From 65fac0d54f374625b43a9d6ad1f2c212bd41f518 Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 26 Jul 2022 20:22:24 +0800 Subject: blk-mq: fix io hung due to missing commit_rqs Currently, in virtio_scsi, if 'bd->last' is not set to true while dispatching request, such io will stay in driver's queue, and driver will wait for block layer to dispatch more rqs. However, if block layer failed to dispatch more rq, it should trigger commit_rqs to inform driver. There is a problem in blk_mq_try_issue_list_directly() that commit_rqs won't be called: // assume that queue_depth is set to 1, list contains two rq blk_mq_try_issue_list_directly blk_mq_request_issue_directly // dispatch first rq // last is false __blk_mq_try_issue_directly blk_mq_get_dispatch_budget // succeed to get first budget __blk_mq_issue_directly scsi_queue_rq cmd->flags |= SCMD_LAST virtscsi_queuecommand kick = (sc->flags & SCMD_LAST) != 0 // kick is false, first rq won't issue to disk queued++ blk_mq_request_issue_directly // dispatch second rq __blk_mq_try_issue_directly blk_mq_get_dispatch_budget // failed to get second budget ret == BLK_STS_RESOURCE blk_mq_request_bypass_insert // errors is still 0 if (!list_empty(list) || errors && ...) // won't pass, commit_rqs won't be called In this situation, first rq relied on second rq to dispatch, while second rq relied on first rq to complete, thus they will both hung. Fix the problem by also treat 'BLK_STS_*RESOURCE' as 'errors' since it means that request is not queued successfully. Same problem exists in blk_mq_dispatch_rq_list(), 'BLK_STS_*RESOURCE' can't be treated as 'errors' here, fix the problem by calling commit_rqs if queue_rq return 'BLK_STS_*RESOURCE'. Fixes: d666ba98f849 ("blk-mq: add mq_ops->commit_rqs()") Signed-off-by: Yu Kuai Reviewed-by: Ming Lei Link: https://lore.kernel.org/r/20220726122224.1790882-1-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe --- block/blk-mq.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq.c b/block/blk-mq.c index 3c1e6b6d991d..c96c8c4f751b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1931,7 +1931,8 @@ out: /* If we didn't flush the entire list, we could have told the driver * there was more coming, but that turned out to be a lie. */ - if ((!list_empty(list) || errors) && q->mq_ops->commit_rqs && queued) + if ((!list_empty(list) || errors || needs_resource || + ret == BLK_STS_DEV_RESOURCE) && q->mq_ops->commit_rqs && queued) q->mq_ops->commit_rqs(hctx); /* * Any items that need requeuing? Stuff them into hctx->dispatch, @@ -2660,6 +2661,7 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, list_del_init(&rq->queuelist); ret = blk_mq_request_issue_directly(rq, list_empty(list)); if (ret != BLK_STS_OK) { + errors++; if (ret == BLK_STS_RESOURCE || ret == BLK_STS_DEV_RESOURCE) { blk_mq_request_bypass_insert(rq, false, @@ -2667,7 +2669,6 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, break; } blk_mq_end_request(rq, ret); - errors++; } else queued++; } -- cgit v1.2.3-58-ga151