[PATCH 3.16 48/63] x86/atomic: Fix smp_mb__{before,after}_atomic()

[Ben Hutchings]

3.16.81-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

commit 69d927bba39517d0980462efc051875b7f4db185 upstream.

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) <peterz@xxxxxxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Signed-off-by: Jari Ruusu <jari.ruusu@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
 arch/x86/include/asm/atomic.h      | 8 ++++----
 arch/x86/include/asm/atomic64_64.h | 8 ++++----
 arch/x86/include/asm/barrier.h     | 4 ++--
 3 files changed, 10 insertions(+), 10 deletions(-)

--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -49,7 +49,7 @@ static inline void atomic_add(int i, ato
 {
 	asm volatile(LOCK_PREFIX "addl %1,%0"
 		     : "+m" (v->counter)
-		     : "ir" (i));
+		     : "ir" (i) : "memory");
 }
 
 /**
@@ -63,7 +63,7 @@ static inline void atomic_sub(int i, ato
 {
 	asm volatile(LOCK_PREFIX "subl %1,%0"
 		     : "+m" (v->counter)
-		     : "ir" (i));
+		     : "ir" (i) : "memory");
 }
 
 /**
@@ -89,7 +89,7 @@ static inline int atomic_sub_and_test(in
 static inline void atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
-		     : "+m" (v->counter));
+		     : "+m" (v->counter) :: "memory");
 }
 
 /**
@@ -101,7 +101,7 @@ static inline void atomic_inc(atomic_t *
 static inline void atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
-		     : "+m" (v->counter));
+		     : "+m" (v->counter) :: "memory");
 }
 
 /**
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -44,7 +44,7 @@ static inline void atomic64_add(long i,
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
 		     : "=m" (v->counter)
-		     : "er" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter) : "memory");
 }
 
 /**
@@ -58,7 +58,7 @@ static inline void atomic64_sub(long i,
 {
 	asm volatile(LOCK_PREFIX "subq %1,%0"
 		     : "=m" (v->counter)
-		     : "er" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter) : "memory");
 }
 
 /**
@@ -85,7 +85,7 @@ static inline void atomic64_inc(atomic64
 {
 	asm volatile(LOCK_PREFIX "incq %0"
 		     : "=m" (v->counter)
-		     : "m" (v->counter));
+		     : "m" (v->counter) : "memory");
 }
 
 /**
@@ -98,7 +98,7 @@ static inline void atomic64_dec(atomic64
 {
 	asm volatile(LOCK_PREFIX "decq %0"
 		     : "=m" (v->counter)
-		     : "m" (v->counter));
+		     : "m" (v->counter) : "memory");
 }
 
 /**
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -167,8 +167,8 @@ do {									\
 #endif
 
 /* 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)
 
 /*
  * Stop RDTSC speculation. This is needed when you need to use RDTSC