locking/atomic/x86: Use ALT_OUTPUT_SP() for __arch_{,try_}cmpxchg64_emu()

x86_32 __arch_{,try_}cmpxchg64_emu()() macros use CALL instruction
inside asm statement. Use ALT_OUTPUT_SP() macro to add required
dependence on %esp register.

Fixes: 79e1dd0 ("x86: Provide an alternative() based cmpxchg64()")
Signed-off-by: Uros Bizjak <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

Author: ubizjak

arch/x86/include/asm/cmpxchg_32.h

@@ -94,7 +94,7 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 *ptr, u64 *oldp,
 	asm volatile(ALTERNATIVE(_lock_loc				\
 				 "call cmpxchg8b_emu",			\
 				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
-		     : "+a" (o.low), "+d" (o.high)			\
+		     : ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high))	\
 		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
 		     : "memory");					\
 									\
@@ -123,8 +123,8 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64
 				 "call cmpxchg8b_emu",			\
 				 _lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
 		     CC_SET(e)						\
-		     : CC_OUT(e) (ret),					\
-		       "+a" (o.low), "+d" (o.high)			\
+		     : ALT_OUTPUT_SP(CC_OUT(e) (ret),			\
+				     "+a" (o.low), "+d" (o.high))	\
 		     : "b" (n.low), "c" (n.high), [ptr] "S" (_ptr)	\
 		     : "memory");					\
 									\