Merge branch 'this_cpu_ops' into for-2.6.38

arch/x86/Kconfig.cpu

@@ -310,6 +310,9 @@ config X86_INTERNODE_CACHE_SHIFT
 config X86_CMPXCHG
 	def_bool X86_64 || (X86_32 && !M386)
 
+config CMPXCHG_LOCAL
+	def_bool X86_64 || (X86_32 && !M386)
+
 config X86_L1_CACHE_SHIFT
 	int
 	default "7" if MPENTIUM4 || MPSC

arch/x86/include/asm/percpu.h

@@ -177,39 +177,6 @@ do {									\
 	}								\
 } while (0)
 
-/*
- * Add return operation
- */
-#define percpu_add_return_op(var, val)					\
-({									\
-	typeof(var) paro_ret__ = val;					\
-	switch (sizeof(var)) {						\
-	case 1:								\
-		asm("xaddb %0, "__percpu_arg(1)				\
-			    : "+q" (paro_ret__), "+m" (var)		\
-			    : : "memory");				\
-		break;							\
-	case 2:								\
-		asm("xaddw %0, "__percpu_arg(1)				\
-			    : "+r" (paro_ret__), "+m" (var)		\
-			    : : "memory");				\
-		break;							\
-	case 4:								\
-		asm("xaddl %0, "__percpu_arg(1)				\
-			    : "+r" (paro_ret__), "+m" (var)		\
-			    : : "memory");				\
-		break;							\
-	case 8:								\
-		asm("xaddq %0, "__percpu_arg(1)				\
-			    : "+re" (paro_ret__), "+m" (var)		\
-			    : : "memory");				\
-		break;							\
-	default: __bad_percpu_size();					\
-	}								\
-	paro_ret__ += val;						\
-	paro_ret__;							\
-})
-
 #define percpu_from_op(op, var, constraint)		\
 ({							\
 	typeof(var) pfo_ret__;				\
@@ -262,6 +229,125 @@ do {									\
 	}						\
 })
 
+/*
+ * Add return operation
+ */
+#define percpu_add_return_op(var, val)					\
+({									\
+	typeof(var) paro_ret__ = val;					\
+	switch (sizeof(var)) {						\
+	case 1:								\
+		asm("xaddb %0, "__percpu_arg(1)				\
+			    : "+q" (paro_ret__), "+m" (var)		\
+			    : : "memory");				\
+		break;							\
+	case 2:								\
+		asm("xaddw %0, "__percpu_arg(1)				\
+			    : "+r" (paro_ret__), "+m" (var)		\
+			    : : "memory");				\
+		break;							\
+	case 4:								\
+		asm("xaddl %0, "__percpu_arg(1)				\
+			    : "+r" (paro_ret__), "+m" (var)		\
+			    : : "memory");				\
+		break;							\
+	case 8:								\
+		asm("xaddq %0, "__percpu_arg(1)				\
+			    : "+re" (paro_ret__), "+m" (var)		\
+			    : : "memory");				\
+		break;							\
+	default: __bad_percpu_size();					\
+	}								\
+	paro_ret__ += val;						\
+	paro_ret__;							\
+})
+
+/*
+ * xchg is implemented using cmpxchg without a lock prefix. xchg is
+ * expensive due to the implied lock prefix.  The processor cannot prefetch
+ * cachelines if xchg is used.
+ */
+#define percpu_xchg_op(var, nval)					\
+({									\
+	typeof(var) pxo_ret__;						\
+	typeof(var) pxo_new__ = (nval);					\
+	switch (sizeof(var)) {						\
+	case 1:								\
+		asm("\n1:mov "__percpu_arg(1)",%%al"			\
+		    "\n\tcmpxchgb %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
+			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "q" (pxo_new__)				\
+			    : "memory");				\
+		break;							\
+	case 2:								\
+		asm("\n1:mov "__percpu_arg(1)",%%ax"			\
+		    "\n\tcmpxchgw %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
+			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "r" (pxo_new__)				\
+			    : "memory");				\
+		break;							\
+	case 4:								\
+		asm("\n1:mov "__percpu_arg(1)",%%eax"			\
+		    "\n\tcmpxchgl %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
+			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "r" (pxo_new__)				\
+			    : "memory");				\
+		break;							\
+	case 8:								\
+		asm("\n1:mov "__percpu_arg(1)",%%rax"			\
+		    "\n\tcmpxchgq %2, "__percpu_arg(1)			\
+		    "\n\tjnz 1b"					\
+			    : "=a" (pxo_ret__), "+m" (var)		\
+			    : "r" (pxo_new__)				\
+			    : "memory");				\
+		break;							\
+	default: __bad_percpu_size();					\
+	}								\
+	pxo_ret__;							\
+})
+
+/*
+ * cmpxchg has no such implied lock semantics as a result it is much
+ * more efficient for cpu local operations.
+ */
+#define percpu_cmpxchg_op(var, oval, nval)				\
+({									\
+	typeof(var) pco_ret__;						\
+	typeof(var) pco_old__ = (oval);					\
+	typeof(var) pco_new__ = (nval);					\
+	switch (sizeof(var)) {						\
+	case 1:								\
+		asm("cmpxchgb %2, "__percpu_arg(1)			\
+			    : "=a" (pco_ret__), "+m" (var)		\
+			    : "q" (pco_new__), "0" (pco_old__)		\
+			    : "memory");				\
+		break;							\
+	case 2:								\
+		asm("cmpxchgw %2, "__percpu_arg(1)			\
+			    : "=a" (pco_ret__), "+m" (var)		\
+			    : "r" (pco_new__), "0" (pco_old__)		\
+			    : "memory");				\
+		break;							\
+	case 4:								\
+		asm("cmpxchgl %2, "__percpu_arg(1)			\
+			    : "=a" (pco_ret__), "+m" (var)		\
+			    : "r" (pco_new__), "0" (pco_old__)		\
+			    : "memory");				\
+		break;							\
+	case 8:								\
+		asm("cmpxchgq %2, "__percpu_arg(1)			\
+			    : "=a" (pco_ret__), "+m" (var)		\
+			    : "r" (pco_new__), "0" (pco_old__)		\
+			    : "memory");				\
+		break;							\
+	default: __bad_percpu_size();					\
+	}								\
+	pco_ret__;							\
+})
+
 /*
  * percpu_read() makes gcc load the percpu variable every time it is
  * accessed while percpu_read_stable() allows the value to be cached.
@@ -300,6 +386,12 @@ do {									\
 #define __this_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
 #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)
+/*
+ * Generic fallback operations for __this_cpu_xchg_[1-4] are okay and much
+ * faster than an xchg with forced lock semantics.
+ */
+#define __this_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define __this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
 
