diff --git a/arch/arm64/include/asm/futex.h b/arch/arm64/include/asm/futex.h
index cccb83ad7fa8..e1d95f08f8e1 100644
--- a/arch/arm64/include/asm/futex.h
+++ b/arch/arm64/include/asm/futex.h
@@ -30,8 +30,8 @@ do {									\
 "	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
-"2:	stlxr	%w3, %w0, %2\n"						\
-"	cbnz	%w3, 1b\n"						\
+"2:	stlxr	%w0, %w3, %2\n"						\
+"	cbnz	%w0, 1b\n"						\
 "	dmb	ish\n"							\
 "3:\n"									\
 "	.pushsection .fixup,\"ax\"\n"					\
@@ -50,30 +50,30 @@ do {									\
 static inline int
 arch_futex_atomic_op_inuser(int op, int oparg, int *oval, u32 __user *_uaddr)
 {
-	int oldval = 0, ret, tmp;
+	int oldval, ret, tmp;
 	u32 __user *uaddr = __uaccess_mask_ptr(_uaddr);
 
 	pagefault_disable();
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%w0, %w4",
+		__futex_atomic_op("mov	%w3, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%w0, %w1, %w4",
+		__futex_atomic_op("add	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%w0, %w1, %w4",
+		__futex_atomic_op("orr	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%w0, %w1, %w4",
+		__futex_atomic_op("and	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%w0, %w1, %w4",
+		__futex_atomic_op("eor	%w3, %w1, %w4",
 				  ret, oldval, uaddr, tmp, oparg);
 		break;
 	default: