From 7520872c0cf4d3df6d74242c6edfb9e70a47df4d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 17 Feb 2017 11:40:44 -0700 Subject: [PATCH] block: don't defer flushes on blk-mq + scheduling For blk-mq with scheduling, we can potentially end up with ALL driver tags assigned and sitting on the flush queues. If we defer because of an inlfight data request, then we can deadlock if that data request doesn't already have a tag assigned. This fixes a deadlock with running the xfs/297 xfstest, where thousands of syncs can cause the drive queue to stall. Signed-off-by: Jens Axboe Reviewed-by: Omar Sandoval --- block/blk-flush.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/block/blk-flush.c b/block/blk-flush.c index 968162579234..0d5a9c1da1fc 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -297,8 +297,14 @@ static bool blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq) if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending)) return false; - /* C2 and C3 */ + /* C2 and C3 + * + * For blk-mq + scheduling, we can risk having all driver tags + * assigned to empty flushes, and we deadlock if we are expecting + * other requests to make progress. Don't defer for that case. + */ if (!list_empty(&fq->flush_data_in_flight) && + !(q->mq_ops && q->elevator) && time_before(jiffies, fq->flush_pending_since + FLUSH_PENDING_TIMEOUT)) return false;