 #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))
@@ -319,6 +411,11 @@ do {									\
 #define this_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
 #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 this_cpu_xchg_1(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
 
 #define irqsafe_cpu_add_1(pcp, val)	percpu_add_op((pcp), val)
 #define irqsafe_cpu_add_2(pcp, val)	percpu_add_op((pcp), val)
@@ -332,15 +429,32 @@ do {									\
 #define irqsafe_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
 #define irqsafe_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
 #define irqsafe_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
+#define irqsafe_cpu_xchg_1(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define irqsafe_cpu_xchg_2(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define irqsafe_cpu_xchg_4(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define irqsafe_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
+#define irqsafe_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
 
 #ifndef CONFIG_M386
 #define __this_cpu_add_return_1(pcp, val) percpu_add_return_op(pcp, val)
 #define __this_cpu_add_return_2(pcp, val) percpu_add_return_op(pcp, val)
 #define __this_cpu_add_return_4(pcp, val) percpu_add_return_op(pcp, val)
+#define __this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define __this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define __this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+
 #define this_cpu_add_return_1(pcp, val)	percpu_add_return_op(pcp, val)
 #define this_cpu_add_return_2(pcp, val)	percpu_add_return_op(pcp, val)
 #define this_cpu_add_return_4(pcp, val)	percpu_add_return_op(pcp, val)
-#endif
+#define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+
+#define irqsafe_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define irqsafe_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define irqsafe_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#endif /* !CONFIG_M386 */
+
 /*
  * Per cpu atomic 64 bit operations are only available under 64 bit.
  * 32 bit must fall back to generic operations.
@@ -352,6 +466,7 @@ do {									\
 #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_add_return_8(pcp, val) percpu_add_return_op(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)
@@ -359,14 +474,12 @@ do {									\
 #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_add_return_8(pcp, val)	percpu_add_return_op(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)
-
-#define __this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val)
-#define this_cpu_add_return_8(pcp, val)	percpu_add_return_op(pcp, val)
 #endif
 
