	asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0"		\
-		     : "=r" (old__), "+m" (per_cpu__##var)		\
+		     : "=r" (old__), "+m" (var)				\
 		     : "dIr" (bit));					\
 	old__;								\
 })
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index e04740f7a0b..b8fe48ee2ed 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -32,7 +32,7 @@ extern void show_regs_common(void);
 	"movl %P[task_canary](%[next]), %%ebx\n\t"			\
 	"movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
 #define __switch_canary_oparam						\
-	, [stack_canary] "=m" (per_cpu_var(stack_canary.canary))
+	, [stack_canary] "=m" (stack_canary.canary)
 #define __switch_canary_iparam						\
 	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
 #else	/* CC_STACKPROTECTOR */
@@ -114,7 +114,7 @@ do {									\
 	"movq %P[task_canary](%%rsi),%%r8\n\t"				  \
 	"movq %%r8,"__percpu_arg([gs_canary])"\n\t"
 #define __switch_canary_oparam						  \
-	, [gs_canary] "=m" (per_cpu_var(irq_stack_union.stack_canary))
+	, [gs_canary] "=m" (irq_stack_union.stack_canary)
 #define __switch_canary_iparam						  \
 	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
 #else	/* CC_STACKPROTECTOR */
@@ -133,7 +133,7 @@ do {									\
 	     __switch_canary						  \
 	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
 	     "movq %%rax,%%rdi\n\t" 					  \
-	     "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"	  \
+	     "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"		  \
 	     "jnz   ret_from_fork\n\t"					  \
 	     RESTORE_CONTEXT						  \
 	     : "=a" (last)					  	  \
@@ -143,7 +143,7 @@ do {									\
 	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
 	       [_tif_fork] "i" (_TIF_FORK),			  	  \
 	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-	       [current_task] "m" (per_cpu_var(current_task))		  \
+	       [current_task] "m" (current_task)			  \
 	       __switch_canary_iparam					  \
 	     : "memory", "cc" __EXTRA_CLOBBER)
 #endif