[PATCH V2 5/5] blk-mq: support concurrent queue quiesce/unquiesce

[Ming Lei]

Turns out that blk_mq_freeze_queue() isn't stronger[1] than
blk_mq_quiesce_queue() because dispatch may still be in-progress after
queue is frozen, and in several cases, such as switching io scheduler,
updating nr_requests & wbt latency, we still need to quiesce queue as a
supplement of freezing queue.

As we need to extend uses of blk_mq_quiesce_queue(), it is inevitable
for us to need support nested quiesce, especially we can't let
unquiesce happen when there is quiesce originated from other contexts.

This patch introduces q->mq_quiesce_depth to deal concurrent quiesce,
and we only unquiesce queue when it is the last/outer-most one of all
contexts.

One kernel panic issue has been reported[2] when running stress test on
dm-mpath's updating nr_requests and suspending queue, and the similar
issue should exist on almost all drivers which use quiesce/unquiesce.

[1] https://marc.info/?l=linux-block&m=150993988115872&w=2
[2] https://listman.redhat.com/archives/dm-devel/2021-September/msg00189.html

Signed-off-by: Ming Lei <ming.lei at redhat.com>
---
 block/blk-mq.c         | 20 +++++++++++++++++---
 include/linux/blkdev.h |  2 ++
 2 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 21bf4c3f0825..10f8a3d4e3a1 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -209,7 +209,12 @@ EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
  */
 void blk_mq_quiesce_queue_nowait(struct request_queue *q)
 {
-	blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->queue_lock, flags);
+	if (!q->quiesce_depth++)
+		blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q);
+	spin_unlock_irqrestore(&q->queue_lock, flags);
 }
 EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
 
@@ -250,10 +255,19 @@ EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
  */
 void blk_mq_unquiesce_queue(struct request_queue *q)
 {
-	blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
+	unsigned long flags;
+	bool run_queue = false;
+
+	spin_lock_irqsave(&q->queue_lock, flags);
+	if (q->quiesce_depth > 0 && !--q->quiesce_depth) {
+		blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
+		run_queue = true;
+	}
+	spin_unlock_irqrestore(&q->queue_lock, flags);
 
 	/* dispatch requests which are inserted during quiescing */
-	blk_mq_run_hw_queues(q, true);
+	if (run_queue)
+		blk_mq_run_hw_queues(q, true);
 }
 EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 0e960d74615e..74c60e2d61f9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -315,6 +315,8 @@ struct request_queue {
 	 */
 	struct mutex		mq_freeze_lock;
 
+	int			quiesce_depth;
+
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
 	struct bio_set		bio_split;
-- 
2.31.1