 /* This is not atomic against other CPUs -- CPU preemption needs to be off */

include/linux/percpu.h

@@ -417,6 +417,89 @@ do {									\
 # define this_cpu_xor(pcp, val)		__pcpu_size_call(this_cpu_or_, (pcp), (val))
 #endif
 
+#define _this_cpu_generic_add_return(pcp, val)				\
+({									\
+	typeof(pcp) ret__;						\
+	preempt_disable();						\
+	__this_cpu_add(pcp, val);					\
+	ret__ = __this_cpu_read(pcp);					\
+	preempt_enable();						\
+	ret__;								\
+})
+
+#ifndef this_cpu_add_return
+# ifndef this_cpu_add_return_1
+#  define this_cpu_add_return_1(pcp, val)	_this_cpu_generic_add_return(pcp, val)
+# endif
+# ifndef this_cpu_add_return_2
+#  define this_cpu_add_return_2(pcp, val)	_this_cpu_generic_add_return(pcp, val)
+# endif
+# ifndef this_cpu_add_return_4
+#  define this_cpu_add_return_4(pcp, val)	_this_cpu_generic_add_return(pcp, val)
+# endif
+# ifndef this_cpu_add_return_8
+#  define this_cpu_add_return_8(pcp, val)	_this_cpu_generic_add_return(pcp, val)
+# endif
+# define this_cpu_add_return(pcp, val)	__pcpu_size_call_return2(this_cpu_add_return_, pcp, val)
+#endif
+
+#define this_cpu_sub_return(pcp, val)	this_cpu_add_return(pcp, -(val))
+#define this_cpu_inc_return(pcp)	this_cpu_add_return(pcp, 1)
+#define this_cpu_dec_return(pcp)	this_cpu_add_return(pcp, -1)
+
+#define _this_cpu_generic_xchg(pcp, nval)				\
+({	typeof(pcp) ret__;						\
+	preempt_disable();						\
+	ret__ = __this_cpu_read(pcp);					\
+	__this_cpu_write(pcp, nval);					\
+	preempt_enable();						\
+	ret__;								\
+})
+
+#ifndef this_cpu_xchg
+# ifndef this_cpu_xchg_1
+#  define this_cpu_xchg_1(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef this_cpu_xchg_2
+#  define this_cpu_xchg_2(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef this_cpu_xchg_4
+#  define this_cpu_xchg_4(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef this_cpu_xchg_8
+#  define this_cpu_xchg_8(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
+# endif
+# define this_cpu_xchg(pcp, nval)	\
+	__pcpu_size_call_return2(this_cpu_xchg_, (pcp), nval)
+#endif
+
+#define _this_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({	typeof(pcp) ret__;						\
+	preempt_disable();						\
+	ret__ = __this_cpu_read(pcp);					\
+	if (ret__ == (oval))						\
+		__this_cpu_write(pcp, nval);				\
+	preempt_enable();						\
+	ret__;								\
+})
+
+#ifndef this_cpu_cmpxchg
+# ifndef this_cpu_cmpxchg_1
+#  define this_cpu_cmpxchg_1(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef this_cpu_cmpxchg_2
+#  define this_cpu_cmpxchg_2(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef this_cpu_cmpxchg_4
+#  define this_cpu_cmpxchg_4(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef this_cpu_cmpxchg_8
+#  define this_cpu_cmpxchg_8(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# define this_cpu_cmpxchg(pcp, oval, nval)	\
+	__pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
+#endif
+
 /*
  * Generic percpu operations that do not require preemption handling.
  * Either we do not care about races or the caller has the
@@ -544,36 +627,6 @@ do {									\
 # define __this_cpu_xor(pcp, val)	__pcpu_size_call(__this_cpu_xor_, (pcp), (val))
 #endif
 
