memory barrier: adding smp_mb__after_lock

Adding smp_mb__after_lock define to be used as a smp_mb call after
a lock.

Making it nop for x86, since {read|write|spin}_lock() on x86 are
full memory barriers.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/x86/include/asm/spinlock.h

@@ -302,4 +302,8 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw)
 #define _raw_read_relax(lock)	cpu_relax()
 #define _raw_write_relax(lock)	cpu_relax()
 
+/* The {read|write|spin}_lock() on x86 are full memory barriers. */
+static inline void smp_mb__after_lock(void) { }
+#define ARCH_HAS_SMP_MB_AFTER_LOCK
+
 #endif /* _ASM_X86_SPINLOCK_H */

include/linux/spinlock.h

@@ -132,6 +132,11 @@ do {								\
 #endif /*__raw_spin_is_contended*/
 #endif
 
+/* The lock does not imply full memory barrier. */
+#ifndef ARCH_HAS_SMP_MB_AFTER_LOCK
+static inline void smp_mb__after_lock(void) { smp_mb(); }
+#endif
+
 /**
  * spin_unlock_wait - wait until the spinlock gets unlocked
  * @lock: the spinlock in question.

include/net/sock.h

@@ -1271,6 +1271,9 @@ static inline int sk_has_allocations(const struct sock *sk)
  * in its cache, and so does the tp->rcv_nxt update on CPU2 side.  The CPU1
  * could then endup calling schedule and sleep forever if there are no more
  * data on the socket.
+ *
+ * The sk_has_sleeper is always called right after a call to read_lock, so we
+ * can use smp_mb__after_lock barrier.
  */
 static inline int sk_has_sleeper(struct sock *sk)
 {
@@ -1280,7 +1283,7 @@ static inline int sk_has_sleeper(struct sock *sk)
 	 *
 	 * This memory barrier is paired in the sock_poll_wait.
 	 */
-	smp_mb();
+	smp_mb__after_lock();
 	return sk->sk_sleep && waitqueue_active(sk->sk_sleep);
 }