percpu,x86: relocate this_cpu_add_return() and friends

- include/linux/percpu.h: this_cpu_add_return() and friends were
  located next to __this_cpu_add_return().  However, the overall
  organization is to first group by preemption safeness.  Relocate
  this_cpu_add_return() and friends to preemption-safe area.

- arch/x86/include/asm/percpu.h: Relocate percpu_add_return_op() after
  other more basic operations.  Relocate [__]this_cpu_add_return_8()
  so that they're first grouped by preemption safeness.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>

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 +229,39 @@ 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__;							\
+})
+
 /*
  * percpu_read() makes gcc load the percpu variable every time it is
  * accessed while percpu_read_stable() allows the value to be cached.
@@ -352,6 +352,7 @@ 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 +360,12 @@ 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 +417,36 @@ 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)
+
 /*
  * Generic percpu operations that do not require preemption handling.
  * Either we do not care about races or the caller has the
@@ -544,36 +574,6 @@ 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);					\