block, bfq: make bfq_has_work() more accurate

bfq_has_work() is using busy_queues currently, which is not accurate
because bfq_queue is busy doesn't represent that it has requests. Since
bfqd aready has a counter 'queued' to record how many requests are in
bfq, use it instead of busy_queues.

Noted that bfq_has_work() can be called with 'bfqd->lock' held, thus the
lock can't be held in bfq_has_work() to protect 'bfqd->queued'.
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://lore.kernel.org/r/20220513023507.2625717-3-yukuai3@huawei.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

block/bfq-iosched.c

@@ -2204,7 +2204,11 @@ static void bfq_add_request(struct request *rq)
 
 	bfq_log_bfqq(bfqd, bfqq, "add_request %d", rq_is_sync(rq));
 	bfqq->queued[rq_is_sync(rq)]++;
-	bfqd->queued++;
+	/*
+	 * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
+	 * may be read without holding the lock in bfq_has_work().
+	 */
+	WRITE_ONCE(bfqd->queued, bfqd->queued + 1);
 
 	if (RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_sync(bfqq)) {
 		bfq_check_waker(bfqd, bfqq, now_ns);
@@ -2396,7 +2400,11 @@ static void bfq_remove_request(struct request_queue *q,
 	if (rq->queuelist.prev != &rq->queuelist)
 		list_del_init(&rq->queuelist);
 	bfqq->queued[sync]--;
-	bfqd->queued--;
+	/*
+	 * Updating of 'bfqd->queued' is protected by 'bfqd->lock', however, it
+	 * may be read without holding the lock in bfq_has_work().
+	 */
+	WRITE_ONCE(bfqd->queued, bfqd->queued - 1);
 	elv_rb_del(&bfqq->sort_list, rq);
 
 	elv_rqhash_del(q, rq);
@@ -5057,11 +5065,11 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx)
 	struct bfq_data *bfqd = hctx->queue->elevator->elevator_data;
 
 	/*
-	 * Avoiding lock: a race on bfqd->busy_queues should cause at
+	 * Avoiding lock: a race on bfqd->queued should cause at
 	 * most a call to dispatch for nothing
 	 */
 	return !list_empty_careful(&bfqd->dispatch) ||
-		bfq_tot_busy_queues(bfqd) > 0;
+		READ_ONCE(bfqd->queued);
 }
 
 static struct request *__bfq_dispatch_request(struct blk_mq_hw_ctx *hctx)