blk-mq: support concurrent queue quiesce/unquiesce

mainline inclusion
from mainline-v5.16
commit e70feb8b
category: bugfix
bugzilla: 182378 https://gitee.com/openeuler/kernel/issues/I4DDEL

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=e70feb8b3e6886c525c88943b5f1508d02f5a683

---------------------------

blk_mq_quiesce_queue() has been used a bit wide now, so far we don't support
concurrent/nested quiesce. One biggest issue is that unquiesce can happen
unexpectedly in case that quiesce/unquiesce are run concurrently from
more than one context.

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.

Several kernel panic issue has been reported[1][2][3] when running stress
quiesce test. And this patch has been verified in these reports.

[1] https://lore.kernel.org/linux-block/9b21c797-e505-3821-4f5b-df7bf9380328@huawei.com/T/#m1fc52431fad7f33b1ffc3f12c4450e4238540787
[2] https://lore.kernel.org/linux-block/9b21c797-e505-3821-4f5b-df7bf9380328@huawei.com/T/#m10ad90afeb9c8cc318334190a7c24c8b5c5e0722
[3] https://listman.redhat.com/archives/dm-devel/2021-September/msg00189.htmlSigned-off-by: NMing Lei <ming.lei@redhat.com>
Reviewed-by: NChristoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211014081710.1871747-7-ming.lei@redhat.comSigned-off-by: NJens Axboe <axboe@kernel.dk>
Signed-off-by: NYu Kuai <yukuai3@huawei.com>
Reviewed-by: NJason Yan <yanaijie@huawei.com>
Signed-off-by: NChen Jun <chenjun102@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

block/blk-mq.c

@@ -206,7 +206,12 @@ 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);
 
@@ -247,10 +252,21 @@ 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 (WARN_ON_ONCE(q->quiesce_depth <= 0)) {
+		;
+	} else if (!--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);
 

include/linux/blkdev.h

@@ -571,6 +571,8 @@ 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;