From 7b17c2f7292ba1f3f98dae3f7077f9e569653276 Mon Sep 17 00:00:00 2001 From: Bart Van Assche Date: Fri, 28 Oct 2016 17:22:16 -0700 Subject: [PATCH] dm: Fix a race condition related to stopping and starting queues Ensure that all ongoing dm_mq_queue_rq() and dm_mq_requeue_request() calls have stopped before setting the "queue stopped" flag. This allows to remove the "queue stopped" test from dm_mq_queue_rq() and dm_mq_requeue_request(). This patch fixes a race condition because dm_mq_queue_rq() is called without holding the queue lock and hence BLK_MQ_S_STOPPED can be set at any time while dm_mq_queue_rq() is in progress. This patch prevents that the following hang occurs sporadically when using dm-mq: INFO: task systemd-udevd:10111 blocked for more than 480 seconds. Call Trace: [] schedule+0x37/0x90 [] schedule_timeout+0x27f/0x470 [] io_schedule_timeout+0x9f/0x110 [] bit_wait_io+0x16/0x60 [] __wait_on_bit_lock+0x49/0xa0 [] __lock_page+0xb9/0xc0 [] truncate_inode_pages_range+0x3e0/0x760 [] truncate_inode_pages+0x10/0x20 [] kill_bdev+0x30/0x40 [] __blkdev_put+0x71/0x360 [] blkdev_put+0x49/0x170 [] blkdev_close+0x20/0x30 [] __fput+0xe8/0x1f0 [] ____fput+0x9/0x10 [] task_work_run+0x83/0xb0 [] do_exit+0x3ee/0xc40 [] do_group_exit+0x4b/0xc0 [] get_signal+0x2ca/0x940 [] do_signal+0x23/0x660 [] exit_to_usermode_loop+0x73/0xb0 [] syscall_return_slowpath+0xb0/0xc0 [] entry_SYSCALL_64_fastpath+0xa6/0xa8 Signed-off-by: Bart Van Assche Acked-by: Mike Snitzer Reviewed-by: Hannes Reinecke Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/md/dm-rq.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 09c958b6f038..8b92e066bb69 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -102,7 +102,7 @@ static void dm_mq_stop_queue(struct request_queue *q) if (blk_mq_queue_stopped(q)) return; - blk_mq_stop_hw_queues(q); + blk_mq_quiesce_queue(q); } void dm_stop_queue(struct request_queue *q) @@ -880,17 +880,6 @@ static int dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx, dm_put_live_table(md, srcu_idx); } - /* - * On suspend dm_stop_queue() handles stopping the blk-mq - * request_queue BUT: even though the hw_queues are marked - * BLK_MQ_S_STOPPED at that point there is still a race that - * is allowing block/blk-mq.c to call ->queue_rq against a - * hctx that it really shouldn't. The following check guards - * against this rarity (albeit _not_ race-free). - */ - if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state))) - return BLK_MQ_RQ_QUEUE_BUSY; - if (ti->type->busy && ti->type->busy(ti)) return BLK_MQ_RQ_QUEUE_BUSY;