arm64: atomics: lse: Dereference matching size

When building with -Warray-bounds, the following warning is generated:

In file included from ./arch/arm64/include/asm/lse.h:16,
                 from ./arch/arm64/include/asm/cmpxchg.h:14,
                 from ./arch/arm64/include/asm/atomic.h:16,
                 from ./include/linux/atomic.h:7,
                 from ./include/asm-generic/bitops/atomic.h:5,
                 from ./arch/arm64/include/asm/bitops.h:25,
                 from ./include/linux/bitops.h:33,
                 from ./include/linux/kernel.h:22,
                 from kernel/printk/printk.c:22:
./arch/arm64/include/asm/atomic_lse.h:247:9: warning: array subscript 'long unsigned int[0]' is partly outside array bounds of 'atomic_t[1]' [-Warray-bounds]
  247 |         asm volatile(                                                   \
      |         ^~~
./arch/arm64/include/asm/atomic_lse.h:266:1: note: in expansion of macro '__CMPXCHG_CASE'
  266 | __CMPXCHG_CASE(w,  , acq_, 32,  a, "memory")
      | ^~~~~~~~~~~~~~
kernel/printk/printk.c:3606:17: note: while referencing 'printk_cpulock_owner'
 3606 | static atomic_t printk_cpulock_owner = ATOMIC_INIT(-1);
      |                 ^~~~~~~~~~~~~~~~~~~~

This is due to the compiler seeing an unsigned long * cast against
something (atomic_t) that is int sized. Replace the cast with the
matching size cast. This results in no change in binary output.

Note that __ll_sc__cmpxchg_case_##name##sz already uses the same
constraint:

	[v] "+Q" (*(u##sz *)ptr

Which is why only the LSE form needs updating and not the
LL/SC form, so this change is unlikely to be problematic.

Cc: Will Deacon <will@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: linux-arm-kernel@lists.infradead.org
Acked-by: Ard Biesheuvel <ardb@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20220112202259.3950286-1-keescook@chromium.org
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>

Author: kees

arch/arm64/include/asm/atomic_lse.h

@@ -249,7 +249,7 @@ __lse__cmpxchg_case_##name##sz(volatile void *ptr,			\
 	"	mov	%" #w "[tmp], %" #w "[old]\n"			\
 	"	cas" #mb #sfx "\t%" #w "[tmp], %" #w "[new], %[v]\n"	\
 	"	mov	%" #w "[ret], %" #w "[tmp]"			\
-	: [ret] "+r" (x0), [v] "+Q" (*(unsigned long *)ptr),		\
+	: [ret] "+r" (x0), [v] "+Q" (*(u##sz *)ptr),			\
 	  [tmp] "=&r" (tmp)						\
 	: [old] "r" (x1), [new] "r" (x2)				\
 	: cl);								\

arch/arm64/include/asm/cmpxchg.h

@@ -243,7 +243,7 @@ static inline void __cmpwait_case_##sz(volatile void *ptr,		\
 	"	cbnz	%" #w "[tmp], 1f\n"				\
 	"	wfe\n"							\
 	"1:"								\
-	: [tmp] "=&r" (tmp), [v] "+Q" (*(unsigned long *)ptr)		\
+	: [tmp] "=&r" (tmp), [v] "+Q" (*(u##sz *)ptr)			\
 	: [val] "r" (val));						\
 }