arm64: compat: fix stxr failure case in SWP emulation

commit 589cb22b upstream.

If the STXR instruction fails in the SWP emulation code, we leave *data
overwritten with the loaded value, therefore corrupting the data written
by a subsequent, successful attempt.

This patch re-jigs the code so that we only write back to *data once we
know that the update has happened.

Fixes: bd35a4ad ("arm64: Port SWP/SWPB emulation support from arm")
Reported-by: Shengjiu Wang <shengjiu.wang@freescale.com>
Reported-by: Vladimir Murzin <vladimir.murzin@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Kamal Mostafa <kamal@canonical.com>

arch/arm64/kernel/armv8_deprecated.c

@@ -228,21 +228,23 @@ static void register_insn_emulation_sysctl(struct ctl_table *table)
  */
 #define __user_swpX_asm(data, addr, res, temp, B)		\
 	__asm__ __volatile__(					\
-	"	mov		%w2, %w1\n"			\
-	"0:	ldxr"B"		%w1, [%3]\n"			\
-	"1:	stxr"B"		%w0, %w2, [%3]\n"		\
+	"0:	ldxr"B"		%w2, [%3]\n"			\
+	"1:	stxr"B"		%w0, %w1, [%3]\n"		\
 	"	cbz		%w0, 2f\n"			\
 	"	mov		%w0, %w4\n"			\
+	"	b		3f\n"				\
 	"2:\n"							\
+	"	mov		%w1, %w2\n"			\
+	"3:\n"							\
 	"	.pushsection	 .fixup,\"ax\"\n"		\
 	"	.align		2\n"				\
-	"3:	mov		%w0, %w5\n"			\
-	"	b		2b\n"				\
+	"4:	mov		%w0, %w5\n"			\
+	"	b		3b\n"				\
 	"	.popsection"					\
 	"	.pushsection	 __ex_table,\"a\"\n"		\
 	"	.align		3\n"				\
-	"	.quad		0b, 3b\n"			\
-	"	.quad		1b, 3b\n"			\
+	"	.quad		0b, 4b\n"			\
+	"	.quad		1b, 4b\n"			\
 	"	.popsection"					\
 	: "=&r" (res), "+r" (data), "=&r" (temp)		\
 	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\