blk-mq: quiesce queue during switching io sched and updating nr_requests

Dispatch may still be in-progress after queue is frozen, so we have to
quiesce queue before switching IO scheduler and updating nr_requests.

Also when switching io schedulers, blk_mq_run_hw_queue() may still be
called somewhere(such as from nvme_reset_work()), and io scheduler's
per-hctx data may not be setup yet, so cause oops even inside
blk_mq_hctx_has_pending(), such as it can be run just between:

        ret = e->ops.mq.init_sched(q, e);
AND
        ret = e->ops.mq.init_hctx(hctx, i)

inside blk_mq_init_sched().

This reverts commit 7a148c2fcff8330(block: don't call blk_mq_quiesce_queue()
after queue is frozen) basically, and makes sure blk_mq_hctx_has_pending
won't be called if queue is quiesced.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Fixes: 7a148c2fcff83309(block: don't call blk_mq_quiesce_queue() after queue is frozen)
Reported-by: Yi Zhang <yi.zhang@redhat.com>
Tested-by: Yi Zhang <yi.zhang@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 28 insertions, 1 deletions

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 11097477eeab6..1c66c319325c6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1285,7 +1285,30 @@ EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
 
 bool blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
 {
-	if (blk_mq_hctx_has_pending(hctx)) {
+	int srcu_idx;
+	bool need_run;
+
+	/*
+	 * When queue is quiesced, we may be switching io scheduler, or
+	 * updating nr_hw_queues, or other things, and we can't run queue
+	 * any more, even __blk_mq_hctx_has_pending() can't be called safely.
+	 *
+	 * And queue will be rerun in blk_mq_unquiesce_queue() if it is
+	 * quiesced.
+	 */
+	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
+		rcu_read_lock();
+		need_run = !blk_queue_quiesced(hctx->queue) &&
+			blk_mq_hctx_has_pending(hctx);
+		rcu_read_unlock();
+	} else {
+		srcu_idx = srcu_read_lock(hctx->queue_rq_srcu);
+		need_run = !blk_queue_quiesced(hctx->queue) &&
+			blk_mq_hctx_has_pending(hctx);
+		srcu_read_unlock(hctx->queue_rq_srcu, srcu_idx);
+	}
+
+	if (need_run) {
 		__blk_mq_delay_run_hw_queue(hctx, async, 0);
 		return true;
 	}
@@ -2710,6 +2733,7 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 		return -EINVAL;
 
 	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue(q);
 
 	ret = 0;
 	queue_for_each_hw_ctx(q, hctx, i) {
@@ -2733,6 +2757,7 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr)
 	if (!ret)
 		q->nr_requests = nr;
 
+	blk_mq_unquiesce_queue(q);
 	blk_mq_unfreeze_queue(q);
 
 	return ret;
diff --git a/block/elevator.c b/block/elevator.c
index 7bda083d59684..138faeb08a7c3 100644
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -968,6 +968,7 @@ static int elevator_switch_mq(struct request_queue *q,
 	int ret;
 
 	blk_mq_freeze_queue(q);
+	blk_mq_quiesce_queue(q);
 
 	if (q->elevator) {
 		if (q->elevator->registered)
@@ -994,6 +995,7 @@ static int elevator_switch_mq(struct request_queue *q,
 		blk_add_trace_msg(q, "elv switch: none");
 
 out:
+	blk_mq_unquiesce_queue(q);
 	blk_mq_unfreeze_queue(q);
 	return ret;
 }