diff options
| author | Ming Lei <ming.lei@redhat.com> | 2021-10-14 11:17:10 +0300 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2021-10-20 03:27:58 +0300 |
| commit | e70feb8b3e6886c525c88943b5f1508d02f5a683 (patch) | |
| tree | b0bb0d783c033f32f32145e993a163477b651f4f | |
| parent | 1d35d519d8bf224ccdb43f9a235b8bda2d6d453c (diff) | |
| download | linux-e70feb8b3e6886c525c88943b5f1508d02f5a683.tar.xz | |
blk-mq: support concurrent queue quiesce/unquiesce
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.html
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20211014081710.1871747-7-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
| -rw-r--r-- | block/blk-mq.c | 22 | ||||
| -rw-r--r-- | 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 bf5936d72de8..31d9e612d236 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -241,7 +241,12 @@ 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); @@ -282,10 +287,21 @@ 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 f13091d3d476..2b22fa36e568 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; |