arm64: rwlocks: don't fail trylock purely due to contention

STXR can fail for a number of reasons, so don't fail an rwlock trylock
operation simply because the STXR reported failure.

I'm not aware of any issues with the current code, but this makes it
consistent with spin_trylock and also other architectures (e.g. arch/arm).
Reported-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

arch/arm64/include/asm/spinlock.h

@@ -140,10 +140,11 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 	unsigned int tmp;
 
 	asm volatile(
-	"	ldaxr	%w0, %1\n"
-	"	cbnz	%w0, 1f\n"
+	"1:	ldaxr	%w0, %1\n"
+	"	cbnz	%w0, 2f\n"
 	"	stxr	%w0, %w2, %1\n"
-	"1:\n"
+	"	cbnz	%w0, 1b\n"
+	"2:\n"
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
 	: "memory");
@@ -209,11 +210,12 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 	unsigned int tmp, tmp2 = 1;
 
 	asm volatile(
-	"	ldaxr	%w0, %2\n"
+	"1:	ldaxr	%w0, %2\n"
 	"	add	%w0, %w0, #1\n"
-	"	tbnz	%w0, #31, 1f\n"
+	"	tbnz	%w0, #31, 2f\n"
 	"	stxr	%w1, %w0, %2\n"
-	"1:\n"
+	"	cbnz	%w1, 1b\n"
+	"2:\n"
 	: "=&r" (tmp), "+r" (tmp2), "+Q" (rw->lock)
 	:
 	: "memory");