arm64: barrier: Use '__unqual_scalar_typeof' for acquire/release macros

Passing volatile-qualified pointers to the arm64 implementations of the
load-acquire/store-release macros results in a re-load from the stack
and a bunch of associated stack-protector churn due to the temporary
result variable inheriting the volatile semantics thanks to the use of
'typeof()'.

Define these temporary variables using 'unqual_scalar_typeof' to drop
the volatile qualifier in the case that they are scalar types.

Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>

arch/arm64/include/asm/barrier.h

@@ -76,8 +76,8 @@ static inline unsigned long array_index_mask_nospec(unsigned long idx,
 #define __smp_store_release(p, v)					\
 do {									\
 	typeof(p) __p = (p);						\
-	union { typeof(*p) __val; char __c[1]; } __u =			\
-		{ .__val = (__force typeof(*p)) (v) };			\
+	union { __unqual_scalar_typeof(*p) __val; char __c[1]; } __u =	\
+		{ .__val = (__force __unqual_scalar_typeof(*p)) (v) };	\
 	compiletime_assert_atomic_type(*p);				\
 	kasan_check_write(__p, sizeof(*p));				\
 	switch (sizeof(*p)) {						\
@@ -110,7 +110,7 @@ do {									\
 
 #define __smp_load_acquire(p)						\
 ({									\
-	union { typeof(*p) __val; char __c[1]; } __u;			\
+	union { __unqual_scalar_typeof(*p) __val; char __c[1]; } __u;	\
 	typeof(p) __p = (p);						\
 	compiletime_assert_atomic_type(*p);				\
 	kasan_check_read(__p, sizeof(*p));				\
@@ -136,33 +136,33 @@ do {									\
 			: "Q" (*__p) : "memory");			\
 		break;							\
 	}								\
-	__u.__val;							\
+	(typeof(*p))__u.__val;						\
 })
 
 #define smp_cond_load_relaxed(ptr, cond_expr)				\
 ({									\
 	typeof(ptr) __PTR = (ptr);					\
-	typeof(*ptr) VAL;						\
+	__unqual_scalar_typeof(*ptr) VAL;				\
 	for (;;) {							\
 		VAL = READ_ONCE(*__PTR);				\
 		if (cond_expr)						\
 			break;						\
 		__cmpwait_relaxed(__PTR, VAL);				\
 	}								\
-	VAL;								\
+	(typeof(*ptr))VAL;						\
 })
 
 #define smp_cond_load_acquire(ptr, cond_expr)				\
 ({									\
 	typeof(ptr) __PTR = (ptr);					\
-	typeof(*ptr) VAL;						\
+	__unqual_scalar_typeof(*ptr) VAL;				\
 	for (;;) {							\
 		VAL = smp_load_acquire(__PTR);				\
 		if (cond_expr)						\
 			break;						\
 		__cmpwait_relaxed(__PTR, VAL);				\
 	}								\
-	VAL;								\
+	(typeof(*ptr))VAL;						\
 })
 
 #include <asm-generic/barrier.h>