fuse: Optimize request_end() by not taking fiq->waitq.lock

We take global fiq->waitq.lock every time, when we are in this function,
but interrupted requests are just small subset of all requests. This patch
optimizes request_end() and makes it to take the lock when it's really
needed.

queue_interrupt() needs small change for that. After req is linked to
interrupt list, we do smp_mb() and check for FR_FINISHED again. In case of
FR_FINISHED bit has appeared, we remove req and leave the function:

Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>

fs/fuse/dev.c

@@ -431,10 +431,16 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req)
 
 	if (test_and_set_bit(FR_FINISHED, &req->flags))
 		goto put_request;
-
-	spin_lock(&fiq->waitq.lock);
-	list_del_init(&req->intr_entry);
-	spin_unlock(&fiq->waitq.lock);
+	/*
+	 * test_and_set_bit() implies smp_mb() between bit
+	 * changing and below intr_entry check. Pairs with
+	 * smp_mb() from queue_interrupt().
+	 */
+	if (!list_empty(&req->intr_entry)) {
+		spin_lock(&fiq->waitq.lock);
+		list_del_init(&req->intr_entry);
+		spin_unlock(&fiq->waitq.lock);
+	}
 	WARN_ON(test_bit(FR_PENDING, &req->flags));
 	WARN_ON(test_bit(FR_SENT, &req->flags));
 	if (test_bit(FR_BACKGROUND, &req->flags)) {
@@ -473,12 +479,18 @@ put_request:
 static void queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
 {
 	spin_lock(&fiq->waitq.lock);
-	if (test_bit(FR_FINISHED, &req->flags)) {
-		spin_unlock(&fiq->waitq.lock);
-		return;
-	}
 	if (list_empty(&req->intr_entry)) {
 		list_add_tail(&req->intr_entry, &fiq->interrupts);
+		/*
+		 * Pairs with smp_mb() implied by test_and_set_bit()
+		 * from request_end().
+		 */
+		smp_mb();
+		if (test_bit(FR_FINISHED, &req->flags)) {
+			list_del_init(&req->intr_entry);
+			spin_unlock(&fiq->waitq.lock);
+			return;
+		}
 		wake_up_locked(&fiq->waitq);
 		kill_fasync(&fiq->fasync, SIGIO, POLL_IN);
 	}