locking/osq: Relax atomic semantics

... by using acquire/release for ops around the lock->tail. As such,
weakly ordered archs can benefit from more relaxed use of barriers
when issuing atomics.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <Waiman.Long@hpe.com>
Link: http://lkml.kernel.org/r/1442216244-4409-3-git-send-email-dave@stgolabs.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>

kernel/locking/osq_lock.c

@@ -50,7 +50,7 @@ osq_wait_next(struct optimistic_spin_queue *lock,
 
 	for (;;) {
 		if (atomic_read(&lock->tail) == curr &&
-		    atomic_cmpxchg(&lock->tail, curr, old) == curr) {
+		    atomic_cmpxchg_acquire(&lock->tail, curr, old) == curr) {
 			/*
 			 * We were the last queued, we moved @lock back. @prev
 			 * will now observe @lock and will complete its
@@ -92,7 +92,11 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	node->next = NULL;
 	node->cpu = curr;
 
-	old = atomic_xchg(&lock->tail, curr);
+	/*
+	 * ACQUIRE semantics, pairs with corresponding RELEASE
+	 * in unlock() uncontended, or fastpath.
+	 */
+	old = atomic_xchg_acquire(&lock->tail, curr);
 	if (old == OSQ_UNLOCKED_VAL)
 		return true;
 
@@ -184,7 +188,8 @@ void osq_unlock(struct optimistic_spin_queue *lock)
 	/*
 	 * Fast path for the uncontended case.
 	 */
-	if (likely(atomic_cmpxchg(&lock->tail, curr, OSQ_UNLOCKED_VAL) == curr))
+	if (likely(atomic_cmpxchg_release(&lock->tail, curr,
+					  OSQ_UNLOCKED_VAL) == curr))
 		return;
 
 	/*