-#define _this_cpu_generic_add_return(pcp, val)				\
-({									\
-	typeof(pcp) ret__;						\
-	preempt_disable();						\
-	__this_cpu_add(pcp, val);					\
-	ret__ = __this_cpu_read(pcp);					\
-	preempt_enable();						\
-	ret__;								\
-})
-
-#ifndef this_cpu_add_return
-# ifndef this_cpu_add_return_1
-#  define this_cpu_add_return_1(pcp, val)	_this_cpu_generic_add_return(pcp, val)
-# endif
-# ifndef this_cpu_add_return_2
-#  define this_cpu_add_return_2(pcp, val)	_this_cpu_generic_add_return(pcp, val)
-# endif
-# ifndef this_cpu_add_return_4
-#  define this_cpu_add_return_4(pcp, val)	_this_cpu_generic_add_return(pcp, val)
-# endif
-# ifndef this_cpu_add_return_8
-#  define this_cpu_add_return_8(pcp, val)	_this_cpu_generic_add_return(pcp, val)
-# endif
-# define this_cpu_add_return(pcp, val)	__pcpu_size_call_return2(this_cpu_add_return_, pcp, val)
-#endif
-
-#define this_cpu_sub_return(pcp, val)	this_cpu_add_return(pcp, -(val))
-#define this_cpu_inc_return(pcp)	this_cpu_add_return(pcp, 1)
-#define this_cpu_dec_return(pcp)	this_cpu_add_return(pcp, -1)
-
 #define __this_cpu_generic_add_return(pcp, val)				\
 ({									\
 	__this_cpu_add(pcp, val);					\
@@ -600,11 +653,61 @@ do {									\
 #define __this_cpu_inc_return(pcp)	this_cpu_add_return(pcp, 1)
 #define __this_cpu_dec_return(pcp)	this_cpu_add_return(pcp, -1)
 
+#define __this_cpu_generic_xchg(pcp, nval)				\
+({	typeof(pcp) ret__;						\
+	ret__ = __this_cpu_read(pcp);					\
+	__this_cpu_write(pcp, nval);					\
+	ret__;								\
+})
+
+#ifndef __this_cpu_xchg
+# ifndef __this_cpu_xchg_1
+#  define __this_cpu_xchg_1(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef __this_cpu_xchg_2
+#  define __this_cpu_xchg_2(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef __this_cpu_xchg_4
+#  define __this_cpu_xchg_4(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef __this_cpu_xchg_8
+#  define __this_cpu_xchg_8(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# endif
+# define __this_cpu_xchg(pcp, nval)	\
+	__pcpu_size_call_return2(__this_cpu_xchg_, (pcp), nval)
+#endif
+
+#define __this_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({									\
+	typeof(pcp) ret__;						\
+	ret__ = __this_cpu_read(pcp);					\
+	if (ret__ == (oval))						\
+		__this_cpu_write(pcp, nval);				\
+	ret__;								\
+})
+
+#ifndef __this_cpu_cmpxchg
+# ifndef __this_cpu_cmpxchg_1
+#  define __this_cpu_cmpxchg_1(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef __this_cpu_cmpxchg_2
+#  define __this_cpu_cmpxchg_2(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef __this_cpu_cmpxchg_4
+#  define __this_cpu_cmpxchg_4(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef __this_cpu_cmpxchg_8
+#  define __this_cpu_cmpxchg_8(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# define __this_cpu_cmpxchg(pcp, oval, nval)	\
+	__pcpu_size_call_return2(__this_cpu_cmpxchg_, pcp, oval, nval)
+#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
+ * They are guaranteed to be atomic vs. local interrupts and
  * preemption only.
  */
 #define irqsafe_cpu_generic_to_op(pcp, val, op)				\
@@ -691,4 +794,33 @@ do {									\
 # define irqsafe_cpu_xor(pcp, val) __pcpu_size_call(irqsafe_cpu_xor_, (val))
 #endif
 
+#define irqsafe_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({									\
+	typeof(pcp) ret__;						\
+	unsigned long flags;						\
+	local_irq_save(flags);						\
+	ret__ = __this_cpu_read(pcp);					\
+	if (ret__ == (oval))						\
+		__this_cpu_write(pcp, nval);				\
+	local_irq_restore(flags);					\
+	ret__;								\
+})
+
+#ifndef irqsafe_cpu_cmpxchg
+# ifndef irqsafe_cpu_cmpxchg_1
+#  define irqsafe_cpu_cmpxchg_1(pcp, oval, nval)	irqsafe_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_2
+#  define irqsafe_cpu_cmpxchg_2(pcp, oval, nval)	irqsafe_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_4
+#  define irqsafe_cpu_cmpxchg_4(pcp, oval, nval)	irqsafe_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_8
+#  define irqsafe_cpu_cmpxchg_8(pcp, oval, nval)	irqsafe_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# define irqsafe_cpu_cmpxchg(pcp, oval, nval)		\
+	__pcpu_size_call_return2(irqsafe_cpu_cmpxchg_, (pcp), oval, nval)
+#endif
+
 #endif /* __LINUX_PERCPU_H */