arm64: add missing data types in smp_load_acquire/smp_store_release

Commit 8053871d0f7f ("smp: Fix smp_call_function_single_async()
locking") introduced a call to smp_load_acquire() with a u16 argument,
but we only cared about u32 and u64 types in that function so far.
This resulted in a compiler warning fortunately, pointing at an
uninitialized use. Due to the implementation structure the compiler
misses that bug in the smp_store_release(), though.
Add the u16 and u8 variants using ldarh/stlrh and ldarb/stlrb,
respectively. Together with the compiletime_assert_atomic_type() check
this should cover all cases now.

Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

arch/arm64/include/asm/barrier.h

@@ -65,6 +65,14 @@ do {									\
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("stlrb %w1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
+	case 2:								\
+		asm volatile ("stlrh %w1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
 				: "=Q" (*p) : "r" (v) : "memory");	\
@@ -81,6 +89,14 @@ do {									\
 	typeof(*p) ___p1;						\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("ldarb %w0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
+	case 2:								\
+		asm volatile ("ldarh %w0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
 	case 4:								\
 		asm volatile ("ldar %w0, %1"				\
 			: "=r" (___p1) : "Q" (*p) : "memory");		\