tools headers barrier: Fix arm64 tools build failure wrt smp_load_{acquire,release}

Cheers for reporting this. I managed to reproduce the build failure with
gcc version 6.3.0 20170516 (Debian 6.3.0-18+deb9u1).

The code in question is the arm64 versions of smp_load_acquire() and
smp_store_release(). Unlike other architectures, these are not built
around READ_ONCE() and WRITE_ONCE() since we have instructions we can
use instead of fences. Bringing our macros up-to-date with those (i.e.
tweaking the union initialisation and using the special "uXX_alias_t"
types) appears to fix the issue for me.

Committer notes:

Testing it in the systems previously failing:

  # time dm android-ndk:r12b-arm \
         android-ndk:r15c-arm \
         debian:experimental-x-arm64 \
         ubuntu:14.04.4-x-linaro-arm64 \
         ubuntu:16.04-x-arm \
         ubuntu:16.04-x-arm64 \
         ubuntu:18.04-x-arm \
         ubuntu:18.04-x-arm64
    1 android-ndk:r12b-arm          : Ok   arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease)
    2 android-ndk:r15c-arm          : Ok   arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease)
    3 debian:experimental-x-arm64   : Ok   aarch64-linux-gnu-gcc (Debian 8.2.0-7) 8.2.0
    4 ubuntu:14.04.4-x-linaro-arm64 : Ok   aarch64-linux-gnu-gcc (Linaro GCC 5.5-2017.10) 5.5.0
    5 ubuntu:16.04-x-arm            : Ok   arm-linux-gnueabihf-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
    6 ubuntu:16.04-x-arm64          : Ok   aarch64-linux-gnu-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609
    7 ubuntu:18.04-x-arm            : Ok   arm-linux-gnueabihf-gcc (Ubuntu/Linaro 7.3.0-27ubuntu1~18.04) 7.3.0
    8 ubuntu:18.04-x-arm64          : Ok   aarch64-linux-gnu-gcc (Ubuntu/Linaro 7.3.0-27ubuntu1~18.04) 7.3.0

Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20181031174408.GA27871@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/arch/arm64/include/asm/barrier.h

@@ -14,74 +14,75 @@
 #define wmb()		asm volatile("dmb ishst" ::: "memory")
 #define rmb()		asm volatile("dmb ishld" ::: "memory")
 
-#define smp_store_release(p, v)					\
-do {								\
-	union { typeof(*p) __val; char __c[1]; } __u =		\
-		{ .__val = (__force typeof(*p)) (v) }; 		\
-								\
-	switch (sizeof(*p)) {					\
-	case 1:							\
-		asm volatile ("stlrb %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u8 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 2:							\
-		asm volatile ("stlrh %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u16 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 4:							\
-		asm volatile ("stlr %w1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u32 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	case 8:							\
-		asm volatile ("stlr %1, %0"			\
-				: "=Q" (*p)			\
-				: "r" (*(__u64 *)__u.__c)	\
-				: "memory");			\
-		break;						\
-	default:						\
-		/* Only to shut up gcc ... */			\
-		mb();						\
-		break;						\
-	}							\
+#define smp_store_release(p, v)						\
+do {									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__val = (v) }; 					\
+									\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("stlrb %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u8_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile ("stlrh %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u16_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile ("stlr %w1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u32_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	case 8:								\
+		asm volatile ("stlr %1, %0"				\
+				: "=Q" (*p)				\
+				: "r" (*(__u64_alias_t *)__u.__c)	\
+				: "memory");				\
+		break;							\
+	default:							\
+		/* Only to shut up gcc ... */				\
+		mb();							\
+		break;							\
+	}								\
 } while (0)
 
-#define smp_load_acquire(p)					\
-({								\
-	union { typeof(*p) __val; char __c[1]; } __u;		\
-								\
-	switch (sizeof(*p)) {					\
-	case 1:							\
-		asm volatile ("ldarb %w0, %1"			\
-			: "=r" (*(__u8 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 2:							\
-		asm volatile ("ldarh %w0, %1"			\
-			: "=r" (*(__u16 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 4:							\
-		asm volatile ("ldar %w0, %1"			\
-			: "=r" (*(__u32 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	case 8:							\
-		asm volatile ("ldar %0, %1"			\
-			: "=r" (*(__u64 *)__u.__c)		\
-			: "Q" (*p) : "memory");			\
-		break;						\
-	default:						\
-		/* Only to shut up gcc ... */			\
-		mb();						\
-		break;						\
-	}							\
-	__u.__val;						\
+#define smp_load_acquire(p)						\
+({									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__c = { 0 } };					\
+									\
+	switch (sizeof(*p)) {						\
+	case 1:								\
+		asm volatile ("ldarb %w0, %1"				\
+			: "=r" (*(__u8_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 2:								\
+		asm volatile ("ldarh %w0, %1"				\
+			: "=r" (*(__u16_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 4:								\
+		asm volatile ("ldar %w0, %1"				\
+			: "=r" (*(__u32_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	case 8:								\
+		asm volatile ("ldar %0, %1"				\
+			: "=r" (*(__u64_alias_t *)__u.__c)		\
+			: "Q" (*p) : "memory");				\
+		break;							\
+	default:							\
+		/* Only to shut up gcc ... */				\
+		mb();							\
+		break;							\
+	}								\
+	__u.__val;							\
 })
 
 #endif /* _TOOLS_LINUX_ASM_AARCH64_BARRIER_H */