[PATCH v6 04/12] this_cpu_cmpxchg: x86: switch this_cpu_cmpxchg to locked, add _local function

[Marcelo Tosatti]

Goal is to have vmstat_shepherd to transfer from
per-CPU counters to global counters remotely. For this,
an atomic this_cpu_cmpxchg is necessary.

Following the kernel convention for cmpxchg/cmpxchg_local,
change x86's this_cpu_cmpxchg_ helpers to be atomic.
and add this_cpu_cmpxchg_local_ helpers which are not atomic.

Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>

Index: linux-vmstat-remote/arch/x86/include/asm/percpu.h
===================================================================
--- linux-vmstat-remote.orig/arch/x86/include/asm/percpu.h
+++ linux-vmstat-remote/arch/x86/include/asm/percpu.h
@@ -197,11 +197,11 @@ do {									\
  * cmpxchg has no such implied lock semantics as a result it is much
  * more efficient for cpu local operations.
  */
-#define percpu_cmpxchg_op(size, qual, _var, _oval, _nval)		\
+#define percpu_cmpxchg_op(size, qual, _var, _oval, _nval, lockp)	\
 ({									\
 	__pcpu_type_##size pco_old__ = __pcpu_cast_##size(_oval);	\
 	__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval);	\
-	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
+	asm qual (__pcpu_op2_##size(lockp "cmpxchg", "%[nval]",		\
 				    __percpu_arg([var]))		\
 		  : [oval] "+a" (pco_old__),				\
 		    [var] "+m" (_var)					\
@@ -279,16 +279,20 @@ do {									\
 #define raw_cpu_add_return_1(pcp, val)		percpu_add_return_op(1, , pcp, val)
 #define raw_cpu_add_return_2(pcp, val)		percpu_add_return_op(2, , pcp, val)
 #define raw_cpu_add_return_4(pcp, val)		percpu_add_return_op(4, , pcp, val)
-#define raw_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(1, , pcp, oval, nval)
-#define raw_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(2, , pcp, oval, nval)
-#define raw_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(4, , pcp, oval, nval)
+#define raw_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(1, , pcp, oval, nval, "")
+#define raw_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(2, , pcp, oval, nval, "")
+#define raw_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(4, , pcp, oval, nval, "")
 
 #define this_cpu_add_return_1(pcp, val)		percpu_add_return_op(1, volatile, pcp, val)
 #define this_cpu_add_return_2(pcp, val)		percpu_add_return_op(2, volatile, pcp, val)
 #define this_cpu_add_return_4(pcp, val)		percpu_add_return_op(4, volatile, pcp, val)
-#define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(1, volatile, pcp, oval, nval)
-#define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(2, volatile, pcp, oval, nval)
-#define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(4, volatile, pcp, oval, nval)
+#define this_cpu_cmpxchg_local_1(pcp, oval, nval)	percpu_cmpxchg_op(1, volatile, pcp, oval, nval, "")
+#define this_cpu_cmpxchg_local_2(pcp, oval, nval)	percpu_cmpxchg_op(2, volatile, pcp, oval, nval, "")
+#define this_cpu_cmpxchg_local_4(pcp, oval, nval)	percpu_cmpxchg_op(4, volatile, pcp, oval, nval, "")
+
+#define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(1, volatile, pcp, oval, nval, LOCK_PREFIX)
+#define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(2, volatile, pcp, oval, nval, LOCK_PREFIX)
+#define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(4, volatile, pcp, oval, nval, LOCK_PREFIX)
 
 #ifdef CONFIG_X86_CMPXCHG64
 #define percpu_cmpxchg8b_double(pcp1, pcp2, o1, o2, n1, n2)		\
@@ -319,16 +323,17 @@ do {									\
 #define raw_cpu_or_8(pcp, val)			percpu_to_op(8, , "or", (pcp), val)
 #define raw_cpu_add_return_8(pcp, val)		percpu_add_return_op(8, , pcp, val)
 #define raw_cpu_xchg_8(pcp, nval)		raw_percpu_xchg_op(pcp, nval)
-#define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, , pcp, oval, nval)
+#define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, , pcp, oval, nval, "")
 
-#define this_cpu_read_8(pcp)			percpu_from_op(8, volatile, "mov", pcp)
-#define this_cpu_write_8(pcp, val)		percpu_to_op(8, volatile, "mov", (pcp), val)
-#define this_cpu_add_8(pcp, val)		percpu_add_op(8, volatile, (pcp), val)
-#define this_cpu_and_8(pcp, val)		percpu_to_op(8, volatile, "and", (pcp), val)
-#define this_cpu_or_8(pcp, val)			percpu_to_op(8, volatile, "or", (pcp), val)
-#define this_cpu_add_return_8(pcp, val)		percpu_add_return_op(8, volatile, pcp, val)
-#define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(8, volatile, pcp, nval)
-#define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
+#define this_cpu_read_8(pcp)				percpu_from_op(8, volatile, "mov", pcp)
+#define this_cpu_write_8(pcp, val)			percpu_to_op(8, volatile, "mov", (pcp), val)
+#define this_cpu_add_8(pcp, val)			percpu_add_op(8, volatile, (pcp), val)
+#define this_cpu_and_8(pcp, val)			percpu_to_op(8, volatile, "and", (pcp), val)
+#define this_cpu_or_8(pcp, val)				percpu_to_op(8, volatile, "or", (pcp), val)
+#define this_cpu_add_return_8(pcp, val)			percpu_add_return_op(8, volatile, pcp, val)
+#define this_cpu_xchg_8(pcp, nval)			percpu_xchg_op(8, volatile, pcp, nval)
+#define this_cpu_cmpxchg_local_8(pcp, oval, nval)	percpu_cmpxchg_op(8, volatile, pcp, oval, nval, "")
+#define this_cpu_cmpxchg_8(pcp, oval, nval)		percpu_cmpxchg_op(8, volatile, pcp, oval, nval, LOCK_PREFIX)
 
 /*
  * Pretty complex macro to generate cmpxchg16 instruction.  The instruction