arm64: uaccess: permit __smp_store_release() to use zero register

Currently the asm constraints for __smp_store_release() require that the
value is placed in a "real" GPR (i.e. one other than [XW]ZR or SP).
This means that for cases such as:

    __smp_store_release(ptr, 0)

... the compiler has to move '0' into "real" GPR, e.g.

    mov     xN, #0
    stlr    xN, [<addr>]

This is unfortunate, as using the zero register would require fewer
instructions and save a "real" GPR for other usage, allowing the
compiler to generate:

    stlr    xzr, [<addr>]

Modify the asm constaints for __smp_store_release() to permit the use of
the zero register for the value.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <[email protected]>
Cc: Catalin Marinas <[email protected]>
Cc: Robin Murphy <[email protected]>
Cc: Will Deacon <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>

Author: mrutland-arm

arch/arm64/include/asm/barrier.h

@@ -131,25 +131,25 @@ do {									\
 	case 1:								\
 		asm volatile ("stlrb %w1, %0"				\
 				: "=Q" (*__p)				\
-				: "r" (*(__u8 *)__u.__c)		\
+				: "rZ" (*(__u8 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("stlrh %w1, %0"				\
 				: "=Q" (*__p)				\
-				: "r" (*(__u16 *)__u.__c)		\
+				: "rZ" (*(__u16 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
 				: "=Q" (*__p)				\
-				: "r" (*(__u32 *)__u.__c)		\
+				: "rZ" (*(__u32 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	case 8:								\
-		asm volatile ("stlr %1, %0"				\
+		asm volatile ("stlr %x1, %0"				\
 				: "=Q" (*__p)				\
-				: "r" (*(__u64 *)__u.__c)		\
+				: "rZ" (*(__u64 *)__u.__c)		\
 				: "memory");				\
 		break;							\
 	}								\