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@xxxxxxxxxx/T/#m1fc52431fad7f33b1ffc3f12c4450e4238540787 [2] https://lore.kernel.org/linux-block/9b21c797-e505-3821-4f5b-df7bf9380328@xxxxxxxxxx/T/#m10ad90afeb9c8cc318334190a7c24c8b5c5e0722 [3] https://listman.redhat.com/archives/dm-devel/2021-September/msg00189.html Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx> --- block/blk-mq.c | 22 +++++++++++++++++++--- include/linux/blkdev.h | 2 ++ 2 files changed, 21 insertions(+), 3 deletions(-) diff --git a/block/blk-mq.c b/block/blk-mq.c index 68cccb2d1f8c..360e8eaee4dc 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 +255,21 @@ 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); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 17705c970d7e..52020fae665c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -314,6 +314,8 @@ 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
