x86/locking: Use ALT_OUTPUT_SP() for percpu_{,try_}cmpxchg{64,128}_op()

percpu_{,try_}cmpxchg{64,128}() macros use CALL instruction inside
asm statement in one of their alternatives. Use ALT_OUTPUT_SP()
macro to add required dependence on %esp register.

ALT_OUTPUT_SP() implements the above dependence by adding
ASM_CALL_CONSTRAINT to its arguments. This constraint should be used
for any inline asm which has a CALL instruction, otherwise the
compiler may schedule the asm before the frame pointer gets set up
by the containing function, causing objtool to print a "call without
frame pointer save/setup" warning.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250214150929.5780-1-ubizjak@gmail.com

Author: ubizjak

arch/x86/include/asm/percpu.h

@@ -350,9 +350,9 @@ do {									\
 									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
 			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
+		  : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				  "+a" (old__.low),			\
+				  "+d" (old__.high))			\
 		  : "b" (new__.low),					\
 		    "c" (new__.high),					\
 		    "S" (&(_var))					\
@@ -381,10 +381,10 @@ do {									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
 			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
 		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
+		  : ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				  [var] "+m" (__my_cpu_var(_var)),	\
+				  "+a" (old__.low),			\
+				  "+d" (old__.high))			\
 		  : "b" (new__.low),					\
 		    "c" (new__.high),					\
 		    "S" (&(_var))					\
@@ -421,9 +421,9 @@ do {									\
 									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
 			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  : [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
+		  : ALT_OUTPUT_SP([var] "+m" (__my_cpu_var(_var)),	\
+				  "+a" (old__.low),			\
+				  "+d" (old__.high))			\
 		  : "b" (new__.low),					\
 		    "c" (new__.high),					\
 		    "S" (&(_var))					\
@@ -452,10 +452,10 @@ do {									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
 			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
 		  CC_SET(z)						\
-		  : CC_OUT(z) (success),				\
-		    [var] "+m" (__my_cpu_var(_var)),			\
-		    "+a" (old__.low),					\
-		    "+d" (old__.high)					\
+		  : ALT_OUTPUT_SP(CC_OUT(z) (success),			\
+				  [var] "+m" (__my_cpu_var(_var)),	\
+				  "+a" (old__.low),			\
+				  "+d" (old__.high))			\
 		  : "b" (new__.low),					\
 		    "c" (new__.high),					\
 		    "S" (&(_var))					\