From 94d7dea448fae6cbb83395323c1d2fd7f19dc388 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 26 Oct 2016 16:57:15 +0800 Subject: [PATCH] block: flush: fix IO hang in case of flood fua req This patch fixes one issue reported by Kent, which can be triggered in bcachefs over sata disk. Actually it is a generic issue in block flush vs. blk-tag. Cc: Christoph Hellwig Reported-by: Kent Overstreet Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-flush.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/block/blk-flush.c b/block/blk-flush.c index 6a14b68b9135..3c882cbc7541 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -342,6 +342,34 @@ static void flush_data_end_io(struct request *rq, int error) struct request_queue *q = rq->q; struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL); + /* + * Updating q->in_flight[] here for making this tag usable + * early. Because in blk_queue_start_tag(), + * q->in_flight[BLK_RW_ASYNC] is used to limit async I/O and + * reserve tags for sync I/O. + * + * More importantly this way can avoid the following I/O + * deadlock: + * + * - suppose there are 40 fua requests comming to flush queue + * and queue depth is 31 + * - 30 rqs are scheduled then blk_queue_start_tag() can't alloc + * tag for async I/O any more + * - all the 30 rqs are completed before FLUSH_PENDING_TIMEOUT + * and flush_data_end_io() is called + * - the other rqs still can't go ahead if not updating + * q->in_flight[BLK_RW_ASYNC] here, meantime these rqs + * are held in flush data queue and make no progress of + * handling post flush rq + * - only after the post flush rq is handled, all these rqs + * can be completed + */ + + elv_completed_request(q, rq); + + /* for avoiding double accounting */ + rq->cmd_flags &= ~REQ_STARTED; + /* * After populating an empty queue, kick it to avoid stall. Read * the comment in flush_end_io(). -- 2.30.2