x86/percpu: Move raw_percpu_xchg_op() to a better place

Move raw_percpu_xchg_op() together with this_percpu_xchg_op()
and trivially rename some internal variables to harmonize them
between macro implementations.

No functional changes intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20240320083127.493250-2-ubizjak@gmail.com

Author: ubizjak

arch/x86/include/asm/percpu.h

@@ -229,6 +229,17 @@ do {									\
 	(typeof(_var))(unsigned long) (paro_tmp__ + _val);		\
 })
 
+/*
+ * raw_cpu_xchg() can use a load-store since
+ * it is not required to be IRQ-safe.
+ */
+#define raw_percpu_xchg_op(_var, _nval)					\
+({									\
+	typeof(_var) pxo_old__ = raw_cpu_read(_var);			\
+	raw_cpu_write(_var, _nval);					\
+	pxo_old__;							\
+})
+
 /*
  * this_cpu_xchg() is implemented using cmpxchg without a lock prefix.
  * xchg is expensive due to the implied lock prefix. The processor
@@ -499,18 +510,6 @@ do {									\
 #define raw_cpu_or_1(pcp, val)		percpu_to_op(1, , "or", (pcp), val)
 #define raw_cpu_or_2(pcp, val)		percpu_to_op(2, , "or", (pcp), val)
 #define raw_cpu_or_4(pcp, val)		percpu_to_op(4, , "or", (pcp), val)
-
-/*
- * raw_cpu_xchg() can use a load-store since it is not required to be
- * IRQ-safe.
- */
-#define raw_percpu_xchg_op(var, nval)					\
-({									\
-	typeof(var) pxo_ret__ = raw_cpu_read(var);			\
-	raw_cpu_write(var, (nval));					\
-	pxo_ret__;							\
-})
-
 #define raw_cpu_xchg_1(pcp, val)	raw_percpu_xchg_op(pcp, val)
 #define raw_cpu_xchg_2(pcp, val)	raw_percpu_xchg_op(pcp, val)
 #define raw_cpu_xchg_4(pcp, val)	raw_percpu_xchg_op(pcp, val)