x86/atomic: Fix smp_mb__{before,after}_atomic()

Recent probing at the Linux Kernel Memory Model uncovered a
'surprise'. Strongly ordered architectures where the atomic RmW
primitive implies full memory ordering and
smp_mb__{before,after}_atomic() are a simple barrier() (such as x86)
fail for:

*x = 1;
atomic_inc(u);
smp_mb__after_atomic();
r0 = *y;

Because, while the atomic_inc() implies memory order, it
(surprisingly) does not provide a compiler barrier. This then allows
the compiler to re-order like so:

atomic_inc(u);
*x = 1;
smp_mb__after_atomic();
r0 = *y;

Which the CPU is then allowed to re-order (under TSO rules) like:

atomic_inc(u);
r0 = *y;
*x = 1;

And this very much was not intended. Therefore strengthen the atomic
RmW ops to include a compiler barrier.

NOTE: atomic_{or,and,xor} and the bitops already had the compiler
barrier.

Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Cc: Linus Torvalds <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Cc: Thomas Gleixner <[e-mail]>
Signed-off-by: Ingo Molnar <[e-mail]>

Documentation/atomic_t.txt

···
 ordering on their SMP atomic primitives. For example our TSO architectures
 provide full ordered atomics and these barriers are no-ops.
 
+NOTE: when the atomic RmW ops are fully ordered, they should also imply a
+compiler barrier.
+
 Thus:
 
   atomic_fetch_add();

arch/x86/include/asm/atomic.h

···
 {
 	asm volatile(LOCK_PREFIX "addl %1,%0"
 		     : "+m" (v->counter)
-		     : "ir" (i));
+		     : "ir" (i) : "memory");
 }
 
 /**
···
 {
 	asm volatile(LOCK_PREFIX "subl %1,%0"
 		     : "+m" (v->counter)
-		     : "ir" (i));
+		     : "ir" (i) : "memory");
 }
 
 /**
···
 static __always_inline void arch_atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
-		     : "+m" (v->counter));
+		     : "+m" (v->counter) :: "memory");
 }
 #define arch_atomic_inc arch_atomic_inc
 
···
 static __always_inline void arch_atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
-		     : "+m" (v->counter));
+		     : "+m" (v->counter) :: "memory");
 }
 #define arch_atomic_dec arch_atomic_dec
 

arch/x86/include/asm/atomic64_64.h

···
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
 		     : "=m" (v->counter)
-		     : "er" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter) : "memory");
 }
 
 /**
···
 {
 	asm volatile(LOCK_PREFIX "subq %1,%0"
 		     : "=m" (v->counter)
-		     : "er" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter) : "memory");
 }
 
 /**
···
 {
 	asm volatile(LOCK_PREFIX "incq %0"
 		     : "=m" (v->counter)
-		     : "m" (v->counter));
+		     : "m" (v->counter) : "memory");
 }
 #define arch_atomic64_inc arch_atomic64_inc
 
···
 {
 	asm volatile(LOCK_PREFIX "decq %0"
 		     : "=m" (v->counter)
-		     : "m" (v->counter));
+		     : "m" (v->counter) : "memory");
 }
 #define arch_atomic64_dec arch_atomic64_dec
 

arch/x86/include/asm/barrier.h

···
 })
 
 /* Atomic operations are already serializing on x86 */
-#define __smp_mb__before_atomic()	barrier()
-#define __smp_mb__after_atomic()	barrier()
+#define __smp_mb__before_atomic()	do { } while (0)
+#define __smp_mb__after_atomic()	do { } while (0)
 
 #include <asm-generic/barrier.h>