tools: add smp_* barrier variants to include infrastructure

Add the definition for smp_rmb(), smp_wmb(), and smp_mb() to the
tools include infrastructure: this patch adds the implementation
for x86-64 and arm64, and have it fall back as currently is for
other archs which do not have it implemented at this point. The
x86-64 one uses lock + add combination for smp_mb() with address
below red zone.

This is on top of 09d62154 ("tools, perf: add and use optimized
ring_buffer_{read_head, write_tail} helpers"), which didn't touch
smp_* barrier implementations. Magnus recently rightfully reported
however that the latter on x86-64 still wrongly falls back to sfence,
lfence and mfence respectively, thus fix that for applications under
tools making use of these to avoid such ugly surprises. The main
header under tools (include/asm/barrier.h) will in that case not
select the fallback implementation.
Reported-by: Magnus Karlsson <magnus.karlsson@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

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

@@ -14,6 +14,16 @@
 #define wmb()		asm volatile("dmb ishst" ::: "memory")
 #define rmb()		asm volatile("dmb ishld" ::: "memory")
 
+/*
+ * Kernel uses dmb variants on arm64 for smp_*() barriers. Pretty much the same
+ * implementation as above mb()/wmb()/rmb(), though for the latter kernel uses
+ * dsb. In any case, should above mb()/wmb()/rmb() change, make sure the below
+ * smp_*() don't.
+ */
+#define smp_mb()	asm volatile("dmb ish" ::: "memory")
+#define smp_wmb()	asm volatile("dmb ishst" ::: "memory")
+#define smp_rmb()	asm volatile("dmb ishld" ::: "memory")
+
 #define smp_store_release(p, v)						\
 do {									\
 	union { typeof(*p) __val; char __c[1]; } __u =			\

tools/arch/x86/include/asm/barrier.h

@@ -21,9 +21,12 @@
 #define rmb()	asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #define wmb()	asm volatile("lock; addl $0,0(%%esp)" ::: "memory")
 #elif defined(__x86_64__)
-#define mb() 	asm volatile("mfence":::"memory")
-#define rmb()	asm volatile("lfence":::"memory")
+#define mb()	asm volatile("mfence" ::: "memory")
+#define rmb()	asm volatile("lfence" ::: "memory")
 #define wmb()	asm volatile("sfence" ::: "memory")
+#define smp_rmb() barrier()
+#define smp_wmb() barrier()
+#define smp_mb()  asm volatile("lock; addl $0,-132(%%rsp)" ::: "memory", "cc")
 #endif
 
 #if defined(__x86_64__)