x86/percpu: Convert this_percpu_xchg_op() from asm() to C code, to generate better code

Rewrite percpu_xchg_op() using generic percpu primitives instead
of using asm. The new implementation is similar to local_xchg() and
allows the compiler to perform various optimizations: e.g. the
compiler is able to create fast path through the loop, according
to likely/unlikely annotations in percpu_try_cmpxchg_op().

No functional changes intended.

Signed-off-by: Uros Bizjak <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Linus Torvalds <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

Author: ubizjak

arch/x86/include/asm/percpu.h

@@ -230,25 +230,15 @@ do {									\
 })
 
 /*
- * 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.
+ * this_cpu_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(size, qual, _var, _nval)				\
+#define this_percpu_xchg_op(_var, _nval)				\
 ({									\
-	__pcpu_type_##size pxo_old__;					\
-	__pcpu_type_##size pxo_new__ = __pcpu_cast_##size(_nval);	\
-	asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]),		\
-				    "%[oval]")				\
-		  "\n1:\t"						\
-		  __pcpu_op2_##size("cmpxchg", "%[nval]",		\
-				    __percpu_arg([var]))		\
-		  "\n\tjnz 1b"						\
-		  : [oval] "=&a" (pxo_old__),				\
-		    [var] "+m" (__my_cpu_var(_var))			\
-		  : [nval] __pcpu_reg_##size(, pxo_new__)		\
-		  : "memory");						\
-	(typeof(_var))(unsigned long) pxo_old__;			\
+	typeof(_var) pxo_old__ = this_cpu_read(_var);			\
+	do { } while (!this_cpu_try_cmpxchg(_var, &pxo_old__, _nval));	\
+	pxo_old__;							\
 })
 
 /*
@@ -534,9 +524,9 @@ do {									\
 #define this_cpu_or_1(pcp, val)		percpu_to_op(1, volatile, "or", (pcp), val)
 #define this_cpu_or_2(pcp, val)		percpu_to_op(2, volatile, "or", (pcp), val)
 #define this_cpu_or_4(pcp, val)		percpu_to_op(4, volatile, "or", (pcp), val)
-#define this_cpu_xchg_1(pcp, nval)	percpu_xchg_op(1, volatile, pcp, nval)
-#define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(2, volatile, pcp, nval)
-#define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(4, volatile, pcp, nval)
+#define this_cpu_xchg_1(pcp, nval)	this_percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_2(pcp, nval)	this_percpu_xchg_op(pcp, nval)
+#define this_cpu_xchg_4(pcp, nval)	this_percpu_xchg_op(pcp, nval)
 
 #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)
@@ -575,7 +565,7 @@ do {									\
 #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_xchg_8(pcp, nval)		this_percpu_xchg_op(pcp, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, volatile, pcp, oval, nval)
 #define this_cpu_try_cmpxchg_8(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, volatile, pcp, ovalp, nval)
 #endif